Merge branch 'x86/unify-cpu-detect' into x86-v28-for-linus-phase4-D

Conflicts:
	arch/x86/kernel/cpu/common.c
	arch/x86/kernel/signal_64.c
	include/asm-x86/cpufeature.h

14 files changed, 467 insertions, 61 deletions

diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
index 4761c461d23..dc604985f2a 100644
--- a/include/asm-x86/bugs.h
+++ b/include/asm-x86/bugs.h
@@ -2,6 +2,11 @@
 #define ASM_X86__BUGS_H
 
 extern void check_bugs(void);
+
+#if defined(CONFIG_CPU_SUP_INTEL) && defined(CONFIG_X86_32)
 int ppro_with_ram_bug(void);
+#else
+static inline int ppro_with_ram_bug(void) { return 0; }
+#endif
 
 #endif /* ASM_X86__BUGS_H */
diff --git a/include/asm-x86/cpufeature.h b/include/asm-x86/cpufeature.h
index 065c6a86ed8..adfeae6586e 100644
--- a/include/asm-x86/cpufeature.h
+++ b/include/asm-x86/cpufeature.h
@@ -6,7 +6,13 @@
 
 #include <asm/required-features.h>
 
-#define NCAPINTS	8	/* N 32-bit words worth of info */
+#define NCAPINTS	9	/* N 32-bit words worth of info */
+
+/*
+ * Note: If the comment begins with a quoted string, that string is used
+ * in /proc/cpuinfo instead of the macro name.  If the string is "",
+ * this feature bit is not displayed in /proc/cpuinfo at all.
+ */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (edx), word 0 */
 #define X86_FEATURE_FPU		(0*32+ 0) /* Onboard FPU */
@@ -14,7 +20,7 @@
 #define X86_FEATURE_DE		(0*32+ 2) /* Debugging Extensions */
 #define X86_FEATURE_PSE		(0*32+ 3) /* Page Size Extensions */
 #define X86_FEATURE_TSC		(0*32+ 4) /* Time Stamp Counter */
-#define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers, RDMSR, WRMSR */
+#define X86_FEATURE_MSR		(0*32+ 5) /* Model-Specific Registers */
 #define X86_FEATURE_PAE		(0*32+ 6) /* Physical Address Extensions */
 #define X86_FEATURE_MCE		(0*32+ 7) /* Machine Check Architecture */
 #define X86_FEATURE_CX8		(0*32+ 8) /* CMPXCHG8 instruction */
@@ -23,22 +29,23 @@
 #define X86_FEATURE_MTRR	(0*32+12) /* Memory Type Range Registers */
 #define X86_FEATURE_PGE		(0*32+13) /* Page Global Enable */
 #define X86_FEATURE_MCA		(0*32+14) /* Machine Check Architecture */
-#define X86_FEATURE_CMOV	(0*32+15) /* CMOV instruction (FCMOVCC and FCOMI too if FPU present) */
+#define X86_FEATURE_CMOV	(0*32+15) /* CMOV instructions */
+					  /* (plus FCMOVcc, FCOMI with FPU) */
 #define X86_FEATURE_PAT		(0*32+16) /* Page Attribute Table */
 #define X86_FEATURE_PSE36	(0*32+17) /* 36-bit PSEs */
 #define X86_FEATURE_PN		(0*32+18) /* Processor serial number */
-#define X86_FEATURE_CLFLSH	(0*32+19) /* Supports the CLFLUSH instruction */
-#define X86_FEATURE_DS		(0*32+21) /* Debug Store */
+#define X86_FEATURE_CLFLSH	(0*32+19) /* "clflush" CLFLUSH instruction */
+#define X86_FEATURE_DS		(0*32+21) /* "dts" Debug Store */
 #define X86_FEATURE_ACPI	(0*32+22) /* ACPI via MSR */
 #define X86_FEATURE_MMX		(0*32+23) /* Multimedia Extensions */
-#define X86_FEATURE_FXSR	(0*32+24) /* FXSAVE and FXRSTOR instructions (fast save and restore */
-					  /* of FPU context), and CR4.OSFXSR available */
-#define X86_FEATURE_XMM		(0*32+25) /* Streaming SIMD Extensions */
-#define X86_FEATURE_XMM2	(0*32+26) /* Streaming SIMD Extensions-2 */
-#define X86_FEATURE_SELFSNOOP	(0*32+27) /* CPU self snoop */
+#define X86_FEATURE_FXSR	(0*32+24) /* FXSAVE/FXRSTOR, CR4.OSFXSR */
+#define X86_FEATURE_XMM		(0*32+25) /* "sse" */
+#define X86_FEATURE_XMM2	(0*32+26) /* "sse2" */
+#define X86_FEATURE_SELFSNOOP	(0*32+27) /* "ss" CPU self snoop */
 #define X86_FEATURE_HT		(0*32+28) /* Hyper-Threading */
-#define X86_FEATURE_ACC		(0*32+29) /* Automatic clock control */
+#define X86_FEATURE_ACC		(0*32+29) /* "tm" Automatic clock control */
 #define X86_FEATURE_IA64	(0*32+30) /* IA-64 processor */
+#define X86_FEATURE_PBE		(0*32+31) /* Pending Break Enable */
 
