summaryrefslogtreecommitdiff
path: root/block/blk-settings.c
blob: 62588d9a38e39a999888c3edfc002c76cba02f85 (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
// SPDX-License-Identifier: GPL-2.0
/*
 * Functions related to setting various queue properties from drivers
 */
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/bio.h>
#include <linux/blk-integrity.h>
#include <linux/pagemap.h>
#include <linux/backing-dev-defs.h>
#include <linux/gcd.h>
#include <linux/lcm.h>
#include <linux/jiffies.h>
#include <linux/gfp.h>
#include <linux/dma-mapping.h>

#include "blk.h"
#include "blk-rq-qos.h"
#include "blk-wbt.h"

void blk_queue_rq_timeout(struct request_queue *q, unsigned int timeout)
{
	q->rq_timeout = timeout;
}
EXPORT_SYMBOL_GPL(blk_queue_rq_timeout);

/**
 * blk_set_stacking_limits - set default limits for stacking devices
 * @lim:  the queue_limits structure to reset
 *
 * Prepare queue limits for applying limits from underlying devices using
 * blk_stack_limits().
 */
void blk_set_stacking_limits(struct queue_limits *lim)
{
	memset(lim, 0, sizeof(*lim));
	lim->logical_block_size = SECTOR_SIZE;
	lim->physical_block_size = SECTOR_SIZE;
	lim->io_min = SECTOR_SIZE;
	lim->discard_granularity = SECTOR_SIZE;
	lim->dma_alignment = SECTOR_SIZE - 1;
	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;

	/* Inherit limits from component devices */
	lim->max_segments = USHRT_MAX;
	lim->max_discard_segments = USHRT_MAX;
	lim->max_hw_sectors = UINT_MAX;
	lim->max_segment_size = UINT_MAX;
	lim->max_sectors = UINT_MAX;
	lim->max_dev_sectors = UINT_MAX;
	lim->max_write_zeroes_sectors = UINT_MAX;
	lim->max_zone_append_sectors = UINT_MAX;
	lim->max_user_discard_sectors = UINT_MAX;
}
EXPORT_SYMBOL(blk_set_stacking_limits);

static void blk_apply_bdi_limits(struct backing_dev_info *bdi,
		struct queue_limits *lim)
{
	/*
	 * For read-ahead of large files to be effective, we need to read ahead
	 * at least twice the optimal I/O size.
	 */
	bdi->ra_pages = max(lim->io_opt * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
	bdi->io_pages = lim->max_sectors >> PAGE_SECTORS_SHIFT;
}

static int blk_validate_zoned_limits(struct queue_limits *lim)
{
	if (!(lim->features & BLK_FEAT_ZONED)) {
		if (WARN_ON_ONCE(lim->max_open_zones) ||
		    WARN_ON_ONCE(lim->max_active_zones) ||
		    WARN_ON_ONCE(lim->zone_write_granularity) ||
		    WARN_ON_ONCE(lim->max_zone_append_sectors))
			return -EINVAL;
		return 0;
	}

	if (WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED)))
		return -EINVAL;

	if (lim->zone_write_granularity < lim->logical_block_size)
		lim->zone_write_granularity = lim->logical_block_size;

	if (lim->max_zone_append_sectors) {
		/*
		 * The Zone Append size is limited by the maximum I/O size
		 * and the zone size given that it can't span zones.
		 */
		lim->max_zone_append_sectors =
			min3(lim->max_hw_sectors,
			     lim->max_zone_append_sectors,
			     lim->chunk_sectors);
	}

	return 0;
}

static int blk_validate_integrity_limits(struct queue_limits *lim)
{
	struct blk_integrity *bi = &lim->integrity;

	if (!bi->tuple_size) {
		if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
		    bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
			pr_warn("invalid PI settings.\n");
			return -EINVAL;
		}
		return 0;
	}

	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
		pr_warn("integrity support disabled.\n");
		return -EINVAL;
	}

	if (bi->csum_type == BLK_INTEGRITY_CSUM_NONE &&
	    (bi->flags & BLK_INTEGRITY_REF_TAG)) {
		pr_warn("ref tag not support without checksum.\n");
		return -EINVAL;
	}

	if (!bi->interval_exp)
		bi->interval_exp = ilog2(lim->logical_block_size);

	return 0;
}

/*
 * Check that the limits in lim are valid, initialize defaults for unset
 * values, and cap values based on others where needed.
 */
static int blk_validate_limits(struct queue_limits *lim)
{
	unsigned int max_hw_sectors;
	unsigned int logical_block_sectors;
	int err;

