read-cache.c 42.6 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
#include "tree.h"
#include "commit.h"
#include "diff.h"
#include "diffcore.h"
#include "revision.h"
16
#include "blob.h"
17 18 19 20 21 22 23 24 25 26 27 28

/* 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" */
29

30
struct index_state the_index;
31

Junio C Hamano's avatar
Junio C Hamano committed
32 33 34
static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	istate->cache[nr] = ce;
35
	add_name_hash(istate, ce);
Junio C Hamano's avatar
Junio C Hamano committed
36 37
}

38 39 40 41
static void replace_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	struct cache_entry *old = istate->cache[nr];

42
	remove_name_hash(old);
43
	set_index_entry(istate, nr, ce);
44 45 46
	istate->cache_changed = 1;
}

47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62
void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name)
{
	struct cache_entry *old = istate->cache[nr], *new;
	int namelen = strlen(new_name);

	new = xmalloc(cache_entry_size(namelen));
	copy_cache_entry(new, old);
	new->ce_flags &= ~(CE_STATE_MASK | CE_NAMEMASK);
	new->ce_flags |= (namelen >= CE_NAMEMASK ? CE_NAMEMASK : namelen);
	memcpy(new->name, new_name, namelen + 1);

	cache_tree_invalidate_path(istate->cache_tree, old->name);
	remove_index_entry_at(istate, nr);
	add_index_entry(istate, new, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}

63 64 65 66 67 68 69
/*
 * 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)
{
70 71 72 73 74 75 76
	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
77 78

	if (assume_unchanged)
79
		ce->ce_flags |= CE_VALID;
80 81 82

	if (S_ISREG(st->st_mode))
		ce_mark_uptodate(ce);
83 84
}

Junio C Hamano's avatar
Junio C Hamano committed
85 86 87 88 89 90 91
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];
92
		if (!index_fd(sha1, fd, st, 0, OBJ_BLOB, ce->name))
93
			match = hashcmp(sha1, ce->sha1);
94
		/* index_fd() closed the file descriptor already */
Junio C Hamano's avatar
Junio C Hamano committed
95 96 97 98
	}
	return match;
}

99
static int ce_compare_link(struct cache_entry *ce, size_t expected_size)
Junio C Hamano's avatar
Junio C Hamano committed
100 101 102 103 104
{
	int match = -1;
	char *target;
	void *buffer;
	unsigned long size;
105
	enum object_type type;
Junio C Hamano's avatar
Junio C Hamano committed
106 107 108 109 110 111 112 113
	int len;

	target = xmalloc(expected_size);
	len = readlink(ce->name, target, expected_size);
	if (len != expected_size) {
		free(target);
		return -1;
	}
114
	buffer = read_sha1_file(ce->sha1, &type, &size);
Junio C Hamano's avatar
Junio C Hamano committed
115 116 117 118 119 120 121 122 123 124 125
	if (!buffer) {
		free(target);
		return -1;
	}
	if (size == expected_size)
		match = memcmp(buffer, target, size);
	free(buffer);
	free(target);
	return match;
}

126 127 128 129 130 131
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
132
	 * under GITLINK directory be a valid git directory. It
133 134 135 136 137 138 139 140 141 142
	 * 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
143 144 145 146 147 148 149 150
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:
151
		if (ce_compare_link(ce, xsize_t(st->st_size)))
Junio C Hamano's avatar
Junio C Hamano committed
152 153
			return DATA_CHANGED;
		break;
154
	case S_IFDIR:
155
		if (S_ISGITLINK(ce->ce_mode))
156
			return ce_compare_gitlink(ce) ? DATA_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
157 158 159 160 161 162
	default:
		return TYPE_CHANGED;
	}
	return 0;
}

