forked from openbmc/linux
-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathsuper.c
2672 lines (2296 loc) · 68.9 KB
/
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
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* super.c
*
* load/unload driver, mount/dismount volumes
*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/module.h>
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/random.h>
#include <linux/statfs.h>
#include <linux/moduleparam.h>
#include <linux/blkdev.h>
#include <linux/socket.h>
#include <linux/inet.h>
#include <linux/parser.h>
#include <linux/crc32.h>
#include <linux/debugfs.h>
#include <linux/mount.h>
#include <linux/seq_file.h>
#include <linux/quotaops.h>
#define MLOG_MASK_PREFIX ML_SUPER
#include <cluster/masklog.h>
#include "ocfs2.h"
/* this should be the only file to include a version 1 header */
#include "ocfs1_fs_compat.h"
#include "alloc.h"
#include "blockcheck.h"
#include "dlmglue.h"
#include "export.h"
#include "extent_map.h"
#include "heartbeat.h"
#include "inode.h"
#include "journal.h"
#include "localalloc.h"
#include "namei.h"
#include "slot_map.h"
#include "super.h"
#include "sysfile.h"
#include "uptodate.h"
#include "ver.h"
#include "xattr.h"
#include "quota.h"
#include "refcounttree.h"
#include "suballoc.h"
#include "buffer_head_io.h"
static struct kmem_cache *ocfs2_inode_cachep = NULL;
struct kmem_cache *ocfs2_dquot_cachep;
struct kmem_cache *ocfs2_qf_chunk_cachep;
/* OCFS2 needs to schedule several differnt types of work which
* require cluster locking, disk I/O, recovery waits, etc. Since these
* types of work tend to be heavy we avoid using the kernel events
* workqueue and schedule on our own. */
struct workqueue_struct *ocfs2_wq = NULL;
static struct dentry *ocfs2_debugfs_root = NULL;
MODULE_AUTHOR("Oracle");
MODULE_LICENSE("GPL");
struct mount_options
{
unsigned long commit_interval;
unsigned long mount_opt;
unsigned int atime_quantum;
signed short slot;
int localalloc_opt;
unsigned int resv_level;
int dir_resv_level;
char cluster_stack[OCFS2_STACK_LABEL_LEN + 1];
};
static int ocfs2_parse_options(struct super_block *sb, char *options,
struct mount_options *mopt,
int is_remount);
static int ocfs2_check_set_options(struct super_block *sb,
struct mount_options *options);
static int ocfs2_show_options(struct seq_file *s, struct vfsmount *mnt);
static void ocfs2_put_super(struct super_block *sb);
static int ocfs2_mount_volume(struct super_block *sb);
static int ocfs2_remount(struct super_block *sb, int *flags, char *data);
static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err);
static int ocfs2_initialize_mem_caches(void);
static void ocfs2_free_mem_caches(void);
static void ocfs2_delete_osb(struct ocfs2_super *osb);
static int ocfs2_statfs(struct dentry *dentry, struct kstatfs *buf);
static int ocfs2_sync_fs(struct super_block *sb, int wait);
static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb);
static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb);
static void ocfs2_release_system_inodes(struct ocfs2_super *osb);
static int ocfs2_check_volume(struct ocfs2_super *osb);
static int ocfs2_verify_volume(struct ocfs2_dinode *di,
struct buffer_head *bh,
u32 sectsize,
struct ocfs2_blockcheck_stats *stats);
static int ocfs2_initialize_super(struct super_block *sb,
struct buffer_head *bh,
int sector_size,
