Merge tag 'pm-4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm

Pull power management updates from Rafael Wysocki:
 "These include a significant update of the generic power domains
  (genpd) and Operating Performance Points (OPP) frameworks, mostly
  related to the introduction of power domain performance levels,
  cpufreq updates (new driver for Qualcomm Kryo processors, updates of
  the existing drivers, some core fixes, schedutil governor
  improvements), PCI power management fixes, ACPI workaround for
  EC-based wakeup events handling on resume from suspend-to-idle, and
  major updates of the turbostat and pm-graph utilities.

  Specifics:

   - Introduce power domain performance levels into the the generic
     power domains (genpd) and Operating Performance Points (OPP)
     frameworks (Viresh Kumar, Rajendra Nayak, Dan Carpenter).

   - Fix two issues in the runtime PM framework related to the
     initialization and removal of devices using device links (Ulf
     Hansson).

   - Clean up the initialization of drivers for devices in PM domains
     (Ulf Hansson, Geert Uytterhoeven).

   - Fix a cpufreq core issue related to the policy sysfs interface
     causing CPU online to fail for CPUs sharing one cpufreq policy in
     some situations (Tao Wang).

   - Make it possible to use platform-specific suspend/resume hooks in
     the cpufreq-dt driver and make the Armada 37xx DVFS use that
     feature (Viresh Kumar, Miquel Raynal).

   - Optimize policy transition notifications in cpufreq (Viresh Kumar).

   - Improve the iowait boost mechanism in the schedutil cpufreq
     governor (Patrick Bellasi).

   - Improve the handling of deferred frequency updates in the schedutil
     cpufreq governor (Joel Fernandes, Dietmar Eggemann, Rafael Wysocki,
     Viresh Kumar).

   - Add a new cpufreq driver for Qualcomm Kryo (Ilia Lin).

   - Fix and clean up some cpufreq drivers (Colin Ian King, Dmitry
     Osipenko, Doug Smythies, Luc Van Oostenryck, Simon Horman, Viresh
     Kumar).

   - Fix the handling of PCI devices with the DPM_SMART_SUSPEND flag set
     and update stale comments in the PCI core PM code (Rafael Wysocki).

   - Work around an issue related to the handling of EC-based wakeup
     events in the ACPI PM core during resume from suspend-to-idle if
     the EC has been put into the low-power mode (Rafael Wysocki).

   - Improve the handling of wakeup source objects in the PM core (Doug
     Berger, Mahendran Ganesh, Rafael Wysocki).

   - Update the driver core to prevent deferred probe from breaking
     suspend/resume ordering (Feng Kan).

   - Clean up the PM core somewhat (Bjorn Helgaas, Ulf Hansson, Rafael
     Wysocki).

   - Make the core suspend/resume code and cpufreq support the RT patch
     (Sebastian Andrzej Siewior, Thomas Gleixner).

   - Consolidate the PM QoS handling in cpuidle governors (Rafael
     Wysocki).

   - Fix a possible crash in the hibernation core (Tetsuo Handa).

   - Update the rockchip-io Adaptive Voltage Scaling (AVS) driver (David
     Wu).

   - Update the turbostat utility (fixes, cleanups, new CPU IDs, new
     command line options, built-in "Low Power Idle" counters support,
     new POLL and POLL% columns) and add an entry for it to MAINTAINERS
     (Len Brown, Artem Bityutskiy, Chen Yu, Laura Abbott, Matt Turner,
     Prarit Bhargava, Srinivas Pandruvada).

   - Update the pm-graph to version 5.1 (Todd Brandt).

   - Update the intel_pstate_tracer utility (Doug Smythies)"

* tag 'pm-4.18-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/rafael/linux-pm: (128 commits)
  tools/power turbostat: update version number
  tools/power turbostat: Add Node in output
  tools/power turbostat: add node information into turbostat calculations
  tools/power turbostat: remove num_ from cpu_topology struct
  tools/power turbostat: rename num_cores_per_pkg to num_cores_per_node
  tools/power turbostat: track thread ID in cpu_topology
  tools/power turbostat: Calculate additional node information for a package
  tools/power turbostat: Fix node and siblings lookup data
  tools/power turbostat: set max_num_cpus equal to the cpumask length
  tools/power turbostat: if --num_iterations, print for specific number of iterations
  tools/power turbostat: Add Cannon Lake support
  tools/power turbostat: delete duplicate #defines
  x86: msr-index.h: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: Correct SNB_C1/C3_AUTO_UNDEMOTE defines
  tools/power turbostat: add POLL and POLL% column
  tools/power turbostat: Fix --hide Pk%pc10
  tools/power turbostat: Build-in "Low Power Idle" counters support
  tools/power turbostat: Don't make man pages executable
  tools/power turbostat: remove blank lines
  tools/power turbostat: a small C-states dump readability immprovement
  ...

46 files changed, 1233 insertions, 599 deletions

diff --git a/drivers/acpi/acpica/evgpe.c b/drivers/acpi/acpica/evgpe.c
index abbd59063906..e10fec99a182 100644
--- a/drivers/acpi/acpica/evgpe.c
+++ b/drivers/acpi/acpica/evgpe.c
@@ -634,6 +634,12 @@ acpi_ev_detect_gpe(struct acpi_namespace_node *gpe_device,
 
 	flags = acpi_os_acquire_lock(acpi_gbl_gpe_lock);
 
+	if (!gpe_event_info) {
+		gpe_event_info = acpi_ev_get_gpe_event_info(gpe_device, gpe_number);
+		if (!gpe_event_info)
+			goto error_exit;
+	}
+
 	/* Get the info block for the entire GPE register */
 
 	gpe_register_info = gpe_event_info->register_info;
diff --git a/drivers/acpi/acpica/evxfgpe.c b/drivers/acpi/acpica/evxfgpe.c
index c80e3bdf4805..b2d5f66cc1b0 100644
--- a/drivers/acpi/acpica/evxfgpe.c
+++ b/drivers/acpi/acpica/evxfgpe.c
@@ -639,6 +639,28 @@ ACPI_EXPORT_SYMBOL(acpi_get_gpe_status)
 
 /*******************************************************************************
  *
+ * FUNCTION:    acpi_gispatch_gpe
+ *
+ * PARAMETERS:  gpe_device          - Parent GPE Device. NULL for GPE0/GPE1
+ *              gpe_number          - GPE level within the GPE block
+ *
+ * RETURN:      None
+ *
+ * DESCRIPTION: Detect and dispatch a General Purpose Event to either a function
+ *              (e.g. EC) or method (e.g. _Lxx/_Exx) handler.
+ *
+ ******************************************************************************/
+void acpi_dispatch_gpe(acpi_handle gpe_device, u32 gpe_number)
+{
+	ACPI_FUNCTION_TRACE(acpi_dispatch_gpe);
+
+	acpi_ev_detect_gpe(gpe_device, NULL, gpe_number);
+}
+
+ACPI_EXPORT_SYMBOL(acpi_dispatch_gpe)
+
+/*******************************************************************************
+ *
  * FUNCTION:    acpi_finish_gpe
  *
  * PARAMETERS:  gpe_device          - Namespace node for the GPE Block
diff --git a/drivers/acpi/device_pm.c b/drivers/acpi/device_pm.c
index 3d96e4da2d98..a7c2673ffd36 100644
--- a/drivers/acpi/device_pm.c
+++ b/drivers/acpi/device_pm.c
@@ -1257,10 +1257,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	struct acpi_device *adev = ACPI_COMPANION(dev);
 
 	if (!adev)
-		return -ENODEV;
-
-	if (dev->pm_domain)
-		return -EEXIST;
+		return 0;
 
 	/*
 	 * Only attach the power domain to the first device if the
@@ -1268,7 +1265,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	 * management twice.
 	 */
 	if (!acpi_device_is_first_physical_node(adev, dev))
-		return -EBUSY;
+		return 0;
 
 	acpi_add_pm_notifier(adev, dev, acpi_pm_notify_work_func);
 	dev_pm_domain_set(dev, &acpi_general_pm_domain);
@@ -1278,7 +1275,7 @@ int acpi_dev_pm_attach(struct device *dev, bool power_on)
 	}
 
 	dev->pm_domain->detach = acpi_dev_pm_detach;
-	return 0;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(acpi_dev_pm_attach);
 #endif /* CONFIG_PM */
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
index 30a572956557..bb94cf0731fe 100644
--- a/drivers/acpi/ec.c
+++ b/drivers/acpi/ec.c
@@ -1034,6 +1034,12 @@ void acpi_ec_unblock_transactions(void)
 		acpi_ec_start(first_ec, true);
 }
 
+void acpi_ec_dispatch_gpe(void)
+{
+	if (first_ec)
+		acpi_dispatch_gpe(NULL, first_ec->gpe);
+}
+
 /* --------------------------------------------------------------------------
                                 Event Management
    -------------------------------------------------------------------------- */
diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
index 1d0a501bc7f0..530a3f675490 100644
--- a/drivers/acpi/internal.h
+++ b/drivers/acpi/internal.h
@@ -188,6 +188,7 @@ int acpi_ec_ecdt_probe(void);
 int acpi_ec_dsdt_probe(void);
 void acpi_ec_block_transactions(void);
 void acpi_ec_unblock_transactions(void);
+void acpi_ec_dispatch_gpe(void);
 int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
 			      acpi_handle handle, acpi_ec_query_func func,
 			      void *data);
diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c
index 974e58457697..5d0486f1cfcd 100644
--- a/drivers/acpi/sleep.c
+++ b/drivers/acpi/sleep.c
@@ -989,6 +989,13 @@ static void acpi_s2idle_wake(void)
 	    !irqd_is_wakeup_armed(irq_get_irq_data(acpi_sci_irq))) {
 		pm_system_cancel_wakeup();
 		s2idle_wakeup = true;
+		/*
+		 * On some platforms with the LPS0 _DSM device noirq resume
+		 * takes too much time for EC wakeup events to survive, so look
+		 * for them now.
+		 */
+		if (lps0_device_handle)
+			acpi_ec_dispatch_gpe();
 	}
 }
 
diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 3b0118786b43..0cf51d57e4ae 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -251,7 +251,7 @@ static int amba_probe(struct device *dev)
 			break;
 
 		ret = dev_pm_domain_attach(dev, true);
-		if (ret == -EPROBE_DEFER)
+		if (ret)
 			break;
 
 		ret = amba_get_enable_pclk(pcdev);
@@ -378,7 +378,7 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 	}
 
 	ret = dev_pm_domain_attach(&dev->dev, true);
-	if (ret == -EPROBE_DEFER) {
+	if (ret) {
 		iounmap(tmp);
 		goto err_release;
 	}
diff --git a/drivers/base/base.h b/drivers/base/base.h
index d800de650fa5..a75c3025fb78 100644
--- a/drivers/base/base.h
+++ b/drivers/base/base.h
@@ -161,3 +161,6 @@ extern void device_links_driver_cleanup(struct device *dev);
 extern void device_links_no_driver(struct device *dev);
 extern bool device_links_busy(struct device *dev);
 extern void device_links_unbind_consumers(struct device *dev);
+
+/* device pm support */
+void device_pm_move_to_tail(struct device *dev);
diff --git a/drivers/base/core.c b/drivers/base/core.c
index b610816eb887..ad7b50897bcc 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -145,6 +145,26 @@ static int device_reorder_to_tail(struct device *dev, void *not_used)
 }
 
 /**
+ * device_pm_move_to_tail - Move set of devices to the end of device lists
+ * @dev: Device to move
+ *
+ * This is a device_reorder_to_tail() wrapper taking the requisite locks.
+ *
+ * It moves the @dev along with all of its children and all of its consumers
+ * to the ends of the device_kset and dpm_list, recursively.
+ */
+void device_pm_move_to_tail(struct device *dev)
+{
+	int idx;
+
+	idx = device_links_read_lock();
+	device_pm_lock();
+	device_reorder_to_tail(dev, NULL);
+	device_pm_unlock();
+	device_links_read_unlock(idx);
+}
+
+/**
  * device_link_add - Create a link between two devices.
  * @consumer: Consumer end of the link.
  * @supplier: Supplier end of the link.
diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index c9f54089429b..a41c91bfac0e 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -122,9 +122,7 @@ static void deferred_probe_work_func(struct work_struct *work)
 		 * the list is a good order for suspend but deferred
 		 * probe makes that very unsafe.
 		 */
-		device_pm_lock();
-		device_pm_move_last(dev);
-		device_pm_unlock();
+		device_pm_move_to_tail(dev);
 
 		dev_dbg(dev, "Retrying from deferred list\n");
 		if (initcall_debug && !initcalls_done)
@@ -582,7 +580,7 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
 	pr_debug("bus: '%s': %s: matched device %s with driver %s\n",
 		 drv->bus->name, __func__, dev_name(dev), drv->name);
 
-	pm_runtime_get_suppliers(dev);
+	pm_runtime_resume_suppliers(dev);
 	if (dev->parent)
 		pm_runtime_get_sync(dev->parent);
 
@@ -593,7 +591,6 @@ int driver_probe_device(struct device_driver *drv, struct device *dev)
 	if (dev->parent)
 		pm_runtime_put(dev->parent);
 
-	pm_runtime_put_suppliers(dev);
 	return ret;
 }
 
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index c0ff1e73a634..dff82a3c2caa 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -572,17 +572,16 @@ static int platform_drv_probe(struct device *_dev)
 		return ret;
 
 	ret = dev_pm_domain_attach(_dev, true);
-	if (ret != -EPROBE_DEFER) {
-		if (drv->probe) {
-			ret = drv->probe(dev);
-			if (ret)
-				dev_pm_domain_detach(_dev, true);
-		} else {
-			/* don't fail if just dev_pm_domain_attach failed */
-			ret = 0;
-		}
+	if (ret)
+		goto out;
+
+	if (drv->probe) {
+		ret = drv->probe(dev);
+		if (ret)
+			dev_pm_domain_detach(_dev, true);
 	}
 
+out:
 	if (drv->prevent_deferred_probe && ret == -EPROBE_DEFER) {
 		dev_warn(_dev, "probe deferral not supported\n");
 		ret = -ENXIO;
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index f6a9ad52cbbf..7ae62b6355b8 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -98,17 +98,21 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
  * Callers must ensure proper synchronization of this function with power
  * management callbacks.
  *
- * Returns 0 on successfully attached PM domain or negative error code.
+ * Returns 0 on successfully attached PM domain, or when it is found that the
+ * device doesn't need a PM domain, else a negative error code.
  */
 int dev_pm_domain_attach(struct device *dev, bool power_on)
 {
 	int ret;
 
+	if (dev->pm_domain)
+		return 0;
+
 	ret = acpi_dev_pm_attach(dev, power_on);
-	if (ret)
+	if (!ret)
 		ret = genpd_dev_pm_attach(dev);
 
