packfile.c 53.6 KB
Newer Older
1
#include "cache.h"
2
#include "list.h"
3
#include "pack.h"
4
#include "repository.h"
5 6 7
#include "dir.h"
#include "mergesort.h"
#include "packfile.h"
8
#include "delta.h"
9 10
#include "list.h"
#include "streaming.h"
11
#include "sha1-lookup.h"
12 13 14 15 16
#include "commit.h"
#include "object.h"
#include "tag.h"
#include "tree-walk.h"
#include "tree.h"
17
#include "object-store.h"
18
#include "midx.h"
19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40

char *odb_pack_name(struct strbuf *buf,
		    const unsigned char *sha1,
		    const char *ext)
{
	strbuf_reset(buf);
	strbuf_addf(buf, "%s/pack/pack-%s.%s", get_object_directory(),
		    sha1_to_hex(sha1), ext);
	return buf->buf;
}

char *sha1_pack_name(const unsigned char *sha1)
{
	static struct strbuf buf = STRBUF_INIT;
	return odb_pack_name(&buf, sha1, "pack");
}

char *sha1_pack_index_name(const unsigned char *sha1)
{
	static struct strbuf buf = STRBUF_INIT;
	return odb_pack_name(&buf, sha1, "idx");
}
41

Jonathan Tan's avatar
Jonathan Tan committed
42 43 44 45
static unsigned int pack_used_ctr;
static unsigned int pack_mmap_calls;
static unsigned int peak_pack_open_windows;
static unsigned int pack_open_windows;
46
static unsigned int pack_open_fds;
Jonathan Tan's avatar
Jonathan Tan committed
47 48 49
static unsigned int pack_max_fds;
static size_t peak_pack_mapped;
static size_t pack_mapped;
Jonathan Tan's avatar
Jonathan Tan committed
50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73

#define SZ_FMT PRIuMAX
static inline uintmax_t sz_fmt(size_t s) { return s; }

void pack_report(void)
{
	fprintf(stderr,
		"pack_report: getpagesize()            = %10" SZ_FMT "\n"
		"pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n"
		"pack_report: core.packedGitLimit      = %10" SZ_FMT "\n",
		sz_fmt(getpagesize()),
		sz_fmt(packed_git_window_size),
		sz_fmt(packed_git_limit));
	fprintf(stderr,
		"pack_report: pack_used_ctr            = %10u\n"
		"pack_report: pack_mmap_calls          = %10u\n"
		"pack_report: pack_open_windows        = %10u / %10u\n"
		"pack_report: pack_mapped              = "
			"%10" SZ_FMT " / %10" SZ_FMT "\n",
		pack_used_ctr,
		pack_mmap_calls,
		pack_open_windows, peak_pack_open_windows,
		sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped));
}
74 75 76 77 78 79 80 81 82 83

/*
 * Open and mmap the index file at path, perform a couple of
 * consistency checks, then record its information to p.  Return 0 on
 * success.
 */
static int check_packed_git_idx(const char *path, struct packed_git *p)
{
	void *idx_map;
	size_t idx_size;
84
	int fd = git_open(path), ret;
85
	struct stat st;
86
	const unsigned int hashsz = the_hash_algo->rawsz;
87 88 89 90 91 92 93 94

	if (fd < 0)
		return -1;
	if (fstat(fd, &st)) {
		close(fd);
		return -1;
	}
	idx_size = xsize_t(st.st_size);
95
	if (idx_size < 4 * 256 + hashsz + hashsz) {
96 97 98 99 100 101
		close(fd);
		return error("index file %s is too small", path);
	}
	idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0);
	close(fd);

102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120
	ret = load_idx(path, hashsz, idx_map, idx_size, p);

	if (ret)
		munmap(idx_map, idx_size);

	return ret;
}

int load_idx(const char *path, const unsigned int hashsz, void *idx_map,
	     size_t idx_size, struct packed_git *p)
{
	struct pack_idx_header *hdr = idx_map;
	uint32_t version, nr, i, *index;

	if (idx_size < 4 * 256 + hashsz + hashsz)
		return error("index file %s is too small", path);
	if (idx_map == NULL)
		return error("empty data");

121 122
	if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) {
		version = ntohl(hdr->idx_version);
123
		if (version < 2 || version > 2)
124 125 126 127 128 129 130 131 132 133 134 135 136
			return error("index file %s is version %"PRIu32
				     " and is not supported by this binary"
				     " (try upgrading GIT to a newer version)",
				     path, version);
	} else
		version = 1;

	nr = 0;
	index = idx_map;
	if (version > 1)
		index += 2;  /* skip index header */
	for (i = 0; i < 256; i++) {
		uint32_t n = ntohl(index[i]);
137
		if (n < nr)
138 139 140 141 142 143 144 145
			return error("non-monotonic index %s", path);
		nr = n;
	}

	if (version == 1) {
		/*
		 * Total size:
		 *  - 256 index entries 4 bytes each
146 147 148
		 *  - 24-byte entries * nr (object ID + 4-byte offset)
		 *  - hash of the packfile
		 *  - file checksum
149
		 */
150
		if (idx_size != 4 * 256 + nr * (hashsz + 4) + hashsz + hashsz)
151 152 153 154 155 156
			return error("wrong index v1 file size in %s", path);
	} else if (version == 2) {
		/*
		 * Minimum size:
		 *  - 8 bytes of header
		 *  - 256 index entries 4 bytes each
157
		 *  - object ID entry * nr
158 159
		 *  - 4-byte crc entry * nr
		 *  - 4-byte offset entry * nr
160 161
		 *  - hash of the packfile
		 *  - file checksum
162 163 164 165
		 * And after the 4-byte offset table might be a
		 * variable sized table containing 8-byte entries
		 * for offsets larger than 2^31.
		 */
166
		unsigned long min_size = 8 + 4*256 + nr*(hashsz + 4 + 4) + hashsz + hashsz;
167 168 169
		unsigned long max_size = min_size;
		if (nr)
			max_size += (nr - 1)*8;
170
		if (idx_size < min_size || idx_size > max_size)
171 172 173 174 175 176 177
			return error("wrong index v2 file size in %s", path);
		if (idx_size != min_size &&
		    /*
		     * make sure we can deal with large pack offsets.
		     * 31-bit signed offset won't be enough, neither
		     * 32-bit unsigned one will be.
		     */
178
		    (sizeof(off_t) <= 4))
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198
			return error("pack too large for current definition of off_t in %s", path);
	}

	p->index_version = version;
	p->index_data = idx_map;
	p->index_size = idx_size;
	p->num_objects = nr;
	return 0;
}

int open_pack_index(struct packed_git *p)
{
	char *idx_name;
	size_t len;
	int ret;

	if (p->index_data)
		return 0;

	if (!strip_suffix(p->pack_name, ".pack", &len))
199
		BUG("pack_name does not end in .pack");
200 201 202 203 204 205
	idx_name = xstrfmt("%.*s.idx", (int)len, p->pack_name);
	ret = check_packed_git_idx(idx_name, p);
	free(idx_name);
	return ret;
}

206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222
uint32_t get_pack_fanout(struct packed_git *p, uint32_t value)
{
	const uint32_t *level1_ofs = p->index_data;

	if (!level1_ofs) {
		if (open_pack_index(p))
			return 0;
		level1_ofs = p->index_data;
	}

	if (p->index_version > 1) {
		level1_ofs += 2;
	}

	return ntohl(level1_ofs[value]);
}

223 224 225 226 227 228 229 230 231 232 233 234 235 236 237
static struct packed_git *alloc_packed_git(int extra)
{
	struct packed_git *p = xmalloc(st_add(sizeof(*p), extra));
	memset(p, 0, sizeof(*p));
	p->pack_fd = -1;
	return p;
}

struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
{
	const char *path = sha1_pack_name(sha1);
	size_t alloc = st_add(strlen(path), 1);
	struct packed_git *p = alloc_packed_git(alloc);

	memcpy(p->pack_name, path, alloc); /* includes NUL */
238
	hashcpy(p->hash, sha1);
239 240 241 242 243 244 245
	if (check_packed_git_idx(idx_path, p)) {
		free(p);
		return NULL;
	}

	return p;
}
246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265

static void scan_windows(struct packed_git *p,
	struct packed_git **lru_p,
	struct pack_window **lru_w,
	struct pack_window **lru_l)
{
	struct pack_window *w, *w_l;

	for (w_l = NULL, w = p->windows; w; w = w->next) {
		if (!w->inuse_cnt) {
			if (!*lru_w || w->last_used < (*lru_w)->last_used) {
				*lru_p = p;
				*lru_w = w;
				*lru_l = w_l;
			}
		}
		w_l = w;
	}
}

