summaryrefslogtreecommitdiff
path: root/fs/jbd2/journal.c
blob: c5ff177400ff52e07d802cccf7b7ce870ccb3d3a (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
/*
 * linux/fs/jbd2/journal.c
 *
 * Written by Stephen C. Tweedie <sct@redhat.com>, 1998
 *
 * Copyright 1998 Red Hat corp --- All Rights Reserved
 *
 * This file is part of the Linux kernel and is made available under
 * the terms of the GNU General Public License, version 2, or at your
 * option, any later version, incorporated herein by reference.
 *
 * Generic filesystem journal-writing code; part of the ext2fs
 * journaling system.
 *
 * This file manages journals: areas of disk reserved for logging
 * transactional updates.  This includes the kernel journaling thread
 * which is responsible for scheduling updates to the log.
 *
 * We do not actually manage the physical storage of the journal in this
 * file: that is left to a per-journal policy function, which allows us
 * to store the journal within a filesystem-specified area for ext2
 * journaling (ext2 can use a reserved inode for storing the log).
 */

#include <linux/module.h>
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/freezer.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/poison.h>
#include <linux/proc_fs.h>
#include <linux/debugfs.h>
#include <linux/seq_file.h>
#include <linux/math64.h>
#include <linux/hash.h>
#include <linux/log2.h>
#include <linux/vmalloc.h>
#include <linux/backing-dev.h>
#include <linux/bitops.h>
#include <linux/ratelimit.h>

#define CREATE_TRACE_POINTS
#include <trace/events/jbd2.h>

#include <asm/uaccess.h>
#include <asm/page.h>
#include <asm/system.h>

EXPORT_SYMBOL(jbd2_journal_extend);
EXPORT_SYMBOL(jbd2_journal_stop);
EXPORT_SYMBOL(jbd2_journal_lock_updates);
EXPORT_SYMBOL(jbd2_journal_unlock_updates);
EXPORT_SYMBOL(jbd2_journal_get_write_access);
EXPORT_SYMBOL(jbd2_journal_get_create_access);
EXPORT_SYMBOL(jbd2_journal_get_undo_access);
EXPORT_SYMBOL(jbd2_journal_set_triggers);
EXPORT_SYMBOL(jbd2_journal_dirty_metadata);
EXPORT_SYMBOL(jbd2_journal_release_buffer);
EXPORT_SYMBOL(jbd2_journal_forget);
#if 0
EXPORT_SYMBOL(journal_sync_buffer);
#endif
EXPORT_SYMBOL(jbd2_journal_flush);
EXPORT_SYMBOL(jbd2_journal_revoke);

EXPORT_SYMBOL(jbd2_journal_init_dev);
EXPORT_SYMBOL(jbd2_journal_init_inode);
EXPORT_SYMBOL(jbd2_journal_check_used_features);
EXPORT_SYMBOL(jbd2_journal_check_available_features);
EXPORT_SYMBOL(jbd2_journal_set_features);
EXPORT_SYMBOL(jbd2_journal_load);
EXPORT_SYMBOL(jbd2_journal_destroy);
EXPORT_SYMBOL(jbd2_journal_abort);
EXPORT_SYMBOL(jbd2_journal_errno);
EXPORT_SYMBOL(jbd2_journal_ack_err);
EXPORT_SYMBOL(jbd2_journal_clear_err);
EXPORT_SYMBOL(jbd2_log_wait_commit);
EXPORT_SYMBOL(jbd2_log_start_commit);
EXPORT_SYMBOL(jbd2_journal_start_commit);
EXPORT_SYMBOL(jbd2_journal_force_commit_nested);
EXPORT_SYMBOL(jbd2_journal_wipe);
EXPORT_SYMBOL(jbd2_journal_blocks_per_page);
EXPORT_SYMBOL(jbd2_journal_invalidatepage);
EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
EXPORT_SYMBOL(jbd2_journal_force_commit);
EXPORT_SYMBOL(jbd2_journal_file_inode);
EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
EXPORT_SYMBOL(jbd2_inode_cache);

static void __journal_abort_soft (journal_t *journal, int errno);
static int jbd2_journal_create_slab(size_t slab_size);

/*
 * Helper function used to manage commit timeouts
 */

static void commit_timeout(unsigned long __data)
{
	struct task_struct * p = (struct task_struct *) __data;

	wake_up_process(p);
}

/*
 * kjournald2: The main thread function used to manage a logging device
 * journal.
 *
 * This kernel thread is responsible for two things:
 *
 * 1) COMMIT:  Every so often we need to commit the current state of the
 *    filesystem to disk.  The journal thread is responsible for writing
 *    all of the metadata buffers to disk.
 *
 * 2) CHECKPOINT: We cannot reuse a used section of the log file until all
 *    of the data in that part of the log has been rewritten elsewhere on
 *    the disk.  Flushing these old buffers to reclaim space in the log is
 *    known as checkpointing, and this thread is responsible for that job.
 */

static int kjournald2(void *arg)
{
	journal_t *journal = arg;
	transaction_t *transaction;

	/*
	 * Set up an interval timer which can be used to trigger a commit wakeup
	 * after the commit interval expires
	 */
	setup_timer(&journal->j_commit_timer, commit_timeout,
			(unsigned long)current);

	/* Record that the journal thread is running */
	journal->j_task = current;
	wake_up(&journal->j_wait_done_commit);

	/*
	 * And now, wait forever for commit wakeup events.
	 */
	write_lock(&journal->j_state_lock);

loop:
	if (journal->j_flags & JBD2_UNMOUNT)
		goto end_loop;

	jbd_debug(1, "commit_sequence=%d, commit_request=%d\n",
		journal->j_commit_sequence, journal->j_commit_request);

	if (journal->j_commit_sequence != journal->j_commit_request) {
		jbd_debug(1, "OK, requests differ\n");
		write_unlock(&journal->j_state_lock);
		del_timer_sync(&journal->j_commit_timer);
		jbd2_journal_commit_transaction(journal);
		write_lock(&journal->j_state_lock);
		goto loop;
	}

	wake_up(&journal->j_wait_done_commit);
	if (freezing(current)) {
		/*
		 * The simpler the better. Flushing journal isn't a
		 * good idea, because that depends on threads that may
		 * be already stopped.
		 */
		jbd_debug(1, "Now suspending kjournald2\n");
		write_unlock(&journal->j_state_lock);
		try_to_freeze();
		write_lock(&journal->j_state_lock);
	} else {
		/*
		 * We assume on resume that commits are already there,
		 * so we don't sleep
		 */
		DEFINE_WAIT(wait);
		int should_sleep = 1;

		prepare_to_wait(&journal->j_wait_commit, &wait,
				TASK_INTERRUPTIBLE);
		if (journal->j_commit_sequence != journal->j_commit_request)
			should_sleep = 0;
		transaction = journal->j_running_transaction;
		if (transaction && time_after_eq(jiffies,
						transaction->t_expires))
			should_sleep = 0;
		if (journal->j_flags & JBD2_UNMOUNT)
			should_sleep = 0;
		if (should_sleep) {
			write_unlock(&journal->j_state_lock);
			schedule();
			write_lock(&journal->j_state_lock);
		}
		finish_wait(&journal->j_wait_commit, &wait);
	}

	jbd_debug(1, "kjournald2 wakes\n");

	/*
	 * Were we woken up by a commit wakeup event?
	 */
	transaction = journal->j_running_transaction;
	if (transaction && time_after_eq(jiffies, transaction->t_expires)) {
		journal->j_commit_request = transaction->t_tid;
		jbd_debug(1, "woke because of timeout\n");
	}
	goto loop;

end_loop:
	write_unlock(&journal->j_state_lock);
	del_timer_sync(&journal->j_commit_timer);
	journal->j_task = NULL;
	wake_up(&journal->j_wait_done_commit);
	jbd_debug(1, "Journal thread exiting.\n");
	return 0;
}

static int jbd2_journal_start_thread(journal_t *journal)
{
	struct task_struct *t;

	t = kthread_run(kjournald2, journal, "jbd2/%s",
			journal->j_devname);
	if (IS_ERR(t))
		return PTR_ERR(t);

	wait_event(journal->j_wait_done_commit, journal->j_task != NULL);
	return 0;
}

static void journal_kill_thread(journal_t *journal)
{
	write_lock(&journal->j_state_lock);
	journal->j_flags |= JBD2_UNMOUNT;

	while (journal->j_task) {
		wake_up(&journal->j_wait_commit);
		write_unlock(&journal->j_state_lock);
		wait_event(journal->j_wait_done_commit, journal->j_task == NULL);
		write_lock(&journal->j_state_lock);
	}
	write_unlock(&journal->j_state_lock);
}

/*
 * jbd2_journal_write_metadata_buffer: write a metadata buffer to the journal.
 *
 * Writes a metadata buffer to a given disk block.  The actual IO is not
 * performed but a new buffer_head is constructed which labels the data
 * to be written with the correct destination disk block.
 *
 * Any magic-number escaping which needs to be done will cause a
 * copy-out here.  If the buffer happens to start with the
 * JBD2_MAGIC_NUMBER, then we can't write it to the log directly: the
 * magic number is only written to the log for descripter blocks.  In
 * this case, we copy the data and replace the first word with 0, and we
 * return a result code which indicates that this buffer needs to be
 * marked as an escaped buffer in the corresponding log descriptor
 * block.  The missing word can then be restored when the block is read
 * during recovery.
 *
 * If the source buffer has already been modified by a new transaction
 * since we took the last commit snapshot, we use the frozen copy of
 * that data for IO.  If we end up using the existing buffer_head's data
 * for the write, then we *have* to lock the buffer to prevent anyone
 * else from using and possibly modifying it while the IO is in
 * progress.
 *
 * The function returns a pointer to the buffer_heads to be used for IO.
 *
 * We assume that the journal has already been locked in this function.
 *
 * Return value:
 *  <0: Error
 * >=0: Finished OK
 *
 * On success:
 * Bit 0 set == escape performed on the data
 * Bit 1 set == buffer copy-out performed (kfree the data after IO)
 */

int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
				  struct journal_head  *jh_in,
				  struct journal_head **jh_out,
				  unsigned long long blocknr)
{
	int need_copy_out = 0;
	int done_copy_out = 0;
	int do_escape = 0;
	char *mapped_data;
	struct buffer_head *new_bh;
	struct journal_head *new_jh;
	struct page *new_page;
	unsigned int new_offset;
	struct buffer_head *bh_in = jh2bh(jh_in);
	journal_t *journal = transaction->t_journal;

