forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xfs_aops.c
1847 lines (1620 loc) · 49 KB
/
xfs_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
/*
* Copyright (c) 2000-2005 Silicon Graphics, Inc.
* 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.
*
* This program is distributed in the hope that it would 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 the Free Software Foundation,
* Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA
*/
#include "xfs.h"
#include "xfs_shared.h"
#include "xfs_format.h"
#include "xfs_log_format.h"
#include "xfs_trans_resv.h"
#include "xfs_mount.h"
#include "xfs_inode.h"
#include "xfs_trans.h"
#include "xfs_inode_item.h"
#include "xfs_alloc.h"
#include "xfs_error.h"
#include "xfs_iomap.h"
#include "xfs_trace.h"
#include "xfs_bmap.h"
#include "xfs_bmap_util.h"
#include "xfs_bmap_btree.h"
#include <linux/aio.h>
#include <linux/gfp.h>
#include <linux/mpage.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
void
xfs_count_page_state(
struct page *page,
int *delalloc,
int *unwritten)
{
struct buffer_head *bh, *head;
*delalloc = *unwritten = 0;
bh = head = page_buffers(page);
do {
if (buffer_unwritten(bh))
(*unwritten) = 1;
else if (buffer_delay(bh))
(*delalloc) = 1;
} while ((bh = bh->b_this_page) != head);
}
STATIC struct block_device *
xfs_find_bdev_for_inode(
struct inode *inode)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
if (XFS_IS_REALTIME_INODE(ip))
return mp->m_rtdev_targp->bt_bdev;
else
return mp->m_ddev_targp->bt_bdev;
}
/*
* We're now finished for good with this ioend structure.
* Update the page state via the associated buffer_heads,
* release holds on the inode and bio, and finally free
* up memory. Do not use the ioend after this.
*/
STATIC void
xfs_destroy_ioend(
xfs_ioend_t *ioend)
{
struct buffer_head *bh, *next;
for (bh = ioend->io_buffer_head; bh; bh = next) {
next = bh->b_private;
bh->b_end_io(bh, !ioend->io_error);
}
mempool_free(ioend, xfs_ioend_pool);
}
/*
* Fast and loose check if this write could update the on-disk inode size.
*/
static inline bool xfs_ioend_is_append(struct xfs_ioend *ioend)
{
return ioend->io_offset + ioend->io_size >
XFS_I(ioend->io_inode)->i_d.di_size;
}
STATIC int
xfs_setfilesize_trans_alloc(
struct xfs_ioend *ioend)
{
struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount;
struct xfs_trans *tp;
int error;
tp = xfs_trans_alloc(mp, XFS_TRANS_FSYNC_TS);
error = xfs_trans_reserve(tp, &M_RES(mp)->tr_fsyncts, 0, 0);
if (error) {
xfs_trans_cancel(tp, 0);
return error;
}
ioend->io_append_trans = tp;
/*
* We may pass freeze protection with a transaction. So tell lockdep
* we released it.
*/
rwsem_release(&ioend->io_inode->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
1, _THIS_IP_);
/*
* We hand off the transaction to the completion thread now, so
* clear the flag here.
*/
current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
return 0;
}
/*
* Update on-disk file size now that data has been written to disk.
*/
STATIC int
xfs_setfilesize(
struct xfs_ioend *ioend)
{
struct xfs_inode *ip = XFS_I(ioend->io_inode);
struct xfs_trans *tp = ioend->io_append_trans;
xfs_fsize_t isize;
/*
* The transaction may have been allocated in the I/O submission thread,
* thus we need to mark ourselves as beeing in a transaction manually.
* Similarly for freeze protection.
*/
current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
rwsem_acquire_read(&VFS_I(ip)->i_sb->s_writers.lock_map[SB_FREEZE_FS-1],
0, 1, _THIS_IP_);
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, ioend->io_offset + ioend->io_size);
if (!isize) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_trans_cancel(tp, 0);
return 0;
}
trace_xfs_setfilesize(ip, ioend->io_offset, ioend->io_size);
ip->i_d.di_size = isize;
xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL);
xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
return xfs_trans_commit(tp, 0);
}
/*
* Schedule IO completion handling on the final put of an ioend.
