preprocessor/58580 - preprocessor goes OOM with warning for zero literals

In this problem report, the compiler is fed a (bogus) translation unit
in which some literals contain bytes whose value is zero.  The
preprocessor detects that and proceeds to emit diagnostics for that
king of bogus literals.  But then when the diagnostics machinery
re-reads the input file again to display the bogus literals with a
caret, it attempts to calculate the length of each of the lines it got
using fgets.  The line length calculation is done using strlen.  But
that doesn't work well when the content of the line can have several
zero bytes.  The result is that the read_line never sees the end of
the line because strlen repeatedly reports that the line ends before
the end-of-line character; so read_line thinks its buffer for reading
the line is too small; it thus increases the buffer, leading to a huge
memory consumption, pain and disaster.

The patch below introduces a new get_line function that returns the
next line of a file and return the length of that line even if the
line contains zero bytes.  That get_line function has been adapted
from the getline function from the GNU C Library because getline being
a GNU extension it is not necessarily supported on all platforms.
read_line is then modified to return the length of the line along with
the line itself, as the line can now contain zero bytes.  Callers of
read_line are adjusted consequently.

diagnostic_show_locus() is modified to consider that a line can have
characters of value zero, and so just shows a white space when
instructed to display one of these characters.

gcc/ChangeLog:

	* input.h (location_get_source_line): Take an additional line_size
	parameter.
	* input.c (get_line): New static function definition.
	(read_line): Take an additional line_length output parameter to be
	set to the size of the line.  Use the new get_line function do the
	actual line reading.
	(location_get_source_line): Take an additional output line_len
	parameter.  Update the use of read_line to pass it the line_len
	parameter.
	* diagnostic.c (adjust_line): Take an additional input parameter
	for the length of the line, rather than calculating it with
	strlen.
	(diagnostic_show_locus): Adjust the use of
	location_get_source_line and adjust_line with respect to their new
	signature.  While displaying a line now, do not stop at the first
	null byte.  Rather, display the zero byte as a space and keep
	going until we reach the size of the line.

gcc/testsuite/ChangeLog:

	* c-c++-common/cpp/warning-zero-in-literals-1.c: New test file.

git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@204453 138bc75d-0d04-0410-961f-82ee72b054a4

1 files changed, 88 insertions, 27 deletions

diff --git a/gcc/input.c b/gcc/input.c
index a141a92cac3..cb3a0a09f33 100644
--- a/gcc/input.c
+++ b/gcc/input.c
@@ -87,53 +87,114 @@ expand_location_1 (source_location loc,
   return xloc;
 }
 
-/* Reads one line from file into a static buffer.  */
-static const char *
-read_line (FILE *file)
+/* This function reads a line that might contain bytes whose value is
+   zero.  It returns the number of bytes read.  The 'end-of-line'
+   character found at the end of the line is not contained in the
+   returned buffer.  Note that this function has been adapted from
+   getline() and _IO_getdelim() GNU C library functions.  It's been
+   duplicated here because the getline() function is not necessarily
+   present on all platforms.
+
+   LINEPTR points to a buffer that is to contain the line read.
+
+   N points to the size of the the LINEPTR buffer.
+
+   FP points to the file to consider.  */
+
+static ssize_t
+get_line (char **lineptr, size_t *n, FILE *fp)
 {
-  static char *string;
-  static size_t string_len;
-  size_t pos = 0;
-  char *ptr;
+  ssize_t cur_len = 0, len;
+  char buf[16384];
+
+  if (lineptr == NULL || n == NULL)
+    return -1;
 
-  if (!string_len)
+  if (*lineptr == NULL || *n == 0)
     {
-      string_len = 200;
-      string = XNEWVEC (char, string_len);
+      *n = 120;
+      *lineptr = XNEWVEC (char, *n);
     }
 
-  while ((ptr = fgets (string + pos, string_len - pos, file)))
-    {
-      size_t len = strlen (string + pos);
+  len = fread (buf, 1, sizeof buf, fp);
+  if (ferror (fp))
+    return -1;
 
-      if (string[pos + len - 1] == '\n')
+  for (;;)
+    {
+      size_t needed;
+      char *t = (char*) memchr (buf, '\n', len);
+      if (t != NULL) len = (t - buf);
+      if (__builtin_expect (len >= SSIZE_MAX - cur_len, 0))
+	return -1;
+      needed = cur_len + len + 1;
+      if (needed > *n)
 	{
-	  string[pos + len - 1] = 0;
-	  return string;
+	  char *new_lineptr;
+	  if (needed < 2 * *n)
+	    needed = 2 * *n;
+	  new_lineptr = XRESIZEVEC (char, *lineptr, needed);
+	  *lineptr = new_lineptr;
+	  *n = needed;
 	}
-      pos += len;
-      string = XRESIZEVEC (char, string, string_len * 2);
-      string_len *= 2;
+      memcpy (*lineptr + cur_len, buf, len);
+      cur_len += len;
+      if (t != NULL)
+	break;
+      len = fread (buf, 1, sizeof buf, fp);
+      if (ferror (fp))
+	return -1;
+      if (len == 0)
+	break;
     }
-      
-  return pos ? string : NULL;
+
+  if (cur_len)
+    (*lineptr)[cur_len] = '\0';
+  return cur_len;
+}
+
+/* Reads one line from FILE into a static buffer.  If LINE_LENGTH is
+ *non-null LINE_LENGTH, will be set by this function to the length of
+ *the returned line.  Note that the returned line can contain several
+ *zero bytes.  Also note that the returned string is allocated in
+ *static storage that is going to be re-used by subsequent invocations
+ *of read_line.  */
+static const char *
+read_line (FILE *file, int *line_length)
+{
+  static char *string;
+  static size_t string_len;
+  int len;
+
+  len = get_line (&string, &string_len, file);
+  if (line_length)
+    *line_length = len;
+  return len ? string : NULL;
 }
 
 /* Return the physical source line that corresponds to xloc in a
    buffer that is statically allocated.  The newline is replaced by
-   the null character.  */
+   the null character.  Note that the line can contain several null
+   characters, so LINE_LEN, if non-null, points to the actual length
+   of the line.  */
 
 const char *
-location_get_source_line (expanded_location xloc)
+location_get_source_line (expanded_location xloc,
+			  int *line_len)
 {
-  const char *buffer;
-  int lines = 1;
+  const char *buffer = NULL, *ptr;
+  int lines = 0, len = 0;
   FILE *stream = xloc.file ? fopen (xloc.file, "r") : NULL;
   if (!stream)
     return NULL;
 
-  while ((buffer = read_line (stream)) && lines < xloc.line)
-    lines++;
+  while ((ptr = read_line (stream, &len)) && lines < xloc.line)
+    {
+      buffer = ptr;
+      lines++;
+      if (line_len)
+	*line_len = len;
+    }
 
   fclose (stream);
   return buffer;