x86-64: Use fxsave/xsave/xsavec in _dl_runtime_resolve [BZ #21265]hjl/pr21265/2.25

In _dl_runtime_resolve, use fxsave/xsave/xsavec to preserve all vector,
mask and bound registers.  It simplifies _dl_runtime_resolve and supports
different calling conventions.  ld.so code size is reduced by more than
1 KB.  However, use fxsave/xsave/xsavec takes a little bit more cycles
than saving and restoring vector and bound registers individually.

Latency for _dl_runtime_resolve to lookup the function, foo, from one
shared library plus libc.so:

                             Before    After     Change

Westmere (SSE)/fxsave         345      866       151%
IvyBridge (AVX)/xsave         420      643       53%
Haswell (AVX)/xsave           713      1252      75%
Skylake (AVX+MPX)/xsavec      559      719       28%
Skylake (AVX512+MPX)/xsavec   145      272       87%
Ryzen (AVX)/xsavec            280      553       97%

This is the worst case where portion of time spent for saving and
restoring registers is bigger than majority of cases.  With smaller
_dl_runtime_resolve code size, overall performance impact is negligible.

On IvyBridge, differences in build and test time of binutils with lazy
binding GCC and binutils are noises.  On Westmere, differences in
bootstrap and "makc check" time of GCC 7 with lazy binding GCC and
binutils are also noises.

	[BZ #21265]
	* sysdeps/x86/cpu-features-offsets.sym (XSAVE_STATE_SIZE_OFFSET):
	New.
	* sysdeps/x86/cpu-features.c: Include <libc-internal.h>.
	(get_common_indeces): Set xsave_state_size and
	bit_arch_XSAVEC_Usable if needed.
	(init_cpu_features): Remove bit_arch_Use_dl_runtime_resolve_slow
	and bit_arch_Use_dl_runtime_resolve_opt.
	* sysdeps/x86/cpu-features.h (bit_arch_Use_dl_runtime_resolve_opt):
	Removed.
	(bit_arch_Use_dl_runtime_resolve_slow): Likewise.
	(bit_arch_Prefer_No_AVX512): Updated.
	(bit_arch_MathVec_Prefer_No_AVX512): Likewise.
	(bit_arch_XSAVEC_Usable): New.
	(STATE_SAVE_OFFSET): Likewise.
	(STATE_SAVE_MASK): Likewise.
	[__ASSEMBLER__]: Include <cpu-features-offsets.h>.
	(cpu_features): Add xsave_state_size.
	(index_arch_Use_dl_runtime_resolve_opt): Removed.
	(index_arch_Use_dl_runtime_resolve_slow): Likewise.
	(index_arch_XSAVEC_Usable): New.
	* sysdeps/x86_64/dl-machine.h (elf_machine_runtime_setup):
	Replace _dl_runtime_resolve_sse, _dl_runtime_resolve_avx,
	_dl_runtime_resolve_avx_slow, _dl_runtime_resolve_avx_opt,
	_dl_runtime_resolve_avx512 and _dl_runtime_resolve_avx512_opt
	with _dl_runtime_resolve_fxsave, _dl_runtime_resolve_xsave and
	_dl_runtime_resolve_xsavec.
	* sysdeps/x86_64/dl-trampoline.S (DL_RUNTIME_UNALIGNED_VEC_SIZE):
	Removed.
	(DL_RUNTIME_RESOLVE_REALIGN_STACK): Check STATE_SAVE_ALIGNMENT
	instead of VEC_SIZE.
	(REGISTER_SAVE_BND0): Removed.
	(REGISTER_SAVE_BND1): Likewise.
	(REGISTER_SAVE_BND3): Likewise.
	(REGISTER_SAVE_RAX): Always defined to 0.
	(VMOV): Removed.
	(_dl_runtime_resolve_avx): Likewise.
	(_dl_runtime_resolve_avx_slow): Likewise.
	(_dl_runtime_resolve_avx_opt): Likewise.
	(_dl_runtime_resolve_avx512): Likewise.
	(_dl_runtime_resolve_avx512_opt): Likewise.
	(_dl_runtime_resolve_sse): Likewise.
	(_dl_runtime_resolve_sse_vex): Likewise.
	(USE_FXSAVE): New.
	(_dl_runtime_resolve_fxsave): Likewise.
	(USE_XSAVE): Likewise.
	(_dl_runtime_resolve_xsave): Likewise.
	(USE_XSAVEC): Likewise.
	(_dl_runtime_resolve_xsavec): Likewise.
	* sysdeps/x86_64/dl-trampoline.h (_dl_runtime_resolve_avx512):
	Removed.
	(_dl_runtime_resolve_avx512_opt): Likewise.
	(_dl_runtime_resolve_avx): Likewise.
	(_dl_runtime_resolve_avx_opt): Likewise.
	(_dl_runtime_resolve_sse): Likewise.
	(_dl_runtime_resolve_sse_vex): Likewise.
	(_dl_runtime_resolve_fxsave): New.
	(_dl_runtime_resolve_xsave): Likewise.
	(_dl_runtime_resolve_xsavec): Likewise.

