summaryrefslogtreecommitdiffstats
path: root/block/blk-iolatency.c
blob: 28f80d22752858a2b1fcdfefb5f079469ec480ee (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
/*
 * Block rq-qos base io controller
 *
 * This works similar to wbt with a few exceptions
 *
 * - It's bio based, so the latency covers the whole block layer in addition to
 *   the actual io.
 * - We will throttle all IO that comes in here if we need to.
 * - We use the mean latency over the 100ms window.  This is because writes can
 *   be particularly fast, which could give us a false sense of the impact of
 *   other workloads on our protected workload.
 * - By default there's no throttling, we set the queue_depth to UINT_MAX so
 *   that we can have as many outstanding bio's as we're allowed to.  Only at
 *   throttle time do we pay attention to the actual queue depth.
 *
 * The hierarchy works like the cpu controller does, we track the latency at
 * every configured node, and each configured node has it's own independent
 * queue depth.  This means that we only care about our latency targets at the
 * peer level.  Some group at the bottom of the hierarchy isn't going to affect
 * a group at the end of some other path if we're only configred at leaf level.
 *
 * Consider the following
 *
 *                   root blkg
 *             /                     \
 *        fast (target=5ms)     slow (target=10ms)
 *         /     \                  /        \
 *       a        b          normal(15ms)   unloved
 *
 * "a" and "b" have no target, but their combined io under "fast" cannot exceed
 * an average latency of 5ms.  If it does then we will throttle the "slow"
 * group.  In the case of "normal", if it exceeds its 15ms target, we will
 * throttle "unloved", but nobody else.
 *
 * In this example "fast", "slow", and "normal" will be the only groups actually
 * accounting their io latencies.  We have to walk up the heirarchy to the root
 * on every submit and complete so we can do the appropriate stat recording and
 * adjust the queue depth of ourselves if needed.
 *
 * There are 2 ways we throttle IO.
 *
 * 1) Queue depth throttling.  As we throttle down we will adjust the maximum
 * number of IO's we're allowed to have in flight.  This starts at (u64)-1 down
 * to 1.  If the group is only ever submitting IO for itself then this is the
 * only way we throttle.
 *
 * 2) Induced delay throttling.  This is for the case that a group is generating
 * IO that has to be issued by the root cg to avoid priority inversion. So think
 * REQ_META or REQ_SWAP.  If we are already at qd == 1 and we're getting a lot
 * of work done for us on behalf of the root cg and are being asked to scale
 * down more then we induce a latency at userspace return.  We accumulate the
 * total amount of time we need to be punished by doing
 *
 * total_time += min_lat_nsec - actual_io_completion
 *
 * and then at throttle time will do
 *
 * throttle_time = min(total_time, NSEC_PER_SEC)
 *
 * This induced delay will throttle back the activity that is generating the
 * root cg issued io's, wethere that's some metadata intensive operation or the
 * group is using so much memory that it is pushing us into swap.
 *
 * Copyright (C) 2018 Josef Bacik
 */
#include <linux/kernel.h>
#include <linux/blk_types.h>
#include <linux/backing-dev.h>
#include <linux/module.h>
#include <linux/timer.h>
#include <linux/memcontrol.h>
#include <linux/sched/loadavg.h>
#include <linux/sched/signal.h>
#include <trace/events/block.h>
#include "blk-rq-qos.h"
#include "blk-stat.h"

#define DEFAULT_SCALE_COOKIE 1000000U

static struct blkcg_policy blkcg_policy_iolatency;
struct iolatency_grp;

struct blk_iolatency {
	struct rq_qos rqos;
	struct timer_list timer;
	atomic_t enabled;
};

static inline struct blk_iolatency *BLKIOLATENCY(struct rq_qos *rqos)
{
	return container_of(rqos, struct blk_iolatency, rqos);
}

static inline bool blk_iolatency_enabled(struct blk_iolatency *blkiolat)
{
	return atomic_read(&blkiolat->enabled) > 0;
}

struct child_latency_info {
	spinlock_t lock;

	/* Last time we adjusted the scale of everybody. */
	u64 last_scale_event;

	/* The latency that we missed. */
	u64 scale_lat;

	/* Total io's from all of our children for the last summation. */
	u64 nr_samples;

	/* The guy who actually changed the latency numbers. */
	struct iolatency_grp *scale_grp;

