Merge tag 'v3.10' into sched/core

Merge in a recent upstream commit:

  c2853c8df57f include/linux/math64.h: add div64_ul()

because:

  72a4cf20cb71 sched: Change cfs_rq load avg to unsigned long

relies on it.

[ We don't rebase sched/core for this, because the handful of
  followup commits after the broken commit are not behavioral
  changes so are unlikely to be needed during bisection. ]

Signed-off-by: Ingo Molnar <mingo@kernel.org>

41 files changed, 371 insertions, 270 deletions

diff --git a/arch/powerpc/include/asm/cputable.h b/arch/powerpc/include/asm/cputable.h
index 26807e5aff51..6f3887d884d2 100644
--- a/arch/powerpc/include/asm/cputable.h
+++ b/arch/powerpc/include/asm/cputable.h
@@ -176,6 +176,7 @@ extern const char *powerpc_base_platform;
 #define CPU_FTR_CFAR			LONG_ASM_CONST(0x0100000000000000)
 #define	CPU_FTR_HAS_PPR			LONG_ASM_CONST(0x0200000000000000)
 #define CPU_FTR_DAWR			LONG_ASM_CONST(0x0400000000000000)
+#define CPU_FTR_DABRX			LONG_ASM_CONST(0x0800000000000000)
 
 #ifndef __ASSEMBLY__
 
@@ -394,19 +395,20 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_201 | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_CAN_NAP | CPU_FTR_MMCRA | \
 	    CPU_FTR_CP_USE_DCBTZ | CPU_FTR_STCX_CHECKS_ADDRESS | \
-	    CPU_FTR_HVMODE)
+	    CPU_FTR_HVMODE | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER5	(CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | CPU_FTR_PURR | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER6 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_COHERENT_ICACHE | \
 	    CPU_FTR_PURR | CPU_FTR_SPURR | CPU_FTR_REAL_LE | \
 	    CPU_FTR_DSCR | CPU_FTR_UNALIGNED_LD_STD | \
-	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR)
+	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_CFAR | \
+	    CPU_FTR_DABRX)
 #define CPU_FTRS_POWER7 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -415,7 +417,7 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_DSCR | CPU_FTR_SAO  | CPU_FTR_ASYM_SMT | \
 	    CPU_FTR_STCX_CHECKS_ADDRESS | CPU_FTR_POPCNTB | CPU_FTR_POPCNTD | \
 	    CPU_FTR_ICSWX | CPU_FTR_CFAR | CPU_FTR_HVMODE | \
-	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR)
+	    CPU_FTR_VMX_COPY | CPU_FTR_HAS_PPR | CPU_FTR_DABRX)
 #define CPU_FTRS_POWER8 (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | CPU_FTR_ARCH_206 |\
 	    CPU_FTR_MMCRA | CPU_FTR_SMT | \
@@ -430,14 +432,15 @@ extern const char *powerpc_base_platform;
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_CTRL | \
 	    CPU_FTR_ALTIVEC_COMP | CPU_FTR_MMCRA | CPU_FTR_SMT | \
 	    CPU_FTR_PAUSE_ZERO  | CPU_FTR_CELL_TB_BUG | CPU_FTR_CP_USE_DCBTZ | \
-	    CPU_FTR_UNALIGNED_LD_STD)
+	    CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_DABRX)
 #define CPU_FTRS_PA6T (CPU_FTR_USE_TB | CPU_FTR_LWSYNC | \
 	    CPU_FTR_PPCAS_ARCH_V2 | CPU_FTR_ALTIVEC_COMP | \
-	    CPU_FTR_PURR | CPU_FTR_REAL_LE)
+	    CPU_FTR_PURR | CPU_FTR_REAL_LE | CPU_FTR_DABRX)
 #define CPU_FTRS_COMPATIBLE	(CPU_FTR_USE_TB | CPU_FTR_PPCAS_ARCH_V2)
 
 #define CPU_FTRS_A2 (CPU_FTR_USE_TB | CPU_FTR_SMT | CPU_FTR_DBELL | \
-		     CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | CPU_FTR_ICSWX)
+		     CPU_FTR_NOEXECUTE | CPU_FTR_NODSISRALIGN | \
+		     CPU_FTR_ICSWX | CPU_FTR_DABRX )
 
 #ifdef __powerpc64__
 #ifdef CONFIG_PPC_BOOK3E
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 8e5fae8beaf6..46793b58a761 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -513,7 +513,7 @@ label##_common:							\
  */
 #define STD_EXCEPTION_COMMON_ASYNC(trap, label, hdlr)		  \
 	EXCEPTION_COMMON(trap, label, hdlr, ret_from_except_lite, \
-			 FINISH_NAP;RUNLATCH_ON;DISABLE_INTS)
+			 FINISH_NAP;DISABLE_INTS;RUNLATCH_ON)
 
 /*
  * When the idle code in power4_idle puts the CPU into NAP mode,
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index cf4df8e2139a..0c7f2bfcf134 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -264,6 +264,7 @@
 #define H_GET_MPP		0x2D4
 #define H_HOME_NODE_ASSOCIATIVITY 0x2EC
 #define H_BEST_ENERGY		0x2F4
+#define H_XIRR_X		0x2FC
 #define H_RANDOM		0x300
 #define H_COP			0x304
 #define H_GET_MPP_X		0x314
diff --git a/arch/powerpc/include/asm/kvm_asm.h b/arch/powerpc/include/asm/kvm_asm.h
index b9dd382cb349..851bac7afa4b 100644
--- a/arch/powerpc/include/asm/kvm_asm.h
+++ b/arch/powerpc/include/asm/kvm_asm.h
@@ -54,8 +54,16 @@
 #define BOOKE_INTERRUPT_DEBUG 15
 
 /* E500 */
-#define BOOKE_INTERRUPT_SPE_UNAVAIL 32
-#define BOOKE_INTERRUPT_SPE_FP_DATA 33
+#define BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL 32
+#define BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST 33
+/*
+ * TODO: Unify 32-bit and 64-bit kernel exception handlers to use same defines
+ */
+#define BOOKE_INTERRUPT_SPE_UNAVAIL BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL
+#define BOOKE_INTERRUPT_SPE_FP_DATA BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST
+#define BOOKE_INTERRUPT_ALTIVEC_UNAVAIL BOOKE_INTERRUPT_SPE_ALTIVEC_UNAVAIL
+#define BOOKE_INTERRUPT_ALTIVEC_ASSIST \
+				BOOKE_INTERRUPT_SPE_FP_DATA_ALTIVEC_ASSIST
 #define BOOKE_INTERRUPT_SPE_FP_ROUND 34
 #define BOOKE_INTERRUPT_PERFORMANCE_MONITOR 35
 #define BOOKE_INTERRUPT_DOORBELL 36
@@ -67,10 +75,6 @@
 #define BOOKE_INTERRUPT_HV_SYSCALL 40
 #define BOOKE_INTERRUPT_HV_PRIV 41
 
-/* altivec */
-#define BOOKE_INTERRUPT_ALTIVEC_UNAVAIL 42
-#define BOOKE_INTERRUPT_ALTIVEC_ASSIST 43
-
 /* book3s */
 
 #define BOOK3S_INTERRUPT_SYSTEM_RESET	0x100
diff --git a/arch/powerpc/include/asm/ppc_asm.h b/arch/powerpc/include/asm/ppc_asm.h
index cea8496091ff..2f1b6c5f8174 100644
--- a/arch/powerpc/include/asm/ppc_asm.h
+++ b/arch/powerpc/include/asm/ppc_asm.h
@@ -523,6 +523,17 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946)
 #define PPC440EP_ERR42
 #endif
 
+/* The following stops all load and store data streams associated with stream
+ * ID (ie. streams created explicitly).  The embedded and server mnemonics for
+ * dcbt are different so we use machine "power4" here explicitly.
+ */
+#define DCBT_STOP_ALL_STREAM_IDS(scratch)	\
+.machine push ;					\
+.machine "power4" ;				\
+       lis     scratch,0x60000000@h;		\
+       dcbt    r0,scratch,0b01010;		\
+.machine pop
+
 /*
  * toreal/fromreal/tophys/tovirt macros. 32-bit BookE makes them
  * keep the address intact to be compatible with code shared with
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 594db6bc093c..14a658363698 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -409,21 +409,16 @@ static inline void prefetchw(const void *x)
 #endif
 
