summaryrefslogtreecommitdiff
path: root/fs/fat/inode.c
blob: 920a576e1c25e26240c8ed583cbdfce7e4452e4e (plain) (blame)
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
/*
 *  linux/fs/fat/inode.c
 *
 *  Written 1992,1993 by Werner Almesberger
 *  VFAT extensions by Gordon Chaffee, merged with msdos fs by Henrik Storner
 *  Rewritten for the constant inumbers support by Al Viro
 *
 *  Fixes:
 *
 *	Max Cohan: Fixed invalid FSINFO offset when info_sector is 0
 */

#include <linux/module.h>
#include <linux/init.h>
#include <linux/time.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/seq_file.h>
#include <linux/msdos_fs.h>
#include <linux/pagemap.h>
#include <linux/mpage.h>
#include <linux/buffer_head.h>
#include <linux/exportfs.h>
#include <linux/mount.h>
#include <linux/vfs.h>
#include <linux/parser.h>
#include <linux/uio.h>
#include <linux/writeback.h>
#include <linux/log2.h>
#include <asm/unaligned.h>

#ifndef CONFIG_FAT_DEFAULT_IOCHARSET
/* if user don't select VFAT, this is undefined. */
#define CONFIG_FAT_DEFAULT_IOCHARSET	""
#endif

static int fat_default_codepage = CONFIG_FAT_DEFAULT_CODEPAGE;
static char fat_default_iocharset[] = CONFIG_FAT_DEFAULT_IOCHARSET;


static int fat_add_cluster(struct inode *inode)
{
	int err, cluster;

	err = fat_alloc_clusters(inode, &cluster, 1);
	if (err)
		return err;
	/* FIXME: this cluster should be added after data of this
	 * cluster is writed */
	err = fat_chain_add(inode, cluster, 1);
	if (err)
		fat_free_clusters(inode, cluster);
	return err;
}

static inline int __fat_get_block(struct inode *inode, sector_t iblock,
				  unsigned long *max_blocks,
				  struct buffer_head *bh_result, int create)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	unsigned long mapped_blocks;
	sector_t phys;
	int err, offset;

	err = fat_bmap(inode, iblock, &phys, &mapped_blocks);
	if (err)
		return err;
	if (phys) {
		map_bh(bh_result, sb, phys);
		*max_blocks = min(mapped_blocks, *max_blocks);
		return 0;
	}
	if (!create)
		return 0;

	if (iblock != MSDOS_I(inode)->mmu_private >> sb->s_blocksize_bits) {
		fat_fs_panic(sb, "corrupted file size (i_pos %lld, %lld)",
			MSDOS_I(inode)->i_pos, MSDOS_I(inode)->mmu_private);
		return -EIO;
	}

	offset = (unsigned long)iblock & (sbi->sec_per_clus - 1);
	if (!offset) {
		/* TODO: multiple cluster allocation would be desirable. */
		err = fat_add_cluster(inode);
		if (err)
			return err;
	}
	/* available blocks on this cluster */
	mapped_blocks = sbi->sec_per_clus - offset;

	*max_blocks = min(mapped_blocks, *max_blocks);
	MSDOS_I(inode)->mmu_private += *max_blocks << sb->s_blocksize_bits;

	err = fat_bmap(inode, iblock, &phys, &mapped_blocks);
	if (err)
		return err;

	BUG_ON(!phys);
	BUG_ON(*max_blocks != mapped_blocks);
	set_buffer_new(bh_result);
	map_bh(bh_result, sb, phys);

	return 0;
}

static int fat_get_block(struct inode *inode, sector_t iblock,
			 struct buffer_head *bh_result, int create)
{
	struct super_block *sb = inode->i_sb;
	unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
	int err;

	err = __fat_get_block(inode, iblock, &max_blocks, bh_result, create);
	if (err)
		return err;
	bh_result->b_size = max_blocks << sb->s_blocksize_bits;
	return 0;
}

static int fat_writepage(struct page *page, struct writeback_control *wbc)
{
	return block_write_full_page(page, fat_get_block, wbc);
}

static int fat_writepages(struct address_space *mapping,
			  struct writeback_control *wbc)
{
	return mpage_writepages(mapping, wbc, fat_get_block);
}

static int fat_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, fat_get_block);
}

static int fat_readpages(struct file *file, struct address_space *mapping,
			 struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, fat_get_block);
}

static int fat_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	*pagep = NULL;
	return cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata,
				fat_get_block,
				&MSDOS_I(mapping->host)->mmu_private);
}

static int fat_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *pagep, void *fsdata)
{
	struct inode *inode = mapping->host;
	int err;
	err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata);
	if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {
		inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC;
		MSDOS_I(inode)->i_attrs |= ATTR_ARCH;
		mark_inode_dirty(inode);
	}
	return err;
}

static ssize_t fat_direct_IO(int rw, struct kiocb *iocb,
			     const struct iovec *iov,
			     loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;

	if (rw == WRITE) {
		/*
		 * FIXME: blockdev_direct_IO() doesn't use ->prepare_write(),
		 * so we need to update the ->mmu_private to block boundary.
		 *
		 * But we must fill the remaining area or hole by nul for
		 * updating ->mmu_private.
		 *
		 * Return 0, and fallback to normal buffered write.
		 */
		loff_t size = offset + iov_length(iov, nr_segs);
		if (MSDOS_I(inode)->mmu_private < size)
			return 0;
	}

	/*
	 * FAT need to use the DIO_LOCKING for avoiding the race
	 * condition of fat_get_block() and ->truncate().
	 */
	return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov,
				  offset, nr_segs, fat_get_block, NULL);
}

static sector_t _fat_bmap(struct address_space *mapping, sector_t block)
{
	return generic_block_bmap(mapping, block, fat_get_block);
}

static const struct address_space_operations fat_aops = {
	.readpage	= fat_readpage,
	.readpages	= fat_readpages,
	.writepage	= fat_writepage,
	.writepages	= fat_writepages,
	.sync_page	= block_sync_page,
	.write_begin	= fat_write_begin,
	.write_end	= fat_write_end,
	.direct_IO	= fat_direct_IO,
	.bmap		= _fat_bmap
};

