diff mbox

Optimize BIT_AND_EXPRs for UBSAN_OBJECT_SIZE

Message ID 20141103204705.GQ20462@redhat.com
State New
Headers show

Commit Message

Marek Polacek Nov. 3, 2014, 8:47 p.m. UTC 
We don't emit UBSAN_BOUNDS checks in case we can at compile-time
prove that the array access is fine.  Also if we have [i & CST],
where CST is <= bound_of_the_array, we know we're fine as well.

But we don't have similar BIT_AND_EXPR check for UBSAN_OBJECT_SIZE
which is what this patch attempts to add.
(This is unrelated to the UBSAN_NULL optimization I posted earlier
today.)

Bootstrap-ubsan/regtest passed on x86_64-linux, ok for trunk?

2014-11-03  Marek Polacek  <polacek@redhat.com>

	* ubsan.c (instrument_object_size): Optimize [x & CST] array accesses.
testsuite/
	* c-c++-common/ubsan/object-size-10.c: New test.


	Marek

Comments

Jeff Law Nov. 3, 2014, 10:07 p.m. UTC | #1 
On 11/03/14 13:47, Marek Polacek wrote:
> We don't emit UBSAN_BOUNDS checks in case we can at compile-time
> prove that the array access is fine.  Also if we have [i & CST],
> where CST is <= bound_of_the_array, we know we're fine as well.
>
> But we don't have similar BIT_AND_EXPR check for UBSAN_OBJECT_SIZE
> which is what this patch attempts to add.
> (This is unrelated to the UBSAN_NULL optimization I posted earlier
> today.)
>
> Bootstrap-ubsan/regtest passed on x86_64-linux, ok for trunk?
>
> 2014-11-03  Marek Polacek  <polacek@redhat.com>
>
> 	* ubsan.c (instrument_object_size): Optimize [x & CST] array accesses.
> testsuite/
> 	* c-c++-common/ubsan/object-size-10.c: New test.
OK.
jeff
Jakub Jelinek Nov. 3, 2014, 10:29 p.m. UTC | #2 
On Mon, Nov 03, 2014 at 09:47:05PM +0100, Marek Polacek wrote:
> @@ -1456,6 +1457,8 @@ instrument_object_size (gimple_stmt_iterator *gsi, bool is_lhs)
>  	}
>        break;
>      case ARRAY_REF:
> +      index = TREE_OPERAND (t, 1);
> +      break;
>      case INDIRECT_REF:
>      case MEM_REF:
>      case VAR_DECL:

In theory, perhaps you could check the offset from get_inner_reference
instead, and look for SSA_NAME set to BIT_AND_EXPR there instead, to handle
cases like
struct S { int a, b; } a[1024];
...
int j = a[i & 1023].b;
etc. - you have size of the base already computed, if the constant part
of offset and bitoffset together is less than that size and the variable
part of it is SSA_NAME set to BIT_AND_EXPR with non-negative const smaller
than size - (constant part of offset + (bitoffset + BITS_PER_UNIT - 1) /
BITS_PER_UNIT + access size), optimize the check away.  But perhaps it can
wait for later.

> @@ -1537,6 +1540,24 @@ instrument_object_size (gimple_stmt_iterator *gsi, bool is_lhs)
>        && tree_int_cst_le (t, sizet))
>      return;
>  
> +  if (index != NULL_TREE
> +      && TREE_CODE (index) == SSA_NAME
> +      && TREE_CODE (sizet) == INTEGER_CST)
> +    {
> +      gimple def = SSA_NAME_DEF_STMT (index);
> +      if (is_gimple_assign (def)
> +	  && gimple_assign_rhs_code (def) == BIT_AND_EXPR
> +	  && TREE_CODE (gimple_assign_rhs2 (def)) == INTEGER_CST)
> +	{
> +	  tree cst = gimple_assign_rhs2 (def);
> +	  tree sz = fold_build2 (EXACT_DIV_EXPR, sizetype, sizet,
> +				 TYPE_SIZE_UNIT (type));
> +	  if (tree_int_cst_sgn (cst) >= 0
> +	      && tree_int_cst_lt (cst, sz))
> +	    return;
> +	}
> +    }
> +
>    /* Nope.  Emit the check.  */
>    t = force_gimple_operand_gsi (gsi, t, true, NULL_TREE, true,
>  				GSI_SAME_STMT);
> 

Ok, thanks.

