forked from kdave/btrfs-progs
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathmain.c
1955 lines (1755 loc) · 51 KB
/
main.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 "kerncompat.h"
#include <sys/stat.h>
#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <unistd.h>
#include <getopt.h>
#include <errno.h>
#include <stdbool.h>
#include <string.h>
#include <pthread.h>
#include <uuid/uuid.h>
#include <blkid/blkid.h>
#include "kernel-lib/list.h"
#include "kernel-lib/list_sort.h"
#include "kernel-lib/rbtree.h"
#include "kernel-lib/sizes.h"
#include "kernel-shared/accessors.h"
#include "kernel-shared/extent_io.h"
#include "kernel-shared/uapi/btrfs_tree.h"
#include "kernel-shared/ctree.h"
#include "kernel-shared/disk-io.h"
#include "kernel-shared/volumes.h"
#include "kernel-shared/transaction.h"
#include "kernel-shared/zoned.h"
#include "kernel-shared/uuid-tree.h"
#include "crypto/hash.h"
#include "common/defs.h"
#include "common/internal.h"
#include "common/messages.h"
#include "common/cpu-utils.h"
#include "common/utils.h"
#include "common/path-utils.h"
#include "common/device-utils.h"
#include "common/device-scan.h"
#include "common/help.h"
#include "common/rbtree-utils.h"
#include "common/parse-utils.h"
#include "common/fsfeatures.h"
#include "common/box.h"
#include "common/units.h"
#include "common/string-utils.h"
#include "common/string-table.h"
#include "common/root-tree-utils.h"
#include "cmds/commands.h"
#include "check/qgroup-verify.h"
#include "mkfs/common.h"
#include "mkfs/rootdir.h"
#include "libbtrfs/ctree.h"
struct mkfs_allocation {
u64 data;
u64 metadata;
u64 mixed;
u64 system;
};
static bool opt_zero_end = true;
static bool opt_discard = true;
static bool opt_zoned = true;
static int opt_oflags = O_RDWR;
struct prepare_device_progress {
int fd;
char *file;
u64 dev_byte_count;
u64 byte_count;
int ret;
};
static int create_metadata_block_groups(struct btrfs_root *root, bool mixed,
struct mkfs_allocation *allocation)
{
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_trans_handle *trans;
struct btrfs_space_info *sinfo;
u64 flags = BTRFS_BLOCK_GROUP_METADATA;
u64 chunk_start = 0;
u64 chunk_size = 0;
u64 system_group_size = BTRFS_MKFS_SYSTEM_GROUP_SIZE;
int ret;
if (btrfs_is_zoned(fs_info)) {
/* Two zones are reserved for superblock */
system_group_size = fs_info->zone_size;
}
if (mixed)
flags |= BTRFS_BLOCK_GROUP_DATA;
/* Create needed space info to trace extents reservation */
ret = update_space_info(fs_info, flags, 0, 0, &sinfo);
if (ret < 0)
return ret;
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
errno = -ret;
error_msg(ERROR_MSG_START_TRANS, "%m");
return ret;
}
root->fs_info->system_allocs = 1;
/*
* We already created the block group item for our temporary system
* chunk in make_btrfs(), so account for the size here.
