aboutsummaryrefslogtreecommitdiffstats
path: root/fs/ceph/addr.c
blob: e00797eed29c076d2643319f78a6637eb8e772ff (plain) (blame)
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
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
#include "ceph_debug.h"

#include <linux/backing-dev.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <linux/pagemap.h>
#include <linux/writeback.h>	/* generic_writepages */
#include <linux/slab.h>
#include <linux/pagevec.h>
#include <linux/task_io_accounting_ops.h>

#include "super.h"
#include "osd_client.h"

/*
 * Ceph address space ops.
 *
 * There are a few funny things going on here.
 *
 * The page->private field is used to reference a struct
 * ceph_snap_context for _every_ dirty page.  This indicates which
 * snapshot the page was logically dirtied in, and thus which snap
 * context needs to be associated with the osd write during writeback.
 *
 * Similarly, struct ceph_inode_info maintains a set of counters to
 * count dirty pages on the inode.  In the absense of snapshots,
 * i_wrbuffer_ref == i_wrbuffer_ref_head == the dirty page count.
 *
 * When a snapshot is taken (that is, when the client receives
 * notification that a snapshot was taken), each inode with caps and
 * with dirty pages (dirty pages implies there is a cap) gets a new
 * ceph_cap_snap in the i_cap_snaps list (which is sorted in ascending
 * order, new snaps go to the tail).  The i_wrbuffer_ref_head count is
 * moved to capsnap->dirty. (Unless a sync write is currently in
 * progress.  In that case, the capsnap is said to be "pending", new
 * writes cannot start, and the capsnap isn't "finalized" until the
 * write completes (or fails) and a final size/mtime for the inode for
 * that snap can be settled upon.)  i_wrbuffer_ref_head is reset to 0.
 *
 * On writeback, we must submit writes to the osd IN SNAP ORDER.  So,
 * we look for the first capsnap in i_cap_snaps and write out pages in
 * that snap context _only_.  Then we move on to the next capsnap,
 * eventually reaching the "live" or "head" context (i.e., pages that
 * are not yet snapped) and are writing the most recently dirtied
 * pages.
 *
 * Invalidate and so forth must take care to ensure the dirty page
 * accounting is preserved.
 */

#define CONGESTION_ON_THRESH(congestion_kb) (congestion_kb >> (PAGE_SHIFT-10))
#define CONGESTION_OFF_THRESH(congestion_kb)				\
	(CONGESTION_ON_THRESH(congestion_kb) -				\
	 (CONGESTION_ON_THRESH(congestion_kb) >> 2))



/*
 * Dirty a page.  Optimistically adjust accounting, on the assumption
 * that we won't race with invalidate.  If we do, readjust.
 */
static int ceph_set_page_dirty(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode;
	struct ceph_inode_info *ci;
	int undo = 0;
	struct ceph_snap_context *snapc;

	if (unlikely(!mapping))
		return !TestSetPageDirty(page);

	if (TestSetPageDirty(page)) {
		dout("%p set_page_dirty %p idx %lu -- already dirty\n",
		     mapping->host, page, page->index);
		return 0;
	}

	inode = mapping->host;
	ci = ceph_inode(inode);

	/*
	 * Note that we're grabbing a snapc ref here without holding
	 * any locks!
	 */
	snapc = ceph_get_snap_context(ci->i_snap_realm->cached_context);

	/* dirty the head */
	spin_lock(&inode->i_lock);
	if (ci->i_wrbuffer_ref_head == 0)
		ci->i_head_snapc = ceph_get_snap_context(snapc);
	++ci->i_wrbuffer_ref_head;
	if (ci->i_wrbuffer_ref == 0)
		igrab(inode);
	++ci->i_wrbuffer_ref;
	dout("%p set_page_dirty %p idx %lu head %d/%d -> %d/%d "
	     "snapc %p seq %lld (%d snaps)\n",
	     mapping->host, page, page->index,
	     ci->i_wrbuffer_ref-1, ci->i_wrbuffer_ref_head-1,
	     ci->i_wrbuffer_ref, ci->i_wrbuffer_ref_head,
	     snapc, snapc->seq, snapc->num_snaps);
	spin_unlock(&inode->i_lock);

	/* now adjust page */
	spin_lock_irq(&mapping->tree_lock);
	if (page->mapping) {	/* Race with truncate? */
		WARN_ON_ONCE(!PageUptodate(page));

		if (mapping_cap_account_dirty(mapping)) {
			__inc_zone_page_state(page, NR_FILE_DIRTY);
			__inc_bdi_stat(mapping->backing_dev_info,
					BDI_RECLAIMABLE);
			task_io_account_write(PAGE_CACHE_SIZE);
		}
		radix_tree_tag_set(&mapping->page_tree,
				page_index(page), PAGECACHE_TAG_DIRTY);

