summaryrefslogtreecommitdiff
path: root/fs/f2fs/data.c
blob: ea58fb698ac6bd01c6e901c8a93c64f1c12f2202 (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
/*
 * fs/f2fs/data.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/buffer_head.h>
#include <linux/mpage.h>
#include <linux/aio.h>
#include <linux/writeback.h>
#include <linux/backing-dev.h>
#include <linux/blkdev.h>
#include <linux/bio.h>
#include <linux/prefetch.h>

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

static void f2fs_read_end_io(struct bio *bio, int err)
{
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (!err) {
			SetPageUptodate(page);
		} else {
			ClearPageUptodate(page);
			SetPageError(page);
		}
		unlock_page(page);
	}
	bio_put(bio);
}

static void f2fs_write_end_io(struct bio *bio, int err)
{
	struct f2fs_sb_info *sbi = bio->bi_private;
	struct bio_vec *bvec;
	int i;

	bio_for_each_segment_all(bvec, bio, i) {
		struct page *page = bvec->bv_page;

		if (unlikely(err)) {
			SetPageError(page);
			set_bit(AS_EIO, &page->mapping->flags);
			f2fs_stop_checkpoint(sbi);
		}
		end_page_writeback(page);
		dec_page_count(sbi, F2FS_WRITEBACK);
	}

	if (sbi->wait_io) {
		complete(sbi->wait_io);
		sbi->wait_io = NULL;
	}

	if (!get_pages(sbi, F2FS_WRITEBACK) &&
			!list_empty(&sbi->cp_wait.task_list))
		wake_up(&sbi->cp_wait);

	bio_put(bio);
}

/*
 * Low-level block read/write IO operations.
 */
static struct bio *__bio_alloc(struct f2fs_sb_info *sbi, block_t blk_addr,
				int npages, bool is_read)
{
	struct bio *bio;

	/* No failure on bio allocation */
	bio = bio_alloc(GFP_NOIO, npages);

	bio->bi_bdev = sbi->sb->s_bdev;
	bio->bi_iter.bi_sector = SECTOR_FROM_BLOCK(sbi, blk_addr);
	bio->bi_end_io = is_read ? f2fs_read_end_io : f2fs_write_end_io;
	bio->bi_private = sbi;

	return bio;
}

static void __submit_merged_bio(struct f2fs_bio_info *io)
{
	struct f2fs_io_info *fio = &io->fio;
	int rw;

	if (!io->bio)
		return;

	rw = fio->rw;

	if (is_read_io(rw)) {
		trace_f2fs_submit_read_bio(io->sbi->sb, rw,
						fio->type, io->bio);
		submit_bio(rw, io->bio);
	} else {
		trace_f2fs_submit_write_bio(io->sbi->sb, rw,
						fio->type, io->bio);
		/*
		 * META_FLUSH is only from the checkpoint procedure, and we
		 * should wait this metadata bio for FS consistency.
		 */
		if (fio->type == META_FLUSH) {
			DECLARE_COMPLETION_ONSTACK(wait);
			io->sbi->wait_io = &wait;
			submit_bio(rw, io->bio);
			wait_for_completion(&wait);
		} else {
			submit_bio(rw, io->bio);
		}
	}

	io->bio = NULL;
}

void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
				enum page_type type, int rw)
{
	enum page_type btype = PAGE_TYPE_OF_BIO(type);
	struct f2fs_bio_info *io;

	io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype];

	down_write(&io->io_rwsem);

	/* change META to META_FLUSH in the checkpoint procedure */
	if (type >= META_FLUSH) {
		io->fio.type = META_FLUSH;
		io->fio.rw = WRITE_FLUSH_FUA | REQ_META | REQ_PRIO;
	}
	__submit_merged_bio(io);
	up_write(&io->io_rwsem);
}

