read-cache.c 33.4 KB
Newer Older
Linus Torvalds's avatar
Linus Torvalds committed
1 2 3 4 5
/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
6
#define NO_THE_INDEX_COMPATIBILITY_MACROS
7
#include "cache.h"
8
#include "cache-tree.h"
9
#include "refs.h"
10
#include "dir.h"
11 12 13 14 15 16 17 18 19 20 21 22

/* Index extensions.
 *
 * The first letter should be 'A'..'Z' for extensions that are not
 * necessary for a correct operation (i.e. optimization data).
 * When new extensions are added that _needs_ to be understood in
 * order to correctly interpret the index file, pick character that
 * is outside the range, to cause the reader to abort.
 */

#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
#define CACHE_EXT_TREE 0x54524545	/* "TREE" */
23

24
struct index_state the_index;
25

Junio C Hamano's avatar
Junio C Hamano committed
26 27 28
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	istate->cache[nr] = ce;
29
	add_name_hash(istate, ce);
Junio C Hamano's avatar
Junio C Hamano committed
30 31
}

32 33 34 35
static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	struct cache_entry *old = istate->cache[nr];

36
	remove_name_hash(old);
37
	set_index_entry(istate, nr, ce);
38 39 40
	istate->cache_changed = 1;
}

41 42 43 44 45 46 47
/*
 * 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)
{
48 49 50 51 52 53 54
	ce->ce_ctime = st->st_ctime;
	ce->ce_mtime = st->st_mtime;
	ce->ce_dev = st->st_dev;
	ce->ce_ino = st->st_ino;
	ce->ce_uid = st->st_uid;
	ce->ce_gid = st->st_gid;
	ce->ce_size = st->st_size;
Junio C Hamano's avatar
Junio C Hamano committed
55 56

	if (assume_unchanged)
57
		ce->ce_flags |= CE_VALID;
58 59 60

	if (S_ISREG(st->st_mode))
		ce_mark_uptodate(ce);
61 62
}

Junio C Hamano's avatar
Junio C Hamano committed
63 64 65 66 67 68 69
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];
70
		if (!index_fd(sha1, fd, st, 0, OBJ_BLOB, ce->name))
71
			match = hashcmp(sha1, ce->sha1);
72
		/* index_fd() closed the file descriptor already */
Junio C Hamano's avatar
Junio C Hamano committed
73 74 75 76
	}
	return match;
}

77
static int ce_compare_link(struct cache_entry *ce, size_t expected_size)
Junio C Hamano's avatar
Junio C Hamano committed
78 79 80 81 82
{
	int match = -1;
	char *target;
	void *buffer;
	unsigned long size;
83
	enum object_type type;
Junio C Hamano's avatar
Junio C Hamano committed
84 85 86 87 88 89 90 91
	int len;

	target = xmalloc(expected_size);
	len = readlink(ce->name, target, expected_size);
	if (len != expected_size) {
		free(target);
		return -1;
	}
92
	buffer = read_sha1_file(ce->sha1, &type, &size);
Junio C Hamano's avatar
Junio C Hamano committed
93 94 95 96 97 98 99 100 101 102 103
	if (!buffer) {
		free(target);
		return -1;
	}
	if (size == expected_size)
		match = memcmp(buffer, target, size);
	free(buffer);
	free(target);
	return match;
}

104 105 106 107 108 109
static int ce_compare_gitlink(struct cache_entry *ce)
{
	unsigned char sha1[20];

	/*
	 * We don't actually require that the .git directory
Martin Waitz's avatar
Martin Waitz committed
110
	 * under GITLINK directory be a valid git directory. It
111 112 113 114 115 116 117 118 119 120
	 * might even be missing (in case nobody populated that
	 * sub-project).
	 *
	 * If so, we consider it always to match.
	 */
	if (resolve_gitlink_ref(ce->name, "HEAD", sha1) < 0)
		return 0;
	return hashcmp(sha1, ce->sha1);
}

Junio C Hamano's avatar
Junio C Hamano committed
121 122 123 124 125 126 127 128
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:
129
		if (ce_compare_link(ce, xsize_t(st->st_size)))
Junio C Hamano's avatar
Junio C Hamano committed
130 131
			return DATA_CHANGED;
		break;
132
	case S_IFDIR:
133
		if (S_ISGITLINK(ce->ce_mode))
134
			return 0;
Junio C Hamano's avatar
Junio C Hamano committed
135 136 137 138 139 140
	default:
		return TYPE_CHANGED;
	}
	return 0;
}

Junio C Hamano's avatar
Junio C Hamano committed
141
static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
142 143 144
{
	unsigned int changed = 0;

