forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xfs_mount.c
2236 lines (2018 loc) · 57.2 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
/*
* 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_types.h"
#include "xfs_bit.h"
#include "xfs_log.h"
#include "xfs_inum.h"
#include "xfs_trans.h"
#include "xfs_sb.h"
#include "xfs_ag.h"
#include "xfs_dir2.h"
#include "xfs_dmapi.h"
#include "xfs_mount.h"
#include "xfs_bmap_btree.h"
#include "xfs_alloc_btree.h"
#include "xfs_ialloc_btree.h"
#include "xfs_dir2_sf.h"
#include "xfs_attr_sf.h"
#include "xfs_dinode.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_ialloc.h"
#include "xfs_alloc.h"
#include "xfs_rtalloc.h"
#include "xfs_bmap.h"
#include "xfs_error.h"
#include "xfs_rw.h"
#include "xfs_quota.h"
#include "xfs_fsops.h"
STATIC void xfs_mount_log_sbunit(xfs_mount_t *, __int64_t);
STATIC int xfs_uuid_mount(xfs_mount_t *);
STATIC void xfs_uuid_unmount(xfs_mount_t *mp);
STATIC void xfs_unmountfs_wait(xfs_mount_t *);
#ifdef HAVE_PERCPU_SB
STATIC void xfs_icsb_destroy_counters(xfs_mount_t *);
STATIC void xfs_icsb_balance_counter(xfs_mount_t *, xfs_sb_field_t,
int, int);
STATIC void xfs_icsb_sync_counters(xfs_mount_t *);
STATIC int xfs_icsb_modify_counters(xfs_mount_t *, xfs_sb_field_t,
int64_t, int);
STATIC int xfs_icsb_disable_counter(xfs_mount_t *, xfs_sb_field_t);
#else
#define xfs_icsb_destroy_counters(mp) do { } while (0)
#define xfs_icsb_balance_counter(mp, a, b, c) do { } while (0)
#define xfs_icsb_sync_counters(mp) do { } while (0)
#define xfs_icsb_modify_counters(mp, a, b, c) do { } while (0)
#endif
static const struct {
short offset;
short type; /* 0 = integer
* 1 = binary / string (no translation)
*/
} xfs_sb_info[] = {
{ offsetof(xfs_sb_t, sb_magicnum), 0 },
{ offsetof(xfs_sb_t, sb_blocksize), 0 },
{ offsetof(xfs_sb_t, sb_dblocks), 0 },
{ offsetof(xfs_sb_t, sb_rblocks), 0 },
{ offsetof(xfs_sb_t, sb_rextents), 0 },
{ offsetof(xfs_sb_t, sb_uuid), 1 },
{ offsetof(xfs_sb_t, sb_logstart), 0 },
{ offsetof(xfs_sb_t, sb_rootino), 0 },
{ offsetof(xfs_sb_t, sb_rbmino), 0 },
{ offsetof(xfs_sb_t, sb_rsumino), 0 },
{ offsetof(xfs_sb_t, sb_rextsize), 0 },
{ offsetof(xfs_sb_t, sb_agblocks), 0 },
{ offsetof(xfs_sb_t, sb_agcount), 0 },
{ offsetof(xfs_sb_t, sb_rbmblocks), 0 },
{ offsetof(xfs_sb_t, sb_logblocks), 0 },
{ offsetof(xfs_sb_t, sb_versionnum), 0 },
{ offsetof(xfs_sb_t, sb_sectsize), 0 },
{ offsetof(xfs_sb_t, sb_inodesize), 0 },
{ offsetof(xfs_sb_t, sb_inopblock), 0 },
{ offsetof(xfs_sb_t, sb_fname[0]), 1 },
{ offsetof(xfs_sb_t, sb_blocklog), 0 },
{ offsetof(xfs_sb_t, sb_sectlog), 0 },
