diff options
author | OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> | 2009-08-01 08:30:31 -0400 |
---|---|---|
committer | OGAWA Hirofumi <hirofumi@mail.parknet.co.jp> | 2009-08-01 08:35:21 -0400 |
commit | 67638e4043083cdc6f10386a75fef87ba46eecb3 (patch) | |
tree | 4bf3c4ba8e5c316f7dcf98083b1a851ce248a2ee /fs | |
parent | ed680c4ad478d0fee9740f7d029087f181346564 (diff) |
fat/nls: Fix handling of utf8 invalid char
With utf8 option, vfat allowed the duplicated filenames.
Normal nls returns -EINVAL for invalid char. But utf8s_to_utf16s()
skipped the invalid char historically.
So, this changes the utf8s_to_utf16s() directly to return -EINVAL for
invalid char, because vfat is only user of it.
mkdir /mnt/fatfs
FILENAME=`echo -ne "invalidutf8char_\\0341_endofchar"`
echo "Using filename: $FILENAME"
dd if=/dev/zero of=fatfs bs=512 count=128
mkdosfs -F 32 fatfs
mount -o loop,utf8 fatfs /mnt/fatfs
touch "/mnt/fatfs/$FILENAME"
umount /mnt/fatfs
mount -o loop,utf8 fatfs /mnt/fatfs
touch "/mnt/fatfs/$FILENAME"
ls -l /mnt/fatfs
umount /mnt/fatfs
---- And the output is:
Using filename: invalidutf8char_\0341_endofchar
128+0 records in
128+0 records out
65536 bytes (66 kB) copied, 0.000388118 s, 169 MB/s
mkdosfs 2.11 (12 Mar 2005)
total 0
-rwxr-xr-x 1 root root 0 Jun 28 19:46 invalidutf8char__endofchar
-rwxr-xr-x 1 root root 0 Jun 28 19:46 invalidutf8char__endofchar
Tested-by: Marton Balint <cus@fazekas.hu>
Signed-off-by: OGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Diffstat (limited to 'fs')
-rw-r--r-- | fs/fat/namei_vfat.c | 15 | ||||
-rw-r--r-- | fs/nls/nls_base.c | 8 |
2 files changed, 8 insertions, 15 deletions
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c index cb6e83557112..f565f24019b5 100644 --- a/fs/fat/namei_vfat.c +++ b/fs/fat/namei_vfat.c | |||
@@ -499,17 +499,10 @@ xlate_to_uni(const unsigned char *name, int len, unsigned char *outname, | |||
499 | int charlen; | 499 | int charlen; |
500 | 500 | ||
501 | if (utf8) { | 501 | if (utf8) { |
502 | int name_len = strlen(name); | 502 | *outlen = utf8s_to_utf16s(name, len, (wchar_t *)outname); |
503 | 503 | if (*outlen < 0) | |
504 | *outlen = utf8s_to_utf16s(name, PATH_MAX, (wchar_t *) outname); | 504 | return *outlen; |
505 | 505 | else if (*outlen > 255) | |
506 | /* | ||
507 | * We stripped '.'s before and set len appropriately, | ||
508 | * but utf8s_to_utf16s doesn't care about len | ||
509 | */ | ||
510 | *outlen -= (name_len - len); | ||
511 | |||
512 | if (*outlen > 255) | ||
513 | return -ENAMETOOLONG; | 506 | return -ENAMETOOLONG; |
514 | 507 | ||
515 | op = &outname[*outlen * sizeof(wchar_t)]; | 508 | op = &outname[*outlen * sizeof(wchar_t)]; |
diff --git a/fs/nls/nls_base.c b/fs/nls/nls_base.c index 477d37d83b31..b25c218671b3 100644 --- a/fs/nls/nls_base.c +++ b/fs/nls/nls_base.c | |||
@@ -124,10 +124,10 @@ int utf8s_to_utf16s(const u8 *s, int len, wchar_t *pwcs) | |||
124 | while (*s && len > 0) { | 124 | while (*s && len > 0) { |
125 | if (*s & 0x80) { | 125 | if (*s & 0x80) { |
126 | size = utf8_to_utf32(s, len, &u); | 126 | size = utf8_to_utf32(s, len, &u); |
127 | if (size < 0) { | 127 | if (size < 0) |
128 | /* Ignore character and move on */ | 128 | return -EINVAL; |
129 | size = 1; | 129 | |
130 | } else if (u >= PLANE_SIZE) { | 130 | if (u >= PLANE_SIZE) { |
131 | u -= PLANE_SIZE; | 131 | u -= PLANE_SIZE; |
132 | *op++ = (wchar_t) (SURROGATE_PAIR | | 132 | *op++ = (wchar_t) (SURROGATE_PAIR | |
133 | ((u >> 10) & SURROGATE_BITS)); | 133 | ((u >> 10) & SURROGATE_BITS)); |