aboutsummaryrefslogtreecommitdiff
path: root/fs/btrfs/dev-replace.c
blob: 6f662b34ba0e8392c58d7d481092f9e461631af4 (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
/*
 * Copyright (C) STRATO AG 2012.  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/random.h>
#include <linux/iocontext.h>
#include <linux/capability.h>
#include <linux/kthread.h>
#include <linux/math64.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 "async-thread.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "sysfs.h"

static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
				       int scrub_ret);
static void btrfs_dev_replace_update_device_in_mapping_tree(
						struct btrfs_fs_info *fs_info,
						struct btrfs_device *srcdev,
						struct btrfs_device *tgtdev);
static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
					 char *srcdev_name,
					 struct btrfs_device **device);
static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info);
static int btrfs_dev_replace_kthread(void *data);
static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info);


int btrfs_init_dev_replace(struct btrfs_fs_info *fs_info)
{
	struct btrfs_key key;
	struct btrfs_root *dev_root = fs_info->dev_root;
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	struct extent_buffer *eb;
	int slot;
	int ret = 0;
	struct btrfs_path *path = NULL;
	int item_size;
	struct btrfs_dev_replace_item *ptr;
	u64 src_devid;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}

	key.objectid = 0;
	key.type = BTRFS_DEV_REPLACE_KEY;
	key.offset = 0;
	ret = btrfs_search_slot(NULL, dev_root, &key, path, 0, 0);
	if (ret) {
no_valid_dev_replace_entry_found:
		ret = 0;
		dev_replace->replace_state =
			BTRFS_DEV_REPLACE_ITEM_STATE_NEVER_STARTED;
		dev_replace->cont_reading_from_srcdev_mode =
		    BTRFS_DEV_REPLACE_ITEM_CONT_READING_FROM_SRCDEV_MODE_ALWAYS;
		dev_replace->replace_state = 0;
		dev_replace->time_started = 0;
		dev_replace->time_stopped = 0;
		atomic64_set(&dev_replace->num_write_errors, 0);
		atomic64_set(&dev_replace->num_uncorrectable_read_errors, 0);
		dev_replace->cursor_left = 0;
		dev_replace->committed_cursor_left = 0;
		dev_replace->cursor_left_last_write_of_item = 0;
		dev_replace->cursor_right = 0;
		dev_replace->srcdev = NULL;
		dev_replace->tgtdev = NULL;
		dev_replace->is_valid = 0;
		dev_replace->item_needs_writeback = 0;
		goto out;
	}
	slot = path->slots[0];
	eb = path->nodes[0];
	item_size = btrfs_item_size_nr(eb, slot);
	ptr = btrfs_item_ptr(eb, slot, struct btrfs_dev_replace_item);

	if (item_size != sizeof(struct btrfs_dev_replace_item)) {
		btrfs_warn(fs_info,
			"dev_replace entry found has unexpected size, ignore entry");
		goto no_valid_dev_replace_entry_found;
	}

	src_devid = btrfs_dev_replace_src_devid(eb, ptr);
	dev_replace->cont_reading_from_srcdev_mode =
		btrfs_dev_replace_cont_reading_from_srcdev_mode(eb, ptr);
	dev_replace->replace_state = btrfs_dev_replace_replace_state(eb, ptr);
	dev_replace->time_started = btrfs_dev_replace_time_started(eb, ptr);
	dev_replace->time_stopped =
		btrfs_dev_replace_time_stopped(eb, ptr);
	atomic64_set(&dev_replace->num_write_errors,
		     btrfs_dev_replace_num_write_errors(eb, ptr));
	atomic64_set(&dev_replace->num_uncorrectable_read_errors,
		     btrfs_dev_replace_num_uncorrectable_read_errors(eb, ptr));
	dev_replace->cursor_left = btrfs_dev_replace_cursor_left(eb, ptr);
	dev_replace->committed_cursor_left = dev_replace->cursor_left;
	dev_replace->cursor_left_last_write_of_item = dev_replace->cursor_left;
	dev_replace->cursor_right = btrfs_dev_replace_cursor_right(eb, ptr);
	dev_replace->is_valid = 1;

