summaryrefslogtreecommitdiffstats
path: root/fs/fs-writeback.c
blob: da355879ba7c55cf9017cf288944a40c5672abad (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
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
/*
 * 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/export.h>
#include <linux/spinlock.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/kthread.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/tracepoint.h>
#include <linux/device.h>
#include "internal.h"

/*
 * 4MB minimal write chunk size
 */
#define MIN_WRITEBACK_PAGES	(4096UL >> (PAGE_CACHE_SHIFT - 10))

struct wb_completion {
	atomic_t		cnt;
};

/*
 * Passed into wb_writeback(), essentially a subset of writeback_control
 */
struct wb_writeback_work {
	long nr_pages;
	struct super_block *sb;
	unsigned long *older_than_this;
	enum writeback_sync_modes sync_mode;
	unsigned int tagged_writepages:1;
	unsigned int for_kupdate:1;
	unsigned int range_cyclic:1;
	unsigned int for_background:1;
	unsigned int for_sync:1;	/* sync(2) WB_SYNC_ALL writeback */
	unsigned int auto_free:1;	/* free on completion */
	unsigned int single_wait:1;
	unsigned int single_done:1;
	enum wb_reason reason;		/* why was writeback initiated? */

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

/*
 * If one wants to wait for one or more wb_writeback_works, each work's
 * ->done should be set to a wb_completion defined using the following
 * macro.  Once all work items are issued with wb_queue_work(), the caller
 * can wait for the completion of all using wb_wait_for_completion().  Work
 * items which are waited upon aren't freed automatically on completion.
 */
#define DEFINE_WB_COMPLETION_ONSTACK(cmpl)				\
	struct wb_completion cmpl = {					\
		.cnt		= ATOMIC_INIT(1),			\
	}


/*
 * If an inode is constantly having its pages dirtied, but then the
 * updates stop dirtytime_expire_interval seconds in the past, it's
 * possible for the worst case time between when an inode has its
 * timestamps updated and when they finally get written out to be two
 * dirtytime_expire_intervals.  We set the default to 12 hours (in
 * seconds), which means most of the time inodes will have their
 * timestamps written to disk after 12 hours, but in the worst case a
 * few inodes might not their timestamps updated for 24 hours.
 */
unsigned int dirtytime_expire_interval = 12 * 60 * 60;

static inline struct inode *wb_inode(struct list_head *head)
{
	return list_entry(head, struct inode, i_wb_list);
}

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

EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage);

static bool wb_io_lists_populated(struct bdi_writeback *wb)
{
	if (wb_has_dirty_io(wb)) {
		return false;
	} else {
		set_bit(WB_has_dirty_io, &wb->state);
		WARN_ON_ONCE(!wb->avg_write_bandwidth);
		atomic_long_add(wb->avg_write_bandwidth,
				&wb->bdi->tot_write_bandwidth);
		return true;
	}
}

static void wb_io_lists_depopulated(struct bdi_writeback *wb)
{
	if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) &&
	    list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) {
		clear_bit(WB_has_dirty_io, &wb->state);
		WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth,
					&wb->bdi->tot_write_bandwidth) < 0);
	}
}

/**
 * inode_wb_list_move_locked - move an inode onto a bdi_writeback IO list
 * @inode: inode to be moved
 * @wb: target bdi_writeback
 * @head: one of @wb->b_{dirty|io|more_io}
 *
 * Move @inode->i_wb_list to @list of @wb and set %WB_has_dirty_io.
 * Returns %true if @inode is the first occupant of the !dirty_time IO
 * lists; otherwise, %false.
 */
static bool inode_wb_list_move_locked(struct inode *inode,
				      struct bdi_writeback *wb,
				      struct list_head *head)
{
	assert_spin_locked(&wb->list_lock);

	list_move(&inode->i_wb_list, head);

	/* dirty_time doesn't count as dirty_io until expiration */
	if (head != &wb->b_dirty_time)
		return wb_io_lists_populated(wb);

	wb_io_lists_depopulated(wb);
	return false;
}

/**
 * inode_wb_list_del_locked - remove an inode from its bdi_writeback IO list
 * @inode: inode to be removed
 * @wb: bdi_writeback @inode is being removed from
 *
 * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and
 * clear %WB_has_dirty_io if all are empty afterwards.
 */
static void inode_wb_list_del_locked(struct inode *inode,
				     struct bdi_writeback *wb)
{
	assert_spin_locked(&wb->list_lock);

	list_del_init(&inode->i_wb_list);
	wb_io_lists_depopulated(wb);
}

static void wb_wakeup(struct bdi_writeback *wb)
{
	spin_lock_bh(&wb->work_lock);
	if (test_bit(WB_registered, &wb->state))
		mod_delayed_work(bdi_wq, &wb->dwork, 0);
	spin_unlock_bh(&wb->work_lock);
}

static void wb_queue_work(struct bdi_writeback *wb,
			  struct wb_writeback_work *work)
{
	trace_writeback_queue(wb->bdi, work);

	spin_lock_bh(&wb->work_lock);
	if (!test_bit(WB_registered, &wb->state)) {
		if (work->single_wait)
			work->single_done = 1;
		goto out_unlock;
	}
	if (work->done)
		atomic_inc(&work->done->cnt);
	list_add_tail(&work->list, &wb->work_list);
	mod_delayed_work(bdi_wq, &wb->dwork, 0);
out_unlock:
	spin_unlock_bh(&wb->work_lock);
}

/**
 * wb_wait_for_completion - wait for completion of bdi_writeback_works
 * @bdi: bdi work items were issued to
 * @done: target wb_completion
 *
 * Wait for one or more work items issued to @bdi with their ->done field
 * set to @done, which should have been defined with
 * DEFINE_WB_COMPLETION_ONSTACK().  This function returns after all such
 * work items are completed.  Work items which are waited upon aren't freed
 * automatically on completion.
 */
static void wb_wait_for_completion(struct backing_dev_info *bdi,
				   struct wb_completion *done)
{
	atomic_dec(&done->cnt);		/* put down the initial count */
	wait_event(bdi->wb_waitq, !atomic_read(&done->cnt));
}

