cifs_unicode.c 10.5 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3
/*
 *   fs/cifs/cifs_unicode.c
 *
4
 *   Copyright (c) International Business Machines  Corp., 2000,2009
L
Linus Torvalds 已提交
5 6 7 8
 *   Modified by Steve French (sfrench@us.ibm.com)
 *
 *   This program is free software;  you can redistribute it and/or modify
 *   it under the terms of the GNU General Public License as published by
S
Steve French 已提交
9
 *   the Free Software Foundation; either version 2 of the License, or
L
Linus Torvalds 已提交
10
 *   (at your option) any later version.
S
Steve French 已提交
11
 *
L
Linus Torvalds 已提交
12 13 14 15 16 17
 *   This program is distributed in the hope that it will be useful,
 *   but WITHOUT ANY WARRANTY;  without even the implied warranty of
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
 *   the GNU General Public License for more details.
 *
 *   You should have received a copy of the GNU General Public License
S
Steve French 已提交
18
 *   along with this program;  if not, write to the Free Software
L
Linus Torvalds 已提交
19 20 21
 *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 */
#include <linux/fs.h>
22
#include <linux/slab.h>
L
Linus Torvalds 已提交
23 24 25
#include "cifs_unicode.h"
#include "cifs_uniupr.h"
#include "cifspdu.h"
26
#include "cifsglob.h"
L
Linus Torvalds 已提交
27 28
#include "cifs_debug.h"

29
/*
30 31
 * cifs_utf16_bytes - how long will a string be after conversion?
 * @utf16 - pointer to input string
32 33 34
 * @maxbytes - don't go past this many bytes of input string
 * @codepage - destination codepage
 *
35
 * Walk a utf16le string and return the number of bytes that the string will
36 37 38 39
 * be after being converted to the given charset, not including any null
 * termination required. Don't walk past maxbytes in the source buffer.
 */
int
40
cifs_utf16_bytes(const __le16 *from, int maxbytes,
41 42 43 44 45 46
		const struct nls_table *codepage)
{
	int i;
	int charlen, outlen = 0;
	int maxwords = maxbytes / 2;
	char tmp[NLS_MAX_CHARSET_SIZE];
47
	__u16 ftmp;
48

49 50 51 52 53 54
	for (i = 0; i < maxwords; i++) {
		ftmp = get_unaligned_le16(&from[i]);
		if (ftmp == 0)
			break;

		charlen = codepage->uni2char(ftmp, tmp, NLS_MAX_CHARSET_SIZE);
55 56 57 58 59 60 61 62 63
		if (charlen > 0)
			outlen += charlen;
		else
			outlen++;
	}

	return outlen;
}

64
/*
65
 * cifs_mapchar - convert a host-endian char to proper char in codepage
66
 * @target - where converted character should be copied
67
 * @src_char - 2 byte host-endian source character
68 69 70 71 72 73 74 75
 * @cp - codepage to which character should be converted
 * @mapchar - should character be mapped according to mapchars mount option?
 *
 * This function handles the conversion of a single character. It is the
 * responsibility of the caller to ensure that the target buffer is large
 * enough to hold the result of the conversion (at least NLS_MAX_CHARSET_SIZE).
 */
static int
76
cifs_mapchar(char *target, const __u16 src_char, const struct nls_table *cp,
77 78 79 80 81 82 83 84 85 86 87 88
	     bool mapchar)
{
	int len = 1;

	if (!mapchar)
		goto cp_convert;

	/*
	 * BB: Cannot handle remapping UNI_SLASH until all the calls to
	 *     build_path_from_dentry are modified, as they use slash as
	 *     separator.
	 */
89
	switch (src_char) {
90 91 92
	case UNI_COLON:
		*target = ':';
		break;
93
	case UNI_ASTERISK:
94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115
		*target = '*';
		break;
	case UNI_QUESTION:
		*target = '?';
		break;
	case UNI_PIPE:
		*target = '|';
		break;
	case UNI_GRTRTHAN:
		*target = '>';
		break;
	case UNI_LESSTHAN:
		*target = '<';
		break;
	default:
		goto cp_convert;
	}

out:
	return len;

cp_convert:
116
	len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
117 118 119 120 121 122 123 124
	if (len <= 0) {
		*target = '?';
		len = 1;
	}
	goto out;
}

