builtins: Force SAVE_EXPR for __builtin_{add,sub,mul}_overflow and __builtin{add...

The following testcase is miscompiled, because we use save_expr
on the .{ADD,SUB,MUL}_OVERFLOW call we are creating, but if the first
two operands are not INTEGER_CSTs (in that case we just fold it right away)
but are TREE_READONLY/!TREE_SIDE_EFFECTS, save_expr doesn't actually
create a SAVE_EXPR at all and so we lower it to
*arg2 = REALPART_EXPR (.ADD_OVERFLOW (arg0, arg1)), \
IMAGPART_EXPR (.ADD_OVERFLOW (arg0, arg1))
which evaluates the ifn twice and just hope it will be CSEd back.
As *arg2 aliases *arg0, that is not the case.
The builtins are really never const/pure as they store into what
the third arguments points to, so after handling the INTEGER_CST+INTEGER_CST
case, I think we should just always use SAVE_EXPR.  Just building SAVE_EXPR
by hand and setting TREE_SIDE_EFFECTS on it doesn't work, because
c_fully_fold optimizes it away again, so the following patch marks the
ifn calls as TREE_SIDE_EFFECTS (but doesn't do it for the
__builtin_{add,sub,mul}_overflow_p case which were designed for use
especially in constant expressions and don't really evaluate the
realpart side, so we don't really need a SAVE_EXPR in that case).

2024-06-04  Jakub Jelinek  <jakub@redhat.com>

	PR middle-end/108789
	* builtins.cc (fold_builtin_arith_overflow): For ovf_only,
	don't call save_expr and don't build REALPART_EXPR, otherwise
	set TREE_SIDE_EFFECTS on call before calling save_expr.
	(fold_builtin_addc_subc): Set TREE_SIDE_EFFECTS on call before
	calling save_expr.

	* gcc.c-torture/execute/pr108789.c: New test.

diff --git a/gcc/builtins.cc b/gcc/builtins.cc
index 00ee9eb2925577e8739ae38a2450d503bc37f721..5b5307c67b8caa776662529451db44a33d464e2d 100644 (file)
--- a/gcc/builtins.cc
+++ b/gcc/builtins.cc
@@ -10042,7 +10042,21 @@ fold_builtin_arith_overflow (location_t loc, enum built_in_function fcode,
       tree ctype = build_complex_type (type);
       tree call = build_call_expr_internal_loc (loc, ifn, ctype, 2,
                                                arg0, arg1);
-      tree tgt = save_expr (call);
+      tree tgt;
+      if (ovf_only)
+       {
+         tgt = call;
+         intres = NULL_TREE;
+       }
+      else
+       {
+         /* Force SAVE_EXPR even for calls which satisfy tree_invariant_p_1,
+            as while the call itself is const, the REALPART_EXPR store is
+            certainly not.  And in any case, we want just one call,
+            not multiple and trying to CSE them later.  */
+         TREE_SIDE_EFFECTS (call) = 1;
+         tgt = save_expr (call);
+       }
       intres = build1_loc (loc, REALPART_EXPR, type, tgt);
       ovfres = build1_loc (loc, IMAGPART_EXPR, type, tgt);
       ovfres = fold_convert_loc (loc, boolean_type_node, ovfres);
@@ -10354,11 +10368,17 @@ fold_builtin_addc_subc (location_t loc, enum built_in_function fcode,
   tree ctype = build_complex_type (type);
   tree call = build_call_expr_internal_loc (loc, ifn, ctype, 2,
                                            args[0], args[1]);
+  /* Force SAVE_EXPR even for calls which satisfy tree_invariant_p_1,
+     as while the call itself is const, the REALPART_EXPR store is
+     certainly not.  And in any case, we want just one call,
+     not multiple and trying to CSE them later.  */
+  TREE_SIDE_EFFECTS (call) = 1;
   tree tgt = save_expr (call);
   tree intres = build1_loc (loc, REALPART_EXPR, type, tgt);
   tree ovfres = build1_loc (loc, IMAGPART_EXPR, type, tgt);
   call = build_call_expr_internal_loc (loc, ifn, ctype, 2,
                                       intres, args[2]);
+  TREE_SIDE_EFFECTS (call) = 1;
   tgt = save_expr (call);
   intres = build1_loc (loc, REALPART_EXPR, type, tgt);
   tree ovfres2 = build1_loc (loc, IMAGPART_EXPR, type, tgt);

diff --git a/gcc/testsuite/gcc.c-torture/execute/pr108789.c b/gcc/testsuite/gcc.c-torture/execute/pr108789.c
new file mode 100644 (file)
index 0000000..32ee19b
--- /dev/null
+++ b/gcc/testsuite/gcc.c-torture/execute/pr108789.c
@@ -0,0 +1,39 @@
+/* PR middle-end/108789 */
+
+int
+add (unsigned *r, const unsigned *a, const unsigned *b)
+{
+  return __builtin_add_overflow (*a, *b, r);
+}
+
+int
+mul (unsigned *r, const unsigned *a, const unsigned *b)
+{
+  return __builtin_mul_overflow (*a, *b, r);
+}
+
+int
+main ()
+{
+  unsigned x;
+
+  /* 1073741824U + 1073741824U should not overflow.  */
+  x = (__INT_MAX__ + 1U) / 2;
+  if (add (&x, &x, &x))
+    __builtin_abort ();
+
+  /* 256U * 256U should not overflow */
+  x = 1U << (sizeof (int) * __CHAR_BIT__ / 4);
+  if (mul (&x, &x, &x))
+    __builtin_abort ();
+
+  /* 2147483648U + 2147483648U should overflow */
+  x = __INT_MAX__ + 1U;
+  if (!add (&x, &x, &x))
+    __builtin_abort ();
+
+  /* 65536U * 65536U should overflow */
+  x = 1U << (sizeof (int) * __CHAR_BIT__ / 2);
+  if (!mul (&x, &x, &x))
+    __builtin_abort ();
+}