summaryrefslogtreecommitdiff
path: root/read-cache.c
blob: 22e7b9944e35d257b144fe06dce2073c91d4819f (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
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
/*
 * GIT - The information manager from hell
 *
 * Copyright (C) Linus Torvalds, 2005
 */
#include "cache.h"
#include "config.h"
#include "diff.h"
#include "diffcore.h"
#include "tempfile.h"
#include "lockfile.h"
#include "cache-tree.h"
#include "refs.h"
#include "dir.h"
#include "object-store.h"
#include "tree.h"
#include "commit.h"
#include "blob.h"
#include "resolve-undo.h"
#include "run-command.h"
#include "strbuf.h"
#include "varint.h"
#include "split-index.h"
#include "utf8.h"
#include "fsmonitor.h"
#include "thread-utils.h"
#include "progress.h"

/* Mask for the name length in ce_flags in the on-disk index */

#define CE_NAMEMASK  (0x0fff)

/* 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" */
#define CACHE_EXT_LINK 0x6c696e6b	  /* "link" */
#define CACHE_EXT_UNTRACKED 0x554E5452	  /* "UNTR" */
#define CACHE_EXT_FSMONITOR 0x46534D4E	  /* "FSMN" */
#define CACHE_EXT_ENDOFINDEXENTRIES 0x454F4945	/* "EOIE" */
#define CACHE_EXT_INDEXENTRYOFFSETTABLE 0x49454F54 /* "IEOT" */

/* changes that can be kept in $GIT_DIR/index (basically all extensions) */
#define EXTMASK (RESOLVE_UNDO_CHANGED | CACHE_TREE_CHANGED | \
		 CE_ENTRY_ADDED | CE_ENTRY_REMOVED | CE_ENTRY_CHANGED | \
		 SPLIT_INDEX_ORDERED | UNTRACKED_CHANGED | FSMONITOR_CHANGED)


/*
 * This is an estimate of the pathname length in the index.  We use
 * this for V4 index files to guess the un-deltafied size of the index
 * in memory because of pathname deltafication.  This is not required
 * for V2/V3 index formats because their pathnames are not compressed.
 * If the initial amount of memory set aside is not sufficient, the
 * mem pool will allocate extra memory.
 */
#define CACHE_ENTRY_PATH_LENGTH 80

static inline struct cache_entry *mem_pool__ce_alloc(struct mem_pool *mem_pool, size_t len)
{
	struct cache_entry *ce;
	ce = mem_pool_alloc(mem_pool, cache_entry_size(len));
	ce->mem_pool_allocated = 1;
	return ce;
}

static inline struct cache_entry *mem_pool__ce_calloc(struct mem_pool *mem_pool, size_t len)
{
	struct cache_entry * ce;
	ce = mem_pool_calloc(mem_pool, 1, cache_entry_size(len));
	ce->mem_pool_allocated = 1;
	return ce;
}

static struct mem_pool *find_mem_pool(struct index_state *istate)
{
	struct mem_pool **pool_ptr;

	if (istate->split_index && istate->split_index->base)
		pool_ptr = &istate->split_index->base->ce_mem_pool;
	else
		pool_ptr = &istate->ce_mem_pool;

	if (!*pool_ptr)
		mem_pool_init(pool_ptr, 0);

	return *pool_ptr;
}

static const char *alternate_index_output;

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];

	replace_index_entry_in_base(istate, old, ce);
	remove_name_hash(istate, old);
	discard_cache_entry(old);
	ce->ce_flags &= ~CE_HASHED;
	set_index_entry(istate, nr, ce);
	ce->ce_flags |= CE_UPDATE_IN_BASE;
	mark_fsmonitor_invalid(istate, ce);
	istate->cache_changed |= CE_ENTRY_CHANGED;
}

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

	new_entry = make_empty_cache_entry(istate, namelen);
	copy_cache_entry(new_entry, old_entry);
	new_entry->ce_flags &= ~CE_HASHED;
	new_entry->ce_namelen = namelen;
	new_entry->index = 0;
	memcpy(new_entry->name, new_name, namelen + 1);

	cache_tree_invalidate_path(istate, old_entry->name);
	untracked_cache_remove_from_index(istate, old_entry->name);
	remove_index_entry_at(istate, nr);
	add_index_entry(istate, new_entry, ADD_CACHE_OK_TO_ADD|ADD_CACHE_OK_TO_REPLACE);
}

void fill_stat_data(struct stat_data *sd, struct stat *st)
{
	sd->sd_ctime.sec = (unsigned int)st->st_ctime;
	sd->sd_mtime.sec = (unsigned int)st->st_mtime;
	sd->sd_ctime.nsec = ST_CTIME_NSEC(*st);
	sd->sd_mtime.nsec = ST_MTIME_NSEC(*st);
	sd->sd_dev = st->st_dev;
	sd->sd_ino = st->st_ino;
	sd->sd_uid = st->st_uid;
	sd->sd_gid = st->st_gid;
	sd->sd_size = st->st_size;
}

int match_stat_data(const struct stat_data *sd, struct stat *st)
{
	int changed = 0;

	if (sd->sd_mtime.sec != (unsigned int)st->st_mtime)
		changed |= MTIME_CHANGED;
	if (trust_ctime && check_stat &&
	    sd->sd_ctime.sec != (unsigned int)st->st_ctime)
		changed |= CTIME_CHANGED;

#ifdef USE_NSEC
	if (check_stat && sd->sd_mtime.nsec != ST_MTIME_NSEC(*st))
		changed |= MTIME_CHANGED;
	if (trust_ctime && check_stat &&
	    sd->sd_ctime.nsec != ST_CTIME_NSEC(*st))
		changed |= CTIME_CHANGED;
#endif

	if (check_stat) {
		if (sd->sd_uid != (unsigned int) st->st_uid ||
			sd->sd_gid != (unsigned int) st->st_gid)
			changed |= OWNER_CHANGED;
		if (sd->sd_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 (check_stat && sd->sd_dev != (unsigned int) st->st_dev)
			changed |= INODE_CHANGED;
#endif

	if (sd->sd_size != (unsigned int) st->st_size)
		changed |= DATA_CHANGED;

	return changed;
}

/*
 * 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)
{
	fill_stat_data(&ce->ce_stat_data, st);

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

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

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

	if (fd >= 0) {
		struct object_id oid;
		if (!index_fd(istate, &oid, fd, st, OBJ_BLOB, ce->name, 0))
			match = !oideq(&oid, &ce->oid);
		/* index_fd() closed the file descriptor already */
	}
	return match;
}

static int ce_compare_link(const 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_object_file(&ce->oid, &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(const struct cache_entry *ce)
{
	struct object_id oid;

	/*
	 * 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", &oid) < 0)
		return 0;
	return !oideq(&oid, &ce->oid);
}

static int ce_modified_check_fs(struct index_state *istate,
				const struct cache_entry *ce,
				struct stat *st)
{
	switch (st->st_mode & S_IFMT) {
	case S_IFREG:
		if (ce_compare_data(istate, 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;
		/* else fallthrough */
	default:
		return TYPE_CHANGED;
	}
	return 0;
}

static int ce_match_stat_basic(const 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:
		BUG("unsupported ce_mode: %o", ce->ce_mode);
	}

	changed |= match_stat_data(&ce->ce_stat_data, st);

	/* Racily smudged entry? */
	if (!ce->ce_stat_data.sd_size) {
		if (!is_empty_blob_sha1(ce->oid.hash))
			changed |= DATA_CHANGED;
	}

	return changed;
}

static int is_racy_stat(const struct index_state *istate,
			const struct stat_data *sd)
{
	return (istate->timestamp.sec &&
#ifdef USE_NSEC
		 /* nanosecond timestamped files can also be racy! */
		(istate->timestamp.sec < sd->sd_mtime.sec ||
		 (istate->timestamp.sec == sd->sd_mtime.sec &&
		  istate->timestamp.nsec <= sd->sd_mtime.nsec))
#else
		istate->timestamp.sec <= sd->sd_mtime.sec
#endif
		);
}

int is_racy_timestamp(const struct index_state *istate,
			     const struct cache_entry *ce)
{
	return (!S_ISGITLINK(ce->ce_mode) &&
		is_racy_stat(istate, &ce->ce_stat_data));
}

int match_stat_data_racy(const struct index_state *istate,
			 const struct stat_data *sd, struct stat *st)
{
	if (is_racy_stat(istate, sd))
		return MTIME_CHANGED;
	return match_stat_data(sd, st);
}

int ie_match_stat(struct index_state *istate,
		  const 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;
	int ignore_fsmonitor = options & CE_MATCH_IGNORE_FSMONITOR;

	if (!ignore_fsmonitor)
		refresh_fsmonitor(istate);
	/*
	 * 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;
	if (!ignore_fsmonitor && (ce->ce_flags & CE_FSMONITOR_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_intent_to_add(ce))
		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(istate, ce, st);
	}

	return changed;
}

int ie_modified(struct index_state *istate,
		const 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_stat_data.sd_size != 0))
		return changed;

	changed_fs = ce_modified_check_fs(istate, 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 name_compare(const char *name1, size_t len1, const char *name2, size_t len2)
{
	size_t min_len = (len1 < len2) ? len1 : len2;
	int cmp = memcmp(name1, name2, min_len);
	if (cmp)
		return cmp;
	if (len1 < len2)
		return -1;
	if (len1 > len2)
		return 1;
	return 0;
}

int cache_name_stage_compare(const char *name1, int len1, int stage1, const char *name2, int len2, int stage2)
{
	int cmp;

	cmp = name_compare(name1, len1, name2, len2);
	if (cmp)
		return cmp;

	if (stage1 < stage2)
		return -1;
	if (stage1 > stage2)
		return 1;
	return 0;
}

static int index_name_stage_pos(const struct index_state *istate, const char *name, int namelen, int stage)
{
	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_stage_compare(name, namelen, stage, ce->name, ce_namelen(ce), ce_stage(ce));
		if (!cmp)
			return next;
		if (cmp < 0) {
			last = next;
			continue;
		}
		first = next+1;
	}
	return -first-1;
}

int index_name_pos(const struct index_state *istate, const char *name, int namelen)
{
	return index_name_stage_pos(istate, name, namelen, 0);
}

