summaryrefslogtreecommitdiffstats
path: root/sys/fs/nfsserver/nfs_nfsdport.c
blob: a6a01692edf0e71c73822d29e857d79e7b494c26 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
/*-
 * Copyright (c) 1989, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * This code is derived from software contributed to Berkeley by
 * Rick Macklem at The University of Guelph.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 */

#include <sys/cdefs.h>
__FBSDID("$FreeBSD$");

#include <sys/capability.h>

/*
 * Functions that perform the vfs operations required by the routines in
 * nfsd_serv.c. It is hoped that this change will make the server more
 * portable.
 */

#include <fs/nfs/nfsport.h>
#include <sys/hash.h>
#include <sys/sysctl.h>
#include <nlm/nlm_prot.h>
#include <nlm/nlm.h>

FEATURE(nfsd, "NFSv4 server");

extern u_int32_t newnfs_true, newnfs_false, newnfs_xdrneg1;
extern int nfsrv_useacl;
extern int newnfs_numnfsd;
extern struct mount nfsv4root_mnt;
extern struct nfsrv_stablefirst nfsrv_stablefirst;
extern void (*nfsd_call_servertimer)(void);
extern SVCPOOL	*nfsrvd_pool;
extern struct nfsv4lock nfsd_suspend_lock;
struct vfsoptlist nfsv4root_opt, nfsv4root_newopt;
NFSDLOCKMUTEX;
struct nfsrchash_bucket nfsrchash_table[NFSRVCACHE_HASHSIZE];
struct mtx nfsrc_udpmtx;
struct mtx nfs_v4root_mutex;
struct nfsrvfh nfs_rootfh, nfs_pubfh;
int nfs_pubfhset = 0, nfs_rootfhset = 0;
struct proc *nfsd_master_proc = NULL;
static pid_t nfsd_master_pid = (pid_t)-1;
static char nfsd_master_comm[MAXCOMLEN + 1];
static struct timeval nfsd_master_start;
static uint32_t nfsv4_sysid = 0;

static int nfssvc_srvcall(struct thread *, struct nfssvc_args *,
    struct ucred *);

int nfsrv_enable_crossmntpt = 1;
static int nfs_commit_blks;
static int nfs_commit_miss;
extern int nfsrv_issuedelegs;
extern int nfsrv_dolocallocks;

SYSCTL_NODE(_vfs, OID_AUTO, nfsd, CTLFLAG_RW, 0, "New NFS server");
SYSCTL_INT(_vfs_nfsd, OID_AUTO, mirrormnt, CTLFLAG_RW,
    &nfsrv_enable_crossmntpt, 0, "Enable nfsd to cross mount points");
SYSCTL_INT(_vfs_nfsd, OID_AUTO, commit_blks, CTLFLAG_RW, &nfs_commit_blks,
    0, "");
SYSCTL_INT(_vfs_nfsd, OID_AUTO, commit_miss, CTLFLAG_RW, &nfs_commit_miss,
    0, "");
SYSCTL_INT(_vfs_nfsd, OID_AUTO, issue_delegations, CTLFLAG_RW,
    &nfsrv_issuedelegs, 0, "Enable nfsd to issue delegations");
SYSCTL_INT(_vfs_nfsd, OID_AUTO, enable_locallocks, CTLFLAG_RW,
    &nfsrv_dolocallocks, 0, "Enable nfsd to acquire local locks on files");

#define	MAX_REORDERED_RPC	16
#define	NUM_HEURISTIC		1031
#define	NHUSE_INIT		64
#define	NHUSE_INC		16
#define	NHUSE_MAX		2048

static struct nfsheur {
	struct vnode *nh_vp;	/* vp to match (unreferenced pointer) */
	off_t nh_nextoff;	/* next offset for sequential detection */
	int nh_use;		/* use count for selection */
	int nh_seqcount;	/* heuristic */
} nfsheur[NUM_HEURISTIC];


/*
 * Heuristic to detect sequential operation.
 */
static struct nfsheur *
nfsrv_sequential_heuristic(struct uio *uio, struct vnode *vp)
{
	struct nfsheur *nh;
	int hi, try;

	/* Locate best candidate. */
	try = 32;
	hi = ((int)(vm_offset_t)vp / sizeof(struct vnode)) % NUM_HEURISTIC;
	nh = &nfsheur[hi];
	while (try--) {
		if (nfsheur[hi].nh_vp == vp) {
			nh = &nfsheur[hi];
			break;
		}
		if (nfsheur[hi].nh_use > 0)
			--nfsheur[hi].nh_use;
		hi = (hi + 1) % NUM_HEURISTIC;
		if (nfsheur[hi].nh_use < nh->nh_use)
			nh = &nfsheur[hi];
	}

	/* Initialize hint if this is a new file. */
	if (nh->nh_vp != vp) {
		nh->nh_vp = vp;
		nh->nh_nextoff = uio->uio_offset;
		nh->nh_use = NHUSE_INIT;
		if (uio->uio_offset == 0)
			nh->nh_seqcount = 4;
		else
			nh->nh_seqcount = 1;
	}

	/* Calculate heuristic. */
	if ((uio->uio_offset == 0 && nh->nh_seqcount > 0) ||
	    uio->uio_offset == nh->nh_nextoff) {
		/* See comments in vfs_vnops.c:sequential_heuristic(). */
		nh->nh_seqcount += howmany(uio->uio_resid, 16384);
		if (nh->nh_seqcount > IO_SEQMAX)
			nh->nh_seqcount = IO_SEQMAX;
	} else if (qabs(uio->uio_offset - nh->nh_nextoff) <= MAX_REORDERED_RPC *
	    imax(vp->v_mount->mnt_stat.f_iosize, uio->uio_resid)) {
		/* Probably a reordered RPC, leave seqcount alone. */
	} else if (nh->nh_seqcount > 1) {
		nh->nh_seqcount /= 2;
	} else {
		nh->nh_seqcount = 0;
	}
	nh->nh_use += NHUSE_INC;
	if (nh->nh_use > NHUSE_MAX)
		nh->nh_use = NHUSE_MAX;
	return (nh);
}

/*
 * Get attributes into nfsvattr structure.
 */
int
nfsvno_getattr(struct vnode *vp, struct nfsvattr *nvap, struct ucred *cred,
    struct thread *p, int vpislocked)
{
	int error, lockedit = 0;

	if (vpislocked == 0) {
		/*
		 * When vpislocked == 0, the vnode is either exclusively
		 * locked by this thread or not locked by this thread.
		 * As such, shared lock it, if not exclusively locked.
		 */
		if (NFSVOPISLOCKED(vp) != LK_EXCLUSIVE) {
			lockedit = 1;
			NFSVOPLOCK(vp, LK_SHARED | LK_RETRY);
		}
	}
	error = VOP_GETATTR(vp, &nvap->na_vattr, cred);
	if (lockedit != 0)
		NFSVOPUNLOCK(vp, 0);

	NFSEXITCODE(error);
	return (error);
}

/*
 * Get a file handle for a vnode.
 */
int
nfsvno_getfh(struct vnode *vp, fhandle_t *fhp, struct thread *p)
{
	int error;

	NFSBZERO((caddr_t)fhp, sizeof(fhandle_t));
	fhp->fh_fsid = vp->v_mount->mnt_stat.f_fsid;
	error = VOP_VPTOFH(vp, &fhp->fh_fid);

	NFSEXITCODE(error);
	return (error);
}

/*
 * Perform access checking for vnodes obtained from file handles that would
 * refer to files already opened by a Unix client. You cannot just use
 * vn_writechk() and VOP_ACCESSX() for two reasons.
 * 1 - You must check for exported rdonly as well as MNT_RDONLY for the write
 *     case.
 * 2 - The owner is to be given access irrespective of mode bits for some
 *     operations, so that processes that chmod after opening a file don't
 *     break.
 */
int
nfsvno_accchk(struct vnode *vp, accmode_t accmode, struct ucred *cred,
    struct nfsexstuff *exp, struct thread *p, int override, int vpislocked,
    u_int32_t *supportedtypep)
{
	struct vattr vattr;
	int error = 0, getret = 0;

	if (vpislocked == 0) {
		if (NFSVOPLOCK(vp, LK_SHARED) != 0) {
			error = EPERM;
			goto out;
		}
	}
	if (accmode & VWRITE) {
		/* Just vn_writechk() changed to check rdonly */
		/*
		 * Disallow write attempts on read-only file systems;
		 * unless the file is a socket or a block or character
		 * device resident on the file system.
		 */
		if (NFSVNO_EXRDONLY(exp) ||
		    (vp->v_mount->mnt_flag & MNT_RDONLY)) {
			switch (vp->v_type) {
			case VREG:
			case VDIR:
			case VLNK:
				error = EROFS;
			default:
				break;
			}
		}
		/*
		 * If there's shared text associated with
		 * the inode, try to free it up once.  If
		 * we fail, we can't allow writing.
		 */
		if (VOP_IS_TEXT(vp) && error == 0)
			error = ETXTBSY;
	}
	if (error != 0) {
		if (vpislocked == 0)
			NFSVOPUNLOCK(vp, 0);
		goto out;
	}

	/*
	 * Should the override still be applied when ACLs are enabled?
	 */
	error = VOP_ACCESSX(vp, accmode, cred, p);
	if (error != 0 && (accmode & (VDELETE | VDELETE_CHILD))) {
		/*
		 * Try again with VEXPLICIT_DENY, to see if the test for
		 * deletion is supported.
		 */
		error = VOP_ACCESSX(vp, accmode | VEXPLICIT_DENY, cred, p);
		if (error == 0) {
			if (vp->v_type == VDIR) {
				accmode &= ~(VDELETE | VDELETE_CHILD);
				accmode |= VWRITE;
				error = VOP_ACCESSX(vp, accmode, cred, p);
			} else if (supportedtypep != NULL) {
				*supportedtypep &= ~NFSACCESS_DELETE;
			}
		}
	}

	/*
	 * Allow certain operations for the owner (reads and writes
	 * on files that are already open).
	 */
	if (override != NFSACCCHK_NOOVERRIDE &&
	    (error == EPERM || error == EACCES)) {
		if (cred->cr_uid == 0 && (override & NFSACCCHK_ALLOWROOT))
			error = 0;
		else if (override & NFSACCCHK_ALLOWOWNER) {
			getret = VOP_GETATTR(vp, &vattr, cred);
			if (getret == 0 && cred->cr_uid == vattr.va_uid)
				error = 0;
		}
	}
	if (vpislocked == 0)
		NFSVOPUNLOCK(vp, 0);

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Set attribute(s) vnop.
 */
int
nfsvno_setattr(struct vnode *vp, struct nfsvattr *nvap, struct ucred *cred,
    struct thread *p, struct nfsexstuff *exp)
{
	int error;

	error = VOP_SETATTR(vp, &nvap->na_vattr, cred);
	NFSEXITCODE(error);
	return (error);
}

/*
 * Set up nameidata for a lookup() call and do it.
 */
int
nfsvno_namei(struct nfsrv_descript *nd, struct nameidata *ndp,
    struct vnode *dp, int islocked, struct nfsexstuff *exp, struct thread *p,
    struct vnode **retdirp)
{
	struct componentname *cnp = &ndp->ni_cnd;
	int i;
	struct iovec aiov;
	struct uio auio;
	int lockleaf = (cnp->cn_flags & LOCKLEAF) != 0, linklen;
	int error = 0, crossmnt;
	char *cp;

	*retdirp = NULL;
	cnp->cn_nameptr = cnp->cn_pnbuf;
	ndp->ni_strictrelative = 0;
	/*
	 * Extract and set starting directory.
	 */
	if (dp->v_type != VDIR) {
		if (islocked)
			vput(dp);
		else
			vrele(dp);
		nfsvno_relpathbuf(ndp);
		error = ENOTDIR;
		goto out1;
	}
	if (islocked)
		NFSVOPUNLOCK(dp, 0);
	VREF(dp);
	*retdirp = dp;
	if (NFSVNO_EXRDONLY(exp))
		cnp->cn_flags |= RDONLY;
	ndp->ni_segflg = UIO_SYSSPACE;
	crossmnt = 1;

	if (nd->nd_flag & ND_PUBLOOKUP) {
		ndp->ni_loopcnt = 0;
		if (cnp->cn_pnbuf[0] == '/') {
			vrele(dp);
			/*
			 * Check for degenerate pathnames here, since lookup()
			 * panics on them.
			 */
			for (i = 1; i < ndp->ni_pathlen; i++)
				if (cnp->cn_pnbuf[i] != '/')
					break;
			if (i == ndp->ni_pathlen) {
				error = NFSERR_ACCES;
				goto out;
			}
			dp = rootvnode;
			VREF(dp);
		}
	} else if ((nfsrv_enable_crossmntpt == 0 && NFSVNO_EXPORTED(exp)) ||
	    (nd->nd_flag & ND_NFSV4) == 0) {
		/*
		 * Only cross mount points for NFSv4 when doing a
		 * mount while traversing the file system above
		 * the mount point, unless nfsrv_enable_crossmntpt is set.
		 */
		cnp->cn_flags |= NOCROSSMOUNT;
		crossmnt = 0;
	}

	/*
	 * Initialize for scan, set ni_startdir and bump ref on dp again
	 * because lookup() will dereference ni_startdir.
	 */

	cnp->cn_thread = p;
	ndp->ni_startdir = dp;
	ndp->ni_rootdir = rootvnode;
	ndp->ni_topdir = NULL;

	if (!lockleaf)
		cnp->cn_flags |= LOCKLEAF;
	for (;;) {
		cnp->cn_nameptr = cnp->cn_pnbuf;
		/*
		 * Call lookup() to do the real work.  If an error occurs,
		 * ndp->ni_vp and ni_dvp are left uninitialized or NULL and
		 * we do not have to dereference anything before returning.
		 * In either case ni_startdir will be dereferenced and NULLed
		 * out.
		 */
		error = lookup(ndp);
		if (error)
			break;

		/*
		 * Check for encountering a symbolic link.  Trivial
		 * termination occurs if no symlink encountered.
		 */
		if ((cnp->cn_flags & ISSYMLINK) == 0) {
			if ((cnp->cn_flags & (SAVENAME | SAVESTART)) == 0)
				nfsvno_relpathbuf(ndp);
			if (ndp->ni_vp && !lockleaf)
				NFSVOPUNLOCK(ndp->ni_vp, 0);
			break;
		}

