summaryrefslogtreecommitdiffstats
path: root/block/mq-deadline-main.c
blob: 294be0c0db65d6a34547bffb3edd810faa50da41 (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
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
// SPDX-License-Identifier: GPL-2.0
/*
 *  MQ Deadline i/o scheduler - adaptation of the legacy deadline scheduler,
 *  for the blk-mq scheduling framework
 *
 *  Copyright (C) 2016 Jens Axboe <axboe@kernel.dk>
 */
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/blkdev.h>
#include <linux/blk-mq.h>
#include <linux/elevator.h>
#include <linux/bio.h>
#include <linux/module.h>
#include <linux/slab.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/rbtree.h>
#include <linux/sbitmap.h>

#include <trace/events/block.h>

#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-tag.h"
#include "blk-mq-sched.h"
#include "mq-deadline-cgroup.h"

/*
 * See Documentation/block/deadline-iosched.rst
 */
static const int read_expire = HZ / 2;  /* max time before a read is submitted. */
static const int write_expire = 5 * HZ; /* ditto for writes, these limits are SOFT! */
/*
 * Time after which to dispatch lower priority requests even if higher
 * priority requests are pending.
 */
static const int aging_expire = 10 * HZ;
static const int writes_starved = 2;    /* max times reads can starve a write */
static const int fifo_batch = 16;       /* # of sequential requests treated as one
				     by the above parameters. For throughput. */

enum dd_data_dir {
	DD_READ		= READ,
	DD_WRITE	= WRITE,
};

enum { DD_DIR_COUNT = 2 };

enum dd_prio {
	DD_RT_PRIO	= 0,
	DD_BE_PRIO	= 1,
	DD_IDLE_PRIO	= 2,
	DD_PRIO_MAX	= 2,
};

enum { DD_PRIO_COUNT = 3 };

/* I/O statistics for all I/O priorities (enum dd_prio). */
struct io_stats {
	struct io_stats_per_prio stats[DD_PRIO_COUNT];
};

/*
 * Deadline scheduler data per I/O priority (enum dd_prio). Requests are
 * present on both sort_list[] and fifo_list[].
 */
struct dd_per_prio {
	struct list_head dispatch;
	struct rb_root sort_list[DD_DIR_COUNT];
	struct list_head fifo_list[DD_DIR_COUNT];
	/* Next request in FIFO order. Read, write or both are NULL. */
	struct request *next_rq[DD_DIR_COUNT];
};

struct deadline_data {
	/*
	 * run time data
	 */

	/* Request queue that owns this data structure. */
	struct request_queue *queue;

	struct dd_per_prio per_prio[DD_PRIO_COUNT];

	/* Data direction of latest dispatched request. */
	enum dd_data_dir last_dir;
	unsigned int batching;		/* number of sequential requests made */
	unsigned int starved;		/* times reads have starved writes */

	struct io_stats __percpu *stats;

	/*
	 * settings that change how the i/o scheduler behaves
	 */
	int fifo_expire[DD_DIR_COUNT];
	int fifo_batch;
	int writes_starved;
	int front_merges;
	u32 async_depth;
	int aging_expire;

	spinlock_t lock;
	spinlock_t zone_lock;
};

/* Count one event of type 'event_type' and with I/O priority 'prio' */
#define dd_count(dd, event_type, prio) do {				\
	struct io_stats *io_stats = get_cpu_ptr((dd)->stats);		\
									\
	BUILD_BUG_ON(!__same_type((dd), struct deadline_data *));	\
	BUILD_BUG_ON(!__same_type((prio), enum dd_prio));		\
	local_inc(&io_stats->stats[(prio)].event_type);			\
	put_cpu_ptr(io_stats);						\
} while (0)

/*
 * Returns the total number of dd_count(dd, event_type, prio) calls across all
 * CPUs. No locking or barriers since it is fine if the returned sum is slightly
 * outdated.
 */
#define dd_sum(dd, event_type, prio) ({					\
	unsigned int cpu;						\
	u32 sum = 0;							\
									\
	BUILD_BUG_ON(!__same_type((dd), struct deadline_data *));	\
	BUILD_BUG_ON(!__same_type((prio), enum dd_prio));		\
	for_each_present_cpu(cpu)					\
		sum += local_read(&per_cpu_ptr((dd)->stats, cpu)->	\
				  stats[(prio)].event_type);		\
	sum;								\
})

/* Maps an I/O priority class to a deadline scheduler priority. */
static const enum dd_prio ioprio_class_to_prio[] = {
	[IOPRIO_CLASS_NONE]	= DD_BE_PRIO,
	[IOPRIO_CLASS_RT]	= DD_RT_PRIO,
	[IOPRIO_CLASS_BE]	= DD_BE_PRIO,
	[IOPRIO_CLASS_IDLE]	= DD_IDLE_PRIO,
};

static inline struct rb_root *
deadline_rb_root(struct dd_per_prio *per_prio, struct request *rq)
{
	return &per_prio->sort_list[rq_data_dir(rq)];
}