 #ifdef CONFIG_PPC64
-static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32)
+static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 {
-	unsigned long sp;
-
 	if (is_32)
-		sp = regs->gpr[1] & 0x0ffffffffUL;
-	else
-		sp = regs->gpr[1];
-
+		return sp & 0x0ffffffffUL;
 	return sp;
 }
 #else
-static inline unsigned long get_clean_sp(struct pt_regs *regs, int is_32)
+static inline unsigned long get_clean_sp(unsigned long sp, int is_32)
 {
-	return regs->gpr[1];
+	return sp;
 }
 #endif
 
diff --git a/arch/powerpc/include/asm/reg.h b/arch/powerpc/include/asm/reg.h
index a6136515c7f2..4a9e408644fe 100644
--- a/arch/powerpc/include/asm/reg.h
+++ b/arch/powerpc/include/asm/reg.h
@@ -111,17 +111,6 @@
 #define MSR_TM_TRANSACTIONAL(x)	(((x) & MSR_TS_MASK) == MSR_TS_T)
 #define MSR_TM_SUSPENDED(x)	(((x) & MSR_TS_MASK) == MSR_TS_S)
 
-/* Reason codes describing kernel causes for transaction aborts.  By
-   convention, bit0 is copied to TEXASR[56] (IBM bit 7) which is set if
-   the failure is persistent.
-*/
-#define TM_CAUSE_RESCHED	0xfe
-#define TM_CAUSE_TLBI		0xfc
-#define TM_CAUSE_FAC_UNAV	0xfa
-#define TM_CAUSE_SYSCALL	0xf9 /* Persistent */
-#define TM_CAUSE_MISC		0xf6
-#define TM_CAUSE_SIGNAL		0xf4
-
 #if defined(CONFIG_PPC_BOOK3S_64)
 #define MSR_64BIT	MSR_SF
 
diff --git a/arch/powerpc/include/asm/signal.h b/arch/powerpc/include/asm/signal.h
index fbe66c463891..9322c28aebd2 100644
--- a/arch/powerpc/include/asm/signal.h
+++ b/arch/powerpc/include/asm/signal.h
@@ -3,5 +3,8 @@
 
 #define __ARCH_HAS_SA_RESTORER
 #include <uapi/asm/signal.h>
+#include <uapi/asm/ptrace.h>
+
+extern unsigned long get_tm_stackpointer(struct pt_regs *regs);
 
 #endif /* _ASM_POWERPC_SIGNAL_H */
diff --git a/arch/powerpc/include/asm/tm.h b/arch/powerpc/include/asm/tm.h
index 4b4449abf3f8..9dfbc34bdbf5 100644
--- a/arch/powerpc/include/asm/tm.h
+++ b/arch/powerpc/include/asm/tm.h
@@ -5,6 +5,8 @@
  * Copyright 2012 Matt Evans & Michael Neuling, IBM Corporation.
  */
 
+#include <uapi/asm/tm.h>
+
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 extern void do_load_up_transact_fpu(struct thread_struct *thread);
 extern void do_load_up_transact_altivec(struct thread_struct *thread);
diff --git a/arch/powerpc/include/uapi/asm/Kbuild b/arch/powerpc/include/uapi/asm/Kbuild
index f7bca6370745..5182c8622b54 100644
--- a/arch/powerpc/include/uapi/asm/Kbuild
+++ b/arch/powerpc/include/uapi/asm/Kbuild
@@ -40,6 +40,7 @@ header-y += statfs.h
 header-y += swab.h
 header-y += termbits.h
 header-y += termios.h
+header-y += tm.h
 header-y += types.h
 header-y += ucontext.h
 header-y += unistd.h
diff --git a/arch/powerpc/include/uapi/asm/tm.h b/arch/powerpc/include/uapi/asm/tm.h
new file mode 100644
index 000000000000..85059a00f560
--- /dev/null
+++ b/arch/powerpc/include/uapi/asm/tm.h
@@ -0,0 +1,18 @@
+#ifndef _ASM_POWERPC_TM_H
+#define _ASM_POWERPC_TM_H
+
+/* Reason codes describing kernel causes for transaction aborts.  By
+ * convention, bit0 is copied to TEXASR[56] (IBM bit 7) which is set if
+ * the failure is persistent.  PAPR saves 0xff-0xe0 for the hypervisor.
+ */
+#define TM_CAUSE_PERSISTENT	0x01
+#define TM_CAUSE_RESCHED	0xde
+#define TM_CAUSE_TLBI		0xdc
+#define TM_CAUSE_FAC_UNAV	0xda
+#define TM_CAUSE_SYSCALL	0xd8  /* future use */
+#define TM_CAUSE_MISC		0xd6  /* future use */
+#define TM_CAUSE_SIGNAL		0xd4
+#define TM_CAUSE_ALIGNMENT	0xd2
+#define TM_CAUSE_EMULATE	0xd0
+
+#endif
diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c
index c60bbec25c1f..2a45d0f04385 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -452,7 +452,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.mmu_features		= MMU_FTRS_POWER8,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
-		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
@@ -482,7 +482,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.cpu_name		= "POWER7+ (raw)",
 		.cpu_features		= CPU_FTRS_POWER7,
 		.cpu_user_features	= COMMON_USER_POWER7,
-		.cpu_user_features	= COMMON_USER2_POWER7,
+		.cpu_user_features2	= COMMON_USER2_POWER7,
 		.mmu_features		= MMU_FTRS_POWER7,
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
@@ -507,7 +507,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.num_pmcs		= 6,
 		.pmc_type		= PPC_PMC_IBM,
 		.oprofile_cpu_type	= "ppc64/power8",
-		.oprofile_type		= PPC_OPROFILE_POWER4,
+		.oprofile_type		= PPC_OPROFILE_INVALID,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
 		.platform		= "power8",
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index d22e73e4618b..22b45a4955cd 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -849,7 +849,7 @@ resume_kernel:
 	/* check current_thread_info, _TIF_EMULATE_STACK_STORE */
 	CURRENT_THREAD_INFO(r9, r1)
 	lwz	r8,TI_FLAGS(r9)
-	andis.	r8,r8,_TIF_EMULATE_STACK_STORE@h
+	andis.	r0,r8,_TIF_EMULATE_STACK_STORE@h
 	beq+	1f
 
 	addi	r8,r1,INT_FRAME_SIZE	/* Get the kprobed function entry */
diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S
index 0e9095e47b5b..8741c854e03d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -465,20 +465,6 @@ BEGIN_FTR_SECTION
 	std	r0, THREAD_EBBHR(r3)
 	mfspr	r0, SPRN_EBBRR
 	std	r0, THREAD_EBBRR(r3)
-
-	/* PMU registers made user read/(write) by EBB */
-	mfspr	r0, SPRN_SIAR
-	std	r0, THREAD_SIAR(r3)
-	mfspr	r0, SPRN_SDAR
-	std	r0, THREAD_SDAR(r3)
-	mfspr	r0, SPRN_SIER
-	std	r0, THREAD_SIER(r3)
-	mfspr	r0, SPRN_MMCR0
-	std	r0, THREAD_MMCR0(r3)
-	mfspr	r0, SPRN_MMCR2
-	std	r0, THREAD_MMCR2(r3)
-	mfspr	r0, SPRN_MMCRA
-	std	r0, THREAD_MMCRA(r3)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 #endif
 
@@ -501,6 +487,13 @@ BEGIN_FTR_SECTION
 	ldarx	r6,0,r1
 END_FTR_SECTION_IFSET(CPU_FTR_STCX_CHECKS_ADDRESS)
 
+#ifdef CONFIG_PPC_BOOK3S
+/* Cancel all explict user streams as they will have no use after context
+ * switch and will stop the HW from creating streams itself
+ */
+	DCBT_STOP_ALL_STREAM_IDS(r6)
+#endif
+
 	addi	r6,r4,-THREAD	/* Convert THREAD to 'current' */
 	std	r6,PACACURRENT(r13)	/* Set new 'current' */
 
@@ -574,20 +567,6 @@ BEGIN_FTR_SECTION
 	ld	r0, THREAD_EBBRR(r4)
 	mtspr	SPRN_EBBRR, r0
 
