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
|
/*
* GIT - The information manager from hell
*
* Copyright (C) Linus Torvalds, 2005
*
* This handles basic git sha1 object files - packing, unpacking,
* creation etc.
*/
#include "cache.h"
#include "delta.h"
#include "pack.h"
#include "blob.h"
#include "commit.h"
#include "tag.h"
#include "tree.h"
#include "tree-walk.h"
#include "refs.h"
#include "pack-revindex.h"
#include "sha1-lookup.h"
#ifndef O_NOATIME
#if defined(__linux__) && (defined(__i386__) || defined(__PPC__))
#define O_NOATIME 01000000
#else
#define O_NOATIME 0
#endif
#endif
#ifdef NO_C99_FORMAT
#define SZ_FMT "lu"
static unsigned long sz_fmt(size_t s) { return (unsigned long)s; }
#else
#define SZ_FMT "zu"
static size_t sz_fmt(size_t s) { return s; }
#endif
const unsigned char null_sha1[20];
static int git_open_noatime(const char *name, struct packed_git *p);
int safe_create_leading_directories(char *path)
{
char *pos = path + offset_1st_component(path);
struct stat st;
while (pos) {
pos = strchr(pos, '/');
if (!pos)
break;
while (*++pos == '/')
;
if (!*pos)
break;
*--pos = '\0';
if (!stat(path, &st)) {
/* path exists */
if (!S_ISDIR(st.st_mode)) {
*pos = '/';
return -3;
}
}
else if (mkdir(path, 0777)) {
*pos = '/';
return -1;
}
else if (adjust_shared_perm(path)) {
*pos = '/';
return -2;
}
*pos++ = '/';
}
return 0;
}
int safe_create_leading_directories_const(const char *path)
{
/* path points to cache entries, so xstrdup before messing with it */
char *buf = xstrdup(path);
int result = safe_create_leading_directories(buf);
free(buf);
return result;
}
static void fill_sha1_path(char *pathbuf, const unsigned char *sha1)
{
int i;
for (i = 0; i < 20; i++) {
static char hex[] = "0123456789abcdef";
unsigned int val = sha1[i];
char *pos = pathbuf + i*2 + (i > 0);
*pos++ = hex[val >> 4];
*pos = hex[val & 0xf];
}
}
/*
* NOTE! This returns a statically allocated buffer, so you have to be
* careful about using it. Do an "xstrdup()" if you need to save the
* filename.
*
* Also note that this returns the location for creating. Reading
* SHA1 file can happen from any alternate directory listed in the
* DB_ENVIRONMENT environment variable if it is not found in
* the primary object database.
*/
char *sha1_file_name(const unsigned char *sha1)
{
static char buf[PATH_MAX];
const char *objdir;
int len;
objdir = get_object_directory();
len = strlen(objdir);
/* '/' + sha1(2) + '/' + sha1(38) + '\0' */
if (len + 43 > PATH_MAX)
die("insanely long object directory %s", objdir);
memcpy(buf, objdir, len);
buf[len] = '/';
buf[len+3] = '/';
buf[len+42] = '\0';
fill_sha1_path(buf + len + 1, sha1);
return buf;
}
static char *sha1_get_pack_name(const unsigned char *sha1,
char **name, char **base, const char *which)
{
static const char hex[] = "0123456789abcdef";
char *buf;
int i;
if (!*base) {
const char *sha1_file_directory = get_object_directory();
int len = strlen(sha1_file_directory);
*base = xmalloc(len + 60);
sprintf(*base, "%s/pack/pack-1234567890123456789012345678901234567890.%s",
sha1_file_directory, which);
*name = *base + len + 11;
}
buf = *name;
for (i = 0; i < 20; i++) {
unsigned int val = *sha1++;
*buf++ = hex[val >> 4];
*buf++ = hex[val & 0xf];
}
return *base;
}
char *sha1_pack_name(const unsigned char *sha1)
{
static char *name, *base;
return sha1_get_pack_name(sha1, &name, &base, "pack");
}
char *sha1_pack_index_name(const unsigned char *sha1)
{
static char *name, *base;
return sha1_get_pack_name(sha1, &name, &base, "idx");
}
struct alternate_object_database *alt_odb_list;
static struct alternate_object_database **alt_odb_tail;
static void read_info_alternates(const char * alternates, int depth);
/*
* Prepare alternate object database registry.
*
* The variable alt_odb_list points at the list of struct
* alternate_object_database. The elements on this list come from
* non-empty elements from colon separated ALTERNATE_DB_ENVIRONMENT
* environment variable, and $GIT_OBJECT_DIRECTORY/info/alternates,
* whose contents is similar to that environment variable but can be
* LF separated. Its base points at a statically allocated buffer that
* contains "/the/directory/corresponding/to/.git/objects/...", while
* its name points just after the slash at the end of ".git/objects/"
* in the example above, and has enough space to hold 40-byte hex
* SHA1, an extra slash for the first level indirection, and the
* terminating NUL.
*/
static int link_alt_odb_entry(const char * entry, int len, const char * relative_base, int depth)
{
const char *objdir = get_object_directory();
struct alternate_object_database *ent;
struct alternate_object_database *alt;
/* 43 = 40-byte + 2 '/' + terminating NUL */
int pfxlen = len;
int entlen = pfxlen + 43;
int base_len = -1;
if (!is_absolute_path(entry) && relative_base) {
/* Relative alt-odb */
if (base_len < 0)
base_len = strlen(relative_base) + 1;
entlen += base_len;
pfxlen += base_len;
}
ent = xmalloc(sizeof(*ent) + entlen);
if (!is_absolute_path(entry) && relative_base) {
memcpy(ent->base, relative_base, base_len - 1);
ent->base[base_len - 1] = '/';
memcpy(ent->base + base_len, entry, len);
}
else
memcpy(ent->base, entry, pfxlen);
ent->name = ent->base + pfxlen + 1;
ent->base[pfxlen + 3] = '/';
ent->base[pfxlen] = ent->base[entlen-1] = 0;
/* Detect cases where alternate disappeared */
if (!is_directory(ent->base)) {
error("object directory %s does not exist; "
"check .git/objects/info/alternates.",
ent->base);
free(ent);
return -1;
}
/* Prevent the common mistake of listing the same
* thing twice, or object directory itself.
*/
for (alt = alt_odb_list; alt; alt = alt->next) {
if (!memcmp(ent->base, alt->base, pfxlen)) {
free(ent);
return -1;
}
}
if (!memcmp(ent->base, objdir, pfxlen)) {
free(ent);
return -1;
}
/* add the alternate entry */
*alt_odb_tail = ent;
alt_odb_tail = &(ent->next);
ent->next = NULL;
/* recursively add alternates */
read_info_alternates(ent->base, depth + 1);
ent->base[pfxlen] = '/';
return 0;
}
static void link_alt_odb_entries(const char *alt, const char *ep, int sep,
const char *relative_base, int depth)
{
const char *cp, *last;
if (depth > 5) {
error("%s: ignoring alternate object stores, nesting too deep.",
relative_base);
return;
}
last = alt;
while (last < ep) {
cp = last;
if (cp < ep && *cp == '#') {
while (cp < ep && *cp != sep)
cp++;
last = cp + 1;
continue;
}
while (cp < ep && *cp != sep)
cp++;
if (last != cp) {
if (!is_absolute_path(last) && depth) {
error("%s: ignoring relative alternate object store %s",
relative_base, last);
} else {
link_alt_odb_entry(last, cp - last,
relative_base, depth);
}
}
while (cp < ep && *cp == sep)
cp++;
last = cp;
}
}
static void read_info_alternates(const char * relative_base, int depth)
{
char *map;
size_t mapsz;
struct stat st;
const char alt_file_name[] = "info/alternates";
/* Given that relative_base is no longer than PATH_MAX,
ensure that "path" has enough space to append "/", the
file name, "info/alternates", and a trailing NUL. */
char path[PATH_MAX + 1 + sizeof alt_file_name];
int fd;
sprintf(path, "%s/%s", relative_base, alt_file_name);
fd = git_open_noatime(path, NULL);
if (fd < 0)
return;
if (fstat(fd, &st) || (st.st_size == 0)) {
close(fd);
return;
}
mapsz = xsize_t(st.st_size);
map = xmmap(NULL, mapsz, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
link_alt_odb_entries(map, map + mapsz, '\n', relative_base, depth);
munmap(map, mapsz);
}
void add_to_alternates_file(const char *reference)
{
struct lock_file *lock = xcalloc(1, sizeof(struct lock_file));
int fd = hold_lock_file_for_append(lock, git_path("objects/info/alternates"), LOCK_DIE_ON_ERROR);
char *alt = mkpath("%s/objects\n", reference);
write_or_die(fd, alt, strlen(alt));
