forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvolumes.c
7222 lines (6227 loc) · 188 KB
/
volumes.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) 2007 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License v2 as published by the Free Software Foundation.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/sched.h>
#include <linux/bio.h>
#include <linux/slab.h>
#include <linux/buffer_head.h>
#include <linux/blkdev.h>
#include <linux/iocontext.h>
#include <linux/capability.h>
#include <linux/ratelimit.h>
#include <linux/kthread.h>
#include <linux/raid/pq.h>
#include <linux/semaphore.h>
#include <linux/uuid.h>
#include <asm/div64.h>
#include "ctree.h"
#include "extent_map.h"
#include "disk-io.h"
#include "transaction.h"
#include "print-tree.h"
#include "volumes.h"
#include "raid56.h"
#include "async-thread.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "math.h"
#include "dev-replace.h"
#include "sysfs.h"
const struct btrfs_raid_attr btrfs_raid_array[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = {
.sub_stripes = 2,
.dev_stripes = 1,
.devs_max = 0, /* 0 == as many as possible */
.devs_min = 4,
.tolerated_failures = 1,
.devs_increment = 2,
.ncopies = 2,
},
[BTRFS_RAID_RAID1] = {
.sub_stripes = 1,
.dev_stripes = 1,
.devs_max = 2,
.devs_min = 2,
.tolerated_failures = 1,
.devs_increment = 2,
.ncopies = 2,
},
[BTRFS_RAID_DUP] = {
.sub_stripes = 1,
.dev_stripes = 2,
.devs_max = 1,
.devs_min = 1,
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 2,
},
[BTRFS_RAID_RAID0] = {
.sub_stripes = 1,
.dev_stripes = 1,
.devs_max = 0,
.devs_min = 2,
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 1,
},
[BTRFS_RAID_SINGLE] = {
.sub_stripes = 1,
.dev_stripes = 1,
.devs_max = 1,
.devs_min = 1,
.tolerated_failures = 0,
.devs_increment = 1,
.ncopies = 1,
},
[BTRFS_RAID_RAID5] = {
.sub_stripes = 1,
.dev_stripes = 1,
.devs_max = 0,
.devs_min = 2,
.tolerated_failures = 1,
.devs_increment = 1,
.ncopies = 2,
},
[BTRFS_RAID_RAID6] = {
.sub_stripes = 1,
.dev_stripes = 1,
.devs_max = 0,
.devs_min = 3,
.tolerated_failures = 2,
.devs_increment = 1,
.ncopies = 3,
},
};
const u64 btrfs_raid_group[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = BTRFS_BLOCK_GROUP_RAID10,
[BTRFS_RAID_RAID1] = BTRFS_BLOCK_GROUP_RAID1,
[BTRFS_RAID_DUP] = BTRFS_BLOCK_GROUP_DUP,
[BTRFS_RAID_RAID0] = BTRFS_BLOCK_GROUP_RAID0,
[BTRFS_RAID_SINGLE] = 0,
[BTRFS_RAID_RAID5] = BTRFS_BLOCK_GROUP_RAID5,
[BTRFS_RAID_RAID6] = BTRFS_BLOCK_GROUP_RAID6,
};
/*
* Table to convert BTRFS_RAID_* to the error code if minimum number of devices
* condition is not met. Zero means there's no corresponding
* BTRFS_ERROR_DEV_*_NOT_MET value.
