summaryrefslogtreecommitdiff
path: root/fs/nfs/dir.c
blob: 3429309962267fb83a5a1712a122b0e9942ada6f (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
// SPDX-License-Identifier: GPL-2.0-only
/*
 *  linux/fs/nfs/dir.c
 *
 *  Copyright (C) 1992  Rick Sladkey
 *
 *  nfs directory handling functions
 *
 * 10 Apr 1996	Added silly rename for unlink	--okir
 * 28 Sep 1996	Improved directory cache --okir
 * 23 Aug 1997  Claus Heine claus@momo.math.rwth-aachen.de 
 *              Re-implemented silly rename for unlink, newly implemented
 *              silly rename for nfs_rename() following the suggestions
 *              of Olaf Kirch (okir) found in this file.
 *              Following Linus comments on my original hack, this version
 *              depends only on the dcache stuff and doesn't touch the inode
 *              layer (iput() and friends).
 *  6 Jun 1999	Cache readdir lookups in the page cache. -DaveM
 */

#include <linux/compat.h>
#include <linux/module.h>
#include <linux/time.h>
#include <linux/errno.h>
#include <linux/stat.h>
#include <linux/fcntl.h>
#include <linux/string.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/sunrpc/clnt.h>
#include <linux/nfs_fs.h>
#include <linux/nfs_mount.h>
#include <linux/pagemap.h>
#include <linux/pagevec.h>
#include <linux/namei.h>
#include <linux/mount.h>
#include <linux/swap.h>
#include <linux/sched.h>
#include <linux/kmemleak.h>
#include <linux/xattr.h>
#include <linux/hash.h>

#include "delegation.h"
#include "iostat.h"
#include "internal.h"
#include "fscache.h"

#include "nfstrace.h"

/* #define NFS_DEBUG_VERBOSE 1 */

static int nfs_opendir(struct inode *, struct file *);
static int nfs_closedir(struct inode *, struct file *);
static int nfs_readdir(struct file *, struct dir_context *);
static int nfs_fsync_dir(struct file *, loff_t, loff_t, int);
static loff_t nfs_llseek_dir(struct file *, loff_t, int);
static void nfs_readdir_clear_array(struct folio *);
static int nfs_do_create(struct inode *dir, struct dentry *dentry,
			 umode_t mode, int open_flags);

const struct file_operations nfs_dir_operations = {
	.llseek		= nfs_llseek_dir,
	.read		= generic_read_dir,
	.iterate_shared	= nfs_readdir,
	.open		= nfs_opendir,
	.release	= nfs_closedir,
	.fsync		= nfs_fsync_dir,
};

const struct address_space_operations nfs_dir_aops = {
	.free_folio = nfs_readdir_clear_array,
};

#define NFS_INIT_DTSIZE PAGE_SIZE

static struct nfs_open_dir_context *
alloc_nfs_open_dir_context(struct inode *dir)
{
	struct nfs_inode *nfsi = NFS_I(dir);
	struct nfs_open_dir_context *ctx;

	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL_ACCOUNT);
	if (ctx != NULL) {
		ctx->attr_gencount = nfsi->attr_gencount;
		ctx->dtsize = NFS_INIT_DTSIZE;
		spin_lock(&dir->i_lock);
		if (list_empty(&nfsi->open_files) &&
		    (nfsi->cache_validity & NFS_INO_DATA_INVAL_DEFER))
			nfs_set_cache_invalid(dir,
					      NFS_INO_INVALID_DATA |
						      NFS_INO_REVAL_FORCED);
		list_add_tail_rcu(&ctx->list, &nfsi->open_files);
		memcpy(ctx->verf, nfsi->cookieverf, sizeof(ctx->verf));
		spin_unlock(&dir->i_lock);
		return ctx;
	}
	return  ERR_PTR(-ENOMEM);
}

static void put_nfs_open_dir_context(struct inode *dir, struct nfs_open_dir_context *ctx)
{
	spin_lock(&dir->i_lock);
	list_del_rcu(&ctx->list);
	spin_unlock(&dir->i_lock);
	kfree_rcu(ctx, rcu_head);
}

/*
 * Open file
 */
static int
nfs_opendir(struct inode *inode, struct file *filp)
{
	int res = 0;
	struct nfs_open_dir_context *ctx;

	dfprintk(FILE, "NFS: open dir(%pD2)\n", filp);

	nfs_inc_stats(inode, NFSIOS_VFSOPEN);

	ctx = alloc_nfs_open_dir_context(inode);
	if (IS_ERR(ctx)) {
		res = PTR_ERR(ctx);
		goto out;
	}
	filp->private_data = ctx;
out:
	return res;
}

static int
nfs_closedir(struct inode *inode, struct file *filp)
{
	put_nfs_open_dir_context(file_inode(filp), filp->private_data);
	return 0;
}

struct nfs_cache_array_entry {
	u64 cookie;
	u64 ino;
	const char *name;
	unsigned int name_len;
	unsigned char d_type;
};

struct nfs_cache_array {
	u64 change_attr;
	u64 last_cookie;
	unsigned int size;
	unsigned char folio_full : 1,
		      folio_is_eof : 1,
		      cookies_are_ordered : 1;
	struct nfs_cache_array_entry array[];
};

struct nfs_readdir_descriptor {
	struct file	*file;
	struct folio	*folio;
	struct dir_context *ctx;
	pgoff_t		folio_index;
	pgoff_t		folio_index_max;
	u64		dir_cookie;
	u64		last_cookie;
	loff_t		current_index;

	__be32		verf[NFS_DIR_VERIFIER_SIZE];
	unsigned long	dir_verifier;
	unsigned long	timestamp;
	unsigned long	gencount;
	unsigned long	attr_gencount;
	unsigned int	cache_entry_index;
	unsigned int	buffer_fills;
	unsigned int	dtsize;
	bool clear_cache;
	bool plus;
	bool eob;
	bool eof;
};

static void nfs_set_dtsize(struct nfs_readdir_descriptor *desc, unsigned int sz)
{
	struct nfs_server *server = NFS_SERVER(file_inode(desc->file));
	unsigned int maxsize = server->dtsize;

	if (sz > maxsize)
		sz = maxsize;
	if (sz < NFS_MIN_FILE_IO_SIZE)
		sz = NFS_MIN_FILE_IO_SIZE;
	desc->dtsize = sz;
}

static void nfs_shrink_dtsize(struct nfs_readdir_descriptor *desc)
{
	nfs_set_dtsize(desc, desc->dtsize >> 1);
}

static void nfs_grow_dtsize(struct nfs_readdir_descriptor *desc)
{
	nfs_set_dtsize(desc, desc->dtsize << 1);
}

static void nfs_readdir_folio_init_array(struct folio *folio, u64 last_cookie,
					 u64 change_attr)
{
	struct nfs_cache_array *array;

	array = kmap_local_folio(folio, 0);
	array->change_attr = change_attr;
	array->last_cookie = last_cookie;
	array->size = 0;
	array->folio_full = 0;
	array->folio_is_eof = 0;
	array->cookies_are_ordered = 1;
	kunmap_local(array);
}

/*
 * we are freeing strings created by nfs_add_to_readdir_array()
 */
static void nfs_readdir_clear_array(struct folio *folio)
{
	struct nfs_cache_array *array;
	unsigned int i;

	array = kmap_local_folio(folio, 0);
	for (i = 0; i < array->size; i++)
		kfree(array->array[i].name);
	array->size = 0;
	kunmap_local(array);
}

static void nfs_readdir_folio_reinit_array(struct folio *folio, u64 last_cookie,
					   u64 change_attr)
{
	nfs_readdir_clear_array(folio);
	nfs_readdir_folio_init_array(folio, last_cookie, change_attr);
}

static struct folio *
nfs_readdir_folio_array_alloc(u64 last_cookie, gfp_t gfp_flags)
{
	struct folio *folio = folio_alloc(gfp_flags, 0);
	if (folio)
		nfs_readdir_folio_init_array(folio, last_cookie, 0);
	return folio;
}

static void nfs_readdir_folio_array_free(struct folio *folio)
{
	if (folio) {
		nfs_readdir_clear_array(folio);
		folio_put(folio);
	}
}

static u64 nfs_readdir_array_index_cookie(struct nfs_cache_array *array)
{
	return array->size == 0 ? array->last_cookie : array->array[0].cookie;
}

static void nfs_readdir_array_set_eof(struct nfs_cache_array *array)
{
	array->folio_is_eof = 1;
	array->folio_full = 1;
}

static bool nfs_readdir_array_is_full(struct nfs_cache_array *array)
{
	return array->folio_full;
}

/*
 * the caller is responsible for freeing qstr.name
 * when called by nfs_readdir_add_to_array, the strings will be freed in
 * nfs_clear_readdir_array()
 */
static const char *nfs_readdir_copy_name(const char *name, unsigned int len)
{
	const char *ret = kmemdup_nul(name, len, GFP_KERNEL);

	/*
	 * Avoid a kmemleak false positive. The pointer to the name is stored
	 * in a page cache page which kmemleak does not scan.
	 */
	if (ret != NULL)
		kmemleak_not_leak(ret);
	return ret;
}

static size_t nfs_readdir_array_maxentries(void)
{
	return (PAGE_SIZE - sizeof(struct nfs_cache_array)) /
	       sizeof(struct nfs_cache_array_entry);
}

/*
 * Check that the next array entry lies entirely within the page bounds
 */
static int nfs_readdir_array_can_expand(struct nfs_cache_array *array)
{
	if (array->folio_full)
		return -ENOSPC;
	if (array->size == nfs_readdir_array_maxentries()) {
		array->folio_full = 1;
		return -ENOSPC;
	}
	return 0;
}

static int nfs_readdir_folio_array_append(struct folio *folio,
					  const struct nfs_entry *entry,
					  u64 *cookie)
{
	struct nfs_cache_array *array;
	struct nfs_cache_array_entry *cache_entry;
	const char *name;
	int ret = -ENOMEM;

	name = nfs_readdir_copy_name(entry->name, entry->len);

	array = kmap_local_folio(folio, 0);
	if (!name)
		goto out;
	ret = nfs_readdir_array_can_expand(array);
	if (ret) {
		kfree(name);
		goto out;
	}

	cache_entry = &array->array[array->size];
	cache_entry->cookie = array->last_cookie;
	cache_entry->ino = entry->ino;
	cache_entry->d_type = entry->d_type;
	cache_entry->name_len = entry->len;
	cache_entry->name = name;
	array->last_cookie = entry->cookie;
	if (array->last_cookie <= cache_entry->cookie)
		array->cookies_are_ordered = 0;
	array->size++;
	if (entry->eof != 0)
		nfs_readdir_array_set_eof(array);
out:
	*cookie = array->last_cookie;
	kunmap_local(array);
	return ret;
}

#define NFS_READDIR_COOKIE_MASK (U32_MAX >> 14)
/*
 * Hash algorithm allowing content addressible access to sequences
 * of directory cookies. Content is addressed by the value of the
 * cookie index of the first readdir entry in a page.
 *
 * We select only the first 18 bits to avoid issues with excessive
 * memory use for the page cache XArray. 18 bits should allow the caching
 * of 262144 pages of sequences of readdir entries. Since each page holds
 * 127 readdir entries for a typical 64-bit system, that works out to a
 * cache of ~ 33 million entries per directory.
 */
static pgoff_t nfs_readdir_folio_cookie_hash(u64 cookie)
{
	if (cookie == 0)
		return 0;
	return hash_64(cookie, 18);
}

static bool nfs_readdir_folio_validate(struct folio *folio, u64 last_cookie,
				       u64 change_attr)
{
	struct nfs_cache_array *array = kmap_local_folio(folio, 0);
	int ret = true;

	if (array->change_attr != change_attr)
		ret = false;
	if (nfs_readdir_array_index_cookie(array) != last_cookie)
		ret = false;
	kunmap_local(array);
	return ret;
}

static void nfs_readdir_folio_unlock_and_put(struct folio *folio)
{
	folio_unlock(folio);
	folio_put(folio);
}

static void nfs_readdir_folio_init_and_validate(struct folio *folio, u64 cookie,
						u64 change_attr)
{
	if (folio_test_uptodate(folio)) {
		if (nfs_readdir_folio_validate(folio, cookie, change_attr))
			return;
		nfs_readdir_clear_array(folio);
	}
	nfs_readdir_folio_init_array(folio, cookie, change_attr);
	folio_mark_uptodate(folio);
}

static struct folio *nfs_readdir_folio_get_locked(struct address_space *mapping,
						  u64 cookie, u64 change_attr)
{
	pgoff_t index = nfs_readdir_folio_cookie_hash(cookie);
	struct folio *folio;

	folio = filemap_grab_folio(mapping, index);
	if (IS_ERR(folio))
		return NULL;
	nfs_readdir_folio_init_and_validate(folio, cookie, change_attr);
	return folio;
}

static u64 nfs_readdir_folio_last_cookie(struct folio *folio)
{
	struct nfs_cache_array *array;
	u64 ret;

	array = kmap_local_folio(folio, 0);
	ret = array->last_cookie;
	kunmap_local(array);
	return ret;
}

static bool nfs_readdir_folio_needs_filling(struct folio *folio)
{
	struct nfs_cache_array *array;
	bool ret;

