forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
aops.c
2048 lines (1746 loc) · 51.7 KB
/
aops.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
/* -*- mode: c; c-basic-offset: 8; -*-
* vim: noexpandtab sw=8 ts=8 sts=0:
*
* Copyright (C) 2002, 2004 Oracle. All rights reserved.
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public
* License as published by the Free Software Foundation; either
* version 2 of the License, or (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
* General Public License for more details.
*
* You should have received a copy of the GNU General Public
* License along with this program; if not, write to the
* Free Software Foundation, Inc., 59 Temple Place - Suite 330,
* Boston, MA 021110-1307, USA.
*/
#include <linux/fs.h>
#include <linux/slab.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <asm/byteorder.h>
#include <linux/swap.h>
#include <linux/pipe_fs_i.h>
#include <linux/mpage.h>
#include <linux/quotaops.h>
#include <cluster/masklog.h>
#include "ocfs2.h"
#include "alloc.h"
#include "aops.h"
#include "dlmglue.h"
#include "extent_map.h"
#include "file.h"
#include "inode.h"
#include "journal.h"
#include "suballoc.h"
#include "super.h"
#include "symlink.h"
#include "refcounttree.h"
#include "ocfs2_trace.h"
#include "buffer_head_io.h"
static int ocfs2_symlink_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int err = -EIO;
int status;
struct ocfs2_dinode *fe = NULL;
struct buffer_head *bh = NULL;
struct buffer_head *buffer_cache_bh = NULL;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
void *kaddr;
trace_ocfs2_symlink_get_block(
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)iblock, bh_result, create);
BUG_ON(ocfs2_inode_is_fast_symlink(inode));
if ((iblock << inode->i_sb->s_blocksize_bits) > PATH_MAX + 1) {
mlog(ML_ERROR, "block offset > PATH_MAX: %llu",
(unsigned long long)iblock);
goto bail;
}
status = ocfs2_read_inode_block(inode, &bh);
if (status < 0) {
mlog_errno(status);
goto bail;
}
fe = (struct ocfs2_dinode *) bh->b_data;
if ((u64)iblock >= ocfs2_clusters_to_blocks(inode->i_sb,
le32_to_cpu(fe->i_clusters))) {
mlog(ML_ERROR, "block offset is outside the allocated size: "
"%llu\n", (unsigned long long)iblock);
goto bail;
}
/* We don't use the page cache to create symlink data, so if
* need be, copy it over from the buffer cache. */
if (!buffer_uptodate(bh_result) && ocfs2_inode_is_new(inode)) {
u64 blkno = le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) +
iblock;
buffer_cache_bh = sb_getblk(osb->sb, blkno);
if (!buffer_cache_bh) {
mlog(ML_ERROR, "couldn't getblock for symlink!\n");
goto bail;
}
/* we haven't locked out transactions, so a commit
* could've happened. Since we've got a reference on
* the bh, even if it commits while we're doing the
* copy, the data is still good. */
if (buffer_jbd(buffer_cache_bh)
&& ocfs2_inode_is_new(inode)) {
kaddr = kmap_atomic(bh_result->b_page, KM_USER0);
if (!kaddr) {
mlog(ML_ERROR, "couldn't kmap!\n");
goto bail;
}
memcpy(kaddr + (bh_result->b_size * iblock),
buffer_cache_bh->b_data,
bh_result->b_size);
kunmap_atomic(kaddr, KM_USER0);
set_buffer_uptodate(bh_result);
}
brelse(buffer_cache_bh);
}
map_bh(bh_result, inode->i_sb,
le64_to_cpu(fe->id2.i_list.l_recs[0].e_blkno) + iblock);
err = 0;
bail:
brelse(bh);
return err;
}
int ocfs2_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int err = 0;
unsigned int ext_flags;
u64 max_blocks = bh_result->b_size >> inode->i_blkbits;
u64 p_blkno, count, past_eof;
struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
trace_ocfs2_get_block((unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)iblock, bh_result, create);
if (OCFS2_I(inode)->ip_flags & OCFS2_INODE_SYSTEM_FILE)
mlog(ML_NOTICE, "get_block on system inode 0x%p (%lu)\n",
inode, inode->i_ino);
if (S_ISLNK(inode->i_mode)) {
/* this always does I/O for some reason. */
err = ocfs2_symlink_get_block(inode, iblock, bh_result, create);
goto bail;
}
err = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno, &count,
&ext_flags);
if (err) {
mlog(ML_ERROR, "Error %d from get_blocks(0x%p, %llu, 1, "
"%llu, NULL)\n", err, inode, (unsigned long long)iblock,
(unsigned long long)p_blkno);
goto bail;
}
if (max_blocks < count)
count = max_blocks;
/*
* ocfs2 never allocates in this function - the only time we
* need to use BH_New is when we're extending i_size on a file
* system which doesn't support holes, in which case BH_New
* allows __block_write_begin() to zero.
