summaryrefslogtreecommitdiff
path: root/block/bfq-iosched.h
blob: 4ce7915e8d8474766c5becc571c088a2fd8908c1 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
/*
 * Header file for the BFQ I/O scheduler: data structures and
 * prototypes of interface functions among BFQ components.
 *
 *  This program is free software; you can redistribute it and/or
 *  modify it under the terms of the GNU General Public License as
 *  published by the Free Software Foundation; either version 2 of the
 *  License, or (at your option) any later version.
 *
 *  This program is distributed in the hope that it will be useful,
 *  but WITHOUT ANY WARRANTY; without even the implied warranty of
 *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 *  General Public License for more details.
 */
#ifndef _BFQ_H
#define _BFQ_H

#include <linux/blktrace_api.h>
#include <linux/hrtimer.h>
#include <linux/blk-cgroup.h>

#define BFQ_IOPRIO_CLASSES	3
#define BFQ_CL_IDLE_TIMEOUT	(HZ/5)

#define BFQ_MIN_WEIGHT			1
#define BFQ_MAX_WEIGHT			1000
#define BFQ_WEIGHT_CONVERSION_COEFF	10

#define BFQ_DEFAULT_QUEUE_IOPRIO	4

#define BFQ_WEIGHT_LEGACY_DFL	100
#define BFQ_DEFAULT_GRP_IOPRIO	0
#define BFQ_DEFAULT_GRP_CLASS	IOPRIO_CLASS_BE

/*
 * Soft real-time applications are extremely more latency sensitive
 * than interactive ones. Over-raise the weight of the former to
 * privilege them against the latter.
 */
#define BFQ_SOFTRT_WEIGHT_FACTOR	100

struct bfq_entity;

/**
 * struct bfq_service_tree - per ioprio_class service tree.
 *
 * Each service tree represents a B-WF2Q+ scheduler on its own.  Each
 * ioprio_class has its own independent scheduler, and so its own
 * bfq_service_tree.  All the fields are protected by the queue lock
 * of the containing bfqd.
 */
struct bfq_service_tree {
	/* tree for active entities (i.e., those backlogged) */
	struct rb_root active;
	/* tree for idle entities (i.e., not backlogged, with V <= F_i)*/
	struct rb_root idle;

	/* idle entity with minimum F_i */
	struct bfq_entity *first_idle;
	/* idle entity with maximum F_i */
	struct bfq_entity *last_idle;

	/* scheduler virtual time */
	u64 vtime;
	/* scheduler weight sum; active and idle entities contribute to it */
	unsigned long wsum;
};

/**
 * struct bfq_sched_data - multi-class scheduler.
 *
 * bfq_sched_data is the basic scheduler queue.  It supports three
 * ioprio_classes, and can be used either as a toplevel queue or as an
 * intermediate queue on a hierarchical setup.  @next_in_service
 * points to the active entity of the sched_data service trees that
 * will be scheduled next. It is used to reduce the number of steps
 * needed for each hierarchical-schedule update.
 *
 * The supported ioprio_classes are the same as in CFQ, in descending
 * priority order, IOPRIO_CLASS_RT, IOPRIO_CLASS_BE, IOPRIO_CLASS_IDLE.
 * Requests from higher priority queues are served before all the
 * requests from lower priority queues; among requests of the same
 * queue requests are served according to B-WF2Q+.
 * All the fields are protected by the queue lock of the containing bfqd.
 */
struct bfq_sched_data {
	/* entity in service */
	struct bfq_entity *in_service_entity;
	/* head-of-line entity (see comments above) */
	struct bfq_entity *next_in_service;
	/* array of service trees, one per ioprio_class */
	struct bfq_service_tree service_tree[BFQ_IOPRIO_CLASSES];
	/* last time CLASS_IDLE was served */
	unsigned long bfq_class_idle_last_service;

};

/**
 * struct bfq_weight_counter - counter of the number of all active entities
 *                             with a given weight.
 */
struct bfq_weight_counter {
	unsigned int weight; /* weight of the entities this counter refers to */
	unsigned int num_active; /* nr of active entities with this weight */
	/*
	 * Weights tree member (see bfq_data's @queue_weights_tree and
	 * @group_weights_tree)
	 */
	struct rb_node weights_node;
};

