forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
transaction.c
2343 lines (2091 loc) · 70.5 KB
/
transaction.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
/*
* linux/fs/jbd2/transaction.c
*
* Written by Stephen C. Tweedie <[email protected]>, 1998
*
* Copyright 1998 Red Hat corp --- All Rights Reserved
*
* This file is part of the Linux kernel and is made available under
* the terms of the GNU General Public License, version 2, or at your
* option, any later version, incorporated herein by reference.
*
* Generic filesystem transaction handling code; part of the ext2fs
* journaling system.
*
* This file manages transactions (compound commits managed by the
* journaling code) and handles (individual atomic operations by the
* filesystem).
*/
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/jbd2.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/hrtimer.h>
#include <linux/backing-dev.h>
#include <linux/bug.h>
#include <linux/module.h>
#include <trace/events/jbd2.h>
static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh);
static void __jbd2_journal_unfile_buffer(struct journal_head *jh);
static struct kmem_cache *transaction_cache;
int __init jbd2_journal_init_transaction_cache(void)
{
J_ASSERT(!transaction_cache);
transaction_cache = kmem_cache_create("jbd2_transaction_s",
sizeof(transaction_t),
0,
SLAB_HWCACHE_ALIGN|SLAB_TEMPORARY,
NULL);
if (transaction_cache)
return 0;
return -ENOMEM;
}
void jbd2_journal_destroy_transaction_cache(void)
{
if (transaction_cache) {
kmem_cache_destroy(transaction_cache);
transaction_cache = NULL;
}
}
void jbd2_journal_free_transaction(transaction_t *transaction)
{
if (unlikely(ZERO_OR_NULL_PTR(transaction)))
return;
kmem_cache_free(transaction_cache, transaction);
}
/*
* jbd2_get_transaction: obtain a new transaction_t object.
*
* Simply allocate and initialise a new transaction. Create it in
* RUNNING state and add it to the current journal (which should not
* have an existing running transaction: we only make a new transaction
* once we have started to commit the old one).
*
* Preconditions:
* The journal MUST be locked. We don't perform atomic mallocs on the
* new transaction and we can't block without protecting against other
* processes trying to touch the journal while it is in transition.
*
*/
static transaction_t *
jbd2_get_transaction(journal_t *journal, transaction_t *transaction)
{
transaction->t_journal = journal;
transaction->t_state = T_RUNNING;
transaction->t_start_time = ktime_get();
transaction->t_tid = journal->j_transaction_sequence++;
transaction->t_expires = jiffies + journal->j_commit_interval;
spin_lock_init(&transaction->t_handle_lock);
atomic_set(&transaction->t_updates, 0);
atomic_set(&transaction->t_outstanding_credits, 0);
atomic_set(&transaction->t_handle_count, 0);
INIT_LIST_HEAD(&transaction->t_inode_list);
INIT_LIST_HEAD(&transaction->t_private_list);
/* Set up the commit timer for the new transaction. */
journal->j_commit_timer.expires = round_jiffies_up(transaction->t_expires);
add_timer(&journal->j_commit_timer);
J_ASSERT(journal->j_running_transaction == NULL);
journal->j_running_transaction = transaction;
transaction->t_max_wait = 0;
transaction->t_start = jiffies;
transaction->t_requested = 0;
return transaction;
}
/*
* Handle management.
*
* A handle_t is an object which represents a single atomic update to a
* filesystem, and which tracks all of the modifications which form part
* of that one update.
*/
/*
* Update transaction's maximum wait time, if debugging is enabled.
*
* In order for t_max_wait to be reliable, it must be protected by a
* lock. But doing so will mean that start_this_handle() can not be
* run in parallel on SMP systems, which limits our scalability. So
* unless debugging is enabled, we no longer update t_max_wait, which
* means that maximum wait time reported by the jbd2_run_stats
* tracepoint will always be zero.
