aboutsummaryrefslogtreecommitdiffstats
path: root/module/os/linux/zfs/zvol_os.c
blob: ce719734c0cc9f346504552cad7c0acab45afae1 (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
/*
 * CDDL HEADER START
 *
 * The contents of this file are subject to the terms of the
 * Common Development and Distribution License (the "License").
 * You may not use this file except in compliance with the License.
 *
 * You can obtain a copy of the license at usr/src/OPENSOLARIS.LICENSE
 * or http://www.opensolaris.org/os/licensing.
 * See the License for the specific language governing permissions
 * and limitations under the License.
 *
 * When distributing Covered Code, include this CDDL HEADER in each
 * file and include the License file at usr/src/OPENSOLARIS.LICENSE.
 * If applicable, add the following below this CDDL HEADER, with the
 * fields enclosed by brackets "[]" replaced with your own identifying
 * information: Portions Copyright [yyyy] [name of copyright owner]
 *
 * CDDL HEADER END
 */

#include <sys/dataset_kstats.h>
#include <sys/dbuf.h>
#include <sys/dmu_traverse.h>
#include <sys/dsl_dataset.h>
#include <sys/dsl_prop.h>
#include <sys/dsl_dir.h>
#include <sys/zap.h>
#include <sys/zfeature.h>
#include <sys/zil_impl.h>
#include <sys/dmu_tx.h>
#include <sys/zio.h>
#include <sys/zfs_rlock.h>
#include <sys/spa_impl.h>
#include <sys/zvol.h>
#include <sys/zvol_impl.h>

#include <linux/blkdev_compat.h>
#include <linux/task_io_accounting_ops.h>

unsigned int zvol_major = ZVOL_MAJOR;
unsigned int zvol_request_sync = 0;
unsigned int zvol_prefetch_bytes = (128 * 1024);
unsigned long zvol_max_discard_blocks = 16384;
unsigned int zvol_threads = 32;

struct zvol_state_os {
	struct gendisk		*zvo_disk;	/* generic disk */
	struct request_queue	*zvo_queue;	/* request queue */
	dataset_kstats_t	zvo_kstat;	/* zvol kstats */
	dev_t			zvo_dev;	/* device id */
};

taskq_t *zvol_taskq;
static struct ida zvol_ida;

typedef struct zv_request {
	zvol_state_t	*zv;
	struct bio	*bio;
	zfs_locked_range_t	*lr;
} zv_request_t;

/*
 * Given a path, return TRUE if path is a ZVOL.
 */
static boolean_t
zvol_is_zvol_impl(const char *device)
{
	struct block_device *bdev;
	unsigned int major;

	bdev = vdev_lookup_bdev(device);
	if (IS_ERR(bdev))
		return (B_FALSE);

	major = MAJOR(bdev->bd_dev);
	bdput(bdev);

	if (major == zvol_major)
		return (B_TRUE);

	return (B_FALSE);
}

static void
uio_from_bio(uio_t *uio, struct bio *bio)
{
	uio->uio_bvec = &bio->bi_io_vec[BIO_BI_IDX(bio)];
	uio->uio_iovcnt = bio->bi_vcnt - BIO_BI_IDX(bio);
	uio->uio_loffset = BIO_BI_SECTOR(bio) << 9;
	uio->uio_segflg = UIO_BVEC;
	uio->uio_limit = MAXOFFSET_T;
	uio->uio_resid = BIO_BI_SIZE(bio);
	uio->uio_skip = BIO_BI_SKIP(bio);
}

static void
zvol_write(void *arg)
{
	int error = 0;

	zv_request_t *zvr = arg;
	struct bio *bio = zvr->bio;
	uio_t uio = { { 0 }, 0 };
	uio_from_bio(&uio, bio);

	zvol_state_t *zv = zvr->zv;
	ASSERT(zv && zv->zv_open_count > 0);
	ASSERT(zv->zv_zilog != NULL);

	ssize_t start_resid = uio.uio_resid;
	unsigned long start_jif = jiffies;
	blk_generic_start_io_acct(zv->zv_zso->zvo_queue, WRITE,
	    bio_sectors(bio), &zv->zv_zso->zvo_disk->part0);

	boolean_t sync =
	    bio_is_fua(bio) || zv->zv_objset->os_sync == ZFS_SYNC_ALWAYS;

	uint64_t volsize = zv->zv_volsize;
	while (uio.uio_resid > 0 && uio.uio_loffset < volsize) {
		uint64_t bytes = MIN(uio.uio_resid, DMU_MAX_ACCESS >> 1);
		uint64_t off = uio.uio_loffset;
		dmu_tx_t *tx = dmu_tx_create(zv->zv_objset);

		if (bytes > volsize - off)	/* don't write past the end */
			bytes = volsize - off;

		dmu_tx_hold_write(tx, ZVOL_OBJ, off, bytes);

