aboutsummaryrefslogtreecommitdiff
path: root/fs/nilfs2/inode.c
blob: ba7a1da7634b2a19a7a01da2dba9712fd6e2971b (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
/*
 * inode.c - NILFS inode operations.
 *
 * 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>
 *
 */

#include <linux/buffer_head.h>
#include <linux/gfp.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/uio.h>
#include "nilfs.h"
#include "btnode.h"
#include "segment.h"
#include "page.h"
#include "mdt.h"
#include "cpfile.h"
#include "ifile.h"

/**
 * struct nilfs_iget_args - arguments used during comparison between inodes
 * @ino: inode number
 * @cno: checkpoint number
 * @root: pointer on NILFS root object (mounted checkpoint)
 * @for_gc: inode for GC flag
 */
struct nilfs_iget_args {
	u64 ino;
	__u64 cno;
	struct nilfs_root *root;
	int for_gc;
};

void nilfs_inode_add_blocks(struct inode *inode, int n)
{
	struct nilfs_root *root = NILFS_I(inode)->i_root;

	inode_add_bytes(inode, (1 << inode->i_blkbits) * n);
	if (root)
		atomic_add(n, &root->blocks_count);
}

void nilfs_inode_sub_blocks(struct inode *inode, int n)
{
	struct nilfs_root *root = NILFS_I(inode)->i_root;

	inode_sub_bytes(inode, (1 << inode->i_blkbits) * n);
	if (root)
		atomic_sub(n, &root->blocks_count);
}

/**
 * nilfs_get_block() - get a file block on the filesystem (callback function)
 * @inode - inode struct of the target file
 * @blkoff - file block number
 * @bh_result - buffer head to be mapped on
 * @create - indicate whether allocating the block or not when it has not
 *      been allocated yet.
 *
 * This function does not issue actual read request of the specified data
 * block. It is done by VFS.
 */
int nilfs_get_block(struct inode *inode, sector_t blkoff,
		    struct buffer_head *bh_result, int create)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
	__u64 blknum = 0;
	int err = 0, ret;
	unsigned maxblocks = bh_result->b_size >> inode->i_blkbits;

	down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
	ret = nilfs_bmap_lookup_contig(ii->i_bmap, blkoff, &blknum, maxblocks);
	up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
	if (ret >= 0) {	/* found */
		map_bh(bh_result, inode->i_sb, blknum);
		if (ret > 0)
			bh_result->b_size = (ret << inode->i_blkbits);
		goto out;
	}
	/* data block was not found */
	if (ret == -ENOENT && create) {
		struct nilfs_transaction_info ti;

		bh_result->b_blocknr = 0;
		err = nilfs_transaction_begin(inode->i_sb, &ti, 1);
		if (unlikely(err))
			goto out;
		err = nilfs_bmap_insert(ii->i_bmap, (unsigned long)blkoff,
					(unsigned long)bh_result);
		if (unlikely(err != 0)) {
			if (err == -EEXIST) {
				/*
				 * The get_block() function could be called
				 * from multiple callers for an inode.
				 * However, the page having this block must
				 * be locked in this case.
				 */
				printk(KERN_WARNING
				       "nilfs_get_block: a race condition "
				       "while inserting a data block. "
				       "(inode number=%lu, file block "
				       "offset=%llu)\n",
				       inode->i_ino,
				       (unsigned long long)blkoff);
				err = 0;
			}
			nilfs_transaction_abort(inode->i_sb);
			goto out;
		}
		nilfs_mark_inode_dirty(inode);
		nilfs_transaction_commit(inode->i_sb); /* never fails */
		/* Error handling should be detailed */
		set_buffer_new(bh_result);
		set_buffer_delay(bh_result);
		map_bh(bh_result, inode->i_sb, 0); /* dbn must be changed
						      to proper value */
	} else if (ret == -ENOENT) {
		/* not found is not error (e.g. hole); must return without
		   the mapped state flag. */
		;
	} else {
		err = ret;
	}

 out:
	return err;
}

/**
 * nilfs_readpage() - implement readpage() method of nilfs_aops {}
 * address_space_operations.
 * @file - file struct of the file to be read
 * @page - the page to be read
 */
static int nilfs_readpage(struct file *file, struct page *page)
{
	return mpage_readpage(page, nilfs_get_block);
}

