include/linux/keyboard.h


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

#ifndef __LINUX_KEYBOARD_H
#define __LINUX_KEYBOARD_H

#include <linux/wait.h>

#define KG_SHIFT	0
#define KG_CTRL		2
#define KG_ALT		3
#define KG_ALTGR	1
#define KG_SHIFTL	4
#define KG_KANASHIFT	4
#define KG_SHIFTR	5
#define KG_CTRLL	6
#define KG_CTRLR	7
#define KG_CAPSSHIFT	8

#define NR_SHIFT	9

#define NR_KEYS		256
#define MAX_NR_KEYMAPS	256
/* This means 128Kb if all keymaps are allocated. Only the superuser
	may increase the number of keymaps beyond MAX_NR_OF_USER_KEYMAPS. */
#define MAX_NR_OF_USER_KEYMAPS 256 	/* should be at least 7 */

#ifdef __KERNEL__
extern const int NR_TYPES;
extern const int max_vals[];
extern unsigned short *key_maps[MAX_NR_KEYMAPS];
extern unsigned short plain_map[NR_KEYS];
#endif

#define MAX_NR_FUNC	256	/* max nr of strings assigned to keys */

#define KT_LATIN	0	/* we depend on this being zero */
#define KT_LETTER	11	/* symbol that can be acted upon by CapsLock */
#define KT_FN		1
#define KT_SPEC		2
#define KT_PAD		3
#define KT_DEAD		4
#define KT_CONS		5
#define KT_CUR		6
#define KT_SHIFT	7
#define KT_META		8
#define KT_ASCII	9
#define KT_LOCK		10
#define KT_SLOCK	12

#define K(t,v)		(((t)<<8)|(v))
#define KTYP(x)		((x) >> 8)
#define KVAL(x)		((x) & 0xff)

#define K_F1		K(KT_FN,0)
#define K_F2		K(KT_FN,1)
#define K_F3		K(KT_FN,2)
#define K_F4		K(KT_FN,3)
#define K_F5		K(KT_FN,4)
#define K_F6		K(KT_FN,5)
#define K_F7		K(KT_FN,6)
#define K_F8		K(KT_FN,7)
#define K_F9		K(KT_FN,8)
#define K_F10		K(KT_FN,9)
#define K_F11		K(KT_FN,10)
#define K_F12		K(KT_FN,11)
#define K_F13		K(KT_FN,12)
#define K_F14		K(KT_FN,13)
#define K_F15		K(KT_FN,14)
#define K_F16		K(KT_FN,15)
#define K_F17		K(KT_FN,16)
#define K_F18		K(KT_FN,17)
#define K_F19		K(KT_FN,18)
#define K_F20		K(KT_FN,19)
#define K_FIND		K(KT_FN,20)
#define K_INSERT	K(KT_FN,21)
#define K_REMOVE	K(KT_FN,22)
#define K_SELECT	K(KT_FN,23)
#define K_PGUP		K(KT_FN,24) /* PGUP is a synonym for PRIOR */
#define K_PGDN		K(KT_FN,25) /* PGDN is a synonym for NEXT */
#define K_MACRO	 	K(KT_FN,26)
#define K_HELP		K(KT_FN,27)
#define K_DO		K(KT_FN,28)
#define K_PAUSE	 	K(KT_FN,29)
#define K_F21		K(KT_FN,30)
#define K_F22		K(KT_FN,31)
#define K_F23		K(KT_FN,32)
#define K_F24		K(KT_FN,33)
#define K_F25		K(KT_FN,34)
#define K_F26		K(KT_FN,35)
#define K_F27		K(KT_FN,36)
#define K_F28		K(KT_FN,37)
#define K_F29		K(KT_FN,38)
#define K_F30		K(KT_FN,39)
#define K_F31		K(KT_FN,40)
#define K_F32		K(KT_FN,41)
#define K_F33		K(KT_FN,42)
#define K_F34		K(KT_FN,43)
#define K_F35		K(KT_FN,44)
#define K_F36		K(KT_FN,45)
#define K_F37		K(KT_FN,46)
#define K_F38		K(KT_FN,47)
#define K_F39		K(KT_FN,48)
#define K_F40		K(KT_FN,49)
#define K_F41		K(KT_FN,50)
#define K_F42		K(KT_FN,51)
#define K_F43		K(KT_FN,52)
#define K_F44		K(KT_FN,53)
#define K_F45		K(KT_FN,54)
#define K_F46		K(KT_FN,55)
#define K_F47		K(KT_FN,56)
#define K_F48		K(KT_FN,57)
#define K_F49		K(KT_FN,58)
#define K_F50		K(KT_FN,59)
#define K_F51		K(KT_FN,60)
#define K_F52		K(KT_FN,61)
#define K_F53		K(KT_FN,62)
#define K_F54		K(KT_FN,63)
#define K_F55		K(KT_FN,64)
#define K_F56		K(KT_FN,65)
#define K_F57		K(KT_FN,66)
#define K_F58		K(KT_FN,67)
#define K_F59		K(KT_FN,68)
#define K_F60		K(KT_FN,69)
#define K_F61		K(KT_FN,70)
#define K_F62		K(KT_FN,71)
#define K_F63		K(KT_FN,72)
#define K_F64		K(KT_FN,73)
#define K_F65		K(KT_FN,74)
#define K_F66		K(KT_FN,75)
#define K_F67		K(KT_FN,76)
#define K_F68		K(KT_FN,77)
#define K_F69		K(KT_FN,78)
#define K_F70		K(KT_FN,79)
#define K_F71		K(KT_FN,80)
#define K_F72		K(KT_FN,81)
#define K_F73		K(KT_FN,82)
#define K_F74		K(KT_FN,83)
#define K_F75		K(KT_FN,84)
#define K_F76		K(KT_FN,85)
#define K_F77		K(KT_FN,86)
#define K_F78		K(KT_FN,87)
#define K_F79		K(KT_FN,88)
#define K_F80		K(KT_FN,89)
#define K_F81		K(KT_FN,90)
#define K_F82		K(KT_FN,91)
#define K_F83		K(KT_FN,92)
#define K_F84		K(KT_FN,93)
#define K_F85		K(KT_FN,94)
#define K_F86		K(KT_FN,95)
#define K_F87		K(KT_FN,96)
#define K_F88		K(KT_FN,97)
#define K_F89		K(KT_FN,98)
#define K_F90		K(KT_FN,99)
#define K_F91		K(KT_FN,100)
#define K_F92		K(KT_FN,101)
#define K_F93		K(KT_FN,102)
#define K_F94		K(KT_FN,103)
#define K_F95		K(KT_FN,104)
#define K_F96		K(KT_FN,105)
#define K_F97		K(KT_FN,106)
#define K_F98		K(KT_FN,107)
#define K_F99		K(KT_FN,108)
#define K_F100		K(KT_FN,109)
#define K_F101		K(KT_FN,110)
#define K_F102		K(KT_FN,111)
#define K_F103		K(KT_FN,112)
#define K_F104		K(KT_FN,113)
#define K_F105		K(KT_FN,114)
#define K_F106		K(KT_FN,115)
#define K_F107		K(KT_FN,116)
#define K_F108		K(KT_FN,117)
#define K_F109		K(KT_FN,118)
#define K_F110		K(KT_FN,119)
#define K_F111		K(KT_FN,120)
#define K_F112		K(KT_FN,121)
#define K_F113		K(KT_FN,122)
#define K_F114		K(KT_FN,123)
#define K_F115		K(KT_FN,124)
#define K_F116		K(KT_FN,125)
#define K_F117		K(KT_FN,126)
#define K_F118		K(KT_FN,127)
#define K_F119		K(KT_FN,128)
#define K_F120		K(KT_FN,129)
#define K_F121		K(KT_FN,130)
#define K_F122		K(KT_FN,131)
#define K_F123		K(KT_FN,132)
#define K_F124		K(KT_FN,133)
#define K_F125		K(KT_FN,134)
#define K_F126		K(KT_FN,135)
#define K_F127		K(KT_FN,136)
#define K_F128		K(KT_FN,137)
#define K_F129		K(KT_FN,138)
#define K_F130		K(KT_FN,139)
#define K_F131		K(KT_FN,140)
#define K_F132		K(KT_FN,141)
#define K_F133		K(KT_FN,142)
#define K_F134		K(KT_FN,143)
#define K_F135		K(KT_FN,144)
#define K_F136		K(KT_FN,145)
#define K_F137		K(KT_FN,146)
#define K_F138		K(KT_FN,147)
#define K_F139		K(KT_FN,148)
#define K_F140		K(KT_FN,149)
#define K_F141		K(KT_FN,150)
#define K_F142		K(KT_FN,151)
#define K_F143		K(KT_FN,152)
#define K_F144		K(KT_FN,153)
#define K_F145		K(KT_FN,154)
#define K_F146		K(KT_FN,155)
#define K_F147		K(KT_FN,156)
#define K_F148		K(KT_FN,157)
#define K_F149		K(KT_FN,158)
#define K_F150		K(KT_FN,159)
#define K_F151		K(KT_FN,160)
#define K_F152		K(KT_FN,161)
#define K_F153		K(KT_FN,162)
#define K_F154		K(KT_FN,163)
#define K_F155		K(KT_FN,164)
#define K_F156		K(KT_FN,165)
#define K_F157		K(KT_FN,166)
#define K_F158		K(KT_FN,167)
#define K_F159		K(KT_FN,168)
#define K_F160		K(KT_FN,169)
#define K_F161		K(KT_FN,170)
#define K_F162		K(KT_FN,171)
#define K_F163		K(KT_FN,172)
#define K_F164		K(KT_FN,173)
#define K_F165		K(KT_FN,174)
#define K_F166		K(KT_FN,175)
#define K_F167		K(KT_FN,176)
#define K_F168		K(KT_FN,177)
#define K_F169		K(KT_FN,178)
#define K_F170		K(KT_FN,179)
#define K_F171		K(KT_FN,180)
#define K_F172		K(KT_FN,181)
#define K_F173		K(KT_FN,182)
#define K_F174		K(KT_FN,183)
#define K_F175		K(KT_FN,184)
#define K_F176		K(KT_FN,185)
#define K_F177		K(KT_FN,186)
#define K_F178		K(KT_FN,187)
#define K_F179		K(KT_FN,188)
#define K_F180		K(KT_FN,189)
#define K_F181		K(KT_FN,190)
#define K_F182		K(KT_FN,191)
#define K_F183		K(KT_FN,192)
#define K_F184		K(KT_FN,193)
#define K_F185		K(KT_FN,194)
#define K_F186		K(KT_FN,195)
#define K_F187		K(KT_FN,196)
#define K_F188		K(KT_FN,197)
#define K_F189		K(KT_FN,198)
#define K_F190		K(KT_FN,199)
#define K_F191		K(KT_FN,200)
#define K_F192		K(KT_FN,201)
#define K_F193		K(KT_FN,202)
#define K_F194		K(KT_FN,203)
#define K_F195		K(KT_FN,204)
#define K_F196		K(KT_FN,205)
#define K_F197		K(KT_FN,206)
#define K_F198		K(KT_FN,207)
#define K_F199		K(KT_FN,208)
#define K_F200		K(KT_FN,209)
#define K_F201		K(KT_FN,210)
#define K_F202		K(KT_FN,211)
#define K_F203		K(KT_FN,212)
#define K_F204		K(KT_FN,213)
#define K_F205		K(KT_FN,214)
#define K_F206		K(KT_FN,215)
#define K_F207		K(KT_FN,216)
#define K_F208		K(KT_FN,217)
#define K_F209		K(KT_FN,218)
#define K_F210		K(KT_FN,219)
#define K_F211		K(KT_FN,220)
#define K_F212		K(KT_FN,221)
#define K_F213		K(KT_FN,222)
#define K_F214		K(KT_FN,223)
#define K_F215		K(KT_FN,224)
#define K_F216		K(KT_FN,225)
#define K_F217		K(KT_FN,226)
#define K_F218		K(KT_FN,227)
#define K_F219		K(KT_FN,228)
#define K_F220		K(KT_FN,229)
#define K_F221		K(KT_FN,230)
#define K_F222		K(KT_FN,231)
#define K_F223		K(KT_FN,232)
#define K_F224		K(KT_FN,233)
#define K_F225		K(KT_FN,234)
#define K_F226		K(KT_FN,235)
#define K_F227		K(KT_FN,236)
#define K_F228		K(KT_FN,237)
#define K_F229		K(KT_FN,238)
#define K_F230		K(KT_FN,239)
#define K_F231		K(KT_FN,240)
#define K_F232		K(KT_FN,241)
#define K_F233		K(KT_FN,242)
#define K_F234		K(KT_FN,243)
#define K_F235		K(KT_FN,244)
#define K_F236		K(KT_FN,245)
#define K_F237		K(KT_FN,246)
#define K_F238		K(KT_FN,247)
#define K_F239		K(KT_FN,248)
#define K_F240		K(KT_FN,249)
#define K_F241		K(KT_FN,250)
#define K_F242		K(KT_FN,251)
#define K_F243		K(KT_FN,252)
#define K_F244		K(KT_FN,253)
#define K_F245		K(KT_FN,254)
#define K_UNDO		K(KT_FN,255)


