forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 1
/
inode.c
3195 lines (2869 loc) · 91.6 KB
/
inode.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/*
* Copyright 2000 by Hans Reiser, licensing governed by reiserfs/README
*/
#include <linux/time.h>
#include <linux/fs.h>
#include <linux/reiserfs_fs.h>
#include <linux/reiserfs_acl.h>
#include <linux/reiserfs_xattr.h>
#include <linux/exportfs.h>
#include <linux/smp_lock.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <asm/uaccess.h>
#include <asm/unaligned.h>
#include <linux/buffer_head.h>
#include <linux/mpage.h>
#include <linux/writeback.h>
#include <linux/quotaops.h>
#include <linux/swap.h>
int reiserfs_commit_write(struct file *f, struct page *page,
unsigned from, unsigned to);
int reiserfs_prepare_write(struct file *f, struct page *page,
unsigned from, unsigned to);
void reiserfs_delete_inode(struct inode *inode)
{
/* We need blocks for transaction + (user+group) quota update (possibly delete) */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 2 +
2 * REISERFS_QUOTA_INIT_BLOCKS(inode->i_sb);
struct reiserfs_transaction_handle th;
int depth;
int err;
if (!is_bad_inode(inode))
dquot_initialize(inode);
truncate_inode_pages(&inode->i_data, 0);
depth = reiserfs_write_lock_once(inode->i_sb);
/* The = 0 happens when we abort creating a new inode for some reason like lack of space.. */
if (!(inode->i_state & I_NEW) && INODE_PKEY(inode)->k_objectid != 0) { /* also handles bad_inode case */
reiserfs_delete_xattrs(inode);
if (journal_begin(&th, inode->i_sb, jbegin_count))
goto out;
reiserfs_update_inode_transaction(inode);
reiserfs_discard_prealloc(&th, inode);
err = reiserfs_delete_object(&th, inode);
/* Do quota update inside a transaction for journaled quotas. We must do that
* after delete_object so that quota updates go into the same transaction as
* stat data deletion */
if (!err)
dquot_free_inode(inode);
if (journal_end(&th, inode->i_sb, jbegin_count))
goto out;
/* check return value from reiserfs_delete_object after
* ending the transaction
*/
if (err)
goto out;
/* all items of file are deleted, so we can remove "save" link */
remove_save_link(inode, 0 /* not truncate */ ); /* we can't do anything
* about an error here */
} else {
/* no object items are in the tree */
;
}
out:
clear_inode(inode); /* note this must go after the journal_end to prevent deadlock */
inode->i_blocks = 0;
reiserfs_write_unlock_once(inode->i_sb, depth);
}
static void _make_cpu_key(struct cpu_key *key, int version, __u32 dirid,
__u32 objectid, loff_t offset, int type, int length)
{
key->version = version;
key->on_disk_key.k_dir_id = dirid;
key->on_disk_key.k_objectid = objectid;
set_cpu_key_k_offset(key, offset);
set_cpu_key_k_type(key, type);
key->key_length = length;
}
/* take base of inode_key (it comes from inode always) (dirid, objectid) and version from an inode, set
offset and type of key */
void make_cpu_key(struct cpu_key *key, struct inode *inode, loff_t offset,
int type, int length)
{
_make_cpu_key(key, get_inode_item_key_version(inode),
le32_to_cpu(INODE_PKEY(inode)->k_dir_id),
le32_to_cpu(INODE_PKEY(inode)->k_objectid), offset, type,
length);
}
//
// when key is 0, do not set version and short key
//
inline void make_le_item_head(struct item_head *ih, const struct cpu_key *key,
int version,
loff_t offset, int type, int length,
int entry_count /*or ih_free_space */ )
{
if (key) {
ih->ih_key.k_dir_id = cpu_to_le32(key->on_disk_key.k_dir_id);
ih->ih_key.k_objectid =
cpu_to_le32(key->on_disk_key.k_objectid);
}
put_ih_version(ih, version);
set_le_ih_k_offset(ih, offset);
set_le_ih_k_type(ih, type);
put_ih_item_len(ih, length);
/* set_ih_free_space (ih, 0); */
// for directory items it is entry count, for directs and stat
// datas - 0xffff, for indirects - 0
put_ih_entry_count(ih, entry_count);
}
//
// FIXME: we might cache recently accessed indirect item
// Ugh. Not too eager for that....
