18 files changed, 345 insertions, 170 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c7e8afc2ead..8207459efe5 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -138,6 +138,9 @@ int main(void)
 	DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
 	DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
 	DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+	DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar));
+	DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
+	DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
 	DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
 	DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
 					 transact_vr[0]));
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 2a45d0f0438..22973a74df7 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -494,9 +494,27 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_restore		= __restore_cpu_power7,
 		.platform		= "power7+",
 	},
-	{	/* Power8 */
+	{	/* Power8E */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x004b0000,
+		.cpu_name		= "POWER8E (raw)",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.platform		= "power8",
+	},
+	{	/* Power8 */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x004d0000,
 		.cpu_name		= "POWER8 (raw)",
 		.cpu_features		= CPU_FTRS_POWER8,
 		.cpu_user_features	= COMMON_USER_POWER8,
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 39954fe941b..55593ee2d5a 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -231,7 +231,7 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
 void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 {
 	size_t loglen = 0;
-	struct eeh_dev *edev;
+	struct eeh_dev *edev, *tmp;
 	bool valid_cfg_log = true;
 
 	/*
@@ -251,7 +251,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 		eeh_pe_restore_bars(pe);
 
 		pci_regs_buf[0] = 0;
-		eeh_pe_for_each_dev(pe, edev) {
+		eeh_pe_for_each_dev(pe, edev, tmp) {
 			loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
 						      EEH_PCI_REGS_LOG_LEN - loglen);
 		}
@@ -499,8 +499,6 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
 	}
 
 	eeh_dev_check_failure(edev);
-
-	pci_dev_put(eeh_dev_to_pci_dev(edev));
 	return val;
 }
 
@@ -838,7 +836,7 @@ core_initcall_sync(eeh_init);
  * on the CEC architecture, type of the device, on earlier boot
  * command-line arguments & etc.
  */
-static void eeh_add_device_early(struct device_node *dn)
+void eeh_add_device_early(struct device_node *dn)
 {
 	struct pci_controller *phb;
 
@@ -886,7 +884,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
  * This routine must be used to complete EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
  */
-static void eeh_add_device_late(struct pci_dev *dev)
+void eeh_add_device_late(struct pci_dev *dev)
 {
 	struct device_node *dn;
 	struct eeh_dev *edev;
@@ -902,9 +900,23 @@ static void eeh_add_device_late(struct pci_dev *dev)
 		pr_debug("EEH: Already referenced !\n");
 		return;
 	}
-	WARN_ON(edev->pdev);
 
-	pci_dev_get(dev);
+	/*
+	 * The EEH cache might not be removed correctly because of
+	 * unbalanced kref to the device during unplug time, which
+	 * relies on pcibios_release_device(). So we have to remove
+	 * that here explicitly.
+	 */
+	if (edev->pdev) {
+		eeh_rmv_from_parent_pe(edev);
+		eeh_addr_cache_rmv_dev(edev->pdev);
+		eeh_sysfs_remove_device(edev->pdev);
+		edev->mode &= ~EEH_DEV_SYSFS;
+
+		edev->pdev = NULL;
+		dev->dev.archdata.edev = NULL;
+	}
+
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
@@ -967,7 +979,6 @@ EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
 /**
  * eeh_remove_device - Undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
- * @purge_pe: remove the PE or not
  *
  * This routine should be called when a device is removed from
  * a running system (e.g. by hotplug or dlpar).  It unregisters
@@ -975,7 +986,7 @@ EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
  * this device will no longer be detected after this call; thus,
  * i/o errors affecting this slot may leave this device unusable.
  */
-static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
+void eeh_remove_device(struct pci_dev *dev)
 {
 	struct eeh_dev *edev;
 
@@ -986,42 +997,29 @@ static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
 	/* Unregister the device with the EEH/PCI address search system */
 	pr_debug("EEH: Removing device %s\n", pci_name(dev));
 
-	if (!edev || !edev->pdev) {
+	if (!edev || !edev->pdev || !edev->pe) {
 		pr_debug("EEH: Not referenced !\n");
 		return;
 	}
+
+	/*
+	 * During the hotplug for EEH error recovery, we need the EEH
+	 * device attached to the parent PE in order for BAR restore
+	 * a bit later. So we keep it for BAR restore and remove it
+	 * from the parent PE during the BAR resotre.
+	 */
 	edev->pdev = NULL;
 	dev->dev.archdata.edev = NULL;
-	pci_dev_put(dev);
+	if (!(edev->pe->state & EEH_PE_KEEP))
+		eeh_rmv_from_parent_pe(edev);
+	else
+		edev->mode |= EEH_DEV_DISCONNECTED;
 
