summaryrefslogtreecommitdiff
path: root/fs/f2fs/checkpoint.c
blob: 5716e5eb4e8ec7ab2c63c69079259e2c5d772918 (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
/*
 * fs/f2fs/checkpoint.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/bio.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/f2fs_fs.h>
#include <linux/pagevec.h>
#include <linux/swap.h>

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

static struct kmem_cache *orphan_entry_slab;
static struct kmem_cache *inode_entry_slab;

/*
 * We guarantee no failure on the returned page.
 */
struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
	struct address_space *mapping = sbi->meta_inode->i_mapping;
	struct page *page = NULL;
repeat:
	page = grab_cache_page(mapping, index);
	if (!page) {
		cond_resched();
		goto repeat;
	}

	/* We wait writeback only inside grab_meta_page() */
	wait_on_page_writeback(page);
	SetPageUptodate(page);
	return page;
}

/*
 * We guarantee no failure on the returned page.
 */
struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index)
{
	struct address_space *mapping = sbi->meta_inode->i_mapping;
	struct page *page;
repeat:
	page = grab_cache_page(mapping, index);
	if (!page) {
		cond_resched();
		goto repeat;
	}
	if (PageUptodate(page))
		goto out;

	if (f2fs_readpage(sbi, page, index, READ_SYNC))
		goto repeat;

	lock_page(page);
	if (page->mapping != mapping) {
		f2fs_put_page(page, 1);
		goto repeat;
	}
out:
	mark_page_accessed(page);
	return page;
}

static int f2fs_write_meta_page(struct page *page,
				struct writeback_control *wbc)
{
	struct inode *inode = page->mapping->host;
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);

	/* Should not write any meta pages, if any IO error was occurred */
	if (wbc->for_reclaim || sbi->por_doing ||
			is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ERROR_FLAG)) {
		dec_page_count(sbi, F2FS_DIRTY_META);
		wbc->pages_skipped++;
		set_page_dirty(page);
		return AOP_WRITEPAGE_ACTIVATE;
	}

	wait_on_page_writeback(page);

	write_meta_page(sbi, page);
	dec_page_count(sbi, F2FS_DIRTY_META);
	unlock_page(page);
	return 0;
}

static int f2fs_write_meta_pages(struct address_space *mapping,
				struct writeback_control *wbc)
{
	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);
	struct block_device *bdev = sbi->sb->s_bdev;
	long written;

	if (wbc->for_kupdate)
		return 0;

	if (get_pages(sbi, F2FS_DIRTY_META) == 0)
		return 0;

	/* if mounting is failed, skip writing node pages */
	mutex_lock(&sbi->cp_mutex);
	written = sync_meta_pages(sbi, META, bio_get_nr_vecs(bdev));
	mutex_unlock(&sbi->cp_mutex);
	wbc->nr_to_write -= written;
	return 0;
}

long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
						long nr_to_write)
{
	struct address_space *mapping = sbi->meta_inode->i_mapping;
	pgoff_t index = 0, end = LONG_MAX;
	struct pagevec pvec;
	long nwritten = 0;
	struct writeback_control wbc = {
		.for_reclaim = 0,
	};

	pagevec_init(&pvec, 0);

	while (index <= end) {
		int i, nr_pages;
		nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
				PAGECACHE_TAG_DIRTY,
				min(end - index, (pgoff_t)PAGEVEC_SIZE-1) + 1);
		if (nr_pages == 0)
			break;

		for (i = 0; i < nr_pages; i++) {
			struct page *page = pvec.pages[i];
			lock_page(page);
			f2fs_bug_on(page->mapping != mapping);
			f2fs_bug_on(!PageDirty(page));
			clear_page_dirty_for_io(page);
			if (f2fs_write_meta_page(page, &wbc)) {
				unlock_page(page);
				break;
			}
			if (nwritten++ >= nr_to_write)
				break;
		}
		pagevec_release(&pvec);
		cond_resched();
	}

	if (nwritten)
		f2fs_submit_bio(sbi, type, nr_to_write == LONG_MAX);

	return nwritten;
}

static int f2fs_set_meta_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct f2fs_sb_info *sbi = F2FS_SB(mapping->host->i_sb);

	trace_f2fs_set_page_dirty(page, META);

