commit 9aaaab7c6e4176e61c59b0a63c6ba906d875dc0e
Author: Andreas Schwab <schwab@suse.de>
Date:   Tue May 22 10:37:59 2018 +0200

    Don't write beyond destination in __mempcpy_avx512_no_vzeroupper (bug 23196)
    
    When compiled as mempcpy, the return value is the end of the destination
    buffer, thus it cannot be used to refer to the start of it.

Conflicts:
	sysdeps/x86_64/multiarch/memmove-avx512-no-vzeroupper.S

Change applied to sysdeps/x86_64/multiarch/memcpy-avx512-no-vzeroupper.S
instead.

diff --git a/string/test-mempcpy.c b/string/test-mempcpy.c
index 1679e9d11f282c55..7ccce13e71bd10a9 100644
--- a/string/test-mempcpy.c
+++ b/string/test-mempcpy.c
@@ -18,6 +18,7 @@
    <http://www.gnu.org/licenses/>.  */
 
 #define MEMCPY_RESULT(dst, len) (dst) + (len)
+#define MIN_PAGE_SIZE 131072
 #define TEST_MAIN
 #define TEST_NAME "mempcpy"
 #include "test-string.h"
diff --git a/sysdeps/x86_64/multiarch/memcpy-avx512-no-vzeroupper.S b/sysdeps/x86_64/multiarch/memcpy-avx512-no-vzeroupper.S
index 058e871847a77c45..b78710ea9359e129 100644
--- a/sysdeps/x86_64/multiarch/memcpy-avx512-no-vzeroupper.S
+++ b/sysdeps/x86_64/multiarch/memcpy-avx512-no-vzeroupper.S
@@ -333,6 +333,7 @@ L(preloop_large):
 	vmovups	(%rsi), %zmm4
 	vmovups	0x40(%rsi), %zmm5
 
+	mov	%rdi, %r11
 /* Align destination for access with non-temporal stores in the loop.  */
 	mov	%rdi, %r8
 	and	$-0x80, %rdi
@@ -363,8 +364,8 @@ L(gobble_256bytes_nt_loop):
 	cmp	$256, %rdx
 	ja	L(gobble_256bytes_nt_loop)
 	sfence
-	vmovups	%zmm4, (%rax)
-	vmovups	%zmm5, 0x40(%rax)
+	vmovups	%zmm4, (%r11)
+	vmovups	%zmm5, 0x40(%r11)
 	jmp	L(check)
 
 L(preloop_large_bkw):