aboutsummaryrefslogtreecommitdiffstats
path: root/drivers/md/dm-zoned-target.c
blob: 697f9de37355eecc555bc5052f13e8867571b9e0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Copyright (C) 2017 Western Digital Corporation or its affiliates.
 *
 * This file is released under the GPL.
 */

#include "dm-zoned.h"

#include <linux/module.h>

#define	DM_MSG_PREFIX		"zoned"

#define DMZ_MIN_BIOS		8192

/*
 * Zone BIO context.
 */
struct dmz_bioctx {
	struct dmz_dev		*dev;
	struct dm_zone		*zone;
	struct bio		*bio;
	refcount_t		ref;
};

/*
 * Chunk work descriptor.
 */
struct dm_chunk_work {
	struct work_struct	work;
	refcount_t		refcount;
	struct dmz_target	*target;
	unsigned int		chunk;
	struct bio_list		bio_list;
};

/*
 * Target descriptor.
 */
struct dmz_target {
	struct dm_dev		**ddev;
	unsigned int		nr_ddevs;

	unsigned int		flags;

	/* Zoned block device information */
	struct dmz_dev		*dev;

	/* For metadata handling */
	struct dmz_metadata     *metadata;

	/* For chunk work */
	struct radix_tree_root	chunk_rxtree;
	struct workqueue_struct *chunk_wq;
	struct mutex		chunk_lock;

	/* For cloned BIOs to zones */
	struct bio_set		bio_set;

	/* For flush */
	spinlock_t		flush_lock;
	struct bio_list		flush_list;
	struct delayed_work	flush_work;
	struct workqueue_struct *flush_wq;
};

/*
 * Flush intervals (seconds).
 */
#define DMZ_FLUSH_PERIOD	(10 * HZ)

/*
 * Target BIO completion.
 */
static inline void dmz_bio_endio(struct bio *bio, blk_status_t status)
{
	struct dmz_bioctx *bioctx =
		dm_per_bio_data(bio, sizeof(struct dmz_bioctx));

	if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK)
		bio->bi_status = status;
	if (bioctx->dev && bio->bi_status != BLK_STS_OK)
		bioctx->dev->flags |= DMZ_CHECK_BDEV;

	if (refcount_dec_and_test(&bioctx->ref)) {
		struct dm_zone *zone = bioctx->zone;

		if (zone) {
			if (bio->bi_status != BLK_STS_OK &&
			    bio_op(bio) == REQ_OP_WRITE &&
			    dmz_is_seq(zone))
				set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags);
			dmz_deactivate_zone(zone);
		}
		bio_endio(bio);
	}
}

/*
 * Completion callback for an internally cloned target BIO. This terminates the
 * target BIO when there are no more references to its context.
 */
static void dmz_clone_endio(struct bio *clone)
{
	struct dmz_bioctx *bioctx = clone->bi_private;
	blk_status_t status = clone->bi_status;

	bio_put(clone);
	dmz_bio_endio(bioctx->bio, status);
}

/*
 * Issue a clone of a target BIO. The clone may only partially process the
 * original target BIO.
 */
static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone,
			  struct bio *bio, sector_t chunk_block,
			  unsigned int nr_blocks)
{
	struct dmz_bioctx *bioctx =
		dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
	struct dmz_dev *dev = zone->dev;
	struct bio *clone;

	if (dev->flags & DMZ_BDEV_DYING)
		return -EIO;

	clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set);
	if (!clone)
		return -ENOMEM;

	bio_set_dev(clone, dev->bdev);
	bioctx->dev = dev;
	clone->bi_iter.bi_sector =
		dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block);
	clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT;
	clone->bi_end_io = dmz_clone_endio;
	clone->bi_private = bioctx;

	bio_advance(bio, clone->bi_iter.bi_size);

	refcount_inc(&bioctx->ref);
	submit_bio_noacct(clone);

	if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone))
		zone->wp_block += nr_blocks;

	return 0;
}

/*
 * Zero out pages of discarded blocks accessed by a read BIO.
 */
static void dmz_handle_read_zero(struct dmz_target *dmz, struct bio *bio,
				 sector_t chunk_block, unsigned int nr_blocks)
{
	unsigned int size = nr_blocks << DMZ_BLOCK_SHIFT;

	/* Clear nr_blocks */
	swap(bio->bi_iter.bi_size, size);
	zero_fill_bio(bio);
	swap(bio->bi_iter.bi_size, size);

	bio_advance(bio, size);
}

/*
 * Process a read BIO.
 */
static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone,
			   struct bio *bio)
{
	struct dmz_metadata *zmd = dmz->metadata;
	sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio));
	unsigned int nr_blocks = dmz_bio_blocks(bio);
	sector_t end_block = chunk_block + nr_blocks;
	struct dm_zone *rzone, *bzone;
	int ret;

