This is the mail archive of the gcc-patches@gcc.gnu.org mailing list for the GCC project.


Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]
Other format: [Raw text]

Re: [PATCH] Make strlen range computations more conservative


Hi,

this is an update (v5) of my patch:

As discussed earlier, this version does no longer enable
-fassume-zero-terminated-char-arrays with -Ofast.

I am ready to remove the -fassume-zero-terminated-char-arrays altogether if we decide what
to do with the code-gen test cases that still use it (xfail or remove).


Bootstrapped and reg-tested on x86_64-pc-linux-gnu.
Is it OK for trunk?


Thanks
Bernd.

Attachment: changelog-range-strlen-v5.txt
Description: changelog-range-strlen-v5.txt

diff -Npur gcc/common.opt gcc/common.opt
--- gcc/common.opt	2018-08-19 17:11:34.000000000 +0200
+++ gcc/common.opt	2018-08-22 09:04:53.520305828 +0200
@@ -1025,6 +1025,10 @@ fsanitize-undefined-trap-on-error
 Common Driver Report Var(flag_sanitize_undefined_trap_on_error) Init(0)
 Use trap instead of a library function for undefined behavior sanitization.
 
+fassume-zero-terminated-char-arrays
+Common Var(flag_assume_zero_terminated_char_arrays) Optimization Init(0)
+Optimize under the assumption that char arrays must always be zero terminated.
+
 fasynchronous-unwind-tables
 Common Report Var(flag_asynchronous_unwind_tables) Optimization
 Generate unwind tables that are exact at each instruction boundary.
diff -Npur gcc/doc/invoke.texi gcc/doc/invoke.texi
--- gcc/doc/invoke.texi	2018-08-21 10:13:34.000000000 +0200
+++ gcc/doc/invoke.texi	2018-08-22 09:06:18.645102845 +0200
@@ -388,7 +388,8 @@ Objective-C and Objective-C++ Dialects}.
 -falign-jumps[=@var{n}[:@var{m}:[@var{n2}[:@var{m2}]]]] @gol
 -falign-labels[=@var{n}[:@var{m}:[@var{n2}[:@var{m2}]]]] @gol
 -falign-loops[=@var{n}[:@var{m}:[@var{n2}[:@var{m2}]]]] @gol
--fassociative-math  -fauto-profile  -fauto-profile[=@var{path}] @gol
+-fassociative-math  -fassume-zero-terminated-char-arrays @gol
+-fauto-profile  -fauto-profile[=@var{path}] @gol
 -fauto-inc-dec  -fbranch-probabilities @gol
 -fbranch-target-load-optimize  -fbranch-target-load-optimize2 @gol
 -fbtr-bb-exclusive  -fcaller-saves @gol
@@ -9978,6 +9979,16 @@ is automatically enabled when both @opti
 
 The default is @option{-fno-associative-math}.
 
+@item -fassume-zero-terminated-char-arrays
+@opindex fassume-zero-terminated-char-arrays
+
+Optimize under the assumption that char arrays must always be zero
+terminated.  This may have an effect on code that uses strlen to
+check the string length, for instance in assertions.  Under certain
+conditions such checks can be optimized away.
+
+The default is @option{-fno-assume-zero-terminated-char-arrays}.
+
 @item -freciprocal-math
 @opindex freciprocal-math
 
diff -Npur gcc/gimple-fold.c gcc/gimple-fold.c
--- gcc/gimple-fold.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/gimple-fold.c	2018-08-22 09:04:53.741302702 +0200
@@ -1257,6 +1257,45 @@ gimple_fold_builtin_memset (gimple_stmt_
   return true;
 }
 
