Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into sh-latest

27 files changed, 752 insertions, 766 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 37ad100a221..49331bedc15 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -145,6 +145,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  */
 #define ASM_OUTPUT2(a...) a
 
+/*
+ * use this macro if you need clobbers but no inputs in
+ * alternative_{input,io,call}()
+ */
+#define ASM_NO_INPUT_CLOBBER(clbr...) "i" (0) : clbr
+
 struct paravirt_patch_site;
 #ifdef CONFIG_PARAVIRT
 void apply_paravirt(struct paravirt_patch_site *start,
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3ab9bdd87e7..a9371c91718 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -288,6 +288,7 @@ struct apic {
 
 	int (*probe)(void);
 	int (*acpi_madt_oem_check)(char *oem_id, char *oem_table_id);
+	int (*apic_id_valid)(int apicid);
 	int (*apic_id_registered)(void);
 
 	u32 irq_delivery_mode;
@@ -532,6 +533,11 @@ static inline unsigned int read_apic_id(void)
 	return apic->get_apic_id(reg);
 }
 
+static inline int default_apic_id_valid(int apicid)
+{
+	return x2apic_mode || (apicid < 255);
+}
+
 extern void default_setup_apic_routing(void);
 
 extern struct apic apic_noop;
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index fa13f0ec287..198119910da 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -14,13 +14,52 @@ typedef struct {
 
 #define ATOMIC64_INIT(val)	{ (val) }
 
+#define __ATOMIC64_DECL(sym) void atomic64_##sym(atomic64_t *, ...)
+#ifndef ATOMIC64_EXPORT
+#define ATOMIC64_DECL_ONE __ATOMIC64_DECL
+#else
+#define ATOMIC64_DECL_ONE(sym) __ATOMIC64_DECL(sym); \
+	ATOMIC64_EXPORT(atomic64_##sym)
+#endif
+
 #ifdef CONFIG_X86_CMPXCHG64
-#define ATOMIC64_ALTERNATIVE_(f, g) "call atomic64_" #g "_cx8"
+#define __alternative_atomic64(f, g, out, in...) \
+	asm volatile("call %P[func]" \
+		     : out : [func] "i" (atomic64_##g##_cx8), ## in)
+
+#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
 #else
-#define ATOMIC64_ALTERNATIVE_(f, g) ALTERNATIVE("call atomic64_" #f "_386", "call atomic64_" #g "_cx8", X86_FEATURE_CX8)
+#define __alternative_atomic64(f, g, out, in...) \
+	alternative_call(atomic64_##f##_386, atomic64_##g##_cx8, \
+			 X86_FEATURE_CX8, ASM_OUTPUT2(out), ## in)
+
+#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8); \
+	ATOMIC64_DECL_ONE(sym##_386)
+
+ATOMIC64_DECL_ONE(add_386);
+ATOMIC64_DECL_ONE(sub_386);
+ATOMIC64_DECL_ONE(inc_386);
+ATOMIC64_DECL_ONE(dec_386);
 #endif
 
-#define ATOMIC64_ALTERNATIVE(f) ATOMIC64_ALTERNATIVE_(f, f)
+#define alternative_atomic64(f, out, in...) \
+	__alternative_atomic64(f, f, ASM_OUTPUT2(out), ## in)
+
+ATOMIC64_DECL(read);
+ATOMIC64_DECL(set);
+ATOMIC64_DECL(xchg);
+ATOMIC64_DECL(add_return);
+ATOMIC64_DECL(sub_return);
+ATOMIC64_DECL(inc_return);
+ATOMIC64_DECL(dec_return);
+ATOMIC64_DECL(dec_if_positive);
+ATOMIC64_DECL(inc_not_zero);
+ATOMIC64_DECL(add_unless);
+
+#undef ATOMIC64_DECL
+#undef ATOMIC64_DECL_ONE
+#undef __ATOMIC64_DECL
+#undef ATOMIC64_EXPORT
 
 /**
  * atomic64_cmpxchg - cmpxchg atomic64 variable
@@ -50,11 +89,9 @@ static inline long long atomic64_xchg(atomic64_t *v, long long n)
 	long long o;
 	unsigned high = (unsigned)(n >> 32);
 	unsigned low = (unsigned)n;
-	asm volatile(ATOMIC64_ALTERNATIVE(xchg)
-		     : "=A" (o), "+b" (low), "+c" (high)
-		     : "S" (v)
-		     : "memory"
-		     );
+	alternative_atomic64(xchg, "=&A" (o),
+			     "S" (v), "b" (low), "c" (high)
+			     : "memory");
 	return o;
 }
 
@@ -69,11 +106,9 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 {
 	unsigned high = (unsigned)(i >> 32);
 	unsigned low = (unsigned)i;
-	asm volatile(ATOMIC64_ALTERNATIVE(set)
-		     : "+b" (low), "+c" (high)
-		     : "S" (v)
-		     : "eax", "edx", "memory"
-		     );
+	alternative_atomic64(set, /* no output */,
+			     "S" (v), "b" (low), "c" (high)
+			     : "eax", "edx", "memory");
 }
 
 /**
@@ -85,10 +120,7 @@ static inline void atomic64_set(atomic64_t *v, long long i)
 static inline long long atomic64_read(const atomic64_t *v)
 {
 	long long r;
-	asm volatile(ATOMIC64_ALTERNATIVE(read)
-		     : "=A" (r), "+c" (v)
-		     : : "memory"
-		     );
+	alternative_atomic64(read, "=&A" (r), "c" (v) : "memory");
 	return r;
  }
 
@@ -101,10 +133,9 @@ static inline long long atomic64_read(const atomic64_t *v)
  */
 static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
-	asm volatile(ATOMIC64_ALTERNATIVE(add_return)
-		     : "+A" (i), "+c" (v)
-		     : : "memory"
-		     );
+	alternative_atomic64(add_return,
+			     ASM_OUTPUT2("+A" (i), "+c" (v)),
+			     ASM_NO_INPUT_CLOBBER("memory"));
 	return i;
 }
 
@@ -113,32 +144,25 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
  */
 static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 {
-	asm volatile(ATOMIC64_ALTERNATIVE(sub_return)
-		     : "+A" (i), "+c" (v)
-		     : : "memory"
-		     );
+	alternative_atomic64(sub_return,
+			     ASM_OUTPUT2("+A" (i), "+c" (v)),
+			     ASM_NO_INPUT_CLOBBER("memory"));
 	return i;
 }
 
 static inline long long atomic64_inc_return(atomic64_t *v)
 {
 	long long a;
-	asm volatile(ATOMIC64_ALTERNATIVE(inc_return)
-		     : "=A" (a)
-		     : "S" (v)
-		     : "memory", "ecx"
-		     );
+	alternative_atomic64(inc_return, "=&A" (a),
+			     "S" (v) : "memory", "ecx");
 	return a;
 }
 
 static inline long long atomic64_dec_return(atomic64_t *v)
 {
 	long long a;
-	asm volatile(ATOMIC64_ALTERNATIVE(dec_return)
-		     : "=A" (a)
-		     : "S" (v)
-		     : "memory", "ecx"
-		     );
+	alternative_atomic64(dec_return, "=&A" (a),
+			     "S" (v) : "memory", "ecx");
 	return a;
 }
 
@@ -151,10 +175,9 @@ static inline long long atomic64_dec_return(atomic64_t *v)
  */
 static inline long long atomic64_add(long long i, atomic64_t *v)
 {
-	asm volatile(ATOMIC64_ALTERNATIVE_(add, add_return)
-		     : "+A" (i), "+c" (v)
-		     : : "memory"
-		     );
+	__alternative_atomic64(add, add_return,
+			       ASM_OUTPUT2("+A" (i), "+c" (v)),
+			       ASM_NO_INPUT_CLOBBER("memory"));
 	return i;
 }
 
@@ -167,10 +190,9 @@ static inline long long atomic64_add(long long i, atomic64_t *v)
  */
 static inline long long atomic64_sub(long long i, atomic64_t *v)
 {
-	asm volatile(ATOMIC64_ALTERNATIVE_(sub, sub_return)
-		     : "+A" (i), "+c" (v)
-		     : : "memory"
-		     );
+	__alternative_atomic64(sub, sub_return,
+			       ASM_OUTPUT2("+A" (i), "+c" (v)),
+			       ASM_NO_INPUT_CLOBBER("memory"));
 	return i;
 }
 
