Merge tag 'v3.11-rc7' into devicetree/next

Linux 3.11-rc7

46 files changed, 636 insertions, 295 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 3bf72cd2c8f..dbd9d3c991e 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -566,7 +566,7 @@ config SCHED_SMT
 config PPC_DENORMALISATION
 	bool "PowerPC denormalisation exception handling"
 	depends on PPC_BOOK3S_64
-	default "n"
+	default "y" if PPC_POWERNV
 	---help---
 	  Add support for handling denormalisation of single precision
 	  values.  Useful for bare metal only.  If unsure say Y here.
diff --git a/arch/powerpc/configs/ppc64_defconfig b/arch/powerpc/configs/ppc64_defconfig
index c86fcb92358..0e8cfd09da2 100644
--- a/arch/powerpc/configs/ppc64_defconfig
+++ b/arch/powerpc/configs/ppc64_defconfig
@@ -58,7 +58,7 @@ CONFIG_SCHED_SMT=y
 CONFIG_PPC_DENORMALISATION=y
 CONFIG_PCCARD=y
 CONFIG_ELECTRA_CF=y
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_RPA=m
 CONFIG_HOTPLUG_PCI_RPA_DLPAR=m
 CONFIG_PACKET=y
diff --git a/arch/powerpc/configs/ppc64e_defconfig b/arch/powerpc/configs/ppc64e_defconfig
index 4b20f76172e..0085dc4642c 100644
--- a/arch/powerpc/configs/ppc64e_defconfig
+++ b/arch/powerpc/configs/ppc64e_defconfig
@@ -32,7 +32,7 @@ CONFIG_IRQ_ALL_CPUS=y
 CONFIG_SPARSEMEM_MANUAL=y
 CONFIG_PCI_MSI=y
 CONFIG_PCCARD=y
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
 CONFIG_XFRM_USER=m
diff --git a/arch/powerpc/configs/pseries_defconfig b/arch/powerpc/configs/pseries_defconfig
index bea8587c3af..1d4b9763895 100644
--- a/arch/powerpc/configs/pseries_defconfig
+++ b/arch/powerpc/configs/pseries_defconfig
@@ -53,7 +53,7 @@ CONFIG_PPC_64K_PAGES=y
 CONFIG_PPC_SUBPAGE_PROT=y
 CONFIG_SCHED_SMT=y
 CONFIG_PPC_DENORMALISATION=y
-CONFIG_HOTPLUG_PCI=m
+CONFIG_HOTPLUG_PCI=y
 CONFIG_HOTPLUG_PCI_RPA=m
 CONFIG_HOTPLUG_PCI_RPA_DLPAR=m
 CONFIG_PACKET=y
diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index 09a8743143f..d3e5e9bc8f9 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -55,6 +55,8 @@ struct device_node;
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
 #define EEH_PE_PHB_DEAD		(1 << 2)	/* Dead PHB		*/
 
+#define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
+
 struct eeh_pe {
 	int type;			/* PE type: PHB/Bus/Device	*/
 	int state;			/* PE EEH dependent mode	*/
@@ -72,8 +74,8 @@ struct eeh_pe {
 	struct list_head child;		/* Child PEs			*/
 };
 
-#define eeh_pe_for_each_dev(pe, edev) \
-		list_for_each_entry(edev, &pe->edevs, list)
+#define eeh_pe_for_each_dev(pe, edev, tmp) \
+		list_for_each_entry_safe(edev, tmp, &pe->edevs, list)
 