+/* Determine if a char array is suitable for strlen range estimations.
+   Return false if ARG is not a char array, or if the inner reference
+   chain appears to go through a type cast, or if !optimistic,
+   or if !flag_assume_zero_terminated_char_arrays.
+   Otherwise return true.
+   Note that type gimple type informations are not 100% guaranteed
+   to be accurate.
+   OPTIMISTIC is true when the result is used for warnings only.  */
+
+bool
+looks_like_a_char_array_without_typecast_p (tree arg, bool optimistic)
+{
+  if (!flag_assume_zero_terminated_char_arrays && !optimistic)
+    return false;
+
+  /* We handle arrays of integer types.  */
+  if (TREE_CODE (TREE_TYPE (arg)) != ARRAY_TYPE
+      || TREE_CODE (TREE_TYPE (TREE_TYPE (arg))) != INTEGER_TYPE
+      || TYPE_MODE (TREE_TYPE (TREE_TYPE (arg))) != TYPE_MODE (char_type_node)
+      || TYPE_PRECISION (TREE_TYPE (TREE_TYPE (arg)))
+	 != TYPE_PRECISION (char_type_node))
+    return false;
+
+  tree base = arg;
+  while (TREE_CODE (base) == ARRAY_REF
+	 || TREE_CODE (base) == ARRAY_RANGE_REF
+	 || TREE_CODE (base) == COMPONENT_REF)
+    base = TREE_OPERAND (base, 0);
+
+  /* If this looks like a type cast don't assume anything.  */
+  if ((TREE_CODE (base) == MEM_REF
+       && (! integer_zerop (TREE_OPERAND (base, 1))
+	   || TYPE_MAIN_VARIANT (TREE_TYPE (TREE_TYPE (TREE_OPERAND (base, 0))))
+	      != TYPE_MAIN_VARIANT (TREE_TYPE (base))))
+      || handled_component_p (base))
+    return false;
+
+  return true;
+}
 
 /* Obtain the minimum and maximum string length or minimum and maximum
    value of ARG in LENGTH[0] and LENGTH[1], respectively.
@@ -1272,6 +1311,7 @@ gimple_fold_builtin_memset (gimple_stmt_
    PHIs and COND_EXPRs optimistically, if we can determine string length
    minimum and maximum, it will use the minimum from the ones where it
    can be determined.
+   TYPE == 2 and FUZZY != 0 cannot be used together.
    Set *FLEXP to true if the range of the string lengths has been
    obtained from the upper bound of an array at the end of a struct.
    Such an array may hold a string that's longer than its upper bound
@@ -1312,8 +1352,8 @@ get_range_strlen (tree arg, tree length[
 		 member.  */
 	      tree idx = TREE_OPERAND (op, 1);
 
-	      arg = TREE_OPERAND (op, 0);
-	      tree optype = TREE_TYPE (arg);
+	      op = TREE_OPERAND (op, 0);
+	      tree optype = TREE_TYPE (op);
 	      if (tree dom = TYPE_DOMAIN (optype))
 		if (tree bound = TYPE_MAX_VALUE (dom))
 		  if (TREE_CODE (bound) == INTEGER_CST
@@ -1339,23 +1379,21 @@ get_range_strlen (tree arg, tree length[
 	    return get_range_strlen (TREE_OPERAND (arg, 0), length,
 				     visited, type, fuzzy, flexp, eltsize);
 
+	  if (eltsize != 1)
+	    return false;
+
 	  if (TREE_CODE (arg) == ARRAY_REF)
 	    {
-	      tree type = TREE_TYPE (TREE_OPERAND (arg, 0));
-
-	      /* Determine the "innermost" array type.  */
-	      while (TREE_CODE (type) == ARRAY_TYPE
-		     && TREE_CODE (TREE_TYPE (type)) == ARRAY_TYPE)
-		type = TREE_TYPE (type);
-
-	      /* Avoid arrays of pointers.  */
-	      tree eltype = TREE_TYPE (type);
-	      if (TREE_CODE (type) != ARRAY_TYPE
-		  || !INTEGRAL_TYPE_P (eltype))
+	      if (!looks_like_a_char_array_without_typecast_p (arg, fuzzy == 2))
 		return false;
 
+	      tree type = TREE_TYPE (arg);
+
+	      /* Fail when the array bound is unknown or zero.  */
 	      val = TYPE_SIZE_UNIT (type);
-	      if (!val || integer_zerop (val))
+	      if (!val
+		  || TREE_CODE (val) != INTEGER_CST
+		  || integer_zerop (val))
 		return false;
 
 	      val = fold_build2 (MINUS_EXPR, TREE_TYPE (val), val,
@@ -1364,15 +1402,16 @@ get_range_strlen (tree arg, tree length[
 		 the array could have zero length.  */
 	      *minlen = ssize_int (0);
 