(cherry picked from commit b52b0d793dcb226ecb0ecca1e672ca265973233c)

1 files changed, 29 insertions, 58 deletions

diff --git a/sysdeps/x86_64/dl-trampoline.S b/sysdeps/x86_64/dl-trampoline.S
index c14c61aa58..a645572e44 100644
--- a/sysdeps/x86_64/dl-trampoline.S
+++ b/sysdeps/x86_64/dl-trampoline.S
@@ -34,41 +34,24 @@
 # define DL_STACK_ALIGNMENT 8
 #endif
 
-#ifndef DL_RUNTIME_UNALIGNED_VEC_SIZE
-/* The maximum size in bytes of unaligned vector load and store in the
-   dynamic linker.  Since SSE optimized memory/string functions with
-   aligned SSE register load and store are used in the dynamic linker,
-   we must set this to 8 so that _dl_runtime_resolve_sse will align the
-   stack before calling _dl_fixup.  */
-# define DL_RUNTIME_UNALIGNED_VEC_SIZE 8
-#endif
-
-/* True if _dl_runtime_resolve should align stack to VEC_SIZE bytes.  */
+/* 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 \
-  (VEC_SIZE > DL_STACK_ALIGNMENT \
-   && VEC_SIZE > DL_RUNTIME_UNALIGNED_VEC_SIZE)
-
-/* Align vector register save area to 16 bytes.  */
-#define REGISTER_SAVE_VEC_OFF	0
+  (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)
@@ -80,68 +63,56 @@
 
 #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		32
 #define VMOVA			vmovdqa
-#if DL_RUNTIME_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_resolve_opt	_dl_runtime_resolve_avx_opt
 #define _dl_runtime_profile	_dl_runtime_profile_avx
 #include "dl-trampoline.h"
-#undef _dl_runtime_resolve
-#undef _dl_runtime_resolve_opt
 #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_RUNTIME_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_resolve
 #undef _dl_runtime_profile
-#undef VMOV
+#undef VEC
 #undef VMOVA
+#undef VEC_SIZE
 
-/* Used by _dl_runtime_resolve_avx_opt/_dl_runtime_resolve_avx512_opt
-   to preserve the full vector registers with zero upper bits.  */
-#define VMOVA			vmovdqa
-#if DL_RUNTIME_RESOLVE_REALIGN_STACK || VEC_SIZE <= DL_STACK_ALIGNMENT
-# define VMOV			vmovdqa
-#else
-# define VMOV			vmovdqu
-#endif
-#define _dl_runtime_resolve	_dl_runtime_resolve_sse_vex
-#define _dl_runtime_resolve_opt	_dl_runtime_resolve_avx512_opt
+#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