struct ocfs2_blockcheck_stats *stats);
static int ocfs2_get_sector(struct super_block *sb,
struct buffer_head **bh,
int block,
int sect_size);
static struct inode *ocfs2_alloc_inode(struct super_block *sb);
static void ocfs2_destroy_inode(struct inode *inode);
static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend);
static int ocfs2_enable_quotas(struct ocfs2_super *osb);
static void ocfs2_disable_quotas(struct ocfs2_super *osb);
static const struct super_operations ocfs2_sops = {
.statfs = ocfs2_statfs,
.alloc_inode = ocfs2_alloc_inode,
.destroy_inode = ocfs2_destroy_inode,
.drop_inode = ocfs2_drop_inode,
.evict_inode = ocfs2_evict_inode,
.sync_fs = ocfs2_sync_fs,
.put_super = ocfs2_put_super,
.remount_fs = ocfs2_remount,
.show_options = ocfs2_show_options,
.quota_read = ocfs2_quota_read,
.quota_write = ocfs2_quota_write,
};
enum {
Opt_barrier,
Opt_err_panic,
Opt_err_ro,
Opt_intr,
Opt_nointr,
Opt_hb_none,
Opt_hb_local,
Opt_hb_global,
Opt_data_ordered,
Opt_data_writeback,
Opt_atime_quantum,
Opt_slot,
Opt_commit,
Opt_localalloc,
Opt_localflocks,
Opt_stack,
Opt_user_xattr,
Opt_nouser_xattr,
Opt_inode64,
Opt_acl,
Opt_noacl,
Opt_usrquota,
Opt_grpquota,
Opt_coherency_buffered,
Opt_coherency_full,
Opt_resv_level,
Opt_dir_resv_level,
Opt_err,
};
static const match_table_t tokens = {
{Opt_barrier, "barrier=%u"},
{Opt_err_panic, "errors=panic"},
{Opt_err_ro, "errors=remount-ro"},
{Opt_intr, "intr"},
{Opt_nointr, "nointr"},
{Opt_hb_none, OCFS2_HB_NONE},
{Opt_hb_local, OCFS2_HB_LOCAL},
{Opt_hb_global, OCFS2_HB_GLOBAL},
{Opt_data_ordered, "data=ordered"},
{Opt_data_writeback, "data=writeback"},
{Opt_atime_quantum, "atime_quantum=%u"},
{Opt_slot, "preferred_slot=%u"},
{Opt_commit, "commit=%u"},
{Opt_localalloc, "localalloc=%d"},
{Opt_localflocks, "localflocks"},
{Opt_stack, "cluster_stack=%s"},
{Opt_user_xattr, "user_xattr"},
{Opt_nouser_xattr, "nouser_xattr"},
{Opt_inode64, "inode64"},
{Opt_acl, "acl"},
{Opt_noacl, "noacl"},
{Opt_usrquota, "usrquota"},
{Opt_grpquota, "grpquota"},
{Opt_coherency_buffered, "coherency=buffered"},
{Opt_coherency_full, "coherency=full"},
{Opt_resv_level, "resv_level=%u"},
{Opt_dir_resv_level, "dir_resv_level=%u"},
{Opt_err, NULL}
};
#ifdef CONFIG_DEBUG_FS
static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
{
struct ocfs2_cluster_connection *cconn = osb->cconn;
struct ocfs2_recovery_map *rm = osb->recovery_map;
struct ocfs2_orphan_scan *os = &osb->osb_orphan_scan;
int i, out = 0;
out += snprintf(buf + out, len - out,
"%10s => Id: %-s Uuid: %-s Gen: 0x%X Label: %-s\n",
"Device", osb->dev_str, osb->uuid_str,
osb->fs_generation, osb->vol_label);
out += snprintf(buf + out, len - out,
"%10s => State: %d Flags: 0x%lX\n", "Volume",
atomic_read(&osb->vol_state), osb->osb_flags);
out += snprintf(buf + out, len - out,
"%10s => Block: %lu Cluster: %d\n", "Sizes",
osb->sb->s_blocksize, osb->s_clustersize);
out += snprintf(buf + out, len - out,
"%10s => Compat: 0x%X Incompat: 0x%X "
"ROcompat: 0x%X\n",
"Features", osb->s_feature_compat,
osb->s_feature_incompat, osb->s_feature_ro_compat);
out += snprintf(buf + out, len - out,
"%10s => Opts: 0x%lX AtimeQuanta: %u\n", "Mount",
osb->s_mount_opt, osb->s_atime_quantum);
if (cconn) {
out += snprintf(buf + out, len - out,
"%10s => Stack: %s Name: %*s "
"Version: %d.%d\n", "Cluster",
(*osb->osb_cluster_stack == '\0' ?