/*
 * Fill the locked page with data located in the block address.
 * Return unlocked page.
 */
int f2fs_submit_page_bio(struct f2fs_sb_info *sbi, struct page *page,
					block_t blk_addr, int rw)
{
	struct bio *bio;

	trace_f2fs_submit_page_bio(page, blk_addr, rw);

	/* Allocate a new bio */
	bio = __bio_alloc(sbi, blk_addr, 1, is_read_io(rw));

	if (bio_add_page(bio, page, PAGE_CACHE_SIZE, 0) < PAGE_CACHE_SIZE) {
		bio_put(bio);
		f2fs_put_page(page, 1);
		return -EFAULT;
	}

	submit_bio(rw, bio);
	return 0;
}

void f2fs_submit_page_mbio(struct f2fs_sb_info *sbi, struct page *page,
			block_t blk_addr, struct f2fs_io_info *fio)
{
	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
	struct f2fs_bio_info *io;
	bool is_read = is_read_io(fio->rw);

	io = is_read ? &sbi->read_io : &sbi->write_io[btype];

	verify_block_addr(sbi, blk_addr);

	down_write(&io->io_rwsem);

	if (!is_read)
		inc_page_count(sbi, F2FS_WRITEBACK);

	if (io->bio && (io->last_block_in_bio != blk_addr - 1 ||
						io->fio.rw != fio->rw))
		__submit_merged_bio(io);
alloc_new:
	if (io->bio == NULL) {
		int bio_blocks = MAX_BIO_BLOCKS(max_hw_blocks(sbi));

		io->bio = __bio_alloc(sbi, blk_addr, bio_blocks, is_read);
		io->fio = *fio;
	}

	if (bio_add_page(io->bio, page, PAGE_CACHE_SIZE, 0) <
							PAGE_CACHE_SIZE) {
		__submit_merged_bio(io);
		goto alloc_new;
	}

	io->last_block_in_bio = blk_addr;

	up_write(&io->io_rwsem);
	trace_f2fs_submit_page_mbio(page, fio->rw, fio->type, blk_addr);
}

/*
 * Lock ordering for the change of data block address:
 * ->data_page
 *  ->node_page
 *    update block addresses in the node page
 */
static void __set_data_blkaddr(struct dnode_of_data *dn, block_t new_addr)
{
	struct f2fs_node *rn;
	__le32 *addr_array;
	struct page *node_page = dn->node_page;
	unsigned int ofs_in_node = dn->ofs_in_node;

	f2fs_wait_on_page_writeback(node_page, NODE);

	rn = F2FS_NODE(node_page);

	/* Get physical address of data block */
	addr_array = blkaddr_in_node(rn);
	addr_array[ofs_in_node] = cpu_to_le32(new_addr);
	set_page_dirty(node_page);
}

int reserve_new_block(struct dnode_of_data *dn)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);

	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
		return -EPERM;
	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
		return -ENOSPC;

	trace_f2fs_reserve_new_block(dn->inode, dn->nid, dn->ofs_in_node);

	__set_data_blkaddr(dn, NEW_ADDR);
	dn->data_blkaddr = NEW_ADDR;
	mark_inode_dirty(dn->inode);
	sync_inode_page(dn);
	return 0;
}

int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
{
	bool need_put = dn->inode_page ? false : true;
	int err;

	/* if inode_page exists, index should be zero */
	f2fs_bug_on(!need_put && index);

	err = get_dnode_of_data(dn, index, ALLOC_NODE);
	if (err)
		return err;

	if (dn->data_blkaddr == NULL_ADDR)
		err = reserve_new_block(dn);
	if (err || need_put)
		f2fs_put_dnode(dn);
	return err;
}

static int check_extent_cache(struct inode *inode, pgoff_t pgofs,
					struct buffer_head *bh_result)
{
	struct f2fs_inode_info *fi = F2FS_I(inode);
	pgoff_t start_fofs, end_fofs;
	block_t start_blkaddr;

	if (is_inode_flag_set(fi, FI_NO_EXTENT))
		return 0;