 /* AMD-defined CPU features, CPUID level 0x80000001, word 1 */
 /* Don't duplicate feature flags which are redundant with Intel! */
@@ -46,7 +53,8 @@
 #define X86_FEATURE_MP		(1*32+19) /* MP Capable. */
 #define X86_FEATURE_NX		(1*32+20) /* Execute Disable */
 #define X86_FEATURE_MMXEXT	(1*32+22) /* AMD MMX extensions */
-#define X86_FEATURE_GBPAGES	(1*32+26) /* GB pages */
+#define X86_FEATURE_FXSR_OPT	(1*32+25) /* FXSAVE/FXRSTOR optimizations */
+#define X86_FEATURE_GBPAGES	(1*32+26) /* "pdpe1gb" GB pages */
 #define X86_FEATURE_RDTSCP	(1*32+27) /* RDTSCP */
 #define X86_FEATURE_LM		(1*32+29) /* Long Mode (x86-64) */
 #define X86_FEATURE_3DNOWEXT	(1*32+30) /* AMD 3DNow! extensions */
@@ -64,54 +72,79 @@
 #define X86_FEATURE_CYRIX_ARR	(3*32+ 2) /* Cyrix ARRs (= MTRRs) */
 #define X86_FEATURE_CENTAUR_MCR	(3*32+ 3) /* Centaur MCRs (= MTRRs) */
 /* cpu types for specific tunings: */
-#define X86_FEATURE_K8		(3*32+ 4) /* Opteron, Athlon64 */
-#define X86_FEATURE_K7		(3*32+ 5) /* Athlon */
-#define X86_FEATURE_P3		(3*32+ 6) /* P3 */
-#define X86_FEATURE_P4		(3*32+ 7) /* P4 */
+#define X86_FEATURE_K8		(3*32+ 4) /* "" Opteron, Athlon64 */
+#define X86_FEATURE_K7		(3*32+ 5) /* "" Athlon */
+#define X86_FEATURE_P3		(3*32+ 6) /* "" P3 */
+#define X86_FEATURE_P4		(3*32+ 7) /* "" P4 */
 #define X86_FEATURE_CONSTANT_TSC (3*32+ 8) /* TSC ticks at a constant rate */
 #define X86_FEATURE_UP		(3*32+ 9) /* smp kernel running on up */
-#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* FXSAVE leaks FOP/FIP/FOP */
+#define X86_FEATURE_FXSAVE_LEAK (3*32+10) /* "" FXSAVE leaks FOP/FIP/FOP */
 #define X86_FEATURE_ARCH_PERFMON (3*32+11) /* Intel Architectural PerfMon */
+#define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_PEBS	(3*32+12) /* Precise-Event Based Sampling */
 #define X86_FEATURE_BTS		(3*32+13) /* Branch Trace Store */
-#define X86_FEATURE_SYSCALL32	(3*32+14) /* syscall in ia32 userspace */
-#define X86_FEATURE_SYSENTER32	(3*32+15) /* sysenter in ia32 userspace */
-#define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well on this CPU */
-#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* Mfence synchronizes RDTSC */
-#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* Lfence synchronizes RDTSC */
-#define X86_FEATURE_11AP	(3*32+19) /* Bad local APIC aka 11AP */
+#define X86_FEATURE_SYSCALL32	(3*32+14) /* "" syscall in ia32 userspace */
+#define X86_FEATURE_SYSENTER32	(3*32+15) /* "" sysenter in ia32 userspace */
+#define X86_FEATURE_REP_GOOD	(3*32+16) /* rep microcode works well */
+#define X86_FEATURE_MFENCE_RDTSC (3*32+17) /* "" Mfence synchronizes RDTSC */
+#define X86_FEATURE_LFENCE_RDTSC (3*32+18) /* "" Lfence synchronizes RDTSC */
+#define X86_FEATURE_11AP	(3*32+19) /* "" Bad local APIC aka 11AP */
 #define X86_FEATURE_NOPL	(3*32+20) /* The NOPL (0F 1F) instructions */
 #define X86_FEATURE_AMDC1E	(3*32+21) /* AMD C1E detected */
+#define X86_FEATURE_XTOPOLOGY	(3*32+21) /* cpu topology enum extensions */
 
 /* Intel-defined CPU features, CPUID level 0x00000001 (ecx), word 4 */
-#define X86_FEATURE_XMM3	(4*32+ 0) /* Streaming SIMD Extensions-3 */
-#define X86_FEATURE_MWAIT	(4*32+ 3) /* Monitor/Mwait support */
-#define X86_FEATURE_DSCPL	(4*32+ 4) /* CPL Qualified Debug Store */
+#define X86_FEATURE_XMM3	(4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_PCLMULQDQ	(4*32+ 1) /* PCLMULQDQ instruction */
+#define X86_FEATURE_DTES64	(4*32+ 2) /* 64-bit Debug Store */
+#define X86_FEATURE_MWAIT	(4*32+ 3) /* "monitor" Monitor/Mwait support */
+#define X86_FEATURE_DSCPL	(4*32+ 4) /* "ds_cpl" CPL Qual. Debug Store */
+#define X86_FEATURE_VMX		(4*32+ 5) /* Hardware virtualization */
+#define X86_FEATURE_SMX		(4*32+ 6) /* Safer mode */
 #define X86_FEATURE_EST		(4*32+ 7) /* Enhanced SpeedStep */
 #define X86_FEATURE_TM2		(4*32+ 8) /* Thermal Monitor 2 */
+#define X86_FEATURE_SSSE3	(4*32+ 9) /* Supplemental SSE-3 */
 #define X86_FEATURE_CID		(4*32+10) /* Context ID */
+#define X86_FEATURE_FMA		(4*32+12) /* Fused multiply-add */
 #define X86_FEATURE_CX16	(4*32+13) /* CMPXCHG16B */
 #define X86_FEATURE_XTPR	(4*32+14) /* Send Task Priority Messages */
+#define X86_FEATURE_PDCM	(4*32+15) /* Performance Capabilities */
 #define X86_FEATURE_DCA		(4*32+18) /* Direct Cache Access */
+#define X86_FEATURE_XMM4_1	(4*32+19) /* "sse4_1" SSE-4.1 */
+#define X86_FEATURE_XMM4_2	(4*32+20) /* "sse4_2" SSE-4.2 */
 #define X86_FEATURE_X2APIC	(4*32+21) /* x2APIC */
-#define X86_FEATURE_XMM4_2	(4*32+20) /* Streaming SIMD Extensions-4.2 */
+#define X86_FEATURE_AES		(4*32+25) /* AES instructions */
+#define X86_FEATURE_XSAVE	(4*32+26) /* XSAVE/XRSTOR/XSETBV/XGETBV */
+#define X86_FEATURE_OSXSAVE	(4*32+27) /* "" XSAVE enabled in the OS */
+#define X86_FEATURE_AVX		(4*32+28) /* Advanced Vector Extensions */
 
