linux/fs/udf/unicode.c

403 lines
9.2 KiB
C
Raw Normal View History

/*
* unicode.c
*
* PURPOSE
* Routines for converting between UTF-8 and OSTA Compressed Unicode.
* Also handles filename mangling
*
* DESCRIPTION
* OSTA Compressed Unicode is explained in the OSTA UDF specification.
* http://www.osta.org/
* UTF-8 is explained in the IETF RFC XXXX.
* ftp://ftp.internic.net/rfc/rfcxxxx.txt
*
* COPYRIGHT
* This file is distributed under the terms of the GNU General Public
* License (GPL). Copies of the GPL can be obtained from:
* ftp://prep.ai.mit.edu/pub/gnu/GPL
* Each contributing author retains all rights to their own work.
*/
#include "udfdecl.h"
#include <linux/kernel.h>
#include <linux/string.h> /* for memset */
#include <linux/nls.h>
#include <linux/crc-itu-t.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 08:04:11 +00:00
#include <linux/slab.h>
#include "udf_sb.h"
#define PLANE_SIZE 0x10000
#define UNICODE_MAX 0x10ffff
#define SURROGATE_MASK 0xfffff800
#define SURROGATE_PAIR 0x0000d800
#define SURROGATE_LOW 0x00000400
#define SURROGATE_CHAR_BITS 10
#define SURROGATE_CHAR_MASK ((1 << SURROGATE_CHAR_BITS) - 1)
#define ILLEGAL_CHAR_MARK '_'
#define EXT_MARK '.'
#define CRC_MARK '#'
#define EXT_SIZE 5
/* Number of chars we need to store generated CRC to make filename unique */
#define CRC_LEN 5
static unicode_t get_utf16_char(const uint8_t *str_i, int str_i_max_len,
int str_i_idx, int u_ch, unicode_t *ret)
{
unicode_t c;
int start_idx = str_i_idx;
/* Expand OSTA compressed Unicode to Unicode */
c = str_i[str_i_idx++];
if (u_ch > 1)
c = (c << 8) | str_i[str_i_idx++];
if ((c & SURROGATE_MASK) == SURROGATE_PAIR) {
unicode_t next;
/* Trailing surrogate char */
if (str_i_idx >= str_i_max_len) {
c = UNICODE_MAX + 1;
goto out;
}
/* Low surrogate must follow the high one... */
if (c & SURROGATE_LOW) {
c = UNICODE_MAX + 1;
goto out;
}
WARN_ON_ONCE(u_ch != 2);
next = str_i[str_i_idx++] << 8;
next |= str_i[str_i_idx++];
if ((next & SURROGATE_MASK) != SURROGATE_PAIR ||
!(next & SURROGATE_LOW)) {
c = UNICODE_MAX + 1;
goto out;
}
c = PLANE_SIZE +
((c & SURROGATE_CHAR_MASK) << SURROGATE_CHAR_BITS) +
(next & SURROGATE_CHAR_MASK);
}
out:
*ret = c;
return str_i_idx - start_idx;
}
static int udf_name_conv_char(uint8_t *str_o, int str_o_max_len,
int *str_o_idx,
const uint8_t *str_i, int str_i_max_len,
int *str_i_idx,
int u_ch, int *needsCRC,
int (*conv_f)(wchar_t, unsigned char *, int),
int translate)
{
unicode_t c;
int illChar = 0;
int len, gotch = 0;
while (!gotch && *str_i_idx < str_i_max_len) {
if (*str_o_idx >= str_o_max_len) {
*needsCRC = 1;
return gotch;
}
len = get_utf16_char(str_i, str_i_max_len, *str_i_idx, u_ch,
&c);
/* These chars cannot be converted. Replace them. */
if (c == 0 || c > UNICODE_MAX || (conv_f && c > MAX_WCHAR_T) ||
