forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathwrite.c
1737 lines (1517 loc) · 43.7 KB
/
write.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
/*
* linux/fs/nfs/write.c
*
* Write file data over NFS.
*
* Copyright (C) 1996, 1997, Olaf Kirch <[email protected]>
*/
#include <linux/types.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/swap.h>
#include <linux/migrate.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/nfs_page.h>
#include <linux/backing-dev.h>
#include <asm/uaccess.h>
#include "delegation.h"
#include "internal.h"
#include "iostat.h"
#include "nfs4_fs.h"
#include "fscache.h"
#include "pnfs.h"
#define NFSDBG_FACILITY NFSDBG_PAGECACHE
#define MIN_POOL_WRITE (32)
#define MIN_POOL_COMMIT (4)
/*
* Local function declarations
*/
static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc,
struct inode *inode, int ioflags);
static void nfs_redirty_request(struct nfs_page *req);
static const struct rpc_call_ops nfs_write_partial_ops;
static const struct rpc_call_ops nfs_write_full_ops;
static const struct rpc_call_ops nfs_commit_ops;
static struct kmem_cache *nfs_wdata_cachep;
static mempool_t *nfs_wdata_mempool;
static mempool_t *nfs_commit_mempool;
struct nfs_write_data *nfs_commitdata_alloc(void)
{
struct nfs_write_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->pages);
}
return p;
}
EXPORT_SYMBOL_GPL(nfs_commitdata_alloc);
void nfs_commit_free(struct nfs_write_data *p)
{
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_commit_mempool);
}
EXPORT_SYMBOL_GPL(nfs_commit_free);
struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
{
struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
if (p) {
memset(p, 0, sizeof(*p));
INIT_LIST_HEAD(&p->pages);
p->npages = pagecount;
if (pagecount <= ARRAY_SIZE(p->page_array))
p->pagevec = p->page_array;
else {
p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS);
if (!p->pagevec) {
mempool_free(p, nfs_wdata_mempool);
p = NULL;
}
}
}
return p;
}
void nfs_writedata_free(struct nfs_write_data *p)
{
if (p && (p->pagevec != &p->page_array[0]))
kfree(p->pagevec);
mempool_free(p, nfs_wdata_mempool);
}
static void nfs_writedata_release(struct nfs_write_data *wdata)
{
put_lseg(wdata->lseg);
put_nfs_open_context(wdata->args.context);
nfs_writedata_free(wdata);
}
static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
{
ctx->error = error;
smp_wmb();
set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
}
static struct nfs_page *nfs_page_find_request_locked(struct page *page)
{
struct nfs_page *req = NULL;
if (PagePrivate(page)) {
req = (struct nfs_page *)page_private(page);
if (req != NULL)
kref_get(&req->wb_kref);
}
return req;
}
static struct nfs_page *nfs_page_find_request(struct page *page)
{
struct inode *inode = page->mapping->host;
struct nfs_page *req = NULL;
spin_lock(&inode->i_lock);
req = nfs_page_find_request_locked(page);
spin_unlock(&inode->i_lock);
return req;
}
/* Adjust the file length if we're writing beyond the end */
static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
{
struct inode *inode = page->mapping->host;
loff_t end, i_size;
pgoff_t end_index;
spin_lock(&inode->i_lock);
i_size = i_size_read(inode);
end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
if (i_size > 0 && page->index < end_index)
goto out;
end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
if (i_size >= end)
goto out;
i_size_write(inode, end);
nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
out:
spin_unlock(&inode->i_lock);
}
/* A writeback failed: mark the page as bad, and invalidate the page cache */
static void nfs_set_pageerror(struct page *page)
{
SetPageError(page);
nfs_zap_mapping(page->mapping->host, page->mapping);
}
/* We can set the PG_uptodate flag if we see that a write request
* covers the full page.