 /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */
-#define X86_FEATURE_XSTORE	(5*32+ 2) /* on-CPU RNG present (xstore insn) */
-#define X86_FEATURE_XSTORE_EN	(5*32+ 3) /* on-CPU RNG enabled */
-#define X86_FEATURE_XCRYPT	(5*32+ 6) /* on-CPU crypto (xcrypt insn) */
-#define X86_FEATURE_XCRYPT_EN	(5*32+ 7) /* on-CPU crypto enabled */
+#define X86_FEATURE_XSTORE	(5*32+ 2) /* "rng" RNG present (xstore) */
+#define X86_FEATURE_XSTORE_EN	(5*32+ 3) /* "rng_en" RNG enabled */
+#define X86_FEATURE_XCRYPT	(5*32+ 6) /* "ace" on-CPU crypto (xcrypt) */
+#define X86_FEATURE_XCRYPT_EN	(5*32+ 7) /* "ace_en" on-CPU crypto enabled */
 #define X86_FEATURE_ACE2	(5*32+ 8) /* Advanced Cryptography Engine v2 */
 #define X86_FEATURE_ACE2_EN	(5*32+ 9) /* ACE v2 enabled */
-#define X86_FEATURE_PHE		(5*32+ 10) /* PadLock Hash Engine */
-#define X86_FEATURE_PHE_EN	(5*32+ 11) /* PHE enabled */
-#define X86_FEATURE_PMM		(5*32+ 12) /* PadLock Montgomery Multiplier */
-#define X86_FEATURE_PMM_EN	(5*32+ 13) /* PMM enabled */
+#define X86_FEATURE_PHE		(5*32+10) /* PadLock Hash Engine */
+#define X86_FEATURE_PHE_EN	(5*32+11) /* PHE enabled */
+#define X86_FEATURE_PMM		(5*32+12) /* PadLock Montgomery Multiplier */
+#define X86_FEATURE_PMM_EN	(5*32+13) /* PMM enabled */
 
 /* More extended AMD flags: CPUID level 0x80000001, ecx, word 6 */
 #define X86_FEATURE_LAHF_LM	(6*32+ 0) /* LAHF/SAHF in long mode */
 #define X86_FEATURE_CMP_LEGACY	(6*32+ 1) /* If yes HyperThreading not valid */
-#define X86_FEATURE_IBS		(6*32+ 10) /* Instruction Based Sampling */
+#define X86_FEATURE_SVM		(6*32+ 2) /* Secure virtual machine */
+#define X86_FEATURE_EXTAPIC	(6*32+ 3) /* Extended APIC space */
+#define X86_FEATURE_CR8_LEGACY	(6*32+ 4) /* CR8 in 32-bit mode */
+#define X86_FEATURE_ABM		(6*32+ 5) /* Advanced bit manipulation */
+#define X86_FEATURE_SSE4A	(6*32+ 6) /* SSE-4A */
+#define X86_FEATURE_MISALIGNSSE (6*32+ 7) /* Misaligned SSE mode */
+#define X86_FEATURE_3DNOWPREFETCH (6*32+ 8) /* 3DNow prefetch instructions */
+#define X86_FEATURE_OSVW	(6*32+ 9) /* OS Visible Workaround */
+#define X86_FEATURE_IBS		(6*32+10) /* Instruction Based Sampling */
+#define X86_FEATURE_SSE5	(6*32+11) /* SSE-5 */
+#define X86_FEATURE_SKINIT	(6*32+12) /* SKINIT/STGI instructions */
+#define X86_FEATURE_WDT		(6*32+13) /* Watchdog timer */
 
 /*
  * Auxiliary flags: Linux defined - For features scattered in various
@@ -119,6 +152,13 @@
  */
 #define X86_FEATURE_IDA		(7*32+ 0) /* Intel Dynamic Acceleration */
 
+/* Virtualization flags: Linux defined */
+#define X86_FEATURE_TPR_SHADOW  (8*32+ 0) /* Intel TPR Shadow */
+#define X86_FEATURE_VNMI        (8*32+ 1) /* Intel Virtual NMI */
+#define X86_FEATURE_FLEXPRIORITY (8*32+ 2) /* Intel FlexPriority */
+#define X86_FEATURE_EPT         (8*32+ 3) /* Intel Extended Page Table */
+#define X86_FEATURE_VPID        (8*32+ 4) /* Intel Virtual Processor ID */
+
 #if defined(__KERNEL__) && !defined(__ASSEMBLY__)
 
