[glibc/release/2.34/master] x86-64: Require BMI2 for AVX2 str(n)casecmp implementations

[glibc/release/2.34/master] x86-64: Require BMI2 for AVX2 str(n)casecmp implementations

[Aurelien Jarno]

https://sourceware.org/git/gitweb.cgi?p=glibc.git;h=414fc856ff4e011e62b88a21d30294637a152dc7

commit 414fc856ff4e011e62b88a21d30294637a152dc7
Author: Aurelien Jarno <aurelien@aurel32.net>
Date:   Mon Oct 3 23:16:46 2022 +0200

    x86-64: Require BMI2 for AVX2 str(n)casecmp implementations
    
    The AVX2 str(n)casecmp implementations use 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 10f79d3670b036925da63dc532b122d27ce65ff8)

Diff:
---
 sysdeps/x86_64/multiarch/ifunc-impl-list.c  | 28 ++++++++++++++++++++--------
 sysdeps/x86_64/multiarch/ifunc-strcasecmp.h |  1 +
 2 files changed, 21 insertions(+), 8 deletions(-)

diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index 8d649e263e..ca64b34c14 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -386,13 +386,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
   IFUNC_IMPL (i, name, strcasecmp,
 	      IFUNC_IMPL_ADD (array, i, strcasecmp,
 			      (CPU_FEATURE_USABLE (AVX512VL)
-			       && CPU_FEATURE_USABLE (AVX512BW)),
+			       && CPU_FEATURE_USABLE (AVX512BW)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strcasecmp_evex)
 	      IFUNC_IMPL_ADD (array, i, strcasecmp,
-			      CPU_FEATURE_USABLE (AVX2),
+			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strcasecmp_avx2)
 	      IFUNC_IMPL_ADD (array, i, strcasecmp,
 			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)
 			       && CPU_FEATURE_USABLE (RTM)),
 			      __strcasecmp_avx2_rtm)
 	      IFUNC_IMPL_ADD (array, i, strcasecmp,
@@ -407,13 +410,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
   IFUNC_IMPL (i, name, strcasecmp_l,
 	      IFUNC_IMPL_ADD (array, i, strcasecmp,
 			      (CPU_FEATURE_USABLE (AVX512VL)
-			       && CPU_FEATURE_USABLE (AVX512BW)),
+			       && CPU_FEATURE_USABLE (AVX512BW)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strcasecmp_l_evex)
 	      IFUNC_IMPL_ADD (array, i, strcasecmp,
-			      CPU_FEATURE_USABLE (AVX2),
+			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strcasecmp_l_avx2)
 	      IFUNC_IMPL_ADD (array, i, strcasecmp,
 			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)
 			       && CPU_FEATURE_USABLE (RTM)),
 			      __strcasecmp_l_avx2_rtm)
 	      IFUNC_IMPL_ADD (array, i, strcasecmp_l,
@@ -542,13 +548,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
   IFUNC_IMPL (i, name, strncasecmp,
 	      IFUNC_IMPL_ADD (array, i, strncasecmp,
 			      (CPU_FEATURE_USABLE (AVX512VL)
-			       && CPU_FEATURE_USABLE (AVX512BW)),
+			       && CPU_FEATURE_USABLE (AVX512BW)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strncasecmp_evex)
 	      IFUNC_IMPL_ADD (array, i, strncasecmp,
-			      CPU_FEATURE_USABLE (AVX2),
+			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strncasecmp_avx2)
 	      IFUNC_IMPL_ADD (array, i, strncasecmp,
 			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)
 			       && CPU_FEATURE_USABLE (RTM)),
 			      __strncasecmp_avx2_rtm)
 	      IFUNC_IMPL_ADD (array, i, strncasecmp,
@@ -564,13 +573,16 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
   IFUNC_IMPL (i, name, strncasecmp_l,
 	      IFUNC_IMPL_ADD (array, i, strncasecmp,
 			      (CPU_FEATURE_USABLE (AVX512VL)
-			       && CPU_FEATURE_USABLE (AVX512BW)),
+			       & CPU_FEATURE_USABLE (AVX512BW)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strncasecmp_l_evex)
 	      IFUNC_IMPL_ADD (array, i, strncasecmp,
-			      CPU_FEATURE_USABLE (AVX2),
+			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)),
 			      __strncasecmp_l_avx2)
 	      IFUNC_IMPL_ADD (array, i, strncasecmp,
 			      (CPU_FEATURE_USABLE (AVX2)
+			       && CPU_FEATURE_USABLE (BMI2)
 			       && CPU_FEATURE_USABLE (RTM)),
 			      __strncasecmp_l_avx2_rtm)
 	      IFUNC_IMPL_ADD (array, i, strncasecmp_l,
diff --git a/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h b/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
index 40819caf5a..e61d6e9497 100644
--- a/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
+++ b/sysdeps/x86_64/multiarch/ifunc-strcasecmp.h
@@ -32,6 +32,7 @@ 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, BMI2)
       && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
     {
       if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)