/*
 * Returns the I/O priority class (IOPRIO_CLASS_*) that has been assigned to a
 * request.
 */
static u8 dd_rq_ioclass(struct request *rq)
{
	return IOPRIO_PRIO_CLASS(req_get_ioprio(rq));
}

/*
 * get the request after `rq' in sector-sorted order
 */
static inline struct request *
deadline_latter_request(struct request *rq)
{
	struct rb_node *node = rb_next(&rq->rb_node);

	if (node)
		return rb_entry_rq(node);

	return NULL;
}

static void
deadline_add_rq_rb(struct dd_per_prio *per_prio, struct request *rq)
{
	struct rb_root *root = deadline_rb_root(per_prio, rq);

	elv_rb_add(root, rq);
}

static inline void
deadline_del_rq_rb(struct dd_per_prio *per_prio, struct request *rq)
{
	const enum dd_data_dir data_dir = rq_data_dir(rq);

	if (per_prio->next_rq[data_dir] == rq)
		per_prio->next_rq[data_dir] = deadline_latter_request(rq);

	elv_rb_del(deadline_rb_root(per_prio, rq), rq);
}

/*
 * remove rq from rbtree and fifo.
 */
static void deadline_remove_request(struct request_queue *q,
				    struct dd_per_prio *per_prio,
				    struct request *rq)
{
	list_del_init(&rq->queuelist);

	/*
	 * We might not be on the rbtree, if we are doing an insert merge
	 */
	if (!RB_EMPTY_NODE(&rq->rb_node))
		deadline_del_rq_rb(per_prio, rq);

	elv_rqhash_del(q, rq);
	if (q->last_merge == rq)
		q->last_merge = NULL;
}

static void dd_request_merged(struct request_queue *q, struct request *req,
			      enum elv_merge type)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	const u8 ioprio_class = dd_rq_ioclass(req);
	const enum dd_prio prio = ioprio_class_to_prio[ioprio_class];
	struct dd_per_prio *per_prio = &dd->per_prio[prio];

	/*
	 * if the merge was a front merge, we need to reposition request
	 */
	if (type == ELEVATOR_FRONT_MERGE) {
		elv_rb_del(deadline_rb_root(per_prio, req), req);
		deadline_add_rq_rb(per_prio, req);
	}
}

/*
 * Callback function that is invoked after @next has been merged into @req.
 */
static void dd_merged_requests(struct request_queue *q, struct request *req,
			       struct request *next)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	const u8 ioprio_class = dd_rq_ioclass(next);
	const enum dd_prio prio = ioprio_class_to_prio[ioprio_class];
	struct dd_blkcg *blkcg = next->elv.priv[0];

	dd_count(dd, merged, prio);
	ddcg_count(blkcg, merged, ioprio_class);

	/*
	 * if next expires before rq, assign its expire time to rq
	 * and move into next position (next will be deleted) in fifo
	 */
	if (!list_empty(&req->queuelist) && !list_empty(&next->queuelist)) {
		if (time_before((unsigned long)next->fifo_time,
				(unsigned long)req->fifo_time)) {
			list_move(&req->queuelist, &next->queuelist);
			req->fifo_time = next->fifo_time;
		}
	}

	/*
	 * kill knowledge of next, this one is a goner
	 */
	deadline_remove_request(q, &dd->per_prio[prio], next);
}

/*
 * move an entry to dispatch queue
 */
static void
deadline_move_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
		      struct request *rq)
{
	const enum dd_data_dir data_dir = rq_data_dir(rq);

	per_prio->next_rq[data_dir] = deadline_latter_request(rq);

	/*
	 * take it off the sort and fifo list
	 */
	deadline_remove_request(rq->q, per_prio, rq);
}

/* Number of requests queued for a given priority level. */
static u32 dd_queued(struct deadline_data *dd, enum dd_prio prio)
{
	return dd_sum(dd, inserted, prio) - dd_sum(dd, completed, prio);
}

/*
 * deadline_check_fifo returns 0 if there are no expired requests on the fifo,
 * 1 otherwise. Requires !list_empty(&dd->fifo_list[data_dir])
 */
static inline int deadline_check_fifo(struct dd_per_prio *per_prio,
				      enum dd_data_dir data_dir)
{
	struct request *rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next);

	/*
	 * rq is expired!
	 */
	if (time_after_eq(jiffies, (unsigned long)rq->fifo_time))
		return 1;

	return 0;
}

/*
 * For the specified data direction, return the next request to
 * dispatch using arrival ordered lists.
 */
static struct request *
deadline_fifo_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
		      enum dd_data_dir data_dir)
{
	struct request *rq;
	unsigned long flags;

	if (list_empty(&per_prio->fifo_list[data_dir]))
		return NULL;

	rq = rq_entry_fifo(per_prio->fifo_list[data_dir].next);
	if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q))
		return rq;

