Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

A set of overlapping changes in macvlan and the rocker
driver, nothing serious.

Signed-off-by: David S. Miller <davem@davemloft.net>

64 files changed, 340 insertions, 395 deletions

diff --git a/arch/arc/include/asm/processor.h b/arch/arc/include/asm/processor.h
index 6e1242d..4104a08 100644
--- a/arch/arc/include/asm/processor.h
+++ b/arch/arc/include/asm/processor.h
@@ -86,8 +86,6 @@ struct task_struct;
 #define TSK_K_BLINK(tsk)	TSK_K_REG(tsk, 4)
 #define TSK_K_FP(tsk)		TSK_K_REG(tsk, 0)
 
-#define thread_saved_pc(tsk)	TSK_K_BLINK(tsk)
-
 extern void start_thread(struct pt_regs * regs, unsigned long pc,
 			 unsigned long usp);
 
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 4c1a35f..c0fcab6 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1416,6 +1416,7 @@ choice
 	config VMSPLIT_3G
 		bool "3G/1G user/kernel split"
 	config VMSPLIT_3G_OPT
+		depends on !ARM_LPAE
 		bool "3G/1G user/kernel split (for full 1G low memory)"
 	config VMSPLIT_2G
 		bool "2G/2G user/kernel split"
diff --git a/arch/arm/boot/compressed/efi-header.S b/arch/arm/boot/compressed/efi-header.S
index 3f7d1b7..a17ca8d 100644
--- a/arch/arm/boot/compressed/efi-header.S
+++ b/arch/arm/boot/compressed/efi-header.S
@@ -17,7 +17,8 @@
 		@ there.
 		.inst	'M' | ('Z' << 8) | (0x1310 << 16)   @ tstne r0, #0x4d000
 #else
-		W(mov)	r0, r0
+ AR_CLASS(	mov	r0, r0		)
+  M_CLASS(	nop.w			)
 #endif
 		.endm
 
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 32e1a95..4e80bf7 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -315,7 +315,7 @@ static void __init cacheid_init(void)
 	if (arch >= CPU_ARCH_ARMv6) {
 		unsigned int cachetype = read_cpuid_cachetype();
 
-		if ((arch == CPU_ARCH_ARMv7M) && !cachetype) {
+		if ((arch == CPU_ARCH_ARMv7M) && !(cachetype & 0xf000f)) {
 			cacheid = 0;
 		} else if ((cachetype & (7 << 29)) == 4 << 29) {
 			/* ARMv7 register format */
diff --git a/arch/arm64/kernel/vdso.c b/arch/arm64/kernel/vdso.c
index 41b6e31..d0cb007 100644
--- a/arch/arm64/kernel/vdso.c
+++ b/arch/arm64/kernel/vdso.c
@@ -221,10 +221,11 @@ void update_vsyscall(struct timekeeper *tk)
 		/* tkr_mono.cycle_last == tkr_raw.cycle_last */
 		vdso_data->cs_cycle_last	= tk->tkr_mono.cycle_last;
 		vdso_data->raw_time_sec		= tk->raw_time.tv_sec;
-		vdso_data->raw_time_nsec	= tk->raw_time.tv_nsec;
+		vdso_data->raw_time_nsec	= (tk->raw_time.tv_nsec <<
+						   tk->tkr_raw.shift) +
+						  tk->tkr_raw.xtime_nsec;
 		vdso_data->xtime_clock_sec	= tk->xtime_sec;
 		vdso_data->xtime_clock_nsec	= tk->tkr_mono.xtime_nsec;
-		/* tkr_raw.xtime_nsec == 0 */
 		vdso_data->cs_mono_mult		= tk->tkr_mono.mult;
 		vdso_data->cs_raw_mult		= tk->tkr_raw.mult;
 		/* tkr_mono.shift == tkr_raw.shift */
diff --git a/arch/arm64/kernel/vdso/gettimeofday.S b/arch/arm64/kernel/vdso/gettimeofday.S
index e00b467..76320e9 100644
--- a/arch/arm64/kernel/vdso/gettimeofday.S
+++ b/arch/arm64/kernel/vdso/gettimeofday.S
@@ -256,7 +256,6 @@ monotonic_raw:
 	seqcnt_check fail=monotonic_raw
 
 	/* All computations are done with left-shifted nsecs. */
-	lsl	x14, x14, x12
 	get_nsec_per_sec res=x9
 	lsl	x9, x9, x12
 
diff --git a/arch/blackfin/include/asm/processor.h b/arch/blackfin/include/asm/processor.h
index 85d4af9..dbdbb8a 100644
--- a/arch/blackfin/include/asm/processor.h
+++ b/arch/blackfin/include/asm/processor.h
@@ -75,11 +75,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-/*
- * Return saved PC of a blocked thread.
- */
-#define thread_saved_pc(tsk)	(tsk->thread.pc)
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define	KSTK_EIP(tsk)							\
diff --git a/arch/c6x/include/asm/processor.h b/arch/c6x/include/asm/processor.h
index b9eb3da..7c87b5b 100644
--- a/arch/c6x/include/asm/processor.h
+++ b/arch/c6x/include/asm/processor.h
@@ -96,11 +96,6 @@ static inline void release_thread(struct task_struct *dead_task)
 #define release_segments(mm)		do { } while (0)
 
 /*
- * saved PC of a blocked thread.
- */
-#define thread_saved_pc(tsk) (task_pt_regs(tsk)->pc)
-
-/*
  * saved kernel SP and DP of a blocked thread.
  */
 #ifdef _BIG_ENDIAN
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index e299d30..a2cdb15 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -69,14 +69,6 @@ void hard_reset_now (void)
 	while(1) /* waiting for RETRIBUTION! */ ;
 }
 
-/*
- * Return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *t)
-{
-	return task_pt_regs(t)->irp;
-}
-
 /* setup the child's kernel stack with a pt_regs and switch_stack on it.
  * it will be un-nested during _resume and _ret_from_sys_call when the
  * new thread is scheduled.
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index c530a8f..fe87b38 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -85,14 +85,6 @@ hard_reset_now(void)
 }
 
 /*
- * Return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *t)
-{
-	return task_pt_regs(t)->erp;
-}
-
-/*
  * Setup the child's kernel stack with a pt_regs and call switch_stack() on it.
  * It will be unnested during _resume and _ret_from_sys_call when the new thread
  * is scheduled.
diff --git a/arch/cris/include/asm/processor.h b/arch/cris/include/asm/processor.h
index 15b815d..bc2729e 100644
--- a/arch/cris/include/asm/processor.h
+++ b/arch/cris/include/asm/processor.h
@@ -52,8 +52,6 @@ unsigned long get_wchan(struct task_struct *p);
 
 #define KSTK_ESP(tsk)   ((tsk) == current ? rdusp() : (tsk)->thread.usp)
 
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
 /* Free all resources held by a thread. */
 static inline void release_thread(struct task_struct *dead_task)
 {
diff --git a/arch/frv/include/asm/processor.h b/arch/frv/include/asm/processor.h
index ddaeb9c..e4d08d7 100644
--- a/arch/frv/include/asm/processor.h
+++ b/arch/frv/include/asm/processor.h
@@ -96,11 +96,6 @@ extern asmlinkage void *restore_user_regs(const struct user_context *target, ...
 #define release_segments(mm)		do { } while (0)
 #define forget_segments()		do { } while (0)
 
-/*
- * Return saved PC of a blocked thread.
- */
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define	KSTK_EIP(tsk)	((tsk)->thread.frame0->pc)
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 5a4c92a..a957b37 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -198,15 +198,6 @@ unsigned long get_wchan(struct task_struct *p)
 	return 0;
 }
 
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	/* Check whether the thread is blocked in resume() */
-	if (in_sched_functions(tsk->thread.pc))
-		return ((unsigned long *)tsk->thread.fp)[2];
-	else
-		return tsk->thread.pc;
-}
-
 int elf_check_arch(const struct elf32_hdr *hdr)
 {
 	unsigned long hsr0 = __get_HSR(0);
diff --git a/arch/h8300/include/asm/processor.h b/arch/h8300/include/asm/processor.h
index 65132d7..afa5314 100644
--- a/arch/h8300/include/asm/processor.h
+++ b/arch/h8300/include/asm/processor.h
@@ -110,10 +110,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-/*
- * Return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk);
 unsigned long get_wchan(struct task_struct *p);
 