*
* If there is no work to do we might as well call it a day and free the
* ioend right now.
*/
STATIC void
xfs_finish_ioend(
struct xfs_ioend *ioend)
{
if (atomic_dec_and_test(&ioend->io_remaining)) {
struct xfs_mount *mp = XFS_I(ioend->io_inode)->i_mount;
if (ioend->io_type == XFS_IO_UNWRITTEN)
queue_work(mp->m_unwritten_workqueue, &ioend->io_work);
else if (ioend->io_append_trans ||
(ioend->io_isdirect && xfs_ioend_is_append(ioend)))
queue_work(mp->m_data_workqueue, &ioend->io_work);
else
xfs_destroy_ioend(ioend);
}
}
/*
* IO write completion.
*/
STATIC void
xfs_end_io(
struct work_struct *work)
{
xfs_ioend_t *ioend = container_of(work, xfs_ioend_t, io_work);
struct xfs_inode *ip = XFS_I(ioend->io_inode);
int error = 0;
if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
ioend->io_error = -EIO;
goto done;
}
if (ioend->io_error)
goto done;
/*
* For unwritten extents we need to issue transactions to convert a
* range to normal written extens after the data I/O has finished.
*/
if (ioend->io_type == XFS_IO_UNWRITTEN) {
error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
ioend->io_size);
} else if (ioend->io_isdirect && xfs_ioend_is_append(ioend)) {
/*
* For direct I/O we do not know if we need to allocate blocks
* or not so we can't preallocate an append transaction as that
* results in nested reservations and log space deadlocks. Hence
* allocate the transaction here. While this is sub-optimal and
* can block IO completion for some time, we're stuck with doing
* it this way until we can pass the ioend to the direct IO
* allocation callbacks and avoid nesting that way.
*/
error = xfs_setfilesize_trans_alloc(ioend);
if (error)
goto done;
error = xfs_setfilesize(ioend);
} else if (ioend->io_append_trans) {
error = xfs_setfilesize(ioend);
} else {
ASSERT(!xfs_ioend_is_append(ioend));
}
done:
if (error)
ioend->io_error = error;
xfs_destroy_ioend(ioend);
}
/*
* Call IO completion handling in caller context on the final put of an ioend.
*/
STATIC void
xfs_finish_ioend_sync(
struct xfs_ioend *ioend)
{
if (atomic_dec_and_test(&ioend->io_remaining))
xfs_end_io(&ioend->io_work);
}
/*
* Allocate and initialise an IO completion structure.
* We need to track unwritten extent write completion here initially.
* We'll need to extend this for updating the ondisk inode size later
* (vs. incore size).
*/
STATIC xfs_ioend_t *
xfs_alloc_ioend(
struct inode *inode,
unsigned int type)
{
xfs_ioend_t *ioend;
ioend = mempool_alloc(xfs_ioend_pool, GFP_NOFS);
/*
* Set the count to 1 initially, which will prevent an I/O
* completion callback from happening before we have started
* all the I/O from calling the completion routine too early.