/**
 * nilfs_readpages() - implement readpages() method of nilfs_aops {}
 * address_space_operations.
 * @file - file struct of the file to be read
 * @mapping - address_space struct used for reading multiple pages
 * @pages - the pages to be read
 * @nr_pages - number of pages to be read
 */
static int nilfs_readpages(struct file *file, struct address_space *mapping,
			   struct list_head *pages, unsigned nr_pages)
{
	return mpage_readpages(mapping, pages, nr_pages, nilfs_get_block);
}

static int nilfs_writepages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	int err = 0;

	if (inode->i_sb->s_flags & MS_RDONLY) {
		nilfs_clear_dirty_pages(mapping, false);
		return -EROFS;
	}

	if (wbc->sync_mode == WB_SYNC_ALL)
		err = nilfs_construct_dsync_segment(inode->i_sb, inode,
						    wbc->range_start,
						    wbc->range_end);
	return err;
}

static int nilfs_writepage(struct page *page, struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	int err;

	if (inode && (inode->i_sb->s_flags & MS_RDONLY)) {
		/*
		 * It means that filesystem was remounted in read-only
		 * mode because of error or metadata corruption. But we
		 * have dirty pages that try to be flushed in background.
		 * So, here we simply discard this dirty page.
		 */
		nilfs_clear_dirty_page(page, false);
		unlock_page(page);
		return -EROFS;
	}

	redirty_page_for_writepage(wbc, page);
	unlock_page(page);

	if (wbc->sync_mode == WB_SYNC_ALL) {
		err = nilfs_construct_segment(inode->i_sb);
		if (unlikely(err))
			return err;
	} else if (wbc->for_reclaim)
		nilfs_flush_segment(inode->i_sb, inode->i_ino);

	return 0;
}

static int nilfs_set_page_dirty(struct page *page)
{
	int ret = __set_page_dirty_buffers(page);

	if (ret) {
		struct inode *inode = page->mapping->host;
		unsigned nr_dirty = 1 << (PAGE_SHIFT - inode->i_blkbits);

		nilfs_set_file_dirty(inode, nr_dirty);
	}
	return ret;
}

void nilfs_write_failed(struct address_space *mapping, loff_t to)
{
	struct inode *inode = mapping->host;

	if (to > inode->i_size) {
		truncate_pagecache(inode, to, inode->i_size);
		nilfs_truncate(inode);
	}
}

static int nilfs_write_begin(struct file *file, struct address_space *mapping,
			     loff_t pos, unsigned len, unsigned flags,
			     struct page **pagep, void **fsdata)

{
	struct inode *inode = mapping->host;
	int err = nilfs_transaction_begin(inode->i_sb, NULL, 1);

	if (unlikely(err))
		return err;

	err = block_write_begin(mapping, pos, len, flags, pagep,
				nilfs_get_block);
	if (unlikely(err)) {
		nilfs_write_failed(mapping, pos + len);
		nilfs_transaction_abort(inode->i_sb);
	}
	return err;
}

static int nilfs_write_end(struct file *file, struct address_space *mapping,
			   loff_t pos, unsigned len, unsigned copied,
			   struct page *page, void *fsdata)
{
	struct inode *inode = mapping->host;
	unsigned start = pos & (PAGE_CACHE_SIZE - 1);
	unsigned nr_dirty;
	int err;

	nr_dirty = nilfs_page_count_clean_buffers(page, start,
						  start + copied);
	copied = generic_write_end(file, mapping, pos, len, copied, page,
				   fsdata);
	nilfs_set_file_dirty(inode, nr_dirty);
	err = nilfs_transaction_commit(inode->i_sb);
	return err ? : copied;
}

static ssize_t
nilfs_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 address_space *mapping = file->f_mapping;
	struct inode *inode = file->f_mapping->host;
	ssize_t size;

	if (rw == WRITE)
		return 0;

	/* Needs synchronization with the cleaner */
	size = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
				  nilfs_get_block);

