summaryrefslogtreecommitdiff
path: root/fs/ceph/file.c
blob: 11929d2bb594c8d5f3d68c7a93946a8966da836f (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
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
// SPDX-License-Identifier: GPL-2.0
#include <linux/ceph/ceph_debug.h>
#include <linux/ceph/striper.h>

#include <linux/module.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/writeback.h>
#include <linux/falloc.h>
#include <linux/iversion.h>

#include "super.h"
#include "mds_client.h"
#include "cache.h"
#include "io.h"

static __le32 ceph_flags_sys2wire(u32 flags)
{
	u32 wire_flags = 0;

	switch (flags & O_ACCMODE) {
	case O_RDONLY:
		wire_flags |= CEPH_O_RDONLY;
		break;
	case O_WRONLY:
		wire_flags |= CEPH_O_WRONLY;
		break;
	case O_RDWR:
		wire_flags |= CEPH_O_RDWR;
		break;
	}

	flags &= ~O_ACCMODE;

#define ceph_sys2wire(a) if (flags & a) { wire_flags |= CEPH_##a; flags &= ~a; }

	ceph_sys2wire(O_CREAT);
	ceph_sys2wire(O_EXCL);
	ceph_sys2wire(O_TRUNC);
	ceph_sys2wire(O_DIRECTORY);
	ceph_sys2wire(O_NOFOLLOW);

#undef ceph_sys2wire

	if (flags)
		dout("unused open flags: %x\n", flags);

	return cpu_to_le32(wire_flags);
}

/*
 * Ceph file operations
 *
 * Implement basic open/close functionality, and implement
 * read/write.
 *
 * We implement three modes of file I/O:
 *  - buffered uses the generic_file_aio_{read,write} helpers
 *
 *  - synchronous is used when there is multi-client read/write
 *    sharing, avoids the page cache, and synchronously waits for an
 *    ack from the OSD.
 *
 *  - direct io takes the variant of the sync path that references
 *    user pages directly.
 *
 * fsync() flushes and waits on dirty pages, but just queues metadata
 * for writeback: since the MDS can recover size and mtime there is no
 * need to wait for MDS acknowledgement.
 */

/*
 * How many pages to get in one call to iov_iter_get_pages().  This
 * determines the size of the on-stack array used as a buffer.
 */
#define ITER_GET_BVECS_PAGES	64

static ssize_t __iter_get_bvecs(struct iov_iter *iter, size_t maxsize,
				struct bio_vec *bvecs)
{
	size_t size = 0;
	int bvec_idx = 0;

	if (maxsize > iov_iter_count(iter))
		maxsize = iov_iter_count(iter);

	while (size < maxsize) {
		struct page *pages[ITER_GET_BVECS_PAGES];
		ssize_t bytes;
		size_t start;
		int idx = 0;

		bytes = iov_iter_get_pages(iter, pages, maxsize - size,
					   ITER_GET_BVECS_PAGES, &start);
		if (bytes < 0)
			return size ?: bytes;

		iov_iter_advance(iter, bytes);
		size += bytes;

		for ( ; bytes; idx++, bvec_idx++) {
			struct bio_vec bv = {
				.bv_page = pages[idx],
				.bv_len = min_t(int, bytes, PAGE_SIZE - start),
				.bv_offset = start,
			};

			bvecs[bvec_idx] = bv;
			bytes -= bv.bv_len;
			start = 0;
		}
	}

	return size;
}

/*
 * iov_iter_get_pages() only considers one iov_iter segment, no matter
 * what maxsize or maxpages are given.  For ITER_BVEC that is a single
 * page.
 *
 * Attempt to get up to @maxsize bytes worth of pages from @iter.
 * Return the number of bytes in the created bio_vec array, or an error.
 */
static ssize_t iter_get_bvecs_alloc(struct iov_iter *iter, size_t maxsize,
				    struct bio_vec **bvecs, int *num_bvecs)
{
	struct bio_vec *bv;
	size_t orig_count = iov_iter_count(iter);
	ssize_t bytes;
	int npages;

	iov_iter_truncate(iter, maxsize);
	npages = iov_iter_npages(iter, INT_MAX);
	iov_iter_reexpand(iter, orig_count);

	/*
	 * __iter_get_bvecs() may populate only part of the array -- zero it
	 * out.
	 */
	bv = kvmalloc_array(npages, sizeof(*bv), GFP_KERNEL | __GFP_ZERO);
	if (!bv)
		return -ENOMEM;

	bytes = __iter_get_bvecs(iter, maxsize, bv);
	if (bytes < 0) {
		/*
		 * No pages were pinned -- just free the array.
		 */
		kvfree(bv);
		return bytes;
	}

	*bvecs = bv;
	*num_bvecs = npages;
	return bytes;
}

static void put_bvecs(struct bio_vec *bvecs, int num_bvecs, bool should_dirty)
{
	int i;

	for (i = 0; i < num_bvecs; i++) {
		if (bvecs[i].bv_page) {
			if (should_dirty)
				set_page_dirty_lock(bvecs[i].bv_page);
			put_page(bvecs[i].bv_page);
		}
	}
	kvfree(bvecs);
}

/*
 * Prepare an open request.  Preallocate ceph_cap to avoid an
 * inopportune ENOMEM later.
 */
static struct ceph_mds_request *
prepare_open_request(struct super_block *sb, int flags, int create_mode)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	int want_auth = USE_ANY_MDS;
	int op = (flags & O_CREAT) ? CEPH_MDS_OP_CREATE : CEPH_MDS_OP_OPEN;

	if (flags & (O_WRONLY|O_RDWR|O_CREAT|O_TRUNC))
		want_auth = USE_AUTH_MDS;

	req = ceph_mdsc_create_request(mdsc, op, want_auth);
	if (IS_ERR(req))
		goto out;
	req->r_fmode = ceph_flags_to_mode(flags);
	req->r_args.open.flags = ceph_flags_sys2wire(flags);
	req->r_args.open.mode = cpu_to_le32(create_mode);
out:
	return req;
}

static int ceph_init_file_info(struct inode *inode, struct file *file,
					int fmode, bool isdir)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_file_info *fi;

	dout("%s %p %p 0%o (%s)\n", __func__, inode, file,
			inode->i_mode, isdir ? "dir" : "regular");
	BUG_ON(inode->i_fop->release != ceph_release);

	if (isdir) {
		struct ceph_dir_file_info *dfi =
			kmem_cache_zalloc(ceph_dir_file_cachep, GFP_KERNEL);
		if (!dfi) {
			ceph_put_fmode(ci, fmode); /* clean up */
			return -ENOMEM;
		}

		file->private_data = dfi;
		fi = &dfi->file_info;
		dfi->next_offset = 2;
		dfi->readdir_cache_idx = -1;
	} else {
		fi = kmem_cache_zalloc(ceph_file_cachep, GFP_KERNEL);
		if (!fi) {
			ceph_put_fmode(ci, fmode); /* clean up */
			return -ENOMEM;
		}

		file->private_data = fi;
	}

	fi->fmode = fmode;
	spin_lock_init(&fi->rw_contexts_lock);
	INIT_LIST_HEAD(&fi->rw_contexts);
	fi->meta_err = errseq_sample(&ci->i_meta_err);
	fi->filp_gen = READ_ONCE(ceph_inode_to_client(inode)->filp_gen);

	return 0;
}

/*
 * initialize private struct file data.
 * if we fail, clean up by dropping fmode reference on the ceph_inode
 */
static int ceph_init_file(struct inode *inode, struct file *file, int fmode)
{
	int ret = 0;

	switch (inode->i_mode & S_IFMT) {
	case S_IFREG:
		ceph_fscache_register_inode_cookie(inode);
		ceph_fscache_file_set_cookie(inode, file);
		/* fall through */
	case S_IFDIR:
		ret = ceph_init_file_info(inode, file, fmode,
						S_ISDIR(inode->i_mode));
		if (ret)
			return ret;
		break;

	case S_IFLNK:
		dout("init_file %p %p 0%o (symlink)\n", inode, file,
		     inode->i_mode);
		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
		break;

	default:
		dout("init_file %p %p 0%o (special)\n", inode, file,
		     inode->i_mode);
		/*
		 * we need to drop the open ref now, since we don't
		 * have .release set to ceph_release.
		 */
		ceph_put_fmode(ceph_inode(inode), fmode); /* clean up */
		BUG_ON(inode->i_fop->release == ceph_release);

		/* call the proper open fop */
		ret = inode->i_fop->open(inode, file);
	}
	return ret;
}

