summaryrefslogtreecommitdiffstats
path: root/drivers/md/dm-rq.c
blob: eadfcfd106ffffa4773421d5b61ae77414e36d6d (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
/*
 * Copyright (C) 2016 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm-core.h"
#include "dm-rq.h"

#include <linux/elevator.h> /* for rq_end_sector() */
#include <linux/blk-mq.h>

#define DM_MSG_PREFIX "core-rq"

#define DM_MQ_NR_HW_QUEUES 1
#define DM_MQ_QUEUE_DEPTH 2048
static unsigned dm_mq_nr_hw_queues = DM_MQ_NR_HW_QUEUES;
static unsigned dm_mq_queue_depth = DM_MQ_QUEUE_DEPTH;

/*
 * Request-based DM's mempools' reserved IOs set by the user.
 */
#define RESERVED_REQUEST_BASED_IOS	256
static unsigned reserved_rq_based_ios = RESERVED_REQUEST_BASED_IOS;

static bool use_blk_mq = IS_ENABLED(CONFIG_DM_MQ_DEFAULT);

bool dm_use_blk_mq_default(void)
{
	return use_blk_mq;
}

bool dm_use_blk_mq(struct mapped_device *md)
{
	return md->use_blk_mq;
}
EXPORT_SYMBOL_GPL(dm_use_blk_mq);

unsigned dm_get_reserved_rq_based_ios(void)
{
	return __dm_get_module_param(&reserved_rq_based_ios,
				     RESERVED_REQUEST_BASED_IOS, DM_RESERVED_MAX_IOS);
}
EXPORT_SYMBOL_GPL(dm_get_reserved_rq_based_ios);

static unsigned dm_get_blk_mq_nr_hw_queues(void)
{
	return __dm_get_module_param(&dm_mq_nr_hw_queues, 1, 32);
}

static unsigned dm_get_blk_mq_queue_depth(void)
{
	return __dm_get_module_param(&dm_mq_queue_depth,
				     DM_MQ_QUEUE_DEPTH, BLK_MQ_MAX_DEPTH);
}

int dm_request_based(struct mapped_device *md)
{
	return blk_queue_stackable(md->queue);
}

static void dm_old_start_queue(struct request_queue *q)
{
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	if (blk_queue_stopped(q))
		blk_start_queue(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

static void dm_mq_start_queue(struct request_queue *q)
{
	blk_mq_unquiesce_queue(q);
	blk_mq_kick_requeue_list(q);
}

void dm_start_queue(struct request_queue *q)
{
	if (!q->mq_ops)
		dm_old_start_queue(q);
	else
		dm_mq_start_queue(q);
}

static void dm_old_stop_queue(struct request_queue *q)
{
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	if (!blk_queue_stopped(q))
		blk_stop_queue(q);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

static void dm_mq_stop_queue(struct request_queue *q)
{
	if (blk_mq_queue_stopped(q))
		return;

	blk_mq_quiesce_queue(q);
}

void dm_stop_queue(struct request_queue *q)
{
	if (!q->mq_ops)
		dm_old_stop_queue(q);
	else
		dm_mq_stop_queue(q);
}

/*
 * Partial completion handling for request-based dm
 */
static void end_clone_bio(struct bio *clone)
{
	struct dm_rq_clone_bio_info *info =
		container_of(clone, struct dm_rq_clone_bio_info, clone);
	struct dm_rq_target_io *tio = info->tio;
	unsigned int nr_bytes = info->orig->bi_iter.bi_size;
	blk_status_t error = clone->bi_status;
	bool is_last = !clone->bi_next;

	bio_put(clone);

	if (tio->error)
		/*
		 * An error has already been detected on the request.
		 * Once error occurred, just let clone->end_io() handle
		 * the remainder.
		 */
		return;
	else if (error) {
		/*
		 * Don't notice the error to the upper layer yet.
		 * The error handling decision is made by the target driver,
		 * when the request is completed.
		 */
		tio->error = error;
		goto exit;
	}

	/*
	 * I/O for the bio successfully completed.
	 * Notice the data completion to the upper layer.
	 */
	tio->completed += nr_bytes;