		/* This will only fail for ENOSPC */
		error = dmu_tx_assign(tx, TXG_WAIT);
		if (error) {
			dmu_tx_abort(tx);
			break;
		}
		error = dmu_write_uio_dnode(zv->zv_dn, &uio, bytes, tx);
		if (error == 0) {
			zvol_log_write(zv, tx, off, bytes, sync);
		}
		dmu_tx_commit(tx);

		if (error)
			break;
	}
	zfs_rangelock_exit(zvr->lr);

	int64_t nwritten = start_resid - uio.uio_resid;
	dataset_kstats_update_write_kstats(&zv->zv_zso->zvo_kstat, nwritten);
	task_io_account_write(nwritten);

	if (sync)
		zil_commit(zv->zv_zilog, ZVOL_OBJ);

	rw_exit(&zv->zv_suspend_lock);
	blk_generic_end_io_acct(zv->zv_zso->zvo_queue,
	    WRITE, &zv->zv_zso->zvo_disk->part0, start_jif);
	BIO_END_IO(bio, -error);
	kmem_free(zvr, sizeof (zv_request_t));
}

static void
zvol_discard(void *arg)
{
	zv_request_t *zvr = arg;
	struct bio *bio = zvr->bio;
	zvol_state_t *zv = zvr->zv;
	uint64_t start = BIO_BI_SECTOR(bio) << 9;
	uint64_t size = BIO_BI_SIZE(bio);
	uint64_t end = start + size;
	boolean_t sync;
	int error = 0;
	dmu_tx_t *tx;
	unsigned long start_jif;

	ASSERT(zv && zv->zv_open_count > 0);
	ASSERT(zv->zv_zilog != NULL);

	start_jif = jiffies;
	blk_generic_start_io_acct(zv->zv_zso->zvo_queue, WRITE,
	    bio_sectors(bio), &zv->zv_zso->zvo_disk->part0);

	sync = bio_is_fua(bio) || zv->zv_objset->os_sync == ZFS_SYNC_ALWAYS;

	if (end > zv->zv_volsize) {
		error = SET_ERROR(EIO);
		goto unlock;
	}

	/*
	 * Align the request to volume block boundaries when a secure erase is
	 * not required.  This will prevent dnode_free_range() from zeroing out
	 * the unaligned parts which is slow (read-modify-write) and useless
	 * since we are not freeing any space by doing so.
	 */
	if (!bio_is_secure_erase(bio)) {
		start = P2ROUNDUP(start, zv->zv_volblocksize);
		end = P2ALIGN(end, zv->zv_volblocksize);
		size = end - start;
	}

	if (start >= end)
		goto unlock;

	tx = dmu_tx_create(zv->zv_objset);
	dmu_tx_mark_netfree(tx);
	error = dmu_tx_assign(tx, TXG_WAIT);
	if (error != 0) {
		dmu_tx_abort(tx);
	} else {
		zvol_log_truncate(zv, tx, start, size, B_TRUE);
		dmu_tx_commit(tx);
		error = dmu_free_long_range(zv->zv_objset,
		    ZVOL_OBJ, start, size);
	}
unlock:
	zfs_rangelock_exit(zvr->lr);

	if (error == 0 && sync)
		zil_commit(zv->zv_zilog, ZVOL_OBJ);

	rw_exit(&zv->zv_suspend_lock);
	blk_generic_end_io_acct(zv->zv_zso->zvo_queue, WRITE,
	    &zv->zv_zso->zvo_disk->part0, start_jif);
	BIO_END_IO(bio, -error);
	kmem_free(zvr, sizeof (zv_request_t));
}

static void
zvol_read(void *arg)
{
	int error = 0;

	zv_request_t *zvr = arg;
	struct bio *bio = zvr->bio;
	uio_t uio = { { 0 }, 0 };
	uio_from_bio(&uio, bio);

	zvol_state_t *zv = zvr->zv;
	ASSERT(zv && zv->zv_open_count > 0);

	ssize_t start_resid = uio.uio_resid;
	unsigned long start_jif = jiffies;
	blk_generic_start_io_acct(zv->zv_zso->zvo_queue, READ, bio_sectors(bio),
	    &zv->zv_zso->zvo_disk->part0);

	uint64_t volsize = zv->zv_volsize;
	while (uio.uio_resid > 0 && uio.uio_loffset < volsize) {
		uint64_t bytes = MIN(uio.uio_resid, DMU_MAX_ACCESS >> 1);

		/* don't read past the end */
		if (bytes > volsize - uio.uio_loffset)
			bytes = volsize - uio.uio_loffset;

		error = dmu_read_uio_dnode(zv->zv_dn, &uio, bytes);
		if (error) {
			/* convert checksum errors into IO errors */
			if (error == ECKSUM)
				error = SET_ERROR(EIO);
			break;
		}
	}
	zfs_rangelock_exit(zvr->lr);

	int64_t nread = start_resid - uio.uio_resid;
	dataset_kstats_update_read_kstats(&zv->zv_zso->zvo_kstat, nread);
	task_io_account_read(nread);

	rw_exit(&zv->zv_suspend_lock);
	blk_generic_end_io_acct(zv->zv_zso->zvo_queue, READ,
	    &zv->zv_zso->zvo_disk->part0, start_jif);
	BIO_END_IO(bio, -error);
	kmem_free(zvr, sizeof (zv_request_t));
}

