Merge branch 'x86/asm' into x86/mm, to resolve conflicts

 Conflicts:
	tools/testing/selftests/x86/Makefile

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

39 files changed, 560 insertions, 275 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d9a94da0c29f..df884a522c39 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -294,11 +294,6 @@ config X86_32_LAZY_GS
 	def_bool y
 	depends on X86_32 && !CC_STACKPROTECTOR
 
-config ARCH_HWEIGHT_CFLAGS
-	string
-	default "-fcall-saved-ecx -fcall-saved-edx" if X86_32
-	default "-fcall-saved-rdi -fcall-saved-rsi -fcall-saved-rdx -fcall-saved-rcx -fcall-saved-r8 -fcall-saved-r9 -fcall-saved-r10 -fcall-saved-r11" if X86_64
-
 config ARCH_SUPPORTS_UPROBES
 	def_bool y
 
diff --git a/arch/x86/boot/bitops.h b/arch/x86/boot/bitops.h
index 878e4b9940d9..0d41d68131cc 100644
--- a/arch/x86/boot/bitops.h
+++ b/arch/x86/boot/bitops.h
@@ -16,14 +16,16 @@
 #define BOOT_BITOPS_H
 #define _LINUX_BITOPS_H		/* Inhibit inclusion of <linux/bitops.h> */
 
-static inline int constant_test_bit(int nr, const void *addr)
+#include <linux/types.h>
+
+static inline bool constant_test_bit(int nr, const void *addr)
 {
 	const u32 *p = (const u32 *)addr;
 	return ((1UL << (nr & 31)) & (p[nr >> 5])) != 0;
 }
-static inline int variable_test_bit(int nr, const void *addr)
+static inline bool variable_test_bit(int nr, const void *addr)
 {
-	u8 v;
+	bool v;
 	const u32 *p = (const u32 *)addr;
 
 	asm("btl %2,%1; setc %0" : "=qm" (v) : "m" (*p), "Ir" (nr));
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index a5ce666a2423..e5612f3e3b57 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -24,6 +24,7 @@
 #include <linux/types.h>
 #include <linux/edd.h>
 #include <asm/setup.h>
+#include <asm/asm.h>
 #include "bitops.h"
 #include "ctype.h"
 #include "cpuflags.h"
@@ -176,18 +177,18 @@ static inline void wrgs32(u32 v, addr_t addr)
 }
 
 /* Note: these only return true/false, not a signed return value! */
-static inline int memcmp_fs(const void *s1, addr_t s2, size_t len)
+static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
 {
-	u8 diff;
-	asm volatile("fs; repe; cmpsb; setnz %0"
-		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	bool diff;
+	asm volatile("fs; repe; cmpsb" CC_SET(nz)
+		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
-static inline int memcmp_gs(const void *s1, addr_t s2, size_t len)
+static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
 {
-	u8 diff;
-	asm volatile("gs; repe; cmpsb; setnz %0"
-		     : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
+	bool diff;
+	asm volatile("gs; repe; cmpsb" CC_SET(nz)
+		     : CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
 }
 
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 318b8465d302..cc3bd583dce1 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -17,7 +17,7 @@
 
 int memcmp(const void *s1, const void *s2, size_t len)
 {
-	u8 diff;
+	bool diff;
 	asm("repe; cmpsb; setnz %0"
 	    : "=qm" (diff), "+D" (s1), "+S" (s2), "+c" (len));
 	return diff;
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index ec138e538c44..9e1e27d31c6d 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -40,10 +40,10 @@ static struct thread_info *pt_regs_to_thread_info(struct pt_regs *regs)
 
 #ifdef CONFIG_CONTEXT_TRACKING
 /* Called on entry from user mode with IRQs off. */
-__visible void enter_from_user_mode(void)
+__visible inline void enter_from_user_mode(void)
 {
 	CT_WARN_ON(ct_state() != CONTEXT_USER);
-	user_exit();
+	user_exit_irqoff();
 }
 #else
 static inline void enter_from_user_mode(void) {}
@@ -274,7 +274,7 @@ __visible inline void prepare_exit_to_usermode(struct pt_regs *regs)
 	ti->status &= ~TS_COMPAT;
 #endif
 
-	user_enter();
+	user_enter_irqoff();
 }
 
 #define SYSCALL_EXIT_WORK_FLAGS				\
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 027aec4a74df..627ecbcb2e62 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -33,7 +33,7 @@
 	.endif
 
 	call \func
-	jmp  restore
+	jmp  .L_restore
 	_ASM_NOKPROBE(\name)
 	.endm
 
@@ -54,7 +54,7 @@
 #if defined(CONFIG_TRACE_IRQFLAGS) \
  || defined(CONFIG_DEBUG_LOCK_ALLOC) \
  || defined(CONFIG_PREEMPT)
-restore:
+.L_restore:
 	popq %r11
 	popq %r10
 	popq %r9
@@ -66,5 +66,5 @@ restore:
 	popq %rdi
 	popq %rbp
 	ret
-	_ASM_NOKPROBE(restore)
+	_ASM_NOKPROBE(.L_restore)
 #endif
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 253b72eaade6..68b63fddc209 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -134,7 +134,7 @@ VDSO_LDFLAGS_vdso32.lds = -m32 -Wl,-m,elf_i386 -Wl,-soname=linux-gate.so.1
 override obj-dirs = $(dir $(obj)) $(obj)/vdso32/
 
 targets += vdso32/vdso32.lds
-targets += vdso32/note.o vdso32/vclock_gettime.o vdso32/system_call.o
+targets += vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
 targets += vdso32/vclock_gettime.o
 
 KBUILD_AFLAGS_32 := $(filter-out -m64,$(KBUILD_AFLAGS)) -DBUILD_VDSO
@@ -156,7 +156,8 @@ $(obj)/vdso32.so.dbg: FORCE \
 		      $(obj)/vdso32/vdso32.lds \
 		      $(obj)/vdso32/vclock_gettime.o \
 		      $(obj)/vdso32/note.o \
-		      $(obj)/vdso32/system_call.o
+		      $(obj)/vdso32/system_call.o \
+		      $(obj)/vdso32/sigreturn.o
 	$(call if_changed,vdso)
 
 #
diff --git a/arch/x86/entry/vdso/vdso32/sigreturn.S b/arch/x86/entry/vdso/vdso32/sigreturn.S
index d7ec4e251c0a..20633e026e82 100644
--- a/arch/x86/entry/vdso/vdso32/sigreturn.S
+++ b/arch/x86/entry/vdso/vdso32/sigreturn.S
@@ -1,11 +1,3 @@
-/*
- * Common code for the sigreturn entry points in vDSO images.
- * So far this code is the same for both int80 and sysenter versions.
- * This file is #include'd by int80.S et al to define them first thing.
- * The kernel assumes that the addresses of these routines are constant
- * for all vDSO implementations.
- */
-
 #include <linux/linkage.h>
 #include <asm/unistd_32.h>
 #include <asm/asm-offsets.h>
diff --git a/arch/x86/entry/vdso/vdso32/system_call.S b/arch/x86/entry/vdso/vdso32/system_call.S
index 0109ac6cb79c..ed4bc9731cbb 100644
--- a/arch/x86/entry/vdso/vdso32/system_call.S
+++ b/arch/x86/entry/vdso/vdso32/system_call.S
@@ -2,16 +2,11 @@
  * AT_SYSINFO entry point
 */
 
+#include <linux/linkage.h>
 #include <asm/dwarf2.h>
 #include <asm/cpufeatures.h>
 #include <asm/alternative-asm.h>
 
