summaryrefslogtreecommitdiffstats
path: root/fs/cifs/file.c
blob: 8a781226ae33eae5bff03ab5d977ebff25069f67 (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
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
/*
 *   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 <linux/swap.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 u32 cifs_posix_convert_flags(unsigned int flags)
{
	u32 posix_flags = 0;

	if ((flags & O_ACCMODE) == O_RDONLY)
		posix_flags = SMB_O_RDONLY;
	else if ((flags & O_ACCMODE) == O_WRONLY)
		posix_flags = SMB_O_WRONLY;
	else if ((flags & O_ACCMODE) == O_RDWR)
		posix_flags = SMB_O_RDWR;

	if (flags & O_CREAT)
		posix_flags |= SMB_O_CREAT;
	if (flags & O_EXCL)
		posix_flags |= SMB_O_EXCL;
	if (flags & O_TRUNC)
		posix_flags |= SMB_O_TRUNC;
	/* be safe and imply O_SYNC for O_DSYNC */
	if (flags & O_DSYNC)
		posix_flags |= SMB_O_SYNC;
	if (flags & O_DIRECTORY)
		posix_flags |= SMB_O_DIRECTORY;
	if (flags & O_NOFOLLOW)
		posix_flags |= SMB_O_NOFOLLOW;
	if (flags & O_DIRECT)
		posix_flags |= SMB_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;
}

int cifs_posix_open(char *full_path, struct inode **pinode,
			struct super_block *sb, int mode, unsigned int f_flags,
			__u32 *poplock, __u16 *pnetfid, unsigned int xid)
{
	int rc;
	FILE_UNIX_BASIC_INFO *presp_data;
	__u32 posix_flags = 0;
	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
	struct cifs_fattr fattr;
	struct tcon_link *tlink;
	struct cifs_tcon *tcon;

	cFYI(1, "posix open %s", full_path);

	presp_data = kzalloc(sizeof(FILE_UNIX_BASIC_INFO), GFP_KERNEL);
	if (presp_data == NULL)
		return -ENOMEM;

	tlink = cifs_sb_tlink(cifs_sb);
	if (IS_ERR(tlink)) {
		rc = PTR_ERR(tlink);
		goto posix_open_ret;
	}

	tcon = tlink_tcon(tlink);
	mode &= ~current_umask();

	posix_flags = cifs_posix_convert_flags(f_flags);
	rc = CIFSPOSIXCreate(xid, tcon, posix_flags, mode, pnetfid, presp_data,
			     poplock, full_path, cifs_sb->local_nls,
			     cifs_sb->mnt_cifs_flags &
					CIFS_MOUNT_MAP_SPECIAL_CHR);
	cifs_put_tlink(tlink);

	if (rc)
		goto posix_open_ret;

	if (presp_data->Type == cpu_to_le32(-1))
		goto posix_open_ret; /* open ok, caller does qpathinfo */

	if (!pinode)
		goto posix_open_ret; /* caller does not need info */

	cifs_unix_basic_to_fattr(&fattr, presp_data, cifs_sb);

	/* get new inode and set it up */
	if (*pinode == NULL) {
		cifs_fill_uniqueid(sb, &fattr);
		*pinode = cifs_iget(sb, &fattr);
		if (!*pinode) {
			rc = -ENOMEM;
			goto posix_open_ret;
		}
	} else {
		cifs_fattr_to_inode(*pinode, &fattr);
	}

posix_open_ret:
	kfree(presp_data);
	return rc;
}

static int
cifs_nt_open(char *full_path, struct inode *inode, struct cifs_sb_info *cifs_sb,
	     struct cifs_tcon *tcon, unsigned int f_flags, __u32 *oplock,
	     struct cifs_fid *fid, unsigned int xid)
{
	int rc;
	int desired_access;
	int disposition;
	int create_options = CREATE_NOT_DIR;
	FILE_ALL_INFO *buf;

	if (!tcon->ses->server->ops->open)
		return -ENOSYS;

	desired_access = cifs_convert_flags(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(f_flags);

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

	buf = kmalloc(sizeof(FILE_ALL_INFO), GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	if (backup_cred(cifs_sb))
		create_options |= CREATE_OPEN_BACKUP_INTENT;

	rc = tcon->ses->server->ops->open(xid, tcon, full_path, disposition,
					  desired_access, create_options, fid,
					  oplock, buf, cifs_sb);

	if (rc)
		goto out;

	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, buf, inode->i_sb,
					 xid, &fid->netfid);

out:
	kfree(buf);
	return rc;
}

struct cifsFileInfo *
cifs_new_fileinfo(struct cifs_fid *fid, struct file *file,
		  struct tcon_link *tlink, __u32 oplock)
{
	struct dentry *dentry = file->f_path.dentry;
	struct inode *inode = dentry->d_inode;
	struct cifsInodeInfo *cinode = CIFS_I(inode);
	struct cifsFileInfo *cfile;

	cfile = kzalloc(sizeof(struct cifsFileInfo), GFP_KERNEL);
	if (cfile == NULL)
		return cfile;

	cfile->count = 1;
	cfile->pid = current->tgid;
	cfile->uid = current_fsuid();
	cfile->dentry = dget(dentry);
	cfile->f_flags = file->f_flags;
	cfile->invalidHandle = false;
	cfile->tlink = cifs_get_tlink(tlink);
	mutex_init(&cfile->fh_mutex);
	INIT_WORK(&cfile->oplock_break, cifs_oplock_break);
	INIT_LIST_HEAD(&cfile->llist);
	tlink_tcon(tlink)->ses->server->ops->set_fid(cfile, fid, oplock);

	spin_lock(&cifs_file_list_lock);
	list_add(&cfile->tlist, &(tlink_tcon(tlink)->openFileList));
	/* if readable file instance put first in list*/
	if (file->f_mode & FMODE_READ)
		list_add(&cfile->flist, &cinode->openFileList);
	else
		list_add_tail(&cfile->flist, &cinode->openFileList);
	spin_unlock(&cifs_file_list_lock);

	file->private_data = cfile;
	return cfile;
}

static void cifs_del_lock_waiters(struct cifsLockInfo *lock);

struct cifsFileInfo *
cifsFileInfo_get(struct cifsFileInfo *cifs_file)
{
	spin_lock(&cifs_file_list_lock);
	cifsFileInfo_get_locked(cifs_file);
	spin_unlock(&cifs_file_list_lock);
	return cifs_file;
}

/*
 * Release a reference on the file private data. This may involve closing
 * the filehandle out on the server. Must be called without holding
 * cifs_file_list_lock.
 */
void cifsFileInfo_put(struct cifsFileInfo *cifs_file)
{
	struct inode *inode = cifs_file->dentry->d_inode;
	struct cifs_tcon *tcon = tlink_tcon(cifs_file->tlink);
	struct cifsInodeInfo *cifsi = CIFS_I(inode);
	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
	struct cifsLockInfo *li, *tmp;

	spin_lock(&cifs_file_list_lock);
	if (--cifs_file->count > 0) {
		spin_unlock(&cifs_file_list_lock);
		return;
	}

	/* remove it from the lists */
	list_del(&cifs_file->flist);
	list_del(&cifs_file->tlist);

	if (list_empty(&cifsi->openFileList)) {
		cFYI(1, "closing last open instance for inode %p",
			cifs_file->dentry->d_inode);
		/*
		 * In strict cache mode we need invalidate mapping on the last
		 * close  because it may cause a error when we open this file
		 * again and get at least level II oplock.
		 */
		if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_STRICT_IO)
			CIFS_I(inode)->invalid_mapping = true;
		cifs_set_oplock_level(cifsi, 0);
	}
	spin_unlock(&cifs_file_list_lock);

	cancel_work_sync(&cifs_file->oplock_break);

	if (!tcon->need_reconnect && !cifs_file->invalidHandle) {
		struct TCP_Server_Info *server = tcon->ses->server;
		unsigned int xid;
		int rc = -ENOSYS;

		xid = get_xid();
		if (server->ops->close)
			rc = server->ops->close(xid, tcon, &cifs_file->fid);
		free_xid(xid);
	}

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

	cifs_put_tlink(cifs_file->tlink);
	dput(cifs_file->dentry);
	kfree(cifs_file);
}

int cifs_open(struct inode *inode, struct file *file)
{
	int rc = -EACCES;
	unsigned int xid;
	__u32 oplock;
	struct cifs_sb_info *cifs_sb;
	struct cifs_tcon *tcon;
	struct tcon_link *tlink;
	struct cifsFileInfo *cfile = NULL;
	char *full_path = NULL;
	bool posix_open_ok = false;
	struct cifs_fid fid;

	xid = get_xid();

	cifs_sb = CIFS_SB(inode->i_sb);
	tlink = cifs_sb_tlink(cifs_sb);
	if (IS_ERR(tlink)) {
		free_xid(xid);
		return PTR_ERR(tlink);
	}
	tcon = tlink_tcon(tlink);

	full_path = build_path_from_dentry(file->f_path.dentry);
	if (full_path == NULL) {
		rc = -ENOMEM;
		goto out;
	}

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

	if (tcon->ses->server->oplocks)
		oplock = REQ_OPLOCK;
	else
		oplock = 0;

	if (!tcon->broken_posix_open && tcon->unix_ext &&
	    cap_unix(tcon->ses) && (CIFS_UNIX_POSIX_PATH_OPS_CAP &
				le64_to_cpu(tcon->fsUnixInfo.Capability))) {
		/* 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 */,
				file->f_flags, &oplock, &fid.netfid, xid);
		if (rc == 0) {
			cFYI(1, "posix open succeeded");
			posix_open_ok = true;
		} 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.
		 */
	}

	if (!posix_open_ok) {
		rc = cifs_nt_open(full_path, inode, cifs_sb, tcon,
				  file->f_flags, &oplock, &fid, xid);
		if (rc)
			goto out;
	}

	cfile = cifs_new_fileinfo(&fid, file, tlink, oplock);
	if (cfile == NULL) {
		if (tcon->ses->server->ops->close)
			tcon->ses->server->ops->close(xid, tcon, &fid);
		rc = -ENOMEM;
		goto out;
	}

	cifs_fscache_set_inode_cookie(inode, file);

	if ((oplock & CIFS_CREATE_ACTION) && !posix_open_ok && tcon->unix_ext) {
		/*
		 * Time to set mode which we can not set earlier due to
		 * problems creating new read-only files.
		 */
		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,
		};
		CIFSSMBUnixSetFileInfo(xid, tcon, &args, fid.netfid,
				       cfile->pid);
	}

out:
	kfree(full_path);
	free_xid(xid);
	cifs_put_tlink(tlink);
	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 cifsFileInfo *cfile, bool can_flush)
{
	int rc = -EACCES;
	unsigned int xid;
	__u32 oplock;
	struct cifs_sb_info *cifs_sb;
	struct cifs_tcon *tcon;
	struct TCP_Server_Info *server;
	struct cifsInodeInfo *cinode;
	struct inode *inode;
	char *full_path = NULL;
	int desired_access;
	int disposition = FILE_OPEN;
	int create_options = CREATE_NOT_DIR;
	struct cifs_fid fid;

	xid = get_xid();
	mutex_lock(&cfile->fh_mutex);
	if (!cfile->invalidHandle) {
		mutex_unlock(&cfile->fh_mutex);
		rc = 0;
		free_xid(xid);
		return rc;
	}

	inode = cfile->dentry->d_inode;
	cifs_sb = CIFS_SB(inode->i_sb);
	tcon = tlink_tcon(cfile->tlink);
	server = tcon->ses->server;