#ifdef CONFIG_CGROUP_WRITEBACK

/**
 * inode_congested - test whether an inode is congested
 * @inode: inode to test for congestion
 * @cong_bits: mask of WB_[a]sync_congested bits to test
 *
 * Tests whether @inode is congested.  @cong_bits is the mask of congestion
 * bits to test and the return value is the mask of set bits.
 *
 * If cgroup writeback is enabled for @inode, the congestion state is
 * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg
 * associated with @inode is congested; otherwise, the root wb's congestion
 * state is used.
 */
int inode_congested(struct inode *inode, int cong_bits)
{
	if (inode) {
		struct bdi_writeback *wb = inode_to_wb(inode);
		if (wb)
			return wb_congested(wb, cong_bits);
	}

	return wb_congested(&inode_to_bdi(inode)->wb, cong_bits);
}
EXPORT_SYMBOL_GPL(inode_congested);

/**
 * wb_wait_for_single_work - wait for completion of a single bdi_writeback_work
 * @bdi: bdi the work item was issued to
 * @work: work item to wait for
 *
 * Wait for the completion of @work which was issued to one of @bdi's
 * bdi_writeback's.  The caller must have set @work->single_wait before
 * issuing it.  This wait operates independently fo
 * wb_wait_for_completion() and also disables automatic freeing of @work.
 */
static void wb_wait_for_single_work(struct backing_dev_info *bdi,
				    struct wb_writeback_work *work)
{
	if (WARN_ON_ONCE(!work->single_wait))
		return;

	wait_event(bdi->wb_waitq, work->single_done);

	/*
	 * Paired with smp_wmb() in wb_do_writeback() and ensures that all
	 * modifications to @work prior to assertion of ->single_done is
	 * visible to the caller once this function returns.
	 */
	smp_rmb();
}

/**
 * wb_split_bdi_pages - split nr_pages to write according to bandwidth
 * @wb: target bdi_writeback to split @nr_pages to
 * @nr_pages: number of pages to write for the whole bdi
 *
 * Split @wb's portion of @nr_pages according to @wb's write bandwidth in
 * relation to the total write bandwidth of all wb's w/ dirty inodes on
 * @wb->bdi.
 */
static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
{
	unsigned long this_bw = wb->avg_write_bandwidth;
	unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth);

	if (nr_pages == LONG_MAX)
		return LONG_MAX;

	/*
	 * This may be called on clean wb's and proportional distribution
	 * may not make sense, just use the original @nr_pages in those
	 * cases.  In general, we wanna err on the side of writing more.
	 */
	if (!tot_bw || this_bw >= tot_bw)
		return nr_pages;
	else
		return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw);
}

/**
 * wb_clone_and_queue_work - clone a wb_writeback_work and issue it to a wb
 * @wb: target bdi_writeback
 * @base_work: source wb_writeback_work
 *
 * Try to make a clone of @base_work and issue it to @wb.  If cloning
 * succeeds, %true is returned; otherwise, @base_work is issued directly
 * and %false is returned.  In the latter case, the caller is required to
 * wait for @base_work's completion using wb_wait_for_single_work().
 *
 * A clone is auto-freed on completion.  @base_work never is.
 */
static bool wb_clone_and_queue_work(struct bdi_writeback *wb,
				    struct wb_writeback_work *base_work)
{
	struct wb_writeback_work *work;

	work = kmalloc(sizeof(*work), GFP_ATOMIC);
	if (work) {
		*work = *base_work;
		work->auto_free = 1;
		work->single_wait = 0;
	} else {
		work = base_work;
		work->auto_free = 0;
		work->single_wait = 1;
	}
	work->single_done = 0;
	wb_queue_work(wb, work);
	return work != base_work;
}

/**
 * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi
 * @bdi: target backing_dev_info
 * @base_work: wb_writeback_work to issue
 * @skip_if_busy: skip wb's which already have writeback in progress
 *
 * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which
 * have dirty inodes.  If @base_work->nr_page isn't %LONG_MAX, it's
 * distributed to the busy wbs according to each wb's proportion in the
 * total active write bandwidth of @bdi.
 */
static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
				  struct wb_writeback_work *base_work,
				  bool skip_if_busy)
{
	long nr_pages = base_work->nr_pages;
	int next_blkcg_id = 0;
	struct bdi_writeback *wb;
	struct wb_iter iter;

	might_sleep();

	if (!bdi_has_dirty_io(bdi))
		return;
restart:
	rcu_read_lock();
	bdi_for_each_wb(wb, bdi, &iter, next_blkcg_id) {
		if (!wb_has_dirty_io(wb) ||
		    (skip_if_busy && writeback_in_progress(wb)))
			continue;

		base_work->nr_pages = wb_split_bdi_pages(wb, nr_pages);
		if (!wb_clone_and_queue_work(wb, base_work)) {
			next_blkcg_id = wb->blkcg_css->id + 1;
			rcu_read_unlock();
			wb_wait_for_single_work(bdi, base_work);
			goto restart;
		}
	}
	rcu_read_unlock();
}

#else	/* CONFIG_CGROUP_WRITEBACK */

static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages)
{
	return nr_pages;
}

static void bdi_split_work_to_wbs(struct backing_dev_info *bdi,
				  struct wb_writeback_work *base_work,
				  bool skip_if_busy)
{
	might_sleep();

	if (bdi_has_dirty_io(bdi) &&
	    (!skip_if_busy || !writeback_in_progress(&bdi->wb))) {
		base_work->auto_free = 0;
		base_work->single_wait = 0;
		base_work->single_done = 0;
		wb_queue_work(&bdi->wb, base_work);
	}
}

