Merge remote-tracking branch 'benh/next' into next

Merge updates collected & acked by Ben. A few EEH patches from Gavin,
some mm updates from Aneesh and a few odds and ends.

18 files changed, 162 insertions, 284 deletions

diff --git a/arch/powerpc/include/asm/eeh.h b/arch/powerpc/include/asm/eeh.h
index ca07f9c27335..0652ebe117af 100644
--- a/arch/powerpc/include/asm/eeh.h
+++ b/arch/powerpc/include/asm/eeh.h
@@ -39,6 +39,7 @@ struct device_node;
 #define EEH_PROBE_MODE_DEV	0x04	/* From PCI device	*/
 #define EEH_PROBE_MODE_DEVTREE	0x08	/* From device tree	*/
 #define EEH_ENABLE_IO_FOR_LOG	0x10	/* Enable IO for log	*/
+#define EEH_EARLY_DUMP_LOG	0x20	/* Dump log immediately	*/
 
 /*
  * Delay for PE reset, all in ms
@@ -72,6 +73,7 @@ struct device_node;
 #define EEH_PE_ISOLATED		(1 << 0)	/* Isolated PE		*/
 #define EEH_PE_RECOVERING	(1 << 1)	/* Recovering PE	*/
 #define EEH_PE_CFG_BLOCKED	(1 << 2)	/* Block config access	*/
+#define EEH_PE_RESET		(1 << 3)	/* PE reset in progress */
 
 #define EEH_PE_KEEP		(1 << 8)	/* Keep PE on hotplug	*/
 #define EEH_PE_CFG_RESTRICTED	(1 << 9)	/* Block config on error */
diff --git a/arch/powerpc/include/asm/machdep.h b/arch/powerpc/include/asm/machdep.h
index 15c9150a58cc..e5c0919acca4 100644
--- a/arch/powerpc/include/asm/machdep.h
+++ b/arch/powerpc/include/asm/machdep.h
@@ -60,7 +60,7 @@ struct machdep_calls {
 	void		(*hugepage_invalidate)(unsigned long vsid,
 					       unsigned long addr,
 					       unsigned char *hpte_slot_array,
-					       int psize, int ssize);
+					       int psize, int ssize, int local);
 	/* special for kexec, to be called in real mode, linear mapping is
 	 * destroyed as well */
 	void		(*hpte_clear_all)(void);
diff --git a/arch/powerpc/include/asm/opal.h b/arch/powerpc/include/asm/opal.h
index 60250e2d1f0d..5cd8d2fddba9 100644
--- a/arch/powerpc/include/asm/opal.h
+++ b/arch/powerpc/include/asm/opal.h
@@ -288,62 +288,6 @@ enum OpalMessageType {
 	OPAL_MSG_TYPE_MAX,
 };
 
-/* Machine check related definitions */
-enum OpalMCE_Version {
-	OpalMCE_V1 = 1,
-};
-
-enum OpalMCE_Severity {
-	OpalMCE_SEV_NO_ERROR = 0,
-	OpalMCE_SEV_WARNING = 1,
-	OpalMCE_SEV_ERROR_SYNC = 2,
-	OpalMCE_SEV_FATAL = 3,
-};
-
-enum OpalMCE_Disposition {
-	OpalMCE_DISPOSITION_RECOVERED = 0,
-	OpalMCE_DISPOSITION_NOT_RECOVERED = 1,
-};
-
-enum OpalMCE_Initiator {
-	OpalMCE_INITIATOR_UNKNOWN = 0,
-	OpalMCE_INITIATOR_CPU = 1,
-};
-
-enum OpalMCE_ErrorType {
-	OpalMCE_ERROR_TYPE_UNKNOWN = 0,
-	OpalMCE_ERROR_TYPE_UE = 1,
-	OpalMCE_ERROR_TYPE_SLB = 2,
-	OpalMCE_ERROR_TYPE_ERAT = 3,
-	OpalMCE_ERROR_TYPE_TLB = 4,
-};
-
-enum OpalMCE_UeErrorType {
-	OpalMCE_UE_ERROR_INDETERMINATE = 0,
-	OpalMCE_UE_ERROR_IFETCH = 1,
-	OpalMCE_UE_ERROR_PAGE_TABLE_WALK_IFETCH = 2,
-	OpalMCE_UE_ERROR_LOAD_STORE = 3,
-	OpalMCE_UE_ERROR_PAGE_TABLE_WALK_LOAD_STORE = 4,
-};
-
-enum OpalMCE_SlbErrorType {
-	OpalMCE_SLB_ERROR_INDETERMINATE = 0,
-	OpalMCE_SLB_ERROR_PARITY = 1,
-	OpalMCE_SLB_ERROR_MULTIHIT = 2,
-};
-
-enum OpalMCE_EratErrorType {
-	OpalMCE_ERAT_ERROR_INDETERMINATE = 0,
-	OpalMCE_ERAT_ERROR_PARITY = 1,
-	OpalMCE_ERAT_ERROR_MULTIHIT = 2,
-};
-
-enum OpalMCE_TlbErrorType {
-	OpalMCE_TLB_ERROR_INDETERMINATE = 0,
-	OpalMCE_TLB_ERROR_PARITY = 1,
-	OpalMCE_TLB_ERROR_MULTIHIT = 2,
-};
-
 enum OpalThreadStatus {
 	OPAL_THREAD_INACTIVE = 0x0,
 	OPAL_THREAD_STARTED = 0x1,
@@ -467,54 +411,6 @@ struct opal_ipmi_msg {
 	uint8_t		data[];
 };
 