*
* If we see this on a sparse file system, then a truncate has
* raced us and removed the cluster. In this case, we clear
* the buffers dirty and uptodate bits and let the buffer code
* ignore it as a hole.
*/
if (create && p_blkno == 0 && ocfs2_sparse_alloc(osb)) {
clear_buffer_dirty(bh_result);
clear_buffer_uptodate(bh_result);
goto bail;
}
/* Treat the unwritten extent as a hole for zeroing purposes. */
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
bh_result->b_size = count << inode->i_blkbits;
if (!ocfs2_sparse_alloc(osb)) {
if (p_blkno == 0) {
err = -EIO;
mlog(ML_ERROR,
"iblock = %llu p_blkno = %llu blkno=(%llu)\n",
(unsigned long long)iblock,
(unsigned long long)p_blkno,
(unsigned long long)OCFS2_I(inode)->ip_blkno);
mlog(ML_ERROR, "Size %llu, clusters %u\n", (unsigned long long)i_size_read(inode), OCFS2_I(inode)->ip_clusters);
dump_stack();
goto bail;
}
}
past_eof = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
trace_ocfs2_get_block_end((unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)past_eof);
if (create && (iblock >= past_eof))
set_buffer_new(bh_result);
bail:
if (err < 0)
err = -EIO;
return err;
}
int ocfs2_read_inline_data(struct inode *inode, struct page *page,
struct buffer_head *di_bh)
{
void *kaddr;
loff_t size;
struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
if (!(le16_to_cpu(di->i_dyn_features) & OCFS2_INLINE_DATA_FL)) {
ocfs2_error(inode->i_sb, "Inode %llu lost inline data flag",
(unsigned long long)OCFS2_I(inode)->ip_blkno);
return -EROFS;
}
size = i_size_read(inode);
if (size > PAGE_CACHE_SIZE ||
size > ocfs2_max_inline_data_with_xattr(inode->i_sb, di)) {
ocfs2_error(inode->i_sb,
"Inode %llu has with inline data has bad size: %Lu",
(unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)size);
return -EROFS;
}
kaddr = kmap_atomic(page, KM_USER0);
if (size)
memcpy(kaddr, di->id2.i_data.id_data, size);
/* Clear the remaining part of the page */
memset(kaddr + size, 0, PAGE_CACHE_SIZE - size);
flush_dcache_page(page);
kunmap_atomic(kaddr, KM_USER0);
SetPageUptodate(page);
return 0;
}
static int ocfs2_readpage_inline(struct inode *inode, struct page *page)
{
int ret;
struct buffer_head *di_bh = NULL;
BUG_ON(!PageLocked(page));
BUG_ON(!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL));
ret = ocfs2_read_inode_block(inode, &di_bh);
if (ret) {
mlog_errno(ret);
goto out;
}
ret = ocfs2_read_inline_data(inode, page, di_bh);
out:
unlock_page(page);
brelse(di_bh);
return ret;
}
static int ocfs2_readpage(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
loff_t start = (loff_t)page->index << PAGE_CACHE_SHIFT;
int ret, unlock = 1;
trace_ocfs2_readpage((unsigned long long)oi->ip_blkno,
(page ? page->index : 0));
ret = ocfs2_inode_lock_with_page(inode, NULL, 0, page);
if (ret != 0) {
if (ret == AOP_TRUNCATED_PAGE)
unlock = 0;
mlog_errno(ret);
goto out;
}
if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
ret = AOP_TRUNCATED_PAGE;
goto out_inode_unlock;
}
/*
* i_size might have just been updated as we grabed the meta lock. We
* might now be discovering a truncate that hit on another node.
