aboutsummaryrefslogtreecommitdiff
path: root/block/blk-mq-debugfs.c
blob: cb1e6cf7ac48f4e187e915896376cdfec79c9d2a (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
/*
 * Copyright (C) 2017 Facebook
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program.  If not, see <https://www.gnu.org/licenses/>.
 */

#include <linux/kernel.h>
#include <linux/blkdev.h>
#include <linux/debugfs.h>

#include <linux/blk-mq.h>
#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-tag.h"

static void print_stat(struct seq_file *m, struct blk_rq_stat *stat)
{
	if (stat->nr_samples) {
		seq_printf(m, "samples=%d, mean=%lld, min=%llu, max=%llu",
			   stat->nr_samples, stat->mean, stat->min, stat->max);
	} else {
		seq_puts(m, "samples=0");
	}
}

static int queue_poll_stat_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	int bucket;

	for (bucket = 0; bucket < BLK_MQ_POLL_STATS_BKTS/2; bucket++) {
		seq_printf(m, "read  (%d Bytes): ", 1 << (9+bucket));
		print_stat(m, &q->poll_stat[2*bucket]);
		seq_puts(m, "\n");

		seq_printf(m, "write (%d Bytes): ",  1 << (9+bucket));
		print_stat(m, &q->poll_stat[2*bucket+1]);
		seq_puts(m, "\n");
	}
	return 0;
}

static void *queue_requeue_list_start(struct seq_file *m, loff_t *pos)
	__acquires(&q->requeue_lock)
{
	struct request_queue *q = m->private;

	spin_lock_irq(&q->requeue_lock);
	return seq_list_start(&q->requeue_list, *pos);
}

static void *queue_requeue_list_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct request_queue *q = m->private;

	return seq_list_next(v, &q->requeue_list, pos);
}

static void queue_requeue_list_stop(struct seq_file *m, void *v)
	__releases(&q->requeue_lock)
{
	struct request_queue *q = m->private;

	spin_unlock_irq(&q->requeue_lock);
}

static const struct seq_operations queue_requeue_list_seq_ops = {
	.start	= queue_requeue_list_start,
	.next	= queue_requeue_list_next,
	.stop	= queue_requeue_list_stop,
	.show	= blk_mq_debugfs_rq_show,
};

static int blk_flags_show(struct seq_file *m, const unsigned long flags,
			  const char *const *flag_name, int flag_name_count)
{
	bool sep = false;
	int i;

	for (i = 0; i < sizeof(flags) * BITS_PER_BYTE; i++) {
		if (!(flags & BIT(i)))
			continue;
		if (sep)
			seq_puts(m, "|");
		sep = true;
		if (i < flag_name_count && flag_name[i])
			seq_puts(m, flag_name[i]);
		else
			seq_printf(m, "%d", i);
	}
	return 0;
}

#define QUEUE_FLAG_NAME(name) [QUEUE_FLAG_##name] = #name
static const char *const blk_queue_flag_name[] = {
	QUEUE_FLAG_NAME(QUEUED),
	QUEUE_FLAG_NAME(STOPPED),
	QUEUE_FLAG_NAME(DYING),
	QUEUE_FLAG_NAME(BYPASS),
	QUEUE_FLAG_NAME(BIDI),
	QUEUE_FLAG_NAME(NOMERGES),
	QUEUE_FLAG_NAME(SAME_COMP),
	QUEUE_FLAG_NAME(FAIL_IO),
	QUEUE_FLAG_NAME(NONROT),
	QUEUE_FLAG_NAME(IO_STAT),
	QUEUE_FLAG_NAME(DISCARD),
	QUEUE_FLAG_NAME(NOXMERGES),
	QUEUE_FLAG_NAME(ADD_RANDOM),
	QUEUE_FLAG_NAME(SECERASE),
	QUEUE_FLAG_NAME(SAME_FORCE),
	QUEUE_FLAG_NAME(DEAD),
	QUEUE_FLAG_NAME(INIT_DONE),
	QUEUE_FLAG_NAME(NO_SG_MERGE),
	QUEUE_FLAG_NAME(POLL),
	QUEUE_FLAG_NAME(WC),
	QUEUE_FLAG_NAME(FUA),
	QUEUE_FLAG_NAME(FLUSH_NQ),
	QUEUE_FLAG_NAME(DAX),
	QUEUE_FLAG_NAME(STATS),
	QUEUE_FLAG_NAME(POLL_STATS),
	QUEUE_FLAG_NAME(REGISTERED),
	QUEUE_FLAG_NAME(SCSI_PASSTHROUGH),
	QUEUE_FLAG_NAME(QUIESCED),
	QUEUE_FLAG_NAME(PREEMPT_ONLY),
};
#undef QUEUE_FLAG_NAME

