Merge branch 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

Pull powerpc updates from Ben Herrenschmidt:
 "This is the powerpc changes for the 3.11 merge window.  In addition to
  the usual bug fixes and small updates, the main highlights are:

   - Support for transparent huge pages by Aneesh Kumar for 64-bit
     server processors.  This allows the use of 16M pages as transparent
     huge pages on kernels compiled with a 64K base page size.

   - Base VFIO support for KVM on power by Alexey Kardashevskiy

   - Wiring up of our nvram to the pstore infrastructure, including
     putting compressed oopses in there by Aruna Balakrishnaiah

   - Move, rework and improve our "EEH" (basically PCI error handling
     and recovery) infrastructure.  It is no longer specific to pseries
     but is now usable by the new "powernv" platform as well (no
     hypervisor) by Gavin Shan.

   - I fixed some bugs in our math-emu instruction decoding and made it
     usable to emulate some optional FP instructions on processors with
     hard FP that lack them (such as fsqrt on Freescale embedded
     processors).

   - Support for Power8 "Event Based Branch" facility by Michael
     Ellerman.  This facility allows what is basically "userspace
     interrupts" for performance monitor events.

   - A bunch of Transactional Memory vs.  Signals bug fixes and HW
     breakpoint/watchpoint fixes by Michael Neuling.

  And more ...  I appologize in advance if I've failed to highlight
  something that somebody deemed worth it."

* 'next' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc: (156 commits)
  pstore: Add hsize argument in write_buf call of pstore_ftrace_call
  powerpc/fsl: add MPIC timer wakeup support
  powerpc/mpic: create mpic subsystem object
  powerpc/mpic: add global timer support
  powerpc/mpic: add irq_set_wake support
  powerpc/85xx: enable coreint for all the 64bit boards
  powerpc/8xx: Erroneous double irq_eoi() on CPM IRQ in MPC8xx
  powerpc/fsl: Enable CONFIG_E1000E in mpc85xx_smp_defconfig
  powerpc/mpic: Add get_version API both for internal and external use
  powerpc: Handle both new style and old style reserve maps
  powerpc/hw_brk: Fix off by one error when validating DAWR region end
  powerpc/pseries: Support compression of oops text via pstore
  powerpc/pseries: Re-organise the oops compression code
  pstore: Pass header size in the pstore write callback
  powerpc/powernv: Fix iommu initialization again
  powerpc/pseries: Inform the hypervisor we are using EBB regs
  powerpc/perf: Add power8 EBB support
  powerpc/perf: Core EBB support for 64-bit book3s
  powerpc/perf: Drop MMCRA from thread_struct
  powerpc/perf: Don't enable if we have zero events
  ...

35 files changed, 3944 insertions, 157 deletions

diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index f960a7944553..a8619bfe879e 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -58,6 +58,8 @@ obj-$(CONFIG_RTAS_PROC)		+= rtas-proc.o
 obj-$(CONFIG_LPARCFG)		+= lparcfg.o
 obj-$(CONFIG_IBMVIO)		+= vio.o
 obj-$(CONFIG_IBMEBUS)           += ibmebus.o
+obj-$(CONFIG_EEH)              += eeh.o eeh_pe.o eeh_dev.o eeh_cache.o \
+				  eeh_driver.o eeh_event.o eeh_sysfs.o
 obj-$(CONFIG_GENERIC_TBSYNC)	+= smp-tbsync.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
 obj-$(CONFIG_FA_DUMP)		+= fadump.o
@@ -100,7 +102,7 @@ obj-$(CONFIG_PPC_UDBG_16550)	+= legacy_serial.o udbg_16550.o
 obj-$(CONFIG_STACKTRACE)	+= stacktrace.o
 obj-$(CONFIG_SWIOTLB)		+= dma-swiotlb.o
 
-pci64-$(CONFIG_PPC64)		+= pci_dn.o isa-bridge.o
+pci64-$(CONFIG_PPC64)		+= pci_dn.o pci-hotplug.o isa-bridge.o
 obj-$(CONFIG_PCI)		+= pci_$(CONFIG_WORD_SIZE).o $(pci64-y) \
 				   pci-common.o pci_of_scan.o
 obj-$(CONFIG_PCI_MSI)		+= msi.o
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 6f16ffafa6f0..c7e8afc2ead0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -105,9 +105,6 @@ int main(void)
 	DEFINE(KSP_VSID, offsetof(struct thread_struct, ksp_vsid));
 #else /* CONFIG_PPC64 */
 	DEFINE(PGDIR, offsetof(struct thread_struct, pgdir));
-#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
-	DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
-#endif
 #ifdef CONFIG_SPE
 	DEFINE(THREAD_EVR0, offsetof(struct thread_struct, evr[0]));
 	DEFINE(THREAD_ACC, offsetof(struct thread_struct, acc));
@@ -115,6 +112,9 @@ int main(void)
 	DEFINE(THREAD_USED_SPE, offsetof(struct thread_struct, used_spe));
 #endif /* CONFIG_SPE */
 #endif /* CONFIG_PPC64 */
+#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
+	DEFINE(THREAD_DBCR0, offsetof(struct thread_struct, dbcr0));
+#endif
 #ifdef CONFIG_KVM_BOOK3S_32_HANDLER
 	DEFINE(THREAD_KVM_SVCPU, offsetof(struct thread_struct, kvm_shadow_vcpu));
 #endif
@@ -132,7 +132,6 @@ int main(void)
 	DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
 	DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
 	DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
-	DEFINE(THREAD_MMCRA, offsetof(struct thread_struct, mmcra));
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
diff --git a/arch/powerpc/kernel/cacheinfo.c b/arch/powerpc/kernel/cacheinfo.c
index 92c6b008dd2b..9262cf2bec4b 100644
--- a/arch/powerpc/kernel/cacheinfo.c
+++ b/arch/powerpc/kernel/cacheinfo.c
@@ -131,7 +131,8 @@ static const char *cache_type_string(const struct cache *cache)
 	return cache_type_info[cache->type].name;
 }
 
-static void __cpuinit cache_init(struct cache *cache, int type, int level, struct device_node *ofnode)
+static void cache_init(struct cache *cache, int type, int level,
+		       struct device_node *ofnode)
 {
 	cache->type = type;
 	cache->level = level;
@@ -140,7 +141,7 @@ static void __cpuinit cache_init(struct cache *cache, int type, int level, struc
 	list_add(&cache->list, &cache_list);
 }
 
-static struct cache *__cpuinit new_cache(int type, int level, struct device_node *ofnode)
+static struct cache *new_cache(int type, int level, struct device_node *ofnode)
 {
 	struct cache *cache;
 
@@ -324,7 +325,8 @@ static bool cache_node_is_unified(const struct device_node *np)
 	return of_get_property(np, "cache-unified", NULL);
 }
 
-static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_unified(struct device_node *node,
+						  int level)
 {
 	struct cache *cache;
 
@@ -335,7 +337,8 @@ static struct cache *__cpuinit cache_do_one_devnode_unified(struct device_node *
 	return cache;
 }
 
-static struct cache *__cpuinit cache_do_one_devnode_split(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode_split(struct device_node *node,
+						int level)
 {
 	struct cache *dcache, *icache;
 
@@ -357,7 +360,7 @@ err:
 	return NULL;
 }
 
-static struct cache *__cpuinit cache_do_one_devnode(struct device_node *node, int level)
+static struct cache *cache_do_one_devnode(struct device_node *node, int level)
 {
 	struct cache *cache;
 
@@ -369,7 +372,8 @@ static struct cache *__cpuinit cache_do_one_devnode(struct device_node *node, in
 	return cache;
 }
 
-static struct cache *__cpuinit cache_lookup_or_instantiate(struct device_node *node, int level)
+static struct cache *cache_lookup_or_instantiate(struct device_node *node,
+						 int level)
 {
 	struct cache *cache;
 
@@ -385,7 +389,7 @@ static struct cache *__cpuinit cache_lookup_or_instantiate(struct device_node *n
 	return cache;
 }
 
-static void __cpuinit link_cache_lists(struct cache *smaller, struct cache *bigger)
+static void link_cache_lists(struct cache *smaller, struct cache *bigger)
 {
 	while (smaller->next_local) {
 		if (smaller->next_local == bigger)
@@ -396,13 +400,13 @@ static void __cpuinit link_cache_lists(struct cache *smaller, struct cache *bigg
 	smaller->next_local = bigger;
 }
 
-static void __cpuinit do_subsidiary_caches_debugcheck(struct cache *cache)
+static void do_subsidiary_caches_debugcheck(struct cache *cache)
 {
 	WARN_ON_ONCE(cache->level != 1);
 	WARN_ON_ONCE(strcmp(cache->ofnode->type, "cpu"));
 }
 
-static void __cpuinit do_subsidiary_caches(struct cache *cache)
+static void do_subsidiary_caches(struct cache *cache)
 {
 	struct device_node *subcache_node;
 	int level = cache->level;
@@ -423,7 +427,7 @@ static void __cpuinit do_subsidiary_caches(struct cache *cache)
 	}
 }
 
-static struct cache *__cpuinit cache_chain_instantiate(unsigned int cpu_id)
+static struct cache *cache_chain_instantiate(unsigned int cpu_id)
 {
 	struct device_node *cpu_node;
 	struct cache *cpu_cache = NULL;
@@ -448,7 +452,7 @@ out:
 	return cpu_cache;
 }
 
-static struct cache_dir *__cpuinit cacheinfo_create_cache_dir(unsigned int cpu_id)
+static struct cache_dir *cacheinfo_create_cache_dir(unsigned int cpu_id)
 {
 	struct cache_dir *cache_dir;
 	struct device *dev;
@@ -653,7 +657,7 @@ static struct kobj_type cache_index_type = {
 	.default_attrs = cache_index_default_attrs,
 };
 
-static void __cpuinit cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
+static void cacheinfo_create_index_opt_attrs(struct cache_index_dir *dir)
 {
 	const char *cache_name;
 	const char *cache_type;
@@ -696,7 +700,8 @@ static void __cpuinit cacheinfo_create_index_opt_attrs(struct cache_index_dir *d
 	kfree(buf);
 }
 
-static void __cpuinit cacheinfo_create_index_dir(struct cache *cache, int index, struct cache_dir *cache_dir)
+static void cacheinfo_create_index_dir(struct cache *cache, int index,
+				       struct cache_dir *cache_dir)
 {
 	struct cache_index_dir *index_dir;
 	int rc;
@@ -722,7 +727,8 @@ err:
 	kfree(index_dir);
 }
 
-static void __cpuinit cacheinfo_sysfs_populate(unsigned int cpu_id, struct cache *cache_list)
+static void cacheinfo_sysfs_populate(unsigned int cpu_id,
+				     struct cache *cache_list)
 {
 	struct cache_dir *cache_dir;
 	struct cache *cache;
@@ -740,7 +746,7 @@ static void __cpuinit cacheinfo_sysfs_populate(unsigned int cpu_id, struct cache
 	}
 }
 
-void __cpuinit cacheinfo_cpu_online(unsigned int cpu_id)
+void cacheinfo_cpu_online(unsigned int cpu_id)
 {
 	struct cache *cache;
 