{ offsetof(xfs_sb_t, sb_inodelog), 0 },
{ offsetof(xfs_sb_t, sb_inopblog), 0 },
{ offsetof(xfs_sb_t, sb_agblklog), 0 },
{ offsetof(xfs_sb_t, sb_rextslog), 0 },
{ offsetof(xfs_sb_t, sb_inprogress), 0 },
{ offsetof(xfs_sb_t, sb_imax_pct), 0 },
{ offsetof(xfs_sb_t, sb_icount), 0 },
{ offsetof(xfs_sb_t, sb_ifree), 0 },
{ offsetof(xfs_sb_t, sb_fdblocks), 0 },
{ offsetof(xfs_sb_t, sb_frextents), 0 },
{ offsetof(xfs_sb_t, sb_uquotino), 0 },
{ offsetof(xfs_sb_t, sb_gquotino), 0 },
{ offsetof(xfs_sb_t, sb_qflags), 0 },
{ offsetof(xfs_sb_t, sb_flags), 0 },
{ offsetof(xfs_sb_t, sb_shared_vn), 0 },
{ offsetof(xfs_sb_t, sb_inoalignmt), 0 },
{ offsetof(xfs_sb_t, sb_unit), 0 },
{ offsetof(xfs_sb_t, sb_width), 0 },
{ offsetof(xfs_sb_t, sb_dirblklog), 0 },
{ offsetof(xfs_sb_t, sb_logsectlog), 0 },
{ offsetof(xfs_sb_t, sb_logsectsize),0 },
{ offsetof(xfs_sb_t, sb_logsunit), 0 },
{ offsetof(xfs_sb_t, sb_features2), 0 },
{ sizeof(xfs_sb_t), 0 }
};
/*
* Return a pointer to an initialized xfs_mount structure.
*/
xfs_mount_t *
xfs_mount_init(void)
{
xfs_mount_t *mp;
mp = kmem_zalloc(sizeof(xfs_mount_t), KM_SLEEP);
if (xfs_icsb_init_counters(mp)) {
mp->m_flags |= XFS_MOUNT_NO_PERCPU_SB;
}
AIL_LOCKINIT(&mp->m_ail_lock, "xfs_ail");
spinlock_init(&mp->m_sb_lock, "xfs_sb");
mutex_init(&mp->m_ilock);
initnsema(&mp->m_growlock, 1, "xfs_grow");
/*
* Initialize the AIL.
*/
xfs_trans_ail_init(mp);
atomic_set(&mp->m_active_trans, 0);
return mp;
}
/*
* Free up the resources associated with a mount structure. Assume that
* the structure was initially zeroed, so we can tell which fields got
* initialized.
*/
void
xfs_mount_free(
xfs_mount_t *mp,
int remove_bhv)
{
if (mp->m_ihash)
xfs_ihash_free(mp);
if (mp->m_chash)
xfs_chash_free(mp);
if (mp->m_perag) {
int agno;
for (agno = 0; agno < mp->m_maxagi; agno++)
if (mp->m_perag[agno].pagb_list)
kmem_free(mp->m_perag[agno].pagb_list,
sizeof(xfs_perag_busy_t) *
XFS_PAGB_NUM_SLOTS);
kmem_free(mp->m_perag,
sizeof(xfs_perag_t) * mp->m_sb.sb_agcount);
}
AIL_LOCK_DESTROY(&mp->m_ail_lock);
spinlock_destroy(&mp->m_sb_lock);
mutex_destroy(&mp->m_ilock);
freesema(&mp->m_growlock);
if (mp->m_quotainfo)
XFS_QM_DONE(mp);
if (mp->m_fsname != NULL)
kmem_free(mp->m_fsname, mp->m_fsname_len);
if (mp->m_rtname != NULL)
kmem_free(mp->m_rtname, strlen(mp->m_rtname) + 1);
if (mp->m_logname != NULL)
kmem_free(mp->m_logname, strlen(mp->m_logname) + 1);
if (remove_bhv) {
struct bhv_vfs *vfsp = XFS_MTOVFS(mp);
bhv_remove_all_vfsops(vfsp, 0);
VFS_REMOVEBHV(vfsp, &mp->m_bhv);
}
xfs_icsb_destroy_counters(mp);
kmem_free(mp, sizeof(xfs_mount_t));
}
/*
* Check the validity of the SB found.