(translate && c == '/')) {
illChar = 1;
if (!translate)
gotch = 1;
} else if (illChar)
break;
else
gotch = 1;
*str_i_idx += len;
}
if (illChar) {
*needsCRC = 1;
c = ILLEGAL_CHAR_MARK;
gotch = 1;
}
if (gotch) {
if (conv_f) {
len = conv_f(c, &str_o[*str_o_idx],
str_o_max_len - *str_o_idx);
} else {
len = utf32_to_utf8(c, &str_o[*str_o_idx],
str_o_max_len - *str_o_idx);
if (len < 0)
len = -ENAMETOOLONG;
}
/* Valid character? */
if (len >= 0)
*str_o_idx += len;
else if (len == -ENAMETOOLONG) {
*needsCRC = 1;
gotch = 0;
} else {
str_o[(*str_o_idx)++] = ILLEGAL_CHAR_MARK;
*needsCRC = 1;
}
}
return gotch;
}
static int udf_name_from_CS0(struct super_block *sb,
uint8_t *str_o, int str_max_len,
const uint8_t *ocu, int ocu_len,
int translate)
{
uint32_t c;
uint8_t cmp_id;
int idx, len;
int u_ch;
int needsCRC = 0;
int ext_i_len, ext_max_len;
int str_o_len = 0; /* Length of resulting output */
int ext_o_len = 0; /* Extension output length */
int ext_crc_len = 0; /* Extension output length if used with CRC */
int i_ext = -1; /* Extension position in input buffer */
int o_crc = 0; /* Rightmost possible output pos for CRC+ext */
unsigned short valueCRC;
uint8_t ext[EXT_SIZE * NLS_MAX_CHARSET_SIZE + 1];
uint8_t crc[CRC_LEN];
int (*conv_f)(wchar_t, unsigned char *, int);
if (str_max_len <= 0)
return 0;
if (ocu_len == 0) {
memset(str_o, 0, str_max_len);
return 0;
}
if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP))
conv_f = UDF_SB(sb)->s_nls_map->uni2char;
else
conv_f = NULL;
cmp_id = ocu[0];
if (cmp_id != 8 && cmp_id != 16) {
memset(str_o, 0, str_max_len);
pr_err("unknown compression code (%u)\n", cmp_id);
return -EINVAL;
}
u_ch = cmp_id >> 3;
ocu++;
ocu_len--;
if (ocu_len % u_ch) {
pr_err("incorrect filename length (%d)\n", ocu_len + 1);
return -EINVAL;
}
if (translate) {
/* Look for extension */
for (idx = ocu_len - u_ch, ext_i_len = 0;
(idx >= 0) && (ext_i_len < EXT_SIZE);
idx -= u_ch, ext_i_len++) {
c = ocu[idx];
if (u_ch > 1)
c = (c << 8) | ocu[idx + 1];
if (c == EXT_MARK) {
if (ext_i_len)
i_ext = idx;
break;
}
}
if (i_ext >= 0) {
/* Convert extension */
ext_max_len = min_t(int, sizeof(ext), str_max_len);
ext[ext_o_len++] = EXT_MARK;
idx = i_ext + u_ch;
while (udf_name_conv_char(ext, ext_max_len, &ext_o_len,
ocu, ocu_len, &idx,
u_ch, &needsCRC,
conv_f, translate)) {
if ((ext_o_len + CRC_LEN) < str_max_len)
ext_crc_len = ext_o_len;
}
}
}
idx = 0;
while (1) {
if (translate && (idx == i_ext)) {
if (str_o_len > (str_max_len - ext_o_len))
needsCRC = 1;
break;
}
if (!udf_name_conv_char(str_o, str_max_len, &str_o_len,
ocu, ocu_len, &idx,
u_ch, &needsCRC, conv_f, translate))
break;
if (translate &&
(str_o_len <= (str_max_len - ext_o_len - CRC_LEN)))
o_crc = str_o_len;
}
if (translate) {
if (str_o_len <= 2 && str_o[0] == '.' &&
(str_o_len == 1 || str_o[1] == '.'))