if (commit_lock_file(lock))
die("could not close alternates file");
if (alt_odb_tail)
link_alt_odb_entries(alt, alt + strlen(alt), '\n', NULL, 0);
}
void foreach_alt_odb(alt_odb_fn fn, void *cb)
{
struct alternate_object_database *ent;
prepare_alt_odb();
for (ent = alt_odb_list; ent; ent = ent->next)
if (fn(ent, cb))
return;
}
void prepare_alt_odb(void)
{
const char *alt;
if (alt_odb_tail)
return;
alt = getenv(ALTERNATE_DB_ENVIRONMENT);
if (!alt) alt = "";
alt_odb_tail = &alt_odb_list;
link_alt_odb_entries(alt, alt + strlen(alt), PATH_SEP, NULL, 0);
read_info_alternates(get_object_directory(), 0);
}
static int has_loose_object_local(const unsigned char *sha1)
{
char *name = sha1_file_name(sha1);
return !access(name, F_OK);
}
int has_loose_object_nonlocal(const unsigned char *sha1)
{
struct alternate_object_database *alt;
prepare_alt_odb();
for (alt = alt_odb_list; alt; alt = alt->next) {
fill_sha1_path(alt->name, sha1);
if (!access(alt->base, F_OK))
return 1;
}
return 0;
}
static int has_loose_object(const unsigned char *sha1)
{
return has_loose_object_local(sha1) ||
has_loose_object_nonlocal(sha1);
}
static unsigned int pack_used_ctr;
static unsigned int pack_mmap_calls;
static unsigned int peak_pack_open_windows;
static unsigned int pack_open_windows;
static size_t peak_pack_mapped;
static size_t pack_mapped;
struct packed_git *packed_git;
void pack_report(void)
{
fprintf(stderr,
"pack_report: getpagesize() = %10" SZ_FMT "\n"
"pack_report: core.packedGitWindowSize = %10" SZ_FMT "\n"
"pack_report: core.packedGitLimit = %10" SZ_FMT "\n",
sz_fmt(getpagesize()),
sz_fmt(packed_git_window_size),
sz_fmt(packed_git_limit));
fprintf(stderr,
"pack_report: pack_used_ctr = %10u\n"
"pack_report: pack_mmap_calls = %10u\n"
"pack_report: pack_open_windows = %10u / %10u\n"
"pack_report: pack_mapped = "
"%10" SZ_FMT " / %10" SZ_FMT "\n",
pack_used_ctr,
pack_mmap_calls,
pack_open_windows, peak_pack_open_windows,
sz_fmt(pack_mapped), sz_fmt(peak_pack_mapped));
}
static int check_packed_git_idx(const char *path, struct packed_git *p)
{
void *idx_map;
struct pack_idx_header *hdr;
size_t idx_size;
uint32_t version, nr, i, *index;
int fd = git_open_noatime(path, p);
struct stat st;
if (fd < 0)
return -1;
if (fstat(fd, &st)) {
close(fd);
return -1;
}
idx_size = xsize_t(st.st_size);
if (idx_size < 4 * 256 + 20 + 20) {
close(fd);
return error("index file %s is too small", path);
}
idx_map = xmmap(NULL, idx_size, PROT_READ, MAP_PRIVATE, fd, 0);
close(fd);
hdr = idx_map;
if (hdr->idx_signature == htonl(PACK_IDX_SIGNATURE)) {
version = ntohl(hdr->idx_version);
if (version < 2 || version > 2) {
munmap(idx_map, idx_size);
return error("index file %s is version %"PRIu32
" and is not supported by this binary"
" (try upgrading GIT to a newer version)",
path, version);
}
} else
version = 1;
nr = 0;
index = idx_map;
if (version > 1)
index += 2; /* skip index header */
for (i = 0; i < 256; i++) {
uint32_t n = ntohl(index[i]);
if (n < nr) {
munmap(idx_map, idx_size);
return error("non-monotonic index %s", path);
}
nr = n;
}
if (version == 1) {
/*
* Total size:
* - 256 index entries 4 bytes each
* - 24-byte entries * nr (20-byte sha1 + 4-byte offset)
* - 20-byte SHA1 of the packfile
* - 20-byte SHA1 file checksum
*/
if (idx_size != 4*256 + nr * 24 + 20 + 20) {
munmap(idx_map, idx_size);
return error("wrong index v1 file size in %s", path);
}
} else if (version == 2) {
/*
* Minimum size:
* - 8 bytes of header
* - 256 index entries 4 bytes each
* - 20-byte sha1 entry * nr
* - 4-byte crc entry * nr
* - 4-byte offset entry * nr
* - 20-byte SHA1 of the packfile
* - 20-byte SHA1 file checksum
* And after the 4-byte offset table might be a
* variable sized table containing 8-byte entries
* for offsets larger than 2^31.
*/
unsigned long min_size = 8 + 4*256 + nr*(20 + 4 + 4) + 20 + 20;
unsigned long max_size = min_size;
if (nr)
max_size += (nr - 1)*8;
if (idx_size < min_size || idx_size > max_size) {
munmap(idx_map, idx_size);
return error("wrong index v2 file size in %s", path);
}
if (idx_size != min_size &&
/*
* make sure we can deal with large pack offsets.
* 31-bit signed offset won't be enough, neither
* 32-bit unsigned one will be.
*/
(sizeof(off_t) <= 4)) {
munmap(idx_map, idx_size);
return error("pack too large for current definition of off_t in %s", path);
}
}
p->index_version = version;
p->index_data = idx_map;
p->index_size = idx_size;
p->num_objects = nr;
return 0;
}
int open_pack_index(struct packed_git *p)
{
char *idx_name;
int ret;
if (p->index_data)
return 0;
idx_name = xstrdup(p->pack_name);
strcpy(idx_name + strlen(idx_name) - strlen(".pack"), ".idx");
ret = check_packed_git_idx(idx_name, p);
free(idx_name);
return ret;
}
static void scan_windows(struct packed_git *p,
struct packed_git **lru_p,
struct pack_window **lru_w,
struct pack_window **lru_l)
{
struct pack_window *w, *w_l;
for (w_l = NULL, w = p->windows; w; w = w->next) {
if (!w->inuse_cnt) {
if (!*lru_w || w->last_used < (*lru_w)->last_used) {
*lru_p = p;
*lru_w = w;
*lru_l = w_l;
}
}
w_l = w;
}
}
static int unuse_one_window(struct packed_git *current, int keep_fd)
{
struct packed_git *p, *lru_p = NULL;
struct pack_window *lru_w = NULL, *lru_l = NULL;
if (current)
scan_windows(current, &lru_p, &lru_w, &lru_l);
for (p = packed_git; p; p = p->next)
scan_windows(p, &lru_p, &lru_w, &lru_l);
if (lru_p) {
munmap(lru_w->base, lru_w->len);
pack_mapped -= lru_w->len;
if (lru_l)
lru_l->next = lru_w->next;
else {
lru_p->windows = lru_w->next;
if (!lru_p->windows && lru_p->pack_fd != keep_fd) {
close(lru_p->pack_fd);
lru_p->pack_fd = -1;
}
}
free(lru_w);
pack_open_windows--;
return 1;
}
return 0;
}
void release_pack_memory(size_t need, int fd)
{
size_t cur = pack_mapped;
while (need >= (cur - pack_mapped) && unuse_one_window(NULL, fd))
; /* nothing */
}
void *xmmap(void *start, size_t length,
int prot, int flags, int fd, off_t offset)
{
void *ret = mmap(start, length, prot, flags, fd, offset);
if (ret == MAP_FAILED) {
if (!length)
return NULL;
release_pack_memory(length, fd);
ret = mmap(start, length, prot, flags, fd, offset);
if (ret == MAP_FAILED)
die_errno("Out of memory? mmap failed");
}
return ret;
}
void close_pack_windows(struct packed_git *p)
{
while (p->windows) {
struct pack_window *w = p->windows;
if (w->inuse_cnt)
die("pack '%s' still has open windows to it",
p->pack_name);
munmap(w->base, w->len);
pack_mapped -= w->len;
pack_open_windows--;
p->windows = w->next;
free(w);
}
}
void unuse_pack(struct pack_window **w_cursor)
{
struct pack_window *w = *w_cursor;
if (w) {
w->inuse_cnt--;
*w_cursor = NULL;
}
}
void close_pack_index(struct packed_git *p)
{
if (p->index_data) {
munmap((void *)p->index_data, p->index_size);
p->index_data = NULL;
}
}
/*
* This is used by git-repack in case a newly created pack happens to
* contain the same set of objects as an existing one. In that case
* the resulting file might be different even if its name would be the
* same. It is best to close any reference to the old pack before it is
* replaced on disk. Of course no index pointers nor windows for given pack
* must subsist at this point. If ever objects from this pack are requested
* again, the new version of the pack will be reinitialized through
* reprepare_packed_git().
*/
void free_pack_by_name(const char *pack_name)
{
struct packed_git *p, **pp = &packed_git;
while (*pp) {
p = *pp;
if (strcmp(pack_name, p->pack_name) == 0) {
clear_delta_base_cache();
close_pack_windows(p);
if (p->pack_fd != -1)
close(p->pack_fd);
close_pack_index(p);
free(p->bad_object_sha1);
*pp = p->next;
free(p);
return;
}
pp = &p->next;
}
}
/*
* Do not call this directly as this leaks p->pack_fd on error return;
* call open_packed_git() instead.
