summaryrefslogtreecommitdiff
path: root/include/linux/jbd2.h
blob: e79d6e0b14e8e8be8e2286908f73d43ca4d52748 (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
/* SPDX-License-Identifier: GPL-2.0-or-later */
/*
 * linux/include/linux/jbd2.h
 *
 * Written by Stephen C. Tweedie <sct@redhat.com>
 *
 * Copyright 1998-2000 Red Hat, Inc --- All Rights Reserved
 *
 * Definitions for transaction data structures for the buffer cache
 * filesystem journaling support.
 */

#ifndef _LINUX_JBD2_H
#define _LINUX_JBD2_H

/* Allow this file to be included directly into e2fsprogs */
#ifndef __KERNEL__
#include "jfs_compat.h"
#define JBD2_DEBUG
#else

#include <linux/types.h>
#include <linux/buffer_head.h>
#include <linux/journal-head.h>
#include <linux/stddef.h>
#include <linux/mutex.h>
#include <linux/timer.h>
#include <linux/slab.h>
#include <linux/bit_spinlock.h>
#include <linux/blkdev.h>
#include <crypto/hash.h>
#endif

#define journal_oom_retry 1

/*
 * Define JBD2_PARANIOD_IOFAIL to cause a kernel BUG() if ext4 finds
 * certain classes of error which can occur due to failed IOs.  Under
 * normal use we want ext4 to continue after such errors, because
 * hardware _can_ fail, but for debugging purposes when running tests on
 * known-good hardware we may want to trap these errors.
 */
#undef JBD2_PARANOID_IOFAIL

/*
 * The default maximum commit age, in seconds.
 */
#define JBD2_DEFAULT_MAX_COMMIT_AGE 5

#ifdef CONFIG_JBD2_DEBUG
/*
 * Define JBD2_EXPENSIVE_CHECKING to enable more expensive internal
 * consistency checks.  By default we don't do this unless
 * CONFIG_JBD2_DEBUG is on.
 */
#define JBD2_EXPENSIVE_CHECKING
extern ushort jbd2_journal_enable_debug;
void __jbd2_debug(int level, const char *file, const char *func,
		  unsigned int line, const char *fmt, ...);

#define jbd_debug(n, fmt, a...) \
	__jbd2_debug((n), __FILE__, __func__, __LINE__, (fmt), ##a)
#else
#define jbd_debug(n, fmt, a...)  no_printk(fmt, ##a)
#endif

extern void *jbd2_alloc(size_t size, gfp_t flags);
extern void jbd2_free(void *ptr, size_t size);

#define JBD2_MIN_JOURNAL_BLOCKS 1024
#define JBD2_DEFAULT_FAST_COMMIT_BLOCKS 256

#ifdef __KERNEL__

/**
 * typedef handle_t - The handle_t type represents a single atomic update being performed by some process.
 *
 * All filesystem modifications made by the process go
 * through this handle.  Recursive operations (such as quota operations)
 * are gathered into a single update.
 *
 * The buffer credits field is used to account for journaled buffers
 * being modified by the running process.  To ensure that there is
 * enough log space for all outstanding operations, we need to limit the
 * number of outstanding buffers possible at any time.  When the
 * operation completes, any buffer credits not used are credited back to
 * the transaction, so that at all times we know how many buffers the
 * outstanding updates on a transaction might possibly touch.
 *
 * This is an opaque datatype.
 **/
typedef struct jbd2_journal_handle handle_t;	/* Atomic operation type */


/**
 * typedef journal_t - The journal_t maintains all of the journaling state information for a single filesystem.
 *
 * journal_t is linked to from the fs superblock structure.
 *
 * We use the journal_t to keep track of all outstanding transaction
 * activity on the filesystem, and to manage the state of the log
 * writing process.
 *
 * This is an opaque datatype.
 **/
typedef struct journal_s	journal_t;	/* Journal control structure */
#endif

/*
 * Internal structures used by the logging mechanism:
 */

#define JBD2_MAGIC_NUMBER 0xc03b3998U /* The first 4 bytes of /dev/random! */

/*
 * On-disk structures
 */

/*
 * Descriptor block types:
 */

#define JBD2_DESCRIPTOR_BLOCK	1
#define JBD2_COMMIT_BLOCK	2
#define JBD2_SUPERBLOCK_V1	3
#define JBD2_SUPERBLOCK_V2	4
#define JBD2_REVOKE_BLOCK	5

/*
 * Standard header for all descriptor blocks:
 */
typedef struct journal_header_s
{
	__be32		h_magic;
	__be32		h_blocktype;
	__be32		h_sequence;
} journal_header_t;

/*
 * Checksum types.
 */
#define JBD2_CRC32_CHKSUM   1
#define JBD2_MD5_CHKSUM     2
#define JBD2_SHA1_CHKSUM    3
#define JBD2_CRC32C_CHKSUM  4

#define JBD2_CRC32_CHKSUM_SIZE 4

#define JBD2_CHECKSUM_BYTES (32 / sizeof(u32))
/*
 * Commit block header for storing transactional checksums:
 *
 * NOTE: If FEATURE_COMPAT_CHECKSUM (checksum v1) is set, the h_chksum*
 * fields are used to store a checksum of the descriptor and data blocks.
 *
 * If FEATURE_INCOMPAT_CSUM_V2 (checksum v2) is set, then the h_chksum
 * field is used to store crc32c(uuid+commit_block).  Each journal metadata
 * block gets its own checksum, and data block checksums are stored in
 * journal_block_tag (in the descriptor).  The other h_chksum* fields are
 * not used.
 *
 * If FEATURE_INCOMPAT_CSUM_V3 is set, the descriptor block uses
 * journal_block_tag3_t to store a full 32-bit checksum.  Everything else
 * is the same as v2.
 *
 * Checksum v1, v2, and v3 are mutually exclusive features.
 */
struct commit_header {
	__be32		h_magic;
	__be32          h_blocktype;
	__be32          h_sequence;
	unsigned char   h_chksum_type;
	unsigned char   h_chksum_size;
	unsigned char 	h_padding[2];
	__be32 		h_chksum[JBD2_CHECKSUM_BYTES];
	__be64		h_commit_sec;
	__be32		h_commit_nsec;
};

/*
 * The block tag: used to describe a single buffer in the journal.
 * t_blocknr_high is only used if INCOMPAT_64BIT is set, so this
 * raw struct shouldn't be used for pointer math or sizeof() - use
 * journal_tag_bytes(journal) instead to compute this.
 */
typedef struct journal_block_tag3_s
{
	__be32		t_blocknr;	/* The on-disk block number */
	__be32		t_flags;	/* See below */
	__be32		t_blocknr_high; /* most-significant high 32bits. */
	__be32		t_checksum;	/* crc32c(uuid+seq+block) */
} journal_block_tag3_t;

typedef struct journal_block_tag_s
{
	__be32		t_blocknr;	/* The on-disk block number */
	__be16		t_checksum;	/* truncated crc32c(uuid+seq+block) */
	__be16		t_flags;	/* See below */
	__be32		t_blocknr_high; /* most-significant high 32bits. */
} journal_block_tag_t;

/* Tail of descriptor or revoke block, for checksumming */
struct jbd2_journal_block_tail {
	__be32		t_checksum;	/* crc32c(uuid+descr_block) */
};

/*
 * The revoke descriptor: used on disk to describe a series of blocks to
 * be revoked from the log
 */
typedef struct jbd2_journal_revoke_header_s
{
	journal_header_t r_header;
	__be32		 r_count;	/* Count of bytes used in the block */
} jbd2_journal_revoke_header_t;