	/*
	 * The buffer really shouldn't be locked: only the current committing
	 * transaction is allowed to write it, so nobody else is allowed
	 * to do any IO.
	 *
	 * akpm: except if we're journalling data, and write() output is
	 * also part of a shared mapping, and another thread has
	 * decided to launch a writepage() against this buffer.
	 */
	J_ASSERT_BH(bh_in, buffer_jbddirty(bh_in));

retry_alloc:
	new_bh = alloc_buffer_head(GFP_NOFS);
	if (!new_bh) {
		/*
		 * Failure is not an option, but __GFP_NOFAIL is going
		 * away; so we retry ourselves here.
		 */
		congestion_wait(BLK_RW_ASYNC, HZ/50);
		goto retry_alloc;
	}

	/* keep subsequent assertions sane */
	new_bh->b_state = 0;
	init_buffer(new_bh, NULL, NULL);
	atomic_set(&new_bh->b_count, 1);
	new_jh = jbd2_journal_add_journal_head(new_bh);	/* This sleeps */

	/*
	 * If a new transaction has already done a buffer copy-out, then
	 * we use that version of the data for the commit.
	 */
	jbd_lock_bh_state(bh_in);
repeat:
	if (jh_in->b_frozen_data) {
		done_copy_out = 1;
		new_page = virt_to_page(jh_in->b_frozen_data);
		new_offset = offset_in_page(jh_in->b_frozen_data);
	} else {
		new_page = jh2bh(jh_in)->b_page;
		new_offset = offset_in_page(jh2bh(jh_in)->b_data);
	}

	mapped_data = kmap_atomic(new_page, KM_USER0);
	/*
	 * Fire data frozen trigger if data already wasn't frozen.  Do this
	 * before checking for escaping, as the trigger may modify the magic
	 * offset.  If a copy-out happens afterwards, it will have the correct
	 * data in the buffer.
	 */
	if (!done_copy_out)
		jbd2_buffer_frozen_trigger(jh_in, mapped_data + new_offset,
					   jh_in->b_triggers);

	/*
	 * Check for escaping
	 */
	if (*((__be32 *)(mapped_data + new_offset)) ==
				cpu_to_be32(JBD2_MAGIC_NUMBER)) {
		need_copy_out = 1;
		do_escape = 1;
	}
	kunmap_atomic(mapped_data, KM_USER0);

	/*
	 * Do we need to do a data copy?
	 */
	if (need_copy_out && !done_copy_out) {
		char *tmp;

		jbd_unlock_bh_state(bh_in);
		tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
		if (!tmp) {
			jbd2_journal_put_journal_head(new_jh);
			return -ENOMEM;
		}
		jbd_lock_bh_state(bh_in);
		if (jh_in->b_frozen_data) {
			jbd2_free(tmp, bh_in->b_size);
			goto repeat;
		}

		jh_in->b_frozen_data = tmp;
		mapped_data = kmap_atomic(new_page, KM_USER0);
		memcpy(tmp, mapped_data + new_offset, jh2bh(jh_in)->b_size);
		kunmap_atomic(mapped_data, KM_USER0);

		new_page = virt_to_page(tmp);
		new_offset = offset_in_page(tmp);
		done_copy_out = 1;

		/*
		 * This isn't strictly necessary, as we're using frozen
		 * data for the escaping, but it keeps consistency with
		 * b_frozen_data usage.
		 */
		jh_in->b_frozen_triggers = jh_in->b_triggers;
	}

	/*
	 * Did we need to do an escaping?  Now we've done all the
	 * copying, we can finally do so.
	 */
	if (do_escape) {
		mapped_data = kmap_atomic(new_page, KM_USER0);
		*((unsigned int *)(mapped_data + new_offset)) = 0;
		kunmap_atomic(mapped_data, KM_USER0);
	}

	set_bh_page(new_bh, new_page, new_offset);
	new_jh->b_transaction = NULL;
	new_bh->b_size = jh2bh(jh_in)->b_size;
	new_bh->b_bdev = transaction->t_journal->j_dev;
	new_bh->b_blocknr = blocknr;
	set_buffer_mapped(new_bh);
	set_buffer_dirty(new_bh);

	*jh_out = new_jh;

	/*
	 * The to-be-written buffer needs to get moved to the io queue,
	 * and the original buffer whose contents we are shadowing or
	 * copying is moved to the transaction's shadow queue.
	 */
	JBUFFER_TRACE(jh_in, "file as BJ_Shadow");
	spin_lock(&journal->j_list_lock);
	__jbd2_journal_file_buffer(jh_in, transaction, BJ_Shadow);
	spin_unlock(&journal->j_list_lock);
	jbd_unlock_bh_state(bh_in);

	JBUFFER_TRACE(new_jh, "file as BJ_IO");
	jbd2_journal_file_buffer(new_jh, transaction, BJ_IO);

	return do_escape | (done_copy_out << 1);
}

/*
 * Allocation code for the journal file.  Manage the space left in the
 * journal, so that we can begin checkpointing when appropriate.
 */

/*
 * __jbd2_log_space_left: Return the number of free blocks left in the journal.
 *
 * Called with the journal already locked.
 *
 * Called under j_state_lock
 */

int __jbd2_log_space_left(journal_t *journal)
{
	int left = journal->j_free;

	/* assert_spin_locked(&journal->j_state_lock); */

	/*
	 * Be pessimistic here about the number of those free blocks which
	 * might be required for log descriptor control blocks.
	 */

#define MIN_LOG_RESERVED_BLOCKS 32 /* Allow for rounding errors */

	left -= MIN_LOG_RESERVED_BLOCKS;

	if (left <= 0)
		return 0;
	left -= (left >> 3);
	return left;
}

/*
 * Called with j_state_lock locked for writing.
 * Returns true if a transaction commit was started.
 */
int __jbd2_log_start_commit(journal_t *journal, tid_t target)
{
	/*
	 * The only transaction we can possibly wait upon is the
	 * currently running transaction (if it exists).  Otherwise,
	 * the target tid must be an old one.
	 */
	if (journal->j_running_transaction &&
	    journal->j_running_transaction->t_tid == target) {
		/*
		 * We want a new commit: OK, mark the request and wakeup the
		 * commit thread.  We do _not_ do the commit ourselves.
		 */

		journal->j_commit_request = target;
		jbd_debug(1, "JBD2: requesting commit %d/%d\n",
			  journal->j_commit_request,
			  journal->j_commit_sequence);
		wake_up(&journal->j_wait_commit);
		return 1;
	} else if (!tid_geq(journal->j_commit_request, target))
		/* This should never happen, but if it does, preserve
		   the evidence before kjournald goes into a loop and
		   increments j_commit_sequence beyond all recognition. */
		WARN_ONCE(1, "JBD2: bad log_start_commit: %u %u %u %u\n",
			  journal->j_commit_request,
			  journal->j_commit_sequence,
			  target, journal->j_running_transaction ? 
			  journal->j_running_transaction->t_tid : 0);
	return 0;
}

int jbd2_log_start_commit(journal_t *journal, tid_t tid)
{
	int ret;

	write_lock(&journal->j_state_lock);
	ret = __jbd2_log_start_commit(journal, tid);
	write_unlock(&journal->j_state_lock);
	return ret;
}

/*
 * Force and wait upon a commit if the calling process is not within
 * transaction.  This is used for forcing out undo-protected data which contains
 * bitmaps, when the fs is running out of space.
 *
 * We can only force the running transaction if we don't have an active handle;
 * otherwise, we will deadlock.
 *
 * Returns true if a transaction was started.
 */
int jbd2_journal_force_commit_nested(journal_t *journal)
{
	transaction_t *transaction = NULL;
	tid_t tid;
	int need_to_start = 0;

	read_lock(&journal->j_state_lock);
	if (journal->j_running_transaction && !current->journal_info) {
		transaction = journal->j_running_transaction;
		if (!tid_geq(journal->j_commit_request, transaction->t_tid))
			need_to_start = 1;
	} else if (journal->j_committing_transaction)
		transaction = journal->j_committing_transaction;

	if (!transaction) {
		read_unlock(&journal->j_state_lock);
		return 0;	/* Nothing to retry */
	}

	tid = transaction->t_tid;
	read_unlock(&journal->j_state_lock);
	if (need_to_start)
		jbd2_log_start_commit(journal, tid);
	jbd2_log_wait_commit(journal, tid);
	return 1;
}

/*
 * Start a commit of the current running transaction (if any).  Returns true
 * if a transaction is going to be committed (or is currently already
 * committing), and fills its tid in at *ptid
 */
int jbd2_journal_start_commit(journal_t *journal, tid_t *ptid)
{
	int ret = 0;

	write_lock(&journal->j_state_lock);
	if (journal->j_running_transaction) {
		tid_t tid = journal->j_running_transaction->t_tid;

		__jbd2_log_start_commit(journal, tid);
		/* There's a running transaction and we've just made sure
		 * it's commit has been scheduled. */
		if (ptid)
			*ptid = tid;
		ret = 1;
	} else if (journal->j_committing_transaction) {
		/*
		 * If ext3_write_super() recently started a commit, then we
		 * have to wait for completion of that transaction
		 */
		if (ptid)
			*ptid = journal->j_committing_transaction->t_tid;
		ret = 1;
	}
	write_unlock(&journal->j_state_lock);
	return ret;
}

