Merge branch 'linus' into x86/microcode, to pick up merge window changes

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

47 files changed, 669 insertions, 320 deletions

diff --git a/arch/x86/include/asm/Kbuild b/arch/x86/include/asm/Kbuild
index aeac434..2cfed17 100644
--- a/arch/x86/include/asm/Kbuild
+++ b/arch/x86/include/asm/Kbuild
@@ -1,5 +1,11 @@
 
 
+generated-y += syscalls_32.h
+generated-y += syscalls_64.h
+generated-y += unistd_32_ia32.h
+generated-y += unistd_64_x32.h
+generated-y += xen-hypercalls.h
+
 genhdr-y += unistd_32.h
 genhdr-y += unistd_64.h
 genhdr-y += unistd_x32.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index bc27611..f5befd4 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -300,7 +300,6 @@ struct apic {
 
 	unsigned int (*get_apic_id)(unsigned long x);
 	unsigned long (*set_apic_id)(unsigned int id);
-	unsigned long apic_id_mask;
 
 	int (*cpu_mask_to_apicid_and)(const struct cpumask *cpumask,
 				      const struct cpumask *andmask,
diff --git a/arch/x86/include/asm/apm.h b/arch/x86/include/asm/apm.h
index 20370c6..93eebc63 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 02e799f..e7cd631 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 69f1366..5b0579a 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 f5063b6..7acb51c 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 3e86742..14635c5 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);
 }
 
 /**
@@ -171,6 +171,16 @@ static __always_inline int atomic_sub_return(int i, atomic_t *v)
 #define atomic_inc_return(v)  (atomic_add_return(1, v))
 #define atomic_dec_return(v)  (atomic_sub_return(1, v))
 
+static __always_inline int atomic_fetch_add(int i, atomic_t *v)
+{
+	return xadd(&v->counter, i);
+}
+
+static __always_inline int atomic_fetch_sub(int i, atomic_t *v)
+{
+	return xadd(&v->counter, -i);
+}
+
 static __always_inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 {
 	return cmpxchg(&v->counter, old, new);
@@ -190,10 +200,29 @@ static inline void atomic_##op(int i, atomic_t *v)			\
 			: "memory");					\
 }
 
-ATOMIC_OP(and)
-ATOMIC_OP(or)
-ATOMIC_OP(xor)
+#define ATOMIC_FETCH_OP(op, c_op)					\
+static inline int atomic_fetch_##op(int i, atomic_t *v)		\
+{									\
+	int old, val = atomic_read(v);					\
+	for (;;) {							\
+		old = atomic_cmpxchg(v, val, val c_op i);		\
+		if (old == val)						\
+			break;						\
+		val = old;						\
+	}								\
+	return old;							\
+}
+
+#define ATOMIC_OPS(op, c_op)						\
+	ATOMIC_OP(op)							\
+	ATOMIC_FETCH_OP(op, c_op)
+
+ATOMIC_OPS(and, &)
+ATOMIC_OPS(or , |)
+ATOMIC_OPS(xor, ^)
 
+#undef ATOMIC_OPS
+#undef ATOMIC_FETCH_OP
 #undef ATOMIC_OP
 
 /**
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index a984111..71d7705 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -320,10 +320,29 @@ static inline void atomic64_##op(long long i, atomic64_t *v)		\
 		c = old;						\
 }
 
-ATOMIC64_OP(and, &)
-ATOMIC64_OP(or, |)
-ATOMIC64_OP(xor, ^)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static inline long long atomic64_fetch_##op(long long i, atomic64_t *v)	\
+{									\
+	long long old, c = 0;						\
+	while ((old = atomic64_cmpxchg(v, c, c c_op i)) != c)		\
+		c = old;						\
+	return old;							\
+}
+
+ATOMIC64_FETCH_OP(add, +)
+
+#define atomic64_fetch_sub(i, v)	atomic64_fetch_add(-(i), (v))
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op, c_op)						\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &)
+ATOMIC64_OPS(or, |)
+ATOMIC64_OPS(xor, ^)
 
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/atomic64_64.h b/arch/x86/include/asm/atomic64_64.h
index 0373510..89ed2f6 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);
 }
 
 /**
@@ -158,6 +158,16 @@ static inline long atomic64_sub_return(long i, atomic64_t *v)
 	return atomic64_add_return(-i, v);
 }
 
+static inline long atomic64_fetch_add(long i, atomic64_t *v)
+{
+	return xadd(&v->counter, i);
+}
+
+static inline long atomic64_fetch_sub(long i, atomic64_t *v)
+{
+	return xadd(&v->counter, -i);
+}
+
 #define atomic64_inc_return(v)  (atomic64_add_return(1, (v)))
 #define atomic64_dec_return(v)  (atomic64_sub_return(1, (v)))
 
@@ -180,7 +190,7 @@ 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);
@@ -229,10 +239,29 @@ static inline void atomic64_##op(long i, atomic64_t *v)			\
 			: "memory");					\
 }
 
-ATOMIC64_OP(and)
-ATOMIC64_OP(or)
-ATOMIC64_OP(xor)
+#define ATOMIC64_FETCH_OP(op, c_op)					\
+static inline long atomic64_fetch_##op(long i, atomic64_t *v)		\
+{									\
+	long old, val = atomic64_read(v);				\
+	for (;;) {							\
+		old = atomic64_cmpxchg(v, val, val c_op i);		\
+		if (old == val)						\
+			break;						\
+		val = old;						\
+	}								\
+	return old;							\
+}
+
+#define ATOMIC64_OPS(op, c_op)						\
+	ATOMIC64_OP(op)							\
+	ATOMIC64_FETCH_OP(op, c_op)
+
+ATOMIC64_OPS(and, &)
+ATOMIC64_OPS(or, |)
+ATOMIC64_OPS(xor, ^)
 
+#undef ATOMIC64_OPS
+#undef ATOMIC64_FETCH_OP
 #undef ATOMIC64_OP
 
 #endif /* _ASM_X86_ATOMIC64_64_H */
diff --git a/arch/x86/include/asm/bios_ebda.h b/arch/x86/include/asm/bios_ebda.h
index 2b00c77..4b7b8e7 100644
--- a/arch/x86/include/asm/bios_ebda.h
+++ b/arch/x86/include/asm/bios_ebda.h
@@ -17,7 +17,7 @@ static inline unsigned int get_bios_ebda(void)
 	return address;	/* 0 means none */
 }
 
-void reserve_ebda_region(void);
+void reserve_bios_regions(void);
 