"o2cb" : osb->osb_cluster_stack),
cconn->cc_namelen, cconn->cc_name,
cconn->cc_version.pv_major,
cconn->cc_version.pv_minor);
}
spin_lock(&osb->dc_task_lock);
out += snprintf(buf + out, len - out,
"%10s => Pid: %d Count: %lu WakeSeq: %lu "
"WorkSeq: %lu\n", "DownCnvt",
(osb->dc_task ? task_pid_nr(osb->dc_task) : -1),
osb->blocked_lock_count, osb->dc_wake_sequence,
osb->dc_work_sequence);
spin_unlock(&osb->dc_task_lock);
spin_lock(&osb->osb_lock);
out += snprintf(buf + out, len - out, "%10s => Pid: %d Nodes:",
"Recovery",
(osb->recovery_thread_task ?
task_pid_nr(osb->recovery_thread_task) : -1));
if (rm->rm_used == 0)
out += snprintf(buf + out, len - out, " None\n");
else {
for (i = 0; i < rm->rm_used; i++)
out += snprintf(buf + out, len - out, " %d",
rm->rm_entries[i]);
out += snprintf(buf + out, len - out, "\n");
}
spin_unlock(&osb->osb_lock);
out += snprintf(buf + out, len - out,
"%10s => Pid: %d Interval: %lu Needs: %d\n", "Commit",
(osb->commit_task ? task_pid_nr(osb->commit_task) : -1),
osb->osb_commit_interval,
atomic_read(&osb->needs_checkpoint));
out += snprintf(buf + out, len - out,
"%10s => State: %d TxnId: %lu NumTxns: %d\n",
"Journal", osb->journal->j_state,
osb->journal->j_trans_id,
atomic_read(&osb->journal->j_num_trans));
out += snprintf(buf + out, len - out,
"%10s => GlobalAllocs: %d LocalAllocs: %d "
"SubAllocs: %d LAWinMoves: %d SAExtends: %d\n",
"Stats",
atomic_read(&osb->alloc_stats.bitmap_data),
atomic_read(&osb->alloc_stats.local_data),
atomic_read(&osb->alloc_stats.bg_allocs),
atomic_read(&osb->alloc_stats.moves),
atomic_read(&osb->alloc_stats.bg_extends));
out += snprintf(buf + out, len - out,
"%10s => State: %u Descriptor: %llu Size: %u bits "
"Default: %u bits\n",
"LocalAlloc", osb->local_alloc_state,
(unsigned long long)osb->la_last_gd,
osb->local_alloc_bits, osb->local_alloc_default_bits);
spin_lock(&osb->osb_lock);
out += snprintf(buf + out, len - out,
"%10s => InodeSlot: %d StolenInodes: %d, "
"MetaSlot: %d StolenMeta: %d\n", "Steal",
osb->s_inode_steal_slot,
atomic_read(&osb->s_num_inodes_stolen),
osb->s_meta_steal_slot,
atomic_read(&osb->s_num_meta_stolen));
spin_unlock(&osb->osb_lock);
out += snprintf(buf + out, len - out, "OrphanScan => ");
out += snprintf(buf + out, len - out, "Local: %u Global: %u ",
os->os_count, os->os_seqno);
out += snprintf(buf + out, len - out, " Last Scan: ");
if (atomic_read(&os->os_state) == ORPHAN_SCAN_INACTIVE)
out += snprintf(buf + out, len - out, "Disabled\n");
else
out += snprintf(buf + out, len - out, "%lu seconds ago\n",
(get_seconds() - os->os_scantime.tv_sec));
out += snprintf(buf + out, len - out, "%10s => %3s %10s\n",
"Slots", "Num", "RecoGen");
for (i = 0; i < osb->max_slots; ++i) {
out += snprintf(buf + out, len - out,
"%10s %c %3d %10d\n",
" ",
(i == osb->slot_num ? '*' : ' '),
i, osb->slot_recovery_generations[i]);
}
return out;
}