	/*
	 * Unless otherwise specified, default to 512 byte logical blocks and a
	 * physical block size equal to the logical block size.
	 */
	if (!lim->logical_block_size)
		lim->logical_block_size = SECTOR_SIZE;
	if (lim->physical_block_size < lim->logical_block_size)
		lim->physical_block_size = lim->logical_block_size;

	/*
	 * The minimum I/O size defaults to the physical block size unless
	 * explicitly overridden.
	 */
	if (lim->io_min < lim->physical_block_size)
		lim->io_min = lim->physical_block_size;

	/*
	 * max_hw_sectors has a somewhat weird default for historical reason,
	 * but driver really should set their own instead of relying on this
	 * value.
	 *
	 * The block layer relies on the fact that every driver can
	 * handle at lest a page worth of data per I/O, and needs the value
	 * aligned to the logical block size.
	 */
	if (!lim->max_hw_sectors)
		lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
	if (WARN_ON_ONCE(lim->max_hw_sectors < PAGE_SECTORS))
		return -EINVAL;
	logical_block_sectors = lim->logical_block_size >> SECTOR_SHIFT;
	if (WARN_ON_ONCE(logical_block_sectors > lim->max_hw_sectors))
		return -EINVAL;
	lim->max_hw_sectors = round_down(lim->max_hw_sectors,
			logical_block_sectors);

	/*
	 * The actual max_sectors value is a complex beast and also takes the
	 * max_dev_sectors value (set by SCSI ULPs) and a user configurable
	 * value into account.  The ->max_sectors value is always calculated
	 * from these, so directly setting it won't have any effect.
	 */
	max_hw_sectors = min_not_zero(lim->max_hw_sectors,
				lim->max_dev_sectors);
	if (lim->max_user_sectors) {
		if (lim->max_user_sectors < PAGE_SIZE / SECTOR_SIZE)
			return -EINVAL;
		lim->max_sectors = min(max_hw_sectors, lim->max_user_sectors);
	} else if (lim->io_opt) {
		lim->max_sectors =
			min(max_hw_sectors, lim->io_opt >> SECTOR_SHIFT);
	} else if (lim->io_min &&
		   lim->io_min > (BLK_DEF_MAX_SECTORS_CAP << SECTOR_SHIFT)) {
		lim->max_sectors =
			min(max_hw_sectors, lim->io_min >> SECTOR_SHIFT);
	} else {
		lim->max_sectors = min(max_hw_sectors, BLK_DEF_MAX_SECTORS_CAP);
	}
	lim->max_sectors = round_down(lim->max_sectors,
			logical_block_sectors);

	/*
	 * Random default for the maximum number of segments.  Driver should not
	 * rely on this and set their own.
	 */
	if (!lim->max_segments)
		lim->max_segments = BLK_MAX_SEGMENTS;

	lim->max_discard_sectors =
		min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors);

	if (!lim->max_discard_segments)
		lim->max_discard_segments = 1;

	if (lim->discard_granularity < lim->physical_block_size)
		lim->discard_granularity = lim->physical_block_size;

	/*
	 * By default there is no limit on the segment boundary alignment,
	 * but if there is one it can't be smaller than the page size as
	 * that would break all the normal I/O patterns.
	 */
	if (!lim->seg_boundary_mask)
		lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
	if (WARN_ON_ONCE(lim->seg_boundary_mask < PAGE_SIZE - 1))
		return -EINVAL;

	/*
	 * Stacking device may have both virtual boundary and max segment
	 * size limit, so allow this setting now, and long-term the two
	 * might need to move out of stacking limits since we have immutable
	 * bvec and lower layer bio splitting is supposed to handle the two
	 * correctly.
	 */
	if (lim->virt_boundary_mask) {
		if (!lim->max_segment_size)
			lim->max_segment_size = UINT_MAX;
	} else {
		/*
		 * The maximum segment size has an odd historic 64k default that
		 * drivers probably should override.  Just like the I/O size we
		 * require drivers to at least handle a full page per segment.
		 */
		if (!lim->max_segment_size)
			lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
		if (WARN_ON_ONCE(lim->max_segment_size < PAGE_SIZE))
			return -EINVAL;
	}