*/
const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = {
[BTRFS_RAID_RAID10] = BTRFS_ERROR_DEV_RAID10_MIN_NOT_MET,
[BTRFS_RAID_RAID1] = BTRFS_ERROR_DEV_RAID1_MIN_NOT_MET,
[BTRFS_RAID_DUP] = 0,
[BTRFS_RAID_RAID0] = 0,
[BTRFS_RAID_SINGLE] = 0,
[BTRFS_RAID_RAID5] = BTRFS_ERROR_DEV_RAID5_MIN_NOT_MET,
[BTRFS_RAID_RAID6] = BTRFS_ERROR_DEV_RAID6_MIN_NOT_MET,
};
static int init_first_rw_device(struct btrfs_trans_handle *trans,
struct btrfs_root *root,
struct btrfs_device *device);
static int btrfs_relocate_sys_chunks(struct btrfs_root *root);
static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
DEFINE_MUTEX(uuid_mutex);
static LIST_HEAD(fs_uuids);
struct list_head *btrfs_get_fs_uuids(void)
{
return &fs_uuids;
}
static struct btrfs_fs_devices *__alloc_fs_devices(void)
{
struct btrfs_fs_devices *fs_devs;
fs_devs = kzalloc(sizeof(*fs_devs), GFP_KERNEL);
if (!fs_devs)
return ERR_PTR(-ENOMEM);
mutex_init(&fs_devs->device_list_mutex);
INIT_LIST_HEAD(&fs_devs->devices);
INIT_LIST_HEAD(&fs_devs->resized_devices);
INIT_LIST_HEAD(&fs_devs->alloc_list);
INIT_LIST_HEAD(&fs_devs->list);
return fs_devs;
}
/**
* alloc_fs_devices - allocate struct btrfs_fs_devices
* @fsid: a pointer to UUID for this FS. If NULL a new UUID is
* generated.
*
* Return: a pointer to a new &struct btrfs_fs_devices on success;
* ERR_PTR() on error. Returned struct is not linked onto any lists and
* can be destroyed with kfree() right away.
*/
static struct btrfs_fs_devices *alloc_fs_devices(const u8 *fsid)
{
struct btrfs_fs_devices *fs_devs;
fs_devs = __alloc_fs_devices();
if (IS_ERR(fs_devs))
return fs_devs;
if (fsid)
memcpy(fs_devs->fsid, fsid, BTRFS_FSID_SIZE);
else
generate_random_uuid(fs_devs->fsid);
return fs_devs;
}
static void free_fs_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_device *device;
WARN_ON(fs_devices->opened);
while (!list_empty(&fs_devices->devices)) {
device = list_entry(fs_devices->devices.next,
struct btrfs_device, dev_list);
list_del(&device->dev_list);
rcu_string_free(device->name);
kfree(device);
}
kfree(fs_devices);
}
static void btrfs_kobject_uevent(struct block_device *bdev,
enum kobject_action action)
{
int ret;
ret = kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, action);
if (ret)
pr_warn("BTRFS: Sending event '%d' to kobject: '%s' (%p): failed\n",
action,
kobject_name(&disk_to_dev(bdev->bd_disk)->kobj),
&disk_to_dev(bdev->bd_disk)->kobj);
}
void btrfs_cleanup_fs_uuids(void)
{
struct btrfs_fs_devices *fs_devices;
while (!list_empty(&fs_uuids)) {
fs_devices = list_entry(fs_uuids.next,
struct btrfs_fs_devices, list);
list_del(&fs_devices->list);
free_fs_devices(fs_devices);
}
}
static struct btrfs_device *__alloc_device(void)
{
struct btrfs_device *dev;
dev = kzalloc(sizeof(*dev), GFP_KERNEL);
if (!dev)
return ERR_PTR(-ENOMEM);
INIT_LIST_HEAD(&dev->dev_list);
INIT_LIST_HEAD(&dev->dev_alloc_list);
INIT_LIST_HEAD(&dev->resized_list);
spin_lock_init(&dev->io_lock);
spin_lock_init(&dev->reada_lock);
atomic_set(&dev->reada_in_flight, 0);
atomic_set(&dev->dev_stats_ccnt, 0);
btrfs_device_data_ordered_init(dev);
INIT_RADIX_TREE(&dev->reada_zones, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
INIT_RADIX_TREE(&dev->reada_extents, GFP_NOFS & ~__GFP_DIRECT_RECLAIM);
return dev;
}
static noinline struct btrfs_device *__find_device(struct list_head *head,
u64 devid, u8 *uuid)
{
struct btrfs_device *dev;
list_for_each_entry(dev, head, dev_list) {