/*
 * try renew caps after session gets killed.
 */
int ceph_renew_caps(struct inode *inode)
{
	struct ceph_mds_client *mdsc = ceph_sb_to_client(inode->i_sb)->mdsc;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_mds_request *req;
	int err, flags, wanted;

	spin_lock(&ci->i_ceph_lock);
	wanted = __ceph_caps_file_wanted(ci);
	if (__ceph_is_any_real_caps(ci) &&
	    (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
		int issued = __ceph_caps_issued(ci, NULL);
		spin_unlock(&ci->i_ceph_lock);
		dout("renew caps %p want %s issued %s updating mds_wanted\n",
		     inode, ceph_cap_string(wanted), ceph_cap_string(issued));
		ceph_check_caps(ci, 0, NULL);
		return 0;
	}
	spin_unlock(&ci->i_ceph_lock);

	flags = 0;
	if ((wanted & CEPH_CAP_FILE_RD) && (wanted & CEPH_CAP_FILE_WR))
		flags = O_RDWR;
	else if (wanted & CEPH_CAP_FILE_RD)
		flags = O_RDONLY;
	else if (wanted & CEPH_CAP_FILE_WR)
		flags = O_WRONLY;
#ifdef O_LAZY
	if (wanted & CEPH_CAP_FILE_LAZYIO)
		flags |= O_LAZY;
#endif

	req = prepare_open_request(inode->i_sb, flags, 0);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}

	req->r_inode = inode;
	ihold(inode);
	req->r_num_caps = 1;
	req->r_fmode = -1;

	err = ceph_mdsc_do_request(mdsc, NULL, req);
	ceph_mdsc_put_request(req);
out:
	dout("renew caps %p open result=%d\n", inode, err);
	return err < 0 ? err : 0;
}

/*
 * If we already have the requisite capabilities, we can satisfy
 * the open request locally (no need to request new caps from the
 * MDS).  We do, however, need to inform the MDS (asynchronously)
 * if our wanted caps set expands.
 */
int ceph_open(struct inode *inode, struct file *file)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_sb_to_client(inode->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	struct ceph_file_info *fi = file->private_data;
	int err;
	int flags, fmode, wanted;

	if (fi) {
		dout("open file %p is already opened\n", file);
		return 0;
	}

	/* filter out O_CREAT|O_EXCL; vfs did that already.  yuck. */
	flags = file->f_flags & ~(O_CREAT|O_EXCL);
	if (S_ISDIR(inode->i_mode))
		flags = O_DIRECTORY;  /* mds likes to know */

	dout("open inode %p ino %llx.%llx file %p flags %d (%d)\n", inode,
	     ceph_vinop(inode), file, flags, file->f_flags);
	fmode = ceph_flags_to_mode(flags);
	wanted = ceph_caps_for_mode(fmode);

	/* snapped files are read-only */
	if (ceph_snap(inode) != CEPH_NOSNAP && (file->f_mode & FMODE_WRITE))
		return -EROFS;

	/* trivially open snapdir */
	if (ceph_snap(inode) == CEPH_SNAPDIR) {
		spin_lock(&ci->i_ceph_lock);
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&ci->i_ceph_lock);
		return ceph_init_file(inode, file, fmode);
	}

	/*
	 * No need to block if we have caps on the auth MDS (for
	 * write) or any MDS (for read).  Update wanted set
	 * asynchronously.
	 */
	spin_lock(&ci->i_ceph_lock);
	if (__ceph_is_any_real_caps(ci) &&
	    (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
		int mds_wanted = __ceph_caps_mds_wanted(ci, true);
		int issued = __ceph_caps_issued(ci, NULL);

		dout("open %p fmode %d want %s issued %s using existing\n",
		     inode, fmode, ceph_cap_string(wanted),
		     ceph_cap_string(issued));
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&ci->i_ceph_lock);

		/* adjust wanted? */
		if ((issued & wanted) != wanted &&
		    (mds_wanted & wanted) != wanted &&
		    ceph_snap(inode) != CEPH_SNAPDIR)
			ceph_check_caps(ci, 0, NULL);

		return ceph_init_file(inode, file, fmode);
	} else if (ceph_snap(inode) != CEPH_NOSNAP &&
		   (ci->i_snap_caps & wanted) == wanted) {
		__ceph_get_fmode(ci, fmode);
		spin_unlock(&ci->i_ceph_lock);
		return ceph_init_file(inode, file, fmode);
	}

	spin_unlock(&ci->i_ceph_lock);

	dout("open fmode %d wants %s\n", fmode, ceph_cap_string(wanted));
	req = prepare_open_request(inode->i_sb, flags, 0);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out;
	}
	req->r_inode = inode;
	ihold(inode);

	req->r_num_caps = 1;
	err = ceph_mdsc_do_request(mdsc, NULL, req);
	if (!err)
		err = ceph_init_file(inode, file, req->r_fmode);
	ceph_mdsc_put_request(req);
	dout("open result=%d on %llx.%llx\n", err, ceph_vinop(inode));
out:
	return err;
}


/*
 * Do a lookup + open with a single request.  If we get a non-existent
 * file or symlink, return 1 so the VFS can retry.
 */
int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
		     struct file *file, unsigned flags, umode_t mode)
{
	struct ceph_fs_client *fsc = ceph_sb_to_client(dir->i_sb);
	struct ceph_mds_client *mdsc = fsc->mdsc;
	struct ceph_mds_request *req;
	struct dentry *dn;
	struct ceph_acl_sec_ctx as_ctx = {};
	int mask;
	int err;

	dout("atomic_open %p dentry %p '%pd' %s flags %d mode 0%o\n",
	     dir, dentry, dentry,
	     d_unhashed(dentry) ? "unhashed" : "hashed", flags, mode);

	if (dentry->d_name.len > NAME_MAX)
		return -ENAMETOOLONG;

	if (flags & O_CREAT) {
		if (ceph_quota_is_max_files_exceeded(dir))
			return -EDQUOT;
		err = ceph_pre_init_acls(dir, &mode, &as_ctx);
		if (err < 0)
			return err;
		err = ceph_security_init_secctx(dentry, mode, &as_ctx);
		if (err < 0)
			goto out_ctx;
	} else if (!d_in_lookup(dentry)) {
		/* If it's not being looked up, it's negative */
		return -ENOENT;
	}

	/* do the open */
	req = prepare_open_request(dir->i_sb, flags, mode);
	if (IS_ERR(req)) {
		err = PTR_ERR(req);
		goto out_ctx;
	}
	req->r_dentry = dget(dentry);
	req->r_num_caps = 2;
	if (flags & O_CREAT) {
		req->r_dentry_drop = CEPH_CAP_FILE_SHARED | CEPH_CAP_AUTH_EXCL;
		req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
		if (as_ctx.pagelist) {
			req->r_pagelist = as_ctx.pagelist;
			as_ctx.pagelist = NULL;
		}
	}

       mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
       if (ceph_security_xattr_wanted(dir))
               mask |= CEPH_CAP_XATTR_SHARED;
       req->r_args.open.mask = cpu_to_le32(mask);

	req->r_parent = dir;
	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
	err = ceph_mdsc_do_request(mdsc,
				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
				   req);
	err = ceph_handle_snapdir(req, dentry, err);
	if (err)
		goto out_req;

	if ((flags & O_CREAT) && !req->r_reply_info.head->is_dentry)
		err = ceph_handle_notrace_create(dir, dentry);

	if (d_in_lookup(dentry)) {
		dn = ceph_finish_lookup(req, dentry, err);
		if (IS_ERR(dn))
			err = PTR_ERR(dn);
	} else {
		/* we were given a hashed negative dentry */
		dn = NULL;
	}
	if (err)
		goto out_req;
	if (dn || d_really_is_negative(dentry) || d_is_symlink(dentry)) {
		/* make vfs retry on splice, ENOENT, or symlink */
		dout("atomic_open finish_no_open on dn %p\n", dn);
		err = finish_no_open(file, dn);
	} else {
		dout("atomic_open finish_open on dn %p\n", dn);
		if (req->r_op == CEPH_MDS_OP_CREATE && req->r_reply_info.has_create_ino) {
			ceph_init_inode_acls(d_inode(dentry), &as_ctx);
			file->f_mode |= FMODE_CREATED;
		}
		err = finish_open(file, dentry, ceph_open);
	}
out_req:
	if (!req->r_err && req->r_target_inode)
		ceph_put_fmode(ceph_inode(req->r_target_inode), req->r_fmode);
	ceph_mdsc_put_request(req);
out_ctx:
	ceph_release_acl_sec_ctx(&as_ctx);
	dout("atomic_open result=%d\n", err);
	return err;
}

int ceph_release(struct inode *inode, struct file *file)
{
	struct ceph_inode_info *ci = ceph_inode(inode);

	if (S_ISDIR(inode->i_mode)) {
		struct ceph_dir_file_info *dfi = file->private_data;
		dout("release inode %p dir file %p\n", inode, file);
		WARN_ON(!list_empty(&dfi->file_info.rw_contexts));

		ceph_put_fmode(ci, dfi->file_info.fmode);

		if (dfi->last_readdir)
			ceph_mdsc_put_request(dfi->last_readdir);
		kfree(dfi->last_name);
		kfree(dfi->dir_info);
		kmem_cache_free(ceph_dir_file_cachep, dfi);
	} else {
		struct ceph_file_info *fi = file->private_data;
		dout("release inode %p regular file %p\n", inode, file);
		WARN_ON(!list_empty(&fi->rw_contexts));

		ceph_put_fmode(ci, fi->fmode);
		kmem_cache_free(ceph_file_cachep, fi);
	}

	/* wake up anyone waiting for caps on this inode */
	wake_up_all(&ci->i_cap_wq);
	return 0;
}

enum {
	HAVE_RETRIED = 1,
	CHECK_EOF =    2,
	READ_INLINE =  3,
};

