Merge Linus master into drm-next

The merge is clean, but the arm build fails afterwards,
due to API changes in the regulator tree.

I've included the patch into the merge to fix the build.

Signed-off-by: Dave Airlie <airlied@redhat.com>

31 files changed, 1440 insertions, 309 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 502cf69b6c89..c1ebbdaac28f 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -33,7 +33,8 @@ obj-y				:= cputable.o ptrace.o syscalls.o \
 				   signal.o sysfs.o cacheinfo.o time.o \
 				   prom.o traps.o setup-common.o \
 				   udbg.o misc.o io.o dma.o \
-				   misc_$(CONFIG_WORD_SIZE).o vdso32/
+				   misc_$(CONFIG_WORD_SIZE).o vdso32/ \
+				   of_platform.o prom_parse.o
 obj-$(CONFIG_PPC64)		+= setup_64.o sys_ppc32.o \
 				   signal_64.o ptrace32.o \
 				   paca.o nvram_64.o firmware.o
@@ -47,7 +48,6 @@ obj-$(CONFIG_PPC64)		+= vdso64/
 obj-$(CONFIG_ALTIVEC)		+= vecemu.o
 obj-$(CONFIG_PPC_970_NAP)	+= idle_power4.o
 obj-$(CONFIG_PPC_P7_NAP)	+= idle_power7.o
-obj-$(CONFIG_PPC_OF)		+= of_platform.o prom_parse.o
 procfs-y			:= proc_powerpc.o
 obj-$(CONFIG_PROC_FS)		+= $(procfs-y)
 rtaspci-$(CONFIG_PPC64)-$(CONFIG_PCI)	:= rtas_pci.o
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index ae77b7e59889..c641983bbdd6 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -61,12 +61,22 @@ struct cache_type_info {
 };
 
 /* These are used to index the cache_type_info array. */
-#define CACHE_TYPE_UNIFIED     0
-#define CACHE_TYPE_INSTRUCTION 1
-#define CACHE_TYPE_DATA        2
+#define CACHE_TYPE_UNIFIED     0 /* cache-size, cache-block-size, etc. */
+#define CACHE_TYPE_UNIFIED_D   1 /* d-cache-size, d-cache-block-size, etc */
+#define CACHE_TYPE_INSTRUCTION 2
+#define CACHE_TYPE_DATA        3
 
 static const struct cache_type_info cache_type_info[] = {
 	{
+		/* Embedded systems that use cache-size, cache-block-size,
+		 * etc. for the Unified (typically L2) cache. */
+		.name            = "Unified",
+		.size_prop       = "cache-size",
+		.line_size_props = { "cache-line-size",
+				     "cache-block-size", },
+		.nr_sets_prop    = "cache-sets",
+	},
+	{
 		/* PowerPC Processor binding says the [di]-cache-*
 		 * must be equal on unified caches, so just use
 		 * d-cache properties. */
@@ -293,7 +303,8 @@ static struct cache *cache_find_first_sibling(struct cache *cache)
 {
 	struct cache *iter;
 
-	if (cache->type == CACHE_TYPE_UNIFIED)
+	if (cache->type == CACHE_TYPE_UNIFIED ||
+	    cache->type == CACHE_TYPE_UNIFIED_D)
 		return cache;
 
 	list_for_each_entry(iter, &cache_list, list)
@@ -324,16 +335,29 @@ static bool cache_node_is_unified(const struct device_node *np)
 	return of_get_property(np, "cache-unified", NULL);
 }
 
-static struct cache *cache_do_one_devnode_unified(struct device_node *node,
-						  int level)
+/*
+ * Unified caches can have two different sets of tags.  Most embedded
+ * use cache-size, etc. for the unified cache size, but open firmware systems
+ * use d-cache-size, etc.   Check on initialization for which type we have, and
+ * return the appropriate structure type.  Assume it's embedded if it isn't
+ * open firmware.  If it's yet a 3rd type, then there will be missing entries
+ * in /sys/devices/system/cpu/cpu0/cache/index2/, and this code will need
+ * to be extended further.
+ */
+static int cache_is_unified_d(const struct device_node *np)
 {
-	struct cache *cache;
+	return of_get_property(np,
+		cache_type_info[CACHE_TYPE_UNIFIED_D].size_prop, NULL) ?
+		CACHE_TYPE_UNIFIED_D : CACHE_TYPE_UNIFIED;
+}
 
+/*
+ */
+static struct cache *cache_do_one_devnode_unified(struct device_node *node, int level)
+{
 	pr_debug("creating L%d ucache for %s\n", level, node->full_name);
 
-	cache = new_cache(CACHE_TYPE_UNIFIED, level, node);
-
-	return cache;
+	return new_cache(cache_is_unified_d(node), level, node);
 }
 
 static struct cache *cache_do_one_devnode_split(struct device_node *node,
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index 46733535cc0b..9c9b7411b28b 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -137,15 +137,11 @@ __init_HFSCR:
 /*
  * Clear the TLB using the specified IS form of tlbiel instruction
  * (invalidate by congruence class). P7 has 128 CCs., P8 has 512.
- *
- * r3 = IS field
  */
 __init_tlb_power7:
-	li	r3,0xc00	/* IS field = 0b11 */
-_GLOBAL(__flush_tlb_power7)
 	li	r6,128
 	mtctr	r6
-	mr	r7,r3		/* IS field */
+	li	r7,0xc00	/* IS field = 0b11 */
 	ptesync
 2:	tlbiel	r7
 	addi	r7,r7,0x1000
@@ -154,11 +150,9 @@ _GLOBAL(__flush_tlb_power7)
 1:	blr
 
 __init_tlb_power8:
-	li	r3,0xc00	/* IS field = 0b11 */
-_GLOBAL(__flush_tlb_power8)
 	li	r6,512
 	mtctr	r6
-	mr	r7,r3		/* IS field */
+	li	r7,0xc00	/* IS field = 0b11 */
 	ptesync
 2:	tlbiel	r7
 	addi	r7,r7,0x1000
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index f83046878336..60262fdf35ba 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -71,8 +71,8 @@ extern void __restore_cpu_power7(void);
 extern void __setup_cpu_power8(unsigned long offset, struct cpu_spec* spec);
 extern void __restore_cpu_power8(void);
 extern void __restore_cpu_a2(void);
-extern void __flush_tlb_power7(unsigned long inval_selector);
-extern void __flush_tlb_power8(unsigned long inval_selector);
+extern void __flush_tlb_power7(unsigned int action);
+extern void __flush_tlb_power8(unsigned int action);
 extern long __machine_check_early_realmode_p7(struct pt_regs *regs);
 extern long __machine_check_early_realmode_p8(struct pt_regs *regs);
 #endif /* CONFIG_PPC64 */
diff --git a/arch/powerpc/kernel/dma-swiotlb.c b/arch/powerpc/kernel/dma-swiotlb.c
index 735979764cd4..6e8d764ce47b 100644
--- a/arch/powerpc/kernel/dma-swiotlb.c
+++ b/arch/powerpc/kernel/dma-swiotlb.c
@@ -116,16 +116,13 @@ void __init swiotlb_detect_4g(void)
 	}
 }
 
-static int __init swiotlb_late_init(void)
+static int __init check_swiotlb_enabled(void)
 {
-	if (ppc_swiotlb_enable) {
+	if (ppc_swiotlb_enable)
 		swiotlb_print_info();
-		set_pci_dma_ops(&swiotlb_dma_ops);
-		ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_swiotlb;
-	} else {
+	else
 		swiotlb_free();
-	}
 
 	return 0;
 }
-subsys_initcall(swiotlb_late_init);
+subsys_initcall(check_swiotlb_enabled);
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 3b2252e7731b..a4c62eb0ee48 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -164,30 +164,34 @@ __setup("eeh=", eeh_setup);
  */
 static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 {
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	u32 cfg;
 	int cap, i;
 	int n = 0, l = 0;
 	char buffer[128];
 
-	n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
-	pr_warn("EEH: of node=%s\n", dn->full_name);
+	n += scnprintf(buf+n, len-n, "%04x:%02x:%02x:%01x\n",
+		       edev->phb->global_number, pdn->busno,
+		       PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
+	pr_warn("EEH: of node=%04x:%02x:%02x:%01x\n",
+		edev->phb->global_number, pdn->busno,
+		PCI_SLOT(pdn->devfn), PCI_FUNC(pdn->devfn));
 
-	eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
+	eeh_ops->read_config(pdn, PCI_VENDOR_ID, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
 	pr_warn("EEH: PCI device/vendor: %08x\n", cfg);
 
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
+	eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cfg);
 	n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
 	pr_warn("EEH: PCI cmd/status register: %08x\n", cfg);
 
 	/* Gather bridge-specific registers */
 	if (edev->mode & EEH_DEV_BRIDGE) {
-		eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
+		eeh_ops->read_config(pdn, PCI_SEC_STATUS, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
 		pr_warn("EEH: Bridge secondary status: %04x\n", cfg);
 
-		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
+		eeh_ops->read_config(pdn, PCI_BRIDGE_CONTROL, 2, &cfg);
 		n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
 		pr_warn("EEH: Bridge control: %04x\n", cfg);
 	}
@@ -195,11 +199,11 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 	/* Dump out the PCI-X command and status regs */
 	cap = edev->pcix_cap;
 	if (cap) {
-		eeh_ops->read_config(dn, cap, 4, &cfg);
+		eeh_ops->read_config(pdn, cap, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
 		pr_warn("EEH: PCI-X cmd: %08x\n", cfg);
 
-		eeh_ops->read_config(dn, cap+4, 4, &cfg);
+		eeh_ops->read_config(pdn, cap+4, 4, &cfg);
 		n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
 		pr_warn("EEH: PCI-X status: %08x\n", cfg);
 	}
@@ -211,7 +215,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 		pr_warn("EEH: PCI-E capabilities and status follow:\n");
 
 		for (i=0; i<=8; i++) {
-			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
 			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
 
 			if ((i % 4) == 0) {
@@ -238,7 +242,7 @@ static size_t eeh_dump_dev_log(struct eeh_dev *edev, char *buf, size_t len)
 		pr_warn("EEH: PCI-E AER capability register set follows:\n");
 
 		for (i=0; i<=13; i++) {
-			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			eeh_ops->read_config(pdn, cap+4*i, 4, &cfg);
 			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
 
 			if ((i % 4) == 0) {
@@ -414,11 +418,11 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	int ret;
 	int active_flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
 	unsigned long flags;
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct pci_dev *dev;
 	struct eeh_pe *pe, *parent_pe, *phb_pe;
 	int rc = 0;
-	const char *location;
+	const char *location = NULL;
 
 	eeh_stats.total_mmio_ffs++;
 
@@ -429,15 +433,14 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 		eeh_stats.no_dn++;
 		return 0;
 	}
-	dn = eeh_dev_to_of_node(edev);
 	dev = eeh_dev_to_pci_dev(edev);
 	pe = eeh_dev_to_pe(edev);
 
 	/* Access to IO BARs might get this far and still not want checking. */
 	if (!pe) {
 		eeh_stats.ignored_check++;
-		pr_debug("EEH: Ignored check for %s %s\n",
-			eeh_pci_name(dev), dn->full_name);
+		pr_debug("EEH: Ignored check for %s\n",
+			eeh_pci_name(dev));
 		return 0;
 	}
 
@@ -473,10 +476,13 @@ int eeh_dev_check_failure(struct eeh_dev *edev)
 	if (pe->state & EEH_PE_ISOLATED) {
 		pe->check_count++;
 		if (pe->check_count % EEH_MAX_FAILS == 0) {
-			location = of_get_property(dn, "ibm,loc-code", NULL);
+			pdn = eeh_dev_to_pdn(edev);
+			if (pdn->node)
+				location = of_get_property(pdn->node, "ibm,loc-code", NULL);
 			printk(KERN_ERR "EEH: %d reads ignored for recovering device at "
 				"location=%s driver=%s pci addr=%s\n",
-				pe->check_count, location,
+				pe->check_count,
+				location ? location : "unknown",
 				eeh_driver_name(dev), eeh_pci_name(dev));
 			printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n",
 				eeh_driver_name(dev));
@@ -667,6 +673,55 @@ int eeh_pci_enable(struct eeh_pe *pe, int function)
 	return rc;
 }
 