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(istate, ce);
	save_or_free_index_entry(istate, ce);
	istate->cache_changed |= CE_ENTRY_REMOVED;
	istate->cache_nr--;
	if (pos >= istate->cache_nr)
		return 0;
	MOVE_ARRAY(istate->cache + pos, istate->cache + pos + 1,
		   istate->cache_nr - pos);
	return 1;
}

/*
 * Remove all cache entries 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, int invalidate)
{
	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) {
			if (invalidate) {
				cache_tree_invalidate_path(istate,
							   ce_array[i]->name);
				untracked_cache_remove_from_index(istate,
								  ce_array[i]->name);
			}
			remove_name_hash(istate, ce_array[i]);
			save_or_free_index_entry(istate, ce_array[i]);
		}
		else
			ce_array[j++] = ce_array[i];
	}
	if (j == istate->cache_nr)
		return;
	istate->cache_changed |= CE_ENTRY_REMOVED;
	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, path);
	untracked_cache_remove_from_index(istate, 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 index_state *istate,
					   struct cache_entry *ce,
					   struct cache_entry *alias)
{
	int len;
	struct cache_entry *new_entry;

	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_entry = make_empty_cache_entry(istate, len);
	memcpy(new_entry->name, alias->name, len);
	copy_cache_entry(new_entry, ce);
	save_or_free_index_entry(istate, ce);
	return new_entry;
}

void set_object_name_for_intent_to_add_entry(struct cache_entry *ce)
{
	struct object_id oid;
	if (write_object_file("", 0, blob_type, &oid))
		die(_("cannot create an empty blob in the object database"));
	oidcpy(&ce->oid, &oid);
}

int add_to_index(struct index_state *istate, const char *path, struct stat *st, int flags)
{
	int namelen, was_same;
	mode_t st_mode = st->st_mode;
	struct cache_entry *ce, *alias = NULL;
	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));
	int hash_flags = HASH_WRITE_OBJECT;
	struct object_id oid;

	if (flags & ADD_CACHE_RENORMALIZE)
		hash_flags |= HASH_RENORMALIZE;

	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)) {
		if (resolve_gitlink_ref(path, "HEAD", &oid) < 0)
			return error(_("'%s' does not have a commit checked out"), path);
		while (namelen && path[namelen-1] == '/')
			namelen--;
	}
	ce = make_empty_cache_entry(istate, namelen);
	memcpy(ce->name, path, namelen);
	ce->ce_namelen = 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) {
		adjust_dirname_case(istate, ce->name);
	}
	if (!(flags & ADD_CACHE_RENORMALIZE)) {
		alias = index_file_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 */
			if (!S_ISGITLINK(alias->ce_mode))
				ce_mark_uptodate(alias);
			alias->ce_flags |= CE_ADDED;

			discard_cache_entry(ce);
			return 0;
		}
	}
	if (!intent_only) {
		if (index_path(istate, &ce->oid, path, st, hash_flags)) {
			discard_cache_entry(ce);
			return error(_("unable to index file '%s'"), path);
		}
	} else
		set_object_name_for_intent_to_add_entry(ce);

	if (ignore_case && alias && different_name(ce, alias))
		ce = create_alias_ce(istate, 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) &&
		    oideq(&alias->oid, &ce->oid) &&
		    ce->ce_mode == alias->ce_mode);

	if (pretend)
		discard_cache_entry(ce);
	else if (add_index_entry(istate, ce, add_option)) {
		discard_cache_entry(ce);
		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_empty_cache_entry(struct index_state *istate, size_t len)
{
	return mem_pool__ce_calloc(find_mem_pool(istate), len);
}

struct cache_entry *make_empty_transient_cache_entry(size_t len)
{
	return xcalloc(1, cache_entry_size(len));
}

struct cache_entry *make_cache_entry(struct index_state *istate,
				     unsigned int mode,
				     const struct object_id *oid,
				     const char *path,
				     int stage,
				     unsigned int refresh_options)
{
	struct cache_entry *ce, *ret;
	int len;

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

	len = strlen(path);
	ce = make_empty_cache_entry(istate, len);

	oidcpy(&ce->oid, oid);
	memcpy(ce->name, path, len);
	ce->ce_flags = create_ce_flags(stage);
	ce->ce_namelen = len;
	ce->ce_mode = create_ce_mode(mode);

	ret = refresh_cache_entry(istate, ce, refresh_options);
	if (ret != ce)
		discard_cache_entry(ce);
	return ret;
}

struct cache_entry *make_transient_cache_entry(unsigned int mode, const struct object_id *oid,
					       const char *path, int stage)
{
	struct cache_entry *ce;
	int len;

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

	len = strlen(path);
	ce = make_empty_transient_cache_entry(len);

	oidcpy(&ce->oid, oid);
	memcpy(ce->name, path, len);
	ce->ce_flags = create_ce_flags(stage);
	ce->ce_namelen = len;
	ce->ce_mode = create_ce_mode(mode);

	return ce;
}

/*
 * Chmod an index entry with either +x or -x.
 *
 * Returns -1 if the chmod for the particular cache entry failed (if it's
 * not a regular file), -2 if an invalid flip argument is passed in, 0
 * otherwise.
 */
int chmod_index_entry(struct index_state *istate, struct cache_entry *ce,
		      char flip)
{
	if (!S_ISREG(ce->ce_mode))
		return -1;
	switch (flip) {
	case '+':
		ce->ce_mode |= 0111;
		break;
	case '-':
		ce->ce_mode &= ~0111;
		break;
	default:
		return -2;
	}
	cache_tree_invalidate_path(istate, ce->name);
	ce->ce_flags |= CE_UPDATE_IN_BASE;
	mark_fsmonitor_invalid(istate, ce);
	istate->cache_changed |= CE_ENTRY_CHANGED;

	return 0;
}

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

/*
 * 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, unsigned mode)
{
	/*
	 * 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. Note that we match
	 * case-insensitively here, even if ignore_case is not set.
	 * This outlaws ".GIT" everywhere out of an abundance of caution,
	 * since there's really no good reason to allow it.
	 *
	 * Once we've seen ".git", we can also find ".gitmodules", etc (also
	 * case-insensitively).
	 */
	case 'g':
	case 'G':
		if (rest[1] != 'i' && rest[1] != 'I')
			break;
		if (rest[2] != 't' && rest[2] != 'T')
			break;
		if (rest[3] == '\0' || is_dir_sep(rest[3]))
			return 0;
		if (S_ISLNK(mode)) {
			rest += 3;
			if (skip_iprefix(rest, "modules", &rest) &&
			    (*rest == '\0' || is_dir_sep(*rest)))
				return 0;
		}
		break;
	case '.':
		if (rest[1] == '\0' || is_dir_sep(rest[1]))
			return 0;
	}
	return 1;
}

int verify_path(const char *path, unsigned mode)
{
	char c;

	if (has_dos_drive_prefix(path))
		return 0;

	goto inside;
	for (;;) {
		if (!c)
			return 1;
		if (is_dir_sep(c)) {
inside:
			if (protect_hfs) {
				if (is_hfs_dotgit(path))
					return 0;
				if (S_ISLNK(mode)) {
					if (is_hfs_dotgitmodules(path))
						return 0;
				}
			}
			if (protect_ntfs) {
				if (is_ntfs_dotgit(path))
					return 0;
				if (S_ISLNK(mode)) {
					if (is_ntfs_dotgitmodules(path))
						return 0;
				}
			}

			c = *path++;
			if ((c == '.' && !verify_dotfile(path, mode)) ||
			    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;
}


/*
 * Like strcmp(), but also return the offset of the first change.
 * If strings are equal, return the length.
 */
int strcmp_offset(const char *s1, const char *s2, size_t *first_change)
{
	size_t k;

	if (!first_change)
		return strcmp(s1, s2);

	for (k = 0; s1[k] == s2[k]; k++)
		if (s1[k] == '\0')
			break;

	*first_change = k;
	return (unsigned char)s1[k] - (unsigned char)s2[k];
}

/*
 * Do we have another file with a pathname that is a proper
 * subset of the name we're trying to add?
 *
 * That is, is there another file in the index with a path
 * that matches a sub-directory in the given entry?
 */
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);
	size_t len_eq_last;
	int cmp_last = 0;

	/*
	 * We are frequently called during an iteration on a sorted
	 * list of pathnames and while building a new index.  Therefore,
	 * there is a high probability that this entry will eventually
	 * be appended to the index, rather than inserted in the middle.
	 * If we can confirm that, we can avoid binary searches on the
	 * components of the pathname.
	 *
	 * Compare the entry's full path with the last path in the index.
	 */
	if (istate->cache_nr > 0) {
		cmp_last = strcmp_offset(name,
			istate->cache[istate->cache_nr - 1]->name,
			&len_eq_last);
		if (cmp_last > 0) {
			if (len_eq_last == 0) {
				/*
				 * The entry sorts AFTER the last one in the
				 * index and their paths have no common prefix,
				 * so there cannot be a F/D conflict.
				 */
				return retval;
			} else {
				/*
				 * The entry sorts AFTER the last one in the
				 * index, but has a common prefix.  Fall through
				 * to the loop below to disect the entry's path
				 * and see where the difference is.
				 */
			}
		} else if (cmp_last == 0) {
			/*
			 * The entry exactly matches the last one in the
			 * index, but because of multiple stage and CE_REMOVE
			 * items, we fall through and let the regular search
			 * code handle it.
			 */
		}
	}

	for (;;) {
		size_t len;

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

		if (cmp_last > 0) {
			/*
			 * (len + 1) is a directory boundary (including
			 * the trailing slash).  And since the loop is
			 * decrementing "slash", the first iteration is
			 * the longest directory prefix; subsequent
			 * iterations consider parent directories.
			 */

			if (len + 1 <= len_eq_last) {
				/*
				 * The directory prefix (including the trailing
				 * slash) also appears as a prefix in the last
				 * entry, so the remainder cannot collide (because
				 * strcmp said the whole path was greater).
				 *
				 * EQ: last: xxx/A
				 *     this: xxx/B
				 *
				 * LT: last: xxx/file_A
				 *     this: xxx/file_B
				 */
				return retval;
			}

			if (len > len_eq_last) {
				/*
				 * This part of the directory prefix (excluding
				 * the trailing slash) is longer than the known
				 * equal portions, so this sub-directory cannot
				 * collide with a file.
				 *
				 * GT: last: xxxA
				 *     this: xxxB/file
				 */
				return retval;
			}

			if (istate->cache_nr > 0 &&
				ce_namelen(istate->cache[istate->cache_nr - 1]) > len) {
				/*
				 * The directory prefix lines up with part of
				 * a longer file or directory name, but sorts
				 * after it, so this sub-directory cannot
				 * collide with a file.
				 *
				 * last: xxx/yy-file (because '-' sorts before '/')
				 * this: xxx/yy/abc
				 */
				return retval;
			}

