git@vger.kernel.org list mirror (unofficial, one of many)
 help / color / Atom feed
220e1e3693f0b16bf3d83d72503ad0ce535a31c8 blob 49359 bytes (raw)

   1
   2
   3
   4
   5
   6
   7
   8
   9
  10
  11
  12
  13
  14
  15
  16
  17
  18
  19
  20
  21
  22
  23
  24
  25
  26
  27
  28
  29
  30
  31
  32
  33
  34
  35
  36
  37
  38
  39
  40
  41
  42
  43
  44
  45
  46
  47
  48
  49
  50
  51
  52
  53
  54
  55
  56
  57
  58
  59
  60
  61
  62
  63
  64
  65
  66
  67
  68
  69
  70
  71
  72
  73
  74
  75
  76
  77
  78
  79
  80
  81
  82
  83
  84
  85
  86
  87
  88
  89
  90
  91
  92
  93
  94
  95
  96
  97
  98
  99
 100
 101
 102
 103
 104
 105
 106
 107
 108
 109
 110
 111
 112
 113
 114
 115
 116
 117
 118
 119
 120
 121
 122
 123
 124
 125
 126
 127
 128
 129
 130
 131
 132
 133
 134
 135
 136
 137
 138
 139
 140
 141
 142
 143
 144
 145
 146
 147
 148
 149
 150
 151
 152
 153
 154
 155
 156
 157
 158
 159
 160
 161
 162
 163
 164
 165
 166
 167
 168
 169
 170
 171
 172
 173
 174
 175
 176
 177
 178
 179
 180
 181
 182
 183
 184
 185
 186
 187
 188
 189
 190
 191
 192
 193
 194
 195
 196
 197
 198
 199
 200
 201
 202
 203
 204
 205
 206
 207
 208
 209
 210
 211
 212
 213
 214
 215
 216
 217
 218
 219
 220
 221
 222
 223
 224
 225
 226
 227
 228
 229
 230
 231
 232
 233
 234
 235
 236
 237
 238
 239
 240
 241
 242
 243
 244
 245
 246
 247
 248
 249
 250
 251
 252
 253
 254
 255
 256
 257
 258
 259
 260
 261
 262
 263
 264
 265
 266
 267
 268
 269
 270
 271
 272
 273
 274
 275
 276
 277
 278
 279
 280
 281
 282
 283
 284
 285
 286
 287
 288
 289
 290
 291
 292
 293
 294
 295
 296
 297
 298
 299
 300
 301
 302
 303
 304
 305
 306
 307
 308
 309
 310
 311
 312
 313
 314
 315
 316
 317
 318
 319
 320
 321
 322
 323
 324
 325
 326
 327
 328
 329
 330
 331
 332
 333
 334
 335
 336
 337
 338
 339
 340
 341
 342
 343
 344
 345
 346
 347
 348
 349
 350
 351
 352
 353
 354
 355
 356
 357
 358
 359
 360
 361
 362
 363
 364
 365
 366
 367
 368
 369
 370
 371
 372
 373
 374
 375
 376
 377
 378
 379
 380
 381
 382
 383
 384
 385
 386
 387
 388
 389
 390
 391
 392
 393
 394
 395
 396
 397
 398
 399
 400
 401
 402
 403
 404
 405
 406
 407
 408
 409
 410
 411
 412
 413
 414
 415
 416
 417
 418
 419
 420
 421
 422
 423
 424
 425
 426
 427
 428
 429
 430
 431
 432
 433
 434
 435
 436
 437
 438
 439
 440
 441
 442
 443
 444
 445
 446
 447
 448
 449
 450
 451
 452
 453
 454
 455
 456
 457
 458
 459
 460
 461
 462
 463
 464
 465
 466
 467
 468
 469
 470
 471
 472
 473
 474
 475
 476
 477
 478
 479
 480
 481
 482
 483
 484
 485
 486
 487
 488
 489
 490
 491
 492
 493
 494
 495
 496
 497
 498
 499
 500
 501
 502
 503
 504
 505
 506
 507
 508
 509
 510
 511
 512
 513
 514
 515
 516
 517
 518
 519
 520
 521
 522
 523
 524
 525
 526
 527
 528
 529
 530
 531
 532
 533
 534
 535
 536
 537
 538
 539
 540
 541
 542
 543
 544
 545
 546
 547
 548
 549
 550
 551
 552
 553
 554
 555
 556
 557
 558
 559
 560
 561
 562
 563
 564
 565
 566
 567
 568
 569
 570
 571
 572
 573
 574
 575
 576
 577
 578
 579
 580
 581
 582
 583
 584
 585
 586
 587
 588
 589
 590
 591
 592
 593
 594
 595
 596
 597
 598
 599
 600
 601
 602
 603
 604
 605
 606
 607
 608
 609
 610
 611
 612
 613
 614
 615
 616
 617
 618
 619
 620
 621
 622
 623
 624
 625
 626
 627
 628
 629
 630
 631
 632
 633
 634
 635
 636
 637
 638
 639
 640
 641
 642
 643
 644
 645
 646
 647
 648
 649
 650
 651
 652
 653
 654
 655
 656
 657
 658
 659
 660
 661
 662
 663
 664
 665
 666
 667
 668
 669
 670
 671
 672
 673
 674
 675
 676
 677
 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
 729
 730
 731
 732
 733
 734
 735
 736
 737
 738
 739
 740
 741
 742
 743
 744
 745
 746
 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
 795
 796
 797
 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
 823
 824
 825
 826
 827
 828
 829
 830
 831
 832
 833
 834
 835
 836
 837
 838
 839
 840
 841
 842
 843
 844
 845
 846
 847
 848
 849
 850
 851
 852
 853
 854
 855
 856
 857
 858
 859
 860
 861
 862
 863
 864
 865
 866
 867
 868
 869
 870
 871
 872
 873
 874
 875
 876
 877
 878
 879
 880
 881
 882
 883
 884
 885
 886
 887
 888
 889
 890
 891
 892
 893
 894
 895
 896
 897
 898
 899
 900
 901
 902
 903
 904
 905
 906
 907
 908
 909
 910
 911
 912
 913
 914
 915
 916
 917
 918
 919
 920
 921
 922
 923
 924
 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
 965
 966
 967
 968
 969
 970
 971
 972
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
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
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
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
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
1208
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
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
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
1298
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
1326
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
1413
1414
1415
1416
1417
1418
1419
1420
1421
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
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
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
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
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
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
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
1665
1666
1667
1668
1669
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
1712
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
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
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
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
 
#include "builtin.h"
#include "config.h"
#include "delta.h"
#include "pack.h"
#include "csum-file.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree.h"
#include "progress.h"
#include "fsck.h"
#include "exec-cmd.h"
#include "streaming.h"
#include "thread-utils.h"
#include "packfile.h"
#include "object-store.h"
#include "promisor-remote.h"

static const char index_pack_usage[] =
"git index-pack [-v] [-o <index-file>] [--keep | --keep=<msg>] [--verify] [--strict] (<pack-file> | --stdin [--fix-thin] [<pack-file>])";

struct object_entry {
	struct pack_idx_entry idx;
	unsigned long size;
	unsigned char hdr_size;
	signed char type;
	signed char real_type;
};

struct object_stat {
	unsigned delta_depth;
	int base_object_no;
};

struct base_data {
	struct base_data *base;
	struct object_entry *obj;
	void *data;
	unsigned long size;
	int ref_first, ref_last;
	int ofs_first, ofs_last;
};

struct thread_local {
	pthread_t thread;
	size_t base_cache_used;
	int pack_fd;
};

/* Remember to update object flag allocation in object.h */
#define FLAG_LINK (1u<<20)
#define FLAG_CHECKED (1u<<21)

struct ofs_delta_entry {
	off_t offset;
	int obj_no;
};

struct ref_delta_entry {
	struct object_id oid;
	int obj_no;
};

static struct object_entry *objects;
static struct object_stat *obj_stat;
static struct ofs_delta_entry *ofs_deltas;
static struct ref_delta_entry *ref_deltas;
static struct thread_local nothread_data;
static int nr_objects;
static int nr_ofs_deltas;
static int nr_ref_deltas;
static int ref_deltas_alloc;
static int nr_resolved_deltas;
static int nr_threads;

static int from_stdin;
static int strict;
static int do_fsck_object;
static struct fsck_options fsck_options = FSCK_OPTIONS_STRICT;
static int verbose;
static int show_resolving_progress;
static int show_stat;
static int check_self_contained_and_connected;

static struct progress *progress;

