forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xfs_super.c
1997 lines (1753 loc) · 50.4 KB
/
xfs_super.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) 2000-2006 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_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_sb.h"
#include "xfs_mount.h"
#include "xfs_da_format.h"
#include "xfs_inode.h"
#include "xfs_btree.h"
#include "xfs_bmap.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_fsops.h"
#include "xfs_trans.h"
#include "xfs_buf_item.h"
#include "xfs_log.h"
#include "xfs_log_priv.h"
#include "xfs_da_btree.h"
#include "xfs_dir2.h"
#include "xfs_extfree_item.h"
#include "xfs_mru_cache.h"
#include "xfs_inode_item.h"
#include "xfs_icache.h"
#include "xfs_trace.h"
#include "xfs_icreate_item.h"
#include "xfs_filestream.h"
#include "xfs_quota.h"
#include "xfs_sysfs.h"
#include "xfs_ondisk.h"
#include "xfs_rmap_item.h"
#include <linux/namei.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/mount.h>
#include <linux/mempool.h>
#include <linux/writeback.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/parser.h>
static const struct super_operations xfs_super_operations;
struct bio_set *xfs_ioend_bioset;
static struct kset *xfs_kset; /* top-level xfs sysfs dir */
#ifdef DEBUG
static struct xfs_kobj xfs_dbg_kobj; /* global debug sysfs attrs */
#endif
/*
* Table driven mount option parser.
*/
enum {
Opt_logbufs, Opt_logbsize, Opt_logdev, Opt_rtdev, Opt_biosize,
Opt_wsync, Opt_noalign, Opt_swalloc, Opt_sunit, Opt_swidth, Opt_nouuid,
Opt_mtpt, Opt_grpid, Opt_nogrpid, Opt_bsdgroups, Opt_sysvgroups,
Opt_allocsize, Opt_norecovery, Opt_barrier, Opt_nobarrier,
Opt_inode64, Opt_inode32, Opt_ikeep, Opt_noikeep,
Opt_largeio, Opt_nolargeio, Opt_attr2, Opt_noattr2, Opt_filestreams,
Opt_quota, Opt_noquota, Opt_usrquota, Opt_grpquota, Opt_prjquota,
Opt_uquota, Opt_gquota, Opt_pquota,
Opt_uqnoenforce, Opt_gqnoenforce, Opt_pqnoenforce, Opt_qnoenforce,
Opt_discard, Opt_nodiscard, Opt_dax, Opt_err,
};
static const match_table_t tokens = {
{Opt_logbufs, "logbufs=%u"}, /* number of XFS log buffers */
{Opt_logbsize, "logbsize=%s"}, /* size of XFS log buffers */
{Opt_logdev, "logdev=%s"}, /* log device */
{Opt_rtdev, "rtdev=%s"}, /* realtime I/O device */
{Opt_biosize, "biosize=%u"}, /* log2 of preferred buffered io size */
{Opt_wsync, "wsync"}, /* safe-mode nfs compatible mount */
{Opt_noalign, "noalign"}, /* turn off stripe alignment */
{Opt_swalloc, "swalloc"}, /* turn on stripe width allocation */
{Opt_sunit, "sunit=%u"}, /* data volume stripe unit */
{Opt_swidth, "swidth=%u"}, /* data volume stripe width */
{Opt_nouuid, "nouuid"}, /* ignore filesystem UUID */
{Opt_mtpt, "mtpt"}, /* filesystem mount point */
{Opt_grpid, "grpid"}, /* group-ID from parent directory */
{Opt_nogrpid, "nogrpid"}, /* group-ID from current process */
{Opt_bsdgroups, "bsdgroups"}, /* group-ID from parent directory */
{Opt_sysvgroups,"sysvgroups"}, /* group-ID from current process */
{Opt_allocsize, "allocsize=%s"},/* preferred allocation size */
{Opt_norecovery,"norecovery"}, /* don't run XFS recovery */
{Opt_barrier, "barrier"}, /* use writer barriers for log write and
* unwritten extent conversion */
{Opt_nobarrier, "nobarrier"}, /* .. disable */
{Opt_inode64, "inode64"}, /* inodes can be allocated anywhere */
{Opt_inode32, "inode32"}, /* inode allocation limited to
