forked from shenki/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
blk-mq.c
3551 lines (2969 loc) · 85.8 KB
/
blk-mq.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0
/*
* Block multiqueue core code
*
* Copyright (C) 2013-2014 Jens Axboe
* Copyright (C) 2013-2014 Christoph Hellwig
*/
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/backing-dev.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/kmemleak.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/workqueue.h>
#include <linux/smp.h>
#include <linux/llist.h>
#include <linux/list_sort.h>
#include <linux/cpu.h>
#include <linux/cache.h>
#include <linux/sched/sysctl.h>
#include <linux/sched/topology.h>
#include <linux/sched/signal.h>
#include <linux/delay.h>
#include <linux/crash_dump.h>
#include <linux/prefetch.h>
#include <trace/events/block.h>
#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-tag.h"
#include "blk-pm.h"
#include "blk-stat.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
static void blk_mq_poll_stats_start(struct request_queue *q);
static void blk_mq_poll_stats_fn(struct blk_stat_callback *cb);
static int blk_mq_poll_stats_bkt(const struct request *rq)
{
int ddir, bytes, bucket;
ddir = rq_data_dir(rq);
bytes = blk_rq_bytes(rq);
bucket = ddir + 2*(ilog2(bytes) - 9);
if (bucket < 0)
return -1;
else if (bucket >= BLK_MQ_POLL_STATS_BKTS)
return ddir + BLK_MQ_POLL_STATS_BKTS - 2;
return bucket;
}
/*
* Check if any of the ctx, dispatch list or elevator
* have pending work in this hardware queue.
*/
static bool blk_mq_hctx_has_pending(struct blk_mq_hw_ctx *hctx)
{
return !list_empty_careful(&hctx->dispatch) ||
sbitmap_any_bit_set(&hctx->ctx_map) ||
blk_mq_sched_has_work(hctx);
}
/*
* Mark this ctx as having pending work in this hardware queue
*/
static void blk_mq_hctx_mark_pending(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx)
{
const int bit = ctx->index_hw[hctx->type];
if (!sbitmap_test_bit(&hctx->ctx_map, bit))
sbitmap_set_bit(&hctx->ctx_map, bit);
}
static void blk_mq_hctx_clear_pending(struct blk_mq_hw_ctx *hctx,
struct blk_mq_ctx *ctx)
{
const int bit = ctx->index_hw[hctx->type];
sbitmap_clear_bit(&hctx->ctx_map, bit);
}
struct mq_inflight {
struct hd_struct *part;
unsigned int *inflight;
};
static bool blk_mq_check_inflight(struct blk_mq_hw_ctx *hctx,
struct request *rq, void *priv,
bool reserved)
{
struct mq_inflight *mi = priv;
/*
* index[0] counts the specific partition that was asked for.
*/
if (rq->part == mi->part)
mi->inflight[0]++;
return true;
}
unsigned int blk_mq_in_flight(struct request_queue *q, struct hd_struct *part)
{
unsigned inflight[2];
struct mq_inflight mi = { .part = part, .inflight = inflight, };
inflight[0] = inflight[1] = 0;
blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight, &mi);
return inflight[0];
}
static bool blk_mq_check_inflight_rw(struct blk_mq_hw_ctx *hctx,
struct request *rq, void *priv,
bool reserved)
{
struct mq_inflight *mi = priv;
if (rq->part == mi->part)
mi->inflight[rq_data_dir(rq)]++;
return true;
}
void blk_mq_in_flight_rw(struct request_queue *q, struct hd_struct *part,
unsigned int inflight[2])
{
struct mq_inflight mi = { .part = part, .inflight = inflight, };
inflight[0] = inflight[1] = 0;
blk_mq_queue_tag_busy_iter(q, blk_mq_check_inflight_rw, &mi);
}
void blk_freeze_queue_start(struct request_queue *q)
{
mutex_lock(&q->mq_freeze_lock);
if (++q->mq_freeze_depth == 1) {
percpu_ref_kill(&q->q_usage_counter);
mutex_unlock(&q->mq_freeze_lock);
if (queue_is_mq(q))
blk_mq_run_hw_queues(q, false);
} else {
mutex_unlock(&q->mq_freeze_lock);
}
}
EXPORT_SYMBOL_GPL(blk_freeze_queue_start);
void blk_mq_freeze_queue_wait(struct request_queue *q)
{
wait_event(q->mq_freeze_wq, percpu_ref_is_zero(&q->q_usage_counter));
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait);
int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
unsigned long timeout)
{
return wait_event_timeout(q->mq_freeze_wq,
percpu_ref_is_zero(&q->q_usage_counter),
timeout);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue_wait_timeout);
/*
* Guarantee no request is in use, so we can change any data structure of
* the queue afterward.