 #ifdef CONFIG_X86_CHECK_BIOS_CORRUPTION
 /*
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 7766d1c..68557f52 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/checksum_32.h b/arch/x86/include/asm/checksum_32.h
index 532f85e..7b53743 100644
--- a/arch/x86/include/asm/checksum_32.h
+++ b/arch/x86/include/asm/checksum_32.h
@@ -2,8 +2,7 @@
 #define _ASM_X86_CHECKSUM_32_H
 
 #include <linux/in6.h>
-
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 
 /*
  * computes the checksum of a memory block at buff, length len,
diff --git a/arch/x86/include/asm/compat.h b/arch/x86/include/asm/compat.h
index 5a3b2c1..a188061 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/cpu.h b/arch/x86/include/asm/cpu.h
index 678637a..59d34c5 100644
--- a/arch/x86/include/asm/cpu.h
+++ b/arch/x86/include/asm/cpu.h
@@ -17,7 +17,6 @@ static inline void prefill_possible_map(void) {}
 
 #define cpu_physical_id(cpu)			boot_cpu_physical_apicid
 #define safe_smp_processor_id()			0
-#define stack_smp_processor_id()		0
 
 #endif /* CONFIG_SMP */
 
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 4a41348..c64b1e9 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -301,10 +301,6 @@
 #define X86_BUG_FXSAVE_LEAK	X86_BUG(6) /* FXSAVE leaks FOP/FIP/FOP */
 #define X86_BUG_CLFLUSH_MONITOR	X86_BUG(7) /* AAI65, CLFLUSH required before MONITOR */
 #define X86_BUG_SYSRET_SS_ATTRS	X86_BUG(8) /* SYSRET doesn't fix up SS attrs */
-#define X86_BUG_NULL_SEG	X86_BUG(9) /* Nulling a selector preserves the base */
-#define X86_BUG_SWAPGS_FENCE	X86_BUG(10) /* SWAPGS without input dep on GS */
-
-
 #ifdef CONFIG_X86_32
 /*
  * 64-bit kernels don't use X86_BUG_ESPFIX.  Make the define conditional
@@ -312,5 +308,7 @@
  */
 #define X86_BUG_ESPFIX		X86_BUG(9) /* "" IRET to 16-bit SS corrupts ESP/RSP high bits */
 #endif
+#define X86_BUG_NULL_SEG	X86_BUG(10) /* Nulling a selector preserves the base */
+#define X86_BUG_SWAPGS_FENCE	X86_BUG(11) /* SWAPGS without input dep on GS */
 
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 78d1e74..d0bb76d 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -41,10 +41,9 @@ extern unsigned long asmlinkage efi_call_phys(void *, ...);
 /*
  * Wrap all the virtual calls in a way that forces the parameters on the stack.
  */
-#define arch_efi_call_virt(f, args...)					\
+#define arch_efi_call_virt(p, f, args...)				\
 ({									\
-	((efi_##f##_t __attribute__((regparm(0)))*)			\
-		efi.systab->runtime->f)(args);				\
+	((efi_##f##_t __attribute__((regparm(0)))*) p->f)(args);	\
 })
 
 #define efi_ioremap(addr, size, type, attr)	ioremap_cache(addr, size)
@@ -81,8 +80,8 @@ struct efi_scratch {
 	}								\
 })
 
-#define arch_efi_call_virt(f, args...)					\
-	efi_call((void *)efi.systab->runtime->f, args)			\
+#define arch_efi_call_virt(p, f, args...)				\
+	efi_call((void *)p->f, args)					\
 
 #define arch_efi_call_virt_teardown()					\
 ({									\
@@ -125,7 +124,6 @@ extern void __init efi_map_region_fixed(efi_memory_desc_t *md);
 extern void efi_sync_low_kernel_mappings(void);
 extern int __init efi_alloc_page_tables(void);
 extern int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages);
-extern void __init efi_cleanup_page_tables(unsigned long pa_memmap, unsigned num_pages);
 extern void __init old_map_region(efi_memory_desc_t *md);
 extern void __init runtime_code_page_mkexec(void);
 extern void __init efi_runtime_update_mappings(void);
diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h
index 31ac8e6..116b583 100644
--- a/arch/x86/include/asm/fpu/internal.h
+++ b/arch/x86/include/asm/fpu/internal.h
@@ -18,6 +18,7 @@
 #include <asm/fpu/api.h>
 #include <asm/fpu/xstate.h>
 #include <asm/cpufeature.h>
+#include <asm/trace/fpu.h>
 
 /*
  * High level FPU state handling functions:
@@ -524,6 +525,7 @@ static inline void __fpregs_deactivate(struct fpu *fpu)
 
 	fpu->fpregs_active = 0;
 	this_cpu_write(fpu_fpregs_owner_ctx, NULL);
+	trace_x86_fpu_regs_deactivated(fpu);
 }
 
 /* Must be paired with a 'clts' (fpregs_activate_hw()) before! */
@@ -533,6 +535,7 @@ static inline void __fpregs_activate(struct fpu *fpu)
 
 	fpu->fpregs_active = 1;
 	this_cpu_write(fpu_fpregs_owner_ctx, fpu);
+	trace_x86_fpu_regs_activated(fpu);
 }
 
 /*
@@ -604,11 +607,13 @@ switch_fpu_prepare(struct fpu *old_fpu, struct fpu *new_fpu, int cpu)
 
 		/* But leave fpu_fpregs_owner_ctx! */
 		old_fpu->fpregs_active = 0;
+		trace_x86_fpu_regs_deactivated(old_fpu);
 
 		/* Don't change CR0.TS if we just switch! */
 		if (fpu.preload) {
 			new_fpu->counter++;
 			__fpregs_activate(new_fpu);
+			trace_x86_fpu_regs_activated(new_fpu);
 			prefetch(&new_fpu->state);
 		} else {
 			__fpregs_deactivate_hw();
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index 36b90bb..48df486 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -122,6 +122,7 @@ enum xfeature {
 #define XFEATURE_MASK_OPMASK		(1 << XFEATURE_OPMASK)
 #define XFEATURE_MASK_ZMM_Hi256		(1 << XFEATURE_ZMM_Hi256)
 #define XFEATURE_MASK_Hi16_ZMM		(1 << XFEATURE_Hi16_ZMM)
+#define XFEATURE_MASK_PT		(1 << XFEATURE_PT_UNIMPLEMENTED_SO_FAR)
 #define XFEATURE_MASK_PKRU		(1 << XFEATURE_PKRU)
 
 #define XFEATURE_MASK_FPSSE		(XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
@@ -231,6 +232,12 @@ struct xstate_header {
 } __attribute__((packed));
 
