aboutsummaryrefslogtreecommitdiff
path: root/fs/fs-writeback.c
blob: 1ce364bbb0037698ecf499132a819058de05ecdf (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
/*
 * fs/fs-writeback.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 *
 * Contains all the functions related to writing back and waiting
 * upon dirty inodes against superblocks, and writing back dirty
 * pages against inodes.  ie: data writeback.  Writeout of the
 * inode itself is not handled here.
 *
 * 10Apr2002	Andrew Morton
 *		Split out of fs/inode.c
 *		Additions for address_space-based writeback
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/buffer_head.h>
#include <linux/tracepoint.h>
#include "internal.h"

/*
 * Passed into wb_writeback(), essentially a subset of writeback_control
 */
struct wb_writeback_work {
	long nr_pages;
	struct super_block *sb;
	enum writeback_sync_modes sync_mode;
	unsigned int for_kupdate:1;
	unsigned int range_cyclic:1;
	unsigned int for_background:1;

	struct list_head list;		/* pending work list */
	struct completion *done;	/* set if the caller waits */
};

/*
 * Include the creation of the trace points after defining the
 * wb_writeback_work structure so that the definition remains local to this
 * file.
 */
#define CREATE_TRACE_POINTS
#include <trace/events/writeback.h>

#define inode_to_bdi(inode)	((inode)->i_mapping->backing_dev_info)

/*
 * We don't actually have pdflush, but this one is exported though /proc...
 */
int nr_pdflush_threads;

/**
 * writeback_in_progress - determine whether there is writeback in progress
 * @bdi: the device's backing_dev_info structure.
 *
 * Determine whether there is writeback waiting to be handled against a
 * backing device.
 */
int writeback_in_progress(struct backing_dev_info *bdi)
{
	return !list_empty(&bdi->work_list);
}

static void bdi_queue_work(struct backing_dev_info *bdi,
		struct wb_writeback_work *work)
{
	trace_writeback_queue(bdi, work);

	spin_lock_bh(&bdi->wb_lock);
	list_add_tail(&work->list, &bdi->work_list);
	if (bdi->wb.task) {
		wake_up_process(bdi->wb.task);
	} else {
		/*
		 * The bdi thread isn't there, wake up the forker thread which
		 * will create and run it.
		 */
		trace_writeback_nothread(bdi, work);
		wake_up_process(default_backing_dev_info.wb.task);
	}
	spin_unlock_bh(&bdi->wb_lock);
}

static void
__bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages,
		bool range_cyclic, bool for_background)
{
	struct wb_writeback_work *work;

	/*
	 * This is WB_SYNC_NONE writeback, so if allocation fails just
	 * wakeup the thread for old dirty data writeback
	 */
	work = kzalloc(sizeof(*work), GFP_ATOMIC);
	if (!work) {
		if (bdi->wb.task) {
			trace_writeback_nowork(bdi);
			wake_up_process(bdi->wb.task);
		}
		return;
	}

	work->sync_mode	= WB_SYNC_NONE;
	work->nr_pages	= nr_pages;
	work->range_cyclic = range_cyclic;
	work->for_background = for_background;

	bdi_queue_work(bdi, work);
}

/**
 * bdi_start_writeback - start writeback
 * @bdi: the backing device to write from
 * @nr_pages: the number of pages to write
 *
 * Description:
 *   This does WB_SYNC_NONE opportunistic writeback. The IO is only
 *   started when this function returns, we make no guarentees on
 *   completion. Caller need not hold sb s_umount semaphore.
 *
 */
void bdi_start_writeback(struct backing_dev_info *bdi, long nr_pages)
{
	__bdi_start_writeback(bdi, nr_pages, true, false);
}

/**
 * bdi_start_background_writeback - start background writeback
 * @bdi: the backing device to write from
 *
 * Description:
 *   This does WB_SYNC_NONE background writeback. The IO is only
 *   started when this function returns, we make no guarentees on
 *   completion. Caller need not hold sb s_umount semaphore.
 */
void bdi_start_background_writeback(struct backing_dev_info *bdi)
{
	__bdi_start_writeback(bdi, LONG_MAX, true, true);
}

/*
 * Redirty an inode: set its when-it-was dirtied timestamp and move it to the
 * furthest end of its superblock's dirty-inode list.
 *
 * Before stamping the inode's ->dirtied_when, we check to see whether it is
 * already the most-recently-dirtied inode on the b_dirty list.  If that is
 * the case then the inode must have been redirtied while it was being written
 * out and we don't reset its dirtied_when.
 */
static void redirty_tail(struct inode *inode)
{
	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;

	if (!list_empty(&wb->b_dirty)) {
		struct inode *tail;

		tail = list_entry(wb->b_dirty.next, struct inode, i_list);
		if (time_before(inode->dirtied_when, tail->dirtied_when))
			inode->dirtied_when = jiffies;
	}
	list_move(&inode->i_list, &wb->b_dirty);
}