-struct opal_machine_check_event {
-	enum OpalMCE_Version	version:8;	/* 0x00 */
-	uint8_t			in_use;		/* 0x01 */
-	enum OpalMCE_Severity	severity:8;	/* 0x02 */
-	enum OpalMCE_Initiator	initiator:8;	/* 0x03 */
-	enum OpalMCE_ErrorType	error_type:8;	/* 0x04 */
-	enum OpalMCE_Disposition disposition:8; /* 0x05 */
-	uint8_t			reserved_1[2];	/* 0x06 */
-	uint64_t		gpr3;		/* 0x08 */
-	uint64_t		srr0;		/* 0x10 */
-	uint64_t		srr1;		/* 0x18 */
-	union {					/* 0x20 */
-		struct {
-			enum OpalMCE_UeErrorType ue_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		physical_address_provided;
-			uint8_t		reserved_1[5];
-			uint64_t	effective_address;
-			uint64_t	physical_address;
-			uint8_t		reserved_2[8];
-		} ue_error;
-
-		struct {
-			enum OpalMCE_SlbErrorType slb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} slb_error;
-
-		struct {
-			enum OpalMCE_EratErrorType erat_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} erat_error;
-
-		struct {
-			enum OpalMCE_TlbErrorType tlb_error_type:8;
-			uint8_t		effective_address_provided;
-			uint8_t		reserved_1[6];
-			uint64_t	effective_address;
-			uint8_t		reserved_2[16];
-		} tlb_error;
-	} u;
-};
-
 /* FSP memory errors handling */
 enum OpalMemErr_Version {
 	OpalMemErr_V1 = 1,
diff --git a/arch/powerpc/include/asm/paca.h b/arch/powerpc/include/asm/paca.h
index a5139ea6910b..24a386cbb928 100644
--- a/arch/powerpc/include/asm/paca.h
+++ b/arch/powerpc/include/asm/paca.h
@@ -42,7 +42,6 @@ extern unsigned int debug_smp_processor_id(void); /* from linux/smp.h */
 #define get_slb_shadow()	(get_paca()->slb_shadow_ptr)
 
 struct task_struct;
-struct opal_machine_check_event;
 
 /*
  * Defines the layout of the paca.
@@ -153,12 +152,6 @@ struct paca_struct {
 	u64 tm_scratch;                 /* TM scratch area for reclaim */
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	/* Pointer to OPAL machine check event structure set by the
-	 * early exception handler for use by high level C handler
-	 */
-	struct opal_machine_check_event *opal_mc_evt;
-#endif
 #ifdef CONFIG_PPC_BOOK3S_64
 	/* Exclusive emergency stack pointer for machine check exception. */
 	void *mc_emergency_sp;
diff --git a/arch/powerpc/include/asm/tlbflush.h b/arch/powerpc/include/asm/tlbflush.h
index cd7c2719d3ef..4d3ecd8d8929 100644
--- a/arch/powerpc/include/asm/tlbflush.h
+++ b/arch/powerpc/include/asm/tlbflush.h
@@ -127,7 +127,9 @@ static inline void arch_leave_lazy_mmu_mode(void)
 extern void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize,
 			    int ssize, int local);
 extern void flush_hash_range(unsigned long number, int local);
-
+extern void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+				pmd_t *pmdp, unsigned int psize, int ssize,
+				int local);
 