*/
static inline void update_t_max_wait(transaction_t *transaction,
unsigned long ts)
{
#ifdef CONFIG_JBD2_DEBUG
if (jbd2_journal_enable_debug &&
time_after(transaction->t_start, ts)) {
ts = jbd2_time_diff(ts, transaction->t_start);
spin_lock(&transaction->t_handle_lock);
if (ts > transaction->t_max_wait)
transaction->t_max_wait = ts;
spin_unlock(&transaction->t_handle_lock);
}
#endif
}
/*
* start_this_handle: Given a handle, deal with any locking or stalling
* needed to make sure that there is enough journal space for the handle
* to begin. Attach the handle to a transaction and set up the
* transaction's buffer credits.
*/
static int start_this_handle(journal_t *journal, handle_t *handle,
gfp_t gfp_mask)
{
transaction_t *transaction, *new_transaction = NULL;
tid_t tid;
int needed, need_to_start;
int nblocks = handle->h_buffer_credits;
unsigned long ts = jiffies;
if (nblocks > journal->j_max_transaction_buffers) {
printk(KERN_ERR "JBD2: %s wants too many credits (%d > %d)\n",
current->comm, nblocks,
journal->j_max_transaction_buffers);
return -ENOSPC;
}
alloc_transaction:
if (!journal->j_running_transaction) {
new_transaction = kmem_cache_zalloc(transaction_cache,
gfp_mask);
if (!new_transaction) {
/*
* If __GFP_FS is not present, then we may be
* being called from inside the fs writeback
* layer, so we MUST NOT fail. Since
* __GFP_NOFAIL is going away, we will arrange
* to retry the allocation ourselves.
*/
if ((gfp_mask & __GFP_FS) == 0) {
congestion_wait(BLK_RW_ASYNC, HZ/50);
goto alloc_transaction;
}
return -ENOMEM;
}
}
jbd_debug(3, "New handle %p going live.\n", handle);
/*
* We need to hold j_state_lock until t_updates has been incremented,
* for proper journal barrier handling
*/
repeat:
read_lock(&journal->j_state_lock);
BUG_ON(journal->j_flags & JBD2_UNMOUNT);
if (is_journal_aborted(journal) ||
(journal->j_errno != 0 && !(journal->j_flags & JBD2_ACK_ERR))) {
read_unlock(&journal->j_state_lock);
jbd2_journal_free_transaction(new_transaction);
return -EROFS;
}
/* Wait on the journal's transaction barrier if necessary */
if (journal->j_barrier_count) {
read_unlock(&journal->j_state_lock);
wait_event(journal->j_wait_transaction_locked,
journal->j_barrier_count == 0);
goto repeat;
}
if (!journal->j_running_transaction) {
read_unlock(&journal->j_state_lock);
if (!new_transaction)
goto alloc_transaction;
write_lock(&journal->j_state_lock);
if (!journal->j_running_transaction &&
!journal->j_barrier_count) {
jbd2_get_transaction(journal, new_transaction);
new_transaction = NULL;
}
write_unlock(&journal->j_state_lock);
goto repeat;
}
transaction = journal->j_running_transaction;
/*
* If the current transaction is locked down for commit, wait for the
* lock to be released.
*/
if (transaction->t_state == T_LOCKED) {
DEFINE_WAIT(wait);
prepare_to_wait(&journal->j_wait_transaction_locked,
&wait, TASK_UNINTERRUPTIBLE);
read_unlock(&journal->j_state_lock);
schedule();
finish_wait(&journal->j_wait_transaction_locked, &wait);
goto repeat;
}
/*
* If there is not enough space left in the log to write all potential
* buffers requested by this operation, we need to stall pending a log
* checkpoint to free some more log space.
*/
needed = atomic_add_return(nblocks,
&transaction->t_outstanding_credits);
if (needed > journal->j_max_transaction_buffers) {
/*
* If the current transaction is already too large, then start
* to commit it: we can then go back and attach this handle to
* a new transaction.
