linux-stable/fs/udf/unicode.c

504 lines
11 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"
static int udf_translate_to_linux(uint8_t *, int, uint8_t *, int, uint8_t *,
int);
static int udf_char_to_ustr(struct ustr *dest, const uint8_t *src, int strlen)
{
if ((!dest) || (!src) || (!strlen) || (strlen > UDF_NAME_LEN - 2))
return 0;
memset(dest, 0, sizeof(struct ustr));
memcpy(dest->u_name, src, strlen);
dest->u_cmpID = 0x08;
dest->u_len = strlen;
return strlen;
}
/*
* udf_build_ustr
*/
int udf_build_ustr(struct ustr *dest, dstring *ptr, int size)
{
int usesize;
if (!dest || !ptr || !size)
return -1;
BUG_ON(size < 2);
usesize = min_t(size_t, ptr[size - 1], sizeof(dest->u_name));
usesize = min(usesize, size - 2);
dest->u_cmpID = ptr[0];
dest->u_len = usesize;
memcpy(dest->u_name, ptr + 1, usesize);
memset(dest->u_name + usesize, 0, sizeof(dest->u_name) - usesize);
return 0;
}
/*
* udf_build_ustr_exact
*/
static void udf_build_ustr_exact(struct ustr *dest, dstring *ptr, int exactsize)
{
memset(dest, 0, sizeof(struct ustr));
dest->u_cmpID = ptr[0];
dest->u_len = exactsize - 1;
memcpy(dest->u_name, ptr + 1, exactsize - 1);
}
/*
* udf_CS0toUTF8
*
* PURPOSE
* Convert OSTA Compressed Unicode to the UTF-8 equivalent.
*
* PRE-CONDITIONS
* utf Pointer to UTF-8 output buffer.
* ocu Pointer to OSTA Compressed Unicode input buffer
* of size UDF_NAME_LEN bytes.
* both of type "struct ustr *"
*
* POST-CONDITIONS
* <return> >= 0 on success.
*
* HISTORY
* November 12, 1997 - Andrew E. Mileski
* Written, tested, and released.
*/
int udf_CS0toUTF8(struct ustr *utf_o, const struct ustr *ocu_i)
{
const uint8_t *ocu;
uint8_t cmp_id, ocu_len;
int i;
ocu_len = ocu_i->u_len;
if (ocu_len == 0) {
memset(utf_o, 0, sizeof(struct ustr));
return 0;
}
cmp_id = ocu_i->u_cmpID;
if (cmp_id != 8 && cmp_id != 16) {
memset(utf_o, 0, sizeof(struct ustr));
pr_err("unknown compression code (%d) stri=%s\n",
cmp_id, ocu_i->u_name);
return -EINVAL;
}
ocu = ocu_i->u_name;
utf_o->u_len = 0;
for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) {
/* Expand OSTA compressed Unicode to Unicode */
uint32_t c = ocu[i++];
if (cmp_id == 16)
c = (c << 8) | ocu[i++];
/* Compress Unicode to UTF-8 */
if (c < 0x80U)
utf_o->u_name[utf_o->u_len++] = (uint8_t)c;
else if (c < 0x800U) {
if (utf_o->u_len > (UDF_NAME_LEN - 4))
break;
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0xc0 | (c >> 6));
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0x80 | (c & 0x3f));
} else {
if (utf_o->u_len > (UDF_NAME_LEN - 5))
break;
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0xe0 | (c >> 12));
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0x80 |
((c >> 6) & 0x3f));
utf_o->u_name[utf_o->u_len++] =
(uint8_t)(0x80 | (c & 0x3f));
}
}
utf_o->u_cmpID = 8;
return utf_o->u_len;
}
/*
*
* udf_UTF8toCS0
*
* PURPOSE
* Convert UTF-8 to the OSTA Compressed Unicode equivalent.
*
* DESCRIPTION
* This routine is only called by udf_lookup().
*
* PRE-CONDITIONS
* ocu Pointer to OSTA Compressed Unicode output
* buffer of size UDF_NAME_LEN bytes.
* utf Pointer to UTF-8 input buffer.
* utf_len Length of UTF-8 input buffer in bytes.
*
* POST-CONDITIONS
* <return> Zero on success.
*
* HISTORY
* November 12, 1997 - Andrew E. Mileski
* Written, tested, and released.
