aboutsummaryrefslogtreecommitdiffstats
blob: 2b52e48d74824dd67cfb8975a09b246a701a870f (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
/*
 * fs/f2fs/file.c
 *
 * Copyright (c) 2012 Samsung Electronics Co., Ltd.
 *             http://www.samsung.com/
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License version 2 as
 * published by the Free Software Foundation.
 */
#include <linux/fs.h>
#include <linux/f2fs_fs.h>
#include <linux/stat.h>
#include <linux/buffer_head.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/falloc.h>
#include <linux/types.h>
#include <linux/compat.h>
#include <linux/uaccess.h>
#include <linux/mount.h>
#include <linux/pagevec.h>

#include "f2fs.h"
#include "node.h"
#include "segment.h"
#include "xattr.h"
#include "acl.h"
#include "trace.h"
#include <trace/events/f2fs.h>

static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
						struct vm_fault *vmf)
{
	struct page *page = vmf->page;
	struct inode *inode = file_inode(vma->vm_file);
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct dnode_of_data dn;
	int err;

	f2fs_balance_fs(sbi);

	sb_start_pagefault(inode->i_sb);

	f2fs_bug_on(sbi, f2fs_has_inline_data(inode));

	/* block allocation */
	f2fs_lock_op(sbi);
	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = f2fs_reserve_block(&dn, page->index);
	if (err) {
		f2fs_unlock_op(sbi);
		goto out;
	}
	f2fs_put_dnode(&dn);
	f2fs_unlock_op(sbi);

	file_update_time(vma->vm_file);
	lock_page(page);
	if (unlikely(page->mapping != inode->i_mapping ||
			page_offset(page) > i_size_read(inode) ||
			!PageUptodate(page))) {
		unlock_page(page);
		err = -EFAULT;
		goto out;
	}

	/*
	 * check to see if the page is mapped already (no holes)
	 */
	if (PageMappedToDisk(page))
		goto mapped;

	/* page is wholly or partially inside EOF */
	if (((page->index + 1) << PAGE_CACHE_SHIFT) > i_size_read(inode)) {
		unsigned offset;
		offset = i_size_read(inode) & ~PAGE_CACHE_MASK;
		zero_user_segment(page, offset, PAGE_CACHE_SIZE);
	}
	set_page_dirty(page);
	SetPageUptodate(page);

	trace_f2fs_vm_page_mkwrite(page, DATA);
mapped:
	/* fill the page */
	f2fs_wait_on_page_writeback(page, DATA);
out:
	sb_end_pagefault(inode->i_sb);
	return block_page_mkwrite_return(err);
}

static const struct vm_operations_struct f2fs_file_vm_ops = {
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= f2fs_vm_page_mkwrite,
};

static int get_parent_ino(struct inode *inode, nid_t *pino)
{
	struct dentry *dentry;

	inode = igrab(inode);
	dentry = d_find_any_alias(inode);
	iput(inode);
	if (!dentry)
		return 0;

	if (update_dent_inode(inode, &dentry->d_name)) {
		dput(dentry);
		return 0;
	}

	*pino = parent_ino(dentry);
	dput(dentry);
	return 1;
}

static inline bool need_do_checkpoint(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	bool need_cp = false;

	if (!S_ISREG(inode->i_mode) || inode->i_nlink != 1)
		need_cp = true;
	else if (file_wrong_pino(inode))
		need_cp = true;
	else if (!space_for_roll_forward(sbi))
		need_cp = true;
	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
		need_cp = true;
	else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
		need_cp = true;
	else if (test_opt(sbi, FASTBOOT))
		need_cp = true;
	else if (sbi->active_logs == 2)
		need_cp = true;

	return need_cp;
}

static bool need_inode_page_update(struct f2fs_sb_info *sbi, nid_t ino)
{
	struct page *i = find_get_page(NODE_MAPPING(sbi), ino);
	bool ret = false;
	/* But we need to avoid that there are some inode updates */
	if ((i && PageDirty(i)) || need_inode_block_update(sbi, ino))
		ret = true;
	f2fs_put_page(i, 0);
	return ret;
}

static void try_to_fix_pino(struct inode *inode)
{
	struct f2fs_inode_info *fi = F2FS_I(inode);
	nid_t pino;