	dev_replace->item_needs_writeback = 0;
	switch (dev_replace->replace_state) {
	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
		dev_replace->srcdev = NULL;
		dev_replace->tgtdev = NULL;
		break;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
		dev_replace->srcdev = btrfs_find_device(fs_info, src_devid,
							NULL, NULL);
		dev_replace->tgtdev = btrfs_find_device(fs_info,
							BTRFS_DEV_REPLACE_DEVID,
							NULL, NULL);
		/*
		 * allow 'btrfs dev replace_cancel' if src/tgt device is
		 * missing
		 */
		if (!dev_replace->srcdev &&
		    !btrfs_test_opt(dev_root, DEGRADED)) {
			ret = -EIO;
			btrfs_warn(fs_info,
			   "cannot mount because device replace operation is ongoing and");
			btrfs_warn(fs_info,
			   "srcdev (devid %llu) is missing, need to run 'btrfs dev scan'?",
			   src_devid);
		}
		if (!dev_replace->tgtdev &&
		    !btrfs_test_opt(dev_root, DEGRADED)) {
			ret = -EIO;
			btrfs_warn(fs_info,
			   "cannot mount because device replace operation is ongoing and");
			btrfs_warn(fs_info,
			   "tgtdev (devid %llu) is missing, need to run 'btrfs dev scan'?",
				BTRFS_DEV_REPLACE_DEVID);
		}
		if (dev_replace->tgtdev) {
			if (dev_replace->srcdev) {
				dev_replace->tgtdev->total_bytes =
					dev_replace->srcdev->total_bytes;
				dev_replace->tgtdev->disk_total_bytes =
					dev_replace->srcdev->disk_total_bytes;
				dev_replace->tgtdev->commit_total_bytes =
					dev_replace->srcdev->commit_total_bytes;
				dev_replace->tgtdev->bytes_used =
					dev_replace->srcdev->bytes_used;
				dev_replace->tgtdev->commit_bytes_used =
					dev_replace->srcdev->commit_bytes_used;
			}
			dev_replace->tgtdev->is_tgtdev_for_dev_replace = 1;
			btrfs_init_dev_replace_tgtdev_for_resume(fs_info,
				dev_replace->tgtdev);
		}
		break;
	}

out:
	if (path)
		btrfs_free_path(path);
	return ret;
}

/*
 * called from commit_transaction. Writes changed device replace state to
 * disk.
 */
int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
			  struct btrfs_fs_info *fs_info)
{
	int ret;
	struct btrfs_root *dev_root = fs_info->dev_root;
	struct btrfs_path *path;
	struct btrfs_key key;
	struct extent_buffer *eb;
	struct btrfs_dev_replace_item *ptr;
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;

	btrfs_dev_replace_lock(dev_replace);
	if (!dev_replace->is_valid ||
	    !dev_replace->item_needs_writeback) {
		btrfs_dev_replace_unlock(dev_replace);
		return 0;
	}
	btrfs_dev_replace_unlock(dev_replace);

	key.objectid = 0;
	key.type = BTRFS_DEV_REPLACE_KEY;
	key.offset = 0;

	path = btrfs_alloc_path();
	if (!path) {
		ret = -ENOMEM;
		goto out;
	}
	ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
	if (ret < 0) {
		btrfs_warn(fs_info, "error %d while searching for dev_replace item!",
			ret);
		goto out;
	}

	if (ret == 0 &&
	    btrfs_item_size_nr(path->nodes[0], path->slots[0]) < sizeof(*ptr)) {
		/*
		 * need to delete old one and insert a new one.
		 * Since no attempt is made to recover any old state, if the
		 * dev_replace state is 'running', the data on the target
		 * drive is lost.
		 * It would be possible to recover the state: just make sure
		 * that the beginning of the item is never changed and always
		 * contains all the essential information. Then read this
		 * minimal set of information and use it as a base for the
		 * new state.
		 */
		ret = btrfs_del_item(trans, dev_root, path);
		if (ret != 0) {
			btrfs_warn(fs_info, "delete too small dev_replace item failed %d!",
				ret);
			goto out;
		}
		ret = 1;
	}

