x86-64: Use fxsave/xsave/xsavec in _dl_runtime_resolve [BZ #21265]hjl/pr21265/2.26

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-pointer-arith.h>.
	(get_common_indeces): Set xsave_state_size, xsave_state_full_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 and xsave_state_full_size.
	(index_arch_Use_dl_runtime_resolve_opt): Removed.
	(index_arch_Use_dl_runtime_resolve_slow): Likewise.
	(index_arch_XSAVEC_Usable): New.
	* sysdeps/x86/cpu-tunables.c (TUNABLE_CALLBACK (set_hwcaps)):
	Support XSAVEC_Usable.  Remove Use_dl_runtime_resolve_slow.
	* sysdeps/x86_64/Makefile (tst-x86_64-1-ENV): New if tunables
	is enabled.
	* 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)

8 files changed, 227 insertions, 306 deletions

diff --git a/sysdeps/x86/cpu-features-offsets.sym b/sysdeps/x86/cpu-features-offsets.sym
index f6739fae81..33dd094e37 100644
--- a/sysdeps/x86/cpu-features-offsets.sym
+++ b/sysdeps/x86/cpu-features-offsets.sym
@@ -15,6 +15,7 @@ CPUID_ECX_OFFSET	offsetof (struct cpuid_registers, ecx)
 CPUID_EDX_OFFSET	offsetof (struct cpuid_registers, edx)
 FAMILY_OFFSET		offsetof (struct cpu_features, family)
 MODEL_OFFSET		offsetof (struct cpu_features, model)
+XSAVE_STATE_SIZE_OFFSET	offsetof (struct cpu_features, xsave_state_size)
 FEATURE_OFFSET		offsetof (struct cpu_features, feature)
 FEATURE_SIZE		sizeof (unsigned int)
 
diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
index c267f17b76..3a5c3e8bfd 100644
--- a/sysdeps/x86/cpu-features.c
+++ b/sysdeps/x86/cpu-features.c
@@ -19,6 +19,7 @@
 #include <cpuid.h>
 #include <cpu-features.h>
 #include <dl-hwcap.h>
+#include <libc-pointer-arith.h>
 
 #if HAVE_TUNABLES
 # define TUNABLE_NAMESPACE tune
@@ -103,6 +104,76 @@ get_common_indeces (struct cpu_features *cpu_features,
 		}
 	    }
 	}
+
+      /* For _dl_runtime_resolve, set xsave_state_size to xsave area
+	 size + integer register save size and align it to 64 bytes.  */
+      if (cpu_features->max_cpuid >= 0xd)
+	{
+	  unsigned int eax, ebx, ecx, edx;
+
+	  __cpuid_count (0xd, 0, eax, ebx, ecx, edx);
+	  if (ebx != 0)
+	    {
+	      unsigned int xsave_state_full_size
+		= ALIGN_UP (ebx + STATE_SAVE_OFFSET, 64);
+
+	      cpu_features->xsave_state_size
+		= xsave_state_full_size;
+	      cpu_features->xsave_state_full_size
+		= xsave_state_full_size;
+
+	      __cpuid_count (0xd, 1, eax, ebx, ecx, edx);
+
+	      /* Check if XSAVEC is available.  */
+	      if ((eax & (1 << 1)) != 0)
+		{
+		  unsigned int xstate_comp_offsets[32];
+		  unsigned int xstate_comp_sizes[32];
+		  unsigned int i;
+
+		  xstate_comp_offsets[0] = 0;
+		  xstate_comp_offsets[1] = 160;
+		  xstate_comp_offsets[2] = 576;
+		  xstate_comp_sizes[0] = 160;
+		  xstate_comp_sizes[1] = 256;
+
+		  for (i = 2; i < 32; i++)
+		    {
+		      if ((STATE_SAVE_MASK & (1 << i)) != 0)
+			{
+			  __cpuid_count (0xd, i, eax, ebx, ecx, edx);
+			  xstate_comp_sizes[i] = eax;
+			}
+		      else
+			{
+			  ecx = 0;
+			  xstate_comp_sizes[i] = 0;
+			}
+
+		      if (i > 2)
+			{
+			  xstate_comp_offsets[i]
+			    = (xstate_comp_offsets[i - 1]
+			       + xstate_comp_sizes[i -1]);
+			  if ((ecx & (1 << 1)) != 0)
+			    xstate_comp_offsets[i]
+			      = ALIGN_UP (xstate_comp_offsets[i], 64);
+			}
+		    }
+
+		  /* Use XSAVEC.  */
+		  unsigned int size
+		    = xstate_comp_offsets[31] + xstate_comp_sizes[31];
+		  if (size)
+		    {
+		      cpu_features->xsave_state_size
+			= ALIGN_UP (size + STATE_SAVE_OFFSET, 64);
+		      cpu_features->feature[index_arch_XSAVEC_Usable]
+			|= bit_arch_XSAVEC_Usable;
+		    }
+		}
+	    }
+	}
     }
 }
 