	array = kmap_local_folio(folio, 0);
	ret = !nfs_readdir_array_is_full(array);
	kunmap_local(array);
	return ret;
}

static void nfs_readdir_folio_set_eof(struct folio *folio)
{
	struct nfs_cache_array *array;

	array = kmap_local_folio(folio, 0);
	nfs_readdir_array_set_eof(array);
	kunmap_local(array);
}

static struct folio *nfs_readdir_folio_get_next(struct address_space *mapping,
						u64 cookie, u64 change_attr)
{
	pgoff_t index = nfs_readdir_folio_cookie_hash(cookie);
	struct folio *folio;

	folio = __filemap_get_folio(mapping, index,
			FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT,
			mapping_gfp_mask(mapping));
	if (IS_ERR(folio))
		return NULL;
	nfs_readdir_folio_init_and_validate(folio, cookie, change_attr);
	if (nfs_readdir_folio_last_cookie(folio) != cookie)
		nfs_readdir_folio_reinit_array(folio, cookie, change_attr);
	return folio;
}

static inline
int is_32bit_api(void)
{
#ifdef CONFIG_COMPAT
	return in_compat_syscall();
#else
	return (BITS_PER_LONG == 32);
#endif
}

static
bool nfs_readdir_use_cookie(const struct file *filp)
{
	if ((filp->f_mode & FMODE_32BITHASH) ||
	    (!(filp->f_mode & FMODE_64BITHASH) && is_32bit_api()))
		return false;
	return true;
}

static void nfs_readdir_seek_next_array(struct nfs_cache_array *array,
					struct nfs_readdir_descriptor *desc)
{
	if (array->folio_full) {
		desc->last_cookie = array->last_cookie;
		desc->current_index += array->size;
		desc->cache_entry_index = 0;
		desc->folio_index++;
	} else
		desc->last_cookie = nfs_readdir_array_index_cookie(array);
}

static void nfs_readdir_rewind_search(struct nfs_readdir_descriptor *desc)
{
	desc->current_index = 0;
	desc->last_cookie = 0;
	desc->folio_index = 0;
}

static int nfs_readdir_search_for_pos(struct nfs_cache_array *array,
				      struct nfs_readdir_descriptor *desc)
{
	loff_t diff = desc->ctx->pos - desc->current_index;
	unsigned int index;

	if (diff < 0)
		goto out_eof;
	if (diff >= array->size) {
		if (array->folio_is_eof)
			goto out_eof;
		nfs_readdir_seek_next_array(array, desc);
		return -EAGAIN;
	}

	index = (unsigned int)diff;
	desc->dir_cookie = array->array[index].cookie;
	desc->cache_entry_index = index;
	return 0;
out_eof:
	desc->eof = true;
	return -EBADCOOKIE;
}

static bool nfs_readdir_array_cookie_in_range(struct nfs_cache_array *array,
					      u64 cookie)
{
	if (!array->cookies_are_ordered)
		return true;
	/* Optimisation for monotonically increasing cookies */
	if (cookie >= array->last_cookie)
		return false;
	if (array->size && cookie < array->array[0].cookie)
		return false;
	return true;
}

static int nfs_readdir_search_for_cookie(struct nfs_cache_array *array,
					 struct nfs_readdir_descriptor *desc)
{
	unsigned int i;
	int status = -EAGAIN;

	if (!nfs_readdir_array_cookie_in_range(array, desc->dir_cookie))
		goto check_eof;

	for (i = 0; i < array->size; i++) {
		if (array->array[i].cookie == desc->dir_cookie) {
			if (nfs_readdir_use_cookie(desc->file))
				desc->ctx->pos = desc->dir_cookie;
			else
				desc->ctx->pos = desc->current_index + i;
			desc->cache_entry_index = i;
			return 0;
		}
	}
check_eof:
	if (array->folio_is_eof) {
		status = -EBADCOOKIE;
		if (desc->dir_cookie == array->last_cookie)
			desc->eof = true;
	} else
		nfs_readdir_seek_next_array(array, desc);
	return status;
}

static int nfs_readdir_search_array(struct nfs_readdir_descriptor *desc)
{
	struct nfs_cache_array *array;
	int status;

	array = kmap_local_folio(desc->folio, 0);

	if (desc->dir_cookie == 0)
		status = nfs_readdir_search_for_pos(array, desc);
	else
		status = nfs_readdir_search_for_cookie(array, desc);

	kunmap_local(array);
	return status;
}

/* Fill a page with xdr information before transferring to the cache page */
static int nfs_readdir_xdr_filler(struct nfs_readdir_descriptor *desc,
				  __be32 *verf, u64 cookie,
				  struct page **pages, size_t bufsize,
				  __be32 *verf_res)
{
	struct inode *inode = file_inode(desc->file);
	struct nfs_readdir_arg arg = {
		.dentry = file_dentry(desc->file),
		.cred = desc->file->f_cred,
		.verf = verf,
		.cookie = cookie,
		.pages = pages,
		.page_len = bufsize,
		.plus = desc->plus,
	};
	struct nfs_readdir_res res = {
		.verf = verf_res,
	};
	unsigned long	timestamp, gencount;
	int		error;

 again:
	timestamp = jiffies;
	gencount = nfs_inc_attr_generation_counter();
	desc->dir_verifier = nfs_save_change_attribute(inode);
	error = NFS_PROTO(inode)->readdir(&arg, &res);
	if (error < 0) {
		/* We requested READDIRPLUS, but the server doesn't grok it */
		if (error == -ENOTSUPP && desc->plus) {
			NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS;
			desc->plus = arg.plus = false;
			goto again;
		}
		goto error;
	}
	desc->timestamp = timestamp;
	desc->gencount = gencount;
error:
	return error;
}

static int xdr_decode(struct nfs_readdir_descriptor *desc,
		      struct nfs_entry *entry, struct xdr_stream *xdr)
{
	struct inode *inode = file_inode(desc->file);
	int error;

	error = NFS_PROTO(inode)->decode_dirent(xdr, entry, desc->plus);
	if (error)
		return error;
	entry->fattr->time_start = desc->timestamp;
	entry->fattr->gencount = desc->gencount;
	return 0;
}

/* Match file and dirent using either filehandle or fileid
 * Note: caller is responsible for checking the fsid
 */
static
int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry)
{
	struct inode *inode;
	struct nfs_inode *nfsi;

	if (d_really_is_negative(dentry))
		return 0;

	inode = d_inode(dentry);
	if (is_bad_inode(inode) || NFS_STALE(inode))
		return 0;

	nfsi = NFS_I(inode);
	if (entry->fattr->fileid != nfsi->fileid)
		return 0;
	if (entry->fh->size && nfs_compare_fh(entry->fh, &nfsi->fh) != 0)
		return 0;
	return 1;
}

#define NFS_READDIR_CACHE_USAGE_THRESHOLD (8UL)

static bool nfs_use_readdirplus(struct inode *dir, struct dir_context *ctx,
				unsigned int cache_hits,
				unsigned int cache_misses)
{
	if (!nfs_server_capable(dir, NFS_CAP_READDIRPLUS))
		return false;
	if (ctx->pos == 0 ||
	    cache_hits + cache_misses > NFS_READDIR_CACHE_USAGE_THRESHOLD)
		return true;
	return false;
}

/*
 * This function is called by the getattr code to request the
 * use of readdirplus to accelerate any future lookups in the same
 * directory.
 */
void nfs_readdir_record_entry_cache_hit(struct inode *dir)
{
	struct nfs_inode *nfsi = NFS_I(dir);
	struct nfs_open_dir_context *ctx;

	if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
	    S_ISDIR(dir->i_mode)) {
		rcu_read_lock();
		list_for_each_entry_rcu (ctx, &nfsi->open_files, list)
			atomic_inc(&ctx->cache_hits);
		rcu_read_unlock();
	}
}

/*
 * This function is mainly for use by nfs_getattr().
 *
 * If this is an 'ls -l', we want to force use of readdirplus.
 */
void nfs_readdir_record_entry_cache_miss(struct inode *dir)
{
	struct nfs_inode *nfsi = NFS_I(dir);
	struct nfs_open_dir_context *ctx;

	if (nfs_server_capable(dir, NFS_CAP_READDIRPLUS) &&
	    S_ISDIR(dir->i_mode)) {
		rcu_read_lock();
		list_for_each_entry_rcu (ctx, &nfsi->open_files, list)
			atomic_inc(&ctx->cache_misses);
		rcu_read_unlock();
	}
}

static void nfs_lookup_advise_force_readdirplus(struct inode *dir,
						unsigned int flags)
{
	if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
		return;
	if (flags & (LOOKUP_EXCL | LOOKUP_PARENT | LOOKUP_REVAL))
		return;
	nfs_readdir_record_entry_cache_miss(dir);
}

static
void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry,
		unsigned long dir_verifier)
{
	struct qstr filename = QSTR_INIT(entry->name, entry->len);
	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
	struct dentry *dentry;
	struct dentry *alias;
	struct inode *inode;
	int status;

	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FILEID))
		return;
	if (!(entry->fattr->valid & NFS_ATTR_FATTR_FSID))
		return;
	if (filename.len == 0)
		return;
	/* Validate that the name doesn't contain any illegal '\0' */
	if (strnlen(filename.name, filename.len) != filename.len)
		return;
	/* ...or '/' */
	if (strnchr(filename.name, filename.len, '/'))
		return;
	if (filename.name[0] == '.') {
		if (filename.len == 1)
			return;
		if (filename.len == 2 && filename.name[1] == '.')
			return;
	}
	filename.hash = full_name_hash(parent, filename.name, filename.len);

	dentry = d_lookup(parent, &filename);
again:
	if (!dentry) {
		dentry = d_alloc_parallel(parent, &filename, &wq);
		if (IS_ERR(dentry))
			return;
	}
	if (!d_in_lookup(dentry)) {
		/* Is there a mountpoint here? If so, just exit */
		if (!nfs_fsid_equal(&NFS_SB(dentry->d_sb)->fsid,
					&entry->fattr->fsid))
			goto out;
		if (nfs_same_file(dentry, entry)) {
			if (!entry->fh->size)
				goto out;
			nfs_set_verifier(dentry, dir_verifier);
			status = nfs_refresh_inode(d_inode(dentry), entry->fattr);
			if (!status)
				nfs_setsecurity(d_inode(dentry), entry->fattr);
			trace_nfs_readdir_lookup_revalidate(d_inode(parent),
							    dentry, 0, status);
			goto out;
		} else {
			trace_nfs_readdir_lookup_revalidate_failed(
				d_inode(parent), dentry, 0);
			d_invalidate(dentry);
			dput(dentry);
			dentry = NULL;
			goto again;
		}
	}
	if (!entry->fh->size) {
		d_lookup_done(dentry);
		goto out;
	}

	inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr);
	alias = d_splice_alias(inode, dentry);
	d_lookup_done(dentry);
	if (alias) {
		if (IS_ERR(alias))
			goto out;
		dput(dentry);
		dentry = alias;
	}
	nfs_set_verifier(dentry, dir_verifier);
	trace_nfs_readdir_lookup(d_inode(parent), dentry, 0);
out:
	dput(dentry);
}

static int nfs_readdir_entry_decode(struct nfs_readdir_descriptor *desc,
				    struct nfs_entry *entry,
				    struct xdr_stream *stream)
{
	int ret;

	if (entry->fattr->label)
		entry->fattr->label->len = NFS4_MAXLABELLEN;
	ret = xdr_decode(desc, entry, stream);
	if (ret || !desc->plus)
		return ret;
	nfs_prime_dcache(file_dentry(desc->file), entry, desc->dir_verifier);
	return 0;
}

/* Perform conversion from xdr to cache array */
static int nfs_readdir_folio_filler(struct nfs_readdir_descriptor *desc,
				    struct nfs_entry *entry,
				    struct page **xdr_pages, unsigned int buflen,
				    struct folio **arrays, size_t narrays,
				    u64 change_attr)
{
	struct address_space *mapping = desc->file->f_mapping;
	struct folio *new, *folio = *arrays;
	struct xdr_stream stream;
	struct page *scratch;
	struct xdr_buf buf;
	u64 cookie;
	int status;

	scratch = alloc_page(GFP_KERNEL);
	if (scratch == NULL)
		return -ENOMEM;

	xdr_init_decode_pages(&stream, &buf, xdr_pages, buflen);
	xdr_set_scratch_page(&stream, scratch);

	do {
		status = nfs_readdir_entry_decode(desc, entry, &stream);
		if (status != 0)
			break;

		status = nfs_readdir_folio_array_append(folio, entry, &cookie);
		if (status != -ENOSPC)
			continue;

		if (folio->mapping != mapping) {
			if (!--narrays)
				break;
			new = nfs_readdir_folio_array_alloc(cookie, GFP_KERNEL);
			if (!new)
				break;
			arrays++;
			*arrays = folio = new;
		} else {
			new = nfs_readdir_folio_get_next(mapping, cookie,
							 change_attr);
			if (!new)
				break;
			if (folio != *arrays)
				nfs_readdir_folio_unlock_and_put(folio);
			folio = new;
		}
		desc->folio_index_max++;
		status = nfs_readdir_folio_array_append(folio, entry, &cookie);
	} while (!status && !entry->eof);

	switch (status) {
	case -EBADCOOKIE:
		if (!entry->eof)
			break;
		nfs_readdir_folio_set_eof(folio);
		fallthrough;
	case -EAGAIN:
		status = 0;
		break;
	case -ENOSPC:
		status = 0;
		if (!desc->plus)
			break;
		while (!nfs_readdir_entry_decode(desc, entry, &stream))
			;
	}

	if (folio != *arrays)
		nfs_readdir_folio_unlock_and_put(folio);

	put_page(scratch);
	return status;
}

static void nfs_readdir_free_pages(struct page **pages, size_t npages)
{
	while (npages--)
		put_page(pages[npages]);
	kfree(pages);
}