/* Definitions for the journal tag flags word: */
#define JBD2_FLAG_ESCAPE		1	/* on-disk block is escaped */
#define JBD2_FLAG_SAME_UUID	2	/* block has same uuid as previous */
#define JBD2_FLAG_DELETED	4	/* block deleted by this transaction */
#define JBD2_FLAG_LAST_TAG	8	/* last tag in this descriptor block */


/*
 * The journal superblock.  All fields are in big-endian byte order.
 */
typedef struct journal_superblock_s
{
/* 0x0000 */
	journal_header_t s_header;

/* 0x000C */
	/* Static information describing the journal */
	__be32	s_blocksize;		/* journal device blocksize */
	__be32	s_maxlen;		/* total blocks in journal file */
	__be32	s_first;		/* first block of log information */

/* 0x0018 */
	/* Dynamic information describing the current state of the log */
	__be32	s_sequence;		/* first commit ID expected in log */
	__be32	s_start;		/* blocknr of start of log */

/* 0x0020 */
	/* Error value, as set by jbd2_journal_abort(). */
	__be32	s_errno;

/* 0x0024 */
	/* Remaining fields are only valid in a version-2 superblock */
	__be32	s_feature_compat;	/* compatible feature set */
	__be32	s_feature_incompat;	/* incompatible feature set */
	__be32	s_feature_ro_compat;	/* readonly-compatible feature set */
/* 0x0030 */
	__u8	s_uuid[16];		/* 128-bit uuid for journal */

/* 0x0040 */
	__be32	s_nr_users;		/* Nr of filesystems sharing log */

	__be32	s_dynsuper;		/* Blocknr of dynamic superblock copy*/

/* 0x0048 */
	__be32	s_max_transaction;	/* Limit of journal blocks per trans.*/
	__be32	s_max_trans_data;	/* Limit of data blocks per trans. */

/* 0x0050 */
	__u8	s_checksum_type;	/* checksum type */
	__u8	s_padding2[3];
/* 0x0054 */
	__be32	s_num_fc_blks;		/* Number of fast commit blocks */
/* 0x0058 */
	__u32	s_padding[41];
	__be32	s_checksum;		/* crc32c(superblock) */

/* 0x0100 */
	__u8	s_users[16*48];		/* ids of all fs'es sharing the log */
/* 0x0400 */
} journal_superblock_t;

/* Use the jbd2_{has,set,clear}_feature_* helpers; these will be removed */
#define JBD2_HAS_COMPAT_FEATURE(j,mask)					\
	((j)->j_format_version >= 2 &&					\
	 ((j)->j_superblock->s_feature_compat & cpu_to_be32((mask))))
#define JBD2_HAS_RO_COMPAT_FEATURE(j,mask)				\
	((j)->j_format_version >= 2 &&					\
	 ((j)->j_superblock->s_feature_ro_compat & cpu_to_be32((mask))))
#define JBD2_HAS_INCOMPAT_FEATURE(j,mask)				\
	((j)->j_format_version >= 2 &&					\
	 ((j)->j_superblock->s_feature_incompat & cpu_to_be32((mask))))

#define JBD2_FEATURE_COMPAT_CHECKSUM		0x00000001

#define JBD2_FEATURE_INCOMPAT_REVOKE		0x00000001
#define JBD2_FEATURE_INCOMPAT_64BIT		0x00000002
#define JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT	0x00000004
#define JBD2_FEATURE_INCOMPAT_CSUM_V2		0x00000008
#define JBD2_FEATURE_INCOMPAT_CSUM_V3		0x00000010
#define JBD2_FEATURE_INCOMPAT_FAST_COMMIT	0x00000020

/* See "journal feature predicate functions" below */

/* Features known to this kernel version: */
#define JBD2_KNOWN_COMPAT_FEATURES	JBD2_FEATURE_COMPAT_CHECKSUM
#define JBD2_KNOWN_ROCOMPAT_FEATURES	0
#define JBD2_KNOWN_INCOMPAT_FEATURES	(JBD2_FEATURE_INCOMPAT_REVOKE | \
					JBD2_FEATURE_INCOMPAT_64BIT | \
					JBD2_FEATURE_INCOMPAT_ASYNC_COMMIT | \
					JBD2_FEATURE_INCOMPAT_CSUM_V2 | \
					JBD2_FEATURE_INCOMPAT_CSUM_V3 | \
					JBD2_FEATURE_INCOMPAT_FAST_COMMIT)

#ifdef __KERNEL__

#include <linux/fs.h>
#include <linux/sched.h>

enum jbd_state_bits {
	BH_JBD			/* Has an attached ext3 journal_head */
	  = BH_PrivateStart,
	BH_JWrite,		/* Being written to log (@@@ DEBUGGING) */
	BH_Freed,		/* Has been freed (truncated) */
	BH_Revoked,		/* Has been revoked from the log */
	BH_RevokeValid,		/* Revoked flag is valid */
	BH_JBDDirty,		/* Is dirty but journaled */
	BH_JournalHead,		/* Pins bh->b_private and jh->b_bh */
	BH_Shadow,		/* IO on shadow buffer is running */
	BH_Verified,		/* Metadata block has been verified ok */
	BH_JBDPrivateStart,	/* First bit available for private use by FS */
};

BUFFER_FNS(JBD, jbd)
BUFFER_FNS(JWrite, jwrite)
BUFFER_FNS(JBDDirty, jbddirty)
TAS_BUFFER_FNS(JBDDirty, jbddirty)
BUFFER_FNS(Revoked, revoked)
TAS_BUFFER_FNS(Revoked, revoked)
BUFFER_FNS(RevokeValid, revokevalid)
TAS_BUFFER_FNS(RevokeValid, revokevalid)
BUFFER_FNS(Freed, freed)
BUFFER_FNS(Shadow, shadow)
BUFFER_FNS(Verified, verified)

static inline struct buffer_head *jh2bh(struct journal_head *jh)
{
	return jh->b_bh;
}

static inline struct journal_head *bh2jh(struct buffer_head *bh)
{
	return bh->b_private;
}

static inline void jbd_lock_bh_journal_head(struct buffer_head *bh)
{
	bit_spin_lock(BH_JournalHead, &bh->b_state);
}

static inline void jbd_unlock_bh_journal_head(struct buffer_head *bh)
{
	bit_spin_unlock(BH_JournalHead, &bh->b_state);
}

#define J_ASSERT(assert)	BUG_ON(!(assert))

#define J_ASSERT_BH(bh, expr)	J_ASSERT(expr)
#define J_ASSERT_JH(jh, expr)	J_ASSERT(expr)

#if defined(JBD2_PARANOID_IOFAIL)
#define J_EXPECT(expr, why...)		J_ASSERT(expr)
#define J_EXPECT_BH(bh, expr, why...)	J_ASSERT_BH(bh, expr)
#define J_EXPECT_JH(jh, expr, why...)	J_ASSERT_JH(jh, expr)
#else
#define __journal_expect(expr, why...)					     \
	({								     \
		int val = (expr);					     \
		if (!val) {						     \
			printk(KERN_ERR					     \
			       "JBD2 unexpected failure: %s: %s;\n",	     \
			       __func__, #expr);			     \
			printk(KERN_ERR why "\n");			     \
		}							     \
		val;							     \
	})
#define J_EXPECT(expr, why...)		__journal_expect(expr, ## why)
#define J_EXPECT_BH(bh, expr, why...)	__journal_expect(expr, ## why)
#define J_EXPECT_JH(jh, expr, why...)	__journal_expect(expr, ## why)
#endif

/* Flags in jbd_inode->i_flags */
#define __JI_COMMIT_RUNNING 0
#define __JI_WRITE_DATA 1
#define __JI_WAIT_DATA 2