-	eeh_rmv_from_parent_pe(edev, purge_pe);
 	eeh_addr_cache_rmv_dev(dev);
 	eeh_sysfs_remove_device(dev);
+	edev->mode &= ~EEH_DEV_SYSFS;
 }
 
-/**
- * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device
- * @dev: PCI device
- * @purge_pe: remove the corresponding PE or not
- *
- * This routine must be called when a device is removed from the
- * running system through hotplug or dlpar. The corresponding
- * PCI address cache will be removed.
- */
-void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe)
-{
-	struct pci_bus *bus = dev->subordinate;
-	struct pci_dev *child, *tmp;
-
-	eeh_remove_device(dev, purge_pe);
-
-	if (bus && dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		list_for_each_entry_safe(child, tmp, &bus->devices, bus_list)
-			 eeh_remove_bus_device(child, purge_pe);
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_remove_bus_device);
-
 static int proc_eeh_show(struct seq_file *m, void *v)
 {
 	if (0 == eeh_subsystem_enabled) {
@@ -1063,7 +1061,7 @@ static const struct file_operations proc_eeh_operations = {
 
 static int __init eeh_init_proc(void)
 {
-	if (machine_is(pseries))
+	if (machine_is(pseries) || machine_is(powernv))
 		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
 	return 0;
 }
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index f9ac1232a74..e8c9fd546a5 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -68,16 +68,12 @@ static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr)
 		struct pci_io_addr_range *piar;
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
 
-		if (addr < piar->addr_lo) {
+		if (addr < piar->addr_lo)
 			n = n->rb_left;
-		} else {
-			if (addr > piar->addr_hi) {
-				n = n->rb_right;
-			} else {
-				pci_dev_get(piar->pcidev);
-				return piar->edev;
-			}
-		}
+		else if (addr > piar->addr_hi)
+			n = n->rb_right;
+		else
+			return piar->edev;
 	}
 
 	return NULL;
@@ -156,7 +152,6 @@ eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 	if (!piar)
 		return NULL;
 
-	pci_dev_get(dev);
 	piar->addr_lo = alo;
 	piar->addr_hi = ahi;
 	piar->edev = pci_dev_to_eeh_dev(dev);
@@ -250,7 +245,6 @@ restart:
 
 		if (piar->pcidev == dev) {
 			rb_erase(n, &pci_io_addr_cache_root.rb_root);
-			pci_dev_put(piar->pcidev);
 			kfree(piar);
 			goto restart;
 		}
@@ -302,12 +296,10 @@ void eeh_addr_cache_build(void)
 		if (!edev)
 			continue;
 
-		pci_dev_get(dev);  /* matching put is in eeh_remove_device() */
 		dev->dev.archdata.edev = edev;
 		edev->pdev = dev;
 
 		eeh_addr_cache_insert_dev(dev);
-
 		eeh_sysfs_add_device(dev);
 	}
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 2b1ce17cae5..36bed5a1275 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -143,10 +143,14 @@ static void eeh_disable_irq(struct pci_dev *dev)
 static void eeh_enable_irq(struct pci_dev *dev)
 {
 	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+	struct irq_desc *desc;
 
 	if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
 		edev->mode &= ~EEH_DEV_IRQ_DISABLED;
-		enable_irq(dev->irq);
+
+		desc = irq_to_desc(dev->irq);
+		if (desc && desc->depth > 0)
+			enable_irq(dev->irq);
 	}
 }
 
@@ -338,6 +342,54 @@ static void *eeh_report_failure(void *data, void *userdata)
 	return NULL;
 }
 
+static void *eeh_rmv_device(void *data, void *userdata)
+{
+	struct pci_driver *driver;
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	int *removed = (int *)userdata;
+
+	/*
+	 * Actually, we should remove the PCI bridges as well.
+	 * However, that's lots of complexity to do that,
+	 * particularly some of devices under the bridge might
+	 * support EEH. So we just care about PCI devices for
+	 * simplicity here.
+	 */
+	if (!dev || (dev->hdr_type & PCI_HEADER_TYPE_BRIDGE))
+		return NULL;
+	driver = eeh_pcid_get(dev);
+	if (driver && driver->err_handler)
+		return NULL;
+
+	/* Remove it from PCI subsystem */
+	pr_debug("EEH: Removing %s without EEH sensitive driver\n",
+		 pci_name(dev));
+	edev->bus = dev->bus;
+	edev->mode |= EEH_DEV_DISCONNECTED;
+	(*removed)++;
+
+	pci_stop_and_remove_bus_device(dev);
+
+	return NULL;
+}
+
+static void *eeh_pe_detach_dev(void *data, void *userdata)
+{
+	struct eeh_pe *pe = (struct eeh_pe *)data;
+	struct eeh_dev *edev, *tmp;
+
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		if (!(edev->mode & EEH_DEV_DISCONNECTED))
+			continue;
+
+		edev->mode &= ~(EEH_DEV_DISCONNECTED | EEH_DEV_IRQ_DISABLED);
+		eeh_rmv_from_parent_pe(edev);
+	}
+
+	return NULL;
+}
+
 /**
  * eeh_reset_device - Perform actual reset of a pci slot
  * @pe: EEH PE
@@ -349,8 +401,9 @@ static void *eeh_report_failure(void *data, void *userdata)
  */
 static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 {
+	struct pci_bus *frozen_bus = eeh_pe_bus_get(pe);
 	struct timeval tstamp;
-	int cnt, rc;
+	int cnt, rc, removed = 0;
 
