summaryrefslogtreecommitdiffstats
path: root/fs/ext2/super.c
blob: 8ff53f8da3bcc414fdad44ac3bb76a88258e4d51 (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
/*
 *  linux/fs/ext2/super.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/inode.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 */

#include <linux/module.h>
#include <linux/string.h>
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/random.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/vfs.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include <linux/log2.h>
#include <linux/quotaops.h>
#include <linux/uaccess.h>
#include <linux/dax.h>
#include <linux/iversion.h>
#include "ext2.h"
#include "xattr.h"
#include "acl.h"

static void ext2_write_super(struct super_block *sb);
static int ext2_remount (struct super_block * sb, int * flags, char * data);
static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
static int ext2_sync_fs(struct super_block *sb, int wait);
static int ext2_freeze(struct super_block *sb);
static int ext2_unfreeze(struct super_block *sb);

void ext2_error(struct super_block *sb, const char *function,
		const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;

	if (!sb_rdonly(sb)) {
		spin_lock(&sbi->s_lock);
		sbi->s_mount_state |= EXT2_ERROR_FS;
		es->s_state |= cpu_to_le16(EXT2_ERROR_FS);
		spin_unlock(&sbi->s_lock);
		ext2_sync_super(sb, es, 1);
	}

	va_start(args, fmt);

	vaf.fmt = fmt;
	vaf.va = &args;

	printk(KERN_CRIT "EXT2-fs (%s): error: %s: %pV\n",
	       sb->s_id, function, &vaf);

	va_end(args);

	if (test_opt(sb, ERRORS_PANIC))
		panic("EXT2-fs: panic from previous error\n");
	if (test_opt(sb, ERRORS_RO)) {
		ext2_msg(sb, KERN_CRIT,
			     "error: remounting filesystem read-only");
		sb->s_flags |= SB_RDONLY;
	}
}

void ext2_msg(struct super_block *sb, const char *prefix,
		const char *fmt, ...)
{
	struct va_format vaf;
	va_list args;

	va_start(args, fmt);

	vaf.fmt = fmt;
	vaf.va = &args;

	printk("%sEXT2-fs (%s): %pV\n", prefix, sb->s_id, &vaf);

	va_end(args);
}

/*
 * This must be called with sbi->s_lock held.
 */
void ext2_update_dynamic_rev(struct super_block *sb)
{
	struct ext2_super_block *es = EXT2_SB(sb)->s_es;

	if (le32_to_cpu(es->s_rev_level) > EXT2_GOOD_OLD_REV)
		return;

	ext2_msg(sb, KERN_WARNING,
		     "warning: updating to rev %d because of "
		     "new feature flag, running e2fsck is recommended",
		     EXT2_DYNAMIC_REV);

	es->s_first_ino = cpu_to_le32(EXT2_GOOD_OLD_FIRST_INO);
	es->s_inode_size = cpu_to_le16(EXT2_GOOD_OLD_INODE_SIZE);
	es->s_rev_level = cpu_to_le32(EXT2_DYNAMIC_REV);
	/* leave es->s_feature_*compat flags alone */
	/* es->s_uuid will be set by e2fsck if empty */

	/*
	 * The rest of the superblock fields should be zero, and if not it
	 * means they are likely already in use, so leave them alone.  We
	 * can leave it up to e2fsck to clean up any inconsistencies there.
	 */
}

#ifdef CONFIG_QUOTA
static int ext2_quota_off(struct super_block *sb, int type);

static void ext2_quota_off_umount(struct super_block *sb)
{
	int type;

	for (type = 0; type < MAXQUOTAS; type++)
		ext2_quota_off(sb, type);
}
#else
static inline void ext2_quota_off_umount(struct super_block *sb)
{
}
#endif

static void ext2_put_super (struct super_block * sb)
{
	int db_count;
	int i;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	ext2_quota_off_umount(sb);

	if (sbi->s_ea_block_cache) {
		ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
		sbi->s_ea_block_cache = NULL;
	}
	if (!sb_rdonly(sb)) {
		struct ext2_super_block *es = sbi->s_es;

		spin_lock(&sbi->s_lock);
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		spin_unlock(&sbi->s_lock);
		ext2_sync_super(sb, es, 1);
	}
	db_count = sbi->s_gdb_count;
	for (i = 0; i < db_count; i++)
		if (sbi->s_group_desc[i])
			brelse (sbi->s_group_desc[i]);
	kfree(sbi->s_group_desc);
	kfree(sbi->s_debts);
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
	brelse (sbi->s_sbh);
	sb->s_fs_info = NULL;
	kfree(sbi->s_blockgroup_lock);
	fs_put_dax(sbi->s_daxdev);
	kfree(sbi);
}

static struct kmem_cache * ext2_inode_cachep;

static struct inode *ext2_alloc_inode(struct super_block *sb)
{
	struct ext2_inode_info *ei;
	ei = kmem_cache_alloc(ext2_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	ei->i_block_alloc_info = NULL;
	inode_set_iversion(&ei->vfs_inode, 1);
#ifdef CONFIG_QUOTA
	memset(&ei->i_dquot, 0, sizeof(ei->i_dquot));
#endif

	return &ei->vfs_inode;
}

static void ext2_i_callback(struct rcu_head *head)
{
	struct inode *inode = container_of(head, struct inode, i_rcu);
	kmem_cache_free(ext2_inode_cachep, EXT2_I(inode));
}

static void ext2_destroy_inode(struct inode *inode)
{
	call_rcu(&inode->i_rcu, ext2_i_callback);
}

static void init_once(void *foo)
{
	struct ext2_inode_info *ei = (struct ext2_inode_info *) foo;

	rwlock_init(&ei->i_meta_lock);
#ifdef CONFIG_EXT2_FS_XATTR
	init_rwsem(&ei->xattr_sem);
#endif
	mutex_init(&ei->truncate_mutex);
#ifdef CONFIG_FS_DAX
	init_rwsem(&ei->dax_sem);
#endif
	inode_init_once(&ei->vfs_inode);
}

static int __init init_inodecache(void)
{
	ext2_inode_cachep = kmem_cache_create_usercopy("ext2_inode_cache",
				sizeof(struct ext2_inode_info), 0,
				(SLAB_RECLAIM_ACCOUNT|SLAB_MEM_SPREAD|
					SLAB_ACCOUNT),
				offsetof(struct ext2_inode_info, i_data),
				sizeof_field(struct ext2_inode_info, i_data),
				init_once);
	if (ext2_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void destroy_inodecache(void)
{
	/*
	 * Make sure all delayed rcu free inodes are flushed before we
	 * destroy cache.
	 */
	rcu_barrier();
	kmem_cache_destroy(ext2_inode_cachep);
}

static int ext2_show_options(struct seq_file *seq, struct dentry *root)
{
	struct super_block *sb = root->d_sb;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;
	unsigned long def_mount_opts;

	spin_lock(&sbi->s_lock);
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);