	/*
	 * Look for a write request that can be dispatched, that is one with
	 * an unlocked target zone.
	 */
	spin_lock_irqsave(&dd->zone_lock, flags);
	list_for_each_entry(rq, &per_prio->fifo_list[DD_WRITE], queuelist) {
		if (blk_req_can_dispatch_to_zone(rq))
			goto out;
	}
	rq = NULL;
out:
	spin_unlock_irqrestore(&dd->zone_lock, flags);

	return rq;
}

/*
 * For the specified data direction, return the next request to
 * dispatch using sector position sorted lists.
 */
static struct request *
deadline_next_request(struct deadline_data *dd, struct dd_per_prio *per_prio,
		      enum dd_data_dir data_dir)
{
	struct request *rq;
	unsigned long flags;

	rq = per_prio->next_rq[data_dir];
	if (!rq)
		return NULL;

	if (data_dir == DD_READ || !blk_queue_is_zoned(rq->q))
		return rq;

	/*
	 * Look for a write request that can be dispatched, that is one with
	 * an unlocked target zone.
	 */
	spin_lock_irqsave(&dd->zone_lock, flags);
	while (rq) {
		if (blk_req_can_dispatch_to_zone(rq))
			break;
		rq = deadline_latter_request(rq);
	}
	spin_unlock_irqrestore(&dd->zone_lock, flags);

	return rq;
}

/*
 * deadline_dispatch_requests selects the best request according to
 * read/write expire, fifo_batch, etc and with a start time <= @latest.
 */
static struct request *__dd_dispatch_request(struct deadline_data *dd,
					     struct dd_per_prio *per_prio,
					     u64 latest_start_ns)
{
	struct request *rq, *next_rq;
	enum dd_data_dir data_dir;
	struct dd_blkcg *blkcg;
	enum dd_prio prio;
	u8 ioprio_class;

	lockdep_assert_held(&dd->lock);

	if (!list_empty(&per_prio->dispatch)) {
		rq = list_first_entry(&per_prio->dispatch, struct request,
				      queuelist);
		if (rq->start_time_ns > latest_start_ns)
			return NULL;
		list_del_init(&rq->queuelist);
		goto done;
	}

	/*
	 * batches are currently reads XOR writes
	 */
	rq = deadline_next_request(dd, per_prio, dd->last_dir);
	if (rq && dd->batching < dd->fifo_batch)
		/* we have a next request are still entitled to batch */
		goto dispatch_request;

	/*
	 * at this point we are not running a batch. select the appropriate
	 * data direction (read / write)
	 */

	if (!list_empty(&per_prio->fifo_list[DD_READ])) {
		BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_READ]));

		if (deadline_fifo_request(dd, per_prio, DD_WRITE) &&
		    (dd->starved++ >= dd->writes_starved))
			goto dispatch_writes;

		data_dir = DD_READ;

		goto dispatch_find_request;
	}

	/*
	 * there are either no reads or writes have been starved
	 */

	if (!list_empty(&per_prio->fifo_list[DD_WRITE])) {
dispatch_writes:
		BUG_ON(RB_EMPTY_ROOT(&per_prio->sort_list[DD_WRITE]));

		dd->starved = 0;

		data_dir = DD_WRITE;

		goto dispatch_find_request;
	}

	return NULL;

dispatch_find_request:
	/*
	 * we are not running a batch, find best request for selected data_dir
	 */
	next_rq = deadline_next_request(dd, per_prio, data_dir);
	if (deadline_check_fifo(per_prio, data_dir) || !next_rq) {
		/*
		 * A deadline has expired, the last request was in the other
		 * direction, or we have run out of higher-sectored requests.
		 * Start again from the request with the earliest expiry time.
		 */
		rq = deadline_fifo_request(dd, per_prio, data_dir);
	} else {
		/*
		 * The last req was the same dir and we have a next request in
		 * sort order. No expired requests so continue on from here.
		 */
		rq = next_rq;
	}

	/*
	 * For a zoned block device, if we only have writes queued and none of
	 * them can be dispatched, rq will be NULL.
	 */
	if (!rq)
		return NULL;

	dd->last_dir = data_dir;
	dd->batching = 0;

dispatch_request:
	if (rq->start_time_ns > latest_start_ns)
		return NULL;
	/*
	 * rq is the selected appropriate request.
	 */
	dd->batching++;
	deadline_move_request(dd, per_prio, rq);
done:
	ioprio_class = dd_rq_ioclass(rq);
	prio = ioprio_class_to_prio[ioprio_class];
	dd_count(dd, dispatched, prio);
	blkcg = rq->elv.priv[0];
	ddcg_count(blkcg, dispatched, ioprio_class);
	/*
	 * If the request needs its target zone locked, do it.
	 */
	blk_req_zone_write_lock(rq);
	rq->rq_flags |= RQF_STARTED;
	return rq;
}