 /*
+ * xstate_header.xcomp_bv[63] indicates that the extended_state_area
+ * is in compacted format.
+ */
+#define XCOMP_BV_COMPACTED_FORMAT ((u64)1 << 63)
+
+/*
  * This is our most modern FPU state format, as saved by the XSAVE
  * and restored by the XRSTOR instructions.
  *
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 38951b0..ae55a43 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -18,6 +18,9 @@
 #define XSAVE_YMM_SIZE	    256
 #define XSAVE_YMM_OFFSET    (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET)
 
+/* Supervisor features */
+#define XFEATURE_MASK_SUPERVISOR (XFEATURE_MASK_PT)
+
 /* Supported features which support lazy state saving */
 #define XFEATURE_MASK_LAZY	(XFEATURE_MASK_FP | \
 				 XFEATURE_MASK_SSE | \
@@ -39,7 +42,6 @@
 #define REX_PREFIX
 #endif
 
-extern unsigned int xstate_size;
 extern u64 xfeatures_mask;
 extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS];
 
@@ -48,5 +50,9 @@ extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask);
 void fpu__xstate_clear_all_cpu_caps(void);
 void *get_xsave_addr(struct xregs_state *xsave, int xstate);
 const void *get_xsave_field_ptr(int xstate_field);
-
+int using_compacted_format(void);
+int copyout_from_xsaves(unsigned int pos, unsigned int count, void *kbuf,
+			void __user *ubuf, struct xregs_state *xsave);
+int copyin_to_xsaves(const void *kbuf, const void __user *ubuf,
+		     struct xregs_state *xsave);
 #endif
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 74a2e31..02aff08 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -48,6 +48,7 @@
 /* AVX VEX prefixes */
 #define INAT_PFX_VEX2	13	/* 2-bytes VEX prefix */
 #define INAT_PFX_VEX3	14	/* 3-bytes VEX prefix */
+#define INAT_PFX_EVEX	15	/* EVEX prefix */
 
 #define INAT_LSTPFX_MAX	3
 #define INAT_LGCPFX_MAX	11
@@ -89,6 +90,7 @@
 #define INAT_VARIANT	(1 << (INAT_FLAG_OFFS + 4))
 #define INAT_VEXOK	(1 << (INAT_FLAG_OFFS + 5))
 #define INAT_VEXONLY	(1 << (INAT_FLAG_OFFS + 6))
+#define INAT_EVEXONLY	(1 << (INAT_FLAG_OFFS + 7))
 /* Attribute making macros for attribute tables */
 #define INAT_MAKE_PREFIX(pfx)	(pfx << INAT_PFX_OFFS)
 #define INAT_MAKE_ESCAPE(esc)	(esc << INAT_ESC_OFFS)
@@ -141,7 +143,13 @@ static inline int inat_last_prefix_id(insn_attr_t attr)
 static inline int inat_is_vex_prefix(insn_attr_t attr)
 {
 	attr &= INAT_PFX_MASK;
-	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3;
+	return attr == INAT_PFX_VEX2 || attr == INAT_PFX_VEX3 ||
+	       attr == INAT_PFX_EVEX;
+}
+
+static inline int inat_is_evex_prefix(insn_attr_t attr)
+{
+	return (attr & INAT_PFX_MASK) == INAT_PFX_EVEX;
 }
 
 static inline int inat_is_vex3_prefix(insn_attr_t attr)
@@ -216,6 +224,11 @@ static inline int inat_accept_vex(insn_attr_t attr)
 
 static inline int inat_must_vex(insn_attr_t attr)
 {
-	return attr & INAT_VEXONLY;
+	return attr & (INAT_VEXONLY | INAT_EVEXONLY);
+}
+
+static inline int inat_must_evex(insn_attr_t attr)
+{
+	return attr & INAT_EVEXONLY;
 }
 #endif
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index e7814b7..b3e32b0 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -91,6 +91,7 @@ struct insn {
 #define X86_VEX_B(vex)	((vex) & 0x20)	/* VEX3 Byte1 */
 #define X86_VEX_L(vex)	((vex) & 0x04)	/* VEX3 Byte2, VEX2 Byte1 */
 /* VEX bit fields */
+#define X86_EVEX_M(vex)	((vex) & 0x03)		/* EVEX Byte1 */
 #define X86_VEX3_M(vex)	((vex) & 0x1f)		/* VEX3 Byte1 */
 #define X86_VEX2_M	1			/* VEX2.M always 1 */
 #define X86_VEX_V(vex)	(((vex) & 0x78) >> 3)	/* VEX3 Byte2, VEX2 Byte1 */
@@ -133,6 +134,13 @@ static inline int insn_is_avx(struct insn *insn)
 	return (insn->vex_prefix.value != 0);
 }
 
+static inline int insn_is_evex(struct insn *insn)
+{
+	if (!insn->prefixes.got)
+		insn_get_prefixes(insn);
+	return (insn->vex_prefix.nbytes == 4);
+}
+
 /* Ensure this instruction is decoded completely */
 static inline int insn_complete(struct insn *insn)
 {
@@ -144,8 +152,10 @@ static inline insn_byte_t insn_vex_m_bits(struct insn *insn)
 {
 	if (insn->vex_prefix.nbytes == 2)	/* 2 bytes VEX */
 		return X86_VEX2_M;
-	else
+	else if (insn->vex_prefix.nbytes == 3)	/* 3 bytes VEX */
 		return X86_VEX3_M(insn->vex_prefix.bytes[1]);
+	else					/* EVEX */
+		return X86_EVEX_M(insn->vex_prefix.bytes[1]);
 }
 
 static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
diff --git a/arch/x86/include/asm/intel-mid.h b/arch/x86/include/asm/intel-mid.h
index 7c5af12..9d6b097 100644
--- a/arch/x86/include/asm/intel-mid.h
+++ b/arch/x86/include/asm/intel-mid.h
@@ -12,9 +12,17 @@
 #define _ASM_X86_INTEL_MID_H
 
 #include <linux/sfi.h>
+#include <linux/pci.h>
 #include <linux/platform_device.h>
 
 extern int intel_mid_pci_init(void);
+extern int intel_mid_pci_set_power_state(struct pci_dev *pdev, pci_power_t state);
+
+#define INTEL_MID_PWR_LSS_OFFSET	4
+#define INTEL_MID_PWR_LSS_TYPE		(1 << 7)
+
+extern int intel_mid_pwr_get_lss_id(struct pci_dev *pdev);
+
 extern int get_gpio_by_name(const char *name);
 extern void intel_scu_device_register(struct platform_device *pdev);
 extern int __init sfi_parse_mrtc(struct sfi_table_header *table);
@@ -34,13 +42,28 @@ struct devs_id {
 	void *(*get_platform_data)(void *info);
 	/* Custom handler for devices */
 	void (*device_handler)(struct sfi_device_table_entry *pentry,
-				struct devs_id *dev);
+			       struct devs_id *dev);
 };
 
