summaryrefslogtreecommitdiff
path: root/include/linux/fs.h
blob: 6867512907d6e593ec18cbd27dc52471b66418a0 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _LINUX_FS_H
#define _LINUX_FS_H

#include <linux/linkage.h>
#include <linux/wait_bit.h>
#include <linux/kdev_t.h>
#include <linux/dcache.h>
#include <linux/path.h>
#include <linux/stat.h>
#include <linux/cache.h>
#include <linux/list.h>
#include <linux/list_lru.h>
#include <linux/llist.h>
#include <linux/radix-tree.h>
#include <linux/xarray.h>
#include <linux/rbtree.h>
#include <linux/init.h>
#include <linux/pid.h>
#include <linux/bug.h>
#include <linux/mutex.h>
#include <linux/rwsem.h>
#include <linux/mm_types.h>
#include <linux/capability.h>
#include <linux/semaphore.h>
#include <linux/fcntl.h>
#include <linux/rculist_bl.h>
#include <linux/atomic.h>
#include <linux/shrinker.h>
#include <linux/migrate_mode.h>
#include <linux/uidgid.h>
#include <linux/lockdep.h>
#include <linux/percpu-rwsem.h>
#include <linux/workqueue.h>
#include <linux/delayed_call.h>
#include <linux/uuid.h>
#include <linux/errseq.h>
#include <linux/ioprio.h>
#include <linux/fs_types.h>
#include <linux/build_bug.h>
#include <linux/stddef.h>
#include <linux/mount.h>
#include <linux/cred.h>
#include <linux/mnt_idmapping.h>
#include <linux/slab.h>

#include <asm/byteorder.h>
#include <uapi/linux/fs.h>

struct backing_dev_info;
struct bdi_writeback;
struct bio;
struct io_comp_batch;
struct export_operations;
struct fiemap_extent_info;
struct hd_geometry;
struct iovec;
struct kiocb;
struct kobject;
struct pipe_inode_info;
struct poll_table_struct;
struct kstatfs;
struct vm_area_struct;
struct vfsmount;
struct cred;
struct swap_info_struct;
struct seq_file;
struct workqueue_struct;
struct iov_iter;
struct fscrypt_info;
struct fscrypt_operations;
struct fsverity_info;
struct fsverity_operations;
struct fs_context;
struct fs_parameter_spec;
struct fileattr;
struct iomap_ops;

extern void __init inode_init(void);
extern void __init inode_init_early(void);
extern void __init files_init(void);
extern void __init files_maxfiles_init(void);

extern unsigned long get_max_files(void);
extern unsigned int sysctl_nr_open;

typedef __kernel_rwf_t rwf_t;

struct buffer_head;
typedef int (get_block_t)(struct inode *inode, sector_t iblock,
			struct buffer_head *bh_result, int create);
typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
			ssize_t bytes, void *private);

#define MAY_EXEC		0x00000001
#define MAY_WRITE		0x00000002
#define MAY_READ		0x00000004
#define MAY_APPEND		0x00000008
#define MAY_ACCESS		0x00000010
#define MAY_OPEN		0x00000020
#define MAY_CHDIR		0x00000040
/* called from RCU mode, don't block */
#define MAY_NOT_BLOCK		0x00000080

/*
 * flags in file.f_mode.  Note that FMODE_READ and FMODE_WRITE must correspond
 * to O_WRONLY and O_RDWR via the strange trick in do_dentry_open()
 */

/* file is open for reading */
#define FMODE_READ		((__force fmode_t)0x1)
/* file is open for writing */
#define FMODE_WRITE		((__force fmode_t)0x2)
/* file is seekable */
#define FMODE_LSEEK		((__force fmode_t)0x4)
/* file can be accessed using pread */
#define FMODE_PREAD		((__force fmode_t)0x8)
/* file can be accessed using pwrite */
#define FMODE_PWRITE		((__force fmode_t)0x10)
/* File is opened for execution with sys_execve / sys_uselib */
#define FMODE_EXEC		((__force fmode_t)0x20)
/* 32bit hashes as llseek() offset (for directories) */
#define FMODE_32BITHASH         ((__force fmode_t)0x200)
/* 64bit hashes as llseek() offset (for directories) */
#define FMODE_64BITHASH         ((__force fmode_t)0x400)

/*
 * Don't update ctime and mtime.
 *
 * Currently a special hack for the XFS open_by_handle ioctl, but we'll
 * hopefully graduate it to a proper O_CMTIME flag supported by open(2) soon.
 */
#define FMODE_NOCMTIME		((__force fmode_t)0x800)

/* Expect random access pattern */
#define FMODE_RANDOM		((__force fmode_t)0x1000)

/* File is huge (eg. /dev/mem): treat loff_t as unsigned */
#define FMODE_UNSIGNED_OFFSET	((__force fmode_t)0x2000)

/* File is opened with O_PATH; almost nothing can be done with it */
#define FMODE_PATH		((__force fmode_t)0x4000)

/* File needs atomic accesses to f_pos */
#define FMODE_ATOMIC_POS	((__force fmode_t)0x8000)
/* Write access to underlying fs */
#define FMODE_WRITER		((__force fmode_t)0x10000)
/* Has read method(s) */
#define FMODE_CAN_READ          ((__force fmode_t)0x20000)
/* Has write method(s) */
#define FMODE_CAN_WRITE         ((__force fmode_t)0x40000)

#define FMODE_OPENED		((__force fmode_t)0x80000)
#define FMODE_CREATED		((__force fmode_t)0x100000)

/* File is stream-like */
#define FMODE_STREAM		((__force fmode_t)0x200000)

/* File supports DIRECT IO */
#define	FMODE_CAN_ODIRECT	((__force fmode_t)0x400000)

#define	FMODE_NOREUSE		((__force fmode_t)0x800000)

/* File supports non-exclusive O_DIRECT writes from multiple threads */
#define FMODE_DIO_PARALLEL_WRITE	((__force fmode_t)0x1000000)

/* File is embedded in backing_file object */
#define FMODE_BACKING		((__force fmode_t)0x2000000)

/* File was opened by fanotify and shouldn't generate fanotify events */
#define FMODE_NONOTIFY		((__force fmode_t)0x4000000)

/* File is capable of returning -EAGAIN if I/O will block */
#define FMODE_NOWAIT		((__force fmode_t)0x8000000)

/* File represents mount that needs unmounting */
#define FMODE_NEED_UNMOUNT	((__force fmode_t)0x10000000)

/* File does not contribute to nr_files count */
#define FMODE_NOACCOUNT		((__force fmode_t)0x20000000)

/* File supports async buffered reads */
#define FMODE_BUF_RASYNC	((__force fmode_t)0x40000000)

/* File supports async nowait buffered writes */
#define FMODE_BUF_WASYNC	((__force fmode_t)0x80000000)

/*
 * Attribute flags.  These should be or-ed together to figure out what
 * has been changed!
 */
#define ATTR_MODE	(1 << 0)
#define ATTR_UID	(1 << 1)
#define ATTR_GID	(1 << 2)
#define ATTR_SIZE	(1 << 3)
#define ATTR_ATIME	(1 << 4)
#define ATTR_MTIME	(1 << 5)
#define ATTR_CTIME	(1 << 6)
#define ATTR_ATIME_SET	(1 << 7)
#define ATTR_MTIME_SET	(1 << 8)
#define ATTR_FORCE	(1 << 9) /* Not a change, but a change it */
#define ATTR_KILL_SUID	(1 << 11)
#define ATTR_KILL_SGID	(1 << 12)
#define ATTR_FILE	(1 << 13)
#define ATTR_KILL_PRIV	(1 << 14)
#define ATTR_OPEN	(1 << 15) /* Truncating from open(O_TRUNC) */
#define ATTR_TIMES_SET	(1 << 16)
#define ATTR_TOUCH	(1 << 17)

/*
 * Whiteout is represented by a char device.  The following constants define the
 * mode and device number to use.
 */
#define WHITEOUT_MODE 0
#define WHITEOUT_DEV 0

/*
 * This is the Inode Attributes structure, used for notify_change().  It
 * uses the above definitions as flags, to know which values have changed.
 * Also, in this manner, a Filesystem can look at only the values it cares
 * about.  Basically, these are the attributes that the VFS layer can
 * request to change from the FS layer.
 *
 * Derek Atkins <warlord@MIT.EDU> 94-10-20
 */
struct iattr {
	unsigned int	ia_valid;
	umode_t		ia_mode;
	/*
	 * The two anonymous unions wrap structures with the same member.
	 *
	 * Filesystems raising FS_ALLOW_IDMAP need to use ia_vfs{g,u}id which
	 * are a dedicated type requiring the filesystem to use the dedicated
	 * helpers. Other filesystem can continue to use ia_{g,u}id until they
	 * have been ported.
	 *
	 * They always contain the same value. In other words FS_ALLOW_IDMAP
	 * pass down the same value on idmapped mounts as they would on regular
	 * mounts.
	 */
	union {
		kuid_t		ia_uid;
		vfsuid_t	ia_vfsuid;
	};
	union {
		kgid_t		ia_gid;
		vfsgid_t	ia_vfsgid;
	};
	loff_t		ia_size;
	struct timespec64 ia_atime;
	struct timespec64 ia_mtime;
	struct timespec64 ia_ctime;

	/*
	 * Not an attribute, but an auxiliary info for filesystems wanting to
	 * implement an ftruncate() like method.  NOTE: filesystem should
	 * check for (ia_valid & ATTR_FILE), and not for (ia_file != NULL).
	 */
	struct file	*ia_file;
};

/*
 * Includes for diskquotas.
 */
#include <linux/quota.h>

/*
 * Maximum number of layers of fs stack.  Needs to be limited to
 * prevent kernel stack overflow
 */
#define FILESYSTEM_MAX_STACK_DEPTH 2

/** 
 * enum positive_aop_returns - aop return codes with specific semantics
 *
 * @AOP_WRITEPAGE_ACTIVATE: Informs the caller that page writeback has
 * 			    completed, that the page is still locked, and
 * 			    should be considered active.  The VM uses this hint
 * 			    to return the page to the active list -- it won't
 * 			    be a candidate for writeback again in the near
 * 			    future.  Other callers must be careful to unlock
 * 			    the page if they get this return.  Returned by
 * 			    writepage(); 
 *
 * @AOP_TRUNCATED_PAGE: The AOP method that was handed a locked page has
 *  			unlocked it and the page might have been truncated.
 *  			The caller should back up to acquiring a new page and
 *  			trying again.  The aop will be taking reasonable
 *  			precautions not to livelock.  If the caller held a page
 *  			reference, it should drop it before retrying.  Returned
 *  			by read_folio().
 *
 * address_space_operation functions return these large constants to indicate
 * special semantics to the caller.  These are much larger than the bytes in a
 * page to allow for functions that return the number of bytes operated on in a
 * given page.
 */

enum positive_aop_returns {
	AOP_WRITEPAGE_ACTIVATE	= 0x80000,
	AOP_TRUNCATED_PAGE	= 0x80001,
};

/*
 * oh the beauties of C type declarations.
 */
struct page;
struct address_space;
struct writeback_control;
struct readahead_control;

/*
 * Write life time hint values.
 * Stored in struct inode as u8.
 */
enum rw_hint {
	WRITE_LIFE_NOT_SET	= 0,
	WRITE_LIFE_NONE		= RWH_WRITE_LIFE_NONE,
	WRITE_LIFE_SHORT	= RWH_WRITE_LIFE_SHORT,
	WRITE_LIFE_MEDIUM	= RWH_WRITE_LIFE_MEDIUM,
	WRITE_LIFE_LONG		= RWH_WRITE_LIFE_LONG,
	WRITE_LIFE_EXTREME	= RWH_WRITE_LIFE_EXTREME,
};

/* Match RWF_* bits to IOCB bits */
#define IOCB_HIPRI		(__force int) RWF_HIPRI
#define IOCB_DSYNC		(__force int) RWF_DSYNC
#define IOCB_SYNC		(__force int) RWF_SYNC
#define IOCB_NOWAIT		(__force int) RWF_NOWAIT
#define IOCB_APPEND		(__force int) RWF_APPEND

/* non-RWF related bits - start at 16 */
#define IOCB_EVENTFD		(1 << 16)
#define IOCB_DIRECT		(1 << 17)
#define IOCB_WRITE		(1 << 18)
/* iocb->ki_waitq is valid */
#define IOCB_WAITQ		(1 << 19)
#define IOCB_NOIO		(1 << 20)
/* can use bio alloc cache */
#define IOCB_ALLOC_CACHE	(1 << 21)

/* for use in trace events */
#define TRACE_IOCB_STRINGS \
	{ IOCB_HIPRI,		"HIPRI" }, \
	{ IOCB_DSYNC,		"DSYNC" }, \
	{ IOCB_SYNC,		"SYNC" }, \
	{ IOCB_NOWAIT,		"NOWAIT" }, \
	{ IOCB_APPEND,		"APPEND" }, \
	{ IOCB_EVENTFD,		"EVENTFD"}, \
	{ IOCB_DIRECT,		"DIRECT" }, \
	{ IOCB_WRITE,		"WRITE" }, \
	{ IOCB_WAITQ,		"WAITQ" }, \
	{ IOCB_NOIO,		"NOIO" }, \
	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }

struct kiocb {
	struct file		*ki_filp;
	loff_t			ki_pos;
	void (*ki_complete)(struct kiocb *iocb, long ret);
	void			*private;
	int			ki_flags;
	u16			ki_ioprio; /* See linux/ioprio.h */
	struct wait_page_queue	*ki_waitq; /* for async buffered IO */
};

static inline bool is_sync_kiocb(struct kiocb *kiocb)
{
	return kiocb->ki_complete == NULL;
}

struct address_space_operations {
	int (*writepage)(struct page *page, struct writeback_control *wbc);
	int (*read_folio)(struct file *, struct folio *);

	/* Write back some dirty pages from this mapping. */
	int (*writepages)(struct address_space *, struct writeback_control *);

	/* Mark a folio dirty.  Return true if this dirtied it */
	bool (*dirty_folio)(struct address_space *, struct folio *);

	void (*readahead)(struct readahead_control *);

	int (*write_begin)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len,
				struct page **pagep, void **fsdata);
	int (*write_end)(struct file *, struct address_space *mapping,
				loff_t pos, unsigned len, unsigned copied,
				struct page *page, void *fsdata);