 static inline void local_flush_tlb_mm(struct mm_struct *mm)
 {
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index 9d7dede2847c..c161ef3f28a1 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -726,12 +726,5 @@ int main(void)
 					arch.timing_last_enter.tv32.tbl));
 #endif
 
-#ifdef CONFIG_PPC_POWERNV
-	DEFINE(OPAL_MC_GPR3, offsetof(struct opal_machine_check_event, gpr3));
-	DEFINE(OPAL_MC_SRR0, offsetof(struct opal_machine_check_event, srr0));
-	DEFINE(OPAL_MC_SRR1, offsetof(struct opal_machine_check_event, srr1));
-	DEFINE(PACA_OPAL_MC_EVT, offsetof(struct paca_struct, opal_mc_evt));
-#endif
-
 	return 0;
 }
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index 2248a1999c64..e1b6d8e17289 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -143,6 +143,8 @@ static int __init eeh_setup(char *str)
 {
 	if (!strcmp(str, "off"))
 		eeh_add_flag(EEH_FORCE_DISABLED);
+	else if (!strcmp(str, "early_log"))
+		eeh_add_flag(EEH_EARLY_DUMP_LOG);
 
 	return 1;
 }
@@ -758,30 +760,41 @@ static void eeh_reset_pe_once(struct eeh_pe *pe)
 int eeh_reset_pe(struct eeh_pe *pe)
 {
 	int flags = (EEH_STATE_MMIO_ACTIVE | EEH_STATE_DMA_ACTIVE);
-	int i, rc;
+	int i, state, ret;
+
+	/* Mark as reset and block config space */
+	eeh_pe_state_mark(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
 
 	/* Take three shots at resetting the bus */
-	for (i=0; i<3; i++) {
+	for (i = 0; i < 3; i++) {
 		eeh_reset_pe_once(pe);
 
 		/*
 		 * EEH_PE_ISOLATED is expected to be removed after
 		 * BAR restore.
 		 */
-		rc = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
-		if ((rc & flags) == flags)
-			return 0;
+		state = eeh_ops->wait_state(pe, PCI_BUS_RESET_WAIT_MSEC);
+		if ((state & flags) == flags) {
+			ret = 0;
+			goto out;
+		}
 
-		if (rc < 0) {
-			pr_err("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
+		if (state < 0) {
+			pr_warn("%s: Unrecoverable slot failure on PHB#%d-PE#%x",
 				__func__, pe->phb->global_number, pe->addr);
-			return -1;
+			ret = -ENOTRECOVERABLE;
+			goto out;
 		}
-		pr_err("EEH: bus reset %d failed on PHB#%d-PE#%x, rc=%d\n",
-			i+1, pe->phb->global_number, pe->addr, rc);
+
+		/* We might run out of credits */
+		ret = -EIO;
+		pr_warn("%s: Failure %d resetting PHB#%x-PE#%x\n (%d)\n",
+			__func__, state, pe->phb->global_number, pe->addr, (i + 1));
 	}
 
-	return -1;
+out:
+	eeh_pe_state_clear(pe, EEH_PE_RESET | EEH_PE_CFG_BLOCKED);
+	return ret;
 }
 
 /**
@@ -920,11 +933,8 @@ int eeh_init(void)
 		pr_warn("%s: Platform EEH operation not found\n",
 			__func__);
 		return -EEXIST;
-	} else if ((ret = eeh_ops->init())) {
-		pr_warn("%s: Failed to call platform init function (%d)\n",
-			__func__, ret);
+	} else if ((ret = eeh_ops->init()))
 		return ret;
-	}
 