	/*
	 * In case of error extending write may have instantiated a few
	 * blocks outside i_size. Trim these off again.
	 */
	if (unlikely((rw & WRITE) && size < 0)) {
		loff_t isize = i_size_read(inode);
		loff_t end = offset + iov_length(iov, nr_segs);

		if (end > isize)
			nilfs_write_failed(mapping, end);
	}

	return size;
}

const struct address_space_operations nilfs_aops = {
	.writepage		= nilfs_writepage,
	.readpage		= nilfs_readpage,
	.writepages		= nilfs_writepages,
	.set_page_dirty		= nilfs_set_page_dirty,
	.readpages		= nilfs_readpages,
	.write_begin		= nilfs_write_begin,
	.write_end		= nilfs_write_end,
	/* .releasepage		= nilfs_releasepage, */
	.invalidatepage		= block_invalidatepage,
	.direct_IO		= nilfs_direct_IO,
	.is_partially_uptodate  = block_is_partially_uptodate,
};

struct inode *nilfs_new_inode(struct inode *dir, umode_t mode)
{
	struct super_block *sb = dir->i_sb;
	struct the_nilfs *nilfs = sb->s_fs_info;
	struct inode *inode;
	struct nilfs_inode_info *ii;
	struct nilfs_root *root;
	int err = -ENOMEM;
	ino_t ino;

	inode = new_inode(sb);
	if (unlikely(!inode))
		goto failed;

	mapping_set_gfp_mask(inode->i_mapping,
			     mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);

	root = NILFS_I(dir)->i_root;
	ii = NILFS_I(inode);
	ii->i_state = 1 << NILFS_I_NEW;
	ii->i_root = root;

	err = nilfs_ifile_create_inode(root->ifile, &ino, &ii->i_bh);
	if (unlikely(err))
		goto failed_ifile_create_inode;
	/* reference count of i_bh inherits from nilfs_mdt_read_block() */

	atomic_inc(&root->inodes_count);
	inode_init_owner(inode, dir, mode);
	inode->i_ino = ino;
	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;

	if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) {
		err = nilfs_bmap_read(ii->i_bmap, NULL);
		if (err < 0)
			goto failed_bmap;

		set_bit(NILFS_I_BMAP, &ii->i_state);
		/* No lock is needed; iget() ensures it. */
	}

	ii->i_flags = nilfs_mask_flags(
		mode, NILFS_I(dir)->i_flags & NILFS_FL_INHERITED);

	/* ii->i_file_acl = 0; */
	/* ii->i_dir_acl = 0; */
	ii->i_dir_start_lookup = 0;
	nilfs_set_inode_flags(inode);
	spin_lock(&nilfs->ns_next_gen_lock);
	inode->i_generation = nilfs->ns_next_generation++;
	spin_unlock(&nilfs->ns_next_gen_lock);
	insert_inode_hash(inode);

	err = nilfs_init_acl(inode, dir);
	if (unlikely(err))
		goto failed_acl; /* never occur. When supporting
				    nilfs_init_acl(), proper cancellation of
				    above jobs should be considered */

	return inode;

 failed_acl:
 failed_bmap:
	clear_nlink(inode);
	iput(inode);  /* raw_inode will be deleted through
			 generic_delete_inode() */
	goto failed;

 failed_ifile_create_inode:
	make_bad_inode(inode);
	iput(inode);  /* if i_nlink == 1, generic_forget_inode() will be
			 called */
 failed:
	return ERR_PTR(err);
}

void nilfs_set_inode_flags(struct inode *inode)
{
	unsigned int flags = NILFS_I(inode)->i_flags;

	inode->i_flags &= ~(S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME |
			    S_DIRSYNC);
	if (flags & FS_SYNC_FL)
		inode->i_flags |= S_SYNC;
	if (flags & FS_APPEND_FL)
		inode->i_flags |= S_APPEND;
	if (flags & FS_IMMUTABLE_FL)
		inode->i_flags |= S_IMMUTABLE;
	if (flags & FS_NOATIME_FL)
		inode->i_flags |= S_NOATIME;
	if (flags & FS_DIRSYNC_FL)
		inode->i_flags |= S_DIRSYNC;
	mapping_set_gfp_mask(inode->i_mapping,
			     mapping_gfp_mask(inode->i_mapping) & ~__GFP_FS);
}

int nilfs_read_inode_common(struct inode *inode,
			    struct nilfs_inode *raw_inode)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	int err;

	inode->i_mode = le16_to_cpu(raw_inode->i_mode);
	i_uid_write(inode, le32_to_cpu(raw_inode->i_uid));
	i_gid_write(inode, le32_to_cpu(raw_inode->i_gid));
	set_nlink(inode, le16_to_cpu(raw_inode->i_links_count));
	inode->i_size = le64_to_cpu(raw_inode->i_size);
	inode->i_atime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
	inode->i_ctime.tv_sec = le64_to_cpu(raw_inode->i_ctime);
	inode->i_mtime.tv_sec = le64_to_cpu(raw_inode->i_mtime);
	inode->i_atime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
	inode->i_ctime.tv_nsec = le32_to_cpu(raw_inode->i_ctime_nsec);
	inode->i_mtime.tv_nsec = le32_to_cpu(raw_inode->i_mtime_nsec);
	if (inode->i_nlink == 0 && inode->i_mode == 0)
		return -EINVAL; /* this inode is deleted */