-	/* PMU registers made user read/(write) by EBB */
-	ld	r0, THREAD_SIAR(r4)
-	mtspr	SPRN_SIAR, r0
-	ld	r0, THREAD_SDAR(r4)
-	mtspr	SPRN_SDAR, r0
-	ld	r0, THREAD_SIER(r4)
-	mtspr	SPRN_SIER, r0
-	ld	r0, THREAD_MMCR0(r4)
-	mtspr	SPRN_MMCR0, r0
-	ld	r0, THREAD_MMCR2(r4)
-	mtspr	SPRN_MMCR2, r0
-	ld	r0, THREAD_MMCRA(r4)
-	mtspr	SPRN_MMCRA, r0
-
 	ld	r0,THREAD_TAR(r4)
 	mtspr	SPRN_TAR,r0
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index e6eba1bf61ad..40e4a17c8ba0 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -454,38 +454,14 @@ BEGIN_FTR_SECTION
 	xori	r10,r10,(MSR_FE0|MSR_FE1)
 	mtmsrd	r10
 	sync
-	fmr	0,0
-	fmr	1,1
-	fmr	2,2
-	fmr	3,3
-	fmr	4,4
-	fmr	5,5
-	fmr	6,6
-	fmr	7,7
-	fmr	8,8
-	fmr	9,9
-	fmr	10,10
-	fmr	11,11
-	fmr	12,12
-	fmr	13,13
-	fmr	14,14
-	fmr	15,15
-	fmr	16,16
-	fmr	17,17
-	fmr	18,18
-	fmr	19,19
-	fmr	20,20
-	fmr	21,21
-	fmr	22,22
-	fmr	23,23
-	fmr	24,24
-	fmr	25,25
-	fmr	26,26
-	fmr	27,27
-	fmr	28,28
-	fmr	29,29
-	fmr	30,30
-	fmr	31,31
+
+#define FMR2(n)  fmr (n), (n) ; fmr n+1, n+1
+#define FMR4(n)  FMR2(n) ; FMR2(n+2)
+#define FMR8(n)  FMR4(n) ; FMR4(n+4)
+#define FMR16(n) FMR8(n) ; FMR8(n+8)
+#define FMR32(n) FMR16(n) ; FMR16(n+16)
+	FMR32(0)
+
 FTR_SECTION_ELSE
 /*
  * To denormalise we need to move a copy of the register to itself.
@@ -495,39 +471,25 @@ FTR_SECTION_ELSE
 	oris	r10,r10,MSR_VSX@h
 	mtmsrd	r10
 	sync
-	XVCPSGNDP(0,0,0)
-	XVCPSGNDP(1,1,1)
-	XVCPSGNDP(2,2,2)
-	XVCPSGNDP(3,3,3)
-	XVCPSGNDP(4,4,4)
-	XVCPSGNDP(5,5,5)
-	XVCPSGNDP(6,6,6)
-	XVCPSGNDP(7,7,7)
-	XVCPSGNDP(8,8,8)
-	XVCPSGNDP(9,9,9)
-	XVCPSGNDP(10,10,10)
-	XVCPSGNDP(11,11,11)
-	XVCPSGNDP(12,12,12)
-	XVCPSGNDP(13,13,13)
-	XVCPSGNDP(14,14,14)
-	XVCPSGNDP(15,15,15)
-	XVCPSGNDP(16,16,16)
-	XVCPSGNDP(17,17,17)
-	XVCPSGNDP(18,18,18)
-	XVCPSGNDP(19,19,19)
-	XVCPSGNDP(20,20,20)
-	XVCPSGNDP(21,21,21)
-	XVCPSGNDP(22,22,22)
-	XVCPSGNDP(23,23,23)
-	XVCPSGNDP(24,24,24)
-	XVCPSGNDP(25,25,25)
-	XVCPSGNDP(26,26,26)
-	XVCPSGNDP(27,27,27)
-	XVCPSGNDP(28,28,28)
-	XVCPSGNDP(29,29,29)
-	XVCPSGNDP(30,30,30)
-	XVCPSGNDP(31,31,31)
+
+#define XVCPSGNDP2(n) XVCPSGNDP(n,n,n) ; XVCPSGNDP(n+1,n+1,n+1)
+#define XVCPSGNDP4(n) XVCPSGNDP2(n) ; XVCPSGNDP2(n+2)
+#define XVCPSGNDP8(n) XVCPSGNDP4(n) ; XVCPSGNDP4(n+4)
+#define XVCPSGNDP16(n) XVCPSGNDP8(n) ; XVCPSGNDP8(n+8)
+#define XVCPSGNDP32(n) XVCPSGNDP16(n) ; XVCPSGNDP16(n+16)
+	XVCPSGNDP32(0)
+
 ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_206)
+
+BEGIN_FTR_SECTION
+	b	denorm_done
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_207S)
+/*
+ * To denormalise we need to move a copy of the register to itself.
+ * For POWER8 we need to do that for all 64 VSX registers
+ */
+	XVCPSGNDP32(32)
+denorm_done:
 	mtspr	SPRN_HSRR0,r11
 	mtcrf	0x80,r9
 	ld	r9,PACA_EXGEN+EX_R9(r13)
@@ -721,7 +683,7 @@ machine_check_common:
 	STD_EXCEPTION_COMMON(0xb00, trap_0b, .unknown_exception)
 	STD_EXCEPTION_COMMON(0xd00, single_step, .single_step_exception)
 	STD_EXCEPTION_COMMON(0xe00, trap_0e, .unknown_exception)
-	STD_EXCEPTION_COMMON(0xe40, emulation_assist, .program_check_exception)
+	STD_EXCEPTION_COMMON(0xe40, emulation_assist, .emulation_assist_interrupt)
 	STD_EXCEPTION_COMMON(0xe60, hmi_exception, .unknown_exception)
 #ifdef CONFIG_PPC_DOORBELL
 	STD_EXCEPTION_COMMON_ASYNC(0xe80, h_doorbell, .doorbell_exception)
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 5cbcf4d5a808..ea185e0b3cae 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -162,7 +162,7 @@ notrace unsigned int __check_irq_replay(void)
 	 * in case we also had a rollover while hard disabled
 	 */
 	local_paca->irq_happened &= ~PACA_IRQ_DEC;
-	if (decrementer_check_overflow())
+	if ((happened & PACA_IRQ_DEC) || decrementer_check_overflow())
 		return 0x900;
 
 	/* Finally check if an external interrupt happened */
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index e9acf50dd5b2..f46914a0f33e 100644
--- a/arch/powerpc/kernel/pci-common.c
+++ b/arch/powerpc/kernel/pci-common.c
@@ -657,15 +657,6 @@ void pci_resource_to_user(const struct pci_dev *dev, int bar,
  *     ranges. However, some machines (thanks Apple !) tend to split their
  *     space into lots of small contiguous ranges. So we have to coalesce.
  *
- *   - We can only cope with all memory ranges having the same offset
- *     between CPU addresses and PCI addresses. Unfortunately, some bridges
- *     are setup for a large 1:1 mapping along with a small "window" which
- *     maps PCI address 0 to some arbitrary high address of the CPU space in
- *     order to give access to the ISA memory hole.
- *     The way out of here that I've chosen for now is to always set the
- *     offset based on the first resource found, then override it if we
- *     have a different offset and the previous was set by an ISA hole.
- *
  *   - Some busses have IO space not starting at 0, which causes trouble with
  *     the way we do our IO resource renumbering. The code somewhat deals with
  *     it for 64 bits but I would expect problems on 32 bits.
@@ -680,10 +671,9 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 	int rlen;
 	int pna = of_n_addr_cells(dev);
 	int np = pna + 5;
-	int memno = 0, isa_hole = -1;
+	int memno = 0;
 	u32 pci_space;
 	unsigned long long pci_addr, cpu_addr, pci_next, cpu_next, size;
-	unsigned long long isa_mb = 0;
 	struct resource *res;
 
 	printk(KERN_INFO "PCI host bridge %s %s ranges:\n",
@@ -777,8 +767,6 @@ void pci_process_bridge_OF_ranges(struct pci_controller *hose,
 			}
 			/* Handles ISA memory hole space here */
 			if (pci_addr == 0) {
-				isa_mb = cpu_addr;
-				isa_hole = memno;
 				if (primary || isa_mem_base == 0)
 					isa_mem_base = cpu_addr;
 				hose->isa_mem_phys = cpu_addr;
@@ -839,6 +827,7 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 	}
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
 		struct resource *res = dev->resource + i;
+		struct pci_bus_region reg;
 		if (!res->flags)
 			continue;
 
@@ -847,8 +836,9 @@ static void pcibios_fixup_resources(struct pci_dev *dev)
 		 * at 0 as unset as well, except if PCI_PROBE_ONLY is also set
 		 * since in that case, we don't want to re-assign anything
 		 */
+		pcibios_resource_to_bus(dev, &reg, res);
 		if (pci_has_flag(PCI_REASSIGN_ALL_RSRC) ||
-		    (res->start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
+		    (reg.start == 0 && !pci_has_flag(PCI_PROBE_ONLY))) {
 			/* Only print message if not re-assigning */
 			if (!pci_has_flag(PCI_REASSIGN_ALL_RSRC))
 				pr_debug("PCI:%s Resource %d %016llx-%016llx [%x] "
@@ -1004,7 +994,7 @@ void pcibios_setup_bus_self(struct pci_bus *bus)
 		ppc_md.pci_dma_bus_setup(bus);
 }
 
