forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathcfq-iosched.c
2512 lines (2081 loc) · 58.9 KB
/
cfq-iosched.c
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
/*
* CFQ, or complete fairness queueing, disk scheduler.
*
* Based on ideas from a previously unfinished io
* scheduler (round robin per-process disk scheduling) and Andrea Arcangeli.
*
* Copyright (C) 2003 Jens Axboe <axboe@suse.de>
*/
#include <linux/config.h>
#include <linux/module.h>
#include <linux/blkdev.h>
#include <linux/elevator.h>
#include <linux/hash.h>
#include <linux/rbtree.h>
#include <linux/ioprio.h>
/*
* tunables
*/
static const int cfq_quantum = 4; /* max queue in one round of service */
static const int cfq_queued = 8; /* minimum rq allocate limit per-queue*/
static const int cfq_fifo_expire[2] = { HZ / 4, HZ / 8 };
static const int cfq_back_max = 16 * 1024; /* maximum backwards seek, in KiB */
static const int cfq_back_penalty = 2; /* penalty of a backwards seek */
static const int cfq_slice_sync = HZ / 10;
static int cfq_slice_async = HZ / 25;
static const int cfq_slice_async_rq = 2;
static int cfq_slice_idle = HZ / 70;
#define CFQ_IDLE_GRACE (HZ / 10)
#define CFQ_SLICE_SCALE (5)
#define CFQ_KEY_ASYNC (0)
static DEFINE_SPINLOCK(cfq_exit_lock);
/*
* for the hash of cfqq inside the cfqd
*/
#define CFQ_QHASH_SHIFT 6
#define CFQ_QHASH_ENTRIES (1 << CFQ_QHASH_SHIFT)
#define list_entry_qhash(entry) hlist_entry((entry), struct cfq_queue, cfq_hash)
/*
* for the hash of crq inside the cfqq
*/
#define CFQ_MHASH_SHIFT 6
#define CFQ_MHASH_BLOCK(sec) ((sec) >> 3)
#define CFQ_MHASH_ENTRIES (1 << CFQ_MHASH_SHIFT)
#define CFQ_MHASH_FN(sec) hash_long(CFQ_MHASH_BLOCK(sec), CFQ_MHASH_SHIFT)
#define rq_hash_key(rq) ((rq)->sector + (rq)->nr_sectors)
#define list_entry_hash(ptr) hlist_entry((ptr), struct cfq_rq, hash)
#define list_entry_cfqq(ptr) list_entry((ptr), struct cfq_queue, cfq_list)
#define list_entry_fifo(ptr) list_entry((ptr), struct request, queuelist)
#define RQ_DATA(rq) (rq)->elevator_private
/*
* rb-tree defines
*/
#define RB_NONE (2)
#define RB_EMPTY(node) ((node)->rb_node == NULL)
#define RB_CLEAR_COLOR(node) (node)->rb_color = RB_NONE
#define RB_CLEAR(node) do { \
(node)->rb_parent = NULL; \
RB_CLEAR_COLOR((node)); \
(node)->rb_right = NULL; \
(node)->rb_left = NULL; \
} while (0)
#define RB_CLEAR_ROOT(root) ((root)->rb_node = NULL)
#define rb_entry_crq(node) rb_entry((node), struct cfq_rq, rb_node)
#define rq_rb_key(rq) (rq)->sector
static kmem_cache_t *crq_pool;
static kmem_cache_t *cfq_pool;
static kmem_cache_t *cfq_ioc_pool;
static atomic_t ioc_count = ATOMIC_INIT(0);
static struct completion *ioc_gone;
#define CFQ_PRIO_LISTS IOPRIO_BE_NR
#define cfq_class_idle(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_IDLE)
#define cfq_class_be(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_BE)
#define cfq_class_rt(cfqq) ((cfqq)->ioprio_class == IOPRIO_CLASS_RT)
#define ASYNC (0)
#define SYNC (1)
#define cfq_cfqq_dispatched(cfqq) \
((cfqq)->on_dispatch[ASYNC] + (cfqq)->on_dispatch[SYNC])
#define cfq_cfqq_class_sync(cfqq) ((cfqq)->key != CFQ_KEY_ASYNC)
#define cfq_cfqq_sync(cfqq) \
(cfq_cfqq_class_sync(cfqq) || (cfqq)->on_dispatch[SYNC])
#define sample_valid(samples) ((samples) > 80)
/*
