forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
xfs_aops.c
1757 lines (1553 loc) · 47.6 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/gfp.h>
#include <linux/mpage.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
/* flags for direct write completions */
#define XFS_DIO_FLAG_UNWRITTEN (1 << 0)
#define XFS_DIO_FLAG_APPEND (1 << 1)
/*
* structure owned by writepages passed to individual writepage calls
*/
struct xfs_writepage_ctx {
struct xfs_bmbt_irec imap;
bool imap_valid;
unsigned int io_type;
struct xfs_ioend *ioend;
sector_t last_block;
};
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);
}
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 page. Update the page state via the
* associated buffer_heads, paying attention to the start and end offsets that
* we need to process on the page.
*/
static void
xfs_finish_page_writeback(
struct inode *inode,
struct bio_vec *bvec,
int error)
{
unsigned int end = bvec->bv_offset + bvec->bv_len - 1;
struct buffer_head *head, *bh;
unsigned int off = 0;
ASSERT(bvec->bv_offset < PAGE_SIZE);
ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
ASSERT(end < PAGE_SIZE);
ASSERT((bvec->bv_len & ((1 << inode->i_blkbits) - 1)) == 0);
bh = head = page_buffers(bvec->bv_page);
do {
if (off < bvec->bv_offset)
goto next_bh;
if (off > end)
break;
bh->b_end_io(bh, !error);
next_bh:
off += bh->b_size;
} while ((bh = bh->b_this_page) != head);
}
/*
* We're now finished for good with this ioend structure. Update the page
* state, release holds on bios, and finally free up memory. Do not use the
* ioend after this.
*/
STATIC void
xfs_destroy_ioend(
struct xfs_ioend *ioend,
int error)
{
struct inode *inode = ioend->io_inode;
struct bio *last = ioend->io_bio;
struct bio *bio, *next;
for (bio = &ioend->io_inline_bio; bio; bio = next) {
struct bio_vec *bvec;
int i;
/*
* For the last bio, bi_private points to the ioend, so we
* need to explicitly end the iteration here.
*/
if (bio == last)
next = NULL;
else
next = bio->bi_private;
/* walk each page on bio, ending page IO on them */
bio_for_each_segment_all(bvec, bio, i)
xfs_finish_page_writeback(inode, bvec, error);
bio_put(bio);
}
}
/*
* 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;
error = xfs_trans_alloc(mp, &M_RES(mp)->tr_fsyncts, 0, 0, 0, &tp);
if (error)
return error;
ioend->io_append_trans = tp;
/*
* We may pass freeze protection with a transaction. So tell lockdep
* we released it.
*/
__sb_writers_release(ioend->io_inode->i_sb, SB_FREEZE_FS);
/*
* 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_inode *ip,
struct xfs_trans *tp,
xfs_off_t offset,
size_t size)
{
xfs_fsize_t isize;
xfs_ilock(ip, XFS_ILOCK_EXCL);
isize = xfs_new_eof(ip, offset + size);
if (!isize) {
xfs_iunlock(ip, XFS_ILOCK_EXCL);
xfs_trans_cancel(tp);
return 0;
}
trace_xfs_setfilesize(ip, offset, 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);
}
STATIC int
xfs_setfilesize_ioend(
struct xfs_ioend *ioend,
int error)
{
struct xfs_inode *ip = XFS_I(ioend->io_inode);
struct xfs_trans *tp = ioend->io_append_trans;
/*
* The transaction may have been allocated in the I/O submission thread,
* thus we need to mark ourselves as being in a transaction manually.
* Similarly for freeze protection.
*/
current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
/* we abort the update if there was an IO error */
if (error) {
xfs_trans_cancel(tp);
return error;
}
return xfs_setfilesize(ip, tp, ioend->io_offset, ioend->io_size);
}
/*
* IO write completion.
*/
STATIC void
xfs_end_io(
struct work_struct *work)
{
struct xfs_ioend *ioend =
container_of(work, struct xfs_ioend, io_work);
struct xfs_inode *ip = XFS_I(ioend->io_inode);
int error = ioend->io_bio->bi_error;
/*
* Set an error if the mount has shut down and proceed with end I/O
* processing so it can perform whatever cleanups are necessary.
*/
if (XFS_FORCED_SHUTDOWN(ip->i_mount))
error = -EIO;
/*
* For unwritten extents we need to issue transactions to convert a
* range to normal written extens after the data I/O has finished.