@@ -196,10 +218,8 @@ static inline int atomic64_sub_and_test(long long i, atomic64_t *v)
  */
 static inline void atomic64_inc(atomic64_t *v)
 {
-	asm volatile(ATOMIC64_ALTERNATIVE_(inc, inc_return)
-		     : : "S" (v)
-		     : "memory", "eax", "ecx", "edx"
-		     );
+	__alternative_atomic64(inc, inc_return, /* no output */,
+			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
 
 /**
@@ -210,10 +230,8 @@ static inline void atomic64_inc(atomic64_t *v)
  */
 static inline void atomic64_dec(atomic64_t *v)
 {
-	asm volatile(ATOMIC64_ALTERNATIVE_(dec, dec_return)
-		     : : "S" (v)
-		     : "memory", "eax", "ecx", "edx"
-		     );
+	__alternative_atomic64(dec, dec_return, /* no output */,
+			       "S" (v) : "memory", "eax", "ecx", "edx");
 }
 
 /**
@@ -263,15 +281,15 @@ static inline int atomic64_add_negative(long long i, atomic64_t *v)
  * @u: ...unless v is equal to u.
  *
  * Atomically adds @a to @v, so long as it was not @u.
- * Returns the old value of @v.
+ * Returns non-zero if the add was done, zero otherwise.
  */
 static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned low = (unsigned)u;
 	unsigned high = (unsigned)(u >> 32);
-	asm volatile(ATOMIC64_ALTERNATIVE(add_unless) "\n\t"
-		     : "+A" (a), "+c" (v), "+S" (low), "+D" (high)
-		     : : "memory");
+	alternative_atomic64(add_unless,
+			     ASM_OUTPUT2("+A" (a), "+c" (low), "+D" (high)),
+			     "S" (v) : "memory");
 	return (int)a;
 }
 
@@ -279,26 +297,20 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 static inline int atomic64_inc_not_zero(atomic64_t *v)
 {
 	int r;
-	asm volatile(ATOMIC64_ALTERNATIVE(inc_not_zero)
-		     : "=a" (r)
-		     : "S" (v)
-		     : "ecx", "edx", "memory"
-		     );
+	alternative_atomic64(inc_not_zero, "=&a" (r),
+			     "S" (v) : "ecx", "edx", "memory");
 	return r;
 }
 
 static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
 	long long r;
-	asm volatile(ATOMIC64_ALTERNATIVE(dec_if_positive)
-		     : "=A" (r)
-		     : "S" (v)
-		     : "ecx", "memory"
-		     );
+	alternative_atomic64(dec_if_positive, "=&A" (r),
+			     "S" (v) : "ecx", "memory");
 	return r;
 }
 
-#undef ATOMIC64_ALTERNATIVE
-#undef ATOMIC64_ALTERNATIVE_
+#undef alternative_atomic64
+#undef __alternative_atomic64
 
 #endif /* _ASM_X86_ATOMIC64_32_H */
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
new file mode 100644
index 00000000000..ff501e511d9
--- /dev/null
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -0,0 +1,13 @@
+#ifndef _CPU_DEVICE_ID
+#define _CPU_DEVICE_ID 1
+
+/*
+ * Declare drivers belonging to specific x86 CPUs
+ * Similar in spirit to pci_device_id and related PCI functions
+ */
+
+#include <linux/mod_devicetable.h>
+
+extern const struct x86_cpu_id *x86_match_cpu(const struct x86_cpu_id *match);
+
+#endif
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 8d67d428b0f..340ee49961a 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -177,6 +177,7 @@
 #define X86_FEATURE_PLN		(7*32+ 5) /* Intel Power Limit Notification */
 #define X86_FEATURE_PTS		(7*32+ 6) /* Intel Package Thermal Status */
 #define X86_FEATURE_DTS		(7*32+ 7) /* Digital Thermal Sensor */
+#define X86_FEATURE_HW_PSTATE	(7*32+ 8) /* AMD HW-PState */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
@@ -199,10 +200,13 @@
 /* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */
 #define X86_FEATURE_FSGSBASE	(9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/
 #define X86_FEATURE_BMI1	(9*32+ 3) /* 1st group bit manipulation extensions */
+#define X86_FEATURE_HLE		(9*32+ 4) /* Hardware Lock Elision */
 #define X86_FEATURE_AVX2	(9*32+ 5) /* AVX2 instructions */
 #define X86_FEATURE_SMEP	(9*32+ 7) /* Supervisor Mode Execution Protection */
 #define X86_FEATURE_BMI2	(9*32+ 8) /* 2nd group bit manipulation extensions */
 #define X86_FEATURE_ERMS	(9*32+ 9) /* Enhanced REP MOVSB/STOSB */
+#define X86_FEATURE_INVPCID	(9*32+10) /* Invalidate Processor Context ID */
+#define X86_FEATURE_RTM		(9*32+11) /* Restricted Transactional Memory */
 
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index b903d5ea394..2d91580bf22 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -78,8 +78,75 @@
  */
 #ifdef __KERNEL__
 
+#include <linux/bug.h>
+
 DECLARE_PER_CPU(unsigned long, cpu_dr7);
 
+#ifndef CONFIG_PARAVIRT
+/*
+ * These special macros can be used to get or set a debugging register
+ */
+#define get_debugreg(var, register)				\
+	(var) = native_get_debugreg(register)
+#define set_debugreg(value, register)				\
+	native_set_debugreg(register, value)
+#endif
+
+static inline unsigned long native_get_debugreg(int regno)
+{
+	unsigned long val = 0;	/* Damn you, gcc! */
+
+	switch (regno) {
+	case 0:
+		asm("mov %%db0, %0" :"=r" (val));
+		break;
+	case 1:
+		asm("mov %%db1, %0" :"=r" (val));
+		break;
+	case 2:
+		asm("mov %%db2, %0" :"=r" (val));
+		break;
+	case 3:
+		asm("mov %%db3, %0" :"=r" (val));
+		break;
+	case 6:
+		asm("mov %%db6, %0" :"=r" (val));
+		break;
+	case 7:
+		asm("mov %%db7, %0" :"=r" (val));
+		break;
+	default:
+		BUG();
+	}
+	return val;
+}
+
+static inline void native_set_debugreg(int regno, unsigned long value)
+{
+	switch (regno) {
+	case 0:
+		asm("mov %0, %%db0"	::"r" (value));
+		break;
+	case 1:
+		asm("mov %0, %%db1"	::"r" (value));
+		break;
+	case 2:
+		asm("mov %0, %%db2"	::"r" (value));
+		break;
+	case 3:
+		asm("mov %0, %%db3"	::"r" (value));
+		break;
+	case 6:
+		asm("mov %0, %%db6"	::"r" (value));
+		break;
+	case 7:
+		asm("mov %0, %%db7"	::"r" (value));
+		break;
+	default:
+		BUG();
+	}
+}
+
 static inline void hw_breakpoint_disable(void)
 {
 	/* Zero the control register for HW Breakpoint */
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 844f735fd63..c9dcc181d4d 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -95,7 +95,7 @@ extern void __iomem *efi_ioremap(unsigned long addr, unsigned long size,
 
 extern int add_efi_memmap;
 extern void efi_set_executable(efi_memory_desc_t *md, bool executable);
-extern void efi_memblock_x86_reserve_range(void);
+extern int efi_memblock_x86_reserve_range(void);
 extern void efi_call_phys_prelog(void);
 extern void efi_call_phys_epilog(void);
 