+static void *eeh_disable_and_save_dev_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+	struct pci_dev *dev = userdata;
+
+	/*
+	 * The caller should have disabled and saved the
+	 * state for the specified device
+	 */
+	if (!pdev || pdev == dev)
+		return NULL;
+
+	/* Ensure we have D0 power state */
+	pci_set_power_state(pdev, PCI_D0);
+
+	/* Save device state */
+	pci_save_state(pdev);
+
+	/*
+	 * Disable device to avoid any DMA traffic and
+	 * interrupt from the device
+	 */
+	pci_write_config_word(pdev, PCI_COMMAND, PCI_COMMAND_INTX_DISABLE);
+
+	return NULL;
+}
+
+static void *eeh_restore_dev_state(void *data, void *userdata)
+{
+	struct eeh_dev *edev = data;
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
+	struct pci_dev *pdev = eeh_dev_to_pci_dev(edev);
+	struct pci_dev *dev = userdata;
+
+	if (!pdev)
+		return NULL;
+
+	/* Apply customization from firmware */
+	if (pdn && eeh_ops->restore_config)
+		eeh_ops->restore_config(pdn);
+
+	/* The caller should restore state for the specified device */
+	if (pdev != dev)
+		pci_save_state(pdev);
+
+	return NULL;
+}
+
 /**
  * pcibios_set_pcie_slot_reset - Set PCI-E reset state
  * @dev: pci device struct
@@ -689,13 +744,19 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state stat
 	switch (state) {
 	case pcie_deassert_reset:
 		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+		eeh_unfreeze_pe(pe, false);
 		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+		eeh_pe_dev_traverse(pe, eeh_restore_dev_state, dev);
 		break;
 	case pcie_hot_reset:
+		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_HOT);
 		break;
 	case pcie_warm_reset:
+		eeh_ops->set_option(pe, EEH_OPT_FREEZE_PE);
+		eeh_pe_dev_traverse(pe, eeh_disable_and_save_dev_state, dev);
 		eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
 		break;
@@ -815,15 +876,15 @@ out:
  */
 void eeh_save_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn;
 	int i;
-	struct device_node *dn;
 
-	if (!edev)
+	pdn = eeh_dev_to_pdn(edev);
+	if (!pdn)
 		return;
-	dn = eeh_dev_to_of_node(edev);
 
 	for (i = 0; i < 16; i++)
-		eeh_ops->read_config(dn, i * 4, 4, &edev->config_space[i]);
+		eeh_ops->read_config(pdn, i * 4, 4, &edev->config_space[i]);
 
 	/*
 	 * For PCI bridges including root port, we need enable bus
@@ -914,7 +975,7 @@ static struct notifier_block eeh_reboot_nb = {
 int eeh_init(void)
 {
 	struct pci_controller *hose, *tmp;
-	struct device_node *phb;
+	struct pci_dn *pdn;
 	static int cnt = 0;
 	int ret = 0;
 
@@ -949,20 +1010,9 @@ int eeh_init(void)
 		return ret;
 
 	/* Enable EEH for all adapters */
-	if (eeh_has_flag(EEH_PROBE_MODE_DEVTREE)) {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node) {
-			phb = hose->dn;
-			traverse_pci_devices(phb, eeh_ops->of_probe, NULL);
-		}
-	} else if (eeh_has_flag(EEH_PROBE_MODE_DEV)) {
-		list_for_each_entry_safe(hose, tmp,
-			&hose_list, list_node)
-			pci_walk_bus(hose->bus, eeh_ops->dev_probe, NULL);
-	} else {
-		pr_warn("%s: Invalid probe mode %x",
-			__func__, eeh_subsystem_flags);
-		return -EINVAL;
+	list_for_each_entry_safe(hose, tmp, &hose_list, list_node) {
+		pdn = hose->pci_data;
+		traverse_pci_dn(pdn, eeh_ops->probe, NULL);
 	}
 
 	/*
@@ -987,8 +1037,8 @@ int eeh_init(void)
 core_initcall_sync(eeh_init);
 
 /**
- * eeh_add_device_early - Enable EEH for the indicated device_node
- * @dn: device node for which to set up EEH
+ * eeh_add_device_early - Enable EEH for the indicated device node
+ * @pdn: PCI device node for which to set up EEH
  *
  * This routine must be used to perform EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
@@ -998,44 +1048,41 @@ core_initcall_sync(eeh_init);
  * on the CEC architecture, type of the device, on earlier boot
  * command-line arguments & etc.
  */
-void eeh_add_device_early(struct device_node *dn)
+void eeh_add_device_early(struct pci_dn *pdn)
 {
 	struct pci_controller *phb;
+	struct eeh_dev *edev = pdn_to_eeh_dev(pdn);
 
-	/*
-	 * If we're doing EEH probe based on PCI device, we
-	 * would delay the probe until late stage because
-	 * the PCI device isn't available this moment.
-	 */
-	if (!eeh_has_flag(EEH_PROBE_MODE_DEVTREE))
+	if (!edev || !eeh_enabled())
 		return;
 
-	if (!of_node_to_eeh_dev(dn))
-		return;
-	phb = of_node_to_eeh_dev(dn)->phb;
-
 	/* USB Bus children of PCI devices will not have BUID's */
-	if (NULL == phb || 0 == phb->buid)
+	phb = edev->phb;
+	if (NULL == phb ||
+	    (eeh_has_flag(EEH_PROBE_MODE_DEVTREE) && 0 == phb->buid))
 		return;
 
-	eeh_ops->of_probe(dn, NULL);
+	eeh_ops->probe(pdn, NULL);
 }
 
 /**
  * eeh_add_device_tree_early - Enable EEH for the indicated device
- * @dn: device node
+ * @pdn: PCI device node
  *
  * This routine must be used to perform EEH initialization for the
  * indicated PCI device that was added after system boot (e.g.
  * hotplug, dlpar).
  */
-void eeh_add_device_tree_early(struct device_node *dn)
+void eeh_add_device_tree_early(struct pci_dn *pdn)
 {
-	struct device_node *sib;
+	struct pci_dn *n;
 
-	for_each_child_of_node(dn, sib)
-		eeh_add_device_tree_early(sib);
-	eeh_add_device_early(dn);
+	if (!pdn)
+		return;
+
+	list_for_each_entry(n, &pdn->child_list, list)
+		eeh_add_device_tree_early(n);
+	eeh_add_device_early(pdn);
 }
 EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
 
@@ -1048,7 +1095,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
  */
 void eeh_add_device_late(struct pci_dev *dev)
 {
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 
 	if (!dev || !eeh_enabled())
@@ -1056,8 +1103,8 @@ void eeh_add_device_late(struct pci_dev *dev)
 
 	pr_debug("EEH: Adding device %s\n", pci_name(dev));
 
-	dn = pci_device_to_OF_node(dev);
-	edev = of_node_to_eeh_dev(dn);
+	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
+	edev = pdn_to_eeh_dev(pdn);
 	if (edev->pdev == dev) {
 		pr_debug("EEH: Already referenced !\n");
 		return;
@@ -1089,13 +1136,6 @@ void eeh_add_device_late(struct pci_dev *dev)
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
-	/*
-	 * We have to do the EEH probe here because the PCI device
-	 * hasn't been created yet in the early stage.
-	 */
-	if (eeh_has_flag(EEH_PROBE_MODE_DEV))
-		eeh_ops->dev_probe(dev, NULL);
-
 	eeh_addr_cache_insert_dev(dev);
 }
 
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index 07d8a2423a61..eeabeabea49c 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -171,30 +171,27 @@ eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 
 static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
 {
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 	int i;
 
-	dn = pci_device_to_OF_node(dev);
-	if (!dn) {
+	pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
+	if (!pdn) {
 		pr_warn("PCI: no pci dn found for dev=%s\n",
 			pci_name(dev));
 		return;
 	}
 
-	edev = of_node_to_eeh_dev(dn);
+	edev = pdn_to_eeh_dev(pdn);
 	if (!edev) {
-		pr_warn("PCI: no EEH dev found for dn=%s\n",
-			dn->full_name);
+		pr_warn("PCI: no EEH dev found for %s\n",
+			pci_name(dev));
 		return;
 	}
 
 	/* Skip any devices for which EEH is not enabled. */
 	if (!edev->pe) {
-#ifdef DEBUG
-		pr_info("PCI: skip building address cache for=%s - %s\n",
-			pci_name(dev), dn->full_name);
-#endif
+		dev_dbg(&dev->dev, "EEH: Skip building address cache\n");
 		return;
 	}
 
@@ -282,18 +279,18 @@ void eeh_addr_cache_rmv_dev(struct pci_dev *dev)
  */
 void eeh_addr_cache_build(void)
 {
-	struct device_node *dn;
+	struct pci_dn *pdn;
 	struct eeh_dev *edev;
 	struct pci_dev *dev = NULL;
 
 	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
 
 	for_each_pci_dev(dev) {
-		dn = pci_device_to_OF_node(dev);
-		if (!dn)
+		pdn = pci_get_pdn_by_devfn(dev->bus, dev->devfn);
+		if (!pdn)
 			continue;
 
-		edev = of_node_to_eeh_dev(dn);
+		edev = pdn_to_eeh_dev(pdn);
 		if (!edev)
 			continue;
 
diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
index e5274ee9a75f..aabba94ff9cb 100644
--- a/arch/powerpc/kernel/eeh_dev.c
+++ b/arch/powerpc/kernel/eeh_dev.c
@@ -43,13 +43,13 @@
 
 /**
  * eeh_dev_init - Create EEH device according to OF node
- * @dn: device node
+ * @pdn: PCI device node
  * @data: PHB
  *
  * It will create EEH device according to the given OF node. The function
  * might be called by PCI emunation, DR, PHB hotplug.
  */
-void *eeh_dev_init(struct device_node *dn, void *data)
+void *eeh_dev_init(struct pci_dn *pdn, void *data)
 {
 	struct pci_controller *phb = data;
 	struct eeh_dev *edev;
@@ -63,8 +63,8 @@ void *eeh_dev_init(struct device_node *dn, void *data)
 	}
 
 	/* Associate EEH device with OF node */
-	PCI_DN(dn)->edev = edev;
-	edev->dn  = dn;
+	pdn->edev = edev;
+	edev->pdn = pdn;
 	edev->phb = phb;
 	INIT_LIST_HEAD(&edev->list);
 
@@ -80,16 +80,16 @@ void *eeh_dev_init(struct device_node *dn, void *data)
  */
 void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
 {
-	struct device_node *dn = phb->dn;
+	struct pci_dn *root = phb->pci_data;
 
 	/* EEH PE for PHB */
 	eeh_phb_pe_create(phb);
 
 	/* EEH device for PHB */
-	eeh_dev_init(dn, phb);
+	eeh_dev_init(root, phb);
 
 	/* EEH devices for children OF nodes */
-	traverse_pci_devices(dn, eeh_dev_init, phb);
+	traverse_pci_dn(root, eeh_dev_init, phb);
 }
 
 /**
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index d099540c0f56..24768ff3cb73 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -83,28 +83,6 @@ static inline void eeh_pcid_put(struct pci_dev *pdev)
 	module_put(pdev->driver->driver.owner);
 }
 
-#if 0
-static void print_device_node_tree(struct pci_dn *pdn, int dent)
-{
-	int i;
-	struct device_node *pc;
-
-	if (!pdn)
-		return;
-	for (i = 0; i < dent; i++)
-		printk(" ");
-	printk("dn=%s mode=%x \tcfg_addr=%x pe_addr=%x \tfull=%s\n",
-		pdn->node->name, pdn->eeh_mode, pdn->eeh_config_addr,
-		pdn->eeh_pe_config_addr, pdn->node->full_name);
-	dent += 3;
-	pc = pdn->node->child;
-	while (pc) {
-		print_device_node_tree(PCI_DN(pc), dent);
-		pc = pc->sibling;
-	}
-}
-#endif
-
 /**
  * eeh_disable_irq - Disable interrupt for the recovering device
  * @dev: PCI device
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
index 1e4946c36f9e..35f0b62259bb 100644
--- a/arch/powerpc/kernel/eeh_pe.c
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -291,27 +291,25 @@ struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
  */
 static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
 {
-	struct device_node *dn;
 	struct eeh_dev *parent;
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	/*
 	 * It might have the case for the indirect parent
 	 * EEH device already having associated PE, but
 	 * the direct parent EEH device doesn't have yet.
 	 */
-	dn = edev->dn->parent;
-	while (dn) {
+	pdn = pdn ? pdn->parent : NULL;
+	while (pdn) {
 		/* We're poking out of PCI territory */
-		if (!PCI_DN(dn)) return NULL;
-
-		parent = of_node_to_eeh_dev(dn);
-		/* We're poking out of PCI territory */
-		if (!parent) return NULL;
+		parent = pdn_to_eeh_dev(pdn);
+		if (!parent)
+			return NULL;
 
 		if (parent->pe)
 			return parent->pe;
 