	if (sbi->s_sb_block != 1)
		seq_printf(seq, ",sb=%lu", sbi->s_sb_block);
	if (test_opt(sb, MINIX_DF))
		seq_puts(seq, ",minixdf");
	if (test_opt(sb, GRPID))
		seq_puts(seq, ",grpid");
	if (!test_opt(sb, GRPID) && (def_mount_opts & EXT2_DEFM_BSDGROUPS))
		seq_puts(seq, ",nogrpid");
	if (!uid_eq(sbi->s_resuid, make_kuid(&init_user_ns, EXT2_DEF_RESUID)) ||
	    le16_to_cpu(es->s_def_resuid) != EXT2_DEF_RESUID) {
		seq_printf(seq, ",resuid=%u",
				from_kuid_munged(&init_user_ns, sbi->s_resuid));
	}
	if (!gid_eq(sbi->s_resgid, make_kgid(&init_user_ns, EXT2_DEF_RESGID)) ||
	    le16_to_cpu(es->s_def_resgid) != EXT2_DEF_RESGID) {
		seq_printf(seq, ",resgid=%u",
				from_kgid_munged(&init_user_ns, sbi->s_resgid));
	}
	if (test_opt(sb, ERRORS_RO)) {
		int def_errors = le16_to_cpu(es->s_errors);

		if (def_errors == EXT2_ERRORS_PANIC ||
		    def_errors == EXT2_ERRORS_CONTINUE) {
			seq_puts(seq, ",errors=remount-ro");
		}
	}
	if (test_opt(sb, ERRORS_CONT))
		seq_puts(seq, ",errors=continue");
	if (test_opt(sb, ERRORS_PANIC))
		seq_puts(seq, ",errors=panic");
	if (test_opt(sb, NO_UID32))
		seq_puts(seq, ",nouid32");
	if (test_opt(sb, DEBUG))
		seq_puts(seq, ",debug");
	if (test_opt(sb, OLDALLOC))
		seq_puts(seq, ",oldalloc");

#ifdef CONFIG_EXT2_FS_XATTR
	if (test_opt(sb, XATTR_USER))
		seq_puts(seq, ",user_xattr");
	if (!test_opt(sb, XATTR_USER) &&
	    (def_mount_opts & EXT2_DEFM_XATTR_USER)) {
		seq_puts(seq, ",nouser_xattr");
	}
#endif

#ifdef CONFIG_EXT2_FS_POSIX_ACL
	if (test_opt(sb, POSIX_ACL))
		seq_puts(seq, ",acl");
	if (!test_opt(sb, POSIX_ACL) && (def_mount_opts & EXT2_DEFM_ACL))
		seq_puts(seq, ",noacl");
#endif

	if (test_opt(sb, NOBH))
		seq_puts(seq, ",nobh");

#if defined(CONFIG_QUOTA)
	if (sbi->s_mount_opt & EXT2_MOUNT_USRQUOTA)
		seq_puts(seq, ",usrquota");

	if (sbi->s_mount_opt & EXT2_MOUNT_GRPQUOTA)
		seq_puts(seq, ",grpquota");
#endif

#ifdef CONFIG_FS_DAX
	if (sbi->s_mount_opt & EXT2_MOUNT_XIP)
		seq_puts(seq, ",xip");
	if (sbi->s_mount_opt & EXT2_MOUNT_DAX)
		seq_puts(seq, ",dax");
#endif

	if (!test_opt(sb, RESERVATION))
		seq_puts(seq, ",noreservation");

	spin_unlock(&sbi->s_lock);
	return 0;
}

#ifdef CONFIG_QUOTA
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off);
static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
static int ext2_quota_on(struct super_block *sb, int type, int format_id,
			 const struct path *path);
static struct dquot **ext2_get_dquots(struct inode *inode)
{
	return EXT2_I(inode)->i_dquot;
}

static const struct quotactl_ops ext2_quotactl_ops = {
	.quota_on	= ext2_quota_on,
	.quota_off	= ext2_quota_off,
	.quota_sync	= dquot_quota_sync,
	.get_state	= dquot_get_state,
	.set_info	= dquot_set_dqinfo,
	.get_dqblk	= dquot_get_dqblk,
	.set_dqblk	= dquot_set_dqblk,
	.get_nextdqblk	= dquot_get_next_dqblk,
};
#endif

static const struct super_operations ext2_sops = {
	.alloc_inode	= ext2_alloc_inode,
	.destroy_inode	= ext2_destroy_inode,
	.write_inode	= ext2_write_inode,
	.evict_inode	= ext2_evict_inode,
	.put_super	= ext2_put_super,
	.sync_fs	= ext2_sync_fs,
	.freeze_fs	= ext2_freeze,
	.unfreeze_fs	= ext2_unfreeze,
	.statfs		= ext2_statfs,
	.remount_fs	= ext2_remount,
	.show_options	= ext2_show_options,
#ifdef CONFIG_QUOTA
	.quota_read	= ext2_quota_read,
	.quota_write	= ext2_quota_write,
	.get_dquots	= ext2_get_dquots,
#endif
};

static struct inode *ext2_nfs_get_inode(struct super_block *sb,
		u64 ino, u32 generation)
{
	struct inode *inode;

	if (ino < EXT2_FIRST_INO(sb) && ino != EXT2_ROOT_INO)
		return ERR_PTR(-ESTALE);
	if (ino > le32_to_cpu(EXT2_SB(sb)->s_es->s_inodes_count))
		return ERR_PTR(-ESTALE);

	/*
	 * ext2_iget isn't quite right if the inode is currently unallocated!
	 * However ext2_iget currently does appropriate checks to handle stale
	 * inodes so everything is OK.
	 */
	inode = ext2_iget(sb, ino);
	if (IS_ERR(inode))
		return ERR_CAST(inode);
	if (generation && inode->i_generation != generation) {
		/* we didn't find the right inode.. */
		iput(inode);
		return ERR_PTR(-ESTALE);
	}
	return inode;
}

static struct dentry *ext2_fh_to_dentry(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
				    ext2_nfs_get_inode);
}

static struct dentry *ext2_fh_to_parent(struct super_block *sb, struct fid *fid,
		int fh_len, int fh_type)
{
	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
				    ext2_nfs_get_inode);
}

static const struct export_operations ext2_export_ops = {
	.fh_to_dentry = ext2_fh_to_dentry,
	.fh_to_parent = ext2_fh_to_parent,
	.get_parent = ext2_get_parent,
};

static unsigned long get_sb_block(void **data)
{
	unsigned long 	sb_block;
	char 		*options = (char *) *data;

	if (!options || strncmp(options, "sb=", 3) != 0)
		return 1;	/* Default location */
	options += 3;
	sb_block = simple_strtoul(options, &options, 0);
	if (*options && *options != ',') {
		printk("EXT2-fs: Invalid sb specification: %s\n",
		       (char *) *data);
		return 1;
	}
	if (*options == ',')
		options++;
	*data = (void *) options;
	return sb_block;
}

enum {
	Opt_bsd_df, Opt_minix_df, Opt_grpid, Opt_nogrpid,
	Opt_resgid, Opt_resuid, Opt_sb, Opt_err_cont, Opt_err_panic,
	Opt_err_ro, Opt_nouid32, Opt_nocheck, Opt_debug,
	Opt_oldalloc, Opt_orlov, Opt_nobh, Opt_user_xattr, Opt_nouser_xattr,
	Opt_acl, Opt_noacl, Opt_xip, Opt_dax, Opt_ignore, Opt_err, Opt_quota,
	Opt_usrquota, Opt_grpquota, Opt_reservation, Opt_noreservation
};