	/* Unfortunately this kludge is needed for FIBMAP. Don't use it */
	sector_t (*bmap)(struct address_space *, sector_t);
	void (*invalidate_folio) (struct folio *, size_t offset, size_t len);
	bool (*release_folio)(struct folio *, gfp_t);
	void (*free_folio)(struct folio *folio);
	ssize_t (*direct_IO)(struct kiocb *, struct iov_iter *iter);
	/*
	 * migrate the contents of a folio to the specified target. If
	 * migrate_mode is MIGRATE_ASYNC, it must not block.
	 */
	int (*migrate_folio)(struct address_space *, struct folio *dst,
			struct folio *src, enum migrate_mode);
	int (*launder_folio)(struct folio *);
	bool (*is_partially_uptodate) (struct folio *, size_t from,
			size_t count);
	void (*is_dirty_writeback) (struct folio *, bool *dirty, bool *wb);
	int (*error_remove_page)(struct address_space *, struct page *);

	/* swapfile support */
	int (*swap_activate)(struct swap_info_struct *sis, struct file *file,
				sector_t *span);
	void (*swap_deactivate)(struct file *file);
	int (*swap_rw)(struct kiocb *iocb, struct iov_iter *iter);
};

extern const struct address_space_operations empty_aops;

/**
 * struct address_space - Contents of a cacheable, mappable object.
 * @host: Owner, either the inode or the block_device.
 * @i_pages: Cached pages.
 * @invalidate_lock: Guards coherency between page cache contents and
 *   file offset->disk block mappings in the filesystem during invalidates.
 *   It is also used to block modification of page cache contents through
 *   memory mappings.
 * @gfp_mask: Memory allocation flags to use for allocating pages.
 * @i_mmap_writable: Number of VM_SHARED mappings.
 * @nr_thps: Number of THPs in the pagecache (non-shmem only).
 * @i_mmap: Tree of private and shared mappings.
 * @i_mmap_rwsem: Protects @i_mmap and @i_mmap_writable.
 * @nrpages: Number of page entries, protected by the i_pages lock.
 * @writeback_index: Writeback starts here.
 * @a_ops: Methods.
 * @flags: Error bits and flags (AS_*).
 * @wb_err: The most recent error which has occurred.
 * @private_lock: For use by the owner of the address_space.
 * @private_list: For use by the owner of the address_space.
 * @private_data: For use by the owner of the address_space.
 */
struct address_space {
	struct inode		*host;
	struct xarray		i_pages;
	struct rw_semaphore	invalidate_lock;
	gfp_t			gfp_mask;
	atomic_t		i_mmap_writable;
#ifdef CONFIG_READ_ONLY_THP_FOR_FS
	/* number of thp, only for non-shmem files */
	atomic_t		nr_thps;
#endif
	struct rb_root_cached	i_mmap;
	struct rw_semaphore	i_mmap_rwsem;
	unsigned long		nrpages;
	pgoff_t			writeback_index;
	const struct address_space_operations *a_ops;
	unsigned long		flags;
	errseq_t		wb_err;
	spinlock_t		private_lock;
	struct list_head	private_list;
	void			*private_data;
} __attribute__((aligned(sizeof(long)))) __randomize_layout;
	/*
	 * On most architectures that alignment is already the case; but
	 * must be enforced here for CRIS, to let the least significant bit
	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
	 */

/* XArray tags, for tagging dirty and writeback pages in the pagecache. */
#define PAGECACHE_TAG_DIRTY	XA_MARK_0
#define PAGECACHE_TAG_WRITEBACK	XA_MARK_1
#define PAGECACHE_TAG_TOWRITE	XA_MARK_2

/*
 * Returns true if any of the pages in the mapping are marked with the tag.
 */
static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag)
{
	return xa_marked(&mapping->i_pages, tag);
}

static inline void i_mmap_lock_write(struct address_space *mapping)
{
	down_write(&mapping->i_mmap_rwsem);
}

static inline int i_mmap_trylock_write(struct address_space *mapping)
{
	return down_write_trylock(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_unlock_write(struct address_space *mapping)
{
	up_write(&mapping->i_mmap_rwsem);
}

static inline int i_mmap_trylock_read(struct address_space *mapping)
{
	return down_read_trylock(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_lock_read(struct address_space *mapping)
{
	down_read(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_unlock_read(struct address_space *mapping)
{
	up_read(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_assert_locked(struct address_space *mapping)
{
	lockdep_assert_held(&mapping->i_mmap_rwsem);
}

static inline void i_mmap_assert_write_locked(struct address_space *mapping)
{
	lockdep_assert_held_write(&mapping->i_mmap_rwsem);
}

/*
 * Might pages of this file be mapped into userspace?
 */
static inline int mapping_mapped(struct address_space *mapping)
{
	return	!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root);
}

/*
 * Might pages of this file have been modified in userspace?
 * Note that i_mmap_writable counts all VM_SHARED vmas: do_mmap
 * marks vma as VM_SHARED if it is shared, and the file was opened for
 * writing i.e. vma may be mprotected writable even if now readonly.
 *
 * If i_mmap_writable is negative, no new writable mappings are allowed. You
 * can only deny writable mappings, if none exists right now.
 */
static inline int mapping_writably_mapped(struct address_space *mapping)
{
	return atomic_read(&mapping->i_mmap_writable) > 0;
}

static inline int mapping_map_writable(struct address_space *mapping)
{
	return atomic_inc_unless_negative(&mapping->i_mmap_writable) ?
		0 : -EPERM;
}

static inline void mapping_unmap_writable(struct address_space *mapping)
{
	atomic_dec(&mapping->i_mmap_writable);
}

static inline int mapping_deny_writable(struct address_space *mapping)
{
	return atomic_dec_unless_positive(&mapping->i_mmap_writable) ?
		0 : -EBUSY;
}

static inline void mapping_allow_writable(struct address_space *mapping)
{
	atomic_inc(&mapping->i_mmap_writable);
}

/*
 * Use sequence counter to get consistent i_size on 32-bit processors.
 */
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
#include <linux/seqlock.h>
#define __NEED_I_SIZE_ORDERED
#define i_size_ordered_init(inode) seqcount_init(&inode->i_size_seqcount)
#else
#define i_size_ordered_init(inode) do { } while (0)
#endif

struct posix_acl;
#define ACL_NOT_CACHED ((void *)(-1))
/*
 * ACL_DONT_CACHE is for stacked filesystems, that rely on underlying fs to
 * cache the ACL.  This also means that ->get_inode_acl() can be called in RCU
 * mode with the LOOKUP_RCU flag.
 */
#define ACL_DONT_CACHE ((void *)(-3))

static inline struct posix_acl *
uncached_acl_sentinel(struct task_struct *task)
{
	return (void *)task + 1;
}

static inline bool
is_uncached_acl(struct posix_acl *acl)
{
	return (long)acl & 1;
}

#define IOP_FASTPERM	0x0001
#define IOP_LOOKUP	0x0002
#define IOP_NOFOLLOW	0x0004
#define IOP_XATTR	0x0008
#define IOP_DEFAULT_READLINK	0x0010

struct fsnotify_mark_connector;

/*
 * Keep mostly read-only and often accessed (especially for
 * the RCU path lookup and 'stat' data) fields at the beginning
 * of the 'struct inode'
 */
struct inode {
	umode_t			i_mode;
	unsigned short		i_opflags;
	kuid_t			i_uid;
	kgid_t			i_gid;
	unsigned int		i_flags;

#ifdef CONFIG_FS_POSIX_ACL
	struct posix_acl	*i_acl;
	struct posix_acl	*i_default_acl;
#endif

	const struct inode_operations	*i_op;
	struct super_block	*i_sb;
	struct address_space	*i_mapping;

#ifdef CONFIG_SECURITY
	void			*i_security;
#endif

	/* Stat data, not accessed from path walking */
	unsigned long		i_ino;
	/*
	 * Filesystems may only read i_nlink directly.  They shall use the
	 * following functions for modification:
	 *
	 *    (set|clear|inc|drop)_nlink
	 *    inode_(inc|dec)_link_count
	 */
	union {
		const unsigned int i_nlink;
		unsigned int __i_nlink;
	};
	dev_t			i_rdev;
	loff_t			i_size;
	struct timespec64	i_atime;
	struct timespec64	i_mtime;
	struct timespec64	i_ctime;
	spinlock_t		i_lock;	/* i_blocks, i_bytes, maybe i_size */
	unsigned short          i_bytes;
	u8			i_blkbits;
	u8			i_write_hint;
	blkcnt_t		i_blocks;

#ifdef __NEED_I_SIZE_ORDERED
	seqcount_t		i_size_seqcount;
#endif

	/* Misc */
	unsigned long		i_state;
	struct rw_semaphore	i_rwsem;

	unsigned long		dirtied_when;	/* jiffies of first dirtying */
	unsigned long		dirtied_time_when;

	struct hlist_node	i_hash;
	struct list_head	i_io_list;	/* backing dev IO list */
#ifdef CONFIG_CGROUP_WRITEBACK
	struct bdi_writeback	*i_wb;		/* the associated cgroup wb */

	/* foreign inode detection, see wbc_detach_inode() */
	int			i_wb_frn_winner;
	u16			i_wb_frn_avg_time;
	u16			i_wb_frn_history;
#endif
	struct list_head	i_lru;		/* inode LRU list */
	struct list_head	i_sb_list;
	struct list_head	i_wb_list;	/* backing dev writeback list */
	union {
		struct hlist_head	i_dentry;
		struct rcu_head		i_rcu;
	};
	atomic64_t		i_version;
	atomic64_t		i_sequence; /* see futex */
	atomic_t		i_count;
	atomic_t		i_dio_count;
	atomic_t		i_writecount;
#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
	atomic_t		i_readcount; /* struct files open RO */
#endif
	union {
		const struct file_operations	*i_fop;	/* former ->i_op->default_file_ops */
		void (*free_inode)(struct inode *);
	};
	struct file_lock_context	*i_flctx;
	struct address_space	i_data;
	struct list_head	i_devices;
	union {
		struct pipe_inode_info	*i_pipe;
		struct cdev		*i_cdev;
		char			*i_link;
		unsigned		i_dir_seq;
	};

	__u32			i_generation;

#ifdef CONFIG_FSNOTIFY
	__u32			i_fsnotify_mask; /* all events this inode cares about */
	struct fsnotify_mark_connector __rcu	*i_fsnotify_marks;
#endif

#ifdef CONFIG_FS_ENCRYPTION
	struct fscrypt_info	*i_crypt_info;
#endif

#ifdef CONFIG_FS_VERITY
	struct fsverity_info	*i_verity_info;
#endif

	void			*i_private; /* fs or device private pointer */
} __randomize_layout;

struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode);

static inline unsigned int i_blocksize(const struct inode *node)
{
	return (1 << node->i_blkbits);
}

static inline int inode_unhashed(struct inode *inode)
{
	return hlist_unhashed(&inode->i_hash);
}

/*
 * __mark_inode_dirty expects inodes to be hashed.  Since we don't
 * want special inodes in the fileset inode space, we make them
 * appear hashed, but do not put on any lists.  hlist_del()
 * will work fine and require no locking.
 */
static inline void inode_fake_hash(struct inode *inode)
{
	hlist_add_fake(&inode->i_hash);
}

/*
 * inode->i_mutex nesting subclasses for the lock validator:
 *
 * 0: the object of the current VFS operation
 * 1: parent
 * 2: child/target
 * 3: xattr
 * 4: second non-directory
 * 5: second parent (when locking independent directories in rename)
 *
 * I_MUTEX_NONDIR2 is for certain operations (such as rename) which lock two
 * non-directories at once.
 *
 * The locking order between these classes is
 * parent[2] -> child -> grandchild -> normal -> xattr -> second non-directory
 */
enum inode_i_mutex_lock_class
{
	I_MUTEX_NORMAL,
	I_MUTEX_PARENT,
	I_MUTEX_CHILD,
	I_MUTEX_XATTR,
	I_MUTEX_NONDIR2,
	I_MUTEX_PARENT2,
};

static inline void inode_lock(struct inode *inode)
{
	down_write(&inode->i_rwsem);
}

static inline void inode_unlock(struct inode *inode)
{
	up_write(&inode->i_rwsem);
}

static inline void inode_lock_shared(struct inode *inode)
{
	down_read(&inode->i_rwsem);
}

static inline void inode_unlock_shared(struct inode *inode)
{
	up_read(&inode->i_rwsem);
}

static inline int inode_trylock(struct inode *inode)
{
	return down_write_trylock(&inode->i_rwsem);
}

static inline int inode_trylock_shared(struct inode *inode)
{
	return down_read_trylock(&inode->i_rwsem);
}

static inline int inode_is_locked(struct inode *inode)
{
	return rwsem_is_locked(&inode->i_rwsem);
}

static inline void inode_lock_nested(struct inode *inode, unsigned subclass)
{
	down_write_nested(&inode->i_rwsem, subclass);
}

static inline void inode_lock_shared_nested(struct inode *inode, unsigned subclass)
{
	down_read_nested(&inode->i_rwsem, subclass);
}

static inline void filemap_invalidate_lock(struct address_space *mapping)
{
	down_write(&mapping->invalidate_lock);
}

static inline void filemap_invalidate_unlock(struct address_space *mapping)
{
	up_write(&mapping->invalidate_lock);
}

static inline void filemap_invalidate_lock_shared(struct address_space *mapping)
{
	down_read(&mapping->invalidate_lock);
}

static inline int filemap_invalidate_trylock_shared(
					struct address_space *mapping)
{
	return down_read_trylock(&mapping->invalidate_lock);
}

static inline void filemap_invalidate_unlock_shared(
					struct address_space *mapping)
{
	up_read(&mapping->invalidate_lock);
}

void lock_two_nondirectories(struct inode *, struct inode*);
void unlock_two_nondirectories(struct inode *, struct inode*);

void filemap_invalidate_lock_two(struct address_space *mapping1,
				 struct address_space *mapping2);
void filemap_invalidate_unlock_two(struct address_space *mapping1,
				   struct address_space *mapping2);


/*
 * NOTE: in a 32bit arch with a preemptable kernel and
 * an UP compile the i_size_read/write must be atomic
 * with respect to the local cpu (unlike with preempt disabled),
 * but they don't need to be atomic with respect to other cpus like in
 * true SMP (so they need either to either locally disable irq around
 * the read or for example on x86 they can be still implemented as a
 * cmpxchg8b without the need of the lock prefix). For SMP compiles
 * and 64bit archs it makes no difference if preempt is enabled or not.
 */
static inline loff_t i_size_read(const struct inode *inode)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	loff_t i_size;
	unsigned int seq;

	do {
		seq = read_seqcount_begin(&inode->i_size_seqcount);
		i_size = inode->i_size;
	} while (read_seqcount_retry(&inode->i_size_seqcount, seq));
	return i_size;
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
	loff_t i_size;

	preempt_disable();
	i_size = inode->i_size;
	preempt_enable();
	return i_size;
#else
	return inode->i_size;
#endif
}