	/* Cookie to tell if we need to scale up or down. */
	atomic_t scale_cookie;
};

struct percentile_stats {
	u64 total;
	u64 missed;
};

struct latency_stat {
	union {
		struct percentile_stats ps;
		struct blk_rq_stat rqs;
	};
};

struct iolatency_grp {
	struct blkg_policy_data pd;
	struct latency_stat __percpu *stats;
	struct latency_stat cur_stat;
	struct blk_iolatency *blkiolat;
	struct rq_depth rq_depth;
	struct rq_wait rq_wait;
	atomic64_t window_start;
	atomic_t scale_cookie;
	u64 min_lat_nsec;
	u64 cur_win_nsec;

	/* total running average of our io latency. */
	u64 lat_avg;

	/* Our current number of IO's for the last summation. */
	u64 nr_samples;

	bool ssd;
	struct child_latency_info child_lat;
};

#define BLKIOLATENCY_MIN_WIN_SIZE (100 * NSEC_PER_MSEC)
#define BLKIOLATENCY_MAX_WIN_SIZE NSEC_PER_SEC
/*
 * These are the constants used to fake the fixed-point moving average
 * calculation just like load average.  The call to calc_load() folds
 * (FIXED_1 (2048) - exp_factor) * new_sample into lat_avg.  The sampling
 * window size is bucketed to try to approximately calculate average
 * latency such that 1/exp (decay rate) is [1 min, 2.5 min) when windows
 * elapse immediately.  Note, windows only elapse with IO activity.  Idle
 * periods extend the most recent window.
 */
#define BLKIOLATENCY_NR_EXP_FACTORS 5
#define BLKIOLATENCY_EXP_BUCKET_SIZE (BLKIOLATENCY_MAX_WIN_SIZE / \
				      (BLKIOLATENCY_NR_EXP_FACTORS - 1))
static const u64 iolatency_exp_factors[BLKIOLATENCY_NR_EXP_FACTORS] = {
	2045, // exp(1/600) - 600 samples
	2039, // exp(1/240) - 240 samples
	2031, // exp(1/120) - 120 samples
	2023, // exp(1/80)  - 80 samples
	2014, // exp(1/60)  - 60 samples
};

static inline struct iolatency_grp *pd_to_lat(struct blkg_policy_data *pd)
{
	return pd ? container_of(pd, struct iolatency_grp, pd) : NULL;
}

static inline struct iolatency_grp *blkg_to_lat(struct blkcg_gq *blkg)
{
	return pd_to_lat(blkg_to_pd(blkg, &blkcg_policy_iolatency));
}

static inline struct blkcg_gq *lat_to_blkg(struct iolatency_grp *iolat)
{
	return pd_to_blkg(&iolat->pd);
}

static inline void latency_stat_init(struct iolatency_grp *iolat,
				     struct latency_stat *stat)
{
	if (iolat->ssd) {
		stat->ps.total = 0;
		stat->ps.missed = 0;
	} else
		blk_rq_stat_init(&stat->rqs);
}

static inline void latency_stat_sum(struct iolatency_grp *iolat,
				    struct latency_stat *sum,
				    struct latency_stat *stat)
{
	if (iolat->ssd) {
		sum->ps.total += stat->ps.total;
		sum->ps.missed += stat->ps.missed;
	} else
		blk_rq_stat_sum(&sum->rqs, &stat->rqs);
}

static inline void latency_stat_record_time(struct iolatency_grp *iolat,
					    u64 req_time)
{
	struct latency_stat *stat = get_cpu_ptr(iolat->stats);
	if (iolat->ssd) {
		if (req_time >= iolat->min_lat_nsec)
			stat->ps.missed++;
		stat->ps.total++;
	} else
		blk_rq_stat_add(&stat->rqs, req_time);
	put_cpu_ptr(stat);
}

static inline bool latency_sum_ok(struct iolatency_grp *iolat,
				  struct latency_stat *stat)
{
	if (iolat->ssd) {
		u64 thresh = div64_u64(stat->ps.total, 10);
		thresh = max(thresh, 1ULL);
		return stat->ps.missed < thresh;
	}
	return stat->rqs.mean <= iolat->min_lat_nsec;
}

static inline u64 latency_stat_samples(struct iolatency_grp *iolat,
				       struct latency_stat *stat)
{
	if (iolat->ssd)
		return stat->ps.total;
	return stat->rqs.nr_samples;
}

static inline void iolat_update_total_lat_avg(struct iolatency_grp *iolat,
					      struct latency_stat *stat)
{
	int exp_idx;

	if (iolat->ssd)
		return;