-	      if (TREE_CODE (TREE_OPERAND (arg, 0)) == COMPONENT_REF
-		  && type == TREE_TYPE (TREE_OPERAND (arg, 0))
-		  && array_at_struct_end_p (TREE_OPERAND (arg, 0)))
+	      if (TREE_CODE (arg) == COMPONENT_REF
+		  && type == TREE_TYPE (arg)
+		  && array_at_struct_end_p (arg))
 		*flexp = true;
 	    }
-	  else if (TREE_CODE (arg) == COMPONENT_REF
-		   && (TREE_CODE (TREE_TYPE (TREE_OPERAND (arg, 1)))
-		       == ARRAY_TYPE))
+	  else if (TREE_CODE (arg) == COMPONENT_REF)
 	    {
+	      if (!looks_like_a_char_array_without_typecast_p (arg, fuzzy == 2))
+		return false;
+
 	      /* Use the type of the member array to determine the upper
 		 bound on the length of the array.  This may be overly
 		 optimistic if the array itself isn't NUL-terminated and
@@ -1388,22 +1427,21 @@ get_range_strlen (tree arg, tree length[
 
 	      tree type = TREE_TYPE (arg);
 
-	      while (TREE_CODE (type) == ARRAY_TYPE
-		     && TREE_CODE (TREE_TYPE (type)) == ARRAY_TYPE)
-		type = TREE_TYPE (type);
-
 	      /* Fail when the array bound is unknown or zero.  */
 	      val = TYPE_SIZE_UNIT (type);
-	      if (!val || integer_zerop (val))
+	      if (!val
+		  || TREE_CODE (val) != INTEGER_CST
+		  || integer_zerop (val))
 		return false;
+
 	      val = fold_build2 (MINUS_EXPR, TREE_TYPE (val), val,
 				 integer_one_node);
 	      /* Set the minimum size to zero since the string in
 		 the array could have zero length.  */
 	      *minlen = ssize_int (0);
 	    }
-
-	  if (VAR_P (arg))
+	  else if (VAR_P (arg)
+		   && (flag_assume_zero_terminated_char_arrays || fuzzy == 2))
 	    {
 	      tree type = TREE_TYPE (arg);
 	      if (POINTER_TYPE_P (type))
@@ -1411,13 +1449,23 @@ get_range_strlen (tree arg, tree length[
 
 	      if (TREE_CODE (type) == ARRAY_TYPE)
 		{
+		  /* We handle arrays of integer types.  */
+		  if (TREE_CODE (TREE_TYPE (type)) != INTEGER_TYPE
+		      || TYPE_MODE (TREE_TYPE (type))
+			 != TYPE_MODE (char_type_node)
+		      || TYPE_PRECISION (TREE_TYPE (type))
+			 != TYPE_PRECISION (char_type_node))
+		    return false;
+
+		  /* Fail when the array bound is unknown or zero.  */
 		  val = TYPE_SIZE_UNIT (type);
 		  if (!val
 		      || TREE_CODE (val) != INTEGER_CST
 		      || integer_zerop (val))
 		    return false;
-		  val = wide_int_to_tree (TREE_TYPE (val),
-					  wi::sub (wi::to_wide (val), 1));
+
+		  val = fold_build2 (MINUS_EXPR, TREE_TYPE (val), val,
+				     integer_one_node);
 		  /* Set the minimum size to zero since the string in
 		     the array could have zero length.  */
 		  *minlen = ssize_int (0);
@@ -1550,6 +1598,7 @@ get_range_strlen (tree arg, tree length[
    if we can determine string length minimum and maximum; it will use
    the minimum from the ones where it can be determined.
    STRICT false should be only used for warning code.
+   STRICT is by default false.
 
    ELTSIZE is 1 for normal single byte character strings, and 2 or
    4 for wide characer strings.  ELTSIZE is by default 1.  */
diff -Npur gcc/gimple-fold.h gcc/gimple-fold.h
--- gcc/gimple-fold.h	2018-08-19 17:11:34.000000000 +0200
+++ gcc/gimple-fold.h	2018-08-22 09:04:53.741302702 +0200
@@ -61,6 +61,7 @@ extern bool gimple_fold_builtin_snprintf
 extern bool arith_code_with_undefined_signed_overflow (tree_code);
 extern gimple_seq rewrite_to_defined_overflow (gimple *);
 extern void replace_call_with_value (gimple_stmt_iterator *, tree);
+extern bool looks_like_a_char_array_without_typecast_p (tree, bool);
 
