-
Notifications
You must be signed in to change notification settings - Fork 127
/
Copy pathxfs_mount.c
1355 lines (1203 loc) · 35.3 KB
/
xfs_mount.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
// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* All Rights Reserved.
*/
#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_dir2.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_bmap.h"
#include "xfs_trans.h"
#include "xfs_trans_priv.h"
#include "xfs_log.h"
#include "xfs_error.h"
#include "xfs_quota.h"
#include "xfs_fsops.h"
#include "xfs_icache.h"
#include "xfs_sysfs.h"
#include "xfs_rmap_btree.h"
#include "xfs_refcount_btree.h"
#include "xfs_reflink.h"
#include "xfs_extent_busy.h"
#include "xfs_health.h"
#include "xfs_trace.h"
#include "xfs_ag.h"
static DEFINE_MUTEX(xfs_uuid_table_mutex);
static int xfs_uuid_table_size;
static uuid_t *xfs_uuid_table;
void
xfs_uuid_table_free(void)
{
if (xfs_uuid_table_size == 0)
return;
kmem_free(xfs_uuid_table);
xfs_uuid_table = NULL;
xfs_uuid_table_size = 0;
}
/*
* See if the UUID is unique among mounted XFS filesystems.
* Mount fails if UUID is nil or a FS with the same UUID is already mounted.
*/
STATIC int
xfs_uuid_mount(
struct xfs_mount *mp)
{
uuid_t *uuid = &mp->m_sb.sb_uuid;
int hole, i;
/* Publish UUID in struct super_block */
uuid_copy(&mp->m_super->s_uuid, uuid);
if (mp->m_flags & XFS_MOUNT_NOUUID)
return 0;
if (uuid_is_null(uuid)) {
xfs_warn(mp, "Filesystem has null UUID - can't mount");
return -EINVAL;
}
mutex_lock(&xfs_uuid_table_mutex);
for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) {
if (uuid_is_null(&xfs_uuid_table[i])) {
hole = i;
continue;
}
if (uuid_equal(uuid, &xfs_uuid_table[i]))
goto out_duplicate;
}
if (hole < 0) {
xfs_uuid_table = krealloc(xfs_uuid_table,
(xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table),
GFP_KERNEL | __GFP_NOFAIL);
hole = xfs_uuid_table_size++;
}
xfs_uuid_table[hole] = *uuid;
mutex_unlock(&xfs_uuid_table_mutex);
return 0;
out_duplicate:
mutex_unlock(&xfs_uuid_table_mutex);
xfs_warn(mp, "Filesystem has duplicate UUID %pU - can't mount", uuid);
return -EINVAL;
}
STATIC void
xfs_uuid_unmount(
struct xfs_mount *mp)
{
uuid_t *uuid = &mp->m_sb.sb_uuid;
int i;
if (mp->m_flags & XFS_MOUNT_NOUUID)
return;
mutex_lock(&xfs_uuid_table_mutex);
for (i = 0; i < xfs_uuid_table_size; i++) {
if (uuid_is_null(&xfs_uuid_table[i]))
continue;
if (!uuid_equal(uuid, &xfs_uuid_table[i]))
continue;
memset(&xfs_uuid_table[i], 0, sizeof(uuid_t));
break;
}
ASSERT(i < xfs_uuid_table_size);
mutex_unlock(&xfs_uuid_table_mutex);
}
STATIC void
__xfs_free_perag(
struct rcu_head *head)
{
struct xfs_perag *pag = container_of(head, struct xfs_perag, rcu_head);
ASSERT(!delayed_work_pending(&pag->pag_blockgc_work));
ASSERT(atomic_read(&pag->pag_ref) == 0);
kmem_free(pag);
}
/*
* Free up the per-ag resources associated with the mount structure.
*/
STATIC void
xfs_free_perag(
xfs_mount_t *mp)
{
xfs_agnumber_t agno;
struct xfs_perag *pag;
for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
spin_lock(&mp->m_perag_lock);
pag = radix_tree_delete(&mp->m_perag_tree, agno);
spin_unlock(&mp->m_perag_lock);
ASSERT(pag);
ASSERT(atomic_read(&pag->pag_ref) == 0);
cancel_delayed_work_sync(&pag->pag_blockgc_work);
xfs_iunlink_destroy(pag);
xfs_buf_hash_destroy(pag);
call_rcu(&pag->rcu_head, __xfs_free_perag);
}
}
/*
* Check size of device based on the (data/realtime) block count.