 #include <linux/bitops.h>
@@ -152,7 +192,7 @@ extern const char * const x86_power_flags[32];
 } while (0)
 #define setup_force_cpu_cap(bit) do { \
 	set_cpu_cap(&boot_cpu_data, bit);	\
-	clear_bit(bit, (unsigned long *)cleared_cpu_caps); 	\
+	clear_bit(bit, (unsigned long *)cleared_cpu_caps);	\
 } while (0)
 
 #define cpu_has_fpu		boot_cpu_has(X86_FEATURE_FPU)
@@ -193,8 +233,10 @@ extern const char * const x86_power_flags[32];
 #define cpu_has_gbpages		boot_cpu_has(X86_FEATURE_GBPAGES)
 #define cpu_has_arch_perfmon	boot_cpu_has(X86_FEATURE_ARCH_PERFMON)
 #define cpu_has_pat		boot_cpu_has(X86_FEATURE_PAT)
-#define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
+#define cpu_has_xmm4_1		boot_cpu_has(X86_FEATURE_XMM4_1)
 #define cpu_has_xmm4_2		boot_cpu_has(X86_FEATURE_XMM4_2)
+#define cpu_has_x2apic		boot_cpu_has(X86_FEATURE_X2APIC)
+#define cpu_has_xsave		boot_cpu_has(X86_FEATURE_XSAVE)
 
 #if defined(CONFIG_X86_INVLPG) || defined(CONFIG_X86_64)
 # define cpu_has_invlpg		1
diff --git a/include/asm-x86/e820.h b/include/asm-x86/e820.h
index f52daf176bc..5abbdec06bd 100644
--- a/include/asm-x86/e820.h
+++ b/include/asm-x86/e820.h
@@ -43,6 +43,7 @@
 #define E820_RESERVED	2
 #define E820_ACPI	3
 #define E820_NVS	4
+#define E820_UNUSABLE	5
 
 /* reserved RAM used by kernel itself */
 #define E820_RESERVED_KERN        128
@@ -121,6 +122,7 @@ extern void e820_register_active_regions(int nid, unsigned long start_pfn,
 extern u64 e820_hole_size(u64 start, u64 end);
 extern void finish_e820_parsing(void);
 extern void e820_reserve_resources(void);
+extern void e820_reserve_resources_late(void);
 extern void setup_memory_map(void);
 extern char *default_machine_specific_memory_setup(void);
 extern char *machine_specific_memory_setup(void);
diff --git a/include/asm-x86/i387.h b/include/asm-x86/i387.h
index 1ecdc3ed96e..9ba862a4eac 100644
--- a/include/asm-x86/i387.h
+++ b/include/asm-x86/i387.h
@@ -19,7 +19,9 @@
 #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);
 extern void mxcsr_feature_mask_init(void);
 extern int init_fpu(struct task_struct *child);
@@ -31,12 +33,18 @@ extern user_regset_active_fn fpregs_active, xfpregs_active;
 extern user_regset_get_fn fpregs_get, xfpregs_get, fpregs_soft_get;
 extern user_regset_set_fn fpregs_set, xfpregs_set, fpregs_soft_set;
 
+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;
-extern int save_i387_ia32(struct _fpstate_ia32 __user *buf);
-extern int restore_i387_ia32(struct _fpstate_ia32 __user *buf);
+struct _xstate_ia32;
+extern int save_i387_xstate_ia32(void __user *buf);
+extern int restore_i387_xstate_ia32(void __user *buf);
 #endif
 
+#define X87_FSW_ES (1 << 7)	/* Exception Summary */
+
 #ifdef CONFIG_X86_64
 
 /* Ignore delayed exceptions from user space */
@@ -47,7 +55,7 @@ static inline void tolerant_fwait(void)
 		     _ASM_EXTABLE(1b, 2b));
 }
 
-static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
+static inline int fxrstor_checking(struct i387_fxsave_struct *fx)
 {
 	int err;
 
@@ -67,15 +75,31 @@ static inline int restore_fpu_checking(struct i387_fxsave_struct *fx)
 	return err;
 }
 
-#define X87_FSW_ES (1 << 7)	/* Exception Summary */
+static inline int restore_fpu_checking(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE)
+		return xrstor_checking(&tsk->thread.xstate->xsave);
+	else
+		return fxrstor_checking(&tsk->thread.xstate->fxsave);
+}
 
 /* AMD CPUs don't save/restore FDP/FIP/FOP unless an exception
    is pending. Clear the x87 state here by setting it to fixed
    values. The kernel data segment can be sometimes 0 and sometimes
    new user value. Both should be ok.
    Use the PDA as safe address because it should be already in L1. */
-static inline void clear_fpu_state(struct i387_fxsave_struct *fx)
+static inline void clear_fpu_state(struct task_struct *tsk)
 {
+	struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
+	struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+
+	/*
+	 * xsave header may indicate the init state of the FP.
+	 */
+	if ((task_thread_info(tsk)->status & TS_XSAVE) &&
+	    !(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
+		return;
+
 	if (unlikely(fx->swd & X87_FSW_ES))
 		asm volatile("fnclex");
 	alternative_input(ASM_NOP8 ASM_NOP2,
@@ -84,7 +108,7 @@ static inline void clear_fpu_state(struct i387_fxsave_struct *fx)
 			  X86_FEATURE_FXSAVE_LEAK);
 }
 
-static inline int save_i387_checking(struct i387_fxsave_struct __user *fx)
+static inline int fxsave_user(struct i387_fxsave_struct __user *fx)
 {
 	int err;
 
