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
|
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* 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 as
* published by the Free Software Foundation.
*
* This program is distributed in the hope that it would 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 the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_fs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_bit.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_trace.h"
#include "xfs_cksum.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
/*
* Physical superblock buffer manipulations. Shared with libxfs in userspace.
*/
/*
* Reference counting access wrappers to the perag structures.
* Because we never free per-ag structures, the only thing we
* have to protect against changes is the tree structure itself.
*/
struct xfs_perag *
xfs_perag_get(
struct xfs_mount *mp,
xfs_agnumber_t agno)
{
struct xfs_perag *pag;
int ref = 0;
rcu_read_lock();
pag = radix_tree_lookup(&mp->m_perag_tree, agno);
if (pag) {
ASSERT(atomic_read(&pag->pag_ref) >= 0);
ref = atomic_inc_return(&pag->pag_ref);
}
rcu_read_unlock();
trace_xfs_perag_get(mp, agno, ref, _RET_IP_);
return pag;
}
/*
* search from @first to find the next perag with the given tag set.
*/
struct xfs_perag *
xfs_perag_get_tag(
struct xfs_mount *mp,
xfs_agnumber_t first,
int tag)
{
struct xfs_perag *pag;
int found;
int ref;
rcu_read_lock();
found = radix_tree_gang_lookup_tag(&mp->m_perag_tree,
(void **)&pag, first, 1, tag);
if (found <= 0) {
rcu_read_unlock();
return NULL;
}
ref = atomic_inc_return(&pag->pag_ref);
rcu_read_unlock();
trace_xfs_perag_get_tag(mp, pag->pag_agno, ref, _RET_IP_);
return pag;
}
void
xfs_perag_put(
struct xfs_perag *pag)
{
int ref;
ASSERT(atomic_read(&pag->pag_ref) > 0);
ref = atomic_dec_return(&pag->pag_ref);
trace_xfs_perag_put(pag->pag_mount, pag->pag_agno, ref, _RET_IP_);
}
/*
* Check the validity of the SB found.
*/
STATIC int
xfs_mount_validate_sb(
xfs_mount_t *mp,
xfs_sb_t *sbp,
bool check_inprogress,
bool check_version)
{
if (sbp->sb_magicnum != XFS_SB_MAGIC) {
xfs_warn(mp, "bad magic number");
return -EWRONGFS;
}
if (!xfs_sb_good_version(sbp)) {
xfs_warn(mp, "bad version");
return -EWRONGFS;
}
/*
* Version 5 superblock feature mask validation. Reject combinations the
* kernel cannot support up front before checking anything else. For
* write validation, we don't need to check feature masks.
*/
if (check_version && XFS_SB_VERSION_NUM(sbp) == XFS_SB_VERSION_5) {
if (xfs_sb_has_compat_feature(sbp,
XFS_SB_FEAT_COMPAT_UNKNOWN)) {
xfs_warn(mp,
"Superblock has unknown compatible features (0x%x) enabled.\n"
"Using a more recent kernel is recommended.",
(sbp->sb_features_compat &
XFS_SB_FEAT_COMPAT_UNKNOWN));
}
if (xfs_sb_has_ro_compat_feature(sbp,
XFS_SB_FEAT_RO_COMPAT_UNKNOWN)) {
xfs_alert(mp,
"Superblock has unknown read-only compatible features (0x%x) enabled.",
(sbp->sb_features_ro_compat &
XFS_SB_FEAT_RO_COMPAT_UNKNOWN));
if (!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_warn(mp,
"Attempted to mount read-only compatible filesystem read-write.\n"
"Filesystem can only be safely mounted read only.");
return -EINVAL;
}
}
if (xfs_sb_has_incompat_feature(sbp,
XFS_SB_FEAT_INCOMPAT_UNKNOWN)) {
xfs_warn(mp,
"Superblock has unknown incompatible features (0x%x) enabled.\n"
"Filesystem can not be safely mounted by this kernel.",
(sbp->sb_features_incompat &
XFS_SB_FEAT_INCOMPAT_UNKNOWN));
return -EINVAL;
}
}
if (xfs_sb_version_has_pquotino(sbp)) {
if (sbp->sb_qflags & (XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD)) {
xfs_notice(mp,
"Version 5 of Super block has XFS_OQUOTA bits.");
return -EFSCORRUPTED;
}
} else if (sbp->sb_qflags & (XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD |
XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD)) {
xfs_notice(mp,
"Superblock earlier than Version 5 has XFS_[PQ]UOTA_{ENFD|CHKD} bits.");
return -EFSCORRUPTED;
}
/*
* Full inode chunks must be aligned to inode chunk size when
* sparse inodes are enabled to support the sparse chunk
* allocation algorithm and prevent overlapping inode records.