* Per block device queue structure
*/
struct cfq_data {
request_queue_t *queue;
/*
* rr list of queues with requests and the count of them
*/
struct list_head rr_list[CFQ_PRIO_LISTS];
struct list_head busy_rr;
struct list_head cur_rr;
struct list_head idle_rr;
unsigned int busy_queues;
/*
* non-ordered list of empty cfqq's
*/
struct list_head empty_list;
/*
* cfqq lookup hash
*/
struct hlist_head *cfq_hash;
/*
* global crq hash for all queues
*/
struct hlist_head *crq_hash;
unsigned int max_queued;
mempool_t *crq_pool;
int rq_in_driver;
int hw_tag;
/*
* schedule slice state info
*/
/*
* idle window management
*/
struct timer_list idle_slice_timer;
struct work_struct unplug_work;
struct cfq_queue *active_queue;
struct cfq_io_context *active_cic;
int cur_prio, cur_end_prio;
unsigned int dispatch_slice;
struct timer_list idle_class_timer;
sector_t last_sector;
unsigned long last_end_request;
unsigned int rq_starved;
/*
* tunables, see top of file
*/
unsigned int cfq_quantum;
unsigned int cfq_queued;
unsigned int cfq_fifo_expire[2];
unsigned int cfq_back_penalty;
unsigned int cfq_back_max;
unsigned int cfq_slice[2];
unsigned int cfq_slice_async_rq;
unsigned int cfq_slice_idle;
struct list_head cic_list;
};
/*
* Per process-grouping structure
*/
struct cfq_queue {
/* reference count */
atomic_t ref;
/* parent cfq_data */
struct cfq_data *cfqd;
/* cfqq lookup hash */
struct hlist_node cfq_hash;
/* hash key */
unsigned int key;
/* on either rr or empty list of cfqd */
struct list_head cfq_list;
/* sorted list of pending requests */
struct rb_root sort_list;
/* if fifo isn't expired, next request to serve */
struct cfq_rq *next_crq;
/* requests queued in sort_list */
int queued[2];
/* currently allocated requests */
int allocated[2];
/* fifo list of requests in sort_list */
struct list_head fifo;
unsigned long slice_start;
unsigned long slice_end;
unsigned long slice_left;
unsigned long service_last;
/* number of requests that are on the dispatch list */
int on_dispatch[2];
/* io prio of this group */
unsigned short ioprio, org_ioprio;
unsigned short ioprio_class, org_ioprio_class;
/* various state flags, see below */
unsigned int flags;
};
struct cfq_rq {
struct rb_node rb_node;
sector_t rb_key;
struct request *request;
struct hlist_node hash;
struct cfq_queue *cfq_queue;
struct cfq_io_context *io_context;
unsigned int crq_flags;
};
enum cfqq_state_flags {
CFQ_CFQQ_FLAG_on_rr = 0,
CFQ_CFQQ_FLAG_wait_request,
CFQ_CFQQ_FLAG_must_alloc,
CFQ_CFQQ_FLAG_must_alloc_slice,
CFQ_CFQQ_FLAG_must_dispatch,
CFQ_CFQQ_FLAG_fifo_expire,
CFQ_CFQQ_FLAG_idle_window,
CFQ_CFQQ_FLAG_prio_changed,
};
#define CFQ_CFQQ_FNS(name) \
static inline void cfq_mark_cfqq_##name(struct cfq_queue *cfqq) \
{ \
cfqq->flags |= (1 << CFQ_CFQQ_FLAG_##name); \
} \
static inline void cfq_clear_cfqq_##name(struct cfq_queue *cfqq) \
{ \
cfqq->flags &= ~(1 << CFQ_CFQQ_FLAG_##name); \
} \
static inline int cfq_cfqq_##name(const struct cfq_queue *cfqq) \
{ \
return (cfqq->flags & (1 << CFQ_CFQQ_FLAG_##name)) != 0; \
}
CFQ_CFQQ_FNS(on_rr);
CFQ_CFQQ_FNS(wait_request);
CFQ_CFQQ_FNS(must_alloc);
CFQ_CFQQ_FNS(must_alloc_slice);
CFQ_CFQQ_FNS(must_dispatch);
CFQ_CFQQ_FNS(fifo_expire);
CFQ_CFQQ_FNS(idle_window);
CFQ_CFQQ_FNS(prio_changed);