#define K_HOLE		K(KT_SPEC,0)
#define K_ENTER		K(KT_SPEC,1)
#define K_SH_REGS	K(KT_SPEC,2)
#define K_SH_MEM	K(KT_SPEC,3)
#define K_SH_STAT	K(KT_SPEC,4)
#define K_BREAK		K(KT_SPEC,5)
#define K_CONS		K(KT_SPEC,6)
#define K_CAPS		K(KT_SPEC,7)
#define K_NUM		K(KT_SPEC,8)
#define K_HOLD		K(KT_SPEC,9)
#define K_SCROLLFORW	K(KT_SPEC,10)
#define K_SCROLLBACK	K(KT_SPEC,11)
#define K_BOOT		K(KT_SPEC,12)
#define K_CAPSON	K(KT_SPEC,13)
#define K_COMPOSE	K(KT_SPEC,14)
#define K_SAK		K(KT_SPEC,15)
#define K_DECRCONSOLE	K(KT_SPEC,16)
#define K_INCRCONSOLE	K(KT_SPEC,17)
#define K_SPAWNCONSOLE	K(KT_SPEC,18)
#define K_BARENUMLOCK	K(KT_SPEC,19)

#define K_ALLOCATED	K(KT_SPEC,126) /* dynamically allocated keymap */
#define K_NOSUCHMAP	K(KT_SPEC,127) /* returned by KDGKBENT */

#define K_P0		K(KT_PAD,0)
#define K_P1		K(KT_PAD,1)
#define K_P2		K(KT_PAD,2)
#define K_P3		K(KT_PAD,3)
#define K_P4		K(KT_PAD,4)
#define K_P5		K(KT_PAD,5)
#define K_P6		K(KT_PAD,6)
#define K_P7		K(KT_PAD,7)
#define K_P8		K(KT_PAD,8)
#define K_P9		K(KT_PAD,9)
#define K_PPLUS		K(KT_PAD,10)	/* key-pad plus */
#define K_PMINUS	K(KT_PAD,11)	/* key-pad minus */
#define K_PSTAR		K(KT_PAD,12)	/* key-pad asterisk (star) */
#define K_PSLASH	K(KT_PAD,13)	/* key-pad slash */
#define K_PENTER	K(KT_PAD,14)	/* key-pad enter */
#define K_PCOMMA	K(KT_PAD,15)	/* key-pad comma: kludge... */
#define K_PDOT		K(KT_PAD,16)	/* key-pad dot (period): kludge... */
#define K_PPLUSMINUS	K(KT_PAD,17)	/* key-pad plus/minus */
#define K_PPARENL	K(KT_PAD,18)	/* key-pad left parenthesis */
#define K_PPARENR	K(KT_PAD,19)	/* key-pad right parenthesis */

#define NR_PAD		20

#define K_DGRAVE	K(KT_DEAD,0)
#define K_DACUTE	K(KT_DEAD,1)
#define K_DCIRCM	K(KT_DEAD,2)
#define K_DTILDE	K(KT_DEAD,3)
#define K_DDIERE	K(KT_DEAD,4)
#define K_DCEDIL	K(KT_DEAD,5)

#define NR_DEAD		6

#define K_DOWN		K(KT_CUR,0)
#define K_LEFT		K(KT_CUR,1)
#define K_RIGHT		K(KT_CUR,2)
#define K_UP		K(KT_CUR,3)

