aboutsummaryrefslogtreecommitdiff
path: root/fs/cifs/file.c
blob: fa04a00d126dc5787850f905e195b41d7b310b5c (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
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
/*
 *   fs/cifs/file.c
 *
 *   vfs operations that deal with files
 *
 *   Copyright (C) International Business Machines  Corp., 2002,2010
 *   Author(s): Steve French (sfrench@us.ibm.com)
 *              Jeremy Allison (jra@samba.org)
 *
 *   This library is free software; you can redistribute it and/or modify
 *   it under the terms of the GNU Lesser General Public License as published
 *   by the Free Software Foundation; either version 2.1 of the License, or
 *   (at your option) any later version.
 *
 *   This library is distributed in the hope that it will be useful,
 *   but WITHOUT ANY WARRANTY; without even the implied warranty of
 *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See
 *   the GNU Lesser General Public License for more details.
 *
 *   You should have received a copy of the GNU Lesser General Public License
 *   along with this library; if not, write to the Free Software
 *   Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
 */
#include <linux/fs.h>
#include <linux/backing-dev.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/writeback.h>
#include <linux/task_io_accounting_ops.h>
#include <linux/delay.h>
#include <linux/mount.h>
#include <linux/slab.h>
#include <asm/div64.h>
#include "cifsfs.h"
#include "cifspdu.h"
#include "cifsglob.h"
#include "cifsproto.h"
#include "cifs_unicode.h"
#include "cifs_debug.h"
#include "cifs_fs_sb.h"
#include "fscache.h"

static inline int cifs_convert_flags(unsigned int flags)
{
	if ((flags & O_ACCMODE) == O_RDONLY)
		return GENERIC_READ;
	else if ((flags & O_ACCMODE) == O_WRONLY)
		return GENERIC_WRITE;
	else if ((flags & O_ACCMODE) == O_RDWR) {
		/* GENERIC_ALL is too much permission to request
		   can cause unnecessary access denied on create */
		/* return GENERIC_ALL; */
		return (GENERIC_READ | GENERIC_WRITE);
	}

	return (READ_CONTROL | FILE_WRITE_ATTRIBUTES | FILE_READ_ATTRIBUTES |
		FILE_WRITE_EA | FILE_APPEND_DATA | FILE_WRITE_DATA |
		FILE_READ_DATA);
}

static inline fmode_t cifs_posix_convert_flags(unsigned int flags)
{
	fmode_t posix_flags = 0;

	if ((flags & O_ACCMODE) == O_RDONLY)
		posix_flags = FMODE_READ;
	else if ((flags & O_ACCMODE) == O_WRONLY)
		posix_flags = FMODE_WRITE;
	else if ((flags & O_ACCMODE) == O_RDWR) {
		/* GENERIC_ALL is too much permission to request
		   can cause unnecessary access denied on create */
		/* return GENERIC_ALL; */
		posix_flags = FMODE_READ | FMODE_WRITE;
	}
	/* can not map O_CREAT or O_EXCL or O_TRUNC flags when
	   reopening a file.  They had their effect on the original open */
	if (flags & O_APPEND)
		posix_flags |= (fmode_t)O_APPEND;
	if (flags & O_DSYNC)
		posix_flags |= (fmode_t)O_DSYNC;
	if (flags & __O_SYNC)
		posix_flags |= (fmode_t)__O_SYNC;
	if (flags & O_DIRECTORY)
		posix_flags |= (fmode_t)O_DIRECTORY;
	if (flags & O_NOFOLLOW)
		posix_flags |= (fmode_t)O_NOFOLLOW;
	if (flags & O_DIRECT)
		posix_flags |= (fmode_t)O_DIRECT;

	return posix_flags;
}

static inline int cifs_get_disposition(unsigned int flags)
{
	if ((flags & (O_CREAT | O_EXCL)) == (O_CREAT | O_EXCL))
		return FILE_CREATE;
	else if ((flags & (O_CREAT | O_TRUNC)) == (O_CREAT | O_TRUNC))
		return FILE_OVERWRITE_IF;
	else if ((flags & O_CREAT) == O_CREAT)
		return FILE_OPEN_IF;
	else if ((flags & O_TRUNC) == O_TRUNC)
		return FILE_OVERWRITE;
	else
		return FILE_OPEN;
}

/* all arguments to this function must be checked for validity in caller */
static inline int
cifs_posix_open_inode_helper(struct inode *inode, struct file *file,
			     struct cifsInodeInfo *pCifsInode, __u32 oplock,
			     u16 netfid)
{

	write_lock(&GlobalSMBSeslock);

	pCifsInode = CIFS_I(file->f_path.dentry->d_inode);
	if (pCifsInode == NULL) {
		write_unlock(&GlobalSMBSeslock);
		return -EINVAL;
	}

	if (pCifsInode->clientCanCacheRead) {
		/* we have the inode open somewhere else
		   no need to discard cache data */
		goto psx_client_can_cache;
	}

	/* BB FIXME need to fix this check to move it earlier into posix_open
	   BB  fIX following section BB FIXME */

	/* if not oplocked, invalidate inode pages if mtime or file
	   size changed */
/*	temp = cifs_NTtimeToUnix(le64_to_cpu(buf->LastWriteTime));
	if (timespec_equal(&file->f_path.dentry->d_inode->i_mtime, &temp) &&
			   (file->f_path.dentry->d_inode->i_size ==
			    (loff_t)le64_to_cpu(buf->EndOfFile))) {
		cFYI(1, "inode unchanged on server");
	} else {
		if (file->f_path.dentry->d_inode->i_mapping) {
			rc = filemap_write_and_wait(file->f_path.dentry->d_inode->i_mapping);
			if (rc != 0)
				CIFS_I(file->f_path.dentry->d_inode)->write_behind_rc = rc;
		}
		cFYI(1, "invalidating remote inode since open detected it "
			 "changed");
		invalidate_remote_inode(file->f_path.dentry->d_inode);
	} */

psx_client_can_cache:
	if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
		pCifsInode->clientCanCacheAll = true;
		pCifsInode->clientCanCacheRead = true;
		cFYI(1, "Exclusive Oplock granted on inode %p",
			 file->f_path.dentry->d_inode);
	} else if ((oplock & 0xF) == OPLOCK_READ)
		pCifsInode->clientCanCacheRead = true;

	/* will have to change the unlock if we reenable the
	   filemap_fdatawrite (which does not seem necessary */
	write_unlock(&GlobalSMBSeslock);
	return 0;
}

/* all arguments to this function must be checked for validity in caller */
static inline int cifs_open_inode_helper(struct inode *inode,
	struct cifsTconInfo *pTcon, int *oplock, FILE_ALL_INFO *buf,
	char *full_path, int xid)
{
	struct cifsInodeInfo *pCifsInode = CIFS_I(inode);
	struct timespec temp;
	int rc;

	if (pCifsInode->clientCanCacheRead) {
		/* we have the inode open somewhere else
		   no need to discard cache data */
		goto client_can_cache;
	}

	/* BB need same check in cifs_create too? */
	/* if not oplocked, invalidate inode pages if mtime or file
	   size changed */
	temp = cifs_NTtimeToUnix(buf->LastWriteTime);
	if (timespec_equal(&inode->i_mtime, &temp) &&
			   (inode->i_size ==
			    (loff_t)le64_to_cpu(buf->EndOfFile))) {
		cFYI(1, "inode unchanged on server");
	} else {
		if (inode->i_mapping) {
			/* BB no need to lock inode until after invalidate
			since namei code should already have it locked? */
			rc = filemap_write_and_wait(inode->i_mapping);
			if (rc != 0)
				pCifsInode->write_behind_rc = rc;
		}
		cFYI(1, "invalidating remote inode since open detected it "
			 "changed");
		invalidate_remote_inode(inode);
	}

client_can_cache:
	if (pTcon->unix_ext)
		rc = cifs_get_inode_info_unix(&inode, full_path, inode->i_sb,
					      xid);
	else
		rc = cifs_get_inode_info(&inode, full_path, buf, inode->i_sb,
					 xid, NULL);

	if ((*oplock & 0xF) == OPLOCK_EXCLUSIVE) {
		pCifsInode->clientCanCacheAll = true;
		pCifsInode->clientCanCacheRead = true;
		cFYI(1, "Exclusive Oplock granted on inode %p", inode);
	} else if ((*oplock & 0xF) == OPLOCK_READ)
		pCifsInode->clientCanCacheRead = true;

	return rc;
}

int cifs_open(struct inode *inode, struct file *file)
{
	int rc = -EACCES;
	int xid;
	__u32 oplock;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *tcon;
	struct cifsFileInfo *pCifsFile = NULL;
	struct cifsInodeInfo *pCifsInode;
	char *full_path = NULL;
	int desiredAccess;
	int disposition;
	__u16 netfid;
	FILE_ALL_INFO *buf = NULL;

	xid = GetXid();

	cifs_sb = CIFS_SB(inode->i_sb);
	tcon = cifs_sb->tcon;

	pCifsInode = CIFS_I(file->f_path.dentry->d_inode);

	full_path = build_path_from_dentry(file->f_path.dentry);
	if (full_path == NULL) {
		rc = -ENOMEM;
		FreeXid(xid);
		return rc;
	}

	cFYI(1, "inode = 0x%p file flags are 0x%x for %s",
		 inode, file->f_flags, full_path);

	if (oplockEnabled)
		oplock = REQ_OPLOCK;
	else
		oplock = 0;

