summaryrefslogtreecommitdiff
path: root/block/blk-sysfs.c
blob: 60116d13cb80436147109f4ec7f4cf14be92ae8f (plain) (blame)
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
// SPDX-License-Identifier: GPL-2.0
/*
 * Functions related to sysfs handling
 */
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/module.h>
#include <linux/bio.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/blktrace_api.h>
#include <linux/debugfs.h>

#include "blk.h"
#include "blk-mq.h"
#include "blk-mq-debugfs.h"
#include "blk-mq-sched.h"
#include "blk-rq-qos.h"
#include "blk-wbt.h"
#include "blk-cgroup.h"
#include "blk-throttle.h"

struct queue_sysfs_entry {
	struct attribute attr;
	ssize_t (*show)(struct gendisk *disk, char *page);
	ssize_t (*store)(struct gendisk *disk, const char *page, size_t count);
};

static ssize_t
queue_var_show(unsigned long var, char *page)
{
	return sprintf(page, "%lu\n", var);
}

static ssize_t
queue_var_store(unsigned long *var, const char *page, size_t count)
{
	int err;
	unsigned long v;

	err = kstrtoul(page, 10, &v);
	if (err || v > UINT_MAX)
		return -EINVAL;

	*var = v;

	return count;
}

static ssize_t queue_requests_show(struct gendisk *disk, char *page)
{
	return queue_var_show(disk->queue->nr_requests, page);
}

static ssize_t
queue_requests_store(struct gendisk *disk, const char *page, size_t count)
{
	unsigned long nr;
	int ret, err;

	if (!queue_is_mq(disk->queue))
		return -EINVAL;

	ret = queue_var_store(&nr, page, count);
	if (ret < 0)
		return ret;

	if (nr < BLKDEV_MIN_RQ)
		nr = BLKDEV_MIN_RQ;

	err = blk_mq_update_nr_requests(disk->queue, nr);
	if (err)
		return err;

	return ret;
}

static ssize_t queue_ra_show(struct gendisk *disk, char *page)
{
	return queue_var_show(disk->bdi->ra_pages << (PAGE_SHIFT - 10), page);
}

static ssize_t
queue_ra_store(struct gendisk *disk, const char *page, size_t count)
{
	unsigned long ra_kb;
	ssize_t ret;

	ret = queue_var_store(&ra_kb, page, count);
	if (ret < 0)
		return ret;
	disk->bdi->ra_pages = ra_kb >> (PAGE_SHIFT - 10);
	return ret;
}

#define QUEUE_SYSFS_LIMIT_SHOW(_field)					\
static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
{									\
	return queue_var_show(disk->queue->limits._field, page);	\
}

QUEUE_SYSFS_LIMIT_SHOW(max_segments)
QUEUE_SYSFS_LIMIT_SHOW(max_discard_segments)
QUEUE_SYSFS_LIMIT_SHOW(max_integrity_segments)
QUEUE_SYSFS_LIMIT_SHOW(max_segment_size)
QUEUE_SYSFS_LIMIT_SHOW(logical_block_size)
QUEUE_SYSFS_LIMIT_SHOW(physical_block_size)
QUEUE_SYSFS_LIMIT_SHOW(chunk_sectors)
QUEUE_SYSFS_LIMIT_SHOW(io_min)
QUEUE_SYSFS_LIMIT_SHOW(io_opt)
QUEUE_SYSFS_LIMIT_SHOW(discard_granularity)
QUEUE_SYSFS_LIMIT_SHOW(zone_write_granularity)
QUEUE_SYSFS_LIMIT_SHOW(virt_boundary_mask)
QUEUE_SYSFS_LIMIT_SHOW(dma_alignment)
QUEUE_SYSFS_LIMIT_SHOW(max_open_zones)
QUEUE_SYSFS_LIMIT_SHOW(max_active_zones)
QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_min)
QUEUE_SYSFS_LIMIT_SHOW(atomic_write_unit_max)

#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(_field)			\
static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
{									\
	return sprintf(page, "%llu\n",					\
		(unsigned long long)disk->queue->limits._field <<	\
			SECTOR_SHIFT);					\
}

QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_discard_sectors)
QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_discard_sectors)
QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_write_zeroes_sectors)
QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_max_sectors)
QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_boundary_sectors)

#define QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(_field)			\
static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
{									\
	return queue_var_show(disk->queue->limits._field >> 1, page);	\
}

QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_sectors)
QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_KB(max_hw_sectors)

#define QUEUE_SYSFS_SHOW_CONST(_name, _val)				\
static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
{									\
	return sprintf(page, "%d\n", _val);				\
}

/* deprecated fields */
QUEUE_SYSFS_SHOW_CONST(discard_zeroes_data, 0)
QUEUE_SYSFS_SHOW_CONST(write_same_max, 0)
QUEUE_SYSFS_SHOW_CONST(poll_delay, -1)

static ssize_t queue_max_discard_sectors_store(struct gendisk *disk,
		const char *page, size_t count)
{
	unsigned long max_discard_bytes;
	struct queue_limits lim;
	ssize_t ret;
	int err;

	ret = queue_var_store(&max_discard_bytes, page, count);
	if (ret < 0)
		return ret;

	if (max_discard_bytes & (disk->queue->limits.discard_granularity - 1))
		return -EINVAL;

	if ((max_discard_bytes >> SECTOR_SHIFT) > UINT_MAX)
		return -EINVAL;

	lim = queue_limits_start_update(disk->queue);
	lim.max_user_discard_sectors = max_discard_bytes >> SECTOR_SHIFT;
	err = queue_limits_commit_update(disk->queue, &lim);
	if (err)
		return err;
	return ret;
}

/*
 * For zone append queue_max_zone_append_sectors does not just return the
 * underlying queue limits, but actually contains a calculation.  Because of
 * that we can't simply use QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES here.
 */
static ssize_t queue_zone_append_max_show(struct gendisk *disk, char *page)
{
	return sprintf(page, "%llu\n",
		(u64)queue_max_zone_append_sectors(disk->queue) <<
			SECTOR_SHIFT);
}

static ssize_t
queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count)
{
	unsigned long max_sectors_kb;
	struct queue_limits lim;
	ssize_t ret;
	int err;

	ret = queue_var_store(&max_sectors_kb, page, count);
	if (ret < 0)
		return ret;

	lim = queue_limits_start_update(disk->queue);
	lim.max_user_sectors = max_sectors_kb << 1;
	err = queue_limits_commit_update(disk->queue, &lim);
	if (err)
		return err;
	return ret;
}

static ssize_t queue_feature_store(struct gendisk *disk, const char *page,
		size_t count, blk_features_t feature)
{
	struct queue_limits lim;
	unsigned long val;
	ssize_t ret;

	ret = queue_var_store(&val, page, count);
	if (ret < 0)
		return ret;

	lim = queue_limits_start_update(disk->queue);
	if (val)
		lim.features |= feature;
	else
		lim.features &= ~feature;
	ret = queue_limits_commit_update(disk->queue, &lim);
	if (ret)
		return ret;
	return count;
}

#define QUEUE_SYSFS_FEATURE(_name, _feature)				\
static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
{									\
	return sprintf(page, "%u\n",					\
		!!(disk->queue->limits.features & _feature));		\
}									\
static ssize_t queue_##_name##_store(struct gendisk *disk,		\
		const char *page, size_t count)				\
{									\
	return queue_feature_store(disk, page, count, _feature);	\
}

QUEUE_SYSFS_FEATURE(rotational, BLK_FEAT_ROTATIONAL)
QUEUE_SYSFS_FEATURE(add_random, BLK_FEAT_ADD_RANDOM)
QUEUE_SYSFS_FEATURE(iostats, BLK_FEAT_IO_STAT)
QUEUE_SYSFS_FEATURE(stable_writes, BLK_FEAT_STABLE_WRITES);

#define QUEUE_SYSFS_FEATURE_SHOW(_name, _feature)			\
static ssize_t queue_##_name##_show(struct gendisk *disk, char *page)	\
{									\
	return sprintf(page, "%u\n",					\
		!!(disk->queue->limits.features & _feature));		\
}