	if (ret == 1) {
		/* need to insert a new item */
		btrfs_release_path(path);
		ret = btrfs_insert_empty_item(trans, dev_root, path,
					      &key, sizeof(*ptr));
		if (ret < 0) {
			btrfs_warn(fs_info, "insert dev_replace item failed %d!",
				ret);
			goto out;
		}
	}

	eb = path->nodes[0];
	ptr = btrfs_item_ptr(eb, path->slots[0],
			     struct btrfs_dev_replace_item);

	btrfs_dev_replace_lock(dev_replace);
	if (dev_replace->srcdev)
		btrfs_set_dev_replace_src_devid(eb, ptr,
			dev_replace->srcdev->devid);
	else
		btrfs_set_dev_replace_src_devid(eb, ptr, (u64)-1);
	btrfs_set_dev_replace_cont_reading_from_srcdev_mode(eb, ptr,
		dev_replace->cont_reading_from_srcdev_mode);
	btrfs_set_dev_replace_replace_state(eb, ptr,
		dev_replace->replace_state);
	btrfs_set_dev_replace_time_started(eb, ptr, dev_replace->time_started);
	btrfs_set_dev_replace_time_stopped(eb, ptr, dev_replace->time_stopped);
	btrfs_set_dev_replace_num_write_errors(eb, ptr,
		atomic64_read(&dev_replace->num_write_errors));
	btrfs_set_dev_replace_num_uncorrectable_read_errors(eb, ptr,
		atomic64_read(&dev_replace->num_uncorrectable_read_errors));
	dev_replace->cursor_left_last_write_of_item =
		dev_replace->cursor_left;
	btrfs_set_dev_replace_cursor_left(eb, ptr,
		dev_replace->cursor_left_last_write_of_item);
	btrfs_set_dev_replace_cursor_right(eb, ptr,
		dev_replace->cursor_right);
	dev_replace->item_needs_writeback = 0;
	btrfs_dev_replace_unlock(dev_replace);

	btrfs_mark_buffer_dirty(eb);

out:
	btrfs_free_path(path);

	return ret;
}

void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info)
{
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;

	dev_replace->committed_cursor_left =
		dev_replace->cursor_left_last_write_of_item;
}

int btrfs_dev_replace_start(struct btrfs_root *root,
			    struct btrfs_ioctl_dev_replace_args *args)
{
	struct btrfs_trans_handle *trans;
	struct btrfs_fs_info *fs_info = root->fs_info;
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	int ret;
	struct btrfs_device *tgt_device = NULL;
	struct btrfs_device *src_device = NULL;

	if (btrfs_fs_incompat(fs_info, RAID56)) {
		btrfs_warn(fs_info, "dev_replace cannot yet handle RAID5/RAID6");
		return -EOPNOTSUPP;
	}

	switch (args->start.cont_reading_from_srcdev_mode) {
	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_ALWAYS:
	case BTRFS_IOCTL_DEV_REPLACE_CONT_READING_FROM_SRCDEV_MODE_AVOID:
		break;
	default:
		return -EINVAL;
	}

	if ((args->start.srcdevid == 0 && args->start.srcdev_name[0] == '\0') ||
	    args->start.tgtdev_name[0] == '\0')
		return -EINVAL;

	/*
	 * Here we commit the transaction to make sure commit_total_bytes
	 * of all the devices are updated.
	 */
	trans = btrfs_attach_transaction(root);
	if (!IS_ERR(trans)) {
		ret = btrfs_commit_transaction(trans, root);
		if (ret)
			return ret;
	} else if (PTR_ERR(trans) != -ENOENT) {
		return PTR_ERR(trans);
	}