/*
 * nfs_readdir_alloc_pages() will allocate pages that must be freed with a call
 * to nfs_readdir_free_pages()
 */
static struct page **nfs_readdir_alloc_pages(size_t npages)
{
	struct page **pages;
	size_t i;

	pages = kmalloc_array(npages, sizeof(*pages), GFP_KERNEL);
	if (!pages)
		return NULL;
	for (i = 0; i < npages; i++) {
		struct page *page = alloc_page(GFP_KERNEL);
		if (page == NULL)
			goto out_freepages;
		pages[i] = page;
	}
	return pages;

out_freepages:
	nfs_readdir_free_pages(pages, i);
	return NULL;
}

static int nfs_readdir_xdr_to_array(struct nfs_readdir_descriptor *desc,
				    __be32 *verf_arg, __be32 *verf_res,
				    struct folio **arrays, size_t narrays)
{
	u64 change_attr;
	struct page **pages;
	struct folio *folio = *arrays;
	struct nfs_entry *entry;
	size_t array_size;
	struct inode *inode = file_inode(desc->file);
	unsigned int dtsize = desc->dtsize;
	unsigned int pglen;
	int status = -ENOMEM;

	entry = kzalloc(sizeof(*entry), GFP_KERNEL);
	if (!entry)
		return -ENOMEM;
	entry->cookie = nfs_readdir_folio_last_cookie(folio);
	entry->fh = nfs_alloc_fhandle();
	entry->fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
	entry->server = NFS_SERVER(inode);
	if (entry->fh == NULL || entry->fattr == NULL)
		goto out;

	array_size = (dtsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
	pages = nfs_readdir_alloc_pages(array_size);
	if (!pages)
		goto out;

	change_attr = inode_peek_iversion_raw(inode);
	status = nfs_readdir_xdr_filler(desc, verf_arg, entry->cookie, pages,
					dtsize, verf_res);
	if (status < 0)
		goto free_pages;

	pglen = status;
	if (pglen != 0)
		status = nfs_readdir_folio_filler(desc, entry, pages, pglen,
						  arrays, narrays, change_attr);
	else
		nfs_readdir_folio_set_eof(folio);
	desc->buffer_fills++;

free_pages:
	nfs_readdir_free_pages(pages, array_size);
out:
	nfs_free_fattr(entry->fattr);
	nfs_free_fhandle(entry->fh);
	kfree(entry);
	return status;
}

static void nfs_readdir_folio_put(struct nfs_readdir_descriptor *desc)
{
	folio_put(desc->folio);
	desc->folio = NULL;
}

static void
nfs_readdir_folio_unlock_and_put_cached(struct nfs_readdir_descriptor *desc)
{
	folio_unlock(desc->folio);
	nfs_readdir_folio_put(desc);
}

static struct folio *
nfs_readdir_folio_get_cached(struct nfs_readdir_descriptor *desc)
{
	struct address_space *mapping = desc->file->f_mapping;
	u64 change_attr = inode_peek_iversion_raw(mapping->host);
	u64 cookie = desc->last_cookie;
	struct folio *folio;

	folio = nfs_readdir_folio_get_locked(mapping, cookie, change_attr);
	if (!folio)
		return NULL;
	if (desc->clear_cache && !nfs_readdir_folio_needs_filling(folio))
		nfs_readdir_folio_reinit_array(folio, cookie, change_attr);
	return folio;
}

/*
 * Returns 0 if desc->dir_cookie was found on page desc->page_index
 * and locks the page to prevent removal from the page cache.
 */
static int find_and_lock_cache_page(struct nfs_readdir_descriptor *desc)
{
	struct inode *inode = file_inode(desc->file);
	struct nfs_inode *nfsi = NFS_I(inode);
	__be32 verf[NFS_DIR_VERIFIER_SIZE];
	int res;

	desc->folio = nfs_readdir_folio_get_cached(desc);
	if (!desc->folio)
		return -ENOMEM;
	if (nfs_readdir_folio_needs_filling(desc->folio)) {
		/* Grow the dtsize if we had to go back for more pages */
		if (desc->folio_index == desc->folio_index_max)
			nfs_grow_dtsize(desc);
		desc->folio_index_max = desc->folio_index;
		trace_nfs_readdir_cache_fill(desc->file, nfsi->cookieverf,
					     desc->last_cookie,
					     desc->folio->index, desc->dtsize);
		res = nfs_readdir_xdr_to_array(desc, nfsi->cookieverf, verf,
					       &desc->folio, 1);
		if (res < 0) {
			nfs_readdir_folio_unlock_and_put_cached(desc);
			trace_nfs_readdir_cache_fill_done(inode, res);
			if (res == -EBADCOOKIE || res == -ENOTSYNC) {
				invalidate_inode_pages2(desc->file->f_mapping);
				nfs_readdir_rewind_search(desc);
				trace_nfs_readdir_invalidate_cache_range(
					inode, 0, MAX_LFS_FILESIZE);
				return -EAGAIN;
			}
			return res;
		}
		/*
		 * Set the cookie verifier if the page cache was empty
		 */
		if (desc->last_cookie == 0 &&
		    memcmp(nfsi->cookieverf, verf, sizeof(nfsi->cookieverf))) {
			memcpy(nfsi->cookieverf, verf,
			       sizeof(nfsi->cookieverf));
			invalidate_inode_pages2_range(desc->file->f_mapping, 1,
						      -1);
			trace_nfs_readdir_invalidate_cache_range(
				inode, 1, MAX_LFS_FILESIZE);
		}
		desc->clear_cache = false;
	}
	res = nfs_readdir_search_array(desc);
	if (res == 0)
		return 0;
	nfs_readdir_folio_unlock_and_put_cached(desc);
	return res;
}

/* Search for desc->dir_cookie from the beginning of the page cache */
static int readdir_search_pagecache(struct nfs_readdir_descriptor *desc)
{
	int res;

	do {
		res = find_and_lock_cache_page(desc);
	} while (res == -EAGAIN);
	return res;
}

#define NFS_READDIR_CACHE_MISS_THRESHOLD (16UL)

/*
 * Once we've found the start of the dirent within a page: fill 'er up...
 */
static void nfs_do_filldir(struct nfs_readdir_descriptor *desc,
			   const __be32 *verf)
{
	struct file	*file = desc->file;
	struct nfs_cache_array *array;
	unsigned int i;
	bool first_emit = !desc->dir_cookie;

	array = kmap_local_folio(desc->folio, 0);
	for (i = desc->cache_entry_index; i < array->size; i++) {
		struct nfs_cache_array_entry *ent;

		/*
		 * nfs_readdir_handle_cache_misses return force clear at
		 * (cache_misses > NFS_READDIR_CACHE_MISS_THRESHOLD) for
		 * readdir heuristic, NFS_READDIR_CACHE_MISS_THRESHOLD + 1
		 * entries need be emitted here.
		 */
		if (first_emit && i > NFS_READDIR_CACHE_MISS_THRESHOLD + 2) {
			desc->eob = true;
			break;
		}

		ent = &array->array[i];
		if (!dir_emit(desc->ctx, ent->name, ent->name_len,
		    nfs_compat_user_ino64(ent->ino), ent->d_type)) {
			desc->eob = true;
			break;
		}
		memcpy(desc->verf, verf, sizeof(desc->verf));
		if (i == array->size - 1) {
			desc->dir_cookie = array->last_cookie;
			nfs_readdir_seek_next_array(array, desc);
		} else {
			desc->dir_cookie = array->array[i + 1].cookie;
			desc->last_cookie = array->array[0].cookie;
		}
		if (nfs_readdir_use_cookie(file))
			desc->ctx->pos = desc->dir_cookie;
		else
			desc->ctx->pos++;
	}
	if (array->folio_is_eof)
		desc->eof = !desc->eob;

	kunmap_local(array);
	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %llu\n",
			(unsigned long long)desc->dir_cookie);
}

/*
 * If we cannot find a cookie in our cache, we suspect that this is
 * because it points to a deleted file, so we ask the server to return
 * whatever it thinks is the next entry. We then feed this to filldir.
 * If all goes well, we should then be able to find our way round the
 * cache on the next call to readdir_search_pagecache();
 *
 * NOTE: we cannot add the anonymous page to the pagecache because
 *	 the data it contains might not be page aligned. Besides,
 *	 we should already have a complete representation of the
 *	 directory in the page cache by the time we get here.
 */
static int uncached_readdir(struct nfs_readdir_descriptor *desc)
{
	struct folio	**arrays;
	size_t		i, sz = 512;
	__be32		verf[NFS_DIR_VERIFIER_SIZE];
	int		status = -ENOMEM;

	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %llu\n",
			(unsigned long long)desc->dir_cookie);

	arrays = kcalloc(sz, sizeof(*arrays), GFP_KERNEL);
	if (!arrays)
		goto out;
	arrays[0] = nfs_readdir_folio_array_alloc(desc->dir_cookie, GFP_KERNEL);
	if (!arrays[0])
		goto out;

	desc->folio_index = 0;
	desc->cache_entry_index = 0;
	desc->last_cookie = desc->dir_cookie;
	desc->folio_index_max = 0;

	trace_nfs_readdir_uncached(desc->file, desc->verf, desc->last_cookie,
				   -1, desc->dtsize);

	status = nfs_readdir_xdr_to_array(desc, desc->verf, verf, arrays, sz);
	if (status < 0) {
		trace_nfs_readdir_uncached_done(file_inode(desc->file), status);
		goto out_free;
	}

	for (i = 0; !desc->eob && i < sz && arrays[i]; i++) {
		desc->folio = arrays[i];
		nfs_do_filldir(desc, verf);
	}
	desc->folio = NULL;

	/*
	 * Grow the dtsize if we have to go back for more pages,
	 * or shrink it if we're reading too many.
	 */
	if (!desc->eof) {
		if (!desc->eob)
			nfs_grow_dtsize(desc);
		else if (desc->buffer_fills == 1 &&
			 i < (desc->folio_index_max >> 1))
			nfs_shrink_dtsize(desc);
	}
out_free:
	for (i = 0; i < sz && arrays[i]; i++)
		nfs_readdir_folio_array_free(arrays[i]);
out:
	if (!nfs_readdir_use_cookie(desc->file))
		nfs_readdir_rewind_search(desc);
	desc->folio_index_max = -1;
	kfree(arrays);
	dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status);
	return status;
}

static bool nfs_readdir_handle_cache_misses(struct inode *inode,
					    struct nfs_readdir_descriptor *desc,
					    unsigned int cache_misses,
					    bool force_clear)
{
	if (desc->ctx->pos == 0 || !desc->plus)
		return false;
	if (cache_misses <= NFS_READDIR_CACHE_MISS_THRESHOLD && !force_clear)
		return false;
	trace_nfs_readdir_force_readdirplus(inode);
	return true;
}

/* The file offset position represents the dirent entry number.  A
   last cookie cache takes care of the common case of reading the
   whole directory.
 */
static int nfs_readdir(struct file *file, struct dir_context *ctx)
{
	struct dentry	*dentry = file_dentry(file);
	struct inode	*inode = d_inode(dentry);
	struct nfs_inode *nfsi = NFS_I(inode);
	struct nfs_open_dir_context *dir_ctx = file->private_data;
	struct nfs_readdir_descriptor *desc;
	unsigned int cache_hits, cache_misses;
	bool force_clear;
	int res;

	dfprintk(FILE, "NFS: readdir(%pD2) starting at cookie %llu\n",
			file, (long long)ctx->pos);
	nfs_inc_stats(inode, NFSIOS_VFSGETDENTS);