diff --git a/arch/x86/include/asm/fpu-internal.h b/arch/x86/include/asm/fpu-internal.h
new file mode 100644
index 00000000000..4fa88154e4d
--- /dev/null
+++ b/arch/x86/include/asm/fpu-internal.h
@@ -0,0 +1,520 @@
+/*
+ * Copyright (C) 1994 Linus Torvalds
+ *
+ * Pentium III FXSR, SSE support
+ * General FPU state handling cleanups
+ *	Gareth Hughes <gareth@valinux.com>, May 2000
+ * x86-64 work by Andi Kleen 2002
+ */
+
+#ifndef _FPU_INTERNAL_H
+#define _FPU_INTERNAL_H
+
+#include <linux/kernel_stat.h>
+#include <linux/regset.h>
+#include <linux/slab.h>
+#include <asm/asm.h>
+#include <asm/cpufeature.h>
+#include <asm/processor.h>
+#include <asm/sigcontext.h>
+#include <asm/user.h>
+#include <asm/uaccess.h>
+#include <asm/xsave.h>
+
+extern unsigned int sig_xstate_size;
+extern void fpu_init(void);
+
+DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
+
+extern user_regset_active_fn fpregs_active, xfpregs_active;
+extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
+				xstateregs_get;
+extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
+				 xstateregs_set;
+
+
+/*
+ * xstateregs_active == fpregs_active. Please refer to the comment
+ * at the definition of fpregs_active.
+ */
+#define xstateregs_active	fpregs_active
+
+extern struct _fpx_sw_bytes fx_sw_reserved;
+#ifdef CONFIG_IA32_EMULATION
+extern unsigned int sig_xstate_ia32_size;
+extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
+struct _fpstate_ia32;
+struct _xstate_ia32;
+extern int save_i387_xstate_ia32(void __user *buf);
+extern int restore_i387_xstate_ia32(void __user *buf);
+#endif
+
+#ifdef CONFIG_MATH_EMULATION
+extern void finit_soft_fpu(struct i387_soft_struct *soft);
+#else
+static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
+#endif
+
+#define X87_FSW_ES (1 << 7)	/* Exception Summary */
+
+static __always_inline __pure bool use_xsaveopt(void)
+{
+	return static_cpu_has(X86_FEATURE_XSAVEOPT);
+}
+
+static __always_inline __pure bool use_xsave(void)
+{
+	return static_cpu_has(X86_FEATURE_XSAVE);
+}
+
+static __always_inline __pure bool use_fxsr(void)
+{
+        return static_cpu_has(X86_FEATURE_FXSR);
+}
+
+extern void __sanitize_i387_state(struct task_struct *);
+
+static inline void sanitize_i387_state(struct task_struct *tsk)
+{
+	if (!use_xsaveopt())
+		return;
+	__sanitize_i387_state(tsk);
+}
+
+#ifdef CONFIG_X86_64
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+{
+	int err;
+
+	/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+	asm volatile("1:  fxrstorq %[fx]\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err)
+		     : [fx] "m" (*fx), "0" (0));
+#else
+	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err)
+		     : [fx] "R" (fx), "m" (*fx), "0" (0));
+#endif
+	return err;
+}
+
+static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
+{
+	int err;
+
+	/*
+	 * Clear the bytes not touched by the fxsave and reserved
+	 * for the SW usage.
+	 */
+	err = __clear_user(&fx->sw_reserved,
+			   sizeof(struct _fpx_sw_bytes));
+	if (unlikely(err))
+		return -EFAULT;
+
+	/* See comment in fxsave() below. */
+#ifdef CONFIG_AS_FXSAVEQ
+	asm volatile("1:  fxsaveq %[fx]\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err), [fx] "=m" (*fx)
+		     : "0" (0));
+#else
+	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
+		     "2:\n"
+		     ".section .fixup,\"ax\"\n"
+		     "3:  movl $-1,%[err]\n"
+		     "    jmp  2b\n"
+		     ".previous\n"
+		     _ASM_EXTABLE(1b, 3b)
+		     : [err] "=r" (err), "=m" (*fx)
+		     : [fx] "R" (fx), "0" (0));
+#endif
+	if (unlikely(err) &&
+	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
+		err = -EFAULT;
+	/* No need to clear here because the caller clears USED_MATH */
+	return err;
+}
+
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+	/* Using "rex64; fxsave %0" is broken because, if the memory operand
+	   uses any extended registers for addressing, a second REX prefix
+	   will be generated (to the assembler, rex64 followed by semicolon
+	   is a separate instruction), and hence the 64-bitness is lost. */
+
+#ifdef CONFIG_AS_FXSAVEQ
+	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
+	   starting with gas 2.16. */
+	__asm__ __volatile__("fxsaveq %0"
+			     : "=m" (fpu->state->fxsave));
+#else
+	/* Using, as a workaround, the properly prefixed form below isn't
+	   accepted by any binutils version so far released, complaining that
+	   the same type of prefix is used twice if an extended register is
+	   needed for addressing (fix submitted to mainline 2005-11-21).
+	asm volatile("rex64/fxsave %0"
+		     : "=m" (fpu->state->fxsave));
+	   This, however, we can work around by forcing the compiler to select
+	   an addressing mode that doesn't require extended registers. */
+	asm volatile("rex64/fxsave (%[fx])"
+		     : "=m" (fpu->state->fxsave)
+		     : [fx] "R" (&fpu->state->fxsave));
+#endif
+}
+
+#else  /* CONFIG_X86_32 */
+
+/* perform fxrstor iff the processor has extended states, otherwise frstor */
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
+{
+	/*
+	 * The "nop" is needed to make the instructions the same
+	 * length.
+	 */
+	alternative_input(
+		"nop ; frstor %1",
+		"fxrstor %1",
+		X86_FEATURE_FXSR,
+		"m" (*fx));
+
+	return 0;
+}
+
+static inline void fpu_fxsave(struct fpu *fpu)
+{
+	asm volatile("fxsave %[fx]"
+		     : [fx] "=m" (fpu->state->fxsave));
+}
+
+#endif	/* CONFIG_X86_64 */
+
+/*
+ * These must be called with preempt disabled. Returns
+ * 'true' if the FPU state is still intact.
+ */
+static inline int fpu_save_init(struct fpu *fpu)
+{
+	if (use_xsave()) {
+		fpu_xsave(fpu);
+
+		/*
+		 * xsave header may indicate the init state of the FP.
+		 */
+		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
+			return 1;
+	} else if (use_fxsr()) {
+		fpu_fxsave(fpu);
+	} else {
+		asm volatile("fnsave %[fx]; fwait"
+			     : [fx] "=m" (fpu->state->fsave));
+		return 0;
+	}
+
+	/*
+	 * If exceptions are pending, we need to clear them so
+	 * that we don't randomly get exceptions later.
+	 *
+	 * FIXME! Is this perhaps only true for the old-style
+	 * irq13 case? Maybe we could leave the x87 state
+	 * intact otherwise?
+	 */
+	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
+		asm volatile("fnclex");
+		return 0;
+	}
+	return 1;
+}
+
+static inline int __save_init_fpu(struct task_struct *tsk)
+{
+	return fpu_save_init(&tsk->thread.fpu);
+}
+
+static inline int fpu_fxrstor_checking(struct fpu *fpu)
+{
+	return fxrstor_checking(&fpu->state->fxsave);
+}
+
+static inline int fpu_restore_checking(struct fpu *fpu)
+{
+	if (use_xsave())
+		return fpu_xrstor_checking(fpu);
+	else
+		return fpu_fxrstor_checking(fpu);
+}
+
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
+	   is pending.  Clear the x87 state here by setting it to fixed
+	   values. "m" is a random variable that should be in L1 */
+	alternative_input(
+		ASM_NOP8 ASM_NOP2,
+		"emms\n\t"		/* clear stack tags */
+		"fildl %P[addr]",	/* set F?P to defined value */
+		X86_FEATURE_FXSAVE_LEAK,
+		[addr] "m" (tsk->thread.fpu.has_fpu));
+
+	return fpu_restore_checking(&tsk->thread.fpu);
+}
+
+/*
+ * Software FPU state helpers. Careful: these need to
+ * be preemption protection *and* they need to be
+ * properly paired with the CR0.TS changes!
+ */
+static inline int __thread_has_fpu(struct task_struct *tsk)
+{
+	return tsk->thread.fpu.has_fpu;
+}
+
+/* Must be paired with an 'stts' after! */
+static inline void __thread_clear_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.fpu.has_fpu = 0;
+	percpu_write(fpu_owner_task, NULL);
+}
+
+/* Must be paired with a 'clts' before! */
+static inline void __thread_set_has_fpu(struct task_struct *tsk)
+{
+	tsk->thread.fpu.has_fpu = 1;
+	percpu_write(fpu_owner_task, tsk);
+}
+
+/*
+ * Encapsulate the CR0.TS handling together with the
+ * software flag.
+ *
+ * These generally need preemption protection to work,
+ * do try to avoid using these on their own.
+ */
+static inline void __thread_fpu_end(struct task_struct *tsk)
+{
+	__thread_clear_has_fpu(tsk);
+	stts();
+}
+
+static inline void __thread_fpu_begin(struct task_struct *tsk)
+{
+	clts();
+	__thread_set_has_fpu(tsk);
+}
+
+/*
+ * FPU state switching for scheduling.
+ *
+ * This is a two-stage process:
+ *
+ *  - switch_fpu_prepare() saves the old state and
+ *    sets the new state of the CR0.TS bit. This is
+ *    done within the context of the old process.
+ *
+ *  - switch_fpu_finish() restores the new state as
+ *    necessary.
+ */
+typedef struct { int preload; } fpu_switch_t;
+
+/*
+ * FIXME! We could do a totally lazy restore, but we need to
+ * add a per-cpu "this was the task that last touched the FPU
+ * on this CPU" variable, and the task needs to have a "I last
+ * touched the FPU on this CPU" and check them.
+ *
+ * We don't do that yet, so "fpu_lazy_restore()" always returns
+ * false, but some day..
+ */
+static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
+{
+	return new == percpu_read_stable(fpu_owner_task) &&
+		cpu == new->thread.fpu.last_cpu;
+}
+
+static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
+{
+	fpu_switch_t fpu;
+
+	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
+	if (__thread_has_fpu(old)) {
+		if (!__save_init_fpu(old))
+			cpu = ~0;
+		old->thread.fpu.last_cpu = cpu;
+		old->thread.fpu.has_fpu = 0;	/* But leave fpu_owner_task! */
+
+		/* Don't change CR0.TS if we just switch! */
+		if (fpu.preload) {
+			new->fpu_counter++;
+			__thread_set_has_fpu(new);
+			prefetch(new->thread.fpu.state);
+		} else
+			stts();
+	} else {
+		old->fpu_counter = 0;
+		old->thread.fpu.last_cpu = ~0;
+		if (fpu.preload) {
+			new->fpu_counter++;
+			if (fpu_lazy_restore(new, cpu))
+				fpu.preload = 0;
+			else
+				prefetch(new->thread.fpu.state);
+			__thread_fpu_begin(new);
+		}
+	}
+	return fpu;
+}
+
+/*
+ * By the time this gets called, we've already cleared CR0.TS and
+ * given the process the FPU if we are going to preload the FPU
+ * state - all we need to do is to conditionally restore the register
+ * state itself.
+ */
+static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
+{
+	if (fpu.preload) {
+		if (unlikely(restore_fpu_checking(new)))
+			__thread_fpu_end(new);
+	}
+}
+
+/*
+ * Signal frame handlers...
+ */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
+
+static inline void __clear_fpu(struct task_struct *tsk)
+{
+	if (__thread_has_fpu(tsk)) {
+		/* Ignore delayed exceptions from user space */
+		asm volatile("1: fwait\n"
+			     "2:\n"
+			     _ASM_EXTABLE(1b, 2b));
+		__thread_fpu_end(tsk);
+	}
+}
+
+/*
+ * The actual user_fpu_begin/end() functions
+ * need to be preemption-safe.
+ *
+ * NOTE! user_fpu_end() must be used only after you
+ * have saved the FP state, and user_fpu_begin() must
+ * be used only immediately before restoring it.
+ * These functions do not do any save/restore on
+ * their own.
+ */
+static inline void user_fpu_end(void)
+{
+	preempt_disable();
+	__thread_fpu_end(current);
+	preempt_enable();
+}
+
+static inline void user_fpu_begin(void)
+{
+	preempt_disable();
+	if (!user_has_fpu())
+		__thread_fpu_begin(current);
+	preempt_enable();
+}
+
+/*
+ * These disable preemption on their own and are safe
+ */
+static inline void save_init_fpu(struct task_struct *tsk)
+{
+	WARN_ON_ONCE(!__thread_has_fpu(tsk));
+	preempt_disable();
+	__save_init_fpu(tsk);
+	__thread_fpu_end(tsk);
+	preempt_enable();
+}
+
+static inline void clear_fpu(struct task_struct *tsk)
+{
+	preempt_disable();
+	__clear_fpu(tsk);
+	preempt_enable();
+}
+
+/*
+ * i387 state interaction
+ */
+static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
+{
+	if (cpu_has_fxsr) {
+		return tsk->thread.fpu.state->fxsave.cwd;
+	} else {
+		return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
+	}
+}
+
+static inline unsigned short get_fpu_swd(struct task_struct *tsk)
+{
+	if (cpu_has_fxsr) {
+		return tsk->thread.fpu.state->fxsave.swd;
+	} else {
+		return (unsigned short)tsk->thread.fpu.state->fsave.swd;
+	}
+}
+
+static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
+{
+	if (cpu_has_xmm) {
+		return tsk->thread.fpu.state->fxsave.mxcsr;
+	} else {
+		return MXCSR_DEFAULT;
+	}
+}
+
+static bool fpu_allocated(struct fpu *fpu)
+{
+	return fpu->state != NULL;
+}
+
+static inline int fpu_alloc(struct fpu *fpu)
+{
+	if (fpu_allocated(fpu))
+		return 0;
+	fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
+	if (!fpu->state)
+		return -ENOMEM;
+	WARN_ON((unsigned long)fpu->state & 15);
+	return 0;
+}
+
+static inline void fpu_free(struct fpu *fpu)
+{
+	if (fpu->state) {
+		kmem_cache_free(task_xstate_cachep, fpu->state);
+		fpu->state = NULL;
+	}
+}
+
+static inline void fpu_copy(struct fpu *dst, struct fpu *src)
+{
+	memcpy(dst->state, src->state, xstate_size);
+}
+
+extern void fpu_finit(struct fpu *fpu);
+
+#endif
diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
index da0b3ca815b..382f75d735f 100644
--- a/arch/x86/include/asm/hardirq.h
+++ b/arch/x86/include/asm/hardirq.h
@@ -7,7 +7,6 @@
 typedef struct {
 	unsigned int __softirq_pending;
 	unsigned int __nmi_count;	/* arch dependent */
-	unsigned int irq0_irqs;
 #ifdef CONFIG_X86_LOCAL_APIC
 	unsigned int apic_timer_irqs;	/* arch dependent */
 	unsigned int irq_spurious_count;
diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h
index 3bd04022fd0..302a323b3f6 100644
--- a/arch/x86/include/asm/highmem.h
+++ b/arch/x86/include/asm/highmem.h
@@ -61,7 +61,7 @@ void *kmap(struct page *page);
 void kunmap(struct page *page);
 
