summaryrefslogtreecommitdiff
path: root/block/blk-settings.c
blob: 4dd59059b788eb3b8b45cc555716eec11bfcd995 (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
// 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/blkdev.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_default_limits - reset limits to default values
 * @lim:  the queue_limits structure to reset
 *
 * Description:
 *   Returns a queue_limit struct to its default state.
 */
void blk_set_default_limits(struct queue_limits *lim)
{
	lim->max_segments = BLK_MAX_SEGMENTS;
	lim->max_discard_segments = 1;
	lim->max_integrity_segments = 0;
	lim->seg_boundary_mask = BLK_SEG_BOUNDARY_MASK;
	lim->virt_boundary_mask = 0;
	lim->max_segment_size = BLK_MAX_SEGMENT_SIZE;
	lim->max_sectors = lim->max_hw_sectors = BLK_SAFE_MAX_SECTORS;
	lim->max_user_sectors = lim->max_dev_sectors = 0;
	lim->chunk_sectors = 0;
	lim->max_write_zeroes_sectors = 0;
	lim->max_zone_append_sectors = 0;
	lim->max_discard_sectors = 0;
	lim->max_hw_discard_sectors = 0;
	lim->max_secure_erase_sectors = 0;
	lim->discard_granularity = 0;
	lim->discard_alignment = 0;
	lim->discard_misaligned = 0;
	lim->logical_block_size = lim->physical_block_size = lim->io_min = 512;
	lim->bounce = BLK_BOUNCE_NONE;
	lim->alignment_offset = 0;
	lim->io_opt = 0;
	lim->misaligned = 0;
	lim->zoned = BLK_ZONED_NONE;
	lim->zone_write_granularity = 0;
	lim->dma_alignment = 511;
}

/**
 * blk_set_stacking_limits - set default limits for stacking devices
 * @lim:  the queue_limits structure to reset
 *
 * Description:
 *   Returns a queue_limit struct to its default state. Should be used
 *   by stacking drivers like DM that have no internal limits.
 */
void blk_set_stacking_limits(struct queue_limits *lim)
{
	blk_set_default_limits(lim);

	/* 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;
}
EXPORT_SYMBOL(blk_set_stacking_limits);

/**
 * blk_queue_bounce_limit - set bounce buffer limit for queue
 * @q: the request queue for the device
 * @bounce: bounce limit to enforce
 *
 * Description:
 *    Force bouncing for ISA DMA ranges or highmem.
 *
 *    DEPRECATED, don't use in new code.
 **/
void blk_queue_bounce_limit(struct request_queue *q, enum blk_bounce bounce)
{
	q->limits.bounce = bounce;
}
EXPORT_SYMBOL(blk_queue_bounce_limit);

/**
 * blk_queue_max_hw_sectors - set max sectors for a request for this queue
 * @q:  the request queue for the device
 * @max_hw_sectors:  max hardware sectors in the usual 512b unit
 *
 * Description:
 *    Enables a low level driver to set a hard upper limit,
 *    max_hw_sectors, on the size of requests.  max_hw_sectors is set by
 *    the device driver based upon the capabilities of the I/O
 *    controller.
 *
 *    max_dev_sectors is a hard limit imposed by the storage device for
 *    READ/WRITE requests. It is set by the disk driver.
 *
 *    max_sectors is a soft limit imposed by the block layer for
 *    filesystem type requests.  This value can be overridden on a
 *    per-device basis in /sys/block/<device>/queue/max_sectors_kb.
 *    The soft limit can not exceed max_hw_sectors.
 **/
void blk_queue_max_hw_sectors(struct request_queue *q, unsigned int max_hw_sectors)
{
	struct queue_limits *limits = &q->limits;
	unsigned int max_sectors;

	if ((max_hw_sectors << 9) < PAGE_SIZE) {
		max_hw_sectors = 1 << (PAGE_SHIFT - 9);
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_hw_sectors);
	}

	max_hw_sectors = round_down(max_hw_sectors,
				    limits->logical_block_size >> SECTOR_SHIFT);
	limits->max_hw_sectors = max_hw_sectors;

	max_sectors = min_not_zero(max_hw_sectors, limits->max_dev_sectors);

	if (limits->max_user_sectors)
		max_sectors = min(max_sectors, limits->max_user_sectors);
	else
		max_sectors = min(max_sectors, BLK_DEF_MAX_SECTORS);

	max_sectors = round_down(max_sectors,
				 limits->logical_block_size >> SECTOR_SHIFT);
	limits->max_sectors = max_sectors;

	if (!q->disk)
		return;
	q->disk->bdi->io_pages = max_sectors >> (PAGE_SHIFT - 9);
}
EXPORT_SYMBOL(blk_queue_max_hw_sectors);