-		dn = dn->parent;
+		pdn = pdn->parent;
 	}
 
 	return NULL;
@@ -330,6 +328,13 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 {
 	struct eeh_pe *pe, *parent;
 
+	/* Check if the PE number is valid */
+	if (!eeh_has_flag(EEH_VALID_PE_ZERO) && !edev->pe_config_addr) {
+		pr_err("%s: Invalid PE#0 for edev 0x%x on PHB#%d\n",
+		       __func__, edev->config_addr, edev->phb->global_number);
+		return -EINVAL;
+	}
+
 	/*
 	 * Search the PE has been existing or not according
 	 * to the PE address. If that has been existing, the
@@ -338,21 +343,18 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 	 */
 	pe = eeh_pe_get(edev);
 	if (pe && !(pe->type & EEH_PE_INVALID)) {
-		if (!edev->pe_config_addr) {
-			pr_err("%s: PE with addr 0x%x already exists\n",
-				__func__, edev->config_addr);
-			return -EEXIST;
-		}
-
 		/* Mark the PE as type of PCI bus */
 		pe->type = EEH_PE_BUS;
 		edev->pe = pe;
 
 		/* Put the edev to PE */
 		list_add_tail(&edev->list, &pe->edevs);
-		pr_debug("EEH: Add %s to Bus PE#%x\n",
-			edev->dn->full_name, pe->addr);
-
+		pr_debug("EEH: Add %04x:%02x:%02x.%01x to Bus PE#%x\n",
+			edev->phb->global_number,
+			edev->config_addr >> 8,
+			PCI_SLOT(edev->config_addr & 0xFF),
+			PCI_FUNC(edev->config_addr & 0xFF),
+			pe->addr);
 		return 0;
 	} else if (pe && (pe->type & EEH_PE_INVALID)) {
 		list_add_tail(&edev->list, &pe->edevs);
@@ -368,9 +370,14 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 			parent->type &= ~(EEH_PE_INVALID | EEH_PE_KEEP);
 			parent = parent->parent;
 		}
-		pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
-			edev->dn->full_name, pe->addr, pe->parent->addr);
 
+		pr_debug("EEH: Add %04x:%02x:%02x.%01x to Device "
+			 "PE#%x, Parent PE#%x\n",
+			edev->phb->global_number,
+			edev->config_addr >> 8,
+                        PCI_SLOT(edev->config_addr & 0xFF),
+                        PCI_FUNC(edev->config_addr & 0xFF),
+			pe->addr, pe->parent->addr);
 		return 0;
 	}
 
@@ -409,8 +416,13 @@ int eeh_add_to_parent_pe(struct eeh_dev *edev)
 	list_add_tail(&pe->child, &parent->child_list);
 	list_add_tail(&edev->list, &pe->edevs);
 	edev->pe = pe;
-	pr_debug("EEH: Add %s to Device PE#%x, Parent PE#%x\n",
-		edev->dn->full_name, pe->addr, pe->parent->addr);
+	pr_debug("EEH: Add %04x:%02x:%02x.%01x to "
+		 "Device PE#%x, Parent PE#%x\n",
+		 edev->phb->global_number,
+		 edev->config_addr >> 8,
+		 PCI_SLOT(edev->config_addr & 0xFF),
+		 PCI_FUNC(edev->config_addr & 0xFF),
+		 pe->addr, pe->parent->addr);
 
 	return 0;
 }
@@ -430,8 +442,11 @@ int eeh_rmv_from_parent_pe(struct eeh_dev *edev)
 	int cnt;
 
 	if (!edev->pe) {
-		pr_debug("%s: No PE found for EEH device %s\n",
-			 __func__, edev->dn->full_name);
+		pr_debug("%s: No PE found for device %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));
 		return -EEXIST;
 	}
 
@@ -653,9 +668,9 @@ 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 eeh_dev *edev,
-				  struct device_node *dn)
+static void eeh_bridge_check_link(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int cap;
 	uint32_t val;
 	int timeout = 0;
@@ -675,32 +690,32 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 
 	/* Check slot status */
 	cap = edev->pcie_cap;
-	eeh_ops->read_config(dn, cap + PCI_EXP_SLTSTA, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_SLTSTA, 2, &val);
 	if (!(val & PCI_EXP_SLTSTA_PDS)) {
 		pr_debug("  No card in the slot (0x%04x) !\n", val);
 		return;
 	}
 
 	/* Check power status if we have the capability */
-	eeh_ops->read_config(dn, cap + PCI_EXP_SLTCAP, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCAP, 2, &val);
 	if (val & PCI_EXP_SLTCAP_PCP) {
-		eeh_ops->read_config(dn, cap + PCI_EXP_SLTCTL, 2, &val);
+		eeh_ops->read_config(pdn, cap + PCI_EXP_SLTCTL, 2, &val);
 		if (val & PCI_EXP_SLTCTL_PCC) {
 			pr_debug("  In power-off state, power it on ...\n");
 			val &= ~(PCI_EXP_SLTCTL_PCC | PCI_EXP_SLTCTL_PIC);
 			val |= (0x0100 & PCI_EXP_SLTCTL_PIC);
-			eeh_ops->write_config(dn, cap + PCI_EXP_SLTCTL, 2, val);
+			eeh_ops->write_config(pdn, cap + PCI_EXP_SLTCTL, 2, val);
 			msleep(2 * 1000);
 		}
 	}
 
 	/* Enable link */
-	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCTL, 2, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCTL, 2, &val);
 	val &= ~PCI_EXP_LNKCTL_LD;
-	eeh_ops->write_config(dn, cap + PCI_EXP_LNKCTL, 2, val);
+	eeh_ops->write_config(pdn, cap + PCI_EXP_LNKCTL, 2, val);
 
 	/* Check link */
-	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCAP, 4, &val);
+	eeh_ops->read_config(pdn, cap + PCI_EXP_LNKCAP, 4, &val);
 	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
 		pr_debug("  No link reporting capability (0x%08x) \n", val);
 		msleep(1000);
@@ -713,7 +728,7 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 		msleep(20);
 		timeout += 20;
 
-		eeh_ops->read_config(dn, cap + PCI_EXP_LNKSTA, 2, &val);
+		eeh_ops->read_config(pdn, cap + PCI_EXP_LNKSTA, 2, &val);
 		if (val & PCI_EXP_LNKSTA_DLLLA)
 			break;
 	}
@@ -728,9 +743,9 @@ static void eeh_bridge_check_link(struct eeh_dev *edev,
 #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 eeh_dev *edev,
-				    struct device_node *dn)
+static void eeh_restore_bridge_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int i;
 
 	/*
@@ -738,49 +753,49 @@ static void eeh_restore_bridge_bars(struct eeh_dev *edev,
 	 * Bus numbers and windows: 0x18 - 0x30
 	 */
 	for (i = 4; i < 13; i++)
-		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+		eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
 	/* Rom: 0x38 */
-	eeh_ops->write_config(dn, 14*4, 4, edev->config_space[14]);
+	eeh_ops->write_config(pdn, 14*4, 4, edev->config_space[14]);
 
 	/* Cache line & Latency timer: 0xC 0xD */
-	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+	eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
                 SAVED_BYTE(PCI_CACHE_LINE_SIZE));
-        eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+        eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
                 SAVED_BYTE(PCI_LATENCY_TIMER));
 	/* Max latency, min grant, interrupt ping and line: 0x3C */
-	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/* PCI Command: 0x4 */
-	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, edev->config_space[1]);
 
 	/* Check the PCIe link is ready */
-	eeh_bridge_check_link(edev, dn);
+	eeh_bridge_check_link(edev);
 }
 
-static void eeh_restore_device_bars(struct eeh_dev *edev,
-				    struct device_node *dn)
+static void eeh_restore_device_bars(struct eeh_dev *edev)
 {
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 	int i;
 	u32 cmd;
 
 	for (i = 4; i < 10; i++)
-		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+		eeh_ops->write_config(pdn, i*4, 4, edev->config_space[i]);
 	/* 12 == Expansion ROM Address */
-	eeh_ops->write_config(dn, 12*4, 4, edev->config_space[12]);
+	eeh_ops->write_config(pdn, 12*4, 4, edev->config_space[12]);
 
-	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+	eeh_ops->write_config(pdn, PCI_CACHE_LINE_SIZE, 1,
 		SAVED_BYTE(PCI_CACHE_LINE_SIZE));
-	eeh_ops->write_config(dn, PCI_LATENCY_TIMER, 1,
+	eeh_ops->write_config(pdn, PCI_LATENCY_TIMER, 1,
 		SAVED_BYTE(PCI_LATENCY_TIMER));
 
 	/* max latency, min grant, interrupt pin and line */
-	eeh_ops->write_config(dn, 15*4, 4, edev->config_space[15]);
+	eeh_ops->write_config(pdn, 15*4, 4, edev->config_space[15]);
 
 	/*
 	 * Restore PERR & SERR bits, some devices require it,
 	 * don't touch the other command bits
 	 */
-	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd);
+	eeh_ops->read_config(pdn, PCI_COMMAND, 4, &cmd);
 	if (edev->config_space[1] & PCI_COMMAND_PARITY)
 		cmd |= PCI_COMMAND_PARITY;
 	else
@@ -789,7 +804,7 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
 		cmd |= PCI_COMMAND_SERR;
 	else
 		cmd &= ~PCI_COMMAND_SERR;
-	eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
+	eeh_ops->write_config(pdn, PCI_COMMAND, 4, cmd);
 }
 
 /**
@@ -804,16 +819,16 @@ static void eeh_restore_device_bars(struct eeh_dev *edev,
 static void *eeh_restore_one_device_bars(void *data, void *flag)
 {
 	struct eeh_dev *edev = (struct eeh_dev *)data;
-	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dn *pdn = eeh_dev_to_pdn(edev);
 
 	/* Do special restore for bridges */
 	if (edev->mode & EEH_DEV_BRIDGE)
-		eeh_restore_bridge_bars(edev, dn);
+		eeh_restore_bridge_bars(edev);
 	else
-		eeh_restore_device_bars(edev, dn);
+		eeh_restore_device_bars(edev);
 
-	if (eeh_ops->restore_config)
-		eeh_ops->restore_config(dn);
+	if (eeh_ops->restore_config && pdn)
+		eeh_ops->restore_config(pdn);
 
 	return NULL;
 }
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index d180caf2d6de..8ca9434c40e6 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -34,6 +34,7 @@
 #include <asm/ftrace.h>
 #include <asm/hw_irq.h>
 #include <asm/context_tracking.h>
+#include <asm/tm.h>
 
 /*
  * System calls.
@@ -145,6 +146,24 @@ END_FW_FTR_SECTION_IFSET(FW_FEATURE_SPLPAR)
 	andi.	r11,r10,_TIF_SYSCALL_DOTRACE
 	bne	syscall_dotrace
 .Lsyscall_dotrace_cont:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+BEGIN_FTR_SECTION
+	b	1f
+END_FTR_SECTION_IFCLR(CPU_FTR_TM)
+	extrdi.	r11, r12, 1, (63-MSR_TS_T_LG) /* transaction active? */
+	beq+	1f
+
+	/* Doom the transaction and don't perform the syscall: */
+	mfmsr	r11
+	li	r12, 1
+	rldimi	r11, r12, MSR_TM_LG, 63-MSR_TM_LG
+	mtmsrd	r11, 0
+	li	r11, (TM_CAUSE_SYSCALL|TM_CAUSE_PERSISTENT)
+	TABORT(R11)
+
+	b	.Lsyscall_exit
+1:
+#endif
 	cmpldi	0,r0,NR_syscalls
 	bge-	syscall_enosys
 
@@ -356,6 +375,11 @@ _GLOBAL(ppc64_swapcontext)
 	bl	sys_swapcontext
 	b	.Lsyscall_exit
 
+_GLOBAL(ppc_switch_endian)
+	bl	save_nvgprs
+	bl	sys_switch_endian
+	b	.Lsyscall_exit
+
 _GLOBAL(ret_from_fork)
 	bl	schedule_tail
 	REST_NVGPRS(r1)
diff --git a/arch/powerpc/kernel/idle_power7.S b/arch/powerpc/kernel/idle_power7.S
index 05adc8bbdef8..eeaa0d5f69d5 100644
--- a/arch/powerpc/kernel/idle_power7.S
+++ b/arch/powerpc/kernel/idle_power7.S
@@ -94,6 +94,7 @@ _GLOBAL(power7_powersave_common)
 	beq	1f
 	addi	r1,r1,INT_FRAME_SIZE
 	ld	r0,16(r1)
+	li	r3,0			/* Return 0 (no nap) */
 	mtlr	r0
 	blr
 
diff --git a/arch/powerpc/kernel/mce_power.c b/arch/powerpc/kernel/mce_power.c
index b6f123ab90ed..2c647b1e62e4 100644
--- a/arch/powerpc/kernel/mce_power.c
+++ b/arch/powerpc/kernel/mce_power.c
@@ -28,6 +28,55 @@
 #include <asm/mce.h>
 #include <asm/machdep.h>
 
