Source

APKinspector / androguard / classification / libsimilarity / sources / xz-5.0.2 / src / common / tuklib_integer.h

The default branch has multiple heads

Full commit
  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
///////////////////////////////////////////////////////////////////////////////
//
/// \file       tuklib_integer.h
/// \brief      Various integer and bit operations
///
/// This file provides macros or functions to do some basic integer and bit
/// operations.
///
/// Endianness related integer operations (XX = 16, 32, or 64; Y = b or l):
///   - Byte swapping: bswapXX(num)
///   - Byte order conversions to/from native: convXXYe(num)
///   - Aligned reads: readXXYe(ptr)
///   - Aligned writes: writeXXYe(ptr, num)
///   - Unaligned reads (16/32-bit only): unaligned_readXXYe(ptr)
///   - Unaligned writes (16/32-bit only): unaligned_writeXXYe(ptr, num)
///
/// Since they can macros, the arguments should have no side effects since
/// they may be evaluated more than once.
///
/// \todo       PowerPC and possibly some other architectures support
///             byte swapping load and store instructions. This file
///             doesn't take advantage of those instructions.
///
/// Bit scan operations for non-zero 32-bit integers:
///   - Bit scan reverse (find highest non-zero bit): bsr32(num)
///   - Count leading zeros: clz32(num)
///   - Count trailing zeros: ctz32(num)
///   - Bit scan forward (simply an alias for ctz32()): bsf32(num)
///
/// The above bit scan operations return 0-31. If num is zero,
/// the result is undefined.
//
//  Authors:    Lasse Collin
//              Joachim Henke
//
//  This file has been put into the public domain.
//  You can do whatever you want with this file.
//
///////////////////////////////////////////////////////////////////////////////

#ifndef TUKLIB_INTEGER_H
#define TUKLIB_INTEGER_H

#include "tuklib_common.h"


////////////////////////////////////////
// Operating system specific features //
////////////////////////////////////////

#if defined(HAVE_BYTESWAP_H)
	// glibc, uClibc, dietlibc
#	include <byteswap.h>
#	ifdef HAVE_BSWAP_16
#		define bswap16(num) bswap_16(num)
#	endif
#	ifdef HAVE_BSWAP_32
#		define bswap32(num) bswap_32(num)
#	endif
#	ifdef HAVE_BSWAP_64
#		define bswap64(num) bswap_64(num)
#	endif

#elif defined(HAVE_SYS_ENDIAN_H)
	// *BSDs and Darwin
#	include <sys/endian.h>

#elif defined(HAVE_SYS_BYTEORDER_H)
	// Solaris
#	include <sys/byteorder.h>
#	ifdef BSWAP_16
#		define bswap16(num) BSWAP_16(num)
#	endif
#	ifdef BSWAP_32
#		define bswap32(num) BSWAP_32(num)
#	endif
#	ifdef BSWAP_64
#		define bswap64(num) BSWAP_64(num)
#	endif
#	ifdef BE_16
#		define conv16be(num) BE_16(num)
#	endif
#	ifdef BE_32
#		define conv32be(num) BE_32(num)
#	endif
#	ifdef BE_64
#		define conv64be(num) BE_64(num)
#	endif
#	ifdef LE_16
#		define conv16le(num) LE_16(num)
#	endif
#	ifdef LE_32
#		define conv32le(num) LE_32(num)
#	endif
#	ifdef LE_64
#		define conv64le(num) LE_64(num)
#	endif
#endif


///////////////////
// Byte swapping //
///////////////////

#ifndef bswap16
#	define bswap16(num) \
		(((uint16_t)(num) << 8) | ((uint16_t)(num) >> 8))
#endif

#ifndef bswap32
#	define bswap32(num) \
		( (((uint32_t)(num) << 24)                       ) \
		| (((uint32_t)(num) <<  8) & UINT32_C(0x00FF0000)) \
		| (((uint32_t)(num) >>  8) & UINT32_C(0x0000FF00)) \
		| (((uint32_t)(num) >> 24)                       ) )
#endif

#ifndef bswap64
#	define bswap64(num) \
		( (((uint64_t)(num) << 56)                               ) \
		| (((uint64_t)(num) << 40) & UINT64_C(0x00FF000000000000)) \
		| (((uint64_t)(num) << 24) & UINT64_C(0x0000FF0000000000)) \
		| (((uint64_t)(num) <<  8) & UINT64_C(0x000000FF00000000)) \
		| (((uint64_t)(num) >>  8) & UINT64_C(0x00000000FF000000)) \
		| (((uint64_t)(num) >> 24) & UINT64_C(0x0000000000FF0000)) \
		| (((uint64_t)(num) >> 40) & UINT64_C(0x000000000000FF00)) \
		| (((uint64_t)(num) >> 56)                               ) )
#endif

