x86-64: Use fxsave/xsave/xsavec in _dl_runtime_resolve [BZ #21265]hjl/pr21265/2.24

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, 66 insertions, 17 deletions

diff --git a/sysdeps/x86/cpu-features.c b/sysdeps/x86/cpu-features.c
index 508ad2ae7b..9eca98817d 100644
--- a/sysdeps/x86/cpu-features.c
+++ b/sysdeps/x86/cpu-features.c
@@ -18,6 +18,7 @@
 
 #include <cpuid.h>
 #include <cpu-features.h>
+#include <libc-internal.h>
 
 static void
 get_common_indeces (struct cpu_features *cpu_features,
@@ -88,6 +89,71 @@ get_common_indeces (struct cpu_features *cpu_features,
 	    cpu_features->feature[index_arch_FMA_Usable]
 	      |= bit_arch_FMA_Usable;
 	}
+
+      /* 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)
+	    {
+	      cpu_features->xsave_state_size
+		= ALIGN_UP (ebx + STATE_SAVE_OFFSET, 64);
+
+	      __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;
+		    }
+		}
+	    }
+	}
     }
 }
 
@@ -213,23 +279,6 @@ 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)