-/*
- * First get the common code for the sigreturn entry points.
- * This must come first.
- */
-#include "sigreturn.S"
-
 	.text
 	.globl __kernel_vsyscall
 	.type __kernel_vsyscall,@function
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 33787ee817f0..26ced536005a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2319,7 +2319,7 @@ void
 perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs)
 {
 	struct stack_frame frame;
-	const void __user *fp;
+	const unsigned long __user *fp;
 
 	if (perf_guest_cbs && perf_guest_cbs->is_in_guest()) {
 		/* TODO: We don't support guest os callchain now */
@@ -2332,7 +2332,7 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	if (regs->flags & (X86_VM_MASK | PERF_EFLAGS_VM))
 		return;
 
-	fp = (void __user *)regs->bp;
+	fp = (unsigned long __user *)regs->bp;
 
 	perf_callchain_store(entry, regs->ip);
 
@@ -2345,16 +2345,17 @@ perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs
 	pagefault_disable();
 	while (entry->nr < entry->max_stack) {
 		unsigned long bytes;
+
 		frame.next_frame	     = NULL;
 		frame.return_address = 0;
 
-		if (!access_ok(VERIFY_READ, fp, 16))
+		if (!access_ok(VERIFY_READ, fp, sizeof(*fp) * 2))
 			break;
 
-		bytes = __copy_from_user_nmi(&frame.next_frame, fp, 8);
+		bytes = __copy_from_user_nmi(&frame.next_frame, fp, sizeof(*fp));
 		if (bytes != 0)
 			break;
-		bytes = __copy_from_user_nmi(&frame.return_address, fp+8, 8);
+		bytes = __copy_from_user_nmi(&frame.return_address, fp + 1, sizeof(*fp));
 		if (bytes != 0)
 			break;
 
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
index 3660b2cf245a..06c2baa51814 100644
--- a/arch/x86/events/intel/Makefile
+++ b/arch/x86/events/intel/Makefile
@@ -1,8 +1,8 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o cqm.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl.o
-intel-rapl-objs				:= rapl.o
+obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
+intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 7c666958a625..9b4f9d3ce465 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -115,6 +115,10 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */
 	INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -139,6 +143,10 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly =
 	INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */
 	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -182,6 +190,16 @@ struct event_constraint intel_skl_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x003c, 1),	/* CPU_CLK_UNHALTED.CORE */
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x1c0, 0x2),	/* INST_RETIRED.PREC_DIST */
+
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xc6, 0xf),	/* FRONTEND_RETIRED.* */
+
 	EVENT_CONSTRAINT_END
 };
 
@@ -250,6 +268,10 @@ static struct event_constraint intel_hsw_event_constraints[] = {
 	/* CYCLE_ACTIVITY.CYCLES_NO_EXECUTE */
 	INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf),
 
+	/*
+	 * When HT is off these events can only run on the bottom 4 counters
+	 * When HT is on, they are impacted by the HT bug and require EXCL access
+	 */
 	INTEL_EXCLEVT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */
 	INTEL_EXCLEVT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */
@@ -264,6 +286,13 @@ struct event_constraint intel_bdw_event_constraints[] = {
 	FIXED_EVENT_CONSTRAINT(0x0300, 2),	/* CPU_CLK_UNHALTED.REF */
 	INTEL_UEVENT_CONSTRAINT(0x148, 0x4),	/* L1D_PEND_MISS.PENDING */
 	INTEL_UBIT_EVENT_CONSTRAINT(0x8a3, 0x4),	/* CYCLE_ACTIVITY.CYCLES_L1D_MISS */
+	/*
+	 * when HT is off, these can only run on the bottom 4 counters
+	 */
+	INTEL_EVENT_CONSTRAINT(0xd0, 0xf),	/* MEM_INST_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd1, 0xf),	/* MEM_LOAD_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xd2, 0xf),	/* MEM_LOAD_L3_HIT_RETIRED.* */
+	INTEL_EVENT_CONSTRAINT(0xcd, 0xf),	/* MEM_TRANS_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 20370c6db74b..93eebc636c76 100644
--- a/arch/x86/include/asm/apm.h
+++ b/arch/x86/include/asm/apm.h
@@ -45,11 +45,11 @@ static inline void apm_bios_call_asm(u32 func, u32 ebx_in, u32 ecx_in,
 		: "memory", "cc");
 }
 
-static inline u8 apm_bios_call_simple_asm(u32 func, u32 ebx_in,
-						u32 ecx_in, u32 *eax)
+static inline bool apm_bios_call_simple_asm(u32 func, u32 ebx_in,
+					    u32 ecx_in, u32 *eax)
 {
 	int	cx, dx, si;
-	u8	error;
+	bool	error;
 
 	/*
 	 * N.B. We do NOT need a cld after the BIOS call
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index 02e799fa43d1..e7cd63175de4 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -4,8 +4,8 @@
 #include <asm/cpufeatures.h>
 
 #ifdef CONFIG_64BIT
-/* popcnt %edi, %eax -- redundant REX prefix for alignment */
-#define POPCNT32 ".byte 0xf3,0x40,0x0f,0xb8,0xc7"
+/* popcnt %edi, %eax */
+#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7"
 /* popcnt %rdi, %rax */
 #define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
 #define REG_IN "D"
@@ -17,19 +17,15 @@
 #define REG_OUT "a"
 #endif
 
-/*
- * __sw_hweightXX are called from within the alternatives below
- * and callee-clobbered registers need to be taken care of. See
- * ARCH_HWEIGHT_CFLAGS in <arch/x86/Kconfig> for the respective
- * compiler switches.
- */
+#define __HAVE_ARCH_SW_HWEIGHT
+
 static __always_inline unsigned int __arch_hweight32(unsigned int w)
 {
-	unsigned int res = 0;
+	unsigned int res;
 
 	asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
-		     : "="REG_OUT (res)
-		     : REG_IN (w));
+			 : "="REG_OUT (res)
+			 : REG_IN (w));
 
 	return res;
 }
@@ -53,11 +49,11 @@ static inline unsigned long __arch_hweight64(__u64 w)
 #else
 static __always_inline unsigned long __arch_hweight64(__u64 w)
 {
-	unsigned long res = 0;
+	unsigned long res;
 
 	asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
-		     : "="REG_OUT (res)
-		     : REG_IN (w));
+			 : "="REG_OUT (res)
+			 : REG_IN (w));
 
 	return res;
 }
diff --git a/arch/x86/include/asm/archrandom.h b/arch/x86/include/asm/archrandom.h
index 69f1366f1aa3..5b0579abb398 100644
--- a/arch/x86/include/asm/archrandom.h
+++ b/arch/x86/include/asm/archrandom.h
@@ -25,8 +25,6 @@
 
 #include <asm/processor.h>
 #include <asm/cpufeature.h>
-#include <asm/alternative.h>
-#include <asm/nops.h>
 
 #define RDRAND_RETRY_LOOPS	10
 
@@ -40,97 +38,91 @@
 # define RDSEED_LONG	RDSEED_INT
 #endif
 
-#ifdef CONFIG_ARCH_RANDOM
+/* Unconditional execution of RDRAND and RDSEED */
 
-/* Instead of arch_get_random_long() when alternatives haven't run. */
-static inline int rdrand_long(unsigned long *v)
+static inline bool rdrand_long(unsigned long *v)
 {
-	int ok;
-	asm volatile("1: " RDRAND_LONG "\n\t"
-		     "jc 2f\n\t"
-		     "decl %0\n\t"
-		     "jnz 1b\n\t"
-		     "2:"
-		     : "=r" (ok), "=a" (*v)
-		     : "0" (RDRAND_RETRY_LOOPS));
-	return ok;
+	bool ok;
+	unsigned int retry = RDRAND_RETRY_LOOPS;
+	do {
+		asm volatile(RDRAND_LONG "\n\t"
+			     CC_SET(c)
+			     : CC_OUT(c) (ok), "=a" (*v));
+		if (ok)
+			return true;
+	} while (--retry);
+	return false;
+}
+
+static inline bool rdrand_int(unsigned int *v)
+{
+	bool ok;
+	unsigned int retry = RDRAND_RETRY_LOOPS;
+	do {
+		asm volatile(RDRAND_INT "\n\t"
+			     CC_SET(c)
+			     : CC_OUT(c) (ok), "=a" (*v));
+		if (ok)
+			return true;
+	} while (--retry);
+	return false;
 }
 
