about summary refs log tree commit diff
diff options
context:
space:
mode:
authorAurelien Jarno <aurelien@aurel32.net>2022-10-03 23:16:46 +0200
committerAurelien Jarno <aurelien@aurel32.net>2022-10-04 00:03:20 +0200
commit67e310afb91fa27295f7cf5140176efd6ba5dd51 (patch)
treec8d694e61d6d2207fa7e6a95665232fd8fda0fb8
parent38e321f4ac70b6aecb35a8af7d1a2fbe366ab482 (diff)
downloadglibc-67e310afb91fa27295f7cf5140176efd6ba5dd51.tar.gz
glibc-67e310afb91fa27295f7cf5140176efd6ba5dd51.tar.xz
glibc-67e310afb91fa27295f7cf5140176efd6ba5dd51.zip
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  <goldstein.w.n@gmail.com>
(cherry picked from commit 7e8283170c5d6805b609a040801d819e362a6292)
-rw-r--r--sysdeps/x86_64/multiarch/ifunc-avx2.h1
-rw-r--r--sysdeps/x86_64/multiarch/ifunc-impl-list.c17
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 52bd00ea5c..877f007dd6 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 d1fc1e75d6..84f9e73e2b 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -498,15 +498,21 @@ __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))
 
@@ -687,15 +693,20 @@ __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))