/*
 * NOTE: unlike i_size_read(), i_size_write() does need locking around it
 * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
 * can be lost, resulting in subsequent i_size_read() calls spinning forever.
 */
static inline void i_size_write(struct inode *inode, loff_t i_size)
{
#if BITS_PER_LONG==32 && defined(CONFIG_SMP)
	preempt_disable();
	write_seqcount_begin(&inode->i_size_seqcount);
	inode->i_size = i_size;
	write_seqcount_end(&inode->i_size_seqcount);
	preempt_enable();
#elif BITS_PER_LONG==32 && defined(CONFIG_PREEMPTION)
	preempt_disable();
	inode->i_size = i_size;
	preempt_enable();
#else
	inode->i_size = i_size;
#endif
}

static inline unsigned iminor(const struct inode *inode)
{
	return MINOR(inode->i_rdev);
}

static inline unsigned imajor(const struct inode *inode)
{
	return MAJOR(inode->i_rdev);
}

struct fown_struct {
	rwlock_t lock;          /* protects pid, uid, euid fields */
	struct pid *pid;	/* pid or -pgrp where SIGIO should be sent */
	enum pid_type pid_type;	/* Kind of process group SIGIO should be sent to */
	kuid_t uid, euid;	/* uid/euid of process setting the owner */
	int signum;		/* posix.1b rt signal to be delivered on IO */
};

/**
 * struct file_ra_state - Track a file's readahead state.
 * @start: Where the most recent readahead started.
 * @size: Number of pages read in the most recent readahead.
 * @async_size: Numer of pages that were/are not needed immediately
 *      and so were/are genuinely "ahead".  Start next readahead when
 *      the first of these pages is accessed.
 * @ra_pages: Maximum size of a readahead request, copied from the bdi.
 * @mmap_miss: How many mmap accesses missed in the page cache.
 * @prev_pos: The last byte in the most recent read request.
 *
 * When this structure is passed to ->readahead(), the "most recent"
 * readahead means the current readahead.
 */
struct file_ra_state {
	pgoff_t start;
	unsigned int size;
	unsigned int async_size;
	unsigned int ra_pages;
	unsigned int mmap_miss;
	loff_t prev_pos;
};

/*
 * Check if @index falls in the readahead windows.
 */
static inline int ra_has_index(struct file_ra_state *ra, pgoff_t index)
{
	return (index >= ra->start &&
		index <  ra->start + ra->size);
}

/*
 * f_{lock,count,pos_lock} members can be highly contended and share
 * the same cacheline. f_{lock,mode} are very frequently used together
 * and so share the same cacheline as well. The read-mostly
 * f_{path,inode,op} are kept on a separate cacheline.
 */
struct file {
	union {
		struct llist_node	f_llist;
		struct rcu_head 	f_rcuhead;
		unsigned int 		f_iocb_flags;
	};

	/*
	 * Protects f_ep, f_flags.
	 * Must not be taken from IRQ context.
	 */
	spinlock_t		f_lock;
	fmode_t			f_mode;
	atomic_long_t		f_count;
	struct mutex		f_pos_lock;
	loff_t			f_pos;
	unsigned int		f_flags;
	struct fown_struct	f_owner;
	const struct cred	*f_cred;
	struct file_ra_state	f_ra;
	struct path		f_path;
	struct inode		*f_inode;	/* cached value */
	const struct file_operations	*f_op;

	u64			f_version;
#ifdef CONFIG_SECURITY
	void			*f_security;
#endif
	/* needed for tty driver, and maybe others */
	void			*private_data;

#ifdef CONFIG_EPOLL
	/* Used by fs/eventpoll.c to link all the hooks to this file */
	struct hlist_head	*f_ep;
#endif /* #ifdef CONFIG_EPOLL */
	struct address_space	*f_mapping;
	errseq_t		f_wb_err;
	errseq_t		f_sb_err; /* for syncfs */
} __randomize_layout
  __attribute__((aligned(4)));	/* lest something weird decides that 2 is OK */

struct file_handle {
	__u32 handle_bytes;
	int handle_type;
	/* file identifier */
	unsigned char f_handle[];
};

static inline struct file *get_file(struct file *f)
{
	atomic_long_inc(&f->f_count);
	return f;
}
#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count)
#define file_count(x)	atomic_long_read(&(x)->f_count)

#define	MAX_NON_LFS	((1UL<<31) - 1)

/* Page cache limit. The filesystems should put that into their s_maxbytes 
   limits, otherwise bad things can happen in VM. */ 
#if BITS_PER_LONG==32
#define MAX_LFS_FILESIZE	((loff_t)ULONG_MAX << PAGE_SHIFT)
#elif BITS_PER_LONG==64
#define MAX_LFS_FILESIZE 	((loff_t)LLONG_MAX)
#endif

/* legacy typedef, should eventually be removed */
typedef void *fl_owner_t;

struct file_lock;

/* The following constant reflects the upper bound of the file/locking space */
#ifndef OFFSET_MAX
#define OFFSET_MAX	type_max(loff_t)
#define OFFT_OFFSET_MAX	type_max(off_t)
#endif

extern void send_sigio(struct fown_struct *fown, int fd, int band);

static inline struct inode *file_inode(const struct file *f)
{
	return f->f_inode;
}

static inline struct dentry *file_dentry(const struct file *file)
{
	return d_real(file->f_path.dentry, file_inode(file));
}

struct fasync_struct {
	rwlock_t		fa_lock;
	int			magic;
	int			fa_fd;
	struct fasync_struct	*fa_next; /* singly linked list */
	struct file		*fa_file;
	struct rcu_head		fa_rcu;
};

#define FASYNC_MAGIC 0x4601

/* SMP safe fasync helpers: */
extern int fasync_helper(int, struct file *, int, struct fasync_struct **);
extern struct fasync_struct *fasync_insert_entry(int, struct file *, struct fasync_struct **, struct fasync_struct *);
extern int fasync_remove_entry(struct file *, struct fasync_struct **);
extern struct fasync_struct *fasync_alloc(void);
extern void fasync_free(struct fasync_struct *);

/* can be called from interrupts */
extern void kill_fasync(struct fasync_struct **, int, int);

extern void __f_setown(struct file *filp, struct pid *, enum pid_type, int force);
extern int f_setown(struct file *filp, unsigned long arg, int force);
extern void f_delown(struct file *filp);
extern pid_t f_getown(struct file *filp);
extern int send_sigurg(struct fown_struct *fown);

/*
 * sb->s_flags.  Note that these mirror the equivalent MS_* flags where
 * represented in both.
 */
#define SB_RDONLY       BIT(0)	/* Mount read-only */
#define SB_NOSUID       BIT(1)	/* Ignore suid and sgid bits */
#define SB_NODEV        BIT(2)	/* Disallow access to device special files */
#define SB_NOEXEC       BIT(3)	/* Disallow program execution */
#define SB_SYNCHRONOUS  BIT(4)	/* Writes are synced at once */
#define SB_MANDLOCK     BIT(6)	/* Allow mandatory locks on an FS */
#define SB_DIRSYNC      BIT(7)	/* Directory modifications are synchronous */
#define SB_NOATIME      BIT(10)	/* Do not update access times. */
#define SB_NODIRATIME   BIT(11)	/* Do not update directory access times */
#define SB_SILENT       BIT(15)
#define SB_POSIXACL     BIT(16)	/* VFS does not apply the umask */
#define SB_INLINECRYPT  BIT(17)	/* Use blk-crypto for encrypted files */
#define SB_KERNMOUNT    BIT(22)	/* this is a kern_mount call */
#define SB_I_VERSION    BIT(23)	/* Update inode I_version field */
#define SB_LAZYTIME     BIT(25)	/* Update the on-disk [acm]times lazily */

/* These sb flags are internal to the kernel */
#define SB_SUBMOUNT     BIT(26)
#define SB_FORCE        BIT(27)
#define SB_NOSEC        BIT(28)
#define SB_BORN         BIT(29)
#define SB_ACTIVE       BIT(30)
#define SB_NOUSER       BIT(31)

/* These flags relate to encoding and casefolding */
#define SB_ENC_STRICT_MODE_FL	(1 << 0)

#define sb_has_strict_encoding(sb) \
	(sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL)

/*
 *	Umount options
 */

#define MNT_FORCE	0x00000001	/* Attempt to forcibily umount */
#define MNT_DETACH	0x00000002	/* Just detach from the tree */
#define MNT_EXPIRE	0x00000004	/* Mark for expiry */
#define UMOUNT_NOFOLLOW	0x00000008	/* Don't follow symlink on umount */
#define UMOUNT_UNUSED	0x80000000	/* Flag guaranteed to be unused */

/* sb->s_iflags */
#define SB_I_CGROUPWB	0x00000001	/* cgroup-aware writeback enabled */
#define SB_I_NOEXEC	0x00000002	/* Ignore executables on this fs */
#define SB_I_NODEV	0x00000004	/* Ignore devices on this fs */
#define SB_I_STABLE_WRITES 0x00000008	/* don't modify blks until WB is done */

/* sb->s_iflags to limit user namespace mounts */
#define SB_I_USERNS_VISIBLE		0x00000010 /* fstype already mounted */
#define SB_I_IMA_UNVERIFIABLE_SIGNATURE	0x00000020
#define SB_I_UNTRUSTED_MOUNTER		0x00000040

#define SB_I_SKIP_SYNC	0x00000100	/* Skip superblock at global sync */
#define SB_I_PERSB_BDI	0x00000200	/* has a per-sb bdi */
#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */
#define SB_I_RETIRED	0x00000800	/* superblock shouldn't be reused */

/* Possible states of 'frozen' field */
enum {
	SB_UNFROZEN = 0,		/* FS is unfrozen */
	SB_FREEZE_WRITE	= 1,		/* Writes, dir ops, ioctls frozen */
	SB_FREEZE_PAGEFAULT = 2,	/* Page faults stopped as well */
	SB_FREEZE_FS = 3,		/* For internal FS use (e.g. to stop
					 * internal threads if needed) */
	SB_FREEZE_COMPLETE = 4,		/* ->freeze_fs finished successfully */
};

#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1)

struct sb_writers {
	int				frozen;		/* Is sb frozen? */
	struct percpu_rw_semaphore	rw_sem[SB_FREEZE_LEVELS];
};

struct super_block {
	struct list_head	s_list;		/* Keep this first */
	dev_t			s_dev;		/* search index; _not_ kdev_t */
	unsigned char		s_blocksize_bits;
	unsigned long		s_blocksize;
	loff_t			s_maxbytes;	/* Max file size */
	struct file_system_type	*s_type;
	const struct super_operations	*s_op;
	const struct dquot_operations	*dq_op;
	const struct quotactl_ops	*s_qcop;
	const struct export_operations *s_export_op;
	unsigned long		s_flags;
	unsigned long		s_iflags;	/* internal SB_I_* flags */
	unsigned long		s_magic;
	struct dentry		*s_root;
	struct rw_semaphore	s_umount;
	int			s_count;
	atomic_t		s_active;
#ifdef CONFIG_SECURITY
	void                    *s_security;
#endif
	const struct xattr_handler **s_xattr;
#ifdef CONFIG_FS_ENCRYPTION
	const struct fscrypt_operations	*s_cop;
	struct fscrypt_keyring	*s_master_keys; /* master crypto keys in use */
#endif
#ifdef CONFIG_FS_VERITY
	const struct fsverity_operations *s_vop;
#endif
#if IS_ENABLED(CONFIG_UNICODE)
	struct unicode_map *s_encoding;
	__u16 s_encoding_flags;
#endif
	struct hlist_bl_head	s_roots;	/* alternate root dentries for NFS */
	struct list_head	s_mounts;	/* list of mounts; _not_ for fs use */
	struct block_device	*s_bdev;
	struct backing_dev_info *s_bdi;
	struct mtd_info		*s_mtd;
	struct hlist_node	s_instances;
	unsigned int		s_quota_types;	/* Bitmask of supported quota types */
	struct quota_info	s_dquot;	/* Diskquota specific options */

	struct sb_writers	s_writers;

	/*
	 * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and
	 * s_fsnotify_marks together for cache efficiency. They are frequently
	 * accessed and rarely modified.
	 */
	void			*s_fs_info;	/* Filesystem private info */

	/* Granularity of c/m/atime in ns (cannot be worse than a second) */
	u32			s_time_gran;
	/* Time limits for c/m/atime in seconds */
	time64_t		   s_time_min;
	time64_t		   s_time_max;
#ifdef CONFIG_FSNOTIFY
	__u32			s_fsnotify_mask;
	struct fsnotify_mark_connector __rcu	*s_fsnotify_marks;
#endif

	char			s_id[32];	/* Informational name */
	uuid_t			s_uuid;		/* UUID */

	unsigned int		s_max_links;

	/*
	 * The next field is for VFS *only*. No filesystems have any business
	 * even looking at it. You had been warned.
	 */
	struct mutex s_vfs_rename_mutex;	/* Kludge */

	/*
	 * Filesystem subtype.  If non-empty the filesystem type field
	 * in /proc/mounts will be "type.subtype"
	 */
	const char *s_subtype;

	const struct dentry_operations *s_d_op; /* default d_op for dentries */

	struct shrinker s_shrink;	/* per-sb shrinker handle */

	/* Number of inodes with nlink == 0 but still referenced */
	atomic_long_t s_remove_count;

	/*
	 * Number of inode/mount/sb objects that are being watched, note that
	 * inodes objects are currently double-accounted.
	 */
	atomic_long_t s_fsnotify_connectors;

	/* Read-only state of the superblock is being changed */
	int s_readonly_remount;

	/* per-sb errseq_t for reporting writeback errors via syncfs */
	errseq_t s_wb_err;

	/* AIO completions deferred from interrupt context */
	struct workqueue_struct *s_dio_done_wq;
	struct hlist_head s_pins;

	/*
	 * Owning user namespace and default context in which to
	 * interpret filesystem uids, gids, quotas, device nodes,
	 * xattrs and security labels.
	 */
	struct user_namespace *s_user_ns;

	/*
	 * The list_lru structure is essentially just a pointer to a table
	 * of per-node lru lists, each of which has its own spinlock.
	 * There is no need to put them into separate cachelines.
	 */
	struct list_lru		s_dentry_lru;
	struct list_lru		s_inode_lru;
	struct rcu_head		rcu;
	struct work_struct	destroy_work;

	struct mutex		s_sync_lock;	/* sync serialisation lock */

	/*
	 * Indicates how deep in a filesystem stack this SB is
	 */
	int s_stack_depth;