* block_read_full_page->get_block freaks out if it is asked to read
* beyond the end of a file, so we check here. Callers
* (generic_file_read, vm_ops->fault) are clever enough to check i_size
* and notice that the page they just read isn't needed.
*
* XXX sys_readahead() seems to get that wrong?
*/
if (start >= i_size_read(inode)) {
zero_user(page, 0, PAGE_SIZE);
SetPageUptodate(page);
ret = 0;
goto out_alloc;
}
if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
ret = ocfs2_readpage_inline(inode, page);
else
ret = block_read_full_page(page, ocfs2_get_block);
unlock = 0;
out_alloc:
up_read(&OCFS2_I(inode)->ip_alloc_sem);
out_inode_unlock:
ocfs2_inode_unlock(inode, 0);
out:
if (unlock)
unlock_page(page);
return ret;
}
/*
* This is used only for read-ahead. Failures or difficult to handle
* situations are safe to ignore.
*
* Right now, we don't bother with BH_Boundary - in-inode extent lists
* are quite large (243 extents on 4k blocks), so most inodes don't
* grow out to a tree. If need be, detecting boundary extents could
* trivially be added in a future version of ocfs2_get_block().
*/
static int ocfs2_readpages(struct file *filp, struct address_space *mapping,
struct list_head *pages, unsigned nr_pages)
{
int ret, err = -EIO;
struct inode *inode = mapping->host;
struct ocfs2_inode_info *oi = OCFS2_I(inode);
loff_t start;
struct page *last;
/*
* Use the nonblocking flag for the dlm code to avoid page
* lock inversion, but don't bother with retrying.
*/
ret = ocfs2_inode_lock_full(inode, NULL, 0, OCFS2_LOCK_NONBLOCK);
if (ret)
return err;
if (down_read_trylock(&oi->ip_alloc_sem) == 0) {
ocfs2_inode_unlock(inode, 0);
return err;
}
/*
* Don't bother with inline-data. There isn't anything
* to read-ahead in that case anyway...
*/
if (oi->ip_dyn_features & OCFS2_INLINE_DATA_FL)
goto out_unlock;
/*
* Check whether a remote node truncated this file - we just
* drop out in that case as it's not worth handling here.
*/
last = list_entry(pages->prev, struct page, lru);
start = (loff_t)last->index << PAGE_CACHE_SHIFT;
if (start >= i_size_read(inode))
goto out_unlock;
err = mpage_readpages(mapping, pages, nr_pages, ocfs2_get_block);
out_unlock:
up_read(&oi->ip_alloc_sem);
ocfs2_inode_unlock(inode, 0);
return err;
}
/* Note: Because we don't support holes, our allocation has
* already happened (allocation writes zeros to the file data)
* so we don't have to worry about ordered writes in
* ocfs2_writepage.
*
* ->writepage is called during the process of invalidating the page cache
* during blocked lock processing. It can't block on any cluster locks
* to during block mapping. It's relying on the fact that the block
* mapping can't have disappeared under the dirty pages that it is
* being asked to write back.