if (dev->devid == devid &&
(!uuid || !memcmp(dev->uuid, uuid, BTRFS_UUID_SIZE))) {
return dev;
}
}
return NULL;
}
static noinline struct btrfs_fs_devices *find_fsid(u8 *fsid)
{
struct btrfs_fs_devices *fs_devices;
list_for_each_entry(fs_devices, &fs_uuids, list) {
if (memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE) == 0)
return fs_devices;
}
return NULL;
}
static int
btrfs_get_bdev_and_sb(const char *device_path, fmode_t flags, void *holder,
int flush, struct block_device **bdev,
struct buffer_head **bh)
{
int ret;
*bdev = blkdev_get_by_path(device_path, flags, holder);
if (IS_ERR(*bdev)) {
ret = PTR_ERR(*bdev);
goto error;
}
if (flush)
filemap_write_and_wait((*bdev)->bd_inode->i_mapping);
ret = set_blocksize(*bdev, 4096);
if (ret) {
blkdev_put(*bdev, flags);
goto error;
}
invalidate_bdev(*bdev);
*bh = btrfs_read_dev_super(*bdev);
if (IS_ERR(*bh)) {
ret = PTR_ERR(*bh);
blkdev_put(*bdev, flags);
goto error;
}
return 0;
error:
*bdev = NULL;
*bh = NULL;
return ret;
}
static void requeue_list(struct btrfs_pending_bios *pending_bios,
struct bio *head, struct bio *tail)
{
struct bio *old_head;
old_head = pending_bios->head;
pending_bios->head = head;
if (pending_bios->tail)
tail->bi_next = old_head;
else
pending_bios->tail = tail;
}
/*
* we try to collect pending bios for a device so we don't get a large
* number of procs sending bios down to the same device. This greatly
* improves the schedulers ability to collect and merge the bios.
*
* But, it also turns into a long list of bios to process and that is sure
* to eventually make the worker thread block. The solution here is to
* make some progress and then put this work struct back at the end of
* the list if the block device is congested. This way, multiple devices
* can make progress from a single worker thread.
*/
static noinline void run_scheduled_bios(struct btrfs_device *device)
{
struct bio *pending;
struct backing_dev_info *bdi;
struct btrfs_fs_info *fs_info;
struct btrfs_pending_bios *pending_bios;
struct bio *tail;
struct bio *cur;
int again = 0;
unsigned long num_run;
unsigned long batch_run = 0;
unsigned long limit;
unsigned long last_waited = 0;
int force_reg = 0;
int sync_pending = 0;
struct blk_plug plug;
/*
* this function runs all the bios we've collected for
* a particular device. We don't want to wander off to
* another device without first sending all of these down.
* So, setup a plug here and finish it off before we return
*/
blk_start_plug(&plug);
bdi = blk_get_backing_dev_info(device->bdev);
fs_info = device->dev_root->fs_info;
limit = btrfs_async_submit_limit(fs_info);
limit = limit * 2 / 3;
loop:
spin_lock(&device->io_lock);
loop_lock:
num_run = 0;
/* take all the bios off the list at once and process them
* later on (without the lock held). But, remember the
* tail and other pointers so the bios can be properly reinserted
* into the list if we hit congestion
*/
if (!force_reg && device->pending_sync_bios.head) {
pending_bios = &device->pending_sync_bios;
force_reg = 1;
} else {
pending_bios = &device->pending_bios;
force_reg = 0;
}
pending = pending_bios->head;
tail = pending_bios->tail;
WARN_ON(pending && !tail);
/*
* if pending was null this time around, no bios need processing
* at all and we can stop. Otherwise it'll loop back up again
* and do an additional check so no bios are missed.
*
* device->running_pending is used to synchronize with the
* schedule_bio code.
