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
|
/*
* Copyright 1996, 1997, 1998 Hans Reiser, see reiserfs/README for licensing and copyright details
*/
#include <linux/reiserfs_fs.h>
#include <linux/slab.h>
#include <linux/interrupt.h>
#include <linux/sched.h>
#include <linux/bug.h>
#include <linux/workqueue.h>
#include <asm/unaligned.h>
#include <linux/bitops.h>
#include <linux/proc_fs.h>
#include <linux/buffer_head.h>
/* the 32 bit compat definitions with int argument */
#define REISERFS_IOC32_UNPACK _IOW(0xCD, 1, int)
#define REISERFS_IOC32_GETFLAGS FS_IOC32_GETFLAGS
#define REISERFS_IOC32_SETFLAGS FS_IOC32_SETFLAGS
#define REISERFS_IOC32_GETVERSION FS_IOC32_GETVERSION
#define REISERFS_IOC32_SETVERSION FS_IOC32_SETVERSION
struct reiserfs_journal_list;
/** bitmasks for i_flags field in reiserfs-specific part of inode */
typedef enum {
/** this says what format of key do all items (but stat data) of
an object have. If this is set, that format is 3.6 otherwise
- 3.5 */
i_item_key_version_mask = 0x0001,
/** If this is unset, object has 3.5 stat data, otherwise, it has
3.6 stat data with 64bit size, 32bit nlink etc. */
i_stat_data_version_mask = 0x0002,
/** file might need tail packing on close */
i_pack_on_close_mask = 0x0004,
/** don't pack tail of file */
i_nopack_mask = 0x0008,
/** If those is set, "safe link" was created for this file during
truncate or unlink. Safe link is used to avoid leakage of disk
space on crash with some files open, but unlinked. */
i_link_saved_unlink_mask = 0x0010,
i_link_saved_truncate_mask = 0x0020,
i_has_xattr_dir = 0x0040,
i_data_log = 0x0080,
} reiserfs_inode_flags;
struct reiserfs_inode_info {
__u32 i_key[4]; /* key is still 4 32 bit integers */
/** transient inode flags that are never stored on disk. Bitmasks
for this field are defined above. */
__u32 i_flags;
__u32 i_first_direct_byte; // offset of first byte stored in direct item.
/* copy of persistent inode flags read from sd_attrs. */
__u32 i_attrs;
int i_prealloc_block; /* first unused block of a sequence of unused blocks */
int i_prealloc_count; /* length of that sequence */
struct list_head i_prealloc_list; /* per-transaction list of inodes which
* have preallocated blocks */
unsigned new_packing_locality:1; /* new_packig_locality is created; new blocks
* for the contents of this directory should be
* displaced */
/* we use these for fsync or O_SYNC to decide which transaction
** needs to be committed in order for this inode to be properly
** flushed */
unsigned int i_trans_id;
struct reiserfs_journal_list *i_jl;
atomic_t openers;
struct mutex tailpack;
#ifdef CONFIG_REISERFS_FS_XATTR
struct rw_semaphore i_xattr_sem;
#endif
struct inode vfs_inode;
};
typedef enum {
reiserfs_attrs_cleared = 0x00000001,
} reiserfs_super_block_flags;
/* struct reiserfs_super_block accessors/mutators
* since this is a disk structure, it will always be in
* little endian format. */
#define sb_block_count(sbp) (le32_to_cpu((sbp)->s_v1.s_block_count))
#define set_sb_block_count(sbp,v) ((sbp)->s_v1.s_block_count = cpu_to_le32(v))
#define sb_free_blocks(sbp) (le32_to_cpu((sbp)->s_v1.s_free_blocks))
#define set_sb_free_blocks(sbp,v) ((sbp)->s_v1.s_free_blocks = cpu_to_le32(v))
#define sb_root_block(sbp) (le32_to_cpu((sbp)->s_v1.s_root_block))
#define set_sb_root_block(sbp,v) ((sbp)->s_v1.s_root_block = cpu_to_le32(v))
#define sb_jp_journal_1st_block(sbp) \
(le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_1st_block))
#define set_sb_jp_journal_1st_block(sbp,v) \
((sbp)->s_v1.s_journal.jp_journal_1st_block = cpu_to_le32(v))
#define sb_jp_journal_dev(sbp) \
(le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_dev))
#define set_sb_jp_journal_dev(sbp,v) \
((sbp)->s_v1.s_journal.jp_journal_dev = cpu_to_le32(v))
#define sb_jp_journal_size(sbp) \
(le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_size))
#define set_sb_jp_journal_size(sbp,v) \
((sbp)->s_v1.s_journal.jp_journal_size = cpu_to_le32(v))
#define sb_jp_journal_trans_max(sbp) \
(le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_trans_max))
#define set_sb_jp_journal_trans_max(sbp,v) \
((sbp)->s_v1.s_journal.jp_journal_trans_max = cpu_to_le32(v))
#define sb_jp_journal_magic(sbp) \
(le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_magic))
#define set_sb_jp_journal_magic(sbp,v) \
((sbp)->s_v1.s_journal.jp_journal_magic = cpu_to_le32(v))
#define sb_jp_journal_max_batch(sbp) \
(le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_max_batch))
#define set_sb_jp_journal_max_batch(sbp,v) \
((sbp)->s_v1.s_journal.jp_journal_max_batch = cpu_to_le32(v))