/*
 * New FAT inode stuff. We do the following:
 *	a) i_ino is constant and has nothing with on-disk location.
 *	b) FAT manages its own cache of directory entries.
 *	c) *This* cache is indexed by on-disk location.
 *	d) inode has an associated directory entry, all right, but
 *		it may be unhashed.
 *	e) currently entries are stored within struct inode. That should
 *		change.
 *	f) we deal with races in the following way:
 *		1. readdir() and lookup() do FAT-dir-cache lookup.
 *		2. rename() unhashes the F-d-c entry and rehashes it in
 *			a new place.
 *		3. unlink() and rmdir() unhash F-d-c entry.
 *		4. fat_write_inode() checks whether the thing is unhashed.
 *			If it is we silently return. If it isn't we do bread(),
 *			check if the location is still valid and retry if it
 *			isn't. Otherwise we do changes.
 *		5. Spinlock is used to protect hash/unhash/location check/lookup
 *		6. fat_clear_inode() unhashes the F-d-c entry.
 *		7. lookup() and readdir() do igrab() if they find a F-d-c entry
 *			and consider negative result as cache miss.
 */

static void fat_hash_init(struct super_block *sb)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	int i;

	spin_lock_init(&sbi->inode_hash_lock);
	for (i = 0; i < FAT_HASH_SIZE; i++)
		INIT_HLIST_HEAD(&sbi->inode_hashtable[i]);
}

static inline unsigned long fat_hash(struct super_block *sb, loff_t i_pos)
{
	unsigned long tmp = (unsigned long)i_pos | (unsigned long) sb;
	tmp = tmp + (tmp >> FAT_HASH_BITS) + (tmp >> FAT_HASH_BITS * 2);
	return tmp & FAT_HASH_MASK;
}

void fat_attach(struct inode *inode, loff_t i_pos)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);

	spin_lock(&sbi->inode_hash_lock);
	MSDOS_I(inode)->i_pos = i_pos;
	hlist_add_head(&MSDOS_I(inode)->i_fat_hash,
			sbi->inode_hashtable + fat_hash(sb, i_pos));
	spin_unlock(&sbi->inode_hash_lock);
}

EXPORT_SYMBOL_GPL(fat_attach);

void fat_detach(struct inode *inode)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	spin_lock(&sbi->inode_hash_lock);
	MSDOS_I(inode)->i_pos = 0;
	hlist_del_init(&MSDOS_I(inode)->i_fat_hash);
	spin_unlock(&sbi->inode_hash_lock);
}

EXPORT_SYMBOL_GPL(fat_detach);

struct inode *fat_iget(struct super_block *sb, loff_t i_pos)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	struct hlist_head *head = sbi->inode_hashtable + fat_hash(sb, i_pos);
	struct hlist_node *_p;
	struct msdos_inode_info *i;
	struct inode *inode = NULL;

	spin_lock(&sbi->inode_hash_lock);
	hlist_for_each_entry(i, _p, head, i_fat_hash) {
		BUG_ON(i->vfs_inode.i_sb != sb);
		if (i->i_pos != i_pos)
			continue;
		inode = igrab(&i->vfs_inode);
		if (inode)
			break;
	}
	spin_unlock(&sbi->inode_hash_lock);
	return inode;
}

static int is_exec(unsigned char *extension)
{
	unsigned char *exe_extensions = "EXECOMBAT", *walk;

	for (walk = exe_extensions; *walk; walk += 3)
		if (!strncmp(extension, walk, 3))
			return 1;
	return 0;
}

static int fat_calc_dir_size(struct inode *inode)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	int ret, fclus, dclus;

	inode->i_size = 0;
	if (MSDOS_I(inode)->i_start == 0)
		return 0;

	ret = fat_get_cluster(inode, FAT_ENT_EOF, &fclus, &dclus);
	if (ret < 0)
		return ret;
	inode->i_size = (fclus + 1) << sbi->cluster_bits;

	return 0;
}

/* doesn't deal with root inode */
static int fat_fill_inode(struct inode *inode, struct msdos_dir_entry *de)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
	int error;

	MSDOS_I(inode)->i_pos = 0;
	inode->i_uid = sbi->options.fs_uid;
	inode->i_gid = sbi->options.fs_gid;
	inode->i_version++;
	inode->i_generation = get_seconds();

	if ((de->attr & ATTR_DIR) && !IS_FREE(de->name)) {
		inode->i_generation &= ~1;
		inode->i_mode = MSDOS_MKMODE(de->attr,
			S_IRWXUGO & ~sbi->options.fs_dmask) | S_IFDIR;
		inode->i_op = sbi->dir_ops;
		inode->i_fop = &fat_dir_operations;

		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
		if (sbi->fat_bits == 32)
			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);

		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
		error = fat_calc_dir_size(inode);
		if (error < 0)
			return error;
		MSDOS_I(inode)->mmu_private = inode->i_size;

		inode->i_nlink = fat_subdirs(inode);
	} else { /* not a directory */
		inode->i_generation |= 1;
		inode->i_mode = MSDOS_MKMODE(de->attr,
		    ((sbi->options.showexec && !is_exec(de->name + 8))
			? S_IRUGO|S_IWUGO : S_IRWXUGO)
		    & ~sbi->options.fs_fmask) | S_IFREG;
		MSDOS_I(inode)->i_start = le16_to_cpu(de->start);
		if (sbi->fat_bits == 32)
			MSDOS_I(inode)->i_start |= (le16_to_cpu(de->starthi) << 16);

		MSDOS_I(inode)->i_logstart = MSDOS_I(inode)->i_start;
		inode->i_size = le32_to_cpu(de->size);
		inode->i_op = &fat_file_inode_operations;
		inode->i_fop = &fat_file_operations;
		inode->i_mapping->a_ops = &fat_aops;
		MSDOS_I(inode)->mmu_private = inode->i_size;
	}
	if (de->attr & ATTR_SYS) {
		if (sbi->options.sys_immutable)
			inode->i_flags |= S_IMMUTABLE;
	}
	MSDOS_I(inode)->i_attrs = de->attr & ATTR_UNUSED;
	inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
			   & ~((loff_t)sbi->cluster_size - 1)) >> 9;
	inode->i_mtime.tv_sec =
		date_dos2unix(le16_to_cpu(de->time), le16_to_cpu(de->date));
	inode->i_mtime.tv_nsec = 0;
	if (sbi->options.isvfat) {
		int secs = de->ctime_cs / 100;
		int csecs = de->ctime_cs % 100;
		inode->i_ctime.tv_sec  =
			date_dos2unix(le16_to_cpu(de->ctime),
				      le16_to_cpu(de->cdate)) + secs;
		inode->i_ctime.tv_nsec = csecs * 10000000;
		inode->i_atime.tv_sec =
			date_dos2unix(0, le16_to_cpu(de->adate));
		inode->i_atime.tv_nsec = 0;
	} else
		inode->i_ctime = inode->i_atime = inode->i_mtime;

