18 files changed, 617 insertions, 126 deletions

diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index c945bed4dc9e..eba9cb10619c 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -66,6 +66,54 @@ static struct notifier_block ioda_eeh_nb = {
 };
 
 #ifdef CONFIG_DEBUG_FS
+static ssize_t ioda_eeh_ei_write(struct file *filp,
+				 const char __user *user_buf,
+				 size_t count, loff_t *ppos)
+{
+	struct pci_controller *hose = filp->private_data;
+	struct pnv_phb *phb = hose->private_data;
+	struct eeh_dev *edev;
+	struct eeh_pe *pe;
+	int pe_no, type, func;
+	unsigned long addr, mask;
+	char buf[50];
+	int ret;
+
+	if (!phb->eeh_ops || !phb->eeh_ops->err_inject)
+		return -ENXIO;
+
+	ret = simple_write_to_buffer(buf, sizeof(buf), ppos, user_buf, count);
+	if (!ret)
+		return -EFAULT;
+
+	/* Retrieve parameters */
+	ret = sscanf(buf, "%x:%x:%x:%lx:%lx",
+		     &pe_no, &type, &func, &addr, &mask);
+	if (ret != 5)
+		return -EINVAL;
+
+	/* Retrieve PE */
+	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+	if (!edev)
+		return -ENOMEM;
+	edev->phb = hose;
+	edev->pe_config_addr = pe_no;
+	pe = eeh_pe_get(edev);
+	kfree(edev);
+	if (!pe)
+		return -ENODEV;
+
+	/* Do error injection */
+	ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask);
+	return ret < 0 ? ret : count;
+}
+
+static const struct file_operations ioda_eeh_ei_fops = {
+	.open   = simple_open,
+	.llseek = no_llseek,
+	.write  = ioda_eeh_ei_write,
+};
+
 static int ioda_eeh_dbgfs_set(void *data, int offset, u64 val)
 {
 	struct pci_controller *hose = data;
@@ -152,6 +200,10 @@ static int ioda_eeh_post_init(struct pci_controller *hose)
 	if (!phb->has_dbgfs && phb->dbgfs) {
 		phb->has_dbgfs = 1;
 
+		debugfs_create_file("err_injct", 0200,
+				    phb->dbgfs, hose,
+				    &ioda_eeh_ei_fops);
+
 		debugfs_create_file("err_injct_outbound", 0600,
 				    phb->dbgfs, hose,
 				    &ioda_eeh_outb_dbgfs_ops);
@@ -189,6 +241,7 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 {
 	struct pci_controller *hose = pe->phb;
 	struct pnv_phb *phb = hose->private_data;
+	bool freeze_pe = false;
 	int enable, ret = 0;
 	s64 rc;
 
@@ -212,6 +265,10 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	case EEH_OPT_THAW_DMA:
 		enable = OPAL_EEH_ACTION_CLEAR_FREEZE_DMA;
 		break;
+	case EEH_OPT_FREEZE_PE:
+		freeze_pe = true;
+		enable = OPAL_EEH_ACTION_SET_FREEZE_ALL;
+		break;
 	default:
 		pr_warn("%s: Invalid option %d\n",
 			__func__, option);
@@ -219,17 +276,35 @@ static int ioda_eeh_set_option(struct eeh_pe *pe, int option)
 	}
 
 	/* If PHB supports compound PE, to handle it */
-	if (phb->unfreeze_pe) {
-		ret = phb->unfreeze_pe(phb, pe->addr, enable);
+	if (freeze_pe) {
+		if (phb->freeze_pe) {
+			phb->freeze_pe(phb, pe->addr);
+		} else {
+			rc = opal_pci_eeh_freeze_set(phb->opal_id,
+						     pe->addr,
+						     enable);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld freezing "
+					"PHB#%x-PE#%x\n",
+					__func__, rc,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
+		}
 	} else {
-		rc = opal_pci_eeh_freeze_clear(phb->opal_id,
-					       pe->addr,
-					       enable);
-		if (rc != OPAL_SUCCESS) {
-			pr_warn("%s: Failure %lld enable %d for PHB#%x-PE#%x\n",
-				__func__, rc, option, phb->hose->global_number,
-				pe->addr);
-			ret = -EIO;
+		if (phb->unfreeze_pe) {
+			ret = phb->unfreeze_pe(phb, pe->addr, enable);
+		} else {
+			rc = opal_pci_eeh_freeze_clear(phb->opal_id,
+						       pe->addr,
+						       enable);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld enable %d "
+					"for PHB#%x-PE#%x\n",
+					__func__, rc, option,
+					phb->hose->global_number, pe->addr);
+				ret = -EIO;
+			}
 		}
 	}
 
@@ -298,7 +373,7 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 	 * moving forward, we have to return operational
 	 * state during PE reset.
 	 */
-	if (pe->state & EEH_PE_RESET) {
+	if (pe->state & EEH_PE_CFG_BLOCKED) {
 		result = (EEH_STATE_MMIO_ACTIVE  |
 			  EEH_STATE_DMA_ACTIVE   |
 			  EEH_STATE_MMIO_ENABLED |
@@ -439,11 +514,11 @@ int ioda_eeh_phb_reset(struct pci_controller *hose, int option)
 	if (option == EEH_RESET_FUNDAMENTAL ||
 	    option == EEH_RESET_HOT)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PHB_COMPLETE,
+				OPAL_RESET_PHB_COMPLETE,
 				OPAL_ASSERT_RESET);
 	else if (option == EEH_RESET_DEACTIVATE)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PHB_COMPLETE,
+				OPAL_RESET_PHB_COMPLETE,
 				OPAL_DEASSERT_RESET);
 	if (rc < 0)
 		goto out;
@@ -483,15 +558,15 @@ static int ioda_eeh_root_reset(struct pci_controller *hose, int option)
 	 */
 	if (option == EEH_RESET_FUNDAMENTAL)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PCI_FUNDAMENTAL_RESET,
+				OPAL_RESET_PCI_FUNDAMENTAL,
 				OPAL_ASSERT_RESET);
 	else if (option == EEH_RESET_HOT)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PCI_HOT_RESET,
+				OPAL_RESET_PCI_HOT,
 				OPAL_ASSERT_RESET);
 	else if (option == EEH_RESET_DEACTIVATE)
 		rc = opal_pci_reset(phb->opal_id,
-				OPAL_PCI_HOT_RESET,
+				OPAL_RESET_PCI_HOT,
 				OPAL_DEASSERT_RESET);
 	if (rc < 0)
 		goto out;
@@ -607,6 +682,31 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 	if (pe->type & EEH_PE_PHB) {
 		ret = ioda_eeh_phb_reset(hose, option);
 	} else {
+		struct pnv_phb *phb;
+		s64 rc;
+
+		/*
+		 * The frozen PE might be caused by PAPR error injection
+		 * registers, which are expected to be cleared after hitting
+		 * frozen PE as stated in the hardware spec. Unfortunately,
+		 * that's not true on P7IOC. So we have to clear it manually
+		 * to avoid recursive EEH errors during recovery.
+		 */
+		phb = hose->private_data;
+		if (phb->model == PNV_PHB_MODEL_P7IOC &&
+		    (option == EEH_RESET_HOT ||
+		    option == EEH_RESET_FUNDAMENTAL)) {
+			rc = opal_pci_reset(phb->opal_id,
+					    OPAL_RESET_PHB_ERROR,
+					    OPAL_ASSERT_RESET);
+			if (rc != OPAL_SUCCESS) {
+				pr_warn("%s: Failure %lld clearing "
+					"error injection registers\n",
+					__func__, rc);
+				return -EIO;
+			}
+		}
+
 		bus = eeh_pe_bus_get(pe);
 		if (pci_is_root_bus(bus) ||
 		    pci_is_root_bus(bus->parent))
@@ -628,8 +728,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
  * Retrieve error log, which contains log from device driver
  * and firmware.
  */
-int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
-		     char *drv_log, unsigned long len)
+static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
+			    char *drv_log, unsigned long len)
 {
 	pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
@@ -650,6 +750,49 @@ static int ioda_eeh_configure_bridge(struct eeh_pe *pe)
 	return 0;
 }
 
