PR tree-optimization/71625 - missing strlen optimization on different array initializ...

gcc/c/ChangeLog:

	PR tree-optimization/71625
	* c-parser.c (c_parser_declaration_or_fndef): Call
	braced_list_to_string.

gcc/c-family/ChangeLog:

	PR tree-optimization/71625
	* c-common.c (braced_list_to_string): New function.
	* c-common.h (braced_list_to_string): Declare it.

gcc/cp/ChangeLog:

	PR tree-optimization/71625
	* decl.c (check_initializer):  Call braced_list_to_string.
	(eval_check_narrowing): New function.
	* gcc/cp/typeck2.c (digest_init_r): Accept strings literals
	as initilizers for all narrow character types.

gcc/testsuite/ChangeLog:

	PR tree-optimization/71625

	* g++.dg/init/string2.C: New test.
	* g++.dg/init/string3.C: New test.
	* g++.dg/init/string4.C: New test.
	* gcc.dg/init-string-3.c: New test.
	* gcc.dg/strlenopt-55.c: New test.
	* gcc.dg/strlenopt-56.c: New test.

From-SVN: r263511

diff --git a/gcc/c-family/ChangeLog b/gcc/c-family/ChangeLog
index aa7aada..3aec883 100644 (file)
--- a/gcc/c-family/ChangeLog
+++ b/gcc/c-family/ChangeLog
@@ -1,3 +1,9 @@
+2018-08-13  Martin Sebor  <msebor@redhat.com>
+
+       PR tree-optimization/71625
+       * c-common.c (braced_list_to_string): New function.
+       * c-common.h (braced_list_to_string): Declare it.
+
 2018-08-08  Nathan Sidwell  <nathan@acm.org>
 
        * c-common.c (try_to_locate_new_include_inertion_point): Use

diff --git a/gcc/c-family/c-common.c b/gcc/c-family/c-common.c
index 91e60f3..55b2e50 100644 (file)
--- a/gcc/c-family/c-common.c
+++ b/gcc/c-family/c-common.c
@@ -8509,4 +8509,96 @@ maybe_add_include_fixit (rich_location *richloc, const char *header)
   free (text);
 }
 
+/* Attempt to convert a braced array initializer list CTOR for array
+   TYPE into a STRING_CST for convenience and efficiency.  When non-null,
+   use EVAL to attempt to evalue constants (used by C++).  Return
+   the converted string on success or null on failure.  */
+
+tree
+braced_list_to_string (tree type, tree ctor, tree (*eval)(tree, tree))
+{
+  unsigned HOST_WIDE_INT nelts = CONSTRUCTOR_NELTS (ctor);
+
+  /* If the array has an explicit bound, use it to constrain the size
+     of the string.  If it doesn't, be sure to create a string that's
+     as long as implied by the index of the last zero specified via
+     a designator, as in:
+       const char a[] = { [7] = 0 };  */
+  unsigned HOST_WIDE_INT maxelts = HOST_WIDE_INT_M1U;
+  if (tree size = TYPE_SIZE_UNIT (type))
+    {
+      if (tree_fits_uhwi_p (size))
+       {
+         maxelts = tree_to_uhwi (size);
+         maxelts /= tree_to_uhwi (TYPE_SIZE_UNIT (TREE_TYPE (type)));
+
+         /* Avoid converting initializers for zero-length arrays.  */
+         if (!maxelts)
+           return NULL_TREE;
+       }
+    }
+  else if (!nelts)
+    /* Avoid handling the undefined/erroneous case of an empty
+       initializer for an arrays with unspecified bound.  */
+    return NULL_TREE;
+
+  tree eltype = TREE_TYPE (type);
+
+  auto_vec<char> str;
+  str.reserve (nelts + 1);
+
+  unsigned HOST_WIDE_INT i;
+  tree index, value;
+
+  FOR_EACH_CONSTRUCTOR_ELT (CONSTRUCTOR_ELTS (ctor), i, index, value)
+    {
+      unsigned HOST_WIDE_INT idx = index ? tree_to_uhwi (index) : i;
+
+      /* auto_vec is limited to UINT_MAX elements.  */
+      if (idx > UINT_MAX)
+       return NULL_TREE;
+
+      /* Attempt to evaluate constants.  */
+      if (eval)
+       value = eval (eltype, value);
+
+      /* Avoid non-constant initializers.  */
+     if (!tree_fits_shwi_p (value))
+       return NULL_TREE;
+
+      /* Skip over embedded nuls except the last one (initializer
+        elements are in ascending order of indices).  */
+      HOST_WIDE_INT val = tree_to_shwi (value);
+      if (!val && i + 1 < nelts)
+       continue;
+
+      /* Bail if the CTOR has a block of more than 256 embedded nuls
+        due to implicitly initialized elements.  */
+      unsigned nchars = (idx - str.length ()) + 1;
+      if (nchars > 256)
+       return NULL_TREE;
+
+      if (nchars > 1)
+       {
+         str.reserve (idx);
+         str.quick_grow_cleared (idx);
+       }
+
+      if (idx > maxelts)
+       return NULL_TREE;
+
+      str.safe_insert (idx, val);
+    }
+
+  if (!nelts)
+    /* Append a nul for the empty initializer { }.  */
+    str.safe_push (0);
+
+  /* Build a STRING_CST with the same type as the array, which
+     may be an array of unknown bound.  */
+  tree res = build_string (str.length (), str.begin ());
+  TREE_TYPE (res) = type;
+  return res;
+}
+
 #include "gt-c-family-c-common.h"