/*
 * Return 1 if a given transaction has not yet sent barrier request
 * connected with a transaction commit. If 0 is returned, transaction
 * may or may not have sent the barrier. Used to avoid sending barrier
 * twice in common cases.
 */
int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid)
{
	int ret = 0;
	transaction_t *commit_trans;

	if (!(journal->j_flags & JBD2_BARRIER))
		return 0;
	read_lock(&journal->j_state_lock);
	/* Transaction already committed? */
	if (tid_geq(journal->j_commit_sequence, tid))
		goto out;
	commit_trans = journal->j_committing_transaction;
	if (!commit_trans || commit_trans->t_tid != tid) {
		ret = 1;
		goto out;
	}
	/*
	 * Transaction is being committed and we already proceeded to
	 * submitting a flush to fs partition?
	 */
	if (journal->j_fs_dev != journal->j_dev) {
		if (!commit_trans->t_need_data_flush ||
		    commit_trans->t_state >= T_COMMIT_DFLUSH)
			goto out;
	} else {
		if (commit_trans->t_state >= T_COMMIT_JFLUSH)
			goto out;
	}
	ret = 1;
out:
	read_unlock(&journal->j_state_lock);
	return ret;
}
EXPORT_SYMBOL(jbd2_trans_will_send_data_barrier);

/*
 * Wait for a specified commit to complete.
 * The caller may not hold the journal lock.
 */
int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
{
	int err = 0;

	read_lock(&journal->j_state_lock);
#ifdef CONFIG_JBD2_DEBUG
	if (!tid_geq(journal->j_commit_request, tid)) {
		printk(KERN_EMERG
		       "%s: error: j_commit_request=%d, tid=%d\n",
		       __func__, journal->j_commit_request, tid);
	}
#endif
	while (tid_gt(tid, journal->j_commit_sequence)) {
		jbd_debug(1, "JBD2: want %d, j_commit_sequence=%d\n",
				  tid, journal->j_commit_sequence);
		wake_up(&journal->j_wait_commit);
		read_unlock(&journal->j_state_lock);
		wait_event(journal->j_wait_done_commit,
				!tid_gt(tid, journal->j_commit_sequence));
		read_lock(&journal->j_state_lock);
	}
	read_unlock(&journal->j_state_lock);

	if (unlikely(is_journal_aborted(journal))) {
		printk(KERN_EMERG "journal commit I/O error\n");
		err = -EIO;
	}
	return err;
}

/*
 * Log buffer allocation routines:
 */

int jbd2_journal_next_log_block(journal_t *journal, unsigned long long *retp)
{
	unsigned long blocknr;

	write_lock(&journal->j_state_lock);
	J_ASSERT(journal->j_free > 1);

	blocknr = journal->j_head;
	journal->j_head++;
	journal->j_free--;
	if (journal->j_head == journal->j_last)
		journal->j_head = journal->j_first;
	write_unlock(&journal->j_state_lock);
	return jbd2_journal_bmap(journal, blocknr, retp);
}

/*
 * Conversion of logical to physical block numbers for the journal
 *
 * On external journals the journal blocks are identity-mapped, so
 * this is a no-op.  If needed, we can use j_blk_offset - everything is
 * ready.
 */
int jbd2_journal_bmap(journal_t *journal, unsigned long blocknr,
		 unsigned long long *retp)
{
	int err = 0;
	unsigned long long ret;

	if (journal->j_inode) {
		ret = bmap(journal->j_inode, blocknr);
		if (ret)
			*retp = ret;
		else {
			printk(KERN_ALERT "%s: journal block not found "
					"at offset %lu on %s\n",
			       __func__, blocknr, journal->j_devname);
			err = -EIO;
			__journal_abort_soft(journal, err);
		}
	} else {
		*retp = blocknr; /* +journal->j_blk_offset */
	}
	return err;
}

/*
 * We play buffer_head aliasing tricks to write data/metadata blocks to
 * the journal without copying their contents, but for journal
 * descriptor blocks we do need to generate bona fide buffers.
 *
 * After the caller of jbd2_journal_get_descriptor_buffer() has finished modifying
 * the buffer's contents they really should run flush_dcache_page(bh->b_page).
 * But we don't bother doing that, so there will be coherency problems with
 * mmaps of blockdevs which hold live JBD-controlled filesystems.
 */
struct journal_head *jbd2_journal_get_descriptor_buffer(journal_t *journal)
{
	struct buffer_head *bh;
	unsigned long long blocknr;
	int err;

	err = jbd2_journal_next_log_block(journal, &blocknr);

	if (err)
		return NULL;

	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
	if (!bh)
		return NULL;
	lock_buffer(bh);
	memset(bh->b_data, 0, journal->j_blocksize);
	set_buffer_uptodate(bh);
	unlock_buffer(bh);
	BUFFER_TRACE(bh, "return this buffer");
	return jbd2_journal_add_journal_head(bh);
}

/*
 * Return tid of the oldest transaction in the journal and block in the journal
 * where the transaction starts.
 *
 * If the journal is now empty, return which will be the next transaction ID
 * we will write and where will that transaction start.
 *
 * The return value is 0 if journal tail cannot be pushed any further, 1 if
 * it can.
 */
int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
			      unsigned long *block)
{
	transaction_t *transaction;
	int ret;

	read_lock(&journal->j_state_lock);
	spin_lock(&journal->j_list_lock);
	transaction = journal->j_checkpoint_transactions;
	if (transaction) {
		*tid = transaction->t_tid;
		*block = transaction->t_log_start;
	} else if ((transaction = journal->j_committing_transaction) != NULL) {
		*tid = transaction->t_tid;
		*block = transaction->t_log_start;
	} else if ((transaction = journal->j_running_transaction) != NULL) {
		*tid = transaction->t_tid;
		*block = journal->j_head;
	} else {
		*tid = journal->j_transaction_sequence;
		*block = journal->j_head;
	}
	ret = tid_gt(*tid, journal->j_tail_sequence);
	spin_unlock(&journal->j_list_lock);
	read_unlock(&journal->j_state_lock);

	return ret;
}

/*
 * Update information in journal structure and in on disk journal superblock
 * about log tail. This function does not check whether information passed in
 * really pushes log tail further. It's responsibility of the caller to make
 * sure provided log tail information is valid (e.g. by holding
 * j_checkpoint_mutex all the time between computing log tail and calling this
 * function as is the case with jbd2_cleanup_journal_tail()).
 *
 * Requires j_checkpoint_mutex
 */
void __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
{
	unsigned long freed;

	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));

	/*
	 * We cannot afford for write to remain in drive's caches since as
	 * soon as we update j_tail, next transaction can start reusing journal
	 * space and if we lose sb update during power failure we'd replay
	 * old transaction with possibly newly overwritten data.
	 */
	jbd2_journal_update_sb_log_tail(journal, tid, block, WRITE_FUA);
	write_lock(&journal->j_state_lock);
	freed = block - journal->j_tail;
	if (block < journal->j_tail)
		freed += journal->j_last - journal->j_first;

	trace_jbd2_update_log_tail(journal, tid, block, freed);
	jbd_debug(1,
		  "Cleaning journal tail from %d to %d (offset %lu), "
		  "freeing %lu\n",
		  journal->j_tail_sequence, tid, block, freed);

	journal->j_free += freed;
	journal->j_tail_sequence = tid;
	journal->j_tail = block;
	write_unlock(&journal->j_state_lock);
}

struct jbd2_stats_proc_session {
	journal_t *journal;
	struct transaction_stats_s *stats;
	int start;
	int max;
};

static void *jbd2_seq_info_start(struct seq_file *seq, loff_t *pos)
{
	return *pos ? NULL : SEQ_START_TOKEN;
}

static void *jbd2_seq_info_next(struct seq_file *seq, void *v, loff_t *pos)
{
	return NULL;
}

static int jbd2_seq_info_show(struct seq_file *seq, void *v)
{
	struct jbd2_stats_proc_session *s = seq->private;

	if (v != SEQ_START_TOKEN)
		return 0;
	seq_printf(seq, "%lu transaction, each up to %u blocks\n",
			s->stats->ts_tid,
			s->journal->j_max_transaction_buffers);
	if (s->stats->ts_tid == 0)
		return 0;
	seq_printf(seq, "average: \n  %ums waiting for transaction\n",
	    jiffies_to_msecs(s->stats->run.rs_wait / s->stats->ts_tid));
	seq_printf(seq, "  %ums running transaction\n",
	    jiffies_to_msecs(s->stats->run.rs_running / s->stats->ts_tid));
	seq_printf(seq, "  %ums transaction was being locked\n",
	    jiffies_to_msecs(s->stats->run.rs_locked / s->stats->ts_tid));
	seq_printf(seq, "  %ums flushing data (in ordered mode)\n",
	    jiffies_to_msecs(s->stats->run.rs_flushing / s->stats->ts_tid));
	seq_printf(seq, "  %ums logging transaction\n",
	    jiffies_to_msecs(s->stats->run.rs_logging / s->stats->ts_tid));
	seq_printf(seq, "  %lluus average transaction commit time\n",
		   div_u64(s->journal->j_average_commit_time, 1000));
	seq_printf(seq, "  %lu handles per transaction\n",
	    s->stats->run.rs_handle_count / s->stats->ts_tid);
	seq_printf(seq, "  %lu blocks per transaction\n",
	    s->stats->run.rs_blocks / s->stats->ts_tid);
	seq_printf(seq, "  %lu logged blocks per transaction\n",
	    s->stats->run.rs_blocks_logged / s->stats->ts_tid);
	return 0;
}

static void jbd2_seq_info_stop(struct seq_file *seq, void *v)
{
}

static const struct seq_operations jbd2_seq_info_ops = {
	.start  = jbd2_seq_info_start,
	.next   = jbd2_seq_info_next,
	.stop   = jbd2_seq_info_stop,
	.show   = jbd2_seq_info_show,
};

static int jbd2_seq_info_open(struct inode *inode, struct file *file)
{
	journal_t *journal = PDE(inode)->data;
	struct jbd2_stats_proc_session *s;
	int rc, size;

	s = kmalloc(sizeof(*s), GFP_KERNEL);
	if (s == NULL)
		return -ENOMEM;
	size = sizeof(struct transaction_stats_s);
	s->stats = kmalloc(size, GFP_KERNEL);
	if (s->stats == NULL) {
		kfree(s);
		return -ENOMEM;
	}
	spin_lock(&journal->j_history_lock);
	memcpy(s->stats, &journal->j_stats, size);
	s->journal = journal;
	spin_unlock(&journal->j_history_lock);

	rc = seq_open(file, &jbd2_seq_info_ops);
	if (rc == 0) {
		struct seq_file *m = file->private_data;
		m->private = s;
	} else {
		kfree(s->stats);
		kfree(s);
	}
	return rc;