	read_lock(&fi->ext.ext_lock);
	if (fi->ext.len == 0) {
		read_unlock(&fi->ext.ext_lock);
		return 0;
	}

	stat_inc_total_hit(inode->i_sb);

	start_fofs = fi->ext.fofs;
	end_fofs = fi->ext.fofs + fi->ext.len - 1;
	start_blkaddr = fi->ext.blk_addr;

	if (pgofs >= start_fofs && pgofs <= end_fofs) {
		unsigned int blkbits = inode->i_sb->s_blocksize_bits;
		size_t count;

		clear_buffer_new(bh_result);
		map_bh(bh_result, inode->i_sb,
				start_blkaddr + pgofs - start_fofs);
		count = end_fofs - pgofs + 1;
		if (count < (UINT_MAX >> blkbits))
			bh_result->b_size = (count << blkbits);
		else
			bh_result->b_size = UINT_MAX;

		stat_inc_read_hit(inode->i_sb);
		read_unlock(&fi->ext.ext_lock);
		return 1;
	}
	read_unlock(&fi->ext.ext_lock);
	return 0;
}

void update_extent_cache(block_t blk_addr, struct dnode_of_data *dn)
{
	struct f2fs_inode_info *fi = F2FS_I(dn->inode);
	pgoff_t fofs, start_fofs, end_fofs;
	block_t start_blkaddr, end_blkaddr;
	int need_update = true;

	f2fs_bug_on(blk_addr == NEW_ADDR);
	fofs = start_bidx_of_node(ofs_of_node(dn->node_page), fi) +
							dn->ofs_in_node;

	/* Update the page address in the parent node */
	__set_data_blkaddr(dn, blk_addr);

	if (is_inode_flag_set(fi, FI_NO_EXTENT))
		return;

	write_lock(&fi->ext.ext_lock);

	start_fofs = fi->ext.fofs;
	end_fofs = fi->ext.fofs + fi->ext.len - 1;
	start_blkaddr = fi->ext.blk_addr;
	end_blkaddr = fi->ext.blk_addr + fi->ext.len - 1;

	/* Drop and initialize the matched extent */
	if (fi->ext.len == 1 && fofs == start_fofs)
		fi->ext.len = 0;

	/* Initial extent */
	if (fi->ext.len == 0) {
		if (blk_addr != NULL_ADDR) {
			fi->ext.fofs = fofs;
			fi->ext.blk_addr = blk_addr;
			fi->ext.len = 1;
		}
		goto end_update;
	}

	/* Front merge */
	if (fofs == start_fofs - 1 && blk_addr == start_blkaddr - 1) {
		fi->ext.fofs--;
		fi->ext.blk_addr--;
		fi->ext.len++;
		goto end_update;
	}

	/* Back merge */
	if (fofs == end_fofs + 1 && blk_addr == end_blkaddr + 1) {
		fi->ext.len++;
		goto end_update;
	}

	/* Split the existing extent */
	if (fi->ext.len > 1 &&
		fofs >= start_fofs && fofs <= end_fofs) {
		if ((end_fofs - fofs) < (fi->ext.len >> 1)) {
			fi->ext.len = fofs - start_fofs;
		} else {
			fi->ext.fofs = fofs + 1;
			fi->ext.blk_addr = start_blkaddr +
					fofs - start_fofs + 1;
			fi->ext.len -= fofs - start_fofs + 1;
		}
	} else {
		need_update = false;
	}

	/* Finally, if the extent is very fragmented, let's drop the cache. */
	if (fi->ext.len < F2FS_MIN_EXTENT_LEN) {
		fi->ext.len = 0;
		set_inode_flag(fi, FI_NO_EXTENT);
		need_update = true;
	}
end_update:
	write_unlock(&fi->ext.ext_lock);
	if (need_update)
		sync_inode_page(dn);
	return;
}

struct page *find_data_page(struct inode *inode, pgoff_t index, bool sync)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct address_space *mapping = inode->i_mapping;
	struct dnode_of_data dn;
	struct page *page;
	int err;

	page = find_get_page(mapping, index);
	if (page && PageUptodate(page))
		return page;
	f2fs_put_page(page, 0);

