summaryrefslogtreecommitdiffstats
path: root/fs/ceph/addr.c
blob: a268abfe60acd53d034b89d53139064ecaa687ac (plain)
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
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
#include <linux/ceph/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 "mds_client.h"
#include "cache.h"
#include <linux/ceph/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 absence 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))

static inline struct ceph_snap_context *page_snap_context(struct page *page)
{
	if (PagePrivate(page))
		return (void *)page->private;
	return NULL;
}

/*
 * 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;
	struct ceph_snap_context *snapc;
	int ret;

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

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

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

	/* dirty the head */
	spin_lock(&ci->i_ceph_lock);
	BUG_ON(ci->i_wr_ref == 0); // caller should hold Fw reference
	if (__ceph_have_pending_cap_snap(ci)) {
		struct ceph_cap_snap *capsnap =
				list_last_entry(&ci->i_cap_snaps,
						struct ceph_cap_snap,
						ci_item);
		snapc = ceph_get_snap_context(capsnap->context);
		capsnap->dirty_pages++;
	} else {
		BUG_ON(!ci->i_head_snapc);
		snapc = ceph_get_snap_context(ci->i_head_snapc);
		++ci->i_wrbuffer_ref_head;
	}
	if (ci->i_wrbuffer_ref == 0)
		ihold(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(&ci->i_ceph_lock);

	/*
	 * Reference snap context in page->private.  Also set
	 * PagePrivate so that we get invalidatepage callback.
	 */
	BUG_ON(PagePrivate(page));
	page->private = (unsigned long)snapc;
	SetPagePrivate(page);

	ret = __set_page_dirty_nobuffers(page);
	WARN_ON(!PageLocked(page));
	WARN_ON(!page->mapping);

	return ret;
}

/*
 * 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 int offset,
				unsigned int length)
{
	struct inode *inode;
	struct ceph_inode_info *ci;
	struct ceph_snap_context *snapc = page_snap_context(page);

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

	if (offset != 0 || length != PAGE_CACHE_SIZE) {
		dout("%p invalidatepage %p idx %lu partial dirty page %u~%u\n",
		     inode, page, page->index, offset, length);
		return;
	}

	ceph_invalidate_fscache_page(inode, page);

	if (!PagePrivate(page))
		return;

	/*
	 * 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);

	ClearPageChecked(page);

	dout("%p invalidatepage %p idx %lu full dirty page\n",
	     inode, page, page->index);

	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
	ceph_put_snap_context(snapc);
	page->private = 0;
	ClearPagePrivate(page);
}

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));

	/* Can we release the page from the cache? */
	if (!ceph_release_fscache_page(page, g))
		return 0;

	return !PagePrivate(page);
}

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

	if (off >= i_size_read(inode)) {
		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
		SetPageUptodate(page);
		return 0;
	}

	if (ci->i_inline_version != CEPH_INLINE_NONE) {
		/*
		 * Uptodate inline data should have been added
		 * into page cache while getting Fcr caps.
		 */
		if (off == 0)
			return -EINVAL;
		zero_user_segment(page, 0, PAGE_CACHE_SIZE);
		SetPageUptodate(page);
		return 0;
	}

	err = ceph_readpage_from_fscache(inode, page);
	if (err == 0)
		goto out;

	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,
				  off, &len,
				  ci->i_truncate_seq, ci->i_truncate_size,
				  &page, 1, 0);
	if (err == -ENOENT)
		err = 0;
	if (err < 0) {
		SetPageError(page);
		ceph_fscache_readpage_cancel(inode, page);
		goto out;
	}
	if (err < PAGE_CACHE_SIZE)
		/* zero fill remainder of page */
		zero_user_segment(page, err, PAGE_CACHE_SIZE);
	else
		flush_dcache_page(page);

	SetPageUptodate(page);
	ceph_readpage_to_fscache(inode, 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;
}

/*
 * Finish an async read(ahead) op.
 */
static void finish_read(struct ceph_osd_request *req, struct ceph_msg *msg)
{
	struct inode *inode = req->r_inode;
	struct ceph_osd_data *osd_data;
	int rc = req->r_result;
	int bytes = le32_to_cpu(msg->hdr.data_len);
	int num_pages;
	int i;

	dout("finish_read %p req %p rc %d bytes %d\n", inode, req, rc, bytes);