*/
static int ocfs2_writepage(struct page *page, struct writeback_control *wbc)
{
trace_ocfs2_writepage(
(unsigned long long)OCFS2_I(page->mapping->host)->ip_blkno,
page->index);
return block_write_full_page(page, ocfs2_get_block, wbc);
}
/* Taken from ext3. We don't necessarily need the full blown
* functionality yet, but IMHO it's better to cut and paste the whole
* thing so we can avoid introducing our own bugs (and easily pick up
* their fixes when they happen) --Mark */
int walk_page_buffers( handle_t *handle,
struct buffer_head *head,
unsigned from,
unsigned to,
int *partial,
int (*fn)( handle_t *handle,
struct buffer_head *bh))
{
struct buffer_head *bh;
unsigned block_start, block_end;
unsigned blocksize = head->b_size;
int err, ret = 0;
struct buffer_head *next;
for ( bh = head, block_start = 0;
ret == 0 && (bh != head || !block_start);
block_start = block_end, bh = next)
{
next = bh->b_this_page;
block_end = block_start + blocksize;
if (block_end <= from || block_start >= to) {
if (partial && !buffer_uptodate(bh))
*partial = 1;
continue;
}
err = (*fn)(handle, bh);
if (!ret)
ret = err;
}
return ret;
}
static sector_t ocfs2_bmap(struct address_space *mapping, sector_t block)
{
sector_t status;
u64 p_blkno = 0;
int err = 0;
struct inode *inode = mapping->host;
trace_ocfs2_bmap((unsigned long long)OCFS2_I(inode)->ip_blkno,
(unsigned long long)block);
/* We don't need to lock journal system files, since they aren't
* accessed concurrently from multiple nodes.
*/
if (!INODE_JOURNAL(inode)) {
err = ocfs2_inode_lock(inode, NULL, 0);
if (err) {
if (err != -ENOENT)
mlog_errno(err);
goto bail;
}
down_read(&OCFS2_I(inode)->ip_alloc_sem);
}
if (!(OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL))
err = ocfs2_extent_map_get_blocks(inode, block, &p_blkno, NULL,
NULL);
if (!INODE_JOURNAL(inode)) {
up_read(&OCFS2_I(inode)->ip_alloc_sem);
ocfs2_inode_unlock(inode, 0);
}
if (err) {
mlog(ML_ERROR, "get_blocks() failed, block = %llu\n",
(unsigned long long)block);
mlog_errno(err);
goto bail;
}
bail:
status = err ? 0 : p_blkno;
return status;
}
/*
* TODO: Make this into a generic get_blocks function.
*
* From do_direct_io in direct-io.c:
* "So what we do is to permit the ->get_blocks function to populate
* bh.b_size with the size of IO which is permitted at this offset and
* this i_blkbits."
*
* This function is called directly from get_more_blocks in direct-io.c.
*
* called like this: dio->get_blocks(dio->inode, fs_startblk,
* fs_count, map_bh, dio->rw == WRITE);
*
* Note that we never bother to allocate blocks here, and thus ignore the
* create argument.
*/
static int ocfs2_direct_IO_get_blocks(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create)
{
int ret;
u64 p_blkno, inode_blocks, contig_blocks;
unsigned int ext_flags;
unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
unsigned long max_blocks = bh_result->b_size >> inode->i_blkbits;
/* This function won't even be called if the request isn't all
* nicely aligned and of the right size, so there's no need
* for us to check any of that. */
inode_blocks = ocfs2_blocks_for_bytes(inode->i_sb, i_size_read(inode));
/* This figures out the size of the next contiguous block, and
* our logical offset */
ret = ocfs2_extent_map_get_blocks(inode, iblock, &p_blkno,
&contig_blocks, &ext_flags);
if (ret) {
mlog(ML_ERROR, "get_blocks() failed iblock=%llu\n",
(unsigned long long)iblock);
ret = -EIO;
goto bail;
}
/* We should already CoW the refcounted extent in case of create. */
BUG_ON(create && (ext_flags & OCFS2_EXT_REFCOUNTED));
/*
* get_more_blocks() expects us to describe a hole by clearing
* the mapped bit on bh_result().
*
* Consider an unwritten extent as a hole.
*/
if (p_blkno && !(ext_flags & OCFS2_EXT_UNWRITTEN))
map_bh(bh_result, inode->i_sb, p_blkno);
else
clear_buffer_mapped(bh_result);
/* make sure we don't map more than max_blocks blocks here as
that's all the kernel will handle at this point. */
if (max_blocks < contig_blocks)
contig_blocks = max_blocks;
bh_result->b_size = contig_blocks << blocksize_bits;
bail:
return ret;
}
/*
* ocfs2_dio_end_io is called by the dio core when a dio is finished. We're
* particularly interested in the aio/dio case. Like the core uses
* i_alloc_sem, we use the rw_lock DLM lock to protect io on one node from
* truncation on another.