Jonathan Tan's avatar
Jonathan Tan committed
266
static int unuse_one_window(struct packed_git *current)
267 268 269 270 271 272
{
	struct packed_git *p, *lru_p = NULL;
	struct pack_window *lru_w = NULL, *lru_l = NULL;

	if (current)
		scan_windows(current, &lru_p, &lru_w, &lru_l);
273
	for (p = the_repository->objects->packed_git; p; p = p->next)
274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294
		scan_windows(p, &lru_p, &lru_w, &lru_l);
	if (lru_p) {
		munmap(lru_w->base, lru_w->len);
		pack_mapped -= lru_w->len;
		if (lru_l)
			lru_l->next = lru_w->next;
		else
			lru_p->windows = lru_w->next;
		free(lru_w);
		pack_open_windows--;
		return 1;
	}
	return 0;
}

void release_pack_memory(size_t need)
{
	size_t cur = pack_mapped;
	while (need >= (cur - pack_mapped) && unuse_one_window(NULL))
		; /* nothing */
}
295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311

void close_pack_windows(struct packed_git *p)
{
	while (p->windows) {
		struct pack_window *w = p->windows;

		if (w->inuse_cnt)
			die("pack '%s' still has open windows to it",
			    p->pack_name);
		munmap(w->base, w->len);
		pack_mapped -= w->len;
		pack_open_windows--;
		p->windows = w->next;
		free(w);
	}
}

312
int close_pack_fd(struct packed_git *p)
313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331
{
	if (p->pack_fd < 0)
		return 0;

	close(p->pack_fd);
	pack_open_fds--;
	p->pack_fd = -1;

	return 1;
}

void close_pack_index(struct packed_git *p)
{
	if (p->index_data) {
		munmap((void *)p->index_data, p->index_size);
		p->index_data = NULL;
	}
}

332
void close_pack(struct packed_git *p)
333 334 335 336 337 338
{
	close_pack_windows(p);
	close_pack_fd(p);
	close_pack_index(p);
}

339
void close_all_packs(struct raw_object_store *o)
340 341 342
{
	struct packed_git *p;

343
	for (p = o->packed_git; p; p = p->next)
344
		if (p->do_not_close)
345
			BUG("want to close pack marked 'do-not-close'");
346 347
		else
			close_pack(p);
348 349 350 351 352

	if (o->multi_pack_index) {
		close_midx(o->multi_pack_index);
		o->multi_pack_index = NULL;
	}
353
}
Jonathan Tan's avatar
Jonathan Tan committed
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

/*
 * The LRU pack is the one with the oldest MRU window, preferring packs
 * with no used windows, or the oldest mtime if it has no windows allocated.
 */
static void find_lru_pack(struct packed_git *p, struct packed_git **lru_p, struct pack_window **mru_w, int *accept_windows_inuse)
{
	struct pack_window *w, *this_mru_w;
	int has_windows_inuse = 0;

	/*
	 * Reject this pack if it has windows and the previously selected
	 * one does not.  If this pack does not have windows, reject
	 * it if the pack file is newer than the previously selected one.
	 */
	if (*lru_p && !*mru_w && (p->windows || p->mtime > (*lru_p)->mtime))
		return;

	for (w = this_mru_w = p->windows; w; w = w->next) {
		/*
		 * Reject this pack if any of its windows are in use,
		 * but the previously selected pack did not have any
		 * inuse windows.  Otherwise, record that this pack
		 * has windows in use.
		 */
		if (w->inuse_cnt) {
			if (*accept_windows_inuse)
				has_windows_inuse = 1;
			else
				return;
		}

		if (w->last_used > this_mru_w->last_used)
			this_mru_w = w;

		/*
		 * Reject this pack if it has windows that have been
		 * used more recently than the previously selected pack.
		 * If the previously selected pack had windows inuse and
		 * we have not encountered a window in this pack that is
		 * inuse, skip this check since we prefer a pack with no
		 * inuse windows to one that has inuse windows.
		 */
		if (*mru_w && *accept_windows_inuse == has_windows_inuse &&
		    this_mru_w->last_used > (*mru_w)->last_used)
			return;
	}

	/*
	 * Select this pack.
	 */
	*mru_w = this_mru_w;
	*lru_p = p;
	*accept_windows_inuse = has_windows_inuse;
}

static int close_one_pack(void)
{
	struct packed_git *p, *lru_p = NULL;
	struct pack_window *mru_w = NULL;
	int accept_windows_inuse = 1;

416
	for (p = the_repository->objects->packed_git; p; p = p->next) {
Jonathan Tan's avatar
Jonathan Tan committed
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
		if (p->pack_fd == -1)
			continue;
		find_lru_pack(p, &lru_p, &mru_w, &accept_windows_inuse);
	}

	if (lru_p)
		return close_pack_fd(lru_p);

	return 0;
}

static unsigned int get_max_fd_limit(void)
{
#ifdef RLIMIT_NOFILE
	{
		struct rlimit lim;

		if (!getrlimit(RLIMIT_NOFILE, &lim))
			return lim.rlim_cur;
	}
#endif

#ifdef _SC_OPEN_MAX
	{
		long open_max = sysconf(_SC_OPEN_MAX);
		if (0 < open_max)
			return open_max;
		/*
		 * Otherwise, we got -1 for one of the two
		 * reasons:
		 *
		 * (1) sysconf() did not understand _SC_OPEN_MAX
		 *     and signaled an error with -1; or
		 * (2) sysconf() said there is no limit.
		 *
		 * We _could_ clear errno before calling sysconf() to
		 * tell these two cases apart and return a huge number
		 * in the latter case to let the caller cap it to a
		 * value that is not so selfish, but letting the
		 * fallback OPEN_MAX codepath take care of these cases
		 * is a lot simpler.
		 */
	}
#endif

#ifdef OPEN_MAX
	return OPEN_MAX;
#else
	return 1; /* see the caller ;-) */
#endif
}

469 470 471 472 473 474 475 476 477 478
const char *pack_basename(struct packed_git *p)
{
	const char *ret = strrchr(p->pack_name, '/');
	if (ret)
		ret = ret + 1; /* skip past slash */
	else
		ret = p->pack_name; /* we only have a base */
	return ret;
}

Jonathan Tan's avatar
Jonathan Tan committed
479 480 481 482 483 484 485 486
/*
 * Do not call this directly as this leaks p->pack_fd on error return;
 * call open_packed_git() instead.
 */
static int open_packed_git_1(struct packed_git *p)
{
	struct stat st;
	struct pack_header hdr;
487 488
	unsigned char hash[GIT_MAX_RAWSZ];
	unsigned char *idx_hash;
Jonathan Tan's avatar
Jonathan Tan committed
489
	long fd_flag;
490
	ssize_t read_result;
491
	const unsigned hashsz = the_hash_algo->rawsz;
Jonathan Tan's avatar
Jonathan Tan committed
492

493 494
	if (!p->index_data) {
		struct multi_pack_index *m;
495
		const char *pack_name = pack_basename(p);
496 497 498 499 500 501 502 503 504 505

		for (m = the_repository->objects->multi_pack_index;
		     m; m = m->next) {
			if (midx_contains_pack(m, pack_name))
				break;
		}

		if (!m && open_pack_index(p))
			return error("packfile %s index unavailable", p->pack_name);
	}
Jonathan Tan's avatar
Jonathan Tan committed
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

	if (!pack_max_fds) {
		unsigned int max_fds = get_max_fd_limit();