		/*
		 * Reference snap context in page->private.  Also set
		 * PagePrivate so that we get invalidatepage callback.
		 */
		page->private = (unsigned long)snapc;
		SetPagePrivate(page);
	} else {
		dout("ANON set_page_dirty %p (raced truncate?)\n", page);
		undo = 1;
	}

	spin_unlock_irq(&mapping->tree_lock);

	if (undo)
		/* whoops, we failed to dirty the page */
		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);

	__mark_inode_dirty(mapping->host, I_DIRTY_PAGES);

	BUG_ON(!PageDirty(page));
	return 1;
}

/*
 * If we are truncating the full page (i.e. offset == 0), adjust the
 * dirty page counters appropriately.  Only called if there is private
 * data on the page.
 */
static void ceph_invalidatepage(struct page *page, unsigned long offset)
{
	struct inode *inode;
	struct ceph_inode_info *ci;
	struct ceph_snap_context *snapc = (void *)page->private;

	BUG_ON(!PageLocked(page));
	BUG_ON(!page->private);
	BUG_ON(!PagePrivate(page));
	BUG_ON(!page->mapping);

	inode = page->mapping->host;

	/*
	 * We can get non-dirty pages here due to races between
	 * set_page_dirty and truncate_complete_page; just spit out a
	 * warning, in case we end up with accounting problems later.
	 */
	if (!PageDirty(page))
		pr_err("%p invalidatepage %p page not dirty\n", inode, page);

	if (offset == 0)
		ClearPageChecked(page);

	ci = ceph_inode(inode);
	if (offset == 0) {
		dout("%p invalidatepage %p idx %lu full dirty page %lu\n",
		     inode, page, page->index, offset);
		ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
		ceph_put_snap_context(snapc);
		page->private = 0;
		ClearPagePrivate(page);
	} else {
		dout("%p invalidatepage %p idx %lu partial dirty page\n",
		     inode, page, page->index);
	}
}

/* just a sanity check */
static int ceph_releasepage(struct page *page, gfp_t g)
{
	struct inode *inode = page->mapping ? page->mapping->host : NULL;
	dout("%p releasepage %p idx %lu\n", inode, page, page->index);
	WARN_ON(PageDirty(page));
	WARN_ON(page->private);
	WARN_ON(PagePrivate(page));
	return 0;
}

/*
 * read a single page, without unlocking it.
 */
static int readpage_nounlock(struct file *filp, struct page *page)
{
	struct inode *inode = filp->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
	int err = 0;
	u64 len = PAGE_CACHE_SIZE;

	dout("readpage inode %p file %p page %p index %lu\n",
	     inode, filp, page, page->index);
	err = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
				  page->index << PAGE_CACHE_SHIFT, &len,
				  ci->i_truncate_seq, ci->i_truncate_size,
				  &page, 1);
	if (err == -ENOENT)
		err = 0;
	if (err < 0) {
		SetPageError(page);
		goto out;
	} else if (err < PAGE_CACHE_SIZE) {
		/* zero fill remainder of page */
		zero_user_segment(page, err, PAGE_CACHE_SIZE);
	}
	SetPageUptodate(page);

out:
	return err < 0 ? err : 0;
}

static int ceph_readpage(struct file *filp, struct page *page)
{
	int r = readpage_nounlock(filp, page);
	unlock_page(page);
	return r;
}

/*
 * Build a vector of contiguous pages from the provided page list.
 */
static struct page **page_vector_from_list(struct list_head *page_list,
					   unsigned *nr_pages)
{
	struct page **pages;
	struct page *page;
	int next_index, contig_pages = 0;

	/* build page vector */
	pages = kmalloc(sizeof(*pages) * *nr_pages, GFP_NOFS);
	if (!pages)
		return ERR_PTR(-ENOMEM);

	BUG_ON(list_empty(page_list));
	next_index = list_entry(page_list->prev, struct page, lru)->index;
	list_for_each_entry_reverse(page, page_list, lru) {
		if (page->index == next_index) {
			dout("readpages page %d %p\n", contig_pages, page);
			pages[contig_pages] = page;
			contig_pages++;
			next_index++;
		} else {
			break;
		}
	}
	*nr_pages = contig_pages;
	return pages;
}

/*
 * Read multiple pages.  Leave pages we don't read + unlock in page_list;
 * the caller (VM) cleans them up.
 */
static int ceph_readpages(struct file *file, struct address_space *mapping,
			  struct list_head *page_list, unsigned nr_pages)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_osd_client *osdc = &ceph_inode_to_client(inode)->osdc;
	int rc = 0;
	struct page **pages;
	loff_t offset;
	u64 len;

	dout("readpages %p file %p nr_pages %d\n",
	     inode, file, nr_pages);

	pages = page_vector_from_list(page_list, &nr_pages);
	if (IS_ERR(pages))
		return PTR_ERR(pages);