#undef CFQ_CFQQ_FNS
enum cfq_rq_state_flags {
CFQ_CRQ_FLAG_is_sync = 0,
};
#define CFQ_CRQ_FNS(name) \
static inline void cfq_mark_crq_##name(struct cfq_rq *crq) \
{ \
crq->crq_flags |= (1 << CFQ_CRQ_FLAG_##name); \
} \
static inline void cfq_clear_crq_##name(struct cfq_rq *crq) \
{ \
crq->crq_flags &= ~(1 << CFQ_CRQ_FLAG_##name); \
} \
static inline int cfq_crq_##name(const struct cfq_rq *crq) \
{ \
return (crq->crq_flags & (1 << CFQ_CRQ_FLAG_##name)) != 0; \
}
CFQ_CRQ_FNS(is_sync);
#undef CFQ_CRQ_FNS
static struct cfq_queue *cfq_find_cfq_hash(struct cfq_data *, unsigned int, unsigned short);
static void cfq_dispatch_insert(request_queue_t *, struct cfq_rq *);
static struct cfq_queue *cfq_get_queue(struct cfq_data *cfqd, unsigned int key, struct task_struct *tsk, gfp_t gfp_mask);
#define process_sync(tsk) ((tsk)->flags & PF_SYNCWRITE)
/*
* lots of deadline iosched dupes, can be abstracted later...
*/
static inline void cfq_del_crq_hash(struct cfq_rq *crq)
{
hlist_del_init(&crq->hash);
}
static inline void cfq_add_crq_hash(struct cfq_data *cfqd, struct cfq_rq *crq)
{
const int hash_idx = CFQ_MHASH_FN(rq_hash_key(crq->request));
hlist_add_head(&crq->hash, &cfqd->crq_hash[hash_idx]);
}
static struct request *cfq_find_rq_hash(struct cfq_data *cfqd, sector_t offset)
{
struct hlist_head *hash_list = &cfqd->crq_hash[CFQ_MHASH_FN(offset)];
struct hlist_node *entry, *next;
hlist_for_each_safe(entry, next, hash_list) {
struct cfq_rq *crq = list_entry_hash(entry);
struct request *__rq = crq->request;
if (!rq_mergeable(__rq)) {
cfq_del_crq_hash(crq);
continue;
}
if (rq_hash_key(__rq) == offset)
return __rq;
}
return NULL;
}
/*
* scheduler run of queue, if there are requests pending and no one in the
* driver that will restart queueing
*/
static inline void cfq_schedule_dispatch(struct cfq_data *cfqd)
{
if (cfqd->busy_queues)
kblockd_schedule_work(&cfqd->unplug_work);
}
static int cfq_queue_empty(request_queue_t *q)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
return !cfqd->busy_queues;
}
static inline pid_t cfq_queue_pid(struct task_struct *task, int rw)
{
if (rw == READ || process_sync(task))
return task->pid;
return CFQ_KEY_ASYNC;
}
/*
* Lifted from AS - choose which of crq1 and crq2 that is best served now.
* We choose the request that is closest to the head right now. Distance
* behind the head is penalized and only allowed to a certain extent.
*/
static struct cfq_rq *
cfq_choose_req(struct cfq_data *cfqd, struct cfq_rq *crq1, struct cfq_rq *crq2)
{
sector_t last, s1, s2, d1 = 0, d2 = 0;
unsigned long back_max;
#define CFQ_RQ1_WRAP 0x01 /* request 1 wraps */
#define CFQ_RQ2_WRAP 0x02 /* request 2 wraps */
unsigned wrap = 0; /* bit mask: requests behind the disk head? */
if (crq1 == NULL || crq1 == crq2)
return crq2;
if (crq2 == NULL)
return crq1;
if (cfq_crq_is_sync(crq1) && !cfq_crq_is_sync(crq2))
return crq1;
else if (cfq_crq_is_sync(crq2) && !cfq_crq_is_sync(crq1))
return crq2;
s1 = crq1->request->sector;
s2 = crq2->request->sector;
last = cfqd->last_sector;
/*
* by definition, 1KiB is 2 sectors
*/
back_max = cfqd->cfq_back_max * 2;
/*
* Strict one way elevator _except_ in the case where we allow
* short backward seeks which are biased as twice the cost of a
* similar forward seek.