*/
atomic_set(&ioend->io_remaining, 1);
ioend->io_isdirect = 0;
ioend->io_error = 0;
ioend->io_list = NULL;
ioend->io_type = type;
ioend->io_inode = inode;
ioend->io_buffer_head = NULL;
ioend->io_buffer_tail = NULL;
ioend->io_offset = 0;
ioend->io_size = 0;
ioend->io_append_trans = NULL;
INIT_WORK(&ioend->io_work, xfs_end_io);
return ioend;
}
STATIC int
xfs_map_blocks(
struct inode *inode,
loff_t offset,
struct xfs_bmbt_irec *imap,
int type,
int nonblocking)
{
struct xfs_inode *ip = XFS_I(inode);
struct xfs_mount *mp = ip->i_mount;
ssize_t count = 1 << inode->i_blkbits;
xfs_fileoff_t offset_fsb, end_fsb;
int error = 0;
int bmapi_flags = XFS_BMAPI_ENTIRE;
int nimaps = 1;
if (XFS_FORCED_SHUTDOWN(mp))
return -EIO;
if (type == XFS_IO_UNWRITTEN)
bmapi_flags |= XFS_BMAPI_IGSTATE;
if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
if (nonblocking)
return -EAGAIN;
xfs_ilock(ip, XFS_ILOCK_SHARED);
}
ASSERT(ip->i_d.di_format != XFS_DINODE_FMT_BTREE ||
(ip->i_df.if_flags & XFS_IFEXTENTS));
ASSERT(offset <= mp->m_super->s_maxbytes);
if (offset + count > mp->m_super->s_maxbytes)
count = mp->m_super->s_maxbytes - offset;
end_fsb = XFS_B_TO_FSB(mp, (xfs_ufsize_t)offset + count);
offset_fsb = XFS_B_TO_FSBT(mp, offset);
error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb,
imap, &nimaps, bmapi_flags);
xfs_iunlock(ip, XFS_ILOCK_SHARED);
if (error)
return error;
if (type == XFS_IO_DELALLOC &&
(!nimaps || isnullstartblock(imap->br_startblock))) {
error = xfs_iomap_write_allocate(ip, offset, imap);
if (!error)
trace_xfs_map_blocks_alloc(ip, offset, count, type, imap);
return error;
}
#ifdef DEBUG
if (type == XFS_IO_UNWRITTEN) {
ASSERT(nimaps);
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
}
#endif
if (nimaps)
trace_xfs_map_blocks_found(ip, offset, count, type, imap);
return 0;
}
STATIC int
xfs_imap_valid(
struct inode *inode,
struct xfs_bmbt_irec *imap,
xfs_off_t offset)
{
offset >>= inode->i_blkbits;
return offset >= imap->br_startoff &&
offset < imap->br_startoff + imap->br_blockcount;
}
/*
* BIO completion handler for buffered IO.
*/
STATIC void
xfs_end_bio(
struct bio *bio,
int error)
{
xfs_ioend_t *ioend = bio->bi_private;
ASSERT(atomic_read(&bio->bi_cnt) >= 1);
ioend->io_error = test_bit(BIO_UPTODATE, &bio->bi_flags) ? 0 : error;
/* Toss bio and pass work off to an xfsdatad thread */
bio->bi_private = NULL;
bio->bi_end_io = NULL;
bio_put(bio);
xfs_finish_ioend(ioend);
}
STATIC void
xfs_submit_ioend_bio(
struct writeback_control *wbc,
xfs_ioend_t *ioend,
struct bio *bio)
{
atomic_inc(&ioend->io_remaining);
bio->bi_private = ioend;
bio->bi_end_io = xfs_end_bio;
submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE, bio);
}
STATIC struct bio *
xfs_alloc_ioend_bio(
struct buffer_head *bh)
{
int nvecs = bio_get_nr_vecs(bh->b_bdev);
struct bio *bio = bio_alloc(GFP_NOIO, nvecs);
ASSERT(bio->bi_private == NULL);
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
return bio;
}
STATIC void
xfs_start_buffer_writeback(
struct buffer_head *bh)
{
ASSERT(buffer_mapped(bh));
ASSERT(buffer_locked(bh));
ASSERT(!buffer_delay(bh));
ASSERT(!buffer_unwritten(bh));
mark_buffer_async_write(bh);
set_buffer_uptodate(bh);
clear_buffer_dirty(bh);
}
STATIC void
xfs_start_page_writeback(
struct page *page,
int clear_dirty,
int buffers)
{
ASSERT(PageLocked(page));
ASSERT(!PageWriteback(page));
/*
* if the page was not fully cleaned, we need to ensure that the higher
* layers come back to it correctly. That means we need to keep the page
* dirty, and for WB_SYNC_ALL writeback we need to ensure the
* PAGECACHE_TAG_TOWRITE index mark is not removed so another attempt to
* write this page in this writeback sweep will be made.
*/
if (clear_dirty) {
clear_page_dirty_for_io(page);
set_page_writeback(page);
} else
set_page_writeback_keepwrite(page);
unlock_page(page);
/* If no buffers on the page are to be written, finish it here */
if (!buffers)
end_page_writeback(page);
}
static inline int xfs_bio_add_buffer(struct bio *bio, struct buffer_head *bh)
{
return bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
}
/*
* Submit all of the bios for all of the ioends we have saved up, covering the
* initial writepage page and also any probed pages.
