tree-optimization/111048 - avoid flawed logic in fold_vec_perm

The following avoids running into somehow flawed logic in fold_vec_perm
for non-VLA vectors.

	PR tree-optimization/111048
	* fold-const.cc (fold_vec_perm_cst): Check for non-VLA
	vectors first.

	* gcc.dg/torture/pr111048.c: New testcase.

2 files changed, 30 insertions, 6 deletions

diff --git a/gcc/fold-const.cc b/gcc/fold-const.cc
index c6fb083..08530b6 100644
--- a/gcc/fold-const.cc
+++ b/gcc/fold-const.cc
@@ -10625,6 +10625,11 @@ fold_vec_perm_cst (tree type, tree arg0, tree arg1, const vec_perm_indices &sel,
   unsigned res_npatterns, res_nelts_per_pattern;
   unsigned HOST_WIDE_INT res_nelts;
 
+  if (TYPE_VECTOR_SUBPARTS (type).is_constant (&res_nelts))
+    {
+      res_npatterns = res_nelts;
+      res_nelts_per_pattern = 1;
+    }
   /* (1) If SEL is a suitable mask as determined by
      valid_mask_for_fold_vec_perm_cst_p, then:
      res_npatterns = max of npatterns between ARG0, ARG1, and SEL
@@ -10634,7 +10639,7 @@ fold_vec_perm_cst (tree type, tree arg0, tree arg1, const vec_perm_indices &sel,
      res_npatterns = nelts in result vector.
      res_nelts_per_pattern = 1.
      This exception is made so that VLS ARG0, ARG1 and SEL work as before.  */
-  if (valid_mask_for_fold_vec_perm_cst_p (arg0, arg1, sel, reason))
+  else if (valid_mask_for_fold_vec_perm_cst_p (arg0, arg1, sel, reason))
     {
       res_npatterns
 	= std::max (VECTOR_CST_NPATTERNS (arg0),
@@ -10648,11 +10653,6 @@ fold_vec_perm_cst (tree type, tree arg0, tree arg1, const vec_perm_indices &sel,
 
       res_nelts = res_npatterns * res_nelts_per_pattern;
     }
-  else if (TYPE_VECTOR_SUBPARTS (type).is_constant (&res_nelts))
-    {
-      res_npatterns = res_nelts;
-      res_nelts_per_pattern = 1;
-    }
   else
     return NULL_TREE;
 
diff --git a/gcc/testsuite/gcc.dg/torture/pr111048.c b/gcc/testsuite/gcc.dg/torture/pr111048.c
new file mode 100644
index 0000000..475978a
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr111048.c
@@ -0,0 +1,24 @@
+/* { dg-do run } */
+/* { dg-additional-options "-mavx2" { target avx2_runtime } } */
+
+typedef unsigned char u8;
+
+__attribute__((noipa))
+static void check(const u8 * v) {
+    if (*v != 15) __builtin_trap();
+}
+
+__attribute__((noipa))
+static void bug(void) {
+    u8 in_lanes[32];
+    for (unsigned i = 0; i < 32; i += 2) {
+      in_lanes[i + 0] = 0;
+      in_lanes[i + 1] = ((u8)0xff) >> (i & 7);
+    }
+
+    check(&in_lanes[13]);
+  }
+
+int main() {
+    bug();
+}