	return 0;
}

struct inode *fat_build_inode(struct super_block *sb,
			struct msdos_dir_entry *de, loff_t i_pos)
{
	struct inode *inode;
	int err;

	inode = fat_iget(sb, i_pos);
	if (inode)
		goto out;
	inode = new_inode(sb);
	if (!inode) {
		inode = ERR_PTR(-ENOMEM);
		goto out;
	}
	inode->i_ino = iunique(sb, MSDOS_ROOT_INO);
	inode->i_version = 1;
	err = fat_fill_inode(inode, de);
	if (err) {
		iput(inode);
		inode = ERR_PTR(err);
		goto out;
	}
	fat_attach(inode, i_pos);
	insert_inode_hash(inode);
out:
	return inode;
}

EXPORT_SYMBOL_GPL(fat_build_inode);

static void fat_delete_inode(struct inode *inode)
{
	truncate_inode_pages(&inode->i_data, 0);

	if (!is_bad_inode(inode)) {
		inode->i_size = 0;
		fat_truncate(inode);
	}
	clear_inode(inode);
}

static void fat_clear_inode(struct inode *inode)
{
	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);

	if (is_bad_inode(inode))
		return;
	lock_kernel();
	spin_lock(&sbi->inode_hash_lock);
	fat_cache_inval_inode(inode);
	hlist_del_init(&MSDOS_I(inode)->i_fat_hash);
	spin_unlock(&sbi->inode_hash_lock);
	unlock_kernel();
}

static void fat_write_super(struct super_block *sb)
{
	sb->s_dirt = 0;

	if (!(sb->s_flags & MS_RDONLY))
		fat_clusters_flush(sb);
}

static void fat_put_super(struct super_block *sb)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);

	if (sbi->nls_disk) {
		unload_nls(sbi->nls_disk);
		sbi->nls_disk = NULL;
		sbi->options.codepage = fat_default_codepage;
	}
	if (sbi->nls_io) {
		unload_nls(sbi->nls_io);
		sbi->nls_io = NULL;
	}
	if (sbi->options.iocharset != fat_default_iocharset) {
		kfree(sbi->options.iocharset);
		sbi->options.iocharset = fat_default_iocharset;
	}

	sb->s_fs_info = NULL;
	kfree(sbi);
}

static struct kmem_cache *fat_inode_cachep;

static struct inode *fat_alloc_inode(struct super_block *sb)
{
	struct msdos_inode_info *ei;
	ei = kmem_cache_alloc(fat_inode_cachep, GFP_KERNEL);
	if (!ei)
		return NULL;
	return &ei->vfs_inode;
}

static void fat_destroy_inode(struct inode *inode)
{
	kmem_cache_free(fat_inode_cachep, MSDOS_I(inode));
}

static void init_once(struct kmem_cache *cachep, void *foo)
{
	struct msdos_inode_info *ei = (struct msdos_inode_info *)foo;

	spin_lock_init(&ei->cache_lru_lock);
	ei->nr_caches = 0;
	ei->cache_valid_id = FAT_CACHE_VALID + 1;
	INIT_LIST_HEAD(&ei->cache_lru);
	INIT_HLIST_NODE(&ei->i_fat_hash);
	inode_init_once(&ei->vfs_inode);
}

static int __init fat_init_inodecache(void)
{
	fat_inode_cachep = kmem_cache_create("fat_inode_cache",
					     sizeof(struct msdos_inode_info),
					     0, (SLAB_RECLAIM_ACCOUNT|
						SLAB_MEM_SPREAD),
					     init_once);
	if (fat_inode_cachep == NULL)
		return -ENOMEM;
	return 0;
}

static void __exit fat_destroy_inodecache(void)
{
	kmem_cache_destroy(fat_inode_cachep);
}

static int fat_remount(struct super_block *sb, int *flags, char *data)
{
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	*flags |= MS_NODIRATIME | (sbi->options.isvfat ? 0 : MS_NOATIME);
	return 0;
}

static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);

	/* If the count of free cluster is still unknown, counts it here. */
	if (sbi->free_clusters == -1) {
		int err = fat_count_free_clusters(dentry->d_sb);
		if (err)
			return err;
	}

	buf->f_type = dentry->d_sb->s_magic;
	buf->f_bsize = sbi->cluster_size;
	buf->f_blocks = sbi->max_cluster - FAT_START_ENT;
	buf->f_bfree = sbi->free_clusters;
	buf->f_bavail = sbi->free_clusters;
	buf->f_namelen = sbi->options.isvfat ? 260 : 12;

	return 0;
}

static int fat_write_inode(struct inode *inode, int wait)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	struct buffer_head *bh;
	struct msdos_dir_entry *raw_entry;
	loff_t i_pos;
	int err = 0;

retry:
	i_pos = MSDOS_I(inode)->i_pos;
	if (inode->i_ino == MSDOS_ROOT_INO || !i_pos)
		return 0;

	lock_kernel();
	bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits);
	if (!bh) {
		printk(KERN_ERR "FAT: unable to read inode block "
		       "for updating (i_pos %lld)\n", i_pos);
		err = -EIO;
		goto out;
	}
	spin_lock(&sbi->inode_hash_lock);
	if (i_pos != MSDOS_I(inode)->i_pos) {
		spin_unlock(&sbi->inode_hash_lock);
		brelse(bh);
		unlock_kernel();
		goto retry;
	}

	raw_entry = &((struct msdos_dir_entry *) (bh->b_data))
	    [i_pos & (sbi->dir_per_block - 1)];
	if (S_ISDIR(inode->i_mode))
		raw_entry->size = 0;
	else
		raw_entry->size = cpu_to_le32(inode->i_size);
	raw_entry->attr = fat_attr(inode);
	raw_entry->start = cpu_to_le16(MSDOS_I(inode)->i_logstart);
	raw_entry->starthi = cpu_to_le16(MSDOS_I(inode)->i_logstart >> 16);
	fat_date_unix2dos(inode->i_mtime.tv_sec, &raw_entry->time, &raw_entry->date);
	if (sbi->options.isvfat) {
		__le16 atime;
		fat_date_unix2dos(inode->i_ctime.tv_sec,&raw_entry->ctime,&raw_entry->cdate);
		fat_date_unix2dos(inode->i_atime.tv_sec,&atime,&raw_entry->adate);
		raw_entry->ctime_cs = (inode->i_ctime.tv_sec & 1) * 100 +
			inode->i_ctime.tv_nsec / 10000000;
	}
	spin_unlock(&sbi->inode_hash_lock);
	mark_buffer_dirty(bh);
	if (wait)
		err = sync_dirty_buffer(bh);
	brelse(bh);
out:
	unlock_kernel();
	return err;
}

