diff mbox series

[v2,5/6] x86-64: Require BMI1/BMI2 for AVX2 strrchr and wcsrchr implementations

Message ID 20221002123424.3079805-6-aurelien@aurel32.net
State New
Headers show
Series x86: Fix AVX2 string functions requiring BMI1, BMI2 or LZCNT (BZ #29611) | expand

Commit Message

Aurelien Jarno Oct. 2, 2022, 12:34 p.m. UTC
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
---
 sysdeps/x86/isa-level.h                    |  1 +
 sysdeps/x86_64/multiarch/ifunc-avx2.h      |  1 +
 sysdeps/x86_64/multiarch/ifunc-impl-list.c | 17 ++++++++++++++---
 3 files changed, 16 insertions(+), 3 deletions(-)

Comments

Noah Goldstein Oct. 2, 2022, 9:08 p.m. UTC | #1
On Sun, Oct 2, 2022 at 8:34 AM Aurelien Jarno <aurelien@aurel32.net> wrote:
>
> 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
> ---
>  sysdeps/x86/isa-level.h                    |  1 +
>  sysdeps/x86_64/multiarch/ifunc-avx2.h      |  1 +
>  sysdeps/x86_64/multiarch/ifunc-impl-list.c | 17 ++++++++++++++---
>  3 files changed, 16 insertions(+), 3 deletions(-)
>
> diff --git a/sysdeps/x86/isa-level.h b/sysdeps/x86/isa-level.h
> index bbb90f5c5e..06f6c9663e 100644
> --- a/sysdeps/x86/isa-level.h
> +++ b/sysdeps/x86/isa-level.h
> @@ -79,6 +79,7 @@
>  /* ISA level >= 3 guaranteed includes.  */
>  #define AVX_X86_ISA_LEVEL 3
>  #define AVX2_X86_ISA_LEVEL 3
> +#define BMI1_X86_ISA_LEVEL 3
>  #define BMI2_X86_ISA_LEVEL 3
>  #define LZCNT_X86_ISA_LEVEL 3
>  #define MOVBE_X86_ISA_LEVEL 3
> diff --git a/sysdeps/x86_64/multiarch/ifunc-avx2.h b/sysdeps/x86_64/multiarch/ifunc-avx2.h
> index f1741083fd..f2f5e8a211 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-avx2.h
> +++ b/sysdeps/x86_64/multiarch/ifunc-avx2.h
> @@ -36,6 +36,7 @@ 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, BMI1)
>        && 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,
> diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> index 4ee28c99bd..1c8afa229f 100644
> --- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> +++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
> @@ -575,13 +575,19 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
>    IFUNC_IMPL (i, name, strrchr,
>               X86_IFUNC_IMPL_ADD_V4 (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)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, strrchr,
> -                                    CPU_FEATURE_USABLE (AVX2),
> +                                    (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)),
>                                      __strrchr_avx2)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, strrchr,
>                                      (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)
>                                       && CPU_FEATURE_USABLE (RTM)),
>                                      __strrchr_avx2_rtm)
>               /* ISA V2 wrapper for SSE2 implementation because the SSE2
> @@ -794,13 +800,18 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
>               X86_IFUNC_IMPL_ADD_V4 (array, i, wcsrchr,
>                                      (CPU_FEATURE_USABLE (AVX512VL)
>                                       && CPU_FEATURE_USABLE (AVX512BW)
> +                                     && CPU_FEATURE_USABLE (BMI1)
>                                       && CPU_FEATURE_USABLE (BMI2)),
>                                      __wcsrchr_evex)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, wcsrchr,
> -                                    CPU_FEATURE_USABLE (AVX2),
> +                                    (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)),
>                                      __wcsrchr_avx2)
>               X86_IFUNC_IMPL_ADD_V3 (array, i, wcsrchr,
>                                      (CPU_FEATURE_USABLE (AVX2)
> +                                     && CPU_FEATURE_USABLE (BMI1)
> +                                     && CPU_FEATURE_USABLE (BMI2)
>                                       && CPU_FEATURE_USABLE (RTM)),
>                                      __wcsrchr_avx2_rtm)
>               /* ISA V2 wrapper for SSE2 implementation because the SSE2
> --
> 2.35.1
>

LGTM.
diff mbox series

Patch

diff --git a/sysdeps/x86/isa-level.h b/sysdeps/x86/isa-level.h
index bbb90f5c5e..06f6c9663e 100644
--- a/sysdeps/x86/isa-level.h
+++ b/sysdeps/x86/isa-level.h
@@ -79,6 +79,7 @@ 
 /* ISA level >= 3 guaranteed includes.  */
 #define AVX_X86_ISA_LEVEL 3
 #define AVX2_X86_ISA_LEVEL 3
+#define BMI1_X86_ISA_LEVEL 3
 #define BMI2_X86_ISA_LEVEL 3
 #define LZCNT_X86_ISA_LEVEL 3
 #define MOVBE_X86_ISA_LEVEL 3
diff --git a/sysdeps/x86_64/multiarch/ifunc-avx2.h b/sysdeps/x86_64/multiarch/ifunc-avx2.h
index f1741083fd..f2f5e8a211 100644
--- a/sysdeps/x86_64/multiarch/ifunc-avx2.h
+++ b/sysdeps/x86_64/multiarch/ifunc-avx2.h
@@ -36,6 +36,7 @@  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, BMI1)
       && 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,
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index 4ee28c99bd..1c8afa229f 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -575,13 +575,19 @@  __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
   IFUNC_IMPL (i, name, strrchr,
 	      X86_IFUNC_IMPL_ADD_V4 (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)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, strrchr,
-				     CPU_FEATURE_USABLE (AVX2),
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI1)
+				      && CPU_FEATURE_USABLE (BMI2)),
 				     __strrchr_avx2)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, strrchr,
 				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI1)
+				      && CPU_FEATURE_USABLE (BMI2)
 				      && CPU_FEATURE_USABLE (RTM)),
 				     __strrchr_avx2_rtm)
 	      /* ISA V2 wrapper for SSE2 implementation because the SSE2
@@ -794,13 +800,18 @@  __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 	      X86_IFUNC_IMPL_ADD_V4 (array, i, wcsrchr,
 				     (CPU_FEATURE_USABLE (AVX512VL)
 				      && CPU_FEATURE_USABLE (AVX512BW)
+				      && CPU_FEATURE_USABLE (BMI1)
 				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcsrchr_evex)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcsrchr,
-				     CPU_FEATURE_USABLE (AVX2),
+				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI1)
+				      && CPU_FEATURE_USABLE (BMI2)),
 				     __wcsrchr_avx2)
 	      X86_IFUNC_IMPL_ADD_V3 (array, i, wcsrchr,
 				     (CPU_FEATURE_USABLE (AVX2)
+				      && CPU_FEATURE_USABLE (BMI1)
+				      && CPU_FEATURE_USABLE (BMI2)
 				      && CPU_FEATURE_USABLE (RTM)),
 				     __wcsrchr_avx2_rtm)
 	      /* ISA V2 wrapper for SSE2 implementation because the SSE2