	down_write(&fi->i_sem);
	fi->xattr_ver = 0;
	if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
			get_parent_ino(inode, &pino)) {
		fi->i_pino = pino;
		file_got_pino(inode);
		up_write(&fi->i_sem);

		mark_inode_dirty_sync(inode);
		f2fs_write_inode(inode, NULL);
	} else {
		up_write(&fi->i_sem);
	}
}

int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
{
	struct inode *inode = file->f_mapping->host;
	struct f2fs_inode_info *fi = F2FS_I(inode);
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	nid_t ino = inode->i_ino;
	int ret = 0;
	bool need_cp = false;
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.for_reclaim = 0,
	};

	if (unlikely(f2fs_readonly(inode->i_sb)))
		return 0;

	trace_f2fs_sync_file_enter(inode);

	/* if fdatasync is triggered, let's do in-place-update */
	if (get_dirty_pages(inode) <= SM_I(sbi)->min_fsync_blocks)
		set_inode_flag(fi, FI_NEED_IPU);
	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
	clear_inode_flag(fi, FI_NEED_IPU);

	if (ret) {
		trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
		return ret;
	}

	/* if the inode is dirty, let's recover all the time */
	if (!datasync && is_inode_flag_set(fi, FI_DIRTY_INODE)) {
		update_inode_page(inode);
		goto go_write;
	}

	/*
	 * if there is no written data, don't waste time to write recovery info.
	 */
	if (!is_inode_flag_set(fi, FI_APPEND_WRITE) &&
			!exist_written_data(sbi, ino, APPEND_INO)) {

		/* it may call write_inode just prior to fsync */
		if (need_inode_page_update(sbi, ino))
			goto go_write;

		if (is_inode_flag_set(fi, FI_UPDATE_WRITE) ||
				exist_written_data(sbi, ino, UPDATE_INO))
			goto flush_out;
		goto out;
	}
go_write:
	/* guarantee free sections for fsync */
	f2fs_balance_fs(sbi);

	/*
	 * Both of fdatasync() and fsync() are able to be recovered from
	 * sudden-power-off.
	 */
	down_read(&fi->i_sem);
	need_cp = need_do_checkpoint(inode);
	up_read(&fi->i_sem);

	if (need_cp) {
		/* all the dirty node pages should be flushed for POR */
		ret = f2fs_sync_fs(inode->i_sb, 1);

		/*
		 * We've secured consistency through sync_fs. Following pino
		 * will be used only for fsynced inodes after checkpoint.
		 */
		try_to_fix_pino(inode);
		clear_inode_flag(fi, FI_APPEND_WRITE);
		clear_inode_flag(fi, FI_UPDATE_WRITE);
		goto out;
	}
sync_nodes:
	sync_node_pages(sbi, ino, &wbc);

	/* if cp_error was enabled, we should avoid infinite loop */
	if (unlikely(f2fs_cp_error(sbi)))
		goto out;

	if (need_inode_block_update(sbi, ino)) {
		mark_inode_dirty_sync(inode);
		f2fs_write_inode(inode, NULL);
		goto sync_nodes;
	}

	ret = wait_on_node_pages_writeback(sbi, ino);
	if (ret)
		goto out;

	/* once recovery info is written, don't need to tack this */
	remove_dirty_inode(sbi, ino, APPEND_INO);
	clear_inode_flag(fi, FI_APPEND_WRITE);
flush_out:
	remove_dirty_inode(sbi, ino, UPDATE_INO);
	clear_inode_flag(fi, FI_UPDATE_WRITE);
	ret = f2fs_issue_flush(sbi);
out:
	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
	f2fs_trace_ios(NULL, NULL, 1);
	return ret;
}

static pgoff_t __get_first_dirty_index(struct address_space *mapping,
						pgoff_t pgofs, int whence)
{
	struct pagevec pvec;
	int nr_pages;

	if (whence != SEEK_DATA)
		return 0;