/* We always read in 4kB chunks. */
static unsigned char input_buffer[4096];
static unsigned int input_offset, input_len;
static off_t consumed_bytes;
static off_t max_input_size;
static unsigned deepest_delta;
static git_hash_ctx input_ctx;
static uint32_t input_crc32;
static int input_fd, output_fd;
static const char *curr_pack;

static struct thread_local *thread_data;
static int nr_dispatched;
static int threads_active;

static pthread_mutex_t read_mutex;
#define read_lock()		lock_mutex(&read_mutex)
#define read_unlock()		unlock_mutex(&read_mutex)

static pthread_mutex_t counter_mutex;
#define counter_lock()		lock_mutex(&counter_mutex)
#define counter_unlock()	unlock_mutex(&counter_mutex)

static pthread_mutex_t work_mutex;
#define work_lock()		lock_mutex(&work_mutex)
#define work_unlock()		unlock_mutex(&work_mutex)

static pthread_mutex_t deepest_delta_mutex;
#define deepest_delta_lock()	lock_mutex(&deepest_delta_mutex)
#define deepest_delta_unlock()	unlock_mutex(&deepest_delta_mutex)

static pthread_mutex_t type_cas_mutex;
#define type_cas_lock()		lock_mutex(&type_cas_mutex)
#define type_cas_unlock()	unlock_mutex(&type_cas_mutex)

static pthread_key_t key;

static inline void lock_mutex(pthread_mutex_t *mutex)
{
	if (threads_active)
		pthread_mutex_lock(mutex);
}

static inline void unlock_mutex(pthread_mutex_t *mutex)
{
	if (threads_active)
		pthread_mutex_unlock(mutex);
}

/*
 * Mutex and conditional variable can't be statically-initialized on Windows.
 */
static void init_thread(void)
{
	int i;
	init_recursive_mutex(&read_mutex);
	pthread_mutex_init(&counter_mutex, NULL);
	pthread_mutex_init(&work_mutex, NULL);
	pthread_mutex_init(&type_cas_mutex, NULL);
	if (show_stat)
		pthread_mutex_init(&deepest_delta_mutex, NULL);
	pthread_key_create(&key, NULL);
	thread_data = xcalloc(nr_threads, sizeof(*thread_data));
	for (i = 0; i < nr_threads; i++) {
		thread_data[i].pack_fd = open(curr_pack, O_RDONLY);
		if (thread_data[i].pack_fd == -1)
			die_errno(_("unable to open %s"), curr_pack);
	}

	threads_active = 1;
}

static void cleanup_thread(void)
{
	int i;
	if (!threads_active)
		return;
	threads_active = 0;
	pthread_mutex_destroy(&read_mutex);
	pthread_mutex_destroy(&counter_mutex);
	pthread_mutex_destroy(&work_mutex);
	pthread_mutex_destroy(&type_cas_mutex);
	if (show_stat)
		pthread_mutex_destroy(&deepest_delta_mutex);
	for (i = 0; i < nr_threads; i++)
		close(thread_data[i].pack_fd);
	pthread_key_delete(key);
	free(thread_data);
}

static int mark_link(struct object *obj, int type, void *data, struct fsck_options *options)
{
	if (!obj)
		return -1;

	if (type != OBJ_ANY && obj->type != type)
		die(_("object type mismatch at %s"), oid_to_hex(&obj->oid));

	obj->flags |= FLAG_LINK;
	return 0;
}

/* The content of each linked object must have been checked
   or it must be already present in the object database */
static unsigned check_object(struct object *obj)
{
	if (!obj)
		return 0;

	if (!(obj->flags & FLAG_LINK))
		return 0;

	if (!(obj->flags & FLAG_CHECKED)) {
		unsigned long size;
		int type = oid_object_info(the_repository, &obj->oid, &size);
		if (type <= 0)
			die(_("did not receive expected object %s"),
			      oid_to_hex(&obj->oid));
		if (type != obj->type)
			die(_("object %s: expected type %s, found %s"),
			    oid_to_hex(&obj->oid),
			    type_name(obj->type), type_name(type));
		obj->flags |= FLAG_CHECKED;
		return 1;
	}

	return 0;
}

static unsigned check_objects(void)
{
	unsigned i, max, foreign_nr = 0;

	max = get_max_object_index();

	if (verbose)
		progress = start_delayed_progress(_("Checking objects"), max);

	for (i = 0; i < max; i++) {
		foreign_nr += check_object(get_indexed_object(i));
		display_progress(progress, i + 1);
	}

	stop_progress(&progress);
	return foreign_nr;
}


/* Discard current buffer used content. */
static void flush(void)
{
	if (input_offset) {
		if (output_fd >= 0)
			write_or_die(output_fd, input_buffer, input_offset);
		the_hash_algo->update_fn(&input_ctx, input_buffer, input_offset);
		memmove(input_buffer, input_buffer + input_offset, input_len);
		input_offset = 0;
	}
}

/*
 * Make sure at least "min" bytes are available in the buffer, and
 * return the pointer to the buffer.
 */
static void *fill(int min)
{
	if (min <= input_len)
		return input_buffer + input_offset;
	if (min > sizeof(input_buffer))
		die(Q_("cannot fill %d byte",
		       "cannot fill %d bytes",
		       min),
		    min);
	flush();
	do {
		ssize_t ret = xread(input_fd, input_buffer + input_len,
				sizeof(input_buffer) - input_len);
		if (ret <= 0) {
			if (!ret)
				die(_("early EOF"));
			die_errno(_("read error on input"));
		}
		input_len += ret;
		if (from_stdin)
			display_throughput(progress, consumed_bytes + input_len);
	} while (input_len < min);
	return input_buffer;
}

static void use(int bytes)
{
	if (bytes > input_len)
		die(_("used more bytes than were available"));
	input_crc32 = crc32(input_crc32, input_buffer + input_offset, bytes);
	input_len -= bytes;
	input_offset += bytes;

	/* make sure off_t is sufficiently large not to wrap */
	if (signed_add_overflows(consumed_bytes, bytes))
		die(_("pack too large for current definition of off_t"));
	consumed_bytes += bytes;
	if (max_input_size && consumed_bytes > max_input_size)
		die(_("pack exceeds maximum allowed size"));
}

static const char *open_pack_file(const char *pack_name)
{
	if (from_stdin) {
		input_fd = 0;
		if (!pack_name) {
			struct strbuf tmp_file = STRBUF_INIT;
			output_fd = odb_mkstemp(&tmp_file,
						"pack/tmp_pack_XXXXXX");
			pack_name = strbuf_detach(&tmp_file, NULL);
		} else {
			output_fd = open(pack_name, O_CREAT|O_EXCL|O_RDWR, 0600);
			if (output_fd < 0)
				die_errno(_("unable to create '%s'"), pack_name);
		}
		nothread_data.pack_fd = output_fd;
	} else {
		input_fd = open(pack_name, O_RDONLY);
		if (input_fd < 0)
			die_errno(_("cannot open packfile '%s'"), pack_name);
		output_fd = -1;
		nothread_data.pack_fd = input_fd;
	}
	the_hash_algo->init_fn(&input_ctx);
	return pack_name;
}

static void parse_pack_header(void)
{
	struct pack_header *hdr = fill(sizeof(struct pack_header));

	/* Header consistency check */
	if (hdr->hdr_signature != htonl(PACK_SIGNATURE))
		die(_("pack signature mismatch"));
	if (!pack_version_ok(hdr->hdr_version))
		die(_("pack version %"PRIu32" unsupported"),
			ntohl(hdr->hdr_version));

	nr_objects = ntohl(hdr->hdr_entries);
	use(sizeof(struct pack_header));
}

static NORETURN void bad_object(off_t offset, const char *format,
		       ...) __attribute__((format (printf, 2, 3)));

static NORETURN void bad_object(off_t offset, const char *format, ...)
{
	va_list params;
	char buf[1024];

	va_start(params, format);
	vsnprintf(buf, sizeof(buf), format, params);
	va_end(params);
	die(_("pack has bad object at offset %"PRIuMAX": %s"),
	    (uintmax_t)offset, buf);
}

static inline struct thread_local *get_thread_data(void)
{
	if (HAVE_THREADS) {
		if (threads_active)
			return pthread_getspecific(key);
		assert(!threads_active &&
		       "This should only be reached when all threads are gone");
	}
	return &nothread_data;
}

static void set_thread_data(struct thread_local *data)
{
	if (threads_active)
		pthread_setspecific(key, data);
}

static struct base_data *alloc_base_data(void)
{
	struct base_data *base = xcalloc(1, sizeof(struct base_data));
	base->ref_last = -1;
	base->ofs_last = -1;
	return base;
}

static void free_base_data(struct base_data *c)
{
	if (c->data) {
		FREE_AND_NULL(c->data);
		get_thread_data()->base_cache_used -= c->size;
	}
}

static void prune_base_data(struct base_data *youngest_child)
{
	struct base_data *b;
	struct thread_local *data = get_thread_data();
	struct base_data **ancestry = NULL;
	size_t nr = 0, alloc = 0;
	ssize_t i;

	if (data->base_cache_used <= delta_base_cache_limit)
		return;