*
* Because we may have multiple ioends spanning a page, we need to start
* writeback on all the buffers before we submit them for I/O. If we mark the
* buffers as we got, then we can end up with a page that only has buffers
* marked async write and I/O complete on can occur before we mark the other
* buffers async write.
*
* The end result of this is that we trip a bug in end_page_writeback() because
* we call it twice for the one page as the code in end_buffer_async_write()
* assumes that all buffers on the page are started at the same time.
*
* The fix is two passes across the ioend list - one to start writeback on the
* buffer_heads, and then submit them for I/O on the second pass.
*
* If @fail is non-zero, it means that we have a situation where some part of
* the submission process has failed after we have marked paged for writeback
* and unlocked them. In this situation, we need to fail the ioend chain rather
* than submit it to IO. This typically only happens on a filesystem shutdown.
*/
STATIC void
xfs_submit_ioend(
struct writeback_control *wbc,
xfs_ioend_t *ioend,
int fail)
{
xfs_ioend_t *head = ioend;
xfs_ioend_t *next;
struct buffer_head *bh;
struct bio *bio;
sector_t lastblock = 0;
/* Pass 1 - start writeback */
do {
next = ioend->io_list;
for (bh = ioend->io_buffer_head; bh; bh = bh->b_private)
xfs_start_buffer_writeback(bh);
} while ((ioend = next) != NULL);
/* Pass 2 - submit I/O */
ioend = head;
do {
next = ioend->io_list;
bio = NULL;
/*
* If we are failing the IO now, just mark the ioend with an
* error and finish it. This will run IO completion immediately
* as there is only one reference to the ioend at this point in
* time.
*/
if (fail) {
ioend->io_error = fail;
xfs_finish_ioend(ioend);
continue;
}
for (bh = ioend->io_buffer_head; bh; bh = bh->b_private) {
if (!bio) {
retry:
bio = xfs_alloc_ioend_bio(bh);
} else if (bh->b_blocknr != lastblock + 1) {
xfs_submit_ioend_bio(wbc, ioend, bio);
goto retry;
}
if (xfs_bio_add_buffer(bio, bh) != bh->b_size) {
xfs_submit_ioend_bio(wbc, ioend, bio);
goto retry;
}
lastblock = bh->b_blocknr;
}
if (bio)
xfs_submit_ioend_bio(wbc, ioend, bio);
xfs_finish_ioend(ioend);
} while ((ioend = next) != NULL);
}
/*
* Cancel submission of all buffer_heads so far in this endio.
* Toss the endio too. Only ever called for the initial page
* in a writepage request, so only ever one page.
*/
STATIC void
xfs_cancel_ioend(
xfs_ioend_t *ioend)
{
xfs_ioend_t *next;
struct buffer_head *bh, *next_bh;
do {
next = ioend->io_list;
bh = ioend->io_buffer_head;
do {
next_bh = bh->b_private;
clear_buffer_async_write(bh);
/*
* The unwritten flag is cleared when added to the
* ioend. We're not submitting for I/O so mark the
* buffer unwritten again for next time around.
*/
if (ioend->io_type == XFS_IO_UNWRITTEN)
set_buffer_unwritten(bh);
unlock_buffer(bh);
} while ((bh = next_bh) != NULL);
mempool_free(ioend, xfs_ioend_pool);
} while ((ioend = next) != NULL);
}
/*
* Test to see if we've been building up a completion structure for
* earlier buffers -- if so, we try to append to this ioend if we
* can, otherwise we finish off any current ioend and start another.
* Return true if we've finished the given ioend.