	SetPageUptodate(page);
	if (!PageDirty(page)) {
		__set_page_dirty_nobuffers(page);
		inc_page_count(sbi, F2FS_DIRTY_META);
		return 1;
	}
	return 0;
}

const struct address_space_operations f2fs_meta_aops = {
	.writepage	= f2fs_write_meta_page,
	.writepages	= f2fs_write_meta_pages,
	.set_page_dirty	= f2fs_set_meta_page_dirty,
};

int acquire_orphan_inode(struct f2fs_sb_info *sbi)
{
	unsigned int max_orphans;
	int err = 0;

	/*
	 * considering 512 blocks in a segment 5 blocks are needed for cp
	 * and log segment summaries. Remaining blocks are used to keep
	 * orphan entries with the limitation one reserved segment
	 * for cp pack we can have max 1020*507 orphan entries
	 */
	max_orphans = (sbi->blocks_per_seg - 5) * F2FS_ORPHANS_PER_BLOCK;
	mutex_lock(&sbi->orphan_inode_mutex);
	if (sbi->n_orphans >= max_orphans)
		err = -ENOSPC;
	else
		sbi->n_orphans++;
	mutex_unlock(&sbi->orphan_inode_mutex);
	return err;
}

void release_orphan_inode(struct f2fs_sb_info *sbi)
{
	mutex_lock(&sbi->orphan_inode_mutex);
	f2fs_bug_on(sbi->n_orphans == 0);
	sbi->n_orphans--;
	mutex_unlock(&sbi->orphan_inode_mutex);
}

void add_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
	struct list_head *head, *this;
	struct orphan_inode_entry *new = NULL, *orphan = NULL;

	mutex_lock(&sbi->orphan_inode_mutex);
	head = &sbi->orphan_inode_list;
	list_for_each(this, head) {
		orphan = list_entry(this, struct orphan_inode_entry, list);
		if (orphan->ino == ino)
			goto out;
		if (orphan->ino > ino)
			break;
		orphan = NULL;
	}

	new = f2fs_kmem_cache_alloc(orphan_entry_slab, GFP_ATOMIC);
	new->ino = ino;

	/* add new_oentry into list which is sorted by inode number */
	if (orphan)
		list_add(&new->list, this->prev);
	else
		list_add_tail(&new->list, head);
out:
	mutex_unlock(&sbi->orphan_inode_mutex);
}

void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
	struct list_head *head;
	struct orphan_inode_entry *orphan;

	mutex_lock(&sbi->orphan_inode_mutex);
	head = &sbi->orphan_inode_list;
	list_for_each_entry(orphan, head, list) {
		if (orphan->ino == ino) {
			list_del(&orphan->list);
			kmem_cache_free(orphan_entry_slab, orphan);
			f2fs_bug_on(sbi->n_orphans == 0);
			sbi->n_orphans--;
			break;
		}
	}
	mutex_unlock(&sbi->orphan_inode_mutex);
}

static void recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
	struct inode *inode = f2fs_iget(sbi->sb, ino);
	f2fs_bug_on(IS_ERR(inode));
	clear_nlink(inode);

	/* truncate all the data during iput */
	iput(inode);
}

int recover_orphan_inodes(struct f2fs_sb_info *sbi)
{
	block_t start_blk, orphan_blkaddr, i, j;

	if (!is_set_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG))
		return 0;

	sbi->por_doing = true;
	start_blk = __start_cp_addr(sbi) + 1;
	orphan_blkaddr = __start_sum_addr(sbi) - 1;

	for (i = 0; i < orphan_blkaddr; i++) {
		struct page *page = get_meta_page(sbi, start_blk + i);
		struct f2fs_orphan_block *orphan_blk;

		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
		for (j = 0; j < le32_to_cpu(orphan_blk->entry_count); j++) {
			nid_t ino = le32_to_cpu(orphan_blk->ino[j]);
			recover_orphan_inode(sbi, ino);
		}
		f2fs_put_page(page, 1);
	}
	/* clear Orphan Flag */
	clear_ckpt_flags(F2FS_CKPT(sbi), CP_ORPHAN_PRESENT_FLAG);
	sbi->por_doing = false;
	return 0;
}

static void write_orphan_inodes(struct f2fs_sb_info *sbi, block_t start_blk)
{
	struct list_head *head, *this, *next;
	struct f2fs_orphan_block *orphan_blk = NULL;
	struct page *page = NULL;
	unsigned int nentries = 0;
	unsigned short index = 1;
	unsigned short orphan_blocks;

	orphan_blocks = (unsigned short)((sbi->n_orphans +
		(F2FS_ORPHANS_PER_BLOCK - 1)) / F2FS_ORPHANS_PER_BLOCK);

	mutex_lock(&sbi->orphan_inode_mutex);
	head = &sbi->orphan_inode_list;

