commit 36d6b9be3d7008a78e1f6e2e2db1947b76b206d8
Author: Aurelien Jarno <aurelien@aurel32.net>
Date: Mon Oct 3 23:16:46 2022 +0200
x86-64: Require BMI2 and LZCNT for AVX2 memrchr implementation
The AVX2 memrchr implementation uses the 'shlxl' instruction, which
belongs to the BMI2 CPU feature and uses the 'lzcnt' instruction, which
belongs to the LZCNT CPU feature.
Fixes: af5306a735eb ("x86: Optimize memrchr-avx2.S")
Partially resolves: BZ #29611
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
(cherry picked from commit 3c0c78afabfed4b6fc161c159e628fbf14ff370b)
diff --git a/sysdeps/x86_64/multiarch/ifunc-avx2.h b/sysdeps/x86_64/multiarch/ifunc-avx2.h
index 6de72f72724b81ba..52bd00ea5cab6b22 100644
--- a/sysdeps/x86_64/multiarch/ifunc-avx2.h
+++ b/sysdeps/x86_64/multiarch/ifunc-avx2.h
@@ -31,6 +31,7 @@ IFUNC_SELECTOR (void)
if (CPU_FEATURE_USABLE_P (cpu_features, AVX2)
&& CPU_FEATURE_USABLE_P (cpu_features, BMI2)
+ && CPU_FEATURE_USABLE_P (cpu_features, LZCNT)
&& CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
{
if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index 81640cf00664e3ed..d1fc1e75d6706413 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -174,15 +174,21 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
/* Support sysdeps/x86_64/multiarch/memrchr.c. */
IFUNC_IMPL (i, name, memrchr,
IFUNC_IMPL_ADD (array, i, memrchr,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
+ && CPU_FEATURE_USABLE (LZCNT)),
__memrchr_avx2)
IFUNC_IMPL_ADD (array, i, memrchr,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
+ && CPU_FEATURE_USABLE (LZCNT)
&& CPU_FEATURE_USABLE (RTM)),
__memrchr_avx2_rtm)
IFUNC_IMPL_ADD (array, i, memrchr,
(CPU_FEATURE_USABLE (AVX512VL)
- && CPU_FEATURE_USABLE (AVX512BW)),
+ && CPU_FEATURE_USABLE (AVX512BW)
+ && CPU_FEATURE_USABLE (BMI2)
+ && CPU_FEATURE_USABLE (LZCNT)),
__memrchr_evex)
IFUNC_IMPL_ADD (array, i, memrchr, 1, __memrchr_sse2))