*/
static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int count)
{
if (PageUptodate(page))
return;
if (base != 0)
return;
if (count != nfs_page_length(page))
return;
SetPageUptodate(page);
}
static int wb_priority(struct writeback_control *wbc)
{
if (wbc->for_reclaim)
return FLUSH_HIGHPRI | FLUSH_STABLE;
if (wbc->for_kupdate || wbc->for_background)
return FLUSH_LOWPRI | FLUSH_COND_STABLE;
return FLUSH_COND_STABLE;
}
/*
* NFS congestion control
*/
int nfs_congestion_kb;
#define NFS_CONGESTION_ON_THRESH (nfs_congestion_kb >> (PAGE_SHIFT-10))
#define NFS_CONGESTION_OFF_THRESH \
(NFS_CONGESTION_ON_THRESH - (NFS_CONGESTION_ON_THRESH >> 2))
static int nfs_set_page_writeback(struct page *page)
{
int ret = test_set_page_writeback(page);
if (!ret) {
struct inode *inode = page->mapping->host;
struct nfs_server *nfss = NFS_SERVER(inode);
page_cache_get(page);
if (atomic_long_inc_return(&nfss->writeback) >
NFS_CONGESTION_ON_THRESH) {
set_bdi_congested(&nfss->backing_dev_info,
BLK_RW_ASYNC);
}
}
return ret;
}
static void nfs_end_page_writeback(struct page *page)
{
struct inode *inode = page->mapping->host;
struct nfs_server *nfss = NFS_SERVER(inode);
end_page_writeback(page);
page_cache_release(page);
if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
}
static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock)
{
struct inode *inode = page->mapping->host;
struct nfs_page *req;
int ret;
spin_lock(&inode->i_lock);
for (;;) {
req = nfs_page_find_request_locked(page);
if (req == NULL)
break;
if (nfs_set_page_tag_locked(req))
break;
/* Note: If we hold the page lock, as is the case in nfs_writepage,
* then the call to nfs_set_page_tag_locked() will always
* succeed provided that someone hasn't already marked the
* request as dirty (in which case we don't care).
*/
spin_unlock(&inode->i_lock);
if (!nonblock)
ret = nfs_wait_on_request(req);
else
ret = -EAGAIN;
nfs_release_request(req);
if (ret != 0)
return ERR_PTR(ret);
spin_lock(&inode->i_lock);
}
spin_unlock(&inode->i_lock);
return req;
}
/*
* Find an associated nfs write request, and prepare to flush it out
* May return an error if the user signalled nfs_wait_on_request().
*/
static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
struct page *page, bool nonblock)
{
struct nfs_page *req;
int ret = 0;
req = nfs_find_and_lock_request(page, nonblock);
if (!req)
goto out;
ret = PTR_ERR(req);
if (IS_ERR(req))
goto out;
ret = nfs_set_page_writeback(page);
BUG_ON(ret != 0);
BUG_ON(test_bit(PG_CLEAN, &req->wb_flags));
if (!nfs_pageio_add_request(pgio, req)) {
nfs_redirty_request(req);
ret = pgio->pg_error;
}
out:
return ret;
}
static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
{
struct inode *inode = page->mapping->host;
int ret;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
nfs_pageio_cond_complete(pgio, page->index);
ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
if (ret == -EAGAIN) {
redirty_page_for_writepage(wbc, page);
ret = 0;
}
return ret;
}
/*
* Write an mmapped page to the server.
*/
static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc)
{
struct nfs_pageio_descriptor pgio;
int err;
nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc));
err = nfs_do_writepage(page, wbc, &pgio);
nfs_pageio_complete(&pgio);
if (err < 0)
return err;
if (pgio.pg_error < 0)
return pgio.pg_error;
return 0;
}
int nfs_writepage(struct page *page, struct writeback_control *wbc)
{
int ret;
ret = nfs_writepage_locked(page, wbc);
unlock_page(page);
return ret;
}
static int nfs_writepages_callback(struct page *page, struct writeback_control *wbc, void *data)
{
int ret;
ret = nfs_do_writepage(page, wbc, data);
unlock_page(page);
return ret;
}
int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
{
struct inode *inode = mapping->host;
unsigned long *bitlock = &NFS_I(inode)->flags;
struct nfs_pageio_descriptor pgio;
int err;
/* Stop dirtying of new pages while we sync */
err = wait_on_bit_lock(bitlock, NFS_INO_FLUSHING,
nfs_wait_bit_killable, TASK_KILLABLE);
if (err)
goto out_err;
nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
nfs_pageio_init_write(&pgio, inode, wb_priority(wbc));
