summaryrefslogtreecommitdiff
path: root/read-cache.c
blob: 1df6adf0bf786d7428d42973b3e7bc41870ff702 (plain)
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
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#define NO_THE_INDEX_COMPATIBILITY_MACROS
#include "cache.h"
#include "cache-tree.h"
#include "refs.h"
#include "dir.h"
#include "tree.h"
#include "commit.h"
#include "blob.h"
#include "resolve-undo.h"
#include "strbuf.h"
#include "varint.h"

static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really);

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

#define CACHE_EXT(s) ( (s[0]<<24)|(s[1]<<16)|(s[2]<<8)|(s[3]) )
#define CACHE_EXT_TREE 0x54524545	/* "TREE" */
#define CACHE_EXT_RESOLVE_UNDO 0x52455543 /* "REUC" */

struct index_state the_index;

static void set_index_entry(struct index_state *istate, int nr, struct cache_entry *ce)
{
	istate->cache[nr] = ce;
	add_name_hash(istate, ce);
}

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

	remove_name_hash(old);
	set_index_entry(istate, nr, ce);
	istate->cache_changed = 1;
}

void rename_index_entry_at(struct index_state *istate, int nr, const char *new_name)
{
	struct cache_entry *old = istate->cache[nr], *new;
	int namelen = strlen(new_name);

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

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

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

	if (assume_unchanged)
		ce->ce_flags |= CE_VALID;

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

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

	if (fd >= 0) {
		unsigned char sha1[20];
		if (!index_fd(sha1, fd, st, OBJ_BLOB, ce->name, 0))
			match = hashcmp(sha1, ce->sha1);
		/* index_fd() closed the file descriptor already */
	}
	return match;
}

static int ce_compare_link(struct cache_entry *ce, size_t expected_size)
{
	int match = -1;
	void *buffer;
	unsigned long size;
	enum object_type type;
	struct strbuf sb = STRBUF_INIT;

	if (strbuf_readlink(&sb, ce->name, expected_size))
		return -1;

	buffer = read_sha1_file(ce->sha1, &type, &size);
	if (buffer) {
		if (size == sb.len)
			match = memcmp(buffer, sb.buf, size);
		free(buffer);
	}
	strbuf_release(&sb);
	return match;
}

static int ce_compare_gitlink(struct cache_entry *ce)
{
	unsigned char sha1[20];

	/*
	 * We don't actually require that the .git directory
	 * under GITLINK directory be a valid git directory. It
	 * might even be missing (in case nobody populated that
	 * sub-project).
	 *
	 * If so, we consider it always to match.
	 */
	if (resolve_gitlink_ref(ce->name, "HEAD", sha1) < 0)
		return 0;
	return hashcmp(sha1, ce->sha1);
}

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

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

	if (ce->ce_flags & CE_REMOVE)
		return MODE_CHANGED | DATA_CHANGED | TYPE_CHANGED;

	switch (ce->ce_mode & S_IFMT) {
	case S_IFREG:
		changed |= !S_ISREG(st->st_mode) ? TYPE_CHANGED : 0;
		/* We consider only the owner x bit to be relevant for
		 * "mode changes"
		 */
		if (trust_executable_bit &&
		    (0100 & (ce->ce_mode ^ st->st_mode)))
			changed |= MODE_CHANGED;
		break;
	case S_IFLNK:
		if (!S_ISLNK(st->st_mode) &&
		    (has_symlinks || !S_ISREG(st->st_mode)))
			changed |= TYPE_CHANGED;
		break;
	case S_IFGITLINK:
		/* We ignore most of the st_xxx fields for gitlinks */
		if (!S_ISDIR(st->st_mode))
			changed |= TYPE_CHANGED;
		else if (ce_compare_gitlink(ce))
			changed |= DATA_CHANGED;
		return changed;
	default:
		die("internal error: ce_mode is %o", ce->ce_mode);
	}
	if (ce->ce_mtime.sec != (unsigned int)st->st_mtime)
		changed |= MTIME_CHANGED;
	if (trust_ctime && ce->ce_ctime.sec != (unsigned int)st->st_ctime)
		changed |= CTIME_CHANGED;

#ifdef USE_NSEC
	if (ce->ce_mtime.nsec != ST_MTIME_NSEC(*st))
		changed |= MTIME_CHANGED;
	if (trust_ctime && ce->ce_ctime.nsec != ST_CTIME_NSEC(*st))
		changed |= CTIME_CHANGED;
#endif

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

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

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

	/* Racily smudged entry? */
	if (!ce->ce_size) {
		if (!is_empty_blob_sha1(ce->sha1))
			changed |= DATA_CHANGED;
	}

	return changed;
}

static int is_racy_timestamp(const struct index_state *istate, struct cache_entry *ce)
{
	return (!S_ISGITLINK(ce->ce_mode) &&
		istate->timestamp.sec &&
#ifdef USE_NSEC
		 /* nanosecond timestamped files can also be racy! */
		(istate->timestamp.sec < ce->ce_mtime.sec ||
		 (istate->timestamp.sec == ce->ce_mtime.sec &&
		  istate->timestamp.nsec <= ce->ce_mtime.nsec))
#else
		istate->timestamp.sec <= ce->ce_mtime.sec
#endif
		 );
}

int ie_match_stat(const struct index_state *istate,
		  struct cache_entry *ce, struct stat *st,
		  unsigned int options)
{
	unsigned int changed;
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
	int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;
	int assume_racy_is_modified = options & CE_MATCH_RACY_IS_DIRTY;