	/* unlock all pages, zeroing any data we didn't read */
	osd_data = osd_req_op_extent_osd_data(req, 0);
	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
	num_pages = calc_pages_for((u64)osd_data->alignment,
					(u64)osd_data->length);
	for (i = 0; i < num_pages; i++) {
		struct page *page = osd_data->pages[i];

		if (rc < 0)
			goto unlock;
		if (bytes < (int)PAGE_CACHE_SIZE) {
			/* zero (remainder of) page */
			int s = bytes < 0 ? 0 : bytes;
			zero_user_segment(page, s, PAGE_CACHE_SIZE);
		}
 		dout("finish_read %p uptodate %p idx %lu\n", inode, page,
		     page->index);
		flush_dcache_page(page);
		SetPageUptodate(page);
		ceph_readpage_to_fscache(inode, page);
unlock:
		unlock_page(page);
		page_cache_release(page);
		bytes -= PAGE_CACHE_SIZE;
	}
	kfree(osd_data->pages);
}

static void ceph_unlock_page_vector(struct page **pages, int num_pages)
{
	int i;

	for (i = 0; i < num_pages; i++)
		unlock_page(pages[i]);
}

/*
 * start an async read(ahead) operation.  return nr_pages we submitted
 * a read for on success, or negative error code.
 */
static int start_read(struct inode *inode, struct list_head *page_list, int max)
{
	struct ceph_osd_client *osdc =
		&ceph_inode_to_client(inode)->client->osdc;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct page *page = list_entry(page_list->prev, struct page, lru);
	struct ceph_vino vino;
	struct ceph_osd_request *req;
	u64 off;
	u64 len;
	int i;
	struct page **pages;
	pgoff_t next_index;
	int nr_pages = 0;
	int ret;

	off = (u64) page_offset(page);

	/* count pages */
	next_index = page->index;
	list_for_each_entry_reverse(page, page_list, lru) {
		if (page->index != next_index)
			break;
		nr_pages++;
		next_index++;
		if (max && nr_pages == max)
			break;
	}
	len = nr_pages << PAGE_CACHE_SHIFT;
	dout("start_read %p nr_pages %d is %lld~%lld\n", inode, nr_pages,
	     off, len);
	vino = ceph_vino(inode);
	req = ceph_osdc_new_request(osdc, &ci->i_layout, vino, off, &len,
				    0, 1, CEPH_OSD_OP_READ,
				    CEPH_OSD_FLAG_READ, NULL,
				    ci->i_truncate_seq, ci->i_truncate_size,
				    false);
	if (IS_ERR(req))
		return PTR_ERR(req);

	/* build page vector */
	nr_pages = calc_pages_for(0, len);
	pages = kmalloc(sizeof(*pages) * nr_pages, GFP_KERNEL);
	ret = -ENOMEM;
	if (!pages)
		goto out;
	for (i = 0; i < nr_pages; ++i) {
		page = list_entry(page_list->prev, struct page, lru);
		BUG_ON(PageLocked(page));
		list_del(&page->lru);

 		dout("start_read %p adding %p idx %lu\n", inode, page,
		     page->index);
		if (add_to_page_cache_lru(page, &inode->i_data, page->index,
					  GFP_KERNEL)) {
			ceph_fscache_uncache_page(inode, page);
			page_cache_release(page);
			dout("start_read %p add_to_page_cache failed %p\n",
			     inode, page);
			nr_pages = i;
			goto out_pages;
		}
		pages[i] = page;
	}
	osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0, false, false);
	req->r_callback = finish_read;
	req->r_inode = inode;

	ceph_osdc_build_request(req, off, NULL, vino.snap, NULL);

	dout("start_read %p starting %p %lld~%lld\n", inode, req, off, len);
	ret = ceph_osdc_start_request(osdc, req, false);
	if (ret < 0)
		goto out_pages;
	ceph_osdc_put_request(req);
	return nr_pages;

out_pages:
	ceph_unlock_page_vector(pages, nr_pages);
	ceph_release_page_vector(pages, nr_pages);
out:
	ceph_osdc_put_request(req);
	return ret;
}