*/
DEFINE_WAIT(wait);
jbd_debug(2, "Handle %p starting new commit...\n", handle);
atomic_sub(nblocks, &transaction->t_outstanding_credits);
prepare_to_wait(&journal->j_wait_transaction_locked, &wait,
TASK_UNINTERRUPTIBLE);
tid = transaction->t_tid;
need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
if (need_to_start)
jbd2_log_start_commit(journal, tid);
schedule();
finish_wait(&journal->j_wait_transaction_locked, &wait);
goto repeat;
}
/*
* The commit code assumes that it can get enough log space
* without forcing a checkpoint. This is *critical* for
* correctness: a checkpoint of a buffer which is also
* associated with a committing transaction creates a deadlock,
* so commit simply cannot force through checkpoints.
*
* We must therefore ensure the necessary space in the journal
* *before* starting to dirty potentially checkpointed buffers
* in the new transaction.
*
* The worst part is, any transaction currently committing can
* reduce the free space arbitrarily. Be careful to account for
* those buffers when checkpointing.
*/
/*
* @@@ AKPM: This seems rather over-defensive. We're giving commit
* a _lot_ of headroom: 1/4 of the journal plus the size of
* the committing transaction. Really, we only need to give it
* committing_transaction->t_outstanding_credits plus "enough" for
* the log control blocks.
* Also, this test is inconsistent with the matching one in
* jbd2_journal_extend().
*/
if (__jbd2_log_space_left(journal) < jbd_space_needed(journal)) {
jbd_debug(2, "Handle %p waiting for checkpoint...\n", handle);
atomic_sub(nblocks, &transaction->t_outstanding_credits);
read_unlock(&journal->j_state_lock);
write_lock(&journal->j_state_lock);
if (__jbd2_log_space_left(journal) < jbd_space_needed(journal))
__jbd2_log_wait_for_space(journal);
write_unlock(&journal->j_state_lock);
goto repeat;
}
/* OK, account for the buffers that this operation expects to
* use and add the handle to the running transaction.
*/
update_t_max_wait(transaction, ts);
handle->h_transaction = transaction;
handle->h_requested_credits = nblocks;
handle->h_start_jiffies = jiffies;
atomic_inc(&transaction->t_updates);
atomic_inc(&transaction->t_handle_count);
jbd_debug(4, "Handle %p given %d credits (total %d, free %d)\n",
handle, nblocks,
atomic_read(&transaction->t_outstanding_credits),
__jbd2_log_space_left(journal));
read_unlock(&journal->j_state_lock);
lock_map_acquire(&handle->h_lockdep_map);
jbd2_journal_free_transaction(new_transaction);
return 0;
}
static struct lock_class_key jbd2_handle_key;
/* Allocate a new handle. This should probably be in a slab... */
static handle_t *new_handle(int nblocks)
{
handle_t *handle = jbd2_alloc_handle(GFP_NOFS);
if (!handle)
return NULL;
memset(handle, 0, sizeof(*handle));
handle->h_buffer_credits = nblocks;
handle->h_ref = 1;
lockdep_init_map(&handle->h_lockdep_map, "jbd2_handle",
&jbd2_handle_key, 0);
return handle;
}
/**
* handle_t *jbd2_journal_start() - Obtain a new handle.
* @journal: Journal to start transaction on.
* @nblocks: number of block buffer we might modify
*
* We make sure that the transaction can guarantee at least nblocks of
* modified buffers in the log. We block until the log can guarantee
* that much space.
*
* This function is visible to journal users (like ext3fs), so is not
* called with the journal already locked.
*
* Return a pointer to a newly allocated handle, or an ERR_PTR() value
* on failure.