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
new file mode 100644
index 000000000000..39954fe941b8
--- /dev/null
+++ b/arch/powerpc/kernel/eeh.c
@@ -0,0 +1,1070 @@
+/*
+ * Copyright IBM Corporation 2001, 2005, 2006
+ * Copyright Dave Engebretsen & Todd Inglett 2001
+ * Copyright Linas Vepstas 2005, 2006
+ * Copyright 2001-2012 IBM Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ * Please address comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/proc_fs.h>
+#include <linux/rbtree.h>
+#include <linux/seq_file.h>
+#include <linux/spinlock.h>
+#include <linux/export.h>
+#include <linux/of.h>
+
+#include <linux/atomic.h>
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/io.h>
+#include <asm/machdep.h>
+#include <asm/ppc-pci.h>
+#include <asm/rtas.h>
+
+
+/** Overview:
+ *  EEH, or "Extended Error Handling" is a PCI bridge technology for
+ *  dealing with PCI bus errors that can't be dealt with within the
+ *  usual PCI framework, except by check-stopping the CPU.  Systems
+ *  that are designed for high-availability/reliability cannot afford
+ *  to crash due to a "mere" PCI error, thus the need for EEH.
+ *  An EEH-capable bridge operates by converting a detected error
+ *  into a "slot freeze", taking the PCI adapter off-line, making
+ *  the slot behave, from the OS'es point of view, as if the slot
+ *  were "empty": all reads return 0xff's and all writes are silently
+ *  ignored.  EEH slot isolation events can be triggered by parity
+ *  errors on the address or data busses (e.g. during posted writes),
+ *  which in turn might be caused by low voltage on the bus, dust,
+ *  vibration, humidity, radioactivity or plain-old failed hardware.
+ *
+ *  Note, however, that one of the leading causes of EEH slot
+ *  freeze events are buggy device drivers, buggy device microcode,
+ *  or buggy device hardware.  This is because any attempt by the
+ *  device to bus-master data to a memory address that is not
+ *  assigned to the device will trigger a slot freeze.   (The idea
+ *  is to prevent devices-gone-wild from corrupting system memory).
+ *  Buggy hardware/drivers will have a miserable time co-existing
+ *  with EEH.
+ *
+ *  Ideally, a PCI device driver, when suspecting that an isolation
+ *  event has occurred (e.g. by reading 0xff's), will then ask EEH
+ *  whether this is the case, and then take appropriate steps to
+ *  reset the PCI slot, the PCI device, and then resume operations.
+ *  However, until that day,  the checking is done here, with the
+ *  eeh_check_failure() routine embedded in the MMIO macros.  If
+ *  the slot is found to be isolated, an "EEH Event" is synthesized
+ *  and sent out for processing.
+ */
+
+/* If a device driver keeps reading an MMIO register in an interrupt
+ * handler after a slot isolation event, it might be broken.
+ * This sets the threshold for how many read attempts we allow
+ * before printing an error message.
+ */
+#define EEH_MAX_FAILS	2100000
+
+/* Time to wait for a PCI slot to report status, in milliseconds */
+#define PCI_BUS_RESET_WAIT_MSEC (60*1000)
+
+/* Platform dependent EEH operations */
+struct eeh_ops *eeh_ops = NULL;
+
+int eeh_subsystem_enabled;
+EXPORT_SYMBOL(eeh_subsystem_enabled);
+
+/*
+ * EEH probe mode support. The intention is to support multiple
+ * platforms for EEH. Some platforms like pSeries do PCI emunation
+ * based on device tree. However, other platforms like powernv probe
+ * PCI devices from hardware. The flag is used to distinguish that.
+ * In addition, struct eeh_ops::probe would be invoked for particular
+ * OF node or PCI device so that the corresponding PE would be created
+ * there.
+ */
+int eeh_probe_mode;
+
+/* Lock to avoid races due to multiple reports of an error */
+DEFINE_RAW_SPINLOCK(confirm_error_lock);
+
+/* Buffer for reporting pci register dumps. Its here in BSS, and
+ * not dynamically alloced, so that it ends up in RMO where RTAS
+ * can access it.
+ */
+#define EEH_PCI_REGS_LOG_LEN 4096
+static unsigned char pci_regs_buf[EEH_PCI_REGS_LOG_LEN];
+
+/*
+ * The struct is used to maintain the EEH global statistic
+ * information. Besides, the EEH global statistics will be
+ * exported to user space through procfs
+ */
+struct eeh_stats {
+	u64 no_device;		/* PCI device not found		*/
+	u64 no_dn;		/* OF node not found		*/
+	u64 no_cfg_addr;	/* Config address not found	*/
+	u64 ignored_check;	/* EEH check skipped		*/
+	u64 total_mmio_ffs;	/* Total EEH checks		*/
+	u64 false_positives;	/* Unnecessary EEH checks	*/
+	u64 slot_resets;	/* PE reset			*/
+};
+
+static struct eeh_stats eeh_stats;
+
+#define IS_BRIDGE(class_code) (((class_code)<<16) == PCI_BASE_CLASS_BRIDGE)
+
+/**
+ * eeh_gather_pci_data - Copy assorted PCI config space registers to buff
+ * @edev: device to report data for
+ * @buf: point to buffer in which to log
+ * @len: amount of room in buffer
+ *
+ * This routine captures assorted PCI configuration space data,
+ * and puts them into a buffer for RTAS error logging.
+ */
+static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
+{
+	struct device_node *dn = eeh_dev_to_of_node(edev);
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	u32 cfg;
+	int cap, i;
+	int n = 0;
+
+	n += scnprintf(buf+n, len-n, "%s\n", dn->full_name);
+	printk(KERN_WARNING "EEH: of node=%s\n", dn->full_name);
+
+	eeh_ops->read_config(dn, PCI_VENDOR_ID, 4, &cfg);
+	n += scnprintf(buf+n, len-n, "dev/vend:%08x\n", cfg);
+	printk(KERN_WARNING "EEH: PCI device/vendor: %08x\n", cfg);
+
+	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cfg);
+	n += scnprintf(buf+n, len-n, "cmd/stat:%x\n", cfg);
+	printk(KERN_WARNING "EEH: PCI cmd/status register: %08x\n", cfg);
+
+	if (!dev) {
+		printk(KERN_WARNING "EEH: no PCI device for this of node\n");
+		return n;
+	}
+
+	/* Gather bridge-specific registers */
+	if (dev->class >> 16 == PCI_BASE_CLASS_BRIDGE) {
+		eeh_ops->read_config(dn, PCI_SEC_STATUS, 2, &cfg);
+		n += scnprintf(buf+n, len-n, "sec stat:%x\n", cfg);
+		printk(KERN_WARNING "EEH: Bridge secondary status: %04x\n", cfg);
+
+		eeh_ops->read_config(dn, PCI_BRIDGE_CONTROL, 2, &cfg);
+		n += scnprintf(buf+n, len-n, "brdg ctl:%x\n", cfg);
+		printk(KERN_WARNING "EEH: Bridge control: %04x\n", cfg);
+	}
+
+	/* Dump out the PCI-X command and status regs */
+	cap = pci_find_capability(dev, PCI_CAP_ID_PCIX);
+	if (cap) {
+		eeh_ops->read_config(dn, cap, 4, &cfg);
+		n += scnprintf(buf+n, len-n, "pcix-cmd:%x\n", cfg);
+		printk(KERN_WARNING "EEH: PCI-X cmd: %08x\n", cfg);
+
+		eeh_ops->read_config(dn, cap+4, 4, &cfg);
+		n += scnprintf(buf+n, len-n, "pcix-stat:%x\n", cfg);
+		printk(KERN_WARNING "EEH: PCI-X status: %08x\n", cfg);
+	}
+
+	/* If PCI-E capable, dump PCI-E cap 10, and the AER */
+	cap = pci_find_capability(dev, PCI_CAP_ID_EXP);
+	if (cap) {
+		n += scnprintf(buf+n, len-n, "pci-e cap10:\n");
+		printk(KERN_WARNING
+		       "EEH: PCI-E capabilities and status follow:\n");
+
+		for (i=0; i<=8; i++) {
+			eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+			n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
+			printk(KERN_WARNING "EEH: PCI-E %02x: %08x\n", i, cfg);
+		}
+
+		cap = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ERR);
+		if (cap) {
+			n += scnprintf(buf+n, len-n, "pci-e AER:\n");
+			printk(KERN_WARNING
+			       "EEH: PCI-E AER capability register set follows:\n");
+
+			for (i=0; i<14; i++) {
+				eeh_ops->read_config(dn, cap+4*i, 4, &cfg);
+				n += scnprintf(buf+n, len-n, "%02x:%x\n", 4*i, cfg);
+				printk(KERN_WARNING "EEH: PCI-E AER %02x: %08x\n", i, cfg);
+			}
+		}
+	}
+
+	return n;
+}
+
+/**
+ * eeh_slot_error_detail - Generate combined log including driver log and error log
+ * @pe: EEH PE
+ * @severity: temporary or permanent error log
+ *
+ * This routine should be called to generate the combined log, which
+ * is comprised of driver log and error log. The driver log is figured
+ * out from the config space of the corresponding PCI device, while
+ * the error log is fetched through platform dependent function call.
+ */
+void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
+{
+	size_t loglen = 0;
+	struct eeh_dev *edev;
+	bool valid_cfg_log = true;
+
+	/*
+	 * When the PHB is fenced or dead, it's pointless to collect
+	 * the data from PCI config space because it should return
+	 * 0xFF's. For ER, we still retrieve the data from the PCI
+	 * config space.
+	 */
+	if (eeh_probe_mode_dev() &&
+	    (pe->type & EEH_PE_PHB) &&
+	    (pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)))
+		valid_cfg_log = false;
+
+	if (valid_cfg_log) {
+		eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+		eeh_ops->configure_bridge(pe);
+		eeh_pe_restore_bars(pe);
+
+		pci_regs_buf[0] = 0;
+		eeh_pe_for_each_dev(pe, edev) {
+			loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
+						      EEH_PCI_REGS_LOG_LEN - loglen);
+		}
+	}
+
+	eeh_ops->get_log(pe, severity, pci_regs_buf, loglen);
+}
+
+/**
+ * eeh_token_to_phys - Convert EEH address token to phys address
+ * @token: I/O token, should be address in the form 0xA....
+ *
+ * This routine should be called to convert virtual I/O address
+ * to physical one.
+ */
+static inline unsigned long eeh_token_to_phys(unsigned long token)
+{
+	pte_t *ptep;
+	unsigned long pa;
+	int hugepage_shift;
+
+	/*
+	 * We won't find hugepages here, iomem
+	 */
+	ptep = find_linux_pte_or_hugepte(init_mm.pgd, token, &hugepage_shift);
+	if (!ptep)
+		return token;
+	WARN_ON(hugepage_shift);
+	pa = pte_pfn(*ptep) << PAGE_SHIFT;
+
+	return pa | (token & (PAGE_SIZE-1));
+}
+
+/*
+ * On PowerNV platform, we might already have fenced PHB there.
+ * For that case, it's meaningless to recover frozen PE. Intead,
+ * We have to handle fenced PHB firstly.
+ */
+static int eeh_phb_check_failure(struct eeh_pe *pe)
+{
+	struct eeh_pe *phb_pe;
+	unsigned long flags;
+	int ret;
+
+	if (!eeh_probe_mode_dev())
+		return -EPERM;
+
+	/* Find the PHB PE */
+	phb_pe = eeh_phb_pe_get(pe->phb);
+	if (!phb_pe) {
+		pr_warning("%s Can't find PE for PHB#%d\n",
+			   __func__, pe->phb->global_number);
+		return -EEXIST;
+	}
+
+	/* If the PHB has been in problematic state */
+	eeh_serialize_lock(&flags);
+	if (phb_pe->state & (EEH_PE_ISOLATED | EEH_PE_PHB_DEAD)) {
+		ret = 0;
+		goto out;
+	}
+
+	/* Check PHB state */
+	ret = eeh_ops->get_state(phb_pe, NULL);
+	if ((ret < 0) ||
+	    (ret == EEH_STATE_NOT_SUPPORT) ||
+	    (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
+	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
+		ret = 0;
+		goto out;
+	}
+
+	/* Isolate the PHB and send event */
+	eeh_pe_state_mark(phb_pe, EEH_PE_ISOLATED);
+	eeh_serialize_unlock(flags);
+	eeh_send_failure_event(phb_pe);
+
+	pr_err("EEH: PHB#%x failure detected\n",
+		phb_pe->phb->global_number);
+	dump_stack();
+
+	return 1;
+out:
+	eeh_serialize_unlock(flags);
+	return ret;
+}
+
+/**
+ * eeh_dev_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @edev: eeh device
+ *
+ * Check for an EEH failure for the given device node.  Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze.  This routine
+ * will query firmware for the EEH status.
+ *
+ * Returns 0 if there has not been an EEH error; otherwise returns
+ * a non-zero value and queues up a slot isolation event notification.
+ *
+ * It is safe to call this routine in an interrupt context.
+ */
+int eeh_dev_check_failure(struct eeh_dev *edev)
+{
+	int ret;
+	unsigned long flags;
+	struct device_node *dn;
+	struct pci_dev *dev;
+	struct eeh_pe *pe;
+	int rc = 0;
+	const char *location;
+
+	eeh_stats.total_mmio_ffs++;
+
+	if (!eeh_subsystem_enabled)
+		return 0;
+
+	if (!edev) {
+		eeh_stats.no_dn++;
+		return 0;
+	}
+	dn = eeh_dev_to_of_node(edev);
+	dev = eeh_dev_to_pci_dev(edev);
+	pe = edev->pe;
+
+	/* 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);
+		return 0;
+	}
+
+	if (!pe->addr && !pe->config_addr) {
+		eeh_stats.no_cfg_addr++;
+		return 0;
+	}
+
+	/*
+	 * On PowerNV platform, we might already have fenced PHB
+	 * there and we need take care of that firstly.
+	 */
+	ret = eeh_phb_check_failure(pe);
+	if (ret > 0)
+		return ret;
+
+	/* If we already have a pending isolation event for this
+	 * slot, we know it's bad already, we don't need to check.
+	 * Do this checking under a lock; as multiple PCI devices
+	 * in one slot might report errors simultaneously, and we
+	 * only want one error recovery routine running.
+	 */
+	eeh_serialize_lock(&flags);
+	rc = 1;
+	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);
+			printk(KERN_ERR "EEH: %d reads ignored for recovering device at "
+				"location=%s driver=%s pci addr=%s\n",
+				pe->check_count, location,
+				eeh_driver_name(dev), eeh_pci_name(dev));
+			printk(KERN_ERR "EEH: Might be infinite loop in %s driver\n",
+				eeh_driver_name(dev));
+			dump_stack();
+		}
+		goto dn_unlock;
+	}
+
+	/*
+	 * Now test for an EEH failure.  This is VERY expensive.
+	 * Note that the eeh_config_addr may be a parent device
+	 * in the case of a device behind a bridge, or it may be
+	 * function zero of a multi-function device.
+	 * In any case they must share a common PHB.
+	 */
+	ret = eeh_ops->get_state(pe, NULL);
+
+	/* Note that config-io to empty slots may fail;
+	 * they are empty when they don't have children.
+	 * We will punt with the following conditions: Failure to get
+	 * PE's state, EEH not support and Permanently unavailable
+	 * state, PE is in good state.
+	 */
+	if ((ret < 0) ||
+	    (ret == EEH_STATE_NOT_SUPPORT) ||
+	    (ret & (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) ==
+	    (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE)) {
+		eeh_stats.false_positives++;
+		pe->false_positives++;
+		rc = 0;
+		goto dn_unlock;
+	}
+
+	eeh_stats.slot_resets++;
+
+	/* Avoid repeated reports of this failure, including problems
+	 * with other functions on this device, and functions under
+	 * bridges.
+	 */
+	eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
+	eeh_serialize_unlock(flags);
+
+	eeh_send_failure_event(pe);
+
+	/* Most EEH events are due to device driver bugs.  Having
+	 * a stack trace will help the device-driver authors figure
+	 * out what happened.  So print that out.
+	 */
+	pr_err("EEH: Frozen PE#%x detected on PHB#%x\n",
+		pe->addr, pe->phb->global_number);
+	dump_stack();
+
+	return 1;
+
+dn_unlock:
+	eeh_serialize_unlock(flags);
+	return rc;
+}
+
+EXPORT_SYMBOL_GPL(eeh_dev_check_failure);
+
+/**
+ * eeh_check_failure - Check if all 1's data is due to EEH slot freeze
+ * @token: I/O token, should be address in the form 0xA....
+ * @val: value, should be all 1's (XXX why do we need this arg??)
+ *
+ * Check for an EEH failure at the given token address.  Call this
+ * routine if the result of a read was all 0xff's and you want to
+ * find out if this is due to an EEH slot freeze event.  This routine
+ * will query firmware for the EEH status.
+ *
+ * Note this routine is safe to call in an interrupt context.
+ */
+unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned long val)
+{
+	unsigned long addr;
+	struct eeh_dev *edev;
+
+	/* Finding the phys addr + pci device; this is pretty quick. */
+	addr = eeh_token_to_phys((unsigned long __force) token);
+	edev = eeh_addr_cache_get_dev(addr);
+	if (!edev) {
+		eeh_stats.no_device++;
+		return val;
+	}
+
+	eeh_dev_check_failure(edev);
+
+	pci_dev_put(eeh_dev_to_pci_dev(edev));
+	return val;
+}
+
+EXPORT_SYMBOL(eeh_check_failure);
+
+
+/**
+ * eeh_pci_enable - Enable MMIO or DMA transfers for this slot
+ * @pe: EEH PE
+ *
+ * This routine should be called to reenable frozen MMIO or DMA
+ * so that it would work correctly again. It's useful while doing
+ * recovery or log collection on the indicated device.
+ */
+int eeh_pci_enable(struct eeh_pe *pe, int function)
+{
+	int rc;
+
+	rc = eeh_ops->set_option(pe, function);
+	if (rc)
+		pr_warning("%s: Unexpected state change %d on PHB#%d-PE#%x, err=%d\n",
+			__func__, function, pe->phb->global_number, pe->addr, rc);
+
+	rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+	if (rc > 0 && (rc & EEH_STATE_MMIO_ENABLED) &&
+	   (function == EEH_OPT_THAW_MMIO))
+		return 0;
+
+	return rc;
+}
+
+/**
+ * pcibios_set_pcie_slot_reset - Set PCI-E reset state
+ * @dev: pci device struct
+ * @state: reset state to enter
+ *
+ * Return value:
+ * 	0 if success
+ */
+int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state)
+{
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+	struct eeh_pe *pe = edev->pe;
+
+	if (!pe) {
+		pr_err("%s: No PE found on PCI device %s\n",
+			__func__, pci_name(dev));
+		return -EINVAL;
+	}
+
+	switch (state) {
+	case pcie_deassert_reset:
+		eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+		break;
+	case pcie_hot_reset:
+		eeh_ops->reset(pe, EEH_RESET_HOT);
+		break;
+	case pcie_warm_reset:
+		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
+		break;
+	default:
+		return -EINVAL;
+	};
+
+	return 0;
+}
+
+/**
+ * eeh_set_pe_freset - Check the required reset for the indicated device
+ * @data: EEH device
+ * @flag: return value
+ *
+ * Each device might have its preferred reset type: fundamental or
+ * hot reset. The routine is used to collected the information for
+ * the indicated device and its children so that the bunch of the
+ * devices could be reset properly.
+ */
+static void *eeh_set_dev_freset(void *data, void *flag)
+{
+	struct pci_dev *dev;
+	unsigned int *freset = (unsigned int *)flag;
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+
+	dev = eeh_dev_to_pci_dev(edev);
+	if (dev)
+		*freset |= dev->needs_freset;
+
+	return NULL;
+}
+
+/**
+ * eeh_reset_pe_once - Assert the pci #RST line for 1/4 second
+ * @pe: EEH PE
+ *
+ * Assert the PCI #RST line for 1/4 second.
+ */
+static void eeh_reset_pe_once(struct eeh_pe *pe)
+{
+	unsigned int freset = 0;
+
+	/* Determine type of EEH reset required for
+	 * Partitionable Endpoint, a hot-reset (1)
+	 * or a fundamental reset (3).
+	 * A fundamental reset required by any device under
+	 * Partitionable Endpoint trumps hot-reset.
+	 */
+	eeh_pe_dev_traverse(pe, eeh_set_dev_freset, &freset);
+
+	if (freset)
+		eeh_ops->reset(pe, EEH_RESET_FUNDAMENTAL);
+	else
+		eeh_ops->reset(pe, EEH_RESET_HOT);
+
+	/* The PCI bus requires that the reset be held high for at least
+	 * a 100 milliseconds. We wait a bit longer 'just in case'.
+	 */
+#define PCI_BUS_RST_HOLD_TIME_MSEC 250
+	msleep(PCI_BUS_RST_HOLD_TIME_MSEC);
+
+	/* We might get hit with another EEH freeze as soon as the
+	 * pci slot reset line is dropped. Make sure we don't miss
+	 * these, and clear the flag now.
+	 */
+	eeh_pe_state_clear(pe, EEH_PE_ISOLATED);
+
+	eeh_ops->reset(pe, EEH_RESET_DEACTIVATE);
+
+	/* After a PCI slot has been reset, the PCI Express spec requires
+	 * a 1.5 second idle time for the bus to stabilize, before starting
+	 * up traffic.
+	 */
+#define PCI_BUS_SETTLE_TIME_MSEC 1800
+	msleep(PCI_BUS_SETTLE_TIME_MSEC);
+}
+
+/**
+ * eeh_reset_pe - Reset the indicated PE
+ * @pe: EEH PE
+ *
+ * This routine should be called to reset indicated device, including
+ * PE. A PE might include multiple PCI devices and sometimes PCI bridges
+ * might be involved as well.
+ */
+int eeh_reset_pe(struct eeh_pe *pe)
+{
+	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
+	int i, rc;
+
+	/* Take three shots at resetting the bus */
+	for (i=0; i<3; i++) {
+		eeh_reset_pe_once(pe);
+
+		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+		if ((rc & flags) == flags)
+			return 0;
+
+		if (rc < 0) {
+			pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+				__func__, pe->phb->global_number, pe->addr);
+			return -1;
+		}
+		pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n",
+			i+1, pe->phb->global_number, pe->addr, rc);
+	}
+
+	return -1;
+}
+
+/**
+ * eeh_save_bars - Save device bars
+ * @edev: PCI device associated EEH device
+ *
+ * Save the values of the device bars. Unlike the restore
+ * routine, this routine is *not* recursive. This is because
+ * PCI devices are added individually; but, for the restore,
+ * an entire slot is reset at a time.
+ */
+void eeh_save_bars(struct eeh_dev *edev)
+{
+	int i;
+	struct device_node *dn;
+
+	if (!edev)
+		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_register - Register platform dependent EEH operations
+ * @ops: platform dependent EEH operations
+ *
+ * Register the platform dependent EEH operation callback
+ * functions. The platform should call this function before
+ * any other EEH operations.
+ */
+int __init eeh_ops_register(struct eeh_ops *ops)
+{
+	if (!ops->name) {
+		pr_warning("%s: Invalid EEH ops name for %p\n",
+			__func__, ops);
+		return -EINVAL;
+	}
+
+	if (eeh_ops && eeh_ops != ops) {
+		pr_warning("%s: EEH ops of platform %s already existing (%s)\n",
+			__func__, eeh_ops->name, ops->name);
+		return -EEXIST;
+	}
+
+	eeh_ops = ops;
+
+	return 0;
+}
+
+/**
+ * eeh_ops_unregister - Unreigster platform dependent EEH operations
+ * @name: name of EEH platform operations
+ *
+ * Unregister the platform dependent EEH operation callback
+ * functions.
+ */
+int __exit eeh_ops_unregister(const char *name)
+{
+	if (!name || !strlen(name)) {
+		pr_warning("%s: Invalid EEH ops name\n",
+			__func__);
+		return -EINVAL;
+	}
+
+	if (eeh_ops && !strcmp(eeh_ops->name, name)) {
+		eeh_ops = NULL;
+		return 0;
+	}
+
+	return -EEXIST;
+}
+
+/**
+ * eeh_init - EEH initialization
+ *
+ * Initialize EEH by trying to enable it for all of the adapters in the system.
+ * As a side effect we can determine here if eeh is supported at all.
+ * Note that we leave EEH on so failed config cycles won't cause a machine
+ * check.  If a user turns off EEH for a particular adapter they are really
+ * telling Linux to ignore errors.  Some hardware (e.g. POWER5) won't
+ * grant access to a slot if EEH isn't enabled, and so we always enable
+ * EEH for all slots/all devices.
+ *
+ * The eeh-force-off option disables EEH checking globally, for all slots.
+ * Even if force-off is set, the EEH hardware is still enabled, so that
+ * newer systems can boot.
+ */
+int eeh_init(void)
+{
+	struct pci_controller *hose, *tmp;
+	struct device_node *phb;
+	static int cnt = 0;
+	int ret = 0;
+
+	/*
+	 * We have to delay the initialization on PowerNV after
+	 * the PCI hierarchy tree has been built because the PEs
+	 * are figured out based on PCI devices instead of device
+	 * tree nodes
+	 */
+	if (machine_is(powernv) && cnt++ <= 0)
+		return ret;
+
+	/* call platform initialization function */
+	if (!eeh_ops) {
+		pr_warning("%s: Platform EEH operation not found\n",
+			__func__);
+		return -EEXIST;
+	} else if ((ret = eeh_ops->init())) {
+		pr_warning("%s: Failed to call platform init function (%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	/* Initialize EEH event */
+	ret = eeh_event_init();
+	if (ret)
+		return ret;
+
+	/* Enable EEH for all adapters */
+	if (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_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_warning("%s: Invalid probe mode %d\n",
+			   __func__, eeh_probe_mode);
+		return -EINVAL;
+	}
+
+	/*
+	 * Call platform post-initialization. Actually, It's good chance
+	 * to inform platform that EEH is ready to supply service if the
+	 * I/O cache stuff has been built up.
+	 */
+	if (eeh_ops->post_init) {
+		ret = eeh_ops->post_init();
+		if (ret)
+			return ret;
+	}
+
+	if (eeh_subsystem_enabled)
+		pr_info("EEH: PCI Enhanced I/O Error Handling Enabled\n");
+	else
+		pr_warning("EEH: No capable adapters found\n");
+
+	return ret;
+}
+
+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
+ *
+ * This routine must be used to perform EEH initialization for PCI
+ * devices that were added after system boot (e.g. hotplug, dlpar).
+ * This routine must be called before any i/o is performed to the
+ * adapter (inluding any config-space i/o).
+ * Whether this actually enables EEH or not for this device depends
+ * 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)
+{
+	struct pci_controller *phb;
+
+	/*
+	 * 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_probe_mode_devtree())
+		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)
+		return;
+
+	eeh_ops->of_probe(dn, NULL);
+}
+
+/**
+ * eeh_add_device_tree_early - Enable EEH for the indicated device
+ * @dn: 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)
+{
+	struct device_node *sib;
+
+	for_each_child_of_node(dn, sib)
+		eeh_add_device_tree_early(sib);
+	eeh_add_device_early(dn);
+}
+EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
+
+/**
+ * eeh_add_device_late - Perform EEH initialization for the indicated pci device
+ * @dev: pci device for which to set up EEH
+ *
+ * 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)
+{
+	struct device_node *dn;
+	struct eeh_dev *edev;
+
+	if (!dev || !eeh_subsystem_enabled)
+		return;
+
+	pr_debug("EEH: Adding device %s\n", pci_name(dev));
+
+	dn = pci_device_to_OF_node(dev);
+	edev = of_node_to_eeh_dev(dn);
+	if (edev->pdev == dev) {
+		pr_debug("EEH: Already referenced !\n");
+		return;
+	}
+	WARN_ON(edev->pdev);
+
+	pci_dev_get(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_probe_mode_dev())
+		eeh_ops->dev_probe(dev, NULL);
+
+	eeh_addr_cache_insert_dev(dev);
+}
+
+/**
+ * eeh_add_device_tree_late - Perform EEH initialization for the indicated PCI bus
+ * @bus: PCI bus
+ *
+ * This routine must be used to perform EEH initialization for PCI
+ * devices which are attached to the indicated PCI bus. The PCI bus
+ * is added after system boot through hotplug or dlpar.
+ */
+void eeh_add_device_tree_late(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		eeh_add_device_late(dev);
+		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+			struct pci_bus *subbus = dev->subordinate;
+			if (subbus)
+				eeh_add_device_tree_late(subbus);
+		}
+	}
+}
+EXPORT_SYMBOL_GPL(eeh_add_device_tree_late);
+
+/**
+ * eeh_add_sysfs_files - Add EEH sysfs files for the indicated PCI bus
+ * @bus: PCI bus
+ *
+ * This routine must be used to add EEH sysfs files for PCI
+ * devices which are attached to the indicated PCI bus. The PCI bus
+ * is added after system boot through hotplug or dlpar.
+ */
+void eeh_add_sysfs_files(struct pci_bus *bus)
+{
+	struct pci_dev *dev;
+
+	list_for_each_entry(dev, &bus->devices, bus_list) {
+		eeh_sysfs_add_device(dev);
+		if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
+			struct pci_bus *subbus = dev->subordinate;
+			if (subbus)
+				eeh_add_sysfs_files(subbus);
+		}
+	}
+}
+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
+ * the PCI device from the EEH subsystem.  I/O errors affecting
+ * 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)
+{
+	struct eeh_dev *edev;
+
+	if (!dev || !eeh_subsystem_enabled)
+		return;
+	edev = pci_dev_to_eeh_dev(dev);
+
+	/* Unregister the device with the EEH/PCI address search system */
+	pr_debug("EEH: Removing device %s\n", pci_name(dev));
+
+	if (!edev || !edev->pdev) {
+		pr_debug("EEH: Not referenced !\n");
+		return;
+	}
+	edev->pdev = NULL;
+	dev->dev.archdata.edev = NULL;