/*
 * requeue inode for re-scanning after bdi->b_io list is exhausted.
 */
static void requeue_io(struct inode *inode)
{
	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;

	list_move(&inode->i_list, &wb->b_more_io);
}

static void inode_sync_complete(struct inode *inode)
{
	/*
	 * Prevent speculative execution through spin_unlock(&inode_lock);
	 */
	smp_mb();
	wake_up_bit(&inode->i_state, __I_SYNC);
}

static bool inode_dirtied_after(struct inode *inode, unsigned long t)
{
	bool ret = time_after(inode->dirtied_when, t);
#ifndef CONFIG_64BIT
	/*
	 * For inodes being constantly redirtied, dirtied_when can get stuck.
	 * It _appears_ to be in the future, but is actually in distant past.
	 * This test is necessary to prevent such wrapped-around relative times
	 * from permanently stopping the whole bdi writeback.
	 */
	ret = ret && time_before_eq(inode->dirtied_when, jiffies);
#endif
	return ret;
}

/*
 * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
 */
static void move_expired_inodes(struct list_head *delaying_queue,
			       struct list_head *dispatch_queue,
				unsigned long *older_than_this)
{
	LIST_HEAD(tmp);
	struct list_head *pos, *node;
	struct super_block *sb = NULL;
	struct inode *inode;
	int do_sb_sort = 0;

	while (!list_empty(delaying_queue)) {
		inode = list_entry(delaying_queue->prev, struct inode, i_list);
		if (older_than_this &&
		    inode_dirtied_after(inode, *older_than_this))
			break;
		if (sb && sb != inode->i_sb)
			do_sb_sort = 1;
		sb = inode->i_sb;
		list_move(&inode->i_list, &tmp);
	}

	/* just one sb in list, splice to dispatch_queue and we're done */
	if (!do_sb_sort) {
		list_splice(&tmp, dispatch_queue);
		return;
	}

	/* Move inodes from one superblock together */
	while (!list_empty(&tmp)) {
		inode = list_entry(tmp.prev, struct inode, i_list);
		sb = inode->i_sb;
		list_for_each_prev_safe(pos, node, &tmp) {
			inode = list_entry(pos, struct inode, i_list);
			if (inode->i_sb == sb)
				list_move(&inode->i_list, dispatch_queue);
		}
	}
}

/*
 * Queue all expired dirty inodes for io, eldest first.
 */
static void queue_io(struct bdi_writeback *wb, unsigned long *older_than_this)
{
	list_splice_init(&wb->b_more_io, wb->b_io.prev);
	move_expired_inodes(&wb->b_dirty, &wb->b_io, older_than_this);
}

static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode))
		return inode->i_sb->s_op->write_inode(inode, wbc);
	return 0;
}

/*
 * Wait for writeback on an inode to complete.
 */
static void inode_wait_for_writeback(struct inode *inode)
{
	DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC);
	wait_queue_head_t *wqh;

	wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
	 while (inode->i_state & I_SYNC) {
		spin_unlock(&inode_lock);
		__wait_on_bit(wqh, &wq, inode_wait, TASK_UNINTERRUPTIBLE);
		spin_lock(&inode_lock);
	}
}

/*
 * Write out an inode's dirty pages.  Called under inode_lock.  Either the
 * caller has ref on the inode (either via __iget or via syscall against an fd)
 * or the inode has I_WILL_FREE set (via generic_forget_inode)
 *
 * If `wait' is set, wait on the writeout.
 *
 * The whole writeout design is quite complex and fragile.  We want to avoid
 * starvation of particular inodes when others are being redirtied, prevent
 * livelocks, etc.
 *
 * Called under inode_lock.
 */
static int
writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
{
	struct address_space *mapping = inode->i_mapping;
	unsigned dirty;
	int ret;

	if (!atomic_read(&inode->i_count))
		WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING)));
	else
		WARN_ON(inode->i_state & I_WILL_FREE);

	if (inode->i_state & I_SYNC) {
		/*
		 * If this inode is locked for writeback and we are not doing
		 * writeback-for-data-integrity, move it to b_more_io so that
		 * writeback can proceed with the other inodes on s_io.
		 *
		 * We'll have another go at writing back this inode when we
		 * completed a full scan of b_io.
		 */
		if (wbc->sync_mode != WB_SYNC_ALL) {
			requeue_io(inode);
			return 0;
		}