// I cut the code until such time as I see a convincing argument (benchmark).
// I don't want a bloated inode struct..., and I don't like code complexity....
/* cutting the code is fine, since it really isn't in use yet and is easy
** to add back in. But, Vladimir has a really good idea here. Think
** about what happens for reading a file. For each page,
** The VFS layer calls reiserfs_readpage, who searches the tree to find
** an indirect item. This indirect item has X number of pointers, where
** X is a big number if we've done the block allocation right. But,
** we only use one or two of these pointers during each call to readpage,
** needlessly researching again later on.
**
** The size of the cache could be dynamic based on the size of the file.
**
** I'd also like to see us cache the location the stat data item, since
** we are needlessly researching for that frequently.
**
** --chris
*/
/* If this page has a file tail in it, and
** it was read in by get_block_create_0, the page data is valid,
** but tail is still sitting in a direct item, and we can't write to
** it. So, look through this page, and check all the mapped buffers
** to make sure they have valid block numbers. Any that don't need
** to be unmapped, so that block_prepare_write will correctly call
** reiserfs_get_block to convert the tail into an unformatted node
*/
static inline void fix_tail_page_for_writing(struct page *page)
{
struct buffer_head *head, *next, *bh;
if (page && page_has_buffers(page)) {
head = page_buffers(page);
bh = head;
do {
next = bh->b_this_page;
if (buffer_mapped(bh) && bh->b_blocknr == 0) {
reiserfs_unmap_buffer(bh);
}
bh = next;
} while (bh != head);
}
}
/* reiserfs_get_block does not need to allocate a block only if it has been
done already or non-hole position has been found in the indirect item */
static inline int allocation_needed(int retval, b_blocknr_t allocated,
struct item_head *ih,
__le32 * item, int pos_in_item)
{
if (allocated)
return 0;
if (retval == POSITION_FOUND && is_indirect_le_ih(ih) &&
get_block_num(item, pos_in_item))
return 0;
return 1;
}
static inline int indirect_item_found(int retval, struct item_head *ih)
{
return (retval == POSITION_FOUND) && is_indirect_le_ih(ih);
}
static inline void set_block_dev_mapped(struct buffer_head *bh,
b_blocknr_t block, struct inode *inode)
{
map_bh(bh, inode->i_sb, block);
}
//
// files which were created in the earlier version can not be longer,
// than 2 gb
//
static int file_capable(struct inode *inode, sector_t block)
{
if (get_inode_item_key_version(inode) != KEY_FORMAT_3_5 || // it is new file.
block < (1 << (31 - inode->i_sb->s_blocksize_bits))) // old file, but 'block' is inside of 2gb
return 1;
return 0;
}
static int restart_transaction(struct reiserfs_transaction_handle *th,
struct inode *inode, struct treepath *path)
{
struct super_block *s = th->t_super;
int len = th->t_blocks_allocated;
int err;
BUG_ON(!th->t_trans_id);
BUG_ON(!th->t_refcount);
pathrelse(path);
/* we cannot restart while nested */
if (th->t_refcount > 1) {
return 0;
}
reiserfs_update_sd(th, inode);
err = journal_end(th, s, len);
if (!err) {
err = journal_begin(th, s, JOURNAL_PER_BALANCE_CNT * 6);
if (!err)
reiserfs_update_inode_transaction(inode);
}
return err;
}
// it is called by get_block when create == 0. Returns block number
// for 'block'-th logical block of file. When it hits direct item it
// returns 0 (being called from bmap) or read direct item into piece
// of page (bh_result)
// Please improve the english/clarity in the comment above, as it is
// hard to understand.