-void pcibios_setup_device(struct pci_dev *dev)
+static void pcibios_setup_device(struct pci_dev *dev)
 {
 	/* Fixup NUMA node as it may not be setup yet by the generic
 	 * code and is needed by the DMA init
@@ -1025,6 +1015,17 @@ void pcibios_setup_device(struct pci_dev *dev)
 		ppc_md.pci_irq_fixup(dev);
 }
 
+int pcibios_add_device(struct pci_dev *dev)
+{
+	/*
+	 * We can only call pcibios_setup_device() after bus setup is complete,
+	 * since some of the platform specific DMA setup code depends on it.
+	 */
+	if (dev->bus->is_added)
+		pcibios_setup_device(dev);
+	return 0;
+}
+
 void pcibios_setup_bus_devices(struct pci_bus *bus)
 {
 	struct pci_dev *dev;
@@ -1479,10 +1480,6 @@ int pcibios_enable_device(struct pci_dev *dev, int mask)
 		if (ppc_md.pcibios_enable_device_hook(dev))
 			return -EINVAL;
 
-	/* avoid pcie irq fix up impact on cardbus */
-	if (dev->hdr_type != PCI_HEADER_TYPE_CARDBUS)
-		pcibios_setup_device(dev);
-
 	return pci_enable_resources(dev, mask);
 }
 
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index a902723fdc69..076d1242507a 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -399,7 +399,8 @@ static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 static inline int __set_dabr(unsigned long dabr, unsigned long dabrx)
 {
 	mtspr(SPRN_DABR, dabr);
-	mtspr(SPRN_DABRX, dabrx);
+	if (cpu_has_feature(CPU_FTR_DABRX))
+		mtspr(SPRN_DABRX, dabrx);
 	return 0;
 }
 #else
@@ -1368,7 +1369,7 @@ void show_stack(struct task_struct *tsk, unsigned long *stack)
 
 #ifdef CONFIG_PPC64
 /* Called with hard IRQs off */
-void __ppc64_runlatch_on(void)
+void notrace __ppc64_runlatch_on(void)
 {
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
@@ -1381,7 +1382,7 @@ void __ppc64_runlatch_on(void)
 }
 
 /* Called with hard IRQs off */
-void __ppc64_runlatch_off(void)
+void notrace __ppc64_runlatch_off(void)
 {
 	struct thread_info *ti = current_thread_info();
 	unsigned long ctrl;
diff --git a/arch/powerpc/kernel/signal.c b/arch/powerpc/kernel/signal.c
index 577a8aa69c6e..457e97aa2945 100644
--- a/arch/powerpc/kernel/signal.c
+++ b/arch/powerpc/kernel/signal.c
@@ -18,6 +18,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/debug.h>
+#include <asm/tm.h>
 
 #include "signal.h"
 
@@ -30,13 +31,13 @@ int show_unhandled_signals = 1;
 /*
  * Allocate space for the signal frame
  */
-void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp,
 			   size_t frame_size, int is_32)
 {
         unsigned long oldsp, newsp;
 
         /* Default to using normal stack */
-        oldsp = get_clean_sp(regs, is_32);
+        oldsp = get_clean_sp(sp, is_32);
 
 	/* Check for alt stack */
 	if ((ka->sa.sa_flags & SA_ONSTACK) &&
@@ -175,3 +176,38 @@ void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags)
 
 	user_enter();
 }
+
+unsigned long get_tm_stackpointer(struct pt_regs *regs)
+{
+	/* When in an active transaction that takes a signal, we need to be
+	 * careful with the stack.  It's possible that the stack has moved back
+	 * up after the tbegin.  The obvious case here is when the tbegin is
+	 * called inside a function that returns before a tend.  In this case,
+	 * the stack is part of the checkpointed transactional memory state.
+	 * If we write over this non transactionally or in suspend, we are in
+	 * trouble because if we get a tm abort, the program counter and stack
+	 * pointer will be back at the tbegin but our in memory stack won't be
+	 * valid anymore.
+	 *
+	 * To avoid this, when taking a signal in an active transaction, we
+	 * need to use the stack pointer from the checkpointed state, rather
+	 * than the speculated state.  This ensures that the signal context
+	 * (written tm suspended) will be written below the stack required for
+	 * the rollback.  The transaction is aborted becuase of the treclaim,
+	 * so any memory written between the tbegin and the signal will be
+	 * rolled back anyway.
+	 *
+	 * For signals taken in non-TM or suspended mode, we use the
+	 * normal/non-checkpointed stack pointer.
+	 */
+
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (MSR_TM_ACTIVE(regs->msr)) {
+		tm_enable();
+		tm_reclaim(&current->thread, regs->msr, TM_CAUSE_SIGNAL);
+		if (MSR_TM_TRANSACTIONAL(regs->msr))
+			return current->thread.ckpt_regs.gpr[1];
+	}
+#endif
+	return regs->gpr[1];
+}
diff --git a/arch/powerpc/kernel/signal.h b/arch/powerpc/kernel/signal.h
index ec84c901ceab..c69b9aeb9f23 100644
--- a/arch/powerpc/kernel/signal.h
+++ b/arch/powerpc/kernel/signal.h
@@ -12,7 +12,7 @@
 
 extern void do_notify_resume(struct pt_regs *regs, unsigned long thread_info_flags);
 
-extern void __user * get_sigframe(struct k_sigaction *ka, struct pt_regs *regs,
+extern void __user * get_sigframe(struct k_sigaction *ka, unsigned long sp,
 				  size_t frame_size, int is_32);
 
 extern int handle_signal32(unsigned long sig, struct k_sigaction *ka,
diff --git a/arch/powerpc/kernel/signal_32.c b/arch/powerpc/kernel/signal_32.c
index 95068bf569ad..201385c3a1ae 100644
--- a/arch/powerpc/kernel/signal_32.c
+++ b/arch/powerpc/kernel/signal_32.c
@@ -503,12 +503,6 @@ static int save_tm_user_regs(struct pt_regs *regs,
 {
 	unsigned long msr = regs->msr;
 
-	/* tm_reclaim rolls back all reg states, updating thread.ckpt_regs,
-	 * thread.transact_fpr[], thread.transact_vr[], etc.
-	 */
-	tm_enable();
-	tm_reclaim(&current->thread, msr, TM_CAUSE_SIGNAL);
-
 	/* Make sure floating point registers are stored in regs */
 	flush_fp_to_thread(current);
 
@@ -965,7 +959,7 @@ int handle_rt_signal32(unsigned long sig, struct k_sigaction *ka,
 
 	/* Set up Signal Frame */
 	/* Put a Real Time Context onto stack */
-	rt_sf = get_sigframe(ka, regs, sizeof(*rt_sf), 1);
+	rt_sf = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*rt_sf), 1);
 	addr = rt_sf;
 	if (unlikely(rt_sf == NULL))
 		goto badframe;
@@ -1403,7 +1397,7 @@ int handle_signal32(unsigned long sig, struct k_sigaction *ka,
 	unsigned long tramp;
 
 	/* Set up Signal Frame */
-	frame = get_sigframe(ka, regs, sizeof(*frame), 1);
+	frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 1);
 	if (unlikely(frame == NULL))
 		goto badframe;
 	sc = (struct sigcontext __user *) &frame->sctx;
diff --git a/arch/powerpc/kernel/signal_64.c b/arch/powerpc/kernel/signal_64.c
index c1794286098c..345947367ec0 100644
--- a/arch/powerpc/kernel/signal_64.c
+++ b/arch/powerpc/kernel/signal_64.c
@@ -154,11 +154,12 @@ static long setup_sigcontext(struct sigcontext __user *sc, struct pt_regs *regs,
  * As above, but Transactional Memory is in use, so deliver sigcontexts
  * containing checkpointed and transactional register states.
  *
- * To do this, we treclaim to gather both sets of registers and set up the
- * 'normal' sigcontext registers with rolled-back register values such that a
- * simple signal handler sees a correct checkpointed register state.
- * If interested, a TM-aware sighandler can examine the transactional registers
- * in the 2nd sigcontext to determine the real origin of the signal.
+ * To do this, we treclaim (done before entering here) to gather both sets of
+ * registers and set up the 'normal' sigcontext registers with rolled-back
+ * register values such that a simple signal handler sees a correct
+ * checkpointed register state.  If interested, a TM-aware sighandler can
+ * examine the transactional registers in the 2nd sigcontext to determine the
+ * real origin of the signal.
  */
 static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 				 struct sigcontext __user *tm_sc,
@@ -184,16 +185,6 @@ static long setup_tm_sigcontexts(struct sigcontext __user *sc,
 