static int ocfs2_osb_debug_open(struct inode *inode, struct file *file)
{
struct ocfs2_super *osb = inode->i_private;
char *buf = NULL;
buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!buf)
goto bail;
i_size_write(inode, ocfs2_osb_dump(osb, buf, PAGE_SIZE));
file->private_data = buf;
return 0;
bail:
return -ENOMEM;
}
static int ocfs2_debug_release(struct inode *inode, struct file *file)
{
kfree(file->private_data);
return 0;
}
static ssize_t ocfs2_debug_read(struct file *file, char __user *buf,
size_t nbytes, loff_t *ppos)
{
return simple_read_from_buffer(buf, nbytes, ppos, file->private_data,
i_size_read(file->f_mapping->host));
}
#else
static int ocfs2_osb_debug_open(struct inode *inode, struct file *file)
{
return 0;
}
static int ocfs2_debug_release(struct inode *inode, struct file *file)
{
return 0;
}
static ssize_t ocfs2_debug_read(struct file *file, char __user *buf,
size_t nbytes, loff_t *ppos)
{
return 0;
}
#endif /* CONFIG_DEBUG_FS */
static const struct file_operations ocfs2_osb_debug_fops = {
.open = ocfs2_osb_debug_open,
.release = ocfs2_debug_release,
.read = ocfs2_debug_read,
.llseek = generic_file_llseek,
};
static int ocfs2_sync_fs(struct super_block *sb, int wait)
{
int status;
tid_t target;
struct ocfs2_super *osb = OCFS2_SB(sb);
if (ocfs2_is_hard_readonly(osb))
return -EROFS;
if (wait) {
status = ocfs2_flush_truncate_log(osb);
if (status < 0)
mlog_errno(status);
} else {
ocfs2_schedule_truncate_log_flush(osb, 0);
}
if (jbd2_journal_start_commit(OCFS2_SB(sb)->journal->j_journal,
&target)) {
if (wait)
jbd2_log_wait_commit(OCFS2_SB(sb)->journal->j_journal,
target);
}
return 0;
}
static int ocfs2_need_system_inode(struct ocfs2_super *osb, int ino)
{
if (!OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, OCFS2_FEATURE_RO_COMPAT_USRQUOTA)
&& (ino == USER_QUOTA_SYSTEM_INODE
|| ino == LOCAL_USER_QUOTA_SYSTEM_INODE))
return 0;
if (!OCFS2_HAS_RO_COMPAT_FEATURE(osb->sb, OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
&& (ino == GROUP_QUOTA_SYSTEM_INODE
|| ino == LOCAL_GROUP_QUOTA_SYSTEM_INODE))
return 0;
return 1;
}
static int ocfs2_init_global_system_inodes(struct ocfs2_super *osb)
{
struct inode *new = NULL;
int status = 0;
int i;
mlog_entry_void();
new = ocfs2_iget(osb, osb->root_blkno, OCFS2_FI_FLAG_SYSFILE, 0);
if (IS_ERR(new)) {
status = PTR_ERR(new);
mlog_errno(status);
goto bail;
}
osb->root_inode = new;
new = ocfs2_iget(osb, osb->system_dir_blkno, OCFS2_FI_FLAG_SYSFILE, 0);
if (IS_ERR(new)) {
status = PTR_ERR(new);
mlog_errno(status);
goto bail;
}
osb->sys_root_inode = new;
for (i = OCFS2_FIRST_ONLINE_SYSTEM_INODE;
i <= OCFS2_LAST_GLOBAL_SYSTEM_INODE; i++) {
if (!ocfs2_need_system_inode(osb, i))
continue;
new = ocfs2_get_system_file_inode(osb, i, osb->slot_num);
if (!new) {
ocfs2_release_system_inodes(osb);
status = -EINVAL;
mlog_errno(status);
/* FIXME: Should ERROR_RO_FS */
mlog(ML_ERROR, "Unable to load system inode %d, "