			/*
			 * This is a possible collision. Fall through and
			 * let the regular search code handle it.
			 *
			 * last: xxx
			 * this: xxx/file
			 */
		}

		pos = index_name_stage_pos(istate, name, 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;

	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
		cache_tree_invalidate_path(istate, ce->name);

	/*
	 * If this entry's path sorts after the last entry in the index,
	 * we can avoid searching for it.
	 */
	if (istate->cache_nr > 0 &&
		strcmp(ce->name, istate->cache[istate->cache_nr - 1]->name) > 0)
		pos = -istate->cache_nr - 1;
	else
		pos = index_name_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));

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

	if (!(option & ADD_CACHE_KEEP_CACHE_TREE))
		untracked_cache_add_to_index(istate, ce->name);

	/*
	 * 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, ce->ce_mode))
		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_stage_pos(istate, ce->name, ce_namelen(ce), ce_stage(ce));
		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 .. */
	ALLOC_GROW(istate->cache, istate->cache_nr + 1, istate->cache_alloc);

	/* Add it in.. */
	istate->cache_nr++;
	if (istate->cache_nr > pos + 1)
		MOVE_ARRAY(istate->cache + pos + 1, istate->cache + pos,
			   istate->cache_nr - pos - 1);
	set_index_entry(istate, pos, ce);
	istate->cache_changed |= CE_ENTRY_ADDED;
	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;
	int refresh = options & CE_MATCH_REFRESH;
	int ignore_valid = options & CE_MATCH_IGNORE_VALID;
	int ignore_skip_worktree = options & CE_MATCH_IGNORE_SKIP_WORKTREE;
	int ignore_missing = options & CE_MATCH_IGNORE_MISSING;
	int ignore_fsmonitor = options & CE_MATCH_IGNORE_FSMONITOR;

	if (!refresh || ce_uptodate(ce))
		return ce;

	if (!ignore_fsmonitor)
		refresh_fsmonitor(istate);
	/*
	 * 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 (!ignore_fsmonitor && (ce->ce_flags & CE_FSMONITOR_VALID)) {
		ce_mark_uptodate(ce);
		return ce;
	}

	if (has_symlink_leading_path(ce->name, ce_namelen(ce))) {
		if (ignore_missing)
			return ce;
		if (err)
			*err = ENOENT;
		return NULL;
	}

	if (lstat(ce->name, &st) < 0) {
		if (ignore_missing && errno == ENOENT)
			return ce;
		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);
				mark_fsmonitor_valid(ce);
			}
			return ce;
		}
	}

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

	updated = make_empty_cache_entry(istate, ce_namelen(ce));
	copy_cache_entry(updated, ce);
	memcpy(updated->name, ce->name, ce->ce_namelen + 1);
	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;

	/* istate->cache_changed is updated in the caller */
	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 struct pathspec *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 = (CE_MATCH_REFRESH |
				(really ? CE_MATCH_IGNORE_VALID : 0) |
				(not_new ? CE_MATCH_IGNORE_MISSING : 0));
	const char *modified_fmt;
	const char *deleted_fmt;
	const char *typechange_fmt;
	const char *added_fmt;
	const char *unmerged_fmt;
	struct progress *progress = NULL;

	if (flags & REFRESH_PROGRESS && isatty(2))
		progress = start_delayed_progress(_("Refresh index"),
						  istate->cache_nr);

	trace_performance_enter();
	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";
	/*
	 * Use the multi-threaded preload_index() to refresh most of the
	 * cache entries quickly then in the single threaded loop below,
	 * we only have to do the special cases that are left.
	 */
	preload_index(istate, pathspec, 0);
	for (i = 0; i < istate->cache_nr; i++) {
		struct cache_entry *ce, *new_entry;
		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 && !ce_path_match(istate, ce, pathspec, 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_entry = refresh_cache_ent(istate, ce, options, &cache_errno, &changed);
		if (new_entry == ce)
			continue;
		if (progress)
			display_progress(progress, i);
		if (!new_entry) {
			const char *fmt;

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

			if (cache_errno == ENOENT)
				fmt = deleted_fmt;
			else if (ce_intent_to_add(ce))
				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_entry);
	}
	if (progress) {
		display_progress(progress, istate->cache_nr);
		stop_progress(&progress);
	}
	trace_performance_leave("refresh index");
	return has_errors;
}

struct cache_entry *refresh_cache_entry(struct index_state *istate,
					struct cache_entry *ce,
					unsigned int options)
{
	return refresh_cache_ent(istate, ce, options, NULL, NULL);
}


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

#define INDEX_FORMAT_DEFAULT 3

static unsigned int get_index_format_default(void)
{
	char *envversion = getenv("GIT_INDEX_VERSION");
	char *endp;
	int value;
	unsigned int version = INDEX_FORMAT_DEFAULT;

	if (!envversion) {
		if (!git_config_get_int("index.version", &value))
			version = value;
		if (version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < version) {
			warning(_("index.version set, but the value is invalid.\n"
				  "Using version %i"), INDEX_FORMAT_DEFAULT);
			return INDEX_FORMAT_DEFAULT;
		}
		return version;
	}

	version = strtoul(envversion, &endp, 10);
	if (*endp ||
	    version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < version) {
		warning(_("GIT_INDEX_VERSION set, but the value is invalid.\n"
			  "Using version %i"), INDEX_FORMAT_DEFAULT);
		version = INDEX_FORMAT_DEFAULT;
	}
	return version;
}

/*
 * 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;
	uint32_t dev;
	uint32_t ino;
	uint32_t mode;
	uint32_t uid;
	uint32_t gid;
	uint32_t size;
	/*
	 * unsigned char hash[hashsz];
	 * uint16_t flags;
	 * if (flags & CE_EXTENDED)
	 *	uint16_t flags2;
	 */
	unsigned char data[GIT_MAX_RAWSZ + 2 * sizeof(uint16_t)];
	char name[FLEX_ARRAY];
};

/* These are only used for v3 or lower */
#define align_padding_size(size, len) ((size + (len) + 8) & ~7) - (size + len)
#define align_flex_name(STRUCT,len) ((offsetof(struct STRUCT,data) + (len) + 8) & ~7)
#define ondisk_cache_entry_size(len) align_flex_name(ondisk_cache_entry,len)
#define ondisk_data_size(flags, len) (the_hash_algo->rawsz + \
				     ((flags & CE_EXTENDED) ? 2 : 1) * sizeof(uint16_t) + len)
#define ondisk_data_size_max(len) (ondisk_data_size(CE_EXTENDED, len))
#define ondisk_ce_size(ce) (ondisk_cache_entry_size(ondisk_data_size((ce)->ce_flags, ce_namelen(ce))))

/* Allow fsck to force verification of the index checksum. */
int verify_index_checksum;

/* Allow fsck to force verification of the cache entry order. */
int verify_ce_order;

static int verify_hdr(const struct cache_header *hdr, unsigned long size)
{
	git_hash_ctx c;
	unsigned char hash[GIT_MAX_RAWSZ];
	int hdr_version;

	if (hdr->hdr_signature != htonl(CACHE_SIGNATURE))
		return error(_("bad signature 0x%08x"), hdr->hdr_signature);
	hdr_version = ntohl(hdr->hdr_version);
	if (hdr_version < INDEX_FORMAT_LB || INDEX_FORMAT_UB < hdr_version)
		return error(_("bad index version %d"), hdr_version);

	if (!verify_index_checksum)
		return 0;

	the_hash_algo->init_fn(&c);
	the_hash_algo->update_fn(&c, hdr, size - the_hash_algo->rawsz);
	the_hash_algo->final_fn(hash, &c);
	if (!hasheq(hash, (unsigned char *)hdr + size - the_hash_algo->rawsz))
		return error(_("bad index file sha1 signature"));
	return 0;
}

static int read_index_extension(struct index_state *istate,
				const char *ext, const char *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;
	case CACHE_EXT_LINK:
		if (read_link_extension(istate, data, sz))
			return -1;
		break;
	case CACHE_EXT_UNTRACKED:
		istate->untracked = read_untracked_extension(data, sz);
		break;
	case CACHE_EXT_FSMONITOR:
		read_fsmonitor_extension(istate, data, sz);
		break;
	case CACHE_EXT_ENDOFINDEXENTRIES:
	case CACHE_EXT_INDEXENTRYOFFSETTABLE:
		/* already handled in do_read_index() */
		break;
	default:
		if (*ext < 'A' || 'Z' < *ext)
			return error(_("index uses %.4s extension, which we do not understand"),
				     ext);
		fprintf_ln(stderr, _("ignoring %.4s extension"), ext);
		break;
	}
	return 0;
}

static struct cache_entry *create_from_disk(struct mem_pool *ce_mem_pool,
					    unsigned int version,
					    struct ondisk_cache_entry *ondisk,
					    unsigned long *ent_size,
					    const struct cache_entry *previous_ce)
{
	struct cache_entry *ce;
	size_t len;
	const char *name;
	const unsigned hashsz = the_hash_algo->rawsz;
	const uint16_t *flagsp = (const uint16_t *)(ondisk->data + hashsz);
	unsigned int flags;
	size_t copy_len = 0;
	/*
	 * 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.
	 */
	int expand_name_field = version == 4;

	/* On-disk flags are just 16 bits */
	flags = get_be16(flagsp);
	len = flags & CE_NAMEMASK;

	if (flags & CE_EXTENDED) {
		int extended_flags;
		extended_flags = get_be16(flagsp + 1) << 16;
		/* We do not yet understand any bit out of CE_EXTENDED_FLAGS */
		if (extended_flags & ~CE_EXTENDED_FLAGS)
			die(_("unknown index entry format 0x%08x"), extended_flags);
		flags |= extended_flags;
		name = (const char *)(flagsp + 2);
	}
	else
		name = (const char *)(flagsp + 1);

	if (expand_name_field) {
		const unsigned char *cp = (const unsigned char *)name;
		size_t strip_len, previous_len;

