Source

git / read-cache.c

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
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
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
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
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#include "cache.h"

struct cache_entry **active_cache = NULL;
static time_t index_file_timestamp;
unsigned int active_nr = 0, active_alloc = 0, active_cache_changed = 0;

/*
 * This only updates the "non-critical" parts of the directory
 * cache, ie the parts that aren't tracked by GIT, and only used
 * to validate the cache.
 */
void fill_stat_cache_info(struct cache_entry *ce, struct stat *st)
{
	ce->ce_ctime.sec = htonl(st->st_ctime);
	ce->ce_mtime.sec = htonl(st->st_mtime);
#ifdef USE_NSEC
	ce->ce_ctime.nsec = htonl(st->st_ctim.tv_nsec);
	ce->ce_mtime.nsec = htonl(st->st_mtim.tv_nsec);
#endif
	ce->ce_dev = htonl(st->st_dev);
	ce->ce_ino = htonl(st->st_ino);
	ce->ce_uid = htonl(st->st_uid);
	ce->ce_gid = htonl(st->st_gid);
	ce->ce_size = htonl(st->st_size);
}

static int ce_compare_data(struct cache_entry *ce, struct stat *st)
{
	int match = -1;
	int fd = open(ce->name, O_RDONLY);

	if (fd >= 0) {
		unsigned char sha1[20];
		if (!index_fd(sha1, fd, st, 0, NULL))
			match = memcmp(sha1, ce->sha1, 20);
		close(fd);
	}
	return match;
}

static int ce_compare_link(struct cache_entry *ce, unsigned long expected_size)
{
	int match = -1;
	char *target;
	void *buffer;
	unsigned long size;
	char type[10];
	int len;

	target = xmalloc(expected_size);
	len = readlink(ce->name, target, expected_size);
	if (len != expected_size) {
		free(target);
		return -1;
	}
	buffer = read_sha1_file(ce->sha1, type, &size);
	if (!buffer) {
		free(target);
		return -1;
	}
	if (size == expected_size)
		match = memcmp(buffer, target, size);
	free(buffer);
	free(target);
	return match;
}

static int ce_modified_check_fs(struct cache_entry *ce, struct stat *st)
{
	switch (st->st_mode & S_IFMT) {
	case S_IFREG:
		if (ce_compare_data(ce, st))
			return DATA_CHANGED;
		break;
	case S_IFLNK:
		if (ce_compare_link(ce, st->st_size))
			return DATA_CHANGED;
		break;
	default:
		return TYPE_CHANGED;
	}
	return 0;
}

static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
{
	unsigned int changed = 0;

	switch (ntohl(ce->ce_mode) & S_IFMT) {
	case S_IFREG:
		changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
		/* We consider only the owner x bit to be relevant for
		 * "mode changes"
		 */
		if (trust_executable_bit &&
		    (0100 & (ntohl(ce->ce_mode) ^ st->st_mode)))
			changed |= MODE_CHANGED;
		break;
	case S_IFLNK:
		changed |= !S_ISLNK(st->st_mode) ? TYPE_CHANGED : 0;
		break;
	default:
		die("internal error: ce_mode is %o", ntohl(ce->ce_mode));
	}
	if (ce->ce_mtime.sec != htonl(st->st_mtime))
		changed |= MTIME_CHANGED;
	if (ce->ce_ctime.sec != htonl(st->st_ctime))
		changed |= CTIME_CHANGED;

#ifdef USE_NSEC
	/*
	 * nsec seems unreliable - not all filesystems support it, so
	 * as long as it is in the inode cache you get right nsec
	 * but after it gets flushed, you get zero nsec.
	 */
	if (ce->ce_mtime.nsec != htonl(st->st_mtim.tv_nsec))
		changed |= MTIME_CHANGED;
	if (ce->ce_ctime.nsec != htonl(st->st_ctim.tv_nsec))
		changed |= CTIME_CHANGED;
#endif	

	if (ce->ce_uid != htonl(st->st_uid) ||
	    ce->ce_gid != htonl(st->st_gid))
		changed |= OWNER_CHANGED;
	if (ce->ce_ino != htonl(st->st_ino))
		changed |= INODE_CHANGED;