err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
nfs_pageio_complete(&pgio);
clear_bit_unlock(NFS_INO_FLUSHING, bitlock);
smp_mb__after_clear_bit();
wake_up_bit(bitlock, NFS_INO_FLUSHING);
if (err < 0)
goto out_err;
err = pgio.pg_error;
if (err < 0)
goto out_err;
return 0;
out_err:
return err;
}
/*
* Insert a write request into an inode
*/
static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
{
struct nfs_inode *nfsi = NFS_I(inode);
int error;
error = radix_tree_preload(GFP_NOFS);
if (error != 0)
goto out;
/* Lock the request! */
nfs_lock_request_dontget(req);
spin_lock(&inode->i_lock);
error = radix_tree_insert(&nfsi->nfs_page_tree, req->wb_index, req);
BUG_ON(error);
if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE))
nfsi->change_attr++;
set_bit(PG_MAPPED, &req->wb_flags);
SetPagePrivate(req->wb_page);
set_page_private(req->wb_page, (unsigned long)req);
nfsi->npages++;
kref_get(&req->wb_kref);
radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index,
NFS_PAGE_TAG_LOCKED);
spin_unlock(&inode->i_lock);
radix_tree_preload_end();
out:
return error;
}
/*
* Remove a write request from an inode
*/
static void nfs_inode_remove_request(struct nfs_page *req)
{
struct inode *inode = req->wb_context->path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
BUG_ON (!NFS_WBACK_BUSY(req));
spin_lock(&inode->i_lock);
set_page_private(req->wb_page, 0);
ClearPagePrivate(req->wb_page);
clear_bit(PG_MAPPED, &req->wb_flags);
radix_tree_delete(&nfsi->nfs_page_tree, req->wb_index);
nfsi->npages--;
spin_unlock(&inode->i_lock);
nfs_release_request(req);
}
static void
nfs_mark_request_dirty(struct nfs_page *req)
{
__set_page_dirty_nobuffers(req->wb_page);
__mark_inode_dirty(req->wb_page->mapping->host, I_DIRTY_DATASYNC);
}
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
/*
* Add a request to the inode's commit list.
*/
static void
nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
{
struct inode *inode = req->wb_context->path.dentry->d_inode;
struct nfs_inode *nfsi = NFS_I(inode);
spin_lock(&inode->i_lock);
set_bit(PG_CLEAN, &(req)->wb_flags);
radix_tree_tag_set(&nfsi->nfs_page_tree,
req->wb_index,
NFS_PAGE_TAG_COMMIT);
nfsi->ncommit++;
spin_unlock(&inode->i_lock);
pnfs_mark_request_commit(req, lseg);
inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
inc_bdi_stat(req->wb_page->mapping->backing_dev_info, BDI_RECLAIMABLE);
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
}
static int
nfs_clear_request_commit(struct nfs_page *req)
{
struct page *page = req->wb_page;
if (test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) {
dec_zone_page_state(page, NR_UNSTABLE_NFS);
dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
return 1;
}
return 0;
}
static inline
int nfs_write_need_commit(struct nfs_write_data *data)
{
if (data->verf.committed == NFS_DATA_SYNC)
return data->lseg == NULL;
else
return data->verf.committed != NFS_FILE_SYNC;
}
static inline
int nfs_reschedule_unstable_write(struct nfs_page *req,
struct nfs_write_data *data)
{
if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) {
nfs_mark_request_commit(req, data->lseg);
return 1;
}
if (test_and_clear_bit(PG_NEED_RESCHED, &req->wb_flags)) {
nfs_mark_request_dirty(req);
return 1;
}
return 0;
}
#else
static inline void
nfs_mark_request_commit(struct nfs_page *req, struct pnfs_layout_segment *lseg)
{
}
static inline int
nfs_clear_request_commit(struct nfs_page *req)
{
return 0;
}
static inline
int nfs_write_need_commit(struct nfs_write_data *data)
{
return 0;
}
static inline
int nfs_reschedule_unstable_write(struct nfs_page *req,
struct nfs_write_data *data)
{
return 0;
}
#endif
#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
static int
nfs_need_commit(struct nfs_inode *nfsi)
{
return radix_tree_tagged(&nfsi->nfs_page_tree, NFS_PAGE_TAG_COMMIT);
}
/*
* nfs_scan_commit - Scan an inode for commit requests
* @inode: NFS inode to scan
* @dst: destination list
* @idx_start: lower bound of page->index to scan.
* @npages: idx_start + npages sets the upper bound to scan.
*
* Moves requests from the inode's 'commit' request list.
* The requests are *not* checked to ensure that they form a contiguous set.