	/* guess read extent */
	offset = pages[0]->index << PAGE_CACHE_SHIFT;
	len = nr_pages << PAGE_CACHE_SHIFT;
	rc = ceph_osdc_readpages(osdc, ceph_vino(inode), &ci->i_layout,
				 offset, &len,
				 ci->i_truncate_seq, ci->i_truncate_size,
				 pages, nr_pages);
	if (rc == -ENOENT)
		rc = 0;
	if (rc < 0)
		goto out;

	for (; !list_empty(page_list) && len > 0;
	     rc -= PAGE_CACHE_SIZE, len -= PAGE_CACHE_SIZE) {
		struct page *page =
			list_entry(page_list->prev, struct page, lru);

		list_del(&page->lru);

		if (rc < (int)PAGE_CACHE_SIZE) {
			/* zero (remainder of) page */
			int s = rc < 0 ? 0 : rc;
			zero_user_segment(page, s, PAGE_CACHE_SIZE);
		}

		if (add_to_page_cache_lru(page, mapping, page->index, GFP_NOFS)) {
			page_cache_release(page);
			dout("readpages %p add_to_page_cache failed %p\n",
			     inode, page);
			continue;
		}
		dout("readpages %p adding %p idx %lu\n", inode, page,
		     page->index);
		flush_dcache_page(page);
		SetPageUptodate(page);
		unlock_page(page);
		page_cache_release(page);
	}
	rc = 0;

out:
	kfree(pages);
	return rc;
}

/*
 * Get ref for the oldest snapc for an inode with dirty data... that is, the
 * only snap context we are allowed to write back.
 */
static struct ceph_snap_context *get_oldest_context(struct inode *inode,
						    u64 *snap_size)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_snap_context *snapc = NULL;
	struct ceph_cap_snap *capsnap = NULL;

	spin_lock(&inode->i_lock);
	list_for_each_entry(capsnap, &ci->i_cap_snaps, ci_item) {
		dout(" cap_snap %p snapc %p has %d dirty pages\n", capsnap,
		     capsnap->context, capsnap->dirty_pages);
		if (capsnap->dirty_pages) {
			snapc = ceph_get_snap_context(capsnap->context);
			if (snap_size)
				*snap_size = capsnap->size;
			break;
		}
	}
	if (!snapc && ci->i_head_snapc) {
		snapc = ceph_get_snap_context(ci->i_head_snapc);
		dout(" head snapc %p has %d dirty pages\n",
		     snapc, ci->i_wrbuffer_ref_head);
	}
	spin_unlock(&inode->i_lock);
	return snapc;
}

/*
 * Write a single page, but leave the page locked.
 *
 * If we get a write error, set the page error bit, but still adjust the
 * dirty page accounting (i.e., page is no longer dirty).
 */
static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
{
	struct inode *inode;
	struct ceph_inode_info *ci;
	struct ceph_client *client;
	struct ceph_osd_client *osdc;
	loff_t page_off = page->index << PAGE_CACHE_SHIFT;
	int len = PAGE_CACHE_SIZE;
	loff_t i_size;
	int err = 0;
	struct ceph_snap_context *snapc, *oldest;
	u64 snap_size = 0;
	long writeback_stat;

	dout("writepage %p idx %lu\n", page, page->index);

	if (!page->mapping || !page->mapping->host) {
		dout("writepage %p - no mapping\n", page);
		return -EFAULT;
	}
	inode = page->mapping->host;
	ci = ceph_inode(inode);
	client = ceph_inode_to_client(inode);
	osdc = &client->osdc;

	/* verify this is a writeable snap context */
	snapc = (void *)page->private;
	if (snapc == NULL) {
		dout("writepage %p page %p not dirty?\n", inode, page);
		goto out;
	}
	oldest = get_oldest_context(inode, &snap_size);
	if (snapc->seq > oldest->seq) {
		dout("writepage %p page %p snapc %p not writeable - noop\n",
		     inode, page, (void *)page->private);
		/* we should only noop if called by kswapd */
		WARN_ON((current->flags & PF_MEMALLOC) == 0);
		ceph_put_snap_context(oldest);
		goto out;
	}
	ceph_put_snap_context(oldest);