-/* A single attempt at RDSEED */
 static inline bool rdseed_long(unsigned long *v)
 {
-	unsigned char ok;
+	bool ok;
 	asm volatile(RDSEED_LONG "\n\t"
-		     "setc %0"
-		     : "=qm" (ok), "=a" (*v));
+		     CC_SET(c)
+		     : CC_OUT(c) (ok), "=a" (*v));
 	return ok;
 }
 
-#define GET_RANDOM(name, type, rdrand, nop)			\
-static inline int name(type *v)					\
-{								\
-	int ok;							\
-	alternative_io("movl $0, %0\n\t"			\
-		       nop,					\
-		       "\n1: " rdrand "\n\t"			\
-		       "jc 2f\n\t"				\
-		       "decl %0\n\t"                            \
-		       "jnz 1b\n\t"                             \
-		       "2:",                                    \
-		       X86_FEATURE_RDRAND,                      \
-		       ASM_OUTPUT2("=r" (ok), "=a" (*v)),       \
-		       "0" (RDRAND_RETRY_LOOPS));		\
-	return ok;						\
-}
-
-#define GET_SEED(name, type, rdseed, nop)			\
-static inline int name(type *v)					\
-{								\
-	unsigned char ok;					\
-	alternative_io("movb $0, %0\n\t"			\
-		       nop,					\
-		       rdseed "\n\t"				\
-		       "setc %0",				\
-		       X86_FEATURE_RDSEED,                      \
-		       ASM_OUTPUT2("=q" (ok), "=a" (*v)));	\
-	return ok;						\
+static inline bool rdseed_int(unsigned int *v)
+{
+	bool ok;
+	asm volatile(RDSEED_INT "\n\t"
+		     CC_SET(c)
+		     : CC_OUT(c) (ok), "=a" (*v));
+	return ok;
 }
 
-#ifdef CONFIG_X86_64
-
-GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP5);
-GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP4);
-
-GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP5);
-GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
-
-#else
-
-GET_RANDOM(arch_get_random_long, unsigned long, RDRAND_LONG, ASM_NOP3);
-GET_RANDOM(arch_get_random_int, unsigned int, RDRAND_INT, ASM_NOP3);
-
-GET_SEED(arch_get_random_seed_long, unsigned long, RDSEED_LONG, ASM_NOP4);
-GET_SEED(arch_get_random_seed_int, unsigned int, RDSEED_INT, ASM_NOP4);
-
-#endif /* CONFIG_X86_64 */
-
+/* Conditional execution based on CPU type */
 #define arch_has_random()	static_cpu_has(X86_FEATURE_RDRAND)
 #define arch_has_random_seed()	static_cpu_has(X86_FEATURE_RDSEED)
 
-#else
+/*
+ * These are the generic interfaces; they must not be declared if the
+ * stubs in <linux/random.h> are to be invoked,
+ * i.e. CONFIG_ARCH_RANDOM is not defined.
+ */
+#ifdef CONFIG_ARCH_RANDOM
 
-static inline int rdrand_long(unsigned long *v)
+static inline bool arch_get_random_long(unsigned long *v)
 {
-	return 0;
+	return arch_has_random() ? rdrand_long(v) : false;
 }
 
-static inline bool rdseed_long(unsigned long *v)
+static inline bool arch_get_random_int(unsigned int *v)
 {
-	return 0;
+	return arch_has_random() ? rdrand_int(v) : false;
 }
 
-#endif  /* CONFIG_ARCH_RANDOM */
+static inline bool arch_get_random_seed_long(unsigned long *v)
+{
+	return arch_has_random_seed() ? rdseed_long(v) : false;
+}
+
+static inline bool arch_get_random_seed_int(unsigned int *v)
+{
+	return arch_has_random_seed() ? rdseed_int(v) : false;
+}
 
 extern void x86_init_rdrand(struct cpuinfo_x86 *c);
 
+#else  /* !CONFIG_ARCH_RANDOM */
+
+static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { }
+
+#endif  /* !CONFIG_ARCH_RANDOM */
+
 #endif /* ASM_X86_ARCHRANDOM_H */
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index f5063b6659eb..7acb51c49fec 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -42,6 +42,18 @@
 #define _ASM_SI		__ASM_REG(si)
 #define _ASM_DI		__ASM_REG(di)
 
+/*
+ * Macros to generate condition code outputs from inline assembly,
+ * The output operand must be type "bool".
+ */
+#ifdef __GCC_ASM_FLAG_OUTPUTS__
+# define CC_SET(c) "\n\t/* output condition code " #c "*/\n"
+# define CC_OUT(c) "=@cc" #c
+#else
+# define CC_SET(c) "\n\tset" #c " %[_cc_" #c "]\n"
+# define CC_OUT(c) [_cc_ ## c] "=qm"
+#endif
+
 /* Exception table entry */
 #ifdef __ASSEMBLY__
 # define _ASM_EXTABLE_HANDLE(from, to, handler)			\
diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h
index 3e8674288198..7322c1566f63 100644
--- a/arch/x86/include/asm/atomic.h
+++ b/arch/x86/include/asm/atomic.h
@@ -75,9 +75,9 @@ static __always_inline void atomic_sub(int i, atomic_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static __always_inline int atomic_sub_and_test(int i, atomic_t *v)
+static __always_inline bool atomic_sub_and_test(int i, atomic_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", "e");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subl", v->counter, "er", i, "%0", e);
 }
 
 /**
@@ -112,9 +112,9 @@ static __always_inline void atomic_dec(atomic_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static __always_inline int atomic_dec_and_test(atomic_t *v)
+static __always_inline bool atomic_dec_and_test(atomic_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decl", v->counter, "%0", e);
 }
 
 /**
@@ -125,9 +125,9 @@ static __always_inline int atomic_dec_and_test(atomic_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static __always_inline int atomic_inc_and_test(atomic_t *v)
+static __always_inline bool atomic_inc_and_test(atomic_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incl", v->counter, "%0", e);
 }
 
 /**
@@ -139,9 +139,9 @@ static __always_inline int atomic_inc_and_test(atomic_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static __always_inline int atomic_add_negative(int i, atomic_t *v)
+static __always_inline bool atomic_add_negative(int i, atomic_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", "s");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addl", v->counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 037351022f54..57bf925710d9 100644
--- a/arch/x86/include/asm/atomic64_64.h
+++ b/arch/x86/include/asm/atomic64_64.h
@@ -70,9 +70,9 @@ static inline void atomic64_sub(long i, atomic64_t *v)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_sub_and_test(long i, atomic64_t *v)
+static inline bool atomic64_sub_and_test(long i, atomic64_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", "e");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "subq", v->counter, "er", i, "%0", e);
 }
 
 /**
@@ -109,9 +109,9 @@ static __always_inline void atomic64_dec(atomic64_t *v)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int atomic64_dec_and_test(atomic64_t *v)
+static inline bool atomic64_dec_and_test(atomic64_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "decq", v->counter, "%0", e);
 }
 
 /**
@@ -122,9 +122,9 @@ static inline int atomic64_dec_and_test(atomic64_t *v)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int atomic64_inc_and_test(atomic64_t *v)
+static inline bool atomic64_inc_and_test(atomic64_t *v)
 {
-	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", "e");
+	GEN_UNARY_RMWcc(LOCK_PREFIX "incq", v->counter, "%0", e);
 }
 
 /**
@@ -136,9 +136,9 @@ static inline int atomic64_inc_and_test(atomic64_t *v)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int atomic64_add_negative(long i, atomic64_t *v)
+static inline bool atomic64_add_negative(long i, atomic64_t *v)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", "s");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "addq", v->counter, "er", i, "%0", s);
 }
 