*/
void blk_freeze_queue(struct request_queue *q)
{
/*
* In the !blk_mq case we are only calling this to kill the
* q_usage_counter, otherwise this increases the freeze depth
* and waits for it to return to zero. For this reason there is
* no blk_unfreeze_queue(), and blk_freeze_queue() is not
* exported to drivers as the only user for unfreeze is blk_mq.
*/
blk_freeze_queue_start(q);
blk_mq_freeze_queue_wait(q);
}
void blk_mq_freeze_queue(struct request_queue *q)
{
/*
* ...just an alias to keep freeze and unfreeze actions balanced
* in the blk_mq_* namespace
*/
blk_freeze_queue(q);
}
EXPORT_SYMBOL_GPL(blk_mq_freeze_queue);
void blk_mq_unfreeze_queue(struct request_queue *q)
{
mutex_lock(&q->mq_freeze_lock);
q->mq_freeze_depth--;
WARN_ON_ONCE(q->mq_freeze_depth < 0);
if (!q->mq_freeze_depth) {
percpu_ref_resurrect(&q->q_usage_counter);
wake_up_all(&q->mq_freeze_wq);
}
mutex_unlock(&q->mq_freeze_lock);
}
EXPORT_SYMBOL_GPL(blk_mq_unfreeze_queue);
/*
* FIXME: replace the scsi_internal_device_*block_nowait() calls in the
* mpt3sas driver such that this function can be removed.
*/
void blk_mq_quiesce_queue_nowait(struct request_queue *q)
{
blk_queue_flag_set(QUEUE_FLAG_QUIESCED, q);
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue_nowait);
/**
* blk_mq_quiesce_queue() - wait until all ongoing dispatches have finished
* @q: request queue.
*
* Note: this function does not prevent that the struct request end_io()
* callback function is invoked. Once this function is returned, we make
* sure no dispatch can happen until the queue is unquiesced via
* blk_mq_unquiesce_queue().
*/
void blk_mq_quiesce_queue(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned int i;
bool rcu = false;
blk_mq_quiesce_queue_nowait(q);
queue_for_each_hw_ctx(q, hctx, i) {
if (hctx->flags & BLK_MQ_F_BLOCKING)
synchronize_srcu(hctx->srcu);
else
rcu = true;
}
if (rcu)
synchronize_rcu();
}
EXPORT_SYMBOL_GPL(blk_mq_quiesce_queue);
/*
* blk_mq_unquiesce_queue() - counterpart of blk_mq_quiesce_queue()
* @q: request queue.
*
* This function recovers queue into the state before quiescing
* which is done by blk_mq_quiesce_queue.
*/
void blk_mq_unquiesce_queue(struct request_queue *q)
{
blk_queue_flag_clear(QUEUE_FLAG_QUIESCED, q);
/* dispatch requests which are inserted during quiescing */
blk_mq_run_hw_queues(q, true);
}
EXPORT_SYMBOL_GPL(blk_mq_unquiesce_queue);
void blk_mq_wake_waiters(struct request_queue *q)
{
struct blk_mq_hw_ctx *hctx;
unsigned int i;
queue_for_each_hw_ctx(q, hctx, i)
if (blk_mq_hw_queue_mapped(hctx))
blk_mq_tag_wakeup_all(hctx->tags, true);
}
bool blk_mq_can_queue(struct blk_mq_hw_ctx *hctx)
{
return blk_mq_has_free_tags(hctx->tags);
}
EXPORT_SYMBOL(blk_mq_can_queue);
/*
* Only need start/end time stamping if we have stats enabled, or using
* an IO scheduler.