	/*
	 * Free all ancestors of youngest_child until we have enough space,
	 * starting with the oldest. (We cannot free youngest_child itself.)
	 */
	for (b = youngest_child->base; b != NULL; b = b->base) {
		ALLOC_GROW(ancestry, nr + 1, alloc);
		ancestry[nr++] = b;
	}
	for (i = nr - 1;
	     i >= 0 && data->base_cache_used > delta_base_cache_limit;
	     i--) {
		if (ancestry[i]->data)
			free_base_data(ancestry[i]);
	}
	free(ancestry);
}

static void link_base_data(struct base_data *base, struct base_data *c)
{
	c->base = base;
	if (c->data)
		get_thread_data()->base_cache_used += c->size;
	prune_base_data(c);
}

static void unlink_base_data(struct base_data *c)
{
	free_base_data(c);
}

static int is_delta_type(enum object_type type)
{
	return (type == OBJ_REF_DELTA || type == OBJ_OFS_DELTA);
}

static void *unpack_entry_data(off_t offset, unsigned long size,
			       enum object_type type, struct object_id *oid)
{
	static char fixed_buf[8192];
	int status;
	git_zstream stream;
	void *buf;
	git_hash_ctx c;
	char hdr[32];
	int hdrlen;

	if (!is_delta_type(type)) {
		hdrlen = xsnprintf(hdr, sizeof(hdr), "%s %"PRIuMAX,
				   type_name(type),(uintmax_t)size) + 1;
		the_hash_algo->init_fn(&c);
		the_hash_algo->update_fn(&c, hdr, hdrlen);
	} else
		oid = NULL;
	if (type == OBJ_BLOB && size > big_file_threshold)
		buf = fixed_buf;
	else
		buf = xmallocz(size);

	memset(&stream, 0, sizeof(stream));
	git_inflate_init(&stream);
	stream.next_out = buf;
	stream.avail_out = buf == fixed_buf ? sizeof(fixed_buf) : size;

	do {
		unsigned char *last_out = stream.next_out;
		stream.next_in = fill(1);
		stream.avail_in = input_len;
		status = git_inflate(&stream, 0);
		use(input_len - stream.avail_in);
		if (oid)
			the_hash_algo->update_fn(&c, last_out, stream.next_out - last_out);
		if (buf == fixed_buf) {
			stream.next_out = buf;
			stream.avail_out = sizeof(fixed_buf);
		}
	} while (status == Z_OK);
	if (stream.total_out != size || status != Z_STREAM_END)
		bad_object(offset, _("inflate returned %d"), status);
	git_inflate_end(&stream);
	if (oid)
		the_hash_algo->final_fn(oid->hash, &c);
	return buf == fixed_buf ? NULL : buf;
}

static void *unpack_raw_entry(struct object_entry *obj,
			      off_t *ofs_offset,
			      struct object_id *ref_oid,
			      struct object_id *oid)
{
	unsigned char *p;
	unsigned long size, c;
	off_t base_offset;
	unsigned shift;
	void *data;

	obj->idx.offset = consumed_bytes;
	input_crc32 = crc32(0, NULL, 0);

	p = fill(1);
	c = *p;
	use(1);
	obj->type = (c >> 4) & 7;
	size = (c & 15);
	shift = 4;
	while (c & 0x80) {
		p = fill(1);
		c = *p;
		use(1);
		size += (c & 0x7f) << shift;
		shift += 7;
	}
	obj->size = size;

	switch (obj->type) {
	case OBJ_REF_DELTA:
		hashcpy(ref_oid->hash, fill(the_hash_algo->rawsz));
		use(the_hash_algo->rawsz);
		break;
	case OBJ_OFS_DELTA:
		p = fill(1);
		c = *p;
		use(1);
		base_offset = c & 127;
		while (c & 128) {
			base_offset += 1;
			if (!base_offset || MSB(base_offset, 7))
				bad_object(obj->idx.offset, _("offset value overflow for delta base object"));
			p = fill(1);
			c = *p;
			use(1);
			base_offset = (base_offset << 7) + (c & 127);
		}
		*ofs_offset = obj->idx.offset - base_offset;
		if (*ofs_offset <= 0 || *ofs_offset >= obj->idx.offset)
			bad_object(obj->idx.offset, _("delta base offset is out of bound"));
		break;
	case OBJ_COMMIT:
	case OBJ_TREE:
	case OBJ_BLOB:
	case OBJ_TAG:
		break;
	default:
		bad_object(obj->idx.offset, _("unknown object type %d"), obj->type);
	}
	obj->hdr_size = consumed_bytes - obj->idx.offset;

	data = unpack_entry_data(obj->idx.offset, obj->size, obj->type, oid);
	obj->idx.crc32 = input_crc32;
	return data;
}

static void *unpack_data(struct object_entry *obj,
			 int (*consume)(const unsigned char *, unsigned long, void *),
			 void *cb_data)
{
	off_t from = obj[0].idx.offset + obj[0].hdr_size;
	off_t len = obj[1].idx.offset - from;
	unsigned char *data, *inbuf;
	git_zstream stream;
	int status;

	data = xmallocz(consume ? 64*1024 : obj->size);
	inbuf = xmalloc((len < 64*1024) ? (int)len : 64*1024);

	memset(&stream, 0, sizeof(stream));
	git_inflate_init(&stream);
	stream.next_out = data;
	stream.avail_out = consume ? 64*1024 : obj->size;

	do {
		ssize_t n = (len < 64*1024) ? (ssize_t)len : 64*1024;
		n = xpread(get_thread_data()->pack_fd, inbuf, n, from);
		if (n < 0)
			die_errno(_("cannot pread pack file"));
		if (!n)
			die(Q_("premature end of pack file, %"PRIuMAX" byte missing",
			       "premature end of pack file, %"PRIuMAX" bytes missing",
			       (unsigned int)len),
			    (uintmax_t)len);
		from += n;
		len -= n;
		stream.next_in = inbuf;
		stream.avail_in = n;
		if (!consume)
			status = git_inflate(&stream, 0);
		else {
			do {
				status = git_inflate(&stream, 0);
				if (consume(data, stream.next_out - data, cb_data)) {
					free(inbuf);
					free(data);
					return NULL;
				}
				stream.next_out = data;
				stream.avail_out = 64*1024;
			} while (status == Z_OK && stream.avail_in);
		}
	} while (len && status == Z_OK && !stream.avail_in);

	/* This has been inflated OK when first encountered, so... */
	if (status != Z_STREAM_END || stream.total_out != obj->size)
		die(_("serious inflate inconsistency"));

	git_inflate_end(&stream);
	free(inbuf);
	if (consume) {
		FREE_AND_NULL(data);
	}
	return data;
}

static void *get_data_from_pack(struct object_entry *obj)
{
	return unpack_data(obj, NULL, NULL);
}

static int compare_ofs_delta_bases(off_t offset1, off_t offset2,
				   enum object_type type1,
				   enum object_type type2)
{
	int cmp = type1 - type2;
	if (cmp)
		return cmp;
	return offset1 < offset2 ? -1 :
	       offset1 > offset2 ?  1 :
	       0;
}

static int find_ofs_delta(const off_t offset)
{
	int first = 0, last = nr_ofs_deltas;

	while (first < last) {
		int next = first + (last - first) / 2;
		struct ofs_delta_entry *delta = &ofs_deltas[next];
		int cmp;

		cmp = compare_ofs_delta_bases(offset, delta->offset,
					      OBJ_OFS_DELTA,
					      objects[delta->obj_no].type);
		if (!cmp)
			return next;
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
	return -first-1;
}

static void find_ofs_delta_children(off_t offset,
				    int *first_index, int *last_index)
{
	int first = find_ofs_delta(offset);
	int last = first;
	int end = nr_ofs_deltas - 1;