/**
 * struct bfq_entity - schedulable entity.
 *
 * A bfq_entity is used to represent either a bfq_queue (leaf node in the
 * cgroup hierarchy) or a bfq_group into the upper level scheduler.  Each
 * entity belongs to the sched_data of the parent group in the cgroup
 * hierarchy.  Non-leaf entities have also their own sched_data, stored
 * in @my_sched_data.
 *
 * Each entity stores independently its priority values; this would
 * allow different weights on different devices, but this
 * functionality is not exported to userspace by now.  Priorities and
 * weights are updated lazily, first storing the new values into the
 * new_* fields, then setting the @prio_changed flag.  As soon as
 * there is a transition in the entity state that allows the priority
 * update to take place the effective and the requested priority
 * values are synchronized.
 *
 * Unless cgroups are used, the weight value is calculated from the
 * ioprio to export the same interface as CFQ.  When dealing with
 * ``well-behaved'' queues (i.e., queues that do not spend too much
 * time to consume their budget and have true sequential behavior, and
 * when there are no external factors breaking anticipation) the
 * relative weights at each level of the cgroups hierarchy should be
 * guaranteed.  All the fields are protected by the queue lock of the
 * containing bfqd.
 */
struct bfq_entity {
	/* service_tree member */
	struct rb_node rb_node;
	/* pointer to the weight counter associated with this entity */
	struct bfq_weight_counter *weight_counter;

	/*
	 * Flag, true if the entity is on a tree (either the active or
	 * the idle one of its service_tree) or is in service.
	 */
	bool on_st;

	/* B-WF2Q+ start and finish timestamps [sectors/weight] */
	u64 start, finish;

	/* tree the entity is enqueued into; %NULL if not on a tree */
	struct rb_root *tree;

	/*
	 * minimum start time of the (active) subtree rooted at this
	 * entity; used for O(log N) lookups into active trees
	 */
	u64 min_start;

	/* amount of service received during the last service slot */
	int service;

	/* budget, used also to calculate F_i: F_i = S_i + @budget / @weight */
	int budget;

	/* weight of the queue */
	int weight;
	/* next weight if a change is in progress */
	int new_weight;

	/* original weight, used to implement weight boosting */
	int orig_weight;

	/* parent entity, for hierarchical scheduling */
	struct bfq_entity *parent;

	/*
	 * For non-leaf nodes in the hierarchy, the associated
	 * scheduler queue, %NULL on leaf nodes.
	 */
	struct bfq_sched_data *my_sched_data;
	/* the scheduler queue this entity belongs to */
	struct bfq_sched_data *sched_data;

	/* flag, set to request a weight, ioprio or ioprio_class change  */
	int prio_changed;
};

struct bfq_group;

/**
 * struct bfq_ttime - per process thinktime stats.
 */
struct bfq_ttime {
	/* completion time of the last request */
	u64 last_end_request;

	/* total process thinktime */
	u64 ttime_total;
	/* number of thinktime samples */
	unsigned long ttime_samples;
	/* average process thinktime */
	u64 ttime_mean;
};

/**
 * struct bfq_queue - leaf schedulable entity.
 *
 * A bfq_queue is a leaf request queue; it can be associated with an
 * io_context or more, if it  is  async or shared  between  cooperating
 * processes. @cgroup holds a reference to the cgroup, to be sure that it
 * does not disappear while a bfqq still references it (mostly to avoid
 * races between request issuing and task migration followed by cgroup
 * destruction).
 * All the fields are protected by the queue lock of the containing bfqd.
 */
struct bfq_queue {
	/* reference counter */
	int ref;
	/* parent bfq_data */
	struct bfq_data *bfqd;

	/* current ioprio and ioprio class */
	unsigned short ioprio, ioprio_class;
	/* next ioprio and ioprio class if a change is in progress */
	unsigned short new_ioprio, new_ioprio_class;

	/*
	 * Shared bfq_queue if queue is cooperating with one or more
	 * other queues.
	 */
	struct bfq_queue *new_bfqq;
	/* request-position tree member (see bfq_group's @rq_pos_tree) */
	struct rb_node pos_node;
	/* request-position tree root (see bfq_group's @rq_pos_tree) */
	struct rb_root *pos_root;