	/* find first dirty page index */
	pagevec_init(&pvec, 0);
	nr_pages = pagevec_lookup_tag(&pvec, mapping, &pgofs,
					PAGECACHE_TAG_DIRTY, 1);
	pgofs = nr_pages ? pvec.pages[0]->index : LONG_MAX;
	pagevec_release(&pvec);
	return pgofs;
}

static bool __found_offset(block_t blkaddr, pgoff_t dirty, pgoff_t pgofs,
							int whence)
{
	switch (whence) {
	case SEEK_DATA:
		if ((blkaddr == NEW_ADDR && dirty == pgofs) ||
			(blkaddr != NEW_ADDR && blkaddr != NULL_ADDR))
			return true;
		break;
	case SEEK_HOLE:
		if (blkaddr == NULL_ADDR)
			return true;
		break;
	}
	return false;
}

static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes = inode->i_sb->s_maxbytes;
	struct dnode_of_data dn;
	pgoff_t pgofs, end_offset, dirty;
	loff_t data_ofs = offset;
	loff_t isize;
	int err = 0;

	mutex_lock(&inode->i_mutex);

	isize = i_size_read(inode);
	if (offset >= isize)
		goto fail;

	/* handle inline data case */
	if (f2fs_has_inline_data(inode) || f2fs_has_inline_dentry(inode)) {
		if (whence == SEEK_HOLE)
			data_ofs = isize;
		goto found;
	}

	pgofs = (pgoff_t)(offset >> PAGE_CACHE_SHIFT);

	dirty = __get_first_dirty_index(inode->i_mapping, pgofs, whence);

	for (; data_ofs < isize; data_ofs = pgofs << PAGE_CACHE_SHIFT) {
		set_new_dnode(&dn, inode, NULL, NULL, 0);
		err = get_dnode_of_data(&dn, pgofs, LOOKUP_NODE_RA);
		if (err && err != -ENOENT) {
			goto fail;
		} else if (err == -ENOENT) {
			/* direct node does not exists */
			if (whence == SEEK_DATA) {
				pgofs = PGOFS_OF_NEXT_DNODE(pgofs,
							F2FS_I(inode));
				continue;
			} else {
				goto found;
			}
		}

		end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));

		/* find data/hole in dnode block */
		for (; dn.ofs_in_node < end_offset;
				dn.ofs_in_node++, pgofs++,
				data_ofs = (loff_t)pgofs << PAGE_CACHE_SHIFT) {
			block_t blkaddr;
			blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);

			if (__found_offset(blkaddr, dirty, pgofs, whence)) {
				f2fs_put_dnode(&dn);
				goto found;
			}
		}
		f2fs_put_dnode(&dn);
	}

	if (whence == SEEK_DATA)
		goto fail;
found:
	if (whence == SEEK_HOLE && data_ofs > isize)
		data_ofs = isize;
	mutex_unlock(&inode->i_mutex);
	return vfs_setpos(file, data_ofs, maxbytes);
fail:
	mutex_unlock(&inode->i_mutex);
	return -ENXIO;
}

static loff_t f2fs_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	loff_t maxbytes = inode->i_sb->s_maxbytes;

	switch (whence) {
	case SEEK_SET:
	case SEEK_CUR:
	case SEEK_END:
		return generic_file_llseek_size(file, offset, whence,
						maxbytes, i_size_read(inode));
	case SEEK_DATA:
	case SEEK_HOLE:
		if (offset < 0)
			return -ENXIO;
		return f2fs_seek_block(file, offset, whence);
	}

	return -EINVAL;
}

static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file_inode(file);

	/* we don't need to use inline_data strictly */
	if (f2fs_has_inline_data(inode)) {
		int err = f2fs_convert_inline_inode(inode);
		if (err)
			return err;
	}

	file_accessed(file);
	vma->vm_ops = &f2fs_file_vm_ops;
	return 0;
}

int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
{
	int nr_free = 0, ofs = dn->ofs_in_node;
	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
	struct f2fs_node *raw_node;
	__le32 *addr;

	raw_node = F2FS_NODE(dn->node_page);
	addr = blkaddr_in_node(raw_node) + ofs;

	for (; count > 0; count--, addr++, dn->ofs_in_node++) {
		block_t blkaddr = le32_to_cpu(*addr);
		if (blkaddr == NULL_ADDR)
			continue;