*/
if (s1 >= last)
d1 = s1 - last;
else if (s1 + back_max >= last)
d1 = (last - s1) * cfqd->cfq_back_penalty;
else
wrap |= CFQ_RQ1_WRAP;
if (s2 >= last)
d2 = s2 - last;
else if (s2 + back_max >= last)
d2 = (last - s2) * cfqd->cfq_back_penalty;
else
wrap |= CFQ_RQ2_WRAP;
/* Found required data */
/*
* By doing switch() on the bit mask "wrap" we avoid having to
* check two variables for all permutations: --> faster!
*/
switch (wrap) {
case 0: /* common case for CFQ: crq1 and crq2 not wrapped */
if (d1 < d2)
return crq1;
else if (d2 < d1)
return crq2;
else {
if (s1 >= s2)
return crq1;
else
return crq2;
}
case CFQ_RQ2_WRAP:
return crq1;
case CFQ_RQ1_WRAP:
return crq2;
case (CFQ_RQ1_WRAP|CFQ_RQ2_WRAP): /* both crqs wrapped */
default:
/*
* Since both rqs are wrapped,
* start with the one that's further behind head
* (--> only *one* back seek required),
* since back seek takes more time than forward.
*/
if (s1 <= s2)
return crq1;
else
return crq2;
}
}
/*
* would be nice to take fifo expire time into account as well
*/
static struct cfq_rq *
cfq_find_next_crq(struct cfq_data *cfqd, struct cfq_queue *cfqq,
struct cfq_rq *last)
{
struct cfq_rq *crq_next = NULL, *crq_prev = NULL;
struct rb_node *rbnext, *rbprev;
if (!(rbnext = rb_next(&last->rb_node))) {
rbnext = rb_first(&cfqq->sort_list);
if (rbnext == &last->rb_node)
rbnext = NULL;
}
rbprev = rb_prev(&last->rb_node);
if (rbprev)
crq_prev = rb_entry_crq(rbprev);
if (rbnext)
crq_next = rb_entry_crq(rbnext);
return cfq_choose_req(cfqd, crq_next, crq_prev);
}
static void cfq_update_next_crq(struct cfq_rq *crq)
{
struct cfq_queue *cfqq = crq->cfq_queue;
if (cfqq->next_crq == crq)
cfqq->next_crq = cfq_find_next_crq(cfqq->cfqd, cfqq, crq);
}
static void cfq_resort_rr_list(struct cfq_queue *cfqq, int preempted)
{
struct cfq_data *cfqd = cfqq->cfqd;
struct list_head *list, *entry;
BUG_ON(!cfq_cfqq_on_rr(cfqq));
list_del(&cfqq->cfq_list);
if (cfq_class_rt(cfqq))
list = &cfqd->cur_rr;
else if (cfq_class_idle(cfqq))
list = &cfqd->idle_rr;
else {
/*
* if cfqq has requests in flight, don't allow it to be
* found in cfq_set_active_queue before it has finished them.
* this is done to increase fairness between a process that
* has lots of io pending vs one that only generates one
* sporadically or synchronously
*/
if (cfq_cfqq_dispatched(cfqq))
list = &cfqd->busy_rr;
else
list = &cfqd->rr_list[cfqq->ioprio];
}
/*
* if queue was preempted, just add to front to be fair. busy_rr
* isn't sorted, but insert at the back for fairness.