+static int ioda_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+			       unsigned long addr, unsigned long mask)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	s64 ret;
+
+	/* Sanity check on error type */
+	if (type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR &&
+	    type != OPAL_ERR_INJECT_TYPE_IOA_BUS_ERR64) {
+		pr_warn("%s: Invalid error type %d\n",
+			__func__, type);
+		return -ERANGE;
+	}
+
+	if (func < OPAL_ERR_INJECT_FUNC_IOA_LD_MEM_ADDR ||
+	    func > OPAL_ERR_INJECT_FUNC_IOA_DMA_WR_TARGET) {
+		pr_warn("%s: Invalid error function %d\n",
+			__func__, func);
+		return -ERANGE;
+	}
+
+	/* Firmware supports error injection ? */
+	if (!opal_check_token(OPAL_PCI_ERR_INJECT)) {
+		pr_warn("%s: Firmware doesn't support error injection\n",
+			__func__);
+		return -ENXIO;
+	}
+
+	/* Do error injection */
+	ret = opal_pci_err_inject(phb->opal_id, pe->addr,
+				  type, func, addr, mask);
+	if (ret != OPAL_SUCCESS) {
+		pr_warn("%s: Failure %lld injecting error "
+			"%d-%d to PHB#%x-PE#%x\n",
+			__func__, ret, type, func,
+			hose->global_number, pe->addr);
+		return -EIO;
+	}
+
+	return 0;
+}
+
 static void ioda_eeh_hub_diag_common(struct OpalIoP7IOCErrorData *data)
 {
 	/* GEM */
@@ -743,14 +886,12 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	 * the master PE because slave PE is invisible
 	 * to EEH core.
 	 */
-	if (phb->get_pe_state) {
-		pnv_pe = &phb->ioda.pe_array[pe_no];
-		if (pnv_pe->flags & PNV_IODA_PE_SLAVE) {
-			pnv_pe = pnv_pe->master;
-			WARN_ON(!pnv_pe ||
-				!(pnv_pe->flags & PNV_IODA_PE_MASTER));
-			pe_no = pnv_pe->pe_number;
-		}
+	pnv_pe = &phb->ioda.pe_array[pe_no];
+	if (pnv_pe->flags & PNV_IODA_PE_SLAVE) {
+		pnv_pe = pnv_pe->master;
+		WARN_ON(!pnv_pe ||
+			!(pnv_pe->flags & PNV_IODA_PE_MASTER));
+		pe_no = pnv_pe->pe_number;
 	}
 
 	/* Find the PE according to PE# */
@@ -761,15 +902,37 @@ static int ioda_eeh_get_pe(struct pci_controller *hose,
 	if (!dev_pe)
 		return -EEXIST;
 
-	/*
-	 * At this point, we're sure the compound PE should
-	 * be put into frozen state.
-	 */
+	/* Freeze the (compound) PE */
 	*pe = dev_pe;
-	if (phb->freeze_pe &&
-	    !(dev_pe->state & EEH_PE_ISOLATED))
+	if (!(dev_pe->state & EEH_PE_ISOLATED))
 		phb->freeze_pe(phb, pe_no);
 
+	/*
+	 * At this point, we're sure the (compound) PE should
+	 * have been frozen. However, we still need poke until
+	 * hitting the frozen PE on top level.
+	 */
+	dev_pe = dev_pe->parent;
+	while (dev_pe && !(dev_pe->type & EEH_PE_PHB)) {
+		int ret;
+		int active_flags = (EEH_STATE_MMIO_ACTIVE |
+				    EEH_STATE_DMA_ACTIVE);
+
+		ret = eeh_ops->get_state(dev_pe, NULL);
+		if (ret <= 0 || (ret & active_flags) == active_flags) {
+			dev_pe = dev_pe->parent;
+			continue;
+		}
+
+		/* Frozen parent PE */
+		*pe = dev_pe;
+		if (!(dev_pe->state & EEH_PE_ISOLATED))
+			phb->freeze_pe(phb, dev_pe->addr);
+
+		/* Next one */
+		dev_pe = dev_pe->parent;
+	}
+
 	return 0;
 }
 
@@ -971,5 +1134,6 @@ struct pnv_eeh_ops ioda_eeh_ops = {
 	.reset			= ioda_eeh_reset,
 	.get_log		= ioda_eeh_get_log,
 	.configure_bridge	= ioda_eeh_configure_bridge,
+	.err_inject		= ioda_eeh_err_inject,
 	.next_error		= ioda_eeh_next_error
 };
diff --git a/arch/powerpc/platforms/powernv/eeh-powernv.c b/arch/powerpc/platforms/powernv/eeh-powernv.c
index fd7a16f855ed..1d19e7917d7f 100644
--- a/arch/powerpc/platforms/powernv/eeh-powernv.c
+++ b/arch/powerpc/platforms/powernv/eeh-powernv.c
@@ -169,6 +169,26 @@ static int powernv_eeh_dev_probe(struct pci_dev *dev, void *flag)
 	}
 