int fat_sync_inode(struct inode *inode)
{
	return fat_write_inode(inode, 1);
}

EXPORT_SYMBOL_GPL(fat_sync_inode);

static int fat_show_options(struct seq_file *m, struct vfsmount *mnt);
static const struct super_operations fat_sops = {
	.alloc_inode	= fat_alloc_inode,
	.destroy_inode	= fat_destroy_inode,
	.write_inode	= fat_write_inode,
	.delete_inode	= fat_delete_inode,
	.put_super	= fat_put_super,
	.write_super	= fat_write_super,
	.statfs		= fat_statfs,
	.clear_inode	= fat_clear_inode,
	.remount_fs	= fat_remount,

	.read_inode	= make_bad_inode,

	.show_options	= fat_show_options,
};

/*
 * a FAT file handle with fhtype 3 is
 *  0/  i_ino - for fast, reliable lookup if still in the cache
 *  1/  i_generation - to see if i_ino is still valid
 *          bit 0 == 0 iff directory
 *  2/  i_pos(8-39) - if ino has changed, but still in cache
 *  3/  i_pos(4-7)|i_logstart - to semi-verify inode found at i_pos
 *  4/  i_pos(0-3)|parent->i_logstart - maybe used to hunt for the file on disc
 *
 * Hack for NFSv2: Maximum FAT entry number is 28bits and maximum
 * i_pos is 40bits (blocknr(32) + dir offset(8)), so two 4bits
 * of i_logstart is used to store the directory entry offset.
 */

static struct dentry *fat_fh_to_dentry(struct super_block *sb,
		struct fid *fid, int fh_len, int fh_type)
{
	struct inode *inode = NULL;
	struct dentry *result;
	u32 *fh = fid->raw;

	if (fh_len < 5 || fh_type != 3)
		return NULL;

	inode = iget(sb, fh[0]);
	if (!inode || is_bad_inode(inode) || inode->i_generation != fh[1]) {
		if (inode)
			iput(inode);
		inode = NULL;
	}
	if (!inode) {
		loff_t i_pos;
		int i_logstart = fh[3] & 0x0fffffff;

		i_pos = (loff_t)fh[2] << 8;
		i_pos |= ((fh[3] >> 24) & 0xf0) | (fh[4] >> 28);

		/* try 2 - see if i_pos is in F-d-c
		 * require i_logstart to be the same
		 * Will fail if you truncate and then re-write
		 */

		inode = fat_iget(sb, i_pos);
		if (inode && MSDOS_I(inode)->i_logstart != i_logstart) {
			iput(inode);
			inode = NULL;
		}
	}
	if (!inode) {
		/* For now, do nothing
		 * What we could do is:
		 * follow the file starting at fh[4], and record
		 * the ".." entry, and the name of the fh[2] entry.
		 * The follow the ".." file finding the next step up.
		 * This way we build a path to the root of
		 * the tree. If this works, we lookup the path and so
		 * get this inode into the cache.
		 * Finally try the fat_iget lookup again
		 * If that fails, then weare totally out of luck
		 * But all that is for another day
		 */
	}
	if (!inode)
		return ERR_PTR(-ESTALE);


	/* now to find a dentry.
	 * If possible, get a well-connected one
	 */
	result = d_alloc_anon(inode);
	if (result == NULL) {
		iput(inode);
		return ERR_PTR(-ENOMEM);
	}
	result->d_op = sb->s_root->d_op;
	return result;
}

static int
fat_encode_fh(struct dentry *de, __u32 *fh, int *lenp, int connectable)
{
	int len = *lenp;
	struct inode *inode =  de->d_inode;
	u32 ipos_h, ipos_m, ipos_l;

	if (len < 5)
		return 255; /* no room */

	ipos_h = MSDOS_I(inode)->i_pos >> 8;
	ipos_m = (MSDOS_I(inode)->i_pos & 0xf0) << 24;
	ipos_l = (MSDOS_I(inode)->i_pos & 0x0f) << 28;
	*lenp = 5;
	fh[0] = inode->i_ino;
	fh[1] = inode->i_generation;
	fh[2] = ipos_h;
	fh[3] = ipos_m | MSDOS_I(inode)->i_logstart;
	spin_lock(&de->d_lock);
	fh[4] = ipos_l | MSDOS_I(de->d_parent->d_inode)->i_logstart;
	spin_unlock(&de->d_lock);
	return 3;
}

static struct dentry *fat_get_parent(struct dentry *child)
{
	struct buffer_head *bh;
	struct msdos_dir_entry *de;
	loff_t i_pos;
	struct dentry *parent;
	struct inode *inode;
	int err;

	lock_kernel();

	err = fat_get_dotdot_entry(child->d_inode, &bh, &de, &i_pos);
	if (err) {
		parent = ERR_PTR(err);
		goto out;
	}
	inode = fat_build_inode(child->d_sb, de, i_pos);
	brelse(bh);
	if (IS_ERR(inode)) {
		parent = ERR_PTR(PTR_ERR(inode));
		goto out;
	}
	parent = d_alloc_anon(inode);
	if (!parent) {
		iput(inode);
		parent = ERR_PTR(-ENOMEM);
	}
out:
	unlock_kernel();

	return parent;
}

static const struct export_operations fat_export_ops = {
	.encode_fh	= fat_encode_fh,
	.fh_to_dentry	= fat_fh_to_dentry,
	.get_parent	= fat_get_parent,
};

static int fat_show_options(struct seq_file *m, struct vfsmount *mnt)
{
	struct msdos_sb_info *sbi = MSDOS_SB(mnt->mnt_sb);
	struct fat_mount_options *opts = &sbi->options;
	int isvfat = opts->isvfat;

