x86-64: Add memset family functions with 256-bit EVEX

Update ifunc-memset.h/ifunc-wmemset.h to select the function optimized
with 256-bit EVEX instructions using YMM16-YMM31 registers to avoid RTM
abort with usable AVX512VL and AVX512BW since VZEROUPPER isn't needed at
function exit.

(cherry picked from commit 1b968b6b9b3aac702ac2f133e0dd16cfdbb415ee)

6 files changed, 90 insertions, 14 deletions

diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
index e75805a645..062e6c0b20 100644
--- a/sysdeps/x86_64/multiarch/Makefile
+++ b/sysdeps/x86_64/multiarch/Makefile
@@ -44,6 +44,7 @@ sysdep_routines += strncat-c stpncpy-c strncpy-c \
 		   memchr-evex \
 		   memmove-evex-unaligned-erms \
 		   memrchr-evex \
+		   memset-evex-unaligned-erms \
 		   rawmemchr-evex \
 		   stpcpy-evex \
 		   stpncpy-evex \
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index d7814a965f..7ef94fe401 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -161,6 +161,14 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      HAS_ARCH_FEATURE (AVX2_Usable),
 			      __memset_chk_avx2_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, __memset_chk,
+			      (HAS_ARCH_FEATURE (AVX512VL_Usable)
+			       && HAS_ARCH_FEATURE (AVX512BW_Usable)),
+			      __memset_chk_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, __memset_chk,
+			      (HAS_ARCH_FEATURE (AVX512VL_Usable)
+			       && HAS_ARCH_FEATURE (AVX512BW_Usable)),
+			      __memset_chk_evex_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, __memset_chk,
 			      HAS_ARCH_FEATURE (AVX512F_Usable),
 			      __memset_chk_avx512_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, __memset_chk,
@@ -186,6 +194,14 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      HAS_ARCH_FEATURE (AVX2_Usable),
 			      __memset_avx2_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, memset,
+			      (HAS_ARCH_FEATURE (AVX512VL_Usable)
+			       && HAS_ARCH_FEATURE (AVX512BW_Usable)),
+			      __memset_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, memset,
+			      (HAS_ARCH_FEATURE (AVX512VL_Usable)
+			       && HAS_ARCH_FEATURE (AVX512BW_Usable)),
+			      __memset_evex_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, memset,
 			      HAS_ARCH_FEATURE (AVX512F_Usable),
 			      __memset_avx512_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, memset,
@@ -544,6 +560,9 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      HAS_ARCH_FEATURE (AVX2_Usable),
 			      __wmemset_avx2_unaligned)
 	      IFUNC_IMPL_ADD (array, i, wmemset,
+			      HAS_ARCH_FEATURE (AVX512VL_Usable),
+			      __wmemset_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, wmemset,
 			      HAS_ARCH_FEATURE (AVX512F_Usable),
 			      __wmemset_avx512_unaligned))
 
@@ -712,6 +731,9 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      HAS_ARCH_FEATURE (AVX2_Usable),
 			      __wmemset_chk_avx2_unaligned)
 	      IFUNC_IMPL_ADD (array, i, __wmemset_chk,
+			      HAS_ARCH_FEATURE (AVX512VL_Usable),
+			      __wmemset_chk_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, __wmemset_chk,
 			      HAS_ARCH_FEATURE (AVX512F_Usable),
 			      __wmemset_chk_avx512_unaligned))
 #endif
diff --git a/sysdeps/x86_64/multiarch/ifunc-memset.h b/sysdeps/x86_64/multiarch/ifunc-memset.h
index 19b5ae676c..fea6c832f4 100644
--- a/sysdeps/x86_64/multiarch/ifunc-memset.h
+++ b/sysdeps/x86_64/multiarch/ifunc-memset.h
@@ -27,6 +27,10 @@ extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_unaligned_erms)
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_unaligned) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_unaligned_erms)
   attribute_hidden;
+extern __typeof (REDIRECT_NAME) OPTIMIZE (evex_unaligned)
+  attribute_hidden;
+extern __typeof (REDIRECT_NAME) OPTIMIZE (evex_unaligned_erms)
+  attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx512_unaligned)
   attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx512_unaligned_erms)
@@ -56,10 +60,22 @@ IFUNC_SELECTOR (void)
 
   if (CPU_FEATURES_ARCH_P (cpu_features, AVX2_Usable))
     {
-      if (CPU_FEATURES_CPU_P (cpu_features, ERMS))
-	return OPTIMIZE (avx2_unaligned_erms);
-      else
-	return OPTIMIZE (avx2_unaligned);
+      if (CPU_FEATURES_ARCH_P (cpu_features, AVX512VL_Usable)
+	  && CPU_FEATURES_ARCH_P (cpu_features, AVX512BW_Usable))
+	{
+	  if (CPU_FEATURES_CPU_P (cpu_features, ERMS))
+	    return OPTIMIZE (evex_unaligned_erms);
+
+	  return OPTIMIZE (evex_unaligned);
+	}
+
+      if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER))
+	{
+	  if (CPU_FEATURES_CPU_P (cpu_features, ERMS))
+	    return OPTIMIZE (avx2_unaligned_erms);
+
+	  return OPTIMIZE (avx2_unaligned);
+	}
     }
 