*/
handle_t *jbd2__journal_start(journal_t *journal, int nblocks, gfp_t gfp_mask,
unsigned int type, unsigned int line_no)
{
handle_t *handle = journal_current_handle();
int err;
if (!journal)
return ERR_PTR(-EROFS);
if (handle) {
J_ASSERT(handle->h_transaction->t_journal == journal);
handle->h_ref++;
return handle;
}
handle = new_handle(nblocks);
if (!handle)
return ERR_PTR(-ENOMEM);
current->journal_info = handle;
err = start_this_handle(journal, handle, gfp_mask);
if (err < 0) {
jbd2_free_handle(handle);
current->journal_info = NULL;
return ERR_PTR(err);
}
handle->h_type = type;
handle->h_line_no = line_no;
trace_jbd2_handle_start(journal->j_fs_dev->bd_dev,
handle->h_transaction->t_tid, type,
line_no, nblocks);
return handle;
}
EXPORT_SYMBOL(jbd2__journal_start);
handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
{
return jbd2__journal_start(journal, nblocks, GFP_NOFS, 0, 0);
}
EXPORT_SYMBOL(jbd2_journal_start);
/**
* int jbd2_journal_extend() - extend buffer credits.
* @handle: handle to 'extend'
* @nblocks: nr blocks to try to extend by.
*
* Some transactions, such as large extends and truncates, can be done
* atomically all at once or in several stages. The operation requests
* a credit for a number of buffer modications in advance, but can
* extend its credit if it needs more.
*
* jbd2_journal_extend tries to give the running handle more buffer credits.
* It does not guarantee that allocation - this is a best-effort only.
* The calling process MUST be able to deal cleanly with a failure to
* extend here.
*
* Return 0 on success, non-zero on failure.
*
* return code < 0 implies an error
* return code > 0 implies normal transaction-full status.
*/
int jbd2_journal_extend(handle_t *handle, int nblocks)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
int result;
int wanted;
result = -EIO;
if (is_handle_aborted(handle))
goto out;
result = 1;
read_lock(&journal->j_state_lock);
/* Don't extend a locked-down transaction! */
if (handle->h_transaction->t_state != T_RUNNING) {
jbd_debug(3, "denied handle %p %d blocks: "
"transaction not running\n", handle, nblocks);
goto error_out;
}
spin_lock(&transaction->t_handle_lock);
wanted = atomic_read(&transaction->t_outstanding_credits) + nblocks;
if (wanted > journal->j_max_transaction_buffers) {
jbd_debug(3, "denied handle %p %d blocks: "
"transaction too large\n", handle, nblocks);
goto unlock;
}
if (wanted > __jbd2_log_space_left(journal)) {
jbd_debug(3, "denied handle %p %d blocks: "
"insufficient log space\n", handle, nblocks);
goto unlock;
}
trace_jbd2_handle_extend(journal->j_fs_dev->bd_dev,
handle->h_transaction->t_tid,
handle->h_type, handle->h_line_no,
handle->h_buffer_credits,
nblocks);
handle->h_buffer_credits += nblocks;
handle->h_requested_credits += nblocks;
atomic_add(nblocks, &transaction->t_outstanding_credits);
result = 0;
jbd_debug(3, "extended handle %p by %d\n", handle, nblocks);
unlock:
spin_unlock(&transaction->t_handle_lock);
error_out:
read_unlock(&journal->j_state_lock);
out:
return result;
}
/**
* int jbd2_journal_restart() - restart a handle .
* @handle: handle to restart
* @nblocks: nr credits requested
*
* Restart a handle for a multi-transaction filesystem
* operation.
*
* If the jbd2_journal_extend() call above fails to grant new buffer credits
* to a running handle, a call to jbd2_journal_restart will commit the
* handle's transaction so far and reattach the handle to a new
* transaction capabable of guaranteeing the requested number of
* credits.
*/
int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
tid_t tid;
int need_to_start, ret;
/* If we've had an abort of any type, don't even think about
* actually doing the restart! */
if (is_handle_aborted(handle))
return 0;
/*
* First unlink the handle from its current transaction, and start the
* commit on that.
