aboutsummaryrefslogtreecommitdiff
path: root/fs/ocfs2/super.c
blob: 01fe40ee5ea943e2a47ae1a96987eed12673a847 (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
/* -*- mode: c; c-basic-offset: 8; -*-
 * vim: noexpandtab sw=8 ts=8 sts=0:
 *
 * super.c
 *
 * load/unload driver, mount/dismount volumes
 *
 * Copyright (C) 2002, 2004 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation; either
 * version 2 of the License, or (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/module.h>
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/utsname.h>
#include <linux/init.h>
#include <linux/random.h>
#include <linux/statfs.h>
#include <linux/moduleparam.h>
#include <linux/blkdev.h>
#include <linux/socket.h>
#include <linux/inet.h>
#include <linux/parser.h>
#include <linux/crc32.h>
#include <linux/debugfs.h>
#include <linux/mount.h>

#include <cluster/nodemanager.h>

#define MLOG_MASK_PREFIX ML_SUPER
#include <cluster/masklog.h>

#include "ocfs2.h"

/* this should be the only file to include a version 1 header */
#include "ocfs1_fs_compat.h"

#include "alloc.h"
#include "dlmglue.h"
#include "export.h"
#include "extent_map.h"
#include "heartbeat.h"
#include "inode.h"
#include "journal.h"
#include "localalloc.h"
#include "namei.h"
#include "slot_map.h"
#include "super.h"
#include "sysfile.h"
#include "uptodate.h"
#include "ver.h"

#include "buffer_head_io.h"

static struct kmem_cache *ocfs2_inode_cachep = NULL;

/* OCFS2 needs to schedule several differnt types of work which
 * require cluster locking, disk I/O, recovery waits, etc. Since these
 * types of work tend to be heavy we avoid using the kernel events
 * workqueue and schedule on our own. */
struct workqueue_struct *ocfs2_wq = NULL;

static struct dentry *ocfs2_debugfs_root = NULL;

MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");

struct mount_options
{
	unsigned long	commit_interval;
	unsigned long	mount_opt;
	unsigned int	atime_quantum;
	signed short	slot;
	unsigned int	localalloc_opt;
};

static int ocfs2_parse_options(struct super_block *sb, char *options,
			       struct mount_options *mopt,
			       int is_remount);
static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt);
static void ocfs2_put_super(struct super_block *sb);
static int ocfs2_mount_volume(struct super_block *sb);
static int ocfs2_remount(struct super_block *sb, int *flags, char *data);
static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err);
static int ocfs2_initialize_mem_caches(void);
static void ocfs2_free_mem_caches(void);
static void ocfs2_delete_osb(struct ocfs2_super *osb);

static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf);

static int ocfs2_sync_fs(struct super_block *sb, int wait);

static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb);
static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb);
static void ocfs2_release_system_inodes(struct ocfs2_super *osb);
static int ocfs2_fill_local_node_info(struct ocfs2_super *osb);
static int ocfs2_check_volume(struct ocfs2_super *osb);
static int ocfs2_verify_volume(struct ocfs2_dinode *di,
			       struct buffer_head *bh,
			       u32 sectsize);
static int ocfs2_initialize_super(struct super_block *sb,
				  struct buffer_head *bh,
				  int sector_size);
static int ocfs2_get_sector(struct super_block *sb,
			    struct buffer_head **bh,
			    int block,
			    int sect_size);
static void ocfs2_write_super(struct super_block *sb);
static struct inode *ocfs2_alloc_inode(struct super_block *sb);
static void ocfs2_destroy_inode(struct inode *inode);

static const struct super_operations ocfs2_sops = {
	.statfs		= ocfs2_statfs,
	.alloc_inode	= ocfs2_alloc_inode,
	.destroy_inode	= ocfs2_destroy_inode,
	.drop_inode	= ocfs2_drop_inode,
	.clear_inode	= ocfs2_clear_inode,
	.delete_inode	= ocfs2_delete_inode,
	.sync_fs	= ocfs2_sync_fs,
	.write_super	= ocfs2_write_super,
	.put_super	= ocfs2_put_super,
	.remount_fs	= ocfs2_remount,
	.show_options   = ocfs2_show_options,
};

enum {
	Opt_barrier,
	Opt_err_panic,
	Opt_err_ro,
	Opt_intr,
	Opt_nointr,
	Opt_hb_none,
	Opt_hb_local,
	Opt_data_ordered,
	Opt_data_writeback,
	Opt_atime_quantum,
	Opt_slot,
	Opt_commit,
	Opt_localalloc,
	Opt_localflocks,
	Opt_err,
};

static match_table_t tokens = {
	{Opt_barrier, "barrier=%u"},
	{Opt_err_panic, "errors=panic"},
	{Opt_err_ro, "errors=remount-ro"},
	{Opt_intr, "intr"},
	{Opt_nointr, "nointr"},
	{Opt_hb_none, OCFS2_HB_NONE},
	{Opt_hb_local, OCFS2_HB_LOCAL},
	{Opt_data_ordered, "data=ordered"},
	{Opt_data_writeback, "data=writeback"},
	{Opt_atime_quantum, "atime_quantum=%u"},
	{Opt_slot, "preferred_slot=%u"},
	{Opt_commit, "commit=%u"},
	{Opt_localalloc, "localalloc=%d"},
	{Opt_localflocks, "localflocks"},
	{Opt_err, NULL}
};

/*
 * write_super and sync_fs ripped right out of ext3.
 */
static void ocfs2_write_super(struct super_block *sb)
{
	if (mutex_trylock(&sb->s_lock) != 0)
		BUG();
	sb->s_dirt = 0;
}

static int ocfs2_sync_fs(struct super_block *sb, int wait)
{
	int status;
	tid_t target;
	struct ocfs2_super *osb = OCFS2_SB(sb);

	sb->s_dirt = 0;

	if (ocfs2_is_hard_readonly(osb))
		return -EROFS;

	if (wait) {
		status = ocfs2_flush_truncate_log(osb);
		if (status < 0)
			mlog_errno(status);
	} else {
		ocfs2_schedule_truncate_log_flush(osb, 0);
	}

	if (journal_start_commit(OCFS2_SB(sb)->journal->j_journal, &target)) {
		if (wait)
			log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
					target);
	}
	return 0;
}

static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb)
{
	struct inode *new = NULL;
	int status = 0;
	int i;

	mlog_entry_void();

	new = ocfs2_iget(osb, osb->root_blkno, OCFS2_FI_FLAG_SYSFILE, 0);
	if (IS_ERR(new)) {
		status = PTR_ERR(new);
		mlog_errno(status);
		goto bail;
	}
	osb->root_inode = new;

	new = ocfs2_iget(osb, osb->system_dir_blkno, OCFS2_FI_FLAG_SYSFILE, 0);
	if (IS_ERR(new)) {
		status = PTR_ERR(new);
		mlog_errno(status);
		goto bail;
	}
	osb->sys_root_inode = new;