163
int is_empty_blob_sha1(const unsigned char *sha1)
164 165 166 167 168 169 170 171 172
{
	static const unsigned char empty_blob_sha1[20] = {
		0xe6,0x9d,0xe2,0x9b,0xb2,0xd1,0xd6,0x43,0x4b,0x8b,
		0x29,0xae,0x77,0x5a,0xd8,0xc2,0xe4,0x8c,0x53,0x91
	};

	return !hashcmp(sha1, empty_blob_sha1);
}

Junio C Hamano's avatar
Junio C Hamano committed
173
static int ce_match_stat_basic(struct cache_entry *ce, struct stat *st)
174 175 176
{
	unsigned int changed = 0;

177 178 179 180
	if (ce->ce_flags & CE_REMOVE)
		return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;

	switch (ce->ce_mode & S_IFMT) {
181 182
	case S_IFREG:
		changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
Junio C Hamano's avatar
Junio C Hamano committed
183 184 185 186
		/* We consider only the owner x bit to be relevant for
		 * "mode changes"
		 */
		if (trust_executable_bit &&
187
		    (0100 & (ce->ce_mode ^ st->st_mode)))
188
			changed |= MODE_CHANGED;
189 190
		break;
	case S_IFLNK:
191 192 193
		if (!S_ISLNK(st->st_mode) &&
		    (has_symlinks || !S_ISREG(st->st_mode)))
			changed |= TYPE_CHANGED;
194
		break;
Martin Waitz's avatar
Martin Waitz committed
195
	case S_IFGITLINK:
196
		/* We ignore most of the st_xxx fields for gitlinks */
197 198 199 200
		if (!S_ISDIR(st->st_mode))
			changed |= TYPE_CHANGED;
		else if (ce_compare_gitlink(ce))
			changed |= DATA_CHANGED;
201
		return changed;
202
	default:
203
		die("internal error: ce_mode is %o", ce->ce_mode);
204
	}
205
	if (ce->ce_mtime != (unsigned int) st->st_mtime)
206
		changed |= MTIME_CHANGED;
207
	if (trust_ctime && ce->ce_ctime != (unsigned int) st->st_ctime)
208
		changed |= CTIME_CHANGED;
209

210 211
	if (ce->ce_uid != (unsigned int) st->st_uid ||
	    ce->ce_gid != (unsigned int) st->st_gid)
212
		changed |= OWNER_CHANGED;
213
	if (ce->ce_ino != (unsigned int) st->st_ino)
214
		changed |= INODE_CHANGED;
215 216 217 218 219 220 221

#ifdef USE_STDEV
	/*
	 * st_dev breaks on network filesystems where different
	 * clients will have different views of what "device"
	 * the filesystem is on
	 */
222
	if (ce->ce_dev != (unsigned int) st->st_dev)
223 224 225
		changed |= INODE_CHANGED;
#endif

226
	if (ce->ce_size != (unsigned int) st->st_size)
227
		changed |= DATA_CHANGED;
228

229 230 231 232 233 234
	/* Racily smudged entry? */
	if (!ce->ce_size) {
		if (!is_empty_blob_sha1(ce->sha1))
			changed |= DATA_CHANGED;
	}

Junio C Hamano's avatar
Junio C Hamano committed
235 236 237
	return changed;
}

238
static int is_racy_timestamp(const struct index_state *istate, struct cache_entry *ce)
239
{
240 241
	return (!S_ISGITLINK(ce->ce_mode) &&
		istate->timestamp &&
242 243 244
		((unsigned int)istate->timestamp) <= ce->ce_mtime);
}

245
int ie_match_stat(const struct index_state *istate,
246 247
		  struct cache_entry *ce, struct stat *st,
		  unsigned int options)
Junio C Hamano's avatar
Junio C Hamano committed
248
{
Junio C Hamano's avatar
Junio C Hamano committed
249
	unsigned int changed;
250 251
	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
252 253 254 255 256

	/*
	 * If it's marked as always valid in the index, it's
	 * valid whatever the checked-out copy says.
	 */
257
	if (!ignore_valid && (ce->ce_flags & CE_VALID))
Junio C Hamano's avatar
Junio C Hamano committed
258 259 260
		return 0;

	changed = ce_match_stat_basic(ce, st);
Junio C Hamano's avatar
Junio C Hamano committed
261