*/
allocation->system += system_group_size;
if (ret)
return ret;
if (mixed) {
ret = btrfs_alloc_chunk(trans, fs_info,
&chunk_start, &chunk_size,
BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DATA);
if (ret == -ENOSPC) {
error("no space to allocate data/metadata chunk");
goto err;
}
if (ret)
return ret;
ret = btrfs_make_block_group(trans, fs_info, 0,
BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DATA,
chunk_start, chunk_size);
if (ret)
return ret;
allocation->mixed += chunk_size;
} else {
ret = btrfs_alloc_chunk(trans, fs_info,
&chunk_start, &chunk_size,
BTRFS_BLOCK_GROUP_METADATA);
if (ret == -ENOSPC) {
error("no space to allocate metadata chunk");
goto err;
}
if (ret)
return ret;
ret = btrfs_make_block_group(trans, fs_info, 0,
BTRFS_BLOCK_GROUP_METADATA,
chunk_start, chunk_size);
allocation->metadata += chunk_size;
if (ret)
return ret;
}
root->fs_info->system_allocs = 0;
ret = btrfs_commit_transaction(trans, root);
if (ret) {
errno = -ret;
error_msg(ERROR_MSG_COMMIT_TRANS, "%m");
}
err:
return ret;
}
static int create_data_block_groups(struct btrfs_trans_handle *trans,
struct btrfs_root *root, bool mixed,
struct mkfs_allocation *allocation)
{
struct btrfs_fs_info *fs_info = root->fs_info;
u64 chunk_start = 0;
u64 chunk_size = 0;
int ret = 0;
if (!mixed) {
struct btrfs_space_info *sinfo;
ret = update_space_info(fs_info, BTRFS_BLOCK_GROUP_DATA,
0, 0, &sinfo);
if (ret < 0)
return ret;
ret = btrfs_alloc_chunk(trans, fs_info,
&chunk_start, &chunk_size,
BTRFS_BLOCK_GROUP_DATA);
if (ret == -ENOSPC) {
error("no space to allocate data chunk");
goto err;
}
if (ret)
return ret;
ret = btrfs_make_block_group(trans, fs_info, 0,
BTRFS_BLOCK_GROUP_DATA,
chunk_start, chunk_size);
allocation->data += chunk_size;
if (ret)
return ret;
}
err:
return ret;
}
static int make_root_dir(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_key location;
int ret;
ret = btrfs_make_root_dir(trans, root->fs_info->tree_root,
BTRFS_ROOT_TREE_DIR_OBJECTID);
if (ret)
goto err;
ret = btrfs_make_root_dir(trans, root, BTRFS_FIRST_FREE_OBJECTID);
if (ret)
goto err;
memcpy(&location, &root->fs_info->fs_root->root_key, sizeof(location));
location.offset = (u64)-1;
ret = btrfs_insert_dir_item(trans, root->fs_info->tree_root,
"default", 7,
btrfs_super_root_dir(root->fs_info->super_copy),
&location, BTRFS_FT_DIR, 0);
if (ret)
goto err;
ret = btrfs_insert_inode_ref(trans, root->fs_info->tree_root,
"default", 7, location.objectid,
BTRFS_ROOT_TREE_DIR_OBJECTID, 0);
if (ret)
goto err;
err:
return ret;
}
static int __recow_root(struct btrfs_trans_handle *trans, struct btrfs_root *root)
{
struct btrfs_path path = { 0 };
struct btrfs_key key;
int ret;
key.objectid = 0;
key.type = 0;
key.offset = 0;
/* Get a path to the left-most leaves */
ret = btrfs_search_slot(NULL, root, &key, &path, 0, 0);
if (ret < 0)
return ret;
while (true) {
struct btrfs_key found_key;
/*
* Our parent nodes must not be newer than the leaf, thus if
* the leaf is as new as the transaction, no need to re-COW.
*/
if (btrfs_header_generation(path.nodes[0]) == trans->transid)
goto next;
/*
* Grab the key of current tree block and do a COW search to
* the current tree block.
*/
btrfs_item_key_to_cpu(path.nodes[0], &key, 0);
btrfs_release_path(&path);
/* This will ensure this leaf and all its parent get COWed */
ret = btrfs_search_slot(trans, root, &key, &path, 0, 1);
if (ret < 0)
goto out;
ret = 0;
btrfs_item_key_to_cpu(path.nodes[0], &found_key, 0);
UASSERT(btrfs_comp_cpu_keys(&key, &found_key) == 0);
next:
ret = btrfs_next_leaf(root, &path);
if (ret < 0)
goto out;
if (ret > 0) {
ret = 0;
goto out;
}
}
out:
btrfs_release_path(&path);
return ret;
}