		dn->data_blkaddr = NULL_ADDR;
		set_data_blkaddr(dn);
		f2fs_update_extent_cache(dn);
		invalidate_blocks(sbi, blkaddr);
		if (dn->ofs_in_node == 0 && IS_INODE(dn->node_page))
			clear_inode_flag(F2FS_I(dn->inode),
						FI_FIRST_BLOCK_WRITTEN);
		nr_free++;
	}
	if (nr_free) {
		dec_valid_block_count(sbi, dn->inode, nr_free);
		set_page_dirty(dn->node_page);
		sync_inode_page(dn);
	}
	dn->ofs_in_node = ofs;

	trace_f2fs_truncate_data_blocks_range(dn->inode, dn->nid,
					 dn->ofs_in_node, nr_free);
	return nr_free;
}

void truncate_data_blocks(struct dnode_of_data *dn)
{
	truncate_data_blocks_range(dn, ADDRS_PER_BLOCK);
}

static int truncate_partial_data_page(struct inode *inode, u64 from,
								bool force)
{
	unsigned offset = from & (PAGE_CACHE_SIZE - 1);
	struct page *page;

	if (!offset && !force)
		return 0;

	page = find_data_page(inode, from >> PAGE_CACHE_SHIFT, force);
	if (IS_ERR(page))
		return 0;

	lock_page(page);
	if (unlikely(!PageUptodate(page) ||
			page->mapping != inode->i_mapping))
		goto out;

	f2fs_wait_on_page_writeback(page, DATA);
	zero_user(page, offset, PAGE_CACHE_SIZE - offset);
	if (!force)
		set_page_dirty(page);
out:
	f2fs_put_page(page, 1);
	return 0;
}

int truncate_blocks(struct inode *inode, u64 from, bool lock)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	unsigned int blocksize = inode->i_sb->s_blocksize;
	struct dnode_of_data dn;
	pgoff_t free_from;
	int count = 0, err = 0;
	struct page *ipage;
	bool truncate_page = false;

	trace_f2fs_truncate_blocks_enter(inode, from);

	free_from = (pgoff_t)F2FS_BYTES_TO_BLK(from + blocksize - 1);

	if (lock)
		f2fs_lock_op(sbi);

	ipage = get_node_page(sbi, inode->i_ino);
	if (IS_ERR(ipage)) {
		err = PTR_ERR(ipage);
		goto out;
	}

	if (f2fs_has_inline_data(inode)) {
		if (truncate_inline_inode(ipage, from))
			set_page_dirty(ipage);
		f2fs_put_page(ipage, 1);
		truncate_page = true;
		goto out;
	}

	set_new_dnode(&dn, inode, ipage, NULL, 0);
	err = get_dnode_of_data(&dn, free_from, LOOKUP_NODE);
	if (err) {
		if (err == -ENOENT)
			goto free_next;
		goto out;
	}

	count = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));

	count -= dn.ofs_in_node;
	f2fs_bug_on(sbi, count < 0);

	if (dn.ofs_in_node || IS_INODE(dn.node_page)) {
		truncate_data_blocks_range(&dn, count);
		free_from += count;
	}

	f2fs_put_dnode(&dn);
free_next:
	err = truncate_inode_blocks(inode, free_from);
out:
	if (lock)
		f2fs_unlock_op(sbi);

	/* lastly zero out the first data page */
	if (!err)
		err = truncate_partial_data_page(inode, from, truncate_page);

	trace_f2fs_truncate_blocks_exit(inode, err);
	return err;
}

void f2fs_truncate(struct inode *inode)
{
	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
				S_ISLNK(inode->i_mode)))
		return;

	trace_f2fs_truncate(inode);

	/* we should check inline_data size */
	if (f2fs_has_inline_data(inode) && !f2fs_may_inline(inode)) {
		if (f2fs_convert_inline_inode(inode))
			return;
	}

	if (!truncate_blocks(inode, i_size_read(inode), true)) {
		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		mark_inode_dirty(inode);
	}
}

int f2fs_getattr(struct vfsmount *mnt,
			 struct dentry *dentry, struct kstat *stat)
{
	struct inode *inode = d_inode(dentry);
	generic_fillattr(inode, stat);
	stat->blocks <<= 3;
	return 0;
}