*/
STATIC int
xfs_mount_validate_sb(
xfs_mount_t *mp,
xfs_sb_t *sbp,
int flags)
{
/*
* If the log device and data device have the
* same device number, the log is internal.
* Consequently, the sb_logstart should be non-zero. If
* we have a zero sb_logstart in this case, we may be trying to mount
* a volume filesystem in a non-volume manner.
*/
if (sbp->sb_magicnum != XFS_SB_MAGIC) {
xfs_fs_mount_cmn_err(flags, "bad magic number");
return XFS_ERROR(EWRONGFS);
}
if (!XFS_SB_GOOD_VERSION(sbp)) {
xfs_fs_mount_cmn_err(flags, "bad version");
return XFS_ERROR(EWRONGFS);
}
if (unlikely(
sbp->sb_logstart == 0 && mp->m_logdev_targp == mp->m_ddev_targp)) {
xfs_fs_mount_cmn_err(flags,
"filesystem is marked as having an external log; "
"specify logdev on the\nmount command line.");
return XFS_ERROR(EINVAL);
}
if (unlikely(
sbp->sb_logstart != 0 && mp->m_logdev_targp != mp->m_ddev_targp)) {
xfs_fs_mount_cmn_err(flags,
"filesystem is marked as having an internal log; "
"do not specify logdev on\nthe mount command line.");
return XFS_ERROR(EINVAL);
}
/*
* More sanity checking. 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_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_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_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 */))) {
xfs_fs_mount_cmn_err(flags, "SB sanity check 1 failed");
return XFS_ERROR(EFSCORRUPTED);
}
/*
* Sanity check AG count, size fields against data size field
*/
if (unlikely(
sbp->sb_dblocks == 0 ||
sbp->sb_dblocks >
(xfs_drfsbno_t)sbp->sb_agcount * sbp->sb_agblocks ||
sbp->sb_dblocks < (xfs_drfsbno_t)(sbp->sb_agcount - 1) *
sbp->sb_agblocks + XFS_MIN_AG_BLOCKS)) {
xfs_fs_mount_cmn_err(flags, "SB sanity check 2 failed");
return XFS_ERROR(EFSCORRUPTED);
}
ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
ASSERT(sbp->sb_blocklog >= BBSHIFT);
#if XFS_BIG_BLKNOS /* Limited by ULONG_MAX of page cache index */
if (unlikely(
(sbp->sb_dblocks >> (PAGE_SHIFT - sbp->sb_blocklog)) > ULONG_MAX ||
(sbp->sb_rblocks >> (PAGE_SHIFT - sbp->sb_blocklog)) > ULONG_MAX)) {
#else /* Limited by UINT_MAX of sectors */
if (unlikely(
(sbp->sb_dblocks << (sbp->sb_blocklog - BBSHIFT)) > UINT_MAX ||
(sbp->sb_rblocks << (sbp->sb_blocklog - BBSHIFT)) > UINT_MAX)) {
#endif
xfs_fs_mount_cmn_err(flags,
"file system too large to be mounted on this system.");
return XFS_ERROR(E2BIG);
}
if (unlikely(sbp->sb_inprogress)) {
xfs_fs_mount_cmn_err(flags, "file system busy");
return XFS_ERROR(EFSCORRUPTED);
}
/*
* Version 1 directory format has never worked on Linux.
*/
if (unlikely(!XFS_SB_VERSION_HASDIRV2(sbp))) {
xfs_fs_mount_cmn_err(flags,
"file system using version 1 directory format");
return XFS_ERROR(ENOSYS);
}
/*
* Until this is fixed only page-sized or smaller data blocks work.