	/* the disk copy procedure reuses the scrub code */
	mutex_lock(&fs_info->volume_mutex);
	ret = btrfs_dev_replace_find_srcdev(root, args->start.srcdevid,
					    args->start.srcdev_name,
					    &src_device);
	if (ret) {
		mutex_unlock(&fs_info->volume_mutex);
		return ret;
	}

	ret = btrfs_init_dev_replace_tgtdev(root, args->start.tgtdev_name,
					    src_device, &tgt_device);
	mutex_unlock(&fs_info->volume_mutex);
	if (ret)
		return ret;

	btrfs_dev_replace_lock(dev_replace);
	switch (dev_replace->replace_state) {
	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
		break;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
		args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_ALREADY_STARTED;
		goto leave;
	}

	dev_replace->cont_reading_from_srcdev_mode =
		args->start.cont_reading_from_srcdev_mode;
	WARN_ON(!src_device);
	dev_replace->srcdev = src_device;
	WARN_ON(!tgt_device);
	dev_replace->tgtdev = tgt_device;

	printk_in_rcu(KERN_INFO
		      "BTRFS: dev_replace from %s (devid %llu) to %s started\n",
		      src_device->missing ? "<missing disk>" :
		        rcu_str_deref(src_device->name),
		      src_device->devid,
		      rcu_str_deref(tgt_device->name));

	/*
	 * from now on, the writes to the srcdev are all duplicated to
	 * go to the tgtdev as well (refer to btrfs_map_block()).
	 */
	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED;
	dev_replace->time_started = get_seconds();
	dev_replace->cursor_left = 0;
	dev_replace->committed_cursor_left = 0;
	dev_replace->cursor_left_last_write_of_item = 0;
	dev_replace->cursor_right = 0;
	dev_replace->is_valid = 1;
	dev_replace->item_needs_writeback = 1;
	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
	btrfs_dev_replace_unlock(dev_replace);

	btrfs_wait_ordered_roots(root->fs_info, -1);

	/* force writing the updated state information to disk */
	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		ret = PTR_ERR(trans);
		btrfs_dev_replace_lock(dev_replace);
		goto leave;
	}

	ret = btrfs_commit_transaction(trans, root);
	WARN_ON(ret);

	/* the disk copy procedure reuses the scrub code */
	ret = btrfs_scrub_dev(fs_info, src_device->devid, 0,
			      btrfs_device_get_total_bytes(src_device),
			      &dev_replace->scrub_progress, 0, 1);

	ret = btrfs_dev_replace_finishing(root->fs_info, ret);
	WARN_ON(ret);

	return 0;

leave:
	dev_replace->srcdev = NULL;
	dev_replace->tgtdev = NULL;
	btrfs_dev_replace_unlock(dev_replace);
	btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
	return ret;
}

/*
 * blocked until all flighting bios are finished.
 */
static void btrfs_rm_dev_replace_blocked(struct btrfs_fs_info *fs_info)
{
	s64 writers;
	DEFINE_WAIT(wait);

	set_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state);
	do {
		prepare_to_wait(&fs_info->replace_wait, &wait,
				TASK_UNINTERRUPTIBLE);
		writers = percpu_counter_sum(&fs_info->bio_counter);
		if (writers)
			schedule();
		finish_wait(&fs_info->replace_wait, &wait);
	} while (writers);
}

/*
 * we have removed target device, it is safe to allow new bios request.
 */
static void btrfs_rm_dev_replace_unblocked(struct btrfs_fs_info *fs_info)
{
	clear_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state);
	if (waitqueue_active(&fs_info->replace_wait))
		wake_up(&fs_info->replace_wait);
}

static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
				       int scrub_ret)
{
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	struct btrfs_device *tgt_device;
	struct btrfs_device *src_device;
	struct btrfs_root *root = fs_info->tree_root;
	u8 uuid_tmp[BTRFS_UUID_SIZE];
	struct btrfs_trans_handle *trans;
	int ret = 0;