145 146 147 148
	if (ce->ce_flags & CE_REMOVE)
		return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;

	switch (ce->ce_mode & S_IFMT) {
149 150
	case S_IFREG:
		changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
151 152 153 154
		/* We consider only the owner x bit to be relevant for
		 * "mode changes"
		 */
		if (trust_executable_bit &&
155
		    (0100 & (ce->ce_mode ^ st->st_mode)))
156
			changed |= MODE_CHANGED;
157 158
		break;
	case S_IFLNK:
159 160 161
		if (!S_ISLNK(st->st_mode) &&
		    (has_symlinks || !S_ISREG(st->st_mode)))
			changed |= TYPE_CHANGED;
162
		break;
Martin Waitz's avatar
Martin Waitz committed
163
	case S_IFGITLINK:
164 165 166 167
		if (!S_ISDIR(st->st_mode))
			changed |= TYPE_CHANGED;
		else if (ce_compare_gitlink(ce))
			changed |= DATA_CHANGED;
168
		return changed;
169
	default:
170
		die("internal error: ce_mode is %o", ce->ce_mode);
171
	}
172
	if (ce->ce_mtime != (unsigned int) st->st_mtime)
173
		changed |= MTIME_CHANGED;
174
	if (ce->ce_ctime != (unsigned int) st->st_ctime)
175
		changed |= CTIME_CHANGED;
176

177 178
	if (ce->ce_uid != (unsigned int) st->st_uid ||
	    ce->ce_gid != (unsigned int) st->st_gid)
179
		changed |= OWNER_CHANGED;
180
	if (ce->ce_ino != (unsigned int) st->st_ino)
181
		changed |= INODE_CHANGED;
182 183 184 185 186 187 188

#ifdef USE_STDEV
	/*
	 * st_dev breaks on network filesystems where different
	 * clients will have different views of what "device"
	 * the filesystem is on
	 */
189
	if (ce->ce_dev != (unsigned int) st->st_dev)
190 191 192
		changed |= INODE_CHANGED;
#endif

193
	if (ce->ce_size != (unsigned int) st->st_size)
194
		changed |= DATA_CHANGED;
195

Junio C Hamano's avatar
Junio C Hamano committed
196 197 198
	return changed;
}

199
static int is_racy_timestamp(const struct index_state *istate, struct cache_entry *ce)
200 201 202 203 204
{
	return (istate->timestamp &&
		((unsigned int)istate->timestamp) <= ce->ce_mtime);
}

205
int ie_match_stat(const struct index_state *istate,
206 207
		  struct cache_entry *ce, struct stat *st,
		  unsigned int options)
Junio C Hamano's avatar
Junio C Hamano committed
208
{
Junio C Hamano's avatar
Junio C Hamano committed
209
	unsigned int changed;
210 211
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
	int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY;
Junio C Hamano's avatar
Junio C Hamano committed
212 213 214 215 216

	/*
	 * If it's marked as always valid in the index, it's
	 * valid whatever the checked-out copy says.
	 */
217
	if (!ignore_valid && (ce->ce_flags & CE_VALID))
Junio C Hamano's avatar
Junio C Hamano committed
218 219 220
		return 0;

	changed = ce_match_stat_basic(ce, st);
Junio C Hamano's avatar
Junio C Hamano committed
221

Junio C Hamano's avatar
Junio C Hamano committed
222 223 224 225 226 227 228 229 230 231 232 233 234 235
	/*
	 * 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
Junio C Hamano's avatar
Junio C Hamano committed
236
	 * carefully than others.
Junio C Hamano's avatar
Junio C Hamano committed
237
	 */
238
	if (!changed && is_racy_timestamp(istate, ce)) {
239 240 241 242 243
		if (assume_racy_is_modified)
			changed |= DATA_CHANGED;
		else
			changed |= ce_modified_check_fs(ce, st);
	}
244

Junio C Hamano's avatar
Junio C Hamano committed
245
	return changed;
246 247
}

248
int ie_modified(const struct index_state *istate,
249
		struct cache_entry *ce, struct stat *st, unsigned int options)
250
{
Junio C Hamano's avatar
Junio C Hamano committed
251
	int changed, changed_fs;
252 253

	changed = ie_match_stat(istate, ce, st, options);
254 255 256 257 258 259 260 261 262 263 264 265 266
	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.
	 */
267
	if ((changed & DATA_CHANGED) && ce->ce_size != 0)
268 269
		return changed;

Junio C Hamano's avatar
Junio C Hamano committed
270 271 272
	changed_fs = ce_modified_check_fs(ce, st);
	if (changed_fs)
		return changed | changed_fs;
273 274 275
	return 0;
}