		/* If we're at the begining of a block, ignore the previous name */
		strip_len = decode_varint(&cp);
		if (previous_ce) {
			previous_len = previous_ce->ce_namelen;
			if (previous_len < strip_len)
				die(_("malformed name field in the index, near path '%s'"),
					previous_ce->name);
			copy_len = previous_len - strip_len;
		}
		name = (const char *)cp;
	}

	if (len == CE_NAMEMASK) {
		len = strlen(name);
		if (expand_name_field)
			len += copy_len;
	}

	ce = mem_pool__ce_alloc(ce_mem_pool, len);

	ce->ce_stat_data.sd_ctime.sec = get_be32(&ondisk->ctime.sec);
	ce->ce_stat_data.sd_mtime.sec = get_be32(&ondisk->mtime.sec);
	ce->ce_stat_data.sd_ctime.nsec = get_be32(&ondisk->ctime.nsec);
	ce->ce_stat_data.sd_mtime.nsec = get_be32(&ondisk->mtime.nsec);
	ce->ce_stat_data.sd_dev   = get_be32(&ondisk->dev);
	ce->ce_stat_data.sd_ino   = get_be32(&ondisk->ino);
	ce->ce_mode  = get_be32(&ondisk->mode);
	ce->ce_stat_data.sd_uid   = get_be32(&ondisk->uid);
	ce->ce_stat_data.sd_gid   = get_be32(&ondisk->gid);
	ce->ce_stat_data.sd_size  = get_be32(&ondisk->size);
	ce->ce_flags = flags & ~CE_NAMEMASK;
	ce->ce_namelen = len;
	ce->index = 0;
	hashcpy(ce->oid.hash, ondisk->data);
	memcpy(ce->name, name, len);
	ce->name[len] = '\0';

	if (expand_name_field) {
		if (copy_len)
			memcpy(ce->name, previous_ce->name, copy_len);
		memcpy(ce->name + copy_len, name, len + 1 - copy_len);
		*ent_size = (name - ((char *)ondisk)) + len + 1 - copy_len;
	} else {
		memcpy(ce->name, name, len + 1);
		*ent_size = ondisk_ce_size(ce);
	}
	return ce;
}

static void check_ce_order(struct index_state *istate)
{
	unsigned int i;

	if (!verify_ce_order)
		return;

	for (i = 1; i < istate->cache_nr; i++) {
		struct cache_entry *ce = istate->cache[i - 1];
		struct cache_entry *next_ce = istate->cache[i];
		int name_compare = strcmp(ce->name, next_ce->name);

		if (0 < name_compare)
			die(_("unordered stage entries in index"));
		if (!name_compare) {
			if (!ce_stage(ce))
				die(_("multiple stage entries for merged file '%s'"),
				    ce->name);
			if (ce_stage(ce) > ce_stage(next_ce))
				die(_("unordered stage entries for '%s'"),
				    ce->name);
		}
	}
}

static void tweak_untracked_cache(struct index_state *istate)
{
	switch (git_config_get_untracked_cache()) {
	case -1: /* keep: do nothing */
		break;
	case 0: /* false */
		remove_untracked_cache(istate);
		break;
	case 1: /* true */
		add_untracked_cache(istate);
		break;
	default: /* unknown value: do nothing */
		break;
	}
}

static void tweak_split_index(struct index_state *istate)
{
	switch (git_config_get_split_index()) {
	case -1: /* unset: do nothing */
		break;
	case 0: /* false */
		remove_split_index(istate);
		break;
	case 1: /* true */
		add_split_index(istate);
		break;
	default: /* unknown value: do nothing */
		break;
	}
}

static void post_read_index_from(struct index_state *istate)
{
	check_ce_order(istate);
	tweak_untracked_cache(istate);
	tweak_split_index(istate);
	tweak_fsmonitor(istate);
}

static size_t estimate_cache_size_from_compressed(unsigned int entries)
{
	return entries * (sizeof(struct cache_entry) + CACHE_ENTRY_PATH_LENGTH);
}

static size_t estimate_cache_size(size_t ondisk_size, unsigned int entries)
{
	long per_entry = sizeof(struct cache_entry) - sizeof(struct ondisk_cache_entry);

	/*
	 * Account for potential alignment differences.
	 */
	per_entry += align_padding_size(sizeof(struct cache_entry), -sizeof(struct ondisk_cache_entry));
	return ondisk_size + entries * per_entry;
}

struct index_entry_offset
{
	/* starting byte offset into index file, count of index entries in this block */
	int offset, nr;
};

struct index_entry_offset_table
{
	int nr;
	struct index_entry_offset entries[FLEX_ARRAY];
};

static struct index_entry_offset_table *read_ieot_extension(const char *mmap, size_t mmap_size, size_t offset);
static void write_ieot_extension(struct strbuf *sb, struct index_entry_offset_table *ieot);

static size_t read_eoie_extension(const char *mmap, size_t mmap_size);
static void write_eoie_extension(struct strbuf *sb, git_hash_ctx *eoie_context, size_t offset);

struct load_index_extensions
{
	pthread_t pthread;
	struct index_state *istate;
	const char *mmap;
	size_t mmap_size;
	unsigned long src_offset;
};

static void *load_index_extensions(void *_data)
{
	struct load_index_extensions *p = _data;
	unsigned long src_offset = p->src_offset;

	while (src_offset <= p->mmap_size - the_hash_algo->rawsz - 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 = get_be32(p->mmap + src_offset + 4);
		if (read_index_extension(p->istate,
					 p->mmap + src_offset,
					 p->mmap + src_offset + 8,
					 extsize) < 0) {
			munmap((void *)p->mmap, p->mmap_size);
			die(_("index file corrupt"));
		}
		src_offset += 8;
		src_offset += extsize;
	}

	return NULL;
}

/*
 * A helper function that will load the specified range of cache entries
 * from the memory mapped file and add them to the given index.
 */
static unsigned long load_cache_entry_block(struct index_state *istate,
			struct mem_pool *ce_mem_pool, int offset, int nr, const char *mmap,
			unsigned long start_offset, const struct cache_entry *previous_ce)
{
	int i;
	unsigned long src_offset = start_offset;

	for (i = offset; i < offset + nr; i++) {
		struct ondisk_cache_entry *disk_ce;
		struct cache_entry *ce;
		unsigned long consumed;

		disk_ce = (struct ondisk_cache_entry *)(mmap + src_offset);
		ce = create_from_disk(ce_mem_pool, istate->version, disk_ce, &consumed, previous_ce);
		set_index_entry(istate, i, ce);

		src_offset += consumed;
		previous_ce = ce;
	}
	return src_offset - start_offset;
}

static unsigned long load_all_cache_entries(struct index_state *istate,
			const char *mmap, size_t mmap_size, unsigned long src_offset)
{
	unsigned long consumed;

	if (istate->version == 4) {
		mem_pool_init(&istate->ce_mem_pool,
				estimate_cache_size_from_compressed(istate->cache_nr));
	} else {
		mem_pool_init(&istate->ce_mem_pool,
				estimate_cache_size(mmap_size, istate->cache_nr));
	}

	consumed = load_cache_entry_block(istate, istate->ce_mem_pool,
					0, istate->cache_nr, mmap, src_offset, NULL);
	return consumed;
}

/*
 * Mostly randomly chosen maximum thread counts: we
 * cap the parallelism to online_cpus() threads, and we want
 * to have at least 10000 cache entries per thread for it to
 * be worth starting a thread.
 */

#define THREAD_COST		(10000)

struct load_cache_entries_thread_data
{
	pthread_t pthread;
	struct index_state *istate;
	struct mem_pool *ce_mem_pool;
	int offset;
	const char *mmap;
	struct index_entry_offset_table *ieot;
	int ieot_start;		/* starting index into the ieot array */
	int ieot_blocks;	/* count of ieot entries to process */
	unsigned long consumed;	/* return # of bytes in index file processed */
};

/*
 * A thread proc to run the load_cache_entries() computation
 * across multiple background threads.
 */
static void *load_cache_entries_thread(void *_data)
{
	struct load_cache_entries_thread_data *p = _data;
	int i;

	/* iterate across all ieot blocks assigned to this thread */
	for (i = p->ieot_start; i < p->ieot_start + p->ieot_blocks; i++) {
		p->consumed += load_cache_entry_block(p->istate, p->ce_mem_pool,
			p->offset, p->ieot->entries[i].nr, p->mmap, p->ieot->entries[i].offset, NULL);
		p->offset += p->ieot->entries[i].nr;
	}
	return NULL;
}

static unsigned long load_cache_entries_threaded(struct index_state *istate, const char *mmap, size_t mmap_size,
			unsigned long src_offset, int nr_threads, struct index_entry_offset_table *ieot)
{
	int i, offset, ieot_blocks, ieot_start, err;
	struct load_cache_entries_thread_data *data;
	unsigned long consumed = 0;

	/* a little sanity checking */
	if (istate->name_hash_initialized)
		BUG("the name hash isn't thread safe");

	mem_pool_init(&istate->ce_mem_pool, 0);

	/* ensure we have no more threads than we have blocks to process */
	if (nr_threads > ieot->nr)
		nr_threads = ieot->nr;
	data = xcalloc(nr_threads, sizeof(*data));

	offset = ieot_start = 0;
	ieot_blocks = DIV_ROUND_UP(ieot->nr, nr_threads);
	for (i = 0; i < nr_threads; i++) {
		struct load_cache_entries_thread_data *p = &data[i];
		int nr, j;

		if (ieot_start + ieot_blocks > ieot->nr)
			ieot_blocks = ieot->nr - ieot_start;

		p->istate = istate;
		p->offset = offset;
		p->mmap = mmap;
		p->ieot = ieot;
		p->ieot_start = ieot_start;
		p->ieot_blocks = ieot_blocks;

		/* create a mem_pool for each thread */
		nr = 0;
		for (j = p->ieot_start; j < p->ieot_start + p->ieot_blocks; j++)
			nr += p->ieot->entries[j].nr;
		if (istate->version == 4) {
			mem_pool_init(&p->ce_mem_pool,
				estimate_cache_size_from_compressed(nr));
		} else {
			mem_pool_init(&p->ce_mem_pool,
				estimate_cache_size(mmap_size, nr));
		}

		err = pthread_create(&p->pthread, NULL, load_cache_entries_thread, p);
		if (err)
			die(_("unable to create load_cache_entries thread: %s"), strerror(err));