@@ -108,7 +132,7 @@ static inline int save_i387_checking(struct i387_fxsave_struct __user *fx)
 	return err;
 }
 
-static inline void __save_init_fpu(struct task_struct *tsk)
+static inline void fxsave(struct task_struct *tsk)
 {
 	/* Using "rex64; fxsave %0" is broken because, if the memory operand
 	   uses any extended registers for addressing, a second REX prefix
@@ -133,7 +157,16 @@ static inline void __save_init_fpu(struct task_struct *tsk)
 			     : "=m" (tsk->thread.xstate->fxsave)
 			     : "cdaSDb" (&tsk->thread.xstate->fxsave));
 #endif
-	clear_fpu_state(&tsk->thread.xstate->fxsave);
+}
+
+static inline void __save_init_fpu(struct task_struct *tsk)
+{
+	if (task_thread_info(tsk)->status & TS_XSAVE)
+		xsave(tsk);
+	else
+		fxsave(tsk);
+
+	clear_fpu_state(tsk);
 	task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
@@ -148,6 +181,10 @@ static inline void tolerant_fwait(void)
 
 static inline void restore_fpu(struct task_struct *tsk)
 {
+	if (task_thread_info(tsk)->status & TS_XSAVE) {
+		xrstor_checking(&tsk->thread.xstate->xsave);
+		return;
+	}
 	/*
 	 * The "nop" is needed to make the instructions the same
 	 * length.
@@ -173,6 +210,27 @@ static inline void restore_fpu(struct task_struct *tsk)
  */
 static inline void __save_init_fpu(struct task_struct *tsk)
 {
+	if (task_thread_info(tsk)->status & TS_XSAVE) {
+		struct xsave_struct *xstate = &tsk->thread.xstate->xsave;
+		struct i387_fxsave_struct *fx = &tsk->thread.xstate->fxsave;
+
+		xsave(tsk);
+
+		/*
+		 * xsave header may indicate the init state of the FP.
+		 */
+		if (!(xstate->xsave_hdr.xstate_bv & XSTATE_FP))
+			goto end;
+
+		if (unlikely(fx->swd & X87_FSW_ES))
+			asm volatile("fnclex");
+
+		/*
+		 * we can do a simple return here or be paranoid :)
+		 */
+		goto clear_state;
+	}
+
 	/* Use more nops than strictly needed in case the compiler
 	   varies code */
 	alternative_input(
@@ -182,6 +240,7 @@ static inline void __save_init_fpu(struct task_struct *tsk)
 		X86_FEATURE_FXSR,
 		[fx] "m" (tsk->thread.xstate->fxsave),
 		[fsw] "m" (tsk->thread.xstate->fxsave.swd) : "memory");
+clear_state:
 	/* 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. safe_address is a random variable that should be in L1 */
@@ -191,16 +250,17 @@ static inline void __save_init_fpu(struct task_struct *tsk)
 		"fildl %[addr]", 	/* set F?P to defined value */
 		X86_FEATURE_FXSAVE_LEAK,
 		[addr] "m" (safe_address));
+end:
 	task_thread_info(tsk)->status &= ~TS_USEDFPU;
 }
 
+#endif	/* CONFIG_X86_64 */
+
 /*
  * Signal frame handlers...
  */
-extern int save_i387(struct _fpstate __user *buf);
-extern int restore_i387(struct _fpstate __user *buf);
-
-#endif	/* CONFIG_X86_64 */
+extern int save_i387_xstate(void __user *buf);
+extern int restore_i387_xstate(void __user *buf);
 
 static inline void __unlazy_fpu(struct task_struct *tsk)
 {
diff --git a/include/asm-x86/msr-index.h b/include/asm-x86/msr-index.h
index 3052f058ab0..0bb43301a20 100644
--- a/include/asm-x86/msr-index.h
+++ b/include/asm-x86/msr-index.h
@@ -176,6 +176,7 @@
 #define MSR_IA32_TSC			0x00000010
 #define MSR_IA32_PLATFORM_ID		0x00000017
 #define MSR_IA32_EBL_CR_POWERON		0x0000002a
+#define MSR_IA32_FEATURE_CONTROL        0x0000003a
 
 #define MSR_IA32_APICBASE		0x0000001b
 #define MSR_IA32_APICBASE_BSP		(1<<8)
@@ -310,4 +311,19 @@
 /* Geode defined MSRs */
 #define MSR_GEODE_BUSCONT_CONF0		0x00001900
 