	if (opts->fs_uid != 0)
		seq_printf(m, ",uid=%u", opts->fs_uid);
	if (opts->fs_gid != 0)
		seq_printf(m, ",gid=%u", opts->fs_gid);
	seq_printf(m, ",fmask=%04o", opts->fs_fmask);
	seq_printf(m, ",dmask=%04o", opts->fs_dmask);
	if (sbi->nls_disk)
		seq_printf(m, ",codepage=%s", sbi->nls_disk->charset);
	if (isvfat) {
		if (sbi->nls_io)
			seq_printf(m, ",iocharset=%s", sbi->nls_io->charset);

		switch (opts->shortname) {
		case VFAT_SFN_DISPLAY_WIN95 | VFAT_SFN_CREATE_WIN95:
			seq_puts(m, ",shortname=win95");
			break;
		case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WINNT:
			seq_puts(m, ",shortname=winnt");
			break;
		case VFAT_SFN_DISPLAY_WINNT | VFAT_SFN_CREATE_WIN95:
			seq_puts(m, ",shortname=mixed");
			break;
		case VFAT_SFN_DISPLAY_LOWER | VFAT_SFN_CREATE_WIN95:
			/* seq_puts(m, ",shortname=lower"); */
			break;
		default:
			seq_puts(m, ",shortname=unknown");
			break;
		}
	}
	if (opts->name_check != 'n')
		seq_printf(m, ",check=%c", opts->name_check);
	if (opts->usefree)
		seq_puts(m, ",usefree");
	if (opts->quiet)
		seq_puts(m, ",quiet");
	if (opts->showexec)
		seq_puts(m, ",showexec");
	if (opts->sys_immutable)
		seq_puts(m, ",sys_immutable");
	if (!isvfat) {
		if (opts->dotsOK)
			seq_puts(m, ",dotsOK=yes");
		if (opts->nocase)
			seq_puts(m, ",nocase");
	} else {
		if (opts->utf8)
			seq_puts(m, ",utf8");
		if (opts->unicode_xlate)
			seq_puts(m, ",uni_xlate");
		if (!opts->numtail)
			seq_puts(m, ",nonumtail");
	}

	return 0;
}

enum {
	Opt_check_n, Opt_check_r, Opt_check_s, Opt_uid, Opt_gid,
	Opt_umask, Opt_dmask, Opt_fmask, Opt_codepage, Opt_usefree, Opt_nocase,
	Opt_quiet, Opt_showexec, Opt_debug, Opt_immutable,
	Opt_dots, Opt_nodots,
	Opt_charset, Opt_shortname_lower, Opt_shortname_win95,
	Opt_shortname_winnt, Opt_shortname_mixed, Opt_utf8_no, Opt_utf8_yes,
	Opt_uni_xl_no, Opt_uni_xl_yes, Opt_nonumtail_no, Opt_nonumtail_yes,
	Opt_obsolate, Opt_flush, Opt_err,
};

static match_table_t fat_tokens = {
	{Opt_check_r, "check=relaxed"},
	{Opt_check_s, "check=strict"},
	{Opt_check_n, "check=normal"},
	{Opt_check_r, "check=r"},
	{Opt_check_s, "check=s"},
	{Opt_check_n, "check=n"},
	{Opt_uid, "uid=%u"},
	{Opt_gid, "gid=%u"},
	{Opt_umask, "umask=%o"},
	{Opt_dmask, "dmask=%o"},
	{Opt_fmask, "fmask=%o"},
	{Opt_codepage, "codepage=%u"},
	{Opt_usefree, "usefree"},
	{Opt_nocase, "nocase"},
	{Opt_quiet, "quiet"},
	{Opt_showexec, "showexec"},
	{Opt_debug, "debug"},
	{Opt_immutable, "sys_immutable"},
	{Opt_obsolate, "conv=binary"},
	{Opt_obsolate, "conv=text"},
	{Opt_obsolate, "conv=auto"},
	{Opt_obsolate, "conv=b"},
	{Opt_obsolate, "conv=t"},
	{Opt_obsolate, "conv=a"},
	{Opt_obsolate, "fat=%u"},
	{Opt_obsolate, "blocksize=%u"},
	{Opt_obsolate, "cvf_format=%20s"},
	{Opt_obsolate, "cvf_options=%100s"},
	{Opt_obsolate, "posix"},
	{Opt_flush, "flush"},
	{Opt_err, NULL},
};
static match_table_t msdos_tokens = {
	{Opt_nodots, "nodots"},
	{Opt_nodots, "dotsOK=no"},
	{Opt_dots, "dots"},
	{Opt_dots, "dotsOK=yes"},
	{Opt_err, NULL}
};
static match_table_t vfat_tokens = {
	{Opt_charset, "iocharset=%s"},
	{Opt_shortname_lower, "shortname=lower"},
	{Opt_shortname_win95, "shortname=win95"},
	{Opt_shortname_winnt, "shortname=winnt"},
	{Opt_shortname_mixed, "shortname=mixed"},
	{Opt_utf8_no, "utf8=0"},		/* 0 or no or false */
	{Opt_utf8_no, "utf8=no"},
	{Opt_utf8_no, "utf8=false"},
	{Opt_utf8_yes, "utf8=1"},		/* empty or 1 or yes or true */
	{Opt_utf8_yes, "utf8=yes"},
	{Opt_utf8_yes, "utf8=true"},
	{Opt_utf8_yes, "utf8"},
	{Opt_uni_xl_no, "uni_xlate=0"},		/* 0 or no or false */
	{Opt_uni_xl_no, "uni_xlate=no"},
	{Opt_uni_xl_no, "uni_xlate=false"},
	{Opt_uni_xl_yes, "uni_xlate=1"},	/* empty or 1 or yes or true */
	{Opt_uni_xl_yes, "uni_xlate=yes"},
	{Opt_uni_xl_yes, "uni_xlate=true"},
	{Opt_uni_xl_yes, "uni_xlate"},
	{Opt_nonumtail_no, "nonumtail=0"},	/* 0 or no or false */
	{Opt_nonumtail_no, "nonumtail=no"},
	{Opt_nonumtail_no, "nonumtail=false"},
	{Opt_nonumtail_yes, "nonumtail=1"},	/* empty or 1 or yes or true */
	{Opt_nonumtail_yes, "nonumtail=yes"},
	{Opt_nonumtail_yes, "nonumtail=true"},
	{Opt_nonumtail_yes, "nonumtail"},
	{Opt_err, NULL}
};

static int parse_options(char *options, int is_vfat, int silent, int *debug,
			 struct fat_mount_options *opts)
{
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;
	char *iocharset;

	opts->isvfat = is_vfat;

	opts->fs_uid = current->uid;
	opts->fs_gid = current->gid;
	opts->fs_fmask = opts->fs_dmask = current->fs->umask;
	opts->codepage = fat_default_codepage;
	opts->iocharset = fat_default_iocharset;
	if (is_vfat)
		opts->shortname = VFAT_SFN_DISPLAY_LOWER|VFAT_SFN_CREATE_WIN95;
	else
		opts->shortname = 0;
	opts->name_check = 'n';
	opts->quiet = opts->showexec = opts->sys_immutable = opts->dotsOK =  0;
	opts->utf8 = opts->unicode_xlate = 0;
	opts->numtail = 1;
	opts->usefree = opts->nocase = 0;
	*debug = 0;

	if (!options)
		return 0;