QUEUE_SYSFS_FEATURE_SHOW(poll, BLK_FEAT_POLL);
QUEUE_SYSFS_FEATURE_SHOW(fua, BLK_FEAT_FUA);
QUEUE_SYSFS_FEATURE_SHOW(dax, BLK_FEAT_DAX);

static ssize_t queue_zoned_show(struct gendisk *disk, char *page)
{
	if (blk_queue_is_zoned(disk->queue))
		return sprintf(page, "host-managed\n");
	return sprintf(page, "none\n");
}

static ssize_t queue_nr_zones_show(struct gendisk *disk, char *page)
{
	return queue_var_show(disk_nr_zones(disk), page);
}

static ssize_t queue_nomerges_show(struct gendisk *disk, char *page)
{
	return queue_var_show((blk_queue_nomerges(disk->queue) << 1) |
			       blk_queue_noxmerges(disk->queue), page);
}

static ssize_t queue_nomerges_store(struct gendisk *disk, const char *page,
				    size_t count)
{
	unsigned long nm;
	ssize_t ret = queue_var_store(&nm, page, count);

	if (ret < 0)
		return ret;

	blk_queue_flag_clear(QUEUE_FLAG_NOMERGES, disk->queue);
	blk_queue_flag_clear(QUEUE_FLAG_NOXMERGES, disk->queue);
	if (nm == 2)
		blk_queue_flag_set(QUEUE_FLAG_NOMERGES, disk->queue);
	else if (nm)
		blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, disk->queue);

	return ret;
}

static ssize_t queue_rq_affinity_show(struct gendisk *disk, char *page)
{
	bool set = test_bit(QUEUE_FLAG_SAME_COMP, &disk->queue->queue_flags);
	bool force = test_bit(QUEUE_FLAG_SAME_FORCE, &disk->queue->queue_flags);

	return queue_var_show(set << force, page);
}

static ssize_t
queue_rq_affinity_store(struct gendisk *disk, const char *page, size_t count)
{
	ssize_t ret = -EINVAL;
#ifdef CONFIG_SMP
	struct request_queue *q = disk->queue;
	unsigned long val;

	ret = queue_var_store(&val, page, count);
	if (ret < 0)
		return ret;

	if (val == 2) {
		blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
		blk_queue_flag_set(QUEUE_FLAG_SAME_FORCE, q);
	} else if (val == 1) {
		blk_queue_flag_set(QUEUE_FLAG_SAME_COMP, q);
		blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
	} else if (val == 0) {
		blk_queue_flag_clear(QUEUE_FLAG_SAME_COMP, q);
		blk_queue_flag_clear(QUEUE_FLAG_SAME_FORCE, q);
	}
#endif
	return ret;
}

static ssize_t queue_poll_delay_store(struct gendisk *disk, const char *page,
				size_t count)
{
	return count;
}

static ssize_t queue_poll_store(struct gendisk *disk, const char *page,
				size_t count)
{
	if (!(disk->queue->limits.features & BLK_FEAT_POLL))
		return -EINVAL;
	pr_info_ratelimited("writes to the poll attribute are ignored.\n");
	pr_info_ratelimited("please use driver specific parameters instead.\n");
	return count;
}

static ssize_t queue_io_timeout_show(struct gendisk *disk, char *page)
{
	return sprintf(page, "%u\n", jiffies_to_msecs(disk->queue->rq_timeout));
}

static ssize_t queue_io_timeout_store(struct gendisk *disk, const char *page,
				  size_t count)
{
	unsigned int val;
	int err;

	err = kstrtou32(page, 10, &val);
	if (err || val == 0)
		return -EINVAL;

	blk_queue_rq_timeout(disk->queue, msecs_to_jiffies(val));

	return count;
}

static ssize_t queue_wc_show(struct gendisk *disk, char *page)
{
	if (blk_queue_write_cache(disk->queue))
		return sprintf(page, "write back\n");
	return sprintf(page, "write through\n");
}

static ssize_t queue_wc_store(struct gendisk *disk, const char *page,
			      size_t count)
{
	struct queue_limits lim;
	bool disable;
	int err;

	if (!strncmp(page, "write back", 10)) {
		disable = false;
	} else if (!strncmp(page, "write through", 13) ||
		   !strncmp(page, "none", 4)) {
		disable = true;
	} else {
		return -EINVAL;
	}

	lim = queue_limits_start_update(disk->queue);
	if (disable)
		lim.flags |= BLK_FLAG_WRITE_CACHE_DISABLED;
	else
		lim.flags &= ~BLK_FLAG_WRITE_CACHE_DISABLED;
	err = queue_limits_commit_update(disk->queue, &lim);
	if (err)
		return err;
	return count;
}