#define K_SHIFT		K(KT_SHIFT,KG_SHIFT)
#define K_CTRL		K(KT_SHIFT,KG_CTRL)
#define K_ALT		K(KT_SHIFT,KG_ALT)
#define K_ALTGR		K(KT_SHIFT,KG_ALTGR)
#define K_SHIFTL	K(KT_SHIFT,KG_SHIFTL)
#define K_SHIFTR	K(KT_SHIFT,KG_SHIFTR)
#define K_CTRLL	 	K(KT_SHIFT,KG_CTRLL)
#define K_CTRLR	 	K(KT_SHIFT,KG_CTRLR)
#define K_CAPSSHIFT	K(KT_SHIFT,KG_CAPSSHIFT)

#define K_ASC0		K(KT_ASCII,0)
#define K_ASC1		K(KT_ASCII,1)
#define K_ASC2		K(KT_ASCII,2)
#define K_ASC3		K(KT_ASCII,3)
#define K_ASC4		K(KT_ASCII,4)
#define K_ASC5		K(KT_ASCII,5)
#define K_ASC6		K(KT_ASCII,6)
#define K_ASC7		K(KT_ASCII,7)
#define K_ASC8		K(KT_ASCII,8)
#define K_ASC9		K(KT_ASCII,9)
#define K_HEX0		K(KT_ASCII,10)
#define K_HEX1		K(KT_ASCII,11)
#define K_HEX2		K(KT_ASCII,12)
#define K_HEX3		K(KT_ASCII,13)
#define K_HEX4		K(KT_ASCII,14)
#define K_HEX5		K(KT_ASCII,15)
#define K_HEX6		K(KT_ASCII,16)
#define K_HEX7		K(KT_ASCII,17)
#define K_HEX8		K(KT_ASCII,18)
#define K_HEX9		K(KT_ASCII,19)
#define K_HEXa		K(KT_ASCII,20)
#define K_HEXb		K(KT_ASCII,21)
#define K_HEXc		K(KT_ASCII,22)
#define K_HEXd		K(KT_ASCII,23)
#define K_HEXe		K(KT_ASCII,24)
#define K_HEXf		K(KT_ASCII,25)

#define NR_ASCII	26

#define K_SHIFTLOCK	K(KT_LOCK,KG_SHIFT)
#define K_CTRLLOCK	K(KT_LOCK,KG_CTRL)
#define K_ALTLOCK	K(KT_LOCK,KG_ALT)
#define K_ALTGRLOCK	K(KT_LOCK,KG_ALTGR)
#define K_SHIFTLLOCK	K(KT_LOCK,KG_SHIFTL)
#define K_SHIFTRLOCK	K(KT_LOCK,KG_SHIFTR)
#define K_CTRLLLOCK	K(KT_LOCK,KG_CTRLL)
#define K_CTRLRLOCK	K(KT_LOCK,KG_CTRLR)

#define K_SHIFT_SLOCK	K(KT_SLOCK,KG_SHIFT)
#define K_CTRL_SLOCK	K(KT_SLOCK,KG_CTRL)
#define K_ALT_SLOCK	K(KT_SLOCK,KG_ALT)
#define K_ALTGR_SLOCK	K(KT_SLOCK,KG_ALTGR)
#define K_SHIFTL_SLOCK	K(KT_SLOCK,KG_SHIFTL)
#define K_SHIFTR_SLOCK	K(KT_SLOCK,KG_SHIFTR)
#define K_CTRLL_SLOCK	K(KT_SLOCK,KG_CTRLL)
#define K_CTRLR_SLOCK	K(KT_SLOCK,KG_CTRLR)

#define NR_LOCK		8

#define MAX_DIACR	256
#endif
/*
 * 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/export.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> /* __set_page_dirty_buffers */
#include <linux/pagevec.h>
#include <trace/events/writeback.h>

/*
 * Sleep at most 200ms at a time in balance_dirty_pages().
 */
#define MAX_PAUSE		max(HZ/5, 1)

/*
 * Try to keep balance_dirty_pages() call intervals higher than this many pages
 * by raising pause time to max_pause when falls below it.
 */
#define DIRTY_POLL_THRESH	(128 >> (PAGE_SHIFT - 10))

/*
 * Estimate write bandwidth at 200ms intervals.
 */
#define BANDWIDTH_INTERVAL	max(HZ/5, 1)

#define RATELIMIT_CALC_SHIFT	10

/*
 * 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;

/* 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 */

EXPORT_SYMBOL_GPL(dirty_writeback_interval);

/*
 * 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 */

unsigned long global_dirty_limit;

/*
 * 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;

/*
 * 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.
 */

/*
 * In a memory zone, there is a certain amount of pages we consider
 * available for the page cache, which is essentially the number of
 * free and reclaimable pages, minus some zone reserves to protect
 * lowmem and the ability to uphold the zone's watermarks without
 * requiring writeback.
 *
 * This number of dirtyable pages is the base value of which the
 * user-configurable dirty ratio is the effictive number of pages that
 * are allowed to be actually dirtied.  Per individual zone, or
 * globally by using the sum of dirtyable pages over all zones.
 *
 * Because the user is allowed to specify the dirty limit globally as
 * absolute number of bytes, calculating the per-zone dirty limit can
 * require translating the configured limit into a percentage of
 * global dirtyable memory first.
 */

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) - z->dirty_balance_reserve;
	}
	/*
	 * 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
}

/**
 * global_dirtyable_memory - number of globally dirtyable pages
 *
 * Returns the global number of pages potentially available for dirty
 * page cache.  This is the base value for the global dirty limits.
 */
unsigned long global_dirtyable_memory(void)
{
	unsigned long x;

	x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages() -
	    dirty_balance_reserve;

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

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

/*
 * global_dirty_limits - background-writeback and dirty-throttling thresholds
 *
 * Calculate the dirty thresholds based on sysctl parameters
 * - vm.dirty_background_ratio  or  vm.dirty_background_bytes
 * - vm.dirty_ratio             or  vm.dirty_bytes
 * The dirty limits will be lifted by 1/4 for PF_LESS_THROTTLE (ie. nfsd) and
 * real-time tasks.
 */
void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty)
{
	unsigned long background;
	unsigned long dirty;
	unsigned long uninitialized_var(available_memory);
	struct task_struct *tsk;

	if (!vm_dirty_bytes || !dirty_background_bytes)
		available_memory = global_dirtyable_memory();

	if (vm_dirty_bytes)
		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE);
	else
		dirty = (vm_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;
	trace_global_dirty_state(background, dirty);
}

/**
 * zone_dirtyable_memory - number of dirtyable pages in a zone
 * @zone: the zone
 *
 * Returns the zone's number of pages potentially available for dirty
 * page cache.  This is the base value for the per-zone dirty limits.
 */
static unsigned long zone_dirtyable_memory(struct zone *zone)
{
	/*
	 * The effective global number of dirtyable pages may exclude
	 * highmem as a big-picture measure to keep the ratio between
	 * dirty memory and lowmem reasonable.
	 *
	 * But this function is purely about the individual zone and a
	 * highmem zone can hold its share of dirty pages, so we don't
	 * care about vm_highmem_is_dirtyable here.
	 */
	return zone_page_state(zone, NR_FREE_PAGES) +
	       zone_reclaimable_pages(zone) -
	       zone->dirty_balance_reserve;
}

/**
 * zone_dirty_limit - maximum number of dirty pages allowed in a zone
 * @zone: the zone
 *
 * Returns the maximum number of dirty pages allowed in a zone, based
 * on the zone's dirtyable memory.
 */
static unsigned long zone_dirty_limit(struct zone *zone)
{
	unsigned long zone_memory = zone_dirtyable_memory(zone);
	struct task_struct *tsk = current;
	unsigned long dirty;

	if (vm_dirty_bytes)
		dirty = DIV_ROUND_UP(vm_dirty_bytes, PAGE_SIZE) *
			zone_memory / global_dirtyable_memory();
	else
		dirty = vm_dirty_ratio * zone_memory / 100;

	if (tsk->flags & PF_LESS_THROTTLE || rt_task(tsk))
		dirty += dirty / 4;

	return dirty;
}

/**
 * zone_dirty_ok - tells whether a zone is within its dirty limits
 * @zone: the zone to check
 *
 * Returns %true when the dirty pages in @zone are within the zone's
 * dirty limit, %false if the limit is exceeded.
 */
bool zone_dirty_ok(struct zone *zone)
{
	unsigned long limit = zone_dirty_limit(zone);

	return zone_page_state(zone, NR_FILE_DIRTY) +
	       zone_page_state(zone, NR_UNSTABLE_NFS) +
	       zone_page_state(zone, NR_WRITEBACK) <= limit;
}

