summaryrefslogtreecommitdiff
path: root/drivers/scsi/sd_zbc.c
blob: abbd08933ac76da8358cdd43c31d29bef1f6aa8f (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * SCSI Zoned Block commands
 *
 * Copyright (C) 2014-2015 SUSE Linux GmbH
 * Written by: Hannes Reinecke <hare@suse.de>
 * Modified by: Damien Le Moal <damien.lemoal@hgst.com>
 * Modified by: Shaun Tancheff <shaun.tancheff@seagate.com>
 */

#include <linux/blkdev.h>
#include <linux/vmalloc.h>
#include <linux/sched/mm.h>
#include <linux/mutex.h>

#include <asm/unaligned.h>

#include <scsi/scsi.h>
#include <scsi/scsi_cmnd.h>

#include "sd.h"

#define CREATE_TRACE_POINTS
#include "sd_trace.h"

/**
 * sd_zbc_get_zone_wp_offset - Get zone write pointer offset.
 * @zone: Zone for which to return the write pointer offset.
 *
 * Return: offset of the write pointer from the start of the zone.
 */
static unsigned int sd_zbc_get_zone_wp_offset(struct blk_zone *zone)
{
	if (zone->type == ZBC_ZONE_TYPE_CONV)
		return 0;

	switch (zone->cond) {
	case BLK_ZONE_COND_IMP_OPEN:
	case BLK_ZONE_COND_EXP_OPEN:
	case BLK_ZONE_COND_CLOSED:
		return zone->wp - zone->start;
	case BLK_ZONE_COND_FULL:
		return zone->len;
	case BLK_ZONE_COND_EMPTY:
	case BLK_ZONE_COND_OFFLINE:
	case BLK_ZONE_COND_READONLY:
	default:
		/*
		 * Offline and read-only zones do not have a valid
		 * write pointer. Use 0 as for an empty zone.
		 */
		return 0;
	}
}

/* Whether or not a SCSI zone descriptor describes a gap zone. */
static bool sd_zbc_is_gap_zone(const u8 buf[64])
{
	return (buf[0] & 0xf) == ZBC_ZONE_TYPE_GAP;
}

/**
 * sd_zbc_parse_report - Parse a SCSI zone descriptor
 * @sdkp: SCSI disk pointer.
 * @buf: SCSI zone descriptor.
 * @idx: Index of the zone relative to the first zone reported by the current
 *	sd_zbc_report_zones() call.
 * @cb: Callback function pointer.
 * @data: Second argument passed to @cb.
 *
 * Return: Value returned by @cb.
 *
 * Convert a SCSI zone descriptor into struct blk_zone format. Additionally,
 * call @cb(blk_zone, @data).
 */
static int sd_zbc_parse_report(struct scsi_disk *sdkp, const u8 buf[64],
			       unsigned int idx, report_zones_cb cb, void *data)
{
	struct scsi_device *sdp = sdkp->device;
	struct blk_zone zone = { 0 };
	sector_t start_lba, gran;
	int ret;

	if (WARN_ON_ONCE(sd_zbc_is_gap_zone(buf)))
		return -EINVAL;

	zone.type = buf[0] & 0x0f;
	zone.cond = (buf[1] >> 4) & 0xf;
	if (buf[1] & 0x01)
		zone.reset = 1;
	if (buf[1] & 0x02)
		zone.non_seq = 1;

	start_lba = get_unaligned_be64(&buf[16]);
	zone.start = logical_to_sectors(sdp, start_lba);
	zone.capacity = logical_to_sectors(sdp, get_unaligned_be64(&buf[8]));
	zone.len = zone.capacity;
	if (sdkp->zone_starting_lba_gran) {
		gran = logical_to_sectors(sdp, sdkp->zone_starting_lba_gran);
		if (zone.len > gran) {
			sd_printk(KERN_ERR, sdkp,
				  "Invalid zone at LBA %llu with capacity %llu and length %llu; granularity = %llu\n",
				  start_lba,
				  sectors_to_logical(sdp, zone.capacity),
				  sectors_to_logical(sdp, zone.len),
				  sectors_to_logical(sdp, gran));
			return -EINVAL;
		}
		/*
		 * Use the starting LBA granularity instead of the zone length
		 * obtained from the REPORT ZONES command.
		 */
		zone.len = gran;
	}
	if (zone.cond == ZBC_ZONE_COND_FULL)
		zone.wp = zone.start + zone.len;
	else
		zone.wp = logical_to_sectors(sdp, get_unaligned_be64(&buf[24]));