*/
if (preempted || list == &cfqd->busy_rr) {
if (preempted)
list = list->prev;
list_add_tail(&cfqq->cfq_list, list);
return;
}
/*
* sort by when queue was last serviced
*/
entry = list;
while ((entry = entry->prev) != list) {
struct cfq_queue *__cfqq = list_entry_cfqq(entry);
if (!__cfqq->service_last)
break;
if (time_before(__cfqq->service_last, cfqq->service_last))
break;
}
list_add(&cfqq->cfq_list, entry);
}
/*
* add to busy list of queues for service, trying to be fair in ordering
* the pending list according to last request service
*/
static inline void
cfq_add_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
BUG_ON(cfq_cfqq_on_rr(cfqq));
cfq_mark_cfqq_on_rr(cfqq);
cfqd->busy_queues++;
cfq_resort_rr_list(cfqq, 0);
}
static inline void
cfq_del_cfqq_rr(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
BUG_ON(!cfq_cfqq_on_rr(cfqq));
cfq_clear_cfqq_on_rr(cfqq);
list_move(&cfqq->cfq_list, &cfqd->empty_list);
BUG_ON(!cfqd->busy_queues);
cfqd->busy_queues--;
}
/*
* rb tree support functions
*/
static inline void cfq_del_crq_rb(struct cfq_rq *crq)
{
struct cfq_queue *cfqq = crq->cfq_queue;
struct cfq_data *cfqd = cfqq->cfqd;
const int sync = cfq_crq_is_sync(crq);
BUG_ON(!cfqq->queued[sync]);
cfqq->queued[sync]--;
cfq_update_next_crq(crq);
rb_erase(&crq->rb_node, &cfqq->sort_list);
RB_CLEAR_COLOR(&crq->rb_node);
if (cfq_cfqq_on_rr(cfqq) && RB_EMPTY(&cfqq->sort_list))
cfq_del_cfqq_rr(cfqd, cfqq);
}
static struct cfq_rq *
__cfq_add_crq_rb(struct cfq_rq *crq)
{
struct rb_node **p = &crq->cfq_queue->sort_list.rb_node;
struct rb_node *parent = NULL;
struct cfq_rq *__crq;
while (*p) {
parent = *p;
__crq = rb_entry_crq(parent);
if (crq->rb_key < __crq->rb_key)
p = &(*p)->rb_left;
else if (crq->rb_key > __crq->rb_key)
p = &(*p)->rb_right;
else
return __crq;
}
rb_link_node(&crq->rb_node, parent, p);
return NULL;
}
static void cfq_add_crq_rb(struct cfq_rq *crq)
{
struct cfq_queue *cfqq = crq->cfq_queue;
struct cfq_data *cfqd = cfqq->cfqd;
struct request *rq = crq->request;
struct cfq_rq *__alias;
crq->rb_key = rq_rb_key(rq);
cfqq->queued[cfq_crq_is_sync(crq)]++;
/*
* looks a little odd, but the first insert might return an alias.
* if that happens, put the alias on the dispatch list
*/
while ((__alias = __cfq_add_crq_rb(crq)) != NULL)
cfq_dispatch_insert(cfqd->queue, __alias);
rb_insert_color(&crq->rb_node, &cfqq->sort_list);
if (!cfq_cfqq_on_rr(cfqq))
cfq_add_cfqq_rr(cfqd, cfqq);
/*
* check if this request is a better next-serve candidate
*/
cfqq->next_crq = cfq_choose_req(cfqd, cfqq->next_crq, crq);
}
static inline void
cfq_reposition_crq_rb(struct cfq_queue *cfqq, struct cfq_rq *crq)
{
rb_erase(&crq->rb_node, &cfqq->sort_list);
cfqq->queued[cfq_crq_is_sync(crq)]--;
cfq_add_crq_rb(crq);
}
static struct request *
cfq_find_rq_fmerge(struct cfq_data *cfqd, struct bio *bio)
{
struct task_struct *tsk = current;
pid_t key = cfq_queue_pid(tsk, bio_data_dir(bio));
struct cfq_queue *cfqq;
struct rb_node *n;
sector_t sector;
cfqq = cfq_find_cfq_hash(cfqd, key, tsk->ioprio);
if (!cfqq)
goto out;
sector = bio->bi_sector + bio_sectors(bio);
n = cfqq->sort_list.rb_node;
while (n) {
struct cfq_rq *crq = rb_entry_crq(n);
if (sector < crq->rb_key)
n = n->rb_left;
else if (sector > crq->rb_key)
n = n->rb_right;
else
return crq->request;
}
out:
return NULL;
}
static void cfq_activate_request(request_queue_t *q, struct request *rq)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
cfqd->rq_in_driver++;
/*
* If the depth is larger 1, it really could be queueing. But lets
* make the mark a little higher - idling could still be good for
* low queueing, and a low queueing number could also just indicate
* a SCSI mid layer like behaviour where limit+1 is often seen.