*/
if (xfs_sb_version_hassparseinodes(sbp)) {
uint32_t align;
xfs_alert(mp,
"EXPERIMENTAL sparse inode feature enabled. Use at your own risk!");
align = XFS_INODES_PER_CHUNK * sbp->sb_inodesize
>> sbp->sb_blocklog;
if (sbp->sb_inoalignmt != align) {
xfs_warn(mp,
"Inode block alignment (%u) must match chunk size (%u) for sparse inodes.",
sbp->sb_inoalignmt, align);
return -EINVAL;
}
}
if (unlikely(
sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
xfs_warn(mp,
"filesystem is marked as having an external log; "
"specify logdev on the mount command line.");
return -EINVAL;
}
if (unlikely(
sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
xfs_warn(mp,
"filesystem is marked as having an internal log; "
"do not specify logdev on the mount command line.");
return -EINVAL;
}
/*
* More sanity checking. Most of these were stolen directly from
* xfs_repair.
*/
if (unlikely(
sbp->sb_agcount <= 0 ||
sbp->sb_sectsize < XFS_MIN_SECTORSIZE ||
sbp->sb_sectsize > XFS_MAX_SECTORSIZE ||
sbp->sb_sectlog < XFS_MIN_SECTORSIZE_LOG ||
sbp->sb_sectlog > XFS_MAX_SECTORSIZE_LOG ||
sbp->sb_sectsize != (1 << sbp->sb_sectlog) ||
sbp->sb_blocksize < XFS_MIN_BLOCKSIZE ||
sbp->sb_blocksize > XFS_MAX_BLOCKSIZE ||
sbp->sb_blocklog < XFS_MIN_BLOCKSIZE_LOG ||
sbp->sb_blocklog > XFS_MAX_BLOCKSIZE_LOG ||
sbp->sb_blocksize != (1 << sbp->sb_blocklog) ||
sbp->sb_dirblklog > XFS_MAX_BLOCKSIZE_LOG ||
sbp->sb_inodesize < XFS_DINODE_MIN_SIZE ||
sbp->sb_inodesize > XFS_DINODE_MAX_SIZE ||
sbp->sb_inodelog < XFS_DINODE_MIN_LOG ||
sbp->sb_inodelog > XFS_DINODE_MAX_LOG ||
sbp->sb_inodesize != (1 << sbp->sb_inodelog) ||
sbp->sb_logsunit > XLOG_MAX_RECORD_BSIZE ||
sbp->sb_inopblock != howmany(sbp->sb_blocksize,sbp->sb_inodesize) ||
(sbp->sb_blocklog - sbp->sb_inodelog != sbp->sb_inopblog) ||
(sbp->sb_rextsize * sbp->sb_blocksize > XFS_MAX_RTEXTSIZE) ||
(sbp->sb_rextsize * sbp->sb_blocksize < XFS_MIN_RTEXTSIZE) ||
(sbp->sb_imax_pct > 100 /* zero sb_imax_pct is valid */) ||
sbp->sb_dblocks == 0 ||
sbp->sb_dblocks > XFS_MAX_DBLOCKS(sbp) ||
sbp->sb_dblocks < XFS_MIN_DBLOCKS(sbp) ||
sbp->sb_shared_vn != 0)) {
xfs_notice(mp, "SB sanity check failed");
return -EFSCORRUPTED;
}
/*
* Until this is fixed only page-sized or smaller data blocks work.