/*
 * Completely synchronous read and write methods.  Direct from __user
 * buffer to osd, or directly to user pages (if O_DIRECT).
 *
 * If the read spans object boundary, just do multiple reads.  (That's not
 * atomic, but good enough for now.)
 *
 * If we get a short result from the OSD, check against i_size; we need to
 * only return a short read to the caller if we hit EOF.
 */
static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to,
			      int *retry_op)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_osd_client *osdc = &fsc->client->osdc;
	ssize_t ret;
	u64 off = iocb->ki_pos;
	u64 len = iov_iter_count(to);

	dout("sync_read on file %p %llu~%u %s\n", file, off, (unsigned)len,
	     (file->f_flags & O_DIRECT) ? "O_DIRECT" : "");

	if (!len)
		return 0;
	/*
	 * flush any page cache pages in this range.  this
	 * will make concurrent normal and sync io slow,
	 * but it will at least behave sensibly when they are
	 * in sequence.
	 */
	ret = filemap_write_and_wait_range(inode->i_mapping,
					   off, off + len - 1);
	if (ret < 0)
		return ret;

	ret = 0;
	while ((len = iov_iter_count(to)) > 0) {
		struct ceph_osd_request *req;
		struct page **pages;
		int num_pages;
		size_t page_off;
		u64 i_size;
		bool more;

		req = ceph_osdc_new_request(osdc, &ci->i_layout,
					ci->i_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)) {
			ret = PTR_ERR(req);
			break;
		}

		more = len < iov_iter_count(to);

		if (unlikely(iov_iter_is_pipe(to))) {
			ret = iov_iter_get_pages_alloc(to, &pages, len,
						       &page_off);
			if (ret <= 0) {
				ceph_osdc_put_request(req);
				ret = -ENOMEM;
				break;
			}
			num_pages = DIV_ROUND_UP(ret + page_off, PAGE_SIZE);
			if (ret < len) {
				len = ret;
				osd_req_op_extent_update(req, 0, len);
				more = false;
			}
		} else {
			num_pages = calc_pages_for(off, len);
			page_off = off & ~PAGE_MASK;
			pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
			if (IS_ERR(pages)) {
				ceph_osdc_put_request(req);
				ret = PTR_ERR(pages);
				break;
			}
		}

		osd_req_op_extent_osd_data_pages(req, 0, pages, len, page_off,
						 false, false);
		ret = ceph_osdc_start_request(osdc, req, false);
		if (!ret)
			ret = ceph_osdc_wait_request(osdc, req);
		ceph_osdc_put_request(req);

		i_size = i_size_read(inode);
		dout("sync_read %llu~%llu got %zd i_size %llu%s\n",
		     off, len, ret, i_size, (more ? " MORE" : ""));

		if (ret == -ENOENT)
			ret = 0;
		if (ret >= 0 && ret < len && (off + ret < i_size)) {
			int zlen = min(len - ret, i_size - off - ret);
			int zoff = page_off + ret;
			dout("sync_read zero gap %llu~%llu\n",
                             off + ret, off + ret + zlen);
			ceph_zero_page_vector_range(zoff, zlen, pages);
			ret += zlen;
		}

		if (unlikely(iov_iter_is_pipe(to))) {
			if (ret > 0) {
				iov_iter_advance(to, ret);
				off += ret;
			} else {
				iov_iter_advance(to, 0);
			}
			ceph_put_page_vector(pages, num_pages, false);
		} else {
			int idx = 0;
			size_t left = ret > 0 ? ret : 0;
			while (left > 0) {
				size_t len, copied;
				page_off = off & ~PAGE_MASK;
				len = min_t(size_t, left, PAGE_SIZE - page_off);
				copied = copy_page_to_iter(pages[idx++],
							   page_off, len, to);
				off += copied;
				left -= copied;
				if (copied < len) {
					ret = -EFAULT;
					break;
				}
			}
			ceph_release_page_vector(pages, num_pages);
		}

		if (ret < 0) {
			if (ret == -EBLACKLISTED)
				fsc->blacklisted = true;
			break;
		}

		if (off >= i_size || !more)
			break;
	}

	if (off > iocb->ki_pos) {
		if (ret >= 0 &&
		    iov_iter_count(to) > 0 && off >= i_size_read(inode))
			*retry_op = CHECK_EOF;
		ret = off - iocb->ki_pos;
		iocb->ki_pos = off;
	}

	dout("sync_read result %zd retry_op %d\n", ret, *retry_op);
	return ret;
}

struct ceph_aio_request {
	struct kiocb *iocb;
	size_t total_len;
	bool write;
	bool should_dirty;
	int error;
	struct list_head osd_reqs;
	unsigned num_reqs;
	atomic_t pending_reqs;
	struct timespec64 mtime;
	struct ceph_cap_flush *prealloc_cf;
};

struct ceph_aio_work {
	struct work_struct work;
	struct ceph_osd_request *req;
};

static void ceph_aio_retry_work(struct work_struct *work);

static void ceph_aio_complete(struct inode *inode,
			      struct ceph_aio_request *aio_req)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	int ret;

	if (!atomic_dec_and_test(&aio_req->pending_reqs))
		return;

	if (aio_req->iocb->ki_flags & IOCB_DIRECT)
		inode_dio_end(inode);

	ret = aio_req->error;
	if (!ret)
		ret = aio_req->total_len;

	dout("ceph_aio_complete %p rc %d\n", inode, ret);

	if (ret >= 0 && aio_req->write) {
		int dirty;

		loff_t endoff = aio_req->iocb->ki_pos + aio_req->total_len;
		if (endoff > i_size_read(inode)) {
			if (ceph_inode_set_size(inode, endoff))
				ceph_check_caps(ci, CHECK_CAPS_AUTHONLY, NULL);
		}

		spin_lock(&ci->i_ceph_lock);
		ci->i_inline_version = CEPH_INLINE_NONE;
		dirty = __ceph_mark_dirty_caps(ci, CEPH_CAP_FILE_WR,
					       &aio_req->prealloc_cf);
		spin_unlock(&ci->i_ceph_lock);
		if (dirty)
			__mark_inode_dirty(inode, dirty);

	}

	ceph_put_cap_refs(ci, (aio_req->write ? CEPH_CAP_FILE_WR :
						CEPH_CAP_FILE_RD));

	aio_req->iocb->ki_complete(aio_req->iocb, ret, 0);

	ceph_free_cap_flush(aio_req->prealloc_cf);
	kfree(aio_req);
}

static void ceph_aio_complete_req(struct ceph_osd_request *req)
{
	int rc = req->r_result;
	struct inode *inode = req->r_inode;
	struct ceph_aio_request *aio_req = req->r_priv;
	struct ceph_osd_data *osd_data = osd_req_op_extent_osd_data(req, 0);

	BUG_ON(osd_data->type != CEPH_OSD_DATA_TYPE_BVECS);
	BUG_ON(!osd_data->num_bvecs);

	dout("ceph_aio_complete_req %p rc %d bytes %u\n",
	     inode, rc, osd_data->bvec_pos.iter.bi_size);

	if (rc == -EOLDSNAPC) {
		struct ceph_aio_work *aio_work;
		BUG_ON(!aio_req->write);

		aio_work = kmalloc(sizeof(*aio_work), GFP_NOFS);
		if (aio_work) {
			INIT_WORK(&aio_work->work, ceph_aio_retry_work);
			aio_work->req = req;
			queue_work(ceph_inode_to_client(inode)->inode_wq,
				   &aio_work->work);
			return;
		}
		rc = -ENOMEM;
	} else if (!aio_req->write) {
		if (rc == -ENOENT)
			rc = 0;
		if (rc >= 0 && osd_data->bvec_pos.iter.bi_size > rc) {
			struct iov_iter i;
			int zlen = osd_data->bvec_pos.iter.bi_size - rc;