	for (i = OCFS2_FIRST_ONLINE_SYSTEM_INODE;
	     i <= OCFS2_LAST_GLOBAL_SYSTEM_INODE; i++) {
		new = ocfs2_get_system_file_inode(osb, i, osb->slot_num);
		if (!new) {
			ocfs2_release_system_inodes(osb);
			status = -EINVAL;
			mlog_errno(status);
			/* FIXME: Should ERROR_RO_FS */
			mlog(ML_ERROR, "Unable to load system inode %d, "
			     "possibly corrupt fs?", i);
			goto bail;
		}
		// the array now has one ref, so drop this one
		iput(new);
	}

bail:
	mlog_exit(status);
	return status;
}

static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb)
{
	struct inode *new = NULL;
	int status = 0;
	int i;

	mlog_entry_void();

	for (i = OCFS2_LAST_GLOBAL_SYSTEM_INODE + 1;
	     i < NUM_SYSTEM_INODES;
	     i++) {
		new = ocfs2_get_system_file_inode(osb, i, osb->slot_num);
		if (!new) {
			ocfs2_release_system_inodes(osb);
			status = -EINVAL;
			mlog(ML_ERROR, "status=%d, sysfile=%d, slot=%d\n",
			     status, i, osb->slot_num);
			goto bail;
		}
		/* the array now has one ref, so drop this one */
		iput(new);
	}

bail:
	mlog_exit(status);
	return status;
}

static void ocfs2_release_system_inodes(struct ocfs2_super *osb)
{
	int i;
	struct inode *inode;

	mlog_entry_void();

	for (i = 0; i < NUM_SYSTEM_INODES; i++) {
		inode = osb->system_inodes[i];
		if (inode) {
			iput(inode);
			osb->system_inodes[i] = NULL;
		}
	}

	inode = osb->sys_root_inode;
	if (inode) {
		iput(inode);
		osb->sys_root_inode = NULL;
	}

	inode = osb->root_inode;
	if (inode) {
		iput(inode);
		osb->root_inode = NULL;
	}

	mlog_exit(0);
}

/* We're allocating fs objects, use GFP_NOFS */
static struct inode *ocfs2_alloc_inode(struct super_block *sb)
{
	struct ocfs2_inode_info *oi;

	oi = kmem_cache_alloc(ocfs2_inode_cachep, GFP_NOFS);
	if (!oi)
		return NULL;

	return &oi->vfs_inode;
}

static void ocfs2_destroy_inode(struct inode *inode)
{
	kmem_cache_free(ocfs2_inode_cachep, OCFS2_I(inode));
}

static unsigned long long ocfs2_max_file_offset(unsigned int bbits,
						unsigned int cbits)
{
	unsigned int bytes = 1 << cbits;
	unsigned int trim = bytes;
	unsigned int bitshift = 32;

	/*
	 * i_size and all block offsets in ocfs2 are always 64 bits
	 * wide. i_clusters is 32 bits, in cluster-sized units. So on
	 * 64 bit platforms, cluster size will be the limiting factor.
	 */

#if BITS_PER_LONG == 32
# if defined(CONFIG_LBD)
	BUILD_BUG_ON(sizeof(sector_t) != 8);
	/*
	 * We might be limited by page cache size.
	 */
	if (bytes > PAGE_CACHE_SIZE) {
		bytes = PAGE_CACHE_SIZE;
		trim = 1;
		/*
		 * Shift by 31 here so that we don't get larger than
		 * MAX_LFS_FILESIZE
		 */
		bitshift = 31;
	}
# else
	/*
	 * We are limited by the size of sector_t. Use block size, as
	 * that's what we expose to the VFS.
	 */
	bytes = 1 << bbits;
	trim = 1;
	bitshift = 31;
# endif
#endif

	/*
	 * Trim by a whole cluster when we can actually approach the
	 * on-disk limits. Otherwise we can overflow i_clusters when
	 * an extent start is at the max offset.
	 */
	return (((unsigned long long)bytes) << bitshift) - trim;
}

static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
{
	int incompat_features;
	int ret = 0;
	struct mount_options parsed_options;
	struct ocfs2_super *osb = OCFS2_SB(sb);

	if (!ocfs2_parse_options(sb, data, &parsed_options, 1)) {
		ret = -EINVAL;
		goto out;
	}

	if ((osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) !=
	    (parsed_options.mount_opt & OCFS2_MOUNT_HB_LOCAL)) {
		ret = -EINVAL;
		mlog(ML_ERROR, "Cannot change heartbeat mode on remount\n");
		goto out;
	}

	if ((osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK) !=
	    (parsed_options.mount_opt & OCFS2_MOUNT_DATA_WRITEBACK)) {
		ret = -EINVAL;
		mlog(ML_ERROR, "Cannot change data mode on remount\n");
		goto out;
	}

	/* We're going to/from readonly mode. */
	if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
		/* Lock here so the check of HARD_RO and the potential
		 * setting of SOFT_RO is atomic. */
		spin_lock(&osb->osb_lock);
		if (osb->osb_flags & OCFS2_OSB_HARD_RO) {
			mlog(ML_ERROR, "Remount on readonly device is forbidden.\n");
			ret = -EROFS;
			goto unlock_osb;
		}

		if (*flags & MS_RDONLY) {
			mlog(0, "Going to ro mode.\n");
			sb->s_flags |= MS_RDONLY;
			osb->osb_flags |= OCFS2_OSB_SOFT_RO;
		} else {
			mlog(0, "Making ro filesystem writeable.\n");

			if (osb->osb_flags & OCFS2_OSB_ERROR_FS) {
				mlog(ML_ERROR, "Cannot remount RDWR "
				     "filesystem due to previous errors.\n");
				ret = -EROFS;
				goto unlock_osb;
			}
			incompat_features = OCFS2_HAS_RO_COMPAT_FEATURE(sb, ~OCFS2_FEATURE_RO_COMPAT_SUPP);
			if (incompat_features) {
				mlog(ML_ERROR, "Cannot remount RDWR because "
				     "of unsupported optional features "
				     "(%x).\n", incompat_features);
				ret = -EINVAL;
				goto unlock_osb;
			}
			sb->s_flags &= ~MS_RDONLY;
			osb->osb_flags &= ~OCFS2_OSB_SOFT_RO;
		}
unlock_osb:
		spin_unlock(&osb->osb_lock);
	}

	if (!ret) {
		/* Only save off the new mount options in case of a successful
		 * remount. */
		osb->s_mount_opt = parsed_options.mount_opt;
		osb->s_atime_quantum = parsed_options.atime_quantum;
		osb->preferred_slot = parsed_options.slot;
		if (parsed_options.commit_interval)
			osb->osb_commit_interval = parsed_options.commit_interval;

		if (!ocfs2_is_hard_readonly(osb))
			ocfs2_set_journal_params(osb);
	}
out:
	return ret;
}

static int ocfs2_sb_probe(struct super_block *sb,
			  struct buffer_head **bh,
			  int *sector_size)
{
	int status, tmpstat;
	struct ocfs1_vol_disk_hdr *hdr;
	struct ocfs2_dinode *di;
	int blksize;

	*bh = NULL;