	/*
	 * Update the original request.
	 * Do not use blk_end_request() here, because it may complete
	 * the original request before the clone, and break the ordering.
	 */
	if (is_last)
 exit:
		blk_update_request(tio->orig, BLK_STS_OK, tio->completed);
}

static struct dm_rq_target_io *tio_from_request(struct request *rq)
{
	return blk_mq_rq_to_pdu(rq);
}

static void rq_end_stats(struct mapped_device *md, struct request *orig)
{
	if (unlikely(dm_stats_used(&md->stats))) {
		struct dm_rq_target_io *tio = tio_from_request(orig);
		tio->duration_jiffies = jiffies - tio->duration_jiffies;
		dm_stats_account_io(&md->stats, rq_data_dir(orig),
				    blk_rq_pos(orig), tio->n_sectors, true,
				    tio->duration_jiffies, &tio->stats_aux);
	}
}

/*
 * Don't touch any member of the md after calling this function because
 * the md may be freed in dm_put() at the end of this function.
 * Or do dm_get() before calling this function and dm_put() later.
 */
static void rq_completed(struct mapped_device *md, int rw, bool run_queue)
{
	struct request_queue *q = md->queue;
	unsigned long flags;

	atomic_dec(&md->pending[rw]);

	/* nudge anyone waiting on suspend queue */
	if (!md_in_flight(md))
		wake_up(&md->wait);

	/*
	 * Run this off this callpath, as drivers could invoke end_io while
	 * inside their request_fn (and holding the queue lock). Calling
	 * back into ->request_fn() could deadlock attempting to grab the
	 * queue lock again.
	 */
	if (!q->mq_ops && run_queue) {
		spin_lock_irqsave(q->queue_lock, flags);
		blk_run_queue_async(q);
		spin_unlock_irqrestore(q->queue_lock, flags);
	}

	/*
	 * dm_put() must be at the end of this function. See the comment above
	 */
	dm_put(md);
}

/*
 * Complete the clone and the original request.
 * Must be called without clone's queue lock held,
 * see end_clone_request() for more details.
 */
static void dm_end_request(struct request *clone, blk_status_t error)
{
	int rw = rq_data_dir(clone);
	struct dm_rq_target_io *tio = clone->end_io_data;
	struct mapped_device *md = tio->md;
	struct request *rq = tio->orig;

	blk_rq_unprep_clone(clone);
	tio->ti->type->release_clone_rq(clone);

	rq_end_stats(md, rq);
	if (!rq->q->mq_ops)
		blk_end_request_all(rq, error);
	else
		blk_mq_end_request(rq, error);
	rq_completed(md, rw, true);
}

/*
 * Requeue the original request of a clone.
 */
static void dm_old_requeue_request(struct request *rq, unsigned long delay_ms)
{
	struct request_queue *q = rq->q;
	unsigned long flags;

	spin_lock_irqsave(q->queue_lock, flags);
	blk_requeue_request(q, rq);
	blk_delay_queue(q, delay_ms);
	spin_unlock_irqrestore(q->queue_lock, flags);
}

static void __dm_mq_kick_requeue_list(struct request_queue *q, unsigned long msecs)
{
	blk_mq_delay_kick_requeue_list(q, msecs);
}

void dm_mq_kick_requeue_list(struct mapped_device *md)
{
	__dm_mq_kick_requeue_list(dm_get_md_queue(md), 0);
}
EXPORT_SYMBOL(dm_mq_kick_requeue_list);

static void dm_mq_delay_requeue_request(struct request *rq, unsigned long msecs)
{
	blk_mq_requeue_request(rq, false);
	__dm_mq_kick_requeue_list(rq->q, msecs);
}

static void dm_requeue_original_request(struct dm_rq_target_io *tio, bool delay_requeue)
{
	struct mapped_device *md = tio->md;
	struct request *rq = tio->orig;
	int rw = rq_data_dir(rq);
	unsigned long delay_ms = delay_requeue ? 100 : 0;

	rq_end_stats(md, rq);
	if (tio->clone) {
		blk_rq_unprep_clone(tio->clone);
		tio->ti->type->release_clone_rq(tio->clone);
	}

	if (!rq->q->mq_ops)
		dm_old_requeue_request(rq, delay_ms);
	else
		dm_mq_delay_requeue_request(rq, delay_ms);

	rq_completed(md, rw, false);
}

static void dm_done(struct request *clone, blk_status_t error, bool mapped)
{
	int r = DM_ENDIO_DONE;
	struct dm_rq_target_io *tio = clone->end_io_data;
	dm_request_endio_fn rq_end_io = NULL;

	if (tio->ti) {
		rq_end_io = tio->ti->type->rq_end_io;