 /*
  * The struct is used to trace EEH state for the associated
@@ -82,7 +84,13 @@ struct eeh_pe {
  * another tree except the currently existing tree of PCI
  * buses and PCI devices
  */
-#define EEH_DEV_IRQ_DISABLED	(1<<0)	/* Interrupt disabled		*/
+#define EEH_DEV_BRIDGE		(1 << 0)	/* PCI bridge		*/
+#define EEH_DEV_ROOT_PORT	(1 << 1)	/* PCIe root port	*/
+#define EEH_DEV_DS_PORT		(1 << 2)	/* Downstream port	*/
+#define EEH_DEV_IRQ_DISABLED	(1 << 3)	/* Interrupt disabled	*/
+#define EEH_DEV_DISCONNECTED	(1 << 4)	/* Removing from PE	*/
+
+#define EEH_DEV_SYSFS		(1 << 8)	/* Sysfs created        */
 
 struct eeh_dev {
 	int mode;			/* EEH mode			*/
@@ -90,11 +98,13 @@ struct eeh_dev {
 	int config_addr;		/* Config address		*/
 	int pe_config_addr;		/* PE config address		*/
 	u32 config_space[16];		/* Saved PCI config space	*/
+	u8 pcie_cap;			/* Saved PCIe capability	*/
 	struct eeh_pe *pe;		/* Associated PE		*/
 	struct list_head list;		/* Form link list in the PE	*/
 	struct pci_controller *phb;	/* Associated PHB		*/
 	struct device_node *dn;		/* Associated device node	*/
 	struct pci_dev *pdev;		/* Associated PCI device	*/
+	struct pci_bus *bus;		/* PCI bus for partial hotplug	*/
 };
 
 static inline struct device_node *eeh_dev_to_of_node(struct eeh_dev *edev)
@@ -193,8 +203,10 @@ int eeh_phb_pe_create(struct pci_controller *phb);
 struct eeh_pe *eeh_phb_pe_get(struct pci_controller *phb);
 struct eeh_pe *eeh_pe_get(struct eeh_dev *edev);
 int eeh_add_to_parent_pe(struct eeh_dev *edev);
-int eeh_rmv_from_parent_pe(struct eeh_dev *edev, int purge_pe);
+int eeh_rmv_from_parent_pe(struct eeh_dev *edev);
 void eeh_pe_update_time_stamp(struct eeh_pe *pe);
+void *eeh_pe_traverse(struct eeh_pe *root,
+		eeh_traverse_func fn, void *flag);
 void *eeh_pe_dev_traverse(struct eeh_pe *root,
 		eeh_traverse_func fn, void *flag);
 void eeh_pe_restore_bars(struct eeh_pe *pe);
@@ -209,10 +221,12 @@ unsigned long eeh_check_failure(const volatile void __iomem *token,
 				unsigned long val);
 int eeh_dev_check_failure(struct eeh_dev *edev);
 void eeh_addr_cache_build(void);
+void eeh_add_device_early(struct device_node *);
 void eeh_add_device_tree_early(struct device_node *);
+void eeh_add_device_late(struct pci_dev *);
 void eeh_add_device_tree_late(struct pci_bus *);
 void eeh_add_sysfs_files(struct pci_bus *);
-void eeh_remove_bus_device(struct pci_dev *, int);
+void eeh_remove_device(struct pci_dev *);
 
 /**
  * EEH_POSSIBLE_ERROR() -- test for possible MMIO failure.
@@ -252,13 +266,17 @@ static inline unsigned long eeh_check_failure(const volatile void __iomem *token
 
 static inline void eeh_addr_cache_build(void) { }
 
+static inline void eeh_add_device_early(struct device_node *dn) { }
+
 static inline void eeh_add_device_tree_early(struct device_node *dn) { }
 
+static inline void eeh_add_device_late(struct pci_dev *dev) { }
+
 static inline void eeh_add_device_tree_late(struct pci_bus *bus) { }
 
 static inline void eeh_add_sysfs_files(struct pci_bus *bus) { }
 
-static inline void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe) { }
+static inline void eeh_remove_device(struct pci_dev *dev) { }
 
 #define EEH_POSSIBLE_ERROR(val, type) (0)
 #define EEH_IO_ERROR_VALUE(size) (-1UL)
diff --git a/arch/powerpc/include/asm/hw_irq.h b/arch/powerpc/include/asm/hw_irq.h
index ba713f166fa..10be1dd01c6 100644
--- a/arch/powerpc/include/asm/hw_irq.h
+++ b/arch/powerpc/include/asm/hw_irq.h
@@ -96,10 +96,11 @@ static inline bool arch_irqs_disabled(void)
 #endif
 