*/
static int open_packed_git_1(struct packed_git *p)
{
struct stat st;
struct pack_header hdr;
unsigned char sha1[20];
unsigned char *idx_sha1;
long fd_flag;
if (!p->index_data && open_pack_index(p))
return error("packfile %s index unavailable", p->pack_name);
p->pack_fd = git_open_noatime(p->pack_name, p);
if (p->pack_fd < 0 || fstat(p->pack_fd, &st))
return -1;
/* If we created the struct before we had the pack we lack size. */
if (!p->pack_size) {
if (!S_ISREG(st.st_mode))
return error("packfile %s not a regular file", p->pack_name);
p->pack_size = st.st_size;
} else if (p->pack_size != st.st_size)
return error("packfile %s size changed", p->pack_name);
/* We leave these file descriptors open with sliding mmap;
* there is no point keeping them open across exec(), though.
*/
fd_flag = fcntl(p->pack_fd, F_GETFD, 0);
if (fd_flag < 0)
return error("cannot determine file descriptor flags");
fd_flag |= FD_CLOEXEC;
if (fcntl(p->pack_fd, F_SETFD, fd_flag) == -1)
return error("cannot set FD_CLOEXEC");
/* Verify we recognize this pack file format. */
if (read_in_full(p->pack_fd, &hdr, sizeof(hdr)) != sizeof(hdr))
return error("file %s is far too short to be a packfile", p->pack_name);
if (hdr.hdr_signature != htonl(PACK_SIGNATURE))
return error("file %s is not a GIT packfile", p->pack_name);
if (!pack_version_ok(hdr.hdr_version))
return error("packfile %s is version %"PRIu32" and not"
" supported (try upgrading GIT to a newer version)",
p->pack_name, ntohl(hdr.hdr_version));
/* Verify the pack matches its index. */
if (p->num_objects != ntohl(hdr.hdr_entries))
return error("packfile %s claims to have %"PRIu32" objects"
" while index indicates %"PRIu32" objects",
p->pack_name, ntohl(hdr.hdr_entries),
p->num_objects);
if (lseek(p->pack_fd, p->pack_size - sizeof(sha1), SEEK_SET) == -1)
return error("end of packfile %s is unavailable", p->pack_name);
if (read_in_full(p->pack_fd, sha1, sizeof(sha1)) != sizeof(sha1))
return error("packfile %s signature is unavailable", p->pack_name);
idx_sha1 = ((unsigned char *)p->index_data) + p->index_size - 40;
if (hashcmp(sha1, idx_sha1))
return error("packfile %s does not match index", p->pack_name);
return 0;
}
static int open_packed_git(struct packed_git *p)
{
if (!open_packed_git_1(p))
return 0;
if (p->pack_fd != -1) {
close(p->pack_fd);
p->pack_fd = -1;
}
return -1;
}
static int in_window(struct pack_window *win, off_t offset)
{
/* We must promise at least 20 bytes (one hash) after the
* offset is available from this window, otherwise the offset
* is not actually in this window and a different window (which
* has that one hash excess) must be used. This is to support
* the object header and delta base parsing routines below.
*/
off_t win_off = win->offset;
return win_off <= offset
&& (offset + 20) <= (win_off + win->len);
}
unsigned char *use_pack(struct packed_git *p,
struct pack_window **w_cursor,
off_t offset,
unsigned int *left)
{
struct pack_window *win = *w_cursor;
if (p->pack_fd == -1 && open_packed_git(p))
die("packfile %s cannot be accessed", p->pack_name);
/* Since packfiles end in a hash of their content and it's
* pointless to ask for an offset into the middle of that
* hash, and the in_window function above wouldn't match
* don't allow an offset too close to the end of the file.
*/
if (offset > (p->pack_size - 20))
die("offset beyond end of packfile (truncated pack?)");
if (!win || !in_window(win, offset)) {
if (win)
win->inuse_cnt--;
for (win = p->windows; win; win = win->next) {
if (in_window(win, offset))
break;
}
if (!win) {
size_t window_align = packed_git_window_size / 2;
off_t len;
win = xcalloc(1, sizeof(*win));
win->offset = (offset / window_align) * window_align;
len = p->pack_size - win->offset;
if (len > packed_git_window_size)
len = packed_git_window_size;
win->len = (size_t)len;
pack_mapped += win->len;
while (packed_git_limit < pack_mapped
&& unuse_one_window(p, p->pack_fd))
; /* nothing */
win->base = xmmap(NULL, win->len,
PROT_READ, MAP_PRIVATE,
p->pack_fd, win->offset);
if (win->base == MAP_FAILED)
die("packfile %s cannot be mapped: %s",
p->pack_name,
strerror(errno));
pack_mmap_calls++;
pack_open_windows++;
if (pack_mapped > peak_pack_mapped)
peak_pack_mapped = pack_mapped;
if (pack_open_windows > peak_pack_open_windows)
peak_pack_open_windows = pack_open_windows;
win->next = p->windows;
p->windows = win;
}
}
if (win != *w_cursor) {
win->last_used = pack_used_ctr++;
win->inuse_cnt++;
*w_cursor = win;
}
offset -= win->offset;
if (left)
*left = win->len - xsize_t(offset);
return win->base + offset;
}
static struct packed_git *alloc_packed_git(int extra)
{
struct packed_git *p = xmalloc(sizeof(*p) + extra);
memset(p, 0, sizeof(*p));
p->pack_fd = -1;
return p;
}
static void try_to_free_pack_memory(size_t size)
{
release_pack_memory(size, -1);
}
struct packed_git *add_packed_git(const char *path, int path_len, int local)
{
static int have_set_try_to_free_routine;
struct stat st;
struct packed_git *p = alloc_packed_git(path_len + 2);
if (!have_set_try_to_free_routine) {
have_set_try_to_free_routine = 1;
set_try_to_free_routine(try_to_free_pack_memory);
}
/*
* Make sure a corresponding .pack file exists and that
* the index looks sane.
*/
path_len -= strlen(".idx");
if (path_len < 1) {
free(p);
return NULL;
}
memcpy(p->pack_name, path, path_len);
strcpy(p->pack_name + path_len, ".keep");
if (!access(p->pack_name, F_OK))
p->pack_keep = 1;
strcpy(p->pack_name + path_len, ".pack");
if (stat(p->pack_name, &st) || !S_ISREG(st.st_mode)) {
free(p);
return NULL;
}
/* ok, it looks sane as far as we can check without
* actually mapping the pack file.
*/
p->pack_size = st.st_size;
p->pack_local = local;
p->mtime = st.st_mtime;
if (path_len < 40 || get_sha1_hex(path + path_len - 40, p->sha1))
hashclr(p->sha1);
return p;
}
struct packed_git *parse_pack_index(unsigned char *sha1, const char *idx_path)
{
const char *path = sha1_pack_name(sha1);
struct packed_git *p = alloc_packed_git(strlen(path) + 1);
strcpy(p->pack_name, path);
hashcpy(p->sha1, sha1);
if (check_packed_git_idx(idx_path, p)) {
free(p);
return NULL;
}
return p;
}
void install_packed_git(struct packed_git *pack)
{
pack->next = packed_git;
packed_git = pack;
}
static void prepare_packed_git_one(char *objdir, int local)
{
/* Ensure that this buffer is large enough so that we can
append "/pack/" without clobbering the stack even if
strlen(objdir) were PATH_MAX. */
char path[PATH_MAX + 1 + 4 + 1 + 1];
int len;
DIR *dir;
struct dirent *de;
sprintf(path, "%s/pack", objdir);
len = strlen(path);
dir = opendir(path);
while (!dir && errno == EMFILE && unuse_one_window(NULL, -1))
dir = opendir(path);
if (!dir) {
if (errno != ENOENT)
error("unable to open object pack directory: %s: %s",
path, strerror(errno));
return;
}
path[len++] = '/';
while ((de = readdir(dir)) != NULL) {
int namelen = strlen(de->d_name);
struct packed_git *p;
if (!has_extension(de->d_name, ".idx"))
continue;
if (len + namelen + 1 > sizeof(path))
continue;
/* Don't reopen a pack we already have. */
strcpy(path + len, de->d_name);
for (p = packed_git; p; p = p->next) {
if (!memcmp(path, p->pack_name, len + namelen - 4))
break;
}
if (p)
continue;
/* See if it really is a valid .idx file with corresponding
* .pack file that we can map.
*/
p = add_packed_git(path, len + namelen, local);
if (!p)
continue;
install_packed_git(p);
}
closedir(dir);
}
static int sort_pack(const void *a_, const void *b_)
{
struct packed_git *a = *((struct packed_git **)a_);
struct packed_git *b = *((struct packed_git **)b_);
int st;
/*
* Local packs tend to contain objects specific to our
* variant of the project than remote ones. In addition,
* remote ones could be on a network mounted filesystem.
* Favor local ones for these reasons.
*/
st = a->pack_local - b->pack_local;
if (st)
return -st;
/*
* Younger packs tend to contain more recent objects,
* and more recent objects tend to get accessed more
* often.