	/* loop for each orphan inode entry and write them in Jornal block */
	list_for_each_safe(this, next, head) {
		struct orphan_inode_entry *orphan;

		orphan = list_entry(this, struct orphan_inode_entry, list);

		if (nentries == F2FS_ORPHANS_PER_BLOCK) {
			/*
			 * an orphan block is full of 1020 entries,
			 * then we need to flush current orphan blocks
			 * and bring another one in memory
			 */
			orphan_blk->blk_addr = cpu_to_le16(index);
			orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
			orphan_blk->entry_count = cpu_to_le32(nentries);
			set_page_dirty(page);
			f2fs_put_page(page, 1);
			index++;
			start_blk++;
			nentries = 0;
			page = NULL;
		}
		if (page)
			goto page_exist;

		page = grab_meta_page(sbi, start_blk);
		orphan_blk = (struct f2fs_orphan_block *)page_address(page);
		memset(orphan_blk, 0, sizeof(*orphan_blk));
page_exist:
		orphan_blk->ino[nentries++] = cpu_to_le32(orphan->ino);
	}
	if (!page)
		goto end;

	orphan_blk->blk_addr = cpu_to_le16(index);
	orphan_blk->blk_count = cpu_to_le16(orphan_blocks);
	orphan_blk->entry_count = cpu_to_le32(nentries);
	set_page_dirty(page);
	f2fs_put_page(page, 1);
end:
	mutex_unlock(&sbi->orphan_inode_mutex);
}

static struct page *validate_checkpoint(struct f2fs_sb_info *sbi,
				block_t cp_addr, unsigned long long *version)
{
	struct page *cp_page_1, *cp_page_2 = NULL;
	unsigned long blk_size = sbi->blocksize;
	struct f2fs_checkpoint *cp_block;
	unsigned long long cur_version = 0, pre_version = 0;
	size_t crc_offset;
	__u32 crc = 0;

	/* Read the 1st cp block in this CP pack */
	cp_page_1 = get_meta_page(sbi, cp_addr);

	/* get the version number */
	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_1);
	crc_offset = le32_to_cpu(cp_block->checksum_offset);
	if (crc_offset >= blk_size)
		goto invalid_cp1;

	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
		goto invalid_cp1;

	pre_version = cur_cp_version(cp_block);

	/* Read the 2nd cp block in this CP pack */
	cp_addr += le32_to_cpu(cp_block->cp_pack_total_block_count) - 1;
	cp_page_2 = get_meta_page(sbi, cp_addr);

	cp_block = (struct f2fs_checkpoint *)page_address(cp_page_2);
	crc_offset = le32_to_cpu(cp_block->checksum_offset);
	if (crc_offset >= blk_size)
		goto invalid_cp2;

	crc = le32_to_cpu(*((__u32 *)((unsigned char *)cp_block + crc_offset)));
	if (!f2fs_crc_valid(crc, cp_block, crc_offset))
		goto invalid_cp2;

	cur_version = cur_cp_version(cp_block);

	if (cur_version == pre_version) {
		*version = cur_version;
		f2fs_put_page(cp_page_2, 1);
		return cp_page_1;
	}
invalid_cp2:
	f2fs_put_page(cp_page_2, 1);
invalid_cp1:
	f2fs_put_page(cp_page_1, 1);
	return NULL;
}

int get_valid_checkpoint(struct f2fs_sb_info *sbi)
{
	struct f2fs_checkpoint *cp_block;
	struct f2fs_super_block *fsb = sbi->raw_super;
	struct page *cp1, *cp2, *cur_page;
	unsigned long blk_size = sbi->blocksize;
	unsigned long long cp1_version = 0, cp2_version = 0;
	unsigned long long cp_start_blk_no;

	sbi->ckpt = kzalloc(blk_size, GFP_KERNEL);
	if (!sbi->ckpt)
		return -ENOMEM;
	/*
	 * Finding out valid cp block involves read both
	 * sets( cp pack1 and cp pack 2)
	 */
	cp_start_blk_no = le32_to_cpu(fsb->cp_blkaddr);
	cp1 = validate_checkpoint(sbi, cp_start_blk_no, &cp1_version);