	/*
	 * ctx->pos points to the dirent entry number.
	 * *desc->dir_cookie has the cookie for the next entry. We have
	 * to either find the entry with the appropriate number or
	 * revalidate the cookie.
	 */
	nfs_revalidate_mapping(inode, file->f_mapping);

	res = -ENOMEM;
	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
	if (!desc)
		goto out;
	desc->file = file;
	desc->ctx = ctx;
	desc->folio_index_max = -1;

	spin_lock(&file->f_lock);
	desc->dir_cookie = dir_ctx->dir_cookie;
	desc->folio_index = dir_ctx->page_index;
	desc->last_cookie = dir_ctx->last_cookie;
	desc->attr_gencount = dir_ctx->attr_gencount;
	desc->eof = dir_ctx->eof;
	nfs_set_dtsize(desc, dir_ctx->dtsize);
	memcpy(desc->verf, dir_ctx->verf, sizeof(desc->verf));
	cache_hits = atomic_xchg(&dir_ctx->cache_hits, 0);
	cache_misses = atomic_xchg(&dir_ctx->cache_misses, 0);
	force_clear = dir_ctx->force_clear;
	spin_unlock(&file->f_lock);

	if (desc->eof) {
		res = 0;
		goto out_free;
	}

	desc->plus = nfs_use_readdirplus(inode, ctx, cache_hits, cache_misses);
	force_clear = nfs_readdir_handle_cache_misses(inode, desc, cache_misses,
						      force_clear);
	desc->clear_cache = force_clear;

	do {
		res = readdir_search_pagecache(desc);

		if (res == -EBADCOOKIE) {
			res = 0;
			/* This means either end of directory */
			if (desc->dir_cookie && !desc->eof) {
				/* Or that the server has 'lost' a cookie */
				res = uncached_readdir(desc);
				if (res == 0)
					continue;
				if (res == -EBADCOOKIE || res == -ENOTSYNC)
					res = 0;
			}
			break;
		}
		if (res == -ETOOSMALL && desc->plus) {
			nfs_zap_caches(inode);
			desc->plus = false;
			desc->eof = false;
			continue;
		}
		if (res < 0)
			break;

		nfs_do_filldir(desc, nfsi->cookieverf);
		nfs_readdir_folio_unlock_and_put_cached(desc);
		if (desc->folio_index == desc->folio_index_max)
			desc->clear_cache = force_clear;
	} while (!desc->eob && !desc->eof);

	spin_lock(&file->f_lock);
	dir_ctx->dir_cookie = desc->dir_cookie;
	dir_ctx->last_cookie = desc->last_cookie;
	dir_ctx->attr_gencount = desc->attr_gencount;
	dir_ctx->page_index = desc->folio_index;
	dir_ctx->force_clear = force_clear;
	dir_ctx->eof = desc->eof;
	dir_ctx->dtsize = desc->dtsize;
	memcpy(dir_ctx->verf, desc->verf, sizeof(dir_ctx->verf));
	spin_unlock(&file->f_lock);
out_free:
	kfree(desc);

out:
	dfprintk(FILE, "NFS: readdir(%pD2) returns %d\n", file, res);
	return res;
}

static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
{
	struct nfs_open_dir_context *dir_ctx = filp->private_data;

	dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
			filp, offset, whence);

	switch (whence) {
	default:
		return -EINVAL;
	case SEEK_SET:
		if (offset < 0)
			return -EINVAL;
		spin_lock(&filp->f_lock);
		break;
	case SEEK_CUR:
		if (offset == 0)
			return filp->f_pos;
		spin_lock(&filp->f_lock);
		offset += filp->f_pos;
		if (offset < 0) {
			spin_unlock(&filp->f_lock);
			return -EINVAL;
		}
	}
	if (offset != filp->f_pos) {
		filp->f_pos = offset;
		dir_ctx->page_index = 0;
		if (!nfs_readdir_use_cookie(filp)) {
			dir_ctx->dir_cookie = 0;
			dir_ctx->last_cookie = 0;
		} else {
			dir_ctx->dir_cookie = offset;
			dir_ctx->last_cookie = offset;
		}
		dir_ctx->eof = false;
	}
	spin_unlock(&filp->f_lock);
	return offset;
}

/*
 * All directory operations under NFS are synchronous, so fsync()
 * is a dummy operation.
 */
static int nfs_fsync_dir(struct file *filp, loff_t start, loff_t end,
			 int datasync)
{
	dfprintk(FILE, "NFS: fsync dir(%pD2) datasync %d\n", filp, datasync);

	nfs_inc_stats(file_inode(filp), NFSIOS_VFSFSYNC);
	return 0;
}

/**
 * nfs_force_lookup_revalidate - Mark the directory as having changed
 * @dir: pointer to directory inode
 *
 * This forces the revalidation code in nfs_lookup_revalidate() to do a
 * full lookup on all child dentries of 'dir' whenever a change occurs
 * on the server that might have invalidated our dcache.
 *
 * Note that we reserve bit '0' as a tag to let us know when a dentry
 * was revalidated while holding a delegation on its inode.
 *
 * The caller should be holding dir->i_lock
 */
void nfs_force_lookup_revalidate(struct inode *dir)
{
	NFS_I(dir)->cache_change_attribute += 2;
}
EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate);

/**
 * nfs_verify_change_attribute - Detects NFS remote directory changes
 * @dir: pointer to parent directory inode
 * @verf: previously saved change attribute
 *
 * Return "false" if the verifiers doesn't match the change attribute.
 * This would usually indicate that the directory contents have changed on
 * the server, and that any dentries need revalidating.
 */
static bool nfs_verify_change_attribute(struct inode *dir, unsigned long verf)
{
	return (verf & ~1UL) == nfs_save_change_attribute(dir);
}

static void nfs_set_verifier_delegated(unsigned long *verf)
{
	*verf |= 1UL;
}

#if IS_ENABLED(CONFIG_NFS_V4)
static void nfs_unset_verifier_delegated(unsigned long *verf)
{
	*verf &= ~1UL;
}
#endif /* IS_ENABLED(CONFIG_NFS_V4) */

static bool nfs_test_verifier_delegated(unsigned long verf)
{
	return verf & 1;
}

static bool nfs_verifier_is_delegated(struct dentry *dentry)
{
	return nfs_test_verifier_delegated(dentry->d_time);
}

static void nfs_set_verifier_locked(struct dentry *dentry, unsigned long verf)
{
	struct inode *inode = d_inode(dentry);
	struct inode *dir = d_inode_rcu(dentry->d_parent);

	if (!dir || !nfs_verify_change_attribute(dir, verf))
		return;
	if (inode && NFS_PROTO(inode)->have_delegation(inode, FMODE_READ))
		nfs_set_verifier_delegated(&verf);
	dentry->d_time = verf;
}

/**
 * nfs_set_verifier - save a parent directory verifier in the dentry
 * @dentry: pointer to dentry
 * @verf: verifier to save
 *
 * Saves the parent directory verifier in @dentry. If the inode has
 * a delegation, we also tag the dentry as having been revalidated
 * while holding a delegation so that we know we don't have to
 * look it up again after a directory change.
 */
void nfs_set_verifier(struct dentry *dentry, unsigned long verf)
{

	spin_lock(&dentry->d_lock);
	nfs_set_verifier_locked(dentry, verf);
	spin_unlock(&dentry->d_lock);
}
EXPORT_SYMBOL_GPL(nfs_set_verifier);

#if IS_ENABLED(CONFIG_NFS_V4)
/**
 * nfs_clear_verifier_delegated - clear the dir verifier delegation tag
 * @inode: pointer to inode
 *
 * Iterates through the dentries in the inode alias list and clears
 * the tag used to indicate that the dentry has been revalidated
 * while holding a delegation.
 * This function is intended for use when the delegation is being
 * returned or revoked.
 */
void nfs_clear_verifier_delegated(struct inode *inode)
{
	struct dentry *alias;

	if (!inode)
		return;
	spin_lock(&inode->i_lock);
	hlist_for_each_entry(alias, &inode->i_dentry, d_u.d_alias) {
		spin_lock(&alias->d_lock);
		nfs_unset_verifier_delegated(&alias->d_time);
		spin_unlock(&alias->d_lock);
	}
	spin_unlock(&inode->i_lock);
}
EXPORT_SYMBOL_GPL(nfs_clear_verifier_delegated);
#endif /* IS_ENABLED(CONFIG_NFS_V4) */

static int nfs_dentry_verify_change(struct inode *dir, struct dentry *dentry)
{
	if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE) &&
	    d_really_is_negative(dentry))
		return dentry->d_time == inode_peek_iversion_raw(dir);
	return nfs_verify_change_attribute(dir, dentry->d_time);
}

/*
 * A check for whether or not the parent directory has changed.
 * In the case it has, we assume that the dentries are untrustworthy
 * and may need to be looked up again.
 * If rcu_walk prevents us from performing a full check, return 0.
 */
static int nfs_check_verifier(struct inode *dir, struct dentry *dentry,
			      int rcu_walk)
{
	if (IS_ROOT(dentry))
		return 1;
	if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
		return 0;
	if (!nfs_dentry_verify_change(dir, dentry))
		return 0;
	/* Revalidate nfsi->cache_change_attribute before we declare a match */
	if (nfs_mapping_need_revalidate_inode(dir)) {
		if (rcu_walk)
			return 0;
		if (__nfs_revalidate_inode(NFS_SERVER(dir), dir) < 0)
			return 0;
	}
	if (!nfs_dentry_verify_change(dir, dentry))
		return 0;
	return 1;
}

/*
 * Use intent information to check whether or not we're going to do
 * an O_EXCL create using this path component.
 */
static int nfs_is_exclusive_create(struct inode *dir, unsigned int flags)
{
	if (NFS_PROTO(dir)->version == 2)
		return 0;
	return flags & LOOKUP_EXCL;
}

/*
 * Inode and filehandle revalidation for lookups.
 *
 * We force revalidation in the cases where the VFS sets LOOKUP_REVAL,
 * or if the intent information indicates that we're about to open this
 * particular file and the "nocto" mount flag is not set.
 *
 */
static
int nfs_lookup_verify_inode(struct inode *inode, unsigned int flags)
{
	struct nfs_server *server = NFS_SERVER(inode);
	int ret;

	if (IS_AUTOMOUNT(inode))
		return 0;

	if (flags & LOOKUP_OPEN) {
		switch (inode->i_mode & S_IFMT) {
		case S_IFREG:
			/* A NFSv4 OPEN will revalidate later */
			if (server->caps & NFS_CAP_ATOMIC_OPEN)
				goto out;
			fallthrough;
		case S_IFDIR:
			if (server->flags & NFS_MOUNT_NOCTO)
				break;
			/* NFS close-to-open cache consistency validation */
			goto out_force;
		}
	}

	/* VFS wants an on-the-wire revalidation */
	if (flags & LOOKUP_REVAL)
		goto out_force;
out:
	if (inode->i_nlink > 0 ||
	    (inode->i_nlink == 0 &&
	     test_bit(NFS_INO_PRESERVE_UNLINKED, &NFS_I(inode)->flags)))
		return 0;
	else
		return -ESTALE;
out_force:
	if (flags & LOOKUP_RCU)
		return -ECHILD;
	ret = __nfs_revalidate_inode(server, inode);
	if (ret != 0)
		return ret;
	goto out;
}

static void nfs_mark_dir_for_revalidate(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	nfs_set_cache_invalid(inode, NFS_INO_INVALID_CHANGE);
	spin_unlock(&inode->i_lock);
}

/*
 * We judge how long we want to trust negative
 * dentries by looking at the parent inode mtime.
 *
 * If parent mtime has changed, we revalidate, else we wait for a
 * period corresponding to the parent's attribute cache timeout value.
 *
 * If LOOKUP_RCU prevents us from performing a full check, return 1
 * suggesting a reval is needed.
 *
 * Note that when creating a new file, or looking up a rename target,
 * then it shouldn't be necessary to revalidate a negative dentry.
 */
static inline
int nfs_neg_need_reval(struct inode *dir, struct dentry *dentry,
		       unsigned int flags)
{
	if (flags & (LOOKUP_CREATE | LOOKUP_RENAME_TARGET))
		return 0;
	if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG)
		return 1;
	/* Case insensitive server? Revalidate negative dentries */
	if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
		return 1;
	return !nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU);
}

static int
nfs_lookup_revalidate_done(struct inode *dir, struct dentry *dentry,
			   struct inode *inode, int error)
{
	switch (error) {
	case 1:
		break;
	case 0:
		/*
		 * We can't d_drop the root of a disconnected tree:
		 * its d_hash is on the s_anon list and d_drop() would hide
		 * it from shrink_dcache_for_unmount(), leading to busy
		 * inodes on unmount and further oopses.
		 */
		if (inode && IS_ROOT(dentry))
			error = 1;
		break;
	}
	trace_nfs_lookup_revalidate_exit(dir, dentry, 0, error);
	return error;
}

static int
nfs_lookup_revalidate_negative(struct inode *dir, struct dentry *dentry,
			       unsigned int flags)
{
	int ret = 1;
	if (nfs_neg_need_reval(dir, dentry, flags)) {
		if (flags & LOOKUP_RCU)
			return -ECHILD;
		ret = 0;
	}
	return nfs_lookup_revalidate_done(dir, dentry, NULL, ret);
}

static int
nfs_lookup_revalidate_delegated(struct inode *dir, struct dentry *dentry,
				struct inode *inode)
{
	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
}

static int nfs_lookup_revalidate_dentry(struct inode *dir,
					struct dentry *dentry,
					struct inode *inode, unsigned int flags)
{
	struct nfs_fh *fhandle;
	struct nfs_fattr *fattr;
	unsigned long dir_verifier;
	int ret;

	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);

	ret = -ENOMEM;
	fhandle = nfs_alloc_fhandle();
	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode));
	if (fhandle == NULL || fattr == NULL)
		goto out;

	dir_verifier = nfs_save_change_attribute(dir);
	ret = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
	if (ret < 0) {
		switch (ret) {
		case -ESTALE:
		case -ENOENT:
			ret = 0;
			break;
		case -ETIMEDOUT:
			if (NFS_SERVER(inode)->flags & NFS_MOUNT_SOFTREVAL)
				ret = 1;
		}
		goto out;
	}