	inode->i_blocks = le64_to_cpu(raw_inode->i_blocks);
	ii->i_flags = le32_to_cpu(raw_inode->i_flags);
#if 0
	ii->i_file_acl = le32_to_cpu(raw_inode->i_file_acl);
	ii->i_dir_acl = S_ISREG(inode->i_mode) ?
		0 : le32_to_cpu(raw_inode->i_dir_acl);
#endif
	ii->i_dir_start_lookup = 0;
	inode->i_generation = le32_to_cpu(raw_inode->i_generation);

	if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
	    S_ISLNK(inode->i_mode)) {
		err = nilfs_bmap_read(ii->i_bmap, raw_inode);
		if (err < 0)
			return err;
		set_bit(NILFS_I_BMAP, &ii->i_state);
		/* No lock is needed; iget() ensures it. */
	}
	return 0;
}

static int __nilfs_read_inode(struct super_block *sb,
			      struct nilfs_root *root, unsigned long ino,
			      struct inode *inode)
{
	struct the_nilfs *nilfs = sb->s_fs_info;
	struct buffer_head *bh;
	struct nilfs_inode *raw_inode;
	int err;

	down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
	err = nilfs_ifile_get_inode_block(root->ifile, ino, &bh);
	if (unlikely(err))
		goto bad_inode;

	raw_inode = nilfs_ifile_map_inode(root->ifile, ino, bh);

	err = nilfs_read_inode_common(inode, raw_inode);
	if (err)
		goto failed_unmap;

	if (S_ISREG(inode->i_mode)) {
		inode->i_op = &nilfs_file_inode_operations;
		inode->i_fop = &nilfs_file_operations;
		inode->i_mapping->a_ops = &nilfs_aops;
	} else if (S_ISDIR(inode->i_mode)) {
		inode->i_op = &nilfs_dir_inode_operations;
		inode->i_fop = &nilfs_dir_operations;
		inode->i_mapping->a_ops = &nilfs_aops;
	} else if (S_ISLNK(inode->i_mode)) {
		inode->i_op = &nilfs_symlink_inode_operations;
		inode->i_mapping->a_ops = &nilfs_aops;
	} else {
		inode->i_op = &nilfs_special_inode_operations;
		init_special_inode(
			inode, inode->i_mode,
			huge_decode_dev(le64_to_cpu(raw_inode->i_device_code)));
	}
	nilfs_ifile_unmap_inode(root->ifile, ino, bh);
	brelse(bh);
	up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
	nilfs_set_inode_flags(inode);
	return 0;

 failed_unmap:
	nilfs_ifile_unmap_inode(root->ifile, ino, bh);
	brelse(bh);

 bad_inode:
	up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
	return err;
}

static int nilfs_iget_test(struct inode *inode, void *opaque)
{
	struct nilfs_iget_args *args = opaque;
	struct nilfs_inode_info *ii;

	if (args->ino != inode->i_ino || args->root != NILFS_I(inode)->i_root)
		return 0;

	ii = NILFS_I(inode);
	if (!test_bit(NILFS_I_GCINODE, &ii->i_state))
		return !args->for_gc;

	return args->for_gc && args->cno == ii->i_cno;
}

static int nilfs_iget_set(struct inode *inode, void *opaque)
{
	struct nilfs_iget_args *args = opaque;

	inode->i_ino = args->ino;
	if (args->for_gc) {
		NILFS_I(inode)->i_state = 1 << NILFS_I_GCINODE;
		NILFS_I(inode)->i_cno = args->cno;
		NILFS_I(inode)->i_root = NULL;
	} else {
		if (args->root && args->ino == NILFS_ROOT_INO)
			nilfs_get_root(args->root);
		NILFS_I(inode)->i_root = args->root;
	}
	return 0;
}

struct inode *nilfs_ilookup(struct super_block *sb, struct nilfs_root *root,
			    unsigned long ino)
{
	struct nilfs_iget_args args = {
		.ino = ino, .root = root, .cno = 0, .for_gc = 0
	};