 	/* pcibios will clear the counter; save the value */
 	cnt = pe->freeze_count;
@@ -362,8 +415,11 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * devices are expected to be attached soon when calling
 	 * into pcibios_add_pci_devices().
 	 */
+	eeh_pe_state_mark(pe, EEH_PE_KEEP);
 	if (bus)
-		__pcibios_remove_pci_devices(bus, 0);
+		pcibios_remove_pci_devices(bus);
+	else if (frozen_bus)
+		eeh_pe_dev_traverse(pe, eeh_rmv_device, &removed);
 
 	/* Reset the pci controller. (Asserts RST#; resets config space).
 	 * Reconfigure bridges and devices. Don't try to bring the system
@@ -384,9 +440,24 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * potentially weird things happen.
 	 */
 	if (bus) {
+		pr_info("EEH: Sleep 5s ahead of complete hotplug\n");
 		ssleep(5);
+
+		/*
+		 * The EEH device is still connected with its parent
+		 * PE. We should disconnect it so the binding can be
+		 * rebuilt when adding PCI devices.
+		 */
+		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
 		pcibios_add_pci_devices(bus);
+	} else if (frozen_bus && removed) {
+		pr_info("EEH: Sleep 5s ahead of partial hotplug\n");
+		ssleep(5);
+
+		eeh_pe_traverse(pe, eeh_pe_detach_dev, NULL);
+		pcibios_add_pci_devices(frozen_bus);
 	}
+	eeh_pe_state_clear(pe, EEH_PE_KEEP);
 
 	pe->tstamp = tstamp;
 	pe->freeze_count = cnt;
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 016588a6f5e..f9450537e33 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -149,8 +149,8 @@ static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
  * callback returns something other than NULL, or no more PEs
  * to be traversed.
  */
-static void *eeh_pe_traverse(struct eeh_pe *root,
-			eeh_traverse_func fn, void *flag)
+void *eeh_pe_traverse(struct eeh_pe *root,
+		      eeh_traverse_func fn, void *flag)
 {
 	struct eeh_pe *pe;
 	void *ret;
@@ -176,7 +176,7 @@ void *eeh_pe_dev_traverse(struct eeh_pe *root,
 		eeh_traverse_func fn, void *flag)
 {
 	struct eeh_pe *pe;
-	struct eeh_dev *edev;
+	struct eeh_dev *edev, *tmp;
 	void *ret;
 
 	if (!root) {
@@ -186,7 +186,7 @@ void *eeh_pe_dev_traverse(struct eeh_pe *root,
 
 	/* Traverse root PE */
 	for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
-		eeh_pe_for_each_dev(pe, edev) {
+		eeh_pe_for_each_dev(pe, edev, tmp) {
 			ret = fn(edev, flag);
 			if (ret)
 				return ret;
@@ -333,7 +333,7 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 		while (parent) {
 			if (!(parent->type & EEH_PE_INVALID))
 				break;
-			parent->type &= ~EEH_PE_INVALID;
+			parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP);
 			parent = parent->parent;
 		}
 		pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
@@ -397,21 +397,20 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 /**
  * eeh_rmv_from_parent_pe - Remove one EEH device from the associated PE
  * @edev: EEH device
- * @purge_pe: remove PE or not
  *
  * The PE hierarchy tree might be changed when doing PCI hotplug.
  * Also, the PCI devices or buses could be removed from the system
  * during EEH recovery. So we have to call the function remove the
  * corresponding PE accordingly if necessary.
  */
-int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe)
+int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 {
 	struct eeh_pe *pe, *parent, *child;
 	int cnt;
 
 	if (!edev->pe) {
-		pr_warning("%s: No PE found for EEH device %s\n",
-			__func__, edev->dn->full_name);
+		pr_debug("%s: No PE found for EEH device %s\n",
+			 __func__, edev->dn->full_name);
 		return -EEXIST;
 	}
 