}

static int jbd2_seq_info_release(struct inode *inode, struct file *file)
{
	struct seq_file *seq = file->private_data;
	struct jbd2_stats_proc_session *s = seq->private;
	kfree(s->stats);
	kfree(s);
	return seq_release(inode, file);
}

static const struct file_operations jbd2_seq_info_fops = {
	.owner		= THIS_MODULE,
	.open           = jbd2_seq_info_open,
	.read           = seq_read,
	.llseek         = seq_lseek,
	.release        = jbd2_seq_info_release,
};

static struct proc_dir_entry *proc_jbd2_stats;

static void jbd2_stats_proc_init(journal_t *journal)
{
	journal->j_proc_entry = proc_mkdir(journal->j_devname, proc_jbd2_stats);
	if (journal->j_proc_entry) {
		proc_create_data("info", S_IRUGO, journal->j_proc_entry,
				 &jbd2_seq_info_fops, journal);
	}
}

static void jbd2_stats_proc_exit(journal_t *journal)
{
	remove_proc_entry("info", journal->j_proc_entry);
	remove_proc_entry(journal->j_devname, proc_jbd2_stats);
}

/*
 * Management for journal control blocks: functions to create and
 * destroy journal_t structures, and to initialise and read existing
 * journal blocks from disk.  */

/* First: create and setup a journal_t object in memory.  We initialise
 * very few fields yet: that has to wait until we have created the
 * journal structures from from scratch, or loaded them from disk. */

static journal_t * journal_init_common (void)
{
	journal_t *journal;
	int err;

	journal = kzalloc(sizeof(*journal), GFP_KERNEL);
	if (!journal)
		return NULL;

	init_waitqueue_head(&journal->j_wait_transaction_locked);
	init_waitqueue_head(&journal->j_wait_logspace);
	init_waitqueue_head(&journal->j_wait_done_commit);
	init_waitqueue_head(&journal->j_wait_checkpoint);
	init_waitqueue_head(&journal->j_wait_commit);
	init_waitqueue_head(&journal->j_wait_updates);
	mutex_init(&journal->j_barrier);
	mutex_init(&journal->j_checkpoint_mutex);
	spin_lock_init(&journal->j_revoke_lock);
	spin_lock_init(&journal->j_list_lock);
	rwlock_init(&journal->j_state_lock);

	journal->j_commit_interval = (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE);
	journal->j_min_batch_time = 0;
	journal->j_max_batch_time = 15000; /* 15ms */

	/* The journal is marked for error until we succeed with recovery! */
	journal->j_flags = JBD2_ABORT;

	/* Set up a default-sized revoke table for the new mount. */
	err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
	if (err) {
		kfree(journal);
		return NULL;
	}

	spin_lock_init(&journal->j_history_lock);

	return journal;
}

/* jbd2_journal_init_dev and jbd2_journal_init_inode:
 *
 * Create a journal structure assigned some fixed set of disk blocks to
 * the journal.  We don't actually touch those disk blocks yet, but we
 * need to set up all of the mapping information to tell the journaling
 * system where the journal blocks are.
 *
 */

/**
 *  journal_t * jbd2_journal_init_dev() - creates and initialises a journal structure
 *  @bdev: Block device on which to create the journal
 *  @fs_dev: Device which hold journalled filesystem for this journal.
 *  @start: Block nr Start of journal.
 *  @len:  Length of the journal in blocks.
 *  @blocksize: blocksize of journalling device
 *
 *  Returns: a newly created journal_t *
 *
 *  jbd2_journal_init_dev creates a journal which maps a fixed contiguous
 *  range of blocks on an arbitrary block device.
 *
 */
journal_t * jbd2_journal_init_dev(struct block_device *bdev,
			struct block_device *fs_dev,
			unsigned long long start, int len, int blocksize)
{
	journal_t *journal = journal_init_common();
	struct buffer_head *bh;
	char *p;
	int n;

	if (!journal)
		return NULL;

	/* journal descriptor can store up to n blocks -bzzz */
	journal->j_blocksize = blocksize;
	journal->j_dev = bdev;
	journal->j_fs_dev = fs_dev;
	journal->j_blk_offset = start;
	journal->j_maxlen = len;
	bdevname(journal->j_dev, journal->j_devname);
	p = journal->j_devname;
	while ((p = strchr(p, '/')))
		*p = '!';
	jbd2_stats_proc_init(journal);
	n = journal->j_blocksize / sizeof(journal_block_tag_t);
	journal->j_wbufsize = n;
	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
	if (!journal->j_wbuf) {
		printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n",
			__func__);
		goto out_err;
	}

	bh = __getblk(journal->j_dev, start, journal->j_blocksize);
	if (!bh) {
		printk(KERN_ERR
		       "%s: Cannot get buffer for journal superblock\n",
		       __func__);
		goto out_err;
	}
	journal->j_sb_buffer = bh;
	journal->j_superblock = (journal_superblock_t *)bh->b_data;

	return journal;
out_err:
	kfree(journal->j_wbuf);
	jbd2_stats_proc_exit(journal);
	kfree(journal);
	return NULL;
}

/**
 *  journal_t * jbd2_journal_init_inode () - creates a journal which maps to a inode.
 *  @inode: An inode to create the journal in
 *
 * jbd2_journal_init_inode creates a journal which maps an on-disk inode as
 * the journal.  The inode must exist already, must support bmap() and
 * must have all data blocks preallocated.
 */
journal_t * jbd2_journal_init_inode (struct inode *inode)
{
	struct buffer_head *bh;
	journal_t *journal = journal_init_common();
	char *p;
	int err;
	int n;
	unsigned long long blocknr;

	if (!journal)
		return NULL;

	journal->j_dev = journal->j_fs_dev = inode->i_sb->s_bdev;
	journal->j_inode = inode;
	bdevname(journal->j_dev, journal->j_devname);
	p = journal->j_devname;
	while ((p = strchr(p, '/')))
		*p = '!';
	p = journal->j_devname + strlen(journal->j_devname);
	sprintf(p, "-%lu", journal->j_inode->i_ino);
	jbd_debug(1,
		  "journal %p: inode %s/%ld, size %Ld, bits %d, blksize %ld\n",
		  journal, inode->i_sb->s_id, inode->i_ino,
		  (long long) inode->i_size,
		  inode->i_sb->s_blocksize_bits, inode->i_sb->s_blocksize);

	journal->j_maxlen = inode->i_size >> inode->i_sb->s_blocksize_bits;
	journal->j_blocksize = inode->i_sb->s_blocksize;
	jbd2_stats_proc_init(journal);

	/* journal descriptor can store up to n blocks -bzzz */
	n = journal->j_blocksize / sizeof(journal_block_tag_t);
	journal->j_wbufsize = n;
	journal->j_wbuf = kmalloc(n * sizeof(struct buffer_head*), GFP_KERNEL);
	if (!journal->j_wbuf) {
		printk(KERN_ERR "%s: Can't allocate bhs for commit thread\n",
			__func__);
		goto out_err;
	}

	err = jbd2_journal_bmap(journal, 0, &blocknr);
	/* If that failed, give up */
	if (err) {
		printk(KERN_ERR "%s: Cannot locate journal superblock\n",
		       __func__);
		goto out_err;
	}

	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
	if (!bh) {
		printk(KERN_ERR
		       "%s: Cannot get buffer for journal superblock\n",
		       __func__);
		goto out_err;
	}
	journal->j_sb_buffer = bh;
	journal->j_superblock = (journal_superblock_t *)bh->b_data;

	return journal;
out_err:
	kfree(journal->j_wbuf);
	jbd2_stats_proc_exit(journal);
	kfree(journal);
	return NULL;
}

/*
 * If the journal init or create aborts, we need to mark the journal
 * superblock as being NULL to prevent the journal destroy from writing
 * back a bogus superblock.
 */
static void journal_fail_superblock (journal_t *journal)
{
	struct buffer_head *bh = journal->j_sb_buffer;
	brelse(bh);
	journal->j_sb_buffer = NULL;
}

/*
 * Given a journal_t structure, initialise the various fields for
 * startup of a new journaling session.  We use this both when creating
 * a journal, and after recovering an old journal to reset it for
 * subsequent use.
 */

static int journal_reset(journal_t *journal)
{
	journal_superblock_t *sb = journal->j_superblock;
	unsigned long long first, last;

	first = be32_to_cpu(sb->s_first);
	last = be32_to_cpu(sb->s_maxlen);
	if (first + JBD2_MIN_JOURNAL_BLOCKS > last + 1) {
		printk(KERN_ERR "JBD2: Journal too short (blocks %llu-%llu).\n",
		       first, last);
		journal_fail_superblock(journal);
		return -EINVAL;
	}

	journal->j_first = first;
	journal->j_last = last;

	journal->j_head = first;
	journal->j_tail = first;
	journal->j_free = last - first;

	journal->j_tail_sequence = journal->j_transaction_sequence;
	journal->j_commit_sequence = journal->j_transaction_sequence - 1;
	journal->j_commit_request = journal->j_commit_sequence;

	journal->j_max_transaction_buffers = journal->j_maxlen / 4;