*/
static inline bool blk_mq_need_time_stamp(struct request *rq)
{
return (rq->rq_flags & RQF_IO_STAT) || rq->q->elevator;
}
static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data,
unsigned int tag, unsigned int op)
{
struct blk_mq_tags *tags = blk_mq_tags_from_data(data);
struct request *rq = tags->static_rqs[tag];
req_flags_t rq_flags = 0;
if (data->flags & BLK_MQ_REQ_INTERNAL) {
rq->tag = -1;
rq->internal_tag = tag;
} else {
if (data->hctx->flags & BLK_MQ_F_TAG_SHARED) {
rq_flags = RQF_MQ_INFLIGHT;
atomic_inc(&data->hctx->nr_active);
}
rq->tag = tag;
rq->internal_tag = -1;
data->hctx->tags->rqs[rq->tag] = rq;
}
/* csd/requeue_work/fifo_time is initialized before use */
rq->q = data->q;
rq->mq_ctx = data->ctx;
rq->mq_hctx = data->hctx;
rq->rq_flags = rq_flags;
rq->cmd_flags = op;
if (data->flags & BLK_MQ_REQ_PREEMPT)
rq->rq_flags |= RQF_PREEMPT;
if (blk_queue_io_stat(data->q))
rq->rq_flags |= RQF_IO_STAT;
INIT_LIST_HEAD(&rq->queuelist);
INIT_HLIST_NODE(&rq->hash);
RB_CLEAR_NODE(&rq->rb_node);
rq->rq_disk = NULL;
rq->part = NULL;
if (blk_mq_need_time_stamp(rq))
rq->start_time_ns = ktime_get_ns();
else
rq->start_time_ns = 0;
rq->io_start_time_ns = 0;
rq->nr_phys_segments = 0;
#if defined(CONFIG_BLK_DEV_INTEGRITY)
rq->nr_integrity_segments = 0;
#endif
/* tag was already set */
rq->extra_len = 0;
WRITE_ONCE(rq->deadline, 0);
rq->timeout = 0;
rq->end_io = NULL;
rq->end_io_data = NULL;
data->ctx->rq_dispatched[op_is_sync(op)]++;
refcount_set(&rq->ref, 1);
return rq;
}
static struct request *blk_mq_get_request(struct request_queue *q,
struct bio *bio,
struct blk_mq_alloc_data *data)
{
struct elevator_queue *e = q->elevator;
struct request *rq;
unsigned int tag;
bool put_ctx_on_error = false;
blk_queue_enter_live(q);
data->q = q;
if (likely(!data->ctx)) {
data->ctx = blk_mq_get_ctx(q);
put_ctx_on_error = true;
}
if (likely(!data->hctx))
data->hctx = blk_mq_map_queue(q, data->cmd_flags,
data->ctx);
if (data->cmd_flags & REQ_NOWAIT)
data->flags |= BLK_MQ_REQ_NOWAIT;
if (e) {
data->flags |= BLK_MQ_REQ_INTERNAL;
/*
* Flush requests are special and go directly to the
* dispatch list. Don't include reserved tags in the
* limiting, as it isn't useful.
*/
if (!op_is_flush(data->cmd_flags) &&
e->type->ops.limit_depth &&
!(data->flags & BLK_MQ_REQ_RESERVED))
e->type->ops.limit_depth(data->cmd_flags, data);
} else {
blk_mq_tag_busy(data->hctx);
}
tag = blk_mq_get_tag(data);
if (tag == BLK_MQ_TAG_FAIL) {
if (put_ctx_on_error) {
blk_mq_put_ctx(data->ctx);
data->ctx = NULL;
}
blk_queue_exit(q);
return NULL;
}
rq = blk_mq_rq_ctx_init(data, tag, data->cmd_flags);
if (!op_is_flush(data->cmd_flags)) {
rq->elv.icq = NULL;
if (e && e->type->ops.prepare_request) {
if (e->type->icq_cache)
blk_mq_sched_assign_ioc(rq);
e->type->ops.prepare_request(rq, bio);
rq->rq_flags |= RQF_ELVPRIV;
}
}
data->hctx->queued++;
return rq;
}
struct request *blk_mq_alloc_request(struct request_queue *q, unsigned int op,
blk_mq_req_flags_t flags)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op };
struct request *rq;
int ret;
ret = blk_queue_enter(q, flags);
if (ret)
return ERR_PTR(ret);
rq = blk_mq_get_request(q, NULL, &alloc_data);
blk_queue_exit(q);
if (!rq)
return ERR_PTR(-EWOULDBLOCK);
blk_mq_put_ctx(alloc_data.ctx);
rq->__data_len = 0;
rq->__sector = (sector_t) -1;
rq->bio = rq->biotail = NULL;
return rq;
}
EXPORT_SYMBOL(blk_mq_alloc_request);
struct request *blk_mq_alloc_request_hctx(struct request_queue *q,
unsigned int op, blk_mq_req_flags_t flags, unsigned int hctx_idx)
{
struct blk_mq_alloc_data alloc_data = { .flags = flags, .cmd_flags = op };
struct request *rq;
unsigned int cpu;
int ret;
/*
* If the tag allocator sleeps we could get an allocation for a
* different hardware context. No need to complicate the low level
* allocator for this for the rare use case of a command tied to
* a specific queue.