			/*
			 * If read is satisfied by single OSD request,
			 * it can pass EOF. Otherwise read is within
			 * i_size.
			 */
			if (aio_req->num_reqs == 1) {
				loff_t i_size = i_size_read(inode);
				loff_t endoff = aio_req->iocb->ki_pos + rc;
				if (endoff < i_size)
					zlen = min_t(size_t, zlen,
						     i_size - endoff);
				aio_req->total_len = rc + zlen;
			}

			iov_iter_bvec(&i, READ, osd_data->bvec_pos.bvecs,
				      osd_data->num_bvecs,
				      osd_data->bvec_pos.iter.bi_size);
			iov_iter_advance(&i, rc);
			iov_iter_zero(zlen, &i);
		}
	}

	put_bvecs(osd_data->bvec_pos.bvecs, osd_data->num_bvecs,
		  aio_req->should_dirty);
	ceph_osdc_put_request(req);

	if (rc < 0)
		cmpxchg(&aio_req->error, 0, rc);

	ceph_aio_complete(inode, aio_req);
	return;
}

static void ceph_aio_retry_work(struct work_struct *work)
{
	struct ceph_aio_work *aio_work =
		container_of(work, struct ceph_aio_work, work);
	struct ceph_osd_request *orig_req = aio_work->req;
	struct ceph_aio_request *aio_req = orig_req->r_priv;
	struct inode *inode = orig_req->r_inode;
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_snap_context *snapc;
	struct ceph_osd_request *req;
	int ret;

	spin_lock(&ci->i_ceph_lock);
	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);
	} else {
		BUG_ON(!ci->i_head_snapc);
		snapc = ceph_get_snap_context(ci->i_head_snapc);
	}
	spin_unlock(&ci->i_ceph_lock);

	req = ceph_osdc_alloc_request(orig_req->r_osdc, snapc, 1,
			false, GFP_NOFS);
	if (!req) {
		ret = -ENOMEM;
		req = orig_req;
		goto out;
	}

	req->r_flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
	ceph_oloc_copy(&req->r_base_oloc, &orig_req->r_base_oloc);
	ceph_oid_copy(&req->r_base_oid, &orig_req->r_base_oid);

	req->r_ops[0] = orig_req->r_ops[0];

	req->r_mtime = aio_req->mtime;
	req->r_data_offset = req->r_ops[0].extent.offset;

	ret = ceph_osdc_alloc_messages(req, GFP_NOFS);
	if (ret) {
		ceph_osdc_put_request(req);
		req = orig_req;
		goto out;
	}

	ceph_osdc_put_request(orig_req);

	req->r_callback = ceph_aio_complete_req;
	req->r_inode = inode;
	req->r_priv = aio_req;

	ret = ceph_osdc_start_request(req->r_osdc, req, false);
out:
	if (ret < 0) {
		req->r_result = ret;
		ceph_aio_complete_req(req);
	}

	ceph_put_snap_context(snapc);
	kfree(aio_work);
}

static ssize_t
ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
		       struct ceph_snap_context *snapc,
		       struct ceph_cap_flush **pcf)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_vino vino;
	struct ceph_osd_request *req;
	struct bio_vec *bvecs;
	struct ceph_aio_request *aio_req = NULL;
	int num_pages = 0;
	int flags;
	int ret = 0;
	struct timespec64 mtime = current_time(inode);
	size_t count = iov_iter_count(iter);
	loff_t pos = iocb->ki_pos;
	bool write = iov_iter_rw(iter) == WRITE;
	bool should_dirty = !write && iter_is_iovec(iter);

	if (write && ceph_snap(file_inode(file)) != CEPH_NOSNAP)
		return -EROFS;

	dout("sync_direct_%s on file %p %lld~%u snapc %p seq %lld\n",
	     (write ? "write" : "read"), file, pos, (unsigned)count,
	     snapc, snapc ? snapc->seq : 0);

	if (write) {
		int ret2 = invalidate_inode_pages2_range(inode->i_mapping,
					pos >> PAGE_SHIFT,
					(pos + count - 1) >> PAGE_SHIFT);
		if (ret2 < 0)
			dout("invalidate_inode_pages2_range returned %d\n", ret2);

		flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;
	} else {
		flags = CEPH_OSD_FLAG_READ;
	}

	while (iov_iter_count(iter) > 0) {
		u64 size = iov_iter_count(iter);
		ssize_t len;

		if (write)
			size = min_t(u64, size, fsc->mount_options->wsize);
		else
			size = min_t(u64, size, fsc->mount_options->rsize);

		vino = ceph_vino(inode);
		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
					    vino, pos, &size, 0,
					    1,
					    write ? CEPH_OSD_OP_WRITE :
						    CEPH_OSD_OP_READ,
					    flags, snapc,
					    ci->i_truncate_seq,
					    ci->i_truncate_size,
					    false);
		if (IS_ERR(req)) {
			ret = PTR_ERR(req);
			break;
		}

		len = iter_get_bvecs_alloc(iter, size, &bvecs, &num_pages);
		if (len < 0) {
			ceph_osdc_put_request(req);
			ret = len;
			break;
		}
		if (len != size)
			osd_req_op_extent_update(req, 0, len);

		/*
		 * To simplify error handling, allow AIO when IO within i_size
		 * or IO can be satisfied by single OSD request.
		 */
		if (pos == iocb->ki_pos && !is_sync_kiocb(iocb) &&
		    (len == count || pos + count <= i_size_read(inode))) {
			aio_req = kzalloc(sizeof(*aio_req), GFP_KERNEL);
			if (aio_req) {
				aio_req->iocb = iocb;
				aio_req->write = write;
				aio_req->should_dirty = should_dirty;
				INIT_LIST_HEAD(&aio_req->osd_reqs);
				if (write) {
					aio_req->mtime = mtime;
					swap(aio_req->prealloc_cf, *pcf);
				}
			}
			/* ignore error */
		}

		if (write) {
			/*
			 * throw out any page cache pages in this range. this
			 * may block.
			 */
			truncate_inode_pages_range(inode->i_mapping, pos,
						   PAGE_ALIGN(pos + len) - 1);

			req->r_mtime = mtime;
		}

		osd_req_op_extent_osd_data_bvecs(req, 0, bvecs, num_pages, len);

		if (aio_req) {
			aio_req->total_len += len;
			aio_req->num_reqs++;
			atomic_inc(&aio_req->pending_reqs);

			req->r_callback = ceph_aio_complete_req;
			req->r_inode = inode;
			req->r_priv = aio_req;
			list_add_tail(&req->r_private_item, &aio_req->osd_reqs);

			pos += len;
			continue;
		}

		ret = ceph_osdc_start_request(req->r_osdc, req, false);
		if (!ret)
			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);

		size = i_size_read(inode);
		if (!write) {
			if (ret == -ENOENT)
				ret = 0;
			if (ret >= 0 && ret < len && pos + ret < size) {
				struct iov_iter i;
				int zlen = min_t(size_t, len - ret,
						 size - pos - ret);

				iov_iter_bvec(&i, READ, bvecs, num_pages, len);
				iov_iter_advance(&i, ret);
				iov_iter_zero(zlen, &i);
				ret += zlen;
			}
			if (ret >= 0)
				len = ret;
		}

		put_bvecs(bvecs, num_pages, should_dirty);
		ceph_osdc_put_request(req);
		if (ret < 0)
			break;

		pos += len;
		if (!write && pos >= size)
			break;

		if (write && pos > size) {
			if (ceph_inode_set_size(inode, pos))
				ceph_check_caps(ceph_inode(inode),
						CHECK_CAPS_AUTHONLY,
						NULL);
		}
	}

	if (aio_req) {
		LIST_HEAD(osd_reqs);

		if (aio_req->num_reqs == 0) {
			kfree(aio_req);
			return ret;
		}

		ceph_get_cap_refs(ci, write ? CEPH_CAP_FILE_WR :
					      CEPH_CAP_FILE_RD);

		list_splice(&aio_req->osd_reqs, &osd_reqs);
		inode_dio_begin(inode);
		while (!list_empty(&osd_reqs)) {
			req = list_first_entry(&osd_reqs,
					       struct ceph_osd_request,
					       r_private_item);
			list_del_init(&req->r_private_item);
			if (ret >= 0)
				ret = ceph_osdc_start_request(req->r_osdc,
							      req, false);
			if (ret < 0) {
				req->r_result = ret;
				ceph_aio_complete_req(req);
			}
		}
		return -EIOCBQUEUED;
	}

	if (ret != -EOLDSNAPC && pos > iocb->ki_pos) {
		ret = pos - iocb->ki_pos;
		iocb->ki_pos = pos;
	}
	return ret;
}