		/*
		 * Validate symlink
		 */
		if ((cnp->cn_flags & LOCKPARENT) && ndp->ni_pathlen == 1)
			NFSVOPUNLOCK(ndp->ni_dvp, 0);
		if (!(nd->nd_flag & ND_PUBLOOKUP)) {
			error = EINVAL;
			goto badlink2;
		}

		if (ndp->ni_loopcnt++ >= MAXSYMLINKS) {
			error = ELOOP;
			goto badlink2;
		}
		if (ndp->ni_pathlen > 1)
			cp = uma_zalloc(namei_zone, M_WAITOK);
		else
			cp = cnp->cn_pnbuf;
		aiov.iov_base = cp;
		aiov.iov_len = MAXPATHLEN;
		auio.uio_iov = &aiov;
		auio.uio_iovcnt = 1;
		auio.uio_offset = 0;
		auio.uio_rw = UIO_READ;
		auio.uio_segflg = UIO_SYSSPACE;
		auio.uio_td = NULL;
		auio.uio_resid = MAXPATHLEN;
		error = VOP_READLINK(ndp->ni_vp, &auio, cnp->cn_cred);
		if (error) {
		badlink1:
			if (ndp->ni_pathlen > 1)
				uma_zfree(namei_zone, cp);
		badlink2:
			vrele(ndp->ni_dvp);
			vput(ndp->ni_vp);
			break;
		}
		linklen = MAXPATHLEN - auio.uio_resid;
		if (linklen == 0) {
			error = ENOENT;
			goto badlink1;
		}
		if (linklen + ndp->ni_pathlen >= MAXPATHLEN) {
			error = ENAMETOOLONG;
			goto badlink1;
		}

		/*
		 * Adjust or replace path
		 */
		if (ndp->ni_pathlen > 1) {
			NFSBCOPY(ndp->ni_next, cp + linklen, ndp->ni_pathlen);
			uma_zfree(namei_zone, cnp->cn_pnbuf);
			cnp->cn_pnbuf = cp;
		} else
			cnp->cn_pnbuf[linklen] = '\0';
		ndp->ni_pathlen += linklen;

		/*
		 * Cleanup refs for next loop and check if root directory
		 * should replace current directory.  Normally ni_dvp
		 * becomes the new base directory and is cleaned up when
		 * we loop.  Explicitly null pointers after invalidation
		 * to clarify operation.
		 */
		vput(ndp->ni_vp);
		ndp->ni_vp = NULL;

		if (cnp->cn_pnbuf[0] == '/') {
			vrele(ndp->ni_dvp);
			ndp->ni_dvp = ndp->ni_rootdir;
			VREF(ndp->ni_dvp);
		}
		ndp->ni_startdir = ndp->ni_dvp;
		ndp->ni_dvp = NULL;
	}
	if (!lockleaf)
		cnp->cn_flags &= ~LOCKLEAF;

out:
	if (error) {
		nfsvno_relpathbuf(ndp);
		ndp->ni_vp = NULL;
		ndp->ni_dvp = NULL;
		ndp->ni_startdir = NULL;
	} else if ((ndp->ni_cnd.cn_flags & (WANTPARENT|LOCKPARENT)) == 0) {
		ndp->ni_dvp = NULL;
	}

out1:
	NFSEXITCODE2(error, nd);
	return (error);
}

/*
 * Set up a pathname buffer and return a pointer to it and, optionally
 * set a hash pointer.
 */
void
nfsvno_setpathbuf(struct nameidata *ndp, char **bufpp, u_long **hashpp)
{
	struct componentname *cnp = &ndp->ni_cnd;

	cnp->cn_flags |= (NOMACCHECK | HASBUF);
	cnp->cn_pnbuf = uma_zalloc(namei_zone, M_WAITOK);
	if (hashpp != NULL)
		*hashpp = NULL;
	*bufpp = cnp->cn_pnbuf;
}

/*
 * Release the above path buffer, if not released by nfsvno_namei().
 */
void
nfsvno_relpathbuf(struct nameidata *ndp)
{

	if ((ndp->ni_cnd.cn_flags & HASBUF) == 0)
		panic("nfsrelpath");
	uma_zfree(namei_zone, ndp->ni_cnd.cn_pnbuf);
	ndp->ni_cnd.cn_flags &= ~HASBUF;
}

/*
 * Readlink vnode op into an mbuf list.
 */
int
nfsvno_readlink(struct vnode *vp, struct ucred *cred, struct thread *p,
    struct mbuf **mpp, struct mbuf **mpendp, int *lenp)
{
	struct iovec iv[(NFS_MAXPATHLEN+MLEN-1)/MLEN];
	struct iovec *ivp = iv;
	struct uio io, *uiop = &io;
	struct mbuf *mp, *mp2 = NULL, *mp3 = NULL;
	int i, len, tlen, error = 0;

	len = 0;
	i = 0;
	while (len < NFS_MAXPATHLEN) {
		NFSMGET(mp);
		MCLGET(mp, M_WAITOK);
		mp->m_len = NFSMSIZ(mp);
		if (len == 0) {
			mp3 = mp2 = mp;
		} else {
			mp2->m_next = mp;
			mp2 = mp;
		}
		if ((len + mp->m_len) > NFS_MAXPATHLEN) {
			mp->m_len = NFS_MAXPATHLEN - len;
			len = NFS_MAXPATHLEN;
		} else {
			len += mp->m_len;
		}
		ivp->iov_base = mtod(mp, caddr_t);
		ivp->iov_len = mp->m_len;
		i++;
		ivp++;
	}
	uiop->uio_iov = iv;
	uiop->uio_iovcnt = i;
	uiop->uio_offset = 0;
	uiop->uio_resid = len;
	uiop->uio_rw = UIO_READ;
	uiop->uio_segflg = UIO_SYSSPACE;
	uiop->uio_td = NULL;
	error = VOP_READLINK(vp, uiop, cred);
	if (error) {
		m_freem(mp3);
		*lenp = 0;
		goto out;
	}
	if (uiop->uio_resid > 0) {
		len -= uiop->uio_resid;
		tlen = NFSM_RNDUP(len);
		nfsrv_adj(mp3, NFS_MAXPATHLEN - tlen, tlen - len);
	}
	*lenp = len;
	*mpp = mp3;
	*mpendp = mp;

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Read vnode op call into mbuf list.
 */
int
nfsvno_read(struct vnode *vp, off_t off, int cnt, struct ucred *cred,
    struct thread *p, struct mbuf **mpp, struct mbuf **mpendp)
{
	struct mbuf *m;
	int i;
	struct iovec *iv;
	struct iovec *iv2;
	int error = 0, len, left, siz, tlen, ioflag = 0;
	struct mbuf *m2 = NULL, *m3;
	struct uio io, *uiop = &io;
	struct nfsheur *nh;

	len = left = NFSM_RNDUP(cnt);
	m3 = NULL;
	/*
	 * Generate the mbuf list with the uio_iov ref. to it.
	 */
	i = 0;
	while (left > 0) {
		NFSMGET(m);
		MCLGET(m, M_WAITOK);
		m->m_len = 0;
		siz = min(M_TRAILINGSPACE(m), left);
		left -= siz;
		i++;
		if (m3)
			m2->m_next = m;
		else
			m3 = m;
		m2 = m;
	}
	MALLOC(iv, struct iovec *, i * sizeof (struct iovec),
	    M_TEMP, M_WAITOK);
	uiop->uio_iov = iv2 = iv;
	m = m3;
	left = len;
	i = 0;
	while (left > 0) {
		if (m == NULL)
			panic("nfsvno_read iov");
		siz = min(M_TRAILINGSPACE(m), left);
		if (siz > 0) {
			iv->iov_base = mtod(m, caddr_t) + m->m_len;
			iv->iov_len = siz;
			m->m_len += siz;
			left -= siz;
			iv++;
			i++;
		}
		m = m->m_next;
	}
	uiop->uio_iovcnt = i;
	uiop->uio_offset = off;
	uiop->uio_resid = len;
	uiop->uio_rw = UIO_READ;
	uiop->uio_segflg = UIO_SYSSPACE;
	nh = nfsrv_sequential_heuristic(uiop, vp);
	ioflag |= nh->nh_seqcount << IO_SEQSHIFT;
	error = VOP_READ(vp, uiop, IO_NODELOCKED | ioflag, cred);
	FREE((caddr_t)iv2, M_TEMP);
	if (error) {
		m_freem(m3);
		*mpp = NULL;
		goto out;
	}
	nh->nh_nextoff = uiop->uio_offset;
	tlen = len - uiop->uio_resid;
	cnt = cnt < tlen ? cnt : tlen;
	tlen = NFSM_RNDUP(cnt);
	if (tlen == 0) {
		m_freem(m3);
		m3 = NULL;
	} else if (len != tlen || tlen != cnt)
		nfsrv_adj(m3, len - tlen, tlen - cnt);
	*mpp = m3;
	*mpendp = m2;

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Write vnode op from an mbuf list.
 */
int
nfsvno_write(struct vnode *vp, off_t off, int retlen, int cnt, int stable,
    struct mbuf *mp, char *cp, struct ucred *cred, struct thread *p)
{
	struct iovec *ivp;
	int i, len;
	struct iovec *iv;
	int ioflags, error;
	struct uio io, *uiop = &io;
	struct nfsheur *nh;

	MALLOC(ivp, struct iovec *, cnt * sizeof (struct iovec), M_TEMP,
	    M_WAITOK);
	uiop->uio_iov = iv = ivp;
	uiop->uio_iovcnt = cnt;
	i = mtod(mp, caddr_t) + mp->m_len - cp;
	len = retlen;
	while (len > 0) {
		if (mp == NULL)
			panic("nfsvno_write");
		if (i > 0) {
			i = min(i, len);
			ivp->iov_base = cp;
			ivp->iov_len = i;
			ivp++;
			len -= i;
		}
		mp = mp->m_next;
		if (mp) {
			i = mp->m_len;
			cp = mtod(mp, caddr_t);
		}
	}

	if (stable == NFSWRITE_UNSTABLE)
		ioflags = IO_NODELOCKED;
	else
		ioflags = (IO_SYNC | IO_NODELOCKED);
	uiop->uio_resid = retlen;
	uiop->uio_rw = UIO_WRITE;
	uiop->uio_segflg = UIO_SYSSPACE;
	NFSUIOPROC(uiop, p);
	uiop->uio_offset = off;
	nh = nfsrv_sequential_heuristic(uiop, vp);
	ioflags |= nh->nh_seqcount << IO_SEQSHIFT;
	error = VOP_WRITE(vp, uiop, ioflags, cred);
	if (error == 0)
		nh->nh_nextoff = uiop->uio_offset;
	FREE((caddr_t)iv, M_TEMP);

	NFSEXITCODE(error);
	return (error);
}

/*
 * Common code for creating a regular file (plus special files for V2).
 */
int
nfsvno_createsub(struct nfsrv_descript *nd, struct nameidata *ndp,
    struct vnode **vpp, struct nfsvattr *nvap, int *exclusive_flagp,
    int32_t *cverf, NFSDEV_T rdev, struct thread *p, struct nfsexstuff *exp)
{
	u_quad_t tempsize;
	int error;

	error = nd->nd_repstat;
	if (!error && ndp->ni_vp == NULL) {
		if (nvap->na_type == VREG || nvap->na_type == VSOCK) {
			vrele(ndp->ni_startdir);
			error = VOP_CREATE(ndp->ni_dvp,
			    &ndp->ni_vp, &ndp->ni_cnd, &nvap->na_vattr);
			vput(ndp->ni_dvp);
			nfsvno_relpathbuf(ndp);
			if (!error) {
				if (*exclusive_flagp) {
					*exclusive_flagp = 0;
					NFSVNO_ATTRINIT(nvap);
					nvap->na_atime.tv_sec = cverf[0];
					nvap->na_atime.tv_nsec = cverf[1];
					error = VOP_SETATTR(ndp->ni_vp,
					    &nvap->na_vattr, nd->nd_cred);
				}
			}
		/*
		 * NFS V2 Only. nfsrvd_mknod() does this for V3.
		 * (This implies, just get out on an error.)
		 */
		} else if (nvap->na_type == VCHR || nvap->na_type == VBLK ||
			nvap->na_type == VFIFO) {
			if (nvap->na_type == VCHR && rdev == 0xffffffff)
				nvap->na_type = VFIFO;
                        if (nvap->na_type != VFIFO &&
			    (error = priv_check_cred(nd->nd_cred,
			     PRIV_VFS_MKNOD_DEV, 0))) {
				vrele(ndp->ni_startdir);
				nfsvno_relpathbuf(ndp);
				vput(ndp->ni_dvp);
				goto out;
			}
			nvap->na_rdev = rdev;
			error = VOP_MKNOD(ndp->ni_dvp, &ndp->ni_vp,
			    &ndp->ni_cnd, &nvap->na_vattr);
			vput(ndp->ni_dvp);
			nfsvno_relpathbuf(ndp);
			vrele(ndp->ni_startdir);
			if (error)
				goto out;
		} else {
			vrele(ndp->ni_startdir);
			nfsvno_relpathbuf(ndp);
			vput(ndp->ni_dvp);
			error = ENXIO;
			goto out;
		}
		*vpp = ndp->ni_vp;
	} else {
		/*
		 * Handle cases where error is already set and/or
		 * the file exists.
		 * 1 - clean up the lookup
		 * 2 - iff !error and na_size set, truncate it
		 */
		vrele(ndp->ni_startdir);
		nfsvno_relpathbuf(ndp);
		*vpp = ndp->ni_vp;
		if (ndp->ni_dvp == *vpp)
			vrele(ndp->ni_dvp);
		else
			vput(ndp->ni_dvp);
		if (!error && nvap->na_size != VNOVAL) {
			error = nfsvno_accchk(*vpp, VWRITE,
			    nd->nd_cred, exp, p, NFSACCCHK_NOOVERRIDE,
			    NFSACCCHK_VPISLOCKED, NULL);
			if (!error) {
				tempsize = nvap->na_size;
				NFSVNO_ATTRINIT(nvap);
				nvap->na_size = tempsize;
				error = VOP_SETATTR(*vpp,
				    &nvap->na_vattr, nd->nd_cred);
			}
		}
		if (error)
			vput(*vpp);
	}

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Do a mknod vnode op.
 */
int
nfsvno_mknod(struct nameidata *ndp, struct nfsvattr *nvap, struct ucred *cred,
    struct thread *p)
{
	int error = 0;
	enum vtype vtyp;

	vtyp = nvap->na_type;
	/*
	 * Iff doesn't exist, create it.
	 */
	if (ndp->ni_vp) {
		vrele(ndp->ni_startdir);
		nfsvno_relpathbuf(ndp);
		vput(ndp->ni_dvp);
		vrele(ndp->ni_vp);
		error = EEXIST;
		goto out;
	}
	if (vtyp != VCHR && vtyp != VBLK && vtyp != VSOCK && vtyp != VFIFO) {
		vrele(ndp->ni_startdir);
		nfsvno_relpathbuf(ndp);
		vput(ndp->ni_dvp);
		error = NFSERR_BADTYPE;
		goto out;
	}
	if (vtyp == VSOCK) {
		vrele(ndp->ni_startdir);
		error = VOP_CREATE(ndp->ni_dvp, &ndp->ni_vp,
		    &ndp->ni_cnd, &nvap->na_vattr);
		vput(ndp->ni_dvp);
		nfsvno_relpathbuf(ndp);
	} else {
		if (nvap->na_type != VFIFO &&
		    (error = priv_check_cred(cred, PRIV_VFS_MKNOD_DEV, 0))) {
			vrele(ndp->ni_startdir);
			nfsvno_relpathbuf(ndp);
			vput(ndp->ni_dvp);
			goto out;
		}
		error = VOP_MKNOD(ndp->ni_dvp, &ndp->ni_vp,
		    &ndp->ni_cnd, &nvap->na_vattr);
		vput(ndp->ni_dvp);
		nfsvno_relpathbuf(ndp);
		vrele(ndp->ni_startdir);
		/*
		 * Since VOP_MKNOD returns the ni_vp, I can't
		 * see any reason to do the lookup.
		 */
	}