static int queue_state_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;

	blk_flags_show(m, q->queue_flags, blk_queue_flag_name,
		       ARRAY_SIZE(blk_queue_flag_name));
	seq_puts(m, "\n");
	return 0;
}

static ssize_t queue_state_write(void *data, const char __user *buf,
				 size_t count, loff_t *ppos)
{
	struct request_queue *q = data;
	char opbuf[16] = { }, *op;

	/*
	 * The "state" attribute is removed after blk_cleanup_queue() has called
	 * blk_mq_free_queue(). Return if QUEUE_FLAG_DEAD has been set to avoid
	 * triggering a use-after-free.
	 */
	if (blk_queue_dead(q))
		return -ENOENT;

	if (count >= sizeof(opbuf)) {
		pr_err("%s: operation too long\n", __func__);
		goto inval;
	}

	if (copy_from_user(opbuf, buf, count))
		return -EFAULT;
	op = strstrip(opbuf);
	if (strcmp(op, "run") == 0) {
		blk_mq_run_hw_queues(q, true);
	} else if (strcmp(op, "start") == 0) {
		blk_mq_start_stopped_hw_queues(q, true);
	} else if (strcmp(op, "kick") == 0) {
		blk_mq_kick_requeue_list(q);
	} else {
		pr_err("%s: unsupported operation '%s'\n", __func__, op);
inval:
		pr_err("%s: use 'run', 'start' or 'kick'\n", __func__);
		return -EINVAL;
	}
	return count;
}

static int queue_write_hint_show(void *data, struct seq_file *m)
{
	struct request_queue *q = data;
	int i;

	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
		seq_printf(m, "hint%d: %llu\n", i, q->write_hints[i]);

	return 0;
}

static ssize_t queue_write_hint_store(void *data, const char __user *buf,
				      size_t count, loff_t *ppos)
{
	struct request_queue *q = data;
	int i;

	for (i = 0; i < BLK_MAX_WRITE_HINTS; i++)
		q->write_hints[i] = 0;

	return count;
}

static const struct blk_mq_debugfs_attr blk_mq_debugfs_queue_attrs[] = {
	{ "poll_stat", 0400, queue_poll_stat_show },
	{ "requeue_list", 0400, .seq_ops = &queue_requeue_list_seq_ops },
	{ "state", 0600, queue_state_show, queue_state_write },
	{ "write_hints", 0600, queue_write_hint_show, queue_write_hint_store },
	{ "zone_wlock", 0400, queue_zone_wlock_show, NULL },
	{ },
};

#define HCTX_STATE_NAME(name) [BLK_MQ_S_##name] = #name
static const char *const hctx_state_name[] = {
	HCTX_STATE_NAME(STOPPED),
	HCTX_STATE_NAME(TAG_ACTIVE),
	HCTX_STATE_NAME(SCHED_RESTART),
};
#undef HCTX_STATE_NAME

static int hctx_state_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;

	blk_flags_show(m, hctx->state, hctx_state_name,
		       ARRAY_SIZE(hctx_state_name));
	seq_puts(m, "\n");
	return 0;
}

#define BLK_TAG_ALLOC_NAME(name) [BLK_TAG_ALLOC_##name] = #name
static const char *const alloc_policy_name[] = {
	BLK_TAG_ALLOC_NAME(FIFO),
	BLK_TAG_ALLOC_NAME(RR),
};
#undef BLK_TAG_ALLOC_NAME