+/* Intel VT MSRs */
+#define MSR_IA32_VMX_BASIC              0x00000480
+#define MSR_IA32_VMX_PINBASED_CTLS      0x00000481
+#define MSR_IA32_VMX_PROCBASED_CTLS     0x00000482
+#define MSR_IA32_VMX_EXIT_CTLS          0x00000483
+#define MSR_IA32_VMX_ENTRY_CTLS         0x00000484
+#define MSR_IA32_VMX_MISC               0x00000485
+#define MSR_IA32_VMX_CR0_FIXED0         0x00000486
+#define MSR_IA32_VMX_CR0_FIXED1         0x00000487
+#define MSR_IA32_VMX_CR4_FIXED0         0x00000488
+#define MSR_IA32_VMX_CR4_FIXED1         0x00000489
+#define MSR_IA32_VMX_VMCS_ENUM          0x0000048a
+#define MSR_IA32_VMX_PROCBASED_CTLS2    0x0000048b
+#define MSR_IA32_VMX_EPT_VPID_CAP       0x0000048c
+
 #endif /* ASM_X86__MSR_INDEX_H */
diff --git a/include/asm-x86/processor-cyrix.h b/include/asm-x86/processor-cyrix.h
index 97568ada1f9..1198f2a0e42 100644
--- a/include/asm-x86/processor-cyrix.h
+++ b/include/asm-x86/processor-cyrix.h
@@ -28,3 +28,11 @@ static inline void setCx86(u8 reg, u8 data)
 	outb(reg, 0x22);
 	outb(data, 0x23);
 }
+
+#define getCx86_old(reg) ({ outb((reg), 0x22); inb(0x23); })
+
+#define setCx86_old(reg, data) do { \
+	outb((reg), 0x22); \
+	outb((data), 0x23); \
+} while (0)
+
diff --git a/include/asm-x86/processor-flags.h b/include/asm-x86/processor-flags.h
index 5dd79774f69..dc5f0712f9f 100644
--- a/include/asm-x86/processor-flags.h
+++ b/include/asm-x86/processor-flags.h
@@ -59,6 +59,7 @@
 #define X86_CR4_OSFXSR	0x00000200 /* enable fast FPU save and restore */
 #define X86_CR4_OSXMMEXCPT 0x00000400 /* enable unmasked SSE exceptions */
 #define X86_CR4_VMXE	0x00002000 /* enable VMX virtualization */
+#define X86_CR4_OSXSAVE 0x00040000 /* enable xsave and xrestore */
 
 /*
  * x86-64 Task Priority Register, CR8
diff --git a/include/asm-x86/processor.h b/include/asm-x86/processor.h
index 5eaf9bf0a62..c7d35464a4b 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -76,11 +76,11 @@ struct cpuinfo_x86 {
 	int			 x86_tlbsize;
 	__u8			x86_virt_bits;
 	__u8			x86_phys_bits;
+#endif
 	/* CPUID returned core id bits: */
 	__u8			x86_coreid_bits;
 	/* Max extended CPUID function supported: */
 	__u32			extended_cpuid_level;
-#endif
 	/* Maximum supported CPUID level, -1=no CPUID: */
 	int			cpuid_level;
 	__u32			x86_capability[NCAPINTS];
@@ -166,11 +166,8 @@ 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;
 
-#if defined(CONFIG_X86_HT) || defined(CONFIG_X86_64)
+extern void detect_extended_topology(struct cpuinfo_x86 *c);
 extern void detect_ht(struct cpuinfo_x86 *c);
-#else
-static inline void detect_ht(struct cpuinfo_x86 *c) {}
-#endif
 
 static inline void native_cpuid(unsigned int *eax, unsigned int *ebx,
 				unsigned int *ecx, unsigned int *edx)
@@ -327,7 +324,12 @@ struct i387_fxsave_struct {
 	/* 16*16 bytes for each XMM-reg = 256 bytes:			*/
 	u32			xmm_space[64];
 
-	u32			padding[24];
+	u32			padding[12];
+
+	union {
+		u32		padding1[12];
+		u32		sw_reserved[12];
+	};
 
 } __attribute__((aligned(16)));
 
@@ -351,10 +353,23 @@ struct i387_soft_struct {
 	u32			entry_eip;
 };
 
+struct xsave_hdr_struct {
+	u64 xstate_bv;
+	u64 reserved1[2];
+	u64 reserved2[5];
+} __attribute__((packed));
+
+struct xsave_struct {
+	struct i387_fxsave_struct i387;
+	struct xsave_hdr_struct xsave_hdr;
+	/* new processor state extensions will go here */
+} __attribute__ ((packed, aligned (64)));
+
 union thread_xstate {
 	struct i387_fsave_struct	fsave;
 	struct i387_fxsave_struct	fxsave;
 	struct i387_soft_struct		soft;
+	struct xsave_struct		xsave;
 };
 
 #ifdef CONFIG_X86_64
diff --git a/include/asm-x86/sigcontext.h b/include/asm-x86/sigcontext.h
index 24879c85b29..ee813f4fe5d 100644
--- a/include/asm-x86/sigcontext.h
+++ b/include/asm-x86/sigcontext.h
@@ -4,6 +4,40 @@
 #include <linux/compiler.h>
 #include <asm/types.h>
 
+#define FP_XSTATE_MAGIC1	0x46505853U
+#define FP_XSTATE_MAGIC2	0x46505845U
+#define FP_XSTATE_MAGIC2_SIZE	sizeof(FP_XSTATE_MAGIC2)
+
+/*
+ * bytes 464..511 in the current 512byte layout of fxsave/fxrstor frame
+ * are reserved for SW usage. On cpu's supporting xsave/xrstor, these bytes
+ * are used to extended the fpstate pointer in the sigcontext, which now
+ * includes the extended state information along with fpstate information.
+ *
+ * Presence of FP_XSTATE_MAGIC1 at the beginning of this SW reserved
+ * area and FP_XSTATE_MAGIC2 at the end of memory layout
+ * (extended_size - FP_XSTATE_MAGIC2_SIZE) indicates the presence of the
+ * extended state information in the memory layout pointed by the fpstate
+ * pointer in sigcontext.
+ */
+struct _fpx_sw_bytes {
+	__u32 magic1;		/* FP_XSTATE_MAGIC1 */
+	__u32 extended_size;	/* total size of the layout referred by
+				 * fpstate pointer in the sigcontext.
+				 */
+	__u64 xstate_bv;
+				/* feature bit mask (including fp/sse/extended
+				 * state) that is present in the memory
+				 * layout.
+				 */
+	__u32 xstate_size;	/* actual xsave state size, based on the
+				 * features saved in the layout.
+				 * 'extended_size' will be greater than
+				 * 'xstate_size'.
+				 */
+	__u32 padding[7];	/*  for future use. */
+};
+
 #ifdef __i386__
 /*
  * As documented in the iBCS2 standard..
@@ -53,7 +87,13 @@ struct _fpstate {
 	unsigned long	reserved;
 	struct _fpxreg	_fxsr_st[8];	/* FXSR FPU reg data is ignored */
 	struct _xmmreg	_xmm[8];
-	unsigned long	padding[56];
+	unsigned long	padding1[44];
+
+	union {
+		unsigned long	padding2[12];
+		struct _fpx_sw_bytes sw_reserved; /* represents the extended
+						   * state info */
+	};
 };
 