+static void flush_tlb_206(unsigned int num_sets, unsigned int action)
+{
+	unsigned long rb;
+	unsigned int i;
+
+	switch (action) {
+	case TLB_INVAL_SCOPE_GLOBAL:
+		rb = TLBIEL_INVAL_SET;
+		break;
+	case TLB_INVAL_SCOPE_LPID:
+		rb = TLBIEL_INVAL_SET_LPID;
+		break;
+	default:
+		BUG();
+		break;
+	}
+
+	asm volatile("ptesync" : : : "memory");
+	for (i = 0; i < num_sets; i++) {
+		asm volatile("tlbiel %0" : : "r" (rb));
+		rb += 1 << TLBIEL_INVAL_SET_SHIFT;
+	}
+	asm volatile("ptesync" : : : "memory");
+}
+
+/*
+ * Generic routine to flush TLB on power7. This routine is used as
+ * flush_tlb hook in cpu_spec for Power7 processor.
+ *
+ * action => TLB_INVAL_SCOPE_GLOBAL:  Invalidate all TLBs.
+ *	     TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID.
+ */
+void __flush_tlb_power7(unsigned int action)
+{
+	flush_tlb_206(POWER7_TLB_SETS, action);
+}
+
+/*
+ * Generic routine to flush TLB on power8. This routine is used as
+ * flush_tlb hook in cpu_spec for power8 processor.
+ *
+ * action => TLB_INVAL_SCOPE_GLOBAL:  Invalidate all TLBs.
+ *	     TLB_INVAL_SCOPE_LPID: Invalidate TLB for current LPID.
+ */
+void __flush_tlb_power8(unsigned int action)
+{
+	flush_tlb_206(POWER8_TLB_SETS, action);
+}
+
 /* flush SLBs and reload */
 static void flush_and_reload_slb(void)
 {
@@ -79,7 +128,7 @@ static long mce_handle_derror(uint64_t dsisr, uint64_t slb_error_bits)
 	}
 	if (dsisr & P7_DSISR_MC_TLB_MULTIHIT_MFTLB) {
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb)
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
+			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
 		/* reset error bits */
 		dsisr &= ~P7_DSISR_MC_TLB_MULTIHIT_MFTLB;
 	}
@@ -110,7 +159,7 @@ static long mce_handle_common_ierror(uint64_t srr1)
 		break;
 	case P7_SRR1_MC_IFETCH_TLB_MULTIHIT:
 		if (cur_cpu_spec && cur_cpu_spec->flush_tlb) {
-			cur_cpu_spec->flush_tlb(TLBIEL_INVAL_SET);
+			cur_cpu_spec->flush_tlb(TLB_INVAL_SCOPE_GLOBAL);
 			handled = 1;
 		}
 		break;
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 34f7c9b7cd96..1e703f8ebad4 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -26,6 +26,9 @@
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/kmsg_dump.h>
+#include <linux/pstore.h>
+#include <linux/zlib.h>
 #include <asm/uaccess.h>
 #include <asm/nvram.h>
 #include <asm/rtas.h>
@@ -54,6 +57,680 @@ struct nvram_partition {
 
 static LIST_HEAD(nvram_partitions);
 