		/* increment by the number of cache entries in the ieot block being processed */
		for (j = 0; j < ieot_blocks; j++)
			offset += ieot->entries[ieot_start + j].nr;
		ieot_start += ieot_blocks;
	}

	for (i = 0; i < nr_threads; i++) {
		struct load_cache_entries_thread_data *p = &data[i];

		err = pthread_join(p->pthread, NULL);
		if (err)
			die(_("unable to join load_cache_entries thread: %s"), strerror(err));
		mem_pool_combine(istate->ce_mem_pool, p->ce_mem_pool);
		consumed += p->consumed;
	}

	free(data);

	return consumed;
}

/* remember to discard_cache() before reading a different cache! */
int do_read_index(struct index_state *istate, const char *path, int must_exist)
{
	int fd;
	struct stat st;
	unsigned long src_offset;
	const struct cache_header *hdr;
	const char *mmap;
	size_t mmap_size;
	struct load_index_extensions p;
	size_t extension_offset = 0;
	int nr_threads, cpus;
	struct index_entry_offset_table *ieot = NULL;

	if (istate->initialized)
		return istate->cache_nr;

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

	if (fstat(fd, &st))
		die_errno(_("%s: cannot stat the open index"), path);

	mmap_size = xsize_t(st.st_size);
	if (mmap_size < sizeof(struct cache_header) + the_hash_algo->rawsz)
		die(_("%s: index file smaller than expected"), path);

	mmap = xmmap(NULL, mmap_size, PROT_READ, MAP_PRIVATE, fd, 0);
	if (mmap == MAP_FAILED)
		die_errno(_("%s: unable to map index file"), path);
	close(fd);

	hdr = (const struct cache_header *)mmap;
	if (verify_hdr(hdr, mmap_size) < 0)
		goto unmap;

	hashcpy(istate->oid.hash, (const unsigned char *)hdr + mmap_size - the_hash_algo->rawsz);
	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(*istate->cache));
	istate->initialized = 1;

	p.istate = istate;
	p.mmap = mmap;
	p.mmap_size = mmap_size;

	src_offset = sizeof(*hdr);

	if (git_config_get_index_threads(&nr_threads))
		nr_threads = 1;

	/* TODO: does creating more threads than cores help? */
	if (!nr_threads) {
		nr_threads = istate->cache_nr / THREAD_COST;
		cpus = online_cpus();
		if (nr_threads > cpus)
			nr_threads = cpus;
	}

	if (!HAVE_THREADS)
		nr_threads = 1;

	if (nr_threads > 1) {
		extension_offset = read_eoie_extension(mmap, mmap_size);
		if (extension_offset) {
			int err;

			p.src_offset = extension_offset;
			err = pthread_create(&p.pthread, NULL, load_index_extensions, &p);
			if (err)
				die(_("unable to create load_index_extensions thread: %s"), strerror(err));

			nr_threads--;
		}
	}

	/*
	 * Locate and read the index entry offset table so that we can use it
	 * to multi-thread the reading of the cache entries.
	 */
	if (extension_offset && nr_threads > 1)
		ieot = read_ieot_extension(mmap, mmap_size, extension_offset);

	if (ieot) {
		src_offset += load_cache_entries_threaded(istate, mmap, mmap_size, src_offset, nr_threads, ieot);
		free(ieot);
	} else {
		src_offset += load_all_cache_entries(istate, mmap, mmap_size, src_offset);
	}

	istate->timestamp.sec = st.st_mtime;
	istate->timestamp.nsec = ST_MTIME_NSEC(st);

	/* if we created a thread, join it otherwise load the extensions on the primary thread */
	if (extension_offset) {
		int ret = pthread_join(p.pthread, NULL);
		if (ret)
			die(_("unable to join load_index_extensions thread: %s"), strerror(ret));
	} else {
		p.src_offset = src_offset;
		load_index_extensions(&p);
	}
	munmap((void *)mmap, mmap_size);

	/*
	 * TODO trace2: replace "the_repository" with the actual repo instance
	 * that is associated with the given "istate".
	 */
	trace2_data_intmax("index", the_repository, "read/version",
			   istate->version);
	trace2_data_intmax("index", the_repository, "read/cache_nr",
			   istate->cache_nr);

	return istate->cache_nr;

unmap:
	munmap((void *)mmap, mmap_size);
	die(_("index file corrupt"));
}

/*
 * Signal that the shared index is used by updating its mtime.
 *
 * This way, shared index can be removed if they have not been used
 * for some time.
 */
static void freshen_shared_index(const char *shared_index, int warn)
{
	if (!check_and_freshen_file(shared_index, 1) && warn)
		warning(_("could not freshen shared index '%s'"), shared_index);
}

int read_index_from(struct index_state *istate, const char *path,
		    const char *gitdir)
{
	struct split_index *split_index;
	int ret;
	char *base_oid_hex;
	char *base_path;

	/* istate->initialized covers both .git/index and .git/sharedindex.xxx */
	if (istate->initialized)
		return istate->cache_nr;

	/*
	 * TODO trace2: replace "the_repository" with the actual repo instance
	 * that is associated with the given "istate".
	 */
	trace2_region_enter_printf("index", "do_read_index", the_repository,
				   "%s", path);
	trace_performance_enter();
	ret = do_read_index(istate, path, 0);
	trace_performance_leave("read cache %s", path);
	trace2_region_leave_printf("index", "do_read_index", the_repository,
				   "%s", path);

	split_index = istate->split_index;
	if (!split_index || is_null_oid(&split_index->base_oid)) {
		post_read_index_from(istate);
		return ret;
	}

	trace_performance_enter();
	if (split_index->base)
		discard_index(split_index->base);
	else
		split_index->base = xcalloc(1, sizeof(*split_index->base));

	base_oid_hex = oid_to_hex(&split_index->base_oid);
	base_path = xstrfmt("%s/sharedindex.%s", gitdir, base_oid_hex);
	trace2_region_enter_printf("index", "shared/do_read_index",
				   the_repository, "%s", base_path);
	ret = do_read_index(split_index->base, base_path, 1);
	trace2_region_leave_printf("index", "shared/do_read_index",
				   the_repository, "%s", base_path);
	if (!oideq(&split_index->base_oid, &split_index->base->oid))
		die(_("broken index, expect %s in %s, got %s"),
		    base_oid_hex, base_path,
		    oid_to_hex(&split_index->base->oid));

	freshen_shared_index(base_path, 0);
	merge_base_index(istate);
	post_read_index_from(istate);
	trace_performance_leave("read cache %s", base_path);
	free(base_path);
	return ret;
}

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

int discard_index(struct index_state *istate)
{
	/*
	 * Cache entries in istate->cache[] should have been allocated
	 * from the memory pool associated with this index, or from an
	 * associated split_index. There is no need to free individual
	 * cache entries. validate_cache_entries can detect when this
	 * assertion does not hold.
	 */
	validate_cache_entries(istate);

	resolve_undo_clear_index(istate);
	istate->cache_nr = 0;
	istate->cache_changed = 0;
	istate->timestamp.sec = 0;
	istate->timestamp.nsec = 0;
	free_name_hash(istate);
	cache_tree_free(&(istate->cache_tree));
	istate->initialized = 0;
	istate->fsmonitor_has_run_once = 0;
	FREE_AND_NULL(istate->cache);
	istate->cache_alloc = 0;
	discard_split_index(istate);
	free_untracked_cache(istate->untracked);
	istate->untracked = NULL;

	if (istate->ce_mem_pool) {
		mem_pool_discard(istate->ce_mem_pool, should_validate_cache_entries());
		istate->ce_mem_pool = NULL;
	}

	return 0;
}

/*
 * Validate the cache entries of this index.
 * All cache entries associated with this index
 * should have been allocated by the memory pool
 * associated with this index, or by a referenced
 * split index.
 */
void validate_cache_entries(const struct index_state *istate)
{
	int i;

	if (!should_validate_cache_entries() ||!istate || !istate->initialized)
		return;

	for (i = 0; i < istate->cache_nr; i++) {
		if (!istate) {
			BUG("cache entry is not allocated from expected memory pool");
		} else if (!istate->ce_mem_pool ||
			!mem_pool_contains(istate->ce_mem_pool, istate->cache[i])) {
			if (!istate->split_index ||
				!istate->split_index->base ||
				!istate->split_index->base->ce_mem_pool ||
				!mem_pool_contains(istate->split_index->base->ce_mem_pool, istate->cache[i])) {
				BUG("cache entry is not allocated from expected memory pool");
			}
		}
	}

	if (istate->split_index)
		validate_cache_entries(istate->split_index->base);
}

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;
}

int repo_index_has_changes(struct repository *repo,
			   struct tree *tree,
			   struct strbuf *sb)
{
	struct index_state *istate = repo->index;
	struct object_id cmp;
	int i;

	if (tree)
		cmp = tree->object.oid;
	if (tree || !get_oid_tree("HEAD", &cmp)) {
		struct diff_options opt;

		repo_diff_setup(repo, &opt);
		opt.flags.exit_with_status = 1;
		if (!sb)
			opt.flags.quick = 1;
		do_diff_cache(&cmp, &opt);
		diffcore_std(&opt);
		for (i = 0; sb && i < diff_queued_diff.nr; i++) {
			if (i)
				strbuf_addch(sb, ' ');
			strbuf_addstr(sb, diff_queued_diff.queue[i]->two->path);
		}
		diff_flush(&opt);
		return opt.flags.has_changes != 0;
	} else {
		for (i = 0; sb && i < istate->cache_nr; i++) {
			if (i)
				strbuf_addch(sb, ' ');
			strbuf_addstr(sb, istate->cache[i]->name);
		}
		return !!istate->cache_nr;
	}
}