static int recow_global_roots(struct btrfs_trans_handle *trans)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root;
struct rb_node *n;
int ret = 0;
for (n = rb_first(&fs_info->global_roots_tree); n; n = rb_next(n)) {
root = rb_entry(n, struct btrfs_root, rb_node);
ret = __recow_root(trans, root);
if (ret)
return ret;
}
return ret;
}
static int recow_roots(struct btrfs_trans_handle *trans,
struct btrfs_root *root)
{
struct btrfs_fs_info *info = root->fs_info;
int ret;
ret = __recow_root(trans, info->fs_root);
if (ret)
return ret;
ret = __recow_root(trans, info->tree_root);
if (ret)
return ret;
ret = __recow_root(trans, info->chunk_root);
if (ret)
return ret;
ret = __recow_root(trans, info->dev_root);
if (ret)
return ret;
if (btrfs_fs_compat_ro(info, BLOCK_GROUP_TREE)) {
ret = __recow_root(trans, info->block_group_root);
if (ret)
return ret;
}
ret = recow_global_roots(trans);
if (ret)
return ret;
return 0;
}
static int create_one_raid_group(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 type,
struct mkfs_allocation *allocation)
{
struct btrfs_fs_info *fs_info = root->fs_info;
u64 chunk_start;
u64 chunk_size;
int ret;
ret = btrfs_alloc_chunk(trans, fs_info,
&chunk_start, &chunk_size, type);
if (ret == -ENOSPC) {
error("not enough free space to allocate chunk");
exit(1);
}
if (ret)
return ret;
ret = btrfs_make_block_group(trans, fs_info, 0,
type, chunk_start, chunk_size);
type &= BTRFS_BLOCK_GROUP_TYPE_MASK;
if (type == BTRFS_BLOCK_GROUP_DATA) {
allocation->data += chunk_size;
} else if (type == BTRFS_BLOCK_GROUP_METADATA) {
allocation->metadata += chunk_size;
} else if (type == BTRFS_BLOCK_GROUP_SYSTEM) {
allocation->system += chunk_size;
} else if (type ==
(BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA)) {
allocation->mixed += chunk_size;
} else {
error("unrecognized profile type: 0x%llx", type);
ret = -EINVAL;
}
return ret;
}
static int create_raid_groups(struct btrfs_trans_handle *trans,
struct btrfs_root *root, u64 data_profile,
u64 metadata_profile, bool mixed,
struct mkfs_allocation *allocation)
{
int ret = 0;
if (metadata_profile) {
u64 meta_flags = BTRFS_BLOCK_GROUP_METADATA;
ret = create_one_raid_group(trans, root,
BTRFS_BLOCK_GROUP_SYSTEM |
metadata_profile, allocation);
if (ret)
return ret;
if (mixed)
meta_flags |= BTRFS_BLOCK_GROUP_DATA;
ret = create_one_raid_group(trans, root, meta_flags |
metadata_profile, allocation);
if (ret)
return ret;
}
if (!mixed && data_profile) {
ret = create_one_raid_group(trans, root,
BTRFS_BLOCK_GROUP_DATA |
data_profile, allocation);
if (ret)
return ret;
}
return ret;
}
static const char * const mkfs_usage[] = {
"mkfs.btrfs [options] <dev> [<dev...>]",
"Create a BTRFS filesystem on a device or multiple devices",
"",
"Allocation profiles:",
OPTLINE("-d|--data PROFILE", "data profile, raid0, raid1, raid1c3, raid1c4, raid5, raid6, raid10, dup or single"),
OPTLINE("-m|--metadata PROFILE", "metadata profile, values like for data profile"),
OPTLINE("-M|--mixed","mix metadata and data together"),
"Features:",
OPTLINE("--csum TYPE", ""),
OPTLINE("--checksum TYPE", "checksum algorithm to use, crc32c (default), xxhash, sha256, blake2"),
OPTLINE("-n|--nodesize SIZE", "size of btree nodes"),
OPTLINE("-s|--sectorsize SIZE", "data block size (may not be mountable by current kernel)"),
OPTLINE("-O|--features LIST", "comma separated list of filesystem features (use '-O list-all' to list features)"),
OPTLINE("-L|--label LABEL", "set the filesystem label"),
OPTLINE("-U|--uuid UUID", "specify the filesystem UUID (must be unique for a filesystem with multiple devices)"),
OPTLINE("--device-uuid UUID", "Specify the filesystem device UUID (a.k.a sub-uuid) (for single device filesystem only)"),
"Creation:",