	/* may be > 512 */
	*sector_size = bdev_hardsect_size(sb->s_bdev);
	if (*sector_size > OCFS2_MAX_BLOCKSIZE) {
		mlog(ML_ERROR, "Hardware sector size too large: %d (max=%d)\n",
		     *sector_size, OCFS2_MAX_BLOCKSIZE);
		status = -EINVAL;
		goto bail;
	}

	/* Can this really happen? */
	if (*sector_size < OCFS2_MIN_BLOCKSIZE)
		*sector_size = OCFS2_MIN_BLOCKSIZE;

	/* check block zero for old format */
	status = ocfs2_get_sector(sb, bh, 0, *sector_size);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}
	hdr = (struct ocfs1_vol_disk_hdr *) (*bh)->b_data;
	if (hdr->major_version == OCFS1_MAJOR_VERSION) {
		mlog(ML_ERROR, "incompatible version: %u.%u\n",
		     hdr->major_version, hdr->minor_version);
		status = -EINVAL;
	}
	if (memcmp(hdr->signature, OCFS1_VOLUME_SIGNATURE,
		   strlen(OCFS1_VOLUME_SIGNATURE)) == 0) {
		mlog(ML_ERROR, "incompatible volume signature: %8s\n",
		     hdr->signature);
		status = -EINVAL;
	}
	brelse(*bh);
	*bh = NULL;
	if (status < 0) {
		mlog(ML_ERROR, "This is an ocfs v1 filesystem which must be "
		     "upgraded before mounting with ocfs v2\n");
		goto bail;
	}

	/*
	 * Now check at magic offset for 512, 1024, 2048, 4096
	 * blocksizes.  4096 is the maximum blocksize because it is
	 * the minimum clustersize.
	 */
	status = -EINVAL;
	for (blksize = *sector_size;
	     blksize <= OCFS2_MAX_BLOCKSIZE;
	     blksize <<= 1) {
		tmpstat = ocfs2_get_sector(sb, bh,
					   OCFS2_SUPER_BLOCK_BLKNO,
					   blksize);
		if (tmpstat < 0) {
			status = tmpstat;
			mlog_errno(status);
			goto bail;
		}
		di = (struct ocfs2_dinode *) (*bh)->b_data;
		status = ocfs2_verify_volume(di, *bh, blksize);
		if (status >= 0)
			goto bail;
		brelse(*bh);
		*bh = NULL;
		if (status != -EAGAIN)
			break;
	}

bail:
	return status;
}

static int ocfs2_verify_heartbeat(struct ocfs2_super *osb)
{
	if (ocfs2_mount_local(osb)) {
		if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) {
			mlog(ML_ERROR, "Cannot heartbeat on a locally "
			     "mounted device.\n");
			return -EINVAL;
		}
	}

	if (!(osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL)) {
		if (!ocfs2_mount_local(osb) && !ocfs2_is_hard_readonly(osb)) {
			mlog(ML_ERROR, "Heartbeat has to be started to mount "
			     "a read-write clustered device.\n");
			return -EINVAL;
		}
	}

	return 0;
}

static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
{
	struct dentry *root;
	int status, sector_size;
	struct mount_options parsed_options;
	struct inode *inode = NULL;
	struct ocfs2_super *osb = NULL;
	struct buffer_head *bh = NULL;
	char nodestr[8];

	mlog_entry("%p, %p, %i", sb, data, silent);

	if (!ocfs2_parse_options(sb, data, &parsed_options, 0)) {
		status = -EINVAL;
		goto read_super_error;
	}

	/* for now we only have one cluster/node, make sure we see it
	 * in the heartbeat universe */
	if (parsed_options.mount_opt & OCFS2_MOUNT_HB_LOCAL) {
		if (!o2hb_check_local_node_heartbeating()) {
			status = -EINVAL;
			goto read_super_error;
		}
	}

	/* probe for superblock */
	status = ocfs2_sb_probe(sb, &bh, &sector_size);
	if (status < 0) {
		mlog(ML_ERROR, "superblock probe failed!\n");
		goto read_super_error;
	}

	status = ocfs2_initialize_super(sb, bh, sector_size);
	osb = OCFS2_SB(sb);
	if (status < 0) {
		mlog_errno(status);
		goto read_super_error;
	}
	brelse(bh);
	bh = NULL;
	osb->s_mount_opt = parsed_options.mount_opt;
	osb->s_atime_quantum = parsed_options.atime_quantum;
	osb->preferred_slot = parsed_options.slot;
	osb->osb_commit_interval = parsed_options.commit_interval;
	osb->local_alloc_size = parsed_options.localalloc_opt;

	sb->s_magic = OCFS2_SUPER_MAGIC;

	/* Hard readonly mode only if: bdev_read_only, MS_RDONLY,
	 * heartbeat=none */
	if (bdev_read_only(sb->s_bdev)) {
		if (!(sb->s_flags & MS_RDONLY)) {
			status = -EACCES;
			mlog(ML_ERROR, "Readonly device detected but readonly "
			     "mount was not specified.\n");
			goto read_super_error;
		}

		/* You should not be able to start a local heartbeat
		 * on a readonly device. */
		if (osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) {
			status = -EROFS;
			mlog(ML_ERROR, "Local heartbeat specified on readonly "
			     "device.\n");
			goto read_super_error;
		}

		status = ocfs2_check_journals_nolocks(osb);
		if (status < 0) {
			if (status == -EROFS)
				mlog(ML_ERROR, "Recovery required on readonly "
				     "file system, but write access is "
				     "unavailable.\n");
			else
				mlog_errno(status);			
			goto read_super_error;
		}

		ocfs2_set_ro_flag(osb, 1);

		printk(KERN_NOTICE "Readonly device detected. No cluster "
		       "services will be utilized for this mount. Recovery "
		       "will be skipped.\n");
	}

	if (!ocfs2_is_hard_readonly(osb)) {
		if (sb->s_flags & MS_RDONLY)
			ocfs2_set_ro_flag(osb, 0);
	}

	status = ocfs2_verify_heartbeat(osb);
	if (status < 0) {
		mlog_errno(status);
		goto read_super_error;
	}

	osb->osb_debug_root = debugfs_create_dir(osb->uuid_str,
						 ocfs2_debugfs_root);
	if (!osb->osb_debug_root) {
		status = -EINVAL;
		mlog(ML_ERROR, "Unable to create per-mount debugfs root.\n");
		goto read_super_error;
	}

	status = ocfs2_mount_volume(sb);
	if (osb->root_inode)
		inode = igrab(osb->root_inode);

	if (status < 0)
		goto read_super_error;

	if (!inode) {
		status = -EIO;
		mlog_errno(status);
		goto read_super_error;
	}

	root = d_alloc_root(inode);
	if (!root) {
		status = -ENOMEM;
		mlog_errno(status);
		goto read_super_error;
	}

	sb->s_root = root;

	ocfs2_complete_mount_recovery(osb);

	if (ocfs2_mount_local(osb))
		snprintf(nodestr, sizeof(nodestr), "local");
	else
		snprintf(nodestr, sizeof(nodestr), "%d", osb->node_num);