static int _get_block_create_0(struct inode *inode, sector_t block,
struct buffer_head *bh_result, int args)
{
INITIALIZE_PATH(path);
struct cpu_key key;
struct buffer_head *bh;
struct item_head *ih, tmp_ih;
b_blocknr_t blocknr;
char *p = NULL;
int chars;
int ret;
int result;
int done = 0;
unsigned long offset;
// prepare the key to look for the 'block'-th block of file
make_cpu_key(&key, inode,
(loff_t) block * inode->i_sb->s_blocksize + 1, TYPE_ANY,
3);
result = search_for_position_by_key(inode->i_sb, &key, &path);
if (result != POSITION_FOUND) {
pathrelse(&path);
if (p)
kunmap(bh_result->b_page);
if (result == IO_ERROR)
return -EIO;
// We do not return -ENOENT if there is a hole but page is uptodate, because it means
// That there is some MMAPED data associated with it that is yet to be written to disk.
if ((args & GET_BLOCK_NO_HOLE)
&& !PageUptodate(bh_result->b_page)) {
return -ENOENT;
}
return 0;
}
//
bh = get_last_bh(&path);
ih = get_ih(&path);
if (is_indirect_le_ih(ih)) {
__le32 *ind_item = (__le32 *) B_I_PITEM(bh, ih);
/* FIXME: here we could cache indirect item or part of it in
the inode to avoid search_by_key in case of subsequent
access to file */
blocknr = get_block_num(ind_item, path.pos_in_item);
ret = 0;
if (blocknr) {
map_bh(bh_result, inode->i_sb, blocknr);
if (path.pos_in_item ==
((ih_item_len(ih) / UNFM_P_SIZE) - 1)) {
set_buffer_boundary(bh_result);
}
} else
// We do not return -ENOENT if there is a hole but page is uptodate, because it means
// That there is some MMAPED data associated with it that is yet to be written to disk.
if ((args & GET_BLOCK_NO_HOLE)
&& !PageUptodate(bh_result->b_page)) {
ret = -ENOENT;
}
pathrelse(&path);
if (p)
kunmap(bh_result->b_page);
return ret;
}
// requested data are in direct item(s)
if (!(args & GET_BLOCK_READ_DIRECT)) {
// we are called by bmap. FIXME: we can not map block of file
// when it is stored in direct item(s)
pathrelse(&path);
if (p)
kunmap(bh_result->b_page);
return -ENOENT;
}
/* if we've got a direct item, and the buffer or page was uptodate,
** we don't want to pull data off disk again. skip to the
** end, where we map the buffer and return
*/
if (buffer_uptodate(bh_result)) {
goto finished;
} else
/*
** grab_tail_page can trigger calls to reiserfs_get_block on up to date
** pages without any buffers. If the page is up to date, we don't want
** read old data off disk. Set the up to date bit on the buffer instead
** and jump to the end
*/
if (!bh_result->b_page || PageUptodate(bh_result->b_page)) {
set_buffer_uptodate(bh_result);
goto finished;
}
// read file tail into part of page
offset = (cpu_key_k_offset(&key) - 1) & (PAGE_CACHE_SIZE - 1);
copy_item_head(&tmp_ih, ih);
/* we only want to kmap if we are reading the tail into the page.