	/* sorted list of pending requests */
	struct rb_root sort_list;
	/* if fifo isn't expired, next request to serve */
	struct request *next_rq;
	/* number of sync and async requests queued */
	int queued[2];
	/* number of requests currently allocated */
	int allocated;
	/* number of pending metadata requests */
	int meta_pending;
	/* fifo list of requests in sort_list */
	struct list_head fifo;

	/* entity representing this queue in the scheduler */
	struct bfq_entity entity;

	/* maximum budget allowed from the feedback mechanism */
	int max_budget;
	/* budget expiration (in jiffies) */
	unsigned long budget_timeout;

	/* number of requests on the dispatch list or inside driver */
	int dispatched;

	/* status flags */
	unsigned long flags;

	/* node for active/idle bfqq list inside parent bfqd */
	struct list_head bfqq_list;

	/* associated @bfq_ttime struct */
	struct bfq_ttime ttime;

	/* bit vector: a 1 for each seeky requests in history */
	u32 seek_history;

	/* node for the device's burst list */
	struct hlist_node burst_list_node;

	/* position of the last request enqueued */
	sector_t last_request_pos;

	/* Number of consecutive pairs of request completion and
	 * arrival, such that the queue becomes idle after the
	 * completion, but the next request arrives within an idle
	 * time slice; used only if the queue's IO_bound flag has been
	 * cleared.
	 */
	unsigned int requests_within_timer;

	/* pid of the process owning the queue, used for logging purposes */
	pid_t pid;

	/*
	 * Pointer to the bfq_io_cq owning the bfq_queue, set to %NULL
	 * if the queue is shared.
	 */
	struct bfq_io_cq *bic;

	/* current maximum weight-raising time for this queue */
	unsigned long wr_cur_max_time;
	/*
	 * Minimum time instant such that, only if a new request is
	 * enqueued after this time instant in an idle @bfq_queue with
	 * no outstanding requests, then the task associated with the
	 * queue it is deemed as soft real-time (see the comments on
	 * the function bfq_bfqq_softrt_next_start())
	 */
	unsigned long soft_rt_next_start;
	/*
	 * Start time of the current weight-raising period if
	 * the @bfq-queue is being weight-raised, otherwise
	 * finish time of the last weight-raising period.
	 */
	unsigned long last_wr_start_finish;
	/* factor by which the weight of this queue is multiplied */
	unsigned int wr_coeff;
	/*
	 * Time of the last transition of the @bfq_queue from idle to
	 * backlogged.
	 */
	unsigned long last_idle_bklogged;
	/*
	 * Cumulative service received from the @bfq_queue since the
	 * last transition from idle to backlogged.
	 */
	unsigned long service_from_backlogged;

	/*
	 * Value of wr start time when switching to soft rt
	 */
	unsigned long wr_start_at_switch_to_srt;

	unsigned long split_time; /* time of last split */
};

/**
 * struct bfq_io_cq - per (request_queue, io_context) structure.
 */
struct bfq_io_cq {
	/* associated io_cq structure */
	struct io_cq icq; /* must be the first member */
	/* array of two process queues, the sync and the async */
	struct bfq_queue *bfqq[2];
	/* per (request_queue, blkcg) ioprio */
	int ioprio;
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	uint64_t blkcg_serial_nr; /* the current blkcg serial */
#endif
	/*
	 * Snapshot of the idle window before merging; taken to
	 * remember this value while the queue is merged, so as to be
	 * able to restore it in case of split.
	 */
	bool saved_idle_window;
	/*
	 * Same purpose as the previous two fields for the I/O bound
	 * classification of a queue.
	 */
	bool saved_IO_bound;

	/*
	 * Same purpose as the previous fields for the value of the
	 * field keeping the queue's belonging to a large burst
	 */
	bool saved_in_large_burst;
	/*
	 * True if the queue belonged to a burst list before its merge
	 * with another cooperating queue.
	 */
	bool was_in_burst_list;

	/*
	 * Similar to previous fields: save wr information.
	 */
	unsigned long saved_wr_coeff;
	unsigned long saved_last_wr_start_finish;
	unsigned long saved_wr_start_at_switch_to_srt;
	unsigned int saved_wr_cur_max_time;
	struct bfq_ttime saved_ttime;
};

enum bfq_device_speed {
	BFQ_BFQD_FAST,
	BFQ_BFQD_SLOW,
};