 	/* Initialize EEH event */
 	ret = eeh_event_init();
@@ -1209,6 +1219,7 @@ int eeh_unfreeze_pe(struct eeh_pe *pe, bool sw_state)
 static struct pci_device_id eeh_reset_ids[] = {
 	{ PCI_DEVICE(0x19a2, 0x0710) },	/* Emulex, BE     */
 	{ PCI_DEVICE(0x10df, 0xe220) },	/* Emulex, Lancer */
+	{ PCI_DEVICE(0x14e4, 0x1657) }, /* Broadcom BCM5719 */
 	{ 0 }
 };
 
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 6535936bdf27..b17e793ba67e 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -528,13 +528,11 @@ int eeh_pe_reset_and_recover(struct eeh_pe *pe)
 	eeh_pe_dev_traverse(pe, eeh_report_error, &result);
 
 	/* Issue reset */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	ret = eeh_reset_pe(pe);
 	if (ret) {
-		eeh_pe_state_clear(pe, EEH_PE_RECOVERING | EEH_PE_CFG_BLOCKED);
+		eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		return ret;
 	}
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Unfreeze the PE */
 	ret = eeh_clear_pe_frozen_state(pe, true);
@@ -601,19 +599,15 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
 	 * config accesses. So we prefer to block them. However, controlled
 	 * PCI config accesses initiated from EEH itself are allowed.
 	 */
-	eeh_pe_state_mark(pe, EEH_PE_CFG_BLOCKED);
 	rc = eeh_reset_pe(pe);
-	if (rc) {
-		eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
+	if (rc)
 		return rc;
-	}
 
 	pci_lock_rescan_remove();
 
 	/* Restore PE */
 	eeh_ops->configure_bridge(pe);
 	eeh_pe_restore_bars(pe);
-	eeh_pe_state_clear(pe, EEH_PE_CFG_BLOCKED);
 
 	/* Clear frozen state */
 	rc = eeh_clear_pe_frozen_state(pe, false);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index a1d45c161e24..ad62f4d6ce31 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1312,23 +1312,6 @@ hmi_exception_after_realmode:
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	hmi_exception_hv
 
-#ifdef CONFIG_PPC_POWERNV
-_GLOBAL(opal_mc_secondary_handler)
-	HMT_MEDIUM_PPR_DISCARD
-	SET_SCRATCH0(r13)
-	GET_PACA(r13)
-	clrldi	r3,r3,2
-	tovirt(r3,r3)
-	std	r3,PACA_OPAL_MC_EVT(r13)
-	ld	r13,OPAL_MC_SRR0(r3)
-	mtspr	SPRN_SRR0,r13
-	ld	r13,OPAL_MC_SRR1(r3)
-	mtspr	SPRN_SRR1,r13
-	ld	r3,OPAL_MC_GPR3(r3)
-	GET_SCRATCH0(r13)
-	b	machine_check_pSeries
-#endif /* CONFIG_PPC_POWERNV */
-
 
 #define MACHINE_CHECK_HANDLER_WINDUP			\
 	/* Clear MSR_RI before setting SRR0 and SRR1. */\
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index d53288a08c37..13700911b522 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -294,8 +294,6 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 	DBG_LOW("    update(vpn=%016lx, avpnv=%016lx, group=%lx, newpp=%lx)",
 		vpn, want_v & HPTE_V_AVPN, slot, newpp);
 
-	native_lock_hpte(hptep);
-
 	hpte_v = be64_to_cpu(hptep->v);
 	/*
 	 * We need to invalidate the TLB always because hpte_remove doesn't do
@@ -308,16 +306,24 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		DBG_LOW(" -> miss\n");
 		ret = -1;
 	} else {
-		DBG_LOW(" -> hit\n");
-		/* Update the HPTE */
-		hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) & ~(HPTE_R_PP | HPTE_R_N)) |
-			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C)));
+		native_lock_hpte(hptep);
+		/* recheck with locks held */
+		hpte_v = be64_to_cpu(hptep->v);
+		if (unlikely(!HPTE_V_COMPARE(hpte_v, want_v) ||
+			     !(hpte_v & HPTE_V_VALID))) {
+			ret = -1;
+		} else {
+			DBG_LOW(" -> hit\n");
+			/* Update the HPTE */
+			hptep->r = cpu_to_be64((be64_to_cpu(hptep->r) &
+						~(HPTE_R_PP | HPTE_R_N)) |
+					       (newpp & (HPTE_R_PP | HPTE_R_N |
+							 HPTE_R_C)));
+		}
+		native_unlock_hpte(hptep);
 	}
-	native_unlock_hpte(hptep);
-
 	/* Ensure it is out of the tlb too. */
 	tlbie(vpn, bpsize, apsize, ssize, local);
-
 	return ret;
 }
 