#ifdef CONFIG_F2FS_FS_POSIX_ACL
static void __setattr_copy(struct inode *inode, const struct iattr *attr)
{
	struct f2fs_inode_info *fi = F2FS_I(inode);
	unsigned int ia_valid = attr->ia_valid;

	if (ia_valid & ATTR_UID)
		inode->i_uid = attr->ia_uid;
	if (ia_valid & ATTR_GID)
		inode->i_gid = attr->ia_gid;
	if (ia_valid & ATTR_ATIME)
		inode->i_atime = timespec_trunc(attr->ia_atime,
						inode->i_sb->s_time_gran);
	if (ia_valid & ATTR_MTIME)
		inode->i_mtime = timespec_trunc(attr->ia_mtime,
						inode->i_sb->s_time_gran);
	if (ia_valid & ATTR_CTIME)
		inode->i_ctime = timespec_trunc(attr->ia_ctime,
						inode->i_sb->s_time_gran);
	if (ia_valid & ATTR_MODE) {
		umode_t mode = attr->ia_mode;

		if (!in_group_p(inode->i_gid) && !capable(CAP_FSETID))
			mode &= ~S_ISGID;
		set_acl_inode(fi, mode);
	}
}
#else
#define __setattr_copy setattr_copy
#endif

int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = d_inode(dentry);
	struct f2fs_inode_info *fi = F2FS_I(inode);
	int err;

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

	if (attr->ia_valid & ATTR_SIZE) {
		if (attr->ia_size != i_size_read(inode)) {
			truncate_setsize(inode, attr->ia_size);
			f2fs_truncate(inode);
			f2fs_balance_fs(F2FS_I_SB(inode));
		} else {
			/*
			 * giving a chance to truncate blocks past EOF which
			 * are fallocated with FALLOC_FL_KEEP_SIZE.
			 */
			f2fs_truncate(inode);
		}
	}

	__setattr_copy(inode, attr);

	if (attr->ia_valid & ATTR_MODE) {
		err = posix_acl_chmod(inode, get_inode_mode(inode));
		if (err || is_inode_flag_set(fi, FI_ACL_MODE)) {
			inode->i_mode = fi->i_acl_mode;
			clear_inode_flag(fi, FI_ACL_MODE);
		}
	}

	mark_inode_dirty(inode);
	return err;
}

const struct inode_operations f2fs_file_inode_operations = {
	.getattr	= f2fs_getattr,
	.setattr	= f2fs_setattr,
	.get_acl	= f2fs_get_acl,
	.set_acl	= f2fs_set_acl,
#ifdef CONFIG_F2FS_FS_XATTR
	.setxattr	= generic_setxattr,
	.getxattr	= generic_getxattr,
	.listxattr	= f2fs_listxattr,
	.removexattr	= generic_removexattr,
#endif
	.fiemap		= f2fs_fiemap,
};

static void fill_zero(struct inode *inode, pgoff_t index,
					loff_t start, loff_t len)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct page *page;

	if (!len)
		return;

	f2fs_balance_fs(sbi);

	f2fs_lock_op(sbi);
	page = get_new_data_page(inode, NULL, index, false);
	f2fs_unlock_op(sbi);

	if (!IS_ERR(page)) {
		f2fs_wait_on_page_writeback(page, DATA);
		zero_user(page, start, len);
		set_page_dirty(page);
		f2fs_put_page(page, 1);
	}
}

int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
{
	pgoff_t index;
	int err;

	for (index = pg_start; index < pg_end; index++) {
		struct dnode_of_data dn;

		set_new_dnode(&dn, inode, NULL, NULL, 0);
		err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
		if (err) {
			if (err == -ENOENT)
				continue;
			return err;
		}

		if (dn.data_blkaddr != NULL_ADDR)
			truncate_data_blocks_range(&dn, 1);
		f2fs_put_dnode(&dn);
	}
	return 0;
}

static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
{
	pgoff_t pg_start, pg_end;
	loff_t off_start, off_end;
	int ret = 0;

	if (!S_ISREG(inode->i_mode))
		return -EOPNOTSUPP;

	/* skip punching hole beyond i_size */
	if (offset >= inode->i_size)
		return ret;

	if (f2fs_has_inline_data(inode)) {
		ret = f2fs_convert_inline_inode(inode);
		if (ret)
			return ret;
	}

