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
diff --git a/include/asm-x86/bugs.h b/include/asm-x86/bugs.h
index 4761c46..dc60498 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 065c6a8..adfeae6 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 @@
} 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 @@
#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 f52daf1..5abbdec 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 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 1ecdc3e..9ba862a 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_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 @@
_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 @@
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 @@
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 @@
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 @@
: "=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 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 __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 @@
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 @@
"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 3052f05..0bb4330 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 97568ad..1198f2a 100644
--- a/include/asm-x86/processor-cyrix.h
+++ b/include/asm-x86/processor-cyrix.h
@@ -28,3 +28,11 @@
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 5dd7977..dc5f071 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 5eaf9bf..c7d3546 100644
--- a/include/asm-x86/processor.h
+++ b/include/asm-x86/processor.h
@@ -76,11 +76,11 @@
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 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 @@
/* 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 @@
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 24879c8..ee813f4 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 @@
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 @@
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 @@
__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 @@
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 @@
#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 4e2ec73..8c34703 100644
--- a/include/asm-x86/sigcontext32.h
+++ b/include/asm-x86/sigcontext32.h
@@ -40,7 +40,11 @@
__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 4db0066..3f4e52b 100644
--- a/include/asm-x86/thread_info.h
+++ b/include/asm-x86/thread_info.h
@@ -241,6 +241,7 @@
#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 9948dd3..89eaa54 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 0000000..f2cba4e
--- /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 0000000..08e9a1a
--- /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