#define sb_jp_jourmal_max_commit_age(sbp) \
(le32_to_cpu((sbp)->s_v1.s_journal.jp_journal_max_commit_age))
#define set_sb_jp_journal_max_commit_age(sbp,v) \
((sbp)->s_v1.s_journal.jp_journal_max_commit_age = cpu_to_le32(v))
#define sb_blocksize(sbp) (le16_to_cpu((sbp)->s_v1.s_blocksize))
#define set_sb_blocksize(sbp,v) ((sbp)->s_v1.s_blocksize = cpu_to_le16(v))
#define sb_oid_maxsize(sbp) (le16_to_cpu((sbp)->s_v1.s_oid_maxsize))
#define set_sb_oid_maxsize(sbp,v) ((sbp)->s_v1.s_oid_maxsize = cpu_to_le16(v))
#define sb_oid_cursize(sbp) (le16_to_cpu((sbp)->s_v1.s_oid_cursize))
#define set_sb_oid_cursize(sbp,v) ((sbp)->s_v1.s_oid_cursize = cpu_to_le16(v))
#define sb_umount_state(sbp) (le16_to_cpu((sbp)->s_v1.s_umount_state))
#define set_sb_umount_state(sbp,v) ((sbp)->s_v1.s_umount_state = cpu_to_le16(v))
#define sb_fs_state(sbp) (le16_to_cpu((sbp)->s_v1.s_fs_state))
#define set_sb_fs_state(sbp,v) ((sbp)->s_v1.s_fs_state = cpu_to_le16(v))
#define sb_hash_function_code(sbp) \
(le32_to_cpu((sbp)->s_v1.s_hash_function_code))
#define set_sb_hash_function_code(sbp,v) \
((sbp)->s_v1.s_hash_function_code = cpu_to_le32(v))
#define sb_tree_height(sbp) (le16_to_cpu((sbp)->s_v1.s_tree_height))
#define set_sb_tree_height(sbp,v) ((sbp)->s_v1.s_tree_height = cpu_to_le16(v))
#define sb_bmap_nr(sbp) (le16_to_cpu((sbp)->s_v1.s_bmap_nr))
#define set_sb_bmap_nr(sbp,v) ((sbp)->s_v1.s_bmap_nr = cpu_to_le16(v))
#define sb_version(sbp) (le16_to_cpu((sbp)->s_v1.s_version))
#define set_sb_version(sbp,v) ((sbp)->s_v1.s_version = cpu_to_le16(v))
#define sb_mnt_count(sbp) (le16_to_cpu((sbp)->s_mnt_count))
#define set_sb_mnt_count(sbp, v) ((sbp)->s_mnt_count = cpu_to_le16(v))
#define sb_reserved_for_journal(sbp) \
(le16_to_cpu((sbp)->s_v1.s_reserved_for_journal))
#define set_sb_reserved_for_journal(sbp,v) \
((sbp)->s_v1.s_reserved_for_journal = cpu_to_le16(v))
/* LOGGING -- */
/* These all interelate for performance.
**
** If the journal block count is smaller than n transactions, you lose speed.
** I don't know what n is yet, I'm guessing 8-16.
**
** typical transaction size depends on the application, how often fsync is
** called, and how many metadata blocks you dirty in a 30 second period.
** The more small files (<16k) you use, the larger your transactions will
** be.
**
** If your journal fills faster than dirty buffers get flushed to disk, it must flush them before allowing the journal
** to wrap, which slows things down. If you need high speed meta data updates, the journal should be big enough
** to prevent wrapping before dirty meta blocks get to disk.
**
** If the batch max is smaller than the transaction max, you'll waste space at the end of the journal
** because journal_end sets the next transaction to start at 0 if the next transaction has any chance of wrapping.
**
** The large the batch max age, the better the speed, and the more meta data changes you'll lose after a crash.
**
*/
/* don't mess with these for a while */
/* we have a node size define somewhere in reiserfs_fs.h. -Hans */
#define JOURNAL_BLOCK_SIZE 4096 /* BUG gotta get rid of this */
#define JOURNAL_MAX_CNODE 1500 /* max cnodes to allocate. */
#define JOURNAL_HASH_SIZE 8192
#define JOURNAL_NUM_BITMAPS 5 /* number of copies of the bitmaps to have floating. Must be >= 2 */
/* One of these for every block in every transaction
** Each one is in two hash tables. First, a hash of the current transaction, and after journal_end, a
** hash of all the in memory transactions.
** next and prev are used by the current transaction (journal_hash).
** hnext and hprev are used by journal_list_hash. If a block is in more than one transaction, the journal_list_hash
** links it in multiple times. This allows flush_journal_list to remove just the cnode belonging
** to a given transaction.
*/
struct reiserfs_journal_cnode {
struct buffer_head *bh; /* real buffer head */
struct super_block *sb; /* dev of real buffer head */
__u32 blocknr; /* block number of real buffer head, == 0 when buffer on disk */
unsigned long state;
struct reiserfs_journal_list *jlist; /* journal list this cnode lives in */
struct reiserfs_journal_cnode *next; /* next in transaction list */
struct reiserfs_journal_cnode *prev; /* prev in transaction list */
struct reiserfs_journal_cnode *hprev; /* prev in hash list */
struct reiserfs_journal_cnode *hnext; /* next in hash list */
};
struct reiserfs_bitmap_node {
int id;
char *data;
struct list_head list;
};
struct reiserfs_list_bitmap {
struct reiserfs_journal_list *journal_list;
struct reiserfs_bitmap_node **bitmaps;
};
