aboutsummaryrefslogtreecommitdiff
path: root/drivers/md/dm.c
blob: 846614e676c6bedb678b81ea2b4ac9e0767ff26d (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
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
/*
 * Copyright (C) 2001, 2002 Sistina Software (UK) Limited.
 * Copyright (C) 2004-2006 Red Hat, Inc. All rights reserved.
 *
 * This file is released under the GPL.
 */

#include "dm.h"
#include "dm-bio-list.h"

#include <linux/init.h>
#include <linux/module.h>
#include <linux/mutex.h>
#include <linux/moduleparam.h>
#include <linux/blkpg.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/mempool.h>
#include <linux/slab.h>
#include <linux/idr.h>
#include <linux/hdreg.h>
#include <linux/blktrace_api.h>
#include <linux/smp_lock.h>

#define DM_MSG_PREFIX "core"

static const char *_name = DM_NAME;

static unsigned int major = 0;
static unsigned int _major = 0;

static DEFINE_SPINLOCK(_minor_lock);
/*
 * One of these is allocated per bio.
 */
struct dm_io {
	struct mapped_device *md;
	int error;
	struct bio *bio;
	atomic_t io_count;
	unsigned long start_time;
};

/*
 * One of these is allocated per target within a bio.  Hopefully
 * this will be simplified out one day.
 */
struct dm_target_io {
	struct dm_io *io;
	struct dm_target *ti;
	union map_info info;
};

union map_info *dm_get_mapinfo(struct bio *bio)
{
	if (bio && bio->bi_private)
		return &((struct dm_target_io *)bio->bi_private)->info;
	return NULL;
}

#define MINOR_ALLOCED ((void *)-1)

/*
 * Bits for the md->flags field.
 */
#define DMF_BLOCK_IO 0
#define DMF_SUSPENDED 1
#define DMF_FROZEN 2
#define DMF_FREEING 3
#define DMF_DELETING 4
#define DMF_NOFLUSH_SUSPENDING 5

struct mapped_device {
	struct rw_semaphore io_lock;
	struct semaphore suspend_lock;
	spinlock_t pushback_lock;
	rwlock_t map_lock;
	atomic_t holders;
	atomic_t open_count;

	unsigned long flags;

	request_queue_t *queue;
	struct gendisk *disk;
	char name[16];

	void *interface_ptr;

	/*
	 * A list of ios that arrived while we were suspended.
	 */
	atomic_t pending;
	wait_queue_head_t wait;
	struct bio_list deferred;
	struct bio_list pushback;

	/*
	 * The current mapping.
	 */
	struct dm_table *map;

	/*
	 * io objects are allocated from here.
	 */
	mempool_t *io_pool;
	mempool_t *tio_pool;

	struct bio_set *bs;

	/*
	 * Event handling.
	 */
	atomic_t event_nr;
	wait_queue_head_t eventq;

	/*
	 * freeze/thaw support require holding onto a super block
	 */
	struct super_block *frozen_sb;
	struct block_device *suspended_bdev;

	/* forced geometry settings */
	struct hd_geometry geometry;
};

#define MIN_IOS 256
static struct kmem_cache *_io_cache;
static struct kmem_cache *_tio_cache;

static int __init local_init(void)
{
	int r;

	/* allocate a slab for the dm_ios */
	_io_cache = KMEM_CACHE(dm_io, 0);
	if (!_io_cache)
		return -ENOMEM;

	/* allocate a slab for the target ios */
	_tio_cache = KMEM_CACHE(dm_target_io, 0);
	if (!_tio_cache) {
		kmem_cache_destroy(_io_cache);
		return -ENOMEM;
	}

	_major = major;
	r = register_blkdev(_major, _name);
	if (r < 0) {
		kmem_cache_destroy(_tio_cache);
		kmem_cache_destroy(_io_cache);
		return r;
	}

	if (!_major)
		_major = r;

	return 0;
}

static void local_exit(void)
{
	kmem_cache_destroy(_tio_cache);
	kmem_cache_destroy(_io_cache);
	unregister_blkdev(_major, _name);

	_major = 0;

	DMINFO("cleaned up");
}

int (*_inits[])(void) __initdata = {
	local_init,
	dm_target_init,
	dm_linear_init,
	dm_stripe_init,
	dm_interface_init,
};

void (*_exits[])(void) = {
	local_exit,
	dm_target_exit,
	dm_linear_exit,
	dm_stripe_exit,
	dm_interface_exit,
};

static int __init dm_init(void)
{
	const int count = ARRAY_SIZE(_inits);

	int r, i;

	for (i = 0; i < count; i++) {
		r = _inits[i]();
		if (r)
			goto bad;
	}

	return 0;

      bad:
	while (i--)
		_exits[i]();

	return r;
}

static void __exit dm_exit(void)
{
	int i = ARRAY_SIZE(_exits);

	while (i--)
		_exits[i]();
}

/*
 * Block device functions
 */
static int dm_blk_open(struct inode *inode, struct file *file)
{
	struct mapped_device *md;

	spin_lock(&_minor_lock);

	md = inode->i_bdev->bd_disk->private_data;
	if (!md)
		goto out;

	if (test_bit(DMF_FREEING, &md->flags) ||
	    test_bit(DMF_DELETING, &md->flags)) {
		md = NULL;
		goto out;
	}

	dm_get(md);
	atomic_inc(&md->open_count);

out:
	spin_unlock(&_minor_lock);

	return md ? 0 : -ENXIO;
}

static int dm_blk_close(struct inode *inode, struct file *file)
{
	struct mapped_device *md;

	md = inode->i_bdev->bd_disk->private_data;
	atomic_dec(&md->open_count);
	dm_put(md);
	return 0;
}

int dm_open_count(struct mapped_device *md)
{
	return atomic_read(&md->open_count);
}