/*
 * 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 * global_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);

	writeback_set_ratelimit();
}

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)
{
	__inc_bdi_stat(bdi, BDI_WRITTEN);
	__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);

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

/*
 * bdi_min_ratio keeps the sum of the minimum dirty shares of all
 * registered backing devices, which, for obvious reasons, can not
 * exceed 100%.
 */
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);

static unsigned long dirty_freerun_ceiling(unsigned long thresh,
					   unsigned long bg_thresh)
{
	return (thresh + bg_thresh) / 2;
}

static unsigned long hard_dirty_limit(unsigned long thresh)
{
	return max(thresh, global_dirty_limit);
}

/**
 * bdi_dirty_limit - @bdi's share of dirty throttling threshold
 * @bdi: the backing_dev_info to query
 * @dirty: global dirty limit in pages
 *
 * Returns @bdi's dirty limit in pages. The term "dirty" in the context of
 * dirty balancing includes all PG_dirty, PG_writeback and NFS unstable pages.
 *
 * Note that balance_dirty_pages() will only seriously take it as a hard limit
 * when sleeping max_pause per page is not enough to keep the dirty pages under
 * control. For example, when the device is completely stalled due to some error
 * conditions, or when there are 1000 dd tasks writing to a slow 10MB/s USB key.
 * In the other normal situations, it acts more gently by throttling the tasks
 * more (rather than completely block them) when the bdi dirty pages go high.
 *
 * It allocates high/low dirty limits to fast/slow devices, in order to prevent
 * - starving fast devices
 * - piling up dirty pages (that will take long time to sync) on slow devices
 *
 * The bdi's share of dirty limit will be adapting to its throughput and
 * bounded by the bdi->min_ratio and/or bdi->max_ratio parameters, if set.
 */
unsigned long bdi_dirty_limit(struct backing_dev_info *bdi, unsigned long dirty)
{
	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;

	return bdi_dirty;
}

/*
 * Dirty position control.
 *
 * (o) global/bdi setpoints
 *
 * We want the dirty pages be balanced around the global/bdi setpoints.
 * When the number of dirty pages is higher/lower than the setpoint, the
 * dirty position control ratio (and hence task dirty ratelimit) will be
 * decreased/increased to bring the dirty pages back to the setpoint.
 *
 *     pos_ratio = 1 << RATELIMIT_CALC_SHIFT
 *
 *     if (dirty < setpoint) scale up   pos_ratio
 *     if (dirty > setpoint) scale down pos_ratio
 *
 *     if (bdi_dirty < bdi_setpoint) scale up   pos_ratio
 *     if (bdi_dirty > bdi_setpoint) scale down pos_ratio
 *
 *     task_ratelimit = dirty_ratelimit * pos_ratio >> RATELIMIT_CALC_SHIFT
 *
 * (o) global control line
 *
 *     ^ pos_ratio
 *     |
 *     |            |<===== global dirty control scope ======>|
 * 2.0 .............*
 *     |            .*
 *     |            . *
 *     |            .   *
 *     |            .     *
 *     |            .        *
 *     |            .            *
 * 1.0 ................................*
 *     |            .                  .     *
 *     |            .                  .          *
 *     |            .                  .              *
 *     |            .                  .                 *
 *     |            .                  .                    *
 *   0 +------------.------------------.----------------------*------------->
 *           freerun^          setpoint^                 limit^   dirty pages
 *
 * (o) bdi control line
 *
 *     ^ pos_ratio
 *     |
 *     |            *
 *     |              *
 *     |                *
 *     |                  *
 *     |                    * |<=========== span ============>|
 * 1.0 .......................*
 *     |                      . *
 *     |                      .   *
 *     |                      .     *
 *     |                      .       *
 *     |                      .         *
 *     |                      .           *
 *     |                      .             *
 *     |                      .               *
 *     |                      .                 *
 *     |                      .                   *
 *     |                      .                     *
 * 1/4 ...............................................* * * * * * * * * * * *
 *     |                      .                         .
 *     |                      .                           .
 *     |                      .                             .
 *   0 +----------------------.-------------------------------.------------->
 *                bdi_setpoint^                    x_intercept^
 *
 * The bdi control line won't drop below pos_ratio=1/4, so that bdi_dirty can
 * be smoothly throttled down to normal if it starts high in situations like
 * - start writing to a slow SD card and a fast disk at the same time. The SD
 *   card's bdi_dirty may rush to many times higher than bdi_setpoint.
 * - the bdi dirty thresh drops quickly due to change of JBOD workload
 */
static unsigned long bdi_position_ratio(struct backing_dev_info *bdi,
					unsigned long thresh,
					unsigned long bg_thresh,
					unsigned long dirty,
					unsigned long bdi_thresh,
					unsigned long bdi_dirty)
{
	unsigned long write_bw = bdi->avg_write_bandwidth;
	unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
	unsigned long limit = hard_dirty_limit(thresh);
	unsigned long x_intercept;
	unsigned long setpoint;		/* dirty pages' target balance point */
	unsigned long bdi_setpoint;
	unsigned long span;
	long long pos_ratio;		/* for scaling up/down the rate limit */
	long x;

	if (unlikely(dirty >= limit))
		return 0;

	/*
	 * global setpoint
	 *
	 *                           setpoint - dirty 3
	 *        f(dirty) := 1.0 + (----------------)
	 *                           limit - setpoint
	 *
	 * it's a 3rd order polynomial that subjects to
	 *
	 * (1) f(freerun)  = 2.0 => rampup dirty_ratelimit reasonably fast
	 * (2) f(setpoint) = 1.0 => the balance point
	 * (3) f(limit)    = 0   => the hard limit
	 * (4) df/dx      <= 0	 => negative feedback control
	 * (5) the closer to setpoint, the smaller |df/dx| (and the reverse)
	 *     => fast response on large errors; small oscillation near setpoint
	 */
	setpoint = (freerun + limit) / 2;
	x = div_s64((setpoint - dirty) << RATELIMIT_CALC_SHIFT,
		    limit - setpoint + 1);
	pos_ratio = x;
	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
	pos_ratio = pos_ratio * x >> RATELIMIT_CALC_SHIFT;
	pos_ratio += 1 << RATELIMIT_CALC_SHIFT;

	/*
	 * We have computed basic pos_ratio above based on global situation. If
	 * the bdi is over/under its share of dirty pages, we want to scale
	 * pos_ratio further down/up. That is done by the following mechanism.
	 */

	/*
	 * bdi setpoint
	 *
	 *        f(bdi_dirty) := 1.0 + k * (bdi_dirty - bdi_setpoint)
	 *
	 *                        x_intercept - bdi_dirty
	 *                     := --------------------------
	 *                        x_intercept - bdi_setpoint
	 *
	 * The main bdi control line is a linear function that subjects to
	 *
	 * (1) f(bdi_setpoint) = 1.0
	 * (2) k = - 1 / (8 * write_bw)  (in single bdi case)
	 *     or equally: x_intercept = bdi_setpoint + 8 * write_bw
	 *
	 * For single bdi case, the dirty pages are observed to fluctuate
	 * regularly within range
	 *        [bdi_setpoint - write_bw/2, bdi_setpoint + write_bw/2]
	 * for various filesystems, where (2) can yield in a reasonable 12.5%
	 * fluctuation range for pos_ratio.
	 *
	 * For JBOD case, bdi_thresh (not bdi_dirty!) could fluctuate up to its
	 * own size, so move the slope over accordingly and choose a slope that
	 * yields 100% pos_ratio fluctuation on suddenly doubled bdi_thresh.
	 */
	if (unlikely(bdi_thresh > thresh))
		bdi_thresh = thresh;
	/*
	 * It's very possible that bdi_thresh is close to 0 not because the
	 * device is slow, but that it has remained inactive for long time.
	 * Honour such devices a reasonable good (hopefully IO efficient)
	 * threshold, so that the occasional writes won't be blocked and active
	 * writes can rampup the threshold quickly.
	 */
	bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);
	/*
	 * scale global setpoint to bdi's:
	 *	bdi_setpoint = setpoint * bdi_thresh / thresh
	 */
	x = div_u64((u64)bdi_thresh << 16, thresh + 1);
	bdi_setpoint = setpoint * (u64)x >> 16;
	/*
	 * Use span=(8*write_bw) in single bdi case as indicated by
	 * (thresh - bdi_thresh ~= 0) and transit to bdi_thresh in JBOD case.
	 *
	 *        bdi_thresh                    thresh - bdi_thresh
	 * span = ---------- * (8 * write_bw) + ------------------- * bdi_thresh
	 *          thresh                            thresh
	 */
	span = (thresh - bdi_thresh + 8 * write_bw) * (u64)x >> 16;
	x_intercept = bdi_setpoint + span;

	if (bdi_dirty < x_intercept - span / 4) {
		pos_ratio = div_u64(pos_ratio * (x_intercept - bdi_dirty),
				    x_intercept - bdi_setpoint + 1);
	} else
		pos_ratio /= 4;