 #define	KSTK_EIP(tsk)	\
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index 0f5db5b..d1ddcab 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -129,11 +129,6 @@ int copy_thread(unsigned long clone_flags,
 	return 0;
 }
 
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	return ((struct pt_regs *)tsk->thread.esp0)->pc;
-}
-
 unsigned long get_wchan(struct task_struct *p)
 {
 	unsigned long fp, pc;
diff --git a/arch/hexagon/include/asm/processor.h b/arch/hexagon/include/asm/processor.h
index 45a8254..ce67940 100644
--- a/arch/hexagon/include/asm/processor.h
+++ b/arch/hexagon/include/asm/processor.h
@@ -33,9 +33,6 @@
 /*  task_struct, defined elsewhere, is the "process descriptor" */
 struct task_struct;
 
-/*  this is defined in arch/process.c  */
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
 extern void start_thread(struct pt_regs *, unsigned long, unsigned long);
 
 /*
diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index de715ba..656050c 100644
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -61,14 +61,6 @@ void arch_cpu_idle(void)
 }
 
 /*
- *  Return saved PC of a blocked thread
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	return 0;
-}
-
-/*
  * Copy architecture-specific thread state
  */
 int copy_thread(unsigned long clone_flags, unsigned long usp,
diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h
index 26a63d6..ab982f0 100644
--- a/arch/ia64/include/asm/processor.h
+++ b/arch/ia64/include/asm/processor.h
@@ -602,23 +602,6 @@ ia64_set_unat (__u64 *unat, void *spill_addr, unsigned long nat)
 }
 
 /*
- * Return saved PC of a blocked thread.
- * Note that the only way T can block is through a call to schedule() -> switch_to().
- */
-static inline unsigned long
-thread_saved_pc (struct task_struct *t)
-{
-	struct unw_frame_info info;
-	unsigned long ip;
-
-	unw_init_from_blocked_task(&info, t);
-	if (unw_unwind(&info) < 0)
-		return 0;
-	unw_get_ip(&info, &ip);
-	return ip;
-}
-
-/*
  * Get the current instruction/program counter value.
  */
 #define current_text_addr() \
diff --git a/arch/m32r/include/asm/processor.h b/arch/m32r/include/asm/processor.h
index 5767367..657874e 100644
--- a/arch/m32r/include/asm/processor.h
+++ b/arch/m32r/include/asm/processor.h
@@ -122,8 +122,6 @@ extern void release_thread(struct task_struct *);
 extern void copy_segments(struct task_struct *p, struct mm_struct * mm);
 extern void release_segments(struct mm_struct * mm);
 
-extern unsigned long thread_saved_pc(struct task_struct *);
-
 /* Copy and release all segment info associated with a VM */
 #define copy_segments(p, mm)  do { } while (0)
 #define release_segments(mm)  do { } while (0)
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index d8ffcfe..8cd7e03 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -39,14 +39,6 @@
 
 #include <linux/err.h>
 
-/*
- * Return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	return tsk->thread.lr;
-}
-
 void (*pm_power_off)(void) = NULL;
 EXPORT_SYMBOL(pm_power_off);
 
diff --git a/arch/m68k/include/asm/processor.h b/arch/m68k/include/asm/processor.h
index 77239e8..94c3603 100644
--- a/arch/m68k/include/asm/processor.h
+++ b/arch/m68k/include/asm/processor.h
@@ -130,8 +130,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define	KSTK_EIP(tsk)	\
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index e475c94..7df92f8 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -40,20 +40,6 @@
 asmlinkage void ret_from_fork(void);
 asmlinkage void ret_from_kernel_thread(void);
 
-
-/*
- * Return saved PC from a blocked thread
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	struct switch_stack *sw = (struct switch_stack *)tsk->thread.ksp;
-	/* Check whether the thread is blocked in resume() */
-	if (in_sched_functions(sw->retpc))
-		return ((unsigned long *)sw->a6)[1];
-	else
-		return sw->retpc;
-}
-
 void arch_cpu_idle(void)
 {
 #if defined(MACH_ATARI_ONLY)
diff --git a/arch/microblaze/include/asm/processor.h b/arch/microblaze/include/asm/processor.h
index 37ef196..330d556 100644
--- a/arch/microblaze/include/asm/processor.h
+++ b/arch/microblaze/include/asm/processor.h
@@ -69,8 +69,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-extern unsigned long thread_saved_pc(struct task_struct *t);
-
 extern unsigned long get_wchan(struct task_struct *p);
 
 # define KSTK_EIP(tsk)	(0)
@@ -121,10 +119,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-/* Return saved (kernel) PC of a blocked thread.  */
-#  define thread_saved_pc(tsk)	\
-	((tsk)->thread.regs ? (tsk)->thread.regs->r15 : 0)
-
 unsigned long get_wchan(struct task_struct *p);
 
 /* The size allocated for kernel stacks. This _must_ be a power of two! */
diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index e92a817..6527ec2 100644
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -119,23 +119,6 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	return 0;
 }
 
-#ifndef CONFIG_MMU
-/*
- * Return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	struct cpu_context *ctx =
-		&(((struct thread_info *)(tsk->stack))->cpu_context);
-
-	/* Check whether the thread is blocked in resume() */
-	if (in_sched_functions(ctx->r15))
-		return (unsigned long)ctx->r15;
-	else
-		return ctx->r14;
-}
-#endif
-
 unsigned long get_wchan(struct task_struct *p)
 {
 /* TBD (used by procfs) */
diff --git a/arch/mips/kvm/tlb.c b/arch/mips/kvm/tlb.c
index 7c6336d..7cd9216 100644
--- a/arch/mips/kvm/tlb.c
+++ b/arch/mips/kvm/tlb.c
@@ -166,7 +166,11 @@ static int _kvm_mips_host_tlb_inv(unsigned long entryhi)
 int kvm_mips_host_tlb_inv(struct kvm_vcpu *vcpu, unsigned long va,
 			  bool user, bool kernel)
 {
-	int idx_user, idx_kernel;
+	/*
+	 * Initialize idx_user and idx_kernel to workaround bogus
+	 * maybe-initialized warning when using GCC 6.
+	 */
+	int idx_user = 0, idx_kernel = 0;
 	unsigned long flags, old_entryhi;
 
 	local_irq_save(flags);
diff --git a/arch/mn10300/include/asm/processor.h b/arch/mn10300/include/asm/processor.h
index 18e17ab..3ae4791 100644
--- a/arch/mn10300/include/asm/processor.h
+++ b/arch/mn10300/include/asm/processor.h
@@ -132,11 +132,6 @@ static inline void start_thread(struct pt_regs *regs,
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
-/*
- * Return saved PC of a blocked thread.
- */
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
 unsigned long get_wchan(struct task_struct *p);
 
 #define task_pt_regs(task) ((task)->thread.uregs)
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index c9fa426..89e8027 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -40,14 +40,6 @@
 #include "internal.h"
 
 /*
- * return saved PC of a blocked thread.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	return ((unsigned long *) tsk->thread.sp)[3];
-}
-
-/*
  * power off function, if any
  */
 void (*pm_power_off)(void);
diff --git a/arch/nios2/include/asm/processor.h b/arch/nios2/include/asm/processor.h
index 3bbbc3d..4944e2e 100644
--- a/arch/nios2/include/asm/processor.h
+++ b/arch/nios2/include/asm/processor.h
@@ -75,9 +75,6 @@ static inline void release_thread(struct task_struct *dead_task)
 {
 }
 
-/* Return saved PC of a blocked thread. */
-#define thread_saved_pc(tsk)	((tsk)->thread.kregs->ea)
-
 extern unsigned long get_wchan(struct task_struct *p);
 
 #define task_pt_regs(p) \
diff --git a/arch/openrisc/include/asm/processor.h b/arch/openrisc/include/asm/processor.h
index a908e6c..396d8f3 100644
--- a/arch/openrisc/include/asm/processor.h
+++ b/arch/openrisc/include/asm/processor.h
@@ -84,11 +84,6 @@ void start_thread(struct pt_regs *regs, unsigned long nip, unsigned long sp);
 void release_thread(struct task_struct *);
 unsigned long get_wchan(struct task_struct *p);
 