/*
 * Commit of the inode data in progress. We use this flag to protect us from
 * concurrent deletion of inode. We cannot use reference to inode for this
 * since we cannot afford doing last iput() on behalf of kjournald
 */
#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
/* Write allocated dirty buffers in this inode before commit */
#define JI_WRITE_DATA (1 << __JI_WRITE_DATA)
/* Wait for outstanding data writes for this inode before commit */
#define JI_WAIT_DATA (1 << __JI_WAIT_DATA)

/**
 * struct jbd2_inode - The jbd_inode type is the structure linking inodes in
 * ordered mode present in a transaction so that we can sync them during commit.
 */
struct jbd2_inode {
	/**
	 * @i_transaction:
	 *
	 * Which transaction does this inode belong to? Either the running
	 * transaction or the committing one. [j_list_lock]
	 */
	transaction_t *i_transaction;

	/**
	 * @i_next_transaction:
	 *
	 * Pointer to the running transaction modifying inode's data in case
	 * there is already a committing transaction touching it. [j_list_lock]
	 */
	transaction_t *i_next_transaction;

	/**
	 * @i_list: List of inodes in the i_transaction [j_list_lock]
	 */
	struct list_head i_list;

	/**
	 * @i_vfs_inode:
	 *
	 * VFS inode this inode belongs to [constant for lifetime of structure]
	 */
	struct inode *i_vfs_inode;

	/**
	 * @i_flags: Flags of inode [j_list_lock]
	 */
	unsigned long i_flags;

	/**
	 * @i_dirty_start:
	 *
	 * Offset in bytes where the dirty range for this inode starts.
	 * [j_list_lock]
	 */
	loff_t i_dirty_start;

	/**
	 * @i_dirty_end:
	 *
	 * Inclusive offset in bytes where the dirty range for this inode
	 * ends. [j_list_lock]
	 */
	loff_t i_dirty_end;
};

struct jbd2_revoke_table_s;

/**
 * struct jbd2_journal_handle - The jbd2_journal_handle type is the concrete
 *     type associated with handle_t.
 * @h_transaction: Which compound transaction is this update a part of?
 * @h_journal: Which journal handle belongs to - used iff h_reserved set.
 * @h_rsv_handle: Handle reserved for finishing the logical operation.
 * @h_total_credits: Number of remaining buffers we are allowed to add to
 *	journal. These are dirty buffers and revoke descriptor blocks.
 * @h_revoke_credits: Number of remaining revoke records available for handle
 * @h_ref: Reference count on this handle.
 * @h_err: Field for caller's use to track errors through large fs operations.
 * @h_sync: Flag for sync-on-close.
 * @h_jdata: Flag to force data journaling.
 * @h_reserved: Flag for handle for reserved credits.
 * @h_aborted: Flag indicating fatal error on handle.
 * @h_type: For handle statistics.
 * @h_line_no: For handle statistics.
 * @h_start_jiffies: Handle Start time.
 * @h_requested_credits: Holds @h_total_credits after handle is started.
 * @h_revoke_credits_requested: Holds @h_revoke_credits after handle is started.
 * @saved_alloc_context: Saved context while transaction is open.
 **/

/* Docbook can't yet cope with the bit fields, but will leave the documentation
 * in so it can be fixed later.
 */

struct jbd2_journal_handle
{
	union {
		transaction_t	*h_transaction;
		/* Which journal handle belongs to - used iff h_reserved set */
		journal_t	*h_journal;
	};

	handle_t		*h_rsv_handle;
	int			h_total_credits;
	int			h_revoke_credits;
	int			h_revoke_credits_requested;
	int			h_ref;
	int			h_err;

	/* Flags [no locking] */
	unsigned int	h_sync:		1;
	unsigned int	h_jdata:	1;
	unsigned int	h_reserved:	1;
	unsigned int	h_aborted:	1;
	unsigned int	h_type:		8;
	unsigned int	h_line_no:	16;

	unsigned long		h_start_jiffies;
	unsigned int		h_requested_credits;

	unsigned int		saved_alloc_context;
};


/*
 * Some stats for checkpoint phase
 */
struct transaction_chp_stats_s {
	unsigned long		cs_chp_time;
	__u32			cs_forced_to_close;
	__u32			cs_written;
	__u32			cs_dropped;
};

/* The transaction_t type is the guts of the journaling mechanism.  It
 * tracks a compound transaction through its various states:
 *
 * RUNNING:	accepting new updates
 * LOCKED:	Updates still running but we don't accept new ones
 * RUNDOWN:	Updates are tidying up but have finished requesting
 *		new buffers to modify (state not used for now)
 * FLUSH:       All updates complete, but we are still writing to disk
 * COMMIT:      All data on disk, writing commit record
 * FINISHED:	We still have to keep the transaction for checkpointing.
 *
 * The transaction keeps track of all of the buffers modified by a
 * running transaction, and all of the buffers committed but not yet
 * flushed to home for finished transactions.
 * (Locking Documentation improved by LockDoc)
 */

/*
 * Lock ranking:
 *
 *    j_list_lock
 *      ->jbd_lock_bh_journal_head()	(This is "innermost")
 *
 *    j_state_lock
 *    ->b_state_lock
 *
 *    b_state_lock
 *    ->j_list_lock
 *
 *    j_state_lock
 *    ->j_list_lock			(journal_unmap_buffer)
 *
 */

struct transaction_s
{
	/* Pointer to the journal for this transaction. [no locking] */
	journal_t		*t_journal;

	/* Sequence number for this transaction [no locking] */
	tid_t			t_tid;

	/*
	 * Transaction's current state
	 * [no locking - only kjournald2 alters this]
	 * [j_list_lock] guards transition of a transaction into T_FINISHED
	 * state and subsequent call of __jbd2_journal_drop_transaction()
	 * FIXME: needs barriers
	 * KLUDGE: [use j_state_lock]
	 */
	enum {
		T_RUNNING,
		T_LOCKED,
		T_SWITCH,
		T_FLUSH,
		T_COMMIT,
		T_COMMIT_DFLUSH,
		T_COMMIT_JFLUSH,
		T_COMMIT_CALLBACK,
		T_FINISHED
	}			t_state;

	/*
	 * Where in the log does this transaction's commit start? [no locking]
	 */
	unsigned long		t_log_start;

	/*
	 * Number of buffers on the t_buffers list [j_list_lock, no locks
	 * needed for jbd2 thread]
	 */
	int			t_nr_buffers;

	/*
	 * Doubly-linked circular list of all buffers reserved but not yet
	 * modified by this transaction [j_list_lock, no locks needed fo
	 * jbd2 thread]
	 */
	struct journal_head	*t_reserved_list;

	/*
	 * Doubly-linked circular list of all metadata buffers owned by this
	 * transaction [j_list_lock, no locks needed for jbd2 thread]
	 */
	struct journal_head	*t_buffers;

	/*
	 * Doubly-linked circular list of all forget buffers (superseded
	 * buffers which we can un-checkpoint once this transaction commits)
	 * [j_list_lock]
	 */
	struct journal_head	*t_forget;

	/*
	 * Doubly-linked circular list of all buffers still to be flushed before
	 * this transaction can be checkpointed. [j_list_lock]
	 */
	struct journal_head	*t_checkpoint_list;

	/*
	 * Doubly-linked circular list of all buffers submitted for IO while
	 * checkpointing. [j_list_lock]
	 */
	struct journal_head	*t_checkpoint_io_list;

	/*
	 * Doubly-linked circular list of metadata buffers being
	 * shadowed by log IO.  The IO buffers on the iobuf list and
	 * the shadow buffers on this list match each other one for
	 * one at all times. [j_list_lock, no locks needed for jbd2
	 * thread]
	 */
	struct journal_head	*t_shadow_list;