/*
 * Guarantees nothing is using the device before it's deleted.
 */
int dm_lock_for_deletion(struct mapped_device *md)
{
	int r = 0;

	spin_lock(&_minor_lock);

	if (dm_open_count(md))
		r = -EBUSY;
	else
		set_bit(DMF_DELETING, &md->flags);

	spin_unlock(&_minor_lock);

	return r;
}

static int dm_blk_getgeo(struct block_device *bdev, struct hd_geometry *geo)
{
	struct mapped_device *md = bdev->bd_disk->private_data;

	return dm_get_geometry(md, geo);
}

static int dm_blk_ioctl(struct inode *inode, struct file *file,
			unsigned int cmd, unsigned long arg)
{
	struct mapped_device *md;
	struct dm_table *map;
	struct dm_target *tgt;
	int r = -ENOTTY;

	/* We don't really need this lock, but we do need 'inode'. */
	unlock_kernel();

	md = inode->i_bdev->bd_disk->private_data;

	map = dm_get_table(md);

	if (!map || !dm_table_get_size(map))
		goto out;

	/* We only support devices that have a single target */
	if (dm_table_get_num_targets(map) != 1)
		goto out;

	tgt = dm_table_get_target(map, 0);

	if (dm_suspended(md)) {
		r = -EAGAIN;
		goto out;
	}

	if (tgt->type->ioctl)
		r = tgt->type->ioctl(tgt, inode, file, cmd, arg);

out:
	dm_table_put(map);

	lock_kernel();
	return r;
}

static struct dm_io *alloc_io(struct mapped_device *md)
{
	return mempool_alloc(md->io_pool, GFP_NOIO);
}

static void free_io(struct mapped_device *md, struct dm_io *io)
{
	mempool_free(io, md->io_pool);
}

static struct dm_target_io *alloc_tio(struct mapped_device *md)
{
	return mempool_alloc(md->tio_pool, GFP_NOIO);
}

static void free_tio(struct mapped_device *md, struct dm_target_io *tio)
{
	mempool_free(tio, md->tio_pool);
}

static void start_io_acct(struct dm_io *io)
{
	struct mapped_device *md = io->md;

	io->start_time = jiffies;

	preempt_disable();
	disk_round_stats(dm_disk(md));
	preempt_enable();
	dm_disk(md)->in_flight = atomic_inc_return(&md->pending);
}

static int end_io_acct(struct dm_io *io)
{
	struct mapped_device *md = io->md;
	struct bio *bio = io->bio;
	unsigned long duration = jiffies - io->start_time;
	int pending;
	int rw = bio_data_dir(bio);

	preempt_disable();
	disk_round_stats(dm_disk(md));
	preempt_enable();
	dm_disk(md)->in_flight = pending = atomic_dec_return(&md->pending);

	disk_stat_add(dm_disk(md), ticks[rw], duration);

	return !pending;
}

/*
 * Add the bio to the list of deferred io.
 */
static int queue_io(struct mapped_device *md, struct bio *bio)
{
	down_write(&md->io_lock);

	if (!test_bit(DMF_BLOCK_IO, &md->flags)) {
		up_write(&md->io_lock);
		return 1;
	}

	bio_list_add(&md->deferred, bio);

	up_write(&md->io_lock);
	return 0;		/* deferred successfully */
}

/*
 * Everyone (including functions in this file), should use this
 * function to access the md->map field, and make sure they call
 * dm_table_put() when finished.
 */
struct dm_table *dm_get_table(struct mapped_device *md)
{
	struct dm_table *t;

	read_lock(&md->map_lock);
	t = md->map;
	if (t)
		dm_table_get(t);
	read_unlock(&md->map_lock);

	return t;
}

/*
 * Get the geometry associated with a dm device
 */
int dm_get_geometry(struct mapped_device *md, struct hd_geometry *geo)
{
	*geo = md->geometry;

	return 0;
}

/*
 * Set the geometry of a device.
 */
int dm_set_geometry(struct mapped_device *md, struct hd_geometry *geo)
{
	sector_t sz = (sector_t)geo->cylinders * geo->heads * geo->sectors;

	if (geo->start > sz) {
		DMWARN("Start sector is beyond the geometry limits.");
		return -EINVAL;
	}

	md->geometry = *geo;

	return 0;
}

/*-----------------------------------------------------------------
 * CRUD START:
 *   A more elegant soln is in the works that uses the queue
 *   merge fn, unfortunately there are a couple of changes to
 *   the block layer that I want to make for this.  So in the
 *   interests of getting something for people to use I give
 *   you this clearly demarcated crap.
 *---------------------------------------------------------------*/

static int __noflush_suspending(struct mapped_device *md)
{
	return test_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
}