		/*
		 * It's a data-integrity sync.  We must wait.
		 */
		inode_wait_for_writeback(inode);
	}

	BUG_ON(inode->i_state & I_SYNC);

	/* Set I_SYNC, reset I_DIRTY_PAGES */
	inode->i_state |= I_SYNC;
	inode->i_state &= ~I_DIRTY_PAGES;
	spin_unlock(&inode_lock);

	ret = do_writepages(mapping, wbc);

	/*
	 * Make sure to wait on the data before writing out the metadata.
	 * This is important for filesystems that modify metadata on data
	 * I/O completion.
	 */
	if (wbc->sync_mode == WB_SYNC_ALL) {
		int err = filemap_fdatawait(mapping);
		if (ret == 0)
			ret = err;
	}

	/*
	 * Some filesystems may redirty the inode during the writeback
	 * due to delalloc, clear dirty metadata flags right before
	 * write_inode()
	 */
	spin_lock(&inode_lock);
	dirty = inode->i_state & I_DIRTY;
	inode->i_state &= ~(I_DIRTY_SYNC | I_DIRTY_DATASYNC);
	spin_unlock(&inode_lock);
	/* Don't write the inode if only I_DIRTY_PAGES was set */
	if (dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
		int err = write_inode(inode, wbc);
		if (ret == 0)
			ret = err;
	}

	spin_lock(&inode_lock);
	inode->i_state &= ~I_SYNC;
	if (!(inode->i_state & I_FREEING)) {
		if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) {
			/*
			 * We didn't write back all the pages.  nfs_writepages()
			 * sometimes bales out without doing anything. Redirty
			 * the inode; Move it from b_io onto b_more_io/b_dirty.
			 */
			/*
			 * akpm: if the caller was the kupdate function we put
			 * this inode at the head of b_dirty so it gets first
			 * consideration.  Otherwise, move it to the tail, for
			 * the reasons described there.  I'm not really sure
			 * how much sense this makes.  Presumably I had a good
			 * reasons for doing it this way, and I'd rather not
			 * muck with it at present.
			 */
			if (wbc->for_kupdate) {
				/*
				 * For the kupdate function we move the inode
				 * to b_more_io so it will get more writeout as
				 * soon as the queue becomes uncongested.
				 */
				inode->i_state |= I_DIRTY_PAGES;
				if (wbc->nr_to_write <= 0) {
					/*
					 * slice used up: queue for next turn
					 */
					requeue_io(inode);
				} else {
					/*
					 * somehow blocked: retry later
					 */
					redirty_tail(inode);
				}
			} else {
				/*
				 * Otherwise fully redirty the inode so that
				 * other inodes on this superblock will get some
				 * writeout.  Otherwise heavy writing to one
				 * file would indefinitely suspend writeout of
				 * all the other files.
				 */
				inode->i_state |= I_DIRTY_PAGES;
				redirty_tail(inode);
			}
		} else if (inode->i_state & I_DIRTY) {
			/*
			 * Filesystems can dirty the inode during writeback
			 * operations, such as delayed allocation during
			 * submission or metadata updates after data IO
			 * completion.
			 */
			redirty_tail(inode);
		} else if (atomic_read(&inode->i_count)) {
			/*
			 * The inode is clean, inuse
			 */
			list_move(&inode->i_list, &inode_in_use);
		} else {
			/*
			 * The inode is clean, unused
			 */
			list_move(&inode->i_list, &inode_unused);
		}
	}
	inode_sync_complete(inode);
	return ret;
}

/*
 * For background writeback the caller does not have the sb pinned
 * before calling writeback. So make sure that we do pin it, so it doesn't
 * go away while we are writing inodes from it.
 */
static bool pin_sb_for_writeback(struct super_block *sb)
{
	spin_lock(&sb_lock);
	if (list_empty(&sb->s_instances)) {
		spin_unlock(&sb_lock);
		return false;
	}

	sb->s_count++;
	spin_unlock(&sb_lock);

	if (down_read_trylock(&sb->s_umount)) {
		if (sb->s_root)
			return true;
		up_read(&sb->s_umount);
	}

	put_super(sb);
	return false;
}

/*
 * Write a portion of b_io inodes which belong to @sb.
 *
 * If @only_this_sb is true, then find and write all such
 * inodes. Otherwise write only ones which go sequentially
 * in reverse order.
 *
 * Return 1, if the caller writeback routine should be
 * interrupted. Otherwise return 0.
 */
static int writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb,
		struct writeback_control *wbc, bool only_this_sb)
{
	while (!list_empty(&wb->b_io)) {
		long pages_skipped;
		struct inode *inode = list_entry(wb->b_io.prev,
						 struct inode, i_list);

		if (inode->i_sb != sb) {
			if (only_this_sb) {
				/*
				 * We only want to write back data for this
				 * superblock, move all inodes not belonging
				 * to it back onto the dirty list.
				 */
				redirty_tail(inode);
				continue;
			}