	if (first < 0) {
		*first_index = 0;
		*last_index = -1;
		return;
	}
	while (first > 0 && ofs_deltas[first - 1].offset == offset)
		--first;
	while (last < end && ofs_deltas[last + 1].offset == offset)
		++last;
	*first_index = first;
	*last_index = last;
}

static int compare_ref_delta_bases(const struct object_id *oid1,
				   const struct object_id *oid2,
				   enum object_type type1,
				   enum object_type type2)
{
	int cmp = type1 - type2;
	if (cmp)
		return cmp;
	return oidcmp(oid1, oid2);
}

static int find_ref_delta(const struct object_id *oid)
{
	int first = 0, last = nr_ref_deltas;

	while (first < last) {
		int next = first + (last - first) / 2;
		struct ref_delta_entry *delta = &ref_deltas[next];
		int cmp;

		cmp = compare_ref_delta_bases(oid, &delta->oid,
					      OBJ_REF_DELTA,
					      objects[delta->obj_no].type);
		if (!cmp)
			return next;
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
	return -first-1;
}

static void find_ref_delta_children(const struct object_id *oid,
				    int *first_index, int *last_index)
{
	int first = find_ref_delta(oid);
	int last = first;
	int end = nr_ref_deltas - 1;

	if (first < 0) {
		*first_index = 0;
		*last_index = -1;
		return;
	}
	while (first > 0 && oideq(&ref_deltas[first - 1].oid, oid))
		--first;
	while (last < end && oideq(&ref_deltas[last + 1].oid, oid))
		++last;
	*first_index = first;
	*last_index = last;
}

struct compare_data {
	struct object_entry *entry;
	struct git_istream *st;
	unsigned char *buf;
	unsigned long buf_size;
};

static int compare_objects(const unsigned char *buf, unsigned long size,
			   void *cb_data)
{
	struct compare_data *data = cb_data;

	if (data->buf_size < size) {
		free(data->buf);
		data->buf = xmalloc(size);
		data->buf_size = size;
	}

	while (size) {
		ssize_t len = read_istream(data->st, data->buf, size);
		if (len == 0)
			die(_("SHA1 COLLISION FOUND WITH %s !"),
			    oid_to_hex(&data->entry->idx.oid));
		if (len < 0)
			die(_("unable to read %s"),
			    oid_to_hex(&data->entry->idx.oid));
		if (memcmp(buf, data->buf, len))
			die(_("SHA1 COLLISION FOUND WITH %s !"),
			    oid_to_hex(&data->entry->idx.oid));
		size -= len;
		buf += len;
	}
	return 0;
}

static int check_collison(struct object_entry *entry)
{
	struct compare_data data;
	enum object_type type;
	unsigned long size;

	if (entry->size <= big_file_threshold || entry->type != OBJ_BLOB)
		return -1;

	memset(&data, 0, sizeof(data));
	data.entry = entry;
	data.st = open_istream(&entry->idx.oid, &type, &size, NULL);
	if (!data.st)
		return -1;
	if (size != entry->size || type != entry->type)
		die(_("SHA1 COLLISION FOUND WITH %s !"),
		    oid_to_hex(&entry->idx.oid));
	unpack_data(entry, compare_objects, &data);
	close_istream(data.st);
	free(data.buf);
	return 0;
}

static void sha1_object(const void *data, struct object_entry *obj_entry,
			unsigned long size, enum object_type type,
			const struct object_id *oid)
{
	void *new_data = NULL;
	int collision_test_needed = 0;

	assert(data || obj_entry);

	if (startup_info->have_repository) {
		read_lock();
		collision_test_needed =
			has_object_file_with_flags(oid, OBJECT_INFO_QUICK);
		read_unlock();
	}

	if (collision_test_needed && !data) {
		read_lock();
		if (!check_collison(obj_entry))
			collision_test_needed = 0;
		read_unlock();
	}
	if (collision_test_needed) {
		void *has_data;
		enum object_type has_type;
		unsigned long has_size;
		read_lock();
		has_type = oid_object_info(the_repository, oid, &has_size);
		if (has_type < 0)
			die(_("cannot read existing object info %s"), oid_to_hex(oid));
		if (has_type != type || has_size != size)
			die(_("SHA1 COLLISION FOUND WITH %s !"), oid_to_hex(oid));
		has_data = read_object_file(oid, &has_type, &has_size);
		read_unlock();
		if (!data)
			data = new_data = get_data_from_pack(obj_entry);
		if (!has_data)
			die(_("cannot read existing object %s"), oid_to_hex(oid));
		if (size != has_size || type != has_type ||
		    memcmp(data, has_data, size) != 0)
			die(_("SHA1 COLLISION FOUND WITH %s !"), oid_to_hex(oid));
		free(has_data);
	}

	if (strict || do_fsck_object) {
		read_lock();
		if (type == OBJ_BLOB) {
			struct blob *blob = lookup_blob(the_repository, oid);
			if (blob)
				blob->object.flags |= FLAG_CHECKED;
			else
				die(_("invalid blob object %s"), oid_to_hex(oid));
			if (do_fsck_object &&
			    fsck_object(&blob->object, (void *)data, size, &fsck_options))
				die(_("fsck error in packed object"));
		} else {
			struct object *obj;
			int eaten;
			void *buf = (void *) data;

			assert(data && "data can only be NULL for large _blobs_");

			/*
			 * we do not need to free the memory here, as the
			 * buf is deleted by the caller.
			 */
			obj = parse_object_buffer(the_repository, oid, type,
						  size, buf,
						  &eaten);
			if (!obj)
				die(_("invalid %s"), type_name(type));
			if (do_fsck_object &&
			    fsck_object(obj, buf, size, &fsck_options))
				die(_("fsck error in packed object"));
			if (strict && fsck_walk(obj, NULL, &fsck_options))
				die(_("Not all child objects of %s are reachable"), oid_to_hex(&obj->oid));

			if (obj->type == OBJ_TREE) {
				struct tree *item = (struct tree *) obj;
				item->buffer = NULL;
				obj->parsed = 0;
			}
			if (obj->type == OBJ_COMMIT) {
				struct commit *commit = (struct commit *) obj;
				if (detach_commit_buffer(commit, NULL) != data)
					BUG("parse_object_buffer transmogrified our buffer");
			}
			obj->flags |= FLAG_CHECKED;
		}
		read_unlock();
	}

	free(new_data);
}

/*
 * This function is part of find_unresolved_deltas(). There are two
 * walkers going in the opposite ways.
 *
 * The first one in find_unresolved_deltas() traverses down from
 * parent node to children, deflating nodes along the way. However,
 * memory for deflated nodes is limited by delta_base_cache_limit, so
 * at some point parent node's deflated content may be freed.
 *
 * The second walker is this function, which goes from current node up
 * to top parent if necessary to deflate the node. In normal
 * situation, its parent node would be already deflated, so it just
 * needs to apply delta.
 *
 * In the worst case scenario, parent node is no longer deflated because
 * we're running out of delta_base_cache_limit; we need to re-deflate
 * parents, possibly up to the top base.
 *
 * All deflated objects here are subject to be freed if we exceed
 * delta_base_cache_limit, just like in find_unresolved_deltas(), we
 * just need to make sure the last node is not freed.
 */
static void *get_base_data(struct base_data *c)
{
	if (!c->data) {
		struct object_entry *obj = c->obj;
		struct base_data **delta = NULL;
		int delta_nr = 0, delta_alloc = 0;

		while (is_delta_type(c->obj->type) && !c->data) {
			ALLOC_GROW(delta, delta_nr + 1, delta_alloc);
			delta[delta_nr++] = c;
			c = c->base;
		}
		if (!delta_nr) {
			c->data = get_data_from_pack(obj);
			c->size = obj->size;
			get_thread_data()->base_cache_used += c->size;
			prune_base_data(c);
		}
		for (; delta_nr > 0; delta_nr--) {
			void *base, *raw;
			c = delta[delta_nr - 1];
			obj = c->obj;
			base = get_base_data(c->base);
			raw = get_data_from_pack(obj);
			c->data = patch_delta(
				base, c->base->size,
				raw, obj->size,
				&c->size);
			free(raw);
			if (!c->data)
				bad_object(obj->idx.offset, _("failed to apply delta"));
			get_thread_data()->base_cache_used += c->size;
			prune_base_data(c);
		}
		free(delta);
	}
	return c->data;
}

static void resolve_delta(struct object_entry *delta_obj,
			  struct base_data *base, struct base_data *result)
{
	void *base_data, *delta_data;

	if (show_stat) {
		int i = delta_obj - objects;
		int j = base->obj - objects;
		obj_stat[i].delta_depth = obj_stat[j].delta_depth + 1;
		deepest_delta_lock();
		if (deepest_delta < obj_stat[i].delta_depth)
			deepest_delta = obj_stat[i].delta_depth;
		deepest_delta_unlock();
		obj_stat[i].base_object_no = j;
	}
	delta_data = get_data_from_pack(delta_obj);
	base_data = get_base_data(base);
	result->obj = delta_obj;
	result->data = patch_delta(base_data, base->size,
				   delta_data, delta_obj->size, &result->size);
	free(delta_data);
	if (!result->data)
		bad_object(delta_obj->idx.offset, _("failed to apply delta"));
	hash_object_file(result->data, result->size,
			 type_name(delta_obj->real_type), &delta_obj->idx.oid);
	sha1_object(result->data, NULL, result->size, delta_obj->real_type,
		    &delta_obj->idx.oid);
	counter_lock();
	nr_resolved_deltas++;
	counter_unlock();
}