*/
static void ocfs2_dio_end_io(struct kiocb *iocb,
loff_t offset,
ssize_t bytes,
void *private,
int ret,
bool is_async)
{
struct inode *inode = iocb->ki_filp->f_path.dentry->d_inode;
int level;
/* this io's submitter should not have unlocked this before we could */
BUG_ON(!ocfs2_iocb_is_rw_locked(iocb));
if (ocfs2_iocb_is_sem_locked(iocb)) {
up_read(&inode->i_alloc_sem);
ocfs2_iocb_clear_sem_locked(iocb);
}
ocfs2_iocb_clear_rw_locked(iocb);
level = ocfs2_iocb_rw_locked_level(iocb);
ocfs2_rw_unlock(inode, level);
if (is_async)
aio_complete(iocb, ret, 0);
}
/*
* ocfs2_invalidatepage() and ocfs2_releasepage() are shamelessly stolen
* from ext3. PageChecked() bits have been removed as OCFS2 does not
* do journalled data.
*/
static void ocfs2_invalidatepage(struct page *page, unsigned long offset)
{
journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
jbd2_journal_invalidatepage(journal, page, offset);
}
static int ocfs2_releasepage(struct page *page, gfp_t wait)
{
journal_t *journal = OCFS2_SB(page->mapping->host->i_sb)->journal->j_journal;
if (!page_has_buffers(page))
return 0;
return jbd2_journal_try_to_free_buffers(journal, page, wait);
}
static ssize_t ocfs2_direct_IO(int rw,
struct kiocb *iocb,
const struct iovec *iov,
loff_t offset,
unsigned long nr_segs)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_path.dentry->d_inode->i_mapping->host;
/*
* Fallback to buffered I/O if we see an inode without
* extents.
*/
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return 0;
/* Fallback to buffered I/O if we are appending. */
if (i_size_read(inode) <= offset)
return 0;
return __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev,
iov, offset, nr_segs,
ocfs2_direct_IO_get_blocks,
ocfs2_dio_end_io, NULL, 0);
}
static void ocfs2_figure_cluster_boundaries(struct ocfs2_super *osb,
u32 cpos,
unsigned int *start,
unsigned int *end)
{
unsigned int cluster_start = 0, cluster_end = PAGE_CACHE_SIZE;
if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits)) {
unsigned int cpp;
cpp = 1 << (PAGE_CACHE_SHIFT - osb->s_clustersize_bits);
cluster_start = cpos % cpp;
cluster_start = cluster_start << osb->s_clustersize_bits;
cluster_end = cluster_start + osb->s_clustersize;
}
BUG_ON(cluster_start > PAGE_SIZE);
BUG_ON(cluster_end > PAGE_SIZE);
if (start)
*start = cluster_start;
if (end)
*end = cluster_end;
}
/*
* 'from' and 'to' are the region in the page to avoid zeroing.
*
* If pagesize > clustersize, this function will avoid zeroing outside
* of the cluster boundary.
*
* from == to == 0 is code for "zero the entire cluster region"
*/
static void ocfs2_clear_page_regions(struct page *page,
struct ocfs2_super *osb, u32 cpos,
unsigned from, unsigned to)
{
void *kaddr;
unsigned int cluster_start, cluster_end;
ocfs2_figure_cluster_boundaries(osb, cpos, &cluster_start, &cluster_end);
kaddr = kmap_atomic(page, KM_USER0);
if (from || to) {
if (from > cluster_start)
memset(kaddr + cluster_start, 0, from - cluster_start);
if (to < cluster_end)
memset(kaddr + to, 0, cluster_end - to);
} else {
memset(kaddr + cluster_start, 0, cluster_end - cluster_start);
}
kunmap_atomic(kaddr, KM_USER0);
}
/*
* Nonsparse file systems fully allocate before we get to the write
* code. This prevents ocfs2_write() from tagging the write as an
* allocating one, which means ocfs2_map_page_blocks() might try to
* read-in the blocks at the tail of our file. Avoid reading them by
* testing i_size against each block offset.