** this is not the common case, so we don't kmap until we are
** sure we need to. But, this means the item might move if
** kmap schedules
*/
if (!p)
p = (char *)kmap(bh_result->b_page);
p += offset;
memset(p, 0, inode->i_sb->s_blocksize);
do {
if (!is_direct_le_ih(ih)) {
BUG();
}
/* make sure we don't read more bytes than actually exist in
** the file. This can happen in odd cases where i_size isn't
** correct, and when direct item padding results in a few
** extra bytes at the end of the direct item
*/
if ((le_ih_k_offset(ih) + path.pos_in_item) > inode->i_size)
break;
if ((le_ih_k_offset(ih) - 1 + ih_item_len(ih)) > inode->i_size) {
chars =
inode->i_size - (le_ih_k_offset(ih) - 1) -
path.pos_in_item;
done = 1;
} else {
chars = ih_item_len(ih) - path.pos_in_item;
}
memcpy(p, B_I_PITEM(bh, ih) + path.pos_in_item, chars);
if (done)
break;
p += chars;
if (PATH_LAST_POSITION(&path) != (B_NR_ITEMS(bh) - 1))
// we done, if read direct item is not the last item of
// node FIXME: we could try to check right delimiting key
// to see whether direct item continues in the right
// neighbor or rely on i_size
break;
// update key to look for the next piece
set_cpu_key_k_offset(&key, cpu_key_k_offset(&key) + chars);
result = search_for_position_by_key(inode->i_sb, &key, &path);
if (result != POSITION_FOUND)
// i/o error most likely
break;
bh = get_last_bh(&path);
ih = get_ih(&path);
} while (1);
flush_dcache_page(bh_result->b_page);
kunmap(bh_result->b_page);
finished:
pathrelse(&path);
if (result == IO_ERROR)
return -EIO;
/* this buffer has valid data, but isn't valid for io. mapping it to
* block #0 tells the rest of reiserfs it just has a tail in it
*/
map_bh(bh_result, inode->i_sb, 0);
set_buffer_uptodate(bh_result);
return 0;
}
// this is called to create file map. So, _get_block_create_0 will not
// read direct item
static int reiserfs_bmap(struct inode *inode, sector_t block,
struct buffer_head *bh_result, int create)
{
if (!file_capable(inode, block))
return -EFBIG;
reiserfs_write_lock(inode->i_sb);
/* do not read the direct item */
_get_block_create_0(inode, block, bh_result, 0);
reiserfs_write_unlock(inode->i_sb);
return 0;
}
/* special version of get_block that is only used by grab_tail_page right
** now. It is sent to block_prepare_write, and when you try to get a
** block past the end of the file (or a block from a hole) it returns
** -ENOENT instead of a valid buffer. block_prepare_write expects to
** be able to do i/o on the buffers returned, unless an error value
** is also returned.
**
** So, this allows block_prepare_write to be used for reading a single block
** in a page. Where it does not produce a valid page for holes, or past the
** end of the file. This turns out to be exactly what we need for reading
** tails for conversion.
**
** The point of the wrapper is forcing a certain value for create, even
** though the VFS layer is calling this function with create==1. If you
** don't want to send create == GET_BLOCK_NO_HOLE to reiserfs_get_block,
** don't use this function.
*/
static int reiserfs_get_block_create_0(struct inode *inode, sector_t block,
struct buffer_head *bh_result,
int create)
{
return reiserfs_get_block(inode, block, bh_result, GET_BLOCK_NO_HOLE);
}
/* This is special helper for reiserfs_get_block in case we are executing
direct_IO request. */
static int reiserfs_get_blocks_direct_io(struct inode *inode,
sector_t iblock,
struct buffer_head *bh_result,
int create)
{
int ret;
bh_result->b_page = NULL;
/* We set the b_size before reiserfs_get_block call since it is
referenced in convert_tail_for_hole() that may be called from
reiserfs_get_block() */
bh_result->b_size = (1 << inode->i_blkbits);
ret = reiserfs_get_block(inode, iblock, bh_result,
create | GET_BLOCK_NO_DANGLE);
if (ret)
goto out;
/* don't allow direct io onto tail pages */
if (buffer_mapped(bh_result) && bh_result->b_blocknr == 0) {
/* make sure future calls to the direct io funcs for this offset
** in the file fail by unmapping the buffer
*/
clear_buffer_mapped(bh_result);
ret = -EINVAL;
}
/* Possible unpacked tail. Flush the data before pages have
disappeared */
if (REISERFS_I(inode)->i_flags & i_pack_on_close_mask) {
int err;
reiserfs_write_lock(inode->i_sb);
err = reiserfs_commit_for_inode(inode);
REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask;
reiserfs_write_unlock(inode->i_sb);
if (err < 0)
ret = err;
}
out:
return ret;