*/
if (a->mtime < b->mtime)
return 1;
else if (a->mtime == b->mtime)
return 0;
return -1;
}
static void rearrange_packed_git(void)
{
struct packed_git **ary, *p;
int i, n;
for (n = 0, p = packed_git; p; p = p->next)
n++;
if (n < 2)
return;
/* prepare an array of packed_git for easier sorting */
ary = xcalloc(n, sizeof(struct packed_git *));
for (n = 0, p = packed_git; p; p = p->next)
ary[n++] = p;
qsort(ary, n, sizeof(struct packed_git *), sort_pack);
/* link them back again */
for (i = 0; i < n - 1; i++)
ary[i]->next = ary[i + 1];
ary[n - 1]->next = NULL;
packed_git = ary[0];
free(ary);
}
static int prepare_packed_git_run_once = 0;
void prepare_packed_git(void)
{
struct alternate_object_database *alt;
if (prepare_packed_git_run_once)
return;
prepare_packed_git_one(get_object_directory(), 1);
prepare_alt_odb();
for (alt = alt_odb_list; alt; alt = alt->next) {
alt->name[-1] = 0;
prepare_packed_git_one(alt->base, 0);
alt->name[-1] = '/';
}
rearrange_packed_git();
prepare_packed_git_run_once = 1;
}
void reprepare_packed_git(void)
{
discard_revindex();
prepare_packed_git_run_once = 0;
prepare_packed_git();
}
static void mark_bad_packed_object(struct packed_git *p,
const unsigned char *sha1)
{
unsigned i;
for (i = 0; i < p->num_bad_objects; i++)
if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
return;
p->bad_object_sha1 = xrealloc(p->bad_object_sha1, 20 * (p->num_bad_objects + 1));
hashcpy(p->bad_object_sha1 + 20 * p->num_bad_objects, sha1);
p->num_bad_objects++;
}
static const struct packed_git *has_packed_and_bad(const unsigned char *sha1)
{
struct packed_git *p;
unsigned i;
for (p = packed_git; p; p = p->next)
for (i = 0; i < p->num_bad_objects; i++)
if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
return p;
return NULL;
}
int check_sha1_signature(const unsigned char *sha1, void *map, unsigned long size, const char *type)
{
unsigned char real_sha1[20];
hash_sha1_file(map, size, type, real_sha1);
return hashcmp(sha1, real_sha1) ? -1 : 0;
}
static int git_open_noatime(const char *name, struct packed_git *p)
{
static int sha1_file_open_flag = O_NOATIME;
for (;;) {
int fd = open(name, O_RDONLY | sha1_file_open_flag);
if (fd >= 0)
return fd;
/* Might the failure be insufficient file descriptors? */
if (errno == EMFILE) {
if (unuse_one_window(p, -1))
continue;
else
return -1;
}
/* Might the failure be due to O_NOATIME? */
if (errno != ENOENT && sha1_file_open_flag) {
sha1_file_open_flag = 0;
continue;
}
return -1;
}
}
static int open_sha1_file(const unsigned char *sha1)
{
int fd;
char *name = sha1_file_name(sha1);
struct alternate_object_database *alt;
fd = git_open_noatime(name, NULL);
if (fd >= 0)
return fd;
prepare_alt_odb();
errno = ENOENT;
for (alt = alt_odb_list; alt; alt = alt->next) {
name = alt->name;
fill_sha1_path(name, sha1);
fd = git_open_noatime(alt->base, NULL);
if (fd >= 0)
return fd;
}
return -1;
}
static void *map_sha1_file(const unsigned char *sha1, unsigned long *size)
{
void *map;
int fd;
fd = open_sha1_file(sha1);
map = NULL;
if (fd >= 0) {
struct stat st;
if (!fstat(fd, &st)) {
*size = xsize_t(st.st_size);
map = xmmap(NULL, *size, PROT_READ, MAP_PRIVATE, fd, 0);
}
close(fd);
}
return map;
}
static int legacy_loose_object(unsigned char *map)
{
unsigned int word;
/*
* Is it a zlib-compressed buffer? If so, the first byte
* must be 0x78 (15-bit window size, deflated), and the
* first 16-bit word is evenly divisible by 31
*/
word = (map[0] << 8) + map[1];
if (map[0] == 0x78 && !(word % 31))
return 1;
else
return 0;
}
unsigned long unpack_object_header_buffer(const unsigned char *buf,
unsigned long len, enum object_type *type, unsigned long *sizep)
{
unsigned shift;
unsigned long size, c;
unsigned long used = 0;
c = buf[used++];
*type = (c >> 4) & 7;
size = c & 15;
shift = 4;
while (c & 0x80) {
if (len <= used || bitsizeof(long) <= shift) {
error("bad object header");
return 0;
}
c = buf[used++];
size += (c & 0x7f) << shift;
shift += 7;
}
*sizep = size;
return used;
}
static int unpack_sha1_header(z_stream *stream, unsigned char *map, unsigned long mapsize, void *buffer, unsigned long bufsiz)
{
unsigned long size, used;
static const char valid_loose_object_type[8] = {
0, /* OBJ_EXT */
1, 1, 1, 1, /* "commit", "tree", "blob", "tag" */
0, /* "delta" and others are invalid in a loose object */
};
enum object_type type;
/* Get the data stream */
memset(stream, 0, sizeof(*stream));
stream->next_in = map;
stream->avail_in = mapsize;
stream->next_out = buffer;
stream->avail_out = bufsiz;
if (legacy_loose_object(map)) {
git_inflate_init(stream);
return git_inflate(stream, 0);
}
/*
* There used to be a second loose object header format which
* was meant to mimic the in-pack format, allowing for direct
* copy of the object data. This format turned up not to be
* really worth it and we don't write it any longer. But we
* can still read it.
*/
used = unpack_object_header_buffer(map, mapsize, &type, &size);
if (!used || !valid_loose_object_type[type])
return -1;
map += used;
mapsize -= used;
/* Set up the stream for the rest.. */
stream->next_in = map;
stream->avail_in = mapsize;
git_inflate_init(stream);
/* And generate the fake traditional header */
stream->total_out = 1 + snprintf(buffer, bufsiz, "%s %lu",
typename(type), size);
return 0;
}
static void *unpack_sha1_rest(z_stream *stream, void *buffer, unsigned long size, const unsigned char *sha1)
{
int bytes = strlen(buffer) + 1;
unsigned char *buf = xmallocz(size);
unsigned long n;
int status = Z_OK;
n = stream->total_out - bytes;
if (n > size)
n = size;
memcpy(buf, (char *) buffer + bytes, n);
bytes = n;
if (bytes <= size) {
/*
* The above condition must be (bytes <= size), not
* (bytes < size). In other words, even though we
* expect no more output and set avail_out to zer0,
* the input zlib stream may have bytes that express
* "this concludes the stream", and we *do* want to
* eat that input.
*
* Otherwise we would not be able to test that we
* consumed all the input to reach the expected size;
* we also want to check that zlib tells us that all
* went well with status == Z_STREAM_END at the end.
*/
stream->next_out = buf + bytes;
stream->avail_out = size - bytes;
while (status == Z_OK)
status = git_inflate(stream, Z_FINISH);
}
if (status == Z_STREAM_END && !stream->avail_in) {
git_inflate_end(stream);
return buf;
}
if (status < 0)
error("corrupt loose object '%s'", sha1_to_hex(sha1));
else if (stream->avail_in)
error("garbage at end of loose object '%s'",
sha1_to_hex(sha1));
free(buf);
return NULL;
}
/*
* We used to just use "sscanf()", but that's actually way
* too permissive for what we want to check. So do an anal
* object header parse by hand.
*/
static int parse_sha1_header(const char *hdr, unsigned long *sizep)
{
char type[10];
int i;
unsigned long size;
/*
* The type can be at most ten bytes (including the
* terminating '\0' that we add), and is followed by
* a space.
*/
i = 0;
for (;;) {
char c = *hdr++;
if (c == ' ')
break;
type[i++] = c;
if (i >= sizeof(type))
return -1;
}
type[i] = 0;
/*
* The length must follow immediately, and be in canonical
* decimal format (ie "010" is not valid).
*/
size = *hdr++ - '0';
if (size > 9)
return -1;
if (size) {
for (;;) {
unsigned long c = *hdr - '0';
if (c > 9)
break;
hdr++;
size = size * 10 + c;
}
}
*sizep = size;
/*
* The length must be followed by a zero byte
*/
return *hdr ? -1 : type_from_string(type);
}
static void *unpack_sha1_file(void *map, unsigned long mapsize, enum object_type *type, unsigned long *size, const unsigned char *sha1)
{
int ret;
z_stream stream;
char hdr[8192];
ret = unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr));
if (ret < Z_OK || (*type = parse_sha1_header(hdr, size)) < 0)
return NULL;
return unpack_sha1_rest(&stream, hdr, *size, sha1);
}
unsigned long get_size_from_delta(struct packed_git *p,
struct pack_window **w_curs,
off_t curpos)
{
const unsigned char *data;
unsigned char delta_head[20], *in;
z_stream stream;
int st;
memset(&stream, 0, sizeof(stream));
stream.next_out = delta_head;
stream.avail_out = sizeof(delta_head);
git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
st = git_inflate(&stream, Z_FINISH);
curpos += stream.next_in - in;
} while ((st == Z_OK || st == Z_BUF_ERROR) &&
stream.total_out < sizeof(delta_head));
git_inflate_end(&stream);
if ((st != Z_STREAM_END) && stream.total_out != sizeof(delta_head)) {
error("delta data unpack-initial failed");
return 0;
}
/* Examine the initial part of the delta to figure out
* the result size.