/*
** one of these for each transaction. The most important part here is the j_realblock.
** this list of cnodes is used to hash all the blocks in all the commits, to mark all the
** real buffer heads dirty once all the commits hit the disk,
** and to make sure every real block in a transaction is on disk before allowing the log area
** to be overwritten */
struct reiserfs_journal_list {
unsigned long j_start;
unsigned long j_state;
unsigned long j_len;
atomic_t j_nonzerolen;
atomic_t j_commit_left;
atomic_t j_older_commits_done; /* all commits older than this on disk */
struct mutex j_commit_mutex;
unsigned int j_trans_id;
time_t j_timestamp;
struct reiserfs_list_bitmap *j_list_bitmap;
struct buffer_head *j_commit_bh; /* commit buffer head */
struct reiserfs_journal_cnode *j_realblock;
struct reiserfs_journal_cnode *j_freedlist; /* list of buffers that were freed during this trans. free each of these on flush */
/* time ordered list of all active transactions */
struct list_head j_list;
/* time ordered list of all transactions we haven't tried to flush yet */
struct list_head j_working_list;
/* list of tail conversion targets in need of flush before commit */
struct list_head j_tail_bh_list;
/* list of data=ordered buffers in need of flush before commit */
struct list_head j_bh_list;
int j_refcount;
};
struct reiserfs_journal {
struct buffer_head **j_ap_blocks; /* journal blocks on disk */
struct reiserfs_journal_cnode *j_last; /* newest journal block */
struct reiserfs_journal_cnode *j_first; /* oldest journal block. start here for traverse */
struct block_device *j_dev_bd;
fmode_t j_dev_mode;
int j_1st_reserved_block; /* first block on s_dev of reserved area journal */
unsigned long j_state;
unsigned int j_trans_id;
unsigned long j_mount_id;
unsigned long j_start; /* start of current waiting commit (index into j_ap_blocks) */
unsigned long j_len; /* length of current waiting commit */
unsigned long j_len_alloc; /* number of buffers requested by journal_begin() */
atomic_t j_wcount; /* count of writers for current commit */
unsigned long j_bcount; /* batch count. allows turning X transactions into 1 */
unsigned long j_first_unflushed_offset; /* first unflushed transactions offset */
unsigned j_last_flush_trans_id; /* last fully flushed journal timestamp */
struct buffer_head *j_header_bh;
time_t j_trans_start_time; /* time this transaction started */
struct mutex j_mutex;
struct mutex j_flush_mutex;
wait_queue_head_t j_join_wait; /* wait for current transaction to finish before starting new one */
atomic_t j_jlock; /* lock for j_join_wait */
int j_list_bitmap_index; /* number of next list bitmap to use */
int j_must_wait; /* no more journal begins allowed. MUST sleep on j_join_wait */
int j_next_full_flush; /* next journal_end will flush all journal list */
int j_next_async_flush; /* next journal_end will flush all async commits */
int j_cnode_used; /* number of cnodes on the used list */
int j_cnode_free; /* number of cnodes on the free list */
unsigned int j_trans_max; /* max number of blocks in a transaction. */
unsigned int j_max_batch; /* max number of blocks to batch into a trans */
unsigned int j_max_commit_age; /* in seconds, how old can an async commit be */
unsigned int j_max_trans_age; /* in seconds, how old can a transaction be */
unsigned int j_default_max_commit_age; /* the default for the max commit age */
struct reiserfs_journal_cnode *j_cnode_free_list;
struct reiserfs_journal_cnode *j_cnode_free_orig; /* orig pointer returned from vmalloc */
struct reiserfs_journal_list *j_current_jl;
int j_free_bitmap_nodes;
int j_used_bitmap_nodes;
int j_num_lists; /* total number of active transactions */
int j_num_work_lists; /* number that need attention from kreiserfsd */
/* debugging to make sure things are flushed in order */
unsigned int j_last_flush_id;
/* debugging to make sure things are committed in order */
unsigned int j_last_commit_id;
struct list_head j_bitmap_nodes;
struct list_head j_dirty_buffers;
spinlock_t j_dirty_buffers_lock; /* protects j_dirty_buffers */
/* list of all active transactions */
struct list_head j_journal_list;
/* lists that haven't been touched by writeback attempts */
struct list_head j_working_list;
struct reiserfs_list_bitmap j_list_bitmap[JOURNAL_NUM_BITMAPS]; /* array of bitmaps to record the deleted blocks */
struct reiserfs_journal_cnode *j_hash_table[JOURNAL_HASH_SIZE]; /* hash table for real buffer heads in current trans */
struct reiserfs_journal_cnode *j_list_hash_table[JOURNAL_HASH_SIZE]; /* hash table for all the real buffer heads in all
the transactions */
struct list_head j_prealloc_list; /* list of inodes which have preallocated blocks */
int j_persistent_trans;
unsigned long j_max_trans_size;
unsigned long j_max_batch_size;
int j_errno;
/* when flushing ordered buffers, throttle new ordered writers */
struct delayed_work j_work;
struct super_block *j_work_sb;
atomic_t j_async_throttle;
};
enum journal_state_bits {
J_WRITERS_BLOCKED = 1, /* set when new writers not allowed */
J_WRITERS_QUEUED, /* set when log is full due to too many writers */
J_ABORTED, /* set when log is aborted */
};
#define JOURNAL_DESC_MAGIC "ReIsErLB" /* ick. magic string to find desc blocks in the journal */
typedef __u32(*hashf_t) (const signed char *, int);
struct reiserfs_bitmap_info {
__u32 free_count;
};
struct proc_dir_entry;
#if defined( CONFIG_PROC_FS ) && defined( CONFIG_REISERFS_PROC_INFO )