-#define sfi_device(i)   \
-	static const struct devs_id *const __intel_mid_sfi_##i##_dev __used \
+#define sfi_device(i)								\
+	static const struct devs_id *const __intel_mid_sfi_##i##_dev __used	\
 	__attribute__((__section__(".x86_intel_mid_dev.init"))) = &i
 
+/**
+* struct mid_sd_board_info - template for SD device creation
+* @name:		identifies the driver
+* @bus_num:		board-specific identifier for a given SD controller
+* @max_clk:		the maximum frequency device supports
+* @platform_data:	the particular data stored there is driver-specific
+*/
+struct mid_sd_board_info {
+	char		name[SFI_NAME_LEN];
+	int		bus_num;
+	unsigned short	addr;
+	u32		max_clk;
+	void		*platform_data;
+};
+
 /*
  * Medfield is the follow-up of Moorestown, it combines two chip solution into
  * one. Other than that it also added always-on and constant tsc and lapic
@@ -60,7 +83,7 @@ extern enum intel_mid_cpu_type __intel_mid_cpu_chip;
 /**
  * struct intel_mid_ops - Interface between intel-mid & sub archs
  * @arch_setup: arch_setup function to re-initialize platform
- *             structures (x86_init, x86_platform_init)
+ *		structures (x86_init, x86_platform_init)
  *
  * This structure can be extended if any new interface is required
  * between intel-mid & its sub arch files.
@@ -70,20 +93,20 @@ struct intel_mid_ops {
 };
 
 /* Helper API's for INTEL_MID_OPS_INIT */
-#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid)	\
-				[cpuid] = get_##cpuname##_ops
+#define DECLARE_INTEL_MID_OPS_INIT(cpuname, cpuid)				\
+	[cpuid] = get_##cpuname##_ops
 
 /* Maximum number of CPU ops */
-#define MAX_CPU_OPS(a) (sizeof(a)/sizeof(void *))
+#define MAX_CPU_OPS(a)			(sizeof(a)/sizeof(void *))
 
 /*
  * For every new cpu addition, a weak get_<cpuname>_ops() function needs be
  * declared in arch/x86/platform/intel_mid/intel_mid_weak_decls.h.
  */
-#define INTEL_MID_OPS_INIT {\
-	DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL), \
-	DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW), \
-	DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER) \
+#define INTEL_MID_OPS_INIT {							\
+	DECLARE_INTEL_MID_OPS_INIT(penwell, INTEL_MID_CPU_CHIP_PENWELL),	\
+	DECLARE_INTEL_MID_OPS_INIT(cloverview, INTEL_MID_CPU_CHIP_CLOVERVIEW),	\
+	DECLARE_INTEL_MID_OPS_INIT(tangier, INTEL_MID_CPU_CHIP_TANGIER)		\
 };
 
 #ifdef CONFIG_X86_INTEL_MID
@@ -100,8 +123,8 @@ static inline bool intel_mid_has_msic(void)
 
 #else /* !CONFIG_X86_INTEL_MID */
 
-#define intel_mid_identify_cpu()    (0)
-#define intel_mid_has_msic()    (0)
+#define intel_mid_identify_cpu()	0
+#define intel_mid_has_msic()		0
 
 #endif /* !CONFIG_X86_INTEL_MID */
 
@@ -117,35 +140,38 @@ extern enum intel_mid_timer_options intel_mid_timer_options;
  * Penwell uses spread spectrum clock, so the freq number is not exactly
  * the same as reported by MSR based on SDM.
  */
-#define FSB_FREQ_83SKU	83200
-#define FSB_FREQ_100SKU	99840
-#define FSB_FREQ_133SKU	133000
+#define FSB_FREQ_83SKU			83200
+#define FSB_FREQ_100SKU			99840
+#define FSB_FREQ_133SKU			133000
 
-#define FSB_FREQ_167SKU	167000
-#define FSB_FREQ_200SKU	200000
-#define FSB_FREQ_267SKU	267000
-#define FSB_FREQ_333SKU	333000
-#define FSB_FREQ_400SKU	400000
+#define FSB_FREQ_167SKU			167000
+#define FSB_FREQ_200SKU			200000
+#define FSB_FREQ_267SKU			267000
+#define FSB_FREQ_333SKU			333000
+#define FSB_FREQ_400SKU			400000
 
 /* Bus Select SoC Fuse value */
-#define BSEL_SOC_FUSE_MASK	0x7
-#define BSEL_SOC_FUSE_001	0x1 /* FSB 133MHz */
-#define BSEL_SOC_FUSE_101	0x5 /* FSB 100MHz */
-#define BSEL_SOC_FUSE_111	0x7 /* FSB 83MHz */
+#define BSEL_SOC_FUSE_MASK		0x7
+/* FSB 133MHz */
+#define BSEL_SOC_FUSE_001		0x1
+/* FSB 100MHz */
+#define BSEL_SOC_FUSE_101		0x5
+/* FSB 83MHz */
+#define BSEL_SOC_FUSE_111		0x7
 
-#define SFI_MTMR_MAX_NUM 8
-#define SFI_MRTC_MAX	8
+#define SFI_MTMR_MAX_NUM		8
+#define SFI_MRTC_MAX			8
 
 extern void intel_scu_devices_create(void);
 extern void intel_scu_devices_destroy(void);
 
 /* VRTC timer */
-#define MRST_VRTC_MAP_SZ	(1024)
-/*#define MRST_VRTC_PGOFFSET	(0xc00) */
+#define MRST_VRTC_MAP_SZ		1024
+/* #define MRST_VRTC_PGOFFSET		0xc00 */
 
 extern void intel_mid_rtc_init(void);
 
-/* the offset for the mapping of global gpio pin to irq */
-#define INTEL_MID_IRQ_OFFSET 0x100
+/* The offset for the mapping of global gpio pin to irq */
+#define INTEL_MID_IRQ_OFFSET		0x100
 