	/*
	 * List of inodes associated with the transaction; e.g., ext4 uses
	 * this to track inodes in data=ordered and data=journal mode that
	 * need special handling on transaction commit; also used by ocfs2.
	 * [j_list_lock]
	 */
	struct list_head	t_inode_list;

	/*
	 * Protects info related to handles
	 */
	spinlock_t		t_handle_lock;

	/*
	 * Longest time some handle had to wait for running transaction
	 */
	unsigned long		t_max_wait;

	/*
	 * When transaction started
	 */
	unsigned long		t_start;

	/*
	 * When commit was requested [j_state_lock]
	 */
	unsigned long		t_requested;

	/*
	 * Checkpointing stats [j_list_lock]
	 */
	struct transaction_chp_stats_s t_chp_stats;

	/*
	 * Number of outstanding updates running on this transaction
	 * [none]
	 */
	atomic_t		t_updates;

	/*
	 * Number of blocks reserved for this transaction in the journal.
	 * This is including all credits reserved when starting transaction
	 * handles as well as all journal descriptor blocks needed for this
	 * transaction. [none]
	 */
	atomic_t		t_outstanding_credits;

	/*
	 * Number of revoke records for this transaction added by already
	 * stopped handles. [none]
	 */
	atomic_t		t_outstanding_revokes;

	/*
	 * How many handles used this transaction? [none]
	 */
	atomic_t		t_handle_count;

	/*
	 * Forward and backward links for the circular list of all transactions
	 * awaiting checkpoint. [j_list_lock]
	 */
	transaction_t		*t_cpnext, *t_cpprev;

	/*
	 * When will the transaction expire (become due for commit), in jiffies?
	 * [no locking]
	 */
	unsigned long		t_expires;

	/*
	 * When this transaction started, in nanoseconds [no locking]
	 */
	ktime_t			t_start_time;

	/*
	 * This transaction is being forced and some process is
	 * waiting for it to finish.
	 */
	unsigned int t_synchronous_commit:1;

	/* Disk flush needs to be sent to fs partition [no locking] */
	int			t_need_data_flush;

	/*
	 * For use by the filesystem to store fs-specific data
	 * structures associated with the transaction
	 */
	struct list_head	t_private_list;
};

struct transaction_run_stats_s {
	unsigned long		rs_wait;
	unsigned long		rs_request_delay;
	unsigned long		rs_running;
	unsigned long		rs_locked;
	unsigned long		rs_flushing;
	unsigned long		rs_logging;

	__u32			rs_handle_count;
	__u32			rs_blocks;
	__u32			rs_blocks_logged;
};

struct transaction_stats_s {
	unsigned long		ts_tid;
	unsigned long		ts_requested;
	struct transaction_run_stats_s run;
};

static inline unsigned long
jbd2_time_diff(unsigned long start, unsigned long end)
{
	if (end >= start)
		return end - start;

	return end + (MAX_JIFFY_OFFSET - start);
}

#define JBD2_NR_BATCH	64

enum passtype {PASS_SCAN, PASS_REVOKE, PASS_REPLAY};

#define JBD2_FC_REPLAY_STOP	0
#define JBD2_FC_REPLAY_CONTINUE	1

/**
 * struct journal_s - The journal_s type is the concrete type associated with
 *     journal_t.
 */
struct journal_s
{
	/**
	 * @j_flags: General journaling state flags [j_state_lock,
	 * no lock for quick racy checks]
	 */
	unsigned long		j_flags;

	/**
	 * @j_atomic_flags: Atomic journaling state flags.
	 */
	unsigned long		j_atomic_flags;

	/**
	 * @j_errno:
	 *
	 * Is there an outstanding uncleared error on the journal (from a prior
	 * abort)? [j_state_lock]
	 */
	int			j_errno;

	/**
	 * @j_abort_mutex: Lock the whole aborting procedure.
	 */
	struct mutex		j_abort_mutex;

	/**
	 * @j_sb_buffer: The first part of the superblock buffer.
	 */
	struct buffer_head	*j_sb_buffer;

	/**
	 * @j_superblock: The second part of the superblock buffer.
	 */
	journal_superblock_t	*j_superblock;

	/**
	 * @j_format_version: Version of the superblock format.
	 */
	int			j_format_version;

	/**
	 * @j_state_lock: Protect the various scalars in the journal.
	 */
	rwlock_t		j_state_lock;

	/**
	 * @j_barrier_count:
	 *
	 * Number of processes waiting to create a barrier lock [j_state_lock,
	 * no lock for quick racy checks]
	 */
	int			j_barrier_count;

	/**
	 * @j_barrier: The barrier lock itself.
	 */
	struct mutex		j_barrier;

	/**
	 * @j_running_transaction:
	 *
	 * Transactions: The current running transaction...
	 * [j_state_lock, no lock for quick racy checks] [caller holding
	 * open handle]
	 */
	transaction_t		*j_running_transaction;

	/**
	 * @j_committing_transaction:
	 *
	 * the transaction we are pushing to disk
	 * [j_state_lock] [caller holding open handle]
	 */
	transaction_t		*j_committing_transaction;

	/**
	 * @j_checkpoint_transactions:
	 *
	 * ... and a linked circular list of all transactions waiting for
	 * checkpointing. [j_list_lock]
	 */
	transaction_t		*j_checkpoint_transactions;

	/**
	 * @j_wait_transaction_locked:
	 *
	 * Wait queue for waiting for a locked transaction to start committing,
	 * or for a barrier lock to be released.
	 */
	wait_queue_head_t	j_wait_transaction_locked;

	/**
	 * @j_wait_done_commit: Wait queue for waiting for commit to complete.
	 */
	wait_queue_head_t	j_wait_done_commit;

	/**
	 * @j_wait_commit: Wait queue to trigger commit.
	 */
	wait_queue_head_t	j_wait_commit;

	/**
	 * @j_wait_updates: Wait queue to wait for updates to complete.
	 */
	wait_queue_head_t	j_wait_updates;

	/**
	 * @j_wait_reserved:
	 *
	 * Wait queue to wait for reserved buffer credits to drop.
	 */
	wait_queue_head_t	j_wait_reserved;

	/**
	 * @j_fc_wait:
	 *
	 * Wait queue to wait for completion of async fast commits.
	 */
	wait_queue_head_t	j_fc_wait;

	/**
	 * @j_checkpoint_mutex:
	 *
	 * Semaphore for locking against concurrent checkpoints.
	 */
	struct mutex		j_checkpoint_mutex;

	/**
	 * @j_chkpt_bhs:
	 *
	 * List of buffer heads used by the checkpoint routine.  This
	 * was moved from jbd2_log_do_checkpoint() to reduce stack
	 * usage.  Access to this array is controlled by the
	 * @j_checkpoint_mutex.  [j_checkpoint_mutex]
	 */
	struct buffer_head	*j_chkpt_bhs[JBD2_NR_BATCH];

	/**
	 * @j_shrinker:
	 *
	 * Journal head shrinker, reclaim buffer's journal head which
	 * has been written back.
	 */
	struct shrinker		j_shrinker;

	/**
	 * @j_checkpoint_jh_count:
	 *
	 * Number of journal buffers on the checkpoint list. [j_list_lock]
	 */
	struct percpu_counter	j_checkpoint_jh_count;

	/**
	 * @j_shrink_transaction:
	 *
	 * Record next transaction will shrink on the checkpoint list.
	 * [j_list_lock]
	 */
	transaction_t		*j_shrink_transaction;

	/**
	 * @j_head:
	 *
	 * Journal head: identifies the first unused block in the journal.
	 * [j_state_lock]
	 */
	unsigned long		j_head;

	/**
	 * @j_tail:
	 *
	 * Journal tail: identifies the oldest still-used block in the journal.
	 * [j_state_lock]
	 */
	unsigned long		j_tail;