typedef unsigned long int stat_cnt_t;
typedef struct reiserfs_proc_info_data {
spinlock_t lock;
int exiting;
int max_hash_collisions;
stat_cnt_t breads;
stat_cnt_t bread_miss;
stat_cnt_t search_by_key;
stat_cnt_t search_by_key_fs_changed;
stat_cnt_t search_by_key_restarted;
stat_cnt_t insert_item_restarted;
stat_cnt_t paste_into_item_restarted;
stat_cnt_t cut_from_item_restarted;
stat_cnt_t delete_solid_item_restarted;
stat_cnt_t delete_item_restarted;
stat_cnt_t leaked_oid;
stat_cnt_t leaves_removable;
/* balances per level. Use explicit 5 as MAX_HEIGHT is not visible yet. */
stat_cnt_t balance_at[5]; /* XXX */
/* sbk == search_by_key */
stat_cnt_t sbk_read_at[5]; /* XXX */
stat_cnt_t sbk_fs_changed[5];
stat_cnt_t sbk_restarted[5];
stat_cnt_t items_at[5]; /* XXX */
stat_cnt_t free_at[5]; /* XXX */
stat_cnt_t can_node_be_removed[5]; /* XXX */
long int lnum[5]; /* XXX */
long int rnum[5]; /* XXX */
long int lbytes[5]; /* XXX */
long int rbytes[5]; /* XXX */
stat_cnt_t get_neighbors[5];
stat_cnt_t get_neighbors_restart[5];
stat_cnt_t need_l_neighbor[5];
stat_cnt_t need_r_neighbor[5];
stat_cnt_t free_block;
struct __scan_bitmap_stats {
stat_cnt_t call;
stat_cnt_t wait;
stat_cnt_t bmap;
stat_cnt_t retry;
stat_cnt_t in_journal_hint;
stat_cnt_t in_journal_nohint;
stat_cnt_t stolen;
} scan_bitmap;
struct __journal_stats {
stat_cnt_t in_journal;
stat_cnt_t in_journal_bitmap;
stat_cnt_t in_journal_reusable;
stat_cnt_t lock_journal;
stat_cnt_t lock_journal_wait;
stat_cnt_t journal_being;
stat_cnt_t journal_relock_writers;
stat_cnt_t journal_relock_wcount;
stat_cnt_t mark_dirty;
stat_cnt_t mark_dirty_already;
stat_cnt_t mark_dirty_notjournal;
stat_cnt_t restore_prepared;
stat_cnt_t prepare;
stat_cnt_t prepare_retry;
} journal;
} reiserfs_proc_info_data_t;
#else
typedef struct reiserfs_proc_info_data {
} reiserfs_proc_info_data_t;
#endif
/* reiserfs union of in-core super block data */
struct reiserfs_sb_info {
struct buffer_head *s_sbh; /* Buffer containing the super block */
/* both the comment and the choice of
name are unclear for s_rs -Hans */
struct reiserfs_super_block *s_rs; /* Pointer to the super block in the buffer */
struct reiserfs_bitmap_info *s_ap_bitmap;
struct reiserfs_journal *s_journal; /* pointer to journal information */
unsigned short s_mount_state; /* reiserfs state (valid, invalid) */
/* Serialize writers access, replace the old bkl */
struct mutex lock;
/* Owner of the lock (can be recursive) */
struct task_struct *lock_owner;
/* Depth of the lock, start from -1 like the bkl */
int lock_depth;
/* Comment? -Hans */
void (*end_io_handler) (struct buffer_head *, int);
hashf_t s_hash_function; /* pointer to function which is used
to sort names in directory. Set on
mount */
unsigned long s_mount_opt; /* reiserfs's mount options are set
here (currently - NOTAIL, NOLOG,
REPLAYONLY) */
struct { /* This is a structure that describes block allocator options */
unsigned long bits; /* Bitfield for enable/disable kind of options */
unsigned long large_file_size; /* size started from which we consider file to be a large one(in blocks) */
int border; /* percentage of disk, border takes */
int preallocmin; /* Minimal file size (in blocks) starting from which we do preallocations */
int preallocsize; /* Number of blocks we try to prealloc when file
reaches preallocmin size (in blocks) or
prealloc_list is empty. */
} s_alloc_options;
/* Comment? -Hans */
wait_queue_head_t s_wait;
/* To be obsoleted soon by per buffer seals.. -Hans */
atomic_t s_generation_counter; // increased by one every time the
// tree gets re-balanced
unsigned long s_properties; /* File system properties. Currently holds
on-disk FS format */
/* session statistics */
int s_disk_reads;
int s_disk_writes;
int s_fix_nodes;
int s_do_balance;
int s_unneeded_left_neighbor;
int s_good_search_by_key_reada;
int s_bmaps;
int s_bmaps_without_search;
int s_direct2indirect;
int s_indirect2direct;
/* set up when it's ok for reiserfs_read_inode2() to read from
disk inode with nlink==0. Currently this is only used during
finish_unfinished() processing at mount time */
int s_is_unlinked_ok;
reiserfs_proc_info_data_t s_proc_info_data;
struct proc_dir_entry *procdir;
int reserved_blocks; /* amount of blocks reserved for further allocations */
spinlock_t bitmap_lock; /* this lock on now only used to protect reserved_blocks variable */
struct dentry *priv_root; /* root of /.reiserfs_priv */
struct dentry *xattr_root; /* root of /.reiserfs_priv/xattrs */
int j_errno;
int work_queued; /* non-zero delayed work is queued */
struct delayed_work old_work; /* old transactions flush delayed work */
spinlock_t old_work_lock; /* protects old_work and work_queued */
#ifdef CONFIG_QUOTA
char *s_qf_names[MAXQUOTAS];
int s_jquota_fmt;
#endif
char *s_jdev; /* Stored jdev for mount option showing */
#ifdef CONFIG_REISERFS_CHECK
struct tree_balance *cur_tb; /*
* Detects whether more than one
* copy of tb exists per superblock
* as a means of checking whether
* do_balance is executing concurrently
* against another tree reader/writer
* on a same mount point.
*/
#endif
};
/* Definitions of reiserfs on-disk properties: */
#define REISERFS_3_5 0
#define REISERFS_3_6 1
#define REISERFS_OLD_FORMAT 2
enum reiserfs_mount_options {
/* Mount options */
REISERFS_LARGETAIL, /* large tails will be created in a session */
REISERFS_SMALLTAIL, /* small (for files less than block size) tails will be created in a session */