}
/*
** helper function for when reiserfs_get_block is called for a hole
** but the file tail is still in a direct item
** bh_result is the buffer head for the hole
** tail_offset is the offset of the start of the tail in the file
**
** This calls prepare_write, which will start a new transaction
** you should not be in a transaction, or have any paths held when you
** call this.
*/
static int convert_tail_for_hole(struct inode *inode,
struct buffer_head *bh_result,
loff_t tail_offset)
{
unsigned long index;
unsigned long tail_end;
unsigned long tail_start;
struct page *tail_page;
struct page *hole_page = bh_result->b_page;
int retval = 0;
if ((tail_offset & (bh_result->b_size - 1)) != 1)
return -EIO;
/* always try to read until the end of the block */
tail_start = tail_offset & (PAGE_CACHE_SIZE - 1);
tail_end = (tail_start | (bh_result->b_size - 1)) + 1;
index = tail_offset >> PAGE_CACHE_SHIFT;
/* hole_page can be zero in case of direct_io, we are sure
that we cannot get here if we write with O_DIRECT into
tail page */
if (!hole_page || index != hole_page->index) {
tail_page = grab_cache_page(inode->i_mapping, index);
retval = -ENOMEM;
if (!tail_page) {
goto out;
}
} else {
tail_page = hole_page;
}
/* we don't have to make sure the conversion did not happen while
** we were locking the page because anyone that could convert
** must first take i_mutex.
**
** We must fix the tail page for writing because it might have buffers
** that are mapped, but have a block number of 0. This indicates tail
** data that has been read directly into the page, and block_prepare_write
** won't trigger a get_block in this case.
*/
fix_tail_page_for_writing(tail_page);
retval = reiserfs_prepare_write(NULL, tail_page, tail_start, tail_end);
if (retval)
goto unlock;
/* tail conversion might change the data in the page */
flush_dcache_page(tail_page);
retval = reiserfs_commit_write(NULL, tail_page, tail_start, tail_end);
unlock:
if (tail_page != hole_page) {
unlock_page(tail_page);
page_cache_release(tail_page);
}
out:
return retval;
}
static inline int _allocate_block(struct reiserfs_transaction_handle *th,
sector_t block,
struct inode *inode,
b_blocknr_t * allocated_block_nr,
struct treepath *path, int flags)
{
BUG_ON(!th->t_trans_id);
#ifdef REISERFS_PREALLOCATE
if (!(flags & GET_BLOCK_NO_IMUX)) {
return reiserfs_new_unf_blocknrs2(th, inode, allocated_block_nr,
path, block);
}
#endif
return reiserfs_new_unf_blocknrs(th, inode, allocated_block_nr, path,
block);
}
int reiserfs_get_block(struct inode *inode, sector_t block,
struct buffer_head *bh_result, int create)
{
int repeat, retval = 0;
b_blocknr_t allocated_block_nr = 0; // b_blocknr_t is (unsigned) 32 bit int
INITIALIZE_PATH(path);
int pos_in_item;
struct cpu_key key;
struct buffer_head *bh, *unbh = NULL;
struct item_head *ih, tmp_ih;
__le32 *item;
int done;
int fs_gen;
int lock_depth;
struct reiserfs_transaction_handle *th = NULL;
/* space reserved in transaction batch:
. 3 balancings in direct->indirect conversion
. 1 block involved into reiserfs_update_sd()
XXX in practically impossible worst case direct2indirect()
can incur (much) more than 3 balancings.
