x86-64: Only define used SSE/AVX/AVX512 run-time resolvers

When glibc is built with x86-64 ISA level v3, SSE run-time resolvers
aren't used.  For x86-64 ISA level v4 build, both SSE and AVX resolvers
are unused.  Check the minimum x86-64 ISA level to exclude the unused
run-time resolvers.

diff --git a/sysdeps/x86/isa-level.h b/sysdeps/x86/isa-level.h
index c6156e7f7ac7ece501ad543e79c253ee5e2a5485..f293aea9068cc2a9034c0a3be383f4fe0a770f8b 100644 (file)
--- a/sysdeps/x86/isa-level.h
+++ b/sysdeps/x86/isa-level.h
@@ -68,10 +68,12 @@
    compile-time constant.. */
 
 /* ISA level >= 4 guaranteed includes.  */
+#define AVX512F_X86_ISA_LEVEL 4
 #define AVX512VL_X86_ISA_LEVEL 4
 #define AVX512BW_X86_ISA_LEVEL 4
 
 /* ISA level >= 3 guaranteed includes.  */
+#define AVX_X86_ISA_LEVEL 3
 #define AVX2_X86_ISA_LEVEL 3
 #define BMI2_X86_ISA_LEVEL 3
 

diff --git a/sysdeps/x86_64/dl-machine.h b/sysdeps/x86_64/dl-machine.h
index 34766325aefb80c9d6b6ef6f9c9e66339321de71..005d089501fa78654e16103de9ec901af7be4ff2 100644 (file)
--- a/sysdeps/x86_64/dl-machine.h
+++ b/sysdeps/x86_64/dl-machine.h
@@ -28,6 +28,7 @@
 #include <dl-tlsdesc.h>
 #include <dl-static-tls.h>
 #include <dl-machine-rel.h>
+#include <isa-level.h>
 
 /* Return nonzero iff ELF header is compatible with the running host.  */
 static inline int __attribute__ ((unused))
@@ -86,6 +87,8 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
       /* Identify this shared object.  */
       *(ElfW(Addr) *) (got + 1) = (ElfW(Addr)) l;
 
+      const struct cpu_features* cpu_features = __get_cpu_features ();
+
       /* The got[2] entry contains the address of a function which gets
         called to get the address of a so far unresolved function and
         jump to it.  The profiling extension of the dynamic linker allows
@@ -94,9 +97,9 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
         end in this function.  */
       if (__glibc_unlikely (profile))
        {
-         if (CPU_FEATURE_USABLE (AVX512F))
+         if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX512F))
            *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_profile_avx512;
-         else if (CPU_FEATURE_USABLE (AVX))
+         else if (X86_ISA_CPU_FEATURE_USABLE_P (cpu_features, AVX))
            *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_profile_avx;
          else
            *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_profile_sse;
@@ -112,9 +115,10 @@ elf_machine_runtime_setup (struct link_map *l, struct r_scope_elem *scope[],
          /* This function will get called to fix up the GOT entry
             indicated by the offset on the stack, and then jump to
             the resolved address.  */
-         if (GLRO(dl_x86_cpu_features).xsave_state_size != 0)
+         if (MINIMUM_X86_ISA_LEVEL >= AVX_X86_ISA_LEVEL
+             || GLRO(dl_x86_cpu_features).xsave_state_size != 0)
            *(ElfW(Addr) *) (got + 2)
-             = (CPU_FEATURE_USABLE (XSAVEC)
+             = (CPU_FEATURE_USABLE_P (cpu_features, XSAVEC)
                 ? (ElfW(Addr)) &_dl_runtime_resolve_xsavec
                 : (ElfW(Addr)) &_dl_runtime_resolve_xsave);
          else

diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S
index 831a654713d1575c3bcb2a354037f7b8f1c3ef94..f669805ac5b2f01742264a871e0cced4ffa1bd5d 100644 (file)
--- a/sysdeps/x86_64/dl-trampoline.S
+++ b/sysdeps/x86_64/dl-trampoline.S
@@ -20,6 +20,7 @@
 #include <sysdep.h>
 #include <cpu-features-offsets.h>
 #include <link-defines.h>
+#include <isa-level.h>
 
 #ifndef DL_STACK_ALIGNMENT
 /* Due to GCC bug:
@@ -62,35 +63,39 @@
 #undef VMOVA
 #undef VEC_SIZE
 
-#define VEC_SIZE               32
-#define VMOVA                  vmovdqa
-#define VEC(i)                 ymm##i
-#define _dl_runtime_profile    _dl_runtime_profile_avx
-#include "dl-trampoline.h"
-#undef _dl_runtime_profile
-#undef VEC
-#undef VMOVA
-#undef VEC_SIZE
+#if MINIMUM_X86_ISA_LEVEL <= AVX_X86_ISA_LEVEL
+# define VEC_SIZE              32
+# define VMOVA                 vmovdqa
+# define VEC(i)                        ymm##i
+# define _dl_runtime_profile   _dl_runtime_profile_avx
+# include "dl-trampoline.h"
+# undef _dl_runtime_profile
+# undef VEC
+# undef VMOVA
+# undef VEC_SIZE
+#endif
 
+#if MINIMUM_X86_ISA_LEVEL < AVX_X86_ISA_LEVEL
 /* movaps/movups is 1-byte shorter.  */
-#define VEC_SIZE               16
-#define VMOVA                  movaps
-#define VEC(i)                 xmm##i
-#define _dl_runtime_profile    _dl_runtime_profile_sse
-#undef RESTORE_AVX
-#include "dl-trampoline.h"
-#undef _dl_runtime_profile
-#undef VEC
-#undef VMOVA
-#undef VEC_SIZE
-
-#define USE_FXSAVE
-#define STATE_SAVE_ALIGNMENT   16
-#define _dl_runtime_resolve    _dl_runtime_resolve_fxsave
-#include "dl-trampoline.h"
-#undef _dl_runtime_resolve
-#undef USE_FXSAVE
-#undef STATE_SAVE_ALIGNMENT
+# define VEC_SIZE              16
+# define VMOVA                 movaps
+# define VEC(i)                        xmm##i
+# define _dl_runtime_profile   _dl_runtime_profile_sse
+# undef RESTORE_AVX
+# include "dl-trampoline.h"
+# undef _dl_runtime_profile
+# undef VEC
+# undef VMOVA
+# undef VEC_SIZE
+
+# define USE_FXSAVE
+# define STATE_SAVE_ALIGNMENT  16
+# define _dl_runtime_resolve   _dl_runtime_resolve_fxsave
+# include "dl-trampoline.h"
+# undef _dl_runtime_resolve
+# undef USE_FXSAVE
+# undef STATE_SAVE_ALIGNMENT
+#endif
 
 #define USE_XSAVE
 #define STATE_SAVE_ALIGNMENT   64