* Detecting and handling completion IO errors is done individually
* for each case as different cleanup operations need to be performed
* on error.
*/
if (ioend->io_type == XFS_IO_UNWRITTEN) {
if (error)
goto done;
error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
ioend->io_size);
} else if (ioend->io_append_trans) {
error = xfs_setfilesize_ioend(ioend, error);
} else {
ASSERT(!xfs_ioend_is_append(ioend));
}
done:
xfs_destroy_ioend(ioend, error);
}
STATIC void
xfs_end_bio(
struct bio *bio)
{
struct xfs_ioend *ioend = bio->bi_private;
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)
queue_work(mp->m_data_workqueue, &ioend->io_work);
else
xfs_destroy_ioend(ioend, bio->bi_error);
}
STATIC int
xfs_map_blocks(
struct inode *inode,
loff_t offset,
struct xfs_bmbt_irec *imap,
int type)
{
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;
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 bool
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;
}
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)
{
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);
}
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 the bio for an ioend. We are passed an ioend with a bio attached to
* it, and we submit that bio. The ioend may be used for multiple bio
* submissions, so we only want to allocate an append transaction for the ioend
* once. In the case of multiple bio submission, each bio will take an IO
* reference to the ioend to ensure that the ioend completion is only done once
* all bios have been submitted and the ioend is really done.
*
* 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 bio and ioend
* rather than submit it to IO. This typically only happens on a filesystem
* shutdown.
*/
STATIC int
xfs_submit_ioend(
struct writeback_control *wbc,
struct xfs_ioend *ioend,
int status)
{
/* Reserve log space if we might write beyond the on-disk inode size. */
if (!status &&
ioend->io_type != XFS_IO_UNWRITTEN &&
xfs_ioend_is_append(ioend) &&
!ioend->io_append_trans)
status = xfs_setfilesize_trans_alloc(ioend);
ioend->io_bio->bi_private = ioend;
ioend->io_bio->bi_end_io = xfs_end_bio;
/*
* 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 (status) {
ioend->io_bio->bi_error = status;
bio_endio(ioend->io_bio);
return status;
}
submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
ioend->io_bio);
return 0;
}
static void
xfs_init_bio_from_bh(
struct bio *bio,
struct buffer_head *bh)
{
bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
bio->bi_bdev = bh->b_bdev;
}
static struct xfs_ioend *
xfs_alloc_ioend(
struct inode *inode,
unsigned int type,
xfs_off_t offset,
struct buffer_head *bh)
{
struct xfs_ioend *ioend;
struct bio *bio;
bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, xfs_ioend_bioset);
xfs_init_bio_from_bh(bio, bh);
ioend = container_of(bio, struct xfs_ioend, io_inline_bio);
INIT_LIST_HEAD(&ioend->io_list);
ioend->io_type = type;
ioend->io_inode = inode;
ioend->io_size = 0;
ioend->io_offset = offset;
INIT_WORK(&ioend->io_work, xfs_end_io);
ioend->io_append_trans = NULL;
ioend->io_bio = bio;
return ioend;
}
/*
* Allocate a new bio, and chain the old bio to the new one.
*
* Note that we have to do perform the chaining in this unintuitive order
* so that the bi_private linkage is set up in the right direction for the
* traversal in xfs_destroy_ioend().
*/
static void
xfs_chain_bio(
struct xfs_ioend *ioend,
struct writeback_control *wbc,
struct buffer_head *bh)
{
struct bio *new;
new = bio_alloc(GFP_NOFS, BIO_MAX_PAGES);
xfs_init_bio_from_bh(new, bh);
bio_chain(ioend->io_bio, new);
bio_get(ioend->io_bio); /* for xfs_destroy_ioend */
submit_bio(wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE,
ioend->io_bio);
ioend->io_bio = new;
}
/*
* 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 the ioend we finished off so that the caller can submit it
* once it has finished processing the dirty page.