	ret = cb(&zone, idx, data);
	if (ret)
		return ret;

	if (sdkp->rev_wp_offset)
		sdkp->rev_wp_offset[idx] = sd_zbc_get_zone_wp_offset(&zone);

	return 0;
}

/**
 * sd_zbc_do_report_zones - Issue a REPORT ZONES scsi command.
 * @sdkp: The target disk
 * @buf: vmalloc-ed buffer to use for the reply
 * @buflen: the buffer size
 * @lba: Start LBA of the report
 * @partial: Do partial report
 *
 * For internal use during device validation.
 * Using partial=true can significantly speed up execution of a report zones
 * command because the disk does not have to count all possible report matching
 * zones and will only report the count of zones fitting in the command reply
 * buffer.
 */
static int sd_zbc_do_report_zones(struct scsi_disk *sdkp, unsigned char *buf,
				  unsigned int buflen, sector_t lba,
				  bool partial)
{
	struct scsi_device *sdp = sdkp->device;
	const int timeout = sdp->request_queue->rq_timeout;
	struct scsi_sense_hdr sshdr;
	const struct scsi_exec_args exec_args = {
		.sshdr = &sshdr,
	};
	unsigned char cmd[16];
	unsigned int rep_len;
	int result;

	memset(cmd, 0, 16);
	cmd[0] = ZBC_IN;
	cmd[1] = ZI_REPORT_ZONES;
	put_unaligned_be64(lba, &cmd[2]);
	put_unaligned_be32(buflen, &cmd[10]);
	if (partial)
		cmd[14] = ZBC_REPORT_ZONE_PARTIAL;

	result = scsi_execute_cmd(sdp, cmd, REQ_OP_DRV_IN, buf, buflen,
				  timeout, SD_MAX_RETRIES, &exec_args);
	if (result) {
		sd_printk(KERN_ERR, sdkp,
			  "REPORT ZONES start lba %llu failed\n", lba);
		sd_print_result(sdkp, "REPORT ZONES", result);
		if (result > 0 && scsi_sense_valid(&sshdr))
			sd_print_sense_hdr(sdkp, &sshdr);
		return -EIO;
	}

	rep_len = get_unaligned_be32(&buf[0]);
	if (rep_len < 64) {
		sd_printk(KERN_ERR, sdkp,
			  "REPORT ZONES report invalid length %u\n",
			  rep_len);
		return -EIO;
	}

	return 0;
}

/**
 * sd_zbc_alloc_report_buffer() - Allocate a buffer for report zones reply.
 * @sdkp: The target disk
 * @nr_zones: Maximum number of zones to report
 * @buflen: Size of the buffer allocated
 *
 * Try to allocate a reply buffer for the number of requested zones.
 * The size of the buffer allocated may be smaller than requested to
 * satify the device constraint (max_hw_sectors, max_segments, etc).
 *
 * Return the address of the allocated buffer and update @buflen with
 * the size of the allocated buffer.
 */
static void *sd_zbc_alloc_report_buffer(struct scsi_disk *sdkp,
					unsigned int nr_zones, size_t *buflen)
{
	struct request_queue *q = sdkp->disk->queue;
	size_t bufsize;
	void *buf;

	/*
	 * Report zone buffer size should be at most 64B times the number of
	 * zones requested plus the 64B reply header, but should be aligned
	 * to SECTOR_SIZE for ATA devices.
	 * Make sure that this size does not exceed the hardware capabilities.
	 * Furthermore, since the report zone command cannot be split, make
	 * sure that the allocated buffer can always be mapped by limiting the
	 * number of pages allocated to the HBA max segments limit.
	 */
	nr_zones = min(nr_zones, sdkp->zone_info.nr_zones);
	bufsize = roundup((nr_zones + 1) * 64, SECTOR_SIZE);
	bufsize = min_t(size_t, bufsize,
			queue_max_hw_sectors(q) << SECTOR_SHIFT);
	bufsize = min_t(size_t, bufsize, queue_max_segments(q) << PAGE_SHIFT);

	while (bufsize >= SECTOR_SIZE) {
		buf = __vmalloc(bufsize,
				GFP_KERNEL | __GFP_ZERO | __GFP_NORETRY);
		if (buf) {
			*buflen = bufsize;
			return buf;
		}
		bufsize = rounddown(bufsize >> 1, SECTOR_SIZE);
	}

	return NULL;
}

/**
 * sd_zbc_zone_sectors - Get the device zone size in number of 512B sectors.
 * @sdkp: The target disk
 */
static inline sector_t sd_zbc_zone_sectors(struct scsi_disk *sdkp)
{
	return logical_to_sectors(sdkp->device, sdkp->zone_info.zone_blocks);
}

