summaryrefslogtreecommitdiff
path: root/fs/fuse/file.c
blob: e35e394264adb74224e3dc8ac7d73d204c9a1e83 (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
/*
  FUSE: Filesystem in Userspace
  Copyright (C) 2001-2008  Miklos Szeredi <miklos@szeredi.hu>

  This program can be distributed under the terms of the GNU GPL.
  See the file COPYING.
*/

#include "fuse_i.h"

#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/sched/signal.h>
#include <linux/module.h>
#include <linux/swap.h>
#include <linux/falloc.h>
#include <linux/uio.h>
#include <linux/fs.h>

static int fuse_send_open(struct fuse_mount *fm, u64 nodeid,
			  unsigned int open_flags, int opcode,
			  struct fuse_open_out *outargp)
{
	struct fuse_open_in inarg;
	FUSE_ARGS(args);

	memset(&inarg, 0, sizeof(inarg));
	inarg.flags = open_flags & ~(O_CREAT | O_EXCL | O_NOCTTY);
	if (!fm->fc->atomic_o_trunc)
		inarg.flags &= ~O_TRUNC;

	if (fm->fc->handle_killpriv_v2 &&
	    (inarg.flags & O_TRUNC) && !capable(CAP_FSETID)) {
		inarg.open_flags |= FUSE_OPEN_KILL_SUIDGID;
	}

	args.opcode = opcode;
	args.nodeid = nodeid;
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	args.out_numargs = 1;
	args.out_args[0].size = sizeof(*outargp);
	args.out_args[0].value = outargp;

	return fuse_simple_request(fm, &args);
}

struct fuse_release_args {
	struct fuse_args args;
	struct fuse_release_in inarg;
	struct inode *inode;
};

struct fuse_file *fuse_file_alloc(struct fuse_mount *fm)
{
	struct fuse_file *ff;

	ff = kzalloc(sizeof(struct fuse_file), GFP_KERNEL_ACCOUNT);
	if (unlikely(!ff))
		return NULL;

	ff->fm = fm;
	ff->release_args = kzalloc(sizeof(*ff->release_args),
				   GFP_KERNEL_ACCOUNT);
	if (!ff->release_args) {
		kfree(ff);
		return NULL;
	}

	INIT_LIST_HEAD(&ff->write_entry);
	mutex_init(&ff->readdir.lock);
	refcount_set(&ff->count, 1);
	RB_CLEAR_NODE(&ff->polled_node);
	init_waitqueue_head(&ff->poll_wait);

	ff->kh = atomic64_inc_return(&fm->fc->khctr);

	return ff;
}

void fuse_file_free(struct fuse_file *ff)
{
	kfree(ff->release_args);
	mutex_destroy(&ff->readdir.lock);
	kfree(ff);
}

static struct fuse_file *fuse_file_get(struct fuse_file *ff)
{
	refcount_inc(&ff->count);
	return ff;
}

static void fuse_release_end(struct fuse_mount *fm, struct fuse_args *args,
			     int error)
{
	struct fuse_release_args *ra = container_of(args, typeof(*ra), args);

	iput(ra->inode);
	kfree(ra);
}

static void fuse_file_put(struct fuse_file *ff, bool sync, bool isdir)
{
	if (refcount_dec_and_test(&ff->count)) {
		struct fuse_args *args = &ff->release_args->args;

		if (isdir ? ff->fm->fc->no_opendir : ff->fm->fc->no_open) {
			/* Do nothing when client does not implement 'open' */
			fuse_release_end(ff->fm, args, 0);
		} else if (sync) {
			fuse_simple_request(ff->fm, args);
			fuse_release_end(ff->fm, args, 0);
		} else {
			args->end = fuse_release_end;
			if (fuse_simple_background(ff->fm, args,
						   GFP_KERNEL | __GFP_NOFAIL))
				fuse_release_end(ff->fm, args, -ENOTCONN);
		}
		kfree(ff);
	}
}

struct fuse_file *fuse_file_open(struct fuse_mount *fm, u64 nodeid,
				 unsigned int open_flags, bool isdir)
{
	struct fuse_conn *fc = fm->fc;
	struct fuse_file *ff;
	int opcode = isdir ? FUSE_OPENDIR : FUSE_OPEN;

	ff = fuse_file_alloc(fm);
	if (!ff)
		return ERR_PTR(-ENOMEM);

	ff->fh = 0;
	/* Default for no-open */
	ff->open_flags = FOPEN_KEEP_CACHE | (isdir ? FOPEN_CACHE_DIR : 0);
	if (isdir ? !fc->no_opendir : !fc->no_open) {
		struct fuse_open_out outarg;
		int err;

		err = fuse_send_open(fm, nodeid, open_flags, opcode, &outarg);
		if (!err) {
			ff->fh = outarg.fh;
			ff->open_flags = outarg.open_flags;

		} else if (err != -ENOSYS) {
			fuse_file_free(ff);
			return ERR_PTR(err);
		} else {
			if (isdir)
				fc->no_opendir = 1;
			else
				fc->no_open = 1;
		}
	}

	if (isdir)
		ff->open_flags &= ~FOPEN_DIRECT_IO;

	ff->nodeid = nodeid;

	return ff;
}

int fuse_do_open(struct fuse_mount *fm, u64 nodeid, struct file *file,
		 bool isdir)
{
	struct fuse_file *ff = fuse_file_open(fm, nodeid, file->f_flags, isdir);

	if (!IS_ERR(ff))
		file->private_data = ff;

	return PTR_ERR_OR_ZERO(ff);
}
EXPORT_SYMBOL_GPL(fuse_do_open);

static void fuse_link_write_file(struct file *file)
{
	struct inode *inode = file_inode(file);
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct fuse_file *ff = file->private_data;
	/*
	 * file may be written through mmap, so chain it onto the
	 * inodes's write_file list
	 */
	spin_lock(&fi->lock);
	if (list_empty(&ff->write_entry))
		list_add(&ff->write_entry, &fi->write_files);
	spin_unlock(&fi->lock);
}

void fuse_finish_open(struct inode *inode, struct file *file)
{
	struct fuse_file *ff = file->private_data;
	struct fuse_conn *fc = get_fuse_conn(inode);

	if (ff->open_flags & FOPEN_STREAM)
		stream_open(inode, file);
	else if (ff->open_flags & FOPEN_NONSEEKABLE)
		nonseekable_open(inode, file);

	if (fc->atomic_o_trunc && (file->f_flags & O_TRUNC)) {
		struct fuse_inode *fi = get_fuse_inode(inode);

		spin_lock(&fi->lock);
		fi->attr_version = atomic64_inc_return(&fc->attr_version);
		i_size_write(inode, 0);
		spin_unlock(&fi->lock);
		truncate_pagecache(inode, 0);
		file_update_time(file);
		fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
	} else if (!(ff->open_flags & FOPEN_KEEP_CACHE)) {
		invalidate_inode_pages2(inode->i_mapping);
	}

	if ((file->f_mode & FMODE_WRITE) && fc->writeback_cache)
		fuse_link_write_file(file);
}

int fuse_open_common(struct inode *inode, struct file *file, bool isdir)
{
	struct fuse_mount *fm = get_fuse_mount(inode);
	struct fuse_conn *fc = fm->fc;
	int err;
	bool is_wb_truncate = (file->f_flags & O_TRUNC) &&
			  fc->atomic_o_trunc &&
			  fc->writeback_cache;
	bool dax_truncate = (file->f_flags & O_TRUNC) &&
			  fc->atomic_o_trunc && FUSE_IS_DAX(inode);

	if (fuse_is_bad(inode))
		return -EIO;

	err = generic_file_open(inode, file);
	if (err)
		return err;

	if (is_wb_truncate || dax_truncate) {
		inode_lock(inode);
		fuse_set_nowrite(inode);
	}

	if (dax_truncate) {
		filemap_invalidate_lock(inode->i_mapping);
		err = fuse_dax_break_layouts(inode, 0, 0);
		if (err)
			goto out;
	}

	err = fuse_do_open(fm, get_node_id(inode), file, isdir);
	if (!err)
		fuse_finish_open(inode, file);

out:
	if (dax_truncate)
		filemap_invalidate_unlock(inode->i_mapping);

	if (is_wb_truncate | dax_truncate) {
		fuse_release_nowrite(inode);
		inode_unlock(inode);
	}

	return err;
}

static void fuse_prepare_release(struct fuse_inode *fi, struct fuse_file *ff,
				 unsigned int flags, int opcode)
{
	struct fuse_conn *fc = ff->fm->fc;
	struct fuse_release_args *ra = ff->release_args;

	/* Inode is NULL on error path of fuse_create_open() */
	if (likely(fi)) {
		spin_lock(&fi->lock);
		list_del(&ff->write_entry);
		spin_unlock(&fi->lock);
	}
	spin_lock(&fc->lock);
	if (!RB_EMPTY_NODE(&ff->polled_node))
		rb_erase(&ff->polled_node, &fc->polled_files);
	spin_unlock(&fc->lock);

	wake_up_interruptible_all(&ff->poll_wait);

	ra->inarg.fh = ff->fh;
	ra->inarg.flags = flags;
	ra->args.in_numargs = 1;
	ra->args.in_args[0].size = sizeof(struct fuse_release_in);
	ra->args.in_args[0].value = &ra->inarg;
	ra->args.opcode = opcode;
	ra->args.nodeid = ff->nodeid;
	ra->args.force = true;
	ra->args.nocreds = true;
}

void fuse_file_release(struct inode *inode, struct fuse_file *ff,
		       unsigned int open_flags, fl_owner_t id, bool isdir)
{
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct fuse_release_args *ra = ff->release_args;
	int opcode = isdir ? FUSE_RELEASEDIR : FUSE_RELEASE;

	fuse_prepare_release(fi, ff, open_flags, opcode);

	if (ff->flock) {
		ra->inarg.release_flags |= FUSE_RELEASE_FLOCK_UNLOCK;
		ra->inarg.lock_owner = fuse_lock_owner_id(ff->fm->fc, id);
	}
	/* Hold inode until release is finished */
	ra->inode = igrab(inode);

	/*
	 * Normally this will send the RELEASE request, however if
	 * some asynchronous READ or WRITE requests are outstanding,
	 * the sending will be delayed.
	 *
	 * Make the release synchronous if this is a fuseblk mount,
	 * synchronous RELEASE is allowed (and desirable) in this case
	 * because the server can be trusted not to screw up.
	 */
	fuse_file_put(ff, ff->fm->fc->destroy, isdir);
}

void fuse_release_common(struct file *file, bool isdir)
{
	fuse_file_release(file_inode(file), file->private_data, file->f_flags,
			  (fl_owner_t) file, isdir);
}

static int fuse_open(struct inode *inode, struct file *file)
{
	return fuse_open_common(inode, file, false);
}

static int fuse_release(struct inode *inode, struct file *file)
{
	fuse_release_common(file, false);

	/* return value is ignored by VFS */
	return 0;
}

void fuse_sync_release(struct fuse_inode *fi, struct fuse_file *ff,
		       unsigned int flags)
{
	WARN_ON(refcount_read(&ff->count) > 1);
	fuse_prepare_release(fi, ff, flags, FUSE_RELEASE);
	/*
	 * iput(NULL) is a no-op and since the refcount is 1 and everything's
	 * synchronous, we are fine with not doing igrab() here"
	 */
	fuse_file_put(ff, true, false);
}
EXPORT_SYMBOL_GPL(fuse_sync_release);