OPTLINE("-b|--byte-count SIZE", "set size of each device to SIZE (filesystem size is sum of all device sizes)"),
OPTLINE("-r|--rootdir DIR", "copy files from DIR to the image root directory"),
OPTLINE("--shrink", "(with --rootdir) shrink the filled filesystem to minimal size"),
OPTLINE("-K|--nodiscard", "do not perform whole device TRIM"),
OPTLINE("-f|--force", "force overwrite of existing filesystem"),
"General:",
OPTLINE("-q|--quiet", "no messages except errors"),
OPTLINE("-v|--verbose", "increase verbosity level, default is 1"),
OPTLINE("-V|--version", "print the mkfs.btrfs version and exit"),
OPTLINE("--help", "print this help and exit"),
"Deprecated:",
OPTLINE("-l|--leafsize SIZE", "removed in 6.0, use --nodesize"),
OPTLINE("-R|--runtime-features LIST", "removed in 6.3, use -O|--features"),
NULL
};
static const struct cmd_struct mkfs_cmd = {
.usagestr = mkfs_usage
};
static int zero_output_file(int out_fd, u64 size)
{
int loop_num;
u64 location = 0;
char buf[SZ_4K];
int ret = 0, i;
ssize_t written;
memset(buf, 0, SZ_4K);
/* Only zero out the first 1M */
loop_num = SZ_1M / SZ_4K;
for (i = 0; i < loop_num; i++) {
written = pwrite(out_fd, buf, SZ_4K, location);
if (written != SZ_4K)
ret = -EIO;
location += SZ_4K;
}
/* Then enlarge the file to size */
written = pwrite(out_fd, buf, 1, size - 1);
if (written < 1)
ret = -EIO;
return ret;
}
static int _cmp_device_by_id(void *priv, struct list_head *a,
struct list_head *b)
{
return list_entry(a, struct btrfs_device, dev_list)->devid -
list_entry(b, struct btrfs_device, dev_list)->devid;
}
static void list_all_devices(struct btrfs_root *root, bool is_zoned)
{
struct btrfs_fs_devices *fs_devices;
struct btrfs_device *device;
int number_of_devices = 0;
struct string_table *tab;
int row, col;
fs_devices = root->fs_info->fs_devices;
list_for_each_entry(device, &fs_devices->devices, dev_list)
number_of_devices++;
list_sort(NULL, &fs_devices->devices, _cmp_device_by_id);
printf("Number of devices: %d\n", number_of_devices);
printf("Devices:\n");
if (is_zoned)
tab = table_create(4, number_of_devices + 1);
else
tab = table_create(3, number_of_devices + 1);
tab->spacing = STRING_TABLE_SPACING_2;
col = 0;
table_printf(tab, col++, 0, "> ID");
table_printf(tab, col++, 0, "> SIZE");
if (is_zoned)
table_printf(tab, col++, 0, ">ZONES");
table_printf(tab, col++, 0, "<PATH");
row = 1;
list_for_each_entry(device, &fs_devices->devices, dev_list) {
col = 0;
table_printf(tab, col++, row, ">%llu", device->devid);
table_printf(tab, col++, row, ">%s", pretty_size(device->total_bytes));
if (is_zoned)
table_printf(tab, col++, row, ">%u", device->zone_info->nr_zones);
table_printf(tab, col++, row, "<%s", device->name);
row++;
}
table_dump(tab);
printf("\n");
table_free(tab);
}
static bool is_temp_block_group(struct extent_buffer *node,
struct btrfs_block_group_item *bgi,
u64 data_profile, u64 meta_profile,
u64 sys_profile)
{
u64 flag = btrfs_block_group_flags(node, bgi);
u64 flag_type = flag & BTRFS_BLOCK_GROUP_TYPE_MASK;
u64 flag_profile = flag & BTRFS_BLOCK_GROUP_PROFILE_MASK;
u64 used = btrfs_block_group_used(node, bgi);
/*
* Chunks meets all the following conditions is a temp chunk
* 1) Empty chunk
* Temp chunk is always empty.
*
* 2) profile mismatch with mkfs profile.
* Temp chunk is always in SINGLE
*
* 3) Size differs with mkfs_alloc
* Special case for SINGLE/SINGLE btrfs.
* In that case, temp data chunk and real data chunk are always empty.
* So we need to use mkfs_alloc to be sure which chunk is the newly
* allocated.
*
* Normally, new chunk size is equal to mkfs one (One chunk)
* If it has multiple chunks, we just refuse to delete any one.
* As they are all single, so no real problem will happen.
* So only use condition 1) and 2) to judge them.