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

		token = match_token(p, fat_tokens, args);
		if (token == Opt_err) {
			if (is_vfat)
				token = match_token(p, vfat_tokens, args);
			else
				token = match_token(p, msdos_tokens, args);
		}
		switch (token) {
		case Opt_check_s:
			opts->name_check = 's';
			break;
		case Opt_check_r:
			opts->name_check = 'r';
			break;
		case Opt_check_n:
			opts->name_check = 'n';
			break;
		case Opt_usefree:
			opts->usefree = 1;
			break;
		case Opt_nocase:
			if (!is_vfat)
				opts->nocase = 1;
			else {
				/* for backward compatibility */
				opts->shortname = VFAT_SFN_DISPLAY_WIN95
					| VFAT_SFN_CREATE_WIN95;
			}
			break;
		case Opt_quiet:
			opts->quiet = 1;
			break;
		case Opt_showexec:
			opts->showexec = 1;
			break;
		case Opt_debug:
			*debug = 1;
			break;
		case Opt_immutable:
			opts->sys_immutable = 1;
			break;
		case Opt_uid:
			if (match_int(&args[0], &option))
				return 0;
			opts->fs_uid = option;
			break;
		case Opt_gid:
			if (match_int(&args[0], &option))
				return 0;
			opts->fs_gid = option;
			break;
		case Opt_umask:
			if (match_octal(&args[0], &option))
				return 0;
			opts->fs_fmask = opts->fs_dmask = option;
			break;
		case Opt_dmask:
			if (match_octal(&args[0], &option))
				return 0;
			opts->fs_dmask = option;
			break;
		case Opt_fmask:
			if (match_octal(&args[0], &option))
				return 0;
			opts->fs_fmask = option;
			break;
		case Opt_codepage:
			if (match_int(&args[0], &option))
				return 0;
			opts->codepage = option;
			break;
		case Opt_flush:
			opts->flush = 1;
			break;

		/* msdos specific */
		case Opt_dots:
			opts->dotsOK = 1;
			break;
		case Opt_nodots:
			opts->dotsOK = 0;
			break;

		/* vfat specific */
		case Opt_charset:
			if (opts->iocharset != fat_default_iocharset)
				kfree(opts->iocharset);
			iocharset = match_strdup(&args[0]);
			if (!iocharset)
				return -ENOMEM;
			opts->iocharset = iocharset;
			break;
		case Opt_shortname_lower:
			opts->shortname = VFAT_SFN_DISPLAY_LOWER
					| VFAT_SFN_CREATE_WIN95;
			break;
		case Opt_shortname_win95:
			opts->shortname = VFAT_SFN_DISPLAY_WIN95
					| VFAT_SFN_CREATE_WIN95;
			break;
		case Opt_shortname_winnt:
			opts->shortname = VFAT_SFN_DISPLAY_WINNT
					| VFAT_SFN_CREATE_WINNT;
			break;
		case Opt_shortname_mixed:
			opts->shortname = VFAT_SFN_DISPLAY_WINNT
					| VFAT_SFN_CREATE_WIN95;
			break;
		case Opt_utf8_no:		/* 0 or no or false */
			opts->utf8 = 0;
			break;
		case Opt_utf8_yes:		/* empty or 1 or yes or true */
			opts->utf8 = 1;
			break;
		case Opt_uni_xl_no:		/* 0 or no or false */
			opts->unicode_xlate = 0;
			break;
		case Opt_uni_xl_yes:		/* empty or 1 or yes or true */
			opts->unicode_xlate = 1;
			break;
		case Opt_nonumtail_no:		/* 0 or no or false */
			opts->numtail = 1;	/* negated option */
			break;
		case Opt_nonumtail_yes:		/* empty or 1 or yes or true */
			opts->numtail = 0;	/* negated option */
			break;

		/* obsolete mount options */
		case Opt_obsolate:
			printk(KERN_INFO "FAT: \"%s\" option is obsolete, "
			       "not supported now\n", p);
			break;
		/* unknown option */
		default:
			if (!silent) {
				printk(KERN_ERR
				       "FAT: Unrecognized mount option \"%s\" "
				       "or missing value\n", p);
			}
			return -EINVAL;
		}
	}
	/* UTF-8 doesn't provide FAT semantics */
	if (!strcmp(opts->iocharset, "utf8")) {
		printk(KERN_ERR "FAT: utf8 is not a recommended IO charset"
		       " for FAT filesystems, filesystem will be case sensitive!\n");
	}

	if (opts->unicode_xlate)
		opts->utf8 = 0;

	return 0;
}

static int fat_read_root(struct inode *inode)
{
	struct super_block *sb = inode->i_sb;
	struct msdos_sb_info *sbi = MSDOS_SB(sb);
	int error;

	MSDOS_I(inode)->i_pos = 0;
	inode->i_uid = sbi->options.fs_uid;
	inode->i_gid = sbi->options.fs_gid;
	inode->i_version++;
	inode->i_generation = 0;
	inode->i_mode = (S_IRWXUGO & ~sbi->options.fs_dmask) | S_IFDIR;
	inode->i_op = sbi->dir_ops;
	inode->i_fop = &fat_dir_operations;
	if (sbi->fat_bits == 32) {
		MSDOS_I(inode)->i_start = sbi->root_cluster;
		error = fat_calc_dir_size(inode);
		if (error < 0)
			return error;
	} else {
		MSDOS_I(inode)->i_start = 0;
		inode->i_size = sbi->dir_entries * sizeof(struct msdos_dir_entry);
	}
	inode->i_blocks = ((inode->i_size + (sbi->cluster_size - 1))
			   & ~((loff_t)sbi->cluster_size - 1)) >> 9;
	MSDOS_I(inode)->i_logstart = 0;
	MSDOS_I(inode)->mmu_private = inode->i_size;