* XFS_MAXINUMBER_32 */
{Opt_ikeep, "ikeep"}, /* do not free empty inode clusters */
{Opt_noikeep, "noikeep"}, /* free empty inode clusters */
{Opt_largeio, "largeio"}, /* report large I/O sizes in stat() */
{Opt_nolargeio, "nolargeio"}, /* do not report large I/O sizes
* in stat(). */
{Opt_attr2, "attr2"}, /* do use attr2 attribute format */
{Opt_noattr2, "noattr2"}, /* do not use attr2 attribute format */
{Opt_filestreams,"filestreams"},/* use filestreams allocator */
{Opt_quota, "quota"}, /* disk quotas (user) */
{Opt_noquota, "noquota"}, /* no quotas */
{Opt_usrquota, "usrquota"}, /* user quota enabled */
{Opt_grpquota, "grpquota"}, /* group quota enabled */
{Opt_prjquota, "prjquota"}, /* project quota enabled */
{Opt_uquota, "uquota"}, /* user quota (IRIX variant) */
{Opt_gquota, "gquota"}, /* group quota (IRIX variant) */
{Opt_pquota, "pquota"}, /* project quota (IRIX variant) */
{Opt_uqnoenforce,"uqnoenforce"},/* user quota limit enforcement */
{Opt_gqnoenforce,"gqnoenforce"},/* group quota limit enforcement */
{Opt_pqnoenforce,"pqnoenforce"},/* project quota limit enforcement */
{Opt_qnoenforce, "qnoenforce"}, /* same as uqnoenforce */
{Opt_discard, "discard"}, /* Discard unused blocks */
{Opt_nodiscard, "nodiscard"}, /* Do not discard unused blocks */
{Opt_dax, "dax"}, /* Enable direct access to bdev pages */
{Opt_err, NULL},
};
STATIC int
suffix_kstrtoint(const substring_t *s, unsigned int base, int *res)
{
int last, shift_left_factor = 0, _res;
char *value;
int ret = 0;
value = match_strdup(s);
if (!value)
return -ENOMEM;
last = strlen(value) - 1;
if (value[last] == 'K' || value[last] == 'k') {
shift_left_factor = 10;
value[last] = '\0';
}
if (value[last] == 'M' || value[last] == 'm') {
shift_left_factor = 20;
value[last] = '\0';
}
if (value[last] == 'G' || value[last] == 'g') {
shift_left_factor = 30;
value[last] = '\0';
}
if (kstrtoint(value, base, &_res))
ret = -EINVAL;
kfree(value);
*res = _res << shift_left_factor;
return ret;
}
/*
* This function fills in xfs_mount_t fields based on mount args.
* Note: the superblock has _not_ yet been read in.
*
* Note that this function leaks the various device name allocations on
* failure. The caller takes care of them.
*
* *sb is const because this is also used to test options on the remount
* path, and we don't want this to have any side effects at remount time.
* Today this function does not change *sb, but just to future-proof...
*/
STATIC int
xfs_parseargs(
struct xfs_mount *mp,
char *options)
{
const struct super_block *sb = mp->m_super;
char *p;
substring_t args[MAX_OPT_ARGS];
int dsunit = 0;
int dswidth = 0;
int iosize = 0;
__uint8_t iosizelog = 0;
/*
* set up the mount name first so all the errors will refer to the
* correct device.
*/
mp->m_fsname = kstrndup(sb->s_id, MAXNAMELEN, GFP_KERNEL);
if (!mp->m_fsname)
return -ENOMEM;
mp->m_fsname_len = strlen(mp->m_fsname) + 1;
/*
* Copy binary VFS mount flags we are interested in.
*/
if (sb->s_flags & MS_RDONLY)
mp->m_flags |= XFS_MOUNT_RDONLY;
if (sb->s_flags & MS_DIRSYNC)
mp->m_flags |= XFS_MOUNT_DIRSYNC;
if (sb->s_flags & MS_SYNCHRONOUS)
mp->m_flags |= XFS_MOUNT_WSYNC;
/*
* Set some default flags that could be cleared by the mount option
* parsing.
*/
mp->m_flags |= XFS_MOUNT_BARRIER;
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
/*
* These can be overridden by the mount option parsing.