*/
if (unlikely(sbp->sb_blocksize > PAGE_SIZE)) {
xfs_fs_mount_cmn_err(flags,
"file system with blocksize %d bytes",
sbp->sb_blocksize);
xfs_fs_mount_cmn_err(flags,
"only pagesize (%ld) or less will currently work.",
PAGE_SIZE);
return XFS_ERROR(ENOSYS);
}
return 0;
}
xfs_agnumber_t
xfs_initialize_perag(
bhv_vfs_t *vfs,
xfs_mount_t *mp,
xfs_agnumber_t agcount)
{
xfs_agnumber_t index, max_metadata;
xfs_perag_t *pag;
xfs_agino_t agino;
xfs_ino_t ino;
xfs_sb_t *sbp = &mp->m_sb;
xfs_ino_t max_inum = XFS_MAXINUMBER_32;
/* Check to see if the filesystem can overflow 32 bit inodes */
agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
/* Clear the mount flag if no inode can overflow 32 bits
* on this filesystem, or if specifically requested..
*/
if ((vfs->vfs_flag & VFS_32BITINODES) && ino > max_inum) {
mp->m_flags |= XFS_MOUNT_32BITINODES;
} else {
mp->m_flags &= ~XFS_MOUNT_32BITINODES;
}
/* If we can overflow then setup the ag headers accordingly */
if (mp->m_flags & XFS_MOUNT_32BITINODES) {
/* Calculate how much should be reserved for inodes to
* meet the max inode percentage.
*/
if (mp->m_maxicount) {
__uint64_t icount;
icount = sbp->sb_dblocks * sbp->sb_imax_pct;
do_div(icount, 100);
icount += sbp->sb_agblocks - 1;
do_div(icount, sbp->sb_agblocks);
max_metadata = icount;
} else {
max_metadata = agcount;
}
for (index = 0; index < agcount; index++) {
ino = XFS_AGINO_TO_INO(mp, index, agino);
if (ino > max_inum) {
index++;
break;
}
/* This ag is preferred for inodes */
pag = &mp->m_perag[index];
pag->pagi_inodeok = 1;
if (index < max_metadata)
pag->pagf_metadata = 1;
}
} else {
/* Setup default behavior for smaller filesystems */
for (index = 0; index < agcount; index++) {
pag = &mp->m_perag[index];
pag->pagi_inodeok = 1;
}
}
return index;
}
/*
* xfs_xlatesb
*
* data - on disk version of sb
* sb - a superblock
* dir - conversion direction: <0 - convert sb to buf
* >0 - convert buf to sb
* fields - which fields to copy (bitmask)
*/
void
xfs_xlatesb(
void *data,
xfs_sb_t *sb,
int dir,
__int64_t fields)
{
xfs_caddr_t buf_ptr;
xfs_caddr_t mem_ptr;
xfs_sb_field_t f;
int first;
int size;
ASSERT(dir);
ASSERT(fields);
if (!fields)
return;
buf_ptr = (xfs_caddr_t)data;
mem_ptr = (xfs_caddr_t)sb;
while (fields) {
f = (xfs_sb_field_t)xfs_lowbit64((__uint64_t)fields);
first = xfs_sb_info[f].offset;
size = xfs_sb_info[f + 1].offset - first;
ASSERT(xfs_sb_info[f].type == 0 || xfs_sb_info[f].type == 1);
if (size == 1 || xfs_sb_info[f].type == 1) {
if (dir > 0) {
memcpy(mem_ptr + first, buf_ptr + first, size);
} else {
memcpy(buf_ptr + first, mem_ptr + first, size);
}
} else {
switch (size) {
case 2:
INT_XLATE(*(__uint16_t*)(buf_ptr+first),
*(__uint16_t*)(mem_ptr+first),
dir, ARCH_CONVERT);
break;
case 4:
INT_XLATE(*(__uint32_t*)(buf_ptr+first),
*(__uint32_t*)(mem_ptr+first),
dir, ARCH_CONVERT);
break;
case 8:
INT_XLATE(*(__uint64_t*)(buf_ptr+first),
*(__uint64_t*)(mem_ptr+first), dir, ARCH_CONVERT);
break;
default:
ASSERT(0);
}
}
fields &= ~(1LL << f);
}
}
/*
* xfs_readsb
*
* Does the initial read of the superblock.