	/**
	 * @j_free:
	 *
	 * Journal free: how many free blocks are there in the journal?
	 * [j_state_lock]
	 */
	unsigned long		j_free;

	/**
	 * @j_first:
	 *
	 * The block number of the first usable block in the journal
	 * [j_state_lock].
	 */
	unsigned long		j_first;

	/**
	 * @j_last:
	 *
	 * The block number one beyond the last usable block in the journal
	 * [j_state_lock].
	 */
	unsigned long		j_last;

	/**
	 * @j_fc_first:
	 *
	 * The block number of the first fast commit block in the journal
	 * [j_state_lock].
	 */
	unsigned long		j_fc_first;

	/**
	 * @j_fc_off:
	 *
	 * Number of fast commit blocks currently allocated. Accessed only
	 * during fast commit. Currently only process can do fast commit, so
	 * this field is not protected by any lock.
	 */
	unsigned long		j_fc_off;

	/**
	 * @j_fc_last:
	 *
	 * The block number one beyond the last fast commit block in the journal
	 * [j_state_lock].
	 */
	unsigned long		j_fc_last;

	/**
	 * @j_dev: Device where we store the journal.
	 */
	struct block_device	*j_dev;

	/**
	 * @j_blocksize: Block size for the location where we store the journal.
	 */
	int			j_blocksize;

	/**
	 * @j_blk_offset:
	 *
	 * Starting block offset into the device where we store the journal.
	 */
	unsigned long long	j_blk_offset;

	/**
	 * @j_devname: Journal device name.
	 */
	char			j_devname[BDEVNAME_SIZE+24];

	/**
	 * @j_fs_dev:
	 *
	 * Device which holds the client fs.  For internal journal this will be
	 * equal to j_dev.
	 */
	struct block_device	*j_fs_dev;

	/**
	 * @j_total_len: Total maximum capacity of the journal region on disk.
	 */
	unsigned int		j_total_len;

	/**
	 * @j_reserved_credits:
	 *
	 * Number of buffers reserved from the running transaction.
	 */
	atomic_t		j_reserved_credits;

	/**
	 * @j_list_lock: Protects the buffer lists and internal buffer state.
	 */
	spinlock_t		j_list_lock;

	/**
	 * @j_inode:
	 *
	 * Optional inode where we store the journal.  If present, all
	 * journal block numbers are mapped into this inode via bmap().
	 */
	struct inode		*j_inode;

	/**
	 * @j_tail_sequence:
	 *
	 * Sequence number of the oldest transaction in the log [j_state_lock]
	 */
	tid_t			j_tail_sequence;

	/**
	 * @j_transaction_sequence:
	 *
	 * Sequence number of the next transaction to grant [j_state_lock]
	 */
	tid_t			j_transaction_sequence;

	/**
	 * @j_commit_sequence:
	 *
	 * Sequence number of the most recently committed transaction
	 * [j_state_lock, no lock for quick racy checks]
	 */
	tid_t			j_commit_sequence;

	/**
	 * @j_commit_request:
	 *
	 * Sequence number of the most recent transaction wanting commit
	 * [j_state_lock, no lock for quick racy checks]
	 */
	tid_t			j_commit_request;

	/**
	 * @j_uuid:
	 *
	 * Journal uuid: identifies the object (filesystem, LVM volume etc)
	 * backed by this journal.  This will eventually be replaced by an array
	 * of uuids, allowing us to index multiple devices within a single
	 * journal and to perform atomic updates across them.
	 */
	__u8			j_uuid[16];

	/**
	 * @j_task: Pointer to the current commit thread for this journal.
	 */
	struct task_struct	*j_task;

	/**
	 * @j_max_transaction_buffers:
	 *
	 * Maximum number of metadata buffers to allow in a single compound
	 * commit transaction.
	 */
	int			j_max_transaction_buffers;

	/**
	 * @j_revoke_records_per_block:
	 *
	 * Number of revoke records that fit in one descriptor block.
	 */
	int			j_revoke_records_per_block;

	/**
	 * @j_commit_interval:
	 *
	 * What is the maximum transaction lifetime before we begin a commit?
	 */
	unsigned long		j_commit_interval;

	/**
	 * @j_commit_timer: The timer used to wakeup the commit thread.
	 */
	struct timer_list	j_commit_timer;

	/**
	 * @j_revoke_lock: Protect the revoke table.
	 */
	spinlock_t		j_revoke_lock;

	/**
	 * @j_revoke:
	 *
	 * The revoke table - maintains the list of revoked blocks in the
	 * current transaction.
	 */
	struct jbd2_revoke_table_s *j_revoke;

	/**
	 * @j_revoke_table: Alternate revoke tables for j_revoke.
	 */
	struct jbd2_revoke_table_s *j_revoke_table[2];

	/**
	 * @j_wbuf: Array of bhs for jbd2_journal_commit_transaction.
	 */
	struct buffer_head	**j_wbuf;

	/**
	 * @j_fc_wbuf: Array of fast commit bhs for fast commit. Accessed only
	 * during a fast commit. Currently only process can do fast commit, so
	 * this field is not protected by any lock.
	 */
	struct buffer_head	**j_fc_wbuf;

	/**
	 * @j_wbufsize:
	 *
	 * Size of @j_wbuf array.
	 */
	int			j_wbufsize;

	/**
	 * @j_fc_wbufsize:
	 *
	 * Size of @j_fc_wbuf array.
	 */
	int			j_fc_wbufsize;

	/**
	 * @j_last_sync_writer:
	 *
	 * The pid of the last person to run a synchronous operation
	 * through the journal.
	 */
	pid_t			j_last_sync_writer;

	/**
	 * @j_average_commit_time:
	 *
	 * The average amount of time in nanoseconds it takes to commit a
	 * transaction to disk. [j_state_lock]
	 */
	u64			j_average_commit_time;

	/**
	 * @j_min_batch_time:
	 *
	 * Minimum time that we should wait for additional filesystem operations
	 * to get batched into a synchronous handle in microseconds.
	 */
	u32			j_min_batch_time;

	/**
	 * @j_max_batch_time:
	 *
	 * Maximum time that we should wait for additional filesystem operations
	 * to get batched into a synchronous handle in microseconds.
	 */
	u32			j_max_batch_time;

	/**
	 * @j_commit_callback:
	 *
	 * This function is called when a transaction is closed.
	 */
	void			(*j_commit_callback)(journal_t *,
						     transaction_t *);

	/**
	 * @j_submit_inode_data_buffers:
	 *
	 * This function is called for all inodes associated with the
	 * committing transaction marked with JI_WRITE_DATA flag
	 * before we start to write out the transaction to the journal.
	 */
	int			(*j_submit_inode_data_buffers)
					(struct jbd2_inode *);

	/**
	 * @j_finish_inode_data_buffers:
	 *
	 * This function is called for all inodes associated with the
	 * committing transaction marked with JI_WAIT_DATA flag
	 * after we have written the transaction to the journal
	 * but before we write out the commit block.
	 */
	int			(*j_finish_inode_data_buffers)
					(struct jbd2_inode *);

	/*
	 * Journal statistics
	 */

	/**
	 * @j_history_lock: Protect the transactions statistics history.
	 */
	spinlock_t		j_history_lock;

	/**
	 * @j_proc_entry: procfs entry for the jbd statistics directory.
	 */
	struct proc_dir_entry	*j_proc_entry;

	/**
	 * @j_stats: Overall statistics.
	 */
	struct transaction_stats_s j_stats;

	/**
	 * @j_failed_commit: Failed journal commit ID.
	 */
	unsigned int		j_failed_commit;