diff --git a/gcc/c-family/c-common.h b/gcc/c-family/c-common.h
index fcec95b..8a802bb 100644 (file)
--- a/gcc/c-family/c-common.h
+++ b/gcc/c-family/c-common.h
@@ -1331,6 +1331,7 @@ extern void maybe_add_include_fixit (rich_location *, const char *);
 extern void maybe_suggest_missing_token_insertion (rich_location *richloc,
                                                   enum cpp_ttype token_type,
                                                   location_t prev_token_loc);
+extern tree braced_list_to_string (tree, tree, tree (*)(tree, tree) = NULL);
 
 #if CHECKING_P
 namespace selftest {

diff --git a/gcc/c/ChangeLog b/gcc/c/ChangeLog
index 40e56f3..be2ffbd 100644 (file)
--- a/gcc/c/ChangeLog
+++ b/gcc/c/ChangeLog
@@ -1,3 +1,9 @@
+2018-08-13  Martin Sebor  <msebor@redhat.com>
+
+       PR tree-optimization/71625
+       * c-parser.c (c_parser_declaration_or_fndef): Call
+       braced_list_to_string.
+
 2018-08-03  Bogdan Harjoc  <harjoc@gmail.com>
 
        PR c/86690

diff --git a/gcc/c/c-parser.c b/gcc/c/c-parser.c
index 7a92628..5ad4f57 100644 (file)
--- a/gcc/c/c-parser.c
+++ b/gcc/c/c-parser.c
@@ -2126,6 +2126,15 @@ c_parser_declaration_or_fndef (c_parser *parser, bool fndef_ok,
              if (d != error_mark_node)
                {
                  maybe_warn_string_init (init_loc, TREE_TYPE (d), init);
+
+                 /* Try to convert a string CONSTRUCTOR into a STRING_CST.  */
+                 tree valtype = TREE_TYPE (init.value);
+                 if (TREE_CODE (init.value) == CONSTRUCTOR
+                     && TREE_CODE (valtype) == ARRAY_TYPE
+                     && TYPE_STRING_FLAG (TREE_TYPE (valtype)))
+                   if (tree str = braced_list_to_string (valtype, init.value))
+                     init.value = str;
+
                  finish_decl (d, init_loc, init.value,
                               init.original_type, asm_name);
                }

diff --git a/gcc/cp/ChangeLog b/gcc/cp/ChangeLog
index da6703b..e4984bd 100644 (file)
--- a/gcc/cp/ChangeLog
+++ b/gcc/cp/ChangeLog
@@ -1,3 +1,11 @@
+2018-08-13  Martin Sebor  <msebor@redhat.com>
+
+       PR tree-optimization/71625
+       * decl.c (check_initializer):  Call braced_list_to_string.
+       (eval_check_narrowing): New function.
+       * gcc/cp/typeck2.c (digest_init_r): Accept strings literals
+       as initilizers for all narrow character types.
+
 2018-08-13  Marek Polacek  <polacek@redhat.com>
 
        P0806R2 - Deprecate implicit capture of this via [=]

diff --git a/gcc/cp/decl.c b/gcc/cp/decl.c
index b021ff6..97f1cfb 100644 (file)
--- a/gcc/cp/decl.c
+++ b/gcc/cp/decl.c
@@ -6282,6 +6282,30 @@ build_aggr_init_full_exprs (tree decl, tree init, int flags)
   return build_aggr_init (decl, init, flags, tf_warning_or_error);
 }
 
+/* Attempt to determine the constant VALUE of integral type and convert
+   it to TYPE, issuing narrowing warnings/errors as necessary.  Return
+   the constant result or null on failure.  Callback for
+   braced_list_to_string.  */
+
+static tree
+eval_check_narrowing (tree type, tree value)
+{
+  if (tree valtype = TREE_TYPE (value))
+    {
+      if (TREE_CODE (valtype) != INTEGER_TYPE)
+       return NULL_TREE;
+    }
+  else
+    return NULL_TREE;
+
+  value = scalar_constant_value (value);
+  if (!value)
+    return NULL_TREE;
+
+  check_narrowing (type, value, tf_warning_or_error);
+  return value;
+}
+
 /* Verify INIT (the initializer for DECL), and record the
    initialization in DECL_INITIAL, if appropriate.  CLEANUP is as for
    grok_reference_init.
@@ -6397,7 +6421,17 @@ check_initializer (tree decl, tree init, int flags, vec<tree, va_gc> **cleanups)
            }
          else
            {
-             init = reshape_init (type, init, tf_warning_or_error);
+             /* Try to convert a string CONSTRUCTOR into a STRING_CST.  */
+             tree valtype = TREE_TYPE (decl);
+             if (TREE_CODE (valtype) == ARRAY_TYPE
+                 && TYPE_STRING_FLAG (TREE_TYPE (valtype))
+                 && BRACE_ENCLOSED_INITIALIZER_P (init))
+               if (tree str = braced_list_to_string (valtype, init,
+                                                     eval_check_narrowing))
+                 init = str;
+
+             if (TREE_CODE (init) != STRING_CST)
+               init = reshape_init (type, init, tf_warning_or_error);
              flags |= LOOKUP_NO_NARROWING;
            }
        }

