From patchwork Thu Mar 3 23:52:40 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "H.J. Lu" X-Patchwork-Id: 11181 Received: (qmail 117049 invoked by alias); 3 Mar 2016 23:52:50 -0000 Mailing-List: contact libc-alpha-help@sourceware.org; run by ezmlm Precedence: bulk List-Id: List-Unsubscribe: List-Subscribe: List-Archive: List-Post: List-Help: , Sender: libc-alpha-owner@sourceware.org Delivered-To: mailing list libc-alpha@sourceware.org Received: (qmail 116963 invoked by uid 89); 3 Mar 2016 23:52:49 -0000 Authentication-Results: sourceware.org; auth=none X-Virus-Found: No X-Spam-SWARE-Status: No, score=1.1 required=5.0 tests=AWL, BAYES_50, FREEMAIL_FROM, SPF_SOFTFAIL autolearn=no version=3.3.2 spammy=1568, fma, testl, edx X-HELO: mga14.intel.com X-ExtLoop1: 1 From: "H.J. Lu" To: libc-alpha@sourceware.org Subject: [PATCH 1/2] Add _arch_/_cpu_ to index_*/bit_* in x86 cpu-features.h Date: Thu, 3 Mar 2016 15:52:40 -0800 Message-Id: <1457049161-13783-1-git-send-email-hjl.tools@gmail.com> index_* and bit_* macros are used to access cpuid and feature arrays o struct cpu_features. It is very easy to use bits and indices of cpuid array on feature array, especially in assembly codes. For example, sysdeps/i386/i686/multiarch/bcopy.S has HAS_CPU_FEATURE (Fast_Rep_String) which should be HAS_ARCH_FEATURE (Fast_Rep_String) We change index_* and bit_* to index_cpu_*/index_arch_* and bit_cpu_*/bit_arch_* so that we can catch such error at build time. [BZ #19762] * sysdeps/unix/sysv/linux/x86_64/64/dl-librecon.h (EXTRA_LD_ENVVARS): Add _arch_ to index_*/bit_*. * sysdeps/x86/cpu-features.c (init_cpu_features): Likewise. * sysdeps/x86/cpu-features.h (bit_*): Renamed to ... (bit_arch_*): This for feature array. (bit_*): Renamed to ... (bit_cpu_*): This for cpu array. (index_*): Renamed to ... (index_arch_*): This for feature array. (index_*): Renamed to ... (index_cpu_*): This for cpu array. [__ASSEMBLER__] (HAS_FEATURE): Add and use field. [__ASSEMBLER__] (HAS_CPU_FEATURE)): Pass cpu to HAS_FEATURE. [__ASSEMBLER__] (HAS_ARCH_FEATURE)): Pass arch to HAS_FEATURE. [!__ASSEMBLER__] (HAS_CPU_FEATURE): Replace index_##name and bit_##name with index_cpu_##name and bit_cpu_##name. [!__ASSEMBLER__] (HAS_ARCH_FEATURE): Replace index_##name and bit_##name with index_arch_##name and bit_arch_##name. --- sysdeps/unix/sysv/linux/x86_64/64/dl-librecon.h | 8 +- sysdeps/x86/cpu-features.c | 80 +++++---- sysdeps/x86/cpu-features.h | 222 ++++++++++++------------ 3 files changed, 159 insertions(+), 151 deletions(-) diff --git a/sysdeps/unix/sysv/linux/x86_64/64/dl-librecon.h b/sysdeps/unix/sysv/linux/x86_64/64/dl-librecon.h index a759934..1c67050 100644 --- a/sysdeps/unix/sysv/linux/x86_64/64/dl-librecon.h +++ b/sysdeps/unix/sysv/linux/x86_64/64/dl-librecon.h @@ -30,10 +30,10 @@ is always disabled for SUID programs and can be enabled by setting environment variable, LD_PREFER_MAP_32BIT_EXEC. */ #define EXTRA_LD_ENVVARS \ - case 21: \ - if (memcmp (envline, "PREFER_MAP_32BIT_EXEC", 21) == 0) \ - GLRO(dl_x86_cpu_features).feature[index_Prefer_MAP_32BIT_EXEC] \ - |= bit_Prefer_MAP_32BIT_EXEC; \ + case 21: \ + if (memcmp (envline, "PREFER_MAP_32BIT_EXEC", 21) == 