/**
 * struct bfq_data - per-device data structure.
 *
 * All the fields are protected by @lock.
 */
struct bfq_data {
	/* device request queue */
	struct request_queue *queue;
	/* dispatch queue */
	struct list_head dispatch;

	/* root bfq_group for the device */
	struct bfq_group *root_group;

	/*
	 * rbtree of weight counters of @bfq_queues, sorted by
	 * weight. Used to keep track of whether all @bfq_queues have
	 * the same weight. The tree contains one counter for each
	 * distinct weight associated to some active and not
	 * weight-raised @bfq_queue (see the comments to the functions
	 * bfq_weights_tree_[add|remove] for further details).
	 */
	struct rb_root queue_weights_tree;
	/*
	 * rbtree of non-queue @bfq_entity weight counters, sorted by
	 * weight. Used to keep track of whether all @bfq_groups have
	 * the same weight. The tree contains one counter for each
	 * distinct weight associated to some active @bfq_group (see
	 * the comments to the functions bfq_weights_tree_[add|remove]
	 * for further details).
	 */
	struct rb_root group_weights_tree;

	/*
	 * Number of bfq_queues containing requests (including the
	 * queue in service, even if it is idling).
	 */
	int busy_queues;
	/* number of weight-raised busy @bfq_queues */
	int wr_busy_queues;
	/* number of queued requests */
	int queued;
	/* number of requests dispatched and waiting for completion */
	int rq_in_driver;

	/*
	 * Maximum number of requests in driver in the last
	 * @hw_tag_samples completed requests.
	 */
	int max_rq_in_driver;
	/* number of samples used to calculate hw_tag */
	int hw_tag_samples;
	/* flag set to one if the driver is showing a queueing behavior */
	int hw_tag;

	/* number of budgets assigned */
	int budgets_assigned;

	/*
	 * Timer set when idling (waiting) for the next request from
	 * the queue in service.
	 */
	struct hrtimer idle_slice_timer;

	/* bfq_queue in service */
	struct bfq_queue *in_service_queue;

	/* on-disk position of the last served request */
	sector_t last_position;

	/* time of last request completion (ns) */
	u64 last_completion;

	/* time of first rq dispatch in current observation interval (ns) */
	u64 first_dispatch;
	/* time of last rq dispatch in current observation interval (ns) */
	u64 last_dispatch;

	/* beginning of the last budget */
	ktime_t last_budget_start;
	/* beginning of the last idle slice */
	ktime_t last_idling_start;

	/* number of samples in current observation interval */
	int peak_rate_samples;
	/* num of samples of seq dispatches in current observation interval */
	u32 sequential_samples;
	/* total num of sectors transferred in current observation interval */
	u64 tot_sectors_dispatched;
	/* max rq size seen during current observation interval (sectors) */
	u32 last_rq_max_size;
	/* time elapsed from first dispatch in current observ. interval (us) */
	u64 delta_from_first;
	/*
	 * Current estimate of the device peak rate, measured in
	 * [BFQ_RATE_SHIFT * sectors/usec]. The left-shift by
	 * BFQ_RATE_SHIFT is performed to increase precision in
	 * fixed-point calculations.
	 */
	u32 peak_rate;

	/* maximum budget allotted to a bfq_queue before rescheduling */
	int bfq_max_budget;

	/* list of all the bfq_queues active on the device */
	struct list_head active_list;
	/* list of all the bfq_queues idle on the device */
	struct list_head idle_list;

	/*
	 * Timeout for async/sync requests; when it fires, requests
	 * are served in fifo order.
	 */
	u64 bfq_fifo_expire[2];
	/* weight of backward seeks wrt forward ones */
	unsigned int bfq_back_penalty;
	/* maximum allowed backward seek */
	unsigned int bfq_back_max;
	/* maximum idling time */
	u32 bfq_slice_idle;

	/* user-configured max budget value (0 for auto-tuning) */
	int bfq_user_max_budget;
	/*
	 * Timeout for bfq_queues to consume their budget; used to
	 * prevent seeky queues from imposing long latencies to
	 * sequential or quasi-sequential ones (this also implies that
	 * seeky queues cannot receive guarantees in the service
	 * domain; after a timeout they are charged for the time they
	 * have been in service, to preserve fairness among them, but
	 * without service-domain guarantees).
	 */
	unsigned int bfq_timeout;