		/* Save 3 for stdin/stdout/stderr, 22 for work */
		if (25 < max_fds)
			pack_max_fds = max_fds - 25;
		else
			pack_max_fds = 1;
	}

	while (pack_max_fds <= pack_open_fds && close_one_pack())
		; /* nothing */

	p->pack_fd = git_open(p->pack_name);
	if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
		return -1;
	pack_open_fds++;

	/* If we created the struct before we had the pack we lack size. */
	if (!p->pack_size) {
		if (!S_ISREG(st.st_mode))
			return error("packfile %s not a regular file", p->pack_name);
		p->pack_size = st.st_size;
	} else if (p->pack_size != st.st_size)
		return error("packfile %s size changed", p->pack_name);

	/* We leave these file descriptors open with sliding mmap;
	 * there is no point keeping them open across exec(), though.
	 */
	fd_flag = fcntl(p->pack_fd, F_GETFD, 0);
	if (fd_flag < 0)
		return error("cannot determine file descriptor flags");
	fd_flag |= FD_CLOEXEC;
	if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1)
		return error("cannot set FD_CLOEXEC");

	/* Verify we recognize this pack file format. */
544 545 546 547
	read_result = read_in_full(p->pack_fd, &hdr, sizeof(hdr));
	if (read_result < 0)
		return error_errno("error reading from %s", p->pack_name);
	if (read_result != sizeof(hdr))
Jonathan Tan's avatar
Jonathan Tan committed
548 549 550 551 552 553 554 555
		return error("file %s is far too short to be a packfile", p->pack_name);
	if (hdr.hdr_signature != htonl(PACK_SIGNATURE))
		return error("file %s is not a GIT packfile", p->pack_name);
	if (!pack_version_ok(hdr.hdr_version))
		return error("packfile %s is version %"PRIu32" and not"
			" supported (try upgrading GIT to a newer version)",
			p->pack_name, ntohl(hdr.hdr_version));

556 557 558 559
	/* Skip index checking if in multi-pack-index */
	if (!p->index_data)
		return 0;

Jonathan Tan's avatar
Jonathan Tan committed
560 561 562 563 564 565
	/* Verify the pack matches its index. */
	if (p->num_objects != ntohl(hdr.hdr_entries))
		return error("packfile %s claims to have %"PRIu32" objects"
			     " while index indicates %"PRIu32" objects",
			     p->pack_name, ntohl(hdr.hdr_entries),
			     p->num_objects);
566
	if (lseek(p->pack_fd, p->pack_size - hashsz, SEEK_SET) == -1)
Jonathan Tan's avatar
Jonathan Tan committed
567
		return error("end of packfile %s is unavailable", p->pack_name);
568
	read_result = read_in_full(p->pack_fd, hash, hashsz);
569 570
	if (read_result < 0)
		return error_errno("error reading from %s", p->pack_name);
571
	if (read_result != hashsz)
Jonathan Tan's avatar
Jonathan Tan committed
572
		return error("packfile %s signature is unavailable", p->pack_name);
573
	idx_hash = ((unsigned char *)p->index_data) + p->index_size - hashsz * 2;
574
	if (!hasheq(hash, idx_hash))
Jonathan Tan's avatar
Jonathan Tan committed
575 576 577 578
		return error("packfile %s does not match index", p->pack_name);
	return 0;
}

579
static int open_packed_git(struct packed_git *p)
Jonathan Tan's avatar
Jonathan Tan committed
580 581 582 583 584 585 586 587 588
{
	if (!open_packed_git_1(p))
		return 0;
	close_pack_fd(p);
	return -1;
}

static int in_window(struct pack_window *win, off_t offset)
{
589
	/* We must promise at least one full hash after the
Jonathan Tan's avatar
Jonathan Tan committed
590 591 592 593 594 595 596
	 * offset is available from this window, otherwise the offset
	 * is not actually in this window and a different window (which
	 * has that one hash excess) must be used.  This is to support
	 * the object header and delta base parsing routines below.
	 */
	off_t win_off = win->offset;
	return win_off <= offset
597
		&& (offset + the_hash_algo->rawsz) <= (win_off + win->len);
Jonathan Tan's avatar
Jonathan Tan committed
598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613
}

unsigned char *use_pack(struct packed_git *p,
		struct pack_window **w_cursor,
		off_t offset,
		unsigned long *left)
{
	struct pack_window *win = *w_cursor;

	/* Since packfiles end in a hash of their content and it's
	 * pointless to ask for an offset into the middle of that
	 * hash, and the in_window function above wouldn't match
	 * don't allow an offset too close to the end of the file.
	 */
	if (!p->pack_size && p->pack_fd == -1 && open_packed_git(p))
		die("packfile %s cannot be accessed", p->pack_name);
614
	if (offset > (p->pack_size - the_hash_algo->rawsz))
Jonathan Tan's avatar
Jonathan Tan committed
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
		die("offset beyond end of packfile (truncated pack?)");
	if (offset < 0)
		die(_("offset before end of packfile (broken .idx?)"));

	if (!win || !in_window(win, offset)) {
		if (win)
			win->inuse_cnt--;
		for (win = p->windows; win; win = win->next) {
			if (in_window(win, offset))
				break;
		}
		if (!win) {
			size_t window_align = packed_git_window_size / 2;
			off_t len;

			if (p->pack_fd == -1 && open_packed_git(p))
				die("packfile %s cannot be accessed", p->pack_name);

			win = xcalloc(1, sizeof(*win));
			win->offset = (offset / window_align) * window_align;
			len = p->pack_size - win->offset;
			if (len > packed_git_window_size)
				len = packed_git_window_size;
			win->len = (size_t)len;
			pack_mapped += win->len;
			while (packed_git_limit < pack_mapped
				&& unuse_one_window(p))
				; /* nothing */
			win->base = xmmap(NULL, win->len,
				PROT_READ, MAP_PRIVATE,
				p->pack_fd, win->offset);
			if (win->base == MAP_FAILED)
				die_errno("packfile %s cannot be mapped",
					  p->pack_name);
			if (!win->offset && win->len == p->pack_size
				&& !p->do_not_close)
				close_pack_fd(p);
			pack_mmap_calls++;
			pack_open_windows++;
			if (pack_mapped > peak_pack_mapped)
				peak_pack_mapped = pack_mapped;
			if (pack_open_windows > peak_pack_open_windows)
				peak_pack_open_windows = pack_open_windows;
			win->next = p->windows;
			p->windows = win;
		}
	}
	if (win != *w_cursor) {
		win->last_used = pack_used_ctr++;
		win->inuse_cnt++;
		*w_cursor = win;
	}
	offset -= win->offset;
	if (left)
		*left = win->len - xsize_t(offset);
	return win->base + offset;
}
Jonathan Tan's avatar
Jonathan Tan committed
672 673 674 675 676 677 678 679 680

void unuse_pack(struct pack_window **w_cursor)
{
	struct pack_window *w = *w_cursor;
	if (w) {
		w->inuse_cnt--;
		*w_cursor = NULL;
	}
}
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

static void try_to_free_pack_memory(size_t size)
{
	release_pack_memory(size);
}

struct packed_git *add_packed_git(const char *path, size_t path_len, int local)
{
	static int have_set_try_to_free_routine;
	struct stat st;
	size_t alloc;
	struct packed_git *p;

	if (!have_set_try_to_free_routine) {
		have_set_try_to_free_routine = 1;
		set_try_to_free_routine(try_to_free_pack_memory);
	}

	/*
	 * Make sure a corresponding .pack file exists and that
	 * the index looks sane.
	 */
	if (!strip_suffix_mem(path, &path_len, ".idx"))
		return NULL;

	/*
707
	 * ".promisor" is long enough to hold any suffix we're adding (and
708 709
	 * the use xsnprintf double-checks that)
	 */
710
	alloc = st_add3(path_len, strlen(".promisor"), 1);
711 712 713 714 715 716 717
	p = alloc_packed_git(alloc);
	memcpy(p->pack_name, path, path_len);

	xsnprintf(p->pack_name + path_len, alloc - path_len, ".keep");
	if (!access(p->pack_name, F_OK))
		p->pack_keep = 1;

