summaryrefslogtreecommitdiff
path: root/fs/nilfs2/super.c
blob: 5893cb27c90921e6b83756070640024109e387d9 (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
/*
 * super.c - NILFS module and super block management.
 *
 * Copyright (C) 2005-2008 Nippon Telegraph and Telephone Corporation.
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
 * GNU General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
 *
 * Written by Ryusuke Konishi <ryusuke@osrg.net>
 */
/*
 *  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/slab.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/parser.h>
#include <linux/random.h>
#include <linux/crc32.h>
#include <linux/vfs.h>
#include <linux/writeback.h>
#include <linux/kobject.h>
#include <linux/seq_file.h>
#include <linux/mount.h>
#include "nilfs.h"
#include "export.h"
#include "mdt.h"
#include "alloc.h"
#include "btree.h"
#include "btnode.h"
#include "page.h"
#include "cpfile.h"
#include "ifile.h"
#include "dat.h"
#include "segment.h"
#include "segbuf.h"

MODULE_AUTHOR("NTT Corp.");
MODULE_DESCRIPTION("A New Implementation of the Log-structured Filesystem "
		   "(NILFS)");
MODULE_LICENSE("GPL");

struct kmem_cache *nilfs_inode_cachep;
struct kmem_cache *nilfs_transaction_cachep;
struct kmem_cache *nilfs_segbuf_cachep;
struct kmem_cache *nilfs_btree_path_cache;

static int nilfs_remount(struct super_block *sb, int *flags, char *data);

static void nilfs_set_error(struct nilfs_sb_info *sbi)
{
	struct the_nilfs *nilfs = sbi->s_nilfs;
	struct nilfs_super_block **sbp;

	down_write(&nilfs->ns_sem);
	if (!(nilfs->ns_mount_state & NILFS_ERROR_FS)) {
		nilfs->ns_mount_state |= NILFS_ERROR_FS;
		sbp = nilfs_prepare_super(sbi, 0);
		if (likely(sbp)) {
			sbp[0]->s_state |= cpu_to_le16(NILFS_ERROR_FS);
			if (sbp[1])
				sbp[1]->s_state |= cpu_to_le16(NILFS_ERROR_FS);
			nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
		}
	}
	up_write(&nilfs->ns_sem);
}

/**
 * nilfs_error() - report failure condition on a filesystem
 *
 * nilfs_error() sets an ERROR_FS flag on the superblock as well as
 * reporting an error message.  It should be called when NILFS detects
 * incoherences or defects of meta data on disk.  As for sustainable
 * errors such as a single-shot I/O error, nilfs_warning() or the printk()
 * function should be used instead.
 *
 * The segment constructor must not call this function because it can
 * kill itself.
 */
void nilfs_error(struct super_block *sb, const char *function,
		 const char *fmt, ...)
{
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	va_list args;

	va_start(args, fmt);
	printk(KERN_CRIT "NILFS error (device %s): %s: ", sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);

	if (!(sb->s_flags & MS_RDONLY)) {
		nilfs_set_error(sbi);

		if (nilfs_test_opt(sbi, ERRORS_RO)) {
			printk(KERN_CRIT "Remounting filesystem read-only\n");
			sb->s_flags |= MS_RDONLY;
		}
	}

	if (nilfs_test_opt(sbi, ERRORS_PANIC))
		panic("NILFS (device %s): panic forced after error\n",
		      sb->s_id);
}

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

	va_start(args, fmt);
	printk(KERN_WARNING "NILFS warning (device %s): %s: ",
	       sb->s_id, function);
	vprintk(fmt, args);
	printk("\n");
	va_end(args);
}


struct inode *nilfs_alloc_inode_common(struct the_nilfs *nilfs)
{
	struct nilfs_inode_info *ii;

	ii = kmem_cache_alloc(nilfs_inode_cachep, GFP_NOFS);
	if (!ii)
		return NULL;
	ii->i_bh = NULL;
	ii->i_state = 0;
	ii->i_cno = 0;
	ii->vfs_inode.i_version = 1;
	nilfs_btnode_cache_init(&ii->i_btnode_cache, nilfs->ns_bdi);
	return &ii->vfs_inode;
}

struct inode *nilfs_alloc_inode(struct super_block *sb)
{
	return nilfs_alloc_inode_common(NILFS_SB(sb)->s_nilfs);
}

void nilfs_destroy_inode(struct inode *inode)
{
	struct nilfs_mdt_info *mdi = NILFS_MDT(inode);

	if (mdi) {
		kfree(mdi->mi_bgl); /* kfree(NULL) is safe */
		kfree(mdi);
	}
	kmem_cache_free(nilfs_inode_cachep, NILFS_I(inode));
}

static int nilfs_sync_super(struct nilfs_sb_info *sbi, int flag)
{
	struct the_nilfs *nilfs = sbi->s_nilfs;
	int err;

 retry:
	set_buffer_dirty(nilfs->ns_sbh[0]);