/**
 * sd_zbc_report_zones - SCSI .report_zones() callback.
 * @disk: Disk to report zones for.
 * @sector: Start sector.
 * @nr_zones: Maximum number of zones to report.
 * @cb: Callback function called to report zone information.
 * @data: Second argument passed to @cb.
 *
 * Called by the block layer to iterate over zone information. See also the
 * disk->fops->report_zones() calls in block/blk-zoned.c.
 */
int sd_zbc_report_zones(struct gendisk *disk, sector_t sector,
			unsigned int nr_zones, report_zones_cb cb, void *data)
{
	struct scsi_disk *sdkp = scsi_disk(disk);
	sector_t lba = sectors_to_logical(sdkp->device, sector);
	unsigned int nr, i;
	unsigned char *buf;
	u64 zone_length, start_lba;
	size_t offset, buflen = 0;
	int zone_idx = 0;
	int ret;

	if (!sd_is_zoned(sdkp))
		/* Not a zoned device */
		return -EOPNOTSUPP;

	if (!sdkp->capacity)
		/* Device gone or invalid */
		return -ENODEV;

	buf = sd_zbc_alloc_report_buffer(sdkp, nr_zones, &buflen);
	if (!buf)
		return -ENOMEM;

	while (zone_idx < nr_zones && lba < sdkp->capacity) {
		ret = sd_zbc_do_report_zones(sdkp, buf, buflen, lba, true);
		if (ret)
			goto out;

		offset = 0;
		nr = min(nr_zones, get_unaligned_be32(&buf[0]) / 64);
		if (!nr)
			break;

		for (i = 0; i < nr && zone_idx < nr_zones; i++) {
			offset += 64;
			start_lba = get_unaligned_be64(&buf[offset + 16]);
			zone_length = get_unaligned_be64(&buf[offset + 8]);
			if ((zone_idx == 0 &&
			    (lba < start_lba ||
			     lba >= start_lba + zone_length)) ||
			    (zone_idx > 0 && start_lba != lba) ||
			    start_lba + zone_length < start_lba) {
				sd_printk(KERN_ERR, sdkp,
					  "Zone %d at LBA %llu is invalid: %llu + %llu\n",
					  zone_idx, lba, start_lba, zone_length);
				ret = -EINVAL;
				goto out;
			}
			lba = start_lba + zone_length;
			if (sd_zbc_is_gap_zone(&buf[offset])) {
				if (sdkp->zone_starting_lba_gran)
					continue;
				sd_printk(KERN_ERR, sdkp,
					  "Gap zone without constant LBA offsets\n");
				ret = -EINVAL;
				goto out;
			}

			ret = sd_zbc_parse_report(sdkp, buf + offset, zone_idx,
						  cb, data);
			if (ret)
				goto out;

			zone_idx++;
		}
	}

	ret = zone_idx;
out:
	kvfree(buf);
	return ret;
}

static blk_status_t sd_zbc_cmnd_checks(struct scsi_cmnd *cmd)
{
	struct request *rq = scsi_cmd_to_rq(cmd);
	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
	sector_t sector = blk_rq_pos(rq);

	if (!sd_is_zoned(sdkp))
		/* Not a zoned device */
		return BLK_STS_IOERR;

	if (sdkp->device->changed)
		return BLK_STS_IOERR;

	if (sector & (sd_zbc_zone_sectors(sdkp) - 1))
		/* Unaligned request */
		return BLK_STS_IOERR;

	return BLK_STS_OK;
}

#define SD_ZBC_INVALID_WP_OFST	(~0u)
#define SD_ZBC_UPDATING_WP_OFST	(SD_ZBC_INVALID_WP_OFST - 1)

static int sd_zbc_update_wp_offset_cb(struct blk_zone *zone, unsigned int idx,
				    void *data)
{
	struct scsi_disk *sdkp = data;

	lockdep_assert_held(&sdkp->zones_wp_offset_lock);

	sdkp->zones_wp_offset[idx] = sd_zbc_get_zone_wp_offset(zone);

	return 0;
}

/*
 * An attempt to append a zone triggered an invalid write pointer error.
 * Reread the write pointer of the zone(s) in which the append failed.
 */
static void sd_zbc_update_wp_offset_workfn(struct work_struct *work)
{
	struct scsi_disk *sdkp;
	unsigned long flags;
	sector_t zno;
	int ret;

	sdkp = container_of(work, struct scsi_disk, zone_wp_offset_work);