 	BUG_ON(!MSR_TM_ACTIVE(regs->msr));
 
-	/* tm_reclaim rolls back all reg states, saving checkpointed (older)
-	 * GPRs to thread.ckpt_regs and (if used) FPRs to (newer)
-	 * thread.transact_fp and/or VRs to (newer) thread.transact_vr.
-	 * THEN we save out FP/VRs, if necessary, to the checkpointed (older)
-	 * thread.fr[]/vr[]s.  The transactional (newer) GPRs are on the
-	 * stack, in *regs.
-	 */
-	tm_enable();
-	tm_reclaim(&current->thread, msr, TM_CAUSE_SIGNAL);
-
 	flush_fp_to_thread(current);
 
 #ifdef CONFIG_ALTIVEC
@@ -711,7 +702,7 @@ int handle_rt_signal64(int signr, struct k_sigaction *ka, siginfo_t *info,
 	unsigned long newsp = 0;
 	long err = 0;
 
-	frame = get_sigframe(ka, regs, sizeof(*frame), 0);
+	frame = get_sigframe(ka, get_tm_stackpointer(regs), sizeof(*frame), 0);
 	if (unlikely(frame == NULL))
 		goto badframe;
 
diff --git a/arch/powerpc/kernel/traps.c b/arch/powerpc/kernel/traps.c
index a7a648f6b750..c0e5caf8ccc7 100644
--- a/arch/powerpc/kernel/traps.c
+++ b/arch/powerpc/kernel/traps.c
@@ -53,6 +53,7 @@
 #ifdef CONFIG_PPC64
 #include <asm/firmware.h>
 #include <asm/processor.h>
+#include <asm/tm.h>
 #endif
 #include <asm/kexec.h>
 #include <asm/ppc-opcode.h>
@@ -932,6 +933,28 @@ static int emulate_isel(struct pt_regs *regs, u32 instword)
 	return 0;
 }
 
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+static inline bool tm_abort_check(struct pt_regs *regs, int cause)
+{
+        /* If we're emulating a load/store in an active transaction, we cannot
+         * emulate it as the kernel operates in transaction suspended context.
+         * We need to abort the transaction.  This creates a persistent TM
+         * abort so tell the user what caused it with a new code.
+	 */
+	if (MSR_TM_TRANSACTIONAL(regs->msr)) {
+		tm_enable();
+		tm_abort(cause);
+		return true;
+	}
+	return false;
+}
+#else
+static inline bool tm_abort_check(struct pt_regs *regs, int reason)
+{
+	return false;
+}
+#endif
+
 static int emulate_instruction(struct pt_regs *regs)
 {
 	u32 instword;
@@ -971,6 +994,9 @@ static int emulate_instruction(struct pt_regs *regs)
 
 	/* Emulate load/store string insn. */
 	if ((instword & PPC_INST_STRING_GEN_MASK) == PPC_INST_STRING) {
+		if (tm_abort_check(regs,
+				   TM_CAUSE_EMULATE | TM_CAUSE_PERSISTENT))
+			return -EINVAL;
 		PPC_WARN_EMULATED(string, regs);
 		return emulate_string_inst(regs, instword);
 	}
@@ -1139,6 +1165,16 @@ bail:
 	exception_exit(prev_state);
 }
 
+/*
+ * This occurs when running in hypervisor mode on POWER6 or later
+ * and an illegal instruction is encountered.
+ */
+void __kprobes emulation_assist_interrupt(struct pt_regs *regs)
+{
+	regs->msr |= REASON_ILLEGAL;
+	program_check_exception(regs);
+}
+
 void alignment_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();
@@ -1148,6 +1184,9 @@ void alignment_exception(struct pt_regs *regs)
 	if (!arch_irq_disabled_regs(regs))
 		local_irq_enable();
 
+	if (tm_abort_check(regs, TM_CAUSE_ALIGNMENT | TM_CAUSE_PERSISTENT))
+		goto bail;
+
 	/* we don't implement logging of alignment exceptions */
 	if (!(current->thread.align_ctl & PR_UNALIGN_SIGBUS))
 		fixed = fix_alignment(regs);
diff --git a/arch/powerpc/kvm/44x_tlb.c b/arch/powerpc/kvm/44x_tlb.c
index 5dd3ab469976..ed0385448148 100644
--- a/arch/powerpc/kvm/44x_tlb.c
+++ b/arch/powerpc/kvm/44x_tlb.c
@@ -441,6 +441,7 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 	struct kvmppc_vcpu_44x *vcpu_44x = to_44x(vcpu);
 	struct kvmppc_44x_tlbe *tlbe;
 	unsigned int gtlb_index;
+	int idx;
 
 	gtlb_index = kvmppc_get_gpr(vcpu, ra);
 	if (gtlb_index >= KVM44x_GUEST_TLB_SIZE) {
@@ -473,6 +474,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		return EMULATE_FAIL;
 	}
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	if (tlbe_is_host_safe(vcpu, tlbe)) {
 		gva_t eaddr;
 		gpa_t gpaddr;
@@ -489,6 +492,8 @@ int kvmppc_44x_emul_tlbwe(struct kvm_vcpu *vcpu, u8 ra, u8 rs, u8 ws)
 		kvmppc_mmu_map(vcpu, eaddr, gpaddr, gtlb_index);
 	}
 
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
 	trace_kvm_gtlb_write(gtlb_index, tlbe->tid, tlbe->word0, tlbe->word1,
 			     tlbe->word2);
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 9de24f8e03c7..550f5928b394 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -562,6 +562,8 @@ int kvmppc_pseries_do_hcall(struct kvm_vcpu *vcpu)
 	case H_CPPR:
 	case H_EOI:
 	case H_IPI:
+	case H_IPOLL:
+	case H_XIRR_X:
 		if (kvmppc_xics_enabled(vcpu)) {
 			ret = kvmppc_xics_hcall(vcpu, req);
 			break;
diff --git a/arch/powerpc/kvm/book3s_pr_papr.c b/arch/powerpc/kvm/book3s_pr_papr.c
index b24309c6c2d5..da0e0bc268bd 100644
--- a/arch/powerpc/kvm/book3s_pr_papr.c
+++ b/arch/powerpc/kvm/book3s_pr_papr.c
@@ -257,6 +257,8 @@ int kvmppc_h_pr(struct kvm_vcpu *vcpu, unsigned long cmd)
 	case H_CPPR:
 	case H_EOI:
 	case H_IPI:
+	case H_IPOLL:
+	case H_XIRR_X:
 		if (kvmppc_xics_enabled(vcpu))
 			return kvmppc_h_pr_xics_hcall(vcpu, cmd);
 		break;
diff --git a/arch/powerpc/kvm/book3s_xics.c b/arch/powerpc/kvm/book3s_xics.c
index f7a103756618..94c1dd46b83d 100644
--- a/arch/powerpc/kvm/book3s_xics.c
+++ b/arch/powerpc/kvm/book3s_xics.c
@@ -650,6 +650,23 @@ static noinline int kvmppc_h_ipi(struct kvm_vcpu *vcpu, unsigned long server,
 	return H_SUCCESS;
 }
 
+static int kvmppc_h_ipoll(struct kvm_vcpu *vcpu, unsigned long server)
+{
+	union kvmppc_icp_state state;
+	struct kvmppc_icp *icp;
+
+	icp = vcpu->arch.icp;
+	if (icp->server_num != server) {
+		icp = kvmppc_xics_find_server(vcpu->kvm, server);
+		if (!icp)
+			return H_PARAMETER;
+	}
+	state = ACCESS_ONCE(icp->state);
+	kvmppc_set_gpr(vcpu, 4, ((u32)state.cppr << 24) | state.xisr);
+	kvmppc_set_gpr(vcpu, 5, state.mfrr);
+	return H_SUCCESS;
+}
+
 static noinline void kvmppc_h_cppr(struct kvm_vcpu *vcpu, unsigned long cppr)
 {
 	union kvmppc_icp_state old_state, new_state;
@@ -787,6 +804,18 @@ int kvmppc_xics_hcall(struct kvm_vcpu *vcpu, u32 req)
 	if (!xics || !vcpu->arch.icp)
 		return H_HARDWARE;
 