	/*
	 * If it's marked as always valid in the index, it's
	 * valid whatever the checked-out copy says.
	 *
	 * skip-worktree has the same effect with higher precedence
	 */
	if (!ignore_skip_worktree && ce_skip_worktree(ce))
		return 0;
	if (!ignore_valid && (ce->ce_flags & CE_VALID))
		return 0;

	/*
	 * Intent-to-add entries have not been added, so the index entry
	 * by definition never matches what is in the work tree until it
	 * actually gets added.
	 */
	if (ce->ce_flags & CE_INTENT_TO_ADD)
		return DATA_CHANGED | TYPE_CHANGED | MODE_CHANGED;

	changed = ce_match_stat_basic(ce, st);

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

	return changed;
}

int ie_modified(const struct index_state *istate,
		struct cache_entry *ce, struct stat *st, unsigned int options)
{
	int changed, changed_fs;

	changed = ie_match_stat(istate, ce, st, options);
	if (!changed)
		return 0;
	/*
	 * If the mode or type has changed, there's no point in trying
	 * to refresh the entry - it's not going to match
	 */
	if (changed & (MODE_CHANGED | TYPE_CHANGED))
		return changed;

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

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

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

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

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

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

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

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

	/* Compare stages  */
	flags1 &= CE_STAGEMASK;
	flags2 &= CE_STAGEMASK;

	if (flags1 < flags2)
		return -1;
	if (flags1 > flags2)
		return 1;
	return 0;
}

int index_name_pos(const struct index_state *istate, const char *name, int namelen)
{
	int first, last;

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

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

	record_resolve_undo(istate, ce);
	remove_name_hash(ce);
	istate->cache_changed = 1;
	istate->cache_nr--;
	if (pos >= istate->cache_nr)
		return 0;
	memmove(istate->cache + pos,
		istate->cache + pos + 1,
		(istate->cache_nr - pos) * sizeof(struct cache_entry *));
	return 1;
}

/*
 * Remove all cache ententries marked for removal, that is where
 * CE_REMOVE is set in ce_flags.  This is much more effective than
 * calling remove_index_entry_at() for each entry to be removed.
 */
void remove_marked_cache_entries(struct index_state *istate)
{
	struct cache_entry **ce_array = istate->cache;
	unsigned int i, j;

	for (i = j = 0; i < istate->cache_nr; i++) {
		if (ce_array[i]->ce_flags & CE_REMOVE)
			remove_name_hash(ce_array[i]);
		else
			ce_array[j++] = ce_array[i];
	}
	istate->cache_changed = 1;
	istate->cache_nr = j;
}

int remove_file_from_index(struct index_state *istate, const char *path)
{
	int pos = index_name_pos(istate, path, strlen(path));
	if (pos < 0)
		pos = -pos-1;
	cache_tree_invalidate_path(istate->cache_tree, path);
	while (pos < istate->cache_nr && !strcmp(istate->cache[pos]->name, path))
		remove_index_entry_at(istate, pos);
	return 0;
}

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

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

	if (pos >= 0)
		return pos;

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

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

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

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

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

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

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

int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
{
	int size, namelen, was_same;
	mode_t st_mode = st->st_mode;
	struct cache_entry *ce, *alias;
	unsigned ce_option = CE_MATCH_IGNORE_VALID|CE_MATCH_IGNORE_SKIP_WORKTREE|CE_MATCH_RACY_IS_DIRTY;
	int verbose = flags & (ADD_CACHE_VERBOSE | ADD_CACHE_PRETEND);
	int pretend = flags & ADD_CACHE_PRETEND;
	int intent_only = flags & ADD_CACHE_INTENT;
	int add_option = (ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE|
			  (intent_only ? ADD_CACHE_NEW_ONLY : 0));

	if (!S_ISREG(st_mode) && !S_ISLNK(st_mode) && !S_ISDIR(st_mode))
		return error("%s: can only add regular files, symbolic links or git-directories", path);

	namelen = strlen(path);
	if (S_ISDIR(st_mode)) {
		while (namelen && path[namelen-1] == '/')
			namelen--;
	}
	size = cache_entry_size(namelen);
	ce = xcalloc(1, size);
	memcpy(ce->name, path, namelen);
	ce->ce_flags = namelen;
	if (!intent_only)
		fill_stat_cache_info(ce, st);
	else
		ce->ce_flags |= CE_INTENT_TO_ADD;

	if (trust_executable_bit && has_symlinks)
		ce->ce_mode = create_ce_mode(st_mode);
	else {
		/* If there is an existing entry, pick the mode bits and type
		 * from it, otherwise assume unexecutable regular file.
		 */
		struct cache_entry *ent;
		int pos = index_name_pos_also_unmerged(istate, path, namelen);

		ent = (0 <= pos) ? istate->cache[pos] : NULL;
		ce->ce_mode = ce_mode_from_stat(ent, st_mode);
	}