* Note: this check is used by the growfs code as well as mount.
*/
int
xfs_sb_validate_fsb_count(
xfs_sb_t *sbp,
uint64_t nblocks)
{
ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
ASSERT(sbp->sb_blocklog >= BBSHIFT);
/* Limited by ULONG_MAX of page cache index */
if (nblocks >> (PAGE_SHIFT - sbp->sb_blocklog) > ULONG_MAX)
return -EFBIG;
return 0;
}
int
xfs_initialize_perag(
xfs_mount_t *mp,
xfs_agnumber_t agcount,
xfs_agnumber_t *maxagi)
{
xfs_agnumber_t index;
xfs_agnumber_t first_initialised = NULLAGNUMBER;
xfs_perag_t *pag;
int error = -ENOMEM;
/*
* Walk the current per-ag tree so we don't try to initialise AGs
* that already exist (growfs case). Allocate and insert all the
* AGs we don't find ready for initialisation.
*/
for (index = 0; index < agcount; index++) {
pag = xfs_perag_get(mp, index);
if (pag) {
xfs_perag_put(pag);
continue;
}
pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
if (!pag) {
error = -ENOMEM;
goto out_unwind_new_pags;
}
pag->pag_agno = index;
pag->pag_mount = mp;
spin_lock_init(&pag->pag_ici_lock);
INIT_DELAYED_WORK(&pag->pag_blockgc_work, xfs_blockgc_worker);
INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
error = xfs_buf_hash_init(pag);
if (error)
goto out_free_pag;
init_waitqueue_head(&pag->pagb_wait);
spin_lock_init(&pag->pagb_lock);
pag->pagb_count = 0;
pag->pagb_tree = RB_ROOT;
error = radix_tree_preload(GFP_NOFS);
if (error)
goto out_hash_destroy;
spin_lock(&mp->m_perag_lock);
if (radix_tree_insert(&mp->m_perag_tree, index, pag)) {
WARN_ON_ONCE(1);
spin_unlock(&mp->m_perag_lock);
radix_tree_preload_end();
error = -EEXIST;
goto out_hash_destroy;
}
spin_unlock(&mp->m_perag_lock);
radix_tree_preload_end();
/* first new pag is fully initialized */
if (first_initialised == NULLAGNUMBER)
first_initialised = index;
error = xfs_iunlink_init(pag);
if (error)
goto out_hash_destroy;
spin_lock_init(&pag->pag_state_lock);
}
index = xfs_set_inode_alloc(mp, agcount);
if (maxagi)
*maxagi = index;
mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp);
return 0;
out_hash_destroy:
xfs_buf_hash_destroy(pag);
out_free_pag:
kmem_free(pag);
out_unwind_new_pags:
/* unwind any prior newly initialized pags */
for (index = first_initialised; index < agcount; index++) {
pag = radix_tree_delete(&mp->m_perag_tree, index);
if (!pag)
break;
xfs_buf_hash_destroy(pag);
xfs_iunlink_destroy(pag);
kmem_free(pag);
}
return error;
}
/*
* xfs_readsb
*
* Does the initial read of the superblock.
*/
int
xfs_readsb(
struct xfs_mount *mp,
int flags)
{
unsigned int sector_size;
struct xfs_buf *bp;
struct xfs_sb *sbp = &mp->m_sb;
int error;
int loud = !(flags & XFS_MFSI_QUIET);
const struct xfs_buf_ops *buf_ops;
ASSERT(mp->m_sb_bp == NULL);
ASSERT(mp->m_ddev_targp != NULL);
/*
* For the initial read, we must guess at the sector
* size based on the block device. It's enough to
* get the sb_sectsize out of the superblock and
* then reread with the proper length.
* We don't verify it yet, because it may not be complete.
*/
sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
buf_ops = NULL;
/*
* Allocate a (locked) buffer to hold the superblock. This will be kept
* around at all times to optimize access to the superblock. Therefore,
* set XBF_NO_IOACCT to make sure it doesn't hold the buftarg count
* elevated.
*/
reread:
error = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
BTOBB(sector_size), XBF_NO_IOACCT, &bp,
buf_ops);
if (error) {
if (loud)
xfs_warn(mp, "SB validate failed with error %d.", error);
/* bad CRC means corrupted metadata */
if (error == -EFSBADCRC)
error = -EFSCORRUPTED;
return error;
}
/*
* Initialize the mount structure from the superblock.