static const match_table_t tokens = {
	{Opt_bsd_df, "bsddf"},
	{Opt_minix_df, "minixdf"},
	{Opt_grpid, "grpid"},
	{Opt_grpid, "bsdgroups"},
	{Opt_nogrpid, "nogrpid"},
	{Opt_nogrpid, "sysvgroups"},
	{Opt_resgid, "resgid=%u"},
	{Opt_resuid, "resuid=%u"},
	{Opt_sb, "sb=%u"},
	{Opt_err_cont, "errors=continue"},
	{Opt_err_panic, "errors=panic"},
	{Opt_err_ro, "errors=remount-ro"},
	{Opt_nouid32, "nouid32"},
	{Opt_nocheck, "check=none"},
	{Opt_nocheck, "nocheck"},
	{Opt_debug, "debug"},
	{Opt_oldalloc, "oldalloc"},
	{Opt_orlov, "orlov"},
	{Opt_nobh, "nobh"},
	{Opt_user_xattr, "user_xattr"},
	{Opt_nouser_xattr, "nouser_xattr"},
	{Opt_acl, "acl"},
	{Opt_noacl, "noacl"},
	{Opt_xip, "xip"},
	{Opt_dax, "dax"},
	{Opt_grpquota, "grpquota"},
	{Opt_ignore, "noquota"},
	{Opt_quota, "quota"},
	{Opt_usrquota, "usrquota"},
	{Opt_reservation, "reservation"},
	{Opt_noreservation, "noreservation"},
	{Opt_err, NULL}
};

static int parse_options(char *options, struct super_block *sb,
			 struct ext2_mount_options *opts)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;
	kuid_t uid;
	kgid_t gid;

	if (!options)
		return 1;

	while ((p = strsep (&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_bsd_df:
			clear_opt (opts->s_mount_opt, MINIX_DF);
			break;
		case Opt_minix_df:
			set_opt (opts->s_mount_opt, MINIX_DF);
			break;
		case Opt_grpid:
			set_opt (opts->s_mount_opt, GRPID);
			break;
		case Opt_nogrpid:
			clear_opt (opts->s_mount_opt, GRPID);
			break;
		case Opt_resuid:
			if (match_int(&args[0], &option))
				return 0;
			uid = make_kuid(current_user_ns(), option);
			if (!uid_valid(uid)) {
				ext2_msg(sb, KERN_ERR, "Invalid uid value %d", option);
				return 0;

			}
			opts->s_resuid = uid;
			break;
		case Opt_resgid:
			if (match_int(&args[0], &option))
				return 0;
			gid = make_kgid(current_user_ns(), option);
			if (!gid_valid(gid)) {
				ext2_msg(sb, KERN_ERR, "Invalid gid value %d", option);
				return 0;
			}
			opts->s_resgid = gid;
			break;
		case Opt_sb:
			/* handled by get_sb_block() instead of here */
			/* *sb_block = match_int(&args[0]); */
			break;
		case Opt_err_panic:
			clear_opt (opts->s_mount_opt, ERRORS_CONT);
			clear_opt (opts->s_mount_opt, ERRORS_RO);
			set_opt (opts->s_mount_opt, ERRORS_PANIC);
			break;
		case Opt_err_ro:
			clear_opt (opts->s_mount_opt, ERRORS_CONT);
			clear_opt (opts->s_mount_opt, ERRORS_PANIC);
			set_opt (opts->s_mount_opt, ERRORS_RO);
			break;
		case Opt_err_cont:
			clear_opt (opts->s_mount_opt, ERRORS_RO);
			clear_opt (opts->s_mount_opt, ERRORS_PANIC);
			set_opt (opts->s_mount_opt, ERRORS_CONT);
			break;
		case Opt_nouid32:
			set_opt (opts->s_mount_opt, NO_UID32);
			break;
		case Opt_nocheck:
			ext2_msg(sb, KERN_WARNING,
				"Option nocheck/check=none is deprecated and"
				" will be removed in June 2020.");
			clear_opt (opts->s_mount_opt, CHECK);
			break;
		case Opt_debug:
			set_opt (opts->s_mount_opt, DEBUG);
			break;
		case Opt_oldalloc:
			set_opt (opts->s_mount_opt, OLDALLOC);
			break;
		case Opt_orlov:
			clear_opt (opts->s_mount_opt, OLDALLOC);
			break;
		case Opt_nobh:
			set_opt (opts->s_mount_opt, NOBH);
			break;
#ifdef CONFIG_EXT2_FS_XATTR
		case Opt_user_xattr:
			set_opt (opts->s_mount_opt, XATTR_USER);
			break;
		case Opt_nouser_xattr:
			clear_opt (opts->s_mount_opt, XATTR_USER);
			break;
#else
		case Opt_user_xattr:
		case Opt_nouser_xattr:
			ext2_msg(sb, KERN_INFO, "(no)user_xattr options"
				"not supported");
			break;
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
		case Opt_acl:
			set_opt(opts->s_mount_opt, POSIX_ACL);
			break;
		case Opt_noacl:
			clear_opt(opts->s_mount_opt, POSIX_ACL);
			break;
#else
		case Opt_acl:
		case Opt_noacl:
			ext2_msg(sb, KERN_INFO,
				"(no)acl options not supported");
			break;
#endif
		case Opt_xip:
			ext2_msg(sb, KERN_INFO, "use dax instead of xip");
			set_opt(opts->s_mount_opt, XIP);
			/* Fall through */
		case Opt_dax:
#ifdef CONFIG_FS_DAX
			ext2_msg(sb, KERN_WARNING,
		"DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
			set_opt(opts->s_mount_opt, DAX);
#else
			ext2_msg(sb, KERN_INFO, "dax option not supported");
#endif
			break;

#if defined(CONFIG_QUOTA)
		case Opt_quota:
		case Opt_usrquota:
			set_opt(opts->s_mount_opt, USRQUOTA);
			break;

		case Opt_grpquota:
			set_opt(opts->s_mount_opt, GRPQUOTA);
			break;
#else
		case Opt_quota:
		case Opt_usrquota:
		case Opt_grpquota:
			ext2_msg(sb, KERN_INFO,
				"quota operations not supported");
			break;
#endif

		case Opt_reservation:
			set_opt(opts->s_mount_opt, RESERVATION);
			ext2_msg(sb, KERN_INFO, "reservations ON");
			break;
		case Opt_noreservation:
			clear_opt(opts->s_mount_opt, RESERVATION);
			ext2_msg(sb, KERN_INFO, "reservations OFF");
			break;
		case Opt_ignore:
			break;
		default:
			return 0;
		}
	}
	return 1;
}