718 719 720 721
	xsnprintf(p->pack_name + path_len, alloc - path_len, ".promisor");
	if (!access(p->pack_name, F_OK))
		p->pack_promisor = 1;

722 723 724 725 726 727 728 729 730 731 732 733
	xsnprintf(p->pack_name + path_len, alloc - path_len, ".pack");
	if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
		free(p);
		return NULL;
	}

	/* ok, it looks sane as far as we can check without
	 * actually mapping the pack file.
	 */
	p->pack_size = st.st_size;
	p->pack_local = local;
	p->mtime = st.st_mtime;
734
	if (path_len < the_hash_algo->hexsz ||
735 736
	    get_sha1_hex(path + path_len - the_hash_algo->hexsz, p->hash))
		hashclr(p->hash);
737 738
	return p;
}
739

740
void install_packed_git(struct repository *r, struct packed_git *pack)
741 742 743 744
{
	if (pack->pack_fd != -1)
		pack_open_fds++;

745 746
	pack->next = r->objects->packed_git;
	r->objects->packed_git = pack;
747
}
748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794

void (*report_garbage)(unsigned seen_bits, const char *path);

static void report_helper(const struct string_list *list,
			  int seen_bits, int first, int last)
{
	if (seen_bits == (PACKDIR_FILE_PACK|PACKDIR_FILE_IDX))
		return;

	for (; first < last; first++)
		report_garbage(seen_bits, list->items[first].string);
}

static void report_pack_garbage(struct string_list *list)
{
	int i, baselen = -1, first = 0, seen_bits = 0;

	if (!report_garbage)
		return;

	string_list_sort(list);

	for (i = 0; i < list->nr; i++) {
		const char *path = list->items[i].string;
		if (baselen != -1 &&
		    strncmp(path, list->items[first].string, baselen)) {
			report_helper(list, seen_bits, first, i);
			baselen = -1;
			seen_bits = 0;
		}
		if (baselen == -1) {
			const char *dot = strrchr(path, '.');
			if (!dot) {
				report_garbage(PACKDIR_FILE_GARBAGE, path);
				continue;
			}
			baselen = dot - path + 1;
			first = i;
		}
		if (!strcmp(path + baselen, "pack"))
			seen_bits |= 1;
		else if (!strcmp(path + baselen, "idx"))
			seen_bits |= 2;
	}
	report_helper(list, seen_bits, first, list->nr);
}

795 796 797
void for_each_file_in_pack_dir(const char *objdir,
			       each_file_in_pack_dir_fn fn,
			       void *data)
798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822
{
	struct strbuf path = STRBUF_INIT;
	size_t dirnamelen;
	DIR *dir;
	struct dirent *de;

	strbuf_addstr(&path, objdir);
	strbuf_addstr(&path, "/pack");
	dir = opendir(path.buf);
	if (!dir) {
		if (errno != ENOENT)
			error_errno("unable to open object pack directory: %s",
				    path.buf);
		strbuf_release(&path);
		return;
	}
	strbuf_addch(&path, '/');
	dirnamelen = path.len;
	while ((de = readdir(dir)) != NULL) {
		if (is_dot_or_dotdot(de->d_name))
			continue;

		strbuf_setlen(&path, dirnamelen);
		strbuf_addstr(&path, de->d_name);

823
		fn(path.buf, path.len, de->d_name, data);
824
	}
825

826 827 828 829
	closedir(dir);
	strbuf_release(&path);
}

830 831 832 833
struct prepare_pack_data {
	struct repository *r;
	struct string_list *garbage;
	int local;
834
	struct multi_pack_index *m;
835 836 837 838 839 840 841 842 843
};

static void prepare_pack(const char *full_name, size_t full_name_len,
			 const char *file_name, void *_data)
{
	struct prepare_pack_data *data = (struct prepare_pack_data *)_data;
	struct packed_git *p;
	size_t base_len = full_name_len;

844 845
	if (strip_suffix_mem(full_name, &base_len, ".idx") &&
	    !(data->m && midx_contains_pack(data->m, file_name))) {
846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864
		/* Don't reopen a pack we already have. */
		for (p = data->r->objects->packed_git; p; p = p->next) {
			size_t len;
			if (strip_suffix(p->pack_name, ".pack", &len) &&
			    len == base_len &&
			    !memcmp(p->pack_name, full_name, len))
				break;
		}

		if (!p) {
			p = add_packed_git(full_name, full_name_len, data->local);
			if (p)
				install_packed_git(data->r, p);
		}
	}

	if (!report_garbage)
		return;

865 866
	if (!strcmp(file_name, "multi-pack-index"))
		return;
867 868 869 870 871 872 873 874 875 876 877 878 879 880 881
	if (ends_with(file_name, ".idx") ||
	    ends_with(file_name, ".pack") ||
	    ends_with(file_name, ".bitmap") ||
	    ends_with(file_name, ".keep") ||
	    ends_with(file_name, ".promisor"))
		string_list_append(data->garbage, full_name);
	else
		report_garbage(PACKDIR_FILE_GARBAGE, full_name);
}

static void prepare_packed_git_one(struct repository *r, char *objdir, int local)
{
	struct prepare_pack_data data;
	struct string_list garbage = STRING_LIST_INIT_DUP;

882 883 884 885 886 887
	data.m = r->objects->multi_pack_index;

	/* look for the multi-pack-index for this object directory */
	while (data.m && strcmp(data.m->object_dir, objdir))
		data.m = data.m->next;

888 889 890 891 892 893 894 895 896 897
	data.r = r;
	data.garbage = &garbage;
	data.local = local;

	for_each_file_in_pack_dir(objdir, prepare_pack, &data);

	report_pack_garbage(data.garbage);
	string_list_clear(data.garbage, 0);
}

898
static void prepare_packed_git(struct repository *r);
899 900 901 902 903 904 905 906 907
/*
 * Give a fast, rough count of the number of objects in the repository. This
 * ignores loose objects completely. If you have a lot of them, then either
 * you should repack because your performance will be awful, or they are
 * all unreachable objects about to be pruned, in which case they're not really
 * interesting as a measure of repo size in the first place.
 */
unsigned long approximate_object_count(void)
{
908 909
	if (!the_repository->objects->approximate_object_count_valid) {
		unsigned long count;
910
		struct multi_pack_index *m;
911 912
		struct packed_git *p;

913
		prepare_packed_git(the_repository);
914
		count = 0;
915 916
		for (m = get_multi_pack_index(the_repository); m; m = m->next)
			count += m->num_objects;
917
		for (p = the_repository->objects->packed_git; p; p = p->next) {
918 919 920 921
			if (open_pack_index(p))
				continue;
			count += p->num_objects;
		}
922
		the_repository->objects->approximate_object_count = count;
923
	}
924
	return the_repository->objects->approximate_object_count;
925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964
}

static void *get_next_packed_git(const void *p)
{
	return ((const struct packed_git *)p)->next;
}

static void set_next_packed_git(void *p, void *next)
{
	((struct packed_git *)p)->next = next;
}

static int sort_pack(const void *a_, const void *b_)
{
	const struct packed_git *a = a_;
	const struct packed_git *b = b_;
	int st;

	/*
	 * Local packs tend to contain objects specific to our
	 * variant of the project than remote ones.  In addition,
	 * remote ones could be on a network mounted filesystem.
	 * Favor local ones for these reasons.
	 */
	st = a->pack_local - b->pack_local;
	if (st)
		return -st;

	/*
	 * Younger packs tend to contain more recent objects,
	 * and more recent objects tend to get accessed more
	 * often.
	 */
	if (a->mtime < b->mtime)
		return 1;
	else if (a->mtime == b->mtime)
		return 0;
	return -1;
}

965
static void rearrange_packed_git(struct repository *r)
966
{
967 968
	r->objects->packed_git = llist_mergesort(
		r->objects->packed_git, get_next_packed_git,
969
		set_next_packed_git, sort_pack);
970 971
}

972
static void prepare_packed_git_mru(struct repository *r)
973 974 975
{
	struct packed_git *p;

