forked from microsoft/WSL2-Linux-Kernel
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathfile.c
2740 lines (2357 loc) · 66.5 KB
/
file.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
// SPDX-License-Identifier: GPL-2.0-or-later
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* file.c
*
* File open, close, extend, truncate
*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
*/
#include <linux/capability.h>
#include <linux/fs.h>
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/uio.h>
#include <linux/sched.h>
#include <linux/splice.h>
#include <linux/mount.h>
#include <linux/writeback.h>
#include <linux/falloc.h>
#include <linux/quotaops.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "alloc.h"
#include "aops.h"
#include "dir.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "file.h"
#include "sysfile.h"
#include "inode.h"
#include "ioctl.h"
#include "journal.h"
#include "locks.h"
#include "mmap.h"
#include "suballoc.h"
#include "super.h"
#include "xattr.h"
#include "acl.h"
#include "quota.h"
#include "refcounttree.h"
#include "ocfs2_trace.h"
#include "buffer_head_io.h"
static int ocfs2_init_file_private(struct inode *inode, struct file *file)
{
struct ocfs2_file_private *fp;
fp = kzalloc(sizeof(struct ocfs2_file_private), GFP_KERNEL);
if (!fp)
return -ENOMEM;
fp->fp_file = file;
mutex_init(&fp->fp_mutex);
ocfs2_file_lock_res_init(&fp->fp_flock, fp);
file->private_data = fp;
return 0;
}
static void ocfs2_free_file_private(struct inode *inode, struct file *file)
{
struct ocfs2_file_private *fp = file->private_data;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if (fp) {
ocfs2_simple_drop_lockres(osb, &fp->fp_flock);
ocfs2_lock_res_free(&fp->fp_flock);
kfree(fp);
file->private_data = NULL;
}
}
static int ocfs2_file_open(struct inode *inode, struct file *file)
{
int status;
int mode = file->f_flags;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
trace_ocfs2_file_open(inode, file, file->f_path.dentry,
(unsigned long long)oi->ip_blkno,
file->f_path.dentry->d_name.len,
file->f_path.dentry->d_name.name, mode);
if (file->f_mode & FMODE_WRITE) {
status = dquot_initialize(inode);
if (status)
goto leave;
}
spin_lock(&oi->ip_lock);
/* Check that the inode hasn't been wiped from disk by another
* node. If it hasn't then we're safe as long as we hold the
* spin lock until our increment of open count. */
if (oi->ip_flags & OCFS2_INODE_DELETED) {
spin_unlock(&oi->ip_lock);
status = -ENOENT;
goto leave;
}
if (mode & O_DIRECT)
oi->ip_flags |= OCFS2_INODE_OPEN_DIRECT;
oi->ip_open_count++;
spin_unlock(&oi->ip_lock);
status = ocfs2_init_file_private(inode, file);
if (status) {
/*
* We want to set open count back if we're failing the
* open.