@@ -242,23 +313,6 @@ init_cpu_features (struct cpu_features *cpu_features)
       else
 	cpu_features->feature[index_arch_Prefer_No_AVX512]
 	  |= bit_arch_Prefer_No_AVX512;
-
-      /* To avoid SSE transition penalty, use _dl_runtime_resolve_slow.
-         If XGETBV suports ECX == 1, use _dl_runtime_resolve_opt.
-	 Use _dl_runtime_resolve_opt only with AVX512F since it is
-	 slower than _dl_runtime_resolve_slow with AVX.  */
-      cpu_features->feature[index_arch_Use_dl_runtime_resolve_slow]
-	|= bit_arch_Use_dl_runtime_resolve_slow;
-      if (CPU_FEATURES_ARCH_P (cpu_features, AVX512F_Usable)
-	  && cpu_features->max_cpuid >= 0xd)
-	{
-	  unsigned int eax;
-
-	  __cpuid_count (0xd, 1, eax, ebx, ecx, edx);
-	  if ((eax & (1 << 2)) != 0)
-	    cpu_features->feature[index_arch_Use_dl_runtime_resolve_opt]
-	      |= bit_arch_Use_dl_runtime_resolve_opt;
-	}
     }
   /* This spells out "AuthenticAMD".  */
   else if (ebx == 0x68747541 && ecx == 0x444d4163 && edx == 0x69746e65)
diff --git a/sysdeps/x86/cpu-features.h b/sysdeps/x86/cpu-features.h
index 3ed67f5800..1d88f7a68c 100644
--- a/sysdeps/x86/cpu-features.h
+++ b/sysdeps/x86/cpu-features.h
@@ -37,9 +37,8 @@
 #define bit_arch_Prefer_No_VZEROUPPER		(1 << 17)
 #define bit_arch_Fast_Unaligned_Copy		(1 << 18)
 #define bit_arch_Prefer_ERMS			(1 << 19)
-#define bit_arch_Use_dl_runtime_resolve_opt	(1 << 20)
-#define bit_arch_Use_dl_runtime_resolve_slow	(1 << 21)
-#define bit_arch_Prefer_No_AVX512		(1 << 22)
+#define bit_arch_Prefer_No_AVX512		(1 << 20)
+#define bit_arch_XSAVEC_Usable			(1 << 21)
 
 /* CPUID Feature flags.  */
 
@@ -88,6 +87,15 @@
 /* The current maximum size of the feature integer bit array.  */
 #define FEATURE_INDEX_MAX 1
 
+/* Offset for fxsave/xsave area used by _dl_runtime_resolve.  Also need
+   space to preserve RCX, RDX, RSI, RDI, R8, R9 and RAX.  It must be
+   aligned to 16 bytes for fxsave and 64 bytes for xsave.  */
+#define STATE_SAVE_OFFSET (8 * 7 + 8)
+
+/* Save SSE, AVX, AVX512, mask and bound registers.  */
+#define STATE_SAVE_MASK \
+  ((1 << 1) | (1 << 2) | (1 << 3) | (1 << 5) | (1 << 6) | (1 << 7))
+
 #ifdef	__ASSEMBLER__
 
 # include <cpu-features-offsets.h>
@@ -123,8 +131,6 @@
 # define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1*FEATURE_SIZE
 # define index_arch_Fast_Unaligned_Copy	FEATURE_INDEX_1*FEATURE_SIZE
 # define index_arch_Prefer_ERMS		FEATURE_INDEX_1*FEATURE_SIZE
-# define index_arch_Use_dl_runtime_resolve_opt FEATURE_INDEX_1*FEATURE_SIZE
-# define index_arch_Use_dl_runtime_resolve_slow FEATURE_INDEX_1*FEATURE_SIZE
 # define index_arch_Prefer_No_AVX512	FEATURE_INDEX_1*FEATURE_SIZE
 