Junio C Hamano's avatar
Junio C Hamano committed
262 263 264 265 266 267 268 269 270 271 272 273 274 275
	/*
	 * 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
276
	 * carefully than others.
Junio C Hamano's avatar
Junio C Hamano committed
277
	 */
278
	if (!changed && is_racy_timestamp(istate, ce)) {
279 280 281 282 283
		if (assume_racy_is_modified)
			changed |= DATA_CHANGED;
		else
			changed |= ce_modified_check_fs(ce, st);
	}
284

Junio C Hamano's avatar
Junio C Hamano committed
285
	return changed;
286 287
}

288
int ie_modified(const struct index_state *istate,
289
		struct cache_entry *ce, struct stat *st, unsigned int options)
290
{
Junio C Hamano's avatar
Junio C Hamano committed
291
	int changed, changed_fs;
292 293

	changed = ie_match_stat(istate, ce, st, options);
294 295 296 297 298 299 300 301 302
	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;

303 304 305 306 307 308 309 310 311 312 313 314 315
	/*
	 * Immediately after read-tree or update-index --cacheinfo,
	 * the length field is zero, as we have never even read the
	 * lstat(2) information once, and we cannot trust DATA_CHANGED
	 * returned by ie_match_stat() which in turn was returned by
	 * ce_match_stat_basic() to signal that the filesize of the
	 * blob changed.  We have to actually go to the filesystem to
	 * see if the contents match, and if so, should answer "unchanged".
	 *
	 * The logic does not apply to gitlinks, as ce_match_stat_basic()
	 * already has checked the actual HEAD from the filesystem in the
	 * subproject.  If ie_match_stat() already said it is different,
	 * then we know it is.
316
	 */
317 318
	if ((changed & DATA_CHANGED) &&
	    (S_ISGITLINK(ce->ce_mode) || ce->ce_size != 0))
319 320
		return changed;

Junio C Hamano's avatar
Junio C Hamano committed
321 322 323
	changed_fs = ce_modified_check_fs(ce, st);
	if (changed_fs)
		return changed | changed_fs;
324 325 326
	return 0;
}

327 328 329 330 331 332 333 334 335 336 337 338
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];
339
	if (!c1 && S_ISDIR(mode1))
340
		c1 = '/';
341
	if (!c2 && S_ISDIR(mode2))
342 343 344 345
		c2 = '/';
	return (c1 < c2) ? -1 : (c1 > c2) ? 1 : 0;
}

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
/*
 * 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;
}

381
int cache_name_compare(const char *name1, int flags1, const char *name2, int flags2)
382
{
383 384
	int len1 = flags1 & CE_NAMEMASK;
	int len2 = flags2 & CE_NAMEMASK;
385 386 387 388 389 390 391 392 393 394
	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
395

396 397 398
	/* Compare stages  */
	flags1 &= CE_STAGEMASK;
	flags2 &= CE_STAGEMASK;
Junio C Hamano's avatar
Junio C Hamano committed
399

400 401 402 403
	if (flags1 < flags2)
		return -1;
	if (flags1 > flags2)
		return 1;
404 405 406
	return 0;
}

407
int index_name_pos(const struct index_state *istate, const char *name, int namelen)
408 409 410 411
{
	int first, last;

	first = 0;
412
	last = istate->cache_nr;
413 414
	while (last > first) {
		int next = (last + first) >> 1;
415
		struct cache_entry *ce = istate->cache[next];
416
		int cmp = cache_name_compare(name, namelen, ce->name, ce->ce_flags);
417
		if (!cmp)
418
			return next;
419 420 421 422 423 424
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
425
	return -first-1;
426 427
}

