diff --git a/Documentation/powerpc/transactional_memory.txt b/Documentation/powerpc/transactional_memory.txt
index c907be41d60f..dc23e58ae264 100644
--- a/Documentation/powerpc/transactional_memory.txt
+++ b/Documentation/powerpc/transactional_memory.txt
@@ -147,6 +147,25 @@ Example signal handler:
       fix_the_problem(ucp->dar);
     }
 
+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.
+
 
 Failure cause codes used by kernel
 ==================================
@@ -155,14 +174,18 @@ These are defined in <asm/reg.h>, and distinguish different reasons why the
 kernel aborted a transaction:
 
  TM_CAUSE_RESCHED       Thread was rescheduled.
+ TM_CAUSE_TLBI          Software TLB invalide.
  TM_CAUSE_FAC_UNAV      FP/VEC/VSX unavailable trap.
  TM_CAUSE_SYSCALL       Currently unused; future syscalls that must abort
                         transactions for consistency will use this.
  TM_CAUSE_SIGNAL        Signal delivered.
  TM_CAUSE_MISC          Currently unused.
+ TM_CAUSE_ALIGNMENT     Alignment fault.
+ TM_CAUSE_EMULATE       Emulation that touched memory.
 
-These can be checked by the user program's abort handler as TEXASR[0:7].
-
+These can be checked by the user program's abort handler as TEXASR[0:7].  If
+bit 7 is set, it indicates that the error is consider persistent.  For example
+a TM_CAUSE_ALIGNMENT will be persistent while a TM_CAUSE_RESCHED will not.q
 
 GDB
 ===
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/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..1f0937d7d4b5 100644
--- a/arch/powerpc/kernel/cputable.c
+++ b/arch/powerpc/kernel/cputable.c
@@ -453,7 +453,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.icache_bsize		= 128,
 		.dcache_bsize		= 128,
 		.oprofile_type		= PPC_OPROFILE_POWER4,
-		.oprofile_cpu_type	= "ppc64/ibm-compat-v1",
+		.oprofile_cpu_type	= 0,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_power8,
 		.platform		= "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,
@@ -506,7 +506,7 @@ static struct cpu_spec __initdata cpu_specs[] = {
 		.dcache_bsize		= 128,
 		.num_pmcs		= 6,
 		.pmc_type		= PPC_PMC_IBM,
-		.oprofile_cpu_type	= "ppc64/power8",
+		.oprofile_cpu_type	= 0,
 		.oprofile_type		= PPC_OPROFILE_POWER4,
 		.cpu_setup		= __setup_cpu_power8,
 		.cpu_restore		= __restore_cpu_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..246b11c4fe7e 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -501,6 +501,13 @@ 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' */
 
diff --git a/arch/powerpc/kernel/pci-common.c b/arch/powerpc/kernel/pci-common.c
index e9acf50dd5b2..7f2273cc3c7d 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;
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..f18c79c324ef 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);
 	}
@@ -1148,6 +1174,9 @@ 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/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/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/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 426180b84978..845c867444e6 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 (!(mmcra & MMCRA_SAMPLE_ENABLE) || (mmcra & 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) || 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;
 }
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/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);