#define HCTX_FLAG_NAME(name) [ilog2(BLK_MQ_F_##name)] = #name
static const char *const hctx_flag_name[] = {
	HCTX_FLAG_NAME(SHOULD_MERGE),
	HCTX_FLAG_NAME(TAG_SHARED),
	HCTX_FLAG_NAME(SG_MERGE),
	HCTX_FLAG_NAME(BLOCKING),
	HCTX_FLAG_NAME(NO_SCHED),
};
#undef HCTX_FLAG_NAME

static int hctx_flags_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;
	const int alloc_policy = BLK_MQ_FLAG_TO_ALLOC_POLICY(hctx->flags);

	seq_puts(m, "alloc_policy=");
	if (alloc_policy < ARRAY_SIZE(alloc_policy_name) &&
	    alloc_policy_name[alloc_policy])
		seq_puts(m, alloc_policy_name[alloc_policy]);
	else
		seq_printf(m, "%d", alloc_policy);
	seq_puts(m, " ");
	blk_flags_show(m,
		       hctx->flags ^ BLK_ALLOC_POLICY_TO_MQ_FLAG(alloc_policy),
		       hctx_flag_name, ARRAY_SIZE(hctx_flag_name));
	seq_puts(m, "\n");
	return 0;
}

#define REQ_OP_NAME(name) [REQ_OP_##name] = #name
static const char *const op_name[] = {
	REQ_OP_NAME(READ),
	REQ_OP_NAME(WRITE),
	REQ_OP_NAME(FLUSH),
	REQ_OP_NAME(DISCARD),
	REQ_OP_NAME(ZONE_REPORT),
	REQ_OP_NAME(SECURE_ERASE),
	REQ_OP_NAME(ZONE_RESET),
	REQ_OP_NAME(WRITE_SAME),
	REQ_OP_NAME(WRITE_ZEROES),
	REQ_OP_NAME(SCSI_IN),
	REQ_OP_NAME(SCSI_OUT),
	REQ_OP_NAME(DRV_IN),
	REQ_OP_NAME(DRV_OUT),
};
#undef REQ_OP_NAME

#define CMD_FLAG_NAME(name) [__REQ_##name] = #name
static const char *const cmd_flag_name[] = {
	CMD_FLAG_NAME(FAILFAST_DEV),
	CMD_FLAG_NAME(FAILFAST_TRANSPORT),
	CMD_FLAG_NAME(FAILFAST_DRIVER),
	CMD_FLAG_NAME(SYNC),
	CMD_FLAG_NAME(META),
	CMD_FLAG_NAME(PRIO),
	CMD_FLAG_NAME(NOMERGE),
	CMD_FLAG_NAME(IDLE),
	CMD_FLAG_NAME(INTEGRITY),
	CMD_FLAG_NAME(FUA),
	CMD_FLAG_NAME(PREFLUSH),
	CMD_FLAG_NAME(RAHEAD),
	CMD_FLAG_NAME(BACKGROUND),
	CMD_FLAG_NAME(NOUNMAP),
	CMD_FLAG_NAME(NOWAIT),
};
#undef CMD_FLAG_NAME

#define RQF_NAME(name) [ilog2((__force u32)RQF_##name)] = #name
static const char *const rqf_name[] = {
	RQF_NAME(SORTED),
	RQF_NAME(STARTED),
	RQF_NAME(QUEUED),
	RQF_NAME(SOFTBARRIER),
	RQF_NAME(FLUSH_SEQ),
	RQF_NAME(MIXED_MERGE),
	RQF_NAME(MQ_INFLIGHT),
	RQF_NAME(DONTPREP),
	RQF_NAME(PREEMPT),
	RQF_NAME(COPY_USER),
	RQF_NAME(FAILED),
	RQF_NAME(QUIET),
	RQF_NAME(ELVPRIV),
	RQF_NAME(IO_STAT),
	RQF_NAME(ALLOCED),
	RQF_NAME(PM),
	RQF_NAME(HASHED),
	RQF_NAME(STATS),
	RQF_NAME(SPECIAL_PAYLOAD),
	RQF_NAME(ZONE_WRITE_LOCKED),
	RQF_NAME(MQ_POLL_SLEPT),
};
#undef RQF_NAME