976
	INIT_LIST_HEAD(&r->objects->packed_git_mru);
977

978 979
	for (p = r->objects->packed_git; p; p = p->next)
		list_add_tail(&p->mru, &r->objects->packed_git_mru);
980 981
}

982
static void prepare_packed_git(struct repository *r)
983
{
984
	struct object_directory *odb;
985

986
	if (r->objects->packed_git_initialized)
987
		return;
988

989
	prepare_alt_odb(r);
990 991 992 993
	for (odb = r->objects->odb; odb; odb = odb->next) {
		int local = (odb == r->objects->odb);
		prepare_multi_pack_index_one(r, odb->path, local);
		prepare_packed_git_one(r, odb->path, local);
994
	}
995
	rearrange_packed_git(r);
996 997 998

	r->objects->all_packs = NULL;

999 1000
	prepare_packed_git_mru(r);
	r->objects->packed_git_initialized = 1;
1001 1002
}

1003
void reprepare_packed_git(struct repository *r)
1004
{
1005 1006
	struct object_directory *odb;

1007 1008
	for (odb = r->objects->odb; odb; odb = odb->next)
		odb_clear_loose_cache(odb);
1009

1010 1011 1012
	r->objects->approximate_object_count_valid = 0;
	r->objects->packed_git_initialized = 0;
	prepare_packed_git(r);
1013
}
1014

1015 1016
struct packed_git *get_packed_git(struct repository *r)
{
1017
	prepare_packed_git(r);
1018 1019 1020
	return r->objects->packed_git;
}

1021 1022 1023 1024 1025 1026
struct multi_pack_index *get_multi_pack_index(struct repository *r)
{
	prepare_packed_git(r);
	return r->objects->multi_pack_index;
}

1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050
struct packed_git *get_all_packs(struct repository *r)
{
	prepare_packed_git(r);

	if (!r->objects->all_packs) {
		struct packed_git *p = r->objects->packed_git;
		struct multi_pack_index *m;

		for (m = r->objects->multi_pack_index; m; m = m->next) {
			uint32_t i;
			for (i = 0; i < m->num_packs; i++) {
				if (!prepare_midx_pack(m, i)) {
					m->packs[i]->next = p;
					p = m->packs[i];
				}
			}
		}

		r->objects->all_packs = p;
	}

	return r->objects->all_packs;
}

1051 1052
struct list_head *get_packed_git_mru(struct repository *r)
{
1053
	prepare_packed_git(r);
1054 1055 1056
	return &r->objects->packed_git_mru;
}

1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080
unsigned long unpack_object_header_buffer(const unsigned char *buf,
		unsigned long len, enum object_type *type, unsigned long *sizep)
{
	unsigned shift;
	unsigned long size, c;
	unsigned long used = 0;

	c = buf[used++];
	*type = (c >> 4) & 7;
	size = c & 15;
	shift = 4;
	while (c & 0x80) {
		if (len <= used || bitsizeof(long) <= shift) {
			error("bad object header");
			size = used = 0;
			break;
		}
		c = buf[used++];
		size += (c & 0x7f) << shift;
		shift += 7;
	}
	*sizep = size;
	return used;
}
1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119

unsigned long get_size_from_delta(struct packed_git *p,
				  struct pack_window **w_curs,
				  off_t curpos)
{
	const unsigned char *data;
	unsigned char delta_head[20], *in;
	git_zstream stream;
	int st;

	memset(&stream, 0, sizeof(stream));
	stream.next_out = delta_head;
	stream.avail_out = sizeof(delta_head);

	git_inflate_init(&stream);
	do {
		in = use_pack(p, w_curs, curpos, &stream.avail_in);
		stream.next_in = in;
		st = git_inflate(&stream, Z_FINISH);
		curpos += stream.next_in - in;
	} while ((st == Z_OK || st == Z_BUF_ERROR) &&
		 stream.total_out < sizeof(delta_head));
	git_inflate_end(&stream);
	if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) {
		error("delta data unpack-initial failed");
		return 0;
	}

	/* Examine the initial part of the delta to figure out
	 * the result size.
	 */
	data = delta_head;

	/* ignore base size */
	get_delta_hdr_size(&data, delta_head+sizeof(delta_head));

	/* Read the result size */
	return get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
}
1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145

int unpack_object_header(struct packed_git *p,
			 struct pack_window **w_curs,
			 off_t *curpos,
			 unsigned long *sizep)
{
	unsigned char *base;
	unsigned long left;
	unsigned long used;
	enum object_type type;

	/* use_pack() assures us we have [base, base + 20) available
	 * as a range that we can look at.  (Its actually the hash
	 * size that is assured.)  With our object header encoding
	 * the maximum deflated object size is 2^137, which is just
	 * insane, so we know won't exceed what we have been given.
	 */
	base = use_pack(p, w_curs, *curpos, &left);
	used = unpack_object_header_buffer(base, left, &type, sizep);
	if (!used) {
		type = OBJ_BAD;
	} else
		*curpos += used;

	return type;
}
1146 1147 1148 1149

void mark_bad_packed_object(struct packed_git *p, const unsigned char *sha1)
{
	unsigned i;
1150
	const unsigned hashsz = the_hash_algo->rawsz;
1151
	for (i = 0; i < p->num_bad_objects; i++)
1152
		if (hasheq(sha1, p->bad_object_sha1 + hashsz * i))
1153 1154 1155 1156
			return;
	p->bad_object_sha1 = xrealloc(p->bad_object_sha1,
				      st_mult(GIT_MAX_RAWSZ,
					      st_add(p->num_bad_objects, 1)));
1157
	hashcpy(p->bad_object_sha1 + hashsz * p->num_bad_objects, sha1);
1158 1159 1160
	p->num_bad_objects++;
}

1161 1162
const struct packed_git *has_packed_and_bad(struct repository *r,
					    const unsigned char *sha1)
1163 1164 1165 1166
{
	struct packed_git *p;
	unsigned i;

1167
	for (p = r->objects->packed_git; p; p = p->next)
1168
		for (i = 0; i < p->num_bad_objects; i++)
1169 1170
			if (hasheq(sha1,
				   p->bad_object_sha1 + the_hash_algo->rawsz * i))
1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207
				return p;
	return NULL;
}

static off_t get_delta_base(struct packed_git *p,
				    struct pack_window **w_curs,
				    off_t *curpos,
				    enum object_type type,
				    off_t delta_obj_offset)
{
	unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL);
	off_t base_offset;

	/* use_pack() assured us we have [base_info, base_info + 20)
	 * as a range that we can look at without walking off the
	 * end of the mapped window.  Its actually the hash size
	 * that is assured.  An OFS_DELTA longer than the hash size
	 * is stupid, as then a REF_DELTA would be smaller to store.
	 */
	if (type == OBJ_OFS_DELTA) {
		unsigned used = 0;
		unsigned char c = base_info[used++];
		base_offset = c & 127;
		while (c & 128) {
			base_offset += 1;
			if (!base_offset || MSB(base_offset, 7))
				return 0;  /* overflow */
			c = base_info[used++];
			base_offset = (base_offset << 7) + (c & 127);
		}
		base_offset = delta_obj_offset - base_offset;
		if (base_offset <= 0 || base_offset >= delta_obj_offset)
			return 0;  /* out of bound */
		*curpos += used;
	} else if (type == OBJ_REF_DELTA) {
		/* The base entry _must_ be in the same pack */
		base_offset = find_pack_entry_one(base_info, p);
1208
		*curpos += the_hash_algo->rawsz;
1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245
	} else
		die("I am totally screwed");
	return base_offset;
}