/*
 * 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_inode(file);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	int rc = 0;
	int max = 0;

	if (ceph_inode(inode)->i_inline_version != CEPH_INLINE_NONE)
		return -EINVAL;

	rc = ceph_readpages_from_fscache(mapping->host, mapping, page_list,
					 &nr_pages);

	if (rc == 0)
		goto out;

	if (fsc->mount_options->rsize >= PAGE_CACHE_SIZE)
		max = (fsc->mount_options->rsize + PAGE_CACHE_SIZE - 1)
			>> PAGE_SHIFT;

	dout("readpages %p file %p nr_pages %d max %d\n", inode,
		file, nr_pages,
	     max);
	while (!list_empty(page_list)) {
		rc = start_read(inode, page_list, max);
		if (rc < 0)
			goto out;
		BUG_ON(rc == 0);
	}
out:
	ceph_fscache_readpages_cancel(inode, page_list);

	dout("readpages %p file %p ret %d\n", inode, file, rc);
	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,
						    loff_t *snap_size)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_snap_context *snapc = NULL;
	struct ceph_cap_snap *capsnap = NULL;

	spin_lock(&ci->i_ceph_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_wrbuffer_ref_head) {
		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(&ci->i_ceph_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_fs_client *fsc;
	struct ceph_osd_client *osdc;
	struct ceph_snap_context *snapc, *oldest;
	loff_t page_off = page_offset(page);
	loff_t snap_size = -1;
	long writeback_stat;
	u64 truncate_size;
	u32 truncate_seq;
	int err = 0, len = PAGE_CACHE_SIZE;

	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);
	fsc = ceph_inode_to_client(inode);
	osdc = &fsc->client->osdc;

	/* verify this is a writeable snap context */
	snapc = page_snap_context(page);
	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, snapc);
		/* 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);

	spin_lock(&ci->i_ceph_lock);
	truncate_seq = ci->i_truncate_seq;
	truncate_size = ci->i_truncate_size;
	if (snap_size == -1)
		snap_size = i_size_read(inode);
	spin_unlock(&ci->i_ceph_lock);

	/* is this a partial page at end of file? */
	if (page_off >= snap_size) {
		dout("%p page eof %llu\n", page, snap_size);
		goto out;
	}
	if (snap_size < page_off + len)
		len = snap_size - page_off;

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

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

	ceph_readpage_to_fscache(inode, page);

	set_page_writeback(page);
	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
				   &ci->i_layout, snapc,
				   page_off, len,
				   truncate_seq, truncate_size,
				   &inode->i_mtime, &page, 1);
	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);
	ihold(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_inode_info *ci = ceph_inode(inode);
	struct ceph_osd_data *osd_data;
	unsigned wrote;
	struct page *page;
	int num_pages;
	int i;
	struct ceph_snap_context *snapc = req->r_snapc;
	struct address_space *mapping = inode->i_mapping;
	int rc = req->r_result;
	u64 bytes = req->r_ops[0].extent.length;
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	long writeback_stat;
	unsigned issued = ceph_caps_issued(ci);

	osd_data = osd_req_op_extent_osd_data(req, 0);
	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_PAGES);
	num_pages = calc_pages_for((u64)osd_data->alignment,
					(u64)osd_data->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 = 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 < num_pages; i++) {
		page = osd_data->pages[i];
		BUG_ON(!page);
		WARN_ON(!PageUptodate(page));

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

		ceph_put_snap_context(page_snap_context(page));
		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, num_pages, snapc);

	ceph_release_pages(osd_data->pages, num_pages);
	if (osd_data->pages_from_pool)
		mempool_free(osd_data->pages,
			     ceph_sb_to_client(inode->i_sb)->wb_pagevec_pool);
	else
		kfree(osd_data->pages);
	ceph_osdc_put_request(req);
}

/*
 * initiate async writeback
 */
static int ceph_writepages_start(struct address_space *mapping,
				 struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_vino vino = ceph_vino(inode);
	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 = 0;
	loff_t snap_size, i_size;
	u64 truncate_size;
	u32 truncate_seq;

	/*
	 * 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.
	 */
	if ((wbc->sync_mode == WB_SYNC_ALL) ||
		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"));

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

	pagevec_init(&pvec, 0);

	/* 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);
	snap_size = -1;
	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);

	spin_lock(&ci->i_ceph_lock);
	truncate_seq = ci->i_truncate_seq;
	truncate_size = ci->i_truncate_size;
	i_size = i_size_read(inode);
	spin_unlock(&ci->i_ceph_lock);