	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
	for (zno = 0; zno < sdkp->zone_info.nr_zones; zno++) {
		if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
			continue;

		spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
		ret = sd_zbc_do_report_zones(sdkp, sdkp->zone_wp_update_buf,
					     SD_BUF_SIZE,
					     zno * sdkp->zone_info.zone_blocks, true);
		spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
		if (!ret)
			sd_zbc_parse_report(sdkp, sdkp->zone_wp_update_buf + 64,
					    zno, sd_zbc_update_wp_offset_cb,
					    sdkp);
	}
	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);

	scsi_device_put(sdkp->device);
}

/**
 * sd_zbc_prepare_zone_append() - Prepare an emulated ZONE_APPEND command.
 * @cmd: the command to setup
 * @lba: the LBA to patch
 * @nr_blocks: the number of LBAs to be written
 *
 * Called from sd_setup_read_write_cmnd() for REQ_OP_ZONE_APPEND.
 * @sd_zbc_prepare_zone_append() handles the necessary zone wrote locking and
 * patching of the lba for an emulated ZONE_APPEND command.
 *
 * In case the cached write pointer offset is %SD_ZBC_INVALID_WP_OFST it will
 * schedule a REPORT ZONES command and return BLK_STS_IOERR.
 */
blk_status_t sd_zbc_prepare_zone_append(struct scsi_cmnd *cmd, sector_t *lba,
					unsigned int nr_blocks)
{
	struct request *rq = scsi_cmd_to_rq(cmd);
	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
	unsigned int wp_offset, zno = blk_rq_zone_no(rq);
	unsigned long flags;
	blk_status_t ret;

	ret = sd_zbc_cmnd_checks(cmd);
	if (ret != BLK_STS_OK)
		return ret;

	if (!blk_rq_zone_is_seq(rq))
		return BLK_STS_IOERR;

	/* Unlock of the write lock will happen in sd_zbc_complete() */
	if (!blk_req_zone_write_trylock(rq))
		return BLK_STS_ZONE_RESOURCE;

	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);
	wp_offset = sdkp->zones_wp_offset[zno];
	switch (wp_offset) {
	case SD_ZBC_INVALID_WP_OFST:
		/*
		 * We are about to schedule work to update a zone write pointer
		 * offset, which will cause the zone append command to be
		 * requeued. So make sure that the scsi device does not go away
		 * while the work is being processed.
		 */
		if (scsi_device_get(sdkp->device)) {
			ret = BLK_STS_IOERR;
			break;
		}
		sdkp->zones_wp_offset[zno] = SD_ZBC_UPDATING_WP_OFST;
		schedule_work(&sdkp->zone_wp_offset_work);
		fallthrough;
	case SD_ZBC_UPDATING_WP_OFST:
		ret = BLK_STS_DEV_RESOURCE;
		break;
	default:
		wp_offset = sectors_to_logical(sdkp->device, wp_offset);
		if (wp_offset + nr_blocks > sdkp->zone_info.zone_blocks) {
			ret = BLK_STS_IOERR;
			break;
		}

		trace_scsi_prepare_zone_append(cmd, *lba, wp_offset);
		*lba += wp_offset;
	}
	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);
	if (ret)
		blk_req_zone_write_unlock(rq);
	return ret;
}

/**
 * sd_zbc_setup_zone_mgmt_cmnd - Prepare a zone ZBC_OUT command. The operations
 *			can be RESET WRITE POINTER, OPEN, CLOSE or FINISH.
 * @cmd: the command to setup
 * @op: Operation to be performed
 * @all: All zones control
 *
 * Called from sd_init_command() for REQ_OP_ZONE_RESET, REQ_OP_ZONE_RESET_ALL,
 * REQ_OP_ZONE_OPEN, REQ_OP_ZONE_CLOSE or REQ_OP_ZONE_FINISH requests.
 */
blk_status_t sd_zbc_setup_zone_mgmt_cmnd(struct scsi_cmnd *cmd,
					 unsigned char op, bool all)
{
	struct request *rq = scsi_cmd_to_rq(cmd);
	sector_t sector = blk_rq_pos(rq);
	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
	sector_t block = sectors_to_logical(sdkp->device, sector);
	blk_status_t ret;