	/*
	 * 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(cfile->dentry);
	if (full_path == NULL) {
		rc = -ENOMEM;
		mutex_unlock(&cfile->fh_mutex);
		free_xid(xid);
		return rc;
	}

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

	if (tcon->ses->server->oplocks)
		oplock = REQ_OPLOCK;
	else
		oplock = 0;

	if (tcon->unix_ext && cap_unix(tcon->ses) &&
	    (CIFS_UNIX_POSIX_PATH_OPS_CAP &
				le64_to_cpu(tcon->fsUnixInfo.Capability))) {
		/*
		 * O_CREAT, O_EXCL and O_TRUNC already had their effect on the
		 * original open. Must mask them off for a reopen.
		 */
		unsigned int oflags = cfile->f_flags &
						~(O_CREAT | O_EXCL | O_TRUNC);

		rc = cifs_posix_open(full_path, NULL, inode->i_sb,
				     cifs_sb->mnt_file_mode /* ignored */,
				     oflags, &oplock, &fid.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
		 */
	}

	desired_access = cifs_convert_flags(cfile->f_flags);

	if (backup_cred(cifs_sb))
		create_options |= CREATE_OPEN_BACKUP_INTENT;

	/*
	 * Can not refresh inode by passing in file_info buf to be returned by
	 * CIFSSMBOpen 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 = server->ops->open(xid, tcon, full_path, disposition,
			       desired_access, create_options, &fid, &oplock,
			       NULL, cifs_sb);
	if (rc) {
		mutex_unlock(&cfile->fh_mutex);
		cFYI(1, "cifs_reopen returned 0x%x", rc);
		cFYI(1, "oplock: %d", oplock);
		goto reopen_error_exit;
	}

reopen_success:
	cfile->invalidHandle = false;
	mutex_unlock(&cfile->fh_mutex);
	cinode = CIFS_I(inode);

	if (can_flush) {
		rc = filemap_write_and_wait(inode->i_mapping);
		mapping_set_error(inode->i_mapping, rc);

		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 inode info.
	 */

	server->ops->set_fid(cfile, &fid, oplock);
	cifs_relock_file(cfile);

reopen_error_exit:
	kfree(full_path);
	free_xid(xid);
	return rc;
}

int cifs_close(struct inode *inode, struct file *file)
{
	if (file->private_data != NULL) {
		cifsFileInfo_put(file->private_data);
		file->private_data = NULL;
	}

	/* return code from the ->release op is always ignored */
	return 0;
}

int cifs_closedir(struct inode *inode, struct file *file)
{
	int rc = 0;
	unsigned int xid;
	struct cifsFileInfo *cfile = file->private_data;
	struct cifs_tcon *tcon;
	struct TCP_Server_Info *server;
	char *buf;

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

	if (cfile == NULL)
		return rc;

	xid = get_xid();
	tcon = tlink_tcon(cfile->tlink);
	server = tcon->ses->server;

	cFYI(1, "Freeing private data in close dir");
	spin_lock(&cifs_file_list_lock);
	if (!cfile->srch_inf.endOfSearch && !cfile->invalidHandle) {
		cfile->invalidHandle = true;
		spin_unlock(&cifs_file_list_lock);
		if (server->ops->close_dir)
			rc = server->ops->close_dir(xid, tcon, &cfile->fid);
		else
			rc = -ENOSYS;
		cFYI(1, "Closing uncompleted readdir with rc %d", rc);
		/* not much we can do if it fails anyway, ignore rc */
		rc = 0;
	} else
		spin_unlock(&cifs_file_list_lock);

	buf = cfile->srch_inf.ntwrk_buf_start;
	if (buf) {
		cFYI(1, "closedir free smb buf in srch struct");
		cfile->srch_inf.ntwrk_buf_start = NULL;
		if (cfile->srch_inf.smallBuf)
			cifs_small_buf_release(buf);
		else
			cifs_buf_release(buf);
	}

	cifs_put_tlink(cfile->tlink);
	kfree(file->private_data);
	file->private_data = NULL;
	/* BB can we lock the filestruct while this is going on? */
	free_xid(xid);
	return rc;
}

static struct cifsLockInfo *
cifs_lock_init(__u64 offset, __u64 length, __u8 type)
{
	struct cifsLockInfo *lock =
		kmalloc(sizeof(struct cifsLockInfo), GFP_KERNEL);
	if (!lock)
		return lock;
	lock->offset = offset;
	lock->length = length;
	lock->type = type;
	lock->pid = current->tgid;
	INIT_LIST_HEAD(&lock->blist);
	init_waitqueue_head(&lock->block_q);
	return lock;
}

static void
cifs_del_lock_waiters(struct cifsLockInfo *lock)
{
	struct cifsLockInfo *li, *tmp;
	list_for_each_entry_safe(li, tmp, &lock->blist, blist) {
		list_del_init(&li->blist);
		wake_up(&li->block_q);
	}
}

static bool
cifs_find_fid_lock_conflict(struct cifsFileInfo *cfile, __u64 offset,
			    __u64 length, __u8 type, struct cifsFileInfo *cur,
			    struct cifsLockInfo **conf_lock)
{
	struct cifsLockInfo *li;
	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;

	list_for_each_entry(li, &cfile->llist, llist) {
		if (offset + length <= li->offset ||
		    offset >= li->offset + li->length)
			continue;
		else if ((type & server->vals->shared_lock_type) &&
			 ((server->ops->compare_fids(cur, cfile) &&
			   current->tgid == li->pid) || type == li->type))
			continue;
		else {
			*conf_lock = li;
			return true;
		}
	}
	return false;
}

static bool
cifs_find_lock_conflict(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
			__u8 type, struct cifsLockInfo **conf_lock)
{
	bool rc = false;
	struct cifsFileInfo *fid, *tmp;
	struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);

	spin_lock(&cifs_file_list_lock);
	list_for_each_entry_safe(fid, tmp, &cinode->openFileList, flist) {
		rc = cifs_find_fid_lock_conflict(fid, offset, length, type,
						 cfile, conf_lock);
		if (rc)
			break;
	}
	spin_unlock(&cifs_file_list_lock);

	return rc;
}

/*
 * Check if there is another lock that prevents us to set the lock (mandatory
 * style). If such a lock exists, update the flock structure with its
 * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
 * or leave it the same if we can't. Returns 0 if we don't need to request to
 * the server or 1 otherwise.
 */
static int
cifs_lock_test(struct cifsFileInfo *cfile, __u64 offset, __u64 length,
	       __u8 type, struct file_lock *flock)
{
	int rc = 0;
	struct cifsLockInfo *conf_lock;
	struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
	bool exist;

	mutex_lock(&cinode->lock_mutex);

	exist = cifs_find_lock_conflict(cfile, offset, length, type,
					&conf_lock);
	if (exist) {
		flock->fl_start = conf_lock->offset;
		flock->fl_end = conf_lock->offset + conf_lock->length - 1;
		flock->fl_pid = conf_lock->pid;
		if (conf_lock->type & server->vals->shared_lock_type)
			flock->fl_type = F_RDLCK;
		else
			flock->fl_type = F_WRLCK;
	} else if (!cinode->can_cache_brlcks)
		rc = 1;
	else
		flock->fl_type = F_UNLCK;

	mutex_unlock(&cinode->lock_mutex);
	return rc;
}

static void
cifs_lock_add(struct cifsFileInfo *cfile, struct cifsLockInfo *lock)
{
	struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
	mutex_lock(&cinode->lock_mutex);
	list_add_tail(&lock->llist, &cfile->llist);
	mutex_unlock(&cinode->lock_mutex);
}

/*
 * Set the byte-range lock (mandatory style). Returns:
 * 1) 0, if we set the lock and don't need to request to the server;
 * 2) 1, if no locks prevent us but we need to request to the server;
 * 3) -EACCESS, if there is a lock that prevents us and wait is false.
 */
static int
cifs_lock_add_if(struct cifsFileInfo *cfile, struct cifsLockInfo *lock,
		 bool wait)
{
	struct cifsLockInfo *conf_lock;
	struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
	bool exist;
	int rc = 0;

try_again:
	exist = false;
	mutex_lock(&cinode->lock_mutex);

	exist = cifs_find_lock_conflict(cfile, lock->offset, lock->length,
					lock->type, &conf_lock);
	if (!exist && cinode->can_cache_brlcks) {
		list_add_tail(&lock->llist, &cfile->llist);
		mutex_unlock(&cinode->lock_mutex);
		return rc;
	}

	if (!exist)
		rc = 1;
	else if (!wait)
		rc = -EACCES;
	else {
		list_add_tail(&lock->blist, &conf_lock->blist);
		mutex_unlock(&cinode->lock_mutex);
		rc = wait_event_interruptible(lock->block_q,
					(lock->blist.prev == &lock->blist) &&
					(lock->blist.next == &lock->blist));
		if (!rc)
			goto try_again;
		mutex_lock(&cinode->lock_mutex);
		list_del_init(&lock->blist);
	}

	mutex_unlock(&cinode->lock_mutex);
	return rc;
}

/*
 * Check if there is another lock that prevents us to set the lock (posix
 * style). If such a lock exists, update the flock structure with its
 * properties. Otherwise, set the flock type to F_UNLCK if we can cache brlocks
 * or leave it the same if we can't. Returns 0 if we don't need to request to
 * the server or 1 otherwise.
 */
static int
cifs_posix_lock_test(struct file *file, struct file_lock *flock)
{
	int rc = 0;
	struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode);
	unsigned char saved_type = flock->fl_type;