*/
J_ASSERT(atomic_read(&transaction->t_updates) > 0);
J_ASSERT(journal_current_handle() == handle);
read_lock(&journal->j_state_lock);
spin_lock(&transaction->t_handle_lock);
atomic_sub(handle->h_buffer_credits,
&transaction->t_outstanding_credits);
if (atomic_dec_and_test(&transaction->t_updates))
wake_up(&journal->j_wait_updates);
spin_unlock(&transaction->t_handle_lock);
jbd_debug(2, "restarting handle %p\n", handle);
tid = transaction->t_tid;
need_to_start = !tid_geq(journal->j_commit_request, tid);
read_unlock(&journal->j_state_lock);
if (need_to_start)
jbd2_log_start_commit(journal, tid);
lock_map_release(&handle->h_lockdep_map);
handle->h_buffer_credits = nblocks;
ret = start_this_handle(journal, handle, gfp_mask);
return ret;
}
EXPORT_SYMBOL(jbd2__journal_restart);
int jbd2_journal_restart(handle_t *handle, int nblocks)
{
return jbd2__journal_restart(handle, nblocks, GFP_NOFS);
}
EXPORT_SYMBOL(jbd2_journal_restart);
/**
* void jbd2_journal_lock_updates () - establish a transaction barrier.
* @journal: Journal to establish a barrier on.
*
* This locks out any further updates from being started, and blocks
* until all existing updates have completed, returning only once the
* journal is in a quiescent state with no updates running.
*
* The journal lock should not be held on entry.
*/
void jbd2_journal_lock_updates(journal_t *journal)
{
DEFINE_WAIT(wait);
write_lock(&journal->j_state_lock);
++journal->j_barrier_count;
/* Wait until there are no running updates */
while (1) {
transaction_t *transaction = journal->j_running_transaction;
if (!transaction)
break;
spin_lock(&transaction->t_handle_lock);
prepare_to_wait(&journal->j_wait_updates, &wait,
TASK_UNINTERRUPTIBLE);
if (!atomic_read(&transaction->t_updates)) {
spin_unlock(&transaction->t_handle_lock);
finish_wait(&journal->j_wait_updates, &wait);
break;
}
spin_unlock(&transaction->t_handle_lock);
write_unlock(&journal->j_state_lock);
schedule();
finish_wait(&journal->j_wait_updates, &wait);
write_lock(&journal->j_state_lock);
}
write_unlock(&journal->j_state_lock);
/*
* We have now established a barrier against other normal updates, but
* we also need to barrier against other jbd2_journal_lock_updates() calls
* to make sure that we serialise special journal-locked operations
* too.
*/
mutex_lock(&journal->j_barrier);
}
/**
* void jbd2_journal_unlock_updates (journal_t* journal) - release barrier
* @journal: Journal to release the barrier on.
*
* Release a transaction barrier obtained with jbd2_journal_lock_updates().
*
* Should be called without the journal lock held.
*/
void jbd2_journal_unlock_updates (journal_t *journal)
{
J_ASSERT(journal->j_barrier_count != 0);
mutex_unlock(&journal->j_barrier);
write_lock(&journal->j_state_lock);
--journal->j_barrier_count;
write_unlock(&journal->j_state_lock);
wake_up(&journal->j_wait_transaction_locked);
}
static void warn_dirty_buffer(struct buffer_head *bh)
{
char b[BDEVNAME_SIZE];
printk(KERN_WARNING
"JBD2: Spotted dirty metadata buffer (dev = %s, blocknr = %llu). "
"There's a risk of filesystem corruption in case of system "
"crash.\n",
bdevname(bh->b_bdev, b), (unsigned long long)bh->b_blocknr);
}
/*
* If the buffer is already part of the current transaction, then there
* is nothing we need to do. If it is already part of a prior
* transaction which we are still committing to disk, then we need to
* make sure that we do not overwrite the old copy: we do copy-out to
* preserve the copy going to disk. We also account the buffer against
* the handle's metadata buffer credits (unless the buffer is already
* part of the transaction, that is).