*/
mp->m_logbufs = -1;
mp->m_logbsize = -1;
if (!options)
goto done;
while ((p = strsep(&options, ",")) != NULL) {
int token;
if (!*p)
continue;
token = match_token(p, tokens, args);
switch (token) {
case Opt_logbufs:
if (match_int(args, &mp->m_logbufs))
return -EINVAL;
break;
case Opt_logbsize:
if (suffix_kstrtoint(args, 10, &mp->m_logbsize))
return -EINVAL;
break;
case Opt_logdev:
mp->m_logname = match_strdup(args);
if (!mp->m_logname)
return -ENOMEM;
break;
case Opt_mtpt:
xfs_warn(mp, "%s option not allowed on this system", p);
return -EINVAL;
case Opt_rtdev:
mp->m_rtname = match_strdup(args);
if (!mp->m_rtname)
return -ENOMEM;
break;
case Opt_allocsize:
case Opt_biosize:
if (suffix_kstrtoint(args, 10, &iosize))
return -EINVAL;
iosizelog = ffs(iosize) - 1;
break;
case Opt_grpid:
case Opt_bsdgroups:
mp->m_flags |= XFS_MOUNT_GRPID;
break;
case Opt_nogrpid:
case Opt_sysvgroups:
mp->m_flags &= ~XFS_MOUNT_GRPID;
break;
case Opt_wsync:
mp->m_flags |= XFS_MOUNT_WSYNC;
break;
case Opt_norecovery:
mp->m_flags |= XFS_MOUNT_NORECOVERY;
break;
case Opt_noalign:
mp->m_flags |= XFS_MOUNT_NOALIGN;
break;
case Opt_swalloc:
mp->m_flags |= XFS_MOUNT_SWALLOC;
break;
case Opt_sunit:
if (match_int(args, &dsunit))
return -EINVAL;
break;
case Opt_swidth:
if (match_int(args, &dswidth))
return -EINVAL;
break;
case Opt_inode32:
mp->m_flags |= XFS_MOUNT_SMALL_INUMS;
break;
case Opt_inode64:
mp->m_flags &= ~XFS_MOUNT_SMALL_INUMS;
break;
case Opt_nouuid:
mp->m_flags |= XFS_MOUNT_NOUUID;
break;
case Opt_barrier:
mp->m_flags |= XFS_MOUNT_BARRIER;
break;
case Opt_nobarrier:
mp->m_flags &= ~XFS_MOUNT_BARRIER;
break;
case Opt_ikeep:
mp->m_flags |= XFS_MOUNT_IKEEP;
break;
case Opt_noikeep:
mp->m_flags &= ~XFS_MOUNT_IKEEP;
break;
case Opt_largeio:
mp->m_flags &= ~XFS_MOUNT_COMPAT_IOSIZE;
break;
case Opt_nolargeio:
mp->m_flags |= XFS_MOUNT_COMPAT_IOSIZE;
break;
case Opt_attr2:
mp->m_flags |= XFS_MOUNT_ATTR2;
break;
case Opt_noattr2:
mp->m_flags &= ~XFS_MOUNT_ATTR2;
mp->m_flags |= XFS_MOUNT_NOATTR2;
break;
case Opt_filestreams:
mp->m_flags |= XFS_MOUNT_FILESTREAMS;
break;
case Opt_noquota:
mp->m_qflags &= ~XFS_ALL_QUOTA_ACCT;
mp->m_qflags &= ~XFS_ALL_QUOTA_ENFD;
mp->m_qflags &= ~XFS_ALL_QUOTA_ACTIVE;
break;
case Opt_quota:
case Opt_uquota:
case Opt_usrquota:
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE |
XFS_UQUOTA_ENFD);
break;
case Opt_qnoenforce:
case Opt_uqnoenforce:
mp->m_qflags |= (XFS_UQUOTA_ACCT | XFS_UQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_UQUOTA_ENFD;
break;
case Opt_pquota:
case Opt_prjquota:
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE |
XFS_PQUOTA_ENFD);
break;
case Opt_pqnoenforce:
mp->m_qflags |= (XFS_PQUOTA_ACCT | XFS_PQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_PQUOTA_ENFD;
break;
case Opt_gquota:
case Opt_grpquota:
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE |
XFS_GQUOTA_ENFD);
break;
