From 669ebabb79906302ba6e6922a683893788a134e8 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Tue, 28 Apr 2015 08:41:33 +0200 Subject: x86/fpu: Rename fpu/xsave.h to fpu/xstate.h 'xsave' is an x86 instruction name to most people - but xsave.h is about a lot more than just the XSAVE instruction: it includes definitions and support, both internal and external, related to xstate and xfeatures support. As a first step in cleaning up the various xstate uses rename this header to 'fpu/xstate.h' to better reflect what this header file is about. Cc: Andy Lutomirski Cc: Borislav Petkov Cc: Dave Hansen Cc: Fenghua Yu Cc: H. Peter Anvin Cc: Linus Torvalds Cc: Oleg Nesterov Cc: Peter Zijlstra Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- arch/x86/crypto/camellia_aesni_avx2_glue.c | 2 +- arch/x86/crypto/camellia_aesni_avx_glue.c | 2 +- arch/x86/crypto/cast5_avx_glue.c | 2 +- arch/x86/crypto/cast6_avx_glue.c | 2 +- arch/x86/crypto/serpent_avx2_glue.c | 2 +- arch/x86/crypto/serpent_avx_glue.c | 2 +- arch/x86/crypto/sha-mb/sha1_mb.c | 2 +- arch/x86/crypto/sha1_ssse3_glue.c | 2 +- arch/x86/crypto/sha256_ssse3_glue.c | 2 +- arch/x86/crypto/sha512_ssse3_glue.c | 2 +- arch/x86/crypto/twofish_avx_glue.c | 2 +- arch/x86/include/asm/fpu/internal.h | 2 +- arch/x86/include/asm/fpu/xsave.h | 254 ----------------------------- arch/x86/include/asm/fpu/xstate.h | 254 +++++++++++++++++++++++++++++ arch/x86/kvm/cpuid.c | 2 +- 15 files changed, 267 insertions(+), 267 deletions(-) delete mode 100644 arch/x86/include/asm/fpu/xsave.h create mode 100644 arch/x86/include/asm/fpu/xstate.h (limited to 'arch/x86') diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c index 004acd7bb4e0..46484482f267 100644 --- a/arch/x86/crypto/camellia_aesni_avx2_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c index 2f7ead8caf53..0122cd95563a 100644 --- a/arch/x86/crypto/camellia_aesni_avx_glue.c +++ b/arch/x86/crypto/camellia_aesni_avx_glue.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c index 2c3360be6fc8..ca4f32e7a423 100644 --- a/arch/x86/crypto/cast5_avx_glue.c +++ b/arch/x86/crypto/cast5_avx_glue.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #define CAST5_PARALLEL_BLOCKS 16 diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c index a2ec18a56e4f..21d0b845c8c4 100644 --- a/arch/x86/crypto/cast6_avx_glue.c +++ b/arch/x86/crypto/cast6_avx_glue.c @@ -37,7 +37,7 @@ #include #include #include -#include +#include #include #define CAST6_PARALLEL_BLOCKS 8 diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c index 206ec57725a3..aa325fa5c7a6 100644 --- a/arch/x86/crypto/serpent_avx2_glue.c +++ b/arch/x86/crypto/serpent_avx2_glue.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c index 4feb68c9a41f..f66ae85f58fe 100644 --- a/arch/x86/crypto/serpent_avx_glue.c +++ b/arch/x86/crypto/serpent_avx_glue.c @@ -37,7 +37,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/crypto/sha-mb/sha1_mb.c b/arch/x86/crypto/sha-mb/sha1_mb.c index 03ffaf8c2244..6f3f76568bd5 100644 --- a/arch/x86/crypto/sha-mb/sha1_mb.c +++ b/arch/x86/crypto/sha-mb/sha1_mb.c @@ -66,7 +66,7 @@ #include #include #include -#include +#include #include #include #include "sha_mb_ctx.h" diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c index 71ab2b35d5e0..84db12f052e8 100644 --- a/arch/x86/crypto/sha1_ssse3_glue.c +++ b/arch/x86/crypto/sha1_ssse3_glue.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include asmlinkage void sha1_transform_ssse3(u32 *digest, const char *data, diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c index dcbd8ea6eaaf..eb65522f02b8 100644 --- a/arch/x86/crypto/sha256_ssse3_glue.c +++ b/arch/x86/crypto/sha256_ssse3_glue.c @@ -39,7 +39,7 @@ #include #include #include -#include +#include #include asmlinkage void sha256_transform_ssse3(u32 *digest, const char *data, diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c index e8836e0c1098..78914641c72b 100644 --- a/arch/x86/crypto/sha512_ssse3_glue.c +++ b/arch/x86/crypto/sha512_ssse3_glue.c @@ -37,7 +37,7 @@ #include #include #include -#include +#include #include diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c