From 29c577e0f54fe6e70ceacb3659179781c5569903 Mon Sep 17 00:00:00 2001
From: Aurelien Jarno <aurelien@aurel32.net>
Date: Mon, 3 Oct 2022 23:46:11 +0200
Subject: [PATCH 151/155] x86-64: Require BMI2 for AVX2 strncmp implementation
The AVX2 strncmp implementations uses the 'bzhi' instruction, which
belongs to the BMI2 CPU feature.
NB: It also uses the 'tzcnt' BMI1 instruction, but it is executed as BSF
as BSF if the CPU doesn't support TZCNT, and produces the same result
for non-zero input.
Partially fixes: b77b06e0e296 ("x86: Optimize strcmp-avx2.S")
Partially resolves: BZ #29611
Reviewed-by: Noah Goldstein <goldstein.w.n@gmail.com>
(cherry picked from commit fc7de1d9b99ae1676bc626ddca422d7abee0eb48)
---
sysdeps/x86_64/multiarch/ifunc-impl-list.c | 7 +++++--
sysdeps/x86_64/multiarch/strncmp.c | 4 ++--
2 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index a42b0a4620b9..aebef3daafc7 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -1176,13 +1176,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
IFUNC_IMPL (i, name, strncmp,
X86_IFUNC_IMPL_ADD_V4 (array, i, strncmp,
(CPU_FEATURE_USABLE (AVX512VL)
- && CPU_FEATURE_USABLE (AVX512BW)),
+ && CPU_FEATURE_USABLE (AVX512BW)
+ && CPU_FEATURE_USABLE (BMI2)),
__strncmp_evex)
X86_IFUNC_IMPL_ADD_V3 (array, i, strncmp,
- CPU_FEATURE_USABLE (AVX2),
+ (CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)),
__strncmp_avx2)
X86_IFUNC_IMPL_ADD_V3 (array, i, strncmp,
(CPU_FEATURE_USABLE (AVX2)
+ && CPU_FEATURE_USABLE (BMI2)
&& CPU_FEATURE_USABLE (RTM)),
__strncmp_avx2_rtm)
X86_IFUNC_IMPL_ADD_V2 (array, i, strncmp,
diff --git a/sysdeps/x86_64/multiarch/strncmp.c b/sysdeps/x86_64/multiarch/strncmp.c
index 4ebe4bde3099..c4f8b6bbb5ee 100644
--- a/sysdeps/x86_64/multiarch/strncmp.c
+++ b/sysdeps/x86_64/multiarch/strncmp.c
@@ -41,12 +41,12 @@ IFUNC_SELECTOR (void)
const struct cpu_features *cpu_features = __get_cpu_features ();
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 (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
- && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW)
- && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2))
+ && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
return OPTIMIZE (evex);
if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
--
2.38.0