*/
if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
xfs_warn(mp,
"File system with blocksize %d bytes. "
"Only pagesize (%ld) or less will currently work.",
sbp->sb_blocksize, PAGE_SIZE);
return -ENOSYS;
}
/*
* Currently only very few inode sizes are supported.
*/
switch (sbp->sb_inodesize) {
case 256:
case 512:
case 1024:
case 2048:
break;
default:
xfs_warn(mp, "inode size of %d bytes not supported",
sbp->sb_inodesize);
return -ENOSYS;
}
if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
xfs_warn(mp,
"file system too large to be mounted on this system.");
return -EFBIG;
}
if (check_inprogress && sbp->sb_inprogress) {
xfs_warn(mp, "Offline file system operation in progress!");
return -EFSCORRUPTED;
}
return 0;
}
void
xfs_sb_quota_from_disk(struct xfs_sb *sbp)
{
/*
* older mkfs doesn't initialize quota inodes to NULLFSINO. This
* leads to in-core values having two different values for a quota
* inode to be invalid: 0 and NULLFSINO. Change it to a single value
* NULLFSINO.
*
* Note that this change affect only the in-core values. These
* values are not written back to disk unless any quota information
* is written to the disk. Even in that case, sb_pquotino field is
* not written to disk unless the superblock supports pquotino.
*/
if (sbp->sb_uquotino == 0)
sbp->sb_uquotino = NULLFSINO;
if (sbp->sb_gquotino == 0)
sbp->sb_gquotino = NULLFSINO;
if (sbp->sb_pquotino == 0)
sbp->sb_pquotino = NULLFSINO;
/*
* We need to do these manipilations only if we are working
* with an older version of on-disk superblock.
*/
if (xfs_sb_version_has_pquotino(sbp))
return;
if (sbp->sb_qflags & XFS_OQUOTA_ENFD)
sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ?
XFS_PQUOTA_ENFD : XFS_GQUOTA_ENFD;
if (sbp->sb_qflags & XFS_OQUOTA_CHKD)
sbp->sb_qflags |= (sbp->sb_qflags & XFS_PQUOTA_ACCT) ?
XFS_PQUOTA_CHKD : XFS_GQUOTA_CHKD;
sbp->sb_qflags &= ~(XFS_OQUOTA_ENFD | XFS_OQUOTA_CHKD);
if (sbp->sb_qflags & XFS_PQUOTA_ACCT) {
/*
* In older version of superblock, on-disk superblock only
* has sb_gquotino, and in-core superblock has both sb_gquotino
* and sb_pquotino. But, only one of them is supported at any
* point of time. So, if PQUOTA is set in disk superblock,
* copy over sb_gquotino to sb_pquotino.