	ret = sd_zbc_cmnd_checks(cmd);
	if (ret != BLK_STS_OK)
		return ret;

	cmd->cmd_len = 16;
	memset(cmd->cmnd, 0, cmd->cmd_len);
	cmd->cmnd[0] = ZBC_OUT;
	cmd->cmnd[1] = op;
	if (all)
		cmd->cmnd[14] = 0x1;
	else
		put_unaligned_be64(block, &cmd->cmnd[2]);

	rq->timeout = SD_TIMEOUT;
	cmd->sc_data_direction = DMA_NONE;
	cmd->transfersize = 0;
	cmd->allowed = 0;

	return BLK_STS_OK;
}

static bool sd_zbc_need_zone_wp_update(struct request *rq)
{
	switch (req_op(rq)) {
	case REQ_OP_ZONE_APPEND:
	case REQ_OP_ZONE_FINISH:
	case REQ_OP_ZONE_RESET:
	case REQ_OP_ZONE_RESET_ALL:
		return true;
	case REQ_OP_WRITE:
	case REQ_OP_WRITE_ZEROES:
		return blk_rq_zone_is_seq(rq);
	default:
		return false;
	}
}

/**
 * sd_zbc_zone_wp_update - Update cached zone write pointer upon cmd completion
 * @cmd: Completed command
 * @good_bytes: Command reply bytes
 *
 * Called from sd_zbc_complete() to handle the update of the cached zone write
 * pointer value in case an update is needed.
 */
static unsigned int sd_zbc_zone_wp_update(struct scsi_cmnd *cmd,
					  unsigned int good_bytes)
{
	int result = cmd->result;
	struct request *rq = scsi_cmd_to_rq(cmd);
	struct scsi_disk *sdkp = scsi_disk(rq->q->disk);
	unsigned int zno = blk_rq_zone_no(rq);
	enum req_op op = req_op(rq);
	unsigned long flags;

	/*
	 * If we got an error for a command that needs updating the write
	 * pointer offset cache, we must mark the zone wp offset entry as
	 * invalid to force an update from disk the next time a zone append
	 * command is issued.
	 */
	spin_lock_irqsave(&sdkp->zones_wp_offset_lock, flags);

	if (result && op != REQ_OP_ZONE_RESET_ALL) {
		if (op == REQ_OP_ZONE_APPEND) {
			/* Force complete completion (no retry) */
			good_bytes = 0;
			scsi_set_resid(cmd, blk_rq_bytes(rq));
		}

		/*
		 * Force an update of the zone write pointer offset on
		 * the next zone append access.
		 */
		if (sdkp->zones_wp_offset[zno] != SD_ZBC_UPDATING_WP_OFST)
			sdkp->zones_wp_offset[zno] = SD_ZBC_INVALID_WP_OFST;
		goto unlock_wp_offset;
	}

	switch (op) {
	case REQ_OP_ZONE_APPEND:
		trace_scsi_zone_wp_update(cmd, rq->__sector,
				  sdkp->zones_wp_offset[zno], good_bytes);
		rq->__sector += sdkp->zones_wp_offset[zno];
		fallthrough;
	case REQ_OP_WRITE_ZEROES:
	case REQ_OP_WRITE:
		if (sdkp->zones_wp_offset[zno] < sd_zbc_zone_sectors(sdkp))
			sdkp->zones_wp_offset[zno] +=
						good_bytes >> SECTOR_SHIFT;
		break;
	case REQ_OP_ZONE_RESET:
		sdkp->zones_wp_offset[zno] = 0;
		break;
	case REQ_OP_ZONE_FINISH:
		sdkp->zones_wp_offset[zno] = sd_zbc_zone_sectors(sdkp);
		break;
	case REQ_OP_ZONE_RESET_ALL:
		memset(sdkp->zones_wp_offset, 0,
		       sdkp->zone_info.nr_zones * sizeof(unsigned int));
		break;
	default:
		break;
	}

unlock_wp_offset:
	spin_unlock_irqrestore(&sdkp->zones_wp_offset_lock, flags);

	return good_bytes;
}

/**
 * sd_zbc_complete - ZBC command post processing.
 * @cmd: Completed command
 * @good_bytes: Command reply bytes
 * @sshdr: command sense header
 *
 * Called from sd_done() to handle zone commands errors and updates to the
 * device queue zone write pointer offset cahce.
 */
unsigned int sd_zbc_complete(struct scsi_cmnd *cmd, unsigned int good_bytes,
		     struct scsi_sense_hdr *sshdr)
{
	int result = cmd->result;
	struct request *rq = scsi_cmd_to_rq(cmd);