276 277 278 279 280 281 282 283 284 285 286 287
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];
288
	if (!c1 && S_ISDIR(mode1))
289
		c1 = '/';
290
	if (!c2 && S_ISDIR(mode2))
291 292 293 294
		c2 = '/';
	return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}

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
/*
 * df_name_compare() is identical to base_name_compare(), except it
 * compares conflicting directory/file entries as equal. Note that
 * while a directory name compares as equal to a regular file, they
 * then individually compare _differently_ to a filename that has
 * a dot after the basename (because '\0' < '.' < '/').
 *
 * This is used by routines that want to traverse the git namespace
 * but then handle conflicting entries together when possible.
 */
int df_name_compare(const char *name1, int len1, int mode1,
		    const char *name2, int len2, int mode2)
{
	int len = len1 < len2 ? len1 : len2, cmp;
	unsigned char c1, c2;

	cmp = memcmp(name1, name2, len);
	if (cmp)
		return cmp;
	/* Directories and files compare equal (same length, same name) */
	if (len1 == len2)
		return 0;
	c1 = name1[len];
	if (!c1 && S_ISDIR(mode1))
		c1 = '/';
	c2 = name2[len];
	if (!c2 && S_ISDIR(mode2))
		c2 = '/';
	if (c1 == '/' && !c2)
		return 0;
	if (c2 == '/' && !c1)
		return 0;
	return c1 - c2;
}

330
int cache_name_compare(const char *name1, int flags1, const char *name2, int flags2)
331
{
332 333
	int len1 = flags1 & CE_NAMEMASK;
	int len2 = flags2 & CE_NAMEMASK;
334 335 336 337 338 339 340 341 342 343
	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;
Junio C Hamano's avatar
Junio C Hamano committed
344

345 346 347
	/* Compare stages  */
	flags1 &= CE_STAGEMASK;
	flags2 &= CE_STAGEMASK;
Junio C Hamano's avatar
Junio C Hamano committed
348

349 350 351 352
	if (flags1 < flags2)
		return -1;
	if (flags1 > flags2)
		return 1;
353 354 355
	return 0;
}

356
int index_name_pos(const struct index_state *istate, const char *name, int namelen)
357 358 359 360
{
	int first, last;

	first = 0;
361
	last = istate->cache_nr;
362 363
	while (last > first) {
		int next = (last + first) >> 1;
364
		struct cache_entry *ce = istate->cache[next];
365
		int cmp = cache_name_compare(name, namelen, ce->name, ce->ce_flags);
366
		if (!cmp)
367
			return next;
368 369 370 371 372 373
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
374
	return -first-1;
375 376
}

377
/* Remove entry, return true if there are more entries to go.. */
378
int remove_index_entry_at(struct index_state *istate, int pos)
379
{
380 381
	struct cache_entry *ce = istate->cache[pos];

382
	remove_name_hash(ce);
383 384 385
	istate->cache_changed = 1;
	istate->cache_nr--;
	if (pos >= istate->cache_nr)
386
		return 0;
387 388 389
	memmove(istate->cache + pos,
		istate->cache + pos + 1,
		(istate->cache_nr - pos) * sizeof(struct cache_entry *));
390 391 392
	return 1;
}

393
int remove_file_from_index(struct index_state *istate, const char *path)
394
{
395
	int pos = index_name_pos(istate, path, strlen(path));
396 397
	if (pos < 0)
		pos = -pos-1;
Junio C Hamano's avatar
Junio C Hamano committed
398
	cache_tree_invalidate_path(istate->cache_tree, path);
399 400
	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
		remove_index_entry_at(istate, pos);
401 402 403
	return 0;
}

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
static int compare_name(struct cache_entry *ce, const char *path, int namelen)
{
	return namelen != ce_namelen(ce) || memcmp(path, ce->name, namelen);
}

static int index_name_pos_also_unmerged(struct index_state *istate,
	const char *path, int namelen)
{
	int pos = index_name_pos(istate, path, namelen);
	struct cache_entry *ce;

	if (pos >= 0)
		return pos;

	/* maybe unmerged? */
	pos = -1 - pos;
	if (pos >= istate->cache_nr ||
			compare_name((ce = istate->cache[pos]), path, namelen))
		return -1;

	/* order of preference: stage 2, 1, 3 */
	if (ce_stage(ce) == 1 && pos + 1 < istate->cache_nr &&
			ce_stage((ce = istate->cache[pos + 1])) == 2 &&
			!compare_name(ce, path, namelen))
		pos++;
	return pos;
}