#define QUEUE_RO_ENTRY(_prefix, _name)			\
static struct queue_sysfs_entry _prefix##_entry = {	\
	.attr	= { .name = _name, .mode = 0444 },	\
	.show	= _prefix##_show,			\
};

#define QUEUE_RW_ENTRY(_prefix, _name)			\
static struct queue_sysfs_entry _prefix##_entry = {	\
	.attr	= { .name = _name, .mode = 0644 },	\
	.show	= _prefix##_show,			\
	.store	= _prefix##_store,			\
};

QUEUE_RW_ENTRY(queue_requests, "nr_requests");
QUEUE_RW_ENTRY(queue_ra, "read_ahead_kb");
QUEUE_RW_ENTRY(queue_max_sectors, "max_sectors_kb");
QUEUE_RO_ENTRY(queue_max_hw_sectors, "max_hw_sectors_kb");
QUEUE_RO_ENTRY(queue_max_segments, "max_segments");
QUEUE_RO_ENTRY(queue_max_integrity_segments, "max_integrity_segments");
QUEUE_RO_ENTRY(queue_max_segment_size, "max_segment_size");
QUEUE_RW_ENTRY(elv_iosched, "scheduler");

QUEUE_RO_ENTRY(queue_logical_block_size, "logical_block_size");
QUEUE_RO_ENTRY(queue_physical_block_size, "physical_block_size");
QUEUE_RO_ENTRY(queue_chunk_sectors, "chunk_sectors");
QUEUE_RO_ENTRY(queue_io_min, "minimum_io_size");
QUEUE_RO_ENTRY(queue_io_opt, "optimal_io_size");

QUEUE_RO_ENTRY(queue_max_discard_segments, "max_discard_segments");
QUEUE_RO_ENTRY(queue_discard_granularity, "discard_granularity");
QUEUE_RO_ENTRY(queue_max_hw_discard_sectors, "discard_max_hw_bytes");
QUEUE_RW_ENTRY(queue_max_discard_sectors, "discard_max_bytes");
QUEUE_RO_ENTRY(queue_discard_zeroes_data, "discard_zeroes_data");

QUEUE_RO_ENTRY(queue_atomic_write_max_sectors, "atomic_write_max_bytes");
QUEUE_RO_ENTRY(queue_atomic_write_boundary_sectors,
		"atomic_write_boundary_bytes");
QUEUE_RO_ENTRY(queue_atomic_write_unit_max, "atomic_write_unit_max_bytes");
QUEUE_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes");

QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes");
QUEUE_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes");
QUEUE_RO_ENTRY(queue_zone_append_max, "zone_append_max_bytes");
QUEUE_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity");

QUEUE_RO_ENTRY(queue_zoned, "zoned");
QUEUE_RO_ENTRY(queue_nr_zones, "nr_zones");
QUEUE_RO_ENTRY(queue_max_open_zones, "max_open_zones");
QUEUE_RO_ENTRY(queue_max_active_zones, "max_active_zones");

QUEUE_RW_ENTRY(queue_nomerges, "nomerges");
QUEUE_RW_ENTRY(queue_rq_affinity, "rq_affinity");
QUEUE_RW_ENTRY(queue_poll, "io_poll");
QUEUE_RW_ENTRY(queue_poll_delay, "io_poll_delay");
QUEUE_RW_ENTRY(queue_wc, "write_cache");
QUEUE_RO_ENTRY(queue_fua, "fua");
QUEUE_RO_ENTRY(queue_dax, "dax");
QUEUE_RW_ENTRY(queue_io_timeout, "io_timeout");
QUEUE_RO_ENTRY(queue_virt_boundary_mask, "virt_boundary_mask");
QUEUE_RO_ENTRY(queue_dma_alignment, "dma_alignment");