/*
 * Scramble the ID space with XTEA, so that the value of the files_struct
 * pointer is not exposed to userspace.
 */
u64 fuse_lock_owner_id(struct fuse_conn *fc, fl_owner_t id)
{
	u32 *k = fc->scramble_key;
	u64 v = (unsigned long) id;
	u32 v0 = v;
	u32 v1 = v >> 32;
	u32 sum = 0;
	int i;

	for (i = 0; i < 32; i++) {
		v0 += ((v1 << 4 ^ v1 >> 5) + v1) ^ (sum + k[sum & 3]);
		sum += 0x9E3779B9;
		v1 += ((v0 << 4 ^ v0 >> 5) + v0) ^ (sum + k[sum>>11 & 3]);
	}

	return (u64) v0 + ((u64) v1 << 32);
}

struct fuse_writepage_args {
	struct fuse_io_args ia;
	struct rb_node writepages_entry;
	struct list_head queue_entry;
	struct fuse_writepage_args *next;
	struct inode *inode;
	struct fuse_sync_bucket *bucket;
};

static struct fuse_writepage_args *fuse_find_writeback(struct fuse_inode *fi,
					    pgoff_t idx_from, pgoff_t idx_to)
{
	struct rb_node *n;

	n = fi->writepages.rb_node;

	while (n) {
		struct fuse_writepage_args *wpa;
		pgoff_t curr_index;

		wpa = rb_entry(n, struct fuse_writepage_args, writepages_entry);
		WARN_ON(get_fuse_inode(wpa->inode) != fi);
		curr_index = wpa->ia.write.in.offset >> PAGE_SHIFT;
		if (idx_from >= curr_index + wpa->ia.ap.num_pages)
			n = n->rb_right;
		else if (idx_to < curr_index)
			n = n->rb_left;
		else
			return wpa;
	}
	return NULL;
}

/*
 * Check if any page in a range is under writeback
 *
 * This is currently done by walking the list of writepage requests
 * for the inode, which can be pretty inefficient.
 */
static bool fuse_range_is_writeback(struct inode *inode, pgoff_t idx_from,
				   pgoff_t idx_to)
{
	struct fuse_inode *fi = get_fuse_inode(inode);
	bool found;

	spin_lock(&fi->lock);
	found = fuse_find_writeback(fi, idx_from, idx_to);
	spin_unlock(&fi->lock);

	return found;
}

static inline bool fuse_page_is_writeback(struct inode *inode, pgoff_t index)
{
	return fuse_range_is_writeback(inode, index, index);
}

/*
 * Wait for page writeback to be completed.
 *
 * Since fuse doesn't rely on the VM writeback tracking, this has to
 * use some other means.
 */
static void fuse_wait_on_page_writeback(struct inode *inode, pgoff_t index)
{
	struct fuse_inode *fi = get_fuse_inode(inode);

	wait_event(fi->page_waitq, !fuse_page_is_writeback(inode, index));
}

/*
 * Wait for all pending writepages on the inode to finish.
 *
 * This is currently done by blocking further writes with FUSE_NOWRITE
 * and waiting for all sent writes to complete.
 *
 * This must be called under i_mutex, otherwise the FUSE_NOWRITE usage
 * could conflict with truncation.
 */
static void fuse_sync_writes(struct inode *inode)
{
	fuse_set_nowrite(inode);
	fuse_release_nowrite(inode);
}

static int fuse_flush(struct file *file, fl_owner_t id)
{
	struct inode *inode = file_inode(file);
	struct fuse_mount *fm = get_fuse_mount(inode);
	struct fuse_file *ff = file->private_data;
	struct fuse_flush_in inarg;
	FUSE_ARGS(args);
	int err;

	if (fuse_is_bad(inode))
		return -EIO;

	if (ff->open_flags & FOPEN_NOFLUSH && !fm->fc->writeback_cache)
		return 0;

	err = write_inode_now(inode, 1);
	if (err)
		return err;

	inode_lock(inode);
	fuse_sync_writes(inode);
	inode_unlock(inode);

	err = filemap_check_errors(file->f_mapping);
	if (err)
		return err;

	err = 0;
	if (fm->fc->no_flush)
		goto inval_attr_out;

	memset(&inarg, 0, sizeof(inarg));
	inarg.fh = ff->fh;
	inarg.lock_owner = fuse_lock_owner_id(fm->fc, id);
	args.opcode = FUSE_FLUSH;
	args.nodeid = get_node_id(inode);
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	args.force = true;

	err = fuse_simple_request(fm, &args);
	if (err == -ENOSYS) {
		fm->fc->no_flush = 1;
		err = 0;
	}

inval_attr_out:
	/*
	 * In memory i_blocks is not maintained by fuse, if writeback cache is
	 * enabled, i_blocks from cached attr may not be accurate.
	 */
	if (!err && fm->fc->writeback_cache)
		fuse_invalidate_attr_mask(inode, STATX_BLOCKS);
	return err;
}

int fuse_fsync_common(struct file *file, loff_t start, loff_t end,
		      int datasync, int opcode)
{
	struct inode *inode = file->f_mapping->host;
	struct fuse_mount *fm = get_fuse_mount(inode);
	struct fuse_file *ff = file->private_data;
	FUSE_ARGS(args);
	struct fuse_fsync_in inarg;

	memset(&inarg, 0, sizeof(inarg));
	inarg.fh = ff->fh;
	inarg.fsync_flags = datasync ? FUSE_FSYNC_FDATASYNC : 0;
	args.opcode = opcode;
	args.nodeid = get_node_id(inode);
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	return fuse_simple_request(fm, &args);
}

static int fuse_fsync(struct file *file, loff_t start, loff_t end,
		      int datasync)
{
	struct inode *inode = file->f_mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	int err;

	if (fuse_is_bad(inode))
		return -EIO;

	inode_lock(inode);

	/*
	 * Start writeback against all dirty pages of the inode, then
	 * wait for all outstanding writes, before sending the FSYNC
	 * request.
	 */
	err = file_write_and_wait_range(file, start, end);
	if (err)
		goto out;

	fuse_sync_writes(inode);

	/*
	 * Due to implementation of fuse writeback
	 * file_write_and_wait_range() does not catch errors.
	 * We have to do this directly after fuse_sync_writes()
	 */
	err = file_check_and_advance_wb_err(file);
	if (err)
		goto out;

	err = sync_inode_metadata(inode, 1);
	if (err)
		goto out;

	if (fc->no_fsync)
		goto out;

	err = fuse_fsync_common(file, start, end, datasync, FUSE_FSYNC);
	if (err == -ENOSYS) {
		fc->no_fsync = 1;
		err = 0;
	}
out:
	inode_unlock(inode);

	return err;
}

void fuse_read_args_fill(struct fuse_io_args *ia, struct file *file, loff_t pos,
			 size_t count, int opcode)
{
	struct fuse_file *ff = file->private_data;
	struct fuse_args *args = &ia->ap.args;

	ia->read.in.fh = ff->fh;
	ia->read.in.offset = pos;
	ia->read.in.size = count;
	ia->read.in.flags = file->f_flags;
	args->opcode = opcode;
	args->nodeid = ff->nodeid;
	args->in_numargs = 1;
	args->in_args[0].size = sizeof(ia->read.in);
	args->in_args[0].value = &ia->read.in;
	args->out_argvar = true;
	args->out_numargs = 1;
	args->out_args[0].size = count;
}

static void fuse_release_user_pages(struct fuse_args_pages *ap,
				    bool should_dirty)
{
	unsigned int i;

	for (i = 0; i < ap->num_pages; i++) {
		if (should_dirty)
			set_page_dirty_lock(ap->pages[i]);
		put_page(ap->pages[i]);
	}
}

static void fuse_io_release(struct kref *kref)
{
	kfree(container_of(kref, struct fuse_io_priv, refcnt));
}

static ssize_t fuse_get_res_by_io(struct fuse_io_priv *io)
{
	if (io->err)
		return io->err;

	if (io->bytes >= 0 && io->write)
		return -EIO;

	return io->bytes < 0 ? io->size : io->bytes;
}

/**
 * In case of short read, the caller sets 'pos' to the position of
 * actual end of fuse request in IO request. Otherwise, if bytes_requested
 * == bytes_transferred or rw == WRITE, the caller sets 'pos' to -1.
 *
 * An example:
 * User requested DIO read of 64K. It was split into two 32K fuse requests,
 * both submitted asynchronously. The first of them was ACKed by userspace as
 * fully completed (req->out.args[0].size == 32K) resulting in pos == -1. The
 * second request was ACKed as short, e.g. only 1K was read, resulting in
 * pos == 33K.
 *
 * Thus, when all fuse requests are completed, the minimal non-negative 'pos'
 * will be equal to the length of the longest contiguous fragment of
 * transferred data starting from the beginning of IO request.
 */
static void fuse_aio_complete(struct fuse_io_priv *io, int err, ssize_t pos)
{
	int left;

	spin_lock(&io->lock);
	if (err)
		io->err = io->err ? : err;
	else if (pos >= 0 && (io->bytes < 0 || pos < io->bytes))
		io->bytes = pos;

	left = --io->reqs;
	if (!left && io->blocking)
		complete(io->done);
	spin_unlock(&io->lock);

	if (!left && !io->blocking) {
		ssize_t res = fuse_get_res_by_io(io);

		if (res >= 0) {
			struct inode *inode = file_inode(io->iocb->ki_filp);
			struct fuse_conn *fc = get_fuse_conn(inode);
			struct fuse_inode *fi = get_fuse_inode(inode);

			spin_lock(&fi->lock);
			fi->attr_version = atomic64_inc_return(&fc->attr_version);
			spin_unlock(&fi->lock);
		}

		io->iocb->ki_complete(io->iocb, res);
	}

	kref_put(&io->refcnt, fuse_io_release);
}

static struct fuse_io_args *fuse_io_alloc(struct fuse_io_priv *io,
					  unsigned int npages)
{
	struct fuse_io_args *ia;

	ia = kzalloc(sizeof(*ia), GFP_KERNEL);
	if (ia) {
		ia->io = io;
		ia->ap.pages = fuse_pages_alloc(npages, GFP_KERNEL,
						&ia->ap.descs);
		if (!ia->ap.pages) {
			kfree(ia);
			ia = NULL;
		}
	}
	return ia;
}

static void fuse_io_free(struct fuse_io_args *ia)
{
	kfree(ia->ap.pages);
	kfree(ia);
}

static void fuse_aio_complete_req(struct fuse_mount *fm, struct fuse_args *args,
				  int err)
{
	struct fuse_io_args *ia = container_of(args, typeof(*ia), ap.args);
	struct fuse_io_priv *io = ia->io;
	ssize_t pos = -1;

	fuse_release_user_pages(&ia->ap, io->should_dirty);

	if (err) {
		/* Nothing */
	} else if (io->write) {
		if (ia->write.out.size > ia->write.in.size) {
			err = -EIO;
		} else if (ia->write.in.size != ia->write.out.size) {
			pos = ia->write.in.offset - io->offset +
				ia->write.out.size;
		}
	} else {
		u32 outsize = args->out_args[0].size;

		if (ia->read.in.size != outsize)
			pos = ia->read.in.offset - io->offset + outsize;
	}

	fuse_aio_complete(io, err, pos);
	fuse_io_free(ia);
}

static ssize_t fuse_async_req_send(struct fuse_mount *fm,
				   struct fuse_io_args *ia, size_t num_bytes)
{
	ssize_t err;
	struct fuse_io_priv *io = ia->io;

	spin_lock(&io->lock);
	kref_get(&io->refcnt);
	io->size += num_bytes;
	io->reqs++;
	spin_unlock(&io->lock);

	ia->ap.args.end = fuse_aio_complete_req;
	ia->ap.args.may_block = io->should_dirty;
	err = fuse_simple_background(fm, &ia->ap.args, GFP_KERNEL);
	if (err)
		fuse_aio_complete_req(fm, &ia->ap.args, err);

	return num_bytes;
}

static ssize_t fuse_send_read(struct fuse_io_args *ia, loff_t pos, size_t count,
			      fl_owner_t owner)
{
	struct file *file = ia->io->iocb->ki_filp;
	struct fuse_file *ff = file->private_data;
	struct fuse_mount *fm = ff->fm;

	fuse_read_args_fill(ia, file, pos, count, FUSE_READ);
	if (owner != NULL) {
		ia->read.in.read_flags |= FUSE_READ_LOCKOWNER;
		ia->read.in.lock_owner = fuse_lock_owner_id(fm->fc, owner);
	}

	if (ia->io->async)
		return fuse_async_req_send(fm, ia, count);

	return fuse_simple_request(fm, &ia->ap.args);
}

static void fuse_read_update_size(struct inode *inode, loff_t size,
				  u64 attr_ver)
{
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);

	spin_lock(&fi->lock);
	if (attr_ver >= fi->attr_version && size < inode->i_size &&
	    !test_bit(FUSE_I_SIZE_UNSTABLE, &fi->state)) {
		fi->attr_version = atomic64_inc_return(&fc->attr_version);
		i_size_write(inode, size);
	}
	spin_unlock(&fi->lock);
}

static void fuse_short_read(struct inode *inode, u64 attr_ver, size_t num_read,
			    struct fuse_args_pages *ap)
{
	struct fuse_conn *fc = get_fuse_conn(inode);