*/
data = delta_head;
/* ignore base size */
get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
/* Read the result size */
return get_delta_hdr_size(&data, delta_head+sizeof(delta_head));
}
static off_t get_delta_base(struct packed_git *p,
struct pack_window **w_curs,
off_t *curpos,
enum object_type type,
off_t delta_obj_offset)
{
unsigned char *base_info = use_pack(p, w_curs, *curpos, NULL);
off_t base_offset;
/* use_pack() assured us we have [base_info, base_info + 20)
* as a range that we can look at without walking off the
* end of the mapped window. Its actually the hash size
* that is assured. An OFS_DELTA longer than the hash size
* is stupid, as then a REF_DELTA would be smaller to store.
*/
if (type == OBJ_OFS_DELTA) {
unsigned used = 0;
unsigned char c = base_info[used++];
base_offset = c & 127;
while (c & 128) {
base_offset += 1;
if (!base_offset || MSB(base_offset, 7))
return 0; /* overflow */
c = base_info[used++];
base_offset = (base_offset << 7) + (c & 127);
}
base_offset = delta_obj_offset - base_offset;
if (base_offset <= 0 || base_offset >= delta_obj_offset)
return 0; /* out of bound */
*curpos += used;
} else if (type == OBJ_REF_DELTA) {
/* The base entry _must_ be in the same pack */
base_offset = find_pack_entry_one(base_info, p);
*curpos += 20;
} else
die("I am totally screwed");
return base_offset;
}
/* forward declaration for a mutually recursive function */
static int packed_object_info(struct packed_git *p, off_t offset,
unsigned long *sizep);
static int packed_delta_info(struct packed_git *p,
struct pack_window **w_curs,
off_t curpos,
enum object_type type,
off_t obj_offset,
unsigned long *sizep)
{
off_t base_offset;
base_offset = get_delta_base(p, w_curs, &curpos, type, obj_offset);
if (!base_offset)
return OBJ_BAD;
type = packed_object_info(p, base_offset, NULL);
if (type <= OBJ_NONE) {
struct revindex_entry *revidx;
const unsigned char *base_sha1;
revidx = find_pack_revindex(p, base_offset);
if (!revidx)
return OBJ_BAD;
base_sha1 = nth_packed_object_sha1(p, revidx->nr);
mark_bad_packed_object(p, base_sha1);
type = sha1_object_info(base_sha1, NULL);
if (type <= OBJ_NONE)
return OBJ_BAD;
}
/* We choose to only get the type of the base object and
* ignore potentially corrupt pack file that expects the delta
* based on a base with a wrong size. This saves tons of
* inflate() calls.
*/
if (sizep) {
*sizep = get_size_from_delta(p, w_curs, curpos);
if (*sizep == 0)
type = OBJ_BAD;
}
return type;
}
static int unpack_object_header(struct packed_git *p,
struct pack_window **w_curs,
off_t *curpos,
unsigned long *sizep)
{
unsigned char *base;
unsigned int left;
unsigned long used;
enum object_type type;
/* use_pack() assures us we have [base, base + 20) available
* as a range that we can look at at. (Its actually the hash
* size that is assured.) With our object header encoding
* the maximum deflated object size is 2^137, which is just
* insane, so we know won't exceed what we have been given.
*/
base = use_pack(p, w_curs, *curpos, &left);
used = unpack_object_header_buffer(base, left, &type, sizep);
if (!used) {
type = OBJ_BAD;
} else
*curpos += used;
return type;
}
const char *packed_object_info_detail(struct packed_git *p,
off_t obj_offset,
unsigned long *size,
unsigned long *store_size,
unsigned int *delta_chain_length,
unsigned char *base_sha1)
{
struct pack_window *w_curs = NULL;
off_t curpos;
unsigned long dummy;
unsigned char *next_sha1;
enum object_type type;
struct revindex_entry *revidx;
*delta_chain_length = 0;
curpos = obj_offset;
type = unpack_object_header(p, &w_curs, &curpos, size);
revidx = find_pack_revindex(p, obj_offset);
*store_size = revidx[1].offset - obj_offset;
for (;;) {
switch (type) {
default:
die("pack %s contains unknown object type %d",
p->pack_name, type);
case OBJ_COMMIT:
case OBJ_TREE:
case OBJ_BLOB:
case OBJ_TAG:
unuse_pack(&w_curs);
return typename(type);
case OBJ_OFS_DELTA:
obj_offset = get_delta_base(p, &w_curs, &curpos, type, obj_offset);
if (!obj_offset)
die("pack %s contains bad delta base reference of type %s",
p->pack_name, typename(type));
if (*delta_chain_length == 0) {
revidx = find_pack_revindex(p, obj_offset);
hashcpy(base_sha1, nth_packed_object_sha1(p, revidx->nr));
}
break;
case OBJ_REF_DELTA:
next_sha1 = use_pack(p, &w_curs, curpos, NULL);
if (*delta_chain_length == 0)
hashcpy(base_sha1, next_sha1);
obj_offset = find_pack_entry_one(next_sha1, p);
break;
}
(*delta_chain_length)++;
curpos = obj_offset;
type = unpack_object_header(p, &w_curs, &curpos, &dummy);
}
}
static int packed_object_info(struct packed_git *p, off_t obj_offset,
unsigned long *sizep)
{
struct pack_window *w_curs = NULL;
unsigned long size;
off_t curpos = obj_offset;
enum object_type type;
type = unpack_object_header(p, &w_curs, &curpos, &size);
switch (type) {
case OBJ_OFS_DELTA:
case OBJ_REF_DELTA:
type = packed_delta_info(p, &w_curs, curpos,
type, obj_offset, sizep);
break;
case OBJ_COMMIT:
case OBJ_TREE:
case OBJ_BLOB:
case OBJ_TAG:
if (sizep)
*sizep = size;
break;
default:
error("unknown object type %i at offset %"PRIuMAX" in %s",
type, (uintmax_t)obj_offset, p->pack_name);
type = OBJ_BAD;
}
unuse_pack(&w_curs);
return type;
}
static void *unpack_compressed_entry(struct packed_git *p,
struct pack_window **w_curs,
off_t curpos,
unsigned long size)
{
int st;
z_stream stream;
unsigned char *buffer, *in;
buffer = xmallocz(size);
memset(&stream, 0, sizeof(stream));
stream.next_out = buffer;
stream.avail_out = size + 1;
git_inflate_init(&stream);
do {
in = use_pack(p, w_curs, curpos, &stream.avail_in);
stream.next_in = in;
st = git_inflate(&stream, Z_FINISH);
if (!stream.avail_out)
break; /* the payload is larger than it should be */
curpos += stream.next_in - in;
} while (st == Z_OK || st == Z_BUF_ERROR);
git_inflate_end(&stream);
if ((st != Z_STREAM_END) || stream.total_out != size) {
free(buffer);
return NULL;
}
return buffer;
}
#define MAX_DELTA_CACHE (256)
static size_t delta_base_cached;
static struct delta_base_cache_lru_list {
struct delta_base_cache_lru_list *prev;
struct delta_base_cache_lru_list *next;
} delta_base_cache_lru = { &delta_base_cache_lru, &delta_base_cache_lru };
static struct delta_base_cache_entry {
struct delta_base_cache_lru_list lru;
void *data;
struct packed_git *p;
off_t base_offset;
unsigned long size;
enum object_type type;
} delta_base_cache[MAX_DELTA_CACHE];
static unsigned long pack_entry_hash(struct packed_git *p, off_t base_offset)
{
unsigned long hash;
hash = (unsigned long)p + (unsigned long)base_offset;
hash += (hash >> 8) + (hash >> 16);
return hash % MAX_DELTA_CACHE;
}
static void *cache_or_unpack_entry(struct packed_git *p, off_t base_offset,
unsigned long *base_size, enum object_type *type, int keep_cache)
{
void *ret;
unsigned long hash = pack_entry_hash(p, base_offset);
struct delta_base_cache_entry *ent = delta_base_cache + hash;
ret = ent->data;
if (!ret || ent->p != p || ent->base_offset != base_offset)
return unpack_entry(p, base_offset, type, base_size);
if (!keep_cache) {
ent->data = NULL;
ent->lru.next->prev = ent->lru.prev;
ent->lru.prev->next = ent->lru.next;
delta_base_cached -= ent->size;
} else {
ret = xmemdupz(ent->data, ent->size);
}
*type = ent->type;
*base_size = ent->size;
return ret;
}
static inline void release_delta_base_cache(struct delta_base_cache_entry *ent)
{
if (ent->data) {
free(ent->data);
ent->data = NULL;
ent->lru.next->prev = ent->lru.prev;
ent->lru.prev->next = ent->lru.next;
delta_base_cached -= ent->size;
}
}
void clear_delta_base_cache(void)
{
unsigned long p;
for (p = 0; p < MAX_DELTA_CACHE; p++)
release_delta_base_cache(&delta_base_cache[p]);
}
static void add_delta_base_cache(struct packed_git *p, off_t base_offset,
void *base, unsigned long base_size, enum object_type type)
{
unsigned long hash = pack_entry_hash(p, base_offset);
struct delta_base_cache_entry *ent = delta_base_cache + hash;
struct delta_base_cache_lru_list *lru;
release_delta_base_cache(ent);
delta_base_cached += base_size;
for (lru = delta_base_cache_lru.next;
delta_base_cached > delta_base_cache_limit
&& lru != &delta_base_cache_lru;
lru = lru->next) {
struct delta_base_cache_entry *f = (void *)lru;
if (f->type == OBJ_BLOB)
release_delta_base_cache(f);
}
for (lru = delta_base_cache_lru.next;
delta_base_cached > delta_base_cache_limit
&& lru != &delta_base_cache_lru;
lru = lru->next) {
struct delta_base_cache_entry *f = (void *)lru;
release_delta_base_cache(f);
}
ent->p = p;
ent->base_offset = base_offset;
ent->type = type;
ent->data = base;
ent->size = base_size;
ent->lru.next = &delta_base_cache_lru;
ent->lru.prev = delta_base_cache_lru.prev;
delta_base_cache_lru.prev->next = &ent->lru;
delta_base_cache_lru.prev = &ent->lru;
}
static void *read_object(const unsigned char *sha1, enum object_type *type,
unsigned long *size);
static void *unpack_delta_entry(struct packed_git *p,
struct pack_window **w_curs,
off_t curpos,
unsigned long delta_size,
off_t obj_offset,
enum object_type *type,
unsigned long *sizep)
{
void *delta_data, *result, *base;
unsigned long base_size;
off_t base_offset;
base_offset = get_delta_base(p, w_curs, &curpos, *type, obj_offset);
if (!base_offset) {
error("failed to validate delta base reference "
"at offset %"PRIuMAX" from %s",
(uintmax_t)curpos, p->pack_name);
return NULL;
}
unuse_pack(w_curs);
base = cache_or_unpack_entry(p, base_offset, &base_size, type, 0);
if (!base) {
/*
* We're probably in deep shit, but let's try to fetch
* the required base anyway from another pack or loose.