	if (!tcon->broken_posix_open && tcon->unix_ext &&
	    (tcon->ses->capabilities & CAP_UNIX) &&
	    (CIFS_UNIX_POSIX_PATH_OPS_CAP &
			le64_to_cpu(tcon->fsUnixInfo.Capability))) {
		int oflags = (int) cifs_posix_convert_flags(file->f_flags);
		oflags |= SMB_O_CREAT;
		/* can not refresh inode info since size could be stale */
		rc = cifs_posix_open(full_path, &inode, inode->i_sb,
				cifs_sb->mnt_file_mode /* ignored */,
				oflags, &oplock, &netfid, xid);
		if (rc == 0) {
			cFYI(1, "posix open succeeded");
			/* no need for special case handling of setting mode
			   on read only files needed here */

			rc = cifs_posix_open_inode_helper(inode, file,
					pCifsInode, oplock, netfid);
			if (rc != 0) {
				CIFSSMBClose(xid, tcon, netfid);
				goto out;
			}

			pCifsFile = cifs_new_fileinfo(inode, netfid, file,
							file->f_path.mnt,
							oflags);
			if (pCifsFile == NULL) {
				CIFSSMBClose(xid, tcon, netfid);
				rc = -ENOMEM;
			}

			cifs_fscache_set_inode_cookie(inode, file);

			goto out;
		} else if ((rc == -EINVAL) || (rc == -EOPNOTSUPP)) {
			if (tcon->ses->serverNOS)
				cERROR(1, "server %s of type %s returned"
					   " unexpected error on SMB posix open"
					   ", disabling posix open support."
					   " Check if server update available.",
					   tcon->ses->serverName,
					   tcon->ses->serverNOS);
			tcon->broken_posix_open = true;
		} else if ((rc != -EIO) && (rc != -EREMOTE) &&
			 (rc != -EOPNOTSUPP)) /* path not found or net err */
			goto out;
		/* else fallthrough to retry open the old way on network i/o
		   or DFS errors */
	}

	desiredAccess = cifs_convert_flags(file->f_flags);

/*********************************************************************
 *  open flag mapping table:
 *
 *	POSIX Flag            CIFS Disposition
 *	----------            ----------------
 *	O_CREAT               FILE_OPEN_IF
 *	O_CREAT | O_EXCL      FILE_CREATE
 *	O_CREAT | O_TRUNC     FILE_OVERWRITE_IF
 *	O_TRUNC               FILE_OVERWRITE
 *	none of the above     FILE_OPEN
 *
 *	Note that there is not a direct match between disposition
 *	FILE_SUPERSEDE (ie create whether or not file exists although
 *	O_CREAT | O_TRUNC is similar but truncates the existing
 *	file rather than creating a new file as FILE_SUPERSEDE does
 *	(which uses the attributes / metadata passed in on open call)
 *?
 *?  O_SYNC is a reasonable match to CIFS writethrough flag
 *?  and the read write flags match reasonably.  O_LARGEFILE
 *?  is irrelevant because largefile support is always used
 *?  by this client. Flags O_APPEND, O_DIRECT, O_DIRECTORY,
 *	 O_FASYNC, O_NOFOLLOW, O_NONBLOCK need further investigation
 *********************************************************************/

	disposition = cifs_get_disposition(file->f_flags);

	/* BB pass O_SYNC flag through on file attributes .. BB */

	/* Also refresh inode by passing in file_info buf returned by SMBOpen
	   and calling get_inode_info with returned buf (at least helps
	   non-Unix server case) */

	/* BB we can not do this if this is the second open of a file
	   and the first handle has writebehind data, we might be
	   able to simply do a filemap_fdatawrite/filemap_fdatawait first */
	buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
	if (!buf) {
		rc = -ENOMEM;
		goto out;
	}

	if (cifs_sb->tcon->ses->capabilities & CAP_NT_SMBS)
		rc = CIFSSMBOpen(xid, tcon, full_path, disposition,
			 desiredAccess, CREATE_NOT_DIR, &netfid, &oplock, buf,
			 cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
				 & CIFS_MOUNT_MAP_SPECIAL_CHR);
	else
		rc = -EIO; /* no NT SMB support fall into legacy open below */

	if (rc == -EIO) {
		/* Old server, try legacy style OpenX */
		rc = SMBLegacyOpen(xid, tcon, full_path, disposition,
			desiredAccess, CREATE_NOT_DIR, &netfid, &oplock, buf,
			cifs_sb->local_nls, cifs_sb->mnt_cifs_flags
				& CIFS_MOUNT_MAP_SPECIAL_CHR);
	}
	if (rc) {
		cFYI(1, "cifs_open returned 0x%x", rc);
		goto out;
	}

	rc = cifs_open_inode_helper(inode, tcon, &oplock, buf, full_path, xid);
	if (rc != 0)
		goto out;

	pCifsFile = cifs_new_fileinfo(inode, netfid, file, file->f_path.mnt,
					file->f_flags);
	if (pCifsFile == NULL) {
		rc = -ENOMEM;
		goto out;
	}

	cifs_fscache_set_inode_cookie(inode, file);

	if (oplock & CIFS_CREATE_ACTION) {
		/* time to set mode which we can not set earlier due to
		   problems creating new read-only files */
		if (tcon->unix_ext) {
			struct cifs_unix_set_info_args args = {
				.mode	= inode->i_mode,
				.uid	= NO_CHANGE_64,
				.gid	= NO_CHANGE_64,
				.ctime	= NO_CHANGE_64,
				.atime	= NO_CHANGE_64,
				.mtime	= NO_CHANGE_64,
				.device	= 0,
			};
			CIFSSMBUnixSetPathInfo(xid, tcon, full_path, &args,
					       cifs_sb->local_nls,
					       cifs_sb->mnt_cifs_flags &
						CIFS_MOUNT_MAP_SPECIAL_CHR);
		}
	}

out:
	kfree(buf);
	kfree(full_path);
	FreeXid(xid);
	return rc;
}

/* Try to reacquire byte range locks that were released when session */
/* to server was lost */
static int cifs_relock_file(struct cifsFileInfo *cifsFile)
{
	int rc = 0;

/* BB list all locks open on this file and relock */

	return rc;
}

static int cifs_reopen_file(struct file *file, bool can_flush)
{
	int rc = -EACCES;
	int xid;
	__u32 oplock;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *tcon;
	struct cifsFileInfo *pCifsFile;
	struct cifsInodeInfo *pCifsInode;
	struct inode *inode;
	char *full_path = NULL;
	int desiredAccess;
	int disposition = FILE_OPEN;
	__u16 netfid;

	if (file->private_data)
		pCifsFile = file->private_data;
	else
		return -EBADF;

	xid = GetXid();
	mutex_lock(&pCifsFile->fh_mutex);
	if (!pCifsFile->invalidHandle) {
		mutex_unlock(&pCifsFile->fh_mutex);
		rc = 0;
		FreeXid(xid);
		return rc;
	}

	if (file->f_path.dentry == NULL) {
		cERROR(1, "no valid name if dentry freed");
		dump_stack();
		rc = -EBADF;
		goto reopen_error_exit;
	}

	inode = file->f_path.dentry->d_inode;
	if (inode == NULL) {
		cERROR(1, "inode not valid");
		dump_stack();
		rc = -EBADF;
		goto reopen_error_exit;
	}

	cifs_sb = CIFS_SB(inode->i_sb);
	tcon = cifs_sb->tcon;

/* can not grab rename sem here because various ops, including
   those that already have the rename sem can end up causing writepage
   to get called and if the server was down that means we end up here,
   and we can never tell if the caller already has the rename_sem */
	full_path = build_path_from_dentry(file->f_path.dentry);
	if (full_path == NULL) {
		rc = -ENOMEM;
reopen_error_exit:
		mutex_unlock(&pCifsFile->fh_mutex);
		FreeXid(xid);
		return rc;
	}

	cFYI(1, "inode = 0x%p file flags 0x%x for %s",
		 inode, file->f_flags, full_path);

	if (oplockEnabled)
		oplock = REQ_OPLOCK;
	else
		oplock = 0;

	if (tcon->unix_ext && (tcon->ses->capabilities & CAP_UNIX) &&
	    (CIFS_UNIX_POSIX_PATH_OPS_CAP &
			le64_to_cpu(tcon->fsUnixInfo.Capability))) {
		int oflags = (int) cifs_posix_convert_flags(file->f_flags);
		/* can not refresh inode info since size could be stale */
		rc = cifs_posix_open(full_path, NULL, inode->i_sb,
				cifs_sb->mnt_file_mode /* ignored */,
				oflags, &oplock, &netfid, xid);
		if (rc == 0) {
			cFYI(1, "posix reopen succeeded");
			goto reopen_success;
		}
		/* fallthrough to retry open the old way on errors, especially
		   in the reconnect path it is important to retry hard */
	}

	desiredAccess = cifs_convert_flags(file->f_flags);