diff --git a/gcc/cp/typeck2.c b/gcc/cp/typeck2.c
index 7763d53..72515d9 100644 (file)
--- a/gcc/cp/typeck2.c
+++ b/gcc/cp/typeck2.c
@@ -1056,7 +1056,9 @@ digest_init_r (tree type, tree init, int nested, int flags,
 
          if (TYPE_PRECISION (typ1) == BITS_PER_UNIT)
            {
-             if (char_type != char_type_node)
+             if (char_type != char_type_node
+                 && char_type != signed_char_type_node
+                 && char_type != unsigned_char_type_node)
                {
                  if (complain & tf_error)
                    error_at (loc, "char-array initialized from wide string");

diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index d7ed84e..ad2610b 100644 (file)
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,14 @@
+2018-08-13  Martin Sebor  <msebor@redhat.com>
+
+       PR tree-optimization/71625
+       * c-c++-common/attr-nonstring-3.c: Temporarily xfail a test case.
+       * g++.dg/init/string2.C: New test.
+       * g++.dg/init/string3.C: New test.
+       * g++.dg/init/string4.C: New test.
+       * gcc.dg/init-string-3.c: New test.
+       * gcc.dg/strlenopt-55.c: New test.
+       * gcc.dg/strlenopt-56.c: New test.
+
 2018-08-13  Marek Polacek  <polacek@redhat.com>
 
        P0806R2 - Deprecate implicit capture of this via [=]

diff --git a/gcc/testsuite/c-c++-common/attr-nonstring-3.c b/gcc/testsuite/c-c++-common/attr-nonstring-3.c
index b1eb8b6..a2aaf7b 100644 (file)
--- a/gcc/testsuite/c-c++-common/attr-nonstring-3.c
+++ b/gcc/testsuite/c-c++-common/attr-nonstring-3.c
@@ -406,7 +406,7 @@ void test_strlen (struct MemArrays *p, char *s NONSTRING, size_t n)
   {
     char a[] __attribute__ ((nonstring)) = { 1, 2, 3 };
 
-    T (strlen (a));             /* { dg-warning "argument 1 declared attribute .nonstring." } */
+    T (strlen (a));             /* { dg-warning "argument 1 declared attribute .nonstring." "pr86688" { xfail *-*-* } } */
   }
 
   {

diff --git a/gcc/testsuite/g++.dg/init/string2.C b/gcc/testsuite/g++.dg/init/string2.C
new file mode 100644 (file)
index 0000000..5da13bd
--- /dev/null
+++ b/gcc/testsuite/g++.dg/init/string2.C
@@ -0,0 +1,104 @@
+// PR tree-optimization/71625 - missing strlen optimization on different
+// array initialization style
+//
+// Verify that strlen() calls with constant character array arguments
+// initialized with string constants are folded.  (This is a small
+// subset of pr71625).
+// { dg-do compile }
+// { dg-options "-O0 -Wno-error=narrowing -fdump-tree-gimple" }
+
+#define A(expr) do { typedef char A[-1 + 2 * !!(expr)]; } while (0)
+
+/* This is undefined but accepted without -Wpedantic.  Verify that
+   the size is zero.  */
+const char ax[] = { };
+
+void size0 ()
+{
+  A (sizeof ax == 0);
+}
+
+const char a0[] = { 'a', 'b', 'c', '\0' };
+
+int len0 ()
+{
+  return __builtin_strlen (a0);
+}
+
+// Verify that narrowing warnings are preserved.
+const signed char
+sa0[] = { 'a', 'b', 255, '\0' };    // { dg-warning "\\\[\(-Wnarrowing|-Woverflow\)" "" { target { ! c++98_only } } }
+
+int lens0 ()
+{
+  return __builtin_strlen ((const char*)sa0);
+}
+
+const unsigned char
+ua0[] = { 'a', 'b', -1, '\0' };     // { dg-warning "\\\[\(-Wnarrowing|-Woverflow\)" "" { target { ! c++98_only } } }
+
+int lenu0 ()
+{
+  return __builtin_strlen ((const char*)ua0);
+}
+
+const char c = 0;
+const char a1[] = { 'a', 'b', 'c', c };
+
+int len1 ()
+{
+  return __builtin_strlen (a1);
+}
+
+template <class T>
+int tmplen ()
+{
+  static const T
+    a[] = { 1, 2, 333, 0 };         // { dg-warning "\\\[\(-Wnarrowing|-Woverflow\)" "" { target { ! c++98_only } } }
+  return __builtin_strlen (a);
+}
+
+template int tmplen<char>();
+
+const wchar_t ws4[] = { 1, 2, 3, 4 };
+const wchar_t ws7[] = { 1, 2, 3, 4, 0, 0, 0 };
+const wchar_t ws9[9] = { 1, 2, 3, 4, 0 };
+
+void wsize ()
+{
+  A (sizeof ws4 == 4 * sizeof *ws4);
+  A (ws4[0] == 1 && ws4[1] == 2 && ws4[2] == 3 && ws4[3] == 4);
+
+  A (sizeof ws7 == 7 * sizeof *ws7);
+  A (ws7[0] == 1 && ws7[1] == 2 && ws7[2] == 3 && ws7[4] == 4
+     && !ws7[5] && !ws7[6]);
+
+  A (sizeof ws9 == 9 * sizeof *ws9);
+  A (ws9[0] == 1 && ws9[1] == 2 && ws9[2] == 3 && ws9[4] == 4
+     && !ws9[5] && !ws9[6] && !ws9[7] && !ws9[8]);
+}
+
+#if 0
+
+// The following aren't handled.
+
+const char &cref = c;
+const char a2[] = { 'a', 'b', 'c', cref };
+
+int len2 ()
+{
+  return __builtin_strlen (a2);
+}
+
+
+const char* const cptr = &cref;
+const char a3[] = { 'a', 'b', 'c', *cptr };
+
+int len3 ()
+{
+  return __builtin_strlen (a3);
+}
+
+#endif
+
+// { dg-final { scan-tree-dump-times "strlen" 0 "gimple" } }