	return ilookup5(sb, ino, nilfs_iget_test, &args);
}

struct inode *nilfs_iget_locked(struct super_block *sb, struct nilfs_root *root,
				unsigned long ino)
{
	struct nilfs_iget_args args = {
		.ino = ino, .root = root, .cno = 0, .for_gc = 0
	};

	return iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
}

struct inode *nilfs_iget(struct super_block *sb, struct nilfs_root *root,
			 unsigned long ino)
{
	struct inode *inode;
	int err;

	inode = nilfs_iget_locked(sb, root, ino);
	if (unlikely(!inode))
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	err = __nilfs_read_inode(sb, root, ino, inode);
	if (unlikely(err)) {
		iget_failed(inode);
		return ERR_PTR(err);
	}
	unlock_new_inode(inode);
	return inode;
}

struct inode *nilfs_iget_for_gc(struct super_block *sb, unsigned long ino,
				__u64 cno)
{
	struct nilfs_iget_args args = {
		.ino = ino, .root = NULL, .cno = cno, .for_gc = 1
	};
	struct inode *inode;
	int err;

	inode = iget5_locked(sb, ino, nilfs_iget_test, nilfs_iget_set, &args);
	if (unlikely(!inode))
		return ERR_PTR(-ENOMEM);
	if (!(inode->i_state & I_NEW))
		return inode;

	err = nilfs_init_gcinode(inode);
	if (unlikely(err)) {
		iget_failed(inode);
		return ERR_PTR(err);
	}
	unlock_new_inode(inode);
	return inode;
}

void nilfs_write_inode_common(struct inode *inode,
			      struct nilfs_inode *raw_inode, int has_bmap)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);

	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
	raw_inode->i_uid = cpu_to_le32(i_uid_read(inode));
	raw_inode->i_gid = cpu_to_le32(i_gid_read(inode));
	raw_inode->i_links_count = cpu_to_le16(inode->i_nlink);
	raw_inode->i_size = cpu_to_le64(inode->i_size);
	raw_inode->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
	raw_inode->i_mtime = cpu_to_le64(inode->i_mtime.tv_sec);
	raw_inode->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
	raw_inode->i_mtime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
	raw_inode->i_blocks = cpu_to_le64(inode->i_blocks);

	raw_inode->i_flags = cpu_to_le32(ii->i_flags);
	raw_inode->i_generation = cpu_to_le32(inode->i_generation);

	if (NILFS_ROOT_METADATA_FILE(inode->i_ino)) {
		struct the_nilfs *nilfs = inode->i_sb->s_fs_info;

		/* zero-fill unused portion in the case of super root block */
		raw_inode->i_xattr = 0;
		raw_inode->i_pad = 0;
		memset((void *)raw_inode + sizeof(*raw_inode), 0,
		       nilfs->ns_inode_size - sizeof(*raw_inode));
	}

	if (has_bmap)
		nilfs_bmap_write(ii->i_bmap, raw_inode);
	else if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
		raw_inode->i_device_code =
			cpu_to_le64(huge_encode_dev(inode->i_rdev));
	/* When extending inode, nilfs->ns_inode_size should be checked
	   for substitutions of appended fields */
}

void nilfs_update_inode(struct inode *inode, struct buffer_head *ibh)
{
	ino_t ino = inode->i_ino;
	struct nilfs_inode_info *ii = NILFS_I(inode);
	struct inode *ifile = ii->i_root->ifile;
	struct nilfs_inode *raw_inode;

	raw_inode = nilfs_ifile_map_inode(ifile, ino, ibh);

	if (test_and_clear_bit(NILFS_I_NEW, &ii->i_state))
		memset(raw_inode, 0, NILFS_MDT(ifile)->mi_entry_size);
	set_bit(NILFS_I_INODE_DIRTY, &ii->i_state);

	nilfs_write_inode_common(inode, raw_inode, 0);
		/* XXX: call with has_bmap = 0 is a workaround to avoid
		   deadlock of bmap. This delays update of i_bmap to just
		   before writing */
	nilfs_ifile_unmap_inode(ifile, ino, ibh);
}