#ifdef USE_STDEV
	/*
	 * st_dev breaks on network filesystems where different
	 * clients will have different views of what "device"
	 * the filesystem is on
	 */
	if (ce->ce_dev != htonl(st->st_dev))
		changed |= INODE_CHANGED;
#endif

	if (ce->ce_size != htonl(st->st_size))
		changed |= DATA_CHANGED;

	return changed;
}

int ce_match_stat(struct cache_entry *ce, struct stat *st)
{
	unsigned int changed = ce_match_stat_basic(ce, st);

	/*
	 * Within 1 second of this sequence:
	 * 	echo xyzzy >file && git-update-index --add file
	 * running this command:
	 * 	echo frotz >file
	 * would give a falsely clean cache entry.  The mtime and
	 * length match the cache, and other stat fields do not change.
	 *
	 * We could detect this at update-index time (the cache entry
	 * being registered/updated records the same time as "now")
	 * and delay the return from git-update-index, but that would
	 * effectively mean we can make at most one commit per second,
	 * which is not acceptable.  Instead, we check cache entries
	 * whose mtime are the same as the index file timestamp more
	 * careful than others.
	 */
	if (!changed &&
	    index_file_timestamp &&
	    index_file_timestamp <= ntohl(ce->ce_mtime.sec))
		changed |= ce_modified_check_fs(ce, st);

	return changed;
}

int ce_modified(struct cache_entry *ce, struct stat *st)
{
	int changed, changed_fs;
	changed = ce_match_stat(ce, st);
	if (!changed)
		return 0;
	/*
	 * If the mode or type has changed, there's no point in trying
	 * to refresh the entry - it's not going to match
	 */
	if (changed & (MODE_CHANGED | TYPE_CHANGED))
		return changed;

	/* Immediately after read-tree or update-index --cacheinfo,
	 * the length field is zero.  For other cases the ce_size
	 * should match the SHA1 recorded in the index entry.
	 */
	if ((changed & DATA_CHANGED) && ce->ce_size != htonl(0))
		return changed;

	changed_fs = ce_modified_check_fs(ce, st);
	if (changed_fs)
		return changed | changed_fs;
	return 0;
}

int base_name_compare(const char *name1, int len1, int mode1,
		      const char *name2, int len2, int mode2)
{
	unsigned char c1, c2;
	int len = len1 < len2 ? len1 : len2;
	int cmp;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	c1 = name1[len];
	c2 = name2[len];
	if (!c1 && S_ISDIR(mode1))
		c1 = '/';
	if (!c2 && S_ISDIR(mode2))
		c2 = '/';
	return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}

int cache_name_compare(const char *name1, int flags1, const char *name2, int flags2)
{
	int len1 = flags1 & CE_NAMEMASK;
	int len2 = flags2 & CE_NAMEMASK;
	int len = len1 < len2 ? len1 : len2;
	int cmp;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	if (len1 < len2)
		return -1;
	if (len1 > len2)
		return 1;
	if (flags1 < flags2)
		return -1;
	if (flags1 > flags2)
		return 1;
	return 0;
}

int cache_name_pos(const char *name, int namelen)
{
	int first, last;

	first = 0;
	last = active_nr;
	while (last > first) {
		int next = (last + first) >> 1;
		struct cache_entry *ce = active_cache[next];
		int cmp = cache_name_compare(name, namelen, ce->name, ntohs(ce->ce_flags));
		if (!cmp)
			return next;
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
	return -first-1;
}