index 3b6c8ba64f81..95434f5b705a 100644 --- a/arch/x86/crypto/twofish_avx_glue.c +++ b/arch/x86/crypto/twofish_avx_glue.c @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/include/asm/fpu/internal.h b/arch/x86/include/asm/fpu/internal.h index 28556c6671c3..8ec785ecce81 100644 --- a/arch/x86/include/asm/fpu/internal.h +++ b/arch/x86/include/asm/fpu/internal.h @@ -17,7 +17,7 @@ #include #include -#include +#include #ifdef CONFIG_X86_64 # include diff --git a/arch/x86/include/asm/fpu/xsave.h b/arch/x86/include/asm/fpu/xsave.h deleted file mode 100644 index 2f2ed322263f..000000000000 --- a/arch/x86/include/asm/fpu/xsave.h +++ /dev/null @@ -1,254 +0,0 @@ -#ifndef __ASM_X86_XSAVE_H -#define __ASM_X86_XSAVE_H - -#include -#include - -#define XSTATE_CPUID 0x0000000d - -#define XSTATE_FP 0x1 -#define XSTATE_SSE 0x2 -#define XSTATE_YMM 0x4 -#define XSTATE_BNDREGS 0x8 -#define XSTATE_BNDCSR 0x10 -#define XSTATE_OPMASK 0x20 -#define XSTATE_ZMM_Hi256 0x40 -#define XSTATE_Hi16_ZMM 0x80 - -/* The highest xstate bit above (of XSTATE_Hi16_ZMM): */ -#define XFEATURES_NR_MAX 8 - -#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) -#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) -/* Bit 63 of XCR0 is reserved for future expansion */ -#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) - -#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) - -/* Supported features which support lazy state saving */ -#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ - | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) - -/* Supported features which require eager state saving */ -#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) - -/* All currently supported features */ -#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) - -#ifdef CONFIG_X86_64 -#define REX_PREFIX "0x48, " -#else -#define REX_PREFIX -#endif - -extern unsigned int xstate_size; -extern u64 xfeatures_mask; -extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; -extern struct xsave_struct init_xstate_ctx; - -extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); - -/* These macros all use (%edi)/(%rdi) as the single memory argument. */ -#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" -#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" -#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" -#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" -#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" - -#define xstate_fault ".section .fixup,\"ax\"\n" \ - "3: movl $-1,%[err]\n" \ - " jmp 2b\n" \ - ".previous\n" \ - _ASM_EXTABLE(1b, 3b) \ - : [err] "=r" (err) - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xsave_state_booting(struct xsave_struct *fx) -{ - u64 mask = -1; - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XSAVES"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XSAVE"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * This function is called only during boot time when x86 caps are not set - * up and alternative can not be used yet. - */ -static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask) -{ - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state != SYSTEM_BOOTING); - - if (boot_cpu_has(X86_FEATURE_XSAVES)) - asm volatile("1:"XRSTORS"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - else - asm volatile("1:"XRSTOR"\n\t" - "2:\n\t" - xstate_fault - : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - return err; -} - -/* - * Save processor xstate to xsave area. - */ -static inline int xsave_state(struct xsave_struct *fx) -{ - u64 mask = -1; - u32 lmask = mask; - u32 hmask = mask >> 32; - int err = 0; - - WARN_ON(system_state == SYSTEM_BOOTING); - - /* - * If xsaves is enabled, xsaves replaces xsaveopt because - * it supports compact format and supervisor states in addition to - * modified optimization in xsaveopt. - * - * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave - * because xsaveopt supports modified optimization which is not - * supported by xsave. - * - * If none of xsaves and xsaveopt is enabled, use xsave. - */ - alternative_input_2( - "1:"XSAVE, - XSAVEOPT, - X86_FEATURE_XSAVEOPT, - XSAVES, - X86_FEATURE_XSAVES, - [fx] "D" (fx), "a" (lmask), "d" (hmask) : - "memory"); - asm volatile("2:\n\t" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Restore processor xstate from xsave area. - */ -static inline int xrstor_state(struct xsave_struct *fx, u64 mask) -{ - int err = 0; - u32 lmask = mask; - u32 hmask = mask >> 32; - - /* - * Use xrstors to restore context if it is enabled. xrstors supports - * compacted format of xsave area which is not supported by xrstor. - */ - alternative_input( - "1: " XRSTOR, - XRSTORS, - X86_FEATURE_XSAVES, - "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) - : "memory"); - - asm volatile("2:\n" - xstate_fault - : "0" (0) - : "memory"); - - return err; -} - -/* - * Restore xstate context for new process during context switch. - */ -static inline int fpu_xrstor_checking(struct xsave_struct *fx) -{ - return xrstor_state(fx, -1); -} - -/* - * Save xstate to user space xsave area. - * - * We don't use modified optimization because xrstor/xrstors might track - * a different application. - * - * We don't use compacted format xsave area for - * backward compatibility for old applications which don't understand - * compacted format of xsave area. - */ -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->header, sizeof(buf->header)); - if (unlikely(err)) - return -EFAULT; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XSAVE"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (buf), "a" (-1), "d" (-1), "0" (0) - : "memory"); - return err; -} - -/* - * Restore xstate from user space xsave area. - */ -static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask) -{ - int err = 0; - struct xsave_struct *xstate = ((__force struct xsave_struct *)buf); - u32 lmask = mask; - u32 hmask = mask >> 32; - - __asm__ __volatile__(ASM_STAC "\n" - "1:"XRSTOR"\n" - "2: " ASM_CLAC "\n" - xstate_fault - : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0) - : "memory"); /* memory required? */ - return err; -} - -void *get_xsave_addr(struct xsave_struct *xsave, int xstate); -void setup_xstate_comp(void); - -#endif diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h new file mode 100644 index 000000000000..2f2ed322263f --- /dev/null +++ b/arch/x86/include/asm/fpu/xstate.h @@ -0,0 +1,254 @@ +#ifndef __ASM_X86_XSAVE_H +#define __ASM_X86_XSAVE_H + +#include +#include + +#define XSTATE_CPUID 0x0000000d + +#define XSTATE_FP 0x1 +#define XSTATE_SSE 0x2 +#define XSTATE_YMM 0x4 +#define XSTATE_BNDREGS 0x8 +#define XSTATE_BNDCSR 0x10 +#define XSTATE_OPMASK 0x20 +#define XSTATE_ZMM_Hi256 0x40 +#define XSTATE_Hi16_ZMM 0x80 + +/* The highest xstate bit above (of XSTATE_Hi16_ZMM): */ +#define XFEATURES_NR_MAX 8 + +#define XSTATE_FPSSE (XSTATE_FP | XSTATE_SSE) +#define XSTATE_AVX512 (XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) +/* Bit 63 of XCR0 is reserved for future expansion */ +#define XSTATE_EXTEND_MASK (~(XSTATE_FPSSE | (1ULL << 63))) + +#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) + +/* Supported features which support lazy state saving */ +#define XSTATE_LAZY (XSTATE_FP | XSTATE_SSE | XSTATE_YMM \ + | XSTATE_OPMASK | XSTATE_ZMM_Hi256 | XSTATE_Hi16_ZMM) + +/* Supported features which require eager state saving */ +#define XSTATE_EAGER (XSTATE_BNDREGS | XSTATE_BNDCSR) + +/* All currently supported features */ +#define XCNTXT_MASK (XSTATE_LAZY | XSTATE_EAGER) + +#ifdef CONFIG_X86_64 +#define REX_PREFIX "0x48, " +#else +#define REX_PREFIX +#endif + +extern unsigned int xstate_size; +extern u64 xfeatures_mask; +extern u64 xstate_fx_sw_bytes[USER_XSTATE_FX_SW_WORDS]; +extern struct xsave_struct init_xstate_ctx; + +extern void update_regset_xstate_info(unsigned int size, u64 xstate_mask); + +/* These macros all use (%edi)/(%rdi) as the single memory argument. */ +#define XSAVE ".byte " REX_PREFIX "0x0f,0xae,0x27" +#define XSAVEOPT ".byte " REX_PREFIX "0x0f,0xae,0x37" +#define XSAVES ".byte " REX_PREFIX "0x0f,0xc7,0x2f" +#define XRSTOR ".byte " REX_PREFIX "0x0f,0xae,0x2f" +#define XRSTORS ".byte " REX_PREFIX "0x0f,0xc7,0x1f" + +#define