/**
 * blk_queue_chunk_sectors - set size of the chunk for this queue
 * @q:  the request queue for the device
 * @chunk_sectors:  chunk sectors in the usual 512b unit
 *
 * Description:
 *    If a driver doesn't want IOs to cross a given chunk size, it can set
 *    this limit and prevent merging across chunks. Note that the block layer
 *    must accept a page worth of data at any offset. So if the crossing of
 *    chunks is a hard limitation in the driver, it must still be prepared
 *    to split single page bios.
 **/
void blk_queue_chunk_sectors(struct request_queue *q, unsigned int chunk_sectors)
{
	q->limits.chunk_sectors = chunk_sectors;
}
EXPORT_SYMBOL(blk_queue_chunk_sectors);

/**
 * blk_queue_max_discard_sectors - set max sectors for a single discard
 * @q:  the request queue for the device
 * @max_discard_sectors: maximum number of sectors to discard
 **/
void blk_queue_max_discard_sectors(struct request_queue *q,
		unsigned int max_discard_sectors)
{
	q->limits.max_hw_discard_sectors = max_discard_sectors;
	q->limits.max_discard_sectors = max_discard_sectors;
}
EXPORT_SYMBOL(blk_queue_max_discard_sectors);

/**
 * blk_queue_max_secure_erase_sectors - set max sectors for a secure erase
 * @q:  the request queue for the device
 * @max_sectors: maximum number of sectors to secure_erase
 **/
void blk_queue_max_secure_erase_sectors(struct request_queue *q,
		unsigned int max_sectors)
{
	q->limits.max_secure_erase_sectors = max_sectors;
}
EXPORT_SYMBOL(blk_queue_max_secure_erase_sectors);

/**
 * blk_queue_max_write_zeroes_sectors - set max sectors for a single
 *                                      write zeroes
 * @q:  the request queue for the device
 * @max_write_zeroes_sectors: maximum number of sectors to write per command
 **/
void blk_queue_max_write_zeroes_sectors(struct request_queue *q,
		unsigned int max_write_zeroes_sectors)
{
	q->limits.max_write_zeroes_sectors = max_write_zeroes_sectors;
}
EXPORT_SYMBOL(blk_queue_max_write_zeroes_sectors);

/**
 * blk_queue_max_zone_append_sectors - set max sectors for a single zone append
 * @q:  the request queue for the device
 * @max_zone_append_sectors: maximum number of sectors to write per command
 **/
void blk_queue_max_zone_append_sectors(struct request_queue *q,
		unsigned int max_zone_append_sectors)
{
	unsigned int max_sectors;

	if (WARN_ON(!blk_queue_is_zoned(q)))
		return;

	max_sectors = min(q->limits.max_hw_sectors, max_zone_append_sectors);
	max_sectors = min(q->limits.chunk_sectors, max_sectors);

	/*
	 * Signal eventual driver bugs resulting in the max_zone_append sectors limit
	 * being 0 due to a 0 argument, the chunk_sectors limit (zone size) not set,
	 * or the max_hw_sectors limit not set.
	 */
	WARN_ON(!max_sectors);

	q->limits.max_zone_append_sectors = max_sectors;
}
EXPORT_SYMBOL_GPL(blk_queue_max_zone_append_sectors);

/**
 * blk_queue_max_segments - set max hw segments for a request for this queue
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    hw data segments in a request.
 **/
void blk_queue_max_segments(struct request_queue *q, unsigned short max_segments)
{
	if (!max_segments) {
		max_segments = 1;
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_segments);
	}

	q->limits.max_segments = max_segments;
}
EXPORT_SYMBOL(blk_queue_max_segments);

/**
 * blk_queue_max_discard_segments - set max segments for discard requests
 * @q:  the request queue for the device
 * @max_segments:  max number of segments
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the number of
 *    segments in a discard request.
 **/
void blk_queue_max_discard_segments(struct request_queue *q,
		unsigned short max_segments)
{
	q->limits.max_discard_segments = max_segments;
}
EXPORT_SYMBOL_GPL(blk_queue_max_discard_segments);

/**
 * blk_queue_max_segment_size - set max segment size for blk_rq_map_sg
 * @q:  the request queue for the device
 * @max_size:  max size of segment in bytes
 *
 * Description:
 *    Enables a low level driver to set an upper limit on the size of a
 *    coalesced segment
 **/
void blk_queue_max_segment_size(struct request_queue *q, unsigned int max_size)
{
	if (max_size < PAGE_SIZE) {
		max_size = PAGE_SIZE;
		printk(KERN_INFO "%s: set to minimum %d\n",
		       __func__, max_size);
	}