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Mkdir vnode op.
 */
int
nfsvno_mkdir(struct nameidata *ndp, struct nfsvattr *nvap, uid_t saved_uid,
    struct ucred *cred, struct thread *p, struct nfsexstuff *exp)
{
	int error = 0;

	if (ndp->ni_vp != NULL) {
		if (ndp->ni_dvp == ndp->ni_vp)
			vrele(ndp->ni_dvp);
		else
			vput(ndp->ni_dvp);
		vrele(ndp->ni_vp);
		nfsvno_relpathbuf(ndp);
		error = EEXIST;
		goto out;
	}
	error = VOP_MKDIR(ndp->ni_dvp, &ndp->ni_vp, &ndp->ni_cnd,
	    &nvap->na_vattr);
	vput(ndp->ni_dvp);
	nfsvno_relpathbuf(ndp);

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * symlink vnode op.
 */
int
nfsvno_symlink(struct nameidata *ndp, struct nfsvattr *nvap, char *pathcp,
    int pathlen, int not_v2, uid_t saved_uid, struct ucred *cred, struct thread *p,
    struct nfsexstuff *exp)
{
	int error = 0;

	if (ndp->ni_vp) {
		vrele(ndp->ni_startdir);
		nfsvno_relpathbuf(ndp);
		if (ndp->ni_dvp == ndp->ni_vp)
			vrele(ndp->ni_dvp);
		else
			vput(ndp->ni_dvp);
		vrele(ndp->ni_vp);
		error = EEXIST;
		goto out;
	}

	error = VOP_SYMLINK(ndp->ni_dvp, &ndp->ni_vp, &ndp->ni_cnd,
	    &nvap->na_vattr, pathcp);
	vput(ndp->ni_dvp);
	vrele(ndp->ni_startdir);
	nfsvno_relpathbuf(ndp);
	/*
	 * Although FreeBSD still had the lookup code in
	 * it for 7/current, there doesn't seem to be any
	 * point, since VOP_SYMLINK() returns the ni_vp.
	 * Just vput it for v2.
	 */
	if (!not_v2 && !error)
		vput(ndp->ni_vp);

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Parse symbolic link arguments.
 * This function has an ugly side effect. It will MALLOC() an area for
 * the symlink and set iov_base to point to it, only if it succeeds.
 * So, if it returns with uiop->uio_iov->iov_base != NULL, that must
 * be FREE'd later.
 */
int
nfsvno_getsymlink(struct nfsrv_descript *nd, struct nfsvattr *nvap,
    struct thread *p, char **pathcpp, int *lenp)
{
	u_int32_t *tl;
	char *pathcp = NULL;
	int error = 0, len;
	struct nfsv2_sattr *sp;

	*pathcpp = NULL;
	*lenp = 0;
	if ((nd->nd_flag & ND_NFSV3) &&
	    (error = nfsrv_sattr(nd, nvap, NULL, NULL, p)))
		goto nfsmout;
	NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
	len = fxdr_unsigned(int, *tl);
	if (len > NFS_MAXPATHLEN || len <= 0) {
		error = EBADRPC;
		goto nfsmout;
	}
	MALLOC(pathcp, caddr_t, len + 1, M_TEMP, M_WAITOK);
	error = nfsrv_mtostr(nd, pathcp, len);
	if (error)
		goto nfsmout;
	if (nd->nd_flag & ND_NFSV2) {
		NFSM_DISSECT(sp, struct nfsv2_sattr *, NFSX_V2SATTR);
		nvap->na_mode = fxdr_unsigned(u_int16_t, sp->sa_mode);
	}
	*pathcpp = pathcp;
	*lenp = len;
	NFSEXITCODE2(0, nd);
	return (0);
nfsmout:
	if (pathcp)
		free(pathcp, M_TEMP);
	NFSEXITCODE2(error, nd);
	return (error);
}

/*
 * Remove a non-directory object.
 */
int
nfsvno_removesub(struct nameidata *ndp, int is_v4, struct ucred *cred,
    struct thread *p, struct nfsexstuff *exp)
{
	struct vnode *vp;
	int error = 0;

	vp = ndp->ni_vp;
	if (vp->v_type == VDIR)
		error = NFSERR_ISDIR;
	else if (is_v4)
		error = nfsrv_checkremove(vp, 1, p);
	if (!error)
		error = VOP_REMOVE(ndp->ni_dvp, vp, &ndp->ni_cnd);
	if (ndp->ni_dvp == vp)
		vrele(ndp->ni_dvp);
	else
		vput(ndp->ni_dvp);
	vput(vp);
	if ((ndp->ni_cnd.cn_flags & SAVENAME) != 0)
		nfsvno_relpathbuf(ndp);
	NFSEXITCODE(error);
	return (error);
}

/*
 * Remove a directory.
 */
int
nfsvno_rmdirsub(struct nameidata *ndp, int is_v4, struct ucred *cred,
    struct thread *p, struct nfsexstuff *exp)
{
	struct vnode *vp;
	int error = 0;

	vp = ndp->ni_vp;
	if (vp->v_type != VDIR) {
		error = ENOTDIR;
		goto out;
	}
	/*
	 * No rmdir "." please.
	 */
	if (ndp->ni_dvp == vp) {
		error = EINVAL;
		goto out;
	}
	/*
	 * The root of a mounted filesystem cannot be deleted.
	 */
	if (vp->v_vflag & VV_ROOT)
		error = EBUSY;
out:
	if (!error)
		error = VOP_RMDIR(ndp->ni_dvp, vp, &ndp->ni_cnd);
	if (ndp->ni_dvp == vp)
		vrele(ndp->ni_dvp);
	else
		vput(ndp->ni_dvp);
	vput(vp);
	if ((ndp->ni_cnd.cn_flags & SAVENAME) != 0)
		nfsvno_relpathbuf(ndp);
	NFSEXITCODE(error);
	return (error);
}

/*
 * Rename vnode op.
 */
int
nfsvno_rename(struct nameidata *fromndp, struct nameidata *tondp,
    u_int32_t ndstat, u_int32_t ndflag, struct ucred *cred, struct thread *p)
{
	struct vnode *fvp, *tvp, *tdvp;
	int error = 0;

	fvp = fromndp->ni_vp;
	if (ndstat) {
		vrele(fromndp->ni_dvp);
		vrele(fvp);
		error = ndstat;
		goto out1;
	}
	tdvp = tondp->ni_dvp;
	tvp = tondp->ni_vp;
	if (tvp != NULL) {
		if (fvp->v_type == VDIR && tvp->v_type != VDIR) {
			error = (ndflag & ND_NFSV2) ? EISDIR : EEXIST;
			goto out;
		} else if (fvp->v_type != VDIR && tvp->v_type == VDIR) {
			error = (ndflag & ND_NFSV2) ? ENOTDIR : EEXIST;
			goto out;
		}
		if (tvp->v_type == VDIR && tvp->v_mountedhere) {
			error = (ndflag & ND_NFSV2) ? ENOTEMPTY : EXDEV;
			goto out;
		}

		/*
		 * A rename to '.' or '..' results in a prematurely
		 * unlocked vnode on FreeBSD5, so I'm just going to fail that
		 * here.
		 */
		if ((tondp->ni_cnd.cn_namelen == 1 &&
		     tondp->ni_cnd.cn_nameptr[0] == '.') ||
		    (tondp->ni_cnd.cn_namelen == 2 &&
		     tondp->ni_cnd.cn_nameptr[0] == '.' &&
		     tondp->ni_cnd.cn_nameptr[1] == '.')) {
			error = EINVAL;
			goto out;
		}
	}
	if (fvp->v_type == VDIR && fvp->v_mountedhere) {
		error = (ndflag & ND_NFSV2) ? ENOTEMPTY : EXDEV;
		goto out;
	}
	if (fvp->v_mount != tdvp->v_mount) {
		error = (ndflag & ND_NFSV2) ? ENOTEMPTY : EXDEV;
		goto out;
	}
	if (fvp == tdvp) {
		error = (ndflag & ND_NFSV2) ? ENOTEMPTY : EINVAL;
		goto out;
	}
	if (fvp == tvp) {
		/*
		 * If source and destination are the same, there is nothing to
		 * do. Set error to -1 to indicate this.
		 */
		error = -1;
		goto out;
	}
	if (ndflag & ND_NFSV4) {
		if (NFSVOPLOCK(fvp, LK_EXCLUSIVE) == 0) {
			error = nfsrv_checkremove(fvp, 0, p);
			NFSVOPUNLOCK(fvp, 0);
		} else
			error = EPERM;
		if (tvp && !error)
			error = nfsrv_checkremove(tvp, 1, p);
	} else {
		/*
		 * For NFSv2 and NFSv3, try to get rid of the delegation, so
		 * that the NFSv4 client won't be confused by the rename.
		 * Since nfsd_recalldelegation() can only be called on an
		 * unlocked vnode at this point and fvp is the file that will
		 * still exist after the rename, just do fvp.
		 */
		nfsd_recalldelegation(fvp, p);
	}
out:
	if (!error) {
		error = VOP_RENAME(fromndp->ni_dvp, fromndp->ni_vp,
		    &fromndp->ni_cnd, tondp->ni_dvp, tondp->ni_vp,
		    &tondp->ni_cnd);
	} else {
		if (tdvp == tvp)
			vrele(tdvp);
		else
			vput(tdvp);
		if (tvp)
			vput(tvp);
		vrele(fromndp->ni_dvp);
		vrele(fvp);
		if (error == -1)
			error = 0;
	}
	vrele(tondp->ni_startdir);
	nfsvno_relpathbuf(tondp);
out1:
	vrele(fromndp->ni_startdir);
	nfsvno_relpathbuf(fromndp);
	NFSEXITCODE(error);
	return (error);
}

/*
 * Link vnode op.
 */
int
nfsvno_link(struct nameidata *ndp, struct vnode *vp, struct ucred *cred,
    struct thread *p, struct nfsexstuff *exp)
{
	struct vnode *xp;
	int error = 0;

	xp = ndp->ni_vp;
	if (xp != NULL) {
		error = EEXIST;
	} else {
		xp = ndp->ni_dvp;
		if (vp->v_mount != xp->v_mount)
			error = EXDEV;
	}
	if (!error) {
		NFSVOPLOCK(vp, LK_EXCLUSIVE | LK_RETRY);
		if ((vp->v_iflag & VI_DOOMED) == 0)
			error = VOP_LINK(ndp->ni_dvp, vp, &ndp->ni_cnd);
		else
			error = EPERM;
		if (ndp->ni_dvp == vp)
			vrele(ndp->ni_dvp);
		else
			vput(ndp->ni_dvp);
		NFSVOPUNLOCK(vp, 0);
	} else {
		if (ndp->ni_dvp == ndp->ni_vp)
			vrele(ndp->ni_dvp);
		else
			vput(ndp->ni_dvp);
		if (ndp->ni_vp)
			vrele(ndp->ni_vp);
	}
	nfsvno_relpathbuf(ndp);
	NFSEXITCODE(error);
	return (error);
}

/*
 * Do the fsync() appropriate for the commit.
 */
int
nfsvno_fsync(struct vnode *vp, u_int64_t off, int cnt, struct ucred *cred,
    struct thread *td)
{
	int error = 0;

	/*
	 * RFC 1813 3.3.21: if count is 0, a flush from offset to the end of
	 * file is done.  At this time VOP_FSYNC does not accept offset and
	 * byte count parameters so call VOP_FSYNC the whole file for now.
	 * The same is true for NFSv4: RFC 3530 Sec. 14.2.3.
	 */
	if (cnt == 0 || cnt > MAX_COMMIT_COUNT) {
		/*
		 * Give up and do the whole thing
		 */
		if (vp->v_object &&
		   (vp->v_object->flags & OBJ_MIGHTBEDIRTY)) {
			VM_OBJECT_WLOCK(vp->v_object);
			vm_object_page_clean(vp->v_object, 0, 0, OBJPC_SYNC);
			VM_OBJECT_WUNLOCK(vp->v_object);
		}
		error = VOP_FSYNC(vp, MNT_WAIT, td);
	} else {
		/*
		 * Locate and synchronously write any buffers that fall
		 * into the requested range.  Note:  we are assuming that
		 * f_iosize is a power of 2.
		 */
		int iosize = vp->v_mount->mnt_stat.f_iosize;
		int iomask = iosize - 1;
		struct bufobj *bo;
		daddr_t lblkno;

		/*
		 * Align to iosize boundry, super-align to page boundry.
		 */
		if (off & iomask) {
			cnt += off & iomask;
			off &= ~(u_quad_t)iomask;
		}
		if (off & PAGE_MASK) {
			cnt += off & PAGE_MASK;
			off &= ~(u_quad_t)PAGE_MASK;
		}
		lblkno = off / iosize;

		if (vp->v_object &&
		   (vp->v_object->flags & OBJ_MIGHTBEDIRTY)) {
			VM_OBJECT_WLOCK(vp->v_object);
			vm_object_page_clean(vp->v_object, off, off + cnt,
			    OBJPC_SYNC);
			VM_OBJECT_WUNLOCK(vp->v_object);
		}

		bo = &vp->v_bufobj;
		BO_LOCK(bo);
		while (cnt > 0) {
			struct buf *bp;

			/*
			 * If we have a buffer and it is marked B_DELWRI we
			 * have to lock and write it.  Otherwise the prior
			 * write is assumed to have already been committed.
			 *
			 * gbincore() can return invalid buffers now so we
			 * have to check that bit as well (though B_DELWRI
			 * should not be set if B_INVAL is set there could be
			 * a race here since we haven't locked the buffer).
			 */
			if ((bp = gbincore(&vp->v_bufobj, lblkno)) != NULL) {
				if (BUF_LOCK(bp, LK_EXCLUSIVE | LK_SLEEPFAIL |
				    LK_INTERLOCK, BO_LOCKPTR(bo)) == ENOLCK) {
					BO_LOCK(bo);
					continue; /* retry */
				}
			    	if ((bp->b_flags & (B_DELWRI|B_INVAL)) ==
				    B_DELWRI) {
					bremfree(bp);
					bp->b_flags &= ~B_ASYNC;
					bwrite(bp);
					++nfs_commit_miss;
				} else
					BUF_UNLOCK(bp);
				BO_LOCK(bo);
			}
			++nfs_commit_blks;
			if (cnt < iosize)
				break;
			cnt -= iosize;
			++lblkno;
		}
		BO_UNLOCK(bo);
	}
	NFSEXITCODE(error);
	return (error);
}

