mm/page-writeback.c



1da177e4c3f4
f30c2269544b
1da177e4c3f4

04fbfdc14e5f
1da177e4c3f4


e1f8e8744914
1da177e4c3f4


55e829af0668
1da177e4c3f4

d08b3851da41
1da177e4c3f4


cf9a2ae8d499
811d736f9e80
1da177e4c3f4

1da177e4c3f4


1da177e4c3f4


3a2e9a5a2afc
1da177e4c3f4

3a2e9a5a2afc
1da177e4c3f4
3a2e9a5a2afc


1da177e4c3f4


5b0830cb9085
1da177e4c3f4
1b5e62b42b55
1da177e4c3f4

2da02997e08d


195cf453d2c3


1da177e4c3f4

1b5e62b42b55
1da177e4c3f4

2da02997e08d


704503d83604
1da177e4c3f4
22ef37eed673
1da177e4c3f4

704503d83604
1da177e4c3f4
22ef37eed673
1da177e4c3f4


ed5b43f15a8e

1da177e4c3f4


1da177e4c3f4
04fbfdc14e5f


3e26c149c358
04fbfdc14e5f
04fbfdc14e5f


2da02997e08d


04fbfdc14e5f


2da02997e08d
04fbfdc14e5f
2da02997e08d


8d65af789f3e
2da02997e08d


8d65af789f3e
2da02997e08d


8d65af789f3e
2da02997e08d


8d65af789f3e
2da02997e08d


04fbfdc14e5f
8d65af789f3e
04fbfdc14e5f


2da02997e08d

8d65af789f3e
04fbfdc14e5f
2da02997e08d


8d65af789f3e
2da02997e08d

fc3501d411d3
2da02997e08d

8d65af789f3e
2da02997e08d


04fbfdc14e5f


a42dde041527

04fbfdc14e5f

dd5656e59ca7


1cf6e7d83bf3
3e26c149c358


04fbfdc14e5f


dcf975d58565

04fbfdc14e5f
dcf975d58565
04fbfdc14e5f
dcf975d58565
04fbfdc14e5f
fc3ba692a4d1
dcf975d58565
04fbfdc14e5f
dcf975d58565