+	pci_dev_put(dev);
+
+	eeh_rmv_from_parent_pe(edev, purge_pe);
+	eeh_addr_cache_rmv_dev(dev);
+	eeh_sysfs_remove_device(dev);
+}
+
+/**
+ * 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) {
+		seq_printf(m, "EEH Subsystem is globally disabled\n");
+		seq_printf(m, "eeh_total_mmio_ffs=%llu\n", eeh_stats.total_mmio_ffs);
+	} else {
+		seq_printf(m, "EEH Subsystem is enabled\n");
+		seq_printf(m,
+				"no device=%llu\n"
+				"no device node=%llu\n"
+				"no config address=%llu\n"
+				"check not wanted=%llu\n"
+				"eeh_total_mmio_ffs=%llu\n"
+				"eeh_false_positives=%llu\n"
+				"eeh_slot_resets=%llu\n",
+				eeh_stats.no_device,
+				eeh_stats.no_dn,
+				eeh_stats.no_cfg_addr,
+				eeh_stats.ignored_check,
+				eeh_stats.total_mmio_ffs,
+				eeh_stats.false_positives,
+				eeh_stats.slot_resets);
+	}
+
+	return 0;
+}
+
+static int proc_eeh_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, proc_eeh_show, NULL);
+}
+
+static const struct file_operations proc_eeh_operations = {
+	.open      = proc_eeh_open,
+	.read      = seq_read,
+	.llseek    = seq_lseek,
+	.release   = single_release,
+};
+
+static int __init eeh_init_proc(void)
+{
+	if (machine_is(pseries))
+		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
+	return 0;
+}
+__initcall(eeh_init_proc);
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
new file mode 100644
index 000000000000..f9ac1232a746
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -0,0 +1,318 @@
+/*
+ * PCI address cache; allows the lookup of PCI devices based on I/O address
+ *
+ * Copyright IBM Corporation 2004
+ * Copyright Linas Vepstas <linas@austin.ibm.com> 2004
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/list.h>
+#include <linux/pci.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <linux/spinlock.h>
+#include <linux/atomic.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+
+/**
+ * The pci address cache subsystem.  This subsystem places
+ * PCI device address resources into a red-black tree, sorted
+ * according to the address range, so that given only an i/o
+ * address, the corresponding PCI device can be **quickly**
+ * found. It is safe to perform an address lookup in an interrupt
+ * context; this ability is an important feature.
+ *
+ * Currently, the only customer of this code is the EEH subsystem;
+ * thus, this code has been somewhat tailored to suit EEH better.
+ * In particular, the cache does *not* hold the addresses of devices
+ * for which EEH is not enabled.
+ *
+ * (Implementation Note: The RB tree seems to be better/faster
+ * than any hash algo I could think of for this problem, even
+ * with the penalty of slow pointer chases for d-cache misses).
+ */
+struct pci_io_addr_range {
+	struct rb_node rb_node;
+	unsigned long addr_lo;
+	unsigned long addr_hi;
+	struct eeh_dev *edev;
+	struct pci_dev *pcidev;
+	unsigned int flags;
+};
+
+static struct pci_io_addr_cache {
+	struct rb_root rb_root;
+	spinlock_t piar_lock;
+} pci_io_addr_cache_root;
+
+static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr)
+{
+	struct rb_node *n = pci_io_addr_cache_root.rb_root.rb_node;
+
+	while (n) {
+		struct pci_io_addr_range *piar;
+		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+		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;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+/**
+ * eeh_addr_cache_get_dev - Get device, given only address
+ * @addr: mmio (PIO) phys address or i/o port number
+ *
+ * Given an mmio phys address, or a port number, find a pci device
+ * that implements this address.  Be sure to pci_dev_put the device
+ * when finished.  I/O port numbers are assumed to be offset
+ * from zero (that is, they do *not* have pci_io_addr added in).
+ * It is safe to call this function within an interrupt.
+ */
+struct eeh_dev *eeh_addr_cache_get_dev(unsigned long addr)
+{
+	struct eeh_dev *edev;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+	edev = __eeh_addr_cache_get_device(addr);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+	return edev;
+}
+
+#ifdef DEBUG
+/*
+ * Handy-dandy debug print routine, does nothing more
+ * than print out the contents of our addr cache.
+ */
+static void eeh_addr_cache_print(struct pci_io_addr_cache *cache)
+{
+	struct rb_node *n;
+	int cnt = 0;
+
+	n = rb_first(&cache->rb_root);
+	while (n) {
+		struct pci_io_addr_range *piar;
+		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+		pr_debug("PCI: %s addr range %d [%lx-%lx]: %s\n",
+		       (piar->flags & IORESOURCE_IO) ? "i/o" : "mem", cnt,
+		       piar->addr_lo, piar->addr_hi, pci_name(piar->pcidev));
+		cnt++;
+		n = rb_next(n);
+	}
+}
+#endif
+
+/* Insert address range into the rb tree. */
+static struct pci_io_addr_range *
+eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
+		      unsigned long ahi, unsigned int flags)
+{
+	struct rb_node **p = &pci_io_addr_cache_root.rb_root.rb_node;
+	struct rb_node *parent = NULL;
+	struct pci_io_addr_range *piar;
+
+	/* Walk tree, find a place to insert into tree */
+	while (*p) {
+		parent = *p;
+		piar = rb_entry(parent, struct pci_io_addr_range, rb_node);
+		if (ahi < piar->addr_lo) {
+			p = &parent->rb_left;
+		} else if (alo > piar->addr_hi) {
+			p = &parent->rb_right;
+		} else {
+			if (dev != piar->pcidev ||
+			    alo != piar->addr_lo || ahi != piar->addr_hi) {
+				pr_warning("PIAR: overlapping address range\n");
+			}
+			return piar;
+		}
+	}
+	piar = kzalloc(sizeof(struct pci_io_addr_range), GFP_ATOMIC);
+	if (!piar)
+		return NULL;
+
+	pci_dev_get(dev);
+	piar->addr_lo = alo;
+	piar->addr_hi = ahi;
+	piar->edev = pci_dev_to_eeh_dev(dev);
+	piar->pcidev = dev;
+	piar->flags = flags;
+
+#ifdef DEBUG
+	pr_debug("PIAR: insert range=[%lx:%lx] dev=%s\n",
+	                  alo, ahi, pci_name(dev));
+#endif
+
+	rb_link_node(&piar->rb_node, parent, p);
+	rb_insert_color(&piar->rb_node, &pci_io_addr_cache_root.rb_root);
+
+	return piar;
+}
+
+static void __eeh_addr_cache_insert_dev(struct pci_dev *dev)
+{
+	struct device_node *dn;
+	struct eeh_dev *edev;
+	int i;
+
+	dn = pci_device_to_OF_node(dev);
+	if (!dn) {
+		pr_warning("PCI: no pci dn found for dev=%s\n", pci_name(dev));
+		return;
+	}
+
+	edev = of_node_to_eeh_dev(dn);
+	if (!edev) {
+		pr_warning("PCI: no EEH dev found for dn=%s\n",
+			dn->full_name);
+		return;
+	}
+
+	/* Skip any devices for which EEH is not enabled. */
+	if (!eeh_probe_mode_dev() && !edev->pe) {
+#ifdef DEBUG
+		pr_info("PCI: skip building address cache for=%s - %s\n",
+			pci_name(dev), dn->full_name);
+#endif
+		return;
+	}
+
+	/* Walk resources on this device, poke them into the tree */
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+		unsigned long start = pci_resource_start(dev,i);
+		unsigned long end = pci_resource_end(dev,i);
+		unsigned int flags = pci_resource_flags(dev,i);
+
+		/* We are interested only bus addresses, not dma or other stuff */
+		if (0 == (flags & (IORESOURCE_IO | IORESOURCE_MEM)))
+			continue;
+		if (start == 0 || ~start == 0 || end == 0 || ~end == 0)
+			 continue;
+		eeh_addr_cache_insert(dev, start, end, flags);
+	}
+}
+
+/**
+ * eeh_addr_cache_insert_dev - Add a device to the address cache
+ * @dev: PCI device whose I/O addresses we are interested in.
+ *
+ * In order to support the fast lookup of devices based on addresses,
+ * we maintain a cache of devices that can be quickly searched.
+ * This routine adds a device to that cache.
+ */
+void eeh_addr_cache_insert_dev(struct pci_dev *dev)
+{
+	unsigned long flags;
+
+	/* Ignore PCI bridges */
+	if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE)
+		return;
+
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+	__eeh_addr_cache_insert_dev(dev);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+static inline void __eeh_addr_cache_rmv_dev(struct pci_dev *dev)
+{
+	struct rb_node *n;
+
+restart:
+	n = rb_first(&pci_io_addr_cache_root.rb_root);
+	while (n) {
+		struct pci_io_addr_range *piar;
+		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
+
+		if (piar->pcidev == dev) {
+			rb_erase(n, &pci_io_addr_cache_root.rb_root);
+			pci_dev_put(piar->pcidev);
+			kfree(piar);
+			goto restart;
+		}
+		n = rb_next(n);
+	}
+}
+
+/**
+ * eeh_addr_cache_rmv_dev - remove pci device from addr cache
+ * @dev: device to remove
+ *
+ * Remove a device from the addr-cache tree.
+ * This is potentially expensive, since it will walk
+ * the tree multiple times (once per resource).
+ * But so what; device removal doesn't need to be that fast.
+ */
+void eeh_addr_cache_rmv_dev(struct pci_dev *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pci_io_addr_cache_root.piar_lock, flags);
+	__eeh_addr_cache_rmv_dev(dev);
+	spin_unlock_irqrestore(&pci_io_addr_cache_root.piar_lock, flags);
+}
+
+/**
+ * eeh_addr_cache_build - Build a cache of I/O addresses
+ *
+ * Build a cache of pci i/o addresses.  This cache will be used to
+ * find the pci device that corresponds to a given address.
+ * This routine scans all pci busses to build the cache.
+ * Must be run late in boot process, after the pci controllers
+ * have been scanned for devices (after all device resources are known).
+ */
+void eeh_addr_cache_build(void)
+{
+	struct device_node *dn;
+	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)
+			continue;
+
+		edev = of_node_to_eeh_dev(dn);
+		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);
+	}
+
+#ifdef DEBUG
+	/* Verify tree built up above, echo back the list of addrs. */
+	eeh_addr_cache_print(&pci_io_addr_cache_root);
+#endif
+}
diff --git a/arch/powerpc/kernel/eeh_dev.c b/arch/powerpc/kernel/eeh_dev.c
new file mode 100644
index 000000000000..1efa28f5fc54
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_dev.c
@@ -0,0 +1,112 @@
+/*
+ * The file intends to implement dynamic creation of EEH device, which will
+ * be bound with OF node and PCI device simutaneously. The EEH devices would
+ * be foundamental information for EEH core components to work proerly. Besides,
+ * We have to support multiple situations where dynamic creation of EEH device
+ * is required:
+ *
+ * 1) Before PCI emunation starts, we need create EEH devices according to the
+ *    PCI sensitive OF nodes.
+ * 2) When PCI emunation is done, we need do the binding between PCI device and
+ *    the associated EEH device.
+ * 3) DR (Dynamic Reconfiguration) would create PCI sensitive OF node. EEH device
+ *    will be created while PCI sensitive OF node is detected from DR.
+ * 4) PCI hotplug needs redoing the binding between PCI device and EEH device. If
+ *    PHB is newly inserted, we also need create EEH devices accordingly.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+/**
+ * eeh_dev_init - Create EEH device according to OF node
+ * @dn: 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)
+{
+	struct pci_controller *phb = data;
+	struct eeh_dev *edev;
+
+	/* Allocate EEH device */
+	edev = kzalloc(sizeof(*edev), GFP_KERNEL);
+	if (!edev) {
+		pr_warning("%s: out of memory\n", __func__);
+		return NULL;
+	}
+
+	/* Associate EEH device with OF node */
+	PCI_DN(dn)->edev = edev;
+	edev->dn  = dn;
+	edev->phb = phb;
+	INIT_LIST_HEAD(&edev->list);
+
+	return NULL;
+}
+
+/**
+ * eeh_dev_phb_init_dynamic - Create EEH devices for devices included in PHB
+ * @phb: PHB
+ *
+ * Scan the PHB OF node and its child association, then create the
+ * EEH devices accordingly
+ */
+void eeh_dev_phb_init_dynamic(struct pci_controller *phb)
+{
+	struct device_node *dn = phb->dn;
+
+	/* EEH PE for PHB */
+	eeh_phb_pe_create(phb);
+
+	/* EEH device for PHB */
+	eeh_dev_init(dn, phb);
+
+	/* EEH devices for children OF nodes */
+	traverse_pci_devices(dn, eeh_dev_init, phb);
+}
+
+/**
+ * eeh_dev_phb_init - Create EEH devices for devices included in existing PHBs
+ *
+ * Scan all the existing PHBs and create EEH devices for their OF
+ * nodes and their children OF nodes
+ */
+static int __init eeh_dev_phb_init(void)
+{
+	struct pci_controller *phb, *tmp;
+
+	list_for_each_entry_safe(phb, tmp, &hose_list, list_node)
+		eeh_dev_phb_init_dynamic(phb);
+
+	pr_info("EEH: devices created\n");
+
+	return 0;
+}
+
+core_initcall(eeh_dev_phb_init);
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
new file mode 100644
index 000000000000..2b1ce17cae50
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -0,0 +1,661 @@
+/*
+ * PCI Error Recovery Driver for RPA-compliant PPC64 platform.
+ * Copyright IBM Corp. 2004 2005
+ * Copyright Linas Vepstas <linas@linas.org> 2004, 2005
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <asm/eeh.h>
+#include <asm/eeh_event.h>
+#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
+#include <asm/prom.h>
+#include <asm/rtas.h>
+
+/**
+ * eeh_pcid_name - Retrieve name of PCI device driver
+ * @pdev: PCI device
+ *
+ * This routine is used to retrieve the name of PCI device driver
+ * if that's valid.
+ */
+static inline const char *eeh_pcid_name(struct pci_dev *pdev)
+{
+	if (pdev && pdev->dev.driver)
+		return pdev->dev.driver->name;
+	return "";
+}
+
+/**
+ * eeh_pcid_get - Get the PCI device driver
+ * @pdev: PCI device
+ *
+ * The function is used to retrieve the PCI device driver for
+ * the indicated PCI device. Besides, we will increase the reference
+ * of the PCI device driver to prevent that being unloaded on
+ * the fly. Otherwise, kernel crash would be seen.
+ */
+static inline struct pci_driver *eeh_pcid_get(struct pci_dev *pdev)
+{
+	if (!pdev || !pdev->driver)
+		return NULL;
+
+	if (!try_module_get(pdev->driver->driver.owner))
+		return NULL;
+
+	return pdev->driver;
+}
+
+/**
+ * eeh_pcid_put - Dereference on the PCI device driver
+ * @pdev: PCI device
+ *
+ * The function is called to do dereference on the PCI device
+ * driver of the indicated PCI device.
+ */
+static inline void eeh_pcid_put(struct pci_dev *pdev)
+{
+	if (!pdev || !pdev->driver)
+		return;
+
+	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
+ *
+ * This routine must be called when reporting temporary or permanent
+ * error to the particular PCI device to disable interrupt of that
+ * device. If the device has enabled MSI or MSI-X interrupt, we needn't
+ * do real work because EEH should freeze DMA transfers for those PCI
+ * devices encountering EEH errors, which includes MSI or MSI-X.
+ */
+static void eeh_disable_irq(struct pci_dev *dev)
+{
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+
+	/* Don't disable MSI and MSI-X interrupts. They are
+	 * effectively disabled by the DMA Stopped state
+	 * when an EEH error occurs.
+	 */
+	if (dev->msi_enabled || dev->msix_enabled)
+		return;
+
+	if (!irq_has_action(dev->irq))
+		return;
+
+	edev->mode |= EEH_DEV_IRQ_DISABLED;
+	disable_irq_nosync(dev->irq);
+}
+
+/**
+ * eeh_enable_irq - Enable interrupt for the recovering device
+ * @dev: PCI device
+ *
+ * This routine must be called to enable interrupt while failed
+ * device could be resumed.
+ */
+static void eeh_enable_irq(struct pci_dev *dev)
+{
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(dev);
+
+	if ((edev->mode) & EEH_DEV_IRQ_DISABLED) {
+		edev->mode &= ~EEH_DEV_IRQ_DISABLED;
+		enable_irq(dev->irq);
+	}
+}
+
+/**
+ * eeh_report_error - Report pci error to each device driver
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * Report an EEH error to each device driver, collect up and
+ * merge the device driver responses. Cumulative response
+ * passed back in "userdata".
+ */
+static void *eeh_report_error(void *data, void *userdata)
+{
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	enum pci_ers_result rc, *res = userdata;
+	struct pci_driver *driver;
+
+	/* We might not have the associated PCI device,
+	 * then we should continue for next one.
+	 */
+	if (!dev) return NULL;
+	dev->error_state = pci_channel_io_frozen;
+
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
+
+	eeh_disable_irq(dev);
+
+	if (!driver->err_handler ||
+	    !driver->err_handler->error_detected) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
+
+	rc = driver->err_handler->error_detected(dev, pci_channel_io_frozen);
+
+	/* A driver that needs a reset trumps all others */
+	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+
+	eeh_pcid_put(dev);
+	return NULL;
+}
+
+/**
+ * eeh_report_mmio_enabled - Tell drivers that MMIO has been enabled
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * Tells each device driver that IO ports, MMIO and config space I/O
+ * are now enabled. Collects up and merges the device driver responses.
+ * Cumulative response passed back in "userdata".
+ */
+static void *eeh_report_mmio_enabled(void *data, void *userdata)
+{
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	enum pci_ers_result rc, *res = userdata;
+	struct pci_driver *driver;
+
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
+
+	if (!driver->err_handler ||
+	    !driver->err_handler->mmio_enabled) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
+
+	rc = driver->err_handler->mmio_enabled(dev);
+
+	/* A driver that needs a reset trumps all others */
+	if (rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+	if (*res == PCI_ERS_RESULT_NONE) *res = rc;
+
+	eeh_pcid_put(dev);
+	return NULL;
+}
+
+/**
+ * eeh_report_reset - Tell device that slot has been reset
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * This routine must be called while EEH tries to reset particular
+ * PCI device so that the associated PCI device driver could take
+ * some actions, usually to save data the driver needs so that the
+ * driver can work again while the device is recovered.
+ */
+static void *eeh_report_reset(void *data, void *userdata)
+{
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	enum pci_ers_result rc, *res = userdata;
+	struct pci_driver *driver;
+
+	if (!dev) return NULL;
+	dev->error_state = pci_channel_io_normal;
+
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
+
+	eeh_enable_irq(dev);
+
+	if (!driver->err_handler ||
+	    !driver->err_handler->slot_reset) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
+
+	rc = driver->err_handler->slot_reset(dev);
+	if ((*res == PCI_ERS_RESULT_NONE) ||
+	    (*res == PCI_ERS_RESULT_RECOVERED)) *res = rc;
+	if (*res == PCI_ERS_RESULT_DISCONNECT &&
+	     rc == PCI_ERS_RESULT_NEED_RESET) *res = rc;
+
+	eeh_pcid_put(dev);
+	return NULL;
+}
+
+/**
+ * eeh_report_resume - Tell device to resume normal operations
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * This routine must be called to notify the device driver that it
+ * could resume so that the device driver can do some initialization
+ * to make the recovered device work again.
+ */
+static void *eeh_report_resume(void *data, void *userdata)
+{
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	struct pci_driver *driver;
+
+	if (!dev) return NULL;
+	dev->error_state = pci_channel_io_normal;
+
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
+
+	eeh_enable_irq(dev);
+
+	if (!driver->err_handler ||
+	    !driver->err_handler->resume) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
+
+	driver->err_handler->resume(dev);
+
+	eeh_pcid_put(dev);
+	return NULL;
+}
+
+/**
+ * eeh_report_failure - Tell device driver that device is dead.
+ * @data: eeh device
+ * @userdata: return value
+ *
+ * This informs the device driver that the device is permanently
+ * dead, and that no further recovery attempts will be made on it.
+ */
+static void *eeh_report_failure(void *data, void *userdata)
+{
+	struct eeh_dev *edev = (struct eeh_dev *)data;
+	struct pci_dev *dev = eeh_dev_to_pci_dev(edev);
+	struct pci_driver *driver;
+
+	if (!dev) return NULL;
+	dev->error_state = pci_channel_io_perm_failure;
+
+	driver = eeh_pcid_get(dev);
+	if (!driver) return NULL;
+
+	eeh_disable_irq(dev);
+
+	if (!driver->err_handler ||
+	    !driver->err_handler->error_detected) {
+		eeh_pcid_put(dev);
+		return NULL;
+	}
+
+	driver->err_handler->error_detected(dev, pci_channel_io_perm_failure);
+
+	eeh_pcid_put(dev);
+	return NULL;
+}
+
+/**
+ * eeh_reset_device - Perform actual reset of a pci slot
+ * @pe: EEH PE
+ * @bus: PCI bus corresponding to the isolcated slot
+ *
+ * This routine must be called to do reset on the indicated PE.
+ * During the reset, udev might be invoked because those affected
+ * PCI devices will be removed and then added.
+ */
+static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
+{
+	struct timeval tstamp;
+	int cnt, rc;
+
+	/* pcibios will clear the counter; save the value */
+	cnt = pe->freeze_count;
+	tstamp = pe->tstamp;
+
+	/*
+	 * We don't remove the corresponding PE instances because
+	 * we need the information afterwords. The attached EEH
+	 * devices are expected to be attached soon when calling
+	 * into pcibios_add_pci_devices().
+	 */
+	if (bus)
+		__pcibios_remove_pci_devices(bus, 0);
+
+	/* Reset the pci controller. (Asserts RST#; resets config space).
+	 * Reconfigure bridges and devices. Don't try to bring the system
+	 * up if the reset failed for some reason.
+	 */
+	rc = eeh_reset_pe(pe);
+	if (rc)
+		return rc;
+
+	/* Restore PE */
+	eeh_ops->configure_bridge(pe);
+	eeh_pe_restore_bars(pe);
+
+	/* Give the system 5 seconds to finish running the user-space
+	 * hotplug shutdown scripts, e.g. ifdown for ethernet.  Yes,
+	 * this is a hack, but if we don't do this, and try to bring
+	 * the device up before the scripts have taken it down,
+	 * potentially weird things happen.
+	 */
+	if (bus) {
+		ssleep(5);
+		pcibios_add_pci_devices(bus);
+	}
+
+	pe->tstamp = tstamp;
+	pe->freeze_count = cnt;
+
+	return 0;
+}
+
+/* The longest amount of time to wait for a pci device
+ * to come back on line, in seconds.
+ */
+#define MAX_WAIT_FOR_RECOVERY 150
+
+static void eeh_handle_normal_event(struct eeh_pe *pe)
+{
+	struct pci_bus *frozen_bus;
+	int rc = 0;
+	enum pci_ers_result result = PCI_ERS_RESULT_NONE;
+
+	frozen_bus = eeh_pe_bus_get(pe);
+	if (!frozen_bus) {
+		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
+			__func__, pe->phb->global_number, pe->addr);
+		return;
+	}
+
+	eeh_pe_update_time_stamp(pe);
+	pe->freeze_count++;
+	if (pe->freeze_count > EEH_MAX_ALLOWED_FREEZES)
+		goto excess_failures;
+	pr_warning("EEH: This PCI device has failed %d times in the last hour\n",
+		pe->freeze_count);
+
+	/* Walk the various device drivers attached to this slot through
+	 * a reset sequence, giving each an opportunity to do what it needs
+	 * to accomplish the reset.  Each child gets a report of the
+	 * status ... if any child can't handle the reset, then the entire
+	 * slot is dlpar removed and added.
+	 */
+	pr_info("EEH: Notify device drivers to shutdown\n");
+	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
+
+	/* Get the current PCI slot state. This can take a long time,
+	 * sometimes over 3 seconds for certain systems.
+	 */
+	rc = eeh_ops->wait_state(pe, MAX_WAIT_FOR_RECOVERY*1000);
+	if (rc < 0 || rc == EEH_STATE_NOT_SUPPORT) {
+		pr_warning("EEH: Permanent failure\n");
+		goto hard_fail;
+	}
+
+	/* Since rtas may enable MMIO when posting the error log,
+	 * don't post the error log until after all dev drivers
+	 * have been informed.
+	 */
+	pr_info("EEH: Collect temporary log\n");
+	eeh_slot_error_detail(pe, EEH_LOG_TEMP);
+
+	/* If all device drivers were EEH-unaware, then shut
+	 * down all of the device drivers, and hope they
+	 * go down willingly, without panicing the system.
+	 */
+	if (result == PCI_ERS_RESULT_NONE) {
+		pr_info("EEH: Reset with hotplug activity\n");
+		rc = eeh_reset_device(pe, frozen_bus);
+		if (rc) {
+			pr_warning("%s: Unable to reset, err=%d\n",
+				   __func__, rc);
+			goto hard_fail;
+		}
+	}
+
+	/* If all devices reported they can proceed, then re-enable MMIO */
+	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+		pr_info("EEH: Enable I/O for affected devices\n");
+		rc = eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
+
+		if (rc < 0)
+			goto hard_fail;
+		if (rc) {
+			result = PCI_ERS_RESULT_NEED_RESET;
+		} else {
+			pr_info("EEH: Notify device drivers to resume I/O\n");
+			result = PCI_ERS_RESULT_NONE;
+			eeh_pe_dev_traverse(pe, eeh_report_mmio_enabled, &result);
+		}
+	}
+
+	/* If all devices reported they can proceed, then re-enable DMA */
+	if (result == PCI_ERS_RESULT_CAN_RECOVER) {
+		pr_info("EEH: Enabled DMA for affected devices\n");
+		rc = eeh_pci_enable(pe, EEH_OPT_THAW_DMA);
+
+		if (rc < 0)
+			goto hard_fail;
+		if (rc)
+			result = PCI_ERS_RESULT_NEED_RESET;
+		else
+			result = PCI_ERS_RESULT_RECOVERED;
+	}
+
+	/* If any device has a hard failure, then shut off everything. */
+	if (result == PCI_ERS_RESULT_DISCONNECT) {
+		pr_warning("EEH: Device driver gave up\n");
+		goto hard_fail;
+	}
+
+	/* If any device called out for a reset, then reset the slot */
+	if (result == PCI_ERS_RESULT_NEED_RESET) {
+		pr_info("EEH: Reset without hotplug activity\n");
+		rc = eeh_reset_device(pe, NULL);
+		if (rc) {
+			pr_warning("%s: Cannot reset, err=%d\n",
+				   __func__, rc);
+			goto hard_fail;
+		}
+
+		pr_info("EEH: Notify device drivers "
+			"the completion of reset\n");
+		result = PCI_ERS_RESULT_NONE;
+		eeh_pe_dev_traverse(pe, eeh_report_reset, &result);
+	}
+
+	/* All devices should claim they have recovered by now. */
+	if ((result != PCI_ERS_RESULT_RECOVERED) &&
+	    (result != PCI_ERS_RESULT_NONE)) {
+		pr_warning("EEH: Not recovered\n");
+		goto hard_fail;
+	}
+
+	/* Tell all device drivers that they can resume operations */
+	pr_info("EEH: Notify device driver to resume\n");
+	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
+
+	return;
+
+excess_failures:
+	/*
+	 * About 90% of all real-life EEH failures in the field
+	 * are due to poorly seated PCI cards. Only 10% or so are
+	 * due to actual, failed cards.
+	 */
+	pr_err("EEH: PHB#%d-PE#%x has failed %d times in the\n"
+	       "last hour and has been permanently disabled.\n"
+	       "Please try reseating or replacing it.\n",
+		pe->phb->global_number, pe->addr,
+		pe->freeze_count);
+	goto perm_error;
+
+hard_fail:
+	pr_err("EEH: Unable to recover from failure from PHB#%d-PE#%x.\n"
+	       "Please try reseating or replacing it\n",
+		pe->phb->global_number, pe->addr);
+
+perm_error:
+	eeh_slot_error_detail(pe, EEH_LOG_PERM);
+
+	/* Notify all devices that they're about to go down. */
+	eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
+
+	/* Shut down the device drivers for good. */
+	if (frozen_bus)
+		pcibios_remove_pci_devices(frozen_bus);
+}
+
+static void eeh_handle_special_event(void)
+{
+	struct eeh_pe *pe, *phb_pe;
+	struct pci_bus *bus;
+	struct pci_controller *hose, *tmp;
+	unsigned long flags;
+	int rc = 0;
+
+	/*
+	 * The return value from next_error() has been classified as follows.
+	 * It might be good to enumerate them. However, next_error() is only
+	 * supported by PowerNV platform for now. So it would be fine to use
+	 * integer directly:
+	 *
+	 * 4 - Dead IOC           3 - Dead PHB
+	 * 2 - Fenced PHB         1 - Frozen PE
+	 * 0 - No error found
+	 *
+	 */
+	rc = eeh_ops->next_error(&pe);
+	if (rc <= 0)
+		return;
+
+	switch (rc) {
+	case 4:
+		/* Mark all PHBs in dead state */
+		eeh_serialize_lock(&flags);
+		list_for_each_entry_safe(hose, tmp,
+				&hose_list, list_node) {
+			phb_pe = eeh_phb_pe_get(hose);
+			if (!phb_pe) continue;
+
+			eeh_pe_state_mark(phb_pe,
+				EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+		}
+		eeh_serialize_unlock(flags);
+
+		/* Purge all events */
+		eeh_remove_event(NULL);
+		break;
+	case 3:
+	case 2:
+	case 1:
+		/* Mark the PE in fenced state */
+		eeh_serialize_lock(&flags);
+		if (rc == 3)
+			eeh_pe_state_mark(pe,
+				EEH_PE_ISOLATED | EEH_PE_PHB_DEAD);
+		else
+			eeh_pe_state_mark(pe,
+				EEH_PE_ISOLATED | EEH_PE_RECOVERING);
+		eeh_serialize_unlock(flags);
+
+		/* Purge all events of the PHB */
+		eeh_remove_event(pe);
+		break;
+	default:
+		pr_err("%s: Invalid value %d from next_error()\n",
+		       __func__, rc);
+		return;
+	}
+
+	/*
+	 * For fenced PHB and frozen PE, it's handled as normal
+	 * event. We have to remove the affected PHBs for dead
+	 * PHB and IOC
+	 */
+	if (rc == 2 || rc == 1)
+		eeh_handle_normal_event(pe);
+	else {
+		list_for_each_entry_safe(hose, tmp,
+			&hose_list, list_node) {
+			phb_pe = eeh_phb_pe_get(hose);
+			if (!phb_pe || !(phb_pe->state & EEH_PE_PHB_DEAD))
+				continue;
+
+			bus = eeh_pe_bus_get(phb_pe);
+			/* Notify all devices that they're about to go down. */
+			eeh_pe_dev_traverse(pe, eeh_report_failure, NULL);
+			pcibios_remove_pci_devices(bus);
+		}
+	}
+}
+
+/**
+ * eeh_handle_event - Reset a PCI device after hard lockup.
+ * @pe: EEH PE
+ *
+ * While PHB detects address or data parity errors on particular PCI
+ * slot, the associated PE will be frozen. Besides, DMA's occurring
+ * to wild addresses (which usually happen due to bugs in device
+ * drivers or in PCI adapter firmware) can cause EEH error. #SERR,
+ * #PERR or other misc PCI-related errors also can trigger EEH errors.
+ *
+ * Recovery process consists of unplugging the device driver (which
+ * generated hotplug events to userspace), then issuing a PCI #RST to
+ * the device, then reconfiguring the PCI config space for all bridges
+ * & devices under this slot, and then finally restarting the device
+ * drivers (which cause a second set of hotplug events to go out to
+ * userspace).
+ */
+void eeh_handle_event(struct eeh_pe *pe)
+{
+	if (pe)
+		eeh_handle_normal_event(pe);
+	else
+		eeh_handle_special_event();
+}
diff --git a/arch/powerpc/kernel/eeh_event.c b/arch/powerpc/kernel/eeh_event.c
new file mode 100644
index 000000000000..d27c5afc90ae
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_event.c
@@ -0,0 +1,182 @@
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ *
+ * Copyright (c) 2005 Linas Vepstas <linas@linas.org>
+ */
+
+#include <linux/delay.h>
+#include <linux/list.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/kthread.h>
+#include <asm/eeh_event.h>
+#include <asm/ppc-pci.h>
+
+/** Overview:
+ *  EEH error states may be detected within exception handlers;
+ *  however, the recovery processing needs to occur asynchronously
+ *  in a normal kernel context and not an interrupt context.
+ *  This pair of routines creates an event and queues it onto a
+ *  work-queue, where a worker thread can drive recovery.
+ */
+
+static DEFINE_SPINLOCK(eeh_eventlist_lock);
+static struct semaphore eeh_eventlist_sem;
+LIST_HEAD(eeh_eventlist);
+
+/**
+ * eeh_event_handler - Dispatch EEH events.
+ * @dummy - unused
+ *
+ * The detection of a frozen slot can occur inside an interrupt,
+ * where it can be hard to do anything about it.  The goal of this
+ * routine is to pull these detection events out of the context
+ * of the interrupt handler, and re-dispatch them for processing
+ * at a later time in a normal context.
+ */
+static int eeh_event_handler(void * dummy)
+{
+	unsigned long flags;
+	struct eeh_event *event;
+	struct eeh_pe *pe;
+
+	while (!kthread_should_stop()) {
+		if (down_interruptible(&eeh_eventlist_sem))
+			break;
+
+		/* Fetch EEH event from the queue */
+		spin_lock_irqsave(&eeh_eventlist_lock, flags);
+		event = NULL;
+		if (!list_empty(&eeh_eventlist)) {
+			event = list_entry(eeh_eventlist.next,
+					   struct eeh_event, list);
+			list_del(&event->list);
+		}
+		spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+		if (!event)
+			continue;
+
+		/* We might have event without binding PE */
+		pe = event->pe;
+		if (pe) {
+			eeh_pe_state_mark(pe, EEH_PE_RECOVERING);
+			pr_info("EEH: Detected PCI bus error on PHB#%d-PE#%x\n",
+				 pe->phb->global_number, pe->addr);
+			eeh_handle_event(pe);
+			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
+		} else {
+			eeh_handle_event(NULL);
+		}
+
+		kfree(event);
+	}
+
+	return 0;
+}
+
+/**
+ * eeh_event_init - Start kernel thread to handle EEH events
+ *
+ * This routine is called to start the kernel thread for processing
+ * EEH event.
+ */
+int eeh_event_init(void)
+{
+	struct task_struct *t;
+	int ret = 0;
+
+	/* Initialize semaphore */
+	sema_init(&eeh_eventlist_sem, 0);
+
+	t = kthread_run(eeh_event_handler, NULL, "eehd");
+	if (IS_ERR(t)) {
+		ret = PTR_ERR(t);
+		pr_err("%s: Failed to start EEH daemon (%d)\n",
+			__func__, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * eeh_send_failure_event - Generate a PCI error event
+ * @pe: EEH PE
+ *
+ * This routine can be called within an interrupt context;
+ * the actual event will be delivered in a normal context
+ * (from a workqueue).
+ */
+int eeh_send_failure_event(struct eeh_pe *pe)
+{
+	unsigned long flags;
+	struct eeh_event *event;
+
+	event = kzalloc(sizeof(*event), GFP_ATOMIC);
+	if (!event) {
+		pr_err("EEH: out of memory, event not handled\n");
+		return -ENOMEM;
+	}
+	event->pe = pe;
+
+	/* We may or may not be called in an interrupt context */
+	spin_lock_irqsave(&eeh_eventlist_lock, flags);
+	list_add(&event->list, &eeh_eventlist);
+	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+
+	/* For EEH deamon to knick in */
+	up(&eeh_eventlist_sem);
+
+	return 0;
+}
+
+/**
+ * eeh_remove_event - Remove EEH event from the queue
+ * @pe: Event binding to the PE
+ *
+ * On PowerNV platform, we might have subsequent coming events
+ * is part of the former one. For that case, those subsequent
+ * coming events are totally duplicated and unnecessary, thus
+ * they should be removed.
+ */
+void eeh_remove_event(struct eeh_pe *pe)
+{
+	unsigned long flags;
+	struct eeh_event *event, *tmp;
+
+	spin_lock_irqsave(&eeh_eventlist_lock, flags);
+	list_for_each_entry_safe(event, tmp, &eeh_eventlist, list) {
+		/*
+		 * If we don't have valid PE passed in, that means
+		 * we already have event corresponding to dead IOC
+		 * and all events should be purged.
+		 */
+		if (!pe) {
+			list_del(&event->list);
+			kfree(event);
+		} else if (pe->type & EEH_PE_PHB) {
+			if (event->pe && event->pe->phb == pe->phb) {
+				list_del(&event->list);
+				kfree(event);
+			}
+		} else if (event->pe == pe) {
+			list_del(&event->list);
+			kfree(event);
+		}
+	}
+	spin_unlock_irqrestore(&eeh_eventlist_lock, flags);
+}
diff --git a/arch/powerpc/kernel/eeh_pe.c b/arch/powerpc/kernel/eeh_pe.c
new file mode 100644
index 000000000000..016588a6f5ed
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_pe.c
@@ -0,0 +1,800 @@
+/*
+ * The file intends to implement PE based on the information from
+ * platforms. Basically, there have 3 types of PEs: PHB/Bus/Device.
+ * All the PEs should be organized as hierarchy tree. The first level
+ * of the tree will be associated to existing PHBs since the particular
+ * PE is only meaningful in one PHB domain.
+ *
+ * Copyright Benjamin Herrenschmidt & Gavin Shan, IBM Corporation 2012.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/delay.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/string.h>
+
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+
+static LIST_HEAD(eeh_phb_pe);
+
+/**
+ * eeh_pe_alloc - Allocate PE
+ * @phb: PCI controller
+ * @type: PE type
+ *
+ * Allocate PE instance dynamically.
+ */
+static struct eeh_pe *eeh_pe_alloc(struct pci_controller *phb, int type)
+{
+	struct eeh_pe *pe;
+
+	/* Allocate PHB PE */
+	pe = kzalloc(sizeof(struct eeh_pe), GFP_KERNEL);
+	if (!pe) return NULL;
+
+	/* Initialize PHB PE */
+	pe->type = type;
+	pe->phb = phb;
+	INIT_LIST_HEAD(&pe->child_list);
+	INIT_LIST_HEAD(&pe->child);
+	INIT_LIST_HEAD(&pe->edevs);
+
+	return pe;
+}
+
+/**
+ * eeh_phb_pe_create - Create PHB PE
+ * @phb: PCI controller
+ *
+ * The function should be called while the PHB is detected during
+ * system boot or PCI hotplug in order to create PHB PE.
+ */
+int eeh_phb_pe_create(struct pci_controller *phb)
+{
+	struct eeh_pe *pe;
+
+	/* Allocate PHB PE */
+	pe = eeh_pe_alloc(phb, EEH_PE_PHB);
+	if (!pe) {
+		pr_err("%s: out of memory!\n", __func__);
+		return -ENOMEM;
+	}
+
+	/* Put it into the list */
+	list_add_tail(&pe->child, &eeh_phb_pe);
+
+	pr_debug("EEH: Add PE for PHB#%d\n", phb->global_number);
+
+	return 0;
+}
+
+/**
+ * eeh_phb_pe_get - Retrieve PHB PE based on the given PHB
+ * @phb: PCI controller
+ *
+ * The overall PEs form hierarchy tree. The first layer of the
+ * hierarchy tree is composed of PHB PEs. The function is used
+ * to retrieve the corresponding PHB PE according to the given PHB.
+ */
+struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb)
+{
+	struct eeh_pe *pe;
+
+	list_for_each_entry(pe, &eeh_phb_pe, child) {
+		/*
+		 * Actually, we needn't check the type since
+		 * the PE for PHB has been determined when that
+		 * was created.
+		 */
+		if ((pe->type & EEH_PE_PHB) && pe->phb == phb)
+			return pe;
+	}
+
+	return NULL;
+}
+
+/**
+ * eeh_pe_next - Retrieve the next PE in the tree
+ * @pe: current PE
+ * @root: root PE
+ *
+ * The function is used to retrieve the next PE in the
+ * hierarchy PE tree.
+ */
+static struct eeh_pe *eeh_pe_next(struct eeh_pe *pe,
+				  struct eeh_pe *root)
+{
+	struct list_head *next = pe->child_list.next;
+
+	if (next == &pe->child_list) {
+		while (1) {
+			if (pe == root)
+				return NULL;
+			next = pe->child.next;
+			if (next != &pe->parent->child_list)
+				break;
+			pe = pe->parent;
+		}
+	}
+
+	return list_entry(next, struct eeh_pe, child);
+}
+
+/**
+ * eeh_pe_traverse - Traverse PEs in the specified PHB
+ * @root: root PE
+ * @fn: callback
+ * @flag: extra parameter to callback
+ *
+ * The function is used to traverse the specified PE and its
+ * child PEs. The traversing is to be terminated once the
+ * 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)
+{
+	struct eeh_pe *pe;
+	void *ret;
+
+	for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
+		ret = fn(pe, flag);
+		if (ret) return ret;
+	}
+
+	return NULL;
+}
+
+/**
+ * eeh_pe_dev_traverse - Traverse the devices from the PE
+ * @root: EEH PE
+ * @fn: function callback
+ * @flag: extra parameter to callback
+ *
+ * The function is used to traverse the devices of the specified
+ * PE and its child PEs.
+ */
+void *eeh_pe_dev_traverse(struct eeh_pe *root,
+		eeh_traverse_func fn, void *flag)
+{
+	struct eeh_pe *pe;
+	struct eeh_dev *edev;
+	void *ret;
+
+	if (!root) {
+		pr_warning("%s: Invalid PE %p\n", __func__, root);
+		return NULL;
+	}
+
+	/* Traverse root PE */
+	for (pe = root; pe; pe = eeh_pe_next(pe, root)) {
+		eeh_pe_for_each_dev(pe, edev) {
+			ret = fn(edev, flag);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return NULL;
+}
+
+/**
+ * __eeh_pe_get - Check the PE address
+ * @data: EEH PE
+ * @flag: EEH device
+ *
+ * For one particular PE, it can be identified by PE address
+ * or tranditional BDF address. BDF address is composed of
+ * Bus/Device/Function number. The extra data referred by flag
+ * indicates which type of address should be used.
+ */
+static void *__eeh_pe_get(void *data, void *flag)
+{
+	struct eeh_pe *pe = (struct eeh_pe *)data;
+	struct eeh_dev *edev = (struct eeh_dev *)flag;
+
+	/* Unexpected PHB PE */
+	if (pe->type & EEH_PE_PHB)
+		return NULL;
+
+	/* We prefer PE address */
+	if (edev->pe_config_addr &&
+	   (edev->pe_config_addr == pe->addr))
+		return pe;
+
+	/* Try BDF address */
+	if (edev->config_addr &&
+	   (edev->config_addr == pe->config_addr))
+		return pe;
+
+	return NULL;
+}
+
+/**
+ * eeh_pe_get - Search PE based on the given address
+ * @edev: EEH device
+ *
+ * Search the corresponding PE based on the specified address which
+ * is included in the eeh device. The function is used to check if
+ * the associated PE has been created against the PE address. It's
+ * notable that the PE address has 2 format: traditional PE address
+ * which is composed of PCI bus/device/function number, or unified
+ * PE address.
+ */
+struct eeh_pe *eeh_pe_get(struct eeh_dev *edev)
+{
+	struct eeh_pe *root = eeh_phb_pe_get(edev->phb);
+	struct eeh_pe *pe;
+
+	pe = eeh_pe_traverse(root, __eeh_pe_get, edev);
+
+	return pe;
+}
+
+/**
+ * eeh_pe_get_parent - Retrieve the parent PE
+ * @edev: EEH device
+ *
+ * The whole PEs existing in the system are organized as hierarchy
+ * tree. The function is used to retrieve the parent PE according
+ * to the parent EEH device.
+ */
+static struct eeh_pe *eeh_pe_get_parent(struct eeh_dev *edev)
+{
+	struct device_node *dn;
+	struct eeh_dev *parent;
+
+	/*
+	 * 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) {
+		/* 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;
+
+		if (parent->pe)
+			return parent->pe;
+
+		dn = dn->parent;
+	}
+
+	return NULL;
+}
+
+/**
+ * eeh_add_to_parent_pe - Add EEH device to parent PE
+ * @edev: EEH device
+ *
+ * Add EEH device to the parent PE. If the parent PE already
+ * exists, the PE type will be changed to EEH_PE_BUS. Otherwise,
+ * we have to create new PE to hold the EEH device and the new
+ * PE will be linked to its parent PE as well.
+ */
+int eeh_add_to_parent_pe(struct eeh_dev *edev)
+{
+	struct eeh_pe *pe, *parent;
+
+	/*
+	 * Search the PE has been existing or not according
+	 * to the PE address. If that has been existing, the
+	 * PE should be composed of PCI bus and its subordinate
+	 * components.
+	 */
+	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);
+
+		return 0;
+	} else if (pe && (pe->type & EEH_PE_INVALID)) {
+		list_add_tail(&edev->list, &pe->edevs);
+		edev->pe = pe;
+		/*
+		 * We're running to here because of PCI hotplug caused by
+		 * EEH recovery. We need clear EEH_PE_INVALID until the top.
+		 */
+		parent = pe;
+		while (parent) {
+			if (!(parent->type & EEH_PE_INVALID))
+				break;
+			parent->type &= ~EEH_PE_INVALID;
+			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);
+
+		return 0;
+	}
+
+	/* Create a new EEH PE */
+	pe = eeh_pe_alloc(edev->phb, EEH_PE_DEVICE);
+	if (!pe) {
+		pr_err("%s: out of memory!\n", __func__);
+		return -ENOMEM;
+	}
+	pe->addr	= edev->pe_config_addr;
+	pe->config_addr	= edev->config_addr;
+
+	/*
+	 * While doing PE reset, we probably hot-reset the
+	 * upstream bridge. However, the PCI devices including
+	 * the associated EEH devices might be removed when EEH
+	 * core is doing recovery. So that won't safe to retrieve
+	 * the bridge through downstream EEH device. We have to
+	 * trace the parent PCI bus, then the upstream bridge.
+	 */
+	if (eeh_probe_mode_dev())
+		pe->bus = eeh_dev_to_pci_dev(edev)->bus;
+
+	/*
+	 * Put the new EEH PE into hierarchy tree. If the parent
+	 * can't be found, the newly created PE will be attached
+	 * to PHB directly. Otherwise, we have to associate the
+	 * PE with its parent.
+	 */
+	parent = eeh_pe_get_parent(edev);
+	if (!parent) {
+		parent = eeh_phb_pe_get(edev->phb);
+		if (!parent) {
+			pr_err("%s: No PHB PE is found (PHB Domain=%d)\n",
+				__func__, edev->phb->global_number);
+			edev->pe = NULL;
+			kfree(pe);
+			return -EEXIST;
+		}
+	}
+	pe->parent = parent;
+
+	/*
+	 * Put the newly created PE into the child list and
+	 * link the EEH device accordingly.
+	 */
+	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);
+
+	return 0;
+}
+
+/**
+ * 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)
+{
+	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);
+		return -EEXIST;
+	}
+
+	/* Remove the EEH device */
+	pe = edev->pe;
+	edev->pe = NULL;
+	list_del(&edev->list);
+
+	/*
+	 * Check if the parent PE includes any EEH devices.
+	 * If not, we should delete that. Also, we should
+	 * delete the parent PE if it doesn't have associated
+	 * child PEs and EEH devices.
+	 */
+	while (1) {
+		parent = pe->parent;
+		if (pe->type & EEH_PE_PHB)
+			break;
+
+		if (purge_pe) {
+			if (list_empty(&pe->edevs) &&
+			    list_empty(&pe->child_list)) {
+				list_del(&pe->child);
+				kfree(pe);
+			} else {
+				break;
+			}
+		} else {
+			if (list_empty(&pe->edevs)) {
+				cnt = 0;
+				list_for_each_entry(child, &pe->child_list, child) {
+					if (!(child->type & EEH_PE_INVALID)) {
+						cnt++;
+						break;
+					}
+				}
+
+				if (!cnt)
+					pe->type |= EEH_PE_INVALID;
+				else
+					break;
+			}
+		}
+
+		pe = parent;
+	}
+
+	return 0;
+}
+
+/**
+ * eeh_pe_update_time_stamp - Update PE's frozen time stamp
+ * @pe: EEH PE
+ *
+ * We have time stamp for each PE to trace its time of getting
+ * frozen in last hour. The function should be called to update
+ * the time stamp on first error of the specific PE. On the other
+ * handle, we needn't account for errors happened in last hour.
+ */
+void eeh_pe_update_time_stamp(struct eeh_pe *pe)
+{
+	struct timeval tstamp;
+
+	if (!pe) return;
+
+	if (pe->freeze_count <= 0) {
+		pe->freeze_count = 0;
+		do_gettimeofday(&pe->tstamp);
+	} else {
+		do_gettimeofday(&tstamp);
+		if (tstamp.tv_sec - pe->tstamp.tv_sec > 3600) {
+			pe->tstamp = tstamp;
+			pe->freeze_count = 0;
+		}
+	}
+}
+
+/**
+ * __eeh_pe_state_mark - Mark the state for the PE
+ * @data: EEH PE
+ * @flag: state
+ *
+ * The function is used to mark the indicated state for the given
+ * PE. Also, the associated PCI devices will be put into IO frozen
+ * state as well.
+ */
+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 pci_dev *pdev;
+
+	/*
+	 * Mark the PE with the indicated state. Also,
+	 * the associated PCI device will be put into
+	 * I/O frozen state to avoid I/O accesses from
+	 * the PCI device driver.
+	 */
+	pe->state |= state;
+	eeh_pe_for_each_dev(pe, tmp) {
+		pdev = eeh_dev_to_pci_dev(tmp);
+		if (pdev)
+			pdev->error_state = pci_channel_io_frozen;
+	}
+
+	return NULL;
+}
+
+/**
+ * eeh_pe_state_mark - Mark specified state for PE and its associated device
+ * @pe: EEH PE
+ *
+ * EEH error affects the current PE and its child PEs. The function
+ * is used to mark appropriate state for the affected PEs and the
+ * associated devices.
+ */
+void eeh_pe_state_mark(struct eeh_pe *pe, int state)
+{
+	eeh_pe_traverse(pe, __eeh_pe_state_mark, &state);
+}
+
+/**
+ * __eeh_pe_state_clear - Clear state for the PE
+ * @data: EEH PE
+ * @flag: state
+ *
+ * The function is used to clear the indicated state from the
+ * given PE. Besides, we also clear the check count of the PE
+ * as well.
+ */
+static void *__eeh_pe_state_clear(void *data, void *flag)
+{
+	struct eeh_pe *pe = (struct eeh_pe *)data;
+	int state = *((int *)flag);
+
+	pe->state &= ~state;
+	pe->check_count = 0;
+
+	return NULL;
+}
+
+/**
+ * eeh_pe_state_clear - Clear state for the PE and its children
+ * @pe: PE
+ * @state: state to be cleared
+ *
+ * When the PE and its children has been recovered from error,
+ * we need clear the error state for that. The function is used
+ * for the purpose.
+ */
+void eeh_pe_state_clear(struct eeh_pe *pe, int state)
+{
+	eeh_pe_traverse(pe, __eeh_pe_state_clear, &state);
+}
+
+/*
+ * Some PCI bridges (e.g. PLX bridges) have primary/secondary
+ * buses assigned explicitly by firmware, and we probably have
+ * lost that after reset. So we have to delay the check until
+ * the PCI-CFG registers have been restored for the parent
+ * bridge.
+ *
+ * Don't use normal PCI-CFG accessors, which probably has been
+ * 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,
+				  struct device_node *dn)
+{
+	int cap;
+	uint32_t val;
+	int timeout = 0;
+
+	/*
+	 * 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))
+		return;
+
+	pr_debug("%s: Check PCIe link for %s ...\n",
+		 __func__, pci_name(pdev));
+
+	/* Check slot status */
+	cap = pdev->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);
+		return;
+	}
+
+	/* Check power status if we have the capability */
+	eeh_ops->read_config(dn, cap + PCI_EXP_SLTCAP, 2, &val);
+	if (val & PCI_EXP_SLTCAP_PCP) {
+		eeh_ops->read_config(dn, 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);
+			msleep(2 * 1000);
+		}
+	}
+
+	/* Enable link */
+	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCTL, 2, &val);
+	val &= ~PCI_EXP_LNKCTL_LD;
+	eeh_ops->write_config(dn, cap + PCI_EXP_LNKCTL, 2, val);
+
+	/* Check link */
+	eeh_ops->read_config(dn, cap + PCI_EXP_LNKCAP, 4, &val);
+	if (!(val & PCI_EXP_LNKCAP_DLLLARC)) {
+		pr_debug("  No link reporting capability (0x%08x) \n", val);
+		msleep(1000);
+		return;
+	}
+
+	/* Wait the link is up until timeout (5s) */
+	timeout = 0;
+	while (timeout < 5000) {
+		msleep(20);
+		timeout += 20;
+
+		eeh_ops->read_config(dn, cap + PCI_EXP_LNKSTA, 2, &val);
+		if (val & PCI_EXP_LNKSTA_DLLLA)
+			break;
+	}
+
+	if (val & PCI_EXP_LNKSTA_DLLLA)
+		pr_debug("  Link up (%s)\n",
+			 (val & PCI_EXP_LNKSTA_CLS_2_5GB) ? "2.5GB" : "5GB");
+	else
+		pr_debug("  Link not ready (0x%04x)\n", val);
+}
+
+#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,
+				    struct device_node *dn)
+{
+	int i;
+
+	/*
+	 * Device BARs: 0x10 - 0x18
+	 * Bus numbers and windows: 0x18 - 0x30
+	 */
+	for (i = 4; i < 13; i++)
+		eeh_ops->write_config(dn, i*4, 4, edev->config_space[i]);
+	/* Rom: 0x38 */
+	eeh_ops->write_config(dn, 14*4, 4, edev->config_space[14]);
+
+	/* Cache line & Latency timer: 0xC 0xD */
+	eeh_ops->write_config(dn, PCI_CACHE_LINE_SIZE, 1,
+                SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+        eeh_ops->write_config(dn, 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]);
+
+	/* PCI Command: 0x4 */
+	eeh_ops->write_config(dn, PCI_COMMAND, 4, edev->config_space[1]);
+
+	/* Check the PCIe link is ready */
+	eeh_bridge_check_link(pdev, dn);
+}
+
+static void eeh_restore_device_bars(struct eeh_dev *edev,
+				    struct device_node *dn)
+{
+	int i;
+	u32 cmd;
+
+	for (i = 4; i < 10; i++)
+		eeh_ops->write_config(dn, 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(dn, PCI_CACHE_LINE_SIZE, 1,
+		SAVED_BYTE(PCI_CACHE_LINE_SIZE));
+	eeh_ops->write_config(dn, 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]);
+
+	/*
+	 * Restore PERR & SERR bits, some devices require it,
+	 * don't touch the other command bits
+	 */
+	eeh_ops->read_config(dn, PCI_COMMAND, 4, &cmd);
+	if (edev->config_space[1] & PCI_COMMAND_PARITY)
+		cmd |= PCI_COMMAND_PARITY;
+	else
+		cmd &= ~PCI_COMMAND_PARITY;
+	if (edev->config_space[1] & PCI_COMMAND_SERR)
+		cmd |= PCI_COMMAND_SERR;
+	else
+		cmd &= ~PCI_COMMAND_SERR;
+	eeh_ops->write_config(dn, PCI_COMMAND, 4, cmd);
+}
+
+/**
+ * eeh_restore_one_device_bars - Restore the Base Address Registers for one device
+ * @data: EEH device
+ * @flag: Unused
+ *
+ * Loads the PCI configuration space base address registers,
+ * the expansion ROM base address, the latency timer, and etc.
+ * from the saved values in the device node.
+ */
+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);
+	else
+		eeh_restore_device_bars(edev, dn);
+
+	return NULL;
+}
+
+/**
+ * eeh_pe_restore_bars - Restore the PCI config space info
+ * @pe: EEH PE
+ *
+ * This routine performs a recursive walk to the children
+ * of this device as well.
+ */
+void eeh_pe_restore_bars(struct eeh_pe *pe)
+{
+	/*
+	 * We needn't take the EEH lock since eeh_pe_dev_traverse()
+	 * will take that.
+	 */
+	eeh_pe_dev_traverse(pe, eeh_restore_one_device_bars, NULL);
+}
+
+/**
+ * eeh_pe_bus_get - Retrieve PCI bus according to the given PE
+ * @pe: EEH PE
+ *
+ * Retrieve the PCI bus according to the given PE. Basically,
+ * there're 3 types of PEs: PHB/Bus/Device. For PHB PE, the
+ * primary PCI bus will be retrieved. The parent bus will be
+ * returned for BUS PE. However, we don't have associated PCI
+ * bus for DEVICE PE.
+ */
+struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
+{
+	struct pci_bus *bus = NULL;
+	struct eeh_dev *edev;
+	struct pci_dev *pdev;
+
+	if (pe->type & EEH_PE_PHB) {
+		bus = pe->phb->bus;
+	} else if (pe->type & EEH_PE_BUS ||
+		   pe->type & EEH_PE_DEVICE) {
+		if (pe->bus) {
+			bus = pe->bus;
+			goto out;
+		}
+
+		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
+		pdev = eeh_dev_to_pci_dev(edev);
+		if (pdev)
+			bus = pdev->bus;
+	}
+
+out:
+	return bus;
+}
diff --git a/arch/powerpc/kernel/eeh_sysfs.c b/arch/powerpc/kernel/eeh_sysfs.c
new file mode 100644
index 000000000000..e7ae3484918c
--- /dev/null
+++ b/arch/powerpc/kernel/eeh_sysfs.c
@@ -0,0 +1,74 @@
+/*
+ * Sysfs entries for PCI Error Recovery for PAPR-compliant platform.
+ * Copyright IBM Corporation 2007
+ * Copyright Linas Vepstas <linas@austin.ibm.com> 2007
+ *
+ * All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
+ * NON INFRINGEMENT.  See the GNU General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ *
+ * Send comments and feedback to Linas Vepstas <linas@austin.ibm.com>
+ */
+#include <linux/pci.h>
+#include <linux/stat.h>
+#include <asm/ppc-pci.h>
+#include <asm/pci-bridge.h>
+
+/**
+ * EEH_SHOW_ATTR -- Create sysfs entry for eeh statistic
+ * @_name: name of file in sysfs directory
+ * @_memb: name of member in struct pci_dn to access
+ * @_format: printf format for display
+ *
+ * All of the attributes look very similar, so just
+ * auto-gen a cut-n-paste routine to display them.
+ */
+#define EEH_SHOW_ATTR(_name,_memb,_format)               \
+static ssize_t eeh_show_##_name(struct device *dev,      \
+		struct device_attribute *attr, char *buf)          \
+{                                                        \
+	struct pci_dev *pdev = to_pci_dev(dev);               \
+	struct eeh_dev *edev = pci_dev_to_eeh_dev(pdev);      \
+	                                                      \
+	if (!edev)                                            \
+		return 0;                                     \
+	                                                      \
+	return sprintf(buf, _format "\n", edev->_memb);       \
+}                                                        \
+static DEVICE_ATTR(_name, S_IRUGO, eeh_show_##_name, NULL);
+
+EEH_SHOW_ATTR(eeh_mode,            mode,            "0x%x");
+EEH_SHOW_ATTR(eeh_config_addr,     config_addr,     "0x%x");
+EEH_SHOW_ATTR(eeh_pe_config_addr,  pe_config_addr,  "0x%x");
+
+void eeh_sysfs_add_device(struct pci_dev *pdev)
+{
+	int rc=0;
+
+	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");
+}
+
+void eeh_sysfs_remove_device(struct pci_dev *pdev)
+{
+	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);
+}
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 8741c854e03d..ab15b8d057ad 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -629,21 +629,43 @@ _GLOBAL(ret_from_except_lite)
 