-/*
- * Return saved PC of a blocked thread. For now, this is the "user" PC
- */
-extern unsigned long thread_saved_pc(struct task_struct *t);
-
 #define init_stack      (init_thread_union.stack)
 
 #define cpu_relax()     barrier()
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 106859a..f9b7700 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -110,11 +110,6 @@ void show_regs(struct pt_regs *regs)
 	show_registers(regs);
 }
 
-unsigned long thread_saved_pc(struct task_struct *t)
-{
-	return (unsigned long)user_regs(t->stack)->pc;
-}
-
 void release_thread(struct task_struct *dead_task)
 {
 }
diff --git a/arch/parisc/include/asm/processor.h b/arch/parisc/include/asm/processor.h
index a3661ee..4c6694b 100644
--- a/arch/parisc/include/asm/processor.h
+++ b/arch/parisc/include/asm/processor.h
@@ -163,12 +163,7 @@ struct thread_struct {
 	.flags		= 0 \
 	}
 
-/*
- * Return saved PC of a blocked thread.  This is used by ps mostly.
- */
-
 struct task_struct;
-unsigned long thread_saved_pc(struct task_struct *t);
 void show_trace(struct task_struct *task, unsigned long *stack);
 
 /*
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 4516a5b..b64d7d2 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -239,11 +239,6 @@ copy_thread(unsigned long clone_flags, unsigned long usp,
 	return 0;
 }
 
-unsigned long thread_saved_pc(struct task_struct *t)
-{
-	return t->thread.regs.kpc;
-}
-
 unsigned long
 get_wchan(struct task_struct *p)
 {
diff --git a/arch/powerpc/include/asm/kprobes.h b/arch/powerpc/include/asm/kprobes.h
index a83821f..8814a72 100644
--- a/arch/powerpc/include/asm/kprobes.h
+++ b/arch/powerpc/include/asm/kprobes.h
@@ -103,6 +103,7 @@ extern int kprobe_exceptions_notify(struct notifier_block *self,
 extern int kprobe_fault_handler(struct pt_regs *regs, int trapnr);
 extern int kprobe_handler(struct pt_regs *regs);
 extern int kprobe_post_handler(struct pt_regs *regs);
+extern int is_current_kprobe_addr(unsigned long addr);
 #ifdef CONFIG_KPROBES_ON_FTRACE
 extern int skip_singlestep(struct kprobe *p, struct pt_regs *regs,
 			   struct kprobe_ctlblk *kcb);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index bb99b65..1189d04 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -378,12 +378,6 @@ struct thread_struct {
 }
 #endif
 
-/*
- * Return saved PC of a blocked thread. For now, this is the "user" PC
- */
-#define thread_saved_pc(tsk)    \
-        ((tsk)->thread.regs? (tsk)->thread.regs->nip: 0)
-
 #define task_pt_regs(tsk)	((struct pt_regs *)(tsk)->thread.regs)
 
 unsigned long get_wchan(struct task_struct *p);
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index ae418b8..b886795 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -1411,10 +1411,8 @@ USE_TEXT_SECTION()
 	.balign	IFETCH_ALIGN_BYTES
 do_hash_page:
 #ifdef CONFIG_PPC_STD_MMU_64
-	andis.	r0,r4,0xa410		/* weird error? */
+	andis.	r0,r4,0xa450		/* weird error? */
 	bne-	handle_page_fault	/* if not, try to insert a HPTE */
-	andis.  r0,r4,DSISR_DABRMATCH@h
-	bne-    handle_dabr_fault
 	CURRENT_THREAD_INFO(r11, r1)
 	lwz	r0,TI_PREEMPT(r11)	/* If we're in an "NMI" */
 	andis.	r0,r0,NMI_MASK@h	/* (i.e. an irq when soft-disabled) */
@@ -1438,11 +1436,16 @@ do_hash_page:
 
 	/* Error */
 	blt-	13f
+
+	/* Reload DSISR into r4 for the DABR check below */
+	ld      r4,_DSISR(r1)
 #endif /* CONFIG_PPC_STD_MMU_64 */
 
 /* Here we have a page fault that hash_page can't handle. */
 handle_page_fault:
-11:	ld	r4,_DAR(r1)
+11:	andis.  r0,r4,DSISR_DABRMATCH@h
+	bne-    handle_dabr_fault
+	ld	r4,_DAR(r1)
 	ld	r5,_DSISR(r1)
 	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	do_page_fault
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index fc43435..01addfb 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -43,6 +43,12 @@ DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
 struct kretprobe_blackpoint kretprobe_blacklist[] = {{NULL, NULL}};
 
+int is_current_kprobe_addr(unsigned long addr)
+{
+	struct kprobe *p = kprobe_running();
+	return (p && (unsigned long)p->addr == addr) ? 1 : 0;
+}
+
 bool arch_within_kprobe_blacklist(unsigned long addr)
 {
 	return  (addr >= (unsigned long)__kprobes_text_start &&
@@ -617,6 +623,15 @@ int setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 	regs->gpr[2] = (unsigned long)(((func_descr_t *)jp->entry)->toc);
 #endif
 
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }
 NOKPROBE_SYMBOL(setjmp_pre_handler);
@@ -642,6 +657,8 @@ int longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index a8c1f99..4640f6d 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -616,6 +616,24 @@ void __init exc_lvl_early_init(void)
 #endif
 
 /*
+ * Emergency stacks are used for a range of things, from asynchronous
+ * NMIs (system reset, machine check) to synchronous, process context.
+ * We set preempt_count to zero, even though that isn't necessarily correct. To
+ * get the right value we'd need to copy it from the previous thread_info, but
+ * doing that might fault causing more problems.
+ * TODO: what to do with accounting?
+ */
+static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
+{
+	ti->task = NULL;
+	ti->cpu = cpu;
+	ti->preempt_count = 0;
+	ti->local_flags = 0;
+	ti->flags = 0;
+	klp_init_thread_info(ti);
+}
+
+/*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled. Exclusive emergency
  * stack for machine checks.
@@ -633,24 +651,31 @@ void __init emergency_stack_init(void)
 	 * Since we use these as temporary stacks during secondary CPU
 	 * bringup, we need to get at them in real mode. This means they
 	 * must also be within the RMO region.
+	 *
+	 * The IRQ stacks allocated elsewhere in this file are zeroed and
+	 * initialized in kernel/irq.c. These are initialized here in order
+	 * to have emergency stacks available as early as possible.
 	 */
 	limit = min(safe_stack_limit(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
 		struct thread_info *ti;
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
 		ti = __va(memblock_alloc_base(THREAD_SIZE, THREAD_SIZE, limit));
-		klp_init_thread_info(ti);
+		memset(ti, 0, THREAD_SIZE);
+		emerg_stack_init_thread_info(ti, i);
 		paca[i].mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}
diff --git a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
index 7c933a9..c98e90b 100644
--- a/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
+++ b/arch/powerpc/kernel/trace/ftrace_64_mprofile.S
@@ -45,10 +45,14 @@ _GLOBAL(ftrace_caller)
 	stdu	r1,-SWITCH_FRAME_SIZE(r1)
 
 	/* Save all gprs to pt_regs */
-	SAVE_8GPRS(0,r1)
-	SAVE_8GPRS(8,r1)
-	SAVE_8GPRS(16,r1)
-	SAVE_8GPRS(24,r1)
+	SAVE_GPR(0, r1)
+	SAVE_10GPRS(2, r1)
+	SAVE_10GPRS(12, r1)
+	SAVE_10GPRS(22, r1)
+
+	/* Save previous stack pointer (r1) */
+	addi	r8, r1, SWITCH_FRAME_SIZE
+	std	r8, GPR1(r1)
 
 	/* Load special regs for save below */
 	mfmsr   r8
@@ -95,18 +99,44 @@ ftrace_call:
 	bl	ftrace_stub
 	nop
 
