cifs_unicode.c 16.3 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>
23
#include "cifs_fs_sb.h"
L
Linus Torvalds 已提交
24 25 26
#include "cifs_unicode.h"
#include "cifs_uniupr.h"
#include "cifspdu.h"
27
#include "cifsglob.h"
L
Linus Torvalds 已提交
28 29
#include "cifs_debug.h"

30 31 32 33 34 35 36 37 38 39 40 41 42 43
int cifs_remap(struct cifs_sb_info *cifs_sb)
{
	int map_type;

	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SFM_CHR)
		map_type = SFM_MAP_UNI_RSVD;
	else if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MAP_SPECIAL_CHR)
		map_type = SFU_MAP_UNI_RSVD;
	else
		map_type = NO_MAP_UNI_RSVD;

	return map_type;
}

44 45 46
/* Convert character using the SFU - "Services for Unix" remapping range */
static bool
convert_sfu_char(const __u16 src_char, char *target)
47 48 49 50 51 52
{
	/*
	 * BB: Cannot handle remapping UNI_SLASH until all the calls to
	 *     build_path_from_dentry are modified, as they use slash as
	 *     separator.
	 */
53
	switch (src_char) {
54 55 56
	case UNI_COLON:
		*target = ':';
		break;
57
	case UNI_ASTERISK:
58 59 60 61 62 63 64 65 66 67 68 69 70 71 72
		*target = '*';
		break;
	case UNI_QUESTION:
		*target = '?';
		break;
	case UNI_PIPE:
		*target = '|';
		break;
	case UNI_GRTRTHAN:
		*target = '>';
		break;
	case UNI_LESSTHAN:
		*target = '<';
		break;
	default:
73
		return false;
74
	}
75 76
	return true;
}
77

78 79 80 81
/* Convert character using the SFM - "Services for Mac" remapping range */
static bool
convert_sfm_char(const __u16 src_char, char *target)
{
82 83 84 85
	if (src_char >= 0xF001 && src_char <= 0xF01F) {
		*target = src_char - 0xF000;
		return true;
	}
86 87 88 89
	switch (src_char) {
	case SFM_COLON:
		*target = ':';
		break;
90 91 92
	case SFM_DOUBLEQUOTE:
		*target = '"';
		break;
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110
	case SFM_ASTERISK:
		*target = '*';
		break;
	case SFM_QUESTION:
		*target = '?';
		break;
	case SFM_PIPE:
		*target = '|';
		break;
	case SFM_GRTRTHAN:
		*target = '>';
		break;
	case SFM_LESSTHAN:
		*target = '<';
		break;
	case SFM_SLASH:
		*target = '\\';
		break;
111 112 113 114 115 116
	case SFM_SPACE:
		*target = ' ';
		break;
	case SFM_PERIOD:
		*target = '.';
		break;
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135
	default:
		return false;
	}
	return true;
}


/*
 * cifs_mapchar - convert a host-endian char to proper char in codepage
 * @target - where converted character should be copied
 * @src_char - 2 byte host-endian source character
 * @cp - codepage to which character should be converted
 * @map_type - How should the 7 NTFS/SMB reserved characters be mapped to UCS2?
 *
 * 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
N
Nakajima Akira 已提交
136
cifs_mapchar(char *target, const __u16 *from, const struct nls_table *cp,
137 138 139
	     int maptype)
{
	int len = 1;
N
Nakajima Akira 已提交
140 141 142
	__u16 src_char;

	src_char = *from;
143 144 145 146 147 148

	if ((maptype == SFM_MAP_UNI_RSVD) && convert_sfm_char(src_char, target))
		return len;
	else if ((maptype == SFU_MAP_UNI_RSVD) &&
		  convert_sfu_char(src_char, target))
		return len;
149

150
	/* if character not one of seven in special remap set */
151
	len = cp->uni2char(src_char, target, NLS_MAX_CHARSET_SIZE);
N
Nakajima Akira 已提交
152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168
	if (len <= 0)
		goto surrogate_pair;

	return len;

surrogate_pair:
	/* convert SURROGATE_PAIR and IVS */
	if (strcmp(cp->charset, "utf8"))
		goto unknown;
	len = utf16s_to_utf8s(from, 3, UTF16_LITTLE_ENDIAN, target, 6);
	if (len <= 0)
		goto unknown;
	return len;