REPLAYONLY, /* replay journal and return 0. Use by fsck */
REISERFS_CONVERT, /* -o conv: causes conversion of old
format super block to the new
format. If not specified - old
partition will be dealt with in a
manner of 3.5.x */
/* -o hash={tea, rupasov, r5, detect} is meant for properly mounting
** reiserfs disks from 3.5.19 or earlier. 99% of the time, this option
** is not required. If the normal autodection code can't determine which
** hash to use (because both hashes had the same value for a file)
** use this option to force a specific hash. It won't allow you to override
** the existing hash on the FS, so if you have a tea hash disk, and mount
** with -o hash=rupasov, the mount will fail.
*/
FORCE_TEA_HASH, /* try to force tea hash on mount */
FORCE_RUPASOV_HASH, /* try to force rupasov hash on mount */
FORCE_R5_HASH, /* try to force rupasov hash on mount */
FORCE_HASH_DETECT, /* try to detect hash function on mount */
REISERFS_DATA_LOG,
REISERFS_DATA_ORDERED,
REISERFS_DATA_WRITEBACK,
/* used for testing experimental features, makes benchmarking new
features with and without more convenient, should never be used by
users in any code shipped to users (ideally) */
REISERFS_NO_BORDER,
REISERFS_NO_UNHASHED_RELOCATION,
REISERFS_HASHED_RELOCATION,
REISERFS_ATTRS,
REISERFS_XATTRS_USER,
REISERFS_POSIXACL,
REISERFS_EXPOSE_PRIVROOT,
REISERFS_BARRIER_NONE,
REISERFS_BARRIER_FLUSH,
/* Actions on error */
REISERFS_ERROR_PANIC,
REISERFS_ERROR_RO,
REISERFS_ERROR_CONTINUE,
REISERFS_USRQUOTA, /* User quota option specified */
REISERFS_GRPQUOTA, /* Group quota option specified */
REISERFS_TEST1,
REISERFS_TEST2,
REISERFS_TEST3,
REISERFS_TEST4,
REISERFS_UNSUPPORTED_OPT,
};
#define reiserfs_r5_hash(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_R5_HASH))
#define reiserfs_rupasov_hash(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_RUPASOV_HASH))
#define reiserfs_tea_hash(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_TEA_HASH))
#define reiserfs_hash_detect(s) (REISERFS_SB(s)->s_mount_opt & (1 << FORCE_HASH_DETECT))
#define reiserfs_no_border(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_NO_BORDER))
#define reiserfs_no_unhashed_relocation(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_NO_UNHASHED_RELOCATION))
#define reiserfs_hashed_relocation(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_HASHED_RELOCATION))
#define reiserfs_test4(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_TEST4))
#define have_large_tails(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_LARGETAIL))
#define have_small_tails(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_SMALLTAIL))
#define replay_only(s) (REISERFS_SB(s)->s_mount_opt & (1 << REPLAYONLY))
#define reiserfs_attrs(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_ATTRS))
#define old_format_only(s) (REISERFS_SB(s)->s_properties & (1 << REISERFS_3_5))
#define convert_reiserfs(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_CONVERT))
#define reiserfs_data_log(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_LOG))
#define reiserfs_data_ordered(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_ORDERED))
#define reiserfs_data_writeback(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_DATA_WRITEBACK))
#define reiserfs_xattrs_user(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_XATTRS_USER))
#define reiserfs_posixacl(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_POSIXACL))
#define reiserfs_expose_privroot(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_EXPOSE_PRIVROOT))
#define reiserfs_xattrs_optional(s) (reiserfs_xattrs_user(s) || reiserfs_posixacl(s))
#define reiserfs_barrier_none(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_NONE))
#define reiserfs_barrier_flush(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_BARRIER_FLUSH))
#define reiserfs_error_panic(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_ERROR_PANIC))
#define reiserfs_error_ro(s) (REISERFS_SB(s)->s_mount_opt & (1 << REISERFS_ERROR_RO))
void reiserfs_file_buffer(struct buffer_head *bh, int list);
extern struct file_system_type reiserfs_fs_type;
int reiserfs_resize(struct super_block *, unsigned long);
#define CARRY_ON 0
#define SCHEDULE_OCCURRED 1
#define SB_BUFFER_WITH_SB(s) (REISERFS_SB(s)->s_sbh)
#define SB_JOURNAL(s) (REISERFS_SB(s)->s_journal)
#define SB_JOURNAL_1st_RESERVED_BLOCK(s) (SB_JOURNAL(s)->j_1st_reserved_block)
#define SB_JOURNAL_LEN_FREE(s) (SB_JOURNAL(s)->j_journal_len_free)
#define SB_AP_BITMAP(s) (REISERFS_SB(s)->s_ap_bitmap)
#define SB_DISK_JOURNAL_HEAD(s) (SB_JOURNAL(s)->j_header_bh->)
/* A safe version of the "bdevname", which returns the "s_id" field of
* a superblock or else "Null superblock" if the super block is NULL.
*/
static inline char *reiserfs_bdevname(struct super_block *s)
{
return (s == NULL) ? "Null superblock" : s->s_id;
}
#define reiserfs_is_journal_aborted(journal) (unlikely (__reiserfs_is_journal_aborted (journal)))
static inline int __reiserfs_is_journal_aborted(struct reiserfs_journal
*journal)
{
return test_bit(J_ABORTED, &journal->j_state);
}
/*
* Locking primitives. The write lock is a per superblock
* special mutex that has properties close to the Big Kernel Lock
* which was used in the previous locking scheme.
*/
void reiserfs_write_lock(struct super_block *s);
void reiserfs_write_unlock(struct super_block *s);
int reiserfs_write_lock_once(struct super_block *s);
void reiserfs_write_unlock_once(struct super_block *s, int lock_depth);
#ifdef CONFIG_REISERFS_CHECK
void reiserfs_lock_check_recursive(struct super_block *s);
#else
static inline void reiserfs_lock_check_recursive(struct super_block *s) { }
#endif
/*
* Several mutexes depend on the write lock.
* However sometimes we want to relax the write lock while we hold
* these mutexes, according to the release/reacquire on schedule()
* properties of the Bkl that were used.
* Reiserfs performances and locking were based on this scheme.
* Now that the write lock is a mutex and not the bkl anymore, doing so
* may result in a deadlock:
*
* A acquire write_lock
* A acquire j_commit_mutex
* A release write_lock and wait for something
* B acquire write_lock
* B can't acquire j_commit_mutex and sleep
* A can't acquire write lock anymore
* deadlock
*
* What we do here is avoiding such deadlock by playing the same game
* than the Bkl: if we can't acquire a mutex that depends on the write lock,
* we release the write lock, wait a bit and then retry.
*
* The mutexes concerned by this hack are:
* - The commit mutex of a journal list
* - The flush mutex
* - The journal lock
* - The inode mutex
*/
static inline void reiserfs_mutex_lock_safe(struct mutex *m,
struct super_block *s)
{
reiserfs_lock_check_recursive(s);
reiserfs_write_unlock(s);
mutex_lock(m);
reiserfs_write_lock(s);
}
static inline void
reiserfs_mutex_lock_nested_safe(struct mutex *m, unsigned int subclass,
struct super_block *s)
{
reiserfs_lock_check_recursive(s);
reiserfs_write_unlock(s);
mutex_lock_nested(m, subclass);
reiserfs_write_lock(s);
}
static inline void
reiserfs_down_read_safe(struct rw_semaphore *sem, struct super_block *s)
{
reiserfs_lock_check_recursive(s);
reiserfs_write_unlock(s);
down_read(sem);
reiserfs_write_lock(s);
}
/*
* When we schedule, we usually want to also release the write lock,
* according to the previous bkl based locking scheme of reiserfs.