static const char *const blk_mq_rq_state_name_array[] = {
	[MQ_RQ_IDLE]		= "idle",
	[MQ_RQ_IN_FLIGHT]	= "in_flight",
	[MQ_RQ_COMPLETE]	= "complete",
};

static const char *blk_mq_rq_state_name(enum mq_rq_state rq_state)
{
	if (WARN_ON_ONCE((unsigned int)rq_state >=
			 ARRAY_SIZE(blk_mq_rq_state_name_array)))
		return "(?)";
	return blk_mq_rq_state_name_array[rq_state];
}

int __blk_mq_debugfs_rq_show(struct seq_file *m, struct request *rq)
{
	const struct blk_mq_ops *const mq_ops = rq->q->mq_ops;
	const unsigned int op = rq->cmd_flags & REQ_OP_MASK;

	seq_printf(m, "%p {.op=", rq);
	if (op < ARRAY_SIZE(op_name) && op_name[op])
		seq_printf(m, "%s", op_name[op]);
	else
		seq_printf(m, "%d", op);
	seq_puts(m, ", .cmd_flags=");
	blk_flags_show(m, rq->cmd_flags & ~REQ_OP_MASK, cmd_flag_name,
		       ARRAY_SIZE(cmd_flag_name));
	seq_puts(m, ", .rq_flags=");
	blk_flags_show(m, (__force unsigned int)rq->rq_flags, rqf_name,
		       ARRAY_SIZE(rqf_name));
	seq_printf(m, ", .state=%s", blk_mq_rq_state_name(blk_mq_rq_state(rq)));
	seq_printf(m, ", .tag=%d, .internal_tag=%d", rq->tag,
		   rq->internal_tag);
	if (mq_ops->show_rq)
		mq_ops->show_rq(m, rq);
	seq_puts(m, "}\n");
	return 0;
}
EXPORT_SYMBOL_GPL(__blk_mq_debugfs_rq_show);

int blk_mq_debugfs_rq_show(struct seq_file *m, void *v)
{
	return __blk_mq_debugfs_rq_show(m, list_entry_rq(v));
}
EXPORT_SYMBOL_GPL(blk_mq_debugfs_rq_show);

static void *hctx_dispatch_start(struct seq_file *m, loff_t *pos)
	__acquires(&hctx->lock)
{
	struct blk_mq_hw_ctx *hctx = m->private;

	spin_lock(&hctx->lock);
	return seq_list_start(&hctx->dispatch, *pos);
}

static void *hctx_dispatch_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct blk_mq_hw_ctx *hctx = m->private;

	return seq_list_next(v, &hctx->dispatch, pos);
}

static void hctx_dispatch_stop(struct seq_file *m, void *v)
	__releases(&hctx->lock)
{
	struct blk_mq_hw_ctx *hctx = m->private;

	spin_unlock(&hctx->lock);
}

static const struct seq_operations hctx_dispatch_seq_ops = {
	.start	= hctx_dispatch_start,
	.next	= hctx_dispatch_next,
	.stop	= hctx_dispatch_stop,
	.show	= blk_mq_debugfs_rq_show,
};

struct show_busy_params {
	struct seq_file		*m;
	struct blk_mq_hw_ctx	*hctx;
};

/*
 * Note: the state of a request may change while this function is in progress,
 * e.g. due to a concurrent blk_mq_finish_request() call.
 */
static void hctx_show_busy_rq(struct request *rq, void *data, bool reserved)
{
	const struct show_busy_params *params = data;

	if (blk_mq_map_queue(rq->q, rq->mq_ctx->cpu) == params->hctx &&
	    blk_mq_rq_state(rq) != MQ_RQ_IDLE)
		__blk_mq_debugfs_rq_show(params->m,
					 list_entry_rq(&rq->queuelist));
}

static int hctx_busy_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;
	struct show_busy_params params = { .m = m, .hctx = hctx };

	blk_mq_tagset_busy_iter(hctx->queue->tag_set, hctx_show_busy_rq,
				&params);

	return 0;
}

static int hctx_ctx_map_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;