			/*
			 * The inode belongs to a different superblock.
			 * Bounce back to the caller to unpin this and
			 * pin the next superblock.
			 */
			return 0;
		}

		if (inode->i_state & (I_NEW | I_WILL_FREE)) {
			requeue_io(inode);
			continue;
		}
		/*
		 * Was this inode dirtied after sync_sb_inodes was called?
		 * This keeps sync from extra jobs and livelock.
		 */
		if (inode_dirtied_after(inode, wbc->wb_start))
			return 1;

		BUG_ON(inode->i_state & I_FREEING);
		__iget(inode);
		pages_skipped = wbc->pages_skipped;
		writeback_single_inode(inode, wbc);
		if (wbc->pages_skipped != pages_skipped) {
			/*
			 * writeback is not making progress due to locked
			 * buffers.  Skip this inode for now.
			 */
			redirty_tail(inode);
		}
		spin_unlock(&inode_lock);
		iput(inode);
		cond_resched();
		spin_lock(&inode_lock);
		if (wbc->nr_to_write <= 0) {
			wbc->more_io = 1;
			return 1;
		}
		if (!list_empty(&wb->b_more_io))
			wbc->more_io = 1;
	}
	/* b_io is empty */
	return 1;
}

void writeback_inodes_wb(struct bdi_writeback *wb,
		struct writeback_control *wbc)
{
	int ret = 0;

	if (!wbc->wb_start)
		wbc->wb_start = jiffies; /* livelock avoidance */
	spin_lock(&inode_lock);
	if (!wbc->for_kupdate || list_empty(&wb->b_io))
		queue_io(wb, wbc->older_than_this);

	while (!list_empty(&wb->b_io)) {
		struct inode *inode = list_entry(wb->b_io.prev,
						 struct inode, i_list);
		struct super_block *sb = inode->i_sb;

		if (!pin_sb_for_writeback(sb)) {
			requeue_io(inode);
			continue;
		}
		ret = writeback_sb_inodes(sb, wb, wbc, false);
		drop_super(sb);

		if (ret)
			break;
	}
	spin_unlock(&inode_lock);
	/* Leave any unwritten inodes on b_io */
}

static void __writeback_inodes_sb(struct super_block *sb,
		struct bdi_writeback *wb, struct writeback_control *wbc)
{
	WARN_ON(!rwsem_is_locked(&sb->s_umount));

	spin_lock(&inode_lock);
	if (!wbc->for_kupdate || list_empty(&wb->b_io))
		queue_io(wb, wbc->older_than_this);
	writeback_sb_inodes(sb, wb, wbc, true);
	spin_unlock(&inode_lock);
}

/*
 * The maximum number of pages to writeout in a single bdi flush/kupdate
 * operation.  We do this so we don't hold I_SYNC against an inode for
 * enormous amounts of time, which would block a userspace task which has
 * been forced to throttle against that inode.  Also, the code reevaluates
 * the dirty each time it has written this many pages.
 */
#define MAX_WRITEBACK_PAGES     1024

static inline bool over_bground_thresh(void)
{
	unsigned long background_thresh, dirty_thresh;

	global_dirty_limits(&background_thresh, &dirty_thresh);

	return (global_page_state(NR_FILE_DIRTY) +
		global_page_state(NR_UNSTABLE_NFS) >= background_thresh);
}