-	/* Load ctr with the possibly modified NIP */
-	ld	r3, _NIP(r1)
-	mtctr	r3
+	/* Load the possibly modified NIP */
+	ld	r15, _NIP(r1)
+
 #ifdef CONFIG_LIVEPATCH
-	cmpd	r14,r3		/* has NIP been altered? */
+	cmpd	r14, r15	/* has NIP been altered? */
+#endif
+
+#if defined(CONFIG_LIVEPATCH) && defined(CONFIG_KPROBES_ON_FTRACE)
+	/* NIP has not been altered, skip over further checks */
+	beq	1f
+
+	/* Check if there is an active kprobe on us */
+	subi	r3, r14, 4
+	bl	is_current_kprobe_addr
+	nop
+
+	/*
+	 * If r3 == 1, then this is a kprobe/jprobe.
+	 * else, this is livepatched function.
+	 *
+	 * The conditional branch for livepatch_handler below will use the
+	 * result of this comparison. For kprobe/jprobe, we just need to branch to
+	 * the new NIP, not call livepatch_handler. The branch below is bne, so we
+	 * want CR0[EQ] to be true if this is a kprobe/jprobe. Which means we want
+	 * CR0[EQ] = (r3 == 1).
+	 */
+	cmpdi	r3, 1
+1:
 #endif
 
+	/* Load CTR with the possibly modified NIP */
+	mtctr	r15
+
 	/* Restore gprs */
-	REST_8GPRS(0,r1)
-	REST_8GPRS(8,r1)
-	REST_8GPRS(16,r1)
-	REST_8GPRS(24,r1)
+	REST_GPR(0,r1)
+	REST_10GPRS(2,r1)
+	REST_10GPRS(12,r1)
+	REST_10GPRS(22,r1)
 
 	/* Restore possibly modified LR */
 	ld	r0, _LINK(r1)
@@ -119,7 +149,10 @@ ftrace_call:
 	addi r1, r1, SWITCH_FRAME_SIZE
 
 #ifdef CONFIG_LIVEPATCH
-        /* Based on the cmpd above, if the NIP was altered handle livepatch */
+        /*
+	 * Based on the cmpd or cmpdi above, if the NIP was altered and we're
+	 * not on a kprobe/jprobe, then handle livepatch.
+	 */
 	bne-	livepatch_handler
 #endif
 
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 42b7a4f..8d1a365 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1486,6 +1486,14 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
 		r = set_vpa(vcpu, &vcpu->arch.dtl, addr, len);
 		break;
 	case KVM_REG_PPC_TB_OFFSET:
+		/*
+		 * POWER9 DD1 has an erratum where writing TBU40 causes
+		 * the timebase to lose ticks.  So we don't let the
+		 * timebase offset be changed on P9 DD1.  (It is
+		 * initialized to zero.)
+		 */
+		if (cpu_has_feature(CPU_FTR_POWER9_DD1))
+			break;
 		/* round up to multiple of 2^24 */
 		vcpu->arch.vcore->tb_offset =
 			ALIGN(set_reg_val(id, *val), 1UL << 24);
@@ -2907,12 +2915,36 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 {
 	int r;
 	int srcu_idx;
+	unsigned long ebb_regs[3] = {};	/* shut up GCC */
+	unsigned long user_tar = 0;
+	unsigned int user_vrsave;
 
 	if (!vcpu->arch.sane) {
 		run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
 		return -EINVAL;
 	}
 
+	/*
+	 * Don't allow entry with a suspended transaction, because
+	 * the guest entry/exit code will lose it.
+	 * If the guest has TM enabled, save away their TM-related SPRs
+	 * (they will get restored by the TM unavailable interrupt).
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
+	    (current->thread.regs->msr & MSR_TM)) {
+		if (MSR_TM_ACTIVE(current->thread.regs->msr)) {
+			run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+			run->fail_entry.hardware_entry_failure_reason = 0;
+			return -EINVAL;
+		}
+		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+		current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+		current->thread.regs->msr &= ~MSR_TM;
+	}
+#endif
+
 	kvmppc_core_prepare_to_enter(vcpu);
 
 	/* No need to go into the guest when all we'll do is come back out */
@@ -2934,6 +2966,15 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 
 	flush_all_to_thread(current);
 
+	/* Save userspace EBB and other register values */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		ebb_regs[0] = mfspr(SPRN_EBBHR);
+		ebb_regs[1] = mfspr(SPRN_EBBRR);
+		ebb_regs[2] = mfspr(SPRN_BESCR);
+		user_tar = mfspr(SPRN_TAR);
+	}
+	user_vrsave = mfspr(SPRN_VRSAVE);
+
 	vcpu->arch.wqp = &vcpu->arch.vcore->wq;
 	vcpu->arch.pgdir = current->mm->pgd;
 	vcpu->arch.state = KVMPPC_VCPU_BUSY_IN_HOST;
@@ -2960,6 +3001,16 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		}
 	} while (is_kvmppc_resume_guest(r));
 
+	/* Restore userspace EBB and other register values */
+	if (cpu_has_feature(CPU_FTR_ARCH_207S)) {
+		mtspr(SPRN_EBBHR, ebb_regs[0]);
+		mtspr(SPRN_EBBRR, ebb_regs[1]);
+		mtspr(SPRN_BESCR, ebb_regs[2]);
+		mtspr(SPRN_TAR, user_tar);
+		mtspr(SPRN_FSCR, current->thread.fscr);
+	}
+	mtspr(SPRN_VRSAVE, user_vrsave);
+
  out:
 	vcpu->arch.state = KVMPPC_VCPU_NOTREADY;
 	atomic_dec(&vcpu->kvm->arch.vcpus_running);
diff --git a/arch/powerpc/kvm/book3s_hv_interrupts.S b/arch/powerpc/kvm/book3s_hv_interrupts.S
index 0fdc4a2..404deb5 100644
--- a/arch/powerpc/kvm/book3s_hv_interrupts.S
+++ b/arch/powerpc/kvm/book3s_hv_interrupts.S
@@ -121,10 +121,20 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 	 * Put whatever is in the decrementer into the
 	 * hypervisor decrementer.
 	 */
+BEGIN_FTR_SECTION
+	ld	r5, HSTATE_KVM_VCORE(r13)
+	ld	r6, VCORE_KVM(r5)
+	ld	r9, KVM_HOST_LPCR(r6)
+	andis.	r9, r9, LPCR_LD@h
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	mfspr	r8,SPRN_DEC
 	mftb	r7
-	mtspr	SPRN_HDEC,r8
+BEGIN_FTR_SECTION
+	/* On POWER9, don't sign-extend if host LPCR[LD] bit is set */
+	bne	32f
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 	extsw	r8,r8
+32:	mtspr	SPRN_HDEC,r8
 	add	r8,r8,r7
 	std	r8,HSTATE_DECEXP(r13)
 
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index bdb3f76..4888dd4 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -32,12 +32,29 @@
 #include <asm/opal.h>
 #include <asm/xive-regs.h>
 
+/* Sign-extend HDEC if not on POWER9 */
+#define EXTEND_HDEC(reg)			\
+BEGIN_FTR_SECTION;				\
+	extsw	reg, reg;			\
+END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
+
 #define VCPU_GPRS_TM(reg) (((reg) * ULONG_SIZE) + VCPU_GPR_TM)
 
 /* Values in HSTATE_NAPPING(r13) */
 #define NAPPING_CEDE	1
 #define NAPPING_NOVCPU	2
 
+/* Stack frame offsets for kvmppc_hv_entry */
+#define SFS			144
+#define STACK_SLOT_TRAP		(SFS-4)
+#define STACK_SLOT_TID		(SFS-16)
+#define STACK_SLOT_PSSCR	(SFS-24)
+#define STACK_SLOT_PID		(SFS-32)
+#define STACK_SLOT_IAMR		(SFS-40)
+#define STACK_SLOT_CIABR	(SFS-48)
+#define STACK_SLOT_DAWR		(SFS-56)
+#define STACK_SLOT_DAWRX	(SFS-64)
+
 /*
  * Call kvmppc_hv_entry in real mode.
  * Must be called with interrupts hard-disabled.
@@ -214,6 +231,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 kvmppc_primary_no_guest:
 	/* We handle this much like a ceded vcpu */
 	/* put the HDEC into the DEC, since HDEC interrupts don't wake us */
+	/* HDEC may be larger than DEC for arch >= v3.00, but since the */
+	/* HDEC value came from DEC in the first place, it will fit */
 	mfspr	r3, SPRN_HDEC
 	mtspr	SPRN_DEC, r3
 	/*
@@ -295,8 +314,9 @@ kvm_novcpu_wakeup:
 