 /**
@@ -180,7 +180,7 @@ static inline long atomic64_xchg(atomic64_t *v, long new)
  * Atomically adds @a to @v, so long as it was not @u.
  * Returns the old value of @v.
  */
-static inline int atomic64_add_unless(atomic64_t *v, long a, long u)
+static inline bool atomic64_add_unless(atomic64_t *v, long a, long u)
 {
 	long c, old;
 	c = atomic64_read(v);
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 7766d1cf096e..68557f52b961 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -201,9 +201,9 @@ static __always_inline void change_bit(long nr, volatile unsigned long *addr)
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static __always_inline int test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", "c");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "bts", *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -213,7 +213,7 @@ static __always_inline int test_and_set_bit(long nr, volatile unsigned long *add
  *
  * This is the same as test_and_set_bit on x86.
  */
-static __always_inline int
+static __always_inline bool
 test_and_set_bit_lock(long nr, volatile unsigned long *addr)
 {
 	return test_and_set_bit(nr, addr);
@@ -228,13 +228,13 @@ test_and_set_bit_lock(long nr, volatile unsigned long *addr)
  * If two examples of this operation race, one can appear to succeed
  * but actually fail.  You must protect multiple accesses with a lock.
  */
-static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	bool oldbit;
 
 	asm("bts %2,%1\n\t"
-	    "sbb %0,%0"
-	    : "=r" (oldbit), ADDR
+	    CC_SET(c)
+	    : CC_OUT(c) (oldbit), ADDR
 	    : "Ir" (nr));
 	return oldbit;
 }
@@ -247,9 +247,9 @@ static __always_inline int __test_and_set_bit(long nr, volatile unsigned long *a
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", "c");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btr", *addr, "Ir", nr, "%0", c);
 }
 
 /**
@@ -268,25 +268,25 @@ static __always_inline int test_and_clear_bit(long nr, volatile unsigned long *a
  * accessed from a hypervisor on the same CPU if running in a VM: don't change
  * this without also updating arch/x86/kernel/kvm.c
  */
-static __always_inline int __test_and_clear_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	bool oldbit;
 
 	asm volatile("btr %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr));
 	return oldbit;
 }
 
 /* WARNING: non atomic and it can be reordered! */
-static __always_inline int __test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	bool oldbit;
 
 	asm volatile("btc %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit), ADDR
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit), ADDR
 		     : "Ir" (nr) : "memory");
 
 	return oldbit;
@@ -300,24 +300,24 @@ static __always_inline int __test_and_change_bit(long nr, volatile unsigned long
  * This operation is atomic and cannot be reordered.
  * It also implies a memory barrier.
  */
-static __always_inline int test_and_change_bit(long nr, volatile unsigned long *addr)
+static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", "c");
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btc", *addr, "Ir", nr, "%0", c);
 }
 
-static __always_inline int constant_test_bit(long nr, const volatile unsigned long *addr)
+static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
 {
 	return ((1UL << (nr & (BITS_PER_LONG-1))) &
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
-static __always_inline int variable_test_bit(long nr, volatile const unsigned long *addr)
+static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
-	int oldbit;
+	bool oldbit;
 
 	asm volatile("bt %2,%1\n\t"
-		     "sbb %0,%0"
-		     : "=r" (oldbit)
+		     CC_SET(c)
+		     : CC_OUT(c) (oldbit)
 		     : "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
@@ -329,7 +329,7 @@ static __always_inline int variable_test_bit(long nr, volatile const unsigned lo
  * @nr: bit number to test
  * @addr: Address to start counting from
  */
-static int test_bit(int nr, const volatile unsigned long *addr);
+static bool test_bit(int nr, const volatile unsigned long *addr);
 #endif
 
 #define test_bit(nr, addr)			\
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 5a3b2c119ed0..a18806165fe4 100644
--- a/arch/x86/include/asm/compat.h
+++ b/arch/x86/include/asm/compat.h
@@ -40,6 +40,7 @@ typedef s32		compat_long_t;
 typedef s64 __attribute__((aligned(4))) compat_s64;
 typedef u32		compat_uint_t;
 typedef u32		compat_ulong_t;
+typedef u32		compat_u32;
 typedef u64 __attribute__((aligned(4))) compat_u64;
 typedef u32		compat_uptr_t;
 
@@ -181,6 +182,16 @@ typedef struct compat_siginfo {
 		/* SIGILL, SIGFPE, SIGSEGV, SIGBUS */
 		struct {
 			unsigned int _addr;	/* faulting insn/memory ref. */
+			short int _addr_lsb;	/* Valid LSB of the reported address. */
+			union {
+				/* used when si_code=SEGV_BNDERR */
+				struct {
+					compat_uptr_t _lower;
+					compat_uptr_t _upper;
+				} _addr_bnd;
+				/* used when si_code=SEGV_PKUERR */
+				compat_u32 _pkey;
+			};
 		} _sigfault;
 
 		/* SIGPOLL */
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 4ad6560847b1..7511978093eb 100644
--- a/arch/x86/include/asm/local.h
+++ b/arch/x86/include/asm/local.h
@@ -50,9 +50,9 @@ static inline void local_sub(long i, local_t *l)
  * true if the result is zero, or false for all
  * other cases.
  */
-static inline int local_sub_and_test(long i, local_t *l)
+static inline bool local_sub_and_test(long i, local_t *l)
 {
-	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", "e");
+	GEN_BINARY_RMWcc(_ASM_SUB, l->a.counter, "er", i, "%0", e);
 }
 
 /**
@@ -63,9 +63,9 @@ static inline int local_sub_and_test(long i, local_t *l)
  * returns true if the result is 0, or false for all other
  * cases.
  */
-static inline int local_dec_and_test(local_t *l)
+static inline bool local_dec_and_test(local_t *l)
 {
-	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", "e");
+	GEN_UNARY_RMWcc(_ASM_DEC, l->a.counter, "%0", e);
 }
 
 /**
@@ -76,9 +76,9 @@ static inline int local_dec_and_test(local_t *l)
  * and returns true if the result is zero, or false for all
  * other cases.
  */
-static inline int local_inc_and_test(local_t *l)
+static inline bool local_inc_and_test(local_t *l)
 {
-	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", "e");
+	GEN_UNARY_RMWcc(_ASM_INC, l->a.counter, "%0", e);
 }
 
 /**
@@ -90,9 +90,9 @@ static inline int local_inc_and_test(local_t *l)
  * if the result is negative, or false when
  * result is greater than or equal to zero.
  */
-static inline int local_add_negative(long i, local_t *l)
+static inline bool local_add_negative(long i, local_t *l)
 {
-	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", "s");
+	GEN_BINARY_RMWcc(_ASM_ADD, l->a.counter, "er", i, "%0", s);
 }
 
 /**
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e0ba66ca68c6..e02e3f80d363 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -510,14 +510,15 @@ do {									\
 /* This is not atomic against other CPUs -- CPU preemption needs to be off */
 #define x86_test_and_clear_bit_percpu(bit, var)				\
 ({									\
-	int old__;							\
-	asm volatile("btr %2,"__percpu_arg(1)"\n\tsbbl %0,%0"		\
-		     : "=r" (old__), "+m" (var)				\
+	bool old__;							\
+	asm volatile("btr %2,"__percpu_arg(1)"\n\t"			\
+		     CC_SET(c)						\
+		     : CC_OUT(c) (old__), "+m" (var)			\
 		     : "dIr" (bit));					\
 	old__;								\
 })
 
-static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
+static __always_inline bool x86_this_cpu_constant_test_bit(unsigned int nr,
                         const unsigned long __percpu *addr)
 {
 	unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG;
@@ -529,14 +530,14 @@ static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr,
 #endif
 }
 