432
int add_file_to_index(struct index_state *istate, const char *path, int verbose)
Johannes Schindelin's avatar
Johannes Schindelin committed
433
{
434
	int size, namelen, pos;
Johannes Schindelin's avatar
Johannes Schindelin committed
435 436
	struct stat st;
	struct cache_entry *ce;
437
	unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_RACY_IS_DIRTY;
Johannes Schindelin's avatar
Johannes Schindelin committed
438 439 440 441

	if (lstat(path, &st))
		die("%s: unable to stat (%s)", path, strerror(errno));

442 443
	if (!S_ISREG(st.st_mode) && !S_ISLNK(st.st_mode) && !S_ISDIR(st.st_mode))
		die("%s: can only add regular files, symbolic links or git-directories", path);
Johannes Schindelin's avatar
Johannes Schindelin committed
444 445

	namelen = strlen(path);
446 447 448 449
	if (S_ISDIR(st.st_mode)) {
		while (namelen && path[namelen-1] == '/')
			namelen--;
	}
Johannes Schindelin's avatar
Johannes Schindelin committed
450 451 452
	size = cache_entry_size(namelen);
	ce = xcalloc(1, size);
	memcpy(ce->name, path, namelen);
453
	ce->ce_flags = namelen;
Johannes Schindelin's avatar
Johannes Schindelin committed
454 455
	fill_stat_cache_info(ce, &st);

456
	if (trust_executable_bit && has_symlinks)
457 458
		ce->ce_mode = create_ce_mode(st.st_mode);
	else {
459 460
		/* If there is an existing entry, pick the mode bits and type
		 * from it, otherwise assume unexecutable regular file.
Johannes Schindelin's avatar
Johannes Schindelin committed
461
		 */
462
		struct cache_entry *ent;
463
		int pos = index_name_pos_also_unmerged(istate, path, namelen);
464

465
		ent = (0 <= pos) ? istate->cache[pos] : NULL;
466
		ce->ce_mode = ce_mode_from_stat(ent, st.st_mode);
Johannes Schindelin's avatar
Johannes Schindelin committed
467 468
	}

469 470 471
	pos = index_name_pos(istate, ce->name, namelen);
	if (0 <= pos &&
	    !ce_stage(istate->cache[pos]) &&
472
	    !ie_match_stat(istate, istate->cache[pos], &st, ce_option)) {
473 474
		/* Nothing changed, really */
		free(ce);
475
		ce_mark_uptodate(istate->cache[pos]);
476 477 478
		return 0;
	}

Johannes Schindelin's avatar
Johannes Schindelin committed
479 480
	if (index_path(ce->sha1, path, &st, 1))
		die("unable to index file %s", path);
481
	if (add_index_entry(istate, ce, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE))
Johannes Schindelin's avatar
Johannes Schindelin committed
482 483 484 485 486 487
		die("unable to add %s to index",path);
	if (verbose)
		printf("add '%s'\n", path);
	return 0;
}

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
struct cache_entry *make_cache_entry(unsigned int mode,
		const unsigned char *sha1, const char *path, int stage,
		int refresh)
{
	int size, len;
	struct cache_entry *ce;

	if (!verify_path(path))
		return NULL;

	len = strlen(path);
	size = cache_entry_size(len);
	ce = xcalloc(1, size);

	hashcpy(ce->sha1, sha1);
	memcpy(ce->name, path, len);
	ce->ce_flags = create_ce_flags(len, stage);
	ce->ce_mode = create_ce_mode(mode);

	if (refresh)
		return refresh_cache_entry(ce, 0);

	return ce;
}

513
int ce_same_name(struct cache_entry *a, struct cache_entry *b)
514 515 516 517 518
{
	int len = ce_namelen(a);
	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}

519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538
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;
539 540
		if (!matchlen)
			return 1;
541 542 543 544
	}
	return 0;
}

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
/*
 * We fundamentally don't like some paths: we don't want
 * dot or dot-dot anywhere, and for obvious reasons don't
 * want to recurse into ".git" either.
 *
 * Also, we don't want double slashes or slashes at the
 * end that can make pathnames ambiguous.
 */
static int verify_dotfile(const char *rest)
{
	/*
	 * The first character was '.', but that
	 * has already been discarded, we now test
	 * the rest.
	 */
	switch (*rest) {
	/* "." is not allowed */
	case '\0': case '/':
		return 0;