*/
static inline void reiserfs_cond_resched(struct super_block *s)
{
if (need_resched()) {
reiserfs_write_unlock(s);
schedule();
reiserfs_write_lock(s);
}
}
struct fid;
/* in reading the #defines, it may help to understand that they employ
the following abbreviations:
B = Buffer
I = Item header
H = Height within the tree (should be changed to LEV)
N = Number of the item in the node
STAT = stat data
DEH = Directory Entry Header
EC = Entry Count
E = Entry number
UL = Unsigned Long
BLKH = BLocK Header
UNFM = UNForMatted node
DC = Disk Child
P = Path
These #defines are named by concatenating these abbreviations,
where first comes the arguments, and last comes the return value,
of the macro.
*/
#define USE_INODE_GENERATION_COUNTER
#define REISERFS_PREALLOCATE
#define DISPLACE_NEW_PACKING_LOCALITIES
#define PREALLOCATION_SIZE 9
/* n must be power of 2 */
#define _ROUND_UP(x,n) (((x)+(n)-1u) & ~((n)-1u))
// to be ok for alpha and others we have to align structures to 8 byte
// boundary.
// FIXME: do not change 4 by anything else: there is code which relies on that
#define ROUND_UP(x) _ROUND_UP(x,8LL)
/* debug levels. Right now, CONFIG_REISERFS_CHECK means print all debug
** messages.
*/
#define REISERFS_DEBUG_CODE 5 /* extra messages to help find/debug errors */
void __reiserfs_warning(struct super_block *s, const char *id,
const char *func, const char *fmt, ...);
#define reiserfs_warning(s, id, fmt, args...) \
__reiserfs_warning(s, id, __func__, fmt, ##args)
/* assertions handling */
/** always check a condition and panic if it's false. */
#define __RASSERT(cond, scond, format, args...) \
do { \
if (!(cond)) \
reiserfs_panic(NULL, "assertion failure", "(" #cond ") at " \
__FILE__ ":%i:%s: " format "\n", \
in_interrupt() ? -1 : task_pid_nr(current), \
__LINE__, __func__ , ##args); \
} while (0)
#define RASSERT(cond, format, args...) __RASSERT(cond, #cond, format, ##args)
#if defined( CONFIG_REISERFS_CHECK )
#define RFALSE(cond, format, args...) __RASSERT(!(cond), "!(" #cond ")", format, ##args)
#else
#define RFALSE( cond, format, args... ) do {;} while( 0 )
#endif
#define CONSTF __attribute_const__
/*
* Disk Data Structures
*/
/***************************************************************************/
/* SUPER BLOCK */
/***************************************************************************/
/*
* Structure of super block on disk, a version of which in RAM is often accessed as REISERFS_SB(s)->s_rs
* the version in RAM is part of a larger structure containing fields never written to disk.
*/
#define UNSET_HASH 0 // read_super will guess about, what hash names
// in directories were sorted with
#define TEA_HASH 1
#define YURA_HASH 2
#define R5_HASH 3
#define DEFAULT_HASH R5_HASH
struct journal_params {
__le32 jp_journal_1st_block; /* where does journal start from on its
* device */
__le32 jp_journal_dev; /* journal device st_rdev */
__le32 jp_journal_size; /* size of the journal */
__le32 jp_journal_trans_max; /* max number of blocks in a transaction. */
__le32 jp_journal_magic; /* random value made on fs creation (this
* was sb_journal_block_count) */
__le32 jp_journal_max_batch; /* max number of blocks to batch into a
* trans */
__le32 jp_journal_max_commit_age; /* in seconds, how old can an async
* commit be */
__le32 jp_journal_max_trans_age; /* in seconds, how old can a transaction
* be */
};
/* this is the super from 3.5.X, where X >= 10 */
struct reiserfs_super_block_v1 {
__le32 s_block_count; /* blocks count */
__le32 s_free_blocks; /* free blocks count */
__le32 s_root_block; /* root block number */
struct journal_params s_journal;
__le16 s_blocksize; /* block size */
__le16 s_oid_maxsize; /* max size of object id array, see
* get_objectid() commentary */
__le16 s_oid_cursize; /* current size of object id array */
__le16 s_umount_state; /* this is set to 1 when filesystem was
* umounted, to 2 - when not */
char s_magic[10]; /* reiserfs magic string indicates that
* file system is reiserfs:
* "ReIsErFs" or "ReIsEr2Fs" or "ReIsEr3Fs" */
__le16 s_fs_state; /* it is set to used by fsck to mark which
* phase of rebuilding is done */
__le32 s_hash_function_code; /* indicate, what hash function is being use
* to sort names in a directory*/
__le16 s_tree_height; /* height of disk tree */
__le16 s_bmap_nr; /* amount of bitmap blocks needed to address
* each block of file system */
__le16 s_version; /* this field is only reliable on filesystem
* with non-standard journal */
__le16 s_reserved_for_journal; /* size in blocks of journal area on main
* device, we need to keep after
* making fs with non-standard journal */
} __attribute__ ((__packed__));
#define SB_SIZE_V1 (sizeof(struct reiserfs_super_block_v1))
/* this is the on disk super block */
struct reiserfs_super_block {
struct reiserfs_super_block_v1 s_v1;
__le32 s_inode_generation;
__le32 s_flags; /* Right now used only by inode-attributes, if enabled */
unsigned char s_uuid[16]; /* filesystem unique identifier */
unsigned char s_label[16]; /* filesystem volume label */
__le16 s_mnt_count; /* Count of mounts since last fsck */
__le16 s_max_mnt_count; /* Maximum mounts before check */
__le32 s_lastcheck; /* Timestamp of last fsck */
__le32 s_check_interval; /* Interval between checks */
char s_unused[76]; /* zero filled by mkreiserfs and
* reiserfs_convert_objectid_map_v1()
* so any additions must be updated
* there as well. */
} __attribute__ ((__packed__));
#define SB_SIZE (sizeof(struct reiserfs_super_block))
#define REISERFS_VERSION_1 0
#define REISERFS_VERSION_2 2
// on-disk super block fields converted to cpu form
#define SB_DISK_SUPER_BLOCK(s) (REISERFS_SB(s)->s_rs)
