Fix memory handling in strxfrm_l [BZ #16009]

[Modified from the original email by Siddhesh Poyarekar]

This patch solves bug #16009 by implementing an additional path in
strxfrm that does not depend on caching the weight and rule indices.

In detail the following changed:

* The old main loop was factored out of strxfrm_l into the function
do_xfrm_cached to be able to alternativly use the non-caching version
do_xfrm.

* strxfrm_l allocates a a fixed size array on the stack. If this is not
sufficiant to store the weight and rule indices, the non-caching path is
taken. As the cache size is not dependent on the input there can be no
problems with integer overflows or stack allocations greater than
__MAX_ALLOCA_CUTOFF. Note that malloc-ing is not possible because the
definition of strxfrm does not allow an oom errorhandling.

* The uncached path determines the weight and rule index for every char
and for every pass again.

* Passing all the locale data array by array resulted in very long
parameter lists, so I introduced a structure that holds them.

* Checking for zero src string has been moved a bit upwards, it is
before the locale data initialization now.

* To verify that the non-caching path works correct I added a test run
to localedata/sort-test.sh & localedata/xfrm-test.c where all strings
are patched up with spaces so that they are too large for the caching path.

1 files changed, 46 insertions, 6 deletions

diff --git a/localedata/xfrm-test.c b/localedata/xfrm-test.c
index 79494bae9b..3ab21402f2 100644
--- a/localedata/xfrm-test.c
+++ b/localedata/xfrm-test.c
@@ -23,7 +23,10 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <stdbool.h>
 
+/* Keep in sync with string/strxfrm_l.c.  */
+#define SMALL_STR_SIZE 4095
 
 struct lines
 {
@@ -37,6 +40,7 @@ int
 main (int argc, char *argv[])
 {
   int result = 0;
+  bool nocache = false;
   size_t nstrings, nstrings_max;
   struct lines *strings;
   char *line = NULL;
@@ -44,7 +48,18 @@ main (int argc, char *argv[])
   size_t n;
 
   if (argc < 2)
-    error (1, 0, "usage: %s <random seed>", argv[0]);
+    error (1, 0, "usage: %s <random seed> [-nocache]", argv[0]);
+
+  if (argc == 3)
+    {
+      if (strcmp (argv[2], "-nocache") == 0)
+	nocache = true;
+      else
+	{
+	  printf ("Unknown option %s!\n", argv[2]);
+	  exit (1);
+	}
+    }
 
   setlocale (LC_ALL, "");
 
@@ -59,9 +74,9 @@ main (int argc, char *argv[])
 
   while (1)
     {
-      char saved, *newp;
-      int needed;
-      int l;
+      char saved, *word, *newp;
+      size_t l, line_len, needed;
+
       if (getline (&line, &len, stdin) < 0)
 	break;
 
@@ -83,10 +98,35 @@ main (int argc, char *argv[])
 
       saved = line[l];
       line[l] = '\0';
-      needed = strxfrm (NULL, line, 0);
+
+      if (nocache)
+	{
+	  line_len = strlen (line);
+	  word = malloc (line_len + SMALL_STR_SIZE + 1);
+	  if (word == NULL)
+	    {
+	      printf ("malloc failed: %m\n");
+	      exit (1);
+	    }
+	  memset (word, ' ', SMALL_STR_SIZE);
+	  memcpy (word + SMALL_STR_SIZE, line, line_len);
+	  word[line_len + SMALL_STR_SIZE] = '\0';
+	}
+      else
+        word = line;
+
+      needed = strxfrm (NULL, word, 0);
       newp = malloc (needed + 1);
-      strxfrm (newp, line, needed + 1);
+      if (newp == NULL)
+	{
+	  printf ("malloc failed: %m\n");
+	  exit (1);
+	}
+      strxfrm (newp, word, needed + 1);
       strings[nstrings].xfrm = newp;
+
+      if (nocache)
+	free (word);
       line[l] = saved;
       ++nstrings;
     }