/*
 * Called from blk_mq_run_hw_queue() -> __blk_mq_sched_dispatch_requests().
 *
 * One confusing aspect here is that we get called for a specific
 * hardware queue, but we may return a request that is for a
 * different hardware queue. This is because mq-deadline has shared
 * state for all hardware queues, in terms of sorting, FIFOs, etc.
 */
static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
{
	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
	const u64 now_ns = ktime_get_ns();
	struct request *rq = NULL;
	enum dd_prio prio;

	spin_lock(&dd->lock);
	/*
	 * Start with dispatching requests whose deadline expired more than
	 * aging_expire jiffies ago.
	 */
	for (prio = DD_BE_PRIO; prio <= DD_PRIO_MAX; prio++) {
		rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns -
					   jiffies_to_nsecs(dd->aging_expire));
		if (rq)
			goto unlock;
	}
	/*
	 * Next, dispatch requests in priority order. Ignore lower priority
	 * requests if any higher priority requests are pending.
	 */
	for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
		rq = __dd_dispatch_request(dd, &dd->per_prio[prio], now_ns);
		if (rq || dd_queued(dd, prio))
			break;
	}

unlock:
	spin_unlock(&dd->lock);

	return rq;
}

/*
 * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
 * function is used by __blk_mq_get_tag().
 */
static void dd_limit_depth(unsigned int op, struct blk_mq_alloc_data *data)
{
	struct deadline_data *dd = data->q->elevator->elevator_data;

	/* Do not throttle synchronous reads. */
	if (op_is_sync(op) && !op_is_write(op))
		return;

	/*
	 * Throttle asynchronous requests and writes such that these requests
	 * do not block the allocation of synchronous requests.
	 */
	data->shallow_depth = dd->async_depth;
}

/* Called by blk_mq_update_nr_requests(). */
static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
{
	struct request_queue *q = hctx->queue;
	struct deadline_data *dd = q->elevator->elevator_data;
	struct blk_mq_tags *tags = hctx->sched_tags;

	dd->async_depth = max(1UL, 3 * q->nr_requests / 4);

	sbitmap_queue_min_shallow_depth(tags->bitmap_tags, dd->async_depth);
}

/* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */
static int dd_init_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_idx)
{
	dd_depth_updated(hctx);
	return 0;
}

static void dd_exit_sched(struct elevator_queue *e)
{
	struct deadline_data *dd = e->elevator_data;
	enum dd_prio prio;

	dd_deactivate_policy(dd->queue);

	for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
		struct dd_per_prio *per_prio = &dd->per_prio[prio];

		WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_READ]));
		WARN_ON_ONCE(!list_empty(&per_prio->fifo_list[DD_WRITE]));
	}

	free_percpu(dd->stats);

	kfree(dd);
}

/*
 * Initialize elevator private data (deadline_data) and associate with blkcg.
 */
static int dd_init_sched(struct request_queue *q, struct elevator_type *e)
{
	struct deadline_data *dd;
	struct elevator_queue *eq;
	enum dd_prio prio;
	int ret = -ENOMEM;

	/*
	 * Initialization would be very tricky if the queue is not frozen,
	 * hence the warning statement below.
	 */
	WARN_ON_ONCE(!percpu_ref_is_zero(&q->q_usage_counter));

	eq = elevator_alloc(q, e);
	if (!eq)
		return ret;

	dd = kzalloc_node(sizeof(*dd), GFP_KERNEL, q->node);
	if (!dd)
		goto put_eq;

	eq->elevator_data = dd;

	dd->stats = alloc_percpu_gfp(typeof(*dd->stats),
				     GFP_KERNEL | __GFP_ZERO);
	if (!dd->stats)
		goto free_dd;

	dd->queue = q;

	for (prio = 0; prio <= DD_PRIO_MAX; prio++) {
		struct dd_per_prio *per_prio = &dd->per_prio[prio];

		INIT_LIST_HEAD(&per_prio->dispatch);
		INIT_LIST_HEAD(&per_prio->fifo_list[DD_READ]);
		INIT_LIST_HEAD(&per_prio->fifo_list[DD_WRITE]);
		per_prio->sort_list[DD_READ] = RB_ROOT;
		per_prio->sort_list[DD_WRITE] = RB_ROOT;
	}
	dd->fifo_expire[DD_READ] = read_expire;
	dd->fifo_expire[DD_WRITE] = write_expire;
	dd->writes_starved = writes_starved;
	dd->front_merges = 1;
	dd->last_dir = DD_WRITE;
	dd->fifo_batch = fifo_batch;
	dd->aging_expire = aging_expire;
	spin_lock_init(&dd->lock);
	spin_lock_init(&dd->zone_lock);

	ret = dd_activate_policy(q);
	if (ret)
		goto free_stats;

	ret = 0;
	q->elevator = eq;
	return 0;

free_stats:
	free_percpu(dd->stats);

free_dd:
	kfree(dd);

put_eq:
	kobject_put(&eq->kobj);
	return ret;
}

/*
 * Try to merge @bio into an existing request. If @bio has been merged into
 * an existing request, store the pointer to that request into *@rq.
 */
static int dd_request_merge(struct request_queue *q, struct request **rq,
			    struct bio *bio)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	const u8 ioprio_class = IOPRIO_PRIO_CLASS(bio->bi_ioprio);
	const enum dd_prio prio = ioprio_class_to_prio[ioprio_class];
	struct dd_per_prio *per_prio = &dd->per_prio[prio];
	sector_t sector = bio_end_sector(bio);
	struct request *__rq;

	if (!dd->front_merges)
		return ELEVATOR_NO_MERGE;