*/
xfs_sb_from_disk(sbp, bp->b_addr);
/*
* If we haven't validated the superblock, do so now before we try
* to check the sector size and reread the superblock appropriately.
*/
if (sbp->sb_magicnum != XFS_SB_MAGIC) {
if (loud)
xfs_warn(mp, "Invalid superblock magic number");
error = -EINVAL;
goto release_buf;
}
/*
* We must be able to do sector-sized and sector-aligned IO.
*/
if (sector_size > sbp->sb_sectsize) {
if (loud)
xfs_warn(mp, "device supports %u byte sectors (not %u)",
sector_size, sbp->sb_sectsize);
error = -ENOSYS;
goto release_buf;
}
if (buf_ops == NULL) {
/*
* Re-read the superblock so the buffer is correctly sized,
* and properly verified.
*/
xfs_buf_relse(bp);
sector_size = sbp->sb_sectsize;
buf_ops = loud ? &xfs_sb_buf_ops : &xfs_sb_quiet_buf_ops;
goto reread;
}
xfs_reinit_percpu_counters(mp);
/* no need to be quiet anymore, so reset the buf ops */
bp->b_ops = &xfs_sb_buf_ops;
mp->m_sb_bp = bp;
xfs_buf_unlock(bp);
return 0;
release_buf:
xfs_buf_relse(bp);
return error;
}
/*
* If the sunit/swidth change would move the precomputed root inode value, we
* must reject the ondisk change because repair will stumble over that.
* However, we allow the mount to proceed because we never rejected this
* combination before. Returns true to update the sb, false otherwise.
*/
static inline int
xfs_check_new_dalign(
struct xfs_mount *mp,
int new_dalign,
bool *update_sb)
{
struct xfs_sb *sbp = &mp->m_sb;
xfs_ino_t calc_ino;
calc_ino = xfs_ialloc_calc_rootino(mp, new_dalign);
trace_xfs_check_new_dalign(mp, new_dalign, calc_ino);
if (sbp->sb_rootino == calc_ino) {
*update_sb = true;
return 0;
}
xfs_warn(mp,
"Cannot change stripe alignment; would require moving root inode.");
/*
* XXX: Next time we add a new incompat feature, this should start
* returning -EINVAL to fail the mount. Until then, spit out a warning
* that we're ignoring the administrator's instructions.
*/
xfs_warn(mp, "Skipping superblock stripe alignment update.");
*update_sb = false;
return 0;
}
/*
* If we were provided with new sunit/swidth values as mount options, make sure
* that they pass basic alignment and superblock feature checks, and convert
* them into the same units (FSB) that everything else expects. This step
* /must/ be done before computing the inode geometry.
*/
STATIC int
xfs_validate_new_dalign(
struct xfs_mount *mp)
{
if (mp->m_dalign == 0)
return 0;
/*
* If stripe unit and stripe width are not multiples
* of the fs blocksize turn off alignment.
*/
if ((BBTOB(mp->m_dalign) & mp->m_blockmask) ||
(BBTOB(mp->m_swidth) & mp->m_blockmask)) {
xfs_warn(mp,
"alignment check failed: sunit/swidth vs. blocksize(%d)",
mp->m_sb.sb_blocksize);
return -EINVAL;
} else {
/*
* Convert the stripe unit and width to FSBs.
*/
mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
if (mp->m_dalign && (mp->m_sb.sb_agblocks % mp->m_dalign)) {
xfs_warn(mp,
"alignment check failed: sunit/swidth vs. agsize(%d)",
mp->m_sb.sb_agblocks);
return -EINVAL;
} else if (mp->m_dalign) {
mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
} else {
xfs_warn(mp,
"alignment check failed: sunit(%d) less than bsize(%d)",
mp->m_dalign, mp->m_sb.sb_blocksize);
return -EINVAL;
}
}
if (!xfs_sb_version_hasdalign(&mp->m_sb)) {
xfs_warn(mp,
"cannot change alignment: superblock does not support data alignment");
return -EINVAL;
}
return 0;
}
/* Update alignment values based on mount options and sb values. */
STATIC int
xfs_update_alignment(
struct xfs_mount *mp)
{
struct xfs_sb *sbp = &mp->m_sb;
if (mp->m_dalign) {
bool update_sb;
int error;
if (sbp->sb_unit == mp->m_dalign &&
sbp->sb_width == mp->m_swidth)
return 0;
error = xfs_check_new_dalign(mp, mp->m_dalign, &update_sb);
if (error || !update_sb)
return error;
sbp->sb_unit = mp->m_dalign;
sbp->sb_width = mp->m_swidth;
mp->m_update_sb = true;
} else if ((mp->m_flags & XFS_MOUNT_NOALIGN) != XFS_MOUNT_NOALIGN &&
xfs_sb_version_hasdalign(&mp->m_sb)) {
mp->m_dalign = sbp->sb_unit;
mp->m_swidth = sbp->sb_width;
}
return 0;
}
/*
* precalculate the low space thresholds for dynamic speculative preallocation.