-	return ret;
+	return ret < 0 ? ret : 0;
 }
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
 
diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c
index 1ea0e2502e8e..6f403d6fccb2 100644
--- a/drivers/base/power/domain.c
+++ b/drivers/base/power/domain.c
@@ -10,6 +10,7 @@
 #include <linux/kernel.h>
 #include <linux/io.h>
 #include <linux/platform_device.h>
+#include <linux/pm_opp.h>
 #include <linux/pm_runtime.h>
 #include <linux/pm_domain.h>
 #include <linux/pm_qos.h>
@@ -1315,7 +1316,6 @@ EXPORT_SYMBOL_GPL(pm_genpd_syscore_poweron);
 #endif /* CONFIG_PM_SLEEP */
 
 static struct generic_pm_domain_data *genpd_alloc_dev_data(struct device *dev,
-					struct generic_pm_domain *genpd,
 					struct gpd_timing_data *td)
 {
 	struct generic_pm_domain_data *gpd_data;
@@ -1377,24 +1377,19 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 			    struct gpd_timing_data *td)
 {
 	struct generic_pm_domain_data *gpd_data;
-	int ret = 0;
+	int ret;
 
 	dev_dbg(dev, "%s()\n", __func__);
 
 	if (IS_ERR_OR_NULL(genpd) || IS_ERR_OR_NULL(dev))
 		return -EINVAL;
 
-	gpd_data = genpd_alloc_dev_data(dev, genpd, td);
+	gpd_data = genpd_alloc_dev_data(dev, td);
 	if (IS_ERR(gpd_data))
 		return PTR_ERR(gpd_data);
 
 	genpd_lock(genpd);
 
-	if (genpd->prepared_count > 0) {
-		ret = -EAGAIN;
-		goto out;
-	}
-
 	ret = genpd->attach_dev ? genpd->attach_dev(genpd, dev) : 0;
 	if (ret)
 		goto out;
@@ -1418,23 +1413,21 @@ static int genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
 }
 
 /**
- * __pm_genpd_add_device - Add a device to an I/O PM domain.
+ * pm_genpd_add_device - Add a device to an I/O PM domain.
  * @genpd: PM domain to add the device to.
  * @dev: Device to be added.
- * @td: Set of PM QoS timing parameters to attach to the device.
  */
-int __pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev,
-			  struct gpd_timing_data *td)
+int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev)
 {
 	int ret;
 
 	mutex_lock(&gpd_list_lock);
-	ret = genpd_add_device(genpd, dev, td);
+	ret = genpd_add_device(genpd, dev, NULL);
 	mutex_unlock(&gpd_list_lock);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(__pm_genpd_add_device);
+EXPORT_SYMBOL_GPL(pm_genpd_add_device);
 
 static int genpd_remove_device(struct generic_pm_domain *genpd,
 			       struct device *dev)
@@ -1481,13 +1474,13 @@ static int genpd_remove_device(struct generic_pm_domain *genpd,
 
 /**
  * pm_genpd_remove_device - Remove a device from an I/O PM domain.
- * @genpd: PM domain to remove the device from.
  * @dev: Device to be removed.
  */
-int pm_genpd_remove_device(struct generic_pm_domain *genpd,
-			   struct device *dev)
+int pm_genpd_remove_device(struct device *dev)
 {
-	if (!genpd || genpd != genpd_lookup_dev(dev))
+	struct generic_pm_domain *genpd = genpd_lookup_dev(dev);
+
+	if (!genpd)
 		return -EINVAL;
 
 	return genpd_remove_device(genpd, dev);
@@ -1696,6 +1689,9 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 			return ret;
 	}
 
+	device_initialize(&genpd->dev);
+	dev_set_name(&genpd->dev, "%s", genpd->name);
+
 	mutex_lock(&gpd_list_lock);
 	list_add(&genpd->gpd_list_node, &gpd_list);
 	mutex_unlock(&gpd_list_lock);
@@ -1892,14 +1888,33 @@ int of_genpd_add_provider_simple(struct device_node *np,
 
 	mutex_lock(&gpd_list_lock);
 
-	if (genpd_present(genpd)) {
-		ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
-		if (!ret) {
-			genpd->provider = &np->fwnode;
-			genpd->has_provider = true;
+	if (!genpd_present(genpd))
+		goto unlock;
+
+	genpd->dev.of_node = np;
+
+	/* Parse genpd OPP table */
+	if (genpd->set_performance_state) {
+		ret = dev_pm_opp_of_add_table(&genpd->dev);
+		if (ret) {
+			dev_err(&genpd->dev, "Failed to add OPP table: %d\n",
+				ret);
+			goto unlock;
 		}
 	}
 
+	ret = genpd_add_provider(np, genpd_xlate_simple, genpd);
+	if (ret) {
+		if (genpd->set_performance_state)
+			dev_pm_opp_of_remove_table(&genpd->dev);
+
+		goto unlock;
+	}
+
+	genpd->provider = &np->fwnode;
+	genpd->has_provider = true;
+
+unlock:
 	mutex_unlock(&gpd_list_lock);
 
 	return ret;
@@ -1914,6 +1929,7 @@ EXPORT_SYMBOL_GPL(of_genpd_add_provider_simple);
 int of_genpd_add_provider_onecell(struct device_node *np,
 				  struct genpd_onecell_data *data)
 {
+	struct generic_pm_domain *genpd;
 	unsigned int i;
 	int ret = -EINVAL;
 
@@ -1926,13 +1942,27 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 		data->xlate = genpd_xlate_onecell;
 
 	for (i = 0; i < data->num_domains; i++) {
-		if (!data->domains[i])
+		genpd = data->domains[i];
+
+		if (!genpd)
 			continue;
-		if (!genpd_present(data->domains[i]))
+		if (!genpd_present(genpd))
 			goto error;
 
-		data->domains[i]->provider = &np->fwnode;
-		data->domains[i]->has_provider = true;
+		genpd->dev.of_node = np;
+
+		/* Parse genpd OPP table */
+		if (genpd->set_performance_state) {
+			ret = dev_pm_opp_of_add_table_indexed(&genpd->dev, i);
+			if (ret) {
+				dev_err(&genpd->dev, "Failed to add OPP table for index %d: %d\n",
+					i, ret);
+				goto error;
+			}
+		}
+
+		genpd->provider = &np->fwnode;
+		genpd->has_provider = true;
 	}
 
 	ret = genpd_add_provider(np, data->xlate, data);
@@ -1945,10 +1975,16 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 
 error:
 	while (i--) {
-		if (!data->domains[i])
+		genpd = data->domains[i];
+
+		if (!genpd)
 			continue;
-		data->domains[i]->provider = NULL;
-		data->domains[i]->has_provider = false;
+
+		genpd->provider = NULL;
+		genpd->has_provider = false;
+
+		if (genpd->set_performance_state)
+			dev_pm_opp_of_remove_table(&genpd->dev);
 	}
 
 	mutex_unlock(&gpd_list_lock);
@@ -1975,10 +2011,17 @@ void of_genpd_del_provider(struct device_node *np)
 			 * provider, set the 'has_provider' to false
 			 * so that the PM domain can be safely removed.
 			 */
-			list_for_each_entry(gpd, &gpd_list, gpd_list_node)
-				if (gpd->provider == &np->fwnode)
+			list_for_each_entry(gpd, &gpd_list, gpd_list_node) {
+				if (gpd->provider == &np->fwnode) {
 					gpd->has_provider = false;
 
+					if (!gpd->set_performance_state)
+						continue;
+
+					dev_pm_opp_of_remove_table(&gpd->dev);
+				}
+			}
+
 			list_del(&cp->link);
 			of_node_put(cp->node);
 			kfree(cp);
@@ -2185,31 +2228,25 @@ static void genpd_dev_pm_sync(struct device *dev)
  * Parse device's OF node to find a PM domain specifier. If such is found,
  * attaches the device to retrieved pm_domain ops.
  *
- * Both generic and legacy Samsung-specific DT bindings are supported to keep
- * backwards compatibility with existing DTBs.
- *
- * Returns 0 on successfully attached PM domain or negative error code. Note
- * that if a power-domain exists for the device, but it cannot be found or
- * turned on, then return -EPROBE_DEFER to ensure that the device is not
- * probed and to re-try again later.
+ * Returns 1 on successfully attached PM domain, 0 when the device don't need a
+ * PM domain or a negative error code in case of failures. Note that if a
+ * power-domain exists for the device, but it cannot be found or turned on,
+ * then return -EPROBE_DEFER to ensure that the device is not probed and to
+ * re-try again later.
  */
 int genpd_dev_pm_attach(struct device *dev)
 {
 	struct of_phandle_args pd_args;
 	struct generic_pm_domain *pd;
-	unsigned int i;
 	int ret;
 
 	if (!dev->of_node)
-		return -ENODEV;
-
-	if (dev->pm_domain)
-		return -EEXIST;
+		return 0;
 
 	ret = of_parse_phandle_with_args(dev->of_node, "power-domains",
 					"#power-domain-cells", 0, &pd_args);
 	if (ret < 0)
-		return ret;
+		return 0;
 
 	mutex_lock(&gpd_list_lock);
 	pd = genpd_get_from_provider(&pd_args);
@@ -2223,21 +2260,14 @@ int genpd_dev_pm_attach(struct device *dev)
 
 	dev_dbg(dev, "adding to PM domain %s\n", pd->name);
 
-	for (i = 1; i < GENPD_RETRY_MAX_MS; i <<= 1) {
-		ret = genpd_add_device(pd, dev, NULL);
-		if (ret != -EAGAIN)
-			break;
-
-		mdelay(i);
-		cond_resched();
-	}
+	ret = genpd_add_device(pd, dev, NULL);
 	mutex_unlock(&gpd_list_lock);
 
 	if (ret < 0) {
 		if (ret != -EPROBE_DEFER)
 			dev_err(dev, "failed to add to PM domain %s: %d",
 				pd->name, ret);
-		goto out;
+		return ret;
 	}
 
 	dev->pm_domain->detach = genpd_dev_pm_detach;
@@ -2246,8 +2276,11 @@ int genpd_dev_pm_attach(struct device *dev)
 	genpd_lock(pd);
 	ret = genpd_power_on(pd, 0);
 	genpd_unlock(pd);
-out:
-	return ret ? -EPROBE_DEFER : 0;
+
+	if (ret)
+		genpd_remove_device(pd, dev);
+
+	return ret ? -EPROBE_DEFER : 1;
 }
 EXPORT_SYMBOL_GPL(genpd_dev_pm_attach);
 
@@ -2361,6 +2394,55 @@ int of_genpd_parse_idle_states(struct device_node *dn,
 }
 EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
 
+/**
+ * of_genpd_opp_to_performance_state- Gets performance state of device's
+ * power domain corresponding to a DT node's "required-opps" property.
+ *
+ * @dev: Device for which the performance-state needs to be found.
+ * @opp_node: DT node where the "required-opps" property is present. This can be
+ *	the device node itself (if it doesn't have an OPP table) or a node
+ *	within the OPP table of a device (if device has an OPP table).
+ * @state: Pointer to return performance state.
+ *
+ * Returns performance state corresponding to the "required-opps" property of
+ * a DT node. This calls platform specific genpd->opp_to_performance_state()
+ * callback to translate power domain OPP to performance state.
+ *
+ * Returns performance state on success and 0 on failure.
+ */
+unsigned int of_genpd_opp_to_performance_state(struct device *dev,
+					       struct device_node *opp_node)
+{
+	struct generic_pm_domain *genpd;
+	struct dev_pm_opp *opp;
+	int state = 0;
+
+	genpd = dev_to_genpd(dev);
+	if (IS_ERR(genpd))
+		return 0;
+
+	if (unlikely(!genpd->set_performance_state))
+		return 0;
+
+	genpd_lock(genpd);
+
+	opp = of_dev_pm_opp_find_required_opp(&genpd->dev, opp_node);
+	if (IS_ERR(opp)) {
+		dev_err(dev, "Failed to find required OPP: %ld\n",
+			PTR_ERR(opp));
+		goto unlock;
+	}
+
+	state = genpd->opp_to_performance_state(genpd, opp);
+	dev_pm_opp_put(opp);
+
+unlock:
+	genpd_unlock(genpd);
+
+	return state;
+}
+EXPORT_SYMBOL_GPL(of_genpd_opp_to_performance_state);
+
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
 
@@ -2628,6 +2710,19 @@ static int genpd_devices_show(struct seq_file *s, void *data)
 	return ret;
 }
 
+static int genpd_perf_state_show(struct seq_file *s, void *data)
+{
+	struct generic_pm_domain *genpd = s->private;
+
+	if (genpd_lock_interruptible(genpd))
+		return -ERESTARTSYS;
+
+	seq_printf(s, "%u\n", genpd->performance_state);
+
+	genpd_unlock(genpd);
+	return 0;
+}
+
 #define define_genpd_open_function(name) \
 static int genpd_##name##_open(struct inode *inode, struct file *file) \
 { \
@@ -2641,6 +2736,7 @@ define_genpd_open_function(idle_states);
 define_genpd_open_function(active_time);
 define_genpd_open_function(total_idle_time);
 define_genpd_open_function(devices);
+define_genpd_open_function(perf_state);
 
 #define define_genpd_debugfs_fops(name) \
 static const struct file_operations genpd_##name##_fops = { \
@@ -2657,6 +2753,7 @@ define_genpd_debugfs_fops(idle_states);
 define_genpd_debugfs_fops(active_time);
 define_genpd_debugfs_fops(total_idle_time);
 define_genpd_debugfs_fops(devices);
+define_genpd_debugfs_fops(perf_state);
 
 static int __init genpd_debug_init(void)
 {
@@ -2690,6 +2787,9 @@ static int __init genpd_debug_init(void)
 				d, genpd, &genpd_total_idle_time_fops);
 		debugfs_create_file("devices", 0444,
 				d, genpd, &genpd_devices_fops);
+		if (genpd->set_performance_state)
+			debugfs_create_file("perf_state", 0444,
+					    d, genpd, &genpd_perf_state_fops);
 	}
 
 	return 0;
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index e5e067091572..3f68e2919dc5 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -192,34 +192,31 @@ void device_pm_move_last(struct device *dev)
 	list_move_tail(&dev->power.entry, &dpm_list);
 }
 
-static ktime_t initcall_debug_start(struct device *dev)
+static ktime_t initcall_debug_start(struct device *dev, void *cb)
 {
-	ktime_t calltime = 0;
-
-	if (pm_print_times_enabled) {
-		pr_info("calling  %s+ @ %i, parent: %s\n",
-			dev_name(dev), task_pid_nr(current),
-			dev->parent ? dev_name(dev->parent) : "none");
-		calltime = ktime_get();
-	}
+	if (!pm_print_times_enabled)
+		return 0;
 
-	return calltime;
+	dev_info(dev, "calling %pF @ %i, parent: %s\n", cb,
+		 task_pid_nr(current),
+		 dev->parent ? dev_name(dev->parent) : "none");
+	return ktime_get();
 }
 
 static void initcall_debug_report(struct device *dev, ktime_t calltime,
-				  int error, pm_message_t state,
-				  const char *info)
+				  void *cb, int error)
 {
 	ktime_t rettime;
 	s64 nsecs;
 
+	if (!pm_print_times_enabled)
+		return;
+
 	rettime = ktime_get();
 	nsecs = (s64) ktime_to_ns(ktime_sub(rettime, calltime));
 
-	if (pm_print_times_enabled) {
-		pr_info("call %s+ returned %d after %Ld usecs\n", dev_name(dev),
-			error, (unsigned long long)nsecs >> 10);
-	}
+	dev_info(dev, "%pF returned %d after %Ld usecs\n", cb, error,
+		 (unsigned long long)nsecs >> 10);
 }
 
 /**
@@ -446,7 +443,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
 	if (!cb)
 		return 0;
 