-static inline int x86_this_cpu_variable_test_bit(int nr,
+static inline bool x86_this_cpu_variable_test_bit(int nr,
                         const unsigned long __percpu *addr)
 {
-	int oldbit;
+	bool oldbit;
 
 	asm volatile("bt "__percpu_arg(2)",%1\n\t"
-			"sbb %0,%0"
-			: "=r" (oldbit)
+			CC_SET(c)
+			: CC_OUT(c) (oldbit)
 			: "m" (*(unsigned long *)addr), "Ir" (nr));
 
 	return oldbit;
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index d397deb58146..17f218645701 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -81,7 +81,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), "e");
+	GEN_UNARY_RMWcc("decl", __preempt_count, __percpu_arg(0), e);
 }
 
 /*
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 8f7866a5b9a4..661dd305694a 100644
--- a/arch/x86/include/asm/rmwcc.h
+++ b/arch/x86/include/asm/rmwcc.h
@@ -1,11 +1,13 @@
 #ifndef _ASM_X86_RMWcc
 #define _ASM_X86_RMWcc
 
-#ifdef CC_HAVE_ASM_GOTO
+#if !defined(__GCC_ASM_FLAG_OUTPUTS__) && defined(CC_HAVE_ASM_GOTO)
+
+/* Use asm goto */
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	asm_volatile_goto (fullop "; j" cc " %l[cc_label]"		\
+	asm_volatile_goto (fullop "; j" #cc " %l[cc_label]"		\
 			: : "m" (var), ## __VA_ARGS__ 			\
 			: "memory" : cc_label);				\
 	return 0;							\
@@ -19,15 +21,17 @@ cc_label:								\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %1, " arg0, var, cc, vcon (val))
 
-#else /* !CC_HAVE_ASM_GOTO */
+#else /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
+
+/* Use flags output or a set instruction */
 
 #define __GEN_RMWcc(fullop, var, cc, ...)				\
 do {									\
-	char c;								\
-	asm volatile (fullop "; set" cc " %1"				\
-			: "+m" (var), "=qm" (c)				\
+	bool c;								\
+	asm volatile (fullop ";" CC_SET(cc)				\
+			: "+m" (var), CC_OUT(cc) (c)			\
 			: __VA_ARGS__ : "memory");			\
-	return c != 0;							\
+	return c;							\
 } while (0)
 
 #define GEN_UNARY_RMWcc(op, var, arg0, cc)				\
@@ -36,6 +40,6 @@ do {									\
 #define GEN_BINARY_RMWcc(op, var, vcon, val, arg0, cc)			\
 	__GEN_RMWcc(op " %2, " arg0, var, cc, vcon (val))
 
-#endif /* CC_HAVE_ASM_GOTO */
+#endif /* defined(__GCC_ASM_FLAG_OUTPUTS__) || !defined(CC_HAVE_ASM_GOTO) */
 
 #endif /* _ASM_X86_RMWcc */
diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h
index 453744c1d347..1e8be263065e 100644
--- a/arch/x86/include/asm/rwsem.h
+++ b/arch/x86/include/asm/rwsem.h
@@ -77,7 +77,7 @@ static inline void __down_read(struct rw_semaphore *sem)
 /*
  * trylock for reading -- returns 1 if successful, 0 if contention
  */
-static inline int __down_read_trylock(struct rw_semaphore *sem)
+static inline bool __down_read_trylock(struct rw_semaphore *sem)
 {
 	long result, tmp;
 	asm volatile("# beginning __down_read_trylock\n\t"
@@ -93,7 +93,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
 		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
 		     : "i" (RWSEM_ACTIVE_READ_BIAS)
 		     : "memory", "cc");
-	return result >= 0 ? 1 : 0;
+	return result >= 0;
 }
 
 /*
@@ -134,9 +134,10 @@ static inline int __down_write_killable(struct rw_semaphore *sem)
 /*
  * trylock for writing -- returns 1 if successful, 0 if contention
  */
-static inline int __down_write_trylock(struct rw_semaphore *sem)
+static inline bool __down_write_trylock(struct rw_semaphore *sem)
 {
-	long result, tmp;
+	bool result;
+	long tmp0, tmp1;
 	asm volatile("# beginning __down_write_trylock\n\t"
 		     "  mov          %0,%1\n\t"
 		     "1:\n\t"
@@ -144,14 +145,14 @@ static inline int __down_write_trylock(struct rw_semaphore *sem)
 		     /* was the active mask 0 before? */
 		     "  jnz          2f\n\t"
 		     "  mov          %1,%2\n\t"
-		     "  add          %3,%2\n\t"
+		     "  add          %4,%2\n\t"
 		     LOCK_PREFIX "  cmpxchg  %2,%0\n\t"
 		     "  jnz	     1b\n\t"
 		     "2:\n\t"
-		     "  sete         %b1\n\t"
-		     "  movzbl       %b1, %k1\n\t"
+		     CC_SET(e)
 		     "# ending __down_write_trylock\n\t"
-		     : "+m" (sem->count), "=&a" (result), "=&r" (tmp)
+		     : "+m" (sem->count), "=&a" (tmp0), "=&r" (tmp1),
+		       CC_OUT(e) (result)
 		     : "er" (RWSEM_ACTIVE_WRITE_BIAS)
 		     : "memory", "cc");
 	return result;
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 2138c9ae19ee..dd1e7d6387ab 100644
--- a/arch/x86/include/asm/signal.h
+++ b/arch/x86/include/asm/signal.h
@@ -81,9 +81,9 @@ static inline int __const_sigismember(sigset_t *set, int _sig)
 
 static inline int __gen_sigismember(sigset_t *set, int _sig)
 {
-	int ret;
-	asm("btl %2,%1\n\tsbbl %0,%0"
-	    : "=r"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
+	unsigned char ret;
+	asm("btl %2,%1\n\tsetc %0"
+	    : "=qm"(ret) : "m"(*set), "Ir"(_sig-1) : "cc");
 	return ret;
 }
 
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index f28a24b51dc7..cbf8847d02a0 100644
--- a/arch/x86/include/asm/sync_bitops.h
+++ b/arch/x86/include/asm/sync_bitops.h
@@ -79,10 +79,10 @@ static inline void sync_change_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; bts %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; bts %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -97,10 +97,10 @@ static inline int sync_test_and_set_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; btr %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; btr %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
@@ -115,10 +115,10 @@ static inline int sync_test_and_clear_bit(long nr, volatile unsigned long *addr)
  */
 static inline int sync_test_and_change_bit(long nr, volatile unsigned long *addr)
 {
-	int oldbit;
+	unsigned char oldbit;
 
-	asm volatile("lock; btc %2,%1\n\tsbbl %0,%0"
-		     : "=r" (oldbit), "+m" (ADDR)
+	asm volatile("lock; btc %2,%1\n\tsetc %0"
+		     : "=qm" (oldbit), "+m" (ADDR)
 		     : "Ir" (nr) : "memory");
 	return oldbit;
 }
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index a147e676fc7b..e991d5c8bb3a 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -71,8 +71,8 @@ int amd_cache_northbridges(void)
 	while ((misc = next_northbridge(misc, amd_nb_misc_ids)) != NULL)
 		i++;
 
-	if (i == 0)
-		return 0;
+	if (!i)
+		return -ENODEV;
 
 	nb = kzalloc(i * sizeof(struct amd_northbridge), GFP_KERNEL);
 	if (!nb)
diff --git a/arch/x86/kernel/cpu/rdrand.c b/arch/x86/kernel/cpu/rdrand.c
index f6f50c4ceaec..cfa97ff67bda 100644
--- a/arch/x86/kernel/cpu/rdrand.c
+++ b/arch/x86/kernel/cpu/rdrand.c
@@ -39,9 +39,9 @@ __setup("nordrand", x86_rdrand_setup);
  */
 #define SANITY_CHECK_LOOPS 8
 
+#ifdef CONFIG_ARCH_RANDOM
 void x86_init_rdrand(struct cpuinfo_x86 *c)
 {
-#ifdef CONFIG_ARCH_RANDOM
 	unsigned long tmp;
 	int i;
 