	__rq = elv_rb_find(&per_prio->sort_list[bio_data_dir(bio)], sector);
	if (__rq) {
		BUG_ON(sector != blk_rq_pos(__rq));

		if (elv_bio_merge_ok(__rq, bio)) {
			*rq = __rq;
			if (blk_discard_mergable(__rq))
				return ELEVATOR_DISCARD_MERGE;
			return ELEVATOR_FRONT_MERGE;
		}
	}

	return ELEVATOR_NO_MERGE;
}

/*
 * Attempt to merge a bio into an existing request. This function is called
 * before @bio is associated with a request.
 */
static bool dd_bio_merge(struct request_queue *q, struct bio *bio,
		unsigned int nr_segs)
{
	struct deadline_data *dd = q->elevator->elevator_data;
	struct request *free = NULL;
	bool ret;

	spin_lock(&dd->lock);
	ret = blk_mq_sched_try_merge(q, bio, nr_segs, &free);
	spin_unlock(&dd->lock);

	if (free)
		blk_mq_free_request(free);

	return ret;
}

/*
 * add rq to rbtree and fifo
 */
static void dd_insert_request(struct blk_mq_hw_ctx *hctx, struct request *rq,
			      bool at_head)
{
	struct request_queue *q = hctx->queue;
	struct deadline_data *dd = q->elevator->elevator_data;
	const enum dd_data_dir data_dir = rq_data_dir(rq);
	u16 ioprio = req_get_ioprio(rq);
	u8 ioprio_class = IOPRIO_PRIO_CLASS(ioprio);
	struct dd_per_prio *per_prio;
	enum dd_prio prio;
	struct dd_blkcg *blkcg;
	LIST_HEAD(free);

	lockdep_assert_held(&dd->lock);

	/*
	 * This may be a requeue of a write request that has locked its
	 * target zone. If it is the case, this releases the zone lock.
	 */
	blk_req_zone_write_unlock(rq);

	/*
	 * If a block cgroup has been associated with the submitter and if an
	 * I/O priority has been set in the associated block cgroup, use the
	 * lowest of the cgroup priority and the request priority for the
	 * request. If no priority has been set in the request, use the cgroup
	 * priority.
	 */
	prio = ioprio_class_to_prio[ioprio_class];
	dd_count(dd, inserted, prio);
	blkcg = dd_blkcg_from_bio(rq->bio);
	ddcg_count(blkcg, inserted, ioprio_class);
	rq->elv.priv[0] = blkcg;

	if (blk_mq_sched_try_insert_merge(q, rq, &free)) {
		blk_mq_free_requests(&free);
		return;
	}

	trace_block_rq_insert(rq);

	per_prio = &dd->per_prio[prio];
	if (at_head) {
		list_add(&rq->queuelist, &per_prio->dispatch);
	} else {
		deadline_add_rq_rb(per_prio, rq);

		if (rq_mergeable(rq)) {
			elv_rqhash_add(q, rq);
			if (!q->last_merge)
				q->last_merge = rq;
		}

		/*
		 * set expire time and add to fifo list
		 */
		rq->fifo_time = jiffies + dd->fifo_expire[data_dir];
		list_add_tail(&rq->queuelist, &per_prio->fifo_list[data_dir]);
	}
}

/*
 * Called from blk_mq_sched_insert_request() or blk_mq_sched_insert_requests().
 */
static void dd_insert_requests(struct blk_mq_hw_ctx *hctx,
			       struct list_head *list, bool at_head)
{
	struct request_queue *q = hctx->queue;
	struct deadline_data *dd = q->elevator->elevator_data;

	spin_lock(&dd->lock);
	while (!list_empty(list)) {
		struct request *rq;

		rq = list_first_entry(list, struct request, queuelist);
		list_del_init(&rq->queuelist);
		dd_insert_request(hctx, rq, at_head);
	}
	spin_unlock(&dd->lock);
}

/* Callback from inside blk_mq_rq_ctx_init(). */
static void dd_prepare_request(struct request *rq)
{
	rq->elv.priv[0] = NULL;
}

