forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathjournal.c
2192 lines (1812 loc) · 56.3 KB
/
journal.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:
*
* journal.c
*
* Defines functions of journalling api
*
* Copyright (C) 2003, 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/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/kthread.h>
#include <linux/time.h>
#include <linux/random.h>
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "alloc.h"
#include "blockcheck.h"
#include "dir.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "heartbeat.h"
#include "inode.h"
#include "journal.h"
#include "localalloc.h"
#include "slot_map.h"
#include "super.h"
#include "sysfile.h"
#include "uptodate.h"
#include "quota.h"
#include "buffer_head_io.h"
#include "ocfs2_trace.h"
DEFINE_SPINLOCK(trans_inc_lock);
#define ORPHAN_SCAN_SCHEDULE_TIMEOUT 300000
static int ocfs2_force_read_journal(struct inode *inode);
static int ocfs2_recover_node(struct ocfs2_super *osb,
int node_num, int slot_num);
static int __ocfs2_recovery_thread(void *arg);
static int ocfs2_commit_cache(struct ocfs2_super *osb);
static int __ocfs2_wait_on_mount(struct ocfs2_super *osb, int quota);
static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
int dirty, int replayed);
static int ocfs2_trylock_journal(struct ocfs2_super *osb,
int slot_num);
static int ocfs2_recover_orphans(struct ocfs2_super *osb,
int slot);
static int ocfs2_commit_thread(void *arg);
static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
int slot_num,
struct ocfs2_dinode *la_dinode,
struct ocfs2_dinode *tl_dinode,
struct ocfs2_quota_recovery *qrec);
static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
{
return __ocfs2_wait_on_mount(osb, 0);
}
static inline int ocfs2_wait_on_quotas(struct ocfs2_super *osb)
{
return __ocfs2_wait_on_mount(osb, 1);
}
/*
* This replay_map is to track online/offline slots, so we could recover
* offline slots during recovery and mount
*/
enum ocfs2_replay_state {
REPLAY_UNNEEDED = 0, /* Replay is not needed, so ignore this map */
REPLAY_NEEDED, /* Replay slots marked in rm_replay_slots */
REPLAY_DONE /* Replay was already queued */
};
struct ocfs2_replay_map {
unsigned int rm_slots;
enum ocfs2_replay_state rm_state;
unsigned char rm_replay_slots[0];
};
void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state)
{
if (!osb->replay_map)
return;
/* If we've already queued the replay, we don't have any more to do */
if (osb->replay_map->rm_state == REPLAY_DONE)
return;
osb->replay_map->rm_state = state;
}
int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
{
struct ocfs2_replay_map *replay_map;
int i, node_num;
/* If replay map is already set, we don't do it again */
if (osb->replay_map)
return 0;
replay_map = kzalloc(sizeof(struct ocfs2_replay_map) +
(osb->max_slots * sizeof(char)), GFP_KERNEL);
if (!replay_map) {
mlog_errno(-ENOMEM);
return -ENOMEM;
}
spin_lock(&osb->osb_lock);
replay_map->rm_slots = osb->max_slots;
replay_map->rm_state = REPLAY_UNNEEDED;
/* set rm_replay_slots for offline slot(s) */
for (i = 0; i < replay_map->rm_slots; i++) {
if (ocfs2_slot_to_node_num_locked(osb, i, &node_num) == -ENOENT)