 void *kmap_atomic_prot(struct page *page, pgprot_t prot);
-void *__kmap_atomic(struct page *page);
+void *kmap_atomic(struct page *page);
 void __kunmap_atomic(void *kvaddr);
 void *kmap_atomic_pfn(unsigned long pfn);
 void *kmap_atomic_prot_pfn(unsigned long pfn, pgprot_t prot);
diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h
index 247904945d3..7ce0798b1b2 100644
--- a/arch/x86/include/asm/i387.h
+++ b/arch/x86/include/asm/i387.h
@@ -13,476 +13,19 @@
 #ifndef __ASSEMBLY__
 
 #include <linux/sched.h>
-#include <linux/kernel_stat.h>
-#include <linux/regset.h>
 #include <linux/hardirq.h>
-#include <linux/slab.h>
-#include <asm/asm.h>
-#include <asm/cpufeature.h>
-#include <asm/processor.h>
-#include <asm/sigcontext.h>
-#include <asm/user.h>
-#include <asm/uaccess.h>
-#include <asm/xsave.h>
+#include <asm/system.h>
+
+struct pt_regs;
+struct user_i387_struct;
 
-extern unsigned int sig_xstate_size;
-extern void fpu_init(void);
-extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
-extern void math_state_restore(void);
 extern int dump_fpu(struct pt_regs *, struct user_i387_struct *);
+extern void math_state_restore(void);
 