	/* don't allow cancel or unmount to disturb the finishing procedure */
	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);

	btrfs_dev_replace_lock(dev_replace);
	/* was the operation canceled, or is it finished? */
	if (dev_replace->replace_state !=
	    BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED) {
		btrfs_dev_replace_unlock(dev_replace);
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
		return 0;
	}

	tgt_device = dev_replace->tgtdev;
	src_device = dev_replace->srcdev;
	btrfs_dev_replace_unlock(dev_replace);

	/*
	 * flush all outstanding I/O and inode extent mappings before the
	 * copy operation is declared as being finished
	 */
	ret = btrfs_start_delalloc_roots(root->fs_info, 0, -1);
	if (ret) {
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
		return ret;
	}
	btrfs_wait_ordered_roots(root->fs_info, -1);

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
		return PTR_ERR(trans);
	}
	ret = btrfs_commit_transaction(trans, root);
	WARN_ON(ret);

	mutex_lock(&uuid_mutex);
	/* keep away write_all_supers() during the finishing procedure */
	mutex_lock(&root->fs_info->fs_devices->device_list_mutex);
	mutex_lock(&root->fs_info->chunk_mutex);
	btrfs_dev_replace_lock(dev_replace);
	dev_replace->replace_state =
		scrub_ret ? BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED
			  : BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED;
	dev_replace->tgtdev = NULL;
	dev_replace->srcdev = NULL;
	dev_replace->time_stopped = get_seconds();
	dev_replace->item_needs_writeback = 1;

	/* replace old device with new one in mapping tree */
	if (!scrub_ret) {
		btrfs_dev_replace_update_device_in_mapping_tree(fs_info,
								src_device,
								tgt_device);
	} else {
		printk_in_rcu(KERN_ERR
			      "BTRFS: btrfs_scrub_dev(%s, %llu, %s) failed %d\n",
			      src_device->missing ? "<missing disk>" :
			        rcu_str_deref(src_device->name),
			      src_device->devid,
			      rcu_str_deref(tgt_device->name), scrub_ret);
		btrfs_dev_replace_unlock(dev_replace);
		mutex_unlock(&root->fs_info->chunk_mutex);
		mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
		mutex_unlock(&uuid_mutex);
		if (tgt_device)
			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);

		return 0;
	}

	printk_in_rcu(KERN_INFO
		      "BTRFS: dev_replace from %s (devid %llu) to %s finished\n",
		      src_device->missing ? "<missing disk>" :
		        rcu_str_deref(src_device->name),
		      src_device->devid,
		      rcu_str_deref(tgt_device->name));
	tgt_device->is_tgtdev_for_dev_replace = 0;
	tgt_device->devid = src_device->devid;
	src_device->devid = BTRFS_DEV_REPLACE_DEVID;
	memcpy(uuid_tmp, tgt_device->uuid, sizeof(uuid_tmp));
	memcpy(tgt_device->uuid, src_device->uuid, sizeof(tgt_device->uuid));
	memcpy(src_device->uuid, uuid_tmp, sizeof(src_device->uuid));
	btrfs_device_set_total_bytes(tgt_device, src_device->total_bytes);
	btrfs_device_set_disk_total_bytes(tgt_device,
					  src_device->disk_total_bytes);
	btrfs_device_set_bytes_used(tgt_device, src_device->bytes_used);
	ASSERT(list_empty(&src_device->resized_list));
	tgt_device->commit_total_bytes = src_device->commit_total_bytes;
	tgt_device->commit_bytes_used = src_device->bytes_used;
	if (fs_info->sb->s_bdev == src_device->bdev)
		fs_info->sb->s_bdev = tgt_device->bdev;
	if (fs_info->fs_devices->latest_bdev == src_device->bdev)
		fs_info->fs_devices->latest_bdev = tgt_device->bdev;
	list_add(&tgt_device->dev_alloc_list, &fs_info->fs_devices->alloc_list);
	fs_info->fs_devices->rw_devices++;