+#ifdef CONFIG_PPC_PSERIES
+struct nvram_os_partition rtas_log_partition = {
+	.name = "ibm,rtas-log",
+	.req_size = 2079,
+	.min_size = 1055,
+	.index = -1,
+	.os_partition = true
+};
+#endif
+
+struct nvram_os_partition oops_log_partition = {
+	.name = "lnx,oops-log",
+	.req_size = 4000,
+	.min_size = 2000,
+	.index = -1,
+	.os_partition = true
+};
+
+static const char *nvram_os_partitions[] = {
+#ifdef CONFIG_PPC_PSERIES
+	"ibm,rtas-log",
+#endif
+	"lnx,oops-log",
+	NULL
+};
+
+static void oops_to_nvram(struct kmsg_dumper *dumper,
+			  enum kmsg_dump_reason reason);
+
+static struct kmsg_dumper nvram_kmsg_dumper = {
+	.dump = oops_to_nvram
+};
+
+/*
+ * For capturing and compressing an oops or panic report...
+
+ * big_oops_buf[] holds the uncompressed text we're capturing.
+ *
+ * oops_buf[] holds the compressed text, preceded by a oops header.
+ * oops header has u16 holding the version of oops header (to differentiate
+ * between old and new format header) followed by u16 holding the length of
+ * the compressed* text (*Or uncompressed, if compression fails.) and u64
+ * holding the timestamp. oops_buf[] gets written to NVRAM.
+ *
+ * oops_log_info points to the header. oops_data points to the compressed text.
+ *
+ * +- oops_buf
+ * |                                   +- oops_data
+ * v                                   v
+ * +-----------+-----------+-----------+------------------------+
+ * | version   | length    | timestamp | text                   |
+ * | (2 bytes) | (2 bytes) | (8 bytes) | (oops_data_sz bytes)   |
+ * +-----------+-----------+-----------+------------------------+
+ * ^
+ * +- oops_log_info
+ *
+ * We preallocate these buffers during init to avoid kmalloc during oops/panic.
+ */
+static size_t big_oops_buf_sz;
+static char *big_oops_buf, *oops_buf;
+static char *oops_data;
+static size_t oops_data_sz;
+
+/* Compression parameters */
+#define COMPR_LEVEL 6
+#define WINDOW_BITS 12
+#define MEM_LEVEL 4
+static struct z_stream_s stream;
+
+#ifdef CONFIG_PSTORE
+#ifdef CONFIG_PPC_POWERNV
+static struct nvram_os_partition skiboot_partition = {
+	.name = "ibm,skiboot",
+	.index = -1,
+	.os_partition = false
+};
+#endif
+
+#ifdef CONFIG_PPC_PSERIES
+static struct nvram_os_partition of_config_partition = {
+	.name = "of-config",
+	.index = -1,
+	.os_partition = false
+};
+#endif
+
+static struct nvram_os_partition common_partition = {
+	.name = "common",
+	.index = -1,
+	.os_partition = false
+};
+
+static enum pstore_type_id nvram_type_ids[] = {
+	PSTORE_TYPE_DMESG,
+	PSTORE_TYPE_PPC_COMMON,
+	-1,
+	-1,
+	-1
+};
+static int read_type;
+#endif
+
+/* nvram_write_os_partition
+ *
+ * We need to buffer the error logs into nvram to ensure that we have
+ * the failure information to decode.  If we have a severe error there
+ * is no way to guarantee that the OS or the machine is in a state to
+ * get back to user land and write the error to disk.  For example if
+ * the SCSI device driver causes a Machine Check by writing to a bad
+ * IO address, there is no way of guaranteeing that the device driver
+ * is in any state that is would also be able to write the error data
+ * captured to disk, thus we buffer it in NVRAM for analysis on the
+ * next boot.
+ *
+ * In NVRAM the partition containing the error log buffer will looks like:
+ * Header (in bytes):
+ * +-----------+----------+--------+------------+------------------+
+ * | signature | checksum | length | name       | data             |
+ * |0          |1         |2      3|4         15|16        length-1|
+ * +-----------+----------+--------+------------+------------------+
+ *
+ * The 'data' section would look like (in bytes):
+ * +--------------+------------+-----------------------------------+
+ * | event_logged | sequence # | error log                         |
+ * |0            3|4          7|8                  error_log_size-1|
+ * +--------------+------------+-----------------------------------+
+ *
+ * event_logged: 0 if event has not been logged to syslog, 1 if it has
+ * sequence #: The unique sequence # for each event. (until it wraps)
+ * error log: The error log from event_scan
+ */
+int nvram_write_os_partition(struct nvram_os_partition *part,
+			     char *buff, int length,
+			     unsigned int err_type,
+			     unsigned int error_log_cnt)
+{
+	int rc;
+	loff_t tmp_index;
+	struct err_log_info info;
+
+	if (part->index == -1)
+		return -ESPIPE;
+
+	if (length > part->size)
+		length = part->size;
+
+	info.error_type = cpu_to_be32(err_type);
+	info.seq_num = cpu_to_be32(error_log_cnt);
+
+	tmp_index = part->index;
+
+	rc = ppc_md.nvram_write((char *)&info, sizeof(struct err_log_info),
+				&tmp_index);
+	if (rc <= 0) {
+		pr_err("%s: Failed nvram_write (%d)\n", __func__, rc);
+		return rc;
+	}
+
+	rc = ppc_md.nvram_write(buff, length, &tmp_index);
+	if (rc <= 0) {
+		pr_err("%s: Failed nvram_write (%d)\n", __func__, rc);
+		return rc;
+	}
+
+	return 0;
+}
+
+/* nvram_read_partition
+ *
+ * Reads nvram partition for at most 'length'
+ */
+int nvram_read_partition(struct nvram_os_partition *part, char *buff,
+			 int length, unsigned int *err_type,
+			 unsigned int *error_log_cnt)
+{
+	int rc;
+	loff_t tmp_index;
+	struct err_log_info info;
+
+	if (part->index == -1)
+		return -1;
+
+	if (length > part->size)
+		length = part->size;
+
+	tmp_index = part->index;
+
+	if (part->os_partition) {
+		rc = ppc_md.nvram_read((char *)&info,
+					sizeof(struct err_log_info),
+					&tmp_index);
+		if (rc <= 0) {
+			pr_err("%s: Failed nvram_read (%d)\n", __func__, rc);
+			return rc;
+		}
+	}
+
+	rc = ppc_md.nvram_read(buff, length, &tmp_index);
+	if (rc <= 0) {
+		pr_err("%s: Failed nvram_read (%d)\n", __func__, rc);
+		return rc;
+	}
+
+	if (part->os_partition) {
+		*error_log_cnt = be32_to_cpu(info.seq_num);
+		*err_type = be32_to_cpu(info.error_type);
+	}
+
+	return 0;
+}
+
+/* nvram_init_os_partition
+ *
+ * This sets up a partition with an "OS" signature.
+ *
+ * The general strategy is the following:
+ * 1.) If a partition with the indicated name already exists...
+ *	- If it's large enough, use it.
+ *	- Otherwise, recycle it and keep going.
+ * 2.) Search for a free partition that is large enough.
+ * 3.) If there's not a free partition large enough, recycle any obsolete
+ * OS partitions and try again.
+ * 4.) Will first try getting a chunk that will satisfy the requested size.
+ * 5.) If a chunk of the requested size cannot be allocated, then try finding
+ * a chunk that will satisfy the minum needed.
+ *
+ * Returns 0 on success, else -1.
+ */
+int __init nvram_init_os_partition(struct nvram_os_partition *part)
+{
+	loff_t p;
+	int size;
+
+	/* Look for ours */
+	p = nvram_find_partition(part->name, NVRAM_SIG_OS, &size);
+
+	/* Found one but too small, remove it */
+	if (p && size < part->min_size) {
+		pr_info("nvram: Found too small %s partition,"
+					" removing it...\n", part->name);
+		nvram_remove_partition(part->name, NVRAM_SIG_OS, NULL);
+		p = 0;
+	}
+
+	/* Create one if we didn't find */
+	if (!p) {
+		p = nvram_create_partition(part->name, NVRAM_SIG_OS,
+					part->req_size, part->min_size);
+		if (p == -ENOSPC) {
+			pr_info("nvram: No room to create %s partition, "
+				"deleting any obsolete OS partitions...\n",
+				part->name);
+			nvram_remove_partition(NULL, NVRAM_SIG_OS,
+					nvram_os_partitions);
+			p = nvram_create_partition(part->name, NVRAM_SIG_OS,
+					part->req_size, part->min_size);
+		}
+	}
+
+	if (p <= 0) {
+		pr_err("nvram: Failed to find or create %s"
+		       " partition, err %d\n", part->name, (int)p);
+		return -1;
+	}
+
+	part->index = p;
+	part->size = nvram_get_partition_size(p) - sizeof(struct err_log_info);
+
+	return 0;
+}
+
+/* Derived from logfs_compress() */
+static int nvram_compress(const void *in, void *out, size_t inlen,
+							size_t outlen)
+{
+	int err, ret;
+
+	ret = -EIO;
+	err = zlib_deflateInit2(&stream, COMPR_LEVEL, Z_DEFLATED, WINDOW_BITS,
+						MEM_LEVEL, Z_DEFAULT_STRATEGY);
+	if (err != Z_OK)
+		goto error;
+
+	stream.next_in = in;
+	stream.avail_in = inlen;
+	stream.total_in = 0;
+	stream.next_out = out;
+	stream.avail_out = outlen;
+	stream.total_out = 0;
+
+	err = zlib_deflate(&stream, Z_FINISH);
+	if (err != Z_STREAM_END)
+		goto error;
+
+	err = zlib_deflateEnd(&stream);
+	if (err != Z_OK)
+		goto error;
+
+	if (stream.total_out >= stream.total_in)
+		goto error;
+
+	ret = stream.total_out;
+error:
+	return ret;
+}
+
+/* Compress the text from big_oops_buf into oops_buf. */
+static int zip_oops(size_t text_len)
+{
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+	int zipped_len = nvram_compress(big_oops_buf, oops_data, text_len,
+								oops_data_sz);
+	if (zipped_len < 0) {
+		pr_err("nvram: compression failed; returned %d\n", zipped_len);
+		pr_err("nvram: logging uncompressed oops/panic report\n");
+		return -1;
+	}
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(zipped_len);
+	oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
+	return 0;
+}
+
+#ifdef CONFIG_PSTORE
+static int nvram_pstore_open(struct pstore_info *psi)
+{
+	/* Reset the iterator to start reading partitions again */
+	read_type = -1;
+	return 0;
+}
+
+/**
+ * nvram_pstore_write - pstore write callback for nvram
+ * @type:               Type of message logged
+ * @reason:             reason behind dump (oops/panic)
+ * @id:                 identifier to indicate the write performed
+ * @part:               pstore writes data to registered buffer in parts,
+ *                      part number will indicate the same.
+ * @count:              Indicates oops count
+ * @compressed:         Flag to indicate the log is compressed
+ * @size:               number of bytes written to the registered buffer
+ * @psi:                registered pstore_info structure
+ *
+ * Called by pstore_dump() when an oops or panic report is logged in the
+ * printk buffer.
+ * Returns 0 on successful write.
+ */
+static int nvram_pstore_write(enum pstore_type_id type,
+				enum kmsg_dump_reason reason,
+				u64 *id, unsigned int part, int count,
+				bool compressed, size_t size,
+				struct pstore_info *psi)
+{
+	int rc;
+	unsigned int err_type = ERR_TYPE_KERNEL_PANIC;
+	struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
+
+	/* part 1 has the recent messages from printk buffer */
+	if (part > 1 || (type != PSTORE_TYPE_DMESG))
+		return -1;
+
+	if (clobbering_unread_rtas_event())
+		return -1;
+
+	oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+	oops_hdr->report_length = cpu_to_be16(size);
+	oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
+
+	if (compressed)
+		err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+
+	rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
+		(int) (sizeof(*oops_hdr) + size), err_type, count);
+
+	if (rc != 0)
+		return rc;
+
+	*id = part;
+	return 0;
+}
+
+/*
+ * Reads the oops/panic report, rtas, of-config and common partition.
+ * Returns the length of the data we read from each partition.
+ * Returns 0 if we've been called before.
+ */
+static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
+				int *count, struct timespec *time, char **buf,
+				bool *compressed, struct pstore_info *psi)
+{
+	struct oops_log_info *oops_hdr;
+	unsigned int err_type, id_no, size = 0;
+	struct nvram_os_partition *part = NULL;
+	char *buff = NULL;
+	int sig = 0;
+	loff_t p;
+
+	read_type++;
+
+	switch (nvram_type_ids[read_type]) {
+	case PSTORE_TYPE_DMESG:
+		part = &oops_log_partition;
+		*type = PSTORE_TYPE_DMESG;
+		break;
+	case PSTORE_TYPE_PPC_COMMON:
+		sig = NVRAM_SIG_SYS;
+		part = &common_partition;
+		*type = PSTORE_TYPE_PPC_COMMON;
+		*id = PSTORE_TYPE_PPC_COMMON;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+#ifdef CONFIG_PPC_PSERIES
+	case PSTORE_TYPE_PPC_RTAS:
+		part = &rtas_log_partition;
+		*type = PSTORE_TYPE_PPC_RTAS;
+		time->tv_sec = last_rtas_event;
+		time->tv_nsec = 0;
+		break;
+	case PSTORE_TYPE_PPC_OF:
+		sig = NVRAM_SIG_OF;
+		part = &of_config_partition;
+		*type = PSTORE_TYPE_PPC_OF;
+		*id = PSTORE_TYPE_PPC_OF;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+#endif
+#ifdef CONFIG_PPC_POWERNV
+	case PSTORE_TYPE_PPC_OPAL:
+		sig = NVRAM_SIG_FW;
+		part = &skiboot_partition;
+		*type = PSTORE_TYPE_PPC_OPAL;
+		*id = PSTORE_TYPE_PPC_OPAL;
+		time->tv_sec = 0;
+		time->tv_nsec = 0;
+		break;
+#endif
+	default:
+		return 0;
+	}
+
+	if (!part->os_partition) {
+		p = nvram_find_partition(part->name, sig, &size);
+		if (p <= 0) {
+			pr_err("nvram: Failed to find partition %s, "
+				"err %d\n", part->name, (int)p);
+			return 0;
+		}
+		part->index = p;
+		part->size = size;
+	}
+
+	buff = kmalloc(part->size, GFP_KERNEL);
+
+	if (!buff)
+		return -ENOMEM;
+
+	if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) {
+		kfree(buff);
+		return 0;
+	}
+
+	*count = 0;
+
+	if (part->os_partition)
+		*id = id_no;
+
+	if (nvram_type_ids[read_type] == PSTORE_TYPE_DMESG) {
+		size_t length, hdr_size;
+
+		oops_hdr = (struct oops_log_info *)buff;
+		if (be16_to_cpu(oops_hdr->version) < OOPS_HDR_VERSION) {
+			/* Old format oops header had 2-byte record size */
+			hdr_size = sizeof(u16);
+			length = be16_to_cpu(oops_hdr->version);
+			time->tv_sec = 0;
+			time->tv_nsec = 0;
+		} else {
+			hdr_size = sizeof(*oops_hdr);
+			length = be16_to_cpu(oops_hdr->report_length);
+			time->tv_sec = be64_to_cpu(oops_hdr->timestamp);
+			time->tv_nsec = 0;
+		}
+		*buf = kmalloc(length, GFP_KERNEL);
+		if (*buf == NULL)
+			return -ENOMEM;
+		memcpy(*buf, buff + hdr_size, length);
+		kfree(buff);
+
+		if (err_type == ERR_TYPE_KERNEL_PANIC_GZ)
+			*compressed = true;
+		else
+			*compressed = false;
+		return length;
+	}
+
+	*buf = buff;
+	return part->size;
+}
+
+static struct pstore_info nvram_pstore_info = {
+	.owner = THIS_MODULE,
+	.name = "nvram",
+	.open = nvram_pstore_open,
+	.read = nvram_pstore_read,
+	.write = nvram_pstore_write,
+};
+
+static int nvram_pstore_init(void)
+{
+	int rc = 0;
+
+	if (machine_is(pseries)) {
+		nvram_type_ids[2] = PSTORE_TYPE_PPC_RTAS;
+		nvram_type_ids[3] = PSTORE_TYPE_PPC_OF;
+	} else
+		nvram_type_ids[2] = PSTORE_TYPE_PPC_OPAL;
+
+	nvram_pstore_info.buf = oops_data;
+	nvram_pstore_info.bufsize = oops_data_sz;
+
+	spin_lock_init(&nvram_pstore_info.buf_lock);
+
+	rc = pstore_register(&nvram_pstore_info);
+	if (rc != 0)
+		pr_err("nvram: pstore_register() failed, defaults to "
+				"kmsg_dump; returned %d\n", rc);
+
+	return rc;
+}
+#else
+static int nvram_pstore_init(void)
+{
+	return -1;
+}
+#endif
+
+void __init nvram_init_oops_partition(int rtas_partition_exists)
+{
+	int rc;
+
+	rc = nvram_init_os_partition(&oops_log_partition);
+	if (rc != 0) {
+#ifdef CONFIG_PPC_PSERIES
+		if (!rtas_partition_exists) {
+			pr_err("nvram: Failed to initialize oops partition!");
+			return;
+		}
+		pr_notice("nvram: Using %s partition to log both"
+			" RTAS errors and oops/panic reports\n",
+			rtas_log_partition.name);
+		memcpy(&oops_log_partition, &rtas_log_partition,
+						sizeof(rtas_log_partition));
+#else
+		pr_err("nvram: Failed to initialize oops partition!");
+		return;
+#endif
+	}
+	oops_buf = kmalloc(oops_log_partition.size, GFP_KERNEL);
+	if (!oops_buf) {
+		pr_err("nvram: No memory for %s partition\n",
+						oops_log_partition.name);
+		return;
+	}
+	oops_data = oops_buf + sizeof(struct oops_log_info);
+	oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
+
+	rc = nvram_pstore_init();
+
+	if (!rc)
+		return;
+
+	/*
+	 * Figure compression (preceded by elimination of each line's <n>
+	 * severity prefix) will reduce the oops/panic report to at most
+	 * 45% of its original size.
+	 */
+	big_oops_buf_sz = (oops_data_sz * 100) / 45;
+	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
+	if (big_oops_buf) {
+		stream.workspace =  kmalloc(zlib_deflate_workspacesize(
+					WINDOW_BITS, MEM_LEVEL), GFP_KERNEL);
+		if (!stream.workspace) {
+			pr_err("nvram: No memory for compression workspace; "
+				"skipping compression of %s partition data\n",
+				oops_log_partition.name);
+			kfree(big_oops_buf);
+			big_oops_buf = NULL;
+		}
+	} else {
+		pr_err("No memory for uncompressed %s data; "
+			"skipping compression\n", oops_log_partition.name);
+		stream.workspace = NULL;
+	}
+
+	rc = kmsg_dump_register(&nvram_kmsg_dumper);
+	if (rc != 0) {
+		pr_err("nvram: kmsg_dump_register() failed; returned %d\n", rc);
+		kfree(oops_buf);
+		kfree(big_oops_buf);
+		kfree(stream.workspace);
+	}
+}
+
+/*
+ * This is our kmsg_dump callback, called after an oops or panic report
+ * has been written to the printk buffer.  We want to capture as much
+ * of the printk buffer as possible.  First, capture as much as we can
+ * that we think will compress sufficiently to fit in the lnx,oops-log
+ * partition.  If that's too much, go back and capture uncompressed text.
+ */
+static void oops_to_nvram(struct kmsg_dumper *dumper,
+			  enum kmsg_dump_reason reason)
+{
+	struct oops_log_info *oops_hdr = (struct oops_log_info *)oops_buf;
+	static unsigned int oops_count = 0;
+	static bool panicking = false;
+	static DEFINE_SPINLOCK(lock);
+	unsigned long flags;
+	size_t text_len;
+	unsigned int err_type = ERR_TYPE_KERNEL_PANIC_GZ;
+	int rc = -1;
+
+	switch (reason) {
+	case KMSG_DUMP_RESTART:
+	case KMSG_DUMP_HALT:
+	case KMSG_DUMP_POWEROFF:
+		/* These are almost always orderly shutdowns. */
+		return;
+	case KMSG_DUMP_OOPS:
+		break;
+	case KMSG_DUMP_PANIC:
+		panicking = true;
+		break;
+	case KMSG_DUMP_EMERG:
+		if (panicking)
+			/* Panic report already captured. */
+			return;
+		break;
+	default:
+		pr_err("%s: ignoring unrecognized KMSG_DUMP_* reason %d\n",
+		       __func__, (int) reason);
+		return;
+	}
+
+	if (clobbering_unread_rtas_event())
+		return;
+
+	if (!spin_trylock_irqsave(&lock, flags))
+		return;
+
+	if (big_oops_buf) {
+		kmsg_dump_get_buffer(dumper, false,
+				     big_oops_buf, big_oops_buf_sz, &text_len);
+		rc = zip_oops(text_len);
+	}
+	if (rc != 0) {
+		kmsg_dump_rewind(dumper);
+		kmsg_dump_get_buffer(dumper, false,
+				     oops_data, oops_data_sz, &text_len);
+		err_type = ERR_TYPE_KERNEL_PANIC;
+		oops_hdr->version = cpu_to_be16(OOPS_HDR_VERSION);
+		oops_hdr->report_length = cpu_to_be16(text_len);
+		oops_hdr->timestamp = cpu_to_be64(ktime_get_real_seconds());
+	}
+
+	(void) nvram_write_os_partition(&oops_log_partition, oops_buf,
+		(int) (sizeof(*oops_hdr) + text_len), err_type,
+		++oops_count);
+
+	spin_unlock_irqrestore(&lock, flags);
+}
+
 static loff_t dev_nvram_llseek(struct file *file, loff_t offset, int origin)
 {
 	int size;
diff --git a/arch/powerpc/kernel/of_platform.c b/arch/powerpc/kernel/of_platform.c
index 2f35a72642c6..b60a67d92ebd 100644
--- a/arch/powerpc/kernel/of_platform.c
+++ b/arch/powerpc/kernel/of_platform.c
@@ -72,7 +72,7 @@ static int of_pci_phb_probe(struct platform_device *dev)
 