 
@@ -214,6 +220,18 @@ struct cpu_features
   } cpuid[COMMON_CPUID_INDEX_MAX];
   unsigned int family;
   unsigned int model;
+  /* The state size for XSAVEC or XSAVE.  The type must be unsigned long
+     int so that we use
+
+	sub xsave_state_size_offset(%rip) %RSP_LP
+
+     in _dl_runtime_resolve.  */
+  unsigned long int xsave_state_size;
+  /* The full state size for XSAVE when XSAVEC is disabled by
+
+     GLIBC_TUNABLES=glibc.tune.hwcaps=-XSAVEC_Usable
+   */
+  unsigned int xsave_state_full_size;
   unsigned int feature[FEATURE_INDEX_MAX];
   /* Data cache size for use in memory and string routines, typically
      L1 size.  */
@@ -326,9 +344,8 @@ extern const struct cpu_features *__get_cpu_features (void)
 # define index_arch_Prefer_No_VZEROUPPER FEATURE_INDEX_1
 # define index_arch_Fast_Unaligned_Copy	FEATURE_INDEX_1
 # define index_arch_Prefer_ERMS		FEATURE_INDEX_1
-# define index_arch_Use_dl_runtime_resolve_opt FEATURE_INDEX_1
-# define index_arch_Use_dl_runtime_resolve_slow FEATURE_INDEX_1
 # define index_arch_Prefer_No_AVX512	FEATURE_INDEX_1
+# define index_arch_XSAVEC_Usable	FEATURE_INDEX_1
 
 #endif	/* !__ASSEMBLER__ */
 
diff --git a/sysdeps/x86/cpu-tunables.c b/sysdeps/x86/cpu-tunables.c
index 872dd1267f..0488f03d32 100644
--- a/sysdeps/x86/cpu-tunables.c
+++ b/sysdeps/x86/cpu-tunables.c
@@ -240,6 +240,16 @@ TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *valp)
 						Slow_SSE4_2, SSE4_2,
 						disable, 11);
 	  break;
+	case 13:
+	  if (disable)
+	    {
+	      /* Update xsave_state_size to XSAVE state size.  */
+	      cpu_features->xsave_state_size
+		= cpu_features->xsave_state_full_size;
+	      CHECK_GLIBC_IFUNC_ARCH_OFF (n, cpu_features,
+					  XSAVEC_Usable, 13);
+	    }
+	  break;
 	case 14:
 	  if (disable)
 	    {
@@ -308,13 +318,6 @@ TUNABLE_CALLBACK (set_hwcaps) (tunable_val_t *valp)
 		 disable, 26);
 	    }
 	  break;
-	case 27:
-	    {
-	      CHECK_GLIBC_IFUNC_ARCH_BOTH (n, cpu_features,
-					   Use_dl_runtime_resolve_slow,
-					   disable, 27);
-	    }
-	  break;
 	}
       p += len + 1;
     }
diff --git a/sysdeps/x86_64/Makefile b/sysdeps/x86_64/Makefile
index 457cf5d129..cb4e63897c 100644
--- a/sysdeps/x86_64/Makefile
+++ b/sysdeps/x86_64/Makefile
@@ -55,6 +55,10 @@ CFLAGS-tst-quad2pie.c = $(PIE-ccflag)
 tests += tst-x86_64-1
 modules-names += x86_64/tst-x86_64mod-1
 LDFLAGS-tst-x86_64mod-1.so = -Wl,-soname,tst-x86_64mod-1.so
+ifneq (no,$(have-tunables))
+# Test the state size for XSAVE when XSAVEC is disabled.
+tst-x86_64-1-ENV = GLIBC_TUNABLES=glibc.tune.hwcaps=-XSAVEC_Usable
+endif
 