*/
static int udf_UTF8toCS0(dstring *ocu, struct ustr *utf, int length)
{
unsigned c, i, max_val, utf_char;
int utf_cnt, u_len;
memset(ocu, 0, sizeof(dstring) * length);
ocu[0] = 8;
max_val = 0xffU;
try_again:
u_len = 0U;
utf_char = 0U;
utf_cnt = 0U;
for (i = 0U; i < utf->u_len; i++) {
c = (uint8_t)utf->u_name[i];
/* Complete a multi-byte UTF-8 character */
if (utf_cnt) {
utf_char = (utf_char << 6) | (c & 0x3fU);
if (--utf_cnt)
continue;
} else {
/* Check for a multi-byte UTF-8 character */
if (c & 0x80U) {
/* Start a multi-byte UTF-8 character */
if ((c & 0xe0U) == 0xc0U) {
utf_char = c & 0x1fU;
utf_cnt = 1;
} else if ((c & 0xf0U) == 0xe0U) {
utf_char = c & 0x0fU;
utf_cnt = 2;
} else if ((c & 0xf8U) == 0xf0U) {
utf_char = c & 0x07U;
utf_cnt = 3;
} else if ((c & 0xfcU) == 0xf8U) {
utf_char = c & 0x03U;
utf_cnt = 4;
} else if ((c & 0xfeU) == 0xfcU) {
utf_char = c & 0x01U;
utf_cnt = 5;
} else {
goto error_out;
}
continue;
} else {
/* Single byte UTF-8 character (most common) */
utf_char = c;
}
}
/* Choose no compression if necessary */
if (utf_char > max_val) {
if (max_val == 0xffU) {
max_val = 0xffffU;
ocu[0] = (uint8_t)0x10U;
goto try_again;
}
goto error_out;
}
if (max_val == 0xffffU)
ocu[++u_len] = (uint8_t)(utf_char >> 8);
ocu[++u_len] = (uint8_t)(utf_char & 0xffU);
}
if (utf_cnt) {
error_out:
ocu[++u_len] = '?';
printk(KERN_DEBUG pr_fmt("bad UTF-8 character\n"));
}
ocu[length - 1] = (uint8_t)u_len + 1;
return u_len + 1;
}
static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o,
const struct ustr *ocu_i)
{
const uint8_t *ocu;
uint8_t cmp_id, ocu_len;
int i, len;
ocu_len = ocu_i->u_len;
if (ocu_len == 0) {
memset(utf_o, 0, sizeof(struct ustr));
return 0;
}
cmp_id = ocu_i->u_cmpID;
if (cmp_id != 8 && cmp_id != 16) {
memset(utf_o, 0, sizeof(struct ustr));
pr_err("unknown compression code (%d) stri=%s\n",
cmp_id, ocu_i->u_name);
return -EINVAL;
}
ocu = ocu_i->u_name;
utf_o->u_len = 0;
for (i = 0; (i < ocu_len) && (utf_o->u_len <= (UDF_NAME_LEN - 3));) {
/* Expand OSTA compressed Unicode to Unicode */
uint32_t c = ocu[i++];
if (cmp_id == 16)
c = (c << 8) | ocu[i++];
len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len],
UDF_NAME_LEN - 2 - utf_o->u_len);
/* Valid character? */
if (len >= 0)
utf_o->u_len += len;
else
utf_o->u_name[utf_o->u_len++] = '?';
}
utf_o->u_cmpID = 8;
return utf_o->u_len;
}
static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni,
int length)
{
int len;
unsigned i, max_val;
uint16_t uni_char;
int u_len;
memset(ocu, 0, sizeof(dstring) * length);
ocu[0] = 8;
max_val = 0xffU;
try_again:
u_len = 0U;
for (i = 0U; i < uni->u_len; i++) {
len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char);
if (!len)
continue;
/* Invalid character, deal with it */
if (len < 0) {
len = 1;
uni_char = '?';
}
if (uni_char > max_val) {
max_val = 0xffffU;
ocu[0] = (uint8_t)0x10U;
goto try_again;
}
if (max_val == 0xffffU)
ocu[++u_len] = (uint8_t)(uni_char >> 8);
ocu[++u_len] = (uint8_t)(uni_char & 0xffU);
i += len - 1;
}
ocu[length - 1] = (uint8_t)u_len + 1;
return u_len + 1;
}
int udf_get_filename(struct super_block *sb, uint8_t *sname, int slen,
uint8_t *dname, int dlen)
{
struct ustr *filename, *unifilename;
int ret;
if (!slen)
return -EIO;
filename = kmalloc(sizeof(struct ustr), GFP_NOFS);
if (!filename)
return -ENOMEM;
unifilename = kmalloc(sizeof(struct ustr), GFP_NOFS);