04fbfdc14e5f


3e26c149c358


dcf975d58565
3e26c149c358

dcf975d58565
3e26c149c358


04fbfdc14e5f
189d3c4a94ef

189d3c4a94ef


189d3c4a94ef
cfc4ba536544
a42dde041527
189d3c4a94ef
a42dde041527


cfc4ba536544
a42dde041527


a42dde041527


cfc4ba536544
a42dde041527


cfc4ba536544
189d3c4a94ef


a42dde041527
189d3c4a94ef

1da177e4c3f4


1b4244647cea


37b07e4163f7
1b4244647cea


adea02a1bea7

1b4244647cea


3eefae994d92


1b4244647cea


adea02a1bea7
195cf453d2c3


1b4244647cea


cf0ca9fe5dd9
364aeb284978

1da177e4c3f4
364aeb284978

1b4244647cea
1da177e4c3f4

2da02997e08d


1da177e4c3f4
2da02997e08d


1da177e4c3f4
2da02997e08d

1da177e4c3f4


04fbfdc14e5f

189d3c4a94ef
04fbfdc14e5f


189d3c4a94ef
04fbfdc14e5f

189d3c4a94ef
a42dde041527

04fbfdc14e5f


3e26c149c358
04fbfdc14e5f
1da177e4c3f4


5b0830cb9085

1da177e4c3f4
3a2e9a5a2afc

1da177e4c3f4
5fce25a9df48

364aeb284978


1da177e4c3f4
87c6a9b25352
1da177e4c3f4


111ebb6e6f7b
1da177e4c3f4

04fbfdc14e5f

5fce25a9df48


04fbfdc14e5f

5fce25a9df48
04fbfdc14e5f

1da177e4c3f4
5fce25a9df48


04fbfdc14e5f

1da177e4c3f4


d7831a0bdf06


1da177e4c3f4
d7831a0bdf06
03ba3782e8dc
1da177e4c3f4
04fbfdc14e5f


1da177e4c3f4
04fbfdc14e5f


d25105e8911b

87c6a9b25352


1da177e4c3f4

04fbfdc14e5f


1da177e4c3f4

5b0830cb9085
1da177e4c3f4


d3ddec7635b6

b6e51316daed
a72bfd4dea05
1da177e4c3f4

a200ee182a01
edc79b2a46ed
a200ee182a01
edc79b2a46ed


245b2e70eabd

1da177e4c3f4
fa5a734e406b
67be2dd1bace
a580290c3e64
1da177e4c3f4


fa5a734e406b

1da177e4c3f4
fa5a734e406b

1da177e4c3f4

04fbfdc14e5f
1da177e4c3f4


fa5a734e406b
245b2e70eabd
fa5a734e406b

3a2e9a5a2afc
fa5a734e406b

3a2e9a5a2afc
1da177e4c3f4

fa5a734e406b
1da177e4c3f4
fa5a734e406b
1da177e4c3f4
232ea4d69d81
1da177e4c3f4
364aeb284978