	/* When core.ignorecase=true, determine if a directory of the same name but differing
	 * case already exists within the Git repository.  If it does, ensure the directory
	 * case of the file being added to the repository matches (is folded into) the existing
	 * entry's directory case.
	 */
	if (ignore_case) {
		const char *startPtr = ce->name;
		const char *ptr = startPtr;
		while (*ptr) {
			while (*ptr && *ptr != '/')
				++ptr;
			if (*ptr == '/') {
				struct cache_entry *foundce;
				++ptr;
				foundce = index_name_exists(&the_index, ce->name, ptr - ce->name, ignore_case);
				if (foundce) {
					memcpy((void *)startPtr, foundce->name + (startPtr - ce->name), ptr - startPtr);
					startPtr = ptr;
				}
			}
		}
	}

	alias = index_name_exists(istate, ce->name, ce_namelen(ce), ignore_case);
	if (alias && !ce_stage(alias) && !ie_match_stat(istate, alias, st, ce_option)) {
		/* Nothing changed, really */
		free(ce);
		if (!S_ISGITLINK(alias->ce_mode))
			ce_mark_uptodate(alias);
		alias->ce_flags |= CE_ADDED;
		return 0;
	}
	if (!intent_only) {
		if (index_path(ce->sha1, path, st, HASH_WRITE_OBJECT))
			return error("unable to index file %s", path);
	} else
		record_intent_to_add(ce);

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

	/* It was suspected to be racily clean, but it turns out to be Ok */
	was_same = (alias &&
		    !ce_stage(alias) &&
		    !hashcmp(alias->sha1, ce->sha1) &&
		    ce->ce_mode == alias->ce_mode);

	if (pretend)
		;
	else if (add_index_entry(istate, ce, add_option))
		return error("unable to add %s to index",path);
	if (verbose && !was_same)
		printf("add '%s'\n", path);
	return 0;
}

int add_file_to_index(struct index_state *istate, const char *path, int flags)
{
	struct stat st;
	if (lstat(path, &st))
		die_errno("unable to stat '%s'", path);
	return add_to_index(istate, path, &st, flags);
}

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

	if (!verify_path(path)) {
		error("Invalid path '%s'", path);
		return NULL;
	}

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

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

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

	return ce;
}

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

int ce_path_match(const struct cache_entry *ce, const struct pathspec *pathspec)
{
	return match_pathspec_depth(pathspec, ce->name, ce_namelen(ce), 0, NULL);
}

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

	/* "." is not allowed */
	if (*rest == '\0' || is_dir_sep(*rest))
		return 0;

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

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

	if (has_dos_drive_prefix(path))
		return 0;

	goto inside;
	for (;;) {
		if (!c)
			return 1;
		if (is_dir_sep(c)) {
inside:
			c = *path++;
			if ((c == '.' && !verify_dotfile(path)) ||
			    is_dir_sep(c) || c == '\0')
				return 0;
		}
		c = *path++;
	}
}

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

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

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

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

	for (;;) {
		int len;

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

		pos = index_name_pos(istate, name, create_ce_flags(len, stage));
		if (pos >= 0) {
			/*
			 * Found one, but not so fast.  This could
			 * be a marker that says "I was here, but
			 * I am being removed".  Such an entry is
			 * not a part of the resulting tree, and
			 * it is Ok to have a directory at the same
			 * path.
			 */
			if (!(istate->cache[pos]->ce_flags & CE_REMOVE)) {
				retval = -1;
				if (!ok_to_replace)
					break;
				remove_index_entry_at(istate, pos);
				continue;
			}
		}
		else
			pos = -pos-1;

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

/* We may be in a situation where we already have path/file and path
 * is being added, or we already have path and path/file is being
 * added.  Either one would result in a nonsense tree that has path
 * twice when git-write-tree tries to write it out.  Prevent it.
 *
 * If ok-to-replace is specified, we remove the conflicting entries
 * from the cache so the caller should recompute the insert position.
 * When this happens, we return non-zero.
 */
static int check_file_directory_conflict(struct index_state *istate,
					 const struct cache_entry *ce,
					 int pos, int ok_to_replace)
{
	int retval;

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

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

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

static int add_index_entry_with_check(struct index_state *istate, struct cache_entry *ce, int option)
{
	int pos;
	int ok_to_add = option & ADD_CACHE_OK_TO_ADD;
	int ok_to_replace = option & ADD_CACHE_OK_TO_REPLACE;
	int skip_df_check = option & ADD_CACHE_SKIP_DFCHECK;
	int new_only = option & ADD_CACHE_NEW_ONLY;

	cache_tree_invalidate_path(istate->cache_tree, ce->name);
	pos = index_name_pos(istate, ce->name, ce->ce_flags);

	/* existing match? Just replace it. */
	if (pos >= 0) {
		if (!new_only)
			replace_index_entry(istate, pos, ce);
		return 0;
	}
	pos = -pos-1;

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

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

	if (!skip_df_check &&
	    check_file_directory_conflict(istate, ce, pos, ok_to_replace)) {
		if (!ok_to_replace)
			return error("'%s' appears as both a file and as a directory",
				     ce->name);
		pos = index_name_pos(istate, ce->name, ce->ce_flags);
		pos = -pos-1;
	}
	return pos + 1;
}