	/*
	 * We require drivers to at least do logical block aligned I/O, but
	 * historically could not check for that due to the separate calls
	 * to set the limits.  Once the transition is finished the check
	 * below should be narrowed down to check the logical block size.
	 */
	if (!lim->dma_alignment)
		lim->dma_alignment = SECTOR_SIZE - 1;
	if (WARN_ON_ONCE(lim->dma_alignment > PAGE_SIZE))
		return -EINVAL;

	if (lim->alignment_offset) {
		lim->alignment_offset &= (lim->physical_block_size - 1);
		lim->features &= ~BLK_FEAT_MISALIGNED;
	}

	if (!(lim->features & BLK_FEAT_WRITE_CACHE))
		lim->features &= ~BLK_FEAT_FUA;

	err = blk_validate_integrity_limits(lim);
	if (err)
		return err;
	return blk_validate_zoned_limits(lim);
}

/*
 * Set the default limits for a newly allocated queue.  @lim contains the
 * initial limits set by the driver, which could be no limit in which case
 * all fields are cleared to zero.
 */
int blk_set_default_limits(struct queue_limits *lim)
{
	/*
	 * Most defaults are set by capping the bounds in blk_validate_limits,
	 * but max_user_discard_sectors is special and needs an explicit
	 * initialization to the max value here.
	 */
	lim->max_user_discard_sectors = UINT_MAX;
	return blk_validate_limits(lim);
}

/**
 * queue_limits_commit_update - commit an atomic update of queue limits
 * @q:		queue to update
 * @lim:	limits to apply
 *
 * Apply the limits in @lim that were obtained from queue_limits_start_update()
 * and updated by the caller to @q.
 *
 * Returns 0 if successful, else a negative error code.
 */
int queue_limits_commit_update(struct request_queue *q,
		struct queue_limits *lim)
	__releases(q->limits_lock)
{
	int error;

	error = blk_validate_limits(lim);
	if (error)
		goto out_unlock;

#ifdef CONFIG_BLK_INLINE_ENCRYPTION
	if (q->crypto_profile && lim->integrity.tag_size) {
		pr_warn("blk-integrity: Integrity and hardware inline encryption are not supported together.\n");
		error = -EINVAL;
		goto out_unlock;
	}
#endif

	q->limits = *lim;
	if (q->disk)
		blk_apply_bdi_limits(q->disk->bdi, lim);
out_unlock:
	mutex_unlock(&q->limits_lock);
	return error;
}
EXPORT_SYMBOL_GPL(queue_limits_commit_update);

/**
 * queue_limits_set - apply queue limits to queue
 * @q:		queue to update
 * @lim:	limits to apply
 *
 * Apply the limits in @lim that were freshly initialized to @q.
 * To update existing limits use queue_limits_start_update() and
 * queue_limits_commit_update() instead.
 *
 * Returns 0 if successful, else a negative error code.
 */
int queue_limits_set(struct request_queue *q, struct queue_limits *lim)
{
	mutex_lock(&q->limits_lock);
	return queue_limits_commit_update(q, lim);
}
EXPORT_SYMBOL_GPL(queue_limits_set);

void disk_update_readahead(struct gendisk *disk)
{
	blk_apply_bdi_limits(disk->bdi, &disk->queue->limits);
}
EXPORT_SYMBOL_GPL(disk_update_readahead);

/**
 * blk_limits_io_min - set minimum request size for a device
 * @limits: the queue limits
 * @min:  smallest I/O size in bytes
 *
 * Description:
 *   Some devices have an internal block size bigger than the reported
 *   hardware sector size.  This function can be used to signal the
 *   smallest I/O the device can perform without incurring a performance
 *   penalty.
 */
void blk_limits_io_min(struct queue_limits *limits, unsigned int min)
{
	limits->io_min = min;

	if (limits->io_min < limits->logical_block_size)
		limits->io_min = limits->logical_block_size;

	if (limits->io_min < limits->physical_block_size)
		limits->io_min = limits->physical_block_size;
}
EXPORT_SYMBOL(blk_limits_io_min);