1da177e4c3f4

04fbfdc14e5f
1da177e4c3f4


c24f21bda88d


8aa7e847d834
369f2389e7d0


1da177e4c3f4


1da177e4c3f4

8d06afab73a7
1da177e4c3f4

1da177e4c3f4


8d65af789f3e
1da177e4c3f4
8d65af789f3e
1da177e4c3f4


03ba3782e8dc
1da177e4c3f4
03ba3782e8dc

1da177e4c3f4


03ba3782e8dc


1da177e4c3f4


ed5b43f15a8e
1da177e4c3f4


2d1d43f6a43b
1da177e4c3f4
40c99aae2352
1da177e4c3f4


26c2143b63b8
1da177e4c3f4

2d1d43f6a43b
aa0f03037422
1da177e4c3f4

74b85f3790aa
1da177e4c3f4


dc6e29da9162


1da177e4c3f4


04fbfdc14e5f

2d1d43f6a43b
1da177e4c3f4
04fbfdc14e5f


3e26c149c358
1da177e4c3f4

811d736f9e80
0ea971801625
811d736f9e80

0ea971801625

811d736f9e80
0ea971801625
811d736f9e80


811d736f9e80
0ea971801625


811d736f9e80
811d736f9e80

811d736f9e80

31a12666d8f0
811d736f9e80

bd19e012f6fd
31a12666d8f0
811d736f9e80
17bc6c30cf6b
811d736f9e80
811d736f9e80

31a12666d8f0


811d736f9e80


31a12666d8f0
811d736f9e80

bd19e012f6fd
5a3d5c9813db


811d736f9e80
811d736f9e80


d5482cdf8a0a


811d736f9e80
d5482cdf8a0a


811d736f9e80

5a3d5c9813db


811d736f9e80
5a3d5c9813db
811d736f9e80


515f4a037fb9


811d736f9e80
515f4a037fb9

5a3d5c9813db
811d736f9e80
0ea971801625
00266770b8b3


89e1219004b3
dcf6a79dda5c
89e1219004b3


05fe478dd04e
811d736f9e80


3a4c6800f31e
811d736f9e80
31a12666d8f0
811d736f9e80


31a12666d8f0
811d736f9e80
31a12666d8f0
811d736f9e80

17bc6c30cf6b

bd19e012f6fd
17bc6c30cf6b

06d6cf6959d2
811d736f9e80

0ea971801625


811d736f9e80


1da177e4c3f4

22905f775dd6

1da177e4c3f4


d08b3851da41
22905f775dd6

22905f775dd6
1da177e4c3f4


67be2dd1bace

1da177e4c3f4


767193253bba


e3a7cca1ef4c


1da177e4c3f4


183ff22bb6bd
1da177e4c3f4


1da177e4c3f4


8c08540f8755


19fd6231279b
8c08540f8755


787d2214c19b
e3a7cca1ef4c
8c08540f8755


19fd6231279b
8c08540f8755


1da177e4c3f4
4741c9fd36b3
1da177e4c3f4
4741c9fd36b3
1da177e4c3f4


6746aff74da2


1da177e4c3f4


1cf6e7d83bf3
1da177e4c3f4


9361401eb761


1da177e4c3f4
4741c9fd36b3


1da177e4c3f4


db37648cd6ce
1da177e4c3f4


1da177e4c3f4


79352894b285

fe3cba17c494
7658cc289288


7658cc289288


79352894b285


7658cc289288
8c08540f8755
c9e51e418069

7658cc289288
1da177e4c3f4
7658cc289288
1da177e4c3f4
7658cc289288
1da177e4c3f4
58bb01a9cd72
1da177e4c3f4


69cb51d18c1e
1da177e4c3f4

19fd6231279b
1da177e4c3f4
69cb51d18c1e
1da177e4c3f4


e4ad08fe64af
69cb51d18c1e
04fbfdc14e5f

69cb51d18c1e
19fd6231279b
1da177e4c3f4


d688abf50bd5

1da177e4c3f4


69cb51d18c1e
1da177e4c3f4

19fd6231279b
1da177e4c3f4
69cb51d18c1e
1da177e4c3f4


e4ad08fe64af
69cb51d18c1e

1da177e4c3f4


19fd6231279b
1da177e4c3f4


d688abf50bd5

1da177e4c3f4


001281881067
1da177e4c3f4


1da177e4c3f4
001281881067
1da177e4c3f4
001281881067
1da177e4c3f4


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

  
/*
 * mm/page-writeback.c
 *
 * Copyright (C) 2002, Linus Torvalds.
 * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com>
 *
 * Contains functions related to writing back dirty pages at the
 * address_space level.
 *
 * 10Apr2002	Andrew Morton
 *		Initial version
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/spinlock.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/slab.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>
#include <linux/init.h>
#include <linux/backing-dev.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/blkdev.h>
#include <linux/mpage.h>
#include <linux/rmap.h>
#include <linux/percpu.h>
#include <linux/notifier.h>
#include <linux/smp.h>
#include <linux/sysctl.h>
#include <linux/cpu.h>
#include <linux/syscalls.h>
#include <linux/buffer_head.h>
#include <linux/pagevec.h>

/*
 * After a CPU has dirtied this many pages, balance_dirty_pages_ratelimited
 * will look to see if it needs to force writeback or throttling.
 */
static long ratelimit_pages = 32;

/*
 * When balance_dirty_pages decides that the caller needs to perform some
 * non-background writeback, this is how many pages it will attempt to write.
 * It should be somewhat larger than dirtied pages to ensure that reasonably
 * large amounts of I/O are submitted.
 */
static inline long sync_writeback_pages(unsigned long dirtied)
{
	if (dirtied < ratelimit_pages)
		dirtied = ratelimit_pages;

	return dirtied + dirtied / 2;
}

/* The following parameters are exported via /proc/sys/vm */

/*
 * Start background writeback (via writeback threads) at this percentage
 */
int dirty_background_ratio = 10;

/*
 * dirty_background_bytes starts at 0 (disabled) so that it is a function of
 * dirty_background_ratio * the amount of dirtyable memory
 */
unsigned long dirty_background_bytes;

/*
 * free highmem will not be subtracted from the total free memory
 * for calculating free ratios if vm_highmem_is_dirtyable is true
 */
int vm_highmem_is_dirtyable;

/*
 * The generator of dirty data starts writeback at this percentage
 */
int vm_dirty_ratio = 20;

/*
 * vm_dirty_bytes starts at 0 (disabled) so that it is a function of
 * vm_dirty_ratio * the amount of dirtyable memory
 */
unsigned long vm_dirty_bytes;