	/*
	 * Number of consecutive requests that must be issued within
	 * the idle time slice to set again idling to a queue which
	 * was marked as non-I/O-bound (see the definition of the
	 * IO_bound flag for further details).
	 */
	unsigned int bfq_requests_within_timer;

	/*
	 * Force device idling whenever needed to provide accurate
	 * service guarantees, without caring about throughput
	 * issues. CAVEAT: this may even increase latencies, in case
	 * of useless idling for processes that did stop doing I/O.
	 */
	bool strict_guarantees;

	/*
	 * Last time at which a queue entered the current burst of
	 * queues being activated shortly after each other; for more
	 * details about this and the following parameters related to
	 * a burst of activations, see the comments on the function
	 * bfq_handle_burst.
	 */
	unsigned long last_ins_in_burst;
	/*
	 * Reference time interval used to decide whether a queue has
	 * been activated shortly after @last_ins_in_burst.
	 */
	unsigned long bfq_burst_interval;
	/* number of queues in the current burst of queue activations */
	int burst_size;

	/* common parent entity for the queues in the burst */
	struct bfq_entity *burst_parent_entity;
	/* Maximum burst size above which the current queue-activation
	 * burst is deemed as 'large'.
	 */
	unsigned long bfq_large_burst_thresh;
	/* true if a large queue-activation burst is in progress */
	bool large_burst;
	/*
	 * Head of the burst list (as for the above fields, more
	 * details in the comments on the function bfq_handle_burst).
	 */
	struct hlist_head burst_list;

	/* if set to true, low-latency heuristics are enabled */
	bool low_latency;
	/*
	 * Maximum factor by which the weight of a weight-raised queue
	 * is multiplied.
	 */
	unsigned int bfq_wr_coeff;
	/* maximum duration of a weight-raising period (jiffies) */
	unsigned int bfq_wr_max_time;

	/* Maximum weight-raising duration for soft real-time processes */
	unsigned int bfq_wr_rt_max_time;
	/*
	 * Minimum idle period after which weight-raising may be
	 * reactivated for a queue (in jiffies).
	 */
	unsigned int bfq_wr_min_idle_time;
	/*
	 * Minimum period between request arrivals after which
	 * weight-raising may be reactivated for an already busy async
	 * queue (in jiffies).
	 */
	unsigned long bfq_wr_min_inter_arr_async;

	/* Max service-rate for a soft real-time queue, in sectors/sec */
	unsigned int bfq_wr_max_softrt_rate;
	/*
	 * Cached value of the product R*T, used for computing the
	 * maximum duration of weight raising automatically.
	 */
	u64 RT_prod;
	/* device-speed class for the low-latency heuristic */
	enum bfq_device_speed device_speed;

	/* fallback dummy bfqq for extreme OOM conditions */
	struct bfq_queue oom_bfqq;

	spinlock_t lock;

	/*
	 * bic associated with the task issuing current bio for
	 * merging. This and the next field are used as a support to
	 * be able to perform the bic lookup, needed by bio-merge
	 * functions, before the scheduler lock is taken, and thus
	 * avoid taking the request-queue lock while the scheduler
	 * lock is being held.
	 */
	struct bfq_io_cq *bio_bic;
	/* bfqq associated with the task issuing current bio for merging */
	struct bfq_queue *bio_bfqq;
};

enum bfqq_state_flags {
	BFQQF_just_created = 0,	/* queue just allocated */
	BFQQF_busy,		/* has requests or is in service */
	BFQQF_wait_request,	/* waiting for a request */
	BFQQF_non_blocking_wait_rq, /*
				     * waiting for a request
				     * without idling the device
				     */
	BFQQF_fifo_expire,	/* FIFO checked in this slice */
	BFQQF_idle_window,	/* slice idling enabled */
	BFQQF_sync,		/* synchronous queue */
	BFQQF_IO_bound,		/*
				 * bfqq has timed-out at least once
				 * having consumed at most 2/10 of
				 * its budget
				 */
	BFQQF_in_large_burst,	/*
				 * bfqq activated in a large burst,
				 * see comments to bfq_handle_burst.
				 */
	BFQQF_softrt_update,	/*
				 * may need softrt-next-start
				 * update
				 */
	BFQQF_coop,		/* bfqq is shared */
	BFQQF_split_coop	/* shared bfqq will be split */
};