 /* gimple_build, functionally matching fold_buildN, outputs stmts
    int the provided sequence, matching and simplifying them on-the-fly.
diff -Npur gcc/testsuite/gcc.dg/pr83373.c gcc/testsuite/gcc.dg/pr83373.c
--- gcc/testsuite/gcc.dg/pr83373.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/testsuite/gcc.dg/pr83373.c	2018-08-22 11:48:17.312080785 +0200
@@ -16,7 +16,7 @@ inline char* my_strcpy (char* dst, const
     __builtin_memcpy (dst, src, len + 1);
   else
     {
-      __builtin_memcpy (dst, src, size - 1); /* { dg-bogus "\\\[-Wstringop-oveflow]" } */
+      __builtin_memcpy (dst, src, size - 1); /* { dg-bogus "\\\[-Wstringop-overflow=]" "" { xfail *-*-* } } */
       dst[size - 1] = '\0';
     }
 
diff -Npur gcc/testsuite/gcc.dg/strlenopt-36.c gcc/testsuite/gcc.dg/strlenopt-36.c
--- gcc/testsuite/gcc.dg/strlenopt-36.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/testsuite/gcc.dg/strlenopt-36.c	2018-08-22 09:04:53.742302688 +0200
@@ -1,7 +1,7 @@
 /* PR tree-optimization/78450 - strlen(s) return value can be assumed
    to be less than the size of s
    { dg-do compile }
-   { dg-options "-O2 -fdump-tree-optimized" } */
+   { dg-options "-O2 -fassume-zero-terminated-char-arrays -fdump-tree-optimized" } */
 
 #include "strlenopt.h"
 
diff -Npur gcc/testsuite/gcc.dg/strlenopt-40.c gcc/testsuite/gcc.dg/strlenopt-40.c
--- gcc/testsuite/gcc.dg/strlenopt-40.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/testsuite/gcc.dg/strlenopt-40.c	2018-08-22 09:04:53.742302688 +0200
@@ -1,7 +1,7 @@
 /* PR tree-optimization/83671 - fix for false positive reported by
    -Wstringop-overflow does not work with inlining
    { dg-do compile }
-   { dg-options "-O1 -fdump-tree-optimized" } */
+   { dg-options "-O1 -fassume-zero-terminated-char-arrays -fdump-tree-optimized" } */
 
 #include "strlenopt.h"
 
@@ -219,10 +219,15 @@ void elim_member_arrays_ptr (struct MemA
 
   ELIM_TRUE (strlen (ma0->a5_7[0]) < 7);
   ELIM_TRUE (strlen (ma0[0].a5_7[0]) < 7);
+#if 0
+  /* This is transformed into strlen ((const char *) &(ma0 + 64)->a5_7[0])
+     which looks like a type cast and fails the check in
+     looks_like_a_char_array_without_typecast_p.  */
   ELIM_TRUE (strlen (ma0[1].a5_7[0]) < 7);
   ELIM_TRUE (strlen (ma0[1].a5_7[4]) < 7);
   ELIM_TRUE (strlen (ma0[9].a5_7[0]) < 7);
   ELIM_TRUE (strlen (ma0[9].a5_7[4]) < 7);
+#endif
 
   ELIM_TRUE (strlen (ma0->a3) < sizeof ma0->a3);
   ELIM_TRUE (strlen (ma0->a5) < sizeof ma0->a5);
diff -Npur gcc/testsuite/gcc.dg/strlenopt-45.c gcc/testsuite/gcc.dg/strlenopt-45.c
--- gcc/testsuite/gcc.dg/strlenopt-45.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/testsuite/gcc.dg/strlenopt-45.c	2018-08-22 09:04:53.767302335 +0200
@@ -2,7 +2,7 @@
    Test to verify that strnlen built-in expansion works correctly
    in the absence of tree strlen optimization.
    { dg-do compile }
-   { dg-options "-O2 -Wall -fdump-tree-optimized" } */
+   { dg-options "-O2 -Wall -fassume-zero-terminated-char-arrays -fdump-tree-optimized" } */
 
 #include "strlenopt.h"
 
@@ -43,7 +43,6 @@ extern size_t strnlen (const char *, siz
   else						\
     FAIL (made_in_false_branch)
 