	/*
	 * bdi reserve area, safeguard against dirty pool underrun and disk idle
	 * It may push the desired control point of global dirty pages higher
	 * than setpoint.
	 */
	x_intercept = bdi_thresh / 2;
	if (bdi_dirty < x_intercept) {
		if (bdi_dirty > x_intercept / 8)
			pos_ratio = div_u64(pos_ratio * x_intercept, bdi_dirty);
		else
			pos_ratio *= 8;
	}

	return pos_ratio;
}

static void bdi_update_write_bandwidth(struct backing_dev_info *bdi,
				       unsigned long elapsed,
				       unsigned long written)
{
	const unsigned long period = roundup_pow_of_two(3 * HZ);
	unsigned long avg = bdi->avg_write_bandwidth;
	unsigned long old = bdi->write_bandwidth;
	u64 bw;

	/*
	 * bw = written * HZ / elapsed
	 *
	 *                   bw * elapsed + write_bandwidth * (period - elapsed)
	 * write_bandwidth = ---------------------------------------------------
	 *                                          period
	 */
	bw = written - bdi->written_stamp;
	bw *= HZ;
	if (unlikely(elapsed > period)) {
		do_div(bw, elapsed);
		avg = bw;
		goto out;
	}
	bw += (u64)bdi->write_bandwidth * (period - elapsed);
	bw >>= ilog2(period);

	/*
	 * one more level of smoothing, for filtering out sudden spikes
	 */
	if (avg > old && old >= (unsigned long)bw)
		avg -= (avg - old) >> 3;

	if (avg < old && old <= (unsigned long)bw)
		avg += (old - avg) >> 3;

out:
	bdi->write_bandwidth = bw;
	bdi->avg_write_bandwidth = avg;
}

/*
 * The global dirtyable memory and dirty threshold could be suddenly knocked
 * down by a large amount (eg. on the startup of KVM in a swapless system).
 * This may throw the system into deep dirty exceeded state and throttle
 * heavy/light dirtiers alike. To retain good responsiveness, maintain
 * global_dirty_limit for tracking slowly down to the knocked down dirty
 * threshold.
 */
static void update_dirty_limit(unsigned long thresh, unsigned long dirty)
{
	unsigned long limit = global_dirty_limit;

	/*
	 * Follow up in one step.
	 */
	if (limit < thresh) {
		limit = thresh;
		goto update;
	}

	/*
	 * Follow down slowly. Use the higher one as the target, because thresh
	 * may drop below dirty. This is exactly the reason to introduce
	 * global_dirty_limit which is guaranteed to lie above the dirty pages.
	 */
	thresh = max(thresh, dirty);
	if (limit > thresh) {
		limit -= (limit - thresh) >> 5;
		goto update;
	}
	return;
update:
	global_dirty_limit = limit;
}

static void global_update_bandwidth(unsigned long thresh,
				    unsigned long dirty,
				    unsigned long now)
{
	static DEFINE_SPINLOCK(dirty_lock);
	static unsigned long update_time;

	/*
	 * check locklessly first to optimize away locking for the most time
	 */
	if (time_before(now, update_time + BANDWIDTH_INTERVAL))
		return;

	spin_lock(&dirty_lock);
	if (time_after_eq(now, update_time + BANDWIDTH_INTERVAL)) {
		update_dirty_limit(thresh, dirty);
		update_time = now;
	}
	spin_unlock(&dirty_lock);
}

/*
 * Maintain bdi->dirty_ratelimit, the base dirty throttle rate.
 *
 * Normal bdi tasks will be curbed at or below it in long term.
 * Obviously it should be around (write_bw / N) when there are N dd tasks.
 */
static void bdi_update_dirty_ratelimit(struct backing_dev_info *bdi,
				       unsigned long thresh,
				       unsigned long bg_thresh,
				       unsigned long dirty,
				       unsigned long bdi_thresh,
				       unsigned long bdi_dirty,
				       unsigned long dirtied,
				       unsigned long elapsed)
{
	unsigned long freerun = dirty_freerun_ceiling(thresh, bg_thresh);
	unsigned long limit = hard_dirty_limit(thresh);
	unsigned long setpoint = (freerun + limit) / 2;
	unsigned long write_bw = bdi->avg_write_bandwidth;
	unsigned long dirty_ratelimit = bdi->dirty_ratelimit;
	unsigned long dirty_rate;
	unsigned long task_ratelimit;
	unsigned long balanced_dirty_ratelimit;
	unsigned long pos_ratio;
	unsigned long step;
	unsigned long x;

	/*
	 * The dirty rate will match the writeout rate in long term, except
	 * when dirty pages are truncated by userspace or re-dirtied by FS.
	 */
	dirty_rate = (dirtied - bdi->dirtied_stamp) * HZ / elapsed;

	pos_ratio = bdi_position_ratio(bdi, thresh, bg_thresh, dirty,
				       bdi_thresh, bdi_dirty);
	/*
	 * task_ratelimit reflects each dd's dirty rate for the past 200ms.
	 */
	task_ratelimit = (u64)dirty_ratelimit *
					pos_ratio >> RATELIMIT_CALC_SHIFT;
	task_ratelimit++; /* it helps rampup dirty_ratelimit from tiny values */

	/*
	 * A linear estimation of the "balanced" throttle rate. The theory is,
	 * if there are N dd tasks, each throttled at task_ratelimit, the bdi's
	 * dirty_rate will be measured to be (N * task_ratelimit). So the below
	 * formula will yield the balanced rate limit (write_bw / N).
	 *
	 * Note that the expanded form is not a pure rate feedback:
	 *	rate_(i+1) = rate_(i) * (write_bw / dirty_rate)		     (1)
	 * but also takes pos_ratio into account:
	 *	rate_(i+1) = rate_(i) * (write_bw / dirty_rate) * pos_ratio  (2)
	 *
	 * (1) is not realistic because pos_ratio also takes part in balancing
	 * the dirty rate.  Consider the state
	 *	pos_ratio = 0.5						     (3)
	 *	rate = 2 * (write_bw / N)				     (4)
	 * If (1) is used, it will stuck in that state! Because each dd will
	 * be throttled at
	 *	task_ratelimit = pos_ratio * rate = (write_bw / N)	     (5)
	 * yielding
	 *	dirty_rate = N * task_ratelimit = write_bw		     (6)
	 * put (6) into (1) we get
	 *	rate_(i+1) = rate_(i)					     (7)
	 *
	 * So we end up using (2) to always keep
	 *	rate_(i+1) ~= (write_bw / N)				     (8)
	 * regardless of the value of pos_ratio. As long as (8) is satisfied,
	 * pos_ratio is able to drive itself to 1.0, which is not only where
	 * the dirty count meet the setpoint, but also where the slope of
	 * pos_ratio is most flat and hence task_ratelimit is least fluctuated.
	 */
	balanced_dirty_ratelimit = div_u64((u64)task_ratelimit * write_bw,
					   dirty_rate | 1);
	/*
	 * balanced_dirty_ratelimit ~= (write_bw / N) <= write_bw
	 */
	if (unlikely(balanced_dirty_ratelimit > write_bw))
		balanced_dirty_ratelimit = write_bw;