	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
	if (err)
		return ERR_PTR(err);
	f2fs_put_dnode(&dn);

	if (dn.data_blkaddr == NULL_ADDR)
		return ERR_PTR(-ENOENT);

	/* By fallocate(), there is no cached page, but with NEW_ADDR */
	if (unlikely(dn.data_blkaddr == NEW_ADDR))
		return ERR_PTR(-EINVAL);

	page = grab_cache_page(mapping, index);
	if (!page)
		return ERR_PTR(-ENOMEM);

	if (PageUptodate(page)) {
		unlock_page(page);
		return page;
	}

	err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
					sync ? READ_SYNC : READA);
	if (err)
		return ERR_PTR(err);

	if (sync) {
		wait_on_page_locked(page);
		if (unlikely(!PageUptodate(page))) {
			f2fs_put_page(page, 0);
			return ERR_PTR(-EIO);
		}
	}
	return page;
}

/*
 * If it tries to access a hole, return an error.
 * Because, the callers, functions in dir.c and GC, should be able to know
 * whether this page exists or not.
 */
struct page *get_lock_data_page(struct inode *inode, pgoff_t index)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct address_space *mapping = inode->i_mapping;
	struct dnode_of_data dn;
	struct page *page;
	int err;

repeat:
	page = grab_cache_page(mapping, index);
	if (!page)
		return ERR_PTR(-ENOMEM);

	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
	if (err) {
		f2fs_put_page(page, 1);
		return ERR_PTR(err);
	}
	f2fs_put_dnode(&dn);

	if (unlikely(dn.data_blkaddr == NULL_ADDR)) {
		f2fs_put_page(page, 1);
		return ERR_PTR(-ENOENT);
	}

	if (PageUptodate(page))
		return page;

	/*
	 * A new dentry page is allocated but not able to be written, since its
	 * new inode page couldn't be allocated due to -ENOSPC.
	 * In such the case, its blkaddr can be remained as NEW_ADDR.
	 * see, f2fs_add_link -> get_new_data_page -> init_inode_metadata.
	 */
	if (dn.data_blkaddr == NEW_ADDR) {
		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
		SetPageUptodate(page);
		return page;
	}

	err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr, READ_SYNC);
	if (err)
		return ERR_PTR(err);

	lock_page(page);
	if (unlikely(!PageUptodate(page))) {
		f2fs_put_page(page, 1);
		return ERR_PTR(-EIO);
	}
	if (unlikely(page->mapping != mapping)) {
		f2fs_put_page(page, 1);
		goto repeat;
	}
	return page;
}

/*
 * Caller ensures that this data page is never allocated.
 * A new zero-filled data page is allocated in the page cache.
 *
 * Also, caller should grab and release a rwsem by calling f2fs_lock_op() and
 * f2fs_unlock_op().
 * Note that, ipage is set only by make_empty_dir.
 */
struct page *get_new_data_page(struct inode *inode,
		struct page *ipage, pgoff_t index, bool new_i_size)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct address_space *mapping = inode->i_mapping;
	struct page *page;
	struct dnode_of_data dn;
	int err;

	set_new_dnode(&dn, inode, ipage, NULL, 0);
	err = f2fs_reserve_block(&dn, index);
	if (err)
		return ERR_PTR(err);
repeat:
	page = grab_cache_page(mapping, index);
	if (!page) {
		err = -ENOMEM;
		goto put_err;
	}

	if (PageUptodate(page))
		return page;

	if (dn.data_blkaddr == NEW_ADDR) {
		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
		SetPageUptodate(page);
	} else {
		err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
								READ_SYNC);
		if (err)
			goto put_err;