static MAKE_REQUEST_FN_RET
zvol_request(struct request_queue *q, struct bio *bio)
{
	zvol_state_t *zv = q->queuedata;
	fstrans_cookie_t cookie = spl_fstrans_mark();
	uint64_t offset = BIO_BI_SECTOR(bio) << 9;
	uint64_t size = BIO_BI_SIZE(bio);
	int rw = bio_data_dir(bio);
	zv_request_t *zvr;

	if (bio_has_data(bio) && offset + size > zv->zv_volsize) {
		printk(KERN_INFO
		    "%s: bad access: offset=%llu, size=%lu\n",
		    zv->zv_zso->zvo_disk->disk_name,
		    (long long unsigned)offset,
		    (long unsigned)size);

		BIO_END_IO(bio, -SET_ERROR(EIO));
		goto out;
	}

	if (rw == WRITE) {
		boolean_t need_sync = B_FALSE;

		if (unlikely(zv->zv_flags & ZVOL_RDONLY)) {
			BIO_END_IO(bio, -SET_ERROR(EROFS));
			goto out;
		}

		/*
		 * To be released in the I/O function. See the comment on
		 * rangelock_enter() below.
		 */
		rw_enter(&zv->zv_suspend_lock, RW_READER);

		/*
		 * Open a ZIL if this is the first time we have written to this
		 * zvol. We protect zv->zv_zilog with zv_suspend_lock rather
		 * than zv_state_lock so that we don't need to acquire an
		 * additional lock in this path.
		 */
		if (zv->zv_zilog == NULL) {
			rw_exit(&zv->zv_suspend_lock);
			rw_enter(&zv->zv_suspend_lock, RW_WRITER);
			if (zv->zv_zilog == NULL) {
				zv->zv_zilog = zil_open(zv->zv_objset,
				    zvol_get_data);
				zv->zv_flags |= ZVOL_WRITTEN_TO;
			}
			rw_downgrade(&zv->zv_suspend_lock);
		}

		/* bio marked as FLUSH need to flush before write */
		if (bio_is_flush(bio))
			zil_commit(zv->zv_zilog, ZVOL_OBJ);

		/* Some requests are just for flush and nothing else. */
		if (size == 0) {
			rw_exit(&zv->zv_suspend_lock);
			BIO_END_IO(bio, 0);
			goto out;
		}

		zvr = kmem_alloc(sizeof (zv_request_t), KM_SLEEP);
		zvr->zv = zv;
		zvr->bio = bio;

		/*
		 * To be released in the I/O function. Since the I/O functions
		 * are asynchronous, we take it here synchronously to make
		 * sure overlapped I/Os are properly ordered.
		 */
		zvr->lr = zfs_rangelock_enter(&zv->zv_rangelock, offset, size,
		    RL_WRITER);
		/*
		 * Sync writes and discards execute zil_commit() which may need
		 * to take a RL_READER lock on the whole block being modified
		 * via its zillog->zl_get_data(): to avoid circular dependency
		 * issues with taskq threads execute these requests
		 * synchronously here in zvol_request().
		 */
		need_sync = bio_is_fua(bio) ||
		    zv->zv_objset->os_sync == ZFS_SYNC_ALWAYS;
		if (bio_is_discard(bio) || bio_is_secure_erase(bio)) {
			if (zvol_request_sync || need_sync ||
			    taskq_dispatch(zvol_taskq, zvol_discard, zvr,
			    TQ_SLEEP) == TASKQID_INVALID)
				zvol_discard(zvr);
		} else {
			if (zvol_request_sync || need_sync ||
			    taskq_dispatch(zvol_taskq, zvol_write, zvr,
			    TQ_SLEEP) == TASKQID_INVALID)
				zvol_write(zvr);
		}
	} else {
		/*
		 * The SCST driver, and possibly others, may issue READ I/Os
		 * with a length of zero bytes.  These empty I/Os contain no
		 * data and require no additional handling.
		 */
		if (size == 0) {
			BIO_END_IO(bio, 0);
			goto out;
		}

		zvr = kmem_alloc(sizeof (zv_request_t), KM_SLEEP);
		zvr->zv = zv;
		zvr->bio = bio;

		rw_enter(&zv->zv_suspend_lock, RW_READER);

		zvr->lr = zfs_rangelock_enter(&zv->zv_rangelock, offset, size,
		    RL_READER);
		if (zvol_request_sync || taskq_dispatch(zvol_taskq,
		    zvol_read, zvr, TQ_SLEEP) == TASKQID_INVALID)
			zvol_read(zvr);
	}

out:
	spl_fstrans_unmark(cookie);
#if defined(HAVE_MAKE_REQUEST_FN_RET_QC)
	return (BLK_QC_T_NONE);
#endif
}

static int
zvol_open(struct block_device *bdev, fmode_t flag)
{
	zvol_state_t *zv;
	int error = 0;
	boolean_t drop_suspend = B_TRUE;