#endif	/* CONFIG_CGROUP_WRITEBACK */

void wb_start_writeback(struct bdi_writeback *wb, long nr_pages,
			bool range_cyclic, enum wb_reason reason)
{
	struct wb_writeback_work *work;

	if (!wb_has_dirty_io(wb))
		return;

	/*
	 * 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) {
		trace_writeback_nowork(wb->bdi);
		wb_wakeup(wb);
		return;
	}

	work->sync_mode	= WB_SYNC_NONE;
	work->nr_pages	= nr_pages;
	work->range_cyclic = range_cyclic;
	work->reason	= reason;
	work->auto_free	= 1;

	wb_queue_work(wb, work);
}

/**
 * wb_start_background_writeback - start background writeback
 * @wb: bdi_writback to write from
 *
 * Description:
 *   This makes sure WB_SYNC_NONE background writeback happens. When
 *   this function returns, it is only guaranteed that for given wb
 *   some IO is happening if we are over background dirty threshold.
 *   Caller need not hold sb s_umount semaphore.
 */
void wb_start_background_writeback(struct bdi_writeback *wb)
{
	/*
	 * We just wake up the flusher thread. It will perform background
	 * writeback as soon as there is no other work to do.
	 */
	trace_writeback_wake_background(wb->bdi);
	wb_wakeup(wb);
}

/*
 * Remove the inode from the writeback list it is on.
 */
void inode_wb_list_del(struct inode *inode)
{
	struct bdi_writeback *wb = inode_to_wb(inode);

	spin_lock(&wb->list_lock);
	inode_wb_list_del_locked(inode, wb);
	spin_unlock(&wb->list_lock);
}

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

		tail = wb_inode(wb->b_dirty.next);
		if (time_before(inode->dirtied_when, tail->dirtied_when))
			inode->dirtied_when = jiffies;
	}
	inode_wb_list_move_locked(inode, wb, &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_wb_list_move_locked(inode, wb, &wb->b_more_io);
}

static void inode_sync_complete(struct inode *inode)
{
	inode->i_state &= ~I_SYNC;
	/* If inode is clean an unused, put it into LRU now... */
	inode_add_lru(inode);
	/* Waiters must see I_SYNC cleared before being woken up */
	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;
}

#define EXPIRE_DIRTY_ATIME 0x0001

/*
 * Move expired (dirtied before work->older_than_this) dirty inodes from
 * @delaying_queue to @dispatch_queue.
 */
static int move_expired_inodes(struct list_head *delaying_queue,
			       struct list_head *dispatch_queue,
			       int flags,
			       struct wb_writeback_work *work)
{
	unsigned long *older_than_this = NULL;
	unsigned long expire_time;
	LIST_HEAD(tmp);
	struct list_head *pos, *node;
	struct super_block *sb = NULL;
	struct inode *inode;
	int do_sb_sort = 0;
	int moved = 0;

	if ((flags & EXPIRE_DIRTY_ATIME) == 0)
		older_than_this = work->older_than_this;
	else if (!work->for_sync) {
		expire_time = jiffies - (dirtytime_expire_interval * HZ);
		older_than_this = &expire_time;
	}
	while (!list_empty(delaying_queue)) {
		inode = wb_inode(delaying_queue->prev);
		if (older_than_this &&
		    inode_dirtied_after(inode, *older_than_this))
			break;
		list_move(&inode->i_wb_list, &tmp);
		moved++;
		if (flags & EXPIRE_DIRTY_ATIME)
			set_bit(__I_DIRTY_TIME_EXPIRED, &inode->i_state);
		if (sb_is_blkdev_sb(inode->i_sb))
			continue;
		if (sb && sb != inode->i_sb)
			do_sb_sort = 1;
		sb = inode->i_sb;
	}

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

	/* Move inodes from one superblock together */
	while (!list_empty(&tmp)) {
		sb = wb_inode(tmp.prev)->i_sb;
		list_for_each_prev_safe(pos, node, &tmp) {
			inode = wb_inode(pos);
			if (inode->i_sb == sb)
				list_move(&inode->i_wb_list, dispatch_queue);
		}
	}
out:
	return moved;
}

/*
 * Queue all expired dirty inodes for io, eldest first.
 * Before
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    gf         edc     BA
 * After
 *         newly dirtied     b_dirty    b_io    b_more_io
 *         =============>    g          fBAedc
 *                                           |
 *                                           +--> dequeue for IO
 */
static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work)
{
	int moved;

	assert_spin_locked(&wb->list_lock);
	list_splice_init(&wb->b_more_io, &wb->b_io);
	moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, 0, work);
	moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io,
				     EXPIRE_DIRTY_ATIME, work);
	if (moved)
		wb_io_lists_populated(wb);
	trace_writeback_queue_io(wb, work, moved);
}

static int write_inode(struct inode *inode, struct writeback_control *wbc)
{
	int ret;

	if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) {
		trace_writeback_write_inode_start(inode, wbc);
		ret = inode->i_sb->s_op->write_inode(inode, wbc);
		trace_writeback_write_inode(inode, wbc);
		return ret;
	}
	return 0;
}

/*
 * Wait for writeback on an inode to complete. Called with i_lock held.
 * Caller must make sure inode cannot go away when we drop i_lock.
 */
static void __inode_wait_for_writeback(struct inode *inode)
	__releases(inode->i_lock)
	__acquires(inode->i_lock)
{
	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->i_lock);
		__wait_on_bit(wqh, &wq, bit_wait,
			      TASK_UNINTERRUPTIBLE);
		spin_lock(&inode->i_lock);
	}
}