	/*
	 * ".git" followed by  NUL or slash is bad. This
	 * shares the path end test with the ".." case.
	 */
	case 'g':
		if (rest[1] != 'i')
			break;
		if (rest[2] != 't')
			break;
		rest += 2;
	/* fallthrough */
	case '.':
		if (rest[1] == '\0' || rest[1] == '/')
			return 0;
	}
	return 1;
}

int verify_path(const char *path)
{
	char c;

	goto inside;
	for (;;) {
		if (!c)
			return 1;
		if (c == '/') {
inside:
			c = *path++;
			switch (c) {
			default:
				continue;
			case '/': case '\0':
				break;
			case '.':
				if (verify_dotfile(path))
					continue;
			}
			return 0;
		}
		c = *path++;
	}
}

609 610 611
/*
 * Do we have another file that has the beginning components being a
 * proper superset of the name we're trying to add?
612
 */
613 614
static int has_file_name(struct index_state *istate,
			 const struct cache_entry *ce, int pos, int ok_to_replace)
615
{
616 617
	int retval = 0;
	int len = ce_namelen(ce);
618
	int stage = ce_stage(ce);
619
	const char *name = ce->name;
620

621 622
	while (pos < istate->cache_nr) {
		struct cache_entry *p = istate->cache[pos++];
623

624
		if (len >= ce_namelen(p))
625
			break;
626 627
		if (memcmp(name, p->name, len))
			break;
628 629
		if (ce_stage(p) != stage)
			continue;
630 631
		if (p->name[len] != '/')
			continue;
632
		if (p->ce_flags & CE_REMOVE)
633
			continue;
634 635 636
		retval = -1;
		if (!ok_to_replace)
			break;
637
		remove_index_entry_at(istate, --pos);
638
	}
639 640
	return retval;
}
641

642 643 644 645
/*
 * Do we have another file with a pathname that is a proper
 * subset of the name we're trying to add?
 */
646 647
static int has_dir_name(struct index_state *istate,
			const struct cache_entry *ce, int pos, int ok_to_replace)
648 649
{
	int retval = 0;
650
	int stage = ce_stage(ce);
651 652
	const char *name = ce->name;
	const char *slash = name + ce_namelen(ce);
653

654 655
	for (;;) {
		int len;
656

657 658 659 660 661 662 663
		for (;;) {
			if (*--slash == '/')
				break;
			if (slash <= ce->name)
				return retval;
		}
		len = slash - name;
664

665
		pos = index_name_pos(istate, name, create_ce_flags(len, stage));
666
		if (pos >= 0) {
667 668 669 670 671 672 673 674
			/*
			 * Found one, but not so fast.  This could
			 * be a marker that says "I was here, but
			 * I am being removed".  Such an entry is
			 * not a part of the resulting tree, and
			 * it is Ok to have a directory at the same
			 * path.
			 */
675
			if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
676 677 678
				retval = -1;
				if (!ok_to_replace)
					break;
679
				remove_index_entry_at(istate, pos);
680 681
				continue;
			}
682
		}
683 684
		else
			pos = -pos-1;
685 686 687 688

		/*
		 * Trivial optimization: if we find an entry that
		 * already matches the sub-directory, then we know
689
		 * we're ok, and we can exit.
690
		 */
691 692
		while (pos < istate->cache_nr) {
			struct cache_entry *p = istate->cache[pos];
693 694 695 696
			if ((ce_namelen(p) <= len) ||
			    (p->name[len] != '/') ||
			    memcmp(p->name, name, len))
				break; /* not our subdirectory */
697 698 699
			if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE))
				/*
				 * p is at the same stage as our entry, and
700 701 702 703 704 705
				 * is a subdirectory of what we are looking
				 * at, so we cannot have conflicts at our
				 * level or anything shorter.
				 */
				return retval;
			pos++;
706
		}
707
	}
708 709 710 711 712 713 714
	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.
Junio C Hamano's avatar
Junio C Hamano committed
715
 *
716 717 718 719
 * 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.
 */
720 721 722
static int check_file_directory_conflict(struct index_state *istate,
					 const struct cache_entry *ce,
					 int pos, int ok_to_replace)
723
{
724 725 726 727 728
	int retval;

	/*
	 * When ce is an "I am going away" entry, we allow it to be added
	 */
729
	if (ce->ce_flags & CE_REMOVE)
730 731
		return 0;

732 733 734
	/*
	 * We check if the path is a sub-path of a subsequent pathname
	 * first, since removing those will not change the position
735
	 * in the array.
736
	 */
737
	retval = has_file_name(istate, ce, pos, ok_to_replace);
738

739 740 741 742
	/*
	 * Then check if the path might have a clashing sub-directory
	 * before it.
	 */
743
	return retval + has_dir_name(istate, ce, pos, ok_to_replace);
744 745
}

