about summary refs log tree commit diff
path: root/wcsmbs/wcrtomb.c
diff options
context:
space:
mode:
authorSiddhesh Poyarekar <siddhesh@sourceware.org>2022-05-13 19:10:15 +0530
committerSiddhesh Poyarekar <siddhesh@sourceware.org>2022-05-13 19:15:46 +0530
commit9bcd12d223a8990254b65e2dada54faa5d2742f3 (patch)
tree788a844ec9f923430664fc8aef7c565b8b3c001b /wcsmbs/wcrtomb.c
parent8162147872491bb5b48e91543b19c49a29ae6b6d (diff)
downloadglibc-9bcd12d223a8990254b65e2dada54faa5d2742f3.tar.gz
glibc-9bcd12d223a8990254b65e2dada54faa5d2742f3.tar.xz
glibc-9bcd12d223a8990254b65e2dada54faa5d2742f3.zip
wcrtomb: Make behavior POSIX compliant
The GNU implementation of wcrtomb assumes that there are at least
MB_CUR_MAX bytes available in the destination buffer passed to wcrtomb
as the first argument.  This is not compatible with the POSIX
definition, which only requires enough space for the input wide
character.

This does not break much in practice because when users supply buffers
smaller than MB_CUR_MAX (e.g. in ncurses), they compute and dynamically
allocate the buffer, which results in enough spare space (thanks to
usable_size in malloc and padding in alloca) that no actual buffer
overflow occurs.  However when the code is built with _FORTIFY_SOURCE,
it runs into the hard check against MB_CUR_MAX in __wcrtomb_chk and
hence fails.  It wasn't evident until now since dynamic allocations
would result in wcrtomb not being fortified but since _FORTIFY_SOURCE=3,
that limitation is gone, resulting in such code failing.

To fix this problem, introduce an internal buffer that is MB_LEN_MAX
long and use that to perform the conversion and then copy the resultant
bytes into the destination buffer.  Also move the fortification check
into the main implementation, which checks the result after conversion
and aborts if the resultant byte count is greater than the destination
buffer size.

One complication is that applications that assume the MB_CUR_MAX
limitation to be gone may not be able to run safely on older glibcs if
they use static destination buffers smaller than MB_CUR_MAX; dynamic
allocations will always have enough spare space that no actual overruns
will occur.  One alternative to fixing this is to bump symbol version to
prevent them from running on older glibcs but that seems too strict a
constraint.  Instead, since these users will only have made this
decision on reading the manual, I have put a note in the manual warning
them about the pitfalls of having static buffers smaller than
MB_CUR_MAX and running them on older glibc.

Benchmarking:

The wcrtomb microbenchmark shows significant increases in maximum
execution time for all locales, ranging from 10x for ar_SA.UTF-8 to
1.5x-2x for nearly everything else.  The mean execution time however saw
practically no impact, with some results even being quicker, indicating
that cache locality has a much bigger role in the overhead.

Given that the additional copy uses a temporary buffer inside wcrtomb,
it's likely that a hot path will end up putting that buffer (which is
responsible for the additional overhead) in a similar place on stack,
giving the necessary cache locality to negate the overhead.  However in
situations where wcrtomb ends up getting called at wildly different
spots on the call stack (or is on different call stacks, e.g. with
threads or different execution contexts) and is still a hotspot, the
performance lag will be visible.

Signed-off-by: Siddhesh Poyarekar <siddhesh@sourceware.org>
Diffstat (limited to 'wcsmbs/wcrtomb.c')
-rw-r--r--wcsmbs/wcrtomb.c31
1 files changed, 23 insertions, 8 deletions
diff --git a/wcsmbs/wcrtomb.c b/wcsmbs/wcrtomb.c
index e17438989f..c0cce3792f 100644
--- a/wcsmbs/wcrtomb.c
+++ b/wcsmbs/wcrtomb.c
@@ -1,4 +1,5 @@
 /* Copyright (C) 1996-2022 Free Software Foundation, Inc.
+   Copyright The GNU Toolchain Authors.
    This file is part of the GNU C Library.
 
    The GNU C Library is free software; you can redistribute it and/or
@@ -20,6 +21,7 @@
 #include <errno.h>
 #include <gconv.h>
 #include <stdlib.h>
+#include <string.h>
 #include <wchar.h>
 #include <wcsmbsload.h>
 
@@ -34,7 +36,7 @@
 static mbstate_t state;
 
 size_t
-__wcrtomb (char *s, wchar_t wc, mbstate_t *ps)
+__wcrtomb_internal (char *s, wchar_t wc, mbstate_t *ps, size_t s_size)
 {
   char buf[MB_LEN_MAX];
   struct __gconv_step_data data;
@@ -52,14 +54,11 @@ __wcrtomb (char *s, wchar_t wc, mbstate_t *ps)
   /* A first special case is if S is NULL.  This means put PS in the
      initial state.  */
   if (s == NULL)
-    {
-      s = buf;
-      wc = L'\0';
-    }
+    wc = L'\0';
 
   /* Tell where we want to have the result.  */
-  data.__outbuf = (unsigned char *) s;
-  data.__outbufend = (unsigned char *) s + MB_CUR_MAX;
+  data.__outbuf = (unsigned char *) buf;
+  data.__outbufend = (unsigned char *) buf + sizeof buf;
 
   /* Get the conversion functions.  */
   fcts = get_gconv_fcts (_NL_CURRENT_DATA (LC_CTYPE));
@@ -101,7 +100,17 @@ __wcrtomb (char *s, wchar_t wc, mbstate_t *ps)
 
   if (status == __GCONV_OK || status == __GCONV_EMPTY_INPUT
       || status == __GCONV_FULL_OUTPUT)
-    result = data.__outbuf - (unsigned char *) s;
+    {
+      result = data.__outbuf - (unsigned char *) buf;
+
+      if (s != NULL)
+	{
+	  if (result > s_size)
+	    __chk_fail ();
+
+	  memcpy (s, buf, result);
+	}
+    }
   else
     {
       result = (size_t) -1;
@@ -110,5 +119,11 @@ __wcrtomb (char *s, wchar_t wc, mbstate_t *ps)
 
   return result;
 }
+
+size_t
+__wcrtomb (char *s, wchar_t wc, mbstate_t *ps)
+{
+  return __wcrtomb_internal (s, wc, ps, (size_t) -1);
+}
 weak_alias (__wcrtomb, wcrtomb)
 libc_hidden_weak (wcrtomb)