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

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

(cherry picked from commit 63ad43566f7a25d140dc723598aeb441ad657eed)

5 files changed, 104 insertions, 11 deletions

diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
index d653a1d923..2a5a3dd71b 100644
--- a/sysdeps/x86_64/multiarch/Makefile
+++ b/sysdeps/x86_64/multiarch/Makefile
@@ -45,6 +45,7 @@ sysdep_routines += strncat-c stpncpy-c strncpy-c \
 		   memset-avx2-unaligned-erms \
 		   memset-avx512-unaligned-erms \
 		   memchr-evex \
+		   memmove-evex-unaligned-erms \
 		   memrchr-evex \
 		   rawmemchr-evex \
 		   stpcpy-evex \
diff --git a/sysdeps/x86_64/multiarch/ifunc-impl-list.c b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
index f7370a62e1..d5d8d1e909 100644
--- a/sysdeps/x86_64/multiarch/ifunc-impl-list.c
+++ b/sysdeps/x86_64/multiarch/ifunc-impl-list.c
@@ -81,6 +81,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      CPU_FEATURE_USABLE (AVX),
 			      __memmove_chk_avx_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, __memmove_chk,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memmove_chk_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, __memmove_chk,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memmove_chk_evex_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, __memmove_chk,
 			      CPU_FEATURE_USABLE (SSSE3),
 			      __memmove_chk_ssse3_back)
 	      IFUNC_IMPL_ADD (array, i, __memmove_chk,
@@ -103,6 +109,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      CPU_FEATURE_USABLE (AVX),
 			      __memmove_avx_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, memmove,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memmove_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, memmove,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memmove_evex_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, memmove,
 			      CPU_FEATURE_USABLE (AVX512F),
 			      __memmove_avx512_no_vzeroupper)
 	      IFUNC_IMPL_ADD (array, i, memmove,
@@ -566,6 +578,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      CPU_FEATURE_USABLE (AVX),
 			      __memcpy_chk_avx_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, __memcpy_chk,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memcpy_chk_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, __memcpy_chk,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memcpy_chk_evex_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, __memcpy_chk,
 			      CPU_FEATURE_USABLE (SSSE3),
 			      __memcpy_chk_ssse3_back)
 	      IFUNC_IMPL_ADD (array, i, __memcpy_chk,
@@ -587,6 +605,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 	      IFUNC_IMPL_ADD (array, i, memcpy,
 			      CPU_FEATURE_USABLE (AVX),
 			      __memcpy_avx_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, memcpy,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memcpy_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, memcpy,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __memcpy_evex_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, memcpy, CPU_FEATURE_USABLE (SSSE3),
 			      __memcpy_ssse3_back)
 	      IFUNC_IMPL_ADD (array, i, memcpy, CPU_FEATURE_USABLE (SSSE3),
@@ -624,6 +648,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 			      CPU_FEATURE_USABLE (AVX),
 			      __mempcpy_chk_avx_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, __mempcpy_chk,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __mempcpy_chk_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, __mempcpy_chk,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __mempcpy_chk_evex_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, __mempcpy_chk,
 			      CPU_FEATURE_USABLE (SSSE3),
 			      __mempcpy_chk_ssse3_back)
 	      IFUNC_IMPL_ADD (array, i, __mempcpy_chk,
@@ -654,6 +684,12 @@ __libc_ifunc_impl_list (const char *name, struct libc_ifunc_impl *array,
 	      IFUNC_IMPL_ADD (array, i, mempcpy,
 			      CPU_FEATURE_USABLE (AVX),
 			      __mempcpy_avx_unaligned_erms)
+	      IFUNC_IMPL_ADD (array, i, mempcpy,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __mempcpy_evex_unaligned)
+	      IFUNC_IMPL_ADD (array, i, mempcpy,
+			      CPU_FEATURE_USABLE (AVX512VL),
+			      __mempcpy_evex_unaligned_erms)
 	      IFUNC_IMPL_ADD (array, i, mempcpy, CPU_FEATURE_USABLE (SSSE3),
 			      __mempcpy_ssse3_back)
 	      IFUNC_IMPL_ADD (array, i, mempcpy, CPU_FEATURE_USABLE (SSSE3),
diff --git a/sysdeps/x86_64/multiarch/ifunc-memmove.h b/sysdeps/x86_64/multiarch/ifunc-memmove.h
index 9ada03aa43..ffb97080cd 100644
--- a/sysdeps/x86_64/multiarch/ifunc-memmove.h
+++ b/sysdeps/x86_64/multiarch/ifunc-memmove.h
@@ -29,6 +29,10 @@ extern __typeof (REDIRECT_NAME) OPTIMIZE (ssse3_back) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx_unaligned) attribute_hidden;
 extern __typeof (REDIRECT_NAME) OPTIMIZE (avx_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)
@@ -59,10 +63,21 @@ IFUNC_SELECTOR (void)
 