 	/*
+	 * If the PE contains any one of following adapters, the
+	 * PCI config space can't be accessed when dumping EEH log.
+	 * Otherwise, we will run into fenced PHB caused by shortage
+	 * of outbound credits in the adapter. The PCI config access
+	 * should be blocked until PE reset. MMIO access is dropped
+	 * by hardware certainly. In order to drop PCI config requests,
+	 * one more flag (EEH_PE_CFG_RESTRICTED) is introduced, which
+	 * will be checked in the backend for PE state retrival. If
+	 * the PE becomes frozen for the first time and the flag has
+	 * been set for the PE, we will set EEH_PE_CFG_BLOCKED for
+	 * that PE to block its config space.
+	 *
+	 * Broadcom Austin 4-ports NICs (14e4:1657)
+	 * Broadcom Shiner 2-ports 10G NICs (14e4:168e)
+	 */
+	if ((dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x1657) ||
+	    (dev->vendor == PCI_VENDOR_ID_BROADCOM && dev->device == 0x168e))
+		edev->pe->state |= EEH_PE_CFG_RESTRICTED;
+
+	/*
 	 * Cache the PE primary bus, which can't be fetched when
 	 * full hotplug is in progress. In that case, all child
 	 * PCI devices of the PE are expected to be removed prior
@@ -359,6 +379,64 @@ static int powernv_eeh_configure_bridge(struct eeh_pe *pe)
 }
 
 /**
+ * powernv_pe_err_inject - Inject specified error to the indicated PE
+ * @pe: the indicated PE
+ * @type: error type
+ * @func: specific error type
+ * @addr: address
+ * @mask: address mask
+ *
+ * The routine is called to inject specified error, which is
+ * determined by @type and @func, to the indicated PE for
+ * testing purpose.
+ */
+static int powernv_eeh_err_inject(struct eeh_pe *pe, int type, int func,
+				  unsigned long addr, unsigned long mask)
+{
+	struct pci_controller *hose = pe->phb;
+	struct pnv_phb *phb = hose->private_data;
+	int ret = -EEXIST;
+
+	if (phb->eeh_ops && phb->eeh_ops->err_inject)
+		ret = phb->eeh_ops->err_inject(pe, type, func, addr, mask);
+
+	return ret;
+}
+
+static inline bool powernv_eeh_cfg_blocked(struct device_node *dn)
+{
+	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+
+	if (!edev || !edev->pe)
+		return false;
+
+	if (edev->pe->state & EEH_PE_CFG_BLOCKED)
+		return true;
+
+	return false;
+}
+
+static int powernv_eeh_read_config(struct device_node *dn,
+				   int where, int size, u32 *val)
+{
+	if (powernv_eeh_cfg_blocked(dn)) {
+		*val = 0xFFFFFFFF;
+		return PCIBIOS_SET_FAILED;
+	}
+
+	return pnv_pci_cfg_read(dn, where, size, val);
+}
+
+static int powernv_eeh_write_config(struct device_node *dn,
+				    int where, int size, u32 val)
+{
+	if (powernv_eeh_cfg_blocked(dn))
+		return PCIBIOS_SET_FAILED;
+
+	return pnv_pci_cfg_write(dn, where, size, val);
+}
+
+/**
  * powernv_eeh_next_error - Retrieve next EEH error to handle
  * @pe: Affected PE
  *
@@ -414,8 +492,9 @@ static struct eeh_ops powernv_eeh_ops = {
 	.wait_state             = powernv_eeh_wait_state,
 	.get_log                = powernv_eeh_get_log,
 	.configure_bridge       = powernv_eeh_configure_bridge,
-	.read_config            = pnv_pci_cfg_read,
-	.write_config           = pnv_pci_cfg_write,
+	.err_inject		= powernv_eeh_err_inject,
+	.read_config            = powernv_eeh_read_config,
+	.write_config           = powernv_eeh_write_config,
 	.next_error		= powernv_eeh_next_error,
 	.restore_config		= powernv_eeh_restore_config
 };
diff --git a/arch/powerpc/platforms/powernv/opal-dump.c b/arch/powerpc/platforms/powernv/opal-dump.c
index 85bb8fff7947..23260f7dfa7a 100644
--- a/arch/powerpc/platforms/powernv/opal-dump.c
+++ b/arch/powerpc/platforms/powernv/opal-dump.c
@@ -112,7 +112,7 @@ static ssize_t init_dump_show(struct dump_obj *dump_obj,
 			      struct dump_attribute *attr,
 			      char *buf)
 {
-	return sprintf(buf, "1 - initiate dump\n");
+	return sprintf(buf, "1 - initiate Service Processor(FSP) dump\n");
 }
 
 static int64_t dump_fips_init(uint8_t type)
@@ -121,7 +121,7 @@ static int64_t dump_fips_init(uint8_t type)
 
 	rc = opal_dump_init(type);
 	if (rc)
-		pr_warn("%s: Failed to initiate FipS dump (%d)\n",
+		pr_warn("%s: Failed to initiate FSP dump (%d)\n",
 			__func__, rc);
 	return rc;
 }
@@ -131,8 +131,12 @@ static ssize_t init_dump_store(struct dump_obj *dump_obj,
 			       const char *buf,
 			       size_t count)
 {
-	dump_fips_init(DUMP_TYPE_FSP);
-	pr_info("%s: Initiated FSP dump\n", __func__);
+	int rc;
+
+	rc = dump_fips_init(DUMP_TYPE_FSP);
+	if (rc == OPAL_SUCCESS)
+		pr_info("%s: Initiated FSP dump\n", __func__);
+
 	return count;
 }
 
@@ -297,7 +301,7 @@ static ssize_t dump_attr_read(struct file *filep, struct kobject *kobj,
 			 * and rely on userspace to ask us to try
 			 * again.
 			 */
-			pr_info("%s: Platform dump partially read.ID = 0x%x\n",
+			pr_info("%s: Platform dump partially read. ID = 0x%x\n",
 				__func__, dump->id);
 			return -EIO;
 		}
@@ -423,6 +427,10 @@ void __init opal_platform_dump_init(void)
 {
 	int rc;
 