	sbitmap_bitmap_show(&hctx->ctx_map, m);
	return 0;
}

static void blk_mq_debugfs_tags_show(struct seq_file *m,
				     struct blk_mq_tags *tags)
{
	seq_printf(m, "nr_tags=%u\n", tags->nr_tags);
	seq_printf(m, "nr_reserved_tags=%u\n", tags->nr_reserved_tags);
	seq_printf(m, "active_queues=%d\n",
		   atomic_read(&tags->active_queues));

	seq_puts(m, "\nbitmap_tags:\n");
	sbitmap_queue_show(&tags->bitmap_tags, m);

	if (tags->nr_reserved_tags) {
		seq_puts(m, "\nbreserved_tags:\n");
		sbitmap_queue_show(&tags->breserved_tags, m);
	}
}

static int hctx_tags_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;
	struct request_queue *q = hctx->queue;
	int res;

	res = mutex_lock_interruptible(&q->sysfs_lock);
	if (res)
		goto out;
	if (hctx->tags)
		blk_mq_debugfs_tags_show(m, hctx->tags);
	mutex_unlock(&q->sysfs_lock);

out:
	return res;
}

static int hctx_tags_bitmap_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;
	struct request_queue *q = hctx->queue;
	int res;

	res = mutex_lock_interruptible(&q->sysfs_lock);
	if (res)
		goto out;
	if (hctx->tags)
		sbitmap_bitmap_show(&hctx->tags->bitmap_tags.sb, m);
	mutex_unlock(&q->sysfs_lock);

out:
	return res;
}

static int hctx_sched_tags_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;
	struct request_queue *q = hctx->queue;
	int res;

	res = mutex_lock_interruptible(&q->sysfs_lock);
	if (res)
		goto out;
	if (hctx->sched_tags)
		blk_mq_debugfs_tags_show(m, hctx->sched_tags);
	mutex_unlock(&q->sysfs_lock);

out:
	return res;
}

static int hctx_sched_tags_bitmap_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;
	struct request_queue *q = hctx->queue;
	int res;

	res = mutex_lock_interruptible(&q->sysfs_lock);
	if (res)
		goto out;
	if (hctx->sched_tags)
		sbitmap_bitmap_show(&hctx->sched_tags->bitmap_tags.sb, m);
	mutex_unlock(&q->sysfs_lock);

out:
	return res;
}

static int hctx_io_poll_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;

	seq_printf(m, "considered=%lu\n", hctx->poll_considered);
	seq_printf(m, "invoked=%lu\n", hctx->poll_invoked);
	seq_printf(m, "success=%lu\n", hctx->poll_success);
	return 0;
}

static ssize_t hctx_io_poll_write(void *data, const char __user *buf,
				  size_t count, loff_t *ppos)
{
	struct blk_mq_hw_ctx *hctx = data;

	hctx->poll_considered = hctx->poll_invoked = hctx->poll_success = 0;
	return count;
}

static int hctx_dispatched_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;
	int i;

	seq_printf(m, "%8u\t%lu\n", 0U, hctx->dispatched[0]);

	for (i = 1; i < BLK_MQ_MAX_DISPATCH_ORDER - 1; i++) {
		unsigned int d = 1U << (i - 1);

		seq_printf(m, "%8u\t%lu\n", d, hctx->dispatched[i]);
	}

	seq_printf(m, "%8u+\t%lu\n", 1U << (i - 1), hctx->dispatched[i]);
	return 0;
}

static ssize_t hctx_dispatched_write(void *data, const char __user *buf,
				     size_t count, loff_t *ppos)
{
	struct blk_mq_hw_ctx *hctx = data;
	int i;

	for (i = 0; i < BLK_MQ_MAX_DISPATCH_ORDER; i++)
		hctx->dispatched[i] = 0;
	return count;
}

static int hctx_queued_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;

	seq_printf(m, "%lu\n", hctx->queued);
	return 0;
}

static ssize_t hctx_queued_write(void *data, const char __user *buf,
				 size_t count, loff_t *ppos)
{
	struct blk_mq_hw_ctx *hctx = data;

	hctx->queued = 0;
	return count;
}

static int hctx_run_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;

	seq_printf(m, "%lu\n", hctx->run);
	return 0;
}

static ssize_t hctx_run_write(void *data, const char __user *buf, size_t count,
			      loff_t *ppos)
{
	struct blk_mq_hw_ctx *hctx = data;

	hctx->run = 0;
	return count;
}

static int hctx_active_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;

	seq_printf(m, "%d\n", atomic_read(&hctx->nr_active));
	return 0;
}

static int hctx_dispatch_busy_show(void *data, struct seq_file *m)
{
	struct blk_mq_hw_ctx *hctx = data;