/*
 * Like get_delta_base above, but we return the sha1 instead of the pack
 * offset. This means it is cheaper for REF deltas (we do not have to do
 * the final object lookup), but more expensive for OFS deltas (we
 * have to load the revidx to convert the offset back into a sha1).
 */
static const unsigned char *get_delta_base_sha1(struct packed_git *p,
						struct pack_window **w_curs,
						off_t curpos,
						enum object_type type,
						off_t delta_obj_offset)
{
	if (type == OBJ_REF_DELTA) {
		unsigned char *base = use_pack(p, w_curs, curpos, NULL);
		return base;
	} else if (type == OBJ_OFS_DELTA) {
		struct revindex_entry *revidx;
		off_t base_offset = get_delta_base(p, w_curs, &curpos,
						   type, delta_obj_offset);

		if (!base_offset)
			return NULL;

		revidx = find_pack_revindex(p, base_offset);
		if (!revidx)
			return NULL;

		return nth_packed_object_sha1(p, revidx->nr);
	} else
		return NULL;
}

1246 1247 1248
static int retry_bad_packed_offset(struct repository *r,
				   struct packed_git *p,
				   off_t obj_offset)
1249 1250 1251
{
	int type;
	struct revindex_entry *revidx;
1252
	struct object_id oid;
1253 1254 1255
	revidx = find_pack_revindex(p, obj_offset);
	if (!revidx)
		return OBJ_BAD;
1256 1257
	nth_packed_object_oid(&oid, p, revidx->nr);
	mark_bad_packed_object(p, oid.hash);
1258
	type = oid_object_info(r, &oid, NULL);
1259 1260 1261 1262 1263 1264 1265
	if (type <= OBJ_NONE)
		return OBJ_BAD;
	return type;
}

#define POI_STACK_PREALLOC 64

1266 1267
static enum object_type packed_to_object_type(struct repository *r,
					      struct packed_git *p,
1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297
					      off_t obj_offset,
					      enum object_type type,
					      struct pack_window **w_curs,
					      off_t curpos)
{
	off_t small_poi_stack[POI_STACK_PREALLOC];
	off_t *poi_stack = small_poi_stack;
	int poi_stack_nr = 0, poi_stack_alloc = POI_STACK_PREALLOC;

	while (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
		off_t base_offset;
		unsigned long size;
		/* Push the object we're going to leave behind */
		if (poi_stack_nr >= poi_stack_alloc && poi_stack == small_poi_stack) {
			poi_stack_alloc = alloc_nr(poi_stack_nr);
			ALLOC_ARRAY(poi_stack, poi_stack_alloc);
			memcpy(poi_stack, small_poi_stack, sizeof(off_t)*poi_stack_nr);
		} else {
			ALLOC_GROW(poi_stack, poi_stack_nr+1, poi_stack_alloc);
		}
		poi_stack[poi_stack_nr++] = obj_offset;
		/* If parsing the base offset fails, just unwind */
		base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
		if (!base_offset)
			goto unwind;
		curpos = obj_offset = base_offset;
		type = unpack_object_header(p, w_curs, &curpos, &size);
		if (type <= OBJ_NONE) {
			/* If getting the base itself fails, we first
			 * retry the base, otherwise unwind */
1298
			type = retry_bad_packed_offset(r, p, base_offset);
1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325
			if (type > OBJ_NONE)
				goto out;
			goto unwind;
		}
	}

	switch (type) {
	case OBJ_BAD:
	case OBJ_COMMIT:
	case OBJ_TREE:
	case OBJ_BLOB:
	case OBJ_TAG:
		break;
	default:
		error("unknown object type %i at offset %"PRIuMAX" in %s",
		      type, (uintmax_t)obj_offset, p->pack_name);
		type = OBJ_BAD;
	}

out:
	if (poi_stack != small_poi_stack)
		free(poi_stack);
	return type;

unwind:
	while (poi_stack_nr) {
		obj_offset = poi_stack[--poi_stack_nr];
1326
		type = retry_bad_packed_offset(r, p, obj_offset);
1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412
		if (type > OBJ_NONE)
			goto out;
	}
	type = OBJ_BAD;
	goto out;
}

static struct hashmap delta_base_cache;
static size_t delta_base_cached;

static LIST_HEAD(delta_base_cache_lru);

struct delta_base_cache_key {
	struct packed_git *p;
	off_t base_offset;
};

struct delta_base_cache_entry {
	struct hashmap hash;
	struct delta_base_cache_key key;
	struct list_head lru;
	void *data;
	unsigned long size;
	enum object_type type;
};

static unsigned int pack_entry_hash(struct packed_git *p, off_t base_offset)
{
	unsigned int hash;

	hash = (unsigned int)(intptr_t)p + (unsigned int)base_offset;
	hash += (hash >> 8) + (hash >> 16);
	return hash;
}

static struct delta_base_cache_entry *
get_delta_base_cache_entry(struct packed_git *p, off_t base_offset)
{
	struct hashmap_entry entry;
	struct delta_base_cache_key key;

	if (!delta_base_cache.cmpfn)
		return NULL;

	hashmap_entry_init(&entry, pack_entry_hash(p, base_offset));
	key.p = p;
	key.base_offset = base_offset;
	return hashmap_get(&delta_base_cache, &entry, &key);
}

static int delta_base_cache_key_eq(const struct delta_base_cache_key *a,
				   const struct delta_base_cache_key *b)
{
	return a->p == b->p && a->base_offset == b->base_offset;
}

static int delta_base_cache_hash_cmp(const void *unused_cmp_data,
				     const void *va, const void *vb,
				     const void *vkey)
{
	const struct delta_base_cache_entry *a = va, *b = vb;
	const struct delta_base_cache_key *key = vkey;
	if (key)
		return !delta_base_cache_key_eq(&a->key, key);
	else
		return !delta_base_cache_key_eq(&a->key, &b->key);
}

static int in_delta_base_cache(struct packed_git *p, off_t base_offset)
{
	return !!get_delta_base_cache_entry(p, base_offset);
}

/*
 * Remove the entry from the cache, but do _not_ free the associated
 * entry data. The caller takes ownership of the "data" buffer, and
 * should copy out any fields it wants before detaching.
 */
static void detach_delta_base_cache_entry(struct delta_base_cache_entry *ent)
{
	hashmap_remove(&delta_base_cache, ent, &ent->key);
	list_del(&ent->lru);
	delta_base_cached -= ent->size;
	free(ent);
}

1413 1414 1415
static void *cache_or_unpack_entry(struct repository *r, struct packed_git *p,
				   off_t base_offset, unsigned long *base_size,
				   enum object_type *type)
1416 1417 1418 1419 1420
{
	struct delta_base_cache_entry *ent;

	ent = get_delta_base_cache_entry(p, base_offset);
	if (!ent)
1421
		return unpack_entry(r, p, base_offset, type, base_size);
1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474

	if (type)
		*type = ent->type;
	if (base_size)
		*base_size = ent->size;
	return xmemdupz(ent->data, ent->size);
}

static inline void release_delta_base_cache(struct delta_base_cache_entry *ent)
{
	free(ent->data);
	detach_delta_base_cache_entry(ent);
}

void clear_delta_base_cache(void)
{
	struct list_head *lru, *tmp;
	list_for_each_safe(lru, tmp, &delta_base_cache_lru) {
		struct delta_base_cache_entry *entry =
			list_entry(lru, struct delta_base_cache_entry, lru);
		release_delta_base_cache(entry);
	}
}

static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
	void *base, unsigned long base_size, enum object_type type)
{
	struct delta_base_cache_entry *ent = xmalloc(sizeof(*ent));
	struct list_head *lru, *tmp;

	delta_base_cached += base_size;

	list_for_each_safe(lru, tmp, &delta_base_cache_lru) {
		struct delta_base_cache_entry *f =
			list_entry(lru, struct delta_base_cache_entry, lru);
		if (delta_base_cached <= delta_base_cache_limit)
			break;
		release_delta_base_cache(f);
	}

	ent->key.p = p;
	ent->key.base_offset = base_offset;
	ent->type = type;
	ent->data = base;
	ent->size = base_size;
	list_add_tail(&ent->lru, &delta_base_cache_lru);

	if (!delta_base_cache.cmpfn)
		hashmap_init(&delta_base_cache, delta_base_cache_hash_cmp, NULL, 0);
	hashmap_entry_init(ent, pack_entry_hash(p, base_offset));
	hashmap_add(&delta_base_cache, ent);
}

1475 1476
int packed_object_info(struct repository *r, struct packed_git *p,
		       off_t obj_offset, struct object_info *oi)
1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487
{
	struct pack_window *w_curs = NULL;
	unsigned long size;
	off_t curpos = obj_offset;
	enum object_type type;