	/*
	 * calc_load() takes in a number stored in fixed point representation.
	 * Because we are using this for IO time in ns, the values stored
	 * are significantly larger than the FIXED_1 denominator (2048).
	 * Therefore, rounding errors in the calculation are negligible and
	 * can be ignored.
	 */
	exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1,
			div64_u64(iolat->cur_win_nsec,
				  BLKIOLATENCY_EXP_BUCKET_SIZE));
	iolat->lat_avg = calc_load(iolat->lat_avg,
				   iolatency_exp_factors[exp_idx],
				   stat->rqs.mean);
}

static inline bool iolatency_may_queue(struct iolatency_grp *iolat,
				       wait_queue_entry_t *wait,
				       bool first_block)
{
	struct rq_wait *rqw = &iolat->rq_wait;

	if (first_block && waitqueue_active(&rqw->wait) &&
	    rqw->wait.head.next != &wait->entry)
		return false;
	return rq_wait_inc_below(rqw, iolat->rq_depth.max_depth);
}

static void __blkcg_iolatency_throttle(struct rq_qos *rqos,
				       struct iolatency_grp *iolat,
				       spinlock_t *lock, bool issue_as_root,
				       bool use_memdelay)
	__releases(lock)
	__acquires(lock)
{
	struct rq_wait *rqw = &iolat->rq_wait;
	unsigned use_delay = atomic_read(&lat_to_blkg(iolat)->use_delay);
	DEFINE_WAIT(wait);
	bool first_block = true;

	if (use_delay)
		blkcg_schedule_throttle(rqos->q, use_memdelay);

	/*
	 * To avoid priority inversions we want to just take a slot if we are
	 * issuing as root.  If we're being killed off there's no point in
	 * delaying things, we may have been killed by OOM so throttling may
	 * make recovery take even longer, so just let the IO's through so the
	 * task can go away.
	 */
	if (issue_as_root || fatal_signal_pending(current)) {
		atomic_inc(&rqw->inflight);
		return;
	}

	if (iolatency_may_queue(iolat, &wait, first_block))
		return;

	do {
		prepare_to_wait_exclusive(&rqw->wait, &wait,
					  TASK_UNINTERRUPTIBLE);

		if (iolatency_may_queue(iolat, &wait, first_block))
			break;
		first_block = false;

		if (lock) {
			spin_unlock_irq(lock);
			io_schedule();
			spin_lock_irq(lock);
		} else {
			io_schedule();
		}
	} while (1);

	finish_wait(&rqw->wait, &wait);
}

#define SCALE_DOWN_FACTOR 2
#define SCALE_UP_FACTOR 4

static inline unsigned long scale_amount(unsigned long qd, bool up)
{
	return max(up ? qd >> SCALE_UP_FACTOR : qd >> SCALE_DOWN_FACTOR, 1UL);
}

/*
 * We scale the qd down faster than we scale up, so we need to use this helper
 * to adjust the scale_cookie accordingly so we don't prematurely get
 * scale_cookie at DEFAULT_SCALE_COOKIE and unthrottle too much.
 *
 * Each group has their own local copy of the last scale cookie they saw, so if
 * the global scale cookie goes up or down they know which way they need to go
 * based on their last knowledge of it.
 */
static void scale_cookie_change(struct blk_iolatency *blkiolat,
				struct child_latency_info *lat_info,
				bool up)
{
	unsigned long qd = blkiolat->rqos.q->nr_requests;
	unsigned long scale = scale_amount(qd, up);
	unsigned long old = atomic_read(&lat_info->scale_cookie);
	unsigned long max_scale = qd << 1;
	unsigned long diff = 0;

	if (old < DEFAULT_SCALE_COOKIE)
		diff = DEFAULT_SCALE_COOKIE - old;

	if (up) {
		if (scale + old > DEFAULT_SCALE_COOKIE)
			atomic_set(&lat_info->scale_cookie,
				   DEFAULT_SCALE_COOKIE);
		else if (diff > qd)
			atomic_inc(&lat_info->scale_cookie);
		else
			atomic_add(scale, &lat_info->scale_cookie);
	} else {
		/*
		 * We don't want to dig a hole so deep that it takes us hours to
		 * dig out of it.  Just enough that we don't throttle/unthrottle
		 * with jagged workloads but can still unthrottle once pressure
		 * has sufficiently dissipated.
		 */
		if (diff > qd) {
			if (diff < max_scale)
				atomic_dec(&lat_info->scale_cookie);
		} else {
			atomic_sub(scale, &lat_info->scale_cookie);
		}
	}
}