	rw_enter(&zvol_state_lock, RW_READER);
	/*
	 * Obtain a copy of private_data under the zvol_state_lock to make
	 * sure that either the result of zvol free code path setting
	 * bdev->bd_disk->private_data to NULL is observed, or zvol_free()
	 * is not called on this zv because of the positive zv_open_count.
	 */
	zv = bdev->bd_disk->private_data;
	if (zv == NULL) {
		rw_exit(&zvol_state_lock);
		return (SET_ERROR(-ENXIO));
	}

	mutex_enter(&zv->zv_state_lock);
	/*
	 * make sure zvol is not suspended during first open
	 * (hold zv_suspend_lock) and respect proper lock acquisition
	 * ordering - zv_suspend_lock before zv_state_lock
	 */
	if (zv->zv_open_count == 0) {
		if (!rw_tryenter(&zv->zv_suspend_lock, RW_READER)) {
			mutex_exit(&zv->zv_state_lock);
			rw_enter(&zv->zv_suspend_lock, RW_READER);
			mutex_enter(&zv->zv_state_lock);
			/* check to see if zv_suspend_lock is needed */
			if (zv->zv_open_count != 0) {
				rw_exit(&zv->zv_suspend_lock);
				drop_suspend = B_FALSE;
			}
		}
	} else {
		drop_suspend = B_FALSE;
	}
	rw_exit(&zvol_state_lock);

	ASSERT(MUTEX_HELD(&zv->zv_state_lock));
	ASSERT(zv->zv_open_count != 0 || RW_READ_HELD(&zv->zv_suspend_lock));

	if (zv->zv_open_count == 0) {
		error = -zvol_first_open(zv, !(flag & FMODE_WRITE));
		if (error)
			goto out_mutex;
	}

	if ((flag & FMODE_WRITE) && (zv->zv_flags & ZVOL_RDONLY)) {
		error = -EROFS;
		goto out_open_count;
	}

	zv->zv_open_count++;

	mutex_exit(&zv->zv_state_lock);
	if (drop_suspend)
		rw_exit(&zv->zv_suspend_lock);

	check_disk_change(bdev);

	return (0);

out_open_count:
	if (zv->zv_open_count == 0)
		zvol_last_close(zv);

out_mutex:
	mutex_exit(&zv->zv_state_lock);
	if (drop_suspend)
		rw_exit(&zv->zv_suspend_lock);
	if (error == -EINTR) {
		error = -ERESTARTSYS;
		schedule();
	}
	return (SET_ERROR(error));
}

static void
zvol_release(struct gendisk *disk, fmode_t mode)
{
	zvol_state_t *zv;
	boolean_t drop_suspend = B_TRUE;

	rw_enter(&zvol_state_lock, RW_READER);
	zv = disk->private_data;

	mutex_enter(&zv->zv_state_lock);
	ASSERT(zv->zv_open_count > 0);
	/*
	 * make sure zvol is not suspended during last close
	 * (hold zv_suspend_lock) and respect proper lock acquisition
	 * ordering - zv_suspend_lock before zv_state_lock
	 */
	if (zv->zv_open_count == 1) {
		if (!rw_tryenter(&zv->zv_suspend_lock, RW_READER)) {
			mutex_exit(&zv->zv_state_lock);
			rw_enter(&zv->zv_suspend_lock, RW_READER);
			mutex_enter(&zv->zv_state_lock);
			/* check to see if zv_suspend_lock is needed */
			if (zv->zv_open_count != 1) {
				rw_exit(&zv->zv_suspend_lock);
				drop_suspend = B_FALSE;
			}
		}
	} else {
		drop_suspend = B_FALSE;
	}
	rw_exit(&zvol_state_lock);

	ASSERT(MUTEX_HELD(&zv->zv_state_lock));
	ASSERT(zv->zv_open_count != 1 || RW_READ_HELD(&zv->zv_suspend_lock));

	zv->zv_open_count--;
	if (zv->zv_open_count == 0)
		zvol_last_close(zv);

	mutex_exit(&zv->zv_state_lock);

	if (drop_suspend)
		rw_exit(&zv->zv_suspend_lock);
}

static int
zvol_ioctl(struct block_device *bdev, fmode_t mode,
    unsigned int cmd, unsigned long arg)
{
	zvol_state_t *zv = bdev->bd_disk->private_data;
	int error = 0;

	ASSERT3U(zv->zv_open_count, >, 0);

	switch (cmd) {
	case BLKFLSBUF:
		fsync_bdev(bdev);
		invalidate_bdev(bdev);
		rw_enter(&zv->zv_suspend_lock, RW_READER);

		if (!(zv->zv_flags & ZVOL_RDONLY))
			txg_wait_synced(dmu_objset_pool(zv->zv_objset), 0);

		rw_exit(&zv->zv_suspend_lock);
		break;

	case BLKZNAME:
		mutex_enter(&zv->zv_state_lock);
		error = copy_to_user((void *)arg, zv->zv_name, MAXNAMELEN);
		mutex_exit(&zv->zv_state_lock);
		break;

