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
|
#ifndef _LINUX_BLKDEV_H
#define _LINUX_BLKDEV_H
#include <linux/major.h>
#include <linux/genhd.h>
#include <linux/list.h>
#include <linux/timer.h>
#include <linux/workqueue.h>
#include <linux/pagemap.h>
#include <linux/backing-dev.h>
#include <linux/wait.h>
#include <linux/mempool.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/stringify.h>
#include <asm/scatterlist.h>
struct scsi_ioctl_command;
struct request_queue;
typedef struct request_queue request_queue_t;
struct elevator_queue;
typedef struct elevator_queue elevator_t;
struct request_pm_state;
struct blk_trace;
#define BLKDEV_MIN_RQ 4
#define BLKDEV_MAX_RQ 128 /* Default maximum */
/*
* This is the per-process anticipatory I/O scheduler state.
*/
struct as_io_context {
spinlock_t lock;
void (*dtor)(struct as_io_context *aic); /* destructor */
void (*exit)(struct as_io_context *aic); /* called on task exit */
unsigned long state;
atomic_t nr_queued; /* queued reads & sync writes */
atomic_t nr_dispatched; /* number of requests gone to the drivers */
/* IO History tracking */
/* Thinktime */
unsigned long last_end_request;
unsigned long ttime_total;
unsigned long ttime_samples;
unsigned long ttime_mean;
/* Layout pattern */
unsigned int seek_samples;
sector_t last_request_pos;
u64 seek_total;
sector_t seek_mean;
};
struct cfq_queue;
struct cfq_io_context {
struct rb_node rb_node;
void *key;
struct cfq_queue *cfqq[2];
struct io_context *ioc;
unsigned long last_end_request;
sector_t last_request_pos;
unsigned long last_queue;
unsigned long ttime_total;
unsigned long ttime_samples;
unsigned long ttime_mean;
unsigned int seek_samples;
u64 seek_total;
sector_t seek_mean;
struct list_head queue_list;
void (*dtor)(struct io_context *); /* destructor */
void (*exit)(struct io_context *); /* called on task exit */
};
/*
* This is the per-process I/O subsystem state. It is refcounted and
* kmalloc'ed. Currently all fields are modified in process io context
* (apart from the atomic refcount), so require no locking.
*/
struct io_context {
atomic_t refcount;
struct task_struct *task;
int (*set_ioprio)(struct io_context *, unsigned int);
/*
* For request batching
*/
unsigned long last_waited; /* Time last woken after wait for request */
int nr_batch_requests; /* Number of requests left in the batch */
struct as_io_context *aic;
struct rb_root cic_root;
};
void put_io_context(struct io_context *ioc);
void exit_io_context(void);
struct io_context *current_io_context(gfp_t gfp_flags);
struct io_context *get_io_context(gfp_t gfp_flags);
void copy_io_context(struct io_context **pdst, struct io_context **psrc);
void swap_io_context(struct io_context **ioc1, struct io_context **ioc2);
struct request;
typedef void (rq_end_io_fn)(struct request *, int);
struct request_list {
int count[2];
int starved[2];
int elvpriv;
mempool_t *rq_pool;
wait_queue_head_t wait[2];
};
/*
* request command types
*/
enum rq_cmd_type_bits {
REQ_TYPE_FS = 1, /* fs request */
REQ_TYPE_BLOCK_PC, /* scsi command */
REQ_TYPE_SENSE, /* sense request */
REQ_TYPE_PM_SUSPEND, /* suspend request */
REQ_TYPE_PM_RESUME, /* resume request */
REQ_TYPE_PM_SHUTDOWN, /* shutdown request */
REQ_TYPE_FLUSH, /* flush request */
REQ_TYPE_SPECIAL, /* driver defined type */
REQ_TYPE_LINUX_BLOCK, /* generic block layer message */
/*
* for ATA/ATAPI devices. this really doesn't belong here, ide should
* use REQ_TYPE_SPECIAL and use rq->cmd[0] with the range of driver
* private REQ_LB opcodes to differentiate what type of request this is
*/
REQ_TYPE_ATA_CMD,
REQ_TYPE_ATA_TASK,
REQ_TYPE_ATA_TASKFILE,
};
/*
* For request of type REQ_TYPE_LINUX_BLOCK, rq->cmd[0] is the opcode being
* sent down (similar to how REQ_TYPE_BLOCK_PC means that ->cmd[] holds a
* SCSI cdb.
