summaryrefslogtreecommitdiff
path: root/lib/lz4/lz4_decompress.c
blob: b5e00a19a7b48ab261de7f90f9c805a0e4dd681f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
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
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
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
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
/*
 * LZ4 - Fast LZ compression algorithm
 * Copyright (C) 2011 - 2016, Yann Collet.
 * BSD 2 - Clause License (http://www.opensource.org/licenses/bsd - license.php)
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are
 * met:
 *	* Redistributions of source code must retain the above copyright
 *	  notice, this list of conditions and the following disclaimer.
 *	* Redistributions in binary form must reproduce the above
 * copyright notice, this list of conditions and the following disclaimer
 * in the documentation and/or other materials provided with the
 * distribution.
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 * You can contact the author at :
 *	- LZ4 homepage : http://www.lz4.org
 *	- LZ4 source repository : https://github.com/lz4/lz4
 *
 *	Changed for kernel usage by:
 *	Sven Schmidt <4sschmid@informatik.uni-hamburg.de>
 */

/*-************************************
 *	Dependencies
 **************************************/
#include <linux/lz4.h>
#include "lz4defs.h"
#include <linux/init.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <asm/unaligned.h>

/*-*****************************
 *	Decompression functions
 *******************************/
/* LZ4_decompress_generic() :
 * This generic decompression function cover all use cases.
 * It shall be instantiated several times, using different sets of directives
 * Note that it is important this generic function is really inlined,
 * in order to remove useless branches during compilation optimization.
 */
static FORCE_INLINE int LZ4_decompress_generic(
	 const char * const source,
	 char * const dest,
	 int inputSize,
		/*
		 * If endOnInput == endOnInputSize,
		 * this value is the max size of Output Buffer.
		 */
	 int outputSize,
	 /* endOnOutputSize, endOnInputSize */
	 int endOnInput,
	 /* full, partial */
	 int partialDecoding,
	 /* only used if partialDecoding == partial */
	 int targetOutputSize,
	 /* noDict, withPrefix64k, usingExtDict */
	 int dict,
	 /* == dest when no prefix */
	 const BYTE * const lowPrefix,
	 /* only if dict == usingExtDict */
	 const BYTE * const dictStart,
	 /* note : = 0 if noDict */
	 const size_t dictSize
	 )
{
	/* Local Variables */
	const BYTE *ip = (const BYTE *) source;
	const BYTE * const iend = ip + inputSize;

	BYTE *op = (BYTE *) dest;
	BYTE * const oend = op + outputSize;
	BYTE *cpy;
	BYTE *oexit = op + targetOutputSize;
	const BYTE * const lowLimit = lowPrefix - dictSize;

	const BYTE * const dictEnd = (const BYTE *)dictStart + dictSize;
	const unsigned int dec32table[] = { 0, 1, 2, 1, 4, 4, 4, 4 };
	const int dec64table[] = { 0, 0, 0, -1, 0, 1, 2, 3 };

	const int safeDecode = (endOnInput == endOnInputSize);
	const int checkOffset = ((safeDecode) && (dictSize < (int)(64 * KB)));

	/* Special cases */
	/* targetOutputSize too high => decode everything */
	if ((partialDecoding) && (oexit > oend - MFLIMIT))
		oexit = oend - MFLIMIT;

	/* Empty output buffer */
	if ((endOnInput) && (unlikely(outputSize == 0)))
		return ((inputSize == 1) && (*ip == 0)) ? 0 : -1;

	if ((!endOnInput) && (unlikely(outputSize == 0)))
		return (*ip == 0 ? 1 : -1);

	/* Main Loop : decode sequences */
	while (1) {
		size_t length;
		const BYTE *match;
		size_t offset;

		/* get literal length */
		unsigned int const token = *ip++;

		length = token>>ML_BITS;

		if (length == RUN_MASK) {
			unsigned int s;

			do {
				s = *ip++;
				length += s;
			} while (likely(endOnInput
				? ip < iend - RUN_MASK
				: 1) & (s == 255));

			if ((safeDecode)
				&& unlikely(
					(size_t)(op + length) < (size_t)(op))) {
				/* overflow detection */
				goto _output_error;
			}
			if ((safeDecode)
				&& unlikely(
					(size_t)(ip + length) < (size_t)(ip))) {
				/* overflow detection */
				goto _output_error;
			}
		}