	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;

	off_start = offset & (PAGE_CACHE_SIZE - 1);
	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);

	if (pg_start == pg_end) {
		fill_zero(inode, pg_start, off_start,
						off_end - off_start);
	} else {
		if (off_start)
			fill_zero(inode, pg_start++, off_start,
					PAGE_CACHE_SIZE - off_start);
		if (off_end)
			fill_zero(inode, pg_end, 0, off_end);

		if (pg_start < pg_end) {
			struct address_space *mapping = inode->i_mapping;
			loff_t blk_start, blk_end;
			struct f2fs_sb_info *sbi = F2FS_I_SB(inode);

			f2fs_balance_fs(sbi);

			blk_start = pg_start << PAGE_CACHE_SHIFT;
			blk_end = pg_end << PAGE_CACHE_SHIFT;
			truncate_inode_pages_range(mapping, blk_start,
					blk_end - 1);

			f2fs_lock_op(sbi);
			ret = truncate_hole(inode, pg_start, pg_end);
			f2fs_unlock_op(sbi);
		}
	}

	return ret;
}

static int expand_inode_data(struct inode *inode, loff_t offset,
					loff_t len, int mode)
{
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	pgoff_t index, pg_start, pg_end;
	loff_t new_size = i_size_read(inode);
	loff_t off_start, off_end;
	int ret = 0;

	f2fs_balance_fs(sbi);

	ret = inode_newsize_ok(inode, (len + offset));
	if (ret)
		return ret;

	if (f2fs_has_inline_data(inode)) {
		ret = f2fs_convert_inline_inode(inode);
		if (ret)
			return ret;
	}

	pg_start = ((unsigned long long) offset) >> PAGE_CACHE_SHIFT;
	pg_end = ((unsigned long long) offset + len) >> PAGE_CACHE_SHIFT;

	off_start = offset & (PAGE_CACHE_SIZE - 1);
	off_end = (offset + len) & (PAGE_CACHE_SIZE - 1);

	f2fs_lock_op(sbi);

	for (index = pg_start; index <= pg_end; index++) {
		struct dnode_of_data dn;

		if (index == pg_end && !off_end)
			goto noalloc;

		set_new_dnode(&dn, inode, NULL, NULL, 0);
		ret = f2fs_reserve_block(&dn, index);
		if (ret)
			break;
noalloc:
		if (pg_start == pg_end)
			new_size = offset + len;
		else if (index == pg_start && off_start)
			new_size = (index + 1) << PAGE_CACHE_SHIFT;
		else if (index == pg_end)
			new_size = (index << PAGE_CACHE_SHIFT) + off_end;
		else
			new_size += PAGE_CACHE_SIZE;
	}

	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
		i_size_read(inode) < new_size) {
		i_size_write(inode, new_size);
		mark_inode_dirty(inode);
		update_inode_page(inode);
	}
	f2fs_unlock_op(sbi);

	return ret;
}

static long f2fs_fallocate(struct file *file, int mode,
				loff_t offset, loff_t len)
{
	struct inode *inode = file_inode(file);
	long ret;

	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	mutex_lock(&inode->i_mutex);

	if (mode & FALLOC_FL_PUNCH_HOLE)
		ret = punch_hole(inode, offset, len);
	else
		ret = expand_inode_data(inode, offset, len, mode);

	if (!ret) {
		inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		mark_inode_dirty(inode);
	}

	mutex_unlock(&inode->i_mutex);

	trace_f2fs_fallocate(inode, mode, offset, len, ret);
	return ret;
}

static int f2fs_release_file(struct inode *inode, struct file *filp)
{
	/* some remained atomic pages should discarded */
	if (f2fs_is_atomic_file(inode))
		commit_inmem_pages(inode, true);
	if (f2fs_is_volatile_file(inode)) {
		set_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
		filemap_fdatawrite(inode->i_mapping);
		clear_inode_flag(F2FS_I(inode), FI_DROP_CACHE);
	}
	return 0;
}