*/
if (WARN_ON_ONCE(!(flags & BLK_MQ_REQ_NOWAIT)))
return ERR_PTR(-EINVAL);
if (hctx_idx >= q->nr_hw_queues)
return ERR_PTR(-EIO);
ret = blk_queue_enter(q, flags);
if (ret)
return ERR_PTR(ret);
/*
* Check if the hardware context is actually mapped to anything.
* If not tell the caller that it should skip this queue.
*/
alloc_data.hctx = q->queue_hw_ctx[hctx_idx];
if (!blk_mq_hw_queue_mapped(alloc_data.hctx)) {
blk_queue_exit(q);
return ERR_PTR(-EXDEV);
}
cpu = cpumask_first_and(alloc_data.hctx->cpumask, cpu_online_mask);
alloc_data.ctx = __blk_mq_get_ctx(q, cpu);
rq = blk_mq_get_request(q, NULL, &alloc_data);
blk_queue_exit(q);
if (!rq)
return ERR_PTR(-EWOULDBLOCK);
return rq;
}
EXPORT_SYMBOL_GPL(blk_mq_alloc_request_hctx);
static void __blk_mq_free_request(struct request *rq)
{
struct request_queue *q = rq->q;
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
const int sched_tag = rq->internal_tag;
blk_pm_mark_last_busy(rq);
rq->mq_hctx = NULL;
if (rq->tag != -1)
blk_mq_put_tag(hctx, hctx->tags, ctx, rq->tag);
if (sched_tag != -1)
blk_mq_put_tag(hctx, hctx->sched_tags, ctx, sched_tag);
blk_mq_sched_restart(hctx);
blk_queue_exit(q);
}
void blk_mq_free_request(struct request *rq)
{
struct request_queue *q = rq->q;
struct elevator_queue *e = q->elevator;
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct blk_mq_hw_ctx *hctx = rq->mq_hctx;
if (rq->rq_flags & RQF_ELVPRIV) {
if (e && e->type->ops.finish_request)
e->type->ops.finish_request(rq);
if (rq->elv.icq) {
put_io_context(rq->elv.icq->ioc);
rq->elv.icq = NULL;
}
}
ctx->rq_completed[rq_is_sync(rq)]++;
if (rq->rq_flags & RQF_MQ_INFLIGHT)
atomic_dec(&hctx->nr_active);
if (unlikely(laptop_mode && !blk_rq_is_passthrough(rq)))
laptop_io_completion(q->backing_dev_info);
rq_qos_done(q, rq);
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
if (refcount_dec_and_test(&rq->ref))
__blk_mq_free_request(rq);
}
EXPORT_SYMBOL_GPL(blk_mq_free_request);
inline void __blk_mq_end_request(struct request *rq, blk_status_t error)
{
u64 now = 0;
if (blk_mq_need_time_stamp(rq))
now = ktime_get_ns();
if (rq->rq_flags & RQF_STATS) {
blk_mq_poll_stats_start(rq->q);
blk_stat_add(rq, now);
}
if (rq->internal_tag != -1)
blk_mq_sched_completed_request(rq, now);
blk_account_io_done(rq, now);
if (rq->end_io) {
rq_qos_done(rq->q, rq);
rq->end_io(rq, error);
} else {
blk_mq_free_request(rq);
}
}
EXPORT_SYMBOL(__blk_mq_end_request);
void blk_mq_end_request(struct request *rq, blk_status_t error)
{
if (blk_update_request(rq, error, blk_rq_bytes(rq)))
BUG();
__blk_mq_end_request(rq, error);
}
EXPORT_SYMBOL(blk_mq_end_request);
static void __blk_mq_complete_request_remote(void *data)
{
struct request *rq = data;
struct request_queue *q = rq->q;
q->mq_ops->complete(rq);
}
static void __blk_mq_complete_request(struct request *rq)
{
struct blk_mq_ctx *ctx = rq->mq_ctx;
struct request_queue *q = rq->q;
bool shared = false;
int cpu;
WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
/*
* Most of single queue controllers, there is only one irq vector
* for handling IO completion, and the only irq's affinity is set
* as all possible CPUs. On most of ARCHs, this affinity means the
* irq is handled on one specific CPU.