unknown:
	*target = '?';
	len = 1;
169
	return len;
170 171 172
}

/*
173
 * cifs_from_utf16 - convert utf16le string to local charset
174 175 176 177 178 179 180
 * @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?
 *
181
 * Convert a little-endian utf16le string (as sent by the server) to a string
182 183 184 185 186 187 188 189
 * 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
190
 * instead of straight UTF16-2. The linux nls routines however aren't able to
191 192 193 194
 * deal with those characters properly. In the event that we get some of
 * those characters, they won't be translated properly.
 */
int
195
cifs_from_utf16(char *to, const __le16 *from, int tolen, int fromlen,
196
		const struct nls_table *codepage, int map_type)
197 198 199 200 201 202
{
	int i, charlen, safelen;
	int outlen = 0;
	int nullsize = nls_nullsize(codepage);
	int fromwords = fromlen / 2;
	char tmp[NLS_MAX_CHARSET_SIZE];
N
Nakajima Akira 已提交
203
	__u16 ftmp[3];		/* ftmp[3] = 3array x 2bytes = 6bytes UTF-16 */
204 205 206 207 208 209 210 211 212

	/*
	 * 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);

213
	for (i = 0; i < fromwords; i++) {
N
Nakajima Akira 已提交
214 215
		ftmp[0] = get_unaligned_le16(&from[i]);
		if (ftmp[0] == 0)
216
			break;
N
Nakajima Akira 已提交
217 218 219 220 221 222 223 224
		if (i + 1 < fromwords)
			ftmp[1] = get_unaligned_le16(&from[i + 1]);
		else
			ftmp[1] = 0;
		if (i + 2 < fromwords)
			ftmp[2] = get_unaligned_le16(&from[i + 2]);
		else
			ftmp[2] = 0;
225

226 227 228 229 230
		/*
		 * check to see if converting this character might make the
		 * conversion bleed into the null terminator
		 */
		if (outlen >= safelen) {
231
			charlen = cifs_mapchar(tmp, ftmp, codepage, map_type);
232 233 234 235 236
			if ((outlen + charlen) > (tolen - nullsize))
				break;
		}

		/* put converted char into 'to' buffer */
237
		charlen = cifs_mapchar(&to[outlen], ftmp, codepage, map_type);
238
		outlen += charlen;
N
Nakajima Akira 已提交
239 240 241 242 243 244 245 246 247 248 249

		/* charlen (=bytes of UTF-8 for 1 character)
		 * 4bytes UTF-8(surrogate pair) is charlen=4
		 *   (4bytes UTF-16 code)
		 * 7-8bytes UTF-8(IVS) is charlen=3+4 or 4+4
		 *   (2 UTF-8 pairs divided to 2 UTF-16 pairs) */
		if (charlen == 4)
			i++;
		else if (charlen >= 5)
			/* 5-6bytes UTF-8 */
			i += 2;
250 251 252 253 254 255 256 257 258
	}

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

	return outlen;
}

L
Linus Torvalds 已提交
259
/*
260
 * NAME:	cifs_strtoUTF16()
L
Linus Torvalds 已提交
261 262 263 264 265
 *
 * FUNCTION:	Convert character string to unicode string
 *
 */
int
266
cifs_strtoUTF16(__le16 *to, const char *from, int len,
L
Linus Torvalds 已提交
267 268 269 270
	      const struct nls_table *codepage)
{
	int charlen;
	int i;
271
	wchar_t wchar_to; /* needed to quiet sparse */
L
Linus Torvalds 已提交
272

F
Frediano Ziglio 已提交
273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293
	/* special case for utf8 to handle no plane0 chars */
	if (!strcmp(codepage->charset, "utf8")) {
		/*
		 * convert utf8 -> utf16, we assume we have enough space
		 * as caller should have assumed conversion does not overflow
		 * in destination len is length in wchar_t units (16bits)
		 */
		i  = utf8s_to_utf16s(from, len, UTF16_LITTLE_ENDIAN,
				       (wchar_t *) to, len);

		/* if success terminate and exit */
		if (i >= 0)
			goto success;
		/*
		 * if fails fall back to UCS encoding as this
		 * function should not return negative values
		 * currently can fail only if source contains
		 * invalid encoded characters
		 */
	}

L
Linus Torvalds 已提交
294
	for (i = 0; len && *from; i++, from += charlen, len -= charlen) {
295
		charlen = codepage->char2uni(from, len, &wchar_to);
L
Linus Torvalds 已提交
296
		if (charlen < 1) {
297 298
			cifs_dbg(VFS, "strtoUTF16: char2uni of 0x%x returned %d\n",
				 *from, charlen);
299
			/* A question mark */
300
			wchar_to = 0x003f;
L
Linus Torvalds 已提交
301
			charlen = 1;
302 303
		}
		put_unaligned_le16(wchar_to, &to[i]);
L
Linus Torvalds 已提交
304 305
	}