	printk(KERN_INFO "ocfs2: Mounting device (%s) on (node %s, slot %d) "
	       "with %s data mode.\n",
	       osb->dev_str, nodestr, osb->slot_num,
	       osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK ? "writeback" :
	       "ordered");

	atomic_set(&osb->vol_state, VOLUME_MOUNTED);
	wake_up(&osb->osb_mount_event);

	mlog_exit(status);
	return status;

read_super_error:
	if (bh != NULL)
		brelse(bh);

	if (inode)
		iput(inode);

	if (osb) {
		atomic_set(&osb->vol_state, VOLUME_DISABLED);
		wake_up(&osb->osb_mount_event);
		ocfs2_dismount_volume(sb, 1);
	}

	mlog_exit(status);
	return status;
}

static int ocfs2_get_sb(struct file_system_type *fs_type,
			int flags,
			const char *dev_name,
			void *data,
			struct vfsmount *mnt)
{
	return get_sb_bdev(fs_type, flags, dev_name, data, ocfs2_fill_super,
			   mnt);
}

static struct file_system_type ocfs2_fs_type = {
	.owner          = THIS_MODULE,
	.name           = "ocfs2",
	.get_sb         = ocfs2_get_sb, /* is this called when we mount
					* the fs? */
	.kill_sb        = kill_block_super, /* set to the generic one
					     * right now, but do we
					     * need to change that? */
	.fs_flags       = FS_REQUIRES_DEV|FS_RENAME_DOES_D_MOVE,
	.next           = NULL
};

static int ocfs2_parse_options(struct super_block *sb,
			       char *options,
			       struct mount_options *mopt,
			       int is_remount)
{
	int status;
	char *p;

	mlog_entry("remount: %d, options: \"%s\"\n", is_remount,
		   options ? options : "(none)");

	mopt->commit_interval = 0;
	mopt->mount_opt = 0;
	mopt->atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;
	mopt->slot = OCFS2_INVALID_SLOT;
	mopt->localalloc_opt = OCFS2_DEFAULT_LOCAL_ALLOC_SIZE;

	if (!options) {
		status = 1;
		goto bail;
	}

	while ((p = strsep(&options, ",")) != NULL) {
		int token, option;
		substring_t args[MAX_OPT_ARGS];

		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_hb_local:
			mopt->mount_opt |= OCFS2_MOUNT_HB_LOCAL;
			break;
		case Opt_hb_none:
			mopt->mount_opt &= ~OCFS2_MOUNT_HB_LOCAL;
			break;
		case Opt_barrier:
			if (match_int(&args[0], &option)) {
				status = 0;
				goto bail;
			}
			if (option)
				mopt->mount_opt |= OCFS2_MOUNT_BARRIER;
			else
				mopt->mount_opt &= ~OCFS2_MOUNT_BARRIER;
			break;
		case Opt_intr:
			mopt->mount_opt &= ~OCFS2_MOUNT_NOINTR;
			break;
		case Opt_nointr:
			mopt->mount_opt |= OCFS2_MOUNT_NOINTR;
			break;
		case Opt_err_panic:
			mopt->mount_opt |= OCFS2_MOUNT_ERRORS_PANIC;
			break;
		case Opt_err_ro:
			mopt->mount_opt &= ~OCFS2_MOUNT_ERRORS_PANIC;
			break;
		case Opt_data_ordered:
			mopt->mount_opt &= ~OCFS2_MOUNT_DATA_WRITEBACK;
			break;
		case Opt_data_writeback:
			mopt->mount_opt |= OCFS2_MOUNT_DATA_WRITEBACK;
			break;
		case Opt_atime_quantum:
			if (match_int(&args[0], &option)) {
				status = 0;
				goto bail;
			}
			if (option >= 0)
				mopt->atime_quantum = option;
			break;
		case Opt_slot:
			option = 0;
			if (match_int(&args[0], &option)) {
				status = 0;
				goto bail;
			}
			if (option)
				mopt->slot = (s16)option;
			break;
		case Opt_commit:
			option = 0;
			if (match_int(&args[0], &option)) {
				status = 0;
				goto bail;
			}
			if (option < 0)
				return 0;
			if (option == 0)
				option = JBD_DEFAULT_MAX_COMMIT_AGE;
			mopt->commit_interval = HZ * option;
			break;
		case Opt_localalloc:
			option = 0;
			if (match_int(&args[0], &option)) {
				status = 0;
				goto bail;
			}
			if (option >= 0 && (option <= ocfs2_local_alloc_size(sb) * 8))
				mopt->localalloc_opt = option;
			break;
		case Opt_localflocks:
			/*
			 * Changing this during remount could race
			 * flock() requests, or "unbalance" existing
			 * ones (e.g., a lock is taken in one mode but
			 * dropped in the other). If users care enough
			 * to flip locking modes during remount, we
			 * could add a "local" flag to individual
			 * flock structures for proper tracking of
			 * state.
			 */
			if (!is_remount)
				mopt->mount_opt |= OCFS2_MOUNT_LOCALFLOCKS;
			break;
		default:
			mlog(ML_ERROR,
			     "Unrecognized mount option \"%s\" "
			     "or missing value\n", p);
			status = 0;
			goto bail;
		}
	}

	status = 1;

bail:
	mlog_exit(status);
	return status;
}

static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt)
{
	struct ocfs2_super *osb = OCFS2_SB(mnt->mnt_sb);
	unsigned long opts = osb->s_mount_opt;

	if (opts & OCFS2_MOUNT_HB_LOCAL)
		seq_printf(s, ",_netdev,heartbeat=local");
	else
		seq_printf(s, ",heartbeat=none");

	if (opts & OCFS2_MOUNT_NOINTR)
		seq_printf(s, ",nointr");

	if (opts & OCFS2_MOUNT_DATA_WRITEBACK)
		seq_printf(s, ",data=writeback");
	else
		seq_printf(s, ",data=ordered");

	if (opts & OCFS2_MOUNT_BARRIER)
		seq_printf(s, ",barrier=1");

	if (opts & OCFS2_MOUNT_ERRORS_PANIC)
		seq_printf(s, ",errors=panic");
	else
		seq_printf(s, ",errors=remount-ro");

	if (osb->preferred_slot != OCFS2_INVALID_SLOT)
		seq_printf(s, ",preferred_slot=%d", osb->preferred_slot);

	if (osb->s_atime_quantum != OCFS2_DEFAULT_ATIME_QUANTUM)
		seq_printf(s, ",atime_quantum=%u", osb->s_atime_quantum);

	if (osb->osb_commit_interval)
		seq_printf(s, ",commit=%u",
			   (unsigned) (osb->osb_commit_interval / HZ));

	if (osb->local_alloc_size != OCFS2_DEFAULT_LOCAL_ALLOC_SIZE)
		seq_printf(s, ",localalloc=%d", osb->local_alloc_size);

	if (opts & OCFS2_MOUNT_LOCALFLOCKS)
		seq_printf(s, ",localflocks,");

	return 0;
}

static int __init ocfs2_init(void)
{
	int status;

	mlog_entry_void();

	ocfs2_print_version();