		lock_page(page);
		if (unlikely(!PageUptodate(page))) {
			f2fs_put_page(page, 1);
			err = -EIO;
			goto put_err;
		}
		if (unlikely(page->mapping != mapping)) {
			f2fs_put_page(page, 1);
			goto repeat;
		}
	}

	if (new_i_size &&
		i_size_read(inode) < ((index + 1) << PAGE_CACHE_SHIFT)) {
		i_size_write(inode, ((index + 1) << PAGE_CACHE_SHIFT));
		/* Only the directory inode sets new_i_size */
		set_inode_flag(F2FS_I(inode), FI_UPDATE_DIR);
	}
	return page;

put_err:
	f2fs_put_dnode(&dn);
	return ERR_PTR(err);
}

static int __allocate_data_block(struct dnode_of_data *dn)
{
	struct f2fs_sb_info *sbi = F2FS_SB(dn->inode->i_sb);
	struct f2fs_summary sum;
	block_t new_blkaddr;
	struct node_info ni;
	int type;

	if (unlikely(is_inode_flag_set(F2FS_I(dn->inode), FI_NO_ALLOC)))
		return -EPERM;
	if (unlikely(!inc_valid_block_count(sbi, dn->inode, 1)))
		return -ENOSPC;

	__set_data_blkaddr(dn, NEW_ADDR);
	dn->data_blkaddr = NEW_ADDR;

	get_node_info(sbi, dn->nid, &ni);
	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);

	type = CURSEG_WARM_DATA;

	allocate_data_block(sbi, NULL, NULL_ADDR, &new_blkaddr, &sum, type);

	/* direct IO doesn't use extent cache to maximize the performance */
	set_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);
	update_extent_cache(new_blkaddr, dn);
	clear_inode_flag(F2FS_I(dn->inode), FI_NO_EXTENT);

	dn->data_blkaddr = new_blkaddr;
	return 0;
}

/*
 * get_data_block() now supported readahead/bmap/rw direct_IO with mapped bh.
 * If original data blocks are allocated, then give them to blockdev.
 * Otherwise,
 *     a. preallocate requested block addresses
 *     b. do not use extent cache for better performance
 *     c. give the block addresses to blockdev
 */
static int get_data_block(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	unsigned int blkbits = inode->i_sb->s_blocksize_bits;
	unsigned maxblocks = bh_result->b_size >> blkbits;
	struct dnode_of_data dn;
	int mode = create ? ALLOC_NODE : LOOKUP_NODE_RA;
	pgoff_t pgofs, end_offset;
	int err = 0, ofs = 1;
	bool allocated = false;

	/* Get the page offset from the block offset(iblock) */
	pgofs =	(pgoff_t)(iblock >> (PAGE_CACHE_SHIFT - blkbits));

	if (check_extent_cache(inode, pgofs, bh_result))
		goto out;

	if (create)
		f2fs_lock_op(sbi);

	/* When reading holes, we need its node page */
	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = get_dnode_of_data(&dn, pgofs, mode);
	if (err) {
		if (err == -ENOENT)
			err = 0;
		goto unlock_out;
	}
	if (dn.data_blkaddr == NEW_ADDR)
		goto put_out;

	if (dn.data_blkaddr != NULL_ADDR) {
		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
	} else if (create) {
		err = __allocate_data_block(&dn);
		if (err)
			goto put_out;
		allocated = true;
		map_bh(bh_result, inode->i_sb, dn.data_blkaddr);
	} else {
		goto put_out;
	}

	end_offset = ADDRS_PER_PAGE(dn.node_page, F2FS_I(inode));
	bh_result->b_size = (((size_t)1) << blkbits);
	dn.ofs_in_node++;
	pgofs++;

get_next:
	if (dn.ofs_in_node >= end_offset) {
		if (allocated)
			sync_inode_page(&dn);
		allocated = false;
		f2fs_put_dnode(&dn);

		set_new_dnode(&dn, inode, NULL, NULL, 0);
		err = get_dnode_of_data(&dn, pgofs, mode);
		if (err) {
			if (err == -ENOENT)
				err = 0;
			goto unlock_out;
		}
		if (dn.data_blkaddr == NEW_ADDR)
			goto put_out;