*/
if (device->pending_sync_bios.head == NULL &&
device->pending_bios.head == NULL) {
again = 0;
device->running_pending = 0;
} else {
again = 1;
device->running_pending = 1;
}
pending_bios->head = NULL;
pending_bios->tail = NULL;
spin_unlock(&device->io_lock);
while (pending) {
rmb();
/* we want to work on both lists, but do more bios on the
* sync list than the regular list
*/
if ((num_run > 32 &&
pending_bios != &device->pending_sync_bios &&
device->pending_sync_bios.head) ||
(num_run > 64 && pending_bios == &device->pending_sync_bios &&
device->pending_bios.head)) {
spin_lock(&device->io_lock);
requeue_list(pending_bios, pending, tail);
goto loop_lock;
}
cur = pending;
pending = pending->bi_next;
cur->bi_next = NULL;
/*
* atomic_dec_return implies a barrier for waitqueue_active
*/
if (atomic_dec_return(&fs_info->nr_async_bios) < limit &&
waitqueue_active(&fs_info->async_submit_wait))
wake_up(&fs_info->async_submit_wait);
BUG_ON(atomic_read(&cur->__bi_cnt) == 0);
/*
* if we're doing the sync list, record that our
* plug has some sync requests on it
*
* If we're doing the regular list and there are
* sync requests sitting around, unplug before
* we add more
*/
if (pending_bios == &device->pending_sync_bios) {
sync_pending = 1;
} else if (sync_pending) {
blk_finish_plug(&plug);
blk_start_plug(&plug);
sync_pending = 0;
}
btrfsic_submit_bio(cur);
num_run++;
batch_run++;
cond_resched();
/*
* we made progress, there is more work to do and the bdi
* is now congested. Back off and let other work structs
* run instead
*/
if (pending && bdi_write_congested(bdi) && batch_run > 8 &&
fs_info->fs_devices->open_devices > 1) {
struct io_context *ioc;
ioc = current->io_context;
/*
* the main goal here is that we don't want to
* block if we're going to be able to submit
* more requests without blocking.
*
* This code does two great things, it pokes into
* the elevator code from a filesystem _and_
* it makes assumptions about how batching works.
*/
if (ioc && ioc->nr_batch_requests > 0 &&
time_before(jiffies, ioc->last_waited + HZ/50UL) &&
(last_waited == 0 ||
ioc->last_waited == last_waited)) {
/*
* we want to go through our batch of
* requests and stop. So, we copy out
* the ioc->last_waited time and test
* against it before looping
*/
last_waited = ioc->last_waited;
cond_resched();
continue;
}
spin_lock(&device->io_lock);
requeue_list(pending_bios, pending, tail);
device->running_pending = 1;
spin_unlock(&device->io_lock);
btrfs_queue_work(fs_info->submit_workers,
&device->work);
goto done;
}
/* unplug every 64 requests just for good measure */
if (batch_run % 64 == 0) {
blk_finish_plug(&plug);
blk_start_plug(&plug);
sync_pending = 0;
}
}
cond_resched();
if (again)
goto loop;
spin_lock(&device->io_lock);
if (device->pending_bios.head || device->pending_sync_bios.head)
goto loop_lock;
spin_unlock(&device->io_lock);
done:
blk_finish_plug(&plug);
}
static void pending_bios_fn(struct btrfs_work *work)
{
struct btrfs_device *device;
device = container_of(work, struct btrfs_device, work);
run_scheduled_bios(device);
}
void btrfs_free_stale_device(struct btrfs_device *cur_dev)
{
struct btrfs_fs_devices *fs_devs;
struct btrfs_device *dev;
if (!cur_dev->name)
return;
list_for_each_entry(fs_devs, &fs_uuids, list) {
int del = 1;
if (fs_devs->opened)
continue;
if (fs_devs->seeding)
continue;
list_for_each_entry(dev, &fs_devs->devices, dev_list) {
if (dev == cur_dev)
continue;
if (!dev->name)
continue;
/*
* Todo: This won't be enough. What if the same device
* comes back (with new uuid and) with its mapper path?