*/
STATIC void
xfs_add_to_ioend(
struct inode *inode,
struct buffer_head *bh,
xfs_off_t offset,
unsigned int type,
xfs_ioend_t **result,
int need_ioend)
{
xfs_ioend_t *ioend = *result;
if (!ioend || need_ioend || type != ioend->io_type) {
xfs_ioend_t *previous = *result;
ioend = xfs_alloc_ioend(inode, type);
ioend->io_offset = offset;
ioend->io_buffer_head = bh;
ioend->io_buffer_tail = bh;
if (previous)
previous->io_list = ioend;
*result = ioend;
} else {
ioend->io_buffer_tail->b_private = bh;
ioend->io_buffer_tail = bh;
}
bh->b_private = NULL;
ioend->io_size += bh->b_size;
}
STATIC void
xfs_map_buffer(
struct inode *inode,
struct buffer_head *bh,
struct xfs_bmbt_irec *imap,
xfs_off_t offset)
{
sector_t bn;
struct xfs_mount *m = XFS_I(inode)->i_mount;
xfs_off_t iomap_offset = XFS_FSB_TO_B(m, imap->br_startoff);
xfs_daddr_t iomap_bn = xfs_fsb_to_db(XFS_I(inode), imap->br_startblock);
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
bn = (iomap_bn >> (inode->i_blkbits - BBSHIFT)) +
((offset - iomap_offset) >> inode->i_blkbits);
ASSERT(bn || XFS_IS_REALTIME_INODE(XFS_I(inode)));
bh->b_blocknr = bn;
set_buffer_mapped(bh);
}
STATIC void
xfs_map_at_offset(
struct inode *inode,
struct buffer_head *bh,
struct xfs_bmbt_irec *imap,
xfs_off_t offset)
{
ASSERT(imap->br_startblock != HOLESTARTBLOCK);
ASSERT(imap->br_startblock != DELAYSTARTBLOCK);
xfs_map_buffer(inode, bh, imap, offset);
set_buffer_mapped(bh);
clear_buffer_delay(bh);
clear_buffer_unwritten(bh);
}
/*
* Test if a given page contains at least one buffer of a given @type.
* If @check_all_buffers is true, then we walk all the buffers in the page to
* try to find one of the type passed in. If it is not set, then the caller only
* needs to check the first buffer on the page for a match.
*/
STATIC bool
xfs_check_page_type(
struct page *page,
unsigned int type,
bool check_all_buffers)
{
struct buffer_head *bh;
struct buffer_head *head;
if (PageWriteback(page))
return false;
if (!page->mapping)
return false;
if (!page_has_buffers(page))
return false;
bh = head = page_buffers(page);
do {
if (buffer_unwritten(bh)) {
if (type == XFS_IO_UNWRITTEN)
return true;
} else if (buffer_delay(bh)) {
if (type == XFS_IO_DELALLOC)
return true;
} else if (buffer_dirty(bh) && buffer_mapped(bh)) {
if (type == XFS_IO_OVERWRITE)
return true;
}
/* If we are only checking the first buffer, we are done now. */
if (!check_all_buffers)
break;
} while ((bh = bh->b_this_page) != head);
return false;
}
/*
* Allocate & map buffers for page given the extent map. Write it out.
* except for the original page of a writepage, this is called on
* delalloc/unwritten pages only, for the original page it is possible
* that the page has no mapping at all.
*/
STATIC int
xfs_convert_page(
struct inode *inode,
struct page *page,
loff_t tindex,
struct xfs_bmbt_irec *imap,
xfs_ioend_t **ioendp,
struct writeback_control *wbc)
{
struct buffer_head *bh, *head;
xfs_off_t end_offset;
unsigned long p_offset;
unsigned int type;
int len, page_dirty;
int count = 0, done = 0, uptodate = 1;
xfs_off_t offset = page_offset(page);
if (page->index != tindex)
goto fail;
if (!trylock_page(page))
goto fail;
if (PageWriteback(page))
goto fail_unlock_page;
if (page->mapping != inode->i_mapping)
goto fail_unlock_page;
if (!xfs_check_page_type(page, (*ioendp)->io_type, false))
goto fail_unlock_page;
/*
* page_dirty is initially a count of buffers on the page before
* EOF and is decremented as we move each into a cleanable state.
*
* Derivation:
*
* End offset is the highest offset that this page should represent.