	/* Request help from readdirplus */
	nfs_lookup_advise_force_readdirplus(dir, flags);

	ret = 0;
	if (nfs_compare_fh(NFS_FH(inode), fhandle))
		goto out;
	if (nfs_refresh_inode(inode, fattr) < 0)
		goto out;

	nfs_setsecurity(inode, fattr);
	nfs_set_verifier(dentry, dir_verifier);

	ret = 1;
out:
	nfs_free_fattr(fattr);
	nfs_free_fhandle(fhandle);

	/*
	 * If the lookup failed despite the dentry change attribute being
	 * a match, then we should revalidate the directory cache.
	 */
	if (!ret && nfs_dentry_verify_change(dir, dentry))
		nfs_mark_dir_for_revalidate(dir);
	return nfs_lookup_revalidate_done(dir, dentry, inode, ret);
}

/*
 * This is called every time the dcache has a lookup hit,
 * and we should check whether we can really trust that
 * lookup.
 *
 * NOTE! The hit can be a negative hit too, don't assume
 * we have an inode!
 *
 * If the parent directory is seen to have changed, we throw out the
 * cached dentry and do a new lookup.
 */
static int
nfs_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
			 unsigned int flags)
{
	struct inode *inode;
	int error;

	nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
	inode = d_inode(dentry);

	if (!inode)
		return nfs_lookup_revalidate_negative(dir, dentry, flags);

	if (is_bad_inode(inode)) {
		dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n",
				__func__, dentry);
		goto out_bad;
	}

	if ((flags & LOOKUP_RENAME_TARGET) && d_count(dentry) < 2 &&
	    nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
		goto out_bad;

	if (nfs_verifier_is_delegated(dentry))
		return nfs_lookup_revalidate_delegated(dir, dentry, inode);

	/* Force a full look up iff the parent directory has changed */
	if (!(flags & (LOOKUP_EXCL | LOOKUP_REVAL)) &&
	    nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
		error = nfs_lookup_verify_inode(inode, flags);
		if (error) {
			if (error == -ESTALE)
				nfs_mark_dir_for_revalidate(dir);
			goto out_bad;
		}
		goto out_valid;
	}

	if (flags & LOOKUP_RCU)
		return -ECHILD;

	if (NFS_STALE(inode))
		goto out_bad;

	return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags);
out_valid:
	return nfs_lookup_revalidate_done(dir, dentry, inode, 1);
out_bad:
	if (flags & LOOKUP_RCU)
		return -ECHILD;
	return nfs_lookup_revalidate_done(dir, dentry, inode, 0);
}

static int
__nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags,
			int (*reval)(struct inode *, struct dentry *, unsigned int))
{
	struct dentry *parent;
	struct inode *dir;
	int ret;

	if (flags & LOOKUP_RCU) {
		if (dentry->d_fsdata == NFS_FSDATA_BLOCKED)
			return -ECHILD;
		parent = READ_ONCE(dentry->d_parent);
		dir = d_inode_rcu(parent);
		if (!dir)
			return -ECHILD;
		ret = reval(dir, dentry, flags);
		if (parent != READ_ONCE(dentry->d_parent))
			return -ECHILD;
	} else {
		/* Wait for unlink to complete */
		wait_var_event(&dentry->d_fsdata,
			       dentry->d_fsdata != NFS_FSDATA_BLOCKED);
		parent = dget_parent(dentry);
		ret = reval(d_inode(parent), dentry, flags);
		dput(parent);
	}
	return ret;
}

static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
	return __nfs_lookup_revalidate(dentry, flags, nfs_do_lookup_revalidate);
}

/*
 * A weaker form of d_revalidate for revalidating just the d_inode(dentry)
 * when we don't really care about the dentry name. This is called when a
 * pathwalk ends on a dentry that was not found via a normal lookup in the
 * parent dir (e.g.: ".", "..", procfs symlinks or mountpoint traversals).
 *
 * In this situation, we just want to verify that the inode itself is OK
 * since the dentry might have changed on the server.
 */
static int nfs_weak_revalidate(struct dentry *dentry, unsigned int flags)
{
	struct inode *inode = d_inode(dentry);
	int error = 0;

	/*
	 * I believe we can only get a negative dentry here in the case of a
	 * procfs-style symlink. Just assume it's correct for now, but we may
	 * eventually need to do something more here.
	 */
	if (!inode) {
		dfprintk(LOOKUPCACHE, "%s: %pd2 has negative inode\n",
				__func__, dentry);
		return 1;
	}

	if (is_bad_inode(inode)) {
		dfprintk(LOOKUPCACHE, "%s: %pd2 has dud inode\n",
				__func__, dentry);
		return 0;
	}

	error = nfs_lookup_verify_inode(inode, flags);
	dfprintk(LOOKUPCACHE, "NFS: %s: inode %lu is %s\n",
			__func__, inode->i_ino, error ? "invalid" : "valid");
	return !error;
}

/*
 * This is called from dput() when d_count is going to 0.
 */
static int nfs_dentry_delete(const struct dentry *dentry)
{
	dfprintk(VFS, "NFS: dentry_delete(%pd2, %x)\n",
		dentry, dentry->d_flags);

	/* Unhash any dentry with a stale inode */
	if (d_really_is_positive(dentry) && NFS_STALE(d_inode(dentry)))
		return 1;

	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
		/* Unhash it, so that ->d_iput() would be called */
		return 1;
	}
	if (!(dentry->d_sb->s_flags & SB_ACTIVE)) {
		/* Unhash it, so that ancestors of killed async unlink
		 * files will be cleaned up during umount */
		return 1;
	}
	return 0;

}

/* Ensure that we revalidate inode->i_nlink */
static void nfs_drop_nlink(struct inode *inode)
{
	spin_lock(&inode->i_lock);
	/* drop the inode if we're reasonably sure this is the last link */
	if (inode->i_nlink > 0)
		drop_nlink(inode);
	NFS_I(inode)->attr_gencount = nfs_inc_attr_generation_counter();
	nfs_set_cache_invalid(
		inode, NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_CTIME |
			       NFS_INO_INVALID_NLINK);
	spin_unlock(&inode->i_lock);
}

/*
 * Called when the dentry loses inode.
 * We use it to clean up silly-renamed files.
 */
static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
{
	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
		nfs_complete_unlink(dentry, inode);
		nfs_drop_nlink(inode);
	}
	iput(inode);
}

static void nfs_d_release(struct dentry *dentry)
{
	/* free cached devname value, if it survived that far */
	if (unlikely(dentry->d_fsdata)) {
		if (dentry->d_flags & DCACHE_NFSFS_RENAMED)
			WARN_ON(1);
		else
			kfree(dentry->d_fsdata);
	}
}

const struct dentry_operations nfs_dentry_operations = {
	.d_revalidate	= nfs_lookup_revalidate,
	.d_weak_revalidate	= nfs_weak_revalidate,
	.d_delete	= nfs_dentry_delete,
	.d_iput		= nfs_dentry_iput,
	.d_automount	= nfs_d_automount,
	.d_release	= nfs_d_release,
};
EXPORT_SYMBOL_GPL(nfs_dentry_operations);

struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags)
{
	struct dentry *res;
	struct inode *inode = NULL;
	struct nfs_fh *fhandle = NULL;
	struct nfs_fattr *fattr = NULL;
	unsigned long dir_verifier;
	int error;

	dfprintk(VFS, "NFS: lookup(%pd2)\n", dentry);
	nfs_inc_stats(dir, NFSIOS_VFSLOOKUP);

	if (unlikely(dentry->d_name.len > NFS_SERVER(dir)->namelen))
		return ERR_PTR(-ENAMETOOLONG);

	/*
	 * If we're doing an exclusive create, optimize away the lookup
	 * but don't hash the dentry.
	 */
	if (nfs_is_exclusive_create(dir, flags) || flags & LOOKUP_RENAME_TARGET)
		return NULL;

	res = ERR_PTR(-ENOMEM);
	fhandle = nfs_alloc_fhandle();
	fattr = nfs_alloc_fattr_with_label(NFS_SERVER(dir));
	if (fhandle == NULL || fattr == NULL)
		goto out;

	dir_verifier = nfs_save_change_attribute(dir);
	trace_nfs_lookup_enter(dir, dentry, flags);
	error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
	if (error == -ENOENT) {
		if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
			dir_verifier = inode_peek_iversion_raw(dir);
		goto no_entry;
	}
	if (error < 0) {
		res = ERR_PTR(error);
		goto out;
	}
	inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
	res = ERR_CAST(inode);
	if (IS_ERR(res))
		goto out;

	/* Notify readdir to use READDIRPLUS */
	nfs_lookup_advise_force_readdirplus(dir, flags);

no_entry:
	res = d_splice_alias(inode, dentry);
	if (res != NULL) {
		if (IS_ERR(res))
			goto out;
		dentry = res;
	}
	nfs_set_verifier(dentry, dir_verifier);
out:
	trace_nfs_lookup_exit(dir, dentry, flags, PTR_ERR_OR_ZERO(res));
	nfs_free_fattr(fattr);
	nfs_free_fhandle(fhandle);
	return res;
}
EXPORT_SYMBOL_GPL(nfs_lookup);

void nfs_d_prune_case_insensitive_aliases(struct inode *inode)
{
	/* Case insensitive server? Revalidate dentries */
	if (inode && nfs_server_capable(inode, NFS_CAP_CASE_INSENSITIVE))
		d_prune_aliases(inode);
}
EXPORT_SYMBOL_GPL(nfs_d_prune_case_insensitive_aliases);

#if IS_ENABLED(CONFIG_NFS_V4)
static int nfs4_lookup_revalidate(struct dentry *, unsigned int);

const struct dentry_operations nfs4_dentry_operations = {
	.d_revalidate	= nfs4_lookup_revalidate,
	.d_weak_revalidate	= nfs_weak_revalidate,
	.d_delete	= nfs_dentry_delete,
	.d_iput		= nfs_dentry_iput,
	.d_automount	= nfs_d_automount,
	.d_release	= nfs_d_release,
};
EXPORT_SYMBOL_GPL(nfs4_dentry_operations);

static struct nfs_open_context *create_nfs_open_context(struct dentry *dentry, int open_flags, struct file *filp)
{
	return alloc_nfs_open_context(dentry, flags_to_mode(open_flags), filp);
}

static int do_open(struct inode *inode, struct file *filp)
{
	nfs_fscache_open_file(inode, filp);
	return 0;
}

static int nfs_finish_open(struct nfs_open_context *ctx,
			   struct dentry *dentry,
			   struct file *file, unsigned open_flags)
{
	int err;

	err = finish_open(file, dentry, do_open);
	if (err)
		goto out;
	if (S_ISREG(file_inode(file)->i_mode))
		nfs_file_set_open_context(file, ctx);
	else
		err = -EOPENSTALE;
out:
	return err;
}

int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
		    struct file *file, unsigned open_flags,
		    umode_t mode)
{
	DECLARE_WAIT_QUEUE_HEAD_ONSTACK(wq);
	struct nfs_open_context *ctx;
	struct dentry *res;
	struct iattr attr = { .ia_valid = ATTR_OPEN };
	struct inode *inode;
	unsigned int lookup_flags = 0;
	unsigned long dir_verifier;
	bool switched = false;
	int created = 0;
	int err;

	/* Expect a negative dentry */
	BUG_ON(d_inode(dentry));

	dfprintk(VFS, "NFS: atomic_open(%s/%lu), %pd\n",
			dir->i_sb->s_id, dir->i_ino, dentry);

	err = nfs_check_flags(open_flags);
	if (err)
		return err;