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

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

	/* Make sure the array is big enough .. */
	if (istate->cache_nr == istate->cache_alloc) {
		istate->cache_alloc = alloc_nr(istate->cache_alloc);
		istate->cache = xrealloc(istate->cache,
					istate->cache_alloc * sizeof(struct cache_entry *));
	}

	/* Add it in.. */
	istate->cache_nr++;
	if (istate->cache_nr > pos + 1)
		memmove(istate->cache + pos + 1,
			istate->cache + pos,
			(istate->cache_nr - pos - 1) * sizeof(ce));
	set_index_entry(istate, pos, ce);
	istate->cache_changed = 1;
	return 0;
}

/*
 * "refresh" does not calculate a new sha1 file or bring the
 * cache up-to-date for mode/content changes. But what it
 * _does_ do is to "re-match" the stat information of a file
 * with the cache, so that you can refresh the cache for a
 * file that hasn't been changed but where the stat entry is
 * out of date.
 *
 * For example, you'd want to do this after doing a "git-read-tree",
 * to link up the stat cache details with the proper files.
 */
static struct cache_entry *refresh_cache_ent(struct index_state *istate,
					     struct cache_entry *ce,
					     unsigned int options, int *err,
					     int *changed_ret)
{
	struct stat st;
	struct cache_entry *updated;
	int changed, size;
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
	int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;

	if (ce_uptodate(ce))
		return ce;

	/*
	 * CE_VALID or CE_SKIP_WORKTREE means the user promised us
	 * that the change to the work tree does not matter and told
	 * us not to worry.
	 */
	if (!ignore_skip_worktree && ce_skip_worktree(ce)) {
		ce_mark_uptodate(ce);
		return ce;
	}
	if (!ignore_valid && (ce->ce_flags & CE_VALID)) {
		ce_mark_uptodate(ce);
		return ce;
	}

	if (lstat(ce->name, &st) < 0) {
		if (err)
			*err = errno;
		return NULL;
	}

	changed = ie_match_stat(istate, ce, &st, options);
	if (changed_ret)
		*changed_ret = changed;
	if (!changed) {
		/*
		 * The path is unchanged.  If we were told to ignore
		 * valid bit, then we did the actual stat check and
		 * found that the entry is unmodified.  If the entry
		 * is not marked VALID, this is the place to mark it
		 * valid again, under "assume unchanged" mode.
		 */
		if (ignore_valid && assume_unchanged &&
		    !(ce->ce_flags & CE_VALID))
			; /* mark this one VALID again */
		else {
			/*
			 * We do not mark the index itself "modified"
			 * because CE_UPTODATE flag is in-core only;
			 * we are not going to write this change out.
			 */
			if (!S_ISGITLINK(ce->ce_mode))
				ce_mark_uptodate(ce);
			return ce;
		}
	}

	if (ie_modified(istate, ce, &st, options)) {
		if (err)
			*err = EINVAL;
		return NULL;
	}

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

	return updated;
}

static void show_file(const char * fmt, const char * name, int in_porcelain,
		      int * first, const char *header_msg)
{
	if (in_porcelain && *first && header_msg) {
		printf("%s\n", header_msg);
		*first = 0;
	}
	printf(fmt, name);
}

int refresh_index(struct index_state *istate, unsigned int flags, const char **pathspec,
		  char *seen, const char *header_msg)
{
	int i;
	int has_errors = 0;
	int really = (flags & REFRESH_REALLY) != 0;
	int allow_unmerged = (flags & REFRESH_UNMERGED) != 0;
	int quiet = (flags & REFRESH_QUIET) != 0;
	int not_new = (flags & REFRESH_IGNORE_MISSING) != 0;
	int ignore_submodules = (flags & REFRESH_IGNORE_SUBMODULES) != 0;
	int first = 1;
	int in_porcelain = (flags & REFRESH_IN_PORCELAIN);
	unsigned int options = really ? CE_MATCH_IGNORE_VALID : 0;
	const char *modified_fmt;
	const char *deleted_fmt;
	const char *typechange_fmt;
	const char *added_fmt;
	const char *unmerged_fmt;

	modified_fmt = (in_porcelain ? "M\t%s\n" : "%s: needs update\n");
	deleted_fmt = (in_porcelain ? "D\t%s\n" : "%s: needs update\n");
	typechange_fmt = (in_porcelain ? "T\t%s\n" : "%s needs update\n");
	added_fmt = (in_porcelain ? "A\t%s\n" : "%s needs update\n");
	unmerged_fmt = (in_porcelain ? "U\t%s\n" : "%s: needs merge\n");
	for (i = 0; i < istate->cache_nr; i++) {
		struct cache_entry *ce, *new;
		int cache_errno = 0;
		int changed = 0;
		int filtered = 0;