*/
static int ocfs2_should_read_blk(struct inode *inode, struct page *page,
unsigned int block_start)
{
u64 offset = page_offset(page) + block_start;
if (ocfs2_sparse_alloc(OCFS2_SB(inode->i_sb)))
return 1;
if (i_size_read(inode) > offset)
return 1;
return 0;
}
/*
* Some of this taken from __block_write_begin(). We already have our
* mapping by now though, and the entire write will be allocating or
* it won't, so not much need to use BH_New.
*
* This will also skip zeroing, which is handled externally.
*/
int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
struct inode *inode, unsigned int from,
unsigned int to, int new)
{
int ret = 0;
struct buffer_head *head, *bh, *wait[2], **wait_bh = wait;
unsigned int block_end, block_start;
unsigned int bsize = 1 << inode->i_blkbits;
if (!page_has_buffers(page))
create_empty_buffers(page, bsize, 0);
head = page_buffers(page);
for (bh = head, block_start = 0; bh != head || !block_start;
bh = bh->b_this_page, block_start += bsize) {
block_end = block_start + bsize;
clear_buffer_new(bh);
/*
* Ignore blocks outside of our i/o range -
* they may belong to unallocated clusters.
*/
if (block_start >= to || block_end <= from) {
if (PageUptodate(page))
set_buffer_uptodate(bh);
continue;
}
/*
* For an allocating write with cluster size >= page
* size, we always write the entire page.
*/
if (new)
set_buffer_new(bh);
if (!buffer_mapped(bh)) {
map_bh(bh, inode->i_sb, *p_blkno);
unmap_underlying_metadata(bh->b_bdev, bh->b_blocknr);
}
if (PageUptodate(page)) {
if (!buffer_uptodate(bh))
set_buffer_uptodate(bh);
} else if (!buffer_uptodate(bh) && !buffer_delay(bh) &&
!buffer_new(bh) &&
ocfs2_should_read_blk(inode, page, block_start) &&
(block_start < from || block_end > to)) {
ll_rw_block(READ, 1, &bh);
*wait_bh++=bh;
}
*p_blkno = *p_blkno + 1;
}
/*
* If we issued read requests - let them complete.
*/
while(wait_bh > wait) {
wait_on_buffer(*--wait_bh);
if (!buffer_uptodate(*wait_bh))
ret = -EIO;
}
if (ret == 0 || !new)
return ret;
/*
* If we get -EIO above, zero out any newly allocated blocks
* to avoid exposing stale data.
*/
bh = head;
block_start = 0;
do {
block_end = block_start + bsize;
if (block_end <= from)
goto next_bh;
if (block_start >= to)
break;
zero_user(page, block_start, bh->b_size);
set_buffer_uptodate(bh);
mark_buffer_dirty(bh);
next_bh:
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
return ret;
}
#if (PAGE_CACHE_SIZE >= OCFS2_MAX_CLUSTERSIZE)
#define OCFS2_MAX_CTXT_PAGES 1
#else
#define OCFS2_MAX_CTXT_PAGES (OCFS2_MAX_CLUSTERSIZE / PAGE_CACHE_SIZE)
#endif
#define OCFS2_MAX_CLUSTERS_PER_PAGE (PAGE_CACHE_SIZE / OCFS2_MIN_CLUSTERSIZE)
/*
* Describe the state of a single cluster to be written to.
*/
struct ocfs2_write_cluster_desc {
u32 c_cpos;
u32 c_phys;
/*
* Give this a unique field because c_phys eventually gets
* filled.
*/
unsigned c_new;
unsigned c_unwritten;
unsigned c_needs_zero;
};
struct ocfs2_write_ctxt {
/* Logical cluster position / len of write */
u32 w_cpos;
u32 w_clen;
/* First cluster allocated in a nonsparse extend */
u32 w_first_new_cpos;
struct ocfs2_write_cluster_desc w_desc[OCFS2_MAX_CLUSTERS_PER_PAGE];
/*
* This is true if page_size > cluster_size.
*
* It triggers a set of special cases during write which might
* have to deal with allocating writes to partial pages.
*/
unsigned int w_large_pages;
/*
* Pages involved in this write.
*
* w_target_page is the page being written to by the user.