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

	if (maxblocks > (bh_result->b_size >> blkbits)) {
		block_t blkaddr = datablock_addr(dn.node_page, dn.ofs_in_node);
		if (blkaddr == NULL_ADDR && create) {
			err = __allocate_data_block(&dn);
			if (err)
				goto sync_out;
			allocated = true;
			blkaddr = dn.data_blkaddr;
		}
		/* Give more consecutive addresses for the read ahead */
		if (blkaddr == (bh_result->b_blocknr + ofs)) {
			ofs++;
			dn.ofs_in_node++;
			pgofs++;
			bh_result->b_size += (((size_t)1) << blkbits);
			goto get_next;
		}
	}
sync_out:
	if (allocated)
		sync_inode_page(&dn);
put_out:
	f2fs_put_dnode(&dn);
unlock_out:
	if (create)
		f2fs_unlock_op(sbi);
out:
	trace_f2fs_get_data_block(inode, iblock, bh_result, err);
	return err;
}

static int f2fs_read_data_page(struct file *file, struct page *page)
{
	struct inode *inode = page->mapping->host;
	int ret;

	/* If the file has inline data, try to read it directlly */
	if (f2fs_has_inline_data(inode))
		ret = f2fs_read_inline_data(inode, page);
	else
		ret = mpage_readpage(page, get_data_block);

	return ret;
}

static int f2fs_read_data_pages(struct file *file,
			struct address_space *mapping,
			struct list_head *pages, unsigned nr_pages)
{
	struct inode *inode = file->f_mapping->host;

	/* If the file has inline data, skip readpages */
	if (f2fs_has_inline_data(inode))
		return 0;

	return mpage_readpages(mapping, pages, nr_pages, get_data_block);
}

int do_write_data_page(struct page *page, struct f2fs_io_info *fio)
{
	struct inode *inode = page->mapping->host;
	block_t old_blkaddr, new_blkaddr;
	struct dnode_of_data dn;
	int err = 0;

	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
	if (err)
		return err;

	old_blkaddr = dn.data_blkaddr;

	/* This page is already truncated */
	if (old_blkaddr == NULL_ADDR)
		goto out_writepage;

	set_page_writeback(page);

	/*
	 * If current allocation needs SSR,
	 * it had better in-place writes for updated data.
	 */
	if (unlikely(old_blkaddr != NEW_ADDR &&
			!is_cold_data(page) &&
			need_inplace_update(inode))) {
		rewrite_data_page(page, old_blkaddr, fio);
	} else {
		write_data_page(page, &dn, &new_blkaddr, fio);
		update_extent_cache(new_blkaddr, &dn);
	}
out_writepage:
	f2fs_put_dnode(&dn);
	return err;
}

static int f2fs_write_data_page(struct page *page,
					struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	loff_t i_size = i_size_read(inode);
	const pgoff_t end_index = ((unsigned long long) i_size)
							>> PAGE_CACHE_SHIFT;
	unsigned offset = 0;
	bool need_balance_fs = false;
	int err = 0;
	struct f2fs_io_info fio = {
		.type = DATA,
		.rw = (wbc->sync_mode == WB_SYNC_ALL) ? WRITE_SYNC : WRITE,
	};

	if (page->index < end_index)
		goto write;

	/*
	 * If the offset is out-of-range of file size,
	 * this page does not have to be written to disk.
	 */
	offset = i_size & (PAGE_CACHE_SIZE - 1);
	if ((page->index >= end_index + 1) || !offset)
		goto out;

	zero_user_segment(page, offset, PAGE_CACHE_SIZE);
write:
	if (unlikely(sbi->por_doing))
		goto redirty_out;

