diff --git a/arch/s390/lib/mem.S b/arch/s390/lib/mem.S
index a27b103d7450..d2e1ca87a568 100644
--- a/arch/s390/lib/mem.S
+++ b/arch/s390/lib/mem.S
@@ -11,37 +11,6 @@
 
 	GEN_BR_THUNK %r14
 
-/*
- * memcpy implementation
- *
- * void *memcpy(void *dest, const void *src, size_t n)
- */
-SYM_FUNC_START(__memcpy)
-	ltgr	%r4,%r4
-	jz	.Lmemcpy_exit
-	aghi	%r4,-1
-	srlg	%r5,%r4,8
-	ltgr	%r5,%r5
-	lgr	%r1,%r2
-	jnz	.Lmemcpy_loop
-.Lmemcpy_remainder:
-	exrl	%r4,.Lmemcpy_mvc
-.Lmemcpy_exit:
-	BR_EX	%r14
-.Lmemcpy_loop:
-	mvc	0(256,%r1),0(%r3)
-	la	%r1,256(%r1)
-	la	%r3,256(%r3)
-	brctg	%r5,.Lmemcpy_loop
-	j	.Lmemcpy_remainder
-.Lmemcpy_mvc:
-	mvc	0(1,%r1),0(%r3)
-SYM_FUNC_END(__memcpy)
-EXPORT_SYMBOL(__memcpy)
-
-SYM_FUNC_ALIAS(memcpy, __memcpy)
-EXPORT_SYMBOL(memcpy)
-
 /*
  * __memset16/32/64
  *
diff --git a/arch/s390/lib/string.c b/arch/s390/lib/string.c
index f59d67925e77..056ea2027ddd 100644
--- a/arch/s390/lib/string.c
+++ b/arch/s390/lib/string.c
@@ -124,6 +124,40 @@ EXPORT_SYMBOL(__memset);
 EXPORT_SYMBOL(memset);
 #endif
 
+#ifdef __HAVE_ARCH_MEMCPY
+noinstr void *__memcpy(void *dest, const void *src, size_t n)
+{
+	void *d = dest;
+
+	if (!n)
+		return d;
+	while (n >= 256) {
+		asm volatile(
+			"	mvc	0(256,%[dest]),0(%[src])"
+			:
+			: [dest] "a" (dest), [src] "a" (src)
+			: "memory");
+		dest += 256;
+		src += 256;
+		n -= 256;
+	}
+	if (!n)
+		return d;
+	asm volatile(
+		"	exrl	%[n],1f\n"
+		"	j	2f\n"
+		"1:	mvc	0(1,%[dest]),0(%[src])\n"
+		"2:"
+		:
+		: [dest] "a" (dest), [src] "a" (src), [n] "a" (n - 1)
+		: "memory");
+	return d;
+}
+SYMBOL_FUNCTION_ALIAS(memcpy, __memcpy);
+EXPORT_SYMBOL(__memcpy);
+EXPORT_SYMBOL(memcpy);
+#endif
+
 /*
  * Helper functions to find the end of a string
  */