/*
 * Change the queue depth of the iolatency_grp.  We add/subtract 1/16th of the
 * queue depth at a time so we don't get wild swings and hopefully dial in to
 * fairer distribution of the overall queue depth.
 */
static void scale_change(struct iolatency_grp *iolat, bool up)
{
	unsigned long qd = iolat->blkiolat->rqos.q->nr_requests;
	unsigned long scale = scale_amount(qd, up);
	unsigned long old = iolat->rq_depth.max_depth;

	if (old > qd)
		old = qd;

	if (up) {
		if (old == 1 && blkcg_unuse_delay(lat_to_blkg(iolat)))
			return;

		if (old < qd) {
			old += scale;
			old = min(old, qd);
			iolat->rq_depth.max_depth = old;
			wake_up_all(&iolat->rq_wait.wait);
		}
	} else {
		old >>= 1;
		iolat->rq_depth.max_depth = max(old, 1UL);
	}
}

/* Check our parent and see if the scale cookie has changed. */
static void check_scale_change(struct iolatency_grp *iolat)
{
	struct iolatency_grp *parent;
	struct child_latency_info *lat_info;
	unsigned int cur_cookie;
	unsigned int our_cookie = atomic_read(&iolat->scale_cookie);
	u64 scale_lat;
	unsigned int old;
	int direction = 0;

	if (lat_to_blkg(iolat)->parent == NULL)
		return;

	parent = blkg_to_lat(lat_to_blkg(iolat)->parent);
	if (!parent)
		return;

	lat_info = &parent->child_lat;
	cur_cookie = atomic_read(&lat_info->scale_cookie);
	scale_lat = READ_ONCE(lat_info->scale_lat);

	if (cur_cookie < our_cookie)
		direction = -1;
	else if (cur_cookie > our_cookie)
		direction = 1;
	else
		return;

	old = atomic_cmpxchg(&iolat->scale_cookie, our_cookie, cur_cookie);

	/* Somebody beat us to the punch, just bail. */
	if (old != our_cookie)
		return;

	if (direction < 0 && iolat->min_lat_nsec) {
		u64 samples_thresh;

		if (!scale_lat || iolat->min_lat_nsec <= scale_lat)
			return;

		/*
		 * Sometimes high priority groups are their own worst enemy, so
		 * instead of taking it out on some poor other group that did 5%
		 * or less of the IO's for the last summation just skip this
		 * scale down event.
		 */
		samples_thresh = lat_info->nr_samples * 5;
		samples_thresh = max(1ULL, div64_u64(samples_thresh, 100));
		if (iolat->nr_samples <= samples_thresh)
			return;
	}

	/* We're as low as we can go. */
	if (iolat->rq_depth.max_depth == 1 && direction < 0) {
		blkcg_use_delay(lat_to_blkg(iolat));
		return;
	}

	/* We're back to the default cookie, unthrottle all the things. */
	if (cur_cookie == DEFAULT_SCALE_COOKIE) {
		blkcg_clear_delay(lat_to_blkg(iolat));
		iolat->rq_depth.max_depth = UINT_MAX;
		wake_up_all(&iolat->rq_wait.wait);
		return;
	}

	scale_change(iolat, direction > 0);
}

static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio,
				     spinlock_t *lock)
{
	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
	struct blkcg_gq *blkg = bio->bi_blkg;
	bool issue_as_root = bio_issue_as_root_blkg(bio);

	if (!blk_iolatency_enabled(blkiolat))
		return;

	while (blkg && blkg->parent) {
		struct iolatency_grp *iolat = blkg_to_lat(blkg);
		if (!iolat) {
			blkg = blkg->parent;
			continue;
		}

		check_scale_change(iolat);
		__blkcg_iolatency_throttle(rqos, iolat, lock, issue_as_root,
				     (bio->bi_opf & REQ_SWAP) == REQ_SWAP);
		blkg = blkg->parent;
	}
	if (!timer_pending(&blkiolat->timer))
		mod_timer(&blkiolat->timer, jiffies + HZ);
}

static void iolatency_record_time(struct iolatency_grp *iolat,
				  struct bio_issue *issue, u64 now,
				  bool issue_as_root)
{
	u64 start = bio_issue_time(issue);
	u64 req_time;

	/*
	 * Have to do this so we are truncated to the correct time that our
	 * issue is truncated to.
	 */
	now = __bio_issue_time(now);

	if (now <= start)
		return;

	req_time = now - start;