case Opt_gqnoenforce:
mp->m_qflags |= (XFS_GQUOTA_ACCT | XFS_GQUOTA_ACTIVE);
mp->m_qflags &= ~XFS_GQUOTA_ENFD;
break;
case Opt_discard:
mp->m_flags |= XFS_MOUNT_DISCARD;
break;
case Opt_nodiscard:
mp->m_flags &= ~XFS_MOUNT_DISCARD;
break;
#ifdef CONFIG_FS_DAX
case Opt_dax:
mp->m_flags |= XFS_MOUNT_DAX;
break;
#endif
default:
xfs_warn(mp, "unknown mount option [%s].", p);
return -EINVAL;
}
}
/*
* no recovery flag requires a read-only mount
*/
if ((mp->m_flags & XFS_MOUNT_NORECOVERY) &&
!(mp->m_flags & XFS_MOUNT_RDONLY)) {
xfs_warn(mp, "no-recovery mounts must be read-only.");
return -EINVAL;
}
if ((mp->m_flags & XFS_MOUNT_NOALIGN) && (dsunit || dswidth)) {
xfs_warn(mp,
"sunit and swidth options incompatible with the noalign option");
return -EINVAL;
}
#ifndef CONFIG_XFS_QUOTA
if (XFS_IS_QUOTA_RUNNING(mp)) {
xfs_warn(mp, "quota support not available in this kernel.");
return -EINVAL;
}
#endif
if ((dsunit && !dswidth) || (!dsunit && dswidth)) {
xfs_warn(mp, "sunit and swidth must be specified together");
return -EINVAL;
}
if (dsunit && (dswidth % dsunit != 0)) {
xfs_warn(mp,
"stripe width (%d) must be a multiple of the stripe unit (%d)",
dswidth, dsunit);
return -EINVAL;
}
done:
if (dsunit && !(mp->m_flags & XFS_MOUNT_NOALIGN)) {
/*
* At this point the superblock has not been read
* in, therefore we do not know the block size.
* Before the mount call ends we will convert
* these to FSBs.
*/
mp->m_dalign = dsunit;
mp->m_swidth = dswidth;
}
if (mp->m_logbufs != -1 &&
mp->m_logbufs != 0 &&
(mp->m_logbufs < XLOG_MIN_ICLOGS ||
mp->m_logbufs > XLOG_MAX_ICLOGS)) {
xfs_warn(mp, "invalid logbufs value: %d [not %d-%d]",
mp->m_logbufs, XLOG_MIN_ICLOGS, XLOG_MAX_ICLOGS);
return -EINVAL;
}
if (mp->m_logbsize != -1 &&
mp->m_logbsize != 0 &&
(mp->m_logbsize < XLOG_MIN_RECORD_BSIZE ||
mp->m_logbsize > XLOG_MAX_RECORD_BSIZE ||
!is_power_of_2(mp->m_logbsize))) {
xfs_warn(mp,
"invalid logbufsize: %d [not 16k,32k,64k,128k or 256k]",
mp->m_logbsize);
return -EINVAL;
}
if (iosizelog) {
if (iosizelog > XFS_MAX_IO_LOG ||
iosizelog < XFS_MIN_IO_LOG) {
xfs_warn(mp, "invalid log iosize: %d [not %d-%d]",
iosizelog, XFS_MIN_IO_LOG,
XFS_MAX_IO_LOG);
return -EINVAL;
}
mp->m_flags |= XFS_MOUNT_DFLT_IOSIZE;
mp->m_readio_log = iosizelog;
mp->m_writeio_log = iosizelog;
}
return 0;
}
struct proc_xfs_info {
uint64_t flag;
char *str;
};
STATIC int
xfs_showargs(
struct xfs_mount *mp,
struct seq_file *m)
{
static struct proc_xfs_info xfs_info_set[] = {
/* the few simple ones we can get from the mount struct */
{ XFS_MOUNT_IKEEP, ",ikeep" },
{ XFS_MOUNT_WSYNC, ",wsync" },
{ XFS_MOUNT_NOALIGN, ",noalign" },
{ XFS_MOUNT_SWALLOC, ",swalloc" },
{ XFS_MOUNT_NOUUID, ",nouuid" },
{ XFS_MOUNT_NORECOVERY, ",norecovery" },
{ XFS_MOUNT_ATTR2, ",attr2" },
{ XFS_MOUNT_FILESTREAMS, ",filestreams" },
{ XFS_MOUNT_GRPID, ",grpid" },
{ XFS_MOUNT_DISCARD, ",discard" },
{ XFS_MOUNT_SMALL_INUMS, ",inode32" },