quota update for user, group */
int jbegin_count =
JOURNAL_PER_BALANCE_CNT * 3 + 1 +
2 * REISERFS_QUOTA_TRANS_BLOCKS(inode->i_sb);
int version;
int dangle = 1;
loff_t new_offset =
(((loff_t) block) << inode->i_sb->s_blocksize_bits) + 1;
lock_depth = reiserfs_write_lock_once(inode->i_sb);
version = get_inode_item_key_version(inode);
if (!file_capable(inode, block)) {
reiserfs_write_unlock_once(inode->i_sb, lock_depth);
return -EFBIG;
}
/* if !create, we aren't changing the FS, so we don't need to
** log anything, so we don't need to start a transaction
*/
if (!(create & GET_BLOCK_CREATE)) {
int ret;
/* find number of block-th logical block of the file */
ret = _get_block_create_0(inode, block, bh_result,
create | GET_BLOCK_READ_DIRECT);
reiserfs_write_unlock_once(inode->i_sb, lock_depth);
return ret;
}
/*
* if we're already in a transaction, make sure to close
* any new transactions we start in this func
*/
if ((create & GET_BLOCK_NO_DANGLE) ||
reiserfs_transaction_running(inode->i_sb))
dangle = 0;
/* If file is of such a size, that it might have a tail and tails are enabled
** we should mark it as possibly needing tail packing on close
*/
if ((have_large_tails(inode->i_sb)
&& inode->i_size < i_block_size(inode) * 4)
|| (have_small_tails(inode->i_sb)
&& inode->i_size < i_block_size(inode)))
REISERFS_I(inode)->i_flags |= i_pack_on_close_mask;
/* set the key of the first byte in the 'block'-th block of file */
make_cpu_key(&key, inode, new_offset, TYPE_ANY, 3 /*key length */ );
if ((new_offset + inode->i_sb->s_blocksize - 1) > inode->i_size) {
start_trans:
th = reiserfs_persistent_transaction(inode->i_sb, jbegin_count);
if (!th) {
retval = -ENOMEM;
goto failure;
}
reiserfs_update_inode_transaction(inode);
}
research:
retval = search_for_position_by_key(inode->i_sb, &key, &path);
if (retval == IO_ERROR) {
retval = -EIO;
goto failure;
}
bh = get_last_bh(&path);
ih = get_ih(&path);
item = get_item(&path);
pos_in_item = path.pos_in_item;
fs_gen = get_generation(inode->i_sb);
copy_item_head(&tmp_ih, ih);
if (allocation_needed
(retval, allocated_block_nr, ih, item, pos_in_item)) {
/* we have to allocate block for the unformatted node */
if (!th) {
pathrelse(&path);
goto start_trans;
}
repeat =
_allocate_block(th, block, inode, &allocated_block_nr,
&path, create);
if (repeat == NO_DISK_SPACE || repeat == QUOTA_EXCEEDED) {
/* restart the transaction to give the journal a chance to free
** some blocks. releases the path, so we have to go back to
** research if we succeed on the second try
*/
SB_JOURNAL(inode->i_sb)->j_next_async_flush = 1;
retval = restart_transaction(th, inode, &path);
if (retval)
goto failure;
repeat =
_allocate_block(th, block, inode,
&allocated_block_nr, NULL, create);
if (repeat != NO_DISK_SPACE && repeat != QUOTA_EXCEEDED) {
goto research;
}
if (repeat == QUOTA_EXCEEDED)
retval = -EDQUOT;
else
retval = -ENOSPC;
goto failure;
}
if (fs_changed(fs_gen, inode->i_sb)
&& item_moved(&tmp_ih, &path)) {
goto research;
}
}
if (indirect_item_found(retval, ih)) {
b_blocknr_t unfm_ptr;
/* 'block'-th block is in the file already (there is
corresponding cell in some indirect item). But it may be
zero unformatted node pointer (hole) */
unfm_ptr = get_block_num(item, pos_in_item);
if (unfm_ptr == 0) {
/* use allocated block to plug the hole */
reiserfs_prepare_for_journal(inode->i_sb, bh, 1);
if (fs_changed(fs_gen, inode->i_sb)
&& item_moved(&tmp_ih, &path)) {
reiserfs_restore_prepared_buffer(inode->i_sb,
bh);
goto research;
}
set_buffer_new(bh_result);
if (buffer_dirty(bh_result)
&& reiserfs_data_ordered(inode->i_sb))
reiserfs_add_ordered_list(inode, bh_result);
put_block_num(item, pos_in_item, allocated_block_nr);
unfm_ptr = allocated_block_nr;
journal_mark_dirty(th, inode->i_sb, bh);
