diff options
Diffstat (limited to 'arch/x86/include')
48 files changed, 737 insertions, 396 deletions
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index aa2c39d968f..92091de1111 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -134,7 +134,7 @@ static inline unsigned int acpi_processor_cstate_check(unsigned int max_cstate) boot_cpu_data.x86_model <= 0x05 && boot_cpu_data.x86_mask < 0x0A) return 1; - else if (boot_cpu_has(X86_FEATURE_AMDC1E)) + else if (c1e_detected) return 1; else return max_cstate; diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 03b6bb5394a..bc6abb7bc7e 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -45,10 +45,9 @@ struct alt_instr { u8 *instr; /* original instruction */ u8 *replacement; - u8 cpuid; /* cpuid bit set for replacement */ + u16 cpuid; /* cpuid bit set for replacement */ u8 instrlen; /* length of original instruction */ u8 replacementlen; /* length of new instruction, <= instrlen */ - u8 pad1; #ifdef CONFIG_X86_64 u32 pad2; #endif @@ -86,9 +85,11 @@ static inline int alternatives_text_reserved(void *start, void *end) _ASM_ALIGN "\n" \ _ASM_PTR "661b\n" /* label */ \ _ASM_PTR "663f\n" /* new instruction */ \ - " .byte " __stringify(feature) "\n" /* feature bit */ \ + " .word " __stringify(feature) "\n" /* feature bit */ \ " .byte 662b-661b\n" /* sourcelen */ \ " .byte 664f-663f\n" /* replacementlen */ \ + ".previous\n" \ + ".section .discard,\"aw\",@progbits\n" \ " .byte 0xff + (664f-663f) - (662b-661b)\n" /* rlen <= slen */ \ ".previous\n" \ ".section .altinstr_replacement, \"ax\"\n" \ diff --git a/arch/x86/include/asm/apb_timer.h b/arch/x86/include/asm/apb_timer.h index c74a2eebe57..a69b1ac9eaf 100644 --- a/arch/x86/include/asm/apb_timer.h +++ b/arch/x86/include/asm/apb_timer.h @@ -55,7 +55,6 @@ extern unsigned long apbt_quick_calibrate(void); extern int arch_setup_apbt_irqs(int irq, int trigger, int mask, int cpu); extern void apbt_setup_secondary_clock(void); extern unsigned int boot_cpu_id; -extern int disable_apbt_percpu; extern struct sfi_timer_table_entry *sfi_get_mtmr(int hint); extern void sfi_free_mtmr(struct sfi_timer_table_entry *mtmr); diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h index 6be33d83c71..8e6218550e7 100644 --- a/arch/x86/include/asm/bootparam.h +++ b/arch/x86/include/asm/bootparam.h @@ -70,6 +70,14 @@ struct sys_desc_table { __u8 table[14]; }; +/* Gleaned from OFW's set-parameters in cpu/x86/pc/linux.fth */ +struct olpc_ofw_header { + __u32 ofw_magic; /* OFW signature */ + __u32 ofw_version; + __u32 cif_handler; /* callback into OFW */ + __u32 irq_desc_table; +} __attribute__((packed)); + struct efi_info { __u32 efi_loader_signature; __u32 efi_systab; @@ -92,7 +100,8 @@ struct boot_params { __u8 hd0_info[16]; /* obsolete! */ /* 0x080 */ __u8 hd1_info[16]; /* obsolete! */ /* 0x090 */ struct sys_desc_table sys_desc_table; /* 0x0a0 */ - __u8 _pad4[144]; /* 0x0b0 */ + struct olpc_ofw_header olpc_ofw_header; /* 0x0b0 */ + __u8 _pad4[128]; /* 0x0c0 */ struct edid_info edid_info; /* 0x140 */ struct efi_info efi_info; /* 0x1c0 */ __u32 alt_mem_k; /* 0x1e0 */ diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h index 8859e12dd3c..284a6e8f7ce 100644 --- a/arch/x86/include/asm/cmpxchg_32.h +++ b/arch/x86/include/asm/cmpxchg_32.h @@ -11,38 +11,42 @@ extern void __xchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ - -struct __xchg_dummy { - unsigned long a[100]; -}; -#define __xg(x) ((struct __xchg_dummy *)(x)) - #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ asm volatile("xchgl %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -53,60 +57,33 @@ struct __xchg_dummy { __xchg((v), (ptr), sizeof(*ptr)) /* - * The semantics of XCHGCMP8B are a bit strange, this is why - * there is a loop and the loading of %%eax and %%edx has to - * be inside. This inlines well in most cases, the cached - * cost is around ~38 cycles. (in the future we might want - * to do an SIMD/3DNOW!/MMX/FPU 64-bit store here, but that - * might have an implicit FPU-save as a cost, so it's not - * clear which path to go.) + * CMPXCHG8B only writes to the target if we had the previous + * value in registers, otherwise it acts as a read and gives us the + * "new previous" value. That is why there is a loop. Preloading + * EDX:EAX is a performance optimization: in the common case it means + * we need only one locked operation. * - * cmpxchg8b must be used with the lock prefix here to allow - * the instruction to be executed atomically, see page 3-102 - * of the instruction set reference 24319102.pdf. We need - * the reader side to see the coherent 64bit value. + * A SIMD/3DNOW!/MMX/FPU 64-bit store here would require at the very + * least an FPU save and/or %cr0.ts manipulation. + * + * cmpxchg8b must be used with the lock prefix here to allow the + * instruction to be executed atomically. We need to have the reader + * side to see the coherent 64bit value. */ -static inline void __set_64bit(unsigned long long *ptr, - unsigned int low, unsigned int high) +static inline void set_64bit(volatile u64 *ptr, u64 value) { + u32 low = value; + u32 high = value >> 32; + u64 prev = *ptr; + asm volatile("\n1:\t" - "movl (%0), %%eax\n\t" - "movl 4(%0), %%edx\n\t" - LOCK_PREFIX "cmpxchg8b (%0)\n\t" + LOCK_PREFIX "cmpxchg8b %0\n\t" "jnz 1b" - : /* no outputs */ - : "D"(ptr), - "b"(low), - "c"(high) - : "ax", "dx", "memory"); -} - -static inline void __set_64bit_constant(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, (unsigned int)value, (unsigned int)(value >> 32)); -} - -#define ll_low(x) *(((unsigned int *)&(x)) + 0) -#define ll_high(x) *(((unsigned int *)&(x)) + 1) - -static inline void __set_64bit_var(unsigned long long *ptr, - unsigned long long value) -{ - __set_64bit(ptr, ll_low(value), ll_high(value)); + : "=m" (*ptr), "+A" (prev) + : "b" (low), "c" (high) + : "memory"); } -#define set_64bit(ptr, value) \ - (__builtin_constant_p((value)) \ - ? __set_64bit_constant((ptr), (value)) \ - : __set_64bit_var((ptr), (value))) - -#define _set_64bit(ptr, value) \ - (__builtin_constant_p(value) \ - ? __set_64bit(ptr, (unsigned int)(value), \ - (unsigned int)((value) >> 32)) \ - : __set_64bit(ptr, ll_low((value)), ll_high((value)))) - extern void __cmpxchg_wrong_size(void); /* @@ -121,23 +98,32 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ @@ -175,32 +161,28 @@ extern void __cmpxchg_wrong_size(void); (unsigned long long)(n))) #endif -static inline unsigned long long __cmpxchg64(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile(LOCK_PREFIX "cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile(LOCK_PREFIX "cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } -static inline unsigned long long __cmpxchg64_local(volatile void *ptr, - unsigned long long old, - unsigned long long new) +static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new) { - unsigned long long prev; - asm volatile("cmpxchg8b %3" - : "=A"(prev) - : "b"((unsigned long)new), - "c"((unsigned long)(new >> 32)), - "m"(*__xg(ptr)), - "0"(old) + u64 prev; + asm volatile("cmpxchg8b %1" + : "=A" (prev), + "+m" (*ptr) + : "b" ((u32)new), + "c" ((u32)(new >> 32)), + "0" (old) : "memory"); return prev; } @@ -264,8 +246,6 @@ static inline unsigned long cmpxchg_386(volatile void *ptr, unsigned long old, * to simulate the cmpxchg8b on the 80386 and 80486 CPU. */ -extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); - #define cmpxchg64(ptr, o, n) \ ({ \ __typeof__(*(ptr)) __ret; \ @@ -283,20 +263,20 @@ extern unsigned long long cmpxchg_486_u64(volatile void *, u64, u64); __ret; }) - -#define cmpxchg64_local(ptr, o, n) \ -({ \ - __typeof__(*(ptr)) __ret; \ - if (likely(boot_cpu_data.x86 > 4)) \ - __ret = (__typeof__(*(ptr)))__cmpxchg64_local((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - else \ - __ret = (__typeof__(*(ptr)))cmpxchg_486_u64((ptr), \ - (unsigned long long)(o), \ - (unsigned long long)(n)); \ - __ret; \ -}) +#define cmpxchg64_local(ptr, o, n) \ +({ \ + __typeof__(*(ptr)) __ret; \ + __typeof__(*(ptr)) __old = (o); \ + __typeof__(*(ptr)) __new = (n); \ + alternative_io("call cmpxchg8b_emu", \ + "cmpxchg8b (%%esi)" , \ + X86_FEATURE_CX8, \ + "=A" (__ret), \ + "S" ((ptr)), "0" (__old), \ + "b" ((unsigned int)__new), \ + "c" ((unsigned int)(__new>>32)) \ + : "memory"); \ + __ret; }) #endif diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h index 485ae415fae..423ae58aa02 100644 --- a/arch/x86/include/asm/cmpxchg_64.h +++ b/arch/x86/include/asm/cmpxchg_64.h @@ -3,51 +3,60 @@ #include <asm/alternative.h> /* Provides LOCK_PREFIX */ -#define __xg(x) ((volatile long *)(x)) - -static inline void set_64bit(volatile unsigned long *ptr, unsigned long val) +static inline void set_64bit(volatile u64 *ptr, u64 val) { *ptr = val; } -#define _set_64bit set_64bit - extern void __xchg_wrong_size(void); extern void __cmpxchg_wrong_size(void); /* - * Note: no "lock" prefix even on SMP: xchg always implies lock anyway - * Note 2: xchg has side effect, so that attribute volatile is necessary, - * but generally the primitive is invalid, *ptr is output argument. --ANK + * Note: no "lock" prefix even on SMP: xchg always implies lock anyway. + * Since this is generally used to protect other memory information, we + * use "asm volatile" and "memory" clobbers to prevent gcc from moving + * information around. */ #define __xchg(x, ptr, size) \ ({ \ __typeof(*(ptr)) __x = (x); \ switch (size) { \ case 1: \ - asm volatile("xchgb %b0,%1" \ - : "=q" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile("xchgb %0,%1" \ + : "=q" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile("xchgw %w0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile("xchgw %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile("xchgl %k0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile("xchgl %0,%1" \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ case 8: \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ asm volatile("xchgq %0,%1" \ - : "=r" (__x) \ - : "m" (*__xg(ptr)), "0" (__x) \ + : "=r" (__x), "+m" (*__ptr) \ + : "0" (__x) \ : "memory"); \ break; \ + } \ default: \ __xchg_wrong_size(); \ } \ @@ -71,29 +80,41 @@ extern void __cmpxchg_wrong_size(void); __typeof__(*(ptr)) __new = (new); \ switch (size) { \ case 1: \ - asm volatile(lock "cmpxchgb %b1,%2" \ - : "=a"(__ret) \ - : "q"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u8 *__ptr = (volatile u8 *)(ptr); \ + asm volatile(lock "cmpxchgb %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "q" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 2: \ - asm volatile(lock "cmpxchgw %w1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u16 *__ptr = (volatile u16 *)(ptr); \ + asm volatile(lock "cmpxchgw %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 4: \ - asm volatile(lock "cmpxchgl %k1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u32 *__ptr = (volatile u32 *)(ptr); \ + asm volatile(lock "cmpxchgl %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ case 8: \ - asm volatile(lock "cmpxchgq %1,%2" \ - : "=a"(__ret) \ - : "r"(__new), "m"(*__xg(ptr)), "0"(__old) \ + { \ + volatile u64 *__ptr = (volatile u64 *)(ptr); \ + asm volatile(lock "cmpxchgq %2,%1" \ + : "=a" (__ret), "+m" (*__ptr) \ + : "r" (__new), "0" (__old) \ : "memory"); \ break; \ + } \ default: \ __cmpxchg_wrong_size(); \ } \ diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 46814591438..781a50b29a4 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -6,7 +6,7 @@ #include <asm/required-features.h> -#define NCAPINTS 9 /* N 32-bit words worth of info */ +#define NCAPINTS 10 /* N 32-bit words worth of info */ /* * Note: If the comment begins with a quoted string, that string is used @@ -89,7 +89,7 @@ #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 */ + /* 21 available, was AMD_C1E */ #define X86_FEATURE_XTOPOLOGY (3*32+22) /* cpu topology enum extensions */ #define X86_FEATURE_TSC_RELIABLE (3*32+23) /* TSC is known to be reliable */ #define X86_FEATURE_NONSTOP_TSC (3*32+24) /* TSC does not stop in C states */ @@ -124,6 +124,8 @@ #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 */ +#define X86_FEATURE_F16C (4*32+29) /* 16-bit fp conversions */ +#define X86_FEATURE_RDRND (4*32+30) /* The RDRAND instruction */ #define X86_FEATURE_HYPERVISOR (4*32+31) /* Running on a hypervisor */ /* VIA/Cyrix/Centaur-defined CPU features, CPUID level 0xC0000001, word 5 */ @@ -157,22 +159,29 @@ /* * Auxiliary flags: Linux defined - For features scattered in various - * CPUID levels like 0x6, 0xA etc + * CPUID levels like 0x6, 0xA etc, word 7 */ #define X86_FEATURE_IDA (7*32+ 0) /* Intel Dynamic Acceleration */ #define X86_FEATURE_ARAT (7*32+ 1) /* Always Running APIC Timer */ #define X86_FEATURE_CPB (7*32+ 2) /* AMD Core Performance Boost */ +#define X86_FEATURE_EPB (7*32+ 3) /* IA32_ENERGY_PERF_BIAS support */ +#define X86_FEATURE_XSAVEOPT (7*32+ 4) /* Optimized Xsave */ +#define X86_FEATURE_PLN (7*32+ 5) /* Intel Power Limit Notification */ +#define X86_FEATURE_PTS (7*32+ 6) /* Intel Package Thermal Status */ -/* Virtualization flags: Linux defined */ +/* Virtualization flags: Linux defined, word 8 */ #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 */ -#define X86_FEATURE_NPT (8*32+5) /* AMD Nested Page Table support */ -#define X86_FEATURE_LBRV (8*32+6) /* AMD LBR Virtualization support */ -#define X86_FEATURE_SVML (8*32+7) /* "svm_lock" AMD SVM locking MSR */ -#define X86_FEATURE_NRIPS (8*32+8) /* "nrip_save" AMD SVM next_rip save */ +#define X86_FEATURE_NPT (8*32+ 5) /* AMD Nested Page Table support */ +#define X86_FEATURE_LBRV (8*32+ 6) /* AMD LBR Virtualization support */ +#define X86_FEATURE_SVML (8*32+ 7) /* "svm_lock" AMD SVM locking MSR */ +#define X86_FEATURE_NRIPS (8*32+ 8) /* "nrip_save" AMD SVM next_rip save */ + +/* Intel-defined CPU features, CPUID level 0x00000007:0 (ebx), word 9 */ +#define X86_FEATURE_FSGSBASE (9*32+ 0) /* {RD/WR}{FS/GS}BASE instructions*/ #if defined(__KERNEL__) && !defined(__ASSEMBLY__) @@ -194,7 +203,9 @@ extern const char * const x86_power_flags[32]; (((bit)>>5)==4 && (1UL<<((bit)&31) & REQUIRED_MASK4)) || \ (((bit)>>5)==5 && (1UL<<((bit)&31) & REQUIRED_MASK5)) || \ (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \ - (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) ) \ + (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \ + (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \ + (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) \ ? 1 : \ test_cpu_cap(c, bit)) @@ -291,7 +302,7 @@ extern const char * const x86_power_flags[32]; * patch the target code for additional performance. * */ -static __always_inline __pure bool __static_cpu_has(u8 bit) +static __always_inline __pure bool __static_cpu_has(u16 bit) { #if __GNUC__ > 4 || (__GNUC__ == 4 && __GNUC_MINOR__ >= 5) asm goto("1: jmp %l[t_no]\n" @@ -300,11 +311,11 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) _ASM_ALIGN "\n" _ASM_PTR "1b\n" _ASM_PTR "0\n" /* no replacement */ - " .byte %P0\n" /* feature bit */ + " .word %P0\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 0\n" /* replacement len */ - " .byte 0xff + 0 - (2b-1b)\n" /* padding */ ".previous\n" + /* skipping size check since replacement size = 0 */ : : "i" (bit) : : t_no); return true; t_no: @@ -318,10 +329,12 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) _ASM_ALIGN "\n" _ASM_PTR "1b\n" _ASM_PTR "3f\n" - " .byte %P1\n" /* feature bit */ + " .word %P1\n" /* feature bit */ " .byte 2b - 1b\n" /* source len */ " .byte 4f - 3f\n" /* replacement len */ - " .byte 0xff + (4f-3f) - (2b-1b)\n" /* padding */ + ".previous\n" + ".section .discard,\"aw\",@progbits\n" + " .byte 0xff + (4f-3f) - (2b-1b)\n" /* size check */ ".previous\n" ".section .altinstr_replacement,\"ax\"\n" "3: movb $1,%0\n" @@ -337,7 +350,7 @@ static __always_inline __pure bool __static_cpu_has(u8 bit) ( \ __builtin_constant_p(boot_cpu_has(bit)) ? \ boot_cpu_has(bit) : \ - (__builtin_constant_p(bit) && !((bit) & ~0xff)) ? \ + __builtin_constant_p(bit) ? \ __static_cpu_has(bit) : \ boot_cpu_has(bit) \ ) diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index ac91eed2106..d4c419f883a 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -54,7 +54,6 @@ static inline int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) #define dma_alloc_noncoherent(d, s, h, f) dma_alloc_coherent(d, s, h, f) #define dma_free_noncoherent(d, s, v, h) dma_free_coherent(d, s, v, h) -#define dma_is_consistent(d, h) (1) extern int dma_supported(struct device *hwdev, u64 mask); extern int dma_set_mask(struct device *dev, u64 mask); @@ -87,13 +86,6 @@ dma_cache_sync(struct device *dev, void *vaddr, size_t size, flush_write_buffers(); } -static inline int dma_get_cache_alignment(void) -{ - /* no easy way to get cache size on all x86, so return the - * maximum possible, to be safe */ - return boot_cpu_data.x86_clflush_size; -} - static inline unsigned long dma_alloc_coherent_mask(struct device *dev, gfp_t gfp) { diff --git a/arch/x86/include/asm/highmem.h b/arch/x86/include/asm/highmem.h index a726650fc80..8caac76ac32 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, enum km_type type, pgprot_t prot); void *kmap_atomic(struct page *page, enum km_type type); -void kunmap_atomic(void *kvaddr, enum km_type type); +void kunmap_atomic_notypecheck(void *kvaddr, enum km_type type); void *kmap_atomic_pfn(unsigned long pfn, enum km_type type); void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot); struct page *kmap_atomic_to_page(void *ptr); diff --git a/arch/x86/include/asm/hw_breakpoint.h b/arch/x86/include/asm/hw_breakpoint.h index 942255310e6..528a11e8d3e 100644 --- a/arch/x86/include/asm/hw_breakpoint.h +++ b/arch/x86/include/asm/hw_breakpoint.h @@ -20,10 +20,10 @@ struct arch_hw_breakpoint { #include <linux/list.h> /* Available HW breakpoint length encodings */ +#define X86_BREAKPOINT_LEN_X 0x00 #define X86_BREAKPOINT_LEN_1 0x40 #define X86_BREAKPOINT_LEN_2 0x44 #define X86_BREAKPOINT_LEN_4 0x4c -#define X86_BREAKPOINT_LEN_EXECUTE 0x40 #ifdef CONFIG_X86_64 #define X86_BREAKPOINT_LEN_8 0x48 diff --git a/arch/x86/include/asm/hypervisor.h b/arch/x86/include/asm/hypervisor.h index 70abda7058c..ff2546ce717 100644 --- a/arch/x86/include/asm/hypervisor.h +++ b/arch/x86/include/asm/hypervisor.h @@ -45,5 +45,6 @@ extern const struct hypervisor_x86 *x86_hyper; /* Recognized hypervisors */ extern const struct hypervisor_x86 x86_hyper_vmware; extern const struct hypervisor_x86 x86_hyper_ms_hyperv; +extern const struct hypervisor_x86 x86_hyper_xen_hvm; #endif diff --git a/arch/x86/include/asm/i387.h b/arch/x86/include/asm/i387.h index c991b3a7b90..a73a8d5a5e6 100644 --- a/arch/x86/include/asm/i387.h +++ b/arch/x86/include/asm/i387.h @@ -31,7 +31,6 @@ extern void mxcsr_feature_mask_init(void); extern int init_fpu(struct task_struct *child); extern asmlinkage void math_state_restore(void); extern void __math_state_restore(void); -extern void init_thread_xstate(void); extern int dump_fpu(struct pt_regs *, struct user_i387_struct *); extern user_regset_active_fn fpregs_active, xfpregs_active; @@ -58,11 +57,25 @@ extern int restore_i387_xstate_ia32(void __user *buf); #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); } +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 /* Ignore delayed exceptions from user space */ @@ -127,6 +140,15 @@ 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; + asm volatile("1: rex64/fxsave (%[fx])\n\t" "2:\n" ".section .fixup,\"ax\"\n" @@ -482,6 +504,8 @@ 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 /* __ASSEMBLY__ */ #define PSHUFB_XMM5_XMM0 .byte 0x66, 0x0f, 0x38, 0x00, 0xc5 diff --git a/arch/x86/include/asm/intel_scu_ipc.h b/arch/x86/include/asm/intel_scu_ipc.h index 4470c9ad4a3..29f66793cc5 100644 --- a/arch/x86/include/asm/intel_scu_ipc.h +++ b/arch/x86/include/asm/intel_scu_ipc.h @@ -1,6 +1,12 @@ #ifndef _ASM_X86_INTEL_SCU_IPC_H_ #define _ASM_X86_INTEL_SCU_IPC_H_ +#define IPCMSG_VRTC 0xFA /* Set vRTC device */ + +/* Command id associated with message IPCMSG_VRTC */ +#define IPC_CMD_VRTC_SETTIME 1 /* Set time */ +#define IPC_CMD_VRTC_SETALARM 2 /* Set alarm */ + /* Read single register */ int intel_scu_ipc_ioread8(u16 addr, u8 *data); @@ -28,20 +34,6 @@ int intel_scu_ipc_writev(u16 *addr, u8 *data, int len); /* Update single register based on the mask */ int intel_scu_ipc_update_register(u16 addr, u8 data, u8 mask); -/* - * Indirect register read - * Can be used when SCCB(System Controller Configuration Block) register - * HRIM(Honor Restricted IPC Messages) is set (bit 23) - */ -int intel_scu_ipc_register_read(u32 addr, u32 *data); - -/* - * Indirect register write - * Can be used when SCCB(System Controller Configuration Block) register - * HRIM(Honor Restricted IPC Messages) is set (bit 23) - */ -int intel_scu_ipc_register_write(u32 addr, u32 data); - /* Issue commands to the SCU with or without data */ int intel_scu_ipc_simple_command(int cmd, int sub); int intel_scu_ipc_command(int cmd, int sub, u32 *in, int inlen, diff --git a/arch/x86/include/asm/irq_vectors.h b/arch/x86/include/asm/irq_vectors.h index 8767d99c4f6..e2ca3009255 100644 --- a/arch/x86/include/asm/irq_vectors.h +++ b/arch/x86/include/asm/irq_vectors.h @@ -125,6 +125,9 @@ */ #define MCE_SELF_VECTOR 0xeb +/* Xen vector callback to receive events in a HVM domain */ +#define XEN_HVM_EVTCHN_CALLBACK 0xe9 + #define NR_VECTORS 256 #define FPU_IRQ 13 diff --git a/arch/x86/include/asm/kdebug.h b/arch/x86/include/asm/kdebug.h index fa7c0b97476..5bdfca86581 100644 --- a/arch/x86/include/asm/kdebug.h +++ b/arch/x86/include/asm/kdebug.h @@ -33,5 +33,11 @@ extern void __show_regs(struct pt_regs *regs, int all); extern void show_regs(struct pt_regs *regs); extern unsigned long oops_begin(void); extern void oops_end(unsigned long, struct pt_regs *, int signr); +#ifdef CONFIG_KEXEC +extern int in_crash_kexec; +#else +/* no crash dump is ever in progress if no crash kernel can be kexec'd */ +#define in_crash_kexec 0 +#endif #endif /* _ASM_X86_KDEBUG_H */ diff --git a/arch/x86/include/asm/kgdb.h b/arch/x86/include/asm/kgdb.h index 006da3687cd..396f5b5fc4d 100644 --- a/arch/x86/include/asm/kgdb.h +++ b/arch/x86/include/asm/kgdb.h @@ -39,9 +39,11 @@ enum regnames { GDB_FS, /* 14 */ GDB_GS, /* 15 */ }; +#define GDB_ORIG_AX 41 +#define DBG_MAX_REG_NUM 16 #define NUMREGBYTES ((GDB_GS+1)*4) #else /* ! CONFIG_X86_32 */ -enum regnames64 { +enum regnames { GDB_AX, /* 0 */ GDB_BX, /* 1 */ GDB_CX, /* 2 */ @@ -59,15 +61,15 @@ enum regnames64 { GDB_R14, /* 14 */ GDB_R15, /* 15 */ GDB_PC, /* 16 */ + GDB_PS, /* 17 */ + GDB_CS, /* 18 */ + GDB_SS, /* 19 */ }; - -enum regnames32 { - GDB_PS = 34, - GDB_CS, - GDB_SS, -}; -#define NUMREGBYTES ((GDB_SS+1)*4) -#endif /* CONFIG_X86_32 */ +#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)) +#endif /* ! CONFIG_X86_32 */ static inline void arch_kgdb_breakpoint(void) { diff --git a/arch/x86/include/asm/kvm.h b/arch/x86/include/asm/kvm.h index ff90055c7f0..4d8dcbdfc12 100644 --- a/arch/x86/include/asm/kvm.h +++ b/arch/x86/include/asm/kvm.h @@ -22,6 +22,8 @@ #define __KVM_HAVE_XEN_HVM #define __KVM_HAVE_VCPU_EVENTS #define __KVM_HAVE_DEBUGREGS +#define __KVM_HAVE_XSAVE +#define __KVM_HAVE_XCRS /* Architectural interrupt line count. */ #define KVM_NR_INTERRUPTS 256 @@ -299,4 +301,24 @@ struct kvm_debugregs { __u64 reserved[9]; }; +/* for KVM_CAP_XSAVE */ +struct kvm_xsave { + __u32 region[1024]; +}; + +#define KVM_MAX_XCRS 16 + +struct kvm_xcr { + __u32 xcr; + __u32 reserved; + __u64 value; +}; + +struct kvm_xcrs { + __u32 nr_xcrs; + __u32 flags; + struct kvm_xcr xcrs[KVM_MAX_XCRS]; + __u64 padding[16]; +}; + #endif /* _ASM_X86_KVM_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 0b2729bf207..51cfd730ac5 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -51,8 +51,10 @@ struct x86_emulate_ctxt; #define X86EMUL_UNHANDLEABLE 1 /* Terminate emulation but return success to the caller. */ #define X86EMUL_PROPAGATE_FAULT 2 /* propagate a generated fault to guest */ -#define X86EMUL_RETRY_INSTR 2 /* retry the instruction for some reason */ -#define X86EMUL_CMPXCHG_FAILED 2 /* cmpxchg did not see expected value */ +#define X86EMUL_RETRY_INSTR 3 /* retry the instruction for some reason */ +#define X86EMUL_CMPXCHG_FAILED 4 /* cmpxchg did not see expected value */ +#define X86EMUL_IO_NEEDED 5 /* IO is needed to complete emulation */ + struct x86_emulate_ops { /* * read_std: Read bytes of standard (non-emulated/special) memory. @@ -92,6 +94,7 @@ struct x86_emulate_ops { int (*read_emulated)(unsigned long addr, void *val, unsigned int bytes, + unsigned int *error, struct kvm_vcpu *vcpu); /* @@ -104,6 +107,7 @@ struct x86_emulate_ops { int (*write_emulated)(unsigned long addr, const void *val, unsigned int bytes, + unsigned int *error, struct kvm_vcpu *vcpu); /* @@ -118,6 +122,7 @@ struct x86_emulate_ops { const void *old, const void *new, unsigned int bytes, + unsigned int *error, struct kvm_vcpu *vcpu); int (*pio_in_emulated)(int size, unsigned short port, void *val, @@ -132,18 +137,26 @@ struct x86_emulate_ops { int seg, struct kvm_vcpu *vcpu); u16 (*get_segment_selector)(int seg, struct kvm_vcpu *vcpu); void (*set_segment_selector)(u16 sel, int seg, struct kvm_vcpu *vcpu); + unsigned long (*get_cached_segment_base)(int seg, struct kvm_vcpu *vcpu); void (*get_gdt)(struct desc_ptr *dt, struct kvm_vcpu *vcpu); ulong (*get_cr)(int cr, struct kvm_vcpu *vcpu); - void (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu); + int (*set_cr)(int cr, ulong val, struct kvm_vcpu *vcpu); int (*cpl)(struct kvm_vcpu *vcpu); - void (*set_rflags)(struct kvm_vcpu *vcpu, unsigned long rflags); + int (*get_dr)(int dr, unsigned long *dest, struct kvm_vcpu *vcpu); + int (*set_dr)(int dr, unsigned long value, struct kvm_vcpu *vcpu); + int (*set_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 data); + int (*get_msr)(struct kvm_vcpu *vcpu, u32 msr_index, u64 *pdata); }; /* Type, address-of, and value of an instruction's operand. */ struct operand { enum { OP_REG, OP_MEM, OP_IMM, OP_NONE } type; unsigned int bytes; - unsigned long val, orig_val, *ptr; + unsigned long orig_val, *ptr; + union { + unsigned long val; + char valptr[sizeof(unsigned long) + 2]; + }; }; struct