* But for now, this does help as mostly an admin will
* either use mapper or non mapper path throughout.
*/
rcu_read_lock();
del = strcmp(rcu_str_deref(dev->name),
rcu_str_deref(cur_dev->name));
rcu_read_unlock();
if (!del)
break;
}
if (!del) {
/* delete the stale device */
if (fs_devs->num_devices == 1) {
btrfs_sysfs_remove_fsid(fs_devs);
list_del(&fs_devs->list);
free_fs_devices(fs_devs);
} else {
fs_devs->num_devices--;
list_del(&dev->dev_list);
rcu_string_free(dev->name);
kfree(dev);
}
break;
}
}
}
/*
* Add new device to list of registered devices
*
* Returns:
* 1 - first time device is seen
* 0 - device already known
* < 0 - error
*/
static noinline int device_list_add(const char *path,
struct btrfs_super_block *disk_super,
u64 devid, struct btrfs_fs_devices **fs_devices_ret)
{
struct btrfs_device *device;
struct btrfs_fs_devices *fs_devices;
struct rcu_string *name;
int ret = 0;
u64 found_transid = btrfs_super_generation(disk_super);
fs_devices = find_fsid(disk_super->fsid);
if (!fs_devices) {
fs_devices = alloc_fs_devices(disk_super->fsid);
if (IS_ERR(fs_devices))
return PTR_ERR(fs_devices);
list_add(&fs_devices->list, &fs_uuids);
device = NULL;
} else {
device = __find_device(&fs_devices->devices, devid,
disk_super->dev_item.uuid);
}
if (!device) {
if (fs_devices->opened)
return -EBUSY;
device = btrfs_alloc_device(NULL, &devid,
disk_super->dev_item.uuid);
if (IS_ERR(device)) {
/* we can safely leave the fs_devices entry around */
return PTR_ERR(device);
}
name = rcu_string_strdup(path, GFP_NOFS);
if (!name) {
kfree(device);
return -ENOMEM;
}
rcu_assign_pointer(device->name, name);
mutex_lock(&fs_devices->device_list_mutex);
list_add_rcu(&device->dev_list, &fs_devices->devices);
fs_devices->num_devices++;
mutex_unlock(&fs_devices->device_list_mutex);
ret = 1;
device->fs_devices = fs_devices;
} else if (!device->name || strcmp(device->name->str, path)) {
/*
* When FS is already mounted.
* 1. If you are here and if the device->name is NULL that
* means this device was missing at time of FS mount.
* 2. If you are here and if the device->name is different
* from 'path' that means either
* a. The same device disappeared and reappeared with
* different name. or
* b. The missing-disk-which-was-replaced, has
* reappeared now.
*
* We must allow 1 and 2a above. But 2b would be a spurious
* and unintentional.
*
* Further in case of 1 and 2a above, the disk at 'path'
* would have missed some transaction when it was away and
* in case of 2a the stale bdev has to be updated as well.
* 2b must not be allowed at all time.
*/
/*
* For now, we do allow update to btrfs_fs_device through the
* btrfs dev scan cli after FS has been mounted. We're still
* tracking a problem where systems fail mount by subvolume id
* when we reject replacement on a mounted FS.
*/
if (!fs_devices->opened && found_transid < device->generation) {
/*
* That is if the FS is _not_ mounted and if you
* are here, that means there is more than one
* disk with same uuid and devid.We keep the one
* with larger generation number or the last-in if
* generation are equal.
*/
return -EEXIST;
}
name = rcu_string_strdup(path, GFP_NOFS);
if (!name)
return -ENOMEM;
rcu_string_free(device->name);
rcu_assign_pointer(device->name, name);
if (device->missing) {
fs_devices->missing_devices--;
device->missing = 0;
}
}
/*
* Unmount does not free the btrfs_device struct but would zero
* generation along with most of the other members. So just update
* it back. We need it to pick the disk with largest generation
* (as above).
*/
if (!fs_devices->opened)
device->generation = found_transid;
/*
* if there is new btrfs on an already registered device,
* then remove the stale device entry.