	/* Dentry blocks are controlled by checkpoint */
	if (S_ISDIR(inode->i_mode)) {
		err = do_write_data_page(page, &fio);
		goto done;
	}

	if (!wbc->for_reclaim)
		need_balance_fs = true;
	else if (has_not_enough_free_secs(sbi, 0))
		goto redirty_out;

	f2fs_lock_op(sbi);
	if (f2fs_has_inline_data(inode) || f2fs_may_inline(inode))
		err = f2fs_write_inline_data(inode, page, offset);
	else
		err = do_write_data_page(page, &fio);
	f2fs_unlock_op(sbi);
done:
	if (err && err != -ENOENT)
		goto redirty_out;

	clear_cold_data(page);
out:
	inode_dec_dirty_dents(inode);
	unlock_page(page);
	if (need_balance_fs)
		f2fs_balance_fs(sbi);
	if (wbc->for_reclaim)
		f2fs_submit_merged_bio(sbi, DATA, WRITE);
	return 0;

redirty_out:
	redirty_page_for_writepage(wbc, page);
	return AOP_WRITEPAGE_ACTIVATE;
}

static int __f2fs_writepage(struct page *page, struct writeback_control *wbc,
			void *data)
{
	struct address_space *mapping = data;
	int ret = mapping->a_ops->writepage(page, wbc);
	mapping_set_error(mapping, ret);
	return ret;
}

static int f2fs_write_data_pages(struct address_space *mapping,
			    struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	bool locked = false;
	int ret;
	long diff;

	/* deal with chardevs and other special file */
	if (!mapping->a_ops->writepage)
		return 0;

	if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
			get_dirty_dents(inode) < nr_pages_to_skip(sbi, DATA) &&
			available_free_memory(sbi, DIRTY_DENTS))
		goto skip_write;

	diff = nr_pages_to_write(sbi, DATA, wbc);

	if (!S_ISDIR(inode->i_mode)) {
		mutex_lock(&sbi->writepages);
		locked = true;
	}
	ret = write_cache_pages(mapping, wbc, __f2fs_writepage, mapping);
	if (locked)
		mutex_unlock(&sbi->writepages);

	f2fs_submit_merged_bio(sbi, DATA, WRITE);

	remove_dirty_dir_inode(inode);

	wbc->nr_to_write = max((long)0, wbc->nr_to_write - diff);
	return ret;

skip_write:
	wbc->pages_skipped += get_dirty_dents(inode);
	return 0;
}

static int f2fs_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;
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct page *page;
	pgoff_t index = ((unsigned long long) pos) >> PAGE_CACHE_SHIFT;
	struct dnode_of_data dn;
	int err = 0;

	trace_f2fs_write_begin(inode, pos, len, flags);

	f2fs_balance_fs(sbi);
repeat:
	err = f2fs_convert_inline_data(inode, pos + len);
	if (err)
		return err;

	page = grab_cache_page_write_begin(mapping, index, flags);
	if (!page)
		return -ENOMEM;

	/* to avoid latency during memory pressure */
	unlock_page(page);

	*pagep = page;

	if (f2fs_has_inline_data(inode) && (pos + len) <= MAX_INLINE_DATA)
		goto inline_data;

	f2fs_lock_op(sbi);
	set_new_dnode(&dn, inode, NULL, NULL, 0);
	err = f2fs_reserve_block(&dn, index);
	f2fs_unlock_op(sbi);

	if (err) {
		f2fs_put_page(page, 0);
		return err;
	}
inline_data:
	lock_page(page);
	if (unlikely(page->mapping != mapping)) {
		f2fs_put_page(page, 1);
		goto repeat;
	}

	f2fs_wait_on_page_writeback(page, DATA);

	if ((len == PAGE_CACHE_SIZE) || PageUptodate(page))
		return 0;

	if ((pos & PAGE_CACHE_MASK) >= i_size_read(inode)) {
		unsigned start = pos & (PAGE_CACHE_SIZE - 1);
		unsigned end = start + len;