	if (nilfs_test_opt(sbi, BARRIER)) {
		err = __sync_dirty_buffer(nilfs->ns_sbh[0],
					  WRITE_SYNC | WRITE_BARRIER);
		if (err == -EOPNOTSUPP) {
			nilfs_warning(sbi->s_super, __func__,
				      "barrier-based sync failed. "
				      "disabling barriers\n");
			nilfs_clear_opt(sbi, BARRIER);
			goto retry;
		}
	} else {
		err = sync_dirty_buffer(nilfs->ns_sbh[0]);
	}

	if (unlikely(err)) {
		printk(KERN_ERR
		       "NILFS: unable to write superblock (err=%d)\n", err);
		if (err == -EIO && nilfs->ns_sbh[1]) {
			/*
			 * sbp[0] points to newer log than sbp[1],
			 * so copy sbp[0] to sbp[1] to take over sbp[0].
			 */
			memcpy(nilfs->ns_sbp[1], nilfs->ns_sbp[0],
			       nilfs->ns_sbsize);
			nilfs_fall_back_super_block(nilfs);
			goto retry;
		}
	} else {
		struct nilfs_super_block *sbp = nilfs->ns_sbp[0];

		nilfs->ns_sbwcount++;

		/*
		 * The latest segment becomes trailable from the position
		 * written in superblock.
		 */
		clear_nilfs_discontinued(nilfs);

		/* update GC protection for recent segments */
		if (nilfs->ns_sbh[1]) {
			if (flag == NILFS_SB_COMMIT_ALL) {
				set_buffer_dirty(nilfs->ns_sbh[1]);
				if (sync_dirty_buffer(nilfs->ns_sbh[1]) < 0)
					goto out;
			}
			if (le64_to_cpu(nilfs->ns_sbp[1]->s_last_cno) <
			    le64_to_cpu(nilfs->ns_sbp[0]->s_last_cno))
				sbp = nilfs->ns_sbp[1];
		}

		spin_lock(&nilfs->ns_last_segment_lock);
		nilfs->ns_prot_seq = le64_to_cpu(sbp->s_last_seq);
		spin_unlock(&nilfs->ns_last_segment_lock);
	}
 out:
	return err;
}

void nilfs_set_log_cursor(struct nilfs_super_block *sbp,
			  struct the_nilfs *nilfs)
{
	sector_t nfreeblocks;

	/* nilfs->ns_sem must be locked by the caller. */
	nilfs_count_free_blocks(nilfs, &nfreeblocks);
	sbp->s_free_blocks_count = cpu_to_le64(nfreeblocks);

	spin_lock(&nilfs->ns_last_segment_lock);
	sbp->s_last_seq = cpu_to_le64(nilfs->ns_last_seq);
	sbp->s_last_pseg = cpu_to_le64(nilfs->ns_last_pseg);
	sbp->s_last_cno = cpu_to_le64(nilfs->ns_last_cno);
	spin_unlock(&nilfs->ns_last_segment_lock);
}

struct nilfs_super_block **nilfs_prepare_super(struct nilfs_sb_info *sbi,
					       int flip)
{
	struct the_nilfs *nilfs = sbi->s_nilfs;
	struct nilfs_super_block **sbp = nilfs->ns_sbp;

	/* nilfs->ns_sem must be locked by the caller. */
	if (sbp[0]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) {
		if (sbp[1] &&
		    sbp[1]->s_magic == cpu_to_le16(NILFS_SUPER_MAGIC)) {
			memcpy(sbp[0], sbp[1], nilfs->ns_sbsize);
		} else {
			printk(KERN_CRIT "NILFS: superblock broke on dev %s\n",
			       sbi->s_super->s_id);
			return NULL;
		}
	} else if (sbp[1] &&
		   sbp[1]->s_magic != cpu_to_le16(NILFS_SUPER_MAGIC)) {
			memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
	}

	if (flip && sbp[1])
		nilfs_swap_super_block(nilfs);

	return sbp;
}

int nilfs_commit_super(struct nilfs_sb_info *sbi, int flag)
{
	struct the_nilfs *nilfs = sbi->s_nilfs;
	struct nilfs_super_block **sbp = nilfs->ns_sbp;
	time_t t;

	/* nilfs->ns_sem must be locked by the caller. */
	t = get_seconds();
	nilfs->ns_sbwtime = t;
	sbp[0]->s_wtime = cpu_to_le64(t);
	sbp[0]->s_sum = 0;
	sbp[0]->s_sum = cpu_to_le32(crc32_le(nilfs->ns_crc_seed,
					     (unsigned char *)sbp[0],
					     nilfs->ns_sbsize));
	if (flag == NILFS_SB_COMMIT_ALL && sbp[1]) {
		sbp[1]->s_wtime = sbp[0]->s_wtime;
		sbp[1]->s_sum = 0;
		sbp[1]->s_sum = cpu_to_le32(crc32_le(nilfs->ns_crc_seed,
					    (unsigned char *)sbp[1],
					    nilfs->ns_sbsize));
	}
	clear_nilfs_sb_dirty(nilfs);
	return nilfs_sync_super(sbi, flag);
}