F
Frediano Ziglio 已提交
306
success:
307
	put_unaligned_le16(0, &to[i]);
L
Linus Torvalds 已提交
308 309 310
	return i;
}

N
Nakajima Akira 已提交
311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350
/*
 * cifs_utf16_bytes - how long will a string be after conversion?
 * @utf16 - pointer to input string
 * @maxbytes - don't go past this many bytes of input string
 * @codepage - destination codepage
 *
 * Walk a utf16le 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.
 */
int
cifs_utf16_bytes(const __le16 *from, int maxbytes,
		const struct nls_table *codepage)
{
	int i;
	int charlen, outlen = 0;
	int maxwords = maxbytes / 2;
	char tmp[NLS_MAX_CHARSET_SIZE];
	__u16 ftmp[3];

	for (i = 0; i < maxwords; i++) {
		ftmp[0] = get_unaligned_le16(&from[i]);
		if (ftmp[0] == 0)
			break;
		if (i + 1 < maxwords)
			ftmp[1] = get_unaligned_le16(&from[i + 1]);
		else
			ftmp[1] = 0;
		if (i + 2 < maxwords)
			ftmp[2] = get_unaligned_le16(&from[i + 2]);
		else
			ftmp[2] = 0;

		charlen = cifs_mapchar(tmp, ftmp, codepage, NO_MAP_UNI_RSVD);
		outlen += charlen;
	}

	return outlen;
}

351
/*
352 353
 * cifs_strndup_from_utf16 - copy a string from wire format to the local
 * codepage
354 355 356 357 358 359 360 361 362 363
 * @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 *
364 365
cifs_strndup_from_utf16(const char *src, const int maxlen,
			const bool is_unicode, const struct nls_table *codepage)
366 367 368 369 370
{
	int len;
	char *dst;

	if (is_unicode) {
371
		len = cifs_utf16_bytes((__le16 *) src, maxlen, codepage);
372 373 374 375
		len += nls_nullsize(codepage);
		dst = kmalloc(len, GFP_KERNEL);
		if (!dst)
			return NULL;
376
		cifs_from_utf16(dst, (__le16 *) src, len, maxlen, codepage,
377
			       NO_MAP_UNI_RSVD);
378 379 380 381 382 383 384 385 386 387 388 389
	} else {
		len = strnlen(src, maxlen);
		len++;
		dst = kmalloc(len, GFP_KERNEL);
		if (!dst)
			return NULL;
		strlcpy(dst, src, len);
	}

	return dst;
}

390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419
static __le16 convert_to_sfu_char(char src_char)
{
	__le16 dest_char;

	switch (src_char) {
	case ':':
		dest_char = cpu_to_le16(UNI_COLON);
		break;
	case '*':
		dest_char = cpu_to_le16(UNI_ASTERISK);
		break;
	case '?':
		dest_char = cpu_to_le16(UNI_QUESTION);
		break;
	case '<':
		dest_char = cpu_to_le16(UNI_LESSTHAN);
		break;
	case '>':
		dest_char = cpu_to_le16(UNI_GRTRTHAN);
		break;
	case '|':
		dest_char = cpu_to_le16(UNI_PIPE);
		break;
	default:
		dest_char = 0;
	}

	return dest_char;
}

420
static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
421 422 423
{
	__le16 dest_char;

424 425 426 427
	if (src_char >= 0x01 && src_char <= 0x1F) {
		dest_char = cpu_to_le16(src_char + 0xF000);
		return dest_char;
	}
428 429 430 431
	switch (src_char) {
	case ':':
		dest_char = cpu_to_le16(SFM_COLON);
		break;
432 433 434
	case '"':
		dest_char = cpu_to_le16(SFM_DOUBLEQUOTE);
		break;
435 436 437 438 439 440 441 442 443 444 445 446 447 448 449
	case '*':
		dest_char = cpu_to_le16(SFM_ASTERISK);
		break;
	case '?':
		dest_char = cpu_to_le16(SFM_QUESTION);
		break;
	case '<':
		dest_char = cpu_to_le16(SFM_LESSTHAN);
		break;
	case '>':
		dest_char = cpu_to_le16(SFM_GRTRTHAN);
		break;
	case '|':
		dest_char = cpu_to_le16(SFM_PIPE);
		break;
450 451 452 453 454 455 456 457 458 459 460 461
	case '.':
		if (end_of_string)
			dest_char = cpu_to_le16(SFM_PERIOD);
		else
			dest_char = 0;
		break;
	case ' ':
		if (end_of_string)
			dest_char = cpu_to_le16(SFM_SPACE);
		else
			dest_char = 0;
		break;
462 463 464 465 466 467 468
	default:
		dest_char = 0;
	}