	Jakub
diff mbox

Patch

diff --git gcc/testsuite/c-c++-common/ubsan/object-size-10.c gcc/testsuite/c-c++-common/ubsan/object-size-10.c
index e69de29..ebc8582 100644
--- gcc/testsuite/c-c++-common/ubsan/object-size-10.c
+++ gcc/testsuite/c-c++-common/ubsan/object-size-10.c
@@ -0,0 +1,79 @@ 
+/* { dg-do run } */
+/* { dg-skip-if "" { *-*-* } { "*" } { "-O2" } } */
+/* { dg-options "-fsanitize=undefined" } */
+
+static char a[128];
+static int b[128];
+
+__attribute__ ((noinline, noclone)) int
+fn1 (int i)
+{
+  asm ("");
+  return a[i & 127];
+}
+
+__attribute__ ((noinline, noclone)) int
+fn2 (int i)
+{
+  asm ("");
+  return a[i & 128];
+}
+
+/* { dg-output "index 128 out of bounds for type 'char \\\[128\\\]'\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*load of address \[^\n\r]* with insufficient space for an object of type 'char'\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*note: pointer points here\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*\\^\[^\n\r]*(\n|\r\n|\r)" } */
+
+__attribute__ ((noinline, noclone)) int
+fn3 (int i)
+{
+  asm ("");
+  return b[i & 127];
+}
+
+__attribute__ ((noinline, noclone)) int
+fn4 (int i)
+{
+  asm ("");
+  return b[i & 128];
+}
+
+/* { dg-output "\[^\n\r]*index 128 out of bounds for type 'int \\\[128\\\]'\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*load of address \[^\n\r]* with insufficient space for an object of type 'int'\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*note: pointer points here\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*\\^\[^\n\r]*(\n|\r\n|\r)" } */
+
+__attribute__ ((noinline, noclone)) int
+fn5 (int i, int j)
+{
+  asm ("");
+  return b[i & j];
+}
+
+/* { dg-output "\[^\n\r]*index 128 out of bounds for type 'int \\\[128\\\]'\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*load of address \[^\n\r]* with insufficient space for an object of type 'int'\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*note: pointer points here\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*\[^\n\r]*(\n|\r\n|\r)" } */
+/* { dg-output "\[^\n\r]*\\^\[^\n\r]*(\n|\r\n|\r)" } */
+
+__attribute__ ((noinline, noclone)) int
+fn6 (int i)
+{
+  asm ("");
+  return b[i & 0];
+}
+
+int
+main (void)
+{
+  fn1 (128);
+  fn2 (128);
+  fn3 (128);
+  fn4 (128);
+  fn5 (128, 127);
+  fn5 (128, 128);
+  fn6 (128);
+  return 0;
+}
diff --git gcc/ubsan.c gcc/ubsan.c
index ed2fc54..41cf546 100644
--- gcc/ubsan.c
+++ gcc/ubsan.c
@@ -1438,6 +1438,7 @@  instrument_object_size (gimple_stmt_iterator *gsi, bool is_lhs)
   location_t loc = gimple_location (stmt);
   tree t = is_lhs ? gimple_get_lhs (stmt) : gimple_assign_rhs1 (stmt);
   tree type;
+  tree index = NULL_TREE;
   HOST_WIDE_INT size_in_bytes;
 
   type = TREE_TYPE (t);
@@ -1456,6 +1457,8 @@  instrument_object_size (gimple_stmt_iterator *gsi, bool is_lhs)
 	}
       break;
     case ARRAY_REF:
+      index = TREE_OPERAND (t, 1);
+      break;
     case INDIRECT_REF:
     case MEM_REF:
     case VAR_DECL:
@@ -1537,6 +1540,24 @@  instrument_object_size (gimple_stmt_iterator *gsi, bool is_lhs)
       && tree_int_cst_le (t, sizet))
     return;
 
+  if (index != NULL_TREE
+      && TREE_CODE (index) == SSA_NAME
+      && TREE_CODE (sizet) == INTEGER_CST)
+    {
+      gimple def = SSA_NAME_DEF_STMT (index);
+      if (is_gimple_assign (def)
+	  && gimple_assign_rhs_code (def) == BIT_AND_EXPR
+	  && TREE_CODE (gimple_assign_rhs2 (def)) == INTEGER_CST)
+	{
+	  tree cst = gimple_assign_rhs2 (def);
+	  tree sz = fold_build2 (EXACT_DIV_EXPR, sizetype, sizet,
+				 TYPE_SIZE_UNIT (type));
+	  if (tree_int_cst_sgn (cst) >= 0
+	      && tree_int_cst_lt (cst, sz))
+	    return;
+	}
+    }
+
   /* Nope.  Emit the check.  */
   t = force_gimple_operand_gsi (gsi, t, true, NULL_TREE, true,
 				GSI_SAME_STMT);