*/
void
xfs_set_low_space_thresholds(
struct xfs_mount *mp)
{
int i;
for (i = 0; i < XFS_LOWSP_MAX; i++) {
uint64_t space = mp->m_sb.sb_dblocks;
do_div(space, 100);
mp->m_low_space[i] = space * (i + 1);
}
}
/*
* Check that the data (and log if separate) is an ok size.
*/
STATIC int
xfs_check_sizes(
struct xfs_mount *mp)
{
struct xfs_buf *bp;
xfs_daddr_t d;
int error;
d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_dblocks) {
xfs_warn(mp, "filesystem size mismatch detected");
return -EFBIG;
}
error = xfs_buf_read_uncached(mp->m_ddev_targp,
d - XFS_FSS_TO_BB(mp, 1),
XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
if (error) {
xfs_warn(mp, "last sector read failed");
return error;
}
xfs_buf_relse(bp);
if (mp->m_logdev_targp == mp->m_ddev_targp)
return 0;
d = (xfs_daddr_t)XFS_FSB_TO_BB(mp, mp->m_sb.sb_logblocks);
if (XFS_BB_TO_FSB(mp, d) != mp->m_sb.sb_logblocks) {
xfs_warn(mp, "log size mismatch detected");
return -EFBIG;
}
error = xfs_buf_read_uncached(mp->m_logdev_targp,
d - XFS_FSB_TO_BB(mp, 1),
XFS_FSB_TO_BB(mp, 1), 0, &bp, NULL);
if (error) {
xfs_warn(mp, "log device read failed");
return error;
}
xfs_buf_relse(bp);
return 0;
}
/*
* Clear the quotaflags in memory and in the superblock.
*/
int
xfs_mount_reset_sbqflags(
struct xfs_mount *mp)
{
mp->m_qflags = 0;
/* It is OK to look at sb_qflags in the mount path without m_sb_lock. */
if (mp->m_sb.sb_qflags == 0)
return 0;
spin_lock(&mp->m_sb_lock);
mp->m_sb.sb_qflags = 0;
spin_unlock(&mp->m_sb_lock);
if (!xfs_fs_writable(mp, SB_FREEZE_WRITE))
return 0;
return xfs_sync_sb(mp, false);
}
uint64_t
xfs_default_resblks(xfs_mount_t *mp)
{
uint64_t resblks;
/*
* We default to 5% or 8192 fsbs of space reserved, whichever is
* smaller. This is intended to cover concurrent allocation
* transactions when we initially hit enospc. These each require a 4
* block reservation. Hence by default we cover roughly 2000 concurrent
* allocation reservations.
*/
resblks = mp->m_sb.sb_dblocks;
do_div(resblks, 20);
resblks = min_t(uint64_t, resblks, 8192);
return resblks;
}
/* Ensure the summary counts are correct. */
STATIC int
xfs_check_summary_counts(
struct xfs_mount *mp)
{
/*
* The AG0 superblock verifier rejects in-progress filesystems,
* so we should never see the flag set this far into mounting.
*/
if (mp->m_sb.sb_inprogress) {
xfs_err(mp, "sb_inprogress set after log recovery??");
WARN_ON(1);
return -EFSCORRUPTED;
}
/*
* Now the log is mounted, we know if it was an unclean shutdown or
* not. If it was, with the first phase of recovery has completed, we
* have consistent AG blocks on disk. We have not recovered EFIs yet,
* but they are recovered transactionally in the second recovery phase
* later.
*
* If the log was clean when we mounted, we can check the summary
* counters. If any of them are obviously incorrect, we can recompute
* them from the AGF headers in the next step.