/*
 * Wait for writeback on an inode to complete. Caller must have inode pinned.
 */
void inode_wait_for_writeback(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	__inode_wait_for_writeback(inode);
	spin_unlock(&inode->i_lock);
}

/*
 * Sleep until I_SYNC is cleared. This function must be called with i_lock
 * held and drops it. It is aimed for callers not holding any inode reference
 * so once i_lock is dropped, inode can go away.
 */
static void inode_sleep_on_writeback(struct inode *inode)
	__releases(inode->i_lock)
{
	DEFINE_WAIT(wait);
	wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC);
	int sleep;

	prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE);
	sleep = inode->i_state & I_SYNC;
	spin_unlock(&inode->i_lock);
	if (sleep)
		schedule();
	finish_wait(wqh, &wait);
}

/*
 * Find proper writeback list for the inode depending on its current state and
 * possibly also change of its state while we were doing writeback.  Here we
 * handle things such as livelock prevention or fairness of writeback among
 * inodes. This function can be called only by flusher thread - noone else
 * processes all inodes in writeback lists and requeueing inodes behind flusher
 * thread's back can have unexpected consequences.
 */
static void requeue_inode(struct inode *inode, struct bdi_writeback *wb,
			  struct writeback_control *wbc)
{
	if (inode->i_state & I_FREEING)
		return;

	/*
	 * Sync livelock prevention. Each inode is tagged and synced in one
	 * shot. If still dirty, it will be redirty_tail()'ed below.  Update
	 * the dirty time to prevent enqueue and sync it again.
	 */
	if ((inode->i_state & I_DIRTY) &&
	    (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages))
		inode->dirtied_when = jiffies;

	if (wbc->pages_skipped) {
		/*
		 * writeback is not making progress due to locked
		 * buffers. Skip this inode for now.
		 */
		redirty_tail(inode, wb);
		return;
	}

	if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) {
		/*
		 * We didn't write back all the pages.  nfs_writepages()
		 * sometimes bales out without doing anything.
		 */
		if (wbc->nr_to_write <= 0) {
			/* Slice used up. Queue for next turn. */
			requeue_io(inode, wb);
		} else {
			/*
			 * Writeback blocked by something other than
			 * congestion. Delay the inode for some time to
			 * avoid spinning on the CPU (100% iowait)
			 * retrying writeback of the dirty page/inode
			 * that cannot be performed immediately.
			 */
			redirty_tail(inode, wb);
		}
	} 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, wb);
	} else if (inode->i_state & I_DIRTY_TIME) {
		inode->dirtied_when = jiffies;
		inode_wb_list_move_locked(inode, wb, &wb->b_dirty_time);
	} else {
		/* The inode is clean. Remove from writeback lists. */
		inode_wb_list_del_locked(inode, wb);
	}
}

/*
 * Write out an inode and its dirty pages. Do not update the writeback list
 * linkage. That is left to the caller. The caller is also responsible for
 * setting I_SYNC flag and calling inode_sync_complete() to clear it.
 */
static int
__writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
{
	struct address_space *mapping = inode->i_mapping;
	long nr_to_write = wbc->nr_to_write;
	unsigned dirty;
	int ret;

	WARN_ON(!(inode->i_state & I_SYNC));

	trace_writeback_single_inode_start(inode, wbc, nr_to_write);

	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. We don't do it for sync(2) writeback because it has a
	 * separate, external IO completion path and ->sync_fs for guaranteeing
	 * inode metadata is written back correctly.
	 */
	if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) {
		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->i_lock);

	dirty = inode->i_state & I_DIRTY;
	if (inode->i_state & I_DIRTY_TIME) {
		if ((dirty & (I_DIRTY_SYNC | I_DIRTY_DATASYNC)) ||
		    unlikely(inode->i_state & I_DIRTY_TIME_EXPIRED) ||
		    unlikely(time_after(jiffies,
					(inode->dirtied_time_when +
					 dirtytime_expire_interval * HZ)))) {
			dirty |= I_DIRTY_TIME | I_DIRTY_TIME_EXPIRED;
			trace_writeback_lazytime(inode);
		}
	} else
		inode->i_state &= ~I_DIRTY_TIME_EXPIRED;
	inode->i_state &= ~dirty;

	/*
	 * Paired with smp_mb() in __mark_inode_dirty().  This allows
	 * __mark_inode_dirty() to test i_state without grabbing i_lock -
	 * either they see the I_DIRTY bits cleared or we see the dirtied
	 * inode.
	 *
	 * I_DIRTY_PAGES is always cleared together above even if @mapping
	 * still has dirty pages.  The flag is reinstated after smp_mb() if
	 * necessary.  This guarantees that either __mark_inode_dirty()
	 * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY.
	 */
	smp_mb();

	if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY))
		inode->i_state |= I_DIRTY_PAGES;

	spin_unlock(&inode->i_lock);

	if (dirty & I_DIRTY_TIME)
		mark_inode_dirty_sync(inode);
	/* Don't write the inode if only I_DIRTY_PAGES was set */
	if (dirty & ~I_DIRTY_PAGES) {
		int err = write_inode(inode, wbc);
		if (ret == 0)
			ret = err;
	}
	trace_writeback_single_inode(inode, wbc, nr_to_write);
	return ret;
}