*
* So complete IO reqeust in softirq context in case of single queue
* for not degrading IO performance by irqsoff latency.
*/
if (q->nr_hw_queues == 1) {
__blk_complete_request(rq);
return;
}
/*
* For a polled request, always complete locallly, it's pointless
* to redirect the completion.
*/
if ((rq->cmd_flags & REQ_HIPRI) ||
!test_bit(QUEUE_FLAG_SAME_COMP, &q->queue_flags)) {
q->mq_ops->complete(rq);
return;
}
cpu = get_cpu();
if (!test_bit(QUEUE_FLAG_SAME_FORCE, &q->queue_flags))
shared = cpus_share_cache(cpu, ctx->cpu);
if (cpu != ctx->cpu && !shared && cpu_online(ctx->cpu)) {
rq->csd.func = __blk_mq_complete_request_remote;
rq->csd.info = rq;
rq->csd.flags = 0;
smp_call_function_single_async(ctx->cpu, &rq->csd);
} else {
q->mq_ops->complete(rq);
}
put_cpu();
}
static void hctx_unlock(struct blk_mq_hw_ctx *hctx, int srcu_idx)
__releases(hctx->srcu)
{
if (!(hctx->flags & BLK_MQ_F_BLOCKING))
rcu_read_unlock();
else
srcu_read_unlock(hctx->srcu, srcu_idx);
}
static void hctx_lock(struct blk_mq_hw_ctx *hctx, int *srcu_idx)
__acquires(hctx->srcu)
{
if (!(hctx->flags & BLK_MQ_F_BLOCKING)) {
/* shut up gcc false positive */
*srcu_idx = 0;
rcu_read_lock();
} else
*srcu_idx = srcu_read_lock(hctx->srcu);
}
/**
* blk_mq_complete_request - end I/O on a request
* @rq: the request being processed
*
* Description:
* Ends all I/O on a request. It does not handle partial completions.
* The actual completion happens out-of-order, through a IPI handler.
**/
bool blk_mq_complete_request(struct request *rq)
{
if (unlikely(blk_should_fake_timeout(rq->q)))
return false;
__blk_mq_complete_request(rq);
return true;
}
EXPORT_SYMBOL(blk_mq_complete_request);
void blk_mq_complete_request_sync(struct request *rq)
{
WRITE_ONCE(rq->state, MQ_RQ_COMPLETE);
rq->q->mq_ops->complete(rq);
}
EXPORT_SYMBOL_GPL(blk_mq_complete_request_sync);
int blk_mq_request_started(struct request *rq)
{
return blk_mq_rq_state(rq) != MQ_RQ_IDLE;
}
EXPORT_SYMBOL_GPL(blk_mq_request_started);
void blk_mq_start_request(struct request *rq)
{
struct request_queue *q = rq->q;
blk_mq_sched_started_request(rq);
trace_block_rq_issue(q, rq);
if (test_bit(QUEUE_FLAG_STATS, &q->queue_flags)) {
rq->io_start_time_ns = ktime_get_ns();
#ifdef CONFIG_BLK_DEV_THROTTLING_LOW
rq->throtl_size = blk_rq_sectors(rq);
#endif
rq->rq_flags |= RQF_STATS;
rq_qos_issue(q, rq);
}
WARN_ON_ONCE(blk_mq_rq_state(rq) != MQ_RQ_IDLE);
blk_add_timer(rq);
WRITE_ONCE(rq->state, MQ_RQ_IN_FLIGHT);
if (q->dma_drain_size && blk_rq_bytes(rq)) {
/*
* Make sure space for the drain appears. We know we can do
* this because max_hw_segments has been adjusted to be one
* fewer than the device can handle.