*/
static int
nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
{
struct nfs_inode *nfsi = NFS_I(inode);
int ret;
if (!nfs_need_commit(nfsi))
return 0;
spin_lock(&inode->i_lock);
ret = nfs_scan_list(nfsi, dst, idx_start, npages, NFS_PAGE_TAG_COMMIT);
if (ret > 0)
nfsi->ncommit -= ret;
spin_unlock(&inode->i_lock);
if (nfs_need_commit(NFS_I(inode)))
__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
return ret;
}
#else
static inline int nfs_need_commit(struct nfs_inode *nfsi)
{
return 0;
}
static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
{
return 0;
}
#endif
/*
* Search for an existing write request, and attempt to update
* it to reflect a new dirty region on a given page.
*
* If the attempt fails, then the existing request is flushed out
* to disk.
*/
static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
struct page *page,
unsigned int offset,
unsigned int bytes)
{
struct nfs_page *req;
unsigned int rqend;
unsigned int end;
int error;
if (!PagePrivate(page))
return NULL;
end = offset + bytes;
spin_lock(&inode->i_lock);
for (;;) {
req = nfs_page_find_request_locked(page);
if (req == NULL)
goto out_unlock;
rqend = req->wb_offset + req->wb_bytes;
/*
* Tell the caller to flush out the request if
* the offsets are non-contiguous.
* Note: nfs_flush_incompatible() will already
* have flushed out requests having wrong owners.
*/
if (offset > rqend
|| end < req->wb_offset)
goto out_flushme;
if (nfs_set_page_tag_locked(req))
break;
/* The request is locked, so wait and then retry */
spin_unlock(&inode->i_lock);
error = nfs_wait_on_request(req);
nfs_release_request(req);
if (error != 0)
goto out_err;
spin_lock(&inode->i_lock);
}
if (nfs_clear_request_commit(req) &&
radix_tree_tag_clear(&NFS_I(inode)->nfs_page_tree,
req->wb_index, NFS_PAGE_TAG_COMMIT) != NULL) {
NFS_I(inode)->ncommit--;
pnfs_clear_request_commit(req);
}
/* Okay, the request matches. Update the region */
if (offset < req->wb_offset) {
req->wb_offset = offset;
req->wb_pgbase = offset;
}
if (end > rqend)
req->wb_bytes = end - req->wb_offset;
else
req->wb_bytes = rqend - req->wb_offset;
out_unlock:
spin_unlock(&inode->i_lock);
return req;
out_flushme:
spin_unlock(&inode->i_lock);
nfs_release_request(req);
error = nfs_wb_page(inode, page);
out_err:
return ERR_PTR(error);
}
/*
* Try to update an existing write request, or create one if there is none.
*
* Note: Should always be called with the Page Lock held to prevent races
* if we have to add a new request. Also assumes that the caller has
* already called nfs_flush_incompatible() if necessary.
*/
static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
struct page *page, unsigned int offset, unsigned int bytes)
{
struct inode *inode = page->mapping->host;
struct nfs_page *req;
int error;
req = nfs_try_to_update_request(inode, page, offset, bytes);
if (req != NULL)
goto out;
req = nfs_create_request(ctx, inode, page, offset, bytes);
if (IS_ERR(req))
goto out;
error = nfs_inode_add_request(inode, req);
if (error != 0) {
nfs_release_request(req);
req = ERR_PTR(error);
}
out:
return req;
}
static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
unsigned int offset, unsigned int count)
{
struct nfs_page *req;
req = nfs_setup_write_request(ctx, page, offset, count);
if (IS_ERR(req))
return PTR_ERR(req);
/* Update file length */
nfs_grow_file(page, offset, count);
nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
nfs_mark_request_dirty(req);
nfs_clear_page_tag_locked(req);
return 0;
}
int nfs_flush_incompatible(struct file *file, struct page *page)
{
struct nfs_open_context *ctx = nfs_file_open_context(file);
struct nfs_page *req;
int do_flush, status;
/*
* Look for a request corresponding to this page. If there
* is one, and it belongs to another file, we flush it out
* before we try to copy anything into the page. Do this
* due to the lack of an ACCESS-type call in NFSv2.
* Also do the same if we find a request from an existing
* dropped page.
*/
do {
req = nfs_page_find_request(page);
if (req == NULL)
return 0;
do_flush = req->wb_page != page || req->wb_context != ctx ||
req->wb_lock_context->lockowner != current->files ||
req->wb_lock_context->pid != current->tgid;
nfs_release_request(req);
if (!do_flush)
return 0;
status = nfs_wb_page(page->mapping->host, page);
} while (status == 0);
return status;
}
/*
* If the page cache is marked as unsafe or invalid, then we can't rely on
* the PageUptodate() flag. In this case, we will need to turn off
* write optimisations that depend on the page contents being correct.