@@ -55,5 +55,5 @@ void x86_init_rdrand(struct cpuinfo_x86 *c)
 			return;
 		}
 	}
-#endif
 }
+#endif
diff --git a/arch/x86/kernel/i386_ksyms_32.c b/arch/x86/kernel/i386_ksyms_32.c
index 64341aa485ae..d40ee8a38fed 100644
--- a/arch/x86/kernel/i386_ksyms_32.c
+++ b/arch/x86/kernel/i386_ksyms_32.c
@@ -42,3 +42,5 @@ EXPORT_SYMBOL(empty_zero_page);
 EXPORT_SYMBOL(___preempt_schedule);
 EXPORT_SYMBOL(___preempt_schedule_notrace);
 #endif
+
+EXPORT_SYMBOL(__sw_hweight32);
diff --git a/arch/x86/kernel/signal_compat.c b/arch/x86/kernel/signal_compat.c
index dc3c0b1c816f..b44564bf86a8 100644
--- a/arch/x86/kernel/signal_compat.c
+++ b/arch/x86/kernel/signal_compat.c
@@ -1,11 +1,104 @@
 #include <linux/compat.h>
 #include <linux/uaccess.h>
 
+/*
+ * The compat_siginfo_t structure and handing code is very easy
+ * to break in several ways.  It must always be updated when new
+ * updates are made to the main siginfo_t, and
+ * copy_siginfo_to_user32() must be updated when the
+ * (arch-independent) copy_siginfo_to_user() is updated.
+ *
+ * It is also easy to put a new member in the compat_siginfo_t
+ * which has implicit alignment which can move internal structure
+ * alignment around breaking the ABI.  This can happen if you,
+ * for instance, put a plain 64-bit value in there.
+ */
+static inline void signal_compat_build_tests(void)
+{
+	int _sifields_offset = offsetof(compat_siginfo_t, _sifields);
+
+	/*
+	 * If adding a new si_code, there is probably new data in
+	 * the siginfo.  Make sure folks bumping the si_code
+	 * limits also have to look at this code.  Make sure any
+	 * new fields are handled in copy_siginfo_to_user32()!
+	 */
+	BUILD_BUG_ON(NSIGILL  != 8);
+	BUILD_BUG_ON(NSIGFPE  != 8);
+	BUILD_BUG_ON(NSIGSEGV != 4);
+	BUILD_BUG_ON(NSIGBUS  != 5);
+	BUILD_BUG_ON(NSIGTRAP != 4);
+	BUILD_BUG_ON(NSIGCHLD != 6);
+	BUILD_BUG_ON(NSIGSYS  != 1);
+
+	/* This is part of the ABI and can never change in size: */
+	BUILD_BUG_ON(sizeof(compat_siginfo_t) != 128);
+	/*
+	 * The offsets of all the (unioned) si_fields are fixed
+	 * in the ABI, of course.  Make sure none of them ever
+	 * move and are always at the beginning:
+	 */
+	BUILD_BUG_ON(offsetof(compat_siginfo_t, _sifields) != 3 * sizeof(int));
+#define CHECK_CSI_OFFSET(name)	  BUILD_BUG_ON(_sifields_offset != offsetof(compat_siginfo_t, _sifields.name))
+
+	 /*
+	 * Ensure that the size of each si_field never changes.
+	 * If it does, it is a sign that the
+	 * copy_siginfo_to_user32() code below needs to updated
+	 * along with the size in the CHECK_SI_SIZE().
+	 *
+	 * We repeat this check for both the generic and compat
+	 * siginfos.
+	 *
+	 * Note: it is OK for these to grow as long as the whole
+	 * structure stays within the padding size (checked
+	 * above).
+	 */
+#define CHECK_CSI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((compat_siginfo_t *)0)->_sifields.name))
+#define CHECK_SI_SIZE(name, size) BUILD_BUG_ON(size != sizeof(((siginfo_t *)0)->_sifields.name))
+
+	CHECK_CSI_OFFSET(_kill);
+	CHECK_CSI_SIZE  (_kill, 2*sizeof(int));
+	CHECK_SI_SIZE   (_kill, 2*sizeof(int));
+
+	CHECK_CSI_OFFSET(_timer);
+	CHECK_CSI_SIZE  (_timer, 5*sizeof(int));
+	CHECK_SI_SIZE   (_timer, 6*sizeof(int));
+
+	CHECK_CSI_OFFSET(_rt);
+	CHECK_CSI_SIZE  (_rt, 3*sizeof(int));
+	CHECK_SI_SIZE   (_rt, 4*sizeof(int));
+
+	CHECK_CSI_OFFSET(_sigchld);
+	CHECK_CSI_SIZE  (_sigchld, 5*sizeof(int));
+	CHECK_SI_SIZE   (_sigchld, 8*sizeof(int));
+
+	CHECK_CSI_OFFSET(_sigchld_x32);
+	CHECK_CSI_SIZE  (_sigchld_x32, 7*sizeof(int));
+	/* no _sigchld_x32 in the generic siginfo_t */
+
+	CHECK_CSI_OFFSET(_sigfault);
+	CHECK_CSI_SIZE  (_sigfault, 4*sizeof(int));
+	CHECK_SI_SIZE   (_sigfault, 8*sizeof(int));
+
+	CHECK_CSI_OFFSET(_sigpoll);
+	CHECK_CSI_SIZE  (_sigpoll, 2*sizeof(int));
+	CHECK_SI_SIZE   (_sigpoll, 4*sizeof(int));
+
+	CHECK_CSI_OFFSET(_sigsys);
+	CHECK_CSI_SIZE  (_sigsys, 3*sizeof(int));
+	CHECK_SI_SIZE   (_sigsys, 4*sizeof(int));
+
+	/* any new si_fields should be added here */
+}
+
 int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 {
 	int err = 0;
 	bool ia32 = test_thread_flag(TIF_IA32);
 
+	signal_compat_build_tests();
+
 	if (!access_ok(VERIFY_WRITE, to, sizeof(compat_siginfo_t)))
 		return -EFAULT;
 
@@ -32,6 +125,21 @@ int copy_siginfo_to_user32(compat_siginfo_t __user *to, const siginfo_t *from)
 					  &to->_sifields._pad[0]);
 			switch (from->si_code >> 16) {
 			case __SI_FAULT >> 16:
+				if (from->si_signo == SIGBUS &&
+				    (from->si_code == BUS_MCEERR_AR ||
+				     from->si_code == BUS_MCEERR_AO))
+					put_user_ex(from->si_addr_lsb, &to->si_addr_lsb);
+
+				if (from->si_signo == SIGSEGV) {
+					if (from->si_code == SEGV_BNDERR) {
+						compat_uptr_t lower = (unsigned long)&to->si_lower;
+						compat_uptr_t upper = (unsigned long)&to->si_upper;
+						put_user_ex(lower, &to->si_lower);
+						put_user_ex(upper, &to->si_upper);
+					}
+					if (from->si_code == SEGV_PKUERR)
+						put_user_ex(from->si_pkey, &to->si_pkey);
+				}
 				break;
 			case __SI_SYS >> 16:
 				put_user_ex(from->si_syscall, &to->si_syscall);
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 3dce1ca0a653..01f30e56f99e 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -440,10 +440,7 @@ static inline unsigned long get_vflags(struct kernel_vm86_regs *regs)
 
 static inline int is_revectored(int nr, struct revectored_struct *bitmap)
 {
-	__asm__ __volatile__("btl %2,%1\n\tsbbl %0,%0"
-		:"=r" (nr)
-		:"m" (*bitmap), "r" (nr));
-	return nr;
+	return test_bit(nr, bitmap->__map);
 }
 