*/
if (XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
(mp->m_sb.sb_fdblocks > mp->m_sb.sb_dblocks ||
!xfs_verify_icount(mp, mp->m_sb.sb_icount) ||
mp->m_sb.sb_ifree > mp->m_sb.sb_icount))
xfs_fs_mark_sick(mp, XFS_SICK_FS_COUNTERS);
/*
* We can safely re-initialise incore superblock counters from the
* per-ag data. These may not be correct if the filesystem was not
* cleanly unmounted, so we waited for recovery to finish before doing
* this.
*
* If the filesystem was cleanly unmounted or the previous check did
* not flag anything weird, then we can trust the values in the
* superblock to be correct and we don't need to do anything here.
* Otherwise, recalculate the summary counters.
*/
if ((!xfs_sb_version_haslazysbcount(&mp->m_sb) ||
XFS_LAST_UNMOUNT_WAS_CLEAN(mp)) &&
!xfs_fs_has_sickness(mp, XFS_SICK_FS_COUNTERS))
return 0;
return xfs_initialize_perag_data(mp, mp->m_sb.sb_agcount);
}
/*
* Flush and reclaim dirty inodes in preparation for unmount. Inodes and
* internal inode structures can be sitting in the CIL and AIL at this point,
* so we need to unpin them, write them back and/or reclaim them before unmount
* can proceed.
*
* An inode cluster that has been freed can have its buffer still pinned in
* memory because the transaction is still sitting in a iclog. The stale inodes
* on that buffer will be pinned to the buffer until the transaction hits the
* disk and the callbacks run. Pushing the AIL will skip the stale inodes and
* may never see the pinned buffer, so nothing will push out the iclog and
* unpin the buffer.
*
* Hence we need to force the log to unpin everything first. However, log
* forces don't wait for the discards they issue to complete, so we have to
* explicitly wait for them to complete here as well.
*
* Then we can tell the world we are unmounting so that error handling knows
* that the filesystem is going away and we should error out anything that we
* have been retrying in the background. This will prevent never-ending
* retries in AIL pushing from hanging the unmount.
*
* Finally, we can push the AIL to clean all the remaining dirty objects, then
* reclaim the remaining inodes that are still in memory at this point in time.
*/
static void
xfs_unmount_flush_inodes(
struct xfs_mount *mp)
{
xfs_log_force(mp, XFS_LOG_SYNC);
xfs_extent_busy_wait_all(mp);
flush_workqueue(xfs_discard_wq);
mp->m_flags |= XFS_MOUNT_UNMOUNTING;
xfs_ail_push_all_sync(mp->m_ail);
cancel_delayed_work_sync(&mp->m_reclaim_work);
xfs_reclaim_inodes(mp);
xfs_health_unmount(mp);
}
static void
xfs_mount_setup_inode_geom(
struct xfs_mount *mp)
{
struct xfs_ino_geometry *igeo = M_IGEO(mp);
igeo->attr_fork_offset = xfs_bmap_compute_attr_offset(mp);
ASSERT(igeo->attr_fork_offset < XFS_LITINO(mp));
xfs_ialloc_setup_geometry(mp);
}
/*
* This function does the following on an initial mount of a file system:
* - reads the superblock from disk and init the mount struct
* - if we're a 32-bit kernel, do a size check on the superblock
* so we don't mount terabyte filesystems
* - init mount struct realtime fields
* - allocate inode hash table for fs
* - init directory manager
* - perform recovery and init the log manager
*/
int
xfs_mountfs(
struct xfs_mount *mp)
{
struct xfs_sb *sbp = &(mp->m_sb);
struct xfs_inode *rip;
struct xfs_ino_geometry *igeo = M_IGEO(mp);
uint64_t resblks;
uint quotamount = 0;
uint quotaflags = 0;
int error = 0;
xfs_sb_mount_common(mp, sbp);
/*
* Check for a mismatched features2 values. Older kernels read & wrote
* into the wrong sb offset for sb_features2 on some platforms due to
* xfs_sb_t not being 64bit size aligned when sb_features2 was added,
* which made older superblock reading/writing routines swap it as a
* 64-bit value.
*
* For backwards compatibility, we make both slots equal.