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

		if (pathspec &&
		    !match_pathspec(pathspec, ce->name, ce_namelen(ce), 0, seen))
			filtered = 1;

		if (ce_stage(ce)) {
			while ((i < istate->cache_nr) &&
			       ! strcmp(istate->cache[i]->name, ce->name))
				i++;
			i--;
			if (allow_unmerged)
				continue;
			if (!filtered)
				show_file(unmerged_fmt, ce->name, in_porcelain,
					  &first, header_msg);
			has_errors = 1;
			continue;
		}

		if (filtered)
			continue;

		new = refresh_cache_ent(istate, ce, options, &cache_errno, &changed);
		if (new == ce)
			continue;
		if (!new) {
			const char *fmt;

			if (not_new && cache_errno == ENOENT)
				continue;
			if (really && cache_errno == EINVAL) {
				/* If we are doing --really-refresh that
				 * means the index is not valid anymore.
				 */
				ce->ce_flags &= ~CE_VALID;
				istate->cache_changed = 1;
			}
			if (quiet)
				continue;

			if (cache_errno == ENOENT)
				fmt = deleted_fmt;
			else if (ce->ce_flags & CE_INTENT_TO_ADD)
				fmt = added_fmt; /* must be before other checks */
			else if (changed & TYPE_CHANGED)
				fmt = typechange_fmt;
			else
				fmt = modified_fmt;
			show_file(fmt,
				  ce->name, in_porcelain, &first, header_msg);
			has_errors = 1;
			continue;
		}

		replace_index_entry(istate, i, new);
	}
	return has_errors;
}

static struct cache_entry *refresh_cache_entry(struct cache_entry *ce, int really)
{
	return refresh_cache_ent(&the_index, ce, really, NULL, NULL);
}


/*****************************************************************
 * Index File I/O
 *****************************************************************/

#define INDEX_FORMAT_DEFAULT 3

/*
 * dev/ino/uid/gid/size are also just tracked to the low 32 bits
 * Again - this is just a (very strong in practice) heuristic that
 * the inode hasn't changed.
 *
 * We save the fields in big-endian order to allow using the
 * index file over NFS transparently.
 */
struct ondisk_cache_entry {
	struct cache_time ctime;
	struct cache_time mtime;
	unsigned int dev;
	unsigned int ino;
	unsigned int mode;
	unsigned int uid;
	unsigned int gid;
	unsigned int size;
	unsigned char sha1[20];
	unsigned short flags;
	char name[FLEX_ARRAY]; /* more */
};

/*
 * This struct is used when CE_EXTENDED bit is 1
 * The struct must match ondisk_cache_entry exactly from
 * ctime till flags
 */
struct ondisk_cache_entry_extended {
	struct cache_time ctime;
	struct cache_time mtime;
	unsigned int dev;
	unsigned int ino;
	unsigned int mode;
	unsigned int uid;
	unsigned int gid;
	unsigned int size;
	unsigned char sha1[20];
	unsigned short flags;
	unsigned short flags2;
	char name[FLEX_ARRAY]; /* more */
};

/* These are only used for v3 or lower */
#define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,name) + (len) + 8) & ~7)
#define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len)
#define ondisk_cache_entry_extended_size(len) align_flex_name(ondisk_cache_entry_extended,len)
#define ondisk_ce_size(ce) (((ce)->ce_flags & CE_EXTENDED) ? \
			    ondisk_cache_entry_extended_size(ce_namelen(ce)) : \
			    ondisk_cache_entry_size(ce_namelen(ce)))

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

	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
		return error("bad signature");
	hdr_version = ntohl(hdr->hdr_version);
	if (hdr_version < 2 || 4 < hdr_version)
		return error("bad index version %d", hdr_version);
	git_SHA1_Init(&c);
	git_SHA1_Update(&c, hdr, size - 20);
	git_SHA1_Final(sha1, &c);
	if (hashcmp(sha1, (unsigned char *)hdr + size - 20))
		return error("bad index file sha1 signature");
	return 0;
}

static int read_index_extension(struct index_state *istate,
				const char *ext, void *data, unsigned long sz)
{
	switch (CACHE_EXT(ext)) {
	case CACHE_EXT_TREE:
		istate->cache_tree = cache_tree_read(data, sz);
		break;
	case CACHE_EXT_RESOLVE_UNDO:
		istate->resolve_undo = resolve_undo_read(data, sz);
		break;
	default:
		if (*ext < 'A' || 'Z' < *ext)
			return error("index uses %.4s extension, which we do not understand",
				     ext);
		fprintf(stderr, "ignoring %.4s extension\n", ext);
		break;
	}
	return 0;
}

int read_index(struct index_state *istate)
{
	return read_index_from(istate, get_index_file());
}

#ifndef NEEDS_ALIGNED_ACCESS
#define ntoh_s(var) ntohs(var)
#define ntoh_l(var) ntohl(var)
#else
static inline uint16_t ntoh_s_force_align(void *p)
{
	uint16_t x;
	memcpy(&x, p, sizeof(x));
	return ntohs(x);
}
static inline uint32_t ntoh_l_force_align(void *p)
{
	uint32_t x;
	memcpy(&x, p, sizeof(x));
	return ntohl(x);
}
#define ntoh_s(var) ntoh_s_force_align(&(var))
#define ntoh_l(var) ntoh_l_force_align(&(var))
#endif

static struct cache_entry *cache_entry_from_ondisk(struct ondisk_cache_entry *ondisk,
						   unsigned int flags,
						   const char *name,
						   size_t len)
{
	struct cache_entry *ce = xmalloc(cache_entry_size(len));

	ce->ce_ctime.sec = ntoh_l(ondisk->ctime.sec);
	ce->ce_mtime.sec = ntoh_l(ondisk->mtime.sec);
	ce->ce_ctime.nsec = ntoh_l(ondisk->ctime.nsec);
	ce->ce_mtime.nsec = ntoh_l(ondisk->mtime.nsec);
	ce->ce_dev   = ntoh_l(ondisk->dev);
	ce->ce_ino   = ntoh_l(ondisk->ino);
	ce->ce_mode  = ntoh_l(ondisk->mode);
	ce->ce_uid   = ntoh_l(ondisk->uid);
	ce->ce_gid   = ntoh_l(ondisk->gid);
	ce->ce_size  = ntoh_l(ondisk->size);
	ce->ce_flags = flags;
	hashcpy(ce->sha1, ondisk->sha1);
	memcpy(ce->name, name, len);
	ce->name[len] = '\0';
	return ce;
}