	/* see blk_queue_virt_boundary() for the explanation */
	WARN_ON_ONCE(q->limits.virt_boundary_mask);

	q->limits.max_segment_size = max_size;
}
EXPORT_SYMBOL(blk_queue_max_segment_size);

/**
 * blk_queue_logical_block_size - set logical block size for the queue
 * @q:  the request queue for the device
 * @size:  the logical block size, in bytes
 *
 * Description:
 *   This should be set to the lowest possible block size that the
 *   storage device can address.  The default of 512 covers most
 *   hardware.
 **/
void blk_queue_logical_block_size(struct request_queue *q, unsigned int size)
{
	struct queue_limits *limits = &q->limits;

	limits->logical_block_size = size;

	if (limits->physical_block_size < size)
		limits->physical_block_size = size;

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

	limits->max_hw_sectors =
		round_down(limits->max_hw_sectors, size >> SECTOR_SHIFT);
	limits->max_sectors =
		round_down(limits->max_sectors, size >> SECTOR_SHIFT);
}
EXPORT_SYMBOL(blk_queue_logical_block_size);

/**
 * blk_queue_physical_block_size - set physical block size for the queue
 * @q:  the request queue for the device
 * @size:  the physical block size, in bytes
 *
 * Description:
 *   This should be set to the lowest possible sector size that the
 *   hardware can operate on without reverting to read-modify-write
 *   operations.
 */
void blk_queue_physical_block_size(struct request_queue *q, unsigned int size)
{
	q->limits.physical_block_size = size;

	if (q->limits.physical_block_size < q->limits.logical_block_size)
		q->limits.physical_block_size = q->limits.logical_block_size;

	if (q->limits.io_min < q->limits.physical_block_size)
		q->limits.io_min = q->limits.physical_block_size;
}
EXPORT_SYMBOL(blk_queue_physical_block_size);

/**
 * blk_queue_zone_write_granularity - set zone write granularity for the queue
 * @q:  the request queue for the zoned device
 * @size:  the zone write granularity size, in bytes
 *
 * Description:
 *   This should be set to the lowest possible size allowing to write in
 *   sequential zones of a zoned block device.
 */
void blk_queue_zone_write_granularity(struct request_queue *q,
				      unsigned int size)
{
	if (WARN_ON_ONCE(!blk_queue_is_zoned(q)))
		return;

	q->limits.zone_write_granularity = size;

	if (q->limits.zone_write_granularity < q->limits.logical_block_size)
		q->limits.zone_write_granularity = q->limits.logical_block_size;
}
EXPORT_SYMBOL_GPL(blk_queue_zone_write_granularity);

/**
 * blk_queue_alignment_offset - set physical block alignment offset
 * @q:	the request queue for the device
 * @offset: alignment offset in bytes
 *
 * Description:
 *   Some devices are naturally misaligned to compensate for things like
 *   the legacy DOS partition table 63-sector offset.  Low-level drivers
 *   should call this function for devices whose first sector is not
 *   naturally aligned.
 */
void blk_queue_alignment_offset(struct request_queue *q, unsigned int offset)
{
	q->limits.alignment_offset =
		offset & (q->limits.physical_block_size - 1);
	q->limits.misaligned = 0;
}
EXPORT_SYMBOL(blk_queue_alignment_offset);

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

	/*
	 * For read-ahead of large files to be effective, we need to read ahead
	 * at least twice the optimal I/O size.
	 */
	disk->bdi->ra_pages =
		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
	disk->bdi->io_pages = queue_max_sectors(q) >> (PAGE_SHIFT - 9);
}
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_queue_io_min - set minimum request size for the queue
 * @q:	the request queue for the device
 * @min:  smallest I/O size in bytes
 *
 * Description:
 *   Storage devices may report a granularity or preferred minimum I/O
 *   size which is the smallest request the device can perform without
 *   incurring a performance penalty.  For disk drives this is often the
 *   physical block size.  For RAID arrays it is often the stripe chunk
 *   size.  A properly aligned multiple of minimum_io_size is the
 *   preferred request size for workloads where a high number of I/O
 *   operations is desired.
 */
void blk_queue_io_min(struct request_queue *q, unsigned int min)
{
	blk_limits_io_min(&q->limits, min);
}
EXPORT_SYMBOL(blk_queue_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);