 #endif /* _ASM_X86_INTEL_MID_H */
diff --git a/arch/x86/include/asm/kaslr.h b/arch/x86/include/asm/kaslr.h
new file mode 100644
index 0000000..2674ee3
--- /dev/null
+++ b/arch/x86/include/asm/kaslr.h
@@ -0,0 +1,15 @@
+#ifndef _ASM_KASLR_H_
+#define _ASM_KASLR_H_
+
+unsigned long kaslr_get_random_long(const char *purpose);
+
+#ifdef CONFIG_RANDOMIZE_MEMORY
+extern unsigned long page_offset_base;
+extern unsigned long vmalloc_base;
+
+void kernel_randomize_memory(void);
+#else
+static inline void kernel_randomize_memory(void) { }
+#endif /* CONFIG_RANDOMIZE_MEMORY */
+
+#endif
diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h
index e5f5dc9..1ef9d58 100644
--- a/arch/x86/include/asm/kdebug.h
+++ b/arch/x86/include/asm/kdebug.h
@@ -26,6 +26,7 @@ extern void die(const char *, struct pt_regs *,long);
 extern int __must_check __die(const char *, struct pt_regs *, long);
 extern void show_trace(struct task_struct *t, struct pt_regs *regs,
 		       unsigned long *sp, unsigned long bp);
+extern void show_stack_regs(struct pt_regs *regs);
 extern void __show_regs(struct pt_regs *regs, int all);
 extern unsigned long oops_begin(void);
 extern void oops_end(unsigned long, struct pt_regs *, int signr);
diff --git a/arch/x86/include/asm/local.h b/arch/x86/include/asm/local.h
index 4ad6560..7511978 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/mutex_32.h b/arch/x86/include/asm/mutex_32.h
index 85e6cda..e9355a8 100644
--- a/arch/x86/include/asm/mutex_32.h
+++ b/arch/x86/include/asm/mutex_32.h
@@ -101,7 +101,7 @@ static inline int __mutex_fastpath_trylock(atomic_t *count,
 					   int (*fail_fn)(atomic_t *))
 {
 	/* cmpxchg because it never induces a false contention state. */
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
 
 	return 0;
diff --git a/arch/x86/include/asm/mutex_64.h b/arch/x86/include/asm/mutex_64.h
index 07537a4..d985075 100644
--- a/arch/x86/include/asm/mutex_64.h
+++ b/arch/x86/include/asm/mutex_64.h
@@ -118,10 +118,10 @@ do {								\
 static inline int __mutex_fastpath_trylock(atomic_t *count,
 					   int (*fail_fn)(atomic_t *))
 {
-	if (likely(atomic_cmpxchg(count, 1, 0) == 1))
+	if (likely(atomic_read(count) == 1 && atomic_cmpxchg(count, 1, 0) == 1))
 		return 1;
-	else
-		return 0;
+
+	return 0;
 }
 
 #endif /* _ASM_X86_MUTEX_64_H */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index d5c2f8b..9215e05 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -1,6 +1,10 @@
 #ifndef _ASM_X86_PAGE_64_DEFS_H
 #define _ASM_X86_PAGE_64_DEFS_H
 
+#ifndef __ASSEMBLY__
+#include <asm/kaslr.h>
+#endif
+
 #ifdef CONFIG_KASAN
 #define KASAN_STACK_ORDER 1
 #else
@@ -32,7 +36,12 @@
  * hypervisor to fit.  Choosing 16 slots here is arbitrary, but it's
  * what Xen requires.
  */
-#define __PAGE_OFFSET           _AC(0xffff880000000000, UL)
+#define __PAGE_OFFSET_BASE      _AC(0xffff880000000000, UL)
+#ifdef CONFIG_RANDOMIZE_MEMORY
+#define __PAGE_OFFSET           page_offset_base
+#else
+#define __PAGE_OFFSET           __PAGE_OFFSET_BASE
+#endif /* CONFIG_RANDOMIZE_MEMORY */
 
 #define __START_KERNEL_map	_AC(0xffffffff80000000, UL)
 
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e0ba66c..e02e3f8 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/pgtable.h b/arch/x86/include/asm/pgtable.h
index 1a27396..437feb4 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -480,7 +480,7 @@ pte_t *populate_extra_pte(unsigned long vaddr);
 
 static inline int pte_none(pte_t pte)
 {
-	return !pte.pte;
+	return !(pte.pte & ~(_PAGE_KNL_ERRATUM_MASK));
 }
 
 #define __HAVE_ARCH_PTE_SAME
@@ -552,7 +552,8 @@ static inline int pmd_none(pmd_t pmd)
 {
 	/* Only check low word on 32-bit platforms, since it might be
 	   out of sync with upper half. */
-	return (unsigned long)native_pmd_val(pmd) == 0;
+	unsigned long val = native_pmd_val(pmd);
+	return (val & ~_PAGE_KNL_ERRATUM_MASK) == 0;
 }
 
 static inline unsigned long pmd_page_vaddr(pmd_t pmd)
@@ -616,7 +617,7 @@ static inline unsigned long pages_to_mb(unsigned long npg)
 #if CONFIG_PGTABLE_LEVELS > 2
 static inline int pud_none(pud_t pud)
 {
-	return native_pud_val(pud) == 0;
+	return (native_pud_val(pud) & ~(_PAGE_KNL_ERRATUM_MASK)) == 0;
 }
 
 static inline int pud_present(pud_t pud)
@@ -694,6 +695,12 @@ static inline int pgd_bad(pgd_t pgd)
 
 static inline int pgd_none(pgd_t pgd)
 {
+	/*
+	 * There is no need to do a workaround for the KNL stray
+	 * A/D bit erratum here.  PGDs only point to page tables
+	 * except on 32-bit non-PAE which is not supported on
+	 * KNL.
+	 */
 	return !native_pgd_val(pgd);
 }
 #endif	/* CONFIG_PGTABLE_LEVELS > 3 */
@@ -729,6 +736,23 @@ extern int direct_gbpages;
 void init_mem_mapping(void);
 void early_alloc_pgt_buf(void);
 
+#ifdef CONFIG_X86_64
+/* Realmode trampoline initialization. */
+extern pgd_t trampoline_pgd_entry;
+static inline void __meminit init_trampoline_default(void)
+{
+	/* Default trampoline pgd value */
+	trampoline_pgd_entry = init_level4_pgt[pgd_index(__PAGE_OFFSET)];
+}
+# ifdef CONFIG_RANDOMIZE_MEMORY
+void __meminit init_trampoline(void);
+# else
+#  define init_trampoline init_trampoline_default
+# endif
+#else
+static inline void init_trampoline(void) { }
+#endif
+
 /* local pte updates need not use xchg for locking */
 static inline pte_t native_local_ptep_get_and_clear(pte_t *ptep)
 {
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index 2ee7811..7e8ec7a 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -140,18 +140,32 @@ static inline int pgd_large(pgd_t pgd) { return 0; }
 #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address))
 #define pte_unmap(pte) ((void)(pte))/* NOP */
 