 #define X86_FXSR_MAGIC		0x0000
@@ -79,7 +119,15 @@ struct sigcontext {
 	unsigned long flags;
 	unsigned long sp_at_signal;
 	unsigned short ss, __ssh;
-	struct _fpstate __user *fpstate;
+
+	/*
+	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
+	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
+	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
+	 * of extended memory layout. See comments at the defintion of
+	 * (struct _fpx_sw_bytes)
+	 */
+	void __user *fpstate;		/* zero when no FPU/extended context */
 	unsigned long oldmask;
 	unsigned long cr2;
 };
@@ -130,7 +178,12 @@ struct _fpstate {
 	__u32	mxcsr_mask;
 	__u32	st_space[32];	/* 8*16 bytes for each FP-reg */
 	__u32	xmm_space[64];	/* 16*16 bytes for each XMM-reg  */
-	__u32	reserved2[24];
+	__u32	reserved2[12];
+	union {
+		__u32	reserved3[12];
+		struct _fpx_sw_bytes sw_reserved; /* represents the extended
+						   * state information */
+	};
 };
 
 #ifdef __KERNEL__
@@ -161,7 +214,15 @@ struct sigcontext {
 	unsigned long trapno;
 	unsigned long oldmask;
 	unsigned long cr2;
-	struct _fpstate __user *fpstate;	/* zero when no FPU context */
+
+	/*
+	 * fpstate is really (struct _fpstate *) or (struct _xstate *)
+	 * depending on the FP_XSTATE_MAGIC1 encoded in the SW reserved
+	 * bytes of (struct _fpstate) and FP_XSTATE_MAGIC2 present at the end
+	 * of extended memory layout. See comments at the defintion of
+	 * (struct _fpx_sw_bytes)
+	 */
+	void __user *fpstate;		/* zero when no FPU/extended context */
 	unsigned long reserved1[8];
 };
 #else /* __KERNEL__ */
@@ -202,4 +263,22 @@ struct sigcontext {
 
 #endif /* !__i386__ */
 
+struct _xsave_hdr {
+	__u64 xstate_bv;
+	__u64 reserved1[2];
+	__u64 reserved2[5];
+};
+
+/*
+ * Extended state pointed by the fpstate pointer in the sigcontext.
+ * In addition to the fpstate, information encoded in the xstate_hdr
+ * indicates the presence of other extended state information
+ * supported by the processor and OS.
+ */
+struct _xstate {
+	struct _fpstate fpstate;
+	struct _xsave_hdr xstate_hdr;
+	/* new processor state extensions go here */
+};
+
 #endif /* ASM_X86__SIGCONTEXT_H */
diff --git a/include/asm-x86/sigcontext32.h b/include/asm-x86/sigcontext32.h
index 4e2ec732dd0..8c347032c2f 100644
--- a/include/asm-x86/sigcontext32.h
+++ b/include/asm-x86/sigcontext32.h
@@ -40,7 +40,11 @@ struct _fpstate_ia32 {
 	__u32	reserved;
 	struct _fpxreg	_fxsr_st[8];
 	struct _xmmreg	_xmm[8];	/* It's actually 16 */
-	__u32	padding[56];
+	__u32	padding[44];
+	union {
+		__u32 padding2[12];
+		struct _fpx_sw_bytes sw_reserved;
+	};
 };
 
 struct sigcontext_ia32 {
diff --git a/include/asm-x86/thread_info.h b/include/asm-x86/thread_info.h
index 4db0066a3a3..3f4e52bb77f 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -241,6 +241,7 @@ static inline struct thread_info *stack_thread_info(void)
 #define TS_POLLING		0x0004	/* true if in idle loop
 					   and not sleeping */
 #define TS_RESTORE_SIGMASK	0x0008	/* restore signal mask in do_signal() */
+#define TS_XSAVE		0x0010	/* Use xsave/xrstor */
 
 #define tsk_is_polling(t) (task_thread_info(t)->status & TS_POLLING)
 
diff --git a/include/asm-x86/ucontext.h b/include/asm-x86/ucontext.h
index 9948dd32808..89eaa5456a7 100644
--- a/include/asm-x86/ucontext.h
+++ b/include/asm-x86/ucontext.h
@@ -1,6 +1,12 @@
 #ifndef ASM_X86__UCONTEXT_H
 #define ASM_X86__UCONTEXT_H
 