/* Remove entry, return true if there are more entries to go.. */
int remove_cache_entry_at(int pos)
{
	active_cache_changed = 1;
	active_nr--;
	if (pos >= active_nr)
		return 0;
	memmove(active_cache + pos, active_cache + pos + 1, (active_nr - pos) * sizeof(struct cache_entry *));
	return 1;
}

int remove_file_from_cache(const char *path)
{
	int pos = cache_name_pos(path, strlen(path));
	if (pos < 0)
		pos = -pos-1;
	while (pos < active_nr && !strcmp(active_cache[pos]->name, path))
		remove_cache_entry_at(pos);
	return 0;
}

int ce_same_name(struct cache_entry *a, struct cache_entry *b)
{
	int len = ce_namelen(a);
	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}

int ce_path_match(const struct cache_entry *ce, const char **pathspec)
{
	const char *match, *name;
	int len;

	if (!pathspec)
		return 1;

	len = ce_namelen(ce);
	name = ce->name;
	while ((match = *pathspec++) != NULL) {
		int matchlen = strlen(match);
		if (matchlen > len)
			continue;
		if (memcmp(name, match, matchlen))
			continue;
		if (matchlen && name[matchlen-1] == '/')
			return 1;
		if (name[matchlen] == '/' || !name[matchlen])
			return 1;
		if (!matchlen)
			return 1;
	}
	return 0;
}

/*
 * Do we have another file that has the beginning components being a
 * proper superset of the name we're trying to add?
 */
static int has_file_name(const struct cache_entry *ce, int pos, int ok_to_replace)
{
	int retval = 0;
	int len = ce_namelen(ce);
	int stage = ce_stage(ce);
	const char *name = ce->name;

	while (pos < active_nr) {
		struct cache_entry *p = active_cache[pos++];

		if (len >= ce_namelen(p))
			break;
		if (memcmp(name, p->name, len))
			break;
		if (ce_stage(p) != stage)
			continue;
		if (p->name[len] != '/')
			continue;
		retval = -1;
		if (!ok_to_replace)
			break;
		remove_cache_entry_at(--pos);
	}
	return retval;
}

/*
 * Do we have another file with a pathname that is a proper
 * subset of the name we're trying to add?
 */
static int has_dir_name(const struct cache_entry *ce, int pos, int ok_to_replace)
{
	int retval = 0;
	int stage = ce_stage(ce);
	const char *name = ce->name;
	const char *slash = name + ce_namelen(ce);

	for (;;) {
		int len;

		for (;;) {
			if (*--slash == '/')
				break;
			if (slash <= ce->name)
				return retval;
		}
		len = slash - name;

		pos = cache_name_pos(name, ntohs(create_ce_flags(len, stage)));
		if (pos >= 0) {
			retval = -1;
			if (ok_to_replace)
				break;
			remove_cache_entry_at(pos);
			continue;
		}

		/*
		 * Trivial optimization: if we find an entry that
		 * already matches the sub-directory, then we know
		 * we're ok, and we can exit.
		 */
		pos = -pos-1;
		while (pos < active_nr) {
			struct cache_entry *p = active_cache[pos];
			if ((ce_namelen(p) <= len) ||
			    (p->name[len] != '/') ||
			    memcmp(p->name, name, len))
				break; /* not our subdirectory */
			if (ce_stage(p) == stage)
				/* p is at the same stage as our entry, and
				 * is a subdirectory of what we are looking
				 * at, so we cannot have conflicts at our
				 * level or anything shorter.
				 */
				return retval;
			pos++;
		}
	}
	return retval;
}

/* We may be in a situation where we already have path/file and path
 * is being added, or we already have path and path/file is being
 * added.  Either one would result in a nonsense tree that has path
 * twice when git-write-tree tries to write it out.  Prevent it.
 * 
 * If ok-to-replace is specified, we remove the conflicting entries
 * from the cache so the caller should recompute the insert position.
 * When this happens, we return non-zero.
 */
static int check_file_directory_conflict(const struct cache_entry *ce, int pos, int ok_to_replace)
{
	/*
	 * We check if the path is a sub-path of a subsequent pathname
	 * first, since removing those will not change the position
	 * in the array
	 */
	int retval = has_file_name(ce, pos, ok_to_replace);
	/*
	 * Then check if the path might have a clashing sub-directory
	 * before it.
	 */
	return retval + has_dir_name(ce, pos, ok_to_replace);
}

int add_cache_entry(struct cache_entry *ce, int option)
{
	int pos;
	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
	pos = cache_name_pos(ce->name, ntohs(ce->ce_flags));