* This is costly but should happen only in the presence
* of a corrupted pack, and is better than failing outright.
*/
struct revindex_entry *revidx;
const unsigned char *base_sha1;
revidx = find_pack_revindex(p, base_offset);
if (!revidx)
return NULL;
base_sha1 = nth_packed_object_sha1(p, revidx->nr);
error("failed to read delta base object %s"
" at offset %"PRIuMAX" from %s",
sha1_to_hex(base_sha1), (uintmax_t)base_offset,
p->pack_name);
mark_bad_packed_object(p, base_sha1);
base = read_object(base_sha1, type, &base_size);
if (!base)
return NULL;
}
delta_data = unpack_compressed_entry(p, w_curs, curpos, delta_size);
if (!delta_data) {
error("failed to unpack compressed delta "
"at offset %"PRIuMAX" from %s",
(uintmax_t)curpos, p->pack_name);
free(base);
return NULL;
}
result = patch_delta(base, base_size,
delta_data, delta_size,
sizep);
if (!result)
die("failed to apply delta");
free(delta_data);
add_delta_base_cache(p, base_offset, base, base_size, *type);
return result;
}
int do_check_packed_object_crc;
void *unpack_entry(struct packed_git *p, off_t obj_offset,
enum object_type *type, unsigned long *sizep)
{
struct pack_window *w_curs = NULL;
off_t curpos = obj_offset;
void *data;
if (do_check_packed_object_crc && p->index_version > 1) {
struct revindex_entry *revidx = find_pack_revindex(p, obj_offset);
unsigned long len = revidx[1].offset - obj_offset;
if (check_pack_crc(p, &w_curs, obj_offset, len, revidx->nr)) {
const unsigned char *sha1 =
nth_packed_object_sha1(p, revidx->nr);
error("bad packed object CRC for %s",
sha1_to_hex(sha1));
mark_bad_packed_object(p, sha1);
unuse_pack(&w_curs);
return NULL;
}
}
*type = unpack_object_header(p, &w_curs, &curpos, sizep);
switch (*type) {
case OBJ_OFS_DELTA:
case OBJ_REF_DELTA:
data = unpack_delta_entry(p, &w_curs, curpos, *sizep,
obj_offset, type, sizep);
break;
case OBJ_COMMIT:
case OBJ_TREE:
case OBJ_BLOB:
case OBJ_TAG:
data = unpack_compressed_entry(p, &w_curs, curpos, *sizep);
break;
default:
data = NULL;
error("unknown object type %i at offset %"PRIuMAX" in %s",
*type, (uintmax_t)obj_offset, p->pack_name);
}
unuse_pack(&w_curs);
return data;
}
const unsigned char *nth_packed_object_sha1(struct packed_git *p,
uint32_t n)
{
const unsigned char *index = p->index_data;
if (!index) {
if (open_pack_index(p))
return NULL;
index = p->index_data;
}
if (n >= p->num_objects)
return NULL;
index += 4 * 256;
if (p->index_version == 1) {
return index + 24 * n + 4;
} else {
index += 8;
return index + 20 * n;
}
}
off_t nth_packed_object_offset(const struct packed_git *p, uint32_t n)
{
const unsigned char *index = p->index_data;
index += 4 * 256;
if (p->index_version == 1) {
return ntohl(*((uint32_t *)(index + 24 * n)));
} else {
uint32_t off;
index += 8 + p->num_objects * (20 + 4);
off = ntohl(*((uint32_t *)(index + 4 * n)));
if (!(off & 0x80000000))
return off;
index += p->num_objects * 4 + (off & 0x7fffffff) * 8;
return (((uint64_t)ntohl(*((uint32_t *)(index + 0)))) << 32) |
ntohl(*((uint32_t *)(index + 4)));
}
}
off_t find_pack_entry_one(const unsigned char *sha1,
struct packed_git *p)
{
const uint32_t *level1_ofs = p->index_data;
const unsigned char *index = p->index_data;
unsigned hi, lo, stride;
static int use_lookup = -1;
static int debug_lookup = -1;
if (debug_lookup < 0)
debug_lookup = !!getenv("GIT_DEBUG_LOOKUP");
if (!index) {
if (open_pack_index(p))
return 0;
level1_ofs = p->index_data;
index = p->index_data;
}
if (p->index_version > 1) {
level1_ofs += 2;
index += 8;
}
index += 4 * 256;
hi = ntohl(level1_ofs[*sha1]);
lo = ((*sha1 == 0x0) ? 0 : ntohl(level1_ofs[*sha1 - 1]));
if (p->index_version > 1) {
stride = 20;
} else {
stride = 24;
index += 4;
}
if (debug_lookup)
printf("%02x%02x%02x... lo %u hi %u nr %"PRIu32"\n",
sha1[0], sha1[1], sha1[2], lo, hi, p->num_objects);
if (use_lookup < 0)
use_lookup = !!getenv("GIT_USE_LOOKUP");
if (use_lookup) {
int pos = sha1_entry_pos(index, stride, 0,
lo, hi, p->num_objects, sha1);
if (pos < 0)
return 0;
return nth_packed_object_offset(p, pos);
}
do {
unsigned mi = (lo + hi) / 2;
int cmp = hashcmp(index + mi * stride, sha1);
if (debug_lookup)
printf("lo %u hi %u rg %u mi %u\n",
lo, hi, hi - lo, mi);
if (!cmp)
return nth_packed_object_offset(p, mi);
if (cmp > 0)
hi = mi;
else
lo = mi+1;
} while (lo < hi);
return 0;
}
static int find_pack_entry(const unsigned char *sha1, struct pack_entry *e)
{
static struct packed_git *last_found = (void *)1;
struct packed_git *p;
off_t offset;
prepare_packed_git();
if (!packed_git)
return 0;
p = (last_found == (void *)1) ? packed_git : last_found;
do {
if (p->num_bad_objects) {
unsigned i;
for (i = 0; i < p->num_bad_objects; i++)
if (!hashcmp(sha1, p->bad_object_sha1 + 20 * i))
goto next;
}
offset = find_pack_entry_one(sha1, p);
if (offset) {
/*
* We are about to tell the caller where they can
* locate the requested object. We better make
* sure the packfile is still here and can be
* accessed before supplying that answer, as
* it may have been deleted since the index
* was loaded!
*/
if (p->pack_fd == -1 && open_packed_git(p)) {
error("packfile %s cannot be accessed", p->pack_name);
goto next;
}
e->offset = offset;
e->p = p;
hashcpy(e->sha1, sha1);
last_found = p;
return 1;
}
next:
if (p == last_found)
p = packed_git;
else
p = p->next;
if (p == last_found)
p = p->next;
} while (p);
return 0;
}
struct packed_git *find_sha1_pack(const unsigned char *sha1,
struct packed_git *packs)
{
struct packed_git *p;
for (p = packs; p; p = p->next) {
if (find_pack_entry_one(sha1, p))
return p;
}
return NULL;
}
static int sha1_loose_object_info(const unsigned char *sha1, unsigned long *sizep)
{
int status;
unsigned long mapsize, size;
void *map;
z_stream stream;
char hdr[32];
map = map_sha1_file(sha1, &mapsize);
if (!map)
return error("unable to find %s", sha1_to_hex(sha1));
if (unpack_sha1_header(&stream, map, mapsize, hdr, sizeof(hdr)) < 0)
status = error("unable to unpack %s header",
sha1_to_hex(sha1));
else if ((status = parse_sha1_header(hdr, &size)) < 0)
status = error("unable to parse %s header", sha1_to_hex(sha1));
else if (sizep)
*sizep = size;
git_inflate_end(&stream);
munmap(map, mapsize);
return status;
}
int sha1_object_info(const unsigned char *sha1, unsigned long *sizep)
{
struct pack_entry e;
int status;
if (!find_pack_entry(sha1, &e)) {
/* Most likely it's a loose object. */
status = sha1_loose_object_info(sha1, sizep);
if (status >= 0)
return status;
/* Not a loose object; someone else may have just packed it. */
reprepare_packed_git();
if (!find_pack_entry(sha1, &e))
return status;
}
status = packed_object_info(e.p, e.offset, sizep);
if (status < 0) {
mark_bad_packed_object(e.p, sha1);
status = sha1_object_info(sha1, sizep);
}
return status;
}
static void *read_packed_sha1(const unsigned char *sha1,
enum object_type *type, unsigned long *size)
{
struct pack_entry e;
void *data;
if (!find_pack_entry(sha1, &e))
return NULL;
data = cache_or_unpack_entry(e.p, e.offset, size, type, 1);
if (!data) {
/*
* We're probably in deep shit, but let's try to fetch
* the required object anyway from another pack or loose.