/*
 * The interval between `kupdate'-style writebacks
 */
unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */

/*
 * The longest time for which data is allowed to remain dirty
 */
unsigned int dirty_expire_interval = 30 * 100; /* centiseconds */

/*
 * Flag that makes the machine dump writes/reads and block dirtyings.
 */
int block_dump;

/*
 * Flag that puts the machine in "laptop mode". Doubles as a timeout in jiffies:
 * a full sync is triggered after this time elapses without any disk activity.
 */
int laptop_mode;

EXPORT_SYMBOL(laptop_mode);

/* End of sysctl-exported parameters */


/*
 * Scale the writeback cache size proportional to the relative writeout speeds.
 *
 * We do this by keeping a floating proportion between BDIs, based on page
 * writeback completions [end_page_writeback()]. Those devices that write out
 * pages fastest will get the larger share, while the slower will get a smaller
 * share.
 *
 * We use page writeout completions because we are interested in getting rid of
 * dirty pages. Having them written out is the primary goal.
 *
 * We introduce a concept of time, a period over which we measure these events,
 * because demand can/will vary over time. The length of this period itself is
 * measured in page writeback completions.
 *
 */
static struct prop_descriptor vm_completions;
static struct prop_descriptor vm_dirties;

/*
 * couple the period to the dirty_ratio:
 *
 *   period/2 ~ roundup_pow_of_two(dirty limit)
 */
static int calc_period_shift(void)
{
	unsigned long dirty_total;

	if (vm_dirty_bytes)
		dirty_total = vm_dirty_bytes / PAGE_SIZE;
	else
		dirty_total = (vm_dirty_ratio * determine_dirtyable_memory()) /
				100;
	return 2 + ilog2(dirty_total - 1);
}

/*
 * update the period when the dirty threshold changes.
 */
static void update_completion_period(void)
{
	int shift = calc_period_shift();
	prop_change_shift(&vm_completions, shift);
	prop_change_shift(&vm_dirties, shift);
}

int dirty_background_ratio_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)
		dirty_background_bytes = 0;
	return ret;
}

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

	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
	if (ret == 0 && write)
		dirty_background_ratio = 0;
	return ret;
}

int dirty_ratio_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	int old_ratio = vm_dirty_ratio;
	int ret;

	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
	if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
		update_completion_period();
		vm_dirty_bytes = 0;
	}
	return ret;
}


int dirty_bytes_handler(struct ctl_table *table, int write,
		void __user *buffer, size_t *lenp,
		loff_t *ppos)
{
	unsigned long old_bytes = vm_dirty_bytes;
	int ret;

	ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
	if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
		update_completion_period();
		vm_dirty_ratio = 0;
	}
	return ret;
}

/*
 * Increment the BDI's writeout completion count and the global writeout
 * completion count. Called from test_clear_page_writeback().
 */
static inline void __bdi_writeout_inc(struct backing_dev_info *bdi)
{
	__prop_inc_percpu_max(&vm_completions, &bdi->completions,
			      bdi->max_prop_frac);
}

void bdi_writeout_inc(struct backing_dev_info *bdi)
{
	unsigned long flags;

	local_irq_save(flags);
	__bdi_writeout_inc(bdi);
	local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(bdi_writeout_inc);

void task_dirty_inc(struct task_struct *tsk)
{
	prop_inc_single(&vm_dirties, &tsk->dirties);
}

/*
 * Obtain an accurate fraction of the BDI's portion.
 */
static void bdi_writeout_fraction(struct backing_dev_info *bdi,
		long *numerator, long *denominator)
{
	if (bdi_cap_writeback_dirty(bdi)) {
		prop_fraction_percpu(&vm_completions, &bdi->completions,
				numerator, denominator);
	} else {
		*numerator = 0;
		*denominator = 1;
	}
}