+#define UC_FP_XSTATE	0x1	/* indicates the presence of extended state
+				 * information in the memory layout pointed
+				 * by the fpstate pointer in the ucontext's
+				 * sigcontext struct (uc_mcontext).
+				 */
+
 struct ucontext {
 	unsigned long	  uc_flags;
 	struct ucontext  *uc_link;
diff --git a/include/asm-x86/xcr.h b/include/asm-x86/xcr.h
new file mode 100644
index 00000000000..f2cba4e79a2
--- /dev/null
+++ b/include/asm-x86/xcr.h
@@ -0,0 +1,49 @@
+/* -*- linux-c -*- ------------------------------------------------------- *
+ *
+ *   Copyright 2008 rPath, Inc. - All Rights Reserved
+ *
+ *   This file is part of the Linux kernel, and is made available under
+ *   the terms of the GNU General Public License version 2 or (at your
+ *   option) any later version; incorporated herein by reference.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * asm-x86/xcr.h
+ *
+ * Definitions for the eXtended Control Register instructions
+ */
+
+#ifndef _ASM_X86_XCR_H
+#define _ASM_X86_XCR_H
+
+#define XCR_XFEATURE_ENABLED_MASK	0x00000000
+
+#ifdef __KERNEL__
+# ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+
+static inline u64 xgetbv(u32 index)
+{
+	u32 eax, edx;
+
+	asm volatile(".byte 0x0f,0x01,0xd0" /* xgetbv */
+		     : "=a" (eax), "=d" (edx)
+		     : "c" (index));
+	return eax + ((u64)edx << 32);
+}
+
+static inline void xsetbv(u32 index, u64 value)
+{
+	u32 eax = value;
+	u32 edx = value >> 32;
+
+	asm volatile(".byte 0x0f,0x01,0xd1" /* xsetbv */
+		     : : "a" (eax), "d" (edx), "c" (index));
+}
+
+# endif /* __ASSEMBLY__ */
+#endif /* __KERNEL__ */
+
+#endif /* _ASM_X86_XCR_H */
diff --git a/include/asm-x86/xsave.h b/include/asm-x86/xsave.h
new file mode 100644
index 00000000000..08e9a1ac07a
--- /dev/null
+++ b/include/asm-x86/xsave.h
@@ -0,0 +1,118 @@
+#ifndef __ASM_X86_XSAVE_H
+#define __ASM_X86_XSAVE_H
+
+#include <linux/types.h>
+#include <asm/processor.h>
+#include <asm/i387.h>
+
+#define XSTATE_FP	0x1
+#define XSTATE_SSE	0x2
+
+#define XSTATE_FPSSE	(XSTATE_FP | XSTATE_SSE)
+
+#define FXSAVE_SIZE	512
+
+/*
+ * These are the features that the OS can handle currently.
+ */
+#define XCNTXT_MASK	(XSTATE_FP | XSTATE_SSE)
+
+#ifdef CONFIG_X86_64
+#define REX_PREFIX	"0x48, "
+#else
+#define REX_PREFIX
+#endif
+
+extern unsigned int xstate_size;
+extern u64 pcntxt_mask;
+extern struct xsave_struct *init_xstate_buf;
+
+extern void xsave_cntxt_init(void);
+extern void xsave_init(void);
+extern int init_fpu(struct task_struct *child);
+extern int check_for_xstate(struct i387_fxsave_struct __user *buf,
+			    void __user *fpstate,
+			    struct _fpx_sw_bytes *sw);
+
+static inline int xrstor_checking(struct xsave_struct *fx)
+{
+	int err;
+
+	asm volatile("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\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)
+		     : "D" (fx), "m" (*fx), "a" (-1), "d" (-1), "0" (0)
+		     : "memory");
+
+	return err;
+}
+
+static inline int xsave_user(struct xsave_struct __user *buf)
+{
+	int err;
+	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n"
+			     "2:\n"
+			     ".section .fixup,\"ax\"\n"
+			     "3:  movl $-1,%[err]\n"
+			     "    jmp  2b\n"
+			     ".previous\n"
+			     ".section __ex_table,\"a\"\n"
+			     _ASM_ALIGN "\n"
+			     _ASM_PTR "1b,3b\n"
+			     ".previous"
+			     : [err] "=r" (err)
+			     : "D" (buf), "a" (-1), "d" (-1), "0" (0)
+			     : "memory");
+	if (unlikely(err) && __clear_user(buf, xstate_size))
+		err = -EFAULT;
+	/* No need to clear here because the caller clears USED_MATH */
+	return err;
+}
+
+static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask)
+{
+	int err;
+	struct xsave_struct *xstate = ((__force struct xsave_struct *)buf);
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+
+	__asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x2f\n"
+			     "2:\n"
+			     ".section .fixup,\"ax\"\n"
+			     "3:  movl $-1,%[err]\n"
+			     "    jmp  2b\n"
+			     ".previous\n"
+			     ".section __ex_table,\"a\"\n"
+			     _ASM_ALIGN "\n"
+			     _ASM_PTR "1b,3b\n"
+			     ".previous"
+			     : [err] "=r" (err)
+			     : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0)
+			     : "memory");	/* memory required? */
+	return err;
+}
+
+static inline void xrstor_state(struct xsave_struct *fx, u64 mask)
+{
+	u32 lmask = mask;
+	u32 hmask = mask >> 32;
+
+	asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x2f\n\t"
+		     : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask)
+		     :   "memory");
+}
+
+static inline void xsave(struct task_struct *tsk)
+{
+	/* This, however, we can work around by forcing the compiler to select
+	   an addressing mode that doesn't require extended registers. */
+	__asm__ __volatile__(".byte " REX_PREFIX "0x0f,0xae,0x27"
+			     : : "D" (&(tsk->thread.xstate->xsave)),
+				 "a" (-1), "d"(-1) : "memory");
+}
+#endif