* This should happen only in the presence of a corrupted
* pack, and is better than failing outright.
*/
error("failed to read object %s at offset %"PRIuMAX" from %s",
sha1_to_hex(sha1), (uintmax_t)e.offset, e.p->pack_name);
mark_bad_packed_object(e.p, sha1);
data = read_object(sha1, type, size);
}
return data;
}
/*
* This is meant to hold a *small* number of objects that you would
* want read_sha1_file() to be able to return, but yet you do not want
* to write them into the object store (e.g. a browse-only
* application).
*/
static struct cached_object {
unsigned char sha1[20];
enum object_type type;
void *buf;
unsigned long size;
} *cached_objects;
static int cached_object_nr, cached_object_alloc;
static struct cached_object empty_tree = {
EMPTY_TREE_SHA1_BIN,
OBJ_TREE,
"",
0
};
static struct cached_object *find_cached_object(const unsigned char *sha1)
{
int i;
struct cached_object *co = cached_objects;
for (i = 0; i < cached_object_nr; i++, co++) {
if (!hashcmp(co->sha1, sha1))
return co;
}
if (!hashcmp(sha1, empty_tree.sha1))
return &empty_tree;
return NULL;
}
int pretend_sha1_file(void *buf, unsigned long len, enum object_type type,
unsigned char *sha1)
{
struct cached_object *co;
hash_sha1_file(buf, len, typename(type), sha1);
if (has_sha1_file(sha1) || find_cached_object(sha1))
return 0;
if (cached_object_alloc <= cached_object_nr) {
cached_object_alloc = alloc_nr(cached_object_alloc);
cached_objects = xrealloc(cached_objects,
sizeof(*cached_objects) *
cached_object_alloc);
}
co = &cached_objects[cached_object_nr++];
co->size = len;
co->type = type;
co->buf = xmalloc(len);
memcpy(co->buf, buf, len);
hashcpy(co->sha1, sha1);
return 0;
}
static void *read_object(const unsigned char *sha1, enum object_type *type,
unsigned long *size)
{
unsigned long mapsize;
void *map, *buf;
struct cached_object *co;
co = find_cached_object(sha1);
if (co) {
*type = co->type;
*size = co->size;
return xmemdupz(co->buf, co->size);
}
buf = read_packed_sha1(sha1, type, size);
if (buf)
return buf;
map = map_sha1_file(sha1, &mapsize);
if (map) {
buf = unpack_sha1_file(map, mapsize, type, size, sha1);
munmap(map, mapsize);
return buf;
}
reprepare_packed_git();
return read_packed_sha1(sha1, type, size);
}
/*
* This function dies on corrupt objects; the callers who want to
* deal with them should arrange to call read_object() and give error
* messages themselves.
*/
void *read_sha1_file_repl(const unsigned char *sha1,
enum object_type *type,
unsigned long *size,
const unsigned char **replacement)
{
const unsigned char *repl = lookup_replace_object(sha1);
void *data;
char *path;
const struct packed_git *p;
errno = 0;
data = read_object(repl, type, size);
if (data) {
if (replacement)
*replacement = repl;
return data;
}
if (errno && errno != ENOENT)
die_errno("failed to read object %s", sha1_to_hex(sha1));
/* die if we replaced an object with one that does not exist */
if (repl != sha1)
die("replacement %s not found for %s",
sha1_to_hex(repl), sha1_to_hex(sha1));
if (has_loose_object(repl)) {
path = sha1_file_name(sha1);
die("loose object %s (stored in %s) is corrupt",
sha1_to_hex(repl), path);
}
if ((p = has_packed_and_bad(repl)) != NULL)
die("packed object %s (stored in %s) is corrupt",
sha1_to_hex(repl), p->pack_name);
return NULL;
}
void *read_object_with_reference(const unsigned char *sha1,
const char *required_type_name,
unsigned long *size,
unsigned char *actual_sha1_return)
{
enum object_type type, required_type;
void *buffer;
unsigned long isize;
unsigned char actual_sha1[20];
required_type = type_from_string(required_type_name);
hashcpy(actual_sha1, sha1);
while (1) {
int ref_length = -1;
const char *ref_type = NULL;
buffer = read_sha1_file(actual_sha1, &type, &isize);
if (!buffer)
return NULL;
if (type == required_type) {
*size = isize;
if (actual_sha1_return)
hashcpy(actual_sha1_return, actual_sha1);
return buffer;
}
/* Handle references */
else if (type == OBJ_COMMIT)
ref_type = "tree ";
else if (type == OBJ_TAG)
ref_type = "object ";
else {
free(buffer);
return NULL;
}
ref_length = strlen(ref_type);
if (ref_length + 40 > isize ||
memcmp(buffer, ref_type, ref_length) ||
get_sha1_hex((char *) buffer + ref_length, actual_sha1)) {
free(buffer);
return NULL;
}
free(buffer);
/* Now we have the ID of the referred-to object in
* actual_sha1. Check again. */
}
}
static void write_sha1_file_prepare(const void *buf, unsigned long len,
const char *type, unsigned char *sha1,
char *hdr, int *hdrlen)
{
git_SHA_CTX c;
/* Generate the header */
*hdrlen = sprintf(hdr, "%s %lu", type, len)+1;
/* Sha1.. */
git_SHA1_Init(&c);
git_SHA1_Update(&c, hdr, *hdrlen);
git_SHA1_Update(&c, buf, len);
git_SHA1_Final(sha1, &c);
}
/*
* Move the just written object into its final resting place.
* NEEDSWORK: this should be renamed to finalize_temp_file() as
* "moving" is only a part of what it does, when no patch between
* master to pu changes the call sites of this function.
*/
int move_temp_to_file(const char *tmpfile, const char *filename)
{
int ret = 0;
if (object_creation_mode == OBJECT_CREATION_USES_RENAMES)
goto try_rename;
else if (link(tmpfile, filename))
ret = errno;
/*
* Coda hack - coda doesn't like cross-directory links,
* so we fall back to a rename, which will mean that it
* won't be able to check collisions, but that's not a
* big deal.
*
* The same holds for FAT formatted media.
*
* When this succeeds, we just return. We have nothing
* left to unlink.
*/
if (ret && ret != EEXIST) {
try_rename:
if (!rename(tmpfile, filename))
goto out;
ret = errno;
}
unlink_or_warn(tmpfile);
if (ret) {
if (ret != EEXIST) {
return error("unable to write sha1 filename %s: %s\n", filename, strerror(ret));
}
/* FIXME!!! Collision check here ? */
}
out:
if (adjust_shared_perm(filename))
return error("unable to set permission to '%s'", filename);
return 0;
}
static int write_buffer(int fd, const void *buf, size_t len)
{
if (write_in_full(fd, buf, len) < 0)
return error("file write error (%s)", strerror(errno));
return 0;
}
int hash_sha1_file(const void *buf, unsigned long len, const char *type,
unsigned char *sha1)
{
char hdr[32];
int hdrlen;
write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
return 0;
}
/* Finalize a file on disk, and close it. */
static void close_sha1_file(int fd)
{
if (fsync_object_files)
fsync_or_die(fd, "sha1 file");
if (close(fd) != 0)
die_errno("error when closing sha1 file");
}
/* Size of directory component, including the ending '/' */
static inline int directory_size(const char *filename)
{
const char *s = strrchr(filename, '/');
if (!s)
return 0;
return s - filename + 1;
}
/*
* This creates a temporary file in the same directory as the final
* 'filename'
*
* We want to avoid cross-directory filename renames, because those
* can have problems on various filesystems (FAT, NFS, Coda).