@@ -431,7 +430,7 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe)
 		if (pe->type & EEH_PE_PHB)
 			break;
 
-		if (purge_pe) {
+		if (!(pe->state & EEH_PE_KEEP)) {
 			if (list_empty(&pe->edevs) &&
 			    list_empty(&pe->child_list)) {
 				list_del(&pe->child);
@@ -502,7 +501,7 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 {
 	struct eeh_pe *pe = (struct eeh_pe *)data;
 	int state = *((int *)flag);
-	struct eeh_dev *tmp;
+	struct eeh_dev *edev, *tmp;
 	struct pci_dev *pdev;
 
 	/*
@@ -512,8 +511,8 @@ static void *__eeh_pe_state_mark(void *data, void *flag)
 	 * the PCI device driver.
 	 */
 	pe->state |= state;
-	eeh_pe_for_each_dev(pe, tmp) {
-		pdev = eeh_dev_to_pci_dev(tmp);
+	eeh_pe_for_each_dev(pe, edev, tmp) {
+		pdev = eeh_dev_to_pci_dev(edev);
 		if (pdev)
 			pdev->error_state = pci_channel_io_frozen;
 	}
@@ -579,7 +578,7 @@ void eeh_pe_state_clear(struct eeh_pe *pe, int state)
  * blocked on normal path during the stage. So we need utilize
  * eeh operations, which is always permitted.
  */
-static void eeh_bridge_check_link(struct pci_dev *pdev,
+static void eeh_bridge_check_link(struct eeh_dev *edev,
 				  struct device_node *dn)
 {
 	int cap;
@@ -590,16 +589,17 @@ static void eeh_bridge_check_link(struct pci_dev *pdev,
 	 * We only check root port and downstream ports of
 	 * PCIe switches
 	 */
-	if (!pci_is_pcie(pdev) ||
-	    (pci_pcie_type(pdev) != PCI_EXP_TYPE_ROOT_PORT &&
-	     pci_pcie_type(pdev) != PCI_EXP_TYPE_DOWNSTREAM))
+	if (!(edev->mode & (EEH_DEV_ROOT_PORT | EEH_DEV_DS_PORT)))
 		return;
 
-	pr_debug("%s: Check PCIe link for %s ...\n",
-		 __func__, pci_name(pdev));
+	pr_debug("%s: Check PCIe link for %04x:%02x:%02x.%01x ...\n",
+		 __func__, edev->phb->global_number,
+		 edev->config_addr >> 8,
+		 PCI_SLOT(edev->config_addr & 0xFF),
+		 PCI_FUNC(edev->config_addr & 0xFF));
 
 	/* Check slot status */
-	cap = pdev->pcie_cap;
+	cap = edev->pcie_cap;
 	eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
 	if (!(val & PCI_EXP_SLTSTA_PDS)) {
 		pr_debug("  No card in the slot (0x%04x) !\n", val);
@@ -653,8 +653,7 @@ static void eeh_bridge_check_link(struct pci_dev *pdev,
 #define BYTE_SWAP(OFF)	(8*((OFF)/4)+3-(OFF))
 #define SAVED_BYTE(OFF)	(((u8 *)(edev->config_space))[BYTE_SWAP(OFF)])
 
-static void eeh_restore_bridge_bars(struct pci_dev *pdev,
-				    struct eeh_dev *edev,
+static void eeh_restore_bridge_bars(struct eeh_dev *edev,
 				    struct device_node *dn)
 {
 	int i;
@@ -680,7 +679,7 @@ static void eeh_restore_bridge_bars(struct pci_dev *pdev,
 	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
 
 	/* Check the PCIe link is ready */
-	eeh_bridge_check_link(pdev, dn);
+	eeh_bridge_check_link(edev, dn);
 }
 
 static void eeh_restore_device_bars(struct eeh_dev *edev,
@@ -729,19 +728,12 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
  */
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
-	struct pci_dev *pdev = NULL;
 	struct eeh_dev *edev = (struct eeh_dev *)data;
 	struct device_node *dn = eeh_dev_to_of_node(edev);
 
-	/* Trace the PCI bridge */
-	if (eeh_probe_mode_dev()) {
-		pdev = eeh_dev_to_pci_dev(edev);
-		if (pdev->hdr_type != PCI_HEADER_TYPE_BRIDGE)
-                        pdev = NULL;
-        }
-
-	if (pdev)
-		eeh_restore_bridge_bars(pdev, edev, dn);
+	/* Do special restore for bridges */
+	if (edev->mode & EEH_DEV_BRIDGE)
+		eeh_restore_bridge_bars(edev, dn);
 	else
 		eeh_restore_device_bars(edev, dn);
 