/*
 * Write out an inode's dirty pages. Either the caller has an active reference
 * on the inode or the inode has I_WILL_FREE set.
 *
 * This function is designed to be called for writing back one inode which
 * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode()
 * and does more profound writeback list handling in writeback_sb_inodes().
 */
static int
writeback_single_inode(struct inode *inode, struct bdi_writeback *wb,
		       struct writeback_control *wbc)
{
	int ret = 0;

	spin_lock(&inode->i_lock);
	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 (wbc->sync_mode != WB_SYNC_ALL)
			goto out;
		/*
		 * It's a data-integrity sync. We must wait. Since callers hold
		 * inode reference or inode has I_WILL_FREE set, it cannot go
		 * away under us.
		 */
		__inode_wait_for_writeback(inode);
	}
	WARN_ON(inode->i_state & I_SYNC);
	/*
	 * Skip inode if it is clean and we have no outstanding writeback in
	 * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this
	 * function since flusher thread may be doing for example sync in
	 * parallel and if we move the inode, it could get skipped. So here we
	 * make sure inode is on some writeback list and leave it there unless
	 * we have completely cleaned the inode.
	 */
	if (!(inode->i_state & I_DIRTY_ALL) &&
	    (wbc->sync_mode != WB_SYNC_ALL ||
	     !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK)))
		goto out;
	inode->i_state |= I_SYNC;
	spin_unlock(&inode->i_lock);

	ret = __writeback_single_inode(inode, wbc);

	spin_lock(&wb->list_lock);
	spin_lock(&inode->i_lock);
	/*
	 * If inode is clean, remove it from writeback lists. Otherwise don't
	 * touch it. See comment above for explanation.
	 */
	if (!(inode->i_state & I_DIRTY_ALL))
		inode_wb_list_del_locked(inode, wb);
	spin_unlock(&wb->list_lock);
	inode_sync_complete(inode);
out:
	spin_unlock(&inode->i_lock);
	return ret;
}

static long writeback_chunk_size(struct bdi_writeback *wb,
				 struct wb_writeback_work *work)
{
	long pages;

	/*
	 * WB_SYNC_ALL mode does livelock avoidance by syncing dirty
	 * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX
	 * here avoids calling into writeback_inodes_wb() more than once.
	 *
	 * The intended call sequence for WB_SYNC_ALL writeback is:
	 *
	 *      wb_writeback()
	 *          writeback_sb_inodes()       <== called only once
	 *              write_cache_pages()     <== called once for each inode
	 *                   (quickly) tag currently dirty pages
	 *                   (maybe slowly) sync all tagged pages
	 */
	if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages)
		pages = LONG_MAX;
	else {
		pages = min(wb->avg_write_bandwidth / 2,
			    global_wb_domain.dirty_limit / DIRTY_SCOPE);
		pages = min(pages, work->nr_pages);
		pages = round_down(pages + MIN_WRITEBACK_PAGES,
				   MIN_WRITEBACK_PAGES);
	}

	return pages;
}

/*
 * Write a portion of b_io inodes which belong to @sb.
 *
 * Return the number of pages and/or inodes written.
 */
static long writeback_sb_inodes(struct super_block *sb,
				struct bdi_writeback *wb,
				struct wb_writeback_work *work)
{
	struct writeback_control wbc = {
		.sync_mode		= work->sync_mode,
		.tagged_writepages	= work->tagged_writepages,
		.for_kupdate		= work->for_kupdate,
		.for_background		= work->for_background,
		.for_sync		= work->for_sync,
		.range_cyclic		= work->range_cyclic,
		.range_start		= 0,
		.range_end		= LLONG_MAX,
	};
	unsigned long start_time = jiffies;
	long write_chunk;
	long wrote = 0;  /* count both pages and inodes */

	while (!list_empty(&wb->b_io)) {
		struct inode *inode = wb_inode(wb->b_io.prev);

		if (inode->i_sb != sb) {
			if (work->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, wb);
				continue;
			}

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

		/*
		 * Don't bother with new inodes or inodes being freed, first
		 * kind does not need periodic writeout yet, and for the latter
		 * kind writeout is handled by the freer.
		 */
		spin_lock(&inode->i_lock);
		if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
			spin_unlock(&inode->i_lock);
			redirty_tail(inode, wb);
			continue;
		}
		if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) {
			/*
			 * 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.
			 */
			spin_unlock(&inode->i_lock);
			requeue_io(inode, wb);
			trace_writeback_sb_inodes_requeue(inode);
			continue;
		}
		spin_unlock(&wb->list_lock);

		/*
		 * We already requeued the inode if it had I_SYNC set and we
		 * are doing WB_SYNC_NONE writeback. So this catches only the
		 * WB_SYNC_ALL case.
		 */
		if (inode->i_state & I_SYNC) {
			/* Wait for I_SYNC. This function drops i_lock... */
			inode_sleep_on_writeback(inode);
			/* Inode may be gone, start again */
			spin_lock(&wb->list_lock);
			continue;
		}
		inode->i_state |= I_SYNC;
		spin_unlock(&inode->i_lock);

		write_chunk = writeback_chunk_size(wb, work);
		wbc.nr_to_write = write_chunk;
		wbc.pages_skipped = 0;

		/*
		 * We use I_SYNC to pin the inode in memory. While it is set
		 * evict_inode() will wait so the inode cannot be freed.
		 */
		__writeback_single_inode(inode, &wbc);

		work->nr_pages -= write_chunk - wbc.nr_to_write;
		wrote += write_chunk - wbc.nr_to_write;
		spin_lock(&wb->list_lock);
		spin_lock(&inode->i_lock);
		if (!(inode->i_state & I_DIRTY_ALL))
			wrote++;
		requeue_inode(inode, wb, &wbc);
		inode_sync_complete(inode);
		spin_unlock(&inode->i_lock);
		cond_resched_lock(&wb->list_lock);
		/*
		 * bail out to wb_writeback() often enough to check
		 * background threshold and other termination conditions.
		 */
		if (wrote) {
			if (time_is_before_jiffies(start_time + HZ / 10UL))
				break;
			if (work->nr_pages <= 0)
				break;
		}
	}
	return wrote;
}

static long __writeback_inodes_wb(struct bdi_writeback *wb,
				  struct wb_writeback_work *work)
{
	unsigned long start_time = jiffies;
	long wrote = 0;