/*
 * Synchronous write, straight from __user pointer or user pages.
 *
 * If write spans object boundary, just do multiple writes.  (For a
 * correct atomic write, we should e.g. take write locks on all
 * objects, rollback on failure, etc.)
 */
static ssize_t
ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
		struct ceph_snap_context *snapc)
{
	struct file *file = iocb->ki_filp;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_vino vino;
	struct ceph_osd_request *req;
	struct page **pages;
	u64 len;
	int num_pages;
	int written = 0;
	int flags;
	int ret;
	bool check_caps = false;
	struct timespec64 mtime = current_time(inode);
	size_t count = iov_iter_count(from);

	if (ceph_snap(file_inode(file)) != CEPH_NOSNAP)
		return -EROFS;

	dout("sync_write on file %p %lld~%u snapc %p seq %lld\n",
	     file, pos, (unsigned)count, snapc, snapc->seq);

	ret = filemap_write_and_wait_range(inode->i_mapping,
					   pos, pos + count - 1);
	if (ret < 0)
		return ret;

	ret = invalidate_inode_pages2_range(inode->i_mapping,
					    pos >> PAGE_SHIFT,
					    (pos + count - 1) >> PAGE_SHIFT);
	if (ret < 0)
		dout("invalidate_inode_pages2_range returned %d\n", ret);

	flags = /* CEPH_OSD_FLAG_ORDERSNAP | */ CEPH_OSD_FLAG_WRITE;

	while ((len = iov_iter_count(from)) > 0) {
		size_t left;
		int n;

		vino = ceph_vino(inode);
		req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
					    vino, pos, &len, 0, 1,
					    CEPH_OSD_OP_WRITE, flags, snapc,
					    ci->i_truncate_seq,
					    ci->i_truncate_size,
					    false);
		if (IS_ERR(req)) {
			ret = PTR_ERR(req);
			break;
		}

		/*
		 * write from beginning of first page,
		 * regardless of io alignment
		 */
		num_pages = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;

		pages = ceph_alloc_page_vector(num_pages, GFP_KERNEL);
		if (IS_ERR(pages)) {
			ret = PTR_ERR(pages);
			goto out;
		}

		left = len;
		for (n = 0; n < num_pages; n++) {
			size_t plen = min_t(size_t, left, PAGE_SIZE);
			ret = copy_page_from_iter(pages[n], 0, plen, from);
			if (ret != plen) {
				ret = -EFAULT;
				break;
			}
			left -= ret;
		}

		if (ret < 0) {
			ceph_release_page_vector(pages, num_pages);
			goto out;
		}

		req->r_inode = inode;

		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
						false, true);

		req->r_mtime = mtime;
		ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
		if (!ret)
			ret = ceph_osdc_wait_request(&fsc->client->osdc, req);

out:
		ceph_osdc_put_request(req);
		if (ret != 0) {
			ceph_set_error_write(ci);
			break;
		}

		ceph_clear_error_write(ci);
		pos += len;
		written += len;
		if (pos > i_size_read(inode)) {
			check_caps = ceph_inode_set_size(inode, pos);
			if (check_caps)
				ceph_check_caps(ceph_inode(inode),
						CHECK_CAPS_AUTHONLY,
						NULL);
		}

	}

	if (ret != -EOLDSNAPC && written > 0) {
		ret = written;
		iocb->ki_pos = pos;
	}
	return ret;
}

/*
 * Wrap generic_file_aio_read with checks for cap bits on the inode.
 * Atomically grab references, so that those bits are not released
 * back to the MDS mid-read.
 *
 * Hmm, the sync read case isn't actually async... should it be?
 */
static ssize_t ceph_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *filp = iocb->ki_filp;
	struct ceph_file_info *fi = filp->private_data;
	size_t len = iov_iter_count(to);
	struct inode *inode = file_inode(filp);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct page *pinned_page = NULL;
	ssize_t ret;
	int want, got = 0;
	int retry_op = 0, read = 0;

again:
	dout("aio_read %p %llx.%llx %llu~%u trying to get caps on %p\n",
	     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len, inode);

	if (iocb->ki_flags & IOCB_DIRECT)
		ceph_start_io_direct(inode);
	else
		ceph_start_io_read(inode);

	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_CACHE;
	ret = ceph_get_caps(filp, CEPH_CAP_FILE_RD, want, -1,
			    &got, &pinned_page);
	if (ret < 0) {
		if (iocb->ki_flags & IOCB_DIRECT)
			ceph_end_io_direct(inode);
		else
			ceph_end_io_read(inode);
		return ret;
	}

	if ((got & (CEPH_CAP_FILE_CACHE|CEPH_CAP_FILE_LAZYIO)) == 0 ||
	    (iocb->ki_flags & IOCB_DIRECT) ||
	    (fi->flags & CEPH_F_SYNC)) {

		dout("aio_sync_read %p %llx.%llx %llu~%u got cap refs on %s\n",
		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
		     ceph_cap_string(got));

		if (ci->i_inline_version == CEPH_INLINE_NONE) {
			if (!retry_op && (iocb->ki_flags & IOCB_DIRECT)) {
				ret = ceph_direct_read_write(iocb, to,
							     NULL, NULL);
				if (ret >= 0 && ret < len)
					retry_op = CHECK_EOF;
			} else {
				ret = ceph_sync_read(iocb, to, &retry_op);
			}
		} else {
			retry_op = READ_INLINE;
		}
	} else {
		CEPH_DEFINE_RW_CONTEXT(rw_ctx, got);
		dout("aio_read %p %llx.%llx %llu~%u got cap refs on %s\n",
		     inode, ceph_vinop(inode), iocb->ki_pos, (unsigned)len,
		     ceph_cap_string(got));
		ceph_add_rw_context(fi, &rw_ctx);
		ret = generic_file_read_iter(iocb, to);
		ceph_del_rw_context(fi, &rw_ctx);
	}

	dout("aio_read %p %llx.%llx dropping cap refs on %s = %d\n",
	     inode, ceph_vinop(inode), ceph_cap_string(got), (int)ret);
	if (pinned_page) {
		put_page(pinned_page);
		pinned_page = NULL;
	}
	ceph_put_cap_refs(ci, got);

	if (iocb->ki_flags & IOCB_DIRECT)
		ceph_end_io_direct(inode);
	else
		ceph_end_io_read(inode);

	if (retry_op > HAVE_RETRIED && ret >= 0) {
		int statret;
		struct page *page = NULL;
		loff_t i_size;
		if (retry_op == READ_INLINE) {
			page = __page_cache_alloc(GFP_KERNEL);
			if (!page)
				return -ENOMEM;
		}

		statret = __ceph_do_getattr(inode, page,
					    CEPH_STAT_CAP_INLINE_DATA, !!page);
		if (statret < 0) {
			if (page)
				__free_page(page);
			if (statret == -ENODATA) {
				BUG_ON(retry_op != READ_INLINE);
				goto again;
			}
			return statret;
		}

		i_size = i_size_read(inode);
		if (retry_op == READ_INLINE) {
			BUG_ON(ret > 0 || read > 0);
			if (iocb->ki_pos < i_size &&
			    iocb->ki_pos < PAGE_SIZE) {
				loff_t end = min_t(loff_t, i_size,
						   iocb->ki_pos + len);
				end = min_t(loff_t, end, PAGE_SIZE);
				if (statret < end)
					zero_user_segment(page, statret, end);
				ret = copy_page_to_iter(page,
						iocb->ki_pos & ~PAGE_MASK,
						end - iocb->ki_pos, to);
				iocb->ki_pos += ret;
				read += ret;
			}
			if (iocb->ki_pos < i_size && read < len) {
				size_t zlen = min_t(size_t, len - read,
						    i_size - iocb->ki_pos);
				ret = iov_iter_zero(zlen, to);
				iocb->ki_pos += ret;
				read += ret;
			}
			__free_pages(page, 0);
			return read;
		}