 	CURRENT_THREAD_INFO(r9, r1)
 	ld	r3,_MSR(r1)
+#ifdef CONFIG_PPC_BOOK3E
+	ld	r10,PACACURRENT(r13)
+#endif /* CONFIG_PPC_BOOK3E */
 	ld	r4,TI_FLAGS(r9)
 	andi.	r3,r3,MSR_PR
 	beq	resume_kernel
+#ifdef CONFIG_PPC_BOOK3E
+	lwz	r3,(THREAD+THREAD_DBCR0)(r10)
+#endif /* CONFIG_PPC_BOOK3E */
 
 	/* Check current_thread_info()->flags */
 	andi.	r0,r4,_TIF_USER_WORK_MASK
+#ifdef CONFIG_PPC_BOOK3E
+	bne	1f
+	/*
+	 * Check to see if the dbcr0 register is set up to debug.
+	 * Use the internal debug mode bit to do this.
+	 */
+	andis.	r0,r3,DBCR0_IDM@h
 	beq	restore
-
-	andi.	r0,r4,_TIF_NEED_RESCHED
-	beq	1f
+	mfmsr	r0
+	rlwinm	r0,r0,0,~MSR_DE	/* Clear MSR.DE */
+	mtmsr	r0
+	mtspr	SPRN_DBCR0,r3
+	li	r10, -1
+	mtspr	SPRN_DBSR,r10
+	b	restore
+#else
+	beq	restore
+#endif
+1:	andi.	r0,r4,_TIF_NEED_RESCHED
+	beq	2f
 	bl	.restore_interrupts
 	SCHEDULE_USER
 	b	.ret_from_except_lite
 