#define F2FS_REG_FLMASK		(~(FS_DIRSYNC_FL | FS_TOPDIR_FL))
#define F2FS_OTHER_FLMASK	(FS_NODUMP_FL | FS_NOATIME_FL)

static inline __u32 f2fs_mask_flags(umode_t mode, __u32 flags)
{
	if (S_ISDIR(mode))
		return flags;
	else if (S_ISREG(mode))
		return flags & F2FS_REG_FLMASK;
	else
		return flags & F2FS_OTHER_FLMASK;
}

static int f2fs_ioc_getflags(struct file *filp, unsigned long arg)
{
	struct inode *inode = file_inode(filp);
	struct f2fs_inode_info *fi = F2FS_I(inode);
	unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
	return put_user(flags, (int __user *)arg);
}

static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
{
	struct inode *inode = file_inode(filp);
	struct f2fs_inode_info *fi = F2FS_I(inode);
	unsigned int flags = fi->i_flags & FS_FL_USER_VISIBLE;
	unsigned int oldflags;
	int ret;

	ret = mnt_want_write_file(filp);
	if (ret)
		return ret;

	if (!inode_owner_or_capable(inode)) {
		ret = -EACCES;
		goto out;
	}

	if (get_user(flags, (int __user *)arg)) {
		ret = -EFAULT;
		goto out;
	}

	flags = f2fs_mask_flags(inode->i_mode, flags);

	mutex_lock(&inode->i_mutex);

	oldflags = fi->i_flags;

	if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
		if (!capable(CAP_LINUX_IMMUTABLE)) {
			mutex_unlock(&inode->i_mutex);
			ret = -EPERM;
			goto out;
		}
	}

	flags = flags & FS_FL_USER_MODIFIABLE;
	flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
	fi->i_flags = flags;
	mutex_unlock(&inode->i_mutex);

	f2fs_set_inode_flags(inode);
	inode->i_ctime = CURRENT_TIME;
	mark_inode_dirty(inode);
out:
	mnt_drop_write_file(filp);
	return ret;
}

static int f2fs_ioc_getversion(struct file *filp, unsigned long arg)
{
	struct inode *inode = file_inode(filp);

	return put_user(inode->i_generation, (int __user *)arg);
}

static int f2fs_ioc_start_atomic_write(struct file *filp)
{
	struct inode *inode = file_inode(filp);

	if (!inode_owner_or_capable(inode))
		return -EACCES;

	f2fs_balance_fs(F2FS_I_SB(inode));

	if (f2fs_is_atomic_file(inode))
		return 0;

	set_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);

	return f2fs_convert_inline_inode(inode);
}

static int f2fs_ioc_commit_atomic_write(struct file *filp)
{
	struct inode *inode = file_inode(filp);
	int ret;

	if (!inode_owner_or_capable(inode))
		return -EACCES;

	if (f2fs_is_volatile_file(inode))
		return 0;

	ret = mnt_want_write_file(filp);
	if (ret)
		return ret;

	if (f2fs_is_atomic_file(inode))
		commit_inmem_pages(inode, false);

	ret = f2fs_sync_file(filp, 0, LONG_MAX, 0);
	mnt_drop_write_file(filp);
	clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
	return ret;
}

static int f2fs_ioc_start_volatile_write(struct file *filp)
{
	struct inode *inode = file_inode(filp);

	if (!inode_owner_or_capable(inode))
		return -EACCES;

	if (f2fs_is_volatile_file(inode))
		return 0;

	set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);

	return f2fs_convert_inline_inode(inode);
}

static int f2fs_ioc_release_volatile_write(struct file *filp)
{
	struct inode *inode = file_inode(filp);

	if (!inode_owner_or_capable(inode))
		return -EACCES;

	if (!f2fs_is_volatile_file(inode))
		return 0;

	if (!f2fs_is_first_block_written(inode))
		return truncate_partial_data_page(inode, 0, true);

	punch_hole(inode, 0, F2FS_BLKSIZE);
	return 0;
}

static int f2fs_ioc_abort_volatile_write(struct file *filp)
{
	struct inode *inode = file_inode(filp);
	int ret;

	if (!inode_owner_or_capable(inode))
		return -EACCES;

	ret = mnt_want_write_file(filp);
	if (ret)
		return ret;

	f2fs_balance_fs(F2FS_I_SB(inode));

	if (f2fs_is_atomic_file(inode)) {
		commit_inmem_pages(inode, false);
		clear_inode_flag(F2FS_I(inode), FI_ATOMIC_FILE);
	}