	default:
		error = -ENOTTY;
		break;
	}

	return (SET_ERROR(error));
}

#ifdef CONFIG_COMPAT
static int
zvol_compat_ioctl(struct block_device *bdev, fmode_t mode,
    unsigned cmd, unsigned long arg)
{
	return (zvol_ioctl(bdev, mode, cmd, arg));
}
#else
#define	zvol_compat_ioctl	NULL
#endif

static unsigned int
zvol_check_events(struct gendisk *disk, unsigned int clearing)
{
	unsigned int mask = 0;

	rw_enter(&zvol_state_lock, RW_READER);

	zvol_state_t *zv = disk->private_data;
	if (zv != NULL) {
		mutex_enter(&zv->zv_state_lock);
		mask = zv->zv_changed ? DISK_EVENT_MEDIA_CHANGE : 0;
		zv->zv_changed = 0;
		mutex_exit(&zv->zv_state_lock);
	}

	rw_exit(&zvol_state_lock);

	return (mask);
}

static int
zvol_revalidate_disk(struct gendisk *disk)
{
	rw_enter(&zvol_state_lock, RW_READER);

	zvol_state_t *zv = disk->private_data;
	if (zv != NULL) {
		mutex_enter(&zv->zv_state_lock);
		set_capacity(zv->zv_zso->zvo_disk,
		    zv->zv_volsize >> SECTOR_BITS);
		mutex_exit(&zv->zv_state_lock);
	}

	rw_exit(&zvol_state_lock);

	return (0);
}

int
zvol_update_volsize(zvol_state_t *zv, uint64_t volsize)
{

	revalidate_disk(zv->zv_zso->zvo_disk);
	return (0);
}

static void
zvol_clear_private(zvol_state_t *zv)
{
	/*
	 * Cleared while holding zvol_state_lock as a writer
	 * which will prevent zvol_open() from opening it.
	 */
	zv->zv_zso->zvo_disk->private_data = NULL;
}

/*
 * Provide a simple virtual geometry for legacy compatibility.  For devices
 * smaller than 1 MiB a small head and sector count is used to allow very
 * tiny devices.  For devices over 1 Mib a standard head and sector count
 * is used to keep the cylinders count reasonable.
 */
static int
zvol_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	zvol_state_t *zv = bdev->bd_disk->private_data;
	sector_t sectors;

	ASSERT3U(zv->zv_open_count, >, 0);

	sectors = get_capacity(zv->zv_zso->zvo_disk);

	if (sectors > 2048) {
		geo->heads = 16;
		geo->sectors = 63;
	} else {
		geo->heads = 2;
		geo->sectors = 4;
	}

	geo->start = 0;
	geo->cylinders = sectors / (geo->heads * geo->sectors);

	return (0);
}

/*
 * Find a zvol_state_t given the full major+minor dev_t. If found,
 * return with zv_state_lock taken, otherwise, return (NULL) without
 * taking zv_state_lock.
 */
static zvol_state_t *
zvol_find_by_dev(dev_t dev)
{
	zvol_state_t *zv;

	rw_enter(&zvol_state_lock, RW_READER);
	for (zv = list_head(&zvol_state_list); zv != NULL;
	    zv = list_next(&zvol_state_list, zv)) {
		mutex_enter(&zv->zv_state_lock);
		if (zv->zv_zso->zvo_dev == dev) {
			rw_exit(&zvol_state_lock);
			return (zv);
		}
		mutex_exit(&zv->zv_state_lock);
	}
	rw_exit(&zvol_state_lock);

	return (NULL);
}

void
zvol_validate_dev(zvol_state_t *zv)
{
	ASSERT3U(MINOR(zv->zv_zso->zvo_dev) & ZVOL_MINOR_MASK, ==, 0);
}

static struct kobject *
zvol_probe(dev_t dev, int *part, void *arg)
{
	zvol_state_t *zv;
	struct kobject *kobj;

	zv = zvol_find_by_dev(dev);
	kobj = zv ? get_disk_and_module(zv->zv_zso->zvo_disk) : NULL;
	ASSERT(zv == NULL || MUTEX_HELD(&zv->zv_state_lock));
	if (zv)
		mutex_exit(&zv->zv_state_lock);

	return (kobj);
}

static struct block_device_operations zvol_ops = {
	.open			= zvol_open,
	.release		= zvol_release,
	.ioctl			= zvol_ioctl,
	.compat_ioctl		= zvol_compat_ioctl,
	.check_events		= zvol_check_events,
	.revalidate_disk	= zvol_revalidate_disk,
	.getgeo			= zvol_getgeo,
	.owner			= THIS_MODULE,
};