{ XFS_MOUNT_DAX, ",dax" },
{ 0, NULL }
};
static struct proc_xfs_info xfs_info_unset[] = {
/* the few simple ones we can get from the mount struct */
{ XFS_MOUNT_COMPAT_IOSIZE, ",largeio" },
{ XFS_MOUNT_BARRIER, ",nobarrier" },
{ XFS_MOUNT_SMALL_INUMS, ",inode64" },
{ 0, NULL }
};
struct proc_xfs_info *xfs_infop;
for (xfs_infop = xfs_info_set; xfs_infop->flag; xfs_infop++) {
if (mp->m_flags & xfs_infop->flag)
seq_puts(m, xfs_infop->str);
}
for (xfs_infop = xfs_info_unset; xfs_infop->flag; xfs_infop++) {
if (!(mp->m_flags & xfs_infop->flag))
seq_puts(m, xfs_infop->str);
}
if (mp->m_flags & XFS_MOUNT_DFLT_IOSIZE)
seq_printf(m, ",allocsize=%dk",
(int)(1 << mp->m_writeio_log) >> 10);
if (mp->m_logbufs > 0)
seq_printf(m, ",logbufs=%d", mp->m_logbufs);
if (mp->m_logbsize > 0)
seq_printf(m, ",logbsize=%dk", mp->m_logbsize >> 10);
if (mp->m_logname)
seq_show_option(m, "logdev", mp->m_logname);
if (mp->m_rtname)
seq_show_option(m, "rtdev", mp->m_rtname);
if (mp->m_dalign > 0)
seq_printf(m, ",sunit=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_dalign));
if (mp->m_swidth > 0)
seq_printf(m, ",swidth=%d",
(int)XFS_FSB_TO_BB(mp, mp->m_swidth));
if (mp->m_qflags & (XFS_UQUOTA_ACCT|XFS_UQUOTA_ENFD))
seq_puts(m, ",usrquota");
else if (mp->m_qflags & XFS_UQUOTA_ACCT)
seq_puts(m, ",uqnoenforce");
if (mp->m_qflags & XFS_PQUOTA_ACCT) {
if (mp->m_qflags & XFS_PQUOTA_ENFD)
seq_puts(m, ",prjquota");
else
seq_puts(m, ",pqnoenforce");
}
if (mp->m_qflags & XFS_GQUOTA_ACCT) {
if (mp->m_qflags & XFS_GQUOTA_ENFD)
seq_puts(m, ",grpquota");
else
seq_puts(m, ",gqnoenforce");
}
if (!(mp->m_qflags & XFS_ALL_QUOTA_ACCT))
seq_puts(m, ",noquota");
return 0;
}
static __uint64_t
xfs_max_file_offset(
unsigned int blockshift)
{
unsigned int pagefactor = 1;
unsigned int bitshift = BITS_PER_LONG - 1;
/* Figure out maximum filesize, on Linux this can depend on
* the filesystem blocksize (on 32 bit platforms).
* __block_write_begin does this in an [unsigned] long...
* page->index << (PAGE_SHIFT - bbits)
* So, for page sized blocks (4K on 32 bit platforms),
* this wraps at around 8Tb (hence MAX_LFS_FILESIZE which is
* (((u64)PAGE_SIZE << (BITS_PER_LONG-1))-1)
* but for smaller blocksizes it is less (bbits = log2 bsize).
* Note1: get_block_t takes a long (implicit cast from above)
* Note2: The Large Block Device (LBD and HAVE_SECTOR_T) patch
* can optionally convert the [unsigned] long from above into
* an [unsigned] long long.
*/
#if BITS_PER_LONG == 32
# if defined(CONFIG_LBDAF)
ASSERT(sizeof(sector_t) == 8);
pagefactor = PAGE_SIZE;
bitshift = BITS_PER_LONG;
# else
pagefactor = PAGE_SIZE >> (PAGE_SHIFT - blockshift);
# endif
#endif
return (((__uint64_t)pagefactor) << bitshift) - 1;
}
/*
* Set parameters for inode allocation heuristics, taking into account
* filesystem size and inode32/inode64 mount options; i.e. specifically
* whether or not XFS_MOUNT_SMALL_INUMS is set.