	/* is this a partial page at end of file? */
	if (snap_size)
		i_size = snap_size;
	else
		i_size = i_size_read(inode);
	if (i_size < page_off + len)
		len = i_size - page_off;

	dout("writepage %p page %p index %lu on %llu~%u\n",
	     inode, page, page->index, page_off, len);

	writeback_stat = atomic_long_inc_return(&client->writeback_count);
	if (writeback_stat >
	    CONGESTION_ON_THRESH(client->mount_args->congestion_kb))
		set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC);

	set_page_writeback(page);
	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
				   &ci->i_layout, snapc,
				   page_off, len,
				   ci->i_truncate_seq, ci->i_truncate_size,
				   &inode->i_mtime,
				   &page, 1, 0, 0, true);
	if (err < 0) {
		dout("writepage setting page/mapping error %d %p\n", err, page);
		SetPageError(page);
		mapping_set_error(&inode->i_data, err);
		if (wbc)
			wbc->pages_skipped++;
	} else {
		dout("writepage cleaned page %p\n", page);
		err = 0;  /* vfs expects us to return 0 */
	}
	page->private = 0;
	ClearPagePrivate(page);
	end_page_writeback(page);
	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
	ceph_put_snap_context(snapc);  /* page's reference */
out:
	return err;
}

static int ceph_writepage(struct page *page, struct writeback_control *wbc)
{
	int err;
	struct inode *inode = page->mapping->host;
	BUG_ON(!inode);
	igrab(inode);
	err = writepage_nounlock(page, wbc);
	unlock_page(page);
	iput(inode);
	return err;
}


/*
 * lame release_pages helper.  release_pages() isn't exported to
 * modules.
 */
static void ceph_release_pages(struct page **pages, int num)
{
	struct pagevec pvec;
	int i;

	pagevec_init(&pvec, 0);
	for (i = 0; i < num; i++) {
		if (pagevec_add(&pvec, pages[i]) == 0)
			pagevec_release(&pvec);
	}
	pagevec_release(&pvec);
}


/*
 * async writeback completion handler.
 *
 * If we get an error, set the mapping error bit, but not the individual
 * page error bits.
 */
static void writepages_finish(struct ceph_osd_request *req,
			      struct ceph_msg *msg)
{
	struct inode *inode = req->r_inode;
	struct ceph_osd_reply_head *replyhead;
	struct ceph_osd_op *op;
	struct ceph_inode_info *ci = ceph_inode(inode);
	unsigned wrote;
	struct page *page;
	int i;
	struct ceph_snap_context *snapc = req->r_snapc;
	struct address_space *mapping = inode->i_mapping;
	__s32 rc = -EIO;
	u64 bytes = 0;
	struct ceph_client *client = ceph_inode_to_client(inode);
	long writeback_stat;
	unsigned issued = ceph_caps_issued(ci);

	/* parse reply */
	replyhead = msg->front.iov_base;
	WARN_ON(le32_to_cpu(replyhead->num_ops) == 0);
	op = (void *)(replyhead + 1);
	rc = le32_to_cpu(replyhead->result);
	bytes = le64_to_cpu(op->extent.length);

	if (rc >= 0) {
		/*
		 * Assume we wrote the pages we originally sent.  The
		 * osd might reply with fewer pages if our writeback
		 * raced with a truncation and was adjusted at the osd,
		 * so don't believe the reply.
		 */
		wrote = req->r_num_pages;
	} else {
		wrote = 0;
		mapping_set_error(mapping, rc);
	}
	dout("writepages_finish %p rc %d bytes %llu wrote %d (pages)\n",
	     inode, rc, bytes, wrote);

	/* clean all pages */
	for (i = 0; i < req->r_num_pages; i++) {
		page = req->r_pages[i];
		BUG_ON(!page);
		WARN_ON(!PageUptodate(page));

		writeback_stat =
			atomic_long_dec_return(&client->writeback_count);
		if (writeback_stat <
		    CONGESTION_OFF_THRESH(client->mount_args->congestion_kb))
			clear_bdi_congested(&client->backing_dev_info,
					    BLK_RW_ASYNC);

		ceph_put_snap_context((void *)page->private);
		page->private = 0;
		ClearPagePrivate(page);
		dout("unlocking %d %p\n", i, page);
		end_page_writeback(page);

		/*
		 * We lost the cache cap, need to truncate the page before
		 * it is unlocked, otherwise we'd truncate it later in the
		 * page truncation thread, possibly losing some data that
		 * raced its way in
		 */
		if ((issued & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0)
			generic_error_remove_page(inode->i_mapping, page);

		unlock_page(page);
	}
	dout("%p wrote+cleaned %d pages\n", inode, wrote);
	ceph_put_wrbuffer_cap_refs(ci, req->r_num_pages, snapc);

	ceph_release_pages(req->r_pages, req->r_num_pages);
	if (req->r_pages_from_pool)
		mempool_free(req->r_pages,
			     ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
	else
		kfree(req->r_pages);
	ceph_osdc_put_request(req);
}