	if ((flock->fl_flags & FL_POSIX) == 0)
		return 1;

	mutex_lock(&cinode->lock_mutex);
	posix_test_lock(file, flock);

	if (flock->fl_type == F_UNLCK && !cinode->can_cache_brlcks) {
		flock->fl_type = saved_type;
		rc = 1;
	}

	mutex_unlock(&cinode->lock_mutex);
	return rc;
}

/*
 * Set the byte-range lock (posix style). Returns:
 * 1) 0, if we set the lock and don't need to request to the server;
 * 2) 1, if we need to request to the server;
 * 3) <0, if the error occurs while setting the lock.
 */
static int
cifs_posix_lock_set(struct file *file, struct file_lock *flock)
{
	struct cifsInodeInfo *cinode = CIFS_I(file->f_path.dentry->d_inode);
	int rc = 1;

	if ((flock->fl_flags & FL_POSIX) == 0)
		return rc;

try_again:
	mutex_lock(&cinode->lock_mutex);
	if (!cinode->can_cache_brlcks) {
		mutex_unlock(&cinode->lock_mutex);
		return rc;
	}

	rc = posix_lock_file(file, flock, NULL);
	mutex_unlock(&cinode->lock_mutex);
	if (rc == FILE_LOCK_DEFERRED) {
		rc = wait_event_interruptible(flock->fl_wait, !flock->fl_next);
		if (!rc)
			goto try_again;
		locks_delete_block(flock);
	}
	return rc;
}

static int
cifs_push_mandatory_locks(struct cifsFileInfo *cfile)
{
	unsigned int xid;
	int rc = 0, stored_rc;
	struct cifsLockInfo *li, *tmp;
	struct cifs_tcon *tcon;
	struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
	unsigned int num, max_num, max_buf;
	LOCKING_ANDX_RANGE *buf, *cur;
	int types[] = {LOCKING_ANDX_LARGE_FILES,
		       LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
	int i;

	xid = get_xid();
	tcon = tlink_tcon(cfile->tlink);

	mutex_lock(&cinode->lock_mutex);
	if (!cinode->can_cache_brlcks) {
		mutex_unlock(&cinode->lock_mutex);
		free_xid(xid);
		return rc;
	}

	/*
	 * Accessing maxBuf is racy with cifs_reconnect - need to store value
	 * and check it for zero before using.
	 */
	max_buf = tcon->ses->server->maxBuf;
	if (!max_buf) {
		mutex_unlock(&cinode->lock_mutex);
		free_xid(xid);
		return -EINVAL;
	}

	max_num = (max_buf - sizeof(struct smb_hdr)) /
						sizeof(LOCKING_ANDX_RANGE);
	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
	if (!buf) {
		mutex_unlock(&cinode->lock_mutex);
		free_xid(xid);
		return -ENOMEM;
	}

	for (i = 0; i < 2; i++) {
		cur = buf;
		num = 0;
		list_for_each_entry_safe(li, tmp, &cfile->llist, llist) {
			if (li->type != types[i])
				continue;
			cur->Pid = cpu_to_le16(li->pid);
			cur->LengthLow = cpu_to_le32((u32)li->length);
			cur->LengthHigh = cpu_to_le32((u32)(li->length>>32));
			cur->OffsetLow = cpu_to_le32((u32)li->offset);
			cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32));
			if (++num == max_num) {
				stored_rc = cifs_lockv(xid, tcon,
						       cfile->fid.netfid,
						       (__u8)li->type, 0, num,
						       buf);
				if (stored_rc)
					rc = stored_rc;
				cur = buf;
				num = 0;
			} else
				cur++;
		}

		if (num) {
			stored_rc = cifs_lockv(xid, tcon, cfile->fid.netfid,
					       (__u8)types[i], 0, num, buf);
			if (stored_rc)
				rc = stored_rc;
		}
	}

	cinode->can_cache_brlcks = false;
	mutex_unlock(&cinode->lock_mutex);

	kfree(buf);
	free_xid(xid);
	return rc;
}

/* copied from fs/locks.c with a name change */
#define cifs_for_each_lock(inode, lockp) \
	for (lockp = &inode->i_flock; *lockp != NULL; \
	     lockp = &(*lockp)->fl_next)

struct lock_to_push {
	struct list_head llist;
	__u64 offset;
	__u64 length;
	__u32 pid;
	__u16 netfid;
	__u8 type;
};

static int
cifs_push_posix_locks(struct cifsFileInfo *cfile)
{
	struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
	struct file_lock *flock, **before;
	unsigned int count = 0, i = 0;
	int rc = 0, xid, type;
	struct list_head locks_to_send, *el;
	struct lock_to_push *lck, *tmp;
	__u64 length;

	xid = get_xid();

	mutex_lock(&cinode->lock_mutex);
	if (!cinode->can_cache_brlcks) {
		mutex_unlock(&cinode->lock_mutex);
		free_xid(xid);
		return rc;
	}

	lock_flocks();
	cifs_for_each_lock(cfile->dentry->d_inode, before) {
		if ((*before)->fl_flags & FL_POSIX)
			count++;
	}
	unlock_flocks();

	INIT_LIST_HEAD(&locks_to_send);

	/*
	 * Allocating count locks is enough because no FL_POSIX locks can be
	 * added to the list while we are holding cinode->lock_mutex that
	 * protects locking operations of this inode.
	 */
	for (; i < count; i++) {
		lck = kmalloc(sizeof(struct lock_to_push), GFP_KERNEL);
		if (!lck) {
			rc = -ENOMEM;
			goto err_out;
		}
		list_add_tail(&lck->llist, &locks_to_send);
	}

	el = locks_to_send.next;
	lock_flocks();
	cifs_for_each_lock(cfile->dentry->d_inode, before) {
		flock = *before;
		if ((flock->fl_flags & FL_POSIX) == 0)
			continue;
		if (el == &locks_to_send) {
			/*
			 * The list ended. We don't have enough allocated
			 * structures - something is really wrong.
			 */
			cERROR(1, "Can't push all brlocks!");
			break;
		}
		length = 1 + flock->fl_end - flock->fl_start;
		if (flock->fl_type == F_RDLCK || flock->fl_type == F_SHLCK)
			type = CIFS_RDLCK;
		else
			type = CIFS_WRLCK;
		lck = list_entry(el, struct lock_to_push, llist);
		lck->pid = flock->fl_pid;
		lck->netfid = cfile->fid.netfid;
		lck->length = length;
		lck->type = type;
		lck->offset = flock->fl_start;
		el = el->next;
	}
	unlock_flocks();

	list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
		int stored_rc;

		stored_rc = CIFSSMBPosixLock(xid, tcon, lck->netfid, lck->pid,
					     lck->offset, lck->length, NULL,
					     lck->type, 0);
		if (stored_rc)
			rc = stored_rc;
		list_del(&lck->llist);
		kfree(lck);
	}

out:
	cinode->can_cache_brlcks = false;
	mutex_unlock(&cinode->lock_mutex);

	free_xid(xid);
	return rc;
err_out:
	list_for_each_entry_safe(lck, tmp, &locks_to_send, llist) {
		list_del(&lck->llist);
		kfree(lck);
	}
	goto out;
}

static int
cifs_push_locks(struct cifsFileInfo *cfile)
{
	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);

	if (cap_unix(tcon->ses) &&
	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
		return cifs_push_posix_locks(cfile);

	return cifs_push_mandatory_locks(cfile);
}

static void
cifs_read_flock(struct file_lock *flock, __u32 *type, int *lock, int *unlock,
		bool *wait_flag, struct TCP_Server_Info *server)
{
	if (flock->fl_flags & FL_POSIX)
		cFYI(1, "Posix");
	if (flock->fl_flags & FL_FLOCK)
		cFYI(1, "Flock");
	if (flock->fl_flags & FL_SLEEP) {
		cFYI(1, "Blocking lock");
		*wait_flag = true;
	}
	if (flock->fl_flags & FL_ACCESS)
		cFYI(1, "Process suspended by mandatory locking - "
			"not implemented yet");
	if (flock->fl_flags & FL_LEASE)
		cFYI(1, "Lease on file - not implemented yet");
	if (flock->fl_flags &
	    (~(FL_POSIX | FL_FLOCK | FL_SLEEP | FL_ACCESS | FL_LEASE)))
		cFYI(1, "Unknown lock flags 0x%x", flock->fl_flags);

	*type = server->vals->large_lock_type;
	if (flock->fl_type == F_WRLCK) {
		cFYI(1, "F_WRLCK ");
		*type |= server->vals->exclusive_lock_type;
		*lock = 1;
	} else if (flock->fl_type == F_UNLCK) {
		cFYI(1, "F_UNLCK");
		*type |= server->vals->unlock_lock_type;
		*unlock = 1;
		/* Check if unlock includes more than one lock range */
	} else if (flock->fl_type == F_RDLCK) {
		cFYI(1, "F_RDLCK");
		*type |= server->vals->shared_lock_type;
		*lock = 1;
	} else if (flock->fl_type == F_EXLCK) {
		cFYI(1, "F_EXLCK");
		*type |= server->vals->exclusive_lock_type;
		*lock = 1;
	} else if (flock->fl_type == F_SHLCK) {
		cFYI(1, "F_SHLCK");
		*type |= server->vals->shared_lock_type;
		*lock = 1;
	} else
		cFYI(1, "Unknown type of lock");
}

static int
cifs_mandatory_lock(unsigned int xid, struct cifsFileInfo *cfile, __u64 offset,
		    __u64 length, __u32 type, int lock, int unlock, bool wait)
{
	return CIFSSMBLock(xid, tlink_tcon(cfile->tlink), cfile->fid.netfid,
			   current->tgid, length, offset, unlock, lock,
			   (__u8)type, wait, 0);
}

static int
cifs_getlk(struct file *file, struct file_lock *flock, __u32 type,
	   bool wait_flag, bool posix_lck, unsigned int xid)
{
	int rc = 0;
	__u64 length = 1 + flock->fl_end - flock->fl_start;
	struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
	struct TCP_Server_Info *server = tcon->ses->server;
	__u16 netfid = cfile->fid.netfid;

	if (posix_lck) {
		int posix_lock_type;

		rc = cifs_posix_lock_test(file, flock);
		if (!rc)
			return rc;

		if (type & server->vals->shared_lock_type)
			posix_lock_type = CIFS_RDLCK;
		else
			posix_lock_type = CIFS_WRLCK;
		rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid,
				      flock->fl_start, length, flock,
				      posix_lock_type, wait_flag);
		return rc;
	}

	rc = cifs_lock_test(cfile, flock->fl_start, length, type, flock);
	if (!rc)
		return rc;