	/*
	 * If writeback_cache is enabled, a short read means there's a hole in
	 * the file.  Some data after the hole is in page cache, but has not
	 * reached the client fs yet.  So the hole is not present there.
	 */
	if (!fc->writeback_cache) {
		loff_t pos = page_offset(ap->pages[0]) + num_read;
		fuse_read_update_size(inode, pos, attr_ver);
	}
}

static int fuse_do_readpage(struct file *file, struct page *page)
{
	struct inode *inode = page->mapping->host;
	struct fuse_mount *fm = get_fuse_mount(inode);
	loff_t pos = page_offset(page);
	struct fuse_page_desc desc = { .length = PAGE_SIZE };
	struct fuse_io_args ia = {
		.ap.args.page_zeroing = true,
		.ap.args.out_pages = true,
		.ap.num_pages = 1,
		.ap.pages = &page,
		.ap.descs = &desc,
	};
	ssize_t res;
	u64 attr_ver;

	/*
	 * Page writeback can extend beyond the lifetime of the
	 * page-cache page, so make sure we read a properly synced
	 * page.
	 */
	fuse_wait_on_page_writeback(inode, page->index);

	attr_ver = fuse_get_attr_version(fm->fc);

	/* Don't overflow end offset */
	if (pos + (desc.length - 1) == LLONG_MAX)
		desc.length--;

	fuse_read_args_fill(&ia, file, pos, desc.length, FUSE_READ);
	res = fuse_simple_request(fm, &ia.ap.args);
	if (res < 0)
		return res;
	/*
	 * Short read means EOF.  If file size is larger, truncate it
	 */
	if (res < desc.length)
		fuse_short_read(inode, attr_ver, res, &ia.ap);

	SetPageUptodate(page);

	return 0;
}

static int fuse_readpage(struct file *file, struct page *page)
{
	struct inode *inode = page->mapping->host;
	int err;

	err = -EIO;
	if (fuse_is_bad(inode))
		goto out;

	err = fuse_do_readpage(file, page);
	fuse_invalidate_atime(inode);
 out:
	unlock_page(page);
	return err;
}

static void fuse_readpages_end(struct fuse_mount *fm, struct fuse_args *args,
			       int err)
{
	int i;
	struct fuse_io_args *ia = container_of(args, typeof(*ia), ap.args);
	struct fuse_args_pages *ap = &ia->ap;
	size_t count = ia->read.in.size;
	size_t num_read = args->out_args[0].size;
	struct address_space *mapping = NULL;

	for (i = 0; mapping == NULL && i < ap->num_pages; i++)
		mapping = ap->pages[i]->mapping;

	if (mapping) {
		struct inode *inode = mapping->host;

		/*
		 * Short read means EOF. If file size is larger, truncate it
		 */
		if (!err && num_read < count)
			fuse_short_read(inode, ia->read.attr_ver, num_read, ap);

		fuse_invalidate_atime(inode);
	}

	for (i = 0; i < ap->num_pages; i++) {
		struct page *page = ap->pages[i];

		if (!err)
			SetPageUptodate(page);
		else
			SetPageError(page);
		unlock_page(page);
		put_page(page);
	}
	if (ia->ff)
		fuse_file_put(ia->ff, false, false);

	fuse_io_free(ia);
}

static void fuse_send_readpages(struct fuse_io_args *ia, struct file *file)
{
	struct fuse_file *ff = file->private_data;
	struct fuse_mount *fm = ff->fm;
	struct fuse_args_pages *ap = &ia->ap;
	loff_t pos = page_offset(ap->pages[0]);
	size_t count = ap->num_pages << PAGE_SHIFT;
	ssize_t res;
	int err;

	ap->args.out_pages = true;
	ap->args.page_zeroing = true;
	ap->args.page_replace = true;

	/* Don't overflow end offset */
	if (pos + (count - 1) == LLONG_MAX) {
		count--;
		ap->descs[ap->num_pages - 1].length--;
	}
	WARN_ON((loff_t) (pos + count) < 0);

	fuse_read_args_fill(ia, file, pos, count, FUSE_READ);
	ia->read.attr_ver = fuse_get_attr_version(fm->fc);
	if (fm->fc->async_read) {
		ia->ff = fuse_file_get(ff);
		ap->args.end = fuse_readpages_end;
		err = fuse_simple_background(fm, &ap->args, GFP_KERNEL);
		if (!err)
			return;
	} else {
		res = fuse_simple_request(fm, &ap->args);
		err = res < 0 ? res : 0;
	}
	fuse_readpages_end(fm, &ap->args, err);
}

static void fuse_readahead(struct readahead_control *rac)
{
	struct inode *inode = rac->mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	unsigned int i, max_pages, nr_pages = 0;

	if (fuse_is_bad(inode))
		return;

	max_pages = min_t(unsigned int, fc->max_pages,
			fc->max_read / PAGE_SIZE);

	for (;;) {
		struct fuse_io_args *ia;
		struct fuse_args_pages *ap;

		if (fc->num_background >= fc->congestion_threshold &&
		    rac->ra->async_size >= readahead_count(rac))
			/*
			 * Congested and only async pages left, so skip the
			 * rest.
			 */
			break;

		nr_pages = readahead_count(rac) - nr_pages;
		if (nr_pages > max_pages)
			nr_pages = max_pages;
		if (nr_pages == 0)
			break;
		ia = fuse_io_alloc(NULL, nr_pages);
		if (!ia)
			return;
		ap = &ia->ap;
		nr_pages = __readahead_batch(rac, ap->pages, nr_pages);
		for (i = 0; i < nr_pages; i++) {
			fuse_wait_on_page_writeback(inode,
						    readahead_index(rac) + i);
			ap->descs[i].length = PAGE_SIZE;
		}
		ap->num_pages = nr_pages;
		fuse_send_readpages(ia, rac->file);
	}
}

static ssize_t fuse_cache_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct inode *inode = iocb->ki_filp->f_mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);

	/*
	 * In auto invalidate mode, always update attributes on read.
	 * Otherwise, only update if we attempt to read past EOF (to ensure
	 * i_size is up to date).
	 */
	if (fc->auto_inval_data ||
	    (iocb->ki_pos + iov_iter_count(to) > i_size_read(inode))) {
		int err;
		err = fuse_update_attributes(inode, iocb->ki_filp, STATX_SIZE);
		if (err)
			return err;
	}

	return generic_file_read_iter(iocb, to);
}

static void fuse_write_args_fill(struct fuse_io_args *ia, struct fuse_file *ff,
				 loff_t pos, size_t count)
{
	struct fuse_args *args = &ia->ap.args;

	ia->write.in.fh = ff->fh;
	ia->write.in.offset = pos;
	ia->write.in.size = count;
	args->opcode = FUSE_WRITE;
	args->nodeid = ff->nodeid;
	args->in_numargs = 2;
	if (ff->fm->fc->minor < 9)
		args->in_args[0].size = FUSE_COMPAT_WRITE_IN_SIZE;
	else
		args->in_args[0].size = sizeof(ia->write.in);
	args->in_args[0].value = &ia->write.in;
	args->in_args[1].size = count;
	args->out_numargs = 1;
	args->out_args[0].size = sizeof(ia->write.out);
	args->out_args[0].value = &ia->write.out;
}

static unsigned int fuse_write_flags(struct kiocb *iocb)
{
	unsigned int flags = iocb->ki_filp->f_flags;

	if (iocb->ki_flags & IOCB_DSYNC)
		flags |= O_DSYNC;
	if (iocb->ki_flags & IOCB_SYNC)
		flags |= O_SYNC;

	return flags;
}

static ssize_t fuse_send_write(struct fuse_io_args *ia, loff_t pos,
			       size_t count, fl_owner_t owner)
{
	struct kiocb *iocb = ia->io->iocb;
	struct file *file = iocb->ki_filp;
	struct fuse_file *ff = file->private_data;
	struct fuse_mount *fm = ff->fm;
	struct fuse_write_in *inarg = &ia->write.in;
	ssize_t err;

	fuse_write_args_fill(ia, ff, pos, count);
	inarg->flags = fuse_write_flags(iocb);
	if (owner != NULL) {
		inarg->write_flags |= FUSE_WRITE_LOCKOWNER;
		inarg->lock_owner = fuse_lock_owner_id(fm->fc, owner);
	}

	if (ia->io->async)
		return fuse_async_req_send(fm, ia, count);

	err = fuse_simple_request(fm, &ia->ap.args);
	if (!err && ia->write.out.size > count)
		err = -EIO;

	return err ?: ia->write.out.size;
}

bool fuse_write_update_attr(struct inode *inode, loff_t pos, ssize_t written)
{
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);
	bool ret = false;

	spin_lock(&fi->lock);
	fi->attr_version = atomic64_inc_return(&fc->attr_version);
	if (written > 0 && pos > inode->i_size) {
		i_size_write(inode, pos);
		ret = true;
	}
	spin_unlock(&fi->lock);

	fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);

	return ret;
}

static ssize_t fuse_send_write_pages(struct fuse_io_args *ia,
				     struct kiocb *iocb, struct inode *inode,
				     loff_t pos, size_t count)
{
	struct fuse_args_pages *ap = &ia->ap;
	struct file *file = iocb->ki_filp;
	struct fuse_file *ff = file->private_data;
	struct fuse_mount *fm = ff->fm;
	unsigned int offset, i;
	bool short_write;
	int err;

	for (i = 0; i < ap->num_pages; i++)
		fuse_wait_on_page_writeback(inode, ap->pages[i]->index);

	fuse_write_args_fill(ia, ff, pos, count);
	ia->write.in.flags = fuse_write_flags(iocb);
	if (fm->fc->handle_killpriv_v2 && !capable(CAP_FSETID))
		ia->write.in.write_flags |= FUSE_WRITE_KILL_SUIDGID;

	err = fuse_simple_request(fm, &ap->args);
	if (!err && ia->write.out.size > count)
		err = -EIO;

	short_write = ia->write.out.size < count;
	offset = ap->descs[0].offset;
	count = ia->write.out.size;
	for (i = 0; i < ap->num_pages; i++) {
		struct page *page = ap->pages[i];

		if (err) {
			ClearPageUptodate(page);
		} else {
			if (count >= PAGE_SIZE - offset)
				count -= PAGE_SIZE - offset;
			else {
				if (short_write)
					ClearPageUptodate(page);
				count = 0;
			}
			offset = 0;
		}
		if (ia->write.page_locked && (i == ap->num_pages - 1))
			unlock_page(page);
		put_page(page);
	}

	return err;
}

static ssize_t fuse_fill_write_pages(struct fuse_io_args *ia,
				     struct address_space *mapping,
				     struct iov_iter *ii, loff_t pos,
				     unsigned int max_pages)
{
	struct fuse_args_pages *ap = &ia->ap;
	struct fuse_conn *fc = get_fuse_conn(mapping->host);
	unsigned offset = pos & (PAGE_SIZE - 1);
	size_t count = 0;
	int err;

	ap->args.in_pages = true;
	ap->descs[0].offset = offset;

	do {
		size_t tmp;
		struct page *page;
		pgoff_t index = pos >> PAGE_SHIFT;
		size_t bytes = min_t(size_t, PAGE_SIZE - offset,
				     iov_iter_count(ii));

		bytes = min_t(size_t, bytes, fc->max_write - count);

 again:
		err = -EFAULT;
		if (fault_in_iov_iter_readable(ii, bytes))
			break;

		err = -ENOMEM;
		page = grab_cache_page_write_begin(mapping, index);
		if (!page)
			break;

		if (mapping_writably_mapped(mapping))
			flush_dcache_page(page);

		tmp = copy_page_from_iter_atomic(page, offset, bytes, ii);
		flush_dcache_page(page);

		if (!tmp) {
			unlock_page(page);
			put_page(page);
			goto again;
		}

		err = 0;
		ap->pages[ap->num_pages] = page;
		ap->descs[ap->num_pages].length = tmp;
		ap->num_pages++;

		count += tmp;
		pos += tmp;
		offset += tmp;
		if (offset == PAGE_SIZE)
			offset = 0;