/*
 * Explicit flushing or periodic writeback of "old" data.
 *
 * Define "old": the first time one of an inode's pages is dirtied, we mark the
 * dirtying-time in the inode's address_space.  So this periodic writeback code
 * just walks the superblock inode list, writing back any inodes which are
 * older than a specific point in time.
 *
 * Try to run once per dirty_writeback_interval.  But if a writeback event
 * takes longer than a dirty_writeback_interval interval, then leave a
 * one-second gap.
 *
 * older_than_this takes precedence over nr_to_write.  So we'll only write back
 * all dirty pages if they are all attached to "old" mappings.
 */
static long wb_writeback(struct bdi_writeback *wb,
			 struct wb_writeback_work *work)
{
	struct writeback_control wbc = {
		.sync_mode		= work->sync_mode,
		.older_than_this	= NULL,
		.for_kupdate		= work->for_kupdate,
		.for_background		= work->for_background,
		.range_cyclic		= work->range_cyclic,
	};
	unsigned long oldest_jif;
	long wrote = 0;
	struct inode *inode;

	if (wbc.for_kupdate) {
		wbc.older_than_this = &oldest_jif;
		oldest_jif = jiffies -
				msecs_to_jiffies(dirty_expire_interval * 10);
	}
	if (!wbc.range_cyclic) {
		wbc.range_start = 0;
		wbc.range_end = LLONG_MAX;
	}

	wbc.wb_start = jiffies; /* livelock avoidance */
	for (;;) {
		/*
		 * Stop writeback when nr_pages has been consumed
		 */
		if (work->nr_pages <= 0)
			break;

		/*
		 * For background writeout, stop when we are below the
		 * background dirty threshold
		 */
		if (work->for_background && !over_bground_thresh())
			break;

		wbc.more_io = 0;
		wbc.nr_to_write = MAX_WRITEBACK_PAGES;
		wbc.pages_skipped = 0;

		trace_wbc_writeback_start(&wbc, wb->bdi);
		if (work->sb)
			__writeback_inodes_sb(work->sb, wb, &wbc);
		else
			writeback_inodes_wb(wb, &wbc);
		trace_wbc_writeback_written(&wbc, wb->bdi);

		work->nr_pages -= MAX_WRITEBACK_PAGES - wbc.nr_to_write;
		wrote += MAX_WRITEBACK_PAGES - wbc.nr_to_write;

		/*
		 * If we consumed everything, see if we have more
		 */
		if (wbc.nr_to_write <= 0)
			continue;
		/*
		 * Didn't write everything and we don't have more IO, bail
		 */
		if (!wbc.more_io)
			break;
		/*
		 * Did we write something? Try for more
		 */
		if (wbc.nr_to_write < MAX_WRITEBACK_PAGES)
			continue;
		/*
		 * Nothing written. Wait for some inode to
		 * become available for writeback. Otherwise
		 * we'll just busyloop.
		 */
		spin_lock(&inode_lock);
		if (!list_empty(&wb->b_more_io))  {
			inode = list_entry(wb->b_more_io.prev,
						struct inode, i_list);
			trace_wbc_writeback_wait(&wbc, wb->bdi);
			inode_wait_for_writeback(inode);
		}
		spin_unlock(&inode_lock);
	}

	return wrote;
}

/*
 * Return the next wb_writeback_work struct that hasn't been processed yet.
 */
static struct wb_writeback_work *
get_next_work_item(struct backing_dev_info *bdi)
{
	struct wb_writeback_work *work = NULL;

	spin_lock_bh(&bdi->wb_lock);
	if (!list_empty(&bdi->work_list)) {
		work = list_entry(bdi->work_list.next,
				  struct wb_writeback_work, list);
		list_del_init(&work->list);
	}
	spin_unlock_bh(&bdi->wb_lock);
	return work;
}

static long wb_check_old_data_flush(struct bdi_writeback *wb)
{
	unsigned long expired;
	long nr_pages;

	/*
	 * When set to zero, disable periodic writeback
	 */
	if (!dirty_writeback_interval)
		return 0;

	expired = wb->last_old_flush +
			msecs_to_jiffies(dirty_writeback_interval * 10);
	if (time_before(jiffies, expired))
		return 0;

	wb->last_old_flush = jiffies;
	nr_pages = global_page_state(NR_FILE_DIRTY) +
			global_page_state(NR_UNSTABLE_NFS) +
			(inodes_stat.nr_inodes - inodes_stat.nr_unused);

	if (nr_pages) {
		struct wb_writeback_work work = {
			.nr_pages	= nr_pages,
			.sync_mode	= WB_SYNC_NONE,
			.for_kupdate	= 1,
			.range_cyclic	= 1,
		};

		return wb_writeback(wb, &work);
	}

	return 0;
}

/*
 * Retrieve work items and do the writeback they describe
 */
long wb_do_writeback(struct bdi_writeback *wb, int force_wait)
{
	struct backing_dev_info *bdi = wb->bdi;
	struct wb_writeback_work *work;
	long wrote = 0;

	while ((work = get_next_work_item(bdi)) != NULL) {
		/*
		 * Override sync mode, in case we must wait for completion
		 * because this thread is exiting now.
		 */
		if (force_wait)
			work->sync_mode = WB_SYNC_ALL;

		trace_writeback_exec(bdi, work);

		wrote += wb_writeback(wb, work);