	/*
	 * We don't want to count issue_as_root bio's in the cgroups latency
	 * statistics as it could skew the numbers downwards.
	 */
	if (unlikely(issue_as_root && iolat->rq_depth.max_depth != UINT_MAX)) {
		u64 sub = iolat->min_lat_nsec;
		if (req_time < sub)
			blkcg_add_delay(lat_to_blkg(iolat), now, sub - req_time);
		return;
	}

	latency_stat_record_time(iolat, req_time);
}

#define BLKIOLATENCY_MIN_ADJUST_TIME (500 * NSEC_PER_MSEC)
#define BLKIOLATENCY_MIN_GOOD_SAMPLES 5

static void iolatency_check_latencies(struct iolatency_grp *iolat, u64 now)
{
	struct blkcg_gq *blkg = lat_to_blkg(iolat);
	struct iolatency_grp *parent;
	struct child_latency_info *lat_info;
	struct latency_stat stat;
	unsigned long flags;
	int cpu;

	latency_stat_init(iolat, &stat);
	preempt_disable();
	for_each_online_cpu(cpu) {
		struct latency_stat *s;
		s = per_cpu_ptr(iolat->stats, cpu);
		latency_stat_sum(iolat, &stat, s);
		latency_stat_init(iolat, s);
	}
	preempt_enable();

	parent = blkg_to_lat(blkg->parent);
	if (!parent)
		return;

	lat_info = &parent->child_lat;

	iolat_update_total_lat_avg(iolat, &stat);

	/* Everything is ok and we don't need to adjust the scale. */
	if (latency_sum_ok(iolat, &stat) &&
	    atomic_read(&lat_info->scale_cookie) == DEFAULT_SCALE_COOKIE)
		return;

	/* Somebody beat us to the punch, just bail. */
	spin_lock_irqsave(&lat_info->lock, flags);

	latency_stat_sum(iolat, &iolat->cur_stat, &stat);
	lat_info->nr_samples -= iolat->nr_samples;
	lat_info->nr_samples += latency_stat_samples(iolat, &iolat->cur_stat);
	iolat->nr_samples = latency_stat_samples(iolat, &iolat->cur_stat);

	if ((lat_info->last_scale_event >= now ||
	    now - lat_info->last_scale_event < BLKIOLATENCY_MIN_ADJUST_TIME))
		goto out;

	if (latency_sum_ok(iolat, &iolat->cur_stat) &&
	    latency_sum_ok(iolat, &stat)) {
		if (latency_stat_samples(iolat, &iolat->cur_stat) <
		    BLKIOLATENCY_MIN_GOOD_SAMPLES)
			goto out;
		if (lat_info->scale_grp == iolat) {
			lat_info->last_scale_event = now;
			scale_cookie_change(iolat->blkiolat, lat_info, true);
		}
	} else if (lat_info->scale_lat == 0 ||
		   lat_info->scale_lat >= iolat->min_lat_nsec) {
		lat_info->last_scale_event = now;
		if (!lat_info->scale_grp ||
		    lat_info->scale_lat > iolat->min_lat_nsec) {
			WRITE_ONCE(lat_info->scale_lat, iolat->min_lat_nsec);
			lat_info->scale_grp = iolat;
		}
		scale_cookie_change(iolat->blkiolat, lat_info, false);
	}
	latency_stat_init(iolat, &iolat->cur_stat);
out:
	spin_unlock_irqrestore(&lat_info->lock, flags);
}

static void blkcg_iolatency_done_bio(struct rq_qos *rqos, struct bio *bio)
{
	struct blkcg_gq *blkg;
	struct rq_wait *rqw;
	struct iolatency_grp *iolat;
	u64 window_start;
	u64 now = ktime_to_ns(ktime_get());
	bool issue_as_root = bio_issue_as_root_blkg(bio);
	bool enabled = false;

	blkg = bio->bi_blkg;
	if (!blkg)
		return;

	iolat = blkg_to_lat(bio->bi_blkg);
	if (!iolat)
		return;

	enabled = blk_iolatency_enabled(iolat->blkiolat);
	while (blkg && blkg->parent) {
		iolat = blkg_to_lat(blkg);
		if (!iolat) {
			blkg = blkg->parent;
			continue;
		}
		rqw = &iolat->rq_wait;