"possibly corrupt fs?", i);
goto bail;
}
// the array now has one ref, so drop this one
iput(new);
}
bail:
mlog_exit(status);
return status;
}
static int ocfs2_init_local_system_inodes(struct ocfs2_super *osb)
{
struct inode *new = NULL;
int status = 0;
int i;
mlog_entry_void();
for (i = OCFS2_LAST_GLOBAL_SYSTEM_INODE + 1;
i < NUM_SYSTEM_INODES;
i++) {
if (!ocfs2_need_system_inode(osb, i))
continue;
new = ocfs2_get_system_file_inode(osb, i, osb->slot_num);
if (!new) {
ocfs2_release_system_inodes(osb);
status = -EINVAL;
mlog(ML_ERROR, "status=%d, sysfile=%d, slot=%d\n",
status, i, osb->slot_num);
goto bail;
}
/* the array now has one ref, so drop this one */
iput(new);
}
bail:
mlog_exit(status);
return status;
}
static void ocfs2_release_system_inodes(struct ocfs2_super *osb)
{
int i;
struct inode *inode;
mlog_entry_void();
for (i = 0; i < NUM_GLOBAL_SYSTEM_INODES; i++) {
inode = osb->global_system_inodes[i];
if (inode) {
iput(inode);
osb->global_system_inodes[i] = NULL;
}
}
inode = osb->sys_root_inode;
if (inode) {
iput(inode);
osb->sys_root_inode = NULL;
}
inode = osb->root_inode;
if (inode) {
iput(inode);
osb->root_inode = NULL;
}
if (!osb->local_system_inodes)
goto out;
for (i = 0; i < NUM_LOCAL_SYSTEM_INODES * osb->max_slots; i++) {
if (osb->local_system_inodes[i]) {
iput(osb->local_system_inodes[i]);
osb->local_system_inodes[i] = NULL;
}
}
kfree(osb->local_system_inodes);
osb->local_system_inodes = NULL;
out:
mlog_exit(0);
}
/* We're allocating fs objects, use GFP_NOFS */
static struct inode *ocfs2_alloc_inode(struct super_block *sb)
{
struct ocfs2_inode_info *oi;
oi = kmem_cache_alloc(ocfs2_inode_cachep, GFP_NOFS);
if (!oi)
return NULL;
jbd2_journal_init_jbd_inode(&oi->ip_jinode, &oi->vfs_inode);
return &oi->vfs_inode;
}
static void ocfs2_destroy_inode(struct inode *inode)
{
kmem_cache_free(ocfs2_inode_cachep, OCFS2_I(inode));
}
static unsigned long long ocfs2_max_file_offset(unsigned int bbits,
unsigned int cbits)
{
unsigned int bytes = 1 << cbits;
unsigned int trim = bytes;
unsigned int bitshift = 32;
/*
* i_size and all block offsets in ocfs2 are always 64 bits
* wide. i_clusters is 32 bits, in cluster-sized units. So on
* 64 bit platforms, cluster size will be the limiting factor.
*/
#if BITS_PER_LONG == 32
# if defined(CONFIG_LBDAF)
BUILD_BUG_ON(sizeof(sector_t) != 8);
/*
* We might be limited by page cache size.
*/
if (bytes > PAGE_CACHE_SIZE) {
bytes = PAGE_CACHE_SIZE;
trim = 1;
/*
* Shift by 31 here so that we don't get larger than
* MAX_LFS_FILESIZE
*/
bitshift = 31;
}
# else
/*
* We are limited by the size of sector_t. Use block size, as
* that's what we expose to the VFS.
*/
bytes = 1 << bbits;
trim = 1;
bitshift = 31;
# endif
#endif
/*
* Trim by a whole cluster when we can actually approach the
* on-disk limits. Otherwise we can overflow i_clusters when
* an extent start is at the max offset.