fetch_cache { @@ -186,6 +199,7 @@ struct decode_cache { unsigned long modrm_val; struct fetch_cache fetch; struct read_cache io_read; + struct read_cache mem_read; }; struct x86_emulate_ctxt { @@ -202,6 +216,12 @@ struct x86_emulate_ctxt { int interruptibility; bool restart; /* restart string instruction after writeback */ + + int exception; /* exception that happens during emulation or -1 */ + u32 error_code; /* error code for exception */ + bool error_code_valid; + unsigned long cr2; /* faulted address in case of #PF */ + /* decode cache */ struct decode_cache decode; }; diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 76f5483cffe..502e53f999c 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -15,6 +15,7 @@ #include <linux/mm.h> #include <linux/mmu_notifier.h> #include <linux/tracepoint.h> +#include <linux/cpumask.h> #include <linux/kvm.h> #include <linux/kvm_para.h> @@ -39,11 +40,14 @@ 0xFFFFFF0000000000ULL) #define INVALID_PAGE (~(hpa_t)0) +#define VALID_PAGE(x) ((x) != INVALID_PAGE) + #define UNMAPPED_GVA (~(gpa_t)0) /* KVM Hugepage definitions for x86 */ #define KVM_NR_PAGE_SIZES 3 -#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + (((x) - 1) * 9)) +#define KVM_HPAGE_GFN_SHIFT(x) (((x) - 1) * 9) +#define KVM_HPAGE_SHIFT(x) (PAGE_SHIFT + KVM_HPAGE_GFN_SHIFT(x)) #define KVM_HPAGE_SIZE(x) (1UL << KVM_HPAGE_SHIFT(x)) #define KVM_HPAGE_MASK(x) (~(KVM_HPAGE_SIZE(x) - 1)) #define KVM_PAGES_PER_HPAGE(x) (KVM_HPAGE_SIZE(x) / PAGE_SIZE) @@ -69,8 +73,6 @@ #define IOPL_SHIFT 12 -#define KVM_ALIAS_SLOTS 4 - #define KVM_PERMILLE_MMU_PAGES 20 #define KVM_MIN_ALLOC_MMU_PAGES 64 #define KVM_MMU_HASH_SHIFT 10 @@ -241,7 +243,7 @@ struct kvm_mmu { void (*prefetch_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *page); int (*sync_page)(struct kvm_vcpu *vcpu, - struct kvm_mmu_page *sp); + struct kvm_mmu_page *sp, bool clear_unsync); void (*invlpg)(struct kvm_vcpu *vcpu, gva_t gva); hpa_t root_hpa; int root_level; @@ -301,8 +303,8 @@ struct kvm_vcpu_arch { unsigned long mmu_seq; } update_pte; - struct i387_fxsave_struct host_fx_image; - struct i387_fxsave_struct guest_fx_image; + struct fpu guest_fpu; + u64 xcr0; gva_t mmio_fault_cr2; struct kvm_pio_request pio; @@ -360,26 +362,11 @@ struct kvm_vcpu_arch { /* fields used by HYPER-V emulation */ u64 hv_vapic; -}; - -struct kvm_mem_alias { - gfn_t base_gfn; - unsigned long npages; - gfn_t target_gfn; -#define KVM_ALIAS_INVALID 1UL - unsigned long flags; -}; -#define KVM_ARCH_HAS_UNALIAS_INSTANTIATION - -struct kvm_mem_aliases { - struct kvm_mem_alias aliases[KVM_ALIAS_SLOTS]; - int naliases; + cpumask_var_t wbinvd_dirty_mask; }; struct kvm_arch { - struct kvm_mem_aliases *aliases; - unsigned int n_free_mmu_pages; unsigned int n_requested_mmu_pages; unsigned int n_alloc_mmu_pages; @@ -533,6 +520,8 @@ struct kvm_x86_ops { void (*set_supported_cpuid)(u32 func, struct kvm_cpuid_entry2 *entry); + bool (*has_wbinvd_exit)(void); + const struct trace_print_flags *exit_reasons_str; }; @@ -576,7 +565,6 @@ enum emulation_result { #define EMULTYPE_SKIP (1 << 2) int emulate_instruction(struct kvm_vcpu *vcpu, unsigned long cr2, u16 error_code, int emulation_type); -void kvm_report_emulation_failure(struct kvm_vcpu *cvpu, const char *context); void realmode_lgdt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); void realmode_lidt(struct kvm_vcpu *vcpu, u16 size, unsigned long address); @@ -591,10 +579,7 @@ void kvm_emulate_cpuid(struct kvm_vcpu *vcpu); int kvm_emulate_halt(struct kvm_vcpu *vcpu); int emulate_invlpg(struct kvm_vcpu *vcpu, gva_t address); int emulate_clts(struct kvm_vcpu *vcpu); -int emulator_get_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long *dest); -int emulator_set_dr(struct x86_emulate_ctxt *ctxt, int dr, - unsigned long value); +int kvm_emulate_wbinvd(struct kvm_vcpu *vcpu); void kvm_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg); int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); @@ -602,15 +587,16 @@ int kvm_load_segment_descriptor(struct kvm_vcpu *vcpu, u16 selector, int seg); int kvm_task_switch(struct kvm_vcpu *vcpu, u16 tss_selector, int reason, bool has_error_code, u32 error_code); -void kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); -void kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); -void kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); +int kvm_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0); +int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3); +int kvm_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4); void kvm_set_cr8(struct kvm_vcpu *vcpu, unsigned long cr8); int kvm_set_dr(struct kvm_vcpu *vcpu, int dr, unsigned long val); int kvm_get_dr(struct kvm_vcpu *vcpu, int dr, unsigned long *val); unsigned long kvm_get_cr8(struct kvm_vcpu *vcpu); void kvm_lmsw(struct kvm_vcpu *vcpu, unsigned long msw); void kvm_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l); +int kvm_set_xcr(struct kvm_vcpu *vcpu, u32 index, u64 xcr); int kvm_get_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 *pdata); int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data); @@ -630,12 +616,7 @@ int kvm_pic_set_irq(void *opaque, int irq, int level); void kvm_inject_nmi(struct kvm_vcpu *vcpu); -void fx_init(struct kvm_vcpu *vcpu); - -int emulator_write_emulated(unsigned long addr, - const void *val, - unsigned int bytes, - struct kvm_vcpu *vcpu); +int fx_init(struct kvm_vcpu *vcpu); void kvm_mmu_flush_tlb(struct kvm_vcpu *vcpu); void kvm_mmu_pte_write(struct kvm_vcpu *vcpu, gpa_t gpa, @@ -664,8 +645,6 @@ void kvm_disable_tdp(void); int complete_pio(struct kvm_vcpu *vcpu); bool kvm_check_iopl(struct kvm_vcpu *vcpu); -struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn); - static inline struct kvm_mmu_page *page_header(hpa_t shadow_page) { struct page *page = pfn_to_page(shadow_page >> PAGE_SHIFT); @@ -719,21 +698,6 @@ static inline unsigned long read_msr(unsigned long msr) } #endif -static inline void kvm_fx_save(struct i387_fxsave_struct *image) -{ - asm("fxsave (%0)":: "r" (image)); -} - -static inline void kvm_fx_restore(struct i387_fxsave_struct *image) -{ - asm("fxrstor (%0)":: "r" (image)); -} - -static inline void kvm_fx_finit(void) -{ - asm("finit"); -} - static inline u32 get_rdx_init_val(void) { return 0x600; /* P6 family */ diff --git a/arch/x86/include/asm/local64.h b/arch/x86/include/asm/local64.h new file mode 100644 index 00000000000..36c93b5cc23 --- /dev/null +++ b/arch/x86/include/asm/local64.h @@ -0,0 +1 @@ +#include <asm-generic/local64.h> diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index f32a4301c4d..c62c13cb978 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -38,6 +38,10 @@ #define MCM_ADDR_MEM 3 /* memory address */ #define MCM_ADDR_GENERIC 7 /* generic */ +/* CTL2 register defines */ +#define MCI_CTL2_CMCI_EN (1ULL << 30) +#define MCI_CTL2_CMCI_THRESHOLD_MASK 0x7fffULL + #define MCJ_CTX_MASK 3 #define MCJ_CTX(flags) ((flags) & MCJ_CTX_MASK) #define MCJ_CTX_RANDOM 0 /* inject context: random */ diff --git a/arch/x86/include/asm/mrst.h b/arch/x86/include/asm/mrst.h index 451d30e7f62..16350740edf 100644 --- a/arch/x86/include/asm/mrst.h +++ b/arch/x86/include/asm/mrst.h @@ -13,6 +13,32 @@ extern int pci_mrst_init(void); int __init sfi_parse_mrtc(struct sfi_table_header *table); +/* + * Medfield is the follow-up of Moorestown, it combines two chip solution into + * one. Other than that it also added always-on and constant tsc and lapic + * timers. Medfield is the platform name, and the chip name is called Penwell + * we treat Medfield/Penwell as a variant of Moorestown. Penwell can be + * identified via MSRs. + */ +enum mrst_cpu_type { + MRST_CPU_CHIP_LINCROFT = 1, + MRST_CPU_CHIP_PENWELL, +}; + +extern enum mrst_cpu_type __mrst_cpu_chip; +static enum mrst_cpu_type mrst_identify_cpu(void) +{ + return __mrst_cpu_chip; +} + +enum mrst_timer_options { + MRST_TIMER_DEFAULT, + MRST_TIMER_APBT_ONLY, + MRST_TIMER_LAPIC_APBT, +}; + +extern enum mrst_timer_options mrst_timer_options; + #define SFI_MTMR_MAX_NUM 8 #define SFI_MRTC_MAX 8 diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 8c7ae431862..986f7790fdb 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -20,6 +20,7 @@ #define _EFER_LMA 10 /* Long mode active (read-only) */ #define _EFER_NX 11 /* No execute enable */ #define _EFER_SVME 12 /* Enable virtualization */ +#define _EFER_LMSLE 13 /* Long Mode Segment Limit Enable */ #define _EFER_FFXSR 14 /* Enable Fast FXSAVE/FXRSTOR */ #define EFER_SCE (1<<_EFER_SCE) @@ -27,6 +28,7 @@ #define EFER_LMA (1<<_EFER_LMA) #define EFER_NX (1<<_EFER_NX) #define EFER_SVME (1<<_EFER_SVME) +#define EFER_LMSLE (1<<_EFER_LMSLE) #define EFER_FFXSR (1<<_EFER_FFXSR) /* Intel MSRs. Some also available on other