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

		if (!trylock_super(sb)) {
			/*
			 * trylock_super() may fail consistently due to
			 * s_umount being grabbed by someone else. Don't use
			 * requeue_io() to avoid busy retrying the inode/sb.
			 */
			redirty_tail(inode, wb);
			continue;
		}
		wrote += writeback_sb_inodes(sb, wb, work);
		up_read(&sb->s_umount);

		/* refer to the same tests at the end of writeback_sb_inodes */
		if (wrote) {
			if (time_is_before_jiffies(start_time + HZ / 10UL))
				break;
			if (work->nr_pages <= 0)
				break;
		}
	}
	/* Leave any unwritten inodes on b_io */
	return wrote;
}

static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages,
				enum wb_reason reason)
{
	struct wb_writeback_work work = {
		.nr_pages	= nr_pages,
		.sync_mode	= WB_SYNC_NONE,
		.range_cyclic	= 1,
		.reason		= reason,
	};

	spin_lock(&wb->list_lock);
	if (list_empty(&wb->b_io))
		queue_io(wb, &work);
	__writeback_inodes_wb(wb, &work);
	spin_unlock(&wb->list_lock);

	return nr_pages - work.nr_pages;
}

/*
 * 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)
{
	unsigned long wb_start = jiffies;
	long nr_pages = work->nr_pages;
	unsigned long oldest_jif;
	struct inode *inode;
	long progress;

	oldest_jif = jiffies;
	work->older_than_this = &oldest_jif;

	spin_lock(&wb->list_lock);
	for (;;) {
		/*
		 * Stop writeback when nr_pages has been consumed
		 */
		if (work->nr_pages <= 0)
			break;

		/*
		 * Background writeout and kupdate-style writeback may
		 * run forever. Stop them if there is other work to do
		 * so that e.g. sync can proceed. They'll be restarted
		 * after the other works are all done.
		 */
		if ((work->for_background || work->for_kupdate) &&
		    !list_empty(&wb->work_list))
			break;

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

		/*
		 * Kupdate and background works are special and we want to
		 * include all inodes that need writing. Livelock avoidance is
		 * handled by these works yielding to any other work so we are
		 * safe.
		 */
		if (work->for_kupdate) {
			oldest_jif = jiffies -
				msecs_to_jiffies(dirty_expire_interval * 10);
		} else if (work->for_background)
			oldest_jif = jiffies;

		trace_writeback_start(wb->bdi, work);
		if (list_empty(&wb->b_io))
			queue_io(wb, work);
		if (work->sb)
			progress = writeback_sb_inodes(work->sb, wb, work);
		else
			progress = __writeback_inodes_wb(wb, work);
		trace_writeback_written(wb->bdi, work);

		wb_update_bandwidth(wb, wb_start);

		/*
		 * Did we write something? Try for more
		 *
		 * Dirty inodes are moved to b_io for writeback in batches.
		 * The completion of the current batch does not necessarily
		 * mean the overall work is done. So we keep looping as long
		 * as made some progress on cleaning pages or inodes.
		 */
		if (progress)
			continue;
		/*
		 * No more inodes for IO, bail
		 */
		if (list_empty(&wb->b_more_io))
			break;
		/*
		 * Nothing written. Wait for some inode to
		 * become available for writeback. Otherwise
		 * we'll just busyloop.
		 */
		if (!list_empty(&wb->b_more_io))  {
			trace_writeback_wait(wb->bdi, work);
			inode = wb_inode(wb->b_more_io.prev);
			spin_lock(&inode->i_lock);
			spin_unlock(&wb->list_lock);
			/* This function drops i_lock... */
			inode_sleep_on_writeback(inode);
			spin_lock(&wb->list_lock);
		}
	}
	spin_unlock(&wb->list_lock);

	return nr_pages - work->nr_pages;
}

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

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

/*
 * Add in the number of potentially dirty inodes, because each inode
 * write can dirty pagecache in the underlying blockdev.
 */
static unsigned long get_nr_dirty_pages(void)
{
	return global_page_state(NR_FILE_DIRTY) +
		global_page_state(NR_UNSTABLE_NFS) +
		get_nr_dirty_inodes();
}

static long wb_check_background_flush(struct bdi_writeback *wb)
{
	if (wb_over_bg_thresh(wb)) {

		struct wb_writeback_work work = {
			.nr_pages	= LONG_MAX,
			.sync_mode	= WB_SYNC_NONE,
			.for_background	= 1,
			.range_cyclic	= 1,
			.reason		= WB_REASON_BACKGROUND,
		};

		return wb_writeback(wb, &work);
	}

	return 0;
}

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 = get_nr_dirty_pages();

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

		return wb_writeback(wb, &work);
	}

	return 0;
}

/*
 * Retrieve work items and do the writeback they describe
 */
static long wb_do_writeback(struct bdi_writeback *wb)
{
	struct wb_writeback_work *work;
	long wrote = 0;

	set_bit(WB_writeback_running, &wb->state);
	while ((work = get_next_work_item(wb)) != NULL) {
		struct wb_completion *done = work->done;
		bool need_wake_up = false;

		trace_writeback_exec(wb->bdi, work);

		wrote += wb_writeback(wb, work);

		if (work->single_wait) {
			WARN_ON_ONCE(work->auto_free);
			/* paired w/ rmb in wb_wait_for_single_work() */
			smp_wmb();
			work->single_done = 1;
			need_wake_up = true;
		} else if (work->auto_free) {
			kfree(work);
		}

		if (done && atomic_dec_and_test(&done->cnt))
			need_wake_up = true;

		if (need_wake_up)
			wake_up_all(&wb->bdi->wb_waitq);
	}

	/*
	 * Check for periodic writeback, kupdated() style
	 */
	wrote += wb_check_old_data_flush(wb);
	wrote += wb_check_background_flush(wb);
	clear_bit(WB_writeback_running, &wb->state);