xstate_fault ".section .fixup,\"ax\"\n" \ + "3: movl $-1,%[err]\n" \ + " jmp 2b\n" \ + ".previous\n" \ + _ASM_EXTABLE(1b, 3b) \ + : [err] "=r" (err) + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline int xsave_state_booting(struct xsave_struct *fx) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XSAVES"\n\t" + "2:\n\t" + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + else + asm volatile("1:"XSAVE"\n\t" + "2:\n\t" + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + return err; +} + +/* + * This function is called only during boot time when x86 caps are not set + * up and alternative can not be used yet. + */ +static inline int xrstor_state_booting(struct xsave_struct *fx, u64 mask) +{ + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state != SYSTEM_BOOTING); + + if (boot_cpu_has(X86_FEATURE_XSAVES)) + asm volatile("1:"XRSTORS"\n\t" + "2:\n\t" + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + else + asm volatile("1:"XRSTOR"\n\t" + "2:\n\t" + xstate_fault + : "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + return err; +} + +/* + * Save processor xstate to xsave area. + */ +static inline int xsave_state(struct xsave_struct *fx) +{ + u64 mask = -1; + u32 lmask = mask; + u32 hmask = mask >> 32; + int err = 0; + + WARN_ON(system_state == SYSTEM_BOOTING); + + /* + * If xsaves is enabled, xsaves replaces xsaveopt because + * it supports compact format and supervisor states in addition to + * modified optimization in xsaveopt. + * + * Otherwise, if xsaveopt is enabled, xsaveopt replaces xsave + * because xsaveopt supports modified optimization which is not + * supported by xsave. + * + * If none of xsaves and xsaveopt is enabled, use xsave. + */ + alternative_input_2( + "1:"XSAVE, + XSAVEOPT, + X86_FEATURE_XSAVEOPT, + XSAVES, + X86_FEATURE_XSAVES, + [fx] "D" (fx), "a" (lmask), "d" (hmask) : + "memory"); + asm volatile("2:\n\t" + xstate_fault + : "0" (0) + : "memory"); + + return err; +} + +/* + * Restore processor xstate from xsave area. + */ +static inline int xrstor_state(struct xsave_struct *fx, u64 mask) +{ + int err = 0; + u32 lmask = mask; + u32 hmask = mask >> 32; + + /* + * Use xrstors to restore context if it is enabled. xrstors supports + * compacted format of xsave area which is not supported by xrstor. + */ + alternative_input( + "1: " XRSTOR, + XRSTORS, + X86_FEATURE_XSAVES, + "D" (fx), "m" (*fx), "a" (lmask), "d" (hmask) + : "memory"); + + asm volatile("2:\n" + xstate_fault + : "0" (0) + : "memory"); + + return err; +} + +/* + * Restore xstate context for new process during context switch. + */ +static inline int fpu_xrstor_checking(struct xsave_struct *fx) +{ + return xrstor_state(fx, -1); +} + +/* + * Save xstate to user space xsave area. + * + * We don't use modified optimization because xrstor/xrstors might track + * a different application. + * + * We don't use compacted format xsave area for + * backward compatibility for old applications which don't understand + * compacted format of xsave area. + */ +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->header, sizeof(buf->header)); + if (unlikely(err)) + return -EFAULT; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XSAVE"\n" + "2: " ASM_CLAC "\n" + xstate_fault + : "D" (buf), "a" (-1), "d" (-1), "0" (0) + : "memory"); + return err; +} + +/* + * Restore xstate from user space xsave area. + */ +static inline int xrestore_user(struct xsave_struct __user *buf, u64 mask) +{ + int err = 0; + struct xsave_struct *xstate = ((__force struct xsave_struct *)buf); + u32 lmask = mask; + u32 hmask = mask >> 32; + + __asm__ __volatile__(ASM_STAC "\n" + "1:"XRSTOR"\n" + "2: " ASM_CLAC "\n" + xstate_fault + : "D" (xstate), "a" (lmask), "d" (hmask), "0" (0) + : "memory"); /* memory required? */ + return err; +} + +void *get_xsave_addr(struct xsave_struct *xsave, int xstate); +void setup_xstate_comp(void); + +#endif diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 0ce4c4f87332..2426e6530d3c 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include "cpuid.h" #include "lapic.h" #include "mmu.h" -- cgit v1.2.3-55-g7522