*
*/
static int
do_get_write_access(handle_t *handle, struct journal_head *jh,
int force_copy)
{
struct buffer_head *bh;
transaction_t *transaction;
journal_t *journal;
int error;
char *frozen_buffer = NULL;
int need_copy = 0;
if (is_handle_aborted(handle))
return -EROFS;
transaction = handle->h_transaction;
journal = transaction->t_journal;
jbd_debug(5, "journal_head %p, force_copy %d\n", jh, force_copy);
JBUFFER_TRACE(jh, "entry");
repeat:
bh = jh2bh(jh);
/* @@@ Need to check for errors here at some point. */
lock_buffer(bh);
jbd_lock_bh_state(bh);
/* We now hold the buffer lock so it is safe to query the buffer
* state. Is the buffer dirty?
*
* If so, there are two possibilities. The buffer may be
* non-journaled, and undergoing a quite legitimate writeback.
* Otherwise, it is journaled, and we don't expect dirty buffers
* in that state (the buffers should be marked JBD_Dirty
* instead.) So either the IO is being done under our own
* control and this is a bug, or it's a third party IO such as
* dump(8) (which may leave the buffer scheduled for read ---
* ie. locked but not dirty) or tune2fs (which may actually have
* the buffer dirtied, ugh.) */
if (buffer_dirty(bh)) {
/*
* First question: is this buffer already part of the current
* transaction or the existing committing transaction?
*/
if (jh->b_transaction) {
J_ASSERT_JH(jh,
jh->b_transaction == transaction ||
jh->b_transaction ==
journal->j_committing_transaction);
if (jh->b_next_transaction)
J_ASSERT_JH(jh, jh->b_next_transaction ==
transaction);
warn_dirty_buffer(bh);
}
/*
* In any case we need to clean the dirty flag and we must
* do it under the buffer lock to be sure we don't race
* with running write-out.
*/
JBUFFER_TRACE(jh, "Journalling dirty buffer");
clear_buffer_dirty(bh);
set_buffer_jbddirty(bh);
}
unlock_buffer(bh);
error = -EROFS;
if (is_handle_aborted(handle)) {
jbd_unlock_bh_state(bh);
goto out;
}
error = 0;
/*
* The buffer is already part of this transaction if b_transaction or
* b_next_transaction points to it
*/
if (jh->b_transaction == transaction ||
jh->b_next_transaction == transaction)
goto done;
/*
* this is the first time this transaction is touching this buffer,
* reset the modified flag
*/
jh->b_modified = 0;
/*
* If there is already a copy-out version of this buffer, then we don't
* need to make another one
*/
if (jh->b_frozen_data) {
JBUFFER_TRACE(jh, "has frozen data");
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
jh->b_next_transaction = transaction;
goto done;
}
/* Is there data here we need to preserve? */
if (jh->b_transaction && jh->b_transaction != transaction) {
JBUFFER_TRACE(jh, "owned by older transaction");
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, jh->b_transaction ==
journal->j_committing_transaction);
/* There is one case we have to be very careful about.
* If the committing transaction is currently writing
* this buffer out to disk and has NOT made a copy-out,
* then we cannot modify the buffer contents at all
* right now. The essence of copy-out is that it is the
* extra copy, not the primary copy, which gets
* journaled. If the primary copy is already going to
* disk then we cannot do copy-out here. */
if (jh->b_jlist == BJ_Shadow) {
DEFINE_WAIT_BIT(wait, &bh->b_state, BH_Unshadow);
wait_queue_head_t *wqh;
wqh = bit_waitqueue(&bh->b_state, BH_Unshadow);
JBUFFER_TRACE(jh, "on shadow: sleep");
jbd_unlock_bh_state(bh);
/* commit wakes up all shadow buffers after IO */
for ( ; ; ) {
prepare_to_wait(wqh, &wait.wait,
TASK_UNINTERRUPTIBLE);
if (jh->b_jlist != BJ_Shadow)
break;
schedule();
}
finish_wait(wqh, &wait.wait);
goto repeat;
}
/* Only do the copy if the currently-owning transaction
* still needs it. If it is on the Forget list, the
* committing transaction is past that stage. The
* buffer had better remain locked during the kmalloc,
* but that should be true --- we hold the journal lock
* still and the buffer is already on the BUF_JOURNAL
* list so won't be flushed.