+	/* ELOG not supported by firmware */
+	if (!opal_check_token(OPAL_DUMP_READ))
+		return;
+
 	dump_kset = kset_create_and_add("dump", NULL, opal_kobj);
 	if (!dump_kset) {
 		pr_warn("%s: Failed to create dump kset\n", __func__);
diff --git a/arch/powerpc/platforms/powernv/opal-elog.c b/arch/powerpc/platforms/powernv/opal-elog.c
index bbdb3ffaab98..518fe95dbf24 100644
--- a/arch/powerpc/platforms/powernv/opal-elog.c
+++ b/arch/powerpc/platforms/powernv/opal-elog.c
@@ -295,6 +295,10 @@ int __init opal_elog_init(void)
 {
 	int rc = 0;
 
+	/* ELOG not supported by firmware */
+	if (!opal_check_token(OPAL_ELOG_READ))
+		return -1;
+
 	elog_kset = kset_create_and_add("elog", NULL, opal_kobj);
 	if (!elog_kset) {
 		pr_warn("%s: failed to create elog kset\n", __func__);
diff --git a/arch/powerpc/platforms/powernv/opal-hmi.c b/arch/powerpc/platforms/powernv/opal-hmi.c
index 97ac8dc33667..5e1ed1575aab 100644
--- a/arch/powerpc/platforms/powernv/opal-hmi.c
+++ b/arch/powerpc/platforms/powernv/opal-hmi.c
@@ -28,6 +28,7 @@
 
 #include <asm/opal.h>
 #include <asm/cputable.h>
+#include <asm/machdep.h>
 
 static int opal_hmi_handler_nb_init;
 struct OpalHmiEvtNode {
@@ -185,4 +186,4 @@ static int __init opal_hmi_handler_init(void)
 	}
 	return 0;
 }
-subsys_initcall(opal_hmi_handler_init);
+machine_subsys_initcall(powernv, opal_hmi_handler_init);
diff --git a/arch/powerpc/platforms/powernv/opal-lpc.c b/arch/powerpc/platforms/powernv/opal-lpc.c
index ad4b31df779a..dd2c285ad170 100644
--- a/arch/powerpc/platforms/powernv/opal-lpc.c
+++ b/arch/powerpc/platforms/powernv/opal-lpc.c
@@ -191,6 +191,7 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf,
 {
 	struct lpc_debugfs_entry *lpc = filp->private_data;
 	u32 data, pos, len, todo;
+	__be32 bedata;
 	int rc;
 
 	if (!access_ok(VERIFY_WRITE, ubuf, count))
@@ -213,9 +214,10 @@ static ssize_t lpc_debug_read(struct file *filp, char __user *ubuf,
 				len = 2;
 		}
 		rc = opal_lpc_read(opal_lpc_chip_id, lpc->lpc_type, pos,
-				   &data, len);
+				   &bedata, len);
 		if (rc)
 			return -ENXIO;
+		data = be32_to_cpu(bedata);
 		switch(len) {
 		case 4:
 			rc = __put_user((u32)data, (u32 __user *)ubuf);
diff --git a/arch/powerpc/platforms/powernv/opal-nvram.c b/arch/powerpc/platforms/powernv/opal-nvram.c
index acd9f7e96678..f9896fd5d04a 100644
--- a/arch/powerpc/platforms/powernv/opal-nvram.c
+++ b/arch/powerpc/platforms/powernv/opal-nvram.c
@@ -78,7 +78,7 @@ void __init opal_nvram_init(void)
 	}
 	nvram_size = be32_to_cpup(nbytes_p);
 
-	printk(KERN_INFO "OPAL nvram setup, %u bytes\n", nvram_size);
+	pr_info("OPAL nvram setup, %u bytes\n", nvram_size);
 	of_node_put(np);
 
 	ppc_md.nvram_read = opal_nvram_read;
diff --git a/arch/powerpc/platforms/powernv/opal-rtc.c b/arch/powerpc/platforms/powernv/opal-rtc.c
index b1885db8fdf3..499707ddaa9c 100644
--- a/arch/powerpc/platforms/powernv/opal-rtc.c
+++ b/arch/powerpc/platforms/powernv/opal-rtc.c
@@ -42,6 +42,9 @@ unsigned long __init opal_get_boot_time(void)
 	__be64 __h_m_s_ms;
 	long rc = OPAL_BUSY;
 
+	if (!opal_check_token(OPAL_RTC_READ))
+		goto out;
+
 	while (rc == OPAL_BUSY || rc == OPAL_BUSY_EVENT) {
 		rc = opal_rtc_read(&__y_m_d, &__h_m_s_ms);
 		if (rc == OPAL_BUSY_EVENT)
@@ -49,16 +52,18 @@ unsigned long __init opal_get_boot_time(void)
 		else
 			mdelay(10);
 	}
-	if (rc != OPAL_SUCCESS) {
-		ppc_md.get_rtc_time = NULL;
-		ppc_md.set_rtc_time = NULL;
-		return 0;
-	}
+	if (rc != OPAL_SUCCESS)
+		goto out;
+
 	y_m_d = be32_to_cpu(__y_m_d);
 	h_m_s_ms = be64_to_cpu(__h_m_s_ms);
 	opal_to_tm(y_m_d, h_m_s_ms, &tm);
 	return mktime(tm.tm_year + 1900, tm.tm_mon + 1, tm.tm_mday,
 		      tm.tm_hour, tm.tm_min, tm.tm_sec);
+out:
+	ppc_md.get_rtc_time = NULL;
+	ppc_md.set_rtc_time = NULL;
+	return 0;
 }
 
 void opal_get_rtc_time(struct rtc_time *tm)
diff --git a/arch/powerpc/platforms/powernv/opal-tracepoints.c b/arch/powerpc/platforms/powernv/opal-tracepoints.c
index d8a000a9988b..ae14c40b4b1c 100644
--- a/arch/powerpc/platforms/powernv/opal-tracepoints.c
+++ b/arch/powerpc/platforms/powernv/opal-tracepoints.c
@@ -2,7 +2,7 @@
 #include <linux/jump_label.h>
 #include <asm/trace.h>
 