*
* Inode allocation patterns are altered only if inode32 is requested
* (XFS_MOUNT_SMALL_INUMS), and the filesystem is sufficiently large.
* If altered, XFS_MOUNT_32BITINODES is set as well.
*
* An agcount independent of that in the mount structure is provided
* because in the growfs case, mp->m_sb.sb_agcount is not yet updated
* to the potentially higher ag count.
*
* Returns the maximum AG index which may contain inodes.
*/
xfs_agnumber_t
xfs_set_inode_alloc(
struct xfs_mount *mp,
xfs_agnumber_t agcount)
{
xfs_agnumber_t index;
xfs_agnumber_t maxagi = 0;
xfs_sb_t *sbp = &mp->m_sb;
xfs_agnumber_t max_metadata;
xfs_agino_t agino;
xfs_ino_t ino;
/*
* Calculate how much should be reserved for inodes to meet
* the max inode percentage. Used only for inode32.
*/
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;
}
/* Get the last possible inode in the filesystem */
agino = XFS_OFFBNO_TO_AGINO(mp, sbp->sb_agblocks - 1, 0);
ino = XFS_AGINO_TO_INO(mp, agcount - 1, agino);
/*
* If user asked for no more than 32-bit inodes, and the fs is
* sufficiently large, set XFS_MOUNT_32BITINODES if we must alter
* the allocator to accommodate the request.
*/
if ((mp->m_flags & XFS_MOUNT_SMALL_INUMS) && ino > XFS_MAXINUMBER_32)
mp->m_flags |= XFS_MOUNT_32BITINODES;
else
mp->m_flags &= ~XFS_MOUNT_32BITINODES;
for (index = 0; index < agcount; index++) {
struct xfs_perag *pag;
ino = XFS_AGINO_TO_INO(mp, index, agino);
pag = xfs_perag_get(mp, index);
if (mp->m_flags & XFS_MOUNT_32BITINODES) {
if (ino > XFS_MAXINUMBER_32) {
pag->pagi_inodeok = 0;
pag->pagf_metadata = 0;
} else {
pag->pagi_inodeok = 1;
maxagi++;
if (index < max_metadata)
pag->pagf_metadata = 1;
else
pag->pagf_metadata = 0;
}
} else {
pag->pagi_inodeok = 1;
pag->pagf_metadata = 0;
}
xfs_perag_put(pag);
}
return (mp->m_flags & XFS_MOUNT_32BITINODES) ? maxagi : agcount;
}
STATIC int
xfs_blkdev_get(
xfs_mount_t *mp,
const char *name,
struct block_device **bdevp)
{
int error = 0;
*bdevp = blkdev_get_by_path(name, FMODE_READ|FMODE_WRITE|FMODE_EXCL,
mp);
if (IS_ERR(*bdevp)) {
error = PTR_ERR(*bdevp);
xfs_warn(mp, "Invalid device [%s], error=%d", name, error);
}
return error;
}
STATIC void
xfs_blkdev_put(
struct block_device *bdev)
{
if (bdev)
blkdev_put(bdev, FMODE_READ|FMODE_WRITE|FMODE_EXCL);
}
void
xfs_blkdev_issue_flush(
xfs_buftarg_t *buftarg)
{
blkdev_issue_flush(buftarg->bt_bdev, GFP_NOFS, NULL);
}
STATIC void
xfs_close_devices(
struct xfs_mount *mp)
{
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
struct block_device *logdev = mp->m_logdev_targp->bt_bdev;
xfs_free_buftarg(mp, mp->m_logdev_targp);
xfs_blkdev_put(logdev);
}
if (mp->m_rtdev_targp) {
struct block_device *rtdev = mp->m_rtdev_targp->bt_bdev;
xfs_free_buftarg(mp, mp->m_rtdev_targp);
xfs_blkdev_put(rtdev);
}
xfs_free_buftarg(mp, mp->m_ddev_targp);
}
/*
* The file system configurations are:
* (1) device (partition) with data and internal log
* (2) logical volume with data and log subvolumes.