+	/* These requests don't have real-mode implementations at present */
+	switch (req) {
+	case H_XIRR_X:
+		res = kvmppc_h_xirr(vcpu);
+		kvmppc_set_gpr(vcpu, 4, res);
+		kvmppc_set_gpr(vcpu, 5, get_tb());
+		return rc;
+	case H_IPOLL:
+		rc = kvmppc_h_ipoll(vcpu, kvmppc_get_gpr(vcpu, 4));
+		return rc;
+	}
+
 	/* Check for real mode returning too hard */
 	if (xics->real_mode)
 		return kvmppc_xics_rm_complete(vcpu, req);
diff --git a/arch/powerpc/kvm/booke.c b/arch/powerpc/kvm/booke.c
index 1020119226db..1a1b51189773 100644
--- a/arch/powerpc/kvm/booke.c
+++ b/arch/powerpc/kvm/booke.c
@@ -673,7 +673,6 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 		ret = s;
 		goto out;
 	}
-	kvmppc_lazy_ee_enable();
 
 	kvm_guest_enter();
 
@@ -699,6 +698,8 @@ int kvmppc_vcpu_run(struct kvm_run *kvm_run, struct kvm_vcpu *vcpu)
 	kvmppc_load_guest_fp(vcpu);
 #endif
 
+	kvmppc_lazy_ee_enable();
+
 	ret = __kvmppc_vcpu_run(kvm_run, vcpu);
 
 	/* No need for kvm_guest_exit. It's done in handle_exit.
@@ -832,6 +833,18 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 {
 	int r = RESUME_HOST;
 	int s;
+	int idx;
+
+#ifdef CONFIG_PPC64
+	WARN_ON(local_paca->irq_happened != 0);
+#endif
+
+	/*
+	 * We enter with interrupts disabled in hardware, but
+	 * we need to call hard_irq_disable anyway to ensure that
+	 * the software state is kept in sync.
+	 */
+	hard_irq_disable();
 
 	/* update before a new last_exit_type is rewritten */
 	kvmppc_update_timing_stats(vcpu);
@@ -1053,6 +1066,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			break;
 		}
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
 		gfn = gpaddr >> PAGE_SHIFT;
 
@@ -1075,6 +1090,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_account_exit(vcpu, MMIO_EXITS);
 		}
 
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 
@@ -1098,6 +1114,8 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 
 		kvmppc_account_exit(vcpu, ITLB_VIRT_MISS_EXITS);
 
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 		gpaddr = kvmppc_mmu_xlate(vcpu, gtlb_index, eaddr);
 		gfn = gpaddr >> PAGE_SHIFT;
 
@@ -1114,6 +1132,7 @@ int kvmppc_handle_exit(struct kvm_run *run, struct kvm_vcpu *vcpu,
 			kvmppc_booke_queue_irqprio(vcpu, BOOKE_IRQPRIO_MACHINE_CHECK);
 		}
 
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
 		break;
 	}
 
diff --git a/arch/powerpc/kvm/e500_mmu.c b/arch/powerpc/kvm/e500_mmu.c
index c41a5a96b558..6d6f153b6c1d 100644
--- a/arch/powerpc/kvm/e500_mmu.c
+++ b/arch/powerpc/kvm/e500_mmu.c
@@ -396,6 +396,7 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 	struct kvm_book3e_206_tlb_entry *gtlbe;
 	int tlbsel, esel;
 	int recal = 0;
+	int idx;
 
 	tlbsel = get_tlb_tlbsel(vcpu);
 	esel = get_tlb_esel(vcpu, tlbsel);
@@ -430,6 +431,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 			kvmppc_set_tlb1map_range(vcpu, gtlbe);
 	}
 
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
 	/* Invalidate shadow mappings for the about-to-be-clobbered TLBE. */
 	if (tlbe_is_host_safe(vcpu, gtlbe)) {
 		u64 eaddr = get_tlb_eaddr(gtlbe);
@@ -444,6 +447,8 @@ int kvmppc_e500_emul_tlbwe(struct kvm_vcpu *vcpu)
 		kvmppc_mmu_map(vcpu, eaddr, raddr, index_of(tlbsel, esel));
 	}
 
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+
 	kvmppc_set_exit_type(vcpu, EMULATED_TLBWE_EXITS);
 	return EMULATE_DONE;
 }
diff --git a/arch/powerpc/kvm/e500mc.c b/arch/powerpc/kvm/e500mc.c
index 753cc99eff2b..19c8379575f7 100644
--- a/arch/powerpc/kvm/e500mc.c
+++ b/arch/powerpc/kvm/e500mc.c
@@ -177,8 +177,6 @@ int kvmppc_core_check_processor_compat(void)
 		r = 0;
 	else if (strcmp(cur_cpu_spec->cpu_name, "e5500") == 0)
 		r = 0;
-	else if (strcmp(cur_cpu_spec->cpu_name, "e6500") == 0)
-		r = 0;
 	else
 		r = -ENOTSUPP;
 
diff --git a/arch/powerpc/lib/copypage_power7.S b/arch/powerpc/lib/copypage_power7.S
index 0ef75bf0695c..395c594722a2 100644
--- a/arch/powerpc/lib/copypage_power7.S
+++ b/arch/powerpc/lib/copypage_power7.S
@@ -28,13 +28,14 @@ _GLOBAL(copypage_power7)
 	 * aligned we don't need to clear the bottom 7 bits of either
 	 * address.
 	 */
-	ori	r9,r3,1		/* stream=1 */
+	ori	r9,r3,1		/* stream=1 => to */
 
 #ifdef CONFIG_PPC_64K_PAGES
-	lis	r7,0x0E01	/* depth=7, units=512 */
+	lis	r7,0x0E01	/* depth=7
+				 * units/cachelines=512 */
 #else
 	lis	r7,0x0E00	/* depth=7 */
-	ori	r7,r7,0x1000	/* units=32 */
+	ori	r7,r7,0x1000	/* units/cachelines=32 */
 #endif
 	ori	r10,r7,1	/* stream=1 */
 
@@ -43,12 +44,14 @@ _GLOBAL(copypage_power7)
 
 .machine push
 .machine "power4"
-	dcbt	r0,r4,0b01000
-	dcbt	r0,r7,0b01010
-	dcbtst	r0,r9,0b01000
-	dcbtst	r0,r10,0b01010
+	/* setup read stream 0  */
+	dcbt	r0,r4,0b01000  	/* addr from */
+	dcbt	r0,r7,0b01010   /* length and depth from */
+	/* setup write stream 1 */
+	dcbtst	r0,r9,0b01000   /* addr to */
+	dcbtst	r0,r10,0b01010  /* length and depth to */
 	eieio
-	dcbt	r0,r8,0b01010	/* GO */
+	dcbt	r0,r8,0b01010	/* all streams GO */
 .machine pop
 
 #ifdef CONFIG_ALTIVEC
diff --git a/arch/powerpc/lib/copyuser_power7.S b/arch/powerpc/lib/copyuser_power7.S
index 0d24ff15f5f6..d1f11795a7ad 100644
--- a/arch/powerpc/lib/copyuser_power7.S
+++ b/arch/powerpc/lib/copyuser_power7.S
@@ -318,12 +318,14 @@ err1;	stb	r0,0(r3)
 
 .machine push
 .machine "power4"
-	dcbt	r0,r6,0b01000
-	dcbt	r0,r7,0b01010
-	dcbtst	r0,r9,0b01000
-	dcbtst	r0,r10,0b01010
+	/* setup read stream 0 */
+	dcbt	r0,r6,0b01000   /* addr from */
+	dcbt	r0,r7,0b01010   /* length and depth from */
+	/* setup write stream 1 */
+	dcbtst	r0,r9,0b01000   /* addr to */
+	dcbtst	r0,r10,0b01010  /* length and depth to */
 	eieio
-	dcbt	r0,r8,0b01010	/* GO */
+	dcbt	r0,r8,0b01010	/* all streams GO */
 .machine pop
 
 	beq	cr1,.Lunwind_stack_nonvmx_copy
diff --git a/arch/powerpc/mm/hash_native_64.c b/arch/powerpc/mm/hash_native_64.c
index 6a2aead5b0e5..4c122c3f1623 100644
--- a/arch/powerpc/mm/hash_native_64.c
+++ b/arch/powerpc/mm/hash_native_64.c
@@ -336,11 +336,18 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 
 	hpte_v = hptep->v;
 	actual_psize = hpte_actual_psize(hptep, psize);
+	/*
+	 * We need to invalidate the TLB always because hpte_remove doesn't do
+	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
+	 * random entry from it. When we do that we don't invalidate the TLB
+	 * (hpte_remove) because we assume the old translation is still
+	 * technically "valid".
+	 */
 	if (actual_psize < 0) {
-		native_unlock_hpte(hptep);
-		return -1;
+		actual_psize = psize;
+		ret = -1;
+		goto err_out;
 	}
-	/* Even if we miss, we need to invalidate the TLB */
 	if (!HPTE_V_COMPARE(hpte_v, want_v)) {
 		DBG_LOW(" -> miss\n");
 		ret = -1;
@@ -350,6 +357,7 @@ static long native_hpte_updatepp(unsigned long slot, unsigned long newpp,
 		hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
 			(newpp & (HPTE_R_PP | HPTE_R_N | HPTE_R_C));
 	}
+err_out:
 	native_unlock_hpte(hptep);
 