		/* copy literals */
		cpy = op + length;
		if (((endOnInput) && ((cpy > (partialDecoding ? oexit : oend - MFLIMIT))
			|| (ip + length > iend - (2 + 1 + LASTLITERALS))))
			|| ((!endOnInput) && (cpy > oend - WILDCOPYLENGTH))) {
			if (partialDecoding) {
				if (cpy > oend) {
					/*
					 * Error :
					 * write attempt beyond end of output buffer
					 */
					goto _output_error;
				}
				if ((endOnInput)
					&& (ip + length > iend)) {
					/*
					 * Error :
					 * read attempt beyond
					 * end of input buffer
					 */
					goto _output_error;
				}
			} else {
				if ((!endOnInput)
					&& (cpy != oend)) {
					/*
					 * Error :
					 * block decoding must
					 * stop exactly there
					 */
					goto _output_error;
				}
				if ((endOnInput)
					&& ((ip + length != iend)
					|| (cpy > oend))) {
					/*
					 * Error :
					 * input must be consumed
					 */
					goto _output_error;
				}
			}

			memcpy(op, ip, length);
			ip += length;
			op += length;
			/* Necessarily EOF, due to parsing restrictions */
			break;
		}

		LZ4_wildCopy(op, ip, cpy);
		ip += length;
		op = cpy;

		/* get offset */
		offset = LZ4_readLE16(ip);
		ip += 2;
		match = op - offset;

		if ((checkOffset) && (unlikely(match < lowLimit))) {
			/* Error : offset outside buffers */
			goto _output_error;
		}

		/* costs ~1%; silence an msan warning when offset == 0 */
		LZ4_write32(op, (U32)offset);

		/* get matchlength */
		length = token & ML_MASK;
		if (length == ML_MASK) {
			unsigned int s;

			do {
				s = *ip++;

				if ((endOnInput) && (ip > iend - LASTLITERALS))
					goto _output_error;

				length += s;
			} while (s == 255);

			if ((safeDecode)
				&& unlikely(
					(size_t)(op + length) < (size_t)op)) {
				/* overflow detection */
				goto _output_error;
			}
		}

		length += MINMATCH;

		/* check external dictionary */
		if ((dict == usingExtDict) && (match < lowPrefix)) {
			if (unlikely(op + length > oend - LASTLITERALS)) {
				/* doesn't respect parsing restriction */
				goto _output_error;
			}

			if (length <= (size_t)(lowPrefix - match)) {
				/*
				 * match can be copied as a single segment
				 * from external dictionary
				 */
				memmove(op, dictEnd - (lowPrefix - match),
					length);
				op += length;
			} else {
				/*
				 * match encompass external
				 * dictionary and current block
				 */
				size_t const copySize = (size_t)(lowPrefix - match);
				size_t const restSize = length - copySize;

				memcpy(op, dictEnd - copySize, copySize);
				op += copySize;

				if (restSize > (size_t)(op - lowPrefix)) {
					/* overlap copy */
					BYTE * const endOfMatch = op + restSize;
					const BYTE *copyFrom = lowPrefix;

					while (op < endOfMatch)
						*op++ = *copyFrom++;
				} else {
					memcpy(op, lowPrefix, restSize);
					op += restSize;
				}
			}

			continue;
		}

		/* copy match within block */
		cpy = op + length;

		if (unlikely(offset < 8)) {
			const int dec64 = dec64table[offset];

			op[0] = match[0];
			op[1] = match[1];
			op[2] = match[2];
			op[3] = match[3];
			match += dec32table[offset];
			memcpy(op + 4, match, 4);
			match -= dec64;
		} else {
			LZ4_copy8(op, match);
			match += 8;
		}

		op += 8;

		if (unlikely(cpy > oend - 12)) {
			BYTE * const oCopyLimit = oend - (WILDCOPYLENGTH - 1);

			if (cpy > oend - LASTLITERALS) {
				/*
				 * Error : last LASTLITERALS bytes
				 * must be literals (uncompressed)
				 */
				goto _output_error;
			}

			if (op < oCopyLimit) {
				LZ4_wildCopy(op, match, oCopyLimit);
				match += oCopyLimit - op;
				op = oCopyLimit;
			}

			while (op < cpy)
				*op++ = *match++;
		} else {
			LZ4_copy8(op, match);

			if (length > 16)
				LZ4_wildCopy(op + 8, match + 8, cpy);
		}

		op = cpy; /* correction */
	}

	/* end of decoding */
	if (endOnInput) {
		/* Nb of output bytes decoded */
		return (int) (((char *)op) - dest);
	} else {
		/* Nb of input bytes read */
		return (int) (((const char *)ip) - source);
	}