*/
STATIC void
xfs_add_to_ioend(
struct inode *inode,
struct buffer_head *bh,
xfs_off_t offset,
struct xfs_writepage_ctx *wpc,
struct writeback_control *wbc,
struct list_head *iolist)
{
if (!wpc->ioend || wpc->io_type != wpc->ioend->io_type ||
bh->b_blocknr != wpc->last_block + 1 ||
offset != wpc->ioend->io_offset + wpc->ioend->io_size) {
if (wpc->ioend)
list_add(&wpc->ioend->io_list, iolist);
wpc->ioend = xfs_alloc_ioend(inode, wpc->io_type, offset, bh);
}
/*
* If the buffer doesn't fit into the bio we need to allocate a new
* one. This shouldn't happen more than once for a given buffer.
*/
while (xfs_bio_add_buffer(wpc->ioend->io_bio, bh) != bh->b_size)
xfs_chain_bio(wpc->ioend, wbc, bh);
wpc->ioend->io_size += bh->b_size;
wpc->last_block = bh->b_blocknr;
xfs_start_buffer_writeback(bh);
}
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;
}
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_SIZE);
return;
}
/*
* We implement an immediate ioend submission policy here to avoid needing to
* chain multiple ioends and hence nest mempool allocations which can violate
* forward progress guarantees we need to provide. The current ioend we are
* adding buffers to is cached on the writepage context, and if the new buffer
* does not append to the cached ioend it will create a new ioend and cache that
* instead.
*
* If a new ioend is created and cached, the old ioend is returned and queued
* locally for submission once the entire page is processed or an error has been
* detected. While ioends are submitted immediately after they are completed,
* batching optimisations are provided by higher level block plugging.
*
* At the end of a writeback pass, there will be a cached ioend remaining on the
* writepage context that the caller will need to submit.
*/
static int
xfs_writepage_map(
struct xfs_writepage_ctx *wpc,
struct writeback_control *wbc,
struct inode *inode,
struct page *page,
loff_t offset,
__uint64_t end_offset)
{
LIST_HEAD(submit_list);
struct xfs_ioend *ioend, *next;
struct buffer_head *bh, *head;
ssize_t len = 1 << inode->i_blkbits;
int error = 0;
int count = 0;
int uptodate = 1;
bh = head = page_buffers(page);
offset = page_offset(page);
do {
if (offset >= end_offset)
break;
if (!buffer_uptodate(bh))
uptodate = 0;
/*
* set_page_dirty dirties all buffers in a page, independent
* of their state. The dirty state however is entirely
* meaningless for holes (!mapped && uptodate), so skip
* buffers covering holes here.
*/
if (!buffer_mapped(bh) && buffer_uptodate(bh)) {
wpc->imap_valid = false;
continue;
}
if (buffer_unwritten(bh)) {
if (wpc->io_type != XFS_IO_UNWRITTEN) {
wpc->io_type = XFS_IO_UNWRITTEN;
wpc->imap_valid = false;
}
} else if (buffer_delay(bh)) {
if (wpc->io_type != XFS_IO_DELALLOC) {
wpc->io_type = XFS_IO_DELALLOC;
wpc->imap_valid = false;
}
} else if (buffer_uptodate(bh)) {
if (wpc->io_type != XFS_IO_OVERWRITE) {
wpc->io_type = XFS_IO_OVERWRITE;
wpc->imap_valid = false;
}
} else {
if (PageUptodate(page))
ASSERT(buffer_mapped(bh));
/*
* This buffer is not uptodate and will not be
* written to disk. Ensure that we will put any
* subsequent writeable buffers into a new
* ioend.
*/
wpc->imap_valid = false;
continue;
}
if (wpc->imap_valid)
wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
offset);
if (!wpc->imap_valid) {
error = xfs_map_blocks(inode, offset, &wpc->imap,
wpc->io_type);
if (error)
goto out;
wpc->imap_valid = xfs_imap_valid(inode, &wpc->imap,
offset);
}
if (wpc->imap_valid) {
lock_buffer(bh);
if (wpc->io_type != XFS_IO_OVERWRITE)
xfs_map_at_offset(inode, bh, &wpc->imap, offset);
xfs_add_to_ioend(inode, bh, offset, wpc, wbc, &submit_list);
count++;
}
} while (offset += len, ((bh = bh->b_this_page) != head));
if (uptodate && bh == head)
SetPageUptodate(page);
ASSERT(wpc->ioend || list_empty(&submit_list));
out:
/*
* On error, we have to fail the ioend here because we have locked
* buffers in the ioend. If we don't do this, we'll deadlock
* invalidating the page as that tries to lock the buffers on the page.