	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 **pages = NULL;
		mempool_t *pool = NULL;	/* Becomes non-null if mempool used */
		struct page *page;
		int want;
		u64 offset, len;
		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 (page_offset(page) >=
			    (snap_size == -1 ? i_size : snap_size)) {
				dout("%p page eof %llu\n", page,
				     (snap_size == -1 ? i_size : snap_size));
				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 = page_snap_context(page);
			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;
			}

			/*
			 * We have something to write.  If this is
			 * the first locked page this time through,
			 * allocate an osd request and a page array
			 * that it will use.
			 */
			if (locked_pages == 0) {
				BUG_ON(pages);
				/* prepare async write request */
				offset = (u64)page_offset(page);
				len = wsize;
				req = ceph_osdc_new_request(&fsc->client->osdc,
							&ci->i_layout, vino,
							offset, &len, 0,
							do_sync ? 2 : 1,
							CEPH_OSD_OP_WRITE,
							CEPH_OSD_FLAG_WRITE |
							CEPH_OSD_FLAG_ONDISK,
							snapc, truncate_seq,
							truncate_size, true);
				if (IS_ERR(req)) {
					rc = PTR_ERR(req);
					unlock_page(page);
					break;
				}

				if (do_sync)
					osd_req_op_init(req, 1,
							CEPH_OSD_OP_STARTSYNC, 0);

				req->r_callback = writepages_finish;
				req->r_inode = inode;

				max_pages = calc_pages_for(0, (u64)len);
				pages = kmalloc(max_pages * sizeof (*pages),
						GFP_NOFS);
				if (!pages) {
					pool = fsc->wb_pagevec_pool;
					pages = mempool_alloc(pool, GFP_NOFS);
					BUG_ON(!pages);
				}
			}

			/* 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(&fsc->writeback_count);
			if (writeback_stat > CONGESTION_ON_THRESH(
				    fsc->mount_options->congestion_kb)) {
				set_bdi_congested(&fsc->backing_dev_info,
						  BLK_RW_ASYNC);
			}

			set_page_writeback(page);
			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;
		}

		/* Format the osd request message and submit the write */
		offset = page_offset(pages[0]);
		len = (u64)locked_pages << PAGE_CACHE_SHIFT;
		if (snap_size == -1) {
			len = min(len, (u64)i_size_read(inode) - offset);
			 /* writepages_finish() clears writeback pages
			  * according to the data length, so make sure
			  * data length covers all locked pages */
			len = max(len, 1 +
				((u64)(locked_pages - 1) << PAGE_CACHE_SHIFT));
		} else {
			len = min(len, snap_size - offset);
		}
		dout("writepages got %d pages at %llu~%llu\n",
		     locked_pages, offset, len);

		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
							!!pool, false);

		pages = NULL;	/* request message now owns the pages array */
		pool = NULL;

		/* Update the write op length in case we changed it */

		osd_req_op_extent_update(req, 0, len);

		vino = ceph_vino(inode);
		ceph_osdc_build_request(req, offset, snapc, vino.snap,
					&inode->i_mtime);

		rc = ceph_osdc_start_request(&fsc->client->osdc, req, true);
		BUG_ON(rc);
		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);
	ceph_put_snap_context(snapc);
	dout("writepages done, rc = %d\n", rc);
	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_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	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);

	snapc = page_snap_context(page);
	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);

		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 (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. */
	r = readpage_nounlock(file, page);
	if (r < 0)
		goto fail_nosnap;
	goto retry_locked;
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_inode(file);
	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);
		if (r < 0)
			page_cache_release(page);
		else
			*pagep = 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
 */
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_inode(file);
	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);
	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(struct kiocb *iocb, struct iov_iter *iter,
			      loff_t pos)
{
	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
 */
static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct inode *inode = file_inode(vma->vm_file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_file_info *fi = vma->vm_file->private_data;
	struct page *pinned_page = NULL;
	loff_t off = vmf->pgoff << PAGE_CACHE_SHIFT;
	int want, got, ret;

	dout("filemap_fault %p %llx.%llx %llu~%zd trying to get caps\n",
	     inode, ceph_vinop(inode), off, (size_t)PAGE_CACHE_SIZE);
	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_CACHE;
	while (1) {
		got = 0;
		ret = ceph_get_caps(ci, CEPH_CAP_FILE_RD, want,
				    -1, &got, &pinned_page);
		if (ret == 0)
			break;
		if (ret != -ERESTARTSYS) {
			WARN_ON(1);
			return VM_FAULT_SIGBUS;
		}
	}
	dout("filemap_fault %p %llu~%zd got cap refs on %s\n",
	     inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got));