*
* Subtle point, though: if this is a get_undo_access,
* then we will be relying on the frozen_data to contain
* the new value of the committed_data record after the
* transaction, so we HAVE to force the frozen_data copy
* in that case. */
if (jh->b_jlist != BJ_Forget || force_copy) {
JBUFFER_TRACE(jh, "generate frozen data");
if (!frozen_buffer) {
JBUFFER_TRACE(jh, "allocate memory for buffer");
jbd_unlock_bh_state(bh);
frozen_buffer =
jbd2_alloc(jh2bh(jh)->b_size,
GFP_NOFS);
if (!frozen_buffer) {
printk(KERN_EMERG
"%s: OOM for frozen_buffer\n",
__func__);
JBUFFER_TRACE(jh, "oom!");
error = -ENOMEM;
jbd_lock_bh_state(bh);
goto done;
}
goto repeat;
}
jh->b_frozen_data = frozen_buffer;
frozen_buffer = NULL;
need_copy = 1;
}
jh->b_next_transaction = transaction;
}
/*
* Finally, if the buffer is not journaled right now, we need to make
* sure it doesn't get written to disk before the caller actually
* commits the new data
*/
if (!jh->b_transaction) {
JBUFFER_TRACE(jh, "no transaction");
J_ASSERT_JH(jh, !jh->b_next_transaction);
JBUFFER_TRACE(jh, "file as BJ_Reserved");
spin_lock(&journal->j_list_lock);
__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
spin_unlock(&journal->j_list_lock);
}
done:
if (need_copy) {
struct page *page;
int offset;
char *source;
J_EXPECT_JH(jh, buffer_uptodate(jh2bh(jh)),
"Possible IO failure.\n");
page = jh2bh(jh)->b_page;
offset = offset_in_page(jh2bh(jh)->b_data);
source = kmap_atomic(page);
/* Fire data frozen trigger just before we copy the data */
jbd2_buffer_frozen_trigger(jh, source + offset,
jh->b_triggers);
memcpy(jh->b_frozen_data, source+offset, jh2bh(jh)->b_size);
kunmap_atomic(source);
/*
* Now that the frozen data is saved off, we need to store
* any matching triggers.
*/
jh->b_frozen_triggers = jh->b_triggers;
}
jbd_unlock_bh_state(bh);
/*
* If we are about to journal a buffer, then any revoke pending on it is
* no longer valid
*/
jbd2_journal_cancel_revoke(handle, jh);
out:
if (unlikely(frozen_buffer)) /* It's usually NULL */
jbd2_free(frozen_buffer, bh->b_size);
JBUFFER_TRACE(jh, "exit");
return error;
}
/**
* int jbd2_journal_get_write_access() - notify intent to modify a buffer for metadata (not data) update.
* @handle: transaction to add buffer modifications to
* @bh: bh to be used for metadata writes
*
* Returns an error code or 0 on success.
*
* In full data journalling mode the buffer may be of type BJ_AsyncData,
* because we're write()ing a buffer which is also part of a shared mapping.
*/
int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
{
struct journal_head *jh = jbd2_journal_add_journal_head(bh);
int rc;
/* We do not want to get caught playing with fields which the
* log thread also manipulates. Make sure that the buffer
* completes any outstanding IO before proceeding. */
rc = do_get_write_access(handle, jh, 0);
jbd2_journal_put_journal_head(jh);
return rc;
}
/*
* When the user wants to journal a newly created buffer_head
* (ie. getblk() returned a new buffer and we are going to populate it
* manually rather than reading off disk), then we need to keep the
* buffer_head locked until it has been completely filled with new
* data. In this case, we should be able to make the assertion that
* the bh is not already part of an existing transaction.