/*
 * Standard boolean compare-and-swap: atomically check whether "*type" is
 * "want"; if so, swap in "set" and return true. Otherwise, leave it untouched
 * and return false.
 */
static int compare_and_swap_type(signed char *type,
				 enum object_type want,
				 enum object_type set)
{
	enum object_type old;

	type_cas_lock();
	old = *type;
	if (old == want)
		*type = set;
	type_cas_unlock();

	return old == want;
}

static struct base_data *find_unresolved_deltas_1(struct base_data *base,
						  struct base_data *prev_base)
{
	if (base->ref_last == -1 && base->ofs_last == -1) {
		find_ref_delta_children(&base->obj->idx.oid,
					&base->ref_first, &base->ref_last);

		find_ofs_delta_children(base->obj->idx.offset,
					&base->ofs_first, &base->ofs_last);

		if (base->ref_last == -1 && base->ofs_last == -1) {
			free(base->data);
			return NULL;
		}

		link_base_data(prev_base, base);
	}

	if (base->ref_first <= base->ref_last) {
		struct object_entry *child = objects + ref_deltas[base->ref_first].obj_no;
		struct base_data *result = alloc_base_data();

		if (!compare_and_swap_type(&child->real_type, OBJ_REF_DELTA,
					   base->obj->real_type))
			BUG("child->real_type != OBJ_REF_DELTA");

		resolve_delta(child, base, result);
		if (base->ref_first == base->ref_last && base->ofs_last == -1)
			free_base_data(base);

		base->ref_first++;
		return result;
	}

	if (base->ofs_first <= base->ofs_last) {
		struct object_entry *child = objects + ofs_deltas[base->ofs_first].obj_no;
		struct base_data *result = alloc_base_data();

		assert(child->real_type == OBJ_OFS_DELTA);
		child->real_type = base->obj->real_type;
		resolve_delta(child, base, result);
		if (base->ofs_first == base->ofs_last)
			free_base_data(base);

		base->ofs_first++;
		return result;
	}

	unlink_base_data(base);
	return NULL;
}

static void find_unresolved_deltas(struct base_data *base)
{
	struct base_data *new_base, *prev_base = NULL;
	for (;;) {
		new_base = find_unresolved_deltas_1(base, prev_base);

		if (new_base) {
			prev_base = base;
			base = new_base;
		} else {
			free(base);
			base = prev_base;
			if (!base)
				return;
			prev_base = base->base;
		}
	}
}

static int compare_ofs_delta_entry(const void *a, const void *b)
{
	const struct ofs_delta_entry *delta_a = a;
	const struct ofs_delta_entry *delta_b = b;

	return delta_a->offset < delta_b->offset ? -1 :
	       delta_a->offset > delta_b->offset ?  1 :
	       0;
}

static int compare_ref_delta_entry(const void *a, const void *b)
{
	const struct ref_delta_entry *delta_a = a;
	const struct ref_delta_entry *delta_b = b;

	return oidcmp(&delta_a->oid, &delta_b->oid);
}

static void resolve_base(struct object_entry *obj)
{
	struct base_data *base_obj = alloc_base_data();
	base_obj->obj = obj;
	base_obj->data = NULL;
	find_unresolved_deltas(base_obj);
}

static void *threaded_second_pass(void *data)
{
	set_thread_data(data);
	for (;;) {
		int i;
		counter_lock();
		display_progress(progress, nr_resolved_deltas);
		counter_unlock();
		work_lock();
		while (nr_dispatched < nr_objects &&
		       is_delta_type(objects[nr_dispatched].type))
			nr_dispatched++;
		if (nr_dispatched >= nr_objects) {
			work_unlock();
			break;
		}
		i = nr_dispatched++;
		work_unlock();

		resolve_base(&objects[i]);
	}
	return NULL;
}

/*
 * First pass:
 * - find locations of all objects;
 * - calculate SHA1 of all non-delta objects;
 * - remember base (SHA1 or offset) for all deltas.
 */
static void parse_pack_objects(unsigned char *hash)
{
	int i, nr_delays = 0;
	struct ofs_delta_entry *ofs_delta = ofs_deltas;
	struct object_id ref_delta_oid;
	struct stat st;

	if (verbose)
		progress = start_progress(
				from_stdin ? _("Receiving objects") : _("Indexing objects"),
				nr_objects);
	for (i = 0; i < nr_objects; i++) {
		struct object_entry *obj = &objects[i];
		void *data = unpack_raw_entry(obj, &ofs_delta->offset,
					      &ref_delta_oid,
					      &obj->idx.oid);
		obj->real_type = obj->type;
		if (obj->type == OBJ_OFS_DELTA) {
			nr_ofs_deltas++;
			ofs_delta->obj_no = i;
			ofs_delta++;
		} else if (obj->type == OBJ_REF_DELTA) {
			ALLOC_GROW(ref_deltas, nr_ref_deltas + 1, ref_deltas_alloc);
			oidcpy(&ref_deltas[nr_ref_deltas].oid, &ref_delta_oid);
			ref_deltas[nr_ref_deltas].obj_no = i;
			nr_ref_deltas++;
		} else if (!data) {
			/* large blobs, check later */
			obj->real_type = OBJ_BAD;
			nr_delays++;
		} else
			sha1_object(data, NULL, obj->size, obj->type,
				    &obj->idx.oid);
		free(data);
		display_progress(progress, i+1);
	}
	objects[i].idx.offset = consumed_bytes;
	stop_progress(&progress);

	/* Check pack integrity */
	flush();
	the_hash_algo->final_fn(hash, &input_ctx);
	if (!hasheq(fill(the_hash_algo->rawsz), hash))
		die(_("pack is corrupted (SHA1 mismatch)"));
	use(the_hash_algo->rawsz);

	/* If input_fd is a file, we should have reached its end now. */
	if (fstat(input_fd, &st))
		die_errno(_("cannot fstat packfile"));
	if (S_ISREG(st.st_mode) &&
			lseek(input_fd, 0, SEEK_CUR) - input_len != st.st_size)
		die(_("pack has junk at the end"));

	for (i = 0; i < nr_objects; i++) {
		struct object_entry *obj = &objects[i];
		if (obj->real_type != OBJ_BAD)
			continue;
		obj->real_type = obj->type;
		sha1_object(NULL, obj, obj->size, obj->type,
			    &obj->idx.oid);
		nr_delays--;
	}
	if (nr_delays)
		die(_("confusion beyond insanity in parse_pack_objects()"));
}

/*
 * Second pass:
 * - for all non-delta objects, look if it is used as a base for
 *   deltas;
 * - if used as a base, uncompress the object and apply all deltas,
 *   recursively checking if the resulting object is used as a base
 *   for some more deltas.
 */
static void resolve_deltas(void)
{
	int i;

	if (!nr_ofs_deltas && !nr_ref_deltas)
		return;

	/* Sort deltas by base SHA1/offset for fast searching */
	QSORT(ofs_deltas, nr_ofs_deltas, compare_ofs_delta_entry);
	QSORT(ref_deltas, nr_ref_deltas, compare_ref_delta_entry);

	if (verbose || show_resolving_progress)
		progress = start_progress(_("Resolving deltas"),
					  nr_ref_deltas + nr_ofs_deltas);

	nr_dispatched = 0;
	if (nr_threads > 1 || getenv("GIT_FORCE_THREADS")) {
		init_thread();
		for (i = 0; i < nr_threads; i++) {
			int ret = pthread_create(&thread_data[i].thread, NULL,
						 threaded_second_pass, thread_data + i);
			if (ret)
				die(_("unable to create thread: %s"),
				    strerror(ret));
		}
		for (i = 0; i < nr_threads; i++)
			pthread_join(thread_data[i].thread, NULL);
		cleanup_thread();
		return;
	}
	threaded_second_pass(&nothread_data);
}