		if (mapped && rq_end_io)
			r = rq_end_io(tio->ti, clone, error, &tio->info);
	}

	if (unlikely(error == BLK_STS_TARGET)) {
		if (req_op(clone) == REQ_OP_WRITE_SAME &&
		    !clone->q->limits.max_write_same_sectors)
			disable_write_same(tio->md);
		if (req_op(clone) == REQ_OP_WRITE_ZEROES &&
		    !clone->q->limits.max_write_zeroes_sectors)
			disable_write_zeroes(tio->md);
	}

	switch (r) {
	case DM_ENDIO_DONE:
		/* The target wants to complete the I/O */
		dm_end_request(clone, error);
		break;
	case DM_ENDIO_INCOMPLETE:
		/* The target will handle the I/O */
		return;
	case DM_ENDIO_REQUEUE:
		/* The target wants to requeue the I/O */
		dm_requeue_original_request(tio, false);
		break;
	default:
		DMWARN("unimplemented target endio return value: %d", r);
		BUG();
	}
}

/*
 * Request completion handler for request-based dm
 */
static void dm_softirq_done(struct request *rq)
{
	bool mapped = true;
	struct dm_rq_target_io *tio = tio_from_request(rq);
	struct request *clone = tio->clone;
	int rw;

	if (!clone) {
		struct mapped_device *md = tio->md;

		rq_end_stats(md, rq);
		rw = rq_data_dir(rq);
		if (!rq->q->mq_ops)
			blk_end_request_all(rq, tio->error);
		else
			blk_mq_end_request(rq, tio->error);
		rq_completed(md, rw, false);
		return;
	}

	if (rq->rq_flags & RQF_FAILED)
		mapped = false;

	dm_done(clone, tio->error, mapped);
}

/*
 * Complete the clone and the original request with the error status
 * through softirq context.
 */
static void dm_complete_request(struct request *rq, blk_status_t error)
{
	struct dm_rq_target_io *tio = tio_from_request(rq);

	tio->error = error;
	if (!rq->q->mq_ops)
		blk_complete_request(rq);
	else
		blk_mq_complete_request(rq);
}

/*
 * Complete the not-mapped clone and the original request with the error status
 * through softirq context.
 * Target's rq_end_io() function isn't called.
 * This may be used when the target's map_rq() or clone_and_map_rq() functions fail.
 */
static void dm_kill_unmapped_request(struct request *rq, blk_status_t error)
{
	rq->rq_flags |= RQF_FAILED;
	dm_complete_request(rq, error);
}

/*
 * Called with the clone's queue lock held (in the case of .request_fn)
 */
static void end_clone_request(struct request *clone, blk_status_t error)
{
	struct dm_rq_target_io *tio = clone->end_io_data;

	/*
	 * Actual request completion is done in a softirq context which doesn't
	 * hold the clone's queue lock.  Otherwise, deadlock could occur because:
	 *     - another request may be submitted by the upper level driver
	 *       of the stacking during the completion
	 *     - the submission which requires queue lock may be done
	 *       against this clone's queue
	 */
	dm_complete_request(tio->orig, error);
}

static void dm_dispatch_clone_request(struct request *clone, struct request *rq)
{
	blk_status_t r;

	if (blk_queue_io_stat(clone->q))
		clone->rq_flags |= RQF_IO_STAT;

	clone->start_time = jiffies;
	r = blk_insert_cloned_request(clone->q, clone);
	if (r)
		/* must complete clone in terms of original request */
		dm_complete_request(rq, r);
}

static int dm_rq_bio_constructor(struct bio *bio, struct bio *bio_orig,
				 void *data)
{
	struct dm_rq_target_io *tio = data;
	struct dm_rq_clone_bio_info *info =
		container_of(bio, struct dm_rq_clone_bio_info, clone);

	info->orig = bio_orig;
	info->tio = tio;
	bio->bi_end_io = end_clone_bio;

	return 0;
}

static int setup_clone(struct request *clone, struct request *rq,
		       struct dm_rq_target_io *tio, gfp_t gfp_mask)
{
	int r;

	r = blk_rq_prep_clone(clone, rq, tio->md->bs, gfp_mask,
			      dm_rq_bio_constructor, tio);
	if (r)
		return r;

	clone->end_io = end_clone_request;
	clone->end_io_data = tio;

	tio->clone = clone;

	return 0;
}

static void map_tio_request(struct kthread_work *work);

static void init_tio(struct dm_rq_target_io *tio, struct request *rq,
		     struct mapped_device *md)
{
	tio->md = md;
	tio->ti = NULL;
	tio->clone = NULL;
	tio->orig = rq;
	tio->error = 0;
	tio->completed = 0;
	/*
	 * Avoid initializing info for blk-mq; it passes
	 * target-specific data through info.ptr
	 * (see: dm_mq_init_request)
	 */
	if (!md->init_tio_pdu)
		memset(&tio->info, 0, sizeof(tio->info));
	if (md->kworker_task)
		kthread_init_work(&tio->work, map_tio_request);
}