*
* 0x00 -> 0x3f are driver private, to be used for whatever purpose they need,
* typically to differentiate REQ_TYPE_SPECIAL requests.
*
*/
enum {
/*
* just examples for now
*/
REQ_LB_OP_EJECT = 0x40, /* eject request */
REQ_LB_OP_FLUSH = 0x41, /* flush device */
};
/*
* request type modified bits. first three bits match BIO_RW* bits, important
*/
enum rq_flag_bits {
__REQ_RW, /* not set, read. set, write */
__REQ_FAILFAST, /* no low level driver retries */
__REQ_SORTED, /* elevator knows about this request */
__REQ_SOFTBARRIER, /* may not be passed by ioscheduler */
__REQ_HARDBARRIER, /* may not be passed by drive either */
__REQ_FUA, /* forced unit access */
__REQ_NOMERGE, /* don't touch this for merging */
__REQ_STARTED, /* drive already may have started this one */
__REQ_DONTPREP, /* don't call prep for this one */
__REQ_QUEUED, /* uses queueing */
__REQ_ELVPRIV, /* elevator private data attached */
__REQ_FAILED, /* set if the request failed */
__REQ_QUIET, /* don't worry about errors */
__REQ_PREEMPT, /* set for "ide_preempt" requests */
__REQ_ORDERED_COLOR, /* is before or after barrier */
__REQ_RW_SYNC, /* request is sync (O_DIRECT) */
__REQ_NR_BITS, /* stops here */
};
#define REQ_RW (1 << __REQ_RW)
#define REQ_FAILFAST (1 << __REQ_FAILFAST)
#define REQ_SORTED (1 << __REQ_SORTED)
#define REQ_SOFTBARRIER (1 << __REQ_SOFTBARRIER)
#define REQ_HARDBARRIER (1 << __REQ_HARDBARRIER)
#define REQ_FUA (1 << __REQ_FUA)
#define REQ_NOMERGE (1 << __REQ_NOMERGE)
#define REQ_STARTED (1 << __REQ_STARTED)
#define REQ_DONTPREP (1 << __REQ_DONTPREP)
#define REQ_QUEUED (1 << __REQ_QUEUED)
#define REQ_ELVPRIV (1 << __REQ_ELVPRIV)
#define REQ_FAILED (1 << __REQ_FAILED)
#define REQ_QUIET (1 << __REQ_QUIET)
#define REQ_PREEMPT (1 << __REQ_PREEMPT)
#define REQ_ORDERED_COLOR (1 << __REQ_ORDERED_COLOR)
#define REQ_RW_SYNC (1 << __REQ_RW_SYNC)
#define BLK_MAX_CDB 16
/*
* try to put the fields that are referenced together in the same cacheline
*/
struct request {
struct list_head queuelist;
struct list_head donelist;
unsigned int cmd_flags;
enum rq_cmd_type_bits cmd_type;
/* Maintain bio traversal state for part by part I/O submission.
* hard_* are block layer internals, no driver should touch them!
*/
sector_t sector; /* next sector to submit */
unsigned long nr_sectors; /* no. of sectors left to submit */
/* no. of sectors left to submit in the current segment */
unsigned int current_nr_sectors;
sector_t hard_sector; /* next sector to complete */
unsigned long hard_nr_sectors; /* no. of sectors left to complete */
/* no. of sectors left to complete in the current segment */
unsigned int hard_cur_sectors;
struct bio *bio;
struct bio *biotail;
struct hlist_node hash; /* merge hash */
struct rb_node rb_node; /* sort/lookup */
void *elevator_private;
|