/*
 * Third pass:
 * - append objects to convert thin pack to full pack if required
 * - write the final pack hash
 */
static void fix_unresolved_deltas(struct hashfile *f);
static void conclude_pack(int fix_thin_pack, const char *curr_pack, unsigned char *pack_hash)
{
	if (nr_ref_deltas + nr_ofs_deltas == nr_resolved_deltas) {
		stop_progress(&progress);
		/* Flush remaining pack final hash. */
		flush();
		return;
	}

	if (fix_thin_pack) {
		struct hashfile *f;
		unsigned char read_hash[GIT_MAX_RAWSZ], tail_hash[GIT_MAX_RAWSZ];
		struct strbuf msg = STRBUF_INIT;
		int nr_unresolved = nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas;
		int nr_objects_initial = nr_objects;
		if (nr_unresolved <= 0)
			die(_("confusion beyond insanity"));
		REALLOC_ARRAY(objects, nr_objects + nr_unresolved + 1);
		memset(objects + nr_objects + 1, 0,
		       nr_unresolved * sizeof(*objects));
		f = hashfd(output_fd, curr_pack);
		fix_unresolved_deltas(f);
		strbuf_addf(&msg, Q_("completed with %d local object",
				     "completed with %d local objects",
				     nr_objects - nr_objects_initial),
			    nr_objects - nr_objects_initial);
		stop_progress_msg(&progress, msg.buf);
		strbuf_release(&msg);
		finalize_hashfile(f, tail_hash, 0);
		hashcpy(read_hash, pack_hash);
		fixup_pack_header_footer(output_fd, pack_hash,
					 curr_pack, nr_objects,
					 read_hash, consumed_bytes-the_hash_algo->rawsz);
		if (!hasheq(read_hash, tail_hash))
			die(_("Unexpected tail checksum for %s "
			      "(disk corruption?)"), curr_pack);
	}
	if (nr_ofs_deltas + nr_ref_deltas != nr_resolved_deltas)
		die(Q_("pack has %d unresolved delta",
		       "pack has %d unresolved deltas",
		       nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas),
		    nr_ofs_deltas + nr_ref_deltas - nr_resolved_deltas);
}

static int write_compressed(struct hashfile *f, void *in, unsigned int size)
{
	git_zstream stream;
	int status;
	unsigned char outbuf[4096];

	git_deflate_init(&stream, zlib_compression_level);
	stream.next_in = in;
	stream.avail_in = size;

	do {
		stream.next_out = outbuf;
		stream.avail_out = sizeof(outbuf);
		status = git_deflate(&stream, Z_FINISH);
		hashwrite(f, outbuf, sizeof(outbuf) - stream.avail_out);
	} while (status == Z_OK);

	if (status != Z_STREAM_END)
		die(_("unable to deflate appended object (%d)"), status);
	size = stream.total_out;
	git_deflate_end(&stream);
	return size;
}

static struct object_entry *append_obj_to_pack(struct hashfile *f,
			       const unsigned char *sha1, void *buf,
			       unsigned long size, enum object_type type)
{
	struct object_entry *obj = &objects[nr_objects++];
	unsigned char header[10];
	unsigned long s = size;
	int n = 0;
	unsigned char c = (type << 4) | (s & 15);
	s >>= 4;
	while (s) {
		header[n++] = c | 0x80;
		c = s & 0x7f;
		s >>= 7;
	}
	header[n++] = c;
	crc32_begin(f);
	hashwrite(f, header, n);
	obj[0].size = size;
	obj[0].hdr_size = n;
	obj[0].type = type;
	obj[0].real_type = type;
	obj[1].idx.offset = obj[0].idx.offset + n;
	obj[1].idx.offset += write_compressed(f, buf, size);
	obj[0].idx.crc32 = crc32_end(f);
	hashflush(f);
	hashcpy(obj->idx.oid.hash, sha1);
	return obj;
}

static int delta_pos_compare(const void *_a, const void *_b)
{
	struct ref_delta_entry *a = *(struct ref_delta_entry **)_a;
	struct ref_delta_entry *b = *(struct ref_delta_entry **)_b;
	return a->obj_no - b->obj_no;
}

static void fix_unresolved_deltas(struct hashfile *f)
{
	struct ref_delta_entry **sorted_by_pos;
	int i;

	/*
	 * Since many unresolved deltas may well be themselves base objects
	 * for more unresolved deltas, we really want to include the
	 * smallest number of base objects that would cover as much delta
	 * as possible by picking the
	 * trunc deltas first, allowing for other deltas to resolve without
	 * additional base objects.  Since most base objects are to be found
	 * before deltas depending on them, a good heuristic is to start
	 * resolving deltas in the same order as their position in the pack.
	 */
	ALLOC_ARRAY(sorted_by_pos, nr_ref_deltas);
	for (i = 0; i < nr_ref_deltas; i++)
		sorted_by_pos[i] = &ref_deltas[i];
	QSORT(sorted_by_pos, nr_ref_deltas, delta_pos_compare);

	if (has_promisor_remote()) {
		/*
		 * Prefetch the delta bases.
		 */
		struct oid_array to_fetch = OID_ARRAY_INIT;
		for (i = 0; i < nr_ref_deltas; i++) {
			struct ref_delta_entry *d = sorted_by_pos[i];
			if (!oid_object_info_extended(the_repository, &d->oid,
						      NULL,
						      OBJECT_INFO_FOR_PREFETCH))
				continue;
			oid_array_append(&to_fetch, &d->oid);
		}
		if (to_fetch.nr)
			promisor_remote_get_direct(the_repository,
						   to_fetch.oid, to_fetch.nr);
		oid_array_clear(&to_fetch);
	}

	for (i = 0; i < nr_ref_deltas; i++) {
		struct ref_delta_entry *d = sorted_by_pos[i];
		enum object_type type;
		struct base_data *base_obj = alloc_base_data();

		if (objects[d->obj_no].real_type != OBJ_REF_DELTA)
			continue;
		base_obj->data = read_object_file(&d->oid, &type,
						  &base_obj->size);
		if (!base_obj->data)
			continue;

		if (check_object_signature(&d->oid, base_obj->data,
				base_obj->size, type_name(type)))
			die(_("local object %s is corrupt"), oid_to_hex(&d->oid));
		base_obj->obj = append_obj_to_pack(f, d->oid.hash,
					base_obj->data, base_obj->size, type);
		find_unresolved_deltas(base_obj);
		display_progress(progress, nr_resolved_deltas);
	}
	free(sorted_by_pos);
}

static const char *derive_filename(const char *pack_name, const char *suffix,
				   struct strbuf *buf)
{
	size_t len;
	if (!strip_suffix(pack_name, ".pack", &len))
		die(_("packfile name '%s' does not end with '.pack'"),
		    pack_name);
	strbuf_add(buf, pack_name, len);
	strbuf_addch(buf, '.');
	strbuf_addstr(buf, suffix);
	return buf->buf;
}

static void write_special_file(const char *suffix, const char *msg,
			       const char *pack_name, const unsigned char *hash,
			       const char **report)
{
	struct strbuf name_buf = STRBUF_INIT;
	const char *filename;
	int fd;
	int msg_len = strlen(msg);

	if (pack_name)
		filename = derive_filename(pack_name, suffix, &name_buf);
	else
		filename = odb_pack_name(&name_buf, hash, suffix);

	fd = odb_pack_keep(filename);
	if (fd < 0) {
		if (errno != EEXIST)
			die_errno(_("cannot write %s file '%s'"),
				  suffix, filename);
	} else {
		if (msg_len > 0) {
			write_or_die(fd, msg, msg_len);
			write_or_die(fd, "\n", 1);
		}
		if (close(fd) != 0)
			die_errno(_("cannot close written %s file '%s'"),
				  suffix, filename);
		if (report)
			*report = suffix;
	}
	strbuf_release(&name_buf);
}

static void final(const char *final_pack_name, const char *curr_pack_name,
		  const char *final_index_name, const char *curr_index_name,
		  const char *keep_msg, const char *promisor_msg,
		  unsigned char *hash)
{
	const char *report = "pack";
	struct strbuf pack_name = STRBUF_INIT;
	struct strbuf index_name = STRBUF_INIT;
	int err;