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
index e7ae3484918..5d753d4f2c7 100644
--- a/arch/powerpc/kernel/eeh_sysfs.c
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -56,19 +56,40 @@ EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
 
 void eeh_sysfs_add_device(struct pci_dev *pdev)
 {
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
 	int rc=0;
 
+	if (edev && (edev->mode & EEH_DEV_SYSFS))
+		return;
+
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_mode);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	rc += device_create_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
 
 	if (rc)
 		printk(KERN_WARNING "EEH: Unable to create sysfs entries\n");
+	else if (edev)
+		edev->mode |= EEH_DEV_SYSFS;
 }
 
 void eeh_sysfs_remove_device(struct pci_dev *pdev)
 {
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);
+
+	/*
+	 * The parent directory might have been removed. We needn't
+	 * continue for that case.
+	 */
+	if (!pdev->dev.kobj.sd) {
+		if (edev)
+			edev->mode &= ~EEH_DEV_SYSFS;
+		return;
+	}
+
 	device_remove_file(&pdev->dev, &dev_attr_eeh_mode);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_config_addr);
 	device_remove_file(&pdev->dev, &dev_attr_eeh_pe_config_addr);
+
+	if (edev)
+		edev->mode &= ~EEH_DEV_SYSFS;
 }
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index ab15b8d057a..2bd0b885b0f 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -449,15 +449,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_DSCR)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 BEGIN_FTR_SECTION
-	/*
-	 * Back up the TAR across context switches.  Note that the TAR is not
-	 * available for use in the kernel.  (To provide this, the TAR should
-	 * be backed up/restored on exception entry/exit instead, and be in
-	 * pt_regs.  FIXME, this should be in pt_regs anyway (for debug).)
-	 */
-	mfspr	r0,SPRN_TAR
-	std	r0,THREAD_TAR(r3)
-
 	/* Event based branch registers */
 	mfspr	r0, SPRN_BESCR
 	std	r0, THREAD_BESCR(r3)
@@ -584,9 +575,34 @@ BEGIN_FTR_SECTION
 	ld	r7,DSCR_DEFAULT@toc(2)
 	ld	r0,THREAD_DSCR(r4)
 	cmpwi	r6,0
+	li	r8, FSCR_DSCR
 	bne	1f
 	ld	r0,0(r7)
-1:	cmpd	r0,r25
+	b	3f
+1:
+  BEGIN_FTR_SECTION_NESTED(70)
+	mfspr	r6, SPRN_FSCR
+	or	r6, r6, r8
+	mtspr	SPRN_FSCR, r6
+    BEGIN_FTR_SECTION_NESTED(69)
+	mfspr	r6, SPRN_HFSCR
+	or	r6, r6, r8
+	mtspr	SPRN_HFSCR, r6
+    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+	b	4f
+  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+3:
+  BEGIN_FTR_SECTION_NESTED(70)
+	mfspr	r6, SPRN_FSCR
+	andc	r6, r6, r8
+	mtspr	SPRN_FSCR, r6
+    BEGIN_FTR_SECTION_NESTED(69)
+	mfspr	r6, SPRN_HFSCR
+	andc	r6, r6, r8
+	mtspr	SPRN_HFSCR, r6
+    END_FTR_SECTION_NESTED(CPU_FTR_HVMODE, CPU_FTR_HVMODE, 69)
+  END_FTR_SECTION_NESTED(CPU_FTR_ARCH_207S, CPU_FTR_ARCH_207S, 70)
+4:	cmpd	r0,r25
 	beq	2f
 	mtspr	SPRN_DSCR,r0
 2:
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 4e00d223b2e..902ca3c6b4b 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -848,7 +848,7 @@ hv_facility_unavailable_relon_trampoline:
 	. = 0x4f80
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	facility_unavailable_relon_hv
+	b	hv_facility_unavailable_relon_hv
 
 	STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint)
 #ifdef CONFIG_PPC_DENORMALISATION
@@ -1175,6 +1175,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	b	.ret_from_except
 
 	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
+	STD_EXCEPTION_COMMON(0xf80, hv_facility_unavailable, .facility_unavailable_exception)
 
 	.align	7
 	.globl	__end_handlers
@@ -1188,7 +1189,7 @@ __end_handlers:
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
-	STD_RELON_EXCEPTION_HV_OOL(0xf80, facility_unavailable)
+	STD_RELON_EXCEPTION_HV_OOL(0xf80, hv_facility_unavailable)
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 2e51cde616d..c69440cef7a 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -362,7 +362,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).spurious_irqs);
 	seq_printf(p, "  Spurious interrupts\n");
 