*/
if (!cfqd->hw_tag && cfqd->rq_in_driver > 4)
cfqd->hw_tag = 1;
}
static void cfq_deactivate_request(request_queue_t *q, struct request *rq)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
WARN_ON(!cfqd->rq_in_driver);
cfqd->rq_in_driver--;
}
static void cfq_remove_request(struct request *rq)
{
struct cfq_rq *crq = RQ_DATA(rq);
list_del_init(&rq->queuelist);
cfq_del_crq_rb(crq);
cfq_del_crq_hash(crq);
}
static int
cfq_merge(request_queue_t *q, struct request **req, struct bio *bio)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
struct request *__rq;
int ret;
__rq = cfq_find_rq_hash(cfqd, bio->bi_sector);
if (__rq && elv_rq_merge_ok(__rq, bio)) {
ret = ELEVATOR_BACK_MERGE;
goto out;
}
__rq = cfq_find_rq_fmerge(cfqd, bio);
if (__rq && elv_rq_merge_ok(__rq, bio)) {
ret = ELEVATOR_FRONT_MERGE;
goto out;
}
return ELEVATOR_NO_MERGE;
out:
*req = __rq;
return ret;
}
static void cfq_merged_request(request_queue_t *q, struct request *req)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_rq *crq = RQ_DATA(req);
cfq_del_crq_hash(crq);
cfq_add_crq_hash(cfqd, crq);
if (rq_rb_key(req) != crq->rb_key) {
struct cfq_queue *cfqq = crq->cfq_queue;
cfq_update_next_crq(crq);
cfq_reposition_crq_rb(cfqq, crq);
}
}
static void
cfq_merged_requests(request_queue_t *q, struct request *rq,
struct request *next)
{
cfq_merged_request(q, rq);
/*
* reposition in fifo if next is older than rq
*/
if (!list_empty(&rq->queuelist) && !list_empty(&next->queuelist) &&
time_before(next->start_time, rq->start_time))
list_move(&rq->queuelist, &next->queuelist);
cfq_remove_request(next);
}
static inline void
__cfq_set_active_queue(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
if (cfqq) {
/*
* stop potential idle class queues waiting service
*/
del_timer(&cfqd->idle_class_timer);
cfqq->slice_start = jiffies;
cfqq->slice_end = 0;
cfqq->slice_left = 0;
cfq_clear_cfqq_must_alloc_slice(cfqq);
cfq_clear_cfqq_fifo_expire(cfqq);
}
cfqd->active_queue = cfqq;
}
/*
* current cfqq expired its slice (or was too idle), select new one
*/
static void
__cfq_slice_expired(struct cfq_data *cfqd, struct cfq_queue *cfqq,
int preempted)
{
unsigned long now = jiffies;
if (cfq_cfqq_wait_request(cfqq))
del_timer(&cfqd->idle_slice_timer);
if (!preempted && !cfq_cfqq_dispatched(cfqq)) {
cfqq->service_last = now;
cfq_schedule_dispatch(cfqd);
}
cfq_clear_cfqq_must_dispatch(cfqq);
cfq_clear_cfqq_wait_request(cfqq);
/*
* store what was left of this slice, if the queue idled out
* or was preempted
*/
if (time_after(cfqq->slice_end, now))
cfqq->slice_left = cfqq->slice_end - now;
else
cfqq->slice_left = 0;
if (cfq_cfqq_on_rr(cfqq))
cfq_resort_rr_list(cfqq, preempted);
if (cfqq == cfqd->active_queue)
cfqd->active_queue = NULL;
if (cfqd->active_cic) {
put_io_context(cfqd->active_cic->ioc);
cfqd->active_cic = NULL;
}
cfqd->dispatch_slice = 0;
}
static inline void cfq_slice_expired(struct cfq_data *cfqd, int preempted)
{
struct cfq_queue *cfqq = cfqd->active_queue;
if (cfqq)
__cfq_slice_expired(cfqd, cfqq, preempted);
}
/*
* 0
* 0,1
* 0,1,2
* 0,1,2,3
* 0,1,2,3,4
* 0,1,2,3,4,5
* 0,1,2,3,4,5,6
* 0,1,2,3,4,5,6,7
*/
static int cfq_get_next_prio_level(struct cfq_data *cfqd)
{
int prio, wrap;
prio = -1;
wrap = 0;
do {
int p;
for (p = cfqd->cur_prio; p <= cfqd->cur_end_prio; p++) {
if (!list_empty(&cfqd->rr_list[p])) {
prio = p;
break;
}
}
if (prio != -1)
break;
cfqd->cur_prio = 0;
if (++cfqd->cur_end_prio == CFQ_PRIO_LISTS) {
cfqd->cur_end_prio = 0;
if (wrap)
break;
wrap = 1;
}
} while (1);
if (unlikely(prio == -1))
return -1;
BUG_ON(prio >= CFQ_PRIO_LISTS);
list_splice_init(&cfqd->rr_list[prio], &cfqd->cur_rr);
cfqd->cur_prio = prio + 1;
if (cfqd->cur_prio > cfqd->cur_end_prio) {
cfqd->cur_end_prio = cfqd->cur_prio;
cfqd->cur_prio = 0;
}
if (cfqd->cur_end_prio == CFQ_PRIO_LISTS) {
cfqd->cur_prio = 0;
cfqd->cur_end_prio = 0;
}
return prio;
}
static struct cfq_queue *cfq_set_active_queue(struct cfq_data *cfqd)
{
struct cfq_queue *cfqq = NULL;
/*
* if current list is non-empty, grab first entry. if it is empty,
* get next prio level and grab first entry then if any are spliced
*/
if (!list_empty(&cfqd->cur_rr) || cfq_get_next_prio_level(cfqd) != -1)
cfqq = list_entry_cfqq(cfqd->cur_rr.next);
/*
* If no new queues are available, check if the busy list has some
* before falling back to idle io.