	if (!from_stdin) {
		close(input_fd);
	} else {
		fsync_or_die(output_fd, curr_pack_name);
		err = close(output_fd);
		if (err)
			die_errno(_("error while closing pack file"));
	}

	if (keep_msg)
		write_special_file("keep", keep_msg, final_pack_name, hash,
				   &report);
	if (promisor_msg)
		write_special_file("promisor", promisor_msg, final_pack_name,
				   hash, NULL);

	if (final_pack_name != curr_pack_name) {
		if (!final_pack_name)
			final_pack_name = odb_pack_name(&pack_name, hash, "pack");
		if (finalize_object_file(curr_pack_name, final_pack_name))
			die(_("cannot store pack file"));
	} else if (from_stdin)
		chmod(final_pack_name, 0444);

	if (final_index_name != curr_index_name) {
		if (!final_index_name)
			final_index_name = odb_pack_name(&index_name, hash, "idx");
		if (finalize_object_file(curr_index_name, final_index_name))
			die(_("cannot store index file"));
	} else
		chmod(final_index_name, 0444);

	if (do_fsck_object) {
		struct packed_git *p;
		p = add_packed_git(final_index_name, strlen(final_index_name), 0);
		if (p)
			install_packed_git(the_repository, p);
	}

	if (!from_stdin) {
		printf("%s\n", hash_to_hex(hash));
	} else {
		struct strbuf buf = STRBUF_INIT;

		strbuf_addf(&buf, "%s\t%s\n", report, hash_to_hex(hash));
		write_or_die(1, buf.buf, buf.len);
		strbuf_release(&buf);

		/*
		 * Let's just mimic git-unpack-objects here and write
		 * the last part of the input buffer to stdout.
		 */
		while (input_len) {
			err = xwrite(1, input_buffer + input_offset, input_len);
			if (err <= 0)
				break;
			input_len -= err;
			input_offset += err;
		}
	}

	strbuf_release(&index_name);
	strbuf_release(&pack_name);
}

static int git_index_pack_config(const char *k, const char *v, void *cb)
{
	struct pack_idx_option *opts = cb;

	if (!strcmp(k, "pack.indexversion")) {
		opts->version = git_config_int(k, v);
		if (opts->version > 2)
			die(_("bad pack.indexversion=%"PRIu32), opts->version);
		return 0;
	}
	if (!strcmp(k, "pack.threads")) {
		nr_threads = git_config_int(k, v);
		if (nr_threads < 0)
			die(_("invalid number of threads specified (%d)"),
			    nr_threads);
		if (!HAVE_THREADS && nr_threads != 1) {
			warning(_("no threads support, ignoring %s"), k);
			nr_threads = 1;
		}
		return 0;
	}
	return git_default_config(k, v, cb);
}

static int cmp_uint32(const void *a_, const void *b_)
{
	uint32_t a = *((uint32_t *)a_);
	uint32_t b = *((uint32_t *)b_);

	return (a < b) ? -1 : (a != b);
}

static void read_v2_anomalous_offsets(struct packed_git *p,
				      struct pack_idx_option *opts)
{
	const uint32_t *idx1, *idx2;
	uint32_t i;
	const uint32_t hashwords = the_hash_algo->rawsz / sizeof(uint32_t);

	/* The address of the 4-byte offset table */
	idx1 = (((const uint32_t *)p->index_data)
		+ 2 /* 8-byte header */
		+ 256 /* fan out */
		+ hashwords * p->num_objects /* object ID table */
		+ p->num_objects /* CRC32 table */
		);

	/* The address of the 8-byte offset table */
	idx2 = idx1 + p->num_objects;

	for (i = 0; i < p->num_objects; i++) {
		uint32_t off = ntohl(idx1[i]);
		if (!(off & 0x80000000))
			continue;
		off = off & 0x7fffffff;
		check_pack_index_ptr(p, &idx2[off * 2]);
		if (idx2[off * 2])
			continue;
		/*
		 * The real offset is ntohl(idx2[off * 2]) in high 4
		 * octets, and ntohl(idx2[off * 2 + 1]) in low 4
		 * octets.  But idx2[off * 2] is Zero!!!
		 */
		ALLOC_GROW(opts->anomaly, opts->anomaly_nr + 1, opts->anomaly_alloc);
		opts->anomaly[opts->anomaly_nr++] = ntohl(idx2[off * 2 + 1]);
	}

	QSORT(opts->anomaly, opts->anomaly_nr, cmp_uint32);
}

static void read_idx_option(struct pack_idx_option *opts, const char *pack_name)
{
	struct packed_git *p = add_packed_git(pack_name, strlen(pack_name), 1);

	if (!p)
		die(_("Cannot open existing pack file '%s'"), pack_name);
	if (open_pack_index(p))
		die(_("Cannot open existing pack idx file for '%s'"), pack_name);

	/* Read the attributes from the existing idx file */
	opts->version = p->index_version;

	if (opts->version == 2)
		read_v2_anomalous_offsets(p, opts);

	/*
	 * Get rid of the idx file as we do not need it anymore.
	 * NEEDSWORK: extract this bit from free_pack_by_name() in
	 * sha1-file.c, perhaps?  It shouldn't matter very much as we
	 * know we haven't installed this pack (hence we never have
	 * read anything from it).
	 */
	close_pack_index(p);
	free(p);
}

static void show_pack_info(int stat_only)
{
	int i, baseobjects = nr_objects - nr_ref_deltas - nr_ofs_deltas;
	unsigned long *chain_histogram = NULL;

	if (deepest_delta)
		chain_histogram = xcalloc(deepest_delta, sizeof(unsigned long));

	for (i = 0; i < nr_objects; i++) {
		struct object_entry *obj = &objects[i];

		if (is_delta_type(obj->type))
			chain_histogram[obj_stat[i].delta_depth - 1]++;
		if (stat_only)
			continue;
		printf("%s %-6s %"PRIuMAX" %"PRIuMAX" %"PRIuMAX,
		       oid_to_hex(&obj->idx.oid),
		       type_name(obj->real_type), (uintmax_t)obj->size,
		       (uintmax_t)(obj[1].idx.offset - obj->idx.offset),
		       (uintmax_t)obj->idx.offset);
		if (is_delta_type(obj->type)) {
			struct object_entry *bobj = &objects[obj_stat[i].base_object_no];
			printf(" %u %s", obj_stat[i].delta_depth,
			       oid_to_hex(&bobj->idx.oid));
		}
		putchar('\n');
	}

	if (baseobjects)
		printf_ln(Q_("non delta: %d object",
			     "non delta: %d objects",
			     baseobjects),
			  baseobjects);
	for (i = 0; i < deepest_delta; i++) {
		if (!chain_histogram[i])
			continue;
		printf_ln(Q_("chain length = %d: %lu object",
			     "chain length = %d: %lu objects",
			     chain_histogram[i]),
			  i + 1,
			  chain_histogram[i]);
	}
}

int cmd_index_pack(int argc, const char **argv, const char *prefix)
{
	int i, fix_thin_pack = 0, verify = 0, stat_only = 0;
	const char *curr_index;
	const char *index_name = NULL, *pack_name = NULL;
	const char *keep_msg = NULL;
	const char *promisor_msg = NULL;
	struct strbuf index_name_buf = STRBUF_INIT;
	struct pack_idx_entry **idx_objects;
	struct pack_idx_option opts;
	unsigned char pack_hash[GIT_MAX_RAWSZ];
	unsigned foreign_nr = 1;	/* zero is a "good" value, assume bad */
	int report_end_of_input = 0;