 	/* Register devices with EEH */
 	if (dev->dev.of_node->child)
-		eeh_add_device_tree_early(dev->dev.of_node);
+		eeh_add_device_tree_early(PCI_DN(dev->dev.of_node));
 
 	/* Scan the bus */
 	pcibios_scan_phb(phb);
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index 2a525c938158..0d054068a21d 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -76,7 +76,7 @@ struct pci_controller *pcibios_alloc_controller(struct device_node *dev)
 	list_add_tail(&phb->list_node, &hose_list);
 	spin_unlock(&hose_spinlock);
 	phb->dn = dev;
-	phb->is_dynamic = mem_init_done;
+	phb->is_dynamic = slab_is_available();
 #ifdef CONFIG_PPC64
 	if (dev) {
 		int nid = of_node_to_nid(dev);
@@ -109,8 +109,10 @@ void pcibios_free_controller(struct pci_controller *phb)
 resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 					 unsigned long type)
 {
-	if (ppc_md.pcibios_window_alignment)
-		return ppc_md.pcibios_window_alignment(bus, type);
+	struct pci_controller *phb = pci_bus_to_host(bus);
+
+	if (phb->controller_ops.window_alignment)
+		return phb->controller_ops.window_alignment(bus, type);
 
 	/*
 	 * PCI core will figure out the default
@@ -122,14 +124,26 @@ resource_size_t pcibios_window_alignment(struct pci_bus *bus,
 
 void pcibios_reset_secondary_bus(struct pci_dev *dev)
 {
-	if (ppc_md.pcibios_reset_secondary_bus) {
-		ppc_md.pcibios_reset_secondary_bus(dev);
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+	if (phb->controller_ops.reset_secondary_bus) {
+		phb->controller_ops.reset_secondary_bus(dev);
 		return;
 	}
 
 	pci_reset_secondary_bus(dev);
 }
 
+#ifdef CONFIG_PCI_IOV
+resource_size_t pcibios_iov_resource_alignment(struct pci_dev *pdev, int resno)
+{
+	if (ppc_md.pcibios_iov_resource_alignment)
+		return ppc_md.pcibios_iov_resource_alignment(pdev, resno);
+
+	return pci_iov_resource_size(pdev, resno);
+}
+#endif /* CONFIG_PCI_IOV */
+
 static resource_size_t pcibios_io_size(const struct pci_controller *hose)
 {
 #ifdef CONFIG_PPC64
@@ -788,6 +802,10 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 		       pci_name(dev));
 		return;
 	}
+
+	if (dev->is_virtfn)
+		return;
+
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 		struct resource *res = dev->resource + i;
 		struct pci_bus_region reg;
@@ -942,6 +960,8 @@ static void pcibios_fixup_bridge(struct pci_bus *bus)
 
 void pcibios_setup_bus_self(struct pci_bus *bus)
 {
+	struct pci_controller *phb;
+
 	/* Fix up the bus resources for P2P bridges */
 	if (bus->self != NULL)
 		pcibios_fixup_bridge(bus);
@@ -953,12 +973,14 @@ void pcibios_setup_bus_self(struct pci_bus *bus)
 		ppc_md.pcibios_fixup_bus(bus);
 
 	/* Setup bus DMA mappings */
-	if (ppc_md.pci_dma_bus_setup)
-		ppc_md.pci_dma_bus_setup(bus);
+	phb = pci_bus_to_host(bus);
+	if (phb->controller_ops.dma_bus_setup)
+		phb->controller_ops.dma_bus_setup(bus);
 }
 
 static void pcibios_setup_device(struct pci_dev *dev)
 {
+	struct pci_controller *phb;
 	/* Fixup NUMA node as it may not be setup yet by the generic
 	 * code and is needed by the DMA init
 	 */
@@ -969,8 +991,9 @@ static void pcibios_setup_device(struct pci_dev *dev)
 	set_dma_offset(&dev->dev, PCI_DRAM_OFFSET);
 
 	/* Additional platform DMA/iommu setup */
-	if (ppc_md.pci_dma_dev_setup)
-		ppc_md.pci_dma_dev_setup(dev);
+	phb = pci_bus_to_host(dev->bus);
+	if (phb->controller_ops.dma_dev_setup)
+		phb->controller_ops.dma_dev_setup(dev);
 
 	/* Read default IRQs and fixup if necessary */
 	pci_read_irq_line(dev);
@@ -986,6 +1009,12 @@ int pcibios_add_device(struct pci_dev *dev)
 	 */
 	if (dev->bus->is_added)
 		pcibios_setup_device(dev);
+
+#ifdef CONFIG_PCI_IOV
+	if (ppc_md.pcibios_fixup_sriov)
+		ppc_md.pcibios_fixup_sriov(dev);
+#endif /* CONFIG_PCI_IOV */
+
 	return 0;
 }
 
@@ -1450,8 +1479,10 @@ EXPORT_SYMBOL_GPL(pcibios_finish_adding_to_bus);
 
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
-	if (ppc_md.pcibios_enable_device_hook)
-		if (ppc_md.pcibios_enable_device_hook(dev))
+	struct pci_controller *phb = pci_bus_to_host(dev->bus);
+
+	if (phb->controller_ops.enable_device_hook)
+		if (!phb->controller_ops.enable_device_hook(dev))
 			return -EINVAL;
 
 	return pci_enable_resources(dev, mask);
@@ -1624,8 +1655,8 @@ void pcibios_scan_phb(struct pci_controller *hose)
 
 	/* Get probe mode and perform scan */
 	mode = PCI_PROBE_NORMAL;
-	if (node && ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
+	if (node && hose->controller_ops.probe_mode)
+		mode = hose->controller_ops.probe_mode(bus);
 	pr_debug("    probe mode: %d\n", mode);
 	if (mode == PCI_PROBE_DEVTREE)
 		of_scan_bus(node, bus);
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
index 5b789177aa29..7ed85a69a9c2 100644
--- a/arch/powerpc/kernel/pci-hotplug.c
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -73,13 +73,16 @@ void pcibios_add_pci_devices(struct pci_bus * bus)
 {
 	int slotno, mode, pass, max;
 	struct pci_dev *dev;
+	struct pci_controller *phb;
 	struct device_node *dn = pci_bus_to_OF_node(bus);
 
-	eeh_add_device_tree_early(dn);
+	eeh_add_device_tree_early(PCI_DN(dn));
+
+	phb = pci_bus_to_host(bus);
 
 	mode = PCI_PROBE_NORMAL;
-	if (ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
+	if (phb->controller_ops.probe_mode)
+		mode = phb->controller_ops.probe_mode(bus);
 
 	if (mode == PCI_PROBE_DEVTREE) {
 		/* use ofdt-based probe */
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index 83df3075d3df..b3b4df91b792 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -32,12 +32,237 @@
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
 
+/*
+ * The function is used to find the firmware data of one
+ * specific PCI device, which is attached to the indicated
+ * PCI bus. For VFs, their firmware data is linked to that
+ * one of PF's bridge. For other devices, their firmware
+ * data is linked to that of their bridge.
+ */
+static struct pci_dn *pci_bus_to_pdn(struct pci_bus *bus)
+{
+	struct pci_bus *pbus;
+	struct device_node *dn;
+	struct pci_dn *pdn;
+
+	/*
+	 * We probably have virtual bus which doesn't
+	 * have associated bridge.
+	 */
+	pbus = bus;
+	while (pbus) {
+		if (pci_is_root_bus(pbus) || pbus->self)
+			break;
+
+		pbus = pbus->parent;
+	}
+
+	/*
+	 * Except virtual bus, all PCI buses should
+	 * have device nodes.
+	 */
+	dn = pci_bus_to_OF_node(pbus);
+	pdn = dn ? PCI_DN(dn) : NULL;
+
+	return pdn;
+}
+
+struct pci_dn *pci_get_pdn_by_devfn(struct pci_bus *bus,
+				    int devfn)
+{
+	struct device_node *dn = NULL;
+	struct pci_dn *parent, *pdn;
+	struct pci_dev *pdev = NULL;
+
+	/* Fast path: fetch from PCI device */
+	list_for_each_entry(pdev, &bus->devices, bus_list) {
+		if (pdev->devfn == devfn) {
+			if (pdev->dev.archdata.pci_data)
+				return pdev->dev.archdata.pci_data;
+
+			dn = pci_device_to_OF_node(pdev);
+			break;
+		}
+	}
+
+	/* Fast path: fetch from device node */
+	pdn = dn ? PCI_DN(dn) : NULL;
+	if (pdn)
+		return pdn;
+
+	/* Slow path: fetch from firmware data hierarchy */
+	parent = pci_bus_to_pdn(bus);
+	if (!parent)
+		return NULL;
+
+	list_for_each_entry(pdn, &parent->child_list, list) {
+		if (pdn->busno == bus->number &&
+                    pdn->devfn == devfn)
+                        return pdn;
+        }
+
+	return NULL;
+}
+
 struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
 {
-	struct device_node *dn = pci_device_to_OF_node(pdev);
-	if (!dn)
+	struct device_node *dn;
+	struct pci_dn *parent, *pdn;
+
+	/* Search device directly */
+	if (pdev->dev.archdata.pci_data)
+		return pdev->dev.archdata.pci_data;
+
+	/* Check device node */
+	dn = pci_device_to_OF_node(pdev);
+	pdn = dn ? PCI_DN(dn) : NULL;
+	if (pdn)
+		return pdn;
+
+	/*
+	 * VFs don't have device nodes. We hook their
+	 * firmware data to PF's bridge.
+	 */
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return NULL;
+
+	list_for_each_entry(pdn, &parent->child_list, list) {
+		if (pdn->busno == pdev->bus->number &&
+		    pdn->devfn == pdev->devfn)
+			return pdn;
+	}
+
+	return NULL;
+}
+
+#ifdef CONFIG_PCI_IOV
+static struct pci_dn *add_one_dev_pci_data(struct pci_dn *parent,
+					   struct pci_dev *pdev,
+					   int busno, int devfn)
+{
+	struct pci_dn *pdn;
+
+	/* Except PHB, we always have the parent */
+	if (!parent)
+		return NULL;
+
+	pdn = kzalloc(sizeof(*pdn), GFP_KERNEL);
+	if (!pdn) {
+		dev_warn(&pdev->dev, "%s: Out of memory!\n", __func__);
 		return NULL;
-	return PCI_DN(dn);
+	}
+
+	pdn->phb = parent->phb;
+	pdn->parent = parent;
+	pdn->busno = busno;
+	pdn->devfn = devfn;
+#ifdef CONFIG_PPC_POWERNV
+	pdn->pe_number = IODA_INVALID_PE;
+#endif
+	INIT_LIST_HEAD(&pdn->child_list);
+	INIT_LIST_HEAD(&pdn->list);
+	list_add_tail(&pdn->list, &parent->child_list);
+
+	/*
+	 * If we already have PCI device instance, lets
+	 * bind them.
+	 */
+	if (pdev)
+		pdev->dev.archdata.pci_data = pdn;
+
+	return pdn;
+}
+#endif
+
+struct pci_dn *add_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent, *pdn;
+	int i;
+
+	/* Only support IOV for now */
+	if (!pdev->is_physfn)
+		return pci_get_pdn(pdev);
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || (pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return NULL;
+
+	pdn->flags |= PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return NULL;
+
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		pdn = add_one_dev_pci_data(parent, NULL,
+					   pci_iov_virtfn_bus(pdev, i),
+					   pci_iov_virtfn_devfn(pdev, i));
+		if (!pdn) {
+			dev_warn(&pdev->dev, "%s: Cannot create firmware data for VF#%d\n",
+				 __func__, i);
+			return NULL;
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
+
+	return pci_get_pdn(pdev);
+}
+
+void remove_dev_pci_data(struct pci_dev *pdev)
+{
+#ifdef CONFIG_PCI_IOV
+	struct pci_dn *parent;
+	struct pci_dn *pdn, *tmp;
+	int i;
+
+	/*
+	 * VF and VF PE are created/released dynamically, so we need to
+	 * bind/unbind them.  Otherwise the VF and VF PE would be mismatched
+	 * when re-enabling SR-IOV.
+	 */
+	if (pdev->is_virtfn) {
+		pdn = pci_get_pdn(pdev);
+#ifdef CONFIG_PPC_POWERNV
+		pdn->pe_number = IODA_INVALID_PE;
+#endif
+		return;
+	}
+
+	/* Only support IOV PF for now */
+	if (!pdev->is_physfn)
+		return;
+
+	/* Check if VFs have been populated */
+	pdn = pci_get_pdn(pdev);
+	if (!pdn || !(pdn->flags & PCI_DN_FLAG_IOV_VF))
+		return;
+
+	pdn->flags &= ~PCI_DN_FLAG_IOV_VF;
+	parent = pci_bus_to_pdn(pdev->bus);
+	if (!parent)
+		return;
+
+	/*
+	 * We might introduce flag to pci_dn in future
+	 * so that we can release VF's firmware data in
+	 * a batch mode.
+	 */
+	for (i = 0; i < pci_sriov_get_totalvfs(pdev); i++) {
+		list_for_each_entry_safe(pdn, tmp,
+			&parent->child_list, list) {
+			if (pdn->busno != pci_iov_virtfn_bus(pdev, i) ||
+			    pdn->devfn != pci_iov_virtfn_devfn(pdev, i))
+				continue;
+
+			if (!list_empty(&pdn->list))
+				list_del(&pdn->list);
+
+			kfree(pdn);
+		}
+	}
+#endif /* CONFIG_PCI_IOV */
 }
 