-extern char c;
 extern char a1[1];
 extern char a3[3];
 extern char a5[5];
@@ -52,18 +51,6 @@ extern char ax[];
 
 void elim_strnlen_arr_cst (void)
 {
-  /* The length of a string stored in a one-element array must be zero.
-     The result reported by strnlen() for such an array can be non-zero
-     only when the bound is equal to 1 (in which case the result must
-     be one).  */
-  ELIM (strnlen (&c, 0) == 0);
-  ELIM (strnlen (&c, 1) < 2);
-  ELIM (strnlen (&c, 2) == 0);
-  ELIM (strnlen (&c, 9) == 0);
-  ELIM (strnlen (&c, PTRDIFF_MAX) == 0);
-  ELIM (strnlen (&c, SIZE_MAX) == 0);
-  ELIM (strnlen (&c, -1) == 0);
-
   ELIM (strnlen (a1, 0) == 0);
   ELIM (strnlen (a1, 1) < 2);
   ELIM (strnlen (a1, 2) == 0);
@@ -99,17 +86,18 @@ void elim_strnlen_arr_cst (void)
   ELIM (strnlen (a3_7[2], SIZE_MAX) < 8);
   ELIM (strnlen (a3_7[2], -1) < 8);
 
-  ELIM (strnlen ((char*)a3_7, 0) == 0);
-  ELIM (strnlen ((char*)a3_7, 1) < 2);
-  ELIM (strnlen ((char*)a3_7, 2) < 3);
-  ELIM (strnlen ((char*)a3_7, 3) < 4);
-  ELIM (strnlen ((char*)a3_7, 9) < 10);
-  ELIM (strnlen ((char*)a3_7, 19) < 20);
-  ELIM (strnlen ((char*)a3_7, 21) < 22);
-  ELIM (strnlen ((char*)a3_7, 23) < 22);
-  ELIM (strnlen ((char*)a3_7, PTRDIFF_MAX) < 22);
-  ELIM (strnlen ((char*)a3_7, SIZE_MAX) < 22);
-  ELIM (strnlen ((char*)a3_7, -1) < 22);
+  ELIM (strnlen ((char*)a3_7[0], 0) == 0);
+  ELIM (strnlen ((char*)a3_7[0], 1) < 2);
+  ELIM (strnlen ((char*)a3_7[0], 2) < 3);
+  ELIM (strnlen ((char*)a3_7[0], 3) < 4);
+  ELIM (strnlen ((char*)a3_7[0], 7) < 8);
+  ELIM (strnlen ((char*)a3_7[0], 9) < 7);
+  ELIM (strnlen ((char*)a3_7[0], 19) < 7);
+  ELIM (strnlen ((char*)a3_7[0], 21) < 7);
+  ELIM (strnlen ((char*)a3_7[0], 23) < 7);
+  ELIM (strnlen ((char*)a3_7[0], PTRDIFF_MAX) < 7);
+  ELIM (strnlen ((char*)a3_7[0], SIZE_MAX) < 7);
+  ELIM (strnlen ((char*)a3_7[0], -1) < 7);
 
   ELIM (strnlen (ax, 0) == 0);
   ELIM (strnlen (ax, 1) < 2);
@@ -122,7 +110,6 @@ void elim_strnlen_arr_cst (void)
 
 struct MemArrays
 {
-  char c;
   char a0[0];
   char a1[1];
   char a3[3];
@@ -133,13 +120,6 @@ struct MemArrays
 
 void elim_strnlen_memarr_cst (struct MemArrays *p, int i)
 {
-  ELIM (strnlen (&p->c, 0) == 0);
-  ELIM (strnlen (&p->c, 1) < 2);
-  ELIM (strnlen (&p->c, 9) == 0);
-  ELIM (strnlen (&p->c, PTRDIFF_MAX) == 0);
-  ELIM (strnlen (&p->c, SIZE_MAX) == 0);
-  ELIM (strnlen (&p->c, -1) == 0);
-
   /* Other accesses to internal zero-length arrays are undefined.  */
   ELIM (strnlen (p->a0, 0) == 0);
 
@@ -154,19 +134,19 @@ void elim_strnlen_memarr_cst (struct Mem
   ELIM (strnlen (p->a3, 1) < 2);
   ELIM (strnlen (p->a3, 2) < 3);
   ELIM (strnlen (p->a3, 3) < 4);
-  ELIM (strnlen (p->a3, 9) < 4);
-  ELIM (strnlen (p->a3, PTRDIFF_MAX) < 4);
-  ELIM (strnlen (p->a3, SIZE_MAX) < 4);
-  ELIM (strnlen (p->a3, -1) < 4);
+  ELIM (strnlen (p->a3, 9) < 3);
+  ELIM (strnlen (p->a3, PTRDIFF_MAX) < 3);
+  ELIM (strnlen (p->a3, SIZE_MAX) < 3);
+  ELIM (strnlen (p->a3, -1) < 3);
 
