16 files changed, 168 insertions, 119 deletions

diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index b51a97cfedf8..6f16ffafa6f0 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -127,6 +127,12 @@ int main(void)
 	DEFINE(THREAD_BESCR, offsetof(struct thread_struct, bescr));
 	DEFINE(THREAD_EBBHR, offsetof(struct thread_struct, ebbhr));
 	DEFINE(THREAD_EBBRR, offsetof(struct thread_struct, ebbrr));
+	DEFINE(THREAD_SIAR, offsetof(struct thread_struct, siar));
+	DEFINE(THREAD_SDAR, offsetof(struct thread_struct, sdar));
+	DEFINE(THREAD_SIER, offsetof(struct thread_struct, sier));
+	DEFINE(THREAD_MMCR0, offsetof(struct thread_struct, mmcr0));
+	DEFINE(THREAD_MMCR2, offsetof(struct thread_struct, mmcr2));
+	DEFINE(THREAD_MMCRA, offsetof(struct thread_struct, mmcra));
 #endif
 #ifdef CONFIG_PPC_TRANSACTIONAL_MEM
 	DEFINE(PACATMSCRATCH, offsetof(struct paca_struct, tm_scratch));
diff --git a/arch/powerpc/kernel/cpu_setup_power.S b/arch/powerpc/kernel/cpu_setup_power.S
index a283b6442b26..18b5b9cf8e37 100644
--- a/arch/powerpc/kernel/cpu_setup_power.S
+++ b/arch/powerpc/kernel/cpu_setup_power.S
@@ -135,8 +135,12 @@ __init_HFSCR:
 	blr
 
 __init_TLB:
-	/* Clear the TLB */
-	li	r6,128
+	/*
+	 * Clear the TLB using the "IS 3" form of tlbiel instruction
+	 * (invalidate by congruence class). P7 has 128 CCs, P8 has 512
+	 * so we just always do 512
+	 */
+	li	r6,512
 	mtctr	r6
 	li	r7,0xc00	/* IS field = 0b11 */
 	ptesync
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 51cfb8fc301f..8741c854e03d 100644
--- a/arch/powerpc/kernel/entry_64.S
+++ b/arch/powerpc/kernel/entry_64.S
@@ -487,6 +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' */
 
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 6053f037ef0a..eabeec991016 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] "
@@ -1520,9 +1510,10 @@ static void pcibios_setup_phb_resources(struct pci_controller *hose,
 	for (i = 0; i < 3; ++i) {
 		res = &hose->mem_resources[i];
 		if (!res->flags) {
-			printk(KERN_ERR "PCI: Memory resource 0 not set for "
-			       "host bridge %s (domain %d)\n",
-			       hose->dn->full_name, hose->global_number);
+			if (i == 0)
+				printk(KERN_ERR "PCI: Memory resource 0 not set for "
+				       "host bridge %s (domain %d)\n",
+				       hose->dn->full_name, hose->global_number);
 			continue;
 		}
 		offset = hose->mem_offset[i];
diff --git a/arch/powerpc/kernel/pci_64.c b/arch/powerpc/kernel/pci_64.c
index 873050d26840..2e8629654ca8 100644
--- a/arch/powerpc/kernel/pci_64.c
+++ b/arch/powerpc/kernel/pci_64.c
@@ -266,3 +266,13 @@ int pcibus_to_node(struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pcibus_to_node);
 #endif
+
+static void quirk_radeon_32bit_msi(struct pci_dev *dev)
+{
+	struct pci_dn *pdn = pci_get_pdn(dev);
+
+	if (pdn)
+		pdn->force_32bit_msi = 1;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x68f2, quirk_radeon_32bit_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0xaa68, quirk_radeon_32bit_msi);
diff --git a/arch/powerpc/kernel/pci_dn.c b/arch/powerpc/kernel/pci_dn.c
index e7af165f8b9d..df038442548a 100644
--- a/arch/powerpc/kernel/pci_dn.c
+++ b/arch/powerpc/kernel/pci_dn.c
@@ -32,6 +32,14 @@
 #include <asm/ppc-pci.h>
 #include <asm/firmware.h>
 
+struct pci_dn *pci_get_pdn(struct pci_dev *pdev)
+{
+	struct device_node *dn = pci_device_to_OF_node(pdev);
+	if (!dn)
+		return NULL;
+	return PCI_DN(dn);
+}
+
 /*
  * Traverse_func that inits the PCI fields of the device node.
  * NOTE: this *must* be done before read/write config to the device.
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);