// Define conversion macros using the basic byte swapping macros.
#ifdef WORDS_BIGENDIAN
#	ifndef conv16be
#		define conv16be(num) ((uint16_t)(num))
#	endif
#	ifndef conv32be
#		define conv32be(num) ((uint32_t)(num))
#	endif
#	ifndef conv64be
#		define conv64be(num) ((uint64_t)(num))
#	endif
#	ifndef conv16le
#		define conv16le(num) bswap16(num)
#	endif
#	ifndef conv32le
#		define conv32le(num) bswap32(num)
#	endif
#	ifndef conv64le
#		define conv64le(num) bswap64(num)
#	endif
#else
#	ifndef conv16be
#		define conv16be(num) bswap16(num)
#	endif
#	ifndef conv32be
#		define conv32be(num) bswap32(num)
#	endif
#	ifndef conv64be
#		define conv64be(num) bswap64(num)
#	endif
#	ifndef conv16le
#		define conv16le(num) ((uint16_t)(num))
#	endif
#	ifndef conv32le
#		define conv32le(num) ((uint32_t)(num))
#	endif
#	ifndef conv64le
#		define conv64le(num) ((uint64_t)(num))
#	endif
#endif


//////////////////////////////
// Aligned reads and writes //
//////////////////////////////

static inline uint16_t
read16be(const uint8_t *buf)
{
	uint16_t num = *(const uint16_t *)buf;
	return conv16be(num);
}


static inline uint16_t
read16le(const uint8_t *buf)
{
	uint16_t num = *(const uint16_t *)buf;
	return conv16le(num);
}


static inline uint32_t
read32be(const uint8_t *buf)
{
	uint32_t num = *(const uint32_t *)buf;
	return conv32be(num);
}


static inline uint32_t
read32le(const uint8_t *buf)
{
	uint32_t num = *(const uint32_t *)buf;
	return conv32le(num);
}


static inline uint64_t
read64be(const uint8_t *buf)
{
	uint64_t num = *(const uint64_t *)buf;
	return conv64be(num);
}


static inline uint64_t
read64le(const uint8_t *buf)
{
	uint64_t num = *(const uint64_t *)buf;
	return conv64le(num);
}


// NOTE: Possible byte swapping must be done in a macro to allow GCC
// to optimize byte swapping of constants when using glibc's or *BSD's
// byte swapping macros. The actual write is done in an inline function
// to make type checking of the buf pointer possible similarly to readXXYe()
// functions.

#define write16be(buf, num) write16ne((buf), conv16be(num))
#define write16le(buf, num) write16ne((buf), conv16le(num))
#define write32be(buf, num) write32ne((buf), conv32be(num))
#define write32le(buf, num) write32ne((buf), conv32le(num))
#define write64be(buf, num) write64ne((buf), conv64be(num))
#define write64le(buf, num) write64ne((buf), conv64le(num))


static inline void
write16ne(uint8_t *buf, uint16_t num)
{
	*(uint16_t *)buf = num;
	return;
}


static inline void
write32ne(uint8_t *buf, uint32_t num)
{
	*(uint32_t *)buf = num;
	return;
}


static inline void
write64ne(uint8_t *buf, uint64_t num)
{
	*(uint64_t *)buf = num;
	return;
}


////////////////////////////////
// Unaligned reads and writes //
////////////////////////////////

// NOTE: TUKLIB_FAST_UNALIGNED_ACCESS indicates only support for 16-bit and
// 32-bit unaligned integer loads and stores. It's possible that 64-bit
// unaligned access doesn't work or is slower than byte-by-byte access.
// Since unaligned 64-bit is probably not needed as often as 16-bit or
// 32-bit, we simply don't support 64-bit unaligned access for now.
#ifdef TUKLIB_FAST_UNALIGNED_ACCESS
#	define unaligned_read16be read16be
#	define unaligned_read16le read16le
#	define unaligned_read32be read32be
#	define unaligned_read32le read32le
#	define unaligned_write16be write16be
#	define unaligned_write16le write16le
#	define unaligned_write32be write32be
#	define unaligned_write32le write32le

#else

static inline uint16_t
unaligned_read16be(const uint8_t *buf)
{
	uint16_t num = ((uint16_t)buf[0] << 8) | (uint16_t)buf[1];
	return num;
}


static inline uint16_t
unaligned_read16le(const uint8_t *buf)
{
	uint16_t num = ((uint16_t)buf[0]) | ((uint16_t)buf[1] << 8);
	return num;
}


static inline uint32_t
unaligned_read32be(const uint8_t *buf)
{
	uint32_t num = (uint32_t)buf[0] << 24;
	num |= (uint32_t)buf[1] << 16;
	num |= (uint32_t)buf[2] << 8;
	num |= (uint32_t)buf[3];
	return num;
}


static inline uint32_t
unaligned_read32le(const uint8_t *buf)
{
	uint32_t num = (uint32_t)buf[0];
	num |= (uint32_t)buf[1] << 8;
	num |= (uint32_t)buf[2] << 16;
	num |= (uint32_t)buf[3] << 24;
	return num;
}


static inline void
unaligned_write16be(uint8_t *buf, uint16_t num)
{
	buf[0] = num >> 8;
	buf[1] = num;
	return;
}


static inline void
unaligned_write16le(uint8_t *buf, uint16_t num)
{
	buf[0] = num;
	buf[1] = num >> 8;
	return;
}


static inline void
unaligned_write32be(uint8_t *buf, uint32_t num)
{
	buf[0] = num >> 24;
	buf[1] = num >> 16;
	buf[2] = num >> 8;
	buf[3] = num;
	return;
}


static inline void
unaligned_write32le(uint8_t *buf, uint32_t num)
{
	buf[0] = num;
	buf[1] = num >> 8;
	buf[2] = num >> 16;
	buf[3] = num >> 24;
	return;
}