/*
 * Statfs vnode op.
 */
int
nfsvno_statfs(struct vnode *vp, struct statfs *sf)
{
	int error;

	error = VFS_STATFS(vp->v_mount, sf);
	if (error == 0) {
		/*
		 * Since NFS handles these values as unsigned on the
		 * wire, there is no way to represent negative values,
		 * so set them to 0. Without this, they will appear
		 * to be very large positive values for clients like
		 * Solaris10.
		 */
		if (sf->f_bavail < 0)
			sf->f_bavail = 0;
		if (sf->f_ffree < 0)
			sf->f_ffree = 0;
	}
	NFSEXITCODE(error);
	return (error);
}

/*
 * Do the vnode op stuff for Open. Similar to nfsvno_createsub(), but
 * must handle nfsrv_opencheck() calls after any other access checks.
 */
void
nfsvno_open(struct nfsrv_descript *nd, struct nameidata *ndp,
    nfsquad_t clientid, nfsv4stateid_t *stateidp, struct nfsstate *stp,
    int *exclusive_flagp, struct nfsvattr *nvap, int32_t *cverf, int create,
    NFSACL_T *aclp, nfsattrbit_t *attrbitp, struct ucred *cred, struct thread *p,
    struct nfsexstuff *exp, struct vnode **vpp)
{
	struct vnode *vp = NULL;
	u_quad_t tempsize;
	struct nfsexstuff nes;

	if (ndp->ni_vp == NULL)
		nd->nd_repstat = nfsrv_opencheck(clientid,
		    stateidp, stp, NULL, nd, p, nd->nd_repstat);
	if (!nd->nd_repstat) {
		if (ndp->ni_vp == NULL) {
			vrele(ndp->ni_startdir);
			nd->nd_repstat = VOP_CREATE(ndp->ni_dvp,
			    &ndp->ni_vp, &ndp->ni_cnd, &nvap->na_vattr);
			vput(ndp->ni_dvp);
			nfsvno_relpathbuf(ndp);
			if (!nd->nd_repstat) {
				if (*exclusive_flagp) {
					*exclusive_flagp = 0;
					NFSVNO_ATTRINIT(nvap);
					nvap->na_atime.tv_sec = cverf[0];
					nvap->na_atime.tv_nsec = cverf[1];
					nd->nd_repstat = VOP_SETATTR(ndp->ni_vp,
					    &nvap->na_vattr, cred);
				} else {
					nfsrv_fixattr(nd, ndp->ni_vp, nvap,
					    aclp, p, attrbitp, exp);
				}
			}
			vp = ndp->ni_vp;
		} else {
			if (ndp->ni_startdir)
				vrele(ndp->ni_startdir);
			nfsvno_relpathbuf(ndp);
			vp = ndp->ni_vp;
			if (create == NFSV4OPEN_CREATE) {
				if (ndp->ni_dvp == vp)
					vrele(ndp->ni_dvp);
				else
					vput(ndp->ni_dvp);
			}
			if (NFSVNO_ISSETSIZE(nvap) && vp->v_type == VREG) {
				if (ndp->ni_cnd.cn_flags & RDONLY)
					NFSVNO_SETEXRDONLY(&nes);
				else
					NFSVNO_EXINIT(&nes);
				nd->nd_repstat = nfsvno_accchk(vp, 
				    VWRITE, cred, &nes, p,
				    NFSACCCHK_NOOVERRIDE,
				    NFSACCCHK_VPISLOCKED, NULL);
				nd->nd_repstat = nfsrv_opencheck(clientid,
				    stateidp, stp, vp, nd, p, nd->nd_repstat);
				if (!nd->nd_repstat) {
					tempsize = nvap->na_size;
					NFSVNO_ATTRINIT(nvap);
					nvap->na_size = tempsize;
					nd->nd_repstat = VOP_SETATTR(vp,
					    &nvap->na_vattr, cred);
				}
			} else if (vp->v_type == VREG) {
				nd->nd_repstat = nfsrv_opencheck(clientid,
				    stateidp, stp, vp, nd, p, nd->nd_repstat);
			}
		}
	} else {
		if (ndp->ni_cnd.cn_flags & HASBUF)
			nfsvno_relpathbuf(ndp);
		if (ndp->ni_startdir && create == NFSV4OPEN_CREATE) {
			vrele(ndp->ni_startdir);
			if (ndp->ni_dvp == ndp->ni_vp)
				vrele(ndp->ni_dvp);
			else
				vput(ndp->ni_dvp);
			if (ndp->ni_vp)
				vput(ndp->ni_vp);
		}
	}
	*vpp = vp;

	NFSEXITCODE2(0, nd);
}

/*
 * Updates the file rev and sets the mtime and ctime
 * to the current clock time, returning the va_filerev and va_Xtime
 * values.
 */
void
nfsvno_updfilerev(struct vnode *vp, struct nfsvattr *nvap,
    struct ucred *cred, struct thread *p)
{
	struct vattr va;

	VATTR_NULL(&va);
	vfs_timestamp(&va.va_mtime);
	(void) VOP_SETATTR(vp, &va, cred);
	(void) nfsvno_getattr(vp, nvap, cred, p, 1);
}

/*
 * Glue routine to nfsv4_fillattr().
 */
int
nfsvno_fillattr(struct nfsrv_descript *nd, struct mount *mp, struct vnode *vp,
    struct nfsvattr *nvap, fhandle_t *fhp, int rderror, nfsattrbit_t *attrbitp,
    struct ucred *cred, struct thread *p, int isdgram, int reterr,
    int supports_nfsv4acls, int at_root, uint64_t mounted_on_fileno)
{
	int error;

	error = nfsv4_fillattr(nd, mp, vp, NULL, &nvap->na_vattr, fhp, rderror,
	    attrbitp, cred, p, isdgram, reterr, supports_nfsv4acls, at_root,
	    mounted_on_fileno);
	NFSEXITCODE2(0, nd);
	return (error);
}

/* Since the Readdir vnode ops vary, put the entire functions in here. */
/*
 * nfs readdir service
 * - mallocs what it thinks is enough to read
 *	count rounded up to a multiple of DIRBLKSIZ <= NFS_MAXREADDIR
 * - calls VOP_READDIR()
 * - loops around building the reply
 *	if the output generated exceeds count break out of loop
 *	The NFSM_CLGET macro is used here so that the reply will be packed
 *	tightly in mbuf clusters.
 * - it trims out records with d_fileno == 0
 *	this doesn't matter for Unix clients, but they might confuse clients
 *	for other os'.
 * - it trims out records with d_type == DT_WHT
 *	these cannot be seen through NFS (unless we extend the protocol)
 *     The alternate call nfsrvd_readdirplus() does lookups as well.
 * PS: The NFS protocol spec. does not clarify what the "count" byte
 *	argument is a count of.. just name strings and file id's or the
 *	entire reply rpc or ...
 *	I tried just file name and id sizes and it confused the Sun client,
 *	so I am using the full rpc size now. The "paranoia.." comment refers
 *	to including the status longwords that are not a part of the dir.
 *	"entry" structures, but are in the rpc.
 */
int
nfsrvd_readdir(struct nfsrv_descript *nd, int isdgram,
    struct vnode *vp, struct thread *p, struct nfsexstuff *exp)
{
	struct dirent *dp;
	u_int32_t *tl;
	int dirlen;
	char *cpos, *cend, *rbuf;
	struct nfsvattr at;
	int nlen, error = 0, getret = 1;
	int siz, cnt, fullsiz, eofflag, ncookies;
	u_int64_t off, toff, verf;
	u_long *cookies = NULL, *cookiep;
	struct uio io;
	struct iovec iv;
	int not_zfs;

	if (nd->nd_repstat) {
		nfsrv_postopattr(nd, getret, &at);
		goto out;
	}
	if (nd->nd_flag & ND_NFSV2) {
		NFSM_DISSECT(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
		off = fxdr_unsigned(u_quad_t, *tl++);
	} else {
		NFSM_DISSECT(tl, u_int32_t *, 5 * NFSX_UNSIGNED);
		off = fxdr_hyper(tl);
		tl += 2;
		verf = fxdr_hyper(tl);
		tl += 2;
	}
	toff = off;
	cnt = fxdr_unsigned(int, *tl);
	if (cnt > NFS_SRVMAXDATA(nd) || cnt < 0)
		cnt = NFS_SRVMAXDATA(nd);
	siz = ((cnt + DIRBLKSIZ - 1) & ~(DIRBLKSIZ - 1));
	fullsiz = siz;
	if (nd->nd_flag & ND_NFSV3) {
		nd->nd_repstat = getret = nfsvno_getattr(vp, &at, nd->nd_cred,
		    p, 1);
#if 0
		/*
		 * va_filerev is not sufficient as a cookie verifier,
		 * since it is not supposed to change when entries are
		 * removed/added unless that offset cookies returned to
		 * the client are no longer valid.
		 */
		if (!nd->nd_repstat && toff && verf != at.na_filerev)
			nd->nd_repstat = NFSERR_BAD_COOKIE;
#endif
	}
	if (!nd->nd_repstat && vp->v_type != VDIR)
		nd->nd_repstat = NFSERR_NOTDIR;
	if (nd->nd_repstat == 0 && cnt == 0) {
		if (nd->nd_flag & ND_NFSV2)
			/* NFSv2 does not have NFSERR_TOOSMALL */
			nd->nd_repstat = EPERM;
		else
			nd->nd_repstat = NFSERR_TOOSMALL;
	}
	if (!nd->nd_repstat)
		nd->nd_repstat = nfsvno_accchk(vp, VEXEC,
		    nd->nd_cred, exp, p, NFSACCCHK_NOOVERRIDE,
		    NFSACCCHK_VPISLOCKED, NULL);
	if (nd->nd_repstat) {
		vput(vp);
		if (nd->nd_flag & ND_NFSV3)
			nfsrv_postopattr(nd, getret, &at);
		goto out;
	}
	not_zfs = strcmp(vp->v_mount->mnt_vfc->vfc_name, "zfs");
	MALLOC(rbuf, caddr_t, siz, M_TEMP, M_WAITOK);
again:
	eofflag = 0;
	if (cookies) {
		free((caddr_t)cookies, M_TEMP);
		cookies = NULL;
	}

	iv.iov_base = rbuf;
	iv.iov_len = siz;
	io.uio_iov = &iv;
	io.uio_iovcnt = 1;
	io.uio_offset = (off_t)off;
	io.uio_resid = siz;
	io.uio_segflg = UIO_SYSSPACE;
	io.uio_rw = UIO_READ;
	io.uio_td = NULL;
	nd->nd_repstat = VOP_READDIR(vp, &io, nd->nd_cred, &eofflag, &ncookies,
	    &cookies);
	off = (u_int64_t)io.uio_offset;
	if (io.uio_resid)
		siz -= io.uio_resid;

	if (!cookies && !nd->nd_repstat)
		nd->nd_repstat = NFSERR_PERM;
	if (nd->nd_flag & ND_NFSV3) {
		getret = nfsvno_getattr(vp, &at, nd->nd_cred, p, 1);
		if (!nd->nd_repstat)
			nd->nd_repstat = getret;
	}

	/*
	 * Handles the failed cases. nd->nd_repstat == 0 past here.
	 */
	if (nd->nd_repstat) {
		vput(vp);
		free((caddr_t)rbuf, M_TEMP);
		if (cookies)
			free((caddr_t)cookies, M_TEMP);
		if (nd->nd_flag & ND_NFSV3)
			nfsrv_postopattr(nd, getret, &at);
		goto out;
	}
	/*
	 * If nothing read, return eof
	 * rpc reply
	 */
	if (siz == 0) {
		vput(vp);
		if (nd->nd_flag & ND_NFSV2) {
			NFSM_BUILD(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
		} else {
			nfsrv_postopattr(nd, getret, &at);
			NFSM_BUILD(tl, u_int32_t *, 4 * NFSX_UNSIGNED);
			txdr_hyper(at.na_filerev, tl);
			tl += 2;
		}
		*tl++ = newnfs_false;
		*tl = newnfs_true;
		FREE((caddr_t)rbuf, M_TEMP);
		FREE((caddr_t)cookies, M_TEMP);
		goto out;
	}

	/*
	 * Check for degenerate cases of nothing useful read.
	 * If so go try again
	 */
	cpos = rbuf;
	cend = rbuf + siz;
	dp = (struct dirent *)cpos;
	cookiep = cookies;

	/*
	 * For some reason FreeBSD's ufs_readdir() chooses to back the
	 * directory offset up to a block boundary, so it is necessary to
	 * skip over the records that precede the requested offset. This
	 * requires the assumption that file offset cookies monotonically
	 * increase.
	 * Since the offset cookies don't monotonically increase for ZFS,
	 * this is not done when ZFS is the file system.
	 */
	while (cpos < cend && ncookies > 0 &&
	    (dp->d_fileno == 0 || dp->d_type == DT_WHT ||
	     (not_zfs != 0 && ((u_quad_t)(*cookiep)) <= toff))) {
		cpos += dp->d_reclen;
		dp = (struct dirent *)cpos;
		cookiep++;
		ncookies--;
	}
	if (cpos >= cend || ncookies == 0) {
		siz = fullsiz;
		toff = off;
		goto again;
	}
	vput(vp);

	/*
	 * dirlen is the size of the reply, including all XDR and must
	 * not exceed cnt. For NFSv2, RFC1094 didn't clearly indicate
	 * if the XDR should be included in "count", but to be safe, we do.
	 * (Include the two booleans at the end of the reply in dirlen now.)
	 */
	if (nd->nd_flag & ND_NFSV3) {
		nfsrv_postopattr(nd, getret, &at);
		NFSM_BUILD(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
		txdr_hyper(at.na_filerev, tl);
		dirlen = NFSX_V3POSTOPATTR + NFSX_VERF + 2 * NFSX_UNSIGNED;
	} else {
		dirlen = 2 * NFSX_UNSIGNED;
	}