 $(objpfx)tst-x86_64-1: $(objpfx)x86_64/tst-x86_64mod-1.so
 
diff --git a/sysdeps/x86_64/dl-machine.h b/sysdeps/x86_64/dl-machine.h
index 6a04cbcdc9..905a37a5cc 100644
--- a/sysdeps/x86_64/dl-machine.h
+++ b/sysdeps/x86_64/dl-machine.h
@@ -66,12 +66,9 @@ static inline int __attribute__ ((unused, always_inline))
 elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
 {
   Elf64_Addr *got;
-  extern void _dl_runtime_resolve_sse (ElfW(Word)) attribute_hidden;
-  extern void _dl_runtime_resolve_avx (ElfW(Word)) attribute_hidden;
-  extern void _dl_runtime_resolve_avx_slow (ElfW(Word)) attribute_hidden;
-  extern void _dl_runtime_resolve_avx_opt (ElfW(Word)) attribute_hidden;
-  extern void _dl_runtime_resolve_avx512 (ElfW(Word)) attribute_hidden;
-  extern void _dl_runtime_resolve_avx512_opt (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_fxsave (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_xsave (ElfW(Word)) attribute_hidden;
+  extern void _dl_runtime_resolve_xsavec (ElfW(Word)) attribute_hidden;
   extern void _dl_runtime_profile_sse (ElfW(Word)) attribute_hidden;
   extern void _dl_runtime_profile_avx (ElfW(Word)) attribute_hidden;
   extern void _dl_runtime_profile_avx512 (ElfW(Word)) attribute_hidden;
@@ -120,29 +117,14 @@ elf_machine_runtime_setup (struct link_map *l, int lazy, int profile)
 	  /* 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 (HAS_ARCH_FEATURE (AVX512F_Usable))
-	    {
-	      if (HAS_ARCH_FEATURE (Use_dl_runtime_resolve_opt))
-		*(ElfW(Addr) *) (got + 2)
-		  = (ElfW(Addr)) &_dl_runtime_resolve_avx512_opt;
-	      else
-		*(ElfW(Addr) *) (got + 2)
-		  = (ElfW(Addr)) &_dl_runtime_resolve_avx512;
-	    }
-	  else if (HAS_ARCH_FEATURE (AVX_Usable))
-	    {
-	      if (HAS_ARCH_FEATURE (Use_dl_runtime_resolve_opt))
-		*(ElfW(Addr) *) (got + 2)
-		  = (ElfW(Addr)) &_dl_runtime_resolve_avx_opt;
-	      else if (HAS_ARCH_FEATURE (Use_dl_runtime_resolve_slow))
-		*(ElfW(Addr) *) (got + 2)
-		  = (ElfW(Addr)) &_dl_runtime_resolve_avx_slow;
-	      else
-		*(ElfW(Addr) *) (got + 2)
-		  = (ElfW(Addr)) &_dl_runtime_resolve_avx;
-	    }
+	  if (GLRO(dl_x86_cpu_features).xsave_state_size != 0)
+	    *(ElfW(Addr) *) (got + 2)
+	      = (HAS_ARCH_FEATURE (XSAVEC_Usable)
+		 ? (ElfW(Addr)) &_dl_runtime_resolve_xsavec
+		 : (ElfW(Addr)) &_dl_runtime_resolve_xsave);
 	  else
-	    *(ElfW(Addr) *) (got + 2) = (ElfW(Addr)) &_dl_runtime_resolve_sse;
+	    *(ElfW(Addr) *) (got + 2)
+	      = (ElfW(Addr)) &_dl_runtime_resolve_fxsave;
 	}
     }
 
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
diff --git a/sysdeps/x86_64/dl-trampoline.h b/sysdeps/x86_64/dl-trampoline.h
index 8db24c16ac..9ddaafee17 100644
--- a/sysdeps/x86_64/dl-trampoline.h
+++ b/sysdeps/x86_64/dl-trampoline.h
@@ -16,140 +16,47 @@
    License along with the GNU C Library; if not, see
    <http://www.gnu.org/licenses/>.  */
 
-#undef REGISTER_SAVE_AREA_RAW
-#ifdef __ILP32__
-/* X32 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as VEC0 to
-   VEC7.  */
-# define REGISTER_SAVE_AREA_RAW	(8 * 7 + VEC_SIZE * 8)
-#else
-/* X86-64 saves RCX, RDX, RSI, RDI, R8 and R9 plus RAX as well as
-   BND0, BND1, BND2, BND3 and VEC0 to VEC7. */
-# define REGISTER_SAVE_AREA_RAW	(8 * 7 + 16 * 4 + VEC_SIZE * 8)
-#endif
+	.text
+#ifdef _dl_runtime_resolve
 