	status = init_ocfs2_uptodate_cache();
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	status = ocfs2_initialize_mem_caches();
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	ocfs2_wq = create_singlethread_workqueue("ocfs2_wq");
	if (!ocfs2_wq) {
		status = -ENOMEM;
		goto leave;
	}

	ocfs2_debugfs_root = debugfs_create_dir("ocfs2", NULL);
	if (!ocfs2_debugfs_root) {
		status = -EFAULT;
		mlog(ML_ERROR, "Unable to create ocfs2 debugfs root.\n");
	}

leave:
	if (status < 0) {
		ocfs2_free_mem_caches();
		exit_ocfs2_uptodate_cache();
	}

	mlog_exit(status);

	if (status >= 0) {
		return register_filesystem(&ocfs2_fs_type);
	} else
		return -1;
}

static void __exit ocfs2_exit(void)
{
	mlog_entry_void();

	if (ocfs2_wq) {
		flush_workqueue(ocfs2_wq);
		destroy_workqueue(ocfs2_wq);
	}

	debugfs_remove(ocfs2_debugfs_root);

	ocfs2_free_mem_caches();

	unregister_filesystem(&ocfs2_fs_type);

	exit_ocfs2_uptodate_cache();

	mlog_exit_void();
}

static void ocfs2_put_super(struct super_block *sb)
{
	mlog_entry("(0x%p)\n", sb);

	ocfs2_sync_blockdev(sb);
	ocfs2_dismount_volume(sb, 0);

	mlog_exit_void();
}

static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct ocfs2_super *osb;
	u32 numbits, freebits;
	int status;
	struct ocfs2_dinode *bm_lock;
	struct buffer_head *bh = NULL;
	struct inode *inode = NULL;

	mlog_entry("(%p, %p)\n", dentry->d_sb, buf);

	osb = OCFS2_SB(dentry->d_sb);

	inode = ocfs2_get_system_file_inode(osb,
					    GLOBAL_BITMAP_SYSTEM_INODE,
					    OCFS2_INVALID_SLOT);
	if (!inode) {
		mlog(ML_ERROR, "failed to get bitmap inode\n");
		status = -EIO;
		goto bail;
	}

	status = ocfs2_inode_lock(inode, &bh, 0);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}

	bm_lock = (struct ocfs2_dinode *) bh->b_data;

	numbits = le32_to_cpu(bm_lock->id1.bitmap1.i_total);
	freebits = numbits - le32_to_cpu(bm_lock->id1.bitmap1.i_used);

	buf->f_type = OCFS2_SUPER_MAGIC;
	buf->f_bsize = dentry->d_sb->s_blocksize;
	buf->f_namelen = OCFS2_MAX_FILENAME_LEN;
	buf->f_blocks = ((sector_t) numbits) *
			(osb->s_clustersize >> osb->sb->s_blocksize_bits);
	buf->f_bfree = ((sector_t) freebits) *
		       (osb->s_clustersize >> osb->sb->s_blocksize_bits);
	buf->f_bavail = buf->f_bfree;
	buf->f_files = numbits;
	buf->f_ffree = freebits;

	brelse(bh);

	ocfs2_inode_unlock(inode, 0);
	status = 0;
bail:
	if (inode)
		iput(inode);

	mlog_exit(status);

	return status;
}

static void ocfs2_inode_init_once(struct kmem_cache *cachep, void *data)
{
	struct ocfs2_inode_info *oi = data;

	oi->ip_flags = 0;
	oi->ip_open_count = 0;
	spin_lock_init(&oi->ip_lock);
	ocfs2_extent_map_init(&oi->vfs_inode);
	INIT_LIST_HEAD(&oi->ip_io_markers);
	oi->ip_created_trans = 0;
	oi->ip_last_trans = 0;
	oi->ip_dir_start_lookup = 0;

	init_rwsem(&oi->ip_alloc_sem);
	mutex_init(&oi->ip_io_mutex);

	oi->ip_blkno = 0ULL;
	oi->ip_clusters = 0;

	ocfs2_lock_res_init_once(&oi->ip_rw_lockres);
	ocfs2_lock_res_init_once(&oi->ip_inode_lockres);
	ocfs2_lock_res_init_once(&oi->ip_open_lockres);

	ocfs2_metadata_cache_init(&oi->vfs_inode);

	inode_init_once(&oi->vfs_inode);
}

static int ocfs2_initialize_mem_caches(void)
{
	ocfs2_inode_cachep = kmem_cache_create("ocfs2_inode_cache",
				       sizeof(struct ocfs2_inode_info),
				       0,
				       (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
				       ocfs2_inode_init_once);
	if (!ocfs2_inode_cachep)
		return -ENOMEM;

	return 0;
}

static void ocfs2_free_mem_caches(void)
{
	if (ocfs2_inode_cachep)
		kmem_cache_destroy(ocfs2_inode_cachep);

	ocfs2_inode_cachep = NULL;
}

static int ocfs2_get_sector(struct super_block *sb,
			    struct buffer_head **bh,
			    int block,
			    int sect_size)
{
	if (!sb_set_blocksize(sb, sect_size)) {
		mlog(ML_ERROR, "unable to set blocksize\n");
		return -EIO;
	}

	*bh = sb_getblk(sb, block);
	if (!*bh) {
		mlog_errno(-EIO);
		return -EIO;
	}
	lock_buffer(*bh);
	if (!buffer_dirty(*bh))
		clear_buffer_uptodate(*bh);
	unlock_buffer(*bh);
	ll_rw_block(READ, 1, bh);
	wait_on_buffer(*bh);
	return 0;
}

/* ocfs2 1.0 only allows one cluster and node identity per kernel image. */
static int ocfs2_fill_local_node_info(struct ocfs2_super *osb)
{
	int status;

	/* XXX hold a ref on the node while mounte?  easy enough, if
	 * desirable. */
	if (ocfs2_mount_local(osb))
		osb->node_num = 0;
	else
		osb->node_num = o2nm_this_node();

	if (osb->node_num == O2NM_MAX_NODES) {
		mlog(ML_ERROR, "could not find this host's node number\n");
		status = -ENOENT;
		goto bail;
	}

	mlog(0, "I am node %d\n", osb->node_num);

	status = 0;
bail:
	return status;
}

static int ocfs2_mount_volume(struct super_block *sb)
{
	int status = 0;
	int unlock_super = 0;
	struct ocfs2_super *osb = OCFS2_SB(sb);

	mlog_entry_void();

	if (ocfs2_is_hard_readonly(osb))
		goto leave;

	status = ocfs2_fill_local_node_info(osb);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	status = ocfs2_dlm_init(osb);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	status = ocfs2_super_lock(osb, 1);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}
	unlock_super = 1;

	/* This will load up the node map and add ourselves to it. */
	status = ocfs2_find_slot(osb);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	/* load all node-local system inodes */
	status = ocfs2_init_local_system_inodes(osb);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	status = ocfs2_check_volume(osb);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	status = ocfs2_truncate_log_init(osb);
	if (status < 0) {
		mlog_errno(status);
		goto leave;
	}

	if (ocfs2_mount_local(osb))
		goto leave;

leave:
	if (unlock_super)
		ocfs2_super_unlock(osb, 1);

	mlog_exit(status);
	return status;
}

/* we can't grab the goofy sem lock from inside wait_event, so we use
 * memory barriers to make sure that we'll see the null task before
 * being woken up */
static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
{
	mb();
	return osb->recovery_thread_task != NULL;
}

static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
{
	int tmp;
	struct ocfs2_super *osb = NULL;
	char nodestr[8];

	mlog_entry("(0x%p)\n", sb);