	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
	    ci->i_inline_version == CEPH_INLINE_NONE)
		ret = filemap_fault(vma, vmf);
	else
		ret = -EAGAIN;

	dout("filemap_fault %p %llu~%zd dropping cap refs on %s ret %d\n",
	     inode, off, (size_t)PAGE_CACHE_SIZE, ceph_cap_string(got), ret);
	if (pinned_page)
		page_cache_release(pinned_page);
	ceph_put_cap_refs(ci, got);

	if (ret != -EAGAIN)
		return ret;

	/* read inline data */
	if (off >= PAGE_CACHE_SIZE) {
		/* does not support inline data > PAGE_SIZE */
		ret = VM_FAULT_SIGBUS;
	} else {
		int ret1;
		struct address_space *mapping = inode->i_mapping;
		struct page *page = find_or_create_page(mapping, 0,
						mapping_gfp_mask(mapping) &
						~__GFP_FS);
		if (!page) {
			ret = VM_FAULT_OOM;
			goto out;
		}
		ret1 = __ceph_do_getattr(inode, page,
					 CEPH_STAT_CAP_INLINE_DATA, true);
		if (ret1 < 0 || off >= i_size_read(inode)) {
			unlock_page(page);
			page_cache_release(page);
			ret = VM_FAULT_SIGBUS;
			goto out;
		}
		if (ret1 < PAGE_CACHE_SIZE)
			zero_user_segment(page, ret1, PAGE_CACHE_SIZE);
		else
			flush_dcache_page(page);
		SetPageUptodate(page);
		vmf->page = page;
		ret = VM_FAULT_MAJOR | VM_FAULT_LOCKED;
	}
out:
	dout("filemap_fault %p %llu~%zd read inline data ret %d\n",
	     inode, off, (size_t)PAGE_CACHE_SIZE, ret);
	return ret;
}

/*
 * Reuse write_begin here for simplicity.
 */
static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct inode *inode = file_inode(vma->vm_file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_file_info *fi = vma->vm_file->private_data;
	struct ceph_cap_flush *prealloc_cf;
	struct page *page = vmf->page;
	loff_t off = page_offset(page);
	loff_t size = i_size_read(inode);
	size_t len;
	int want, got, ret;

	prealloc_cf = ceph_alloc_cap_flush();
	if (!prealloc_cf)
		return VM_FAULT_SIGBUS;

	if (ci->i_inline_version != CEPH_INLINE_NONE) {
		struct page *locked_page = NULL;
		if (off == 0) {
			lock_page(page);
			locked_page = page;
		}
		ret = ceph_uninline_data(vma->vm_file, locked_page);
		if (locked_page)
			unlock_page(locked_page);
		if (ret < 0) {
			ret = VM_FAULT_SIGBUS;
			goto out_free;
		}
	}

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

	dout("page_mkwrite %p %llx.%llx %llu~%zd getting caps i_size %llu\n",
	     inode, ceph_vinop(inode), off, len, size);
	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_BUFFER;
	while (1) {
		got = 0;
		ret = ceph_get_caps(ci, CEPH_CAP_FILE_WR, want, off + len,
				    &got, NULL);
		if (ret == 0)
			break;
		if (ret != -ERESTARTSYS) {
			WARN_ON(1);
			ret = VM_FAULT_SIGBUS;
			goto out_free;
		}
	}
	dout("page_mkwrite %p %llu~%zd got cap refs on %s\n",
	     inode, off, len, ceph_cap_string(got));

	/* Update time before taking page lock */
	file_update_time(vma->vm_file);