diff --git a/gcc/testsuite/g++.dg/init/string3.C b/gcc/testsuite/g++.dg/init/string3.C
new file mode 100644 (file)
index 0000000..8212e81
--- /dev/null
+++ b/gcc/testsuite/g++.dg/init/string3.C
@@ -0,0 +1,35 @@
+// PR tree-optimization/71625 - missing strlen optimization on different
+// array initialization style
+//
+// Verify that strlen() call with a constant character array argument
+// initialized with non-constant elements isn't folded.
+//
+// { dg-do compile }
+// { dg-options "-O2 -fdump-tree-optimized" }
+
+
+extern const char c;
+const char a0[] = { 'a', 'b', 'c', c };
+
+int len0 ()
+{
+  return __builtin_strlen (a0);
+}
+
+const char &ref = c;
+const char a1[] = { 'a', 'b', 'c', ref };
+
+int len1 ()
+{
+  return __builtin_strlen (a1);
+}
+
+const char* const ptr = &c;
+const char a2[] = { 'a', 'b', 'c', *ptr };
+
+int len2 ()
+{
+  return __builtin_strlen (a2);
+}
+
+// { dg-final { scan-tree-dump-times "strlen" 3 "optimized" } }

diff --git a/gcc/testsuite/g++.dg/init/string4.C b/gcc/testsuite/g++.dg/init/string4.C
new file mode 100644 (file)
index 0000000..5df4176
--- /dev/null
+++ b/gcc/testsuite/g++.dg/init/string4.C
@@ -0,0 +1,60 @@
+// PR tree-optimization/71625 - missing strlen optimization on different
+// array initialization style
+
+// Verify that zero-length array initialization results in the expected
+// array sizes and in the expected diagnostics.  See init-string-3.c
+// for the corresponding C test.
+
+// { dg-do compile }
+// { dg-options "-Wall -Wno-unused-local-typedefs -fpermissive" }
+
+#define A(expr) typedef char A[-1 + 2 * !!(expr)];
+
+const char a[] = { };
+
+A (sizeof a == 0);
+
+
+const char b[0] = { };
+
+A (sizeof b == 0);
+
+// Also verify that the error is "too many initializers for
+// 'const char [0]'" and not "initializer-string is too long."
+const char c[0] = { 1 };      // { dg-error "too many initializers for .const char \\\[0]" }
+
+A (sizeof c == 0);
+
+
+void test_auto_empty (void)
+{
+  const char a[] = { };
+
+  A (sizeof a == 0);
+}
+
+void test_auto_zero_length (void)
+{
+  const char a[0] = { };
+
+  A (sizeof a == 0);
+
+  const char b[0] = { 0 };    // { dg-error "too many initializers" }
+
+  A (sizeof b == 0);
+
+  const char c[0] = "";       // { dg-warning "too long" }
+
+  A (sizeof c == 0);
+}
+
+
+void test_compound_zero_length (void)
+{
+  A (sizeof (const char[]){ } == 0);
+  A (sizeof (const char[0]){ } == 0);
+  A (sizeof (const char[0]){ 0 } == 0);    // { dg-error "too many" }
+  A (sizeof (const char[0]){ 1 } == 0);    // { dg-error "too many" }
+  A (sizeof (const char[0]){ "" } == 0);   // { dg-warning "too long" }
+  A (sizeof (const char[0]){ "1" } == 0);  // { dg-warning "too long" }
+}