#define NILFS_MAX_TRUNCATE_BLOCKS	16384  /* 64MB for 4KB block */

static void nilfs_truncate_bmap(struct nilfs_inode_info *ii,
				unsigned long from)
{
	unsigned long b;
	int ret;

	if (!test_bit(NILFS_I_BMAP, &ii->i_state))
		return;
repeat:
	ret = nilfs_bmap_last_key(ii->i_bmap, &b);
	if (ret == -ENOENT)
		return;
	else if (ret < 0)
		goto failed;

	if (b < from)
		return;

	b -= min_t(unsigned long, NILFS_MAX_TRUNCATE_BLOCKS, b - from);
	ret = nilfs_bmap_truncate(ii->i_bmap, b);
	nilfs_relax_pressure_in_lock(ii->vfs_inode.i_sb);
	if (!ret || (ret == -ENOMEM &&
		     nilfs_bmap_truncate(ii->i_bmap, b) == 0))
		goto repeat;

failed:
	nilfs_warning(ii->vfs_inode.i_sb, __func__,
		      "failed to truncate bmap (ino=%lu, err=%d)",
		      ii->vfs_inode.i_ino, ret);
}

void nilfs_truncate(struct inode *inode)
{
	unsigned long blkoff;
	unsigned int blocksize;
	struct nilfs_transaction_info ti;
	struct super_block *sb = inode->i_sb;
	struct nilfs_inode_info *ii = NILFS_I(inode);

	if (!test_bit(NILFS_I_BMAP, &ii->i_state))
		return;
	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
		return;

	blocksize = sb->s_blocksize;
	blkoff = (inode->i_size + blocksize - 1) >> sb->s_blocksize_bits;
	nilfs_transaction_begin(sb, &ti, 0); /* never fails */

	block_truncate_page(inode->i_mapping, inode->i_size, nilfs_get_block);

	nilfs_truncate_bmap(ii, blkoff);

	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
	if (IS_SYNC(inode))
		nilfs_set_transaction_flag(NILFS_TI_SYNC);

	nilfs_mark_inode_dirty(inode);
	nilfs_set_file_dirty(inode, 0);
	nilfs_transaction_commit(sb);
	/* May construct a logical segment and may fail in sync mode.
	   But truncate has no return value. */
}

static void nilfs_clear_inode(struct inode *inode)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	struct nilfs_mdt_info *mdi = NILFS_MDT(inode);

	/*
	 * Free resources allocated in nilfs_read_inode(), here.
	 */
	BUG_ON(!list_empty(&ii->i_dirty));
	brelse(ii->i_bh);
	ii->i_bh = NULL;

	if (mdi && mdi->mi_palloc_cache)
		nilfs_palloc_destroy_cache(inode);

	if (test_bit(NILFS_I_BMAP, &ii->i_state))
		nilfs_bmap_clear(ii->i_bmap);

	nilfs_btnode_cache_clear(&ii->i_btnode_cache);

	if (ii->i_root && inode->i_ino == NILFS_ROOT_INO)
		nilfs_put_root(ii->i_root);
}

void nilfs_evict_inode(struct inode *inode)
{
	struct nilfs_transaction_info ti;
	struct super_block *sb = inode->i_sb;
	struct nilfs_inode_info *ii = NILFS_I(inode);
	int ret;

	if (inode->i_nlink || !ii->i_root || unlikely(is_bad_inode(inode))) {
		if (inode->i_data.nrpages)
			truncate_inode_pages(&inode->i_data, 0);
		clear_inode(inode);
		nilfs_clear_inode(inode);
		return;
	}
	nilfs_transaction_begin(sb, &ti, 0); /* never fails */

	if (inode->i_data.nrpages)
		truncate_inode_pages(&inode->i_data, 0);

	/* TODO: some of the following operations may fail.  */
	nilfs_truncate_bmap(ii, 0);
	nilfs_mark_inode_dirty(inode);
	clear_inode(inode);

	ret = nilfs_ifile_delete_inode(ii->i_root->ifile, inode->i_ino);
	if (!ret)
		atomic_dec(&ii->i_root->inodes_count);

	nilfs_clear_inode(inode);

	if (IS_SYNC(inode))
		nilfs_set_transaction_flag(NILFS_TI_SYNC);
	nilfs_transaction_commit(sb);
	/* May construct a logical segment and may fail in sync mode.
	   But delete_inode has no return value. */
}

int nilfs_setattr(struct dentry *dentry, struct iattr *iattr)
{
	struct nilfs_transaction_info ti;
	struct inode *inode = dentry->d_inode;
	struct super_block *sb = inode->i_sb;
	int err;

	err = inode_change_ok(inode, iattr);
	if (err)
		return err;

	err = nilfs_transaction_begin(sb, &ti, 0);
	if (unlikely(err))
		return err;

	if ((iattr->ia_valid & ATTR_SIZE) &&
	    iattr->ia_size != i_size_read(inode)) {
		inode_dio_wait(inode);
		truncate_setsize(inode, iattr->ia_size);
		nilfs_truncate(inode);
	}