		/* Reading beyond i_size is simple: memset to zero */
		zero_user_segments(page, 0, start, end, PAGE_CACHE_SIZE);
		goto out;
	}

	if (dn.data_blkaddr == NEW_ADDR) {
		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
	} else {
		if (f2fs_has_inline_data(inode)) {
			err = f2fs_read_inline_data(inode, page);
			if (err) {
				page_cache_release(page);
				return err;
			}
		} else {
			err = f2fs_submit_page_bio(sbi, page, dn.data_blkaddr,
							READ_SYNC);
			if (err)
				return err;
		}

		lock_page(page);
		if (unlikely(!PageUptodate(page))) {
			f2fs_put_page(page, 1);
			return -EIO;
		}
		if (unlikely(page->mapping != mapping)) {
			f2fs_put_page(page, 1);
			goto repeat;
		}
	}
out:
	SetPageUptodate(page);
	clear_cold_data(page);
	return 0;
}

static int f2fs_write_end(struct file *file,
			struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	struct inode *inode = page->mapping->host;

	trace_f2fs_write_end(inode, pos, len, copied);

	SetPageUptodate(page);
	set_page_dirty(page);

	if (pos + copied > i_size_read(inode)) {
		i_size_write(inode, pos + copied);
		mark_inode_dirty(inode);
		update_inode_page(inode);
	}

	f2fs_put_page(page, 1);
	return copied;
}

static int check_direct_IO(struct inode *inode, int rw,
		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
{
	unsigned blocksize_mask = inode->i_sb->s_blocksize - 1;
	int i;

	if (rw == READ)
		return 0;

	if (offset & blocksize_mask)
		return -EINVAL;

	for (i = 0; i < nr_segs; i++)
		if (iov[i].iov_len & blocksize_mask)
			return -EINVAL;
	return 0;
}

static ssize_t f2fs_direct_IO(int rw, struct kiocb *iocb,
		const struct iovec *iov, loff_t offset, unsigned long nr_segs)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;

	/* Let buffer I/O handle the inline data case. */
	if (f2fs_has_inline_data(inode))
		return 0;

	if (check_direct_IO(inode, rw, iov, offset, nr_segs))
		return 0;

	return blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs,
							get_data_block);
}

static void f2fs_invalidate_data_page(struct page *page, unsigned int offset,
				      unsigned int length)
{
	struct inode *inode = page->mapping->host;
	if (PageDirty(page))
		inode_dec_dirty_dents(inode);
	ClearPagePrivate(page);
}

static int f2fs_release_data_page(struct page *page, gfp_t wait)
{
	ClearPagePrivate(page);
	return 1;
}

static int f2fs_set_data_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode = mapping->host;

	trace_f2fs_set_page_dirty(page, DATA);

	SetPageUptodate(page);
	mark_inode_dirty(inode);

	if (!PageDirty(page)) {
		__set_page_dirty_nobuffers(page);
		set_dirty_dir_page(inode, page);
		return 1;
	}
	return 0;
}

static sector_t f2fs_bmap(struct address_space *mapping, sector_t block)
{
	struct inode *inode = mapping->host;

	if (f2fs_has_inline_data(inode))
		return 0;

	return generic_block_bmap(mapping, block, get_data_block);
}

const struct address_space_operations f2fs_dblock_aops = {
	.readpage	= f2fs_read_data_page,
	.readpages	= f2fs_read_data_pages,
	.writepage	= f2fs_write_data_page,
	.writepages	= f2fs_write_data_pages,
	.write_begin	= f2fs_write_begin,
	.write_end	= f2fs_write_end,
	.set_page_dirty	= f2fs_set_data_page_dirty,
	.invalidatepage	= f2fs_invalidate_data_page,
	.releasepage	= f2fs_release_data_page,
	.direct_IO	= f2fs_direct_IO,
	.bmap		= f2fs_bmap,
};