 #define hard_irq_disable()	do {			\
-	u8 _was_enabled = get_paca()->soft_enabled;	\
+	u8 _was_enabled;				\
 	__hard_irq_disable();				\
-	get_paca()->soft_enabled = 0;			\
-	get_paca()->irq_happened |= PACA_IRQ_HARD_DIS;	\
+	_was_enabled = local_paca->soft_enabled;	\
+	local_paca->soft_enabled = 0;			\
+	local_paca->irq_happened |= PACA_IRQ_HARD_DIS;	\
 	if (_was_enabled)				\
 		trace_hardirqs_off();			\
 } while(0)
diff --git a/arch/powerpc/include/asm/module.h b/arch/powerpc/include/asm/module.h
index c1df590ec44..49fa55bfbac 100644
--- a/arch/powerpc/include/asm/module.h
+++ b/arch/powerpc/include/asm/module.h
@@ -82,10 +82,9 @@ struct exception_table_entry;
 void sort_ex_table(struct exception_table_entry *start,
 		   struct exception_table_entry *finish);
 
-#ifdef CONFIG_MODVERSIONS
+#if defined(CONFIG_MODVERSIONS) && defined(CONFIG_PPC64)
 #define ARCH_RELOCATES_KCRCTAB
-
-extern const unsigned long reloc_start[];
+#define reloc_start PHYSICAL_START
 #endif
 #endif /* __KERNEL__ */
 #endif	/* _ASM_POWERPC_MODULE_H */
diff --git a/arch/powerpc/include/asm/pci-bridge.h b/arch/powerpc/include/asm/pci-bridge.h
index 2c1d8cb9b26..32d0d2018fa 100644
--- a/arch/powerpc/include/asm/pci-bridge.h
+++ b/arch/powerpc/include/asm/pci-bridge.h
@@ -209,7 +209,6 @@ static inline struct eeh_dev *of_node_to_eeh_dev(struct device_node *dn)
 extern struct pci_bus *pcibios_find_pci_bus(struct device_node *dn);
 
 /** Remove all of the PCI devices under this bus */
-extern void __pcibios_remove_pci_devices(struct pci_bus *bus, int purge_pe);
 extern void pcibios_remove_pci_devices(struct pci_bus *bus);
 
 /** Discover new pci devices under this bus, and add them */
diff --git a/arch/powerpc/include/asm/perf_event_server.h b/arch/powerpc/include/asm/perf_event_server.h
index 2dd7bfc459b..8b249264475 100644
--- a/arch/powerpc/include/asm/perf_event_server.h
+++ b/arch/powerpc/include/asm/perf_event_server.h
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <asm/hw_irq.h>
 #include <linux/device.h>
+#include <uapi/asm/perf_event.h>
 
 #define MAX_HWEVENTS		8
 #define MAX_EVENT_ALTERNATIVES	8
@@ -69,11 +70,6 @@ struct power_pmu {
 #define PPMU_LIMITED_PMC_REQD	2	/* have to put this on a limited PMC */
 #define PPMU_ONLY_COUNT_RUN	4	/* only counting in run state */
 
-/*
- * We use the event config bit 63 as a flag to request EBB.
- */
-#define EVENT_CONFIG_EBB_SHIFT	63
-
 extern int register_power_pmu(struct power_pmu *);
 
 struct pt_regs;
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 47a35b08b96..e378cccfca5 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -247,6 +247,10 @@ struct thread_struct {
 	unsigned long	tm_orig_msr;	/* Thread's MSR on ctx switch */
 	struct pt_regs	ckpt_regs;	/* Checkpointed registers */
 