	/* existing match? Just replace it. */
	if (pos >= 0) {
		active_cache_changed = 1;
		active_cache[pos] = ce;
		return 0;
	}
	pos = -pos-1;

	/*
	 * Inserting a merged entry ("stage 0") into the index
	 * will always replace all non-merged entries..
	 */
	if (pos < active_nr && ce_stage(ce) == 0) {
		while (ce_same_name(active_cache[pos], ce)) {
			ok_to_add = 1;
			if (!remove_cache_entry_at(pos))
				break;
		}
	}

	if (!ok_to_add)
		return -1;

	if (!skip_df_check &&
	    check_file_directory_conflict(ce, pos, ok_to_replace)) {
		if (!ok_to_replace)
			return -1;
		pos = cache_name_pos(ce->name, ntohs(ce->ce_flags));
		pos = -pos-1;
	}

	/* Make sure the array is big enough .. */
	if (active_nr == active_alloc) {
		active_alloc = alloc_nr(active_alloc);
		active_cache = xrealloc(active_cache, active_alloc * sizeof(struct cache_entry *));
	}

	/* Add it in.. */
	active_nr++;
	if (active_nr > pos)
		memmove(active_cache + pos + 1, active_cache + pos, (active_nr - pos - 1) * sizeof(ce));
	active_cache[pos] = ce;
	active_cache_changed = 1;
	return 0;
}

static int verify_hdr(struct cache_header *hdr, unsigned long size)
{
	SHA_CTX c;
	unsigned char sha1[20];

	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
		return error("bad signature");
	if (hdr->hdr_version != htonl(2))
		return error("bad index version");
	SHA1_Init(&c);
	SHA1_Update(&c, hdr, size - 20);
	SHA1_Final(sha1, &c);
	if (memcmp(sha1, (void *)hdr + size - 20, 20))
		return error("bad index file sha1 signature");
	return 0;
}

int read_cache(void)
{
	int fd, i;
	struct stat st;
	unsigned long size, offset;
	void *map;
	struct cache_header *hdr;

	errno = EBUSY;
	if (active_cache)
		return active_nr;

	errno = ENOENT;
	index_file_timestamp = 0;
	fd = open(get_index_file(), O_RDONLY);
	if (fd < 0) {
		if (errno == ENOENT)
			return 0;
		die("index file open failed (%s)", strerror(errno));
	}

	size = 0; // avoid gcc warning
	map = MAP_FAILED;
	if (!fstat(fd, &st)) {
		size = st.st_size;
		errno = EINVAL;
		if (size >= sizeof(struct cache_header) + 20)
			map = mmap(NULL, size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
	}
	close(fd);
	if (map == MAP_FAILED)
		die("index file mmap failed (%s)", strerror(errno));

	hdr = map;
	if (verify_hdr(hdr, size) < 0)
		goto unmap;

	active_nr = ntohl(hdr->hdr_entries);
	active_alloc = alloc_nr(active_nr);
	active_cache = calloc(active_alloc, sizeof(struct cache_entry *));

	offset = sizeof(*hdr);
	for (i = 0; i < active_nr; i++) {
		struct cache_entry *ce = map + offset;
		offset = offset + ce_size(ce);
		active_cache[i] = ce;
	}
	index_file_timestamp = st.st_mtime;
	return active_nr;

unmap:
	munmap(map, size);
	errno = EINVAL;
	die("index file corrupt");
}

#define WRITE_BUFFER_SIZE 8192
static unsigned char write_buffer[WRITE_BUFFER_SIZE];
static unsigned long write_buffer_len;