	/* The second checkpoint pack should start at the next segment */
	cp_start_blk_no += 1 << le32_to_cpu(fsb->log_blocks_per_seg);
	cp2 = validate_checkpoint(sbi, cp_start_blk_no, &cp2_version);

	if (cp1 && cp2) {
		if (ver_after(cp2_version, cp1_version))
			cur_page = cp2;
		else
			cur_page = cp1;
	} else if (cp1) {
		cur_page = cp1;
	} else if (cp2) {
		cur_page = cp2;
	} else {
		goto fail_no_cp;
	}

	cp_block = (struct f2fs_checkpoint *)page_address(cur_page);
	memcpy(sbi->ckpt, cp_block, blk_size);

	f2fs_put_page(cp1, 1);
	f2fs_put_page(cp2, 1);
	return 0;

fail_no_cp:
	kfree(sbi->ckpt);
	return -EINVAL;
}

static int __add_dirty_inode(struct inode *inode, struct dir_inode_entry *new)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct list_head *head = &sbi->dir_inode_list;
	struct list_head *this;

	list_for_each(this, head) {
		struct dir_inode_entry *entry;
		entry = list_entry(this, struct dir_inode_entry, list);
		if (entry->inode == inode)
			return -EEXIST;
	}
	list_add_tail(&new->list, head);
	stat_inc_dirty_dir(sbi);
	return 0;
}

void set_dirty_dir_page(struct inode *inode, struct page *page)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct dir_inode_entry *new;

	if (!S_ISDIR(inode->i_mode))
		return;

	new = f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);
	new->inode = inode;
	INIT_LIST_HEAD(&new->list);

	spin_lock(&sbi->dir_inode_lock);
	if (__add_dirty_inode(inode, new))
		kmem_cache_free(inode_entry_slab, new);

	inc_page_count(sbi, F2FS_DIRTY_DENTS);
	inode_inc_dirty_dents(inode);
	SetPagePrivate(page);
	spin_unlock(&sbi->dir_inode_lock);
}

void add_dirty_dir_inode(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct dir_inode_entry *new =
			f2fs_kmem_cache_alloc(inode_entry_slab, GFP_NOFS);

	new->inode = inode;
	INIT_LIST_HEAD(&new->list);

	spin_lock(&sbi->dir_inode_lock);
	if (__add_dirty_inode(inode, new))
		kmem_cache_free(inode_entry_slab, new);
	spin_unlock(&sbi->dir_inode_lock);
}

void remove_dirty_dir_inode(struct inode *inode)
{
	struct f2fs_sb_info *sbi = F2FS_SB(inode->i_sb);
	struct list_head *head = &sbi->dir_inode_list;
	struct list_head *this;

	if (!S_ISDIR(inode->i_mode))
		return;

	spin_lock(&sbi->dir_inode_lock);
	if (atomic_read(&F2FS_I(inode)->dirty_dents)) {
		spin_unlock(&sbi->dir_inode_lock);
		return;
	}

	list_for_each(this, head) {
		struct dir_inode_entry *entry;
		entry = list_entry(this, struct dir_inode_entry, list);
		if (entry->inode == inode) {
			list_del(&entry->list);
			kmem_cache_free(inode_entry_slab, entry);
			stat_dec_dirty_dir(sbi);
			break;
		}
	}
	spin_unlock(&sbi->dir_inode_lock);

	/* Only from the recovery routine */
	if (is_inode_flag_set(F2FS_I(inode), FI_DELAY_IPUT)) {
		clear_inode_flag(F2FS_I(inode), FI_DELAY_IPUT);
		iput(inode);
	}
}

struct inode *check_dirty_dir_inode(struct f2fs_sb_info *sbi, nid_t ino)
{
	struct list_head *head = &sbi->dir_inode_list;
	struct list_head *this;
	struct inode *inode = NULL;

	spin_lock(&sbi->dir_inode_lock);
	list_for_each(this, head) {
		struct dir_inode_entry *entry;
		entry = list_entry(this, struct dir_inode_entry, list);
		if (entry->inode->i_ino == ino) {
			inode = entry->inode;
			break;
		}
	}
	spin_unlock(&sbi->dir_inode_lock);
	return inode;
}

void sync_dirty_dir_inodes(struct f2fs_sb_info *sbi)
{
	struct list_head *head = &sbi->dir_inode_list;
	struct dir_inode_entry *entry;
	struct inode *inode;
retry:
	spin_lock(&sbi->dir_inode_lock);
	if (list_empty(head)) {
		spin_unlock(&sbi->dir_inode_lock);
		return;
	}
	entry = list_entry(head->next, struct dir_inode_entry, list);
	inode = igrab(entry->inode);
	spin_unlock(&sbi->dir_inode_lock);
	if (inode) {
		filemap_flush(inode->i_mapping);
		iput(inode);
	} else {
		/*
		 * We should submit bio, since it exists several
		 * wribacking dentry pages in the freeing inode.
		 */
		f2fs_submit_bio(sbi, DATA, true);
	}
	goto retry;
}