	/* Read into unmapped chunks need only zeroing the BIO buffer */
	if (!zone) {
		zero_fill_bio(bio);
		return 0;
	}

	DMDEBUG("(%s): READ chunk %llu -> %s zone %u, block %llu, %u blocks",
		dmz_metadata_label(zmd),
		(unsigned long long)dmz_bio_chunk(zmd, bio),
		(dmz_is_rnd(zone) ? "RND" :
		 (dmz_is_cache(zone) ? "CACHE" : "SEQ")),
		zone->id,
		(unsigned long long)chunk_block, nr_blocks);

	/* Check block validity to determine the read location */
	bzone = zone->bzone;
	while (chunk_block < end_block) {
		nr_blocks = 0;
		if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
		    chunk_block < zone->wp_block) {
			/* Test block validity in the data zone */
			ret = dmz_block_valid(zmd, zone, chunk_block);
			if (ret < 0)
				return ret;
			if (ret > 0) {
				/* Read data zone blocks */
				nr_blocks = ret;
				rzone = zone;
			}
		}

		/*
		 * No valid blocks found in the data zone.
		 * Check the buffer zone, if there is one.
		 */
		if (!nr_blocks && bzone) {
			ret = dmz_block_valid(zmd, bzone, chunk_block);
			if (ret < 0)
				return ret;
			if (ret > 0) {
				/* Read buffer zone blocks */
				nr_blocks = ret;
				rzone = bzone;
			}
		}

		if (nr_blocks) {
			/* Valid blocks found: read them */
			nr_blocks = min_t(unsigned int, nr_blocks,
					  end_block - chunk_block);
			ret = dmz_submit_bio(dmz, rzone, bio,
					     chunk_block, nr_blocks);
			if (ret)
				return ret;
			chunk_block += nr_blocks;
		} else {
			/* No valid block: zeroout the current BIO block */
			dmz_handle_read_zero(dmz, bio, chunk_block, 1);
			chunk_block++;
		}
	}

	return 0;
}

/*
 * Write blocks directly in a data zone, at the write pointer.
 * If a buffer zone is assigned, invalidate the blocks written
 * in place.
 */
static int dmz_handle_direct_write(struct dmz_target *dmz,
				   struct dm_zone *zone, struct bio *bio,
				   sector_t chunk_block,
				   unsigned int nr_blocks)
{
	struct dmz_metadata *zmd = dmz->metadata;
	struct dm_zone *bzone = zone->bzone;
	int ret;

	if (dmz_is_readonly(zone))
		return -EROFS;

	/* Submit write */
	ret = dmz_submit_bio(dmz, zone, bio, chunk_block, nr_blocks);
	if (ret)
		return ret;

	/*
	 * Validate the blocks in the data zone and invalidate
	 * in the buffer zone, if there is one.
	 */
	ret = dmz_validate_blocks(zmd, zone, chunk_block, nr_blocks);
	if (ret == 0 && bzone)
		ret = dmz_invalidate_blocks(zmd, bzone, chunk_block, nr_blocks);

	return ret;
}

/*
 * Write blocks in the buffer zone of @zone.
 * If no buffer zone is assigned yet, get one.
 * Called with @zone write locked.
 */
static int dmz_handle_buffered_write(struct dmz_target *dmz,
				     struct dm_zone *zone, struct bio *bio,
				     sector_t chunk_block,
				     unsigned int nr_blocks)
{
	struct dmz_metadata *zmd = dmz->metadata;
	struct dm_zone *bzone;
	int ret;

	/* Get the buffer zone. One will be allocated if needed */
	bzone = dmz_get_chunk_buffer(zmd, zone);
	if (IS_ERR(bzone))
		return PTR_ERR(bzone);

	if (dmz_is_readonly(bzone))
		return -EROFS;

	/* Submit write */
	ret = dmz_submit_bio(dmz, bzone, bio, chunk_block, nr_blocks);
	if (ret)
		return ret;

	/*
	 * Validate the blocks in the buffer zone
	 * and invalidate in the data zone.
	 */
	ret = dmz_validate_blocks(zmd, bzone, chunk_block, nr_blocks);
	if (ret == 0 && chunk_block < zone->wp_block)
		ret = dmz_invalidate_blocks(zmd, zone, chunk_block, nr_blocks);

	return ret;
}

/*
 * Process a write BIO.
 */
static int dmz_handle_write(struct dmz_target *dmz, struct dm_zone *zone,
			    struct bio *bio)
{
	struct dmz_metadata *zmd = dmz->metadata;
	sector_t chunk_block = dmz_chunk_block(zmd, dmz_bio_block(bio));
	unsigned int nr_blocks = dmz_bio_blocks(bio);

	if (!zone)
		return -ENOSPC;

