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>

diff --git a/sysdeps/x86/isa-level.h b/sysdeps/x86/isa-level.h
index 3c4480a..bbb90f5 100644 (file)
--- a/sysdeps/x86/isa-level.h
+++ b/sysdeps/x86/isa-level.h
@@ -80,6 +80,7 @@
 #define AVX_X86_ISA_LEVEL 3
 #define AVX2_X86_ISA_LEVEL 3
 #define BMI2_X86_ISA_LEVEL 3
+#define LZCNT_X86_ISA_LEVEL 3
 #define MOVBE_X86_ISA_LEVEL 3
 
 /* ISA level >= 2 guaranteed includes.  */

diff --git a/sysdeps/x86_64/multiarch/ifunc-avx2.h b/sysdeps/x86_64/multiarch/ifunc-avx2.h
index a57a995..f174108 100644 (file)
--- a/sysdeps/x86_64/multiarch/ifunc-avx2.h
+++ b/sysdeps/x86_64/multiarch/ifunc-avx2.h
@@ -37,6 +37,7 @@ IFUNC_SELECTOR (void)
 
   if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2)
       && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, BMI2)
+      && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, LZCNT)
       && X86_ISA_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 7c84963..ec1c5b5 100644 (file)
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -209,13 +209,19 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
   IFUNC_IMPL (i, name, memrchr,
              X86_IFUNC_IMPL_ADD_V4 (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)
              X86_IFUNC_IMPL_ADD_V3 (array, i, memrchr,
-                                    CPU_FEATURE_USABLE (AVX2),
+                                    (CPU_FEATURE_USABLE (AVX2)
+                                     && CPU_FEATURE_USABLE (BMI2)
+                                     && CPU_FEATURE_USABLE (LZCNT)),
                                     __memrchr_avx2)
              X86_IFUNC_IMPL_ADD_V3 (array, i, memrchr,
                                     (CPU_FEATURE_USABLE (AVX2)
+                                     && CPU_FEATURE_USABLE (BMI2)
+                                     && CPU_FEATURE_USABLE (LZCNT)
                                      && CPU_FEATURE_USABLE (RTM)),
                                     __memrchr_avx2_rtm)
              /* ISA V2 wrapper for SSE2 implementation because the SSE2