*/
int
xfs_readsb(xfs_mount_t *mp, int flags)
{
unsigned int sector_size;
unsigned int extra_flags;
xfs_buf_t *bp;
xfs_sb_t *sbp;
int error;
ASSERT(mp->m_sb_bp == NULL);
ASSERT(mp->m_ddev_targp != NULL);
/*
* Allocate a (locked) buffer to hold the superblock.
* This will be kept around at all times to optimize
* access to the superblock.
*/
sector_size = xfs_getsize_buftarg(mp->m_ddev_targp);
extra_flags = XFS_BUF_LOCK | XFS_BUF_MANAGE | XFS_BUF_MAPPED;
bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
BTOBB(sector_size), extra_flags);
if (!bp || XFS_BUF_ISERROR(bp)) {
xfs_fs_mount_cmn_err(flags, "SB read failed");
error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
goto fail;
}
ASSERT(XFS_BUF_ISBUSY(bp));
ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
/*
* Initialize the mount structure from the superblock.
* But first do some basic consistency checking.
*/
sbp = XFS_BUF_TO_SBP(bp);
xfs_xlatesb(XFS_BUF_PTR(bp), &(mp->m_sb), 1, XFS_SB_ALL_BITS);
error = xfs_mount_validate_sb(mp, &(mp->m_sb), flags);
if (error) {
xfs_fs_mount_cmn_err(flags, "SB validate failed");
goto fail;
}
/*
* We must be able to do sector-sized and sector-aligned IO.
*/
if (sector_size > mp->m_sb.sb_sectsize) {
xfs_fs_mount_cmn_err(flags,
"device supports only %u byte sectors (not %u)",
sector_size, mp->m_sb.sb_sectsize);
error = ENOSYS;
goto fail;
}
/*
* If device sector size is smaller than the superblock size,
* re-read the superblock so the buffer is correctly sized.
*/
if (sector_size < mp->m_sb.sb_sectsize) {
XFS_BUF_UNMANAGE(bp);
xfs_buf_relse(bp);
sector_size = mp->m_sb.sb_sectsize;
bp = xfs_buf_read_flags(mp->m_ddev_targp, XFS_SB_DADDR,
BTOBB(sector_size), extra_flags);
if (!bp || XFS_BUF_ISERROR(bp)) {
xfs_fs_mount_cmn_err(flags, "SB re-read failed");
error = bp ? XFS_BUF_GETERROR(bp) : ENOMEM;
goto fail;
}
ASSERT(XFS_BUF_ISBUSY(bp));
ASSERT(XFS_BUF_VALUSEMA(bp) <= 0);
}
/* Initialize per-cpu counters */
xfs_icsb_reinit_counters(mp);
mp->m_sb_bp = bp;
xfs_buf_relse(bp);
ASSERT(XFS_BUF_VALUSEMA(bp) > 0);
return 0;
fail:
if (bp) {
XFS_BUF_UNMANAGE(bp);
xfs_buf_relse(bp);
}
return error;
}
/*
* xfs_mount_common
*
* Mount initialization code establishing various mount
* fields from the superblock associated with the given
* mount structure
*/
STATIC void
xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
{
int i;
mp->m_agfrotor = mp->m_agirotor = 0;
spinlock_init(&mp->m_agirotor_lock, "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_litino = sbp->sb_inodesize -
((uint)sizeof(xfs_dinode_core_t) + (uint)sizeof(xfs_agino_t));
mp->m_blockmask = sbp->sb_blocksize - 1;
mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
mp->m_blockwmask = mp->m_blockwsize - 1;
INIT_LIST_HEAD(&mp->m_del_inodes);
/*
* Setup for attributes, in case they get created.
* This value is for inodes getting attributes for the first time,
* the per-inode value is for old attribute values.