 #define val_byte(val, n) (((__u8 *)&val)[n])
diff --git a/arch/x86/kernel/x8664_ksyms_64.c b/arch/x86/kernel/x8664_ksyms_64.c
index cd05942bc918..f1aebfb49c36 100644
--- a/arch/x86/kernel/x8664_ksyms_64.c
+++ b/arch/x86/kernel/x8664_ksyms_64.c
@@ -44,6 +44,9 @@ EXPORT_SYMBOL(clear_page);
 
 EXPORT_SYMBOL(csum_partial);
 
+EXPORT_SYMBOL(__sw_hweight32);
+EXPORT_SYMBOL(__sw_hweight64);
+
 /*
  * Export string functions. We normally rely on gcc builtin for most of these,
  * but gcc sometimes decides not to inline them.
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 72a576752a7e..ec969cc3eb20 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -25,7 +25,7 @@ lib-y += memcpy_$(BITS).o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_INSTRUCTION_DECODER) += insn.o inat.o
 
-obj-y += msr.o msr-reg.o msr-reg-export.o
+obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
 
 ifeq ($(CONFIG_X86_32),y)
         obj-y += atomic64_32.o
diff --git a/arch/x86/lib/hweight.S b/arch/x86/lib/hweight.S
new file mode 100644
index 000000000000..02de3d74d2c5
--- /dev/null
+++ b/arch/x86/lib/hweight.S
@@ -0,0 +1,77 @@
+#include <linux/linkage.h>
+
+#include <asm/asm.h>
+
+/*
+ * unsigned int __sw_hweight32(unsigned int w)
+ * %rdi: w
+ */
+ENTRY(__sw_hweight32)
+
+#ifdef CONFIG_X86_64
+	movl %edi, %eax				# w
+#endif
+	__ASM_SIZE(push,) %__ASM_REG(dx)
+	movl %eax, %edx				# w -> t
+	shrl %edx				# t >>= 1
+	andl $0x55555555, %edx			# t &= 0x55555555
+	subl %edx, %eax				# w -= t
+
+	movl %eax, %edx				# w -> t
+	shrl $2, %eax				# w_tmp >>= 2
+	andl $0x33333333, %edx			# t	&= 0x33333333
+	andl $0x33333333, %eax			# w_tmp &= 0x33333333
+	addl %edx, %eax				# w = w_tmp + t
+
+	movl %eax, %edx				# w -> t
+	shrl $4, %edx				# t >>= 4
+	addl %edx, %eax				# w_tmp += t
+	andl  $0x0f0f0f0f, %eax			# w_tmp &= 0x0f0f0f0f
+	imull $0x01010101, %eax, %eax		# w_tmp *= 0x01010101
+	shrl $24, %eax				# w = w_tmp >> 24
+	__ASM_SIZE(pop,) %__ASM_REG(dx)
+	ret
+ENDPROC(__sw_hweight32)
+
+ENTRY(__sw_hweight64)
+#ifdef CONFIG_X86_64
+	pushq   %rdx
+
+	movq    %rdi, %rdx                      # w -> t
+	movabsq $0x5555555555555555, %rax
+	shrq    %rdx                            # t >>= 1
+	andq    %rdx, %rax                      # t &= 0x5555555555555555
+	movabsq $0x3333333333333333, %rdx
+	subq    %rax, %rdi                      # w -= t
+
+	movq    %rdi, %rax                      # w -> t
+	shrq    $2, %rdi                        # w_tmp >>= 2
+	andq    %rdx, %rax                      # t     &= 0x3333333333333333
+	andq    %rdi, %rdx                      # w_tmp &= 0x3333333333333333
+	addq    %rdx, %rax                      # w = w_tmp + t
+
+	movq    %rax, %rdx                      # w -> t
+	shrq    $4, %rdx                        # t >>= 4
+	addq    %rdx, %rax                      # w_tmp += t
+	movabsq $0x0f0f0f0f0f0f0f0f, %rdx
+	andq    %rdx, %rax                      # w_tmp &= 0x0f0f0f0f0f0f0f0f
+	movabsq $0x0101010101010101, %rdx
+	imulq   %rdx, %rax                      # w_tmp *= 0x0101010101010101
+	shrq    $56, %rax                       # w = w_tmp >> 56
+
+	popq    %rdx
+	ret
+#else /* CONFIG_X86_32 */
+	/* We're getting an u64 arg in (%eax,%edx): unsigned long hweight64(__u64 w) */
+	pushl   %ecx
+
+	call    __sw_hweight32
+	movl    %eax, %ecx                      # stash away result
+	movl    %edx, %eax                      # second part of input
+	call    __sw_hweight32
+	addl    %ecx, %eax                      # result
+
+	popl    %ecx
+	ret
+#endif
+ENDPROC(__sw_hweight64)
diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c
index b2a4e2a61f6b..3cd69832d7f4 100644
--- a/arch/x86/pci/acpi.c
+++ b/arch/x86/pci/acpi.c
@@ -396,6 +396,7 @@ int __init pci_acpi_init(void)
 		return -ENODEV;
 
 	printk(KERN_INFO "PCI: Using ACPI for IRQ routing\n");
+	acpi_irq_penalty_init();
 	pcibios_enable_irq = acpi_pci_irq_enable;
 	pcibios_disable_irq = acpi_pci_irq_disable;
 	x86_init.pci.init_irq = x86_init_noop;
diff --git a/arch/x86/power/hibernate_64.c b/arch/x86/power/hibernate_64.c
index 009947d419a6..f2b5e6a5cf95 100644
--- a/arch/x86/power/hibernate_64.c
+++ b/arch/x86/power/hibernate_64.c
@@ -19,6 +19,7 @@
 #include <asm/mtrr.h>
 #include <asm/sections.h>
 #include <asm/suspend.h>
+#include <asm/tlbflush.h>
 
 /* Defined in hibernate_asm_64.S */
 extern asmlinkage __visible int restore_image(void);
@@ -28,6 +29,7 @@ extern asmlinkage __visible int restore_image(void);
  * kernel's text (this value is passed in the image header).
  */
 unsigned long restore_jump_address __visible;
+unsigned long jump_address_phys;
 
 /*
  * Value of the cr3 register from before the hibernation (this value is passed
@@ -37,7 +39,43 @@ unsigned long restore_cr3 __visible;
 
 pgd_t *temp_level4_pgt __visible;
 
-void *relocated_restore_code __visible;
+unsigned long relocated_restore_code __visible;
+
+static int set_up_temporary_text_mapping(void)
+{
+	pmd_t *pmd;
+	pud_t *pud;
+
+	/*
+	 * The new mapping only has to cover the page containing the image
+	 * kernel's entry point (jump_address_phys), because the switch over to
+	 * it is carried out by relocated code running from a page allocated
+	 * specifically for this purpose and covered by the identity mapping, so
+	 * the temporary kernel text mapping is only needed for the final jump.
+	 * Moreover, in that mapping the virtual address of the image kernel's
+	 * entry point must be the same as its virtual address in the image
+	 * kernel (restore_jump_address), so the image kernel's
+	 * restore_registers() code doesn't find itself in a different area of
+	 * the virtual address space after switching over to the original page
+	 * tables used by the image kernel.
+	 */
+	pud = (pud_t *)get_safe_page(GFP_ATOMIC);
+	if (!pud)
+		return -ENOMEM;
+
+	pmd = (pmd_t *)get_safe_page(GFP_ATOMIC);
+	if (!pmd)
+		return -ENOMEM;
+
+	set_pmd(pmd + pmd_index(restore_jump_address),
+		__pmd((jump_address_phys & PMD_MASK) | __PAGE_KERNEL_LARGE_EXEC));
+	set_pud(pud + pud_index(restore_jump_address),
+		__pud(__pa(pmd) | _KERNPG_TABLE));
+	set_pgd(temp_level4_pgt + pgd_index(restore_jump_address),
+		__pgd(__pa(pud) | _KERNPG_TABLE));
+
+	return 0;
+}
 
 static void *alloc_pgt_page(void *context)
 {
@@ -59,9 +97,10 @@ static int set_up_temporary_mappings(void)
 	if (!temp_level4_pgt)
 		return -ENOMEM;
 
