diff --git a/xen/arch/x86/Makefile b/xen/arch/x86/Makefile
index 8a9d021223..e32200f5e3 100644
--- a/xen/arch/x86/Makefile
+++ b/xen/arch/x86/Makefile
@@ -47,6 +47,7 @@ obj-$(CONFIG_RETURN_THUNK) += indirect-thunk.o
 obj-$(CONFIG_PV) += ioport_emulate.o
 obj-y += irq.o
 obj-$(CONFIG_KEXEC) += machine_kexec.o
+obj-y += memcpy.o
 obj-y += memset.o
 obj-y += mm.o x86_64/mm.o
 obj-$(CONFIG_VM_EVENT) += monitor.o
diff --git a/xen/arch/x86/memcpy.S b/xen/arch/x86/memcpy.S
new file mode 100644
index 0000000000..aaee012126
--- /dev/null
+++ b/xen/arch/x86/memcpy.S
@@ -0,0 +1,20 @@
+#include <asm/asm_defns.h>
+
+FUNC(memcpy)
+        mov     %rdx, %rcx
+        mov     %rdi, %rax
+        /*
+         * We need to be careful here: memcpy() is involved in alternatives
+         * patching, so the code doing the actual copying (i.e. past setting
+         * up registers) may not be subject to patching (unless further
+         * precautions were taken).
+         */
+        ALTERNATIVE "and $7, %edx; shr $3, %rcx", \
+                    STR(rep movsb; RET), X86_FEATURE_ERMS
+        rep movsq
+        or      %edx, %ecx
+        jz      1f
+        rep movsb
+1:
+        RET
+END(memcpy)
diff --git a/xen/arch/x86/string.c b/xen/arch/x86/string.c
index 5b52981260..61c4aae6b4 100644
--- a/xen/arch/x86/string.c
+++ b/xen/arch/x86/string.c
@@ -7,21 +7,6 @@
 
 #include <xen/lib.h>
 
-void *(memcpy)(void *dest, const void *src, size_t n)
-{
-    long d0, d1, d2;
-
-    asm volatile (
-        "   rep ; movs"__OS" ; "
-        "   mov %k4,%k3      ; "
-        "   rep ; movsb        "
-        : "=&c" (d0), "=&D" (d1), "=&S" (d2)
-        : "0" (n/BYTES_PER_LONG), "r" (n%BYTES_PER_LONG), "1" (dest), "2" (src)
-        : "memory" );
-
-    return dest;
-}
-
 void *(memmove)(void *dest, const void *src, size_t n)
 {
     long d0, d1, d2;