-	calltime = initcall_debug_start(dev);
+	calltime = initcall_debug_start(dev, cb);
 
 	pm_dev_dbg(dev, state, info);
 	trace_device_pm_callback_start(dev, info, state.event);
@@ -454,7 +451,7 @@ static int dpm_run_callback(pm_callback_t cb, struct device *dev,
 	trace_device_pm_callback_end(dev, error);
 	suspend_report_result(cb, error);
 
-	initcall_debug_report(dev, calltime, error, state, info);
+	initcall_debug_report(dev, calltime, cb, error);
 
 	return error;
 }
@@ -1664,14 +1661,14 @@ static int legacy_suspend(struct device *dev, pm_message_t state,
 	int error;
 	ktime_t calltime;
 
-	calltime = initcall_debug_start(dev);
+	calltime = initcall_debug_start(dev, cb);
 
 	trace_device_pm_callback_start(dev, info, state.event);
 	error = cb(dev, state);
 	trace_device_pm_callback_end(dev, error);
 	suspend_report_result(cb, error);
 
-	initcall_debug_report(dev, calltime, error, state, info);
+	initcall_debug_report(dev, calltime, cb, error);
 
 	return error;
 }
diff --git a/drivers/base/power/power.h b/drivers/base/power/power.h
index 86e67e70b509..c511def48b48 100644
--- a/drivers/base/power/power.h
+++ b/drivers/base/power/power.h
@@ -56,14 +56,6 @@ static inline void device_wakeup_detach_irq(struct device *dev)
 {
 }
 
-static inline void device_wakeup_arm_wake_irqs(void)
-{
-}
-
-static inline void device_wakeup_disarm_wake_irqs(void)
-{
-}
-
 #endif /* CONFIG_PM_SLEEP */
 
 /*
@@ -95,28 +87,6 @@ static inline void pm_runtime_remove(struct device *dev) {}
 
 static inline int dpm_sysfs_add(struct device *dev) { return 0; }
 static inline void dpm_sysfs_remove(struct device *dev) {}
-static inline void rpm_sysfs_remove(struct device *dev) {}
-static inline int wakeup_sysfs_add(struct device *dev) { return 0; }
-static inline void wakeup_sysfs_remove(struct device *dev) {}
-static inline int pm_qos_sysfs_add(struct device *dev) { return 0; }
-static inline void pm_qos_sysfs_remove(struct device *dev) {}
-
-static inline void dev_pm_arm_wake_irq(struct wake_irq *wirq)
-{
-}
-
-static inline void dev_pm_disarm_wake_irq(struct wake_irq *wirq)
-{
-}
-
-static inline void dev_pm_enable_wake_irq_check(struct device *dev,
-						bool can_change_status)
-{
-}
-
-static inline void dev_pm_disable_wake_irq_check(struct device *dev)
-{
-}
 
 #endif
 
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 8bef3cb2424d..c6030f100c08 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1563,37 +1563,16 @@ void pm_runtime_clean_up_links(struct device *dev)
 }
 
 /**
- * pm_runtime_get_suppliers - Resume and reference-count supplier devices.
+ * pm_runtime_resume_suppliers - Resume supplier devices.
  * @dev: Consumer device.
  */
-void pm_runtime_get_suppliers(struct device *dev)
+void pm_runtime_resume_suppliers(struct device *dev)
 {
-	struct device_link *link;
-	int idx;
-
-	idx = device_links_read_lock();
-
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
-		if (link->flags & DL_FLAG_PM_RUNTIME)
-			pm_runtime_get_sync(link->supplier);
-
-	device_links_read_unlock(idx);
-}
-
-/**
- * pm_runtime_put_suppliers - Drop references to supplier devices.
- * @dev: Consumer device.
- */
-void pm_runtime_put_suppliers(struct device *dev)
-{
-	struct device_link *link;
 	int idx;
 
 	idx = device_links_read_lock();
 
-	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node)
-		if (link->flags & DL_FLAG_PM_RUNTIME)
-			pm_runtime_put(link->supplier);
+	rpm_get_suppliers(dev);
 
 	device_links_read_unlock(idx);
 }
@@ -1607,6 +1586,8 @@ void pm_runtime_new_link(struct device *dev)
 
 void pm_runtime_drop_link(struct device *dev)
 {
+	rpm_put_suppliers(dev);
+
 	spin_lock_irq(&dev->power.lock);
 	WARN_ON(dev->power.links_count == 0);
 	dev->power.links_count--;
diff --git a/drivers/base/power/wakeup.c b/drivers/base/power/wakeup.c
index ea01621ed769..5fa1898755a3 100644
--- a/drivers/base/power/wakeup.c
+++ b/drivers/base/power/wakeup.c
@@ -57,7 +57,7 @@ static void split_counters(unsigned int *cnt, unsigned int *inpr)
 /* A preserved old value of the events counter. */
 static unsigned int saved_count;
 
-static DEFINE_SPINLOCK(events_lock);
+static DEFINE_RAW_SPINLOCK(events_lock);
 
 static void pm_wakeup_timer_fn(struct timer_list *t);
 
@@ -183,11 +183,10 @@ void wakeup_source_add(struct wakeup_source *ws)
 	spin_lock_init(&ws->lock);
 	timer_setup(&ws->timer, pm_wakeup_timer_fn, 0);
 	ws->active = false;
-	ws->last_time = ktime_get();
 
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	list_add_rcu(&ws->entry, &wakeup_sources);
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_add);
 
@@ -202,9 +201,9 @@ void wakeup_source_remove(struct wakeup_source *ws)
 	if (WARN_ON(!ws))
 		return;
 
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	list_del_rcu(&ws->entry);
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 	synchronize_srcu(&wakeup_srcu);
 }
 EXPORT_SYMBOL_GPL(wakeup_source_remove);
@@ -843,7 +842,7 @@ bool pm_wakeup_pending(void)
 	unsigned long flags;
 	bool ret = false;
 
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	if (events_check_enabled) {
 		unsigned int cnt, inpr;
 
@@ -851,10 +850,10 @@ bool pm_wakeup_pending(void)
 		ret = (cnt != saved_count || inpr > 0);
 		events_check_enabled = !ret;
 	}
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 
 	if (ret) {
-		pr_info("PM: Wakeup pending, aborting suspend\n");
+		pr_debug("PM: Wakeup pending, aborting suspend\n");
 		pm_print_active_wakeup_sources();
 	}
 
@@ -940,13 +939,13 @@ bool pm_save_wakeup_count(unsigned int count)
 	unsigned long flags;
 
 	events_check_enabled = false;
-	spin_lock_irqsave(&events_lock, flags);
+	raw_spin_lock_irqsave(&events_lock, flags);
 	split_counters(&cnt, &inpr);
 	if (cnt == count && inpr == 0) {
 		saved_count = count;
 		events_check_enabled = true;
 	}
-	spin_unlock_irqrestore(&events_lock, flags);
+	raw_spin_unlock_irqrestore(&events_lock, flags);
 	return events_check_enabled;
 }
 
@@ -1029,32 +1028,75 @@ static int print_wakeup_source_stats(struct seq_file *m,
 	return 0;
 }
 
-/**
- * wakeup_sources_stats_show - Print wakeup sources statistics information.
- * @m: seq_file to print the statistics into.
- */
-static int wakeup_sources_stats_show(struct seq_file *m, void *unused)
+static void *wakeup_sources_stats_seq_start(struct seq_file *m,
+					loff_t *pos)
 {
 	struct wakeup_source *ws;
-	int srcuidx;
+	loff_t n = *pos;
+	int *srcuidx = m->private;
 
-	seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
-		"expire_count\tactive_since\ttotal_time\tmax_time\t"
-		"last_change\tprevent_suspend_time\n");
+	if (n == 0) {
+		seq_puts(m, "name\t\tactive_count\tevent_count\twakeup_count\t"
+			"expire_count\tactive_since\ttotal_time\tmax_time\t"
+			"last_change\tprevent_suspend_time\n");
+	}
 
-	srcuidx = srcu_read_lock(&wakeup_srcu);
-	list_for_each_entry_rcu(ws, &wakeup_sources, entry)
-		print_wakeup_source_stats(m, ws);
-	srcu_read_unlock(&wakeup_srcu, srcuidx);
+	*srcuidx = srcu_read_lock(&wakeup_srcu);
+	list_for_each_entry_rcu(ws, &wakeup_sources, entry) {
+		if (n-- <= 0)
+			return ws;
+	}
+
+	return NULL;
+}
+
+static void *wakeup_sources_stats_seq_next(struct seq_file *m,
+					void *v, loff_t *pos)
+{
+	struct wakeup_source *ws = v;
+	struct wakeup_source *next_ws = NULL;
 
-	print_wakeup_source_stats(m, &deleted_ws);
+	++(*pos);
+
+	list_for_each_entry_continue_rcu(ws, &wakeup_sources, entry) {
+		next_ws = ws;
+		break;
+	}
+
+	return next_ws;
+}
+
+static void wakeup_sources_stats_seq_stop(struct seq_file *m, void *v)
+{
+	int *srcuidx = m->private;
+
+	srcu_read_unlock(&wakeup_srcu, *srcuidx);
+}
+
+/**
+ * wakeup_sources_stats_seq_show - Print wakeup sources statistics information.
+ * @m: seq_file to print the statistics into.
+ * @v: wakeup_source of each iteration
+ */
+static int wakeup_sources_stats_seq_show(struct seq_file *m, void *v)
+{
+	struct wakeup_source *ws = v;
+
+	print_wakeup_source_stats(m, ws);
 
 	return 0;
 }
 
+static const struct seq_operations wakeup_sources_stats_seq_ops = {
+	.start = wakeup_sources_stats_seq_start,
+	.next  = wakeup_sources_stats_seq_next,
+	.stop  = wakeup_sources_stats_seq_stop,
+	.show  = wakeup_sources_stats_seq_show,
+};
+
 static int wakeup_sources_stats_open(struct inode *inode, struct file *file)
 {
-	return single_open(file, wakeup_sources_stats_show, NULL);
+	return seq_open_private(file, &wakeup_sources_stats_seq_ops, sizeof(int));
 }
 
 static const struct file_operations wakeup_sources_stats_fops = {
@@ -1062,7 +1104,7 @@ static const struct file_operations wakeup_sources_stats_fops = {
 	.open = wakeup_sources_stats_open,
 	.read = seq_read,
 	.llseek = seq_lseek,
-	.release = single_release,
+	.release = seq_release_private,
 };
 
 static int __init wakeup_sources_debugfs_init(void)
diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm
index 96b35b8b3606..c7ce928fbf1f 100644
--- a/drivers/cpufreq/Kconfig.arm
+++ b/drivers/cpufreq/Kconfig.arm
@@ -124,6 +124,17 @@ config ARM_OMAP2PLUS_CPUFREQ
 	depends on ARCH_OMAP2PLUS
 	default ARCH_OMAP2PLUS
 
+config ARM_QCOM_CPUFREQ_KRYO
+	bool "Qualcomm Kryo based CPUFreq"
+	depends on ARM64
+	depends on QCOM_QFPROM
+	depends on QCOM_SMEM
+	select PM_OPP
+	help
+	  This adds the CPUFreq driver for Qualcomm Kryo SoC based boards.
+
+	  If in doubt, say N.
+
 config ARM_S3C_CPUFREQ
 	bool
 	help
@@ -264,7 +275,7 @@ config ARM_TANGO_CPUFREQ
 	default y
 
 config ARM_TEGRA20_CPUFREQ
-	bool "Tegra20 CPUFreq support"
+	tristate "Tegra20 CPUFreq support"
 	depends on ARCH_TEGRA
 	default y
 	help
diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile
index 8d24ade3bd02..fb4a2ecac43b 100644
--- a/drivers/cpufreq/Makefile
+++ b/drivers/cpufreq/Makefile
@@ -65,6 +65,7 @@ obj-$(CONFIG_MACH_MVEBU_V7)		+= mvebu-cpufreq.o
 obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ)	+= omap-cpufreq.o
 obj-$(CONFIG_ARM_PXA2xx_CPUFREQ)	+= pxa2xx-cpufreq.o
 obj-$(CONFIG_PXA3xx)			+= pxa3xx-cpufreq.o
+obj-$(CONFIG_ARM_QCOM_CPUFREQ_KRYO)	+= qcom-cpufreq-kryo.o
 obj-$(CONFIG_ARM_S3C2410_CPUFREQ)	+= s3c2410-cpufreq.o
 obj-$(CONFIG_ARM_S3C2412_CPUFREQ)	+= s3c2412-cpufreq.o
 obj-$(CONFIG_ARM_S3C2416_CPUFREQ)	+= s3c2416-cpufreq.o
diff --git a/drivers/cpufreq/armada-37xx-cpufreq.c b/drivers/cpufreq/armada-37xx-cpufreq.c
index 72a2975499db..739da90ff3f6 100644
--- a/drivers/cpufreq/armada-37xx-cpufreq.c
+++ b/drivers/cpufreq/armada-37xx-cpufreq.c
@@ -23,6 +23,8 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
+#include "cpufreq-dt.h"
+
 /* Power management in North Bridge register set */
 #define ARMADA_37XX_NB_L0L1	0x18
 #define ARMADA_37XX_NB_L2L3	0x1C
@@ -56,6 +58,16 @@
  */
 #define LOAD_LEVEL_NR	4
 
+struct armada37xx_cpufreq_state {
+	struct regmap *regmap;
+	u32 nb_l0l1;
+	u32 nb_l2l3;
+	u32 nb_dyn_mod;
+	u32 nb_cpu_load;
+};
+
+static struct armada37xx_cpufreq_state *armada37xx_cpufreq_state;
+
 struct armada_37xx_dvfs {
 	u32 cpu_freq_max;
 	u8 divider[LOAD_LEVEL_NR];
@@ -136,7 +148,7 @@ static void __init armada37xx_cpufreq_dvfs_setup(struct regmap *base,
 	clk_set_parent(clk, parent);
 }
 
-static void __init armada37xx_cpufreq_disable_dvfs(struct regmap *base)
+static void armada37xx_cpufreq_disable_dvfs(struct regmap *base)
 {
 	unsigned int reg = ARMADA_37XX_NB_DYN_MOD,
 		mask = ARMADA_37XX_NB_DFS_EN;
@@ -162,10 +174,47 @@ static void __init armada37xx_cpufreq_enable_dvfs(struct regmap *base)
 	regmap_update_bits(base, reg, mask, mask);
 }
 