/**
 * nilfs_cleanup_super() - write filesystem state for cleanup
 * @sbi: nilfs_sb_info to be unmounted or degraded to read-only
 *
 * This function restores state flags in the on-disk super block.
 * This will set "clean" flag (i.e. NILFS_VALID_FS) unless the
 * filesystem was not clean previously.
 */
int nilfs_cleanup_super(struct nilfs_sb_info *sbi)
{
	struct nilfs_super_block **sbp;
	int flag = NILFS_SB_COMMIT;
	int ret = -EIO;

	sbp = nilfs_prepare_super(sbi, 0);
	if (sbp) {
		sbp[0]->s_state = cpu_to_le16(sbi->s_nilfs->ns_mount_state);
		nilfs_set_log_cursor(sbp[0], sbi->s_nilfs);
		if (sbp[1] && sbp[0]->s_last_cno == sbp[1]->s_last_cno) {
			/*
			 * make the "clean" flag also to the opposite
			 * super block if both super blocks point to
			 * the same checkpoint.
			 */
			sbp[1]->s_state = sbp[0]->s_state;
			flag = NILFS_SB_COMMIT_ALL;
		}
		ret = nilfs_commit_super(sbi, flag);
	}
	return ret;
}

static void nilfs_put_super(struct super_block *sb)
{
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	struct the_nilfs *nilfs = sbi->s_nilfs;

	nilfs_detach_segment_constructor(sbi);

	if (!(sb->s_flags & MS_RDONLY)) {
		down_write(&nilfs->ns_sem);
		nilfs_cleanup_super(sbi);
		up_write(&nilfs->ns_sem);
	}

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

static int nilfs_sync_fs(struct super_block *sb, int wait)
{
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	struct the_nilfs *nilfs = sbi->s_nilfs;
	struct nilfs_super_block **sbp;
	int err = 0;

	/* This function is called when super block should be written back */
	if (wait)
		err = nilfs_construct_segment(sb);

	down_write(&nilfs->ns_sem);
	if (nilfs_sb_dirty(nilfs)) {
		sbp = nilfs_prepare_super(sbi, nilfs_sb_will_flip(nilfs));
		if (likely(sbp)) {
			nilfs_set_log_cursor(sbp[0], nilfs);
			nilfs_commit_super(sbi, NILFS_SB_COMMIT);
		}
	}
	up_write(&nilfs->ns_sem);

	return err;
}

int nilfs_attach_checkpoint(struct nilfs_sb_info *sbi, __u64 cno, int curr_mnt,
			    struct nilfs_root **rootp)
{
	struct the_nilfs *nilfs = sbi->s_nilfs;
	struct nilfs_root *root;
	struct nilfs_checkpoint *raw_cp;
	struct buffer_head *bh_cp;
	int err = -ENOMEM;

	root = nilfs_find_or_create_root(
		nilfs, curr_mnt ? NILFS_CPTREE_CURRENT_CNO : cno);
	if (!root)
		return err;

	if (root->ifile)
		goto reuse; /* already attached checkpoint */

	root->ifile = nilfs_ifile_new(sbi, nilfs->ns_inode_size);
	if (!root->ifile)
		goto failed;

	down_read(&nilfs->ns_segctor_sem);
	err = nilfs_cpfile_get_checkpoint(nilfs->ns_cpfile, cno, 0, &raw_cp,
					  &bh_cp);
	up_read(&nilfs->ns_segctor_sem);
	if (unlikely(err)) {
		if (err == -ENOENT || err == -EINVAL) {
			printk(KERN_ERR
			       "NILFS: Invalid checkpoint "
			       "(checkpoint number=%llu)\n",
			       (unsigned long long)cno);
			err = -EINVAL;
		}
		goto failed;
	}
	err = nilfs_read_inode_common(root->ifile, &raw_cp->cp_ifile_inode);
	if (unlikely(err))
		goto failed_bh;

	atomic_set(&root->inodes_count, le64_to_cpu(raw_cp->cp_inodes_count));
	atomic_set(&root->blocks_count, le64_to_cpu(raw_cp->cp_blocks_count));

	nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, cno, bh_cp);

 reuse:
	*rootp = root;
	return 0;

 failed_bh:
	nilfs_cpfile_put_checkpoint(nilfs->ns_cpfile, cno, bh_cp);
 failed:
	nilfs_put_root(root);

	return err;
}

static int nilfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct super_block *sb = dentry->d_sb;
	struct nilfs_root *root = NILFS_I(dentry->d_inode)->i_root;
	struct the_nilfs *nilfs = root->nilfs;
	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
	unsigned long long blocks;
	unsigned long overhead;
	unsigned long nrsvblocks;
	sector_t nfreeblocks;
	int err;

	/*
	 * Compute all of the segment blocks
	 *
	 * The blocks before first segment and after last segment
	 * are excluded.
	 */
	blocks = nilfs->ns_blocks_per_segment * nilfs->ns_nsegments
		- nilfs->ns_first_data_block;
	nrsvblocks = nilfs->ns_nrsvsegs * nilfs->ns_blocks_per_segment;