/*
 * Allocate memory for a new zvol_state_t and setup the required
 * request queue and generic disk structures for the block device.
 */
static zvol_state_t *
zvol_alloc(dev_t dev, const char *name)
{
	zvol_state_t *zv;
	uint64_t volmode;

	if (dsl_prop_get_integer(name, "volmode", &volmode, NULL) != 0)
		return (NULL);

	if (volmode == ZFS_VOLMODE_DEFAULT)
		volmode = zvol_volmode;

	if (volmode == ZFS_VOLMODE_NONE)
		return (NULL);

	zv = kmem_zalloc(sizeof (zvol_state_t), KM_SLEEP);
	zv->zv_zso = kmem_zalloc(sizeof (struct zvol_state_os), KM_SLEEP);

	list_link_init(&zv->zv_next);

	mutex_init(&zv->zv_state_lock, NULL, MUTEX_DEFAULT, NULL);

	zv->zv_zso->zvo_queue = blk_alloc_queue(GFP_ATOMIC);
	if (zv->zv_zso->zvo_queue == NULL)
		goto out_kmem;

	blk_queue_make_request(zv->zv_zso->zvo_queue, zvol_request);
	blk_queue_set_write_cache(zv->zv_zso->zvo_queue, B_TRUE, B_TRUE);

	/* Limit read-ahead to a single page to prevent over-prefetching. */
	blk_queue_set_read_ahead(zv->zv_zso->zvo_queue, 1);

	/* Disable write merging in favor of the ZIO pipeline. */
	blk_queue_flag_set(QUEUE_FLAG_NOMERGES, zv->zv_zso->zvo_queue);

	zv->zv_zso->zvo_disk = alloc_disk(ZVOL_MINORS);
	if (zv->zv_zso->zvo_disk == NULL)
		goto out_queue;

	zv->zv_zso->zvo_queue->queuedata = zv;
	zv->zv_zso->zvo_dev = dev;
	zv->zv_open_count = 0;
	strlcpy(zv->zv_name, name, MAXNAMELEN);

	zfs_rangelock_init(&zv->zv_rangelock, NULL, NULL);
	rw_init(&zv->zv_suspend_lock, NULL, RW_DEFAULT, NULL);

	zv->zv_zso->zvo_disk->major = zvol_major;
	zv->zv_zso->zvo_disk->events = DISK_EVENT_MEDIA_CHANGE;

	if (volmode == ZFS_VOLMODE_DEV) {
		/*
		 * ZFS_VOLMODE_DEV disable partitioning on ZVOL devices: set
		 * gendisk->minors = 1 as noted in include/linux/genhd.h.
		 * Also disable extended partition numbers (GENHD_FL_EXT_DEVT)
		 * and suppresses partition scanning (GENHD_FL_NO_PART_SCAN)
		 * setting gendisk->flags accordingly.
		 */
		zv->zv_zso->zvo_disk->minors = 1;
#if defined(GENHD_FL_EXT_DEVT)
		zv->zv_zso->zvo_disk->flags &= ~GENHD_FL_EXT_DEVT;
#endif
#if defined(GENHD_FL_NO_PART_SCAN)
		zv->zv_zso->zvo_disk->flags |= GENHD_FL_NO_PART_SCAN;
#endif
	}
	zv->zv_zso->zvo_disk->first_minor = (dev & MINORMASK);
	zv->zv_zso->zvo_disk->fops = &zvol_ops;
	zv->zv_zso->zvo_disk->private_data = zv;
	zv->zv_zso->zvo_disk->queue = zv->zv_zso->zvo_queue;
	snprintf(zv->zv_zso->zvo_disk->disk_name, DISK_NAME_LEN, "%s%d",
	    ZVOL_DEV_NAME, (dev & MINORMASK));

	return (zv);

out_queue:
	blk_cleanup_queue(zv->zv_zso->zvo_queue);
out_kmem:
	kmem_free(zv->zv_zso, sizeof (struct zvol_state_os));
	kmem_free(zv, sizeof (zvol_state_t));
	return (NULL);
}

/*
 * Cleanup then free a zvol_state_t which was created by zvol_alloc().
 * At this time, the structure is not opened by anyone, is taken off
 * the zvol_state_list, and has its private data set to NULL.
 * The zvol_state_lock is dropped.
 *
 * This function may take many milliseconds to complete (e.g. we've seen
 * it take over 256ms), due to the calls to "blk_cleanup_queue" and
 * "del_gendisk". Thus, consumers need to be careful to account for this
 * latency when calling this function.
 */
static void
zvol_free(zvol_state_t *zv)
{

	ASSERT(!RW_LOCK_HELD(&zv->zv_suspend_lock));
	ASSERT(!MUTEX_HELD(&zv->zv_state_lock));
	ASSERT(zv->zv_open_count == 0);
	ASSERT(zv->zv_zso->zvo_disk->private_data == NULL);

	rw_destroy(&zv->zv_suspend_lock);
	zfs_rangelock_fini(&zv->zv_rangelock);

	del_gendisk(zv->zv_zso->zvo_disk);
	blk_cleanup_queue(zv->zv_zso->zvo_queue);
	put_disk(zv->zv_zso->zvo_disk);

	ida_simple_remove(&zvol_ida,
	    MINOR(zv->zv_zso->zvo_dev) >> ZVOL_MINOR_BITS);

	mutex_destroy(&zv->zv_state_lock);
	dataset_kstats_destroy(&zv->zv_zso->zvo_kstat);

	kmem_free(zv->zv_zso, sizeof (struct zvol_state_os));
	kmem_free(zv, sizeof (zvol_state_t));
}