	/* Can not refresh inode by passing in file_info buf to be returned
	   by SMBOpen and then calling get_inode_info with returned buf
	   since file might have write behind data that needs to be flushed
	   and server version of file size can be stale. If we knew for sure
	   that inode was not dirty locally we could do this */

	rc = CIFSSMBOpen(xid, tcon, full_path, disposition, desiredAccess,
			 CREATE_NOT_DIR, &netfid, &oplock, NULL,
			 cifs_sb->local_nls, cifs_sb->mnt_cifs_flags &
				CIFS_MOUNT_MAP_SPECIAL_CHR);
	if (rc) {
		mutex_unlock(&pCifsFile->fh_mutex);
		cFYI(1, "cifs_open returned 0x%x", rc);
		cFYI(1, "oplock: %d", oplock);
	} else {
reopen_success:
		pCifsFile->netfid = netfid;
		pCifsFile->invalidHandle = false;
		mutex_unlock(&pCifsFile->fh_mutex);
		pCifsInode = CIFS_I(inode);
		if (pCifsInode) {
			if (can_flush) {
				rc = filemap_write_and_wait(inode->i_mapping);
				if (rc != 0)
					CIFS_I(inode)->write_behind_rc = rc;
			/* temporarily disable caching while we
			   go to server to get inode info */
				pCifsInode->clientCanCacheAll = false;
				pCifsInode->clientCanCacheRead = false;
				if (tcon->unix_ext)
					rc = cifs_get_inode_info_unix(&inode,
						full_path, inode->i_sb, xid);
				else
					rc = cifs_get_inode_info(&inode,
						full_path, NULL, inode->i_sb,
						xid, NULL);
			} /* else we are writing out data to server already
			     and could deadlock if we tried to flush data, and
			     since we do not know if we have data that would
			     invalidate the current end of file on the server
			     we can not go to the server to get the new inod
			     info */
			if ((oplock & 0xF) == OPLOCK_EXCLUSIVE) {
				pCifsInode->clientCanCacheAll = true;
				pCifsInode->clientCanCacheRead = true;
				cFYI(1, "Exclusive Oplock granted on inode %p",
					 file->f_path.dentry->d_inode);
			} else if ((oplock & 0xF) == OPLOCK_READ) {
				pCifsInode->clientCanCacheRead = true;
				pCifsInode->clientCanCacheAll = false;
			} else {
				pCifsInode->clientCanCacheRead = false;
				pCifsInode->clientCanCacheAll = false;
			}
			cifs_relock_file(pCifsFile);
		}
	}
	kfree(full_path);
	FreeXid(xid);
	return rc;
}

int cifs_close(struct inode *inode, struct file *file)
{
	int rc = 0;
	int xid, timeout;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	struct cifsFileInfo *pSMBFile = file->private_data;

	xid = GetXid();

	cifs_sb = CIFS_SB(inode->i_sb);
	pTcon = cifs_sb->tcon;
	if (pSMBFile) {
		struct cifsLockInfo *li, *tmp;
		write_lock(&GlobalSMBSeslock);
		pSMBFile->closePend = true;
		if (pTcon) {
			/* no sense reconnecting to close a file that is
			   already closed */
			if (!pTcon->need_reconnect) {
				write_unlock(&GlobalSMBSeslock);
				timeout = 2;
				while ((atomic_read(&pSMBFile->count) != 1)
					&& (timeout <= 2048)) {
					/* Give write a better chance to get to
					server ahead of the close.  We do not
					want to add a wait_q here as it would
					increase the memory utilization as
					the struct would be in each open file,
					but this should give enough time to
					clear the socket */
					cFYI(DBG2, "close delay, write pending");
					msleep(timeout);
					timeout *= 4;
				}
				if (!pTcon->need_reconnect &&
				    !pSMBFile->invalidHandle)
					rc = CIFSSMBClose(xid, pTcon,
						  pSMBFile->netfid);
			} else
				write_unlock(&GlobalSMBSeslock);
		} else
			write_unlock(&GlobalSMBSeslock);

		/* Delete any outstanding lock records.
		   We'll lose them when the file is closed anyway. */
		mutex_lock(&pSMBFile->lock_mutex);
		list_for_each_entry_safe(li, tmp, &pSMBFile->llist, llist) {
			list_del(&li->llist);
			kfree(li);
		}
		mutex_unlock(&pSMBFile->lock_mutex);

		write_lock(&GlobalSMBSeslock);
		list_del(&pSMBFile->flist);
		list_del(&pSMBFile->tlist);
		write_unlock(&GlobalSMBSeslock);
		cifsFileInfo_put(file->private_data);
		file->private_data = NULL;
	} else
		rc = -EBADF;

	read_lock(&GlobalSMBSeslock);
	if (list_empty(&(CIFS_I(inode)->openFileList))) {
		cFYI(1, "closing last open instance for inode %p", inode);
		/* if the file is not open we do not know if we can cache info
		   on this inode, much less write behind and read ahead */
		CIFS_I(inode)->clientCanCacheRead = false;
		CIFS_I(inode)->clientCanCacheAll  = false;
	}
	read_unlock(&GlobalSMBSeslock);
	if ((rc == 0) && CIFS_I(inode)->write_behind_rc)
		rc = CIFS_I(inode)->write_behind_rc;
	FreeXid(xid);
	return rc;
}

int cifs_closedir(struct inode *inode, struct file *file)
{
	int rc = 0;
	int xid;
	struct cifsFileInfo *pCFileStruct = file->private_data;
	char *ptmp;

	cFYI(1, "Closedir inode = 0x%p", inode);

	xid = GetXid();

	if (pCFileStruct) {
		struct cifsTconInfo *pTcon;
		struct cifs_sb_info *cifs_sb =
			CIFS_SB(file->f_path.dentry->d_sb);

		pTcon = cifs_sb->tcon;

		cFYI(1, "Freeing private data in close dir");
		write_lock(&GlobalSMBSeslock);
		if (!pCFileStruct->srch_inf.endOfSearch &&
		    !pCFileStruct->invalidHandle) {
			pCFileStruct->invalidHandle = true;
			write_unlock(&GlobalSMBSeslock);
			rc = CIFSFindClose(xid, pTcon, pCFileStruct->netfid);
			cFYI(1, "Closing uncompleted readdir with rc %d",
				 rc);
			/* not much we can do if it fails anyway, ignore rc */
			rc = 0;
		} else
			write_unlock(&GlobalSMBSeslock);
		ptmp = pCFileStruct->srch_inf.ntwrk_buf_start;
		if (ptmp) {
			cFYI(1, "closedir free smb buf in srch struct");
			pCFileStruct->srch_inf.ntwrk_buf_start = NULL;
			if (pCFileStruct->srch_inf.smallBuf)
				cifs_small_buf_release(ptmp);
			else
				cifs_buf_release(ptmp);
		}
		kfree(file->private_data);
		file->private_data = NULL;
	}
	/* BB can we lock the filestruct while this is going on? */
	FreeXid(xid);
	return rc;
}

static int store_file_lock(struct cifsFileInfo *fid, __u64 len,
				__u64 offset, __u8 lockType)
{
	struct cifsLockInfo *li =
		kmalloc(sizeof(struct cifsLockInfo), GFP_KERNEL);
	if (li == NULL)
		return -ENOMEM;
	li->offset = offset;
	li->length = len;
	li->type = lockType;
	mutex_lock(&fid->lock_mutex);
	list_add(&li->llist, &fid->llist);
	mutex_unlock(&fid->lock_mutex);
	return 0;
}

int cifs_lock(struct file *file, int cmd, struct file_lock *pfLock)
{
	int rc, xid;
	__u32 numLock = 0;
	__u32 numUnlock = 0;
	__u64 length;
	bool wait_flag = false;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *tcon;
	__u16 netfid;
	__u8 lockType = LOCKING_ANDX_LARGE_FILES;
	bool posix_locking = 0;

	length = 1 + pfLock->fl_end - pfLock->fl_start;
	rc = -EACCES;
	xid = GetXid();

	cFYI(1, "Lock parm: 0x%x flockflags: "
		 "0x%x flocktype: 0x%x start: %lld end: %lld",
		cmd, pfLock->fl_flags, pfLock->fl_type, pfLock->fl_start,
		pfLock->fl_end);

	if (pfLock->fl_flags & FL_POSIX)
		cFYI(1, "Posix");
	if (pfLock->fl_flags & FL_FLOCK)
		cFYI(1, "Flock");
	if (pfLock->fl_flags & FL_SLEEP) {
		cFYI(1, "Blocking lock");
		wait_flag = true;
	}
	if (pfLock->fl_flags & FL_ACCESS)
		cFYI(1, "Process suspended by mandatory locking - "
			 "not implemented yet");
	if (pfLock->fl_flags & FL_LEASE)
		cFYI(1, "Lease on file - not implemented yet");
	if (pfLock->fl_flags &
	    (~(FL_POSIX | FL_FLOCK | FL_SLEEP | FL_ACCESS | FL_LEASE)))
		cFYI(1, "Unknown lock flags 0x%x", pfLock->fl_flags);

	if (pfLock->fl_type == F_WRLCK) {
		cFYI(1, "F_WRLCK ");
		numLock = 1;
	} else if (pfLock->fl_type == F_UNLCK) {
		cFYI(1, "F_UNLCK");
		numUnlock = 1;
		/* Check if unlock includes more than
		one lock range */
	} else if (pfLock->fl_type == F_RDLCK) {
		cFYI(1, "F_RDLCK");
		lockType |= LOCKING_ANDX_SHARED_LOCK;
		numLock = 1;
	} else if (pfLock->fl_type == F_EXLCK) {
		cFYI(1, "F_EXLCK");
		numLock = 1;
	} else if (pfLock->fl_type == F_SHLCK) {
		cFYI(1, "F_SHLCK");
		lockType |= LOCKING_ANDX_SHARED_LOCK;
		numLock = 1;
	} else
		cFYI(1, "Unknown type of lock");