	/* BB we could chain these into one lock request BB */
	rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length, type,
				 1, 0, false);
	if (rc == 0) {
		rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length,
					 type, 0, 1, false);
		flock->fl_type = F_UNLCK;
		if (rc != 0)
			cERROR(1, "Error unlocking previously locked "
				  "range %d during test of lock", rc);
		return 0;
	}

	if (type & server->vals->shared_lock_type) {
		flock->fl_type = F_WRLCK;
		return 0;
	}

	rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length,
				 type | server->vals->shared_lock_type, 1, 0,
				 false);
	if (rc == 0) {
		rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length,
					 type | server->vals->shared_lock_type,
					 0, 1, false);
		flock->fl_type = F_RDLCK;
		if (rc != 0)
			cERROR(1, "Error unlocking previously locked "
				  "range %d during test of lock", rc);
	} else
		flock->fl_type = F_WRLCK;

	return 0;
}

static void
cifs_move_llist(struct list_head *source, struct list_head *dest)
{
	struct list_head *li, *tmp;
	list_for_each_safe(li, tmp, source)
		list_move(li, dest);
}

static void
cifs_free_llist(struct list_head *llist)
{
	struct cifsLockInfo *li, *tmp;
	list_for_each_entry_safe(li, tmp, llist, llist) {
		cifs_del_lock_waiters(li);
		list_del(&li->llist);
		kfree(li);
	}
}

static int
cifs_unlock_range(struct cifsFileInfo *cfile, struct file_lock *flock,
		  unsigned int xid)
{
	int rc = 0, stored_rc;
	int types[] = {LOCKING_ANDX_LARGE_FILES,
		       LOCKING_ANDX_SHARED_LOCK | LOCKING_ANDX_LARGE_FILES};
	unsigned int i;
	unsigned int max_num, num, max_buf;
	LOCKING_ANDX_RANGE *buf, *cur;
	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
	struct cifsInodeInfo *cinode = CIFS_I(cfile->dentry->d_inode);
	struct cifsLockInfo *li, *tmp;
	__u64 length = 1 + flock->fl_end - flock->fl_start;
	struct list_head tmp_llist;

	INIT_LIST_HEAD(&tmp_llist);

	/*
	 * Accessing maxBuf is racy with cifs_reconnect - need to store value
	 * and check it for zero before using.
	 */
	max_buf = tcon->ses->server->maxBuf;
	if (!max_buf)
		return -EINVAL;

	max_num = (max_buf - sizeof(struct smb_hdr)) /
						sizeof(LOCKING_ANDX_RANGE);
	buf = kzalloc(max_num * sizeof(LOCKING_ANDX_RANGE), GFP_KERNEL);
	if (!buf)
		return -ENOMEM;

	mutex_lock(&cinode->lock_mutex);
	for (i = 0; i < 2; i++) {
		cur = buf;
		num = 0;
		list_for_each_entry_safe(li, tmp, &cfile->llist, llist) {
			if (flock->fl_start > li->offset ||
			    (flock->fl_start + length) <
			    (li->offset + li->length))
				continue;
			if (current->tgid != li->pid)
				continue;
			if (types[i] != li->type)
				continue;
			if (cinode->can_cache_brlcks) {
				/*
				 * We can cache brlock requests - simply remove
				 * a lock from the file's list.
				 */
				list_del(&li->llist);
				cifs_del_lock_waiters(li);
				kfree(li);
				continue;
			}
			cur->Pid = cpu_to_le16(li->pid);
			cur->LengthLow = cpu_to_le32((u32)li->length);
			cur->LengthHigh = cpu_to_le32((u32)(li->length>>32));
			cur->OffsetLow = cpu_to_le32((u32)li->offset);
			cur->OffsetHigh = cpu_to_le32((u32)(li->offset>>32));
			/*
			 * We need to save a lock here to let us add it again to
			 * the file's list if the unlock range request fails on
			 * the server.
			 */
			list_move(&li->llist, &tmp_llist);
			if (++num == max_num) {
				stored_rc = cifs_lockv(xid, tcon,
						       cfile->fid.netfid,
						       li->type, num, 0, buf);
				if (stored_rc) {
					/*
					 * We failed on the unlock range
					 * request - add all locks from the tmp
					 * list to the head of the file's list.
					 */
					cifs_move_llist(&tmp_llist,
							&cfile->llist);
					rc = stored_rc;
				} else
					/*
					 * The unlock range request succeed -
					 * free the tmp list.
					 */
					cifs_free_llist(&tmp_llist);
				cur = buf;
				num = 0;
			} else
				cur++;
		}
		if (num) {
			stored_rc = cifs_lockv(xid, tcon, cfile->fid.netfid,
					       types[i], num, 0, buf);
			if (stored_rc) {
				cifs_move_llist(&tmp_llist, &cfile->llist);
				rc = stored_rc;
			} else
				cifs_free_llist(&tmp_llist);
		}
	}

	mutex_unlock(&cinode->lock_mutex);
	kfree(buf);
	return rc;
}

static int
cifs_setlk(struct file *file,  struct file_lock *flock, __u32 type,
	   bool wait_flag, bool posix_lck, int lock, int unlock,
	   unsigned int xid)
{
	int rc = 0;
	__u64 length = 1 + flock->fl_end - flock->fl_start;
	struct cifsFileInfo *cfile = (struct cifsFileInfo *)file->private_data;
	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
	struct TCP_Server_Info *server = tcon->ses->server;
	__u16 netfid = cfile->fid.netfid;

	if (posix_lck) {
		int posix_lock_type;

		rc = cifs_posix_lock_set(file, flock);
		if (!rc || rc < 0)
			return rc;

		if (type & server->vals->shared_lock_type)
			posix_lock_type = CIFS_RDLCK;
		else
			posix_lock_type = CIFS_WRLCK;

		if (unlock == 1)
			posix_lock_type = CIFS_UNLCK;

		rc = CIFSSMBPosixLock(xid, tcon, netfid, current->tgid,
				      flock->fl_start, length, NULL,
				      posix_lock_type, wait_flag);
		goto out;
	}

	if (lock) {
		struct cifsLockInfo *lock;

		lock = cifs_lock_init(flock->fl_start, length, type);
		if (!lock)
			return -ENOMEM;

		rc = cifs_lock_add_if(cfile, lock, wait_flag);
		if (rc < 0)
			kfree(lock);
		if (rc <= 0)
			goto out;

		rc = cifs_mandatory_lock(xid, cfile, flock->fl_start, length,
					 type, 1, 0, wait_flag);
		if (rc) {
			kfree(lock);
			goto out;
		}

		cifs_lock_add(cfile, lock);
	} else if (unlock)
		rc = cifs_unlock_range(cfile, flock, xid);

out:
	if (flock->fl_flags & FL_POSIX)
		posix_lock_file_wait(file, flock);
	return rc;
}

int cifs_lock(struct file *file, int cmd, struct file_lock *flock)
{
	int rc, xid;
	int lock = 0, unlock = 0;
	bool wait_flag = false;
	bool posix_lck = false;
	struct cifs_sb_info *cifs_sb;
	struct cifs_tcon *tcon;
	struct cifsInodeInfo *cinode;
	struct cifsFileInfo *cfile;
	__u16 netfid;
	__u32 type;

	rc = -EACCES;
	xid = get_xid();

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

	cfile = (struct cifsFileInfo *)file->private_data;
	tcon = tlink_tcon(cfile->tlink);

	cifs_read_flock(flock, &type, &lock, &unlock, &wait_flag,
			tcon->ses->server);

	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	netfid = cfile->fid.netfid;
	cinode = CIFS_I(file->f_path.dentry->d_inode);

	if (cap_unix(tcon->ses) &&
	    (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
	    ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0))
		posix_lck = true;
	/*
	 * 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)) {
		rc = cifs_getlk(file, flock, type, wait_flag, posix_lck, xid);
		free_xid(xid);
		return rc;
	}

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

	rc = cifs_setlk(file, flock, type, wait_flag, posix_lck, lock, unlock,
			xid);
	free_xid(xid);
	return rc;
}

/*
 * update the file size (if needed) after a write. Should be called with
 * the inode->i_lock held
 */
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;
}

static ssize_t
cifs_write(struct cifsFileInfo *open_file, __u32 pid, const char *write_data,
	   size_t write_size, loff_t *offset)
{
	int rc = 0;
	unsigned int bytes_written = 0;
	unsigned int total_written;
	struct cifs_sb_info *cifs_sb;
	struct cifs_tcon *tcon;
	struct TCP_Server_Info *server;
	unsigned int xid;
	struct dentry *dentry = open_file->dentry;
	struct cifsInodeInfo *cifsi = CIFS_I(dentry->d_inode);
	struct cifs_io_parms io_parms;

	cifs_sb = CIFS_SB(dentry->d_sb);

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

	tcon = tlink_tcon(open_file->tlink);
	server = tcon->ses->server;

	if (!server->ops->sync_write)
		return -ENOSYS;

	xid = get_xid();

	for (total_written = 0; write_size > total_written;
	     total_written += bytes_written) {
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			struct kvec iov[2];
			unsigned int len;

			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(open_file, false);
				if (rc != 0)
					break;
			}

			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;
			io_parms.pid = pid;
			io_parms.tcon = tcon;
			io_parms.offset = *offset;
			io_parms.length = len;
			rc = server->ops->sync_write(xid, open_file, &io_parms,
						     &bytes_written, iov, 1);
		}
		if (rc || (bytes_written == 0)) {
			if (total_written)
				break;
			else {
				free_xid(xid);
				return rc;
			}
		} else {
			spin_lock(&dentry->d_inode->i_lock);
			cifs_update_eof(cifsi, *offset, bytes_written);
			spin_unlock(&dentry->d_inode->i_lock);
			*offset += bytes_written;
		}
	}

	cifs_stats_bytes_written(tcon, total_written);

	if (total_written > 0) {
		spin_lock(&dentry->d_inode->i_lock);
		if (*offset > dentry->d_inode->i_size)
			i_size_write(dentry->d_inode, *offset);
		spin_unlock(&dentry->d_inode->i_lock);
	}
	mark_inode_dirty_sync(dentry->d_inode);
	free_xid(xid);
	return total_written;
}

struct cifsFileInfo *find_readable_file(struct cifsInodeInfo *cifs_inode,
					bool fsuid_only)
{
	struct cifsFileInfo *open_file = NULL;
	struct cifs_sb_info *cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);