+static int armada37xx_cpufreq_suspend(struct cpufreq_policy *policy)
+{
+	struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+	regmap_read(state->regmap, ARMADA_37XX_NB_L0L1, &state->nb_l0l1);
+	regmap_read(state->regmap, ARMADA_37XX_NB_L2L3, &state->nb_l2l3);
+	regmap_read(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+		    &state->nb_cpu_load);
+	regmap_read(state->regmap, ARMADA_37XX_NB_DYN_MOD, &state->nb_dyn_mod);
+
+	return 0;
+}
+
+static int armada37xx_cpufreq_resume(struct cpufreq_policy *policy)
+{
+	struct armada37xx_cpufreq_state *state = armada37xx_cpufreq_state;
+
+	/* Ensure DVFS is disabled otherwise the following registers are RO */
+	armada37xx_cpufreq_disable_dvfs(state->regmap);
+
+	regmap_write(state->regmap, ARMADA_37XX_NB_L0L1, state->nb_l0l1);
+	regmap_write(state->regmap, ARMADA_37XX_NB_L2L3, state->nb_l2l3);
+	regmap_write(state->regmap, ARMADA_37XX_NB_CPU_LOAD,
+		     state->nb_cpu_load);
+
+	/*
+	 * NB_DYN_MOD register is the one that actually enable back DVFS if it
+	 * was enabled before the suspend operation. This must be done last
+	 * otherwise other registers are not writable.
+	 */
+	regmap_write(state->regmap, ARMADA_37XX_NB_DYN_MOD, state->nb_dyn_mod);
+
+	return 0;
+}
+
 static int __init armada37xx_cpufreq_driver_init(void)
 {
+	struct cpufreq_dt_platform_data pdata;
 	struct armada_37xx_dvfs *dvfs;
 	struct platform_device *pdev;
+	unsigned long freq;
 	unsigned int cur_frequency;
 	struct regmap *nb_pm_base;
 	struct device *cpu_dev;
@@ -207,33 +256,58 @@ static int __init armada37xx_cpufreq_driver_init(void)
 	}
 
 	dvfs = armada_37xx_cpu_freq_info_get(cur_frequency);
-	if (!dvfs)
+	if (!dvfs) {
+		clk_put(clk);
 		return -EINVAL;
+	}
+
+	armada37xx_cpufreq_state = kmalloc(sizeof(*armada37xx_cpufreq_state),
+					   GFP_KERNEL);
+	if (!armada37xx_cpufreq_state) {
+		clk_put(clk);
+		return -ENOMEM;
+	}
+
+	armada37xx_cpufreq_state->regmap = nb_pm_base;
 
 	armada37xx_cpufreq_dvfs_setup(nb_pm_base, clk, dvfs->divider);
 	clk_put(clk);
 
 	for (load_lvl = ARMADA_37XX_DVFS_LOAD_0; load_lvl < LOAD_LEVEL_NR;
 	     load_lvl++) {
-		unsigned long freq = cur_frequency / dvfs->divider[load_lvl];
+		freq = cur_frequency / dvfs->divider[load_lvl];
 
 		ret = dev_pm_opp_add(cpu_dev, freq, 0);
-		if (ret) {
-			/* clean-up the already added opp before leaving */
-			while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
-				freq = cur_frequency / dvfs->divider[load_lvl];
-				dev_pm_opp_remove(cpu_dev, freq);
-			}
-			return ret;
-		}
+		if (ret)
+			goto remove_opp;
 	}
 
 	/* Now that everything is setup, enable the DVFS at hardware level */
 	armada37xx_cpufreq_enable_dvfs(nb_pm_base);
 
-	pdev = platform_device_register_simple("cpufreq-dt", -1, NULL, 0);
+	pdata.suspend = armada37xx_cpufreq_suspend;
+	pdata.resume = armada37xx_cpufreq_resume;
+
+	pdev = platform_device_register_data(NULL, "cpufreq-dt", -1, &pdata,
+					     sizeof(pdata));
+	ret = PTR_ERR_OR_ZERO(pdev);
+	if (ret)
+		goto disable_dvfs;
+
+	return 0;
+
+disable_dvfs:
+	armada37xx_cpufreq_disable_dvfs(nb_pm_base);
+remove_opp:
+	/* clean-up the already added opp before leaving */
+	while (load_lvl-- > ARMADA_37XX_DVFS_LOAD_0) {
+		freq = cur_frequency / dvfs->divider[load_lvl];
+		dev_pm_opp_remove(cpu_dev, freq);
+	}
+
+	kfree(armada37xx_cpufreq_state);
 
-	return PTR_ERR_OR_ZERO(pdev);
+	return ret;
 }
 /* late_initcall, to guarantee the driver is loaded after A37xx clock driver */
 late_initcall(armada37xx_cpufreq_driver_init);
diff --git a/drivers/cpufreq/cpufreq-dt-platdev.c b/drivers/cpufreq/cpufreq-dt-platdev.c
index 3b585e4bfac5..fe14c57de6ca 100644
--- a/drivers/cpufreq/cpufreq-dt-platdev.c
+++ b/drivers/cpufreq/cpufreq-dt-platdev.c
@@ -66,8 +66,6 @@ static const struct of_device_id whitelist[] __initconst = {
 	{ .compatible = "renesas,r8a7792", },
 	{ .compatible = "renesas,r8a7793", },
 	{ .compatible = "renesas,r8a7794", },
-	{ .compatible = "renesas,r8a7795", },
-	{ .compatible = "renesas,r8a7796", },
 	{ .compatible = "renesas,sh73a0", },
 
 	{ .compatible = "rockchip,rk2928", },
@@ -118,6 +116,9 @@ static const struct of_device_id blacklist[] __initconst = {
 
 	{ .compatible = "nvidia,tegra124", },
 
+	{ .compatible = "qcom,apq8096", },
+	{ .compatible = "qcom,msm8996", },
+
 	{ .compatible = "st,stih407", },
 	{ .compatible = "st,stih410", },
 
diff --git a/drivers/cpufreq/cpufreq-dt.c b/drivers/cpufreq/cpufreq-dt.c
index 190ea0dccb79..0a9ebf00be46 100644
--- a/drivers/cpufreq/cpufreq-dt.c
+++ b/drivers/cpufreq/cpufreq-dt.c
@@ -346,8 +346,14 @@ static int dt_cpufreq_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	if (data && data->have_governor_per_policy)
-		dt_cpufreq_driver.flags |= CPUFREQ_HAVE_GOVERNOR_PER_POLICY;
+	if (data) {
+		if (data->have_governor_per_policy)
+			dt_cpufreq_driver.flags |= CPUFREQ_HAVE_GOVERNOR_PER_POLICY;
+
+		dt_cpufreq_driver.resume = data->resume;
+		if (data->suspend)
+			dt_cpufreq_driver.suspend = data->suspend;
+	}
 
 	ret = cpufreq_register_driver(&dt_cpufreq_driver);
 	if (ret)
diff --git a/drivers/cpufreq/cpufreq-dt.h b/drivers/cpufreq/cpufreq-dt.h
index 54d774e46c43..d5aeea13433e 100644
--- a/drivers/cpufreq/cpufreq-dt.h
+++ b/drivers/cpufreq/cpufreq-dt.h
@@ -12,8 +12,13 @@
 
 #include <linux/types.h>
 
+struct cpufreq_policy;
+
 struct cpufreq_dt_platform_data {
 	bool have_governor_per_policy;
+
+	int (*suspend)(struct cpufreq_policy *policy);
+	int (*resume)(struct cpufreq_policy *policy);
 };
 
 #endif /* __CPUFREQ_DT_H__ */
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 075d18f6ba7a..b0dfd3222013 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -89,16 +89,7 @@ static void cpufreq_governor_limits(struct cpufreq_policy *policy);
  * The mutex locks both lists.
  */
 static BLOCKING_NOTIFIER_HEAD(cpufreq_policy_notifier_list);
-static struct srcu_notifier_head cpufreq_transition_notifier_list;
-
-static bool init_cpufreq_transition_notifier_list_called;
-static int __init init_cpufreq_transition_notifier_list(void)
-{
-	srcu_init_notifier_head(&cpufreq_transition_notifier_list);
-	init_cpufreq_transition_notifier_list_called = true;
-	return 0;
-}
-pure_initcall(init_cpufreq_transition_notifier_list);
+SRCU_NOTIFIER_HEAD_STATIC(cpufreq_transition_notifier_list);
 
 static int off __read_mostly;
 static int cpufreq_disabled(void)
@@ -300,8 +291,19 @@ static void adjust_jiffies(unsigned long val, struct cpufreq_freqs *ci)
 #endif
 }
 
-static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
-		struct cpufreq_freqs *freqs, unsigned int state)
+/**
+ * cpufreq_notify_transition - Notify frequency transition and adjust_jiffies.
+ * @policy: cpufreq policy to enable fast frequency switching for.
+ * @freqs: contain details of the frequency update.
+ * @state: set to CPUFREQ_PRECHANGE or CPUFREQ_POSTCHANGE.
+ *
+ * This function calls the transition notifiers and the "adjust_jiffies"
+ * function. It is called twice on all CPU frequency changes that have
+ * external effects.
+ */
+static void cpufreq_notify_transition(struct cpufreq_policy *policy,
+				      struct cpufreq_freqs *freqs,
+				      unsigned int state)
 {
 	BUG_ON(irqs_disabled());
 
@@ -313,54 +315,44 @@ static void __cpufreq_notify_transition(struct cpufreq_policy *policy,
 		 state, freqs->new);
 
 	switch (state) {
-
 	case CPUFREQ_PRECHANGE:
-		/* detect if the driver reported a value as "old frequency"
+		/*
+		 * Detect if the driver reported a value as "old frequency"
 		 * which is not equal to what the cpufreq core thinks is
 		 * "old frequency".
 		 */
 		if (!(cpufreq_driver->flags & CPUFREQ_CONST_LOOPS)) {
-			if ((policy) && (policy->cpu == freqs->cpu) &&
-			    (policy->cur) && (policy->cur != freqs->old)) {
+			if (policy->cur && (policy->cur != freqs->old)) {
 				pr_debug("Warning: CPU frequency is %u, cpufreq assumed %u kHz\n",
 					 freqs->old, policy->cur);
 				freqs->old = policy->cur;
 			}
 		}
-		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
-				CPUFREQ_PRECHANGE, freqs);
+
+		for_each_cpu(freqs->cpu, policy->cpus) {
+			srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
+						 CPUFREQ_PRECHANGE, freqs);
+		}
+
 		adjust_jiffies(CPUFREQ_PRECHANGE, freqs);
 		break;
 
 	case CPUFREQ_POSTCHANGE:
 		adjust_jiffies(CPUFREQ_POSTCHANGE, freqs);
-		pr_debug("FREQ: %lu - CPU: %lu\n",
-			 (unsigned long)freqs->new, (unsigned long)freqs->cpu);
-		trace_cpu_frequency(freqs->new, freqs->cpu);
+		pr_debug("FREQ: %u - CPUs: %*pbl\n", freqs->new,
+			 cpumask_pr_args(policy->cpus));
+
+		for_each_cpu(freqs->cpu, policy->cpus) {
+			trace_cpu_frequency(freqs->new, freqs->cpu);
+			srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
+						 CPUFREQ_POSTCHANGE, freqs);
+		}
+
 		cpufreq_stats_record_transition(policy, freqs->new);
-		srcu_notifier_call_chain(&cpufreq_transition_notifier_list,
-				CPUFREQ_POSTCHANGE, freqs);
-		if (likely(policy) && likely(policy->cpu == freqs->cpu))
-			policy->cur = freqs->new;
-		break;
+		policy->cur = freqs->new;
 	}
 }
 
-/**
- * cpufreq_notify_transition - call notifier chain and adjust_jiffies
- * on frequency transition.
- *
- * This function calls the transition notifiers and the "adjust_jiffies"
- * function. It is called twice on all CPU frequency changes that have
- * external effects.
- */
-static void cpufreq_notify_transition(struct cpufreq_policy *policy,
-		struct cpufreq_freqs *freqs, unsigned int state)
-{
-	for_each_cpu(freqs->cpu, policy->cpus)
-		__cpufreq_notify_transition(policy, freqs, state);
-}
-
 /* Do post notifications when there are chances that transition has failed */
 static void cpufreq_notify_post_transition(struct cpufreq_policy *policy,
 		struct cpufreq_freqs *freqs, int transition_failed)
@@ -696,6 +688,8 @@ static ssize_t store_##file_name					\
 	struct cpufreq_policy new_policy;				\
 									\
 	memcpy(&new_policy, policy, sizeof(*policy));			\
+	new_policy.min = policy->user_policy.min;			\
+	new_policy.max = policy->user_policy.max;			\
 									\
 	ret = sscanf(buf, "%u", &new_policy.object);			\
 	if (ret != 1)							\
@@ -1764,8 +1758,6 @@ int cpufreq_register_notifier(struct notifier_block *nb, unsigned int list)
 	if (cpufreq_disabled())
 		return -EINVAL;
 
-	WARN_ON(!init_cpufreq_transition_notifier_list_called);
-
 	switch (list) {
 	case CPUFREQ_TRANSITION_NOTIFIER:
 		mutex_lock(&cpufreq_fast_switch_lock);
diff --git a/drivers/cpufreq/cpufreq_governor.c b/drivers/cpufreq/cpufreq_governor.c
index ca38229b045a..871bf9cf55cf 100644
--- a/drivers/cpufreq/cpufreq_governor.c
+++ b/drivers/cpufreq/cpufreq_governor.c
@@ -278,7 +278,7 @@ static void dbs_update_util_handler(struct update_util_data *data, u64 time,
 	struct policy_dbs_info *policy_dbs = cdbs->policy_dbs;
 	u64 delta_ns, lst;
 
-	if (!cpufreq_can_do_remote_dvfs(policy_dbs->policy))
+	if (!cpufreq_this_cpu_can_update(policy_dbs->policy))
 		return;
 
 	/*
diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c
index 17e566afbb41..08960a55eb27 100644
--- a/drivers/cpufreq/intel_pstate.c
+++ b/drivers/cpufreq/intel_pstate.c
@@ -1939,13 +1939,51 @@ static int intel_cpufreq_verify_policy(struct cpufreq_policy *policy)
 	return 0;
 }
 
+/* Use of trace in passive mode:
+ *
+ * In passive mode the trace core_busy field (also known as the
+ * performance field, and lablelled as such on the graphs; also known as
+ * core_avg_perf) is not needed and so is re-assigned to indicate if the
+ * driver call was via the normal or fast switch path. Various graphs
+ * output from the intel_pstate_tracer.py utility that include core_busy
+ * (or performance or core_avg_perf) have a fixed y-axis from 0 to 100%,
+ * so we use 10 to indicate the the normal path through the driver, and
+ * 90 to indicate the fast switch path through the driver.
+ * The scaled_busy field is not used, and is set to 0.
+ */
+
+#define	INTEL_PSTATE_TRACE_TARGET 10
+#define	INTEL_PSTATE_TRACE_FAST_SWITCH 90
+
+static void intel_cpufreq_trace(struct cpudata *cpu, unsigned int trace_type, int old_pstate)
+{
+	struct sample *sample;
+
+	if (!trace_pstate_sample_enabled())
+		return;
+
+	if (!intel_pstate_sample(cpu, ktime_get()))
+		return;
+
+	sample = &cpu->sample;
+	trace_pstate_sample(trace_type,
+		0,
+		old_pstate,
+		cpu->pstate.current_pstate,
+		sample->mperf,
+		sample->aperf,
+		sample->tsc,
+		get_avg_frequency(cpu),
+		fp_toint(cpu->iowait_boost * 100));
+}
+
 static int intel_cpufreq_target(struct cpufreq_policy *policy,
 				unsigned int target_freq,
 				unsigned int relation)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
 	struct cpufreq_freqs freqs;
-	int target_pstate;
+	int target_pstate, old_pstate;
 
 	update_turbo_state();
 