*/
sbp->sb_pquotino = sbp->sb_gquotino;
sbp->sb_gquotino = NULLFSINO;
}
}
static void
__xfs_sb_from_disk(
struct xfs_sb *to,
xfs_dsb_t *from,
bool convert_xquota)
{
to->sb_magicnum = be32_to_cpu(from->sb_magicnum);
to->sb_blocksize = be32_to_cpu(from->sb_blocksize);
to->sb_dblocks = be64_to_cpu(from->sb_dblocks);
to->sb_rblocks = be64_to_cpu(from->sb_rblocks);
to->sb_rextents = be64_to_cpu(from->sb_rextents);
memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid));
to->sb_logstart = be64_to_cpu(from->sb_logstart);
to->sb_rootino = be64_to_cpu(from->sb_rootino);
to->sb_rbmino = be64_to_cpu(from->sb_rbmino);
to->sb_rsumino = be64_to_cpu(from->sb_rsumino);
to->sb_rextsize = be32_to_cpu(from->sb_rextsize);
to->sb_agblocks = be32_to_cpu(from->sb_agblocks);
to->sb_agcount = be32_to_cpu(from->sb_agcount);
to->sb_rbmblocks = be32_to_cpu(from->sb_rbmblocks);
to->sb_logblocks = be32_to_cpu(from->sb_logblocks);
to->sb_versionnum = be16_to_cpu(from->sb_versionnum);
to->sb_sectsize = be16_to_cpu(from->sb_sectsize);
to->sb_inodesize = be16_to_cpu(from->sb_inodesize);
to->sb_inopblock = be16_to_cpu(from->sb_inopblock);
memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname));
to->sb_blocklog = from->sb_blocklog;
to->sb_sectlog = from->sb_sectlog;
to->sb_inodelog = from->sb_inodelog;
to->sb_inopblog = from->sb_inopblog;
to->sb_agblklog = from->sb_agblklog;
to->sb_rextslog = from->sb_rextslog;
to->sb_inprogress = from->sb_inprogress;
to->sb_imax_pct = from->sb_imax_pct;
to->sb_icount = be64_to_cpu(from->sb_icount);
to->sb_ifree = be64_to_cpu(from->sb_ifree);
to->sb_fdblocks = be64_to_cpu(from->sb_fdblocks);
to->sb_frextents = be64_to_cpu(from->sb_frextents);
to->sb_uquotino = be64_to_cpu(from->sb_uquotino);
to->sb_gquotino = be64_to_cpu(from->sb_gquotino);
to->sb_qflags = be16_to_cpu(from->sb_qflags);
to->sb_flags = from->sb_flags;
to->sb_shared_vn = from->sb_shared_vn;
to->sb_inoalignmt = be32_to_cpu(from->sb_inoalignmt);
to->sb_unit = be32_to_cpu(from->sb_unit);
to->sb_width = be32_to_cpu(from->sb_width);
to->sb_dirblklog = from->sb_dirblklog;
to->sb_logsectlog = from->sb_logsectlog;
to->sb_logsectsize = be16_to_cpu(from->sb_logsectsize);
to->sb_logsunit = be32_to_cpu(from->sb_logsunit);
to->sb_features2 = be32_to_cpu(from->sb_features2);
to->sb_bad_features2 = be32_to_cpu(from->sb_bad_features2);
to->sb_features_compat = be32_to_cpu(from->sb_features_compat);
to->sb_features_ro_compat = be32_to_cpu(from->sb_features_ro_compat);
to->sb_features_incompat = be32_to_cpu(from->sb_features_incompat);
to->sb_features_log_incompat =
be32_to_cpu(from->sb_features_log_incompat);
/* crc is only used on disk, not in memory; just init to 0 here. */
to->sb_crc = 0;
to->sb_spino_align = be32_to_cpu(from->sb_spino_align);
to->sb_pquotino = be64_to_cpu(from->sb_pquotino);
to->sb_lsn = be64_to_cpu(from->sb_lsn);
/*
* sb_meta_uuid is only on disk if it differs from sb_uuid and the
* feature flag is set; if not set we keep it only in memory.