*/
spin_lock(&oi->ip_lock);
oi->ip_open_count--;
spin_unlock(&oi->ip_lock);
}
file->f_mode |= FMODE_NOWAIT;
leave:
return status;
}
static int ocfs2_file_release(struct inode *inode, struct file *file)
{
struct ocfs2_inode_info *oi = OCFS2_I(inode);
spin_lock(&oi->ip_lock);
if (!--oi->ip_open_count)
oi->ip_flags &= ~OCFS2_INODE_OPEN_DIRECT;
trace_ocfs2_file_release(inode, file, file->f_path.dentry,
oi->ip_blkno,
file->f_path.dentry->d_name.len,
file->f_path.dentry->d_name.name,
oi->ip_open_count);
spin_unlock(&oi->ip_lock);
ocfs2_free_file_private(inode, file);
return 0;
}
static int ocfs2_dir_open(struct inode *inode, struct file *file)
{
return ocfs2_init_file_private(inode, file);
}
static int ocfs2_dir_release(struct inode *inode, struct file *file)
{
ocfs2_free_file_private(inode, file);
return 0;
}
static int ocfs2_sync_file(struct file *file, loff_t start, loff_t end,
int datasync)
{
int err = 0;
struct inode *inode = file->f_mapping->host;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_inode_info *oi = OCFS2_I(inode);
journal_t *journal = osb->journal->j_journal;
int ret;
tid_t commit_tid;
bool needs_barrier = false;
trace_ocfs2_sync_file(inode, file, file->f_path.dentry,
oi->ip_blkno,
file->f_path.dentry->d_name.len,
file->f_path.dentry->d_name.name,
(unsigned long long)datasync);
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
return -EROFS;
err = file_write_and_wait_range(file, start, end);
if (err)
return err;
commit_tid = datasync ? oi->i_datasync_tid : oi->i_sync_tid;
if (journal->j_flags & JBD2_BARRIER &&
!jbd2_trans_will_send_data_barrier(journal, commit_tid))
needs_barrier = true;
err = jbd2_complete_transaction(journal, commit_tid);
if (needs_barrier) {
ret = blkdev_issue_flush(inode->i_sb->s_bdev, GFP_KERNEL, NULL);
if (!err)
err = ret;
}
if (err)
mlog_errno(err);
return (err < 0) ? -EIO : 0;
}
int ocfs2_should_update_atime(struct inode *inode,
struct vfsmount *vfsmnt)
{
struct timespec64 now;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
if (ocfs2_is_hard_readonly(osb) || ocfs2_is_soft_readonly(osb))
return 0;
if ((inode->i_flags & S_NOATIME) ||
((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)))
return 0;
/*
* We can be called with no vfsmnt structure - NFSD will
* sometimes do this.
*
* Note that our action here is different than touch_atime() -
* if we can't tell whether this is a noatime mount, then we
* don't know whether to trust the value of s_atime_quantum.
*/
if (vfsmnt == NULL)
return 0;
if ((vfsmnt->mnt_flags & MNT_NOATIME) ||
((vfsmnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
return 0;
if (vfsmnt->mnt_flags & MNT_RELATIME) {
if ((timespec64_compare(&inode->i_atime, &inode->i_mtime) <= 0) ||
(timespec64_compare(&inode->i_atime, &inode->i_ctime) <= 0))
return 1;
return 0;
}
now = current_time(inode);
if ((now.tv_sec - inode->i_atime.tv_sec <= osb->s_atime_quantum))
return 0;
else
return 1;
}
int ocfs2_update_inode_atime(struct inode *inode,
struct buffer_head *bh)
{
int ret;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
handle_t *handle;
struct ocfs2_dinode *di = (struct ocfs2_dinode *) bh->b_data;
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
mlog_errno(ret);
goto out;
}
ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
goto out_commit;
}
/*
* Don't use ocfs2_mark_inode_dirty() here as we don't always
* have i_mutex to guard against concurrent changes to other
* inode fields.
*/
inode->i_atime = current_time(inode);
di->i_atime = cpu_to_le64(inode->i_atime.tv_sec);
di->i_atime_nsec = cpu_to_le32(inode->i_atime.tv_nsec);
ocfs2_update_inode_fsync_trans(handle, inode, 0);
ocfs2_journal_dirty(handle, bh);
out_commit:
ocfs2_commit_trans(osb, handle);
out:
return ret;
}
int ocfs2_set_inode_size(handle_t *handle,
struct inode *inode,
struct buffer_head *fe_bh,
u64 new_i_size)
{
int status;
i_size_write(inode, new_i_size);
inode->i_blocks = ocfs2_inode_sector_count(inode);
inode->i_ctime = inode->i_mtime = current_time(inode);
status = ocfs2_mark_inode_dirty(handle, inode, fe_bh);
if (status < 0) {
mlog_errno(status);
goto bail;
}
bail:
return status;
}
int ocfs2_simple_size_update(struct inode *inode,
struct buffer_head *di_bh,
u64 new_i_size)
{
int ret;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
handle_t *handle = NULL;
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
mlog_errno(ret);
goto out;
}
ret = ocfs2_set_inode_size(handle, inode, di_bh,
new_i_size);
if (ret < 0)
mlog_errno(ret);
ocfs2_update_inode_fsync_trans(handle, inode, 0);
ocfs2_commit_trans(osb, handle);
out:
return ret;
}
static int ocfs2_cow_file_pos(struct inode *inode,
struct buffer_head *fe_bh,
u64 offset)
{
int status;
u32 phys, cpos = offset >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
unsigned int num_clusters = 0;
unsigned int ext_flags = 0;
/*
* If the new offset is aligned to the range of the cluster, there is
* no space for ocfs2_zero_range_for_truncate to fill, so no need to
* CoW either.