	DMDEBUG("(%s): WRITE chunk %llu -> %s zone %u, block %llu, %u blocks",
		dmz_metadata_label(zmd),
		(unsigned long long)dmz_bio_chunk(zmd, bio),
		(dmz_is_rnd(zone) ? "RND" :
		 (dmz_is_cache(zone) ? "CACHE" : "SEQ")),
		zone->id,
		(unsigned long long)chunk_block, nr_blocks);

	if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
	    chunk_block == zone->wp_block) {
		/*
		 * zone is a random zone or it is a sequential zone
		 * and the BIO is aligned to the zone write pointer:
		 * direct write the zone.
		 */
		return dmz_handle_direct_write(dmz, zone, bio,
					       chunk_block, nr_blocks);
	}

	/*
	 * This is an unaligned write in a sequential zone:
	 * use buffered write.
	 */
	return dmz_handle_buffered_write(dmz, zone, bio, chunk_block, nr_blocks);
}

/*
 * Process a discard BIO.
 */
static int dmz_handle_discard(struct dmz_target *dmz, struct dm_zone *zone,
			      struct bio *bio)
{
	struct dmz_metadata *zmd = dmz->metadata;
	sector_t block = dmz_bio_block(bio);
	unsigned int nr_blocks = dmz_bio_blocks(bio);
	sector_t chunk_block = dmz_chunk_block(zmd, block);
	int ret = 0;

	/* For unmapped chunks, there is nothing to do */
	if (!zone)
		return 0;

	if (dmz_is_readonly(zone))
		return -EROFS;

	DMDEBUG("(%s): DISCARD chunk %llu -> zone %u, block %llu, %u blocks",
		dmz_metadata_label(dmz->metadata),
		(unsigned long long)dmz_bio_chunk(zmd, bio),
		zone->id,
		(unsigned long long)chunk_block, nr_blocks);

	/*
	 * Invalidate blocks in the data zone and its
	 * buffer zone if one is mapped.
	 */
	if (dmz_is_rnd(zone) || dmz_is_cache(zone) ||
	    chunk_block < zone->wp_block)
		ret = dmz_invalidate_blocks(zmd, zone, chunk_block, nr_blocks);
	if (ret == 0 && zone->bzone)
		ret = dmz_invalidate_blocks(zmd, zone->bzone,
					    chunk_block, nr_blocks);
	return ret;
}

/*
 * Process a BIO.
 */
static void dmz_handle_bio(struct dmz_target *dmz, struct dm_chunk_work *cw,
			   struct bio *bio)
{
	struct dmz_bioctx *bioctx =
		dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
	struct dmz_metadata *zmd = dmz->metadata;
	struct dm_zone *zone;
	int ret;

	dmz_lock_metadata(zmd);

	/*
	 * Get the data zone mapping the chunk. There may be no
	 * mapping for read and discard. If a mapping is obtained,
	 + the zone returned will be set to active state.
	 */
	zone = dmz_get_chunk_mapping(zmd, dmz_bio_chunk(zmd, bio),
				     bio_op(bio));
	if (IS_ERR(zone)) {
		ret = PTR_ERR(zone);
		goto out;
	}

	/* Process the BIO */
	if (zone) {
		dmz_activate_zone(zone);
		bioctx->zone = zone;
		dmz_reclaim_bio_acc(zone->dev->reclaim);
	}

	switch (bio_op(bio)) {
	case REQ_OP_READ:
		ret = dmz_handle_read(dmz, zone, bio);
		break;
	case REQ_OP_WRITE:
		ret = dmz_handle_write(dmz, zone, bio);
		break;
	case REQ_OP_DISCARD:
	case REQ_OP_WRITE_ZEROES:
		ret = dmz_handle_discard(dmz, zone, bio);
		break;
	default:
		DMERR("(%s): Unsupported BIO operation 0x%x",
		      dmz_metadata_label(dmz->metadata), bio_op(bio));
		ret = -EIO;
	}

	/*
	 * Release the chunk mapping. This will check that the mapping
	 * is still valid, that is, that the zone used still has valid blocks.
	 */
	if (zone)
		dmz_put_chunk_mapping(zmd, zone);
out:
	dmz_bio_endio(bio, errno_to_blk_status(ret));

	dmz_unlock_metadata(zmd);
}

/*
 * Increment a chunk reference counter.
 */
static inline void dmz_get_chunk_work(struct dm_chunk_work *cw)
{
	refcount_inc(&cw->refcount);
}

/*
 * Decrement a chunk work reference count and
 * free it if it becomes 0.
 */
static void dmz_put_chunk_work(struct dm_chunk_work *cw)
{
	if (refcount_dec_and_test(&cw->refcount)) {
		WARN_ON(!bio_list_empty(&cw->bio_list));
		radix_tree_delete(&cw->target->chunk_rxtree, cw->chunk);
		kfree(cw);
	}
}