		/*
		 * Notify the caller of completion if this is a synchronous
		 * work item, otherwise just free it.
		 */
		if (work->done)
			complete(work->done);
		else
			kfree(work);
	}

	/*
	 * Check for periodic writeback, kupdated() style
	 */
	wrote += wb_check_old_data_flush(wb);

	return wrote;
}

/*
 * Handle writeback of dirty data for the device backed by this bdi. Also
 * wakes up periodically and does kupdated style flushing.
 */
int bdi_writeback_thread(void *data)
{
	struct bdi_writeback *wb = data;
	struct backing_dev_info *bdi = wb->bdi;
	long pages_written;

	current->flags |= PF_FLUSHER | PF_SWAPWRITE;
	set_freezable();
	wb->last_active = jiffies;

	/*
	 * Our parent may run at a different priority, just set us to normal
	 */
	set_user_nice(current, 0);

	trace_writeback_thread_start(bdi);

	while (!kthread_should_stop()) {
		/*
		 * Remove own delayed wake-up timer, since we are already awake
		 * and we'll take care of the preriodic write-back.
		 */
		del_timer(&wb->wakeup_timer);

		pages_written = wb_do_writeback(wb, 0);

		trace_writeback_pages_written(pages_written);

		if (pages_written)
			wb->last_active = jiffies;

		set_current_state(TASK_INTERRUPTIBLE);
		if (!list_empty(&bdi->work_list)) {
			__set_current_state(TASK_RUNNING);
			continue;
		}

		if (wb_has_dirty_io(wb) && dirty_writeback_interval)
			schedule_timeout(msecs_to_jiffies(dirty_writeback_interval * 10));
		else {
			/*
			 * We have nothing to do, so can go sleep without any
			 * timeout and save power. When a work is queued or
			 * something is made dirty - we will be woken up.
			 */
			schedule();
		}

		try_to_freeze();
	}

	/* Flush any work that raced with us exiting */
	if (!list_empty(&bdi->work_list))
		wb_do_writeback(wb, 1);

	trace_writeback_thread_stop(bdi);
	return 0;
}


/*
 * Start writeback of `nr_pages' pages.  If `nr_pages' is zero, write back
 * the whole world.
 */
void wakeup_flusher_threads(long nr_pages)
{
	struct backing_dev_info *bdi;

	if (!nr_pages) {
		nr_pages = global_page_state(NR_FILE_DIRTY) +
				global_page_state(NR_UNSTABLE_NFS);
	}

	rcu_read_lock();
	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
		if (!bdi_has_dirty_io(bdi))
			continue;
		__bdi_start_writeback(bdi, nr_pages, false, false);
	}
	rcu_read_unlock();
}

static noinline void block_dump___mark_inode_dirty(struct inode *inode)
{
	if (inode->i_ino || strcmp(inode->i_sb->s_id, "bdev")) {
		struct dentry *dentry;
		const char *name = "?";

		dentry = d_find_alias(inode);
		if (dentry) {
			spin_lock(&dentry->d_lock);
			name = (const char *) dentry->d_name.name;
		}
		printk(KERN_DEBUG
		       "%s(%d): dirtied inode %lu (%s) on %s\n",
		       current->comm, task_pid_nr(current), inode->i_ino,
		       name, inode->i_sb->s_id);
		if (dentry) {
			spin_unlock(&dentry->d_lock);
			dput(dentry);
		}
	}
}

/**
 *	__mark_inode_dirty -	internal function
 *	@inode: inode to mark
 *	@flags: what kind of dirty (i.e. I_DIRTY_SYNC)
 *	Mark an inode as dirty. Callers should use mark_inode_dirty or
 *  	mark_inode_dirty_sync.
 *
 * Put the inode on the super block's dirty list.
 *
 * CAREFUL! We mark it dirty unconditionally, but move it onto the
 * dirty list only if it is hashed or if it refers to a blockdev.
 * If it was not hashed, it will never be added to the dirty list
 * even if it is later hashed, as it will have been marked dirty already.
 *
 * In short, make sure you hash any inodes _before_ you start marking
 * them dirty.
 *
 * This function *must* be atomic for the I_DIRTY_PAGES case -
 * set_page_dirty() is called under spinlock in several places.
 *
 * Note that for blockdevs, inode->dirtied_when represents the dirtying time of
 * the block-special inode (/dev/hda1) itself.  And the ->dirtied_when field of
 * the kernel-internal blockdev inode represents the dirtying time of the
 * blockdev's pages.  This is why for I_DIRTY_PAGES we always use
 * page->mapping->host, so the page-dirtying time is recorded in the internal
 * blockdev inode.
 */
void __mark_inode_dirty(struct inode *inode, int flags)
{
	struct super_block *sb = inode->i_sb;
	struct backing_dev_info *bdi = NULL;
	bool wakeup_bdi = false;