	/**
	 * @j_private:
	 *
	 * An opaque pointer to fs-private information.  ext3 puts its
	 * superblock pointer here.
	 */
	void *j_private;

	/**
	 * @j_chksum_driver:
	 *
	 * Reference to checksum algorithm driver via cryptoapi.
	 */
	struct crypto_shash *j_chksum_driver;

	/**
	 * @j_csum_seed:
	 *
	 * Precomputed journal UUID checksum for seeding other checksums.
	 */
	__u32 j_csum_seed;

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	/**
	 * @j_trans_commit_map:
	 *
	 * Lockdep entity to track transaction commit dependencies. Handles
	 * hold this "lock" for read, when we wait for commit, we acquire the
	 * "lock" for writing. This matches the properties of jbd2 journalling
	 * where the running transaction has to wait for all handles to be
	 * dropped to commit that transaction and also acquiring a handle may
	 * require transaction commit to finish.
	 */
	struct lockdep_map	j_trans_commit_map;
#endif

	/**
	 * @j_fc_cleanup_callback:
	 *
	 * Clean-up after fast commit or full commit. JBD2 calls this function
	 * after every commit operation.
	 */
	void (*j_fc_cleanup_callback)(struct journal_s *journal, int full, tid_t tid);

	/**
	 * @j_fc_replay_callback:
	 *
	 * File-system specific function that performs replay of a fast
	 * commit. JBD2 calls this function for each fast commit block found in
	 * the journal. This function should return JBD2_FC_REPLAY_CONTINUE
	 * to indicate that the block was processed correctly and more fast
	 * commit replay should continue. Return value of JBD2_FC_REPLAY_STOP
	 * indicates the end of replay (no more blocks remaining). A negative
	 * return value indicates error.
	 */
	int (*j_fc_replay_callback)(struct journal_s *journal,
				    struct buffer_head *bh,
				    enum passtype pass, int off,
				    tid_t expected_commit_id);
};

#define jbd2_might_wait_for_commit(j) \
	do { \
		rwsem_acquire(&j->j_trans_commit_map, 0, 0, _THIS_IP_); \
		rwsem_release(&j->j_trans_commit_map, _THIS_IP_); \
	} while (0)

/* journal feature predicate functions */
#define JBD2_FEATURE_COMPAT_FUNCS(name, flagname) \
static inline bool jbd2_has_feature_##name(journal_t *j) \
{ \
	return ((j)->j_format_version >= 2 && \
		((j)->j_superblock->s_feature_compat & \
		 cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname)) != 0); \
} \
static inline void jbd2_set_feature_##name(journal_t *j) \
{ \
	(j)->j_superblock->s_feature_compat |= \
		cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \
} \
static inline void jbd2_clear_feature_##name(journal_t *j) \
{ \
	(j)->j_superblock->s_feature_compat &= \
		~cpu_to_be32(JBD2_FEATURE_COMPAT_##flagname); \
}

#define JBD2_FEATURE_RO_COMPAT_FUNCS(name, flagname) \
static inline bool jbd2_has_feature_##name(journal_t *j) \
{ \
	return ((j)->j_format_version >= 2 && \
		((j)->j_superblock->s_feature_ro_compat & \
		 cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname)) != 0); \
} \
static inline void jbd2_set_feature_##name(journal_t *j) \
{ \
	(j)->j_superblock->s_feature_ro_compat |= \
		cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \
} \
static inline void jbd2_clear_feature_##name(journal_t *j) \
{ \
	(j)->j_superblock->s_feature_ro_compat &= \
		~cpu_to_be32(JBD2_FEATURE_RO_COMPAT_##flagname); \
}

#define JBD2_FEATURE_INCOMPAT_FUNCS(name, flagname) \
static inline bool jbd2_has_feature_##name(journal_t *j) \
{ \
	return ((j)->j_format_version >= 2 && \
		((j)->j_superblock->s_feature_incompat & \
		 cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname)) != 0); \
} \
static inline void jbd2_set_feature_##name(journal_t *j) \
{ \
	(j)->j_superblock->s_feature_incompat |= \
		cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \
} \
static inline void jbd2_clear_feature_##name(journal_t *j) \
{ \
	(j)->j_superblock->s_feature_incompat &= \
		~cpu_to_be32(JBD2_FEATURE_INCOMPAT_##flagname); \
}

JBD2_FEATURE_COMPAT_FUNCS(checksum,		CHECKSUM)

JBD2_FEATURE_INCOMPAT_FUNCS(revoke,		REVOKE)
JBD2_FEATURE_INCOMPAT_FUNCS(64bit,		64BIT)
JBD2_FEATURE_INCOMPAT_FUNCS(async_commit,	ASYNC_COMMIT)
JBD2_FEATURE_INCOMPAT_FUNCS(csum2,		CSUM_V2)
JBD2_FEATURE_INCOMPAT_FUNCS(csum3,		CSUM_V3)
JBD2_FEATURE_INCOMPAT_FUNCS(fast_commit,	FAST_COMMIT)

/*
 * Journal flag definitions
 */
#define JBD2_UNMOUNT	0x001	/* Journal thread is being destroyed */
#define JBD2_ABORT	0x002	/* Journaling has been aborted for errors. */
#define JBD2_ACK_ERR	0x004	/* The errno in the sb has been acked */
#define JBD2_FLUSHED	0x008	/* The journal superblock has been flushed */
#define JBD2_LOADED	0x010	/* The journal superblock has been loaded */
#define JBD2_BARRIER	0x020	/* Use IDE barriers */
#define JBD2_ABORT_ON_SYNCDATA_ERR	0x040	/* Abort the journal on file
						 * data write error in ordered
						 * mode */
#define JBD2_FAST_COMMIT_ONGOING	0x100	/* Fast commit is ongoing */
#define JBD2_FULL_COMMIT_ONGOING	0x200	/* Full commit is ongoing */
#define JBD2_JOURNAL_FLUSH_DISCARD	0x0001
#define JBD2_JOURNAL_FLUSH_ZEROOUT	0x0002
#define JBD2_JOURNAL_FLUSH_VALID	(JBD2_JOURNAL_FLUSH_DISCARD | \
					JBD2_JOURNAL_FLUSH_ZEROOUT)

/*
 * Journal atomic flag definitions
 */
#define JBD2_CHECKPOINT_IO_ERROR	0x001	/* Detect io error while writing
						 * buffer back to disk */

/*
 * Function declarations for the journaling transaction and buffer
 * management
 */

/* Filing buffers */
extern void jbd2_journal_unfile_buffer(journal_t *, struct journal_head *);
extern bool __jbd2_journal_refile_buffer(struct journal_head *);
extern void jbd2_journal_refile_buffer(journal_t *, struct journal_head *);
extern void __jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
extern void jbd2_journal_file_buffer(struct journal_head *, transaction_t *, int);
static inline void jbd2_file_log_bh(struct list_head *head, struct buffer_head *bh)
{
	list_add_tail(&bh->b_assoc_buffers, head);
}
static inline void jbd2_unfile_log_bh(struct buffer_head *bh)
{
	list_del_init(&bh->b_assoc_buffers);
}

/* Log buffer allocation */
struct buffer_head *jbd2_journal_get_descriptor_buffer(transaction_t *, int);
void jbd2_descriptor_block_csum_set(journal_t *, struct buffer_head *);
int jbd2_journal_next_log_block(journal_t *, unsigned long long *);
int jbd2_journal_get_log_tail(journal_t *journal, tid_t *tid,
			      unsigned long *block);
int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);
void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block);

/* Commit management */
extern void jbd2_journal_commit_transaction(journal_t *);