*/
if (!cfqq && !list_empty(&cfqd->busy_rr))
cfqq = list_entry_cfqq(cfqd->busy_rr.next);
/*
* if we have idle queues and no rt or be queues had pending
* requests, either allow immediate service if the grace period
* has passed or arm the idle grace timer
*/
if (!cfqq && !list_empty(&cfqd->idle_rr)) {
unsigned long end = cfqd->last_end_request + CFQ_IDLE_GRACE;
if (time_after_eq(jiffies, end))
cfqq = list_entry_cfqq(cfqd->idle_rr.next);
else
mod_timer(&cfqd->idle_class_timer, end);
}
__cfq_set_active_queue(cfqd, cfqq);
return cfqq;
}
static int cfq_arm_slice_timer(struct cfq_data *cfqd, struct cfq_queue *cfqq)
{
struct cfq_io_context *cic;
unsigned long sl;
WARN_ON(!RB_EMPTY(&cfqq->sort_list));
WARN_ON(cfqq != cfqd->active_queue);
/*
* idle is disabled, either manually or by past process history
*/
if (!cfqd->cfq_slice_idle)
return 0;
if (!cfq_cfqq_idle_window(cfqq))
return 0;
/*
* task has exited, don't wait
*/
cic = cfqd->active_cic;
if (!cic || !cic->ioc->task)
return 0;
cfq_mark_cfqq_must_dispatch(cfqq);
cfq_mark_cfqq_wait_request(cfqq);
sl = min(cfqq->slice_end - 1, (unsigned long) cfqd->cfq_slice_idle);
/*
* we don't want to idle for seeks, but we do want to allow
* fair distribution of slice time for a process doing back-to-back
* seeks. so allow a little bit of time for him to submit a new rq
*/
if (sample_valid(cic->seek_samples) && cic->seek_mean > 131072)
sl = 2;
mod_timer(&cfqd->idle_slice_timer, jiffies + sl);
return 1;
}
static void cfq_dispatch_insert(request_queue_t *q, struct cfq_rq *crq)
{
struct cfq_data *cfqd = q->elevator->elevator_data;
struct cfq_queue *cfqq = crq->cfq_queue;
cfqq->next_crq = cfq_find_next_crq(cfqd, cfqq, crq);
cfq_remove_request(crq->request);
cfqq->on_dispatch[cfq_crq_is_sync(crq)]++;
elv_dispatch_sort(q, crq->request);
}
/*
* return expired entry, or NULL to just start from scratch in rbtree
*/
static inline struct cfq_rq *cfq_check_fifo(struct cfq_queue *cfqq)
{
struct cfq_data *cfqd = cfqq->cfqd;
struct request *rq;
struct cfq_rq *crq;
if (cfq_cfqq_fifo_expire(cfqq))
return NULL;
if (!list_empty(&cfqq->fifo)) {
int fifo = cfq_cfqq_class_sync(cfqq);
crq = RQ_DATA(list_entry_fifo(cfqq->fifo.next));
rq = crq->request;
if (time_after(jiffies, rq->start_time + cfqd->cfq_fifo_expire[fifo])) {
cfq_mark_cfqq_fifo_expire(cfqq);
return crq;
}
}
return NULL;
}
/*
* Scale schedule slice based on io priority. Use the sync time slice only
* if a queue is marked sync and has sync io queued. A sync queue with async
* io only, should not get full sync slice length.
*/