@@ -1965,12 +2003,14 @@ static int intel_cpufreq_target(struct cpufreq_policy *policy,
 		break;
 	}
 	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+	old_pstate = cpu->pstate.current_pstate;
 	if (target_pstate != cpu->pstate.current_pstate) {
 		cpu->pstate.current_pstate = target_pstate;
 		wrmsrl_on_cpu(policy->cpu, MSR_IA32_PERF_CTL,
 			      pstate_funcs.get_val(cpu, target_pstate));
 	}
 	freqs.new = target_pstate * cpu->pstate.scaling;
+	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_TARGET, old_pstate);
 	cpufreq_freq_transition_end(policy, &freqs, false);
 
 	return 0;
@@ -1980,13 +2020,15 @@ static unsigned int intel_cpufreq_fast_switch(struct cpufreq_policy *policy,
 					      unsigned int target_freq)
 {
 	struct cpudata *cpu = all_cpu_data[policy->cpu];
-	int target_pstate;
+	int target_pstate, old_pstate;
 
 	update_turbo_state();
 
 	target_pstate = DIV_ROUND_UP(target_freq, cpu->pstate.scaling);
 	target_pstate = intel_pstate_prepare_request(cpu, target_pstate);
+	old_pstate = cpu->pstate.current_pstate;
 	intel_pstate_update_pstate(cpu, target_pstate);
+	intel_cpufreq_trace(cpu, INTEL_PSTATE_TRACE_FAST_SWITCH, old_pstate);
 	return target_pstate * cpu->pstate.scaling;
 }
 
diff --git a/drivers/cpufreq/qcom-cpufreq-kryo.c b/drivers/cpufreq/qcom-cpufreq-kryo.c
new file mode 100644
index 000000000000..d049fe4b80c4
--- /dev/null
+++ b/drivers/cpufreq/qcom-cpufreq-kryo.c
@@ -0,0 +1,212 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018, The Linux Foundation. All rights reserved.
+ */
+
+/*
+ * In Certain QCOM SoCs like apq8096 and msm8996 that have KRYO processors,
+ * the CPU frequency subset and voltage value of each OPP varies
+ * based on the silicon variant in use. Qualcomm Process Voltage Scaling Tables
+ * defines the voltage and frequency value based on the msm-id in SMEM
+ * and speedbin blown in the efuse combination.
+ * The qcom-cpufreq-kryo driver reads the msm-id and efuse value from the SoC
+ * to provide the OPP framework with required information.
+ * This is used to determine the voltage and frequency value for each OPP of
+ * operating-points-v2 table when it is parsed by the OPP framework.
+ */
+
+#include <linux/cpu.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/nvmem-consumer.h>
+#include <linux/of.h>
+#include <linux/platform_device.h>
+#include <linux/pm_opp.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/smem.h>
+
+#define MSM_ID_SMEM	137
+
+enum _msm_id {
+	MSM8996V3 = 0xF6ul,
+	APQ8096V3 = 0x123ul,
+	MSM8996SG = 0x131ul,
+	APQ8096SG = 0x138ul,
+};
+
+enum _msm8996_version {
+	MSM8996_V3,
+	MSM8996_SG,
+	NUM_OF_MSM8996_VERSIONS,
+};
+
+static enum _msm8996_version __init qcom_cpufreq_kryo_get_msm_id(void)
+{
+	size_t len;
+	u32 *msm_id;
+	enum _msm8996_version version;
+
+	msm_id = qcom_smem_get(QCOM_SMEM_HOST_ANY, MSM_ID_SMEM, &len);
+	if (IS_ERR(msm_id))
+		return NUM_OF_MSM8996_VERSIONS;
+
+	/* The first 4 bytes are format, next to them is the actual msm-id */
+	msm_id++;
+
+	switch ((enum _msm_id)*msm_id) {
+	case MSM8996V3:
+	case APQ8096V3:
+		version = MSM8996_V3;
+		break;
+	case MSM8996SG:
+	case APQ8096SG:
+		version = MSM8996_SG;
+		break;
+	default:
+		version = NUM_OF_MSM8996_VERSIONS;
+	}
+
+	return version;
+}
+
+static int qcom_cpufreq_kryo_probe(struct platform_device *pdev)
+{
+	struct opp_table *opp_tables[NR_CPUS] = {0};
+	struct platform_device *cpufreq_dt_pdev;
+	enum _msm8996_version msm8996_version;
+	struct nvmem_cell *speedbin_nvmem;
+	struct device_node *np;
+	struct device *cpu_dev;
+	unsigned cpu;
+	u8 *speedbin;
+	u32 versions;
+	size_t len;
+	int ret;
+
+	cpu_dev = get_cpu_device(0);
+	if (NULL == cpu_dev)
+		ret = -ENODEV;
+
+	msm8996_version = qcom_cpufreq_kryo_get_msm_id();
+	if (NUM_OF_MSM8996_VERSIONS == msm8996_version) {
+		dev_err(cpu_dev, "Not Snapdragon 820/821!");
+		return -ENODEV;
+	}
+
+	np = dev_pm_opp_of_get_opp_desc_node(cpu_dev);
+	if (IS_ERR(np))
+		return PTR_ERR(np);
+
+	ret = of_device_is_compatible(np, "operating-points-v2-kryo-cpu");
+	if (!ret) {
+		of_node_put(np);
+		return -ENOENT;
+	}
+
+	speedbin_nvmem = of_nvmem_cell_get(np, NULL);
+	of_node_put(np);
+	if (IS_ERR(speedbin_nvmem)) {
+		dev_err(cpu_dev, "Could not get nvmem cell: %ld\n",
+			PTR_ERR(speedbin_nvmem));
+		return PTR_ERR(speedbin_nvmem);
+	}
+
+	speedbin = nvmem_cell_read(speedbin_nvmem, &len);
+	nvmem_cell_put(speedbin_nvmem);
+
+	switch (msm8996_version) {
+	case MSM8996_V3:
+		versions = 1 << (unsigned int)(*speedbin);
+		break;
+	case MSM8996_SG:
+		versions = 1 << ((unsigned int)(*speedbin) + 4);
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	for_each_possible_cpu(cpu) {
+		cpu_dev = get_cpu_device(cpu);
+		if (NULL == cpu_dev) {
+			ret = -ENODEV;
+			goto free_opp;
+		}
+
+		opp_tables[cpu] = dev_pm_opp_set_supported_hw(cpu_dev,
+							      &versions, 1);
+		if (IS_ERR(opp_tables[cpu])) {
+			ret = PTR_ERR(opp_tables[cpu]);
+			dev_err(cpu_dev, "Failed to set supported hardware\n");
+			goto free_opp;
+		}
+	}
+
+	cpufreq_dt_pdev = platform_device_register_simple("cpufreq-dt", -1,
+							  NULL, 0);
+	if (!IS_ERR(cpufreq_dt_pdev))
+		return 0;
+
+	ret = PTR_ERR(cpufreq_dt_pdev);
+	dev_err(cpu_dev, "Failed to register platform device\n");
+
+free_opp:
+	for_each_possible_cpu(cpu) {
+		if (IS_ERR_OR_NULL(opp_tables[cpu]))
+			break;
+		dev_pm_opp_put_supported_hw(opp_tables[cpu]);
+	}
+
+	return ret;
+}
+
+static struct platform_driver qcom_cpufreq_kryo_driver = {
+	.probe = qcom_cpufreq_kryo_probe,
+	.driver = {
+		.name = "qcom-cpufreq-kryo",
+	},
+};
+
+static const struct of_device_id qcom_cpufreq_kryo_match_list[] __initconst = {
+	{ .compatible = "qcom,apq8096", },
+	{ .compatible = "qcom,msm8996", },
+};
+
+/*
+ * Since the driver depends on smem and nvmem drivers, which may
+ * return EPROBE_DEFER, all the real activity is done in the probe,
+ * which may be defered as well. The init here is only registering
+ * the driver and the platform device.
+ */
+static int __init qcom_cpufreq_kryo_init(void)
+{
+	struct device_node *np = of_find_node_by_path("/");
+	const struct of_device_id *match;
+	int ret;
+
+	if (!np)
+		return -ENODEV;
+
+	match = of_match_node(qcom_cpufreq_kryo_match_list, np);
+	of_node_put(np);
+	if (!match)
+		return -ENODEV;
+
+	ret = platform_driver_register(&qcom_cpufreq_kryo_driver);
+	if (unlikely(ret < 0))
+		return ret;
+
+	ret = PTR_ERR_OR_ZERO(platform_device_register_simple(
+		"qcom-cpufreq-kryo", -1, NULL, 0));
+	if (0 == ret)
+		return 0;
+
+	platform_driver_unregister(&qcom_cpufreq_kryo_driver);
+	return ret;
+}
+module_init(qcom_cpufreq_kryo_init);
+
+MODULE_DESCRIPTION("Qualcomm Technologies, Inc. Kryo CPUfreq driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/cpufreq/s3c2440-cpufreq.c b/drivers/cpufreq/s3c2440-cpufreq.c
index d0d75b65ddd6..d2f67b7a20dd 100644
--- a/drivers/cpufreq/s3c2440-cpufreq.c
+++ b/drivers/cpufreq/s3c2440-cpufreq.c
@@ -143,7 +143,7 @@ static void s3c2440_cpufreq_setdivs(struct s3c_cpufreq_config *cfg)
 {
 	unsigned long clkdiv, camdiv;
 
-	s3c_freq_dbg("%s: divsiors: h=%d, p=%d\n", __func__,
+	s3c_freq_dbg("%s: divisors: h=%d, p=%d\n", __func__,
 		     cfg->divs.h_divisor, cfg->divs.p_divisor);
 
 	clkdiv = __raw_readl(S3C2410_CLKDIVN);
diff --git a/drivers/cpufreq/speedstep-lib.c b/drivers/cpufreq/speedstep-lib.c
index e3a9962ee410..cabb6f48eb77 100644
--- a/drivers/cpufreq/speedstep-lib.c
+++ b/drivers/cpufreq/speedstep-lib.c
@@ -252,7 +252,7 @@ EXPORT_SYMBOL_GPL(speedstep_get_frequency);
  *********************************************************************/
 
 /* Keep in sync with the x86_cpu_id tables in the different modules */
-unsigned int speedstep_detect_processor(void)
+enum speedstep_processor speedstep_detect_processor(void)
 {
 	struct cpuinfo_x86 *c = &cpu_data(0);
 	u32 ebx, msr_lo, msr_hi;
diff --git a/drivers/cpufreq/tegra20-cpufreq.c b/drivers/cpufreq/tegra20-cpufreq.c
index 2bd62845e9d5..05f57dcd5215 100644
--- a/drivers/cpufreq/tegra20-cpufreq.c
+++ b/drivers/cpufreq/tegra20-cpufreq.c
@@ -16,16 +16,13 @@
  *
  */
 
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/sched.h>
+#include <linux/clk.h>
 #include <linux/cpufreq.h>
-#include <linux/delay.h>
-#include <linux/init.h>
 #include <linux/err.h>
-#include <linux/clk.h>
-#include <linux/io.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
 
 static struct cpufreq_frequency_table freq_table[] = {
 	{ .frequency = 216000 },
@@ -39,25 +36,27 @@ static struct cpufreq_frequency_table freq_table[] = {
 	{ .frequency = CPUFREQ_TABLE_END },
 };
 
-#define NUM_CPUS	2
-
-static struct clk *cpu_clk;
-static struct clk *pll_x_clk;
-static struct clk *pll_p_clk;
-static struct clk *emc_clk;
-static bool pll_x_prepared;
+struct tegra20_cpufreq {
+	struct device *dev;
+	struct cpufreq_driver driver;
+	struct clk *cpu_clk;
+	struct clk *pll_x_clk;
+	struct clk *pll_p_clk;
+	bool pll_x_prepared;
+};
 
 static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
 					   unsigned int index)
 {
-	unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
+	unsigned int ifreq = clk_get_rate(cpufreq->pll_p_clk) / 1000;
 
 	/*
 	 * Don't switch to intermediate freq if:
 	 * - we are already at it, i.e. policy->cur == ifreq
 	 * - index corresponds to ifreq
 	 */
-	if ((freq_table[index].frequency == ifreq) || (policy->cur == ifreq))
+	if (freq_table[index].frequency == ifreq || policy->cur == ifreq)
 		return 0;
 
 	return ifreq;
@@ -66,6 +65,7 @@ static unsigned int tegra_get_intermediate(struct cpufreq_policy *policy,
 static int tegra_target_intermediate(struct cpufreq_policy *policy,
 				     unsigned int index)
 {
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
 	int ret;
 
 	/*
@@ -78,47 +78,37 @@ static int tegra_target_intermediate(struct cpufreq_policy *policy,
 	 * Also, we wouldn't be using pll_x anymore and must not take extra
 	 * reference to it, as it can be disabled now to save some power.
 	 */
-	clk_prepare_enable(pll_x_clk);
+	clk_prepare_enable(cpufreq->pll_x_clk);
 
-	ret = clk_set_parent(cpu_clk, pll_p_clk);
+	ret = clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_p_clk);
 	if (ret)
-		clk_disable_unprepare(pll_x_clk);
+		clk_disable_unprepare(cpufreq->pll_x_clk);
 	else
-		pll_x_prepared = true;
+		cpufreq->pll_x_prepared = true;
 
 	return ret;
 }
 
 static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 {
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
 	unsigned long rate = freq_table[index].frequency;
-	unsigned int ifreq = clk_get_rate(pll_p_clk) / 1000;
-	int ret = 0;
-
-	/*
-	 * Vote on memory bus frequency based on cpu frequency
-	 * This sets the minimum frequency, display or avp may request higher
-	 */
-	if (rate >= 816000)
-		clk_set_rate(emc_clk, 600000000); /* cpu 816 MHz, emc max */
-	else if (rate >= 456000)
-		clk_set_rate(emc_clk, 300000000); /* cpu 456 MHz, emc 150Mhz */
-	else
-		clk_set_rate(emc_clk, 100000000);  /* emc 50Mhz */
+	unsigned int ifreq = clk_get_rate(cpufreq->pll_p_clk) / 1000;
+	int ret;
 
 	/*
 	 * target freq == pll_p, don't need to take extra reference to pll_x_clk
 	 * as it isn't used anymore.
 	 */
 	if (rate == ifreq)
-		return clk_set_parent(cpu_clk, pll_p_clk);
+		return clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_p_clk);
 
-	ret = clk_set_rate(pll_x_clk, rate * 1000);
+	ret = clk_set_rate(cpufreq->pll_x_clk, rate * 1000);
 	/* Restore to earlier frequency on error, i.e. pll_x */
 	if (ret)
-		pr_err("Failed to change pll_x to %lu\n", rate);
+		dev_err(cpufreq->dev, "Failed to change pll_x to %lu\n", rate);
 
-	ret = clk_set_parent(cpu_clk, pll_x_clk);
+	ret = clk_set_parent(cpufreq->cpu_clk, cpufreq->pll_x_clk);
 	/* This shouldn't fail while changing or restoring */
 	WARN_ON(ret);
 
@@ -126,9 +116,9 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 	 * Drop count to pll_x clock only if we switched to intermediate freq
 	 * earlier while transitioning to a target frequency.
 	 */
-	if (pll_x_prepared) {
-		clk_disable_unprepare(pll_x_clk);
-		pll_x_prepared = false;
+	if (cpufreq->pll_x_prepared) {
+		clk_disable_unprepare(cpufreq->pll_x_clk);
+		cpufreq->pll_x_prepared = false;
 	}
 
 	return ret;
@@ -136,81 +126,111 @@ static int tegra_target(struct cpufreq_policy *policy, unsigned int index)
 
 static int tegra_cpu_init(struct cpufreq_policy *policy)
 {
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
 	int ret;
 
-	if (policy->cpu >= NUM_CPUS)
-		return -EINVAL;
-
-	clk_prepare_enable(emc_clk);
-	clk_prepare_enable(cpu_clk);
+	clk_prepare_enable(cpufreq->cpu_clk);
 