*/
static int nfs_write_pageuptodate(struct page *page, struct inode *inode)
{
return PageUptodate(page) &&
!(NFS_I(inode)->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA));
}
/*
* Update and possibly write a cached page of an NFS file.
*
* XXX: Keep an eye on generic_file_read to make sure it doesn't do bad
* things with a page scheduled for an RPC call (e.g. invalidate it).
*/
int nfs_updatepage(struct file *file, struct page *page,
unsigned int offset, unsigned int count)
{
struct nfs_open_context *ctx = nfs_file_open_context(file);
struct inode *inode = page->mapping->host;
int status = 0;
nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
dprintk("NFS: nfs_updatepage(%s/%s %d@%lld)\n",
file->f_path.dentry->d_parent->d_name.name,
file->f_path.dentry->d_name.name, count,
(long long)(page_offset(page) + offset));
/* If we're not using byte range locks, and we know the page
* is up to date, it may be more efficient to extend the write
* to cover the entire page in order to avoid fragmentation
* inefficiencies.
*/
if (nfs_write_pageuptodate(page, inode) &&
inode->i_flock == NULL &&
!(file->f_flags & O_DSYNC)) {
count = max(count + offset, nfs_page_length(page));
offset = 0;
}
status = nfs_writepage_setup(ctx, page, offset, count);
if (status < 0)
nfs_set_pageerror(page);
dprintk("NFS: nfs_updatepage returns %d (isize %lld)\n",
status, (long long)i_size_read(inode));
return status;
}
static void nfs_writepage_release(struct nfs_page *req,
struct nfs_write_data *data)
{
struct page *page = req->wb_page;
if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req, data))
nfs_inode_remove_request(req);
nfs_clear_page_tag_locked(req);
nfs_end_page_writeback(page);
}
static int flush_task_priority(int how)
{
switch (how & (FLUSH_HIGHPRI|FLUSH_LOWPRI)) {
case FLUSH_HIGHPRI:
return RPC_PRIORITY_HIGH;
case FLUSH_LOWPRI:
return RPC_PRIORITY_LOW;
}
return RPC_PRIORITY_NORMAL;
}
int nfs_initiate_write(struct nfs_write_data *data,
struct rpc_clnt *clnt,
const struct rpc_call_ops *call_ops,
int how)
{
struct inode *inode = data->inode;
int priority = flush_task_priority(how);
struct rpc_task *task;
struct rpc_message msg = {
.rpc_argp = &data->args,
.rpc_resp = &data->res,
.rpc_cred = data->cred,
};
struct rpc_task_setup task_setup_data = {
.rpc_client = clnt,
.task = &data->task,
.rpc_message = &msg,
.callback_ops = call_ops,
.callback_data = data,
.workqueue = nfsiod_workqueue,
.flags = RPC_TASK_ASYNC,
.priority = priority,
};
int ret = 0;
/* Set up the initial task struct. */
NFS_PROTO(inode)->write_setup(data, &msg);
dprintk("NFS: %5u initiated write call "
"(req %s/%lld, %u bytes @ offset %llu)\n",
data->task.tk_pid,
inode->i_sb->s_id,
(long long)NFS_FILEID(inode),
data->args.count,
(unsigned long long)data->args.offset);
task = rpc_run_task(&task_setup_data);
if (IS_ERR(task)) {
ret = PTR_ERR(task);
goto out;
}
if (how & FLUSH_SYNC) {
ret = rpc_wait_for_completion_task(task);
if (ret == 0)
ret = task->tk_status;
}
rpc_put_task(task);
out:
return ret;
}
EXPORT_SYMBOL_GPL(nfs_initiate_write);
/*
* Set up the argument/result storage required for the RPC call.