reiserfs_update_sd(th, inode);
}
set_block_dev_mapped(bh_result, unfm_ptr, inode);
pathrelse(&path);
retval = 0;
if (!dangle && th)
retval = reiserfs_end_persistent_transaction(th);
reiserfs_write_unlock_once(inode->i_sb, lock_depth);
/* the item was found, so new blocks were not added to the file
** there is no need to make sure the inode is updated with this
** transaction
*/
return retval;
}
if (!th) {
pathrelse(&path);
goto start_trans;
}
/* desired position is not found or is in the direct item. We have
to append file with holes up to 'block'-th block converting
direct items to indirect one if necessary */
done = 0;
do {
if (is_statdata_le_ih(ih)) {
__le32 unp = 0;
struct cpu_key tmp_key;
/* indirect item has to be inserted */
make_le_item_head(&tmp_ih, &key, version, 1,
TYPE_INDIRECT, UNFM_P_SIZE,
0 /* free_space */ );
if (cpu_key_k_offset(&key) == 1) {
/* we are going to add 'block'-th block to the file. Use
allocated block for that */
unp = cpu_to_le32(allocated_block_nr);
set_block_dev_mapped(bh_result,
allocated_block_nr, inode);
set_buffer_new(bh_result);
done = 1;
}
tmp_key = key; // ;)
set_cpu_key_k_offset(&tmp_key, 1);
PATH_LAST_POSITION(&path)++;
retval =
reiserfs_insert_item(th, &path, &tmp_key, &tmp_ih,
inode, (char *)&unp);
if (retval) {
reiserfs_free_block(th, inode,
allocated_block_nr, 1);
goto failure; // retval == -ENOSPC, -EDQUOT or -EIO or -EEXIST
}
//mark_tail_converted (inode);
} else if (is_direct_le_ih(ih)) {
/* direct item has to be converted */
loff_t tail_offset;
tail_offset =
((le_ih_k_offset(ih) -
1) & ~(inode->i_sb->s_blocksize - 1)) + 1;
if (tail_offset == cpu_key_k_offset(&key)) {
/* direct item we just found fits into block we have
to map. Convert it into unformatted node: use
bh_result for the conversion */
set_block_dev_mapped(bh_result,
allocated_block_nr, inode);
unbh = bh_result;
done = 1;
} else {
/* we have to padd file tail stored in direct item(s)
up to block size and convert it to unformatted
node. FIXME: this should also get into page cache */
pathrelse(&path);
/*
* ugly, but we can only end the transaction if
* we aren't nested
*/
BUG_ON(!th->t_refcount);
if (th->t_refcount == 1) {
retval =
reiserfs_end_persistent_transaction
(th);
th = NULL;
if (retval)
goto failure;
}
retval =
convert_tail_for_hole(inode, bh_result,
tail_offset);
if (retval) {
if (retval != -ENOSPC)
reiserfs_error(inode->i_sb,
"clm-6004",
"convert tail failed "
"inode %lu, error %d",
inode->i_ino,
retval);
if (allocated_block_nr) {
/* the bitmap, the super, and the stat data == 3 */
if (!th)
th = reiserfs_persistent_transaction(inode->i_sb, 3);
if (th)
reiserfs_free_block(th,
inode,
allocated_block_nr,
1);
}
goto failure;
}
goto research;
}
retval =
direct2indirect(th, inode, &path, unbh,
tail_offset);
if (retval) {
reiserfs_unmap_buffer(unbh);
reiserfs_free_block(th, inode,
allocated_block_nr, 1);
goto failure;
}
/* it is important the set_buffer_uptodate is done after
** the direct2indirect. The buffer might contain valid
** data newer than the data on disk (read by readpage, changed,
** and then sent here by writepage). direct2indirect needs
** to know if unbh was already up to date, so it can decide
** if the data in unbh needs to be replaced with data from
** the disk
*/
set_buffer_uptodate(unbh);
/* unbh->b_page == NULL in case of DIRECT_IO request, this means
buffer will disappear shortly, so it should not be added to
*/
if (unbh->b_page) {
/* we've converted the tail, so we must
** flush unbh before the transaction commits
*/
reiserfs_add_tail_list(inode, unbh);
/* mark it dirty now to prevent commit_write from adding
** this buffer to the inode's dirty buffer list
*/
/*
* AKPM: changed __mark_buffer_dirty to mark_buffer_dirty().