		/* If we copied full page, mark it uptodate */
		if (tmp == PAGE_SIZE)
			SetPageUptodate(page);

		if (PageUptodate(page)) {
			unlock_page(page);
		} else {
			ia->write.page_locked = true;
			break;
		}
		if (!fc->big_writes)
			break;
	} while (iov_iter_count(ii) && count < fc->max_write &&
		 ap->num_pages < max_pages && offset == 0);

	return count > 0 ? count : err;
}

static inline unsigned int fuse_wr_pages(loff_t pos, size_t len,
				     unsigned int max_pages)
{
	return min_t(unsigned int,
		     ((pos + len - 1) >> PAGE_SHIFT) -
		     (pos >> PAGE_SHIFT) + 1,
		     max_pages);
}

static ssize_t fuse_perform_write(struct kiocb *iocb,
				  struct address_space *mapping,
				  struct iov_iter *ii, loff_t pos)
{
	struct inode *inode = mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);
	int err = 0;
	ssize_t res = 0;

	if (inode->i_size < pos + iov_iter_count(ii))
		set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);

	do {
		ssize_t count;
		struct fuse_io_args ia = {};
		struct fuse_args_pages *ap = &ia.ap;
		unsigned int nr_pages = fuse_wr_pages(pos, iov_iter_count(ii),
						      fc->max_pages);

		ap->pages = fuse_pages_alloc(nr_pages, GFP_KERNEL, &ap->descs);
		if (!ap->pages) {
			err = -ENOMEM;
			break;
		}

		count = fuse_fill_write_pages(&ia, mapping, ii, pos, nr_pages);
		if (count <= 0) {
			err = count;
		} else {
			err = fuse_send_write_pages(&ia, iocb, inode,
						    pos, count);
			if (!err) {
				size_t num_written = ia.write.out.size;

				res += num_written;
				pos += num_written;

				/* break out of the loop on short write */
				if (num_written != count)
					err = -EIO;
			}
		}
		kfree(ap->pages);
	} while (!err && iov_iter_count(ii));

	fuse_write_update_attr(inode, pos, res);
	clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);

	return res > 0 ? res : err;
}

static ssize_t fuse_cache_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct address_space *mapping = file->f_mapping;
	ssize_t written = 0;
	ssize_t written_buffered = 0;
	struct inode *inode = mapping->host;
	ssize_t err;
	struct fuse_conn *fc = get_fuse_conn(inode);
	loff_t endbyte = 0;

	if (fc->writeback_cache) {
		/* Update size (EOF optimization) and mode (SUID clearing) */
		err = fuse_update_attributes(mapping->host, file,
					     STATX_SIZE | STATX_MODE);
		if (err)
			return err;

		if (fc->handle_killpriv_v2 &&
		    should_remove_suid(file_dentry(file))) {
			goto writethrough;
		}

		return generic_file_write_iter(iocb, from);
	}

writethrough:
	inode_lock(inode);

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

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

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

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

	if (iocb->ki_flags & IOCB_DIRECT) {
		loff_t pos = iocb->ki_pos;
		written = generic_file_direct_write(iocb, from);
		if (written < 0 || !iov_iter_count(from))
			goto out;

		pos += written;

		written_buffered = fuse_perform_write(iocb, mapping, from, pos);
		if (written_buffered < 0) {
			err = written_buffered;
			goto out;
		}
		endbyte = pos + written_buffered - 1;

		err = filemap_write_and_wait_range(file->f_mapping, pos,
						   endbyte);
		if (err)
			goto out;

		invalidate_mapping_pages(file->f_mapping,
					 pos >> PAGE_SHIFT,
					 endbyte >> PAGE_SHIFT);

		written += written_buffered;
		iocb->ki_pos = pos + written_buffered;
	} else {
		written = fuse_perform_write(iocb, mapping, from, iocb->ki_pos);
		if (written >= 0)
			iocb->ki_pos += written;
	}
out:
	current->backing_dev_info = NULL;
	inode_unlock(inode);
	if (written > 0)
		written = generic_write_sync(iocb, written);

	return written ? written : err;
}

static inline unsigned long fuse_get_user_addr(const struct iov_iter *ii)
{
	return (unsigned long)ii->iov->iov_base + ii->iov_offset;
}

static inline size_t fuse_get_frag_size(const struct iov_iter *ii,
					size_t max_size)
{
	return min(iov_iter_single_seg_count(ii), max_size);
}

static int fuse_get_user_pages(struct fuse_args_pages *ap, struct iov_iter *ii,
			       size_t *nbytesp, int write,
			       unsigned int max_pages)
{
	size_t nbytes = 0;  /* # bytes already packed in req */
	ssize_t ret = 0;

	/* Special case for kernel I/O: can copy directly into the buffer */
	if (iov_iter_is_kvec(ii)) {
		unsigned long user_addr = fuse_get_user_addr(ii);
		size_t frag_size = fuse_get_frag_size(ii, *nbytesp);

		if (write)
			ap->args.in_args[1].value = (void *) user_addr;
		else
			ap->args.out_args[0].value = (void *) user_addr;

		iov_iter_advance(ii, frag_size);
		*nbytesp = frag_size;
		return 0;
	}

	while (nbytes < *nbytesp && ap->num_pages < max_pages) {
		unsigned npages;
		size_t start;
		ret = iov_iter_get_pages(ii, &ap->pages[ap->num_pages],
					*nbytesp - nbytes,
					max_pages - ap->num_pages,
					&start);
		if (ret < 0)
			break;

		iov_iter_advance(ii, ret);
		nbytes += ret;

		ret += start;
		npages = DIV_ROUND_UP(ret, PAGE_SIZE);

		ap->descs[ap->num_pages].offset = start;
		fuse_page_descs_length_init(ap->descs, ap->num_pages, npages);

		ap->num_pages += npages;
		ap->descs[ap->num_pages - 1].length -=
			(PAGE_SIZE - ret) & (PAGE_SIZE - 1);
	}

	ap->args.user_pages = true;
	if (write)
		ap->args.in_pages = true;
	else
		ap->args.out_pages = true;

	*nbytesp = nbytes;

	return ret < 0 ? ret : 0;
}

ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
		       loff_t *ppos, int flags)
{
	int write = flags & FUSE_DIO_WRITE;
	int cuse = flags & FUSE_DIO_CUSE;
	struct file *file = io->iocb->ki_filp;
	struct inode *inode = file->f_mapping->host;
	struct fuse_file *ff = file->private_data;
	struct fuse_conn *fc = ff->fm->fc;
	size_t nmax = write ? fc->max_write : fc->max_read;
	loff_t pos = *ppos;
	size_t count = iov_iter_count(iter);
	pgoff_t idx_from = pos >> PAGE_SHIFT;
	pgoff_t idx_to = (pos + count - 1) >> PAGE_SHIFT;
	ssize_t res = 0;
	int err = 0;
	struct fuse_io_args *ia;
	unsigned int max_pages;

	max_pages = iov_iter_npages(iter, fc->max_pages);
	ia = fuse_io_alloc(io, max_pages);
	if (!ia)
		return -ENOMEM;

	if (!cuse && fuse_range_is_writeback(inode, idx_from, idx_to)) {
		if (!write)
			inode_lock(inode);
		fuse_sync_writes(inode);
		if (!write)
			inode_unlock(inode);
	}

	io->should_dirty = !write && iter_is_iovec(iter);
	while (count) {
		ssize_t nres;
		fl_owner_t owner = current->files;
		size_t nbytes = min(count, nmax);

		err = fuse_get_user_pages(&ia->ap, iter, &nbytes, write,
					  max_pages);
		if (err && !nbytes)
			break;

		if (write) {
			if (!capable(CAP_FSETID))
				ia->write.in.write_flags |= FUSE_WRITE_KILL_SUIDGID;

			nres = fuse_send_write(ia, pos, nbytes, owner);
		} else {
			nres = fuse_send_read(ia, pos, nbytes, owner);
		}

		if (!io->async || nres < 0) {
			fuse_release_user_pages(&ia->ap, io->should_dirty);
			fuse_io_free(ia);
		}
		ia = NULL;
		if (nres < 0) {
			iov_iter_revert(iter, nbytes);
			err = nres;
			break;
		}
		WARN_ON(nres > nbytes);

		count -= nres;
		res += nres;
		pos += nres;
		if (nres != nbytes) {
			iov_iter_revert(iter, nbytes - nres);
			break;
		}
		if (count) {
			max_pages = iov_iter_npages(iter, fc->max_pages);
			ia = fuse_io_alloc(io, max_pages);
			if (!ia)
				break;
		}
	}
	if (ia)
		fuse_io_free(ia);
	if (res > 0)
		*ppos = pos;

	return res > 0 ? res : err;
}
EXPORT_SYMBOL_GPL(fuse_direct_io);

static ssize_t __fuse_direct_read(struct fuse_io_priv *io,
				  struct iov_iter *iter,
				  loff_t *ppos)
{
	ssize_t res;
	struct inode *inode = file_inode(io->iocb->ki_filp);

	res = fuse_direct_io(io, iter, ppos, 0);

	fuse_invalidate_atime(inode);

	return res;
}

static ssize_t fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter);

static ssize_t fuse_direct_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	ssize_t res;

	if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
		res = fuse_direct_IO(iocb, to);
	} else {
		struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);

		res = __fuse_direct_read(&io, to, &iocb->ki_pos);
	}

	return res;
}

static ssize_t fuse_direct_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct inode *inode = file_inode(iocb->ki_filp);
	struct fuse_io_priv io = FUSE_IO_PRIV_SYNC(iocb);
	ssize_t res;

	/* Don't allow parallel writes to the same file */
	inode_lock(inode);
	res = generic_write_checks(iocb, from);
	if (res > 0) {
		if (!is_sync_kiocb(iocb) && iocb->ki_flags & IOCB_DIRECT) {
			res = fuse_direct_IO(iocb, from);
		} else {
			res = fuse_direct_io(&io, from, &iocb->ki_pos,
					     FUSE_DIO_WRITE);
			fuse_write_update_attr(inode, iocb->ki_pos, res);
		}
	}
	inode_unlock(inode);

	return res;
}

static ssize_t fuse_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
	struct file *file = iocb->ki_filp;
	struct fuse_file *ff = file->private_data;
	struct inode *inode = file_inode(file);

	if (fuse_is_bad(inode))
		return -EIO;

	if (FUSE_IS_DAX(inode))
		return fuse_dax_read_iter(iocb, to);

	if (!(ff->open_flags & FOPEN_DIRECT_IO))
		return fuse_cache_read_iter(iocb, to);
	else
		return fuse_direct_read_iter(iocb, to);
}

static ssize_t fuse_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
	struct file *file = iocb->ki_filp;
	struct fuse_file *ff = file->private_data;
	struct inode *inode = file_inode(file);

	if (fuse_is_bad(inode))
		return -EIO;

	if (FUSE_IS_DAX(inode))
		return fuse_dax_write_iter(iocb, from);

	if (!(ff->open_flags & FOPEN_DIRECT_IO))
		return fuse_cache_write_iter(iocb, from);
	else
		return fuse_direct_write_iter(iocb, from);
}

static void fuse_writepage_free(struct fuse_writepage_args *wpa)
{
	struct fuse_args_pages *ap = &wpa->ia.ap;
	int i;

	if (wpa->bucket)
		fuse_sync_bucket_dec(wpa->bucket);

	for (i = 0; i < ap->num_pages; i++)
		__free_page(ap->pages[i]);

	if (wpa->ia.ff)
		fuse_file_put(wpa->ia.ff, false, false);

	kfree(ap->pages);
	kfree(wpa);
}

static void fuse_writepage_finish(struct fuse_mount *fm,
				  struct fuse_writepage_args *wpa)
{
	struct fuse_args_pages *ap = &wpa->ia.ap;
	struct inode *inode = wpa->inode;
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct backing_dev_info *bdi = inode_to_bdi(inode);
	int i;

	for (i = 0; i < ap->num_pages; i++) {
		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
		dec_node_page_state(ap->pages[i], NR_WRITEBACK_TEMP);
		wb_writeout_inc(&bdi->wb);
	}
	wake_up(&fi->page_waitq);
}