	return wrote;
}

/*
 * Handle writeback of dirty data for the device backed by this bdi. Also
 * reschedules periodically and does kupdated style flushing.
 */
void wb_workfn(struct work_struct *work)
{
	struct bdi_writeback *wb = container_of(to_delayed_work(work),
						struct bdi_writeback, dwork);
	long pages_written;

	set_worker_desc("flush-%s", dev_name(wb->bdi->dev));
	current->flags |= PF_SWAPWRITE;

	if (likely(!current_is_workqueue_rescuer() ||
		   !test_bit(WB_registered, &wb->state))) {
		/*
		 * The normal path.  Keep writing back @wb until its
		 * work_list is empty.  Note that this path is also taken
		 * if @wb is shutting down even when we're running off the
		 * rescuer as work_list needs to be drained.
		 */
		do {
			pages_written = wb_do_writeback(wb);
			trace_writeback_pages_written(pages_written);
		} while (!list_empty(&wb->work_list));
	} else {
		/*
		 * bdi_wq can't get enough workers and we're running off
		 * the emergency worker.  Don't hog it.  Hopefully, 1024 is
		 * enough for efficient IO.
		 */
		pages_written = writeback_inodes_wb(wb, 1024,
						    WB_REASON_FORKER_THREAD);
		trace_writeback_pages_written(pages_written);
	}

	if (!list_empty(&wb->work_list))
		mod_delayed_work(bdi_wq, &wb->dwork, 0);
	else if (wb_has_dirty_io(wb) && dirty_writeback_interval)
		wb_wakeup_delayed(wb);

	current->flags &= ~PF_SWAPWRITE;
}

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

	if (!nr_pages)
		nr_pages = get_nr_dirty_pages();

	rcu_read_lock();
	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
		struct bdi_writeback *wb;
		struct wb_iter iter;

		if (!bdi_has_dirty_io(bdi))
			continue;

		bdi_for_each_wb(wb, bdi, &iter, 0)
			wb_start_writeback(wb, wb_split_bdi_pages(wb, nr_pages),
					   false, reason);
	}
	rcu_read_unlock();
}

/*
 * Wake up bdi's periodically to make sure dirtytime inodes gets
 * written back periodically.  We deliberately do *not* check the
 * b_dirtytime list in wb_has_dirty_io(), since this would cause the
 * kernel to be constantly waking up once there are any dirtytime
 * inodes on the system.  So instead we define a separate delayed work
 * function which gets called much more rarely.  (By default, only
 * once every 12 hours.)
 *
 * If there is any other write activity going on in the file system,
 * this function won't be necessary.  But if the only thing that has
 * happened on the file system is a dirtytime inode caused by an atime
 * update, we need this infrastructure below to make sure that inode
 * eventually gets pushed out to disk.
 */
static void wakeup_dirtytime_writeback(struct work_struct *w);
static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback);

static void wakeup_dirtytime_writeback(struct work_struct *w)
{
	struct backing_dev_info *bdi;

	rcu_read_lock();
	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) {
		struct bdi_writeback *wb;
		struct wb_iter iter;

		bdi_for_each_wb(wb, bdi, &iter, 0)
			if (!list_empty(&bdi->wb.b_dirty_time))
				wb_wakeup(&bdi->wb);
	}
	rcu_read_unlock();
	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
}

static int __init start_dirtytime_writeback(void)
{
	schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ);
	return 0;
}
__initcall(start_dirtytime_writeback);

int dirtytime_interval_handler(struct ctl_table *table, int write,
			       void __user *buffer, size_t *lenp, loff_t *ppos)
{
	int ret;

	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
	if (ret == 0 && write)
		mod_delayed_work(system_wq, &dirtytime_work, 0);
	return ret;
}

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.
 *
 * 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.
 */
#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
void __mark_inode_dirty(struct inode *inode, int flags)
{
	struct super_block *sb = inode->i_sb;
	int dirtytime;

	trace_writeback_mark_inode_dirty(inode, flags);

	/*
	 * Don't do this for I_DIRTY_PAGES - that doesn't actually
	 * dirty the inode itself
	 */
	if (flags & (I_DIRTY_SYNC | I_DIRTY_DATASYNC | I_DIRTY_TIME)) {
		trace_writeback_dirty_inode_start(inode, flags);

		if (sb->s_op->dirty_inode)
			sb->s_op->dirty_inode(inode, flags);

		trace_writeback_dirty_inode(inode, flags);
	}
	if (flags & I_DIRTY_INODE)
		flags &= ~I_DIRTY_TIME;
	dirtytime = flags & I_DIRTY_TIME;

	/*
	 * Paired with smp_mb() in __writeback_single_inode() for the
	 * following lockless i_state test.  See there for details.
	 */
	smp_mb();

	if (((inode->i_state & flags) == flags) ||
	    (dirtytime && (inode->i_state & I_DIRTY_INODE)))
		return;

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

	spin_lock(&inode->i_lock);
	if (dirtytime && (inode->i_state & I_DIRTY_INODE))
		goto out_unlock_inode;
	if ((inode->i_state & flags) != flags) {
		const int was_dirty = inode->i_state & I_DIRTY;

		inode_attach_wb(inode, NULL);

		if (flags & I_DIRTY_INODE)
			inode->i_state &= ~I_DIRTY_TIME;
		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_unlock_inode;

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

		/*
		 * 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) {
			struct bdi_writeback *wb = inode_to_wb(inode);
			struct list_head *dirty_list;
			bool wakeup_bdi = false;

			spin_unlock(&inode->i_lock);
			spin_lock(&wb->list_lock);