	if (op_is_zone_mgmt(req_op(rq)) &&
	    result &&
	    sshdr->sense_key == ILLEGAL_REQUEST &&
	    sshdr->asc == 0x24) {
		/*
		 * INVALID FIELD IN CDB error: a zone management command was
		 * attempted on a conventional zone. Nothing to worry about,
		 * so be quiet about the error.
		 */
		rq->rq_flags |= RQF_QUIET;
	} else if (sd_zbc_need_zone_wp_update(rq))
		good_bytes = sd_zbc_zone_wp_update(cmd, good_bytes);

	if (req_op(rq) == REQ_OP_ZONE_APPEND)
		blk_req_zone_write_unlock(rq);

	return good_bytes;
}

/**
 * sd_zbc_check_zoned_characteristics - Check zoned block device characteristics
 * @sdkp: Target disk
 * @buf: Buffer where to store the VPD page data
 *
 * Read VPD page B6, get information and check that reads are unconstrained.
 */
static int sd_zbc_check_zoned_characteristics(struct scsi_disk *sdkp,
					      unsigned char *buf)
{
	u64 zone_starting_lba_gran;

	if (scsi_get_vpd_page(sdkp->device, 0xb6, buf, 64)) {
		sd_printk(KERN_NOTICE, sdkp,
			  "Read zoned characteristics VPD page failed\n");
		return -ENODEV;
	}

	if (sdkp->device->type != TYPE_ZBC) {
		/* Host-aware */
		sdkp->urswrz = 1;
		sdkp->zones_optimal_open = get_unaligned_be32(&buf[8]);
		sdkp->zones_optimal_nonseq = get_unaligned_be32(&buf[12]);
		sdkp->zones_max_open = 0;
		return 0;
	}

	/* Host-managed */
	sdkp->urswrz = buf[4] & 1;
	sdkp->zones_optimal_open = 0;
	sdkp->zones_optimal_nonseq = 0;
	sdkp->zones_max_open = get_unaligned_be32(&buf[16]);
	/* Check zone alignment method */
	switch (buf[23] & 0xf) {
	case 0:
	case ZBC_CONSTANT_ZONE_LENGTH:
		/* Use zone length */
		break;
	case ZBC_CONSTANT_ZONE_START_OFFSET:
		zone_starting_lba_gran = get_unaligned_be64(&buf[24]);
		if (zone_starting_lba_gran == 0 ||
		    !is_power_of_2(zone_starting_lba_gran) ||
		    logical_to_sectors(sdkp->device, zone_starting_lba_gran) >
		    UINT_MAX) {
			sd_printk(KERN_ERR, sdkp,
				  "Invalid zone starting LBA granularity %llu\n",
				  zone_starting_lba_gran);
			return -ENODEV;
		}
		sdkp->zone_starting_lba_gran = zone_starting_lba_gran;
		break;
	default:
		sd_printk(KERN_ERR, sdkp, "Invalid zone alignment method\n");
		return -ENODEV;
	}

	/*
	 * Check for unconstrained reads: host-managed devices with
	 * constrained reads (drives failing read after write pointer)
	 * are not supported.
	 */
	if (!sdkp->urswrz) {
		if (sdkp->first_scan)
			sd_printk(KERN_NOTICE, sdkp,
			  "constrained reads devices are not supported\n");
		return -ENODEV;
	}

	return 0;
}

/**
 * sd_zbc_check_capacity - Check the device capacity
 * @sdkp: Target disk
 * @buf: command buffer
 * @zblocks: zone size in logical blocks
 *
 * Get the device zone size and check that the device capacity as reported
 * by READ CAPACITY matches the max_lba value (plus one) of the report zones
 * command reply for devices with RC_BASIS == 0.
 *
 * Returns 0 upon success or an error code upon failure.
 */
static int sd_zbc_check_capacity(struct scsi_disk *sdkp, unsigned char *buf,
				 u32 *zblocks)
{
	u64 zone_blocks;
	sector_t max_lba;
	unsigned char *rec;
	int ret;