   if (CPU_FEATURES_ARCH_P (cpu_features, AVX_Fast_Unaligned_Load))
     {
-      if (CPU_FEATURE_USABLE_P (cpu_features, ERMS))
-	return OPTIMIZE (avx_unaligned_erms);
+      if (CPU_FEATURE_USABLE_P (cpu_features, AVX512VL))
+	{
+	  if (CPU_FEATURE_USABLE_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_FEATURE_USABLE_P (cpu_features, ERMS))
+	    return OPTIMIZE (avx_unaligned_erms);
 
-      return OPTIMIZE (avx_unaligned);
+	  return OPTIMIZE (avx_unaligned);
+	}
     }
 
   if (!CPU_FEATURE_USABLE_P (cpu_features, SSSE3)
diff --git a/sysdeps/x86_64/multiarch/memmove-evex-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-evex-unaligned-erms.S
new file mode 100644
index 0000000000..0cbce8f944
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/memmove-evex-unaligned-erms.S
@@ -0,0 +1,33 @@
+#if IS_IN (libc)
+# define VEC_SIZE	32
+# define XMM0		xmm16
+# define XMM1		xmm17
+# define YMM0		ymm16
+# define YMM1		ymm17
+# define VEC0		ymm16
+# define VEC1		ymm17
+# define VEC2		ymm18
+# define VEC3		ymm19
+# define VEC4		ymm20
+# define VEC5		ymm21
+# define VEC6		ymm22
+# define VEC7		ymm23
+# define VEC8		ymm24
+# define VEC9		ymm25
+# define VEC10		ymm26
+# define VEC11		ymm27
+# define VEC12		ymm28
+# define VEC13		ymm29
+# define VEC14		ymm30
+# define VEC15		ymm31
+# define VEC(i)		VEC##i
+# define VMOVNT		vmovntdq
+# define VMOVU		vmovdqu64
+# define VMOVA		vmovdqa64
+# define VZEROUPPER
+
+# define SECTION(p)		p##.evex
+# define MEMMOVE_SYMBOL(p,s)	p##_evex_##s
+
+# include "memmove-vec-unaligned-erms.S"
+#endif
diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
index 092f364bb6..c2e405519e 100644
--- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
+++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
@@ -48,6 +48,14 @@
 # define MEMMOVE_CHK_SYMBOL(p,s)	MEMMOVE_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
@@ -298,20 +306,20 @@ L(less_vec):
 #if VEC_SIZE > 32
 L(between_32_63):
 	/* From 32 to 63.  No branch when size == 32.  */
-	vmovdqu	(%rsi), %ymm0
-	vmovdqu	-32(%rsi,%rdx), %ymm1
-	vmovdqu	%ymm0, (%rdi)
-	vmovdqu	%ymm1, -32(%rdi,%rdx)
+	VMOVU	(%rsi), %YMM0
+	VMOVU	-32(%rsi,%rdx), %YMM1
+	VMOVU	%YMM0, (%rdi)
+	VMOVU	%YMM1, -32(%rdi,%rdx)
 	VZEROUPPER
 	ret
 #endif
 #if VEC_SIZE > 16
 	/* From 16 to 31.  No branch when size == 16.  */
 L(between_16_31):
-	vmovdqu	(%rsi), %xmm0
-	vmovdqu	-16(%rsi,%rdx), %xmm1
-	vmovdqu	%xmm0, (%rdi)
-	vmovdqu	%xmm1, -16(%rdi,%rdx)
+	VMOVU	(%rsi), %XMM0
+	VMOVU	-16(%rsi,%rdx), %XMM1
+	VMOVU	%XMM0, (%rdi)
+	VMOVU	%XMM1, -16(%rdi,%rdx)
 	ret
 #endif
 L(between_8_15):