	/* only filter by fsuid on multiuser mounts */
	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
		fsuid_only = false;

	spin_lock(&cifs_file_list_lock);
	/* 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 (fsuid_only && open_file->uid != current_fsuid())
			continue;
		if (OPEN_FMODE(open_file->f_flags) & FMODE_READ) {
			if (!open_file->invalidHandle) {
				/* found a good file */
				/* lock it so it will not be closed on us */
				cifsFileInfo_get_locked(open_file);
				spin_unlock(&cifs_file_list_lock);
				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 */
	}
	spin_unlock(&cifs_file_list_lock);
	return NULL;
}

struct cifsFileInfo *find_writable_file(struct cifsInodeInfo *cifs_inode,
					bool fsuid_only)
{
	struct cifsFileInfo *open_file, *inv_file = NULL;
	struct cifs_sb_info *cifs_sb;
	bool any_available = false;
	int rc;
	unsigned int refind = 0;

	/* 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;
	}

	cifs_sb = CIFS_SB(cifs_inode->vfs_inode.i_sb);

	/* only filter by fsuid on multiuser mounts */
	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_MULTIUSER))
		fsuid_only = false;

	spin_lock(&cifs_file_list_lock);
refind_writable:
	if (refind > MAX_REOPEN_ATT) {
		spin_unlock(&cifs_file_list_lock);
		return NULL;
	}
	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
		if (!any_available && open_file->pid != current->tgid)
			continue;
		if (fsuid_only && open_file->uid != current_fsuid())
			continue;
		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
			if (!open_file->invalidHandle) {
				/* found a good writable file */
				cifsFileInfo_get_locked(open_file);
				spin_unlock(&cifs_file_list_lock);
				return open_file;
			} else {
				if (!inv_file)
					inv_file = open_file;
			}
		}
	}
	/* couldn't find useable FH with same pid, try any available */
	if (!any_available) {
		any_available = true;
		goto refind_writable;
	}

	if (inv_file) {
		any_available = false;
		cifsFileInfo_get_locked(inv_file);
	}

	spin_unlock(&cifs_file_list_lock);

	if (inv_file) {
		rc = cifs_reopen_file(inv_file, false);
		if (!rc)
			return inv_file;
		else {
			spin_lock(&cifs_file_list_lock);
			list_move_tail(&inv_file->flist,
					&cifs_inode->openFileList);
			spin_unlock(&cifs_file_list_lock);
			cifsFileInfo_put(inv_file);
			spin_lock(&cifs_file_list_lock);
			++refind;
			goto refind_writable;
		}
	}

	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 inode *inode;
	struct cifsFileInfo *open_file;

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

	inode = page->mapping->host;

	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), false);
	if (open_file) {
		bytes_written = cifs_write(open_file, open_file->pid,
					   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 cifs_sb_info *cifs_sb = CIFS_SB(mapping->host->i_sb);
	bool done = false, scanned = false, range_whole = false;
	pgoff_t end, index;
	struct cifs_writedata *wdata;
	struct TCP_Server_Info *server;
	struct page *page;
	int rc = 0;
	loff_t isize = i_size_read(mapping->host);

	/*
	 * If wsize is smaller than 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 (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 = true;
		scanned = true;
	}
retry:
	while (!done && index <= end) {
		unsigned int i, nr_pages, found_pages;
		pgoff_t next = 0, tofind;
		struct page **pages;

		tofind = min((cifs_sb->wsize / PAGE_CACHE_SIZE) - 1,
				end - index) + 1;

		wdata = cifs_writedata_alloc((unsigned int)tofind,
					     cifs_writev_complete);
		if (!wdata) {
			rc = -ENOMEM;
			break;
		}

		/*
		 * find_get_pages_tag seems to return a max of 256 on each
		 * iteration, so we must call it several times in order to
		 * fill the array or the wsize is effectively limited to
		 * 256 * PAGE_CACHE_SIZE.
		 */
		found_pages = 0;
		pages = wdata->pages;
		do {
			nr_pages = find_get_pages_tag(mapping, &index,
							PAGECACHE_TAG_DIRTY,
							tofind, pages);
			found_pages += nr_pages;
			tofind -= nr_pages;
			pages += nr_pages;
		} while (nr_pages && tofind && index <= end);

		if (found_pages == 0) {
			kref_put(&wdata->refcount, cifs_writedata_release);
			break;
		}

		nr_pages = 0;
		for (i = 0; i < found_pages; i++) {
			page = wdata->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 (nr_pages == 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 = true;
				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) >= isize) {
				done = true;
				unlock_page(page);
				end_page_writeback(page);
				break;
			}

			wdata->pages[i] = page;
			next = page->index + 1;
			++nr_pages;
		}

		/* reset index to refind any pages skipped */
		if (nr_pages == 0)
			index = wdata->pages[0]->index + 1;

		/* put any pages we aren't going to use */
		for (i = nr_pages; i < found_pages; i++) {
			page_cache_release(wdata->pages[i]);
			wdata->pages[i] = NULL;
		}

		/* nothing to write? */
		if (nr_pages == 0) {
			kref_put(&wdata->refcount, cifs_writedata_release);
			continue;
		}

		wdata->sync_mode = wbc->sync_mode;
		wdata->nr_pages = nr_pages;
		wdata->offset = page_offset(wdata->pages[0]);
		wdata->pagesz = PAGE_CACHE_SIZE;
		wdata->tailsz =
			min(isize - page_offset(wdata->pages[nr_pages - 1]),
			    (loff_t)PAGE_CACHE_SIZE);
		wdata->bytes = ((nr_pages - 1) * PAGE_CACHE_SIZE) +
					wdata->tailsz;

		do {
			if (wdata->cfile != NULL)
				cifsFileInfo_put(wdata->cfile);
			wdata->cfile = find_writable_file(CIFS_I(mapping->host),
							  false);
			if (!wdata->cfile) {
				cERROR(1, "No writable handles for inode");
				rc = -EBADF;
				break;
			}
			wdata->pid = wdata->cfile->pid;
			server = tlink_tcon(wdata->cfile->tlink)->ses->server;
			rc = server->ops->async_writev(wdata);
		} while (wbc->sync_mode == WB_SYNC_ALL && rc == -EAGAIN);

		for (i = 0; i < nr_pages; ++i)
			unlock_page(wdata->pages[i]);

		/* send failure -- clean up the mess */
		if (rc != 0) {
			for (i = 0; i < nr_pages; ++i) {
				if (rc == -EAGAIN)
					redirty_page_for_writepage(wbc,
							   wdata->pages[i]);
				else
					SetPageError(wdata->pages[i]);
				end_page_writeback(wdata->pages[i]);
				page_cache_release(wdata->pages[i]);
			}
			if (rc != -EAGAIN)
				mapping_set_error(mapping, rc);
		}
		kref_put(&wdata->refcount, cifs_writedata_release);

		wbc->nr_to_write -= nr_pages;
		if (wbc->nr_to_write <= 0)
			done = true;

		index = next;
	}

	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 = true;
		index = 0;
		goto retry;
	}

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

	return rc;
}

static int
cifs_writepage_locked(struct page *page, struct writeback_control *wbc)
{
	int rc;
	unsigned int xid;

	xid = get_xid();
/* 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);
retry_write:
	rc = cifs_partialpagewrite(page, 0, PAGE_CACHE_SIZE);
	if (rc == -EAGAIN && wbc->sync_mode == WB_SYNC_ALL)
		goto retry_write;
	else if (rc == -EAGAIN)
		redirty_page_for_writepage(wbc, page);
	else if (rc != 0)
		SetPageError(page);
	else
		SetPageUptodate(page);
	end_page_writeback(page);
	page_cache_release(page);
	free_xid(xid);
	return rc;
}

static int cifs_writepage(struct page *page, struct writeback_control *wbc)
{
	int rc = cifs_writepage_locked(page, wbc);
	unlock_page(page);
	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;
	struct cifsFileInfo *cfile = file->private_data;
	struct cifs_sb_info *cifs_sb = CIFS_SB(cfile->dentry->d_sb);
	__u32 pid;

	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
		pid = cfile->pid;
	else
		pid = current->tgid;

	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);
		unsigned int xid;

		xid = get_xid();
		/* 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(cfile, pid, page_data + offset, copied, &pos);
		/* if (rc < 0) should we set writebehind rc? */
		kunmap(page);

		free_xid(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_strict_fsync(struct file *file, loff_t start, loff_t end,
		      int datasync)
{
	unsigned int xid;
	int rc = 0;
	struct cifs_tcon *tcon;
	struct TCP_Server_Info *server;
	struct cifsFileInfo *smbfile = file->private_data;
	struct inode *inode = file->f_path.dentry->d_inode;
	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);

	rc = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (rc)
		return rc;
	mutex_lock(&inode->i_mutex);

	xid = get_xid();

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

	if (!CIFS_I(inode)->clientCanCacheRead) {
		rc = cifs_invalidate_mapping(inode);
		if (rc) {
			cFYI(1, "rc: %d during invalidate phase", rc);
			rc = 0; /* don't care about it in fsync */
		}
	}

	tcon = tlink_tcon(smbfile->tlink);
	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
		server = tcon->ses->server;
		if (server->ops->flush)
			rc = server->ops->flush(xid, tcon, &smbfile->fid);
		else
			rc = -ENOSYS;
	}

	free_xid(xid);
	mutex_unlock(&inode->i_mutex);
	return rc;
}

int cifs_fsync(struct file *file, loff_t start, loff_t end, int datasync)
{
	unsigned int xid;
	int rc = 0;
	struct cifs_tcon *tcon;
	struct TCP_Server_Info *server;
	struct cifsFileInfo *smbfile = file->private_data;
	struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	struct inode *inode = file->f_mapping->host;

	rc = filemap_write_and_wait_range(inode->i_mapping, start, end);
	if (rc)
		return rc;
	mutex_lock(&inode->i_mutex);

	xid = get_xid();