	MSDOS_I(inode)->i_attrs = ATTR_NONE;
	inode->i_mtime.tv_sec = inode->i_atime.tv_sec = inode->i_ctime.tv_sec = 0;
	inode->i_mtime.tv_nsec = inode->i_atime.tv_nsec = inode->i_ctime.tv_nsec = 0;
	inode->i_nlink = fat_subdirs(inode)+2;

	return 0;
}

/*
 * Read the super block of an MS-DOS FS.
 */
int fat_fill_super(struct super_block *sb, void *data, int silent,
		   const struct inode_operations *fs_dir_inode_ops, int isvfat)
{
	struct inode *root_inode = NULL;
	struct buffer_head *bh;
	struct fat_boot_sector *b;
	struct msdos_sb_info *sbi;
	u16 logical_sector_size;
	u32 total_sectors, total_clusters, fat_clusters, rootdir_sectors;
	int debug;
	unsigned int media;
	long error;
	char buf[50];

	sbi = kzalloc(sizeof(struct msdos_sb_info), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;
	sb->s_fs_info = sbi;

	sb->s_flags |= MS_NODIRATIME;
	sb->s_magic = MSDOS_SUPER_MAGIC;
	sb->s_op = &fat_sops;
	sb->s_export_op = &fat_export_ops;
	sbi->dir_ops = fs_dir_inode_ops;

	error = parse_options(data, isvfat, silent, &debug, &sbi->options);
	if (error)
		goto out_fail;

	error = -EIO;
	sb_min_blocksize(sb, 512);
	bh = sb_bread(sb, 0);
	if (bh == NULL) {
		printk(KERN_ERR "FAT: unable to read boot sector\n");
		goto out_fail;
	}

	b = (struct fat_boot_sector *) bh->b_data;
	if (!b->reserved) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus number of reserved sectors\n");
		brelse(bh);
		goto out_invalid;
	}
	if (!b->fats) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus number of FAT structure\n");
		brelse(bh);
		goto out_invalid;
	}

	/*
	 * Earlier we checked here that b->secs_track and b->head are nonzero,
	 * but it turns out valid FAT filesystems can have zero there.
	 */

	media = b->media;
	if (!FAT_VALID_MEDIA(media)) {
		if (!silent)
			printk(KERN_ERR "FAT: invalid media value (0x%02x)\n",
			       media);
		brelse(bh);
		goto out_invalid;
	}
	logical_sector_size =
		le16_to_cpu(get_unaligned((__le16 *)&b->sector_size));
	if (!is_power_of_2(logical_sector_size)
	    || (logical_sector_size < 512)
	    || (PAGE_CACHE_SIZE < logical_sector_size)) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus logical sector size %u\n",
			       logical_sector_size);
		brelse(bh);
		goto out_invalid;
	}
	sbi->sec_per_clus = b->sec_per_clus;
	if (!is_power_of_2(sbi->sec_per_clus)) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus sectors per cluster %u\n",
			       sbi->sec_per_clus);
		brelse(bh);
		goto out_invalid;
	}

	if (logical_sector_size < sb->s_blocksize) {
		printk(KERN_ERR "FAT: logical sector size too small for device"
		       " (logical sector size = %u)\n", logical_sector_size);
		brelse(bh);
		goto out_fail;
	}
	if (logical_sector_size > sb->s_blocksize) {
		brelse(bh);

		if (!sb_set_blocksize(sb, logical_sector_size)) {
			printk(KERN_ERR "FAT: unable to set blocksize %u\n",
			       logical_sector_size);
			goto out_fail;
		}
		bh = sb_bread(sb, 0);
		if (bh == NULL) {
			printk(KERN_ERR "FAT: unable to read boot sector"
			       " (logical sector size = %lu)\n",
			       sb->s_blocksize);
			goto out_fail;
		}
		b = (struct fat_boot_sector *) bh->b_data;
	}

	sbi->cluster_size = sb->s_blocksize * sbi->sec_per_clus;
	sbi->cluster_bits = ffs(sbi->cluster_size) - 1;
	sbi->fats = b->fats;
	sbi->fat_bits = 0;		/* Don't know yet */
	sbi->fat_start = le16_to_cpu(b->reserved);
	sbi->fat_length = le16_to_cpu(b->fat_length);
	sbi->root_cluster = 0;
	sbi->free_clusters = -1;	/* Don't know yet */
	sbi->prev_free = FAT_START_ENT;

	if (!sbi->fat_length && b->fat32_length) {
		struct fat_boot_fsinfo *fsinfo;
		struct buffer_head *fsinfo_bh;

		/* Must be FAT32 */
		sbi->fat_bits = 32;
		sbi->fat_length = le32_to_cpu(b->fat32_length);
		sbi->root_cluster = le32_to_cpu(b->root_cluster);

		sb->s_maxbytes = 0xffffffff;

		/* MC - if info_sector is 0, don't multiply by 0 */
		sbi->fsinfo_sector = le16_to_cpu(b->info_sector);
		if (sbi->fsinfo_sector == 0)
			sbi->fsinfo_sector = 1;

		fsinfo_bh = sb_bread(sb, sbi->fsinfo_sector);
		if (fsinfo_bh == NULL) {
			printk(KERN_ERR "FAT: bread failed, FSINFO block"
			       " (sector = %lu)\n", sbi->fsinfo_sector);
			brelse(bh);
			goto out_fail;
		}

		fsinfo = (struct fat_boot_fsinfo *)fsinfo_bh->b_data;
		if (!IS_FSINFO(fsinfo)) {
			printk(KERN_WARNING
			       "FAT: Did not find valid FSINFO signature.\n"
			       "     Found signature1 0x%08x signature2 0x%08x"
			       " (sector = %lu)\n",
			       le32_to_cpu(fsinfo->signature1),
			       le32_to_cpu(fsinfo->signature2),
			       sbi->fsinfo_sector);
		} else {
			if (sbi->options.usefree)
				sbi->free_clusters =
					le32_to_cpu(fsinfo->free_clusters);
			sbi->prev_free = le32_to_cpu(fsinfo->next_cluster);
		}