*/
static int create_tmpfile(char *buffer, size_t bufsiz, const char *filename)
{
int fd, dirlen = directory_size(filename);
if (dirlen + 20 > bufsiz) {
errno = ENAMETOOLONG;
return -1;
}
memcpy(buffer, filename, dirlen);
strcpy(buffer + dirlen, "tmp_obj_XXXXXX");
fd = git_mkstemp_mode(buffer, 0444);
if (fd < 0 && dirlen && errno == ENOENT) {
/* Make sure the directory exists */
memcpy(buffer, filename, dirlen);
buffer[dirlen-1] = 0;
if (mkdir(buffer, 0777) || adjust_shared_perm(buffer))
return -1;
/* Try again */
strcpy(buffer + dirlen - 1, "/tmp_obj_XXXXXX");
fd = git_mkstemp_mode(buffer, 0444);
}
return fd;
}
static int write_loose_object(const unsigned char *sha1, char *hdr, int hdrlen,
const void *buf, unsigned long len, time_t mtime)
{
int fd, ret;
unsigned char compressed[4096];
z_stream stream;
git_SHA_CTX c;
unsigned char parano_sha1[20];
char *filename;
static char tmpfile[PATH_MAX];
filename = sha1_file_name(sha1);
fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
while (fd < 0 && errno == EMFILE && unuse_one_window(NULL, -1))
fd = create_tmpfile(tmpfile, sizeof(tmpfile), filename);
if (fd < 0) {
if (errno == EACCES)
return error("insufficient permission for adding an object to repository database %s\n", get_object_directory());
else
return error("unable to create temporary sha1 filename %s: %s\n", tmpfile, strerror(errno));
}
/* Set it up */
memset(&stream, 0, sizeof(stream));
deflateInit(&stream, zlib_compression_level);
stream.next_out = compressed;
stream.avail_out = sizeof(compressed);
git_SHA1_Init(&c);
/* First header.. */
stream.next_in = (unsigned char *)hdr;
stream.avail_in = hdrlen;
while (deflate(&stream, 0) == Z_OK)
/* nothing */;
git_SHA1_Update(&c, hdr, hdrlen);
/* Then the data itself.. */
stream.next_in = (void *)buf;
stream.avail_in = len;
do {
unsigned char *in0 = stream.next_in;
ret = deflate(&stream, Z_FINISH);
git_SHA1_Update(&c, in0, stream.next_in - in0);
if (write_buffer(fd, compressed, stream.next_out - compressed) < 0)
die("unable to write sha1 file");
stream.next_out = compressed;
stream.avail_out = sizeof(compressed);
} while (ret == Z_OK);
if (ret != Z_STREAM_END)
die("unable to deflate new object %s (%d)", sha1_to_hex(sha1), ret);
ret = deflateEnd(&stream);
if (ret != Z_OK)
die("deflateEnd on object %s failed (%d)", sha1_to_hex(sha1), ret);
git_SHA1_Final(parano_sha1, &c);
if (hashcmp(sha1, parano_sha1) != 0)
die("confused by unstable object source data for %s", sha1_to_hex(sha1));
close_sha1_file(fd);
if (mtime) {
struct utimbuf utb;
utb.actime = mtime;
utb.modtime = mtime;
if (utime(tmpfile, &utb) < 0)
warning("failed utime() on %s: %s",
tmpfile, strerror(errno));
}
return move_temp_to_file(tmpfile, filename);
}
int write_sha1_file(const void *buf, unsigned long len, const char *type, unsigned char *returnsha1)
{
unsigned char sha1[20];
char hdr[32];
int hdrlen;
/* Normally if we have it in the pack then we do not bother writing
* it out into .git/objects/??/?{38} file.
*/
write_sha1_file_prepare(buf, len, type, sha1, hdr, &hdrlen);
if (returnsha1)
hashcpy(returnsha1, sha1);
if (has_sha1_file(sha1))
return 0;
return write_loose_object(sha1, hdr, hdrlen, buf, len, 0);
}
int force_object_loose(const unsigned char *sha1, time_t mtime)
{
void *buf;
unsigned long len;
enum object_type type;
char hdr[32];
int hdrlen;
int ret;
if (has_loose_object(sha1))
return 0;
buf = read_packed_sha1(sha1, &type, &len);
if (!buf)
return error("cannot read sha1_file for %s", sha1_to_hex(sha1));
hdrlen = sprintf(hdr, "%s %lu", typename(type), len) + 1;
ret = write_loose_object(sha1, hdr, hdrlen, buf, len, mtime);
free(buf);
return ret;
}
int has_pack_index(const unsigned char *sha1)
{
struct stat st;
if (stat(sha1_pack_index_name(sha1), &st))
return 0;
return 1;
}
int has_sha1_pack(const unsigned char *sha1)
{
struct pack_entry e;
return find_pack_entry(sha1, &e);
}
int has_sha1_file(const unsigned char *sha1)
{
struct pack_entry e;
if (find_pack_entry(sha1, &e))
return 1;
return has_loose_object(sha1);
}
static void check_tree(const void *buf, size_t size)
{
struct tree_desc desc;
struct name_entry entry;
init_tree_desc(&desc, buf, size);
while (tree_entry(&desc, &entry))
/* do nothing
* tree_entry() will die() on malformed entries */
;
}
static void check_commit(const void *buf, size_t size)
{
struct commit c;
memset(&c, 0, sizeof(c));
if (parse_commit_buffer(&c, buf, size))
die("corrupt commit");
}
static void check_tag(const void *buf, size_t size)
{
struct tag t;
memset(&t, 0, sizeof(t));
if (parse_tag_buffer(&t, buf, size))
die("corrupt tag");
}
static int index_mem(unsigned char *sha1, void *buf, size_t size,
int write_object, enum object_type type,
const char *path, int format_check)
{
int ret, re_allocated = 0;
if (!type)
type = OBJ_BLOB;
/*
* Convert blobs to git internal format
*/
if ((type == OBJ_BLOB) && path) {
struct strbuf nbuf = STRBUF_INIT;
if (convert_to_git(path, buf, size, &nbuf,
write_object ? safe_crlf : 0)) {
buf = strbuf_detach(&nbuf, &size);
re_allocated = 1;
}
}
if (format_check) {
if (type == OBJ_TREE)
check_tree(buf, size);
if (type == OBJ_COMMIT)
check_commit(buf, size);
if (type == OBJ_TAG)
check_tag(buf, size);
}
if (write_object)
ret = write_sha1_file(buf, size, typename(type), sha1);
else
ret = hash_sha1_file(buf, size, typename(type), sha1);
if (re_allocated)
free(buf);
return ret;
}
#define SMALL_FILE_SIZE (32*1024)
int index_fd(unsigned char *sha1, int fd, struct stat *st, int write_object,
enum object_type type, const char *path, int format_check)
{
int ret;
size_t size = xsize_t(st->st_size);
if (!S_ISREG(st->st_mode)) {
struct strbuf sbuf = STRBUF_INIT;
if (strbuf_read(&sbuf, fd, 4096) >= 0)
ret = index_mem(sha1, sbuf.buf, sbuf.len, write_object,
type, path, format_check);
else
ret = -1;
strbuf_release(&sbuf);
} else if (!size) {
ret = index_mem(sha1, NULL, size, write_object, type, path,
format_check);
} else if (size <= SMALL_FILE_SIZE) {
char *buf = xmalloc(size);
if (size == read_in_full(fd, buf, size))
ret = index_mem(sha1, buf, size, write_object, type,
path, format_check);
else
ret = error("short read %s", strerror(errno));
free(buf);
} else {
void *buf = xmmap(NULL, size, PROT_READ, MAP_PRIVATE, fd, 0);
ret = index_mem(sha1, buf, size, write_object, type, path,
format_check);
munmap(buf, size);
}
close(fd);
return ret;
}
int index_path(unsigned char *sha1, const char *path, struct stat *st, int write_object)
{
int fd;
struct strbuf sb = STRBUF_INIT;
switch (st->st_mode & S_IFMT) {
case S_IFREG:
fd = open(path, O_RDONLY);
if (fd < 0)
return error("open(\"%s\"): %s", path,
strerror(errno));
if (index_fd(sha1, fd, st, write_object, OBJ_BLOB, path, 0) < 0)
return error("%s: failed to insert into database",
path);
break;
case S_IFLNK:
if (strbuf_readlink(&sb, path, st->st_size)) {
char *errstr = strerror(errno);
return error("readlink(\"%s\"): %s", path,
errstr);
}
if (!write_object)
hash_sha1_file(sb.buf, sb.len, blob_type, sha1);
else if (write_sha1_file(sb.buf, sb.len, blob_type, sha1))
return error("%s: failed to insert into database",
path);
strbuf_release(&sb);
break;
case S_IFDIR:
return resolve_gitlink_ref(path, "HEAD", sha1);
default:
return error("%s: unsupported file type", path);
}
return 0;
}
int read_pack_header(int fd, struct pack_header *header)
{
if (read_in_full(fd, header, sizeof(*header)) < sizeof(*header))
/* "eof before pack header was fully read" */
return PH_ERROR_EOF;
if (header->hdr_signature != htonl(PACK_SIGNATURE))
/* "protocol error (pack signature mismatch detected)" */
return PH_ERROR_PACK_SIGNATURE;
if (!pack_version_ok(header->hdr_version))
/* "protocol error (pack version unsupported)" */
return PH_ERROR_PROTOCOL;
return 0;
}
void assert_sha1_type(const unsigned char *sha1, enum object_type expect)
{
enum object_type type = sha1_object_info(sha1, NULL);
if (type < 0)
die("%s is not a valid object", sha1_to_hex(sha1));
if (type != expect)
die("%s is not a valid '%s' object", sha1_to_hex(sha1),
typename(expect));
}
|