-#undef REGISTER_SAVE_AREA
-#undef LOCAL_STORAGE_AREA
-#undef BASE
-#if DL_RUNTIME_RESOLVE_REALIGN_STACK
-# define REGISTER_SAVE_AREA	(REGISTER_SAVE_AREA_RAW + 8)
-/* Local stack area before jumping to function address: RBX.  */
-# define LOCAL_STORAGE_AREA	8
-# define BASE			rbx
-# if (REGISTER_SAVE_AREA % VEC_SIZE) != 0
-#  error REGISTER_SAVE_AREA must be multples of VEC_SIZE
-# endif
-#else
-# define REGISTER_SAVE_AREA	REGISTER_SAVE_AREA_RAW
-/* Local stack area before jumping to function address:  All saved
-   registers.  */
-# define LOCAL_STORAGE_AREA	REGISTER_SAVE_AREA
-# define BASE			rsp
-# if (REGISTER_SAVE_AREA % 16) != 8
-#  error REGISTER_SAVE_AREA must be odd multples of 8
+# undef REGISTER_SAVE_AREA
+# undef LOCAL_STORAGE_AREA
+# undef BASE
+
+# if (STATE_SAVE_ALIGNMENT % 16) != 0
+#  error STATE_SAVE_ALIGNMENT must be multples of 16
 # endif
-#endif
 
-	.text
-#ifdef _dl_runtime_resolve_opt
-/* Use the smallest vector registers to preserve the full YMM/ZMM
-   registers to avoid SSE transition penalty.  */
-
-# if VEC_SIZE == 32
-/* Check if the upper 128 bits in %ymm0 - %ymm7 registers are non-zero
-   and preserve %xmm0 - %xmm7 registers with the zero upper bits.  Since
-   there is no SSE transition penalty on AVX512 processors which don't
-   support XGETBV with ECX == 1, _dl_runtime_resolve_avx512_slow isn't
-   provided.   */
-	.globl _dl_runtime_resolve_avx_slow
-	.hidden _dl_runtime_resolve_avx_slow
-	.type _dl_runtime_resolve_avx_slow, @function
-	.align 16
-_dl_runtime_resolve_avx_slow:
-	cfi_startproc
-	cfi_adjust_cfa_offset(16) # Incorporate PLT
-	vorpd %ymm0, %ymm1, %ymm8
-	vorpd %ymm2, %ymm3, %ymm9
-	vorpd %ymm4, %ymm5, %ymm10
-	vorpd %ymm6, %ymm7, %ymm11
-	vorpd %ymm8, %ymm9, %ymm9
-	vorpd %ymm10, %ymm11, %ymm10
-	vpcmpeqd %xmm8, %xmm8, %xmm8
-	vorpd %ymm9, %ymm10, %ymm10
-	vptest %ymm10, %ymm8
-	# Preserve %ymm0 - %ymm7 registers if the upper 128 bits of any
-	# %ymm0 - %ymm7 registers aren't zero.
-	PRESERVE_BND_REGS_PREFIX
-	jnc _dl_runtime_resolve_avx
-	# Use vzeroupper to avoid SSE transition penalty.
-	vzeroupper
-	# Preserve %xmm0 - %xmm7 registers with the zero upper 128 bits
-	# when the upper 128 bits of %ymm0 - %ymm7 registers are zero.
-	PRESERVE_BND_REGS_PREFIX
-	jmp _dl_runtime_resolve_sse_vex
-	cfi_adjust_cfa_offset(-16) # Restore PLT adjustment
-	cfi_endproc
-	.size _dl_runtime_resolve_avx_slow, .-_dl_runtime_resolve_avx_slow
+# if (STATE_SAVE_OFFSET % STATE_SAVE_ALIGNMENT) != 0
+#  error STATE_SAVE_OFFSET must be multples of STATE_SAVE_ALIGNMENT
 # endif
 