*/
rq->nr_phys_segments++;
}
}
EXPORT_SYMBOL(blk_mq_start_request);
static void __blk_mq_requeue_request(struct request *rq)
{
struct request_queue *q = rq->q;
blk_mq_put_driver_tag(rq);
trace_block_rq_requeue(q, rq);
rq_qos_requeue(q, rq);
if (blk_mq_request_started(rq)) {
WRITE_ONCE(rq->state, MQ_RQ_IDLE);
rq->rq_flags &= ~RQF_TIMED_OUT;
if (q->dma_drain_size && blk_rq_bytes(rq))
rq->nr_phys_segments--;
}
}
void blk_mq_requeue_request(struct request *rq, bool kick_requeue_list)
{
__blk_mq_requeue_request(rq);
/* this request will be re-inserted to io scheduler queue */
blk_mq_sched_requeue_request(rq);
BUG_ON(!list_empty(&rq->queuelist));
blk_mq_add_to_requeue_list(rq, true, kick_requeue_list);
}
EXPORT_SYMBOL(blk_mq_requeue_request);
static void blk_mq_requeue_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, requeue_work.work);
LIST_HEAD(rq_list);
struct request *rq, *next;
spin_lock_irq(&q->requeue_lock);
list_splice_init(&q->requeue_list, &rq_list);
spin_unlock_irq(&q->requeue_lock);
list_for_each_entry_safe(rq, next, &rq_list, queuelist) {
if (!(rq->rq_flags & (RQF_SOFTBARRIER | RQF_DONTPREP)))
continue;
rq->rq_flags &= ~RQF_SOFTBARRIER;
list_del_init(&rq->queuelist);
/*
* If RQF_DONTPREP, rq has contained some driver specific
* data, so insert it to hctx dispatch list to avoid any
* merge.
*/
if (rq->rq_flags & RQF_DONTPREP)
blk_mq_request_bypass_insert(rq, false);
else
blk_mq_sched_insert_request(rq, true, false, false);
}
while (!list_empty(&rq_list)) {
rq = list_entry(rq_list.next, struct request, queuelist);
list_del_init(&rq->queuelist);
blk_mq_sched_insert_request(rq, false, false, false);
}
blk_mq_run_hw_queues(q, false);
}
void blk_mq_add_to_requeue_list(struct request *rq, bool at_head,
bool kick_requeue_list)
{
struct request_queue *q = rq->q;
unsigned long flags;
/*
* We abuse this flag that is otherwise used by the I/O scheduler to
* request head insertion from the workqueue.
*/
BUG_ON(rq->rq_flags & RQF_SOFTBARRIER);
spin_lock_irqsave(&q->requeue_lock, flags);
if (at_head) {
rq->rq_flags |= RQF_SOFTBARRIER;
list_add(&rq->queuelist, &q->requeue_list);
} else {
list_add_tail(&rq->queuelist, &q->requeue_list);
}
spin_unlock_irqrestore(&q->requeue_lock, flags);
if (kick_requeue_list)
blk_mq_kick_requeue_list(q);
}
void blk_mq_kick_requeue_list(struct request_queue *q)
{
kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work, 0);
}
EXPORT_SYMBOL(blk_mq_kick_requeue_list);
void blk_mq_delay_kick_requeue_list(struct request_queue *q,
unsigned long msecs)
{
kblockd_mod_delayed_work_on(WORK_CPU_UNBOUND, &q->requeue_work,
msecs_to_jiffies(msecs));
}
EXPORT_SYMBOL(blk_mq_delay_kick_requeue_list);
struct request *blk_mq_tag_to_rq(struct blk_mq_tags *tags, unsigned int tag)
{
if (tag < tags->nr_tags) {
prefetch(tags->rqs[tag]);
return tags->rqs[tag];
}
return NULL;
}
EXPORT_SYMBOL(blk_mq_tag_to_rq);
static bool blk_mq_rq_inflight(struct blk_mq_hw_ctx *hctx, struct request *rq,
void *priv, bool reserved)
{
/*
* If we find a request that is inflight and the queue matches,
* we know the queue is busy. Return false to stop the iteration.