	/*
	 * We always get the representation type, but only convert it to
	 * a "real" type later if the caller is interested.
	 */
	if (oi->contentp) {
1488
		*oi->contentp = cache_or_unpack_entry(r, p, obj_offset, oi->sizep,
1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519
						      &type);
		if (!*oi->contentp)
			type = OBJ_BAD;
	} else {
		type = unpack_object_header(p, &w_curs, &curpos, &size);
	}

	if (!oi->contentp && oi->sizep) {
		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
			off_t tmp_pos = curpos;
			off_t base_offset = get_delta_base(p, &w_curs, &tmp_pos,
							   type, obj_offset);
			if (!base_offset) {
				type = OBJ_BAD;
				goto out;
			}
			*oi->sizep = get_size_from_delta(p, &w_curs, tmp_pos);
			if (*oi->sizep == 0) {
				type = OBJ_BAD;
				goto out;
			}
		} else {
			*oi->sizep = size;
		}
	}

	if (oi->disk_sizep) {
		struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
		*oi->disk_sizep = revidx[1].offset - obj_offset;
	}

1520
	if (oi->typep || oi->type_name) {
1521
		enum object_type ptot;
1522
		ptot = packed_to_object_type(r, p, obj_offset,
1523
					     type, &w_curs, curpos);
1524 1525
		if (oi->typep)
			*oi->typep = ptot;
1526
		if (oi->type_name) {
1527
			const char *tn = type_name(ptot);
1528
			if (tn)
1529
				strbuf_addstr(oi->type_name, tn);
1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591
		}
		if (ptot < 0) {
			type = OBJ_BAD;
			goto out;
		}
	}

	if (oi->delta_base_sha1) {
		if (type == OBJ_OFS_DELTA || type == OBJ_REF_DELTA) {
			const unsigned char *base;

			base = get_delta_base_sha1(p, &w_curs, curpos,
						   type, obj_offset);
			if (!base) {
				type = OBJ_BAD;
				goto out;
			}

			hashcpy(oi->delta_base_sha1, base);
		} else
			hashclr(oi->delta_base_sha1);
	}

	oi->whence = in_delta_base_cache(p, obj_offset) ? OI_DBCACHED :
							  OI_PACKED;

out:
	unuse_pack(&w_curs);
	return type;
}

static void *unpack_compressed_entry(struct packed_git *p,
				    struct pack_window **w_curs,
				    off_t curpos,
				    unsigned long size)
{
	int st;
	git_zstream stream;
	unsigned char *buffer, *in;

	buffer = xmallocz_gently(size);
	if (!buffer)
		return NULL;
	memset(&stream, 0, sizeof(stream));
	stream.next_out = buffer;
	stream.avail_out = size + 1;

	git_inflate_init(&stream);
	do {
		in = use_pack(p, w_curs, curpos, &stream.avail_in);
		stream.next_in = in;
		st = git_inflate(&stream, Z_FINISH);
		if (!stream.avail_out)
			break; /* the payload is larger than it should be */
		curpos += stream.next_in - in;
	} while (st == Z_OK || st == Z_BUF_ERROR);
	git_inflate_end(&stream);
	if ((st != Z_STREAM_END) || stream.total_out != size) {
		free(buffer);
		return NULL;
	}

1592 1593 1594
	/* versions of zlib can clobber unconsumed portion of outbuf */
	buffer[size] = '\0';

1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613
	return buffer;
}

static void write_pack_access_log(struct packed_git *p, off_t obj_offset)
{
	static struct trace_key pack_access = TRACE_KEY_INIT(PACK_ACCESS);
	trace_printf_key(&pack_access, "%s %"PRIuMAX"\n",
			 p->pack_name, (uintmax_t)obj_offset);
}

int do_check_packed_object_crc;

#define UNPACK_ENTRY_STACK_PREALLOC 64
struct unpack_entry_stack_ent {
	off_t obj_offset;
	off_t curpos;
	unsigned long size;
};

1614 1615 1616
static void *read_object(struct repository *r,
			 const struct object_id *oid,
			 enum object_type *type,
1617 1618 1619 1620 1621 1622 1623 1624
			 unsigned long *size)
{
	struct object_info oi = OBJECT_INFO_INIT;
	void *content;
	oi.typep = type;
	oi.sizep = size;
	oi.contentp = &content;

1625
	if (oid_object_info_extended(r, oid, &oi, 0) < 0)
1626 1627 1628 1629
		return NULL;
	return content;
}

1630
void *unpack_entry(struct repository *r, struct packed_git *p, off_t obj_offset,
1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664
		   enum object_type *final_type, unsigned long *final_size)
{
	struct pack_window *w_curs = NULL;
	off_t curpos = obj_offset;
	void *data = NULL;
	unsigned long size;
	enum object_type type;
	struct unpack_entry_stack_ent small_delta_stack[UNPACK_ENTRY_STACK_PREALLOC];
	struct unpack_entry_stack_ent *delta_stack = small_delta_stack;
	int delta_stack_nr = 0, delta_stack_alloc = UNPACK_ENTRY_STACK_PREALLOC;
	int base_from_cache = 0;

	write_pack_access_log(p, obj_offset);

	/* PHASE 1: drill down to the innermost base object */
	for (;;) {
		off_t base_offset;
		int i;
		struct delta_base_cache_entry *ent;

		ent = get_delta_base_cache_entry(p, curpos);
		if (ent) {
			type = ent->type;
			data = ent->data;
			size = ent->size;
			detach_delta_base_cache_entry(ent);
			base_from_cache = 1;
			break;
		}

		if (do_check_packed_object_crc && p->index_version > 1) {
			struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
			off_t len = revidx[1].offset - obj_offset;
			if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
1665 1666
				struct object_id oid;
				nth_packed_object_oid(&oid, p, revidx->nr);
1667
				error("bad packed object CRC for %s",
1668 1669
				      oid_to_hex(&oid));
				mark_bad_packed_object(p, oid.hash);
1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711
				data = NULL;
				goto out;
			}
		}

		type = unpack_object_header(p, &w_curs, &curpos, &size);
		if (type != OBJ_OFS_DELTA && type != OBJ_REF_DELTA)
			break;

		base_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
		if (!base_offset) {
			error("failed to validate delta base reference "
			      "at offset %"PRIuMAX" from %s",
			      (uintmax_t)curpos, p->pack_name);
			/* bail to phase 2, in hopes of recovery */
			data = NULL;
			break;
		}

		/* push object, proceed to base */
		if (delta_stack_nr >= delta_stack_alloc
		    && delta_stack == small_delta_stack) {
			delta_stack_alloc = alloc_nr(delta_stack_nr);
			ALLOC_ARRAY(delta_stack, delta_stack_alloc);
			memcpy(delta_stack, small_delta_stack,
			       sizeof(*delta_stack)*delta_stack_nr);
		} else {
			ALLOC_GROW(delta_stack, delta_stack_nr+1, delta_stack_alloc);
		}
		i = delta_stack_nr++;
		delta_stack[i].obj_offset = obj_offset;
		delta_stack[i].curpos = curpos;
		delta_stack[i].size = size;

		curpos = obj_offset = base_offset;
	}

	/* PHASE 2: handle the base */
	switch (type) {
	case OBJ_OFS_DELTA:
	case OBJ_REF_DELTA:
		if (data)
1712
			BUG("unpack_entry: left loop at a valid delta");
1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751
		break;
	case OBJ_COMMIT:
	case OBJ_TREE:
	case OBJ_BLOB:
	case OBJ_TAG:
		if (!base_from_cache)
			data = unpack_compressed_entry(p, &w_curs, curpos, size);
		break;
	default:
		data = NULL;
		error("unknown object type %i at offset %"PRIuMAX" in %s",
		      type, (uintmax_t)obj_offset, p->pack_name);
	}