/* Called under fi->lock, may release and reacquire it */
static void fuse_send_writepage(struct fuse_mount *fm,
				struct fuse_writepage_args *wpa, loff_t size)
__releases(fi->lock)
__acquires(fi->lock)
{
	struct fuse_writepage_args *aux, *next;
	struct fuse_inode *fi = get_fuse_inode(wpa->inode);
	struct fuse_write_in *inarg = &wpa->ia.write.in;
	struct fuse_args *args = &wpa->ia.ap.args;
	__u64 data_size = wpa->ia.ap.num_pages * PAGE_SIZE;
	int err;

	fi->writectr++;
	if (inarg->offset + data_size <= size) {
		inarg->size = data_size;
	} else if (inarg->offset < size) {
		inarg->size = size - inarg->offset;
	} else {
		/* Got truncated off completely */
		goto out_free;
	}

	args->in_args[1].size = inarg->size;
	args->force = true;
	args->nocreds = true;

	err = fuse_simple_background(fm, args, GFP_ATOMIC);
	if (err == -ENOMEM) {
		spin_unlock(&fi->lock);
		err = fuse_simple_background(fm, args, GFP_NOFS | __GFP_NOFAIL);
		spin_lock(&fi->lock);
	}

	/* Fails on broken connection only */
	if (unlikely(err))
		goto out_free;

	return;

 out_free:
	fi->writectr--;
	rb_erase(&wpa->writepages_entry, &fi->writepages);
	fuse_writepage_finish(fm, wpa);
	spin_unlock(&fi->lock);

	/* After fuse_writepage_finish() aux request list is private */
	for (aux = wpa->next; aux; aux = next) {
		next = aux->next;
		aux->next = NULL;
		fuse_writepage_free(aux);
	}

	fuse_writepage_free(wpa);
	spin_lock(&fi->lock);
}

/*
 * If fi->writectr is positive (no truncate or fsync going on) send
 * all queued writepage requests.
 *
 * Called with fi->lock
 */
void fuse_flush_writepages(struct inode *inode)
__releases(fi->lock)
__acquires(fi->lock)
{
	struct fuse_mount *fm = get_fuse_mount(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);
	loff_t crop = i_size_read(inode);
	struct fuse_writepage_args *wpa;

	while (fi->writectr >= 0 && !list_empty(&fi->queued_writes)) {
		wpa = list_entry(fi->queued_writes.next,
				 struct fuse_writepage_args, queue_entry);
		list_del_init(&wpa->queue_entry);
		fuse_send_writepage(fm, wpa, crop);
	}
}

static struct fuse_writepage_args *fuse_insert_writeback(struct rb_root *root,
						struct fuse_writepage_args *wpa)
{
	pgoff_t idx_from = wpa->ia.write.in.offset >> PAGE_SHIFT;
	pgoff_t idx_to = idx_from + wpa->ia.ap.num_pages - 1;
	struct rb_node **p = &root->rb_node;
	struct rb_node  *parent = NULL;

	WARN_ON(!wpa->ia.ap.num_pages);
	while (*p) {
		struct fuse_writepage_args *curr;
		pgoff_t curr_index;

		parent = *p;
		curr = rb_entry(parent, struct fuse_writepage_args,
				writepages_entry);
		WARN_ON(curr->inode != wpa->inode);
		curr_index = curr->ia.write.in.offset >> PAGE_SHIFT;

		if (idx_from >= curr_index + curr->ia.ap.num_pages)
			p = &(*p)->rb_right;
		else if (idx_to < curr_index)
			p = &(*p)->rb_left;
		else
			return curr;
	}

	rb_link_node(&wpa->writepages_entry, parent, p);
	rb_insert_color(&wpa->writepages_entry, root);
	return NULL;
}

static void tree_insert(struct rb_root *root, struct fuse_writepage_args *wpa)
{
	WARN_ON(fuse_insert_writeback(root, wpa));
}

static void fuse_writepage_end(struct fuse_mount *fm, struct fuse_args *args,
			       int error)
{
	struct fuse_writepage_args *wpa =
		container_of(args, typeof(*wpa), ia.ap.args);
	struct inode *inode = wpa->inode;
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct fuse_conn *fc = get_fuse_conn(inode);

	mapping_set_error(inode->i_mapping, error);
	/*
	 * A writeback finished and this might have updated mtime/ctime on
	 * server making local mtime/ctime stale.  Hence invalidate attrs.
	 * Do this only if writeback_cache is not enabled.  If writeback_cache
	 * is enabled, we trust local ctime/mtime.
	 */
	if (!fc->writeback_cache)
		fuse_invalidate_attr_mask(inode, FUSE_STATX_MODIFY);
	spin_lock(&fi->lock);
	rb_erase(&wpa->writepages_entry, &fi->writepages);
	while (wpa->next) {
		struct fuse_mount *fm = get_fuse_mount(inode);
		struct fuse_write_in *inarg = &wpa->ia.write.in;
		struct fuse_writepage_args *next = wpa->next;

		wpa->next = next->next;
		next->next = NULL;
		next->ia.ff = fuse_file_get(wpa->ia.ff);
		tree_insert(&fi->writepages, next);

		/*
		 * Skip fuse_flush_writepages() to make it easy to crop requests
		 * based on primary request size.
		 *
		 * 1st case (trivial): there are no concurrent activities using
		 * fuse_set/release_nowrite.  Then we're on safe side because
		 * fuse_flush_writepages() would call fuse_send_writepage()
		 * anyway.
		 *
		 * 2nd case: someone called fuse_set_nowrite and it is waiting
		 * now for completion of all in-flight requests.  This happens
		 * rarely and no more than once per page, so this should be
		 * okay.
		 *
		 * 3rd case: someone (e.g. fuse_do_setattr()) is in the middle
		 * of fuse_set_nowrite..fuse_release_nowrite section.  The fact
		 * that fuse_set_nowrite returned implies that all in-flight
		 * requests were completed along with all of their secondary
		 * requests.  Further primary requests are blocked by negative
		 * writectr.  Hence there cannot be any in-flight requests and
		 * no invocations of fuse_writepage_end() while we're in
		 * fuse_set_nowrite..fuse_release_nowrite section.
		 */
		fuse_send_writepage(fm, next, inarg->offset + inarg->size);
	}
	fi->writectr--;
	fuse_writepage_finish(fm, wpa);
	spin_unlock(&fi->lock);
	fuse_writepage_free(wpa);
}

static struct fuse_file *__fuse_write_file_get(struct fuse_inode *fi)
{
	struct fuse_file *ff;

	spin_lock(&fi->lock);
	ff = list_first_entry_or_null(&fi->write_files, struct fuse_file,
				      write_entry);
	if (ff)
		fuse_file_get(ff);
	spin_unlock(&fi->lock);

	return ff;
}

static struct fuse_file *fuse_write_file_get(struct fuse_inode *fi)
{
	struct fuse_file *ff = __fuse_write_file_get(fi);
	WARN_ON(!ff);
	return ff;
}

int fuse_write_inode(struct inode *inode, struct writeback_control *wbc)
{
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct fuse_file *ff;
	int err;

	/*
	 * Inode is always written before the last reference is dropped and
	 * hence this should not be reached from reclaim.
	 *
	 * Writing back the inode from reclaim can deadlock if the request
	 * processing itself needs an allocation.  Allocations triggering
	 * reclaim while serving a request can't be prevented, because it can
	 * involve any number of unrelated userspace processes.
	 */
	WARN_ON(wbc->for_reclaim);

	ff = __fuse_write_file_get(fi);
	err = fuse_flush_times(inode, ff);
	if (ff)
		fuse_file_put(ff, false, false);

	return err;
}

static struct fuse_writepage_args *fuse_writepage_args_alloc(void)
{
	struct fuse_writepage_args *wpa;
	struct fuse_args_pages *ap;

	wpa = kzalloc(sizeof(*wpa), GFP_NOFS);
	if (wpa) {
		ap = &wpa->ia.ap;
		ap->num_pages = 0;
		ap->pages = fuse_pages_alloc(1, GFP_NOFS, &ap->descs);
		if (!ap->pages) {
			kfree(wpa);
			wpa = NULL;
		}
	}
	return wpa;

}

static void fuse_writepage_add_to_bucket(struct fuse_conn *fc,
					 struct fuse_writepage_args *wpa)
{
	if (!fc->sync_fs)
		return;

	rcu_read_lock();
	/* Prevent resurrection of dead bucket in unlikely race with syncfs */
	do {
		wpa->bucket = rcu_dereference(fc->curr_bucket);
	} while (unlikely(!atomic_inc_not_zero(&wpa->bucket->count)));
	rcu_read_unlock();
}

static int fuse_writepage_locked(struct page *page)
{
	struct address_space *mapping = page->mapping;
	struct inode *inode = mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct fuse_writepage_args *wpa;
	struct fuse_args_pages *ap;
	struct page *tmp_page;
	int error = -ENOMEM;

	set_page_writeback(page);

	wpa = fuse_writepage_args_alloc();
	if (!wpa)
		goto err;
	ap = &wpa->ia.ap;

	tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
	if (!tmp_page)
		goto err_free;

	error = -EIO;
	wpa->ia.ff = fuse_write_file_get(fi);
	if (!wpa->ia.ff)
		goto err_nofile;

	fuse_writepage_add_to_bucket(fc, wpa);
	fuse_write_args_fill(&wpa->ia, wpa->ia.ff, page_offset(page), 0);

	copy_highpage(tmp_page, page);
	wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE;
	wpa->next = NULL;
	ap->args.in_pages = true;
	ap->num_pages = 1;
	ap->pages[0] = tmp_page;
	ap->descs[0].offset = 0;
	ap->descs[0].length = PAGE_SIZE;
	ap->args.end = fuse_writepage_end;
	wpa->inode = inode;