	/*
	 * index-pack never needs to fetch missing objects except when
	 * REF_DELTA bases are missing (which are explicitly handled). It only
	 * accesses the repo to do hash collision checks and to check which
	 * REF_DELTA bases need to be fetched.
	 */
	fetch_if_missing = 0;

	if (argc == 2 && !strcmp(argv[1], "-h"))
		usage(index_pack_usage);

	read_replace_refs = 0;
	fsck_options.walk = mark_link;

	reset_pack_idx_option(&opts);
	git_config(git_index_pack_config, &opts);
	if (prefix && chdir(prefix))
		die(_("Cannot come back to cwd"));

	for (i = 1; i < argc; i++) {
		const char *arg = argv[i];

		if (*arg == '-') {
			if (!strcmp(arg, "--stdin")) {
				from_stdin = 1;
			} else if (!strcmp(arg, "--fix-thin")) {
				fix_thin_pack = 1;
			} else if (skip_to_optional_arg(arg, "--strict", &arg)) {
				strict = 1;
				do_fsck_object = 1;
				fsck_set_msg_types(&fsck_options, arg);
			} else if (!strcmp(arg, "--check-self-contained-and-connected")) {
				strict = 1;
				check_self_contained_and_connected = 1;
			} else if (!strcmp(arg, "--fsck-objects")) {
				do_fsck_object = 1;
			} else if (!strcmp(arg, "--verify")) {
				verify = 1;
			} else if (!strcmp(arg, "--verify-stat")) {
				verify = 1;
				show_stat = 1;
			} else if (!strcmp(arg, "--verify-stat-only")) {
				verify = 1;
				show_stat = 1;
				stat_only = 1;
			} else if (skip_to_optional_arg(arg, "--keep", &keep_msg)) {
				; /* nothing to do */
			} else if (skip_to_optional_arg(arg, "--promisor", &promisor_msg)) {
				; /* already parsed */
			} else if (starts_with(arg, "--threads=")) {
				char *end;
				nr_threads = strtoul(arg+10, &end, 0);
				if (!arg[10] || *end || nr_threads < 0)
					usage(index_pack_usage);
				if (!HAVE_THREADS && nr_threads != 1) {
					warning(_("no threads support, ignoring %s"), arg);
					nr_threads = 1;
				}
			} else if (starts_with(arg, "--pack_header=")) {
				struct pack_header *hdr;
				char *c;

				hdr = (struct pack_header *)input_buffer;
				hdr->hdr_signature = htonl(PACK_SIGNATURE);
				hdr->hdr_version = htonl(strtoul(arg + 14, &c, 10));
				if (*c != ',')
					die(_("bad %s"), arg);
				hdr->hdr_entries = htonl(strtoul(c + 1, &c, 10));
				if (*c)
					die(_("bad %s"), arg);
				input_len = sizeof(*hdr);
			} else if (!strcmp(arg, "-v")) {
				verbose = 1;
			} else if (!strcmp(arg, "--show-resolving-progress")) {
				show_resolving_progress = 1;
			} else if (!strcmp(arg, "--report-end-of-input")) {
				report_end_of_input = 1;
			} else if (!strcmp(arg, "-o")) {
				if (index_name || (i+1) >= argc)
					usage(index_pack_usage);
				index_name = argv[++i];
			} else if (starts_with(arg, "--index-version=")) {
				char *c;
				opts.version = strtoul(arg + 16, &c, 10);
				if (opts.version > 2)
					die(_("bad %s"), arg);
				if (*c == ',')
					opts.off32_limit = strtoul(c+1, &c, 0);
				if (*c || opts.off32_limit & 0x80000000)
					die(_("bad %s"), arg);
			} else if (skip_prefix(arg, "--max-input-size=", &arg)) {
				max_input_size = strtoumax(arg, NULL, 10);
			} else
				usage(index_pack_usage);
			continue;
		}

		if (pack_name)
			usage(index_pack_usage);
		pack_name = arg;
	}

	if (!pack_name && !from_stdin)
		usage(index_pack_usage);
	if (fix_thin_pack && !from_stdin)
		die(_("--fix-thin cannot be used without --stdin"));
	if (from_stdin && !startup_info->have_repository)
		die(_("--stdin requires a git repository"));
	if (!index_name && pack_name)
		index_name = derive_filename(pack_name, "idx", &index_name_buf);

	if (verify) {
		if (!index_name)
			die(_("--verify with no packfile name given"));
		read_idx_option(&opts, index_name);
		opts.flags |= WRITE_IDX_VERIFY | WRITE_IDX_STRICT;
	}
	if (strict)
		opts.flags |= WRITE_IDX_STRICT;

	if (HAVE_THREADS && !nr_threads) {
		nr_threads = online_cpus();
		/* An experiment showed that more threads does not mean faster */
		if (nr_threads > 3)
			nr_threads = 3;
	}

	curr_pack = open_pack_file(pack_name);
	parse_pack_header();
	objects = xcalloc(st_add(nr_objects, 1), sizeof(struct object_entry));
	if (show_stat)
		obj_stat = xcalloc(st_add(nr_objects, 1), sizeof(struct object_stat));
	ofs_deltas = xcalloc(nr_objects, sizeof(struct ofs_delta_entry));
	parse_pack_objects(pack_hash);
	if (report_end_of_input)
		write_in_full(2, "\0", 1);
	resolve_deltas();
	conclude_pack(fix_thin_pack, curr_pack, pack_hash);
	free(ofs_deltas);
	free(ref_deltas);
	if (strict)
		foreign_nr = check_objects();

	if (show_stat)
		show_pack_info(stat_only);

	ALLOC_ARRAY(idx_objects, nr_objects);
	for (i = 0; i < nr_objects; i++)
		idx_objects[i] = &objects[i].idx;
	curr_index = write_idx_file(index_name, idx_objects, nr_objects, &opts, pack_hash);
	free(idx_objects);

	if (!verify)
		final(pack_name, curr_pack,
		      index_name, curr_index,
		      keep_msg, promisor_msg,
		      pack_hash);
	else
		close(input_fd);

	if (do_fsck_object && fsck_finish(&fsck_options))
		die(_("fsck error in pack objects"));

	free(objects);
	strbuf_release(&index_name_buf);
	if (pack_name == NULL)
		free((void *) curr_pack);
	if (index_name == NULL)
		free((void *) curr_index);

	/*
	 * Let the caller know this pack is not self contained
	 */
	if (check_self_contained_and_connected && foreign_nr)
		return 1;

	return 0;
}
debug log:

solving 220e1e3693 ...
found 220e1e3693 in https://public-inbox.org/git/3359b66b841e7eabdc45d3d937e97208b22e2901.1571343096.git.jonathantanmy@google.com/
found 296804230c in https://public-inbox.org/git/f01f069a080d705ddb52e2353fa303b979a3cb78.1571343096.git.jonathantanmy@google.com/
found df6b3b8cf6 in https://public-inbox.org/git/b19d6131e01692e47eafd58bb5a9b0cd2a8c88ee.1571343096.git.jonathantanmy@google.com/
found 60a5591039 in https://80x24.org/mirrors/git.git
preparing index
index prepared:
100644 60a5591039abbdb9e0050bfda53123c577b41864	builtin/index-pack.c

applying [1/3] https://public-inbox.org/git/b19d6131e01692e47eafd58bb5a9b0cd2a8c88ee.1571343096.git.jonathantanmy@google.com/
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 60a5591039..df6b3b8cf6 100644


applying [2/3] https://public-inbox.org/git/f01f069a080d705ddb52e2353fa303b979a3cb78.1571343096.git.jonathantanmy@google.com/
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index df6b3b8cf6..296804230c 100644


applying [3/3] https://public-inbox.org/git/3359b66b841e7eabdc45d3d937e97208b22e2901.1571343096.git.jonathantanmy@google.com/
diff --git a/builtin/index-pack.c b/builtin/index-pack.c
index 296804230c..220e1e3693 100644

Checking patch builtin/index-pack.c...
Applied patch builtin/index-pack.c cleanly.
Checking patch builtin/index-pack.c...
Applied patch builtin/index-pack.c cleanly.
Checking patch builtin/index-pack.c...
Applied patch builtin/index-pack.c cleanly.

index at:
100644 220e1e3693f0b16bf3d83d72503ad0ce535a31c8	builtin/index-pack.c

git@vger.kernel.org list mirror (unofficial, one of many)

Archives are clonable:
	git clone --mirror https://public-inbox.org/git
	git clone --mirror http://ou63pmih66umazou.onion/git
	git clone --mirror http://czquwvybam4bgbro.onion/git
	git clone --mirror http://hjrcffqmbrq6wope.onion/git

Example config snippet for mirrors

Newsgroups are available over NNTP:
	nntp://news.public-inbox.org/inbox.comp.version-control.git
	nntp://ou63pmih66umazou.onion/inbox.comp.version-control.git
	nntp://czquwvybam4bgbro.onion/inbox.comp.version-control.git
	nntp://hjrcffqmbrq6wope.onion/inbox.comp.version-control.git
	nntp://news.gmane.org/gmane.comp.version-control.git

 note: .onion URLs require Tor: https://www.torproject.org/

AGPL code for this site: git clone https://public-inbox.org/public-inbox.git