-/* Use XGETBV with ECX == 1 to check which bits in vector registers are
-   non-zero and only preserve the non-zero lower bits with zero upper
-   bits.  */
-	.globl _dl_runtime_resolve_opt
-	.hidden _dl_runtime_resolve_opt
-	.type _dl_runtime_resolve_opt, @function
-	.align 16
-_dl_runtime_resolve_opt:
-	cfi_startproc
-	cfi_adjust_cfa_offset(16) # Incorporate PLT
-	pushq %rax
-	cfi_adjust_cfa_offset(8)
-	cfi_rel_offset(%rax, 0)
-	pushq %rcx
-	cfi_adjust_cfa_offset(8)
-	cfi_rel_offset(%rcx, 0)
-	pushq %rdx
-	cfi_adjust_cfa_offset(8)
-	cfi_rel_offset(%rdx, 0)
-	movl $1, %ecx
-	xgetbv
-	movl %eax, %r11d
-	popq %rdx
-	cfi_adjust_cfa_offset(-8)
-	cfi_restore (%rdx)
-	popq %rcx
-	cfi_adjust_cfa_offset(-8)
-	cfi_restore (%rcx)
-	popq %rax
-	cfi_adjust_cfa_offset(-8)
-	cfi_restore (%rax)
-# if VEC_SIZE == 32
-	# For YMM registers, check if YMM state is in use.
-	andl $bit_YMM_state, %r11d
-	# Preserve %xmm0 - %xmm7 registers with the zero upper 128 bits if
-	# YMM state isn't in use.
-	PRESERVE_BND_REGS_PREFIX
-	jz _dl_runtime_resolve_sse_vex
-# elif VEC_SIZE == 16
-	# For ZMM registers, check if YMM state and ZMM state are in
-	# use.
-	andl $(bit_YMM_state | bit_ZMM0_15_state), %r11d
-	cmpl $bit_YMM_state, %r11d
-	# Preserve %zmm0 - %zmm7 registers if ZMM state is in use.
-	PRESERVE_BND_REGS_PREFIX
-	jg _dl_runtime_resolve_avx512
-	# Preserve %ymm0 - %ymm7 registers with the zero upper 256 bits if
-	# ZMM state isn't in use.
-	PRESERVE_BND_REGS_PREFIX
-	je _dl_runtime_resolve_avx
-	# Preserve %xmm0 - %xmm7 registers with the zero upper 384 bits if
-	# neither YMM state nor ZMM state are in use.
+# if DL_RUNTIME_RESOLVE_REALIGN_STACK
+/* Local stack area before jumping to function address: RBX.  */
+#  define LOCAL_STORAGE_AREA	8
+#  define BASE			rbx
+#  ifdef USE_FXSAVE
+/* Use fxsave to save XMM registers.  */
+#   define REGISTER_SAVE_AREA	(512 + STATE_SAVE_OFFSET)
+#   if (REGISTER_SAVE_AREA % 16) != 0
+#    error REGISTER_SAVE_AREA must be multples of 16
+#   endif
+#  endif
 # else
-#  error Unsupported VEC_SIZE!
+#  ifndef USE_FXSAVE
+#   error USE_FXSAVE must be defined
+#  endif
+/* Use fxsave to save XMM registers.  */
+#  define REGISTER_SAVE_AREA	(512 + STATE_SAVE_OFFSET + 8)
+/* Local stack area before jumping to function address:  All saved
+   registers.  */
+#  define LOCAL_STORAGE_AREA	REGISTER_SAVE_AREA
+#  define BASE			rsp
+#  if (REGISTER_SAVE_AREA % 16) != 8
+#   error REGISTER_SAVE_AREA must be odd multples of 8
+#  endif
 # endif
-	cfi_adjust_cfa_offset(-16) # Restore PLT adjustment
-	cfi_endproc
-	.size _dl_runtime_resolve_opt, .-_dl_runtime_resolve_opt
-#endif
+
 	.globl _dl_runtime_resolve
 	.hidden _dl_runtime_resolve
 	.type _dl_runtime_resolve, @function
@@ -157,21 +64,30 @@ _dl_runtime_resolve_opt:
 	cfi_startproc
 _dl_runtime_resolve:
 	cfi_adjust_cfa_offset(16) # Incorporate PLT
-#if DL_RUNTIME_RESOLVE_REALIGN_STACK