replay_map->rm_replay_slots[i] = 1;
}
osb->replay_map = replay_map;
spin_unlock(&osb->osb_lock);
return 0;
}
void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
{
struct ocfs2_replay_map *replay_map = osb->replay_map;
int i;
if (!replay_map)
return;
if (replay_map->rm_state != REPLAY_NEEDED)
return;
for (i = 0; i < replay_map->rm_slots; i++)
if (replay_map->rm_replay_slots[i])
ocfs2_queue_recovery_completion(osb->journal, i, NULL,
NULL, NULL);
replay_map->rm_state = REPLAY_DONE;
}
void ocfs2_free_replay_slots(struct ocfs2_super *osb)
{
struct ocfs2_replay_map *replay_map = osb->replay_map;
if (!osb->replay_map)
return;
kfree(replay_map);
osb->replay_map = NULL;
}
int ocfs2_recovery_init(struct ocfs2_super *osb)
{
struct ocfs2_recovery_map *rm;
mutex_init(&osb->recovery_lock);
osb->disable_recovery = 0;
osb->recovery_thread_task = NULL;
init_waitqueue_head(&osb->recovery_event);
rm = kzalloc(sizeof(struct ocfs2_recovery_map) +
osb->max_slots * sizeof(unsigned int),
GFP_KERNEL);
if (!rm) {
mlog_errno(-ENOMEM);
return -ENOMEM;
}
rm->rm_entries = (unsigned int *)((char *)rm +
sizeof(struct ocfs2_recovery_map));
osb->recovery_map = rm;
return 0;
}
/* we can't grab the goofy sem lock from inside wait_event, so we use
* memory barriers to make sure that we'll see the null task before
* being woken up */
static int ocfs2_recovery_thread_running(struct ocfs2_super *osb)
{
mb();
return osb->recovery_thread_task != NULL;
}
void ocfs2_recovery_exit(struct ocfs2_super *osb)
{
struct ocfs2_recovery_map *rm;
/* disable any new recovery threads and wait for any currently
* running ones to exit. Do this before setting the vol_state. */
mutex_lock(&osb->recovery_lock);
osb->disable_recovery = 1;
mutex_unlock(&osb->recovery_lock);
wait_event(osb->recovery_event, !ocfs2_recovery_thread_running(osb));
/* At this point, we know that no more recovery threads can be
* launched, so wait for any recovery completion work to
* complete. */
flush_workqueue(ocfs2_wq);
/*
* Now that recovery is shut down, and the osb is about to be
* freed, the osb_lock is not taken here.
*/
rm = osb->recovery_map;
/* XXX: Should we bug if there are dirty entries? */
kfree(rm);
}
static int __ocfs2_recovery_map_test(struct ocfs2_super *osb,
unsigned int node_num)
{
int i;
struct ocfs2_recovery_map *rm = osb->recovery_map;
assert_spin_locked(&osb->osb_lock);
for (i = 0; i < rm->rm_used; i++) {
if (rm->rm_entries[i] == node_num)
return 1;
}
return 0;
}
/* Behaves like test-and-set. Returns the previous value */
static int ocfs2_recovery_map_set(struct ocfs2_super *osb,
unsigned int node_num)
{
struct ocfs2_recovery_map *rm = osb->recovery_map;
spin_lock(&osb->osb_lock);
if (__ocfs2_recovery_map_test(osb, node_num)) {
spin_unlock(&osb->osb_lock);
return 1;
}
/* XXX: Can this be exploited? Not from o2dlm... */
BUG_ON(rm->rm_used >= osb->max_slots);
rm->rm_entries[rm->rm_used] = node_num;
rm->rm_used++;
spin_unlock(&osb->osb_lock);
return 0;
}
static void ocfs2_recovery_map_clear(struct ocfs2_super *osb,
unsigned int node_num)
{
int i;
struct ocfs2_recovery_map *rm = osb->recovery_map;
spin_lock(&osb->osb_lock);