/**
 * blk_queue_io_opt - set optimal request size for the queue
 * @q:	the request queue for the device
 * @opt:  optimal request 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_queue_io_opt(struct request_queue *q, unsigned int opt)
{
	blk_limits_io_opt(&q->limits, opt);
	if (!q->disk)
		return;
	q->disk->bdi->ra_pages =
		max(queue_io_opt(q) * 2 / PAGE_SIZE, VM_READAHEAD_PAGES);
}
EXPORT_SYMBOL(blk_queue_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->max_sectors = min_not_zero(t->max_sectors, b->max_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(t->max_zone_append_sectors,
					b->max_zone_append_sectors);
	t->bounce = max(t->bounce, b->bounce);

	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);

	t->misaligned |= b->misaligned;

	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->misaligned = 1;
			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->misaligned = 1;
		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->misaligned = 1;
		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->misaligned = 1;
		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->misaligned = 1;
		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->misaligned = 1;
		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);

		if (t->discard_granularity != 0 &&
		    t->discard_alignment != alignment) {
			top = t->discard_granularity + t->discard_alignment;
			bottom = b->discard_granularity + alignment;

			/* Verify that top and bottom intervals line up */
			if ((max(top, bottom) % min(top, bottom)) != 0)
				t->discard_misaligned = 1;
		}

		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);
	t->zoned = max(t->zoned, b->zoned);
	return ret;
}
EXPORT_SYMBOL(blk_stack_limits);

/**
 * disk_stack_limits - adjust queue limits for stacked drivers
 * @disk:  MD/DM gendisk (top)
 * @bdev:  the underlying block device (bottom)
 * @offset:  offset to beginning of data within component device
 *
 * Description:
 *    Merges the limits for a top level gendisk and a bottom level
 *    block_device.
 */
void disk_stack_limits(struct gendisk *disk, struct block_device *bdev,
		       sector_t offset)
{
	struct request_queue *t = disk->queue;

	if (blk_stack_limits(&t->limits, &bdev_get_queue(bdev)->limits,
			get_start_sect(bdev) + (offset >> 9)) < 0)
		pr_notice("%s: Warning: Device %pg is misaligned\n",
			disk->disk_name, bdev);

	disk_update_readahead(disk);
}
EXPORT_SYMBOL(disk_stack_limits);

/**
 * 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_queue_segment_boundary - set boundary rules for segment merging
 * @q:  the request queue for the device
 * @mask:  the memory boundary mask
 **/
void blk_queue_segment_boundary(struct request_queue *q, unsigned long mask)
{
	if (mask < PAGE_SIZE - 1) {
		mask = PAGE_SIZE - 1;
		printk(KERN_INFO "%s: set to minimum %lx\n",
		       __func__, mask);
	}

	q->limits.seg_boundary_mask = mask;
}
EXPORT_SYMBOL(blk_queue_segment_boundary);

/**
 * blk_queue_virt_boundary - set boundary rules for bio merging
 * @q:  the request queue for the device
 * @mask:  the memory boundary mask
 **/
void blk_queue_virt_boundary(struct request_queue *q, unsigned long mask)
{
	q->limits.virt_boundary_mask = mask;

	/*
	 * Devices that require a virtual boundary do not support scatter/gather
	 * I/O natively, but instead require a descriptor list entry for each
	 * page (which might not be idential to the Linux PAGE_SIZE).  Because
	 * of that they are not limited by our notion of "segment size".
	 */
	if (mask)
		q->limits.max_segment_size = UINT_MAX;
}
EXPORT_SYMBOL(blk_queue_virt_boundary);

/**
 * blk_queue_dma_alignment - set dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    set required memory and length alignment for direct dma transactions.
 *    this is used when building direct io requests for the queue.
 *
 **/
void blk_queue_dma_alignment(struct request_queue *q, int mask)
{
	q->limits.dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_dma_alignment);

/**
 * blk_queue_update_dma_alignment - update dma length and memory alignment
 * @q:     the request queue for the device
 * @mask:  alignment mask
 *
 * description:
 *    update required memory and length alignment for direct dma transactions.
 *    If the requested alignment is larger than the current alignment, then
 *    the current queue alignment is updated to the new value, otherwise it
 *    is left alone.  The design of this is to allow multiple objects
 *    (driver, device, transport etc) to set their respective
 *    alignments without having them interfere.
 *
 **/
void blk_queue_update_dma_alignment(struct request_queue *q, int mask)
{
	BUG_ON(mask > PAGE_SIZE);

	if (mask > q->limits.dma_alignment)
		q->limits.dma_alignment = mask;
}
EXPORT_SYMBOL(blk_queue_update_dma_alignment);

/**
 * 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);