/*
125
 * cifs_from_utf16 - convert utf16le string to local charset
126 127 128 129 130 131 132
 * @to - destination buffer
 * @from - source buffer
 * @tolen - destination buffer size (in bytes)
 * @fromlen - source buffer size (in bytes)
 * @codepage - codepage to which characters should be converted
 * @mapchar - should characters be remapped according to the mapchars option?
 *
133
 * Convert a little-endian utf16le string (as sent by the server) to a string
134 135 136 137 138 139 140 141
 * in the provided codepage. The tolen and fromlen parameters are to ensure
 * that the code doesn't walk off of the end of the buffer (which is always
 * a danger if the alignment of the source buffer is off). The destination
 * string is always properly null terminated and fits in the destination
 * buffer. Returns the length of the destination string in bytes (including
 * null terminator).
 *
 * Note that some windows versions actually send multiword UTF-16 characters
142
 * instead of straight UTF16-2. The linux nls routines however aren't able to
143 144 145 146
 * deal with those characters properly. In the event that we get some of
 * those characters, they won't be translated properly.
 */
int
147
cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
148 149 150 151 152 153 154
		 const struct nls_table *codepage, bool mapchar)
{
	int i, charlen, safelen;
	int outlen = 0;
	int nullsize = nls_nullsize(codepage);
	int fromwords = fromlen / 2;
	char tmp[NLS_MAX_CHARSET_SIZE];
155
	__u16 ftmp;
156 157 158 159 160 161 162 163 164

	/*
	 * because the chars can be of varying widths, we need to take care
	 * not to overflow the destination buffer when we get close to the
	 * end of it. Until we get to this offset, we don't need to check
	 * for overflow however.
	 */
	safelen = tolen - (NLS_MAX_CHARSET_SIZE + nullsize);

165 166 167 168 169
	for (i = 0; i < fromwords; i++) {
		ftmp = get_unaligned_le16(&from[i]);
		if (ftmp == 0)
			break;

170 171 172 173 174
		/*
		 * check to see if converting this character might make the
		 * conversion bleed into the null terminator
		 */
		if (outlen >= safelen) {
175
			charlen = cifs_mapchar(tmp, ftmp, codepage, mapchar);
176 177 178 179 180
			if ((outlen + charlen) > (tolen - nullsize))
				break;
		}

		/* put converted char into 'to' buffer */
181
		charlen = cifs_mapchar(&to[outlen], ftmp, codepage, mapchar);
182 183 184 185 186 187 188 189 190 191
		outlen += charlen;
	}

	/* properly null-terminate string */
	for (i = 0; i < nullsize; i++)
		to[outlen++] = 0;

	return outlen;
}

L
Linus Torvalds 已提交
192
/*
193
 * NAME:	cifs_strtoUTF16()
L
Linus Torvalds 已提交
194 195 196 197 198
 *
 * FUNCTION:	Convert character string to unicode string
 *
 */
int
199
cifs_strtoUTF16(__le16 *to, const char *from, int len,
L
Linus Torvalds 已提交
200 201 202 203
	      const struct nls_table *codepage)
{
	int charlen;
	int i;
204
	wchar_t wchar_to; /* needed to quiet sparse */
L
Linus Torvalds 已提交
205 206

	for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
207
		charlen = codepage->char2uni(from, len, &wchar_to);
L
Linus Torvalds 已提交
208
		if (charlen < 1) {
209
			cERROR(1, "strtoUTF16: char2uni of 0x%x returned %d",
210
				*from, charlen);
211
			/* A question mark */
212
			wchar_to = 0x003f;
L
Linus Torvalds 已提交
213
			charlen = 1;
214 215
		}
		put_unaligned_le16(wchar_to, &to[i]);
L
Linus Torvalds 已提交
216 217
	}

218
	put_unaligned_le16(0, &to[i]);
L
Linus Torvalds 已提交
219 220 221
	return i;
}

222
/*
223 224
 * cifs_strndup_from_utf16 - copy a string from wire format to the local
 * codepage
225 226 227 228 229 230 231 232 233 234
 * @src - source string
 * @maxlen - don't walk past this many bytes in the source string
 * @is_unicode - is this a unicode string?
 * @codepage - destination codepage
 *
 * Take a string given by the server, convert it to the local codepage and
 * put it in a new buffer. Returns a pointer to the new string or NULL on
 * error.
 */
char *
235 236
cifs_strndup_from_utf16(const char *src, const int maxlen,
			const bool is_unicode, const struct nls_table *codepage)
237 238 239 240 241
{
	int len;
	char *dst;