/*
 * Clip the earned share of dirty pages to that which is actually available.
 * This avoids exceeding the total dirty_limit when the floating averages
 * fluctuate too quickly.
 */
static void clip_bdi_dirty_limit(struct backing_dev_info *bdi,
		unsigned long dirty, unsigned long *pbdi_dirty)
{
	unsigned long avail_dirty;

	avail_dirty = global_page_state(NR_FILE_DIRTY) +
		 global_page_state(NR_WRITEBACK) +
		 global_page_state(NR_UNSTABLE_NFS) +
		 global_page_state(NR_WRITEBACK_TEMP);

	if (avail_dirty < dirty)
		avail_dirty = dirty - avail_dirty;
	else
		avail_dirty = 0;

	avail_dirty += bdi_stat(bdi, BDI_RECLAIMABLE) +
		bdi_stat(bdi, BDI_WRITEBACK);

	*pbdi_dirty = min(*pbdi_dirty, avail_dirty);
}

static inline void task_dirties_fraction(struct task_struct *tsk,
		long *numerator, long *denominator)
{
	prop_fraction_single(&vm_dirties, &tsk->dirties,
				numerator, denominator);
}

/*
 * scale the dirty limit
 *
 * task specific dirty limit:
 *
 *   dirty -= (dirty/8) * p_{t}
 */
static void task_dirty_limit(struct task_struct *tsk, unsigned long *pdirty)
{
	long numerator, denominator;
	unsigned long dirty = *pdirty;
	u64 inv = dirty >> 3;

	task_dirties_fraction(tsk, &numerator, &denominator);
	inv *= numerator;
	do_div(inv, denominator);

	dirty -= inv;
	if (dirty < *pdirty/2)
		dirty = *pdirty/2;

	*pdirty = dirty;
}

/*
 *
 */
static unsigned int bdi_min_ratio;

int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio)
{
	int ret = 0;

	spin_lock_bh(&bdi_lock);
	if (min_ratio > bdi->max_ratio) {
		ret = -EINVAL;
	} else {
		min_ratio -= bdi->min_ratio;
		if (bdi_min_ratio + min_ratio < 100) {
			bdi_min_ratio += min_ratio;
			bdi->min_ratio += min_ratio;
		} else {
			ret = -EINVAL;
		}
	}
	spin_unlock_bh(&bdi_lock);

	return ret;
}

int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned max_ratio)
{
	int ret = 0;

	if (max_ratio > 100)
		return -EINVAL;

	spin_lock_bh(&bdi_lock);
	if (bdi->min_ratio > max_ratio) {
		ret = -EINVAL;
	} else {
		bdi->max_ratio = max_ratio;
		bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
	}
	spin_unlock_bh(&bdi_lock);

	return ret;
}
EXPORT_SYMBOL(bdi_set_max_ratio);

/*
 * Work out the current dirty-memory clamping and background writeout
 * thresholds.
 *
 * The main aim here is to lower them aggressively if there is a lot of mapped
 * memory around.  To avoid stressing page reclaim with lots of unreclaimable
 * pages.  It is better to clamp down on writers than to start swapping, and
 * performing lots of scanning.
 *
 * We only allow 1/2 of the currently-unmapped memory to be dirtied.
 *
 * We don't permit the clamping level to fall below 5% - that is getting rather
 * excessive.
 *
 * We make sure that the background writeout level is below the adjusted
 * clamping level.
 */

static unsigned long highmem_dirtyable_memory(unsigned long total)
{
#ifdef CONFIG_HIGHMEM
	int node;
	unsigned long x = 0;

	for_each_node_state(node, N_HIGH_MEMORY) {
		struct zone *z =
			&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];

		x += zone_page_state(z, NR_FREE_PAGES) +
		     zone_reclaimable_pages(z);
	}
	/*
	 * Make sure that the number of highmem pages is never larger
	 * than the number of the total dirtyable memory. This can only
	 * occur in very strange VM situations but we want to make sure
	 * that this does not occur.
	 */
	return min(x, total);
#else
	return 0;
#endif
}