746
static int add_index_entry_with_check(struct index_state *istate, struct cache_entry *ce, int option)
747 748
{
	int pos;
749 750
	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
751
	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
Junio C Hamano's avatar
Junio C Hamano committed
752

Junio C Hamano's avatar
Junio C Hamano committed
753
	cache_tree_invalidate_path(istate->cache_tree, ce->name);
754
	pos = index_name_pos(istate, ce->name, ce->ce_flags);
755

Junio C Hamano's avatar
Junio C Hamano committed
756
	/* existing match? Just replace it. */
757
	if (pos >= 0) {
758
		replace_index_entry(istate, pos, ce);
759 760
		return 0;
	}
761
	pos = -pos-1;
762

763 764 765 766
	/*
	 * Inserting a merged entry ("stage 0") into the index
	 * will always replace all non-merged entries..
	 */
767 768
	if (pos < istate->cache_nr && ce_stage(ce) == 0) {
		while (ce_same_name(istate->cache[pos], ce)) {
769
			ok_to_add = 1;
770
			if (!remove_index_entry_at(istate, pos))
771 772 773 774
				break;
		}
	}

775 776
	if (!ok_to_add)
		return -1;
777 778
	if (!verify_path(ce->name))
		return -1;
779

Junio C Hamano's avatar
Junio C Hamano committed
780
	if (!skip_df_check &&
781
	    check_file_directory_conflict(istate, ce, pos, ok_to_replace)) {
782
		if (!ok_to_replace)
783 784
			return error("'%s' appears as both a file and as a directory",
				     ce->name);
785
		pos = index_name_pos(istate, ce->name, ce->ce_flags);
786 787
		pos = -pos-1;
	}
788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803
	return pos + 1;
}

int add_index_entry(struct index_state *istate, struct cache_entry *ce, int option)
{
	int pos;

	if (option & ADD_CACHE_JUST_APPEND)
		pos = istate->cache_nr;
	else {
		int ret;
		ret = add_index_entry_with_check(istate, ce, option);
		if (ret <= 0)
			return ret;
		pos = ret - 1;
	}
804

805
	/* Make sure the array is big enough .. */
806 807 808 809
	if (istate->cache_nr == istate->cache_alloc) {
		istate->cache_alloc = alloc_nr(istate->cache_alloc);
		istate->cache = xrealloc(istate->cache,
					istate->cache_alloc * sizeof(struct cache_entry *));
810 811 812
	}

	/* Add it in.. */
813
	istate->cache_nr++;
814
	if (istate->cache_nr > pos + 1)
815 816 817
		memmove(istate->cache + pos + 1,
			istate->cache + pos,
			(istate->cache_nr - pos - 1) * sizeof(ce));
818
	set_index_entry(istate, pos, ce);
819
	istate->cache_changed = 1;
820 821 822
	return 0;
}

823 824 825 826 827 828 829 830 831 832 833
/*
 * "refresh" does not calculate a new sha1 file or bring the
 * cache up-to-date for mode/content changes. But what it
 * _does_ do is to "re-match" the stat information of a file
 * with the cache, so that you can refresh the cache for a
 * file that hasn't been changed but where the stat entry is
 * out of date.
 *
 * For example, you'd want to do this after doing a "git-read-tree",
 * to link up the stat cache details with the proper files.
 */
834
static struct cache_entry *refresh_cache_ent(struct index_state *istate,
835 836
					     struct cache_entry *ce,
					     unsigned int options, int *err)
837 838 839 840
{
	struct stat st;
	struct cache_entry *updated;
	int changed, size;
841
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
842

843 844 845
	if (ce_uptodate(ce))
		return ce;

846
	if (lstat(ce->name, &st) < 0) {
847 848
		if (err)
			*err = errno;
849 850
		return NULL;
	}
851

852
	changed = ie_match_stat(istate, ce, &st, options);
853
	if (!changed) {
854 855 856 857 858 859 860 861
		/*
		 * The path is unchanged.  If we were told to ignore
		 * valid bit, then we did the actual stat check and
		 * found that the entry is unmodified.  If the entry
		 * is not marked VALID, this is the place to mark it
		 * valid again, under "assume unchanged" mode.
		 */
		if (ignore_valid && assume_unchanged &&
862
		    !(ce->ce_flags & CE_VALID))
863
			; /* mark this one VALID again */
864 865 866 867 868 869 870
		else {
			/*
			 * We do not mark the index itself "modified"
			 * because CE_UPTODATE flag is in-core only;
			 * we are not going to write this change out.
			 */
			ce_mark_uptodate(ce);
871
			return ce;
872
		}
873 874
	}