/*
 * Returns:
 * DM_MAPIO_*       : the request has been processed as indicated
 * DM_MAPIO_REQUEUE : the original request needs to be immediately requeued
 * < 0              : the request was completed due to failure
 */
static int map_request(struct dm_rq_target_io *tio)
{
	int r;
	struct dm_target *ti = tio->ti;
	struct mapped_device *md = tio->md;
	struct request *rq = tio->orig;
	struct request *clone = NULL;

	r = ti->type->clone_and_map_rq(ti, rq, &tio->info, &clone);
	switch (r) {
	case DM_MAPIO_SUBMITTED:
		/* The target has taken the I/O to submit by itself later */
		break;
	case DM_MAPIO_REMAPPED:
		if (setup_clone(clone, rq, tio, GFP_ATOMIC)) {
			/* -ENOMEM */
			ti->type->release_clone_rq(clone);
			return DM_MAPIO_REQUEUE;
		}

		/* The target has remapped the I/O so dispatch it */
		trace_block_rq_remap(clone->q, clone, disk_devt(dm_disk(md)),
				     blk_rq_pos(rq));
		dm_dispatch_clone_request(clone, rq);
		break;
	case DM_MAPIO_REQUEUE:
		/* The target wants to requeue the I/O */
		break;
	case DM_MAPIO_DELAY_REQUEUE:
		/* The target wants to requeue the I/O after a delay */
		dm_requeue_original_request(tio, true);
		break;
	case DM_MAPIO_KILL:
		/* The target wants to complete the I/O */
		dm_kill_unmapped_request(rq, BLK_STS_IOERR);
		break;
	default:
		DMWARN("unimplemented target map return value: %d", r);
		BUG();
	}

	return r;
}

static void dm_start_request(struct mapped_device *md, struct request *orig)
{
	if (!orig->q->mq_ops)
		blk_start_request(orig);
	else
		blk_mq_start_request(orig);
	atomic_inc(&md->pending[rq_data_dir(orig)]);

	if (md->seq_rq_merge_deadline_usecs) {
		md->last_rq_pos = rq_end_sector(orig);
		md->last_rq_rw = rq_data_dir(orig);
		md->last_rq_start_time = ktime_get();
	}

	if (unlikely(dm_stats_used(&md->stats))) {
		struct dm_rq_target_io *tio = tio_from_request(orig);
		tio->duration_jiffies = jiffies;
		tio->n_sectors = blk_rq_sectors(orig);
		dm_stats_account_io(&md->stats, rq_data_dir(orig),
				    blk_rq_pos(orig), tio->n_sectors, false, 0,
				    &tio->stats_aux);
	}

	/*
	 * Hold the md reference here for the in-flight I/O.
	 * We can't rely on the reference count by device opener,
	 * because the device may be closed during the request completion
	 * when all bios are completed.
	 * See the comment in rq_completed() too.
	 */
	dm_get(md);
}

static int __dm_rq_init_rq(struct mapped_device *md, struct request *rq)
{
	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);

	/*
	 * Must initialize md member of tio, otherwise it won't
	 * be available in dm_mq_queue_rq.
	 */
	tio->md = md;

	if (md->init_tio_pdu) {
		/* target-specific per-io data is immediately after the tio */
		tio->info.ptr = tio + 1;
	}

	return 0;
}

static int dm_rq_init_rq(struct request_queue *q, struct request *rq, gfp_t gfp)
{
	return __dm_rq_init_rq(q->rq_alloc_data, rq);
}

static void map_tio_request(struct kthread_work *work)
{
	struct dm_rq_target_io *tio = container_of(work, struct dm_rq_target_io, work);

	if (map_request(tio) == DM_MAPIO_REQUEUE)
		dm_requeue_original_request(tio, false);
}

ssize_t dm_attr_rq_based_seq_io_merge_deadline_show(struct mapped_device *md, char *buf)
{
	return sprintf(buf, "%u\n", md->seq_rq_merge_deadline_usecs);
}