	/* Do a report zone to get max_lba and the size of the first zone */
	ret = sd_zbc_do_report_zones(sdkp, buf, SD_BUF_SIZE, 0, false);
	if (ret)
		return ret;

	if (sdkp->rc_basis == 0) {
		/* The max_lba field is the capacity of this device */
		max_lba = get_unaligned_be64(&buf[8]);
		if (sdkp->capacity != max_lba + 1) {
			if (sdkp->first_scan)
				sd_printk(KERN_WARNING, sdkp,
					"Changing capacity from %llu to max LBA+1 %llu\n",
					(unsigned long long)sdkp->capacity,
					(unsigned long long)max_lba + 1);
			sdkp->capacity = max_lba + 1;
		}
	}

	if (sdkp->zone_starting_lba_gran == 0) {
		/* Get the size of the first reported zone */
		rec = buf + 64;
		zone_blocks = get_unaligned_be64(&rec[8]);
		if (logical_to_sectors(sdkp->device, zone_blocks) > UINT_MAX) {
			if (sdkp->first_scan)
				sd_printk(KERN_NOTICE, sdkp,
					  "Zone size too large\n");
			return -EFBIG;
		}
	} else {
		zone_blocks = sdkp->zone_starting_lba_gran;
	}

	if (!is_power_of_2(zone_blocks)) {
		sd_printk(KERN_ERR, sdkp,
			  "Zone size %llu is not a power of two.\n",
			  zone_blocks);
		return -EINVAL;
	}

	*zblocks = zone_blocks;

	return 0;
}

static void sd_zbc_print_zones(struct scsi_disk *sdkp)
{
	if (!sd_is_zoned(sdkp) || !sdkp->capacity)
		return;

	if (sdkp->capacity & (sdkp->zone_info.zone_blocks - 1))
		sd_printk(KERN_NOTICE, sdkp,
			  "%u zones of %u logical blocks + 1 runt zone\n",
			  sdkp->zone_info.nr_zones - 1,
			  sdkp->zone_info.zone_blocks);
	else
		sd_printk(KERN_NOTICE, sdkp,
			  "%u zones of %u logical blocks\n",
			  sdkp->zone_info.nr_zones,
			  sdkp->zone_info.zone_blocks);
}

static int sd_zbc_init_disk(struct scsi_disk *sdkp)
{
	sdkp->zones_wp_offset = NULL;
	spin_lock_init(&sdkp->zones_wp_offset_lock);
	sdkp->rev_wp_offset = NULL;
	mutex_init(&sdkp->rev_mutex);
	INIT_WORK(&sdkp->zone_wp_offset_work, sd_zbc_update_wp_offset_workfn);
	sdkp->zone_wp_update_buf = kzalloc(SD_BUF_SIZE, GFP_KERNEL);
	if (!sdkp->zone_wp_update_buf)
		return -ENOMEM;

	return 0;
}

void sd_zbc_free_zone_info(struct scsi_disk *sdkp)
{
	if (!sdkp->zone_wp_update_buf)
		return;

	/* Serialize against revalidate zones */
	mutex_lock(&sdkp->rev_mutex);

	kvfree(sdkp->zones_wp_offset);
	sdkp->zones_wp_offset = NULL;
	kfree(sdkp->zone_wp_update_buf);
	sdkp->zone_wp_update_buf = NULL;

	sdkp->early_zone_info = (struct zoned_disk_info){ };
	sdkp->zone_info = (struct zoned_disk_info){ };

	mutex_unlock(&sdkp->rev_mutex);
}

static void sd_zbc_revalidate_zones_cb(struct gendisk *disk)
{
	struct scsi_disk *sdkp = scsi_disk(disk);

	swap(sdkp->zones_wp_offset, sdkp->rev_wp_offset);
}

/*
 * Call blk_revalidate_disk_zones() if any of the zoned disk properties have
 * changed that make it necessary to call that function. Called by
 * sd_revalidate_disk() after the gendisk capacity has been set.
 */
int sd_zbc_revalidate_zones(struct scsi_disk *sdkp)
{
	struct gendisk *disk = sdkp->disk;
	struct request_queue *q = disk->queue;
	u32 zone_blocks = sdkp->early_zone_info.zone_blocks;
	unsigned int nr_zones = sdkp->early_zone_info.nr_zones;
	u32 max_append;
	int ret = 0;
	unsigned int flags;

	/*
	 * For all zoned disks, initialize zone append emulation data if not
	 * already done. This is necessary also for host-aware disks used as
	 * regular disks due to the presence of partitions as these partitions
	 * may be deleted and the disk zoned model changed back from
	 * BLK_ZONED_NONE to BLK_ZONED_HA.
	 */
	if (sd_is_zoned(sdkp) && !sdkp->zone_wp_update_buf) {
		ret = sd_zbc_init_disk(sdkp);
		if (ret)
			return ret;
	}