+	unsigned long	tm_tar;
+	unsigned long	tm_ppr;
+	unsigned long	tm_dscr;
+
 	/*
 	 * Transactional FP and VSX 0-31 register set.
 	 * NOTE: the sense of these is the opposite of the integer ckpt_regs!
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index 5d7d9c2a547..99222e27f17 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -254,19 +254,28 @@
 #define SPRN_HRMOR	0x139	/* Real mode offset register */
 #define SPRN_HSRR0	0x13A	/* Hypervisor Save/Restore 0 */
 #define SPRN_HSRR1	0x13B	/* Hypervisor Save/Restore 1 */
+/* HFSCR and FSCR bit numbers are the same */
+#define FSCR_TAR_LG	8	/* Enable Target Address Register */
+#define FSCR_EBB_LG	7	/* Enable Event Based Branching */
+#define FSCR_TM_LG	5	/* Enable Transactional Memory */
+#define FSCR_PM_LG	4	/* Enable prob/priv access to PMU SPRs */
+#define FSCR_BHRB_LG	3	/* Enable Branch History Rolling Buffer*/
+#define FSCR_DSCR_LG	2	/* Enable Data Stream Control Register */
+#define FSCR_VECVSX_LG	1	/* Enable VMX/VSX  */
+#define FSCR_FP_LG	0	/* Enable Floating Point */
 #define SPRN_FSCR	0x099	/* Facility Status & Control Register */
-#define   FSCR_TAR	(1 << (63-55)) /* Enable Target Address Register */
-#define   FSCR_EBB	(1 << (63-56)) /* Enable Event Based Branching */
-#define   FSCR_DSCR	(1 << (63-61)) /* Enable Data Stream Control Register */
+#define   FSCR_TAR	__MASK(FSCR_TAR_LG)
+#define   FSCR_EBB	__MASK(FSCR_EBB_LG)
+#define   FSCR_DSCR	__MASK(FSCR_DSCR_LG)
 #define SPRN_HFSCR	0xbe	/* HV=1 Facility Status & Control Register */
-#define   HFSCR_TAR	(1 << (63-55)) /* Enable Target Address Register */
-#define   HFSCR_EBB	(1 << (63-56)) /* Enable Event Based Branching */
-#define   HFSCR_TM	(1 << (63-58)) /* Enable Transactional Memory */
-#define   HFSCR_PM	(1 << (63-60)) /* Enable prob/priv access to PMU SPRs */
-#define   HFSCR_BHRB	(1 << (63-59)) /* Enable Branch History Rolling Buffer*/
-#define   HFSCR_DSCR	(1 << (63-61)) /* Enable Data Stream Control Register */
-#define   HFSCR_VECVSX	(1 << (63-62)) /* Enable VMX/VSX  */
-#define   HFSCR_FP	(1 << (63-63)) /* Enable Floating Point */
+#define   HFSCR_TAR	__MASK(FSCR_TAR_LG)
+#define   HFSCR_EBB	__MASK(FSCR_EBB_LG)
+#define   HFSCR_TM	__MASK(FSCR_TM_LG)
+#define   HFSCR_PM	__MASK(FSCR_PM_LG)
+#define   HFSCR_BHRB	__MASK(FSCR_BHRB_LG)
+#define   HFSCR_DSCR	__MASK(FSCR_DSCR_LG)
+#define   HFSCR_VECVSX	__MASK(FSCR_VECVSX_LG)
+#define   HFSCR_FP	__MASK(FSCR_FP_LG)
 #define SPRN_TAR	0x32f	/* Target Address Register */
 #define SPRN_LPCR	0x13E	/* LPAR Control Register */
 #define   LPCR_VPM0	(1ul << (63-0))
@@ -1088,7 +1097,8 @@
 #define PVR_970MP	0x0044
 #define PVR_970GX	0x0045
 #define PVR_POWER7p	0x004A
-#define PVR_POWER8	0x004B
+#define PVR_POWER8E	0x004B
+#define PVR_POWER8	0x004D
 #define PVR_BE		0x0070
 #define PVR_PA6T	0x0090
 
diff --git a/arch/powerpc/include/asm/smp.h b/arch/powerpc/include/asm/smp.h
index ffbaabebcdc..48cfc858abd 100644
--- a/arch/powerpc/include/asm/smp.h
+++ b/arch/powerpc/include/asm/smp.h
@@ -145,6 +145,10 @@ extern void __cpu_die(unsigned int cpu);
 #define smp_setup_cpu_maps()
 static inline void inhibit_secondary_onlining(void) {}
 static inline void uninhibit_secondary_onlining(void) {}
+static inline const struct cpumask *cpu_sibling_mask(int cpu)
+{
+	return cpumask_of(cpu);
+}
 