*/
if (xfs_sb_version_hasmetauuid(to))
uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
else
uuid_copy(&to->sb_meta_uuid, &from->sb_uuid);
/* Convert on-disk flags to in-memory flags? */
if (convert_xquota)
xfs_sb_quota_from_disk(to);
}
void
xfs_sb_from_disk(
struct xfs_sb *to,
xfs_dsb_t *from)
{
__xfs_sb_from_disk(to, from, true);
}
static void
xfs_sb_quota_to_disk(
struct xfs_dsb *to,
struct xfs_sb *from)
{
__uint16_t qflags = from->sb_qflags;
to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
if (xfs_sb_version_has_pquotino(from)) {
to->sb_qflags = cpu_to_be16(from->sb_qflags);
to->sb_gquotino = cpu_to_be64(from->sb_gquotino);
to->sb_pquotino = cpu_to_be64(from->sb_pquotino);
return;
}
/*
* The in-core version of sb_qflags do not have XFS_OQUOTA_*
* flags, whereas the on-disk version does. So, convert incore
* XFS_{PG}QUOTA_* flags to on-disk XFS_OQUOTA_* flags.
*/
qflags &= ~(XFS_PQUOTA_ENFD | XFS_PQUOTA_CHKD |
XFS_GQUOTA_ENFD | XFS_GQUOTA_CHKD);
if (from->sb_qflags &
(XFS_PQUOTA_ENFD | XFS_GQUOTA_ENFD))
qflags |= XFS_OQUOTA_ENFD;
if (from->sb_qflags &
(XFS_PQUOTA_CHKD | XFS_GQUOTA_CHKD))
qflags |= XFS_OQUOTA_CHKD;
to->sb_qflags = cpu_to_be16(qflags);
/*
* GQUOTINO and PQUOTINO cannot be used together in versions
* of superblock that do not have pquotino. from->sb_flags
* tells us which quota is active and should be copied to
* disk. If neither are active, we should NULL the inode.
*
* In all cases, the separate pquotino must remain 0 because it
* it beyond the "end" of the valid non-pquotino superblock.
*/
if (from->sb_qflags & XFS_GQUOTA_ACCT)
to->sb_gquotino = cpu_to_be64(from->sb_gquotino);
else if (from->sb_qflags & XFS_PQUOTA_ACCT)
to->sb_gquotino = cpu_to_be64(from->sb_pquotino);
else {
/*
* We can't rely on just the fields being logged to tell us
* that it is safe to write NULLFSINO - we should only do that
* if quotas are not actually enabled. Hence only write
* NULLFSINO if both in-core quota inodes are NULL.
*/
if (from->sb_gquotino == NULLFSINO &&
from->sb_pquotino == NULLFSINO)
to->sb_gquotino = cpu_to_be64(NULLFSINO);
}
to->sb_pquotino = 0;
}
void
xfs_sb_to_disk(
struct xfs_dsb *to,
struct xfs_sb *from)
{
xfs_sb_quota_to_disk(to, from);
to->sb_magicnum = cpu_to_be32(from->sb_magicnum);
to->sb_blocksize = cpu_to_be32(from->sb_blocksize);
to->sb_dblocks = cpu_to_be64(from->sb_dblocks);
to->sb_rblocks = cpu_to_be64(from->sb_rblocks);
to->sb_rextents = cpu_to_be64(from->sb_rextents);
memcpy(&to->sb_uuid, &from->sb_uuid, sizeof(to->sb_uuid));
to->sb_logstart = cpu_to_be64(from->sb_logstart);
to->sb_rootino = cpu_to_be64(from->sb_rootino);
to->sb_rbmino = cpu_to_be64(from->sb_rbmino);
to->sb_rsumino = cpu_to_be64(from->sb_rsumino);
to->sb_rextsize = cpu_to_be32(from->sb_rextsize);
to->sb_agblocks = cpu_to_be32(from->sb_agblocks);
to->sb_agcount = cpu_to_be32(from->sb_agcount);
to->sb_rbmblocks = cpu_to_be32(from->sb_rbmblocks);
to->sb_logblocks = cpu_to_be32(from->sb_logblocks);
to->sb_versionnum = cpu_to_be16(from->sb_versionnum);
to->sb_sectsize = cpu_to_be16(from->sb_sectsize);