diff --git a/gcc/testsuite/gcc.dg/init-string-3.c b/gcc/testsuite/gcc.dg/init-string-3.c
new file mode 100644 (file)
index 0000000..e955f2e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/init-string-3.c
@@ -0,0 +1,58 @@
+/* PR tree-optimization/71625 - missing strlen optimization on different
+   array initialization style
+
+   Verify that zero-length array initialization results in the expected
+   array sizes.
+
+   { dg-do compile }
+   { dg-options "-Wall -Wno-unused-local-typedefs" }  */
+
+#define A(expr) typedef char A[-1 + 2 * !!(expr)];
+
+const char a[] = { };
+
+A (sizeof a == 0);
+
+
+const char b[0] = { };
+
+A (sizeof b == 0);
+
+
+const char c[0] = { 1 };    /* { dg-warning "excess elements" } */
+
+A (sizeof c == 0);
+
+
+void test_auto_empty (void)
+{
+  const char a[] = { };
+
+  A (sizeof a == 0);
+}
+
+void test_auto_zero_length (void)
+{
+  const char a[0] = { };
+
+  A (sizeof a == 0);
+
+  const char b[0] = { 0 };    /* { dg-warning "excess elements" } */
+
+  A (sizeof b == 0);
+
+  const char c[0] = "";
+
+  A (sizeof c == 0);
+}
+
+
+void test_compound_zero_length (void)
+{
+  A (sizeof (const char[]){ } == 0);
+  A (sizeof (const char[0]){ } == 0);
+  A (sizeof (const char[0]){ 0 } == 0);   /* { dg-warning "excess elements" } */
+  A (sizeof (const char[0]){ 1 } == 0);   /* { dg-warning "excess elements" } */
+  A (sizeof (const char[0]){ "" } == 0);
+  A (sizeof (const char[0]){ "1" } == 0);  /* { dg-warning "too long" } */
+}