*/
if (used != 0)
return false;
switch (flag_type) {
case BTRFS_BLOCK_GROUP_DATA:
case BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA:
data_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
if (flag_profile != data_profile)
return true;
break;
case BTRFS_BLOCK_GROUP_METADATA:
meta_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
if (flag_profile != meta_profile)
return true;
break;
case BTRFS_BLOCK_GROUP_SYSTEM:
sys_profile &= BTRFS_BLOCK_GROUP_PROFILE_MASK;
if (flag_profile != sys_profile)
return true;
break;
}
return false;
}
/* Note: if current is a block group, it will skip it anyway */
static int next_block_group(struct btrfs_root *root,
struct btrfs_path *path)
{
struct btrfs_key key;
int ret = 0;
while (1) {
ret = btrfs_next_item(root, path);
if (ret)
goto out;
btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
if (key.type == BTRFS_BLOCK_GROUP_ITEM_KEY)
goto out;
}
out:
return ret;
}
/* This function will cleanup */
static int cleanup_temp_chunks(struct btrfs_fs_info *fs_info,
struct mkfs_allocation *alloc,
u64 data_profile, u64 meta_profile,
u64 sys_profile)
{
struct btrfs_trans_handle *trans = NULL;
struct btrfs_block_group_item *bgi;
struct btrfs_root *root = btrfs_block_group_root(fs_info);
struct btrfs_key key;
struct btrfs_key found_key;
struct btrfs_path path = { 0 };
int ret = 0;
trans = btrfs_start_transaction(root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
errno = -ret;
error_msg(ERROR_MSG_START_TRANS, "%m");
return ret;
}
key.objectid = 0;
key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
key.offset = 0;
while (1) {
/*
* as the rest of the loop may modify the tree, we need to
* start a new search each time.
*/
ret = btrfs_search_slot(trans, root, &key, &path, 0, 0);
if (ret < 0)
goto out;
/* Don't pollute ret for >0 case */
if (ret > 0)
ret = 0;
btrfs_item_key_to_cpu(path.nodes[0], &found_key,
path.slots[0]);
if (found_key.objectid < key.objectid)
goto out;
if (found_key.type != BTRFS_BLOCK_GROUP_ITEM_KEY) {
ret = next_block_group(root, &path);
if (ret < 0)
goto out;
if (ret > 0) {
ret = 0;
goto out;
}
btrfs_item_key_to_cpu(path.nodes[0], &found_key,
path.slots[0]);
}
bgi = btrfs_item_ptr(path.nodes[0], path.slots[0],
struct btrfs_block_group_item);
if (is_temp_block_group(path.nodes[0], bgi,
data_profile, meta_profile,
sys_profile)) {
u64 flags = btrfs_block_group_flags(path.nodes[0], bgi);
ret = btrfs_remove_block_group(trans,
found_key.objectid, found_key.offset);
if (ret < 0)
goto out;
if ((flags & BTRFS_BLOCK_GROUP_TYPE_MASK) ==
BTRFS_BLOCK_GROUP_DATA)
alloc->data -= found_key.offset;
else if ((flags & BTRFS_BLOCK_GROUP_TYPE_MASK) ==
BTRFS_BLOCK_GROUP_METADATA)
alloc->metadata -= found_key.offset;
else if ((flags & BTRFS_BLOCK_GROUP_TYPE_MASK) ==
BTRFS_BLOCK_GROUP_SYSTEM)
alloc->system -= found_key.offset;
else if ((flags & BTRFS_BLOCK_GROUP_TYPE_MASK) ==
(BTRFS_BLOCK_GROUP_METADATA |
BTRFS_BLOCK_GROUP_DATA))
alloc->mixed -= found_key.offset;
}
btrfs_release_path(&path);
key.objectid = found_key.objectid + found_key.offset;
}
out:
if (trans) {
ret = btrfs_commit_transaction(trans, root);
if (ret) {
errno = -ret;
error_msg(ERROR_MSG_COMMIT_TRANS, "%m");
}
}
btrfs_release_path(&path);
return ret;
}
/*
* Just update chunk allocation info, since --rootdir may allocate new
* chunks which is not updated in @allocation structure.