#define MAX_SEQ_RQ_MERGE_DEADLINE_USECS 100000

ssize_t dm_attr_rq_based_seq_io_merge_deadline_store(struct mapped_device *md,
						     const char *buf, size_t count)
{
	unsigned deadline;

	if (dm_get_md_type(md) != DM_TYPE_REQUEST_BASED)
		return count;

	if (kstrtouint(buf, 10, &deadline))
		return -EINVAL;

	if (deadline > MAX_SEQ_RQ_MERGE_DEADLINE_USECS)
		deadline = MAX_SEQ_RQ_MERGE_DEADLINE_USECS;

	md->seq_rq_merge_deadline_usecs = deadline;

	return count;
}

static bool dm_old_request_peeked_before_merge_deadline(struct mapped_device *md)
{
	ktime_t kt_deadline;

	if (!md->seq_rq_merge_deadline_usecs)
		return false;

	kt_deadline = ns_to_ktime((u64)md->seq_rq_merge_deadline_usecs * NSEC_PER_USEC);
	kt_deadline = ktime_add_safe(md->last_rq_start_time, kt_deadline);

	return !ktime_after(ktime_get(), kt_deadline);
}

/*
 * q->request_fn for old request-based dm.
 * Called with the queue lock held.
 */
static void dm_old_request_fn(struct request_queue *q)
{
	struct mapped_device *md = q->queuedata;
	struct dm_target *ti = md->immutable_target;
	struct request *rq;
	struct dm_rq_target_io *tio;
	sector_t pos = 0;

	if (unlikely(!ti)) {
		int srcu_idx;
		struct dm_table *map = dm_get_live_table(md, &srcu_idx);

		if (unlikely(!map)) {
			dm_put_live_table(md, srcu_idx);
			return;
		}
		ti = dm_table_find_target(map, pos);
		dm_put_live_table(md, srcu_idx);
	}

	/*
	 * For suspend, check blk_queue_stopped() and increment
	 * ->pending within a single queue_lock not to increment the
	 * number of in-flight I/Os after the queue is stopped in
	 * dm_suspend().
	 */
	while (!blk_queue_stopped(q)) {
		rq = blk_peek_request(q);
		if (!rq)
			return;

		/* always use block 0 to find the target for flushes for now */
		pos = 0;
		if (req_op(rq) != REQ_OP_FLUSH)
			pos = blk_rq_pos(rq);

		if ((dm_old_request_peeked_before_merge_deadline(md) &&
		     md_in_flight(md) && rq->bio && !bio_multiple_segments(rq->bio) &&
		     md->last_rq_pos == pos && md->last_rq_rw == rq_data_dir(rq)) ||
		    (ti->type->busy && ti->type->busy(ti))) {
			blk_delay_queue(q, 10);
			return;
		}

		dm_start_request(md, rq);

		tio = tio_from_request(rq);
		init_tio(tio, rq, md);
		/* Establish tio->ti before queuing work (map_tio_request) */
		tio->ti = ti;
		kthread_queue_work(&md->kworker, &tio->work);
		BUG_ON(!irqs_disabled());
	}
}

/*
 * Fully initialize a .request_fn request-based queue.
 */
int dm_old_init_request_queue(struct mapped_device *md, struct dm_table *t)
{
	struct dm_target *immutable_tgt;

	/* Fully initialize the queue */
	md->queue->cmd_size = sizeof(struct dm_rq_target_io);
	md->queue->rq_alloc_data = md;
	md->queue->request_fn = dm_old_request_fn;
	md->queue->init_rq_fn = dm_rq_init_rq;

	immutable_tgt = dm_table_get_immutable_target(t);
	if (immutable_tgt && immutable_tgt->per_io_data_size) {
		/* any target-specific per-io data is immediately after the tio */
		md->queue->cmd_size += immutable_tgt->per_io_data_size;
		md->init_tio_pdu = true;
	}
	if (blk_init_allocated_queue(md->queue) < 0)
		return -EINVAL;

	/* disable dm_old_request_fn's merge heuristic by default */
	md->seq_rq_merge_deadline_usecs = 0;

	dm_init_normal_md_queue(md);
	blk_queue_softirq_done(md->queue, dm_softirq_done);