 	/* FIXME: what's the actual transition time? */
 	ret = cpufreq_generic_init(policy, freq_table, 300 * 1000);
 	if (ret) {
-		clk_disable_unprepare(cpu_clk);
-		clk_disable_unprepare(emc_clk);
+		clk_disable_unprepare(cpufreq->cpu_clk);
 		return ret;
 	}
 
-	policy->clk = cpu_clk;
+	policy->clk = cpufreq->cpu_clk;
 	policy->suspend_freq = freq_table[0].frequency;
 	return 0;
 }
 
 static int tegra_cpu_exit(struct cpufreq_policy *policy)
 {
-	clk_disable_unprepare(cpu_clk);
-	clk_disable_unprepare(emc_clk);
+	struct tegra20_cpufreq *cpufreq = cpufreq_get_driver_data();
+
+	clk_disable_unprepare(cpufreq->cpu_clk);
 	return 0;
 }
 
-static struct cpufreq_driver tegra_cpufreq_driver = {
-	.flags			= CPUFREQ_NEED_INITIAL_FREQ_CHECK,
-	.verify			= cpufreq_generic_frequency_table_verify,
-	.get_intermediate	= tegra_get_intermediate,
-	.target_intermediate	= tegra_target_intermediate,
-	.target_index		= tegra_target,
-	.get			= cpufreq_generic_get,
-	.init			= tegra_cpu_init,
-	.exit			= tegra_cpu_exit,
-	.name			= "tegra",
-	.attr			= cpufreq_generic_attr,
-	.suspend		= cpufreq_generic_suspend,
-};
-
-static int __init tegra_cpufreq_init(void)
+static int tegra20_cpufreq_probe(struct platform_device *pdev)
 {
-	cpu_clk = clk_get_sys(NULL, "cclk");
-	if (IS_ERR(cpu_clk))
-		return PTR_ERR(cpu_clk);
-
-	pll_x_clk = clk_get_sys(NULL, "pll_x");
-	if (IS_ERR(pll_x_clk))
-		return PTR_ERR(pll_x_clk);
-
-	pll_p_clk = clk_get_sys(NULL, "pll_p");
-	if (IS_ERR(pll_p_clk))
-		return PTR_ERR(pll_p_clk);
-
-	emc_clk = clk_get_sys("cpu", "emc");
-	if (IS_ERR(emc_clk)) {
-		clk_put(cpu_clk);
-		return PTR_ERR(emc_clk);
+	struct tegra20_cpufreq *cpufreq;
+	int err;
+
+	cpufreq = devm_kzalloc(&pdev->dev, sizeof(*cpufreq), GFP_KERNEL);
+	if (!cpufreq)
+		return -ENOMEM;
+
+	cpufreq->cpu_clk = clk_get_sys(NULL, "cclk");
+	if (IS_ERR(cpufreq->cpu_clk))
+		return PTR_ERR(cpufreq->cpu_clk);
+
+	cpufreq->pll_x_clk = clk_get_sys(NULL, "pll_x");
+	if (IS_ERR(cpufreq->pll_x_clk)) {
+		err = PTR_ERR(cpufreq->pll_x_clk);
+		goto put_cpu;
+	}
+
+	cpufreq->pll_p_clk = clk_get_sys(NULL, "pll_p");
+	if (IS_ERR(cpufreq->pll_p_clk)) {
+		err = PTR_ERR(cpufreq->pll_p_clk);
+		goto put_pll_x;
 	}
 
-	return cpufreq_register_driver(&tegra_cpufreq_driver);
+	cpufreq->dev = &pdev->dev;
+	cpufreq->driver.get = cpufreq_generic_get;
+	cpufreq->driver.attr = cpufreq_generic_attr;
+	cpufreq->driver.init = tegra_cpu_init;
+	cpufreq->driver.exit = tegra_cpu_exit;
+	cpufreq->driver.flags = CPUFREQ_NEED_INITIAL_FREQ_CHECK;
+	cpufreq->driver.verify = cpufreq_generic_frequency_table_verify;
+	cpufreq->driver.suspend = cpufreq_generic_suspend;
+	cpufreq->driver.driver_data = cpufreq;
+	cpufreq->driver.target_index = tegra_target;
+	cpufreq->driver.get_intermediate = tegra_get_intermediate;
+	cpufreq->driver.target_intermediate = tegra_target_intermediate;
+	snprintf(cpufreq->driver.name, CPUFREQ_NAME_LEN, "tegra");
+
+	err = cpufreq_register_driver(&cpufreq->driver);
+	if (err)
+		goto put_pll_p;
+
+	platform_set_drvdata(pdev, cpufreq);
+
+	return 0;
+
+put_pll_p:
+	clk_put(cpufreq->pll_p_clk);
+put_pll_x:
+	clk_put(cpufreq->pll_x_clk);
+put_cpu:
+	clk_put(cpufreq->cpu_clk);
+
+	return err;
 }
 
-static void __exit tegra_cpufreq_exit(void)
+static int tegra20_cpufreq_remove(struct platform_device *pdev)
 {
-        cpufreq_unregister_driver(&tegra_cpufreq_driver);
-	clk_put(emc_clk);
-	clk_put(cpu_clk);
+	struct tegra20_cpufreq *cpufreq = platform_get_drvdata(pdev);
+
+	cpufreq_unregister_driver(&cpufreq->driver);
+
+	clk_put(cpufreq->pll_p_clk);
+	clk_put(cpufreq->pll_x_clk);
+	clk_put(cpufreq->cpu_clk);
+
+	return 0;
 }
 
+static struct platform_driver tegra20_cpufreq_driver = {
+	.probe		= tegra20_cpufreq_probe,
+	.remove		= tegra20_cpufreq_remove,
+	.driver		= {
+		.name	= "tegra20-cpufreq",
+	},
+};
+module_platform_driver(tegra20_cpufreq_driver);
 
+MODULE_ALIAS("platform:tegra20-cpufreq");
 MODULE_AUTHOR("Colin Cross <ccross@android.com>");
-MODULE_DESCRIPTION("cpufreq driver for Nvidia Tegra2");
+MODULE_DESCRIPTION("NVIDIA Tegra20 cpufreq driver");
 MODULE_LICENSE("GPL");
-module_init(tegra_cpufreq_init);
-module_exit(tegra_cpufreq_exit);
diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c
index 5d359aff3cc5..9fed1b829292 100644
--- a/drivers/cpuidle/governor.c
+++ b/drivers/cpuidle/governor.c
@@ -8,8 +8,10 @@
  * This code is licenced under the GPL.
  */
 
-#include <linux/mutex.h>
+#include <linux/cpu.h>
 #include <linux/cpuidle.h>
+#include <linux/mutex.h>
+#include <linux/pm_qos.h>
 
 #include "cpuidle.h"
 
@@ -93,3 +95,16 @@ int cpuidle_register_governor(struct cpuidle_governor *gov)
 
 	return ret;
 }
+
+/**
+ * cpuidle_governor_latency_req - Compute a latency constraint for CPU
+ * @cpu: Target CPU
+ */
+int cpuidle_governor_latency_req(unsigned int cpu)
+{
+	int global_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+	struct device *device = get_cpu_device(cpu);
+	int device_req = dev_pm_qos_raw_read_value(device);
+
+	return device_req < global_req ? device_req : global_req;
+}
diff --git a/drivers/cpuidle/governors/ladder.c b/drivers/cpuidle/governors/ladder.c
index b24883f85c99..704880a6612a 100644
--- a/drivers/cpuidle/governors/ladder.c
+++ b/drivers/cpuidle/governors/ladder.c
@@ -14,10 +14,8 @@
 
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
-#include <linux/pm_qos.h>
 #include <linux/jiffies.h>
 #include <linux/tick.h>
-#include <linux/cpu.h>
 
 #include <asm/io.h>
 #include <linux/uaccess.h>
@@ -69,16 +67,10 @@ static int ladder_select_state(struct cpuidle_driver *drv,
 			       struct cpuidle_device *dev, bool *dummy)
 {
 	struct ladder_device *ldev = this_cpu_ptr(&ladder_devices);
-	struct device *device = get_cpu_device(dev->cpu);
 	struct ladder_device_state *last_state;
 	int last_residency, last_idx = ldev->last_state_idx;
 	int first_idx = drv->states[0].flags & CPUIDLE_FLAG_POLLING ? 1 : 0;
-	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
-	int resume_latency = dev_pm_qos_raw_read_value(device);
-
-	if (resume_latency < latency_req &&
-	    resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
-		latency_req = resume_latency;
+	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
diff --git a/drivers/cpuidle/governors/menu.c b/drivers/cpuidle/governors/menu.c
index 1bfe03ceb236..1aef60d160eb 100644
--- a/drivers/cpuidle/governors/menu.c
+++ b/drivers/cpuidle/governors/menu.c
@@ -12,7 +12,6 @@
 
 #include <linux/kernel.h>
 #include <linux/cpuidle.h>
-#include <linux/pm_qos.h>
 #include <linux/time.h>
 #include <linux/ktime.h>
 #include <linux/hrtimer.h>
@@ -21,7 +20,6 @@
 #include <linux/sched/loadavg.h>
 #include <linux/sched/stat.h>
 #include <linux/math64.h>
-#include <linux/cpu.h>
 
 /*
  * Please note when changing the tuning values:
@@ -286,15 +284,13 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		       bool *stop_tick)
 {
 	struct menu_device *data = this_cpu_ptr(&menu_devices);
-	struct device *device = get_cpu_device(dev->cpu);
-	int latency_req = pm_qos_request(PM_QOS_CPU_DMA_LATENCY);
+	int latency_req = cpuidle_governor_latency_req(dev->cpu);
 	int i;
 	int first_idx;
 	int idx;
 	unsigned int interactivity_req;
 	unsigned int expected_interval;
 	unsigned long nr_iowaiters, cpu_load;
-	int resume_latency = dev_pm_qos_raw_read_value(device);
 	ktime_t delta_next;
 
 	if (data->needs_update) {
@@ -302,10 +298,6 @@ static int menu_select(struct cpuidle_driver *drv, struct cpuidle_device *dev,
 		data->needs_update = 0;
 	}
 
-	if (resume_latency < latency_req &&
-	    resume_latency != PM_QOS_RESUME_LATENCY_NO_CONSTRAINT)
-		latency_req = resume_latency;
-
 	/* Special case when user has set very strict latency requirement */
 	if (unlikely(latency_req == 0)) {
 		*stop_tick = false;
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
index a29362f9ef41..12558044acd4 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_acp.c
@@ -513,7 +513,7 @@ static int acp_hw_fini(void *handle)
 	if (adev->acp.acp_genpd) {
 		for (i = 0; i < ACP_DEVS ; i++) {
 			dev = get_mfd_cell_dev(adev->acp.acp_cell[i].name, i);
-			ret = pm_genpd_remove_device(&adev->acp.acp_genpd->gpd, dev);
+			ret = pm_genpd_remove_device(dev);
 			/* If removal fails, dont giveup and try rest */
 			if (ret)
 				dev_err(dev, "remove dev from genpd failed\n");
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 1ba40bb2b966..a17f46a95f73 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -363,7 +363,7 @@ static int i2c_device_probe(struct device *dev)
 		goto err_clear_wakeup_irq;
 
 	status = dev_pm_domain_attach(&client->dev, true);
-	if (status == -EPROBE_DEFER)
+	if (status)
 		goto err_clear_wakeup_irq;
 
 	/*
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index 2b32b88949ba..b6d8203e46eb 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -139,7 +139,7 @@ static int sdio_bus_probe(struct device *dev)
 		return -ENODEV;
 
 	ret = dev_pm_domain_attach(dev, false);
-	if (ret == -EPROBE_DEFER)
+	if (ret)
 		return ret;
 
 	/* Unbound SDIO functions are always suspended.
diff --git a/drivers/opp/core.c b/drivers/opp/core.c
index 92fa94a6dcc1..ab2f3fead6b1 100644
--- a/drivers/opp/core.c
+++ b/drivers/opp/core.c
@@ -33,8 +33,6 @@ LIST_HEAD(opp_tables);
 /* Lock to allow exclusive modification to the device and opp lists */
 DEFINE_MUTEX(opp_table_lock);
 
-static void dev_pm_opp_get(struct dev_pm_opp *opp);
-
 static struct opp_device *_find_opp_dev(const struct device *dev,
 					struct opp_table *opp_table)
 {
@@ -281,6 +279,23 @@ unsigned long dev_pm_opp_get_suspend_opp_freq(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 
+int _get_opp_count(struct opp_table *opp_table)
+{
+	struct dev_pm_opp *opp;
+	int count = 0;
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(opp, &opp_table->opp_list, node) {
+		if (opp->available)
+			count++;
+	}
+
+	mutex_unlock(&opp_table->lock);
+
+	return count;
+}
+
 /**
  * dev_pm_opp_get_opp_count() - Get number of opps available in the opp table
  * @dev:	device for which we do this operation
@@ -291,25 +306,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_get_suspend_opp_freq);
 int dev_pm_opp_get_opp_count(struct device *dev)
 {
 	struct opp_table *opp_table;
-	struct dev_pm_opp *temp_opp;
-	int count = 0;
+	int count;
 
 	opp_table = _find_opp_table(dev);
 	if (IS_ERR(opp_table)) {
 		count = PTR_ERR(opp_table);
 		dev_dbg(dev, "%s: OPP table not found (%d)\n",
 			__func__, count);
-		return count;
-	}
-
-	mutex_lock(&opp_table->lock);
-
-	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
-		if (temp_opp->available)
-			count++;
+		return 0;
 	}
 
-	mutex_unlock(&opp_table->lock);
+	count = _get_opp_count(opp_table);
 	dev_pm_opp_put_opp_table(opp_table);
 
 	return count;
@@ -892,7 +899,7 @@ static void _opp_kref_release(struct kref *kref)
 	dev_pm_opp_put_opp_table(opp_table);
 }
 
-static void dev_pm_opp_get(struct dev_pm_opp *opp)
+void dev_pm_opp_get(struct dev_pm_opp *opp)
 {
 	kref_get(&opp->kref);
 }
@@ -985,22 +992,11 @@ static bool _opp_supported_by_regulators(struct dev_pm_opp *opp,
 	return true;
 }
 
-/*
- * Returns:
- * 0: On success. And appropriate error message for duplicate OPPs.
- * -EBUSY: For OPP with same freq/volt and is available. The callers of
- *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
- *  sure we don't print error messages unnecessarily if different parts of
- *  kernel try to initialize the OPP table.
- * -EEXIST: For OPP with same freq but different volt or is unavailable. This
- *  should be considered an error by the callers of _opp_add().
- */
-int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
-	     struct opp_table *opp_table)
+static int _opp_is_duplicate(struct device *dev, struct dev_pm_opp *new_opp,
+			     struct opp_table *opp_table,
+			     struct list_head **head)
 {
 	struct dev_pm_opp *opp;
-	struct list_head *head;
-	int ret;
 
 	/*
 	 * Insert new OPP in order of increasing frequency and discard if
@@ -1010,17 +1006,14 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 	 * loop, don't replace it with head otherwise it will become an infinite
 	 * loop.
 	 */
-	mutex_lock(&opp_table->lock);
-	head = &opp_table->opp_list;
-
 	list_for_each_entry(opp, &opp_table->opp_list, node) {
 		if (new_opp->rate > opp->rate) {
-			head = &opp->node;
+			*head = &opp->node;
 			continue;
 		}
 
 		if (new_opp->rate < opp->rate)
-			break;
+			return 0;
 