   if (CPU_FEATURES_CPU_P (cpu_features, ERMS))
diff --git a/sysdeps/x86_64/multiarch/ifunc-wmemset.h b/sysdeps/x86_64/multiarch/ifunc-wmemset.h
index 2f1085f5fc..fae721cdb0 100644
--- a/sysdeps/x86_64/multiarch/ifunc-wmemset.h
+++ b/sysdeps/x86_64/multiarch/ifunc-wmemset.h
@@ -20,6 +20,7 @@
 
 extern __typeof (REDIRECT_NAME) OPTIMIZE (sse2_unaligned) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx2_unaligned) attribute_hidden;
+extern __typeof (REDIRECT_NAME) OPTIMIZE (evex_unaligned) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx512_unaligned) attribute_hidden;
 
 static inline void *
@@ -27,14 +28,18 @@ IFUNC_SELECTOR (void)
 {
   const struct cpu_features* cpu_features = __get_cpu_features ();
 
-  if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER)
-      && CPU_FEATURES_ARCH_P (cpu_features, AVX2_Usable)
+  if (CPU_FEATURES_ARCH_P (cpu_features, AVX2_Usable)
       && CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
     {
       if (CPU_FEATURES_ARCH_P (cpu_features, AVX512F_Usable)
-	  && !CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_AVX512))
+	  && !CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_AVX512)
+	  && !CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER))
 	return OPTIMIZE (avx512_unaligned);
-      else
+
+      if (CPU_FEATURES_ARCH_P (cpu_features, AVX512VL_Usable))
+	return OPTIMIZE (evex_unaligned);
+
+      if (!CPU_FEATURES_ARCH_P (cpu_features, Prefer_No_VZEROUPPER))
 	return OPTIMIZE (avx2_unaligned);
     }
 
diff --git a/sysdeps/x86_64/multiarch/memset-evex-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-evex-unaligned-erms.S
new file mode 100644
index 0000000000..ae0a4d6e46
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/memset-evex-unaligned-erms.S
@@ -0,0 +1,24 @@
+#if IS_IN (libc)
+# define VEC_SIZE	32
+# define XMM0		xmm16
+# define YMM0		ymm16
+# define VEC0		ymm16
+# define VEC(i)		VEC##i
+# define VMOVU		vmovdqu64
+# define VMOVA		vmovdqa64
+# define VZEROUPPER
+
+# define MEMSET_VDUP_TO_VEC0_AND_SET_RETURN(d, r) \
+  movq r, %rax; \
+  vpbroadcastb d, %VEC0
+
+# define WMEMSET_VDUP_TO_VEC0_AND_SET_RETURN(d, r) \
+  movq r, %rax; \
+  vpbroadcastd d, %VEC0
+
+# define SECTION(p)		p##.evex
+# define MEMSET_SYMBOL(p,s)	p##_evex_##s
+# define WMEMSET_SYMBOL(p,s)	p##_evex_##s
+
+# include "memset-vec-unaligned-erms.S"
+#endif
diff --git a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
index a44f1bc3b2..9f14e956d1 100644
--- a/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
+++ b/sysdeps/x86_64/multiarch/memset-vec-unaligned-erms.S
@@ -34,6 +34,14 @@
 # define WMEMSET_CHK_SYMBOL(p,s)	WMEMSET_SYMBOL(p, s)
 #endif
 
+#ifndef XMM0
+# define XMM0				xmm0
+#endif
+
+#ifndef YMM0
+# define YMM0				ymm0
+#endif
+
 #ifndef VZEROUPPER
 # if VEC_SIZE > 16
 #  define VZEROUPPER			vzeroupper
@@ -77,7 +85,7 @@
 ENTRY (__bzero)
 	mov	%RDI_LP, %RAX_LP /* Set return value.  */
 	mov	%RSI_LP, %RDX_LP /* Set n.  */
-	pxor	%xmm0, %xmm0
+	pxor	%XMM0, %XMM0
 	jmp	L(entry_from_bzero)
 END (__bzero)
 weak_alias (__bzero, bzero)
@@ -233,7 +241,7 @@ L(less_vec):
 	cmpb	$16, %dl
 	jae	L(between_16_31)
 # endif
-	MOVQ	%xmm0, %rcx
+	MOVQ	%XMM0, %rcx
 	cmpb	$8, %dl
 	jae	L(between_8_15)
 	cmpb	$4, %dl
@@ -248,16 +256,16 @@ L(less_vec):
 # if VEC_SIZE > 32
 	/* From 32 to 63.  No branch when size == 32.  */
 L(between_32_63):
-	vmovdqu	%ymm0, -32(%rdi,%rdx)
-	vmovdqu	%ymm0, (%rdi)
+	VMOVU	%YMM0, -32(%rdi,%rdx)
+	VMOVU	%YMM0, (%rdi)
 	VZEROUPPER
 	ret
 # endif
 # if VEC_SIZE > 16
 	/* From 16 to 31.  No branch when size == 16.  */
 L(between_16_31):
-	vmovdqu	%xmm0, -16(%rdi,%rdx)
-	vmovdqu	%xmm0, (%rdi)
+	VMOVU	%XMM0, -16(%rdi,%rdx)
+	VMOVU	%XMM0, (%rdi)
 	VZEROUPPER
 	ret
 # endif