#endif


static inline uint32_t
bsr32(uint32_t n)
{
	// Check for ICC first, since it tends to define __GNUC__ too.
#if defined(__INTEL_COMPILER)
	return _bit_scan_reverse(n);

#elif TUKLIB_GNUC_REQ(3, 4) && UINT_MAX == UINT32_MAX
	// GCC >= 3.4 has __builtin_clz(), which gives good results on
	// multiple architectures. On x86, __builtin_clz() ^ 31U becomes
	// either plain BSR (so the XOR gets optimized away) or LZCNT and
	// XOR (if -march indicates that SSE4a instructions are supported).
	return __builtin_clz(n) ^ 31U;

#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
	uint32_t i;
	__asm__("bsrl %1, %0" : "=r" (i) : "rm" (n));
	return i;

#elif defined(_MSC_VER) && _MSC_VER >= 1400
	// MSVC isn't supported by tuklib, but since this code exists,
	// it doesn't hurt to have it here anyway.
	uint32_t i;
	_BitScanReverse((DWORD *)&i, n);
	return i;

#else
	uint32_t i = 31;

	if ((n & UINT32_C(0xFFFF0000)) == 0) {
		n <<= 16;
		i = 15;
	}

	if ((n & UINT32_C(0xFF000000)) == 0) {
		n <<= 8;
		i -= 8;
	}

	if ((n & UINT32_C(0xF0000000)) == 0) {
		n <<= 4;
		i -= 4;
	}

	if ((n & UINT32_C(0xC0000000)) == 0) {
		n <<= 2;
		i -= 2;
	}

	if ((n & UINT32_C(0x80000000)) == 0)
		--i;

	return i;
#endif
}


static inline uint32_t
clz32(uint32_t n)
{
#if defined(__INTEL_COMPILER)
	return _bit_scan_reverse(n) ^ 31U;

#elif TUKLIB_GNUC_REQ(3, 4) && UINT_MAX == UINT32_MAX
	return __builtin_clz(n);

#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
	uint32_t i;
	__asm__("bsrl %1, %0\n\t"
		"xorl $31, %0"
		: "=r" (i) : "rm" (n));
	return i;

#elif defined(_MSC_VER) && _MSC_VER >= 1400
	uint32_t i;
	_BitScanReverse((DWORD *)&i, n);
	return i ^ 31U;

#else
	uint32_t i = 0;

	if ((n & UINT32_C(0xFFFF0000)) == 0) {
		n <<= 16;
		i = 16;
	}

	if ((n & UINT32_C(0xFF000000)) == 0) {
		n <<= 8;
		i += 8;
	}

	if ((n & UINT32_C(0xF0000000)) == 0) {
		n <<= 4;
		i += 4;
	}

	if ((n & UINT32_C(0xC0000000)) == 0) {
		n <<= 2;
		i += 2;
	}

	if ((n & UINT32_C(0x80000000)) == 0)
		++i;

	return i;
#endif
}


static inline uint32_t
ctz32(uint32_t n)
{
#if defined(__INTEL_COMPILER)
	return _bit_scan_forward(n);

#elif TUKLIB_GNUC_REQ(3, 4) && UINT_MAX >= UINT32_MAX
	return __builtin_ctz(n);

#elif defined(__GNUC__) && (defined(__i386__) || defined(__x86_64__))
	uint32_t i;
	__asm__("bsfl %1, %0" : "=r" (i) : "rm" (n));
	return i;

#elif defined(_MSC_VER) && _MSC_VER >= 1400
	uint32_t i;
	_BitScanForward((DWORD *)&i, n);
	return i;

#else
	uint32_t i = 0;

	if ((n & UINT32_C(0x0000FFFF)) == 0) {
		n >>= 16;
		i = 16;
	}

	if ((n & UINT32_C(0x000000FF)) == 0) {
		n >>= 8;
		i += 8;
	}

	if ((n & UINT32_C(0x0000000F)) == 0) {
		n >>= 4;
		i += 4;
	}

	if ((n & UINT32_C(0x00000003)) == 0) {
		n >>= 2;
		i += 2;
	}

	if ((n & UINT32_C(0x00000001)) == 0)
		++i;

	return i;
#endif
}

#define bsf32 ctz32

#endif