 		/* Duplicate OPPs */
 		dev_warn(dev, "%s: duplicate OPPs detected. Existing: freq: %lu, volt: %lu, enabled: %d. New: freq: %lu, volt: %lu, enabled: %d\n",
@@ -1029,15 +1022,39 @@ int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
 			 new_opp->supplies[0].u_volt, new_opp->available);
 
 		/* Should we compare voltages for all regulators here ? */
-		ret = opp->available &&
-		      new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
-
-		mutex_unlock(&opp_table->lock);
-		return ret;
+		return opp->available &&
+		       new_opp->supplies[0].u_volt == opp->supplies[0].u_volt ? -EBUSY : -EEXIST;
 	}
 
-	if (opp_table->get_pstate)
-		new_opp->pstate = opp_table->get_pstate(dev, new_opp->rate);
+	return 0;
+}
+
+/*
+ * Returns:
+ * 0: On success. And appropriate error message for duplicate OPPs.
+ * -EBUSY: For OPP with same freq/volt and is available. The callers of
+ *  _opp_add() must return 0 if they receive -EBUSY from it. This is to make
+ *  sure we don't print error messages unnecessarily if different parts of
+ *  kernel try to initialize the OPP table.
+ * -EEXIST: For OPP with same freq but different volt or is unavailable. This
+ *  should be considered an error by the callers of _opp_add().
+ */
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp,
+	     struct opp_table *opp_table, bool rate_not_available)
+{
+	struct list_head *head;
+	int ret;
+
+	mutex_lock(&opp_table->lock);
+	head = &opp_table->opp_list;
+
+	if (likely(!rate_not_available)) {
+		ret = _opp_is_duplicate(dev, new_opp, opp_table, &head);
+		if (ret) {
+			mutex_unlock(&opp_table->lock);
+			return ret;
+		}
+	}
 
 	list_add(&new_opp->node, head);
 	mutex_unlock(&opp_table->lock);
@@ -1104,7 +1121,7 @@ int _opp_add_v1(struct opp_table *opp_table, struct device *dev,
 	new_opp->available = true;
 	new_opp->dynamic = dynamic;
 
-	ret = _opp_add(dev, new_opp, opp_table);
+	ret = _opp_add(dev, new_opp, opp_table, false);
 	if (ret) {
 		/* Don't return error for duplicate OPPs */
 		if (ret == -EBUSY)
@@ -1140,7 +1157,6 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
 			const u32 *versions, unsigned int count)
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
 	if (!opp_table)
@@ -1149,29 +1165,20 @@ struct opp_table *dev_pm_opp_set_supported_hw(struct device *dev,
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a version hierarchy associated with opp_table? */
-	if (opp_table->supported_hw) {
-		dev_err(dev, "%s: Already have supported hardware list\n",
-			__func__);
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the property ? */
+	if (opp_table->supported_hw)
+		return opp_table;
 
 	opp_table->supported_hw = kmemdup(versions, count * sizeof(*versions),
 					GFP_KERNEL);
 	if (!opp_table->supported_hw) {
-		ret = -ENOMEM;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	opp_table->supported_hw_count = count;
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_supported_hw);
 
@@ -1188,12 +1195,6 @@ void dev_pm_opp_put_supported_hw(struct opp_table *opp_table)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	if (!opp_table->supported_hw) {
-		pr_err("%s: Doesn't have supported hardware list\n",
-		       __func__);
-		return;
-	}
-
 	kfree(opp_table->supported_hw);
 	opp_table->supported_hw = NULL;
 	opp_table->supported_hw_count = 0;
@@ -1215,7 +1216,6 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_put_supported_hw);
 struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	opp_table = dev_pm_opp_get_opp_table(dev);
 	if (!opp_table)
@@ -1224,26 +1224,17 @@ struct opp_table *dev_pm_opp_set_prop_name(struct device *dev, const char *name)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	/* Do we already have a prop-name associated with opp_table? */
-	if (opp_table->prop_name) {
-		dev_err(dev, "%s: Already have prop-name %s\n", __func__,
-			opp_table->prop_name);
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the property ? */
+	if (opp_table->prop_name)
+		return opp_table;
 
 	opp_table->prop_name = kstrdup(name, GFP_KERNEL);
 	if (!opp_table->prop_name) {
-		ret = -ENOMEM;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-ENOMEM);
 	}
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_set_prop_name);
 
@@ -1260,11 +1251,6 @@ void dev_pm_opp_put_prop_name(struct opp_table *opp_table)
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
-	if (!opp_table->prop_name) {
-		pr_err("%s: Doesn't have a prop-name\n", __func__);
-		return;
-	}
-
 	kfree(opp_table->prop_name);
 	opp_table->prop_name = NULL;
 
@@ -1334,11 +1320,9 @@ struct opp_table *dev_pm_opp_set_regulators(struct device *dev,
 		goto err;
 	}
 
-	/* Already have regulators set */
-	if (opp_table->regulators) {
-		ret = -EBUSY;
-		goto err;
-	}
+	/* Another CPU that shares the OPP table has set the regulators ? */
+	if (opp_table->regulators)
+		return opp_table;
 
 	opp_table->regulators = kmalloc_array(count,
 					      sizeof(*opp_table->regulators),
@@ -1392,10 +1376,8 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 {
 	int i;
 
-	if (!opp_table->regulators) {
-		pr_err("%s: Doesn't have regulators set\n", __func__);
-		return;
-	}
+	if (!opp_table->regulators)
+		goto put_opp_table;
 
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
@@ -1409,6 +1391,7 @@ void dev_pm_opp_put_regulators(struct opp_table *opp_table)
 	opp_table->regulators = NULL;
 	opp_table->regulator_count = 0;
 
+put_opp_table:
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_put_regulators);
@@ -1494,7 +1477,6 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 			int (*set_opp)(struct dev_pm_set_opp_data *data))
 {
 	struct opp_table *opp_table;
-	int ret;
 
 	if (!set_opp)
 		return ERR_PTR(-EINVAL);
@@ -1505,24 +1487,15 @@ struct opp_table *dev_pm_opp_register_set_opp_helper(struct device *dev,
 
 	/* This should be called before OPPs are initialized */
 	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	/* Already have custom set_opp helper */
-	if (WARN_ON(opp_table->set_opp)) {
-		ret = -EBUSY;
-		goto err;
+		dev_pm_opp_put_opp_table(opp_table);
+		return ERR_PTR(-EBUSY);
 	}
 
-	opp_table->set_opp = set_opp;
+	/* Another CPU that shares the OPP table has set the helper ? */
+	if (!opp_table->set_opp)
+		opp_table->set_opp = set_opp;
 
 	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
 
@@ -1535,97 +1508,15 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_register_set_opp_helper);
  */
 void dev_pm_opp_unregister_set_opp_helper(struct opp_table *opp_table)
 {
-	if (!opp_table->set_opp) {
-		pr_err("%s: Doesn't have custom set_opp helper set\n",
-		       __func__);
-		return;
-	}
-
 	/* Make sure there are no concurrent readers while updating opp_table */
 	WARN_ON(!list_empty(&opp_table->opp_list));
 
 	opp_table->set_opp = NULL;
-
 	dev_pm_opp_put_opp_table(opp_table);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_set_opp_helper);
 
 /**
- * dev_pm_opp_register_get_pstate_helper() - Register get_pstate() helper.
- * @dev: Device for which the helper is getting registered.
- * @get_pstate: Helper.
- *
- * TODO: Remove this callback after the same information is available via Device
- * Tree.
- *
- * This allows a platform to initialize the performance states of individual
- * OPPs for its devices, until we get similar information directly from DT.
- *
- * This must be called before the OPPs are initialized for the device.
- */
-struct opp_table *dev_pm_opp_register_get_pstate_helper(struct device *dev,
-		int (*get_pstate)(struct device *dev, unsigned long rate))
-{
-	struct opp_table *opp_table;
-	int ret;
-
-	if (!get_pstate)
-		return ERR_PTR(-EINVAL);
-
-	opp_table = dev_pm_opp_get_opp_table(dev);
-	if (!opp_table)
-		return ERR_PTR(-ENOMEM);
-
-	/* This should be called before OPPs are initialized */
-	if (WARN_ON(!list_empty(&opp_table->opp_list))) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	/* Already have genpd_performance_state set */
-	if (WARN_ON(opp_table->genpd_performance_state)) {
-		ret = -EBUSY;
-		goto err;
-	}
-
-	opp_table->genpd_performance_state = true;
-	opp_table->get_pstate = get_pstate;
-
-	return opp_table;
-
-err:
-	dev_pm_opp_put_opp_table(opp_table);
-
-	return ERR_PTR(ret);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_register_get_pstate_helper);
-
-/**
- * dev_pm_opp_unregister_get_pstate_helper() - Releases resources blocked for
- *					   get_pstate() helper
- * @opp_table: OPP table returned from dev_pm_opp_register_get_pstate_helper().
- *
- * Release resources blocked for platform specific get_pstate() helper.
- */
-void dev_pm_opp_unregister_get_pstate_helper(struct opp_table *opp_table)
-{
-	if (!opp_table->genpd_performance_state) {
-		pr_err("%s: Doesn't have performance states set\n",
-		       __func__);
-		return;
-	}
-
-	/* Make sure there are no concurrent readers while updating opp_table */
-	WARN_ON(!list_empty(&opp_table->opp_list));
-
-	opp_table->genpd_performance_state = false;
-	opp_table->get_pstate = NULL;
-
-	dev_pm_opp_put_opp_table(opp_table);
-}
-EXPORT_SYMBOL_GPL(dev_pm_opp_unregister_get_pstate_helper);
-
-/**
  * dev_pm_opp_add()  - Add an OPP table from a table definitions
  * @dev:	device for which we do this operation
  * @freq:	Frequency in Hz for this OPP
diff --git a/drivers/opp/debugfs.c b/drivers/opp/debugfs.c
index b03c03576a62..e6828e5f81b0 100644
--- a/drivers/opp/debugfs.c
+++ b/drivers/opp/debugfs.c
@@ -77,10 +77,21 @@ int opp_debug_create_one(struct dev_pm_opp *opp, struct opp_table *opp_table)
 {
 	struct dentry *pdentry = opp_table->dentry;
 	struct dentry *d;
+	unsigned long id;
 	char name[25];	/* 20 chars for 64 bit value + 5 (opp:\0) */
 
-	/* Rate is unique to each OPP, use it to give opp-name */
-	snprintf(name, sizeof(name), "opp:%lu", opp->rate);
+	/*
+	 * Get directory name for OPP.
+	 *
+	 * - Normally rate is unique to each OPP, use it to get unique opp-name.
+	 * - For some devices rate isn't available, use index instead.
+	 */
+	if (likely(opp->rate))
+		id = opp->rate;
+	else
+		id = _get_opp_count(opp_table);
+
+	snprintf(name, sizeof(name), "opp:%lu", id);
 
 	/* Create per-opp directory */
 	d = debugfs_create_dir(name, pdentry);
diff --git a/drivers/opp/of.c b/drivers/opp/of.c
index cb716aa2f44b..7af0ddec936b 100644
--- a/drivers/opp/of.c
+++ b/drivers/opp/of.c
@@ -17,6 +17,7 @@
 #include <linux/errno.h>
 #include <linux/device.h>
 #include <linux/of_device.h>
+#include <linux/pm_domain.h>
 #include <linux/slab.h>
 #include <linux/export.h>
 
@@ -250,20 +251,17 @@ EXPORT_SYMBOL_GPL(dev_pm_opp_of_remove_table);
 
 /* Returns opp descriptor node for a device node, caller must
  * do of_node_put() */
-static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np)
+static struct device_node *_opp_of_get_opp_desc_node(struct device_node *np,
+						     int index)
 {
-	/*
-	 * There should be only ONE phandle present in "operating-points-v2"
-	 * property.
-	 */
-
-	return of_parse_phandle(np, "operating-points-v2", 0);
+	/* "operating-points-v2" can be an array for power domain providers */
+	return of_parse_phandle(np, "operating-points-v2", index);
 }
 
 /* Returns opp descriptor node for a device, caller must do of_node_put() */
 struct device_node *dev_pm_opp_of_get_opp_desc_node(struct device *dev)
 {
-	return _opp_of_get_opp_desc_node(dev->of_node);
+	return _opp_of_get_opp_desc_node(dev->of_node, 0);
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_opp_desc_node);
 
@@ -289,9 +287,10 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 			      struct device_node *np)
 {
 	struct dev_pm_opp *new_opp;
-	u64 rate;
+	u64 rate = 0;
 	u32 val;
 	int ret;
+	bool rate_not_available = false;
 
 	new_opp = _opp_allocate(opp_table);
 	if (!new_opp)
@@ -299,8 +298,21 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 
 	ret = of_property_read_u64(np, "opp-hz", &rate);
 	if (ret < 0) {
-		dev_err(dev, "%s: opp-hz not found\n", __func__);
-		goto free_opp;
+		/* "opp-hz" is optional for devices like power domains. */
+		if (!of_find_property(dev->of_node, "#power-domain-cells",
+				      NULL)) {
+			dev_err(dev, "%s: opp-hz not found\n", __func__);
+			goto free_opp;
+		}
+
+		rate_not_available = true;
+	} else {
+		/*
+		 * Rate is defined as an unsigned long in clk API, and so
+		 * casting explicitly to its type. Must be fixed once rate is 64
+		 * bit guaranteed in clk API.
+		 */
+		new_opp->rate = (unsigned long)rate;
 	}
 
 	/* Check if the OPP supports hardware's hierarchy of versions or not */
@@ -309,12 +321,6 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 		goto free_opp;
 	}
 
-	/*
-	 * Rate is defined as an unsigned long in clk API, and so casting
-	 * explicitly to its type. Must be fixed once rate is 64 bit
-	 * guaranteed in clk API.
-	 */
-	new_opp->rate = (unsigned long)rate;
 	new_opp->turbo = of_property_read_bool(np, "turbo-mode");
 
 	new_opp->np = np;
@@ -324,11 +330,13 @@ static int _opp_add_static_v2(struct opp_table *opp_table, struct device *dev,
 	if (!of_property_read_u32(np, "clock-latency-ns", &val))
 		new_opp->clock_latency_ns = val;
 
+	new_opp->pstate = of_genpd_opp_to_performance_state(dev, np);
+
 	ret = opp_parse_supplies(new_opp, dev, opp_table);
 	if (ret)
 		goto free_opp;
 
-	ret = _opp_add(dev, new_opp, opp_table);
+	ret = _opp_add(dev, new_opp, opp_table, rate_not_available);
 	if (ret) {
 		/* Don't return error for duplicate OPPs */
 		if (ret == -EBUSY)
@@ -374,7 +382,8 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 {
 	struct device_node *np;
 	struct opp_table *opp_table;
-	int ret = 0, count = 0;
+	int ret = 0, count = 0, pstate_count = 0;
+	struct dev_pm_opp *opp;
 
 	opp_table = _managed_opp(opp_np);
 	if (opp_table) {
@@ -408,6 +417,20 @@ static int _of_add_opp_table_v2(struct device *dev, struct device_node *opp_np)
 		goto put_opp_table;
 	}
 