/*
 * Chunk BIO work function.
 */
static void dmz_chunk_work(struct work_struct *work)
{
	struct dm_chunk_work *cw = container_of(work, struct dm_chunk_work, work);
	struct dmz_target *dmz = cw->target;
	struct bio *bio;

	mutex_lock(&dmz->chunk_lock);

	/* Process the chunk BIOs */
	while ((bio = bio_list_pop(&cw->bio_list))) {
		mutex_unlock(&dmz->chunk_lock);
		dmz_handle_bio(dmz, cw, bio);
		mutex_lock(&dmz->chunk_lock);
		dmz_put_chunk_work(cw);
	}

	/* Queueing the work incremented the work refcount */
	dmz_put_chunk_work(cw);

	mutex_unlock(&dmz->chunk_lock);
}

/*
 * Flush work.
 */
static void dmz_flush_work(struct work_struct *work)
{
	struct dmz_target *dmz = container_of(work, struct dmz_target, flush_work.work);
	struct bio *bio;
	int ret;

	/* Flush dirty metadata blocks */
	ret = dmz_flush_metadata(dmz->metadata);
	if (ret)
		DMDEBUG("(%s): Metadata flush failed, rc=%d",
			dmz_metadata_label(dmz->metadata), ret);

	/* Process queued flush requests */
	while (1) {
		spin_lock(&dmz->flush_lock);
		bio = bio_list_pop(&dmz->flush_list);
		spin_unlock(&dmz->flush_lock);

		if (!bio)
			break;

		dmz_bio_endio(bio, errno_to_blk_status(ret));
	}

	queue_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD);
}

/*
 * Get a chunk work and start it to process a new BIO.
 * If the BIO chunk has no work yet, create one.
 */
static int dmz_queue_chunk_work(struct dmz_target *dmz, struct bio *bio)
{
	unsigned int chunk = dmz_bio_chunk(dmz->metadata, bio);
	struct dm_chunk_work *cw;
	int ret = 0;

	mutex_lock(&dmz->chunk_lock);

	/* Get the BIO chunk work. If one is not active yet, create one */
	cw = radix_tree_lookup(&dmz->chunk_rxtree, chunk);
	if (cw) {
		dmz_get_chunk_work(cw);
	} else {
		/* Create a new chunk work */
		cw = kmalloc(sizeof(struct dm_chunk_work), GFP_NOIO);
		if (unlikely(!cw)) {
			ret = -ENOMEM;
			goto out;
		}

		INIT_WORK(&cw->work, dmz_chunk_work);
		refcount_set(&cw->refcount, 1);
		cw->target = dmz;
		cw->chunk = chunk;
		bio_list_init(&cw->bio_list);

		ret = radix_tree_insert(&dmz->chunk_rxtree, chunk, cw);
		if (unlikely(ret)) {
			kfree(cw);
			goto out;
		}
	}

	bio_list_add(&cw->bio_list, bio);

	if (queue_work(dmz->chunk_wq, &cw->work))
		dmz_get_chunk_work(cw);
out:
	mutex_unlock(&dmz->chunk_lock);
	return ret;
}

/*
 * Check if the backing device is being removed. If it's on the way out,
 * start failing I/O. Reclaim and metadata components also call this
 * function to cleanly abort operation in the event of such failure.
 */
bool dmz_bdev_is_dying(struct dmz_dev *dmz_dev)
{
	if (dmz_dev->flags & DMZ_BDEV_DYING)
		return true;

	if (dmz_dev->flags & DMZ_CHECK_BDEV)
		return !dmz_check_bdev(dmz_dev);

	if (blk_queue_dying(bdev_get_queue(dmz_dev->bdev))) {
		dmz_dev_warn(dmz_dev, "Backing device queue dying");
		dmz_dev->flags |= DMZ_BDEV_DYING;
	}

	return dmz_dev->flags & DMZ_BDEV_DYING;
}

/*
 * Check the backing device availability. This detects such events as
 * backing device going offline due to errors, media removals, etc.
 * This check is less efficient than dmz_bdev_is_dying() and should
 * only be performed as a part of error handling.
 */
bool dmz_check_bdev(struct dmz_dev *dmz_dev)
{
	struct gendisk *disk;

	dmz_dev->flags &= ~DMZ_CHECK_BDEV;

	if (dmz_bdev_is_dying(dmz_dev))
		return false;

	disk = dmz_dev->bdev->bd_disk;
	if (disk->fops->check_events &&
	    disk->fops->check_events(disk, 0) & DISK_EVENT_MEDIA_CHANGE) {
		dmz_dev_warn(dmz_dev, "Backing device offline");
		dmz_dev->flags |= DMZ_BDEV_DYING;
	}

	return !(dmz_dev->flags & DMZ_BDEV_DYING);
}

/*
 * Process a new BIO.
 */
static int dmz_map(struct dm_target *ti, struct bio *bio)
{
	struct dmz_target *dmz = ti->private;
	struct dmz_metadata *zmd = dmz->metadata;
	struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx));
	sector_t sector = bio->bi_iter.bi_sector;
	unsigned int nr_sectors = bio_sectors(bio);
	sector_t chunk_sector;
	int ret;

	if (dmz_dev_is_dying(zmd))
		return DM_MAPIO_KILL;