#define BFQ_BFQQ_FNS(name)						\
void bfq_mark_bfqq_##name(struct bfq_queue *bfqq);			\
void bfq_clear_bfqq_##name(struct bfq_queue *bfqq);			\
int bfq_bfqq_##name(const struct bfq_queue *bfqq);

BFQ_BFQQ_FNS(just_created);
BFQ_BFQQ_FNS(busy);
BFQ_BFQQ_FNS(wait_request);
BFQ_BFQQ_FNS(non_blocking_wait_rq);
BFQ_BFQQ_FNS(fifo_expire);
BFQ_BFQQ_FNS(idle_window);
BFQ_BFQQ_FNS(sync);
BFQ_BFQQ_FNS(IO_bound);
BFQ_BFQQ_FNS(in_large_burst);
BFQ_BFQQ_FNS(coop);
BFQ_BFQQ_FNS(split_coop);
BFQ_BFQQ_FNS(softrt_update);
#undef BFQ_BFQQ_FNS

/* Expiration reasons. */
enum bfqq_expiration {
	BFQQE_TOO_IDLE = 0,		/*
					 * queue has been idling for
					 * too long
					 */
	BFQQE_BUDGET_TIMEOUT,	/* budget took too long to be used */
	BFQQE_BUDGET_EXHAUSTED,	/* budget consumed */
	BFQQE_NO_MORE_REQUESTS,	/* the queue has no more requests */
	BFQQE_PREEMPTED		/* preemption in progress */
};

struct bfqg_stats {
#ifdef CONFIG_BFQ_GROUP_IOSCHED
	/* number of ios merged */
	struct blkg_rwstat		merged;
	/* total time spent on device in ns, may not be accurate w/ queueing */
	struct blkg_rwstat		service_time;
	/* total time spent waiting in scheduler queue in ns */
	struct blkg_rwstat		wait_time;
	/* number of IOs queued up */
	struct blkg_rwstat		queued;
	/* total disk time and nr sectors dispatched by this group */
	struct blkg_stat		time;
	/* sum of number of ios queued across all samples */
	struct blkg_stat		avg_queue_size_sum;
	/* count of samples taken for average */
	struct blkg_stat		avg_queue_size_samples;
	/* how many times this group has been removed from service tree */
	struct blkg_stat		dequeue;
	/* total time spent waiting for it to be assigned a timeslice. */
	struct blkg_stat		group_wait_time;
	/* time spent idling for this blkcg_gq */
	struct blkg_stat		idle_time;
	/* total time with empty current active q with other requests queued */
	struct blkg_stat		empty_time;
	/* fields after this shouldn't be cleared on stat reset */
	uint64_t			start_group_wait_time;
	uint64_t			start_idle_time;
	uint64_t			start_empty_time;
	uint16_t			flags;
#endif	/* CONFIG_BFQ_GROUP_IOSCHED */
};

#ifdef CONFIG_BFQ_GROUP_IOSCHED

/*
 * struct bfq_group_data - per-blkcg storage for the blkio subsystem.
 *
 * @ps: @blkcg_policy_storage that this structure inherits
 * @weight: weight of the bfq_group
 */
struct bfq_group_data {
	/* must be the first member */
	struct blkcg_policy_data pd;

	unsigned int weight;
};

/**
 * struct bfq_group - per (device, cgroup) data structure.
 * @entity: schedulable entity to insert into the parent group sched_data.
 * @sched_data: own sched_data, to contain child entities (they may be
 *              both bfq_queues and bfq_groups).
 * @bfqd: the bfq_data for the device this group acts upon.
 * @async_bfqq: array of async queues for all the tasks belonging to
 *              the group, one queue per ioprio value per ioprio_class,
 *              except for the idle class that has only one queue.
 * @async_idle_bfqq: async queue for the idle class (ioprio is ignored).
 * @my_entity: pointer to @entity, %NULL for the toplevel group; used
 *             to avoid too many special cases during group creation/
 *             migration.
 * @stats: stats for this bfqg.
 * @active_entities: number of active entities belonging to the group;
 *                   unused for the root group. Used to know whether there
 *                   are groups with more than one active @bfq_entity
 *                   (see the comments to the function
 *                   bfq_bfqq_may_idle()).
 * @rq_pos_tree: rbtree sorted by next_request position, used when
 *               determining if two or more queues have interleaving
 *               requests (see bfq_find_close_cooperator()).
 *
 * Each (device, cgroup) pair has its own bfq_group, i.e., for each cgroup
 * there is a set of bfq_groups, each one collecting the lower-level
 * entities belonging to the group that are acting on the same device.
 *
 * Locking works as follows:
 *    o @bfqd is protected by the queue lock, RCU is used to access it
 *      from the readers.
 *    o All the other fields are protected by the @bfqd queue lock.
 */
struct bfq_group {
	/* must be the first member */
	struct blkg_policy_data pd;