/* legacy alias for logical_block_size: */
static struct queue_sysfs_entry queue_hw_sector_size_entry = {
	.attr = {.name = "hw_sector_size", .mode = 0444 },
	.show = queue_logical_block_size_show,
};

QUEUE_RW_ENTRY(queue_rotational, "rotational");
QUEUE_RW_ENTRY(queue_iostats, "iostats");
QUEUE_RW_ENTRY(queue_add_random, "add_random");
QUEUE_RW_ENTRY(queue_stable_writes, "stable_writes");

#ifdef CONFIG_BLK_WBT
static ssize_t queue_var_store64(s64 *var, const char *page)
{
	int err;
	s64 v;

	err = kstrtos64(page, 10, &v);
	if (err < 0)
		return err;

	*var = v;
	return 0;
}

static ssize_t queue_wb_lat_show(struct gendisk *disk, char *page)
{
	if (!wbt_rq_qos(disk->queue))
		return -EINVAL;

	if (wbt_disabled(disk->queue))
		return sprintf(page, "0\n");

	return sprintf(page, "%llu\n",
		div_u64(wbt_get_min_lat(disk->queue), 1000));
}

static ssize_t queue_wb_lat_store(struct gendisk *disk, const char *page,
				  size_t count)
{
	struct request_queue *q = disk->queue;
	struct rq_qos *rqos;
	ssize_t ret;
	s64 val;

	ret = queue_var_store64(&val, page);
	if (ret < 0)
		return ret;
	if (val < -1)
		return -EINVAL;

	rqos = wbt_rq_qos(q);
	if (!rqos) {
		ret = wbt_init(disk);
		if (ret)
			return ret;
	}

	if (val == -1)
		val = wbt_default_latency_nsec(q);
	else if (val >= 0)
		val *= 1000ULL;

	if (wbt_get_min_lat(q) == val)
		return count;

	/*
	 * Ensure that the queue is idled, in case the latency update
	 * ends up either enabling or disabling wbt completely. We can't
	 * have IO inflight if that happens.
	 */
	blk_mq_quiesce_queue(q);

	wbt_set_min_lat(q, val);

	blk_mq_unquiesce_queue(q);

	return count;
}

QUEUE_RW_ENTRY(queue_wb_lat, "wbt_lat_usec");
#endif

/* Common attributes for bio-based and request-based queues. */
static struct attribute *queue_attrs[] = {
	&queue_ra_entry.attr,
	&queue_max_hw_sectors_entry.attr,
	&queue_max_sectors_entry.attr,
	&queue_max_segments_entry.attr,
	&queue_max_discard_segments_entry.attr,
	&queue_max_integrity_segments_entry.attr,
	&queue_max_segment_size_entry.attr,
	&queue_hw_sector_size_entry.attr,
	&queue_logical_block_size_entry.attr,
	&queue_physical_block_size_entry.attr,
	&queue_chunk_sectors_entry.attr,
	&queue_io_min_entry.attr,
	&queue_io_opt_entry.attr,
	&queue_discard_granularity_entry.attr,
	&queue_max_discard_sectors_entry.attr,
	&queue_max_hw_discard_sectors_entry.attr,
	&queue_discard_zeroes_data_entry.attr,
	&queue_atomic_write_max_sectors_entry.attr,
	&queue_atomic_write_boundary_sectors_entry.attr,
	&queue_atomic_write_unit_min_entry.attr,
	&queue_atomic_write_unit_max_entry.attr,
	&queue_write_same_max_entry.attr,
	&queue_max_write_zeroes_sectors_entry.attr,
	&queue_zone_append_max_entry.attr,
	&queue_zone_write_granularity_entry.attr,
	&queue_rotational_entry.attr,
	&queue_zoned_entry.attr,
	&queue_nr_zones_entry.attr,
	&queue_max_open_zones_entry.attr,
	&queue_max_active_zones_entry.attr,
	&queue_nomerges_entry.attr,
	&queue_iostats_entry.attr,
	&queue_stable_writes_entry.attr,
	&queue_add_random_entry.attr,
	&queue_poll_entry.attr,
	&queue_wc_entry.attr,
	&queue_fua_entry.attr,
	&queue_dax_entry.attr,
	&queue_poll_delay_entry.attr,
	&queue_virt_boundary_mask_entry.attr,
	&queue_dma_alignment_entry.attr,
	NULL,
};