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

	tcon = tlink_tcon(smbfile->tlink);
	if (!(cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOSSYNC)) {
		server = tcon->ses->server;
		if (server->ops->flush)
			rc = server->ops->flush(xid, tcon, &smbfile->fid);
		else
			rc = -ENOSYS;
	}

	free_xid(xid);
	mutex_unlock(&inode->i_mutex);
	return rc;
}

/*
 * 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;

	if (file->f_mode & FMODE_WRITE)
		rc = filemap_write_and_wait(inode->i_mapping);

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

	return rc;
}

static int
cifs_write_allocate_pages(struct page **pages, unsigned long num_pages)
{
	int rc = 0;
	unsigned long i;

	for (i = 0; i < num_pages; i++) {
		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
		if (!pages[i]) {
			/*
			 * save number of pages we have already allocated and
			 * return with ENOMEM error
			 */
			num_pages = i;
			rc = -ENOMEM;
			break;
		}
	}

	if (rc) {
		for (i = 0; i < num_pages; i++)
			put_page(pages[i]);
	}
	return rc;
}

static inline
size_t get_numpages(const size_t wsize, const size_t len, size_t *cur_len)
{
	size_t num_pages;
	size_t clen;

	clen = min_t(const size_t, len, wsize);
	num_pages = DIV_ROUND_UP(clen, PAGE_SIZE);

	if (cur_len)
		*cur_len = clen;

	return num_pages;
}

static void
cifs_uncached_writev_complete(struct work_struct *work)
{
	int i;
	struct cifs_writedata *wdata = container_of(work,
					struct cifs_writedata, work);
	struct inode *inode = wdata->cfile->dentry->d_inode;
	struct cifsInodeInfo *cifsi = CIFS_I(inode);

	spin_lock(&inode->i_lock);
	cifs_update_eof(cifsi, wdata->offset, wdata->bytes);
	if (cifsi->server_eof > inode->i_size)
		i_size_write(inode, cifsi->server_eof);
	spin_unlock(&inode->i_lock);

	complete(&wdata->done);

	if (wdata->result != -EAGAIN) {
		for (i = 0; i < wdata->nr_pages; i++)
			put_page(wdata->pages[i]);
	}

	kref_put(&wdata->refcount, cifs_writedata_release);
}

/* attempt to send write to server, retry on any -EAGAIN errors */
static int
cifs_uncached_retry_writev(struct cifs_writedata *wdata)
{
	int rc;
	struct TCP_Server_Info *server;

	server = tlink_tcon(wdata->cfile->tlink)->ses->server;

	do {
		if (wdata->cfile->invalidHandle) {
			rc = cifs_reopen_file(wdata->cfile, false);
			if (rc != 0)
				continue;
		}
		rc = server->ops->async_writev(wdata);
	} while (rc == -EAGAIN);

	return rc;
}

static ssize_t
cifs_iovec_write(struct file *file, const struct iovec *iov,
		 unsigned long nr_segs, loff_t *poffset)
{
	unsigned long nr_pages, i;
	size_t copied, len, cur_len;
	ssize_t total_written = 0;
	loff_t offset;
	struct iov_iter it;
	struct cifsFileInfo *open_file;
	struct cifs_tcon *tcon;
	struct cifs_sb_info *cifs_sb;
	struct cifs_writedata *wdata, *tmp;
	struct list_head wdata_list;
	int rc;
	pid_t pid;

	len = iov_length(iov, nr_segs);
	if (!len)
		return 0;

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

	INIT_LIST_HEAD(&wdata_list);
	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	open_file = file->private_data;
	tcon = tlink_tcon(open_file->tlink);

	if (!tcon->ses->server->ops->async_writev)
		return -ENOSYS;

	offset = *poffset;

	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
		pid = open_file->pid;
	else
		pid = current->tgid;

	iov_iter_init(&it, iov, nr_segs, len, 0);
	do {
		size_t save_len;

		nr_pages = get_numpages(cifs_sb->wsize, len, &cur_len);
		wdata = cifs_writedata_alloc(nr_pages,
					     cifs_uncached_writev_complete);
		if (!wdata) {
			rc = -ENOMEM;
			break;
		}

		rc = cifs_write_allocate_pages(wdata->pages, nr_pages);
		if (rc) {
			kfree(wdata);
			break;
		}

		save_len = cur_len;
		for (i = 0; i < nr_pages; i++) {
			copied = min_t(const size_t, cur_len, PAGE_SIZE);
			copied = iov_iter_copy_from_user(wdata->pages[i], &it,
							 0, copied);
			cur_len -= copied;
			iov_iter_advance(&it, copied);
		}
		cur_len = save_len - cur_len;

		wdata->sync_mode = WB_SYNC_ALL;
		wdata->nr_pages = nr_pages;
		wdata->offset = (__u64)offset;
		wdata->cfile = cifsFileInfo_get(open_file);
		wdata->pid = pid;
		wdata->bytes = cur_len;
		wdata->pagesz = PAGE_SIZE;
		wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
		rc = cifs_uncached_retry_writev(wdata);
		if (rc) {
			kref_put(&wdata->refcount, cifs_writedata_release);
			break;
		}

		list_add_tail(&wdata->list, &wdata_list);
		offset += cur_len;
		len -= cur_len;
	} while (len > 0);

	/*
	 * If at least one write was successfully sent, then discard any rc
	 * value from the later writes. If the other write succeeds, then
	 * we'll end up returning whatever was written. If it fails, then
	 * we'll get a new rc value from that.
	 */
	if (!list_empty(&wdata_list))
		rc = 0;

	/*
	 * Wait for and collect replies for any successful sends in order of
	 * increasing offset. Once an error is hit or we get a fatal signal
	 * while waiting, then return without waiting for any more replies.
	 */
restart_loop:
	list_for_each_entry_safe(wdata, tmp, &wdata_list, list) {
		if (!rc) {
			/* FIXME: freezable too? */
			rc = wait_for_completion_killable(&wdata->done);
			if (rc)
				rc = -EINTR;
			else if (wdata->result)
				rc = wdata->result;
			else
				total_written += wdata->bytes;

			/* resend call if it's a retryable error */
			if (rc == -EAGAIN) {
				rc = cifs_uncached_retry_writev(wdata);
				goto restart_loop;
			}
		}
		list_del_init(&wdata->list);
		kref_put(&wdata->refcount, cifs_writedata_release);
	}

	if (total_written > 0)
		*poffset += total_written;

	cifs_stats_bytes_written(tcon, total_written);
	return total_written ? total_written : (ssize_t)rc;
}

ssize_t cifs_user_writev(struct kiocb *iocb, const struct iovec *iov,
				unsigned long nr_segs, loff_t pos)
{
	ssize_t written;
	struct inode *inode;

	inode = iocb->ki_filp->f_path.dentry->d_inode;

	/*
	 * BB - optimize the way when signing is disabled. We can drop this
	 * extra memory-to-memory copying and use iovec buffers for constructing
	 * write request.
	 */

	written = cifs_iovec_write(iocb->ki_filp, iov, nr_segs, &pos);
	if (written > 0) {
		CIFS_I(inode)->invalid_mapping = true;
		iocb->ki_pos = pos;
	}

	return written;
}

ssize_t cifs_strict_writev(struct kiocb *iocb, const struct iovec *iov,
			   unsigned long nr_segs, loff_t pos)
{
	struct inode *inode;

	inode = iocb->ki_filp->f_path.dentry->d_inode;

	if (CIFS_I(inode)->clientCanCacheAll)
		return generic_file_aio_write(iocb, iov, nr_segs, pos);

	/*
	 * In strict cache mode we need to write the data to the server exactly
	 * from the pos to pos+len-1 rather than flush all affected pages
	 * because it may cause a error with mandatory locks on these pages but
	 * not on the region from pos to ppos+len-1.
	 */

	return cifs_user_writev(iocb, iov, nr_segs, pos);
}

static struct cifs_readdata *
cifs_readdata_alloc(unsigned int nr_vecs, work_func_t complete)
{
	struct cifs_readdata *rdata;

	rdata = kzalloc(sizeof(*rdata) +
			sizeof(struct kvec) * nr_vecs, GFP_KERNEL);
	if (rdata != NULL) {
		kref_init(&rdata->refcount);
		INIT_LIST_HEAD(&rdata->list);
		init_completion(&rdata->done);
		INIT_WORK(&rdata->work, complete);
		INIT_LIST_HEAD(&rdata->pages);
	}
	return rdata;
}

void
cifs_readdata_release(struct kref *refcount)
{
	struct cifs_readdata *rdata = container_of(refcount,
					struct cifs_readdata, refcount);

	if (rdata->cfile)
		cifsFileInfo_put(rdata->cfile);

	kfree(rdata);
}

static int
cifs_read_allocate_pages(struct list_head *list, unsigned int npages)
{
	int rc = 0;
	struct page *page, *tpage;
	unsigned int i;

	for (i = 0; i < npages; i++) {
		page = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
		if (!page) {
			rc = -ENOMEM;
			break;
		}
		list_add(&page->lru, list);
	}

	if (rc) {
		list_for_each_entry_safe(page, tpage, list, lru) {
			list_del(&page->lru);
			put_page(page);
		}
	}
	return rc;
}

static void
cifs_uncached_readdata_release(struct kref *refcount)
{
	struct page *page, *tpage;
	struct cifs_readdata *rdata = container_of(refcount,
					struct cifs_readdata, refcount);

	list_for_each_entry_safe(page, tpage, &rdata->pages, lru) {
		list_del(&page->lru);
		put_page(page);
	}
	cifs_readdata_release(refcount);
}

static int
cifs_retry_async_readv(struct cifs_readdata *rdata)
{
	int rc;
	struct TCP_Server_Info *server;

	server = tlink_tcon(rdata->cfile->tlink)->ses->server;

	do {
		if (rdata->cfile->invalidHandle) {
			rc = cifs_reopen_file(rdata->cfile, true);
			if (rc != 0)
				continue;
		}
		rc = server->ops->async_readv(rdata);
	} while (rc == -EAGAIN);

	return rc;
}

/**
 * cifs_readdata_to_iov - copy data from pages in response to an iovec
 * @rdata:	the readdata response with list of pages holding data
 * @iov:	vector in which we should copy the data
 * @nr_segs:	number of segments in vector
 * @offset:	offset into file of the first iovec
 * @copied:	used to return the amount of data copied to the iov
 *
 * This function copies data from a list of pages in a readdata response into
 * an array of iovecs. It will first calculate where the data should go
 * based on the info in the readdata and then copy the data into that spot.
 */
static ssize_t
cifs_readdata_to_iov(struct cifs_readdata *rdata, const struct iovec *iov,
			unsigned long nr_segs, loff_t offset, ssize_t *copied)
{
	int rc = 0;
	struct iov_iter ii;
	size_t pos = rdata->offset - offset;
	struct page *page, *tpage;
	ssize_t remaining = rdata->bytes;
	unsigned char *pdata;