 /*
@@ -49,6 +274,7 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
 	struct pci_controller *phb = data;
 	const __be32 *type = of_get_property(dn, "ibm,pci-config-space-type", NULL);
 	const __be32 *regs;
+	struct device_node *parent;
 	struct pci_dn *pdn;
 
 	pdn = zalloc_maybe_bootmem(sizeof(*pdn), GFP_KERNEL);
@@ -69,7 +295,25 @@ void *update_dn_pci_info(struct device_node *dn, void *data)
 		pdn->devfn = (addr >> 8) & 0xff;
 	}
 
+	/* vendor/device IDs and class code */
+	regs = of_get_property(dn, "vendor-id", NULL);
+	pdn->vendor_id = regs ? of_read_number(regs, 1) : 0;
+	regs = of_get_property(dn, "device-id", NULL);
+	pdn->device_id = regs ? of_read_number(regs, 1) : 0;
+	regs = of_get_property(dn, "class-code", NULL);
+	pdn->class_code = regs ? of_read_number(regs, 1) : 0;
+
+	/* Extended config space */
 	pdn->pci_ext_config_space = (type && of_read_number(type, 1) == 1);
+
+	/* Attach to parent node */
+	INIT_LIST_HEAD(&pdn->child_list);
+	INIT_LIST_HEAD(&pdn->list);
+	parent = of_get_parent(dn);
+	pdn->parent = parent ? PCI_DN(parent) : NULL;
+	if (pdn->parent)
+		list_add_tail(&pdn->list, &pdn->parent->child_list);
+
 	return NULL;
 }
 
@@ -131,6 +375,46 @@ void *traverse_pci_devices(struct device_node *start, traverse_func pre,
 	return NULL;
 }
 
+static struct pci_dn *pci_dn_next_one(struct pci_dn *root,
+				      struct pci_dn *pdn)
+{
+	struct list_head *next = pdn->child_list.next;
+
+	if (next != &pdn->child_list)
+		return list_entry(next, struct pci_dn, list);
+
+	while (1) {
+		if (pdn == root)
+			return NULL;
+
+		next = pdn->list.next;
+		if (next != &pdn->parent->child_list)
+			break;
+
+		pdn = pdn->parent;
+	}
+
+	return list_entry(next, struct pci_dn, list);
+}
+
+void *traverse_pci_dn(struct pci_dn *root,
+		      void *(*fn)(struct pci_dn *, void *),
+		      void *data)
+{
+	struct pci_dn *pdn = root;
+	void *ret;
+
+	/* Only scan the child nodes */
+	for (pdn = pci_dn_next_one(root, pdn); pdn;
+	     pdn = pci_dn_next_one(root, pdn)) {
+		ret = fn(pdn, data);
+		if (ret)
+			return ret;
+	}
+
+	return NULL;
+}
+
 /** 
  * pci_devs_phb_init_dynamic - setup pci devices under this PHB
  * phb: pci-to-host bridge (top-level bridge connecting to cpu)
@@ -147,8 +431,12 @@ void pci_devs_phb_init_dynamic(struct pci_controller *phb)
 	/* PHB nodes themselves must not match */
 	update_dn_pci_info(dn, phb);
 	pdn = dn->data;
-	if (pdn)
+	if (pdn) {
 		pdn->devfn = pdn->busno = -1;
+		pdn->vendor_id = pdn->device_id = pdn->class_code = 0;
+		pdn->phb = phb;
+		phb->pci_data = pdn;
+	}
 
 	/* Update dn->phb ptrs for new phb and children devices */
 	traverse_pci_devices(dn, update_dn_pci_info, phb);
@@ -171,3 +459,16 @@ void __init pci_devs_phb_init(void)
 	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
 		pci_devs_phb_init_dynamic(phb);
 }
+
+static void pci_dev_pdn_setup(struct pci_dev *pdev)
+{
+	struct pci_dn *pdn;
+
+	if (pdev->dev.archdata.pci_data)
+		return;
+
+	/* Setup the fast path */
+	pdn = pci_get_pdn(pdev);
+	pdev->dev.archdata.pci_data = pdn;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_ANY_ID, PCI_ANY_ID, pci_dev_pdn_setup);
diff --git a/arch/powerpc/kernel/pci_of_scan.c b/arch/powerpc/kernel/pci_of_scan.c
index e6245e9c7d8d..42e02a2d570b 100644
--- a/arch/powerpc/kernel/pci_of_scan.c
+++ b/arch/powerpc/kernel/pci_of_scan.c
@@ -207,6 +207,7 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 {
 	struct device_node *node = dev->dev.of_node;
 	struct pci_bus *bus;
+	struct pci_controller *phb;
 	const __be32 *busrange, *ranges;
 	int len, i, mode;
 	struct pci_bus_region region;
@@ -286,9 +287,11 @@ void of_scan_pci_bridge(struct pci_dev *dev)
 		bus->number);
 	pr_debug("    bus name: %s\n", bus->name);
 
+	phb = pci_bus_to_host(bus);
+
 	mode = PCI_PROBE_NORMAL;
-	if (ppc_md.pci_probe_mode)
-		mode = ppc_md.pci_probe_mode(bus);
+	if (phb->controller_ops.probe_mode)
+		mode = phb->controller_ops.probe_mode(bus);
 	pr_debug("    probe mode: %d\n", mode);
 
 	if (mode == PCI_PROBE_DEVTREE)
@@ -305,7 +308,7 @@ static struct pci_dev *of_scan_pci_dev(struct pci_bus *bus,
 	const __be32 *reg;
 	int reglen, devfn;
 #ifdef CONFIG_EEH
-	struct eeh_dev *edev = of_node_to_eeh_dev(dn);
+	struct eeh_dev *edev = pdn_to_eeh_dev(PCI_DN(dn));
 #endif
 
 	pr_debug("  * %s\n", dn->full_name);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index b4cc7bef6b16..febb50dd5328 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1114,8 +1114,11 @@ static void setup_ksp_vsid(struct task_struct *p, unsigned long sp)
  */
 extern unsigned long dscr_default; /* defined in arch/powerpc/kernel/sysfs.c */
 
+/*
+ * Copy architecture-specific thread state
+ */
 int copy_thread(unsigned long clone_flags, unsigned long usp,
-		unsigned long arg, struct task_struct *p)
+		unsigned long kthread_arg, struct task_struct *p)
 {
 	struct pt_regs *childregs, *kregs;
 	extern void ret_from_fork(void);
@@ -1127,6 +1130,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	sp -= sizeof(struct pt_regs);
 	childregs = (struct pt_regs *) sp;
 	if (unlikely(p->flags & PF_KTHREAD)) {
+		/* kernel thread */
 		struct thread_info *ti = (void *)task_stack_page(p);
 		memset(childregs, 0, sizeof(struct pt_regs));
 		childregs->gpr[1] = sp + sizeof(struct pt_regs);
@@ -1137,11 +1141,12 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 		clear_tsk_thread_flag(p, TIF_32BIT);
 		childregs->softe = 1;
 #endif
-		childregs->gpr[15] = arg;
+		childregs->gpr[15] = kthread_arg;
 		p->thread.regs = NULL;	/* no user register state */
 		ti->flags |= _TIF_RESTOREALL;
 		f = ret_from_kernel_thread;
 	} else {
+		/* user thread */
 		struct pt_regs *regs = current_pt_regs();
 		CHECK_FULL_REGS(regs);
 		*childregs = *regs;
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index b8e15c678960..308c5e15676b 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -721,7 +721,7 @@ void __init early_init_devtree(void *params)
 	 */
 	of_scan_flat_dt(early_init_dt_scan_cpus, NULL);
 	if (boot_cpuid < 0) {
-		printk("Failed to indentify boot CPU !\n");
+		printk("Failed to identify boot CPU !\n");
 		BUG();
 	}
 
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index 1a85d8f96739..fd1fe4c37599 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -2898,7 +2898,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 	 * Call OF "quiesce" method to shut down pending DMA's from
 	 * devices etc...
 	 */
-	prom_printf("Calling quiesce...\n");
+	prom_printf("Quiescing Open Firmware ...\n");
 	call_prom("quiesce", 0, 0);
 
 	/*
@@ -2910,7 +2910,7 @@ unsigned long __init prom_init(unsigned long r3, unsigned long r4,
 
 	/* Don't print anything after quiesce under OPAL, it crashes OFW */
 	if (of_platform != PLATFORM_OPAL) {
-		prom_printf("returning from prom_init\n");
+		prom_printf("Booting Linux via __start() ...\n");
 		prom_debug("->dt_header_start=0x%x\n", hdr);
 	}
 
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 21c45a2d0706..7a488c108410 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -401,7 +401,7 @@ static char *__fetch_rtas_last_error(char *altbuf)
 			buf = altbuf;
 		} else {
 			buf = rtas_err_buf;
-			if (mem_init_done)
+			if (slab_is_available())
 				buf = kmalloc(RTAS_ERROR_LOG_MAX, GFP_ATOMIC);
 		}
 		if (buf)
@@ -461,7 +461,7 @@ int rtas_call(int token, int nargs, int nret, int *outputs, ...)
 
 	if (buff_copy) {
 		log_error(buff_copy, ERR_TYPE_RTAS_LOG, 0);
-		if (mem_init_done)
+		if (slab_is_available())
 			kfree(buff_copy);
 	}
 	return ret;
@@ -897,7 +897,7 @@ int rtas_offline_cpus_mask(cpumask_var_t cpus)
 }
 EXPORT_SYMBOL(rtas_offline_cpus_mask);
 
-int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
+int rtas_ibm_suspend_me(u64 handle)
 {
 	long state;
 	long rc;
@@ -919,13 +919,11 @@ int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
 		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned %ld\n",rc);
 		return rc;
 	} else if (state == H_VASI_ENABLED) {
-		*vasi_return = RTAS_NOT_SUSPENDABLE;
-		return 0;
+		return -EAGAIN;
 	} else if (state != H_VASI_SUSPENDING) {
 		printk(KERN_ERR "rtas_ibm_suspend_me: vasi_state returned state %ld\n",
 		       state);
-		*vasi_return = -1;
-		return 0;
+		return -EIO;
 	}
 
 	if (!alloc_cpumask_var(&offline_mask, GFP_TEMPORARY))
@@ -972,7 +970,7 @@ out:
 	return atomic_read(&data.error);
 }
 #else /* CONFIG_PPC_PSERIES */
-int rtas_ibm_suspend_me(u64 handle, int *vasi_return)
+int rtas_ibm_suspend_me(u64 handle)
 {
 	return -ENOSYS;
 }
@@ -1022,7 +1020,6 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	unsigned long flags;
 	char *buff_copy, *errbuf = NULL;
 	int nargs, nret, token;
-	int rc;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
@@ -1054,15 +1051,18 @@ asmlinkage int ppc_rtas(struct rtas_args __user *uargs)
 	if (token == ibm_suspend_me_token) {
 
