mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-29 13:53:33 +00:00
udf: Fix leak of UTF-16 surrogates into encoded strings
commit 44f06ba829
upstream.
OSTA UDF specification does not mention whether the CS0 charset in case
of two bytes per character encoding should be treated in UTF-16 or
UCS-2. The sample code in the standard does not treat UTF-16 surrogates
in any special way but on systems such as Windows which work in UTF-16
internally, filenames would be treated as being in UTF-16 effectively.
In Linux it is more difficult to handle characters outside of Base
Multilingual plane (beyond 0xffff) as NLS framework works with 2-byte
characters only. Just make sure we don't leak UTF-16 surrogates into the
resulting string when loading names from the filesystem for now.
CC: stable@vger.kernel.org # >= v4.6
Reported-by: Mingye Wang <arthur200126@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
This commit is contained in:
parent
f86815184c
commit
a2a9d0190f
1 changed files with 6 additions and 0 deletions
|
@ -28,6 +28,9 @@
|
|||
|
||||
#include "udf_sb.h"
|
||||
|
||||
#define SURROGATE_MASK 0xfffff800
|
||||
#define SURROGATE_PAIR 0x0000d800
|
||||
|
||||
static int udf_uni2char_utf8(wchar_t uni,
|
||||
unsigned char *out,
|
||||
int boundlen)
|
||||
|
@ -37,6 +40,9 @@ static int udf_uni2char_utf8(wchar_t uni,
|
|||
if (boundlen <= 0)
|
||||
return -ENAMETOOLONG;
|
||||
|
||||
if ((uni & SURROGATE_MASK) == SURROGATE_PAIR)
|
||||
return -EINVAL;
|
||||
|
||||
if (uni < 0x80) {
|
||||
out[u_len++] = (unsigned char)uni;
|
||||
} else if (uni < 0x800) {
|
||||
|
|
Loading…
Reference in a new issue