static int ext2_setup_super (struct super_block * sb,
			      struct ext2_super_block * es,
			      int read_only)
{
	int res = 0;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	if (le32_to_cpu(es->s_rev_level) > EXT2_MAX_SUPP_REV) {
		ext2_msg(sb, KERN_ERR,
			"error: revision level too high, "
			"forcing read-only mode");
		res = SB_RDONLY;
	}
	if (read_only)
		return res;
	if (!(sbi->s_mount_state & EXT2_VALID_FS))
		ext2_msg(sb, KERN_WARNING,
			"warning: mounting unchecked fs, "
			"running e2fsck is recommended");
	else if ((sbi->s_mount_state & EXT2_ERROR_FS))
		ext2_msg(sb, KERN_WARNING,
			"warning: mounting fs with errors, "
			"running e2fsck is recommended");
	else if ((__s16) le16_to_cpu(es->s_max_mnt_count) >= 0 &&
		 le16_to_cpu(es->s_mnt_count) >=
		 (unsigned short) (__s16) le16_to_cpu(es->s_max_mnt_count))
		ext2_msg(sb, KERN_WARNING,
			"warning: maximal mount count reached, "
			"running e2fsck is recommended");
	else if (le32_to_cpu(es->s_checkinterval) &&
		(le32_to_cpu(es->s_lastcheck) +
			le32_to_cpu(es->s_checkinterval) <= get_seconds()))
		ext2_msg(sb, KERN_WARNING,
			"warning: checktime reached, "
			"running e2fsck is recommended");
	if (!le16_to_cpu(es->s_max_mnt_count))
		es->s_max_mnt_count = cpu_to_le16(EXT2_DFL_MAX_MNT_COUNT);
	le16_add_cpu(&es->s_mnt_count, 1);
	if (test_opt (sb, DEBUG))
		ext2_msg(sb, KERN_INFO, "%s, %s, bs=%lu, fs=%lu, gc=%lu, "
			"bpg=%lu, ipg=%lu, mo=%04lx]",
			EXT2FS_VERSION, EXT2FS_DATE, sb->s_blocksize,
			sbi->s_frag_size,
			sbi->s_groups_count,
			EXT2_BLOCKS_PER_GROUP(sb),
			EXT2_INODES_PER_GROUP(sb),
			sbi->s_mount_opt);
	return res;
}

static int ext2_check_descriptors(struct super_block *sb)
{
	int i;
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	ext2_debug ("Checking group descriptors");

	for (i = 0; i < sbi->s_groups_count; i++) {
		struct ext2_group_desc *gdp = ext2_get_group_desc(sb, i, NULL);
		ext2_fsblk_t first_block = ext2_group_first_block_no(sb, i);
		ext2_fsblk_t last_block;

		if (i == sbi->s_groups_count - 1)
			last_block = le32_to_cpu(sbi->s_es->s_blocks_count) - 1;
		else
			last_block = first_block +
				(EXT2_BLOCKS_PER_GROUP(sb) - 1);

		if (le32_to_cpu(gdp->bg_block_bitmap) < first_block ||
		    le32_to_cpu(gdp->bg_block_bitmap) > last_block)
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Block bitmap for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_block_bitmap));
			return 0;
		}
		if (le32_to_cpu(gdp->bg_inode_bitmap) < first_block ||
		    le32_to_cpu(gdp->bg_inode_bitmap) > last_block)
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Inode bitmap for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_bitmap));
			return 0;
		}
		if (le32_to_cpu(gdp->bg_inode_table) < first_block ||
		    le32_to_cpu(gdp->bg_inode_table) + sbi->s_itb_per_group - 1 >
		    last_block)
		{
			ext2_error (sb, "ext2_check_descriptors",
				    "Inode table for group %d"
				    " not in group (block %lu)!",
				    i, (unsigned long) le32_to_cpu(gdp->bg_inode_table));
			return 0;
		}
	}
	return 1;
}

/*
 * Maximal file size.  There is a direct, and {,double-,triple-}indirect
 * block limit, and also a limit of (2^32 - 1) 512-byte sectors in i_blocks.
 * We need to be 1 filesystem block less than the 2^32 sector limit.
 */
static loff_t ext2_max_size(int bits)
{
	loff_t res = EXT2_NDIR_BLOCKS;
	int meta_blocks;
	loff_t upper_limit;

	/* This is calculated to be the largest file size for a
	 * dense, file such that the total number of
	 * sectors in the file, including data and all indirect blocks,
	 * does not exceed 2^32 -1
	 * __u32 i_blocks representing the total number of
	 * 512 bytes blocks of the file
	 */
	upper_limit = (1LL << 32) - 1;

	/* total blocks in file system block size */
	upper_limit >>= (bits - 9);


	/* indirect blocks */
	meta_blocks = 1;
	/* double indirect blocks */
	meta_blocks += 1 + (1LL << (bits-2));
	/* tripple indirect blocks */
	meta_blocks += 1 + (1LL << (bits-2)) + (1LL << (2*(bits-2)));

	upper_limit -= meta_blocks;
	upper_limit <<= bits;

	res += 1LL << (bits-2);
	res += 1LL << (2*(bits-2));
	res += 1LL << (3*(bits-2));
	res <<= bits;
	if (res > upper_limit)
		res = upper_limit;

	if (res > MAX_LFS_FILESIZE)
		res = MAX_LFS_FILESIZE;

	return res;
}

static unsigned long descriptor_loc(struct super_block *sb,
				    unsigned long logic_sb_block,
				    int nr)
{
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	unsigned long bg, first_meta_bg;
	int has_super = 0;
	
	first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);

	if (!EXT2_HAS_INCOMPAT_FEATURE(sb, EXT2_FEATURE_INCOMPAT_META_BG) ||
	    nr < first_meta_bg)
		return (logic_sb_block + nr + 1);
	bg = sbi->s_desc_per_block * nr;
	if (ext2_bg_has_super(sb, bg))
		has_super = 1;

	return ext2_group_first_block_no(sb, bg) + has_super;
}

static int ext2_fill_super(struct super_block *sb, void *data, int silent)
{
	struct dax_device *dax_dev = fs_dax_get_by_bdev(sb->s_bdev);
	struct buffer_head * bh;
	struct ext2_sb_info * sbi;
	struct ext2_super_block * es;
	struct inode *root;
	unsigned long block;
	unsigned long sb_block = get_sb_block(&data);
	unsigned long logic_sb_block;
	unsigned long offset = 0;
	unsigned long def_mount_opts;
	long ret = -ENOMEM;
	int blocksize = BLOCK_SIZE;
	int db_count;
	int i, j;
	__le32 features;
	int err;
	struct ext2_mount_options opts;

	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		goto failed;

	sbi->s_blockgroup_lock =
		kzalloc(sizeof(struct blockgroup_lock), GFP_KERNEL);
	if (!sbi->s_blockgroup_lock) {
		kfree(sbi);
		goto failed;
	}
	sb->s_fs_info = sbi;
	sbi->s_sb_block = sb_block;
	sbi->s_daxdev = dax_dev;

	spin_lock_init(&sbi->s_lock);
	ret = -EINVAL;

	/*
	 * See what the current blocksize for the device is, and
	 * use that as the blocksize.  Otherwise (or if the blocksize
	 * is smaller than the default) use the default.
	 * This is important for devices that have a hardware
	 * sectorsize that is larger than the default.
	 */
	blocksize = sb_min_blocksize(sb, BLOCK_SIZE);
	if (!blocksize) {
		ext2_msg(sb, KERN_ERR, "error: unable to set blocksize");
		goto failed_sbi;
	}

	/*
	 * If the superblock doesn't start on a hardware sector boundary,
	 * calculate the offset.  
	 */
	if (blocksize != BLOCK_SIZE) {
		logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
		offset = (sb_block*BLOCK_SIZE) % blocksize;
	} else {
		logic_sb_block = sb_block;
	}

	if (!(bh = sb_bread(sb, logic_sb_block))) {
		ext2_msg(sb, KERN_ERR, "error: unable to read superblock");
		goto failed_sbi;
	}
	/*
	 * Note: s_es must be initialized as soon as possible because
	 *       some ext2 macro-instructions depend on its value
	 */
	es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
	sbi->s_es = es;
	sb->s_magic = le16_to_cpu(es->s_magic);

	if (sb->s_magic != EXT2_SUPER_MAGIC)
		goto cantfind_ext2;