-	/* It is safe to reuse the original kernel mapping */
-	set_pgd(temp_level4_pgt + pgd_index(__START_KERNEL_map),
-		init_level4_pgt[pgd_index(__START_KERNEL_map)]);
+	/* Prepare a temporary mapping for the kernel text */
+	result = set_up_temporary_text_mapping();
+	if (result)
+		return result;
 
 	/* Set up the direct mapping from scratch */
 	for (i = 0; i < nr_pfn_mapped; i++) {
@@ -78,19 +117,50 @@ static int set_up_temporary_mappings(void)
 	return 0;
 }
 
+static int relocate_restore_code(void)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	relocated_restore_code = get_safe_page(GFP_ATOMIC);
+	if (!relocated_restore_code)
+		return -ENOMEM;
+
+	memcpy((void *)relocated_restore_code, &core_restore_code, PAGE_SIZE);
+
+	/* Make the page containing the relocated code executable */
+	pgd = (pgd_t *)__va(read_cr3()) + pgd_index(relocated_restore_code);
+	pud = pud_offset(pgd, relocated_restore_code);
+	if (pud_large(*pud)) {
+		set_pud(pud, __pud(pud_val(*pud) & ~_PAGE_NX));
+	} else {
+		pmd_t *pmd = pmd_offset(pud, relocated_restore_code);
+
+		if (pmd_large(*pmd)) {
+			set_pmd(pmd, __pmd(pmd_val(*pmd) & ~_PAGE_NX));
+		} else {
+			pte_t *pte = pte_offset_kernel(pmd, relocated_restore_code);
+
+			set_pte(pte, __pte(pte_val(*pte) & ~_PAGE_NX));
+		}
+	}
+	__flush_tlb_all();
+
+	return 0;
+}
+
 int swsusp_arch_resume(void)
 {
 	int error;
 
 	/* We have got enough memory and from now on we cannot recover */
-	if ((error = set_up_temporary_mappings()))
+	error = set_up_temporary_mappings();
+	if (error)
 		return error;
 
-	relocated_restore_code = (void *)get_safe_page(GFP_ATOMIC);
-	if (!relocated_restore_code)
-		return -ENOMEM;
-	memcpy(relocated_restore_code, &core_restore_code,
-	       &restore_registers - &core_restore_code);
+	error = relocate_restore_code();
+	if (error)
+		return error;
 
 	restore_image();
 	return 0;
@@ -109,11 +179,12 @@ int pfn_is_nosave(unsigned long pfn)
 
 struct restore_data_record {
 	unsigned long jump_address;
+	unsigned long jump_address_phys;
 	unsigned long cr3;
 	unsigned long magic;
 };
 
-#define RESTORE_MAGIC	0x0123456789ABCDEFUL
+#define RESTORE_MAGIC	0x123456789ABCDEF0UL
 
 /**
  *	arch_hibernation_header_save - populate the architecture specific part
@@ -126,7 +197,8 @@ int arch_hibernation_header_save(void *addr, unsigned int max_size)
 
 	if (max_size < sizeof(struct restore_data_record))
 		return -EOVERFLOW;
-	rdr->jump_address = restore_jump_address;
+	rdr->jump_address = (unsigned long)&restore_registers;
+	rdr->jump_address_phys = __pa_symbol(&restore_registers);
 	rdr->cr3 = restore_cr3;
 	rdr->magic = RESTORE_MAGIC;
 	return 0;
@@ -142,6 +214,7 @@ int arch_hibernation_header_restore(void *addr)
 	struct restore_data_record *rdr = addr;
 
 	restore_jump_address = rdr->jump_address;
+	jump_address_phys = rdr->jump_address_phys;
 	restore_cr3 = rdr->cr3;
 	return (rdr->magic == RESTORE_MAGIC) ? 0 : -EINVAL;
 }
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 4400a43b9e28..3177c2bc26f6 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -44,9 +44,6 @@ ENTRY(swsusp_arch_suspend)
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	/* save the address of restore_registers */
-	movq	$restore_registers, %rax
-	movq	%rax, restore_jump_address(%rip)
 	/* save cr3 */
 	movq	%cr3, %rax
 	movq	%rax, restore_cr3(%rip)
@@ -57,31 +54,34 @@ ENTRY(swsusp_arch_suspend)
 ENDPROC(swsusp_arch_suspend)
 
 ENTRY(restore_image)
-	/* switch to temporary page tables */
-	movq	$__PAGE_OFFSET, %rdx
-	movq	temp_level4_pgt(%rip), %rax
-	subq	%rdx, %rax
-	movq	%rax, %cr3
-	/* Flush TLB */
-	movq	mmu_cr4_features(%rip), %rax
-	movq	%rax, %rdx
-	andq	$~(X86_CR4_PGE), %rdx
-	movq	%rdx, %cr4;  # turn off PGE
-	movq	%cr3, %rcx;  # flush TLB
-	movq	%rcx, %cr3;
-	movq	%rax, %cr4;  # turn PGE back on
-
 	/* prepare to jump to the image kernel */
-	movq	restore_jump_address(%rip), %rax
-	movq	restore_cr3(%rip), %rbx
+	movq	restore_jump_address(%rip), %r8
+	movq	restore_cr3(%rip), %r9
+
+	/* prepare to switch to temporary page tables */
+	movq	temp_level4_pgt(%rip), %rax
+	movq	mmu_cr4_features(%rip), %rbx
 
 	/* prepare to copy image data to their original locations */
 	movq	restore_pblist(%rip), %rdx
+
+	/* jump to relocated restore code */
 	movq	relocated_restore_code(%rip), %rcx
 	jmpq	*%rcx
 
 	/* code below has been relocated to a safe page */
 ENTRY(core_restore_code)
+	/* switch to temporary page tables */
+	movq	$__PAGE_OFFSET, %rcx
+	subq	%rcx, %rax
+	movq	%rax, %cr3
+	/* flush TLB */
+	movq	%rbx, %rcx
+	andq	$~(X86_CR4_PGE), %rcx
+	movq	%rcx, %cr4;  # turn off PGE
+	movq	%cr3, %rcx;  # flush TLB
+	movq	%rcx, %cr3;
+	movq	%rbx, %cr4;  # turn PGE back on
 .Lloop:
 	testq	%rdx, %rdx
 	jz	.Ldone
@@ -96,24 +96,17 @@ ENTRY(core_restore_code)
 	/* progress to the next pbe */
 	movq	pbe_next(%rdx), %rdx
 	jmp	.Lloop
+
 .Ldone:
 	/* jump to the restore_registers address from the image header */
-	jmpq	*%rax
-	/*
-	 * NOTE: This assumes that the boot kernel's text mapping covers the
-	 * image kernel's page containing restore_registers and the address of
-	 * this page is the same as in the image kernel's text mapping (it
-	 * should always be true, because the text mapping is linear, starting
-	 * from 0, and is supposed to cover the entire kernel text for every
-	 * kernel).
-	 *
-	 * code below belongs to the image kernel
-	 */
+	jmpq	*%r8
 
+	 /* code below belongs to the image kernel */
+	.align PAGE_SIZE
 ENTRY(restore_registers)
 	FRAME_BEGIN
 	/* go back to the original page tables */
-	movq    %rbx, %cr3
+	movq    %r9, %cr3
 
 	/* Flush TLB, including "global" things (vmalloc) */
 	movq	mmu_cr4_features(%rip), %rax
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index 760789ae8562..0f87db2cc6a8 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -521,9 +521,7 @@ static void set_aliased_prot(void *v, pgprot_t prot)
 
 	preempt_disable();
 
-	pagefault_disable();	/* Avoid warnings due to being atomic. */
-	__get_user(dummy, (unsigned char __user __force *)v);
-	pagefault_enable();
+	probe_kernel_read(&dummy, v, 1);
 
 	if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
 		BUG();