/* Request-based queue attributes that are not relevant for bio-based queues. */
static struct attribute *blk_mq_queue_attrs[] = {
	&queue_requests_entry.attr,
	&elv_iosched_entry.attr,
	&queue_rq_affinity_entry.attr,
	&queue_io_timeout_entry.attr,
#ifdef CONFIG_BLK_WBT
	&queue_wb_lat_entry.attr,
#endif
	NULL,
};

static umode_t queue_attr_visible(struct kobject *kobj, struct attribute *attr,
				int n)
{
	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
	struct request_queue *q = disk->queue;

	if ((attr == &queue_max_open_zones_entry.attr ||
	     attr == &queue_max_active_zones_entry.attr) &&
	    !blk_queue_is_zoned(q))
		return 0;

	return attr->mode;
}

static umode_t blk_mq_queue_attr_visible(struct kobject *kobj,
					 struct attribute *attr, int n)
{
	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
	struct request_queue *q = disk->queue;

	if (!queue_is_mq(q))
		return 0;

	if (attr == &queue_io_timeout_entry.attr && !q->mq_ops->timeout)
		return 0;

	return attr->mode;
}

static struct attribute_group queue_attr_group = {
	.attrs = queue_attrs,
	.is_visible = queue_attr_visible,
};

static struct attribute_group blk_mq_queue_attr_group = {
	.attrs = blk_mq_queue_attrs,
	.is_visible = blk_mq_queue_attr_visible,
};

#define to_queue(atr) container_of((atr), struct queue_sysfs_entry, attr)

static ssize_t
queue_attr_show(struct kobject *kobj, struct attribute *attr, char *page)
{
	struct queue_sysfs_entry *entry = to_queue(attr);
	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
	ssize_t res;

	if (!entry->show)
		return -EIO;
	mutex_lock(&disk->queue->sysfs_lock);
	res = entry->show(disk, page);
	mutex_unlock(&disk->queue->sysfs_lock);
	return res;
}

static ssize_t
queue_attr_store(struct kobject *kobj, struct attribute *attr,
		    const char *page, size_t length)
{
	struct queue_sysfs_entry *entry = to_queue(attr);
	struct gendisk *disk = container_of(kobj, struct gendisk, queue_kobj);
	struct request_queue *q = disk->queue;
	ssize_t res;

	if (!entry->store)
		return -EIO;

	blk_mq_freeze_queue(q);
	mutex_lock(&q->sysfs_lock);
	res = entry->store(disk, page, length);
	mutex_unlock(&q->sysfs_lock);
	blk_mq_unfreeze_queue(q);
	return res;
}

static const struct sysfs_ops queue_sysfs_ops = {
	.show	= queue_attr_show,
	.store	= queue_attr_store,
};

static const struct attribute_group *blk_queue_attr_groups[] = {
	&queue_attr_group,
	&blk_mq_queue_attr_group,
	NULL
};

static void blk_queue_release(struct kobject *kobj)
{
	/* nothing to do here, all data is associated with the parent gendisk */
}

static const struct kobj_type blk_queue_ktype = {
	.default_groups = blk_queue_attr_groups,
	.sysfs_ops	= &queue_sysfs_ops,
	.release	= blk_queue_release,
};

static void blk_debugfs_remove(struct gendisk *disk)
{
	struct request_queue *q = disk->queue;

	mutex_lock(&q->debugfs_mutex);
	blk_trace_shutdown(q);
	debugfs_remove_recursive(q->debugfs_dir);
	q->debugfs_dir = NULL;
	q->sched_debugfs_dir = NULL;
	q->rqos_debugfs_dir = NULL;
	mutex_unlock(&q->debugfs_mutex);
}