		/* hit EOF or hole? */
		if (retry_op == CHECK_EOF && iocb->ki_pos < i_size &&
		    ret < len) {
			dout("sync_read hit hole, ppos %lld < size %lld"
			     ", reading more\n", iocb->ki_pos, i_size);

			read += ret;
			len -= ret;
			retry_op = HAVE_RETRIED;
			goto again;
		}
	}

	if (ret >= 0)
		ret += read;

	return ret;
}

/*
 * Take cap references to avoid releasing caps to MDS mid-write.
 *
 * If we are synchronous, and write with an old snap context, the OSD
 * may return EOLDSNAPC.  In that case, retry the write.. _after_
 * dropping our cap refs and allowing the pending snap to logically
 * complete _before_ this write occurs.
 *
 * If we are near ENOSPC, write synchronously.
 */
static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct ceph_file_info *fi = file->private_data;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_cap_flush *prealloc_cf;
	ssize_t count, written = 0;
	int err, want, got;
	loff_t pos;
	loff_t limit = max(i_size_read(inode), fsc->max_file_size);

	if (ceph_snap(inode) != CEPH_NOSNAP)
		return -EROFS;

	prealloc_cf = ceph_alloc_cap_flush();
	if (!prealloc_cf)
		return -ENOMEM;

retry_snap:
	if (iocb->ki_flags & IOCB_DIRECT)
		ceph_start_io_direct(inode);
	else
		ceph_start_io_write(inode);

	/* We can write back this queue in page reclaim */
	current->backing_dev_info = inode_to_bdi(inode);

	if (iocb->ki_flags & IOCB_APPEND) {
		err = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
		if (err < 0)
			goto out;
	}

	err = generic_write_checks(iocb, from);
	if (err <= 0)
		goto out;

	pos = iocb->ki_pos;
	if (unlikely(pos >= limit)) {
		err = -EFBIG;
		goto out;
	} else {
		iov_iter_truncate(from, limit - pos);
	}

	count = iov_iter_count(from);
	if (ceph_quota_is_max_bytes_exceeded(inode, pos + count)) {
		err = -EDQUOT;
		goto out;
	}

	err = file_remove_privs(file);
	if (err)
		goto out;

	err = file_update_time(file);
	if (err)
		goto out;

	inode_inc_iversion_raw(inode);

	if (ci->i_inline_version != CEPH_INLINE_NONE) {
		err = ceph_uninline_data(file, NULL);
		if (err < 0)
			goto out;
	}

	/* FIXME: not complete since it doesn't account for being at quota */
	if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_FULL)) {
		err = -ENOSPC;
		goto out;
	}

	dout("aio_write %p %llx.%llx %llu~%zd getting caps. i_size %llu\n",
	     inode, ceph_vinop(inode), pos, count, i_size_read(inode));
	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_BUFFER;
	got = 0;
	err = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, pos + count,
			    &got, NULL);
	if (err < 0)
		goto out;

	dout("aio_write %p %llx.%llx %llu~%zd got cap refs on %s\n",
	     inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));

	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) ||
	    (ci->i_ceph_flags & CEPH_I_ERROR_WRITE)) {
		struct ceph_snap_context *snapc;
		struct iov_iter data;

		spin_lock(&ci->i_ceph_lock);
		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);
		} else {
			BUG_ON(!ci->i_head_snapc);
			snapc = ceph_get_snap_context(ci->i_head_snapc);
		}
		spin_unlock(&ci->i_ceph_lock);

		/* we might need to revert back to that point */
		data = *from;
		if (iocb->ki_flags & IOCB_DIRECT) {
			written = ceph_direct_read_write(iocb, &data, snapc,
							 &prealloc_cf);
			ceph_end_io_direct(inode);
		} else {
			written = ceph_sync_write(iocb, &data, pos, snapc);
			ceph_end_io_write(inode);
		}
		if (written > 0)
			iov_iter_advance(from, written);
		ceph_put_snap_context(snapc);
	} else {
		/*
		 * No need to acquire the i_truncate_mutex. Because
		 * the MDS revokes Fwb caps before sending truncate
		 * message to us. We can't get Fwb cap while there
		 * are pending vmtruncate. So write and vmtruncate
		 * can not run at the same time
		 */
		written = generic_perform_write(file, from, pos);
		if (likely(written >= 0))
			iocb->ki_pos = pos + written;
		ceph_end_io_write(inode);
	}

	if (written >= 0) {
		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);
		if (ceph_quota_is_max_bytes_approaching(inode, iocb->ki_pos))
			ceph_check_caps(ci, CHECK_CAPS_NODELAY, NULL);
	}

	dout("aio_write %p %llx.%llx %llu~%u  dropping cap refs on %s\n",
	     inode, ceph_vinop(inode), pos, (unsigned)count,
	     ceph_cap_string(got));
	ceph_put_cap_refs(ci, got);

	if (written == -EOLDSNAPC) {
		dout("aio_write %p %llx.%llx %llu~%u" "got EOLDSNAPC, retrying\n",
		     inode, ceph_vinop(inode), pos, (unsigned)count);
		goto retry_snap;
	}

	if (written >= 0) {
		if (ceph_osdmap_flag(&fsc->client->osdc, CEPH_OSDMAP_NEARFULL))
			iocb->ki_flags |= IOCB_DSYNC;
		written = generic_write_sync(iocb, written);
	}

	goto out_unlocked;
out:
	if (iocb->ki_flags & IOCB_DIRECT)
		ceph_end_io_direct(inode);
	else
		ceph_end_io_write(inode);
out_unlocked:
	ceph_free_cap_flush(prealloc_cf);
	current->backing_dev_info = NULL;
	return written ? written : err;
}

/*
 * llseek.  be sure to verify file size on SEEK_END.
 */
static loff_t ceph_llseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	loff_t i_size;
	loff_t ret;

	inode_lock(inode);

	if (whence == SEEK_END || whence == SEEK_DATA || whence == SEEK_HOLE) {
		ret = ceph_do_getattr(inode, CEPH_STAT_CAP_SIZE, false);
		if (ret < 0)
			goto out;
	}

	i_size = i_size_read(inode);
	switch (whence) {
	case SEEK_END:
		offset += i_size;
		break;
	case SEEK_CUR:
		/*
		 * Here we special-case the lseek(fd, 0, SEEK_CUR)
		 * position-querying operation.  Avoid rewriting the "same"
		 * f_pos value back to the file because a concurrent read(),
		 * write() or lseek() might have altered it
		 */
		if (offset == 0) {
			ret = file->f_pos;
			goto out;
		}
		offset += file->f_pos;
		break;
	case SEEK_DATA:
		if (offset < 0 || offset >= i_size) {
			ret = -ENXIO;
			goto out;
		}
		break;
	case SEEK_HOLE:
		if (offset < 0 || offset >= i_size) {
			ret = -ENXIO;
			goto out;
		}
		offset = i_size;
		break;
	}

	ret = vfs_setpos(file, offset, max(i_size, fsc->max_file_size));

out:
	inode_unlock(inode);
	return ret;
}

static inline void ceph_zero_partial_page(
	struct inode *inode, loff_t offset, unsigned size)
{
	struct page *page;
	pgoff_t index = offset >> PAGE_SHIFT;

	page = find_lock_page(inode->i_mapping, index);
	if (page) {
		wait_on_page_writeback(page);
		zero_user(page, offset & (PAGE_SIZE - 1), size);
		unlock_page(page);
		put_page(page);
	}
}

static void ceph_zero_pagecache_range(struct inode *inode, loff_t offset,
				      loff_t length)
{
	loff_t nearly = round_up(offset, PAGE_SIZE);
	if (offset < nearly) {
		loff_t size = nearly - offset;
		if (length < size)
			size = length;
		ceph_zero_partial_page(inode, offset, size);
		offset += size;
		length -= size;
	}
	if (length >= PAGE_SIZE) {
		loff_t size = round_down(length, PAGE_SIZE);
		truncate_pagecache_range(inode, offset, offset + size - 1);
		offset += size;
		length -= size;
	}
	if (length)
		ceph_zero_partial_page(inode, offset, length);
}

static int ceph_zero_partial_object(struct inode *inode,
				    loff_t offset, loff_t *length)
{
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_fs_client *fsc = ceph_inode_to_client(inode);
	struct ceph_osd_request *req;
	int ret = 0;
	loff_t zero = 0;
	int op;

	if (!length) {
		op = offset ? CEPH_OSD_OP_DELETE : CEPH_OSD_OP_TRUNCATE;
		length = &zero;
	} else {
		op = CEPH_OSD_OP_ZERO;
	}