	/* NFS only supports OPEN on regular files */
	if ((open_flags & O_DIRECTORY)) {
		if (!d_in_lookup(dentry)) {
			/*
			 * Hashed negative dentry with O_DIRECTORY: dentry was
			 * revalidated and is fine, no need to perform lookup
			 * again
			 */
			return -ENOENT;
		}
		lookup_flags = LOOKUP_OPEN|LOOKUP_DIRECTORY;
		goto no_open;
	}

	if (dentry->d_name.len > NFS_SERVER(dir)->namelen)
		return -ENAMETOOLONG;

	if (open_flags & O_CREAT) {
		struct nfs_server *server = NFS_SERVER(dir);

		if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK))
			mode &= ~current_umask();

		attr.ia_valid |= ATTR_MODE;
		attr.ia_mode = mode;
	}
	if (open_flags & O_TRUNC) {
		attr.ia_valid |= ATTR_SIZE;
		attr.ia_size = 0;
	}

	if (!(open_flags & O_CREAT) && !d_in_lookup(dentry)) {
		d_drop(dentry);
		switched = true;
		dentry = d_alloc_parallel(dentry->d_parent,
					  &dentry->d_name, &wq);
		if (IS_ERR(dentry))
			return PTR_ERR(dentry);
		if (unlikely(!d_in_lookup(dentry)))
			return finish_no_open(file, dentry);
	}

	ctx = create_nfs_open_context(dentry, open_flags, file);
	err = PTR_ERR(ctx);
	if (IS_ERR(ctx))
		goto out;

	trace_nfs_atomic_open_enter(dir, ctx, open_flags);
	inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr, &created);
	if (created)
		file->f_mode |= FMODE_CREATED;
	if (IS_ERR(inode)) {
		err = PTR_ERR(inode);
		trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
		put_nfs_open_context(ctx);
		d_drop(dentry);
		switch (err) {
		case -ENOENT:
			d_splice_alias(NULL, dentry);
			if (nfs_server_capable(dir, NFS_CAP_CASE_INSENSITIVE))
				dir_verifier = inode_peek_iversion_raw(dir);
			else
				dir_verifier = nfs_save_change_attribute(dir);
			nfs_set_verifier(dentry, dir_verifier);
			break;
		case -EISDIR:
		case -ENOTDIR:
			goto no_open;
		case -ELOOP:
			if (!(open_flags & O_NOFOLLOW))
				goto no_open;
			break;
			/* case -EINVAL: */
		default:
			break;
		}
		goto out;
	}
	file->f_mode |= FMODE_CAN_ODIRECT;

	err = nfs_finish_open(ctx, ctx->dentry, file, open_flags);
	trace_nfs_atomic_open_exit(dir, ctx, open_flags, err);
	put_nfs_open_context(ctx);
out:
	if (unlikely(switched)) {
		d_lookup_done(dentry);
		dput(dentry);
	}
	return err;

no_open:
	res = nfs_lookup(dir, dentry, lookup_flags);
	if (!res) {
		inode = d_inode(dentry);
		if ((lookup_flags & LOOKUP_DIRECTORY) && inode &&
		    !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)))
			res = ERR_PTR(-ENOTDIR);
		else if (inode && S_ISREG(inode->i_mode))
			res = ERR_PTR(-EOPENSTALE);
	} else if (!IS_ERR(res)) {
		inode = d_inode(res);
		if ((lookup_flags & LOOKUP_DIRECTORY) && inode &&
		    !(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) {
			dput(res);
			res = ERR_PTR(-ENOTDIR);
		} else if (inode && S_ISREG(inode->i_mode)) {
			dput(res);
			res = ERR_PTR(-EOPENSTALE);
		}
	}
	if (switched) {
		d_lookup_done(dentry);
		if (!res)
			res = dentry;
		else
			dput(dentry);
	}
	if (IS_ERR(res))
		return PTR_ERR(res);
	return finish_no_open(file, res);
}
EXPORT_SYMBOL_GPL(nfs_atomic_open);

static int
nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
			  unsigned int flags)
{
	struct inode *inode;

	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);

	if (!(flags & LOOKUP_OPEN) || (flags & LOOKUP_DIRECTORY))
		goto full_reval;
	if (d_mountpoint(dentry))
		goto full_reval;

	inode = d_inode(dentry);

	/* We can't create new files in nfs_open_revalidate(), so we
	 * optimize away revalidation of negative dentries.
	 */
	if (inode == NULL)
		goto full_reval;

	if (nfs_verifier_is_delegated(dentry))
		return nfs_lookup_revalidate_delegated(dir, dentry, inode);

	/* NFS only supports OPEN on regular files */
	if (!S_ISREG(inode->i_mode))
		goto full_reval;

	/* We cannot do exclusive creation on a positive dentry */
	if (flags & (LOOKUP_EXCL | LOOKUP_REVAL))
		goto reval_dentry;

	/* Check if the directory changed */
	if (!nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU))
		goto reval_dentry;

	/* Let f_op->open() actually open (and revalidate) the file */
	return 1;
reval_dentry:
	if (flags & LOOKUP_RCU)
		return -ECHILD;
	return nfs_lookup_revalidate_dentry(dir, dentry, inode, flags);

full_reval:
	return nfs_do_lookup_revalidate(dir, dentry, flags);
}

static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags)
{
	return __nfs_lookup_revalidate(dentry, flags,
			nfs4_do_lookup_revalidate);
}

#endif /* CONFIG_NFSV4 */

int nfs_atomic_open_v23(struct inode *dir, struct dentry *dentry,
			struct file *file, unsigned int open_flags,
			umode_t mode)
{

	/* Same as look+open from lookup_open(), but with different O_TRUNC
	 * handling.
	 */
	int error = 0;

	if (open_flags & O_CREAT) {
		file->f_mode |= FMODE_CREATED;
		error = nfs_do_create(dir, dentry, mode, open_flags);
		if (error)
			return error;
		return finish_open(file, dentry, NULL);
	} else if (d_in_lookup(dentry)) {
		/* The only flags nfs_lookup considers are
		 * LOOKUP_EXCL and LOOKUP_RENAME_TARGET, and
		 * we want those to be zero so the lookup isn't skipped.
		 */
		struct dentry *res = nfs_lookup(dir, dentry, 0);

		d_lookup_done(dentry);
		if (unlikely(res)) {
			if (IS_ERR(res))
				return PTR_ERR(res);
			return finish_no_open(file, res);
		}
	}
	return finish_no_open(file, NULL);

}
EXPORT_SYMBOL_GPL(nfs_atomic_open_v23);

struct dentry *
nfs_add_or_obtain(struct dentry *dentry, struct nfs_fh *fhandle,
				struct nfs_fattr *fattr)
{
	struct dentry *parent = dget_parent(dentry);
	struct inode *dir = d_inode(parent);
	struct inode *inode;
	struct dentry *d;
	int error;

	d_drop(dentry);

	if (fhandle->size == 0) {
		error = NFS_PROTO(dir)->lookup(dir, dentry, fhandle, fattr);
		if (error)
			goto out_error;
	}
	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
	if (!(fattr->valid & NFS_ATTR_FATTR)) {
		struct nfs_server *server = NFS_SB(dentry->d_sb);
		error = server->nfs_client->rpc_ops->getattr(server, fhandle,
				fattr, NULL);
		if (error < 0)
			goto out_error;
	}
	inode = nfs_fhget(dentry->d_sb, fhandle, fattr);
	d = d_splice_alias(inode, dentry);
out:
	dput(parent);
	return d;
out_error:
	d = ERR_PTR(error);
	goto out;
}
EXPORT_SYMBOL_GPL(nfs_add_or_obtain);

/*
 * Code common to create, mkdir, and mknod.
 */
int nfs_instantiate(struct dentry *dentry, struct nfs_fh *fhandle,
				struct nfs_fattr *fattr)
{
	struct dentry *d;

	d = nfs_add_or_obtain(dentry, fhandle, fattr);
	if (IS_ERR(d))
		return PTR_ERR(d);

	/* Callers don't care */
	dput(d);
	return 0;
}
EXPORT_SYMBOL_GPL(nfs_instantiate);

/*
 * Following a failed create operation, we drop the dentry rather
 * than retain a negative dentry. This avoids a problem in the event
 * that the operation succeeded on the server, but an error in the
 * reply path made it appear to have failed.
 */
static int nfs_do_create(struct inode *dir, struct dentry *dentry,
			 umode_t mode, int open_flags)
{
	struct iattr attr;
	int error;

	open_flags |= O_CREAT;

	dfprintk(VFS, "NFS: create(%s/%lu), %pd\n",
			dir->i_sb->s_id, dir->i_ino, dentry);

	attr.ia_mode = mode;
	attr.ia_valid = ATTR_MODE;
	if (open_flags & O_TRUNC) {
		attr.ia_size = 0;
		attr.ia_valid |= ATTR_SIZE;
	}

	trace_nfs_create_enter(dir, dentry, open_flags);
	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags);
	trace_nfs_create_exit(dir, dentry, open_flags, error);
	if (error != 0)
		goto out_err;
	return 0;
out_err:
	d_drop(dentry);
	return error;
}

int nfs_create(struct mnt_idmap *idmap, struct inode *dir,
	       struct dentry *dentry, umode_t mode, bool excl)
{
	return nfs_do_create(dir, dentry, mode, excl ? O_EXCL : 0);
}
EXPORT_SYMBOL_GPL(nfs_create);

/*
 * See comments for nfs_proc_create regarding failed operations.
 */
int
nfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
	  struct dentry *dentry, umode_t mode, dev_t rdev)
{
	struct iattr attr;
	int status;

	dfprintk(VFS, "NFS: mknod(%s/%lu), %pd\n",
			dir->i_sb->s_id, dir->i_ino, dentry);

	attr.ia_mode = mode;
	attr.ia_valid = ATTR_MODE;

	trace_nfs_mknod_enter(dir, dentry);
	status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev);
	trace_nfs_mknod_exit(dir, dentry, status);
	if (status != 0)
		goto out_err;
	return 0;
out_err:
	d_drop(dentry);
	return status;
}
EXPORT_SYMBOL_GPL(nfs_mknod);

/*
 * See comments for nfs_proc_create regarding failed operations.
 */
int nfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
	      struct dentry *dentry, umode_t mode)
{
	struct iattr attr;
	int error;

	dfprintk(VFS, "NFS: mkdir(%s/%lu), %pd\n",
			dir->i_sb->s_id, dir->i_ino, dentry);

	attr.ia_valid = ATTR_MODE;
	attr.ia_mode = mode | S_IFDIR;

	trace_nfs_mkdir_enter(dir, dentry);
	error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr);
	trace_nfs_mkdir_exit(dir, dentry, error);
	if (error != 0)
		goto out_err;
	return 0;
out_err:
	d_drop(dentry);
	return error;
}
EXPORT_SYMBOL_GPL(nfs_mkdir);

static void nfs_dentry_handle_enoent(struct dentry *dentry)
{
	if (simple_positive(dentry))
		d_delete(dentry);
}

static void nfs_dentry_remove_handle_error(struct inode *dir,
					   struct dentry *dentry, int error)
{
	switch (error) {
	case -ENOENT:
		if (d_really_is_positive(dentry))
			d_delete(dentry);
		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
		break;
	case 0:
		nfs_d_prune_case_insensitive_aliases(d_inode(dentry));
		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
	}
}

int nfs_rmdir(struct inode *dir, struct dentry *dentry)
{
	int error;

	dfprintk(VFS, "NFS: rmdir(%s/%lu), %pd\n",
			dir->i_sb->s_id, dir->i_ino, dentry);

	trace_nfs_rmdir_enter(dir, dentry);
	if (d_really_is_positive(dentry)) {
		down_write(&NFS_I(d_inode(dentry))->rmdir_sem);
		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
		/* Ensure the VFS deletes this inode */
		switch (error) {
		case 0:
			clear_nlink(d_inode(dentry));
			break;
		case -ENOENT:
			nfs_dentry_handle_enoent(dentry);
		}
		up_write(&NFS_I(d_inode(dentry))->rmdir_sem);
	} else
		error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
	nfs_dentry_remove_handle_error(dir, dentry, error);
	trace_nfs_rmdir_exit(dir, dentry, error);

	return error;
}
EXPORT_SYMBOL_GPL(nfs_rmdir);

/*
 * Remove a file after making sure there are no pending writes,
 * and after checking that the file has only one user. 
 *
 * We invalidate the attribute cache and free the inode prior to the operation
 * to avoid possible races if the server reuses the inode.
 */
static int nfs_safe_remove(struct dentry *dentry)
{
	struct inode *dir = d_inode(dentry->d_parent);
	struct inode *inode = d_inode(dentry);
	int error = -EBUSY;
		
	dfprintk(VFS, "NFS: safe_remove(%pd2)\n", dentry);

	/* If the dentry was sillyrenamed, we simply call d_delete() */
	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
		error = 0;
		goto out;
	}

	trace_nfs_remove_enter(dir, dentry);
	if (inode != NULL) {
		error = NFS_PROTO(dir)->remove(dir, dentry);
		if (error == 0)
			nfs_drop_nlink(inode);
	} else
		error = NFS_PROTO(dir)->remove(dir, dentry);
	if (error == -ENOENT)
		nfs_dentry_handle_enoent(dentry);
	trace_nfs_remove_exit(dir, dentry, error);
out:
	return error;
}

/*  We do silly rename. In case sillyrename() returns -EBUSY, the inode
 *  belongs to an active ".nfs..." file and we return -EBUSY.
 *
 *  If sillyrename() returns 0, we do nothing, otherwise we unlink.
 */
int nfs_unlink(struct inode *dir, struct dentry *dentry)
{
	int error;

	dfprintk(VFS, "NFS: unlink(%s/%lu, %pd)\n", dir->i_sb->s_id,
		dir->i_ino, dentry);

	trace_nfs_unlink_enter(dir, dentry);
	spin_lock(&dentry->d_lock);
	if (d_count(dentry) > 1 && !test_bit(NFS_INO_PRESERVE_UNLINKED,
					     &NFS_I(d_inode(dentry))->flags)) {
		spin_unlock(&dentry->d_lock);
		/* Start asynchronous writeout of the inode */
		write_inode_now(d_inode(dentry), 0);
		error = nfs_sillyrename(dir, dentry);
		goto out;
	}
	/* We must prevent any concurrent open until the unlink
	 * completes.  ->d_revalidate will wait for ->d_fsdata
	 * to clear.  We set it here to ensure no lookup succeeds until
	 * the unlink is complete on the server.
	 */
	error = -ETXTBSY;
	if (WARN_ON(dentry->d_flags & DCACHE_NFSFS_RENAMED) ||
	    WARN_ON(dentry->d_fsdata == NFS_FSDATA_BLOCKED)) {
		spin_unlock(&dentry->d_lock);
		goto out;
	}
	/* old devname */
	kfree(dentry->d_fsdata);
	dentry->d_fsdata = NFS_FSDATA_BLOCKED;

	spin_unlock(&dentry->d_lock);
	error = nfs_safe_remove(dentry);
	nfs_dentry_remove_handle_error(dir, dentry, error);
	dentry->d_fsdata = NULL;
	wake_up_var(&dentry->d_fsdata);
out:
	trace_nfs_unlink_exit(dir, dentry, error);
	return error;
}
EXPORT_SYMBOL_GPL(nfs_unlink);