	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	tcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		rc = -EBADF;
		FreeXid(xid);
		return rc;
	}
	netfid = ((struct cifsFileInfo *)file->private_data)->netfid;

	if ((tcon->ses->capabilities & CAP_UNIX) &&
	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
		posix_locking = 1;
	/* BB add code here to normalize offset and length to
	account for negative length which we can not accept over the
	wire */
	if (IS_GETLK(cmd)) {
		if (posix_locking) {
			int posix_lock_type;
			if (lockType & LOCKING_ANDX_SHARED_LOCK)
				posix_lock_type = CIFS_RDLCK;
			else
				posix_lock_type = CIFS_WRLCK;
			rc = CIFSSMBPosixLock(xid, tcon, netfid, 1 /* get */,
					length,	pfLock,
					posix_lock_type, wait_flag);
			FreeXid(xid);
			return rc;
		}

		/* BB we could chain these into one lock request BB */
		rc = CIFSSMBLock(xid, tcon, netfid, length, pfLock->fl_start,
				 0, 1, lockType, 0 /* wait flag */ );
		if (rc == 0) {
			rc = CIFSSMBLock(xid, tcon, netfid, length,
					 pfLock->fl_start, 1 /* numUnlock */ ,
					 0 /* numLock */ , lockType,
					 0 /* wait flag */ );
			pfLock->fl_type = F_UNLCK;
			if (rc != 0)
				cERROR(1, "Error unlocking previously locked "
					   "range %d during test of lock", rc);
			rc = 0;

		} else {
			/* if rc == ERR_SHARING_VIOLATION ? */
			rc = 0;

			if (lockType & LOCKING_ANDX_SHARED_LOCK) {
				pfLock->fl_type = F_WRLCK;
			} else {
				rc = CIFSSMBLock(xid, tcon, netfid, length,
					pfLock->fl_start, 0, 1,
					lockType | LOCKING_ANDX_SHARED_LOCK,
					0 /* wait flag */);
				if (rc == 0) {
					rc = CIFSSMBLock(xid, tcon, netfid,
						length, pfLock->fl_start, 1, 0,
						lockType |
						LOCKING_ANDX_SHARED_LOCK,
						0 /* wait flag */);
					pfLock->fl_type = F_RDLCK;
					if (rc != 0)
						cERROR(1, "Error unlocking "
						"previously locked range %d "
						"during test of lock", rc);
					rc = 0;
				} else {
					pfLock->fl_type = F_WRLCK;
					rc = 0;
				}
			}
		}

		FreeXid(xid);
		return rc;
	}

	if (!numLock && !numUnlock) {
		/* if no lock or unlock then nothing
		to do since we do not know what it is */
		FreeXid(xid);
		return -EOPNOTSUPP;
	}

	if (posix_locking) {
		int posix_lock_type;
		if (lockType & LOCKING_ANDX_SHARED_LOCK)
			posix_lock_type = CIFS_RDLCK;
		else
			posix_lock_type = CIFS_WRLCK;

		if (numUnlock == 1)
			posix_lock_type = CIFS_UNLCK;

		rc = CIFSSMBPosixLock(xid, tcon, netfid, 0 /* set */,
				      length, pfLock,
				      posix_lock_type, wait_flag);
	} else {
		struct cifsFileInfo *fid = file->private_data;

		if (numLock) {
			rc = CIFSSMBLock(xid, tcon, netfid, length,
					pfLock->fl_start,
					0, numLock, lockType, wait_flag);

			if (rc == 0) {
				/* For Windows locks we must store them. */
				rc = store_file_lock(fid, length,
						pfLock->fl_start, lockType);
			}
		} else if (numUnlock) {
			/* For each stored lock that this unlock overlaps
			   completely, unlock it. */
			int stored_rc = 0;
			struct cifsLockInfo *li, *tmp;

			rc = 0;
			mutex_lock(&fid->lock_mutex);
			list_for_each_entry_safe(li, tmp, &fid->llist, llist) {
				if (pfLock->fl_start <= li->offset &&
						(pfLock->fl_start + length) >=
						(li->offset + li->length)) {
					stored_rc = CIFSSMBLock(xid, tcon,
							netfid,
							li->length, li->offset,
							1, 0, li->type, false);
					if (stored_rc)
						rc = stored_rc;
					else {
						list_del(&li->llist);
						kfree(li);
					}
				}
			}
			mutex_unlock(&fid->lock_mutex);
		}
	}

	if (pfLock->fl_flags & FL_POSIX)
		posix_lock_file_wait(file, pfLock);
	FreeXid(xid);
	return rc;
}

/*
 * Set the timeout on write requests past EOF. For some servers (Windows)
 * these calls can be very long.
 *
 * If we're writing >10M past the EOF we give a 180s timeout. Anything less
 * than that gets a 45s timeout. Writes not past EOF get 15s timeouts.
 * The 10M cutoff is totally arbitrary. A better scheme for this would be
 * welcome if someone wants to suggest one.
 *
 * We may be able to do a better job with this if there were some way to
 * declare that a file should be sparse.
 */
static int
cifs_write_timeout(struct cifsInodeInfo *cifsi, loff_t offset)
{
	if (offset <= cifsi->server_eof)
		return CIFS_STD_OP;
	else if (offset > (cifsi->server_eof + (10 * 1024 * 1024)))
		return CIFS_VLONG_OP;
	else
		return CIFS_LONG_OP;
}

/* update the file size (if needed) after a write */
static void
cifs_update_eof(struct cifsInodeInfo *cifsi, loff_t offset,
		      unsigned int bytes_written)
{
	loff_t end_of_write = offset + bytes_written;

	if (end_of_write > cifsi->server_eof)
		cifsi->server_eof = end_of_write;
}

ssize_t cifs_user_write(struct file *file, const char __user *write_data,
	size_t write_size, loff_t *poffset)
{
	int rc = 0;
	unsigned int bytes_written = 0;
	unsigned int total_written;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid, long_op;
	struct cifsFileInfo *open_file;
	struct cifsInodeInfo *cifsi = CIFS_I(file->f_path.dentry->d_inode);

	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);

	pTcon = cifs_sb->tcon;

	/* cFYI(1, " write %d bytes to offset %lld of %s", write_size,
	   *poffset, file->f_path.dentry->d_name.name); */

	if (file->private_data == NULL)
		return -EBADF;
	open_file = file->private_data;

	rc = generic_write_checks(file, poffset, &write_size, 0);
	if (rc)
		return rc;

	xid = GetXid();

	long_op = cifs_write_timeout(cifsi, *poffset);
	for (total_written = 0; write_size > total_written;
	     total_written += bytes_written) {
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if (file->private_data == NULL) {
				/* file has been closed on us */
				FreeXid(xid);
			/* if we have gotten here we have written some data
			   and blocked, and the file has been freed on us while
			   we blocked so return what we managed to write */
				return total_written;
			}
			if (open_file->closePend) {
				FreeXid(xid);
				if (total_written)
					return total_written;
				else
					return -EBADF;
			}
			if (open_file->invalidHandle) {
				/* we could deadlock if we called
				   filemap_fdatawait from here so tell
				   reopen_file not to flush data to server
				   now */
				rc = cifs_reopen_file(file, false);
				if (rc != 0)
					break;
			}

			rc = CIFSSMBWrite(xid, pTcon,
				open_file->netfid,
				min_t(const int, cifs_sb->wsize,
				      write_size - total_written),
				*poffset, &bytes_written,
				NULL, write_data + total_written, long_op);
		}
		if (rc || (bytes_written == 0)) {
			if (total_written)
				break;
			else {
				FreeXid(xid);
				return rc;
			}
		} else {
			cifs_update_eof(cifsi, *poffset, bytes_written);
			*poffset += bytes_written;
		}
		long_op = CIFS_STD_OP; /* subsequent writes fast -
				    15 seconds is plenty */
	}

	cifs_stats_bytes_written(pTcon, total_written);

	/* since the write may have blocked check these pointers again */
	if ((file->f_path.dentry) && (file->f_path.dentry->d_inode)) {
		struct inode *inode = file->f_path.dentry->d_inode;
/* Do not update local mtime - server will set its actual value on write
 *		inode->i_ctime = inode->i_mtime =
 * 			current_fs_time(inode->i_sb);*/
		if (total_written > 0) {
			spin_lock(&inode->i_lock);
			if (*poffset > file->f_path.dentry->d_inode->i_size)
				i_size_write(file->f_path.dentry->d_inode,
					*poffset);
			spin_unlock(&inode->i_lock);
		}
		mark_inode_dirty_sync(file->f_path.dentry->d_inode);
	}
	FreeXid(xid);
	return total_written;
}

static ssize_t cifs_write(struct file *file, const char *write_data,
			  size_t write_size, loff_t *poffset)
{
	int rc = 0;
	unsigned int bytes_written = 0;
	unsigned int total_written;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid, long_op;
	struct cifsFileInfo *open_file;
	struct cifsInodeInfo *cifsi = CIFS_I(file->f_path.dentry->d_inode);