CPUs */ @@ -94,9 +96,6 @@ #define MSR_IA32_MC0_CTL2 0x00000280 #define MSR_IA32_MCx_CTL2(x) (MSR_IA32_MC0_CTL2 + (x)) -#define CMCI_EN (1ULL << 30) -#define CMCI_THRESHOLD_MASK 0xffffULL - #define MSR_P6_PERFCTR0 0x000000c1 #define MSR_P6_PERFCTR1 0x000000c2 #define MSR_P6_EVNTSEL0 0x00000186 @@ -159,8 +158,6 @@ #define MSR_K7_FID_VID_STATUS 0xc0010042 /* K6 MSRs */ -#define MSR_K6_EFER 0xc0000080 -#define MSR_K6_STAR 0xc0000081 #define MSR_K6_WHCR 0xc0000082 #define MSR_K6_UWCCR 0xc0000085 #define MSR_K6_EPMR 0xc0000086 @@ -224,12 +221,14 @@ #define MSR_IA32_THERM_CONTROL 0x0000019a #define MSR_IA32_THERM_INTERRUPT 0x0000019b -#define THERM_INT_LOW_ENABLE (1 << 0) -#define THERM_INT_HIGH_ENABLE (1 << 1) +#define THERM_INT_HIGH_ENABLE (1 << 0) +#define THERM_INT_LOW_ENABLE (1 << 1) +#define THERM_INT_PLN_ENABLE (1 << 24) #define MSR_IA32_THERM_STATUS 0x0000019c #define THERM_STATUS_PROCHOT (1 << 0) +#define THERM_STATUS_POWER_LIMIT (1 << 10) #define MSR_THERM2_CTL 0x0000019d @@ -239,6 +238,19 @@ #define MSR_IA32_TEMPERATURE_TARGET 0x000001a2 +#define MSR_IA32_ENERGY_PERF_BIAS 0x000001b0 + +#define MSR_IA32_PACKAGE_THERM_STATUS 0x000001b1 + +#define PACKAGE_THERM_STATUS_PROCHOT (1 << 0) +#define PACKAGE_THERM_STATUS_POWER_LIMIT (1 << 10) + +#define MSR_IA32_PACKAGE_THERM_INTERRUPT 0x000001b2 + +#define PACKAGE_THERM_INT_HIGH_ENABLE (1 << 0) +#define PACKAGE_THERM_INT_LOW_ENABLE (1 << 1) +#define PACKAGE_THERM_INT_PLN_ENABLE (1 << 24) + /* MISC_ENABLE bits: architectural */ #define MSR_IA32_MISC_ENABLE_FAST_STRING (1ULL << 0) #define MSR_IA32_MISC_ENABLE_TCC (1ULL << 1) diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h index c5bc4c2d33f..084ef95274c 100644 --- a/arch/x86/include/asm/msr.h +++ b/arch/x86/include/asm/msr.h @@ -148,8 +148,8 @@ static inline unsigned long long native_read_pmc(int counter) #define rdmsr(msr, val1, val2) \ do { \ u64 __val = native_read_msr((msr)); \ - (val1) = (u32)__val; \ - (val2) = (u32)(__val >> 32); \ + (void)((val1) = (u32)__val); \ + (void)((val2) = (u32)(__val >> 32)); \ } while (0) static inline void wrmsr(unsigned msr, unsigned low, unsigned high) diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h index 93da9c3f334..932f0f86b4b 100644 --- a/arch/x86/include/asm/nmi.h +++ b/arch/x86/include/asm/nmi.h @@ -17,7 +17,9 @@ int do_nmi_callback(struct pt_regs *regs, int cpu); extern void die_nmi(char *str, struct pt_regs *regs, int do_panic); extern int check_nmi_watchdog(void); +#if !defined(CONFIG_LOCKUP_DETECTOR) extern int nmi_watchdog_enabled; +#endif extern int avail_to_resrv_perfctr_nmi_bit(unsigned int); extern int reserve_perfctr_nmi(unsigned int); extern void release_perfctr_nmi(unsigned int); diff --git a/arch/x86/include/asm/olpc_ofw.h b/arch/x86/include/asm/olpc_ofw.h new file mode 100644 index 00000000000..08fde475cb3 --- /dev/null +++ b/arch/x86/include/asm/olpc_ofw.h @@ -0,0 +1,31 @@ +#ifndef _ASM_X86_OLPC_OFW_H +#define _ASM_X86_OLPC_OFW_H + +/* index into the page table containing the entry OFW occupies */ +#define OLPC_OFW_PDE_NR 1022 + +#define OLPC_OFW_SIG 0x2057464F /* aka "OFW " */ + +#ifdef CONFIG_OLPC_OPENFIRMWARE + +/* run an OFW command by calling into the firmware */ +#define olpc_ofw(name, args, res) \ + __olpc_ofw((name), ARRAY_SIZE(args), args, ARRAY_SIZE(res), res) + +extern int __olpc_ofw(const char *name, int nr_args, const void **args, int nr_res, + void **res); + +/* determine whether OFW is available and lives in the proper memory */ +extern void olpc_ofw_detect(void); + +/* install OFW's pde permanently into the kernel's pgtable */ +extern void setup_olpc_ofw_pgd(void); + +#else /* !CONFIG_OLPC_OPENFIRMWARE */ + +static inline void olpc_ofw_detect(void) { } +static inline void setup_olpc_ofw_pgd(void) { } + +#endif /* !CONFIG_OLPC_OPENFIRMWARE */ + +#endif /* _ASM_X86_OLPC_OFW_H */ diff --git a/arch/x86/include/asm/page.h b/arch/x86/include/asm/page.h index 625c3f0e741..8ca82839288 100644 --- a/arch/x86/include/asm/page.h +++ b/arch/x86/include/asm/page.h @@ -37,6 +37,13 @@ static inline void copy_user_page(void *to, void *from, unsigned long vaddr, #define __pa_nodebug(x) __phys_addr_nodebug((unsigned long)(x)) /* __pa_symbol should be used for C visible symbols. This seems to be the official gcc blessed way to do such arithmetic. */ +/* + * We need __phys_reloc_hide() here because gcc may assume that there is no + * overflow during __pa() calculation and can optimize it unexpectedly. + * Newer versions of gcc provide -fno-strict-overflow switch to handle this + * case properly. Once all supported versions of gcc understand it, we can + * remove this Voodoo magic stuff. (i.e. once gcc3.x is deprecated) + */ #define __pa_symbol(x) __pa(__phys_reloc_hide((unsigned long)(x))) #define __va(x) ((void *)((unsigned long)(x)+PAGE_OFFSET)) diff --git a/arch/x86/include/asm/pci_x86.h b/arch/x86/include/asm/pci_x86.h index cd2a31dc5fb..49c7219826f 100644 --- a/arch/x86/include/asm/pci_x86.h +++ b/arch/x86/include/asm/pci_x86.h @@ -30,6 +30,7 @@ #define PCI_HAS_IO_ECS 0x40000 #define PCI_NOASSIGN_ROMS 0x80000 #define PCI_ROOT_NO_CRS 0x100000 +#define PCI_NOASSIGN_BARS 0x200000 extern unsigned int pci_probe; extern unsigned long pirq_table_addr; diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 254883d0c7e..6e742cc4251 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -68,8 +68,9 @@ union cpuid10_eax { union cpuid10_edx { struct { - unsigned int num_counters_fixed:4; - unsigned int reserved:28; + unsigned int num_counters_fixed:5; + unsigned int bit_width_fixed:8; + unsigned int reserved:19; } split; unsigned int full; }; @@ -140,6 +141,19 @@ extern unsigned long perf_instruction_pointer(struct pt_regs *regs); extern unsigned long perf_misc_flags(struct pt_regs *regs); #define perf_misc_flags(regs) perf_misc_flags(regs) +#include <asm/stacktrace.h> + +/* + * We abuse bit 3 from flags to pass exact information, see perf_misc_flags + * and the comment with PERF_EFLAGS_EXACT. + */ +#define perf_arch_fetch_caller_regs(regs, __ip) { \ + (regs)->ip = (__ip); \ + (regs)->bp = caller_frame_pointer(); \ + (regs)->cs = __KERNEL_CS; \ + regs->flags = 0; \ +} + #else static inline void init_hw_perf_events(void) { } static inline void perf_events_lapic_init(void) { } diff --git a/arch/x86/include/asm/perf_event_p4.h b/arch/x86/include/asm/perf_event_p4.h index 64a8ebff06f..def500776b1 100644 --- a/arch/x86/include/asm/perf_event_p4.h +++ b/arch/x86/include/asm/perf_event_p4.h @@ -19,7 +19,6 @@ #define ARCH_P4_RESERVED_ESCR (2) /* IQ_ESCR(0,1) not always present */ #define ARCH_P4_MAX_ESCR (ARCH_P4_TOTAL_ESCR - ARCH_P4_RESERVED_ESCR) #define ARCH_P4_MAX_CCCR (18) -#define ARCH_P4_MAX_COUNTER (ARCH_P4_MAX_CCCR / 2) #define P4_ESCR_EVENT_MASK 0x7e000000U #define P4_ESCR_EVENT_SHIFT 25 @@ -71,10 +70,6 @@ #define P4_CCCR_THRESHOLD(v) ((v) << P4_CCCR_THRESHOLD_SHIFT) #define P4_CCCR_ESEL(v) ((v) << P4_CCCR_ESCR_SELECT_SHIFT) -/* Custom bits in reerved CCCR area */ -#define P4_CCCR_CACHE_OPS_MASK 0x0000003fU - - /* Non HT mask */ #define P4_CCCR_MASK \ (P4_CCCR_OVF | \ @@ -106,8 +101,7 @@ * ESCR and CCCR but rather an only packed value should * be unpacked and written to a proper addresses * - * the base idea is to pack as much info as - * possible + * the base idea is to pack as much info as possible */ #define p4_config_pack_escr(v) (((u64)(v)) << 32) #define p4_config_pack_cccr(v) (((u64)(v)) & 0xffffffffULL) @@ -130,8 +124,6 @@ t; \ }) -#define p4_config_unpack_cache_event(v) (((u64)(v)) & P4_CCCR_CACHE_OPS_MASK) - #define P4_CONFIG_HT_SHIFT 63 #define P4_CONFIG_HT (1ULL << P4_CONFIG_HT_SHIFT) @@ -214,6 +206,12 @@ static inline u32 p4_default_escr_conf(int cpu, int exclude_os, int exclude_usr) return escr; } +/* + * This are the events which should be used in "Event Select" + * field of ESCR register, they are like unique keys which allow + * the kernel to determinate which CCCR and COUNTER should be + * used to track an event + */ enum P4_EVENTS { P4_EVENT_TC_DELIVER_MODE, P4_EVENT_BPU_FETCH_REQUEST, @@ -561,7 +559,7 @@ enum P4_EVENT_OPCODES { * a caller should use P4_ESCR_EMASK_NAME helper to * pick the EventMask needed, for example * - * P4_ESCR_EMASK_NAME(P4_EVENT_TC_DELIVER_MODE, DD) + * P4_ESCR_EMASK_BIT(P4_EVENT_TC_DELIVER_MODE, DD) */ enum P4_ESCR_EMASKS { P4_GEN_ESCR_EMASK(P4_EVENT_TC_DELIVER_MODE, DD, 0), @@ -753,43 +751,50 @@ enum P4_ESCR_EMASKS { P4_GEN_ESCR_EMASK(P4_EVENT_INSTR_COMPLETED, BOGUS, 1), }; -/* P4 PEBS: stale for a while */ -#define P4_PEBS_METRIC_MASK 0x00001fffU -#define P4_PEBS_UOB_TAG 0x01000000U -#define P4_PEBS_ENABLE 0x02000000U - -/* Replay metrics for MSR_IA32_PEBS_ENABLE and MSR_P4_PEBS_MATRIX_VERT */ -#define P4_PEBS__1stl_cache_load_miss_retired 0x3000001 -#define