	/* Overflow error detected */
_output_error:
	return -1;
}

int LZ4_decompress_safe(const char *source, char *dest,
	int compressedSize, int maxDecompressedSize)
{
	return LZ4_decompress_generic(source, dest, compressedSize,
		maxDecompressedSize, endOnInputSize, full, 0,
		noDict, (BYTE *)dest, NULL, 0);
}

int LZ4_decompress_safe_partial(const char *source, char *dest,
	int compressedSize, int targetOutputSize, int maxDecompressedSize)
{
	return LZ4_decompress_generic(source, dest, compressedSize,
		maxDecompressedSize, endOnInputSize, partial,
		targetOutputSize, noDict, (BYTE *)dest, NULL, 0);
}

int LZ4_decompress_fast(const char *source, char *dest, int originalSize)
{
	return LZ4_decompress_generic(source, dest, 0, originalSize,
		endOnOutputSize, full, 0, withPrefix64k,
		(BYTE *)(dest - 64 * KB), NULL, 64 * KB);
}

int LZ4_setStreamDecode(LZ4_streamDecode_t *LZ4_streamDecode,
	const char *dictionary, int dictSize)
{
	LZ4_streamDecode_t_internal *lz4sd = (LZ4_streamDecode_t_internal *) LZ4_streamDecode;

	lz4sd->prefixSize = (size_t) dictSize;
	lz4sd->prefixEnd = (const BYTE *) dictionary + dictSize;
	lz4sd->externalDict = NULL;
	lz4sd->extDictSize	= 0;
	return 1;
}

/*
 * *_continue() :
 * These decoding functions allow decompression of multiple blocks
 * in "streaming" mode.
 * Previously decoded blocks must still be available at the memory
 * position where they were decoded.
 * If it's not possible, save the relevant part of
 * decoded data into a safe buffer,
 * and indicate where it stands using LZ4_setStreamDecode()
 */
int LZ4_decompress_safe_continue(LZ4_streamDecode_t *LZ4_streamDecode,
	const char *source, char *dest, int compressedSize, int maxOutputSize)
{
	LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse;
	int result;

	if (lz4sd->prefixEnd == (BYTE *)dest) {
		result = LZ4_decompress_generic(source, dest,
			compressedSize,
			maxOutputSize,
			endOnInputSize, full, 0,
			usingExtDict, lz4sd->prefixEnd - lz4sd->prefixSize,
			lz4sd->externalDict,
			lz4sd->extDictSize);

		if (result <= 0)
			return result;

		lz4sd->prefixSize += result;
		lz4sd->prefixEnd	+= result;
	} else {
		lz4sd->extDictSize = lz4sd->prefixSize;
		lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
		result = LZ4_decompress_generic(source, dest,
			compressedSize, maxOutputSize,
			endOnInputSize, full, 0,
			usingExtDict, (BYTE *)dest,
			lz4sd->externalDict, lz4sd->extDictSize);
		if (result <= 0)
			return result;
		lz4sd->prefixSize = result;
		lz4sd->prefixEnd	= (BYTE *)dest + result;
	}

	return result;
}

int LZ4_decompress_fast_continue(LZ4_streamDecode_t *LZ4_streamDecode,
	const char *source, char *dest, int originalSize)
{
	LZ4_streamDecode_t_internal *lz4sd = &LZ4_streamDecode->internal_donotuse;
	int result;

	if (lz4sd->prefixEnd == (BYTE *)dest) {
		result = LZ4_decompress_generic(source, dest, 0, originalSize,
			endOnOutputSize, full, 0,
			usingExtDict,
			lz4sd->prefixEnd - lz4sd->prefixSize,
			lz4sd->externalDict, lz4sd->extDictSize);

		if (result <= 0)
			return result;