-#ifdef CONFIG_JUMP_LABEL
+#ifdef HAVE_JUMP_LABEL
 struct static_key opal_tracepoint_key = STATIC_KEY_INIT;
 
 void opal_tracepoint_regfunc(void)
diff --git a/arch/powerpc/platforms/powernv/opal-wrappers.S b/arch/powerpc/platforms/powernv/opal-wrappers.S
index 2e6ce1b8dc8f..e9e2450c1fdd 100644
--- a/arch/powerpc/platforms/powernv/opal-wrappers.S
+++ b/arch/powerpc/platforms/powernv/opal-wrappers.S
@@ -184,6 +184,7 @@ OPAL_CALL(opal_register_exception_handler,	OPAL_REGISTER_OPAL_EXCEPTION_HANDLER)
 OPAL_CALL(opal_pci_eeh_freeze_status,		OPAL_PCI_EEH_FREEZE_STATUS);
 OPAL_CALL(opal_pci_eeh_freeze_clear,		OPAL_PCI_EEH_FREEZE_CLEAR);
 OPAL_CALL(opal_pci_eeh_freeze_set,		OPAL_PCI_EEH_FREEZE_SET);
+OPAL_CALL(opal_pci_err_inject,			OPAL_PCI_ERR_INJECT);
 OPAL_CALL(opal_pci_shpc,			OPAL_PCI_SHPC);
 OPAL_CALL(opal_pci_phb_mmio_enable,		OPAL_PCI_PHB_MMIO_ENABLE);
 OPAL_CALL(opal_pci_set_phb_mem_window,		OPAL_PCI_SET_PHB_MEM_WINDOW);
@@ -232,6 +233,7 @@ OPAL_CALL(opal_validate_flash,			OPAL_FLASH_VALIDATE);
 OPAL_CALL(opal_manage_flash,			OPAL_FLASH_MANAGE);
 OPAL_CALL(opal_update_flash,			OPAL_FLASH_UPDATE);
 OPAL_CALL(opal_resync_timebase,			OPAL_RESYNC_TIMEBASE);
+OPAL_CALL(opal_check_token,			OPAL_CHECK_TOKEN);
 OPAL_CALL(opal_dump_init,			OPAL_DUMP_INIT);
 OPAL_CALL(opal_dump_info,			OPAL_DUMP_INFO);
 OPAL_CALL(opal_dump_info2,			OPAL_DUMP_INFO2);
@@ -247,3 +249,4 @@ OPAL_CALL(opal_set_param,			OPAL_SET_PARAM);
 OPAL_CALL(opal_handle_hmi,			OPAL_HANDLE_HMI);
 OPAL_CALL(opal_register_dump_region,		OPAL_REGISTER_DUMP_REGION);
 OPAL_CALL(opal_unregister_dump_region,		OPAL_UNREGISTER_DUMP_REGION);
+OPAL_CALL(opal_pci_set_phb_cxl_mode,		OPAL_PCI_SET_PHB_CXL_MODE);
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index b44eec3e8dbd..d019b081df9d 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -105,12 +105,12 @@ int __init early_init_dt_scan_opal(unsigned long node,
 	if (of_flat_dt_is_compatible(node, "ibm,opal-v3")) {
 		powerpc_firmware_features |= FW_FEATURE_OPALv2;
 		powerpc_firmware_features |= FW_FEATURE_OPALv3;
-		printk("OPAL V3 detected !\n");
+		pr_info("OPAL V3 detected !\n");
 	} else if (of_flat_dt_is_compatible(node, "ibm,opal-v2")) {
 		powerpc_firmware_features |= FW_FEATURE_OPALv2;
-		printk("OPAL V2 detected !\n");
+		pr_info("OPAL V2 detected !\n");
 	} else {
-		printk("OPAL V1 detected !\n");
+		pr_info("OPAL V1 detected !\n");
 	}
 
 	/* Reinit all cores with the right endian */
@@ -194,6 +194,27 @@ static int __init opal_register_exception_handlers(void)
 	 * fwnmi area at 0x7000 to provide the glue space to OPAL
 	 */
 	glue = 0x7000;
+
+	/*
+	 * Check if we are running on newer firmware that exports
+	 * OPAL_HANDLE_HMI token. If yes, then don't ask OPAL to patch
+	 * the HMI interrupt and we catch it directly in Linux.
+	 *
+	 * For older firmware (i.e currently released POWER8 System Firmware
+	 * as of today <= SV810_087), we fallback to old behavior and let OPAL
+	 * patch the HMI vector and handle it inside OPAL firmware.
+	 *
+	 * For newer firmware (in development/yet to be released) we will
+	 * start catching/handling HMI directly in Linux.
+	 */
+	if (!opal_check_token(OPAL_HANDLE_HMI)) {
+		pr_info("opal: Old firmware detected, OPAL handles HMIs.\n");
+		opal_register_exception_handler(
+				OPAL_HYPERVISOR_MAINTENANCE_HANDLER,
+				0, glue);
+		glue += 128;
+	}
+
 	opal_register_exception_handler(OPAL_SOFTPATCH_HANDLER, 0, glue);
 #endif
 
@@ -322,7 +343,7 @@ static void opal_handle_message(void)
 
 	/* check for errors. */
 	if (ret) {
-		pr_warning("%s: Failed to retrive opal message, err=%lld\n",
+		pr_warning("%s: Failed to retrieve opal message, err=%lld\n",
 				__func__, ret);
 		return;
 	}
diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c
index df241b11d4f7..468a0f23c7f2 100644
--- a/arch/powerpc/platforms/powernv/pci-ioda.c
+++ b/arch/powerpc/platforms/powernv/pci-ioda.c
@@ -37,41 +37,43 @@
 #include <asm/xics.h>
 #include <asm/debug.h>
 #include <asm/firmware.h>
+#include <asm/pnv-pci.h>
+
+#include <misc/cxl.h>
 
 #include "powernv.h"
 #include "pci.h"
 
-#define define_pe_printk_level(func, kern_level)		\
-static int func(const struct pnv_ioda_pe *pe, const char *fmt, ...)	\
-{								\
-	struct va_format vaf;					\
-	va_list args;						\
-	char pfix[32];						\
-	int r;							\
-								\
-	va_start(args, fmt);					\
-								\
-	vaf.fmt = fmt;						\
-	vaf.va = &args;						\
-								\
-	if (pe->pdev)						\
-		strlcpy(pfix, dev_name(&pe->pdev->dev),		\
-			sizeof(pfix));				\
-	else							\
-		sprintf(pfix, "%04x:%02x     ",			\
-			pci_domain_nr(pe->pbus),		\
-			pe->pbus->number);			\
-	r = printk(kern_level "pci %s: [PE# %.3d] %pV",		\
-		   pfix, pe->pe_number, &vaf);			\
-								\
-	va_end(args);						\
-								\
-	return r;						\
-}								\
-
-define_pe_printk_level(pe_err, KERN_ERR);
-define_pe_printk_level(pe_warn, KERN_WARNING);
-define_pe_printk_level(pe_info, KERN_INFO);
+static void pe_level_printk(const struct pnv_ioda_pe *pe, const char *level,
+			    const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	char pfix[32];
+
+	va_start(args, fmt);
+
+	vaf.fmt = fmt;
+	vaf.va = &args;
+
+	if (pe->pdev)
+		strlcpy(pfix, dev_name(&pe->pdev->dev), sizeof(pfix));
+	else
+		sprintf(pfix, "%04x:%02x     ",
+			pci_domain_nr(pe->pbus), pe->pbus->number);
+
+	printk("%spci %s: [PE# %.3d] %pV",
+	       level, pfix, pe->pe_number, &vaf);
+
+	va_end(args);
+}
+
+#define pe_err(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_ERR, fmt, ##__VA_ARGS__)
+#define pe_warn(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_WARNING, fmt, ##__VA_ARGS__)
+#define pe_info(pe, fmt, ...)					\
+	pe_level_printk(pe, KERN_INFO, fmt, ##__VA_ARGS__)
 