-DECLARE_PER_CPU(struct task_struct *, fpu_owner_task);
-
-extern user_regset_active_fn fpregs_active, xfpregs_active;
-extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get,
-				xstateregs_get;
-extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set,
-				 xstateregs_set;
-
-/*
- * xstateregs_active == fpregs_active. Please refer to the comment
- * at the definition of fpregs_active.
- */
-#define xstateregs_active	fpregs_active
-
-extern struct _fpx_sw_bytes fx_sw_reserved;
-#ifdef CONFIG_IA32_EMULATION
-extern unsigned int sig_xstate_ia32_size;
-extern struct _fpx_sw_bytes fx_sw_reserved_ia32;
-struct _fpstate_ia32;
-struct _xstate_ia32;
-extern int save_i387_xstate_ia32(void __user *buf);
-extern int restore_i387_xstate_ia32(void __user *buf);
-#endif
-
-#ifdef CONFIG_MATH_EMULATION
-extern void finit_soft_fpu(struct i387_soft_struct *soft);
-#else
-static inline void finit_soft_fpu(struct i387_soft_struct *soft) {}
-#endif
-
-#define X87_FSW_ES (1 << 7)	/* Exception Summary */
-
-static __always_inline __pure bool use_xsaveopt(void)
-{
-	return static_cpu_has(X86_FEATURE_XSAVEOPT);
-}
-
-static __always_inline __pure bool use_xsave(void)
-{
-	return static_cpu_has(X86_FEATURE_XSAVE);
-}
-
-static __always_inline __pure bool use_fxsr(void)
-{
-        return static_cpu_has(X86_FEATURE_FXSR);
-}
-
-extern void __sanitize_i387_state(struct task_struct *);
-
-static inline void sanitize_i387_state(struct task_struct *tsk)
-{
-	if (!use_xsaveopt())
-		return;
-	__sanitize_i387_state(tsk);
-}
-
-#ifdef CONFIG_X86_64
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
-	int err;
-
-	/* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
-	asm volatile("1:  fxrstorq %[fx]\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : [fx] "m" (*fx), "0" (0));
-#else
-	asm volatile("1:  rex64/fxrstor (%[fx])\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err)
-		     : [fx] "R" (fx), "m" (*fx), "0" (0));
-#endif
-	return err;
-}
-
-static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
-{
-	int err;
-
-	/*
-	 * Clear the bytes not touched by the fxsave and reserved
-	 * for the SW usage.
-	 */
-	err = __clear_user(&fx->sw_reserved,
-			   sizeof(struct _fpx_sw_bytes));
-	if (unlikely(err))
-		return -EFAULT;
-
-	/* See comment in fxsave() below. */
-#ifdef CONFIG_AS_FXSAVEQ
-	asm volatile("1:  fxsaveq %[fx]\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), [fx] "=m" (*fx)
-		     : "0" (0));
-#else
-	asm volatile("1:  rex64/fxsave (%[fx])\n\t"
-		     "2:\n"
-		     ".section .fixup,\"ax\"\n"
-		     "3:  movl $-1,%[err]\n"
-		     "    jmp  2b\n"
-		     ".previous\n"
-		     _ASM_EXTABLE(1b, 3b)
-		     : [err] "=r" (err), "=m" (*fx)
-		     : [fx] "R" (fx), "0" (0));
-#endif
-	if (unlikely(err) &&
-	    __clear_user(fx, sizeof(struct i387_fxsave_struct)))
-		err = -EFAULT;
-	/* No need to clear here because the caller clears USED_MATH */
-	return err;
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
-	/* Using "rex64; fxsave %0" is broken because, if the memory operand
-	   uses any extended registers for addressing, a second REX prefix
-	   will be generated (to the assembler, rex64 followed by semicolon
-	   is a separate instruction), and hence the 64-bitness is lost. */
-
-#ifdef CONFIG_AS_FXSAVEQ
-	/* Using "fxsaveq %0" would be the ideal choice, but is only supported
-	   starting with gas 2.16. */
-	__asm__ __volatile__("fxsaveq %0"
-			     : "=m" (fpu->state->fxsave));
-#else
-	/* Using, as a workaround, the properly prefixed form below isn't
-	   accepted by any binutils version so far released, complaining that
-	   the same type of prefix is used twice if an extended register is
-	   needed for addressing (fix submitted to mainline 2005-11-21).
-	asm volatile("rex64/fxsave %0"
-		     : "=m" (fpu->state->fxsave));
-	   This, however, we can work around by forcing the compiler to select
-	   an addressing mode that doesn't require extended registers. */
-	asm volatile("rex64/fxsave (%[fx])"
-		     : "=m" (fpu->state->fxsave)
-		     : [fx] "R" (&fpu->state->fxsave));
-#endif
-}
-
-#else  /* CONFIG_X86_32 */
-
-/* perform fxrstor iff the processor has extended states, otherwise frstor */
-static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
-{
-	/*
-	 * The "nop" is needed to make the instructions the same
-	 * length.
-	 */
-	alternative_input(
-		"nop ; frstor %1",
-		"fxrstor %1",
-		X86_FEATURE_FXSR,
-		"m" (*fx));
-
-	return 0;
-}
-
-static inline void fpu_fxsave(struct fpu *fpu)
-{
-	asm volatile("fxsave %[fx]"
-		     : [fx] "=m" (fpu->state->fxsave));
-}
-
-#endif	/* CONFIG_X86_64 */
-
-/*
- * These must be called with preempt disabled. Returns
- * 'true' if the FPU state is still intact.
- */
-static inline int fpu_save_init(struct fpu *fpu)
-{
-	if (use_xsave()) {
-		fpu_xsave(fpu);
-
-		/*
-		 * xsave header may indicate the init state of the FP.
-		 */
-		if (!(fpu->state->xsave.xsave_hdr.xstate_bv & XSTATE_FP))
-			return 1;
-	} else if (use_fxsr()) {
-		fpu_fxsave(fpu);
-	} else {
-		asm volatile("fnsave %[fx]; fwait"
-			     : [fx] "=m" (fpu->state->fsave));
-		return 0;
-	}
-
-	/*
-	 * If exceptions are pending, we need to clear them so
-	 * that we don't randomly get exceptions later.
-	 *
-	 * FIXME! Is this perhaps only true for the old-style
-	 * irq13 case? Maybe we could leave the x87 state
-	 * intact otherwise?
-	 */
-	if (unlikely(fpu->state->fxsave.swd & X87_FSW_ES)) {
-		asm volatile("fnclex");
-		return 0;
-	}
-	return 1;
-}
-
-static inline int __save_init_fpu(struct task_struct *tsk)
-{
-	return fpu_save_init(&tsk->thread.fpu);
-}
-
-static inline int fpu_fxrstor_checking(struct fpu *fpu)
-{
-	return fxrstor_checking(&fpu->state->fxsave);
-}
-
-static inline int fpu_restore_checking(struct fpu *fpu)
-{
-	if (use_xsave())
-		return fpu_xrstor_checking(fpu);
-	else
-		return fpu_fxrstor_checking(fpu);
-}
-
-static inline int restore_fpu_checking(struct task_struct *tsk)
-{
-	/* AMD K7/K8 CPUs don't save/restore FDP/FIP/FOP unless an exception
-	   is pending.  Clear the x87 state here by setting it to fixed
-	   values. "m" is a random variable that should be in L1 */
-	alternative_input(
-		ASM_NOP8 ASM_NOP2,
-		"emms\n\t"	  	/* clear stack tags */
-		"fildl %P[addr]",	/* set F?P to defined value */
-		X86_FEATURE_FXSAVE_LEAK,
-		[addr] "m" (tsk->thread.fpu.has_fpu));
-
-	return fpu_restore_checking(&tsk->thread.fpu);
-}
-
-/*
- * Software FPU state helpers. Careful: these need to
- * be preemption protection *and* they need to be
- * properly paired with the CR0.TS changes!
- */
-static inline int __thread_has_fpu(struct task_struct *tsk)
-{
-	return tsk->thread.fpu.has_fpu;
-}
-
-/* Must be paired with an 'stts' after! */
-static inline void __thread_clear_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 0;
-	percpu_write(fpu_owner_task, NULL);
-}
-
-/* Must be paired with a 'clts' before! */
-static inline void __thread_set_has_fpu(struct task_struct *tsk)
-{
-	tsk->thread.fpu.has_fpu = 1;
-	percpu_write(fpu_owner_task, tsk);
-}
-
-/*
- * Encapsulate the CR0.TS handling together with the
- * software flag.
- *
- * These generally need preemption protection to work,
- * do try to avoid using these on their own.
- */
-static inline void __thread_fpu_end(struct task_struct *tsk)
-{
-	__thread_clear_has_fpu(tsk);
-	stts();
-}
-
-static inline void __thread_fpu_begin(struct task_struct *tsk)
-{
-	clts();
-	__thread_set_has_fpu(tsk);
-}
-
-/*
- * FPU state switching for scheduling.
- *
- * This is a two-stage process:
- *
- *  - switch_fpu_prepare() saves the old state and
- *    sets the new state of the CR0.TS bit. This is
- *    done within the context of the old process.
- *
- *  - switch_fpu_finish() restores the new state as
- *    necessary.
- */
-typedef struct { int preload; } fpu_switch_t;
-
-/*
- * FIXME! We could do a totally lazy restore, but we need to
- * add a per-cpu "this was the task that last touched the FPU
- * on this CPU" variable, and the task needs to have a "I last
- * touched the FPU on this CPU" and check them.
- *
- * We don't do that yet, so "fpu_lazy_restore()" always returns
- * false, but some day..
- */
-static inline int fpu_lazy_restore(struct task_struct *new, unsigned int cpu)
-{
-	return new == percpu_read_stable(fpu_owner_task) &&
-		cpu == new->thread.fpu.last_cpu;
-}
-
-static inline fpu_switch_t switch_fpu_prepare(struct task_struct *old, struct task_struct *new, int cpu)
-{
-	fpu_switch_t fpu;
-
-	fpu.preload = tsk_used_math(new) && new->fpu_counter > 5;
-	if (__thread_has_fpu(old)) {
-		if (!__save_init_fpu(old))
-			cpu = ~0;
-		old->thread.fpu.last_cpu = cpu;
-		old->thread.fpu.has_fpu = 0;	/* But leave fpu_owner_task! */
-
-		/* Don't change CR0.TS if we just switch! */
-		if (fpu.preload) {
-			new->fpu_counter++;
-			__thread_set_has_fpu(new);
-			prefetch(new->thread.fpu.state);
-		} else
-			stts();
-	} else {
-		old->fpu_counter = 0;
-		old->thread.fpu.last_cpu = ~0;
-		if (fpu.preload) {
-			new->fpu_counter++;
-			if (fpu_lazy_restore(new, cpu))
-				fpu.preload = 0;
-			else
-				prefetch(new->thread.fpu.state);
-			__thread_fpu_begin(new);
-		}
-	}
-	return fpu;
-}
-
-/*
- * By the time this gets called, we've already cleared CR0.TS and
- * given the process the FPU if we are going to preload the FPU
- * state - all we need to do is to conditionally restore the register
- * state itself.
- */
-static inline void switch_fpu_finish(struct task_struct *new, fpu_switch_t fpu)
-{
-	if (fpu.preload) {
-		if (unlikely(restore_fpu_checking(new)))
-			__thread_fpu_end(new);
-	}
-}
-
-/*
- * Signal frame handlers...
- */
-extern int save_i387_xstate(void __user *buf);
-extern int restore_i387_xstate(void __user *buf);
-
-static inline void __clear_fpu(struct task_struct *tsk)
-{
-	if (__thread_has_fpu(tsk)) {
-		/* Ignore delayed exceptions from user space */
-		asm volatile("1: fwait\n"
-			     "2:\n"
-			     _ASM_EXTABLE(1b, 2b));
-		__thread_fpu_end(tsk);
-	}
-}
-
-/*
- * Were we in an interrupt that interrupted kernel mode?
- *
- * We can do a kernel_fpu_begin/end() pair *ONLY* if that
- * pair does nothing at all: the thread must not have fpu (so
- * that we don't try to save the FPU state), and TS must
- * be set (so that the clts/stts pair does nothing that is
- * visible in the interrupted kernel thread).
- */
-static inline bool interrupted_kernel_fpu_idle(void)
-{
-	return !__thread_has_fpu(current) &&
-		(read_cr0() & X86_CR0_TS);
-}
-
-/*
- * Were we in user mode (or vm86 mode) when we were
- * interrupted?
- *
- * Doing kernel_fpu_begin/end() is ok if we are running
- * in an interrupt context from user mode - we'll just
- * save the FPU state as required.
- */
-static inline bool interrupted_user_mode(void)
-{
-	struct pt_regs *regs = get_irq_regs();
-	return regs && user_mode_vm(regs);
-}
-
-/*
- * Can we use the FPU in kernel mode with the
- * whole "kernel_fpu_begin/end()" sequence?
- *
- * It's always ok in process context (ie "not interrupt")
- * but it is sometimes ok even from an irq.
- */
-static inline bool irq_fpu_usable(void)
-{
-	return !in_interrupt() ||
-		interrupted_user_mode() ||
-		interrupted_kernel_fpu_idle();
-}
-
-static inline void kernel_fpu_begin(void)
-{
-	struct task_struct *me = current;
-
-	WARN_ON_ONCE(!irq_fpu_usable());
-	preempt_disable();
-	if (__thread_has_fpu(me)) {
-		__save_init_fpu(me);
-		__thread_clear_has_fpu(me);
-		/* We do 'stts()' in kernel_fpu_end() */
-	} else {
-		percpu_write(fpu_owner_task, NULL);
-		clts();
-	}
-}
-
-static inline void kernel_fpu_end(void)
-{
-	stts();
-	preempt_enable();
-}
+extern bool irq_fpu_usable(void);
+extern void kernel_fpu_begin(void);
+extern void kernel_fpu_end(void);
 