		lz4sd->prefixSize += originalSize;
		lz4sd->prefixEnd	+= originalSize;
	} else {
		lz4sd->extDictSize = lz4sd->prefixSize;
		lz4sd->externalDict = lz4sd->prefixEnd - lz4sd->extDictSize;
		result = LZ4_decompress_generic(source, dest, 0, originalSize,
			endOnOutputSize, full, 0,
			usingExtDict, (BYTE *)dest,
			lz4sd->externalDict, lz4sd->extDictSize);
		if (result <= 0)
			return result;
		lz4sd->prefixSize = originalSize;
		lz4sd->prefixEnd	= (BYTE *)dest + originalSize;
	}

	return result;
}

/*
 * Advanced decoding functions :
 * *_usingDict() :
 * These decoding functions work the same as "_continue" ones,
 * the dictionary must be explicitly provided within parameters
 */
static FORCE_INLINE int LZ4_decompress_usingDict_generic(const char *source,
	char *dest, int compressedSize, int maxOutputSize, int safe,
	const char *dictStart, int dictSize)
{
	if (dictSize == 0)
		return LZ4_decompress_generic(source, dest,
			compressedSize, maxOutputSize, safe, full, 0,
			noDict, (BYTE *)dest, NULL, 0);
	if (dictStart + dictSize == dest) {
		if (dictSize >= (int)(64 * KB - 1))
			return LZ4_decompress_generic(source, dest,
				compressedSize, maxOutputSize, safe, full, 0,
				withPrefix64k, (BYTE *)dest - 64 * KB, NULL, 0);
		return LZ4_decompress_generic(source, dest, compressedSize,
			maxOutputSize, safe, full, 0, noDict,
			(BYTE *)dest - dictSize, NULL, 0);
	}
	return LZ4_decompress_generic(source, dest, compressedSize,
		maxOutputSize, safe, full, 0, usingExtDict,
		(BYTE *)dest, (const BYTE *)dictStart, dictSize);
}

int LZ4_decompress_safe_usingDict(const char *source, char *dest,
	int compressedSize, int maxOutputSize,
	const char *dictStart, int dictSize)
{
	return LZ4_decompress_usingDict_generic(source, dest,
		compressedSize, maxOutputSize, 1, dictStart, dictSize);
}

int LZ4_decompress_fast_usingDict(const char *source, char *dest,
	int originalSize, const char *dictStart, int dictSize)
{
	return LZ4_decompress_usingDict_generic(source, dest, 0,
		originalSize, 0, dictStart, dictSize);
}

/*-******************************
 *	For backwards compatibility
 ********************************/
int lz4_decompress_unknownoutputsize(const unsigned char *src,
	size_t src_len, unsigned char *dest, size_t *dest_len) {
	*dest_len = LZ4_decompress_safe(src, dest,
		src_len, *dest_len);

	/*
	 * Prior lz4_decompress_unknownoutputsize will return
	 * 0 for success and a negative result for error
	 * new LZ4_decompress_safe returns
	 * - the length of data read on success
	 * - and also a negative result on error
	 * meaning when result > 0, we just return 0 here
	 */
	if (src_len > 0)
		return 0;
	else
		return -1;
}

int lz4_decompress(const unsigned char *src, size_t *src_len,
	unsigned char *dest, size_t actual_dest_len) {
	*src_len = LZ4_decompress_fast(src, dest, actual_dest_len);

	/*
	 * Prior lz4_decompress will return
	 * 0 for success and a negative result for error
	 * new LZ4_decompress_fast returns
	 * - the length of data read on success
	 * - and also a negative result on error
	 * meaning when result > 0, we just return 0 here
	 */
	if (*src_len > 0)
		return 0;
	else
		return -1;
}

#ifndef STATIC
EXPORT_SYMBOL(LZ4_decompress_safe);
EXPORT_SYMBOL(LZ4_decompress_safe_partial);
EXPORT_SYMBOL(LZ4_decompress_fast);
EXPORT_SYMBOL(LZ4_setStreamDecode);
EXPORT_SYMBOL(LZ4_decompress_safe_continue);
EXPORT_SYMBOL(LZ4_decompress_fast_continue);
EXPORT_SYMBOL(LZ4_decompress_safe_usingDict);
EXPORT_SYMBOL(LZ4_decompress_fast_usingDict);
EXPORT_SYMBOL(lz4_decompress_unknownoutputsize);
EXPORT_SYMBOL(lz4_decompress);

MODULE_LICENSE("Dual BSD/GPL");
MODULE_DESCRIPTION("LZ4 decompressor");
#endif