 #endif /* CONFIG_SMP */
 
diff --git a/arch/powerpc/include/asm/switch_to.h b/arch/powerpc/include/asm/switch_to.h
index 49a13e0ef23..294c2cedcf7 100644
--- a/arch/powerpc/include/asm/switch_to.h
+++ b/arch/powerpc/include/asm/switch_to.h
@@ -15,6 +15,15 @@ extern struct task_struct *__switch_to(struct task_struct *,
 struct thread_struct;
 extern struct task_struct *_switch(struct thread_struct *prev,
 				   struct thread_struct *next);
+#ifdef CONFIG_PPC_BOOK3S_64
+static inline void save_tar(struct thread_struct *prev)
+{
+	if (cpu_has_feature(CPU_FTR_ARCH_207S))
+		prev->tar = mfspr(SPRN_TAR);
+}
+#else
+static inline void save_tar(struct thread_struct *prev) {}
+#endif
 
 extern void giveup_fpu(struct task_struct *);
 extern void load_up_fpu(void);
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index 5182c8622b5..48be855ef37 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -20,6 +20,7 @@ header-y += mman.h
 header-y += msgbuf.h
 header-y += nvram.h
 header-y += param.h
+header-y += perf_event.h
 header-y += poll.h
 header-y += posix_types.h
 header-y += ps3fb.h
diff --git a/arch/powerpc/include/uapi/asm/perf_event.h b/arch/powerpc/include/uapi/asm/perf_event.h
new file mode 100644
index 00000000000..80a4d40cf5b
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/perf_event.h
@@ -0,0 +1,18 @@
+/*
+ * Copyright 2013 Michael Ellerman, IBM Corp.
+ *
+ * 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; version 2 of the
+ * License.
+ */
+
+#ifndef _UAPI_ASM_POWERPC_PERF_EVENT_H
+#define _UAPI_ASM_POWERPC_PERF_EVENT_H
+
+/*
+ * We use bit 63 of perf_event_attr.config as a flag to request EBB.
+ */
+#define PERF_EVENT_CONFIG_EBB_SHIFT	63
+
+#endif /* _UAPI_ASM_POWERPC_PERF_EVENT_H */
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index c7e8afc2ead..8207459efe5 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -138,6 +138,9 @@ int main(void)
 	DEFINE(THREAD_TM_TFHAR, offsetof(struct thread_struct, tm_tfhar));
 	DEFINE(THREAD_TM_TEXASR, offsetof(struct thread_struct, tm_texasr));
 	DEFINE(THREAD_TM_TFIAR, offsetof(struct thread_struct, tm_tfiar));
+	DEFINE(THREAD_TM_TAR, offsetof(struct thread_struct, tm_tar));
+	DEFINE(THREAD_TM_PPR, offsetof(struct thread_struct, tm_ppr));
+	DEFINE(THREAD_TM_DSCR, offsetof(struct thread_struct, tm_dscr));
 	DEFINE(PT_CKPT_REGS, offsetof(struct thread_struct, ckpt_regs));
 	DEFINE(THREAD_TRANSACT_VR0, offsetof(struct thread_struct,
 					 transact_vr[0]));
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index 2a45d0f0438..22973a74df7 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -494,9 +494,27 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_restore		= __restore_cpu_power7,
 		.platform		= "power7+",
 	},
-	{	/* Power8 */
+	{	/* Power8E */
 		.pvr_mask		= 0xffff0000,
 		.pvr_value		= 0x004b0000,
+		.cpu_name		= "POWER8E (raw)",
+		.cpu_features		= CPU_FTRS_POWER8,
+		.cpu_user_features	= COMMON_USER_POWER8,
+		.cpu_user_features2	= COMMON_USER2_POWER8,
+		.mmu_features		= MMU_FTRS_POWER8,
+		.icache_bsize		= 128,
+		.dcache_bsize		= 128,
+		.num_pmcs		= 6,
+		.pmc_type		= PPC_PMC_IBM,
+		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_type		= PPC_OPROFILE_INVALID,
+		.cpu_setup		= __setup_cpu_power8,
+		.cpu_restore		= __restore_cpu_power8,
+		.platform		= "power8",
+	},
+	{	/* Power8 */
+		.pvr_mask		= 0xffff0000,
+		.pvr_value		= 0x004d0000,
 		.cpu_name		= "POWER8 (raw)",
 		.cpu_features		= CPU_FTRS_POWER8,
 		.cpu_user_features	= COMMON_USER_POWER8,
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 39954fe941b..55593ee2d5a 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -231,7 +231,7 @@ static size_t eeh_gather_pci_data(struct eeh_dev *edev, char * buf, size_t len)
 void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 {
 	size_t loglen = 0;
-	struct eeh_dev *edev;
+	struct eeh_dev *edev, *tmp;
 	bool valid_cfg_log = true;
 