	/* replace the sysfs entry */
	btrfs_kobj_rm_device(fs_info, src_device);
	btrfs_kobj_add_device(fs_info, tgt_device);

	btrfs_dev_replace_unlock(dev_replace);

	btrfs_rm_dev_replace_blocked(fs_info);

	btrfs_rm_dev_replace_srcdev(fs_info, src_device);

	btrfs_rm_dev_replace_unblocked(fs_info);

	/*
	 * this is again a consistent state where no dev_replace procedure
	 * is running, the target device is part of the filesystem, the
	 * source device is not part of the filesystem anymore and its 1st
	 * superblock is scratched out so that it is no longer marked to
	 * belong to this filesystem.
	 */
	mutex_unlock(&root->fs_info->chunk_mutex);
	mutex_unlock(&root->fs_info->fs_devices->device_list_mutex);
	mutex_unlock(&uuid_mutex);

	/* write back the superblocks */
	trans = btrfs_start_transaction(root, 0);
	if (!IS_ERR(trans))
		btrfs_commit_transaction(trans, root);

	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);

	return 0;
}

static void btrfs_dev_replace_update_device_in_mapping_tree(
						struct btrfs_fs_info *fs_info,
						struct btrfs_device *srcdev,
						struct btrfs_device *tgtdev)
{
	struct extent_map_tree *em_tree = &fs_info->mapping_tree.map_tree;
	struct extent_map *em;
	struct map_lookup *map;
	u64 start = 0;
	int i;

	write_lock(&em_tree->lock);
	do {
		em = lookup_extent_mapping(em_tree, start, (u64)-1);
		if (!em)
			break;
		map = (struct map_lookup *)em->bdev;
		for (i = 0; i < map->num_stripes; i++)
			if (srcdev == map->stripes[i].dev)
				map->stripes[i].dev = tgtdev;
		start = em->start + em->len;
		free_extent_map(em);
	} while (start);
	write_unlock(&em_tree->lock);
}

static int btrfs_dev_replace_find_srcdev(struct btrfs_root *root, u64 srcdevid,
					 char *srcdev_name,
					 struct btrfs_device **device)
{
	int ret;

	if (srcdevid) {
		ret = 0;
		*device = btrfs_find_device(root->fs_info, srcdevid, NULL,
					    NULL);
		if (!*device)
			ret = -ENOENT;
	} else {
		ret = btrfs_find_device_missing_or_by_path(root, srcdev_name,
							   device);
	}
	return ret;
}

void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
			      struct btrfs_ioctl_dev_replace_args *args)
{
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	struct btrfs_device *srcdev;

	btrfs_dev_replace_lock(dev_replace);
	/* even if !dev_replace_is_valid, the values are good enough for
	 * the replace_status ioctl */
	args->result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
	args->status.replace_state = dev_replace->replace_state;
	args->status.time_started = dev_replace->time_started;
	args->status.time_stopped = dev_replace->time_stopped;
	args->status.num_write_errors =
		atomic64_read(&dev_replace->num_write_errors);
	args->status.num_uncorrectable_read_errors =
		atomic64_read(&dev_replace->num_uncorrectable_read_errors);
	switch (dev_replace->replace_state) {
	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
		args->status.progress_1000 = 0;
		break;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
		args->status.progress_1000 = 1000;
		break;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
		srcdev = dev_replace->srcdev;
		args->status.progress_1000 = div64_u64(dev_replace->cursor_left,
			div64_u64(btrfs_device_get_total_bytes(srcdev), 1000));
		break;
	}
	btrfs_dev_replace_unlock(dev_replace);
}

int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
			     struct btrfs_ioctl_dev_replace_args *args)
{
	args->result = __btrfs_dev_replace_cancel(fs_info);
	return 0;
}

static u64 __btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info)
{
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	struct btrfs_device *tgt_device = NULL;
	struct btrfs_trans_handle *trans;
	struct btrfs_root *root = fs_info->tree_root;
	u64 result;
	int ret;

	if (fs_info->sb->s_flags & MS_RDONLY)
		return -EROFS;