P4_PEBS__2ndl_cache_load_miss_retired 0x3000002 -#define P4_PEBS__dtlb_load_miss_retired 0x3000004 -#define P4_PEBS__dtlb_store_miss_retired 0x3000004 -#define P4_PEBS__dtlb_all_miss_retired 0x3000004 -#define P4_PEBS__tagged_mispred_branch 0x3018000 -#define P4_PEBS__mob_load_replay_retired 0x3000200 -#define P4_PEBS__split_load_retired 0x3000400 -#define P4_PEBS__split_store_retired 0x3000400 - -#define P4_VERT__1stl_cache_load_miss_retired 0x0000001 -#define P4_VERT__2ndl_cache_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_load_miss_retired 0x0000001 -#define P4_VERT__dtlb_store_miss_retired 0x0000002 -#define P4_VERT__dtlb_all_miss_retired 0x0000003 -#define P4_VERT__tagged_mispred_branch 0x0000010 -#define P4_VERT__mob_load_replay_retired 0x0000001 -#define P4_VERT__split_load_retired 0x0000001 -#define P4_VERT__split_store_retired 0x0000002 - -enum P4_CACHE_EVENTS { - P4_CACHE__NONE, - - P4_CACHE__1stl_cache_load_miss_retired, - P4_CACHE__2ndl_cache_load_miss_retired, - P4_CACHE__dtlb_load_miss_retired, - P4_CACHE__dtlb_store_miss_retired, - P4_CACHE__itlb_reference_hit, - P4_CACHE__itlb_reference_miss, - - P4_CACHE__MAX +/* + * P4 PEBS specifics (Replay Event only) + * + * Format (bits): + * 0-6: metric from P4_PEBS_METRIC enum + * 7 : reserved + * 8 : reserved + * 9-11 : reserved + * + * Note we have UOP and PEBS bits reserved for now + * just in case if we will need them once + */ +#define P4_PEBS_CONFIG_ENABLE (1 << 7) +#define P4_PEBS_CONFIG_UOP_TAG (1 << 8) +#define P4_PEBS_CONFIG_METRIC_MASK 0x3f +#define P4_PEBS_CONFIG_MASK 0xff + +/* + * mem: Only counters MSR_IQ_COUNTER4 (16) and + * MSR_IQ_COUNTER5 (17) are allowed for PEBS sampling + */ +#define P4_PEBS_ENABLE 0x02000000U +#define P4_PEBS_ENABLE_UOP_TAG 0x01000000U + +#define p4_config_unpack_metric(v) (((u64)(v)) & P4_PEBS_CONFIG_METRIC_MASK) +#define p4_config_unpack_pebs(v) (((u64)(v)) & P4_PEBS_CONFIG_MASK) + +#define p4_config_pebs_has(v, mask) (p4_config_unpack_pebs(v) & (mask)) + +enum P4_PEBS_METRIC { + P4_PEBS_METRIC__none, + + P4_PEBS_METRIC__1stl_cache_load_miss_retired, + P4_PEBS_METRIC__2ndl_cache_load_miss_retired, + P4_PEBS_METRIC__dtlb_load_miss_retired, + P4_PEBS_METRIC__dtlb_store_miss_retired, + P4_PEBS_METRIC__dtlb_all_miss_retired, + P4_PEBS_METRIC__tagged_mispred_branch, + P4_PEBS_METRIC__mob_load_replay_retired, + P4_PEBS_METRIC__split_load_retired, + P4_PEBS_METRIC__split_store_retired, + + P4_PEBS_METRIC__max }; #endif /* PERF_EVENT_P4_H */ + diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index 181be528c61..076052cd62b 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -126,8 +126,8 @@ static inline int pgd_large(pgd_t pgd) { return 0; } /* x86-64 always has all page tables mapped. */ #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) #define pte_offset_map_nested(dir, address) pte_offset_kernel((dir), (address)) -#define pte_unmap(pte) /* NOP */ -#define pte_unmap_nested(pte) /* NOP */ +#define pte_unmap(pte) ((void)(pte))/* NOP */ +#define pte_unmap_nested(pte) ((void)(pte)) /* NOP */ #define update_mmu_cache(vma, address, ptep) do { } while (0) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 7e5c6a60b8e..325b7bdbeba 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -762,6 +762,7 @@ extern void init_c1e_mask(void); extern unsigned long boot_option_idle_override; extern unsigned long idle_halt; extern unsigned long idle_nomwait; +extern bool c1e_detected; /* * on systems with caches, caches must be flashed as the absolute @@ -1025,4 +1026,24 @@ unsigned long calc_aperfmperf_ratio(struct aperfmperf *old, return ratio; } +/* + * AMD errata checking + */ +#ifdef CONFIG_CPU_SUP_AMD +extern const int amd_erratum_383[]; +extern const int amd_erratum_400[]; +extern bool cpu_has_amd_erratum(const int *); + +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +#else +#define cpu_has_amd_erratum(x) (false) +#endif /* CONFIG_CPU_SUP_AMD */ + #endif /* _ASM_X86_PROCESSOR_H */ diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h index 64cf2d24fad..6c7fc25f2c3 100644 --- a/arch/x86/include/asm/required-features.h +++ b/arch/x86/include/asm/required-features.h @@ -84,5 +84,7 @@ #define REQUIRED_MASK5 0 #define REQUIRED_MASK6 0 #define REQUIRED_MASK7 0 +#define REQUIRED_MASK8 0 +#define REQUIRED_MASK9 0 #endif /* _ASM_X86_REQUIRED_FEATURES_H */ diff --git a/arch/x86/include/asm/rwsem.h b/arch/x86/include/asm/rwsem.h index 606ede12697..d1e41b0f9b6 100644 --- a/arch/x86/include/asm/rwsem.h +++ b/arch/x86/include/asm/rwsem.h @@ -118,7 +118,7 @@ static inline void __down_read(struct rw_semaphore *sem) { asm volatile("# beginning down_read\n\t" LOCK_PREFIX _ASM_INC "(%1)\n\t" - /* adds 0x00000001, returns the old value */ + /* adds 0x00000001 */ " jns 1f\n" " call call_rwsem_down_read_failed\n" "1:\n\t" @@ -156,11 +156,9 @@ static inline int __down_read_trylock(struct rw_semaphore *sem) static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) { rwsem_count_t tmp; - - tmp = RWSEM_ACTIVE_WRITE_BIAS; asm volatile("# beginning down_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* subtract 0x0000ffff, returns the old value */ + /* adds 0xffff0001, returns the old value */ " test %1,%1\n\t" /* was the count 0 before? */ " jz 1f\n" @@ -168,7 +166,7 @@ static inline void __down_write_nested(struct rw_semaphore *sem, int subclass) "1:\n" "# ending down_write" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (RWSEM_ACTIVE_WRITE_BIAS) : "memory", "cc"); } @@ -195,16 +193,16 @@ static inline int __down_write_trylock(struct rw_semaphore *sem) */ static inline void __up_read(struct rw_semaphore *sem) { - rwsem_count_t tmp = -RWSEM_ACTIVE_READ_BIAS; + rwsem_count_t tmp; asm volatile("# beginning __up_read\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" /* subtracts 1, returns the old value */ " jns 1f\n\t" - " call call_rwsem_wake\n" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n" "# ending __up_read\n" : "+m" (sem->count), "=d" (tmp) - : "a" (sem), "1" (tmp) + : "a" (sem), "1" (-RWSEM_ACTIVE_READ_BIAS) : "memory", "cc"); } @@ -216,10 +214,9 @@ static inline void __up_write(struct rw_semaphore *sem) rwsem_count_t tmp; asm volatile("# beginning __up_write\n\t" LOCK_PREFIX " xadd %1,(%2)\n\t" - /* tries to transition - 0xffff0001 -> 0x00000000 */ - " jz 1f\n" - " call call_rwsem_wake\n" + /* subtracts 0xffff0001, returns the old value */ + " jns 1f\n\t" + " call call_rwsem_wake\n" /* expects old value in %edx */ "1:\n\t" "# ending __up_write\n" : "+m" (sem->count), "=d" (tmp) diff --git a/arch/x86/include/asm/scatterlist.h b/arch/x86/include/asm/scatterlist.h index fb0b1874396..4240878b9d7 100644 --- a/arch/x86/include/asm/scatterlist.h +++ b/arch/x86/include/asm/scatterlist.h @@ -3,7 +3,6 @@ #include <asm-generic/scatterlist.h> -#define ISA_DMA_THRESHOLD (0x00ffffff) #define ARCH_HAS_SG_CHAIN #endif /* _ASM_X86_SCATTERLIST_H */ diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h index 86b1506f417..ef292c792d7 100644 --- a/arch/x86/include/asm/setup.h +++ b/arch/x86/include/asm/setup.h @@ -82,7 +82,7 @@ void *extend_brk(size_t size, size_t align); * executable.) */ #define RESERVE_BRK(name,sz) \ - static void __section(.discard) __used \ + static void __section(.discard.text) __used \ __brk_reservation_fn_##name##__(void) { \ asm volatile ( \ ".pushsection .brk_reservation,\"aw\",@nobits;" \ diff --git a/arch/x86/include/asm/stacktrace.h b/arch/x86/include/asm/stacktrace.h index 4dab78edbad..2b16a2ad23d 100644 --- a/arch/x86/include/asm/stacktrace.h +++ b/arch/x86/include/asm/stacktrace.h @@ -1,6 +1,13 @@ +/* + * Copyright (C) 1991, 1992 Linus Torvalds + * Copyright (C) 2000, 2001, 2002 Andi Kleen, SuSE Labs + */ + #ifndef _ASM_X86_STACKTRACE_H #define _ASM_X86_STACKTRACE_H +#include <linux/uaccess.h> + extern int kstack_depth_to_print; struct thread_info; @@ -42,4 +49,46 @@ void dump_trace(struct task_struct *tsk, struct pt_regs *regs, unsigned long *stack, unsigned long bp, const struct stacktrace_ops *ops, void *data); +#ifdef CONFIG_X86_32 +#define STACKSLOTS_PER_LINE 8 +#define get_bp(bp) asm("movl %%ebp, %0" : "=r" (bp) :) +#else +#define STACKSLOTS_PER_LINE 4 +#define get_bp(bp) asm("movq %%rbp, %0" : "=r" (bp) :) +#endif + +extern void +show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *stack, unsigned long bp, char *log_lvl); + +extern void +show_stack_log_lvl(struct task_struct *task, struct pt_regs *regs, + unsigned long *sp, unsigned long bp, char *log_lvl); + +extern unsigned int code_bytes; + +/* The form of the top of the frame on the stack */ +struct stack_frame { + struct stack_frame *next_frame; + unsigned long return_address; +}; + +struct stack_frame_ia32 { + u32 next_frame; + u32 return_address; +}; + +static