*/
return (((unsigned long long)bytes) << bitshift) - trim;
}
static int ocfs2_remount(struct super_block *sb, int *flags, char *data)
{
int incompat_features;
int ret = 0;
struct mount_options parsed_options;
struct ocfs2_super *osb = OCFS2_SB(sb);
u32 tmp;
if (!ocfs2_parse_options(sb, data, &parsed_options, 1) ||
!ocfs2_check_set_options(sb, &parsed_options)) {
ret = -EINVAL;
goto out;
}
tmp = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL |
OCFS2_MOUNT_HB_NONE;
if ((osb->s_mount_opt & tmp) != (parsed_options.mount_opt & tmp)) {
ret = -EINVAL;
mlog(ML_ERROR, "Cannot change heartbeat mode on remount\n");
goto out;
}
if ((osb->s_mount_opt & OCFS2_MOUNT_DATA_WRITEBACK) !=
(parsed_options.mount_opt & OCFS2_MOUNT_DATA_WRITEBACK)) {
ret = -EINVAL;
mlog(ML_ERROR, "Cannot change data mode on remount\n");
goto out;
}
/* Probably don't want this on remount; it might
* mess with other nodes */
if (!(osb->s_mount_opt & OCFS2_MOUNT_INODE64) &&
(parsed_options.mount_opt & OCFS2_MOUNT_INODE64)) {
ret = -EINVAL;
mlog(ML_ERROR, "Cannot enable inode64 on remount\n");
goto out;
}
/* We're going to/from readonly mode. */
if ((*flags & MS_RDONLY) != (sb->s_flags & MS_RDONLY)) {
/* Disable quota accounting before remounting RO */
if (*flags & MS_RDONLY) {
ret = ocfs2_susp_quotas(osb, 0);
if (ret < 0)
goto out;
}
/* Lock here so the check of HARD_RO and the potential
* setting of SOFT_RO is atomic. */
spin_lock(&osb->osb_lock);
if (osb->osb_flags & OCFS2_OSB_HARD_RO) {
mlog(ML_ERROR, "Remount on readonly device is forbidden.\n");
ret = -EROFS;
goto unlock_osb;
}
if (*flags & MS_RDONLY) {
mlog(0, "Going to ro mode.\n");
sb->s_flags |= MS_RDONLY;
osb->osb_flags |= OCFS2_OSB_SOFT_RO;
} else {
mlog(0, "Making ro filesystem writeable.\n");
if (osb->osb_flags & OCFS2_OSB_ERROR_FS) {
mlog(ML_ERROR, "Cannot remount RDWR "
"filesystem due to previous errors.\n");
ret = -EROFS;
goto unlock_osb;
}
incompat_features = OCFS2_HAS_RO_COMPAT_FEATURE(sb, ~OCFS2_FEATURE_RO_COMPAT_SUPP);
if (incompat_features) {
mlog(ML_ERROR, "Cannot remount RDWR because "
"of unsupported optional features "
"(%x).\n", incompat_features);
ret = -EINVAL;
goto unlock_osb;
}
sb->s_flags &= ~MS_RDONLY;
osb->osb_flags &= ~OCFS2_OSB_SOFT_RO;
}
unlock_osb:
spin_unlock(&osb->osb_lock);
/* Enable quota accounting after remounting RW */
if (!ret && !(*flags & MS_RDONLY)) {
if (sb_any_quota_suspended(sb))
ret = ocfs2_susp_quotas(osb, 1);
else
ret = ocfs2_enable_quotas(osb);
if (ret < 0) {
/* Return back changes... */
spin_lock(&osb->osb_lock);
sb->s_flags |= MS_RDONLY;
osb->osb_flags |= OCFS2_OSB_SOFT_RO;
spin_unlock(&osb->osb_lock);
goto out;
}
}
}
if (!ret) {
/* Only save off the new mount options in case of a successful
* remount. */
osb->s_mount_opt = parsed_options.mount_opt;
osb->s_atime_quantum = parsed_options.atime_quantum;
osb->preferred_slot = parsed_options.slot;
if (parsed_options.commit_interval)
osb->osb_commit_interval = parsed_options.commit_interval;
if (!ocfs2_is_hard_readonly(osb))
ocfs2_set_journal_params(osb);
sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) ?