		atomic_dec(&rqw->inflight);
		if (!enabled || iolat->min_lat_nsec == 0)
			goto next;
		iolatency_record_time(iolat, &bio->bi_issue, now,
				      issue_as_root);
		window_start = atomic64_read(&iolat->window_start);
		if (now > window_start &&
		    (now - window_start) >= iolat->cur_win_nsec) {
			if (atomic64_cmpxchg(&iolat->window_start,
					window_start, now) == window_start)
				iolatency_check_latencies(iolat, now);
		}
next:
		wake_up(&rqw->wait);
		blkg = blkg->parent;
	}
}

static void blkcg_iolatency_cleanup(struct rq_qos *rqos, struct bio *bio)
{
	struct blkcg_gq *blkg;

	blkg = bio->bi_blkg;
	while (blkg && blkg->parent) {
		struct rq_wait *rqw;
		struct iolatency_grp *iolat;

		iolat = blkg_to_lat(blkg);
		if (!iolat)
			goto next;

		rqw = &iolat->rq_wait;
		atomic_dec(&rqw->inflight);
		wake_up(&rqw->wait);
next:
		blkg = blkg->parent;
	}
}

static void blkcg_iolatency_exit(struct rq_qos *rqos)
{
	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);

	del_timer_sync(&blkiolat->timer);
	blkcg_deactivate_policy(rqos->q, &blkcg_policy_iolatency);
	kfree(blkiolat);
}

static struct rq_qos_ops blkcg_iolatency_ops = {
	.throttle = blkcg_iolatency_throttle,
	.cleanup = blkcg_iolatency_cleanup,
	.done_bio = blkcg_iolatency_done_bio,
	.exit = blkcg_iolatency_exit,
};

static void blkiolatency_timer_fn(struct timer_list *t)
{
	struct blk_iolatency *blkiolat = from_timer(blkiolat, t, timer);
	struct blkcg_gq *blkg;
	struct cgroup_subsys_state *pos_css;
	u64 now = ktime_to_ns(ktime_get());

	rcu_read_lock();
	blkg_for_each_descendant_pre(blkg, pos_css,
				     blkiolat->rqos.q->root_blkg) {
		struct iolatency_grp *iolat;
		struct child_latency_info *lat_info;
		unsigned long flags;
		u64 cookie;

		/*
		 * We could be exiting, don't access the pd unless we have a
		 * ref on the blkg.
		 */
		if (!blkg_tryget(blkg))
			continue;

		iolat = blkg_to_lat(blkg);
		if (!iolat)
			goto next;

		lat_info = &iolat->child_lat;
		cookie = atomic_read(&lat_info->scale_cookie);

		if (cookie >= DEFAULT_SCALE_COOKIE)
			goto next;

		spin_lock_irqsave(&lat_info->lock, flags);
		if (lat_info->last_scale_event >= now)
			goto next_lock;

		/*
		 * We scaled down but don't have a scale_grp, scale up and carry
		 * on.
		 */
		if (lat_info->scale_grp == NULL) {
			scale_cookie_change(iolat->blkiolat, lat_info, true);
			goto next_lock;
		}

		/*
		 * It's been 5 seconds since our last scale event, clear the
		 * scale grp in case the group that needed the scale down isn't
		 * doing any IO currently.
		 */
		if (now - lat_info->last_scale_event >=
		    ((u64)NSEC_PER_SEC * 5))
			lat_info->scale_grp = NULL;
next_lock:
		spin_unlock_irqrestore(&lat_info->lock, flags);
next:
		blkg_put(blkg);
	}
	rcu_read_unlock();
}

int blk_iolatency_init(struct request_queue *q)
{
	struct blk_iolatency *blkiolat;
	struct rq_qos *rqos;
	int ret;

	blkiolat = kzalloc(sizeof(*blkiolat), GFP_KERNEL);
	if (!blkiolat)
		return -ENOMEM;

	rqos = &blkiolat->rqos;
	rqos->id = RQ_QOS_CGROUP;
	rqos->ops = &blkcg_iolatency_ops;
	rqos->q = q;

	rq_qos_add(q, rqos);

	ret = blkcg_activate_policy(q, &blkcg_policy_iolatency);
	if (ret) {
		rq_qos_del(q, rqos);
		kfree(blkiolat);
		return ret;
	}

	timer_setup(&blkiolat->timer, blkiolatency_timer_fn, 0);

	return 0;
}

static void iolatency_set_min_lat_nsec(struct blkcg_gq *blkg, u64 val)
{
	struct iolatency_grp *iolat = blkg_to_lat(blkg);
	struct blk_iolatency *blkiolat = iolat->blkiolat;
	u64 oldval = iolat->min_lat_nsec;