/*
 * Decrements the number of outstanding ios that a bio has been
 * cloned into, completing the original io if necc.
 */
static void dec_pending(struct dm_io *io, int error)
{
	unsigned long flags;

	/* Push-back supersedes any I/O errors */
	if (error && !(io->error > 0 && __noflush_suspending(io->md)))
		io->error = error;

	if (atomic_dec_and_test(&io->io_count)) {
		if (io->error == DM_ENDIO_REQUEUE) {
			/*
			 * Target requested pushing back the I/O.
			 * This must be handled before the sleeper on
			 * suspend queue merges the pushback list.
			 */
			spin_lock_irqsave(&io->md->pushback_lock, flags);
			if (__noflush_suspending(io->md))
				bio_list_add(&io->md->pushback, io->bio);
			else
				/* noflush suspend was interrupted. */
				io->error = -EIO;
			spin_unlock_irqrestore(&io->md->pushback_lock, flags);
		}

		if (end_io_acct(io))
			/* nudge anyone waiting on suspend queue */
			wake_up(&io->md->wait);

		if (io->error != DM_ENDIO_REQUEUE) {
			blk_add_trace_bio(io->md->queue, io->bio,
					  BLK_TA_COMPLETE);

			bio_endio(io->bio, io->bio->bi_size, io->error);
		}

		free_io(io->md, io);
	}
}

static int clone_endio(struct bio *bio, unsigned int done, int error)
{
	int r = 0;
	struct dm_target_io *tio = bio->bi_private;
	struct mapped_device *md = tio->io->md;
	dm_endio_fn endio = tio->ti->type->end_io;

	if (bio->bi_size)
		return 1;

	if (!bio_flagged(bio, BIO_UPTODATE) && !error)
		error = -EIO;

	if (endio) {
		r = endio(tio->ti, bio, error, &tio->info);
		if (r < 0 || r == DM_ENDIO_REQUEUE)
			/*
			 * error and requeue request are handled
			 * in dec_pending().
			 */
			error = r;
		else if (r == DM_ENDIO_INCOMPLETE)
			/* The target will handle the io */
			return 1;
		else if (r) {
			DMWARN("unimplemented target endio return value: %d", r);
			BUG();
		}
	}

	dec_pending(tio->io, error);

	/*
	 * Store md for cleanup instead of tio which is about to get freed.
	 */
	bio->bi_private = md->bs;

	bio_put(bio);
	free_tio(md, tio);
	return r;
}

static sector_t max_io_len(struct mapped_device *md,
			   sector_t sector, struct dm_target *ti)
{
	sector_t offset = sector - ti->begin;
	sector_t len = ti->len - offset;

	/*
	 * Does the target need to split even further ?
	 */
	if (ti->split_io) {
		sector_t boundary;
		boundary = ((offset + ti->split_io) & ~(ti->split_io - 1))
			   - offset;
		if (len > boundary)
			len = boundary;
	}

	return len;
}

static void __map_bio(struct dm_target *ti, struct bio *clone,
		      struct dm_target_io *tio)
{
	int r;
	sector_t sector;
	struct mapped_device *md;

	/*
	 * Sanity checks.
	 */
	BUG_ON(!clone->bi_size);

	clone->bi_end_io = clone_endio;
	clone->bi_private = tio;

	/*
	 * Map the clone.  If r == 0 we don't need to do
	 * anything, the target has assumed ownership of
	 * this io.
	 */
	atomic_inc(&tio->io->io_count);
	sector = clone->bi_sector;
	r = ti->type->map(ti, clone, &tio->info);
	if (r == DM_MAPIO_REMAPPED) {
		/* the bio has been remapped so dispatch it */

		blk_add_trace_remap(bdev_get_queue(clone->bi_bdev), clone,
				    tio->io->bio->bi_bdev->bd_dev, sector,
				    clone->bi_sector);

		generic_make_request(clone);
	} else if (r < 0 || r == DM_MAPIO_REQUEUE) {
		/* error the io and bail out, or requeue it if needed */
		md = tio->io->md;
		dec_pending(tio->io, r);
		/*
		 * Store bio_set for cleanup.
		 */
		clone->bi_private = md->bs;
		bio_put(clone);
		free_tio(md, tio);
	} else if (r) {
		DMWARN("unimplemented target map return value: %d", r);
		BUG();
	}
}

struct clone_info {
	struct mapped_device *md;
	struct dm_table *map;
	struct bio *bio;
	struct dm_io *io;
	sector_t sector;
	sector_t sector_count;
	unsigned short idx;
};

static void dm_bio_destructor(struct bio *bio)
{
	struct bio_set *bs = bio->bi_private;