/**
 * blk_register_queue - register a block layer queue with sysfs
 * @disk: Disk of which the request queue should be registered with sysfs.
 */
int blk_register_queue(struct gendisk *disk)
{
	struct request_queue *q = disk->queue;
	int ret;

	mutex_lock(&q->sysfs_dir_lock);
	kobject_init(&disk->queue_kobj, &blk_queue_ktype);
	ret = kobject_add(&disk->queue_kobj, &disk_to_dev(disk)->kobj, "queue");
	if (ret < 0)
		goto out_put_queue_kobj;

	if (queue_is_mq(q)) {
		ret = blk_mq_sysfs_register(disk);
		if (ret)
			goto out_put_queue_kobj;
	}
	mutex_lock(&q->sysfs_lock);

	mutex_lock(&q->debugfs_mutex);
	q->debugfs_dir = debugfs_create_dir(disk->disk_name, blk_debugfs_root);
	if (queue_is_mq(q))
		blk_mq_debugfs_register(q);
	mutex_unlock(&q->debugfs_mutex);

	ret = disk_register_independent_access_ranges(disk);
	if (ret)
		goto out_debugfs_remove;

	if (q->elevator) {
		ret = elv_register_queue(q, false);
		if (ret)
			goto out_unregister_ia_ranges;
	}

	ret = blk_crypto_sysfs_register(disk);
	if (ret)
		goto out_elv_unregister;

	blk_queue_flag_set(QUEUE_FLAG_REGISTERED, q);
	wbt_enable_default(disk);

	/* Now everything is ready and send out KOBJ_ADD uevent */
	kobject_uevent(&disk->queue_kobj, KOBJ_ADD);
	if (q->elevator)
		kobject_uevent(&q->elevator->kobj, KOBJ_ADD);
	mutex_unlock(&q->sysfs_lock);
	mutex_unlock(&q->sysfs_dir_lock);

	/*
	 * SCSI probing may synchronously create and destroy a lot of
	 * request_queues for non-existent devices.  Shutting down a fully
	 * functional queue takes measureable wallclock time as RCU grace
	 * periods are involved.  To avoid excessive latency in these
	 * cases, a request_queue starts out in a degraded mode which is
	 * faster to shut down and is made fully functional here as
	 * request_queues for non-existent devices never get registered.
	 */
	if (!blk_queue_init_done(q)) {
		blk_queue_flag_set(QUEUE_FLAG_INIT_DONE, q);
		percpu_ref_switch_to_percpu(&q->q_usage_counter);
	}

	return ret;

out_elv_unregister:
	elv_unregister_queue(q);
out_unregister_ia_ranges:
	disk_unregister_independent_access_ranges(disk);
out_debugfs_remove:
	blk_debugfs_remove(disk);
	mutex_unlock(&q->sysfs_lock);
out_put_queue_kobj:
	kobject_put(&disk->queue_kobj);
	mutex_unlock(&q->sysfs_dir_lock);
	return ret;
}

/**
 * blk_unregister_queue - counterpart of blk_register_queue()
 * @disk: Disk of which the request queue should be unregistered from sysfs.
 *
 * Note: the caller is responsible for guaranteeing that this function is called
 * after blk_register_queue() has finished.
 */
void blk_unregister_queue(struct gendisk *disk)
{
	struct request_queue *q = disk->queue;

	if (WARN_ON(!q))
		return;

	/* Return early if disk->queue was never registered. */
	if (!blk_queue_registered(q))
		return;

	/*
	 * Since sysfs_remove_dir() prevents adding new directory entries
	 * before removal of existing entries starts, protect against
	 * concurrent elv_iosched_store() calls.
	 */
	mutex_lock(&q->sysfs_lock);
	blk_queue_flag_clear(QUEUE_FLAG_REGISTERED, q);
	mutex_unlock(&q->sysfs_lock);

	mutex_lock(&q->sysfs_dir_lock);
	/*
	 * Remove the sysfs attributes before unregistering the queue data
	 * structures that can be modified through sysfs.
	 */
	if (queue_is_mq(q))
		blk_mq_sysfs_unregister(disk);
	blk_crypto_sysfs_unregister(disk);

	mutex_lock(&q->sysfs_lock);
	elv_unregister_queue(q);
	disk_unregister_independent_access_ranges(disk);
	mutex_unlock(&q->sysfs_lock);

	/* Now that we've deleted all child objects, we can delete the queue. */
	kobject_uevent(&disk->queue_kobj, KOBJ_REMOVE);
	kobject_del(&disk->queue_kobj);
	mutex_unlock(&q->sysfs_dir_lock);

	blk_debugfs_remove(disk);
}