forked from microsoft/WSL2-Linux-Kernel
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathdm.c
1358 lines (1086 loc) · 26.4 KB
/
dm.c
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
/*
* 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>
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 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 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
struct mapped_device {
struct rw_semaphore io_lock;
struct semaphore suspend_lock;
rwlock_t map_lock;
atomic_t holders;
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;
/*
* The current mapping.
*/
struct dm_table *map;
/*
* io objects are allocated from here.
*/
mempool_t *io_pool;
mempool_t *tio_pool;
/*
* 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 kmem_cache_t *_io_cache;
static kmem_cache_t *_tio_cache;
static struct bio_set *dm_set;
static int __init local_init(void)
{
int r;
dm_set = bioset_create(16, 16, 4);
if (!dm_set)
return -ENOMEM;
/* allocate a slab for the dm_ios */
_io_cache = kmem_cache_create("dm_io",
sizeof(struct dm_io), 0, 0, NULL, NULL);
if (!_io_cache)
return -ENOMEM;
/* allocate a slab for the target ios */
_tio_cache = kmem_cache_create("dm_tio", sizeof(struct target_io),
0, 0, NULL, NULL);
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);
bioset_free(dm_set);
if (unregister_blkdev(_major, _name) < 0)
DMERR("devfs_unregister_blkdev failed");
_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)) {
md = NULL;
goto out;
}
dm_get(md);
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;
dm_put(md);
return 0;
}
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 inline struct dm_io *alloc_io(struct mapped_device *md)
{
return mempool_alloc(md->io_pool, GFP_NOIO);
}
static inline void free_io(struct mapped_device *md, struct dm_io *io)
{
mempool_free(io, md->io_pool);
}
static inline struct target_io *alloc_tio(struct mapped_device *md)
{
return mempool_alloc(md->tio_pool, GFP_NOIO);
}
static inline void free_tio(struct mapped_device *md, struct 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.
*---------------------------------------------------------------*/
/*
* 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)
{
if (error)
io->error = error;
if (atomic_dec_and_test(&io->io_count)) {
if (end_io_acct(io))
/* nudge anyone waiting on suspend queue */
wake_up(&io->md->wait);
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 target_io *tio = bio->bi_private;
struct dm_io *io = tio->io;
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)
error = r;
else if (r > 0)
/* the target wants another shot at the io */
return 1;
}
free_tio(io->md, tio);
dec_pending(io, error);
bio_put(bio);
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 target_io *tio)
{
int r;
sector_t sector;
/*
* 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 > 0) {
/* 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) {
/* error the io and bail out */
struct dm_io *io = tio->io;
free_tio(tio->io->md, tio);
dec_pending(io, r);
bio_put(clone);
}
}
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)
{
bio_free(bio, dm_set);
}
/*
* 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 *clone;
struct bio_vec *bv = bio->bi_io_vec + idx;
clone = bio_alloc_bioset(GFP_NOIO, 1, dm_set);
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 *clone;
clone = bio_clone(bio, GFP_NOIO);
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 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);
__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);
__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);
__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;
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);
rwlock_init(&md->map_lock);
atomic_set(&md->holders, 1);
atomic_set(&md->event_nr, 0);
md->queue = blk_alloc_queue(GFP_KERNEL);
if (!md->queue)
goto bad1;
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->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:
mempool_destroy(md->tio_pool);
bad3:
mempool_destroy(md->io_pool);
bad2:
blk_cleanup_queue(md->queue);
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);
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));
__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;