	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);

	spin_lock(&fi->lock);
	tree_insert(&fi->writepages, wpa);
	list_add_tail(&wpa->queue_entry, &fi->queued_writes);
	fuse_flush_writepages(inode);
	spin_unlock(&fi->lock);

	end_page_writeback(page);

	return 0;

err_nofile:
	__free_page(tmp_page);
err_free:
	kfree(wpa);
err:
	mapping_set_error(page->mapping, error);
	end_page_writeback(page);
	return error;
}

static int fuse_writepage(struct page *page, struct writeback_control *wbc)
{
	struct fuse_conn *fc = get_fuse_conn(page->mapping->host);
	int err;

	if (fuse_page_is_writeback(page->mapping->host, page->index)) {
		/*
		 * ->writepages() should be called for sync() and friends.  We
		 * should only get here on direct reclaim and then we are
		 * allowed to skip a page which is already in flight
		 */
		WARN_ON(wbc->sync_mode == WB_SYNC_ALL);

		redirty_page_for_writepage(wbc, page);
		unlock_page(page);
		return 0;
	}

	if (wbc->sync_mode == WB_SYNC_NONE &&
	    fc->num_background >= fc->congestion_threshold)
		return AOP_WRITEPAGE_ACTIVATE;

	err = fuse_writepage_locked(page);
	unlock_page(page);

	return err;
}

struct fuse_fill_wb_data {
	struct fuse_writepage_args *wpa;
	struct fuse_file *ff;
	struct inode *inode;
	struct page **orig_pages;
	unsigned int max_pages;
};

static bool fuse_pages_realloc(struct fuse_fill_wb_data *data)
{
	struct fuse_args_pages *ap = &data->wpa->ia.ap;
	struct fuse_conn *fc = get_fuse_conn(data->inode);
	struct page **pages;
	struct fuse_page_desc *descs;
	unsigned int npages = min_t(unsigned int,
				    max_t(unsigned int, data->max_pages * 2,
					  FUSE_DEFAULT_MAX_PAGES_PER_REQ),
				    fc->max_pages);
	WARN_ON(npages <= data->max_pages);

	pages = fuse_pages_alloc(npages, GFP_NOFS, &descs);
	if (!pages)
		return false;

	memcpy(pages, ap->pages, sizeof(struct page *) * ap->num_pages);
	memcpy(descs, ap->descs, sizeof(struct fuse_page_desc) * ap->num_pages);
	kfree(ap->pages);
	ap->pages = pages;
	ap->descs = descs;
	data->max_pages = npages;

	return true;
}

static void fuse_writepages_send(struct fuse_fill_wb_data *data)
{
	struct fuse_writepage_args *wpa = data->wpa;
	struct inode *inode = data->inode;
	struct fuse_inode *fi = get_fuse_inode(inode);
	int num_pages = wpa->ia.ap.num_pages;
	int i;

	wpa->ia.ff = fuse_file_get(data->ff);
	spin_lock(&fi->lock);
	list_add_tail(&wpa->queue_entry, &fi->queued_writes);
	fuse_flush_writepages(inode);
	spin_unlock(&fi->lock);

	for (i = 0; i < num_pages; i++)
		end_page_writeback(data->orig_pages[i]);
}

/*
 * Check under fi->lock if the page is under writeback, and insert it onto the
 * rb_tree if not. Otherwise iterate auxiliary write requests, to see if there's
 * one already added for a page at this offset.  If there's none, then insert
 * this new request onto the auxiliary list, otherwise reuse the existing one by
 * swapping the new temp page with the old one.
 */
static bool fuse_writepage_add(struct fuse_writepage_args *new_wpa,
			       struct page *page)
{
	struct fuse_inode *fi = get_fuse_inode(new_wpa->inode);
	struct fuse_writepage_args *tmp;
	struct fuse_writepage_args *old_wpa;
	struct fuse_args_pages *new_ap = &new_wpa->ia.ap;

	WARN_ON(new_ap->num_pages != 0);
	new_ap->num_pages = 1;

	spin_lock(&fi->lock);
	old_wpa = fuse_insert_writeback(&fi->writepages, new_wpa);
	if (!old_wpa) {
		spin_unlock(&fi->lock);
		return true;
	}

	for (tmp = old_wpa->next; tmp; tmp = tmp->next) {
		pgoff_t curr_index;

		WARN_ON(tmp->inode != new_wpa->inode);
		curr_index = tmp->ia.write.in.offset >> PAGE_SHIFT;
		if (curr_index == page->index) {
			WARN_ON(tmp->ia.ap.num_pages != 1);
			swap(tmp->ia.ap.pages[0], new_ap->pages[0]);
			break;
		}
	}

	if (!tmp) {
		new_wpa->next = old_wpa->next;
		old_wpa->next = new_wpa;
	}

	spin_unlock(&fi->lock);

	if (tmp) {
		struct backing_dev_info *bdi = inode_to_bdi(new_wpa->inode);

		dec_wb_stat(&bdi->wb, WB_WRITEBACK);
		dec_node_page_state(new_ap->pages[0], NR_WRITEBACK_TEMP);
		wb_writeout_inc(&bdi->wb);
		fuse_writepage_free(new_wpa);
	}

	return false;
}

static bool fuse_writepage_need_send(struct fuse_conn *fc, struct page *page,
				     struct fuse_args_pages *ap,
				     struct fuse_fill_wb_data *data)
{
	WARN_ON(!ap->num_pages);

	/*
	 * Being under writeback is unlikely but possible.  For example direct
	 * read to an mmaped fuse file will set the page dirty twice; once when
	 * the pages are faulted with get_user_pages(), and then after the read
	 * completed.
	 */
	if (fuse_page_is_writeback(data->inode, page->index))
		return true;

	/* Reached max pages */
	if (ap->num_pages == fc->max_pages)
		return true;

	/* Reached max write bytes */
	if ((ap->num_pages + 1) * PAGE_SIZE > fc->max_write)
		return true;

	/* Discontinuity */
	if (data->orig_pages[ap->num_pages - 1]->index + 1 != page->index)
		return true;

	/* Need to grow the pages array?  If so, did the expansion fail? */
	if (ap->num_pages == data->max_pages && !fuse_pages_realloc(data))
		return true;

	return false;
}

static int fuse_writepages_fill(struct page *page,
		struct writeback_control *wbc, void *_data)
{
	struct fuse_fill_wb_data *data = _data;
	struct fuse_writepage_args *wpa = data->wpa;
	struct fuse_args_pages *ap = &wpa->ia.ap;
	struct inode *inode = data->inode;
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct page *tmp_page;
	int err;

	if (!data->ff) {
		err = -EIO;
		data->ff = fuse_write_file_get(fi);
		if (!data->ff)
			goto out_unlock;
	}

	if (wpa && fuse_writepage_need_send(fc, page, ap, data)) {
		fuse_writepages_send(data);
		data->wpa = NULL;
	}

	err = -ENOMEM;
	tmp_page = alloc_page(GFP_NOFS | __GFP_HIGHMEM);
	if (!tmp_page)
		goto out_unlock;

	/*
	 * The page must not be redirtied until the writeout is completed
	 * (i.e. userspace has sent a reply to the write request).  Otherwise
	 * there could be more than one temporary page instance for each real
	 * page.
	 *
	 * This is ensured by holding the page lock in page_mkwrite() while
	 * checking fuse_page_is_writeback().  We already hold the page lock
	 * since clear_page_dirty_for_io() and keep it held until we add the
	 * request to the fi->writepages list and increment ap->num_pages.
	 * After this fuse_page_is_writeback() will indicate that the page is
	 * under writeback, so we can release the page lock.
	 */
	if (data->wpa == NULL) {
		err = -ENOMEM;
		wpa = fuse_writepage_args_alloc();
		if (!wpa) {
			__free_page(tmp_page);
			goto out_unlock;
		}
		fuse_writepage_add_to_bucket(fc, wpa);

		data->max_pages = 1;

		ap = &wpa->ia.ap;
		fuse_write_args_fill(&wpa->ia, data->ff, page_offset(page), 0);
		wpa->ia.write.in.write_flags |= FUSE_WRITE_CACHE;
		wpa->next = NULL;
		ap->args.in_pages = true;
		ap->args.end = fuse_writepage_end;
		ap->num_pages = 0;
		wpa->inode = inode;
	}
	set_page_writeback(page);

	copy_highpage(tmp_page, page);
	ap->pages[ap->num_pages] = tmp_page;
	ap->descs[ap->num_pages].offset = 0;
	ap->descs[ap->num_pages].length = PAGE_SIZE;
	data->orig_pages[ap->num_pages] = page;

	inc_wb_stat(&inode_to_bdi(inode)->wb, WB_WRITEBACK);
	inc_node_page_state(tmp_page, NR_WRITEBACK_TEMP);

	err = 0;
	if (data->wpa) {
		/*
		 * Protected by fi->lock against concurrent access by
		 * fuse_page_is_writeback().
		 */
		spin_lock(&fi->lock);
		ap->num_pages++;
		spin_unlock(&fi->lock);
	} else if (fuse_writepage_add(wpa, page)) {
		data->wpa = wpa;
	} else {
		end_page_writeback(page);
	}
out_unlock:
	unlock_page(page);

	return err;
}

static int fuse_writepages(struct address_space *mapping,
			   struct writeback_control *wbc)
{
	struct inode *inode = mapping->host;
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_fill_wb_data data;
	int err;

	err = -EIO;
	if (fuse_is_bad(inode))
		goto out;

	if (wbc->sync_mode == WB_SYNC_NONE &&
	    fc->num_background >= fc->congestion_threshold)
		return 0;

	data.inode = inode;
	data.wpa = NULL;
	data.ff = NULL;

	err = -ENOMEM;
	data.orig_pages = kcalloc(fc->max_pages,
				  sizeof(struct page *),
				  GFP_NOFS);
	if (!data.orig_pages)
		goto out;

	err = write_cache_pages(mapping, wbc, fuse_writepages_fill, &data);
	if (data.wpa) {
		WARN_ON(!data.wpa->ia.ap.num_pages);
		fuse_writepages_send(&data);
	}
	if (data.ff)
		fuse_file_put(data.ff, false, false);

	kfree(data.orig_pages);
out:
	return err;
}

/*
 * It's worthy to make sure that space is reserved on disk for the write,
 * but how to implement it without killing performance need more thinking.
 */
static int fuse_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_SHIFT;
	struct fuse_conn *fc = get_fuse_conn(file_inode(file));
	struct page *page;
	loff_t fsize;
	int err = -ENOMEM;

	WARN_ON(!fc->writeback_cache);

	page = grab_cache_page_write_begin(mapping, index);
	if (!page)
		goto error;

	fuse_wait_on_page_writeback(mapping->host, page->index);

	if (PageUptodate(page) || len == PAGE_SIZE)
		goto success;
	/*
	 * Check if the start this page comes after the end of file, in which
	 * case the readpage can be optimized away.
	 */
	fsize = i_size_read(mapping->host);
	if (fsize <= (pos & PAGE_MASK)) {
		size_t off = pos & ~PAGE_MASK;
		if (off)
			zero_user_segment(page, 0, off);
		goto success;
	}
	err = fuse_do_readpage(file, page);
	if (err)
		goto cleanup;
success:
	*pagep = page;
	return 0;

cleanup:
	unlock_page(page);
	put_page(page);
error:
	return err;
}

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

	/* Haven't copied anything?  Skip zeroing, size extending, dirtying. */
	if (!copied)
		goto unlock;

	pos += copied;
	if (!PageUptodate(page)) {
		/* Zero any unwritten bytes at the end of the page */
		size_t endoff = pos & ~PAGE_MASK;
		if (endoff)
			zero_user_segment(page, endoff, PAGE_SIZE);
		SetPageUptodate(page);
	}

	if (pos > inode->i_size)
		i_size_write(inode, pos);

	set_page_dirty(page);

unlock:
	unlock_page(page);
	put_page(page);

	return copied;
}

static int fuse_launder_folio(struct folio *folio)
{
	int err = 0;
	if (folio_clear_dirty_for_io(folio)) {
		struct inode *inode = folio->mapping->host;

		/* Serialize with pending writeback for the same page */
		fuse_wait_on_page_writeback(inode, folio->index);
		err = fuse_writepage_locked(&folio->page);
		if (!err)
			fuse_wait_on_page_writeback(inode, folio->index);
	}
	return err;
}

/*
 * Write back dirty data/metadata now (there may not be any suitable
 * open files later for data)
 */
static void fuse_vma_close(struct vm_area_struct *vma)
{
	int err;

	err = write_inode_now(vma->vm_file->f_mapping->host, 1);
	mapping_set_error(vma->vm_file->f_mapping, err);
}

/*
 * Wait for writeback against this page to complete before allowing it
 * to be marked dirty again, and hence written back again, possibly
 * before the previous writepage completed.
 *
 * Block here, instead of in ->writepage(), so that the userspace fs
 * can only block processes actually operating on the filesystem.
 *
 * Otherwise unprivileged userspace fs would be able to block
 * unrelated:
 *
 * - page migration
 * - sync(2)
 * - try_to_free_pages() with order > PAGE_ALLOC_COSTLY_ORDER
 */
static vm_fault_t fuse_page_mkwrite(struct vm_fault *vmf)
{
	struct page *page = vmf->page;
	struct inode *inode = file_inode(vmf->vma->vm_file);

	file_update_time(vmf->vma->vm_file);
	lock_page(page);
	if (page->mapping != inode->i_mapping) {
		unlock_page(page);
		return VM_FAULT_NOPAGE;
	}

	fuse_wait_on_page_writeback(inode, page->index);
	return VM_FAULT_LOCKED;
}

static const struct vm_operations_struct fuse_file_vm_ops = {
	.close		= fuse_vma_close,
	.fault		= filemap_fault,
	.map_pages	= filemap_map_pages,
	.page_mkwrite	= fuse_page_mkwrite,
};

static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct fuse_file *ff = file->private_data;