	bio_free(bio, bs);
}

/*
 * Creates a little bio that is just does part of a bvec.
 */
static struct bio *split_bvec(struct bio *bio, sector_t sector,
			      unsigned short idx, unsigned int offset,
			      unsigned int len, struct bio_set *bs)
{
	struct bio *clone;
	struct bio_vec *bv = bio->bi_io_vec + idx;

	clone = bio_alloc_bioset(GFP_NOIO, 1, bs);
	clone->bi_destructor = dm_bio_destructor;
	*clone->bi_io_vec = *bv;

	clone->bi_sector = sector;
	clone->bi_bdev = bio->bi_bdev;
	clone->bi_rw = bio->bi_rw;
	clone->bi_vcnt = 1;
	clone->bi_size = to_bytes(len);
	clone->bi_io_vec->bv_offset = offset;
	clone->bi_io_vec->bv_len = clone->bi_size;

	return clone;
}

/*
 * Creates a bio that consists of range of complete bvecs.
 */
static struct bio *clone_bio(struct bio *bio, sector_t sector,
			     unsigned short idx, unsigned short bv_count,
			     unsigned int len, struct bio_set *bs)
{
	struct bio *clone;

	clone = bio_alloc_bioset(GFP_NOIO, bio->bi_max_vecs, bs);
	__bio_clone(clone, bio);
	clone->bi_destructor = dm_bio_destructor;
	clone->bi_sector = sector;
	clone->bi_idx = idx;
	clone->bi_vcnt = idx + bv_count;
	clone->bi_size = to_bytes(len);
	clone->bi_flags &= ~(1 << BIO_SEG_VALID);

	return clone;
}

static void __clone_and_map(struct clone_info *ci)
{
	struct bio *clone, *bio = ci->bio;
	struct dm_target *ti = dm_table_find_target(ci->map, ci->sector);
	sector_t len = 0, max = max_io_len(ci->md, ci->sector, ti);
	struct dm_target_io *tio;

	/*
	 * Allocate a target io object.
	 */
	tio = alloc_tio(ci->md);
	tio->io = ci->io;
	tio->ti = ti;
	memset(&tio->info, 0, sizeof(tio->info));

	if (ci->sector_count <= max) {
		/*
		 * Optimise for the simple case where we can do all of
		 * the remaining io with a single clone.
		 */
		clone = clone_bio(bio, ci->sector, ci->idx,
				  bio->bi_vcnt - ci->idx, ci->sector_count,
				  ci->md->bs);
		__map_bio(ti, clone, tio);
		ci->sector_count = 0;

	} else if (to_sector(bio->bi_io_vec[ci->idx].bv_len) <= max) {
		/*
		 * There are some bvecs that don't span targets.
		 * Do as many of these as possible.
		 */
		int i;
		sector_t remaining = max;
		sector_t bv_len;

		for (i = ci->idx; remaining && (i < bio->bi_vcnt); i++) {
			bv_len = to_sector(bio->bi_io_vec[i].bv_len);

			if (bv_len > remaining)
				break;

			remaining -= bv_len;
			len += bv_len;
		}

		clone = clone_bio(bio, ci->sector, ci->idx, i - ci->idx, len,
				  ci->md->bs);
		__map_bio(ti, clone, tio);

		ci->sector += len;
		ci->sector_count -= len;
		ci->idx = i;

	} else {
		/*
		 * Handle a bvec that must be split between two or more targets.
		 */
		struct bio_vec *bv = bio->bi_io_vec + ci->idx;
		sector_t remaining = to_sector(bv->bv_len);
		unsigned int offset = 0;

		do {
			if (offset) {
				ti = dm_table_find_target(ci->map, ci->sector);
				max = max_io_len(ci->md, ci->sector, ti);

				tio = alloc_tio(ci->md);
				tio->io = ci->io;
				tio->ti = ti;
				memset(&tio->info, 0, sizeof(tio->info));
			}

			len = min(remaining, max);

			clone = split_bvec(bio, ci->sector, ci->idx,
					   bv->bv_offset + offset, len,
					   ci->md->bs);

			__map_bio(ti, clone, tio);

			ci->sector += len;
			ci->sector_count -= len;
			offset += to_bytes(len);
		} while (remaining -= len);

		ci->idx++;
	}
}

/*
 * Split the bio into several clones.
 */
static void __split_bio(struct mapped_device *md, struct bio *bio)
{
	struct clone_info ci;

	ci.map = dm_get_table(md);
	if (!ci.map) {
		bio_io_error(bio, bio->bi_size);
		return;
	}

	ci.md = md;
	ci.bio = bio;
	ci.io = alloc_io(md);
	ci.io->error = 0;
	atomic_set(&ci.io->io_count, 1);
	ci.io->bio = bio;
	ci.io->md = md;
	ci.sector = bio->bi_sector;
	ci.sector_count = bio_sectors(bio);
	ci.idx = bio->bi_idx;

	start_io_acct(ci.io);
	while (ci.sector_count)
		__clone_and_map(&ci);

	/* drop the extra reference count */
	dec_pending(ci.io, 0);
	dm_table_put(ci.map);
}
/*-----------------------------------------------------------------
 * CRUD END
 *---------------------------------------------------------------*/