/**
 * blk_queue_write_cache - configure queue's write cache
 * @q:		the request queue for the device
 * @wc:		write back cache on or off
 * @fua:	device supports FUA writes, if true
 *
 * Tell the block layer about the write cache of @q.
 */
void blk_queue_write_cache(struct request_queue *q, bool wc, bool fua)
{
	if (wc)
		blk_queue_flag_set(QUEUE_FLAG_WC, q);
	else
		blk_queue_flag_clear(QUEUE_FLAG_WC, q);
	if (fua)
		blk_queue_flag_set(QUEUE_FLAG_FUA, q);
	else
		blk_queue_flag_clear(QUEUE_FLAG_FUA, q);

	wbt_set_write_cache(q, test_bit(QUEUE_FLAG_WC, &q->queue_flags));
}
EXPORT_SYMBOL_GPL(blk_queue_write_cache);

/**
 * blk_queue_required_elevator_features - Set a queue required elevator features
 * @q:		the request queue for the target device
 * @features:	Required elevator features OR'ed together
 *
 * Tell the block layer that for the device controlled through @q, only the
 * only elevators that can be used are those that implement at least the set of
 * features specified by @features.
 */
void blk_queue_required_elevator_features(struct request_queue *q,
					  unsigned int features)
{
	q->required_elevator_features = features;
}
EXPORT_SYMBOL_GPL(blk_queue_required_elevator_features);

/**
 * blk_queue_can_use_dma_map_merging - configure queue for merging segments.
 * @q:		the request queue for the device
 * @dev:	the device pointer for dma
 *
 * Tell the block layer about merging the segments by dma map of @q.
 */
bool blk_queue_can_use_dma_map_merging(struct request_queue *q,
				       struct device *dev)
{
	unsigned long boundary = dma_get_merge_boundary(dev);

	if (!boundary)
		return false;

	/* No need to update max_segment_size. see blk_queue_virt_boundary() */
	blk_queue_virt_boundary(q, boundary);

	return true;
}
EXPORT_SYMBOL_GPL(blk_queue_can_use_dma_map_merging);

static bool disk_has_partitions(struct gendisk *disk)
{
	unsigned long idx;
	struct block_device *part;
	bool ret = false;

	rcu_read_lock();
	xa_for_each(&disk->part_tbl, idx, part) {
		if (bdev_is_partition(part)) {
			ret = true;
			break;
		}
	}
	rcu_read_unlock();

	return ret;
}

/**
 * disk_set_zoned - configure the zoned model for a disk
 * @disk:	the gendisk of the queue to configure
 * @model:	the zoned model to set
 *
 * Set the zoned model of @disk to @model.
 *
 * When @model is BLK_ZONED_HM (host managed), this should be called only
 * if zoned block device support is enabled (CONFIG_BLK_DEV_ZONED option).
 * If @model specifies BLK_ZONED_HA (host aware), the effective model used
 * depends on CONFIG_BLK_DEV_ZONED settings and on the existence of partitions
 * on the disk.
 */
void disk_set_zoned(struct gendisk *disk, enum blk_zoned_model model)
{
	struct request_queue *q = disk->queue;
	unsigned int old_model = q->limits.zoned;

	switch (model) {
	case BLK_ZONED_HM:
		/*
		 * Host managed devices are supported only if
		 * CONFIG_BLK_DEV_ZONED is enabled.
		 */
		WARN_ON_ONCE(!IS_ENABLED(CONFIG_BLK_DEV_ZONED));
		break;
	case BLK_ZONED_HA:
		/*
		 * Host aware devices can be treated either as regular block
		 * devices (similar to drive managed devices) or as zoned block
		 * devices to take advantage of the zone command set, similarly
		 * to host managed devices. We try the latter if there are no
		 * partitions and zoned block device support is enabled, else
		 * we do nothing special as far as the block layer is concerned.
		 */
		if (!IS_ENABLED(CONFIG_BLK_DEV_ZONED) ||
		    disk_has_partitions(disk))
			model = BLK_ZONED_NONE;
		break;
	case BLK_ZONED_NONE:
	default:
		if (WARN_ON_ONCE(model != BLK_ZONED_NONE))
			model = BLK_ZONED_NONE;
		break;
	}

	q->limits.zoned = model;
	if (model != BLK_ZONED_NONE) {
		/*
		 * Set the zone write granularity to the device logical block
		 * size by default. The driver can change this value if needed.
		 */
		blk_queue_zone_write_granularity(q,
						queue_logical_block_size(q));
	} else if (old_model != BLK_ZONED_NONE) {
		disk_clear_zone_settings(disk);
	}
}
EXPORT_SYMBOL_GPL(disk_set_zoned);

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

	if (q->limits.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);