 	/* Ensure it is out of the tlb too. */
@@ -409,7 +417,7 @@ static void native_hpte_updateboltedpp(unsigned long newpp, unsigned long ea,
 	hptep = htab_address + slot;
 	actual_psize = hpte_actual_psize(hptep, psize);
 	if (actual_psize < 0)
-		return;
+		actual_psize = psize;
 
 	/* Update the HPTE */
 	hptep->r = (hptep->r & ~(HPTE_R_PP | HPTE_R_N)) |
@@ -437,21 +445,27 @@ static void native_hpte_invalidate(unsigned long slot, unsigned long vpn,
 	hpte_v = hptep->v;
 
 	actual_psize = hpte_actual_psize(hptep, psize);
+	/*
+	 * We need to invalidate the TLB always because hpte_remove doesn't do
+	 * a tlb invalidate. If a hash bucket gets full, we "evict" a more/less
+	 * random entry from it. When we do that we don't invalidate the TLB
+	 * (hpte_remove) because we assume the old translation is still
+	 * technically "valid".
+	 */
 	if (actual_psize < 0) {
+		actual_psize = psize;
 		native_unlock_hpte(hptep);
-		local_irq_restore(flags);
-		return;
+		goto err_out;
 	}
-	/* Even if we miss, we need to invalidate the TLB */
 	if (!HPTE_V_COMPARE(hpte_v, want_v))
 		native_unlock_hpte(hptep);
 	else
 		/* Invalidate the hpte. NOTE: this also unlocks it */
 		hptep->v = 0;
 
+err_out:
 	/* Invalidate the TLB */
 	tlbie(vpn, psize, actual_psize, ssize, local);
-
 	local_irq_restore(flags);
 }
 
diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c
index 237c8e5f2640..77fdd2cef33b 100644
--- a/arch/powerpc/mm/hugetlbpage.c
+++ b/arch/powerpc/mm/hugetlbpage.c
@@ -592,8 +592,14 @@ static void hugetlb_free_pmd_range(struct mmu_gather *tlb, pud_t *pud,
 	do {
 		pmd = pmd_offset(pud, addr);
 		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_clear_bad(pmd))
+		if (!is_hugepd(pmd)) {
+			/*
+			 * if it is not hugepd pointer, we should already find
+			 * it cleared.
+			 */
+			WARN_ON(!pmd_none_or_clear_bad(pmd));
 			continue;
+		}
 #ifdef CONFIG_PPC_FSL_BOOK3E
 		/*
 		 * Increment next by the size of the huge mapping since
diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 426180b84978..29c6482890c8 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -110,7 +110,7 @@ static inline void power_pmu_bhrb_read(struct cpu_hw_events *cpuhw) {}
 
 static bool regs_use_siar(struct pt_regs *regs)
 {
-	return !!(regs->result & 1);
+	return !!regs->result;
 }
 
 /*
@@ -136,22 +136,30 @@ static inline unsigned long perf_ip_adjust(struct pt_regs *regs)
  * If we're not doing instruction sampling, give them the SDAR
  * (sampled data address).  If we are doing instruction sampling, then
  * only give them the SDAR if it corresponds to the instruction
- * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC or
- * the [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA.
+ * pointed to by SIAR; this is indicated by the [POWER6_]MMCRA_SDSYNC, the
+ * [POWER7P_]MMCRA_SDAR_VALID bit in MMCRA, or the SDAR_VALID bit in SIER.
  */
 static inline void perf_get_data_addr(struct pt_regs *regs, u64 *addrp)
 {
 	unsigned long mmcra = regs->dsisr;
-	unsigned long sdsync;
+	bool sdar_valid;
 
-	if (ppmu->flags & PPMU_SIAR_VALID)
-		sdsync = POWER7P_MMCRA_SDAR_VALID;
-	else if (ppmu->flags & PPMU_ALT_SIPR)
-		sdsync = POWER6_MMCRA_SDSYNC;
-	else
-		sdsync = MMCRA_SDSYNC;
+	if (ppmu->flags & PPMU_HAS_SIER)
+		sdar_valid = regs->dar & SIER_SDAR_VALID;
+	else {
+		unsigned long sdsync;
+
+		if (ppmu->flags & PPMU_SIAR_VALID)
+			sdsync = POWER7P_MMCRA_SDAR_VALID;
+		else if (ppmu->flags & PPMU_ALT_SIPR)
+			sdsync = POWER6_MMCRA_SDSYNC;
+		else
+			sdsync = MMCRA_SDSYNC;
+
+		sdar_valid = mmcra & sdsync;
+	}
 
-	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & sdsync))
+	if (!(mmcra & MMCRA_SAMPLE_ENABLE) || sdar_valid)
 		*addrp = mfspr(SPRN_SDAR);
 }
 
@@ -181,11 +189,6 @@ static bool regs_sipr(struct pt_regs *regs)
 	return !!(regs->dsisr & sipr);
 }
 
-static bool regs_no_sipr(struct pt_regs *regs)
-{
-	return !!(regs->result & 2);
-}
-
 static inline u32 perf_flags_from_msr(struct pt_regs *regs)
 {
 	if (regs->msr & MSR_PR)
@@ -208,7 +211,7 @@ static inline u32 perf_get_misc_flags(struct pt_regs *regs)
 	 * SIAR which should give slightly more reliable
 	 * results
 	 */
-	if (regs_no_sipr(regs)) {
+	if (ppmu->flags & PPMU_NO_SIPR) {
 		unsigned long siar = mfspr(SPRN_SIAR);
 		if (siar >= PAGE_OFFSET)
 			return PERF_RECORD_MISC_KERNEL;
@@ -239,22 +242,9 @@ static inline void perf_read_regs(struct pt_regs *regs)
 	int use_siar;
 
 	regs->dsisr = mmcra;
-	regs->result = 0;
-
-	if (ppmu->flags & PPMU_NO_SIPR)
-		regs->result |= 2;
-
-	/*
-	 * On power8 if we're in random sampling mode, the SIER is updated.
-	 * If we're in continuous sampling mode, we don't have SIPR.
-	 */
-	if (ppmu->flags & PPMU_HAS_SIER) {
-		if (marked)
-			regs->dar = mfspr(SPRN_SIER);
-		else
-			regs->result |= 2;
-	}
 
+	if (ppmu->flags & PPMU_HAS_SIER)
+		regs->dar = mfspr(SPRN_SIER);
 
 	/*
 	 * If this isn't a PMU exception (eg a software event) the SIAR is
@@ -279,12 +269,12 @@ static inline void perf_read_regs(struct pt_regs *regs)
 		use_siar = 1;
 	else if ((ppmu->flags & PPMU_NO_CONT_SAMPLING))
 		use_siar = 0;
-	else if (!regs_no_sipr(regs) && regs_sipr(regs))
+	else if (!(ppmu->flags & PPMU_NO_SIPR) && regs_sipr(regs))
 		use_siar = 0;
 	else
 		use_siar = 1;
 
-	regs->result |= use_siar;
+	regs->result = use_siar;
 }
 
 /*
@@ -308,8 +298,13 @@ static inline int siar_valid(struct pt_regs *regs)
 	unsigned long mmcra = regs->dsisr;
 	int marked = mmcra & MMCRA_SAMPLE_ENABLE;
 
-	if ((ppmu->flags & PPMU_SIAR_VALID) && marked)
-		return mmcra & POWER7P_MMCRA_SIAR_VALID;
+	if (marked) {
+		if (ppmu->flags & PPMU_HAS_SIER)
+			return regs->dar & SIER_SIAR_VALID;
+
+		if (ppmu->flags & PPMU_SIAR_VALID)
+			return mmcra & POWER7P_MMCRA_SIAR_VALID;
+	}
 
 	return 1;
 }
@@ -1763,7 +1758,7 @@ static void perf_event_interrupt(struct pt_regs *regs)
 			}
 		}
 	}
-	if ((!found) && printk_ratelimit())
+	if (!found && !nmi && printk_ratelimit())
 		printk(KERN_WARNING "Can't find PMC that caused IRQ\n");
 