875
	if (ie_modified(istate, ce, &st, options)) {
876 877
		if (err)
			*err = EINVAL;
878 879
		return NULL;
	}
880 881 882 883 884

	size = ce_size(ce);
	updated = xmalloc(size);
	memcpy(updated, ce, size);
	fill_stat_cache_info(updated, &st);
885 886 887 888 889
	/*
	 * If ignore_valid is not set, we should leave CE_VALID bit
	 * alone.  Otherwise, paths marked with --no-assume-unchanged
	 * (i.e. things to be edited) will reacquire CE_VALID bit
	 * automatically, which is not really what we want.
890
	 */
891
	if (!ignore_valid && assume_unchanged &&
892 893
	    !(ce->ce_flags & CE_VALID))
		updated->ce_flags &= ~CE_VALID;
894 895 896 897

	return updated;
}

898
int refresh_index(struct index_state *istate, unsigned int flags, const char **pathspec, char *seen)
899 900 901 902 903 904 905
{
	int i;
	int has_errors = 0;
	int really = (flags & REFRESH_REALLY) != 0;
	int allow_unmerged = (flags & REFRESH_UNMERGED) != 0;
	int quiet = (flags & REFRESH_QUIET) != 0;
	int not_new = (flags & REFRESH_IGNORE_MISSING) != 0;
906
	unsigned int options = really ? CE_MATCH_IGNORE_VALID : 0;
907

908
	for (i = 0; i < istate->cache_nr; i++) {
909
		struct cache_entry *ce, *new;
910 911
		int cache_errno = 0;

912
		ce = istate->cache[i];
913
		if (ce_stage(ce)) {
914 915
			while ((i < istate->cache_nr) &&
			       ! strcmp(istate->cache[i]->name, ce->name))
916 917 918 919 920 921 922 923 924
				i++;
			i--;
			if (allow_unmerged)
				continue;
			printf("%s: needs merge\n", ce->name);
			has_errors = 1;
			continue;
		}

925 926 927
		if (pathspec && !match_pathspec(pathspec, ce->name, strlen(ce->name), 0, seen))
			continue;

928
		new = refresh_cache_ent(istate, ce, options, &cache_errno);
929
		if (new == ce)
930
			continue;
931 932
		if (!new) {
			if (not_new && cache_errno == ENOENT)
933
				continue;
934
			if (really && cache_errno == EINVAL) {
935 936 937
				/* If we are doing --really-refresh that
				 * means the index is not valid anymore.
				 */
938
				ce->ce_flags &= ~CE_VALID;
939
				istate->cache_changed = 1;
940 941 942 943 944 945 946
			}
			if (quiet)
				continue;
			printf("%s: needs update\n", ce->name);
			has_errors = 1;
			continue;
		}
947 948

		replace_index_entry(istate, i, new);
949 950 951 952
	}
	return has_errors;
}

953 954
struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really)
{
955
	return refresh_cache_ent(&the_index, ce, really, NULL);
956 957
}

958
static int verify_hdr(struct cache_header *hdr, unsigned long size)
959 960
{
	SHA_CTX c;
961
	unsigned char sha1[20];
962

963
	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
964
		return error("bad signature");
965 966
	if (hdr->hdr_version != htonl(2))
		return error("bad index version");
967
	SHA1_Init(&c);
968
	SHA1_Update(&c, hdr, size - 20);
969
	SHA1_Final(sha1, &c);
970
	if (hashcmp(sha1, (unsigned char *)hdr + size - 20))
971
		return error("bad index file sha1 signature");
972 973 974
	return 0;
}

975 976
static int read_index_extension(struct index_state *istate,
				const char *ext, void *data, unsigned long sz)
977 978 979
{
	switch (CACHE_EXT(ext)) {
	case CACHE_EXT_TREE:
980
		istate->cache_tree = cache_tree_read(data, sz);
981 982 983 984 985 986 987 988 989 990 991
		break;
	default:
		if (*ext < 'A' || 'Z' < *ext)
			return error("index uses %.4s extension, which we do not understand",
				     ext);
		fprintf(stderr, "ignoring %.4s extension\n", ext);
		break;
	}
	return 0;
}

992
int read_index(struct index_state *istate)
993
{
994
	return read_index_from(istate, get_index_file());
995 996
}

997 998
static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce)
{
999 1000
	size_t len;