	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
	btrfs_dev_replace_lock(dev_replace);
	switch (dev_replace->replace_state) {
	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
		result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NOT_STARTED;
		btrfs_dev_replace_unlock(dev_replace);
		goto leave;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
		result = BTRFS_IOCTL_DEV_REPLACE_RESULT_NO_ERROR;
		tgt_device = dev_replace->tgtdev;
		dev_replace->tgtdev = NULL;
		dev_replace->srcdev = NULL;
		break;
	}
	dev_replace->replace_state = BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED;
	dev_replace->time_stopped = get_seconds();
	dev_replace->item_needs_writeback = 1;
	btrfs_dev_replace_unlock(dev_replace);
	btrfs_scrub_cancel(fs_info);

	trans = btrfs_start_transaction(root, 0);
	if (IS_ERR(trans)) {
		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
		return PTR_ERR(trans);
	}
	ret = btrfs_commit_transaction(trans, root);
	WARN_ON(ret);
	if (tgt_device)
		btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);

leave:
	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
	return result;
}

void btrfs_dev_replace_suspend_for_unmount(struct btrfs_fs_info *fs_info)
{
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;

	mutex_lock(&dev_replace->lock_finishing_cancel_unmount);
	btrfs_dev_replace_lock(dev_replace);
	switch (dev_replace->replace_state) {
	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
		break;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
		dev_replace->replace_state =
			BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED;
		dev_replace->time_stopped = get_seconds();
		dev_replace->item_needs_writeback = 1;
		btrfs_info(fs_info, "suspending dev_replace for unmount");
		break;
	}

	btrfs_dev_replace_unlock(dev_replace);
	mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
}

/* resume dev_replace procedure that was interrupted by unmount */
int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
{
	struct task_struct *task;
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;

	btrfs_dev_replace_lock(dev_replace);
	switch (dev_replace->replace_state) {
	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
		btrfs_dev_replace_unlock(dev_replace);
		return 0;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
		break;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
		dev_replace->replace_state =
			BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED;
		break;
	}
	if (!dev_replace->tgtdev || !dev_replace->tgtdev->bdev) {
		btrfs_info(fs_info, "cannot continue dev_replace, tgtdev is missing");
		btrfs_info(fs_info,
			"you may cancel the operation after 'mount -o degraded'");
		btrfs_dev_replace_unlock(dev_replace);
		return 0;
	}
	btrfs_dev_replace_unlock(dev_replace);

	WARN_ON(atomic_xchg(
		&fs_info->mutually_exclusive_operation_running, 1));
	task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl");
	return PTR_ERR_OR_ZERO(task);
}

static int btrfs_dev_replace_kthread(void *data)
{
	struct btrfs_fs_info *fs_info = data;
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	struct btrfs_ioctl_dev_replace_args *status_args;
	u64 progress;

	status_args = kzalloc(sizeof(*status_args), GFP_NOFS);
	if (status_args) {
		btrfs_dev_replace_status(fs_info, status_args);
		progress = status_args->status.progress_1000;
		kfree(status_args);
		do_div(progress, 10);
		printk_in_rcu(KERN_INFO
			"BTRFS: continuing dev_replace from %s (devid %llu) to %s @%u%%\n",
			dev_replace->srcdev->missing ? "<missing disk>" :
			rcu_str_deref(dev_replace->srcdev->name),
			dev_replace->srcdev->devid,
			dev_replace->tgtdev ?
			rcu_str_deref(dev_replace->tgtdev->name) :
			"<missing target disk>",
			(unsigned int)progress);
	}
	btrfs_dev_replace_continue_on_mount(fs_info);
	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);

	return 0;
}

static int btrfs_dev_replace_continue_on_mount(struct btrfs_fs_info *fs_info)
{
	struct btrfs_dev_replace *dev_replace = &fs_info->dev_replace;
	int ret;