	/* Loop through the records and build reply */
	while (cpos < cend && ncookies > 0) {
		nlen = dp->d_namlen;
		if (dp->d_fileno != 0 && dp->d_type != DT_WHT &&
			nlen <= NFS_MAXNAMLEN) {
			if (nd->nd_flag & ND_NFSV3)
				dirlen += (6*NFSX_UNSIGNED + NFSM_RNDUP(nlen));
			else
				dirlen += (4*NFSX_UNSIGNED + NFSM_RNDUP(nlen));
			if (dirlen > cnt) {
				eofflag = 0;
				break;
			}

			/*
			 * Build the directory record xdr from
			 * the dirent entry.
			 */
			if (nd->nd_flag & ND_NFSV3) {
				NFSM_BUILD(tl, u_int32_t *, 3 * NFSX_UNSIGNED);
				*tl++ = newnfs_true;
				*tl++ = 0;
			} else {
				NFSM_BUILD(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
				*tl++ = newnfs_true;
			}
			*tl = txdr_unsigned(dp->d_fileno);
			(void) nfsm_strtom(nd, dp->d_name, nlen);
			if (nd->nd_flag & ND_NFSV3) {
				NFSM_BUILD(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
				*tl++ = 0;
			} else
				NFSM_BUILD(tl, u_int32_t *, NFSX_UNSIGNED);
			*tl = txdr_unsigned(*cookiep);
		}
		cpos += dp->d_reclen;
		dp = (struct dirent *)cpos;
		cookiep++;
		ncookies--;
	}
	if (cpos < cend)
		eofflag = 0;
	NFSM_BUILD(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
	*tl++ = newnfs_false;
	if (eofflag)
		*tl = newnfs_true;
	else
		*tl = newnfs_false;
	FREE((caddr_t)rbuf, M_TEMP);
	FREE((caddr_t)cookies, M_TEMP);

out:
	NFSEXITCODE2(0, nd);
	return (0);
nfsmout:
	vput(vp);
	NFSEXITCODE2(error, nd);
	return (error);
}

/*
 * Readdirplus for V3 and Readdir for V4.
 */
int
nfsrvd_readdirplus(struct nfsrv_descript *nd, int isdgram,
    struct vnode *vp, struct thread *p, struct nfsexstuff *exp)
{
	struct dirent *dp;
	u_int32_t *tl;
	int dirlen;
	char *cpos, *cend, *rbuf;
	struct vnode *nvp;
	fhandle_t nfh;
	struct nfsvattr nva, at, *nvap = &nva;
	struct mbuf *mb0, *mb1;
	struct nfsreferral *refp;
	int nlen, r, error = 0, getret = 1, usevget = 1;
	int siz, cnt, fullsiz, eofflag, ncookies, entrycnt;
	caddr_t bpos0, bpos1;
	u_int64_t off, toff, verf;
	u_long *cookies = NULL, *cookiep;
	nfsattrbit_t attrbits, rderrbits, savbits;
	struct uio io;
	struct iovec iv;
	struct componentname cn;
	int at_root, needs_unbusy, not_zfs, supports_nfsv4acls;
	struct mount *mp, *new_mp;
	uint64_t mounted_on_fileno;

	if (nd->nd_repstat) {
		nfsrv_postopattr(nd, getret, &at);
		goto out;
	}
	NFSM_DISSECT(tl, u_int32_t *, 6 * NFSX_UNSIGNED);
	off = fxdr_hyper(tl);
	toff = off;
	tl += 2;
	verf = fxdr_hyper(tl);
	tl += 2;
	siz = fxdr_unsigned(int, *tl++);
	cnt = fxdr_unsigned(int, *tl);

	/*
	 * Use the server's maximum data transfer size as the upper bound
	 * on reply datalen.
	 */
	if (cnt > NFS_SRVMAXDATA(nd) || cnt < 0)
		cnt = NFS_SRVMAXDATA(nd);

	/*
	 * siz is a "hint" of how much directory information (name, fileid,
	 * cookie) should be in the reply. At least one client "hints" 0,
	 * so I set it to cnt for that case. I also round it up to the
	 * next multiple of DIRBLKSIZ.
	 */
	if (siz <= 0)
		siz = cnt;
	siz = ((siz + DIRBLKSIZ - 1) & ~(DIRBLKSIZ - 1));

	if (nd->nd_flag & ND_NFSV4) {
		error = nfsrv_getattrbits(nd, &attrbits, NULL, NULL);
		if (error)
			goto nfsmout;
		NFSSET_ATTRBIT(&savbits, &attrbits);
		NFSCLRNOTFILLABLE_ATTRBIT(&attrbits);
		NFSZERO_ATTRBIT(&rderrbits);
		NFSSETBIT_ATTRBIT(&rderrbits, NFSATTRBIT_RDATTRERROR);
	} else {
		NFSZERO_ATTRBIT(&attrbits);
	}
	fullsiz = siz;
	nd->nd_repstat = getret = nfsvno_getattr(vp, &at, nd->nd_cred, p, 1);
	if (!nd->nd_repstat) {
	    if (off && verf != at.na_filerev) {
		/*
		 * va_filerev is not sufficient as a cookie verifier,
		 * since it is not supposed to change when entries are
		 * removed/added unless that offset cookies returned to
		 * the client are no longer valid.
		 */
#if 0
		if (nd->nd_flag & ND_NFSV4) {
			nd->nd_repstat = NFSERR_NOTSAME;
		} else {
			nd->nd_repstat = NFSERR_BAD_COOKIE;
		}
#endif
	    } else if ((nd->nd_flag & ND_NFSV4) && off == 0 && verf != 0) {
		nd->nd_repstat = NFSERR_BAD_COOKIE;
	    }
	}
	if (!nd->nd_repstat && vp->v_type != VDIR)
		nd->nd_repstat = NFSERR_NOTDIR;
	if (!nd->nd_repstat && cnt == 0)
		nd->nd_repstat = NFSERR_TOOSMALL;
	if (!nd->nd_repstat)
		nd->nd_repstat = nfsvno_accchk(vp, VEXEC,
		    nd->nd_cred, exp, p, NFSACCCHK_NOOVERRIDE,
		    NFSACCCHK_VPISLOCKED, NULL);
	if (nd->nd_repstat) {
		vput(vp);
		if (nd->nd_flag & ND_NFSV3)
			nfsrv_postopattr(nd, getret, &at);
		goto out;
	}
	not_zfs = strcmp(vp->v_mount->mnt_vfc->vfc_name, "zfs");

	MALLOC(rbuf, caddr_t, siz, M_TEMP, M_WAITOK);
again:
	eofflag = 0;
	if (cookies) {
		free((caddr_t)cookies, M_TEMP);
		cookies = NULL;
	}

	iv.iov_base = rbuf;
	iv.iov_len = siz;
	io.uio_iov = &iv;
	io.uio_iovcnt = 1;
	io.uio_offset = (off_t)off;
	io.uio_resid = siz;
	io.uio_segflg = UIO_SYSSPACE;
	io.uio_rw = UIO_READ;
	io.uio_td = NULL;
	nd->nd_repstat = VOP_READDIR(vp, &io, nd->nd_cred, &eofflag, &ncookies,
	    &cookies);
	off = (u_int64_t)io.uio_offset;
	if (io.uio_resid)
		siz -= io.uio_resid;

	getret = nfsvno_getattr(vp, &at, nd->nd_cred, p, 1);

	if (!cookies && !nd->nd_repstat)
		nd->nd_repstat = NFSERR_PERM;
	if (!nd->nd_repstat)
		nd->nd_repstat = getret;
	if (nd->nd_repstat) {
		vput(vp);
		if (cookies)
			free((caddr_t)cookies, M_TEMP);
		free((caddr_t)rbuf, M_TEMP);
		if (nd->nd_flag & ND_NFSV3)
			nfsrv_postopattr(nd, getret, &at);
		goto out;
	}
	/*
	 * If nothing read, return eof
	 * rpc reply
	 */
	if (siz == 0) {
		vput(vp);
		if (nd->nd_flag & ND_NFSV3)
			nfsrv_postopattr(nd, getret, &at);
		NFSM_BUILD(tl, u_int32_t *, 4 * NFSX_UNSIGNED);
		txdr_hyper(at.na_filerev, tl);
		tl += 2;
		*tl++ = newnfs_false;
		*tl = newnfs_true;
		free((caddr_t)cookies, M_TEMP);
		free((caddr_t)rbuf, M_TEMP);
		goto out;
	}

	/*
	 * Check for degenerate cases of nothing useful read.
	 * If so go try again
	 */
	cpos = rbuf;
	cend = rbuf + siz;
	dp = (struct dirent *)cpos;
	cookiep = cookies;

	/*
	 * For some reason FreeBSD's ufs_readdir() chooses to back the
	 * directory offset up to a block boundary, so it is necessary to
	 * skip over the records that precede the requested offset. This
	 * requires the assumption that file offset cookies monotonically
	 * increase.
	 * Since the offset cookies don't monotonically increase for ZFS,
	 * this is not done when ZFS is the file system.
	 */
	while (cpos < cend && ncookies > 0 &&
	  (dp->d_fileno == 0 || dp->d_type == DT_WHT ||
	   (not_zfs != 0 && ((u_quad_t)(*cookiep)) <= toff) ||
	   ((nd->nd_flag & ND_NFSV4) &&
	    ((dp->d_namlen == 1 && dp->d_name[0] == '.') ||
	     (dp->d_namlen==2 && dp->d_name[0]=='.' && dp->d_name[1]=='.'))))) {
		cpos += dp->d_reclen;
		dp = (struct dirent *)cpos;
		cookiep++;
		ncookies--;
	}
	if (cpos >= cend || ncookies == 0) {
		siz = fullsiz;
		toff = off;
		goto again;
	}

	/*
	 * Busy the file system so that the mount point won't go away
	 * and, as such, VFS_VGET() can be used safely.
	 */
	mp = vp->v_mount;
	vfs_ref(mp);
	NFSVOPUNLOCK(vp, 0);
	nd->nd_repstat = vfs_busy(mp, 0);
	vfs_rel(mp);
	if (nd->nd_repstat != 0) {
		vrele(vp);
		free(cookies, M_TEMP);
		free(rbuf, M_TEMP);
		if (nd->nd_flag & ND_NFSV3)
			nfsrv_postopattr(nd, getret, &at);
		goto out;
	}

	/*
	 * Save this position, in case there is an error before one entry
	 * is created.
	 */
	mb0 = nd->nd_mb;
	bpos0 = nd->nd_bpos;

	/*
	 * Fill in the first part of the reply.
	 * dirlen is the reply length in bytes and cannot exceed cnt.
	 * (Include the two booleans at the end of the reply in dirlen now,
	 *  so we recognize when we have exceeded cnt.)
	 */
	if (nd->nd_flag & ND_NFSV3) {
		dirlen = NFSX_V3POSTOPATTR + NFSX_VERF + 2 * NFSX_UNSIGNED;
		nfsrv_postopattr(nd, getret, &at);
	} else {
		dirlen = NFSX_VERF + 2 * NFSX_UNSIGNED;
	}
	NFSM_BUILD(tl, u_int32_t *, NFSX_VERF);
	txdr_hyper(at.na_filerev, tl);

	/*
	 * Save this position, in case there is an empty reply needed.
	 */
	mb1 = nd->nd_mb;
	bpos1 = nd->nd_bpos;

	/* Loop through the records and build reply */
	entrycnt = 0;
	while (cpos < cend && ncookies > 0 && dirlen < cnt) {
		nlen = dp->d_namlen;
		if (dp->d_fileno != 0 && dp->d_type != DT_WHT &&
		    nlen <= NFS_MAXNAMLEN &&
		    ((nd->nd_flag & ND_NFSV3) || nlen > 2 ||
		     (nlen==2 && (dp->d_name[0]!='.' || dp->d_name[1]!='.'))
		      || (nlen == 1 && dp->d_name[0] != '.'))) {
			/*
			 * Save the current position in the reply, in case
			 * this entry exceeds cnt.
			 */
			mb1 = nd->nd_mb;
			bpos1 = nd->nd_bpos;
	
			/*
			 * For readdir_and_lookup get the vnode using
			 * the file number.
			 */
			nvp = NULL;
			refp = NULL;
			r = 0;
			at_root = 0;
			needs_unbusy = 0;
			new_mp = mp;
			mounted_on_fileno = (uint64_t)dp->d_fileno;
			if ((nd->nd_flag & ND_NFSV3) ||
			    NFSNONZERO_ATTRBIT(&savbits)) {
				if (nd->nd_flag & ND_NFSV4)
					refp = nfsv4root_getreferral(NULL,
					    vp, dp->d_fileno);
				if (refp == NULL) {
					if (usevget)
						r = VFS_VGET(mp, dp->d_fileno,
						    LK_SHARED, &nvp);
					else
						r = EOPNOTSUPP;
					if (r == EOPNOTSUPP) {
						if (usevget) {
							usevget = 0;
							cn.cn_nameiop = LOOKUP;
							cn.cn_lkflags =
							    LK_SHARED |
							    LK_RETRY;
							cn.cn_cred =
							    nd->nd_cred;
							cn.cn_thread = p;
						}
						cn.cn_nameptr = dp->d_name;
						cn.cn_namelen = nlen;
						cn.cn_flags = ISLASTCN |
						    NOFOLLOW | LOCKLEAF;
						if (nlen == 2 &&
						    dp->d_name[0] == '.' &&
						    dp->d_name[1] == '.')
							cn.cn_flags |=
							    ISDOTDOT;
						if (NFSVOPLOCK(vp, LK_SHARED)
						    != 0) {
							nd->nd_repstat = EPERM;
							break;
						}
						if ((vp->v_vflag & VV_ROOT) != 0
						    && (cn.cn_flags & ISDOTDOT)
						    != 0) {
							vref(vp);
							nvp = vp;
							r = 0;
						} else {
							r = VOP_LOOKUP(vp, &nvp,
							    &cn);
							if (vp != nvp)
								NFSVOPUNLOCK(vp,
								    0);
						}
					}

					/*
					 * For NFSv4, check to see if nvp is
					 * a mount point and get the mount
					 * point vnode, as required.
					 */
					if (r == 0 &&
					    nfsrv_enable_crossmntpt != 0 &&
					    (nd->nd_flag & ND_NFSV4) != 0 &&
					    nvp->v_type == VDIR &&
					    nvp->v_mountedhere != NULL) {
						new_mp = nvp->v_mountedhere;
						r = vfs_busy(new_mp, 0);
						vput(nvp);
						nvp = NULL;
						if (r == 0) {
							r = VFS_ROOT(new_mp,
							    LK_SHARED, &nvp);
							needs_unbusy = 1;
							if (r == 0)
								at_root = 1;
						}
					}
				}
				if (!r) {
				    if (refp == NULL &&
					((nd->nd_flag & ND_NFSV3) ||
					 NFSNONZERO_ATTRBIT(&attrbits))) {
					r = nfsvno_getfh(nvp, &nfh, p);
					if (!r)
					    r = nfsvno_getattr(nvp, nvap,
						nd->nd_cred, p, 1);
				    }
				} else {
				    nvp = NULL;
				}
				if (r) {
					if (!NFSISSET_ATTRBIT(&attrbits,
					    NFSATTRBIT_RDATTRERROR)) {
						if (nvp != NULL)
							vput(nvp);
						if (needs_unbusy != 0)
							vfs_unbusy(new_mp);
						nd->nd_repstat = r;
						break;
					}
				}
			}