/*
 * allocate a page vec, either directly, or if necessary, via a the
 * mempool.  we avoid the mempool if we can because req->r_num_pages
 * may be less than the maximum write size.
 */
static void alloc_page_vec(struct ceph_client *client,
			   struct ceph_osd_request *req)
{
	req->r_pages = kmalloc(sizeof(struct page *) * req->r_num_pages,
			       GFP_NOFS);
	if (!req->r_pages) {
		req->r_pages = mempool_alloc(client->wb_pagevec_pool, GFP_NOFS);
		req->r_pages_from_pool = 1;
		WARN_ON(!req->r_pages);
	}
}

/*
 * initiate async writeback
 */
static int ceph_writepages_start(struct address_space *mapping,
				 struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_client *client;
	pgoff_t index, start, end;
	int range_whole = 0;
	int should_loop = 1;
	pgoff_t max_pages = 0, max_pages_ever = 0;
	struct ceph_snap_context *snapc = NULL, *last_snapc = NULL, *pgsnapc;
	struct pagevec pvec;
	int done = 0;
	int rc = 0;
	unsigned wsize = 1 << inode->i_blkbits;
	struct ceph_osd_request *req = NULL;
	int do_sync;
	u64 snap_size = 0;

	/*
	 * Include a 'sync' in the OSD request if this is a data
	 * integrity write (e.g., O_SYNC write or fsync()), or if our
	 * cap is being revoked.
	 */
	do_sync = wbc->sync_mode == WB_SYNC_ALL;
	if (ceph_caps_revoking(ci, CEPH_CAP_FILE_BUFFER))
		do_sync = 1;
	dout("writepages_start %p dosync=%d (mode=%s)\n",
	     inode, do_sync,
	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));

	client = ceph_inode_to_client(inode);
	if (client->mount_state == CEPH_MOUNT_SHUTDOWN) {
		pr_warning("writepage_start %p on forced umount\n", inode);
		return -EIO; /* we're in a forced umount, don't write! */
	}
	if (client->mount_args->wsize && client->mount_args->wsize < wsize)
		wsize = client->mount_args->wsize;
	if (wsize < PAGE_CACHE_SIZE)
		wsize = PAGE_CACHE_SIZE;
	max_pages_ever = wsize >> PAGE_CACHE_SHIFT;

	pagevec_init(&pvec, 0);

	/* ?? */
	if (wbc->nonblocking && bdi_write_congested(bdi)) {
		dout(" writepages congested\n");
		wbc->encountered_congestion = 1;
		goto out_final;
	}

	/* where to start/end? */
	if (wbc->range_cyclic) {
		start = mapping->writeback_index; /* Start from prev offset */
		end = -1;
		dout(" cyclic, start at %lu\n", start);
	} else {
		start = wbc->range_start >> PAGE_CACHE_SHIFT;
		end = wbc->range_end >> PAGE_CACHE_SHIFT;
		if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX)
			range_whole = 1;
		should_loop = 0;
		dout(" not cyclic, %lu to %lu\n", start, end);
	}
	index = start;

retry:
	/* find oldest snap context with dirty data */
	ceph_put_snap_context(snapc);
	snapc = get_oldest_context(inode, &snap_size);
	if (!snapc) {
		/* hmm, why does writepages get called when there
		   is no dirty data? */
		dout(" no snap context with dirty data?\n");
		goto out;
	}
	dout(" oldest snapc is %p seq %lld (%d snaps)\n",
	     snapc, snapc->seq, snapc->num_snaps);
	if (last_snapc && snapc != last_snapc) {
		/* if we switched to a newer snapc, restart our scan at the
		 * start of the original file range. */
		dout("  snapc differs from last pass, restarting at %lu\n",
		     index);
		index = start;
	}
	last_snapc = snapc;

	while (!done && index <= end) {
		unsigned i;
		int first;
		pgoff_t next;
		int pvec_pages, locked_pages;
		struct page *page;
		int want;
		u64 offset, len;
		struct ceph_osd_request_head *reqhead;
		struct ceph_osd_op *op;
		long writeback_stat;

		next = 0;
		locked_pages = 0;
		max_pages = max_pages_ever;

get_more_pages:
		first = -1;
		want = min(end - index,
			   min((pgoff_t)PAGEVEC_SIZE,
			       max_pages - (pgoff_t)locked_pages) - 1)
			+ 1;
		pvec_pages = pagevec_lookup_tag(&pvec, mapping, &index,
						PAGECACHE_TAG_DIRTY,
						want);
		dout("pagevec_lookup_tag got %d\n", pvec_pages);
		if (!pvec_pages && !locked_pages)
			break;
		for (i = 0; i < pvec_pages && locked_pages < max_pages; i++) {
			page = pvec.pages[i];
			dout("? %p idx %lu\n", page, page->index);
			if (locked_pages == 0)
				lock_page(page);  /* first page */
			else if (!trylock_page(page))
				break;