-	seq_printf(p, "%*s: ", prec, "CNT");
+	seq_printf(p, "%*s: ", prec, "PMI");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", per_cpu(irq_stat, j).pmu_irqs);
 	seq_printf(p, "  Performance monitoring interrupts\n");
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index f46914a0f33..7d22a675fe1 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -1462,6 +1462,8 @@ void pcibios_finish_adding_to_bus(struct pci_bus *bus)
 	/* Allocate bus and devices resources */
 	pcibios_allocate_bus_resources(bus);
 	pcibios_claim_one_bus(bus);
+	if (!pci_has_flag(PCI_PROBE_ONLY))
+		pci_assign_unassigned_bus_resources(bus);
 
 	/* Fixup EEH */
 	eeh_add_device_tree_late(bus);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 3f608800c06..c1e17ae68a0 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -22,45 +22,40 @@
 #include <asm/eeh.h>
 
 /**
- * __pcibios_remove_pci_devices - remove all devices under this bus
+ * pcibios_release_device - release PCI device
+ * @dev: PCI device
+ *
+ * The function is called before releasing the indicated PCI device.
+ */
+void pcibios_release_device(struct pci_dev *dev)
+{
+	eeh_remove_device(dev);
+}
+
+/**
+ * pcibios_remove_pci_devices - remove all devices under this bus
  * @bus: the indicated PCI bus
- * @purge_pe: destroy the PE on removal of PCI devices
  *
  * Remove all of the PCI devices under this bus both from the
  * linux pci device tree, and from the powerpc EEH address cache.
- * By default, the corresponding PE will be destroied during the
- * normal PCI hotplug path. For PCI hotplug during EEH recovery,
- * the corresponding PE won't be destroied and deallocated.
  */
-void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe)
+void pcibios_remove_pci_devices(struct pci_bus *bus)
 {
 	struct pci_dev *dev, *tmp;
 	struct pci_bus *child_bus;
 
 	/* First go down child busses */
 	list_for_each_entry(child_bus, &bus->children, node)
-		__pcibios_remove_pci_devices(child_bus, purge_pe);
+		pcibios_remove_pci_devices(child_bus);
 
 	pr_debug("PCI: Removing devices on bus %04x:%02x\n",
 		 pci_domain_nr(bus),  bus->number);
 	list_for_each_entry_safe(dev, tmp, &bus->devices, bus_list) {
-		pr_debug("     * Removing %s...\n", pci_name(dev));
-		eeh_remove_bus_device(dev, purge_pe);
+		pr_debug("   Removing %s...\n", pci_name(dev));
 		pci_stop_and_remove_bus_device(dev);
 	}
 }
 
-/**
- * pcibios_remove_pci_devices - remove all devices under this bus
- * @bus: the indicated PCI bus
- *
- * Remove all of the PCI devices under this bus both from the
- * linux pci device tree, and from the powerpc EEH address cache.
- */
-void pcibios_remove_pci_devices(struct pci_bus *bus)
-{
-	__pcibios_remove_pci_devices(bus, 1);
-}
 EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
 
 /**
@@ -76,7 +71,7 @@ EXPORT_SYMBOL_GPL(pcibios_remove_pci_devices);
  */
 void pcibios_add_pci_devices(struct pci_bus * bus)
 {
-	int slotno, num, mode, pass, max;
+	int slotno, mode, pass, max;
 	struct pci_dev *dev;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
@@ -90,11 +85,15 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 		/* use ofdt-based probe */
 		of_rescan_bus(dn, bus);
 	} else if (mode == PCI_PROBE_NORMAL) {
-		/* use legacy probe */
+		/*
+		 * Use legacy probe. In the partial hotplug case, we
+		 * probably have grandchildren devices unplugged. So
+		 * we don't check the return value from pci_scan_slot() in
+		 * order for fully rescan all the way down to pick them up.
+		 * They can have been removed during partial hotplug.
+		 */
 		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
-		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
-		if (!num)
-			return;
+		pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
 		pcibios_setup_bus_devices(bus);
 		max = bus->busn_res.start;
 		for (pass = 0; pass < 2; pass++) {
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index 6b0ba5854d9..15d9105323b 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -230,11 +230,14 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		return;
 	}
 
-	bus = pci_add_new_bus(dev->bus, dev, busrange[0]);
+	bus = pci_find_bus(pci_domain_nr(dev->bus), busrange[0]);
 	if (!bus) {
-		printk(KERN_ERR "Failed to create pci bus for %s\n",
-		       node->full_name);
-		return;
+		bus = pci_add_new_bus(dev->bus, dev, busrange[0]);
+		if (!bus) {
+			printk(KERN_ERR "Failed to create pci bus for %s\n",
+			       node->full_name);
+			return;
+		}
 	}
 
 	bus->primary = dev->bus->number;
@@ -292,6 +295,38 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 }
 EXPORT_SYMBOL(of_scan_pci_bridge);
 