	/*
	 * As a special case, if the on-disk copy is already marked as needing
	 * no recovery (s_start == 0), then we can safely defer the superblock
	 * update until the next commit by setting JBD2_FLUSHED.  This avoids
	 * attempting a write to a potential-readonly device.
	 */
	if (sb->s_start == 0) {
		jbd_debug(1, "JBD2: Skipping superblock update on recovered sb "
			"(start %ld, seq %d, errno %d)\n",
			journal->j_tail, journal->j_tail_sequence,
			journal->j_errno);
		journal->j_flags |= JBD2_FLUSHED;
	} else {
		/* Lock here to make assertions happy... */
		mutex_lock(&journal->j_checkpoint_mutex);
		/*
		 * Update log tail information. We use WRITE_FUA since new
		 * transaction will start reusing journal space and so we
		 * must make sure information about current log tail is on
		 * disk before that.
		 */
		jbd2_journal_update_sb_log_tail(journal,
						journal->j_tail_sequence,
						journal->j_tail,
						WRITE_FUA);
		mutex_unlock(&journal->j_checkpoint_mutex);
	}
	return jbd2_journal_start_thread(journal);
}

static void jbd2_write_superblock(journal_t *journal, int write_op)
{
	struct buffer_head *bh = journal->j_sb_buffer;
	int ret;

	trace_jbd2_write_superblock(journal, write_op);
	if (!(journal->j_flags & JBD2_BARRIER))
		write_op &= ~(REQ_FUA | REQ_FLUSH);
	lock_buffer(bh);
	if (buffer_write_io_error(bh)) {
		/*
		 * Oh, dear.  A previous attempt to write the journal
		 * superblock failed.  This could happen because the
		 * USB device was yanked out.  Or it could happen to
		 * be a transient write error and maybe the block will
		 * be remapped.  Nothing we can do but to retry the
		 * write and hope for the best.
		 */
		printk(KERN_ERR "JBD2: previous I/O error detected "
		       "for journal superblock update for %s.\n",
		       journal->j_devname);
		clear_buffer_write_io_error(bh);
		set_buffer_uptodate(bh);
	}
	get_bh(bh);
	bh->b_end_io = end_buffer_write_sync;
	ret = submit_bh(write_op, bh);
	wait_on_buffer(bh);
	if (buffer_write_io_error(bh)) {
		clear_buffer_write_io_error(bh);
		set_buffer_uptodate(bh);
		ret = -EIO;
	}
	if (ret) {
		printk(KERN_ERR "JBD2: Error %d detected when updating "
		       "journal superblock for %s.\n", ret,
		       journal->j_devname);
	}
}

/**
 * jbd2_journal_update_sb_log_tail() - Update log tail in journal sb on disk.
 * @journal: The journal to update.
 * @tail_tid: TID of the new transaction at the tail of the log
 * @tail_block: The first block of the transaction at the tail of the log
 * @write_op: With which operation should we write the journal sb
 *
 * Update a journal's superblock information about log tail and write it to
 * disk, waiting for the IO to complete.
 */
void jbd2_journal_update_sb_log_tail(journal_t *journal, tid_t tail_tid,
				     unsigned long tail_block, int write_op)
{
	journal_superblock_t *sb = journal->j_superblock;

	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
	jbd_debug(1, "JBD2: updating superblock (start %lu, seq %u)\n",
		  tail_block, tail_tid);

	sb->s_sequence = cpu_to_be32(tail_tid);
	sb->s_start    = cpu_to_be32(tail_block);

	jbd2_write_superblock(journal, write_op);

	/* Log is no longer empty */
	write_lock(&journal->j_state_lock);
	WARN_ON(!sb->s_sequence);
	journal->j_flags &= ~JBD2_FLUSHED;
	write_unlock(&journal->j_state_lock);
}

/**
 * jbd2_mark_journal_empty() - Mark on disk journal as empty.
 * @journal: The journal to update.
 *
 * Update a journal's dynamic superblock fields to show that journal is empty.
 * Write updated superblock to disk waiting for IO to complete.
 */
static void jbd2_mark_journal_empty(journal_t *journal)
{
	journal_superblock_t *sb = journal->j_superblock;

	BUG_ON(!mutex_is_locked(&journal->j_checkpoint_mutex));
	read_lock(&journal->j_state_lock);
	jbd_debug(1, "JBD2: Marking journal as empty (seq %d)\n",
		  journal->j_tail_sequence);

	sb->s_sequence = cpu_to_be32(journal->j_tail_sequence);
	sb->s_start    = cpu_to_be32(0);
	read_unlock(&journal->j_state_lock);

	jbd2_write_superblock(journal, WRITE_FUA);

	/* Log is no longer empty */
	write_lock(&journal->j_state_lock);
	journal->j_flags |= JBD2_FLUSHED;
	write_unlock(&journal->j_state_lock);
}


/**
 * jbd2_journal_update_sb_errno() - Update error in the journal.
 * @journal: The journal to update.
 *
 * Update a journal's errno.  Write updated superblock to disk waiting for IO
 * to complete.
 */
static void jbd2_journal_update_sb_errno(journal_t *journal)
{
	journal_superblock_t *sb = journal->j_superblock;

	read_lock(&journal->j_state_lock);
	jbd_debug(1, "JBD2: updating superblock error (errno %d)\n",
		  journal->j_errno);
	sb->s_errno    = cpu_to_be32(journal->j_errno);
	read_unlock(&journal->j_state_lock);

	jbd2_write_superblock(journal, WRITE_SYNC);
}

/*
 * Read the superblock for a given journal, performing initial
 * validation of the format.
 */
static int journal_get_superblock(journal_t *journal)
{
	struct buffer_head *bh;
	journal_superblock_t *sb;
	int err = -EIO;

	bh = journal->j_sb_buffer;

	J_ASSERT(bh != NULL);
	if (!buffer_uptodate(bh)) {
		ll_rw_block(READ, 1, &bh);
		wait_on_buffer(bh);
		if (!buffer_uptodate(bh)) {
			printk(KERN_ERR
				"JBD2: IO error reading journal superblock\n");
			goto out;
		}
	}

	sb = journal->j_superblock;

	err = -EINVAL;

	if (sb->s_header.h_magic != cpu_to_be32(JBD2_MAGIC_NUMBER) ||
	    sb->s_blocksize != cpu_to_be32(journal->j_blocksize)) {
		printk(KERN_WARNING "JBD2: no valid journal superblock found\n");
		goto out;
	}

	switch(be32_to_cpu(sb->s_header.h_blocktype)) {
	case JBD2_SUPERBLOCK_V1:
		journal->j_format_version = 1;
		break;
	case JBD2_SUPERBLOCK_V2:
		journal->j_format_version = 2;
		break;
	default:
		printk(KERN_WARNING "JBD2: unrecognised superblock format ID\n");
		goto out;
	}

	if (be32_to_cpu(sb->s_maxlen) < journal->j_maxlen)
		journal->j_maxlen = be32_to_cpu(sb->s_maxlen);
	else if (be32_to_cpu(sb->s_maxlen) > journal->j_maxlen) {
		printk(KERN_WARNING "JBD2: journal file too short\n");
		goto out;
	}

	if (be32_to_cpu(sb->s_first) == 0 ||
	    be32_to_cpu(sb->s_first) >= journal->j_maxlen) {
		printk(KERN_WARNING
			"JBD2: Invalid start block of journal: %u\n",
			be32_to_cpu(sb->s_first));
		goto out;
	}

	return 0;

out:
	journal_fail_superblock(journal);
	return err;
}

/*
 * Load the on-disk journal superblock and read the key fields into the
 * journal_t.
 */

static int load_superblock(journal_t *journal)
{
	int err;
	journal_superblock_t *sb;

	err = journal_get_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;

	journal->j_tail_sequence = be32_to_cpu(sb->s_sequence);
	journal->j_tail = be32_to_cpu(sb->s_start);
	journal->j_first = be32_to_cpu(sb->s_first);
	journal->j_last = be32_to_cpu(sb->s_maxlen);
	journal->j_errno = be32_to_cpu(sb->s_errno);

	return 0;
}


/**
 * int jbd2_journal_load() - Read journal from disk.
 * @journal: Journal to act on.
 *
 * Given a journal_t structure which tells us which disk blocks contain
 * a journal, read the journal from disk to initialise the in-memory
 * structures.
 */
int jbd2_journal_load(journal_t *journal)
{
	int err;
	journal_superblock_t *sb;

	err = load_superblock(journal);
	if (err)
		return err;

	sb = journal->j_superblock;
	/* If this is a V2 superblock, then we have to check the
	 * features flags on it. */

	if (journal->j_format_version >= 2) {
		if ((sb->s_feature_ro_compat &
		     ~cpu_to_be32(JBD2_KNOWN_ROCOMPAT_FEATURES)) ||
		    (sb->s_feature_incompat &
		     ~cpu_to_be32(JBD2_KNOWN_INCOMPAT_FEATURES))) {
			printk(KERN_WARNING
				"JBD2: Unrecognised features on journal\n");
			return -EINVAL;
		}
	}

	/*
	 * Create a slab for this blocksize
	 */
	err = jbd2_journal_create_slab(be32_to_cpu(sb->s_blocksize));
	if (err)
		return err;

	/* Let the recovery code check whether it needs to recover any
	 * data from the journal. */
	if (jbd2_journal_recover(journal))
		goto recovery_error;

	if (journal->j_failed_commit) {
		printk(KERN_ERR "JBD2: journal transaction %u on %s "
		       "is corrupt.\n", journal->j_failed_commit,
		       journal->j_devname);
		return -EIO;
	}

	/* OK, we've finished with the dynamic journal bits:
	 * reinitialise the dynamic contents of the superblock in memory
	 * and reset them on disk. */
	if (journal_reset(journal))
		goto recovery_error;

	journal->j_flags &= ~JBD2_ABORT;
	journal->j_flags |= JBD2_LOADED;
	return 0;

recovery_error:
	printk(KERN_WARNING "JBD2: recovery failed\n");
	return -EIO;
}

/**
 * void jbd2_journal_destroy() - Release a journal_t structure.
 * @journal: Journal to act on.
 *
 * Release a journal_t structure once it is no longer in use by the
 * journaled object.
 * Return <0 if we couldn't clean up the journal.
 */
int jbd2_journal_destroy(journal_t *journal)
{
	int err = 0;