*/
ASSERT(sbp->sb_inodesize >= 256 && sbp->sb_inodesize <= 2048);
switch (sbp->sb_inodesize) {
case 256:
mp->m_attroffset = XFS_LITINO(mp) -
XFS_BMDR_SPACE_CALC(MINABTPTRS);
break;
case 512:
case 1024:
case 2048:
mp->m_attroffset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
break;
default:
ASSERT(0);
}
ASSERT(mp->m_attroffset < XFS_LITINO(mp));
for (i = 0; i < 2; i++) {
mp->m_alloc_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
xfs_alloc, i == 0);
mp->m_alloc_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
xfs_alloc, i == 0);
}
for (i = 0; i < 2; i++) {
mp->m_bmap_dmxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
xfs_bmbt, i == 0);
mp->m_bmap_dmnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
xfs_bmbt, i == 0);
}
for (i = 0; i < 2; i++) {
mp->m_inobt_mxr[i] = XFS_BTREE_BLOCK_MAXRECS(sbp->sb_blocksize,
xfs_inobt, i == 0);
mp->m_inobt_mnr[i] = XFS_BTREE_BLOCK_MINRECS(sbp->sb_blocksize,
xfs_inobt, i == 0);
}
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;
}
/*
* xfs_mountfs
*
* 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(
bhv_vfs_t *vfsp,
xfs_mount_t *mp,
int mfsi_flags)
{
xfs_buf_t *bp;
xfs_sb_t *sbp = &(mp->m_sb);
xfs_inode_t *rip;
bhv_vnode_t *rvp = NULL;
int readio_log, writeio_log;
xfs_daddr_t d;
__uint64_t ret64;
__int64_t update_flags;
uint quotamount, quotaflags;
int agno;
int uuid_mounted = 0;
int error = 0;
if (mp->m_sb_bp == NULL) {
if ((error = xfs_readsb(mp, mfsi_flags))) {
return error;
}
}
xfs_mount_common(mp, sbp);
/*
* 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.
*/
update_flags = 0LL;
if (mp->m_dalign && !(mfsi_flags & XFS_MFSI_SECOND)) {
/*
* 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)) {
if (mp->m_flags & XFS_MOUNT_RETERR) {
cmn_err(CE_WARN,
"XFS: alignment check 1 failed");
error = XFS_ERROR(EINVAL);
goto error1;
}
mp->m_dalign = mp->m_swidth = 0;
} else {
/*
* Convert the stripe unit and width to FSBs.
*/
mp->m_dalign = XFS_BB_TO_FSBT(mp, mp->m_dalign);
if (mp->m_dalign && (sbp->sb_agblocks % mp->m_dalign)) {
if (mp->m_flags & XFS_MOUNT_RETERR) {
error = XFS_ERROR(EINVAL);
goto error1;
}
xfs_fs_cmn_err(CE_WARN, mp,
"stripe alignment turned off: sunit(%d)/swidth(%d) incompatible with agsize(%d)",
mp->m_dalign, mp->m_swidth,
sbp->sb_agblocks);
mp->m_dalign = 0;
mp->m_swidth = 0;
} else if (mp->m_dalign) {
mp->m_swidth = XFS_BB_TO_FSBT(mp, mp->m_swidth);
} else {
if (mp->m_flags & XFS_MOUNT_RETERR) {
xfs_fs_cmn_err(CE_WARN, mp,
"stripe alignment turned off: sunit(%d) less than bsize(%d)",
mp->m_dalign,
mp->m_blockmask +1);
error = XFS_ERROR(EINVAL);
goto error1;
}
mp->m_swidth = 0;
}
}
/*
* Update superblock with new values
* and log changes
*/
if (XFS_SB_VERSION_HASDALIGN(sbp)) {
if (sbp->sb_unit != mp->m_dalign) {
sbp->sb_unit = mp->m_dalign;
update_flags |= XFS_SB_UNIT;
}
if (sbp->sb_width != mp->m_swidth) {
sbp->sb_width = mp->m_swidth;
update_flags |= XFS_SB_WIDTH;
}
}
} 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;
}
xfs_alloc_compute_maxlevels(mp);
xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
xfs_bmap_compute_maxlevels(mp, XFS_ATTR_FORK);
xfs_ialloc_compute_maxlevels(mp);
if (sbp->sb_imax_pct) {
__uint64_t icount;
/* Make sure the maximum inode count is a multiple of the
* units we allocate inodes in.