 		/*
-		 * rtas_ibm_suspend_me assumes args are in cpu endian, or at least the
-		 * hcall within it requires it.
+		 * rtas_ibm_suspend_me assumes the streamid handle is in cpu
+		 * endian, or at least the hcall within it requires it.
 		 */
-		int vasi_rc = 0;
+		int rc = 0;
 		u64 handle = ((u64)be32_to_cpu(args.args[0]) << 32)
 		              | be32_to_cpu(args.args[1]);
-		rc = rtas_ibm_suspend_me(handle, &vasi_rc);
-		args.rets[0] = cpu_to_be32(vasi_rc);
-		if (rc)
+		rc = rtas_ibm_suspend_me(handle);
+		if (rc == -EAGAIN)
+			args.rets[0] = cpu_to_be32(RTAS_NOT_SUSPENDABLE);
+		else if (rc == -EIO)
+			args.rets[0] = cpu_to_be32(-1);
+		else if (rc)
 			return rc;
 		goto copy_return;
 	}
diff --git a/arch/powerpc/kernel/rtas_pci.c b/arch/powerpc/kernel/rtas_pci.c
index ce230da2c015..73f1934582c2 100644
--- a/arch/powerpc/kernel/rtas_pci.c
+++ b/arch/powerpc/kernel/rtas_pci.c
@@ -113,7 +113,7 @@ static int rtas_pci_read_config(struct pci_bus *bus,
 
 	ret = rtas_read_config(pdn, where, size, val);
 	if (*val == EEH_IO_ERROR_VALUE(size) &&
-	    eeh_dev_check_failure(of_node_to_eeh_dev(dn)))
+	    eeh_dev_check_failure(pdn_to_eeh_dev(pdn)))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	return ret;
@@ -277,50 +277,3 @@ int rtas_setup_phb(struct pci_controller *phb)
 
 	return 0;
 }
-
-void __init find_and_init_phbs(void)
-{
-	struct device_node *node;
-	struct pci_controller *phb;
-	struct device_node *root = of_find_node_by_path("/");
-
-	for_each_child_of_node(root, node) {
-		if (node->type == NULL || (strcmp(node->type, "pci") != 0 &&
-					   strcmp(node->type, "pciex") != 0))
-			continue;
-
-		phb = pcibios_alloc_controller(node);
-		if (!phb)
-			continue;
-		rtas_setup_phb(phb);
-		pci_process_bridge_OF_ranges(phb, node, 0);
-		isa_bridge_find_early(phb);
-	}
-
-	of_node_put(root);
-	pci_devs_phb_init();
-
-	/*
-	 * PCI_PROBE_ONLY and PCI_REASSIGN_ALL_BUS can be set via properties
-	 * in chosen.
-	 */
-	if (of_chosen) {
-		const int *prop;
-
-		prop = of_get_property(of_chosen,
-				"linux,pci-probe-only", NULL);
-		if (prop) {
-			if (*prop)
-				pci_add_flags(PCI_PROBE_ONLY);
-			else
-				pci_clear_flags(PCI_PROBE_ONLY);
-		}
-
-#ifdef CONFIG_PPC32 /* Will be made generic soon */
-		prop = of_get_property(of_chosen,
-				"linux,pci-assign-all-buses", NULL);
-		if (prop && *prop)
-			pci_add_flags(PCI_REASSIGN_ALL_BUS);
-#endif /* CONFIG_PPC32 */
-	}
-}
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 49f553bbb360..c69671c03c3b 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -37,6 +37,7 @@
 #include <linux/memblock.h>
 #include <linux/hugetlb.h>
 #include <linux/memory.h>
+#include <linux/nmi.h>
 
 #include <asm/io.h>
 #include <asm/kdump.h>
@@ -779,3 +780,22 @@ unsigned long memory_block_size_bytes(void)
 struct ppc_pci_io ppc_pci_io;
 EXPORT_SYMBOL(ppc_pci_io);
 #endif
+
+#ifdef CONFIG_HARDLOCKUP_DETECTOR
+u64 hw_nmi_get_sample_period(int watchdog_thresh)
+{
+	return ppc_proc_freq * watchdog_thresh;
+}
+
+/*
+ * The hardlockup detector breaks PMU event based branches and is likely
+ * to get false positives in KVM guests, so disable it by default.
+ */
+static int __init disable_hardlockup_detector(void)
+{
+	hardlockup_detector_disable();
+
+	return 0;
+}
+early_initcall(disable_hardlockup_detector);
+#endif
diff --git a/arch/powerpc/kernel/syscalls.c b/arch/powerpc/kernel/syscalls.c
index b2702e87db0d..5fa92706444b 100644
--- a/arch/powerpc/kernel/syscalls.c
+++ b/arch/powerpc/kernel/syscalls.c
@@ -121,3 +121,20 @@ long ppc_fadvise64_64(int fd, int advice, u32 offset_high, u32 offset_low,
 	return sys_fadvise64(fd, (u64)offset_high << 32 | offset_low,
 			     (u64)len_high << 32 | len_low, advice);
 }
+
+long sys_switch_endian(void)
+{
+	struct thread_info *ti;
+
+	current->thread.regs->msr ^= MSR_LE;
+
+	/*
+	 * Set TIF_RESTOREALL so that r3 isn't clobbered on return to
+	 * userspace. That also has the effect of restoring the non-volatile
+	 * GPRs, so we saved them on the way in here.
+	 */
+	ti = current_thread_info();
+	ti->flags |= _TIF_RESTOREALL;
+
+	return 0;
+}
diff --git a/arch/powerpc/kernel/systbl.S b/arch/powerpc/kernel/systbl.S
index 7ab5d434e2ee..4d6b1d3a747f 100644
--- a/arch/powerpc/kernel/systbl.S
+++ b/arch/powerpc/kernel/systbl.S
@@ -22,6 +22,7 @@
 #define PPC_SYS(func)		.llong	DOTSYM(ppc_##func),DOTSYM(ppc_##func)
 #define OLDSYS(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(sys_ni_syscall)
 #define SYS32ONLY(func)		.llong	DOTSYM(sys_ni_syscall),DOTSYM(compat_sys_##func)
+#define PPC64ONLY(func)		.llong	DOTSYM(ppc_##func),DOTSYM(sys_ni_syscall)
 #define SYSX(f, f3264, f32)	.llong	DOTSYM(f),DOTSYM(f3264)
 #else
 #define SYSCALL(func)		.long	sys_##func
@@ -29,6 +30,7 @@
 #define PPC_SYS(func)		.long	ppc_##func
 #define OLDSYS(func)		.long	sys_##func
 #define SYS32ONLY(func)		.long	sys_##func
+#define PPC64ONLY(func)		.long	sys_ni_syscall
 #define SYSX(f, f3264, f32)	.long	f32
 #endif
 #define SYSCALL_SPU(func)	SYSCALL(func)
diff --git a/arch/powerpc/kernel/systbl_chk.c b/arch/powerpc/kernel/systbl_chk.c
index 238aa63ced8f..2384129f5893 100644
--- a/arch/powerpc/kernel/systbl_chk.c
+++ b/arch/powerpc/kernel/systbl_chk.c
@@ -21,9 +21,11 @@
 #ifdef CONFIG_PPC64
 #define OLDSYS(func)		-1
 #define SYS32ONLY(func)		-1
+#define PPC64ONLY(func)		__NR_##func
 #else
 #define OLDSYS(func)		__NR_old##func
 #define SYS32ONLY(func)		__NR_##func
+#define PPC64ONLY(func)		-1
 #endif
 #define SYSX(f, f3264, f32)	-1
 
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 2a324f4cb1b9..5754b226da7e 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -152,9 +152,9 @@ _GLOBAL(tm_reclaim)
 
 	addi	r7, r3, THREAD_TRANSACT_VRSTATE
 	SAVE_32VRS(0, r6, r7)	/* r6 scratch, r7 transact vr state */
-	mfvscr	vr0
+	mfvscr	v0
 	li	r6, VRSTATE_VSCR
-	stvx	vr0, r7, r6
+	stvx	v0, r7, r6
 dont_backup_vec:
 	mfspr	r0, SPRN_VRSAVE
 	std	r0, THREAD_TRANSACT_VRSAVE(r3)
@@ -359,8 +359,8 @@ _GLOBAL(__tm_recheckpoint)
 
 	addi	r8, r3, THREAD_VRSTATE
 	li	r5, VRSTATE_VSCR
-	lvx	vr0, r8, r5
-	mtvscr	vr0
+	lvx	v0, r8, r5
+	mtvscr	v0
 	REST_32VRS(0, r5, r8)			/* r5 scratch, r8 ptr */
 dont_restore_vec:
 	ld	r5, THREAD_VRSAVE(r3)
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index b7aa07279a63..7cc38b5b58bc 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -46,8 +46,6 @@ void __init udbg_early_init(void)
 #elif defined(CONFIG_PPC_EARLY_DEBUG_MAPLE)
 	/* Maple real mode debug */
 	udbg_init_maple_realmode();
-#elif defined(CONFIG_PPC_EARLY_DEBUG_BEAT)
-	udbg_init_debug_beat();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
 	udbg_init_pas_realmode();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
diff --git a/arch/powerpc/kernel/vector.S b/arch/powerpc/kernel/vector.S
index 74f8050518d6..f5c80d567d8d 100644
--- a/arch/powerpc/kernel/vector.S
+++ b/arch/powerpc/kernel/vector.S
@@ -24,8 +24,8 @@ _GLOBAL(do_load_up_transact_altivec)
 	stw	r4,THREAD_USED_VR(r3)
 
 	li	r10,THREAD_TRANSACT_VRSTATE+VRSTATE_VSCR
-	lvx	vr0,r10,r3
-	mtvscr	vr0
+	lvx	v0,r10,r3
+	mtvscr	v0
 	addi	r10,r3,THREAD_TRANSACT_VRSTATE
 	REST_32VRS(0,r4,r10)
 
@@ -52,8 +52,8 @@ _GLOBAL(vec_enable)
  */
 _GLOBAL(load_vr_state)
 	li	r4,VRSTATE_VSCR
-	lvx	vr0,r4,r3
-	mtvscr	vr0
+	lvx	v0,r4,r3
+	mtvscr	v0
 	REST_32VRS(0,r4,r3)
 	blr
 
@@ -63,9 +63,9 @@ _GLOBAL(load_vr_state)
  */
 _GLOBAL(store_vr_state)
 	SAVE_32VRS(0, r4, r3)
-	mfvscr	vr0
+	mfvscr	v0
 	li	r4, VRSTATE_VSCR
-	stvx	vr0, r4, r3
+	stvx	v0, r4, r3
 	blr
 
 /*
@@ -104,9 +104,9 @@ _GLOBAL(load_up_altivec)
 	addi	r4,r4,THREAD
 	addi	r6,r4,THREAD_VRSTATE
 	SAVE_32VRS(0,r5,r6)
-	mfvscr	vr0
+	mfvscr	v0
 	li	r10,VRSTATE_VSCR
-	stvx	vr0,r10,r6
+	stvx	v0,r10,r6
 	/* Disable VMX for last_task_used_altivec */
 	PPC_LL	r5,PT_REGS(r4)
 	toreal(r5)
@@ -142,8 +142,8 @@ _GLOBAL(load_up_altivec)
 	li	r4,1
 	li	r10,VRSTATE_VSCR
 	stw	r4,THREAD_USED_VR(r5)
-	lvx	vr0,r10,r6
-	mtvscr	vr0
+	lvx	v0,r10,r6
+	mtvscr	v0
 	REST_32VRS(0,r4,r6)
 #ifndef CONFIG_SMP
 	/* Update last_task_used_altivec to 'current' */
@@ -186,9 +186,9 @@ _GLOBAL(giveup_altivec)
 	addi	r7,r3,THREAD_VRSTATE
 2:	PPC_LCMPI	0,r5,0
 	SAVE_32VRS(0,r4,r7)
-	mfvscr	vr0
+	mfvscr	v0
 	li	r4,VRSTATE_VSCR
-	stvx	vr0,r4,r7
+	stvx	v0,r4,r7
 	beq	1f
 	PPC_LL	r4,_MSR-STACK_FRAME_OVERHEAD(r5)
 #ifdef CONFIG_VSX