	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);
		ret = VM_FAULT_LOCKED;
	} else {
		if (ret == -ENOMEM)
			ret = VM_FAULT_OOM;
		else
			ret = VM_FAULT_SIGBUS;
	}
out:
	if (ret != VM_FAULT_LOCKED)
		unlock_page(page);
	if (ret == VM_FAULT_LOCKED ||
	    ci->i_inline_version != CEPH_INLINE_NONE) {
		int dirty;
		spin_lock(&ci->i_ceph_lock);
		ci->i_inline_version = CEPH_INLINE_NONE;
		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
					       &prealloc_cf);
		spin_unlock(&ci->i_ceph_lock);
		if (dirty)
			__mark_inode_dirty(inode, dirty);
	}

	dout("page_mkwrite %p %llu~%zd dropping cap refs on %s ret %d\n",
	     inode, off, len, ceph_cap_string(got), ret);
	ceph_put_cap_refs(ci, got);
out_free:
	ceph_free_cap_flush(prealloc_cf);

	return ret;
}

void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
			   char	*data, size_t len)
{
	struct address_space *mapping = inode->i_mapping;
	struct page *page;

	if (locked_page) {
		page = locked_page;
	} else {
		if (i_size_read(inode) == 0)
			return;
		page = find_or_create_page(mapping, 0,
					   mapping_gfp_mask(mapping) & ~__GFP_FS);
		if (!page)
			return;
		if (PageUptodate(page)) {
			unlock_page(page);
			page_cache_release(page);
			return;
		}
	}

	dout("fill_inline_data %p %llx.%llx len %zu locked_page %p\n",
	     inode, ceph_vinop(inode), len, locked_page);

	if (len > 0) {
		void *kaddr = kmap_atomic(page);
		memcpy(kaddr, data, len);
		kunmap_atomic(kaddr);
	}

	if (page != locked_page) {
		if (len < PAGE_CACHE_SIZE)
			zero_user_segment(page, len, PAGE_CACHE_SIZE);
		else
			flush_dcache_page(page);

		SetPageUptodate(page);
		unlock_page(page);
		page_cache_release(page);
	}
}

int ceph_uninline_data(struct file *filp, struct page *locked_page)
{
	struct inode *inode = file_inode(filp);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_osd_request *req;
	struct page *page = NULL;
	u64 len, inline_version;
	int err = 0;
	bool from_pagecache = false;

	spin_lock(&ci->i_ceph_lock);
	inline_version = ci->i_inline_version;
	spin_unlock(&ci->i_ceph_lock);

	dout("uninline_data %p %llx.%llx inline_version %llu\n",
	     inode, ceph_vinop(inode), inline_version);

	if (inline_version == 1 || /* initial version, no data */
	    inline_version == CEPH_INLINE_NONE)
		goto out;

	if (locked_page) {
		page = locked_page;
		WARN_ON(!PageUptodate(page));
	} else if (ceph_caps_issued(ci) &
		   (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) {
		page = find_get_page(inode->i_mapping, 0);
		if (page) {
			if (PageUptodate(page)) {
				from_pagecache = true;
				lock_page(page);
			} else {
				page_cache_release(page);
				page = NULL;
			}
		}
	}

	if (page) {
		len = i_size_read(inode);
		if (len > PAGE_CACHE_SIZE)
			len = PAGE_CACHE_SIZE;
	} else {
		page = __page_cache_alloc(GFP_NOFS);
		if (!page) {
			err = -ENOMEM;
			goto out;
		}
		err = __ceph_do_getattr(inode, page,
					CEPH_STAT_CAP_INLINE_DATA, true);
		if (err < 0) {
			/* no inline data */
			if (err == -ENODATA)
				err = 0;
			goto out;
		}
		len = err;
	}

	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
				    ceph_vino(inode), 0, &len, 0, 1,
				    CEPH_OSD_OP_CREATE,
				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
				    ceph_empty_snapc, 0, 0, false);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}

	ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime);
	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
	if (!err)
		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
	ceph_osdc_put_request(req);
	if (err < 0)
		goto out;

	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
				    ceph_vino(inode), 0, &len, 1, 3,
				    CEPH_OSD_OP_WRITE,
				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
				    ceph_empty_snapc,
				    ci->i_truncate_seq, ci->i_truncate_size,
				    false);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}

	osd_req_op_extent_osd_data_pages(req, 1, &page, len, 0, false, false);