	return dest_char;
}

469 470 471 472 473 474 475
/*
 * 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
476
cifsConvertToUTF16(__le16 *target, const char *source, int srclen,
477
		 const struct nls_table *cp, int map_chars)
478
{
479 480
	int i, charlen;
	int j = 0;
481
	char src_char;
482 483
	__le16 dst_char;
	wchar_t tmp;
N
Nakajima Akira 已提交
484 485 486
	wchar_t *wchar_to;	/* UTF-16 */
	int ret;
	unicode_t u;
487

488
	if (map_chars == NO_MAP_UNI_RSVD)
489
		return cifs_strtoUTF16(target, source, PATH_MAX, cp);
490

N
Nakajima Akira 已提交
491 492
	wchar_to = kzalloc(6, GFP_KERNEL);

493
	for (i = 0; i < srclen; j++) {
494
		src_char = source[i];
495
		charlen = 1;
496 497 498

		/* check if end of string */
		if (src_char == 0)
499
			goto ctoUTF16_out;
500 501 502 503

		/* see if we must remap this char */
		if (map_chars == SFU_MAP_UNI_RSVD)
			dst_char = convert_to_sfu_char(src_char);
504 505 506 507 508 509 510 511 512 513
		else if (map_chars == SFM_MAP_UNI_RSVD) {
			bool end_of_string;

			if (i == srclen - 1)
				end_of_string = true;
			else
				end_of_string = false;

			dst_char = convert_to_sfm_char(src_char, end_of_string);
		} else
514
			dst_char = 0;
515 516 517 518 519
		/*
		 * 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.
		 */
520
		if (dst_char == 0) {
521 522 523
			charlen = cp->char2uni(source + i, srclen - i, &tmp);
			dst_char = cpu_to_le16(tmp);

524 525 526 527
			/*
			 * if no match, use question mark, which at least in
			 * some cases serves as wild card
			 */
N
Nakajima Akira 已提交
528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567
			if (charlen > 0)
				goto ctoUTF16;

			/* convert SURROGATE_PAIR */
			if (strcmp(cp->charset, "utf8") || !wchar_to)
				goto unknown;
			if (*(source + i) & 0x80) {
				charlen = utf8_to_utf32(source + i, 6, &u);
				if (charlen < 0)
					goto unknown;
			} else
				goto unknown;
			ret  = utf8s_to_utf16s(source + i, charlen,
					       UTF16_LITTLE_ENDIAN,
					       wchar_to, 6);
			if (ret < 0)
				goto unknown;

			i += charlen;
			dst_char = cpu_to_le16(*wchar_to);
			if (charlen <= 3)
				/* 1-3bytes UTF-8 to 2bytes UTF-16 */
				put_unaligned(dst_char, &target[j]);
			else if (charlen == 4) {
				/* 4bytes UTF-8(surrogate pair) to 4bytes UTF-16
				 * 7-8bytes UTF-8(IVS) divided to 2 UTF-16
				 *   (charlen=3+4 or 4+4) */
				put_unaligned(dst_char, &target[j]);
				dst_char = cpu_to_le16(*(wchar_to + 1));
				j++;
				put_unaligned(dst_char, &target[j]);
			} else if (charlen >= 5) {
				/* 5-6bytes UTF-8 to 6bytes UTF-16 */
				put_unaligned(dst_char, &target[j]);
				dst_char = cpu_to_le16(*(wchar_to + 1));
				j++;
				put_unaligned(dst_char, &target[j]);
				dst_char = cpu_to_le16(*(wchar_to + 2));
				j++;
				put_unaligned(dst_char, &target[j]);
568
			}
N
Nakajima Akira 已提交
569 570 571 572 573
			continue;

unknown:
			dst_char = cpu_to_le16(0x003f);
			charlen = 1;
574
		}
N
Nakajima Akira 已提交
575 576

ctoUTF16:
577 578 579 580 581
		/*
		 * character may take more than one byte in the source string,
		 * but will take exactly two bytes in the target string
		 */
		i += charlen;
582
		put_unaligned(dst_char, &target[j]);
583 584
	}

585
ctoUTF16_out:
586
	put_unaligned(0, &target[j]); /* Null terminate target unicode string */
N
Nakajima Akira 已提交
587
	kfree(wchar_to);
588
	return j;
589
}
590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650

#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 */