-1:	bl	.save_nvgprs
+2:	bl	.save_nvgprs
 	bl	.restore_interrupts
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	.do_notify_resume
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 40e4a17c8ba0..4e00d223b2e3 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -341,10 +341,17 @@ vsx_unavailable_pSeries_1:
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_pSeries
 
+facility_unavailable_trampoline:
 	. = 0xf60
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	tm_unavailable_pSeries
+	b	facility_unavailable_pSeries
+
+hv_facility_unavailable_trampoline:
+	. = 0xf80
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b	facility_unavailable_hv
 
 #ifdef CONFIG_CBE_RAS
 	STD_EXCEPTION_HV(0x1200, 0x1202, cbe_system_error)
@@ -522,8 +529,10 @@ denorm_done:
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf20)
 	STD_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf40)
-	STD_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable)
+	STD_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xf60)
+	STD_EXCEPTION_HV_OOL(0xf82, facility_unavailable)
+	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xf82)
 
 /*
  * An interrupt came in while soft-disabled. We set paca->irq_happened, then:
@@ -793,14 +802,10 @@ system_call_relon_pSeries:
 	STD_RELON_EXCEPTION_PSERIES(0x4d00, 0xd00, single_step)
 
 	. = 0x4e00
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	h_data_storage_relon_hv
+	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e20
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	h_instr_storage_relon_hv
+	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e40
 	SET_SCRATCH0(r13)
@@ -808,9 +813,7 @@ system_call_relon_pSeries:
 	b	emulation_assist_relon_hv
 
 	. = 0x4e60
-	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	hmi_exception_relon_hv
+	b	.	/* Can't happen, see v2.07 Book III-S section 6.5 */
 
 	. = 0x4e80
 	SET_SCRATCH0(r13)
@@ -835,11 +838,17 @@ vsx_unavailable_relon_pSeries_1:
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	vsx_unavailable_relon_pSeries
 
-tm_unavailable_relon_pSeries_1:
+facility_unavailable_relon_trampoline:
 	. = 0x4f60
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
-	b	tm_unavailable_relon_pSeries
+	b	facility_unavailable_relon_pSeries
+
+hv_facility_unavailable_relon_trampoline:
+	. = 0x4f80
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b	facility_unavailable_relon_hv
 
 	STD_RELON_EXCEPTION_PSERIES(0x5300, 0x1300, instruction_breakpoint)
 #ifdef CONFIG_PPC_DENORMALISATION
@@ -1165,36 +1174,21 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 	bl	.vsx_unavailable_exception
 	b	.ret_from_except
 
-	.align	7
-	.globl tm_unavailable_common
-tm_unavailable_common:
-	EXCEPTION_PROLOG_COMMON(0xf60, PACA_EXGEN)
-	bl	.save_nvgprs
-	DISABLE_INTS
-	addi	r3,r1,STACK_FRAME_OVERHEAD
-	bl	.tm_unavailable_exception
-	b	.ret_from_except
+	STD_EXCEPTION_COMMON(0xf60, facility_unavailable, .facility_unavailable_exception)
 
 	.align	7
 	.globl	__end_handlers
 __end_handlers:
 
 	/* Equivalents to the above handlers for relocation-on interrupt vectors */
-	STD_RELON_EXCEPTION_HV_OOL(0xe00, h_data_storage)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe00)
-	STD_RELON_EXCEPTION_HV_OOL(0xe20, h_instr_storage)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe20)
 	STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe40)
-	STD_RELON_EXCEPTION_HV_OOL(0xe60, hmi_exception)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe60)
 	MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
-	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0xe80)
 
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf00, performance_monitor)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf20, altivec_unavailable)
 	STD_RELON_EXCEPTION_PSERIES_OOL(0xf40, vsx_unavailable)
-	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, tm_unavailable)
+	STD_RELON_EXCEPTION_PSERIES_OOL(0xf60, facility_unavailable)
+	STD_RELON_EXCEPTION_HV_OOL(0xf80, facility_unavailable)
 
 #if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
 /*
diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index a949bdfc9623..f0b47d1a6b0e 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -176,7 +176,7 @@ int arch_validate_hwbkpt_settings(struct perf_event *bp)
 		length_max = 512 ; /* 64 doublewords */
 		/* DAWR region can't cross 512 boundary */
 		if ((bp->attr.bp_addr >> 10) != 
-		    ((bp->attr.bp_addr + bp->attr.bp_len) >> 10))
+		    ((bp->attr.bp_addr + bp->attr.bp_len - 1) >> 10))
 			return -EINVAL;
 	}
 	if (info->len >
@@ -250,6 +250,7 @@ int __kprobes hw_breakpoint_handler(struct die_args *args)
 	 * we still need to single-step the instruction, but we don't
 	 * generate an event.
 	 */
+	info->type &= ~HW_BRK_TYPE_EXTRANEOUS_IRQ;
 	if (!((bp->attr.bp_addr <= dar) &&
 	      (dar - bp->attr.bp_addr < bp->attr.bp_len)))
 		info->type |= HW_BRK_TYPE_EXTRANEOUS_IRQ;
diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index 939ea7ef0dc8..d7216c9abda1 100644
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -85,7 +85,7 @@ int powersave_nap;
 /*
  * Register the sysctl to set/clear powersave_nap.
  */
-static ctl_table powersave_nap_ctl_table[]={
+static struct ctl_table powersave_nap_ctl_table[] = {
 	{
 		.procname	= "powersave-nap",
 		.data		= &powersave_nap,
@@ -95,7 +95,7 @@ static ctl_table powersave_nap_ctl_table[]={
 	},
 	{}
 };
-static ctl_table powersave_nap_sysctl_root[] = {
+static struct ctl_table powersave_nap_sysctl_root[] = {
 	{
 		.procname	= "kernel",
 		.mode		= 0555,
diff --git a/arch/powerpc/kernel/io-workarounds.c b/arch/powerpc/kernel/io-workarounds.c
index 50e90b7e7139..fa0b54b2a362 100644
--- a/arch/powerpc/kernel/io-workarounds.c
+++ b/arch/powerpc/kernel/io-workarounds.c
@@ -55,6 +55,7 @@ static struct iowa_bus *iowa_pci_find(unsigned long vaddr, unsigned long paddr)
 
 struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 {
+	unsigned hugepage_shift;
 	struct iowa_bus *bus;
 	int token;
 
@@ -70,11 +71,17 @@ struct iowa_bus *iowa_mem_find_bus(const PCI_IO_ADDR addr)
 		if (vaddr < PHB_IO_BASE || vaddr >= PHB_IO_END)
 			return NULL;
 
-		ptep = find_linux_pte(init_mm.pgd, vaddr);
+		ptep = find_linux_pte_or_hugepte(init_mm.pgd, vaddr,
+						 &hugepage_shift);
 		if (ptep == NULL)
 			paddr = 0;
-		else
+		else {
+			/*
+			 * we don't have hugepages backing iomem
+			 */
+			WARN_ON(hugepage_shift);
 			paddr = pte_pfn(*ptep) << PAGE_SHIFT;
+		}
 		bus = iowa_pci_find(vaddr, paddr);
 
 		if (bus == NULL)
diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c
index c0d0dbddfba1..b20ff173a671 100644
--- a/arch/powerpc/kernel/iommu.c
+++ b/arch/powerpc/kernel/iommu.c
@@ -36,6 +36,8 @@
 #include <linux/hash.h>
 #include <linux/fault-inject.h>
 #include <linux/pci.h>
+#include <linux/iommu.h>
+#include <linux/sched.h>
 #include <asm/io.h>
 #include <asm/prom.h>
 #include <asm/iommu.h>
@@ -44,6 +46,7 @@
 #include <asm/kdump.h>
 #include <asm/fadump.h>
 #include <asm/vio.h>
+#include <asm/tce.h>
 
 #define DBG(...)
 
@@ -724,6 +727,13 @@ void iommu_free_table(struct iommu_table *tbl, const char *node_name)
 	if (tbl->it_offset == 0)
 		clear_bit(0, tbl->it_map);
 
