From ceabdcd130ca7043b0fcf2676183d79431d10493 Mon Sep 17 00:00:00 2001 From: Noah Goldstein Date: Wed, 13 Jul 2022 16:32:59 -0700 Subject: x86: Add support to build strcmp/strlen/strchr with explicit ISA level 1. Add default ISA level selection in non-multiarch/rtld implementations. 2. Add ISA level build guards to different implementations. - I.e strcmp-avx2.S which is ISA level 3 will only build if compiled ISA level <= 3. Otherwise there is no reason to include it as we will always use one of the ISA level 4 implementations (strcmp-evex.S). 3. Refactor the ifunc selector and ifunc implementation list to use the ISA level aware wrapper macros that allow functions below the compiled ISA level (with a guranteed replacement) to be skipped. Tested with and without multiarch on x86_64 for ISA levels: {generic, x86-64-v2, x86-64-v3, x86-64-v4} And m32 with and without multiarch. --- sysdeps/x86_64/multiarch/strchr.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) (limited to 'sysdeps/x86_64/multiarch/strchr.c') diff --git a/sysdeps/x86_64/multiarch/strchr.c b/sysdeps/x86_64/multiarch/strchr.c index de737580eb..ce7441c532 100644 --- a/sysdeps/x86_64/multiarch/strchr.c +++ b/sysdeps/x86_64/multiarch/strchr.c @@ -26,36 +26,40 @@ # define SYMBOL_NAME strchr # include -extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden; -extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_no_bsf) attribute_hidden; +extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden; + extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden; extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_rtm) attribute_hidden; -extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden; + +extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2) attribute_hidden; +extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_no_bsf) attribute_hidden; static inline void * IFUNC_SELECTOR (void) { - const struct cpu_features* cpu_features = __get_cpu_features (); + const struct cpu_features *cpu_features = __get_cpu_features (); - if (CPU_FEATURE_USABLE_P (cpu_features, AVX2) - && CPU_FEATURE_USABLE_P (cpu_features, BMI2) - && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load)) + if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2) + && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2) + && X86_ISA_CPU_FEATURES_ARCH_P (cpu_features, + AVX_Fast_Unaligned_Load, )) { - if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL) - && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)) + if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL) + && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)) return OPTIMIZE (evex); if (CPU_FEATURE_USABLE_P (cpu_features, RTM)) return OPTIMIZE (avx2_rtm); - if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER)) + if (X86_ISA_CPU_FEATURES_ARCH_P (cpu_features, + Prefer_No_VZEROUPPER, !)) return OPTIMIZE (avx2); } - if (CPU_FEATURES_ARCH_P (cpu_features, Slow_BSF)) - return OPTIMIZE (sse2_no_bsf); + if (X86_ISA_CPU_FEATURES_ARCH_P (cpu_features, Slow_BSF, !)) + return OPTIMIZE (sse2); - return OPTIMIZE (sse2); + return OPTIMIZE (sse2_no_bsf); } libc_ifunc_redirected (__redirect_strchr, strchr, IFUNC_SELECTOR ()); -- cgit 1.4.1