 /*
  * Some instructions like VIA's padlock instructions generate a spurious
@@ -524,126 +67,13 @@ static inline void irq_ts_restore(int TS_state)
  * we can just assume we have FPU access - typically
  * to save the FP state - we'll just take a #NM
  * fault and get the FPU access back.
- *
- * The actual user_fpu_begin/end() functions
- * need to be preemption-safe, though.
- *
- * NOTE! user_fpu_end() must be used only after you
- * have saved the FP state, and user_fpu_begin() must
- * be used only immediately before restoring it.
- * These functions do not do any save/restore on
- * their own.
  */
 static inline int user_has_fpu(void)
 {
-	return __thread_has_fpu(current);
-}
-
-static inline void user_fpu_end(void)
-{
-	preempt_disable();
-	__thread_fpu_end(current);
-	preempt_enable();
-}
-
-static inline void user_fpu_begin(void)
-{
-	preempt_disable();
-	if (!user_has_fpu())
-		__thread_fpu_begin(current);
-	preempt_enable();
-}
-
-/*
- * These disable preemption on their own and are safe
- */
-static inline void save_init_fpu(struct task_struct *tsk)
-{
-	WARN_ON_ONCE(!__thread_has_fpu(tsk));
-	preempt_disable();
-	__save_init_fpu(tsk);
-	__thread_fpu_end(tsk);
-	preempt_enable();
-}
-
-static inline void unlazy_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	if (__thread_has_fpu(tsk)) {
-		__save_init_fpu(tsk);
-		__thread_fpu_end(tsk);
-	} else
-		tsk->fpu_counter = 0;
-	preempt_enable();
-}
-
-static inline void clear_fpu(struct task_struct *tsk)
-{
-	preempt_disable();
-	__clear_fpu(tsk);
-	preempt_enable();
-}
-
-/*
- * i387 state interaction
- */
-static inline unsigned short get_fpu_cwd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.cwd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.cwd;
-	}
-}
-
-static inline unsigned short get_fpu_swd(struct task_struct *tsk)
-{
-	if (cpu_has_fxsr) {
-		return tsk->thread.fpu.state->fxsave.swd;
-	} else {
-		return (unsigned short)tsk->thread.fpu.state->fsave.swd;
-	}
-}
-
-static inline unsigned short get_fpu_mxcsr(struct task_struct *tsk)
-{
-	if (cpu_has_xmm) {
-		return tsk->thread.fpu.state->fxsave.mxcsr;
-	} else {
-		return MXCSR_DEFAULT;
-	}
-}
-
-static bool fpu_allocated(struct fpu *fpu)
-{
-	return fpu->state != NULL;
-}
-
-static inline int fpu_alloc(struct fpu *fpu)
-{
-	if (fpu_allocated(fpu))
-		return 0;
-	fpu->state = kmem_cache_alloc(task_xstate_cachep, GFP_KERNEL);
-	if (!fpu->state)
-		return -ENOMEM;
-	WARN_ON((unsigned long)fpu->state & 15);
-	return 0;
-}
-
-static inline void fpu_free(struct fpu *fpu)
-{
-	if (fpu->state) {
-		kmem_cache_free(task_xstate_cachep, fpu->state);
-		fpu->state = NULL;
-	}
-}
-
-static inline void fpu_copy(struct fpu *dst, struct fpu *src)
-{
-	memcpy(dst->state, src->state, xstate_size);
+	return current->thread.fpu.has_fpu;
 }
 