*
* The buffer should already be locked by the caller by this point.
* There is no lock ranking violation: it was a newly created,
* unlocked buffer beforehand. */
/**
* int jbd2_journal_get_create_access () - notify intent to use newly created bh
* @handle: transaction to new buffer to
* @bh: new buffer.
*
* Call this if you create a new bh.
*/
int jbd2_journal_get_create_access(handle_t *handle, struct buffer_head *bh)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal = transaction->t_journal;
struct journal_head *jh = jbd2_journal_add_journal_head(bh);
int err;
jbd_debug(5, "journal_head %p\n", jh);
err = -EROFS;
if (is_handle_aborted(handle))
goto out;
err = 0;
JBUFFER_TRACE(jh, "entry");
/*
* The buffer may already belong to this transaction due to pre-zeroing
* in the filesystem's new_block code. It may also be on the previous,
* committing transaction's lists, but it HAS to be in Forget state in
* that case: the transaction must have deleted the buffer for it to be
* reused here.
*/
jbd_lock_bh_state(bh);
spin_lock(&journal->j_list_lock);
J_ASSERT_JH(jh, (jh->b_transaction == transaction ||
jh->b_transaction == NULL ||
(jh->b_transaction == journal->j_committing_transaction &&
jh->b_jlist == BJ_Forget)));
J_ASSERT_JH(jh, jh->b_next_transaction == NULL);
J_ASSERT_JH(jh, buffer_locked(jh2bh(jh)));
if (jh->b_transaction == NULL) {
/*
* Previous jbd2_journal_forget() could have left the buffer
* with jbddirty bit set because it was being committed. When
* the commit finished, we've filed the buffer for
* checkpointing and marked it dirty. Now we are reallocating
* the buffer so the transaction freeing it must have
* committed and so it's safe to clear the dirty bit.
*/
clear_buffer_dirty(jh2bh(jh));
/* first access by this transaction */
jh->b_modified = 0;
JBUFFER_TRACE(jh, "file as BJ_Reserved");
__jbd2_journal_file_buffer(jh, transaction, BJ_Reserved);
} else if (jh->b_transaction == journal->j_committing_transaction) {
/* first access by this transaction */
jh->b_modified = 0;
JBUFFER_TRACE(jh, "set next transaction");
jh->b_next_transaction = transaction;
}
spin_unlock(&journal->j_list_lock);
jbd_unlock_bh_state(bh);
/*
* akpm: I added this. ext3_alloc_branch can pick up new indirect
* blocks which contain freed but then revoked metadata. We need
* to cancel the revoke in case we end up freeing it yet again
* and the reallocating as data - this would cause a second revoke,
* which hits an assertion error.
*/
JBUFFER_TRACE(jh, "cancelling revoke");
jbd2_journal_cancel_revoke(handle, jh);
out:
jbd2_journal_put_journal_head(jh);
return err;
}
/**
* int jbd2_journal_get_undo_access() - Notify intent to modify metadata with
* non-rewindable consequences
* @handle: transaction
* @bh: buffer to undo
*
* Sometimes there is a need to distinguish between metadata which has
* been committed to disk and that which has not. The ext3fs code uses
* this for freeing and allocating space, we have to make sure that we
* do not reuse freed space until the deallocation has been committed,
* since if we overwrote that space we would make the delete
* un-rewindable in case of a crash.
*
* To deal with that, jbd2_journal_get_undo_access requests write access to a
* buffer for parts of non-rewindable operations such as delete
* operations on the bitmaps. The journaling code must keep a copy of
* the buffer's contents prior to the undo_access call until such time
* as we know that the buffer has definitely been committed to disk.
*
* We never need to know which transaction the committed data is part
* of, buffers touched here are guaranteed to be dirtied later and so
* will be committed to a new transaction in due course, at which point
* we can discard the old committed data pointer.