#define SB_V1_DISK_SUPER_BLOCK(s) (&(SB_DISK_SUPER_BLOCK(s)->s_v1))
#define SB_BLOCKSIZE(s) \
le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_blocksize))
#define SB_BLOCK_COUNT(s) \
le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_block_count))
#define SB_FREE_BLOCKS(s) \
le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_free_blocks))
#define SB_REISERFS_MAGIC(s) \
(SB_V1_DISK_SUPER_BLOCK(s)->s_magic)
#define SB_ROOT_BLOCK(s) \
le32_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_root_block))
#define SB_TREE_HEIGHT(s) \
le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_tree_height))
#define SB_REISERFS_STATE(s) \
le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_umount_state))
#define SB_VERSION(s) le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_version))
#define SB_BMAP_NR(s) le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_bmap_nr))
#define PUT_SB_BLOCK_COUNT(s, val) \
do { SB_V1_DISK_SUPER_BLOCK(s)->s_block_count = cpu_to_le32(val); } while (0)
#define PUT_SB_FREE_BLOCKS(s, val) \
do { SB_V1_DISK_SUPER_BLOCK(s)->s_free_blocks = cpu_to_le32(val); } while (0)
#define PUT_SB_ROOT_BLOCK(s, val) \
do { SB_V1_DISK_SUPER_BLOCK(s)->s_root_block = cpu_to_le32(val); } while (0)
#define PUT_SB_TREE_HEIGHT(s, val) \
do { SB_V1_DISK_SUPER_BLOCK(s)->s_tree_height = cpu_to_le16(val); } while (0)
#define PUT_SB_REISERFS_STATE(s, val) \
do { SB_V1_DISK_SUPER_BLOCK(s)->s_umount_state = cpu_to_le16(val); } while (0)
#define PUT_SB_VERSION(s, val) \
do { SB_V1_DISK_SUPER_BLOCK(s)->s_version = cpu_to_le16(val); } while (0)
#define PUT_SB_BMAP_NR(s, val) \
do { SB_V1_DISK_SUPER_BLOCK(s)->s_bmap_nr = cpu_to_le16 (val); } while (0)
#define SB_ONDISK_JP(s) (&SB_V1_DISK_SUPER_BLOCK(s)->s_journal)
#define SB_ONDISK_JOURNAL_SIZE(s) \
le32_to_cpu ((SB_ONDISK_JP(s)->jp_journal_size))
#define SB_ONDISK_JOURNAL_1st_BLOCK(s) \
le32_to_cpu ((SB_ONDISK_JP(s)->jp_journal_1st_block))
#define SB_ONDISK_JOURNAL_DEVICE(s) \
le32_to_cpu ((SB_ONDISK_JP(s)->jp_journal_dev))
#define SB_ONDISK_RESERVED_FOR_JOURNAL(s) \
le16_to_cpu ((SB_V1_DISK_SUPER_BLOCK(s)->s_reserved_for_journal))
#define is_block_in_log_or_reserved_area(s, block) \
block >= SB_JOURNAL_1st_RESERVED_BLOCK(s) \
&& block < SB_JOURNAL_1st_RESERVED_BLOCK(s) + \
((!is_reiserfs_jr(SB_DISK_SUPER_BLOCK(s)) ? \
SB_ONDISK_JOURNAL_SIZE(s) + 1 : SB_ONDISK_RESERVED_FOR_JOURNAL(s)))
int is_reiserfs_3_5(struct reiserfs_super_block *rs);
int is_reiserfs_3_6(struct reiserfs_super_block *rs);
int is_reiserfs_jr(struct reiserfs_super_block *rs);
/* ReiserFS leaves the first 64k unused, so that partition labels have
enough space. If someone wants to write a fancy bootloader that
needs more than 64k, let us know, and this will be increased in size.
This number must be larger than than the largest block size on any
platform, or code will break. -Hans */
#define REISERFS_DISK_OFFSET_IN_BYTES (64 * 1024)
#define REISERFS_FIRST_BLOCK unused_define
#define REISERFS_JOURNAL_OFFSET_IN_BYTES REISERFS_DISK_OFFSET_IN_BYTES
/* the spot for the super in versions 3.5 - 3.5.10 (inclusive) */
#define REISERFS_OLD_DISK_OFFSET_IN_BYTES (8 * 1024)
/* reiserfs internal error code (used by search_by_key and fix_nodes)) */
#define CARRY_ON 0
#define REPEAT_SEARCH -1
#define IO_ERROR -2
#define NO_DISK_SPACE -3
#define NO_BALANCING_NEEDED (-4)
#define NO_MORE_UNUSED_CONTIGUOUS_BLOCKS (-5)
#define QUOTA_EXCEEDED -6
typedef __u32 b_blocknr_t;
typedef __le32 unp_t;
struct unfm_nodeinfo {
unp_t unfm_nodenum;
unsigned short unfm_freespace;
};
/* there are two formats of keys: 3.5 and 3.6
*/
#define KEY_FORMAT_3_5 0
#define KEY_FORMAT_3_6 1
/* there are two stat datas */
#define STAT_DATA_V1 0
#define STAT_DATA_V2 1
static inline struct reiserfs_inode_info *REISERFS_I(const struct inode *inode)
{
return container_of(inode, struct reiserfs_inode_info, vfs_inode);
}
static inline struct reiserfs_sb_info *REISERFS_SB(const struct super_block *sb)
{
return sb->s_fs_info;
}
/* Don't trust REISERFS_SB(sb)->s_bmap_nr, it's a u16
* which overflows on large file systems. */
static inline __u32 reiserfs_bmap_count(struct super_block *sb)
{
return (SB_BLOCK_COUNT(sb) - 1) / (sb->s_blocksize * 8) + 1;
}
static inline int bmap_would_wrap(unsigned bmap_nr)
{
return bmap_nr > ((1LL << 16) - 1);
}
/** this says about version of key of all items (but stat data) the
object consists of */
#define get_inode_item_key_version( inode ) \
((REISERFS_I(inode)->i_flags & i_item_key_version_mask) ? KEY_FORMAT_3_6 : KEY_FORMAT_3_5)
#define set_inode_item_key_version( inode, version ) \
({ if((version)==KEY_FORMAT_3_6) \
REISERFS_I(inode)->i_flags |= i_item_key_version_mask; \
else \
REISERFS_I(inode)->i_flags &= ~i_item_key_version_mask; })
#define get_inode_sd_version(inode) \
((REISERFS_I(inode)->i_flags & i_stat_data_version_mask) ? STAT_DATA_V2 : STAT_DATA_V1)
#define set_inode_sd_version(inode, version) \
({ if((version)==STAT_DATA_V2) \
REISERFS_I(inode)->i_flags |= i_stat_data_version_mask; \
else \
REISERFS_I(inode)->i_flags &= ~i_stat_data_version_mask; })
/* This is an aggressive tail suppression policy, I am hoping it
improves our benchmarks. The principle behind it is that percentage
space saving is what matters, not absolute space saving. This is
non-intuitive, but it helps to understand it if you consider that the
cost to access 4 blocks is not much more than the cost to access 1
block, if you have to do a seek and rotate. A tail risks a
non-linear disk access that is significant as a percentage of total
time cost for a 4 block file and saves an amount of space that is
less significant as a percentage of space, or so goes the hypothesis.