			/*
			 * Build the directory record xdr
			 */
			if (nd->nd_flag & ND_NFSV3) {
				NFSM_BUILD(tl, u_int32_t *, 3 * NFSX_UNSIGNED);
				*tl++ = newnfs_true;
				*tl++ = 0;
				*tl = txdr_unsigned(dp->d_fileno);
				dirlen += nfsm_strtom(nd, dp->d_name, nlen);
				NFSM_BUILD(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
				*tl++ = 0;
				*tl = txdr_unsigned(*cookiep);
				nfsrv_postopattr(nd, 0, nvap);
				dirlen += nfsm_fhtom(nd,(u_int8_t *)&nfh,0,1);
				dirlen += (5*NFSX_UNSIGNED+NFSX_V3POSTOPATTR);
				if (nvp != NULL)
					vput(nvp);
			} else {
				NFSM_BUILD(tl, u_int32_t *, 3 * NFSX_UNSIGNED);
				*tl++ = newnfs_true;
				*tl++ = 0;
				*tl = txdr_unsigned(*cookiep);
				dirlen += nfsm_strtom(nd, dp->d_name, nlen);
				if (nvp != NULL) {
					supports_nfsv4acls =
					    nfs_supportsnfsv4acls(nvp);
					NFSVOPUNLOCK(nvp, 0);
				} else
					supports_nfsv4acls = 0;
				if (refp != NULL) {
					dirlen += nfsrv_putreferralattr(nd,
					    &savbits, refp, 0,
					    &nd->nd_repstat);
					if (nd->nd_repstat) {
						if (nvp != NULL)
							vrele(nvp);
						if (needs_unbusy != 0)
							vfs_unbusy(new_mp);
						break;
					}
				} else if (r) {
					dirlen += nfsvno_fillattr(nd, new_mp,
					    nvp, nvap, &nfh, r, &rderrbits,
					    nd->nd_cred, p, isdgram, 0,
					    supports_nfsv4acls, at_root,
					    mounted_on_fileno);
				} else {
					dirlen += nfsvno_fillattr(nd, new_mp,
					    nvp, nvap, &nfh, r, &attrbits,
					    nd->nd_cred, p, isdgram, 0,
					    supports_nfsv4acls, at_root,
					    mounted_on_fileno);
				}
				if (nvp != NULL)
					vrele(nvp);
				dirlen += (3 * NFSX_UNSIGNED);
			}
			if (needs_unbusy != 0)
				vfs_unbusy(new_mp);
			if (dirlen <= cnt)
				entrycnt++;
		}
		cpos += dp->d_reclen;
		dp = (struct dirent *)cpos;
		cookiep++;
		ncookies--;
	}
	vrele(vp);
	vfs_unbusy(mp);

	/*
	 * If dirlen > cnt, we must strip off the last entry. If that
	 * results in an empty reply, report NFSERR_TOOSMALL.
	 */
	if (dirlen > cnt || nd->nd_repstat) {
		if (!nd->nd_repstat && entrycnt == 0)
			nd->nd_repstat = NFSERR_TOOSMALL;
		if (nd->nd_repstat)
			newnfs_trimtrailing(nd, mb0, bpos0);
		else
			newnfs_trimtrailing(nd, mb1, bpos1);
		eofflag = 0;
	} else if (cpos < cend)
		eofflag = 0;
	if (!nd->nd_repstat) {
		NFSM_BUILD(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
		*tl++ = newnfs_false;
		if (eofflag)
			*tl = newnfs_true;
		else
			*tl = newnfs_false;
	}
	FREE((caddr_t)cookies, M_TEMP);
	FREE((caddr_t)rbuf, M_TEMP);

out:
	NFSEXITCODE2(0, nd);
	return (0);
nfsmout:
	vput(vp);
	NFSEXITCODE2(error, nd);
	return (error);
}

/*
 * Get the settable attributes out of the mbuf list.
 * (Return 0 or EBADRPC)
 */
int
nfsrv_sattr(struct nfsrv_descript *nd, struct nfsvattr *nvap,
    nfsattrbit_t *attrbitp, NFSACL_T *aclp, struct thread *p)
{
	u_int32_t *tl;
	struct nfsv2_sattr *sp;
	int error = 0, toclient = 0;

	switch (nd->nd_flag & (ND_NFSV2 | ND_NFSV3 | ND_NFSV4)) {
	case ND_NFSV2:
		NFSM_DISSECT(sp, struct nfsv2_sattr *, NFSX_V2SATTR);
		/*
		 * Some old clients didn't fill in the high order 16bits.
		 * --> check the low order 2 bytes for 0xffff
		 */
		if ((fxdr_unsigned(int, sp->sa_mode) & 0xffff) != 0xffff)
			nvap->na_mode = nfstov_mode(sp->sa_mode);
		if (sp->sa_uid != newnfs_xdrneg1)
			nvap->na_uid = fxdr_unsigned(uid_t, sp->sa_uid);
		if (sp->sa_gid != newnfs_xdrneg1)
			nvap->na_gid = fxdr_unsigned(gid_t, sp->sa_gid);
		if (sp->sa_size != newnfs_xdrneg1)
			nvap->na_size = fxdr_unsigned(u_quad_t, sp->sa_size);
		if (sp->sa_atime.nfsv2_sec != newnfs_xdrneg1) {
#ifdef notyet
			fxdr_nfsv2time(&sp->sa_atime, &nvap->na_atime);
#else
			nvap->na_atime.tv_sec =
				fxdr_unsigned(u_int32_t,sp->sa_atime.nfsv2_sec);
			nvap->na_atime.tv_nsec = 0;
#endif
		}
		if (sp->sa_mtime.nfsv2_sec != newnfs_xdrneg1)
			fxdr_nfsv2time(&sp->sa_mtime, &nvap->na_mtime);
		break;
	case ND_NFSV3:
		NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
		if (*tl == newnfs_true) {
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			nvap->na_mode = nfstov_mode(*tl);
		}
		NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
		if (*tl == newnfs_true) {
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			nvap->na_uid = fxdr_unsigned(uid_t, *tl);
		}
		NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
		if (*tl == newnfs_true) {
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			nvap->na_gid = fxdr_unsigned(gid_t, *tl);
		}
		NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
		if (*tl == newnfs_true) {
			NFSM_DISSECT(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
			nvap->na_size = fxdr_hyper(tl);
		}
		NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
		switch (fxdr_unsigned(int, *tl)) {
		case NFSV3SATTRTIME_TOCLIENT:
			NFSM_DISSECT(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
			fxdr_nfsv3time(tl, &nvap->na_atime);
			toclient = 1;
			break;
		case NFSV3SATTRTIME_TOSERVER:
			vfs_timestamp(&nvap->na_atime);
			nvap->na_vaflags |= VA_UTIMES_NULL;
			break;
		};
		NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
		switch (fxdr_unsigned(int, *tl)) {
		case NFSV3SATTRTIME_TOCLIENT:
			NFSM_DISSECT(tl, u_int32_t *, 2 * NFSX_UNSIGNED);
			fxdr_nfsv3time(tl, &nvap->na_mtime);
			nvap->na_vaflags &= ~VA_UTIMES_NULL;
			break;
		case NFSV3SATTRTIME_TOSERVER:
			vfs_timestamp(&nvap->na_mtime);
			if (!toclient)
				nvap->na_vaflags |= VA_UTIMES_NULL;
			break;
		};
		break;
	case ND_NFSV4:
		error = nfsv4_sattr(nd, nvap, attrbitp, aclp, p);
	};
nfsmout:
	NFSEXITCODE2(error, nd);
	return (error);
}

/*
 * Handle the setable attributes for V4.
 * Returns NFSERR_BADXDR if it can't be parsed, 0 otherwise.
 */
int
nfsv4_sattr(struct nfsrv_descript *nd, struct nfsvattr *nvap,
    nfsattrbit_t *attrbitp, NFSACL_T *aclp, struct thread *p)
{
	u_int32_t *tl;
	int attrsum = 0;
	int i, j;
	int error, attrsize, bitpos, aclsize, aceerr, retnotsup = 0;
	int toclient = 0;
	u_char *cp, namestr[NFSV4_SMALLSTR + 1];
	uid_t uid;
	gid_t gid;

	error = nfsrv_getattrbits(nd, attrbitp, NULL, &retnotsup);
	if (error)
		goto nfsmout;
	NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
	attrsize = fxdr_unsigned(int, *tl);

	/*
	 * Loop around getting the setable attributes. If an unsupported
	 * one is found, set nd_repstat == NFSERR_ATTRNOTSUPP and return.
	 */
	if (retnotsup) {
		nd->nd_repstat = NFSERR_ATTRNOTSUPP;
		bitpos = NFSATTRBIT_MAX;
	} else {
		bitpos = 0;
	}
	for (; bitpos < NFSATTRBIT_MAX; bitpos++) {
	    if (attrsum > attrsize) {
		error = NFSERR_BADXDR;
		goto nfsmout;
	    }
	    if (NFSISSET_ATTRBIT(attrbitp, bitpos))
		switch (bitpos) {
		case NFSATTRBIT_SIZE:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_HYPER);
			nvap->na_size = fxdr_hyper(tl);
			attrsum += NFSX_HYPER;
			break;
		case NFSATTRBIT_ACL:
			error = nfsrv_dissectacl(nd, aclp, &aceerr, &aclsize,
			    p);
			if (error)
				goto nfsmout;
			if (aceerr && !nd->nd_repstat)
				nd->nd_repstat = aceerr;
			attrsum += aclsize;
			break;
		case NFSATTRBIT_ARCHIVE:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			if (!nd->nd_repstat)
				nd->nd_repstat = NFSERR_ATTRNOTSUPP;
			attrsum += NFSX_UNSIGNED;
			break;
		case NFSATTRBIT_HIDDEN:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			if (!nd->nd_repstat)
				nd->nd_repstat = NFSERR_ATTRNOTSUPP;
			attrsum += NFSX_UNSIGNED;
			break;
		case NFSATTRBIT_MIMETYPE:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			i = fxdr_unsigned(int, *tl);
			error = nfsm_advance(nd, NFSM_RNDUP(i), -1);
			if (error)
				goto nfsmout;
			if (!nd->nd_repstat)
				nd->nd_repstat = NFSERR_ATTRNOTSUPP;
			attrsum += (NFSX_UNSIGNED + NFSM_RNDUP(i));
			break;
		case NFSATTRBIT_MODE:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			nvap->na_mode = nfstov_mode(*tl);
			attrsum += NFSX_UNSIGNED;
			break;
		case NFSATTRBIT_OWNER:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			j = fxdr_unsigned(int, *tl);
			if (j < 0) {
				error = NFSERR_BADXDR;
				goto nfsmout;
			}
			if (j > NFSV4_SMALLSTR)
				cp = malloc(j + 1, M_NFSSTRING, M_WAITOK);
			else
				cp = namestr;
			error = nfsrv_mtostr(nd, cp, j);
			if (error) {
				if (j > NFSV4_SMALLSTR)
					free(cp, M_NFSSTRING);
				goto nfsmout;
			}
			if (!nd->nd_repstat) {
				nd->nd_repstat = nfsv4_strtouid(nd, cp, j, &uid,
				    p);
				if (!nd->nd_repstat)
					nvap->na_uid = uid;
			}
			if (j > NFSV4_SMALLSTR)
				free(cp, M_NFSSTRING);
			attrsum += (NFSX_UNSIGNED + NFSM_RNDUP(j));
			break;
		case NFSATTRBIT_OWNERGROUP:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			j = fxdr_unsigned(int, *tl);
			if (j < 0) {
				error = NFSERR_BADXDR;
				goto nfsmout;
			}
			if (j > NFSV4_SMALLSTR)
				cp = malloc(j + 1, M_NFSSTRING, M_WAITOK);
			else
				cp = namestr;
			error = nfsrv_mtostr(nd, cp, j);
			if (error) {
				if (j > NFSV4_SMALLSTR)
					free(cp, M_NFSSTRING);
				goto nfsmout;
			}
			if (!nd->nd_repstat) {
				nd->nd_repstat = nfsv4_strtogid(nd, cp, j, &gid,
				    p);
				if (!nd->nd_repstat)
					nvap->na_gid = gid;
			}
			if (j > NFSV4_SMALLSTR)
				free(cp, M_NFSSTRING);
			attrsum += (NFSX_UNSIGNED + NFSM_RNDUP(j));
			break;
		case NFSATTRBIT_SYSTEM:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			if (!nd->nd_repstat)
				nd->nd_repstat = NFSERR_ATTRNOTSUPP;
			attrsum += NFSX_UNSIGNED;
			break;
		case NFSATTRBIT_TIMEACCESSSET:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			attrsum += NFSX_UNSIGNED;
			if (fxdr_unsigned(int, *tl)==NFSV4SATTRTIME_TOCLIENT) {
			    NFSM_DISSECT(tl, u_int32_t *, NFSX_V4TIME);
			    fxdr_nfsv4time(tl, &nvap->na_atime);
			    toclient = 1;
			    attrsum += NFSX_V4TIME;
			} else {
			    vfs_timestamp(&nvap->na_atime);
			    nvap->na_vaflags |= VA_UTIMES_NULL;
			}
			break;
		case NFSATTRBIT_TIMEBACKUP:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_V4TIME);
			if (!nd->nd_repstat)
				nd->nd_repstat = NFSERR_ATTRNOTSUPP;
			attrsum += NFSX_V4TIME;
			break;
		case NFSATTRBIT_TIMECREATE:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_V4TIME);
			if (!nd->nd_repstat)
				nd->nd_repstat = NFSERR_ATTRNOTSUPP;
			attrsum += NFSX_V4TIME;
			break;
		case NFSATTRBIT_TIMEMODIFYSET:
			NFSM_DISSECT(tl, u_int32_t *, NFSX_UNSIGNED);
			attrsum += NFSX_UNSIGNED;
			if (fxdr_unsigned(int, *tl)==NFSV4SATTRTIME_TOCLIENT) {
			    NFSM_DISSECT(tl, u_int32_t *, NFSX_V4TIME);
			    fxdr_nfsv4time(tl, &nvap->na_mtime);
			    nvap->na_vaflags &= ~VA_UTIMES_NULL;
			    attrsum += NFSX_V4TIME;
			} else {
			    vfs_timestamp(&nvap->na_mtime);
			    if (!toclient)
				nvap->na_vaflags |= VA_UTIMES_NULL;
			}
			break;
		default:
			nd->nd_repstat = NFSERR_ATTRNOTSUPP;
			/*
			 * set bitpos so we drop out of the loop.
			 */
			bitpos = NFSATTRBIT_MAX;
			break;
		};
	}