to->sb_inodesize = cpu_to_be16(from->sb_inodesize);
to->sb_inopblock = cpu_to_be16(from->sb_inopblock);
memcpy(&to->sb_fname, &from->sb_fname, sizeof(to->sb_fname));
to->sb_blocklog = from->sb_blocklog;
to->sb_sectlog = from->sb_sectlog;
to->sb_inodelog = from->sb_inodelog;
to->sb_inopblog = from->sb_inopblog;
to->sb_agblklog = from->sb_agblklog;
to->sb_rextslog = from->sb_rextslog;
to->sb_inprogress = from->sb_inprogress;
to->sb_imax_pct = from->sb_imax_pct;
to->sb_icount = cpu_to_be64(from->sb_icount);
to->sb_ifree = cpu_to_be64(from->sb_ifree);
to->sb_fdblocks = cpu_to_be64(from->sb_fdblocks);
to->sb_frextents = cpu_to_be64(from->sb_frextents);
to->sb_flags = from->sb_flags;
to->sb_shared_vn = from->sb_shared_vn;
to->sb_inoalignmt = cpu_to_be32(from->sb_inoalignmt);
to->sb_unit = cpu_to_be32(from->sb_unit);
to->sb_width = cpu_to_be32(from->sb_width);
to->sb_dirblklog = from->sb_dirblklog;
to->sb_logsectlog = from->sb_logsectlog;
to->sb_logsectsize = cpu_to_be16(from->sb_logsectsize);
to->sb_logsunit = cpu_to_be32(from->sb_logsunit);
/*
* We need to ensure that bad_features2 always matches features2.
* Hence we enforce that here rather than having to remember to do it
* everywhere else that updates features2.
*/
from->sb_bad_features2 = from->sb_features2;
to->sb_features2 = cpu_to_be32(from->sb_features2);
to->sb_bad_features2 = cpu_to_be32(from->sb_bad_features2);
if (xfs_sb_version_hascrc(from)) {
to->sb_features_compat = cpu_to_be32(from->sb_features_compat);
to->sb_features_ro_compat =
cpu_to_be32(from->sb_features_ro_compat);
to->sb_features_incompat =
cpu_to_be32(from->sb_features_incompat);
to->sb_features_log_incompat =
cpu_to_be32(from->sb_features_log_incompat);
to->sb_spino_align = cpu_to_be32(from->sb_spino_align);
to->sb_lsn = cpu_to_be64(from->sb_lsn);
if (xfs_sb_version_hasmetauuid(from))
uuid_copy(&to->sb_meta_uuid, &from->sb_meta_uuid);
}
}
static int
xfs_sb_verify(
struct xfs_buf *bp,
bool check_version)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_sb sb;
/*
* Use call variant which doesn't convert quota flags from disk
* format, because xfs_mount_validate_sb checks the on-disk flags.
*/
__xfs_sb_from_disk(&sb, XFS_BUF_TO_SBP(bp), false);
/*
* Only check the in progress field for the primary superblock as
* mkfs.xfs doesn't clear it from secondary superblocks.
*/
return xfs_mount_validate_sb(mp, &sb, bp->b_bn == XFS_SB_DADDR,
check_version);
}
/*
* If the superblock has the CRC feature bit set or the CRC field is non-null,
* check that the CRC is valid. We check the CRC field is non-null because a
* single bit error could clear the feature bit and unused parts of the
* superblock are supposed to be zero. Hence a non-null crc field indicates that
* we've potentially lost a feature bit and we should check it anyway.
*
* However, past bugs (i.e. in growfs) left non-zeroed regions beyond the
* last field in V4 secondary superblocks. So for secondary superblocks,
* we are more forgiving, and ignore CRC failures if the primary doesn't
* indicate that the fs version is V5.