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

static void *ctx_rq_list_start(struct seq_file *m, loff_t *pos)
	__acquires(&ctx->lock)
{
	struct blk_mq_ctx *ctx = m->private;

	spin_lock(&ctx->lock);
	return seq_list_start(&ctx->rq_list, *pos);
}

static void *ctx_rq_list_next(struct seq_file *m, void *v, loff_t *pos)
{
	struct blk_mq_ctx *ctx = m->private;

	return seq_list_next(v, &ctx->rq_list, pos);
}

static void ctx_rq_list_stop(struct seq_file *m, void *v)
	__releases(&ctx->lock)
{
	struct blk_mq_ctx *ctx = m->private;

	spin_unlock(&ctx->lock);
}

static const struct seq_operations ctx_rq_list_seq_ops = {
	.start	= ctx_rq_list_start,
	.next	= ctx_rq_list_next,
	.stop	= ctx_rq_list_stop,
	.show	= blk_mq_debugfs_rq_show,
};
static int ctx_dispatched_show(void *data, struct seq_file *m)
{
	struct blk_mq_ctx *ctx = data;

	seq_printf(m, "%lu %lu\n", ctx->rq_dispatched[1], ctx->rq_dispatched[0]);
	return 0;
}

static ssize_t ctx_dispatched_write(void *data, const char __user *buf,
				    size_t count, loff_t *ppos)
{
	struct blk_mq_ctx *ctx = data;

	ctx->rq_dispatched[0] = ctx->rq_dispatched[1] = 0;
	return count;
}

static int ctx_merged_show(void *data, struct seq_file *m)
{
	struct blk_mq_ctx *ctx = data;

	seq_printf(m, "%lu\n", ctx->rq_merged);
	return 0;
}

static ssize_t ctx_merged_write(void *data, const char __user *buf,
				size_t count, loff_t *ppos)
{
	struct blk_mq_ctx *ctx = data;

	ctx->rq_merged = 0;
	return count;
}

static int ctx_completed_show(void *data, struct seq_file *m)
{
	struct blk_mq_ctx *ctx = data;

	seq_printf(m, "%lu %lu\n", ctx->rq_completed[1], ctx->rq_completed[0]);
	return 0;
}

static ssize_t ctx_completed_write(void *data, const char __user *buf,
				   size_t count, loff_t *ppos)
{
	struct blk_mq_ctx *ctx = data;

	ctx->rq_completed[0] = ctx->rq_completed[1] = 0;
	return count;
}

static int blk_mq_debugfs_show(struct seq_file *m, void *v)
{
	const struct blk_mq_debugfs_attr *attr = m->private;
	void *data = d_inode(m->file->f_path.dentry->d_parent)->i_private;

	return attr->show(data, m);
}

static ssize_t blk_mq_debugfs_write(struct file *file, const char __user *buf,
				    size_t count, loff_t *ppos)
{
	struct seq_file *m = file->private_data;
	const struct blk_mq_debugfs_attr *attr = m->private;
	void *data = d_inode(file->f_path.dentry->d_parent)->i_private;