-Hans */
#define STORE_TAIL_IN_UNFM_S1(n_file_size,n_tail_size,n_block_size) \
(\
(!(n_tail_size)) || \
(((n_tail_size) > MAX_DIRECT_ITEM_LEN(n_block_size)) || \
( (n_file_size) >= (n_block_size) * 4 ) || \
( ( (n_file_size) >= (n_block_size) * 3 ) && \
( (n_tail_size) >= (MAX_DIRECT_ITEM_LEN(n_block_size))/4) ) || \
( ( (n_file_size) >= (n_block_size) * 2 ) && \
( (n_tail_size) >= (MAX_DIRECT_ITEM_LEN(n_block_size))/2) ) || \
( ( (n_file_size) >= (n_block_size) ) && \
( (n_tail_size) >= (MAX_DIRECT_ITEM_LEN(n_block_size) * 3)/4) ) ) \
)
/* Another strategy for tails, this one means only create a tail if all the
file would fit into one DIRECT item.
Primary intention for this one is to increase performance by decreasing
seeking.
*/
#define STORE_TAIL_IN_UNFM_S2(n_file_size,n_tail_size,n_block_size) \
(\
(!(n_tail_size)) || \
(((n_file_size) > MAX_DIRECT_ITEM_LEN(n_block_size)) ) \
)
/*
* values for s_umount_state field
*/
#define REISERFS_VALID_FS 1
#define REISERFS_ERROR_FS 2
//
// there are 5 item types currently
//
#define TYPE_STAT_DATA 0
#define TYPE_INDIRECT 1
#define TYPE_DIRECT 2
#define TYPE_DIRENTRY 3
#define TYPE_MAXTYPE 3
#define TYPE_ANY 15 // FIXME: comment is required
/***************************************************************************/
/* KEY & ITEM HEAD */
/***************************************************************************/
//
// directories use this key as well as old files
//
struct offset_v1 {
__le32 k_offset;
__le32 k_uniqueness;
} __attribute__ ((__packed__));
struct offset_v2 {
__le64 v;
} __attribute__ ((__packed__));
static inline __u16 offset_v2_k_type(const struct offset_v2 *v2)
{
__u8 type = le64_to_cpu(v2->v) >> 60;
return (type <= TYPE_MAXTYPE) ? type : TYPE_ANY;
}
static inline void set_offset_v2_k_type(struct offset_v2 *v2, int type)
{
v2->v =
(v2->v & cpu_to_le64(~0ULL >> 4)) | cpu_to_le64((__u64) type << 60);
}
static inline loff_t offset_v2_k_offset(const struct offset_v2 *v2)
{
return le64_to_cpu(v2->v) & (~0ULL >> 4);
}
static inline void set_offset_v2_k_offset(struct offset_v2 *v2, loff_t offset)
{
offset &= (~0ULL >> 4);
v2->v = (v2->v & cpu_to_le64(15ULL << 60)) | cpu_to_le64(offset);
}
/* Key of an item determines its location in the S+tree, and
is composed of 4 components */
struct reiserfs_key {
__le32 k_dir_id; /* packing locality: by default parent
directory object id */
__le32 k_objectid; /* object identifier */
union {
struct offset_v1 k_offset_v1;
struct offset_v2 k_offset_v2;
} __attribute__ ((__packed__)) u;
} __attribute__ ((__packed__));
struct in_core_key {
__u32 k_dir_id; /* packing locality: by default parent
directory object id */
__u32 k_objectid; /* object identifier */
__u64 k_offset;
__u8 k_type;
};
struct cpu_key {
struct in_core_key on_disk_key;
int version;
int key_length; /* 3 in all cases but direct2indirect and
indirect2direct conversion */
};
/* Our function for comparing keys can compare keys of different
lengths. It takes as a parameter the length of the keys it is to
compare. These defines are used in determining what is to be passed
to it as that parameter. */
#define REISERFS_FULL_KEY_LEN 4
#define REISERFS_SHORT_KEY_LEN 2
/* The result of the key compare */
#define FIRST_GREATER 1
#define SECOND_GREATER -1
#define KEYS_IDENTICAL 0
#define KEY_FOUND 1
#define KEY_NOT_FOUND 0
#define KEY_SIZE (sizeof(struct reiserfs_key))
#define SHORT_KEY_SIZE (sizeof (__u32) + sizeof (__u32))
/* return values for search_by_key and clones */
#define ITEM_FOUND 1
|