/*
 * The request function that just remaps the bio built up by
 * dm_merge_bvec.
 */
static int dm_request(request_queue_t *q, struct bio *bio)
{
	int r;
	int rw = bio_data_dir(bio);
	struct mapped_device *md = q->queuedata;

	/*
	 * There is no use in forwarding any barrier request since we can't
	 * guarantee it is (or can be) handled by the targets correctly.
	 */
	if (unlikely(bio_barrier(bio))) {
		bio_endio(bio, bio->bi_size, -EOPNOTSUPP);
		return 0;
	}

	down_read(&md->io_lock);

	disk_stat_inc(dm_disk(md), ios[rw]);
	disk_stat_add(dm_disk(md), sectors[rw], bio_sectors(bio));

	/*
	 * If we're suspended we have to queue
	 * this io for later.
	 */
	while (test_bit(DMF_BLOCK_IO, &md->flags)) {
		up_read(&md->io_lock);

		if (bio_rw(bio) == READA) {
			bio_io_error(bio, bio->bi_size);
			return 0;
		}

		r = queue_io(md, bio);
		if (r < 0) {
			bio_io_error(bio, bio->bi_size);
			return 0;

		} else if (r == 0)
			return 0;	/* deferred successfully */

		/*
		 * We're in a while loop, because someone could suspend
		 * before we get to the following read lock.
		 */
		down_read(&md->io_lock);
	}

	__split_bio(md, bio);
	up_read(&md->io_lock);
	return 0;
}

static int dm_flush_all(request_queue_t *q, struct gendisk *disk,
			sector_t *error_sector)
{
	struct mapped_device *md = q->queuedata;
	struct dm_table *map = dm_get_table(md);
	int ret = -ENXIO;

	if (map) {
		ret = dm_table_flush_all(map);
		dm_table_put(map);
	}

	return ret;
}

static void dm_unplug_all(request_queue_t *q)
{
	struct mapped_device *md = q->queuedata;
	struct dm_table *map = dm_get_table(md);

	if (map) {
		dm_table_unplug_all(map);
		dm_table_put(map);
	}
}

static int dm_any_congested(void *congested_data, int bdi_bits)
{
	int r;
	struct mapped_device *md = (struct mapped_device *) congested_data;
	struct dm_table *map = dm_get_table(md);

	if (!map || test_bit(DMF_BLOCK_IO, &md->flags))
		r = bdi_bits;
	else
		r = dm_table_any_congested(map, bdi_bits);

	dm_table_put(map);
	return r;
}

/*-----------------------------------------------------------------
 * An IDR is used to keep track of allocated minor numbers.
 *---------------------------------------------------------------*/
static DEFINE_IDR(_minor_idr);

static void free_minor(int minor)
{
	spin_lock(&_minor_lock);
	idr_remove(&_minor_idr, minor);
	spin_unlock(&_minor_lock);
}

/*
 * See if the device with a specific minor # is free.
 */
static int specific_minor(struct mapped_device *md, int minor)
{
	int r, m;

	if (minor >= (1 << MINORBITS))
		return -EINVAL;

	r = idr_pre_get(&_minor_idr, GFP_KERNEL);
	if (!r)
		return -ENOMEM;

	spin_lock(&_minor_lock);

	if (idr_find(&_minor_idr, minor)) {
		r = -EBUSY;
		goto out;
	}

	r = idr_get_new_above(&_minor_idr, MINOR_ALLOCED, minor, &m);
	if (r)
		goto out;

	if (m != minor) {
		idr_remove(&_minor_idr, m);
		r = -EBUSY;
		goto out;
	}

out:
	spin_unlock(&_minor_lock);
	return r;
}

static int next_free_minor(struct mapped_device *md, int *minor)
{
	int r, m;

	r = idr_pre_get(&_minor_idr, GFP_KERNEL);
	if (!r)
		return -ENOMEM;

	spin_lock(&_minor_lock);

	r = idr_get_new(&_minor_idr, MINOR_ALLOCED, &m);
	if (r) {
		goto out;
	}

	if (m >= (1 << MINORBITS)) {
		idr_remove(&_minor_idr, m);
		r = -ENOSPC;
		goto out;
	}

	*minor = m;

out:
	spin_unlock(&_minor_lock);
	return r;
}

static struct block_device_operations dm_blk_dops;

/*
 * Allocate and initialise a blank device with a given minor.
 */
static struct mapped_device *alloc_dev(int minor)
{
	int r;
	struct mapped_device *md = kmalloc(sizeof(*md), GFP_KERNEL);
	void *old_md;

	if (!md) {
		DMWARN("unable to allocate device, out of memory.");
		return NULL;
	}

	if (!try_module_get(THIS_MODULE))
		goto bad0;