*/
if ((offset & (OCFS2_SB(inode->i_sb)->s_clustersize - 1)) == 0)
return 0;
status = ocfs2_get_clusters(inode, cpos, &phys,
&num_clusters, &ext_flags);
if (status) {
mlog_errno(status);
goto out;
}
if (!(ext_flags & OCFS2_EXT_REFCOUNTED))
goto out;
return ocfs2_refcount_cow(inode, fe_bh, cpos, 1, cpos+1);
out:
return status;
}
static int ocfs2_orphan_for_truncate(struct ocfs2_super *osb,
struct inode *inode,
struct buffer_head *fe_bh,
u64 new_i_size)
{
int status;
handle_t *handle;
struct ocfs2_dinode *di;
u64 cluster_bytes;
/*
* We need to CoW the cluster contains the offset if it is reflinked
* since we will call ocfs2_zero_range_for_truncate later which will
* write "0" from offset to the end of the cluster.
*/
status = ocfs2_cow_file_pos(inode, fe_bh, new_i_size);
if (status) {
mlog_errno(status);
return status;
}
/* TODO: This needs to actually orphan the inode in this
* transaction. */
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
mlog_errno(status);
goto out;
}
status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), fe_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto out_commit;
}
/*
* Do this before setting i_size.
*/
cluster_bytes = ocfs2_align_bytes_to_clusters(inode->i_sb, new_i_size);
status = ocfs2_zero_range_for_truncate(inode, handle, new_i_size,
cluster_bytes);
if (status) {
mlog_errno(status);
goto out_commit;
}
i_size_write(inode, new_i_size);
inode->i_ctime = inode->i_mtime = current_time(inode);
di = (struct ocfs2_dinode *) fe_bh->b_data;
di->i_size = cpu_to_le64(new_i_size);
di->i_ctime = di->i_mtime = cpu_to_le64(inode->i_ctime.tv_sec);
di->i_ctime_nsec = di->i_mtime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
ocfs2_update_inode_fsync_trans(handle, inode, 0);
ocfs2_journal_dirty(handle, fe_bh);
out_commit:
ocfs2_commit_trans(osb, handle);
out:
return status;
}
int ocfs2_truncate_file(struct inode *inode,
struct buffer_head *di_bh,
u64 new_i_size)
{
int status = 0;
struct ocfs2_dinode *fe = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
/* We trust di_bh because it comes from ocfs2_inode_lock(), which
* already validated it */
fe = (struct ocfs2_dinode *) di_bh->b_data;
trace_ocfs2_truncate_file((unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)le64_to_cpu(fe->i_size),
(unsigned long long)new_i_size);
mlog_bug_on_msg(le64_to_cpu(fe->i_size) != i_size_read(inode),
"Inode %llu, inode i_size = %lld != di "
"i_size = %llu, i_flags = 0x%x\n",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
i_size_read(inode),
(unsigned long long)le64_to_cpu(fe->i_size),
le32_to_cpu(fe->i_flags));
if (new_i_size > le64_to_cpu(fe->i_size)) {
trace_ocfs2_truncate_file_error(
(unsigned long long)le64_to_cpu(fe->i_size),
(unsigned long long)new_i_size);
status = -EINVAL;
mlog_errno(status);
goto bail;
}
down_write(&OCFS2_I(inode)->ip_alloc_sem);
ocfs2_resv_discard(&osb->osb_la_resmap,
&OCFS2_I(inode)->ip_la_data_resv);
/*
* The inode lock forced other nodes to sync and drop their
* pages, which (correctly) happens even if we have a truncate
* without allocation change - ocfs2 cluster sizes can be much
* greater than page size, so we have to truncate them
* anyway.