	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);

	pTcon = cifs_sb->tcon;

	cFYI(1, "write %zd bytes to offset %lld of %s", write_size,
	   *poffset, file->f_path.dentry->d_name.name);

	if (file->private_data == NULL)
		return -EBADF;
	open_file = file->private_data;

	xid = GetXid();

	long_op = cifs_write_timeout(cifsi, *poffset);
	for (total_written = 0; write_size > total_written;
	     total_written += bytes_written) {
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if (file->private_data == NULL) {
				/* file has been closed on us */
				FreeXid(xid);
			/* if we have gotten here we have written some data
			   and blocked, and the file has been freed on us
			   while we blocked so return what we managed to
			   write */
				return total_written;
			}
			if (open_file->closePend) {
				FreeXid(xid);
				if (total_written)
					return total_written;
				else
					return -EBADF;
			}
			if (open_file->invalidHandle) {
				/* we could deadlock if we called
				   filemap_fdatawait from here so tell
				   reopen_file not to flush data to
				   server now */
				rc = cifs_reopen_file(file, false);
				if (rc != 0)
					break;
			}
			if (experimEnabled || (pTcon->ses->server &&
				((pTcon->ses->server->secMode &
				(SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
				== 0))) {
				struct kvec iov[2];
				unsigned int len;

				len = min((size_t)cifs_sb->wsize,
					  write_size - total_written);
				/* iov[0] is reserved for smb header */
				iov[1].iov_base = (char *)write_data +
						  total_written;
				iov[1].iov_len = len;
				rc = CIFSSMBWrite2(xid, pTcon,
						open_file->netfid, len,
						*poffset, &bytes_written,
						iov, 1, long_op);
			} else
				rc = CIFSSMBWrite(xid, pTcon,
					 open_file->netfid,
					 min_t(const int, cifs_sb->wsize,
					       write_size - total_written),
					 *poffset, &bytes_written,
					 write_data + total_written,
					 NULL, long_op);
		}
		if (rc || (bytes_written == 0)) {
			if (total_written)
				break;
			else {
				FreeXid(xid);
				return rc;
			}
		} else {
			cifs_update_eof(cifsi, *poffset, bytes_written);
			*poffset += bytes_written;
		}
		long_op = CIFS_STD_OP; /* subsequent writes fast -
				    15 seconds is plenty */
	}

	cifs_stats_bytes_written(pTcon, total_written);

	/* since the write may have blocked check these pointers again */
	if ((file->f_path.dentry) && (file->f_path.dentry->d_inode)) {
/*BB We could make this contingent on superblock ATIME flag too */
/*		file->f_path.dentry->d_inode->i_ctime =
		file->f_path.dentry->d_inode->i_mtime = CURRENT_TIME;*/
		if (total_written > 0) {
			spin_lock(&file->f_path.dentry->d_inode->i_lock);
			if (*poffset > file->f_path.dentry->d_inode->i_size)
				i_size_write(file->f_path.dentry->d_inode,
					     *poffset);
			spin_unlock(&file->f_path.dentry->d_inode->i_lock);
		}
		mark_inode_dirty_sync(file->f_path.dentry->d_inode);
	}
	FreeXid(xid);
	return total_written;
}

#ifdef CONFIG_CIFS_EXPERIMENTAL
struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode)
{
	struct cifsFileInfo *open_file = NULL;

	read_lock(&GlobalSMBSeslock);
	/* we could simply get the first_list_entry since write-only entries
	   are always at the end of the list but since the first entry might
	   have a close pending, we go through the whole list */
	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
		if (open_file->closePend)
			continue;
		if (open_file->pfile && ((open_file->pfile->f_flags & O_RDWR) ||
		    (open_file->pfile->f_flags & O_RDONLY))) {
			if (!open_file->invalidHandle) {
				/* found a good file */
				/* lock it so it will not be closed on us */
				cifsFileInfo_get(open_file);
				read_unlock(&GlobalSMBSeslock);
				return open_file;
			} /* else might as well continue, and look for
			     another, or simply have the caller reopen it
			     again rather than trying to fix this handle */
		} else /* write only file */
			break; /* write only files are last so must be done */
	}
	read_unlock(&GlobalSMBSeslock);
	return NULL;
}
#endif

struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode)
{
	struct cifsFileInfo *open_file;
	bool any_available = false;
	int rc;

	/* Having a null inode here (because mapping->host was set to zero by
	the VFS or MM) should not happen but we had reports of on oops (due to
	it being zero) during stress testcases so we need to check for it */

	if (cifs_inode == NULL) {
		cERROR(1, "Null inode passed to cifs_writeable_file");
		dump_stack();
		return NULL;
	}

	read_lock(&GlobalSMBSeslock);
refind_writable:
	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
		if (open_file->closePend ||
		    (!any_available && open_file->pid != current->tgid))
			continue;

		if (open_file->pfile &&
		    ((open_file->pfile->f_flags & O_RDWR) ||
		     (open_file->pfile->f_flags & O_WRONLY))) {
			cifsFileInfo_get(open_file);

			if (!open_file->invalidHandle) {
				/* found a good writable file */
				read_unlock(&GlobalSMBSeslock);
				return open_file;
			}

			read_unlock(&GlobalSMBSeslock);
			/* Had to unlock since following call can block */
			rc = cifs_reopen_file(open_file->pfile, false);
			if (!rc) {
				if (!open_file->closePend)
					return open_file;
				else { /* start over in case this was deleted */
				       /* since the list could be modified */
					read_lock(&GlobalSMBSeslock);
					cifsFileInfo_put(open_file);
					goto refind_writable;
				}
			}

			/* if it fails, try another handle if possible -
			(we can not do this if closePending since
			loop could be modified - in which case we
			have to start at the beginning of the list
			again. Note that it would be bad
			to hold up writepages here (rather than
			in caller) with continuous retries */
			cFYI(1, "wp failed on reopen file");
			read_lock(&GlobalSMBSeslock);
			/* can not use this handle, no write
			   pending on this one after all */
			cifsFileInfo_put(open_file);

			if (open_file->closePend) /* list could have changed */
				goto refind_writable;
			/* else we simply continue to the next entry. Thus
			   we do not loop on reopen errors.  If we
			   can not reopen the file, for example if we
			   reconnected to a server with another client
			   racing to delete or lock the file we would not
			   make progress if we restarted before the beginning
			   of the loop here. */
		}
	}
	/* couldn't find useable FH with same pid, try any available */
	if (!any_available) {
		any_available = true;
		goto refind_writable;
	}
	read_unlock(&GlobalSMBSeslock);
	return NULL;
}

static int cifs_partialpagewrite(struct page *page, unsigned from, unsigned to)
{
	struct address_space *mapping = page->mapping;
	loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
	char *write_data;
	int rc = -EFAULT;
	int bytes_written = 0;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	struct inode *inode;
	struct cifsFileInfo *open_file;

	if (!mapping || !mapping->host)
		return -EFAULT;

	inode = page->mapping->host;
	cifs_sb = CIFS_SB(inode->i_sb);
	pTcon = cifs_sb->tcon;

	offset += (loff_t)from;
	write_data = kmap(page);
	write_data += from;

	if ((to > PAGE_CACHE_SIZE) || (from > to)) {
		kunmap(page);
		return -EIO;
	}

	/* racing with truncate? */
	if (offset > mapping->host->i_size) {
		kunmap(page);
		return 0; /* don't care */
	}

	/* check to make sure that we are not extending the file */
	if (mapping->host->i_size - offset < (loff_t)to)
		to = (unsigned)(mapping->host->i_size - offset);

	open_file = find_writable_file(CIFS_I(mapping->host));
	if (open_file) {
		bytes_written = cifs_write(open_file->pfile, write_data,
					   to-from, &offset);
		cifsFileInfo_put(open_file);
		/* Does mm or vfs already set times? */
		inode->i_atime = inode->i_mtime = current_fs_time(inode->i_sb);
		if ((bytes_written > 0) && (offset))
			rc = 0;
		else if (bytes_written < 0)
			rc = bytes_written;
	} else {
		cFYI(1, "No writeable filehandles for inode");
		rc = -EIO;
	}

	kunmap(page);
	return rc;
}

static int cifs_writepages(struct address_space *mapping,
			   struct writeback_control *wbc)
{
	struct backing_dev_info *bdi = mapping->backing_dev_info;
	unsigned int bytes_to_write;
	unsigned int bytes_written;
	struct cifs_sb_info *cifs_sb;
	int done = 0;
	pgoff_t end;
	pgoff_t index;
	int range_whole = 0;
	struct kvec *iov;
	int len;
	int n_iov = 0;
	pgoff_t next;
	int nr_pages;
	__u64 offset = 0;
	struct cifsFileInfo *open_file;
	struct cifsInodeInfo *cifsi = CIFS_I(mapping->host);
	struct page *page;
	struct pagevec pvec;
	int rc = 0;
	int scanned = 0;
	int xid, long_op;

	cifs_sb = CIFS_SB(mapping->host->i_sb);

	/*
	 * If wsize is smaller that the page cache size, default to writing
	 * one page at a time via cifs_writepage
	 */
	if (cifs_sb->wsize < PAGE_CACHE_SIZE)
		return generic_writepages(mapping, wbc);

	if ((cifs_sb->tcon->ses) && (cifs_sb->tcon->ses->server))
		if (cifs_sb->tcon->ses->server->secMode &
				(SECMODE_SIGN_REQUIRED | SECMODE_SIGN_ENABLED))
			if (!experimEnabled)
				return generic_writepages(mapping, wbc);

	iov = kmalloc(32 * sizeof(struct kvec), GFP_KERNEL);
	if (iov == NULL)
		return generic_writepages(mapping, wbc);