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

			inode->dirtied_when = jiffies;
			if (dirtytime)
				inode->dirtied_time_when = jiffies;

			if (inode->i_state & (I_DIRTY_INODE | I_DIRTY_PAGES))
				dirty_list = &wb->b_dirty;
			else
				dirty_list = &wb->b_dirty_time;

			wakeup_bdi = inode_wb_list_move_locked(inode, wb,
							       dirty_list);

			spin_unlock(&wb->list_lock);
			trace_writeback_dirty_inode_enqueue(inode);

			/*
			 * 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 (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi)
				wb_wakeup_delayed(wb);
			return;
		}
	}
out_unlock_inode:
	spin_unlock(&inode->i_lock);

}
EXPORT_SYMBOL(__mark_inode_dirty);

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_sb_list_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 = inode->i_mapping;

		spin_lock(&inode->i_lock);
		if ((inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) ||
		    (mapping->nrpages == 0)) {
			spin_unlock(&inode->i_lock);
			continue;
		}
		__iget(inode);
		spin_unlock(&inode->i_lock);
		spin_unlock(&inode_sb_list_lock);

		/*
		 * We hold a reference to 'inode' so it couldn't have been
		 * removed from s_inodes list while we dropped the
		 * inode_sb_list_lock.  We cannot iput the inode now as we can
		 * be holding the last reference and we cannot iput it under
		 * inode_sb_list_lock. So we keep the reference and iput it
		 * later.
		 */
		iput(old_inode);
		old_inode = inode;

		filemap_fdatawait(mapping);

		cond_resched();

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

static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
				     enum wb_reason reason, bool skip_if_busy)
{
	DEFINE_WB_COMPLETION_ONSTACK(done);
	struct wb_writeback_work work = {
		.sb			= sb,
		.sync_mode		= WB_SYNC_NONE,
		.tagged_writepages	= 1,
		.done			= &done,
		.nr_pages		= nr,
		.reason			= reason,
	};
	struct backing_dev_info *bdi = sb->s_bdi;

	if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info)
		return;
	WARN_ON(!rwsem_is_locked(&sb->s_umount));

	bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy);
	wb_wait_for_completion(bdi, &done);
}

/**
 * writeback_inodes_sb_nr -	writeback dirty inodes from given super_block
 * @sb: the superblock
 * @nr: the number of pages to write
 * @reason: reason why some writeback work initiated
 *
 * 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.
 */
void writeback_inodes_sb_nr(struct super_block *sb,
			    unsigned long nr,
			    enum wb_reason reason)
{
	__writeback_inodes_sb_nr(sb, nr, reason, false);
}
EXPORT_SYMBOL(writeback_inodes_sb_nr);

/**
 * writeback_inodes_sb	-	writeback dirty inodes from given super_block
 * @sb: the superblock
 * @reason: reason why some writeback work was initiated
 *
 * 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.
 */
void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
{
	return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
}
EXPORT_SYMBOL(writeback_inodes_sb);

/**
 * try_to_writeback_inodes_sb_nr - try to start writeback if none underway
 * @sb: the superblock
 * @nr: the number of pages to write
 * @reason: the reason of writeback
 *
 * Invoke writeback_inodes_sb_nr if no writeback is currently underway.
 * Returns 1 if writeback was started, 0 if not.
 */
bool try_to_writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr,
				   enum wb_reason reason)
{
	if (!down_read_trylock(&sb->s_umount))
		return false;

	__writeback_inodes_sb_nr(sb, nr, reason, true);
	up_read(&sb->s_umount);
	return true;
}
EXPORT_SYMBOL(try_to_writeback_inodes_sb_nr);

/**
 * try_to_writeback_inodes_sb - try to start writeback if none underway
 * @sb: the superblock
 * @reason: reason why some writeback work was initiated
 *
 * Implement by try_to_writeback_inodes_sb_nr()
 * Returns 1 if writeback was started, 0 if not.
 */
bool try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason)
{
	return try_to_writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason);
}
EXPORT_SYMBOL(try_to_writeback_inodes_sb);

/**
 * sync_inodes_sb	-	sync sb inode pages
 * @sb: the superblock
 *
 * This function writes and waits on any dirty inode belonging to this
 * super_block.
 */
void sync_inodes_sb(struct super_block *sb)
{
	DEFINE_WB_COMPLETION_ONSTACK(done);
	struct wb_writeback_work work = {
		.sb		= sb,
		.sync_mode	= WB_SYNC_ALL,
		.nr_pages	= LONG_MAX,
		.range_cyclic	= 0,
		.done		= &done,
		.reason		= WB_REASON_SYNC,
		.for_sync	= 1,
	};
	struct backing_dev_info *bdi = sb->s_bdi;

	/* Nothing to do? */
	if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info)
		return;
	WARN_ON(!rwsem_is_locked(&sb->s_umount));

	bdi_split_work_to_wbs(bdi, &work, false);
	wb_wait_for_completion(bdi, &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)
{
	struct bdi_writeback *wb = &inode_to_bdi(inode)->wb;
	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();
	return writeback_single_inode(inode, wb, &wbc);
}
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)
{
	return writeback_single_inode(inode, &inode_to_bdi(inode)->wb, wbc);
}
EXPORT_SYMBOL(sync_inode);

/**
 * sync_inode_metadata - write an inode to disk
 * @inode: the inode to sync
 * @wait: wait for I/O to complete.
 *
 * Write an inode to disk and adjust its dirty state after completion.
 *
 * Note: only writes the actual inode, no associated data or other metadata.
 */
int sync_inode_metadata(struct inode *inode, int wait)
{
	struct writeback_control wbc = {
		.sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE,
		.nr_to_write = 0, /* metadata-only */
	};

	return sync_inode(inode, &wbc);
}
EXPORT_SYMBOL(sync_inode_metadata);
OpenPOWER on IntegriCloud