for (i = 0; i < rm->rm_used; i++) {
if (rm->rm_entries[i] == node_num)
break;
}
if (i < rm->rm_used) {
/* XXX: be careful with the pointer math */
memmove(&(rm->rm_entries[i]), &(rm->rm_entries[i + 1]),
(rm->rm_used - i - 1) * sizeof(unsigned int));
rm->rm_used--;
}
spin_unlock(&osb->osb_lock);
}
static int ocfs2_commit_cache(struct ocfs2_super *osb)
{
int status = 0;
unsigned int flushed;
struct ocfs2_journal *journal = NULL;
journal = osb->journal;
/* Flush all pending commits and checkpoint the journal. */
down_write(&journal->j_trans_barrier);
flushed = atomic_read(&journal->j_num_trans);
trace_ocfs2_commit_cache_begin(flushed);
if (flushed == 0) {
up_write(&journal->j_trans_barrier);
goto finally;
}
jbd2_journal_lock_updates(journal->j_journal);
status = jbd2_journal_flush(journal->j_journal);
jbd2_journal_unlock_updates(journal->j_journal);
if (status < 0) {
up_write(&journal->j_trans_barrier);
mlog_errno(status);
goto finally;
}
ocfs2_inc_trans_id(journal);
flushed = atomic_read(&journal->j_num_trans);
atomic_set(&journal->j_num_trans, 0);
up_write(&journal->j_trans_barrier);
trace_ocfs2_commit_cache_end(journal->j_trans_id, flushed);
ocfs2_wake_downconvert_thread(osb);
wake_up(&journal->j_checkpointed);
finally:
return status;
}
handle_t *ocfs2_start_trans(struct ocfs2_super *osb, int max_buffs)
{
journal_t *journal = osb->journal->j_journal;
handle_t *handle;
BUG_ON(!osb || !osb->journal->j_journal);
if (ocfs2_is_hard_readonly(osb))
return ERR_PTR(-EROFS);
BUG_ON(osb->journal->j_state == OCFS2_JOURNAL_FREE);
BUG_ON(max_buffs <= 0);
/* Nested transaction? Just return the handle... */
if (journal_current_handle())
return jbd2_journal_start(journal, max_buffs);
down_read(&osb->journal->j_trans_barrier);
handle = jbd2_journal_start(journal, max_buffs);
if (IS_ERR(handle)) {
up_read(&osb->journal->j_trans_barrier);
mlog_errno(PTR_ERR(handle));
if (is_journal_aborted(journal)) {
ocfs2_abort(osb->sb, "Detected aborted journal");
handle = ERR_PTR(-EROFS);
}
} else {
if (!ocfs2_mount_local(osb))
atomic_inc(&(osb->journal->j_num_trans));
}
return handle;
}
int ocfs2_commit_trans(struct ocfs2_super *osb,
handle_t *handle)
{
int ret, nested;
struct ocfs2_journal *journal = osb->journal;
BUG_ON(!handle);
nested = handle->h_ref > 1;
ret = jbd2_journal_stop(handle);
if (ret < 0)
mlog_errno(ret);
if (!nested)
up_read(&journal->j_trans_barrier);
return ret;
}
/*
* 'nblocks' is what you want to add to the current transaction.
*
* This might call jbd2_journal_restart() which will commit dirty buffers
* and then restart the transaction. Before calling
* ocfs2_extend_trans(), any changed blocks should have been
* dirtied. After calling it, all blocks which need to be changed must
* go through another set of journal_access/journal_dirty calls.
*
* WARNING: This will not release any semaphores or disk locks taken
* during the transaction, so make sure they were taken *before*
* start_trans or we'll have ordering deadlocks.
*
* WARNING2: Note that we do *not* drop j_trans_barrier here. This is
* good because transaction ids haven't yet been recorded on the
* cluster locks associated with this handle.