	struct bfq_entity entity;
	struct bfq_sched_data sched_data;

	void *bfqd;

	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
	struct bfq_queue *async_idle_bfqq;

	struct bfq_entity *my_entity;

	int active_entities;

	struct rb_root rq_pos_tree;

	struct bfqg_stats stats;
};

#else
struct bfq_group {
	struct bfq_sched_data sched_data;

	struct bfq_queue *async_bfqq[2][IOPRIO_BE_NR];
	struct bfq_queue *async_idle_bfqq;

	struct rb_root rq_pos_tree;
};
#endif

struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);

/* --------------- main algorithm interface ----------------- */

#define BFQ_SERVICE_TREE_INIT	((struct bfq_service_tree)		\
				{ RB_ROOT, RB_ROOT, NULL, NULL, 0, 0 })

extern const int bfq_timeout;

struct bfq_queue *bic_to_bfqq(struct bfq_io_cq *bic, bool is_sync);
void bic_set_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq, bool is_sync);
struct bfq_data *bic_to_bfqd(struct bfq_io_cq *bic);
void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_pos_tree_add_move(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_weights_tree_add(struct bfq_data *bfqd, struct bfq_entity *entity,
			  struct rb_root *root);
void bfq_weights_tree_remove(struct bfq_data *bfqd, struct bfq_entity *entity,
			     struct rb_root *root);
void bfq_bfqq_expire(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		     bool compensate, enum bfqq_expiration reason);
void bfq_put_queue(struct bfq_queue *bfqq);
void bfq_end_wr_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);
void bfq_schedule_dispatch(struct bfq_data *bfqd);
void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg);

/* ------------ end of main algorithm interface -------------- */

/* ---------------- cgroups-support interface ---------------- */

extern struct cftype bfq_blkcg_legacy_files[];
extern struct cftype bfq_blkg_files[];

void bfqg_stats_update_io_add(struct bfq_group *bfqg, struct bfq_queue *bfqq,
			      unsigned int op);
void bfqg_stats_update_io_remove(struct bfq_group *bfqg, unsigned int op);
void bfqg_stats_update_io_merged(struct bfq_group *bfqg, unsigned int op);
void bfqg_stats_update_completion(struct bfq_group *bfqg, uint64_t start_time,
				  uint64_t io_start_time, unsigned int op);
void bfqg_stats_update_dequeue(struct bfq_group *bfqg);
void bfqg_stats_set_start_empty_time(struct bfq_group *bfqg);
void bfqg_stats_update_idle_time(struct bfq_group *bfqg);
void bfqg_stats_set_start_idle_time(struct bfq_group *bfqg);
void bfqg_stats_update_avg_queue_size(struct bfq_group *bfqg);
void bfq_bfqq_move(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		   struct bfq_group *bfqg);

void bfq_init_entity(struct bfq_entity *entity, struct bfq_group *bfqg);
void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio);
void bfq_end_wr_async(struct bfq_data *bfqd);
struct bfq_group *bfq_find_set_group(struct bfq_data *bfqd,
				     struct blkcg *blkcg);
struct blkcg_gq *bfqg_to_blkg(struct bfq_group *bfqg);
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);
struct bfq_group *bfq_create_group_hierarchy(struct bfq_data *bfqd, int node);
void bfqg_put(struct bfq_group *bfqg);

#ifdef CONFIG_BFQ_GROUP_IOSCHED
extern struct blkcg_policy blkcg_policy_bfq;
#endif