428
/* Remove entry, return true if there are more entries to go.. */
429
int remove_index_entry_at(struct index_state *istate, int pos)
430
{
431 432
	struct cache_entry *ce = istate->cache[pos];

433
	remove_name_hash(ce);
434 435 436
	istate->cache_changed = 1;
	istate->cache_nr--;
	if (pos >= istate->cache_nr)
437
		return 0;
438 439 440
	memmove(istate->cache + pos,
		istate->cache + pos + 1,
		(istate->cache_nr - pos) * sizeof(struct cache_entry *));
441 442 443
	return 1;
}

444
int remove_file_from_index(struct index_state *istate, const char *path)
445
{
446
	int pos = index_name_pos(istate, path, strlen(path));
447 448
	if (pos < 0)
		pos = -pos-1;
Junio C Hamano's avatar
Junio C Hamano committed
449
	cache_tree_invalidate_path(istate->cache_tree, path);
450 451
	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
		remove_index_entry_at(istate, pos);
452 453 454
	return 0;
}

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
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;
}

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
static int different_name(struct cache_entry *ce, struct cache_entry *alias)
{
	int len = ce_namelen(ce);
	return ce_namelen(alias) != len || memcmp(ce->name, alias->name, len);
}

/*
 * If we add a filename that aliases in the cache, we will use the
 * name that we already have - but we don't want to update the same
 * alias twice, because that implies that there were actually two
 * different files with aliasing names!
 *
 * So we use the CE_ADDED flag to verify that the alias was an old
 * one before we accept it as
 */
static struct cache_entry *create_alias_ce(struct cache_entry *ce, struct cache_entry *alias)
{
	int len;
	struct cache_entry *new;

	if (alias->ce_flags & CE_ADDED)
		die("Will not add file alias '%s' ('%s' already exists in index)", ce->name, alias->name);

	/* Ok, create the new entry using the name of the existing alias */
	len = ce_namelen(alias);
	new = xcalloc(1, cache_entry_size(len));
	memcpy(new->name, alias->name, len);
	copy_cache_entry(new, ce);
	free(ce);
	return new;
}

515 516 517 518 519 520 521 522
static void record_intent_to_add(struct cache_entry *ce)
{
	unsigned char sha1[20];
	if (write_sha1_file("", 0, blob_type, sha1))
		die("cannot create an empty blob in the object database");
	hashcpy(ce->sha1, sha1);
}

523
int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
Johannes Schindelin's avatar
Johannes Schindelin committed
524
{
525
	int size, namelen, was_same;
526
	mode_t st_mode = st->st_mode;
527
	struct cache_entry *ce, *alias;
528
	unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_RACY_IS_DIRTY;
529 530
	int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
	int pretend = flags & ADD_CACHE_PRETEND;
531 532 533
	int intent_only = flags & ADD_CACHE_INTENT;
	int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE|
			  (intent_only ? ADD_CACHE_NEW_ONLY : 0));
Johannes Schindelin's avatar
Johannes Schindelin committed
534

535
	if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
536
		return error("%s: can only add regular files, symbolic links or git-directories", path);
Johannes Schindelin's avatar
Johannes Schindelin committed
537 538

	namelen = strlen(path);
539
	if (S_ISDIR(st_mode)) {
540 541 542
		while (namelen && path[namelen-1] == '/')
			namelen--;
	}
Johannes Schindelin's avatar
Johannes Schindelin committed
543 544 545
	size = cache_entry_size(namelen);
	ce = xcalloc(1, size);
	memcpy(ce->name, path, namelen);
546
	ce->ce_flags = namelen;
547 548
	if (!intent_only)
		fill_stat_cache_info(ce, st);
549 550
	else
		ce->ce_flags |= CE_INTENT_TO_ADD;
Johannes Schindelin's avatar
Johannes Schindelin committed
551

552
	if (trust_executable_bit && has_symlinks)
553
		ce->ce_mode = create_ce_mode(st_mode);
554
	else {
555 556
		/* 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
557
		 */
558
		struct cache_entry *ent;
559
		int pos = index_name_pos_also_unmerged(istate, path, namelen);
560