/*
 * Adjacent cache entries tend to share the leading paths, so it makes
 * sense to only store the differences in later entries.  In the v4
 * on-disk format of the index, each on-disk cache entry stores the
 * number of bytes to be stripped from the end of the previous name,
 * and the bytes to append to the result, to come up with its name.
 */
static unsigned long expand_name_field(struct strbuf *name, const char *cp_)
{
	const unsigned char *ep, *cp = (const unsigned char *)cp_;
	size_t len = decode_varint(&cp);

	if (name->len < len)
		die("malformed name field in the index");
	strbuf_remove(name, name->len - len, len);
	for (ep = cp; *ep; ep++)
		; /* find the end */
	strbuf_add(name, cp, ep - cp);
	return (const char *)ep + 1 - cp_;
}

static struct cache_entry *create_from_disk(struct ondisk_cache_entry *ondisk,
					    unsigned long *ent_size,
					    struct strbuf *previous_name)
{
	struct cache_entry *ce;
	size_t len;
	const char *name;
	unsigned int flags;

	/* On-disk flags are just 16 bits */
	flags = ntoh_s(ondisk->flags);
	len = flags & CE_NAMEMASK;

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

	if (!previous_name) {
		/* v3 and earlier */
		if (len == CE_NAMEMASK)
			len = strlen(name);
		ce = cache_entry_from_ondisk(ondisk, flags, name, len);

		*ent_size = ondisk_ce_size(ce);
	} else {
		unsigned long consumed;
		consumed = expand_name_field(previous_name, name);
		ce = cache_entry_from_ondisk(ondisk, flags,
					     previous_name->buf,
					     previous_name->len);

		*ent_size = (name - ((char *)ondisk)) + consumed;
	}
	return ce;
}

/* remember to discard_cache() before reading a different cache! */
int read_index_from(struct index_state *istate, const char *path)
{
	int fd, i;
	struct stat st;
	unsigned long src_offset;
	struct cache_header *hdr;
	void *mmap;
	size_t mmap_size;
	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;

	errno = EBUSY;
	if (istate->initialized)
		return istate->cache_nr;

	errno = ENOENT;
	istate->timestamp.sec = 0;
	istate->timestamp.nsec = 0;
	fd = open(path, O_RDONLY);
	if (fd < 0) {
		if (errno == ENOENT)
			return 0;
		die_errno("index file open failed");
	}

	if (fstat(fd, &st))
		die_errno("cannot stat the open index");

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

	mmap = xmmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, 0);
	close(fd);
	if (mmap == MAP_FAILED)
		die_errno("unable to map index file");

	hdr = mmap;
	if (verify_hdr(hdr, mmap_size) < 0)
		goto unmap;

	istate->version = ntohl(hdr->hdr_version);
	istate->cache_nr = ntohl(hdr->hdr_entries);
	istate->cache_alloc = alloc_nr(istate->cache_nr);
	istate->cache = xcalloc(istate->cache_alloc, sizeof(struct cache_entry *));
	istate->initialized = 1;

	if (istate->version == 4)
		previous_name = &previous_name_buf;
	else
		previous_name = NULL;

	src_offset = sizeof(*hdr);
	for (i = 0; i < istate->cache_nr; i++) {
		struct ondisk_cache_entry *disk_ce;
		struct cache_entry *ce;
		unsigned long consumed;

		disk_ce = (struct ondisk_cache_entry *)((char *)mmap + src_offset);
		ce = create_from_disk(disk_ce, &consumed, previous_name);
		set_index_entry(istate, i, ce);

		src_offset += consumed;
	}
	strbuf_release(&previous_name_buf);
	istate->timestamp.sec = st.st_mtime;
	istate->timestamp.nsec = ST_MTIME_NSEC(st);

	while (src_offset <= mmap_size - 20 - 8) {
		/* After an array of active_nr index entries,
		 * there can be arbitrary number of extended
		 * sections, each of which is prefixed with
		 * extension name (4-byte) and section length
		 * in 4-byte network byte order.
		 */
		uint32_t extsize;
		memcpy(&extsize, (char *)mmap + src_offset + 4, 4);
		extsize = ntohl(extsize);
		if (read_index_extension(istate,
					 (const char *) mmap + src_offset,
					 (char *) mmap + src_offset + 8,
					 extsize) < 0)
			goto unmap;
		src_offset += 8;
		src_offset += extsize;
	}
	munmap(mmap, mmap_size);
	return istate->cache_nr;