	/* get a minor number for the dev */
	if (minor == DM_ANY_MINOR)
		r = next_free_minor(md, &minor);
	else
		r = specific_minor(md, minor);
	if (r < 0)
		goto bad1;

	memset(md, 0, sizeof(*md));
	init_rwsem(&md->io_lock);
	init_MUTEX(&md->suspend_lock);
	spin_lock_init(&md->pushback_lock);
	rwlock_init(&md->map_lock);
	atomic_set(&md->holders, 1);
	atomic_set(&md->open_count, 0);
	atomic_set(&md->event_nr, 0);

	md->queue = blk_alloc_queue(GFP_KERNEL);
	if (!md->queue)
		goto bad1_free_minor;

	md->queue->queuedata = md;
	md->queue->backing_dev_info.congested_fn = dm_any_congested;
	md->queue->backing_dev_info.congested_data = md;
	blk_queue_make_request(md->queue, dm_request);
	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
	md->queue->unplug_fn = dm_unplug_all;
	md->queue->issue_flush_fn = dm_flush_all;

	md->io_pool = mempool_create_slab_pool(MIN_IOS, _io_cache);
	if (!md->io_pool)
		goto bad2;

	md->tio_pool = mempool_create_slab_pool(MIN_IOS, _tio_cache);
	if (!md->tio_pool)
		goto bad3;

	md->bs = bioset_create(16, 16);
	if (!md->bs)
		goto bad_no_bioset;

	md->disk = alloc_disk(1);
	if (!md->disk)
		goto bad4;

	atomic_set(&md->pending, 0);
	init_waitqueue_head(&md->wait);
	init_waitqueue_head(&md->eventq);

	md->disk->major = _major;
	md->disk->first_minor = minor;
	md->disk->fops = &dm_blk_dops;
	md->disk->queue = md->queue;
	md->disk->private_data = md;
	sprintf(md->disk->disk_name, "dm-%d", minor);
	add_disk(md->disk);
	format_dev_t(md->name, MKDEV(_major, minor));

	/* Populate the mapping, nobody knows we exist yet */
	spin_lock(&_minor_lock);
	old_md = idr_replace(&_minor_idr, md, minor);
	spin_unlock(&_minor_lock);

	BUG_ON(old_md != MINOR_ALLOCED);

	return md;

 bad4:
	bioset_free(md->bs);
 bad_no_bioset:
	mempool_destroy(md->tio_pool);
 bad3:
	mempool_destroy(md->io_pool);
 bad2:
	blk_cleanup_queue(md->queue);
 bad1_free_minor:
	free_minor(minor);
 bad1:
	module_put(THIS_MODULE);
 bad0:
	kfree(md);
	return NULL;
}

static void free_dev(struct mapped_device *md)
{
	int minor = md->disk->first_minor;

	if (md->suspended_bdev) {
		thaw_bdev(md->suspended_bdev, NULL);
		bdput(md->suspended_bdev);
	}
	mempool_destroy(md->tio_pool);
	mempool_destroy(md->io_pool);
	bioset_free(md->bs);
	del_gendisk(md->disk);
	free_minor(minor);

	spin_lock(&_minor_lock);
	md->disk->private_data = NULL;
	spin_unlock(&_minor_lock);

	put_disk(md->disk);
	blk_cleanup_queue(md->queue);
	module_put(THIS_MODULE);
	kfree(md);
}

/*
 * Bind a table to the device.
 */
static void event_callback(void *context)
{
	struct mapped_device *md = (struct mapped_device *) context;

	atomic_inc(&md->event_nr);
	wake_up(&md->eventq);
}

static void __set_size(struct mapped_device *md, sector_t size)
{
	set_capacity(md->disk, size);

	mutex_lock(&md->suspended_bdev->bd_inode->i_mutex);
	i_size_write(md->suspended_bdev->bd_inode, (loff_t)size << SECTOR_SHIFT);
	mutex_unlock(&md->suspended_bdev->bd_inode->i_mutex);
}

static int __bind(struct mapped_device *md, struct dm_table *t)
{
	request_queue_t *q = md->queue;
	sector_t size;

	size = dm_table_get_size(t);

	/*
	 * Wipe any geometry if the size of the table changed.
	 */
	if (size != get_capacity(md->disk))
		memset(&md->geometry, 0, sizeof(md->geometry));

	if (md->suspended_bdev)
		__set_size(md, size);
	if (size == 0)
		return 0;

	dm_table_get(t);
	dm_table_event_callback(t, event_callback, md);

	write_lock(&md->map_lock);
	md->map = t;
	dm_table_set_restrictions(t, q);
	write_unlock(&md->map_lock);

	return 0;
}

static void __unbind(struct mapped_device *md)
{
	struct dm_table *map = md->map;

	if (!map)
		return;

	dm_table_event_callback(map, NULL, NULL);
	write_lock(&md->map_lock);
	md->map = NULL;
	write_unlock(&md->map_lock);
	dm_table_put(map);
}

/*
 * Constructor for a new device.
 */
int dm_create(int minor, struct mapped_device **result)
{
	struct mapped_device *md;

	md = alloc_dev(minor);
	if (!md)
		return -ENXIO;