*/
unmap_mapping_range(inode->i_mapping, new_i_size + PAGE_SIZE - 1, 0, 1);
truncate_inode_pages(inode->i_mapping, new_i_size);
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
status = ocfs2_truncate_inline(inode, di_bh, new_i_size,
i_size_read(inode), 1);
if (status)
mlog_errno(status);
goto bail_unlock_sem;
}
/* alright, we're going to need to do a full blown alloc size
* change. Orphan the inode so that recovery can complete the
* truncate if necessary. This does the task of marking
* i_size. */
status = ocfs2_orphan_for_truncate(osb, inode, di_bh, new_i_size);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_sem;
}
status = ocfs2_commit_truncate(osb, inode, di_bh);
if (status < 0) {
mlog_errno(status);
goto bail_unlock_sem;
}
/* TODO: orphan dir cleanup here. */
bail_unlock_sem:
up_write(&OCFS2_I(inode)->ip_alloc_sem);
bail:
if (!status && OCFS2_I(inode)->ip_clusters == 0)
status = ocfs2_try_remove_refcount_tree(inode, di_bh);
return status;
}
/*
* extend file allocation only here.
* we'll update all the disk stuff, and oip->alloc_size
*
* expect stuff to be locked, a transaction started and enough data /
* metadata reservations in the contexts.
*
* Will return -EAGAIN, and a reason if a restart is needed.
* If passed in, *reason will always be set, even in error.
*/
int ocfs2_add_inode_data(struct ocfs2_super *osb,
struct inode *inode,
u32 *logical_offset,
u32 clusters_to_add,
int mark_unwritten,
struct buffer_head *fe_bh,
handle_t *handle,
struct ocfs2_alloc_context *data_ac,
struct ocfs2_alloc_context *meta_ac,
enum ocfs2_alloc_restarted *reason_ret)
{
int ret;
struct ocfs2_extent_tree et;
ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), fe_bh);
ret = ocfs2_add_clusters_in_btree(handle, &et, logical_offset,
clusters_to_add, mark_unwritten,
data_ac, meta_ac, reason_ret);
return ret;
}
static int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
u32 clusters_to_add, int mark_unwritten)
{
int status = 0;
int restart_func = 0;
int credits;
u32 prev_clusters;
struct buffer_head *bh = NULL;
struct ocfs2_dinode *fe = NULL;
handle_t *handle = NULL;
struct ocfs2_alloc_context *data_ac = NULL;
struct ocfs2_alloc_context *meta_ac = NULL;
enum ocfs2_alloc_restarted why = RESTART_NONE;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
struct ocfs2_extent_tree et;
int did_quota = 0;
/*
* Unwritten extent only exists for file systems which
* support holes.