/**
 * blk_limits_io_opt - set optimal request size for a device
 * @limits: the queue limits
 * @opt:  smallest I/O size in bytes
 *
 * Description:
 *   Storage devices may report an optimal I/O size, which is the
 *   device's preferred unit for sustained I/O.  This is rarely reported
 *   for disk drives.  For RAID arrays it is usually the stripe width or
 *   the internal track size.  A properly aligned multiple of
 *   optimal_io_size is the preferred request size for workloads where
 *   sustained throughput is desired.
 */
void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt)
{
	limits->io_opt = opt;
}
EXPORT_SYMBOL(blk_limits_io_opt);

static int queue_limit_alignment_offset(const struct queue_limits *lim,
		sector_t sector)
{
	unsigned int granularity = max(lim->physical_block_size, lim->io_min);
	unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT)
		<< SECTOR_SHIFT;

	return (granularity + lim->alignment_offset - alignment) % granularity;
}

static unsigned int queue_limit_discard_alignment(
		const struct queue_limits *lim, sector_t sector)
{
	unsigned int alignment, granularity, offset;

	if (!lim->max_discard_sectors)
		return 0;

	/* Why are these in bytes, not sectors? */
	alignment = lim->discard_alignment >> SECTOR_SHIFT;
	granularity = lim->discard_granularity >> SECTOR_SHIFT;
	if (!granularity)
		return 0;

	/* Offset of the partition start in 'granularity' sectors */
	offset = sector_div(sector, granularity);

	/* And why do we do this modulus *again* in blkdev_issue_discard()? */
	offset = (granularity + alignment - offset) % granularity;

	/* Turn it back into bytes, gaah */
	return offset << SECTOR_SHIFT;
}

static unsigned int blk_round_down_sectors(unsigned int sectors, unsigned int lbs)
{
	sectors = round_down(sectors, lbs >> SECTOR_SHIFT);
	if (sectors < PAGE_SIZE >> SECTOR_SHIFT)
		sectors = PAGE_SIZE >> SECTOR_SHIFT;
	return sectors;
}

/**
 * blk_stack_limits - adjust queue_limits for stacked devices
 * @t:	the stacking driver limits (top device)
 * @b:  the underlying queue limits (bottom, component device)
 * @start:  first data sector within component device
 *
 * Description:
 *    This function is used by stacking drivers like MD and DM to ensure
 *    that all component devices have compatible block sizes and
 *    alignments.  The stacking driver must provide a queue_limits
 *    struct (top) and then iteratively call the stacking function for
 *    all component (bottom) devices.  The stacking function will
 *    attempt to combine the values and ensure proper alignment.
 *
 *    Returns 0 if the top and bottom queue_limits are compatible.  The
 *    top device's block sizes and alignment offsets may be adjusted to
 *    ensure alignment with the bottom device. If no compatible sizes
 *    and alignments exist, -1 is returned and the resulting top
 *    queue_limits will have the misaligned flag set to indicate that
 *    the alignment_offset is undefined.
 */
int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
		     sector_t start)
{
	unsigned int top, bottom, alignment, ret = 0;

	t->features |= (b->features & BLK_FEAT_INHERIT_MASK);

	/*
	 * BLK_FEAT_NOWAIT and BLK_FEAT_POLL need to be supported both by the
	 * stacking driver and all underlying devices.  The stacking driver sets
	 * the flags before stacking the limits, and this will clear the flags
	 * if any of the underlying devices does not support it.
	 */
	if (!(b->features & BLK_FEAT_NOWAIT))
		t->features &= ~BLK_FEAT_NOWAIT;
	if (!(b->features & BLK_FEAT_POLL))
		t->features &= ~BLK_FEAT_POLL;

	t->flags |= (b->flags & BLK_FEAT_MISALIGNED);

	t->max_sectors = min_not_zero(t->max_sectors, b->max_sectors);
	t->max_user_sectors = min_not_zero(t->max_user_sectors,
			b->max_user_sectors);
	t->max_hw_sectors = min_not_zero(t->max_hw_sectors, b->max_hw_sectors);
	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
					b->max_write_zeroes_sectors);
	t->max_zone_append_sectors = min(queue_limits_max_zone_append_sectors(t),
					 queue_limits_max_zone_append_sectors(b));

	t->seg_boundary_mask = min_not_zero(t->seg_boundary_mask,
					    b->seg_boundary_mask);
	t->virt_boundary_mask = min_not_zero(t->virt_boundary_mask,
					    b->virt_boundary_mask);

	t->max_segments = min_not_zero(t->max_segments, b->max_segments);
	t->max_discard_segments = min_not_zero(t->max_discard_segments,
					       b->max_discard_segments);
	t->max_integrity_segments = min_not_zero(t->max_integrity_segments,
						 b->max_integrity_segments);

	t->max_segment_size = min_not_zero(t->max_segment_size,
					   b->max_segment_size);

	alignment = queue_limit_alignment_offset(b, start);