-extern void fpu_finit(struct fpu *fpu);
+extern void unlazy_fpu(struct task_struct *tsk);
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 205b063e3e3..74a2e312e8a 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -97,11 +97,12 @@
 
 /* Attribute search APIs */
 extern insn_attr_t inat_get_opcode_attribute(insn_byte_t opcode);
+extern int inat_get_last_prefix_id(insn_byte_t last_pfx);
 extern insn_attr_t inat_get_escape_attribute(insn_byte_t opcode,
-					     insn_byte_t last_pfx,
+					     int lpfx_id,
 					     insn_attr_t esc_attr);
 extern insn_attr_t inat_get_group_attribute(insn_byte_t modrm,
-					    insn_byte_t last_pfx,
+					    int lpfx_id,
 					    insn_attr_t esc_attr);
 extern insn_attr_t inat_get_avx_attribute(insn_byte_t opcode,
 					  insn_byte_t vex_m,
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 74df3f1eddf..48eb30a8606 100644
--- a/arch/x86/include/asm/insn.h
+++ b/arch/x86/include/asm/insn.h
@@ -96,12 +96,6 @@ struct insn {
 #define X86_VEX_P(vex)	((vex) & 0x03)		/* VEX3 Byte2, VEX2 Byte1 */
 #define X86_VEX_M_MAX	0x1f			/* VEX3.M Maximum value */
 
-/* The last prefix is needed for two-byte and three-byte opcodes */
-static inline insn_byte_t insn_last_prefix(struct insn *insn)
-{
-	return insn->prefixes.bytes[3];
-}
-
 extern void insn_init(struct insn *insn, const void *kaddr, int x86_64);
 extern void insn_get_prefixes(struct insn *insn);
 extern void insn_get_opcode(struct insn *insn);
@@ -160,6 +154,18 @@ static inline insn_byte_t insn_vex_p_bits(struct insn *insn)
 		return X86_VEX_P(insn->vex_prefix.bytes[2]);
 }
 
+/* Get the last prefix id from last prefix or VEX prefix */
+static inline int insn_last_prefix_id(struct insn *insn)
+{
+	if (insn_is_avx(insn))
+		return insn_vex_p_bits(insn);	/* VEX_p is a SIMD prefix id */
+
+	if (insn->prefixes.bytes[3])
+		return inat_get_last_prefix_id(insn->prefixes.bytes[3]);
+
+	return 0;
+}
+
 /* Offset of each field from kaddr */
 static inline int insn_offset_rex_prefix(struct insn *insn)
 {
diff --git a/arch/x86/include/asm/irq_controller.h b/arch/x86/include/asm/irq_controller.h
deleted file mode 100644
index 423bbbddf36..00000000000
--- a/arch/x86/include/asm/irq_controller.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __IRQ_CONTROLLER__
-#define __IRQ_CONTROLLER__
-
-struct irq_domain {
-	int (*xlate)(struct irq_domain *h, const u32 *intspec, u32 intsize,
-			u32 *out_hwirq, u32 *out_type);
-	void *priv;
-	struct device_node *controller;
-	struct list_head l;
-};
-
-#endif
diff --git a/arch/x86/include/asm/jump_label.h b/arch/x86/include/asm/jump_label.h
index a32b18ce6ea..3a16c1483b4 100644
--- a/arch/x86/include/asm/jump_label.h
+++ b/arch/x86/include/asm/jump_label.h
@@ -9,12 +9,12 @@
 
 #define JUMP_LABEL_NOP_SIZE 5
 
-#define JUMP_LABEL_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
+#define STATIC_KEY_INITIAL_NOP ".byte 0xe9 \n\t .long 0\n\t"
 
-static __always_inline bool arch_static_branch(struct jump_label_key *key)
+static __always_inline bool arch_static_branch(struct static_key *key)
 {
 	asm goto("1:"
-		JUMP_LABEL_INITIAL_NOP
+		STATIC_KEY_INITIAL_NOP
 		".pushsection __jump_table,  \"aw\" \n\t"
 		_ASM_ALIGN "\n\t"
 		_ASM_PTR "1b, %l[l_yes], %c0 \n\t"
diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h
index 77e95f54570..332f98c9111 100644
--- a/arch/x86/include/asm/kgdb.h
+++ b/arch/x86/include/asm/kgdb.h
@@ -64,11 +64,15 @@ enum regnames {
 	GDB_PS,			/* 17 */
 	GDB_CS,			/* 18 */
 	GDB_SS,			/* 19 */
+	GDB_DS,			/* 20 */
+	GDB_ES,			/* 21 */
+	GDB_FS,			/* 22 */
+	GDB_GS,			/* 23 */
 };
 #define GDB_ORIG_AX		57
-#define DBG_MAX_REG_NUM		20
-/* 17 64 bit regs and 3 32 bit regs */
-#define NUMREGBYTES		((17 * 8) + (3 * 4))
+#define DBG_MAX_REG_NUM		24
+/* 17 64 bit regs and 5 32 bit regs */
+#define NUMREGBYTES		((17 * 8) + (5 * 4))
 #endif /* ! CONFIG_X86_32 */
 
 static inline void arch_kgdb_breakpoint(void)
diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 6aefb14cbbc..441520e4174 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -151,7 +151,7 @@ static inline void enable_p5_mce(void) {}
 
 void mce_setup(struct mce *m);
 void mce_log(struct mce *m);
-extern struct device *mce_device[CONFIG_NR_CPUS];
+DECLARE_PER_CPU(struct device *, mce_device);
 
 /*
  * Maximum banks number.
diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h
index 0a0a9546043..fc18bf3ce7c 100644
--- a/arch/x86/include/asm/mrst.h
+++ b/arch/x86/include/asm/mrst.h
@@ -26,8 +26,8 @@ extern struct sfi_rtc_table_entry sfi_mrtc_array[];
  * identified via MSRs.
  */
 enum mrst_cpu_type {
-	MRST_CPU_CHIP_LINCROFT = 1,
-	MRST_CPU_CHIP_PENWELL,
+	/* 1 was Moorestown */
+	MRST_CPU_CHIP_PENWELL = 2,
 };
 
 extern enum mrst_cpu_type __mrst_cpu_chip;
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index a6962d9161a..ccb805966f6 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -56,6 +56,13 @@
 #define MSR_OFFCORE_RSP_0		0x000001a6
 #define MSR_OFFCORE_RSP_1		0x000001a7
 
+#define MSR_LBR_SELECT			0x000001c8
+#define MSR_LBR_TOS			0x000001c9
+#define MSR_LBR_NHM_FROM		0x00000680
+#define MSR_LBR_NHM_TO			0x000006c0
+#define MSR_LBR_CORE_FROM		0x00000040
+#define MSR_LBR_CORE_TO			0x00000060
+
 #define MSR_IA32_PEBS_ENABLE		0x000003f1
 #define MSR_IA32_DS_AREA		0x00000600
 #define MSR_IA32_PERF_CAPABILITIES	0x00000345
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index a7d2db9a74f..aa0f9130836 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -10,6 +10,7 @@
 #include <asm/paravirt_types.h>
 
