diff --git a/gcc/expr.c b/gcc/expr.c
index ebf0c9e4797d..2406f9039eab 100644
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -1637,6 +1637,12 @@ emit_block_move_hints (rtx x, rtx y, rtx size, enum block_op_methods method,
   x = adjust_address (x, BLKmode, 0);
   y = adjust_address (y, BLKmode, 0);
 
+  /* If source and destination are the same, no need to copy anything.  */
+  if (rtx_equal_p (x, y)
+      && !MEM_VOLATILE_P (x)
+      && !MEM_VOLATILE_P (y))
+    return 0;
+
   /* Set MEM_SIZE as appropriate for this block copy.  The main place this
      can be incorrect is coming from __builtin_memcpy.  */
   poly_int64 const_size;
diff --git a/gcc/testsuite/gcc.target/i386/pr96539.c b/gcc/testsuite/gcc.target/i386/pr96539.c
new file mode 100644
index 000000000000..fc164f8b8898
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr96539.c
@@ -0,0 +1,16 @@
+/* PR rtl-optimization/96539 */
+/* { dg-do compile } *
+/* { dg-options "-Os" } */
+/* { dg-final { scan-assembler-not "rep\[^\n\r]\*movs" } } */
+
+struct A { int a, b, c, d, e, f; void *g, *h, *i, *j, *k, *l, *m; };
+
+int bar (int a);
+int baz (int a, int b, int c, void *p, struct A s);
+
+int
+foo (int a, int b, int c, void *p, struct A s)
+{
+  bar (a);
+  return baz (a, b, c, p, s);
+}