/*
 * Freeze all the FS-operations for checkpoint.
 */
static void block_operations(struct f2fs_sb_info *sbi)
{
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = LONG_MAX,
		.for_reclaim = 0,
	};
	struct blk_plug plug;

	blk_start_plug(&plug);

retry_flush_dents:
	f2fs_lock_all(sbi);
	/* write all the dirty dentry pages */
	if (get_pages(sbi, F2FS_DIRTY_DENTS)) {
		f2fs_unlock_all(sbi);
		sync_dirty_dir_inodes(sbi);
		goto retry_flush_dents;
	}

	/*
	 * POR: we should ensure that there is no dirty node pages
	 * until finishing nat/sit flush.
	 */
retry_flush_nodes:
	mutex_lock(&sbi->node_write);

	if (get_pages(sbi, F2FS_DIRTY_NODES)) {
		mutex_unlock(&sbi->node_write);
		sync_node_pages(sbi, 0, &wbc);
		goto retry_flush_nodes;
	}
	blk_finish_plug(&plug);
}

static void unblock_operations(struct f2fs_sb_info *sbi)
{
	mutex_unlock(&sbi->node_write);
	f2fs_unlock_all(sbi);
}

static void wait_on_all_pages_writeback(struct f2fs_sb_info *sbi)
{
	DEFINE_WAIT(wait);

	for (;;) {
		prepare_to_wait(&sbi->cp_wait, &wait, TASK_UNINTERRUPTIBLE);

		if (!get_pages(sbi, F2FS_WRITEBACK))
			break;

		io_schedule();
	}
	finish_wait(&sbi->cp_wait, &wait);
}

static void do_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
	nid_t last_nid = 0;
	block_t start_blk;
	struct page *cp_page;
	unsigned int data_sum_blocks, orphan_blocks;
	__u32 crc32 = 0;
	void *kaddr;
	int i;

	/* Flush all the NAT/SIT pages */
	while (get_pages(sbi, F2FS_DIRTY_META))
		sync_meta_pages(sbi, META, LONG_MAX);

	next_free_nid(sbi, &last_nid);

	/*
	 * modify checkpoint
	 * version number is already updated
	 */
	ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
	ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
	ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
	for (i = 0; i < 3; i++) {
		ckpt->cur_node_segno[i] =
			cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_NODE));
		ckpt->cur_node_blkoff[i] =
			cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_NODE));
		ckpt->alloc_type[i + CURSEG_HOT_NODE] =
				curseg_alloc_type(sbi, i + CURSEG_HOT_NODE);
	}
	for (i = 0; i < 3; i++) {
		ckpt->cur_data_segno[i] =
			cpu_to_le32(curseg_segno(sbi, i + CURSEG_HOT_DATA));
		ckpt->cur_data_blkoff[i] =
			cpu_to_le16(curseg_blkoff(sbi, i + CURSEG_HOT_DATA));
		ckpt->alloc_type[i + CURSEG_HOT_DATA] =
				curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
	}

	ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
	ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
	ckpt->next_free_nid = cpu_to_le32(last_nid);

	/* 2 cp  + n data seg summary + orphan inode blocks */
	data_sum_blocks = npages_for_summary_flush(sbi);
	if (data_sum_blocks < 3)
		set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
	else
		clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);

	orphan_blocks = (sbi->n_orphans + F2FS_ORPHANS_PER_BLOCK - 1)
					/ F2FS_ORPHANS_PER_BLOCK;
	ckpt->cp_pack_start_sum = cpu_to_le32(1 + orphan_blocks);

	if (is_umount) {
		set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
			data_sum_blocks + orphan_blocks + NR_CURSEG_NODE_TYPE);
	} else {
		clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
		ckpt->cp_pack_total_block_count = cpu_to_le32(2 +
			data_sum_blocks + orphan_blocks);
	}

	if (sbi->n_orphans)
		set_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);
	else
		clear_ckpt_flags(ckpt, CP_ORPHAN_PRESENT_FLAG);