/**
 * determine_dirtyable_memory - amount of memory that may be used
 *
 * Returns the numebr of pages that can currently be freed and used
 * by the kernel for direct mappings.
 */
unsigned long determine_dirtyable_memory(void)
{
	unsigned long x;

	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();

	if (!vm_highmem_is_dirtyable)
		x -= highmem_dirtyable_memory(x);

	return x + 1;	/* Ensure that we never return 0 */
}

void
get_dirty_limits(unsigned long *pbackground, unsigned long *pdirty,
		 unsigned long *pbdi_dirty, struct backing_dev_info *bdi)
{
	unsigned long background;
	unsigned long dirty;
	unsigned long available_memory = determine_dirtyable_memory();
	struct task_struct *tsk;

	if (vm_dirty_bytes)
		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
	else {
		int dirty_ratio;

		dirty_ratio = vm_dirty_ratio;
		if (dirty_ratio < 5)
			dirty_ratio = 5;
		dirty = (dirty_ratio * available_memory) / 100;
	}

	if (dirty_background_bytes)
		background = DIV_ROUND_UP(dirty_background_bytes, PAGE_SIZE);
	else
		background = (dirty_background_ratio * available_memory) / 100;

	if (background >= dirty)
		background = dirty / 2;
	tsk = current;
	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk)) {
		background += background / 4;
		dirty += dirty / 4;
	}
	*pbackground = background;
	*pdirty = dirty;

	if (bdi) {
		u64 bdi_dirty;
		long numerator, denominator;

		/*
		 * Calculate this BDI's share of the dirty ratio.
		 */
		bdi_writeout_fraction(bdi, &numerator, &denominator);

		bdi_dirty = (dirty * (100 - bdi_min_ratio)) / 100;
		bdi_dirty *= numerator;
		do_div(bdi_dirty, denominator);
		bdi_dirty += (dirty * bdi->min_ratio) / 100;
		if (bdi_dirty > (dirty * bdi->max_ratio) / 100)
			bdi_dirty = dirty * bdi->max_ratio / 100;

		*pbdi_dirty = bdi_dirty;
		clip_bdi_dirty_limit(bdi, dirty, pbdi_dirty);
		task_dirty_limit(current, pbdi_dirty);
	}
}

/*
 * balance_dirty_pages() must be called by processes which are generating dirty
 * data.  It looks at the number of dirty pages in the machine and will force
 * the caller to perform writeback if the system is over `vm_dirty_ratio'.
 * If we're over `background_thresh' then the writeback threads are woken to
 * perform some writeout.
 */
static void balance_dirty_pages(struct address_space *mapping,
				unsigned long write_chunk)
{
	long nr_reclaimable, bdi_nr_reclaimable;
	long nr_writeback, bdi_nr_writeback;
	unsigned long background_thresh;
	unsigned long dirty_thresh;
	unsigned long bdi_thresh;
	unsigned long pages_written = 0;
	unsigned long pause = 1;

	struct backing_dev_info *bdi = mapping->backing_dev_info;

	for (;;) {
		struct writeback_control wbc = {
			.bdi		= bdi,
			.sync_mode	= WB_SYNC_NONE,
			.older_than_this = NULL,
			.nr_to_write	= write_chunk,
			.range_cyclic	= 1,
		};

		get_dirty_limits(&background_thresh, &dirty_thresh,
				&bdi_thresh, bdi);

		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
					global_page_state(NR_UNSTABLE_NFS);
		nr_writeback = global_page_state(NR_WRITEBACK);

		bdi_nr_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
		bdi_nr_writeback = bdi_stat(bdi, BDI_WRITEBACK);

		if (bdi_nr_reclaimable + bdi_nr_writeback <= bdi_thresh)
			break;

		/*
		 * Throttle it only when the background writeback cannot
		 * catch-up. This avoids (excessively) small writeouts
		 * when the bdi limits are ramping up.