	if (is_unicode) {
242
		len = cifs_utf16_bytes((__le16 *) src, maxlen, codepage);
243 244 245 246
		len += nls_nullsize(codepage);
		dst = kmalloc(len, GFP_KERNEL);
		if (!dst)
			return NULL;
247
		cifs_from_utf16(dst, (__le16 *) src, len, maxlen, codepage,
248 249 250 251 252 253 254 255 256 257 258 259 260
			       false);
	} else {
		len = strnlen(src, maxlen);
		len++;
		dst = kmalloc(len, GFP_KERNEL);
		if (!dst)
			return NULL;
		strlcpy(dst, src, len);
	}

	return dst;
}

261 262 263 264 265 266 267
/*
 * Convert 16 bit Unicode pathname to wire format from string in current code
 * page. Conversion may involve remapping up the six characters that are
 * only legal in POSIX-like OS (if they are present in the string). Path
 * names are little endian 16 bit Unicode on the wire
 */
int
268
cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
269 270 271 272
		 const struct nls_table *cp, int mapChars)
{
	int i, j, charlen;
	char src_char;
273 274
	__le16 dst_char;
	wchar_t tmp;
275 276

	if (!mapChars)
277
		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
278

279
	for (i = 0, j = 0; i < srclen; j++) {
280
		src_char = source[i];
281
		charlen = 1;
282 283
		switch (src_char) {
		case 0:
284
			put_unaligned(0, &target[j]);
285
			goto ctoUTF16_out;
286
		case ':':
287
			dst_char = cpu_to_le16(UNI_COLON);
288 289
			break;
		case '*':
290
			dst_char = cpu_to_le16(UNI_ASTERISK);
291 292
			break;
		case '?':
293
			dst_char = cpu_to_le16(UNI_QUESTION);
294 295
			break;
		case '<':
296
			dst_char = cpu_to_le16(UNI_LESSTHAN);
297 298
			break;
		case '>':
299
			dst_char = cpu_to_le16(UNI_GRTRTHAN);
300 301
			break;
		case '|':
302
			dst_char = cpu_to_le16(UNI_PIPE);
303 304 305 306 307 308 309
			break;
		/*
		 * FIXME: We can not handle remapping backslash (UNI_SLASH)
		 * until all the calls to build_path_from_dentry are modified,
		 * as they use backslash as separator.
		 */
		default:
310 311 312
			charlen = cp->char2uni(source + i, srclen - i, &tmp);
			dst_char = cpu_to_le16(tmp);

313 314 315 316 317
			/*
			 * if no match, use question mark, which at least in
			 * some cases serves as wild card
			 */
			if (charlen < 1) {
318
				dst_char = cpu_to_le16(0x003f);
319 320 321
				charlen = 1;
			}
		}
322 323 324 325 326
		/*
		 * character may take more than one byte in the source string,
		 * but will take exactly two bytes in the target string
		 */
		i += charlen;
327
		put_unaligned(dst_char, &target[j]);
328 329
	}

330
ctoUTF16_out:
331
	return j;
332
}
333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393

#ifdef CONFIG_CIFS_SMB2
/*
 * cifs_local_to_utf16_bytes - how long will a string be after conversion?
 * @from - pointer to input string
 * @maxbytes - don't go past this many bytes of input string
 * @codepage - source codepage
 *
 * Walk a string and return the number of bytes that the string will
 * be after being converted to the given charset, not including any null
 * termination required. Don't walk past maxbytes in the source buffer.
 */

static int
cifs_local_to_utf16_bytes(const char *from, int len,
			  const struct nls_table *codepage)
{
	int charlen;
	int i;
	wchar_t wchar_to;

	for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
		charlen = codepage->char2uni(from, len, &wchar_to);
		/* Failed conversion defaults to a question mark */
		if (charlen < 1)
			charlen = 1;
	}
	return 2 * i; /* UTF16 characters are two bytes */
}

/*
 * cifs_strndup_to_utf16 - copy a string to wire format from the local codepage
 * @src - source string
 * @maxlen - don't walk past this many bytes in the source string
 * @utf16_len - the length of the allocated string in bytes (including null)
 * @cp - source codepage
 * @remap - map special chars
 *
 * Take a string convert it from the local codepage to UTF16 and
 * put it in a new buffer. Returns a pointer to the new string or NULL on
 * error.
 */
__le16 *
cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len,
		      const struct nls_table *cp, int remap)
{
	int len;
	__le16 *dst;

	len = cifs_local_to_utf16_bytes(src, maxlen, cp);
	len += 2; /* NULL */
	dst = kmalloc(len, GFP_KERNEL);
	if (!dst) {
		*utf16_len = 0;
		return NULL;
	}
	cifsConvertToUTF16(dst, src, strlen(src), cp, remap);
	*utf16_len = len;
	return dst;
}
#endif /* CONFIG_CIFS_SMB2 */