/*
 * To create a symbolic link, most file systems instantiate a new inode,
 * add a page to it containing the path, then write it out to the disk
 * using prepare_write/commit_write.
 *
 * Unfortunately the NFS client can't create the in-core inode first
 * because it needs a file handle to create an in-core inode (see
 * fs/nfs/inode.c:nfs_fhget).  We only have a file handle *after* the
 * symlink request has completed on the server.
 *
 * So instead we allocate a raw page, copy the symname into it, then do
 * the SYMLINK request with the page as the buffer.  If it succeeds, we
 * now have a new file handle and can instantiate an in-core NFS inode
 * and move the raw page into its mapping.
 */
int nfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
		struct dentry *dentry, const char *symname)
{
	struct folio *folio;
	char *kaddr;
	struct iattr attr;
	unsigned int pathlen = strlen(symname);
	int error;

	dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s)\n", dir->i_sb->s_id,
		dir->i_ino, dentry, symname);

	if (pathlen > PAGE_SIZE)
		return -ENAMETOOLONG;

	attr.ia_mode = S_IFLNK | S_IRWXUGO;
	attr.ia_valid = ATTR_MODE;

	folio = folio_alloc(GFP_USER, 0);
	if (!folio)
		return -ENOMEM;

	kaddr = folio_address(folio);
	memcpy(kaddr, symname, pathlen);
	if (pathlen < PAGE_SIZE)
		memset(kaddr + pathlen, 0, PAGE_SIZE - pathlen);

	trace_nfs_symlink_enter(dir, dentry);
	error = NFS_PROTO(dir)->symlink(dir, dentry, folio, pathlen, &attr);
	trace_nfs_symlink_exit(dir, dentry, error);
	if (error != 0) {
		dfprintk(VFS, "NFS: symlink(%s/%lu, %pd, %s) error %d\n",
			dir->i_sb->s_id, dir->i_ino,
			dentry, symname, error);
		d_drop(dentry);
		folio_put(folio);
		return error;
	}

	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));

	/*
	 * No big deal if we can't add this page to the page cache here.
	 * READLINK will get the missing page from the server if needed.
	 */
	if (filemap_add_folio(d_inode(dentry)->i_mapping, folio, 0,
							GFP_KERNEL) == 0) {
		folio_mark_uptodate(folio);
		folio_unlock(folio);
	}

	folio_put(folio);
	return 0;
}
EXPORT_SYMBOL_GPL(nfs_symlink);

int
nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
	struct inode *inode = d_inode(old_dentry);
	int error;

	dfprintk(VFS, "NFS: link(%pd2 -> %pd2)\n",
		old_dentry, dentry);

	trace_nfs_link_enter(inode, dir, dentry);
	d_drop(dentry);
	if (S_ISREG(inode->i_mode))
		nfs_sync_inode(inode);
	error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
	if (error == 0) {
		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
		ihold(inode);
		d_add(dentry, inode);
	}
	trace_nfs_link_exit(inode, dir, dentry, error);
	return error;
}
EXPORT_SYMBOL_GPL(nfs_link);

static void
nfs_unblock_rename(struct rpc_task *task, struct nfs_renamedata *data)
{
	struct dentry *new_dentry = data->new_dentry;

	new_dentry->d_fsdata = NULL;
	wake_up_var(&new_dentry->d_fsdata);
}

/*
 * RENAME
 * FIXME: Some nfsds, like the Linux user space nfsd, may generate a
 * different file handle for the same inode after a rename (e.g. when
 * moving to a different directory). A fail-safe method to do so would
 * be to look up old_dir/old_name, create a link to new_dir/new_name and
 * rename the old file using the sillyrename stuff. This way, the original
 * file in old_dir will go away when the last process iput()s the inode.
 *
 * FIXED.
 * 
 * It actually works quite well. One needs to have the possibility for
 * at least one ".nfs..." file in each directory the file ever gets
 * moved or linked to which happens automagically with the new
 * implementation that only depends on the dcache stuff instead of
 * using the inode layer
 *
 * Unfortunately, things are a little more complicated than indicated
 * above. For a cross-directory move, we want to make sure we can get
 * rid of the old inode after the operation.  This means there must be
 * no pending writes (if it's a file), and the use count must be 1.
 * If these conditions are met, we can drop the dentries before doing
 * the rename.
 */
int nfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
	       struct dentry *old_dentry, struct inode *new_dir,
	       struct dentry *new_dentry, unsigned int flags)
{
	struct inode *old_inode = d_inode(old_dentry);
	struct inode *new_inode = d_inode(new_dentry);
	struct dentry *dentry = NULL;
	struct rpc_task *task;
	bool must_unblock = false;
	int error = -EBUSY;

	if (flags)
		return -EINVAL;

	dfprintk(VFS, "NFS: rename(%pd2 -> %pd2, ct=%d)\n",
		 old_dentry, new_dentry,
		 d_count(new_dentry));

	trace_nfs_rename_enter(old_dir, old_dentry, new_dir, new_dentry);
	/*
	 * For non-directories, check whether the target is busy and if so,
	 * make a copy of the dentry and then do a silly-rename. If the
	 * silly-rename succeeds, the copied dentry is hashed and becomes
	 * the new target.
	 */
	if (new_inode && !S_ISDIR(new_inode->i_mode)) {
		/* We must prevent any concurrent open until the unlink
		 * completes.  ->d_revalidate will wait for ->d_fsdata
		 * to clear.  We set it here to ensure no lookup succeeds until
		 * the unlink is complete on the server.
		 */
		error = -ETXTBSY;
		if (WARN_ON(new_dentry->d_flags & DCACHE_NFSFS_RENAMED) ||
		    WARN_ON(new_dentry->d_fsdata == NFS_FSDATA_BLOCKED))
			goto out;
		if (new_dentry->d_fsdata) {
			/* old devname */
			kfree(new_dentry->d_fsdata);
			new_dentry->d_fsdata = NULL;
		}

		spin_lock(&new_dentry->d_lock);
		if (d_count(new_dentry) > 2) {
			int err;

			spin_unlock(&new_dentry->d_lock);

			/* copy the target dentry's name */
			dentry = d_alloc(new_dentry->d_parent,
					 &new_dentry->d_name);
			if (!dentry)
				goto out;

			/* silly-rename the existing target ... */
			err = nfs_sillyrename(new_dir, new_dentry);
			if (err)
				goto out;

			new_dentry = dentry;
			new_inode = NULL;
		} else {
			new_dentry->d_fsdata = NFS_FSDATA_BLOCKED;
			must_unblock = true;
			spin_unlock(&new_dentry->d_lock);
		}

	}

	if (S_ISREG(old_inode->i_mode))
		nfs_sync_inode(old_inode);
	task = nfs_async_rename(old_dir, new_dir, old_dentry, new_dentry,
				must_unblock ? nfs_unblock_rename : NULL);
	if (IS_ERR(task)) {
		error = PTR_ERR(task);
		goto out;
	}

	error = rpc_wait_for_completion_task(task);
	if (error != 0) {
		((struct nfs_renamedata *)task->tk_calldata)->cancelled = 1;
		/* Paired with the atomic_dec_and_test() barrier in rpc_do_put_task() */
		smp_wmb();
	} else
		error = task->tk_status;
	rpc_put_task(task);
	/* Ensure the inode attributes are revalidated */
	if (error == 0) {
		spin_lock(&old_inode->i_lock);
		NFS_I(old_inode)->attr_gencount = nfs_inc_attr_generation_counter();
		nfs_set_cache_invalid(old_inode, NFS_INO_INVALID_CHANGE |
							 NFS_INO_INVALID_CTIME |
							 NFS_INO_REVAL_FORCED);
		spin_unlock(&old_inode->i_lock);
	}
out:
	trace_nfs_rename_exit(old_dir, old_dentry,
			new_dir, new_dentry, error);
	if (!error) {
		if (new_inode != NULL)
			nfs_drop_nlink(new_inode);
		/*
		 * The d_move() should be here instead of in an async RPC completion
		 * handler because we need the proper locks to move the dentry.  If
		 * we're interrupted by a signal, the async RPC completion handler
		 * should mark the directories for revalidation.
		 */
		d_move(old_dentry, new_dentry);
		nfs_set_verifier(old_dentry,
					nfs_save_change_attribute(new_dir));
	} else if (error == -ENOENT)
		nfs_dentry_handle_enoent(old_dentry);

	/* new dentry created? */
	if (dentry)
		dput(dentry);
	return error;
}
EXPORT_SYMBOL_GPL(nfs_rename);

static DEFINE_SPINLOCK(nfs_access_lru_lock);
static LIST_HEAD(nfs_access_lru_list);
static atomic_long_t nfs_access_nr_entries;

static unsigned long nfs_access_max_cachesize = 4*1024*1024;
module_param(nfs_access_max_cachesize, ulong, 0644);
MODULE_PARM_DESC(nfs_access_max_cachesize, "NFS access maximum total cache length");

static void nfs_access_free_entry(struct nfs_access_entry *entry)
{
	put_group_info(entry->group_info);
	kfree_rcu(entry, rcu_head);
	smp_mb__before_atomic();
	atomic_long_dec(&nfs_access_nr_entries);
	smp_mb__after_atomic();
}

static void nfs_access_free_list(struct list_head *head)
{
	struct nfs_access_entry *cache;

	while (!list_empty(head)) {
		cache = list_entry(head->next, struct nfs_access_entry, lru);
		list_del(&cache->lru);
		nfs_access_free_entry(cache);
	}
}

static unsigned long
nfs_do_access_cache_scan(unsigned int nr_to_scan)
{
	LIST_HEAD(head);
	struct nfs_inode *nfsi, *next;
	struct nfs_access_entry *cache;
	long freed = 0;

	spin_lock(&nfs_access_lru_lock);
	list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) {
		struct inode *inode;

		if (nr_to_scan-- == 0)
			break;
		inode = &nfsi->vfs_inode;
		spin_lock(&inode->i_lock);
		if (list_empty(&nfsi->access_cache_entry_lru))
			goto remove_lru_entry;
		cache = list_entry(nfsi->access_cache_entry_lru.next,
				struct nfs_access_entry, lru);
		list_move(&cache->lru, &head);
		rb_erase(&cache->rb_node, &nfsi->access_cache);
		freed++;
		if (!list_empty(&nfsi->access_cache_entry_lru))
			list_move_tail(&nfsi->access_cache_inode_lru,
					&nfs_access_lru_list);
		else {
remove_lru_entry:
			list_del_init(&nfsi->access_cache_inode_lru);
			smp_mb__before_atomic();
			clear_bit(NFS_INO_ACL_LRU_SET, &nfsi->flags);
			smp_mb__after_atomic();
		}
		spin_unlock(&inode->i_lock);
	}
	spin_unlock(&nfs_access_lru_lock);
	nfs_access_free_list(&head);
	return freed;
}

unsigned long
nfs_access_cache_scan(struct shrinker *shrink, struct shrink_control *sc)
{
	int nr_to_scan = sc->nr_to_scan;
	gfp_t gfp_mask = sc->gfp_mask;

	if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL)
		return SHRINK_STOP;
	return nfs_do_access_cache_scan(nr_to_scan);
}


unsigned long
nfs_access_cache_count(struct shrinker *shrink, struct shrink_control *sc)
{
	return vfs_pressure_ratio(atomic_long_read(&nfs_access_nr_entries));
}

static void
nfs_access_cache_enforce_limit(void)
{
	long nr_entries = atomic_long_read(&nfs_access_nr_entries);
	unsigned long diff;
	unsigned int nr_to_scan;

	if (nr_entries < 0 || nr_entries <= nfs_access_max_cachesize)
		return;
	nr_to_scan = 100;
	diff = nr_entries - nfs_access_max_cachesize;
	if (diff < nr_to_scan)
		nr_to_scan = diff;
	nfs_do_access_cache_scan(nr_to_scan);
}

static void __nfs_access_zap_cache(struct nfs_inode *nfsi, struct list_head *head)
{
	struct rb_root *root_node = &nfsi->access_cache;
	struct rb_node *n;
	struct nfs_access_entry *entry;