	/*
	 * Compute the overhead
	 *
	 * When distributing meta data blocks outside segment structure,
	 * We must count them as the overhead.
	 */
	overhead = 0;

	err = nilfs_count_free_blocks(nilfs, &nfreeblocks);
	if (unlikely(err))
		return err;

	buf->f_type = NILFS_SUPER_MAGIC;
	buf->f_bsize = sb->s_blocksize;
	buf->f_blocks = blocks - overhead;
	buf->f_bfree = nfreeblocks;
	buf->f_bavail = (buf->f_bfree >= nrsvblocks) ?
		(buf->f_bfree - nrsvblocks) : 0;
	buf->f_files = atomic_read(&root->inodes_count);
	buf->f_ffree = 0; /* nilfs_count_free_inodes(sb); */
	buf->f_namelen = NILFS_NAME_LEN;
	buf->f_fsid.val[0] = (u32)id;
	buf->f_fsid.val[1] = (u32)(id >> 32);

	return 0;
}

static int nilfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
{
	struct super_block *sb = vfs->mnt_sb;
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	struct nilfs_root *root = NILFS_I(vfs->mnt_root->d_inode)->i_root;

	if (!nilfs_test_opt(sbi, BARRIER))
		seq_puts(seq, ",nobarrier");
	if (root->cno != NILFS_CPTREE_CURRENT_CNO)
		seq_printf(seq, ",cp=%llu", (unsigned long long)root->cno);
	if (nilfs_test_opt(sbi, ERRORS_PANIC))
		seq_puts(seq, ",errors=panic");
	if (nilfs_test_opt(sbi, ERRORS_CONT))
		seq_puts(seq, ",errors=continue");
	if (nilfs_test_opt(sbi, STRICT_ORDER))
		seq_puts(seq, ",order=strict");
	if (nilfs_test_opt(sbi, NORECOVERY))
		seq_puts(seq, ",norecovery");
	if (nilfs_test_opt(sbi, DISCARD))
		seq_puts(seq, ",discard");

	return 0;
}

static const struct super_operations nilfs_sops = {
	.alloc_inode    = nilfs_alloc_inode,
	.destroy_inode  = nilfs_destroy_inode,
	.dirty_inode    = nilfs_dirty_inode,
	/* .write_inode    = nilfs_write_inode, */
	/* .put_inode      = nilfs_put_inode, */
	/* .drop_inode	  = nilfs_drop_inode, */
	.evict_inode    = nilfs_evict_inode,
	.put_super      = nilfs_put_super,
	/* .write_super    = nilfs_write_super, */
	.sync_fs        = nilfs_sync_fs,
	/* .write_super_lockfs */
	/* .unlockfs */
	.statfs         = nilfs_statfs,
	.remount_fs     = nilfs_remount,
	/* .umount_begin */
	.show_options = nilfs_show_options
};

enum {
	Opt_err_cont, Opt_err_panic, Opt_err_ro,
	Opt_barrier, Opt_nobarrier, Opt_snapshot, Opt_order, Opt_norecovery,
	Opt_discard, Opt_nodiscard, Opt_err,
};

static match_table_t tokens = {
	{Opt_err_cont, "errors=continue"},
	{Opt_err_panic, "errors=panic"},
	{Opt_err_ro, "errors=remount-ro"},
	{Opt_barrier, "barrier"},
	{Opt_nobarrier, "nobarrier"},
	{Opt_snapshot, "cp=%u"},
	{Opt_order, "order=%s"},
	{Opt_norecovery, "norecovery"},
	{Opt_discard, "discard"},
	{Opt_nodiscard, "nodiscard"},
	{Opt_err, NULL}
};

static int parse_options(char *options, struct super_block *sb, int is_remount)
{
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	char *p;
	substring_t args[MAX_OPT_ARGS];
	int option;

	if (!options)
		return 1;

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

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_barrier:
			nilfs_set_opt(sbi, BARRIER);
			break;
		case Opt_nobarrier:
			nilfs_clear_opt(sbi, BARRIER);
			break;
		case Opt_order:
			if (strcmp(args[0].from, "relaxed") == 0)
				/* Ordered data semantics */
				nilfs_clear_opt(sbi, STRICT_ORDER);
			else if (strcmp(args[0].from, "strict") == 0)
				/* Strict in-order semantics */
				nilfs_set_opt(sbi, STRICT_ORDER);
			else
				return 0;
			break;
		case Opt_err_panic:
			nilfs_write_opt(sbi, ERROR_MODE, ERRORS_PANIC);
			break;
		case Opt_err_ro:
			nilfs_write_opt(sbi, ERROR_MODE, ERRORS_RO);
			break;
		case Opt_err_cont:
			nilfs_write_opt(sbi, ERROR_MODE, ERRORS_CONT);
			break;
		case Opt_snapshot:
			if (match_int(&args[0], &option) || option <= 0)
				return 0;
			if (is_remount) {
				printk(KERN_ERR
				       "NILFS: \"%s\" option is invalid "
				       "for remount.\n", p);
				return 0;
			}
			break;
		case Opt_norecovery:
			nilfs_set_opt(sbi, NORECOVERY);
			break;
		case Opt_discard:
			nilfs_set_opt(sbi, DISCARD);
			break;
		case Opt_nodiscard:
			nilfs_clear_opt(sbi, DISCARD);
			break;
		default:
			printk(KERN_ERR
			       "NILFS: Unrecognized mount option \"%s\"\n", p);
			return 0;
		}
	}
	return 1;
}

static inline void
nilfs_set_default_options(struct nilfs_sb_info *sbi,
			  struct nilfs_super_block *sbp)
{
	sbi->s_mount_opt =
		NILFS_MOUNT_ERRORS_RO | NILFS_MOUNT_BARRIER;
}

static int nilfs_setup_super(struct nilfs_sb_info *sbi)
{
	struct the_nilfs *nilfs = sbi->s_nilfs;
	struct nilfs_super_block **sbp;
	int max_mnt_count;
	int mnt_count;