   ELIM (strnlen (p[i].a3, 0) == 0);
   ELIM (strnlen (p[i].a3, 1) < 2);
   ELIM (strnlen (p[i].a3, 2) < 3);
   ELIM (strnlen (p[i].a3, 3) < 4);
-  ELIM (strnlen (p[i].a3, 9) < 4);
-  ELIM (strnlen (p[i].a3, PTRDIFF_MAX) < 4);
-  ELIM (strnlen (p[i].a3, SIZE_MAX) < 4);
-  ELIM (strnlen (p[i].a3, -1) < 4);
+  ELIM (strnlen (p[i].a3, 9) < 3);
+  ELIM (strnlen (p[i].a3, PTRDIFF_MAX) < 3);
+  ELIM (strnlen (p[i].a3, SIZE_MAX) < 3);
+  ELIM (strnlen (p[i].a3, -1) < 3);
 
   ELIM (strnlen (p->a3_7[0], 0) == 0);
   ELIM (strnlen (p->a3_7[0], 1) < 2);
@@ -203,17 +183,18 @@ void elim_strnlen_memarr_cst (struct Mem
   ELIM (strnlen (p->a3_7[i], 19) < 20);
 #endif
 
-  ELIM (strnlen ((char*)p->a3_7, 0) == 0);
-  ELIM (strnlen ((char*)p->a3_7, 1) < 2);
-  ELIM (strnlen ((char*)p->a3_7, 2) < 3);
-  ELIM (strnlen ((char*)p->a3_7, 3) < 4);
-  ELIM (strnlen ((char*)p->a3_7, 9) < 10);
-  ELIM (strnlen ((char*)p->a3_7, 19) < 20);
-  ELIM (strnlen ((char*)p->a3_7, 21) < 22);
-  ELIM (strnlen ((char*)p->a3_7, 23) < 22);
-  ELIM (strnlen ((char*)p->a3_7, PTRDIFF_MAX) < 22);
-  ELIM (strnlen ((char*)p->a3_7, SIZE_MAX) < 22);
-  ELIM (strnlen ((char*)p->a3_7, -1) < 22);
+  ELIM (strnlen ((char*)p->a3_7[0], 0) == 0);
+  ELIM (strnlen ((char*)p->a3_7[0], 1) < 2);
+  ELIM (strnlen ((char*)p->a3_7[0], 2) < 3);
+  ELIM (strnlen ((char*)p->a3_7[0], 3) < 4);
+  ELIM (strnlen ((char*)p->a3_7[0], 7) < 8);
+  ELIM (strnlen ((char*)p->a3_7[0], 9) < 7);
+  ELIM (strnlen ((char*)p->a3_7[0], 19) < 7);
+  ELIM (strnlen ((char*)p->a3_7[0], 21) < 7);
+  ELIM (strnlen ((char*)p->a3_7[0], 23) < 7);
+  ELIM (strnlen ((char*)p->a3_7[0], PTRDIFF_MAX) < 7);
+  ELIM (strnlen ((char*)p->a3_7[0], SIZE_MAX) < 7);
+  ELIM (strnlen ((char*)p->a3_7[0], -1) < 7);
 
   ELIM (strnlen (p->ax, 0) == 0);
   ELIM (strnlen (p->ax, 1) < 2);
@@ -290,9 +271,6 @@ void elim_strnlen_range (char *s)
 
 void keep_strnlen_arr_cst (void)
 {
-  KEEP (strnlen (&c, 1) == 0);
-  KEEP (strnlen (&c, 1) == 1);
-
   KEEP (strnlen (a1, 1) == 0);
   KEEP (strnlen (a1, 1) == 1);
 
@@ -301,16 +279,12 @@ void keep_strnlen_arr_cst (void)
 
 struct FlexArrays
 {
-  char c;
   char a0[0];   /* Access to internal zero-length arrays are undefined.  */
   char a1[1];
 };
 
 void keep_strnlen_memarr_cst (struct FlexArrays *p)
 {
-  KEEP (strnlen (&p->c, 1) == 0);
-  KEEP (strnlen (&p->c, 1) == 1);
-
 #if 0
   /* Accesses to internal zero-length arrays are undefined so avoid
      exercising them.  */
@@ -331,5 +305,5 @@ void keep_strnlen_memarr_cst (struct Fle
 
 /* { dg-final { scan-tree-dump-times "call_in_true_branch_not_eliminated_" 0 "optimized" } }
 