			/* only dirty pages, or our accounting breaks */
			if (unlikely(!PageDirty(page)) ||
			    unlikely(page->mapping != mapping)) {
				dout("!dirty or !mapping %p\n", page);
				unlock_page(page);
				break;
			}
			if (!wbc->range_cyclic && page->index > end) {
				dout("end of range %p\n", page);
				done = 1;
				unlock_page(page);
				break;
			}
			if (next && (page->index != next)) {
				dout("not consecutive %p\n", page);
				unlock_page(page);
				break;
			}
			if (wbc->sync_mode != WB_SYNC_NONE) {
				dout("waiting on writeback %p\n", page);
				wait_on_page_writeback(page);
			}
			if ((snap_size && page_offset(page) > snap_size) ||
			    (!snap_size &&
			     page_offset(page) > i_size_read(inode))) {
				dout("%p page eof %llu\n", page, snap_size ?
				     snap_size : i_size_read(inode));
				done = 1;
				unlock_page(page);
				break;
			}
			if (PageWriteback(page)) {
				dout("%p under writeback\n", page);
				unlock_page(page);
				break;
			}

			/* only if matching snap context */
			pgsnapc = (void *)page->private;
			if (pgsnapc->seq > snapc->seq) {
				dout("page snapc %p %lld > oldest %p %lld\n",
				     pgsnapc, pgsnapc->seq, snapc, snapc->seq);
				unlock_page(page);
				if (!locked_pages)
					continue; /* keep looking for snap */
				break;
			}

			if (!clear_page_dirty_for_io(page)) {
				dout("%p !clear_page_dirty_for_io\n", page);
				unlock_page(page);
				break;
			}

			/* ok */
			if (locked_pages == 0) {
				/* prepare async write request */
				offset = page->index << PAGE_CACHE_SHIFT;
				len = wsize;
				req = ceph_osdc_new_request(&client->osdc,
					    &ci->i_layout,
					    ceph_vino(inode),
					    offset, &len,
					    CEPH_OSD_OP_WRITE,
					    CEPH_OSD_FLAG_WRITE |
						    CEPH_OSD_FLAG_ONDISK,
					    snapc, do_sync,
					    ci->i_truncate_seq,
					    ci->i_truncate_size,
					    &inode->i_mtime, true, 1);
				max_pages = req->r_num_pages;

				alloc_page_vec(client, req);
				req->r_callback = writepages_finish;
				req->r_inode = inode;
			}

			/* note position of first page in pvec */
			if (first < 0)
				first = i;
			dout("%p will write page %p idx %lu\n",
			     inode, page, page->index);

			writeback_stat = atomic_long_inc_return(&client->writeback_count);
			if (writeback_stat > CONGESTION_ON_THRESH(client->mount_args->congestion_kb)) {
				set_bdi_congested(&client->backing_dev_info, BLK_RW_ASYNC);
			}

			set_page_writeback(page);
			req->r_pages[locked_pages] = page;
			locked_pages++;
			next = page->index + 1;
		}

		/* did we get anything? */
		if (!locked_pages)
			goto release_pvec_pages;
		if (i) {
			int j;
			BUG_ON(!locked_pages || first < 0);

			if (pvec_pages && i == pvec_pages &&
			    locked_pages < max_pages) {
				dout("reached end pvec, trying for more\n");
				pagevec_reinit(&pvec);
				goto get_more_pages;
			}

			/* shift unused pages over in the pvec...  we
			 * will need to release them below. */
			for (j = i; j < pvec_pages; j++) {
				dout(" pvec leftover page %p\n",
				     pvec.pages[j]);
				pvec.pages[j-i+first] = pvec.pages[j];
			}
			pvec.nr -= i-first;
		}

		/* submit the write */
		offset = req->r_pages[0]->index << PAGE_CACHE_SHIFT;
		len = min((snap_size ? snap_size : i_size_read(inode)) - offset,
			  (u64)locked_pages << PAGE_CACHE_SHIFT);
		dout("writepages got %d pages at %llu~%llu\n",
		     locked_pages, offset, len);

		/* revise final length, page count */
		req->r_num_pages = locked_pages;
		reqhead = req->r_request->front.iov_base;
		op = (void *)(reqhead + 1);
		op->extent.length = cpu_to_le64(len);
		op->payload_len = cpu_to_le32(len);
		req->r_request->hdr.data_len = cpu_to_le32(len);

		ceph_osdc_start_request(&client->osdc, req, true);
		req = NULL;

