Re: [PATCH] tree-optimization/109170 - bogus use-after-free with __builtin_expect

[Richard Biener <rguenther@suse.de>]

On Mon, 20 Mar 2023, Jakub Jelinek wrote:

> On Mon, Mar 20, 2023 at 12:12:14PM +0000, Richard Biener wrote:
> > 	PR tree-optimization/109170
> > 	* gimple-range-op.cc (cfn_pass_through_arg1): New.
> > 	(gimple_range_op_handler::maybe_builtin_call): Handle
> > 	__builtin_expect and similar via cfn_pass_through_arg1
> > 	and inspecting the calls fnspec.
> > 	* builtins.cc (builtin_fnspec): Handle BUILT_IN_EXPECT
> > 	and BUILT_IN_EXPECT_WITH_PROBABILITY.
> 
> I'm still worried about this builtins.cc change, can't we defer
> that part till GCC 14 where there will be enough time to see if it
> doesn't result in some undesirable problems (__builtin_expect* being
> optimized away when it still shouldn't etc.)?

Sure.  I've retested and pushed the following.

Richard.

From 02face8ff38e5a7942cfcb8c7444e6cca35d7523 Mon Sep 17 00:00:00 2001
From: Richard Biener <rguenther@suse.de>
Date: Fri, 17 Mar 2023 13:14:49 +0100
Subject: [PATCH] tree-optimization/109170 - bogus use-after-free with
 __builtin_expect
To: gcc-patches@gcc.gnu.org

The following adds a missing range-op for __builtin_expect which
helps -Wuse-after-free to detect the case a realloc original
pointer is used when the result was NULL.  The implementation
should handle all argument one pass-through builtins we handle
in the fnspec machinery, but that's defered to GCC 14.

The gcc.dg/tree-ssa/ssa-lim-21.c testcase needs adjustment because

   for (int j = 0; j < m; j++)
     if (__builtin_expect (m, 0))
       for (int i = 0; i < m; i++)

is now correctly optimized to a unconditional jump by EVRP - m
cannot be zero when the outer loop is entered.  I've adjusted
the outer loop to iterate 'n' times which makes us apply store-motion
to 'count' and 'q->data1' but only out of the inner loop and
as expected not apply store motion to 'q->data' at all.

The gcc.dg/predict-20.c testcase relies on broken behavior of
profile estimation when trying to handle __builtin_expect values
flowing into PHI nodes.  I have opened PR109210 and removed
the expected matching from the testcase.

	PR tree-optimization/109170
	* gimple-range-op.cc (cfn_pass_through_arg1): New.
	(gimple_range_op_handler::maybe_builtin_call): Handle
	__builtin_expect via cfn_pass_through_arg1.

	* gcc.dg/Wuse-after-free-pr109170.c: New testcase.
	* gcc.dg/tree-ssa/ssa-lim-21.c: Adjust.
	* gcc.dg/predict-20.c: Likewise.
---
 gcc/gimple-range-op.cc                        | 27 +++++++++++++++++++
 .../gcc.dg/Wuse-after-free-pr109170.c         | 15 +++++++++++
 gcc/testsuite/gcc.dg/predict-20.c             |  3 ++-
 gcc/testsuite/gcc.dg/tree-ssa/ssa-lim-21.c    |  7 ++---
 4 files changed, 48 insertions(+), 4 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/Wuse-after-free-pr109170.c

diff --git a/gcc/gimple-range-op.cc b/gcc/gimple-range-op.cc
index a5d625387e7..c7c546caf43 100644
--- a/gcc/gimple-range-op.cc
+++ b/gcc/gimple-range-op.cc
@@ -309,6 +309,26 @@ public:
   }
 } op_cfn_constant_p;
 
+// Implement range operator for integral/pointer functions returning
+// the first argument.
+class cfn_pass_through_arg1 : public range_operator
+{
+public:
+  using range_operator::fold_range;
+  virtual bool fold_range (irange &r, tree, const irange &lh,
+			   const irange &, relation_trio) const
+  {
+    r = lh;
+    return true;
+  }
+  virtual bool op1_range (irange &r, tree, const irange &lhs,
+			  const irange &, relation_trio) const
+  {
+    r = lhs;
+    return true;
+  }
+} op_cfn_pass_through_arg1;
+
 // Implement range operator for CFN_BUILT_IN_SIGNBIT.
 class cfn_signbit : public range_operator_float
 {
@@ -966,6 +986,13 @@ gimple_range_op_handler::maybe_builtin_call ()
       m_int = &op_cfn_parity;
       break;
 
+    case CFN_BUILT_IN_EXPECT:
+    case CFN_BUILT_IN_EXPECT_WITH_PROBABILITY:
+      m_valid = true;
+      m_op1 = gimple_call_arg (call, 0);
+      m_int = &op_cfn_pass_through_arg1;
+      break;
+
     default:
       break;
     }
diff --git a/gcc/testsuite/gcc.dg/Wuse-after-free-pr109170.c b/gcc/testsuite/gcc.dg/Wuse-after-free-pr109170.c
new file mode 100644
index 00000000000..14f1350aa29
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/Wuse-after-free-pr109170.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -Wuse-after-free=2" } */
+
+unsigned long bufmax = 0;
+unsigned long __open_catalog_bufmax;
+void *realloc(void *, __SIZE_TYPE__);
+void free(void *);
+
+void __open_catalog(char *buf)
+{
+  char *old_buf = buf;
+  buf = realloc (buf, bufmax);
+  if (__builtin_expect ((buf == ((void *)0)), 0))
+    free (old_buf); /* { dg-bogus "used after" } */
+}
diff --git a/gcc/testsuite/gcc.dg/predict-20.c b/gcc/testsuite/gcc.dg/predict-20.c
index 31d01835b80..7bb0d411f88 100644
--- a/gcc/testsuite/gcc.dg/predict-20.c
+++ b/gcc/testsuite/gcc.dg/predict-20.c
@@ -16,8 +16,9 @@ c ()
 	break;
     }
   int d = b < 0;
+  /* We fail to apply __builtin_expect heuristics here.  Se PR109210.  */
   if (__builtin_expect (d, 0))
     asm("");
 }
 
-/* { dg-final { scan-tree-dump-times "__builtin_expect heuristics of edge" 3 "profile_estimate"} } */
+/* { dg-final { scan-tree-dump-times "__builtin_expect heuristics of edge" 2 "profile_estimate" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-lim-21.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-lim-21.c
index ffe6f8f699d..fe29e841f28 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-lim-21.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-lim-21.c
@@ -17,7 +17,7 @@ void
 func (int m, int n, int k, struct obj *a)
 {
   struct obj *q = a;
-  for (int j = 0; j < m; j++)
+  for (int j = 0; j < n; j++)
     if (__builtin_expect (m, 0))
       for (int i = 0; i < m; i++)
 	{
@@ -31,5 +31,6 @@ func (int m, int n, int k, struct obj *a)
 	}
 }
 
-/* { dg-final { scan-tree-dump-not "Executing store motion of" "lim2"  }  } */
-
+/* { dg-final { scan-tree-dump "Executing store motion of count from loop 2" "lim2"  }  } */
+/* { dg-final { scan-tree-dump "Executing store motion of \[^ \]*data1 from loop 2" "lim2"  }  } */
+/* { dg-final { scan-tree-dump-times "Executing store motion of" 2 "lim2"  }  } */
-- 
2.35.3