	DMDEBUG("(%s): BIO op %d sector %llu + %u => chunk %llu, block %llu, %u blocks",
		dmz_metadata_label(zmd),
		bio_op(bio), (unsigned long long)sector, nr_sectors,
		(unsigned long long)dmz_bio_chunk(zmd, bio),
		(unsigned long long)dmz_chunk_block(zmd, dmz_bio_block(bio)),
		(unsigned int)dmz_bio_blocks(bio));

	if (!nr_sectors && bio_op(bio) != REQ_OP_WRITE)
		return DM_MAPIO_REMAPPED;

	/* The BIO should be block aligned */
	if ((nr_sectors & DMZ_BLOCK_SECTORS_MASK) || (sector & DMZ_BLOCK_SECTORS_MASK))
		return DM_MAPIO_KILL;

	/* Initialize the BIO context */
	bioctx->dev = NULL;
	bioctx->zone = NULL;
	bioctx->bio = bio;
	refcount_set(&bioctx->ref, 1);

	/* Set the BIO pending in the flush list */
	if (!nr_sectors && bio_op(bio) == REQ_OP_WRITE) {
		spin_lock(&dmz->flush_lock);
		bio_list_add(&dmz->flush_list, bio);
		spin_unlock(&dmz->flush_lock);
		mod_delayed_work(dmz->flush_wq, &dmz->flush_work, 0);
		return DM_MAPIO_SUBMITTED;
	}

	/* Split zone BIOs to fit entirely into a zone */
	chunk_sector = sector & (dmz_zone_nr_sectors(zmd) - 1);
	if (chunk_sector + nr_sectors > dmz_zone_nr_sectors(zmd))
		dm_accept_partial_bio(bio, dmz_zone_nr_sectors(zmd) - chunk_sector);

	/* Now ready to handle this BIO */
	ret = dmz_queue_chunk_work(dmz, bio);
	if (ret) {
		DMDEBUG("(%s): BIO op %d, can't process chunk %llu, err %i",
			dmz_metadata_label(zmd),
			bio_op(bio), (u64)dmz_bio_chunk(zmd, bio),
			ret);
		return DM_MAPIO_REQUEUE;
	}

	return DM_MAPIO_SUBMITTED;
}

/*
 * Get zoned device information.
 */
static int dmz_get_zoned_device(struct dm_target *ti, char *path,
				int idx, int nr_devs)
{
	struct dmz_target *dmz = ti->private;
	struct dm_dev *ddev;
	struct dmz_dev *dev;
	int ret;
	struct block_device *bdev;

	/* Get the target device */
	ret = dm_get_device(ti, path, dm_table_get_mode(ti->table), &ddev);
	if (ret) {
		ti->error = "Get target device failed";
		return ret;
	}

	bdev = ddev->bdev;
	if (bdev_zoned_model(bdev) == BLK_ZONED_NONE) {
		if (nr_devs == 1) {
			ti->error = "Invalid regular device";
			goto err;
		}
		if (idx != 0) {
			ti->error = "First device must be a regular device";
			goto err;
		}
		if (dmz->ddev[0]) {
			ti->error = "Too many regular devices";
			goto err;
		}
		dev = &dmz->dev[idx];
		dev->flags = DMZ_BDEV_REGULAR;
	} else {
		if (dmz->ddev[idx]) {
			ti->error = "Too many zoned devices";
			goto err;
		}
		if (nr_devs > 1 && idx == 0) {
			ti->error = "First device must be a regular device";
			goto err;
		}
		dev = &dmz->dev[idx];
	}
	dev->bdev = bdev;
	dev->dev_idx = idx;
	(void)bdevname(dev->bdev, dev->name);

	dev->capacity = i_size_read(bdev->bd_inode) >> SECTOR_SHIFT;
	if (ti->begin) {
		ti->error = "Partial mapping is not supported";
		goto err;
	}

	dmz->ddev[idx] = ddev;

	return 0;
err:
	dm_put_device(ti, ddev);
	return -EINVAL;
}

/*
 * Cleanup zoned device information.
 */
static void dmz_put_zoned_device(struct dm_target *ti)
{
	struct dmz_target *dmz = ti->private;
	int i;

	for (i = 0; i < dmz->nr_ddevs; i++) {
		if (dmz->ddev[i]) {
			dm_put_device(ti, dmz->ddev[i]);
			dmz->ddev[i] = NULL;
		}
	}
}

static int dmz_fixup_devices(struct dm_target *ti)
{
	struct dmz_target *dmz = ti->private;
	struct dmz_dev *reg_dev, *zoned_dev;
	struct request_queue *q;
	sector_t zone_nr_sectors = 0;
	int i;