	/*
	 * BB: Is this meaningful for a non-block-device file system?
	 * If it is, we should test it again after we do I/O
	 */
	if (wbc->nonblocking && bdi_write_congested(bdi)) {
		wbc->encountered_congestion = 1;
		kfree(iov);
		return 0;
	}

	xid = GetXid();

	pagevec_init(&pvec, 0);
	if (wbc->range_cyclic) {
		index = mapping->writeback_index; /* Start from prev offset */
		end = -1;
	} else {
		index = 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;
		scanned = 1;
	}
retry:
	while (!done && (index <= end) &&
	       (nr_pages = pagevec_lookup_tag(&pvec, mapping, &index,
			PAGECACHE_TAG_DIRTY,
			min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1))) {
		int first;
		unsigned int i;

		first = -1;
		next = 0;
		n_iov = 0;
		bytes_to_write = 0;

		for (i = 0; i < nr_pages; i++) {
			page = pvec.pages[i];
			/*
			 * At this point we hold neither mapping->tree_lock nor
			 * lock on the page itself: the page may be truncated or
			 * invalidated (changing page->mapping to NULL), or even
			 * swizzled back from swapper_space to tmpfs file
			 * mapping
			 */

			if (first < 0)
				lock_page(page);
			else if (!trylock_page(page))
				break;

			if (unlikely(page->mapping != mapping)) {
				unlock_page(page);
				break;
			}

			if (!wbc->range_cyclic && page->index > end) {
				done = 1;
				unlock_page(page);
				break;
			}

			if (next && (page->index != next)) {
				/* Not next consecutive page */
				unlock_page(page);
				break;
			}

			if (wbc->sync_mode != WB_SYNC_NONE)
				wait_on_page_writeback(page);

			if (PageWriteback(page) ||
					!clear_page_dirty_for_io(page)) {
				unlock_page(page);
				break;
			}

			/*
			 * This actually clears the dirty bit in the radix tree.
			 * See cifs_writepage() for more commentary.
			 */
			set_page_writeback(page);

			if (page_offset(page) >= mapping->host->i_size) {
				done = 1;
				unlock_page(page);
				end_page_writeback(page);
				break;
			}

			/*
			 * BB can we get rid of this?  pages are held by pvec
			 */
			page_cache_get(page);

			len = min(mapping->host->i_size - page_offset(page),
				  (loff_t)PAGE_CACHE_SIZE);

			/* reserve iov[0] for the smb header */
			n_iov++;
			iov[n_iov].iov_base = kmap(page);
			iov[n_iov].iov_len = len;
			bytes_to_write += len;

			if (first < 0) {
				first = i;
				offset = page_offset(page);
			}
			next = page->index + 1;
			if (bytes_to_write + PAGE_CACHE_SIZE > cifs_sb->wsize)
				break;
		}
		if (n_iov) {
			/* Search for a writable handle every time we call
			 * CIFSSMBWrite2.  We can't rely on the last handle
			 * we used to still be valid
			 */
			open_file = find_writable_file(CIFS_I(mapping->host));
			if (!open_file) {
				cERROR(1, "No writable handles for inode");
				rc = -EBADF;
			} else {
				long_op = cifs_write_timeout(cifsi, offset);
				rc = CIFSSMBWrite2(xid, cifs_sb->tcon,
						   open_file->netfid,
						   bytes_to_write, offset,
						   &bytes_written, iov, n_iov,
						   long_op);
				cifsFileInfo_put(open_file);
				cifs_update_eof(cifsi, offset, bytes_written);

				if (rc || bytes_written < bytes_to_write) {
					cERROR(1, "Write2 ret %d, wrote %d",
						  rc, bytes_written);
					/* BB what if continued retry is
					   requested via mount flags? */
					if (rc == -ENOSPC)
						set_bit(AS_ENOSPC, &mapping->flags);
					else
						set_bit(AS_EIO, &mapping->flags);
				} else {
					cifs_stats_bytes_written(cifs_sb->tcon,
								 bytes_written);
				}
			}
			for (i = 0; i < n_iov; i++) {
				page = pvec.pages[first + i];
				/* Should we also set page error on
				success rc but too little data written? */
				/* BB investigate retry logic on temporary
				server crash cases and how recovery works
				when page marked as error */
				if (rc)
					SetPageError(page);
				kunmap(page);
				unlock_page(page);
				end_page_writeback(page);
				page_cache_release(page);
			}
			if ((wbc->nr_to_write -= n_iov) <= 0)
				done = 1;
			index = next;
		} else
			/* Need to re-find the pages we skipped */
			index = pvec.pages[0]->index + 1;

		pagevec_release(&pvec);
	}
	if (!scanned && !done) {
		/*
		 * We hit the last page and there is more work to be done: wrap
		 * back to the start of the file
		 */
		scanned = 1;
		index = 0;
		goto retry;
	}
	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
		mapping->writeback_index = index;

	FreeXid(xid);
	kfree(iov);
	return rc;
}

static int cifs_writepage(struct page *page, struct writeback_control *wbc)
{
	int rc = -EFAULT;
	int xid;

	xid = GetXid();
/* BB add check for wbc flags */
	page_cache_get(page);
	if (!PageUptodate(page))
		cFYI(1, "ppw - page not up to date");

	/*
	 * Set the "writeback" flag, and clear "dirty" in the radix tree.
	 *
	 * A writepage() implementation always needs to do either this,
	 * or re-dirty the page with "redirty_page_for_writepage()" in
	 * the case of a failure.
	 *
	 * Just unlocking the page will cause the radix tree tag-bits
	 * to fail to update with the state of the page correctly.
	 */
	set_page_writeback(page);
	rc = cifs_partialpagewrite(page, 0, PAGE_CACHE_SIZE);
	SetPageUptodate(page); /* BB add check for error and Clearuptodate? */
	unlock_page(page);
	end_page_writeback(page);
	page_cache_release(page);
	FreeXid(xid);
	return rc;
}

static int cifs_write_end(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned copied,
			struct page *page, void *fsdata)
{
	int rc;
	struct inode *inode = mapping->host;

	cFYI(1, "write_end for page %p from pos %lld with %d bytes",
		 page, pos, copied);

	if (PageChecked(page)) {
		if (copied == len)
			SetPageUptodate(page);
		ClearPageChecked(page);
	} else if (!PageUptodate(page) && copied == PAGE_CACHE_SIZE)
		SetPageUptodate(page);

	if (!PageUptodate(page)) {
		char *page_data;
		unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
		int xid;

		xid = GetXid();
		/* this is probably better than directly calling
		   partialpage_write since in this function the file handle is
		   known which we might as well	leverage */
		/* BB check if anything else missing out of ppw
		   such as updating last write time */
		page_data = kmap(page);
		rc = cifs_write(file, page_data + offset, copied, &pos);
		/* if (rc < 0) should we set writebehind rc? */
		kunmap(page);

		FreeXid(xid);
	} else {
		rc = copied;
		pos += copied;
		set_page_dirty(page);
	}

	if (rc > 0) {
		spin_lock(&inode->i_lock);
		if (pos > inode->i_size)
			i_size_write(inode, pos);
		spin_unlock(&inode->i_lock);
	}

	unlock_page(page);
	page_cache_release(page);

	return rc;
}

int cifs_fsync(struct file *file, int datasync)
{
	int xid;
	int rc = 0;
	struct cifsTconInfo *tcon;
	struct cifsFileInfo *smbfile = file->private_data;
	struct inode *inode = file->f_path.dentry->d_inode;

	xid = GetXid();

	cFYI(1, "Sync file - name: %s datasync: 0x%x",
		file->f_path.dentry->d_name.name, datasync);

	rc = filemap_write_and_wait(inode->i_mapping);
	if (rc == 0) {
		rc = CIFS_I(inode)->write_behind_rc;
		CIFS_I(inode)->write_behind_rc = 0;
		tcon = CIFS_SB(inode->i_sb)->tcon;
		if (!rc && tcon && smbfile &&
		   !(CIFS_SB(inode->i_sb)->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC))
			rc = CIFSSMBFlush(xid, tcon, smbfile->netfid);
	}

	FreeXid(xid);
	return rc;
}

/* static void cifs_sync_page(struct page *page)
{
	struct address_space *mapping;
	struct inode *inode;
	unsigned long index = page->index;
	unsigned int rpages = 0;
	int rc = 0;

	cFYI(1, "sync page %p", page);
	mapping = page->mapping;
	if (!mapping)
		return 0;
	inode = mapping->host;
	if (!inode)
		return; */

/*	fill in rpages then
	result = cifs_pagein_inode(inode, index, rpages); */ /* BB finish */

/*	cFYI(1, "rpages is %d for sync page of Index %ld", rpages, index);

#if 0
	if (rc < 0)
		return rc;
	return 0;
#endif
} */

/*
 * As file closes, flush all cached write data for this inode checking
 * for write behind errors.
 */
int cifs_flush(struct file *file, fl_owner_t id)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	int rc = 0;

	/* Rather than do the steps manually:
	   lock the inode for writing
	   loop through pages looking for write behind data (dirty pages)
	   coalesce into contiguous 16K (or smaller) chunks to write to server
	   send to server (prefer in parallel)
	   deal with writebehind errors
	   unlock inode for writing
	   filemapfdatawrite appears easier for the time being */

	rc = filemap_fdatawrite(inode->i_mapping);
	/* reset wb rc if we were able to write out dirty pages */
	if (!rc) {
		rc = CIFS_I(inode)->write_behind_rc;
		CIFS_I(inode)->write_behind_rc = 0;
	}

	cFYI(1, "Flush inode %p file %p rc %d", inode, file, rc);

	return rc;
}

ssize_t cifs_user_read(struct file *file, char __user *read_data,
	size_t read_size, loff_t *poffset)
{
	int rc = -EACCES;
	unsigned int bytes_read = 0;
	unsigned int total_read = 0;
	unsigned int current_read_size;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid;
	struct cifsFileInfo *open_file;
	char *smb_read_data;
	char __user *current_offset;
	struct smb_com_read_rsp *pSMBr;

	xid = GetXid();
	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	pTcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		rc = -EBADF;
		FreeXid(xid);
		return rc;
	}
	open_file = file->private_data;