	ret = btrfs_scrub_dev(fs_info, dev_replace->srcdev->devid,
			      dev_replace->committed_cursor_left,
			      btrfs_device_get_total_bytes(dev_replace->srcdev),
			      &dev_replace->scrub_progress, 0, 1);
	ret = btrfs_dev_replace_finishing(fs_info, ret);
	WARN_ON(ret);
	return 0;
}

int btrfs_dev_replace_is_ongoing(struct btrfs_dev_replace *dev_replace)
{
	if (!dev_replace->is_valid)
		return 0;

	switch (dev_replace->replace_state) {
	case BTRFS_IOCTL_DEV_REPLACE_STATE_NEVER_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_FINISHED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_CANCELED:
		return 0;
	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
		/*
		 * return true even if tgtdev is missing (this is
		 * something that can happen if the dev_replace
		 * procedure is suspended by an umount and then
		 * the tgtdev is missing (or "btrfs dev scan") was
		 * not called and the the filesystem is remounted
		 * in degraded state. This does not stop the
		 * dev_replace procedure. It needs to be canceled
		 * manually if the cancelation is wanted.
		 */
		break;
	}
	return 1;
}

void btrfs_dev_replace_lock(struct btrfs_dev_replace *dev_replace)
{
	/* the beginning is just an optimization for the typical case */
	if (atomic_read(&dev_replace->nesting_level) == 0) {
acquire_lock:
		/* this is not a nested case where the same thread
		 * is trying to acqurire the same lock twice */
		mutex_lock(&dev_replace->lock);
		mutex_lock(&dev_replace->lock_management_lock);
		dev_replace->lock_owner = current->pid;
		atomic_inc(&dev_replace->nesting_level);
		mutex_unlock(&dev_replace->lock_management_lock);
		return;
	}

	mutex_lock(&dev_replace->lock_management_lock);
	if (atomic_read(&dev_replace->nesting_level) > 0 &&
	    dev_replace->lock_owner == current->pid) {
		WARN_ON(!mutex_is_locked(&dev_replace->lock));
		atomic_inc(&dev_replace->nesting_level);
		mutex_unlock(&dev_replace->lock_management_lock);
		return;
	}

	mutex_unlock(&dev_replace->lock_management_lock);
	goto acquire_lock;
}

void btrfs_dev_replace_unlock(struct btrfs_dev_replace *dev_replace)
{
	WARN_ON(!mutex_is_locked(&dev_replace->lock));
	mutex_lock(&dev_replace->lock_management_lock);
	WARN_ON(atomic_read(&dev_replace->nesting_level) < 1);
	WARN_ON(dev_replace->lock_owner != current->pid);
	atomic_dec(&dev_replace->nesting_level);
	if (atomic_read(&dev_replace->nesting_level) == 0) {
		dev_replace->lock_owner = 0;
		mutex_unlock(&dev_replace->lock_management_lock);
		mutex_unlock(&dev_replace->lock);
	} else {
		mutex_unlock(&dev_replace->lock_management_lock);
	}
}

void btrfs_bio_counter_inc_noblocked(struct btrfs_fs_info *fs_info)
{
	percpu_counter_inc(&fs_info->bio_counter);
}

void btrfs_bio_counter_dec(struct btrfs_fs_info *fs_info)
{
	percpu_counter_dec(&fs_info->bio_counter);

	if (waitqueue_active(&fs_info->replace_wait))
		wake_up(&fs_info->replace_wait);
}

void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info)
{
	DEFINE_WAIT(wait);
again:
	percpu_counter_inc(&fs_info->bio_counter);
	if (test_bit(BTRFS_FS_STATE_DEV_REPLACING, &fs_info->fs_state)) {
		btrfs_bio_counter_dec(fs_info);
		wait_event(fs_info->replace_wait,
			   !test_bit(BTRFS_FS_STATE_DEV_REPLACING,
				     &fs_info->fs_state));
		goto again;
	}

}