	/* Set defaults before we parse the mount options */
	def_mount_opts = le32_to_cpu(es->s_default_mount_opts);
	if (def_mount_opts & EXT2_DEFM_DEBUG)
		set_opt(opts.s_mount_opt, DEBUG);
	if (def_mount_opts & EXT2_DEFM_BSDGROUPS)
		set_opt(opts.s_mount_opt, GRPID);
	if (def_mount_opts & EXT2_DEFM_UID16)
		set_opt(opts.s_mount_opt, NO_UID32);
#ifdef CONFIG_EXT2_FS_XATTR
	if (def_mount_opts & EXT2_DEFM_XATTR_USER)
		set_opt(opts.s_mount_opt, XATTR_USER);
#endif
#ifdef CONFIG_EXT2_FS_POSIX_ACL
	if (def_mount_opts & EXT2_DEFM_ACL)
		set_opt(opts.s_mount_opt, POSIX_ACL);
#endif
	
	if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_PANIC)
		set_opt(opts.s_mount_opt, ERRORS_PANIC);
	else if (le16_to_cpu(sbi->s_es->s_errors) == EXT2_ERRORS_CONTINUE)
		set_opt(opts.s_mount_opt, ERRORS_CONT);
	else
		set_opt(opts.s_mount_opt, ERRORS_RO);

	opts.s_resuid = make_kuid(&init_user_ns, le16_to_cpu(es->s_def_resuid));
	opts.s_resgid = make_kgid(&init_user_ns, le16_to_cpu(es->s_def_resgid));
	
	set_opt(opts.s_mount_opt, RESERVATION);

	if (!parse_options((char *) data, sb, &opts))
		goto failed_mount;

	sbi->s_mount_opt = opts.s_mount_opt;
	sbi->s_resuid = opts.s_resuid;
	sbi->s_resgid = opts.s_resgid;

	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
		((EXT2_SB(sb)->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ?
		 SB_POSIXACL : 0);
	sb->s_iflags |= SB_I_CGROUPWB;

	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV &&
	    (EXT2_HAS_COMPAT_FEATURE(sb, ~0U) ||
	     EXT2_HAS_RO_COMPAT_FEATURE(sb, ~0U) ||
	     EXT2_HAS_INCOMPAT_FEATURE(sb, ~0U)))
		ext2_msg(sb, KERN_WARNING,
			"warning: feature flags set on rev 0 fs, "
			"running e2fsck is recommended");
	/*
	 * Check feature flags regardless of the revision level, since we
	 * previously didn't change the revision level when setting the flags,
	 * so there is a chance incompat flags are set on a rev 0 filesystem.
	 */
	features = EXT2_HAS_INCOMPAT_FEATURE(sb, ~EXT2_FEATURE_INCOMPAT_SUPP);
	if (features) {
		ext2_msg(sb, KERN_ERR,	"error: couldn't mount because of "
		       "unsupported optional features (%x)",
			le32_to_cpu(features));
		goto failed_mount;
	}
	if (!sb_rdonly(sb) && (features = EXT2_HAS_RO_COMPAT_FEATURE(sb, ~EXT2_FEATURE_RO_COMPAT_SUPP))){
		ext2_msg(sb, KERN_ERR, "error: couldn't mount RDWR because of "
		       "unsupported optional features (%x)",
		       le32_to_cpu(features));
		goto failed_mount;
	}

	blocksize = BLOCK_SIZE << le32_to_cpu(sbi->s_es->s_log_block_size);

	if (sbi->s_mount_opt & EXT2_MOUNT_DAX) {
		if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
			ext2_msg(sb, KERN_ERR,
				"DAX unsupported by block device. Turning off DAX.");
			sbi->s_mount_opt &= ~EXT2_MOUNT_DAX;
		}
	}

	/* If the blocksize doesn't match, re-read the thing.. */
	if (sb->s_blocksize != blocksize) {
		brelse(bh);

		if (!sb_set_blocksize(sb, blocksize)) {
			ext2_msg(sb, KERN_ERR,
				"error: bad blocksize %d", blocksize);
			goto failed_sbi;
		}

		logic_sb_block = (sb_block*BLOCK_SIZE) / blocksize;
		offset = (sb_block*BLOCK_SIZE) % blocksize;
		bh = sb_bread(sb, logic_sb_block);
		if(!bh) {
			ext2_msg(sb, KERN_ERR, "error: couldn't read"
				"superblock on 2nd try");
			goto failed_sbi;
		}
		es = (struct ext2_super_block *) (((char *)bh->b_data) + offset);
		sbi->s_es = es;
		if (es->s_magic != cpu_to_le16(EXT2_SUPER_MAGIC)) {
			ext2_msg(sb, KERN_ERR, "error: magic mismatch");
			goto failed_mount;
		}
	}

	sb->s_maxbytes = ext2_max_size(sb->s_blocksize_bits);
	sb->s_max_links = EXT2_LINK_MAX;

	if (le32_to_cpu(es->s_rev_level) == EXT2_GOOD_OLD_REV) {
		sbi->s_inode_size = EXT2_GOOD_OLD_INODE_SIZE;
		sbi->s_first_ino = EXT2_GOOD_OLD_FIRST_INO;
	} else {
		sbi->s_inode_size = le16_to_cpu(es->s_inode_size);
		sbi->s_first_ino = le32_to_cpu(es->s_first_ino);
		if ((sbi->s_inode_size < EXT2_GOOD_OLD_INODE_SIZE) ||
		    !is_power_of_2(sbi->s_inode_size) ||
		    (sbi->s_inode_size > blocksize)) {
			ext2_msg(sb, KERN_ERR,
				"error: unsupported inode size: %d",
				sbi->s_inode_size);
			goto failed_mount;
		}
	}

	sbi->s_frag_size = EXT2_MIN_FRAG_SIZE <<
				   le32_to_cpu(es->s_log_frag_size);
	if (sbi->s_frag_size == 0)
		goto cantfind_ext2;
	sbi->s_frags_per_block = sb->s_blocksize / sbi->s_frag_size;

	sbi->s_blocks_per_group = le32_to_cpu(es->s_blocks_per_group);
	sbi->s_frags_per_group = le32_to_cpu(es->s_frags_per_group);
	sbi->s_inodes_per_group = le32_to_cpu(es->s_inodes_per_group);

	if (EXT2_INODE_SIZE(sb) == 0)
		goto cantfind_ext2;
	sbi->s_inodes_per_block = sb->s_blocksize / EXT2_INODE_SIZE(sb);
	if (sbi->s_inodes_per_block == 0 || sbi->s_inodes_per_group == 0)
		goto cantfind_ext2;
	sbi->s_itb_per_group = sbi->s_inodes_per_group /
					sbi->s_inodes_per_block;
	sbi->s_desc_per_block = sb->s_blocksize /
					sizeof (struct ext2_group_desc);
	sbi->s_sbh = bh;
	sbi->s_mount_state = le16_to_cpu(es->s_state);
	sbi->s_addr_per_block_bits =
		ilog2 (EXT2_ADDR_PER_BLOCK(sb));
	sbi->s_desc_per_block_bits =
		ilog2 (EXT2_DESC_PER_BLOCK(sb));