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

int is_index_unborn(struct index_state *istate)
{
	return (!istate->cache_nr && !istate->timestamp.sec);
}

int discard_index(struct index_state *istate)
{
	int i;

	for (i = 0; i < istate->cache_nr; i++)
		free(istate->cache[i]);
	resolve_undo_clear_index(istate);
	istate->cache_nr = 0;
	istate->cache_changed = 0;
	istate->timestamp.sec = 0;
	istate->timestamp.nsec = 0;
	istate->name_hash_initialized = 0;
	free_hash(&istate->name_hash);
	cache_tree_free(&(istate->cache_tree));
	istate->initialized = 0;

	/* no need to throw away allocated active_cache */
	return 0;
}

int unmerged_index(const struct index_state *istate)
{
	int i;
	for (i = 0; i < istate->cache_nr; i++) {
		if (ce_stage(istate->cache[i]))
			return 1;
	}
	return 0;
}

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

static int ce_write_flush(git_SHA_CTX *context, int fd)
{
	unsigned int buffered = write_buffer_len;
	if (buffered) {
		git_SHA1_Update(context, write_buffer, buffered);
		if (write_in_full(fd, write_buffer, buffered) != buffered)
			return -1;
		write_buffer_len = 0;
	}
	return 0;
}

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

static int write_index_ext_header(git_SHA_CTX *context, int fd,
				  unsigned int ext, unsigned int sz)
{
	ext = htonl(ext);
	sz = htonl(sz);
	return ((ce_write(context, fd, &ext, 4) < 0) ||
		(ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0;
}

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

	if (left) {
		write_buffer_len = 0;
		git_SHA1_Update(context, write_buffer, left);
	}

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

	/* Append the SHA1 signature at the end */
	git_SHA1_Final(write_buffer + left, context);
	left += 20;
	return (write_in_full(fd, write_buffer, left) != left) ? -1 : 0;
}

static void ce_smudge_racily_clean_entry(struct cache_entry *ce)
{
	/*
	 * The only thing we care about in this function is to smudge the
	 * falsely clean entry due to touch-update-touch race, so we leave
	 * everything else as they are.  We are called for entries whose
	 * ce_mtime match the index file mtime.
	 *
	 * Note that this actually does not do much for gitlinks, for
	 * which ce_match_stat_basic() always goes to the actual
	 * contents.  The caller checks with is_racy_timestamp() which
	 * always says "no" for gitlinks, so we are not called for them ;-)
	 */
	struct stat st;

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

/* Copy miscellaneous fields but not the name */
static char *copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk,
				       struct cache_entry *ce)
{
	ondisk->ctime.sec = htonl(ce->ce_ctime.sec);
	ondisk->mtime.sec = htonl(ce->ce_mtime.sec);
	ondisk->ctime.nsec = htonl(ce->ce_ctime.nsec);
	ondisk->mtime.nsec = htonl(ce->ce_mtime.nsec);
	ondisk->dev  = htonl(ce->ce_dev);
	ondisk->ino  = htonl(ce->ce_ino);
	ondisk->mode = htonl(ce->ce_mode);
	ondisk->uid  = htonl(ce->ce_uid);
	ondisk->gid  = htonl(ce->ce_gid);
	ondisk->size = htonl(ce->ce_size);
	hashcpy(ondisk->sha1, ce->sha1);
	ondisk->flags = htons(ce->ce_flags);
	if (ce->ce_flags & CE_EXTENDED) {
		struct ondisk_cache_entry_extended *ondisk2;
		ondisk2 = (struct ondisk_cache_entry_extended *)ondisk;
		ondisk2->flags2 = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16);
		return ondisk2->name;
	}
	else {
		return ondisk->name;
	}
}

static int ce_write_entry(git_SHA_CTX *c, int fd, struct cache_entry *ce,
			  struct strbuf *previous_name)
{
	int size;
	struct ondisk_cache_entry *ondisk;
	char *name;
	int result;

	if (!previous_name) {
		size = ondisk_ce_size(ce);
		ondisk = xcalloc(1, size);
		name = copy_cache_entry_to_ondisk(ondisk, ce);
		memcpy(name, ce->name, ce_namelen(ce));
	} else {
		int common, to_remove, prefix_size;
		unsigned char to_remove_vi[16];
		for (common = 0;
		     (ce->name[common] &&
		      common < previous_name->len &&
		      ce->name[common] == previous_name->buf[common]);
		     common++)
			; /* still matching */
		to_remove = previous_name->len - common;
		prefix_size = encode_varint(to_remove, to_remove_vi);

		if (ce->ce_flags & CE_EXTENDED)
			size = offsetof(struct ondisk_cache_entry_extended, name);
		else
			size = offsetof(struct ondisk_cache_entry, name);
		size += prefix_size + (ce_namelen(ce) - common + 1);

		ondisk = xcalloc(1, size);
		name = copy_cache_entry_to_ondisk(ondisk, ce);
		memcpy(name, to_remove_vi, prefix_size);
		memcpy(name + prefix_size, ce->name + common, ce_namelen(ce) - common);

		strbuf_splice(previous_name, common, to_remove,
			      ce->name + common, ce_namelen(ce) - common);
	}

	result = ce_write(c, fd, ondisk, size);
	free(ondisk);
	return result;
}

static int has_racy_timestamp(struct index_state *istate)
{
	int entries = istate->cache_nr;
	int i;

	for (i = 0; i < entries; i++) {
		struct cache_entry *ce = istate->cache[i];
		if (is_racy_timestamp(istate, ce))
			return 1;
	}
	return 0;
}