/*
 * Create a block device minor node and setup the linkage between it
 * and the specified volume.  Once this function returns the block
 * device is live and ready for use.
 */
static int
zvol_os_create_minor(const char *name)
{
	zvol_state_t *zv;
	objset_t *os;
	dmu_object_info_t *doi;
	uint64_t volsize;
	uint64_t len;
	unsigned minor = 0;
	int error = 0;
	int idx;
	uint64_t hash = zvol_name_hash(name);

	if (zvol_inhibit_dev)
		return (0);

	idx = ida_simple_get(&zvol_ida, 0, 0, kmem_flags_convert(KM_SLEEP));
	if (idx < 0)
		return (SET_ERROR(-idx));
	minor = idx << ZVOL_MINOR_BITS;

	zv = zvol_find_by_name_hash(name, hash, RW_NONE);
	if (zv) {
		ASSERT(MUTEX_HELD(&zv->zv_state_lock));
		mutex_exit(&zv->zv_state_lock);
		ida_simple_remove(&zvol_ida, idx);
		return (SET_ERROR(EEXIST));
	}

	doi = kmem_alloc(sizeof (dmu_object_info_t), KM_SLEEP);

	error = dmu_objset_own(name, DMU_OST_ZVOL, B_TRUE, B_TRUE, FTAG, &os);
	if (error)
		goto out_doi;

	error = dmu_object_info(os, ZVOL_OBJ, doi);
	if (error)
		goto out_dmu_objset_disown;

	error = zap_lookup(os, ZVOL_ZAP_OBJ, "size", 8, 1, &volsize);
	if (error)
		goto out_dmu_objset_disown;

	zv = zvol_alloc(MKDEV(zvol_major, minor), name);
	if (zv == NULL) {
		error = SET_ERROR(EAGAIN);
		goto out_dmu_objset_disown;
	}
	zv->zv_hash = hash;

	if (dmu_objset_is_snapshot(os))
		zv->zv_flags |= ZVOL_RDONLY;

	zv->zv_volblocksize = doi->doi_data_block_size;
	zv->zv_volsize = volsize;
	zv->zv_objset = os;

	set_capacity(zv->zv_zso->zvo_disk, zv->zv_volsize >> 9);

	blk_queue_max_hw_sectors(zv->zv_zso->zvo_queue,
	    (DMU_MAX_ACCESS / 4) >> 9);
	blk_queue_max_segments(zv->zv_zso->zvo_queue, UINT16_MAX);
	blk_queue_max_segment_size(zv->zv_zso->zvo_queue, UINT_MAX);
	blk_queue_physical_block_size(zv->zv_zso->zvo_queue,
	    zv->zv_volblocksize);
	blk_queue_io_opt(zv->zv_zso->zvo_queue, zv->zv_volblocksize);
	blk_queue_max_discard_sectors(zv->zv_zso->zvo_queue,
	    (zvol_max_discard_blocks * zv->zv_volblocksize) >> 9);
	blk_queue_discard_granularity(zv->zv_zso->zvo_queue,
	    zv->zv_volblocksize);
	blk_queue_flag_set(QUEUE_FLAG_DISCARD, zv->zv_zso->zvo_queue);
#ifdef QUEUE_FLAG_NONROT
	blk_queue_flag_set(QUEUE_FLAG_NONROT, zv->zv_zso->zvo_queue);
#endif
#ifdef QUEUE_FLAG_ADD_RANDOM
	blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, zv->zv_zso->zvo_queue);
#endif
	/* This flag was introduced in kernel version 4.12. */
#ifdef QUEUE_FLAG_SCSI_PASSTHROUGH
	blk_queue_flag_set(QUEUE_FLAG_SCSI_PASSTHROUGH, zv->zv_zso->zvo_queue);
#endif

	if (spa_writeable(dmu_objset_spa(os))) {
		if (zil_replay_disable)
			zil_destroy(dmu_objset_zil(os), B_FALSE);
		else
			zil_replay(os, zv, zvol_replay_vector);
	}
	ASSERT3P(zv->zv_zso->zvo_kstat.dk_kstats, ==, NULL);
	dataset_kstats_create(&zv->zv_zso->zvo_kstat, zv->zv_objset);

	/*
	 * When udev detects the addition of the device it will immediately
	 * invoke blkid(8) to determine the type of content on the device.
	 * Prefetching the blocks commonly scanned by blkid(8) will speed
	 * up this process.
	 */
	len = MIN(MAX(zvol_prefetch_bytes, 0), SPA_MAXBLOCKSIZE);
	if (len > 0) {
		dmu_prefetch(os, ZVOL_OBJ, 0, 0, len, ZIO_PRIORITY_SYNC_READ);
		dmu_prefetch(os, ZVOL_OBJ, 0, volsize - len, len,
		    ZIO_PRIORITY_SYNC_READ);
	}

	zv->zv_objset = NULL;
out_dmu_objset_disown:
	dmu_objset_disown(os, B_TRUE, FTAG);
out_doi:
	kmem_free(doi, sizeof (dmu_object_info_t));