	if (sb->s_magic != EXT2_SUPER_MAGIC)
		goto cantfind_ext2;

	if (sb->s_blocksize != bh->b_size) {
		if (!silent)
			ext2_msg(sb, KERN_ERR, "error: unsupported blocksize");
		goto failed_mount;
	}

	if (sb->s_blocksize != sbi->s_frag_size) {
		ext2_msg(sb, KERN_ERR,
			"error: fragsize %lu != blocksize %lu"
			"(not supported yet)",
			sbi->s_frag_size, sb->s_blocksize);
		goto failed_mount;
	}

	if (sbi->s_blocks_per_group > sb->s_blocksize * 8) {
		ext2_msg(sb, KERN_ERR,
			"error: #blocks per group too big: %lu",
			sbi->s_blocks_per_group);
		goto failed_mount;
	}
	if (sbi->s_frags_per_group > sb->s_blocksize * 8) {
		ext2_msg(sb, KERN_ERR,
			"error: #fragments per group too big: %lu",
			sbi->s_frags_per_group);
		goto failed_mount;
	}
	if (sbi->s_inodes_per_group > sb->s_blocksize * 8) {
		ext2_msg(sb, KERN_ERR,
			"error: #inodes per group too big: %lu",
			sbi->s_inodes_per_group);
		goto failed_mount;
	}

	if (EXT2_BLOCKS_PER_GROUP(sb) == 0)
		goto cantfind_ext2;
 	sbi->s_groups_count = ((le32_to_cpu(es->s_blocks_count) -
 				le32_to_cpu(es->s_first_data_block) - 1)
 					/ EXT2_BLOCKS_PER_GROUP(sb)) + 1;
	db_count = (sbi->s_groups_count + EXT2_DESC_PER_BLOCK(sb) - 1) /
		   EXT2_DESC_PER_BLOCK(sb);
	sbi->s_group_desc = kmalloc_array (db_count,
					   sizeof(struct buffer_head *),
					   GFP_KERNEL);
	if (sbi->s_group_desc == NULL) {
		ext2_msg(sb, KERN_ERR, "error: not enough memory");
		goto failed_mount;
	}
	bgl_lock_init(sbi->s_blockgroup_lock);
	sbi->s_debts = kcalloc(sbi->s_groups_count, sizeof(*sbi->s_debts), GFP_KERNEL);
	if (!sbi->s_debts) {
		ext2_msg(sb, KERN_ERR, "error: not enough memory");
		goto failed_mount_group_desc;
	}
	for (i = 0; i < db_count; i++) {
		block = descriptor_loc(sb, logic_sb_block, i);
		sbi->s_group_desc[i] = sb_bread(sb, block);
		if (!sbi->s_group_desc[i]) {
			for (j = 0; j < i; j++)
				brelse (sbi->s_group_desc[j]);
			ext2_msg(sb, KERN_ERR,
				"error: unable to read group descriptors");
			goto failed_mount_group_desc;
		}
	}
	if (!ext2_check_descriptors (sb)) {
		ext2_msg(sb, KERN_ERR, "group descriptors corrupted");
		goto failed_mount2;
	}
	sbi->s_gdb_count = db_count;
	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
	spin_lock_init(&sbi->s_next_gen_lock);

	/* per fileystem reservation list head & lock */
	spin_lock_init(&sbi->s_rsv_window_lock);
	sbi->s_rsv_window_root = RB_ROOT;
	/*
	 * Add a single, static dummy reservation to the start of the
	 * reservation window list --- it gives us a placeholder for
	 * append-at-start-of-list which makes the allocation logic
	 * _much_ simpler.
	 */
	sbi->s_rsv_window_head.rsv_start = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_end = EXT2_RESERVE_WINDOW_NOT_ALLOCATED;
	sbi->s_rsv_window_head.rsv_alloc_hit = 0;
	sbi->s_rsv_window_head.rsv_goal_size = 0;
	ext2_rsv_window_add(sb, &sbi->s_rsv_window_head);

	err = percpu_counter_init(&sbi->s_freeblocks_counter,
				ext2_count_free_blocks(sb), GFP_KERNEL);
	if (!err) {
		err = percpu_counter_init(&sbi->s_freeinodes_counter,
				ext2_count_free_inodes(sb), GFP_KERNEL);
	}
	if (!err) {
		err = percpu_counter_init(&sbi->s_dirs_counter,
				ext2_count_dirs(sb), GFP_KERNEL);
	}
	if (err) {
		ext2_msg(sb, KERN_ERR, "error: insufficient memory");
		goto failed_mount3;
	}

#ifdef CONFIG_EXT2_FS_XATTR
	sbi->s_ea_block_cache = ext2_xattr_create_cache();
	if (!sbi->s_ea_block_cache) {
		ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache");
		goto failed_mount3;
	}
#endif
	/*
	 * set up enough so that it can read an inode
	 */
	sb->s_op = &ext2_sops;
	sb->s_export_op = &ext2_export_ops;
	sb->s_xattr = ext2_xattr_handlers;

#ifdef CONFIG_QUOTA
	sb->dq_op = &dquot_operations;
	sb->s_qcop = &ext2_quotactl_ops;
	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
#endif

	root = ext2_iget(sb, EXT2_ROOT_INO);
	if (IS_ERR(root)) {
		ret = PTR_ERR(root);
		goto failed_mount3;
	}
	if (!S_ISDIR(root->i_mode) || !root->i_blocks || !root->i_size) {
		iput(root);
		ext2_msg(sb, KERN_ERR, "error: corrupt root inode, run e2fsck");
		goto failed_mount3;
	}

	sb->s_root = d_make_root(root);
	if (!sb->s_root) {
		ext2_msg(sb, KERN_ERR, "error: get root inode failed");
		ret = -ENOMEM;
		goto failed_mount3;
	}
	if (EXT2_HAS_COMPAT_FEATURE(sb, EXT3_FEATURE_COMPAT_HAS_JOURNAL))
		ext2_msg(sb, KERN_WARNING,
			"warning: mounting ext3 filesystem as ext2");
	if (ext2_setup_super (sb, es, sb_rdonly(sb)))
		sb->s_flags |= SB_RDONLY;
	ext2_write_super(sb);
	return 0;

cantfind_ext2:
	if (!silent)
		ext2_msg(sb, KERN_ERR,
			"error: can't find an ext2 filesystem on dev %s.",
			sb->s_id);
	goto failed_mount;
failed_mount3:
	if (sbi->s_ea_block_cache)
		ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
	percpu_counter_destroy(&sbi->s_freeblocks_counter);
	percpu_counter_destroy(&sbi->s_freeinodes_counter);
	percpu_counter_destroy(&sbi->s_dirs_counter);
failed_mount2:
	for (i = 0; i < db_count; i++)
		brelse(sbi->s_group_desc[i]);
failed_mount_group_desc:
	kfree(sbi->s_group_desc);
	kfree(sbi->s_debts);
failed_mount:
	brelse(bh);
failed_sbi:
	sb->s_fs_info = NULL;
	kfree(sbi->s_blockgroup_lock);
	kfree(sbi);
failed:
	fs_put_dax(dax_dev);
	return ret;
}