#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_hash_ctx *context, int fd)
{
	unsigned int buffered = write_buffer_len;
	if (buffered) {
		the_hash_algo->update_fn(context, write_buffer, buffered);
		if (write_in_full(fd, write_buffer, buffered) < 0)
			return -1;
		write_buffer_len = 0;
	}
	return 0;
}

static int ce_write(git_hash_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_hash_ctx *context, git_hash_ctx *eoie_context,
				  int fd, unsigned int ext, unsigned int sz)
{
	ext = htonl(ext);
	sz = htonl(sz);
	if (eoie_context) {
		the_hash_algo->update_fn(eoie_context, &ext, 4);
		the_hash_algo->update_fn(eoie_context, &sz, 4);
	}
	return ((ce_write(context, fd, &ext, 4) < 0) ||
		(ce_write(context, fd, &sz, 4) < 0)) ? -1 : 0;
}

static int ce_flush(git_hash_ctx *context, int fd, unsigned char *hash)
{
	unsigned int left = write_buffer_len;

	if (left) {
		write_buffer_len = 0;
		the_hash_algo->update_fn(context, write_buffer, left);
	}

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

	/* Append the hash signature at the end */
	the_hash_algo->final_fn(write_buffer + left, context);
	hashcpy(hash, write_buffer + left);
	left += the_hash_algo->rawsz;
	return (write_in_full(fd, write_buffer, left) < 0) ? -1 : 0;
}

static void ce_smudge_racily_clean_entry(struct index_state *istate,
					 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_stat_data.sd_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(istate, 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_stat_data.sd_size = 0;
	}
}

/* Copy miscellaneous fields but not the name */
static void copy_cache_entry_to_ondisk(struct ondisk_cache_entry *ondisk,
				       struct cache_entry *ce)
{
	short flags;
	const unsigned hashsz = the_hash_algo->rawsz;
	uint16_t *flagsp = (uint16_t *)(ondisk->data + hashsz);

	ondisk->ctime.sec = htonl(ce->ce_stat_data.sd_ctime.sec);
	ondisk->mtime.sec = htonl(ce->ce_stat_data.sd_mtime.sec);
	ondisk->ctime.nsec = htonl(ce->ce_stat_data.sd_ctime.nsec);
	ondisk->mtime.nsec = htonl(ce->ce_stat_data.sd_mtime.nsec);
	ondisk->dev  = htonl(ce->ce_stat_data.sd_dev);
	ondisk->ino  = htonl(ce->ce_stat_data.sd_ino);
	ondisk->mode = htonl(ce->ce_mode);
	ondisk->uid  = htonl(ce->ce_stat_data.sd_uid);
	ondisk->gid  = htonl(ce->ce_stat_data.sd_gid);
	ondisk->size = htonl(ce->ce_stat_data.sd_size);
	hashcpy(ondisk->data, ce->oid.hash);

	flags = ce->ce_flags & ~CE_NAMEMASK;
	flags |= (ce_namelen(ce) >= CE_NAMEMASK ? CE_NAMEMASK : ce_namelen(ce));
	flagsp[0] = htons(flags);
	if (ce->ce_flags & CE_EXTENDED) {
		flagsp[1] = htons((ce->ce_flags & CE_EXTENDED_FLAGS) >> 16);
	}
}

static int ce_write_entry(git_hash_ctx *c, int fd, struct cache_entry *ce,
			  struct strbuf *previous_name, struct ondisk_cache_entry *ondisk)
{
	int size;
	int result;
	unsigned int saved_namelen;
	int stripped_name = 0;
	static unsigned char padding[8] = { 0x00 };

	if (ce->ce_flags & CE_STRIP_NAME) {
		saved_namelen = ce_namelen(ce);
		ce->ce_namelen = 0;
		stripped_name = 1;
	}

	size = offsetof(struct ondisk_cache_entry,data) + ondisk_data_size(ce->ce_flags, 0);

	if (!previous_name) {
		int len = ce_namelen(ce);
		copy_cache_entry_to_ondisk(ondisk, ce);
		result = ce_write(c, fd, ondisk, size);
		if (!result)
			result = ce_write(c, fd, ce->name, len);
		if (!result)
			result = ce_write(c, fd, padding, align_padding_size(size, len));
	} 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);

		copy_cache_entry_to_ondisk(ondisk, ce);
		result = ce_write(c, fd, ondisk, size);
		if (!result)
			result = ce_write(c, fd, to_remove_vi, prefix_size);
		if (!result)
			result = ce_write(c, fd, ce->name + common, ce_namelen(ce) - common);
		if (!result)
			result = ce_write(c, fd, padding, 1);

		strbuf_splice(previous_name, common, to_remove,
			      ce->name + common, ce_namelen(ce) - common);
	}
	if (stripped_name) {
		ce->ce_namelen = saved_namelen;
		ce->ce_flags &= ~CE_STRIP_NAME;
	}

	return result;
}

/*
 * This function verifies if index_state has the correct sha1 of the
 * index file.  Don't die if we have any other failure, just return 0.
 */
static int verify_index_from(const struct index_state *istate, const char *path)
{
	int fd;
	ssize_t n;
	struct stat st;
	unsigned char hash[GIT_MAX_RAWSZ];

	if (!istate->initialized)
		return 0;

	fd = open(path, O_RDONLY);
	if (fd < 0)
		return 0;

	if (fstat(fd, &st))
		goto out;

	if (st.st_size < sizeof(struct cache_header) + the_hash_algo->rawsz)
		goto out;

	n = pread_in_full(fd, hash, the_hash_algo->rawsz, st.st_size - the_hash_algo->rawsz);
	if (n != the_hash_algo->rawsz)
		goto out;

	if (!hasheq(istate->oid.hash, hash))
		goto out;

	close(fd);
	return 1;

out:
	close(fd);
	return 0;
}

static int repo_verify_index(struct repository *repo)
{
	return verify_index_from(repo->index, repo->index_file);
}

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;
}

void repo_update_index_if_able(struct repository *repo,
			       struct lock_file *lockfile)
{
	if ((repo->index->cache_changed ||
	     has_racy_timestamp(repo->index)) &&
	    repo_verify_index(repo))
		write_locked_index(repo->index, lockfile, COMMIT_LOCK);
	else
		rollback_lock_file(lockfile);
}

static int record_eoie(void)
{
	int val;

	if (!git_config_get_bool("index.recordendofindexentries", &val))
		return val;

	/*
	 * As a convenience, the end of index entries extension
	 * used for threading is written by default if the user
	 * explicitly requested threaded index reads.
	 */
	return !git_config_get_index_threads(&val) && val != 1;
}

static int record_ieot(void)
{
	int val;

	if (!git_config_get_bool("index.recordoffsettable", &val))
		return val;

	/*
	 * As a convenience, the offset table used for threading is
	 * written by default if the user explicitly requested
	 * threaded index reads.
	 */
	return !git_config_get_index_threads(&val) && val != 1;
}

/*
 * On success, `tempfile` is closed. If it is the temporary file
 * of a `struct lock_file`, we will therefore effectively perform
 * a 'close_lock_file_gently()`. Since that is an implementation
 * detail of lockfiles, callers of `do_write_index()` should not
 * rely on it.
 */
static int do_write_index(struct index_state *istate, struct tempfile *tempfile,
			  int strip_extensions)
{
	uint64_t start = getnanotime();
	int newfd = tempfile->fd;
	git_hash_ctx c, eoie_c;
	struct cache_header hdr;
	int i, err = 0, removed, extended, hdr_version;
	struct cache_entry **cache = istate->cache;
	int entries = istate->cache_nr;
	struct stat st;
	struct ondisk_cache_entry ondisk;
	struct strbuf previous_name_buf = STRBUF_INIT, *previous_name;
	int drop_cache_tree = istate->drop_cache_tree;
	off_t offset;
	int ieot_entries = 1;
	struct index_entry_offset_table *ieot = NULL;
	int nr, nr_threads;

	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 = get_index_format_default();
		if (git_env_bool("GIT_TEST_SPLIT_INDEX", 0))
			init_split_index(istate);
	}

	/* 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);

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

	if (!HAVE_THREADS || git_config_get_index_threads(&nr_threads))
		nr_threads = 1;

	if (nr_threads != 1 && record_ieot()) {
		int ieot_blocks, cpus;

		/*
		 * ensure default number of ieot blocks maps evenly to the
		 * default number of threads that will process them leaving
		 * room for the thread to load the index extensions.
		 */
		if (!nr_threads) {
			ieot_blocks = istate->cache_nr / THREAD_COST;
			cpus = online_cpus();
			if (ieot_blocks > cpus - 1)
				ieot_blocks = cpus - 1;
		} else {
			ieot_blocks = nr_threads;
			if (ieot_blocks > istate->cache_nr)
				ieot_blocks = istate->cache_nr;
		}

		/*
		 * no reason to write out the IEOT extension if we don't
		 * have enough blocks to utilize multi-threading
		 */
		if (ieot_blocks > 1) {
			ieot = xcalloc(1, sizeof(struct index_entry_offset_table)
				+ (ieot_blocks * sizeof(struct index_entry_offset)));
			ieot_entries = DIV_ROUND_UP(entries, ieot_blocks);
		}
	}

	offset = lseek(newfd, 0, SEEK_CUR);
	if (offset < 0) {
		free(ieot);
		return -1;
	}
	offset += write_buffer_len;
	nr = 0;
	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(istate, ce);
		if (is_null_oid(&ce->oid)) {
			static const char msg[] = "cache entry has null sha1: %s";
			static int allow = -1;

			if (allow < 0)
				allow = git_env_bool("GIT_ALLOW_NULL_SHA1", 0);
			if (allow)
				warning(msg, ce->name);
			else
				err = error(msg, ce->name);

			drop_cache_tree = 1;
		}
		if (ieot && i && (i % ieot_entries == 0)) {
			ieot->entries[ieot->nr].nr = nr;
			ieot->entries[ieot->nr].offset = offset;
			ieot->nr++;
			/*
			 * If we have a V4 index, set the first byte to an invalid
			 * character to ensure there is nothing common with the previous
			 * entry
			 */
			if (previous_name)
				previous_name->buf[0] = 0;
			nr = 0;
			offset = lseek(newfd, 0, SEEK_CUR);
			if (offset < 0) {
				free(ieot);
				return -1;
			}
			offset += write_buffer_len;
		}
		if (ce_write_entry(&c, newfd, ce, previous_name, (struct ondisk_cache_entry *)&ondisk) < 0)
			err = -1;

		if (err)
			break;
		nr++;
	}
	if (ieot && nr) {
		ieot->entries[ieot->nr].nr = nr;
		ieot->entries[ieot->nr].offset = offset;
		ieot->nr++;
	}
	strbuf_release(&previous_name_buf);

	if (err) {
		free(ieot);
		return err;
	}

	/* Write extension data here */
	offset = lseek(newfd, 0, SEEK_CUR);
	if (offset < 0) {
		free(ieot);
		return -1;
	}
	offset += write_buffer_len;
	the_hash_algo->init_fn(&eoie_c);