	*result = md;
	return 0;
}

static struct mapped_device *dm_find_md(dev_t dev)
{
	struct mapped_device *md;
	unsigned minor = MINOR(dev);

	if (MAJOR(dev) != _major || minor >= (1 << MINORBITS))
		return NULL;

	spin_lock(&_minor_lock);

	md = idr_find(&_minor_idr, minor);
	if (md && (md == MINOR_ALLOCED ||
		   (dm_disk(md)->first_minor != minor) ||
		   test_bit(DMF_FREEING, &md->flags))) {
		md = NULL;
		goto out;
	}

out:
	spin_unlock(&_minor_lock);

	return md;
}

struct mapped_device *dm_get_md(dev_t dev)
{
	struct mapped_device *md = dm_find_md(dev);

	if (md)
		dm_get(md);

	return md;
}

void *dm_get_mdptr(struct mapped_device *md)
{
	return md->interface_ptr;
}

void dm_set_mdptr(struct mapped_device *md, void *ptr)
{
	md->interface_ptr = ptr;
}

void dm_get(struct mapped_device *md)
{
	atomic_inc(&md->holders);
}

const char *dm_device_name(struct mapped_device *md)
{
	return md->name;
}
EXPORT_SYMBOL_GPL(dm_device_name);

void dm_put(struct mapped_device *md)
{
	struct dm_table *map;

	BUG_ON(test_bit(DMF_FREEING, &md->flags));

	if (atomic_dec_and_lock(&md->holders, &_minor_lock)) {
		map = dm_get_table(md);
		idr_replace(&_minor_idr, MINOR_ALLOCED, dm_disk(md)->first_minor);
		set_bit(DMF_FREEING, &md->flags);
		spin_unlock(&_minor_lock);
		if (!dm_suspended(md)) {
			dm_table_presuspend_targets(map);
			dm_table_postsuspend_targets(map);
		}
		__unbind(md);
		dm_table_put(map);
		free_dev(md);
	}
}
EXPORT_SYMBOL_GPL(dm_put);

/*
 * Process the deferred bios
 */
static void __flush_deferred_io(struct mapped_device *md, struct bio *c)
{
	struct bio *n;

	while (c) {
		n = c->bi_next;
		c->bi_next = NULL;
		__split_bio(md, c);
		c = n;
	}
}

/*
 * Swap in a new table (destroying old one).
 */
int dm_swap_table(struct mapped_device *md, struct dm_table *table)
{
	int r = -EINVAL;

	down(&md->suspend_lock);

	/* device must be suspended */
	if (!dm_suspended(md))
		goto out;

	/* without bdev, the device size cannot be changed */
	if (!md->suspended_bdev)
		if (get_capacity(md->disk) != dm_table_get_size(table))
			goto out;

	__unbind(md);
	r = __bind(md, table);

out:
	up(&md->suspend_lock);
	return r;
}

/*
 * Functions to lock and unlock any filesystem running on the
 * device.
 */
static int lock_fs(struct mapped_device *md)
{
	int r;

	WARN_ON(md->frozen_sb);

	md->frozen_sb = freeze_bdev(md->suspended_bdev);
	if (IS_ERR(md->frozen_sb)) {
		r = PTR_ERR(md->frozen_sb);
		md->frozen_sb = NULL;
		return r;
	}

	set_bit(DMF_FROZEN, &md->flags);

	/* don't bdput right now, we don't want the bdev
	 * to go away while it is locked.
	 */
	return 0;
}

static void unlock_fs(struct mapped_device *md)
{
	if (!test_bit(DMF_FROZEN, &md->flags))
		return;

	thaw_bdev(md->suspended_bdev, md->frozen_sb);
	md->frozen_sb = NULL;
	clear_bit(DMF_FROZEN, &md->flags);
}

/*
 * We need to be able to change a mapping table under a mounted
 * filesystem.  For example we might want to move some data in
 * the background.  Before the table can be swapped with
 * dm_bind_table, dm_suspend must be called to flush any in
 * flight bios and ensure that any further io gets deferred.
 */
int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
{
	struct dm_table *map = NULL;
	unsigned long flags;
	DECLARE_WAITQUEUE(wait, current);
	struct bio *def;
	int r = -EINVAL;
	int do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG ? 1 : 0;
	int noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG ? 1 : 0;

	down(&md->suspend_lock);

	if (dm_suspended(md))
		goto out_unlock;

	map = dm_get_table(md);

	/*
	 * DMF_NOFLUSH_SUSPENDING must be set before presuspend.
	 * This flag is cleared before dm_suspend returns.
	 */
	if (noflush)
		set_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);

	/* This does not get reverted if there's an error later. */
	dm_table_presuspend_targets(map);

	/* bdget() can stall if the pending I/Os are not flushed */
	if (!noflush) {
		md->suspended_bdev = bdget_disk(md->disk, 0);
		if (!md->suspended_bdev) {
			DMWARN("bdget failed in dm_suspend");
			r = -ENOMEM;
			goto flush_and_out;
		}
	}

	/*
	 * Flush I/O to the device.
	 * noflush supersedes do_lockfs, because lock_fs() needs to flush I/Os.
	 */
	if (do_lockfs && !noflush) {
		r = lock_fs(md);
		if (r)
			goto out;
	}