	/*
	 * When we have more than on devices, the first one must be a
	 * regular block device and the others zoned block devices.
	 */
	if (dmz->nr_ddevs > 1) {
		reg_dev = &dmz->dev[0];
		if (!(reg_dev->flags & DMZ_BDEV_REGULAR)) {
			ti->error = "Primary disk is not a regular device";
			return -EINVAL;
		}
		for (i = 1; i < dmz->nr_ddevs; i++) {
			zoned_dev = &dmz->dev[i];
			if (zoned_dev->flags & DMZ_BDEV_REGULAR) {
				ti->error = "Secondary disk is not a zoned device";
				return -EINVAL;
			}
			q = bdev_get_queue(zoned_dev->bdev);
			if (zone_nr_sectors &&
			    zone_nr_sectors != blk_queue_zone_sectors(q)) {
				ti->error = "Zone nr sectors mismatch";
				return -EINVAL;
			}
			zone_nr_sectors = blk_queue_zone_sectors(q);
			zoned_dev->zone_nr_sectors = zone_nr_sectors;
			zoned_dev->nr_zones =
				blkdev_nr_zones(zoned_dev->bdev->bd_disk);
		}
	} else {
		reg_dev = NULL;
		zoned_dev = &dmz->dev[0];
		if (zoned_dev->flags & DMZ_BDEV_REGULAR) {
			ti->error = "Disk is not a zoned device";
			return -EINVAL;
		}
		q = bdev_get_queue(zoned_dev->bdev);
		zoned_dev->zone_nr_sectors = blk_queue_zone_sectors(q);
		zoned_dev->nr_zones = blkdev_nr_zones(zoned_dev->bdev->bd_disk);
	}

	if (reg_dev) {
		sector_t zone_offset;

		reg_dev->zone_nr_sectors = zone_nr_sectors;
		reg_dev->nr_zones =
			DIV_ROUND_UP_SECTOR_T(reg_dev->capacity,
					      reg_dev->zone_nr_sectors);
		reg_dev->zone_offset = 0;
		zone_offset = reg_dev->nr_zones;
		for (i = 1; i < dmz->nr_ddevs; i++) {
			dmz->dev[i].zone_offset = zone_offset;
			zone_offset += dmz->dev[i].nr_zones;
		}
	}
	return 0;
}

/*
 * Setup target.
 */
static int dmz_ctr(struct dm_target *ti, unsigned int argc, char **argv)
{
	struct dmz_target *dmz;
	int ret, i;

	/* Check arguments */
	if (argc < 1) {
		ti->error = "Invalid argument count";
		return -EINVAL;
	}

	/* Allocate and initialize the target descriptor */
	dmz = kzalloc(sizeof(struct dmz_target), GFP_KERNEL);
	if (!dmz) {
		ti->error = "Unable to allocate the zoned target descriptor";
		return -ENOMEM;
	}
	dmz->dev = kcalloc(argc, sizeof(struct dmz_dev), GFP_KERNEL);
	if (!dmz->dev) {
		ti->error = "Unable to allocate the zoned device descriptors";
		kfree(dmz);
		return -ENOMEM;
	}
	dmz->ddev = kcalloc(argc, sizeof(struct dm_dev *), GFP_KERNEL);
	if (!dmz->ddev) {
		ti->error = "Unable to allocate the dm device descriptors";
		ret = -ENOMEM;
		goto err;
	}
	dmz->nr_ddevs = argc;

	ti->private = dmz;

	/* Get the target zoned block device */
	for (i = 0; i < argc; i++) {
		ret = dmz_get_zoned_device(ti, argv[i], i, argc);
		if (ret)
			goto err_dev;
	}
	ret = dmz_fixup_devices(ti);
	if (ret)
		goto err_dev;

	/* Initialize metadata */
	ret = dmz_ctr_metadata(dmz->dev, argc, &dmz->metadata,
			       dm_table_device_name(ti->table));
	if (ret) {
		ti->error = "Metadata initialization failed";
		goto err_dev;
	}

	/* Set target (no write same support) */
	ti->max_io_len = dmz_zone_nr_sectors(dmz->metadata);
	ti->num_flush_bios = 1;
	ti->num_discard_bios = 1;
	ti->num_write_zeroes_bios = 1;
	ti->per_io_data_size = sizeof(struct dmz_bioctx);
	ti->flush_supported = true;
	ti->discards_supported = true;

	/* The exposed capacity is the number of chunks that can be mapped */
	ti->len = (sector_t)dmz_nr_chunks(dmz->metadata) <<
		dmz_zone_nr_sectors_shift(dmz->metadata);