* (3) logical volume with data, log, and realtime subvolumes.
*
* We only have to handle opening the log and realtime volumes here if
* they are present. The data subvolume has already been opened by
* get_sb_bdev() and is stored in sb->s_bdev.
*/
STATIC int
xfs_open_devices(
struct xfs_mount *mp)
{
struct block_device *ddev = mp->m_super->s_bdev;
struct block_device *logdev = NULL, *rtdev = NULL;
int error;
/*
* Open real time and log devices - order is important.
*/
if (mp->m_logname) {
error = xfs_blkdev_get(mp, mp->m_logname, &logdev);
if (error)
goto out;
}
if (mp->m_rtname) {
error = xfs_blkdev_get(mp, mp->m_rtname, &rtdev);
if (error)
goto out_close_logdev;
if (rtdev == ddev || rtdev == logdev) {
xfs_warn(mp,
"Cannot mount filesystem with identical rtdev and ddev/logdev.");
error = -EINVAL;
goto out_close_rtdev;
}
}
/*
* Setup xfs_mount buffer target pointers
*/
error = -ENOMEM;
mp->m_ddev_targp = xfs_alloc_buftarg(mp, ddev);
if (!mp->m_ddev_targp)
goto out_close_rtdev;
if (rtdev) {
mp->m_rtdev_targp = xfs_alloc_buftarg(mp, rtdev);
if (!mp->m_rtdev_targp)
goto out_free_ddev_targ;
}
if (logdev && logdev != ddev) {
mp->m_logdev_targp = xfs_alloc_buftarg(mp, logdev);
if (!mp->m_logdev_targp)
goto out_free_rtdev_targ;
} else {
mp->m_logdev_targp = mp->m_ddev_targp;
}
return 0;
out_free_rtdev_targ:
if (mp->m_rtdev_targp)
xfs_free_buftarg(mp, mp->m_rtdev_targp);
out_free_ddev_targ:
xfs_free_buftarg(mp, mp->m_ddev_targp);
out_close_rtdev:
xfs_blkdev_put(rtdev);
out_close_logdev:
if (logdev && logdev != ddev)
xfs_blkdev_put(logdev);
out:
return error;
}
/*
* Setup xfs_mount buffer target pointers based on superblock
*/
STATIC int
xfs_setup_devices(
struct xfs_mount *mp)
{
int error;
error = xfs_setsize_buftarg(mp->m_ddev_targp, mp->m_sb.sb_sectsize);
if (error)
return error;
if (mp->m_logdev_targp && mp->m_logdev_targp != mp->m_ddev_targp) {
unsigned int log_sector_size = BBSIZE;
if (xfs_sb_version_hassector(&mp->m_sb))
log_sector_size = mp->m_sb.sb_logsectsize;
error = xfs_setsize_buftarg(mp->m_logdev_targp,
log_sector_size);
if (error)
return error;
}
if (mp->m_rtdev_targp) {
error = xfs_setsize_buftarg(mp->m_rtdev_targp,
mp->m_sb.sb_sectsize);
if (error)
return error;
}
return 0;
}
STATIC int
xfs_init_mount_workqueues(
struct xfs_mount *mp)
{
mp->m_buf_workqueue = alloc_workqueue("xfs-buf/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 1, mp->m_fsname);
if (!mp->m_buf_workqueue)
goto out;
mp->m_data_workqueue = alloc_workqueue("xfs-data/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_data_workqueue)
goto out_destroy_buf;
mp->m_unwritten_workqueue = alloc_workqueue("xfs-conv/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_unwritten_workqueue)
goto out_destroy_data_iodone_queue;
mp->m_cil_workqueue = alloc_workqueue("xfs-cil/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_cil_workqueue)
goto out_destroy_unwritten;
mp->m_reclaim_workqueue = alloc_workqueue("xfs-reclaim/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_reclaim_workqueue)
goto out_destroy_cil;
mp->m_log_workqueue = alloc_workqueue("xfs-log/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE|WQ_HIGHPRI, 0,
mp->m_fsname);
if (!mp->m_log_workqueue)
goto out_destroy_reclaim;
mp->m_eofblocks_workqueue = alloc_workqueue("xfs-eofblocks/%s",
WQ_MEM_RECLAIM|WQ_FREEZABLE, 0, mp->m_fsname);
if (!mp->m_eofblocks_workqueue)
goto out_destroy_log;
return 0;
out_destroy_log:
destroy_workqueue(mp->m_log_workqueue);
out_destroy_reclaim:
destroy_workqueue(mp->m_reclaim_workqueue);
out_destroy_cil:
destroy_workqueue(mp->m_cil_workqueue);
out_destroy_unwritten:
destroy_workqueue(mp->m_unwritten_workqueue);
out_destroy_data_iodone_queue:
destroy_workqueue(mp->m_data_workqueue);
out_destroy_buf:
destroy_workqueue(mp->m_buf_workqueue);
out:
return -ENOMEM;
}
STATIC void
xfs_destroy_mount_workqueues(
struct xfs_mount *mp)
{
destroy_workqueue(mp->m_eofblocks_workqueue);
destroy_workqueue(mp->m_log_workqueue);
destroy_workqueue(mp->m_reclaim_workqueue);
destroy_workqueue(mp->m_cil_workqueue);
destroy_workqueue(mp->m_data_workqueue);
destroy_workqueue(mp->m_unwritten_workqueue);
destroy_workqueue(mp->m_buf_workqueue);
}
/*
* Flush all dirty data to disk. Must not be called while holding an XFS_ILOCK
* or a page lock. We use sync_inodes_sb() here to ensure we block while waiting
* for IO to complete so that we effectively throttle multiple callers to the
* rate at which IO is completing.
*/
void
xfs_flush_inodes(
struct xfs_mount *mp)
{
struct super_block *sb = mp->m_super;
if (down_read_trylock(&sb->s_umount)) {
sync_inodes_sb(sb);
up_read(&sb->s_umount);
}
}
/* Catch misguided souls that try to use this interface on XFS */
STATIC struct inode *
xfs_fs_alloc_inode(
struct super_block *sb)
{
BUG();
return NULL;
}
/*
* Now that the generic code is guaranteed not to be accessing
* the linux inode, we can inactivate and reclaim the inode.
*/
STATIC void
xfs_fs_destroy_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
trace_xfs_destroy_inode(ip);
ASSERT(!rwsem_is_locked(&ip->i_iolock.mr_lock));
XFS_STATS_INC(ip->i_mount, vn_rele);
XFS_STATS_INC(ip->i_mount, vn_remove);
xfs_inactive(ip);
ASSERT(XFS_FORCED_SHUTDOWN(ip->i_mount) || ip->i_delayed_blks == 0);
XFS_STATS_INC(ip->i_mount, vn_reclaim);
/*
* We should never get here with one of the reclaim flags already set.
*/
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIMABLE));
ASSERT_ALWAYS(!xfs_iflags_test(ip, XFS_IRECLAIM));
/*
* We always use background reclaim here because even if the
* inode is clean, it still may be under IO and hence we have
* to take the flush lock. The background reclaim path handles
* this more efficiently than we can here, so simply let background
* reclaim tear down all inodes.
*/
xfs_inode_set_reclaim_tag(ip);
}
/*
* Slab object creation initialisation for the XFS inode.
* This covers only the idempotent fields in the XFS inode;
* all other fields need to be initialised on allocation
* from the slab. This avoids the need to repeatedly initialise
* fields in the xfs inode that left in the initialise state
* when freeing the inode.
*/
STATIC void
xfs_fs_inode_init_once(
void *inode)
{
struct xfs_inode *ip = inode;
memset(ip, 0, sizeof(struct xfs_inode));
/* vfs inode */
inode_init_once(VFS_I(ip));
/* xfs inode */
atomic_set(&ip->i_pincount, 0);
spin_lock_init(&ip->i_flags_lock);
mrlock_init(&ip->i_mmaplock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
mrlock_init(&ip->i_lock, MRLOCK_ALLOW_EQUAL_PRI|MRLOCK_BARRIER,
"xfsino", ip->i_ino);
}
/*
* We do an unlocked check for XFS_IDONTCACHE here because we are already
* serialised against cache hits here via the inode->i_lock and igrab() in
* xfs_iget_cache_hit(). Hence a lookup that might clear this flag will not be
* racing with us, and it avoids needing to grab a spinlock here for every inode