* If we are on the last page, (end_offset & (PAGE_CACHE_SIZE - 1))
* will evaluate non-zero and be less than PAGE_CACHE_SIZE and
* hence give us the correct page_dirty count. On any other page,
* it will be zero and in that case we need page_dirty to be the
* count of buffers on the page.
*/
end_offset = min_t(unsigned long long,
(xfs_off_t)(page->index + 1) << PAGE_CACHE_SHIFT,
i_size_read(inode));
/*
* If the current map does not span the entire page we are about to try
* to write, then give up. The only way we can write a page that spans
* multiple mappings in a single writeback iteration is via the
* xfs_vm_writepage() function. Data integrity writeback requires the
* entire page to be written in a single attempt, otherwise the part of
* the page we don't write here doesn't get written as part of the data
* integrity sync.
*
* For normal writeback, we also don't attempt to write partial pages
* here as it simply means that write_cache_pages() will see it under
* writeback and ignore the page until some point in the future, at
* which time this will be the only page in the file that needs
* writeback. Hence for more optimal IO patterns, we should always
* avoid partial page writeback due to multiple mappings on a page here.
*/
if (!xfs_imap_valid(inode, imap, end_offset))
goto fail_unlock_page;
len = 1 << inode->i_blkbits;
p_offset = min_t(unsigned long, end_offset & (PAGE_CACHE_SIZE - 1),
PAGE_CACHE_SIZE);
p_offset = p_offset ? roundup(p_offset, len) : PAGE_CACHE_SIZE;
page_dirty = p_offset / len;
/*
* The moment we find a buffer that doesn't match our current type
* specification or can't be written, abort the loop and start
* writeback. As per the above xfs_imap_valid() check, only
* xfs_vm_writepage() can handle partial page writeback fully - we are
* limited here to the buffers that are contiguous with the current
* ioend, and hence a buffer we can't write breaks that contiguity and
* we have to defer the rest of the IO to xfs_vm_writepage().
*/
bh = head = page_buffers(page);
do {
if (offset >= end_offset)
break;
if (!buffer_uptodate(bh))
uptodate = 0;
if (!(PageUptodate(page) || buffer_uptodate(bh))) {
done = 1;
break;
}
if (buffer_unwritten(bh) || buffer_delay(bh) ||
buffer_mapped(bh)) {
if (buffer_unwritten(bh))
type = XFS_IO_UNWRITTEN;
else if (buffer_delay(bh))
type = XFS_IO_DELALLOC;
else
type = XFS_IO_OVERWRITE;
/*
* imap should always be valid because of the above
* partial page end_offset check on the imap.
*/
ASSERT(xfs_imap_valid(inode, imap, offset));
lock_buffer(bh);
if (type != XFS_IO_OVERWRITE)
xfs_map_at_offset(inode, bh, imap, offset);
xfs_add_to_ioend(inode, bh, offset, type,
ioendp, done);
page_dirty--;
count++;
} else {
done = 1;
break;
}
} while (offset += len, (bh = bh->b_this_page) != head);
if (uptodate && bh == head)
SetPageUptodate(page);
if (count) {
if (--wbc->nr_to_write <= 0 &&
wbc->sync_mode == WB_SYNC_NONE)
done = 1;
}
xfs_start_page_writeback(page, !page_dirty, count);
return done;
fail_unlock_page:
unlock_page(page);
fail:
return 1;
}
/*
* Convert & write out a cluster of pages in the same extent as defined
* by mp and following the start page.
*/
STATIC void
xfs_cluster_write(
struct inode *inode,
pgoff_t tindex,
struct xfs_bmbt_irec *imap,
xfs_ioend_t **ioendp,
struct writeback_control *wbc,
pgoff_t tlast)
{
struct pagevec pvec;
int done = 0, i;
pagevec_init(&pvec, 0);
while (!done && tindex <= tlast) {
unsigned len = min_t(pgoff_t, PAGEVEC_SIZE, tlast - tindex + 1);
if (!pagevec_lookup(&pvec, inode->i_mapping, tindex, len))
break;
for (i = 0; i < pagevec_count(&pvec); i++) {
done = xfs_convert_page(inode, pvec.pages[i], tindex++,
imap, ioendp, wbc);
if (done)
break;
}
pagevec_release(&pvec);
cond_resched();
}
}
STATIC void
xfs_vm_invalidatepage(
struct page *page,
unsigned int offset,
unsigned int length)
{
trace_xfs_invalidatepage(page->mapping->host, page, offset,
length);
block_invalidatepage(page, offset, length);
}
/*
* If the page has delalloc buffers on it, we need to punch them out before we
* invalidate the page. If we don't, we leave a stale delalloc mapping on the
* inode that can trip a BUG() in xfs_get_blocks() later on if a direct IO read
* is done on that same region - the delalloc extent is returned when none is
* supposed to be there.