561
		ent = (0 <= pos) ? istate->cache[pos] : NULL;
562
		ce->ce_mode = ce_mode_from_stat(ent, st_mode);
Johannes Schindelin's avatar
Johannes Schindelin committed
563 564
	}

565
	alias = index_name_exists(istate, ce->name, ce_namelen(ce), ignore_case);
566
	if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
567 568
		/* Nothing changed, really */
		free(ce);
569
		ce_mark_uptodate(alias);
570
		alias->ce_flags |= CE_ADDED;
571 572
		return 0;
	}
573 574 575 576 577 578
	if (!intent_only) {
		if (index_path(ce->sha1, path, st, 1))
			return error("unable to index file %s", path);
	} else
		record_intent_to_add(ce);

579 580 581
	if (ignore_case && alias && different_name(ce, alias))
		ce = create_alias_ce(ce, alias);
	ce->ce_flags |= CE_ADDED;
582

Junio C Hamano's avatar
Junio C Hamano committed
583
	/* It was suspected to be racily clean, but it turns out to be Ok */
584 585 586 587 588 589 590
	was_same = (alias &&
		    !ce_stage(alias) &&
		    !hashcmp(alias->sha1, ce->sha1) &&
		    ce->ce_mode == alias->ce_mode);

	if (pretend)
		;
591
	else if (add_index_entry(istate, ce, add_option))
592
		return error("unable to add %s to index",path);
593
	if (verbose && !was_same)
Johannes Schindelin's avatar
Johannes Schindelin committed
594 595 596 597
		printf("add '%s'\n", path);
	return 0;
}

598
int add_file_to_index(struct index_state *istate, const char *path, int flags)
599 600 601 602
{
	struct stat st;
	if (lstat(path, &st))
		die("%s: unable to stat (%s)", path, strerror(errno));
603
	return add_to_index(istate, path, &st, flags);
604 605
}

606 607 608 609 610 611 612
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;

613 614
	if (!verify_path(path)) {
		error("Invalid path '%s'", path);
615
		return NULL;
616
	}
617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632

	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;
}

633
int ce_same_name(struct cache_entry *a, struct cache_entry *b)
634 635 636 637 638
{
	int len = ce_namelen(a);
	return ce_namelen(b) == len && !memcmp(a->name, b->name, len);
}

639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658
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;
659 660
		if (!matchlen)
			return 1;
661 662 663 664
	}
	return 0;
}

665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728
/*
 * 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++;
	}
}

729 730 731
/*
 * Do we have another file that has the beginning components being a
 * proper superset of the name we're trying to add?
732
 */
733 734
static int has_file_name(struct index_state *istate,
			 const struct cache_entry *ce, int pos, int ok_to_replace)
735
{
736 737
	int retval = 0;
	int len = ce_namelen(ce);
738
	int stage = ce_stage(ce);
739
	const char *name = ce->name;
740

741 742
	while (pos < istate->cache_nr) {
		struct cache_entry *p = istate->cache[pos++];
743

744
		if (len >= ce_namelen(p))
745
			break;
746 747
		if (memcmp(name, p->name, len))
			break;
748 749
		if (ce_stage(p) != stage)
			continue;
750 751
		if (p->name[len] != '/')
			continue;
752
		if (p->ce_flags & CE_REMOVE)
753
			continue;
754 755 756
		retval = -1;
		if (!ok_to_replace)
			break;
757
		remove_index_entry_at(istate, --pos);
758
	}
759 760
	return retval;
}
761

762 763 764 765
/*
 * Do we have another file with a pathname that is a proper
 * subset of the name we're trying to add?
 */
766 767
static int has_dir_name(struct index_state *istate,
			const struct cache_entry *ce, int pos, int ok_to_replace)
768 769
{
	int retval = 0;
770
	int stage = ce_stage(ce);
771 772
	const char *name = ce->name;
	const char *slash = name + ce_namelen(ce);
773