	{
		__le64 xattr_buf = cpu_to_le64(inline_version);
		err = osd_req_op_xattr_init(req, 0, CEPH_OSD_OP_CMPXATTR,
					    "inline_version", &xattr_buf,
					    sizeof(xattr_buf),
					    CEPH_OSD_CMPXATTR_OP_GT,
					    CEPH_OSD_CMPXATTR_MODE_U64);
		if (err)
			goto out_put;
	}

	{
		char xattr_buf[32];
		int xattr_len = snprintf(xattr_buf, sizeof(xattr_buf),
					 "%llu", inline_version);
		err = osd_req_op_xattr_init(req, 2, CEPH_OSD_OP_SETXATTR,
					    "inline_version",
					    xattr_buf, xattr_len, 0, 0);
		if (err)
			goto out_put;
	}

	ceph_osdc_build_request(req, 0, NULL, CEPH_NOSNAP, &inode->i_mtime);
	err = ceph_osdc_start_request(&fsc->client->osdc, req, false);
	if (!err)
		err = ceph_osdc_wait_request(&fsc->client->osdc, req);
out_put:
	ceph_osdc_put_request(req);
	if (err == -ECANCELED)
		err = 0;
out:
	if (page && page != locked_page) {
		if (from_pagecache) {
			unlock_page(page);
			page_cache_release(page);
		} else
			__free_pages(page, 0);
	}

	dout("uninline_data %p %llx.%llx inline_version %llu = %d\n",
	     inode, ceph_vinop(inode), inline_version, err);
	return err;
}

static const struct vm_operations_struct ceph_vmops = {
	.fault		= ceph_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;
	return 0;
}

enum {
	POOL_READ	= 1,
	POOL_WRITE	= 2,
};

static int __ceph_pool_perm_get(struct ceph_inode_info *ci, u32 pool)
{
	struct ceph_fs_client *fsc = ceph_inode_to_client(&ci->vfs_inode);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_osd_request *rd_req = NULL, *wr_req = NULL;
	struct rb_node **p, *parent;
	struct ceph_pool_perm *perm;
	struct page **pages;
	int err = 0, err2 = 0, have = 0;

	down_read(&mdsc->pool_perm_rwsem);
	p = &mdsc->pool_perm_tree.rb_node;
	while (*p) {
		perm = rb_entry(*p, struct ceph_pool_perm, node);
		if (pool < perm->pool)
			p = &(*p)->rb_left;
		else if (pool > perm->pool)
			p = &(*p)->rb_right;
		else {
			have = perm->perm;
			break;
		}
	}
	up_read(&mdsc->pool_perm_rwsem);
	if (*p)
		goto out;

	dout("__ceph_pool_perm_get pool %u no perm cached\n", pool);

	down_write(&mdsc->pool_perm_rwsem);
	parent = NULL;
	while (*p) {
		parent = *p;
		perm = rb_entry(parent, struct ceph_pool_perm, node);
		if (pool < perm->pool)
			p = &(*p)->rb_left;
		else if (pool > perm->pool)
			p = &(*p)->rb_right;
		else {
			have = perm->perm;
			break;
		}
	}
	if (*p) {
		up_write(&mdsc->pool_perm_rwsem);
		goto out;
	}

	rd_req = ceph_osdc_alloc_request(&fsc->client->osdc,
					 ceph_empty_snapc,
					 1, false, GFP_NOFS);
	if (!rd_req) {
		err = -ENOMEM;
		goto out_unlock;
	}

	rd_req->r_flags = CEPH_OSD_FLAG_READ;
	osd_req_op_init(rd_req, 0, CEPH_OSD_OP_STAT, 0);
	rd_req->r_base_oloc.pool = pool;
	snprintf(rd_req->r_base_oid.name, sizeof(rd_req->r_base_oid.name),
		 "%llx.00000000", ci->i_vino.ino);
	rd_req->r_base_oid.name_len = strlen(rd_req->r_base_oid.name);

	wr_req = ceph_osdc_alloc_request(&fsc->client->osdc,
					 ceph_empty_snapc,
					 1, false, GFP_NOFS);
	if (!wr_req) {
		err = -ENOMEM;
		goto out_unlock;
	}

	wr_req->r_flags = CEPH_OSD_FLAG_WRITE |
			  CEPH_OSD_FLAG_ACK | CEPH_OSD_FLAG_ONDISK;
	osd_req_op_init(wr_req, 0, CEPH_OSD_OP_CREATE, CEPH_OSD_OP_FLAG_EXCL);
	wr_req->r_base_oloc.pool = pool;
	wr_req->r_base_oid = rd_req->r_base_oid;