 	/* See if our timeslice has expired (HDEC is negative) */
 	mfspr	r0, SPRN_HDEC
+	EXTEND_HDEC(r0)
 	li	r12, BOOK3S_INTERRUPT_HV_DECREMENTER
-	cmpwi	r0, 0
+	cmpdi	r0, 0
 	blt	kvm_novcpu_exit
 
 	/* Got an IPI but other vcpus aren't yet exiting, must be a latecomer */
@@ -319,10 +339,10 @@ kvm_novcpu_exit:
 	bl	kvmhv_accumulate_time
 #endif
 13:	mr	r3, r12
-	stw	r12, 112-4(r1)
+	stw	r12, STACK_SLOT_TRAP(r1)
 	bl	kvmhv_commence_exit
 	nop
-	lwz	r12, 112-4(r1)
+	lwz	r12, STACK_SLOT_TRAP(r1)
 	b	kvmhv_switch_to_host
 
 /*
@@ -390,8 +410,8 @@ kvm_secondary_got_guest:
 	lbz	r4, HSTATE_PTID(r13)
 	cmpwi	r4, 0
 	bne	63f
-	lis	r6, 0x7fff
-	ori	r6, r6, 0xffff
+	LOAD_REG_ADDR(r6, decrementer_max)
+	ld	r6, 0(r6)
 	mtspr	SPRN_HDEC, r6
 	/* and set per-LPAR registers, if doing dynamic micro-threading */
 	ld	r6, HSTATE_SPLIT_MODE(r13)
@@ -545,11 +565,6 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
  *                                                                            *
  *****************************************************************************/
 
-/* Stack frame offsets */
-#define STACK_SLOT_TID		(112-16)
-#define STACK_SLOT_PSSCR	(112-24)
-#define STACK_SLOT_PID		(112-32)
-
 .global kvmppc_hv_entry
 kvmppc_hv_entry:
 
@@ -565,7 +580,7 @@ kvmppc_hv_entry:
 	 */
 	mflr	r0
 	std	r0, PPC_LR_STKOFF(r1)
-	stdu	r1, -112(r1)
+	stdu	r1, -SFS(r1)
 
 	/* Save R1 in the PACA */
 	std	r1, HSTATE_HOST_R1(r13)
@@ -749,10 +764,20 @@ BEGIN_FTR_SECTION
 	mfspr	r5, SPRN_TIDR
 	mfspr	r6, SPRN_PSSCR
 	mfspr	r7, SPRN_PID
+	mfspr	r8, SPRN_IAMR
 	std	r5, STACK_SLOT_TID(r1)
 	std	r6, STACK_SLOT_PSSCR(r1)
 	std	r7, STACK_SLOT_PID(r1)
+	std	r8, STACK_SLOT_IAMR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
+BEGIN_FTR_SECTION
+	mfspr	r5, SPRN_CIABR
+	mfspr	r6, SPRN_DAWR
+	mfspr	r7, SPRN_DAWRX
+	std	r5, STACK_SLOT_CIABR(r1)
+	std	r6, STACK_SLOT_DAWR(r1)
+	std	r7, STACK_SLOT_DAWRX(r1)
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 BEGIN_FTR_SECTION
 	/* Set partition DABR */
@@ -968,7 +993,8 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 
 	/* Check if HDEC expires soon */
 	mfspr	r3, SPRN_HDEC
-	cmpwi	r3, 512		/* 1 microsecond */
+	EXTEND_HDEC(r3)
+	cmpdi	r3, 512		/* 1 microsecond */
 	blt	hdec_soon
 
 #ifdef CONFIG_KVM_XICS
@@ -1505,11 +1531,10 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
 	 * set by the guest could disrupt the host.
 	 */
 	li	r0, 0
-	mtspr	SPRN_IAMR, r0
-	mtspr	SPRN_CIABR, r0
-	mtspr	SPRN_DAWRX, r0
+	mtspr	SPRN_PSPB, r0
 	mtspr	SPRN_WORT, r0
 BEGIN_FTR_SECTION
+	mtspr	SPRN_IAMR, r0
 	mtspr	SPRN_TCSCR, r0
 	/* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
 	li	r0, 1
@@ -1525,6 +1550,7 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 	std	r6,VCPU_UAMOR(r9)
 	li	r6,0
 	mtspr	SPRN_AMR,r6
+	mtspr	SPRN_UAMOR, r6
 
 	/* Switch DSCR back to host value */
 	mfspr	r8, SPRN_DSCR
@@ -1670,12 +1696,22 @@ END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
 	/* Restore host values of some registers */
 BEGIN_FTR_SECTION
+	ld	r5, STACK_SLOT_CIABR(r1)
+	ld	r6, STACK_SLOT_DAWR(r1)
+	ld	r7, STACK_SLOT_DAWRX(r1)
+	mtspr	SPRN_CIABR, r5
+	mtspr	SPRN_DAWR, r6
+	mtspr	SPRN_DAWRX, r7
+END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
+BEGIN_FTR_SECTION
 	ld	r5, STACK_SLOT_TID(r1)
 	ld	r6, STACK_SLOT_PSSCR(r1)
 	ld	r7, STACK_SLOT_PID(r1)
+	ld	r8, STACK_SLOT_IAMR(r1)
 	mtspr	SPRN_TIDR, r5
 	mtspr	SPRN_PSSCR, r6
 	mtspr	SPRN_PID, r7
+	mtspr	SPRN_IAMR, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 BEGIN_FTR_SECTION
 	PPC_INVALIDATE_ERAT
@@ -1819,8 +1855,8 @@ END_MMU_FTR_SECTION_IFSET(MMU_FTR_TYPE_RADIX)
 	li	r0, KVM_GUEST_MODE_NONE
 	stb	r0, HSTATE_IN_GUEST(r13)
 
-	ld	r0, 112+PPC_LR_STKOFF(r1)
-	addi	r1, r1, 112
+	ld	r0, SFS+PPC_LR_STKOFF(r1)
+	addi	r1, r1, SFS
 	mtlr	r0
 	blr
 
@@ -2366,12 +2402,13 @@ END_FTR_SECTION_IFSET(CPU_FTR_TM)
 	mfspr	r3, SPRN_DEC
 	mfspr	r4, SPRN_HDEC
 	mftb	r5
-	cmpw	r3, r4
+	extsw	r3, r3
+	EXTEND_HDEC(r4)
+	cmpd	r3, r4
 	ble	67f
 	mtspr	SPRN_DEC, r4
 67:
 	/* save expiry time of guest decrementer */
-	extsw	r3, r3
 	add	r3, r3, r5
 	ld	r4, HSTATE_KVM_VCPU(r13)
 	ld	r5, HSTATE_KVM_VCORE(r13)
diff --git a/arch/powerpc/perf/perf_regs.c b/arch/powerpc/perf/perf_regs.c
index cbd82fd..09ceea6 100644
--- a/arch/powerpc/perf/perf_regs.c
+++ b/arch/powerpc/perf/perf_regs.c
@@ -101,5 +101,6 @@ void perf_get_regs_user(struct perf_regs *regs_user,
 			struct pt_regs *regs_user_copy)
 {
 	regs_user->regs = task_pt_regs(current);
-	regs_user->abi  = perf_reg_abi(current);
+	regs_user->abi = (regs_user->regs) ? perf_reg_abi(current) :
+			 PERF_SAMPLE_REGS_ABI_NONE;
 }
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index e6f444b..b5d960d 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -449,7 +449,7 @@ static int mmio_launch_invalidate(struct npu *npu, unsigned long launch,
 	return mmio_atsd_reg;
 }
 
-static int mmio_invalidate_pid(struct npu *npu, unsigned long pid)
+static int mmio_invalidate_pid(struct npu *npu, unsigned long pid, bool flush)
 {
 	unsigned long launch;
 
@@ -465,12 +465,15 @@ static int mmio_invalidate_pid(struct npu *npu, unsigned long pid)
 	/* PID */
 	launch |= pid << PPC_BITLSHIFT(38);
 
+	/* No flush */
+	launch |= !flush << PPC_BITLSHIFT(39);
+
 	/* Invalidating the entire process doesn't use a va */
 	return mmio_launch_invalidate(npu, launch, 0);
 }
 
 static int mmio_invalidate_va(struct npu *npu, unsigned long va,
-			unsigned long pid)
+			unsigned long pid, bool flush)
 {
 	unsigned long launch;
 