	/*
	 * Attributes that only implement .seq_ops are read-only and 'attr' is
	 * the same with 'data' in this case.
	 */
	if (attr == data || !attr->write)
		return -EPERM;

	return attr->write(data, buf, count, ppos);
}

static int blk_mq_debugfs_open(struct inode *inode, struct file *file)
{
	const struct blk_mq_debugfs_attr *attr = inode->i_private;
	void *data = d_inode(file->f_path.dentry->d_parent)->i_private;
	struct seq_file *m;
	int ret;

	if (attr->seq_ops) {
		ret = seq_open(file, attr->seq_ops);
		if (!ret) {
			m = file->private_data;
			m->private = data;
		}
		return ret;
	}

	if (WARN_ON_ONCE(!attr->show))
		return -EPERM;

	return single_open(file, blk_mq_debugfs_show, inode->i_private);
}

static int blk_mq_debugfs_release(struct inode *inode, struct file *file)
{
	const struct blk_mq_debugfs_attr *attr = inode->i_private;

	if (attr->show)
		return single_release(inode, file);
	else
		return seq_release(inode, file);
}

static const struct file_operations blk_mq_debugfs_fops = {
	.open		= blk_mq_debugfs_open,
	.read		= seq_read,
	.write		= blk_mq_debugfs_write,
	.llseek		= seq_lseek,
	.release	= blk_mq_debugfs_release,
};

static const struct blk_mq_debugfs_attr blk_mq_debugfs_hctx_attrs[] = {
	{"state", 0400, hctx_state_show},
	{"flags", 0400, hctx_flags_show},
	{"dispatch", 0400, .seq_ops = &hctx_dispatch_seq_ops},
	{"busy", 0400, hctx_busy_show},
	{"ctx_map", 0400, hctx_ctx_map_show},
	{"tags", 0400, hctx_tags_show},
	{"tags_bitmap", 0400, hctx_tags_bitmap_show},
	{"sched_tags", 0400, hctx_sched_tags_show},
	{"sched_tags_bitmap", 0400, hctx_sched_tags_bitmap_show},
	{"io_poll", 0600, hctx_io_poll_show, hctx_io_poll_write},
	{"dispatched", 0600, hctx_dispatched_show, hctx_dispatched_write},
	{"queued", 0600, hctx_queued_show, hctx_queued_write},
	{"run", 0600, hctx_run_show, hctx_run_write},
	{"active", 0400, hctx_active_show},
	{"dispatch_busy", 0400, hctx_dispatch_busy_show},
	{},
};

static const struct blk_mq_debugfs_attr blk_mq_debugfs_ctx_attrs[] = {
	{"rq_list", 0400, .seq_ops = &ctx_rq_list_seq_ops},
	{"dispatched", 0600, ctx_dispatched_show, ctx_dispatched_write},
	{"merged", 0600, ctx_merged_show, ctx_merged_write},
	{"completed", 0600, ctx_completed_show, ctx_completed_write},
	{},
};

static bool debugfs_create_files(struct dentry *parent, void *data,
				 const struct blk_mq_debugfs_attr *attr)
{
	d_inode(parent)->i_private = data;

	for (; attr->name; attr++) {
		if (!debugfs_create_file(attr->name, attr->mode, parent,
					 (void *)attr, &blk_mq_debugfs_fops))
			return false;
	}
	return true;
}

int blk_mq_debugfs_register(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	if (!blk_debugfs_root)
		return -ENOENT;

	q->debugfs_dir = debugfs_create_dir(kobject_name(q->kobj.parent),
					    blk_debugfs_root);
	if (!q->debugfs_dir)
		return -ENOMEM;

	if (!debugfs_create_files(q->debugfs_dir, q,
				  blk_mq_debugfs_queue_attrs))
		goto err;

	/*
	 * blk_mq_init_sched() attempted to do this already, but q->debugfs_dir
	 * didn't exist yet (because we don't know what to name the directory
	 * until the queue is registered to a gendisk).
	 */
	if (q->elevator && !q->sched_debugfs_dir)
		blk_mq_debugfs_register_sched(q);

	/* Similarly, blk_mq_init_hctx() couldn't do this previously. */
	queue_for_each_hw_ctx(q, hctx, i) {
		if (!hctx->debugfs_dir && blk_mq_debugfs_register_hctx(q, hctx))
			goto err;
		if (q->elevator && !hctx->sched_debugfs_dir &&
		    blk_mq_debugfs_register_sched_hctx(q, hctx))
			goto err;
	}

	return 0;

err:
	blk_mq_debugfs_unregister(q);
	return -ENOMEM;
}

void blk_mq_debugfs_unregister(struct request_queue *q)
{
	debugfs_remove_recursive(q->debugfs_dir);
	q->sched_debugfs_dir = NULL;
	q->debugfs_dir = NULL;
}