0) \ + GLRO(dl_x86_cpu_features).feature[index_arch_Prefer_MAP_32BIT_EXEC] \ + |= bit_arch_Prefer_MAP_32BIT_EXEC; \ break; /* Extra unsecure variables. The names are all stuffed in a single diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c index 218ff2b..1787716 100644 --- a/sysdeps/x86/cpu-features.c +++ b/sysdeps/x86/cpu-features.c @@ -75,13 +75,14 @@ init_cpu_features (struct cpu_features *cpu_features) case 0x1c: case 0x26: /* BSF is slow on Atom. */ - cpu_features->feature[index_Slow_BSF] |= bit_Slow_BSF; + cpu_features->feature[index_arch_Slow_BSF] + |= bit_arch_Slow_BSF; break; case 0x57: /* Knights Landing. Enable Silvermont optimizations. */ - cpu_features->feature[index_Prefer_No_VZEROUPPER] - |= bit_Prefer_No_VZEROUPPER; + cpu_features->feature[index_arch_Prefer_No_VZEROUPPER] + |= bit_arch_Prefer_No_VZEROUPPER; case 0x37: case 0x4a: @@ -90,22 +91,22 @@ init_cpu_features (struct cpu_features *cpu_features) case 0x5d: /* Unaligned load versions are faster than SSSE3 on Silvermont. */ -#if index_Fast_Unaligned_Load != index_Prefer_PMINUB_for_stringop -# error index_Fast_Unaligned_Load != index_Prefer_PMINUB_for_stringop +#if index_arch_Fast_Unaligned_Load != index_arch_Prefer_PMINUB_for_stringop +# error index_arch_Fast_Unaligned_Load != index_arch_Prefer_PMINUB_for_stringop #endif -#if index_Fast_Unaligned_Load != index_Slow_SSE4_2 -# error index_Fast_Unaligned_Load != index_Slow_SSE4_2 +#if index_arch_Fast_Unaligned_Load != index_arch_Slow_SSE4_2 +# error index_arch_Fast_Unaligned_Load != index_arch_Slow_SSE4_2 #endif - cpu_features->feature[index_Fast_Unaligned_Load] - |= (bit_Fast_Unaligned_Load - | bit_Prefer_PMINUB_for_stringop - | bit_Slow_SSE4_2); + cpu_features->feature[index_arch_Fast_Unaligned_Load] + |= (bit_arch_Fast_Unaligned_Load + | bit_arch_Prefer_PMINUB_for_stringop + | bit_arch_Slow_SSE4_2); break; default: /* Unknown family 0x06 processors. Assuming this is one of Core i3/i5/i7 processors if AVX is available. */ - if ((ecx & bit_AVX) == 0) + if ((ecx & bit_cpu_AVX) == 0) break; case 0x1a: @@ -117,20 +118,20 @@ init_cpu_features (struct cpu_features *cpu_features) case 0x2f: /* Rep string instructions, copy backward, unaligned loads and pminub are fast on Intel Core i3, i5 and i7. */ -#if index_Fast_Rep_String != index_Fast_Copy_Backward -# error index_Fast_Rep_String != index_Fast_Copy_Backward +#if index_arch_Fast_Rep_String != index_arch_Fast_Copy_Backward +# error index_arch_Fast_Rep_String != index_arch_Fast_Copy_Backward #endif -#if index_Fast_Rep_String != index_Fast_Unaligned_Load -# error index_Fast_Rep_String != index_Fast_Unaligned_Load +#if index_arch_Fast_Rep_String != index_arch_Fast_Unaligned_Load +# error index_arch_Fast_Rep_String != index_arch_Fast_Unaligned_Load #endif -#if index_Fast_Rep_String != index_Prefer_PMINUB_for_stringop -# error index_Fast_Rep_String != index_Prefer_PMINUB_for_stringop +#if index_arch_Fast_Rep_String != index_arch_Prefer_PMINUB_for_stringop +# error index_arch_Fast_Rep_String != index_arch_Prefer_PMINUB_for_stringop #endif - cpu_features->feature[index_Fast_Rep_String] - |= (bit_Fast_Rep_String - | bit_Fast_Copy_Backward - | bit_Fast_Unaligned_Load - | bit_Prefer_PMINUB_for_stringop); + cpu_features->feature[index_arch_Fast_Rep_String] + |= (bit_arch_Fast_Rep_String + | bit_arch_Fast_Copy_Backward + | bit_arch_Fast_Unaligned_Load + | bit_arch_Prefer_PMINUB_for_stringop); break; } } @@ -159,8 +160,8 @@ init_cpu_features (struct cpu_features *cpu_features) { /* "Excavator" */ if (model >= 0x60 && model <= 0x7f) - cpu_features->feature[index_Fast_Unaligned_Load] - |= bit_Fast_Unaligned_Load; + cpu_features->feature[index_arch_Fast_Unaligned_Load] + |= bit_arch_Fast_Unaligned_Load; } } else @@ -168,11 +169,11 @@ init_cpu_features (struct cpu_features *cpu_features) /* Support i586 if CX8 is available. */ if (HAS_CPU_FEATURE (CX8)) - cpu_features->feature[index_I586] |= bit_I586; + cpu_features->feature[index_arch_I586] |= bit_arch_I586; /* Support i686 if CMOV is available. */ if (HAS_CPU_FEATURE (CMOV)) - cpu_features->feature[index_I686] |= bit_I686; + cpu_features->feature[index_arch_I686] |= bit_arch_I686; if (cpu_features->max_cpuid >= 7) __cpuid_count (7, 0, @@ -193,15 +194,16 @@ init_cpu_features (struct cpu_features *cpu_features) { /* Determine if AVX is usable. */ if (HAS_CPU_FEATURE (AVX)) - cpu_features->feature[index_AVX_Usable] |= bit_AVX_Usable; -#if index_AVX2_Usable != index_AVX_Fast_Unaligned_Load -# error index_AVX2_Usable != index_AVX_Fast_Unaligned_Load + cpu_features->feature[index_arch_AVX_Usable] + |= bit_arch_AVX_Usable; +#if index_arch_AVX2_Usable != index_arch_AVX_Fast_Unaligned_Load +# error index_arch_AVX2_Usable != index_arch_AVX_Fast_Unaligned_Load #endif /* Determine if AVX2 is usable. Unaligned load with 256-bit AVX registers are faster on processors with AVX2. */ if (HAS_CPU_FEATURE (AVX2)) - cpu_features->feature[index_AVX2_Usable] - |= bit_AVX2_Usable | bit_AVX_Fast_Unaligned_Load; + cpu_features->feature[index_arch_AVX2_Usable] + |= bit_arch_AVX2_Usable | bit_arch_AVX_Fast_Unaligned_Load; /* Check if OPMASK state, upper 256-bit of ZMM0-ZMM15 and ZMM16-ZMM31 state are enabled. */ if ((xcrlow & (bit_Opmask_state | bit_ZMM0_15_state @@ -211,20 +213,22 @@ init_cpu_features (struct cpu_features *cpu_features) /* Determine if AVX512F is usable. */ if (HAS_CPU_FEATURE (AVX512F)) { - cpu_features->feature[index_AVX512F_Usable] - |= bit_AVX512F_Usable; + cpu_features->feature[index_arch_AVX512F_Usable] + |= bit_arch_AVX512F_Usable; /* Determine if AVX512DQ is usable. */ if (HAS_CPU_FEATURE (AVX512DQ)) - cpu_features->feature[index_AVX512DQ_Usable] - |= bit_AVX512DQ_Usable; + cpu_features->feature[index_arch_AVX512DQ_Usable] + |= bit_arch_AVX512DQ_Usable; } } /* Determine if FMA is usable. */ if (HAS_CPU_FEATURE (FMA)) - cpu_features->feature[index_FMA_Usable] |= bit_FMA_Usable; + cpu_features->feature[index_arch_FMA_Usable] + |= bit_arch_FMA_Usable; /* Determine if FMA4 is usable. */ if (HAS_CPU_FEATURE (FMA4)) - cpu_features->feature[index_FMA4_Usable] |= bit_FMA4_Usable; + cpu_features->feature[index_arch_FMA4_Usable] + |= bit_arch_FMA4_Usable; } } diff --git a/sysdeps/x86/cpu-features.h b/sysdeps/x86/cpu-features.h index e354920..0624a92 100644 --- a/sysdeps/x86/cpu-features.h +++ b/sysdeps/x86/cpu-features.h @@ -18,48 +18,48 @@ #ifndef cpu_features_h #define cpu_features_h -#define bit_Fast_Rep_String (1 << 0) -#define bit_Fast_Copy_Backward (1 << 1) -#define bit_Slow_BSF (1 << 2) -#define bit_Fast_Unaligned_Load (1 << 4) -#define bit_Prefer_PMINUB_for_stringop (1 << 5) -#define bit_AVX_Usable (1 << 6) -#define bit_FMA_Usable (1 << 7) -#define bit_FMA4_Usable (1 << 8) -#define bit_Slow_SSE4_2 (1 << 9) -#define bit_AVX2_Usable (1 << 10) -#define bit_AVX_Fast_Unaligned_Load (1 << 11) -#define bit_AVX512F_Usable (1 << 12) -#define bit_AVX512DQ_Usable (1 << 13) -#define bit_I586 (1 << 14) -#define bit_I686 (1 << 15) -#define bit_Prefer_MAP_32BIT_EXEC (1 << 16) -#define bit_Prefer_No_VZEROUPPER (1 << 17) +#define bit_arch_Fast_Rep_String (1 << 0) +#define bit_arch_Fast_Copy_Backward (1 << 1) +#define bit_arch_Slow_BSF (1 << 2) +#define bit_arch_Fast_Unaligned_Load (1 << 4) +#define bit_arch_Prefer_PMINUB_for_stringop (1 << 5) +#define bit_arch_AVX_Usable (1 << 6) +#define bit_arch_FMA_Usable (1 << 7) +#define bit_arch_FMA4_Usable (1 << 8) +#define bit_arch_Slow_SSE4_2 (1 << 9) +#define bit_arch_AVX2_Usable (1 << 10) +#define bit_arch_AVX_Fast_Unaligned_Load (1 << 11) +#define bit_arch_AVX512F_Usable (1 << 12) +#define bit_arch_AVX512DQ_Usable (1 << 13) +#define bit_arch_I586 (1 << 14) +#define bit_arch_I686 (1 << 15) +#define bit_arch_Prefer_MAP_32BIT_EXEC (1 << 16) +#define bit_arch_Prefer_No_VZEROUPPER (1 << 17) /* CPUID Feature flags. */ /* COMMON_CPUID_INDEX_1. */ -#define bit_CX8 (1 << 8) -#define bit_CMOV (1 << 15) -#define bit_SSE2 (1 << 26) -#define bit_SSSE3 (1 << 9) -#define bit_SSE4_1 (1 << 19) -#define bit_SSE4_2 (1 << 20) -#define bit_OSXSAVE (1 << 27) -#define bit_AVX (1 << 28) -#define bit_POPCOUNT (1 << 23) -#define bit_FMA (1 << 12) -#define bit_FMA4 (1 << 16) +#define bit_cpu_CX8 (1 << 8) +#define bit_cpu_CMOV (1 << 15) +#define bit_cpu_SSE2 (1 << 26) +#define bit_cpu_SSSE3 (1 << 9) +#define bit_cpu_SSE4_1 (1 << 19) +#define bit_cpu_SSE4_2 (1 << 20) +#define bit_cpu_OSXSAVE (1 << 27) +#define bit_cpu_AVX (1 << 28) +#define bit_cpu_POPCOUNT (1 << 23) +#define bit_cpu_FMA (1 << 12) +#define bit_cpu_FMA4 (1 << 16) /* COMMON_CPUID_INDEX_7. */ -#define bit_RTM (1 << 11) -#define bit_AVX2 (1 << 5) -#define bit_AVX512F (1 << 16) -#define bit_AVX512DQ (1 << 17) +#define bit_cpu_RTM (1 << 11) +#define bit_cpu_AVX2 (1 << 5) +#define bit_cpu_AVX512F (1 << 16) +#define bit_cpu_AVX512DQ (1 << 17) /* XCR0 Feature flags. */ -#define bit_XMM_state (1 << 1) -#define bit_YMM_state (2 << 1) +#define bit_XMM_state (1 << 1) +#define bit_YMM_state (2 << 1) #define bit_Opmask_state (1 << 5) #define bit_ZMM0_15_state (1 << 6) #define bit_ZMM16_31_state (1 << 7) @@ -75,32 +75,32 @@ # include # include -# define index_CX8 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_EDX_OFFSET -# define index_CMOV COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_EDX_OFFSET -# define index_SSE2 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_EDX_OFFSET -# define index_SSSE3 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET -# define index_SSE4_1 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET -# define index_SSE4_2 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET -# define index_AVX COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET -# define index_AVX2 COMMON_CPUID_INDEX_7*CPUID_SIZE+CPUID_EBX_OFFSET +# define index_cpu_CX8 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_EDX_OFFSET +# define index_cpu_CMOV COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_EDX_OFFSET +# define index_cpu_SSE2 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_EDX_OFFSET +# define index_cpu_SSSE3 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET +# define index_cpu_SSE4_1 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET +# define index_cpu_SSE4_2 COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET +# define index_cpu_AVX COMMON_CPUID_INDEX_1*CPUID_SIZE+CPUID_ECX_OFFSET +# define index_cpu_AVX2 COMMON_CPUID_INDEX_7*CPUID_SIZE+CPUID_EBX_OFFSET -# define index_Fast_Rep_String FEATURE_INDEX_1*FEATURE_SIZE -# define index_Fast_Copy_Backward FEATURE_INDEX_1*FEATURE_SIZE -# define index_Slow_BSF FEATURE_INDEX_1*FEATURE_SIZE -# define index_Fast_Unaligned_Load FEATURE_INDEX_1*FEATURE_SIZE -# define index_Prefer_PMINUB_for_stringop FEATURE_INDEX_1*FEATURE_SIZE -# define index_AVX_Usable FEATURE_INDEX_1*FEATURE_SIZE -# define index_FMA_Usable FEATURE_INDEX_1*FEATURE_SIZE -# define index_FMA4_Usable FEATURE_INDEX_1*FEATURE_SIZE -# define index_Slow_SSE4_2 FEATURE_INDEX_1*FEATURE_SIZE -# define index_AVX2_Usable FEATURE_INDEX_1*FEATURE_SIZE -# define index_AVX_Fast_Unaligned_Load FEATURE_INDEX_1*FEATURE_SIZE -# define index_AVX512F_Usable FEATURE_INDEX_1*FEATURE_SIZE -# define index_AVX512DQ_Usable FEATURE_INDEX_1*FEATURE_SIZE -# define index_I586 FEATURE_INDEX_1*FEATURE_SIZE -# define index_I686 FEATURE_INDEX_1*FEATURE_SIZE -# define index_Prefer_MAP_32BIT_EXEC FEATURE_INDEX_1*FEATURE_SIZE -# define index_Prefer_No_VZEROUPPER FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Fast_Rep_String FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Fast_Copy_Backward FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Slow_BSF FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Fast_Unaligned_Load FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Prefer_PMINUB_for_stringop FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_AVX_Usable FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_FMA_Usable FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_FMA4_Usable FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Slow_SSE4_2 FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_AVX2_Usable FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_AVX_Fast_Unaligned_Load FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_AVX512F_Usable FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_AVX512DQ_Usable FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_I586 FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_I686 FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Prefer_MAP_32BIT_EXEC FEATURE_INDEX_1*FEATURE_SIZE +# define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1*FEATURE_SIZE # if defined (_LIBC) && !IS_IN (nonlib) @@ -108,19 +108,21 @@ # ifdef SHARED # if IS_IN (rtld) # define LOAD_RTLD_GLOBAL_RO_RDX -# define HAS_FEATURE(offset, name) \ - testl $(bit_##name), _rtld_local_ro+offset+(index_##name)(%rip) +# define HAS_FEATURE(offset, field, name) \ + testl $(bit_##field##_##name), \ + _rtld_local_ro+offset+(index_##field##_##name)(%rip) # else # define LOAD_RTLD_GLOBAL_RO_RDX \ mov _rtld_global_ro@GOTPCREL(%rip), %RDX_LP -# define HAS_FEATURE(offset, name) \ - testl $(bit_##name), \ - RTLD_GLOBAL_RO_DL_X86_CPU_FEATURES_OFFSET+offset+(index_##name)(%rdx) +# define HAS_FEATURE(offset, field, name) \ + testl $(bit_##field##_##name), \ + RTLD_GLOBAL_RO_DL_X86_CPU_FEATURES_OFFSET+offset+(index_##field##_##name)(%rdx) # endif # else /* SHARED */ # define LOAD_RTLD_GLOBAL_RO_RDX -# define HAS_FEATURE(offset, name) \ - testl $(bit_##name), _dl_x86_cpu_features+offset+(index_##name)(%rip) +# define HAS_FEATURE(offset, field, name) \ + testl $(bit_##field##_##name), \ + _dl_x86_cpu_features+offset+(index_##field##_##name)(%rip) # endif /* !SHARED */ # else /* __x86_64__ */ # ifdef SHARED @@ -129,22 +131,24 @@ # if IS_IN (rtld) # define LOAD_GOT_AND_RTLD_GLOBAL_RO \ LOAD_PIC_REG(dx) -# define HAS_FEATURE(offset, name) \ - testl $(bit_##name), offset+(index_##name)+_rtld_local_ro@GOTOFF(%edx) +# define HAS_FEATURE(offset, field, name) \ + testl $(bit_##field##_##name), \ + offset+(index_##field##_##name)+_rtld_local_ro@GOTOFF(%edx) # else # define LOAD_GOT_AND_RTLD_GLOBAL_RO \ LOAD_PIC_REG(dx); \ mov _rtld_global_ro@GOT(%edx), %ecx -# define HAS_FEATURE(offset, name) \ - testl $(bit_##name), \ - RTLD_GLOBAL_RO_DL_X86_CPU_FEATURES_OFFSET+offset+(index_##name)(%ecx) +# define HAS_FEATURE(offset, field, name) \ + testl $(bit_##field##_##name), \ + RTLD_GLOBAL_RO_DL_X86_CPU_FEATURES_OFFSET+offset+(index_##field##_##name)(%ecx) # endif # else /* SHARED */ # define LOAD_FUNC_GOT_EAX(func) \ leal func, %eax # define LOAD_GOT_AND_RTLD_GLOBAL_RO -# define HAS_FEATURE(offset, name) \ - testl $(bit_##name), _dl_x86_cpu_features+offset+(index_##name) +# define HAS_FEATURE(offset, field, name) \ + testl $(bit_##field##_##name), \ + _dl_x86_cpu_features+offset+(index_##field##_##name) # endif /* !SHARED */ # endif /* !__x86_64__ */ # else /* _LIBC && !nonlib */ @@ -152,8 +156,8 @@ # endif /* !_LIBC || nonlib */ /* HAS_* evaluates to true if we may use the feature at runtime. */ -# define HAS_CPU_FEATURE(name) HAS_FEATURE (CPUID_OFFSET, name) -# define HAS_ARCH_FEATURE(name) HAS_FEATURE (FEATURE_OFFSET, name) +# define HAS_CPU_FEATURE(name) HAS_FEATURE (CPUID_OFFSET, cpu, name) +# define HAS_ARCH_FEATURE(name) HAS_FEATURE (FEATURE_OFFSET, arch, name) #else /* __ASSEMBLER__ */ @@ -202,25 +206,25 @@ extern const struct cpu_features *__get_cpu_features (void) /* HAS_* evaluates to true if we may use the feature at runtime. */ # define HAS_CPU_FEATURE(name) \ - ((__get_cpu_features ()->cpuid[index_##name].reg_##name & (bit_##name)) != 0) + ((__get_cpu_features ()->cpuid[index_cpu_##name].reg_##name & (bit_cpu_##name)) != 0) # define HAS_ARCH_FEATURE(name) \ - ((__get_cpu_features ()->feature[index_##name] & (bit_##name)) != 0) + ((__get_cpu_features ()->feature[index_arch_##name] & (bit_arch_##name)) != 0) -# define index_CX8 COMMON_CPUID_INDEX_1 -# define index_CMOV COMMON_CPUID_INDEX_1 -# define index_SSE2 COMMON_CPUID_INDEX_1 -# define index_SSSE3 COMMON_CPUID_INDEX_1 -# define index_SSE4_1 COMMON_CPUID_INDEX_1 -# define index_SSE4_2 COMMON_CPUID_INDEX_1 -# define index_AVX COMMON_CPUID_INDEX_1 -# define index_AVX2 COMMON_CPUID_INDEX_7 -# define index_AVX512F COMMON_CPUID_INDEX_7 -# define index_AVX512DQ COMMON_CPUID_INDEX_7 -# define index_RTM COMMON_CPUID_INDEX_7 -# define index_FMA COMMON_CPUID_INDEX_1 -# define index_FMA4 COMMON_CPUID_INDEX_80000001 -# define index_POPCOUNT COMMON_CPUID_INDEX_1 -# define index_OSXSAVE COMMON_CPUID_INDEX_1 +# define index_cpu_CX8 COMMON_CPUID_INDEX_1 +# define index_cpu_CMOV COMMON_CPUID_INDEX_1 +# define index_cpu_SSE2 COMMON_CPUID_INDEX_1 +# define index_cpu_SSSE3 COMMON_CPUID_INDEX_1 +# define index_cpu_SSE4_1 COMMON_CPUID_INDEX_1 +# define index_cpu_SSE4_2 COMMON_CPUID_INDEX_1 +# define index_cpu_AVX COMMON_CPUID_INDEX_1 +# define index_cpu_AVX2 COMMON_CPUID_INDEX_7 +# define index_cpu_AVX512F COMMON_CPUID_INDEX_7 +# define index_cpu_AVX512DQ COMMON_CPUID_INDEX_7 +# define index_cpu_RTM COMMON_CPUID_INDEX_7 +# define index_cpu_FMA COMMON_CPUID_INDEX_1 +# define index_cpu_FMA4 COMMON_CPUID_INDEX_80000001 +# define index_cpu_POPCOUNT COMMON_CPUID_INDEX_1 +# define index_cpu_OSXSAVE COMMON_CPUID_INDEX_1 # define reg_CX8 edx # define reg_CMOV edx @@ -238,23 +242,23 @@ extern const struct cpu_features *__get_cpu_features (void) # define reg_POPCOUNT ecx # define reg_OSXSAVE ecx -# define index_Fast_Rep_String FEATURE_INDEX_1 -# define index_Fast_Copy_Backward FEATURE_INDEX_1 -# define index_Slow_BSF FEATURE_INDEX_1 -# define index_Fast_Unaligned_Load FEATURE_INDEX_1 -# define index_Prefer_PMINUB_for_stringop FEATURE_INDEX_1 -# define index_AVX_Usable FEATURE_INDEX_1 -# define index_FMA_Usable FEATURE_INDEX_1 -# define index_FMA4_Usable FEATURE_INDEX_1 -# define index_Slow_SSE4_2 FEATURE_INDEX_1 -# define index_AVX2_Usable FEATURE_INDEX_1 -# define index_AVX_Fast_Unaligned_Load FEATURE_INDEX_1 -# define index_AVX512F_Usable FEATURE_INDEX_1 -# define index_AVX512DQ_Usable FEATURE_INDEX_1 -# define index_I586 FEATURE_INDEX_1 -# define index_I686 FEATURE_INDEX_1 -# define index_Prefer_MAP_32BIT_EXEC FEATURE_INDEX_1 -# define index_Prefer_No_VZEROUPPER FEATURE_INDEX_1 +# define index_arch_Fast_Rep_String FEATURE_INDEX_1 +# define index_arch_Fast_Copy_Backward FEATURE_INDEX_1 +# define index_arch_Slow_BSF FEATURE_INDEX_1 +# define index_arch_Fast_Unaligned_Load FEATURE_INDEX_1 +# define index_arch_Prefer_PMINUB_for_stringop FEATURE_INDEX_1 +# define index_arch_AVX_Usable FEATURE_INDEX_1 +# define index_arch_FMA_Usable FEATURE_INDEX_1 +# define index_arch_FMA4_Usable FEATURE_INDEX_1 +# define index_arch_Slow_SSE4_2 FEATURE_INDEX_1 +# define index_arch_AVX2_Usable FEATURE_INDEX_1 +# define index_arch_AVX_Fast_Unaligned_Load FEATURE_INDEX_1 +# define index_arch_AVX512F_Usable FEATURE_INDEX_1 +# define index_arch_AVX512DQ_Usable FEATURE_INDEX_1 +# define index_arch_I586 FEATURE_INDEX_1 +# define index_arch_I686 FEATURE_INDEX_1 +# define index_arch_Prefer_MAP_32BIT_EXEC FEATURE_INDEX_1 +# define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1 #endif /* !__ASSEMBLER__ */