* Also, because we may have set pages under writeback, we have to make
* sure we run IO completion to mark the error state of the IO
* appropriately, so we can't cancel the ioend directly here. That means
* we have to mark this page as under writeback if we included any
* buffers from it in the ioend chain so that completion treats it
* correctly.
*
* If we didn't include the page in the ioend, the on error we can
* simply discard and unlock it as there are no other users of the page
* or it's buffers right now. The caller will still need to trigger
* submission of outstanding ioends on the writepage context so they are
* treated correctly on error.
*/
if (count) {
xfs_start_page_writeback(page, !error);
/*
* Preserve the original error if there was one, otherwise catch
* submission errors here and propagate into subsequent ioend
* submissions.
*/
list_for_each_entry_safe(ioend, next, &submit_list, io_list) {
int error2;
list_del_init(&ioend->io_list);
error2 = xfs_submit_ioend(wbc, ioend, error);
if (error2 && !error)
error = error2;
}
} else if (error) {
xfs_aops_discard_page(page);
ClearPageUptodate(page);
unlock_page(page);
} else {
/*
* We can end up here with no error and nothing to write if we
* race with a partial page truncate on a sub-page block sized
* filesystem. In that case we need to mark the page clean.
*/
xfs_start_page_writeback(page, 1);
end_page_writeback(page);
}
mapping_set_error(page->mapping, error);
return error;
}
/*
* 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_do_writepage(
struct page *page,
struct writeback_control *wbc,
void *data)
{
struct xfs_writepage_ctx *wpc = data;
struct inode *inode = page->mapping->host;
loff_t offset;
__uint64_t end_offset;
pgoff_t end_index;
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?
*
* The page index is less than the end_index, adjust the end_offset
* to the highest offset that this page should represent.
* -----------------------------------------------------
* | file mapping | <EOF> |
* -----------------------------------------------------
* | Page ... | Page N-2 | Page N-1 | Page N | |
* ^--------------------------------^----------|--------
* | desired writeback range | see else |
* ---------------------------------^------------------|
*/
offset = i_size_read(inode);
end_index = offset >> PAGE_SHIFT;
if (page->index < end_index)
end_offset = (xfs_off_t)(page->index + 1) << PAGE_SHIFT;
else {
/*
* Check whether the page to write out is beyond or straddles
* i_size or not.
* -------------------------------------------------------
* | file mapping | <EOF> |
* -------------------------------------------------------
* | Page ... | Page N-2 | Page N-1 | Page N | Beyond |
* ^--------------------------------^-----------|---------
* | | Straddles |
* ---------------------------------^-----------|--------|
*/
unsigned offset_into_page = offset & (PAGE_SIZE - 1);
/*
* Skip the page if it is fully outside i_size, e.g. due to a
* truncate operation that is in progress. We must redirty the
* page so that reclaim stops reclaiming it. Otherwise
* xfs_vm_releasepage() is called on it and gets confused.
*
* Note that the end_index is unsigned long, it would overflow
* if the given offset is greater than 16TB on 32-bit system
* and if we do check the page is fully outside i_size or not
* via "if (page->index >= end_index + 1)" as "end_index + 1"
* will be evaluated to 0. Hence this page will be redirtied
* and be written out repeatedly which would result in an
* infinite loop, the user program that perform this operation
* will hang. Instead, we can verify this situation by checking
* if the page to write is totally beyond the i_size or if it's
* offset is just equal to the EOF.
*/
if (page->index > end_index ||
(page->index == end_index && offset_into_page == 0))
goto redirty;
/*
* The page straddles i_size. It must be zeroed out on each
* and every writepage invocation because it may be mmapped.
* "A file is mapped in multiples of the page size. For a file
* that is not a multiple of the page size, the remaining
* memory is zeroed when mapped, and writes to that region are
* not written out to the file."
*/
zero_user_segment(page, offset_into_page, PAGE_SIZE);
/* Adjust the end_offset to the end of file */
end_offset = offset;
}
return xfs_writepage_map(wpc, wbc, inode, page, offset, end_offset);
redirty:
redirty_page_for_writepage(wbc, page);
unlock_page(page);
return 0;
}
STATIC int
xfs_vm_writepage(
struct page *page,
struct writeback_control *wbc)
{
struct xfs_writepage_ctx wpc = {
.io_type = XFS_IO_INVALID,
};
int ret;
ret = xfs_do_writepage(page, wbc, &wpc);