MS_POSIXACL : 0);
}
out:
return ret;
}
static int ocfs2_sb_probe(struct super_block *sb,
struct buffer_head **bh,
int *sector_size,
struct ocfs2_blockcheck_stats *stats)
{
int status, tmpstat;
struct ocfs1_vol_disk_hdr *hdr;
struct ocfs2_dinode *di;
int blksize;
*bh = NULL;
/* may be > 512 */
*sector_size = bdev_logical_block_size(sb->s_bdev);
if (*sector_size > OCFS2_MAX_BLOCKSIZE) {
mlog(ML_ERROR, "Hardware sector size too large: %d (max=%d)\n",
*sector_size, OCFS2_MAX_BLOCKSIZE);
status = -EINVAL;
goto bail;
}
/* Can this really happen? */
if (*sector_size < OCFS2_MIN_BLOCKSIZE)
*sector_size = OCFS2_MIN_BLOCKSIZE;
/* check block zero for old format */
status = ocfs2_get_sector(sb, bh, 0, *sector_size);
if (status < 0) {
mlog_errno(status);
goto bail;
}
hdr = (struct ocfs1_vol_disk_hdr *) (*bh)->b_data;
if (hdr->major_version == OCFS1_MAJOR_VERSION) {
mlog(ML_ERROR, "incompatible version: %u.%u\n",
hdr->major_version, hdr->minor_version);
status = -EINVAL;
}
if (memcmp(hdr->signature, OCFS1_VOLUME_SIGNATURE,
strlen(OCFS1_VOLUME_SIGNATURE)) == 0) {
mlog(ML_ERROR, "incompatible volume signature: %8s\n",
hdr->signature);
status = -EINVAL;
}
brelse(*bh);
*bh = NULL;
if (status < 0) {
mlog(ML_ERROR, "This is an ocfs v1 filesystem which must be "
"upgraded before mounting with ocfs v2\n");
goto bail;
}
/*
* Now check at magic offset for 512, 1024, 2048, 4096
* blocksizes. 4096 is the maximum blocksize because it is
* the minimum clustersize.
*/
status = -EINVAL;
for (blksize = *sector_size;
blksize <= OCFS2_MAX_BLOCKSIZE;
blksize <<= 1) {
tmpstat = ocfs2_get_sector(sb, bh,
OCFS2_SUPER_BLOCK_BLKNO,
blksize);
if (tmpstat < 0) {
status = tmpstat;
mlog_errno(status);
break;
}
di = (struct ocfs2_dinode *) (*bh)->b_data;
memset(stats, 0, sizeof(struct ocfs2_blockcheck_stats));
spin_lock_init(&stats->b_lock);
tmpstat = ocfs2_verify_volume(di, *bh, blksize, stats);
if (tmpstat < 0) {
brelse(*bh);
*bh = NULL;
}
if (tmpstat != -EAGAIN) {
status = tmpstat;
break;
}
}
bail:
return status;
}
static int ocfs2_verify_heartbeat(struct ocfs2_super *osb)
{
u32 hb_enabled = OCFS2_MOUNT_HB_LOCAL | OCFS2_MOUNT_HB_GLOBAL;
if (osb->s_mount_opt & hb_enabled) {
if (ocfs2_mount_local(osb)) {
mlog(ML_ERROR, "Cannot heartbeat on a locally "
"mounted device.\n");
return -EINVAL;
}
if (ocfs2_userspace_stack(osb)) {
mlog(ML_ERROR, "Userspace stack expected, but "
"o2cb heartbeat arguments passed to mount\n");
return -EINVAL;
}
if (((osb->s_mount_opt & OCFS2_MOUNT_HB_GLOBAL) &&
!ocfs2_cluster_o2cb_global_heartbeat(osb)) ||
((osb->s_mount_opt & OCFS2_MOUNT_HB_LOCAL) &&
ocfs2_cluster_o2cb_global_heartbeat(osb))) {
mlog(ML_ERROR, "Mismatching o2cb heartbeat modes\n");
return -EINVAL;
}
}
if (!(osb->s_mount_opt & hb_enabled)) {
if (!ocfs2_mount_local(osb) && !ocfs2_is_hard_readonly(osb) &&
!ocfs2_userspace_stack(osb)) {
mlog(ML_ERROR, "Heartbeat has to be started to mount "
"a read-write clustered device.\n");
return -EINVAL;
}
}
return 0;
}
/*
* If we're using a userspace stack, mount should have passed
* a name that matches the disk. If not, mount should not
* have passed a stack.