774 775
	for (;;) {
		int len;
776

777 778 779 780 781 782 783
		for (;;) {
			if (*--slash == '/')
				break;
			if (slash <= ce->name)
				return retval;
		}
		len = slash - name;
784

785
		pos = index_name_pos(istate, name, create_ce_flags(len, stage));
786
		if (pos >= 0) {
787 788 789 790 791 792 793 794
			/*
			 * 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.
			 */
795
			if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
796 797 798
				retval = -1;
				if (!ok_to_replace)
					break;
799
				remove_index_entry_at(istate, pos);
800 801
				continue;
			}
802
		}
803 804
		else
			pos = -pos-1;
805 806 807 808

		/*
		 * Trivial optimization: if we find an entry that
		 * already matches the sub-directory, then we know
809
		 * we're ok, and we can exit.
810
		 */
811 812
		while (pos < istate->cache_nr) {
			struct cache_entry *p = istate->cache[pos];
813 814 815 816
			if ((ce_namelen(p) <= len) ||
			    (p->name[len] != '/') ||
			    memcmp(p->name, name, len))
				break; /* not our subdirectory */
817 818 819
			if (ce_stage(p) == stage && !(p->ce_flags & CE_REMOVE))
				/*
				 * p is at the same stage as our entry, and
820 821 822 823 824 825
				 * is a subdirectory of what we are looking
				 * at, so we cannot have conflicts at our
				 * level or anything shorter.
				 */
				return retval;
			pos++;
826
		}
827
	}
828 829 830 831 832 833 834
	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
835
 *
836 837 838 839
 * 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.
 */
840 841 842
static int check_file_directory_conflict(struct index_state *istate,
					 const struct cache_entry *ce,
					 int pos, int ok_to_replace)
843
{
844 845 846 847 848
	int retval;

	/*
	 * When ce is an "I am going away" entry, we allow it to be added
	 */
849
	if (ce->ce_flags & CE_REMOVE)
850 851
		return 0;

852 853 854
	/*
	 * We check if the path is a sub-path of a subsequent pathname
	 * first, since removing those will not change the position
855
	 * in the array.
856
	 */
857
	retval = has_file_name(istate, ce, pos, ok_to_replace);
858

859 860 861 862
	/*
	 * Then check if the path might have a clashing sub-directory
	 * before it.
	 */
863
	return retval + has_dir_name(istate, ce, pos, ok_to_replace);
864 865
}

866
static int add_index_entry_with_check(struct index_state *istate, struct cache_entry *ce, int option)
867 868
{
	int pos;
869 870
	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
871
	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
872
	int new_only = option & ADD_CACHE_NEW_ONLY;
Junio C Hamano's avatar
Junio C Hamano committed
873

Junio C Hamano's avatar
Junio C Hamano committed
874
	cache_tree_invalidate_path(istate->cache_tree, ce->name);
875
	pos = index_name_pos(istate, ce->name, ce->ce_flags);
876

Junio C Hamano's avatar
Junio C Hamano committed
877
	/* existing match? Just replace it. */
878
	if (pos >= 0) {
879 880
		if (!new_only)
			replace_index_entry(istate, pos, ce);
881 882
		return 0;
	}
883
	pos = -pos-1;
884

885 886 887 888
	/*
	 * Inserting a merged entry ("stage 0") into the index
	 * will always replace all non-merged entries..
	 */
889 890
	if (pos < istate->cache_nr && ce_stage(ce) == 0) {
		while (ce_same_name(istate->cache[pos], ce)) {
891
			ok_to_add = 1;
892
			if (!remove_index_entry_at(istate, pos))
893 894 895 896
				break;
		}
	}

897 898
	if (!ok_to_add)
		return -1;
899
	if (!verify_path(ce->name))
900
		return error("Invalid path '%s'", ce->name);
901