-/* Encode and de-code a swap entry */
+/*
+ * Encode and de-code a swap entry
+ *
+ * |     ...            | 11| 10|  9|8|7|6|5| 4| 3|2|1|0| <- bit number
+ * |     ...            |SW3|SW2|SW1|G|L|D|A|CD|WT|U|W|P| <- bit names
+ * | OFFSET (14->63) | TYPE (10-13) |0|X|X|X| X| X|X|X|0| <- swp entry
+ *
+ * G (8) is aliased and used as a PROT_NONE indicator for
+ * !present ptes.  We need to start storing swap entries above
+ * there.  We also need to avoid using A and D because of an
+ * erratum where they can be incorrectly set by hardware on
+ * non-present PTEs.
+ */
+#define SWP_TYPE_FIRST_BIT (_PAGE_BIT_PROTNONE + 1)
 #define SWP_TYPE_BITS 5
-#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1)
+/* Place the offset above the type: */
+#define SWP_OFFSET_FIRST_BIT (SWP_TYPE_FIRST_BIT + SWP_TYPE_BITS + 1)
 
 #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS)
 
-#define __swp_type(x)			(((x).val >> (_PAGE_BIT_PRESENT + 1)) \
+#define __swp_type(x)			(((x).val >> (SWP_TYPE_FIRST_BIT)) \
 					 & ((1U << SWP_TYPE_BITS) - 1))
-#define __swp_offset(x)			((x).val >> SWP_OFFSET_SHIFT)
+#define __swp_offset(x)			((x).val >> SWP_OFFSET_FIRST_BIT)
 #define __swp_entry(type, offset)	((swp_entry_t) { \
-					 ((type) << (_PAGE_BIT_PRESENT + 1)) \
-					 | ((offset) << SWP_OFFSET_SHIFT) })
+					 ((type) << (SWP_TYPE_FIRST_BIT)) \
+					 | ((offset) << SWP_OFFSET_FIRST_BIT) })
 #define __pte_to_swp_entry(pte)		((swp_entry_t) { pte_val((pte)) })
 #define __swp_entry_to_pte(x)		((pte_t) { .pte = (x).val })
 
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index e6844df..6fdef9e 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -5,6 +5,7 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
+#include <asm/kaslr.h>
 
 /*
  * These are used to make use of C type-checking..
@@ -53,10 +54,16 @@ typedef struct { pteval_t pte; } pte_t;
 #define PGDIR_MASK	(~(PGDIR_SIZE - 1))
 
 /* See Documentation/x86/x86_64/mm.txt for a description of the memory map. */
-#define MAXMEM		 _AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
-#define VMALLOC_START    _AC(0xffffc90000000000, UL)
-#define VMALLOC_END      _AC(0xffffe8ffffffffff, UL)
-#define VMEMMAP_START	 _AC(0xffffea0000000000, UL)
+#define MAXMEM		_AC(__AC(1, UL) << MAX_PHYSMEM_BITS, UL)
+#define VMALLOC_SIZE_TB	_AC(32, UL)
+#define __VMALLOC_BASE	_AC(0xffffc90000000000, UL)
+#define VMEMMAP_START	_AC(0xffffea0000000000, UL)
+#ifdef CONFIG_RANDOMIZE_MEMORY
+#define VMALLOC_START	vmalloc_base
+#else
+#define VMALLOC_START	__VMALLOC_BASE
+#endif /* CONFIG_RANDOMIZE_MEMORY */
+#define VMALLOC_END	(VMALLOC_START + _AC((VMALLOC_SIZE_TB << 40) - 1, UL))
 #define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 7b5efe2..f1218f5 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -70,6 +70,12 @@
 			 _PAGE_PKEY_BIT2 | \
 			 _PAGE_PKEY_BIT3)
 
+#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
+#define _PAGE_KNL_ERRATUM_MASK (_PAGE_DIRTY | _PAGE_ACCESSED)
+#else
+#define _PAGE_KNL_ERRATUM_MASK 0
+#endif
+
 #ifdef CONFIG_KMEMCHECK
 #define _PAGE_HIDDEN	(_AT(pteval_t, 1) << _PAGE_BIT_HIDDEN)
 #else
@@ -475,8 +481,6 @@ extern pmd_t *lookup_pmd_address(unsigned long address);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn, unsigned long address,
 				   unsigned numpages, unsigned long page_flags);
-void kernel_unmap_pages_in_pgd(pgd_t *root, unsigned long address,
-			       unsigned numpages);
 #endif	/* !__ASSEMBLY__ */
 
 #endif /* _ASM_X86_PGTABLE_DEFS_H */
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index d397deb..17f2186 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/processor.h b/arch/x86/include/asm/processor.h
index 62c6cc3..63def95 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -367,10 +367,15 @@ DECLARE_PER_CPU(struct irq_stack *, hardirq_stack);
 DECLARE_PER_CPU(struct irq_stack *, softirq_stack);
 #endif	/* X86_64 */
 
-extern unsigned int xstate_size;
+extern unsigned int fpu_kernel_xstate_size;
+extern unsigned int fpu_user_xstate_size;
 
 struct perf_event;
 
+typedef struct {
+	unsigned long		seg;
+} mm_segment_t;
+
 struct thread_struct {
 	/* Cached TLS descriptors: */
 	struct desc_struct	tls_array[GDT_ENTRY_TLS_ENTRIES];
@@ -419,6 +424,11 @@ struct thread_struct {
 	/* Max allowed port in the bitmap, in bytes: */
 	unsigned		io_bitmap_max;
 
+	mm_segment_t		addr_limit;
+
+	unsigned int		sig_on_uaccess_err:1;
+	unsigned int		uaccess_err:1;	/* uaccess failed */
+
 	/* Floating point and extended processor state */
 	struct fpu		fpu;
 	/*
@@ -490,11 +500,6 @@ static inline void load_sp0(struct tss_struct *tss,
 #define set_iopl_mask native_set_iopl_mask
 #endif /* CONFIG_PARAVIRT */
 
-typedef struct {
-	unsigned long		seg;
-} mm_segment_t;
-
-
 /* Free all resources held by a thread. */
 extern void release_thread(struct task_struct *);
 
@@ -716,6 +721,7 @@ static inline void spin_lock_prefetch(const void *x)
 	.sp0			= TOP_OF_INIT_STACK,			  \
 	.sysenter_cs		= __KERNEL_CS,				  \
 	.io_bitmap_ptr		= NULL,					  \
+	.addr_limit		= KERNEL_DS,				  \
 }
 
 extern unsigned long thread_saved_pc(struct task_struct *tsk);
@@ -765,8 +771,9 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define STACK_TOP		TASK_SIZE
 #define STACK_TOP_MAX		TASK_SIZE_MAX
 
