aboutsummaryrefslogtreecommitdiff
path: root/sysdeps/x86_64/dl-trampoline.S
diff options
context:
space:
mode:
authorH.J. Lu <hjl.tools@gmail.com>2016-07-01 05:54:43 -0700
committerH.J. Lu <hjl.tools@gmail.com>2016-07-01 06:03:05 -0700
commitf43cb35c9b3c35addc6dc0f1427caf51786ca1d2 (patch)
treea2c943de50b515cca9d14ea8e26d6c76152de139 /sysdeps/x86_64/dl-trampoline.S
parentee2196bb6766ca7e63a1ba22ebb7619a3266776a (diff)
downloadglibc-f43cb35c9b3c35addc6dc0f1427caf51786ca1d2.zip
glibc-f43cb35c9b3c35addc6dc0f1427caf51786ca1d2.tar.gz
glibc-f43cb35c9b3c35addc6dc0f1427caf51786ca1d2.tar.bz2
Require binutils 2.24 to build x86-64 glibc [BZ #20139]
If assembler doesn't support AVX512DQ, _dl_runtime_resolve_avx is used to save the first 8 vector registers, which only saves the lower 256 bits of vector register, for lazy binding. When it is called on AVX512 platform, the upper 256 bits of ZMM registers are clobbered. Parameters passed in ZMM registers will be wrong when the function is called the first time. This patch requires binutils 2.24, whose assembler can store and load ZMM registers, to build x86-64 glibc. Since mathvec library needs assembler support for AVX512DQ, we disable mathvec if assembler doesn't support AVX512DQ. [BZ #20139] * config.h.in (HAVE_AVX512_ASM_SUPPORT): Renamed to ... (HAVE_AVX512DQ_ASM_SUPPORT): This. * sysdeps/x86_64/configure.ac: Require assembler from binutils 2.24 or above. (HAVE_AVX512_ASM_SUPPORT): Removed. (HAVE_AVX512DQ_ASM_SUPPORT): New. * sysdeps/x86_64/configure: Regenerated. * sysdeps/x86_64/dl-trampoline.S: Make HAVE_AVX512_ASM_SUPPORT check unconditional. * sysdeps/x86_64/multiarch/ifunc-impl-list.c: Likewise. * sysdeps/x86_64/multiarch/memcpy.S: Likewise. * sysdeps/x86_64/multiarch/memcpy_chk.S: Likewise. * sysdeps/x86_64/multiarch/memmove-avx512-no-vzeroupper.S: Likewise. * sysdeps/x86_64/multiarch/memmove-avx512-unaligned-erms.S: Likewise. * sysdeps/x86_64/multiarch/memmove.S: Likewise. * sysdeps/x86_64/multiarch/memmove_chk.S: Likewise. * sysdeps/x86_64/multiarch/mempcpy.S: Likewise. * sysdeps/x86_64/multiarch/mempcpy_chk.S: Likewise. * sysdeps/x86_64/multiarch/memset-avx512-no-vzeroupper.S: Likewise. * sysdeps/x86_64/multiarch/memset-avx512-unaligned-erms.S: Likewise. * sysdeps/x86_64/multiarch/memset.S: Likewise. * sysdeps/x86_64/multiarch/memset_chk.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_cos8_core_avx512.S: Check HAVE_AVX512DQ_ASM_SUPPORT instead of HAVE_AVX512_ASM_SUPPORT. * sysdeps/x86_64/fpu/multiarch/svml_d_exp8_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_log8_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_pow8_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sin8_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_cosf16_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_expf16_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_logf16_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_powf16_core_avx512.S: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx51: Likewise. * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S: Likewise.
Diffstat (limited to 'sysdeps/x86_64/dl-trampoline.S')
-rw-r--r--sysdeps/x86_64/dl-trampoline.S37
1 files changed, 15 insertions, 22 deletions
diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S
index 39b8771..12f1a5cf 100644
--- a/sysdeps/x86_64/dl-trampoline.S
+++ b/sysdeps/x86_64/dl-trampoline.S
@@ -77,30 +77,23 @@
#define RESTORE_AVX
-#ifdef HAVE_AVX512_ASM_SUPPORT
-# define VEC_SIZE 64
-# define VMOVA vmovdqa64
-# if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
-# define VMOV vmovdqa64
-# else
-# define VMOV vmovdqu64
-# endif
-# define VEC(i) zmm##i
-# define _dl_runtime_resolve _dl_runtime_resolve_avx512
-# define _dl_runtime_profile _dl_runtime_profile_avx512
-# include "dl-trampoline.h"
-# undef _dl_runtime_resolve
-# undef _dl_runtime_profile
-# undef VEC
-# undef VMOV
-# undef VMOVA
-# undef VEC_SIZE
+#define VEC_SIZE 64
+#define VMOVA vmovdqa64
+#if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
+# define VMOV vmovdqa64
#else
-strong_alias (_dl_runtime_resolve_avx, _dl_runtime_resolve_avx512)
- .hidden _dl_runtime_resolve_avx512
-strong_alias (_dl_runtime_profile_avx, _dl_runtime_profile_avx512)
- .hidden _dl_runtime_profile_avx512
+# define VMOV vmovdqu64
#endif
+#define VEC(i) zmm##i
+#define _dl_runtime_resolve _dl_runtime_resolve_avx512
+#define _dl_runtime_profile _dl_runtime_profile_avx512
+#include "dl-trampoline.h"
+#undef _dl_runtime_resolve
+#undef _dl_runtime_profile
+#undef VEC
+#undef VMOV
+#undef VMOVA
+#undef VEC_SIZE
#define VEC_SIZE 32
#define VMOVA vmovdqa