*/
int ocfs2_extend_trans(handle_t *handle, int nblocks)
{
int status, old_nblocks;
BUG_ON(!handle);
BUG_ON(nblocks < 0);
if (!nblocks)
return 0;
old_nblocks = handle->h_buffer_credits;
trace_ocfs2_extend_trans(old_nblocks, nblocks);
#ifdef CONFIG_OCFS2_DEBUG_FS
status = 1;
#else
status = jbd2_journal_extend(handle, nblocks);
if (status < 0) {
mlog_errno(status);
goto bail;
}
#endif
if (status > 0) {
trace_ocfs2_extend_trans_restart(old_nblocks + nblocks);
status = jbd2_journal_restart(handle,
old_nblocks + nblocks);
if (status < 0) {
mlog_errno(status);
goto bail;
}
}
status = 0;
bail:
return status;
}
struct ocfs2_triggers {
struct jbd2_buffer_trigger_type ot_triggers;
int ot_offset;
};
static inline struct ocfs2_triggers *to_ocfs2_trigger(struct jbd2_buffer_trigger_type *triggers)
{
return container_of(triggers, struct ocfs2_triggers, ot_triggers);
}
static void ocfs2_frozen_trigger(struct jbd2_buffer_trigger_type *triggers,
struct buffer_head *bh,
void *data, size_t size)
{
struct ocfs2_triggers *ot = to_ocfs2_trigger(triggers);
/*
* We aren't guaranteed to have the superblock here, so we
* must unconditionally compute the ecc data.
* __ocfs2_journal_access() will only set the triggers if
* metaecc is enabled.
*/
ocfs2_block_check_compute(data, size, data + ot->ot_offset);
}
/*
* Quota blocks have their own trigger because the struct ocfs2_block_check
* offset depends on the blocksize.
*/
static void ocfs2_dq_frozen_trigger(struct jbd2_buffer_trigger_type *triggers,
struct buffer_head *bh,
void *data, size_t size)
{
struct ocfs2_disk_dqtrailer *dqt =
ocfs2_block_dqtrailer(size, data);
/*
* We aren't guaranteed to have the superblock here, so we
* must unconditionally compute the ecc data.
* __ocfs2_journal_access() will only set the triggers if
* metaecc is enabled.
*/
ocfs2_block_check_compute(data, size, &dqt->dq_check);
}
/*
* Directory blocks also have their own trigger because the
* struct ocfs2_block_check offset depends on the blocksize.
*/
static void ocfs2_db_frozen_trigger(struct jbd2_buffer_trigger_type *triggers,
struct buffer_head *bh,
void *data, size_t size)
{
struct ocfs2_dir_block_trailer *trailer =
ocfs2_dir_trailer_from_size(size, data);
/*
* We aren't guaranteed to have the superblock here, so we
* must unconditionally compute the ecc data.
* __ocfs2_journal_access() will only set the triggers if
* metaecc is enabled.
*/
ocfs2_block_check_compute(data, size, &trailer->db_check);
}
static void ocfs2_abort_trigger(struct jbd2_buffer_trigger_type *triggers,
struct buffer_head *bh)
{
mlog(ML_ERROR,
"ocfs2_abort_trigger called by JBD2. bh = 0x%lx, "
"bh->b_blocknr = %llu\n",
(unsigned long)bh,
(unsigned long long)bh->b_blocknr);
/* We aren't guaranteed to have the superblock here - but if we
* don't, it'll just crash. */
ocfs2_error(bh->b_assoc_map->host->i_sb,
"JBD2 has aborted our journal, ocfs2 cannot continue\n");
}
static struct ocfs2_triggers di_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
.ot_offset = offsetof(struct ocfs2_dinode, i_check),
};
static struct ocfs2_triggers eb_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
.ot_offset = offsetof(struct ocfs2_extent_block, h_check),
};
static struct ocfs2_triggers rb_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
.ot_offset = offsetof(struct ocfs2_refcount_block, rf_check),
};
static struct ocfs2_triggers gd_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
.ot_offset = offsetof(struct ocfs2_group_desc, bg_check),
};
static struct ocfs2_triggers db_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_db_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
};