 	/*
diff --git a/arch/powerpc/platforms/pseries/Kconfig b/arch/powerpc/platforms/pseries/Kconfig
index 023b288f895b..4459eff7a75a 100644
--- a/arch/powerpc/platforms/pseries/Kconfig
+++ b/arch/powerpc/platforms/pseries/Kconfig
@@ -19,6 +19,8 @@ config PPC_PSERIES
 	select ZLIB_DEFLATE
 	select PPC_DOORBELL
 	select HAVE_CONTEXT_TRACKING
+	select HOTPLUG if SMP
+	select HOTPLUG_CPU if SMP
 	default y
 
 config PPC_SPLPAR
diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c
index 5a4c87903057..5ce3ba7ad137 100644
--- a/arch/powerpc/platforms/pseries/eeh_cache.c
+++ b/arch/powerpc/platforms/pseries/eeh_cache.c
@@ -294,8 +294,6 @@ void __init eeh_addr_cache_build(void)
 	spin_lock_init(&pci_io_addr_cache_root.piar_lock);
 
 	for_each_pci_dev(dev) {
-		eeh_addr_cache_insert_dev(dev);
-
 		dn = pci_device_to_OF_node(dev);
 		if (!dn)
 			continue;
@@ -308,6 +306,8 @@ void __init eeh_addr_cache_build(void)
 		dev->dev.archdata.edev = edev;
 		edev->pdev = dev;
 
+		eeh_addr_cache_insert_dev(dev);
+
 		eeh_sysfs_add_device(dev);
 	}
 
diff --git a/arch/powerpc/platforms/pseries/eeh_pe.c b/arch/powerpc/platforms/pseries/eeh_pe.c
index fe43d1aa2cf1..9d4a9e8562b2 100644
--- a/arch/powerpc/platforms/pseries/eeh_pe.c
+++ b/arch/powerpc/platforms/pseries/eeh_pe.c
@@ -639,7 +639,8 @@ struct pci_bus *eeh_pe_bus_get(struct eeh_pe *pe)
 
 	if (pe->type & EEH_PE_PHB) {
 		bus = pe->phb->bus;
-	} else if (pe->type & EEH_PE_BUS) {
+	} else if (pe->type & EEH_PE_BUS ||
+		   pe->type & EEH_PE_DEVICE) {
 		edev = list_first_entry(&pe->edevs, struct eeh_dev, list);
 		pdev = eeh_dev_to_pci_dev(edev);
 		if (pdev)
diff --git a/arch/powerpc/platforms/pseries/eeh_pseries.c b/arch/powerpc/platforms/pseries/eeh_pseries.c
index 19506f935737..b456b157d33d 100644
--- a/arch/powerpc/platforms/pseries/eeh_pseries.c
+++ b/arch/powerpc/platforms/pseries/eeh_pseries.c
@@ -83,7 +83,11 @@ static int pseries_eeh_init(void)
 	ibm_configure_pe		= rtas_token("ibm,configure-pe");
 	ibm_configure_bridge		= rtas_token("ibm,configure-bridge");
 
-	/* necessary sanity check */
+	/*
+	 * Necessary sanity check. We needn't check "get-config-addr-info"
+	 * and its variant since the old firmware probably support address
+	 * of domain/bus/slot/function for EEH RTAS operations.
+	 */
 	if (ibm_set_eeh_option == RTAS_UNKNOWN_SERVICE) {
 		pr_warning("%s: RTAS service <ibm,set-eeh-option> invalid\n",
 			__func__);
@@ -102,12 +106,6 @@ static int pseries_eeh_init(void)
 		pr_warning("%s: RTAS service <ibm,slot-error-detail> invalid\n",
 			__func__);
 		return -EINVAL;
-	} else if (ibm_get_config_addr_info2 == RTAS_UNKNOWN_SERVICE &&
-		   ibm_get_config_addr_info == RTAS_UNKNOWN_SERVICE) {
-		pr_warning("%s: RTAS service <ibm,get-config-addr-info2> and "
-			"<ibm,get-config-addr-info> invalid\n",
-			__func__);
-		return -EINVAL;
 	} else if (ibm_configure_pe == RTAS_UNKNOWN_SERVICE &&
 		   ibm_configure_bridge == RTAS_UNKNOWN_SERVICE) {
 		pr_warning("%s: RTAS service <ibm,configure-pe> and "
diff --git a/arch/powerpc/sysdev/fsl_pci.c b/arch/powerpc/sysdev/fsl_pci.c
index 028ac1f71b51..46ac1ddea683 100644
--- a/arch/powerpc/sysdev/fsl_pci.c
+++ b/arch/powerpc/sysdev/fsl_pci.c
@@ -97,22 +97,14 @@ static int fsl_indirect_read_config(struct pci_bus *bus, unsigned int devfn,
 	return indirect_read_config(bus, devfn, offset, len, val);
 }
 
-static struct pci_ops fsl_indirect_pci_ops =
+#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
+
+static struct pci_ops fsl_indirect_pcie_ops =
 {
 	.read = fsl_indirect_read_config,
 	.write = indirect_write_config,
 };
 
-static void __init fsl_setup_indirect_pci(struct pci_controller* hose,
-					  resource_size_t cfg_addr,
-					  resource_size_t cfg_data, u32 flags)
-{
-	setup_indirect_pci(hose, cfg_addr, cfg_data, flags);
-	hose->ops = &fsl_indirect_pci_ops;
-}
-
-#if defined(CONFIG_FSL_SOC_BOOKE) || defined(CONFIG_PPC_86xx)
-
 #define MAX_PHYS_ADDR_BITS	40
 static u64 pci64_dma_offset = 1ull << MAX_PHYS_ADDR_BITS;
 
@@ -504,13 +496,15 @@ int __init fsl_add_bridge(struct platform_device *pdev, int is_primary)
 	if (!hose->private_data)
 		goto no_bridge;
 
-	fsl_setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4,
-			       PPC_INDIRECT_TYPE_BIG_ENDIAN);
+	setup_indirect_pci(hose, rsrc.start, rsrc.start + 0x4,
+			   PPC_INDIRECT_TYPE_BIG_ENDIAN);
 
 	if (in_be32(&pci->block_rev1) < PCIE_IP_REV_3_0)
 		hose->indirect_type |= PPC_INDIRECT_TYPE_FSL_CFG_REG_LINK;
 
 	if (early_find_capability(hose, 0, 0, PCI_CAP_ID_EXP)) {
+		/* use fsl_indirect_read_config for PCIe */
+		hose->ops = &fsl_indirect_pcie_ops;
 		/* For PCIE read HEADER_TYPE to identify controler mode */
 		early_read_config_byte(hose, 0, 0, PCI_HEADER_TYPE, &hdr_type);
 		if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
@@ -814,8 +808,8 @@ int __init mpc83xx_add_bridge(struct device_node *dev)
 		if (ret)
 			goto err0;
 	} else {
-		fsl_setup_indirect_pci(hose, rsrc_cfg.start,
-				       rsrc_cfg.start + 4, 0);
+		setup_indirect_pci(hose, rsrc_cfg.start,
+				   rsrc_cfg.start + 4, 0);
 	}
 
 	printk(KERN_INFO "Found FSL PCI host bridge at 0x%016llx. "
diff --git a/arch/powerpc/sysdev/mpic.c b/arch/powerpc/sysdev/mpic.c
index 0a13ecb270c7..3cc2f9159ab1 100644
--- a/arch/powerpc/sysdev/mpic.c
+++ b/arch/powerpc/sysdev/mpic.c
@@ -54,7 +54,7 @@ static DEFINE_RAW_SPINLOCK(mpic_lock);
 
 #ifdef CONFIG_PPC32	/* XXX for now */
 #ifdef CONFIG_IRQ_ALL_CPUS
-#define distribute_irqs	(!(mpic->flags & MPIC_SINGLE_DEST_CPU))
+#define distribute_irqs	(1)
 #else
 #define distribute_irqs	(0)
 #endif
@@ -1703,7 +1703,7 @@ void mpic_setup_this_cpu(void)
 	 * it differently, then we should make sure we also change the default
 	 * values of irq_desc[].affinity in irq.c.
  	 */
-	if (distribute_irqs) {
+	if (distribute_irqs && !(mpic->flags & MPIC_SINGLE_DEST_CPU)) {
 	 	for (i = 0; i < mpic->num_sources ; i++)
 			mpic_irq_write(i, MPIC_INFO(IRQ_DESTINATION),
 				mpic_irq_read(i, MPIC_INFO(IRQ_DESTINATION)) | msk);