if (!unifilename) {
ret = -ENOMEM;
goto out1;
}
udf_build_ustr_exact(unifilename, sname, slen);
if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
ret = udf_CS0toUTF8(filename, unifilename);
if (ret < 0) {
udf_debug("Failed in udf_get_filename: sname = %s\n",
sname);
goto out2;
}
} else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) {
ret = udf_CS0toNLS(UDF_SB(sb)->s_nls_map, filename,
unifilename);
if (ret < 0) {
udf_debug("Failed in udf_get_filename: sname = %s\n",
sname);
goto out2;
}
} else
BUG();
ret = udf_translate_to_linux(dname, dlen,
filename->u_name, filename->u_len,
unifilename->u_name, unifilename->u_len);
/* Zero length filename isn't valid... */
if (ret == 0)
ret = -EINVAL;
out2:
kfree(unifilename);
out1:
kfree(filename);
return ret;
}
int udf_put_filename(struct super_block *sb, const uint8_t *sname,
uint8_t *dname, int flen)
{
struct ustr unifilename;
int namelen;
if (!udf_char_to_ustr(&unifilename, sname, flen))
return 0;
if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
namelen = udf_UTF8toCS0(dname, &unifilename, UDF_NAME_LEN);
if (!namelen)
return 0;
} else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) {
namelen = udf_NLStoCS0(UDF_SB(sb)->s_nls_map, dname,
&unifilename, UDF_NAME_LEN);
if (!namelen)
return 0;
} else
return 0;
return namelen;
}
#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 int udf_translate_to_linux(uint8_t *newName, int newLen,
uint8_t *udfName, int udfLen,
uint8_t *fidName, int fidNameLen)
{
int index, newIndex = 0, needsCRC = 0;
int extIndex = 0, newExtIndex = 0, hasExt = 0;
unsigned short valueCRC;
uint8_t curr;
if (udfName[0] == '.' &&
(udfLen == 1 || (udfLen == 2 && udfName[1] == '.'))) {
needsCRC = 1;
newIndex = udfLen;
memcpy(newName, udfName, udfLen);
} else {
for (index = 0; index < udfLen; index++) {
curr = udfName[index];
if (curr == '/' || curr == 0) {
needsCRC = 1;
curr = ILLEGAL_CHAR_MARK;
while (index + 1 < udfLen &&
(udfName[index + 1] == '/' ||
udfName[index + 1] == 0))
index++;
}
if (curr == EXT_MARK &&
(udfLen - index - 1) <= EXT_SIZE) {
if (udfLen == index + 1)
hasExt = 0;
else {
hasExt = 1;
extIndex = index;
newExtIndex = newIndex;
}
}
if (newIndex < newLen)
newName[newIndex++] = curr;
else
needsCRC = 1;
}
}
if (needsCRC) {
uint8_t ext[EXT_SIZE];
int localExtIndex = 0;
if (hasExt) {
int maxFilenameLen;
for (index = 0;
index < EXT_SIZE && extIndex + index + 1 < udfLen;
index++) {
curr = udfName[extIndex + index + 1];
if (curr == '/' || curr == 0) {
needsCRC = 1;
curr = ILLEGAL_CHAR_MARK;
while (extIndex + index + 2 < udfLen &&
(index + 1 < EXT_SIZE &&
(udfName[extIndex + index + 2] == '/' ||
udfName[extIndex + index + 2] == 0)))
index++;
}
ext[localExtIndex++] = curr;
}
maxFilenameLen = newLen - CRC_LEN - localExtIndex;
if (newIndex > maxFilenameLen)
newIndex = maxFilenameLen;
else
newIndex = newExtIndex;
} else if (newIndex > newLen - CRC_LEN)
newIndex = newLen - CRC_LEN;
newName[newIndex++] = CRC_MARK;
valueCRC = crc_itu_t(0, fidName, fidNameLen);
newName[newIndex++] = hex_asc_upper_hi(valueCRC >> 8);
newName[newIndex++] = hex_asc_upper_lo(valueCRC >> 8);
newName[newIndex++] = hex_asc_upper_hi(valueCRC);
newName[newIndex++] = hex_asc_upper_lo(valueCRC);
if (hasExt) {
newName[newIndex++] = EXT_MARK;
for (index = 0; index < localExtIndex; index++)
newName[newIndex++] = ext[index];
}
}
return newIndex;
}