From 44f06ba8297c7e9dfd0e49b40cbe119113cca094 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 12 Apr 2018 17:22:23 +0200 Subject: udf: Fix leak of UTF-16 surrogates into encoded strings 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 Signed-off-by: Jan Kara --- fs/udf/unicode.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'fs/udf') diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c index f897e55f2cd0..16a8ad21b77e 100644 --- a/fs/udf/unicode.c +++ b/fs/udf/unicode.c @@ -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) { -- cgit v1.2.3-55-g7522