	BUG_ON(!sb);
	osb = OCFS2_SB(sb);
	BUG_ON(!osb);

	ocfs2_shutdown_local_alloc(osb);

	ocfs2_truncate_log_shutdown(osb);

	/* disable any new recovery threads and wait for any currently
	 * running ones to exit. Do this before setting the vol_state. */
	mutex_lock(&osb->recovery_lock);
	osb->disable_recovery = 1;
	mutex_unlock(&osb->recovery_lock);
	wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));

	/* At this point, we know that no more recovery threads can be
	 * launched, so wait for any recovery completion work to
	 * complete. */
	flush_workqueue(ocfs2_wq);

	ocfs2_journal_shutdown(osb);

	ocfs2_sync_blockdev(sb);

	/* No dlm means we've failed during mount, so skip all the
	 * steps which depended on that to complete. */
	if (osb->dlm) {
		tmp = ocfs2_super_lock(osb, 1);
		if (tmp < 0) {
			mlog_errno(tmp);
			return;
		}
	}

	if (osb->slot_num != OCFS2_INVALID_SLOT)
		ocfs2_put_slot(osb);

	if (osb->dlm)
		ocfs2_super_unlock(osb, 1);

	ocfs2_release_system_inodes(osb);

	if (osb->dlm)
		ocfs2_dlm_shutdown(osb);

	debugfs_remove(osb->osb_debug_root);

	if (!mnt_err)
		ocfs2_stop_heartbeat(osb);

	atomic_set(&osb->vol_state, VOLUME_DISMOUNTED);

	if (ocfs2_mount_local(osb))
		snprintf(nodestr, sizeof(nodestr), "local");
	else
		snprintf(nodestr, sizeof(nodestr), "%d", osb->node_num);

	printk(KERN_INFO "ocfs2: Unmounting device (%s) on (node %s)\n",
	       osb->dev_str, nodestr);

	ocfs2_delete_osb(osb);
	kfree(osb);
	sb->s_dev = 0;
	sb->s_fs_info = NULL;
}

static int ocfs2_setup_osb_uuid(struct ocfs2_super *osb, const unsigned char *uuid,
				unsigned uuid_bytes)
{
	int i, ret;
	char *ptr;

	BUG_ON(uuid_bytes != OCFS2_VOL_UUID_LEN);

	osb->uuid_str = kzalloc(OCFS2_VOL_UUID_LEN * 2 + 1, GFP_KERNEL);
	if (osb->uuid_str == NULL)
		return -ENOMEM;

	for (i = 0, ptr = osb->uuid_str; i < OCFS2_VOL_UUID_LEN; i++) {
		/* print with null */
		ret = snprintf(ptr, 3, "%02X", uuid[i]);
		if (ret != 2) /* drop super cleans up */
			return -EINVAL;
		/* then only advance past the last char */
		ptr += 2;
	}

	return 0;
}

static int ocfs2_initialize_super(struct super_block *sb,
				  struct buffer_head *bh,
				  int sector_size)
{
	int status;
	int i, cbits, bbits;
	struct ocfs2_dinode *di = (struct ocfs2_dinode *)bh->b_data;
	struct inode *inode = NULL;
	struct ocfs2_journal *journal;
	__le32 uuid_net_key;
	struct ocfs2_super *osb;

	mlog_entry_void();

	osb = kzalloc(sizeof(struct ocfs2_super), GFP_KERNEL);
	if (!osb) {
		status = -ENOMEM;
		mlog_errno(status);
		goto bail;
	}

	sb->s_fs_info = osb;
	sb->s_op = &ocfs2_sops;
	sb->s_export_op = &ocfs2_export_ops;
	sb->s_time_gran = 1;
	sb->s_flags |= MS_NOATIME;
	/* this is needed to support O_LARGEFILE */
	cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits);
	bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
	sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits);

	osb->sb = sb;
	/* Save off for ocfs2_rw_direct */
	osb->s_sectsize_bits = blksize_bits(sector_size);
	BUG_ON(!osb->s_sectsize_bits);

	init_waitqueue_head(&osb->recovery_event);
	spin_lock_init(&osb->dc_task_lock);
	init_waitqueue_head(&osb->dc_event);
	osb->dc_work_sequence = 0;
	osb->dc_wake_sequence = 0;
	INIT_LIST_HEAD(&osb->blocked_lock_list);
	osb->blocked_lock_count = 0;
	spin_lock_init(&osb->osb_lock);

	atomic_set(&osb->alloc_stats.moves, 0);
	atomic_set(&osb->alloc_stats.local_data, 0);
	atomic_set(&osb->alloc_stats.bitmap_data, 0);
	atomic_set(&osb->alloc_stats.bg_allocs, 0);
	atomic_set(&osb->alloc_stats.bg_extends, 0);

	ocfs2_init_node_maps(osb);

	snprintf(osb->dev_str, sizeof(osb->dev_str), "%u,%u",
		 MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));

	mutex_init(&osb->recovery_lock);

	osb->disable_recovery = 0;
	osb->recovery_thread_task = NULL;

	init_waitqueue_head(&osb->checkpoint_event);
	atomic_set(&osb->needs_checkpoint, 0);

	osb->s_atime_quantum = OCFS2_DEFAULT_ATIME_QUANTUM;

	osb->node_num = O2NM_INVALID_NODE_NUM;
	osb->slot_num = OCFS2_INVALID_SLOT;

	osb->local_alloc_state = OCFS2_LA_UNUSED;
	osb->local_alloc_bh = NULL;

	ocfs2_setup_hb_callbacks(osb);

	init_waitqueue_head(&osb->osb_mount_event);

	osb->vol_label = kmalloc(OCFS2_MAX_VOL_LABEL_LEN, GFP_KERNEL);
	if (!osb->vol_label) {
		mlog(ML_ERROR, "unable to alloc vol label\n");
		status = -ENOMEM;
		goto bail;
	}

	osb->max_slots = le16_to_cpu(di->id2.i_super.s_max_slots);
	if (osb->max_slots > OCFS2_MAX_SLOTS || osb->max_slots == 0) {
		mlog(ML_ERROR, "Invalid number of node slots (%u)\n",
		     osb->max_slots);
		status = -EINVAL;
		goto bail;
	}
	mlog(0, "max_slots for this device: %u\n", osb->max_slots);

	init_waitqueue_head(&osb->osb_wipe_event);
	osb->osb_orphan_wipes = kcalloc(osb->max_slots,
					sizeof(*osb->osb_orphan_wipes),
					GFP_KERNEL);
	if (!osb->osb_orphan_wipes) {
		status = -ENOMEM;
		mlog_errno(status);
		goto bail;
	}