	/*
	 * First we set the BLOCK_IO flag so no more ios will be mapped.
	 */
	down_write(&md->io_lock);
	set_bit(DMF_BLOCK_IO, &md->flags);

	add_wait_queue(&md->wait, &wait);
	up_write(&md->io_lock);

	/* unplug */
	if (map)
		dm_table_unplug_all(map);

	/*
	 * Then we wait for the already mapped ios to
	 * complete.
	 */
	while (1) {
		set_current_state(TASK_INTERRUPTIBLE);

		if (!atomic_read(&md->pending) || signal_pending(current))
			break;

		io_schedule();
	}
	set_current_state(TASK_RUNNING);

	down_write(&md->io_lock);
	remove_wait_queue(&md->wait, &wait);

	if (noflush) {
		spin_lock_irqsave(&md->pushback_lock, flags);
		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
		bio_list_merge_head(&md->deferred, &md->pushback);
		bio_list_init(&md->pushback);
		spin_unlock_irqrestore(&md->pushback_lock, flags);
	}

	/* were we interrupted ? */
	r = -EINTR;
	if (atomic_read(&md->pending)) {
		clear_bit(DMF_BLOCK_IO, &md->flags);
		def = bio_list_get(&md->deferred);
		__flush_deferred_io(md, def);
		up_write(&md->io_lock);
		unlock_fs(md);
		goto out; /* pushback list is already flushed, so skip flush */
	}
	up_write(&md->io_lock);

	dm_table_postsuspend_targets(map);

	set_bit(DMF_SUSPENDED, &md->flags);

	r = 0;

flush_and_out:
	if (r && noflush) {
		/*
		 * Because there may be already I/Os in the pushback list,
		 * flush them before return.
		 */
		down_write(&md->io_lock);

		spin_lock_irqsave(&md->pushback_lock, flags);
		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
		bio_list_merge_head(&md->deferred, &md->pushback);
		bio_list_init(&md->pushback);
		spin_unlock_irqrestore(&md->pushback_lock, flags);

		def = bio_list_get(&md->deferred);
		__flush_deferred_io(md, def);
		up_write(&md->io_lock);
	}

out:
	if (r && md->suspended_bdev) {
		bdput(md->suspended_bdev);
		md->suspended_bdev = NULL;
	}

	dm_table_put(map);

out_unlock:
	up(&md->suspend_lock);
	return r;
}

int dm_resume(struct mapped_device *md)
{
	int r = -EINVAL;
	struct bio *def;
	struct dm_table *map = NULL;

	down(&md->suspend_lock);
	if (!dm_suspended(md))
		goto out;

	map = dm_get_table(md);
	if (!map || !dm_table_get_size(map))
		goto out;

	r = dm_table_resume_targets(map);
	if (r)
		goto out;

	down_write(&md->io_lock);
	clear_bit(DMF_BLOCK_IO, &md->flags);

	def = bio_list_get(&md->deferred);
	__flush_deferred_io(md, def);
	up_write(&md->io_lock);

	unlock_fs(md);

	if (md->suspended_bdev) {
		bdput(md->suspended_bdev);
		md->suspended_bdev = NULL;
	}

	clear_bit(DMF_SUSPENDED, &md->flags);

	dm_table_unplug_all(map);

	kobject_uevent(&md->disk->kobj, KOBJ_CHANGE);

	r = 0;

out:
	dm_table_put(map);
	up(&md->suspend_lock);

	return r;
}

/*-----------------------------------------------------------------
 * Event notification.
 *---------------------------------------------------------------*/
uint32_t dm_get_event_nr(struct mapped_device *md)
{
	return atomic_read(&md->event_nr);
}

int dm_wait_event(struct mapped_device *md, int event_nr)
{
	return wait_event_interruptible(md->eventq,
			(event_nr != atomic_read(&md->event_nr)));
}

/*
 * The gendisk is only valid as long as you have a reference
 * count on 'md'.
 */
struct gendisk *dm_disk(struct mapped_device *md)
{
	return md->disk;
}

int dm_suspended(struct mapped_device *md)
{
	return test_bit(DMF_SUSPENDED, &md->flags);
}

int dm_noflush_suspending(struct dm_target *ti)
{
	struct mapped_device *md = dm_table_get_md(ti->table);
	int r = __noflush_suspending(md);

	dm_put(md);

	return r;
}
EXPORT_SYMBOL_GPL(dm_noflush_suspending);

static struct block_device_operations dm_blk_dops = {
	.open = dm_blk_open,
	.release = dm_blk_close,
	.ioctl = dm_blk_ioctl,
	.getgeo = dm_blk_getgeo,
	.owner = THIS_MODULE
};

EXPORT_SYMBOL(dm_get_mapinfo);

/*
 * module hooks
 */
module_init(dm_init);
module_exit(dm_exit);

module_param(major, uint, 0);
MODULE_PARM_DESC(major, "The major number of the device mapper");
MODULE_DESCRIPTION(DM_NAME " driver");
MODULE_AUTHOR("Joe Thornber <dm-devel@redhat.com>");
MODULE_LICENSE("GPL");