-# if LOCAL_STORAGE_AREA != 8
-#  error LOCAL_STORAGE_AREA must be 8
-# endif
+# if DL_RUNTIME_RESOLVE_REALIGN_STACK
+#  if LOCAL_STORAGE_AREA != 8
+#   error LOCAL_STORAGE_AREA must be 8
+#  endif
 	pushq %rbx			# push subtracts stack by 8.
 	cfi_adjust_cfa_offset(8)
 	cfi_rel_offset(%rbx, 0)
 	mov %RSP_LP, %RBX_LP
 	cfi_def_cfa_register(%rbx)
-	and $-VEC_SIZE, %RSP_LP
-#endif
+	and $-STATE_SAVE_ALIGNMENT, %RSP_LP
+# endif
+# ifdef REGISTER_SAVE_AREA
 	sub $REGISTER_SAVE_AREA, %RSP_LP
-#if !DL_RUNTIME_RESOLVE_REALIGN_STACK
+#  if !DL_RUNTIME_RESOLVE_REALIGN_STACK
 	cfi_adjust_cfa_offset(REGISTER_SAVE_AREA)
-#endif
+#  endif
+# else
+	# Allocate stack space of the required size to save the state.
+#  if IS_IN (rtld)
+	sub _rtld_local_ro+RTLD_GLOBAL_RO_DL_X86_CPU_FEATURES_OFFSET+XSAVE_STATE_SIZE_OFFSET(%rip), %RSP_LP
+#  else
+	sub _dl_x86_cpu_features+XSAVE_STATE_SIZE_OFFSET(%rip), %RSP_LP
+#  endif
+# endif
 	# Preserve registers otherwise clobbered.
 	movq %rax, REGISTER_SAVE_RAX(%rsp)
 	movq %rcx, REGISTER_SAVE_RCX(%rsp)
@@ -180,59 +96,42 @@ _dl_runtime_resolve:
 	movq %rdi, REGISTER_SAVE_RDI(%rsp)
 	movq %r8, REGISTER_SAVE_R8(%rsp)
 	movq %r9, REGISTER_SAVE_R9(%rsp)
-	VMOV %VEC(0), (REGISTER_SAVE_VEC_OFF)(%rsp)
-	VMOV %VEC(1), (REGISTER_SAVE_VEC_OFF + VEC_SIZE)(%rsp)
-	VMOV %VEC(2), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 2)(%rsp)
-	VMOV %VEC(3), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 3)(%rsp)
-	VMOV %VEC(4), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 4)(%rsp)
-	VMOV %VEC(5), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 5)(%rsp)
-	VMOV %VEC(6), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 6)(%rsp)
-	VMOV %VEC(7), (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 7)(%rsp)
-#ifndef __ILP32__
-	# We also have to preserve bound registers.  These are nops if
-	# Intel MPX isn't available or disabled.
-# ifdef HAVE_MPX_SUPPORT
-	bndmov %bnd0, REGISTER_SAVE_BND0(%rsp)
-	bndmov %bnd1, REGISTER_SAVE_BND1(%rsp)
-	bndmov %bnd2, REGISTER_SAVE_BND2(%rsp)
-	bndmov %bnd3, REGISTER_SAVE_BND3(%rsp)
+# ifdef USE_FXSAVE
+	fxsave STATE_SAVE_OFFSET(%rsp)
 # else
-#  if REGISTER_SAVE_BND0 == 0
-	.byte 0x66,0x0f,0x1b,0x04,0x24
+	movl $STATE_SAVE_MASK, %eax
+	xorl %edx, %edx
+	# Clear the XSAVE Header.
+#  ifdef USE_XSAVE
+	movq %rdx, (STATE_SAVE_OFFSET + 512)(%rsp)
+	movq %rdx, (STATE_SAVE_OFFSET + 512 + 8)(%rsp)
+#  endif
+	movq %rdx, (STATE_SAVE_OFFSET + 512 + 8 * 2)(%rsp)
+	movq %rdx, (STATE_SAVE_OFFSET + 512 + 8 * 3)(%rsp)
+	movq %rdx, (STATE_SAVE_OFFSET + 512 + 8 * 4)(%rsp)
+	movq %rdx, (STATE_SAVE_OFFSET + 512 + 8 * 5)(%rsp)
+	movq %rdx, (STATE_SAVE_OFFSET + 512 + 8 * 6)(%rsp)
+	movq %rdx, (STATE_SAVE_OFFSET + 512 + 8 * 7)(%rsp)
+#  ifdef USE_XSAVE
+	xsave STATE_SAVE_OFFSET(%rsp)
 #  else
-	.byte 0x66,0x0f,0x1b,0x44,0x24,REGISTER_SAVE_BND0
+	xsavec STATE_SAVE_OFFSET(%rsp)