static void ext2_clear_super_error(struct super_block *sb)
{
	struct buffer_head *sbh = EXT2_SB(sb)->s_sbh;

	if (buffer_write_io_error(sbh)) {
		/*
		 * Oh, dear.  A previous attempt to write the
		 * superblock failed.  This could happen because the
		 * USB device was yanked out.  Or it could happen to
		 * be a transient write error and maybe the block will
		 * be remapped.  Nothing we can do but to retry the
		 * write and hope for the best.
		 */
		ext2_msg(sb, KERN_ERR,
		       "previous I/O error to superblock detected");
		clear_buffer_write_io_error(sbh);
		set_buffer_uptodate(sbh);
	}
}

void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
		     int wait)
{
	ext2_clear_super_error(sb);
	spin_lock(&EXT2_SB(sb)->s_lock);
	es->s_free_blocks_count = cpu_to_le32(ext2_count_free_blocks(sb));
	es->s_free_inodes_count = cpu_to_le32(ext2_count_free_inodes(sb));
	es->s_wtime = cpu_to_le32(get_seconds());
	/* unlock before we do IO */
	spin_unlock(&EXT2_SB(sb)->s_lock);
	mark_buffer_dirty(EXT2_SB(sb)->s_sbh);
	if (wait)
		sync_dirty_buffer(EXT2_SB(sb)->s_sbh);
}

/*
 * In the second extended file system, it is not necessary to
 * write the super block since we use a mapping of the
 * disk super block in a buffer.
 *
 * However, this function is still used to set the fs valid
 * flags to 0.  We need to set this flag to 0 since the fs
 * may have been checked while mounted and e2fsck may have
 * set s_state to EXT2_VALID_FS after some corrections.
 */
static int ext2_sync_fs(struct super_block *sb, int wait)
{
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = EXT2_SB(sb)->s_es;

	/*
	 * Write quota structures to quota file, sync_blockdev() will write
	 * them to disk later
	 */
	dquot_writeback_dquots(sb, -1);

	spin_lock(&sbi->s_lock);
	if (es->s_state & cpu_to_le16(EXT2_VALID_FS)) {
		ext2_debug("setting valid to 0\n");
		es->s_state &= cpu_to_le16(~EXT2_VALID_FS);
	}
	spin_unlock(&sbi->s_lock);
	ext2_sync_super(sb, es, wait);
	return 0;
}

static int ext2_freeze(struct super_block *sb)
{
	struct ext2_sb_info *sbi = EXT2_SB(sb);

	/*
	 * Open but unlinked files present? Keep EXT2_VALID_FS flag cleared
	 * because we have unattached inodes and thus filesystem is not fully
	 * consistent.
	 */
	if (atomic_long_read(&sb->s_remove_count)) {
		ext2_sync_fs(sb, 1);
		return 0;
	}
	/* Set EXT2_FS_VALID flag */
	spin_lock(&sbi->s_lock);
	sbi->s_es->s_state = cpu_to_le16(sbi->s_mount_state);
	spin_unlock(&sbi->s_lock);
	ext2_sync_super(sb, sbi->s_es, 1);

	return 0;
}

static int ext2_unfreeze(struct super_block *sb)
{
	/* Just write sb to clear EXT2_VALID_FS flag */
	ext2_write_super(sb);

	return 0;
}

static void ext2_write_super(struct super_block *sb)
{
	if (!sb_rdonly(sb))
		ext2_sync_fs(sb, 1);
}

static int ext2_remount (struct super_block * sb, int * flags, char * data)
{
	struct ext2_sb_info * sbi = EXT2_SB(sb);
	struct ext2_super_block * es;
	struct ext2_mount_options new_opts;
	int err;

	sync_filesystem(sb);

	spin_lock(&sbi->s_lock);
	new_opts.s_mount_opt = sbi->s_mount_opt;
	new_opts.s_resuid = sbi->s_resuid;
	new_opts.s_resgid = sbi->s_resgid;
	spin_unlock(&sbi->s_lock);

	if (!parse_options(data, sb, &new_opts))
		return -EINVAL;

	spin_lock(&sbi->s_lock);
	es = sbi->s_es;
	if ((sbi->s_mount_opt ^ new_opts.s_mount_opt) & EXT2_MOUNT_DAX) {
		ext2_msg(sb, KERN_WARNING, "warning: refusing change of "
			 "dax flag with busy inodes while remounting");
		new_opts.s_mount_opt ^= EXT2_MOUNT_DAX;
	}
	if ((bool)(*flags & SB_RDONLY) == sb_rdonly(sb))
		goto out_set;
	if (*flags & SB_RDONLY) {
		if (le16_to_cpu(es->s_state) & EXT2_VALID_FS ||
		    !(sbi->s_mount_state & EXT2_VALID_FS))
			goto out_set;

		/*
		 * OK, we are remounting a valid rw partition rdonly, so set
		 * the rdonly flag and then mark the partition as valid again.
		 */
		es->s_state = cpu_to_le16(sbi->s_mount_state);
		es->s_mtime = cpu_to_le32(get_seconds());
		spin_unlock(&sbi->s_lock);

		err = dquot_suspend(sb, -1);
		if (err < 0)
			return err;

		ext2_sync_super(sb, es, 1);
	} else {
		__le32 ret = EXT2_HAS_RO_COMPAT_FEATURE(sb,
					       ~EXT2_FEATURE_RO_COMPAT_SUPP);
		if (ret) {
			spin_unlock(&sbi->s_lock);
			ext2_msg(sb, KERN_WARNING,
				"warning: couldn't remount RDWR because of "
				"unsupported optional features (%x).",
				le32_to_cpu(ret));
			return -EROFS;
		}
		/*
		 * Mounting a RDONLY partition read-write, so reread and
		 * store the current valid flag.  (It may have been changed
		 * by e2fsck since we originally mounted the partition.)
		 */
		sbi->s_mount_state = le16_to_cpu(es->s_state);
		if (!ext2_setup_super (sb, es, 0))
			sb->s_flags &= ~SB_RDONLY;
		spin_unlock(&sbi->s_lock);

		ext2_write_super(sb);

		dquot_resume(sb, -1);
	}

	spin_lock(&sbi->s_lock);
out_set:
	sbi->s_mount_opt = new_opts.s_mount_opt;
	sbi->s_resuid = new_opts.s_resuid;
	sbi->s_resgid = new_opts.s_resgid;
	sb->s_flags = (sb->s_flags & ~SB_POSIXACL) |
		((sbi->s_mount_opt & EXT2_MOUNT_POSIX_ACL) ? SB_POSIXACL : 0);
	spin_unlock(&sbi->s_lock);

	return 0;
}

static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf)
{
	struct super_block *sb = dentry->d_sb;
	struct ext2_sb_info *sbi = EXT2_SB(sb);
	struct ext2_super_block *es = sbi->s_es;
	u64 fsid;

	spin_lock(&sbi->s_lock);

	if (test_opt (sb, MINIX_DF))
		sbi->s_overhead_last = 0;
	else if (sbi->s_blocks_last != le32_to_cpu(es->s_blocks_count)) {
		unsigned long i, overhead = 0;
		smp_rmb();