*/
BUG_ON(mark_unwritten && !ocfs2_sparse_alloc(osb));
status = ocfs2_read_inode_block(inode, &bh);
if (status < 0) {
mlog_errno(status);
goto leave;
}
fe = (struct ocfs2_dinode *) bh->b_data;
restart_all:
BUG_ON(le32_to_cpu(fe->i_clusters) != OCFS2_I(inode)->ip_clusters);
ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode), bh);
status = ocfs2_lock_allocators(inode, &et, clusters_to_add, 0,
&data_ac, &meta_ac);
if (status) {
mlog_errno(status);
goto leave;
}
credits = ocfs2_calc_extend_credits(osb->sb, &fe->id2.i_list);
handle = ocfs2_start_trans(osb, credits);
if (IS_ERR(handle)) {
status = PTR_ERR(handle);
handle = NULL;
mlog_errno(status);
goto leave;
}
restarted_transaction:
trace_ocfs2_extend_allocation(
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)i_size_read(inode),
le32_to_cpu(fe->i_clusters), clusters_to_add,
why, restart_func);
status = dquot_alloc_space_nodirty(inode,
ocfs2_clusters_to_bytes(osb->sb, clusters_to_add));
if (status)
goto leave;
did_quota = 1;
/* reserve a write to the file entry early on - that we if we
* run out of credits in the allocation path, we can still
* update i_size. */
status = ocfs2_journal_access_di(handle, INODE_CACHE(inode), bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (status < 0) {
mlog_errno(status);
goto leave;
}
prev_clusters = OCFS2_I(inode)->ip_clusters;
status = ocfs2_add_inode_data(osb,
inode,
&logical_start,
clusters_to_add,
mark_unwritten,
bh,
handle,
data_ac,
meta_ac,
&why);
if ((status < 0) && (status != -EAGAIN)) {
if (status != -ENOSPC)
mlog_errno(status);
goto leave;
}
ocfs2_update_inode_fsync_trans(handle, inode, 1);
ocfs2_journal_dirty(handle, bh);
spin_lock(&OCFS2_I(inode)->ip_lock);
clusters_to_add -= (OCFS2_I(inode)->ip_clusters - prev_clusters);
spin_unlock(&OCFS2_I(inode)->ip_lock);
/* Release unused quota reservation */
dquot_free_space(inode,
ocfs2_clusters_to_bytes(osb->sb, clusters_to_add));
did_quota = 0;
if (why != RESTART_NONE && clusters_to_add) {
if (why == RESTART_META) {
restart_func = 1;
status = 0;
} else {
BUG_ON(why != RESTART_TRANS);
status = ocfs2_allocate_extend_trans(handle, 1);
if (status < 0) {
/* handle still has to be committed at
* this point. */
status = -ENOMEM;
mlog_errno(status);
goto leave;
}
goto restarted_transaction;
}
}
trace_ocfs2_extend_allocation_end(OCFS2_I(inode)->ip_blkno,
le32_to_cpu(fe->i_clusters),
(unsigned long long)le64_to_cpu(fe->i_size),
OCFS2_I(inode)->ip_clusters,
(unsigned long long)i_size_read(inode));
leave:
if (status < 0 && did_quota)
dquot_free_space(inode,
ocfs2_clusters_to_bytes(osb->sb, clusters_to_add));
if (handle) {
ocfs2_commit_trans(osb, handle);
handle = NULL;
}
if (data_ac) {
ocfs2_free_alloc_context(data_ac);
data_ac = NULL;
}
if (meta_ac) {
ocfs2_free_alloc_context(meta_ac);
meta_ac = NULL;
}
if ((!status) && restart_func) {
restart_func = 0;
goto restart_all;
}
brelse(bh);
bh = NULL;
return status;
}
/*
* While a write will already be ordering the data, a truncate will not.
* Thus, we need to explicitly order the zeroed pages.