*/
if (rq->state == MQ_RQ_IN_FLIGHT && rq->q == hctx->queue) {
bool *busy = priv;
*busy = true;
return false;
}
return true;
}
bool blk_mq_queue_inflight(struct request_queue *q)
{
bool busy = false;
blk_mq_queue_tag_busy_iter(q, blk_mq_rq_inflight, &busy);
return busy;
}
EXPORT_SYMBOL_GPL(blk_mq_queue_inflight);
static void blk_mq_rq_timed_out(struct request *req, bool reserved)
{
req->rq_flags |= RQF_TIMED_OUT;
if (req->q->mq_ops->timeout) {
enum blk_eh_timer_return ret;
ret = req->q->mq_ops->timeout(req, reserved);
if (ret == BLK_EH_DONE)
return;
WARN_ON_ONCE(ret != BLK_EH_RESET_TIMER);
}
blk_add_timer(req);
}
static bool blk_mq_req_expired(struct request *rq, unsigned long *next)
{
unsigned long deadline;
if (blk_mq_rq_state(rq) != MQ_RQ_IN_FLIGHT)
return false;
if (rq->rq_flags & RQF_TIMED_OUT)
return false;
deadline = READ_ONCE(rq->deadline);
if (time_after_eq(jiffies, deadline))
return true;
if (*next == 0)
*next = deadline;
else if (time_after(*next, deadline))
*next = deadline;
return false;
}
static bool blk_mq_check_expired(struct blk_mq_hw_ctx *hctx,
struct request *rq, void *priv, bool reserved)
{
unsigned long *next = priv;
/*
* Just do a quick check if it is expired before locking the request in
* so we're not unnecessarilly synchronizing across CPUs.
*/
if (!blk_mq_req_expired(rq, next))
return true;
/*
* We have reason to believe the request may be expired. Take a
* reference on the request to lock this request lifetime into its
* currently allocated context to prevent it from being reallocated in
* the event the completion by-passes this timeout handler.
*
* If the reference was already released, then the driver beat the
* timeout handler to posting a natural completion.
*/
if (!refcount_inc_not_zero(&rq->ref))
return true;
/*
* The request is now locked and cannot be reallocated underneath the
* timeout handler's processing. Re-verify this exact request is truly
* expired; if it is not expired, then the request was completed and
* reallocated as a new request.
*/
if (blk_mq_req_expired(rq, next))
blk_mq_rq_timed_out(rq, reserved);
if (refcount_dec_and_test(&rq->ref))
__blk_mq_free_request(rq);
return true;
}
static void blk_mq_timeout_work(struct work_struct *work)
{
struct request_queue *q =
container_of(work, struct request_queue, timeout_work);
unsigned long next = 0;
struct blk_mq_hw_ctx *hctx;
int i;
/* A deadlock might occur if a request is stuck requiring a
* timeout at the same time a queue freeze is waiting
* completion, since the timeout code would not be able to
* acquire the queue reference here.
*
* That's why we don't use blk_queue_enter here; instead, we use
* percpu_ref_tryget directly, because we need to be able to
* obtain a reference even in the short window between the queue
* starting to freeze, by dropping the first reference in
* blk_freeze_queue_start, and the moment the last request is
* consumed, marked by the instant q_usage_counter reaches
* zero.
*/
if (!percpu_ref_tryget(&q->q_usage_counter))
return;
blk_mq_queue_tag_busy_iter(q, blk_mq_check_expired, &next);
if (next != 0) {
mod_timer(&q->timeout, next);
} else {
/*
* Request timeouts are handled as a forward rolling timer. If
* we end up here it means that no requests are pending and
* also that no request has been pending for a while. Mark
* each hctx as idle.
*/
queue_for_each_hw_ctx(q, hctx, i) {
/* the hctx may be unmapped, so check it here */
if (blk_mq_hw_queue_mapped(hctx))
blk_mq_tag_idle(hctx);
}
}
blk_queue_exit(q);
}
struct flush_busy_ctx_data {
struct blk_mq_hw_ctx *hctx;
struct list_head *list;
};
static bool flush_busy_ctx(struct sbitmap *sb, unsigned int bitnr, void *data)
{
struct flush_busy_ctx_data *flush_data = data;
struct blk_mq_hw_ctx *hctx = flush_data->hctx;
struct blk_mq_ctx *ctx = hctx->ctxs[bitnr];
enum hctx_type type = hctx->type;
spin_lock(&ctx->lock);
list_splice_tail_init(&ctx->rq_lists[type], flush_data->list);
sbitmap_clear_bit(sb, bitnr);
spin_unlock(&ctx->lock);
return true;
}
/*
* Process software queues that have been marked busy, splicing them
* to the for-dispatch
*/
void blk_mq_flush_busy_ctxs(struct blk_mq_hw_ctx *hctx, struct list_head *list)
{
struct flush_busy_ctx_data data = {
.hctx = hctx,
.list = list,
};
sbitmap_for_each_set(&hctx->ctx_map, flush_busy_ctx, &data);
}
EXPORT_SYMBOL_GPL(blk_mq_flush_busy_ctxs);
struct dispatch_rq_data {
struct blk_mq_hw_ctx *hctx;
struct request *rq;