	/* s_inode_list_lock protects s_inodes */
	spinlock_t		s_inode_list_lock ____cacheline_aligned_in_smp;
	struct list_head	s_inodes;	/* all inodes */

	spinlock_t		s_inode_wblist_lock;
	struct list_head	s_inodes_wb;	/* writeback inodes */
} __randomize_layout;

static inline struct user_namespace *i_user_ns(const struct inode *inode)
{
	return inode->i_sb->s_user_ns;
}

/* Helper functions so that in most cases filesystems will
 * not need to deal directly with kuid_t and kgid_t and can
 * instead deal with the raw numeric values that are stored
 * in the filesystem.
 */
static inline uid_t i_uid_read(const struct inode *inode)
{
	return from_kuid(i_user_ns(inode), inode->i_uid);
}

static inline gid_t i_gid_read(const struct inode *inode)
{
	return from_kgid(i_user_ns(inode), inode->i_gid);
}

static inline void i_uid_write(struct inode *inode, uid_t uid)
{
	inode->i_uid = make_kuid(i_user_ns(inode), uid);
}

static inline void i_gid_write(struct inode *inode, gid_t gid)
{
	inode->i_gid = make_kgid(i_user_ns(inode), gid);
}

/**
 * i_uid_into_vfsuid - map an inode's i_uid down according to an idmapping
 * @idmap: idmap of the mount the inode was found from
 * @inode: inode to map
 *
 * Return: whe inode's i_uid mapped down according to @idmap.
 * If the inode's i_uid has no mapping INVALID_VFSUID is returned.
 */
static inline vfsuid_t i_uid_into_vfsuid(struct mnt_idmap *idmap,
					 const struct inode *inode)
{
	return make_vfsuid(idmap, i_user_ns(inode), inode->i_uid);
}

/**
 * i_uid_needs_update - check whether inode's i_uid needs to be updated
 * @idmap: idmap of the mount the inode was found from
 * @attr: the new attributes of @inode
 * @inode: the inode to update
 *
 * Check whether the $inode's i_uid field needs to be updated taking idmapped
 * mounts into account if the filesystem supports it.
 *
 * Return: true if @inode's i_uid field needs to be updated, false if not.
 */
static inline bool i_uid_needs_update(struct mnt_idmap *idmap,
				      const struct iattr *attr,
				      const struct inode *inode)
{
	return ((attr->ia_valid & ATTR_UID) &&
		!vfsuid_eq(attr->ia_vfsuid,
			   i_uid_into_vfsuid(idmap, inode)));
}

/**
 * i_uid_update - update @inode's i_uid field
 * @idmap: idmap of the mount the inode was found from
 * @attr: the new attributes of @inode
 * @inode: the inode to update
 *
 * Safely update @inode's i_uid field translating the vfsuid of any idmapped
 * mount into the filesystem kuid.
 */
static inline void i_uid_update(struct mnt_idmap *idmap,
				const struct iattr *attr,
				struct inode *inode)
{
	if (attr->ia_valid & ATTR_UID)
		inode->i_uid = from_vfsuid(idmap, i_user_ns(inode),
					   attr->ia_vfsuid);
}

/**
 * i_gid_into_vfsgid - map an inode's i_gid down according to an idmapping
 * @idmap: idmap of the mount the inode was found from
 * @inode: inode to map
 *
 * Return: the inode's i_gid mapped down according to @idmap.
 * If the inode's i_gid has no mapping INVALID_VFSGID is returned.
 */
static inline vfsgid_t i_gid_into_vfsgid(struct mnt_idmap *idmap,
					 const struct inode *inode)
{
	return make_vfsgid(idmap, i_user_ns(inode), inode->i_gid);
}

/**
 * i_gid_needs_update - check whether inode's i_gid needs to be updated
 * @idmap: idmap of the mount the inode was found from
 * @attr: the new attributes of @inode
 * @inode: the inode to update
 *
 * Check whether the $inode's i_gid field needs to be updated taking idmapped
 * mounts into account if the filesystem supports it.
 *
 * Return: true if @inode's i_gid field needs to be updated, false if not.
 */
static inline bool i_gid_needs_update(struct mnt_idmap *idmap,
				      const struct iattr *attr,
				      const struct inode *inode)
{
	return ((attr->ia_valid & ATTR_GID) &&
		!vfsgid_eq(attr->ia_vfsgid,
			   i_gid_into_vfsgid(idmap, inode)));
}

/**
 * i_gid_update - update @inode's i_gid field
 * @idmap: idmap of the mount the inode was found from
 * @attr: the new attributes of @inode
 * @inode: the inode to update
 *
 * Safely update @inode's i_gid field translating the vfsgid of any idmapped
 * mount into the filesystem kgid.
 */
static inline void i_gid_update(struct mnt_idmap *idmap,
				const struct iattr *attr,
				struct inode *inode)
{
	if (attr->ia_valid & ATTR_GID)
		inode->i_gid = from_vfsgid(idmap, i_user_ns(inode),
					   attr->ia_vfsgid);
}

/**
 * inode_fsuid_set - initialize inode's i_uid field with callers fsuid
 * @inode: inode to initialize
 * @idmap: idmap of the mount the inode was found from
 *
 * Initialize the i_uid field of @inode. If the inode was found/created via
 * an idmapped mount map the caller's fsuid according to @idmap.
 */
static inline void inode_fsuid_set(struct inode *inode,
				   struct mnt_idmap *idmap)
{
	inode->i_uid = mapped_fsuid(idmap, i_user_ns(inode));
}

/**
 * inode_fsgid_set - initialize inode's i_gid field with callers fsgid
 * @inode: inode to initialize
 * @idmap: idmap of the mount the inode was found from
 *
 * Initialize the i_gid field of @inode. If the inode was found/created via
 * an idmapped mount map the caller's fsgid according to @idmap.
 */
static inline void inode_fsgid_set(struct inode *inode,
				   struct mnt_idmap *idmap)
{
	inode->i_gid = mapped_fsgid(idmap, i_user_ns(inode));
}

/**
 * fsuidgid_has_mapping() - check whether caller's fsuid/fsgid is mapped
 * @sb: the superblock we want a mapping in
 * @idmap: idmap of the relevant mount
 *
 * Check whether the caller's fsuid and fsgid have a valid mapping in the
 * s_user_ns of the superblock @sb. If the caller is on an idmapped mount map
 * the caller's fsuid and fsgid according to the @idmap first.
 *
 * Return: true if fsuid and fsgid is mapped, false if not.
 */
static inline bool fsuidgid_has_mapping(struct super_block *sb,
					struct mnt_idmap *idmap)
{
	struct user_namespace *fs_userns = sb->s_user_ns;
	kuid_t kuid;
	kgid_t kgid;

	kuid = mapped_fsuid(idmap, fs_userns);
	if (!uid_valid(kuid))
		return false;
	kgid = mapped_fsgid(idmap, fs_userns);
	if (!gid_valid(kgid))
		return false;
	return kuid_has_mapping(fs_userns, kuid) &&
	       kgid_has_mapping(fs_userns, kgid);
}

extern struct timespec64 current_time(struct inode *inode);

/*
 * Snapshotting support.
 */

/*
 * These are internal functions, please use sb_start_{write,pagefault,intwrite}
 * instead.
 */
static inline void __sb_end_write(struct super_block *sb, int level)
{
	percpu_up_read(sb->s_writers.rw_sem + level-1);
}

static inline void __sb_start_write(struct super_block *sb, int level)
{
	percpu_down_read(sb->s_writers.rw_sem + level - 1);
}

static inline bool __sb_start_write_trylock(struct super_block *sb, int level)
{
	return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1);
}

#define __sb_writers_acquired(sb, lev)	\
	percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)
#define __sb_writers_release(sb, lev)	\
	percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_)

static inline bool sb_write_started(const struct super_block *sb)
{
	return lockdep_is_held_type(sb->s_writers.rw_sem + SB_FREEZE_WRITE - 1, 1);
}

/**
 * sb_end_write - drop write access to a superblock
 * @sb: the super we wrote to
 *
 * Decrement number of writers to the filesystem. Wake up possible waiters
 * wanting to freeze the filesystem.
 */
static inline void sb_end_write(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_WRITE);
}

/**
 * sb_end_pagefault - drop write access to a superblock from a page fault
 * @sb: the super we wrote to
 *
 * Decrement number of processes handling write page fault to the filesystem.
 * Wake up possible waiters wanting to freeze the filesystem.
 */
static inline void sb_end_pagefault(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_PAGEFAULT);
}

/**
 * sb_end_intwrite - drop write access to a superblock for internal fs purposes
 * @sb: the super we wrote to
 *
 * Decrement fs-internal number of writers to the filesystem.  Wake up possible
 * waiters wanting to freeze the filesystem.
 */
static inline void sb_end_intwrite(struct super_block *sb)
{
	__sb_end_write(sb, SB_FREEZE_FS);
}

/**
 * sb_start_write - get write access to a superblock
 * @sb: the super we write to
 *
 * When a process wants to write data or metadata to a file system (i.e. dirty
 * a page or an inode), it should embed the operation in a sb_start_write() -
 * sb_end_write() pair to get exclusion against file system freezing. This
 * function increments number of writers preventing freezing. If the file
 * system is already frozen, the function waits until the file system is
 * thawed.
 *
 * Since freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. Generally,
 * freeze protection should be the outermost lock. In particular, we have:
 *
 * sb_start_write
 *   -> i_mutex			(write path, truncate, directory ops, ...)
 *   -> s_umount		(freeze_super, thaw_super)
 */
static inline void sb_start_write(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_WRITE);
}

static inline bool sb_start_write_trylock(struct super_block *sb)
{
	return __sb_start_write_trylock(sb, SB_FREEZE_WRITE);
}

/**
 * sb_start_pagefault - get write access to a superblock from a page fault
 * @sb: the super we write to
 *
 * When a process starts handling write page fault, it should embed the
 * operation into sb_start_pagefault() - sb_end_pagefault() pair to get
 * exclusion against file system freezing. This is needed since the page fault
 * is going to dirty a page. This function increments number of running page
 * faults preventing freezing. If the file system is already frozen, the
 * function waits until the file system is thawed.
 *
 * Since page fault freeze protection behaves as a lock, users have to preserve
 * ordering of freeze protection and other filesystem locks. It is advised to
 * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault
 * handling code implies lock dependency:
 *
 * mmap_lock
 *   -> sb_start_pagefault
 */
static inline void sb_start_pagefault(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_PAGEFAULT);
}

/**
 * sb_start_intwrite - get write access to a superblock for internal fs purposes
 * @sb: the super we write to
 *
 * This is the third level of protection against filesystem freezing. It is
 * free for use by a filesystem. The only requirement is that it must rank
 * below sb_start_pagefault.
 *
 * For example filesystem can call sb_start_intwrite() when starting a
 * transaction which somewhat eases handling of freezing for internal sources
 * of filesystem changes (internal fs threads, discarding preallocation on file
 * close, etc.).
 */
static inline void sb_start_intwrite(struct super_block *sb)
{
	__sb_start_write(sb, SB_FREEZE_FS);
}

static inline bool sb_start_intwrite_trylock(struct super_block *sb)
{
	return __sb_start_write_trylock(sb, SB_FREEZE_FS);
}

bool inode_owner_or_capable(struct mnt_idmap *idmap,
			    const struct inode *inode);

/*
 * VFS helper functions..
 */
int vfs_create(struct mnt_idmap *, struct inode *,
	       struct dentry *, umode_t, bool);
int vfs_mkdir(struct mnt_idmap *, struct inode *,
	      struct dentry *, umode_t);
int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *,
              umode_t, dev_t);
int vfs_symlink(struct mnt_idmap *, struct inode *,
		struct dentry *, const char *);
int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *,
	     struct dentry *, struct inode **);
int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *);
int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *,
	       struct inode **);

/**
 * struct renamedata - contains all information required for renaming
 * @old_mnt_idmap:     idmap of the old mount the inode was found from
 * @old_dir:           parent of source
 * @old_dentry:                source
 * @new_mnt_idmap:     idmap of the new mount the inode was found from
 * @new_dir:           parent of destination
 * @new_dentry:                destination
 * @delegated_inode:   returns an inode needing a delegation break
 * @flags:             rename flags
 */
struct renamedata {
	struct mnt_idmap *old_mnt_idmap;
	struct inode *old_dir;
	struct dentry *old_dentry;
	struct mnt_idmap *new_mnt_idmap;
	struct inode *new_dir;
	struct dentry *new_dentry;
	struct inode **delegated_inode;
	unsigned int flags;
} __randomize_layout;

int vfs_rename(struct renamedata *);

static inline int vfs_whiteout(struct mnt_idmap *idmap,
			       struct inode *dir, struct dentry *dentry)
{
	return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE,
			 WHITEOUT_DEV);
}

struct file *kernel_tmpfile_open(struct mnt_idmap *idmap,
				 const struct path *parentpath,
				 umode_t mode, int open_flag,
				 const struct cred *cred);
struct file *kernel_file_open(const struct path *path, int flags,
			      struct inode *inode, const struct cred *cred);

int vfs_mkobj(struct dentry *, umode_t,
		int (*f)(struct dentry *, umode_t, void *),
		void *);

int vfs_fchown(struct file *file, uid_t user, gid_t group);
int vfs_fchmod(struct file *file, umode_t mode);
int vfs_utimes(const struct path *path, struct timespec64 *times);

extern long vfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);

#ifdef CONFIG_COMPAT
extern long compat_ptr_ioctl(struct file *file, unsigned int cmd,
					unsigned long arg);
#else
#define compat_ptr_ioctl NULL
#endif

/*
 * VFS file helper functions.
 */
void inode_init_owner(struct mnt_idmap *idmap, struct inode *inode,
		      const struct inode *dir, umode_t mode);
extern bool may_open_dev(const struct path *path);
umode_t mode_strip_sgid(struct mnt_idmap *idmap,
			const struct inode *dir, umode_t mode);

/*
 * This is the "filldir" function type, used by readdir() to let
 * the kernel specify what kind of dirent layout it wants to have.
 * This allows the kernel to read directories into kernel space or
 * to have different dirent layouts depending on the binary type.
 * Return 'true' to keep going and 'false' if there are no more entries.
 */
struct dir_context;
typedef bool (*filldir_t)(struct dir_context *, const char *, int, loff_t, u64,
			 unsigned);

struct dir_context {
	filldir_t actor;
	loff_t pos;
};

/*
 * These flags let !MMU mmap() govern direct device mapping vs immediate
 * copying more easily for MAP_PRIVATE, especially for ROM filesystems.
 *
 * NOMMU_MAP_COPY:	Copy can be mapped (MAP_PRIVATE)
 * NOMMU_MAP_DIRECT:	Can be mapped directly (MAP_SHARED)
 * NOMMU_MAP_READ:	Can be mapped for reading
 * NOMMU_MAP_WRITE:	Can be mapped for writing
 * NOMMU_MAP_EXEC:	Can be mapped for execution
 */
#define NOMMU_MAP_COPY		0x00000001
#define NOMMU_MAP_DIRECT	0x00000008
#define NOMMU_MAP_READ		VM_MAYREAD
#define NOMMU_MAP_WRITE		VM_MAYWRITE
#define NOMMU_MAP_EXEC		VM_MAYEXEC