@@ -486,26 +489,60 @@ static int mmio_invalidate_va(struct npu *npu, unsigned long va,
 	/* PID */
 	launch |= pid << PPC_BITLSHIFT(38);
 
+	/* No flush */
+	launch |= !flush << PPC_BITLSHIFT(39);
+
 	return mmio_launch_invalidate(npu, launch, va);
 }
 
 #define mn_to_npu_context(x) container_of(x, struct npu_context, mn)
 
+struct mmio_atsd_reg {
+	struct npu *npu;
+	int reg;
+};
+
+static void mmio_invalidate_wait(
+	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS], bool flush)
+{
+	struct npu *npu;
+	int i, reg;
+
+	/* Wait for all invalidations to complete */
+	for (i = 0; i <= max_npu2_index; i++) {
+		if (mmio_atsd_reg[i].reg < 0)
+			continue;
+
+		/* Wait for completion */
+		npu = mmio_atsd_reg[i].npu;
+		reg = mmio_atsd_reg[i].reg;
+		while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
+			cpu_relax();
+
+		put_mmio_atsd_reg(npu, reg);
+
+		/*
+		 * The GPU requires two flush ATSDs to ensure all entries have
+		 * been flushed. We use PID 0 as it will never be used for a
+		 * process on the GPU.
+		 */
+		if (flush)
+			mmio_invalidate_pid(npu, 0, true);
+	}
+}
+
 /*
  * Invalidate either a single address or an entire PID depending on
  * the value of va.
  */
 static void mmio_invalidate(struct npu_context *npu_context, int va,
-			unsigned long address)
+			unsigned long address, bool flush)
 {
-	int i, j, reg;
+	int i, j;
 	struct npu *npu;
 	struct pnv_phb *nphb;
 	struct pci_dev *npdev;
-	struct {
-		struct npu *npu;
-		int reg;
-	} mmio_atsd_reg[NV_MAX_NPUS];
+	struct mmio_atsd_reg mmio_atsd_reg[NV_MAX_NPUS];
 	unsigned long pid = npu_context->mm->context.id;
 
 	/*
@@ -525,10 +562,11 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 
 			if (va)
 				mmio_atsd_reg[i].reg =
-					mmio_invalidate_va(npu, address, pid);
+					mmio_invalidate_va(npu, address, pid,
+							flush);
 			else
 				mmio_atsd_reg[i].reg =
-					mmio_invalidate_pid(npu, pid);
+					mmio_invalidate_pid(npu, pid, flush);
 
 			/*
 			 * The NPU hardware forwards the shootdown to all GPUs
@@ -544,18 +582,10 @@ static void mmio_invalidate(struct npu_context *npu_context, int va,
 	 */
 	flush_tlb_mm(npu_context->mm);
 
-	/* Wait for all invalidations to complete */
-	for (i = 0; i <= max_npu2_index; i++) {
-		if (mmio_atsd_reg[i].reg < 0)
-			continue;
-
-		/* Wait for completion */
-		npu = mmio_atsd_reg[i].npu;
-		reg = mmio_atsd_reg[i].reg;
-		while (__raw_readq(npu->mmio_atsd_regs[reg] + XTS_ATSD_STAT))
-			cpu_relax();
-		put_mmio_atsd_reg(npu, reg);
-	}
+	mmio_invalidate_wait(mmio_atsd_reg, flush);
+	if (flush)
+		/* Wait for the flush to complete */
+		mmio_invalidate_wait(mmio_atsd_reg, false);
 }
 
 static void pnv_npu2_mn_release(struct mmu_notifier *mn,
@@ -571,7 +601,7 @@ static void pnv_npu2_mn_release(struct mmu_notifier *mn,
 	 * There should be no more translation requests for this PID, but we
 	 * need to ensure any entries for it are removed from the TLB.
 	 */
-	mmio_invalidate(npu_context, 0, 0);
+	mmio_invalidate(npu_context, 0, 0, true);
 }
 
 static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
@@ -581,7 +611,7 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
 {
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 
-	mmio_invalidate(npu_context, 1, address);
+	mmio_invalidate(npu_context, 1, address, true);
 }
 
 static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
@@ -590,7 +620,7 @@ static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
 {
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 
-	mmio_invalidate(npu_context, 1, address);
+	mmio_invalidate(npu_context, 1, address, true);
 }
 
 static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
@@ -600,8 +630,11 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
 	struct npu_context *npu_context = mn_to_npu_context(mn);
 	unsigned long address;
 
-	for (address = start; address <= end; address += PAGE_SIZE)
-		mmio_invalidate(npu_context, 1, address);
+	for (address = start; address < end; address += PAGE_SIZE)
+		mmio_invalidate(npu_context, 1, address, false);
+
+	/* Do the flush only on the final addess == end */
+	mmio_invalidate(npu_context, 1, address, true);
 }
 
 static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
@@ -651,8 +684,11 @@ struct npu_context *pnv_npu2_init_context(struct pci_dev *gpdev,
 		/* No nvlink associated with this GPU device */
 		return ERR_PTR(-ENODEV);
 
-	if (!mm) {
-		/* kernel thread contexts are not supported */
+	if (!mm || mm->context.id == 0) {
+		/*
+		 * Kernel thread contexts are not supported and context id 0 is
+		 * reserved on the GPU.
+		 */
 		return ERR_PTR(-EINVAL);
 	}
 
diff --git a/arch/s390/include/asm/processor.h b/arch/s390/include/asm/processor.h
index 60d395f..aeac013 100644
--- a/arch/s390/include/asm/processor.h
+++ b/arch/s390/include/asm/processor.h
@@ -221,11 +221,6 @@ extern void release_thread(struct task_struct *);
 /* Free guarded storage control block for current */
 void exit_thread_gs(void);
 
-/*
- * Return saved PC of a blocked thread.
- */
-extern unsigned long thread_saved_pc(struct task_struct *t);
-
 unsigned long get_wchan(struct task_struct *p);
 #define task_pt_regs(tsk) ((struct pt_regs *) \
         (task_stack_page(tsk) + THREAD_SIZE) - 1)
diff --git a/arch/s390/kernel/ipl.c b/arch/s390/kernel/ipl.c
index e545ffe..8e622bb5 100644
--- a/arch/s390/kernel/ipl.c
+++ b/arch/s390/kernel/ipl.c
@@ -564,8 +564,6 @@ static struct kset *ipl_kset;
 
 static void __ipl_run(void *unused)
 {
-	if (MACHINE_IS_LPAR && ipl_info.type == IPL_TYPE_CCW)
-		diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
 	diag308(DIAG308_LOAD_CLEAR, NULL);
 	if (MACHINE_IS_VM)
 		__cpcmd("IPL", NULL, 0, NULL);
@@ -1088,10 +1086,7 @@ static void __reipl_run(void *unused)
 		break;
 	case REIPL_METHOD_CCW_DIAG:
 		diag308(DIAG308_SET, reipl_block_ccw);
-		if (MACHINE_IS_LPAR)
-			diag308(DIAG308_LOAD_NORMAL_DUMP, NULL);
-		else
-			diag308(DIAG308_LOAD_CLEAR, NULL);
+		diag308(DIAG308_LOAD_CLEAR, NULL);
 		break;
 	case REIPL_METHOD_FCP_RW_DIAG:
 		diag308(DIAG308_SET, reipl_block_fcp);
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index 999d715..bb32b86 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -41,31 +41,6 @@
 
 asmlinkage void ret_from_fork(void) asm ("ret_from_fork");
 
-/*
- * Return saved PC of a blocked thread. used in kernel/sched.
- * resume in entry.S does not create a new stack frame, it
- * just stores the registers %r6-%r15 to the frame given by
- * schedule. We want to return the address of the caller of
- * schedule, so we have to walk the backchain one time to
- * find the frame schedule() store its return address.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	struct stack_frame *sf, *low, *high;
-
-	if (!tsk || !task_stack_page(tsk))
-		return 0;
-	low = task_stack_page(tsk);
-	high = (struct stack_frame *) task_pt_regs(tsk);
-	sf = (struct stack_frame *) tsk->thread.ksp;
-	if (sf <= low || sf > high)
-		return 0;
-	sf = (struct stack_frame *) sf->back_chain;
-	if (sf <= low || sf > high)
-		return 0;
-	return sf->gprs[8];
-}
-
 extern void kernel_thread_starter(void);
 