*
* If we detect a mismatched field, we OR the set bits into the existing
* features2 field in case it has already been modified; we don't want
* to lose any features. We then update the bad location with the ORed
* value so that older kernels will see any features2 flags. The
* superblock writeback code ensures the new sb_features2 is copied to
* sb_bad_features2 before it is logged or written to disk.
*/
if (xfs_sb_has_mismatched_features2(sbp)) {
xfs_warn(mp, "correcting sb_features alignment problem");
sbp->sb_features2 |= sbp->sb_bad_features2;
mp->m_update_sb = true;
/*
* Re-check for ATTR2 in case it was found in bad_features2
* slot.
*/
if (xfs_sb_version_hasattr2(&mp->m_sb) &&
!(mp->m_flags & XFS_MOUNT_NOATTR2))
mp->m_flags |= XFS_MOUNT_ATTR2;
}
if (xfs_sb_version_hasattr2(&mp->m_sb) &&
(mp->m_flags & XFS_MOUNT_NOATTR2)) {
xfs_sb_version_removeattr2(&mp->m_sb);
mp->m_update_sb = true;
/* update sb_versionnum for the clearing of the morebits */
if (!sbp->sb_features2)
mp->m_update_sb = true;
}
/* always use v2 inodes by default now */
if (!(mp->m_sb.sb_versionnum & XFS_SB_VERSION_NLINKBIT)) {
mp->m_sb.sb_versionnum |= XFS_SB_VERSION_NLINKBIT;
mp->m_update_sb = true;
}
/*
* If we were given new sunit/swidth options, do some basic validation
* checks and convert the incore dalign and swidth values to the
* same units (FSB) that everything else uses. This /must/ happen
* before computing the inode geometry.
*/
error = xfs_validate_new_dalign(mp);
if (error)
goto out;
xfs_alloc_compute_maxlevels(mp);
xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
xfs_mount_setup_inode_geom(mp);
xfs_rmapbt_compute_maxlevels(mp);
xfs_refcountbt_compute_maxlevels(mp);
/*
* Check if sb_agblocks is aligned at stripe boundary. If sb_agblocks
* is NOT aligned turn off m_dalign since allocator alignment is within
* an ag, therefore ag has to be aligned at stripe boundary. Note that
* we must compute the free space and rmap btree geometry before doing
* this.
*/
error = xfs_update_alignment(mp);
if (error)
goto out;
/* enable fail_at_unmount as default */
mp->m_fail_unmount = true;
error = xfs_sysfs_init(&mp->m_kobj, &xfs_mp_ktype,
NULL, mp->m_super->s_id);
if (error)
goto out;
error = xfs_sysfs_init(&mp->m_stats.xs_kobj, &xfs_stats_ktype,
&mp->m_kobj, "stats");
if (error)
goto out_remove_sysfs;
error = xfs_error_sysfs_init(mp);
if (error)
goto out_del_stats;
error = xfs_errortag_init(mp);
if (error)
goto out_remove_error_sysfs;
error = xfs_uuid_mount(mp);
if (error)
goto out_remove_errortag;
/*
* Update the preferred write size based on the information from the
* on-disk superblock.
*/
mp->m_allocsize_log =
max_t(uint32_t, sbp->sb_blocklog, mp->m_allocsize_log);
mp->m_allocsize_blocks = 1U << (mp->m_allocsize_log - sbp->sb_blocklog);
/* set the low space thresholds for dynamic preallocation */
xfs_set_low_space_thresholds(mp);
/*
* If enabled, sparse inode chunk alignment is expected to match the
* cluster size. Full inode chunk alignment must match the chunk size,
* but that is checked on sb read verification...
*/
if (xfs_sb_version_hassparseinodes(&mp->m_sb) &&
mp->m_sb.sb_spino_align !=
XFS_B_TO_FSBT(mp, igeo->inode_cluster_size_raw)) {
xfs_warn(mp,
"Sparse inode block alignment (%u) must match cluster size (%llu).",
mp->m_sb.sb_spino_align,
XFS_B_TO_FSBT(mp, igeo->inode_cluster_size_raw));
error = -EINVAL;
goto out_remove_uuid;
}
/*
* Check that the data (and log if separate) is an ok size.
*/
error = xfs_check_sizes(mp);
if (error)
goto out_remove_uuid;
/*
* Initialize realtime fields in the mount structure
*/
error = xfs_rtmount_init(mp);
if (error) {
xfs_warn(mp, "RT mount failed");
goto out_remove_uuid;
}
/*
* Copies the low order bits of the timestamp and the randomly
* set "sequence" number out of a UUID.