@@ -419,7 +425,7 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 static void native_hugepage_invalidate(unsigned long vsid,
 				       unsigned long addr,
 				       unsigned char *hpte_slot_array,
-				       int psize, int ssize)
+				       int psize, int ssize, int local)
 {
 	int i;
 	struct hash_pte *hptep;
@@ -465,7 +471,7 @@ static void native_hugepage_invalidate(unsigned long vsid,
 		 * instruction compares entry_VA in tlb with the VA specified
 		 * here
 		 */
-		tlbie(vpn, psize, actual_psize, ssize, 0);
+		tlbie(vpn, psize, actual_psize, ssize, local);
 	}
 	local_irq_restore(flags);
 }
diff --git a/arch/powerpc/mm/hash_utils_64.c b/arch/powerpc/mm/hash_utils_64.c
index f01027731e23..68211d398fdb 100644
--- a/arch/powerpc/mm/hash_utils_64.c
+++ b/arch/powerpc/mm/hash_utils_64.c
@@ -1315,6 +1315,76 @@ void flush_hash_page(unsigned long vpn, real_pte_t pte, int psize, int ssize,
 #endif
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+void flush_hash_hugepage(unsigned long vsid, unsigned long addr,
+			 pmd_t *pmdp, unsigned int psize, int ssize, int local)
+{
+	int i, max_hpte_count, valid;
+	unsigned long s_addr;
+	unsigned char *hpte_slot_array;
+	unsigned long hidx, shift, vpn, hash, slot;
+
+	s_addr = addr & HPAGE_PMD_MASK;
+	hpte_slot_array = get_hpte_slot_array(pmdp);
+	/*
+	 * IF we try to do a HUGE PTE update after a withdraw is done.
+	 * we will find the below NULL. This happens when we do
+	 * split_huge_page_pmd
+	 */
+	if (!hpte_slot_array)
+		return;
+
+	if (ppc_md.hugepage_invalidate) {
+		ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
+					   psize, ssize, local);
+		goto tm_abort;
+	}
+	/*
+	 * No bluk hpte removal support, invalidate each entry
+	 */
+	shift = mmu_psize_defs[psize].shift;
+	max_hpte_count = HPAGE_PMD_SIZE >> shift;
+	for (i = 0; i < max_hpte_count; i++) {
+		/*
+		 * 8 bits per each hpte entries
+		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
+		 */
+		valid = hpte_valid(hpte_slot_array, i);
+		if (!valid)
+			continue;
+		hidx =  hpte_hash_index(hpte_slot_array, i);
+
+		/* get the vpn */
+		addr = s_addr + (i * (1ul << shift));
+		vpn = hpt_vpn(addr, vsid, ssize);
+		hash = hpt_hash(vpn, shift, ssize);
+		if (hidx & _PTEIDX_SECONDARY)
+			hash = ~hash;
+
+		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
+		slot += hidx & _PTEIDX_GROUP_IX;
+		ppc_md.hpte_invalidate(slot, vpn, psize,
+				       MMU_PAGE_16M, ssize, local);
+	}
+tm_abort:
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	/* Transactions are not aborted by tlbiel, only tlbie.
+	 * Without, syncing a page back to a block device w/ PIO could pick up
+	 * transactional data (bad!) so we force an abort here.  Before the
+	 * sync the page will be made read-only, which will flush_hash_page.
+	 * BIG ISSUE here: if the kernel uses a page from userspace without
+	 * unmapping it first, it may see the speculated version.
+	 */
+	if (local && cpu_has_feature(CPU_FTR_TM) &&
+	    current->thread.regs &&
+	    MSR_TM_ACTIVE(current->thread.regs->msr)) {
+		tm_enable();
+		tm_abort(TM_CAUSE_TLBI);
+	}
+#endif
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
 void flush_hash_range(unsigned long number, int local)
 {
 	if (ppc_md.flush_hash_range)
diff --git a/arch/powerpc/mm/hugepage-hash64.c b/arch/powerpc/mm/hugepage-hash64.c
index 5f5e6328c21c..3a648cd363ae 100644
--- a/arch/powerpc/mm/hugepage-hash64.c
+++ b/arch/powerpc/mm/hugepage-hash64.c
@@ -18,57 +18,6 @@
 #include <linux/mm.h>
 #include <asm/machdep.h>
 