-#define INIT_THREAD  { \
-	.sp0 = TOP_OF_INIT_STACK \
+#define INIT_THREAD  {						\
+	.sp0			= TOP_OF_INIT_STACK,		\
+	.addr_limit		= KERNEL_DS,			\
 }
 
 /*
diff --git a/arch/x86/include/asm/rmwcc.h b/arch/x86/include/asm/rmwcc.h
index 8f7866a..661dd30 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 453744c..8dbc762 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;
@@ -213,23 +214,5 @@ static inline void __downgrade_write(struct rw_semaphore *sem)
 		     : "memory", "cc");
 }
 
-/*
- * implement atomic add functionality
- */
-static inline void rwsem_atomic_add(long delta, struct rw_semaphore *sem)
-{
-	asm volatile(LOCK_PREFIX _ASM_ADD "%1,%0"
-		     : "+m" (sem->count)
-		     : "er" (delta));
-}
-
-/*
- * implement exchange and add functionality
- */
-static inline long rwsem_atomic_update(long delta, struct rw_semaphore *sem)
-{
-	return delta + xadd(&sem->count, delta);
-}
-
 #endif /* __KERNEL__ */
 #endif /* _ASM_X86_RWSEM_H */
diff --git a/arch/x86/include/asm/signal.h b/arch/x86/include/asm/signal.h
index 2138c9a..dd1e7d6 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/smp.h b/arch/x86/include/asm/smp.h
index 66b0573..0576b61 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -172,12 +172,6 @@ extern int safe_smp_processor_id(void);
 #elif defined(CONFIG_X86_64_SMP)
 #define raw_smp_processor_id() (this_cpu_read(cpu_number))
 
-#define stack_smp_processor_id()					\
-({								\
-	struct thread_info *ti;						\
-	__asm__("andq %%rsp,%0; ":"=r" (ti) : "0" (CURRENT_MASK));	\
-	ti->cpu;							\
-})
 #define safe_smp_processor_id()		smp_processor_id()
 
 #endif
diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h
index f28a24b..cbf8847 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/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 30c133a..89bff04 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -57,9 +57,6 @@ struct thread_info {
 	__u32			flags;		/* low level flags */
 	__u32			status;		/* thread synchronous flags */
 	__u32			cpu;		/* current CPU */
-	mm_segment_t		addr_limit;
-	unsigned int		sig_on_uaccess_error:1;
-	unsigned int		uaccess_err:1;	/* uaccess failed */
 };
 
 #define INIT_THREAD_INFO(tsk)			\
@@ -67,7 +64,6 @@ struct thread_info {
 	.task		= &tsk,			\
 	.flags		= 0,			\
 	.cpu		= 0,			\
-	.addr_limit	= KERNEL_DS,		\
 }
 
 #define init_thread_info	(init_thread_union.thread_info)
@@ -186,11 +182,6 @@ static inline unsigned long current_stack_pointer(void)
 # define cpu_current_top_of_stack (cpu_tss + TSS_sp0)
 #endif
 
-/* Load thread_info address into "reg" */
-#define GET_THREAD_INFO(reg) \
-	_ASM_MOV PER_CPU_VAR(cpu_current_top_of_stack),reg ; \
-	_ASM_SUB $(THREAD_SIZE),reg ;
-
 /*
  * ASM operand which evaluates to a 'thread_info' address of
  * the current task, if it is known that "reg" is exactly "off"
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 7f991bd5..43e87a3 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -25,16 +25,6 @@
 #ifndef _ASM_X86_TOPOLOGY_H
 #define _ASM_X86_TOPOLOGY_H
 
-#ifdef CONFIG_X86_32
-# ifdef CONFIG_SMP
-#  define ENABLE_TOPO_DEFINES
-# endif
-#else
-# ifdef CONFIG_SMP
-#  define ENABLE_TOPO_DEFINES
-# endif
-#endif
-
 /*
  * to preserve the visibility of NUMA_NO_NODE definition,
  * moved to there from here.  May be used independent of
@@ -123,12 +113,20 @@ extern const struct cpumask *cpu_coregroup_mask(int cpu);
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
 
-#ifdef ENABLE_TOPO_DEFINES
+#ifdef CONFIG_SMP
 #define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
 #define topology_sibling_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
 extern unsigned int __max_logical_packages;
 #define topology_max_packages()			(__max_logical_packages)
+
+extern int __max_smt_threads;
+
+static inline int topology_max_smt_threads(void)
+{
+	return __max_smt_threads;
+}
+
 int topology_update_package_map(unsigned int apicid, unsigned int cpu);
 extern int topology_phys_to_logical_pkg(unsigned int pkg);
 #else
@@ -136,6 +134,7 @@ extern int topology_phys_to_logical_pkg(unsigned int pkg);
 static inline int
 topology_update_package_map(unsigned int apicid, unsigned int cpu) { return 0; }
 static inline int topology_phys_to_logical_pkg(unsigned int pkg) { return 0; }
+static inline int topology_max_smt_threads(void) { return 1; }
 #endif
 
 static inline void arch_fix_phys_package_id(int num, u32 slot)
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
new file mode 100644
index 0000000..9217ab1
--- /dev/null
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -0,0 +1,119 @@
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM x86_fpu
+
+#if !defined(_TRACE_FPU_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _TRACE_FPU_H
+
+#include <linux/tracepoint.h>
+
+DECLARE_EVENT_CLASS(x86_fpu,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu),
+
+	TP_STRUCT__entry(
+		__field(struct fpu *, fpu)
+		__field(bool, fpregs_active)
+		__field(bool, fpstate_active)
+		__field(int, counter)
+		__field(u64, xfeatures)
+		__field(u64, xcomp_bv)
+		),
+
+	TP_fast_assign(
+		__entry->fpu		= fpu;
+		__entry->fpregs_active	= fpu->fpregs_active;
+		__entry->fpstate_active	= fpu->fpstate_active;
+		__entry->counter	= fpu->counter;
+		if (boot_cpu_has(X86_FEATURE_OSXSAVE)) {
+			__entry->xfeatures = fpu->state.xsave.header.xfeatures;
+			__entry->xcomp_bv  = fpu->state.xsave.header.xcomp_bv;
+		}
+	),
+	TP_printk("x86/fpu: %p fpregs_active: %d fpstate_active: %d counter: %d xfeatures: %llx xcomp_bv: %llx",
+			__entry->fpu,
+			__entry->fpregs_active,
+			__entry->fpstate_active,
+			__entry->counter,
+			__entry->xfeatures,
+			__entry->xcomp_bv
+	)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_before_save,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_after_save,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_before_restore,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_after_restore,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_activate_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_deactivate_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_dropped,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_copy_src,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+DEFINE_EVENT(x86_fpu, x86_fpu_xstate_check_failed,
+	TP_PROTO(struct fpu *fpu),
+	TP_ARGS(fpu)
+);
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH asm/trace/
+#undef TRACE_INCLUDE_FILE
+#define TRACE_INCLUDE_FILE fpu
+#endif /* _TRACE_FPU_H */
+
+/* This part must be outside protection */
+#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 7428697..33b6365 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -35,7 +35,7 @@ extern void tsc_init(void);
 extern void mark_tsc_unstable(char *reason);
 extern int unsynchronized_tsc(void);
 extern int check_tsc_unstable(void);
-extern int check_tsc_disabled(void);
+extern unsigned long native_calibrate_cpu(void);
 extern unsigned long native_calibrate_tsc(void);
 extern unsigned long long native_sched_clock_from_tsc(u64 tsc);
 