*/
static void
xfs_sb_read_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
int error;
/*
* open code the version check to avoid needing to convert the entire
* superblock from disk order just to check the version number
*/
if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC) &&
(((be16_to_cpu(dsb->sb_versionnum) & XFS_SB_VERSION_NUMBITS) ==
XFS_SB_VERSION_5) ||
dsb->sb_crc != 0)) {
if (!xfs_buf_verify_cksum(bp, XFS_SB_CRC_OFF)) {
/* Only fail bad secondaries on a known V5 filesystem */
if (bp->b_bn == XFS_SB_DADDR ||
xfs_sb_version_hascrc(&mp->m_sb)) {
error = -EFSBADCRC;
goto out_error;
}
}
}
error = xfs_sb_verify(bp, true);
out_error:
if (error) {
xfs_buf_ioerror(bp, error);
if (error == -EFSCORRUPTED || error == -EFSBADCRC)
xfs_verifier_error(bp);
}
}
/*
* We may be probed for a filesystem match, so we may not want to emit
* messages when the superblock buffer is not actually an XFS superblock.
* If we find an XFS superblock, then run a normal, noisy mount because we are
* really going to mount it and want to know about errors.
*/
static void
xfs_sb_quiet_read_verify(
struct xfs_buf *bp)
{
struct xfs_dsb *dsb = XFS_BUF_TO_SBP(bp);
if (dsb->sb_magicnum == cpu_to_be32(XFS_SB_MAGIC)) {
/* XFS filesystem, verify noisily! */
xfs_sb_read_verify(bp);
return;
}
/* quietly fail */
xfs_buf_ioerror(bp, -EWRONGFS);
}
static void
xfs_sb_write_verify(
struct xfs_buf *bp)
{
struct xfs_mount *mp = bp->b_target->bt_mount;
struct xfs_buf_log_item *bip = bp->b_fspriv;
int error;
error = xfs_sb_verify(bp, false);
if (error) {
xfs_buf_ioerror(bp, error);
xfs_verifier_error(bp);
return;
}
if (!xfs_sb_version_hascrc(&mp->m_sb))
return;
if (bip)
XFS_BUF_TO_SBP(bp)->sb_lsn = cpu_to_be64(bip->bli_item.li_lsn);
xfs_buf_update_cksum(bp, XFS_SB_CRC_OFF);
}
const struct xfs_buf_ops xfs_sb_buf_ops = {
.verify_read = xfs_sb_read_verify,
.verify_write = xfs_sb_write_verify,
};
const struct xfs_buf_ops xfs_sb_quiet_buf_ops = {
.verify_read = xfs_sb_quiet_read_verify,
.verify_write = xfs_sb_write_verify,
};
/*
* xfs_mount_common
*
* Mount initialization code establishing various mount
* fields from the superblock associated with the given
* mount structure
*/
void
xfs_sb_mount_common(
struct xfs_mount *mp,
struct xfs_sb *sbp)
{
mp->m_agfrotor = mp->m_agirotor = 0;
spin_lock_init(&mp->m_agirotor_lock);
mp->m_maxagi = mp->m_sb.sb_agcount;
mp->m_blkbit_log = sbp->sb_blocklog + XFS_NBBYLOG;
mp->m_blkbb_log = sbp->sb_blocklog - BBSHIFT;
mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
mp->m_blockmask = sbp->sb_blocksize - 1;
mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
mp->m_blockwmask = mp->m_blockwsize - 1;
mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 1);
mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 0);
mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2;
mp->m_alloc_mnr[1] = mp->m_alloc_mxr[1] / 2;
mp->m_inobt_mxr[0] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 1);
mp->m_inobt_mxr[1] = xfs_inobt_maxrecs(mp, sbp->sb_blocksize, 0);
mp->m_inobt_mnr[0] = mp->m_inobt_mxr[0] / 2;
mp->m_inobt_mnr[1] = mp->m_inobt_mxr[1] / 2;
mp->m_bmap_dmxr[0] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 1);
mp->m_bmap_dmxr[1] = xfs_bmbt_maxrecs(mp, sbp->sb_blocksize, 0);
mp->m_bmap_dmnr[0] = mp->m_bmap_dmxr[0] / 2;
mp->m_bmap_dmnr[1] = mp->m_bmap_dmxr[1] / 2;
mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK,
sbp->sb_inopblock);
mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
if (sbp->sb_spino_align)
mp->m_ialloc_min_blks = sbp->sb_spino_align;
else
mp->m_ialloc_min_blks = mp->m_ialloc_blks;
}
/*
* xfs_initialize_perag_data
*
* Read in each per-ag structure so we can count up the number of
* allocated inodes, free inodes and used filesystem blocks as this
* information is no longer persistent in the superblock. Once we have
* this information, write it into the in-core superblock structure.