*/
static int nfs_write_rpcsetup(struct nfs_page *req,
struct nfs_write_data *data,
const struct rpc_call_ops *call_ops,
unsigned int count, unsigned int offset,
struct pnfs_layout_segment *lseg,
int how)
{
struct inode *inode = req->wb_context->path.dentry->d_inode;
/* Set up the RPC argument and reply structs
* NB: take care not to mess about with data->commit et al. */
data->req = req;
data->inode = inode = req->wb_context->path.dentry->d_inode;
data->cred = req->wb_context->cred;
data->lseg = get_lseg(lseg);
data->args.fh = NFS_FH(inode);
data->args.offset = req_offset(req) + offset;
data->args.pgbase = req->wb_pgbase + offset;
data->args.pages = data->pagevec;
data->args.count = count;
data->args.context = get_nfs_open_context(req->wb_context);
data->args.lock_context = req->wb_lock_context;
data->args.stable = NFS_UNSTABLE;
if (how & (FLUSH_STABLE | FLUSH_COND_STABLE)) {
data->args.stable = NFS_DATA_SYNC;
if (!nfs_need_commit(NFS_I(inode)))
data->args.stable = NFS_FILE_SYNC;
}
data->res.fattr = &data->fattr;
data->res.count = count;
data->res.verf = &data->verf;
nfs_fattr_init(&data->fattr);
if (data->lseg &&
(pnfs_try_to_write_data(data, call_ops, how) == PNFS_ATTEMPTED))
return 0;
return nfs_initiate_write(data, NFS_CLIENT(inode), call_ops, how);
}
/* If a nfs_flush_* function fails, it should remove reqs from @head and
* call this on each, which will prepare them to be retried on next
* writeback using standard nfs.
*/
static void nfs_redirty_request(struct nfs_page *req)
{
struct page *page = req->wb_page;
nfs_mark_request_dirty(req);
nfs_clear_page_tag_locked(req);
nfs_end_page_writeback(page);
}
/*
* Generate multiple small requests to write out a single
* contiguous dirty area on one page.
*/
static int nfs_flush_multi(struct nfs_pageio_descriptor *desc)
{
struct nfs_page *req = nfs_list_entry(desc->pg_list.next);
struct page *page = req->wb_page;
struct nfs_write_data *data;
size_t wsize = NFS_SERVER(desc->pg_inode)->wsize, nbytes;
unsigned int offset;
int requests = 0;
int ret = 0;
struct pnfs_layout_segment *lseg;
LIST_HEAD(list);
nfs_list_remove_request(req);
if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
(desc->pg_moreio || NFS_I(desc->pg_inode)->ncommit ||
desc->pg_count > wsize))
desc->pg_ioflags &= ~FLUSH_COND_STABLE;
nbytes = desc->pg_count;
do {
size_t len = min(nbytes, wsize);
data = nfs_writedata_alloc(1);
if (!data)
goto out_bad;
list_add(&data->pages, &list);
requests++;
nbytes -= len;
} while (nbytes != 0);
atomic_set(&req->wb_complete, requests);
BUG_ON(desc->pg_lseg);
lseg = pnfs_update_layout(desc->pg_inode, req->wb_context, IOMODE_RW);
ClearPageError(page);
offset = 0;
nbytes = desc->pg_count;
do {
int ret2;
data = list_entry(list.next, struct nfs_write_data, pages);
list_del_init(&data->pages);
data->pagevec[0] = page;
if (nbytes < wsize)
wsize = nbytes;
ret2 = nfs_write_rpcsetup(req, data, &nfs_write_partial_ops,
wsize, offset, lseg, desc->pg_ioflags);
if (ret == 0)
ret = ret2;
offset += wsize;
nbytes -= wsize;
} while (nbytes != 0);
put_lseg(lseg);
desc->pg_lseg = NULL;
return ret;
out_bad:
while (!list_empty(&list)) {
data = list_entry(list.next, struct nfs_write_data, pages);
list_del(&data->pages);
nfs_writedata_free(data);
}
nfs_redirty_request(req);
return -ENOMEM;
}
/*
* Create an RPC task for the given write request and kick it.
* The page must have been locked by the caller.
*
* It may happen that the page we're passed is not marked dirty.
* This is the case if nfs_updatepage detects a conflicting request
* that has been written but not committed.
*/
static int nfs_flush_one(struct nfs_pageio_descriptor *desc)
{
struct nfs_page *req;
struct page **pages;
struct nfs_write_data *data;
struct list_head *head = &desc->pg_list;
struct pnfs_layout_segment *lseg = desc->pg_lseg;
int ret;
data = nfs_writedata_alloc(nfs_page_array_len(desc->pg_base,
desc->pg_count));
if (!data) {
while (!list_empty(head)) {
req = nfs_list_entry(head->next);
nfs_list_remove_request(req);