	/* Bottom device has different alignment.  Check that it is
	 * compatible with the current top alignment.
	 */
	if (t->alignment_offset != alignment) {

		top = max(t->physical_block_size, t->io_min)
			+ t->alignment_offset;
		bottom = max(b->physical_block_size, b->io_min) + alignment;

		/* Verify that top and bottom intervals line up */
		if (max(top, bottom) % min(top, bottom)) {
			t->flags |= BLK_FEAT_MISALIGNED;
			ret = -1;
		}
	}

	t->logical_block_size = max(t->logical_block_size,
				    b->logical_block_size);

	t->physical_block_size = max(t->physical_block_size,
				     b->physical_block_size);

	t->io_min = max(t->io_min, b->io_min);
	t->io_opt = lcm_not_zero(t->io_opt, b->io_opt);
	t->dma_alignment = max(t->dma_alignment, b->dma_alignment);

	/* Set non-power-of-2 compatible chunk_sectors boundary */
	if (b->chunk_sectors)
		t->chunk_sectors = gcd(t->chunk_sectors, b->chunk_sectors);

	/* Physical block size a multiple of the logical block size? */
	if (t->physical_block_size & (t->logical_block_size - 1)) {
		t->physical_block_size = t->logical_block_size;
		t->flags |= BLK_FEAT_MISALIGNED;
		ret = -1;
	}

	/* Minimum I/O a multiple of the physical block size? */
	if (t->io_min & (t->physical_block_size - 1)) {
		t->io_min = t->physical_block_size;
		t->flags |= BLK_FEAT_MISALIGNED;
		ret = -1;
	}

	/* Optimal I/O a multiple of the physical block size? */
	if (t->io_opt & (t->physical_block_size - 1)) {
		t->io_opt = 0;
		t->flags |= BLK_FEAT_MISALIGNED;
		ret = -1;
	}

	/* chunk_sectors a multiple of the physical block size? */
	if ((t->chunk_sectors << 9) & (t->physical_block_size - 1)) {
		t->chunk_sectors = 0;
		t->flags |= BLK_FEAT_MISALIGNED;
		ret = -1;
	}

	t->raid_partial_stripes_expensive =
		max(t->raid_partial_stripes_expensive,
		    b->raid_partial_stripes_expensive);

	/* Find lowest common alignment_offset */
	t->alignment_offset = lcm_not_zero(t->alignment_offset, alignment)
		% max(t->physical_block_size, t->io_min);

	/* Verify that new alignment_offset is on a logical block boundary */
	if (t->alignment_offset & (t->logical_block_size - 1)) {
		t->flags |= BLK_FEAT_MISALIGNED;
		ret = -1;
	}

	t->max_sectors = blk_round_down_sectors(t->max_sectors, t->logical_block_size);
	t->max_hw_sectors = blk_round_down_sectors(t->max_hw_sectors, t->logical_block_size);
	t->max_dev_sectors = blk_round_down_sectors(t->max_dev_sectors, t->logical_block_size);

	/* Discard alignment and granularity */
	if (b->discard_granularity) {
		alignment = queue_limit_discard_alignment(b, start);

		t->max_discard_sectors = min_not_zero(t->max_discard_sectors,
						      b->max_discard_sectors);
		t->max_hw_discard_sectors = min_not_zero(t->max_hw_discard_sectors,
							 b->max_hw_discard_sectors);
		t->discard_granularity = max(t->discard_granularity,
					     b->discard_granularity);
		t->discard_alignment = lcm_not_zero(t->discard_alignment, alignment) %
			t->discard_granularity;
	}
	t->max_secure_erase_sectors = min_not_zero(t->max_secure_erase_sectors,
						   b->max_secure_erase_sectors);
	t->zone_write_granularity = max(t->zone_write_granularity,
					b->zone_write_granularity);
	if (!(t->features & BLK_FEAT_ZONED)) {
		t->zone_write_granularity = 0;
		t->max_zone_append_sectors = 0;
	}
	return ret;
}
EXPORT_SYMBOL(blk_stack_limits);