-static void invalidate_old_hpte(unsigned long vsid, unsigned long addr,
-				pmd_t *pmdp, unsigned int psize, int ssize)
-{
-	int i, max_hpte_count, valid;
-	unsigned long s_addr;
-	unsigned char *hpte_slot_array;
-	unsigned long hidx, shift, vpn, hash, slot;
-
-	s_addr = addr & HPAGE_PMD_MASK;
-	hpte_slot_array = get_hpte_slot_array(pmdp);
-	/*
-	 * IF we try to do a HUGE PTE update after a withdraw is done.
-	 * we will find the below NULL. This happens when we do
-	 * split_huge_page_pmd
-	 */
-	if (!hpte_slot_array)
-		return;
-
-	if (ppc_md.hugepage_invalidate)
-		return ppc_md.hugepage_invalidate(vsid, s_addr, hpte_slot_array,
-						  psize, ssize);
-	/*
-	 * No bluk hpte removal support, invalidate each entry
-	 */
-	shift = mmu_psize_defs[psize].shift;
-	max_hpte_count = HPAGE_PMD_SIZE >> shift;
-	for (i = 0; i < max_hpte_count; i++) {
-		/*
-		 * 8 bits per each hpte entries
-		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
-		 */
-		valid = hpte_valid(hpte_slot_array, i);
-		if (!valid)
-			continue;
-		hidx =  hpte_hash_index(hpte_slot_array, i);
-
-		/* get the vpn */
-		addr = s_addr + (i * (1ul << shift));
-		vpn = hpt_vpn(addr, vsid, ssize);
-		hash = hpt_hash(vpn, shift, ssize);
-		if (hidx & _PTEIDX_SECONDARY)
-			hash = ~hash;
-
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += hidx & _PTEIDX_GROUP_IX;
-		ppc_md.hpte_invalidate(slot, vpn, psize,
-				       MMU_PAGE_16M, ssize, 0);
-	}
-}
-
-
 int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		    pmd_t *pmdp, unsigned long trap, int local, int ssize,
 		    unsigned int psize)
@@ -145,7 +94,8 @@ int __hash_page_thp(unsigned long ea, unsigned long access, unsigned long vsid,
 		 * hash page table entries.
 		 */
 		if ((old_pmd & _PAGE_HASHPTE) && !(old_pmd & _PAGE_COMBO))
-			invalidate_old_hpte(vsid, ea, pmdp, MMU_PAGE_64K, ssize);
+			flush_hash_hugepage(vsid, ea, pmdp, MMU_PAGE_64K,
+					    ssize, local);
 	}
 
 	valid = hpte_valid(hpte_slot_array, index);
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 8c9b8115867c..868ab0fc5fbf 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -355,6 +355,13 @@ static int __init do_gpage_early_setup(char *param, char *val,
 		if (size != 0) {
 			if (sscanf(val, "%lu", &npages) <= 0)
 				npages = 0;
+			if (npages > MAX_NUMBER_GPAGES) {
+				pr_warn("MMU: %lu pages requested for page "
+					"size %llu KB, limiting to "
+					__stringify(MAX_NUMBER_GPAGES) "\n",
+					npages, size / 1024);
+				npages = MAX_NUMBER_GPAGES;
+			}
 			gpage_npages[shift_to_mmu_psize(__ffs(size))] = npages;
 			size = 0;
 		}
diff --git a/arch/powerpc/mm/pgtable_64.c b/arch/powerpc/mm/pgtable_64.c
index 87ff0c1908a9..eea9fa1f8ae7 100644
--- a/arch/powerpc/mm/pgtable_64.c
+++ b/arch/powerpc/mm/pgtable_64.c
@@ -739,29 +739,14 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 			    pmd_t *pmdp, unsigned long old_pmd)
 {
-	int ssize, i;
-	unsigned long s_addr;
-	int max_hpte_count;
-	unsigned int psize, valid;
-	unsigned char *hpte_slot_array;
-	unsigned long hidx, vpn, vsid, hash, shift, slot;
-
-	/*
-	 * Flush all the hptes mapping this hugepage
-	 */
-	s_addr = addr & HPAGE_PMD_MASK;
-	hpte_slot_array = get_hpte_slot_array(pmdp);
-	/*
-	 * IF we try to do a HUGE PTE update after a withdraw is done.
-	 * we will find the below NULL. This happens when we do
-	 * split_huge_page_pmd
-	 */
-	if (!hpte_slot_array)
-		return;
+	int ssize, local = 0;
+	unsigned int psize;
+	unsigned long vsid;
+	const struct cpumask *tmp;
 