*/
static int ocfs2_verify_userspace_stack(struct ocfs2_super *osb,
struct mount_options *mopt)
{
if (!ocfs2_userspace_stack(osb) && mopt->cluster_stack[0]) {
mlog(ML_ERROR,
"cluster stack passed to mount, but this filesystem "
"does not support it\n");
return -EINVAL;
}
if (ocfs2_userspace_stack(osb) &&
strncmp(osb->osb_cluster_stack, mopt->cluster_stack,
OCFS2_STACK_LABEL_LEN)) {
mlog(ML_ERROR,
"cluster stack passed to mount (\"%s\") does not "
"match the filesystem (\"%s\")\n",
mopt->cluster_stack,
osb->osb_cluster_stack);
return -EINVAL;
}
return 0;
}
static int ocfs2_susp_quotas(struct ocfs2_super *osb, int unsuspend)
{
int type;
struct super_block *sb = osb->sb;
unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
int status = 0;
for (type = 0; type < MAXQUOTAS; type++) {
if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
continue;
if (unsuspend)
status = dquot_resume(sb, type);
else {
struct ocfs2_mem_dqinfo *oinfo;
/* Cancel periodic syncing before suspending */
oinfo = sb_dqinfo(sb, type)->dqi_priv;
cancel_delayed_work_sync(&oinfo->dqi_sync_work);
status = dquot_suspend(sb, type);
}
if (status < 0)
break;
}
if (status < 0)
mlog(ML_ERROR, "Failed to suspend/unsuspend quotas on "
"remount (error = %d).\n", status);
return status;
}
static int ocfs2_enable_quotas(struct ocfs2_super *osb)
{
struct inode *inode[MAXQUOTAS] = { NULL, NULL };
struct super_block *sb = osb->sb;
unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
unsigned int ino[MAXQUOTAS] = { LOCAL_USER_QUOTA_SYSTEM_INODE,
LOCAL_GROUP_QUOTA_SYSTEM_INODE };
int status;
int type;
sb_dqopt(sb)->flags |= DQUOT_QUOTA_SYS_FILE | DQUOT_NEGATIVE_USAGE;
for (type = 0; type < MAXQUOTAS; type++) {
if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
continue;
inode[type] = ocfs2_get_system_file_inode(osb, ino[type],
osb->slot_num);
if (!inode[type]) {
status = -ENOENT;
goto out_quota_off;
}
status = dquot_enable(inode[type], type, QFMT_OCFS2,
DQUOT_USAGE_ENABLED);
if (status < 0)
goto out_quota_off;
}
for (type = 0; type < MAXQUOTAS; type++)
iput(inode[type]);
return 0;
out_quota_off:
ocfs2_disable_quotas(osb);
for (type = 0; type < MAXQUOTAS; type++)
iput(inode[type]);
mlog_errno(status);
return status;
}
static void ocfs2_disable_quotas(struct ocfs2_super *osb)
{
int type;
struct inode *inode;
struct super_block *sb = osb->sb;
struct ocfs2_mem_dqinfo *oinfo;
/* We mostly ignore errors in this function because there's not much
* we can do when we see them */
for (type = 0; type < MAXQUOTAS; type++) {
if (!sb_has_quota_loaded(sb, type))
continue;
/* Cancel periodic syncing before we grab dqonoff_mutex */
oinfo = sb_dqinfo(sb, type)->dqi_priv;
cancel_delayed_work_sync(&oinfo->dqi_sync_work);
inode = igrab(sb->s_dquot.files[type]);
/* Turn off quotas. This will remove all dquot structures from
* memory and so they will be automatically synced to global
* quota files */
dquot_disable(sb, type, DQUOT_USAGE_ENABLED |
DQUOT_LIMITS_ENABLED);
if (!inode)
continue;
iput(inode);
}
}
/* Handle quota on quotactl */
static int ocfs2_quota_on(struct super_block *sb, int type, int format_id,
char *path)
{
unsigned int feature[MAXQUOTAS] = { OCFS2_FEATURE_RO_COMPAT_USRQUOTA,
OCFS2_FEATURE_RO_COMPAT_GRPQUOTA};
if (!OCFS2_HAS_RO_COMPAT_FEATURE(sb, feature[type]))
return -EINVAL;
return dquot_enable(sb_dqopt(sb)->files[type], type,
format_id, DQUOT_LIMITS_ENABLED);
}