	if (f2fs_is_volatile_file(inode)) {
		clear_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
		filemap_fdatawrite(inode->i_mapping);
		set_inode_flag(F2FS_I(inode), FI_VOLATILE_FILE);
	}
	mnt_drop_write_file(filp);
	return ret;
}

static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
{
	struct inode *inode = file_inode(filp);
	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
	struct super_block *sb = sbi->sb;
	__u32 in;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (get_user(in, (__u32 __user *)arg))
		return -EFAULT;

	switch (in) {
	case F2FS_GOING_DOWN_FULLSYNC:
		sb = freeze_bdev(sb->s_bdev);
		if (sb && !IS_ERR(sb)) {
			f2fs_stop_checkpoint(sbi);
			thaw_bdev(sb->s_bdev, sb);
		}
		break;
	case F2FS_GOING_DOWN_METASYNC:
		/* do checkpoint only */
		f2fs_sync_fs(sb, 1);
		f2fs_stop_checkpoint(sbi);
		break;
	case F2FS_GOING_DOWN_NOSYNC:
		f2fs_stop_checkpoint(sbi);
		break;
	default:
		return -EINVAL;
	}
	return 0;
}

static int f2fs_ioc_fitrim(struct file *filp, unsigned long arg)
{
	struct inode *inode = file_inode(filp);
	struct super_block *sb = inode->i_sb;
	struct request_queue *q = bdev_get_queue(sb->s_bdev);
	struct fstrim_range range;
	int ret;

	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!blk_queue_discard(q))
		return -EOPNOTSUPP;

	if (copy_from_user(&range, (struct fstrim_range __user *)arg,
				sizeof(range)))
		return -EFAULT;

	range.minlen = max((unsigned int)range.minlen,
				q->limits.discard_granularity);
	ret = f2fs_trim_fs(F2FS_SB(sb), &range);
	if (ret < 0)
		return ret;

	if (copy_to_user((struct fstrim_range __user *)arg, &range,
				sizeof(range)))
		return -EFAULT;
	return 0;
}

long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case F2FS_IOC_GETFLAGS:
		return f2fs_ioc_getflags(filp, arg);
	case F2FS_IOC_SETFLAGS:
		return f2fs_ioc_setflags(filp, arg);
	case F2FS_IOC_GETVERSION:
		return f2fs_ioc_getversion(filp, arg);
	case F2FS_IOC_START_ATOMIC_WRITE:
		return f2fs_ioc_start_atomic_write(filp);
	case F2FS_IOC_COMMIT_ATOMIC_WRITE:
		return f2fs_ioc_commit_atomic_write(filp);
	case F2FS_IOC_START_VOLATILE_WRITE:
		return f2fs_ioc_start_volatile_write(filp);
	case F2FS_IOC_RELEASE_VOLATILE_WRITE:
		return f2fs_ioc_release_volatile_write(filp);
	case F2FS_IOC_ABORT_VOLATILE_WRITE:
		return f2fs_ioc_abort_volatile_write(filp);
	case F2FS_IOC_SHUTDOWN:
		return f2fs_ioc_shutdown(filp, arg);
	case FITRIM:
		return f2fs_ioc_fitrim(filp, arg);
	default:
		return -ENOTTY;
	}
}

#ifdef CONFIG_COMPAT
long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
{
	switch (cmd) {
	case F2FS_IOC32_GETFLAGS:
		cmd = F2FS_IOC_GETFLAGS;
		break;
	case F2FS_IOC32_SETFLAGS:
		cmd = F2FS_IOC_SETFLAGS;
		break;
	default:
		return -ENOIOCTLCMD;
	}
	return f2fs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
}
#endif

const struct file_operations f2fs_file_operations = {
	.llseek		= f2fs_llseek,
	.read_iter	= generic_file_read_iter,
	.write_iter	= generic_file_write_iter,
	.open		= generic_file_open,
	.release	= f2fs_release_file,
	.mmap		= f2fs_file_mmap,
	.fsync		= f2fs_sync_file,
	.fallocate	= f2fs_fallocate,
	.unlocked_ioctl	= f2fs_ioctl,
#ifdef CONFIG_COMPAT
	.compat_ioctl	= f2fs_compat_ioctl,
#endif
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
};