*/
static handle_t *ocfs2_zero_start_ordered_transaction(struct inode *inode,
struct buffer_head *di_bh,
loff_t start_byte,
loff_t length)
{
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
handle_t *handle = NULL;
int ret = 0;
if (!ocfs2_should_order_data(inode))
goto out;
handle = ocfs2_start_trans(osb, OCFS2_INODE_UPDATE_CREDITS);
if (IS_ERR(handle)) {
ret = -ENOMEM;
mlog_errno(ret);
goto out;
}
ret = ocfs2_jbd2_inode_add_write(handle, inode, start_byte, length);
if (ret < 0) {
mlog_errno(ret);
goto out;
}
ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret)
mlog_errno(ret);
ocfs2_update_inode_fsync_trans(handle, inode, 1);
out:
if (ret) {
if (!IS_ERR(handle))
ocfs2_commit_trans(osb, handle);
handle = ERR_PTR(ret);
}
return handle;
}
/* Some parts of this taken from generic_cont_expand, which turned out
* to be too fragile to do exactly what we need without us having to
* worry about recursive locking in ->write_begin() and ->write_end(). */
static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
u64 abs_to, struct buffer_head *di_bh)
{
struct address_space *mapping = inode->i_mapping;
struct page *page;
unsigned long index = abs_from >> PAGE_SHIFT;
handle_t *handle;
int ret = 0;
unsigned zero_from, zero_to, block_start, block_end;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
BUG_ON(abs_from >= abs_to);
BUG_ON(abs_to > (((u64)index + 1) << PAGE_SHIFT));
BUG_ON(abs_from & (inode->i_blkbits - 1));
handle = ocfs2_zero_start_ordered_transaction(inode, di_bh,
abs_from,
abs_to - abs_from);
if (IS_ERR(handle)) {
ret = PTR_ERR(handle);
goto out;
}
page = find_or_create_page(mapping, index, GFP_NOFS);
if (!page) {
ret = -ENOMEM;
mlog_errno(ret);
goto out_commit_trans;
}
/* Get the offsets within the page that we want to zero */
zero_from = abs_from & (PAGE_SIZE - 1);
zero_to = abs_to & (PAGE_SIZE - 1);
if (!zero_to)
zero_to = PAGE_SIZE;
trace_ocfs2_write_zero_page(
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)abs_from,
(unsigned long long)abs_to,
index, zero_from, zero_to);
/* We know that zero_from is block aligned */
for (block_start = zero_from; block_start < zero_to;
block_start = block_end) {
block_end = block_start + i_blocksize(inode);
/*
* block_start is block-aligned. Bump it by one to force
* __block_write_begin and block_commit_write to zero the
* whole block.
*/
ret = __block_write_begin(page, block_start + 1, 0,
ocfs2_get_block);
if (ret < 0) {
mlog_errno(ret);
goto out_unlock;
}
/* must not update i_size! */
ret = block_commit_write(page, block_start + 1,
block_start + 1);
if (ret < 0)
mlog_errno(ret);
else
ret = 0;
}
/*
* fs-writeback will release the dirty pages without page lock
* whose offset are over inode size, the release happens at
* block_write_full_page().
*/
i_size_write(inode, abs_to);
inode->i_blocks = ocfs2_inode_sector_count(inode);
di->i_size = cpu_to_le64((u64)i_size_read(inode));
inode->i_mtime = inode->i_ctime = current_time(inode);
di->i_mtime = di->i_ctime = cpu_to_le64(inode->i_mtime.tv_sec);
di->i_ctime_nsec = cpu_to_le32(inode->i_mtime.tv_nsec);
di->i_mtime_nsec = di->i_ctime_nsec;
if (handle) {
ocfs2_journal_dirty(handle, di_bh);
ocfs2_update_inode_fsync_trans(handle, inode, 1);
}
out_unlock:
unlock_page(page);
put_page(page);
out_commit_trans:
if (handle)
ocfs2_commit_trans(OCFS2_SB(inode->i_sb), handle);
out:
return ret;
}
/*
* Find the next range to zero. We do this in terms of bytes because
* that's what ocfs2_zero_extend() wants, and it is dealing with the
* pagecache. We may return multiple extents.
*
* zero_start and zero_end are ocfs2_zero_extend()s current idea of what
* needs to be zeroed. range_start and range_end return the next zeroing
* range. A subsequent call should pass the previous range_end as its
* zero_start. If range_end is 0, there's nothing to do.
*
* Unwritten extents are skipped over. Refcounted extents are CoWd.