Junio C Hamano's avatar
Junio C Hamano committed
902
	if (!skip_df_check &&
903
	    check_file_directory_conflict(istate, ce, pos, ok_to_replace)) {
904
		if (!ok_to_replace)
905 906
			return error("'%s' appears as both a file and as a directory",
				     ce->name);
907
		pos = index_name_pos(istate, ce->name, ce->ce_flags);
908 909
		pos = -pos-1;
	}
910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925
	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;
	}
926

927
	/* Make sure the array is big enough .. */
928 929 930 931
	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 *));
932 933 934
	}

	/* Add it in.. */
935
	istate->cache_nr++;
936
	if (istate->cache_nr > pos + 1)
937 938 939
		memmove(istate->cache + pos + 1,
			istate->cache + pos,
			(istate->cache_nr - pos - 1) * sizeof(ce));
940
	set_index_entry(istate, pos, ce);
941
	istate->cache_changed = 1;
942 943 944
	return 0;
}

945 946 947 948 949 950 951 952 953 954 955
/*
 * "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.
 */
956
static struct cache_entry *refresh_cache_ent(struct index_state *istate,
957 958
					     struct cache_entry *ce,
					     unsigned int options, int *err)
959 960 961 962
{
	struct stat st;
	struct cache_entry *updated;
	int changed, size;
963
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
964

965 966 967
	if (ce_uptodate(ce))
		return ce;

968 969 970 971 972 973 974 975 976
	/*
	 * CE_VALID means the user promised us that the change to
	 * the work tree does not matter and told us not to worry.
	 */
	if (!ignore_valid && (ce->ce_flags & CE_VALID)) {
		ce_mark_uptodate(ce);
		return ce;
	}

977
	if (lstat(ce->name, &st) < 0) {
978 979
		if (err)
			*err = errno;
980 981
		return NULL;
	}
982

983
	changed = ie_match_stat(istate, ce, &st, options);
984
	if (!changed) {
985 986 987 988 989 990 991 992
		/*
		 * 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 &&
993
		    !(ce->ce_flags & CE_VALID))
994
			; /* mark this one VALID again */
995 996 997 998 999 1000 1001
		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);
1002
			return ce;
1003
		}
1004 1005
	}

1006
	if (ie_modified(istate, ce, &st, options)) {
1007 1008
		if (err)
			*err = EINVAL;
1009 1010
		return NULL;
	}
1011 1012 1013 1014 1015

	size = ce_size(ce);
	updated = xmalloc(size);
	memcpy(updated, ce, size);
	fill_stat_cache_info(updated, &st);
1016 1017 1018 1019 1020
	/*
	 * 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.
1021
	 */
1022
	if (!ignore_valid && assume_unchanged &&
1023 1024
	    !(ce->ce_flags & CE_VALID))
		updated->ce_flags &= ~CE_VALID;
1025 1026 1027 1028

	return updated;
}

1029
int refresh_index(struct index_state *istate, unsigned int flags, const char **pathspec, char *seen)
1030 1031 1032 1033 1034 1035 1036
{
	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;
1037
	int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0;
1038
	unsigned int options = really ? CE_MATCH_IGNORE_VALID : 0;
1039
	const char *needs_update_message;
1040

1041 1042
	needs_update_message = ((flags & REFRESH_SAY_CHANGED)
				? "locally modified" : "needs update");
1043
	for (i = 0; i < istate->cache_nr; i++) {
1044
		struct cache_entry *ce, *new;
1045 1046
		int cache_errno = 0;

1047
		ce = istate->cache[i];
1048 1049 1050
		if (ignore_submodules && S_ISGITLINK(ce->ce_mode))
			continue;

1051
		if (ce_stage(ce)) {
1052 1053
			while ((i < istate->cache_nr) &&
			       ! strcmp(istate->cache[i]->name, ce->name))
1054 1055 1056 1057 1058 1059 1060 1061 1062
				i++;
			i--;
			if (allow_unmerged)
				continue;
			printf("%s: needs merge\n", ce->name);
			has_errors = 1;
			continue;
		}