+	list_for_each_entry(opp, &opp_table->opp_list, node)
+		pstate_count += !!opp->pstate;
+
+	/* Either all or none of the nodes shall have performance state set */
+	if (pstate_count && pstate_count != count) {
+		dev_err(dev, "Not all nodes have performance state set (%d: %d)\n",
+			count, pstate_count);
+		ret = -ENOENT;
+		goto put_opp_table;
+	}
+
+	if (pstate_count)
+		opp_table->genpd_performance_state = true;
+
 	opp_table->np = opp_np;
 	if (of_property_read_bool(opp_np, "opp-shared"))
 		opp_table->shared_opp = OPP_TABLE_ACCESS_SHARED;
@@ -509,6 +532,54 @@ int dev_pm_opp_of_add_table(struct device *dev)
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table);
 
+/**
+ * dev_pm_opp_of_add_table_indexed() - Initialize indexed opp table from device tree
+ * @dev:	device pointer used to lookup OPP table.
+ * @index:	Index number.
+ *
+ * Register the initial OPP table with the OPP library for given device only
+ * using the "operating-points-v2" property.
+ *
+ * Return:
+ * 0		On success OR
+ *		Duplicate OPPs (both freq and volt are same) and opp->available
+ * -EEXIST	Freq are same and volt are different OR
+ *		Duplicate OPPs (both freq and volt are same) and !opp->available
+ * -ENOMEM	Memory allocation failure
+ * -ENODEV	when 'operating-points' property is not found or is invalid data
+ *		in device node.
+ * -ENODATA	when empty 'operating-points' property is found
+ * -EINVAL	when invalid entries are found in opp-v2 table
+ */
+int dev_pm_opp_of_add_table_indexed(struct device *dev, int index)
+{
+	struct device_node *opp_np;
+	int ret, count;
+
+again:
+	opp_np = _opp_of_get_opp_desc_node(dev->of_node, index);
+	if (!opp_np) {
+		/*
+		 * If only one phandle is present, then the same OPP table
+		 * applies for all index requests.
+		 */
+		count = of_count_phandle_with_args(dev->of_node,
+						   "operating-points-v2", NULL);
+		if (count == 1 && index) {
+			index = 0;
+			goto again;
+		}
+
+		return -ENODEV;
+	}
+
+	ret = _of_add_opp_table_v2(dev, opp_np);
+	of_node_put(opp_np);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_of_add_table_indexed);
+
 /* CPU device specific helpers */
 
 /**
@@ -613,7 +684,7 @@ int dev_pm_opp_of_get_sharing_cpus(struct device *cpu_dev,
 		}
 
 		/* Get OPP descriptor node */
-		tmp_np = _opp_of_get_opp_desc_node(cpu_np);
+		tmp_np = _opp_of_get_opp_desc_node(cpu_np, 0);
 		of_node_put(cpu_np);
 		if (!tmp_np) {
 			pr_err("%pOF: Couldn't find opp node\n", cpu_np);
@@ -633,3 +704,76 @@ put_cpu_node:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dev_pm_opp_of_get_sharing_cpus);
+
+/**
+ * of_dev_pm_opp_find_required_opp() - Search for required OPP.
+ * @dev: The device whose OPP node is referenced by the 'np' DT node.
+ * @np: Node that contains the "required-opps" property.
+ *
+ * Returns the OPP of the device 'dev', whose phandle is present in the "np"
+ * node. Although the "required-opps" property supports having multiple
+ * phandles, this helper routine only parses the very first phandle in the list.
+ *
+ * Return: Matching opp, else returns ERR_PTR in case of error and should be
+ * handled using IS_ERR.
+ *
+ * The callers are required to call dev_pm_opp_put() for the returned OPP after
+ * use.
+ */
+struct dev_pm_opp *of_dev_pm_opp_find_required_opp(struct device *dev,
+						   struct device_node *np)
+{
+	struct dev_pm_opp *temp_opp, *opp = ERR_PTR(-ENODEV);
+	struct device_node *required_np;
+	struct opp_table *opp_table;
+
+	opp_table = _find_opp_table(dev);
+	if (IS_ERR(opp_table))
+		return ERR_CAST(opp_table);
+
+	required_np = of_parse_phandle(np, "required-opps", 0);
+	if (unlikely(!required_np)) {
+		dev_err(dev, "Unable to parse required-opps\n");
+		goto put_opp_table;
+	}
+
+	mutex_lock(&opp_table->lock);
+
+	list_for_each_entry(temp_opp, &opp_table->opp_list, node) {
+		if (temp_opp->available && temp_opp->np == required_np) {
+			opp = temp_opp;
+
+			/* Increment the reference count of OPP */
+			dev_pm_opp_get(opp);
+			break;
+		}
+	}
+
+	mutex_unlock(&opp_table->lock);
+
+	of_node_put(required_np);
+put_opp_table:
+	dev_pm_opp_put_opp_table(opp_table);
+
+	return opp;
+}
+EXPORT_SYMBOL_GPL(of_dev_pm_opp_find_required_opp);
+
+/**
+ * dev_pm_opp_get_of_node() - Gets the DT node corresponding to an opp
+ * @opp:	opp for which DT node has to be returned for
+ *
+ * Return: DT node corresponding to the opp, else 0 on success.
+ *
+ * The caller needs to put the node with of_node_put() after using it.
+ */
+struct device_node *dev_pm_opp_get_of_node(struct dev_pm_opp *opp)
+{
+	if (IS_ERR_OR_NULL(opp)) {
+		pr_err("%s: Invalid parameters\n", __func__);
+		return NULL;
+	}
+
+	return of_node_get(opp->np);
+}
+EXPORT_SYMBOL_GPL(dev_pm_opp_get_of_node);
diff --git a/drivers/opp/opp.h b/drivers/opp/opp.h
index 4d00061648a3..7c540fd063b2 100644
--- a/drivers/opp/opp.h
+++ b/drivers/opp/opp.h
@@ -140,7 +140,6 @@ enum opp_table_access {
  * @genpd_performance_state: Device's power domain support performance state.
  * @set_opp: Platform specific set_opp callback
  * @set_opp_data: Data to be passed to set_opp callback
- * @get_pstate: Platform specific get_pstate callback
  * @dentry:	debugfs dentry pointer of the real device directory (not links).
  * @dentry_name: Name of the real dentry.
  *
@@ -178,7 +177,6 @@ struct opp_table {
 
 	int (*set_opp)(struct dev_pm_set_opp_data *data);
 	struct dev_pm_set_opp_data *set_opp_data;
-	int (*get_pstate)(struct device *dev, unsigned long rate);
 
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *dentry;
@@ -187,14 +185,16 @@ struct opp_table {
 };
 
 /* Routines internal to opp core */
+void dev_pm_opp_get(struct dev_pm_opp *opp);
 void _get_opp_table_kref(struct opp_table *opp_table);
+int _get_opp_count(struct opp_table *opp_table);
 struct opp_table *_find_opp_table(struct device *dev);
 struct opp_device *_add_opp_dev(const struct device *dev, struct opp_table *opp_table);
 void _dev_pm_opp_remove_table(struct opp_table *opp_table, struct device *dev, bool remove_all);
 void _dev_pm_opp_find_and_remove_table(struct device *dev, bool remove_all);
 struct dev_pm_opp *_opp_allocate(struct opp_table *opp_table);
 void _opp_free(struct dev_pm_opp *opp);
-int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table);
+int _opp_add(struct device *dev, struct dev_pm_opp *new_opp, struct opp_table *opp_table, bool rate_not_available);
 int _opp_add_v1(struct opp_table *opp_table, struct device *dev, unsigned long freq, long u_volt, bool dynamic);
 void _dev_pm_opp_cpumask_remove_table(const struct cpumask *cpumask, bool of);
 struct opp_table *_add_opp_table(struct device *dev);
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index f8269a725667..18ba62c76480 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -755,10 +755,11 @@ static int pci_pm_suspend(struct device *dev)
 	 * better to resume the device from runtime suspend here.
 	 */
 	if (!dev_pm_test_driver_flags(dev, DPM_FLAG_SMART_SUSPEND) ||
-	    !pci_dev_keep_suspended(pci_dev))
+	    !pci_dev_keep_suspended(pci_dev)) {
 		pm_runtime_resume(dev);
+		pci_dev->state_saved = false;
+	}
 
-	pci_dev->state_saved = false;
 	if (pm->suspend) {
 		pci_power_t prev = pci_dev->current_state;
 		int error;
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index dbfe7c4f3776..e90cf5c32e14 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2025,8 +2025,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 
 	if (platform_pci_power_manageable(dev)) {
 		/*
-		 * Call the platform to choose the target state of the device
-		 * and enable wake-up from this state if supported.
+		 * Call the platform to find the target state for the device.
 		 */
 		pci_power_t state = platform_pci_choose_state(dev);
 
@@ -2059,8 +2058,7 @@ static pci_power_t pci_target_state(struct pci_dev *dev, bool wakeup)
 	if (wakeup) {
 		/*
 		 * Find the deepest state from which the device can generate
-		 * wake-up events, make it the target state and enable device
-		 * to generate PME#.
+		 * PME#.
 		 */
 		if (dev->pme_support) {
 			while (target_state
diff --git a/drivers/power/avs/rockchip-io-domain.c b/drivers/power/avs/rockchip-io-domain.c
index ed2b109ae8fc..d6a5e6bf5f12 100644
--- a/drivers/power/avs/rockchip-io-domain.c
+++ b/drivers/power/avs/rockchip-io-domain.c
@@ -39,6 +39,10 @@
 #define MAX_VOLTAGE_1_8		1980000
 #define MAX_VOLTAGE_3_3		3600000
 
+#define PX30_IO_VSEL			0x180
+#define PX30_IO_VSEL_VCCIO6_SRC		BIT(0)
+#define PX30_IO_VSEL_VCCIO6_SUPPLY_NUM	1
+
 #define RK3288_SOC_CON2			0x24c
 #define RK3288_SOC_CON2_FLASH0		BIT(7)
 #define RK3288_SOC_FLASH_SUPPLY_NUM	2
@@ -151,6 +155,25 @@ static int rockchip_iodomain_notify(struct notifier_block *nb,
 	return NOTIFY_OK;
 }
 
+static void px30_iodomain_init(struct rockchip_iodomain *iod)
+{
+	int ret;
+	u32 val;
+
+	/* if no VCCIO0 supply we should leave things alone */
+	if (!iod->supplies[PX30_IO_VSEL_VCCIO6_SUPPLY_NUM].reg)
+		return;
+
+	/*
+	 * set vccio0 iodomain to also use this framework
+	 * instead of a special gpio.
+	 */
+	val = PX30_IO_VSEL_VCCIO6_SRC | (PX30_IO_VSEL_VCCIO6_SRC << 16);
+	ret = regmap_write(iod->grf, PX30_IO_VSEL, val);
+	if (ret < 0)
+		dev_warn(iod->dev, "couldn't update vccio0 ctrl\n");
+}
+
 static void rk3288_iodomain_init(struct rockchip_iodomain *iod)
 {
 	int ret;
@@ -227,6 +250,43 @@ static void rk3399_pmu_iodomain_init(struct rockchip_iodomain *iod)
 		dev_warn(iod->dev, "couldn't update pmu io iodomain ctrl\n");
 }
 
+static const struct rockchip_iodomain_soc_data soc_data_px30 = {
+	.grf_offset = 0x180,
+	.supply_names = {
+		NULL,
+		"vccio6",
+		"vccio1",
+		"vccio2",
+		"vccio3",
+		"vccio4",
+		"vccio5",
+		"vccio-oscgpi",
+	},
+	.init = px30_iodomain_init,
+};
+
+static const struct rockchip_iodomain_soc_data soc_data_px30_pmu = {
+	.grf_offset = 0x100,
+	.supply_names = {
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		NULL,
+		"pmuio1",
+		"pmuio2",
+	},
+};
+
 /*
  * On the rk3188 the io-domains are handled by a shared register with the
  * lower 8 bits being still being continuing drive-strength settings.
@@ -381,6 +441,14 @@ static const struct rockchip_iodomain_soc_data soc_data_rv1108_pmu = {
 
 static const struct of_device_id rockchip_iodomain_match[] = {
 	{
+		.compatible = "rockchip,px30-io-voltage-domain",
+		.data = (void *)&soc_data_px30
+	},
+	{
+		.compatible = "rockchip,px30-pmu-io-voltage-domain",
+		.data = (void *)&soc_data_px30_pmu
+	},
+	{
 		.compatible = "rockchip,rk3188-io-voltage-domain",
 		.data = &soc_data_rk3188
 	},
diff --git a/drivers/soc/tegra/pmc.c b/drivers/soc/tegra/pmc.c
index d9fcdb592b39..3e3d12ce4587 100644
--- a/drivers/soc/tegra/pmc.c
+++ b/drivers/soc/tegra/pmc.c
@@ -559,22 +559,28 @@ EXPORT_SYMBOL(tegra_powergate_remove_clamping);
 int tegra_powergate_sequence_power_up(unsigned int id, struct clk *clk,
 				      struct reset_control *rst)
 {
-	struct tegra_powergate pg;
+	struct tegra_powergate *pg;
 	int err;
 
 	if (!tegra_powergate_is_available(id))
 		return -EINVAL;
 
-	pg.id = id;
-	pg.clks = &clk;
-	pg.num_clks = 1;
-	pg.reset = rst;
-	pg.pmc = pmc;
+	pg = kzalloc(sizeof(*pg), GFP_KERNEL);
+	if (!pg)
+		return -ENOMEM;
 
-	err = tegra_powergate_power_up(&pg, false);
+	pg->id = id;
+	pg->clks = &clk;
+	pg->num_clks = 1;
+	pg->reset = rst;
+	pg->pmc = pmc;
+
+	err = tegra_powergate_power_up(pg, false);
 	if (err)
 		pr_err("failed to turn on partition %d: %d\n", id, err);
 
+	kfree(pg);
+
 	return err;
 }
 EXPORT_SYMBOL(tegra_powergate_sequence_power_up);
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index d5f3a70c06b0..283b2832728e 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -83,17 +83,16 @@ static int sdw_drv_probe(struct device *dev)
 	 * attach to power domain but don't turn on (last arg)
 	 */
 	ret = dev_pm_domain_attach(dev, false);
-	if (ret != -EPROBE_DEFER) {
-		ret = drv->probe(slave, id);
-		if (ret) {
-			dev_err(dev, "Probe of %s failed: %d\n", drv->name, ret);
-			dev_pm_domain_detach(dev, false);
-		}
-	}
-
 	if (ret)
 		return ret;
 
+	ret = drv->probe(slave, id);
+	if (ret) {
+		dev_err(dev, "Probe of %s failed: %d\n", drv->name, ret);
+		dev_pm_domain_detach(dev, false);
+		return ret;
+	}
+
 	/* device is probed so let's read the properties now */
 	if (slave->ops && slave->ops->read_prop)
 		slave->ops->read_prop(slave);
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 20b5b2754830..efc624f9e490 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -359,11 +359,12 @@ static int spi_drv_probe(struct device *dev)
 	}
 
 	ret = dev_pm_domain_attach(dev, true);
-	if (ret != -EPROBE_DEFER) {
-		ret = sdrv->probe(spi);
-		if (ret)
-			dev_pm_domain_detach(dev, true);
-	}
+	if (ret)
+		return ret;
+
+	ret = sdrv->probe(spi);
+	if (ret)
+		dev_pm_domain_detach(dev, true);
 
 	return ret;
 }