*/
static int ocfs2_zero_extend_get_range(struct inode *inode,
struct buffer_head *di_bh,
u64 zero_start, u64 zero_end,
u64 *range_start, u64 *range_end)
{
int rc = 0, needs_cow = 0;
u32 p_cpos, zero_clusters = 0;
u32 zero_cpos =
zero_start >> OCFS2_SB(inode->i_sb)->s_clustersize_bits;
u32 last_cpos = ocfs2_clusters_for_bytes(inode->i_sb, zero_end);
unsigned int num_clusters = 0;
unsigned int ext_flags = 0;
while (zero_cpos < last_cpos) {
rc = ocfs2_get_clusters(inode, zero_cpos, &p_cpos,
&num_clusters, &ext_flags);
if (rc) {
mlog_errno(rc);
goto out;
}
if (p_cpos && !(ext_flags & OCFS2_EXT_UNWRITTEN)) {
zero_clusters = num_clusters;
if (ext_flags & OCFS2_EXT_REFCOUNTED)
needs_cow = 1;
break;
}
zero_cpos += num_clusters;
}
if (!zero_clusters) {
*range_end = 0;
goto out;
}
while ((zero_cpos + zero_clusters) < last_cpos) {
rc = ocfs2_get_clusters(inode, zero_cpos + zero_clusters,
&p_cpos, &num_clusters,
&ext_flags);
if (rc) {
mlog_errno(rc);
goto out;
}
if (!p_cpos || (ext_flags & OCFS2_EXT_UNWRITTEN))
break;
if (ext_flags & OCFS2_EXT_REFCOUNTED)
needs_cow = 1;
zero_clusters += num_clusters;
}
if ((zero_cpos + zero_clusters) > last_cpos)
zero_clusters = last_cpos - zero_cpos;
if (needs_cow) {
rc = ocfs2_refcount_cow(inode, di_bh, zero_cpos,
zero_clusters, UINT_MAX);
if (rc) {
mlog_errno(rc);
goto out;
}
}
*range_start = ocfs2_clusters_to_bytes(inode->i_sb, zero_cpos);
*range_end = ocfs2_clusters_to_bytes(inode->i_sb,
zero_cpos + zero_clusters);
out:
return rc;
}
/*
* Zero one range returned from ocfs2_zero_extend_get_range(). The caller
* has made sure that the entire range needs zeroing.
*/
static int ocfs2_zero_extend_range(struct inode *inode, u64 range_start,
u64 range_end, struct buffer_head *di_bh)
{
int rc = 0;
u64 next_pos;
u64 zero_pos = range_start;
trace_ocfs2_zero_extend_range(
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)range_start,
(unsigned long long)range_end);
BUG_ON(range_start >= range_end);
while (zero_pos < range_end) {
next_pos = (zero_pos & PAGE_MASK) + PAGE_SIZE;
if (next_pos > range_end)
next_pos = range_end;
rc = ocfs2_write_zero_page(inode, zero_pos, next_pos, di_bh);
if (rc < 0) {
mlog_errno(rc);
break;
}
zero_pos = next_pos;
/*
* Very large extends have the potential to lock up
* the cpu for extended periods of time.
*/
cond_resched();
}
return rc;
}
int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
loff_t zero_to_size)
{
int ret = 0;
u64 zero_start, range_start = 0, range_end = 0;
struct super_block *sb = inode->i_sb;
zero_start = ocfs2_align_bytes_to_blocks(sb, i_size_read(inode));
trace_ocfs2_zero_extend((unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)zero_start,
(unsigned long long)i_size_read(inode));
while (zero_start < zero_to_size) {
ret = ocfs2_zero_extend_get_range(inode, di_bh, zero_start,
zero_to_size,
&range_start,
&range_end);
if (ret) {
mlog_errno(ret);
break;
}
if (!range_end)
break;
/* Trim the ends */
if (range_start < zero_start)
range_start = zero_start;
if (range_end > zero_to_size)
range_end = zero_to_size;
ret = ocfs2_zero_extend_range(inode, range_start,
range_end, di_bh);
if (ret) {
mlog_errno(ret);
break;
}