1063 1064 1065
		if (pathspec && !match_pathspec(pathspec, ce->name, strlen(ce->name), 0, seen))
			continue;

1066
		new = refresh_cache_ent(istate, ce, options, &cache_errno);
1067
		if (new == ce)
1068
			continue;
1069 1070
		if (!new) {
			if (not_new && cache_errno == ENOENT)
1071
				continue;
1072
			if (really && cache_errno == EINVAL) {
1073 1074 1075
				/* If we are doing --really-refresh that
				 * means the index is not valid anymore.
				 */
1076
				ce->ce_flags &= ~CE_VALID;
1077
				istate->cache_changed = 1;
1078 1079 1080
			}
			if (quiet)
				continue;
1081
			printf("%s: %s\n", ce->name, needs_update_message);
1082 1083 1084
			has_errors = 1;
			continue;
		}
1085 1086

		replace_index_entry(istate, i, new);
1087 1088 1089 1090
	}
	return has_errors;
}

1091 1092
struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really)
{
1093
	return refresh_cache_ent(&the_index, ce, really, NULL);
1094 1095
}

1096
static int verify_hdr(struct cache_header *hdr, unsigned long size)
1097
{
1098
	git_SHA_CTX c;
1099
	unsigned char sha1[20];
1100

1101
	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
1102
		return error("bad signature");
Duy Nguyen's avatar
Duy Nguyen committed
1103
	if (hdr->hdr_version != htonl(2) && hdr->hdr_version != htonl(3))
1104
		return error("bad index version");
1105 1106 1107
	git_SHA1_Init(&c);
	git_SHA1_Update(&c, hdr, size - 20);
	git_SHA1_Final(sha1, &c);
1108
	if (hashcmp(sha1, (unsigned char *)hdr + size - 20))
1109
		return error("bad index file sha1 signature");
1110 1111 1112
	return 0;
}

1113 1114
static int read_index_extension(struct index_state *istate,
				const char *ext, void *data, unsigned long sz)
1115 1116 1117
{
	switch (CACHE_EXT(ext)) {
	case CACHE_EXT_TREE:
1118
		istate->cache_tree = cache_tree_read(data, sz);
1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129
		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;
}

1130
int read_index(struct index_state *istate)
1131
{
1132
	return read_index_from(istate, get_index_file());
1133 1134
}

1135 1136
static void convert_from_disk(struct ondisk_cache_entry *ondisk, struct cache_entry *ce)
{
1137
	size_t len;
Duy Nguyen's avatar
Duy Nguyen committed
1138
	const char *name;
1139

1140 1141 1142 1143 1144 1145 1146 1147 1148 1149
	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);
1150

1151
	hashcpy(ce->sha1, ondisk->sha1);
1152 1153

	len = ce->ce_flags & CE_NAMEMASK;
Duy Nguyen's avatar
Duy Nguyen committed
1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168

	if (ce->ce_flags & CE_EXTENDED) {
		struct ondisk_cache_entry_extended *ondisk2;
		int extended_flags;
		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
		extended_flags = ntohs(ondisk2->flags2) << 16;
		/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
		if (extended_flags & ~CE_EXTENDED_FLAGS)
			die("Unknown index entry format %08x", extended_flags);
		ce->ce_flags |= extended_flags;
		name = ondisk2->name;
	}
	else
		name = ondisk->name;

1169
	if (len == CE_NAMEMASK)
Duy Nguyen's avatar
Duy Nguyen committed
1170
		len = strlen(name);
1171 1172 1173 1174
	/*
	 * NEEDSWORK: If the original index is crafted, this copy could
	 * go unchecked.
	 */
Duy Nguyen's avatar
Duy Nguyen committed
1175
	memcpy(ce->name, name, len + 1);
1176 1177
}

1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191
static inline size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)
{
	long per_entry