inline unsigned long caller_frame_pointer(void) +{ + struct stack_frame *frame; + + get_bp(frame); + +#ifdef CONFIG_FRAME_POINTER + frame = frame->next_frame; +#endif + + return (unsigned long)frame; +} + #endif /* _ASM_X86_STACKTRACE_H */ diff --git a/arch/x86/include/asm/sys_ia32.h b/arch/x86/include/asm/sys_ia32.h index 3ad421784ae..cb238526a9f 100644 --- a/arch/x86/include/asm/sys_ia32.h +++ b/arch/x86/include/asm/sys_ia32.h @@ -18,13 +18,13 @@ #include <asm/ia32.h> /* ia32/sys_ia32.c */ -asmlinkage long sys32_truncate64(char __user *, unsigned long, unsigned long); +asmlinkage long sys32_truncate64(const char __user *, unsigned long, unsigned long); asmlinkage long sys32_ftruncate64(unsigned int, unsigned long, unsigned long); -asmlinkage long sys32_stat64(char __user *, struct stat64 __user *); -asmlinkage long sys32_lstat64(char __user *, struct stat64 __user *); +asmlinkage long sys32_stat64(const char __user *, struct stat64 __user *); +asmlinkage long sys32_lstat64(const char __user *, struct stat64 __user *); asmlinkage long sys32_fstat64(unsigned int, struct stat64 __user *); -asmlinkage long sys32_fstatat(unsigned int, char __user *, +asmlinkage long sys32_fstatat(unsigned int, const char __user *, struct stat64 __user *, int); struct mmap_arg_struct32; asmlinkage long sys32_mmap(struct mmap_arg_struct32 __user *); @@ -49,12 +49,12 @@ asmlinkage long sys32_rt_sigpending(compat_sigset_t __user *, compat_size_t); asmlinkage long sys32_rt_sigqueueinfo(int, int, compat_siginfo_t __user *); asmlinkage long sys32_pread(unsigned int, char __user *, u32, u32, u32); -asmlinkage long sys32_pwrite(unsigned int, char __user *, u32, u32, u32); +asmlinkage long sys32_pwrite(unsigned int, const char __user *, u32, u32, u32); asmlinkage long sys32_personality(unsigned long); asmlinkage long sys32_sendfile(int, int, compat_off_t __user *, s32); -asmlinkage long sys32_execve(char __user *, compat_uptr_t __user *, +asmlinkage long sys32_execve(const char __user *, compat_uptr_t __user *, compat_uptr_t __user *, struct pt_regs *); asmlinkage long sys32_clone(unsigned int, unsigned int, struct pt_regs *); @@ -80,4 +80,7 @@ asmlinkage long sys32_rt_sigreturn(struct pt_regs *); /* ia32/ipc32.c */ asmlinkage long sys32_ipc(u32, int, int, int, compat_uptr_t, u32); + +asmlinkage long sys32_fanotify_mark(int, unsigned int, u32, u32, int, + const char __user *); #endif /* _ASM_X86_SYS_IA32_H */ diff --git a/arch/x86/include/asm/syscalls.h b/arch/x86/include/asm/syscalls.h index 5c044b43e9a..feb2ff9bfc2 100644 --- a/arch/x86/include/asm/syscalls.h +++ b/arch/x86/include/asm/syscalls.h @@ -23,7 +23,7 @@ long sys_iopl(unsigned int, struct pt_regs *); /* kernel/process.c */ int sys_fork(struct pt_regs *); int sys_vfork(struct pt_regs *); -long sys_execve(char __user *, char __user * __user *, +long sys_execve(const char __user *, char __user * __user *, char __user * __user *, struct pt_regs *); long sys_clone(unsigned long, unsigned long, void __user *, void __user *, struct pt_regs *); diff --git a/arch/x86/include/asm/system.h b/arch/x86/include/asm/system.h index e7f4d33c55e..33ecc3ea878 100644 --- a/arch/x86/include/asm/system.h +++ b/arch/x86/include/asm/system.h @@ -457,4 +457,11 @@ static __always_inline void rdtsc_barrier(void) alternative(ASM_NOP3, "lfence", X86_FEATURE_LFENCE_RDTSC); } +/* + * We handle most unaligned accesses in hardware. On the other hand + * unaligned DMA can be quite expensive on some Nehalem processors. + * + * Based on this we disable the IP header alignment in network drivers. + */ +#define NET_IP_ALIGN 0 #endif /* _ASM_X86_SYSTEM_H */ diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h index beb9b5f8f8a..b766a5e8ba0 100644 --- a/arch/x86/include/asm/unistd_32.h +++ b/arch/x86/include/asm/unistd_32.h @@ -343,10 +343,13 @@ #define __NR_rt_tgsigqueueinfo 335 #define __NR_perf_event_open 336 #define __NR_recvmmsg 337 +#define __NR_fanotify_init 338 +#define __NR_fanotify_mark 339 +#define __NR_prlimit64 340 #ifdef __KERNEL__ -#define NR_syscalls 338 +#define NR_syscalls 341 #define __ARCH_WANT_IPC_PARSE_VERSION #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h index ff4307b0e81..363e9b8a715 100644 --- a/arch/x86/include/asm/unistd_64.h +++ b/arch/x86/include/asm/unistd_64.h @@ -663,6 +663,12 @@ __SYSCALL(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo) __SYSCALL(__NR_perf_event_open, sys_perf_event_open) #define __NR_recvmmsg 299 __SYSCALL(__NR_recvmmsg, sys_recvmmsg) +#define __NR_fanotify_init 300 +__SYSCALL(__NR_fanotify_init, sys_fanotify_init) +#define __NR_fanotify_mark 301 +__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark) +#define __NR_prlimit64 302 +__SYSCALL(__NR_prlimit64, sys_prlimit64) #ifndef __NO_STUBS #define __ARCH_WANT_OLD_READDIR diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h index aa558ac0306..42d412fd8b0 100644 --- a/arch/x86/include/asm/uv/uv_bau.h +++ b/arch/x86/include/asm/uv/uv_bau.h @@ -34,6 +34,7 @@ */ #define UV_ITEMS_PER_DESCRIPTOR 8 +/* the 'throttle' to prevent the hardware stay-busy bug */ #define MAX_BAU_CONCURRENT 3 #define UV_CPUS_PER_ACT_STATUS 32 #define UV_ACT_STATUS_MASK 0x3 @@ -45,10 +46,26 @@ #define UV_DESC_BASE_PNODE_SHIFT 49 #define UV_PAYLOADQ_PNODE_SHIFT 49 #define UV_PTC_BASENAME "sgi_uv/ptc_statistics" +#define UV_BAU_BASENAME "sgi_uv/bau_tunables" +#define UV_BAU_TUNABLES_DIR "sgi_uv" +#define UV_BAU_TUNABLES_FILE "bau_tunables" +#define WHITESPACE " \t\n" #define uv_physnodeaddr(x) ((__pa((unsigned long)(x)) & uv_mmask)) #define UV_ENABLE_INTD_SOFT_ACK_MODE_SHIFT 15 #define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD_SHIFT 16 -#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x000000000bUL +#define UV_INTD_SOFT_ACK_TIMEOUT_PERIOD 0x0000000009UL +/* [19:16] SOFT_ACK timeout period 19: 1 is urgency 7 17:16 1 is multiplier */ +#define BAU_MISC_CONTROL_MULT_MASK 3 + +#define UVH_AGING_PRESCALE_SEL 0x000000b000UL +/* [30:28] URGENCY_7 an index into a table of times */ +#define BAU_URGENCY_7_SHIFT 28 +#define BAU_URGENCY_7_MASK 7 + +#define UVH_TRANSACTION_TIMEOUT 0x000000b200UL +/* [45:40] BAU - BAU transaction timeout select - a multiplier */ +#define BAU_TRANS_SHIFT 40 +#define BAU_TRANS_MASK 0x3f /* * bits in UVH_LB_BAU_SB_ACTIVATION_STATUS_0/1 @@ -59,24 +76,21 @@ #define DESC_STATUS_SOURCE_TIMEOUT 3 /* - * source side threshholds at which message retries print a warning - */ -#define SOURCE_TIMEOUT_LIMIT 20 -#define DESTINATION_TIMEOUT_LIMIT 20 - -/* - * misc. delays, in microseconds + * delay for 'plugged' timeout retries, in microseconds */ -#define THROTTLE_DELAY 10 -#define TIMEOUT_DELAY 10 -#define BIOS_TO 1000 -/* BIOS is assumed to set the destination timeout to 1003520 nanoseconds */ +#define PLUGGED_DELAY 10 /* * threshholds at which to use IPI to free resources */ +/* after this # consecutive 'plugged' timeouts, use IPI to release resources */ #define PLUGSB4RESET 100 -#define TIMEOUTSB4RESET 100 +/* after this many consecutive timeouts, use IPI to release resources */ +#define TIMEOUTSB4RESET 1 +/* at this number uses of IPI to release resources, giveup the request */ +#define IPI_RESET_LIMIT 1 +/* after this # consecutive successes, bump up the throttle if it was lowered */ +#define COMPLETE_THRESHOLD 5 /* * number of entries in the destination side payload queue @@ -96,6 +110,13 @@ #define FLUSH_COMPLETE 4 /* + * tuning the action when the numalink network is extremely delayed + */ +#define CONGESTED_RESPONSE_US 1000 /* 'long' response time, in microseconds */ +#define CONGESTED_REPS 10 /* long delays averaged over this many broadcasts */ +#define CONGESTED_PERIOD 30 /* time for the bau to be disabled, in seconds */ + +/* * Distribution: 32 bytes (256 bits) (bytes 0-0x1f of descriptor) * If the 'multilevel' flag in the header portion of the descriptor * has been set to 0, then endpoint multi-unicast mode is selected. @@ -300,37 +321,16 @@ struct bau_payload_queue_entry { /* bytes 24-31 */ }; -/* - * one per-cpu; to locate the software tables - */ -struct bau_control { - struct bau_desc *descriptor_base; +struct msg_desc { + struct bau_payload_queue_entry *msg; + int msg_slot; + int sw_ack_slot; struct bau_payload_queue_entry *va_queue_first; struct bau_payload_queue_entry *va_queue_last; - struct bau_payload_queue_entry *bau_msg_head; - struct bau_control *uvhub_master; - struct bau_control *socket_master; - unsigned long timeout_interval; - atomic_t active_descriptor_count; - int max_concurrent; - int max_concurrent_constant; - int retry_message_scans; - int plugged_tries; - int timeout_tries; - int ipi_attempts; - int conseccompletes; - short cpu; - short uvhub_cpu; - short uvhub; - short cpus_in_socket; - short cpus_in_uvhub; - unsigned