	/*
	 * Lets write out CACHE_EXT_INDEXENTRYOFFSETTABLE first so that we
	 * can minimize the number of extensions we have to scan through to
	 * find it during load.  Write it out regardless of the
	 * strip_extensions parameter as we need it when loading the shared
	 * index.
	 */
	if (ieot) {
		struct strbuf sb = STRBUF_INIT;

		write_ieot_extension(&sb, ieot);
		err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_INDEXENTRYOFFSETTABLE, sb.len) < 0
			|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
		strbuf_release(&sb);
		free(ieot);
		if (err)
			return -1;
	}

	if (!strip_extensions && istate->split_index &&
	    !is_null_oid(&istate->split_index->base_oid)) {
		struct strbuf sb = STRBUF_INIT;

		err = write_link_extension(&sb, istate) < 0 ||
			write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_LINK,
					       sb.len) < 0 ||
			ce_write(&c, newfd, sb.buf, sb.len) < 0;
		strbuf_release(&sb);
		if (err)
			return -1;
	}
	if (!strip_extensions && !drop_cache_tree && istate->cache_tree) {
		struct strbuf sb = STRBUF_INIT;

		cache_tree_write(&sb, istate->cache_tree);
		err = write_index_ext_header(&c, &eoie_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 (!strip_extensions && istate->resolve_undo) {
		struct strbuf sb = STRBUF_INIT;

		resolve_undo_write(&sb, istate->resolve_undo);
		err = write_index_ext_header(&c, &eoie_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 (!strip_extensions && istate->untracked) {
		struct strbuf sb = STRBUF_INIT;

		write_untracked_extension(&sb, istate->untracked);
		err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_UNTRACKED,
					     sb.len) < 0 ||
			ce_write(&c, newfd, sb.buf, sb.len) < 0;
		strbuf_release(&sb);
		if (err)
			return -1;
	}
	if (!strip_extensions && istate->fsmonitor_last_update) {
		struct strbuf sb = STRBUF_INIT;

		write_fsmonitor_extension(&sb, istate);
		err = write_index_ext_header(&c, &eoie_c, newfd, CACHE_EXT_FSMONITOR, sb.len) < 0
			|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
		strbuf_release(&sb);
		if (err)
			return -1;
	}

	/*
	 * CACHE_EXT_ENDOFINDEXENTRIES must be written as the last entry before the SHA1
	 * so that it can be found and processed before all the index entries are
	 * read.  Write it out regardless of the strip_extensions parameter as we need it
	 * when loading the shared index.
	 */
	if (offset && record_eoie()) {
		struct strbuf sb = STRBUF_INIT;

		write_eoie_extension(&sb, &eoie_c, offset);
		err = write_index_ext_header(&c, NULL, newfd, CACHE_EXT_ENDOFINDEXENTRIES, sb.len) < 0
			|| ce_write(&c, newfd, sb.buf, sb.len) < 0;
		strbuf_release(&sb);
		if (err)
			return -1;
	}

	if (ce_flush(&c, newfd, istate->oid.hash))
		return -1;
	if (close_tempfile_gently(tempfile)) {
		error(_("could not close '%s'"), tempfile->filename.buf);
		return -1;
	}
	if (stat(tempfile->filename.buf, &st))
		return -1;
	istate->timestamp.sec = (unsigned int)st.st_mtime;
	istate->timestamp.nsec = ST_MTIME_NSEC(st);
	trace_performance_since(start, "write index, changed mask = %x", istate->cache_changed);

	/*
	 * TODO trace2: replace "the_repository" with the actual repo instance
	 * that is associated with the given "istate".
	 */
	trace2_data_intmax("index", the_repository, "write/version",
			   istate->version);
	trace2_data_intmax("index", the_repository, "write/cache_nr",
			   istate->cache_nr);

	return 0;
}

void set_alternate_index_output(const char *name)
{
	alternate_index_output = name;
}

static int commit_locked_index(struct lock_file *lk)
{
	if (alternate_index_output)
		return commit_lock_file_to(lk, alternate_index_output);
	else
		return commit_lock_file(lk);
}

static int do_write_locked_index(struct index_state *istate, struct lock_file *lock,
				 unsigned flags)
{
	int ret;

	/*
	 * TODO trace2: replace "the_repository" with the actual repo instance
	 * that is associated with the given "istate".
	 */
	trace2_region_enter_printf("index", "do_write_index", the_repository,
				   "%s", lock->tempfile->filename.buf);
	ret = do_write_index(istate, lock->tempfile, 0);
	trace2_region_leave_printf("index", "do_write_index", the_repository,
				   "%s", lock->tempfile->filename.buf);

	if (ret)
		return ret;
	if (flags & COMMIT_LOCK)
		ret = commit_locked_index(lock);
	else
		ret = close_lock_file_gently(lock);

	run_hook_le(NULL, "post-index-change",
			istate->updated_workdir ? "1" : "0",
			istate->updated_skipworktree ? "1" : "0", NULL);
	istate->updated_workdir = 0;
	istate->updated_skipworktree = 0;

	return ret;
}

static int write_split_index(struct index_state *istate,
			     struct lock_file *lock,
			     unsigned flags)
{
	int ret;
	prepare_to_write_split_index(istate);
	ret = do_write_locked_index(istate, lock, flags);
	finish_writing_split_index(istate);
	return ret;
}

static const char *shared_index_expire = "2.weeks.ago";

static unsigned long get_shared_index_expire_date(void)
{
	static unsigned long shared_index_expire_date;
	static int shared_index_expire_date_prepared;

	if (!shared_index_expire_date_prepared) {
		git_config_get_expiry("splitindex.sharedindexexpire",
				      &shared_index_expire);
		shared_index_expire_date = approxidate(shared_index_expire);
		shared_index_expire_date_prepared = 1;
	}

	return shared_index_expire_date;
}

static int should_delete_shared_index(const char *shared_index_path)
{
	struct stat st;
	unsigned long expiration;

	/* Check timestamp */
	expiration = get_shared_index_expire_date();
	if (!expiration)
		return 0;
	if (stat(shared_index_path, &st))
		return error_errno(_("could not stat '%s'"), shared_index_path);
	if (st.st_mtime > expiration)
		return 0;

	return 1;
}

static int clean_shared_index_files(const char *current_hex)
{
	struct dirent *de;
	DIR *dir = opendir(get_git_dir());

	if (!dir)
		return error_errno(_("unable to open git dir: %s"), get_git_dir());

	while ((de = readdir(dir)) != NULL) {
		const char *sha1_hex;
		const char *shared_index_path;
		if (!skip_prefix(de->d_name, "sharedindex.", &sha1_hex))
			continue;
		if (!strcmp(sha1_hex, current_hex))
			continue;
		shared_index_path = git_path("%s", de->d_name);
		if (should_delete_shared_index(shared_index_path) > 0 &&
		    unlink(shared_index_path))
			warning_errno(_("unable to unlink: %s"), shared_index_path);
	}
	closedir(dir);

	return 0;
}

static int write_shared_index(struct index_state *istate,
			      struct tempfile **temp)
{
	struct split_index *si = istate->split_index;
	int ret;

	move_cache_to_base_index(istate);

	trace2_region_enter_printf("index", "shared/do_write_index",
				   the_repository, "%s", (*temp)->filename.buf);
	ret = do_write_index(si->base, *temp, 1);
	trace2_region_leave_printf("index", "shared/do_write_index",
				   the_repository, "%s", (*temp)->filename.buf);

	if (ret)
		return ret;
	ret = adjust_shared_perm(get_tempfile_path(*temp));
	if (ret) {
		error(_("cannot fix permission bits on '%s'"), get_tempfile_path(*temp));
		return ret;
	}
	ret = rename_tempfile(temp,
			      git_path("sharedindex.%s", oid_to_hex(&si->base->oid)));
	if (!ret) {
		oidcpy(&si->base_oid, &si->base->oid);
		clean_shared_index_files(oid_to_hex(&si->base->oid));
	}

	return ret;
}

static const int default_max_percent_split_change = 20;

static int too_many_not_shared_entries(struct index_state *istate)
{
	int i, not_shared = 0;
	int max_split = git_config_get_max_percent_split_change();

	switch (max_split) {
	case -1:
		/* not or badly configured: use the default value */
		max_split = default_max_percent_split_change;
		break;
	case 0:
		return 1; /* 0% means always write a new shared index */
	case 100:
		return 0; /* 100% means never write a new shared index */
	default:
		break; /* just use the configured value */
	}

	/* Count not shared entries */
	for (i = 0; i < istate->cache_nr; i++) {
		struct cache_entry *ce = istate->cache[i];
		if (!ce->index)
			not_shared++;
	}

	return (int64_t)istate->cache_nr * max_split < (int64_t)not_shared * 100;
}

int write_locked_index(struct index_state *istate, struct lock_file *lock,
		       unsigned flags)
{
	int new_shared_index, ret;
	struct split_index *si = istate->split_index;

	if (git_env_bool("GIT_TEST_CHECK_CACHE_TREE", 0))
		cache_tree_verify(the_repository, istate);

	if ((flags & SKIP_IF_UNCHANGED) && !istate->cache_changed) {
		if (flags & COMMIT_LOCK)
			rollback_lock_file(lock);
		return 0;
	}

	if (istate->fsmonitor_last_update)
		fill_fsmonitor_bitmap(istate);

	if (!si || alternate_index_output ||
	    (istate->cache_changed & ~EXTMASK)) {
		if (si)
			oidclr(&si->base_oid);
		ret = do_write_locked_index(istate, lock, flags);
		goto out;
	}

	if (git_env_bool("GIT_TEST_SPLIT_INDEX", 0)) {
		int v = si->base_oid.hash[0];
		if ((v & 15) < 6)
			istate->cache_changed |= SPLIT_INDEX_ORDERED;
	}
	if (too_many_not_shared_entries(istate))
		istate->cache_changed |= SPLIT_INDEX_ORDERED;

	new_shared_index = istate->cache_changed & SPLIT_INDEX_ORDERED;

	if (new_shared_index) {
		struct tempfile *temp;
		int saved_errno;