#define NOMMU_VMFLAGS \
	(NOMMU_MAP_READ | NOMMU_MAP_WRITE | NOMMU_MAP_EXEC)

/*
 * These flags control the behavior of the remap_file_range function pointer.
 * If it is called with len == 0 that means "remap to end of source file".
 * See Documentation/filesystems/vfs.rst for more details about this call.
 *
 * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate)
 * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request
 */
#define REMAP_FILE_DEDUP		(1 << 0)
#define REMAP_FILE_CAN_SHORTEN		(1 << 1)

/*
 * These flags signal that the caller is ok with altering various aspects of
 * the behavior of the remap operation.  The changes must be made by the
 * implementation; the vfs remap helper functions can take advantage of them.
 * Flags in this category exist to preserve the quirky behavior of the hoisted
 * btrfs clone/dedupe ioctls.
 */
#define REMAP_FILE_ADVISORY		(REMAP_FILE_CAN_SHORTEN)

/*
 * These flags control the behavior of vfs_copy_file_range().
 * They are not available to the user via syscall.
 *
 * COPY_FILE_SPLICE: call splice direct instead of fs clone/copy ops
 */
#define COPY_FILE_SPLICE		(1 << 0)

struct iov_iter;
struct io_uring_cmd;

struct file_operations {
	struct module *owner;
	loff_t (*llseek) (struct file *, loff_t, int);
	ssize_t (*read) (struct file *, char __user *, size_t, loff_t *);
	ssize_t (*write) (struct file *, const char __user *, size_t, loff_t *);
	ssize_t (*read_iter) (struct kiocb *, struct iov_iter *);
	ssize_t (*write_iter) (struct kiocb *, struct iov_iter *);
	int (*iopoll)(struct kiocb *kiocb, struct io_comp_batch *,
			unsigned int flags);
	int (*iterate) (struct file *, struct dir_context *);
	int (*iterate_shared) (struct file *, struct dir_context *);
	__poll_t (*poll) (struct file *, struct poll_table_struct *);
	long (*unlocked_ioctl) (struct file *, unsigned int, unsigned long);
	long (*compat_ioctl) (struct file *, unsigned int, unsigned long);
	int (*mmap) (struct file *, struct vm_area_struct *);
	unsigned long mmap_supported_flags;
	int (*open) (struct inode *, struct file *);
	int (*flush) (struct file *, fl_owner_t id);
	int (*release) (struct inode *, struct file *);
	int (*fsync) (struct file *, loff_t, loff_t, int datasync);
	int (*fasync) (int, struct file *, int);
	int (*lock) (struct file *, int, struct file_lock *);
	unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long);
	int (*check_flags)(int);
	int (*flock) (struct file *, int, struct file_lock *);
	ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *, size_t, unsigned int);
	ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *, size_t, unsigned int);
	void (*splice_eof)(struct file *file);
	int (*setlease)(struct file *, long, struct file_lock **, void **);
	long (*fallocate)(struct file *file, int mode, loff_t offset,
			  loff_t len);
	void (*show_fdinfo)(struct seq_file *m, struct file *f);
#ifndef CONFIG_MMU
	unsigned (*mmap_capabilities)(struct file *);
#endif
	ssize_t (*copy_file_range)(struct file *, loff_t, struct file *,
			loff_t, size_t, unsigned int);
	loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in,
				   struct file *file_out, loff_t pos_out,
				   loff_t len, unsigned int remap_flags);
	int (*fadvise)(struct file *, loff_t, loff_t, int);
	int (*uring_cmd)(struct io_uring_cmd *ioucmd, unsigned int issue_flags);
	int (*uring_cmd_iopoll)(struct io_uring_cmd *, struct io_comp_batch *,
				unsigned int poll_flags);
} __randomize_layout;

struct inode_operations {
	struct dentry * (*lookup) (struct inode *,struct dentry *, unsigned int);
	const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *);
	int (*permission) (struct mnt_idmap *, struct inode *, int);
	struct posix_acl * (*get_inode_acl)(struct inode *, int, bool);

	int (*readlink) (struct dentry *, char __user *,int);

	int (*create) (struct mnt_idmap *, struct inode *,struct dentry *,
		       umode_t, bool);
	int (*link) (struct dentry *,struct inode *,struct dentry *);
	int (*unlink) (struct inode *,struct dentry *);
	int (*symlink) (struct mnt_idmap *, struct inode *,struct dentry *,
			const char *);
	int (*mkdir) (struct mnt_idmap *, struct inode *,struct dentry *,
		      umode_t);
	int (*rmdir) (struct inode *,struct dentry *);
	int (*mknod) (struct mnt_idmap *, struct inode *,struct dentry *,
		      umode_t,dev_t);
	int (*rename) (struct mnt_idmap *, struct inode *, struct dentry *,
			struct inode *, struct dentry *, unsigned int);
	int (*setattr) (struct mnt_idmap *, struct dentry *, struct iattr *);
	int (*getattr) (struct mnt_idmap *, const struct path *,
			struct kstat *, u32, unsigned int);
	ssize_t (*listxattr) (struct dentry *, char *, size_t);
	int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start,
		      u64 len);
	int (*update_time)(struct inode *, struct timespec64 *, int);
	int (*atomic_open)(struct inode *, struct dentry *,
			   struct file *, unsigned open_flag,
			   umode_t create_mode);
	int (*tmpfile) (struct mnt_idmap *, struct inode *,
			struct file *, umode_t);
	struct posix_acl *(*get_acl)(struct mnt_idmap *, struct dentry *,
				     int);
	int (*set_acl)(struct mnt_idmap *, struct dentry *,
		       struct posix_acl *, int);
	int (*fileattr_set)(struct mnt_idmap *idmap,
			    struct dentry *dentry, struct fileattr *fa);
	int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
} ____cacheline_aligned;

static inline ssize_t call_read_iter(struct file *file, struct kiocb *kio,
				     struct iov_iter *iter)
{
	return file->f_op->read_iter(kio, iter);
}

static inline ssize_t call_write_iter(struct file *file, struct kiocb *kio,
				      struct iov_iter *iter)
{
	return file->f_op->write_iter(kio, iter);
}

static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
{
	return file->f_op->mmap(file, vma);
}

extern ssize_t vfs_read(struct file *, char __user *, size_t, loff_t *);
extern ssize_t vfs_write(struct file *, const char __user *, size_t, loff_t *);
extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *,
				   loff_t, size_t, unsigned int);
extern ssize_t generic_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);
int __generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
				    struct file *file_out, loff_t pos_out,
				    loff_t *len, unsigned int remap_flags,
				    const struct iomap_ops *dax_read_ops);
int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in,
				  struct file *file_out, loff_t pos_out,
				  loff_t *count, unsigned int remap_flags);
extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in,
				  struct file *file_out, loff_t pos_out,
				  loff_t len, unsigned int remap_flags);
extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in,
				   struct file *file_out, loff_t pos_out,
				   loff_t len, unsigned int remap_flags);
extern int vfs_dedupe_file_range(struct file *file,
				 struct file_dedupe_range *same);
extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos,
					struct file *dst_file, loff_t dst_pos,
					loff_t len, unsigned int remap_flags);


struct super_operations {
   	struct inode *(*alloc_inode)(struct super_block *sb);
	void (*destroy_inode)(struct inode *);
	void (*free_inode)(struct inode *);

   	void (*dirty_inode) (struct inode *, int flags);
	int (*write_inode) (struct inode *, struct writeback_control *wbc);
	int (*drop_inode) (struct inode *);
	void (*evict_inode) (struct inode *);
	void (*put_super) (struct super_block *);
	int (*sync_fs)(struct super_block *sb, int wait);
	int (*freeze_super) (struct super_block *);
	int (*freeze_fs) (struct super_block *);
	int (*thaw_super) (struct super_block *);
	int (*unfreeze_fs) (struct super_block *);
	int (*statfs) (struct dentry *, struct kstatfs *);
	int (*remount_fs) (struct super_block *, int *, char *);
	void (*umount_begin) (struct super_block *);

	int (*show_options)(struct seq_file *, struct dentry *);
	int (*show_devname)(struct seq_file *, struct dentry *);
	int (*show_path)(struct seq_file *, struct dentry *);
	int (*show_stats)(struct seq_file *, struct dentry *);
#ifdef CONFIG_QUOTA
	ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
	ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
	struct dquot **(*get_dquots)(struct inode *);
#endif
	long (*nr_cached_objects)(struct super_block *,
				  struct shrink_control *);
	long (*free_cached_objects)(struct super_block *,
				    struct shrink_control *);
	void (*shutdown)(struct super_block *sb);
};

/*
 * Inode flags - they have no relation to superblock flags now
 */
#define S_SYNC		(1 << 0)  /* Writes are synced at once */
#define S_NOATIME	(1 << 1)  /* Do not update access times */
#define S_APPEND	(1 << 2)  /* Append-only file */
#define S_IMMUTABLE	(1 << 3)  /* Immutable file */
#define S_DEAD		(1 << 4)  /* removed, but still open directory */
#define S_NOQUOTA	(1 << 5)  /* Inode is not counted to quota */
#define S_DIRSYNC	(1 << 6)  /* Directory modifications are synchronous */
#define S_NOCMTIME	(1 << 7)  /* Do not update file c/mtime */
#define S_SWAPFILE	(1 << 8)  /* Do not truncate: swapon got its bmaps */
#define S_PRIVATE	(1 << 9)  /* Inode is fs-internal */
#define S_IMA		(1 << 10) /* Inode has an associated IMA struct */
#define S_AUTOMOUNT	(1 << 11) /* Automount/referral quasi-directory */
#define S_NOSEC		(1 << 12) /* no suid or xattr security attributes */
#ifdef CONFIG_FS_DAX
#define S_DAX		(1 << 13) /* Direct Access, avoiding the page cache */
#else
#define S_DAX		0	  /* Make all the DAX code disappear */
#endif
#define S_ENCRYPTED	(1 << 14) /* Encrypted file (using fs/crypto/) */
#define S_CASEFOLD	(1 << 15) /* Casefolded file */
#define S_VERITY	(1 << 16) /* Verity file (using fs/verity/) */
#define S_KERNEL_FILE	(1 << 17) /* File is in use by the kernel (eg. fs/cachefiles) */

/*
 * Note that nosuid etc flags are inode-specific: setting some file-system
 * flags just means all the inodes inherit those flags by default. It might be
 * possible to override it selectively if you really wanted to with some
 * ioctl() that is not currently implemented.
 *
 * Exception: SB_RDONLY is always applied to the entire file system.
 *
 * Unfortunately, it is possible to change a filesystems flags with it mounted
 * with files in use.  This means that all of the inodes will not have their
 * i_flags updated.  Hence, i_flags no longer inherit the superblock mount
 * flags, so these have to be checked separately. -- rmk@arm.uk.linux.org
 */
#define __IS_FLG(inode, flg)	((inode)->i_sb->s_flags & (flg))

static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; }
#define IS_RDONLY(inode)	sb_rdonly((inode)->i_sb)
#define IS_SYNC(inode)		(__IS_FLG(inode, SB_SYNCHRONOUS) || \
					((inode)->i_flags & S_SYNC))
#define IS_DIRSYNC(inode)	(__IS_FLG(inode, SB_SYNCHRONOUS|SB_DIRSYNC) || \
					((inode)->i_flags & (S_SYNC|S_DIRSYNC)))
#define IS_MANDLOCK(inode)	__IS_FLG(inode, SB_MANDLOCK)
#define IS_NOATIME(inode)	__IS_FLG(inode, SB_RDONLY|SB_NOATIME)
#define IS_I_VERSION(inode)	__IS_FLG(inode, SB_I_VERSION)

#define IS_NOQUOTA(inode)	((inode)->i_flags & S_NOQUOTA)
#define IS_APPEND(inode)	((inode)->i_flags & S_APPEND)
#define IS_IMMUTABLE(inode)	((inode)->i_flags & S_IMMUTABLE)
#define IS_POSIXACL(inode)	__IS_FLG(inode, SB_POSIXACL)

#define IS_DEADDIR(inode)	((inode)->i_flags & S_DEAD)
#define IS_NOCMTIME(inode)	((inode)->i_flags & S_NOCMTIME)
#define IS_SWAPFILE(inode)	((inode)->i_flags & S_SWAPFILE)
#define IS_PRIVATE(inode)	((inode)->i_flags & S_PRIVATE)
#define IS_IMA(inode)		((inode)->i_flags & S_IMA)
#define IS_AUTOMOUNT(inode)	((inode)->i_flags & S_AUTOMOUNT)
#define IS_NOSEC(inode)		((inode)->i_flags & S_NOSEC)
#define IS_DAX(inode)		((inode)->i_flags & S_DAX)
#define IS_ENCRYPTED(inode)	((inode)->i_flags & S_ENCRYPTED)
#define IS_CASEFOLDED(inode)	((inode)->i_flags & S_CASEFOLD)
#define IS_VERITY(inode)	((inode)->i_flags & S_VERITY)

#define IS_WHITEOUT(inode)	(S_ISCHR(inode->i_mode) && \
				 (inode)->i_rdev == WHITEOUT_DEV)

static inline bool HAS_UNMAPPED_ID(struct mnt_idmap *idmap,
				   struct inode *inode)
{
	return !vfsuid_valid(i_uid_into_vfsuid(idmap, inode)) ||
	       !vfsgid_valid(i_gid_into_vfsgid(idmap, inode));
}

static inline void init_sync_kiocb(struct kiocb *kiocb, struct file *filp)
{
	*kiocb = (struct kiocb) {
		.ki_filp = filp,
		.ki_flags = filp->f_iocb_flags,
		.ki_ioprio = get_current_ioprio(),
	};
}

static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
			       struct file *filp)
{
	*kiocb = (struct kiocb) {
		.ki_filp = filp,
		.ki_flags = kiocb_src->ki_flags,
		.ki_ioprio = kiocb_src->ki_ioprio,
		.ki_pos = kiocb_src->ki_pos,
	};
}