+#ifdef CONFIG_IOMMU_API
+	if (tbl->it_group) {
+		iommu_group_put(tbl->it_group);
+		BUG_ON(tbl->it_group);
+	}
+#endif
+
 	/* verify that table contains no entries */
 	if (!bitmap_empty(tbl->it_map, tbl->it_size))
 		pr_warn("%s: Unexpected TCEs for %s\n", __func__, node_name);
@@ -860,3 +870,316 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size,
 		free_pages((unsigned long)vaddr, get_order(size));
 	}
 }
+
+#ifdef CONFIG_IOMMU_API
+/*
+ * SPAPR TCE API
+ */
+static void group_release(void *iommu_data)
+{
+	struct iommu_table *tbl = iommu_data;
+	tbl->it_group = NULL;
+}
+
+void iommu_register_group(struct iommu_table *tbl,
+		int pci_domain_number, unsigned long pe_num)
+{
+	struct iommu_group *grp;
+	char *name;
+
+	grp = iommu_group_alloc();
+	if (IS_ERR(grp)) {
+		pr_warn("powerpc iommu api: cannot create new group, err=%ld\n",
+				PTR_ERR(grp));
+		return;
+	}
+	tbl->it_group = grp;
+	iommu_group_set_iommudata(grp, tbl, group_release);
+	name = kasprintf(GFP_KERNEL, "domain%d-pe%lx",
+			pci_domain_number, pe_num);
+	if (!name)
+		return;
+	iommu_group_set_name(grp, name);
+	kfree(name);
+}
+
+enum dma_data_direction iommu_tce_direction(unsigned long tce)
+{
+	if ((tce & TCE_PCI_READ) && (tce & TCE_PCI_WRITE))
+		return DMA_BIDIRECTIONAL;
+	else if (tce & TCE_PCI_READ)
+		return DMA_TO_DEVICE;
+	else if (tce & TCE_PCI_WRITE)
+		return DMA_FROM_DEVICE;
+	else
+		return DMA_NONE;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_direction);
+
+void iommu_flush_tce(struct iommu_table *tbl)
+{
+	/* Flush/invalidate TLB caches if necessary */
+	if (ppc_md.tce_flush)
+		ppc_md.tce_flush(tbl);
+
+	/* Make sure updates are seen by hardware */
+	mb();
+}
+EXPORT_SYMBOL_GPL(iommu_flush_tce);
+
+int iommu_tce_clear_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce_value,
+		unsigned long npages)
+{
+	/* ppc_md.tce_free() does not support any value but 0 */
+	if (tce_value)
+		return -EINVAL;
+
+	if (ioba & ~IOMMU_PAGE_MASK)
+		return -EINVAL;
+
+	ioba >>= IOMMU_PAGE_SHIFT;
+	if (ioba < tbl->it_offset)
+		return -EINVAL;
+
+	if ((ioba + npages) > (tbl->it_offset + tbl->it_size))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_clear_param_check);
+
+int iommu_tce_put_param_check(struct iommu_table *tbl,
+		unsigned long ioba, unsigned long tce)
+{
+	if (!(tce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		return -EINVAL;
+
+	if (tce & ~(IOMMU_PAGE_MASK | TCE_PCI_WRITE | TCE_PCI_READ))
+		return -EINVAL;
+
+	if (ioba & ~IOMMU_PAGE_MASK)
+		return -EINVAL;
+
+	ioba >>= IOMMU_PAGE_SHIFT;
+	if (ioba < tbl->it_offset)
+		return -EINVAL;
+
+	if ((ioba + 1) > (tbl->it_offset + tbl->it_size))
+		return -EINVAL;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_put_param_check);
+
+unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry)
+{
+	unsigned long oldtce;
+	struct iommu_pool *pool = get_pool(tbl, entry);
+
+	spin_lock(&(pool->lock));
+
+	oldtce = ppc_md.tce_get(tbl, entry);
+	if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))
+		ppc_md.tce_free(tbl, entry, 1);
+	else
+		oldtce = 0;
+
+	spin_unlock(&(pool->lock));
+
+	return oldtce;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tce);
+
+int iommu_clear_tces_and_put_pages(struct iommu_table *tbl,
+		unsigned long entry, unsigned long pages)
+{
+	unsigned long oldtce;
+	struct page *page;
+
+	for ( ; pages; --pages, ++entry) {
+		oldtce = iommu_clear_tce(tbl, entry);
+		if (!oldtce)
+			continue;
+
+		page = pfn_to_page(oldtce >> PAGE_SHIFT);
+		WARN_ON(!page);
+		if (page) {
+			if (oldtce & TCE_PCI_WRITE)
+				SetPageDirty(page);
+			put_page(page);
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages);
+
+/*
+ * hwaddr is a kernel virtual address here (0xc... bazillion),
+ * tce_build converts it to a physical address.
+ */
+int iommu_tce_build(struct iommu_table *tbl, unsigned long entry,
+		unsigned long hwaddr, enum dma_data_direction direction)
+{
+	int ret = -EBUSY;
+	unsigned long oldtce;
+	struct iommu_pool *pool = get_pool(tbl, entry);
+
+	spin_lock(&(pool->lock));
+
+	oldtce = ppc_md.tce_get(tbl, entry);
+	/* Add new entry if it is not busy */
+	if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)))
+		ret = ppc_md.tce_build(tbl, entry, 1, hwaddr, direction, NULL);
+
+	spin_unlock(&(pool->lock));
+
+	/* if (unlikely(ret))
+		pr_err("iommu_tce: %s failed on hwaddr=%lx ioba=%lx kva=%lx ret=%d\n",
+				__func__, hwaddr, entry << IOMMU_PAGE_SHIFT,
+				hwaddr, ret); */
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_tce_build);
+
+int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry,
+		unsigned long tce)
+{
+	int ret;
+	struct page *page = NULL;
+	unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK & ~PAGE_MASK;
+	enum dma_data_direction direction = iommu_tce_direction(tce);
+
+	ret = get_user_pages_fast(tce & PAGE_MASK, 1,
+			direction != DMA_TO_DEVICE, &page);
+	if (unlikely(ret != 1)) {
+		/* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n",
+				tce, entry << IOMMU_PAGE_SHIFT, ret); */
+		return -EFAULT;
+	}
+	hwaddr = (unsigned long) page_address(page) + offset;
+
+	ret = iommu_tce_build(tbl, entry, hwaddr, direction);
+	if (ret)
+		put_page(page);
+
+	if (ret < 0)
+		pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n",
+				__func__, entry << IOMMU_PAGE_SHIFT, tce, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode);
+
+int iommu_take_ownership(struct iommu_table *tbl)
+{
+	unsigned long sz = (tbl->it_size + 7) >> 3;
+
+	if (tbl->it_offset == 0)
+		clear_bit(0, tbl->it_map);
+
+	if (!bitmap_empty(tbl->it_map, tbl->it_size)) {
+		pr_err("iommu_tce: it_map is not empty");
+		return -EBUSY;
+	}
+
+	memset(tbl->it_map, 0xff, sz);
+	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(iommu_take_ownership);
+
+void iommu_release_ownership(struct iommu_table *tbl)
+{
+	unsigned long sz = (tbl->it_size + 7) >> 3;
+
+	iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size);
+	memset(tbl->it_map, 0, sz);
+
+	/* Restore bit#0 set by iommu_init_table() */
+	if (tbl->it_offset == 0)
+		set_bit(0, tbl->it_map);
+}
+EXPORT_SYMBOL_GPL(iommu_release_ownership);
+
+static int iommu_add_device(struct device *dev)
+{
+	struct iommu_table *tbl;
+	int ret = 0;
+
+	if (WARN_ON(dev->iommu_group)) {
+		pr_warn("iommu_tce: device %s is already in iommu group %d, skipping\n",
+				dev_name(dev),
+				iommu_group_id(dev->iommu_group));
+		return -EBUSY;
+	}
+
+	tbl = get_iommu_table_base(dev);
+	if (!tbl || !tbl->it_group) {
+		pr_debug("iommu_tce: skipping device %s with no tbl\n",
+				dev_name(dev));
+		return 0;
+	}
+
+	pr_debug("iommu_tce: adding %s to iommu group %d\n",
+			dev_name(dev), iommu_group_id(tbl->it_group));
+
+	ret = iommu_group_add_device(tbl->it_group, dev);
+	if (ret < 0)
+		pr_err("iommu_tce: %s has not been added, ret=%d\n",
+				dev_name(dev), ret);
+
+	return ret;
+}
+
+static void iommu_del_device(struct device *dev)
+{
+	iommu_group_remove_device(dev);
+}
+
+static int iommu_bus_notifier(struct notifier_block *nb,
+			      unsigned long action, void *data)
+{
+	struct device *dev = data;
+
+	switch (action) {
+	case BUS_NOTIFY_ADD_DEVICE:
+		return iommu_add_device(dev);
+	case BUS_NOTIFY_DEL_DEVICE:
+		iommu_del_device(dev);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static struct notifier_block tce_iommu_bus_nb = {
+	.notifier_call = iommu_bus_notifier,
+};
+
+static int __init tce_iommu_init(void)
+{
+	struct pci_dev *pdev = NULL;
+
+	BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE);
+
+	for_each_pci_dev(pdev)
+		iommu_add_device(&pdev->dev);
+
+	bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb);
+	return 0;
+}
+
+subsys_initcall_sync(tce_iommu_init);
+
+#else
+
+void iommu_register_group(struct iommu_table *tbl,
+		int pci_domain_number, unsigned long pe_num)
+{
+}
+
+#endif /* CONFIG_IOMMU_API */
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index ea185e0b3cae..2e51cde616d2 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -116,8 +116,6 @@ static inline notrace int decrementer_check_overflow(void)
  	u64 now = get_tb_or_rtc();
  	u64 *next_tb = &__get_cpu_var(decrementers_next_tb);
  
-	if (now >= *next_tb)
-		set_dec(1);
 	return now >= *next_tb;
 }
 
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 11f5b03a0b06..2156ea90eb54 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -36,12 +36,6 @@
 #include <asm/sstep.h>
 #include <asm/uaccess.h>
 
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-#define MSR_SINGLESTEP	(MSR_DE)
-#else
-#define MSR_SINGLESTEP	(MSR_SE)
-#endif
-
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
@@ -104,19 +98,7 @@ void __kprobes arch_remove_kprobe(struct kprobe *p)
 
 static void __kprobes prepare_singlestep(struct kprobe *p, struct pt_regs *regs)
 {
-	/* We turn off async exceptions to ensure that the single step will
-	 * be for the instruction we have the kprobe on, if we dont its
-	 * possible we'd get the single step reported for an exception handler
-	 * like Decrementer or External Interrupt */
-	regs->msr &= ~MSR_EE;
-	regs->msr |= MSR_SINGLESTEP;
-#ifdef CONFIG_PPC_ADV_DEBUG_REGS
-	regs->msr &= ~MSR_CE;
-	mtspr(SPRN_DBCR0, mfspr(SPRN_DBCR0) | DBCR0_IC | DBCR0_IDM);
-#ifdef CONFIG_PPC_47x
-	isync();
-#endif
-#endif
+	enable_single_step(regs);
 
 	/*
 	 * On powerpc we should single step on the original
diff --git a/arch/powerpc/kernel/nvram_64.c b/arch/powerpc/kernel/nvram_64.c
index 48fbc2b97e95..8213ee1eb05a 100644
--- a/arch/powerpc/kernel/nvram_64.c
+++ b/arch/powerpc/kernel/nvram_64.c
@@ -84,22 +84,30 @@ static ssize_t dev_nvram_read(struct file *file, char __user *buf,
 	char *tmp = NULL;
 	ssize_t size;
 
-	ret = -ENODEV;
-	if (!ppc_md.nvram_size)
+	if (!ppc_md.nvram_size) {
+		ret = -ENODEV;
 		goto out;
+	}
 
-	ret = 0;
 	size = ppc_md.nvram_size();
-	if (*ppos >= size || size < 0)
+	if (size < 0) {
+		ret = size;
+		goto out;
+	}
+
+	if (*ppos >= size) {
+		ret = 0;
 		goto out;
+	}
 
 	count = min_t(size_t, count, size - *ppos);
 	count = min(count, PAGE_SIZE);
 
-	ret = -ENOMEM;
 	tmp = kmalloc(count, GFP_KERNEL);
-	if (!tmp)
+	if (!tmp) {
+		ret = -ENOMEM;
 		goto out;
+	}
 
 	ret = ppc_md.nvram_read(tmp, count, ppos);
 	if (ret <= 0)
diff --git a/arch/powerpc/kernel/pci-hotplug.c b/arch/powerpc/kernel/pci-hotplug.c
new file mode 100644
index 000000000000..3f608800c06b
--- /dev/null
+++ b/arch/powerpc/kernel/pci-hotplug.c
@@ -0,0 +1,111 @@
+/*
+ * Derived from "arch/powerpc/platforms/pseries/pci_dlpar.c"
+ *
+ * Copyright (C) 2003 Linda Xie <lxie@us.ibm.com>
+ * Copyright (C) 2005 International Business Machines
+ *
+ * Updates, 2005, John Rose <johnrose@austin.ibm.com>
+ * Updates, 2005, Linas Vepstas <linas@austin.ibm.com>
+ * Updates, 2013, Gavin Shan <shangw@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/pci.h>
+#include <linux/export.h>
+#include <asm/pci-bridge.h>
+#include <asm/ppc-pci.h>
+#include <asm/firmware.h>
+#include <asm/eeh.h>
+
+/**
+ * __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)
+{
+	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);
+
+	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);
+		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);
+
+/**
+ * pcibios_add_pci_devices - adds new pci devices to bus
+ * @bus: the indicated PCI bus
+ *
+ * This routine will find and fixup new pci devices under
+ * the indicated bus. This routine presumes that there
+ * might already be some devices under this bridge, so
+ * it carefully tries to add only new devices.  (And that
+ * is how this routine differs from other, similar pcibios
+ * routines.)
+ */
+void pcibios_add_pci_devices(struct pci_bus * bus)
+{
+	int slotno, num, mode, pass, max;
+	struct pci_dev *dev;
+	struct device_node *dn = pci_bus_to_OF_node(bus);
+
+	eeh_add_device_tree_early(dn);
+
+	mode = PCI_PROBE_NORMAL;
+	if (ppc_md.pci_probe_mode)
+		mode = ppc_md.pci_probe_mode(bus);
+
+	if (mode == PCI_PROBE_DEVTREE) {
+		/* use ofdt-based probe */
+		of_rescan_bus(dn, bus);
+	} else if (mode == PCI_PROBE_NORMAL) {
+		/* use legacy probe */
+		slotno = PCI_SLOT(PCI_DN(dn->child)->devfn);
+		num = pci_scan_slot(bus, PCI_DEVFN(slotno, 0));
+		if (!num)
+			return;
+		pcibios_setup_bus_devices(bus);
+		max = bus->busn_res.start;
+		for (pass = 0; pass < 2; pass++) {
+			list_for_each_entry(dev, &bus->devices, bus_list) {
+				if (dev->hdr_type == PCI_HEADER_TYPE_BRIDGE ||
+				    dev->hdr_type == PCI_HEADER_TYPE_CARDBUS)
+					max = pci_scan_bridge(bus, dev,
+							      max, pass);
+			}
+		}
+	}
+	pcibios_finish_adding_to_bus(bus);
+}
+EXPORT_SYMBOL_GPL(pcibios_add_pci_devices);
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index 076d1242507a..c517dbe705fd 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -916,7 +916,11 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
 	flush_altivec_to_thread(src);
 	flush_vsx_to_thread(src);
 	flush_spe_to_thread(src);
+
 	*dst = *src;
+
+	clear_task_ebb(dst);
+
 	return 0;
 }
 
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index 8b6f7a99cce2..eb23ac92abb9 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -559,6 +559,35 @@ void __init early_init_dt_setup_initrd_arch(unsigned long start,
 }
 #endif
 
+static void __init early_reserve_mem_dt(void)
+{
+	unsigned long i, len, dt_root;
+	const __be32 *prop;
+
+	dt_root = of_get_flat_dt_root();
+
+	prop = of_get_flat_dt_prop(dt_root, "reserved-ranges", &len);
+
+	if (!prop)
+		return;
+
+	DBG("Found new-style reserved-ranges\n");
+
+	/* Each reserved range is an (address,size) pair, 2 cells each,
+	 * totalling 4 cells per range. */
+	for (i = 0; i < len / (sizeof(*prop) * 4); i++) {
+		u64 base, size;
+
+		base = of_read_number(prop + (i * 4) + 0, 2);
+		size = of_read_number(prop + (i * 4) + 2, 2);
+
+		if (size) {
+			DBG("reserving: %llx -> %llx\n", base, size);
+			memblock_reserve(base, size);
+		}
+	}
+}
+
 static void __init early_reserve_mem(void)
 {
 	u64 base, size;
@@ -574,12 +603,16 @@ static void __init early_reserve_mem(void)
 	self_size = initial_boot_params->totalsize;
 	memblock_reserve(self_base, self_size);
 
+	/* Look for the new "reserved-regions" property in the DT */
+	early_reserve_mem_dt();
+
 #ifdef CONFIG_BLK_DEV_INITRD
-	/* then reserve the initrd, if any */
-	if (initrd_start && (initrd_end > initrd_start))
+	/* Then reserve the initrd, if any */
+	if (initrd_start && (initrd_end > initrd_start)) {
 		memblock_reserve(_ALIGN_DOWN(__pa(initrd_start), PAGE_SIZE),
 			_ALIGN_UP(initrd_end, PAGE_SIZE) -
 			_ALIGN_DOWN(initrd_start, PAGE_SIZE));
+	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 
 #ifdef CONFIG_PPC32
@@ -591,6 +624,8 @@ static void __init early_reserve_mem(void)
 		u32 base_32, size_32;
 		u32 *reserve_map_32 = (u32 *)reserve_map;
 
+		DBG("Found old 32-bit reserve map\n");
+
 		while (1) {
 			base_32 = *(reserve_map_32++);
 			size_32 = *(reserve_map_32++);
@@ -605,6 +640,9 @@ static void __init early_reserve_mem(void)
 		return;
 	}
 #endif
+	DBG("Processing reserve map\n");
+
+	/* Handle the reserve map in the fdt blob if it exists */
 	while (1) {
 		base = *(reserve_map++);
 		size = *(reserve_map++);
diff --git a/arch/powerpc/kernel/ptrace.c b/arch/powerpc/kernel/ptrace.c
index 98c2fc198712..64f7bd5b1b0f 100644
--- a/arch/powerpc/kernel/ptrace.c
+++ b/arch/powerpc/kernel/ptrace.c
@@ -1449,7 +1449,9 @@ static long ppc_set_hwdebug(struct task_struct *child,
 	 */
 	if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_RANGE_INCLUSIVE) {
 		len = bp_info->addr2 - bp_info->addr;
-	} else if (bp_info->addr_mode != PPC_BREAKPOINT_MODE_EXACT) {
+	} else if (bp_info->addr_mode == PPC_BREAKPOINT_MODE_EXACT)
+		len = 1;
+	else {
 		ptrace_put_breakpoints(child);
 		return -EINVAL;
 	}
diff --git a/arch/powerpc/kernel/reloc_32.S b/arch/powerpc/kernel/reloc_32.S
index ef46ba6e094f..f366fedb0872 100644
--- a/arch/powerpc/kernel/reloc_32.S
+++ b/arch/powerpc/kernel/reloc_32.S
@@ -166,7 +166,7 @@ ha16:
 	/* R_PPC_ADDR16_LO */
 lo16:
 	cmpwi	r4, R_PPC_ADDR16_LO
-	bne	nxtrela
+	bne	unknown_type
 	lwz	r4, 0(r9)	/* r_offset */
 	lwz	r0, 8(r9)	/* r_addend */
 	add	r0, r0, r3
@@ -191,6 +191,7 @@ nxtrela:
 	dcbst	r4,r7
 	sync			/* Ensure the data is flushed before icbi */
 	icbi	r4,r7
+unknown_type:
 	cmpwi	r8, 0		/* relasz = 0 ? */
 	ble	done
 	add	r9, r9, r6	/* move to next entry in the .rela table */
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 52add6f3e201..80b5ef403f68 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -1172,7 +1172,7 @@ int __init early_init_dt_scan_rtas(unsigned long node,
 static arch_spinlock_t timebase_lock;
 static u64 timebase = 0;
 
-void __cpuinit rtas_give_timebase(void)
+void rtas_give_timebase(void)
 {
 	unsigned long flags;
 
@@ -1189,7 +1189,7 @@ void __cpuinit rtas_give_timebase(void)
 	local_irq_restore(flags);
 }
 
-void __cpuinit rtas_take_timebase(void)
+void rtas_take_timebase(void)
 {
 	while (!timebase)
 		barrier();
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index e379d3fd1694..389fb8077cc9 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -76,7 +76,7 @@
 #endif
 
 int boot_cpuid = 0;
-int __initdata spinning_secondaries;
+int spinning_secondaries;
 u64 ppc64_pft_size;
 
 /* Pick defaults since we might want to patch instructions
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 201385c3a1ae..0f83122e6676 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -407,7 +407,8 @@ inline unsigned long copy_transact_fpr_from_user(struct task_struct *task,
  * altivec/spe instructions at some point.
  */
 static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
-		int sigret, int ctx_has_vsx_region)
+			  struct mcontext __user *tm_frame, int sigret,
+			  int ctx_has_vsx_region)
 {
 	unsigned long msr = regs->msr;
 