	/*
	 * There is nothing to do for regular disks, including host-aware disks
	 * that have partitions.
	 */
	if (!blk_queue_is_zoned(q))
		return 0;

	/*
	 * Make sure revalidate zones are serialized to ensure exclusive
	 * updates of the scsi disk data.
	 */
	mutex_lock(&sdkp->rev_mutex);

	if (sdkp->zone_info.zone_blocks == zone_blocks &&
	    sdkp->zone_info.nr_zones == nr_zones &&
	    disk->nr_zones == nr_zones)
		goto unlock;

	flags = memalloc_noio_save();
	sdkp->zone_info.zone_blocks = zone_blocks;
	sdkp->zone_info.nr_zones = nr_zones;
	sdkp->rev_wp_offset = kvcalloc(nr_zones, sizeof(u32), GFP_KERNEL);
	if (!sdkp->rev_wp_offset) {
		ret = -ENOMEM;
		memalloc_noio_restore(flags);
		goto unlock;
	}

	ret = blk_revalidate_disk_zones(disk, sd_zbc_revalidate_zones_cb);

	memalloc_noio_restore(flags);
	kvfree(sdkp->rev_wp_offset);
	sdkp->rev_wp_offset = NULL;

	if (ret) {
		sdkp->zone_info = (struct zoned_disk_info){ };
		sdkp->capacity = 0;
		goto unlock;
	}

	max_append = min_t(u32, logical_to_sectors(sdkp->device, zone_blocks),
			   q->limits.max_segments << PAGE_SECTORS_SHIFT);
	max_append = min_t(u32, max_append, queue_max_hw_sectors(q));

	blk_queue_max_zone_append_sectors(q, max_append);

	sd_zbc_print_zones(sdkp);

unlock:
	mutex_unlock(&sdkp->rev_mutex);

	return ret;
}

/**
 * sd_zbc_read_zones - Read zone information and update the request queue
 * @sdkp: SCSI disk pointer.
 * @buf: 512 byte buffer used for storing SCSI command output.
 *
 * Read zone information and update the request queue zone characteristics and
 * also the zoned device information in *sdkp. Called by sd_revalidate_disk()
 * before the gendisk capacity has been set.
 */
int sd_zbc_read_zones(struct scsi_disk *sdkp, u8 buf[SD_BUF_SIZE])
{
	struct gendisk *disk = sdkp->disk;
	struct request_queue *q = disk->queue;
	unsigned int nr_zones;
	u32 zone_blocks = 0;
	int ret;

	if (!sd_is_zoned(sdkp)) {
		/*
		 * Device managed or normal SCSI disk, no special handling
		 * required. Nevertheless, free the disk zone information in
		 * case the device type changed.
		 */
		sd_zbc_free_zone_info(sdkp);
		return 0;
	}

	/* READ16/WRITE16/SYNC16 is mandatory for ZBC devices */
	sdkp->device->use_16_for_rw = 1;
	sdkp->device->use_10_for_rw = 0;
	sdkp->device->use_16_for_sync = 1;

	if (!blk_queue_is_zoned(q)) {
		/*
		 * This can happen for a host aware disk with partitions.
		 * The block device zone model was already cleared by
		 * disk_set_zoned(). Only free the scsi disk zone
		 * information and exit early.
		 */
		sd_zbc_free_zone_info(sdkp);
		return 0;
	}

	/* Check zoned block device characteristics (unconstrained reads) */
	ret = sd_zbc_check_zoned_characteristics(sdkp, buf);
	if (ret)
		goto err;

	/* Check the device capacity reported by report zones */
	ret = sd_zbc_check_capacity(sdkp, buf, &zone_blocks);
	if (ret != 0)
		goto err;

	/* The drive satisfies the kernel restrictions: set it up */
	blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q);
	blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE);
	if (sdkp->zones_max_open == U32_MAX)
		disk_set_max_open_zones(disk, 0);
	else
		disk_set_max_open_zones(disk, sdkp->zones_max_open);
	disk_set_max_active_zones(disk, 0);
	nr_zones = round_up(sdkp->capacity, zone_blocks) >> ilog2(zone_blocks);

	sdkp->early_zone_info.nr_zones = nr_zones;
	sdkp->early_zone_info.zone_blocks = zone_blocks;

	return 0;

err:
	sdkp->capacity = 0;

	return ret;
}