	/* Unhook entries from the cache */
	while ((n = rb_first(root_node)) != NULL) {
		entry = rb_entry(n, struct nfs_access_entry, rb_node);
		rb_erase(n, root_node);
		list_move(&entry->lru, head);
	}
	nfsi->cache_validity &= ~NFS_INO_INVALID_ACCESS;
}

void nfs_access_zap_cache(struct inode *inode)
{
	LIST_HEAD(head);

	if (test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags) == 0)
		return;
	/* Remove from global LRU init */
	spin_lock(&nfs_access_lru_lock);
	if (test_and_clear_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags))
		list_del_init(&NFS_I(inode)->access_cache_inode_lru);

	spin_lock(&inode->i_lock);
	__nfs_access_zap_cache(NFS_I(inode), &head);
	spin_unlock(&inode->i_lock);
	spin_unlock(&nfs_access_lru_lock);
	nfs_access_free_list(&head);
}
EXPORT_SYMBOL_GPL(nfs_access_zap_cache);

static int access_cmp(const struct cred *a, const struct nfs_access_entry *b)
{
	struct group_info *ga, *gb;
	int g;

	if (uid_lt(a->fsuid, b->fsuid))
		return -1;
	if (uid_gt(a->fsuid, b->fsuid))
		return 1;

	if (gid_lt(a->fsgid, b->fsgid))
		return -1;
	if (gid_gt(a->fsgid, b->fsgid))
		return 1;

	ga = a->group_info;
	gb = b->group_info;
	if (ga == gb)
		return 0;
	if (ga == NULL)
		return -1;
	if (gb == NULL)
		return 1;
	if (ga->ngroups < gb->ngroups)
		return -1;
	if (ga->ngroups > gb->ngroups)
		return 1;

	for (g = 0; g < ga->ngroups; g++) {
		if (gid_lt(ga->gid[g], gb->gid[g]))
			return -1;
		if (gid_gt(ga->gid[g], gb->gid[g]))
			return 1;
	}
	return 0;
}

static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, const struct cred *cred)
{
	struct rb_node *n = NFS_I(inode)->access_cache.rb_node;

	while (n != NULL) {
		struct nfs_access_entry *entry =
			rb_entry(n, struct nfs_access_entry, rb_node);
		int cmp = access_cmp(cred, entry);

		if (cmp < 0)
			n = n->rb_left;
		else if (cmp > 0)
			n = n->rb_right;
		else
			return entry;
	}
	return NULL;
}

static u64 nfs_access_login_time(const struct task_struct *task,
				 const struct cred *cred)
{
	const struct task_struct *parent;
	const struct cred *pcred;
	u64 ret;

	rcu_read_lock();
	for (;;) {
		parent = rcu_dereference(task->real_parent);
		pcred = __task_cred(parent);
		if (parent == task || cred_fscmp(pcred, cred) != 0)
			break;
		task = parent;
	}
	ret = task->start_time;
	rcu_read_unlock();
	return ret;
}

static int nfs_access_get_cached_locked(struct inode *inode, const struct cred *cred, u32 *mask, bool may_block)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	u64 login_time = nfs_access_login_time(current, cred);
	struct nfs_access_entry *cache;
	bool retry = true;
	int err;

	spin_lock(&inode->i_lock);
	for(;;) {
		if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
			goto out_zap;
		cache = nfs_access_search_rbtree(inode, cred);
		err = -ENOENT;
		if (cache == NULL)
			goto out;
		/* Found an entry, is our attribute cache valid? */
		if (!nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
			break;
		if (!retry)
			break;
		err = -ECHILD;
		if (!may_block)
			goto out;
		spin_unlock(&inode->i_lock);
		err = __nfs_revalidate_inode(NFS_SERVER(inode), inode);
		if (err)
			return err;
		spin_lock(&inode->i_lock);
		retry = false;
	}
	err = -ENOENT;
	if ((s64)(login_time - cache->timestamp) > 0)
		goto out;
	*mask = cache->mask;
	list_move_tail(&cache->lru, &nfsi->access_cache_entry_lru);
	err = 0;
out:
	spin_unlock(&inode->i_lock);
	return err;
out_zap:
	spin_unlock(&inode->i_lock);
	nfs_access_zap_cache(inode);
	return -ENOENT;
}

static int nfs_access_get_cached_rcu(struct inode *inode, const struct cred *cred, u32 *mask)
{
	/* Only check the most recently returned cache entry,
	 * but do it without locking.
	 */
	struct nfs_inode *nfsi = NFS_I(inode);
	u64 login_time = nfs_access_login_time(current, cred);
	struct nfs_access_entry *cache;
	int err = -ECHILD;
	struct list_head *lh;

	rcu_read_lock();
	if (nfsi->cache_validity & NFS_INO_INVALID_ACCESS)
		goto out;
	lh = rcu_dereference(list_tail_rcu(&nfsi->access_cache_entry_lru));
	cache = list_entry(lh, struct nfs_access_entry, lru);
	if (lh == &nfsi->access_cache_entry_lru ||
	    access_cmp(cred, cache) != 0)
		cache = NULL;
	if (cache == NULL)
		goto out;
	if ((s64)(login_time - cache->timestamp) > 0)
		goto out;
	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_ACCESS))
		goto out;
	*mask = cache->mask;
	err = 0;
out:
	rcu_read_unlock();
	return err;
}

int nfs_access_get_cached(struct inode *inode, const struct cred *cred,
			  u32 *mask, bool may_block)
{
	int status;

	status = nfs_access_get_cached_rcu(inode, cred, mask);
	if (status != 0)
		status = nfs_access_get_cached_locked(inode, cred, mask,
		    may_block);

	return status;
}
EXPORT_SYMBOL_GPL(nfs_access_get_cached);

static void nfs_access_add_rbtree(struct inode *inode,
				  struct nfs_access_entry *set,
				  const struct cred *cred)
{
	struct nfs_inode *nfsi = NFS_I(inode);
	struct rb_root *root_node = &nfsi->access_cache;
	struct rb_node **p = &root_node->rb_node;
	struct rb_node *parent = NULL;
	struct nfs_access_entry *entry;
	int cmp;

	spin_lock(&inode->i_lock);
	while (*p != NULL) {
		parent = *p;
		entry = rb_entry(parent, struct nfs_access_entry, rb_node);
		cmp = access_cmp(cred, entry);

		if (cmp < 0)
			p = &parent->rb_left;
		else if (cmp > 0)
			p = &parent->rb_right;
		else
			goto found;
	}
	rb_link_node(&set->rb_node, parent, p);
	rb_insert_color(&set->rb_node, root_node);
	list_add_tail(&set->lru, &nfsi->access_cache_entry_lru);
	spin_unlock(&inode->i_lock);
	return;
found:
	rb_replace_node(parent, &set->rb_node, root_node);
	list_add_tail(&set->lru, &nfsi->access_cache_entry_lru);
	list_del(&entry->lru);
	spin_unlock(&inode->i_lock);
	nfs_access_free_entry(entry);
}

void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set,
			  const struct cred *cred)
{
	struct nfs_access_entry *cache = kmalloc(sizeof(*cache), GFP_KERNEL);
	if (cache == NULL)
		return;
	RB_CLEAR_NODE(&cache->rb_node);
	cache->fsuid = cred->fsuid;
	cache->fsgid = cred->fsgid;
	cache->group_info = get_group_info(cred->group_info);
	cache->mask = set->mask;
	cache->timestamp = ktime_get_ns();

	/* The above field assignments must be visible
	 * before this item appears on the lru.  We cannot easily
	 * use rcu_assign_pointer, so just force the memory barrier.
	 */
	smp_wmb();
	nfs_access_add_rbtree(inode, cache, cred);

	/* Update accounting */
	smp_mb__before_atomic();
	atomic_long_inc(&nfs_access_nr_entries);
	smp_mb__after_atomic();

	/* Add inode to global LRU list */
	if (!test_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags)) {
		spin_lock(&nfs_access_lru_lock);
		if (!test_and_set_bit(NFS_INO_ACL_LRU_SET, &NFS_I(inode)->flags))
			list_add_tail(&NFS_I(inode)->access_cache_inode_lru,
					&nfs_access_lru_list);
		spin_unlock(&nfs_access_lru_lock);
	}
	nfs_access_cache_enforce_limit();
}
EXPORT_SYMBOL_GPL(nfs_access_add_cache);

#define NFS_MAY_READ (NFS_ACCESS_READ)
#define NFS_MAY_WRITE (NFS_ACCESS_MODIFY | \
		NFS_ACCESS_EXTEND | \
		NFS_ACCESS_DELETE)
#define NFS_FILE_MAY_WRITE (NFS_ACCESS_MODIFY | \
		NFS_ACCESS_EXTEND)
#define NFS_DIR_MAY_WRITE NFS_MAY_WRITE
#define NFS_MAY_LOOKUP (NFS_ACCESS_LOOKUP)
#define NFS_MAY_EXECUTE (NFS_ACCESS_EXECUTE)
static int
nfs_access_calc_mask(u32 access_result, umode_t umode)
{
	int mask = 0;

	if (access_result & NFS_MAY_READ)
		mask |= MAY_READ;
	if (S_ISDIR(umode)) {
		if ((access_result & NFS_DIR_MAY_WRITE) == NFS_DIR_MAY_WRITE)
			mask |= MAY_WRITE;
		if ((access_result & NFS_MAY_LOOKUP) == NFS_MAY_LOOKUP)
			mask |= MAY_EXEC;
	} else if (S_ISREG(umode)) {
		if ((access_result & NFS_FILE_MAY_WRITE) == NFS_FILE_MAY_WRITE)
			mask |= MAY_WRITE;
		if ((access_result & NFS_MAY_EXECUTE) == NFS_MAY_EXECUTE)
			mask |= MAY_EXEC;
	} else if (access_result & NFS_MAY_WRITE)
			mask |= MAY_WRITE;
	return mask;
}

void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result)
{
	entry->mask = access_result;
}
EXPORT_SYMBOL_GPL(nfs_access_set_mask);

static int nfs_do_access(struct inode *inode, const struct cred *cred, int mask)
{
	struct nfs_access_entry cache;
	bool may_block = (mask & MAY_NOT_BLOCK) == 0;
	int cache_mask = -1;
	int status;

	trace_nfs_access_enter(inode);

	status = nfs_access_get_cached(inode, cred, &cache.mask, may_block);
	if (status == 0)
		goto out_cached;

	status = -ECHILD;
	if (!may_block)
		goto out;

	/*
	 * Determine which access bits we want to ask for...
	 */
	cache.mask = NFS_ACCESS_READ | NFS_ACCESS_MODIFY | NFS_ACCESS_EXTEND |
		     nfs_access_xattr_mask(NFS_SERVER(inode));
	if (S_ISDIR(inode->i_mode))
		cache.mask |= NFS_ACCESS_DELETE | NFS_ACCESS_LOOKUP;
	else
		cache.mask |= NFS_ACCESS_EXECUTE;
	status = NFS_PROTO(inode)->access(inode, &cache, cred);
	if (status != 0) {
		if (status == -ESTALE) {
			if (!S_ISDIR(inode->i_mode))
				nfs_set_inode_stale(inode);
			else
				nfs_zap_caches(inode);
		}
		goto out;
	}
	nfs_access_add_cache(inode, &cache, cred);
out_cached:
	cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode);
	if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
		status = -EACCES;
out:
	trace_nfs_access_exit(inode, mask, cache_mask, status);
	return status;
}

static int nfs_open_permission_mask(int openflags)
{
	int mask = 0;

	if (openflags & __FMODE_EXEC) {
		/* ONLY check exec rights */
		mask = MAY_EXEC;
	} else {
		if ((openflags & O_ACCMODE) != O_WRONLY)
			mask |= MAY_READ;
		if ((openflags & O_ACCMODE) != O_RDONLY)
			mask |= MAY_WRITE;
	}

	return mask;
}

int nfs_may_open(struct inode *inode, const struct cred *cred, int openflags)
{
	return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags));
}
EXPORT_SYMBOL_GPL(nfs_may_open);

static int nfs_execute_ok(struct inode *inode, int mask)
{
	struct nfs_server *server = NFS_SERVER(inode);
	int ret = 0;

	if (S_ISDIR(inode->i_mode))
		return 0;
	if (nfs_check_cache_invalid(inode, NFS_INO_INVALID_MODE)) {
		if (mask & MAY_NOT_BLOCK)
			return -ECHILD;
		ret = __nfs_revalidate_inode(server, inode);
	}
	if (ret == 0 && !execute_ok(inode))
		ret = -EACCES;
	return ret;
}

int nfs_permission(struct mnt_idmap *idmap,
		   struct inode *inode,
		   int mask)
{
	const struct cred *cred = current_cred();
	int res = 0;

	nfs_inc_stats(inode, NFSIOS_VFSACCESS);

	if ((mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
		goto out;
	/* Is this sys_access() ? */
	if (mask & (MAY_ACCESS | MAY_CHDIR))
		goto force_lookup;

	switch (inode->i_mode & S_IFMT) {
		case S_IFLNK:
			goto out;
		case S_IFREG:
			if ((mask & MAY_OPEN) &&
			   nfs_server_capable(inode, NFS_CAP_ATOMIC_OPEN))
				return 0;
			break;
		case S_IFDIR:
			/*
			 * Optimize away all write operations, since the server
			 * will check permissions when we perform the op.
			 */
			if ((mask & MAY_WRITE) && !(mask & MAY_READ))
				goto out;
	}

force_lookup:
	if (!NFS_PROTO(inode)->access)
		goto out_notsup;

	res = nfs_do_access(inode, cred, mask);
out:
	if (!res && (mask & MAY_EXEC))
		res = nfs_execute_ok(inode, mask);

	dfprintk(VFS, "NFS: permission(%s/%lu), mask=0x%x, res=%d\n",
		inode->i_sb->s_id, inode->i_ino, mask, res);
	return res;
out_notsup:
	if (mask & MAY_NOT_BLOCK)
		return -ECHILD;

	res = nfs_revalidate_inode(inode, NFS_INO_INVALID_MODE |
						  NFS_INO_INVALID_OTHER);
	if (res == 0)
		res = generic_permission(&nop_mnt_idmap, inode, mask);
	goto out;
}
EXPORT_SYMBOL_GPL(nfs_permission);