 /*
  * stdcix is only supposed to be used in hypervisor real mode as per
@@ -385,7 +387,7 @@ static void pnv_ioda_freeze_pe(struct pnv_phb *phb, int pe_no)
 	}
 }
 
-int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt)
+static int pnv_ioda_unfreeze_pe(struct pnv_phb *phb, int pe_no, int opt)
 {
 	struct pnv_ioda_pe *pe, *slave;
 	s64 rc;
@@ -890,6 +892,28 @@ static int pnv_pci_ioda_dma_set_mask(struct pnv_phb *phb,
 	return 0;
 }
 
+static u64 pnv_pci_ioda_dma_get_required_mask(struct pnv_phb *phb,
+					      struct pci_dev *pdev)
+{
+	struct pci_dn *pdn = pci_get_pdn(pdev);
+	struct pnv_ioda_pe *pe;
+	u64 end, mask;
+
+	if (WARN_ON(!pdn || pdn->pe_number == IODA_INVALID_PE))
+		return 0;
+
+	pe = &phb->ioda.pe_array[pdn->pe_number];
+	if (!pe->tce_bypass_enabled)
+		return __dma_get_required_mask(&pdev->dev);
+
+
+	end = pe->tce_bypass_base + memblock_end_of_DRAM();
+	mask = 1ULL << (fls64(end) - 1);
+	mask += mask - 1;
+
+	return mask;
+}
+
 static void pnv_ioda_setup_bus_dma(struct pnv_ioda_pe *pe,
 				   struct pci_bus *bus,
 				   bool add_to_iommu_group)
@@ -1306,14 +1330,186 @@ static void pnv_ioda2_msi_eoi(struct irq_data *d)
 	icp_native_eoi(d);
 }
 
+
+static void set_msi_irq_chip(struct pnv_phb *phb, unsigned int virq)
+{
+	struct irq_data *idata;
+	struct irq_chip *ichip;
+
+	if (phb->type != PNV_PHB_IODA2)
+		return;
+
+	if (!phb->ioda.irq_chip_init) {
+		/*
+		 * First time we setup an MSI IRQ, we need to setup the
+		 * corresponding IRQ chip to route correctly.
+		 */
+		idata = irq_get_irq_data(virq);
+		ichip = irq_data_get_irq_chip(idata);
+		phb->ioda.irq_chip_init = 1;
+		phb->ioda.irq_chip = *ichip;
+		phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
+	}
+	irq_set_chip(virq, &phb->ioda.irq_chip);
+}
+
+#ifdef CONFIG_CXL_BASE
+
+struct device_node *pnv_pci_to_phb_node(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+
+	return hose->dn;
+}
+EXPORT_SYMBOL(pnv_pci_to_phb_node);
+
+int pnv_phb_to_cxl(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	pe = pnv_ioda_get_pe(dev);
+	if (!pe)
+		return -ENODEV;
+
+	pe_info(pe, "Switching PHB to CXL\n");
+
+	rc = opal_pci_set_phb_cxl_mode(phb->opal_id, 1, pe->pe_number);
+	if (rc)
+		dev_err(&dev->dev, "opal_pci_set_phb_cxl_mode failed: %i\n", rc);
+
+	return rc;
+}
+EXPORT_SYMBOL(pnv_phb_to_cxl);
+
+/* Find PHB for cxl dev and allocate MSI hwirqs?
+ * Returns the absolute hardware IRQ number
+ */
+int pnv_cxl_alloc_hwirqs(struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, num);
+
+	if (hwirq < 0) {
+		dev_warn(&dev->dev, "Failed to find a free MSI\n");
+		return -ENOSPC;
+	}
+
+	return phb->msi_base + hwirq;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirqs);
+
+void pnv_cxl_release_hwirqs(struct pci_dev *dev, int hwirq, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq - phb->msi_base, num);
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirqs);
+
+void pnv_cxl_release_hwirq_ranges(struct cxl_irq_ranges *irqs,
+				  struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq;
+
+	for (i = 1; i < CXL_IRQ_RANGES; i++) {
+		if (!irqs->range[i])
+			continue;
+		pr_devel("cxl release irq range 0x%x: offset: 0x%lx  limit: %ld\n",
+			 i, irqs->offset[i],
+			 irqs->range[i]);
+		hwirq = irqs->offset[i] - phb->msi_base;
+		msi_bitmap_free_hwirqs(&phb->msi_bmp, hwirq,
+				       irqs->range[i]);
+	}
+}
+EXPORT_SYMBOL(pnv_cxl_release_hwirq_ranges);
+
+int pnv_cxl_alloc_hwirq_ranges(struct cxl_irq_ranges *irqs,
+			       struct pci_dev *dev, int num)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	int i, hwirq, try;
+
+	memset(irqs, 0, sizeof(struct cxl_irq_ranges));
+
+	/* 0 is reserved for the multiplexed PSL DSI interrupt */
+	for (i = 1; i < CXL_IRQ_RANGES && num; i++) {
+		try = num;
+		while (try) {
+			hwirq = msi_bitmap_alloc_hwirqs(&phb->msi_bmp, try);
+			if (hwirq >= 0)
+				break;
+			try /= 2;
+		}
+		if (!try)
+			goto fail;
+
+		irqs->offset[i] = phb->msi_base + hwirq;
+		irqs->range[i] = try;
+		pr_devel("cxl alloc irq range 0x%x: offset: 0x%lx  limit: %li\n",
+			 i, irqs->offset[i], irqs->range[i]);
+		num -= try;
+	}
+	if (num)
+		goto fail;
+
+	return 0;
+fail:
+	pnv_cxl_release_hwirq_ranges(irqs, dev);
+	return -ENOSPC;
+}
+EXPORT_SYMBOL(pnv_cxl_alloc_hwirq_ranges);
+
+int pnv_cxl_get_irq_count(struct pci_dev *dev)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	return phb->msi_bmp.irq_count;
+}
+EXPORT_SYMBOL(pnv_cxl_get_irq_count);
+
+int pnv_cxl_ioda_msi_setup(struct pci_dev *dev, unsigned int hwirq,
+			   unsigned int virq)
+{
+	struct pci_controller *hose = pci_bus_to_host(dev->bus);
+	struct pnv_phb *phb = hose->private_data;
+	unsigned int xive_num = hwirq - phb->msi_base;
+	struct pnv_ioda_pe *pe;
+	int rc;
+
+	if (!(pe = pnv_ioda_get_pe(dev)))
+		return -ENODEV;
+
+	/* Assign XIVE to PE */
+	rc = opal_pci_set_xive_pe(phb->opal_id, pe->pe_number, xive_num);
+	if (rc) {
+		pe_warn(pe, "%s: OPAL error %d setting msi_base 0x%x "
+			"hwirq 0x%x XIVE 0x%x PE\n",
+			pci_name(dev), rc, phb->msi_base, hwirq, xive_num);
+		return -EIO;
+	}
+	set_msi_irq_chip(phb, virq);
+
+	return 0;
+}
+EXPORT_SYMBOL(pnv_cxl_ioda_msi_setup);
+#endif
+
 static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 				  unsigned int hwirq, unsigned int virq,
 				  unsigned int is_64, struct msi_msg *msg)
 {
 	struct pnv_ioda_pe *pe = pnv_ioda_get_pe(dev);
 	struct pci_dn *pdn = pci_get_pdn(dev);
-	struct irq_data *idata;
-	struct irq_chip *ichip;
 	unsigned int xive_num = hwirq - phb->msi_base;
 	__be32 data;
 	int rc;
@@ -1365,22 +1561,7 @@ static int pnv_pci_ioda_msi_setup(struct pnv_phb *phb, struct pci_dev *dev,
 	}
 	msg->data = be32_to_cpu(data);
 