	iolat->min_lat_nsec = val;
	iolat->cur_win_nsec = max_t(u64, val << 4, BLKIOLATENCY_MIN_WIN_SIZE);
	iolat->cur_win_nsec = min_t(u64, iolat->cur_win_nsec,
				    BLKIOLATENCY_MAX_WIN_SIZE);

	if (!oldval && val)
		atomic_inc(&blkiolat->enabled);
	if (oldval && !val)
		atomic_dec(&blkiolat->enabled);
}

static void iolatency_clear_scaling(struct blkcg_gq *blkg)
{
	if (blkg->parent) {
		struct iolatency_grp *iolat = blkg_to_lat(blkg->parent);
		struct child_latency_info *lat_info;
		if (!iolat)
			return;

		lat_info = &iolat->child_lat;
		spin_lock(&lat_info->lock);
		atomic_set(&lat_info->scale_cookie, DEFAULT_SCALE_COOKIE);
		lat_info->last_scale_event = 0;
		lat_info->scale_grp = NULL;
		lat_info->scale_lat = 0;
		spin_unlock(&lat_info->lock);
	}
}

static ssize_t iolatency_set_limit(struct kernfs_open_file *of, char *buf,
			     size_t nbytes, loff_t off)
{
	struct blkcg *blkcg = css_to_blkcg(of_css(of));
	struct blkcg_gq *blkg;
	struct blkg_conf_ctx ctx;
	struct iolatency_grp *iolat;
	char *p, *tok;
	u64 lat_val = 0;
	u64 oldval;
	int ret;

	ret = blkg_conf_prep(blkcg, &blkcg_policy_iolatency, buf, &ctx);
	if (ret)
		return ret;

	iolat = blkg_to_lat(ctx.blkg);
	p = ctx.body;

	ret = -EINVAL;
	while ((tok = strsep(&p, " "))) {
		char key[16];
		char val[21];	/* 18446744073709551616 */

		if (sscanf(tok, "%15[^=]=%20s", key, val) != 2)
			goto out;

		if (!strcmp(key, "target")) {
			u64 v;

			if (!strcmp(val, "max"))
				lat_val = 0;
			else if (sscanf(val, "%llu", &v) == 1)
				lat_val = v * NSEC_PER_USEC;
			else
				goto out;
		} else {
			goto out;
		}
	}

	/* Walk up the tree to see if our new val is lower than it should be. */
	blkg = ctx.blkg;
	oldval = iolat->min_lat_nsec;

	iolatency_set_min_lat_nsec(blkg, lat_val);
	if (oldval != iolat->min_lat_nsec) {
		iolatency_clear_scaling(blkg);
	}

	ret = 0;
out:
	blkg_conf_finish(&ctx);
	return ret ?: nbytes;
}

static u64 iolatency_prfill_limit(struct seq_file *sf,
				  struct blkg_policy_data *pd, int off)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	const char *dname = blkg_dev_name(pd->blkg);

	if (!dname || !iolat->min_lat_nsec)
		return 0;
	seq_printf(sf, "%s target=%llu\n",
		   dname, div_u64(iolat->min_lat_nsec, NSEC_PER_USEC));
	return 0;
}

static int iolatency_print_limit(struct seq_file *sf, void *v)
{
	blkcg_print_blkgs(sf, css_to_blkcg(seq_css(sf)),
			  iolatency_prfill_limit,
			  &blkcg_policy_iolatency, seq_cft(sf)->private, false);
	return 0;
}

static size_t iolatency_ssd_stat(struct iolatency_grp *iolat, char *buf,
				 size_t size)
{
	struct latency_stat stat;
	int cpu;

	latency_stat_init(iolat, &stat);
	preempt_disable();
	for_each_online_cpu(cpu) {
		struct latency_stat *s;
		s = per_cpu_ptr(iolat->stats, cpu);
		latency_stat_sum(iolat, &stat, s);
	}
	preempt_enable();

	if (iolat->rq_depth.max_depth == UINT_MAX)
		return scnprintf(buf, size, " missed=%llu total=%llu depth=max",
				 (unsigned long long)stat.ps.missed,
				 (unsigned long long)stat.ps.total);
	return scnprintf(buf, size, " missed=%llu total=%llu depth=%u",
			 (unsigned long long)stat.ps.missed,
			 (unsigned long long)stat.ps.total,
			 iolat->rq_depth.max_depth);
}

static size_t iolatency_pd_stat(struct blkg_policy_data *pd, char *buf,
				size_t size)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	unsigned long long avg_lat;
	unsigned long long cur_win;