needsCRC = 1;
if (needsCRC) {
str_o_len = o_crc;
valueCRC = crc_itu_t(0, ocu, ocu_len);
crc[0] = CRC_MARK;
crc[1] = hex_asc_upper_hi(valueCRC >> 8);
crc[2] = hex_asc_upper_lo(valueCRC >> 8);
crc[3] = hex_asc_upper_hi(valueCRC);
crc[4] = hex_asc_upper_lo(valueCRC);
len = min_t(int, CRC_LEN, str_max_len - str_o_len);
memcpy(&str_o[str_o_len], crc, len);
str_o_len += len;
ext_o_len = ext_crc_len;
}
if (ext_o_len > 0) {
memcpy(&str_o[str_o_len], ext, ext_o_len);
str_o_len += ext_o_len;
}
}
return str_o_len;
}
static int udf_name_to_CS0(struct super_block *sb,
uint8_t *ocu, int ocu_max_len,
const uint8_t *str_i, int str_len)
{
int i, len;
unsigned int max_val;
int u_len, u_ch;
unicode_t uni_char;
int (*conv_f)(const unsigned char *, int, wchar_t *);
if (ocu_max_len <= 0)
return 0;
if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP))
conv_f = UDF_SB(sb)->s_nls_map->char2uni;
else
conv_f = NULL;
memset(ocu, 0, ocu_max_len);
ocu[0] = 8;
max_val = 0xff;
u_ch = 1;
try_again:
u_len = 1;
for (i = 0; i < str_len; i += len) {
/* Name didn't fit? */
if (u_len + u_ch > ocu_max_len)
return 0;
if (conv_f) {
wchar_t wchar;
len = conv_f(&str_i[i], str_len - i, &wchar);
if (len > 0)
uni_char = wchar;
} else {
len = utf8_to_utf32(&str_i[i], str_len - i,
&uni_char);
}
/* Invalid character, deal with it */
if (len <= 0 || uni_char > UNICODE_MAX) {
len = 1;
uni_char = '?';
}
if (uni_char > max_val) {
unicode_t c;
if (max_val == 0xff) {
max_val = 0xffff;
ocu[0] = 0x10;
u_ch = 2;
goto try_again;
}
/*
* Use UTF-16 encoding for chars outside we
* cannot encode directly.
*/
if (u_len + 2 * u_ch > ocu_max_len)
return 0;
uni_char -= PLANE_SIZE;
c = SURROGATE_PAIR |
((uni_char >> SURROGATE_CHAR_BITS) &
SURROGATE_CHAR_MASK);
ocu[u_len++] = (uint8_t)(c >> 8);
ocu[u_len++] = (uint8_t)(c & 0xff);
uni_char = SURROGATE_PAIR | SURROGATE_LOW |
(uni_char & SURROGATE_CHAR_MASK);
}
if (max_val == 0xffff)
ocu[u_len++] = (uint8_t)(uni_char >> 8);
ocu[u_len++] = (uint8_t)(uni_char & 0xff);
}
return u_len;
}
/*
* Convert CS0 dstring to output charset. Warning: This function may truncate
* input string if it is too long as it is used for informational strings only
* and it is better to truncate the string than to refuse mounting a media.
*/
int udf_dstrCS0toChar(struct super_block *sb, uint8_t *utf_o, int o_len,
udf: Fix conversion of 'dstring' fields to UTF8 Commit 9293fcfbc1812a22ad5ce1b542eb90c1bbe01be1 ("udf: Remove struct ustr as non-needed intermediate storage"), while getting rid of 'struct ustr', does not take any special care of 'dstring' fields and effectively use fixed field length instead of actual string length, encoded in the last byte of the field. Also, commit 484a10f49387e4386bf2708532e75bf78ffea2cb ("udf: Merge linux specific translation into CS0 conversion function") introduced checking of the length of the string being converted, requiring proper alignment to number of bytes constituing each character. The UDF volume identifier is represented as a 32-bytes 'dstring', and needs to be converted from CS0 to UTF8, while mounting UDF filesystem. The changes in mentioned commits can in some cases lead to incorrect handling of volume identifier: - if the actual string in 'dstring' is of maximal length and does not have zero bytes separating it from dstring encoded length in last byte, that last byte may be included in conversion, thus making incorrect resulting string; - if the identifier is encoded with 2-bytes characters (compression code is 16), the length of 31 bytes (32 bytes of field length minus 1 byte of compression code), taken as the string length, is reported as an incorrect (unaligned) length, and the conversion fails, which in its turn leads to volume mounting failure. This patch introduces handling of 'dstring' encoded length field in udf_CS0toUTF8 function, that is used in all and only cases when 'dstring' fields are converted. Currently these cases are processing of Volume Identifier and Volume Set Identifier fields. The function is also renamed to udf_dstrCS0toUTF8 to distinctly indicate that it handles 'dstring' input. Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Jan Kara <jack@suse.cz>
2016-04-25 11:19:38 +00:00
const uint8_t *ocu_i, int i_len)
{