		/* continue? */
		index = next;
		wbc->nr_to_write -= locked_pages;
		if (wbc->nr_to_write <= 0)
			done = 1;

release_pvec_pages:
		dout("pagevec_release on %d pages (%p)\n", (int)pvec.nr,
		     pvec.nr ? pvec.pages[0] : NULL);
		pagevec_release(&pvec);

		if (locked_pages && !done)
			goto retry;
	}

	if (should_loop && !done) {
		/* more to do; loop back to beginning of file */
		dout("writepages looping back to beginning of file\n");
		should_loop = 0;
		index = 0;
		goto retry;
	}

	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
		mapping->writeback_index = index;

out:
	if (req)
		ceph_osdc_put_request(req);
	if (rc > 0)
		rc = 0;  /* vfs expects us to return 0 */
	ceph_put_snap_context(snapc);
	dout("writepages done, rc = %d\n", rc);
out_final:
	return rc;
}



/*
 * See if a given @snapc is either writeable, or already written.
 */
static int context_is_writeable_or_written(struct inode *inode,
					   struct ceph_snap_context *snapc)
{
	struct ceph_snap_context *oldest = get_oldest_context(inode, NULL);
	int ret = !oldest || snapc->seq <= oldest->seq;

	ceph_put_snap_context(oldest);
	return ret;
}

/*
 * We are only allowed to write into/dirty the page if the page is
 * clean, or already dirty within the same snap context.
 *
 * called with page locked.
 * return success with page locked,
 * or any failure (incl -EAGAIN) with page unlocked.
 */
static int ceph_update_writeable_page(struct file *file,
			    loff_t pos, unsigned len,
			    struct page *page)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
	loff_t page_off = pos & PAGE_CACHE_MASK;
	int pos_in_page = pos & ~PAGE_CACHE_MASK;
	int end_in_page = pos_in_page + len;
	loff_t i_size;
	int r;
	struct ceph_snap_context *snapc, *oldest;

retry_locked:
	/* writepages currently holds page lock, but if we change that later, */
	wait_on_page_writeback(page);

	/* check snap context */
	BUG_ON(!ci->i_snap_realm);
	down_read(&mdsc->snap_rwsem);
	BUG_ON(!ci->i_snap_realm->cached_context);
	snapc = (void *)page->private;
	if (snapc && snapc != ci->i_head_snapc) {
		/*
		 * this page is already dirty in another (older) snap
		 * context!  is it writeable now?
		 */
		oldest = get_oldest_context(inode, NULL);
		up_read(&mdsc->snap_rwsem);

		if (snapc->seq > oldest->seq) {
			ceph_put_snap_context(oldest);
			dout(" page %p snapc %p not current or oldest\n",
			     page, snapc);
			/*
			 * queue for writeback, and wait for snapc to
			 * be writeable or written
			 */
			snapc = ceph_get_snap_context(snapc);
			unlock_page(page);
			ceph_queue_writeback(inode);
			r = wait_event_interruptible(ci->i_cap_wq,
			       context_is_writeable_or_written(inode, snapc));
			ceph_put_snap_context(snapc);
			if (r == -ERESTARTSYS)
				return r;
			return -EAGAIN;
		}
		ceph_put_snap_context(oldest);

		/* yay, writeable, do it now (without dropping page lock) */
		dout(" page %p snapc %p not current, but oldest\n",
		     page, snapc);
		if (!clear_page_dirty_for_io(page))
			goto retry_locked;
		r = writepage_nounlock(page, NULL);
		if (r < 0)
			goto fail_nosnap;
		goto retry_locked;
	}

	if (PageUptodate(page)) {
		dout(" page %p already uptodate\n", page);
		return 0;
	}

	/* full page? */
	if (pos_in_page == 0 && len == PAGE_CACHE_SIZE)
		return 0;

	/* past end of file? */
	i_size = inode->i_size;   /* caller holds i_mutex */

	if (i_size + len > inode->i_sb->s_maxbytes) {
		/* file is too big */
		r = -EINVAL;
		goto fail;
	}

	if (page_off >= i_size ||
	    (pos_in_page == 0 && (pos+len) >= i_size &&
	     end_in_page - pos_in_page != PAGE_CACHE_SIZE)) {
		dout(" zeroing %p 0 - %d and %d - %d\n",
		     page, pos_in_page, end_in_page, (int)PAGE_CACHE_SIZE);
		zero_user_segments(page,
				   0, pos_in_page,
				   end_in_page, PAGE_CACHE_SIZE);
		return 0;
	}