/* ------------- end of cgroups-support interface ------------- */

/* - interface of the internal hierarchical B-WF2Q+ scheduler - */

#ifdef CONFIG_BFQ_GROUP_IOSCHED
/* both next loops stop at one of the child entities of the root group */
#define for_each_entity(entity)	\
	for (; entity ; entity = entity->parent)

/*
 * For each iteration, compute parent in advance, so as to be safe if
 * entity is deallocated during the iteration. Such a deallocation may
 * happen as a consequence of a bfq_put_queue that frees the bfq_queue
 * containing entity.
 */
#define for_each_entity_safe(entity, parent) \
	for (; entity && ({ parent = entity->parent; 1; }); entity = parent)

#else /* CONFIG_BFQ_GROUP_IOSCHED */
/*
 * Next two macros are fake loops when cgroups support is not
 * enabled. I fact, in such a case, there is only one level to go up
 * (to reach the root group).
 */
#define for_each_entity(entity)	\
	for (; entity ; entity = NULL)

#define for_each_entity_safe(entity, parent) \
	for (parent = NULL; entity ; entity = parent)
#endif /* CONFIG_BFQ_GROUP_IOSCHED */

struct bfq_group *bfq_bfqq_to_bfqg(struct bfq_queue *bfqq);
struct bfq_queue *bfq_entity_to_bfqq(struct bfq_entity *entity);
struct bfq_service_tree *bfq_entity_service_tree(struct bfq_entity *entity);
struct bfq_entity *bfq_entity_of(struct rb_node *node);
unsigned short bfq_ioprio_to_weight(int ioprio);
void bfq_put_idle_entity(struct bfq_service_tree *st,
			 struct bfq_entity *entity);
struct bfq_service_tree *
__bfq_entity_update_weight_prio(struct bfq_service_tree *old_st,
				struct bfq_entity *entity);
void bfq_bfqq_served(struct bfq_queue *bfqq, int served);
void bfq_bfqq_charge_time(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			  unsigned long time_ms);
bool __bfq_deactivate_entity(struct bfq_entity *entity,
			     bool ins_into_idle_tree);
bool next_queue_may_preempt(struct bfq_data *bfqd);
struct bfq_queue *bfq_get_next_queue(struct bfq_data *bfqd);
void __bfq_bfqd_reset_in_service(struct bfq_data *bfqd);
void bfq_deactivate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq,
			 bool ins_into_idle_tree, bool expiration);
void bfq_activate_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_requeue_bfqq(struct bfq_data *bfqd, struct bfq_queue *bfqq);
void bfq_del_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq,
		       bool expiration);
void bfq_add_bfqq_busy(struct bfq_data *bfqd, struct bfq_queue *bfqq);

/* --------------- end of interface of B-WF2Q+ ---------------- */

/* Logging facilities. */
#ifdef CONFIG_BFQ_GROUP_IOSCHED
struct bfq_group *bfqq_group(struct bfq_queue *bfqq);

#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	do {			\
	char __pbuf[128];						\
									\
	blkg_path(bfqg_to_blkg(bfqq_group(bfqq)), __pbuf, sizeof(__pbuf)); \
	blk_add_trace_msg((bfqd)->queue, "bfq%d%c %s " fmt, (bfqq)->pid, \
			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
			  __pbuf, ##args);				\
} while (0)

#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)	do {			\
	char __pbuf[128];						\
									\
	blkg_path(bfqg_to_blkg(bfqg), __pbuf, sizeof(__pbuf));		\
	blk_add_trace_msg((bfqd)->queue, "%s " fmt, __pbuf, ##args);	\
} while (0)

#else /* CONFIG_BFQ_GROUP_IOSCHED */

#define bfq_log_bfqq(bfqd, bfqq, fmt, args...)	\
	blk_add_trace_msg((bfqd)->queue, "bfq%d%c " fmt, (bfqq)->pid,	\
			bfq_bfqq_sync((bfqq)) ? 'S' : 'A',		\
				##args)
#define bfq_log_bfqg(bfqd, bfqg, fmt, args...)		do {} while (0)

#endif /* CONFIG_BFQ_GROUP_IOSCHED */

#define bfq_log(bfqd, fmt, args...) \
	blk_add_trace_msg((bfqd)->queue, "bfq " fmt, ##args)

#endif /* _BFQ_H */