	/* DAX mmap is superior to direct_io mmap */
	if (FUSE_IS_DAX(file_inode(file)))
		return fuse_dax_mmap(file, vma);

	if (ff->open_flags & FOPEN_DIRECT_IO) {
		/* Can't provide the coherency needed for MAP_SHARED */
		if (vma->vm_flags & VM_MAYSHARE)
			return -ENODEV;

		invalidate_inode_pages2(file->f_mapping);

		return generic_file_mmap(file, vma);
	}

	if ((vma->vm_flags & VM_SHARED) && (vma->vm_flags & VM_MAYWRITE))
		fuse_link_write_file(file);

	file_accessed(file);
	vma->vm_ops = &fuse_file_vm_ops;
	return 0;
}

static int convert_fuse_file_lock(struct fuse_conn *fc,
				  const struct fuse_file_lock *ffl,
				  struct file_lock *fl)
{
	switch (ffl->type) {
	case F_UNLCK:
		break;

	case F_RDLCK:
	case F_WRLCK:
		if (ffl->start > OFFSET_MAX || ffl->end > OFFSET_MAX ||
		    ffl->end < ffl->start)
			return -EIO;

		fl->fl_start = ffl->start;
		fl->fl_end = ffl->end;

		/*
		 * Convert pid into init's pid namespace.  The locks API will
		 * translate it into the caller's pid namespace.
		 */
		rcu_read_lock();
		fl->fl_pid = pid_nr_ns(find_pid_ns(ffl->pid, fc->pid_ns), &init_pid_ns);
		rcu_read_unlock();
		break;

	default:
		return -EIO;
	}
	fl->fl_type = ffl->type;
	return 0;
}

static void fuse_lk_fill(struct fuse_args *args, struct file *file,
			 const struct file_lock *fl, int opcode, pid_t pid,
			 int flock, struct fuse_lk_in *inarg)
{
	struct inode *inode = file_inode(file);
	struct fuse_conn *fc = get_fuse_conn(inode);
	struct fuse_file *ff = file->private_data;

	memset(inarg, 0, sizeof(*inarg));
	inarg->fh = ff->fh;
	inarg->owner = fuse_lock_owner_id(fc, fl->fl_owner);
	inarg->lk.start = fl->fl_start;
	inarg->lk.end = fl->fl_end;
	inarg->lk.type = fl->fl_type;
	inarg->lk.pid = pid;
	if (flock)
		inarg->lk_flags |= FUSE_LK_FLOCK;
	args->opcode = opcode;
	args->nodeid = get_node_id(inode);
	args->in_numargs = 1;
	args->in_args[0].size = sizeof(*inarg);
	args->in_args[0].value = inarg;
}

static int fuse_getlk(struct file *file, struct file_lock *fl)
{
	struct inode *inode = file_inode(file);
	struct fuse_mount *fm = get_fuse_mount(inode);
	FUSE_ARGS(args);
	struct fuse_lk_in inarg;
	struct fuse_lk_out outarg;
	int err;

	fuse_lk_fill(&args, file, fl, FUSE_GETLK, 0, 0, &inarg);
	args.out_numargs = 1;
	args.out_args[0].size = sizeof(outarg);
	args.out_args[0].value = &outarg;
	err = fuse_simple_request(fm, &args);
	if (!err)
		err = convert_fuse_file_lock(fm->fc, &outarg.lk, fl);

	return err;
}

static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
{
	struct inode *inode = file_inode(file);
	struct fuse_mount *fm = get_fuse_mount(inode);
	FUSE_ARGS(args);
	struct fuse_lk_in inarg;
	int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
	struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL;
	pid_t pid_nr = pid_nr_ns(pid, fm->fc->pid_ns);
	int err;

	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
		/* NLM needs asynchronous locks, which we don't support yet */
		return -ENOLCK;
	}

	/* Unlock on close is handled by the flush method */
	if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
		return 0;

	fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
	err = fuse_simple_request(fm, &args);

	/* locking is restartable */
	if (err == -EINTR)
		err = -ERESTARTSYS;

	return err;
}

static int fuse_file_lock(struct file *file, int cmd, struct file_lock *fl)
{
	struct inode *inode = file_inode(file);
	struct fuse_conn *fc = get_fuse_conn(inode);
	int err;

	if (cmd == F_CANCELLK) {
		err = 0;
	} else if (cmd == F_GETLK) {
		if (fc->no_lock) {
			posix_test_lock(file, fl);
			err = 0;
		} else
			err = fuse_getlk(file, fl);
	} else {
		if (fc->no_lock)
			err = posix_lock_file(file, fl, NULL);
		else
			err = fuse_setlk(file, fl, 0);
	}
	return err;
}

static int fuse_file_flock(struct file *file, int cmd, struct file_lock *fl)
{
	struct inode *inode = file_inode(file);
	struct fuse_conn *fc = get_fuse_conn(inode);
	int err;

	if (fc->no_flock) {
		err = locks_lock_file_wait(file, fl);
	} else {
		struct fuse_file *ff = file->private_data;

		/* emulate flock with POSIX locks */
		ff->flock = true;
		err = fuse_setlk(file, fl, 1);
	}

	return err;
}

static sector_t fuse_bmap(struct address_space *mapping, sector_t block)
{
	struct inode *inode = mapping->host;
	struct fuse_mount *fm = get_fuse_mount(inode);
	FUSE_ARGS(args);
	struct fuse_bmap_in inarg;
	struct fuse_bmap_out outarg;
	int err;

	if (!inode->i_sb->s_bdev || fm->fc->no_bmap)
		return 0;

	memset(&inarg, 0, sizeof(inarg));
	inarg.block = block;
	inarg.blocksize = inode->i_sb->s_blocksize;
	args.opcode = FUSE_BMAP;
	args.nodeid = get_node_id(inode);
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	args.out_numargs = 1;
	args.out_args[0].size = sizeof(outarg);
	args.out_args[0].value = &outarg;
	err = fuse_simple_request(fm, &args);
	if (err == -ENOSYS)
		fm->fc->no_bmap = 1;

	return err ? 0 : outarg.block;
}

static loff_t fuse_lseek(struct file *file, loff_t offset, int whence)
{
	struct inode *inode = file->f_mapping->host;
	struct fuse_mount *fm = get_fuse_mount(inode);
	struct fuse_file *ff = file->private_data;
	FUSE_ARGS(args);
	struct fuse_lseek_in inarg = {
		.fh = ff->fh,
		.offset = offset,
		.whence = whence
	};
	struct fuse_lseek_out outarg;
	int err;

	if (fm->fc->no_lseek)
		goto fallback;

	args.opcode = FUSE_LSEEK;
	args.nodeid = ff->nodeid;
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	args.out_numargs = 1;
	args.out_args[0].size = sizeof(outarg);
	args.out_args[0].value = &outarg;
	err = fuse_simple_request(fm, &args);
	if (err) {
		if (err == -ENOSYS) {
			fm->fc->no_lseek = 1;
			goto fallback;
		}
		return err;
	}

	return vfs_setpos(file, outarg.offset, inode->i_sb->s_maxbytes);

fallback:
	err = fuse_update_attributes(inode, file, STATX_SIZE);
	if (!err)
		return generic_file_llseek(file, offset, whence);
	else
		return err;
}

static loff_t fuse_file_llseek(struct file *file, loff_t offset, int whence)
{
	loff_t retval;
	struct inode *inode = file_inode(file);

	switch (whence) {
	case SEEK_SET:
	case SEEK_CUR:
		 /* No i_mutex protection necessary for SEEK_CUR and SEEK_SET */
		retval = generic_file_llseek(file, offset, whence);
		break;
	case SEEK_END:
		inode_lock(inode);
		retval = fuse_update_attributes(inode, file, STATX_SIZE);
		if (!retval)
			retval = generic_file_llseek(file, offset, whence);
		inode_unlock(inode);
		break;
	case SEEK_HOLE:
	case SEEK_DATA:
		inode_lock(inode);
		retval = fuse_lseek(file, offset, whence);
		inode_unlock(inode);
		break;
	default:
		retval = -EINVAL;
	}

	return retval;
}

/*
 * All files which have been polled are linked to RB tree
 * fuse_conn->polled_files which is indexed by kh.  Walk the tree and
 * find the matching one.
 */
static struct rb_node **fuse_find_polled_node(struct fuse_conn *fc, u64 kh,
					      struct rb_node **parent_out)
{
	struct rb_node **link = &fc->polled_files.rb_node;
	struct rb_node *last = NULL;

	while (*link) {
		struct fuse_file *ff;

		last = *link;
		ff = rb_entry(last, struct fuse_file, polled_node);

		if (kh < ff->kh)
			link = &last->rb_left;
		else if (kh > ff->kh)
			link = &last->rb_right;
		else
			return link;
	}

	if (parent_out)
		*parent_out = last;
	return link;
}

/*
 * The file is about to be polled.  Make sure it's on the polled_files
 * RB tree.  Note that files once added to the polled_files tree are
 * not removed before the file is released.  This is because a file
 * polled once is likely to be polled again.
 */
static void fuse_register_polled_file(struct fuse_conn *fc,
				      struct fuse_file *ff)
{
	spin_lock(&fc->lock);
	if (RB_EMPTY_NODE(&ff->polled_node)) {
		struct rb_node **link, *parent;

		link = fuse_find_polled_node(fc, ff->kh, &parent);
		BUG_ON(*link);
		rb_link_node(&ff->polled_node, parent, link);
		rb_insert_color(&ff->polled_node, &fc->polled_files);
	}
	spin_unlock(&fc->lock);
}

__poll_t fuse_file_poll(struct file *file, poll_table *wait)
{
	struct fuse_file *ff = file->private_data;
	struct fuse_mount *fm = ff->fm;
	struct fuse_poll_in inarg = { .fh = ff->fh, .kh = ff->kh };
	struct fuse_poll_out outarg;
	FUSE_ARGS(args);
	int err;

	if (fm->fc->no_poll)
		return DEFAULT_POLLMASK;

	poll_wait(file, &ff->poll_wait, wait);
	inarg.events = mangle_poll(poll_requested_events(wait));

	/*
	 * Ask for notification iff there's someone waiting for it.
	 * The client may ignore the flag and always notify.
	 */
	if (waitqueue_active(&ff->poll_wait)) {
		inarg.flags |= FUSE_POLL_SCHEDULE_NOTIFY;
		fuse_register_polled_file(fm->fc, ff);
	}

	args.opcode = FUSE_POLL;
	args.nodeid = ff->nodeid;
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	args.out_numargs = 1;
	args.out_args[0].size = sizeof(outarg);
	args.out_args[0].value = &outarg;
	err = fuse_simple_request(fm, &args);

	if (!err)
		return demangle_poll(outarg.revents);
	if (err == -ENOSYS) {
		fm->fc->no_poll = 1;
		return DEFAULT_POLLMASK;
	}
	return EPOLLERR;
}
EXPORT_SYMBOL_GPL(fuse_file_poll);