	/* Zone BIO */
	ret = bioset_init(&dmz->bio_set, DMZ_MIN_BIOS, 0, 0);
	if (ret) {
		ti->error = "Create BIO set failed";
		goto err_meta;
	}

	/* Chunk BIO work */
	mutex_init(&dmz->chunk_lock);
	INIT_RADIX_TREE(&dmz->chunk_rxtree, GFP_NOIO);
	dmz->chunk_wq = alloc_workqueue("dmz_cwq_%s",
					WQ_MEM_RECLAIM | WQ_UNBOUND, 0,
					dmz_metadata_label(dmz->metadata));
	if (!dmz->chunk_wq) {
		ti->error = "Create chunk workqueue failed";
		ret = -ENOMEM;
		goto err_bio;
	}

	/* Flush work */
	spin_lock_init(&dmz->flush_lock);
	bio_list_init(&dmz->flush_list);
	INIT_DELAYED_WORK(&dmz->flush_work, dmz_flush_work);
	dmz->flush_wq = alloc_ordered_workqueue("dmz_fwq_%s", WQ_MEM_RECLAIM,
						dmz_metadata_label(dmz->metadata));
	if (!dmz->flush_wq) {
		ti->error = "Create flush workqueue failed";
		ret = -ENOMEM;
		goto err_cwq;
	}
	mod_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD);

	/* Initialize reclaim */
	for (i = 0; i < dmz->nr_ddevs; i++) {
		ret = dmz_ctr_reclaim(dmz->metadata, &dmz->dev[i].reclaim, i);
		if (ret) {
			ti->error = "Zone reclaim initialization failed";
			goto err_fwq;
		}
	}

	DMINFO("(%s): Target device: %llu 512-byte logical sectors (%llu blocks)",
	       dmz_metadata_label(dmz->metadata),
	       (unsigned long long)ti->len,
	       (unsigned long long)dmz_sect2blk(ti->len));

	return 0;
err_fwq:
	destroy_workqueue(dmz->flush_wq);
err_cwq:
	destroy_workqueue(dmz->chunk_wq);
err_bio:
	mutex_destroy(&dmz->chunk_lock);
	bioset_exit(&dmz->bio_set);
err_meta:
	dmz_dtr_metadata(dmz->metadata);
err_dev:
	dmz_put_zoned_device(ti);
err:
	kfree(dmz->dev);
	kfree(dmz);

	return ret;
}

/*
 * Cleanup target.
 */
static void dmz_dtr(struct dm_target *ti)
{
	struct dmz_target *dmz = ti->private;
	int i;

	flush_workqueue(dmz->chunk_wq);
	destroy_workqueue(dmz->chunk_wq);

	for (i = 0; i < dmz->nr_ddevs; i++)
		dmz_dtr_reclaim(dmz->dev[i].reclaim);

	cancel_delayed_work_sync(&dmz->flush_work);
	destroy_workqueue(dmz->flush_wq);

	(void) dmz_flush_metadata(dmz->metadata);

	dmz_dtr_metadata(dmz->metadata);

	bioset_exit(&dmz->bio_set);

	dmz_put_zoned_device(ti);

	mutex_destroy(&dmz->chunk_lock);

	kfree(dmz->dev);
	kfree(dmz);
}

/*
 * Setup target request queue limits.
 */
static void dmz_io_hints(struct dm_target *ti, struct queue_limits *limits)
{
	struct dmz_target *dmz = ti->private;
	unsigned int chunk_sectors = dmz_zone_nr_sectors(dmz->metadata);

	limits->logical_block_size = DMZ_BLOCK_SIZE;
	limits->physical_block_size = DMZ_BLOCK_SIZE;

	blk_limits_io_min(limits, DMZ_BLOCK_SIZE);
	blk_limits_io_opt(limits, DMZ_BLOCK_SIZE);

	limits->discard_alignment = DMZ_BLOCK_SIZE;
	limits->discard_granularity = DMZ_BLOCK_SIZE;
	limits->max_discard_sectors = chunk_sectors;
	limits->max_hw_discard_sectors = chunk_sectors;
	limits->max_write_zeroes_sectors = chunk_sectors;

	/* FS hint to try to align to the device zone size */
	limits->chunk_sectors = chunk_sectors;
	limits->max_sectors = chunk_sectors;

	/* We are exposing a drive-managed zoned block device */
	limits->zoned = BLK_ZONED_NONE;
}

/*
 * Pass on ioctl to the backend device.
 */
static int dmz_prepare_ioctl(struct dm_target *ti, struct block_device **bdev)
{
	struct dmz_target *dmz = ti->private;
	struct dmz_dev *dev = &dmz->dev[0];

	if (!dmz_check_bdev(dev))
		return -EIO;