diff --git a/gcc/testsuite/gcc.dg/strlenopt-55.c b/gcc/testsuite/gcc.dg/strlenopt-55.c
new file mode 100644 (file)
index 0000000..d5a0295
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/strlenopt-55.c
@@ -0,0 +1,230 @@
+/* PR tree-optimization/71625 - missing strlen optimization on different
+   array initialization style
+
+   Verify that strlen() of braced initialized array is folded
+   { dg-do compile }
+   { dg-options "-O1 -Wall -fdump-tree-gimple -fdump-tree-optimized" } */
+
+#include "strlenopt.h"
+
+#define S                                                              \
+  "\x01\x02\x03\x04\x05\x06\x07\x08\x09\x0a\x0b\x0c\x0d\x0e\x0f"       \
+  "\x10\x11\x12\x13\x14\x15\x16\x17\x18\x19\x1a\x1b\x1c\x1d\x1e\x1f"   \
+  "\x20\x21\x22\x23\x24\x25\x26\x27\x28\x29\x2a\x2b\x2c\x2d\x2e\x2f"   \
+  "\x30\x31\x32\x33\x34\x35\x36\x37\x38\x39\x3a\x3b\x3c\x3d\x3e\x3f"   \
+  "\x40\x41\x42\x43\x44\x45\x46\x47\x48\x49\x4a\x4b\x4c\x4d\x4e\x4f"   \
+  "\x50\x51\x52\x53\x54\x55\x56\x57\x58\x59\x5a\x5b\x5c\x5d\x5e\x5f"   \
+  "\x60\x61\x62\x63\x64\x65\x66\x67\x68\x69\x6a\x6b\x6c\x6d\x6e\x6f"   \
+  "\x70\x71\x72\x73\x74\x75\x76\x77\x78\x79\x7a\x7b\x7c\x7d\x7e\x7f"   \
+  "\x80\x81\x82\x83\x84\x85\x86\x87\x88\x89\x8a\x8b\x8c\x8d\x8e\x8f"   \
+  "\x90\x91\x92\x93\x94\x95\x96\x97\x98\x99\x9a\x9b\x9c\x9d\x9e\x9f"   \
+  "\xa0\xa1\xa2\xa3\xa4\xa5\xa6\xa7\xa8\xa9\xaa\xab\xac\xad\xae\xaf"   \
+  "\xb0\xb1\xb2\xb3\xb4\xb5\xb6\xb7\xb8\xb9\xba\xbb\xbc\xbd\xbe\xbf"   \
+  "\xc0\xc1\xc2\xc3\xc4\xc5\xc6\xc7\xc8\xc9\xca\xcb\xcc\xcd\xce\xcf"   \
+  "\xd0\xd1\xd2\xd3\xd4\xd5\xd6\xd7\xd8\xd9\xda\xdb\xdc\xdd\xde\xdf"   \
+  "\xe0\xe1\xe2\xe3\xe4\xe5\xe6\xe7\xe8\xe9\xea\xeb\xec\xed\xee\xef"   \
+  "\xf0\xf1\xf2\xf3\xf4\xf5\xf6\xf7\xf8\xf9\xfa\xfb\xfc\xfd\xfe\xff"
+
+/* Arrays of char, signed char, and unsigned char to verify that
+   the length and contents of all are the same as that of the string
+   literal above.  */
+
+const char c256[] = {
+  S[0], S[1], S[2], S[3], S[4], S[5], S[6], S[7], S[8], S[9], S[10],
+  S[11], S[12], S[13], S[14], S[15], S[16], S[17], S[18], S[19], S[20],
+  S[21], S[22], S[23], S[24], S[25], S[26], S[27], S[28], S[29], S[30],
+  S[31], S[32], S[33], S[34], S[35], S[36], S[37], S[38], S[39], S[40],
+  S[41], S[42], S[43], S[44], S[45], S[46], S[47], S[48], S[49], S[50],
+  S[51], S[52], S[53], S[54], S[55], S[56], S[57], S[58], S[59], S[60],
+  S[61], S[62], S[63], S[64], S[65], S[66], S[67], S[68], S[69], S[70],
+  S[71], S[72], S[73], S[74], S[75], S[76], S[77], S[78], S[79], S[80],
+  S[81], S[82], S[83], S[84], S[85], S[86], S[87], S[88], S[89], S[90],
+  S[91], S[92], S[93], S[94], S[95], S[96], S[97], S[98], S[99], S[100],
+  S[101], S[102], S[103], S[104], S[105], S[106], S[107], S[108], S[109],
+  S[110], S[111], S[112], S[113], S[114], S[115], S[116], S[117], S[118],
+  S[119], S[120], S[121], S[122], S[123], S[124], S[125], S[126], S[127],
+  S[128], S[129], S[130], S[131], S[132], S[133], S[134], S[135], S[136],
+  S[137], S[138], S[139], S[140], S[141], S[142], S[143], S[144], S[145],
+  S[146], S[147], S[148], S[149], S[150], S[151], S[152], S[153], S[154],
+  S[155], S[156], S[157], S[158], S[159], S[160], S[161], S[162], S[163],
+  S[164], S[165], S[166], S[167], S[168], S[169], S[170], S[171], S[172],
+  S[173], S[174], S[175], S[176], S[177], S[178], S[179], S[180], S[181],
+  S[182], S[183], S[184], S[185], S[186], S[187], S[188], S[189], S[190],
+  S[191], S[192], S[193], S[194], S[195], S[196], S[197], S[198], S[199],
+  S[200], S[201], S[202], S[203], S[204], S[205], S[206], S[207], S[208],
+  S[209], S[210], S[211], S[212], S[213], S[214], S[215], S[216], S[217],
+  S[218], S[219], S[220], S[221], S[222], S[223], S[224], S[225], S[226],
+  S[227], S[228], S[229], S[230], S[231], S[232], S[233], S[234], S[235],
+  S[236], S[237], S[238], S[239], S[240], S[241], S[242], S[243], S[244],
+  S[245], S[246], S[247], S[248], S[249], S[250], S[251], S[252], S[253],
+  S[254], S[255] /* = NUL */
+};
+
+const signed char sc256[] = {
+  S[0], S[1], S[2], S[3], S[4], S[5], S[6], S[7], S[8], S[9], S[10],
+  S[11], S[12], S[13], S[14], S[15], S[16], S[17], S[18], S[19], S[20],
+  S[21], S[22], S[23], S[24], S[25], S[26], S[27], S[28], S[29], S[30],
+  S[31], S[32], S[33], S[34], S[35], S[36], S[37], S[38], S[39], S[40],
+  S[41], S[42], S[43], S[44], S[45], S[46], S[47], S[48], S[49], S[50],
+  S[51], S[52], S[53], S[54], S[55], S[56], S[57], S[58], S[59], S[60],
+  S[61], S[62], S[63], S[64], S[65], S[66], S[67], S[68], S[69], S[70],
+  S[71], S[72], S[73], S[74], S[75], S[76], S[77], S[78], S[79], S[80],
+  S[81], S[82], S[83], S[84], S[85], S[86], S[87], S[88], S[89], S[90],
+  S[91], S[92], S[93], S[94], S[95], S[96], S[97], S[98], S[99], S[100],
+  S[101], S[102], S[103], S[104], S[105], S[106], S[107], S[108], S[109],
+  S[110], S[111], S[112], S[113], S[114], S[115], S[116], S[117], S[118],
+  S[119], S[120], S[121], S[122], S[123], S[124], S[125], S[126], S[127],
+  S[128], S[129], S[130], S[131], S[132], S[133], S[134], S[135], S[136],
+  S[137], S[138], S[139], S[140], S[141], S[142], S[143], S[144], S[145],
+  S[146], S[147], S[148], S[149], S[150], S[151], S[152], S[153], S[154],
+  S[155], S[156], S[157], S[158], S[159], S[160], S[161], S[162], S[163],
+  S[164], S[165], S[166], S[167], S[168], S[169], S[170], S[171], S[172],
+  S[173], S[174], S[175], S[176], S[177], S[178], S[179], S[180], S[181],
+  S[182], S[183], S[184], S[185], S[186], S[187], S[188], S[189], S[190],
+  S[191], S[192], S[193], S[194], S[195], S[196], S[197], S[198], S[199],
+  S[200], S[201], S[202], S[203], S[204], S[205], S[206], S[207], S[208],
+  S[209], S[210], S[211], S[212], S[213], S[214], S[215], S[216], S[217],
+  S[218], S[219], S[220], S[221], S[222], S[223], S[224], S[225], S[226],