 	/*
@@ -251,7 +251,7 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 		eeh_pe_restore_bars(pe);
 
 		pci_regs_buf[0] = 0;
-		eeh_pe_for_each_dev(pe, edev) {
+		eeh_pe_for_each_dev(pe, edev, tmp) {
 			loglen += eeh_gather_pci_data(edev, pci_regs_buf + loglen,
 						      EEH_PCI_REGS_LOG_LEN - loglen);
 		}
@@ -499,8 +499,6 @@ unsigned long eeh_check_failure(const volatile void __iomem *token, unsigned lon
 	}
 
 	eeh_dev_check_failure(edev);
-
-	pci_dev_put(eeh_dev_to_pci_dev(edev));
 	return val;
 }
 
@@ -838,7 +836,7 @@ core_initcall_sync(eeh_init);
  * on the CEC architecture, type of the device, on earlier boot
  * command-line arguments & etc.
  */
-static void eeh_add_device_early(struct device_node *dn)
+void eeh_add_device_early(struct device_node *dn)
 {
 	struct pci_controller *phb;
 
@@ -886,7 +884,7 @@ EXPORT_SYMBOL_GPL(eeh_add_device_tree_early);
  * This routine must be used to complete EEH initialization for PCI
  * devices that were added after system boot (e.g. hotplug, dlpar).
  */
-static void eeh_add_device_late(struct pci_dev *dev)
+void eeh_add_device_late(struct pci_dev *dev)
 {
 	struct device_node *dn;
 	struct eeh_dev *edev;
@@ -902,9 +900,23 @@ static void eeh_add_device_late(struct pci_dev *dev)
 		pr_debug("EEH: Already referenced !\n");
 		return;
 	}
-	WARN_ON(edev->pdev);
 
-	pci_dev_get(dev);
+	/*
+	 * The EEH cache might not be removed correctly because of
+	 * unbalanced kref to the device during unplug time, which
+	 * relies on pcibios_release_device(). So we have to remove
+	 * that here explicitly.
+	 */
+	if (edev->pdev) {
+		eeh_rmv_from_parent_pe(edev);
+		eeh_addr_cache_rmv_dev(edev->pdev);
+		eeh_sysfs_remove_device(edev->pdev);
+		edev->mode &= ~EEH_DEV_SYSFS;
+
+		edev->pdev = NULL;
+		dev->dev.archdata.edev = NULL;
+	}
+
 	edev->pdev = dev;
 	dev->dev.archdata.edev = edev;
 
@@ -967,7 +979,6 @@ EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
 /**
  * eeh_remove_device - Undo EEH setup for the indicated pci device
  * @dev: pci device to be removed
- * @purge_pe: remove the PE or not
  *
  * This routine should be called when a device is removed from
  * a running system (e.g. by hotplug or dlpar).  It unregisters
@@ -975,7 +986,7 @@ EXPORT_SYMBOL_GPL(eeh_add_sysfs_files);
  * this device will no longer be detected after this call; thus,
  * i/o errors affecting this slot may leave this device unusable.
  */
-static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
+void eeh_remove_device(struct pci_dev *dev)
 {
 	struct eeh_dev *edev;
 
