summaryrefslogtreecommitdiff
path: root/sysdeps/x86_64/dl-trampoline.S
diff options
context:
space:
mode:
Diffstat (limited to 'sysdeps/x86_64/dl-trampoline.S')
-rw-r--r--sysdeps/x86_64/dl-trampoline.S103
1 files changed, 45 insertions, 58 deletions
diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S
index 9fb6b13983..ef1425cbb9 100644
--- a/sysdeps/x86_64/dl-trampoline.S
+++ b/sysdeps/x86_64/dl-trampoline.S
@@ -1,5 +1,5 @@
/* PLT trampolines. x86-64 version.
- Copyright (C) 2004-2016 Free Software Foundation, Inc.
+ Copyright (C) 2004-2018 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
@@ -18,6 +18,7 @@
#include <config.h>
#include <sysdep.h>
+#include <cpu-features.h>
#include <link-defines.h>
#ifndef DL_STACK_ALIGNMENT
@@ -33,37 +34,24 @@
# define DL_STACK_ALIGNMENT 8
#endif
-#ifndef DL_RUNIME_UNALIGNED_VEC_SIZE
-/* The maximum size of unaligned vector load and store. */
-# define DL_RUNIME_UNALIGNED_VEC_SIZE 16
-#endif
-
-/* True if _dl_runtime_resolve should align stack to VEC_SIZE bytes. */
-#define DL_RUNIME_RESOLVE_REALIGN_STACK \
- (VEC_SIZE > DL_STACK_ALIGNMENT \
- && VEC_SIZE > DL_RUNIME_UNALIGNED_VEC_SIZE)
-
-/* Align vector register save area to 16 bytes. */
-#define REGISTER_SAVE_VEC_OFF 0
+/* True if _dl_runtime_resolve should align stack for STATE_SAVE or align
+ stack to 16 bytes before calling _dl_fixup. */
+#define DL_RUNTIME_RESOLVE_REALIGN_STACK \
+ (STATE_SAVE_ALIGNMENT > DL_STACK_ALIGNMENT \
+ || 16 > DL_STACK_ALIGNMENT)
/* Area on stack to save and restore registers used for parameter
passing when calling _dl_fixup. */
#ifdef __ILP32__
-# define REGISTER_SAVE_RAX (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8)
# define PRESERVE_BND_REGS_PREFIX
#else
-/* Align bound register save area to 16 bytes. */
-# define REGISTER_SAVE_BND0 (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 8)
-# define REGISTER_SAVE_BND1 (REGISTER_SAVE_BND0 + 16)
-# define REGISTER_SAVE_BND2 (REGISTER_SAVE_BND1 + 16)
-# define REGISTER_SAVE_BND3 (REGISTER_SAVE_BND2 + 16)
-# define REGISTER_SAVE_RAX (REGISTER_SAVE_BND3 + 16)
# ifdef HAVE_MPX_SUPPORT
# define PRESERVE_BND_REGS_PREFIX bnd
# else
# define PRESERVE_BND_REGS_PREFIX .byte 0xf2
# endif
#endif
+#define REGISTER_SAVE_RAX 0
#define REGISTER_SAVE_RCX (REGISTER_SAVE_RAX + 8)
#define REGISTER_SAVE_RDX (REGISTER_SAVE_RCX + 8)
#define REGISTER_SAVE_RSI (REGISTER_SAVE_RDX + 8)
@@ -73,59 +61,58 @@
#define RESTORE_AVX
-#ifdef HAVE_AVX512_ASM_SUPPORT
-# define VEC_SIZE 64
-# define VMOVA vmovdqa64
-# if DL_RUNIME_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
-#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
-#endif
+#define VEC_SIZE 64
+#define VMOVA vmovdqa64
+#define VEC(i) zmm##i
+#define _dl_runtime_profile _dl_runtime_profile_avx512
+#include "dl-trampoline.h"
+#undef _dl_runtime_profile
+#undef VEC
+#undef VMOVA
+#undef VEC_SIZE
#define VEC_SIZE 32
#define VMOVA vmovdqa
-#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
-# define VMOV vmovdqa
-#else
-# define VMOV vmovdqu
-#endif
#define VEC(i) ymm##i
-#define _dl_runtime_resolve _dl_runtime_resolve_avx
#define _dl_runtime_profile _dl_runtime_profile_avx
#include "dl-trampoline.h"
-#undef _dl_runtime_resolve
#undef _dl_runtime_profile
#undef VEC
-#undef VMOV
#undef VMOVA
#undef VEC_SIZE
/* movaps/movups is 1-byte shorter. */
#define VEC_SIZE 16
#define VMOVA movaps
-#if DL_RUNIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
-# define VMOV movaps
-#else
-# define VMOV movups
-#endif
#define VEC(i) xmm##i
-#define _dl_runtime_resolve _dl_runtime_resolve_sse
#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 USE_XSAVE
+#define STATE_SAVE_ALIGNMENT 64
+#define _dl_runtime_resolve _dl_runtime_resolve_xsave
+#include "dl-trampoline.h"
+#undef _dl_runtime_resolve
+#undef USE_XSAVE
+#undef STATE_SAVE_ALIGNMENT
+
+#define USE_XSAVEC
+#define STATE_SAVE_ALIGNMENT 64
+#define _dl_runtime_resolve _dl_runtime_resolve_xsavec
+#include "dl-trampoline.h"
+#undef _dl_runtime_resolve
+#undef USE_XSAVEC
+#undef STATE_SAVE_ALIGNMENT