	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
		cFYI(1, "attempting read on write only file instance");

	for (total_read = 0, current_offset = read_data;
	     read_size > total_read;
	     total_read += bytes_read, current_offset += bytes_read) {
		current_read_size = min_t(const int, read_size - total_read,
					  cifs_sb->rsize);
		rc = -EAGAIN;
		smb_read_data = NULL;
		while (rc == -EAGAIN) {
			int buf_type = CIFS_NO_BUFFER;
			if ((open_file->invalidHandle) &&
			    (!open_file->closePend)) {
				rc = cifs_reopen_file(file, true);
				if (rc != 0)
					break;
			}
			rc = CIFSSMBRead(xid, pTcon,
					 open_file->netfid,
					 current_read_size, *poffset,
					 &bytes_read, &smb_read_data,
					 &buf_type);
			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
			if (smb_read_data) {
				if (copy_to_user(current_offset,
						smb_read_data +
						4 /* RFC1001 length field */ +
						le16_to_cpu(pSMBr->DataOffset),
						bytes_read))
					rc = -EFAULT;

				if (buf_type == CIFS_SMALL_BUFFER)
					cifs_small_buf_release(smb_read_data);
				else if (buf_type == CIFS_LARGE_BUFFER)
					cifs_buf_release(smb_read_data);
				smb_read_data = NULL;
			}
		}
		if (rc || (bytes_read == 0)) {
			if (total_read) {
				break;
			} else {
				FreeXid(xid);
				return rc;
			}
		} else {
			cifs_stats_bytes_read(pTcon, bytes_read);
			*poffset += bytes_read;
		}
	}
	FreeXid(xid);
	return total_read;
}


static ssize_t cifs_read(struct file *file, char *read_data, size_t read_size,
	loff_t *poffset)
{
	int rc = -EACCES;
	unsigned int bytes_read = 0;
	unsigned int total_read;
	unsigned int current_read_size;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	int xid;
	char *current_offset;
	struct cifsFileInfo *open_file;
	int buf_type = CIFS_NO_BUFFER;

	xid = GetXid();
	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	pTcon = cifs_sb->tcon;

	if (file->private_data == NULL) {
		rc = -EBADF;
		FreeXid(xid);
		return rc;
	}
	open_file = file->private_data;

	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
		cFYI(1, "attempting read on write only file instance");

	for (total_read = 0, current_offset = read_data;
	     read_size > total_read;
	     total_read += bytes_read, current_offset += bytes_read) {
		current_read_size = min_t(const int, read_size - total_read,
					  cifs_sb->rsize);
		/* For windows me and 9x we do not want to request more
		than it negotiated since it will refuse the read then */
		if ((pTcon->ses) &&
			!(pTcon->ses->capabilities & CAP_LARGE_FILES)) {
			current_read_size = min_t(const int, current_read_size,
					pTcon->ses->server->maxBuf - 128);
		}
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if ((open_file->invalidHandle) &&
			    (!open_file->closePend)) {
				rc = cifs_reopen_file(file, true);
				if (rc != 0)
					break;
			}
			rc = CIFSSMBRead(xid, pTcon,
					 open_file->netfid,
					 current_read_size, *poffset,
					 &bytes_read, &current_offset,
					 &buf_type);
		}
		if (rc || (bytes_read == 0)) {
			if (total_read) {
				break;
			} else {
				FreeXid(xid);
				return rc;
			}
		} else {
			cifs_stats_bytes_read(pTcon, total_read);
			*poffset += bytes_read;
		}
	}
	FreeXid(xid);
	return total_read;
}

int cifs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	int rc, xid;

	xid = GetXid();
	rc = cifs_revalidate_file(file);
	if (rc) {
		cFYI(1, "Validation prior to mmap failed, error=%d", rc);
		FreeXid(xid);
		return rc;
	}
	rc = generic_file_mmap(file, vma);
	FreeXid(xid);
	return rc;
}


static void cifs_copy_cache_pages(struct address_space *mapping,
	struct list_head *pages, int bytes_read, char *data)
{
	struct page *page;
	char *target;

	while (bytes_read > 0) {
		if (list_empty(pages))
			break;

		page = list_entry(pages->prev, struct page, lru);
		list_del(&page->lru);

		if (add_to_page_cache_lru(page, mapping, page->index,
				      GFP_KERNEL)) {
			page_cache_release(page);
			cFYI(1, "Add page cache failed");
			data += PAGE_CACHE_SIZE;
			bytes_read -= PAGE_CACHE_SIZE;
			continue;
		}
		page_cache_release(page);

		target = kmap_atomic(page, KM_USER0);

		if (PAGE_CACHE_SIZE > bytes_read) {
			memcpy(target, data, bytes_read);
			/* zero the tail end of this partial page */
			memset(target + bytes_read, 0,
			       PAGE_CACHE_SIZE - bytes_read);
			bytes_read = 0;
		} else {
			memcpy(target, data, PAGE_CACHE_SIZE);
			bytes_read -= PAGE_CACHE_SIZE;
		}
		kunmap_atomic(target, KM_USER0);

		flush_dcache_page(page);
		SetPageUptodate(page);
		unlock_page(page);
		data += PAGE_CACHE_SIZE;

		/* add page to FS-Cache */
		cifs_readpage_to_fscache(mapping->host, page);
	}
	return;
}

static int cifs_readpages(struct file *file, struct address_space *mapping,
	struct list_head *page_list, unsigned num_pages)
{
	int rc = -EACCES;
	int xid;
	loff_t offset;
	struct page *page;
	struct cifs_sb_info *cifs_sb;
	struct cifsTconInfo *pTcon;
	unsigned int bytes_read = 0;
	unsigned int read_size, i;
	char *smb_read_data = NULL;
	struct smb_com_read_rsp *pSMBr;
	struct cifsFileInfo *open_file;
	int buf_type = CIFS_NO_BUFFER;

	xid = GetXid();
	if (file->private_data == NULL) {
		rc = -EBADF;
		FreeXid(xid);
		return rc;
	}
	open_file = file->private_data;
	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	pTcon = cifs_sb->tcon;

	/*
	 * Reads as many pages as possible from fscache. Returns -ENOBUFS
	 * immediately if the cookie is negative
	 */
	rc = cifs_readpages_from_fscache(mapping->host, mapping, page_list,
					 &num_pages);
	if (rc == 0)
		goto read_complete;

	cFYI(DBG2, "rpages: num pages %d", num_pages);
	for (i = 0; i < num_pages; ) {
		unsigned contig_pages;
		struct page *tmp_page;
		unsigned long expected_index;

		if (list_empty(page_list))
			break;

		page = list_entry(page_list->prev, struct page, lru);
		offset = (loff_t)page->index << PAGE_CACHE_SHIFT;

		/* count adjacent pages that we will read into */
		contig_pages = 0;
		expected_index =
			list_entry(page_list->prev, struct page, lru)->index;
		list_for_each_entry_reverse(tmp_page, page_list, lru) {
			if (tmp_page->index == expected_index) {
				contig_pages++;
				expected_index++;
			} else
				break;
		}
		if (contig_pages + i >  num_pages)
			contig_pages = num_pages - i;

		/* for reads over a certain size could initiate async
		   read ahead */

		read_size = contig_pages * PAGE_CACHE_SIZE;
		/* Read size needs to be in multiples of one page */
		read_size = min_t(const unsigned int, read_size,
				  cifs_sb->rsize & PAGE_CACHE_MASK);
		cFYI(DBG2, "rpages: read size 0x%x  contiguous pages %d",
				read_size, contig_pages);
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if ((open_file->invalidHandle) &&
			    (!open_file->closePend)) {
				rc = cifs_reopen_file(file, true);
				if (rc != 0)
					break;
			}

			rc = CIFSSMBRead(xid, pTcon,
					 open_file->netfid,
					 read_size, offset,
					 &bytes_read, &smb_read_data,
					 &buf_type);
			/* BB more RC checks ? */
			if (rc == -EAGAIN) {
				if (smb_read_data) {
					if (buf_type == CIFS_SMALL_BUFFER)
						cifs_small_buf_release(smb_read_data);
					else if (buf_type == CIFS_LARGE_BUFFER)
						cifs_buf_release(smb_read_data);
					smb_read_data = NULL;
				}
			}
		}
		if ((rc < 0) || (smb_read_data == NULL)) {
			cFYI(1, "Read error in readpages: %d", rc);
			break;
		} else if (bytes_read > 0) {
			task_io_account_read(bytes_read);
			pSMBr = (struct smb_com_read_rsp *)smb_read_data;
			cifs_copy_cache_pages(mapping, page_list, bytes_read,
				smb_read_data + 4 /* RFC1001 hdr */ +
				le16_to_cpu(pSMBr->DataOffset));

			i +=  bytes_read >> PAGE_CACHE_SHIFT;
			cifs_stats_bytes_read(pTcon, bytes_read);
			if ((bytes_read & PAGE_CACHE_MASK) != bytes_read) {
				i++; /* account for partial page */

				/* server copy of file can have smaller size
				   than client */
				/* BB do we need to verify this common case ?
				   this case is ok - if we are at server EOF
				   we will hit it on next read */

				/* break; */
			}
		} else {
			cFYI(1, "No bytes read (%d) at offset %lld . "
				"Cleaning remaining pages from readahead list",
				bytes_read, offset);
			/* BB turn off caching and do new lookup on
			   file size at server? */
			break;
		}
		if (smb_read_data) {
			if (buf_type == CIFS_SMALL_BUFFER)
				cifs_small_buf_release(smb_read_data);
			else if (buf_type == CIFS_LARGE_BUFFER)
				cifs_buf_release(smb_read_data);
			smb_read_data = NULL;
		}
		bytes_read = 0;
	}