/*
 * Inode state bits.  Protected by inode->i_lock
 *
 * Four bits determine the dirty state of the inode: I_DIRTY_SYNC,
 * I_DIRTY_DATASYNC, I_DIRTY_PAGES, and I_DIRTY_TIME.
 *
 * Four bits define the lifetime of an inode.  Initially, inodes are I_NEW,
 * until that flag is cleared.  I_WILL_FREE, I_FREEING and I_CLEAR are set at
 * various stages of removing an inode.
 *
 * Two bits are used for locking and completion notification, I_NEW and I_SYNC.
 *
 * I_DIRTY_SYNC		Inode is dirty, but doesn't have to be written on
 *			fdatasync() (unless I_DIRTY_DATASYNC is also set).
 *			Timestamp updates are the usual cause.
 * I_DIRTY_DATASYNC	Data-related inode changes pending.  We keep track of
 *			these changes separately from I_DIRTY_SYNC so that we
 *			don't have to write inode on fdatasync() when only
 *			e.g. the timestamps have changed.
 * I_DIRTY_PAGES	Inode has dirty pages.  Inode itself may be clean.
 * I_DIRTY_TIME		The inode itself has dirty timestamps, and the
 *			lazytime mount option is enabled.  We keep track of this
 *			separately from I_DIRTY_SYNC in order to implement
 *			lazytime.  This gets cleared if I_DIRTY_INODE
 *			(I_DIRTY_SYNC and/or I_DIRTY_DATASYNC) gets set. But
 *			I_DIRTY_TIME can still be set if I_DIRTY_SYNC is already
 *			in place because writeback might already be in progress
 *			and we don't want to lose the time update
 * I_NEW		Serves as both a mutex and completion notification.
 *			New inodes set I_NEW.  If two processes both create
 *			the same inode, one of them will release its inode and
 *			wait for I_NEW to be released before returning.
 *			Inodes in I_WILL_FREE, I_FREEING or I_CLEAR state can
 *			also cause waiting on I_NEW, without I_NEW actually
 *			being set.  find_inode() uses this to prevent returning
 *			nearly-dead inodes.
 * I_WILL_FREE		Must be set when calling write_inode_now() if i_count
 *			is zero.  I_FREEING must be set when I_WILL_FREE is
 *			cleared.
 * I_FREEING		Set when inode is about to be freed but still has dirty
 *			pages or buffers attached or the inode itself is still
 *			dirty.
 * I_CLEAR		Added by clear_inode().  In this state the inode is
 *			clean and can be destroyed.  Inode keeps I_FREEING.
 *
 *			Inodes that are I_WILL_FREE, I_FREEING or I_CLEAR are
 *			prohibited for many purposes.  iget() must wait for
 *			the inode to be completely released, then create it
 *			anew.  Other functions will just ignore such inodes,
 *			if appropriate.  I_NEW is used for waiting.
 *
 * I_SYNC		Writeback of inode is running. The bit is set during
 *			data writeback, and cleared with a wakeup on the bit
 *			address once it is done. The bit is also used to pin
 *			the inode in memory for flusher thread.
 *
 * I_REFERENCED		Marks the inode as recently references on the LRU list.
 *
 * I_DIO_WAKEUP		Never set.  Only used as a key for wait_on_bit().
 *
 * I_WB_SWITCH		Cgroup bdi_writeback switching in progress.  Used to
 *			synchronize competing switching instances and to tell
 *			wb stat updates to grab the i_pages lock.  See
 *			inode_switch_wbs_work_fn() for details.
 *
 * I_OVL_INUSE		Used by overlayfs to get exclusive ownership on upper
 *			and work dirs among overlayfs mounts.
 *
 * I_CREATING		New object's inode in the middle of setting up.
 *
 * I_DONTCACHE		Evict inode as soon as it is not used anymore.
 *
 * I_SYNC_QUEUED	Inode is queued in b_io or b_more_io writeback lists.
 *			Used to detect that mark_inode_dirty() should not move
 * 			inode between dirty lists.
 *
 * I_PINNING_FSCACHE_WB	Inode is pinning an fscache object for writeback.
 *
 * Q: What is the difference between I_WILL_FREE and I_FREEING?
 */
#define I_DIRTY_SYNC		(1 << 0)
#define I_DIRTY_DATASYNC	(1 << 1)
#define I_DIRTY_PAGES		(1 << 2)
#define __I_NEW			3
#define I_NEW			(1 << __I_NEW)
#define I_WILL_FREE		(1 << 4)
#define I_FREEING		(1 << 5)
#define I_CLEAR			(1 << 6)
#define __I_SYNC		7
#define I_SYNC			(1 << __I_SYNC)
#define I_REFERENCED		(1 << 8)
#define __I_DIO_WAKEUP		9
#define I_DIO_WAKEUP		(1 << __I_DIO_WAKEUP)
#define I_LINKABLE		(1 << 10)
#define I_DIRTY_TIME		(1 << 11)
#define I_WB_SWITCH		(1 << 13)
#define I_OVL_INUSE		(1 << 14)
#define I_CREATING		(1 << 15)
#define I_DONTCACHE		(1 << 16)
#define I_SYNC_QUEUED		(1 << 17)
#define I_PINNING_FSCACHE_WB	(1 << 18)

#define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
#define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
#define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME)

extern void __mark_inode_dirty(struct inode *, int);
static inline void mark_inode_dirty(struct inode *inode)
{
	__mark_inode_dirty(inode, I_DIRTY);
}

static inline void mark_inode_dirty_sync(struct inode *inode)
{
	__mark_inode_dirty(inode, I_DIRTY_SYNC);
}

/*
 * Returns true if the given inode itself only has dirty timestamps (its pages
 * may still be dirty) and isn't currently being allocated or freed.
 * Filesystems should call this if when writing an inode when lazytime is
 * enabled, they want to opportunistically write the timestamps of other inodes
 * located very nearby on-disk, e.g. in the same inode block.  This returns true
 * if the given inode is in need of such an opportunistic update.  Requires
 * i_lock, or at least later re-checking under i_lock.
 */
static inline bool inode_is_dirtytime_only(struct inode *inode)
{
	return (inode->i_state & (I_DIRTY_TIME | I_NEW |
				  I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME;
}

extern void inc_nlink(struct inode *inode);
extern void drop_nlink(struct inode *inode);
extern void clear_nlink(struct inode *inode);
extern void set_nlink(struct inode *inode, unsigned int nlink);

static inline void inode_inc_link_count(struct inode *inode)
{
	inc_nlink(inode);
	mark_inode_dirty(inode);
}

static inline void inode_dec_link_count(struct inode *inode)
{
	drop_nlink(inode);
	mark_inode_dirty(inode);
}

enum file_time_flags {
	S_ATIME = 1,
	S_MTIME = 2,
	S_CTIME = 4,
	S_VERSION = 8,
};

extern bool atime_needs_update(const struct path *, struct inode *);
extern void touch_atime(const struct path *);
int inode_update_time(struct inode *inode, struct timespec64 *time, int flags);

static inline void file_accessed(struct file *file)
{
	if (!(file->f_flags & O_NOATIME))
		touch_atime(&file->f_path);
}

extern int file_modified(struct file *file);
int kiocb_modified(struct kiocb *iocb);

int sync_inode_metadata(struct inode *inode, int wait);

struct file_system_type {
	const char *name;
	int fs_flags;
#define FS_REQUIRES_DEV		1 
#define FS_BINARY_MOUNTDATA	2
#define FS_HAS_SUBTYPE		4
#define FS_USERNS_MOUNT		8	/* Can be mounted by userns root */
#define FS_DISALLOW_NOTIFY_PERM	16	/* Disable fanotify permission events */
#define FS_ALLOW_IDMAP         32      /* FS has been updated to handle vfs idmappings. */
#define FS_RENAME_DOES_D_MOVE	32768	/* FS will handle d_move() during rename() internally. */
	int (*init_fs_context)(struct fs_context *);
	const struct fs_parameter_spec *parameters;
	struct dentry *(*mount) (struct file_system_type *, int,
		       const char *, void *);
	void (*kill_sb) (struct super_block *);
	struct module *owner;
	struct file_system_type * next;
	struct hlist_head fs_supers;

	struct lock_class_key s_lock_key;
	struct lock_class_key s_umount_key;
	struct lock_class_key s_vfs_rename_key;
	struct lock_class_key s_writers_key[SB_FREEZE_LEVELS];

	struct lock_class_key i_lock_key;
	struct lock_class_key i_mutex_key;
	struct lock_class_key invalidate_lock_key;
	struct lock_class_key i_mutex_dir_key;
};

#define MODULE_ALIAS_FS(NAME) MODULE_ALIAS("fs-" NAME)

extern struct dentry *mount_bdev(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data,
	int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_single(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_nodev(struct file_system_type *fs_type,
	int flags, void *data,
	int (*fill_super)(struct super_block *, void *, int));
extern struct dentry *mount_subtree(struct vfsmount *mnt, const char *path);
void retire_super(struct super_block *sb);
void generic_shutdown_super(struct super_block *sb);
void kill_block_super(struct super_block *sb);
void kill_anon_super(struct super_block *sb);
void kill_litter_super(struct super_block *sb);
void deactivate_super(struct super_block *sb);
void deactivate_locked_super(struct super_block *sb);
int set_anon_super(struct super_block *s, void *data);
int set_anon_super_fc(struct super_block *s, struct fs_context *fc);
int get_anon_bdev(dev_t *);
void free_anon_bdev(dev_t);
struct super_block *sget_fc(struct fs_context *fc,
			    int (*test)(struct super_block *, struct fs_context *),
			    int (*set)(struct super_block *, struct fs_context *));
struct super_block *sget(struct file_system_type *type,
			int (*test)(struct super_block *,void *),
			int (*set)(struct super_block *,void *),
			int flags, void *data);

/* Alas, no aliases. Too much hassle with bringing module.h everywhere */
#define fops_get(fops) \
	(((fops) && try_module_get((fops)->owner) ? (fops) : NULL))
#define fops_put(fops) \
	do { if (fops) module_put((fops)->owner); } while(0)
/*
 * This one is to be used *ONLY* from ->open() instances.
 * fops must be non-NULL, pinned down *and* module dependencies
 * should be sufficient to pin the caller down as well.
 */
#define replace_fops(f, fops) \
	do {	\
		struct file *__file = (f); \
		fops_put(__file->f_op); \
		BUG_ON(!(__file->f_op = (fops))); \
	} while(0)

extern int register_filesystem(struct file_system_type *);
extern int unregister_filesystem(struct file_system_type *);
extern int vfs_statfs(const struct path *, struct kstatfs *);
extern int user_statfs(const char __user *, struct kstatfs *);
extern int fd_statfs(int, struct kstatfs *);
extern int freeze_super(struct super_block *super);
extern int thaw_super(struct super_block *super);
extern __printf(2, 3)
int super_setup_bdi_name(struct super_block *sb, char *fmt, ...);
extern int super_setup_bdi(struct super_block *sb);

extern int current_umask(void);

extern void ihold(struct inode * inode);
extern void iput(struct inode *);
extern int generic_update_time(struct inode *, struct timespec64 *, int);

/* /sys/fs */
extern struct kobject *fs_kobj;

#define MAX_RW_COUNT (INT_MAX & PAGE_MASK)

/* fs/open.c */
struct audit_names;
struct filename {
	const char		*name;	/* pointer to actual string */
	const __user char	*uptr;	/* original userland pointer */
	int			refcnt;
	struct audit_names	*aname;
	const char		iname[];
};
static_assert(offsetof(struct filename, iname) % sizeof(long) == 0);

static inline struct mnt_idmap *file_mnt_idmap(struct file *file)
{
	return mnt_idmap(file->f_path.mnt);
}

/**
 * is_idmapped_mnt - check whether a mount is mapped
 * @mnt: the mount to check
 *
 * If @mnt has an non @nop_mnt_idmap attached to it then @mnt is mapped.
 *
 * Return: true if mount is mapped, false if not.
 */
static inline bool is_idmapped_mnt(const struct vfsmount *mnt)
{
	return mnt_idmap(mnt) != &nop_mnt_idmap;
}

extern long vfs_truncate(const struct path *, loff_t);
int do_truncate(struct mnt_idmap *, struct dentry *, loff_t start,
		unsigned int time_attrs, struct file *filp);
extern int vfs_fallocate(struct file *file, int mode, loff_t offset,
			loff_t len);
extern long do_sys_open(int dfd, const char __user *filename, int flags,
			umode_t mode);
extern struct file *file_open_name(struct filename *, int, umode_t);
extern struct file *filp_open(const char *, int, umode_t);
extern struct file *file_open_root(const struct path *,
				   const char *, int, umode_t);
static inline struct file *file_open_root_mnt(struct vfsmount *mnt,
				   const char *name, int flags, umode_t mode)
{
	return file_open_root(&(struct path){.mnt = mnt, .dentry = mnt->mnt_root},
			      name, flags, mode);
}
struct file *dentry_open(const struct path *path, int flags,
			 const struct cred *creds);
struct file *dentry_create(const struct path *path, int flags, umode_t mode,
			   const struct cred *cred);
struct file *backing_file_open(const struct path *path, int flags,
			       const struct path *real_path,
			       const struct cred *cred);
struct path *backing_file_real_path(struct file *f);

/*
 * file_real_path - get the path corresponding to f_inode
 *
 * When opening a backing file for a stackable filesystem (e.g.,
 * overlayfs) f_path may be on the stackable filesystem and f_inode on
 * the underlying filesystem.  When the path associated with f_inode is
 * needed, this helper should be used instead of accessing f_path
 * directly.
*/
static inline const struct path *file_real_path(struct file *f)
{
	if (unlikely(f->f_mode & FMODE_BACKING))
		return backing_file_real_path(f);
	return &f->f_path;
}

static inline struct file *file_clone_open(struct file *file)
{
	return dentry_open(&file->f_path, file->f_flags, file->f_cred);
}
extern int filp_close(struct file *, fl_owner_t id);

extern struct filename *getname_flags(const char __user *, int, int *);
extern struct filename *getname_uflags(const char __user *, int);
extern struct filename *getname(const char __user *);
extern struct filename *getname_kernel(const char *);
extern void putname(struct filename *name);

extern int finish_open(struct file *file, struct dentry *dentry,
			int (*open)(struct inode *, struct file *));
extern int finish_no_open(struct file *file, struct dentry *dentry);

/* Helper for the simple case when original dentry is used */
static inline int finish_open_simple(struct file *file, int error)
{
	if (error)
		return error;

	return finish_open(file, file->f_path.dentry, NULL);
}

/* fs/dcache.c */
extern void __init vfs_caches_init_early(void);
extern void __init vfs_caches_init(void);

extern struct kmem_cache *names_cachep;

#define __getname()		kmem_cache_alloc(names_cachep, GFP_KERNEL)
#define __putname(name)		kmem_cache_free(names_cachep, (void *)(name))

extern struct super_block *blockdev_superblock;
static inline bool sb_is_blkdev_sb(struct super_block *sb)
{
	return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock;
}

void emergency_thaw_all(void);
extern int sync_filesystem(struct super_block *);
extern const struct file_operations def_blk_fops;
extern const struct file_operations def_chr_fops;