-	/*
-	 * Change the IRQ chip for the MSI interrupts on PHB3.
-	 * The corresponding IRQ chip should be populated for
-	 * the first time.
-	 */
-	if (phb->type == PNV_PHB_IODA2) {
-		if (!phb->ioda.irq_chip_init) {
-			idata = irq_get_irq_data(virq);
-			ichip = irq_data_get_irq_chip(idata);
-			phb->ioda.irq_chip_init = 1;
-			phb->ioda.irq_chip = *ichip;
-			phb->ioda.irq_chip.irq_eoi = pnv_ioda2_msi_eoi;
-		}
-
-		irq_set_chip(virq, &phb->ioda.irq_chip);
-	}
+	set_msi_irq_chip(phb, virq);
 
 	pr_devel("%s: %s-bit MSI on hwirq %x (xive #%d),"
 		 " address=%x_%08x data=%x PE# %d\n",
@@ -1627,12 +1808,12 @@ static u32 pnv_ioda_bdfn_to_pe(struct pnv_phb *phb, struct pci_bus *bus,
 
 static void pnv_pci_ioda_shutdown(struct pnv_phb *phb)
 {
-	opal_pci_reset(phb->opal_id, OPAL_PCI_IODA_TABLE_RESET,
+	opal_pci_reset(phb->opal_id, OPAL_RESET_PCI_IODA_TABLE,
 		       OPAL_ASSERT_RESET);
 }
 
-void __init pnv_pci_init_ioda_phb(struct device_node *np,
-				  u64 hub_id, int ioda_type)
+static void __init pnv_pci_init_ioda_phb(struct device_node *np,
+					 u64 hub_id, int ioda_type)
 {
 	struct pci_controller *hose;
 	struct pnv_phb *phb;
@@ -1782,6 +1963,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	/* Setup TCEs */
 	phb->dma_dev_setup = pnv_pci_ioda_dma_dev_setup;
 	phb->dma_set_mask = pnv_pci_ioda_dma_set_mask;
+	phb->dma_get_required_mask = pnv_pci_ioda_dma_get_required_mask;
 
 	/* Setup shutdown function for kexec */
 	phb->shutdown = pnv_pci_ioda_shutdown;
@@ -1803,7 +1985,7 @@ void __init pnv_pci_init_ioda_phb(struct device_node *np,
 	pci_add_flags(PCI_REASSIGN_ALL_RSRC);
 
 	/* Reset IODA tables to a clean state */
-	rc = opal_pci_reset(phb_id, OPAL_PCI_IODA_TABLE_RESET, OPAL_ASSERT_RESET);
+	rc = opal_pci_reset(phb_id, OPAL_RESET_PCI_IODA_TABLE, OPAL_ASSERT_RESET);
 	if (rc)
 		pr_warning("  OPAL Error %ld performing IODA table reset !\n", rc);
 
diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c
index b854b57ed5e1..b2187d0068b8 100644
--- a/arch/powerpc/platforms/powernv/pci.c
+++ b/arch/powerpc/platforms/powernv/pci.c
@@ -46,29 +46,21 @@
 //#define cfg_dbg(fmt...)	printk(fmt)
 
 #ifdef CONFIG_PCI_MSI
-static int pnv_msi_check_device(struct pci_dev* pdev, int nvec, int type)
-{
-	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
-	struct pnv_phb *phb = hose->private_data;
-	struct pci_dn *pdn = pci_get_pdn(pdev);
-
-	if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
-		return -ENODEV;
-
-	return (phb && phb->msi_bmp.bitmap) ? 0 : -ENODEV;
-}
-
 static int pnv_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
 {
 	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
 	struct pnv_phb *phb = hose->private_data;
+	struct pci_dn *pdn = pci_get_pdn(pdev);
 	struct msi_desc *entry;
 	struct msi_msg msg;
 	int hwirq;
 	unsigned int virq;
 	int rc;
 