* It's still atomic, but it sets the page dirty too,
* which makes it eligible for writeback at any time by the
* VM (which was also the case with __mark_buffer_dirty())
*/
mark_buffer_dirty(unbh);
}
} else {
/* append indirect item with holes if needed, when appending
pointer to 'block'-th block use block, which is already
allocated */
struct cpu_key tmp_key;
unp_t unf_single = 0; // We use this in case we need to allocate only
// one block which is a fastpath
unp_t *un;
__u64 max_to_insert =
MAX_ITEM_LEN(inode->i_sb->s_blocksize) /
UNFM_P_SIZE;
__u64 blocks_needed;
RFALSE(pos_in_item != ih_item_len(ih) / UNFM_P_SIZE,
"vs-804: invalid position for append");
/* indirect item has to be appended, set up key of that position */
make_cpu_key(&tmp_key, inode,
le_key_k_offset(version,
&(ih->ih_key)) +
op_bytes_number(ih,
inode->i_sb->s_blocksize),
//pos_in_item * inode->i_sb->s_blocksize,
TYPE_INDIRECT, 3); // key type is unimportant
RFALSE(cpu_key_k_offset(&tmp_key) > cpu_key_k_offset(&key),
"green-805: invalid offset");
blocks_needed =
1 +
((cpu_key_k_offset(&key) -
cpu_key_k_offset(&tmp_key)) >> inode->i_sb->
s_blocksize_bits);
if (blocks_needed == 1) {
un = &unf_single;
} else {
un = kzalloc(min(blocks_needed, max_to_insert) * UNFM_P_SIZE, GFP_NOFS);
if (!un) {
un = &unf_single;
blocks_needed = 1;
max_to_insert = 0;
}
}
if (blocks_needed <= max_to_insert) {
/* we are going to add target block to the file. Use allocated
block for that */
un[blocks_needed - 1] =
cpu_to_le32(allocated_block_nr);
set_block_dev_mapped(bh_result,
allocated_block_nr, inode);
set_buffer_new(bh_result);
done = 1;
} else {
/* paste hole to the indirect item */
/* If kmalloc failed, max_to_insert becomes zero and it means we
only have space for one block */
blocks_needed =
max_to_insert ? max_to_insert : 1;
}
retval =
reiserfs_paste_into_item(th, &path, &tmp_key, inode,
(char *)un,
UNFM_P_SIZE *
blocks_needed);
if (blocks_needed != 1)
kfree(un);
if (retval) {
reiserfs_free_block(th, inode,
allocated_block_nr, 1);
goto failure;
}
if (!done) {
/* We need to mark new file size in case this function will be
interrupted/aborted later on. And we may do this only for
holes. */
inode->i_size +=
inode->i_sb->s_blocksize * blocks_needed;
}
}
if (done == 1)
break;
/* this loop could log more blocks than we had originally asked
** for. So, we have to allow the transaction to end if it is
** too big or too full. Update the inode so things are
** consistent if we crash before the function returns
**
** release the path so that anybody waiting on the path before
** ending their transaction will be able to continue.
*/
if (journal_transaction_should_end(th, th->t_blocks_allocated)) {
retval = restart_transaction(th, inode, &path);
if (retval)
goto failure;
}