		brelse(fsinfo_bh);
	}

	sbi->dir_per_block = sb->s_blocksize / sizeof(struct msdos_dir_entry);
	sbi->dir_per_block_bits = ffs(sbi->dir_per_block) - 1;

	sbi->dir_start = sbi->fat_start + sbi->fats * sbi->fat_length;
	sbi->dir_entries =
		le16_to_cpu(get_unaligned((__le16 *)&b->dir_entries));
	if (sbi->dir_entries & (sbi->dir_per_block - 1)) {
		if (!silent)
			printk(KERN_ERR "FAT: bogus directroy-entries per block"
			       " (%u)\n", sbi->dir_entries);
		brelse(bh);
		goto out_invalid;
	}

	rootdir_sectors = sbi->dir_entries
		* sizeof(struct msdos_dir_entry) / sb->s_blocksize;
	sbi->data_start = sbi->dir_start + rootdir_sectors;
	total_sectors = le16_to_cpu(get_unaligned((__le16 *)&b->sectors));
	if (total_sectors == 0)
		total_sectors = le32_to_cpu(b->total_sect);

	total_clusters = (total_sectors - sbi->data_start) / sbi->sec_per_clus;

	if (sbi->fat_bits != 32)
		sbi->fat_bits = (total_clusters > MAX_FAT12) ? 16 : 12;

	/* check that FAT table does not overflow */
	fat_clusters = sbi->fat_length * sb->s_blocksize * 8 / sbi->fat_bits;
	total_clusters = min(total_clusters, fat_clusters - FAT_START_ENT);
	if (total_clusters > MAX_FAT(sb)) {
		if (!silent)
			printk(KERN_ERR "FAT: count of clusters too big (%u)\n",
			       total_clusters);
		brelse(bh);
		goto out_invalid;
	}

	sbi->max_cluster = total_clusters + FAT_START_ENT;
	/* check the free_clusters, it's not necessarily correct */
	if (sbi->free_clusters != -1 && sbi->free_clusters > total_clusters)
		sbi->free_clusters = -1;
	/* check the prev_free, it's not necessarily correct */
	sbi->prev_free %= sbi->max_cluster;
	if (sbi->prev_free < FAT_START_ENT)
		sbi->prev_free = FAT_START_ENT;

	brelse(bh);

	/* set up enough so that it can read an inode */
	fat_hash_init(sb);
	fat_ent_access_init(sb);

	/*
	 * The low byte of FAT's first entry must have same value with
	 * media-field.  But in real world, too many devices is
	 * writing wrong value.  So, removed that validity check.
	 *
	 * if (FAT_FIRST_ENT(sb, media) != first)
	 */

	error = -EINVAL;
	sprintf(buf, "cp%d", sbi->options.codepage);
	sbi->nls_disk = load_nls(buf);
	if (!sbi->nls_disk) {
		printk(KERN_ERR "FAT: codepage %s not found\n", buf);
		goto out_fail;
	}

	/* FIXME: utf8 is using iocharset for upper/lower conversion */
	if (sbi->options.isvfat) {
		sbi->nls_io = load_nls(sbi->options.iocharset);
		if (!sbi->nls_io) {
			printk(KERN_ERR "FAT: IO charset %s not found\n",
			       sbi->options.iocharset);
			goto out_fail;
		}
	}

	error = -ENOMEM;
	root_inode = new_inode(sb);
	if (!root_inode)
		goto out_fail;
	root_inode->i_ino = MSDOS_ROOT_INO;
	root_inode->i_version = 1;
	error = fat_read_root(root_inode);
	if (error < 0)
		goto out_fail;
	error = -ENOMEM;
	insert_inode_hash(root_inode);
	sb->s_root = d_alloc_root(root_inode);
	if (!sb->s_root) {
		printk(KERN_ERR "FAT: get root inode failed\n");
		goto out_fail;
	}

	return 0;

out_invalid:
	error = -EINVAL;
	if (!silent)
		printk(KERN_INFO "VFS: Can't find a valid FAT filesystem"
		       " on dev %s.\n", sb->s_id);

out_fail:
	if (root_inode)
		iput(root_inode);
	if (sbi->nls_io)
		unload_nls(sbi->nls_io);
	if (sbi->nls_disk)
		unload_nls(sbi->nls_disk);
	if (sbi->options.iocharset != fat_default_iocharset)
		kfree(sbi->options.iocharset);
	sb->s_fs_info = NULL;
	kfree(sbi);
	return error;
}

EXPORT_SYMBOL_GPL(fat_fill_super);

/*
 * helper function for fat_flush_inodes.  This writes both the inode
 * and the file data blocks, waiting for in flight data blocks before
 * the start of the call.  It does not wait for any io started
 * during the call
 */
static int writeback_inode(struct inode *inode)
{

	int ret;
	struct address_space *mapping = inode->i_mapping;
	struct writeback_control wbc = {
	       .sync_mode = WB_SYNC_NONE,
	      .nr_to_write = 0,
	};
	/* if we used WB_SYNC_ALL, sync_inode waits for the io for the
	* inode to finish.  So WB_SYNC_NONE is sent down to sync_inode
	* and filemap_fdatawrite is used for the data blocks
	*/
	ret = sync_inode(inode, &wbc);
	if (!ret)
	       ret = filemap_fdatawrite(mapping);
	return ret;
}

/*
 * write data and metadata corresponding to i1 and i2.  The io is
 * started but we do not wait for any of it to finish.
 *
 * filemap_flush is used for the block device, so if there is a dirty
 * page for a block already in flight, we will not wait and start the
 * io over again
 */
int fat_flush_inodes(struct super_block *sb, struct inode *i1, struct inode *i2)
{
	int ret = 0;
	if (!MSDOS_SB(sb)->options.flush)
		return 0;
	if (i1)
		ret = writeback_inode(i1);
	if (!ret && i2)
		ret = writeback_inode(i2);
	if (!ret) {
		struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
		ret = filemap_flush(mapping);
	}
	return ret;
}
EXPORT_SYMBOL_GPL(fat_flush_inodes);

static int __init init_fat_fs(void)
{
	int err;

	err = fat_cache_init();
	if (err)
		return err;

	err = fat_init_inodecache();
	if (err)
		goto failed;

	return 0;

failed:
	fat_cache_destroy();
	return err;
}

static void __exit exit_fat_fs(void)
{
	fat_cache_destroy();
	fat_destroy_inodecache();
}

module_init(init_fat_fs)
module_exit(exit_fat_fs)

MODULE_LICENSE("GPL");