udf: Fix conversion of 'dstring' fields to UTF8 Commit 9293fcfbc1812a22ad5ce1b542eb90c1bbe01be1 ("udf: Remove struct ustr as non-needed intermediate storage"), while getting rid of 'struct ustr', does not take any special care of 'dstring' fields and effectively use fixed field length instead of actual string length, encoded in the last byte of the field. Also, commit 484a10f49387e4386bf2708532e75bf78ffea2cb ("udf: Merge linux specific translation into CS0 conversion function") introduced checking of the length of the string being converted, requiring proper alignment to number of bytes constituing each character. The UDF volume identifier is represented as a 32-bytes 'dstring', and needs to be converted from CS0 to UTF8, while mounting UDF filesystem. The changes in mentioned commits can in some cases lead to incorrect handling of volume identifier: - if the actual string in 'dstring' is of maximal length and does not have zero bytes separating it from dstring encoded length in last byte, that last byte may be included in conversion, thus making incorrect resulting string; - if the identifier is encoded with 2-bytes characters (compression code is 16), the length of 31 bytes (32 bytes of field length minus 1 byte of compression code), taken as the string length, is reported as an incorrect (unaligned) length, and the conversion fails, which in its turn leads to volume mounting failure. This patch introduces handling of 'dstring' encoded length field in udf_CS0toUTF8 function, that is used in all and only cases when 'dstring' fields are converted. Currently these cases are processing of Volume Identifier and Volume Set Identifier fields. The function is also renamed to udf_dstrCS0toUTF8 to distinctly indicate that it handles 'dstring' input. Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Jan Kara <jack@suse.cz>
2016-04-25 11:19:38 +00:00
int s_len = 0;
if (i_len > 0) {
s_len = ocu_i[i_len - 1];
if (s_len >= i_len) {
pr_warn("incorrect dstring lengths (%d/%d),"
" truncating\n", s_len, i_len);
s_len = i_len - 1;
/* 2-byte encoding? Need to round properly... */
if (ocu_i[0] == 16)
s_len -= (s_len - 1) & 2;
udf: Fix conversion of 'dstring' fields to UTF8 Commit 9293fcfbc1812a22ad5ce1b542eb90c1bbe01be1 ("udf: Remove struct ustr as non-needed intermediate storage"), while getting rid of 'struct ustr', does not take any special care of 'dstring' fields and effectively use fixed field length instead of actual string length, encoded in the last byte of the field. Also, commit 484a10f49387e4386bf2708532e75bf78ffea2cb ("udf: Merge linux specific translation into CS0 conversion function") introduced checking of the length of the string being converted, requiring proper alignment to number of bytes constituing each character. The UDF volume identifier is represented as a 32-bytes 'dstring', and needs to be converted from CS0 to UTF8, while mounting UDF filesystem. The changes in mentioned commits can in some cases lead to incorrect handling of volume identifier: - if the actual string in 'dstring' is of maximal length and does not have zero bytes separating it from dstring encoded length in last byte, that last byte may be included in conversion, thus making incorrect resulting string; - if the identifier is encoded with 2-bytes characters (compression code is 16), the length of 31 bytes (32 bytes of field length minus 1 byte of compression code), taken as the string length, is reported as an incorrect (unaligned) length, and the conversion fails, which in its turn leads to volume mounting failure. This patch introduces handling of 'dstring' encoded length field in udf_CS0toUTF8 function, that is used in all and only cases when 'dstring' fields are converted. Currently these cases are processing of Volume Identifier and Volume Set Identifier fields. The function is also renamed to udf_dstrCS0toUTF8 to distinctly indicate that it handles 'dstring' input. Signed-off-by: Andrew Gabbasov <andrew_gabbasov@mentor.com> Signed-off-by: Jan Kara <jack@suse.cz>
2016-04-25 11:19:38 +00:00
}
}
return udf_name_from_CS0(sb, utf_o, o_len, ocu_i, s_len, 0);
}
int udf_get_filename(struct super_block *sb, const uint8_t *sname, int slen,
uint8_t *dname, int dlen)
{
int ret;
if (!slen)
return -EIO;
if (dlen <= 0)
return 0;
ret = udf_name_from_CS0(sb, dname, dlen, sname, slen, 1);
/* Zero length filename isn't valid... */
if (ret == 0)
ret = -EINVAL;
return ret;
}
int udf_put_filename(struct super_block *sb, const uint8_t *sname, int slen,
uint8_t *dname, int dlen)
{
return udf_name_to_CS0(sb, dname, dlen, sname, slen);
}