	/*
	 * Keep in mind that once add_disk() is called, the zvol is
	 * announced to the world, and zvol_open()/zvol_release() can
	 * be called at any time. Incidentally, add_disk() itself calls
	 * zvol_open()->zvol_first_open() and zvol_release()->zvol_last_close()
	 * directly as well.
	 */
	if (error == 0) {
		rw_enter(&zvol_state_lock, RW_WRITER);
		zvol_insert(zv);
		rw_exit(&zvol_state_lock);
		add_disk(zv->zv_zso->zvo_disk);
	} else {
		ida_simple_remove(&zvol_ida, idx);
	}

	return (error);
}

static void
zvol_rename_minor(zvol_state_t *zv, const char *newname)
{
	int readonly = get_disk_ro(zv->zv_zso->zvo_disk);

	ASSERT(RW_LOCK_HELD(&zvol_state_lock));
	ASSERT(MUTEX_HELD(&zv->zv_state_lock));

	strlcpy(zv->zv_name, newname, sizeof (zv->zv_name));

	/* move to new hashtable entry  */
	zv->zv_hash = zvol_name_hash(zv->zv_name);
	hlist_del(&zv->zv_hlink);
	hlist_add_head(&zv->zv_hlink, ZVOL_HT_HEAD(zv->zv_hash));

	/*
	 * The block device's read-only state is briefly changed causing
	 * a KOBJ_CHANGE uevent to be issued.  This ensures udev detects
	 * the name change and fixes the symlinks.  This does not change
	 * ZVOL_RDONLY in zv->zv_flags so the actual read-only state never
	 * changes.  This would normally be done using kobject_uevent() but
	 * that is a GPL-only symbol which is why we need this workaround.
	 */
	set_disk_ro(zv->zv_zso->zvo_disk, !readonly);
	set_disk_ro(zv->zv_zso->zvo_disk, readonly);
}

static void
zvol_set_disk_ro_impl(zvol_state_t *zv, int flags)
{

	set_disk_ro(zv->zv_zso->zvo_disk, flags);
}

static void
zvol_set_capacity_impl(zvol_state_t *zv, uint64_t capacity)
{

	set_capacity(zv->zv_zso->zvo_disk, capacity);
}

const static zvol_platform_ops_t zvol_linux_ops = {
	.zv_free = zvol_free,
	.zv_rename_minor = zvol_rename_minor,
	.zv_create_minor = zvol_os_create_minor,
	.zv_update_volsize = zvol_update_volsize,
	.zv_clear_private = zvol_clear_private,
	.zv_is_zvol = zvol_is_zvol_impl,
	.zv_set_disk_ro = zvol_set_disk_ro_impl,
	.zv_set_capacity = zvol_set_capacity_impl,
};

int
zvol_init(void)
{
	int error;
	int threads = MIN(MAX(zvol_threads, 1), 1024);

	error = register_blkdev(zvol_major, ZVOL_DRIVER);
	if (error) {
		printk(KERN_INFO "ZFS: register_blkdev() failed %d\n", error);
		return (error);
	}
	zvol_taskq = taskq_create(ZVOL_DRIVER, threads, maxclsyspri,
	    threads * 2, INT_MAX, TASKQ_PREPOPULATE | TASKQ_DYNAMIC);
	if (zvol_taskq == NULL) {
		unregister_blkdev(zvol_major, ZVOL_DRIVER);
		return (-ENOMEM);
	}
	zvol_init_impl();
	blk_register_region(MKDEV(zvol_major, 0), 1UL << MINORBITS,
	    THIS_MODULE, zvol_probe, NULL, NULL);

	ida_init(&zvol_ida);
	zvol_register_ops(&zvol_linux_ops);
	return (0);
}

void
zvol_fini(void)
{
	zvol_fini_impl();
	blk_unregister_region(MKDEV(zvol_major, 0), 1UL << MINORBITS);
	unregister_blkdev(zvol_major, ZVOL_DRIVER);
	taskq_destroy(zvol_taskq);
	ida_destroy(&zvol_ida);
}

/* BEGIN CSTYLED */
module_param(zvol_inhibit_dev, uint, 0644);
MODULE_PARM_DESC(zvol_inhibit_dev, "Do not create zvol device nodes");

module_param(zvol_major, uint, 0444);
MODULE_PARM_DESC(zvol_major, "Major number for zvol device");

module_param(zvol_threads, uint, 0444);
MODULE_PARM_DESC(zvol_threads, "Max number of threads to handle I/O requests");

module_param(zvol_request_sync, uint, 0644);
MODULE_PARM_DESC(zvol_request_sync, "Synchronously handle bio requests");

module_param(zvol_max_discard_blocks, ulong, 0444);
MODULE_PARM_DESC(zvol_max_discard_blocks, "Max number of blocks to discard");

module_param(zvol_prefetch_bytes, uint, 0644);
MODULE_PARM_DESC(zvol_prefetch_bytes, "Prefetch N bytes at zvol start+end");

module_param(zvol_volmode, uint, 0644);
MODULE_PARM_DESC(zvol_volmode, "Default volmode property value");
/* END CSTYLED */