	/*
	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
	 * dirty the inode itself
	 */
	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) {
		if (sb->s_op->dirty_inode)
			sb->s_op->dirty_inode(inode);
	}

	/*
	 * make sure that changes are seen by all cpus before we test i_state
	 * -- mikulas
	 */
	smp_mb();

	/* avoid the locking if we can */
	if ((inode->i_state & flags) == flags)
		return;

	if (unlikely(block_dump))
		block_dump___mark_inode_dirty(inode);

	spin_lock(&inode_lock);
	if ((inode->i_state & flags) != flags) {
		const int was_dirty = inode->i_state & I_DIRTY;

		inode->i_state |= flags;

		/*
		 * If the inode is being synced, just update its dirty state.
		 * The unlocker will place the inode on the appropriate
		 * superblock list, based upon its state.
		 */
		if (inode->i_state & I_SYNC)
			goto out;

		/*
		 * Only add valid (hashed) inodes to the superblock's
		 * dirty list.  Add blockdev inodes as well.
		 */
		if (!S_ISBLK(inode->i_mode)) {
			if (hlist_unhashed(&inode->i_hash))
				goto out;
		}
		if (inode->i_state & I_FREEING)
			goto out;

		/*
		 * If the inode was already on b_dirty/b_io/b_more_io, don't
		 * reposition it (that would break b_dirty time-ordering).
		 */
		if (!was_dirty) {
			bdi = inode_to_bdi(inode);

			if (bdi_cap_writeback_dirty(bdi)) {
				WARN(!test_bit(BDI_registered, &bdi->state),
				     "bdi-%s not registered\n", bdi->name);

				/*
				 * If this is the first dirty inode for this
				 * bdi, we have to wake-up the corresponding
				 * bdi thread to make sure background
				 * write-back happens later.
				 */
				if (!wb_has_dirty_io(&bdi->wb))
					wakeup_bdi = true;
			}

			inode->dirtied_when = jiffies;
			list_move(&inode->i_list, &bdi->wb.b_dirty);
		}
	}
out:
	spin_unlock(&inode_lock);

	if (wakeup_bdi)
		bdi_wakeup_thread_delayed(bdi);
}
EXPORT_SYMBOL(__mark_inode_dirty);

/*
 * Write out a superblock's list of dirty inodes.  A wait will be performed
 * upon no inodes, all inodes or the final one, depending upon sync_mode.
 *
 * If older_than_this is non-NULL, then only write out inodes which
 * had their first dirtying at a time earlier than *older_than_this.
 *
 * If `bdi' is non-zero then we're being asked to writeback a specific queue.
 * This function assumes that the blockdev superblock's inodes are backed by
 * a variety of queues, so all inodes are searched.  For other superblocks,
 * assume that all inodes are backed by the same queue.
 *
 * The inodes to be written are parked on bdi->b_io.  They are moved back onto
 * bdi->b_dirty as they are selected for writing.  This way, none can be missed
 * on the writer throttling path, and we get decent balancing between many
 * throttled threads: we don't want them all piling up on inode_sync_wait.
 */
static void wait_sb_inodes(struct super_block *sb)
{
	struct inode *inode, *old_inode = NULL;

	/*
	 * We need to be protected against the filesystem going from
	 * r/o to r/w or vice versa.
	 */
	WARN_ON(!rwsem_is_locked(&sb->s_umount));

	spin_lock(&inode_lock);

	/*
	 * Data integrity sync. Must wait for all pages under writeback,
	 * because there may have been pages dirtied before our sync
	 * call, but which had writeout started before we write it out.
	 * In which case, the inode may not be on the dirty list, but
	 * we still have to wait for that writeout.
	 */
	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
		struct address_space *mapping;