/* need to free smb_read_data buf before exit */
	if (smb_read_data) {
		if (buf_type == CIFS_SMALL_BUFFER)
			cifs_small_buf_release(smb_read_data);
		else if (buf_type == CIFS_LARGE_BUFFER)
			cifs_buf_release(smb_read_data);
		smb_read_data = NULL;
	}

read_complete:
	FreeXid(xid);
	return rc;
}

static int cifs_readpage_worker(struct file *file, struct page *page,
	loff_t *poffset)
{
	char *read_data;
	int rc;

	/* Is the page cached? */
	rc = cifs_readpage_from_fscache(file->f_path.dentry->d_inode, page);
	if (rc == 0)
		goto read_complete;

	page_cache_get(page);
	read_data = kmap(page);
	/* for reads over a certain size could initiate async read ahead */

	rc = cifs_read(file, read_data, PAGE_CACHE_SIZE, poffset);

	if (rc < 0)
		goto io_error;
	else
		cFYI(1, "Bytes read %d", rc);

	file->f_path.dentry->d_inode->i_atime =
		current_fs_time(file->f_path.dentry->d_inode->i_sb);

	if (PAGE_CACHE_SIZE > rc)
		memset(read_data + rc, 0, PAGE_CACHE_SIZE - rc);

	flush_dcache_page(page);
	SetPageUptodate(page);

	/* send this page to the cache */
	cifs_readpage_to_fscache(file->f_path.dentry->d_inode, page);

	rc = 0;

io_error:
	kunmap(page);
	page_cache_release(page);

read_complete:
	return rc;
}

static int cifs_readpage(struct file *file, struct page *page)
{
	loff_t offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
	int rc = -EACCES;
	int xid;

	xid = GetXid();

	if (file->private_data == NULL) {
		rc = -EBADF;
		FreeXid(xid);
		return rc;
	}

	cFYI(1, "readpage %p at offset %d 0x%x\n",
		 page, (int)offset, (int)offset);

	rc = cifs_readpage_worker(file, page, &offset);

	unlock_page(page);

	FreeXid(xid);
	return rc;
}

static int is_inode_writable(struct cifsInodeInfo *cifs_inode)
{
	struct cifsFileInfo *open_file;

	read_lock(&GlobalSMBSeslock);
	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
		if (open_file->closePend)
			continue;
		if (open_file->pfile &&
		    ((open_file->pfile->f_flags & O_RDWR) ||
		     (open_file->pfile->f_flags & O_WRONLY))) {
			read_unlock(&GlobalSMBSeslock);
			return 1;
		}
	}
	read_unlock(&GlobalSMBSeslock);
	return 0;
}

/* We do not want to update the file size from server for inodes
   open for write - to avoid races with writepage extending
   the file - in the future we could consider allowing
   refreshing the inode only on increases in the file size
   but this is tricky to do without racing with writebehind
   page caching in the current Linux kernel design */
bool is_size_safe_to_change(struct cifsInodeInfo *cifsInode, __u64 end_of_file)
{
	if (!cifsInode)
		return true;

	if (is_inode_writable(cifsInode)) {
		/* This inode is open for write at least once */
		struct cifs_sb_info *cifs_sb;

		cifs_sb = CIFS_SB(cifsInode->vfs_inode.i_sb);
		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_DIRECT_IO) {
			/* since no page cache to corrupt on directio
			we can change size safely */
			return true;
		}

		if (i_size_read(&cifsInode->vfs_inode) < end_of_file)
			return true;

		return false;
	} else
		return true;
}

static int cifs_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len, unsigned flags,
			struct page **pagep, void **fsdata)
{
	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
	loff_t offset = pos & (PAGE_CACHE_SIZE - 1);
	loff_t page_start = pos & PAGE_MASK;
	loff_t i_size;
	struct page *page;
	int rc = 0;

	cFYI(1, "write_begin from %lld len %d", (long long)pos, len);

	page = grab_cache_page_write_begin(mapping, index, flags);
	if (!page) {
		rc = -ENOMEM;
		goto out;
	}

	if (PageUptodate(page))
		goto out;

	/*
	 * If we write a full page it will be up to date, no need to read from
	 * the server. If the write is short, we'll end up doing a sync write
	 * instead.
	 */
	if (len == PAGE_CACHE_SIZE)
		goto out;

	/*
	 * optimize away the read when we have an oplock, and we're not
	 * expecting to use any of the data we'd be reading in. That
	 * is, when the page lies beyond the EOF, or straddles the EOF
	 * and the write will cover all of the existing data.
	 */
	if (CIFS_I(mapping->host)->clientCanCacheRead) {
		i_size = i_size_read(mapping->host);
		if (page_start >= i_size ||
		    (offset == 0 && (pos + len) >= i_size)) {
			zero_user_segments(page, 0, offset,
					   offset + len,
					   PAGE_CACHE_SIZE);
			/*
			 * PageChecked means that the parts of the page
			 * to which we're not writing are considered up
			 * to date. Once the data is copied to the
			 * page, it can be set uptodate.
			 */
			SetPageChecked(page);
			goto out;
		}
	}

	if ((file->f_flags & O_ACCMODE) != O_WRONLY) {
		/*
		 * might as well read a page, it is fast enough. If we get
		 * an error, we don't need to return it. cifs_write_end will
		 * do a sync write instead since PG_uptodate isn't set.
		 */
		cifs_readpage_worker(file, page, &page_start);
	} else {
		/* we could try using another file handle if there is one -
		   but how would we lock it to prevent close of that handle
		   racing with this read? In any case
		   this will be written out by write_end so is fine */
	}
out:
	*pagep = page;
	return rc;
}

static int cifs_release_page(struct page *page, gfp_t gfp)
{
	if (PagePrivate(page))
		return 0;

	return cifs_fscache_release_page(page, gfp);
}

static void cifs_invalidate_page(struct page *page, unsigned long offset)
{
	struct cifsInodeInfo *cifsi = CIFS_I(page->mapping->host);

	if (offset == 0)
		cifs_fscache_invalidate_page(page, &cifsi->vfs_inode);
}

static void
cifs_oplock_break(struct slow_work *work)
{
	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
						  oplock_break);
	struct inode *inode = cfile->pInode;
	struct cifsInodeInfo *cinode = CIFS_I(inode);
	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->mnt->mnt_sb);
	int rc, waitrc = 0;

	if (inode && S_ISREG(inode->i_mode)) {
		if (cinode->clientCanCacheRead)
			break_lease(inode, O_RDONLY);
		else
			break_lease(inode, O_WRONLY);
		rc = filemap_fdatawrite(inode->i_mapping);
		if (cinode->clientCanCacheRead == 0) {
			waitrc = filemap_fdatawait(inode->i_mapping);
			invalidate_remote_inode(inode);
		}
		if (!rc)
			rc = waitrc;
		if (rc)
			cinode->write_behind_rc = rc;
		cFYI(1, "Oplock flush inode %p rc %d", inode, rc);
	}

	/*
	 * releasing stale oplock after recent reconnect of smb session using
	 * a now incorrect file handle is not a data integrity issue but do
	 * not bother sending an oplock release if session to server still is
	 * disconnected since oplock already released by the server
	 */
	if (!cfile->closePend && !cfile->oplock_break_cancelled) {
		rc = CIFSSMBLock(0, cifs_sb->tcon, cfile->netfid, 0, 0, 0, 0,
				 LOCKING_ANDX_OPLOCK_RELEASE, false);
		cFYI(1, "Oplock release rc = %d", rc);
	}
}

static int
cifs_oplock_break_get(struct slow_work *work)
{
	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
						  oplock_break);
	mntget(cfile->mnt);
	cifsFileInfo_get(cfile);
	return 0;
}

static void
cifs_oplock_break_put(struct slow_work *work)
{
	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
						  oplock_break);
	mntput(cfile->mnt);
	cifsFileInfo_put(cfile);
}

const struct slow_work_ops cifs_oplock_break_ops = {
	.get_ref	= cifs_oplock_break_get,
	.put_ref	= cifs_oplock_break_put,
	.execute	= cifs_oplock_break,
};

const struct address_space_operations cifs_addr_ops = {
	.readpage = cifs_readpage,
	.readpages = cifs_readpages,
	.writepage = cifs_writepage,
	.writepages = cifs_writepages,
	.write_begin = cifs_write_begin,
	.write_end = cifs_write_end,
	.set_page_dirty = __set_page_dirty_nobuffers,
	.releasepage = cifs_release_page,
	.invalidatepage = cifs_invalidate_page,
	/* .sync_page = cifs_sync_page, */
	/* .direct_IO = */
};

/*
 * cifs_readpages requires the server to support a buffer large enough to
 * contain the header plus one complete page of data.  Otherwise, we need
 * to leave cifs_readpages out of the address space operations.
 */
const struct address_space_operations cifs_addr_ops_smallbuf = {
	.readpage = cifs_readpage,
	.writepage = cifs_writepage,
	.writepages = cifs_writepages,
	.write_begin = cifs_write_begin,
	.write_end = cifs_write_end,
	.set_page_dirty = __set_page_dirty_nobuffers,
	.releasepage = cifs_release_page,
	.invalidatepage = cifs_invalidate_page,
	/* .sync_page = cifs_sync_page, */
	/* .direct_IO = */
};