+static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus,
+			    struct device_node *dn)
+{
+	struct pci_dev *dev = NULL;
+	const u32 *reg;
+	int reglen, devfn;
+
+	pr_debug("  * %s\n", dn->full_name);
+	if (!of_device_is_available(dn))
+		return NULL;
+
+	reg = of_get_property(dn, "reg", &reglen);
+	if (reg == NULL || reglen < 20)
+		return NULL;
+	devfn = (reg[0] >> 8) & 0xff;
+
+	/* Check if the PCI device is already there */
+	dev = pci_get_slot(bus, devfn);
+	if (dev) {
+		pci_dev_put(dev);
+		return dev;
+	}
+
+	/* create a new pci_dev for this device */
+	dev = of_create_pci_dev(dn, bus, devfn);
+	if (!dev)
+		return NULL;
+
+	pr_debug("  dev header type: %x\n", dev->hdr_type);
+	return dev;
+}
+
 /**
  * __of_scan_bus - given a PCI bus node, setup bus and scan for child devices
  * @node: device tree node for the PCI bus
@@ -302,8 +337,6 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus,
 			  int rescan_existing)
 {
 	struct device_node *child;
-	const u32 *reg;
-	int reglen, devfn;
 	struct pci_dev *dev;
 
 	pr_debug("of_scan_bus(%s) bus no %d...\n",
@@ -311,16 +344,7 @@ static void __of_scan_bus(struct device_node *node, struct pci_bus *bus,
 
 	/* Scan direct children */
 	for_each_child_of_node(node, child) {
-		pr_debug("  * %s\n", child->full_name);
-		if (!of_device_is_available(child))
-			continue;
-		reg = of_get_property(child, "reg", &reglen);
-		if (reg == NULL || reglen < 20)
-			continue;
-		devfn = (reg[0] >> 8) & 0xff;
-
-		/* create a new pci_dev for this device */
-		dev = of_create_pci_dev(child, bus, devfn);
+		dev = of_scan_pci_dev(bus, child);
 		if (!dev)
 			continue;
 		pr_debug("    dev header type: %x\n", dev->hdr_type);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index c517dbe705f..8083be20fe5 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -600,6 +600,16 @@ struct task_struct *__switch_to(struct task_struct *prev,
 	struct ppc64_tlb_batch *batch;
 #endif
 
+	/* Back up the TAR across context switches.
+	 * Note that the TAR is not available for use in the kernel.  (To
+	 * provide this, the TAR should be backed up/restored on exception
+	 * entry/exit instead, and be in pt_regs.  FIXME, this should be in
+	 * pt_regs anyway (for debug).)
+	 * Save the TAR here before we do treclaim/trecheckpoint as these
+	 * will change the TAR.
+	 */
+	save_tar(&prev->thread);
+
 	__switch_to_tm(prev);
 
 #ifdef CONFIG_SMP
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 5eccda9fd33..607902424e7 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -644,7 +644,8 @@ unsigned char ibm_architecture_vec[] = {
 	W(0xfffe0000), W(0x003a0000),	/* POWER5/POWER5+ */
 	W(0xffff0000), W(0x003e0000),	/* POWER6 */
 	W(0xffff0000), W(0x003f0000),	/* POWER7 */
-	W(0xffff0000), W(0x004b0000),	/* POWER8 */
+	W(0xffff0000), W(0x004b0000),	/* POWER8E */
+	W(0xffff0000), W(0x004d0000),	/* POWER8 */
 	W(0xffffffff), W(0x0f000004),	/* all 2.07-compliant */
 	W(0xffffffff), W(0x0f000003),	/* all 2.06-compliant */
 	W(0xffffffff), W(0x0f000002),	/* all 2.05-compliant */
@@ -706,7 +707,7 @@ unsigned char ibm_architecture_vec[] = {
 	 * must match by the macro below. Update the definition if
 	 * the structure layout changes.
 	 */
-#define IBM_ARCH_VEC_NRCORES_OFFSET	117
+#define IBM_ARCH_VEC_NRCORES_OFFSET	125
 	W(NR_CPUS),			/* number of cores supported */
 	0,
 	0,
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 51be8fb2480..0554d1f6d70 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -233,6 +233,16 @@ dont_backup_fp:
 	std	r5, _CCR(r7)
 	std	r6, _XER(r7)
 