+  S[227], S[228], S[229], S[230], S[231], S[232], S[233], S[234], S[235],
+  S[236], S[237], S[238], S[239], S[240], S[241], S[242], S[243], S[244],
+  S[245], S[246], S[247], S[248], S[249], S[250], S[251], S[252], S[253],
+  S[254], S[255] /* = NUL */
+};
+
+const unsigned char uc256[] = {
+  S[0], S[1], S[2], S[3], S[4], S[5], S[6], S[7], S[8], S[9], S[10],
+  S[11], S[12], S[13], S[14], S[15], S[16], S[17], S[18], S[19], S[20],
+  S[21], S[22], S[23], S[24], S[25], S[26], S[27], S[28], S[29], S[30],
+  S[31], S[32], S[33], S[34], S[35], S[36], S[37], S[38], S[39], S[40],
+  S[41], S[42], S[43], S[44], S[45], S[46], S[47], S[48], S[49], S[50],
+  S[51], S[52], S[53], S[54], S[55], S[56], S[57], S[58], S[59], S[60],
+  S[61], S[62], S[63], S[64], S[65], S[66], S[67], S[68], S[69], S[70],
+  S[71], S[72], S[73], S[74], S[75], S[76], S[77], S[78], S[79], S[80],
+  S[81], S[82], S[83], S[84], S[85], S[86], S[87], S[88], S[89], S[90],
+  S[91], S[92], S[93], S[94], S[95], S[96], S[97], S[98], S[99], S[100],
+  S[101], S[102], S[103], S[104], S[105], S[106], S[107], S[108], S[109],
+  S[110], S[111], S[112], S[113], S[114], S[115], S[116], S[117], S[118],
+  S[119], S[120], S[121], S[122], S[123], S[124], S[125], S[126], S[127],
+  S[128], S[129], S[130], S[131], S[132], S[133], S[134], S[135], S[136],
+  S[137], S[138], S[139], S[140], S[141], S[142], S[143], S[144], S[145],
+  S[146], S[147], S[148], S[149], S[150], S[151], S[152], S[153], S[154],
+  S[155], S[156], S[157], S[158], S[159], S[160], S[161], S[162], S[163],
+  S[164], S[165], S[166], S[167], S[168], S[169], S[170], S[171], S[172],
+  S[173], S[174], S[175], S[176], S[177], S[178], S[179], S[180], S[181],
+  S[182], S[183], S[184], S[185], S[186], S[187], S[188], S[189], S[190],
+  S[191], S[192], S[193], S[194], S[195], S[196], S[197], S[198], S[199],
+  S[200], S[201], S[202], S[203], S[204], S[205], S[206], S[207], S[208],
+  S[209], S[210], S[211], S[212], S[213], S[214], S[215], S[216], S[217],
+  S[218], S[219], S[220], S[221], S[222], S[223], S[224], S[225], S[226],
+  S[227], S[228], S[229], S[230], S[231], S[232], S[233], S[234], S[235],
+  S[236], S[237], S[238], S[239], S[240], S[241], S[242], S[243], S[244],
+  S[245], S[246], S[247], S[248], S[249], S[250], S[251], S[252], S[253],
+  S[254], S[255] /* = NUL */
+};
+
+const __CHAR16_TYPE__ c16_4[] = {
+  1, 0x7fff, 0x8000, 0xffff,
+  0x10000   /* { dg-warning "\\\[-Woverflow]" } */
+};
+
+const char a2_implicit[2] = { };
+const char a3_implicit[3] = { };
+
+const char a3_nul[3] = { 0 };
+const char a5_nul1[3] = { [1] = 0 };
+const char a7_nul2[3] = { [2] = 0 };
+
+const char ax_2_nul[] = { '1', '2', '\0' };
+const char ax_3_nul[] = { '1', '2', '3', '\0' };
+
+const char ax_3_des_nul[] = { [3] = 0, [2] = '3', [1] = '2', [0] = '1' };
+
+const char ax_3[] = { '1', '2', '3' };
+const char a3_3[3] = { '1', '2', '3' };
+
+const char ax_100_3[] = { '1', '2', '3', [100] = '\0' };
+
+#define CONCAT(x, y) x ## y
+#define CAT(x, y) CONCAT (x, y)
+#define FAILNAME(name) CAT (call_ ## name ##_on_line_, __LINE__)
+
+#define FAIL(name) do {                                \
+    extern void FAILNAME (name) (void);                \
+    FAILNAME (name)();                         \
+  } while (0)
+
+/* Macro to emit a call to funcation named
+   call_in_true_branch_not_eliminated_on_line_NNN()
+   for each call that's expected to be eliminated.  The dg-final
+   scan-tree-dump-time directive at the bottom of the test verifies
+   that no such call appears in output.  */
+#define ELIM(expr)                                                     \
+  if (!(expr)) FAIL (in_true_branch_not_eliminated); else (void)0
+
+#define T(s, n) ELIM (strlen (s) == n)
+
+void test_nulstring (void)
+{
+  T (a2_implicit, 0);
+  T (a3_implicit, 0);
+
+  T (a3_nul, 0);
+  T (a5_nul1, 0);
+  T (a7_nul2, 0);
+
+  T (ax_2_nul, 2);
+  T (ax_3_nul, 3);
+  T (ax_3_des_nul, 3);
+
+  T (ax_100_3, 3);
+  T (ax_100_3 + 4, 0);
+  ELIM (101 == sizeof ax_100_3);
+  ELIM ('\0' == ax_100_3[100]);
+
+  /* Verify that all three character arrays have the same length
+     as the string literal they are initialized with.  */
+  T (S, 255);
+  T (c256, 255);
+  T ((const char*)sc256, 255);
+  T ((const char*)uc256, 255);
+
+  /* Verify that all three character arrays have the same contents
+     as the string literal they are initialized with.  */
+  ELIM (0 == memcmp (c256, S, sizeof c256));
+  ELIM (0 == memcmp (c256, (const char*)sc256, sizeof c256));
+  ELIM (0 == memcmp (c256, (const char*)uc256, sizeof c256));
+
+  ELIM (0 == strcmp (c256, (const char*)sc256));
+  ELIM (0 == strcmp (c256, (const char*)uc256));
+
+  /* Verify that the char16_t array has the expected contents.  */
+  ELIM (c16_4[0] == 1 && c16_4[1] == 0x7fff
+       && c16_4[2] == 0x8000 && c16_4[3] == 0xffff
+       && c16_4[4] == 0);
+}
+
+/* Verify that excessively large initializers don't run out of
+   memory.  Also verify that the they have the expected size and
+   contents.  */
+
+#define MAX (__PTRDIFF_MAX__ - 1)
+
+const char large_string[] = { 'a', [1234] = 'b', [MAX] = '\0' };
+
+const void test_large_string_size (void)
+{
+  ELIM (sizeof large_string == MAX + 1);
+
+  /* The following expressions are not folded without optimization.  */
+  ELIM ('a'  == large_string[0]);
+  ELIM ('\0' == large_string[1233]);
+  ELIM ('b'  == large_string[1234]);
+  ELIM ('\0' == large_string[1235]);
+  ELIM ('\0' == large_string[MAX - 1]);
+}
+
+
+/* { dg-final { scan-tree-dump-times "strlen" 0 "gimple" } }
+   { dg-final { scan-tree-dump-times "memcmp" 0 "gimple" } }
+   { dg-final { scan-tree-dump-times "strcmp" 0 "gimple" } }
+   { dg-final { scan-tree-dump-times "call_in_true_branch_not_eliminated" 0 "optimized" } } */