@@ -52,7 +52,6 @@ extern int notsc_setup(char *);
 extern void tsc_save_sched_clock_state(void);
 extern void tsc_restore_sched_clock_state(void);
 
-/* MSR based TSC calibration for Intel Atom SoC platforms */
-unsigned long try_msr_calibrate_tsc(void);
+unsigned long cpu_khz_from_msr(void);
 
 #endif /* _ASM_X86_TSC_H */
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 2982387..c03bfb6 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -29,12 +29,12 @@
 #define USER_DS 	MAKE_MM_SEG(TASK_SIZE_MAX)
 
 #define get_ds()	(KERNEL_DS)
-#define get_fs()	(current_thread_info()->addr_limit)
-#define set_fs(x)	(current_thread_info()->addr_limit = (x))
+#define get_fs()	(current->thread.addr_limit)
+#define set_fs(x)	(current->thread.addr_limit = (x))
 
 #define segment_eq(a, b)	((a).seg == (b).seg)
 
-#define user_addr_max() (current_thread_info()->addr_limit.seg)
+#define user_addr_max() (current->thread.addr_limit.seg)
 #define __addr_ok(addr) 	\
 	((unsigned long __force)(addr) < user_addr_max())
 
@@ -342,7 +342,26 @@ do {									\
 } while (0)
 
 #ifdef CONFIG_X86_32
-#define __get_user_asm_u64(x, ptr, retval, errret)	(x) = __get_user_bad()
+#define __get_user_asm_u64(x, ptr, retval, errret)			\
+({									\
+	__typeof__(ptr) __ptr = (ptr);					\
+	asm volatile(ASM_STAC "\n"					\
+		     "1:	movl %2,%%eax\n"			\
+		     "2:	movl %3,%%edx\n"			\
+		     "3: " ASM_CLAC "\n"				\
+		     ".section .fixup,\"ax\"\n"				\
+		     "4:	mov %4,%0\n"				\
+		     "	xorl %%eax,%%eax\n"				\
+		     "	xorl %%edx,%%edx\n"				\
+		     "	jmp 3b\n"					\
+		     ".previous\n"					\
+		     _ASM_EXTABLE(1b, 4b)				\
+		     _ASM_EXTABLE(2b, 4b)				\
+		     : "=r" (retval), "=A"(x)				\
+		     : "m" (__m(__ptr)), "m" __m(((u32 *)(__ptr)) + 1),	\
+		       "i" (errret), "0" (retval));			\
+})
+
 #define __get_user_asm_ex_u64(x, ptr)			(x) = __get_user_bad()
 #else
 #define __get_user_asm_u64(x, ptr, retval, errret) \
@@ -429,7 +448,7 @@ do {									\
 #define __get_user_nocheck(x, ptr, size)				\
 ({									\
 	int __gu_err;							\
-	unsigned long __gu_val;						\
+	__inttype(*(ptr)) __gu_val;					\
 	__uaccess_begin();						\
 	__get_user_size(__gu_val, (ptr), (size), __gu_err, -EFAULT);	\
 	__uaccess_end();						\
@@ -468,13 +487,13 @@ struct __large_struct { unsigned long buf[100]; };
  * uaccess_try and catch
  */
 #define uaccess_try	do {						\
-	current_thread_info()->uaccess_err = 0;				\
+	current->thread.uaccess_err = 0;				\
 	__uaccess_begin();						\
 	barrier();
 
 #define uaccess_catch(err)						\
 	__uaccess_end();						\
-	(err) |= (current_thread_info()->uaccess_err ? -EFAULT : 0);	\
+	(err) |= (current->thread.uaccess_err ? -EFAULT : 0);		\
 } while (0)
 
 /**
diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h
index 2b19caa..32712a9 100644
--- a/arch/x86/include/asm/unistd.h
+++ b/arch/x86/include/asm/unistd.h
@@ -26,6 +26,8 @@
 #  define __ARCH_WANT_COMPAT_SYS_GETDENTS64
 #  define __ARCH_WANT_COMPAT_SYS_PREADV64
 #  define __ARCH_WANT_COMPAT_SYS_PWRITEV64
+#  define __ARCH_WANT_COMPAT_SYS_PREADV64V2
+#  define __ARCH_WANT_COMPAT_SYS_PWRITEV64V2
 
 # endif
 
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 4dcdf74..6ba7931 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -168,20 +168,22 @@ struct x86_legacy_devices {
  * struct x86_legacy_features - legacy x86 features
  *
  * @rtc: this device has a CMOS real-time clock present
- * @ebda_search: it's safe to search for the EBDA signature in the hardware's
- * 	low RAM
+ * @reserve_bios_regions: boot code will search for the EBDA address and the
+ * 	start of the 640k - 1M BIOS region.  If false, the platform must
+ * 	ensure that its memory map correctly reserves sub-1MB regions as needed.
  * @devices: legacy x86 devices, refer to struct x86_legacy_devices
  * 	documentation for further details.
  */
 struct x86_legacy_features {
 	int rtc;
-	int ebda_search;
+	int reserve_bios_regions;
 	struct x86_legacy_devices devices;
 };
 
 /**
  * struct x86_platform_ops - platform specific runtime functions
- * @calibrate_tsc:		calibrate TSC
+ * @calibrate_cpu:		calibrate CPU
+ * @calibrate_tsc:		calibrate TSC, if different from CPU
  * @get_wallclock:		get time from HW clock like RTC etc.
  * @set_wallclock:		set time back to HW clock
  * @is_untracked_pat_range	exclude from PAT logic
@@ -200,6 +202,7 @@ struct x86_legacy_features {
  * 				semantics.
  */
 struct x86_platform_ops {
+	unsigned long (*calibrate_cpu)(void);
 	unsigned long (*calibrate_tsc)(void);
 	void (*get_wallclock)(struct timespec *ts);
 	int (*set_wallclock)(const struct timespec *ts);