*/
icount = sbp->sb_dblocks * sbp->sb_imax_pct;
do_div(icount, 100);
do_div(icount, mp->m_ialloc_blks);
mp->m_maxicount = (icount * mp->m_ialloc_blks) <<
sbp->sb_inopblog;
} else
mp->m_maxicount = 0;
mp->m_maxioffset = xfs_max_file_offset(sbp->sb_blocklog);
/*
* XFS uses the uuid from the superblock as the unique
* identifier for fsid. We can not use the uuid from the volume
* since a single partition filesystem is identical to a single
* partition volume/filesystem.
*/
if ((mfsi_flags & XFS_MFSI_SECOND) == 0 &&
(mp->m_flags & XFS_MOUNT_NOUUID) == 0) {
if (xfs_uuid_mount(mp)) {
error = XFS_ERROR(EINVAL);
goto error1;
}
uuid_mounted=1;
ret64 = uuid_hash64(&sbp->sb_uuid);
memcpy(&vfsp->vfs_fsid, &ret64, sizeof(ret64));
}
/*
* Set the default minimum read and write sizes unless
* already specified in a mount option.
* We use smaller I/O sizes when the file system
* is being used for NFS service (wsync mount option).
*/
if (!(mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)) {
if (mp->m_flags & XFS_MOUNT_WSYNC) {
readio_log = XFS_WSYNC_READIO_LOG;
writeio_log = XFS_WSYNC_WRITEIO_LOG;
} else {
readio_log = XFS_READIO_LOG_LARGE;
writeio_log = XFS_WRITEIO_LOG_LARGE;
}
} else {
readio_log = mp->m_readio_log;
writeio_log = mp->m_writeio_log;
}
/*
* Set the number of readahead buffers to use based on
* physical memory size.
*/
if (xfs_physmem <= 4096) /* <= 16MB */
mp->m_nreadaheads = XFS_RW_NREADAHEAD_16MB;
else if (xfs_physmem <= 8192) /* <= 32MB */
mp->m_nreadaheads = XFS_RW_NREADAHEAD_32MB;
else
mp->m_nreadaheads = XFS_RW_NREADAHEAD_K32;
if (sbp->sb_blocklog > readio_log) {
mp->m_readio_log = sbp->sb_blocklog;
} else {
mp->m_readio_log = readio_log;
}
mp->m_readio_blocks = 1 << (mp->m_readio_log - sbp->sb_blocklog);
if (sbp->sb_blocklog > writeio_log) {
mp->m_writeio_log = sbp->sb_blocklog;
} else {
mp->m_writeio_log = writeio_log;
}
mp->m_writeio_blocks = 1 << (mp->m_writeio_log - sbp->sb_blocklog);
/*
* Set the inode cluster size based on the physical memory
* size. This may still be overridden by the file system
* block size if it is larger than the chosen cluster size.
*/
if (xfs_physmem <= btoc(32 * 1024 * 1024)) { /* <= 32 MB */
mp->m_inode_cluster_size = XFS_INODE_SMALL_CLUSTER_SIZE;
} else {
mp->m_inode_cluster_size = XFS_INODE_BIG_CLUSTER_SIZE;
}
/*
* Set whether we're using inode alignment.
*/
if (XFS_SB_VERSION_HASALIGN(&mp->m_sb) &&
mp->m_sb.sb_inoalignmt >=
XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
else
mp->m_inoalign_mask = 0;
/*
* If we are using stripe alignment, check whether
* the stripe unit is a multiple of the inode alignment
*/
if (mp->m_dalign && mp->m_inoalign_mask &&
!(mp->m_dalign & mp->m_inoalign_mask))
mp->m_sinoalign = mp->m_dalign;
else
mp->m_sinoalign = 0;
/*
* Check that the data (and log if separate) are an ok size.