/* Checkpoint list management */
void __jbd2_journal_clean_checkpoint_list(journal_t *journal, bool destroy);
unsigned long jbd2_journal_shrink_checkpoint_list(journal_t *journal, unsigned long *nr_to_scan);
int __jbd2_journal_remove_checkpoint(struct journal_head *);
void jbd2_journal_destroy_checkpoint(journal_t *journal);
void __jbd2_journal_insert_checkpoint(struct journal_head *, transaction_t *);


/*
 * Triggers
 */

struct jbd2_buffer_trigger_type {
	/*
	 * Fired a the moment data to write to the journal are known to be
	 * stable - so either at the moment b_frozen_data is created or just
	 * before a buffer is written to the journal.  mapped_data is a mapped
	 * buffer that is the frozen data for commit.
	 */
	void (*t_frozen)(struct jbd2_buffer_trigger_type *type,
			 struct buffer_head *bh, void *mapped_data,
			 size_t size);

	/*
	 * Fired during journal abort for dirty buffers that will not be
	 * committed.
	 */
	void (*t_abort)(struct jbd2_buffer_trigger_type *type,
			struct buffer_head *bh);
};

extern void jbd2_buffer_frozen_trigger(struct journal_head *jh,
				       void *mapped_data,
				       struct jbd2_buffer_trigger_type *triggers);
extern void jbd2_buffer_abort_trigger(struct journal_head *jh,
				      struct jbd2_buffer_trigger_type *triggers);

/* Buffer IO */
extern int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
					      struct journal_head *jh_in,
					      struct buffer_head **bh_out,
					      sector_t blocknr);

/* Transaction cache support */
extern void jbd2_journal_destroy_transaction_cache(void);
extern int __init jbd2_journal_init_transaction_cache(void);
extern void jbd2_journal_free_transaction(transaction_t *);

/*
 * Journal locking.
 *
 * We need to lock the journal during transaction state changes so that nobody
 * ever tries to take a handle on the running transaction while we are in the
 * middle of moving it to the commit phase.  j_state_lock does this.
 *
 * Note that the locking is completely interrupt unsafe.  We never touch
 * journal structures from interrupts.
 */

static inline handle_t *journal_current_handle(void)
{
	return current->journal_info;
}

/* The journaling code user interface:
 *
 * Create and destroy handles
 * Register buffer modifications against the current transaction.
 */

extern handle_t *jbd2_journal_start(journal_t *, int nblocks);
extern handle_t *jbd2__journal_start(journal_t *, int blocks, int rsv_blocks,
				     int revoke_records, gfp_t gfp_mask,
				     unsigned int type, unsigned int line_no);
extern int	 jbd2_journal_restart(handle_t *, int nblocks);
extern int	 jbd2__journal_restart(handle_t *, int nblocks,
				       int revoke_records, gfp_t gfp_mask);
extern int	 jbd2_journal_start_reserved(handle_t *handle,
				unsigned int type, unsigned int line_no);
extern void	 jbd2_journal_free_reserved(handle_t *handle);
extern int	 jbd2_journal_extend(handle_t *handle, int nblocks,
				     int revoke_records);
extern int	 jbd2_journal_get_write_access(handle_t *, struct buffer_head *);
extern int	 jbd2_journal_get_create_access (handle_t *, struct buffer_head *);
extern int	 jbd2_journal_get_undo_access(handle_t *, struct buffer_head *);
void		 jbd2_journal_set_triggers(struct buffer_head *,
					   struct jbd2_buffer_trigger_type *type);
extern int	 jbd2_journal_dirty_metadata (handle_t *, struct buffer_head *);
extern int	 jbd2_journal_forget (handle_t *, struct buffer_head *);
int jbd2_journal_invalidate_folio(journal_t *, struct folio *,
					size_t offset, size_t length);
bool jbd2_journal_try_to_free_buffers(journal_t *journal, struct folio *folio);
extern int	 jbd2_journal_stop(handle_t *);
extern int	 jbd2_journal_flush(journal_t *journal, unsigned int flags);
extern void	 jbd2_journal_lock_updates (journal_t *);
extern void	 jbd2_journal_unlock_updates (journal_t *);

void jbd2_journal_wait_updates(journal_t *);

extern journal_t * jbd2_journal_init_dev(struct block_device *bdev,
				struct block_device *fs_dev,
				unsigned long long start, int len, int bsize);
extern journal_t * jbd2_journal_init_inode (struct inode *);
extern int	   jbd2_journal_update_format (journal_t *);
extern int	   jbd2_journal_check_used_features
		   (journal_t *, unsigned long, unsigned long, unsigned long);
extern int	   jbd2_journal_check_available_features
		   (journal_t *, unsigned long, unsigned long, unsigned long);
extern int	   jbd2_journal_set_features
		   (journal_t *, unsigned long, unsigned long, unsigned long);
extern void	   jbd2_journal_clear_features
		   (journal_t *, unsigned long, unsigned long, unsigned long);
extern int	   jbd2_journal_load       (journal_t *journal);
extern int	   jbd2_journal_destroy    (journal_t *);
extern int	   jbd2_journal_recover    (journal_t *journal);
extern int	   jbd2_journal_wipe       (journal_t *, int);
extern int	   jbd2_journal_skip_recovery	(journal_t *);
extern void	   jbd2_journal_update_sb_errno(journal_t *);
extern int	   jbd2_journal_update_sb_log_tail	(journal_t *, tid_t,
				unsigned long, int);
extern void	   jbd2_journal_abort      (journal_t *, int);
extern int	   jbd2_journal_errno      (journal_t *);
extern void	   jbd2_journal_ack_err    (journal_t *);
extern int	   jbd2_journal_clear_err  (journal_t *);
extern int	   jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
extern int	   jbd2_journal_force_commit(journal_t *);
extern int	   jbd2_journal_force_commit_nested(journal_t *);
extern int	   jbd2_journal_inode_ranged_write(handle_t *handle,
			struct jbd2_inode *inode, loff_t start_byte,
			loff_t length);
extern int	   jbd2_journal_inode_ranged_wait(handle_t *handle,
			struct jbd2_inode *inode, loff_t start_byte,
			loff_t length);
extern int	   jbd2_journal_submit_inode_data_buffers(
			struct jbd2_inode *jinode);
extern int	   jbd2_journal_finish_inode_data_buffers(
			struct jbd2_inode *jinode);
extern int	   jbd2_journal_begin_ordered_truncate(journal_t *journal,
				struct jbd2_inode *inode, loff_t new_size);
extern void	   jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
extern void	   jbd2_journal_release_jbd_inode(journal_t *journal, struct jbd2_inode *jinode);

/*
 * journal_head management
 */
struct journal_head *jbd2_journal_add_journal_head(struct buffer_head *bh);
struct journal_head *jbd2_journal_grab_journal_head(struct buffer_head *bh);
void jbd2_journal_put_journal_head(struct journal_head *jh);

/*
 * handle management
 */
extern struct kmem_cache *jbd2_handle_cache;

static inline handle_t *jbd2_alloc_handle(gfp_t gfp_flags)
{
	return kmem_cache_zalloc(jbd2_handle_cache, gfp_flags);
}

static inline void jbd2_free_handle(handle_t *handle)
{
	kmem_cache_free(jbd2_handle_cache, handle);
}

/*
 * jbd2_inode management (optional, for those file systems that want to use
 * dynamically allocated jbd2_inode structures)
 */
extern struct kmem_cache *jbd2_inode_cache;

static inline struct jbd2_inode *jbd2_alloc_inode(gfp_t gfp_flags)
{
	return kmem_cache_alloc(jbd2_inode_cache, gfp_flags);
}

static inline void jbd2_free_inode(struct jbd2_inode *jinode)
{
	kmem_cache_free(jbd2_inode_cache, jinode);
}