 /*
diff --git a/arch/s390/kvm/gaccess.c b/arch/s390/kvm/gaccess.c
index 9da243d..3b297fa 100644
--- a/arch/s390/kvm/gaccess.c
+++ b/arch/s390/kvm/gaccess.c
@@ -977,11 +977,12 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
 	ptr = asce.origin * 4096;
 	if (asce.r) {
 		*fake = 1;
+		ptr = 0;
 		asce.dt = ASCE_TYPE_REGION1;
 	}
 	switch (asce.dt) {
 	case ASCE_TYPE_REGION1:
-		if (vaddr.rfx01 > asce.tl && !asce.r)
+		if (vaddr.rfx01 > asce.tl && !*fake)
 			return PGM_REGION_FIRST_TRANS;
 		break;
 	case ASCE_TYPE_REGION2:
@@ -1009,8 +1010,7 @@ static int kvm_s390_shadow_tables(struct gmap *sg, unsigned long saddr,
 		union region1_table_entry rfte;
 
 		if (*fake) {
-			/* offset in 16EB guest memory block */
-			ptr = ptr + ((unsigned long) vaddr.rsx << 53UL);
+			ptr += (unsigned long) vaddr.rfx << 53;
 			rfte.val = ptr;
 			goto shadow_r2t;
 		}
@@ -1036,8 +1036,7 @@ shadow_r2t:
 		union region2_table_entry rste;
 
 		if (*fake) {
-			/* offset in 8PB guest memory block */
-			ptr = ptr + ((unsigned long) vaddr.rtx << 42UL);
+			ptr += (unsigned long) vaddr.rsx << 42;
 			rste.val = ptr;
 			goto shadow_r3t;
 		}
@@ -1064,8 +1063,7 @@ shadow_r3t:
 		union region3_table_entry rtte;
 
 		if (*fake) {
-			/* offset in 4TB guest memory block */
-			ptr = ptr + ((unsigned long) vaddr.sx << 31UL);
+			ptr += (unsigned long) vaddr.rtx << 31;
 			rtte.val = ptr;
 			goto shadow_sgt;
 		}
@@ -1101,8 +1099,7 @@ shadow_sgt:
 		union segment_table_entry ste;
 
 		if (*fake) {
-			/* offset in 2G guest memory block */
-			ptr = ptr + ((unsigned long) vaddr.sx << 20UL);
+			ptr += (unsigned long) vaddr.sx << 20;
 			ste.val = ptr;
 			goto shadow_pgt;
 		}
diff --git a/arch/score/include/asm/processor.h b/arch/score/include/asm/processor.h
index d9a922d..2992745 100644
--- a/arch/score/include/asm/processor.h
+++ b/arch/score/include/asm/processor.h
@@ -13,7 +13,6 @@ struct task_struct;
  */
 extern void (*cpu_wait)(void);
 
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
 extern void start_thread(struct pt_regs *regs,
 			unsigned long pc, unsigned long sp);
 extern unsigned long get_wchan(struct task_struct *p);
diff --git a/arch/score/kernel/process.c b/arch/score/kernel/process.c
index eb64d7a..6e20241 100644
--- a/arch/score/kernel/process.c
+++ b/arch/score/kernel/process.c
@@ -101,11 +101,6 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *r)
 	return 1;
 }
 
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	return task_pt_regs(tsk)->cp0_epc;
-}
-
 unsigned long get_wchan(struct task_struct *task)
 {
 	if (!task || task == current || task->state == TASK_RUNNING)
diff --git a/arch/sparc/include/asm/processor_32.h b/arch/sparc/include/asm/processor_32.h
index dd27159..b395e56 100644
--- a/arch/sparc/include/asm/processor_32.h
+++ b/arch/sparc/include/asm/processor_32.h
@@ -67,9 +67,6 @@ struct thread_struct {
 	.current_ds = KERNEL_DS, \
 }
 
-/* Return saved PC of a blocked thread. */
-unsigned long thread_saved_pc(struct task_struct *t);
-
 /* Do necessary setup to start up a newly executed thread. */
 static inline void start_thread(struct pt_regs * regs, unsigned long pc,
 				    unsigned long sp)
diff --git a/arch/sparc/include/asm/processor_64.h b/arch/sparc/include/asm/processor_64.h
index b58ee90..f04dc5a 100644
--- a/arch/sparc/include/asm/processor_64.h
+++ b/arch/sparc/include/asm/processor_64.h
@@ -89,9 +89,7 @@ struct thread_struct {
 #include <linux/types.h>
 #include <asm/fpumacro.h>
 
-/* Return saved PC of a blocked thread. */
 struct task_struct;
-unsigned long thread_saved_pc(struct task_struct *);
 
 /* On Uniprocessor, even in RMO processes see TSO semantics */
 #ifdef CONFIG_SMP
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index b6dac8e..9245f93 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -177,14 +177,6 @@ void show_stack(struct task_struct *tsk, unsigned long *_ksp)
 }
 
 /*
- * Note: sparc64 has a pretty intricated thread_saved_pc, check it out.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	return task_thread_info(tsk)->kpc;
-}
-
-/*
  * Free current thread data structures etc..
  */
 void exit_thread(struct task_struct *tsk)
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index 1badc49..b96104d 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -400,25 +400,6 @@ core_initcall(sparc_sysrq_init);
 
 #endif
 
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	struct thread_info *ti = task_thread_info(tsk);
-	unsigned long ret = 0xdeadbeefUL;
-	
-	if (ti && ti->ksp) {
-		unsigned long *sp;
-		sp = (unsigned long *)(ti->ksp + STACK_BIAS);
-		if (((unsigned long)sp & (sizeof(long) - 1)) == 0UL &&
-		    sp[14]) {
-			unsigned long *fp;
-			fp = (unsigned long *)(sp[14] + STACK_BIAS);
-			if (((unsigned long)fp & (sizeof(long) - 1)) == 0UL)
-				ret = fp[15];
-		}
-	}
-	return ret;
-}
-
 /* Free current thread data structures etc.. */
 void exit_thread(struct task_struct *tsk)
 {
diff --git a/arch/tile/include/asm/processor.h b/arch/tile/include/asm/processor.h
index 0bc9968..f71e520 100644
--- a/arch/tile/include/asm/processor.h
+++ b/arch/tile/include/asm/processor.h
@@ -214,13 +214,6 @@ static inline void release_thread(struct task_struct *dead_task)
 
 extern void prepare_exit_to_usermode(struct pt_regs *regs, u32 flags);
 
-
-/*
- * Return saved (kernel) PC of a blocked thread.
- * Only used in a printk() in kernel/sched/core.c, so don't work too hard.
- */
-#define thread_saved_pc(t)   ((t)->thread.pc)
-
 unsigned long get_wchan(struct task_struct *p);
 
 /* Return initial ksp value for given task. */
diff --git a/arch/um/include/asm/processor-generic.h b/arch/um/include/asm/processor-generic.h
index 2d1e0dd..f6d1a3f 100644
--- a/arch/um/include/asm/processor-generic.h
+++ b/arch/um/include/asm/processor-generic.h
@@ -58,8 +58,6 @@ static inline void release_thread(struct task_struct *task)
 {
 }
 
-extern unsigned long thread_saved_pc(struct task_struct *t);
-
 static inline void mm_copy_segments(struct mm_struct *from_mm,
 				    struct mm_struct *new_mm)
 {
diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c
index 64a1fd0..7b56401 100644
--- a/arch/um/kernel/um_arch.c
+++ b/arch/um/kernel/um_arch.c
@@ -56,12 +56,6 @@ union thread_union cpu0_irqstack
 	__attribute__((__section__(".data..init_irqstack"))) =
 		{ INIT_THREAD_INFO(init_task) };
 