	/*
	 * We could safely do this and return immediately:
	 *
	 *	bdi->dirty_ratelimit = balanced_dirty_ratelimit;
	 *
	 * However to get a more stable dirty_ratelimit, the below elaborated
	 * code makes use of task_ratelimit to filter out sigular points and
	 * limit the step size.
	 *
	 * The below code essentially only uses the relative value of
	 *
	 *	task_ratelimit - dirty_ratelimit
	 *	= (pos_ratio - 1) * dirty_ratelimit
	 *
	 * which reflects the direction and size of dirty position error.
	 */

	/*
	 * dirty_ratelimit will follow balanced_dirty_ratelimit iff
	 * task_ratelimit is on the same side of dirty_ratelimit, too.
	 * For example, when
	 * - dirty_ratelimit > balanced_dirty_ratelimit
	 * - dirty_ratelimit > task_ratelimit (dirty pages are above setpoint)
	 * lowering dirty_ratelimit will help meet both the position and rate
	 * control targets. Otherwise, don't update dirty_ratelimit if it will
	 * only help meet the rate target. After all, what the users ultimately
	 * feel and care are stable dirty rate and small position error.
	 *
	 * |task_ratelimit - dirty_ratelimit| is used to limit the step size
	 * and filter out the sigular points of balanced_dirty_ratelimit. Which
	 * keeps jumping around randomly and can even leap far away at times
	 * due to the small 200ms estimation period of dirty_rate (we want to
	 * keep that period small to reduce time lags).
	 */
	step = 0;
	if (dirty < setpoint) {
		x = min(bdi->balanced_dirty_ratelimit,
			 min(balanced_dirty_ratelimit, task_ratelimit));
		if (dirty_ratelimit < x)
			step = x - dirty_ratelimit;
	} else {
		x = max(bdi->balanced_dirty_ratelimit,
			 max(balanced_dirty_ratelimit, task_ratelimit));
		if (dirty_ratelimit > x)
			step = dirty_ratelimit - x;
	}

	/*
	 * Don't pursue 100% rate matching. It's impossible since the balanced
	 * rate itself is constantly fluctuating. So decrease the track speed
	 * when it gets close to the target. Helps eliminate pointless tremors.
	 */
	step >>= dirty_ratelimit / (2 * step + 1);
	/*
	 * Limit the tracking speed to avoid overshooting.
	 */
	step = (step + 7) / 8;

	if (dirty_ratelimit < balanced_dirty_ratelimit)
		dirty_ratelimit += step;
	else
		dirty_ratelimit -= step;

	bdi->dirty_ratelimit = max(dirty_ratelimit, 1UL);
	bdi->balanced_dirty_ratelimit = balanced_dirty_ratelimit;

	trace_bdi_dirty_ratelimit(bdi, dirty_rate, task_ratelimit);
}

void __bdi_update_bandwidth(struct backing_dev_info *bdi,
			    unsigned long thresh,
			    unsigned long bg_thresh,
			    unsigned long dirty,
			    unsigned long bdi_thresh,
			    unsigned long bdi_dirty,
			    unsigned long start_time)
{
	unsigned long now = jiffies;
	unsigned long elapsed = now - bdi->bw_time_stamp;
	unsigned long dirtied;
	unsigned long written;

	/*
	 * rate-limit, only update once every 200ms.
	 */
	if (elapsed < BANDWIDTH_INTERVAL)
		return;

	dirtied = percpu_counter_read(&bdi->bdi_stat[BDI_DIRTIED]);
	written = percpu_counter_read(&bdi->bdi_stat[BDI_WRITTEN]);

	/*
	 * Skip quiet periods when disk bandwidth is under-utilized.
	 * (at least 1s idle time between two flusher runs)
	 */
	if (elapsed > HZ && time_before(bdi->bw_time_stamp, start_time))
		goto snapshot;

	if (thresh) {
		global_update_bandwidth(thresh, dirty, now);
		bdi_update_dirty_ratelimit(bdi, thresh, bg_thresh, dirty,
					   bdi_thresh, bdi_dirty,
					   dirtied, elapsed);
	}
	bdi_update_write_bandwidth(bdi, elapsed, written);

snapshot:
	bdi->dirtied_stamp = dirtied;
	bdi->written_stamp = written;
	bdi->bw_time_stamp = now;
}

static void bdi_update_bandwidth(struct backing_dev_info *bdi,
				 unsigned long thresh,
				 unsigned long bg_thresh,
				 unsigned long dirty,
				 unsigned long bdi_thresh,
				 unsigned long bdi_dirty,
				 unsigned long start_time)
{
	if (time_is_after_eq_jiffies(bdi->bw_time_stamp + BANDWIDTH_INTERVAL))
		return;
	spin_lock(&bdi->wb.list_lock);
	__bdi_update_bandwidth(bdi, thresh, bg_thresh, dirty,
			       bdi_thresh, bdi_dirty, start_time);
	spin_unlock(&bdi->wb.list_lock);
}

/*
 * After a task dirtied this many pages, balance_dirty_pages_ratelimited_nr()
 * will look to see if it needs to start dirty throttling.
 *
 * If dirty_poll_interval is too low, big NUMA machines will call the expensive
 * global_page_state() too often. So scale it near-sqrt to the safety margin
 * (the number of pages we may dirty without exceeding the dirty limits).
 */
static unsigned long dirty_poll_interval(unsigned long dirty,
					 unsigned long thresh)
{
	if (thresh > dirty)
		return 1UL << (ilog2(thresh - dirty) >> 1);

	return 1;
}

static long bdi_max_pause(struct backing_dev_info *bdi,
			  unsigned long bdi_dirty)
{
	long bw = bdi->avg_write_bandwidth;
	long t;

	/*
	 * Limit pause time for small memory systems. If sleeping for too long
	 * time, a small pool of dirty/writeback pages may go empty and disk go
	 * idle.
	 *
	 * 8 serves as the safety ratio.
	 */
	t = bdi_dirty / (1 + bw / roundup_pow_of_two(1 + HZ / 8));
	t++;

	return min_t(long, t, MAX_PAUSE);
}

static long bdi_min_pause(struct backing_dev_info *bdi,
			  long max_pause,
			  unsigned long task_ratelimit,
			  unsigned long dirty_ratelimit,
			  int *nr_dirtied_pause)
{
	long hi = ilog2(bdi->avg_write_bandwidth);
	long lo = ilog2(bdi->dirty_ratelimit);
	long t;		/* target pause */
	long pause;	/* estimated next pause */
	int pages;	/* target nr_dirtied_pause */

	/* target for 10ms pause on 1-dd case */
	t = max(1, HZ / 100);

	/*
	 * Scale up pause time for concurrent dirtiers in order to reduce CPU
	 * overheads.
	 *
	 * (N * 10ms) on 2^N concurrent tasks.
	 */
	if (hi > lo)
		t += (hi - lo) * (10 * HZ) / 1024;

	/*
	 * This is a bit convoluted. We try to base the next nr_dirtied_pause
	 * on the much more stable dirty_ratelimit. However the next pause time
	 * will be computed based on task_ratelimit and the two rate limits may
	 * depart considerably at some time. Especially if task_ratelimit goes
	 * below dirty_ratelimit/2 and the target pause is max_pause, the next
	 * pause time will be max_pause*2 _trimmed down_ to max_pause.  As a
	 * result task_ratelimit won't be executed faithfully, which could
	 * eventually bring down dirty_ratelimit.
	 *
	 * We apply two rules to fix it up:
	 * 1) try to estimate the next pause time and if necessary, use a lower
	 *    nr_dirtied_pause so as not to exceed max_pause. When this happens,
	 *    nr_dirtied_pause will be "dancing" with task_ratelimit.
	 * 2) limit the target pause time to max_pause/2, so that the normal
	 *    small fluctuations of task_ratelimit won't trigger rule (1) and
	 *    nr_dirtied_pause will remain as stable as dirty_ratelimit.
	 */
	t = min(t, 1 + max_pause / 2);
	pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);

	/*
	 * Tiny nr_dirtied_pause is found to hurt I/O performance in the test
	 * case fio-mmap-randwrite-64k, which does 16*{sync read, async write}.
	 * When the 16 consecutive reads are often interrupted by some dirty
	 * throttling pause during the async writes, cfq will go into idles
	 * (deadline is fine). So push nr_dirtied_pause as high as possible
	 * until reaches DIRTY_POLL_THRESH=32 pages.
	 */
	if (pages < DIRTY_POLL_THRESH) {
		t = max_pause;
		pages = dirty_ratelimit * t / roundup_pow_of_two(HZ);
		if (pages > DIRTY_POLL_THRESH) {
			pages = DIRTY_POLL_THRESH;
			t = HZ * DIRTY_POLL_THRESH / dirty_ratelimit;
		}
	}

	pause = HZ * pages / (task_ratelimit + 1);
	if (pause > max_pause) {
		t = max_pause;
		pages = task_ratelimit * t / roundup_pow_of_two(HZ);
	}