/* fs/char_dev.c */
#define CHRDEV_MAJOR_MAX 512
/* Marks the bottom of the first segment of free char majors */
#define CHRDEV_MAJOR_DYN_END 234
/* Marks the top and bottom of the second segment of free char majors */
#define CHRDEV_MAJOR_DYN_EXT_START 511
#define CHRDEV_MAJOR_DYN_EXT_END 384

extern int alloc_chrdev_region(dev_t *, unsigned, unsigned, const char *);
extern int register_chrdev_region(dev_t, unsigned, const char *);
extern int __register_chrdev(unsigned int major, unsigned int baseminor,
			     unsigned int count, const char *name,
			     const struct file_operations *fops);
extern void __unregister_chrdev(unsigned int major, unsigned int baseminor,
				unsigned int count, const char *name);
extern void unregister_chrdev_region(dev_t, unsigned);
extern void chrdev_show(struct seq_file *,off_t);

static inline int register_chrdev(unsigned int major, const char *name,
				  const struct file_operations *fops)
{
	return __register_chrdev(major, 0, 256, name, fops);
}

static inline void unregister_chrdev(unsigned int major, const char *name)
{
	__unregister_chrdev(major, 0, 256, name);
}

extern void init_special_inode(struct inode *, umode_t, dev_t);

/* Invalid inode operations -- fs/bad_inode.c */
extern void make_bad_inode(struct inode *);
extern bool is_bad_inode(struct inode *);

extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart,
						loff_t lend);
extern int __must_check file_check_and_advance_wb_err(struct file *file);
extern int __must_check file_write_and_wait_range(struct file *file,
						loff_t start, loff_t end);

static inline int file_write_and_wait(struct file *file)
{
	return file_write_and_wait_range(file, 0, LLONG_MAX);
}

extern int vfs_fsync_range(struct file *file, loff_t start, loff_t end,
			   int datasync);
extern int vfs_fsync(struct file *file, int datasync);

extern int sync_file_range(struct file *file, loff_t offset, loff_t nbytes,
				unsigned int flags);

static inline bool iocb_is_dsync(const struct kiocb *iocb)
{
	return (iocb->ki_flags & IOCB_DSYNC) ||
		IS_SYNC(iocb->ki_filp->f_mapping->host);
}

/*
 * Sync the bytes written if this was a synchronous write.  Expect ki_pos
 * to already be updated for the write, and will return either the amount
 * of bytes passed in, or an error if syncing the file failed.
 */
static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count)
{
	if (iocb_is_dsync(iocb)) {
		int ret = vfs_fsync_range(iocb->ki_filp,
				iocb->ki_pos - count, iocb->ki_pos - 1,
				(iocb->ki_flags & IOCB_SYNC) ? 0 : 1);
		if (ret)
			return ret;
	}

	return count;
}

extern void emergency_sync(void);
extern void emergency_remount(void);

#ifdef CONFIG_BLOCK
extern int bmap(struct inode *inode, sector_t *block);
#else
static inline int bmap(struct inode *inode,  sector_t *block)
{
	return -EINVAL;
}
#endif

int notify_change(struct mnt_idmap *, struct dentry *,
		  struct iattr *, struct inode **);
int inode_permission(struct mnt_idmap *, struct inode *, int);
int generic_permission(struct mnt_idmap *, struct inode *, int);
static inline int file_permission(struct file *file, int mask)
{
	return inode_permission(file_mnt_idmap(file),
				file_inode(file), mask);
}
static inline int path_permission(const struct path *path, int mask)
{
	return inode_permission(mnt_idmap(path->mnt),
				d_inode(path->dentry), mask);
}
int __check_sticky(struct mnt_idmap *idmap, struct inode *dir,
		   struct inode *inode);

static inline bool execute_ok(struct inode *inode)
{
	return (inode->i_mode & S_IXUGO) || S_ISDIR(inode->i_mode);
}

static inline bool inode_wrong_type(const struct inode *inode, umode_t mode)
{
	return (inode->i_mode ^ mode) & S_IFMT;
}

static inline void file_start_write(struct file *file)
{
	if (!S_ISREG(file_inode(file)->i_mode))
		return;
	sb_start_write(file_inode(file)->i_sb);
}

static inline bool file_start_write_trylock(struct file *file)
{
	if (!S_ISREG(file_inode(file)->i_mode))
		return true;
	return sb_start_write_trylock(file_inode(file)->i_sb);
}

static inline void file_end_write(struct file *file)
{
	if (!S_ISREG(file_inode(file)->i_mode))
		return;
	__sb_end_write(file_inode(file)->i_sb, SB_FREEZE_WRITE);
}

/*
 * This is used for regular files where some users -- especially the
 * currently executed binary in a process, previously handled via
 * VM_DENYWRITE -- cannot handle concurrent write (and maybe mmap
 * read-write shared) accesses.
 *
 * get_write_access() gets write permission for a file.
 * put_write_access() releases this write permission.
 * deny_write_access() denies write access to a file.
 * allow_write_access() re-enables write access to a file.
 *
 * The i_writecount field of an inode can have the following values:
 * 0: no write access, no denied write access
 * < 0: (-i_writecount) users that denied write access to the file.
 * > 0: (i_writecount) users that have write access to the file.
 *
 * Normally we operate on that counter with atomic_{inc,dec} and it's safe
 * except for the cases where we don't hold i_writecount yet. Then we need to
 * use {get,deny}_write_access() - these functions check the sign and refuse
 * to do the change if sign is wrong.
 */
static inline int get_write_access(struct inode *inode)
{
	return atomic_inc_unless_negative(&inode->i_writecount) ? 0 : -ETXTBSY;
}
static inline int deny_write_access(struct file *file)
{
	struct inode *inode = file_inode(file);
	return atomic_dec_unless_positive(&inode->i_writecount) ? 0 : -ETXTBSY;
}
static inline void put_write_access(struct inode * inode)
{
	atomic_dec(&inode->i_writecount);
}
static inline void allow_write_access(struct file *file)
{
	if (file)
		atomic_inc(&file_inode(file)->i_writecount);
}
static inline bool inode_is_open_for_write(const struct inode *inode)
{
	return atomic_read(&inode->i_writecount) > 0;
}

#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING)
static inline void i_readcount_dec(struct inode *inode)
{
	BUG_ON(!atomic_read(&inode->i_readcount));
	atomic_dec(&inode->i_readcount);
}
static inline void i_readcount_inc(struct inode *inode)
{
	atomic_inc(&inode->i_readcount);
}
#else
static inline void i_readcount_dec(struct inode *inode)
{
	return;
}
static inline void i_readcount_inc(struct inode *inode)
{
	return;
}
#endif
extern int do_pipe_flags(int *, int);

extern ssize_t kernel_read(struct file *, void *, size_t, loff_t *);
ssize_t __kernel_read(struct file *file, void *buf, size_t count, loff_t *pos);
extern ssize_t kernel_write(struct file *, const void *, size_t, loff_t *);
extern ssize_t __kernel_write(struct file *, const void *, size_t, loff_t *);
extern struct file * open_exec(const char *);
 
/* fs/dcache.c -- generic fs support functions */
extern bool is_subdir(struct dentry *, struct dentry *);
extern bool path_is_under(const struct path *, const struct path *);

extern char *file_path(struct file *, char *, int);

#include <linux/err.h>

/* needed for stackable file system support */
extern loff_t default_llseek(struct file *file, loff_t offset, int whence);

extern loff_t vfs_llseek(struct file *file, loff_t offset, int whence);

extern int inode_init_always(struct super_block *, struct inode *);
extern void inode_init_once(struct inode *);
extern void address_space_init_once(struct address_space *mapping);
extern struct inode * igrab(struct inode *);
extern ino_t iunique(struct super_block *, ino_t);
extern int inode_needs_sync(struct inode *inode);
extern int generic_delete_inode(struct inode *inode);
static inline int generic_drop_inode(struct inode *inode)
{
	return !inode->i_nlink || inode_unhashed(inode);
}
extern void d_mark_dontcache(struct inode *inode);

extern struct inode *ilookup5_nowait(struct super_block *sb,
		unsigned long hashval, int (*test)(struct inode *, void *),
		void *data);
extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval,
		int (*test)(struct inode *, void *), void *data);
extern struct inode *ilookup(struct super_block *sb, unsigned long ino);

extern struct inode *inode_insert5(struct inode *inode, unsigned long hashval,
		int (*test)(struct inode *, void *),
		int (*set)(struct inode *, void *),
		void *data);
extern struct inode * iget5_locked(struct super_block *, unsigned long, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *);
extern struct inode * iget_locked(struct super_block *, unsigned long);
extern struct inode *find_inode_nowait(struct super_block *,
				       unsigned long,
				       int (*match)(struct inode *,
						    unsigned long, void *),
				       void *data);
extern struct inode *find_inode_rcu(struct super_block *, unsigned long,
				    int (*)(struct inode *, void *), void *);
extern struct inode *find_inode_by_ino_rcu(struct super_block *, unsigned long);
extern int insert_inode_locked4(struct inode *, unsigned long, int (*test)(struct inode *, void *), void *);
extern int insert_inode_locked(struct inode *);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
extern void lockdep_annotate_inode_mutex_key(struct inode *inode);
#else
static inline void lockdep_annotate_inode_mutex_key(struct inode *inode) { };
#endif
extern void unlock_new_inode(struct inode *);
extern void discard_new_inode(struct inode *);
extern unsigned int get_next_ino(void);
extern void evict_inodes(struct super_block *sb);
void dump_mapping(const struct address_space *);

/*
 * Userspace may rely on the inode number being non-zero. For example, glibc
 * simply ignores files with zero i_ino in unlink() and other places.
 *
 * As an additional complication, if userspace was compiled with
 * _FILE_OFFSET_BITS=32 on a 64-bit kernel we'll only end up reading out the
 * lower 32 bits, so we need to check that those aren't zero explicitly. With
 * _FILE_OFFSET_BITS=64, this may cause some harmless false-negatives, but
 * better safe than sorry.
 */
static inline bool is_zero_ino(ino_t ino)
{
	return (u32)ino == 0;
}

extern void __iget(struct inode * inode);
extern void iget_failed(struct inode *);
extern void clear_inode(struct inode *);
extern void __destroy_inode(struct inode *);
extern struct inode *new_inode_pseudo(struct super_block *sb);
extern struct inode *new_inode(struct super_block *sb);
extern void free_inode_nonrcu(struct inode *inode);
extern int setattr_should_drop_suidgid(struct mnt_idmap *, struct inode *);
extern int file_remove_privs(struct file *);
int setattr_should_drop_sgid(struct mnt_idmap *idmap,
			     const struct inode *inode);

/*
 * This must be used for allocating filesystems specific inodes to set
 * up the inode reclaim context correctly.
 */
static inline void *
alloc_inode_sb(struct super_block *sb, struct kmem_cache *cache, gfp_t gfp)
{
	return kmem_cache_alloc_lru(cache, &sb->s_inode_lru, gfp);
}

extern void __insert_inode_hash(struct inode *, unsigned long hashval);
static inline void insert_inode_hash(struct inode *inode)
{
	__insert_inode_hash(inode, inode->i_ino);
}

extern void __remove_inode_hash(struct inode *);
static inline void remove_inode_hash(struct inode *inode)
{
	if (!inode_unhashed(inode) && !hlist_fake(&inode->i_hash))
		__remove_inode_hash(inode);
}

extern void inode_sb_list_add(struct inode *inode);
extern void inode_add_lru(struct inode *inode);

extern int sb_set_blocksize(struct super_block *, int);
extern int sb_min_blocksize(struct super_block *, int);

extern int generic_file_mmap(struct file *, struct vm_area_struct *);
extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
int generic_write_checks_count(struct kiocb *iocb, loff_t *count);
extern int generic_write_check_limits(struct file *file, loff_t pos,
		loff_t *count);
extern int generic_file_rw_checks(struct file *file_in, struct file *file_out);
ssize_t filemap_read(struct kiocb *iocb, struct iov_iter *to,
		ssize_t already_read);
extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *);
extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *);
extern ssize_t generic_file_direct_write(struct kiocb *, struct iov_iter *);
ssize_t generic_perform_write(struct kiocb *, struct iov_iter *);
ssize_t direct_write_fallback(struct kiocb *iocb, struct iov_iter *iter,
		ssize_t direct_written, ssize_t buffered_written);

ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
		rwf_t flags);
ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
		rwf_t flags);
ssize_t vfs_iocb_iter_read(struct file *file, struct kiocb *iocb,
			   struct iov_iter *iter);
ssize_t vfs_iocb_iter_write(struct file *file, struct kiocb *iocb,
			    struct iov_iter *iter);

/* fs/splice.c */
ssize_t filemap_splice_read(struct file *in, loff_t *ppos,
			    struct pipe_inode_info *pipe,
			    size_t len, unsigned int flags);
ssize_t copy_splice_read(struct file *in, loff_t *ppos,
			 struct pipe_inode_info *pipe,
			 size_t len, unsigned int flags);
extern ssize_t iter_file_splice_write(struct pipe_inode_info *,
		struct file *, loff_t *, size_t, unsigned int);
extern long do_splice_direct(struct file *in, loff_t *ppos, struct file *out,
		loff_t *opos, size_t len, unsigned int flags);


extern void
file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping);
extern loff_t noop_llseek(struct file *file, loff_t offset, int whence);
#define no_llseek NULL
extern loff_t vfs_setpos(struct file *file, loff_t offset, loff_t maxsize);
extern loff_t generic_file_llseek(struct file *file, loff_t offset, int whence);
extern loff_t generic_file_llseek_size(struct file *file, loff_t offset,
		int whence, loff_t maxsize, loff_t eof);
extern loff_t fixed_size_llseek(struct file *file, loff_t offset,
		int whence, loff_t size);
extern loff_t no_seek_end_llseek_size(struct file *, loff_t, int, loff_t);
extern loff_t no_seek_end_llseek(struct file *, loff_t, int);
int rw_verify_area(int, struct file *, const loff_t *, size_t);
extern int generic_file_open(struct inode * inode, struct file * filp);
extern int nonseekable_open(struct inode * inode, struct file * filp);
extern int stream_open(struct inode * inode, struct file * filp);

#ifdef CONFIG_BLOCK
typedef void (dio_submit_t)(struct bio *bio, struct inode *inode,
			    loff_t file_offset);

enum {
	/* need locking between buffered and direct access */
	DIO_LOCKING	= 0x01,

	/* filesystem does not support filling holes */
	DIO_SKIP_HOLES	= 0x02,
};

ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
			     struct block_device *bdev, struct iov_iter *iter,
			     get_block_t get_block,
			     dio_iodone_t end_io,
			     int flags);

static inline ssize_t blockdev_direct_IO(struct kiocb *iocb,
					 struct inode *inode,
					 struct iov_iter *iter,
					 get_block_t get_block)
{
	return __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
			get_block, NULL, DIO_LOCKING | DIO_SKIP_HOLES);
}
#endif

void inode_dio_wait(struct inode *inode);

/**
 * inode_dio_begin - signal start of a direct I/O requests
 * @inode: inode the direct I/O happens on
 *
 * This is called once we've finished processing a direct I/O request,
 * and is used to wake up callers waiting for direct I/O to be quiesced.
 */
static inline void inode_dio_begin(struct inode *inode)
{
	atomic_inc(&inode->i_dio_count);
}

/**
 * inode_dio_end - signal finish of a direct I/O requests
 * @inode: inode the direct I/O happens on
 *
 * This is called once we've finished processing a direct I/O request,
 * and is used to wake up callers waiting for direct I/O to be quiesced.
 */
static inline void inode_dio_end(struct inode *inode)
{
	if (atomic_dec_and_test(&inode->i_dio_count))
		wake_up_bit(&inode->i_state, __I_DIO_WAKEUP);
}

extern void inode_set_flags(struct inode *inode, unsigned int flags,
			    unsigned int mask);

extern const struct file_operations generic_ro_fops;

#define special_file(m) (S_ISCHR(m)||S_ISBLK(m)||S_ISFIFO(m)||S_ISSOCK(m))

extern int readlink_copy(char __user *, int, const char *);
extern int page_readlink(struct dentry *, char __user *, int);
extern const char *page_get_link(struct dentry *, struct inode *,
				 struct delayed_call *);
extern void page_put_link(void *);
extern int page_symlink(struct inode *inode, const char *symname, int len);
extern const struct inode_operations page_symlink_inode_operations;
extern void kfree_link(void *);
void generic_fillattr(struct mnt_idmap *, struct inode *, struct kstat *);
void generic_fill_statx_attr(struct inode *inode, struct kstat *stat);
extern int vfs_getattr_nosec(const struct path *, struct kstat *, u32, unsigned int);
extern int vfs_getattr(const struct path *, struct kstat *, u32, unsigned int);
void __inode_add_bytes(struct inode *inode, loff_t bytes);
void inode_add_bytes(struct inode *inode, loff_t bytes);
void __inode_sub_bytes(struct inode *inode, loff_t bytes);
void inode_sub_bytes(struct inode *inode, loff_t bytes);
static inline loff_t __inode_get_bytes(struct inode *inode)
{
	return (((loff_t)inode->i_blocks) << 9) + inode->i_bytes;
}
loff_t inode_get_bytes(struct inode *inode);
void inode_set_bytes(struct inode *inode, loff_t bytes);
const char *simple_get_link(struct dentry *, struct inode *,
			    struct delayed_call *);
extern const struct inode_operations simple_symlink_inode_operations;

extern int iterate_dir(struct file *, struct dir_context *);

int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
		int flags);
int vfs_fstat(int fd, struct kstat *stat);

static inline int vfs_stat(const char __user *filename, struct kstat *stat)
{
	return vfs_fstatat(AT_FDCWD, filename, stat, 0);
}
static inline int vfs_lstat(const char __user *name, struct kstat *stat)
{
	return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
}

extern const char *vfs_get_link(struct dentry *, struct delayed_call *);
extern int vfs_readlink(struct dentry *, char __user *, int);

extern struct file_system_type *get_filesystem(struct file_system_type *fs);
extern void put_filesystem(struct file_system_type *fs);
extern struct file_system_type *get_fs_type(const char *name);
extern struct super_block *get_super(struct block_device *);
extern struct super_block *get_active_super(struct block_device *bdev);
extern void drop_super(struct super_block *sb);
extern void drop_super_exclusive(struct super_block *sb);
extern void iterate_supers(void (*)(struct super_block *, void *), void *);
extern void iterate_supers_type(struct file_system_type *,
			        void (*)(struct super_block *, void *), void *);

extern int dcache_dir_open(struct inode *, struct file *);
extern int dcache_dir_close(struct inode *, struct file *);
extern loff_t dcache_dir_lseek(struct file *, loff_t, int);
extern int dcache_readdir(struct file *, struct dir_context *);
extern int simple_setattr(struct mnt_idmap *, struct dentry *,
			  struct iattr *);
extern int simple_getattr(struct mnt_idmap *, const struct path *,
			  struct kstat *, u32, unsigned int);
extern int simple_statfs(struct dentry *, struct kstatfs *);
extern int simple_open(struct inode *inode, struct file *file);
extern int simple_link(struct dentry *, struct inode *, struct dentry *);
extern int simple_unlink(struct inode *, struct dentry *);
extern int simple_rmdir(struct inode *, struct dentry *);
extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
				  struct inode *new_dir, struct dentry *new_dentry);
extern int simple_rename(struct mnt_idmap *, struct inode *,
			 struct dentry *, struct inode *, struct dentry *,
			 unsigned int);
extern void simple_recursive_removal(struct dentry *,
                              void (*callback)(struct dentry *));
extern int noop_fsync(struct file *, loff_t, loff_t, int);
extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
extern int simple_empty(struct dentry *);
extern int simple_write_begin(struct file *file, struct address_space *mapping,
			loff_t pos, unsigned len,
			struct page **pagep, void **fsdata);
extern const struct address_space_operations ram_aops;
extern int always_delete_dentry(const struct dentry *);
extern struct inode *alloc_anon_inode(struct super_block *);
extern int simple_nosetlease(struct file *, long, struct file_lock **, void **);
extern const struct dentry_operations simple_dentry_operations;

extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
extern const struct file_operations simple_dir_operations;
extern const struct inode_operations simple_dir_inode_operations;
extern void make_empty_dir_inode(struct inode *inode);
extern bool is_empty_dir_inode(struct inode *inode);
struct tree_descr { const char *name; const struct file_operations *ops; int mode; };
struct dentry *d_alloc_name(struct dentry *, const char *);
extern int simple_fill_super(struct super_block *, unsigned long,
			     const struct tree_descr *);
extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
extern void simple_release_fs(struct vfsmount **mount, int *count);

extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
			loff_t *ppos, const void *from, size_t available);
extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos,
		const void __user *from, size_t count);

extern int __generic_file_fsync(struct file *, loff_t, loff_t, int);
extern int generic_file_fsync(struct file *, loff_t, loff_t, int);

extern int generic_check_addressable(unsigned, u64);

extern void generic_set_encrypted_ci_d_ops(struct dentry *dentry);

int may_setattr(struct mnt_idmap *idmap, struct inode *inode,
		unsigned int ia_valid);
int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *);
extern int inode_newsize_ok(const struct inode *, loff_t offset);
void setattr_copy(struct mnt_idmap *, struct inode *inode,
		  const struct iattr *attr);

extern int file_update_time(struct file *file);

static inline bool vma_is_dax(const struct vm_area_struct *vma)
{
	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
}

static inline bool vma_is_fsdax(struct vm_area_struct *vma)
{
	struct inode *inode;

	if (!IS_ENABLED(CONFIG_FS_DAX) || !vma->vm_file)
		return false;
	if (!vma_is_dax(vma))
		return false;
	inode = file_inode(vma->vm_file);
	if (S_ISCHR(inode->i_mode))
		return false; /* device-dax */
	return true;
}

static inline int iocb_flags(struct file *file)
{
	int res = 0;
	if (file->f_flags & O_APPEND)
		res |= IOCB_APPEND;
	if (file->f_flags & O_DIRECT)
		res |= IOCB_DIRECT;
	if (file->f_flags & O_DSYNC)
		res |= IOCB_DSYNC;
	if (file->f_flags & __O_SYNC)
		res |= IOCB_SYNC;
	return res;
}

static inline int kiocb_set_rw_flags(struct kiocb *ki, rwf_t flags)
{
	int kiocb_flags = 0;

	/* make sure there's no overlap between RWF and private IOCB flags */
	BUILD_BUG_ON((__force int) RWF_SUPPORTED & IOCB_EVENTFD);

	if (!flags)
		return 0;
	if (unlikely(flags & ~RWF_SUPPORTED))
		return -EOPNOTSUPP;

	if (flags & RWF_NOWAIT) {
		if (!(ki->ki_filp->f_mode & FMODE_NOWAIT))
			return -EOPNOTSUPP;
		kiocb_flags |= IOCB_NOIO;
	}
	kiocb_flags |= (__force int) (flags & RWF_SUPPORTED);
	if (flags & RWF_SYNC)
		kiocb_flags |= IOCB_DSYNC;

	ki->ki_flags |= kiocb_flags;
	return 0;
}

static inline ino_t parent_ino(struct dentry *dentry)
{
	ino_t res;

	/*
	 * Don't strictly need d_lock here? If the parent ino could change
	 * then surely we'd have a deeper race in the caller?
	 */
	spin_lock(&dentry->d_lock);
	res = dentry->d_parent->d_inode->i_ino;
	spin_unlock(&dentry->d_lock);
	return res;
}

/* Transaction based IO helpers */

/*
 * An argresp is stored in an allocated page and holds the
 * size of the argument or response, along with its content
 */
struct simple_transaction_argresp {
	ssize_t size;
	char data[];
};

#define SIMPLE_TRANSACTION_LIMIT (PAGE_SIZE - sizeof(struct simple_transaction_argresp))

char *simple_transaction_get(struct file *file, const char __user *buf,
				size_t size);
ssize_t simple_transaction_read(struct file *file, char __user *buf,
				size_t size, loff_t *pos);
int simple_transaction_release(struct inode *inode, struct file *file);

void simple_transaction_set(struct file *file, size_t n);

/*
 * simple attribute files
 *
 * These attributes behave similar to those in sysfs:
 *
 * Writing to an attribute immediately sets a value, an open file can be
 * written to multiple times.
 *
 * Reading from an attribute creates a buffer from the value that might get
 * read with multiple read calls. When the attribute has been read
 * completely, no further read calls are possible until the file is opened
 * again.
 *
 * All attributes contain a text representation of a numeric value
 * that are accessed with the get() and set() functions.
 */
#define DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, __is_signed)	\
static int __fops ## _open(struct inode *inode, struct file *file)	\
{									\
	__simple_attr_check_format(__fmt, 0ull);			\
	return simple_attr_open(inode, file, __get, __set, __fmt);	\
}									\
static const struct file_operations __fops = {				\
	.owner	 = THIS_MODULE,						\
	.open	 = __fops ## _open,					\
	.release = simple_attr_release,					\
	.read	 = simple_attr_read,					\
	.write	 = (__is_signed) ? simple_attr_write_signed : simple_attr_write,	\
	.llseek	 = generic_file_llseek,					\
}

#define DEFINE_SIMPLE_ATTRIBUTE(__fops, __get, __set, __fmt)		\
	DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, false)

#define DEFINE_SIMPLE_ATTRIBUTE_SIGNED(__fops, __get, __set, __fmt)	\
	DEFINE_SIMPLE_ATTRIBUTE_XSIGNED(__fops, __get, __set, __fmt, true)

static inline __printf(1, 2)
void __simple_attr_check_format(const char *fmt, ...)
{
	/* don't do anything, just let the compiler check the arguments; */
}

int simple_attr_open(struct inode *inode, struct file *file,
		     int (*get)(void *, u64 *), int (*set)(void *, u64),
		     const char *fmt);
int simple_attr_release(struct inode *inode, struct file *file);
ssize_t simple_attr_read(struct file *file, char __user *buf,
			 size_t len, loff_t *ppos);
ssize_t simple_attr_write(struct file *file, const char __user *buf,
			  size_t len, loff_t *ppos);
ssize_t simple_attr_write_signed(struct file *file, const char __user *buf,
				 size_t len, loff_t *ppos);

struct ctl_table;
int __init list_bdev_fs_names(char *buf, size_t size);

#define __FMODE_EXEC		((__force int) FMODE_EXEC)
#define __FMODE_NONOTIFY	((__force int) FMODE_NONOTIFY)

#define ACC_MODE(x) ("\004\002\006\006"[(x)&O_ACCMODE])
#define OPEN_FMODE(flag) ((__force fmode_t)(((flag + 1) & O_ACCMODE) | \
					    (flag & __FMODE_NONOTIFY)))

static inline bool is_sxid(umode_t mode)
{
	return mode & (S_ISUID | S_ISGID);
}

static inline int check_sticky(struct mnt_idmap *idmap,
			       struct inode *dir, struct inode *inode)
{
	if (!(dir->i_mode & S_ISVTX))
		return 0;

	return __check_sticky(idmap, dir, inode);
}

static inline void inode_has_no_xattr(struct inode *inode)
{
	if (!is_sxid(inode->i_mode) && (inode->i_sb->s_flags & SB_NOSEC))
		inode->i_flags |= S_NOSEC;
}

static inline bool is_root_inode(struct inode *inode)
{
	return inode == inode->i_sb->s_root->d_inode;
}

static inline bool dir_emit(struct dir_context *ctx,
			    const char *name, int namelen,
			    u64 ino, unsigned type)
{
	return ctx->actor(ctx, name, namelen, ctx->pos, ino, type);
}
static inline bool dir_emit_dot(struct file *file, struct dir_context *ctx)
{
	return ctx->actor(ctx, ".", 1, ctx->pos,
			  file->f_path.dentry->d_inode->i_ino, DT_DIR);
}
static inline bool dir_emit_dotdot(struct file *file, struct dir_context *ctx)
{
	return ctx->actor(ctx, "..", 2, ctx->pos,
			  parent_ino(file->f_path.dentry), DT_DIR);
}
static inline bool dir_emit_dots(struct file *file, struct dir_context *ctx)
{
	if (ctx->pos == 0) {
		if (!dir_emit_dot(file, ctx))
			return false;
		ctx->pos = 1;
	}
	if (ctx->pos == 1) {
		if (!dir_emit_dotdot(file, ctx))
			return false;
		ctx->pos = 2;
	}
	return true;
}
static inline bool dir_relax(struct inode *inode)
{
	inode_unlock(inode);
	inode_lock(inode);
	return !IS_DEADDIR(inode);
}

static inline bool dir_relax_shared(struct inode *inode)
{
	inode_unlock_shared(inode);
	inode_lock_shared(inode);
	return !IS_DEADDIR(inode);
}

extern bool path_noexec(const struct path *path);
extern void inode_nohighmem(struct inode *inode);

/* mm/fadvise.c */
extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len,
		       int advice);
extern int generic_fadvise(struct file *file, loff_t offset, loff_t len,
			   int advice);

#endif /* _LINUX_FS_H */