	/* nilfs->ns_sem must be locked by the caller. */
	sbp = nilfs_prepare_super(sbi, 0);
	if (!sbp)
		return -EIO;

	max_mnt_count = le16_to_cpu(sbp[0]->s_max_mnt_count);
	mnt_count = le16_to_cpu(sbp[0]->s_mnt_count);

	if (nilfs->ns_mount_state & NILFS_ERROR_FS) {
		printk(KERN_WARNING
		       "NILFS warning: mounting fs with errors\n");
#if 0
	} else if (max_mnt_count >= 0 && mnt_count >= max_mnt_count) {
		printk(KERN_WARNING
		       "NILFS warning: maximal mount count reached\n");
#endif
	}
	if (!max_mnt_count)
		sbp[0]->s_max_mnt_count = cpu_to_le16(NILFS_DFL_MAX_MNT_COUNT);

	sbp[0]->s_mnt_count = cpu_to_le16(mnt_count + 1);
	sbp[0]->s_state =
		cpu_to_le16(le16_to_cpu(sbp[0]->s_state) & ~NILFS_VALID_FS);
	sbp[0]->s_mtime = cpu_to_le64(get_seconds());
	/* synchronize sbp[1] with sbp[0] */
	memcpy(sbp[1], sbp[0], nilfs->ns_sbsize);
	return nilfs_commit_super(sbi, NILFS_SB_COMMIT_ALL);
}

struct nilfs_super_block *nilfs_read_super_block(struct super_block *sb,
						 u64 pos, int blocksize,
						 struct buffer_head **pbh)
{
	unsigned long long sb_index = pos;
	unsigned long offset;

	offset = do_div(sb_index, blocksize);
	*pbh = sb_bread(sb, sb_index);
	if (!*pbh)
		return NULL;
	return (struct nilfs_super_block *)((char *)(*pbh)->b_data + offset);
}

int nilfs_store_magic_and_option(struct super_block *sb,
				 struct nilfs_super_block *sbp,
				 char *data)
{
	struct nilfs_sb_info *sbi = NILFS_SB(sb);

	sb->s_magic = le16_to_cpu(sbp->s_magic);

	/* FS independent flags */
#ifdef NILFS_ATIME_DISABLE
	sb->s_flags |= MS_NOATIME;
#endif

	nilfs_set_default_options(sbi, sbp);

	sbi->s_resuid = le16_to_cpu(sbp->s_def_resuid);
	sbi->s_resgid = le16_to_cpu(sbp->s_def_resgid);
	sbi->s_interval = le32_to_cpu(sbp->s_c_interval);
	sbi->s_watermark = le32_to_cpu(sbp->s_c_block_max);

	return !parse_options(data, sb, 0) ? -EINVAL : 0 ;
}

int nilfs_check_feature_compatibility(struct super_block *sb,
				      struct nilfs_super_block *sbp)
{
	__u64 features;

	features = le64_to_cpu(sbp->s_feature_incompat) &
		~NILFS_FEATURE_INCOMPAT_SUPP;
	if (features) {
		printk(KERN_ERR "NILFS: couldn't mount because of unsupported "
		       "optional features (%llx)\n",
		       (unsigned long long)features);
		return -EINVAL;
	}
	features = le64_to_cpu(sbp->s_feature_compat_ro) &
		~NILFS_FEATURE_COMPAT_RO_SUPP;
	if (!(sb->s_flags & MS_RDONLY) && features) {
		printk(KERN_ERR "NILFS: couldn't mount RDWR because of "
		       "unsupported optional features (%llx)\n",
		       (unsigned long long)features);
		return -EINVAL;
	}
	return 0;
}

static int nilfs_get_root_dentry(struct super_block *sb,
				 struct nilfs_root *root,
				 struct dentry **root_dentry)
{
	struct inode *inode;
	struct dentry *dentry;
	int ret = 0;

	inode = nilfs_iget(sb, root, NILFS_ROOT_INO);
	if (IS_ERR(inode)) {
		printk(KERN_ERR "NILFS: get root inode failed\n");
		ret = PTR_ERR(inode);
		goto out;
	}
	if (!S_ISDIR(inode->i_mode) || !inode->i_blocks || !inode->i_size) {
		iput(inode);
		printk(KERN_ERR "NILFS: corrupt root inode.\n");
		ret = -EINVAL;
		goto out;
	}