	*nr_dirtied_pause = pages;
	/*
	 * The minimal pause time will normally be half the target pause time.
	 */
	return pages >= DIRTY_POLL_THRESH ? 1 + t / 2 : t;
}

/*
 * 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 wait once crossing the (background_thresh + dirty_thresh) / 2.
 * 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 pages_dirtied)
{
	unsigned long nr_reclaimable;	/* = file_dirty + unstable_nfs */
	unsigned long bdi_reclaimable;
	unsigned long nr_dirty;  /* = file_dirty + writeback + unstable_nfs */
	unsigned long bdi_dirty;
	unsigned long freerun;
	unsigned long background_thresh;
	unsigned long dirty_thresh;
	unsigned long bdi_thresh;
	long period;
	long pause;
	long max_pause;
	long min_pause;
	int nr_dirtied_pause;
	bool dirty_exceeded = false;
	unsigned long task_ratelimit;
	unsigned long dirty_ratelimit;
	unsigned long pos_ratio;
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	unsigned long start_time = jiffies;

	for (;;) {
		unsigned long now = jiffies;

		/*
		 * Unstable writes are a feature of certain networked
		 * filesystems (i.e. NFS) in which data may have been
		 * written to the server's write cache, but has not yet
		 * been flushed to permanent storage.
		 */
		nr_reclaimable = global_page_state(NR_FILE_DIRTY) +
					global_page_state(NR_UNSTABLE_NFS);
		nr_dirty = nr_reclaimable + global_page_state(NR_WRITEBACK);

		global_dirty_limits(&background_thresh, &dirty_thresh);

		/*
		 * Throttle it only when the background writeback cannot
		 * catch-up. This avoids (excessively) small writeouts
		 * when the bdi limits are ramping up.
		 */
		freerun = dirty_freerun_ceiling(dirty_thresh,
						background_thresh);
		if (nr_dirty <= freerun) {
			current->dirty_paused_when = now;
			current->nr_dirtied = 0;
			current->nr_dirtied_pause =
				dirty_poll_interval(nr_dirty, dirty_thresh);
			break;
		}

		if (unlikely(!writeback_in_progress(bdi)))
			bdi_start_background_writeback(bdi);

		/*
		 * bdi_thresh is not treated as some limiting factor as
		 * dirty_thresh, due to reasons
		 * - in JBOD setup, bdi_thresh can fluctuate a lot
		 * - in a system with HDD and USB key, the USB key may somehow
		 *   go into state (bdi_dirty >> bdi_thresh) either because
		 *   bdi_dirty starts high, or because bdi_thresh drops low.
		 *   In this case we don't want to hard throttle the USB key
		 *   dirtiers for 100 seconds until bdi_dirty drops under
		 *   bdi_thresh. Instead the auxiliary bdi control line in
		 *   bdi_position_ratio() will let the dirtier task progress
		 *   at some rate <= (write_bw / 2) for bringing down bdi_dirty.
		 */
		bdi_thresh = bdi_dirty_limit(bdi, dirty_thresh);

		/*
		 * In order to avoid the stacked BDI deadlock we need
		 * to ensure we accurately count the 'dirty' pages when
		 * the threshold is low.
		 *
		 * Otherwise it would be possible to get thresh+n pages
		 * reported dirty, even though there are thresh-m pages
		 * actually dirty; with m+n sitting in the percpu
		 * deltas.
		 */
		if (bdi_thresh < 2 * bdi_stat_error(bdi)) {
			bdi_reclaimable = bdi_stat_sum(bdi, BDI_RECLAIMABLE);
			bdi_dirty = bdi_reclaimable +
				    bdi_stat_sum(bdi, BDI_WRITEBACK);
		} else {
			bdi_reclaimable = bdi_stat(bdi, BDI_RECLAIMABLE);
			bdi_dirty = bdi_reclaimable +
				    bdi_stat(bdi, BDI_WRITEBACK);
		}

		dirty_exceeded = (bdi_dirty > bdi_thresh) &&
				  (nr_dirty > dirty_thresh);
		if (dirty_exceeded && !bdi->dirty_exceeded)
			bdi->dirty_exceeded = 1;

		bdi_update_bandwidth(bdi, dirty_thresh, background_thresh,
				     nr_dirty, bdi_thresh, bdi_dirty,
				     start_time);

		dirty_ratelimit = bdi->dirty_ratelimit;
		pos_ratio = bdi_position_ratio(bdi, dirty_thresh,
					       background_thresh, nr_dirty,
					       bdi_thresh, bdi_dirty);
		task_ratelimit = ((u64)dirty_ratelimit * pos_ratio) >>
							RATELIMIT_CALC_SHIFT;
		max_pause = bdi_max_pause(bdi, bdi_dirty);
		min_pause = bdi_min_pause(bdi, max_pause,
					  task_ratelimit, dirty_ratelimit,
					  &nr_dirtied_pause);

		if (unlikely(task_ratelimit == 0)) {
			period = max_pause;
			pause = max_pause;
			goto pause;
		}
		period = HZ * pages_dirtied / task_ratelimit;
		pause = period;
		if (current->dirty_paused_when)
			pause -= now - current->dirty_paused_when;
		/*
		 * For less than 1s think time (ext3/4 may block the dirtier
		 * for up to 800ms from time to time on 1-HDD; so does xfs,
		 * however at much less frequency), try to compensate it in
		 * future periods by updating the virtual time; otherwise just
		 * do a reset, as it may be a light dirtier.
		 */
		if (pause < min_pause) {
			trace_balance_dirty_pages(bdi,
						  dirty_thresh,
						  background_thresh,
						  nr_dirty,
						  bdi_thresh,
						  bdi_dirty,
						  dirty_ratelimit,
						  task_ratelimit,
						  pages_dirtied,
						  period,
						  min(pause, 0L),
						  start_time);
			if (pause < -HZ) {
				current->dirty_paused_when = now;
				current->nr_dirtied = 0;
			} else if (period) {
				current->dirty_paused_when += period;
				current->nr_dirtied = 0;
			} else if (current->nr_dirtied_pause <= pages_dirtied)
				current->nr_dirtied_pause += pages_dirtied;
			break;
		}
		if (unlikely(pause > max_pause)) {
			/* for occasional dropped task_ratelimit */
			now += min(pause - max_pause, max_pause);
			pause = max_pause;
		}

pause:
		trace_balance_dirty_pages(bdi,
					  dirty_thresh,
					  background_thresh,
					  nr_dirty,
					  bdi_thresh,
					  bdi_dirty,
					  dirty_ratelimit,
					  task_ratelimit,
					  pages_dirtied,
					  period,
					  pause,
					  start_time);
		__set_current_state(TASK_KILLABLE);
		io_schedule_timeout(pause);

		current->dirty_paused_when = now + pause;
		current->nr_dirtied = 0;
		current->nr_dirtied_pause = nr_dirtied_pause;

		/*
		 * This is typically equal to (nr_dirty < dirty_thresh) and can
		 * also keep "1000+ dd on a slow USB stick" under control.
		 */
		if (task_ratelimit)
			break;

		/*
		 * In the case of an unresponding NFS server and the NFS dirty
		 * pages exceeds dirty_thresh, give the other good bdi's a pipe
		 * to go through, so that tasks on them still remain responsive.
		 *
		 * In theory 1 page is enough to keep the comsumer-producer
		 * pipe going: the flusher cleans 1 page => the task dirties 1
		 * more page. However bdi_dirty has accounting errors.  So use
		 * the larger and more IO friendly bdi_stat_error.
		 */
		if (bdi_dirty <= bdi_stat_error(bdi))
			break;

		if (fatal_signal_pending(current))
			break;
	}

	if (!dirty_exceeded && bdi->dirty_exceeded)
		bdi->dirty_exceeded = 0;

	if (writeback_in_progress(bdi))
		return;