	if (iolat->ssd)
		return iolatency_ssd_stat(iolat, buf, size);

	avg_lat = div64_u64(iolat->lat_avg, NSEC_PER_USEC);
	cur_win = div64_u64(iolat->cur_win_nsec, NSEC_PER_MSEC);
	if (iolat->rq_depth.max_depth == UINT_MAX)
		return scnprintf(buf, size, " depth=max avg_lat=%llu win=%llu",
				 avg_lat, cur_win);

	return scnprintf(buf, size, " depth=%u avg_lat=%llu win=%llu",
			 iolat->rq_depth.max_depth, avg_lat, cur_win);
}


static struct blkg_policy_data *iolatency_pd_alloc(gfp_t gfp, int node)
{
	struct iolatency_grp *iolat;

	iolat = kzalloc_node(sizeof(*iolat), gfp, node);
	if (!iolat)
		return NULL;
	iolat->stats = __alloc_percpu_gfp(sizeof(struct latency_stat),
				       __alignof__(struct latency_stat), gfp);
	if (!iolat->stats) {
		kfree(iolat);
		return NULL;
	}
	return &iolat->pd;
}

static void iolatency_pd_init(struct blkg_policy_data *pd)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	struct blkcg_gq *blkg = lat_to_blkg(iolat);
	struct rq_qos *rqos = blkcg_rq_qos(blkg->q);
	struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos);
	u64 now = ktime_to_ns(ktime_get());
	int cpu;

	if (blk_queue_nonrot(blkg->q))
		iolat->ssd = true;
	else
		iolat->ssd = false;

	for_each_possible_cpu(cpu) {
		struct latency_stat *stat;
		stat = per_cpu_ptr(iolat->stats, cpu);
		latency_stat_init(iolat, stat);
	}

	latency_stat_init(iolat, &iolat->cur_stat);
	rq_wait_init(&iolat->rq_wait);
	spin_lock_init(&iolat->child_lat.lock);
	iolat->rq_depth.queue_depth = blkg->q->nr_requests;
	iolat->rq_depth.max_depth = UINT_MAX;
	iolat->rq_depth.default_depth = iolat->rq_depth.queue_depth;
	iolat->blkiolat = blkiolat;
	iolat->cur_win_nsec = 100 * NSEC_PER_MSEC;
	atomic64_set(&iolat->window_start, now);

	/*
	 * We init things in list order, so the pd for the parent may not be
	 * init'ed yet for whatever reason.
	 */
	if (blkg->parent && blkg_to_pd(blkg->parent, &blkcg_policy_iolatency)) {
		struct iolatency_grp *parent = blkg_to_lat(blkg->parent);
		atomic_set(&iolat->scale_cookie,
			   atomic_read(&parent->child_lat.scale_cookie));
	} else {
		atomic_set(&iolat->scale_cookie, DEFAULT_SCALE_COOKIE);
	}

	atomic_set(&iolat->child_lat.scale_cookie, DEFAULT_SCALE_COOKIE);
}

static void iolatency_pd_offline(struct blkg_policy_data *pd)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	struct blkcg_gq *blkg = lat_to_blkg(iolat);

	iolatency_set_min_lat_nsec(blkg, 0);
	iolatency_clear_scaling(blkg);
}

static void iolatency_pd_free(struct blkg_policy_data *pd)
{
	struct iolatency_grp *iolat = pd_to_lat(pd);
	free_percpu(iolat->stats);
	kfree(iolat);
}

static struct cftype iolatency_files[] = {
	{
		.name = "latency",
		.flags = CFTYPE_NOT_ON_ROOT,
		.seq_show = iolatency_print_limit,
		.write = iolatency_set_limit,
	},
	{}
};

static struct blkcg_policy blkcg_policy_iolatency = {
	.dfl_cftypes	= iolatency_files,
	.pd_alloc_fn	= iolatency_pd_alloc,
	.pd_init_fn	= iolatency_pd_init,
	.pd_offline_fn	= iolatency_pd_offline,
	.pd_free_fn	= iolatency_pd_free,
	.pd_stat_fn	= iolatency_pd_stat,
};

static int __init iolatency_init(void)
{
	return blkcg_policy_register(&blkcg_policy_iolatency);
}

static void __exit iolatency_exit(void)
{
	return blkcg_policy_unregister(&blkcg_policy_iolatency);
}

module_init(iolatency_init);
module_exit(iolatency_exit);