/*
 * Opportunisticly update the index but do not complain if we can't
 */
void update_index_if_able(struct index_state *istate, struct lock_file *lockfile)
{
	if ((istate->cache_changed || has_racy_timestamp(istate)) &&
	    !write_index(istate, lockfile->fd))
		commit_locked_index(lockfile);
	else
		rollback_lock_file(lockfile);
}

int write_index(struct index_state *istate, int newfd)
{
	git_SHA_CTX c;
	struct cache_header hdr;
	int i, err, removed, extended, hdr_version;
	struct cache_entry **cache = istate->cache;
	int entries = istate->cache_nr;
	struct stat st;
	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;

	for (i = removed = extended = 0; i < entries; i++) {
		if (cache[i]->ce_flags & CE_REMOVE)
			removed++;

		/* reduce extended entries if possible */
		cache[i]->ce_flags &= ~CE_EXTENDED;
		if (cache[i]->ce_flags & CE_EXTENDED_FLAGS) {
			extended++;
			cache[i]->ce_flags |= CE_EXTENDED;
		}
	}

	if (!istate->version)
		istate->version = INDEX_FORMAT_DEFAULT;

	/* demote version 3 to version 2 when the latter suffices */
	if (istate->version == 3 || istate->version == 2)
		istate->version = extended ? 3 : 2;

	hdr_version = istate->version;

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

	git_SHA1_Init(&c);
	if (ce_write(&c, newfd, &hdr, sizeof(hdr)) < 0)
		return -1;

	previous_name = (hdr_version == 4) ? &previous_name_buf : NULL;
	for (i = 0; i < entries; i++) {
		struct cache_entry *ce = cache[i];
		if (ce->ce_flags & CE_REMOVE)
			continue;
		if (!ce_uptodate(ce) && is_racy_timestamp(istate, ce))
			ce_smudge_racily_clean_entry(ce);
		if (ce_write_entry(&c, newfd, ce, previous_name) < 0)
			return -1;
	}
	strbuf_release(&previous_name_buf);

	/* Write extension data here */
	if (istate->cache_tree) {
		struct strbuf sb = STRBUF_INIT;

		cache_tree_write(&sb, istate->cache_tree);
		err = write_index_ext_header(&c, newfd, CACHE_EXT_TREE, sb.len) < 0
			|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
		strbuf_release(&sb);
		if (err)
			return -1;
	}
	if (istate->resolve_undo) {
		struct strbuf sb = STRBUF_INIT;

		resolve_undo_write(&sb, istate->resolve_undo);
		err = write_index_ext_header(&c, newfd, CACHE_EXT_RESOLVE_UNDO,
					     sb.len) < 0
			|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
		strbuf_release(&sb);
		if (err)
			return -1;
	}

	if (ce_flush(&c, newfd) || fstat(newfd, &st))
		return -1;
	istate->timestamp.sec = (unsigned int)st.st_mtime;
	istate->timestamp.nsec = ST_MTIME_NSEC(st);
	return 0;
}

/*
 * Read the index file that is potentially unmerged into given
 * index_state, dropping any unmerged entries.  Returns true if
 * the index is unmerged.  Callers who want to refuse to work
 * from an unmerged state can call this and check its return value,
 * instead of calling read_cache().
 */
int read_index_unmerged(struct index_state *istate)
{
	int i;
	int unmerged = 0;

	read_index(istate);
	for (i = 0; i < istate->cache_nr; i++) {
		struct cache_entry *ce = istate->cache[i];
		struct cache_entry *new_ce;
		int size, len;

		if (!ce_stage(ce))
			continue;
		unmerged = 1;
		len = ce_namelen(ce);
		size = cache_entry_size(len);
		new_ce = xcalloc(1, size);
		memcpy(new_ce->name, ce->name, len);
		new_ce->ce_flags = create_ce_flags(len, 0) | CE_CONFLICTED;
		new_ce->ce_mode = ce->ce_mode;
		if (add_index_entry(istate, new_ce, 0))
			return error("%s: cannot drop to stage #0",
				     ce->name);
		i = index_name_pos(istate, new_ce->name, len);
	}
	return unmerged;
}

/*
 * Returns 1 if the path is an "other" path with respect to
 * the index; that is, the path is not mentioned in the index at all,
 * either as a file, a directory with some files in the index,
 * or as an unmerged entry.
 *
 * We helpfully remove a trailing "/" from directories so that
 * the output of read_directory can be used as-is.
 */
int index_name_is_other(const struct index_state *istate, const char *name,
		int namelen)
{
	int pos;
	if (namelen && name[namelen - 1] == '/')
		namelen--;
	pos = index_name_pos(istate, name, namelen);
	if (0 <= pos)
		return 0;	/* exact match */
	pos = -pos - 1;
	if (pos < istate->cache_nr) {
		struct cache_entry *ce = istate->cache[pos];
		if (ce_namelen(ce) == namelen &&
		    !memcmp(ce->name, name, namelen))
			return 0; /* Yup, this one exists unmerged */
	}
	return 1;
}