static struct ocfs2_triggers xb_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
.ot_offset = offsetof(struct ocfs2_xattr_block, xb_check),
};
static struct ocfs2_triggers dq_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_dq_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
};
static struct ocfs2_triggers dr_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
.ot_offset = offsetof(struct ocfs2_dx_root_block, dr_check),
};
static struct ocfs2_triggers dl_triggers = {
.ot_triggers = {
.t_frozen = ocfs2_frozen_trigger,
.t_abort = ocfs2_abort_trigger,
},
.ot_offset = offsetof(struct ocfs2_dx_leaf, dl_check),
};
static int __ocfs2_journal_access(handle_t *handle,
struct ocfs2_caching_info *ci,
struct buffer_head *bh,
struct ocfs2_triggers *triggers,
int type)
{
int status;
struct ocfs2_super *osb =
OCFS2_SB(ocfs2_metadata_cache_get_super(ci));
BUG_ON(!ci || !ci->ci_ops);
BUG_ON(!handle);
BUG_ON(!bh);
trace_ocfs2_journal_access(
(unsigned long long)ocfs2_metadata_cache_owner(ci),
(unsigned long long)bh->b_blocknr, type, bh->b_size);
/* we can safely remove this assertion after testing. */
if (!buffer_uptodate(bh)) {
mlog(ML_ERROR, "giving me a buffer that's not uptodate!\n");
mlog(ML_ERROR, "b_blocknr=%llu\n",
(unsigned long long)bh->b_blocknr);
BUG();
}
/* Set the current transaction information on the ci so
* that the locking code knows whether it can drop it's locks
* on this ci or not. We're protected from the commit
* thread updating the current transaction id until
* ocfs2_commit_trans() because ocfs2_start_trans() took
* j_trans_barrier for us. */
ocfs2_set_ci_lock_trans(osb->journal, ci);
ocfs2_metadata_cache_io_lock(ci);
switch (type) {
case OCFS2_JOURNAL_ACCESS_CREATE:
case OCFS2_JOURNAL_ACCESS_WRITE:
status = jbd2_journal_get_write_access(handle, bh);
break;
case OCFS2_JOURNAL_ACCESS_UNDO:
status = jbd2_journal_get_undo_access(handle, bh);
break;
default:
status = -EINVAL;
mlog(ML_ERROR, "Unknown access type!\n");
}
if (!status && ocfs2_meta_ecc(osb) && triggers)
jbd2_journal_set_triggers(bh, &triggers->ot_triggers);
ocfs2_metadata_cache_io_unlock(ci);
if (status < 0)
mlog(ML_ERROR, "Error %d getting %d access to buffer!\n",
status, type);
return status;
}
int ocfs2_journal_access_di(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &di_triggers, type);
}
int ocfs2_journal_access_eb(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &eb_triggers, type);
}
int ocfs2_journal_access_rb(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &rb_triggers,
type);
}
int ocfs2_journal_access_gd(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &gd_triggers, type);
}
int ocfs2_journal_access_db(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &db_triggers, type);
}
int ocfs2_journal_access_xb(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &xb_triggers, type);
}
int ocfs2_journal_access_dq(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &dq_triggers, type);
}
int ocfs2_journal_access_dr(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &dr_triggers, type);
}
int ocfs2_journal_access_dl(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, &dl_triggers, type);
}
int ocfs2_journal_access(handle_t *handle, struct ocfs2_caching_info *ci,
struct buffer_head *bh, int type)
{
return __ocfs2_journal_access(handle, ci, bh, NULL, type);
}
void ocfs2_journal_dirty(handle_t *handle, struct buffer_head *bh)
{
int status;
trace_ocfs2_journal_dirty((unsigned long long)bh->b_blocknr);
status = jbd2_journal_dirty_metadata(handle, bh);
BUG_ON(status);
}
#define OCFS2_DEFAULT_COMMIT_INTERVAL (HZ * JBD2_DEFAULT_MAX_COMMIT_AGE)
void ocfs2_set_journal_params(struct ocfs2_super *osb)
