diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 9bea8ce88f9..36b65df50c5 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -26851,8 +26851,8 @@ aarch64_vectorize_vec_perm_const (machine_mode vmode, machine_mode op_mode,
   d.op_vec_flags = aarch64_classify_vector_mode (d.op_mode);
   d.target = target;
   d.op0 = op0 ? force_reg (op_mode, op0) : NULL_RTX;
-  if (op0 == op1)
-    d.op1 = d.op0;
+  if (op0 && d.one_vector_p)
+    d.op1 = copy_rtx (d.op0);
   else
     d.op1 = op1 ? force_reg (op_mode, op1) : NULL_RTX;
   d.testing_p = !target;
diff --git a/gcc/testsuite/gcc.target/aarch64/pr115258_2.c b/gcc/testsuite/gcc.target/aarch64/pr115258_2.c
new file mode 100644
index 00000000000..065e1bb9e7a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr115258_2.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-Ofast -mcpu=neoverse-v2" } */
+
+extern __attribute__((aligned(64))) float a[32000], b[32000];
+int dummy(float[32000], float[32000], float);
+
+void s1112() {
+
+  for (int nl = 0; nl < 100000 * 3; nl++) {
+    for (int i = 32000 - 1; i >= 0; i--) {
+      a[i] = b[i] + (float)1.;
+    }
+    dummy(a, b, 0.);
+  }
+}
+
+/* { dg-final { scan-assembler-not {\tmov\tv[0-9]+\.16b,} } } */