*
* w_pages is an array of pages which always contains
* w_target_page, and in the case of an allocating write with
* page_size < cluster size, it will contain zero'd and mapped
* pages adjacent to w_target_page which need to be written
* out in so that future reads from that region will get
* zero's.
*/
unsigned int w_num_pages;
struct page *w_pages[OCFS2_MAX_CTXT_PAGES];
struct page *w_target_page;
/*
* ocfs2_write_end() uses this to know what the real range to
* write in the target should be.
*/
unsigned int w_target_from;
unsigned int w_target_to;
/*
* We could use journal_current_handle() but this is cleaner,
* IMHO -Mark
*/
handle_t *w_handle;
struct buffer_head *w_di_bh;
struct ocfs2_cached_dealloc_ctxt w_dealloc;
};
void ocfs2_unlock_and_free_pages(struct page **pages, int num_pages)
{
int i;
for(i = 0; i < num_pages; i++) {
if (pages[i]) {
unlock_page(pages[i]);
mark_page_accessed(pages[i]);
page_cache_release(pages[i]);
}
}
}
static void ocfs2_free_write_ctxt(struct ocfs2_write_ctxt *wc)
{
ocfs2_unlock_and_free_pages(wc->w_pages, wc->w_num_pages);
brelse(wc->w_di_bh);
kfree(wc);
}
static int ocfs2_alloc_write_ctxt(struct ocfs2_write_ctxt **wcp,
struct ocfs2_super *osb, loff_t pos,
unsigned len, struct buffer_head *di_bh)
{
u32 cend;
struct ocfs2_write_ctxt *wc;
wc = kzalloc(sizeof(struct ocfs2_write_ctxt), GFP_NOFS);
if (!wc)
return -ENOMEM;
wc->w_cpos = pos >> osb->s_clustersize_bits;
wc->w_first_new_cpos = UINT_MAX;
cend = (pos + len - 1) >> osb->s_clustersize_bits;
wc->w_clen = cend - wc->w_cpos + 1;
get_bh(di_bh);
wc->w_di_bh = di_bh;
if (unlikely(PAGE_CACHE_SHIFT > osb->s_clustersize_bits))
wc->w_large_pages = 1;
else
wc->w_large_pages = 0;
ocfs2_init_dealloc_ctxt(&wc->w_dealloc);
*wcp = wc;
return 0;
}
/*
* If a page has any new buffers, zero them out here, and mark them uptodate
* and dirty so they'll be written out (in order to prevent uninitialised
* block data from leaking). And clear the new bit.
*/
static void ocfs2_zero_new_buffers(struct page *page, unsigned from, unsigned to)
{
unsigned int block_start, block_end;
struct buffer_head *head, *bh;
BUG_ON(!PageLocked(page));
if (!page_has_buffers(page))
return;
bh = head = page_buffers(page);
block_start = 0;
do {
block_end = block_start + bh->b_size;
if (buffer_new(bh)) {
if (block_end > from && block_start < to) {
if (!PageUptodate(page)) {
unsigned start, end;
start = max(from, block_start);
end = min(to, block_end);
zero_user_segment(page, start, end);
set_buffer_uptodate(bh);
}
clear_buffer_new(bh);
mark_buffer_dirty(bh);
}
}
block_start = block_end;
bh = bh->b_this_page;
} while (bh != head);
}
/*
* Only called when we have a failure during allocating write to write
* zero's to the newly allocated region.
*/
static void ocfs2_write_failure(struct inode *inode,
struct ocfs2_write_ctxt *wc,
loff_t user_pos, unsigned user_len)
{
int i;
unsigned from = user_pos & (PAGE_CACHE_SIZE - 1),
to = user_pos + user_len;
struct page *tmppage;
ocfs2_zero_new_buffers(wc->w_target_page, from, to);
for(i = 0; i < wc->w_num_pages; i++) {
tmppage = wc->w_pages[i];
if (page_has_buffers(tmppage)) {
if (ocfs2_should_order_data(inode))
ocfs2_jbd2_file_inode(wc->w_handle, inode);
block_commit_write(tmppage, from, to);
}