	/* set up iov_iter and advance to the correct offset */
	iov_iter_init(&ii, iov, nr_segs, iov_length(iov, nr_segs), 0);
	iov_iter_advance(&ii, pos);

	*copied = 0;
	list_for_each_entry_safe(page, tpage, &rdata->pages, lru) {
		ssize_t copy;

		/* copy a whole page or whatever's left */
		copy = min_t(ssize_t, remaining, PAGE_SIZE);

		/* ...but limit it to whatever space is left in the iov */
		copy = min_t(ssize_t, copy, iov_iter_count(&ii));

		/* go while there's data to be copied and no errors */
		if (copy && !rc) {
			pdata = kmap(page);
			rc = memcpy_toiovecend(ii.iov, pdata, ii.iov_offset,
						(int)copy);
			kunmap(page);
			if (!rc) {
				*copied += copy;
				remaining -= copy;
				iov_iter_advance(&ii, copy);
			}
		}

		list_del(&page->lru);
		put_page(page);
	}

	return rc;
}

static void
cifs_uncached_readv_complete(struct work_struct *work)
{
	struct cifs_readdata *rdata = container_of(work,
						struct cifs_readdata, work);

	/* if the result is non-zero then the pages weren't kmapped */
	if (rdata->result == 0) {
		struct page *page;

		list_for_each_entry(page, &rdata->pages, lru)
			kunmap(page);
	}

	complete(&rdata->done);
	kref_put(&rdata->refcount, cifs_uncached_readdata_release);
}

static int
cifs_uncached_read_marshal_iov(struct cifs_readdata *rdata,
				unsigned int remaining)
{
	int len = 0;
	struct page *page, *tpage;

	rdata->nr_iov = 1;
	list_for_each_entry_safe(page, tpage, &rdata->pages, lru) {
		if (remaining >= PAGE_SIZE) {
			/* enough data to fill the page */
			rdata->iov[rdata->nr_iov].iov_base = kmap(page);
			rdata->iov[rdata->nr_iov].iov_len = PAGE_SIZE;
			cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu",
				rdata->nr_iov, page->index,
				rdata->iov[rdata->nr_iov].iov_base,
				rdata->iov[rdata->nr_iov].iov_len);
			++rdata->nr_iov;
			len += PAGE_SIZE;
			remaining -= PAGE_SIZE;
		} else if (remaining > 0) {
			/* enough for partial page, fill and zero the rest */
			rdata->iov[rdata->nr_iov].iov_base = kmap(page);
			rdata->iov[rdata->nr_iov].iov_len = remaining;
			cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu",
				rdata->nr_iov, page->index,
				rdata->iov[rdata->nr_iov].iov_base,
				rdata->iov[rdata->nr_iov].iov_len);
			memset(rdata->iov[rdata->nr_iov].iov_base + remaining,
				'\0', PAGE_SIZE - remaining);
			++rdata->nr_iov;
			len += remaining;
			remaining = 0;
		} else {
			/* no need to hold page hostage */
			list_del(&page->lru);
			put_page(page);
		}
	}

	return len;
}

static ssize_t
cifs_iovec_read(struct file *file, const struct iovec *iov,
		 unsigned long nr_segs, loff_t *poffset)
{
	ssize_t rc;
	size_t len, cur_len;
	ssize_t total_read = 0;
	loff_t offset = *poffset;
	unsigned int npages;
	struct cifs_sb_info *cifs_sb;
	struct cifs_tcon *tcon;
	struct cifsFileInfo *open_file;
	struct cifs_readdata *rdata, *tmp;
	struct list_head rdata_list;
	pid_t pid;

	if (!nr_segs)
		return 0;

	len = iov_length(iov, nr_segs);
	if (!len)
		return 0;

	INIT_LIST_HEAD(&rdata_list);
	cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	open_file = file->private_data;
	tcon = tlink_tcon(open_file->tlink);

	if (!tcon->ses->server->ops->async_readv)
		return -ENOSYS;

	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
		pid = open_file->pid;
	else
		pid = current->tgid;

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

	do {
		cur_len = min_t(const size_t, len - total_read, cifs_sb->rsize);
		npages = DIV_ROUND_UP(cur_len, PAGE_SIZE);

		/* allocate a readdata struct */
		rdata = cifs_readdata_alloc(npages,
					    cifs_uncached_readv_complete);
		if (!rdata) {
			rc = -ENOMEM;
			goto error;
		}

		rc = cifs_read_allocate_pages(&rdata->pages, npages);
		if (rc)
			goto error;

		rdata->cfile = cifsFileInfo_get(open_file);
		rdata->offset = offset;
		rdata->bytes = cur_len;
		rdata->pid = pid;
		rdata->marshal_iov = cifs_uncached_read_marshal_iov;

		rc = cifs_retry_async_readv(rdata);
error:
		if (rc) {
			kref_put(&rdata->refcount,
				 cifs_uncached_readdata_release);
			break;
		}

		list_add_tail(&rdata->list, &rdata_list);
		offset += cur_len;
		len -= cur_len;
	} while (len > 0);

	/* if at least one read request send succeeded, then reset rc */
	if (!list_empty(&rdata_list))
		rc = 0;

	/* the loop below should proceed in the order of increasing offsets */
restart_loop:
	list_for_each_entry_safe(rdata, tmp, &rdata_list, list) {
		if (!rc) {
			ssize_t copied;

			/* FIXME: freezable sleep too? */
			rc = wait_for_completion_killable(&rdata->done);
			if (rc)
				rc = -EINTR;
			else if (rdata->result)
				rc = rdata->result;
			else {
				rc = cifs_readdata_to_iov(rdata, iov,
							nr_segs, *poffset,
							&copied);
				total_read += copied;
			}

			/* resend call if it's a retryable error */
			if (rc == -EAGAIN) {
				rc = cifs_retry_async_readv(rdata);
				goto restart_loop;
			}
		}
		list_del_init(&rdata->list);
		kref_put(&rdata->refcount, cifs_uncached_readdata_release);
	}

	cifs_stats_bytes_read(tcon, total_read);
	*poffset += total_read;

	/* mask nodata case */
	if (rc == -ENODATA)
		rc = 0;

	return total_read ? total_read : rc;
}

ssize_t cifs_user_readv(struct kiocb *iocb, const struct iovec *iov,
			       unsigned long nr_segs, loff_t pos)
{
	ssize_t read;

	read = cifs_iovec_read(iocb->ki_filp, iov, nr_segs, &pos);
	if (read > 0)
		iocb->ki_pos = pos;

	return read;
}

ssize_t cifs_strict_readv(struct kiocb *iocb, const struct iovec *iov,
			  unsigned long nr_segs, loff_t pos)
{
	struct inode *inode;

	inode = iocb->ki_filp->f_path.dentry->d_inode;

	if (CIFS_I(inode)->clientCanCacheRead)
		return generic_file_aio_read(iocb, iov, nr_segs, pos);

	/*
	 * In strict cache mode we need to read from the server all the time
	 * if we don't have level II oplock because the server can delay mtime
	 * change - so we can't make a decision about inode invalidating.
	 * And we can also fail with pagereading if there are mandatory locks
	 * on pages affected by this read but not on the region from pos to
	 * pos+len-1.
	 */

	return cifs_user_readv(iocb, iov, nr_segs, pos);
}

static ssize_t
cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
{
	int rc = -EACCES;
	unsigned int bytes_read = 0;
	unsigned int total_read;
	unsigned int current_read_size;
	unsigned int rsize;
	struct cifs_sb_info *cifs_sb;
	struct cifs_tcon *tcon;
	struct TCP_Server_Info *server;
	unsigned int xid;
	char *cur_offset;
	struct cifsFileInfo *open_file;
	struct cifs_io_parms io_parms;
	int buf_type = CIFS_NO_BUFFER;
	__u32 pid;

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

	/* FIXME: set up handlers for larger reads and/or convert to async */
	rsize = min_t(unsigned int, cifs_sb->rsize, CIFSMaxBufSize);

	if (file->private_data == NULL) {
		rc = -EBADF;
		free_xid(xid);
		return rc;
	}
	open_file = file->private_data;
	tcon = tlink_tcon(open_file->tlink);
	server = tcon->ses->server;

	if (!server->ops->sync_read) {
		free_xid(xid);
		return -ENOSYS;
	}

	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
		pid = open_file->pid;
	else
		pid = current->tgid;

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

	for (total_read = 0, cur_offset = read_data; read_size > total_read;
	     total_read += bytes_read, cur_offset += bytes_read) {
		current_read_size = min_t(uint, read_size - total_read, rsize);
		/*
		 * For windows me and 9x we do not want to request more than it
		 * negotiated since it will refuse the read then.
		 */
		if ((tcon->ses) && !(tcon->ses->capabilities &
				tcon->ses->server->vals->cap_large_files)) {
			current_read_size = min_t(uint, current_read_size,
					CIFSMaxBufSize);
		}
		rc = -EAGAIN;
		while (rc == -EAGAIN) {
			if (open_file->invalidHandle) {
				rc = cifs_reopen_file(open_file, true);
				if (rc != 0)
					break;
			}
			io_parms.pid = pid;
			io_parms.tcon = tcon;
			io_parms.offset = *offset;
			io_parms.length = current_read_size;
			rc = server->ops->sync_read(xid, open_file, &io_parms,
						    &bytes_read, &cur_offset,
						    &buf_type);
		}
		if (rc || (bytes_read == 0)) {
			if (total_read) {
				break;
			} else {
				free_xid(xid);
				return rc;
			}
		} else {
			cifs_stats_bytes_read(tcon, total_read);
			*offset += bytes_read;
		}
	}
	free_xid(xid);
	return total_read;
}