	/* Wait for the commit thread to wake up and die. */
	journal_kill_thread(journal);

	/* Force a final log commit */
	if (journal->j_running_transaction)
		jbd2_journal_commit_transaction(journal);

	/* Force any old transactions to disk */

	/* Totally anal locking here... */
	spin_lock(&journal->j_list_lock);
	while (journal->j_checkpoint_transactions != NULL) {
		spin_unlock(&journal->j_list_lock);
		mutex_lock(&journal->j_checkpoint_mutex);
		jbd2_log_do_checkpoint(journal);
		mutex_unlock(&journal->j_checkpoint_mutex);
		spin_lock(&journal->j_list_lock);
	}

	J_ASSERT(journal->j_running_transaction == NULL);
	J_ASSERT(journal->j_committing_transaction == NULL);
	J_ASSERT(journal->j_checkpoint_transactions == NULL);
	spin_unlock(&journal->j_list_lock);

	if (journal->j_sb_buffer) {
		if (!is_journal_aborted(journal)) {
			mutex_lock(&journal->j_checkpoint_mutex);
			jbd2_mark_journal_empty(journal);
			mutex_unlock(&journal->j_checkpoint_mutex);
		} else
			err = -EIO;
		brelse(journal->j_sb_buffer);
	}

	if (journal->j_proc_entry)
		jbd2_stats_proc_exit(journal);
	if (journal->j_inode)
		iput(journal->j_inode);
	if (journal->j_revoke)
		jbd2_journal_destroy_revoke(journal);
	kfree(journal->j_wbuf);
	kfree(journal);

	return err;
}


/**
 *int jbd2_journal_check_used_features () - Check if features specified are used.
 * @journal: Journal to check.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Check whether the journal uses all of a given set of
 * features.  Return true (non-zero) if it does.
 **/

int jbd2_journal_check_used_features (journal_t *journal, unsigned long compat,
				 unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (!compat && !ro && !incompat)
		return 1;
	/* Load journal superblock if it is not loaded yet. */
	if (journal->j_format_version == 0 &&
	    journal_get_superblock(journal) != 0)
		return 0;
	if (journal->j_format_version == 1)
		return 0;

	sb = journal->j_superblock;

	if (((be32_to_cpu(sb->s_feature_compat) & compat) == compat) &&
	    ((be32_to_cpu(sb->s_feature_ro_compat) & ro) == ro) &&
	    ((be32_to_cpu(sb->s_feature_incompat) & incompat) == incompat))
		return 1;

	return 0;
}

/**
 * int jbd2_journal_check_available_features() - Check feature set in journalling layer
 * @journal: Journal to check.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Check whether the journaling code supports the use of
 * all of a given set of features on this journal.  Return true
 * (non-zero) if it can. */

int jbd2_journal_check_available_features (journal_t *journal, unsigned long compat,
				      unsigned long ro, unsigned long incompat)
{
	if (!compat && !ro && !incompat)
		return 1;

	/* We can support any known requested features iff the
	 * superblock is in version 2.  Otherwise we fail to support any
	 * extended sb features. */

	if (journal->j_format_version != 2)
		return 0;

	if ((compat   & JBD2_KNOWN_COMPAT_FEATURES) == compat &&
	    (ro       & JBD2_KNOWN_ROCOMPAT_FEATURES) == ro &&
	    (incompat & JBD2_KNOWN_INCOMPAT_FEATURES) == incompat)
		return 1;

	return 0;
}

/**
 * int jbd2_journal_set_features () - Mark a given journal feature in the superblock
 * @journal: Journal to act on.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Mark a given journal feature as present on the
 * superblock.  Returns true if the requested features could be set.
 *
 */

int jbd2_journal_set_features (journal_t *journal, unsigned long compat,
			  unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	if (jbd2_journal_check_used_features(journal, compat, ro, incompat))
		return 1;

	if (!jbd2_journal_check_available_features(journal, compat, ro, incompat))
		return 0;

	jbd_debug(1, "Setting new features 0x%lx/0x%lx/0x%lx\n",
		  compat, ro, incompat);

	sb = journal->j_superblock;

	sb->s_feature_compat    |= cpu_to_be32(compat);
	sb->s_feature_ro_compat |= cpu_to_be32(ro);
	sb->s_feature_incompat  |= cpu_to_be32(incompat);

	return 1;
}

/*
 * jbd2_journal_clear_features () - Clear a given journal feature in the
 * 				    superblock
 * @journal: Journal to act on.
 * @compat: bitmask of compatible features
 * @ro: bitmask of features that force read-only mount
 * @incompat: bitmask of incompatible features
 *
 * Clear a given journal feature as present on the
 * superblock.
 */
void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
				unsigned long ro, unsigned long incompat)
{
	journal_superblock_t *sb;

	jbd_debug(1, "Clear features 0x%lx/0x%lx/0x%lx\n",
		  compat, ro, incompat);

	sb = journal->j_superblock;

	sb->s_feature_compat    &= ~cpu_to_be32(compat);
	sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
	sb->s_feature_incompat  &= ~cpu_to_be32(incompat);
}
EXPORT_SYMBOL(jbd2_journal_clear_features);

/**
 * int jbd2_journal_flush () - Flush journal
 * @journal: Journal to act on.
 *
 * Flush all data for a given journal to disk and empty the journal.
 * Filesystems can use this when remounting readonly to ensure that
 * recovery does not need to happen on remount.
 */

int jbd2_journal_flush(journal_t *journal)
{
	int err = 0;
	transaction_t *transaction = NULL;

	write_lock(&journal->j_state_lock);

	/* Force everything buffered to the log... */
	if (journal->j_running_transaction) {
		transaction = journal->j_running_transaction;
		__jbd2_log_start_commit(journal, transaction->t_tid);
	} else if (journal->j_committing_transaction)
		transaction = journal->j_committing_transaction;

	/* Wait for the log commit to complete... */
	if (transaction) {
		tid_t tid = transaction->t_tid;

		write_unlock(&journal->j_state_lock);
		jbd2_log_wait_commit(journal, tid);
	} else {
		write_unlock(&journal->j_state_lock);
	}

	/* ...and flush everything in the log out to disk. */
	spin_lock(&journal->j_list_lock);
	while (!err && journal->j_checkpoint_transactions != NULL) {
		spin_unlock(&journal->j_list_lock);
		mutex_lock(&journal->j_checkpoint_mutex);
		err = jbd2_log_do_checkpoint(journal);
		mutex_unlock(&journal->j_checkpoint_mutex);
		spin_lock(&journal->j_list_lock);
	}
	spin_unlock(&journal->j_list_lock);

	if (is_journal_aborted(journal))
		return -EIO;

	mutex_lock(&journal->j_checkpoint_mutex);
	jbd2_cleanup_journal_tail(journal);

	/* Finally, mark the journal as really needing no recovery.
	 * This sets s_start==0 in the underlying superblock, which is
	 * the magic code for a fully-recovered superblock.  Any future
	 * commits of data to the journal will restore the current
	 * s_start value. */
	jbd2_mark_journal_empty(journal);
	mutex_unlock(&journal->j_checkpoint_mutex);
	write_lock(&journal->j_state_lock);
	J_ASSERT(!journal->j_running_transaction);
	J_ASSERT(!journal->j_committing_transaction);
	J_ASSERT(!journal->j_checkpoint_transactions);
	J_ASSERT(journal->j_head == journal->j_tail);
	J_ASSERT(journal->j_tail_sequence == journal->j_transaction_sequence);
	write_unlock(&journal->j_state_lock);
	return 0;
}

/**
 * int jbd2_journal_wipe() - Wipe journal contents
 * @journal: Journal to act on.
 * @write: flag (see below)
 *
 * Wipe out all of the contents of a journal, safely.  This will produce
 * a warning if the journal contains any valid recovery information.
 * Must be called between journal_init_*() and jbd2_journal_load().
 *
 * If 'write' is non-zero, then we wipe out the journal on disk; otherwise
 * we merely suppress recovery.
 */

int jbd2_journal_wipe(journal_t *journal, int write)
{
	int err = 0;

	J_ASSERT (!(journal->j_flags & JBD2_LOADED));

	err = load_superblock(journal);
	if (err)
		return err;

	if (!journal->j_tail)
		goto no_recovery;

	printk(KERN_WARNING "JBD2: %s recovery information on journal\n",
		write ? "Clearing" : "Ignoring");

	err = jbd2_journal_skip_recovery(journal);
	if (write) {
		/* Lock to make assertions happy... */
		mutex_lock(&journal->j_checkpoint_mutex);
		jbd2_mark_journal_empty(journal);
		mutex_unlock(&journal->j_checkpoint_mutex);
	}

 no_recovery:
	return err;
}

/*
 * Journal abort has very specific semantics, which we describe
 * for journal abort.
 *
 * Two internal functions, which provide abort to the jbd layer
 * itself are here.
 */

/*
 * Quick version for internal journal use (doesn't lock the journal).
 * Aborts hard --- we mark the abort as occurred, but do _nothing_ else,
 * and don't attempt to make any other journal updates.
 */
void __jbd2_journal_abort_hard(journal_t *journal)
{
	transaction_t *transaction;

	if (journal->j_flags & JBD2_ABORT)
		return;

	printk(KERN_ERR "Aborting journal on device %s.\n",
	       journal->j_devname);

	write_lock(&journal->j_state_lock);
	journal->j_flags |= JBD2_ABORT;
	transaction = journal->j_running_transaction;
	if (transaction)
		__jbd2_log_start_commit(journal, transaction->t_tid);
	write_unlock(&journal->j_state_lock);
}

/* Soft abort: record the abort error status in the journal superblock,
 * but don't do any other IO. */
static void __journal_abort_soft (journal_t *journal, int errno)
{
	if (journal->j_flags & JBD2_ABORT)
		return;

	if (!journal->j_errno)
		journal->j_errno = errno;