*
* We prevent this by truncating away the delalloc regions on the page before
* invalidating it. Because they are delalloc, we can do this without needing a
* transaction. Indeed - if we get ENOSPC errors, we have to be able to do this
* truncation without a transaction as there is no space left for block
* reservation (typically why we see a ENOSPC in writeback).
*
* This is not a performance critical path, so for now just do the punching a
* buffer head at a time.
*/
STATIC void
xfs_aops_discard_page(
struct page *page)
{
struct inode *inode = page->mapping->host;
struct xfs_inode *ip = XFS_I(inode);
struct buffer_head *bh, *head;
loff_t offset = page_offset(page);
if (!xfs_check_page_type(page, XFS_IO_DELALLOC, true))
goto out_invalidate;
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
goto out_invalidate;
xfs_alert(ip->i_mount,
"page discard on page %p, inode 0x%llx, offset %llu.",
page, ip->i_ino, offset);
xfs_ilock(ip, XFS_ILOCK_EXCL);
bh = head = page_buffers(page);
do {
int error;
xfs_fileoff_t start_fsb;
if (!buffer_delay(bh))
goto next_buffer;
start_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
error = xfs_bmap_punch_delalloc_range(ip, start_fsb, 1);
if (error) {
/* something screwed, just bail */
if (!XFS_FORCED_SHUTDOWN(ip->i_mount)) {
xfs_alert(ip->i_mount,
"page discard unable to remove delalloc mapping.");
}
break;
}
next_buffer:
offset += 1 << inode->i_blkbits;
} while ((bh = bh->b_this_page) != head);
xfs_iunlock(ip, XFS_ILOCK_EXCL);
out_invalidate:
xfs_vm_invalidatepage(page, 0, PAGE_CACHE_SIZE);
return;
}
/*
* Write out a dirty page.
*
* For delalloc space on the page we need to allocate space and flush it.
* For unwritten space on the page we need to start the conversion to
* regular allocated space.
* For any other dirty buffer heads on the page we should flush them.
*/
STATIC int
xfs_vm_writepage(
struct page *page,
struct writeback_control *wbc)
{
struct inode *inode = page->mapping->host;
struct buffer_head *bh, *head;
struct xfs_bmbt_irec imap;
xfs_ioend_t *ioend = NULL, *iohead = NULL;
loff_t offset;
unsigned int type;
__uint64_t end_offset;
pgoff_t end_index, last_index;
ssize_t len;
int err, imap_valid = 0, uptodate = 1;
int count = 0;
int nonblocking = 0;
trace_xfs_writepage(inode, page, 0, 0);
ASSERT(page_has_buffers(page));
/*
* Refuse to write the page out if we are called from reclaim context.
*
* This avoids stack overflows when called from deeply used stacks in
* random callers for direct reclaim or memcg reclaim. We explicitly
* allow reclaim from kswapd as the stack usage there is relatively low.
*
* This should never happen except in the case of a VM regression so
* warn about it.
*/
if (WARN_ON_ONCE((current->flags & (PF_MEMALLOC|PF_KSWAPD)) ==
PF_MEMALLOC))
goto redirty;
/*
* Given that we do not allow direct reclaim to call us, we should
* never be called while in a filesystem transaction.
*/
if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
goto redirty;
/* Is this page beyond the end of the file? */
offset = i_size_read(inode);
end_index = offset >> PAGE_CACHE_SHIFT;
last_index = (offset - 1) >> PAGE_CACHE_SHIFT;