	/* one page should be large enough for STAT data */
	pages = ceph_alloc_page_vector(1, GFP_KERNEL);
	if (IS_ERR(pages)) {
		err = PTR_ERR(pages);
		goto out_unlock;
	}

	osd_req_op_raw_data_in_pages(rd_req, 0, pages, PAGE_SIZE,
				     0, false, true);
	ceph_osdc_build_request(rd_req, 0, NULL, CEPH_NOSNAP,
				&ci->vfs_inode.i_mtime);
	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);

	ceph_osdc_build_request(wr_req, 0, NULL, CEPH_NOSNAP,
				&ci->vfs_inode.i_mtime);
	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);

	if (!err)
		err = ceph_osdc_wait_request(&fsc->client->osdc, rd_req);
	if (!err2)
		err2 = ceph_osdc_wait_request(&fsc->client->osdc, wr_req);

	if (err >= 0 || err == -ENOENT)
		have |= POOL_READ;
	else if (err != -EPERM)
		goto out_unlock;

	if (err2 == 0 || err2 == -EEXIST)
		have |= POOL_WRITE;
	else if (err2 != -EPERM) {
		err = err2;
		goto out_unlock;
	}

	perm = kmalloc(sizeof(*perm), GFP_NOFS);
	if (!perm) {
		err = -ENOMEM;
		goto out_unlock;
	}

	perm->pool = pool;
	perm->perm = have;
	rb_link_node(&perm->node, parent, p);
	rb_insert_color(&perm->node, &mdsc->pool_perm_tree);
	err = 0;
out_unlock:
	up_write(&mdsc->pool_perm_rwsem);

	if (rd_req)
		ceph_osdc_put_request(rd_req);
	if (wr_req)
		ceph_osdc_put_request(wr_req);
out:
	if (!err)
		err = have;
	dout("__ceph_pool_perm_get pool %u result = %d\n", pool, err);
	return err;
}

int ceph_pool_perm_check(struct ceph_inode_info *ci, int need)
{
	u32 pool;
	int ret, flags;

	if (ceph_test_mount_opt(ceph_inode_to_client(&ci->vfs_inode),
				NOPOOLPERM))
		return 0;

	spin_lock(&ci->i_ceph_lock);
	flags = ci->i_ceph_flags;
	pool = ceph_file_layout_pg_pool(ci->i_layout);
	spin_unlock(&ci->i_ceph_lock);
check:
	if (flags & CEPH_I_POOL_PERM) {
		if ((need & CEPH_CAP_FILE_RD) && !(flags & CEPH_I_POOL_RD)) {
			dout("ceph_pool_perm_check pool %u no read perm\n",
			     pool);
			return -EPERM;
		}
		if ((need & CEPH_CAP_FILE_WR) && !(flags & CEPH_I_POOL_WR)) {
			dout("ceph_pool_perm_check pool %u no write perm\n",
			     pool);
			return -EPERM;
		}
		return 0;
	}

	ret = __ceph_pool_perm_get(ci, pool);
	if (ret < 0)
		return ret;

	flags = CEPH_I_POOL_PERM;
	if (ret & POOL_READ)
		flags |= CEPH_I_POOL_RD;
	if (ret & POOL_WRITE)
		flags |= CEPH_I_POOL_WR;

	spin_lock(&ci->i_ceph_lock);
	if (pool == ceph_file_layout_pg_pool(ci->i_layout)) {
		ci->i_ceph_flags = flags;
        } else {
		pool = ceph_file_layout_pg_pool(ci->i_layout);
		flags = ci->i_ceph_flags;
	}
	spin_unlock(&ci->i_ceph_lock);
	goto check;
}

void ceph_pool_perm_destroy(struct ceph_mds_client *mdsc)
{
	struct ceph_pool_perm *perm;
	struct rb_node *n;

	while (!RB_EMPTY_ROOT(&mdsc->pool_perm_tree)) {
		n = rb_first(&mdsc->pool_perm_tree);
		perm = rb_entry(n, struct ceph_pool_perm, node);
		rb_erase(n, &mdsc->pool_perm_tree);
		kfree(perm);
	}
}