diff --git a/gcc/testsuite/gcc.dg/strlenopt-56.c b/gcc/testsuite/gcc.dg/strlenopt-56.c
new file mode 100644 (file)
index 0000000..39a532b
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/strlenopt-56.c
@@ -0,0 +1,50 @@
+/* PR tree-optimization/71625 - conversion of braced initializers to strings
+   Verify that array elements have the expected values regardless of sign
+   and non-ASCII execution character set.
+   { dg-do compile }
+   { dg-require-iconv "IBM1047" }
+   { dg-options "-O -Wall -fexec-charset=IBM1047 -fdump-tree-gimple -fdump-tree-optimized" } */
+
+#include "strlenopt.h"
+
+const char a[] = { 'a', 129, 0 };
+const signed char b[] = { 'b', 130, 0 };
+const unsigned char c[] = { 'c', 131, 0 };
+
+const char s[] = "a\201";
+const signed char ss[] = "b\202";
+const unsigned char us[] = "c\203";
+
+
+#define A(expr)   ((expr) ? (void)0 : __builtin_abort ())
+
+void test_values (void)
+{
+  A (a[0] == a[1]);
+  A (a[1] == 'a');
+
+  A (b[0] == b[1]);
+  A (b[1] == (signed char)'b');
+
+  A (c[0] == c[1]);
+  A (c[1] == (unsigned char)'c');
+}
+
+void test_lengths (void)
+{
+  A (2 == strlen (a));
+  A (2 == strlen ((const char*)b));
+  A (2 == strlen ((const char*)c));
+}
+
+void test_contents (void)
+{
+  A (0 == strcmp (a, s));
+  A (0 == strcmp ((const char*)b, (const char*)ss));
+  A (0 == strcmp ((const char*)c, (const char*)us));
+}
+
+
+/* { dg-final { scan-tree-dump-times "strlen" 0 "gimple" } }
+   { dg-final { scan-tree-dump-times "strcmp" 0 "gimple" } }
+   { dg-final { scan-tree-dump-times "abort" 0 "optimized" } } */