		/* Same initial permissions as the main .git/index file */
		temp = mks_tempfile_sm(git_path("sharedindex_XXXXXX"), 0, 0666);
		if (!temp) {
			oidclr(&si->base_oid);
			ret = do_write_locked_index(istate, lock, flags);
			goto out;
		}
		ret = write_shared_index(istate, &temp);

		saved_errno = errno;
		if (is_tempfile_active(temp))
			delete_tempfile(&temp);
		errno = saved_errno;

		if (ret)
			goto out;
	}

	ret = write_split_index(istate, lock, flags);

	/* Freshen the shared index only if the split-index was written */
	if (!ret && !new_shared_index && !is_null_oid(&si->base_oid)) {
		const char *shared_index = git_path("sharedindex.%s",
						    oid_to_hex(&si->base_oid));
		freshen_shared_index(shared_index, 1);
	}

out:
	if (flags & COMMIT_LOCK)
		rollback_lock_file(lock);
	return ret;
}

/*
 * Read the index file that is potentially unmerged into given
 * index_state, dropping any unmerged entries to stage #0 (potentially
 * resulting in a path appearing as both a file and a directory in the
 * index; the caller is responsible to clear out the extra entries
 * before writing the index to a tree).  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 repo_read_index_unmerged(struct repository *repo)
{
	struct index_state *istate;
	int i;
	int unmerged = 0;

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

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

void *read_blob_data_from_index(const struct index_state *istate,
				const char *path, unsigned long *size)
{
	int pos, len;
	unsigned long sz;
	enum object_type type;
	void *data;

	len = strlen(path);
	pos = index_name_pos(istate, path, len);
	if (pos < 0) {
		/*
		 * We might be in the middle of a merge, in which
		 * case we would read stage #2 (ours).
		 */
		int i;
		for (i = -pos - 1;
		     (pos < 0 && i < istate->cache_nr &&
		      !strcmp(istate->cache[i]->name, path));
		     i++)
			if (ce_stage(istate->cache[i]) == 2)
				pos = i;
	}
	if (pos < 0)
		return NULL;
	data = read_object_file(&istate->cache[pos]->oid, &type, &sz);
	if (!data || type != OBJ_BLOB) {
		free(data);
		return NULL;
	}
	if (size)
		*size = sz;
	return data;
}

void stat_validity_clear(struct stat_validity *sv)
{
	FREE_AND_NULL(sv->sd);
}

int stat_validity_check(struct stat_validity *sv, const char *path)
{
	struct stat st;

	if (stat(path, &st) < 0)
		return sv->sd == NULL;
	if (!sv->sd)
		return 0;
	return S_ISREG(st.st_mode) && !match_stat_data(sv->sd, &st);
}

void stat_validity_update(struct stat_validity *sv, int fd)
{
	struct stat st;

	if (fstat(fd, &st) < 0 || !S_ISREG(st.st_mode))
		stat_validity_clear(sv);
	else {
		if (!sv->sd)
			sv->sd = xcalloc(1, sizeof(struct stat_data));
		fill_stat_data(sv->sd, &st);
	}
}

void move_index_extensions(struct index_state *dst, struct index_state *src)
{
	dst->untracked = src->untracked;
	src->untracked = NULL;
	dst->cache_tree = src->cache_tree;
	src->cache_tree = NULL;
}

struct cache_entry *dup_cache_entry(const struct cache_entry *ce,
				    struct index_state *istate)
{
	unsigned int size = ce_size(ce);
	int mem_pool_allocated;
	struct cache_entry *new_entry = make_empty_cache_entry(istate, ce_namelen(ce));
	mem_pool_allocated = new_entry->mem_pool_allocated;

	memcpy(new_entry, ce, size);
	new_entry->mem_pool_allocated = mem_pool_allocated;
	return new_entry;
}

void discard_cache_entry(struct cache_entry *ce)
{
	if (ce && should_validate_cache_entries())
		memset(ce, 0xCD, cache_entry_size(ce->ce_namelen));

	if (ce && ce->mem_pool_allocated)
		return;

	free(ce);
}

int should_validate_cache_entries(void)
{
	static int validate_index_cache_entries = -1;

	if (validate_index_cache_entries < 0) {
		if (getenv("GIT_TEST_VALIDATE_INDEX_CACHE_ENTRIES"))
			validate_index_cache_entries = 1;
		else
			validate_index_cache_entries = 0;
	}

	return validate_index_cache_entries;
}

#define EOIE_SIZE (4 + GIT_SHA1_RAWSZ) /* <4-byte offset> + <20-byte hash> */
#define EOIE_SIZE_WITH_HEADER (4 + 4 + EOIE_SIZE) /* <4-byte signature> + <4-byte length> + EOIE_SIZE */

static size_t read_eoie_extension(const char *mmap, size_t mmap_size)
{
	/*
	 * The end of index entries (EOIE) extension is guaranteed to be last
	 * so that it can be found by scanning backwards from the EOF.
	 *
	 * "EOIE"
	 * <4-byte length>
	 * <4-byte offset>
	 * <20-byte hash>
	 */
	const char *index, *eoie;
	uint32_t extsize;
	size_t offset, src_offset;
	unsigned char hash[GIT_MAX_RAWSZ];
	git_hash_ctx c;

	/* ensure we have an index big enough to contain an EOIE extension */
	if (mmap_size < sizeof(struct cache_header) + EOIE_SIZE_WITH_HEADER + the_hash_algo->rawsz)
		return 0;

	/* validate the extension signature */
	index = eoie = mmap + mmap_size - EOIE_SIZE_WITH_HEADER - the_hash_algo->rawsz;
	if (CACHE_EXT(index) != CACHE_EXT_ENDOFINDEXENTRIES)
		return 0;
	index += sizeof(uint32_t);

	/* validate the extension size */
	extsize = get_be32(index);
	if (extsize != EOIE_SIZE)
		return 0;
	index += sizeof(uint32_t);

	/*
	 * Validate the offset we're going to look for the first extension
	 * signature is after the index header and before the eoie extension.
	 */
	offset = get_be32(index);
	if (mmap + offset < mmap + sizeof(struct cache_header))
		return 0;
	if (mmap + offset >= eoie)
		return 0;
	index += sizeof(uint32_t);

	/*
	 * The hash is computed over extension types and their sizes (but not
	 * their contents).  E.g. if we have "TREE" extension that is N-bytes
	 * long, "REUC" extension that is M-bytes long, followed by "EOIE",
	 * then the hash would be:
	 *
	 * SHA-1("TREE" + <binary representation of N> +
	 *	 "REUC" + <binary representation of M>)
	 */
	src_offset = offset;
	the_hash_algo->init_fn(&c);
	while (src_offset < mmap_size - the_hash_algo->rawsz - EOIE_SIZE_WITH_HEADER) {
		/* 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, mmap + src_offset + 4, 4);
		extsize = ntohl(extsize);

		/* verify the extension size isn't so large it will wrap around */
		if (src_offset + 8 + extsize < src_offset)
			return 0;

		the_hash_algo->update_fn(&c, mmap + src_offset, 8);

		src_offset += 8;
		src_offset += extsize;
	}
	the_hash_algo->final_fn(hash, &c);
	if (!hasheq(hash, (const unsigned char *)index))
		return 0;

	/* Validate that the extension offsets returned us back to the eoie extension. */
	if (src_offset != mmap_size - the_hash_algo->rawsz - EOIE_SIZE_WITH_HEADER)
		return 0;

	return offset;
}

static void write_eoie_extension(struct strbuf *sb, git_hash_ctx *eoie_context, size_t offset)
{
	uint32_t buffer;
	unsigned char hash[GIT_MAX_RAWSZ];

	/* offset */
	put_be32(&buffer, offset);
	strbuf_add(sb, &buffer, sizeof(uint32_t));

	/* hash */
	the_hash_algo->final_fn(hash, eoie_context);
	strbuf_add(sb, hash, the_hash_algo->rawsz);
}

#define IEOT_VERSION	(1)

static struct index_entry_offset_table *read_ieot_extension(const char *mmap, size_t mmap_size, size_t offset)
{
	const char *index = NULL;
	uint32_t extsize, ext_version;
	struct index_entry_offset_table *ieot;
	int i, nr;

	/* find the IEOT extension */
	if (!offset)
		return NULL;
	while (offset <= mmap_size - the_hash_algo->rawsz - 8) {
		extsize = get_be32(mmap + offset + 4);
		if (CACHE_EXT((mmap + offset)) == CACHE_EXT_INDEXENTRYOFFSETTABLE) {
			index = mmap + offset + 4 + 4;
			break;
		}
		offset += 8;
		offset += extsize;
	}
	if (!index)
		return NULL;

	/* validate the version is IEOT_VERSION */
	ext_version = get_be32(index);
	if (ext_version != IEOT_VERSION) {
		error("invalid IEOT version %d", ext_version);
		return NULL;
	}
	index += sizeof(uint32_t);

	/* extension size - version bytes / bytes per entry */
	nr = (extsize - sizeof(uint32_t)) / (sizeof(uint32_t) + sizeof(uint32_t));
	if (!nr) {
		error("invalid number of IEOT entries %d", nr);
		return NULL;
	}
	ieot = xmalloc(sizeof(struct index_entry_offset_table)
		       + (nr * sizeof(struct index_entry_offset)));
	ieot->nr = nr;
	for (i = 0; i < nr; i++) {
		ieot->entries[i].offset = get_be32(index);
		index += sizeof(uint32_t);
		ieot->entries[i].nr = get_be32(index);
		index += sizeof(uint32_t);
	}

	return ieot;
}

static void write_ieot_extension(struct strbuf *sb, struct index_entry_offset_table *ieot)
{
	uint32_t buffer;
	int i;

	/* version */
	put_be32(&buffer, IEOT_VERSION);
	strbuf_add(sb, &buffer, sizeof(uint32_t));

	/* ieot */
	for (i = 0; i < ieot->nr; i++) {

		/* offset */
		put_be32(&buffer, ieot->entries[i].offset);
		strbuf_add(sb, &buffer, sizeof(uint32_t));

		/* count */
		put_be32(&buffer, ieot->entries[i].nr);
		strbuf_add(sb, &buffer, sizeof(uint32_t));
	}
}