/*
 * Callback from inside blk_mq_free_request().
 *
 * For zoned block devices, write unlock the target zone of
 * completed write requests. Do this while holding the zone lock
 * spinlock so that the zone is never unlocked while deadline_fifo_request()
 * or deadline_next_request() are executing. This function is called for
 * all requests, whether or not these requests complete successfully.
 *
 * For a zoned block device, __dd_dispatch_request() may have stopped
 * dispatching requests if all the queued requests are write requests directed
 * at zones that are already locked due to on-going write requests. To ensure
 * write request dispatch progress in this case, mark the queue as needing a
 * restart to ensure that the queue is run again after completion of the
 * request and zones being unlocked.
 */
static void dd_finish_request(struct request *rq)
{
	struct request_queue *q = rq->q;
	struct deadline_data *dd = q->elevator->elevator_data;
	struct dd_blkcg *blkcg = rq->elv.priv[0];
	const u8 ioprio_class = dd_rq_ioclass(rq);
	const enum dd_prio prio = ioprio_class_to_prio[ioprio_class];
	struct dd_per_prio *per_prio = &dd->per_prio[prio];

	dd_count(dd, completed, prio);
	ddcg_count(blkcg, completed, ioprio_class);

	if (blk_queue_is_zoned(q)) {
		unsigned long flags;

		spin_lock_irqsave(&dd->zone_lock, flags);
		blk_req_zone_write_unlock(rq);
		if (!list_empty(&per_prio->fifo_list[DD_WRITE]))
			blk_mq_sched_mark_restart_hctx(rq->mq_hctx);
		spin_unlock_irqrestore(&dd->zone_lock, flags);
	}
}

static bool dd_has_work_for_prio(struct dd_per_prio *per_prio)
{
	return !list_empty_careful(&per_prio->dispatch) ||
		!list_empty_careful(&per_prio->fifo_list[DD_READ]) ||
		!list_empty_careful(&per_prio->fifo_list[DD_WRITE]);
}

static bool dd_has_work(struct blk_mq_hw_ctx *hctx)
{
	struct deadline_data *dd = hctx->queue->elevator->elevator_data;
	enum dd_prio prio;

	for (prio = 0; prio <= DD_PRIO_MAX; prio++)
		if (dd_has_work_for_prio(&dd->per_prio[prio]))
			return true;

	return false;
}

/*
 * sysfs parts below
 */
#define SHOW_INT(__FUNC, __VAR)						\
static ssize_t __FUNC(struct elevator_queue *e, char *page)		\
{									\
	struct deadline_data *dd = e->elevator_data;			\
									\
	return sysfs_emit(page, "%d\n", __VAR);				\
}
#define SHOW_JIFFIES(__FUNC, __VAR) SHOW_INT(__FUNC, jiffies_to_msecs(__VAR))
SHOW_JIFFIES(deadline_read_expire_show, dd->fifo_expire[DD_READ]);
SHOW_JIFFIES(deadline_write_expire_show, dd->fifo_expire[DD_WRITE]);
SHOW_JIFFIES(deadline_aging_expire_show, dd->aging_expire);
SHOW_INT(deadline_writes_starved_show, dd->writes_starved);
SHOW_INT(deadline_front_merges_show, dd->front_merges);
SHOW_INT(deadline_async_depth_show, dd->front_merges);
SHOW_INT(deadline_fifo_batch_show, dd->fifo_batch);
#undef SHOW_INT
#undef SHOW_JIFFIES

#define STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, __CONV)			\
static ssize_t __FUNC(struct elevator_queue *e, const char *page, size_t count)	\
{									\
	struct deadline_data *dd = e->elevator_data;			\
	int __data, __ret;						\
									\
	__ret = kstrtoint(page, 0, &__data);				\
	if (__ret < 0)							\
		return __ret;						\
	if (__data < (MIN))						\
		__data = (MIN);						\
	else if (__data > (MAX))					\
		__data = (MAX);						\
	*(__PTR) = __CONV(__data);					\
	return count;							\
}
#define STORE_INT(__FUNC, __PTR, MIN, MAX)				\
	STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, )
#define STORE_JIFFIES(__FUNC, __PTR, MIN, MAX)				\
	STORE_FUNCTION(__FUNC, __PTR, MIN, MAX, msecs_to_jiffies)
STORE_JIFFIES(deadline_read_expire_store, &dd->fifo_expire[DD_READ], 0, INT_MAX);
STORE_JIFFIES(deadline_write_expire_store, &dd->fifo_expire[DD_WRITE], 0, INT_MAX);
STORE_JIFFIES(deadline_aging_expire_store, &dd->aging_expire, 0, INT_MAX);
STORE_INT(deadline_writes_starved_store, &dd->writes_starved, INT_MIN, INT_MAX);
STORE_INT(deadline_front_merges_store, &dd->front_merges, 0, 1);
STORE_INT(deadline_async_depth_store, &dd->front_merges, 1, INT_MAX);
STORE_INT(deadline_fifo_batch_store, &dd->fifo_batch, 0, INT_MAX);
#undef STORE_FUNCTION
#undef STORE_INT
#undef STORE_JIFFIES