*/
mp->m_fixedfsid[0] =
(get_unaligned_be16(&sbp->sb_uuid.b[8]) << 16) |
get_unaligned_be16(&sbp->sb_uuid.b[4]);
mp->m_fixedfsid[1] = get_unaligned_be32(&sbp->sb_uuid.b[0]);
error = xfs_da_mount(mp);
if (error) {
xfs_warn(mp, "Failed dir/attr init: %d", error);
goto out_remove_uuid;
}
/*
* Initialize the precomputed transaction reservations values.
*/
xfs_trans_init(mp);
/*
* Allocate and initialize the per-ag data.
*/
error = xfs_initialize_perag(mp, sbp->sb_agcount, &mp->m_maxagi);
if (error) {
xfs_warn(mp, "Failed per-ag init: %d", error);
goto out_free_dir;
}
if (XFS_IS_CORRUPT(mp, !sbp->sb_logblocks)) {
xfs_warn(mp, "no log defined");
error = -EFSCORRUPTED;
goto out_free_perag;
}
/*
* Log's mount-time initialization. The first part of recovery can place
* some items on the AIL, to be handled when recovery is finished or
* cancelled.
*/
error = xfs_log_mount(mp, mp->m_logdev_targp,
XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
if (error) {
xfs_warn(mp, "log mount failed");
goto out_fail_wait;
}
/* Make sure the summary counts are ok. */
error = xfs_check_summary_counts(mp);
if (error)
goto out_log_dealloc;
/*
* Get and sanity-check the root inode.
* Save the pointer to it in the mount structure.
*/
error = xfs_iget(mp, NULL, sbp->sb_rootino, XFS_IGET_UNTRUSTED,
XFS_ILOCK_EXCL, &rip);
if (error) {
xfs_warn(mp,
"Failed to read root inode 0x%llx, error %d",
sbp->sb_rootino, -error);
goto out_log_dealloc;
}
ASSERT(rip != NULL);
if (XFS_IS_CORRUPT(mp, !S_ISDIR(VFS_I(rip)->i_mode))) {
xfs_warn(mp, "corrupted root inode %llu: not a directory",
(unsigned long long)rip->i_ino);
xfs_iunlock(rip, XFS_ILOCK_EXCL);
error = -EFSCORRUPTED;
goto out_rele_rip;
}
mp->m_rootip = rip; /* save it */
xfs_iunlock(rip, XFS_ILOCK_EXCL);
/*
* Initialize realtime inode pointers in the mount structure
*/
error = xfs_rtmount_inodes(mp);
if (error) {
/*
* Free up the root inode.
*/
xfs_warn(mp, "failed to read RT inodes");
goto out_rele_rip;
}
/*
* If this is a read-only mount defer the superblock updates until
* the next remount into writeable mode. Otherwise we would never
* perform the update e.g. for the root filesystem.
*/
if (mp->m_update_sb && !(mp->m_flags & XFS_MOUNT_RDONLY)) {
error = xfs_sync_sb(mp, false);
if (error) {
xfs_warn(mp, "failed to write sb changes");
goto out_rtunmount;
}
}
/*
* Initialise the XFS quota management subsystem for this mount
*/
if (XFS_IS_QUOTA_RUNNING(mp)) {
error = xfs_qm_newmount(mp, "amount, "aflags);
if (error)
goto out_rtunmount;
} else {
ASSERT(!XFS_IS_QUOTA_ON(mp));
/*
* If a file system had quotas running earlier, but decided to
* mount without -o uquota/pquota/gquota options, revoke the
* quotachecked license.
*/
if (mp->m_sb.sb_qflags & XFS_ALL_QUOTA_ACCT) {
xfs_notice(mp, "resetting quota flags");
error = xfs_mount_reset_sbqflags(mp);
if (error)
goto out_rtunmount;
}
}
/*
* Finish recovering the file system. This part needed to be delayed
* until after the root and real-time bitmap inodes were consistently
* read in.
*/
error = xfs_log_mount_finish(mp);
if (error) {
xfs_warn(mp, "log mount finish failed");
goto out_rtunmount;
}
/*
* Now the log is fully replayed, we can transition to full read-only
* mode for read-only mounts. This will sync all the metadata and clean
* the log so that the recovery we just performed does not have to be
* replayed again on the next mount.
*