 	/* get the base page size,vsid and segment size */
 #ifdef CONFIG_DEBUG_VM
-	psize = get_slice_psize(mm, s_addr);
+	psize = get_slice_psize(mm, addr);
 	BUG_ON(psize == MMU_PAGE_16M);
 #endif
 	if (old_pmd & _PAGE_COMBO)
@@ -769,46 +754,20 @@ void hpte_do_hugepage_flush(struct mm_struct *mm, unsigned long addr,
 	else
 		psize = MMU_PAGE_64K;
 
-	if (!is_kernel_addr(s_addr)) {
-		ssize = user_segment_size(s_addr);
-		vsid = get_vsid(mm->context.id, s_addr, ssize);
+	if (!is_kernel_addr(addr)) {
+		ssize = user_segment_size(addr);
+		vsid = get_vsid(mm->context.id, addr, ssize);
 		WARN_ON(vsid == 0);
 	} else {
-		vsid = get_kernel_vsid(s_addr, mmu_kernel_ssize);
+		vsid = get_kernel_vsid(addr, mmu_kernel_ssize);
 		ssize = mmu_kernel_ssize;
 	}
 
-	if (ppc_md.hugepage_invalidate)
-		return ppc_md.hugepage_invalidate(vsid, s_addr,
-						  hpte_slot_array,
-						  psize, ssize);
-	/*
-	 * No bluk hpte removal support, invalidate each entry
-	 */
-	shift = mmu_psize_defs[psize].shift;
-	max_hpte_count = HPAGE_PMD_SIZE >> shift;
-	for (i = 0; i < max_hpte_count; i++) {
-		/*
-		 * 8 bits per each hpte entries
-		 * 000| [ secondary group (one bit) | hidx (3 bits) | valid bit]
-		 */
-		valid = hpte_valid(hpte_slot_array, i);
-		if (!valid)
-			continue;
-		hidx =  hpte_hash_index(hpte_slot_array, i);
-
-		/* get the vpn */
-		addr = s_addr + (i * (1ul << shift));
-		vpn = hpt_vpn(addr, vsid, ssize);
-		hash = hpt_hash(vpn, shift, ssize);
-		if (hidx & _PTEIDX_SECONDARY)
-			hash = ~hash;
-
-		slot = (hash & htab_hash_mask) * HPTES_PER_GROUP;
-		slot += hidx & _PTEIDX_GROUP_IX;
-		ppc_md.hpte_invalidate(slot, vpn, psize,
-				       MMU_PAGE_16M, ssize, 0);
-	}
+	tmp = cpumask_of(smp_processor_id());
+	if (cpumask_equal(mm_cpumask(mm), tmp))
+		local = 1;
+
+	return flush_hash_hugepage(vsid, addr, pmdp, psize, ssize, local);
 }
 
 static pmd_t pmd_set_protbits(pmd_t pmd, pgprot_t pgprot)
diff --git a/arch/powerpc/oprofile/backtrace.c b/arch/powerpc/oprofile/backtrace.c
index 6adf55fa5d88..ecc66d5f02c9 100644
--- a/arch/powerpc/oprofile/backtrace.c
+++ b/arch/powerpc/oprofile/backtrace.c
@@ -10,7 +10,7 @@
 #include <linux/oprofile.h>
 #include <linux/sched.h>
 #include <asm/processor.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/compat.h>
 #include <asm/oprofile_impl.h>
 