	if (root->cno == NILFS_CPTREE_CURRENT_CNO) {
		dentry = d_find_alias(inode);
		if (!dentry) {
			dentry = d_alloc_root(inode);
			if (!dentry) {
				iput(inode);
				ret = -ENOMEM;
				goto failed_dentry;
			}
		} else {
			iput(inode);
		}
	} else {
		dentry = d_obtain_alias(inode);
		if (IS_ERR(dentry)) {
			ret = PTR_ERR(dentry);
			goto failed_dentry;
		}
	}
	*root_dentry = dentry;
 out:
	return ret;

 failed_dentry:
	printk(KERN_ERR "NILFS: get root dentry failed\n");
	goto out;
}

static int nilfs_attach_snapshot(struct super_block *s, __u64 cno,
				 struct dentry **root_dentry)
{
	struct the_nilfs *nilfs = NILFS_SB(s)->s_nilfs;
	struct nilfs_root *root;
	int ret;

	down_read(&nilfs->ns_segctor_sem);
	ret = nilfs_cpfile_is_snapshot(nilfs->ns_cpfile, cno);
	up_read(&nilfs->ns_segctor_sem);
	if (ret < 0) {
		ret = (ret == -ENOENT) ? -EINVAL : ret;
		goto out;
	} else if (!ret) {
		printk(KERN_ERR "NILFS: The specified checkpoint is "
		       "not a snapshot (checkpoint number=%llu).\n",
		       (unsigned long long)cno);
		ret = -EINVAL;
		goto out;
	}

	ret = nilfs_attach_checkpoint(NILFS_SB(s), cno, false, &root);
	if (ret) {
		printk(KERN_ERR "NILFS: error loading snapshot "
		       "(checkpoint number=%llu).\n",
	       (unsigned long long)cno);
		goto out;
	}
	ret = nilfs_get_root_dentry(s, root, root_dentry);
	nilfs_put_root(root);
 out:
	return ret;
}

static int nilfs_tree_was_touched(struct dentry *root_dentry)
{
	return atomic_read(&root_dentry->d_count) > 1;
}

/**
 * nilfs_try_to_shrink_tree() - try to shrink dentries of a checkpoint
 * @root_dentry: root dentry of the tree to be shrunk
 *
 * This function returns true if the tree was in-use.
 */
static int nilfs_try_to_shrink_tree(struct dentry *root_dentry)
{
	if (have_submounts(root_dentry))
		return true;
	shrink_dcache_parent(root_dentry);
	return nilfs_tree_was_touched(root_dentry);
}

/**
 * nilfs_fill_super() - initialize a super block instance
 * @sb: super_block
 * @data: mount options
 * @silent: silent mode flag
 *
 * This function is called exclusively by nilfs->ns_mount_mutex.
 * So, the recovery process is protected from other simultaneous mounts.
 */
static int
nilfs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct the_nilfs *nilfs;
	struct nilfs_sb_info *sbi;
	struct nilfs_root *fsroot;
	__u64 cno;
	int err;

	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
	if (!sbi)
		return -ENOMEM;

	sb->s_fs_info = sbi;
	sbi->s_super = sb;

	nilfs = alloc_nilfs(sb->s_bdev);
	if (!nilfs) {
		err = -ENOMEM;
		goto failed_sbi;
	}
	sbi->s_nilfs = nilfs;

	err = init_nilfs(nilfs, sbi, (char *)data);
	if (err)
		goto failed_nilfs;

	spin_lock_init(&sbi->s_inode_lock);
	INIT_LIST_HEAD(&sbi->s_dirty_files);

	/*
	 * Following initialization is overlapped because
	 * nilfs_sb_info structure has been cleared at the beginning.
	 * But we reserve them to keep our interest and make ready
	 * for the future change.
	 */
	get_random_bytes(&sbi->s_next_generation,
			 sizeof(sbi->s_next_generation));
	spin_lock_init(&sbi->s_next_gen_lock);

	sb->s_op = &nilfs_sops;
	sb->s_export_op = &nilfs_export_ops;
	sb->s_root = NULL;
	sb->s_time_gran = 1;
	sb->s_bdi = nilfs->ns_bdi;

	err = load_nilfs(nilfs, sbi);
	if (err)
		goto failed_nilfs;

	cno = nilfs_last_cno(nilfs);
	err = nilfs_attach_checkpoint(sbi, cno, true, &fsroot);
	if (err) {
		printk(KERN_ERR "NILFS: error loading last checkpoint "
		       "(checkpoint number=%llu).\n", (unsigned long long)cno);
		goto failed_nilfs;
	}

	if (!(sb->s_flags & MS_RDONLY)) {
		err = nilfs_attach_segment_constructor(sbi, fsroot);
		if (err)
			goto failed_checkpoint;
	}

	err = nilfs_get_root_dentry(sb, fsroot, &sb->s_root);
	if (err)
		goto failed_segctor;

	nilfs_put_root(fsroot);

	if (!(sb->s_flags & MS_RDONLY)) {
		down_write(&nilfs->ns_sem);
		nilfs_setup_super(sbi);
		up_write(&nilfs->ns_sem);
	}

	return 0;

 failed_segctor:
	nilfs_detach_segment_constructor(sbi);

 failed_checkpoint:
	nilfs_put_root(fsroot);

 failed_nilfs:
	destroy_nilfs(nilfs);