 #ifndef __ASSEMBLY__
+#include <linux/bug.h>
 #include <linux/types.h>
 #include <linux/cpumask.h>
 
@@ -230,9 +231,9 @@ static inline unsigned long long paravirt_sched_clock(void)
 	return PVOP_CALL0(unsigned long long, pv_time_ops.sched_clock);
 }
 
-struct jump_label_key;
-extern struct jump_label_key paravirt_steal_enabled;
-extern struct jump_label_key paravirt_steal_rq_enabled;
+struct static_key;
+extern struct static_key paravirt_steal_enabled;
+extern struct static_key paravirt_steal_rq_enabled;
 
 static inline u64 paravirt_steal_clock(int cpu)
 {
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 461ce432b1c..e8fb2c7a5f4 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -188,8 +188,6 @@ extern u32 get_ibs_caps(void);
 #ifdef CONFIG_PERF_EVENTS
 extern void perf_events_lapic_init(void);
 
-#define PERF_EVENT_INDEX_OFFSET			0
-
 /*
  * Abuse bit 3 of the cpu eflags register to indicate proper PEBS IP fixups.
  * This flag is otherwise unused and ABI specified to be 0, so nobody should
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 58545c97d07..5533b30cac0 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -162,6 +162,7 @@ extern void early_cpu_init(void);
 extern void identify_boot_cpu(void);
 extern void identify_secondary_cpu(struct cpuinfo_x86 *);
 extern void print_cpu_info(struct cpuinfo_x86 *);
+void print_cpu_msr(struct cpuinfo_x86 *);
 extern void init_scattered_cpuid_features(struct cpuinfo_x86 *c);
 extern unsigned int init_intel_cacheinfo(struct cpuinfo_x86 *c);
 extern unsigned short num_cache_leaves;
@@ -474,61 +475,6 @@ struct thread_struct {
 	unsigned		io_bitmap_max;
 };
 
-static inline unsigned long native_get_debugreg(int regno)
-{
-	unsigned long val = 0;	/* Damn you, gcc! */
-
-	switch (regno) {
-	case 0:
-		asm("mov %%db0, %0" :"=r" (val));
-		break;
-	case 1:
-		asm("mov %%db1, %0" :"=r" (val));
-		break;
-	case 2:
-		asm("mov %%db2, %0" :"=r" (val));
-		break;
-	case 3:
-		asm("mov %%db3, %0" :"=r" (val));
-		break;
-	case 6:
-		asm("mov %%db6, %0" :"=r" (val));
-		break;
-	case 7:
-		asm("mov %%db7, %0" :"=r" (val));
-		break;
-	default:
-		BUG();
-	}
-	return val;
-}
-
-static inline void native_set_debugreg(int regno, unsigned long value)
-{
-	switch (regno) {
-	case 0:
-		asm("mov %0, %%db0"	::"r" (value));
-		break;
-	case 1:
-		asm("mov %0, %%db1"	::"r" (value));
-		break;
-	case 2:
-		asm("mov %0, %%db2"	::"r" (value));
-		break;
-	case 3:
-		asm("mov %0, %%db3"	::"r" (value));
-		break;
-	case 6:
-		asm("mov %0, %%db6"	::"r" (value));
-		break;
-	case 7:
-		asm("mov %0, %%db7"	::"r" (value));
-		break;
-	default:
-		BUG();
-	}
-}
-
 /*
  * Set IOPL bits in EFLAGS from given mask
  */
@@ -574,14 +520,6 @@ static inline void native_swapgs(void)
 #define __cpuid			native_cpuid
 #define paravirt_enabled()	0
 
-/*
- * These special macros can be used to get or set a debugging register
- */
-#define get_debugreg(var, register)				\
-	(var) = native_get_debugreg(register)
-#define set_debugreg(value, register)				\
-	native_set_debugreg(register, value)
-
 static inline void load_sp0(struct tss_struct *tss,
 			    struct thread_struct *thread)
 {
diff --git a/arch/x86/include/asm/prom.h b/arch/x86/include/asm/prom.h
index 644dd885f05..60bef663609 100644
--- a/arch/x86/include/asm/prom.h
+++ b/arch/x86/include/asm/prom.h
@@ -21,7 +21,6 @@
 #include <asm/irq.h>
 #include <linux/atomic.h>
 #include <asm/setup.h>
-#include <asm/irq_controller.h>
 
 #ifdef CONFIG_OF
 extern int of_ioapic;
@@ -43,15 +42,6 @@ extern char cmd_line[COMMAND_LINE_SIZE];
 #define pci_address_to_pio pci_address_to_pio
 unsigned long pci_address_to_pio(phys_addr_t addr);
 
-/**
- * irq_dispose_mapping - Unmap an interrupt
- * @virq: linux virq number of the interrupt to unmap
- *
- * FIXME: We really should implement proper virq handling like power,
- * but that's going to be major surgery.
- */
-static inline void irq_dispose_mapping(unsigned int virq) { }
-
 #define HAVE_ARCH_DEVTREE_FIXUPS
 
 #endif /* __ASSEMBLY__ */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index a82c2bf504b..76bfa2cf301 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -88,14 +88,14 @@ static inline int __ticket_spin_is_locked(arch_spinlock_t *lock)
 {
 	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
 
-	return !!(tmp.tail ^ tmp.head);
+	return tmp.tail != tmp.head;
 }
 
 static inline int __ticket_spin_is_contended(arch_spinlock_t *lock)
 {
 	struct __raw_tickets tmp = ACCESS_ONCE(lock->tickets);
 
-	return ((tmp.tail - tmp.head) & TICKET_MASK) > 1;
+	return (__ticket_t)(tmp.tail - tmp.head) > 1;
 }
 
 #ifndef CONFIG_PARAVIRT_SPINLOCKS
diff --git a/arch/x86/include/asm/spinlock_types.h b/arch/x86/include/asm/spinlock_types.h
index 8ebd5df7451..ad0ad07fc00 100644
--- a/arch/x86/include/asm/spinlock_types.h
+++ b/arch/x86/include/asm/spinlock_types.h
@@ -16,7 +16,6 @@ typedef u32 __ticketpair_t;
 #endif
 
 #define TICKET_SHIFT	(sizeof(__ticket_t) * 8)
-#define TICKET_MASK	((__ticket_t)((1 << TICKET_SHIFT) - 1))
 
 typedef struct arch_spinlock {
 	union {
diff --git a/arch/x86/include/asm/timer.h b/arch/x86/include/asm/timer.h
index 431793e5d48..34baa0eb5d0 100644
--- a/arch/x86/include/asm/timer.h
+++ b/arch/x86/include/asm/timer.h
@@ -57,14 +57,10 @@ DECLARE_PER_CPU(unsigned long long, cyc2ns_offset);
 
 static inline unsigned long long __cycles_2_ns(unsigned long long cyc)
 {
-	unsigned long long quot;
-	unsigned long long rem;
 	int cpu = smp_processor_id();
 	unsigned long long ns = per_cpu(cyc2ns_offset, cpu);
-	quot = (cyc >> CYC2NS_SCALE_FACTOR);
-	rem = cyc & ((1ULL << CYC2NS_SCALE_FACTOR) - 1);
-	ns += quot * per_cpu(cyc2ns, cpu) +
-		((rem * per_cpu(cyc2ns, cpu)) >> CYC2NS_SCALE_FACTOR);
+	ns += mult_frac(cyc, per_cpu(cyc2ns, cpu),
+			(1UL << CYC2NS_SCALE_FACTOR));
 	return ns;
 }
 
diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h
index a1f2db5f117..cbf0c9d50b9 100644
--- a/arch/x86/include/asm/xen/interface.h
+++ b/arch/x86/include/asm/xen/interface.h
@@ -56,6 +56,7 @@ DEFINE_GUEST_HANDLE(int);
 DEFINE_GUEST_HANDLE(long);
 DEFINE_GUEST_HANDLE(void);
 DEFINE_GUEST_HANDLE(uint64_t);
+DEFINE_GUEST_HANDLE(uint32_t);
 #endif
 
 #ifndef HYPERVISOR_VIRT_START