	/*
	 * some clients pad the attrlist, so we need to skip over the
	 * padding.
	 */
	if (attrsum > attrsize) {
		error = NFSERR_BADXDR;
	} else {
		attrsize = NFSM_RNDUP(attrsize);
		if (attrsum < attrsize)
			error = nfsm_advance(nd, attrsize - attrsum, -1);
	}
nfsmout:
	NFSEXITCODE2(error, nd);
	return (error);
}

/*
 * Check/setup export credentials.
 */
int
nfsd_excred(struct nfsrv_descript *nd, struct nfsexstuff *exp,
    struct ucred *credanon)
{
	int error = 0;

	/*
	 * Check/setup credentials.
	 */
	if (nd->nd_flag & ND_GSS)
		exp->nes_exflag &= ~MNT_EXPORTANON;

	/*
	 * Check to see if the operation is allowed for this security flavor.
	 * RFC2623 suggests that the NFSv3 Fsinfo RPC be allowed to
	 * AUTH_NONE or AUTH_SYS for file systems requiring RPCSEC_GSS.
	 * Also, allow Secinfo, so that it can acquire the correct flavor(s).
	 */
	if (nfsvno_testexp(nd, exp) &&
	    nd->nd_procnum != NFSV4OP_SECINFO &&
	    nd->nd_procnum != NFSPROC_FSINFO) {
		if (nd->nd_flag & ND_NFSV4)
			error = NFSERR_WRONGSEC;
		else
			error = (NFSERR_AUTHERR | AUTH_TOOWEAK);
		goto out;
	}

	/*
	 * Check to see if the file system is exported V4 only.
	 */
	if (NFSVNO_EXV4ONLY(exp) && !(nd->nd_flag & ND_NFSV4)) {
		error = NFSERR_PROGNOTV4;
		goto out;
	}

	/*
	 * Now, map the user credentials.
	 * (Note that ND_AUTHNONE will only be set for an NFSv3
	 *  Fsinfo RPC. If set for anything else, this code might need
	 *  to change.)
	 */
	if (NFSVNO_EXPORTED(exp) &&
	    ((!(nd->nd_flag & ND_GSS) && nd->nd_cred->cr_uid == 0) ||
	     NFSVNO_EXPORTANON(exp) ||
	     (nd->nd_flag & ND_AUTHNONE))) {
		nd->nd_cred->cr_uid = credanon->cr_uid;
		nd->nd_cred->cr_gid = credanon->cr_gid;
		crsetgroups(nd->nd_cred, credanon->cr_ngroups,
		    credanon->cr_groups);
	}

out:
	NFSEXITCODE2(error, nd);
	return (error);
}

/*
 * Check exports.
 */
int
nfsvno_checkexp(struct mount *mp, struct sockaddr *nam, struct nfsexstuff *exp,
    struct ucred **credp)
{
	int i, error, *secflavors;

	error = VFS_CHECKEXP(mp, nam, &exp->nes_exflag, credp,
	    &exp->nes_numsecflavor, &secflavors);
	if (error) {
		if (nfs_rootfhset) {
			exp->nes_exflag = 0;
			exp->nes_numsecflavor = 0;
			error = 0;
		}
	} else {
		/* Copy the security flavors. */
		for (i = 0; i < exp->nes_numsecflavor; i++)
			exp->nes_secflavors[i] = secflavors[i];
	}
	NFSEXITCODE(error);
	return (error);
}

/*
 * Get a vnode for a file handle and export stuff.
 */
int
nfsvno_fhtovp(struct mount *mp, fhandle_t *fhp, struct sockaddr *nam,
    int lktype, struct vnode **vpp, struct nfsexstuff *exp,
    struct ucred **credp)
{
	int i, error, *secflavors;

	*credp = NULL;
	exp->nes_numsecflavor = 0;
	error = VFS_FHTOVP(mp, &fhp->fh_fid, lktype, vpp);
	if (error != 0)
		/* Make sure the server replies ESTALE to the client. */
		error = ESTALE;
	if (nam && !error) {
		error = VFS_CHECKEXP(mp, nam, &exp->nes_exflag, credp,
		    &exp->nes_numsecflavor, &secflavors);
		if (error) {
			if (nfs_rootfhset) {
				exp->nes_exflag = 0;
				exp->nes_numsecflavor = 0;
				error = 0;
			} else {
				vput(*vpp);
			}
		} else {
			/* Copy the security flavors. */
			for (i = 0; i < exp->nes_numsecflavor; i++)
				exp->nes_secflavors[i] = secflavors[i];
		}
	}
	NFSEXITCODE(error);
	return (error);
}

/*
 * nfsd_fhtovp() - convert a fh to a vnode ptr
 * 	- look up fsid in mount list (if not found ret error)
 *	- get vp and export rights by calling nfsvno_fhtovp()
 *	- if cred->cr_uid == 0 or MNT_EXPORTANON set it to credanon
 *	  for AUTH_SYS
 *	- if mpp != NULL, return the mount point so that it can
 *	  be used for vn_finished_write() by the caller
 */
void
nfsd_fhtovp(struct nfsrv_descript *nd, struct nfsrvfh *nfp, int lktype,
    struct vnode **vpp, struct nfsexstuff *exp,
    struct mount **mpp, int startwrite, struct thread *p)
{
	struct mount *mp;
	struct ucred *credanon;
	fhandle_t *fhp;

	fhp = (fhandle_t *)nfp->nfsrvfh_data;
	/*
	 * Check for the special case of the nfsv4root_fh.
	 */
	mp = vfs_busyfs(&fhp->fh_fsid);
	if (mpp != NULL)
		*mpp = mp;
	if (mp == NULL) {
		*vpp = NULL;
		nd->nd_repstat = ESTALE;
		goto out;
	}

	if (startwrite) {
		vn_start_write(NULL, mpp, V_WAIT);
		if (lktype == LK_SHARED && !(MNT_SHARED_WRITES(mp)))
			lktype = LK_EXCLUSIVE;
	}
	nd->nd_repstat = nfsvno_fhtovp(mp, fhp, nd->nd_nam, lktype, vpp, exp,
	    &credanon);
	vfs_unbusy(mp);

	/*
	 * For NFSv4 without a pseudo root fs, unexported file handles
	 * can be returned, so that Lookup works everywhere.
	 */
	if (!nd->nd_repstat && exp->nes_exflag == 0 &&
	    !(nd->nd_flag & ND_NFSV4)) {
		vput(*vpp);
		nd->nd_repstat = EACCES;
	}

	/*
	 * Personally, I've never seen any point in requiring a
	 * reserved port#, since only in the rare case where the
	 * clients are all boxes with secure system priviledges,
	 * does it provide any enhanced security, but... some people
	 * believe it to be useful and keep putting this code back in.
	 * (There is also some "security checker" out there that
	 *  complains if the nfs server doesn't enforce this.)
	 * However, note the following:
	 * RFC3530 (NFSv4) specifies that a reserved port# not be
	 *	required.
	 * RFC2623 recommends that, if a reserved port# is checked for,
	 *	that there be a way to turn that off--> ifdef'd.
	 */
#ifdef NFS_REQRSVPORT
	if (!nd->nd_repstat) {
		struct sockaddr_in *saddr;
		struct sockaddr_in6 *saddr6;

		saddr = NFSSOCKADDR(nd->nd_nam, struct sockaddr_in *);
		saddr6 = NFSSOCKADDR(nd->nd_nam, struct sockaddr_in6 *);
		if (!(nd->nd_flag & ND_NFSV4) &&
		    ((saddr->sin_family == AF_INET &&
		      ntohs(saddr->sin_port) >= IPPORT_RESERVED) ||
		     (saddr6->sin6_family == AF_INET6 &&
		      ntohs(saddr6->sin6_port) >= IPPORT_RESERVED))) {
			vput(*vpp);
			nd->nd_repstat = (NFSERR_AUTHERR | AUTH_TOOWEAK);
		}
	}
#endif	/* NFS_REQRSVPORT */

	/*
	 * Check/setup credentials.
	 */
	if (!nd->nd_repstat) {
		nd->nd_saveduid = nd->nd_cred->cr_uid;
		nd->nd_repstat = nfsd_excred(nd, exp, credanon);
		if (nd->nd_repstat)
			vput(*vpp);
	}
	if (credanon != NULL)
		crfree(credanon);
	if (nd->nd_repstat) {
		if (startwrite)
			vn_finished_write(mp);
		*vpp = NULL;
		if (mpp != NULL)
			*mpp = NULL;
	}

out:
	NFSEXITCODE2(0, nd);
}

/*
 * glue for fp.
 */
static int
fp_getfvp(struct thread *p, int fd, struct file **fpp, struct vnode **vpp)
{
	struct filedesc *fdp;
	struct file *fp;
	int error = 0;

	fdp = p->td_proc->p_fd;
	if (fd < 0 || fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[fd].fde_file) == NULL) {
		error = EBADF;
		goto out;
	}
	*fpp = fp;

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Called from nfssvc() to update the exports list. Just call
 * vfs_export(). This has to be done, since the v4 root fake fs isn't
 * in the mount list.
 */
int
nfsrv_v4rootexport(void *argp, struct ucred *cred, struct thread *p)
{
	struct nfsex_args *nfsexargp = (struct nfsex_args *)argp;
	int error = 0;
	struct nameidata nd;
	fhandle_t fh;

	error = vfs_export(&nfsv4root_mnt, &nfsexargp->export);
	if ((nfsexargp->export.ex_flags & MNT_DELEXPORT) != 0)
		nfs_rootfhset = 0;
	else if (error == 0) {
		if (nfsexargp->fspec == NULL) {
			error = EPERM;
			goto out;
		}
		/*
		 * If fspec != NULL, this is the v4root path.
		 */
		NDINIT(&nd, LOOKUP, FOLLOW, UIO_USERSPACE,
		    nfsexargp->fspec, p);
		if ((error = namei(&nd)) != 0)
			goto out;
		error = nfsvno_getfh(nd.ni_vp, &fh, p);
		vrele(nd.ni_vp);
		if (!error) {
			nfs_rootfh.nfsrvfh_len = NFSX_MYFH;
			NFSBCOPY((caddr_t)&fh,
			    nfs_rootfh.nfsrvfh_data,
			    sizeof (fhandle_t));
			nfs_rootfhset = 1;
		}
	}

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Get the tcp socket sequence numbers we need.
 * (Maybe this should be moved to the tcp sources?)
 */
int
nfsrv_getsocksndseq(struct socket *so, tcp_seq *maxp, tcp_seq *unap)
{
	struct inpcb *inp;
	struct tcpcb *tp;
	int error = 0;

	inp = sotoinpcb(so);
	KASSERT(inp != NULL, ("nfsrv_getsocksndseq: inp == NULL"));
	INP_RLOCK(inp);
	if (inp->inp_flags & (INP_TIMEWAIT | INP_DROPPED)) {
		INP_RUNLOCK(inp);
		error = EPIPE;
		goto out;
	}
	tp = intotcpcb(inp);
	if (tp->t_state != TCPS_ESTABLISHED) {
		INP_RUNLOCK(inp);
		error = EPIPE;
		goto out;
	}
	*maxp = tp->snd_max;
	*unap = tp->snd_una;
	INP_RUNLOCK(inp);

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * This function needs to test to see if the system is near its limit
 * for memory allocation via malloc() or mget() and return True iff
 * either of these resources are near their limit.
 * XXX (For now, this is just a stub.)
 */
int nfsrv_testmalloclimit = 0;
int
nfsrv_mallocmget_limit(void)
{
	static int printmesg = 0;
	static int testval = 1;

	if (nfsrv_testmalloclimit && (testval++ % 1000) == 0) {
		if ((printmesg++ % 100) == 0)
			printf("nfsd: malloc/mget near limit\n");
		return (1);
	}
	return (0);
}

/*
 * BSD specific initialization of a mount point.
 */
void
nfsd_mntinit(void)
{
	static int inited = 0;

	if (inited)
		return;
	inited = 1;
	nfsv4root_mnt.mnt_flag = (MNT_RDONLY | MNT_EXPORTED);
	TAILQ_INIT(&nfsv4root_mnt.mnt_nvnodelist);
	TAILQ_INIT(&nfsv4root_mnt.mnt_activevnodelist);
	nfsv4root_mnt.mnt_export = NULL;
	TAILQ_INIT(&nfsv4root_opt);
	TAILQ_INIT(&nfsv4root_newopt);
	nfsv4root_mnt.mnt_opt = &nfsv4root_opt;
	nfsv4root_mnt.mnt_optnew = &nfsv4root_newopt;
	nfsv4root_mnt.mnt_nvnodelistsize = 0;
	nfsv4root_mnt.mnt_activevnodelistsize = 0;
}

/*
 * Get a vnode for a file handle, without checking exports, etc.
 */
struct vnode *
nfsvno_getvp(fhandle_t *fhp)
{
	struct mount *mp;
	struct vnode *vp;
	int error;

	mp = vfs_busyfs(&fhp->fh_fsid);
	if (mp == NULL)
		return (NULL);
	error = VFS_FHTOVP(mp, &fhp->fh_fid, LK_EXCLUSIVE, &vp);
	vfs_unbusy(mp);
	if (error)
		return (NULL);
	return (vp);
}

/*
 * Do a local VOP_ADVLOCK().
 */
int
nfsvno_advlock(struct vnode *vp, int ftype, u_int64_t first,
    u_int64_t end, struct thread *td)
{
	int error = 0;
	struct flock fl;
	u_int64_t tlen;

	if (nfsrv_dolocallocks == 0)
		goto out;

	/* Check for VI_DOOMED here, so that VOP_ADVLOCK() isn't performed. */
	if ((vp->v_iflag & VI_DOOMED) != 0) {
		error = EPERM;
		goto out;
	}

	fl.l_whence = SEEK_SET;
	fl.l_type = ftype;
	fl.l_start = (off_t)first;
	if (end == NFS64BITSSET) {
		fl.l_len = 0;
	} else {
		tlen = end - first;
		fl.l_len = (off_t)tlen;
	}
	/*
	 * For FreeBSD8, the l_pid and l_sysid must be set to the same
	 * values for all calls, so that all locks will be held by the
	 * nfsd server. (The nfsd server handles conflicts between the
	 * various clients.)
	 * Since an NFSv4 lockowner is a ClientID plus an array of up to 1024
	 * bytes, so it can't be put in l_sysid.
	 */
	if (nfsv4_sysid == 0)
		nfsv4_sysid = nlm_acquire_next_sysid();
	fl.l_pid = (pid_t)0;
	fl.l_sysid = (int)nfsv4_sysid;