	/* update SIT/NAT bitmap */
	get_sit_bitmap(sbi, __bitmap_ptr(sbi, SIT_BITMAP));
	get_nat_bitmap(sbi, __bitmap_ptr(sbi, NAT_BITMAP));

	crc32 = f2fs_crc32(ckpt, le32_to_cpu(ckpt->checksum_offset));
	*((__le32 *)((unsigned char *)ckpt +
				le32_to_cpu(ckpt->checksum_offset)))
				= cpu_to_le32(crc32);

	start_blk = __start_cp_addr(sbi);

	/* write out checkpoint buffer at block 0 */
	cp_page = grab_meta_page(sbi, start_blk++);
	kaddr = page_address(cp_page);
	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
	set_page_dirty(cp_page);
	f2fs_put_page(cp_page, 1);

	if (sbi->n_orphans) {
		write_orphan_inodes(sbi, start_blk);
		start_blk += orphan_blocks;
	}

	write_data_summaries(sbi, start_blk);
	start_blk += data_sum_blocks;
	if (is_umount) {
		write_node_summaries(sbi, start_blk);
		start_blk += NR_CURSEG_NODE_TYPE;
	}

	/* writeout checkpoint block */
	cp_page = grab_meta_page(sbi, start_blk);
	kaddr = page_address(cp_page);
	memcpy(kaddr, ckpt, (1 << sbi->log_blocksize));
	set_page_dirty(cp_page);
	f2fs_put_page(cp_page, 1);

	/* wait for previous submitted node/meta pages writeback */
	wait_on_all_pages_writeback(sbi);

	filemap_fdatawait_range(sbi->node_inode->i_mapping, 0, LONG_MAX);
	filemap_fdatawait_range(sbi->meta_inode->i_mapping, 0, LONG_MAX);

	/* update user_block_counts */
	sbi->last_valid_block_count = sbi->total_valid_block_count;
	sbi->alloc_valid_block_count = 0;

	/* Here, we only have one bio having CP pack */
	sync_meta_pages(sbi, META_FLUSH, LONG_MAX);

	if (!is_set_ckpt_flags(ckpt, CP_ERROR_FLAG)) {
		clear_prefree_segments(sbi);
		F2FS_RESET_SB_DIRT(sbi);
	}
}

/*
 * We guarantee that this checkpoint procedure should not fail.
 */
void write_checkpoint(struct f2fs_sb_info *sbi, bool is_umount)
{
	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
	unsigned long long ckpt_ver;

	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "start block_ops");

	mutex_lock(&sbi->cp_mutex);
	block_operations(sbi);

	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish block_ops");

	f2fs_submit_bio(sbi, DATA, true);
	f2fs_submit_bio(sbi, NODE, true);
	f2fs_submit_bio(sbi, META, true);

	/*
	 * update checkpoint pack index
	 * Increase the version number so that
	 * SIT entries and seg summaries are written at correct place
	 */
	ckpt_ver = cur_cp_version(ckpt);
	ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);

	/* write cached NAT/SIT entries to NAT/SIT area */
	flush_nat_entries(sbi);
	flush_sit_entries(sbi);

	/* unlock all the fs_lock[] in do_checkpoint() */
	do_checkpoint(sbi, is_umount);

	unblock_operations(sbi);
	mutex_unlock(&sbi->cp_mutex);

	trace_f2fs_write_checkpoint(sbi->sb, is_umount, "finish checkpoint");
}

void init_orphan_info(struct f2fs_sb_info *sbi)
{
	mutex_init(&sbi->orphan_inode_mutex);
	INIT_LIST_HEAD(&sbi->orphan_inode_list);
	sbi->n_orphans = 0;
}

int __init create_checkpoint_caches(void)
{
	orphan_entry_slab = f2fs_kmem_cache_create("f2fs_orphan_entry",
			sizeof(struct orphan_inode_entry), NULL);
	if (unlikely(!orphan_entry_slab))
		return -ENOMEM;
	inode_entry_slab = f2fs_kmem_cache_create("f2fs_dirty_dir_entry",
			sizeof(struct dir_inode_entry), NULL);
	if (unlikely(!inode_entry_slab)) {
		kmem_cache_destroy(orphan_entry_slab);
		return -ENOMEM;
	}
	return 0;
}

void destroy_checkpoint_caches(void)
{
	kmem_cache_destroy(orphan_entry_slab);
	kmem_cache_destroy(inode_entry_slab);
}