-   { dg-final { scan-tree-dump-times "call_made_in_true_branch_on_line_1\[0-9\]\[0-9\]\[0-9\]" 13 "optimized" } }
-   { dg-final { scan-tree-dump-times "call_made_in_false_branch_on_line_1\[0-9\]\[0-9\]\[0-9\]" 13 "optimized" } } */
+   { dg-final { scan-tree-dump-times "call_made_in_true_branch_on_line_1\[0-9\]\[0-9\]\[0-9\]" 9 "optimized" } }
+   { dg-final { scan-tree-dump-times "call_made_in_false_branch_on_line_1\[0-9\]\[0-9\]\[0-9\]" 9 "optimized" } } */
diff -Npur gcc/testsuite/gcc.dg/strlenopt-48.c gcc/testsuite/gcc.dg/strlenopt-48.c
--- gcc/testsuite/gcc.dg/strlenopt-48.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/testsuite/gcc.dg/strlenopt-48.c	2018-08-22 09:04:53.767302335 +0200
@@ -3,7 +3,7 @@
    Verify that strlen() calls with one-character array elements of
    multidimensional arrays are still folded.
    { dg-do compile }
-   { dg-options "-O2 -Wall -fdump-tree-optimized" } */
+   { dg-options "-O2 -Wall -fassume-zero-terminated-char-arrays -fdump-tree-optimized" } */
 
 #include "strlenopt.h"
 
diff -Npur gcc/testsuite/gcc.dg/strlenopt-51.c gcc/testsuite/gcc.dg/strlenopt-51.c
--- gcc/testsuite/gcc.dg/strlenopt-51.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/testsuite/gcc.dg/strlenopt-51.c	2018-08-22 09:04:53.768302320 +0200
@@ -101,7 +101,7 @@ void test_keep_a9_9 (int i)
 {
 #undef T
 #define T(I)					\
-  KEEP (strlen (&a9_9[i][I][0]) > (1 + I) % 9);	\
+  KEEP (strlen (&a9_9[i][I][0]) > (0 + I) % 9);	\
   KEEP (strlen (&a9_9[i][I][1]) > (1 + I) % 9);	\
   KEEP (strlen (&a9_9[i][I][2]) > (2 + I) % 9);	\
   KEEP (strlen (&a9_9[i][I][3]) > (3 + I) % 9);	\
@@ -115,7 +115,7 @@ void test_keep_a9_9 (int i)
 }
 
 /* { dg-final { scan-tree-dump-times "strlen" 72 "gimple" } }
-   { dg-final { scan-tree-dump-times "strlen" 63 "optimized" } }
+   { dg-final { scan-tree-dump-times "strlen" 72 "optimized" } }
 