	/*
	 * In laptop mode, we wait until hitting the higher threshold before
	 * starting background writeout, and then write out all the way down
	 * to the lower threshold.  So slow writers cause minimal disk activity.
	 *
	 * In normal mode, we start background writeout at the lower
	 * background_thresh, to keep the amount of dirty memory low.
	 */
	if (laptop_mode)
		return;

	if (nr_reclaimable > background_thresh)
		bdi_start_background_writeback(bdi);
}

void set_page_dirty_balance(struct page *page, int page_mkwrite)
{
	if (set_page_dirty(page) || page_mkwrite) {
		struct address_space *mapping = page_mapping(page);

		if (mapping)
			balance_dirty_pages_ratelimited(mapping);
	}
}

static DEFINE_PER_CPU(int, bdp_ratelimits);

/*
 * Normal tasks are throttled by
 *	loop {
 *		dirty tsk->nr_dirtied_pause pages;
 *		take a snap in balance_dirty_pages();
 *	}
 * However there is a worst case. If every task exit immediately when dirtied
 * (tsk->nr_dirtied_pause - 1) pages, balance_dirty_pages() will never be
 * called to throttle the page dirties. The solution is to save the not yet
 * throttled page dirties in dirty_throttle_leaks on task exit and charge them
 * randomly into the running tasks. This works well for the above worst case,
 * as the new task will pick up and accumulate the old task's leaked dirty
 * count and eventually get throttled.
 */
DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0;

/**
 * balance_dirty_pages_ratelimited_nr - balance dirty memory state
 * @mapping: address_space which was dirtied
 * @nr_pages_dirtied: number of pages which the caller has just dirtied
 *
 * Processes which are dirtying memory should call in here once for each page
 * which was newly dirtied.  The function will periodically check the system's
 * dirty state and will initiate writeback if needed.
 *
 * On really big machines, get_writeback_state is expensive, so try to avoid
 * calling it too often (ratelimiting).  But once we're over the dirty memory
 * limit we decrease the ratelimiting by a lot, to prevent individual processes
 * from overshooting the limit by (ratelimit_pages) each.
 */
void balance_dirty_pages_ratelimited_nr(struct address_space *mapping,
					unsigned long nr_pages_dirtied)
{
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	int ratelimit;
	int *p;

	if (!bdi_cap_account_dirty(bdi))
		return;

	ratelimit = current->nr_dirtied_pause;
	if (bdi->dirty_exceeded)
		ratelimit = min(ratelimit, 32 >> (PAGE_SHIFT - 10));

	preempt_disable();
	/*
	 * This prevents one CPU to accumulate too many dirtied pages without
	 * calling into balance_dirty_pages(), which can happen when there are
	 * 1000+ tasks, all of them start dirtying pages at exactly the same
	 * time, hence all honoured too large initial task->nr_dirtied_pause.
	 */
	p =  &__get_cpu_var(bdp_ratelimits);
	if (unlikely(current->nr_dirtied >= ratelimit))
		*p = 0;
	else if (unlikely(*p >= ratelimit_pages)) {
		*p = 0;
		ratelimit = 0;
	}
	/*
	 * Pick up the dirtied pages by the exited tasks. This avoids lots of
	 * short-lived tasks (eg. gcc invocations in a kernel build) escaping
	 * the dirty throttling and livelock other long-run dirtiers.
	 */
	p = &__get_cpu_var(dirty_throttle_leaks);
	if (*p > 0 && current->nr_dirtied < ratelimit) {
		nr_pages_dirtied = min(*p, ratelimit - current->nr_dirtied);
		*p -= nr_pages_dirtied;
		current->nr_dirtied += nr_pages_dirtied;
	}
	preempt_enable();

	if (unlikely(current->nr_dirtied >= ratelimit))
		balance_dirty_pages(mapping, current->nr_dirtied);
}
EXPORT_SYMBOL(balance_dirty_pages_ratelimited_nr);

void throttle_vm_writeout(gfp_t gfp_mask)
{
	unsigned long background_thresh;
	unsigned long dirty_thresh;

        for ( ; ; ) {
		global_dirty_limits(&background_thresh, &dirty_thresh);
		dirty_thresh = hard_dirty_limit(dirty_thresh);

                /*
                 * Boost the allowable dirty threshold a bit for page
                 * allocators so they don't get DoS'ed by heavy writers
                 */
                dirty_thresh += dirty_thresh / 10;      /* wheeee... */

                if (global_page_state(NR_UNSTABLE_NFS) +
			global_page_state(NR_WRITEBACK) <= dirty_thresh)
                        	break;
                congestion_wait(BLK_RW_ASYNC, HZ/10);

		/*
		 * The caller might hold locks which can prevent IO completion
		 * or progress in the filesystem.  So we cannot just sit here
		 * waiting for IO to complete.
		 */
		if ((gfp_mask & (__GFP_FS|__GFP_IO)) != (__GFP_FS|__GFP_IO))
			break;
        }
}

/*
 * sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
 */
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
	void __user *buffer, size_t *length, loff_t *ppos)
{
	proc_dointvec(table, write, buffer, length, ppos);
	bdi_arm_supers_timer();
	return 0;
}

#ifdef CONFIG_BLOCK
void laptop_mode_timer_fn(unsigned long data)
{
	struct request_queue *q = (struct request_queue *)data;
	int nr_pages = global_page_state(NR_FILE_DIRTY) +
		global_page_state(NR_UNSTABLE_NFS);

	/*
	 * We want to write everything out, not just down to the dirty
	 * threshold
	 */
	if (bdi_has_dirty_io(&q->backing_dev_info))
		bdi_start_writeback(&q->backing_dev_info, nr_pages,
					WB_REASON_LAPTOP_TIMER);
}

/*
 * We've spun up the disk and we're in laptop mode: schedule writeback
 * of all dirty data a few seconds from now.  If the flush is already scheduled
 * then push it back - the user is still using the disk.
 */
void laptop_io_completion(struct backing_dev_info *info)
{
	mod_timer(&info->laptop_mode_wb_timer, jiffies + laptop_mode);
}

/*
 * We're in laptop mode and we've just synced. The sync's writes will have
 * caused another writeback to be scheduled by laptop_io_completion.
 * Nothing needs to be written back anymore, so we unschedule the writeback.
 */
void laptop_sync_completion(void)
{
	struct backing_dev_info *bdi;

	rcu_read_lock();

	list_for_each_entry_rcu(bdi, &bdi_list, bdi_list)
		del_timer(&bdi->laptop_mode_wb_timer);

	rcu_read_unlock();
}
#endif

/*
 * If ratelimit_pages is too high then we can get into dirty-data overload
 * if a large number of processes all perform writes at the same time.
 * If it is too low then SMP machines will call the (expensive)
 * get_writeback_state too often.
 *
 * Here we set ratelimit_pages to a level which ensures that when all CPUs are
 * dirtying in parallel, we cannot go more than 3% (1/32) over the dirty memory
 * thresholds.
 */

void writeback_set_ratelimit(void)
{
	unsigned long background_thresh;
	unsigned long dirty_thresh;
	global_dirty_limits(&background_thresh, &dirty_thresh);
	ratelimit_pages = dirty_thresh / (num_online_cpus() * 32);
	if (ratelimit_pages < 16)
		ratelimit_pages = 16;
}

static int __cpuinit
ratelimit_handler(struct notifier_block *self, unsigned long u, void *v)
{
	writeback_set_ratelimit();
	return NOTIFY_DONE;
}

static struct notifier_block __cpuinitdata ratelimit_nb = {
	.notifier_call	= ratelimit_handler,
	.next		= NULL,
};

/*
 * Called early on to tune the page writeback dirty limits.
 *
 * We used to scale dirty pages according to how total memory
 * related to pages that could be allocated for buffers (by
 * comparing nr_free_buffer_pages() to vm_total_pages.
 *
 * However, that was when we used "dirty_ratio" to scale with
 * all memory, and we don't do that any more. "dirty_ratio"
 * is now applied to total non-HIGHPAGE memory (by subtracting
 * totalhigh_pages from vm_total_pages), and as such we can't
 * get into the old insane situation any more where we had
 * large amounts of dirty pages compared to a small amount of
 * non-HIGHMEM memory.
 *
 * But we might still want to scale the dirty_ratio by how
 * much memory the box has..
 */
void __init page_writeback_init(void)
{
	int shift;

	writeback_set_ratelimit();