 #  endif
-	.byte 0x66,0x0f,0x1b,0x4c,0x24,REGISTER_SAVE_BND1
-	.byte 0x66,0x0f,0x1b,0x54,0x24,REGISTER_SAVE_BND2
-	.byte 0x66,0x0f,0x1b,0x5c,0x24,REGISTER_SAVE_BND3
 # endif
-#endif
 	# Copy args pushed by PLT in register.
 	# %rdi: link_map, %rsi: reloc_index
 	mov (LOCAL_STORAGE_AREA + 8)(%BASE), %RSI_LP
 	mov LOCAL_STORAGE_AREA(%BASE), %RDI_LP
 	call _dl_fixup		# Call resolver.
 	mov %RAX_LP, %R11_LP	# Save return value
-#ifndef __ILP32__
-	# Restore bound registers.  These are nops if Intel MPX isn't
-	# avaiable or disabled.
-# ifdef HAVE_MPX_SUPPORT
-	bndmov REGISTER_SAVE_BND3(%rsp), %bnd3
-	bndmov REGISTER_SAVE_BND2(%rsp), %bnd2
-	bndmov REGISTER_SAVE_BND1(%rsp), %bnd1
-	bndmov REGISTER_SAVE_BND0(%rsp), %bnd0
+	# Get register content back.
+# ifdef USE_FXSAVE
+	fxrstor STATE_SAVE_OFFSET(%rsp)
 # else
-	.byte 0x66,0x0f,0x1a,0x5c,0x24,REGISTER_SAVE_BND3
-	.byte 0x66,0x0f,0x1a,0x54,0x24,REGISTER_SAVE_BND2
-	.byte 0x66,0x0f,0x1a,0x4c,0x24,REGISTER_SAVE_BND1
-#  if REGISTER_SAVE_BND0 == 0
-	.byte 0x66,0x0f,0x1a,0x04,0x24
-#  else
-	.byte 0x66,0x0f,0x1a,0x44,0x24,REGISTER_SAVE_BND0
-#  endif
+	movl $STATE_SAVE_MASK, %eax
+	xorl %edx, %edx
+	xrstor STATE_SAVE_OFFSET(%rsp)
 # endif
-#endif
-	# Get register content back.
 	movq REGISTER_SAVE_R9(%rsp), %r9
 	movq REGISTER_SAVE_R8(%rsp), %r8
 	movq REGISTER_SAVE_RDI(%rsp), %rdi
@@ -240,20 +139,12 @@ _dl_runtime_resolve:
 	movq REGISTER_SAVE_RDX(%rsp), %rdx
 	movq REGISTER_SAVE_RCX(%rsp), %rcx
 	movq REGISTER_SAVE_RAX(%rsp), %rax
-	VMOV (REGISTER_SAVE_VEC_OFF)(%rsp), %VEC(0)
-	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE)(%rsp), %VEC(1)
-	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 2)(%rsp), %VEC(2)
-	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 3)(%rsp), %VEC(3)
-	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 4)(%rsp), %VEC(4)
-	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 5)(%rsp), %VEC(5)
-	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 6)(%rsp), %VEC(6)
-	VMOV (REGISTER_SAVE_VEC_OFF + VEC_SIZE * 7)(%rsp), %VEC(7)
-#if DL_RUNTIME_RESOLVE_REALIGN_STACK
+# if DL_RUNTIME_RESOLVE_REALIGN_STACK
 	mov %RBX_LP, %RSP_LP
 	cfi_def_cfa_register(%rsp)
 	movq (%rsp), %rbx
 	cfi_restore(%rbx)
-#endif
+# endif
 	# Adjust stack(PLT did 2 pushes)
 	add $(LOCAL_STORAGE_AREA + 16), %RSP_LP
 	cfi_adjust_cfa_offset(-(LOCAL_STORAGE_AREA + 16))
@@ -262,11 +153,9 @@ _dl_runtime_resolve:
 	jmp *%r11		# Jump to function address.
 	cfi_endproc
 	.size _dl_runtime_resolve, .-_dl_runtime_resolve
+#endif
 
 
-/* To preserve %xmm0 - %xmm7 registers, dl-trampoline.h is included
-   twice, for _dl_runtime_resolve_sse and _dl_runtime_resolve_sse_vex.
-   But we don't need another _dl_runtime_profile for XMM registers.  */
 #if !defined PROF && defined _dl_runtime_profile
 # if (LR_VECTOR_OFFSET % VEC_SIZE) != 0
 #  error LR_VECTOR_OFFSET must be multples of VEC_SIZE