static int blk_mq_debugfs_register_ctx(struct blk_mq_hw_ctx *hctx,
				       struct blk_mq_ctx *ctx)
{
	struct dentry *ctx_dir;
	char name[20];

	snprintf(name, sizeof(name), "cpu%u", ctx->cpu);
	ctx_dir = debugfs_create_dir(name, hctx->debugfs_dir);
	if (!ctx_dir)
		return -ENOMEM;

	if (!debugfs_create_files(ctx_dir, ctx, blk_mq_debugfs_ctx_attrs))
		return -ENOMEM;

	return 0;
}

int blk_mq_debugfs_register_hctx(struct request_queue *q,
				 struct blk_mq_hw_ctx *hctx)
{
	struct blk_mq_ctx *ctx;
	char name[20];
	int i;

	if (!q->debugfs_dir)
		return -ENOENT;

	snprintf(name, sizeof(name), "hctx%u", hctx->queue_num);
	hctx->debugfs_dir = debugfs_create_dir(name, q->debugfs_dir);
	if (!hctx->debugfs_dir)
		return -ENOMEM;

	if (!debugfs_create_files(hctx->debugfs_dir, hctx,
				  blk_mq_debugfs_hctx_attrs))
		goto err;

	hctx_for_each_ctx(hctx, ctx, i) {
		if (blk_mq_debugfs_register_ctx(hctx, ctx))
			goto err;
	}

	return 0;

err:
	blk_mq_debugfs_unregister_hctx(hctx);
	return -ENOMEM;
}

void blk_mq_debugfs_unregister_hctx(struct blk_mq_hw_ctx *hctx)
{
	debugfs_remove_recursive(hctx->debugfs_dir);
	hctx->sched_debugfs_dir = NULL;
	hctx->debugfs_dir = NULL;
}

int blk_mq_debugfs_register_hctxs(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i) {
		if (blk_mq_debugfs_register_hctx(q, hctx))
			return -ENOMEM;
	}

	return 0;
}

void blk_mq_debugfs_unregister_hctxs(struct request_queue *q)
{
	struct blk_mq_hw_ctx *hctx;
	int i;

	queue_for_each_hw_ctx(q, hctx, i)
		blk_mq_debugfs_unregister_hctx(hctx);
}

int blk_mq_debugfs_register_sched(struct request_queue *q)
{
	struct elevator_type *e = q->elevator->type;

	if (!q->debugfs_dir)
		return -ENOENT;

	if (!e->queue_debugfs_attrs)
		return 0;

	q->sched_debugfs_dir = debugfs_create_dir("sched", q->debugfs_dir);
	if (!q->sched_debugfs_dir)
		return -ENOMEM;

	if (!debugfs_create_files(q->sched_debugfs_dir, q,
				  e->queue_debugfs_attrs))
		goto err;

	return 0;

err:
	blk_mq_debugfs_unregister_sched(q);
	return -ENOMEM;
}

void blk_mq_debugfs_unregister_sched(struct request_queue *q)
{
	debugfs_remove_recursive(q->sched_debugfs_dir);
	q->sched_debugfs_dir = NULL;
}

int blk_mq_debugfs_register_sched_hctx(struct request_queue *q,
				       struct blk_mq_hw_ctx *hctx)
{
	struct elevator_type *e = q->elevator->type;

	if (!hctx->debugfs_dir)
		return -ENOENT;

	if (!e->hctx_debugfs_attrs)
		return 0;

	hctx->sched_debugfs_dir = debugfs_create_dir("sched",
						     hctx->debugfs_dir);
	if (!hctx->sched_debugfs_dir)
		return -ENOMEM;

	if (!debugfs_create_files(hctx->sched_debugfs_dir, hctx,
				  e->hctx_debugfs_attrs))
		return -ENOMEM;

	return 0;
}

void blk_mq_debugfs_unregister_sched_hctx(struct blk_mq_hw_ctx *hctx)
{
	debugfs_remove_recursive(hctx->sched_debugfs_dir);
	hctx->sched_debugfs_dir = NULL;
}