	/* we need to read it. */
	up_read(&mdsc->snap_rwsem);
	r = readpage_nounlock(file, page);
	if (r < 0)
		goto fail_nosnap;
	goto retry_locked;

fail:
	up_read(&mdsc->snap_rwsem);
fail_nosnap:
	unlock_page(page);
	return r;
}

/*
 * We are only allowed to write into/dirty the page if the page is
 * clean, or already dirty within the same snap context.
 */
static int ceph_write_begin(struct file *file, struct address_space *mapping,
			    loff_t pos, unsigned len, unsigned flags,
			    struct page **pagep, void **fsdata)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct page *page;
	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
	int r;

	do {
		/* get a page */
		page = grab_cache_page_write_begin(mapping, index, 0);
		if (!page)
			return -ENOMEM;
		*pagep = page;

		dout("write_begin file %p inode %p page %p %d~%d\n", file,
	     	inode, page, (int)pos, (int)len);

		r = ceph_update_writeable_page(file, pos, len, page);
	} while (r == -EAGAIN);

	return r;
}

/*
 * we don't do anything in here that simple_write_end doesn't do
 * except adjust dirty page accounting and drop read lock on
 * mdsc->snap_rwsem.
 */
static int ceph_write_end(struct file *file, struct address_space *mapping,
			  loff_t pos, unsigned len, unsigned copied,
			  struct page *page, void *fsdata)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct ceph_client *client = ceph_inode_to_client(inode);
	struct ceph_mds_client *mdsc = &client->mdsc;
	unsigned from = pos & (PAGE_CACHE_SIZE - 1);
	int check_cap = 0;

	dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
	     inode, page, (int)pos, (int)copied, (int)len);

	/* zero the stale part of the page if we did a short copy */
	if (copied < len)
		zero_user_segment(page, from+copied, len);

	/* did file size increase? */
	/* (no need for i_size_read(); we caller holds i_mutex */
	if (pos+copied > inode->i_size)
		check_cap = ceph_inode_set_size(inode, pos+copied);

	if (!PageUptodate(page))
		SetPageUptodate(page);

	set_page_dirty(page);

	unlock_page(page);
	up_read(&mdsc->snap_rwsem);
	page_cache_release(page);

	if (check_cap)
		ceph_check_caps(ceph_inode(inode), CHECK_CAPS_AUTHONLY, NULL);

	return copied;
}

/*
 * we set .direct_IO to indicate direct io is supported, but since we
 * intercept O_DIRECT reads and writes early, this function should
 * never get called.
 */
static ssize_t ceph_direct_io(int rw, struct kiocb *iocb,
			      const struct iovec *iov,
			      loff_t pos, unsigned long nr_segs)
{
	WARN_ON(1);
	return -EINVAL;
}

const struct address_space_operations ceph_aops = {
	.readpage = ceph_readpage,
	.readpages = ceph_readpages,
	.writepage = ceph_writepage,
	.writepages = ceph_writepages_start,
	.write_begin = ceph_write_begin,
	.write_end = ceph_write_end,
	.set_page_dirty = ceph_set_page_dirty,
	.invalidatepage = ceph_invalidatepage,
	.releasepage = ceph_releasepage,
	.direct_IO = ceph_direct_io,
};


/*
 * vm ops
 */

/*
 * Reuse write_begin here for simplicity.
 */
static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct inode *inode = vma->vm_file->f_dentry->d_inode;
	struct page *page = vmf->page;
	struct ceph_mds_client *mdsc = &ceph_inode_to_client(inode)->mdsc;
	loff_t off = page->index << PAGE_CACHE_SHIFT;
	loff_t size, len;
	int ret;

	size = i_size_read(inode);
	if (off + PAGE_CACHE_SIZE <= size)
		len = PAGE_CACHE_SIZE;
	else
		len = size & ~PAGE_CACHE_MASK;

	dout("page_mkwrite %p %llu~%llu page %p idx %lu\n", inode,
	     off, len, page, page->index);

	lock_page(page);

	ret = VM_FAULT_NOPAGE;
	if ((off > size) ||
	    (page->mapping != inode->i_mapping))
		goto out;

	ret = ceph_update_writeable_page(vma->vm_file, off, len, page);
	if (ret == 0) {
		/* success.  we'll keep the page locked. */
		set_page_dirty(page);
		up_read(&mdsc->snap_rwsem);
		ret = VM_FAULT_LOCKED;
	} else {
		if (ret == -ENOMEM)
			ret = VM_FAULT_OOM;
		else
			ret = VM_FAULT_SIGBUS;
	}
out:
	dout("page_mkwrite %p %llu~%llu = %d\n", inode, off, len, ret);
	if (ret != VM_FAULT_LOCKED)
		unlock_page(page);
	return ret;
}

static struct vm_operations_struct ceph_vmops = {
	.fault		= filemap_fault,
	.page_mkwrite	= ceph_page_mkwrite,
};

int ceph_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct address_space *mapping = file->f_mapping;

	if (!mapping->a_ops->readpage)
		return -ENOEXEC;
	file_accessed(file);
	vma->vm_ops = &ceph_vmops;
	vma->vm_flags |= VM_CAN_NONLINEAR;
	return 0;
}