		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
			continue;
		mapping = inode->i_mapping;
		if (mapping->nrpages == 0)
			continue;
		__iget(inode);
		spin_unlock(&inode_lock);
		/*
		 * We hold a reference to 'inode' so it couldn't have
		 * been removed from s_inodes list while we dropped the
		 * inode_lock.  We cannot iput the inode now as we can
		 * be holding the last reference and we cannot iput it
		 * under inode_lock. So we keep the reference and iput
		 * it later.
		 */
		iput(old_inode);
		old_inode = inode;

		filemap_fdatawait(mapping);

		cond_resched();

		spin_lock(&inode_lock);
	}
	spin_unlock(&inode_lock);
	iput(old_inode);
}

/**
 * writeback_inodes_sb	-	writeback dirty inodes from given super_block
 * @sb: the superblock
 *
 * Start writeback on some inodes on this super_block. No guarantees are made
 * on how many (if any) will be written, and this function does not wait
 * for IO completion of submitted IO. The number of pages submitted is
 * returned.
 */
void writeback_inodes_sb(struct super_block *sb)
{
	unsigned long nr_dirty = global_page_state(NR_FILE_DIRTY);
	unsigned long nr_unstable = global_page_state(NR_UNSTABLE_NFS);
	DECLARE_COMPLETION_ONSTACK(done);
	struct wb_writeback_work work = {
		.sb		= sb,
		.sync_mode	= WB_SYNC_NONE,
		.done		= &done,
	};

	WARN_ON(!rwsem_is_locked(&sb->s_umount));

	work.nr_pages = nr_dirty + nr_unstable +
			(inodes_stat.nr_inodes - inodes_stat.nr_unused);

	bdi_queue_work(sb->s_bdi, &work);
	wait_for_completion(&done);
}
EXPORT_SYMBOL(writeback_inodes_sb);

/**
 * writeback_inodes_sb_if_idle	-	start writeback if none underway
 * @sb: the superblock
 *
 * Invoke writeback_inodes_sb if no writeback is currently underway.
 * Returns 1 if writeback was started, 0 if not.
 */
int writeback_inodes_sb_if_idle(struct super_block *sb)
{
	if (!writeback_in_progress(sb->s_bdi)) {
		down_read(&sb->s_umount);
		writeback_inodes_sb(sb);
		up_read(&sb->s_umount);
		return 1;
	} else
		return 0;
}
EXPORT_SYMBOL(writeback_inodes_sb_if_idle);

/**
 * sync_inodes_sb	-	sync sb inode pages
 * @sb: the superblock
 *
 * This function writes and waits on any dirty inode belonging to this
 * super_block. The number of pages synced is returned.
 */
void sync_inodes_sb(struct super_block *sb)
{
	DECLARE_COMPLETION_ONSTACK(done);
	struct wb_writeback_work work = {
		.sb		= sb,
		.sync_mode	= WB_SYNC_ALL,
		.nr_pages	= LONG_MAX,
		.range_cyclic	= 0,
		.done		= &done,
	};

	WARN_ON(!rwsem_is_locked(&sb->s_umount));

	bdi_queue_work(sb->s_bdi, &work);
	wait_for_completion(&done);

	wait_sb_inodes(sb);
}
EXPORT_SYMBOL(sync_inodes_sb);

/**
 * write_inode_now	-	write an inode to disk
 * @inode: inode to write to disk
 * @sync: whether the write should be synchronous or not
 *
 * This function commits an inode to disk immediately if it is dirty. This is
 * primarily needed by knfsd.
 *
 * The caller must either have a ref on the inode or must have set I_WILL_FREE.
 */
int write_inode_now(struct inode *inode, int sync)
{
	int ret;
	struct writeback_control wbc = {
		.nr_to_write = LONG_MAX,
		.sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE,
		.range_start = 0,
		.range_end = LLONG_MAX,
	};

	if (!mapping_cap_writeback_dirty(inode->i_mapping))
		wbc.nr_to_write = 0;

	might_sleep();
	spin_lock(&inode_lock);
	ret = writeback_single_inode(inode, &wbc);
	spin_unlock(&inode_lock);
	if (sync)
		inode_sync_wait(inode);
	return ret;
}
EXPORT_SYMBOL(write_inode_now);

/**
 * sync_inode - write an inode and its pages to disk.
 * @inode: the inode to sync
 * @wbc: controls the writeback mode
 *
 * sync_inode() will write an inode and its pages to disk.  It will also
 * correctly update the inode on its superblock's dirty inode lists and will
 * update inode->i_state.
 *
 * The caller must have a ref on the inode.
 */
int sync_inode(struct inode *inode, struct writeback_control *wbc)
{
	int ret;

	spin_lock(&inode_lock);
	ret = writeback_single_inode(inode, wbc);
	spin_unlock(&inode_lock);
	return ret;
}
EXPORT_SYMBOL(sync_inode);