static int ce_write(SHA_CTX *context, int fd, void *data, unsigned int len)
{
	while (len) {
		unsigned int buffered = write_buffer_len;
		unsigned int partial = WRITE_BUFFER_SIZE - buffered;
		if (partial > len)
			partial = len;
		memcpy(write_buffer + buffered, data, partial);
		buffered += partial;
		if (buffered == WRITE_BUFFER_SIZE) {
			SHA1_Update(context, write_buffer, WRITE_BUFFER_SIZE);
			if (write(fd, write_buffer, WRITE_BUFFER_SIZE) != WRITE_BUFFER_SIZE)
				return -1;
			buffered = 0;
		}
		write_buffer_len = buffered;
		len -= partial;
		data += partial;
 	}
 	return 0;
}

static int ce_flush(SHA_CTX *context, int fd)
{
	unsigned int left = write_buffer_len;

	if (left) {
		write_buffer_len = 0;
		SHA1_Update(context, write_buffer, left);
	}

	/* Flush first if not enough space for SHA1 signature */
	if (left + 20 > WRITE_BUFFER_SIZE) {
		if (write(fd, write_buffer, left) != left)
			return -1;
		left = 0;
	}

	/* Append the SHA1 signature at the end */
	SHA1_Final(write_buffer + left, context);
	left += 20;
	if (write(fd, write_buffer, left) != left)
		return -1;
	return 0;
}

static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
{
	/*
	 * The only thing we care about in this function is to smudge the
	 * falsely clean entry due to touch-update-touch race, so we leave
	 * everything else as they are.  We are called for entries whose
	 * ce_mtime match the index file mtime.
	 */
	struct stat st;

	if (lstat(ce->name, &st) < 0)
		return;
	if (ce_match_stat_basic(ce, &st))
		return;
	if (ce_modified_check_fs(ce, &st)) {
		/* This is "racily clean"; smudge it.  Note that this
		 * is a tricky code.  At first glance, it may appear
		 * that it can break with this sequence:
		 *
		 * $ echo xyzzy >frotz
		 * $ git-update-index --add frotz
		 * $ : >frotz
		 * $ sleep 3
		 * $ echo filfre >nitfol
		 * $ git-update-index --add nitfol
		 *
		 * but it does not.  Whe the second update-index runs,
		 * it notices that the entry "frotz" has the same timestamp
		 * as index, and if we were to smudge it by resetting its
		 * size to zero here, then the object name recorded
		 * in index is the 6-byte file but the cached stat information
		 * becomes zero --- which would then match what we would
		 * obtain from the filesystem next time we stat("frotz"). 
		 *
		 * However, the second update-index, before calling
		 * this function, notices that the cached size is 6
		 * bytes and what is on the filesystem is an empty
		 * file, and never calls us, so the cached size information
		 * for "frotz" stays 6 which does not match the filesystem.
		 */
		ce->ce_size = htonl(0);
	}
}

int write_cache(int newfd, struct cache_entry **cache, int entries)
{
	SHA_CTX c;
	struct cache_header hdr;
	int i, removed;

	for (i = removed = 0; i < entries; i++)
		if (!cache[i]->ce_mode)
			removed++;

	hdr.hdr_signature = htonl(CACHE_SIGNATURE);
	hdr.hdr_version = htonl(2);
	hdr.hdr_entries = htonl(entries - removed);

	SHA1_Init(&c);
	if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0)
		return -1;

	for (i = 0; i < entries; i++) {
		struct cache_entry *ce = cache[i];
		if (!ce->ce_mode)
			continue;
		if (index_file_timestamp &&
		    index_file_timestamp <= ntohl(ce->ce_mtime.sec))
			ce_smudge_racily_clean_entry(ce);
		if (ce_write(&c, newfd, ce, ce_size(ce)) < 0)
			return -1;
	}
	return ce_flush(&c, newfd);
}