@@ -475,6 +476,12 @@ static int save_user_regs(struct pt_regs *regs, struct mcontext __user *frame,
 
 	if (__put_user(msr, &frame->mc_gregs[PT_MSR]))
 		return 1;
+	/* We need to write 0 the MSR top 32 bits in the tm frame so that we
+	 * can check it on the restore to see if TM is active
+	 */
+	if (tm_frame && __put_user(0, &tm_frame->mc_gregs[PT_MSR]))
+		return 1;
+
 	if (sigret) {
 		/* Set up the sigreturn trampoline: li r0,sigret; sc */
 		if (__put_user(0x38000000UL + sigret, &frame->tramp[0])
@@ -747,7 +754,7 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 				 struct mcontext __user *tm_sr)
 {
 	long err;
-	unsigned long msr;
+	unsigned long msr, msr_hi;
 #ifdef CONFIG_VSX
 	int i;
 #endif
@@ -852,8 +859,11 @@ static long restore_tm_user_regs(struct pt_regs *regs,
 	tm_enable();
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
-	/* The task has moved into TM state S, so ensure MSR reflects this */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | MSR_TS_S;
+	/* Get the top half of the MSR */
+	if (__get_user(msr_hi, &tm_sr->mc_gregs[PT_MSR]))
+		return 1;
+	/* Pull in MSR TM from user context */
+	regs->msr = (regs->msr & ~MSR_TS_MASK) | ((msr_hi<<32) & MSR_TS_MASK);
 
 	/* This loads the speculative FP/VEC state, if used */
 	if (msr & MSR_FP) {
@@ -952,6 +962,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 {
 	struct rt_sigframe __user *rt_sf;
 	struct mcontext __user *frame;
+	struct mcontext __user *tm_frame = NULL;
 	void __user *addr;
 	unsigned long newsp = 0;
 	int sigret;
@@ -985,23 +996,24 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 	}
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	tm_frame = &rt_sf->uc_transact.uc_mcontext;
 	if (MSR_TM_ACTIVE(regs->msr)) {
-		if (save_tm_user_regs(regs, &rt_sf->uc.uc_mcontext,
-				      &rt_sf->uc_transact.uc_mcontext, sigret))
+		if (save_tm_user_regs(regs, frame, tm_frame, sigret))
 			goto badframe;
 	}
 	else
 #endif
-		if (save_user_regs(regs, frame, sigret, 1))
+	{
+		if (save_user_regs(regs, frame, tm_frame, sigret, 1))
 			goto badframe;
+	}
 	regs->link = tramp;
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (MSR_TM_ACTIVE(regs->msr)) {
 		if (__put_user((unsigned long)&rt_sf->uc_transact,
 			       &rt_sf->uc.uc_link)
-		    || __put_user(to_user_ptr(&rt_sf->uc_transact.uc_mcontext),
-				  &rt_sf->uc_transact.uc_regs))
+		    || __put_user((unsigned long)tm_frame, &rt_sf->uc_transact.uc_regs))
 			goto badframe;
 	}
 	else
@@ -1170,7 +1182,7 @@ long sys_swapcontext(struct ucontext __user *old_ctx,
 		mctx = (struct mcontext __user *)
 			((unsigned long) &old_ctx->uc_mcontext & ~0xfUL);
 		if (!access_ok(VERIFY_WRITE, old_ctx, ctx_size)
-		    || save_user_regs(regs, mctx, 0, ctx_has_vsx_region)
+		    || save_user_regs(regs, mctx, NULL, 0, ctx_has_vsx_region)
 		    || put_sigset_t(&old_ctx->uc_sigmask, &current->blocked)
 		    || __put_user(to_user_ptr(mctx), &old_ctx->uc_regs))
 			return -EFAULT;
@@ -1233,7 +1245,7 @@ long sys_rt_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 		if (__get_user(msr_hi, &mcp->mc_gregs[PT_MSR]))
 			goto bad;
 
-		if (MSR_TM_SUSPENDED(msr_hi<<32)) {
+		if (MSR_TM_ACTIVE(msr_hi<<32)) {
 			/* We only recheckpoint on return if we're
 			 * transaction.
 			 */
@@ -1392,6 +1404,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 {
 	struct sigcontext __user *sc;
 	struct sigframe __user *frame;
+	struct mcontext __user *tm_mctx = NULL;
 	unsigned long newsp = 0;
 	int sigret;
 	unsigned long tramp;
@@ -1425,6 +1438,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	}
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	tm_mctx = &frame->mctx_transact;
 	if (MSR_TM_ACTIVE(regs->msr)) {
 		if (save_tm_user_regs(regs, &frame->mctx, &frame->mctx_transact,
 				      sigret))
@@ -1432,8 +1446,10 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	}
 	else
 #endif
-		if (save_user_regs(regs, &frame->mctx, sigret, 1))
+	{
+		if (save_user_regs(regs, &frame->mctx, tm_mctx, sigret, 1))
 			goto badframe;
+	}
 
 	regs->link = tramp;
 
@@ -1481,16 +1497,22 @@ badframe:
 long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 		       struct pt_regs *regs)
 {
+	struct sigframe __user *sf;
 	struct sigcontext __user *sc;
 	struct sigcontext sigctx;
 	struct mcontext __user *sr;
 	void __user *addr;
 	sigset_t set;
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	struct mcontext __user *mcp, *tm_mcp;
+	unsigned long msr_hi;
+#endif
 
 	/* Always make any pending restarted system calls return -EINTR */
 	current_thread_info()->restart_block.fn = do_no_restart_syscall;
 
-	sc = (struct sigcontext __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+	sf = (struct sigframe __user *)(regs->gpr[1] + __SIGNAL_FRAMESIZE);
+	sc = &sf->sctx;
 	addr = sc;
 	if (copy_from_user(&sigctx, sc, sizeof(sigctx)))
 		goto badframe;
@@ -1507,11 +1529,25 @@ long sys_sigreturn(int r3, int r4, int r5, int r6, int r7, int r8,
 #endif
 	set_current_blocked(&set);
 
-	sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
-	addr = sr;
-	if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
-	    || restore_user_regs(regs, sr, 1))
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	mcp = (struct mcontext __user *)&sf->mctx;
+	tm_mcp = (struct mcontext __user *)&sf->mctx_transact;
+	if (__get_user(msr_hi, &tm_mcp->mc_gregs[PT_MSR]))
 		goto badframe;
+	if (MSR_TM_ACTIVE(msr_hi<<32)) {
+		if (!cpu_has_feature(CPU_FTR_TM))
+			goto badframe;
+		if (restore_tm_user_regs(regs, mcp, tm_mcp))
+			goto badframe;
+	} else
+#endif
+	{
+		sr = (struct mcontext __user *)from_user_ptr(sigctx.regs);
+		addr = sr;
+		if (!access_ok(VERIFY_READ, sr, sizeof(*sr))
+		    || restore_user_regs(regs, sr, 1))
+			goto badframe;
+	}
 
 	set_thread_flag(TIF_RESTOREALL);
 	return 0;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index 345947367ec0..887e99d85bc2 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -410,6 +410,10 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 
 	/* get MSR separately, transfer the LE bit if doing signal return */
 	err |= __get_user(msr, &sc->gp_regs[PT_MSR]);
+	/* pull in MSR TM from user context */
+	regs->msr = (regs->msr & ~MSR_TS_MASK) | (msr & MSR_TS_MASK);
+
+	/* pull in MSR LE from user context */
 	regs->msr = (regs->msr & ~MSR_LE) | (msr & MSR_LE);
 
 	/* The following non-GPR non-FPR non-VR state is also checkpointed: */
@@ -505,8 +509,6 @@ static long restore_tm_sigcontexts(struct pt_regs *regs,
 	tm_enable();
 	/* This loads the checkpointed FP/VEC state, if used */
 	tm_recheckpoint(&current->thread, msr);
-	/* The task has moved into TM state S, so ensure MSR reflects this: */
-	regs->msr = (regs->msr & ~MSR_TS_MASK) | __MASK(33);
 
 	/* This loads the speculative FP/VEC state, if used */
 	if (msr & MSR_FP) {
@@ -654,7 +656,7 @@ int sys_rt_sigreturn(unsigned long r3, unsigned long r4, unsigned long r5,
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	if (__get_user(msr, &uc->uc_mcontext.gp_regs[PT_MSR]))
 		goto badframe;
-	if (MSR_TM_SUSPENDED(msr)) {
+	if (MSR_TM_ACTIVE(msr)) {
 		/* We recheckpoint on return. */
 		struct ucontext __user *uc_transact;
 		if (__get_user(uc_transact, &uc->uc_link))
diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index ee7ac5e6e28a..38b0ba65a735 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -480,7 +480,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
 	secondary_ti = current_set[cpu] = ti;
 }
 
-int __cpuinit __cpu_up(unsigned int cpu, struct task_struct *tidle)
+int __cpu_up(unsigned int cpu, struct task_struct *tidle)
 {
 	int rc, c;
 
@@ -610,7 +610,7 @@ static struct device_node *cpu_to_l2cache(int cpu)
 }
 
 /* Activate a secondary processor. */
-__cpuinit void start_secondary(void *unused)
+void start_secondary(void *unused)
 {
 	unsigned int cpu = smp_processor_id();
 	struct device_node *l2_cache;
@@ -637,12 +637,10 @@ __cpuinit void start_secondary(void *unused)
 
 	vdso_getcpu_init();
 #endif
-	notify_cpu_starting(cpu);
-	set_cpu_online(cpu, true);
 	/* Update sibling maps */
 	base = cpu_first_thread_sibling(cpu);
 	for (i = 0; i < threads_per_core; i++) {
-		if (cpu_is_offline(base + i))
+		if (cpu_is_offline(base + i) && (cpu != base + i))
 			continue;
 		cpumask_set_cpu(cpu, cpu_sibling_mask(base + i));
 		cpumask_set_cpu(base + i, cpu_sibling_mask(cpu));
@@ -667,6 +665,10 @@ __cpuinit void start_secondary(void *unused)
 	}
 	of_node_put(l2_cache);
 
+	smp_wmb();
+	notify_cpu_starting(cpu);
+	set_cpu_online(cpu, true);
+
 	local_irq_enable();
 
 	cpu_startup_entry(CPUHP_ONLINE);
diff --git a/arch/powerpc/kernel/sysfs.c b/arch/powerpc/kernel/sysfs.c
index e68a84568b8b..27a90b99ef67 100644
--- a/arch/powerpc/kernel/sysfs.c
+++ b/arch/powerpc/kernel/sysfs.c
@@ -341,7 +341,7 @@ static struct device_attribute pa6t_attrs[] = {
 #endif /* HAS_PPC_PMC_PA6T */
 #endif /* HAS_PPC_PMC_CLASSIC */
 
-static void __cpuinit register_cpu_online(unsigned int cpu)
+static void register_cpu_online(unsigned int cpu)
 {
 	struct cpu *c = &per_cpu(cpu_devices, cpu);
 	struct device *s = &c->dev;
@@ -502,7 +502,7 @@ ssize_t arch_cpu_release(const char *buf, size_t count)
 
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int __cpuinit sysfs_cpu_notify(struct notifier_block *self,
+static int sysfs_cpu_notify(struct notifier_block *self,
 				      unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (unsigned int)(long)hcpu;
@@ -522,7 +522,7 @@ static int __cpuinit sysfs_cpu_notify(struct notifier_block *self,
 	return NOTIFY_OK;
 }
 
-static struct notifier_block __cpuinitdata sysfs_cpu_nb = {
+static struct notifier_block sysfs_cpu_nb = {
 	.notifier_call	= sysfs_cpu_notify,
 };
 
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index 5fc29ad7e26f..65ab9e909377 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -631,7 +631,6 @@ static int __init get_freq(char *name, int cells, unsigned long *val)
 	return found;
 }
 
-/* should become __cpuinit when secondary_cpu_time_init also is */
 void start_cpu_decrementer(void)
 {
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
diff --git a/arch/powerpc/kernel/tm.S b/arch/powerpc/kernel/tm.S
index 2da67e7a16d5..51be8fb24803 100644
--- a/arch/powerpc/kernel/tm.S
+++ b/arch/powerpc/kernel/tm.S
@@ -112,9 +112,18 @@ _GLOBAL(tm_reclaim)
 	std	r3, STACK_PARAM(0)(r1)
 	SAVE_NVGPRS(r1)
 
+	/* We need to setup MSR for VSX register save instructions.  Here we
+	 * also clear the MSR RI since when we do the treclaim, we won't have a
+	 * valid kernel pointer for a while.  We clear RI here as it avoids
+	 * adding another mtmsr closer to the treclaim.  This makes the region
+	 * maked as non-recoverable wider than it needs to be but it saves on
+	 * inserting another mtmsrd later.
+	 */
 	mfmsr	r14
 	mr	r15, r14
 	ori	r15, r15, MSR_FP
+	li	r16, MSR_RI
+	andc	r15, r15, r16
 	oris	r15, r15, MSR_VEC@h
 #ifdef CONFIG_VSX
 	BEGIN_FTR_SECTION
@@ -349,9 +358,10 @@ restore_gprs:
 	mtcr	r5
 	mtxer	r6
 
-	/* MSR and flags:  We don't change CRs, and we don't need to alter
-	 * MSR.
+	/* Clear the MSR RI since we are about to change R1.  EE is already off
 	 */
+	li	r4, 0
+	mtmsrd	r4, 1
 
 	REST_4GPRS(0, r7)			/* GPR0-3 */
 	REST_GPR(4, r7)				/* GPR4-6 */
@@ -377,6 +387,10 @@ restore_gprs:
 	GET_PACA(r13)
 	GET_SCRATCH0(r1)
 
+	/* R1 is restored, so we are recoverable again.  EE is still off */
+	li	r4, MSR_RI
+	mtmsrd	r4, 1
+
 	REST_NVGPRS(r1)
 
 	addi    r1, r1, TM_FRAME_SIZE
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index c0e5caf8ccc7..bf33c22e38a4 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -866,6 +866,10 @@ static int emulate_string_inst(struct pt_regs *regs, u32 instword)
 		u8 val;
 		u32 shift = 8 * (3 - (pos & 0x3));
 
+		/* if process is 32-bit, clear upper 32 bits of EA */
+		if ((regs->msr & MSR_64BIT) == 0)
+			EA &= 0xFFFFFFFF;
+
 		switch ((instword & PPC_INST_STRING_MASK)) {
 			case PPC_INST_LSWX:
 			case PPC_INST_LSWI:
@@ -1125,7 +1129,17 @@ void __kprobes program_check_exception(struct pt_regs *regs)
 	 * ESR_DST (!?) or 0.  In the process of chasing this with the
 	 * hardware people - not sure if it can happen on any illegal
 	 * instruction or only on FP instructions, whether there is a
-	 * pattern to occurrences etc. -dgibson 31/Mar/2003 */
+	 * pattern to occurrences etc. -dgibson 31/Mar/2003
+	 */
+
+	/*
+	 * If we support a HW FPU, we need to ensure the FP state
+	 * if flushed into the thread_struct before attempting
+	 * emulation
+	 */
+#ifdef CONFIG_PPC_FPU
+	flush_fp_to_thread(current);
+#endif
 	switch (do_mathemu(regs)) {
 	case 0:
 		emulate_single_step(regs);
@@ -1282,25 +1296,50 @@ void vsx_unavailable_exception(struct pt_regs *regs)
 	die("Unrecoverable VSX Unavailable Exception", regs, SIGABRT);
 }
 
-void tm_unavailable_exception(struct pt_regs *regs)
+void facility_unavailable_exception(struct pt_regs *regs)
 {
+	static char *facility_strings[] = {
+		"FPU",
+		"VMX/VSX",
+		"DSCR",
+		"PMU SPRs",
+		"BHRB",
+		"TM",
+		"AT",
+		"EBB",
+		"TAR",
+	};
+	char *facility, *prefix;
+	u64 value;
+
+	if (regs->trap == 0xf60) {
+		value = mfspr(SPRN_FSCR);
+		prefix = "";
+	} else {
+		value = mfspr(SPRN_HFSCR);
+		prefix = "Hypervisor ";
+	}
+
+	value = value >> 56;
+
 	/* We restore the interrupt state now */
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
-	/* Currently we never expect a TMU exception.  Catch
-	 * this and kill the process!
-	 */
-	printk(KERN_EMERG "Unexpected TM unavailable exception at %lx "
-	       "(msr %lx)\n",
-	       regs->nip, regs->msr);
+	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);
 
 	if (user_mode(regs)) {
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 		return;
 	}
 
-	die("Unexpected TM unavailable exception", regs, SIGABRT);
+	die("Unexpected facility unavailable exception", regs, SIGABRT);
 }
 
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
@@ -1396,8 +1435,7 @@ void performance_monitor_exception(struct pt_regs *regs)
 void SoftwareEmulation(struct pt_regs *regs)
 {
 	extern int do_mathemu(struct pt_regs *);
-	extern int Soft_emulate_8xx(struct pt_regs *);
-#if defined(CONFIG_MATH_EMULATION) || defined(CONFIG_8XX_MINIMAL_FPEMU)
+#if defined(CONFIG_MATH_EMULATION)
 	int errcode;
 #endif
 
@@ -1430,23 +1468,6 @@ void SoftwareEmulation(struct pt_regs *regs)
 		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 		return;
 	}
-
-#elif defined(CONFIG_8XX_MINIMAL_FPEMU)
-	errcode = Soft_emulate_8xx(regs);
-	if (errcode >= 0)
-		PPC_WARN_EMULATED(8xx, regs);
-
-	switch (errcode) {
-	case 0:
-		emulate_single_step(regs);
-		return;
-	case 1:
-		_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
-		return;
-	case -EFAULT:
-		_exception(SIGSEGV, regs, SEGV_MAPERR, regs->nip);
-		return;
-	}
 #else
 	_exception(SIGILL, regs, ILL_ILLOPC, regs->nip);
 #endif
@@ -1796,8 +1817,6 @@ struct ppc_emulated ppc_emulated = {
 	WARN_EMULATED_SETUP(unaligned),
 #ifdef CONFIG_MATH_EMULATION
 	WARN_EMULATED_SETUP(math),
-#elif defined(CONFIG_8XX_MINIMAL_FPEMU)
-	WARN_EMULATED_SETUP(8xx),
 #endif
 #ifdef CONFIG_VSX
 	WARN_EMULATED_SETUP(vsx),
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 9d3fdcd66290..a15837519dca 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -50,7 +50,7 @@ void __init udbg_early_init(void)
 	udbg_init_debug_beat();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_PAS_REALMODE)
 	udbg_init_pas_realmode();
-#elif defined(CONFIG_BOOTX_TEXT)
+#elif defined(CONFIG_PPC_EARLY_DEBUG_BOOTX)
 	udbg_init_btext();
 #elif defined(CONFIG_PPC_EARLY_DEBUG_44x)
 	/* PPC44x debug */
diff --git a/arch/powerpc/kernel/vdso.c b/arch/powerpc/kernel/vdso.c
index d4f463ac65b1..1d9c92621b36 100644
--- a/arch/powerpc/kernel/vdso.c
+++ b/arch/powerpc/kernel/vdso.c
@@ -711,7 +711,7 @@ static void __init vdso_setup_syscall_map(void)
 }
 
 #ifdef CONFIG_PPC64
-int __cpuinit vdso_getcpu_init(void)
+int vdso_getcpu_init(void)
 {
 	unsigned long cpu, node, val;