	/* Initialize the request-based DM worker thread */
	kthread_init_worker(&md->kworker);
	md->kworker_task = kthread_run(kthread_worker_fn, &md->kworker,
				       "kdmwork-%s", dm_device_name(md));
	if (IS_ERR(md->kworker_task)) {
		int error = PTR_ERR(md->kworker_task);
		md->kworker_task = NULL;
		return error;
	}

	elv_register_queue(md->queue);

	return 0;
}

static int dm_mq_init_request(struct blk_mq_tag_set *set, struct request *rq,
		unsigned int hctx_idx, unsigned int numa_node)
{
	return __dm_rq_init_rq(set->driver_data, rq);
}

static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
			  const struct blk_mq_queue_data *bd)
{
	struct request *rq = bd->rq;
	struct dm_rq_target_io *tio = blk_mq_rq_to_pdu(rq);
	struct mapped_device *md = tio->md;
	struct dm_target *ti = md->immutable_target;

	if (unlikely(!ti)) {
		int srcu_idx;
		struct dm_table *map = dm_get_live_table(md, &srcu_idx);

		ti = dm_table_find_target(map, 0);
		dm_put_live_table(md, srcu_idx);
	}

	if (ti->type->busy && ti->type->busy(ti))
		return BLK_STS_RESOURCE;

	dm_start_request(md, rq);

	/* Init tio using md established in .init_request */
	init_tio(tio, rq, md);

	/*
	 * Establish tio->ti before calling map_request().
	 */
	tio->ti = ti;

	/* Direct call is fine since .queue_rq allows allocations */
	if (map_request(tio) == DM_MAPIO_REQUEUE) {
		/* Undo dm_start_request() before requeuing */
		rq_end_stats(md, rq);
		rq_completed(md, rq_data_dir(rq), false);
		blk_mq_delay_run_hw_queue(hctx, 100/*ms*/);
		return BLK_STS_RESOURCE;
	}

	return BLK_STS_OK;
}

static const struct blk_mq_ops dm_mq_ops = {
	.queue_rq = dm_mq_queue_rq,
	.complete = dm_softirq_done,
	.init_request = dm_mq_init_request,
};

int dm_mq_init_request_queue(struct mapped_device *md, struct dm_table *t)
{
	struct request_queue *q;
	struct dm_target *immutable_tgt;
	int err;

	if (!dm_table_all_blk_mq_devices(t)) {
		DMERR("request-based dm-mq may only be stacked on blk-mq device(s)");
		return -EINVAL;
	}

	md->tag_set = kzalloc_node(sizeof(struct blk_mq_tag_set), GFP_KERNEL, md->numa_node_id);
	if (!md->tag_set)
		return -ENOMEM;

	md->tag_set->ops = &dm_mq_ops;
	md->tag_set->queue_depth = dm_get_blk_mq_queue_depth();
	md->tag_set->numa_node = md->numa_node_id;
	md->tag_set->flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
	md->tag_set->nr_hw_queues = dm_get_blk_mq_nr_hw_queues();
	md->tag_set->driver_data = md;

	md->tag_set->cmd_size = sizeof(struct dm_rq_target_io);
	immutable_tgt = dm_table_get_immutable_target(t);
	if (immutable_tgt && immutable_tgt->per_io_data_size) {
		/* any target-specific per-io data is immediately after the tio */
		md->tag_set->cmd_size += immutable_tgt->per_io_data_size;
		md->init_tio_pdu = true;
	}

	err = blk_mq_alloc_tag_set(md->tag_set);
	if (err)
		goto out_kfree_tag_set;

	q = blk_mq_init_allocated_queue(md->tag_set, md->queue);
	if (IS_ERR(q)) {
		err = PTR_ERR(q);
		goto out_tag_set;
	}
	dm_init_md_queue(md);

	/* backfill 'mq' sysfs registration normally done in blk_register_queue */
	err = blk_mq_register_dev(disk_to_dev(md->disk), q);
	if (err)
		goto out_cleanup_queue;

	return 0;

out_cleanup_queue:
	blk_cleanup_queue(q);
out_tag_set:
	blk_mq_free_tag_set(md->tag_set);
out_kfree_tag_set:
	kfree(md->tag_set);

	return err;
}

void dm_mq_cleanup_mapped_device(struct mapped_device *md)
{
	if (md->tag_set) {
		blk_mq_free_tag_set(md->tag_set);
		kfree(md->tag_set);
	}
}

module_param(reserved_rq_based_ios, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(reserved_rq_based_ios, "Reserved IOs in request-based mempools");

module_param(use_blk_mq, bool, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(use_blk_mq, "Use block multiqueue for request-based DM devices");

module_param(dm_mq_nr_hw_queues, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dm_mq_nr_hw_queues, "Number of hardware queues for request-based dm-mq devices");

module_param(dm_mq_queue_depth, uint, S_IRUGO | S_IWUSR);
MODULE_PARM_DESC(dm_mq_queue_depth, "Queue depth for request-based dm-mq devices");