From 20152a849b34abe83c702b27b7276c96b191b644 Mon Sep 17 00:00:00 2001 From: Aurelien Jarno Date: Mon, 3 Oct 2022 23:16:46 +0200 Subject: [PATCH] x86-64: Require BMI1/BMI2 for AVX2 strrchr and wcsrchr implementations The AVX2 strrchr and wcsrchr implementation uses the 'blsmsk' instruction which belongs to the BMI1 CPU feature and the 'shrx' instruction, which belongs to the BMI2 CPU feature. Fixes: df7e295d18ff ("x86: Optimize {str|wcs}rchr-avx2") Partially resolves: BZ #29611 Reviewed-by: Noah Goldstein (cherry picked from commit 7e8283170c5d6805b609a040801d819e362a6292) --- sysdeps/x86_64/multiarch/ifunc-avx2.h | 1 + sysdeps/x86_64/multiarch/ifunc-impl-list.c | 17 ++++++++++++++--- 2 files changed, 15 insertions(+), 3 deletions(-) diff --git a/sysdeps/x86_64/multiarch/ifunc-avx2.h b/sysdeps/x86_64/multiarch/ifunc-avx2.h index 5cc1e4b0bc3..0456fa6efe1 100644 --- a/sysdeps/x86_64/multiarch/ifunc-avx2.h +++ b/sysdeps/x86_64/multiarch/ifunc-avx2.h @@ -30,6 +30,7 @@ IFUNC_SELECTOR (void) const struct cpu_features* cpu_features = __get_cpu_features (); if (CPU_FEATURE_USABLE_P (cpu_features, AVX2) + && CPU_FEATURE_USABLE_P (cpu_features, BMI1) && CPU_FEATURE_USABLE_P (cpu_features, BMI2) && CPU_FEATURE_USABLE_P (cpu_features, LZCNT) && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load)) diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c index a7c8ebbe850..b224e6a644f 100644 --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c @@ -516,15 +516,21 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, /* Support sysdeps/x86_64/multiarch/strrchr.c. */ IFUNC_IMPL (i, name, strrchr, IFUNC_IMPL_ADD (array, i, strrchr, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI1) + && CPU_FEATURE_USABLE (BMI2)), __strrchr_avx2) IFUNC_IMPL_ADD (array, i, strrchr, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI1) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __strrchr_avx2_rtm) IFUNC_IMPL_ADD (array, i, strrchr, (CPU_FEATURE_USABLE (AVX512VL) - && CPU_FEATURE_USABLE (AVX512BW)), + && CPU_FEATURE_USABLE (AVX512BW) + && CPU_FEATURE_USABLE (BMI1) + && CPU_FEATURE_USABLE (BMI2)), __strrchr_evex) IFUNC_IMPL_ADD (array, i, strrchr, 1, __strrchr_sse2)) @@ -705,15 +711,20 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array, /* Support sysdeps/x86_64/multiarch/wcsrchr.c. */ IFUNC_IMPL (i, name, wcsrchr, IFUNC_IMPL_ADD (array, i, wcsrchr, - CPU_FEATURE_USABLE (AVX2), + (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI1) + && CPU_FEATURE_USABLE (BMI2)), __wcsrchr_avx2) IFUNC_IMPL_ADD (array, i, wcsrchr, (CPU_FEATURE_USABLE (AVX2) + && CPU_FEATURE_USABLE (BMI1) + && CPU_FEATURE_USABLE (BMI2) && CPU_FEATURE_USABLE (RTM)), __wcsrchr_avx2_rtm) IFUNC_IMPL_ADD (array, i, wcsrchr, (CPU_FEATURE_USABLE (AVX512VL) && CPU_FEATURE_USABLE (AVX512BW) + && CPU_FEATURE_USABLE (BMI1) && CPU_FEATURE_USABLE (BMI2)), __wcsrchr_evex) IFUNC_IMPL_ADD (array, i, wcsrchr, 1, __wcsrchr_sse2)) -- 2.47.2