short message_number; - unsigned short uvhub_quiesce; - short socket_acknowledge_count[DEST_Q_SIZE]; - cycles_t send_message; - spinlock_t masks_lock; - spinlock_t uvhub_lock; - spinlock_t queue_lock; +}; + +struct reset_args { + int sender; }; /* @@ -344,18 +344,25 @@ struct ptc_stats { unsigned long s_dtimeout; /* destination side timeouts */ unsigned long s_time; /* time spent in sending side */ unsigned long s_retriesok; /* successful retries */ - unsigned long s_ntargcpu; /* number of cpus targeted */ - unsigned long s_ntarguvhub; /* number of uvhubs targeted */ - unsigned long s_ntarguvhub16; /* number of times >= 16 target hubs */ - unsigned long s_ntarguvhub8; /* number of times >= 8 target hubs */ - unsigned long s_ntarguvhub4; /* number of times >= 4 target hubs */ - unsigned long s_ntarguvhub2; /* number of times >= 2 target hubs */ - unsigned long s_ntarguvhub1; /* number of times == 1 target hub */ + unsigned long s_ntargcpu; /* total number of cpu's targeted */ + unsigned long s_ntargself; /* times the sending cpu was targeted */ + unsigned long s_ntarglocals; /* targets of cpus on the local blade */ + unsigned long s_ntargremotes; /* targets of cpus on remote blades */ + unsigned long s_ntarglocaluvhub; /* targets of the local hub */ + unsigned long s_ntargremoteuvhub; /* remotes hubs targeted */ + unsigned long s_ntarguvhub; /* total number of uvhubs targeted */ + unsigned long s_ntarguvhub16; /* number of times target hubs >= 16*/ + unsigned long s_ntarguvhub8; /* number of times target hubs >= 8 */ + unsigned long s_ntarguvhub4; /* number of times target hubs >= 4 */ + unsigned long s_ntarguvhub2; /* number of times target hubs >= 2 */ + unsigned long s_ntarguvhub1; /* number of times target hubs == 1 */ unsigned long s_resets_plug; /* ipi-style resets from plug state */ unsigned long s_resets_timeout; /* ipi-style resets from timeouts */ unsigned long s_busy; /* status stayed busy past s/w timer */ unsigned long s_throttles; /* waits in throttle */ unsigned long s_retry_messages; /* retry broadcasts */ + unsigned long s_bau_reenabled; /* for bau enable/disable */ + unsigned long s_bau_disabled; /* for bau enable/disable */ /* destination statistics */ unsigned long d_alltlb; /* times all tlb's on this cpu were flushed */ unsigned long d_onetlb; /* times just one tlb on this cpu was flushed */ @@ -370,6 +377,52 @@ struct ptc_stats { unsigned long d_rcanceled; /* number of messages canceled by resets */ }; +/* + * one per-cpu; to locate the software tables + */ +struct bau_control { + struct bau_desc *descriptor_base; + struct bau_payload_queue_entry *va_queue_first; + struct bau_payload_queue_entry *va_queue_last; + struct bau_payload_queue_entry *bau_msg_head; + struct bau_control *uvhub_master; + struct bau_control *socket_master; + struct ptc_stats *statp; + unsigned long timeout_interval; + unsigned long set_bau_on_time; + atomic_t active_descriptor_count; + int plugged_tries; + int timeout_tries; + int ipi_attempts; + int conseccompletes; + int baudisabled; + int set_bau_off; + short cpu; + short uvhub_cpu; + short uvhub; + short cpus_in_socket; + short cpus_in_uvhub; + unsigned short message_number; + unsigned short uvhub_quiesce; + short socket_acknowledge_count[DEST_Q_SIZE]; + cycles_t send_message; + spinlock_t uvhub_lock; + spinlock_t queue_lock; + /* tunables */ + int max_bau_concurrent; + int max_bau_concurrent_constant; + int plugged_delay; + int plugsb4reset; + int timeoutsb4reset; + int ipi_reset_limit; + int complete_threshold; + int congested_response_us; + int congested_reps; + int congested_period; + cycles_t period_time; + long period_requests; +}; + static inline int bau_uvhub_isset(int uvhub, struct bau_target_uvhubmask *dstp) { return constant_test_bit(uvhub, &dstp->bits[0]); diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h index 9e6779f7cf2..9f0cbd987d5 100644 --- a/arch/x86/include/asm/vmx.h +++ b/arch/x86/include/asm/vmx.h @@ -257,6 +257,7 @@ enum vmcs_field { #define EXIT_REASON_IO_INSTRUCTION 30 #define EXIT_REASON_MSR_READ 31 #define EXIT_REASON_MSR_WRITE 32 +#define EXIT_REASON_INVALID_STATE 33 #define EXIT_REASON_MWAIT_INSTRUCTION 36 #define EXIT_REASON_MONITOR_INSTRUCTION 39 #define EXIT_REASON_PAUSE_INSTRUCTION 40 @@ -266,6 +267,7 @@ enum vmcs_field { #define EXIT_REASON_EPT_VIOLATION 48 #define EXIT_REASON_EPT_MISCONFIG 49 #define EXIT_REASON_WBINVD 54 +#define EXIT_REASON_XSETBV 55 /* * Interruption-information format @@ -375,6 +377,9 @@ enum vmcs_field { #define VMX_EPT_EXTENT_CONTEXT_BIT (1ull << 25) #define VMX_EPT_EXTENT_GLOBAL_BIT (1ull << 26) +#define VMX_VPID_EXTENT_SINGLE_CONTEXT_BIT (1ull << 9) /* (41 - 32) */ +#define VMX_VPID_EXTENT_GLOBAL_CONTEXT_BIT (1ull << 10) /* (42 - 32) */ + #define VMX_EPT_DEFAULT_GAW 3 #define VMX_EPT_MAX_GAW 0x4 #define VMX_EPT_MT_EPTE_SHIFT 3 diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index 9c371e4a9fa..7fda040a76c 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -417,6 +417,12 @@ HYPERVISOR_nmi_op(unsigned long op, unsigned long arg) return _hypercall2(int, nmi_op, op, arg); } +static inline unsigned long __must_check +HYPERVISOR_hvm_op(int op, void *arg) +{ + return _hypercall2(unsigned long, hvm_op, op, arg); +} + static inline void MULTI_fpu_taskswitch(struct multicall_entry *mcl, int set) { diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 018a0a40079..bf5f7d32bd0 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -112,13 +112,9 @@ static inline xpaddr_t machine_to_phys(xmaddr_t machine) */ static inline unsigned long mfn_to_local_pfn(unsigned long mfn) { - extern unsigned long max_mapnr; unsigned long pfn = mfn_to_pfn(mfn); - if ((pfn < max_mapnr) - && !xen_feature(XENFEAT_auto_translated_physmap) - && (get_phys_to_machine(pfn) != mfn)) - return max_mapnr; /* force !pfn_valid() */ - /* XXX fixme; not true with sparsemem */ + if (get_phys_to_machine(pfn) != mfn) + return -1; /* force !pfn_valid() */ return pfn; } diff --git a/arch/x86/include/asm/xen/swiotlb-xen.h b/arch/x86/include/asm/xen/swiotlb-xen.h new file mode 100644 index 00000000000..1be1ab7d6a4 --- /dev/null +++ b/arch/x86/include/asm/xen/swiotlb-xen.h @@ -0,0 +1,14 @@ +#ifndef _ASM_X86_SWIOTLB_XEN_H +#define _ASM_X86_SWIOTLB_XEN_H + +#ifdef CONFIG_SWIOTLB_XEN +extern int xen_swiotlb; +extern int __init pci_xen_swiotlb_detect(void); +extern void __init pci_xen_swiotlb_init(void); +#else +#define xen_swiotlb (0) +static inline int __init pci_xen_swiotlb_detect(void) { return 0; } +static inline void __init pci_xen_swiotlb_init(void) { } +#endif + +#endif /* _ASM_X86_SWIOTLB_XEN_H */ diff --git a/arch/x86/include/asm/xsave.h b/arch/x86/include/asm/xsave.h index 2c4390cae22..c6ce2452f10 100644 --- a/arch/x86/include/asm/xsave.h +++ b/arch/x86/include/asm/xsave.h @@ -3,7 +3,8 @@ #include <linux/types.h> #include <asm/processor.h> -#include <asm/i387.h> + +#define XSTATE_CPUID 0x0000000d #define XSTATE_FP 0x1 #define XSTATE_SSE 0x2 @@ -13,6 +14,12 @@ #define FXSAVE_SIZE 512 +#define XSAVE_HDR_SIZE 64 +#define XSAVE_HDR_OFFSET FXSAVE_SIZE + +#define XSAVE_YMM_SIZE 256 +#define XSAVE_YMM_OFFSET (XSAVE_HDR_SIZE + XSAVE_HDR_OFFSET) + /* * These are the features that the OS can handle currently. */ @@ -26,10 +33,8 @@ extern unsigned int xstate_size; extern u64 pcntxt_mask; -extern struct xsave_struct *init_xstate_buf; extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern void xsave_cntxt_init(void); extern void xsave_init(void); extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); extern int init_fpu(struct task_struct *child); @@ -59,6 +64,16 @@ static inline int fpu_xrstor_checking(struct fpu *fpu) static inline int xsave_user(struct xsave_struct __user *buf) { int err; + + /* + * Clear the xsave header first, so that reserved fields are + * initialized to zero. + */ + err = __clear_user(&buf->xsave_hdr, + sizeof(struct xsave_hdr_struct)); + if (unlikely(err)) + return -EFAULT; + __asm__ __volatile__("1: .byte " REX_PREFIX "0x0f,0xae,0x27\n" "2:\n" ".section .fixup,\"ax\"\n" @@ -111,12 +126,25 @@ static inline void xrstor_state(struct xsave_struct *fx, u64 mask) : "memory"); } +static inline void xsave_state(struct xsave_struct *fx, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + + asm volatile(".byte " REX_PREFIX "0x0f,0xae,0x27\n\t" + : : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); +} + static inline void fpu_xsave(struct fpu *fpu) { /* 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" (&(fpu->state->xsave)), - "a" (-1), "d"(-1) : "memory"); + alternative_input( + ".byte " REX_PREFIX "0x0f,0xae,0x27", + ".byte " REX_PREFIX "0x0f,0xae,0x37", + X86_FEATURE_XSAVEOPT, + [fx] "D" (&fpu->state->xsave), "a" (-1), "d" (-1) : + "memory"); } #endif |