[PATCH v2 1/2] x86: Move mem{p}{mov|cpy}_{chk_}erms to its own file

[Noah Goldstein <goldstein.w.n@gmail.com>]

The primary memmove_{impl}_unaligned_erms implementations don't
interact with this function. Putting them in same file both
wastes space and unnecessarily bloats a hot code section.
---
 sysdeps/x86_64/multiarch/Makefile             |  1 +
 sysdeps/x86_64/multiarch/memmove-erms.S       | 53 +++++++++++++++++++
 .../multiarch/memmove-vec-unaligned-erms.S    | 50 -----------------
 3 files changed, 54 insertions(+), 50 deletions(-)
 create mode 100644 sysdeps/x86_64/multiarch/memmove-erms.S

diff --git a/sysdeps/x86_64/multiarch/Makefile b/sysdeps/x86_64/multiarch/Makefile
index 666ee4d5d6..62a4d96fb8 100644
--- a/sysdeps/x86_64/multiarch/Makefile
+++ b/sysdeps/x86_64/multiarch/Makefile
@@ -18,6 +18,7 @@ sysdep_routines += \
   memmove-avx-unaligned-erms-rtm \
   memmove-avx512-no-vzeroupper \
   memmove-avx512-unaligned-erms \
+  memmove-erms \
   memmove-evex-unaligned-erms \
   memmove-sse2-unaligned-erms \
   memmove-ssse3 \
diff --git a/sysdeps/x86_64/multiarch/memmove-erms.S b/sysdeps/x86_64/multiarch/memmove-erms.S
new file mode 100644
index 0000000000..d98d21644b
--- /dev/null
+++ b/sysdeps/x86_64/multiarch/memmove-erms.S
@@ -0,0 +1,53 @@
+#include <sysdep.h>
+
+#if defined USE_MULTIARCH && IS_IN (libc)
+	.text
+ENTRY (__mempcpy_chk_erms)
+	cmp	%RDX_LP, %RCX_LP
+	jb	HIDDEN_JUMPTARGET (__chk_fail)
+END (__mempcpy_chk_erms)
+
+/* Only used to measure performance of REP MOVSB.  */
+ENTRY (__mempcpy_erms)
+	mov	%RDI_LP, %RAX_LP
+	/* Skip zero length.  */
+	test	%RDX_LP, %RDX_LP
+	jz	2f
+	add	%RDX_LP, %RAX_LP
+	jmp	L(start_movsb)
+END (__mempcpy_erms)
+
+ENTRY (__memmove_chk_erms)
+	cmp	%RDX_LP, %RCX_LP
+	jb	HIDDEN_JUMPTARGET (__chk_fail)
+END (__memmove_chk_erms)
+
+ENTRY (__memmove_erms)
+	movq	%rdi, %rax
+	/* Skip zero length.  */
+	test	%RDX_LP, %RDX_LP
+	jz	2f
+L(start_movsb):
+	mov	%RDX_LP, %RCX_LP
+	cmp	%RSI_LP, %RDI_LP
+	jb	1f
+	/* Source == destination is less common.  */
+	je	2f
+	lea	(%rsi,%rcx), %RDX_LP
+	cmp	%RDX_LP, %RDI_LP
+	jb	L(movsb_backward)
+1:
+	rep movsb
+2:
+	ret
+L(movsb_backward):
+	leaq	-1(%rdi,%rcx), %rdi
+	leaq	-1(%rsi,%rcx), %rsi
+	std
+	rep movsb
+	cld
+	ret
+END (__memmove_erms)
+strong_alias (__memmove_erms, __memcpy_erms)
+strong_alias (__memmove_chk_erms, __memcpy_chk_erms)
+#endif
diff --git a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
index d1518b8bab..04747133b7 100644
--- a/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
+++ b/sysdeps/x86_64/multiarch/memmove-vec-unaligned-erms.S
@@ -239,56 +239,6 @@ L(start):
 #endif
 #if defined USE_MULTIARCH && IS_IN (libc)
 END (MEMMOVE_SYMBOL (__memmove, unaligned))
-# if VEC_SIZE == 16
-ENTRY (__mempcpy_chk_erms)
-	cmp	%RDX_LP, %RCX_LP
-	jb	HIDDEN_JUMPTARGET (__chk_fail)
-END (__mempcpy_chk_erms)
-
-/* Only used to measure performance of REP MOVSB.  */
-ENTRY (__mempcpy_erms)
-	mov	%RDI_LP, %RAX_LP
-	/* Skip zero length.  */
-	test	%RDX_LP, %RDX_LP
-	jz	2f
-	add	%RDX_LP, %RAX_LP
-	jmp	L(start_movsb)
-END (__mempcpy_erms)
-
-ENTRY (__memmove_chk_erms)
-	cmp	%RDX_LP, %RCX_LP
-	jb	HIDDEN_JUMPTARGET (__chk_fail)
-END (__memmove_chk_erms)
-
-ENTRY (__memmove_erms)
-	movq	%rdi, %rax
-	/* Skip zero length.  */
-	test	%RDX_LP, %RDX_LP
-	jz	2f
-L(start_movsb):
-	mov	%RDX_LP, %RCX_LP
-	cmp	%RSI_LP, %RDI_LP
-	jb	1f
-	/* Source == destination is less common.  */
-	je	2f
-	lea	(%rsi,%rcx), %RDX_LP
-	cmp	%RDX_LP, %RDI_LP
-	jb	L(movsb_backward)
-1:
-	rep movsb
-2:
-	ret
-L(movsb_backward):
-	leaq	-1(%rdi,%rcx), %rdi
-	leaq	-1(%rsi,%rcx), %rsi
-	std
-	rep movsb
-	cld
-	ret
-END (__memmove_erms)
-strong_alias (__memmove_erms, __memcpy_erms)
-strong_alias (__memmove_chk_erms, __memcpy_chk_erms)
-# endif
 
 # ifdef SHARED
 ENTRY (MEMMOVE_CHK_SYMBOL (__mempcpy_chk, unaligned_erms))
-- 
2.34.1