	osb->s_feature_compat =
		le32_to_cpu(OCFS2_RAW_SB(di)->s_feature_compat);
	osb->s_feature_ro_compat =
		le32_to_cpu(OCFS2_RAW_SB(di)->s_feature_ro_compat);
	osb->s_feature_incompat =
		le32_to_cpu(OCFS2_RAW_SB(di)->s_feature_incompat);

	if ((i = OCFS2_HAS_INCOMPAT_FEATURE(osb->sb, ~OCFS2_FEATURE_INCOMPAT_SUPP))) {
		mlog(ML_ERROR, "couldn't mount because of unsupported "
		     "optional features (%x).\n", i);
		status = -EINVAL;
		goto bail;
	}
	if (!(osb->sb->s_flags & MS_RDONLY) &&
	    (i = OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, ~OCFS2_FEATURE_RO_COMPAT_SUPP))) {
		mlog(ML_ERROR, "couldn't mount RDWR because of "
		     "unsupported optional features (%x).\n", i);
		status = -EINVAL;
		goto bail;
	}

	get_random_bytes(&osb->s_next_generation, sizeof(u32));

	/* FIXME
	 * This should be done in ocfs2_journal_init(), but unknown
	 * ordering issues will cause the filesystem to crash.
	 * If anyone wants to figure out what part of the code
	 * refers to osb->journal before ocfs2_journal_init() is run,
	 * be my guest.
	 */
	/* initialize our journal structure */

	journal = kzalloc(sizeof(struct ocfs2_journal), GFP_KERNEL);
	if (!journal) {
		mlog(ML_ERROR, "unable to alloc journal\n");
		status = -ENOMEM;
		goto bail;
	}
	osb->journal = journal;
	journal->j_osb = osb;

	atomic_set(&journal->j_num_trans, 0);
	init_rwsem(&journal->j_trans_barrier);
	init_waitqueue_head(&journal->j_checkpointed);
	spin_lock_init(&journal->j_lock);
	journal->j_trans_id = (unsigned long) 1;
	INIT_LIST_HEAD(&journal->j_la_cleanups);
	INIT_WORK(&journal->j_recovery_work, ocfs2_complete_recovery);
	journal->j_state = OCFS2_JOURNAL_FREE;

	/* get some pseudo constants for clustersize bits */
	osb->s_clustersize_bits =
		le32_to_cpu(di->id2.i_super.s_clustersize_bits);
	osb->s_clustersize = 1 << osb->s_clustersize_bits;
	mlog(0, "clusterbits=%d\n", osb->s_clustersize_bits);

	if (osb->s_clustersize < OCFS2_MIN_CLUSTERSIZE ||
	    osb->s_clustersize > OCFS2_MAX_CLUSTERSIZE) {
		mlog(ML_ERROR, "Volume has invalid cluster size (%d)\n",
		     osb->s_clustersize);
		status = -EINVAL;
		goto bail;
	}

	if (ocfs2_clusters_to_blocks(osb->sb, le32_to_cpu(di->i_clusters) - 1)
	    > (u32)~0UL) {
		mlog(ML_ERROR, "Volume might try to write to blocks beyond "
		     "what jbd can address in 32 bits.\n");
		status = -EINVAL;
		goto bail;
	}

	if (ocfs2_setup_osb_uuid(osb, di->id2.i_super.s_uuid,
				 sizeof(di->id2.i_super.s_uuid))) {
		mlog(ML_ERROR, "Out of memory trying to setup our uuid.\n");
		status = -ENOMEM;
		goto bail;
	}

	memcpy(&uuid_net_key, di->id2.i_super.s_uuid, sizeof(uuid_net_key));

	strncpy(osb->vol_label, di->id2.i_super.s_label, 63);
	osb->vol_label[63] = '\0';
	osb->root_blkno = le64_to_cpu(di->id2.i_super.s_root_blkno);
	osb->system_dir_blkno = le64_to_cpu(di->id2.i_super.s_system_dir_blkno);
	osb->first_cluster_group_blkno =
		le64_to_cpu(di->id2.i_super.s_first_cluster_group);
	osb->fs_generation = le32_to_cpu(di->i_fs_generation);
	mlog(0, "vol_label: %s\n", osb->vol_label);
	mlog(0, "uuid: %s\n", osb->uuid_str);
	mlog(0, "root_blkno=%llu, system_dir_blkno=%llu\n",
	     (unsigned long long)osb->root_blkno,
	     (unsigned long long)osb->system_dir_blkno);

	osb->osb_dlm_debug = ocfs2_new_dlm_debug();
	if (!osb->osb_dlm_debug) {
		status = -ENOMEM;
		mlog_errno(status);
		goto bail;
	}

	atomic_set(&osb->vol_state, VOLUME_INIT);

	/* load root, system_dir, and all global system inodes */
	status = ocfs2_init_global_system_inodes(osb);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}

	/*
	 * global bitmap
	 */
	inode = ocfs2_get_system_file_inode(osb, GLOBAL_BITMAP_SYSTEM_INODE,
					    OCFS2_INVALID_SLOT);
	if (!inode) {
		status = -EINVAL;
		mlog_errno(status);
		goto bail;
	}

	osb->bitmap_blkno = OCFS2_I(inode)->ip_blkno;
	iput(inode);

	osb->bitmap_cpg = ocfs2_group_bitmap_size(sb) * 8;

	status = ocfs2_init_slot_info(osb);
	if (status < 0) {
		mlog_errno(status);
		goto bail;
	}

bail:
	mlog_exit(status);
	return status;
}

/*
 * will return: -EAGAIN if it is ok to keep searching for superblocks
 *              -EINVAL if there is a bad superblock
 *              0 on success
 */
static int ocfs2_verify_volume(struct ocfs2_dinode *di,
			       struct buffer_head *bh,
			       u32 blksz)
{
	int status = -EAGAIN;

	mlog_entry_void();