#define DD_ATTR(name) \
	__ATTR(name, 0644, deadline_##name##_show, deadline_##name##_store)

static struct elv_fs_entry deadline_attrs[] = {
	DD_ATTR(read_expire),
	DD_ATTR(write_expire),
	DD_ATTR(writes_starved),
	DD_ATTR(front_merges),
	DD_ATTR(async_depth),
	DD_ATTR(fifo_batch),
	DD_ATTR(aging_expire),
	__ATTR_NULL
};

#ifdef CONFIG_BLK_DEBUG_FS
#define DEADLINE_DEBUGFS_DDIR_ATTRS(prio, data_dir, name)		\
static void *deadline_##name##_fifo_start(struct seq_file *m,		\
					  loff_t *pos)			\
	__acquires(&dd->lock)						\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
	struct dd_per_prio *per_prio = &dd->per_prio[prio];		\
									\
	spin_lock(&dd->lock);						\
	return seq_list_start(&per_prio->fifo_list[data_dir], *pos);	\
}									\
									\
static void *deadline_##name##_fifo_next(struct seq_file *m, void *v,	\
					 loff_t *pos)			\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
	struct dd_per_prio *per_prio = &dd->per_prio[prio];		\
									\
	return seq_list_next(v, &per_prio->fifo_list[data_dir], pos);	\
}									\
									\
static void deadline_##name##_fifo_stop(struct seq_file *m, void *v)	\
	__releases(&dd->lock)						\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
									\
	spin_unlock(&dd->lock);						\
}									\
									\
static const struct seq_operations deadline_##name##_fifo_seq_ops = {	\
	.start	= deadline_##name##_fifo_start,				\
	.next	= deadline_##name##_fifo_next,				\
	.stop	= deadline_##name##_fifo_stop,				\
	.show	= blk_mq_debugfs_rq_show,				\
};									\
									\
static int deadline_##name##_next_rq_show(void *data,			\
					  struct seq_file *m)		\
{									\
	struct request_queue *q = data;					\
	struct deadline_data *dd = q->elevator->elevator_data;		\
	struct dd_per_prio *per_prio = &dd->per_prio[prio];		\
	struct request *rq = per_prio->next_rq[data_dir];		\
									\
	if (rq)								\
		__blk_mq_debugfs_rq_show(m, rq);			\
	return 0;							\
}

DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_READ, read0);
DEADLINE_DEBUGFS_DDIR_ATTRS(DD_RT_PRIO, DD_WRITE, write0);
DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_READ, read1);
DEADLINE_DEBUGFS_DDIR_ATTRS(DD_BE_PRIO, DD_WRITE, write1);
DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_READ, read2);
DEADLINE_DEBUGFS_DDIR_ATTRS(DD_IDLE_PRIO, DD_WRITE, write2);
#undef DEADLINE_DEBUGFS_DDIR_ATTRS

static int deadline_batching_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	struct deadline_data *dd = q->elevator->elevator_data;

	seq_printf(m, "%u\n", dd->batching);
	return 0;
}

static int deadline_starved_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	struct deadline_data *dd = q->elevator->elevator_data;

	seq_printf(m, "%u\n", dd->starved);
	return 0;
}

static int dd_async_depth_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	struct deadline_data *dd = q->elevator->elevator_data;

	seq_printf(m, "%u\n", dd->async_depth);
	return 0;
}

static int dd_queued_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	struct deadline_data *dd = q->elevator->elevator_data;

	seq_printf(m, "%u %u %u\n", dd_queued(dd, DD_RT_PRIO),
		   dd_queued(dd, DD_BE_PRIO),
		   dd_queued(dd, DD_IDLE_PRIO));
	return 0;
}

/* Number of requests owned by the block driver for a given priority. */
static u32 dd_owned_by_driver(struct deadline_data *dd, enum dd_prio prio)
{
	return dd_sum(dd, dispatched, prio) + dd_sum(dd, merged, prio)
		- dd_sum(dd, completed, prio);
}

static int dd_owned_by_driver_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	struct deadline_data *dd = q->elevator->elevator_data;

	seq_printf(m, "%u %u %u\n", dd_owned_by_driver(dd, DD_RT_PRIO),
		   dd_owned_by_driver(dd, DD_BE_PRIO),
		   dd_owned_by_driver(dd, DD_IDLE_PRIO));
	return 0;
}