-   { dg-final { scan-tree-dump-times "call_made_in_true_branch_on_line_1\[0-9\]\[0-9\]\[0-9\]" 72 "optimized" } }
+   { dg-final { scan-tree-dump-times "call_made_in_true_branch_on_line_1\[0-9\]\[0-9\]\[0-9\]" 81 "optimized" } }
    { dg-final { scan-tree-dump-times "call_made_in_false_branch_on_line_1\[0-9\]\[0-9\]\[0-9\]" 81 "optimized" } } */
diff -Npur gcc/testsuite/gcc.dg/strlenopt-57.c gcc/testsuite/gcc.dg/strlenopt-57.c
--- gcc/testsuite/gcc.dg/strlenopt-57.c	1970-01-01 01:00:00.000000000 +0100
+++ gcc/testsuite/gcc.dg/strlenopt-57.c	2018-08-22 09:04:53.768302320 +0200
@@ -0,0 +1,25 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fdump-tree-optimized" } */
+
+#define assert(x) do { if (!(x)) __builtin_abort (); } while (0)
+extern int system (const char *);
+static int fun (char *p)
+{
+  char buf[16];
+
+  assert (__builtin_strlen (p) < 4);
+
+  __builtin_sprintf (buf, "echo %s - %s", p, p);
+  return system (buf);
+}
+
+void test (void)
+{
+  char b[2] = "ab";
+  fun (b);
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_strlen" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "__builtin_abort" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "__builtin_sprintf" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "system" 1 "optimized" } } */
diff -Npur gcc/testsuite/gcc.dg/strlenopt-58.c gcc/testsuite/gcc.dg/strlenopt-58.c
--- gcc/testsuite/gcc.dg/strlenopt-58.c	1970-01-01 01:00:00.000000000 +0100
+++ gcc/testsuite/gcc.dg/strlenopt-58.c	2018-08-22 09:10:24.485637281 +0200
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fassume-zero-terminated-char-arrays -fdump-tree-optimized" } */
+
+typedef char A[6];
+typedef char B[2][3];
+
+A a;
+
+void test (void)
+{
+  B* b = (B*) a;
+  if (__builtin_strlen ((*b)[0]) > 2)
+    __builtin_abort ();
+}
+
+/* { dg-final { scan-tree-dump-times "__builtin_strlen" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "__builtin_abort" 1 "optimized" } } */
diff -Npur gcc/testsuite/gcc.dg/strlenopt-59.c gcc/testsuite/gcc.dg/strlenopt-59.c
--- gcc/testsuite/gcc.dg/strlenopt-59.c	1970-01-01 01:00:00.000000000 +0100
+++ gcc/testsuite/gcc.dg/strlenopt-59.c	2018-08-22 09:11:03.197092493 +0200
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fassume-zero-terminated-char-arrays -fdump-tree-optimized" } */
+
+typedef char B[2][3];
+
+B b;
+
+void test (void)
+{
+  if (__builtin_strlen (b[0]) > 2)
+    __builtin_abort ();
+}
+
+/* { dg-final { scan-tree-dump-not "__builtin_strlen" "optimized" } } */
+/* { dg-final { scan-tree-dump-not "__builtin_abort" "optimized" } } */
diff -Npur gcc/tree-ssa-dse.c gcc/tree-ssa-dse.c
--- gcc/tree-ssa-dse.c	2018-08-19 17:11:34.000000000 +0200
+++ gcc/tree-ssa-dse.c	2018-08-22 09:04:53.768302320 +0200
@@ -248,6 +248,12 @@ compute_trims (ao_ref *ref, sbitmap live
 	 residual handling in mem* and str* functions is usually
 	 reasonably efficient.  */
       *trim_tail = last_orig - last_live;
+      /* Don't fold away an out of bounds access, as this defeats proper
+	 warnings.  */
+      if (*trim_tail
+	  && compare_tree_int (TYPE_SIZE_UNIT (TREE_TYPE (ref->base)),
+			       last_orig) <= 0)
+	*trim_tail = 0;
     }
   else
     *trim_tail = 0;
diff -Npur gcc/tree-ssa-strlen.c gcc/tree-ssa-strlen.c
--- gcc/tree-ssa-strlen.c	2018-08-21 10:51:08.000000000 +0200
+++ gcc/tree-ssa-strlen.c	2018-08-22 09:04:53.786302066 +0200
@@ -1156,11 +1156,13 @@ maybe_set_strlen_range (tree lhs, tree s
 
   if (TREE_CODE (src) == ADDR_EXPR)
     {
+      src = TREE_OPERAND (src, 0);
+
+      if (!looks_like_a_char_array_without_typecast_p (src, false))
+	;
       /* The last array member of a struct can be bigger than its size
 	 suggests if it's treated as a poor-man's flexible array member.  */
-      src = TREE_OPERAND (src, 0);
-      bool src_is_array = TREE_CODE (TREE_TYPE (src)) == ARRAY_TYPE;
-      if (src_is_array && !array_at_struct_end_p (src))
+      else if (!array_at_struct_end_p (src))
 	{
 	  tree type = TREE_TYPE (src);
 	  if (tree size = TYPE_SIZE_UNIT (type))
@@ -1177,8 +1179,6 @@ maybe_set_strlen_range (tree lhs, tree s
 	}
       else
 	{
-	  if (TREE_CODE (src) == COMPONENT_REF && !src_is_array)
-	    src = TREE_OPERAND (src, 1);
 	  if (DECL_P (src))
 	    {
 	      /* Handle the unlikely case of strlen (&c) where c is some
@@ -3192,7 +3192,9 @@ get_min_string_length (tree rhs, bool *f
       && TREE_READONLY (rhs))
     rhs = DECL_INITIAL (rhs);
 
-  if (rhs && TREE_CODE (rhs) == STRING_CST)
+  if (rhs && TREE_CODE (rhs) == STRING_CST
+      && compare_tree_int (TYPE_SIZE_UNIT (TREE_TYPE (rhs)),
+			   TREE_STRING_LENGTH (rhs)) >= 0)
     {
       *full_string_p = true;
       return strlen (TREE_STRING_POINTER (rhs));

Index Nav: [Date Index] [Subject Index] [Author Index] [Thread Index]
Message Nav: [Date Prev] [Date Next] [Thread Prev] [Thread Next]