	*bdev = dev->bdev;

	return 0;
}

/*
 * Stop works on suspend.
 */
static void dmz_suspend(struct dm_target *ti)
{
	struct dmz_target *dmz = ti->private;
	int i;

	flush_workqueue(dmz->chunk_wq);
	for (i = 0; i < dmz->nr_ddevs; i++)
		dmz_suspend_reclaim(dmz->dev[i].reclaim);
	cancel_delayed_work_sync(&dmz->flush_work);
}

/*
 * Restart works on resume or if suspend failed.
 */
static void dmz_resume(struct dm_target *ti)
{
	struct dmz_target *dmz = ti->private;
	int i;

	queue_delayed_work(dmz->flush_wq, &dmz->flush_work, DMZ_FLUSH_PERIOD);
	for (i = 0; i < dmz->nr_ddevs; i++)
		dmz_resume_reclaim(dmz->dev[i].reclaim);
}

static int dmz_iterate_devices(struct dm_target *ti,
			       iterate_devices_callout_fn fn, void *data)
{
	struct dmz_target *dmz = ti->private;
	unsigned int zone_nr_sectors = dmz_zone_nr_sectors(dmz->metadata);
	sector_t capacity;
	int i, r;

	for (i = 0; i < dmz->nr_ddevs; i++) {
		capacity = dmz->dev[i].capacity & ~(zone_nr_sectors - 1);
		r = fn(ti, dmz->ddev[i], 0, capacity, data);
		if (r)
			break;
	}
	return r;
}

static void dmz_status(struct dm_target *ti, status_type_t type,
		       unsigned int status_flags, char *result,
		       unsigned int maxlen)
{
	struct dmz_target *dmz = ti->private;
	ssize_t sz = 0;
	char buf[BDEVNAME_SIZE];
	struct dmz_dev *dev;
	int i;

	switch (type) {
	case STATUSTYPE_INFO:
		DMEMIT("%u zones %u/%u cache",
		       dmz_nr_zones(dmz->metadata),
		       dmz_nr_unmap_cache_zones(dmz->metadata),
		       dmz_nr_cache_zones(dmz->metadata));
		for (i = 0; i < dmz->nr_ddevs; i++) {
			/*
			 * For a multi-device setup the first device
			 * contains only cache zones.
			 */
			if ((i == 0) &&
			    (dmz_nr_cache_zones(dmz->metadata) > 0))
				continue;
			DMEMIT(" %u/%u random %u/%u sequential",
			       dmz_nr_unmap_rnd_zones(dmz->metadata, i),
			       dmz_nr_rnd_zones(dmz->metadata, i),
			       dmz_nr_unmap_seq_zones(dmz->metadata, i),
			       dmz_nr_seq_zones(dmz->metadata, i));
		}
		break;
	case STATUSTYPE_TABLE:
		dev = &dmz->dev[0];
		format_dev_t(buf, dev->bdev->bd_dev);
		DMEMIT("%s", buf);
		for (i = 1; i < dmz->nr_ddevs; i++) {
			dev = &dmz->dev[i];
			format_dev_t(buf, dev->bdev->bd_dev);
			DMEMIT(" %s", buf);
		}
		break;
	}
	return;
}

static int dmz_message(struct dm_target *ti, unsigned int argc, char **argv,
		       char *result, unsigned int maxlen)
{
	struct dmz_target *dmz = ti->private;
	int r = -EINVAL;

	if (!strcasecmp(argv[0], "reclaim")) {
		int i;

		for (i = 0; i < dmz->nr_ddevs; i++)
			dmz_schedule_reclaim(dmz->dev[i].reclaim);
		r = 0;
	} else
		DMERR("unrecognized message %s", argv[0]);
	return r;
}

static struct target_type dmz_type = {
	.name		 = "zoned",
	.version	 = {2, 0, 0},
	.features	 = DM_TARGET_SINGLETON | DM_TARGET_ZONED_HM,
	.module		 = THIS_MODULE,
	.ctr		 = dmz_ctr,
	.dtr		 = dmz_dtr,
	.map		 = dmz_map,
	.io_hints	 = dmz_io_hints,
	.prepare_ioctl	 = dmz_prepare_ioctl,
	.postsuspend	 = dmz_suspend,
	.resume		 = dmz_resume,
	.iterate_devices = dmz_iterate_devices,
	.status		 = dmz_status,
	.message	 = dmz_message,
};

static int __init dmz_init(void)
{
	return dm_register_target(&dmz_type);
}

static void __exit dmz_exit(void)
{
	dm_unregister_target(&dmz_type);
}

module_init(dmz_init);
module_exit(dmz_exit);

MODULE_DESCRIPTION(DM_NAME " target for zoned block devices");
MODULE_AUTHOR("Damien Le Moal <damien.lemoal@wdc.com>");
MODULE_LICENSE("GPL");