1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011
	ce->ce_ctime = ntohl(ondisk->ctime.sec);
	ce->ce_mtime = ntohl(ondisk->mtime.sec);
	ce->ce_dev   = ntohl(ondisk->dev);
	ce->ce_ino   = ntohl(ondisk->ino);
	ce->ce_mode  = ntohl(ondisk->mode);
	ce->ce_uid   = ntohl(ondisk->uid);
	ce->ce_gid   = ntohl(ondisk->gid);
	ce->ce_size  = ntohl(ondisk->size);
	/* On-disk flags are just 16 bits */
	ce->ce_flags = ntohs(ondisk->flags);
	hashcpy(ce->sha1, ondisk->sha1);
1012 1013 1014 1015 1016 1017 1018 1019 1020

	len = ce->ce_flags & CE_NAMEMASK;
	if (len == CE_NAMEMASK)
		len = strlen(ondisk->name);
	/*
	 * NEEDSWORK: If the original index is crafted, this copy could
	 * go unchecked.
	 */
	memcpy(ce->name, ondisk->name, len + 1);
1021 1022
}

1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036
static inline size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)
{
	long per_entry;

	per_entry = sizeof(struct cache_entry) - sizeof(struct ondisk_cache_entry);

	/*
	 * Alignment can cause differences. This should be "alignof", but
	 * since that's a gcc'ism, just use the size of a pointer.
	 */
	per_entry += sizeof(void *);
	return ondisk_size + entries*per_entry;
}

1037
/* remember to discard_cache() before reading a different cache! */
1038
int read_index_from(struct index_state *istate, const char *path)
1039 1040 1041
{
	int fd, i;
	struct stat st;
1042
	unsigned long src_offset, dst_offset;
1043
	struct cache_header *hdr;
1044 1045
	void *mmap;
	size_t mmap_size;
1046 1047

	errno = EBUSY;
1048
	if (istate->alloc)
1049
		return istate->cache_nr;
1050

1051
	errno = ENOENT;
1052
	istate->timestamp = 0;
1053
	fd = open(path, O_RDONLY);
1054 1055 1056 1057 1058
	if (fd < 0) {
		if (errno == ENOENT)
			return 0;
		die("index file open failed (%s)", strerror(errno));
	}
1059

1060
	if (fstat(fd, &st))
1061
		die("cannot stat the open index (%s)", strerror(errno));
1062 1063

	errno = EINVAL;
1064 1065
	mmap_size = xsize_t(st.st_size);
	if (mmap_size < sizeof(struct cache_header) + 20)
1066 1067
		die("index file smaller than expected");

1068
	mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
1069
	close(fd);
1070 1071
	if (mmap == MAP_FAILED)
		die("unable to map index file");
1072

1073 1074
	hdr = mmap;
	if (verify_hdr(hdr, mmap_size) < 0)
1075 1076
		goto unmap;

1077 1078 1079
	istate->cache_nr = ntohl(hdr->hdr_entries);
	istate->cache_alloc = alloc_nr(istate->cache_nr);
	istate->cache = xcalloc(istate->cache_alloc, sizeof(struct cache_entry *));
1080

1081 1082 1083 1084 1085 1086
	/*
	 * The disk format is actually larger than the in-memory format,
	 * due to space for nsec etc, so even though the in-memory one
	 * has room for a few  more flags, we can allocate using the same
	 * index size
	 */
1087
	istate->alloc = xmalloc(estimate_cache_size(mmap_size, istate->cache_nr));
1088 1089 1090

	src_offset = sizeof(*hdr);
	dst_offset = 0;
1091
	for (i = 0; i < istate->cache_nr; i++) {
1092
		struct ondisk_cache_entry *disk_ce;
1093 1094
		struct cache_entry *ce;

1095 1096 1097
		disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset);
		ce = (struct cache_entry *)((char *)istate->alloc + dst_offset);
		convert_from_disk(disk_ce, ce);
1098
		set_index_entry(istate, i, ce);
1099 1100 1101

		src_offset += ondisk_ce_size(ce);
		dst_offset += ce_size(ce);
1102
	}
1103
	istate->timestamp = st.st_mtime;
1104
	while (src_offset <= mmap_size - 20 - 8) {
1105 1106 1107 1108 1109 1110 1111
		/* After an array of active_nr index entries,
		 * there can be arbitrary number of extended
		 * sections, each of which is prefixed with
		 * extension name (4-byte) and section length
		 * in 4-byte network byte order.
		 */
		unsigned long extsize;
1112
		memcpy(&extsize, (char *)mmap + src_offset + 4, 4);
1113
		extsize = ntohl(extsize);
1114
		if (read_index_extension(istate,
1115 1116
					 (const char *) mmap + src_offset,
					 (char *) mmap + src_offset + 8,
1117
					 extsize) < 0)
1118
			goto unmap;
1119 1120
		src_offset += 8;
		src_offset += extsize;