*/
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) {
cmn_err(CE_WARN, "XFS: size check 1 failed");
error = XFS_ERROR(E2BIG);
goto error1;
}
error = xfs_read_buf(mp, mp->m_ddev_targp,
d - XFS_FSS_TO_BB(mp, 1),
XFS_FSS_TO_BB(mp, 1), 0, &bp);
if (!error) {
xfs_buf_relse(bp);
} else {
cmn_err(CE_WARN, "XFS: size check 2 failed");
if (error == ENOSPC) {
error = XFS_ERROR(E2BIG);
}
goto error1;
}
if (((mfsi_flags & XFS_MFSI_CLIENT) == 0) &&
mp->m_logdev_targp != mp->m_ddev_targp) {
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) {
cmn_err(CE_WARN, "XFS: size check 3 failed");
error = XFS_ERROR(E2BIG);
goto error1;
}
error = xfs_read_buf(mp, mp->m_logdev_targp,
d - XFS_FSB_TO_BB(mp, 1),
XFS_FSB_TO_BB(mp, 1), 0, &bp);
if (!error) {
xfs_buf_relse(bp);
} else {
cmn_err(CE_WARN, "XFS: size check 3 failed");
if (error == ENOSPC) {
error = XFS_ERROR(E2BIG);
}
goto error1;
}
}
/*
* Initialize realtime fields in the mount structure
*/
if ((error = xfs_rtmount_init(mp))) {
cmn_err(CE_WARN, "XFS: RT mount failed");
goto error1;
}
/*
* For client case we are done now
*/
if (mfsi_flags & XFS_MFSI_CLIENT) {
return 0;
}
/*
* Copies the low order bits of the timestamp and the randomly
* set "sequence" number out of a UUID.
*/
uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid);
/*
* The vfs structure needs to have a file system independent
* way of checking for the invariant file system ID. Since it
* can't look at mount structures it has a pointer to the data
* in the mount structure.
*
* File systems that don't support user level file handles (i.e.
* all of them except for XFS) will leave vfs_altfsid as NULL.
*/
vfsp->vfs_altfsid = (xfs_fsid_t *)mp->m_fixedfsid;
mp->m_dmevmask = 0; /* not persistent; set after each mount */
xfs_dir_mount(mp);
/*
* Initialize the attribute manager's entries.
*/
mp->m_attr_magicpct = (mp->m_sb.sb_blocksize * 37) / 100;
/*
* Initialize the precomputed transaction reservations values.
*/
xfs_trans_init(mp);
/*
* Allocate and initialize the inode hash table for this
* file system.
*/
xfs_ihash_init(mp);
xfs_chash_init(mp);
/*
* Allocate and initialize the per-ag data.
*/
init_rwsem(&mp->m_peraglock);
mp->m_perag =
kmem_zalloc(sbp->sb_agcount * sizeof(xfs_perag_t), KM_SLEEP);
mp->m_maxagi = xfs_initialize_perag(vfsp, mp, sbp->sb_agcount);
/*
* log's mount-time initialization. Perform 1st part recovery if needed
*/
if (likely(sbp->sb_logblocks > 0)) { /* check for volume case */
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) {
cmn_err(CE_WARN, "XFS: log mount failed");
goto error2;
}
} else { /* No log has been defined */
cmn_err(CE_WARN, "XFS: no log defined");
XFS_ERROR_REPORT("xfs_mountfs_int(1)", XFS_ERRLEVEL_LOW, mp);
error = XFS_ERROR(EFSCORRUPTED);
goto error2;
}
/*
* Get and sanity-check the root inode.
* Save the pointer to it in the mount structure.
*/
error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip, 0);
if (error) {
cmn_err(CE_WARN, "XFS: failed to read root inode");
goto error3;
}
ASSERT(rip != NULL);
rvp = XFS_ITOV(rip);
if (unlikely((rip->i_d.di_mode & S_IFMT) != S_IFDIR)) {
cmn_err(CE_WARN, "XFS: corrupted root inode");
cmn_err(CE_WARN, "Device %s - root %llu is not a directory",
XFS_BUFTARG_NAME(mp->m_ddev_targp),
(unsigned long long)rip->i_ino);
xfs_iunlock(rip, XFS_ILOCK_EXCL);
XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW,
mp);
error = XFS_ERROR(EFSCORRUPTED);
goto error4;