/* Primary revoke support */
#define JOURNAL_REVOKE_DEFAULT_HASH 256
extern int	   jbd2_journal_init_revoke(journal_t *, int);
extern void	   jbd2_journal_destroy_revoke_record_cache(void);
extern void	   jbd2_journal_destroy_revoke_table_cache(void);
extern int __init jbd2_journal_init_revoke_record_cache(void);
extern int __init jbd2_journal_init_revoke_table_cache(void);

extern void	   jbd2_journal_destroy_revoke(journal_t *);
extern int	   jbd2_journal_revoke (handle_t *, unsigned long long, struct buffer_head *);
extern int	   jbd2_journal_cancel_revoke(handle_t *, struct journal_head *);
extern void	   jbd2_journal_write_revoke_records(transaction_t *transaction,
						     struct list_head *log_bufs);

/* Recovery revoke support */
extern int	jbd2_journal_set_revoke(journal_t *, unsigned long long, tid_t);
extern int	jbd2_journal_test_revoke(journal_t *, unsigned long long, tid_t);
extern void	jbd2_journal_clear_revoke(journal_t *);
extern void	jbd2_journal_switch_revoke_table(journal_t *journal);
extern void	jbd2_clear_buffer_revoked_flags(journal_t *journal);

/*
 * The log thread user interface:
 *
 * Request space in the current transaction, and force transaction commit
 * transitions on demand.
 */

int jbd2_log_start_commit(journal_t *journal, tid_t tid);
int __jbd2_log_start_commit(journal_t *journal, tid_t tid);
int jbd2_journal_start_commit(journal_t *journal, tid_t *tid);
int jbd2_log_wait_commit(journal_t *journal, tid_t tid);
int jbd2_transaction_committed(journal_t *journal, tid_t tid);
int jbd2_complete_transaction(journal_t *journal, tid_t tid);
int jbd2_log_do_checkpoint(journal_t *journal);
int jbd2_trans_will_send_data_barrier(journal_t *journal, tid_t tid);

void __jbd2_log_wait_for_space(journal_t *journal);
extern void __jbd2_journal_drop_transaction(journal_t *, transaction_t *);
extern int jbd2_cleanup_journal_tail(journal_t *);

/* Fast commit related APIs */
int jbd2_fc_begin_commit(journal_t *journal, tid_t tid);
int jbd2_fc_end_commit(journal_t *journal);
int jbd2_fc_end_commit_fallback(journal_t *journal);
int jbd2_fc_get_buf(journal_t *journal, struct buffer_head **bh_out);
int jbd2_submit_inode_data(struct jbd2_inode *jinode);
int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
int jbd2_fc_release_bufs(journal_t *journal);

static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
{
	return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
}

/*
 * is_journal_abort
 *
 * Simple test wrapper function to test the JBD2_ABORT state flag.  This
 * bit, when set, indicates that we have had a fatal error somewhere,
 * either inside the journaling layer or indicated to us by the client
 * (eg. ext3), and that we and should not commit any further
 * transactions.
 */

static inline int is_journal_aborted(journal_t *journal)
{
	return journal->j_flags & JBD2_ABORT;
}

static inline int is_handle_aborted(handle_t *handle)
{
	if (handle->h_aborted || !handle->h_transaction)
		return 1;
	return is_journal_aborted(handle->h_transaction->t_journal);
}

static inline void jbd2_journal_abort_handle(handle_t *handle)
{
	handle->h_aborted = 1;
}

#endif /* __KERNEL__   */

/* Comparison functions for transaction IDs: perform comparisons using
 * modulo arithmetic so that they work over sequence number wraps. */

static inline int tid_gt(tid_t x, tid_t y)
{
	int difference = (x - y);
	return (difference > 0);
}

static inline int tid_geq(tid_t x, tid_t y)
{
	int difference = (x - y);
	return (difference >= 0);
}

extern int jbd2_journal_blocks_per_page(struct inode *inode);
extern size_t journal_tag_bytes(journal_t *journal);

static inline bool jbd2_journal_has_csum_v2or3_feature(journal_t *j)
{
	return jbd2_has_feature_csum2(j) || jbd2_has_feature_csum3(j);
}

static inline int jbd2_journal_has_csum_v2or3(journal_t *journal)
{
	WARN_ON_ONCE(jbd2_journal_has_csum_v2or3_feature(journal) &&
		     journal->j_chksum_driver == NULL);

	return journal->j_chksum_driver != NULL;
}

static inline int jbd2_journal_get_num_fc_blks(journal_superblock_t *jsb)
{
	int num_fc_blocks = be32_to_cpu(jsb->s_num_fc_blks);

	return num_fc_blocks ? num_fc_blocks : JBD2_DEFAULT_FAST_COMMIT_BLOCKS;
}

/*
 * Return number of free blocks in the log. Must be called under j_state_lock.
 */
static inline unsigned long jbd2_log_space_left(journal_t *journal)
{
	/* Allow for rounding errors */
	long free = journal->j_free - 32;

	if (journal->j_committing_transaction) {
		free -= atomic_read(&journal->
                        j_committing_transaction->t_outstanding_credits);
	}
	return max_t(long, free, 0);
}

/*
 * Definitions which augment the buffer_head layer
 */

/* journaling buffer types */
#define BJ_None		0	/* Not journaled */
#define BJ_Metadata	1	/* Normal journaled metadata */
#define BJ_Forget	2	/* Buffer superseded by this transaction */
#define BJ_Shadow	3	/* Buffer contents being shadowed to the log */
#define BJ_Reserved	4	/* Buffer is reserved for access by journal */
#define BJ_Types	5

/* JBD uses a CRC32 checksum */
#define JBD_MAX_CHECKSUM_SIZE 4

static inline u32 jbd2_chksum(journal_t *journal, u32 crc,
			      const void *address, unsigned int length)
{
	struct {
		struct shash_desc shash;
		char ctx[JBD_MAX_CHECKSUM_SIZE];
	} desc;
	int err;

	BUG_ON(crypto_shash_descsize(journal->j_chksum_driver) >
		JBD_MAX_CHECKSUM_SIZE);

	desc.shash.tfm = journal->j_chksum_driver;
	*(u32 *)desc.ctx = crc;

	err = crypto_shash_update(&desc.shash, address, length);
	BUG_ON(err);

	return *(u32 *)desc.ctx;
}

/* Return most recent uncommitted transaction */
static inline tid_t  jbd2_get_latest_transaction(journal_t *journal)
{
	tid_t tid;

	read_lock(&journal->j_state_lock);
	tid = journal->j_commit_request;
	if (journal->j_running_transaction)
		tid = journal->j_running_transaction->t_tid;
	read_unlock(&journal->j_state_lock);
	return tid;
}

static inline int jbd2_handle_buffer_credits(handle_t *handle)
{
	journal_t *journal;

	if (!handle->h_reserved)
		journal = handle->h_transaction->t_journal;
	else
		journal = handle->h_journal;

	return handle->h_total_credits -
		DIV_ROUND_UP(handle->h_revoke_credits_requested,
			     journal->j_revoke_records_per_block);
}

#ifdef __KERNEL__

#define buffer_trace_init(bh)	do {} while (0)
#define print_buffer_fields(bh)	do {} while (0)
#define print_buffer_trace(bh)	do {} while (0)
#define BUFFER_TRACE(bh, info)	do {} while (0)
#define BUFFER_TRACE2(bh, bh2, info)	do {} while (0)
#define JBUFFER_TRACE(jh, info)	do {} while (0)

#endif	/* __KERNEL__ */

#define EFSBADCRC	EBADMSG		/* Bad CRC detected */
#define EFSCORRUPTED	EUCLEAN		/* Filesystem is corrupted */

#endif	/* _LINUX_JBD2_H */