/**
 * queue_limits_stack_bdev - adjust queue_limits for stacked devices
 * @t:	the stacking driver limits (top device)
 * @bdev:  the underlying block device (bottom)
 * @offset:  offset to beginning of data within component device
 * @pfx: prefix to use for warnings logged
 *
 * Description:
 *    This function is used by stacking drivers like MD and DM to ensure
 *    that all component devices have compatible block sizes and
 *    alignments.  The stacking driver must provide a queue_limits
 *    struct (top) and then iteratively call the stacking function for
 *    all component (bottom) devices.  The stacking function will
 *    attempt to combine the values and ensure proper alignment.
 */
void queue_limits_stack_bdev(struct queue_limits *t, struct block_device *bdev,
		sector_t offset, const char *pfx)
{
	if (blk_stack_limits(t, &bdev_get_queue(bdev)->limits,
			get_start_sect(bdev) + offset))
		pr_notice("%s: Warning: Device %pg is misaligned\n",
			pfx, bdev);
}
EXPORT_SYMBOL_GPL(queue_limits_stack_bdev);

/**
 * queue_limits_stack_integrity - stack integrity profile
 * @t: target queue limits
 * @b: base queue limits
 *
 * Check if the integrity profile in the @b can be stacked into the
 * target @t.  Stacking is possible if either:
 *
 *   a) does not have any integrity information stacked into it yet
 *   b) the integrity profile in @b is identical to the one in @t
 *
 * If @b can be stacked into @t, return %true.  Else return %false and clear the
 * integrity information in @t.
 */
bool queue_limits_stack_integrity(struct queue_limits *t,
		struct queue_limits *b)
{
	struct blk_integrity *ti = &t->integrity;
	struct blk_integrity *bi = &b->integrity;

	if (!IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY))
		return true;

	if (!ti->tuple_size) {
		/* inherit the settings from the first underlying device */
		if (!(ti->flags & BLK_INTEGRITY_STACKED)) {
			ti->flags = BLK_INTEGRITY_DEVICE_CAPABLE |
				(bi->flags & BLK_INTEGRITY_REF_TAG);
			ti->csum_type = bi->csum_type;
			ti->tuple_size = bi->tuple_size;
			ti->pi_offset = bi->pi_offset;
			ti->interval_exp = bi->interval_exp;
			ti->tag_size = bi->tag_size;
			goto done;
		}
		if (!bi->tuple_size)
			goto done;
	}

	if (ti->tuple_size != bi->tuple_size)
		goto incompatible;
	if (ti->interval_exp != bi->interval_exp)
		goto incompatible;
	if (ti->tag_size != bi->tag_size)
		goto incompatible;
	if (ti->csum_type != bi->csum_type)
		goto incompatible;
	if ((ti->flags & BLK_INTEGRITY_REF_TAG) !=
	    (bi->flags & BLK_INTEGRITY_REF_TAG))
		goto incompatible;

done:
	ti->flags |= BLK_INTEGRITY_STACKED;
	return true;

incompatible:
	memset(ti, 0, sizeof(*ti));
	return false;
}
EXPORT_SYMBOL_GPL(queue_limits_stack_integrity);

/**
 * blk_queue_update_dma_pad - update pad mask
 * @q:     the request queue for the device
 * @mask:  pad mask
 *
 * Update dma pad mask.
 *
 * Appending pad buffer to a request modifies the last entry of a
 * scatter list such that it includes the pad buffer.
 **/
void blk_queue_update_dma_pad(struct request_queue *q, unsigned int mask)
{
	if (mask > q->dma_pad_mask)
		q->dma_pad_mask = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_pad);

/**
 * blk_set_queue_depth - tell the block layer about the device queue depth
 * @q:		the request queue for the device
 * @depth:		queue depth
 *
 */
void blk_set_queue_depth(struct request_queue *q, unsigned int depth)
{
	q->queue_depth = depth;
	rq_qos_queue_depth_changed(q);
}
EXPORT_SYMBOL(blk_set_queue_depth);

int bdev_alignment_offset(struct block_device *bdev)
{
	struct request_queue *q = bdev_get_queue(bdev);

	if (q->limits.flags & BLK_FEAT_MISALIGNED)
		return -1;
	if (bdev_is_partition(bdev))
		return queue_limit_alignment_offset(&q->limits,
				bdev->bd_start_sect);
	return q->limits.alignment_offset;
}
EXPORT_SYMBOL_GPL(bdev_alignment_offset);

unsigned int bdev_discard_alignment(struct block_device *bdev)
{
	struct request_queue *q = bdev_get_queue(bdev);

	if (bdev_is_partition(bdev))
		return queue_limit_discard_alignment(&q->limits,
				bdev->bd_start_sect);
	return q->limits.discard_alignment;
}
EXPORT_SYMBOL_GPL(bdev_discard_alignment);