	setattr_copy(inode, iattr);
	mark_inode_dirty(inode);

	if (iattr->ia_valid & ATTR_MODE) {
		err = nilfs_acl_chmod(inode);
		if (unlikely(err))
			goto out_err;
	}

	return nilfs_transaction_commit(sb);

out_err:
	nilfs_transaction_abort(sb);
	return err;
}

int nilfs_permission(struct inode *inode, int mask)
{
	struct nilfs_root *root = NILFS_I(inode)->i_root;
	if ((mask & MAY_WRITE) && root &&
	    root->cno != NILFS_CPTREE_CURRENT_CNO)
		return -EROFS; /* snapshot is not writable */

	return generic_permission(inode, mask);
}

int nilfs_load_inode_block(struct inode *inode, struct buffer_head **pbh)
{
	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
	struct nilfs_inode_info *ii = NILFS_I(inode);
	int err;

	spin_lock(&nilfs->ns_inode_lock);
	if (ii->i_bh == NULL) {
		spin_unlock(&nilfs->ns_inode_lock);
		err = nilfs_ifile_get_inode_block(ii->i_root->ifile,
						  inode->i_ino, pbh);
		if (unlikely(err))
			return err;
		spin_lock(&nilfs->ns_inode_lock);
		if (ii->i_bh == NULL)
			ii->i_bh = *pbh;
		else {
			brelse(*pbh);
			*pbh = ii->i_bh;
		}
	} else
		*pbh = ii->i_bh;

	get_bh(*pbh);
	spin_unlock(&nilfs->ns_inode_lock);
	return 0;
}

int nilfs_inode_dirty(struct inode *inode)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
	int ret = 0;

	if (!list_empty(&ii->i_dirty)) {
		spin_lock(&nilfs->ns_inode_lock);
		ret = test_bit(NILFS_I_DIRTY, &ii->i_state) ||
			test_bit(NILFS_I_BUSY, &ii->i_state);
		spin_unlock(&nilfs->ns_inode_lock);
	}
	return ret;
}

int nilfs_set_file_dirty(struct inode *inode, unsigned nr_dirty)
{
	struct nilfs_inode_info *ii = NILFS_I(inode);
	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;

	atomic_add(nr_dirty, &nilfs->ns_ndirtyblks);

	if (test_and_set_bit(NILFS_I_DIRTY, &ii->i_state))
		return 0;

	spin_lock(&nilfs->ns_inode_lock);
	if (!test_bit(NILFS_I_QUEUED, &ii->i_state) &&
	    !test_bit(NILFS_I_BUSY, &ii->i_state)) {
		/* Because this routine may race with nilfs_dispose_list(),
		   we have to check NILFS_I_QUEUED here, too. */
		if (list_empty(&ii->i_dirty) && igrab(inode) == NULL) {
			/* This will happen when somebody is freeing
			   this inode. */
			nilfs_warning(inode->i_sb, __func__,
				      "cannot get inode (ino=%lu)\n",
				      inode->i_ino);
			spin_unlock(&nilfs->ns_inode_lock);
			return -EINVAL; /* NILFS_I_DIRTY may remain for
					   freeing inode */
		}
		list_move_tail(&ii->i_dirty, &nilfs->ns_dirty_files);
		set_bit(NILFS_I_QUEUED, &ii->i_state);
	}
	spin_unlock(&nilfs->ns_inode_lock);
	return 0;
}

int nilfs_mark_inode_dirty(struct inode *inode)
{
	struct buffer_head *ibh;
	int err;

	err = nilfs_load_inode_block(inode, &ibh);
	if (unlikely(err)) {
		nilfs_warning(inode->i_sb, __func__,
			      "failed to reget inode block.\n");
		return err;
	}
	nilfs_update_inode(inode, ibh);
	mark_buffer_dirty(ibh);
	nilfs_mdt_mark_dirty(NILFS_I(inode)->i_root->ifile);
	brelse(ibh);
	return 0;
}