	__jbd2_journal_abort_hard(journal);

	if (errno)
		jbd2_journal_update_sb_errno(journal);
}

/**
 * void jbd2_journal_abort () - Shutdown the journal immediately.
 * @journal: the journal to shutdown.
 * @errno:   an error number to record in the journal indicating
 *           the reason for the shutdown.
 *
 * Perform a complete, immediate shutdown of the ENTIRE
 * journal (not of a single transaction).  This operation cannot be
 * undone without closing and reopening the journal.
 *
 * The jbd2_journal_abort function is intended to support higher level error
 * recovery mechanisms such as the ext2/ext3 remount-readonly error
 * mode.
 *
 * Journal abort has very specific semantics.  Any existing dirty,
 * unjournaled buffers in the main filesystem will still be written to
 * disk by bdflush, but the journaling mechanism will be suspended
 * immediately and no further transaction commits will be honoured.
 *
 * Any dirty, journaled buffers will be written back to disk without
 * hitting the journal.  Atomicity cannot be guaranteed on an aborted
 * filesystem, but we _do_ attempt to leave as much data as possible
 * behind for fsck to use for cleanup.
 *
 * Any attempt to get a new transaction handle on a journal which is in
 * ABORT state will just result in an -EROFS error return.  A
 * jbd2_journal_stop on an existing handle will return -EIO if we have
 * entered abort state during the update.
 *
 * Recursive transactions are not disturbed by journal abort until the
 * final jbd2_journal_stop, which will receive the -EIO error.
 *
 * Finally, the jbd2_journal_abort call allows the caller to supply an errno
 * which will be recorded (if possible) in the journal superblock.  This
 * allows a client to record failure conditions in the middle of a
 * transaction without having to complete the transaction to record the
 * failure to disk.  ext3_error, for example, now uses this
 * functionality.
 *
 * Errors which originate from within the journaling layer will NOT
 * supply an errno; a null errno implies that absolutely no further
 * writes are done to the journal (unless there are any already in
 * progress).
 *
 */

void jbd2_journal_abort(journal_t *journal, int errno)
{
	__journal_abort_soft(journal, errno);
}

/**
 * int jbd2_journal_errno () - returns the journal's error state.
 * @journal: journal to examine.
 *
 * This is the errno number set with jbd2_journal_abort(), the last
 * time the journal was mounted - if the journal was stopped
 * without calling abort this will be 0.
 *
 * If the journal has been aborted on this mount time -EROFS will
 * be returned.
 */
int jbd2_journal_errno(journal_t *journal)
{
	int err;

	read_lock(&journal->j_state_lock);
	if (journal->j_flags & JBD2_ABORT)
		err = -EROFS;
	else
		err = journal->j_errno;
	read_unlock(&journal->j_state_lock);
	return err;
}

/**
 * int jbd2_journal_clear_err () - clears the journal's error state
 * @journal: journal to act on.
 *
 * An error must be cleared or acked to take a FS out of readonly
 * mode.
 */
int jbd2_journal_clear_err(journal_t *journal)
{
	int err = 0;

	write_lock(&journal->j_state_lock);
	if (journal->j_flags & JBD2_ABORT)
		err = -EROFS;
	else
		journal->j_errno = 0;
	write_unlock(&journal->j_state_lock);
	return err;
}

/**
 * void jbd2_journal_ack_err() - Ack journal err.
 * @journal: journal to act on.
 *
 * An error must be cleared or acked to take a FS out of readonly
 * mode.
 */
void jbd2_journal_ack_err(journal_t *journal)
{
	write_lock(&journal->j_state_lock);
	if (journal->j_errno)
		journal->j_flags |= JBD2_ACK_ERR;
	write_unlock(&journal->j_state_lock);
}

int jbd2_journal_blocks_per_page(struct inode *inode)
{
	return 1 << (PAGE_CACHE_SHIFT - inode->i_sb->s_blocksize_bits);
}

/*
 * helper functions to deal with 32 or 64bit block numbers.
 */
size_t journal_tag_bytes(journal_t *journal)
{
	if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_64BIT))
		return JBD2_TAG_SIZE64;
	else
		return JBD2_TAG_SIZE32;
}

/*
 * JBD memory management
 *
 * These functions are used to allocate block-sized chunks of memory
 * used for making copies of buffer_head data.  Very often it will be
 * page-sized chunks of data, but sometimes it will be in
 * sub-page-size chunks.  (For example, 16k pages on Power systems
 * with a 4k block file system.)  For blocks smaller than a page, we
 * use a SLAB allocator.  There are slab caches for each block size,
 * which are allocated at mount time, if necessary, and we only free
 * (all of) the slab caches when/if the jbd2 module is unloaded.  For
 * this reason we don't need to a mutex to protect access to
 * jbd2_slab[] allocating or releasing memory; only in
 * jbd2_journal_create_slab().
 */
#define JBD2_MAX_SLABS 8
static struct kmem_cache *jbd2_slab[JBD2_MAX_SLABS];

static const char *jbd2_slab_names[JBD2_MAX_SLABS] = {
	"jbd2_1k", "jbd2_2k", "jbd2_4k", "jbd2_8k",
	"jbd2_16k", "jbd2_32k", "jbd2_64k", "jbd2_128k"
};


static void jbd2_journal_destroy_slabs(void)
{
	int i;

	for (i = 0; i < JBD2_MAX_SLABS; i++) {
		if (jbd2_slab[i])
			kmem_cache_destroy(jbd2_slab[i]);
		jbd2_slab[i] = NULL;
	}
}

static int jbd2_journal_create_slab(size_t size)
{
	static DEFINE_MUTEX(jbd2_slab_create_mutex);
	int i = order_base_2(size) - 10;
	size_t slab_size;

	if (size == PAGE_SIZE)
		return 0;

	if (i >= JBD2_MAX_SLABS)
		return -EINVAL;

	if (unlikely(i < 0))
		i = 0;
	mutex_lock(&jbd2_slab_create_mutex);
	if (jbd2_slab[i]) {
		mutex_unlock(&jbd2_slab_create_mutex);
		return 0;	/* Already created */
	}

	slab_size = 1 << (i+10);
	jbd2_slab[i] = kmem_cache_create(jbd2_slab_names[i], slab_size,
					 slab_size, 0, NULL);
	mutex_unlock(&jbd2_slab_create_mutex);
	if (!jbd2_slab[i]) {
		printk(KERN_EMERG "JBD2: no memory for jbd2_slab cache\n");
		return -ENOMEM;
	}
	return 0;
}

static struct kmem_cache *get_slab(size_t size)
{
	int i = order_base_2(size) - 10;

	BUG_ON(i >= JBD2_MAX_SLABS);
	if (unlikely(i < 0))
		i = 0;
	BUG_ON(jbd2_slab[i] == NULL);
	return jbd2_slab[i];
}

void *jbd2_alloc(size_t size, gfp_t flags)
{
	void *ptr;

	BUG_ON(size & (size-1)); /* Must be a power of 2 */

	flags |= __GFP_REPEAT;
	if (size == PAGE_SIZE)
		ptr = (void *)__get_free_pages(flags, 0);
	else if (size > PAGE_SIZE) {
		int order = get_order(size);

		if (order < 3)
			ptr = (void *)__get_free_pages(flags, order);
		else
			ptr = vmalloc(size);
	} else
		ptr = kmem_cache_alloc(get_slab(size), flags);

	/* Check alignment; SLUB has gotten this wrong in the past,
	 * and this can lead to user data corruption! */
	BUG_ON(((unsigned long) ptr) & (size-1));

	return ptr;
}

void jbd2_free(void *ptr, size_t size)
{
	if (size == PAGE_SIZE) {
		free_pages((unsigned long)ptr, 0);
		return;
	}
	if (size > PAGE_SIZE) {
		int order = get_order(size);

		if (order < 3)
			free_pages((unsigned long)ptr, order);
		else
			vfree(ptr);
		return;
	}
	kmem_cache_free(get_slab(size), ptr);
};

/*
 * Journal_head storage management
 */
static struct kmem_cache *jbd2_journal_head_cache;
#ifdef CONFIG_JBD2_DEBUG
static atomic_t nr_journal_heads = ATOMIC_INIT(0);
#endif

static int jbd2_journal_init_journal_head_cache(void)
{
	int retval;

	J_ASSERT(jbd2_journal_head_cache == NULL);
	jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
				sizeof(struct journal_head),
				0,		/* offset */
				SLAB_TEMPORARY,	/* flags */
				NULL);		/* ctor */
	retval = 0;
	if (!jbd2_journal_head_cache) {
		retval = -ENOMEM;
		printk(KERN_EMERG "JBD2: no memory for journal_head cache\n");
	}
	return retval;
}

static void jbd2_journal_destroy_journal_head_cache(void)
{
	if (jbd2_journal_head_cache) {
		kmem_cache_destroy(jbd2_journal_head_cache);
		jbd2_journal_head_cache = NULL;
	}
}

/*
 * journal_head splicing and dicing
 */
static struct journal_head *journal_alloc_journal_head(void)
{
	struct journal_head *ret;

#ifdef CONFIG_JBD2_DEBUG
	atomic_inc(&nr_journal_heads);
#endif
	ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
	if (!ret) {
		jbd_debug(1, "out of memory for journal_head\n");
		pr_notice_ratelimited("ENOMEM in %s, retrying.\n", __func__);
		while (!ret) {
			yield();
			ret = kmem_cache_alloc(jbd2_journal_head_cache, GFP_NOFS);
		}
	}
	return ret;
}

static void journal_free_journal_head(struct journal_head *jh)
{
#ifdef CONFIG_JBD2_DEBUG
	atomic_dec(&nr_journal_heads);
	memset(jh, JBD2_POISON_FREE, sizeof(*jh));
#endif
	kmem_cache_free(jbd2_journal_head_cache, jh);
}