@@ -986,42 +997,29 @@ static void eeh_remove_device(struct pci_dev *dev, int purge_pe)
 	/* Unregister the device with the EEH/PCI address search system */
 	pr_debug("EEH: Removing device %s\n", pci_name(dev));
 
-	if (!edev || !edev->pdev) {
+	if (!edev || !edev->pdev || !edev->pe) {
 		pr_debug("EEH: Not referenced !\n");
 		return;
 	}
+
+	/*
+	 * During the hotplug for EEH error recovery, we need the EEH
+	 * device attached to the parent PE in order for BAR restore
+	 * a bit later. So we keep it for BAR restore and remove it
+	 * from the parent PE during the BAR resotre.
+	 */
 	edev->pdev = NULL;
 	dev->dev.archdata.edev = NULL;
-	pci_dev_put(dev);
+	if (!(edev->pe->state & EEH_PE_KEEP))
+		eeh_rmv_from_parent_pe(edev);
+	else
+		edev->mode |= EEH_DEV_DISCONNECTED;
 
-	eeh_rmv_from_parent_pe(edev, purge_pe);
 	eeh_addr_cache_rmv_dev(dev);
 	eeh_sysfs_remove_device(dev);
+	edev->mode &= ~EEH_DEV_SYSFS;
 }
 
-/**
- * eeh_remove_bus_device - Undo EEH setup for the indicated PCI device
- * @dev: PCI device
- * @purge_pe: remove the corresponding PE or not
- *
- * This routine must be called when a device is removed from the
- * running system through hotplug or dlpar. The corresponding
- * PCI address cache will be removed.
- */
-void eeh_remove_bus_device(struct pci_dev *dev, int purge_pe)
-{
-	struct pci_bus *bus = dev->subordinate;
-	struct pci_dev *child, *tmp;
-
-	eeh_remove_device(dev, purge_pe);
-
-	if (bus && dev->hdr_type == PCI_HEADER_TYPE_BRIDGE) {
-		list_for_each_entry_safe(child, tmp, &bus->devices, bus_list)
-			 eeh_remove_bus_device(child, purge_pe);
-	}
-}
-EXPORT_SYMBOL_GPL(eeh_remove_bus_device);
-
 static int proc_eeh_show(struct seq_file *m, void *v)
 {
 	if (0 == eeh_subsystem_enabled) {
@@ -1063,7 +1061,7 @@ static const struct file_operations proc_eeh_operations = {
 
 static int __init eeh_init_proc(void)
 {
-	if (machine_is(pseries))
+	if (machine_is(pseries) || machine_is(powernv))
 		proc_create("powerpc/eeh", 0, NULL, &proc_eeh_operations);
 	return 0;
 }
diff --git a/arch/powerpc/kernel/eeh_cache.c b/arch/powerpc/kernel/eeh_cache.c
index f9ac1232a74..e8c9fd546a5 100644
--- a/arch/powerpc/kernel/eeh_cache.c
+++ b/arch/powerpc/kernel/eeh_cache.c
@@ -68,16 +68,12 @@ static inline struct eeh_dev *__eeh_addr_cache_get_device(unsigned long addr)
 		struct pci_io_addr_range *piar;
 		piar = rb_entry(n, struct pci_io_addr_range, rb_node);
 
-		if (addr < piar->addr_lo) {
+		if (addr < piar->addr_lo)
 			n = n->rb_left;
-		} else {
-			if (addr > piar->addr_hi) {
-				n = n->rb_right;
-			} else {
-				pci_dev_get(piar->pcidev);
-				return piar->edev;
-			}
-		}
+		else if (addr > piar->addr_hi)
+			n = n->rb_right;
+		else
+			return piar->edev;
 	}
 
 	return NULL;
@@ -156,7 +152,6 @@ eeh_addr_cache_insert(struct pci_dev *dev, unsigned long alo,
 	if (!piar)
 		return NULL;
 
-	pci_dev_get(dev);
 	piar->addr_lo = alo;
 	piar-&