{
journal_t *journal = osb->journal->j_journal;
unsigned long commit_interval = OCFS2_DEFAULT_COMMIT_INTERVAL;
if (osb->osb_commit_interval)
commit_interval = osb->osb_commit_interval;
write_lock(&journal->j_state_lock);
journal->j_commit_interval = commit_interval;
if (osb->s_mount_opt & OCFS2_MOUNT_BARRIER)
journal->j_flags |= JBD2_BARRIER;
else
journal->j_flags &= ~JBD2_BARRIER;
write_unlock(&journal->j_state_lock);
}
int ocfs2_journal_init(struct ocfs2_journal *journal, int *dirty)
{
int status = -1;
struct inode *inode = NULL; /* the journal inode */
journal_t *j_journal = NULL;
struct ocfs2_dinode *di = NULL;
struct buffer_head *bh = NULL;
struct ocfs2_super *osb;
int inode_lock = 0;
BUG_ON(!journal);
osb = journal->j_osb;
/* already have the inode for our journal */
inode = ocfs2_get_system_file_inode(osb, JOURNAL_SYSTEM_INODE,
osb->slot_num);
if (inode == NULL) {
status = -EACCES;
mlog_errno(status);
goto done;
}
if (is_bad_inode(inode)) {
mlog(ML_ERROR, "access error (bad inode)\n");
iput(inode);
inode = NULL;
status = -EACCES;
goto done;
}
SET_INODE_JOURNAL(inode);
OCFS2_I(inode)->ip_open_count++;
/* Skip recovery waits here - journal inode metadata never
* changes in a live cluster so it can be considered an
* exception to the rule. */
status = ocfs2_inode_lock_full(inode, &bh, 1, OCFS2_META_LOCK_RECOVERY);
if (status < 0) {
if (status != -ERESTARTSYS)
mlog(ML_ERROR, "Could not get lock on journal!\n");
goto done;
}
inode_lock = 1;
di = (struct ocfs2_dinode *)bh->b_data;
if (inode->i_size < OCFS2_MIN_JOURNAL_SIZE) {
mlog(ML_ERROR, "Journal file size (%lld) is too small!\n",
inode->i_size);
status = -EINVAL;
goto done;
}
trace_ocfs2_journal_init(inode->i_size,
(unsigned long long)inode->i_blocks,
OCFS2_I(inode)->ip_clusters);
/* call the kernels journal init function now */
j_journal = jbd2_journal_init_inode(inode);
if (j_journal == NULL) {
mlog(ML_ERROR, "Linux journal layer error\n");
status = -EINVAL;
goto done;
}
trace_ocfs2_journal_init_maxlen(j_journal->j_maxlen);
*dirty = (le32_to_cpu(di->id1.journal1.ij_flags) &
OCFS2_JOURNAL_DIRTY_FL);
journal->j_journal = j_journal;
journal->j_inode = inode;
journal->j_bh = bh;
ocfs2_set_journal_params(osb);
journal->j_state = OCFS2_JOURNAL_LOADED;
status = 0;
done:
if (status < 0) {
if (inode_lock)
ocfs2_inode_unlock(inode, 1);
brelse(bh);
if (inode) {
OCFS2_I(inode)->ip_open_count--;
iput(inode);
}
}
return status;
}
static void ocfs2_bump_recovery_generation(struct ocfs2_dinode *di)
{
le32_add_cpu(&(di->id1.journal1.ij_recovery_generation), 1);
}
static u32 ocfs2_get_recovery_generation(struct ocfs2_dinode *di)
{
return le32_to_cpu(di->id1.journal1.ij_recovery_generation);
}
static int ocfs2_journal_toggle_dirty(struct ocfs2_super *osb,
int dirty, int replayed)
{
int status;
unsigned int flags;
struct ocfs2_journal *journal = osb->journal;
struct buffer_head *bh = journal->j_bh;
struct ocfs2_dinode *fe;
fe = (struct ocfs2_dinode *)bh->b_data;
/* The journal bh on the osb always comes from ocfs2_journal_init()
* and was validated there inside ocfs2_inode_lock_full(). It's a
* code bug if we mess it up. */
BUG_ON(!OCFS2_IS_VALID_DINODE(fe));
flags = le32_to_cpu(fe->id1.journal1.ij_flags);
if (dirty)
flags |= OCFS2_JOURNAL_DIRTY_FL;
else
flags &= ~OCFS2_JOURNAL_DIRTY_FL;
fe->id1.journal1.ij_flags = cpu_to_le32(flags);
if (replayed)
ocfs2_bump_recovery_generation(fe);
ocfs2_compute_meta_ecc(osb->sb, bh->b_data, &fe->i_check);
status = ocfs2_write_block(osb, bh, INODE_CACHE(journal->j_inode));
if (status < 0)
mlog_errno(status);
return status;
}
/*
* If the journal has been kmalloc'd it needs to be freed after this
* call.