		/*
		 * Compute the overhead (FS structures). This is constant
		 * for a given filesystem unless the number of block groups
		 * changes so we cache the previous value until it does.
		 */

		/*
		 * All of the blocks before first_data_block are
		 * overhead
		 */
		overhead = le32_to_cpu(es->s_first_data_block);

		/*
		 * Add the overhead attributed to the superblock and
		 * block group descriptors.  If the sparse superblocks
		 * feature is turned on, then not all groups have this.
		 */
		for (i = 0; i < sbi->s_groups_count; i++)
			overhead += ext2_bg_has_super(sb, i) +
				ext2_bg_num_gdb(sb, i);

		/*
		 * Every block group has an inode bitmap, a block
		 * bitmap, and an inode table.
		 */
		overhead += (sbi->s_groups_count *
			     (2 + sbi->s_itb_per_group));
		sbi->s_overhead_last = overhead;
		smp_wmb();
		sbi->s_blocks_last = le32_to_cpu(es->s_blocks_count);
	}

	buf->f_type = EXT2_SUPER_MAGIC;
	buf->f_bsize = sb->s_blocksize;
	buf->f_blocks = le32_to_cpu(es->s_blocks_count) - sbi->s_overhead_last;
	buf->f_bfree = ext2_count_free_blocks(sb);
	es->s_free_blocks_count = cpu_to_le32(buf->f_bfree);
	buf->f_bavail = buf->f_bfree - le32_to_cpu(es->s_r_blocks_count);
	if (buf->f_bfree < le32_to_cpu(es->s_r_blocks_count))
		buf->f_bavail = 0;
	buf->f_files = le32_to_cpu(es->s_inodes_count);
	buf->f_ffree = ext2_count_free_inodes(sb);
	es->s_free_inodes_count = cpu_to_le32(buf->f_ffree);
	buf->f_namelen = EXT2_NAME_LEN;
	fsid = le64_to_cpup((void *)es->s_uuid) ^
	       le64_to_cpup((void *)es->s_uuid + sizeof(u64));
	buf->f_fsid.val[0] = fsid & 0xFFFFFFFFUL;
	buf->f_fsid.val[1] = (fsid >> 32) & 0xFFFFFFFFUL;
	spin_unlock(&sbi->s_lock);
	return 0;
}

static struct dentry *ext2_mount(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data)
{
	return mount_bdev(fs_type, flags, dev_name, data, ext2_fill_super);
}

#ifdef CONFIG_QUOTA

/* Read data from quotafile - avoid pagecache and such because we cannot afford
 * acquiring the locks... As quota files are never truncated and quota code
 * itself serializes the operations (and no one else should touch the files)
 * we don't have to be afraid of races */
static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data,
			       size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t toread;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;
	loff_t i_size = i_size_read(inode);

	if (off > i_size)
		return 0;
	if (off+len > i_size)
		len = i_size-off;
	toread = len;
	while (toread > 0) {
		tocopy = sb->s_blocksize - offset < toread ?
				sb->s_blocksize - offset : toread;

		tmp_bh.b_state = 0;
		tmp_bh.b_size = sb->s_blocksize;
		err = ext2_get_block(inode, blk, &tmp_bh, 0);
		if (err < 0)
			return err;
		if (!buffer_mapped(&tmp_bh))	/* A hole? */
			memset(data, 0, tocopy);
		else {
			bh = sb_bread(sb, tmp_bh.b_blocknr);
			if (!bh)
				return -EIO;
			memcpy(data, bh->b_data+offset, tocopy);
			brelse(bh);
		}
		offset = 0;
		toread -= tocopy;
		data += tocopy;
		blk++;
	}
	return len;
}

/* Write to quotafile */
static ssize_t ext2_quota_write(struct super_block *sb, int type,
				const char *data, size_t len, loff_t off)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	sector_t blk = off >> EXT2_BLOCK_SIZE_BITS(sb);
	int err = 0;
	int offset = off & (sb->s_blocksize - 1);
	int tocopy;
	size_t towrite = len;
	struct buffer_head tmp_bh;
	struct buffer_head *bh;

	while (towrite > 0) {
		tocopy = sb->s_blocksize - offset < towrite ?
				sb->s_blocksize - offset : towrite;

		tmp_bh.b_state = 0;
		tmp_bh.b_size = sb->s_blocksize;
		err = ext2_get_block(inode, blk, &tmp_bh, 1);
		if (err < 0)
			goto out;
		if (offset || tocopy != EXT2_BLOCK_SIZE(sb))
			bh = sb_bread(sb, tmp_bh.b_blocknr);
		else
			bh = sb_getblk(sb, tmp_bh.b_blocknr);
		if (unlikely(!bh)) {
			err = -EIO;
			goto out;
		}
		lock_buffer(bh);
		memcpy(bh->b_data+offset, data, tocopy);
		flush_dcache_page(bh->b_page);
		set_buffer_uptodate(bh);
		mark_buffer_dirty(bh);
		unlock_buffer(bh);
		brelse(bh);
		offset = 0;
		towrite -= tocopy;
		data += tocopy;
		blk++;
	}
out:
	if (len == towrite)
		return err;
	if (inode->i_size < off+len-towrite)
		i_size_write(inode, off+len-towrite);
	inode_inc_iversion(inode);
	inode->i_mtime = inode->i_ctime = current_time(inode);
	mark_inode_dirty(inode);
	return len - towrite;
}

static int ext2_quota_on(struct super_block *sb, int type, int format_id,
			 const struct path *path)
{
	int err;
	struct inode *inode;

	err = dquot_quota_on(sb, type, format_id, path);
	if (err)
		return err;

	inode = d_inode(path->dentry);
	inode_lock(inode);
	EXT2_I(inode)->i_flags |= EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL;
	inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
			S_NOATIME | S_IMMUTABLE);
	inode_unlock(inode);
	mark_inode_dirty(inode);

	return 0;
}

static int ext2_quota_off(struct super_block *sb, int type)
{
	struct inode *inode = sb_dqopt(sb)->files[type];
	int err;

	if (!inode || !igrab(inode))
		goto out;

	err = dquot_quota_off(sb, type);
	if (err)
		goto out_put;

	inode_lock(inode);
	EXT2_I(inode)->i_flags &= ~(EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL);
	inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
	inode_unlock(inode);
	mark_inode_dirty(inode);
out_put:
	iput(inode);
	return err;
out:
	return dquot_quota_off(sb, type);
}

#endif

static struct file_system_type ext2_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "ext2",
	.mount		= ext2_mount,
	.kill_sb	= kill_block_super,
	.fs_flags	= FS_REQUIRES_DEV,
};
MODULE_ALIAS_FS("ext2");

static int __init init_ext2_fs(void)
{
	int err;

	err = init_inodecache();
	if (err)
		return err;
        err = register_filesystem(&ext2_fs_type);
	if (err)
		goto out;
	return 0;
out:
	destroy_inodecache();
	return err;
}

static void __exit exit_ext2_fs(void)
{
	unregister_filesystem(&ext2_fs_type);
	destroy_inodecache();
}

MODULE_AUTHOR("Remy Card and others");
MODULE_DESCRIPTION("Second Extended Filesystem");
MODULE_LICENSE("GPL");
module_init(init_ext2_fs)
module_exit(exit_ext2_fs)
OpenPOWER on IntegriCloud