*/
int
xfs_initialize_perag_data(
struct xfs_mount *mp,
xfs_agnumber_t agcount)
{
xfs_agnumber_t index;
xfs_perag_t *pag;
xfs_sb_t *sbp = &mp->m_sb;
uint64_t ifree = 0;
uint64_t ialloc = 0;
uint64_t bfree = 0;
uint64_t bfreelst = 0;
uint64_t btree = 0;
int error;
for (index = 0; index < agcount; index++) {
/*
* read the agf, then the agi. This gets us
* all the information we need and populates the
* per-ag structures for us.
*/
error = xfs_alloc_pagf_init(mp, NULL, index, 0);
if (error)
return error;
error = xfs_ialloc_pagi_init(mp, NULL, index);
if (error)
return error;
pag = xfs_perag_get(mp, index);
ifree += pag->pagi_freecount;
ialloc += pag->pagi_count;
bfree += pag->pagf_freeblks;
bfreelst += pag->pagf_flcount;
btree += pag->pagf_btreeblks;
xfs_perag_put(pag);
}
/* Overwrite incore superblock counters with just-read data */
spin_lock(&mp->m_sb_lock);
sbp->sb_ifree = ifree;
sbp->sb_icount = ialloc;
sbp->sb_fdblocks = bfree + bfreelst + btree;
spin_unlock(&mp->m_sb_lock);
xfs_reinit_percpu_counters(mp);
return 0;
}
/*
* xfs_log_sb() can be used to copy arbitrary changes to the in-core superblock
* into the superblock buffer to be logged. It does not provide the higher
* level of locking that is needed to protect the in-core superblock from
* concurrent access.
*/
void
xfs_log_sb(
struct xfs_trans *tp)
{
struct xfs_mount *mp = tp->t_mountp;
struct xfs_buf *bp = xfs_trans_getsb(tp, mp, 0);
mp->m_sb.sb_icount = percpu_counter_sum(&mp->m_icount);
mp->m_sb.sb_ifree = percpu_counter_sum(&mp->m_ifree);
mp->m_sb.sb_fdblocks = percpu_counter_sum(&mp->m_fdblocks);
xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb);
xfs_trans_buf_set_type(tp, bp, XFS_BLFT_SB_BUF);
xfs_trans_log_buf(tp, bp, 0, sizeof(struct xfs_dsb));
}
/*
* xfs_sync_sb
*
* Sync the superblock to disk.
*
* Note that the caller is responsible for checking the frozen state of the
* filesystem. This procedure uses the non-blocking transaction allocator and
* thus will allow modifications to a frozen fs. This is required because this
* code can be called during the process of freezing where use of the high-level
* allocator would deadlock.
*/
int
xfs_sync_sb(
struct xfs_mount *mp,
bool wait)
{
struct xfs_trans *tp;
int error;
tp = _xfs_trans_alloc(mp, XFS_TRANS_SB_CHANGE, KM_SLEEP);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_sb, 0, 0);
if (error) {
xfs_trans_cancel(tp);
return error;
}
xfs_log_sb(tp);
if (wait)
xfs_trans_set_sync(tp);
return xfs_trans_commit(tp);
}
|