 failed_sbi:
	sb->s_fs_info = NULL;
	kfree(sbi);
	return err;
}

static int nilfs_remount(struct super_block *sb, int *flags, char *data)
{
	struct nilfs_sb_info *sbi = NILFS_SB(sb);
	struct the_nilfs *nilfs = sbi->s_nilfs;
	unsigned long old_sb_flags;
	struct nilfs_mount_options old_opts;
	int err;

	old_sb_flags = sb->s_flags;
	old_opts.mount_opt = sbi->s_mount_opt;

	if (!parse_options(data, sb, 1)) {
		err = -EINVAL;
		goto restore_opts;
	}
	sb->s_flags = (sb->s_flags & ~MS_POSIXACL);

	err = -EINVAL;

	if (!nilfs_valid_fs(nilfs)) {
		printk(KERN_WARNING "NILFS (device %s): couldn't "
		       "remount because the filesystem is in an "
		       "incomplete recovery state.\n", sb->s_id);
		goto restore_opts;
	}

	if ((*flags & MS_RDONLY) == (sb->s_flags & MS_RDONLY))
		goto out;
	if (*flags & MS_RDONLY) {
		/* Shutting down the segment constructor */
		nilfs_detach_segment_constructor(sbi);
		sb->s_flags |= MS_RDONLY;

		/*
		 * Remounting a valid RW partition RDONLY, so set
		 * the RDONLY flag and then mark the partition as valid again.
		 */
		down_write(&nilfs->ns_sem);
		nilfs_cleanup_super(sbi);
		up_write(&nilfs->ns_sem);
	} else {
		__u64 features;
		struct nilfs_root *root;

		/*
		 * Mounting a RDONLY partition read-write, so reread and
		 * store the current valid flag.  (It may have been changed
		 * by fsck since we originally mounted the partition.)
		 */
		down_read(&nilfs->ns_sem);
		features = le64_to_cpu(nilfs->ns_sbp[0]->s_feature_compat_ro) &
			~NILFS_FEATURE_COMPAT_RO_SUPP;
		up_read(&nilfs->ns_sem);
		if (features) {
			printk(KERN_WARNING "NILFS (device %s): couldn't "
			       "remount RDWR because of unsupported optional "
			       "features (%llx)\n",
			       sb->s_id, (unsigned long long)features);
			err = -EROFS;
			goto restore_opts;
		}

		sb->s_flags &= ~MS_RDONLY;

		root = NILFS_I(sb->s_root->d_inode)->i_root;
		err = nilfs_attach_segment_constructor(sbi, root);
		if (err)
			goto restore_opts;

		down_write(&nilfs->ns_sem);
		nilfs_setup_super(sbi);
		up_write(&nilfs->ns_sem);
	}
 out:
	return 0;

 restore_opts:
	sb->s_flags = old_sb_flags;
	sbi->s_mount_opt = old_opts.mount_opt;
	return err;
}

struct nilfs_super_data {
	struct block_device *bdev;
	struct nilfs_sb_info *sbi;
	__u64 cno;
	int flags;
};

/**
 * nilfs_identify - pre-read mount options needed to identify mount instance
 * @data: mount options
 * @sd: nilfs_super_data
 */
static int nilfs_identify(char *data, struct nilfs_super_data *sd)
{
	char *p, *options = data;
	substring_t args[MAX_OPT_ARGS];
	int option, token;
	int ret = 0;

	do {
		p = strsep(&options, ",");
		if (p != NULL && *p) {
			token = match_token(p, tokens, args);
			if (token == Opt_snapshot) {
				if (!(sd->flags & MS_RDONLY))
					ret++;
				else {
					ret = match_int(&args[0], &option);
					if (!ret) {
						if (option > 0)
							sd->cno = option;
						else
							ret++;
					}
				}
			}
			if (ret)
				printk(KERN_ERR
				       "NILFS: invalid mount option: %s\n", p);
		}
		if (!options)
			break;
		BUG_ON(options == data);
		*(options - 1) = ',';
	} while (!ret);
	return ret;
}

static int nilfs_set_bdev_super(struct super_block *s, void *data)
{
	s->s_bdev = data;
	s->s_dev = s->s_bdev->bd_dev;
	return 0;
}

static int nilfs_test_bdev_super(struct super_block *s, void *data)
{
	return (void *)s->s_bdev == data;
}

static int
nilfs_get_sb(struct file_system_type *fs_type, int flags,
	     const char *dev_name, void *data, struct vfsmount *mnt)
{
	struct nilfs_super_data sd;
	struct super_block *s;
	fmode_t mode = FMODE_READ;
	struct dentry *root_dentry;
	int err, s_new = false;

	if (!(flags & MS_RDONLY))
		mode |= FMODE_WRITE;

	sd.bdev = open_bdev_exclusive(dev_name, mode, fs_type);
	if (IS_ERR(sd.bdev))
		return PTR_ERR(sd.bdev);

	sd.cno = 0;
	sd.flags = flags;
	if (nilfs_identify((char *)data, &sd)) {
		err = -EINVAL;
		goto failed;
	}

	s = sget(fs_type, nilfs_test_bdev_super, nilfs_set_bdev_super, sd.bdev);
	if (IS_ERR(s)) {
		err = PTR_ERR(s);
		goto failed;
	}

	if (!s->s_root) {
		char b[BDEVNAME_SIZE];

		s_new = true;