-unsigned long thread_saved_pc(struct task_struct *task)
-{
-	/* FIXME: Need to look up userspace_pid by cpu */
-	return os_process_pc(userspace_pid[0]);
-}
-
 /* Changed in setup_arch, which is called in early boot */
 static char host_info[(__NEW_UTS_LEN + 1) * 5];
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index a6d91d4..110ce82 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -431,11 +431,11 @@ static __initconst const u64 skl_hw_cache_event_ids
  [ C(DTLB) ] = {
 	[ C(OP_READ) ] = {
 		[ C(RESULT_ACCESS) ] = 0x81d0,	/* MEM_INST_RETIRED.ALL_LOADS */
-		[ C(RESULT_MISS)   ] = 0x608,	/* DTLB_LOAD_MISSES.WALK_COMPLETED */
+		[ C(RESULT_MISS)   ] = 0xe08,	/* DTLB_LOAD_MISSES.WALK_COMPLETED */
 	},
 	[ C(OP_WRITE) ] = {
 		[ C(RESULT_ACCESS) ] = 0x82d0,	/* MEM_INST_RETIRED.ALL_STORES */
-		[ C(RESULT_MISS)   ] = 0x649,	/* DTLB_STORE_MISSES.WALK_COMPLETED */
+		[ C(RESULT_MISS)   ] = 0xe49,	/* DTLB_STORE_MISSES.WALK_COMPLETED */
 	},
 	[ C(OP_PREFETCH) ] = {
 		[ C(RESULT_ACCESS) ] = 0x0,
diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h
index 0559626..722d0e5 100644
--- a/arch/x86/include/asm/kvm_emulate.h
+++ b/arch/x86/include/asm/kvm_emulate.h
@@ -296,6 +296,7 @@ struct x86_emulate_ctxt {
 
 	bool perm_ok; /* do not check permissions if true */
 	bool ud;	/* inject an #UD if host doesn't support insn */
+	bool tf;	/* TF value before instruction (after for syscall/sysret) */
 
 	bool have_exception;
 	struct x86_exception exception;
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index fba1007..d5acc27 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -2,8 +2,7 @@
 #define _ASM_X86_MSHYPER_H
 
 #include <linux/types.h>
-#include <linux/interrupt.h>
-#include <linux/clocksource.h>
+#include <linux/atomic.h>
 #include <asm/hyperv.h>
 
 /*
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3cada99..a28b671 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -860,8 +860,6 @@ extern unsigned long KSTK_ESP(struct task_struct *task);
 
 #endif /* CONFIG_X86_64 */
 
-extern unsigned long thread_saved_pc(struct task_struct *tsk);
-
 extern void start_thread(struct pt_regs *regs, unsigned long new_ip,
 					       unsigned long new_sp);
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 0bb8842..3ca1980 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -545,17 +545,6 @@ unsigned long arch_randomize_brk(struct mm_struct *mm)
 }
 
 /*
- * Return saved PC of a blocked thread.
- * What is this good for? it will be always the scheduler or ret_from_fork.
- */
-unsigned long thread_saved_pc(struct task_struct *tsk)
-{
-	struct inactive_task_frame *frame =
-		(struct inactive_task_frame *) READ_ONCE(tsk->thread.sp);
-	return READ_ONCE_NOCHECK(frame->ret_addr);
-}
-
-/*
  * Called from fs/proc with a reference on @p to find the function
  * which called into schedule(). This needs to be done carefully
  * because the task might wake up and we might look at a stack
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0816ab2..80890de 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -2742,6 +2742,7 @@ static int em_syscall(struct x86_emulate_ctxt *ctxt)
 		ctxt->eflags &= ~(X86_EFLAGS_VM | X86_EFLAGS_IF);
 	}
 
+	ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
 	return X86EMUL_CONTINUE;
 }
 
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 87d3cb9..0e846f0 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5313,6 +5313,8 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu)
 	kvm_x86_ops->get_cs_db_l_bits(vcpu, &cs_db, &cs_l);
 
 	ctxt->eflags = kvm_get_rflags(vcpu);
+	ctxt->tf = (ctxt->eflags & X86_EFLAGS_TF) != 0;
+
 	ctxt->eip = kvm_rip_read(vcpu);
 	ctxt->mode = (!is_protmode(vcpu))		? X86EMUL_MODE_REAL :
 		     (ctxt->eflags & X86_EFLAGS_VM)	? X86EMUL_MODE_VM86 :
@@ -5528,36 +5530,25 @@ static int kvm_vcpu_check_hw_bp(unsigned long addr, u32 type, u32 dr7,
 	return dr6;
 }
 
-static void kvm_vcpu_check_singlestep(struct kvm_vcpu *vcpu, unsigned long rflags, int *r)
+static void kvm_vcpu_do_singlestep(struct kvm_vcpu *vcpu, int *r)
 {
 	struct kvm_run *kvm_run = vcpu->run;
 
-	/*
-	 * rflags is the old, "raw" value of the flags.  The new value has
-	 * not been saved yet.
-	 *
-	 * This is correct even for TF set by the guest, because "the
-	 * processor will not generate this exception after the instruction
-	 * that sets the TF flag".
-	 */
-	if (unlikely(rflags & X86_EFLAGS_TF)) {
-		if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
-			kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 |
-						  DR6_RTM;
-			kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
-			kvm_run->debug.arch.exception = DB_VECTOR;
-			kvm_run->exit_reason = KVM_EXIT_DEBUG;
-			*r = EMULATE_USER_EXIT;
-		} else {
-			/*
-			 * "Certain debug exceptions may clear bit 0-3.  The
-			 * remaining contents of the DR6 register are never
-			 * cleared by the processor".
-			 */
-			vcpu->arch.dr6 &= ~15;
-			vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
-			kvm_queue_exception(vcpu, DB_VECTOR);
-		}
+	if (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP) {
+		kvm_run->debug.arch.dr6 = DR6_BS | DR6_FIXED_1 | DR6_RTM;
+		kvm_run->debug.arch.pc = vcpu->arch.singlestep_rip;
+		kvm_run->debug.arch.exception = DB_VECTOR;
+		kvm_run->exit_reason = KVM_EXIT_DEBUG;
+		*r = EMULATE_USER_EXIT;
+	} else {
+		/*
+		 * "Certain debug exceptions may clear bit 0-3.  The
+		 * remaining contents of the DR6 register are never
+		 * cleared by the processor".
+		 */
+		vcpu->arch.dr6 &= ~15;
+		vcpu->arch.dr6 |= DR6_BS | DR6_RTM;
+		kvm_queue_exception(vcpu, DB_VECTOR);
 	}
 }
 
@@ -5567,7 +5558,17 @@ int kvm_skip_emulated_instruction(struct kvm_vcpu *vcpu)
 	int r = EMULATE_DONE;
 
 	kvm_x86_ops->skip_emulated_instruction(vcpu);
-	kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+
+	/*
+	 * rflags is the old, "raw" value of the flags.  The new value has
+	 * not been saved yet.
+	 *
+	 * This is correct even for TF set by the guest, because "the
+	 * processor will not generate this exception after the instruction
+	 * that sets the TF flag".
+	 */
+	if (unlikely(rflags & X86_EFLAGS_TF))
+		kvm_vcpu_do_singlestep(vcpu, &r);
 	return r == EMULATE_DONE;
 }
 EXPORT_SYMBOL_GPL(kvm_skip_emulated_instruction);
@@ -5726,8 +5727,9 @@ restart:
 		toggle_interruptibility(vcpu, ctxt->interruptibility);
 		vcpu->arch.emulate_regs_need_sync_to_vcpu = false;
 		kvm_rip_write(vcpu, ctxt->eip);
-		if (r == EMULATE_DONE)
-			kvm_vcpu_check_singlestep(vcpu, rflags, &r);
+		if (r == EMULATE_DONE &&
+		    (ctxt->tf || (vcpu->guest_debug & KVM_GUESTDBG_SINGLESTEP)))
+			kvm_vcpu_do_singlestep(vcpu, &r);
 		if (!ctxt->have_exception ||
 		    exception_type(ctxt->exception.vector) == EXCPT_TRAP)
 			__kvm_set_rflags(vcpu, ctxt->eflags);
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 003eeee..30ee8c6 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -213,8 +213,6 @@ struct mm_struct;
 #define release_segments(mm)	do { } while(0)
 #define forget_segments()	do { } while (0)
 
-#define thread_saved_pc(tsk)	(task_pt_regs(tsk)->pc)
-
 extern unsigned long get_wchan(struct task_struct *p);
 
 #define KSTK_EIP(tsk)		(task_pt_regs(tsk)->pc)