*/
static void update_chunk_allocation(struct btrfs_fs_info *fs_info,
struct mkfs_allocation *allocation)
{
struct btrfs_block_group *bg_cache;
const u64 mixed_flag = BTRFS_BLOCK_GROUP_DATA | BTRFS_BLOCK_GROUP_METADATA;
u64 search_start = 0;
allocation->mixed = 0;
allocation->data = 0;
allocation->metadata = 0;
allocation->system = 0;
while (1) {
bg_cache = btrfs_lookup_first_block_group(fs_info,
search_start);
if (!bg_cache)
break;
if ((bg_cache->flags & mixed_flag) == mixed_flag)
allocation->mixed += bg_cache->length;
else if (bg_cache->flags & BTRFS_BLOCK_GROUP_DATA)
allocation->data += bg_cache->length;
else if (bg_cache->flags & BTRFS_BLOCK_GROUP_METADATA)
allocation->metadata += bg_cache->length;
else
allocation->system += bg_cache->length;
search_start = bg_cache->start + bg_cache->length;
}
}
static int create_global_root(struct btrfs_trans_handle *trans, u64 objectid,
int root_id)
{
struct btrfs_fs_info *fs_info = trans->fs_info;
struct btrfs_root *root;
struct btrfs_key key = {
.objectid = objectid,
.type = BTRFS_ROOT_ITEM_KEY,
.offset = root_id,
};
int ret = 0;
root = btrfs_create_tree(trans, &key);
if (IS_ERR(root)) {
ret = PTR_ERR(root);
goto out;
}
ret = btrfs_global_root_insert(fs_info, root);
out:
if (ret)
btrfs_abort_transaction(trans, ret);
return ret;
}
static int create_global_roots(struct btrfs_trans_handle *trans,
int nr_global_roots)
{
int ret, i;
for (i = 1; i < nr_global_roots; i++) {
ret = create_global_root(trans, BTRFS_EXTENT_TREE_OBJECTID, i);
if (ret)
return ret;
ret = create_global_root(trans, BTRFS_CSUM_TREE_OBJECTID, i);
if (ret)
return ret;
ret = create_global_root(trans, BTRFS_FREE_SPACE_TREE_OBJECTID, i);
if (ret)
return ret;
}
btrfs_set_super_nr_global_roots(trans->fs_info->super_copy,
nr_global_roots);
return 0;
}
static int insert_qgroup_items(struct btrfs_trans_handle *trans,
struct btrfs_fs_info *fs_info,
u64 qgroupid)
{
struct btrfs_path path = { 0 };
struct btrfs_root *quota_root = fs_info->quota_root;
struct btrfs_key key;
int ret;
if (qgroupid >> BTRFS_QGROUP_LEVEL_SHIFT) {
error("qgroup level other than 0 is not supported yet");
return -ENOTTY;
}
key.objectid = 0;
key.type = BTRFS_QGROUP_INFO_KEY;
key.offset = qgroupid;
ret = btrfs_insert_empty_item(trans, quota_root, &path, &key,
sizeof(struct btrfs_qgroup_info_item));
btrfs_release_path(&path);
if (ret < 0)
return ret;
key.objectid = 0;
key.type = BTRFS_QGROUP_LIMIT_KEY;
key.offset = qgroupid;
ret = btrfs_insert_empty_item(trans, quota_root, &path, &key,
sizeof(struct btrfs_qgroup_limit_item));
btrfs_release_path(&path);
return ret;
}
/*
* Workaround for squota so the enable_gen can be properly used.
*/
static int touch_root_subvol(struct btrfs_fs_info *fs_info)
{
struct btrfs_trans_handle *trans;
struct btrfs_key key = {
.objectid = BTRFS_FIRST_FREE_OBJECTID,
.type = BTRFS_INODE_ITEM_KEY,
.offset = 0,
};
struct extent_buffer *leaf;
int slot;
struct btrfs_path path = { 0 };
int ret;
trans = btrfs_start_transaction(fs_info->fs_root, 1);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
errno = -ret;
error_msg(ERROR_MSG_START_TRANS, "%m");
return ret;
}
ret = btrfs_search_slot(trans, fs_info->fs_root, &key, &path, 0, 1);
if (ret)
goto fail;
leaf = path.nodes[0];
slot = path.slots[0];
btrfs_item_key_to_cpu(leaf, &key, slot);
btrfs_mark_buffer_dirty(leaf);
ret = btrfs_commit_transaction(trans, fs_info->fs_root);
if (ret < 0) {
errno = -ret;
error_msg(ERROR_MSG_COMMIT_TRANS, "%m");
return ret;
}
btrfs_release_path(&path);
return 0;
fail:
btrfs_abort_transaction(trans, ret);