		/* New superblock instance created */
		s->s_flags = flags;
		s->s_mode = mode;
		strlcpy(s->s_id, bdevname(sd.bdev, b), sizeof(s->s_id));
		sb_set_blocksize(s, block_size(sd.bdev));

		err = nilfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0);
		if (err)
			goto failed_super;

		s->s_flags |= MS_ACTIVE;
	} else if (!sd.cno) {
		int busy = false;

		if (nilfs_tree_was_touched(s->s_root)) {
			busy = nilfs_try_to_shrink_tree(s->s_root);
			if (busy && (flags ^ s->s_flags) & MS_RDONLY) {
				printk(KERN_ERR "NILFS: the device already "
				       "has a %s mount.\n",
				       (s->s_flags & MS_RDONLY) ?
				       "read-only" : "read/write");
				err = -EBUSY;
				goto failed_super;
			}
		}
		if (!busy) {
			/*
			 * Try remount to setup mount states if the current
			 * tree is not mounted and only snapshots use this sb.
			 */
			err = nilfs_remount(s, &flags, data);
			if (err)
				goto failed_super;
		}
	}

	if (sd.cno) {
		err = nilfs_attach_snapshot(s, sd.cno, &root_dentry);
		if (err)
			goto failed_super;
	} else {
		root_dentry = dget(s->s_root);
	}

	if (!s_new)
		close_bdev_exclusive(sd.bdev, mode);

	mnt->mnt_sb = s;
	mnt->mnt_root = root_dentry;
	return 0;

 failed_super:
	deactivate_locked_super(s);

 failed:
	if (!s_new)
		close_bdev_exclusive(sd.bdev, mode);
	return err;
}

struct file_system_type nilfs_fs_type = {
	.owner    = THIS_MODULE,
	.name     = "nilfs2",
	.get_sb   = nilfs_get_sb,
	.kill_sb  = kill_block_super,
	.fs_flags = FS_REQUIRES_DEV,
};

static void nilfs_inode_init_once(void *obj)
{
	struct nilfs_inode_info *ii = obj;

	INIT_LIST_HEAD(&ii->i_dirty);
#ifdef CONFIG_NILFS_XATTR
	init_rwsem(&ii->xattr_sem);
#endif
	nilfs_btnode_cache_init_once(&ii->i_btnode_cache);
	ii->i_bmap = &ii->i_bmap_data;
	inode_init_once(&ii->vfs_inode);
}

static void nilfs_segbuf_init_once(void *obj)
{
	memset(obj, 0, sizeof(struct nilfs_segment_buffer));
}

static void nilfs_destroy_cachep(void)
{
	if (nilfs_inode_cachep)
		kmem_cache_destroy(nilfs_inode_cachep);
	if (nilfs_transaction_cachep)
		kmem_cache_destroy(nilfs_transaction_cachep);
	if (nilfs_segbuf_cachep)
		kmem_cache_destroy(nilfs_segbuf_cachep);
	if (nilfs_btree_path_cache)
		kmem_cache_destroy(nilfs_btree_path_cache);
}

static int __init nilfs_init_cachep(void)
{
	nilfs_inode_cachep = kmem_cache_create("nilfs2_inode_cache",
			sizeof(struct nilfs_inode_info), 0,
			SLAB_RECLAIM_ACCOUNT, nilfs_inode_init_once);
	if (!nilfs_inode_cachep)
		goto fail;

	nilfs_transaction_cachep = kmem_cache_create("nilfs2_transaction_cache",
			sizeof(struct nilfs_transaction_info), 0,
			SLAB_RECLAIM_ACCOUNT, NULL);
	if (!nilfs_transaction_cachep)
		goto fail;

	nilfs_segbuf_cachep = kmem_cache_create("nilfs2_segbuf_cache",
			sizeof(struct nilfs_segment_buffer), 0,
			SLAB_RECLAIM_ACCOUNT, nilfs_segbuf_init_once);
	if (!nilfs_segbuf_cachep)
		goto fail;

	nilfs_btree_path_cache = kmem_cache_create("nilfs2_btree_path_cache",
			sizeof(struct nilfs_btree_path) * NILFS_BTREE_LEVEL_MAX,
			0, 0, NULL);
	if (!nilfs_btree_path_cache)
		goto fail;

	return 0;

fail:
	nilfs_destroy_cachep();
	return -ENOMEM;
}

static int __init init_nilfs_fs(void)
{
	int err;

	err = nilfs_init_cachep();
	if (err)
		goto fail;

	err = register_filesystem(&nilfs_fs_type);
	if (err)
		goto free_cachep;

	printk(KERN_INFO "NILFS version 2 loaded\n");
	return 0;

free_cachep:
	nilfs_destroy_cachep();
fail:
	return err;
}

static void __exit exit_nilfs_fs(void)
{
	nilfs_destroy_cachep();
	unregister_filesystem(&nilfs_fs_type);
}

module_init(init_nilfs_fs)
module_exit(exit_nilfs_fs)