+
+	/* ******************** TAR, PPR, DSCR ********** */
+	mfspr	r3, SPRN_TAR
+	mfspr	r4, SPRN_PPR
+	mfspr	r5, SPRN_DSCR
+
+	std	r3, THREAD_TM_TAR(r12)
+	std	r4, THREAD_TM_PPR(r12)
+	std	r5, THREAD_TM_DSCR(r12)
+
 	/* MSR and flags:  We don't change CRs, and we don't need to alter
 	 * MSR.
 	 */
@@ -347,6 +357,16 @@ dont_restore_fp:
 	mtmsr	r6				/* FP/Vec off again! */
 
 restore_gprs:
+
+	/* ******************** TAR, PPR, DSCR ********** */
+	ld	r4, THREAD_TM_TAR(r3)
+	ld	r5, THREAD_TM_PPR(r3)
+	ld	r6, THREAD_TM_DSCR(r3)
+
+	mtspr	SPRN_TAR,	r4
+	mtspr	SPRN_PPR,	r5
+	mtspr	SPRN_DSCR,	r6
+
 	/* ******************** CR,LR,CCR,MSR ********** */
 	ld	r3, _CTR(r7)
 	ld	r4, _LINK(r7)
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index bf33c22e38a..e435bc089ea 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -44,9 +44,7 @@
 #include <asm/machdep.h>
 #include <asm/rtas.h>
 #include <asm/pmc.h>
-#ifdef CONFIG_PPC32
 #include <asm/reg.h>
-#endif
 #ifdef CONFIG_PMAC_BACKLIGHT
 #include <asm/backlight.h>
 #endif
@@ -1296,43 +1294,54 @@ void vsx_unavailable_exception(struct pt_regs *regs)
 	die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
 }
 
+#ifdef CONFIG_PPC64
 void facility_unavailable_exception(struct pt_regs *regs)
 {
 	static char *facility_strings[] = {
-		"FPU",
-		"VMX/VSX",
-		"DSCR",
-		"PMU SPRs",
-		"BHRB",
-		"TM",
-		"AT",
-		"EBB",
-		"TAR",
+		[FSCR_FP_LG] = "FPU",
+		[FSCR_VECVSX_LG] = "VMX/VSX",
+		[FSCR_DSCR_LG] = "DSCR",
+		[FSCR_PM_LG] = "PMU SPRs",
+		[FSCR_BHRB_LG] = "BHRB",
+		[FSCR_TM_LG] = "TM",
+		[FSCR_EBB_LG] = "EBB",
+		[FSCR_TAR_LG] = "TAR",
 	};
-	char *facility, *prefix;
+	char *facility = "unknown";
 	u64 value;
+	u8 status;
+	bool hv;
 
-	if (regs->trap == 0xf60) {
-		value = mfspr(SPRN_FSCR);
-		prefix = "";
-	} else {
+	hv = (regs->trap == 0xf80);
+	if (hv)
 		value = mfspr(SPRN_HFSCR);
-		prefix = "Hypervisor ";
+	else
+		value = mfspr(SPRN_FSCR);
+
+	status = value >> 56;
+	if (status == FSCR_DSCR_LG) {
+		/* User is acessing the DSCR.  Set the inherit bit and allow
+		 * the user to set it directly in future by setting via the
+		 * H/FSCR DSCR bit.
+		 */
+		current->thread.dscr_inherit = 1;
+		if (hv)
+			mtspr(SPRN_HFSCR, value | HFSCR_DSCR);
+		else
+			mtspr(SPRN_FSCR,  value | FSCR_DSCR);
+		return;
 	}
 
-	value = value >> 56;
+	if ((status < ARRAY_SIZE(facility_strings)) &&
+	    facility_strings[status])
+		facility = facility_strings[status];
 
 	/* We restore the interrupt state now */
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	if (value < ARRAY_SIZE(facility_strings))
-		facility = facility_strings[value];
-	else
-		facility = "unknown";
-
 	pr_err("%sFacility '%s' unavailable, exception at 0x%lx, MSR=%lx\n",
-		prefix, facility, regs->nip, regs->msr);
+	       hv ? "Hypervisor " : "", facility, regs->nip, regs->msr);
 
 	if (user_mode(regs)) {
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
@@ -1341,6 +1350,7 @@ void facility_unavailable_exception(struct pt_regs *regs)
 
 	die("Unexpected facility unavailable exception", regs, SIGABRT);
 }
+#endif
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 654e479802f..f096e72262f 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -38,9 +38,6 @@ jiffies = jiffies_64 + 4;
 #endif
 SECTIONS
 {
-	. = 0;
-	reloc_start = .;
-
 	. = KERNELBASE;
 
 /*