/*
 * This is called from fuse_handle_notify() on FUSE_NOTIFY_POLL and
 * wakes up the poll waiters.
 */
int fuse_notify_poll_wakeup(struct fuse_conn *fc,
			    struct fuse_notify_poll_wakeup_out *outarg)
{
	u64 kh = outarg->kh;
	struct rb_node **link;

	spin_lock(&fc->lock);

	link = fuse_find_polled_node(fc, kh, NULL);
	if (*link) {
		struct fuse_file *ff;

		ff = rb_entry(*link, struct fuse_file, polled_node);
		wake_up_interruptible_sync(&ff->poll_wait);
	}

	spin_unlock(&fc->lock);
	return 0;
}

static void fuse_do_truncate(struct file *file)
{
	struct inode *inode = file->f_mapping->host;
	struct iattr attr;

	attr.ia_valid = ATTR_SIZE;
	attr.ia_size = i_size_read(inode);

	attr.ia_file = file;
	attr.ia_valid |= ATTR_FILE;

	fuse_do_setattr(file_dentry(file), &attr, file);
}

static inline loff_t fuse_round_up(struct fuse_conn *fc, loff_t off)
{
	return round_up(off, fc->max_pages << PAGE_SHIFT);
}

static ssize_t
fuse_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
{
	DECLARE_COMPLETION_ONSTACK(wait);
	ssize_t ret = 0;
	struct file *file = iocb->ki_filp;
	struct fuse_file *ff = file->private_data;
	loff_t pos = 0;
	struct inode *inode;
	loff_t i_size;
	size_t count = iov_iter_count(iter), shortened = 0;
	loff_t offset = iocb->ki_pos;
	struct fuse_io_priv *io;

	pos = offset;
	inode = file->f_mapping->host;
	i_size = i_size_read(inode);

	if ((iov_iter_rw(iter) == READ) && (offset >= i_size))
		return 0;

	io = kmalloc(sizeof(struct fuse_io_priv), GFP_KERNEL);
	if (!io)
		return -ENOMEM;
	spin_lock_init(&io->lock);
	kref_init(&io->refcnt);
	io->reqs = 1;
	io->bytes = -1;
	io->size = 0;
	io->offset = offset;
	io->write = (iov_iter_rw(iter) == WRITE);
	io->err = 0;
	/*
	 * By default, we want to optimize all I/Os with async request
	 * submission to the client filesystem if supported.
	 */
	io->async = ff->fm->fc->async_dio;
	io->iocb = iocb;
	io->blocking = is_sync_kiocb(iocb);

	/* optimization for short read */
	if (io->async && !io->write && offset + count > i_size) {
		iov_iter_truncate(iter, fuse_round_up(ff->fm->fc, i_size - offset));
		shortened = count - iov_iter_count(iter);
		count -= shortened;
	}

	/*
	 * We cannot asynchronously extend the size of a file.
	 * In such case the aio will behave exactly like sync io.
	 */
	if ((offset + count > i_size) && io->write)
		io->blocking = true;

	if (io->async && io->blocking) {
		/*
		 * Additional reference to keep io around after
		 * calling fuse_aio_complete()
		 */
		kref_get(&io->refcnt);
		io->done = &wait;
	}

	if (iov_iter_rw(iter) == WRITE) {
		ret = fuse_direct_io(io, iter, &pos, FUSE_DIO_WRITE);
		fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);
	} else {
		ret = __fuse_direct_read(io, iter, &pos);
	}
	iov_iter_reexpand(iter, iov_iter_count(iter) + shortened);

	if (io->async) {
		bool blocking = io->blocking;

		fuse_aio_complete(io, ret < 0 ? ret : 0, -1);

		/* we have a non-extending, async request, so return */
		if (!blocking)
			return -EIOCBQUEUED;

		wait_for_completion(&wait);
		ret = fuse_get_res_by_io(io);
	}

	kref_put(&io->refcnt, fuse_io_release);

	if (iov_iter_rw(iter) == WRITE) {
		fuse_write_update_attr(inode, pos, ret);
		if (ret < 0 && offset + count > i_size)
			fuse_do_truncate(file);
	}

	return ret;
}

static int fuse_writeback_range(struct inode *inode, loff_t start, loff_t end)
{
	int err = filemap_write_and_wait_range(inode->i_mapping, start, LLONG_MAX);

	if (!err)
		fuse_sync_writes(inode);

	return err;
}

static long fuse_file_fallocate(struct file *file, int mode, loff_t offset,
				loff_t length)
{
	struct fuse_file *ff = file->private_data;
	struct inode *inode = file_inode(file);
	struct fuse_inode *fi = get_fuse_inode(inode);
	struct fuse_mount *fm = ff->fm;
	FUSE_ARGS(args);
	struct fuse_fallocate_in inarg = {
		.fh = ff->fh,
		.offset = offset,
		.length = length,
		.mode = mode
	};
	int err;
	bool lock_inode = !(mode & FALLOC_FL_KEEP_SIZE) ||
			   (mode & (FALLOC_FL_PUNCH_HOLE |
				    FALLOC_FL_ZERO_RANGE));

	bool block_faults = FUSE_IS_DAX(inode) && lock_inode;

	if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE |
		     FALLOC_FL_ZERO_RANGE))
		return -EOPNOTSUPP;

	if (fm->fc->no_fallocate)
		return -EOPNOTSUPP;

	if (lock_inode) {
		inode_lock(inode);
		if (block_faults) {
			filemap_invalidate_lock(inode->i_mapping);
			err = fuse_dax_break_layouts(inode, 0, 0);
			if (err)
				goto out;
		}

		if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE)) {
			loff_t endbyte = offset + length - 1;

			err = fuse_writeback_range(inode, offset, endbyte);
			if (err)
				goto out;
		}
	}

	if (!(mode & FALLOC_FL_KEEP_SIZE) &&
	    offset + length > i_size_read(inode)) {
		err = inode_newsize_ok(inode, offset + length);
		if (err)
			goto out;
	}

	if (!(mode & FALLOC_FL_KEEP_SIZE))
		set_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);

	args.opcode = FUSE_FALLOCATE;
	args.nodeid = ff->nodeid;
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	err = fuse_simple_request(fm, &args);
	if (err == -ENOSYS) {
		fm->fc->no_fallocate = 1;
		err = -EOPNOTSUPP;
	}
	if (err)
		goto out;

	/* we could have extended the file */
	if (!(mode & FALLOC_FL_KEEP_SIZE)) {
		if (fuse_write_update_attr(inode, offset + length, length))
			file_update_time(file);
	}

	if (mode & (FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE))
		truncate_pagecache_range(inode, offset, offset + length - 1);

	fuse_invalidate_attr_mask(inode, FUSE_STATX_MODSIZE);

out:
	if (!(mode & FALLOC_FL_KEEP_SIZE))
		clear_bit(FUSE_I_SIZE_UNSTABLE, &fi->state);

	if (block_faults)
		filemap_invalidate_unlock(inode->i_mapping);

	if (lock_inode)
		inode_unlock(inode);

	fuse_flush_time_update(inode);

	return err;
}

static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in,
				      struct file *file_out, loff_t pos_out,
				      size_t len, unsigned int flags)
{
	struct fuse_file *ff_in = file_in->private_data;
	struct fuse_file *ff_out = file_out->private_data;
	struct inode *inode_in = file_inode(file_in);
	struct inode *inode_out = file_inode(file_out);
	struct fuse_inode *fi_out = get_fuse_inode(inode_out);
	struct fuse_mount *fm = ff_in->fm;
	struct fuse_conn *fc = fm->fc;
	FUSE_ARGS(args);
	struct fuse_copy_file_range_in inarg = {
		.fh_in = ff_in->fh,
		.off_in = pos_in,
		.nodeid_out = ff_out->nodeid,
		.fh_out = ff_out->fh,
		.off_out = pos_out,
		.len = len,
		.flags = flags
	};
	struct fuse_write_out outarg;
	ssize_t err;
	/* mark unstable when write-back is not used, and file_out gets
	 * extended */
	bool is_unstable = (!fc->writeback_cache) &&
			   ((pos_out + len) > inode_out->i_size);

	if (fc->no_copy_file_range)
		return -EOPNOTSUPP;

	if (file_inode(file_in)->i_sb != file_inode(file_out)->i_sb)
		return -EXDEV;

	inode_lock(inode_in);
	err = fuse_writeback_range(inode_in, pos_in, pos_in + len - 1);
	inode_unlock(inode_in);
	if (err)
		return err;

	inode_lock(inode_out);

	err = file_modified(file_out);
	if (err)
		goto out;

	/*
	 * Write out dirty pages in the destination file before sending the COPY
	 * request to userspace.  After the request is completed, truncate off
	 * pages (including partial ones) from the cache that have been copied,
	 * since these contain stale data at that point.
	 *
	 * This should be mostly correct, but if the COPY writes to partial
	 * pages (at the start or end) and the parts not covered by the COPY are
	 * written through a memory map after calling fuse_writeback_range(),
	 * then these partial page modifications will be lost on truncation.
	 *
	 * It is unlikely that someone would rely on such mixed style
	 * modifications.  Yet this does give less guarantees than if the
	 * copying was performed with write(2).
	 *
	 * To fix this a mapping->invalidate_lock could be used to prevent new
	 * faults while the copy is ongoing.
	 */
	err = fuse_writeback_range(inode_out, pos_out, pos_out + len - 1);
	if (err)
		goto out;

	if (is_unstable)
		set_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state);

	args.opcode = FUSE_COPY_FILE_RANGE;
	args.nodeid = ff_in->nodeid;
	args.in_numargs = 1;
	args.in_args[0].size = sizeof(inarg);
	args.in_args[0].value = &inarg;
	args.out_numargs = 1;
	args.out_args[0].size = sizeof(outarg);
	args.out_args[0].value = &outarg;
	err = fuse_simple_request(fm, &args);
	if (err == -ENOSYS) {
		fc->no_copy_file_range = 1;
		err = -EOPNOTSUPP;
	}
	if (err)
		goto out;

	truncate_inode_pages_range(inode_out->i_mapping,
				   ALIGN_DOWN(pos_out, PAGE_SIZE),
				   ALIGN(pos_out + outarg.size, PAGE_SIZE) - 1);

	file_update_time(file_out);
	fuse_write_update_attr(inode_out, pos_out + outarg.size, outarg.size);

	err = outarg.size;
out:
	if (is_unstable)
		clear_bit(FUSE_I_SIZE_UNSTABLE, &fi_out->state);

	inode_unlock(inode_out);
	file_accessed(file_in);

	fuse_flush_time_update(inode_out);

	return err;
}

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

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

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

static const struct file_operations fuse_file_operations = {
	.llseek		= fuse_file_llseek,
	.read_iter	= fuse_file_read_iter,
	.write_iter	= fuse_file_write_iter,
	.mmap		= fuse_file_mmap,
	.open		= fuse_open,
	.flush		= fuse_flush,
	.release	= fuse_release,
	.fsync		= fuse_fsync,
	.lock		= fuse_file_lock,
	.get_unmapped_area = thp_get_unmapped_area,
	.flock		= fuse_file_flock,
	.splice_read	= generic_file_splice_read,
	.splice_write	= iter_file_splice_write,
	.unlocked_ioctl	= fuse_file_ioctl,
	.compat_ioctl	= fuse_file_compat_ioctl,
	.poll		= fuse_file_poll,
	.fallocate	= fuse_file_fallocate,
	.copy_file_range = fuse_copy_file_range,
};

static const struct address_space_operations fuse_file_aops  = {
	.readpage	= fuse_readpage,
	.readahead	= fuse_readahead,
	.writepage	= fuse_writepage,
	.writepages	= fuse_writepages,
	.launder_folio	= fuse_launder_folio,
	.dirty_folio	= filemap_dirty_folio,
	.bmap		= fuse_bmap,
	.direct_IO	= fuse_direct_IO,
	.write_begin	= fuse_write_begin,
	.write_end	= fuse_write_end,
};

void fuse_init_file_inode(struct inode *inode, unsigned int flags)
{
	struct fuse_inode *fi = get_fuse_inode(inode);

	inode->i_fop = &fuse_file_operations;
	inode->i_data.a_ops = &fuse_file_aops;

	INIT_LIST_HEAD(&fi->write_files);
	INIT_LIST_HEAD(&fi->queued_writes);
	fi->writectr = 0;
	init_waitqueue_head(&fi->page_waitq);
	fi->writepages = RB_ROOT;

	if (IS_ENABLED(CONFIG_FUSE_DAX))
		fuse_dax_inode_init(inode, flags);
}