@@ -105,6 +105,7 @@ void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth)
 			first_frame = 0;
 		}
 	} else {
+		pagefault_disable();
 #ifdef CONFIG_PPC64
 		if (!is_32bit_task()) {
 			while (depth--) {
@@ -113,7 +114,7 @@ void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth)
 					break;
 				first_frame = 0;
 			}
-
+			pagefault_enable();
 			return;
 		}
 #endif
@@ -124,5 +125,6 @@ void op_powerpc_backtrace(struct pt_regs * const regs, unsigned int depth)
 				break;
 			first_frame = 0;
 		}
+		pagefault_enable();
 	}
 }
diff --git a/arch/powerpc/platforms/powernv/eeh-ioda.c b/arch/powerpc/platforms/powernv/eeh-ioda.c
index db3803e21483..2809c9895288 100644
--- a/arch/powerpc/platforms/powernv/eeh-ioda.c
+++ b/arch/powerpc/platforms/powernv/eeh-ioda.c
@@ -353,6 +353,9 @@ static int ioda_eeh_get_phb_state(struct eeh_pe *pe)
 	} else if (!(pe->state & EEH_PE_ISOLATED)) {
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
@@ -372,7 +375,7 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 	 * moving forward, we have to return operational
 	 * state during PE reset.
 	 */
-	if (pe->state & EEH_PE_CFG_BLOCKED) {
+	if (pe->state & EEH_PE_RESET) {
 		result = (EEH_STATE_MMIO_ACTIVE  |
 			  EEH_STATE_DMA_ACTIVE   |
 			  EEH_STATE_MMIO_ENABLED |
@@ -451,6 +454,9 @@ static int ioda_eeh_get_pe_state(struct eeh_pe *pe)
 
 		eeh_pe_state_mark(pe, EEH_PE_ISOLATED);
 		ioda_eeh_phb_diag(pe);
+
+		if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+			pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 	}
 
 	return result;
@@ -730,7 +736,8 @@ static int ioda_eeh_reset(struct eeh_pe *pe, int option)
 static int ioda_eeh_get_log(struct eeh_pe *pe, int severity,
 			    char *drv_log, unsigned long len)
 {
-	pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
+	if (!eeh_has_flag(EEH_EARLY_DUMP_LOG))
+		pnv_pci_dump_phb_diag_data(pe->phb, pe->data);
 
 	return 0;
 }
@@ -1086,6 +1093,10 @@ static int ioda_eeh_next_error(struct eeh_pe **pe)
 		    !((*pe)->state & EEH_PE_ISOLATED)) {
 			eeh_pe_state_mark(*pe, EEH_PE_ISOLATED);
 			ioda_eeh_phb_diag(*pe);
+
+			if (eeh_has_flag(EEH_EARLY_DUMP_LOG))
+				pnv_pci_dump_phb_diag_data((*pe)->phb,
+							   (*pe)->data);
 		}
 
 		/*
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index a1c37f9d60d2..cb0b6de79cd4 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -50,7 +50,6 @@ static int mc_recoverable_range_len;
 
 struct device_node *opal_node;
 static DEFINE_SPINLOCK(opal_write_lock);
-extern u64 opal_mc_secondary_handler[];
 static unsigned int *opal_irqs;
 static unsigned int opal_irq_count;
 static ATOMIC_NOTIFIER_HEAD(opal_notifier_head);
diff --git a/arch/powerpc/platforms/pseries/lpar.c b/arch/powerpc/platforms/pseries/lpar.c
index d214a012b026..832f221840f2 100644
--- a/arch/powerpc/platforms/pseries/lpar.c
+++ b/arch/powerpc/platforms/pseries/lpar.c
@@ -442,7 +442,7 @@ static void __pSeries_lpar_hugepage_invalidate(unsigned long *slot,
 static void pSeries_lpar_hugepage_invalidate(unsigned long vsid,
 					     unsigned long addr,
 					     unsigned char *hpte_slot_array,
-					     int psize, int ssize)
+					     int psize, int ssize, int local)
 {
 	int i, index = 0;
 	unsigned long s_addr = addr;