/**
 * nilfs_dirty_inode - reflect changes on given inode to an inode block.
 * @inode: inode of the file to be registered.
 *
 * nilfs_dirty_inode() loads a inode block containing the specified
 * @inode and copies data from a nilfs_inode to a corresponding inode
 * entry in the inode block. This operation is excluded from the segment
 * construction. This function can be called both as a single operation
 * and as a part of indivisible file operations.
 */
void nilfs_dirty_inode(struct inode *inode, int flags)
{
	struct nilfs_transaction_info ti;
	struct nilfs_mdt_info *mdi = NILFS_MDT(inode);

	if (is_bad_inode(inode)) {
		nilfs_warning(inode->i_sb, __func__,
			      "tried to mark bad_inode dirty. ignored.\n");
		dump_stack();
		return;
	}
	if (mdi) {
		nilfs_mdt_mark_dirty(inode);
		return;
	}
	nilfs_transaction_begin(inode->i_sb, &ti, 0);
	nilfs_mark_inode_dirty(inode);
	nilfs_transaction_commit(inode->i_sb); /* never fails */
}

int nilfs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
		 __u64 start, __u64 len)
{
	struct the_nilfs *nilfs = inode->i_sb->s_fs_info;
	__u64 logical = 0, phys = 0, size = 0;
	__u32 flags = 0;
	loff_t isize;
	sector_t blkoff, end_blkoff;
	sector_t delalloc_blkoff;
	unsigned long delalloc_blklen;
	unsigned int blkbits = inode->i_blkbits;
	int ret, n;

	ret = fiemap_check_flags(fieinfo, FIEMAP_FLAG_SYNC);
	if (ret)
		return ret;

	mutex_lock(&inode->i_mutex);

	isize = i_size_read(inode);

	blkoff = start >> blkbits;
	end_blkoff = (start + len - 1) >> blkbits;

	delalloc_blklen = nilfs_find_uncommitted_extent(inode, blkoff,
							&delalloc_blkoff);

	do {
		__u64 blkphy;
		unsigned int maxblocks;

		if (delalloc_blklen && blkoff == delalloc_blkoff) {
			if (size) {
				/* End of the current extent */
				ret = fiemap_fill_next_extent(
					fieinfo, logical, phys, size, flags);
				if (ret)
					break;
			}
			if (blkoff > end_blkoff)
				break;

			flags = FIEMAP_EXTENT_MERGED | FIEMAP_EXTENT_DELALLOC;
			logical = blkoff << blkbits;
			phys = 0;
			size = delalloc_blklen << blkbits;

			blkoff = delalloc_blkoff + delalloc_blklen;
			delalloc_blklen = nilfs_find_uncommitted_extent(
				inode, blkoff, &delalloc_blkoff);
			continue;
		}

		/*
		 * Limit the number of blocks that we look up so as
		 * not to get into the next delayed allocation extent.
		 */
		maxblocks = INT_MAX;
		if (delalloc_blklen)
			maxblocks = min_t(sector_t, delalloc_blkoff - blkoff,
					  maxblocks);
		blkphy = 0;

		down_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);
		n = nilfs_bmap_lookup_contig(
			NILFS_I(inode)->i_bmap, blkoff, &blkphy, maxblocks);
		up_read(&NILFS_MDT(nilfs->ns_dat)->mi_sem);

		if (n < 0) {
			int past_eof;

			if (unlikely(n != -ENOENT))
				break; /* error */

			/* HOLE */
			blkoff++;
			past_eof = ((blkoff << blkbits) >= isize);

			if (size) {
				/* End of the current extent */

				if (past_eof)
					flags |= FIEMAP_EXTENT_LAST;

				ret = fiemap_fill_next_extent(
					fieinfo, logical, phys, size, flags);
				if (ret)
					break;
				size = 0;
			}
			if (blkoff > end_blkoff || past_eof)
				break;
		} else {
			if (size) {
				if (phys && blkphy << blkbits == phys + size) {
					/* The current extent goes on */
					size += n << blkbits;
				} else {
					/* Terminate the current extent */
					ret = fiemap_fill_next_extent(
						fieinfo, logical, phys, size,
						flags);
					if (ret || blkoff > end_blkoff)
						break;

					/* Start another extent */
					flags = FIEMAP_EXTENT_MERGED;
					logical = blkoff << blkbits;
					phys = blkphy << blkbits;
					size = n << blkbits;
				}
			} else {
				/* Start a new extent */
				flags = FIEMAP_EXTENT_MERGED;
				logical = blkoff << blkbits;
				phys = blkphy << blkbits;
				size = n << blkbits;
			}
			blkoff += n;
		}
		cond_resched();
	} while (true);

	/* If ret is 1 then we just hit the end of the extent array */
	if (ret == 1)
		ret = 0;

	mutex_unlock(&inode->i_mutex);
	return ret;
}