	if (memcmp(di->i_signature, OCFS2_SUPER_BLOCK_SIGNATURE,
		   strlen(OCFS2_SUPER_BLOCK_SIGNATURE)) == 0) {
		status = -EINVAL;
		if ((1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits)) != blksz) {
			mlog(ML_ERROR, "found superblock with incorrect block "
			     "size: found %u, should be %u\n",
			     1 << le32_to_cpu(di->id2.i_super.s_blocksize_bits),
			       blksz);
		} else if (le16_to_cpu(di->id2.i_super.s_major_rev_level) !=
			   OCFS2_MAJOR_REV_LEVEL ||
			   le16_to_cpu(di->id2.i_super.s_minor_rev_level) !=
			   OCFS2_MINOR_REV_LEVEL) {
			mlog(ML_ERROR, "found superblock with bad version: "
			     "found %u.%u, should be %u.%u\n",
			     le16_to_cpu(di->id2.i_super.s_major_rev_level),
			     le16_to_cpu(di->id2.i_super.s_minor_rev_level),
			     OCFS2_MAJOR_REV_LEVEL,
			     OCFS2_MINOR_REV_LEVEL);
		} else if (bh->b_blocknr != le64_to_cpu(di->i_blkno)) {
			mlog(ML_ERROR, "bad block number on superblock: "
			     "found %llu, should be %llu\n",
			     (unsigned long long)le64_to_cpu(di->i_blkno),
			     (unsigned long long)bh->b_blocknr);
		} else if (le32_to_cpu(di->id2.i_super.s_clustersize_bits) < 12 ||
			    le32_to_cpu(di->id2.i_super.s_clustersize_bits) > 20) {
			mlog(ML_ERROR, "bad cluster size found: %u\n",
			     1 << le32_to_cpu(di->id2.i_super.s_clustersize_bits));
		} else if (!le64_to_cpu(di->id2.i_super.s_root_blkno)) {
			mlog(ML_ERROR, "bad root_blkno: 0\n");
		} else if (!le64_to_cpu(di->id2.i_super.s_system_dir_blkno)) {
			mlog(ML_ERROR, "bad system_dir_blkno: 0\n");
		} else if (le16_to_cpu(di->id2.i_super.s_max_slots) > OCFS2_MAX_SLOTS) {
			mlog(ML_ERROR,
			     "Superblock slots found greater than file system "
			     "maximum: found %u, max %u\n",
			     le16_to_cpu(di->id2.i_super.s_max_slots),
			     OCFS2_MAX_SLOTS);
		} else {
			/* found it! */
			status = 0;
		}
	}

	mlog_exit(status);
	return status;
}

static int ocfs2_check_volume(struct ocfs2_super *osb)
{
	int status;
	int dirty;
	int local;
	struct ocfs2_dinode *local_alloc = NULL; /* only used if we
						  * recover
						  * ourselves. */

	mlog_entry_void();

	/* Init our journal object. */
	status = ocfs2_journal_init(osb->journal, &dirty);
	if (status < 0) {
		mlog(ML_ERROR, "Could not initialize journal!\n");
		goto finally;
	}

	/* If the journal was unmounted cleanly then we don't want to
	 * recover anything. Otherwise, journal_load will do that
	 * dirty work for us :) */
	if (!dirty) {
		status = ocfs2_journal_wipe(osb->journal, 0);
		if (status < 0) {
			mlog_errno(status);
			goto finally;
		}
	} else {
		mlog(ML_NOTICE, "File system was not unmounted cleanly, "
		     "recovering volume.\n");
	}

	local = ocfs2_mount_local(osb);

	/* will play back anything left in the journal. */
	ocfs2_journal_load(osb->journal, local);

	if (dirty) {
		/* recover my local alloc if we didn't unmount cleanly. */
		status = ocfs2_begin_local_alloc_recovery(osb,
							  osb->slot_num,
							  &local_alloc);
		if (status < 0) {
			mlog_errno(status);
			goto finally;
		}
		/* we complete the recovery process after we've marked
		 * ourselves as mounted. */
	}

	mlog(0, "Journal loaded.\n");

	status = ocfs2_load_local_alloc(osb);
	if (status < 0) {
		mlog_errno(status);
		goto finally;
	}

	if (dirty) {
		/* Recovery will be completed after we've mounted the
		 * rest of the volume. */
		osb->dirty = 1;
		osb->local_alloc_copy = local_alloc;
		local_alloc = NULL;
	}

	/* go through each journal, trylock it and if you get the
	 * lock, and it's marked as dirty, set the bit in the recover
	 * map and launch a recovery thread for it. */
	status = ocfs2_mark_dead_nodes(osb);
	if (status < 0)
		mlog_errno(status);

finally:
	if (local_alloc)
		kfree(local_alloc);

	mlog_exit(status);
	return status;
}

/*
 * The routine gets called from dismount or close whenever a dismount on
 * volume is requested and the osb open count becomes 1.
 * It will remove the osb from the global list and also free up all the
 * initialized resources and fileobject.
 */
static void ocfs2_delete_osb(struct ocfs2_super *osb)
{
	mlog_entry_void();

	/* This function assumes that the caller has the main osb resource */

	if (osb->slot_info)
		ocfs2_free_slot_info(osb->slot_info);

	kfree(osb->osb_orphan_wipes);
	/* FIXME
	 * This belongs in journal shutdown, but because we have to
	 * allocate osb->journal at the start of ocfs2_initalize_osb(),
	 * we free it here.
	 */
	kfree(osb->journal);
	if (osb->local_alloc_copy)
		kfree(osb->local_alloc_copy);
	kfree(osb->uuid_str);
	ocfs2_put_dlm_debug(osb->osb_dlm_debug);
	memset(osb, 0, sizeof(struct ocfs2_super));

	mlog_exit_void();
}

/* Put OCFS2 into a readonly state, or (if the user specifies it),
 * panic(). We do not support continue-on-error operation. */
static void ocfs2_handle_error(struct super_block *sb)
{
	struct ocfs2_super *osb = OCFS2_SB(sb);

	if (osb->s_mount_opt & OCFS2_MOUNT_ERRORS_PANIC)
		panic("OCFS2: (device %s): panic forced after error\n",
		      sb->s_id);

	ocfs2_set_osb_flag(osb, OCFS2_OSB_ERROR_FS);

	if (sb->s_flags & MS_RDONLY &&
	    (ocfs2_is_soft_readonly(osb) ||
	     ocfs2_is_hard_readonly(osb)))
		return;

	printk(KERN_CRIT "File system is now read-only due to the potential "
	       "of on-disk corruption. Please run fsck.ocfs2 once the file "
	       "system is unmounted.\n");
	sb->s_flags |= MS_RDONLY;
	ocfs2_set_ro_flag(osb, 0);
}

static char error_buf[1024];

void __ocfs2_error(struct super_block *sb,
		   const char *function,
		   const char *fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	vsnprintf(error_buf, sizeof(error_buf), fmt, args);
	va_end(args);

	/* Not using mlog here because we want to show the actual
	 * function the error came from. */
	printk(KERN_CRIT "OCFS2: ERROR (device %s): %s: %s\n",
	       sb->s_id, function, error_buf);

	ocfs2_handle_error(sb);
}

/* Handle critical errors. This is intentionally more drastic than
 * ocfs2_handle_error, so we only use for things like journal errors,
 * etc. */
void __ocfs2_abort(struct super_block* sb,
		   const char *function,
		   const char *fmt, ...)
{
	va_list args;

	va_start(args, fmt);
	vsnprintf(error_buf, sizeof(error_buf), fmt, args);
	va_end(args);

	printk(KERN_CRIT "OCFS2: abort (device %s): %s: %s\n",
	       sb->s_id, function, error_buf);

	/* We don't have the cluster support yet to go straight to
	 * hard readonly in here. Until then, we want to keep
	 * ocfs2_abort() so that we can at least mark critical
	 * errors.
	 *
	 * TODO: This should abort the journal and alert other nodes
	 * that our slot needs recovery. */

	/* Force a panic(). This stinks, but it's better than letting
	 * things continue without having a proper hard readonly
	 * here. */
	OCFS2_SB(sb)->s_mount_opt |= OCFS2_MOUNT_ERRORS_PANIC;
	ocfs2_handle_error(sb);
}

module_init(ocfs2_init);
module_exit(ocfs2_exit);