	/* PHASE 3: apply deltas in order */

	/* invariants:
	 *   'data' holds the base data, or NULL if there was corruption
	 */
	while (delta_stack_nr) {
		void *delta_data;
		void *base = data;
		void *external_base = NULL;
		unsigned long delta_size, base_size = size;
		int i;

		data = NULL;

		if (base)
			add_delta_base_cache(p, obj_offset, base, base_size, type);

		if (!base) {
			/*
			 * We're probably in deep shit, but let's try to fetch
			 * the required base anyway from another pack or loose.
			 * This is costly but should happen only in the presence
			 * of a corrupted pack, and is better than failing outright.
			 */
			struct revindex_entry *revidx;
1752
			struct object_id base_oid;
1753 1754
			revidx = find_pack_revindex(p, obj_offset);
			if (revidx) {
1755
				nth_packed_object_oid(&base_oid, p, revidx->nr);
1756 1757
				error("failed to read delta base object %s"
				      " at offset %"PRIuMAX" from %s",
1758
				      oid_to_hex(&base_oid), (uintmax_t)obj_offset,
1759
				      p->pack_name);
1760
				mark_bad_packed_object(p, base_oid.hash);
1761
				base = read_object(r, &base_oid, &type, &base_size);
1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816
				external_base = base;
			}
		}

		i = --delta_stack_nr;
		obj_offset = delta_stack[i].obj_offset;
		curpos = delta_stack[i].curpos;
		delta_size = delta_stack[i].size;

		if (!base)
			continue;

		delta_data = unpack_compressed_entry(p, &w_curs, curpos, delta_size);

		if (!delta_data) {
			error("failed to unpack compressed delta "
			      "at offset %"PRIuMAX" from %s",
			      (uintmax_t)curpos, p->pack_name);
			data = NULL;
			free(external_base);
			continue;
		}

		data = patch_delta(base, base_size,
				   delta_data, delta_size,
				   &size);

		/*
		 * We could not apply the delta; warn the user, but keep going.
		 * Our failure will be noticed either in the next iteration of
		 * the loop, or if this is the final delta, in the caller when
		 * we return NULL. Those code paths will take care of making
		 * a more explicit warning and retrying with another copy of
		 * the object.
		 */
		if (!data)
			error("failed to apply delta");

		free(delta_data);
		free(external_base);
	}

	if (final_type)
		*final_type = type;
	if (final_size)
		*final_size = size;

out:
	unuse_pack(&w_curs);

	if (delta_stack != small_delta_stack)
		free(delta_stack);

	return data;
}
1817

1818 1819 1820 1821
int bsearch_pack(const struct object_id *oid, const struct packed_git *p, uint32_t *result)
{
	const unsigned char *index_fanout = p->index_data;
	const unsigned char *index_lookup;
1822
	const unsigned int hashsz = the_hash_algo->rawsz;
1823 1824 1825 1826 1827 1828 1829
	int index_lookup_width;

	if (!index_fanout)
		BUG("bsearch_pack called without a valid pack-index");

	index_lookup = index_fanout + 4 * 256;
	if (p->index_version == 1) {
1830
		index_lookup_width = hashsz + 4;
1831 1832
		index_lookup += 4;
	} else {
1833
		index_lookup_width = hashsz;
1834 1835 1836 1837 1838 1839 1840 1841
		index_fanout += 8;
		index_lookup += 8;
	}

	return bsearch_hash(oid->hash, (const uint32_t*)index_fanout,
			    index_lookup, index_lookup_width, result);
}

1842 1843 1844 1845
const unsigned char *nth_packed_object_sha1(struct packed_git *p,
					    uint32_t n)
{
	const unsigned char *index = p->index_data;
1846
	const unsigned int hashsz = the_hash_algo->rawsz;
1847 1848 1849 1850 1851 1852 1853 1854 1855
	if (!index) {
		if (open_pack_index(p))
			return NULL;
		index = p->index_data;
	}
	if (n >= p->num_objects)
		return NULL;
	index += 4 * 256;
	if (p->index_version == 1) {
1856
		return index + (hashsz + 4) * n + 4;
1857 1858
	} else {
		index += 8;
1859
		return index + hashsz * n;
1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872
	}
}

const struct object_id *nth_packed_object_oid(struct object_id *oid,
					      struct packed_git *p,
					      uint32_t n)
{
	const unsigned char *hash = nth_packed_object_sha1(p, n);
	if (!hash)
		return NULL;
	hashcpy(oid->hash, hash);
	return oid;
}
1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890

void check_pack_index_ptr(const struct packed_git *p, const void *vptr)
{
	const unsigned char *ptr = vptr;
	const unsigned char *start = p->index_data;
	const unsigned char *end = start + p->index_size;
	if (ptr < start)
		die(_("offset before start of pack index for %s (corrupt index?)"),
		    p->pack_name);
	/* No need to check for underflow; .idx files must be at least 8 bytes */
	if (ptr >= end - 8)
		die(_("offset beyond end of pack index for %s (truncated index?)"),
		    p->pack_name);
}

off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
{
	const unsigned char *index = p->index_data;
1891
	const unsigned int hashsz = the_hash_algo->rawsz;
1892 1893
	index += 4 * 256;
	if (p->index_version == 1) {
1894
		return ntohl(*((uint32_t *)(index + (hashsz + 4) * n)));
1895 1896
	} else {
		uint32_t off;
1897
		index += 8 + p->num_objects * (hashsz + 4);
1898 1899 1900 1901 1902
		off = ntohl(*((uint32_t *)(index + 4 * n)));
		if (!(off & 0x80000000))
			return off;
		index += p->num_objects * 4 + (off & 0x7fffffff) * 8;
		check_pack_index_ptr(p, index);
1903
		return get_be64(index);
1904 1905
	}
}
1906 1907 1908 1909 1910

off_t find_pack_entry_one(const unsigned char *sha1,
				  struct packed_git *p)
{
	const unsigned char *index = p->index_data;
1911
	struct object_id oid;
1912
	uint32_t result;
1913 1914 1915 1916 1917 1918

	if (!index) {
		if (open_pack_index(p))
			return 0;
	}

1919 1920
	hashcpy(oid.hash, sha1);
	if (bsearch_pack(&oid, p, &result))
1921
		return nth_packed_object_offset(p, result);
1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944
	return 0;
}

int is_pack_valid(struct packed_git *p)
{
	/* An already open pack is known to be valid. */
	if (p->pack_fd != -1)
		return 1;

	/* If the pack has one window completely covering the
	 * file size, the pack is known to be valid even if
	 * the descriptor is not currently open.
	 */
	if (p->windows) {
		struct pack_window *w = p->windows;

		if (!w->offset && w->len == p->pack_size)
			return 1;
	}

	/* Force the pack to open to prove its valid. */
	return !open_packed_git(p);
}
1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957

struct packed_git *find_sha1_pack(const unsigned char *sha1,
				  struct packed_git *packs)
{
	struct packed_git *p;

	for (p = packs; p; p = p->next) {
		if (find_pack_entry_one(sha1, p))
			return p;
	}
	return NULL;

}
1958

1959
static int fill_pack_entry(const struct object_id *oid,
1960 1961 1962 1963 1964 1965 1966 1967
			   struct pack_entry *e,
			   struct packed_git *p)
{
	off_t offset;

	if (p->num_bad_objects) {
		unsigned i;
		for (i = 0; i < p->num_bad_objects; i++)
1968 1969
			if (hasheq(oid->hash,
				   p->bad_object_sha1 + the_hash_algo->rawsz * i))
1970 1971 1972
				return 0;
	}

1973
	offset = find_pack_entry_one(oid->hash, p);
1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990
	if (!offset)
		return 0;

	/*
	 * We are about to tell the caller where they can locate the
	 * requested object.  We better make sure the packfile is
	 * still here and can be accessed before supplying that
	 * answer, as it may have been deleted since the index was
	 * loaded!
	 */
	if (!is_pack_valid(p))
		return 0;
	e->offset = offset;
	e->p = p;
	return 1;
}

1991
int find_pack_entry(struct repository *r, const struct object_id *oid, struct pack_entry *e)
1992
{
1993
	struct list_head *pos;
1994
	struct multi_pack_index *m;
1995

1996
	prepare_packed_git(r);
1997
	if (!r->objects->packed_git && !r->objects->multi_pack_index)
1998 1999
		return 0;