	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
					ceph_vino(inode),
					offset, length,
					0, 1, op,
					CEPH_OSD_FLAG_WRITE,
					NULL, 0, 0, false);
	if (IS_ERR(req)) {
		ret = PTR_ERR(req);
		goto out;
	}

	req->r_mtime = inode->i_mtime;
	ret = ceph_osdc_start_request(&fsc->client->osdc, req, false);
	if (!ret) {
		ret = ceph_osdc_wait_request(&fsc->client->osdc, req);
		if (ret == -ENOENT)
			ret = 0;
	}
	ceph_osdc_put_request(req);

out:
	return ret;
}

static int ceph_zero_objects(struct inode *inode, loff_t offset, loff_t length)
{
	int ret = 0;
	struct ceph_inode_info *ci = ceph_inode(inode);
	s32 stripe_unit = ci->i_layout.stripe_unit;
	s32 stripe_count = ci->i_layout.stripe_count;
	s32 object_size = ci->i_layout.object_size;
	u64 object_set_size = object_size * stripe_count;
	u64 nearly, t;

	/* round offset up to next period boundary */
	nearly = offset + object_set_size - 1;
	t = nearly;
	nearly -= do_div(t, object_set_size);

	while (length && offset < nearly) {
		loff_t size = length;
		ret = ceph_zero_partial_object(inode, offset, &size);
		if (ret < 0)
			return ret;
		offset += size;
		length -= size;
	}
	while (length >= object_set_size) {
		int i;
		loff_t pos = offset;
		for (i = 0; i < stripe_count; ++i) {
			ret = ceph_zero_partial_object(inode, pos, NULL);
			if (ret < 0)
				return ret;
			pos += stripe_unit;
		}
		offset += object_set_size;
		length -= object_set_size;
	}
	while (length) {
		loff_t size = length;
		ret = ceph_zero_partial_object(inode, offset, &size);
		if (ret < 0)
			return ret;
		offset += size;
		length -= size;
	}
	return ret;
}

static long ceph_fallocate(struct file *file, int mode,
				loff_t offset, loff_t length)
{
	struct ceph_file_info *fi = file->private_data;
	struct inode *inode = file_inode(file);
	struct ceph_inode_info *ci = ceph_inode(inode);
	struct ceph_cap_flush *prealloc_cf;
	int want, got = 0;
	int dirty;
	int ret = 0;
	loff_t endoff = 0;
	loff_t size;

	if (mode != (FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
		return -EOPNOTSUPP;

	if (!S_ISREG(inode->i_mode))
		return -EOPNOTSUPP;

	prealloc_cf = ceph_alloc_cap_flush();
	if (!prealloc_cf)
		return -ENOMEM;

	inode_lock(inode);

	if (ceph_snap(inode) != CEPH_NOSNAP) {
		ret = -EROFS;
		goto unlock;
	}

	if (ci->i_inline_version != CEPH_INLINE_NONE) {
		ret = ceph_uninline_data(file, NULL);
		if (ret < 0)
			goto unlock;
	}

	size = i_size_read(inode);

	/* Are we punching a hole beyond EOF? */
	if (offset >= size)
		goto unlock;
	if ((offset + length) > size)
		length = size - offset;

	if (fi->fmode & CEPH_FILE_MODE_LAZY)
		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
	else
		want = CEPH_CAP_FILE_BUFFER;

	ret = ceph_get_caps(file, CEPH_CAP_FILE_WR, want, endoff, &got, NULL);
	if (ret < 0)
		goto unlock;

	ceph_zero_pagecache_range(inode, offset, length);
	ret = ceph_zero_objects(inode, offset, length);

	if (!ret) {
		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);
	}

	ceph_put_cap_refs(ci, got);
unlock:
	inode_unlock(inode);
	ceph_free_cap_flush(prealloc_cf);
	return ret;
}

/*
 * This function tries to get FILE_WR capabilities for dst_ci and FILE_RD for
 * src_ci.  Two attempts are made to obtain both caps, and an error is return if
 * this fails; zero is returned on success.
 */
static int get_rd_wr_caps(struct file *src_filp, int *src_got,
			  struct file *dst_filp,
			  loff_t dst_endoff, int *dst_got)
{
	int ret = 0;
	bool retrying = false;

retry_caps:
	ret = ceph_get_caps(dst_filp, CEPH_CAP_FILE_WR, CEPH_CAP_FILE_BUFFER,
			    dst_endoff, dst_got, NULL);
	if (ret < 0)
		return ret;

	/*
	 * Since we're already holding the FILE_WR capability for the dst file,
	 * we would risk a deadlock by using ceph_get_caps.  Thus, we'll do some
	 * retry dance instead to try to get both capabilities.
	 */
	ret = ceph_try_get_caps(file_inode(src_filp),
				CEPH_CAP_FILE_RD, CEPH_CAP_FILE_SHARED,
				false, src_got);
	if (ret <= 0) {
		/* Start by dropping dst_ci caps and getting src_ci caps */
		ceph_put_cap_refs(ceph_inode(file_inode(dst_filp)), *dst_got);
		if (retrying) {
			if (!ret)
				/* ceph_try_get_caps masks EAGAIN */
				ret = -EAGAIN;
			return ret;
		}
		ret = ceph_get_caps(src_filp, CEPH_CAP_FILE_RD,
				    CEPH_CAP_FILE_SHARED, -1, src_got, NULL);
		if (ret < 0)
			return ret;
		/*... drop src_ci caps too, and retry */
		ceph_put_cap_refs(ceph_inode(file_inode(src_filp)), *src_got);
		retrying = true;
		goto retry_caps;
	}
	return ret;
}

static void put_rd_wr_caps(struct ceph_inode_info *src_ci, int src_got,
			   struct ceph_inode_info *dst_ci, int dst_got)
{
	ceph_put_cap_refs(src_ci, src_got);
	ceph_put_cap_refs(dst_ci, dst_got);
}

/*
 * This function does several size-related checks, returning an error if:
 *  - source file is smaller than off+len
 *  - destination file size is not OK (inode_newsize_ok())
 *  - max bytes quotas is exceeded
 */
static int is_file_size_ok(struct inode *src_inode, struct inode *dst_inode,
			   loff_t src_off, loff_t dst_off, size_t len)
{
	loff_t size, endoff;

	size = i_size_read(src_inode);
	/*
	 * Don't copy beyond source file EOF.  Instead of simply setting length
	 * to (size - src_off), just drop to VFS default implementation, as the
	 * local i_size may be stale due to other clients writing to the source
	 * inode.
	 */
	if (src_off + len > size) {
		dout("Copy beyond EOF (%llu + %zu > %llu)\n",
		     src_off, len, size);
		return -EOPNOTSUPP;
	}
	size = i_size_read(dst_inode);

	endoff = dst_off + len;
	if (inode_newsize_ok(dst_inode, endoff))
		return -EOPNOTSUPP;

	if (ceph_quota_is_max_bytes_exceeded(dst_inode, endoff))
		return -EDQUOT;

	return 0;
}

static ssize_t __ceph_copy_file_range(struct file *src_file, loff_t src_off,
				      struct file *dst_file, loff_t dst_off,
				      size_t len, unsigned int flags)
{
	struct inode *src_inode = file_inode(src_file);
	struct inode *dst_inode = file_inode(dst_file);
	struct ceph_inode_info *src_ci = ceph_inode(src_inode);
	struct ceph_inode_info *dst_ci = ceph_inode(dst_inode);
	struct ceph_cap_flush *prealloc_cf;
	struct ceph_fs_client *src_fsc = ceph_inode_to_client(src_inode);
	struct ceph_object_locator src_oloc, dst_oloc;
	struct ceph_object_id src_oid, dst_oid;
	loff_t endoff = 0, size;
	ssize_t ret = -EIO;
	u64 src_objnum, dst_objnum, src_objoff, dst_objoff;
	u32 src_objlen, dst_objlen, object_size;
	int src_got = 0, dst_got = 0, err, dirty;
	bool do_final_copy = false;

	if (src_inode->i_sb != dst_inode->i_sb) {
		struct ceph_fs_client *dst_fsc = ceph_inode_to_client(dst_inode);

		if (ceph_fsid_compare(&src_fsc->client->fsid,
				      &dst_fsc->client->fsid)) {
			dout("Copying files across clusters: src: %pU dst: %pU\n",
			     &src_fsc->client->fsid, &dst_fsc->client->fsid);
			return -EXDEV;
		}
	}
	if (ceph_snap(dst_inode) != CEPH_NOSNAP)
		return -EROFS;