-	if (WARN_ON(!phb))
+	if (WARN_ON(!phb) || !phb->msi_bmp.bitmap)
+		return -ENODEV;
+
+	if (pdn && pdn->force_32bit_msi && !phb->msi32_support)
 		return -ENODEV;
 
 	list_for_each_entry(entry, &pdev->msi_list, list) {
@@ -513,7 +505,7 @@ static bool pnv_pci_cfg_check(struct pci_controller *hose,
 	edev = of_node_to_eeh_dev(dn);
 	if (edev) {
 		if (edev->pe &&
-		    (edev->pe->state & EEH_PE_RESET))
+		    (edev->pe->state & EEH_PE_CFG_BLOCKED))
 			return false;
 
 		if (edev->mode & EEH_DEV_REMOVED)
@@ -761,6 +753,17 @@ int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 	return __dma_set_mask(&pdev->dev, dma_mask);
 }
 
+u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
+{
+	struct pci_controller *hose = pci_bus_to_host(pdev->bus);
+	struct pnv_phb *phb = hose->private_data;
+
+	if (phb && phb->dma_get_required_mask)
+		return phb->dma_get_required_mask(phb, pdev);
+
+	return __dma_get_required_mask(&pdev->dev);
+}
+
 void pnv_pci_shutdown(void)
 {
 	struct pci_controller *hose;
@@ -860,7 +863,6 @@ void __init pnv_pci_init(void)
 
 	/* Configure MSIs */
 #ifdef CONFIG_PCI_MSI
-	ppc_md.msi_check_device = pnv_msi_check_device;
 	ppc_md.setup_msi_irqs = pnv_setup_msi_irqs;
 	ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs;
 #endif
diff --git a/arch/powerpc/platforms/powernv/pci.h b/arch/powerpc/platforms/powernv/pci.h
index 48494d4b6058..34d29eb2a4de 100644
--- a/arch/powerpc/platforms/powernv/pci.h
+++ b/arch/powerpc/platforms/powernv/pci.h
@@ -85,6 +85,8 @@ struct pnv_eeh_ops {
 	int (*get_log)(struct eeh_pe *pe, int severity,
 		       char *drv_log, unsigned long len);
 	int (*configure_bridge)(struct eeh_pe *pe);
+	int (*err_inject)(struct eeh_pe *pe, int type, int func,
+			  unsigned long addr, unsigned long mask);
 	int (*next_error)(struct eeh_pe **pe);
 };
 #endif /* CONFIG_EEH */
@@ -122,6 +124,8 @@ struct pnv_phb {
 	void (*dma_dev_setup)(struct pnv_phb *phb, struct pci_dev *pdev);
 	int (*dma_set_mask)(struct pnv_phb *phb, struct pci_dev *pdev,
 			    u64 dma_mask);
+	u64 (*dma_get_required_mask)(struct pnv_phb *phb,
+				     struct pci_dev *pdev);
 	void (*fixup_phb)(struct pci_controller *hose);
 	u32 (*bdfn_to_pe)(struct pnv_phb *phb, struct pci_bus *bus, u32 devfn);
 	void (*shutdown)(struct pnv_phb *phb);
diff --git a/arch/powerpc/platforms/powernv/powernv.h b/arch/powerpc/platforms/powernv/powernv.h
index 75501bfede7f..6c8e2d188cd0 100644
--- a/arch/powerpc/platforms/powernv/powernv.h
+++ b/arch/powerpc/platforms/powernv/powernv.h
@@ -13,6 +13,7 @@ struct pci_dev;
 extern void pnv_pci_init(void);
 extern void pnv_pci_shutdown(void);
 extern int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask);
+extern u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev);
 #else
 static inline void pnv_pci_init(void) { }
 static inline void pnv_pci_shutdown(void) { }
@@ -21,6 +22,11 @@ static inline int pnv_pci_dma_set_mask(struct pci_dev *pdev, u64 dma_mask)
 {
 	return -ENODEV;
 }
+
+static inline u64 pnv_pci_dma_get_required_mask(struct pci_dev *pdev)
+{
+	return 0;
+}
 #endif
 
 extern void pnv_lpc_init(void);
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index 5a0e2dc6de5f..3f9546d8a51f 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -173,6 +173,14 @@ static int pnv_dma_set_mask(struct device *dev, u64 dma_mask)
 	return __dma_set_mask(dev, dma_mask);
 }
 
+static u64 pnv_dma_get_required_mask(struct device *dev)
+{
+	if (dev_is_pci(dev))
+		return pnv_pci_dma_get_required_mask(to_pci_dev(dev));
+
+	return __dma_get_required_mask(dev);
+}
+
 static void pnv_shutdown(void)
 {
 	/* Let the PCI code clear up IODA tables */
@@ -307,7 +315,7 @@ static int __init pnv_probe(void)
  * Returns the cpu frequency for 'cpu' in Hz. This is used by
  * /proc/cpuinfo
  */
-unsigned long pnv_get_proc_freq(unsigned int cpu)
+static unsigned long pnv_get_proc_freq(unsigned int cpu)
 {
 	unsigned long ret_freq;
 
@@ -335,6 +343,7 @@ define_machine(powernv) {
 	.power_save             = power7_idle,
 	.calibrate_decr		= generic_calibrate_decr,
 	.dma_set_mask		= pnv_dma_set_mask,
+	.dma_get_required_mask	= pnv_dma_get_required_mask,
 #ifdef CONFIG_KEXEC
 	.kexec_cpu_down		= pnv_kexec_cpu_down,
 #endif
diff --git a/arch/powerpc/platforms/powernv/smp.c b/arch/powerpc/platforms/powernv/smp.c
index 5fcfcf44e3a9..4753958cd509 100644
--- a/arch/powerpc/platforms/powernv/smp.c
+++ b/arch/powerpc/platforms/powernv/smp.c
@@ -54,7 +54,7 @@ static void pnv_smp_setup_cpu(int cpu)
 #endif
 }
 
-int pnv_smp_kick_cpu(int nr)
+static int pnv_smp_kick_cpu(int nr)
 {
 	unsigned int pcpu = get_hard_smp_processor_id(nr);
 	unsigned long start_here =
@@ -168,9 +168,9 @@ static void pnv_smp_cpu_kill_self(void)
 		power7_nap(1);
 		ppc64_runlatch_on();
 
-		/* Reenable IRQs briefly to clear the IPI that woke us */
-		local_irq_enable();
-		local_irq_disable();
+		/* Clear the IPI that woke us up */
+		icp_native_flush_interrupt();
+		local_paca->irq_happened &= PACA_IRQ_HARD_DIS;
 		mb();
 
 		if (cpu_core_split_required())
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 894ecb3eb596..c87f96b79d1a 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -24,6 +24,7 @@
 #include <asm/smp.h>
 
 #include "subcore.h"
+#include "powernv.h"
 
 
 /*