/*
 * A journal_head is attached to a buffer_head whenever JBD has an
 * interest in the buffer.
 *
 * Whenever a buffer has an attached journal_head, its ->b_state:BH_JBD bit
 * is set.  This bit is tested in core kernel code where we need to take
 * JBD-specific actions.  Testing the zeroness of ->b_private is not reliable
 * there.
 *
 * When a buffer has its BH_JBD bit set, its ->b_count is elevated by one.
 *
 * When a buffer has its BH_JBD bit set it is immune from being released by
 * core kernel code, mainly via ->b_count.
 *
 * A journal_head is detached from its buffer_head when the journal_head's
 * b_jcount reaches zero. Running transaction (b_transaction) and checkpoint
 * transaction (b_cp_transaction) hold their references to b_jcount.
 *
 * Various places in the kernel want to attach a journal_head to a buffer_head
 * _before_ attaching the journal_head to a transaction.  To protect the
 * journal_head in this situation, jbd2_journal_add_journal_head elevates the
 * journal_head's b_jcount refcount by one.  The caller must call
 * jbd2_journal_put_journal_head() to undo this.
 *
 * So the typical usage would be:
 *
 *	(Attach a journal_head if needed.  Increments b_jcount)
 *	struct journal_head *jh = jbd2_journal_add_journal_head(bh);
 *	...
 *      (Get another reference for transaction)
 *	jbd2_journal_grab_journal_head(bh);
 *	jh->b_transaction = xxx;
 *	(Put original reference)
 *	jbd2_journal_put_journal_head(jh);
 */

/*
 * Give a buffer_head a journal_head.
 *
 * May sleep.
 */
struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh)
{
	struct journal_head *jh;
	struct journal_head *new_jh = NULL;

repeat:
	if (!buffer_jbd(bh)) {
		new_jh = journal_alloc_journal_head();
		memset(new_jh, 0, sizeof(*new_jh));
	}

	jbd_lock_bh_journal_head(bh);
	if (buffer_jbd(bh)) {
		jh = bh2jh(bh);
	} else {
		J_ASSERT_BH(bh,
			(atomic_read(&bh->b_count) > 0) ||
			(bh->b_page && bh->b_page->mapping));

		if (!new_jh) {
			jbd_unlock_bh_journal_head(bh);
			goto repeat;
		}

		jh = new_jh;
		new_jh = NULL;		/* We consumed it */
		set_buffer_jbd(bh);
		bh->b_private = jh;
		jh->b_bh = bh;
		get_bh(bh);
		BUFFER_TRACE(bh, "added journal_head");
	}
	jh->b_jcount++;
	jbd_unlock_bh_journal_head(bh);
	if (new_jh)
		journal_free_journal_head(new_jh);
	return bh->b_private;
}

/*
 * Grab a ref against this buffer_head's journal_head.  If it ended up not
 * having a journal_head, return NULL
 */
struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh)
{
	struct journal_head *jh = NULL;

	jbd_lock_bh_journal_head(bh);
	if (buffer_jbd(bh)) {
		jh = bh2jh(bh);
		jh->b_jcount++;
	}
	jbd_unlock_bh_journal_head(bh);
	return jh;
}

static void __journal_remove_journal_head(struct buffer_head *bh)
{
	struct journal_head *jh = bh2jh(bh);

	J_ASSERT_JH(jh, jh->b_jcount >= 0);
	J_ASSERT_JH(jh, jh->b_transaction == NULL);
	J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
	J_ASSERT_JH(jh, jh->b_cp_transaction == NULL);
	J_ASSERT_JH(jh, jh->b_jlist == BJ_None);
	J_ASSERT_BH(bh, buffer_jbd(bh));
	J_ASSERT_BH(bh, jh2bh(jh) == bh);
	BUFFER_TRACE(bh, "remove journal_head");
	if (jh->b_frozen_data) {
		printk(KERN_WARNING "%s: freeing b_frozen_data\n", __func__);
		jbd2_free(jh->b_frozen_data, bh->b_size);
	}
	if (jh->b_committed_data) {
		printk(KERN_WARNING "%s: freeing b_committed_data\n", __func__);
		jbd2_free(jh->b_committed_data, bh->b_size);
	}
	bh->b_private = NULL;
	jh->b_bh = NULL;	/* debug, really */
	clear_buffer_jbd(bh);
	journal_free_journal_head(jh);
}

/*
 * Drop a reference on the passed journal_head.  If it fell to zero then
 * release the journal_head from the buffer_head.
 */
void jbd2_journal_put_journal_head(struct journal_head *jh)
{
	struct buffer_head *bh = jh2bh(jh);

	jbd_lock_bh_journal_head(bh);
	J_ASSERT_JH(jh, jh->b_jcount > 0);
	--jh->b_jcount;
	if (!jh->b_jcount) {
		__journal_remove_journal_head(bh);
		jbd_unlock_bh_journal_head(bh);
		__brelse(bh);
	} else
		jbd_unlock_bh_journal_head(bh);
}

/*
 * Initialize jbd inode head
 */
void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode)
{
	jinode->i_transaction = NULL;
	jinode->i_next_transaction = NULL;
	jinode->i_vfs_inode = inode;
	jinode->i_flags = 0;
	INIT_LIST_HEAD(&jinode->i_list);
}

/*
 * Function to be called before we start removing inode from memory (i.e.,
 * clear_inode() is a fine place to be called from). It removes inode from
 * transaction's lists.
 */
void jbd2_journal_release_jbd_inode(journal_t *journal,
				    struct jbd2_inode *jinode)
{
	if (!journal)
		return;
restart:
	spin_lock(&journal->j_list_lock);
	/* Is commit writing out inode - we have to wait */
	if (test_bit(__JI_COMMIT_RUNNING, &jinode->i_flags)) {
		wait_queue_head_t *wq;
		DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
		wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
		spin_unlock(&journal->j_list_lock);
		schedule();
		finish_wait(wq, &wait.wait);
		goto restart;
	}

	if (jinode->i_transaction) {
		list_del(&jinode->i_list);
		jinode->i_transaction = NULL;
	}
	spin_unlock(&journal->j_list_lock);
}

/*
 * debugfs tunables
 */
#ifdef CONFIG_JBD2_DEBUG
u8 jbd2_journal_enable_debug __read_mostly;
EXPORT_SYMBOL(jbd2_journal_enable_debug);

#define JBD2_DEBUG_NAME "jbd2-debug"

static struct dentry *jbd2_debugfs_dir;
static struct dentry *jbd2_debug;

static void __init jbd2_create_debugfs_entry(void)
{
	jbd2_debugfs_dir = debugfs_create_dir("jbd2", NULL);
	if (jbd2_debugfs_dir)
		jbd2_debug = debugfs_create_u8(JBD2_DEBUG_NAME,
					       S_IRUGO | S_IWUSR,
					       jbd2_debugfs_dir,
					       &jbd2_journal_enable_debug);
}

static void __exit jbd2_remove_debugfs_entry(void)
{
	debugfs_remove(jbd2_debug);
	debugfs_remove(jbd2_debugfs_dir);
}

#else

static void __init jbd2_create_debugfs_entry(void)
{
}

static void __exit jbd2_remove_debugfs_entry(void)
{
}

#endif

#ifdef CONFIG_PROC_FS

#define JBD2_STATS_PROC_NAME "fs/jbd2"

static void __init jbd2_create_jbd_stats_proc_entry(void)
{
	proc_jbd2_stats = proc_mkdir(JBD2_STATS_PROC_NAME, NULL);
}

static void __exit jbd2_remove_jbd_stats_proc_entry(void)
{
	if (proc_jbd2_stats)
		remove_proc_entry(JBD2_STATS_PROC_NAME, NULL);
}

#else

#define jbd2_create_jbd_stats_proc_entry() do {} while (0)
#define jbd2_remove_jbd_stats_proc_entry() do {} while (0)

#endif

struct kmem_cache *jbd2_handle_cache, *jbd2_inode_cache;

static int __init jbd2_journal_init_handle_cache(void)
{
	jbd2_handle_cache = KMEM_CACHE(jbd2_journal_handle, SLAB_TEMPORARY);
	if (jbd2_handle_cache == NULL) {
		printk(KERN_EMERG "JBD2: failed to create handle cache\n");
		return -ENOMEM;
	}
	jbd2_inode_cache = KMEM_CACHE(jbd2_inode, 0);
	if (jbd2_inode_cache == NULL) {
		printk(KERN_EMERG "JBD2: failed to create inode cache\n");
		kmem_cache_destroy(jbd2_handle_cache);
		return -ENOMEM;
	}
	return 0;
}

static void jbd2_journal_destroy_handle_cache(void)
{
	if (jbd2_handle_cache)
		kmem_cache_destroy(jbd2_handle_cache);
	if (jbd2_inode_cache)
		kmem_cache_destroy(jbd2_inode_cache);

}

/*
 * Module startup and shutdown
 */

static int __init journal_init_caches(void)
{
	int ret;

	ret = jbd2_journal_init_revoke_caches();
	if (ret == 0)
		ret = jbd2_journal_init_journal_head_cache();
	if (ret == 0)
		ret = jbd2_journal_init_handle_cache();
	if (ret == 0)
		ret = jbd2_journal_init_transaction_cache();
	return ret;
}

static void jbd2_journal_destroy_caches(void)
{
	jbd2_journal_destroy_revoke_caches();
	jbd2_journal_destroy_journal_head_cache();
	jbd2_journal_destroy_handle_cache();
	jbd2_journal_destroy_transaction_cache();
	jbd2_journal_destroy_slabs();
}

static int __init journal_init(void)
{
	int ret;

	BUILD_BUG_ON(sizeof(struct journal_superblock_s) != 1024);

	ret = journal_init_caches();
	if (ret == 0) {
		jbd2_create_debugfs_entry();
		jbd2_create_jbd_stats_proc_entry();
	} else {
		jbd2_journal_destroy_caches();
	}
	return ret;
}

static void __exit journal_exit(void)
{
#ifdef CONFIG_JBD2_DEBUG
	int n = atomic_read(&nr_journal_heads);
	if (n)
		printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n);
#endif
	jbd2_remove_debugfs_entry();
	jbd2_remove_jbd_stats_proc_entry();
	jbd2_journal_destroy_caches();
}

MODULE_LICENSE("GPL");
module_init(journal_init);
module_exit(journal_exit);