#define DEADLINE_DISPATCH_ATTR(prio)					\
static void *deadline_dispatch##prio##_start(struct seq_file *m,	\
					     loff_t *pos)		\
	__acquires(&dd->lock)						\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
	struct dd_per_prio *per_prio = &dd->per_prio[prio];		\
									\
	spin_lock(&dd->lock);						\
	return seq_list_start(&per_prio->dispatch, *pos);		\
}									\
									\
static void *deadline_dispatch##prio##_next(struct seq_file *m,		\
					    void *v, loff_t *pos)	\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
	struct dd_per_prio *per_prio = &dd->per_prio[prio];		\
									\
	return seq_list_next(v, &per_prio->dispatch, pos);		\
}									\
									\
static void deadline_dispatch##prio##_stop(struct seq_file *m, void *v)	\
	__releases(&dd->lock)						\
{									\
	struct request_queue *q = m->private;				\
	struct deadline_data *dd = q->elevator->elevator_data;		\
									\
	spin_unlock(&dd->lock);						\
}									\
									\
static const struct seq_operations deadline_dispatch##prio##_seq_ops = { \
	.start	= deadline_dispatch##prio##_start,			\
	.next	= deadline_dispatch##prio##_next,			\
	.stop	= deadline_dispatch##prio##_stop,			\
	.show	= blk_mq_debugfs_rq_show,				\
}

DEADLINE_DISPATCH_ATTR(0);
DEADLINE_DISPATCH_ATTR(1);
DEADLINE_DISPATCH_ATTR(2);
#undef DEADLINE_DISPATCH_ATTR

#define DEADLINE_QUEUE_DDIR_ATTRS(name)					\
	{#name "_fifo_list", 0400,					\
			.seq_ops = &deadline_##name##_fifo_seq_ops}
#define DEADLINE_NEXT_RQ_ATTR(name)					\
	{#name "_next_rq", 0400, deadline_##name##_next_rq_show}
static const struct blk_mq_debugfs_attr deadline_queue_debugfs_attrs[] = {
	DEADLINE_QUEUE_DDIR_ATTRS(read0),
	DEADLINE_QUEUE_DDIR_ATTRS(write0),
	DEADLINE_QUEUE_DDIR_ATTRS(read1),
	DEADLINE_QUEUE_DDIR_ATTRS(write1),
	DEADLINE_QUEUE_DDIR_ATTRS(read2),
	DEADLINE_QUEUE_DDIR_ATTRS(write2),
	DEADLINE_NEXT_RQ_ATTR(read0),
	DEADLINE_NEXT_RQ_ATTR(write0),
	DEADLINE_NEXT_RQ_ATTR(read1),
	DEADLINE_NEXT_RQ_ATTR(write1),
	DEADLINE_NEXT_RQ_ATTR(read2),
	DEADLINE_NEXT_RQ_ATTR(write2),
	{"batching", 0400, deadline_batching_show},
	{"starved", 0400, deadline_starved_show},
	{"async_depth", 0400, dd_async_depth_show},
	{"dispatch0", 0400, .seq_ops = &deadline_dispatch0_seq_ops},
	{"dispatch1", 0400, .seq_ops = &deadline_dispatch1_seq_ops},
	{"dispatch2", 0400, .seq_ops = &deadline_dispatch2_seq_ops},
	{"owned_by_driver", 0400, dd_owned_by_driver_show},
	{"queued", 0400, dd_queued_show},
	{},
};
#undef DEADLINE_QUEUE_DDIR_ATTRS
#endif

static struct elevator_type mq_deadline = {
	.ops = {
		.depth_updated		= dd_depth_updated,
		.limit_depth		= dd_limit_depth,
		.insert_requests	= dd_insert_requests,
		.dispatch_request	= dd_dispatch_request,
		.prepare_request	= dd_prepare_request,
		.finish_request		= dd_finish_request,
		.next_request		= elv_rb_latter_request,
		.former_request		= elv_rb_former_request,
		.bio_merge		= dd_bio_merge,
		.request_merge		= dd_request_merge,
		.requests_merged	= dd_merged_requests,
		.request_merged		= dd_request_merged,
		.has_work		= dd_has_work,
		.init_sched		= dd_init_sched,
		.exit_sched		= dd_exit_sched,
		.init_hctx		= dd_init_hctx,
	},

#ifdef CONFIG_BLK_DEBUG_FS
	.queue_debugfs_attrs = deadline_queue_debugfs_attrs,
#endif
	.elevator_attrs = deadline_attrs,
	.elevator_name = "mq-deadline",
	.elevator_alias = "deadline",
	.elevator_features = ELEVATOR_F_ZBD_SEQ_WRITE,
	.elevator_owner = THIS_MODULE,
};
MODULE_ALIAS("mq-deadline-iosched");

static int __init deadline_init(void)
{
	int ret;

	ret = elv_register(&mq_deadline);
	if (ret)
		goto out;
	ret = dd_blkcg_init();
	if (ret)
		goto unreg;

out:
	return ret;

unreg:
	elv_unregister(&mq_deadline);
	goto out;
}

static void __exit deadline_exit(void)
{
	dd_blkcg_exit();
	elv_unregister(&mq_deadline);
}

module_init(deadline_init);
module_exit(deadline_exit);

MODULE_AUTHOR("Jens Axboe, Damien Le Moal and Bart Van Assche");
MODULE_LICENSE("GPL");
MODULE_DESCRIPTION("MQ deadline IO scheduler");