*/
if (ret > 0)
btrfs_free_stale_device(device);
*fs_devices_ret = fs_devices;
return ret;
}
static struct btrfs_fs_devices *clone_fs_devices(struct btrfs_fs_devices *orig)
{
struct btrfs_fs_devices *fs_devices;
struct btrfs_device *device;
struct btrfs_device *orig_dev;
fs_devices = alloc_fs_devices(orig->fsid);
if (IS_ERR(fs_devices))
return fs_devices;
mutex_lock(&orig->device_list_mutex);
fs_devices->total_devices = orig->total_devices;
/* We have held the volume lock, it is safe to get the devices. */
list_for_each_entry(orig_dev, &orig->devices, dev_list) {
struct rcu_string *name;
device = btrfs_alloc_device(NULL, &orig_dev->devid,
orig_dev->uuid);
if (IS_ERR(device))
goto error;
/*
* This is ok to do without rcu read locked because we hold the
* uuid mutex so nothing we touch in here is going to disappear.
*/
if (orig_dev->name) {
name = rcu_string_strdup(orig_dev->name->str,
GFP_KERNEL);
if (!name) {
kfree(device);
goto error;
}
rcu_assign_pointer(device->name, name);
}
list_add(&device->dev_list, &fs_devices->devices);
device->fs_devices = fs_devices;
fs_devices->num_devices++;
}
mutex_unlock(&orig->device_list_mutex);
return fs_devices;
error:
mutex_unlock(&orig->device_list_mutex);
free_fs_devices(fs_devices);
return ERR_PTR(-ENOMEM);
}
void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step)
{
struct btrfs_device *device, *next;
struct btrfs_device *latest_dev = NULL;
mutex_lock(&uuid_mutex);
again:
/* This is the initialized path, it is safe to release the devices. */
list_for_each_entry_safe(device, next, &fs_devices->devices, dev_list) {
if (device->in_fs_metadata) {
if (!device->is_tgtdev_for_dev_replace &&
(!latest_dev ||
device->generation > latest_dev->generation)) {
latest_dev = device;
}
continue;
}
if (device->devid == BTRFS_DEV_REPLACE_DEVID) {
/*
* In the first step, keep the device which has
* the correct fsid and the devid that is used
* for the dev_replace procedure.
* In the second step, the dev_replace state is
* read from the device tree and it is known
* whether the procedure is really active or
* not, which means whether this device is
* used or whether it should be removed.
*/
if (step == 0 || device->is_tgtdev_for_dev_replace) {
continue;
}
}
if (device->bdev) {
blkdev_put(device->bdev, device->mode);
device->bdev = NULL;
fs_devices->open_devices--;
}
if (device->writeable) {
list_del_init(&device->dev_alloc_list);
device->writeable = 0;
if (!device->is_tgtdev_for_dev_replace)
fs_devices->rw_devices--;
}
list_del_init(&device->dev_list);
fs_devices->num_devices--;
rcu_string_free(device->name);
kfree(device);
}
if (fs_devices->seed) {
fs_devices = fs_devices->seed;
goto again;
}
fs_devices->latest_bdev = latest_dev->bdev;
mutex_unlock(&uuid_mutex);
}
static void __free_device(struct work_struct *work)
{
struct btrfs_device *device;
device = container_of(work, struct btrfs_device, rcu_work);
rcu_string_free(device->name);
kfree(device);
}
static void free_device(struct rcu_head *head)
{
struct btrfs_device *device;
device = container_of(head, struct btrfs_device, rcu);
INIT_WORK(&device->rcu_work, __free_device);
schedule_work(&device->rcu_work);
}
static void btrfs_close_bdev(struct btrfs_device *device)
{
if (device->bdev && device->writeable) {
sync_blockdev(device->bdev);
invalidate_bdev(device->bdev);
}
if (device->bdev)
blkdev_put(device->bdev, device->mode);
}