btrfs_release_path(&path);
return ret;
}
static int setup_quota_root(struct btrfs_fs_info *fs_info)
{
struct btrfs_trans_handle *trans;
struct btrfs_qgroup_status_item *qsi;
struct btrfs_root *quota_root;
struct btrfs_path path = { 0 };
struct btrfs_key key;
int qgroup_repaired = 0;
bool simple = btrfs_fs_incompat(fs_info, SIMPLE_QUOTA);
int flags;
int ret;
/* One to modify tree root, one for quota root */
trans = btrfs_start_transaction(fs_info->tree_root, 2);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
errno = -ret;
error_msg(ERROR_MSG_START_TRANS, "%m");
return ret;
}
ret = btrfs_create_root(trans, fs_info, BTRFS_QUOTA_TREE_OBJECTID);
if (ret < 0) {
error("failed to create quota root: %d (%m)", ret);
goto fail;
}
quota_root = fs_info->quota_root;
key.objectid = 0;
key.type = BTRFS_QGROUP_STATUS_KEY;
key.offset = 0;
ret = btrfs_insert_empty_item(trans, quota_root, &path, &key,
sizeof(*qsi));
if (ret < 0) {
error("failed to insert qgroup status item: %d (%m)", ret);
goto fail;
}
qsi = btrfs_item_ptr(path.nodes[0], path.slots[0],
struct btrfs_qgroup_status_item);
btrfs_set_qgroup_status_generation(path.nodes[0], qsi, trans->transid);
btrfs_set_qgroup_status_rescan(path.nodes[0], qsi, 0);
flags = BTRFS_QGROUP_STATUS_FLAG_ON;
if (simple) {
btrfs_set_qgroup_status_enable_gen(path.nodes[0], qsi, trans->transid);
flags |= BTRFS_QGROUP_STATUS_FLAG_SIMPLE_MODE;
}
else {
flags |= BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT;
}
btrfs_set_qgroup_status_version(path.nodes[0], qsi, 1);
btrfs_set_qgroup_status_flags(path.nodes[0], qsi, flags);
btrfs_release_path(&path);
/* Currently mkfs will only create one subvolume */
ret = insert_qgroup_items(trans, fs_info, BTRFS_FS_TREE_OBJECTID);
if (ret < 0) {
error("failed to insert qgroup items: %d (%m)", ret);
goto fail;
}
ret = btrfs_commit_transaction(trans, fs_info->tree_root);
if (ret < 0) {
errno = -ret;
error_msg(ERROR_MSG_COMMIT_TRANS, "%m");
return ret;
}
/* Hack to count the default subvol metadata by dirtying it */
if (simple) {
ret = touch_root_subvol(fs_info);
if (ret) {
error("failed to touch root dir for simple quota accounting %d (%m)", ret);
goto fail;
}
}
/*
* Qgroup is setup but with wrong info, use qgroup-verify
* infrastructure to repair them. (Just acts as offline rescan)
*/
ret = qgroup_verify_all(fs_info);
if (ret < 0) {
error("qgroup rescan failed: %d (%m)", ret);
return ret;
}
ret = repair_qgroups(fs_info, &qgroup_repaired, true);
if (ret < 0)
error("failed to fill qgroup info: %d (%m)", ret);
return ret;
fail:
btrfs_abort_transaction(trans, ret);
return ret;
}
static int setup_raid_stripe_tree_root(struct btrfs_fs_info *fs_info)
{
struct btrfs_trans_handle *trans;
struct btrfs_root *stripe_root;
struct btrfs_key key = {
.objectid = BTRFS_RAID_STRIPE_TREE_OBJECTID,
.type = BTRFS_ROOT_ITEM_KEY,
};
int ret;
trans = btrfs_start_transaction(fs_info->tree_root, 0);
if (IS_ERR(trans)) {
ret = PTR_ERR(trans);
errno = -ret;
error_msg(ERROR_MSG_START_TRANS, "%m");
return ret;
}
stripe_root = btrfs_create_tree(trans, &key);
if (IS_ERR(stripe_root)) {
ret = PTR_ERR(stripe_root);
btrfs_abort_transaction(trans, ret);
return ret;
}
fs_info->stripe_root = stripe_root;
add_root_to_dirty_list(stripe_root);
ret = btrfs_commit_transaction(trans, fs_info->tree_root);
if (ret) {
errno = -ret;
error_msg(ERROR_MSG_COMMIT_TRANS, "%m");
return ret;
}
return 0;
}
/* Thread callback for device preparation */
static void *prepare_one_device(void *ctx)
{
struct prepare_device_progress *prepare_ctx = ctx;