/*
 * If the page is mmap'ed into a process' page tables, then we need to make
 * sure that it doesn't change while being written back.
 */
static int
cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
{
	struct page *page = vmf->page;

	lock_page(page);
	return VM_FAULT_LOCKED;
}

static struct vm_operations_struct cifs_file_vm_ops = {
	.fault = filemap_fault,
	.page_mkwrite = cifs_page_mkwrite,
};

int cifs_file_strict_mmap(struct file *file, struct vm_area_struct *vma)
{
	int rc, xid;
	struct inode *inode = file->f_path.dentry->d_inode;

	xid = get_xid();

	if (!CIFS_I(inode)->clientCanCacheRead) {
		rc = cifs_invalidate_mapping(inode);
		if (rc)
			return rc;
	}

	rc = generic_file_mmap(file, vma);
	if (rc == 0)
		vma->vm_ops = &cifs_file_vm_ops;
	free_xid(xid);
	return rc;
}

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

	xid = get_xid();
	rc = cifs_revalidate_file(file);
	if (rc) {
		cFYI(1, "Validation prior to mmap failed, error=%d", rc);
		free_xid(xid);
		return rc;
	}
	rc = generic_file_mmap(file, vma);
	if (rc == 0)
		vma->vm_ops = &cifs_file_vm_ops;
	free_xid(xid);
	return rc;
}

static void
cifs_readv_complete(struct work_struct *work)
{
	struct cifs_readdata *rdata = container_of(work,
						struct cifs_readdata, work);
	struct page *page, *tpage;

	list_for_each_entry_safe(page, tpage, &rdata->pages, lru) {
		list_del(&page->lru);
		lru_cache_add_file(page);

		if (rdata->result == 0) {
			kunmap(page);
			flush_dcache_page(page);
			SetPageUptodate(page);
		}

		unlock_page(page);

		if (rdata->result == 0)
			cifs_readpage_to_fscache(rdata->mapping->host, page);

		page_cache_release(page);
	}
	kref_put(&rdata->refcount, cifs_readdata_release);
}

static int
cifs_readpages_marshal_iov(struct cifs_readdata *rdata, unsigned int remaining)
{
	int len = 0;
	struct page *page, *tpage;
	u64 eof;
	pgoff_t eof_index;

	/* determine the eof that the server (probably) has */
	eof = CIFS_I(rdata->mapping->host)->server_eof;
	eof_index = eof ? (eof - 1) >> PAGE_CACHE_SHIFT : 0;
	cFYI(1, "eof=%llu eof_index=%lu", eof, eof_index);

	rdata->nr_iov = 1;
	list_for_each_entry_safe(page, tpage, &rdata->pages, lru) {
		if (remaining >= PAGE_CACHE_SIZE) {
			/* enough data to fill the page */
			rdata->iov[rdata->nr_iov].iov_base = kmap(page);
			rdata->iov[rdata->nr_iov].iov_len = PAGE_CACHE_SIZE;
			cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu",
				rdata->nr_iov, page->index,
				rdata->iov[rdata->nr_iov].iov_base,
				rdata->iov[rdata->nr_iov].iov_len);
			++rdata->nr_iov;
			len += PAGE_CACHE_SIZE;
			remaining -= PAGE_CACHE_SIZE;
		} else if (remaining > 0) {
			/* enough for partial page, fill and zero the rest */
			rdata->iov[rdata->nr_iov].iov_base = kmap(page);
			rdata->iov[rdata->nr_iov].iov_len = remaining;
			cFYI(1, "%u: idx=%lu iov_base=%p iov_len=%zu",
				rdata->nr_iov, page->index,
				rdata->iov[rdata->nr_iov].iov_base,
				rdata->iov[rdata->nr_iov].iov_len);
			memset(rdata->iov[rdata->nr_iov].iov_base + remaining,
				'\0', PAGE_CACHE_SIZE - remaining);
			++rdata->nr_iov;
			len += remaining;
			remaining = 0;
		} else if (page->index > eof_index) {
			/*
			 * The VFS will not try to do readahead past the
			 * i_size, but it's possible that we have outstanding
			 * writes with gaps in the middle and the i_size hasn't
			 * caught up yet. Populate those with zeroed out pages
			 * to prevent the VFS from repeatedly attempting to
			 * fill them until the writes are flushed.
			 */
			zero_user(page, 0, PAGE_CACHE_SIZE);
			list_del(&page->lru);
			lru_cache_add_file(page);
			flush_dcache_page(page);
			SetPageUptodate(page);
			unlock_page(page);
			page_cache_release(page);
		} else {
			/* no need to hold page hostage */
			list_del(&page->lru);
			lru_cache_add_file(page);
			unlock_page(page);
			page_cache_release(page);
		}
	}

	return len;
}

static int cifs_readpages(struct file *file, struct address_space *mapping,
	struct list_head *page_list, unsigned num_pages)
{
	int rc;
	struct list_head tmplist;
	struct cifsFileInfo *open_file = file->private_data;
	struct cifs_sb_info *cifs_sb = CIFS_SB(file->f_path.dentry->d_sb);
	unsigned int rsize = cifs_sb->rsize;
	pid_t pid;

	/*
	 * Give up immediately if rsize is too small to read an entire page.
	 * The VFS will fall back to readpage. We should never reach this
	 * point however since we set ra_pages to 0 when the rsize is smaller
	 * than a cache page.
	 */
	if (unlikely(rsize < PAGE_CACHE_SIZE))
		return 0;

	/*
	 * 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)
		return rc;

	if (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_RWPIDFORWARD)
		pid = open_file->pid;
	else
		pid = current->tgid;

	rc = 0;
	INIT_LIST_HEAD(&tmplist);

	cFYI(1, "%s: file=%p mapping=%p num_pages=%u", __func__, file,
		mapping, num_pages);

	/*
	 * Start with the page at end of list and move it to private
	 * list. Do the same with any following pages until we hit
	 * the rsize limit, hit an index discontinuity, or run out of
	 * pages. Issue the async read and then start the loop again
	 * until the list is empty.
	 *
	 * Note that list order is important. The page_list is in
	 * the order of declining indexes. When we put the pages in
	 * the rdata->pages, then we want them in increasing order.
	 */
	while (!list_empty(page_list)) {
		unsigned int bytes = PAGE_CACHE_SIZE;
		unsigned int expected_index;
		unsigned int nr_pages = 1;
		loff_t offset;
		struct page *page, *tpage;
		struct cifs_readdata *rdata;

		page = list_entry(page_list->prev, struct page, lru);

		/*
		 * Lock the page and put it in the cache. Since no one else
		 * should have access to this page, we're safe to simply set
		 * PG_locked without checking it first.
		 */
		__set_page_locked(page);
		rc = add_to_page_cache_locked(page, mapping,
					      page->index, GFP_KERNEL);

		/* give up if we can't stick it in the cache */
		if (rc) {
			__clear_page_locked(page);
			break;
		}

		/* move first page to the tmplist */
		offset = (loff_t)page->index << PAGE_CACHE_SHIFT;
		list_move_tail(&page->lru, &tmplist);

		/* now try and add more pages onto the request */
		expected_index = page->index + 1;
		list_for_each_entry_safe_reverse(page, tpage, page_list, lru) {
			/* discontinuity ? */
			if (page->index != expected_index)
				break;

			/* would this page push the read over the rsize? */
			if (bytes + PAGE_CACHE_SIZE > rsize)
				break;

			__set_page_locked(page);
			if (add_to_page_cache_locked(page, mapping,
						page->index, GFP_KERNEL)) {
				__clear_page_locked(page);
				break;
			}
			list_move_tail(&page->lru, &tmplist);
			bytes += PAGE_CACHE_SIZE;
			expected_index++;
			nr_pages++;
		}

		rdata = cifs_readdata_alloc(nr_pages, cifs_readv_complete);
		if (!rdata) {
			/* best to give up if we're out of mem */
			list_for_each_entry_safe(page, tpage, &tmplist, lru) {
				list_del(&page->lru);
				lru_cache_add_file(page);
				unlock_page(page);
				page_cache_release(page);
			}
			rc = -ENOMEM;
			break;
		}

		rdata->cfile = cifsFileInfo_get(open_file);
		rdata->mapping = mapping;
		rdata->offset = offset;
		rdata->bytes = bytes;
		rdata->pid = pid;
		rdata->marshal_iov = cifs_readpages_marshal_iov;
		list_splice_init(&tmplist, &rdata->pages);

		rc = cifs_retry_async_readv(rdata);
		if (rc != 0) {
			list_for_each_entry_safe(page, tpage, &rdata->pages,
						 lru) {
				list_del(&page->lru);
				lru_cache_add_file(page);
				unlock_page(page);
				page_cache_release(page);
			}
			kref_put(&rdata->refcount, cifs_readdata_release);
			break;
		}

		kref_put(&rdata->refcount, cifs_readdata_release);
	}

	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;
	unsigned int xid;

	xid = get_xid();

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

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

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

	unlock_page(page);

	free_xid(xid);
	return rc;
}

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

	spin_lock(&cifs_file_list_lock);
	list_for_each_entry(open_file, &cifs_inode->openFileList, flist) {
		if (OPEN_FMODE(open_file->f_flags) & FMODE_WRITE) {
			spin_unlock(&cifs_file_list_lock);
			return 1;
		}
	}
	spin_unlock(&cifs_file_list_lock);
	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 int cifs_launder_page(struct page *page)
{
	int rc = 0;
	loff_t range_start = page_offset(page);
	loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1);
	struct writeback_control wbc = {
		.sync_mode = WB_SYNC_ALL,
		.nr_to_write = 0,
		.range_start = range_start,
		.range_end = range_end,
	};

	cFYI(1, "Launder page: %p", page);

	if (clear_page_dirty_for_io(page))
		rc = cifs_writepage_locked(page, &wbc);

	cifs_fscache_invalidate_page(page, page->mapping->host);
	return rc;
}

void cifs_oplock_break(struct work_struct *work)
{
	struct cifsFileInfo *cfile = container_of(work, struct cifsFileInfo,
						  oplock_break);
	struct inode *inode = cfile->dentry->d_inode;
	struct cifsInodeInfo *cinode = CIFS_I(inode);
	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
	int rc = 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) {
			rc = filemap_fdatawait(inode->i_mapping);
			mapping_set_error(inode->i_mapping, rc);
			invalidate_remote_inode(inode);
		}
		cFYI(1, "Oplock flush inode %p rc %d", inode, rc);
	}

	rc = cifs_push_locks(cfile);
	if (rc)
		cERROR(1, "Push locks rc = %d", 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->oplock_break_cancelled) {
		rc = tcon->ses->server->ops->oplock_response(tcon, &cfile->fid,
							     cinode);
		cFYI(1, "Oplock release rc = %d", rc);
	}
}

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,
	.launder_page = cifs_launder_page,
};

/*
 * 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,
	.launder_page = cifs_launder_page,
};