static void btrfs_prepare_close_one_device(struct btrfs_device *device)
{
struct btrfs_fs_devices *fs_devices = device->fs_devices;
struct btrfs_device *new_device;
struct rcu_string *name;
if (device->bdev)
fs_devices->open_devices--;
if (device->writeable &&
device->devid != BTRFS_DEV_REPLACE_DEVID) {
list_del_init(&device->dev_alloc_list);
fs_devices->rw_devices--;
}
if (device->missing)
fs_devices->missing_devices--;
new_device = btrfs_alloc_device(NULL, &device->devid,
device->uuid);
BUG_ON(IS_ERR(new_device)); /* -ENOMEM */
/* Safe because we are under uuid_mutex */
if (device->name) {
name = rcu_string_strdup(device->name->str, GFP_NOFS);
BUG_ON(!name); /* -ENOMEM */
rcu_assign_pointer(new_device->name, name);
}
list_replace_rcu(&device->dev_list, &new_device->dev_list);
new_device->fs_devices = device->fs_devices;
}
static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_device *device, *tmp;
struct list_head pending_put;
INIT_LIST_HEAD(&pending_put);
if (--fs_devices->opened > 0)
return 0;
mutex_lock(&fs_devices->device_list_mutex);
list_for_each_entry_safe(device, tmp, &fs_devices->devices, dev_list) {
btrfs_prepare_close_one_device(device);
list_add(&device->dev_list, &pending_put);
}
mutex_unlock(&fs_devices->device_list_mutex);
/*
* btrfs_show_devname() is using the device_list_mutex,
* sometimes call to blkdev_put() leads vfs calling
* into this func. So do put outside of device_list_mutex,
* as of now.
*/
while (!list_empty(&pending_put)) {
device = list_first_entry(&pending_put,
struct btrfs_device, dev_list);
list_del(&device->dev_list);
btrfs_close_bdev(device);
call_rcu(&device->rcu, free_device);
}
WARN_ON(fs_devices->open_devices);
WARN_ON(fs_devices->rw_devices);
fs_devices->opened = 0;
fs_devices->seeding = 0;
return 0;
}
int btrfs_close_devices(struct btrfs_fs_devices *fs_devices)
{
struct btrfs_fs_devices *seed_devices = NULL;
int ret;
mutex_lock(&uuid_mutex);
ret = __btrfs_close_devices(fs_devices);
if (!fs_devices->opened) {
seed_devices = fs_devices->seed;
fs_devices->seed = NULL;
}
mutex_unlock(&uuid_mutex);
while (seed_devices) {
fs_devices = seed_devices;
seed_devices = fs_devices->seed;
__btrfs_close_devices(fs_devices);
free_fs_devices(fs_devices);
}
/*
* Wait for rcu kworkers under __btrfs_close_devices
* to finish all blkdev_puts so device is really
* free when umount is done.
*/
rcu_barrier();
return ret;
}
static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
fmode_t flags, void *holder)
{
struct request_queue *q;
struct block_device *bdev;
struct list_head *head = &fs_devices->devices;
struct btrfs_device *device;
struct btrfs_device *latest_dev = NULL;
struct buffer_head *bh;
struct btrfs_super_block *disk_super;
u64 devid;
int seeding = 1;
int ret = 0;
flags |= FMODE_EXCL;
list_for_each_entry(device, head, dev_list) {
if (device->bdev)
continue;
if (!device->name)
continue;
/* Just open everything we can; ignore failures here */
if (btrfs_get_bdev_and_sb(device->name->str, flags, holder, 1,
&bdev, &bh))
continue;
disk_super = (struct btrfs_super_block *)bh->b_data;
devid = btrfs_stack_device_id(&disk_super->dev_item);
if (devid != device->devid)
goto error_brelse;
if (memcmp(device->uuid, disk_super->dev_item.uuid,
BTRFS_UUID_SIZE))
goto error_brelse;
device->generation = btrfs_super_generation(disk_super);
if (!latest_dev ||
device->generation > latest_dev->generation)