	/*
	 * Some of the checks below will return -EOPNOTSUPP, which will force a
	 * fallback to the default VFS copy_file_range implementation.  This is
	 * desirable in several cases (for ex, the 'len' is smaller than the
	 * size of the objects, or in cases where that would be more
	 * efficient).
	 */

	if (ceph_test_mount_opt(src_fsc, NOCOPYFROM))
		return -EOPNOTSUPP;

	/*
	 * Striped file layouts require that we copy partial objects, but the
	 * OSD copy-from operation only supports full-object copies.  Limit
	 * this to non-striped file layouts for now.
	 */
	if ((src_ci->i_layout.stripe_unit != dst_ci->i_layout.stripe_unit) ||
	    (src_ci->i_layout.stripe_count != 1) ||
	    (dst_ci->i_layout.stripe_count != 1) ||
	    (src_ci->i_layout.object_size != dst_ci->i_layout.object_size)) {
		dout("Invalid src/dst files layout\n");
		return -EOPNOTSUPP;
	}

	if (len < src_ci->i_layout.object_size)
		return -EOPNOTSUPP; /* no remote copy will be done */

	prealloc_cf = ceph_alloc_cap_flush();
	if (!prealloc_cf)
		return -ENOMEM;

	/* Start by sync'ing the source and destination files */
	ret = file_write_and_wait_range(src_file, src_off, (src_off + len));
	if (ret < 0) {
		dout("failed to write src file (%zd)\n", ret);
		goto out;
	}
	ret = file_write_and_wait_range(dst_file, dst_off, (dst_off + len));
	if (ret < 0) {
		dout("failed to write dst file (%zd)\n", ret);
		goto out;
	}

	/*
	 * We need FILE_WR caps for dst_ci and FILE_RD for src_ci as other
	 * clients may have dirty data in their caches.  And OSDs know nothing
	 * about caps, so they can't safely do the remote object copies.
	 */
	err = get_rd_wr_caps(src_file, &src_got,
			     dst_file, (dst_off + len), &dst_got);
	if (err < 0) {
		dout("get_rd_wr_caps returned %d\n", err);
		ret = -EOPNOTSUPP;
		goto out;
	}

	ret = is_file_size_ok(src_inode, dst_inode, src_off, dst_off, len);
	if (ret < 0)
		goto out_caps;

	size = i_size_read(dst_inode);
	endoff = dst_off + len;

	/* Drop dst file cached pages */
	ret = invalidate_inode_pages2_range(dst_inode->i_mapping,
					    dst_off >> PAGE_SHIFT,
					    endoff >> PAGE_SHIFT);
	if (ret < 0) {
		dout("Failed to invalidate inode pages (%zd)\n", ret);
		ret = 0; /* XXX */
	}
	src_oloc.pool = src_ci->i_layout.pool_id;
	src_oloc.pool_ns = ceph_try_get_string(src_ci->i_layout.pool_ns);
	dst_oloc.pool = dst_ci->i_layout.pool_id;
	dst_oloc.pool_ns = ceph_try_get_string(dst_ci->i_layout.pool_ns);

	ceph_calc_file_object_mapping(&src_ci->i_layout, src_off,
				      src_ci->i_layout.object_size,
				      &src_objnum, &src_objoff, &src_objlen);
	ceph_calc_file_object_mapping(&dst_ci->i_layout, dst_off,
				      dst_ci->i_layout.object_size,
				      &dst_objnum, &dst_objoff, &dst_objlen);
	/* object-level offsets need to the same */
	if (src_objoff != dst_objoff) {
		ret = -EOPNOTSUPP;
		goto out_caps;
	}

	/*
	 * Do a manual copy if the object offset isn't object aligned.
	 * 'src_objlen' contains the bytes left until the end of the object,
	 * starting at the src_off
	 */
	if (src_objoff) {
		/*
		 * we need to temporarily drop all caps as we'll be calling
		 * {read,write}_iter, which will get caps again.
		 */
		put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got);
		ret = do_splice_direct(src_file, &src_off, dst_file,
				       &dst_off, src_objlen, flags);
		if (ret < 0) {
			dout("do_splice_direct returned %d\n", err);
			goto out;
		}
		len -= ret;
		err = get_rd_wr_caps(src_file, &src_got,
				     dst_file, (dst_off + len), &dst_got);
		if (err < 0)
			goto out;
		err = is_file_size_ok(src_inode, dst_inode,
				      src_off, dst_off, len);
		if (err < 0)
			goto out_caps;
	}
	object_size = src_ci->i_layout.object_size;
	while (len >= object_size) {
		ceph_calc_file_object_mapping(&src_ci->i_layout, src_off,
					      object_size, &src_objnum,
					      &src_objoff, &src_objlen);
		ceph_calc_file_object_mapping(&dst_ci->i_layout, dst_off,
					      object_size, &dst_objnum,
					      &dst_objoff, &dst_objlen);
		ceph_oid_init(&src_oid);
		ceph_oid_printf(&src_oid, "%llx.%08llx",
				src_ci->i_vino.ino, src_objnum);
		ceph_oid_init(&dst_oid);
		ceph_oid_printf(&dst_oid, "%llx.%08llx",
				dst_ci->i_vino.ino, dst_objnum);
		/* Do an object remote copy */
		err = ceph_osdc_copy_from(
			&src_fsc->client->osdc,
			src_ci->i_vino.snap, 0,
			&src_oid, &src_oloc,
			CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
			CEPH_OSD_OP_FLAG_FADVISE_NOCACHE,
			&dst_oid, &dst_oloc,
			CEPH_OSD_OP_FLAG_FADVISE_SEQUENTIAL |
			CEPH_OSD_OP_FLAG_FADVISE_DONTNEED, 0);
		if (err) {
			dout("ceph_osdc_copy_from returned %d\n", err);
			if (!ret)
				ret = err;
			goto out_caps;
		}
		len -= object_size;
		src_off += object_size;
		dst_off += object_size;
		ret += object_size;
	}

	if (len)
		/* We still need one final local copy */
		do_final_copy = true;

	file_update_time(dst_file);
	inode_inc_iversion_raw(dst_inode);

	if (endoff > size) {
		int caps_flags = 0;

		/* Let the MDS know about dst file size change */
		if (ceph_quota_is_max_bytes_approaching(dst_inode, endoff))
			caps_flags |= CHECK_CAPS_NODELAY;
		if (ceph_inode_set_size(dst_inode, endoff))
			caps_flags |= CHECK_CAPS_AUTHONLY;
		if (caps_flags)
			ceph_check_caps(dst_ci, caps_flags, NULL);
	}
	/* Mark Fw dirty */
	spin_lock(&dst_ci->i_ceph_lock);
	dst_ci->i_inline_version = CEPH_INLINE_NONE;
	dirty = __ceph_mark_dirty_caps(dst_ci, CEPH_CAP_FILE_WR, &prealloc_cf);
	spin_unlock(&dst_ci->i_ceph_lock);
	if (dirty)
		__mark_inode_dirty(dst_inode, dirty);

out_caps:
	put_rd_wr_caps(src_ci, src_got, dst_ci, dst_got);

	if (do_final_copy) {
		err = do_splice_direct(src_file, &src_off, dst_file,
				       &dst_off, len, flags);
		if (err < 0) {
			dout("do_splice_direct returned %d\n", err);
			goto out;
		}
		len -= err;
		ret += err;
	}

out:
	ceph_free_cap_flush(prealloc_cf);

	return ret;
}

static ssize_t ceph_copy_file_range(struct file *src_file, loff_t src_off,
				    struct file *dst_file, loff_t dst_off,
				    size_t len, unsigned int flags)
{
	ssize_t ret;

	ret = __ceph_copy_file_range(src_file, src_off, dst_file, dst_off,
				     len, flags);

	if (ret == -EOPNOTSUPP || ret == -EXDEV)
		ret = generic_copy_file_range(src_file, src_off, dst_file,
					      dst_off, len, flags);
	return ret;
}

const struct file_operations ceph_file_fops = {
	.open = ceph_open,
	.release = ceph_release,
	.llseek = ceph_llseek,
	.read_iter = ceph_read_iter,
	.write_iter = ceph_write_iter,
	.mmap = ceph_mmap,
	.fsync = ceph_fsync,
	.lock = ceph_lock,
	.flock = ceph_flock,
	.splice_read = generic_file_splice_read,
	.splice_write = iter_file_splice_write,
	.unlocked_ioctl = ceph_ioctl,
	.compat_ioctl = compat_ptr_ioctl,
	.fallocate	= ceph_fallocate,
	.copy_file_range = ceph_copy_file_range,
};