*/
void ocfs2_journal_shutdown(struct ocfs2_super *osb)
{
struct ocfs2_journal *journal = NULL;
int status = 0;
struct inode *inode = NULL;
int num_running_trans = 0;
BUG_ON(!osb);
journal = osb->journal;
if (!journal)
goto done;
inode = journal->j_inode;
if (journal->j_state != OCFS2_JOURNAL_LOADED)
goto done;
/* need to inc inode use count - jbd2_journal_destroy will iput. */
if (!igrab(inode))
BUG();
num_running_trans = atomic_read(&(osb->journal->j_num_trans));
trace_ocfs2_journal_shutdown(num_running_trans);
/* Do a commit_cache here. It will flush our journal, *and*
* release any locks that are still held.
* set the SHUTDOWN flag and release the trans lock.
* the commit thread will take the trans lock for us below. */
journal->j_state = OCFS2_JOURNAL_IN_SHUTDOWN;
/* The OCFS2_JOURNAL_IN_SHUTDOWN will signal to commit_cache to not
* drop the trans_lock (which we want to hold until we
* completely destroy the journal. */
if (osb->commit_task) {
/* Wait for the commit thread */
trace_ocfs2_journal_shutdown_wait(osb->commit_task);
kthread_stop(osb->commit_task);
osb->commit_task = NULL;
}
BUG_ON(atomic_read(&(osb->journal->j_num_trans)) != 0);
if (ocfs2_mount_local(osb)) {
jbd2_journal_lock_updates(journal->j_journal);
status = jbd2_journal_flush(journal->j_journal);
jbd2_journal_unlock_updates(journal->j_journal);
if (status < 0)
mlog_errno(status);
}
if (status == 0) {
/*
* Do not toggle if flush was unsuccessful otherwise
* will leave dirty metadata in a "clean" journal
*/
status = ocfs2_journal_toggle_dirty(osb, 0, 0);
if (status < 0)
mlog_errno(status);
}
/* Shutdown the kernel journal system */
jbd2_journal_destroy(journal->j_journal);
journal->j_journal = NULL;
OCFS2_I(inode)->ip_open_count--;
/* unlock our journal */
ocfs2_inode_unlock(inode, 1);
brelse(journal->j_bh);
journal->j_bh = NULL;
journal->j_state = OCFS2_JOURNAL_FREE;
// up_write(&journal->j_trans_barrier);
done:
if (inode)
iput(inode);
}
static void ocfs2_clear_journal_error(struct super_block *sb,
journal_t *journal,
int slot)
{
int olderr;
olderr = jbd2_journal_errno(journal);
if (olderr) {
mlog(ML_ERROR, "File system error %d recorded in "
"journal %u.\n", olderr, slot);
mlog(ML_ERROR, "File system on device %s needs checking.\n",
sb->s_id);
jbd2_journal_ack_err(journal);
jbd2_journal_clear_err(journal);
}
}
int ocfs2_journal_load(struct ocfs2_journal *journal, int local, int replayed)
{
int status = 0;
struct ocfs2_super *osb;
BUG_ON(!journal);
osb = journal->j_osb;