	NFSVOPUNLOCK(vp, 0);
	if (ftype == F_UNLCK)
		error = VOP_ADVLOCK(vp, (caddr_t)td->td_proc, F_UNLCK, &fl,
		    (F_POSIX | F_REMOTE));
	else
		error = VOP_ADVLOCK(vp, (caddr_t)td->td_proc, F_SETLK, &fl,
		    (F_POSIX | F_REMOTE));
	NFSVOPLOCK(vp, LK_EXCLUSIVE | LK_RETRY);

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Check the nfsv4 root exports.
 */
int
nfsvno_v4rootexport(struct nfsrv_descript *nd)
{
	struct ucred *credanon;
	int exflags, error = 0, numsecflavor, *secflavors, i;

	error = vfs_stdcheckexp(&nfsv4root_mnt, nd->nd_nam, &exflags,
	    &credanon, &numsecflavor, &secflavors);
	if (error) {
		error = NFSERR_PROGUNAVAIL;
		goto out;
	}
	if (credanon != NULL)
		crfree(credanon);
	for (i = 0; i < numsecflavor; i++) {
		if (secflavors[i] == AUTH_SYS)
			nd->nd_flag |= ND_EXAUTHSYS;
		else if (secflavors[i] == RPCSEC_GSS_KRB5)
			nd->nd_flag |= ND_EXGSS;
		else if (secflavors[i] == RPCSEC_GSS_KRB5I)
			nd->nd_flag |= ND_EXGSSINTEGRITY;
		else if (secflavors[i] == RPCSEC_GSS_KRB5P)
			nd->nd_flag |= ND_EXGSSPRIVACY;
	}

out:
	NFSEXITCODE(error);
	return (error);
}

/*
 * Nfs server psuedo system call for the nfsd's
 */
/*
 * MPSAFE
 */
static int
nfssvc_nfsd(struct thread *td, struct nfssvc_args *uap)
{
	struct file *fp;
	struct nfsd_addsock_args sockarg;
	struct nfsd_nfsd_args nfsdarg;
	int error;

	if (uap->flag & NFSSVC_NFSDADDSOCK) {
		error = copyin(uap->argp, (caddr_t)&sockarg, sizeof (sockarg));
		if (error)
			goto out;
		/*
		 * Since we don't know what rights might be required,
		 * pretend that we need them all. It is better to be too
		 * careful than too reckless.
		 */
		if ((error = fget(td, sockarg.sock, CAP_SOCK_SERVER, &fp)) != 0)
			goto out;
		if (fp->f_type != DTYPE_SOCKET) {
			fdrop(fp, td);
			error = EPERM;
			goto out;
		}
		error = nfsrvd_addsock(fp);
		fdrop(fp, td);
	} else if (uap->flag & NFSSVC_NFSDNFSD) {
		if (uap->argp == NULL) {
			error = EINVAL;
			goto out;
		}
		error = copyin(uap->argp, (caddr_t)&nfsdarg,
		    sizeof (nfsdarg));
		if (error)
			goto out;
		error = nfsrvd_nfsd(td, &nfsdarg);
	} else {
		error = nfssvc_srvcall(td, uap, td->td_ucred);
	}

out:
	NFSEXITCODE(error);
	return (error);
}

static int
nfssvc_srvcall(struct thread *p, struct nfssvc_args *uap, struct ucred *cred)
{
	struct nfsex_args export;
	struct file *fp = NULL;
	int stablefd, len;
	struct nfsd_clid adminrevoke;
	struct nfsd_dumplist dumplist;
	struct nfsd_dumpclients *dumpclients;
	struct nfsd_dumplocklist dumplocklist;
	struct nfsd_dumplocks *dumplocks;
	struct nameidata nd;
	vnode_t vp;
	int error = EINVAL, igotlock;
	struct proc *procp;
	static int suspend_nfsd = 0;

	if (uap->flag & NFSSVC_PUBLICFH) {
		NFSBZERO((caddr_t)&nfs_pubfh.nfsrvfh_data,
		    sizeof (fhandle_t));
		error = copyin(uap->argp,
		    &nfs_pubfh.nfsrvfh_data, sizeof (fhandle_t));
		if (!error)
			nfs_pubfhset = 1;
	} else if (uap->flag & NFSSVC_V4ROOTEXPORT) {
		error = copyin(uap->argp,(caddr_t)&export,
		    sizeof (struct nfsex_args));
		if (!error)
			error = nfsrv_v4rootexport(&export, cred, p);
	} else if (uap->flag & NFSSVC_NOPUBLICFH) {
		nfs_pubfhset = 0;
		error = 0;
	} else if (uap->flag & NFSSVC_STABLERESTART) {
		error = copyin(uap->argp, (caddr_t)&stablefd,
		    sizeof (int));
		if (!error)
			error = fp_getfvp(p, stablefd, &fp, &vp);
		if (!error && (NFSFPFLAG(fp) & (FREAD | FWRITE)) != (FREAD | FWRITE))
			error = EBADF;
		if (!error && newnfs_numnfsd != 0)
			error = EPERM;
		if (!error) {
			nfsrv_stablefirst.nsf_fp = fp;
			nfsrv_setupstable(p);
		}
	} else if (uap->flag & NFSSVC_ADMINREVOKE) {
		error = copyin(uap->argp, (caddr_t)&adminrevoke,
		    sizeof (struct nfsd_clid));
		if (!error)
			error = nfsrv_adminrevoke(&adminrevoke, p);
	} else if (uap->flag & NFSSVC_DUMPCLIENTS) {
		error = copyin(uap->argp, (caddr_t)&dumplist,
		    sizeof (struct nfsd_dumplist));
		if (!error && (dumplist.ndl_size < 1 ||
			dumplist.ndl_size > NFSRV_MAXDUMPLIST))
			error = EPERM;
		if (!error) {
		    len = sizeof (struct nfsd_dumpclients) * dumplist.ndl_size;
		    dumpclients = (struct nfsd_dumpclients *)malloc(len,
			M_TEMP, M_WAITOK);
		    nfsrv_dumpclients(dumpclients, dumplist.ndl_size);
		    error = copyout(dumpclients,
			CAST_USER_ADDR_T(dumplist.ndl_list), len);
		    free((caddr_t)dumpclients, M_TEMP);
		}
	} else if (uap->flag & NFSSVC_DUMPLOCKS) {
		error = copyin(uap->argp, (caddr_t)&dumplocklist,
		    sizeof (struct nfsd_dumplocklist));
		if (!error && (dumplocklist.ndllck_size < 1 ||
			dumplocklist.ndllck_size > NFSRV_MAXDUMPLIST))
			error = EPERM;
		if (!error)
			error = nfsrv_lookupfilename(&nd,
				dumplocklist.ndllck_fname, p);
		if (!error) {
			len = sizeof (struct nfsd_dumplocks) *
				dumplocklist.ndllck_size;
			dumplocks = (struct nfsd_dumplocks *)malloc(len,
				M_TEMP, M_WAITOK);
			nfsrv_dumplocks(nd.ni_vp, dumplocks,
			    dumplocklist.ndllck_size, p);
			vput(nd.ni_vp);
			error = copyout(dumplocks,
			    CAST_USER_ADDR_T(dumplocklist.ndllck_list), len);
			free((caddr_t)dumplocks, M_TEMP);
		}
	} else if (uap->flag & NFSSVC_BACKUPSTABLE) {
		procp = p->td_proc;
		PROC_LOCK(procp);
		nfsd_master_pid = procp->p_pid;
		bcopy(procp->p_comm, nfsd_master_comm, MAXCOMLEN + 1);
		nfsd_master_start = procp->p_stats->p_start;
		nfsd_master_proc = procp;
		PROC_UNLOCK(procp);
	} else if ((uap->flag & NFSSVC_SUSPENDNFSD) != 0) {
		NFSLOCKV4ROOTMUTEX();
		if (suspend_nfsd == 0) {
			/* Lock out all nfsd threads */
			do {
				igotlock = nfsv4_lock(&nfsd_suspend_lock, 1,
				    NULL, NFSV4ROOTLOCKMUTEXPTR, NULL);
			} while (igotlock == 0 && suspend_nfsd == 0);
			suspend_nfsd = 1;
		}
		NFSUNLOCKV4ROOTMUTEX();
		error = 0;
	} else if ((uap->flag & NFSSVC_RESUMENFSD) != 0) {
		NFSLOCKV4ROOTMUTEX();
		if (suspend_nfsd != 0) {
			nfsv4_unlock(&nfsd_suspend_lock, 0);
			suspend_nfsd = 0;
		}
		NFSUNLOCKV4ROOTMUTEX();
		error = 0;
	}

	NFSEXITCODE(error);
	return (error);
}

/*
 * Check exports.
 * Returns 0 if ok, 1 otherwise.
 */
int
nfsvno_testexp(struct nfsrv_descript *nd, struct nfsexstuff *exp)
{
	int i;

	/*
	 * This seems odd, but allow the case where the security flavor
	 * list is empty. This happens when NFSv4 is traversing non-exported
	 * file systems. Exported file systems should always have a non-empty
	 * security flavor list.
	 */
	if (exp->nes_numsecflavor == 0)
		return (0);

	for (i = 0; i < exp->nes_numsecflavor; i++) {
		/*
		 * The tests for privacy and integrity must be first,
		 * since ND_GSS is set for everything but AUTH_SYS.
		 */
		if (exp->nes_secflavors[i] == RPCSEC_GSS_KRB5P &&
		    (nd->nd_flag & ND_GSSPRIVACY))
			return (0);
		if (exp->nes_secflavors[i] == RPCSEC_GSS_KRB5I &&
		    (nd->nd_flag & ND_GSSINTEGRITY))
			return (0);
		if (exp->nes_secflavors[i] == RPCSEC_GSS_KRB5 &&
		    (nd->nd_flag & ND_GSS))
			return (0);
		if (exp->nes_secflavors[i] == AUTH_SYS &&
		    (nd->nd_flag & ND_GSS) == 0)
			return (0);
	}
	return (1);
}

/*
 * Calculate a hash value for the fid in a file handle.
 */
uint32_t
nfsrv_hashfh(fhandle_t *fhp)
{
	uint32_t hashval;

	hashval = hash32_buf(&fhp->fh_fid, sizeof(struct fid), 0);
	return (hashval);
}

/*
 * Signal the userland master nfsd to backup the stable restart file.
 */
void
nfsrv_backupstable(void)
{
	struct proc *procp;

	if (nfsd_master_proc != NULL) {
		procp = pfind(nfsd_master_pid);
		/* Try to make sure it is the correct process. */
		if (procp == nfsd_master_proc &&
		    procp->p_stats->p_start.tv_sec ==
		    nfsd_master_start.tv_sec &&
		    procp->p_stats->p_start.tv_usec ==
		    nfsd_master_start.tv_usec &&
		    strcmp(procp->p_comm, nfsd_master_comm) == 0)
			kern_psignal(procp, SIGUSR2);
		else
			nfsd_master_proc = NULL;

		if (procp != NULL)
			PROC_UNLOCK(procp);
	}
}

extern int (*nfsd_call_nfsd)(struct thread *, struct nfssvc_args *);

/*
 * Called once to initialize data structures...
 */
static int
nfsd_modevent(module_t mod, int type, void *data)
{
	int error = 0, i;
	static int loaded = 0;

	switch (type) {
	case MOD_LOAD:
		if (loaded)
			goto out;
		newnfs_portinit();
		for (i = 0; i < NFSRVCACHE_HASHSIZE; i++) {
			snprintf(nfsrchash_table[i].lock_name,
			    sizeof(nfsrchash_table[i].lock_name), "nfsrc_tcp%d",
			    i);
			mtx_init(&nfsrchash_table[i].mtx,
			    nfsrchash_table[i].lock_name, NULL, MTX_DEF);
		}
		mtx_init(&nfsrc_udpmtx, "nfs_udpcache_mutex", NULL, MTX_DEF);
		mtx_init(&nfs_v4root_mutex, "nfs_v4root_mutex", NULL, MTX_DEF);
		mtx_init(&nfsv4root_mnt.mnt_mtx, "struct mount mtx", NULL,
		    MTX_DEF);
		lockinit(&nfsv4root_mnt.mnt_explock, PVFS, "explock", 0, 0);
		nfsrvd_initcache();
		nfsd_init();
		NFSD_LOCK();
		nfsrvd_init(0);
		NFSD_UNLOCK();
		nfsd_mntinit();
#ifdef VV_DISABLEDELEG
		vn_deleg_ops.vndeleg_recall = nfsd_recalldelegation;
		vn_deleg_ops.vndeleg_disable = nfsd_disabledelegation;
#endif
		nfsd_call_servertimer = nfsrv_servertimer;
		nfsd_call_nfsd = nfssvc_nfsd;
		loaded = 1;
		break;

	case MOD_UNLOAD:
		if (newnfs_numnfsd != 0) {
			error = EBUSY;
			break;
		}

#ifdef VV_DISABLEDELEG
		vn_deleg_ops.vndeleg_recall = NULL;
		vn_deleg_ops.vndeleg_disable = NULL;
#endif
		nfsd_call_servertimer = NULL;
		nfsd_call_nfsd = NULL;

		/* Clean out all NFSv4 state. */
		nfsrv_throwawayallstate(curthread);

		/* Clean the NFS server reply cache */
		nfsrvd_cleancache();

		/* Free up the krpc server pool. */
		if (nfsrvd_pool != NULL)
			svcpool_destroy(nfsrvd_pool);

		/* and get rid of the locks */
		for (i = 0; i < NFSRVCACHE_HASHSIZE; i++)
			mtx_destroy(&nfsrchash_table[i].mtx);
		mtx_destroy(&nfsrc_udpmtx);
		mtx_destroy(&nfs_v4root_mutex);
		mtx_destroy(&nfsv4root_mnt.mnt_mtx);
		lockdestroy(&nfsv4root_mnt.mnt_explock);
		loaded = 0;
		break;
	default:
		error = EOPNOTSUPP;
		break;
	}

out:
	NFSEXITCODE(error);
	return (error);
}
static moduledata_t nfsd_mod = {
	"nfsd",
	nfsd_modevent,
	NULL,
};
DECLARE_MODULE(nfsd, nfsd_mod, SI_SUB_VFS, SI_ORDER_ANY);

/* So that loader and kldload(2) can find us, wherever we are.. */
MODULE_VERSION(nfsd, 1);
MODULE_DEPEND(nfsd, nfscommon, 1, 1, 1);
MODULE_DEPEND(nfsd, nfslock, 1, 1, 1);
MODULE_DEPEND(nfsd, nfslockd, 1, 1, 1);
MODULE_DEPEND(nfsd, krpc, 1, 1, 1);
MODULE_DEPEND(nfsd, nfssvc, 1, 1, 1);

OpenPOWER on IntegriCloud