about summary refs log tree commit diff
path: root/sysdeps/x86_64/multiarch/ifunc-strncpy.h
diff options
context:
space:
mode:
authorNoah Goldstein <goldstein.w.n@gmail.com>2022-07-13 16:33:01 -0700
committerNoah Goldstein <goldstein.w.n@gmail.com>2022-07-16 03:07:59 -0700
commit49889fb256a7f9b894b2d16fea23de1ac25b65e2 (patch)
tree923f7a6a2eb94e4baf9141783b19df06ed9ee747 /sysdeps/x86_64/multiarch/ifunc-strncpy.h
parent192979ee351315b84ff4277d0985f26243717cd7 (diff)
downloadglibc-49889fb256a7f9b894b2d16fea23de1ac25b65e2.tar.gz
glibc-49889fb256a7f9b894b2d16fea23de1ac25b65e2.tar.xz
glibc-49889fb256a7f9b894b2d16fea23de1ac25b65e2.zip
x86: Add support to build st{p|r}{n}{cpy|cat} with explicit ISA level
1. Add default ISA level selection in non-multiarch/rtld
   implementations.

2. Add ISA level build guards to different implementations.
    - I.e strcpy-avx2.S which is ISA level 3 will only build if
      compiled ISA level <= 3. Otherwise there is no reason to
      include it as we will always use one of the ISA level 4
      implementations (strcpy-evex.S).

3. Refactor the ifunc selector and ifunc implementation list to use
   the ISA level aware wrapper macros that allow functions below the
   compiled ISA level (with a guranteed replacement) to be skipped.

Tested with and without multiarch on x86_64 for ISA levels:
{generic, x86-64-v2, x86-64-v3, x86-64-v4}

And m32 with and without multiarch.
Diffstat (limited to 'sysdeps/x86_64/multiarch/ifunc-strncpy.h')
-rw-r--r--sysdeps/x86_64/multiarch/ifunc-strncpy.h22
1 files changed, 13 insertions, 9 deletions
diff --git a/sysdeps/x86_64/multiarch/ifunc-strncpy.h b/sysdeps/x86_64/multiarch/ifunc-strncpy.h
index 323225af4d..5c1c46b885 100644
--- a/sysdeps/x86_64/multiarch/ifunc-strncpy.h
+++ b/sysdeps/x86_64/multiarch/ifunc-strncpy.h
@@ -19,28 +19,32 @@
 
 #include <init-arch.h>
 
-extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_unaligned)
-  attribute_hidden;
+extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden;
+
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_rtm) attribute_hidden;
-extern __typeof (REDIRECT_NAME) OPTIMIZE (evex) attribute_hidden;
+
+extern __typeof (REDIRECT_NAME)
+    OPTIMIZE (sse2_unaligned) attribute_hidden;
 
 static inline void *
 IFUNC_SELECTOR (void)
 {
-  const struct cpu_features* cpu_features = __get_cpu_features ();
+  const struct cpu_features *cpu_features = __get_cpu_features ();
 
-  if (CPU_FEATURE_USABLE_P (cpu_features, AVX2)
-      && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
+  if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX2)
+      && X86_ISA_CPU_FEATURES_ARCH_P (cpu_features,
+				      AVX_Fast_Unaligned_Load, ))
     {
-      if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
-	  && CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
+      if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512VL)
+	  && X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512BW))
 	return OPTIMIZE (evex);
 
       if (CPU_FEATURE_USABLE_P (cpu_features, RTM))
 	return OPTIMIZE (avx2_rtm);
 
-      if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER))
+      if (X86_ISA_CPU_FEATURES_ARCH_P (cpu_features,
+				       Prefer_No_VZEROUPPER, !))
 	return OPTIMIZE (avx2);
     }