summaryrefslogtreecommitdiff
path: root/fs/nfsd/nfsctl.c
blob: c848ebe5d08f121cff5ffb7b5a64e148194fa960 (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
// SPDX-License-Identifier: GPL-2.0-only
/*
 * Syscall interface to knfsd.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/slab.h>
#include <linux/namei.h>
#include <linux/ctype.h>
#include <linux/fs_context.h>

#include <linux/sunrpc/svcsock.h>
#include <linux/lockd/lockd.h>
#include <linux/sunrpc/addr.h>
#include <linux/sunrpc/gss_api.h>
#include <linux/sunrpc/rpc_pipe_fs.h>
#include <linux/sunrpc/svc.h>
#include <linux/module.h>
#include <linux/fsnotify.h>

#include "idmap.h"
#include "nfsd.h"
#include "cache.h"
#include "state.h"
#include "netns.h"
#include "pnfs.h"
#include "filecache.h"
#include "trace.h"
#include "netlink.h"

/*
 *	We have a single directory with several nodes in it.
 */
enum {
	NFSD_Root = 1,
	NFSD_List,
	NFSD_Export_Stats,
	NFSD_Export_features,
	NFSD_Fh,
	NFSD_FO_UnlockIP,
	NFSD_FO_UnlockFS,
	NFSD_Threads,
	NFSD_Pool_Threads,
	NFSD_Pool_Stats,
	NFSD_Reply_Cache_Stats,
	NFSD_Versions,
	NFSD_Ports,
	NFSD_MaxBlkSize,
	NFSD_MaxConnections,
	NFSD_Filecache,
	NFSD_Leasetime,
	NFSD_Gracetime,
	NFSD_RecoveryDir,
	NFSD_V4EndGrace,
	NFSD_MaxReserved
};

/*
 * write() for these nodes.
 */
static ssize_t write_filehandle(struct file *file, char *buf, size_t size);
static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size);
static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size);
static ssize_t write_threads(struct file *file, char *buf, size_t size);
static ssize_t write_pool_threads(struct file *file, char *buf, size_t size);
static ssize_t write_versions(struct file *file, char *buf, size_t size);
static ssize_t write_ports(struct file *file, char *buf, size_t size);
static ssize_t write_maxblksize(struct file *file, char *buf, size_t size);
static ssize_t write_maxconn(struct file *file, char *buf, size_t size);
#ifdef CONFIG_NFSD_V4
static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
static ssize_t write_gracetime(struct file *file, char *buf, size_t size);
#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
#endif
static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size);
#endif

static ssize_t (*const write_op[])(struct file *, char *, size_t) = {
	[NFSD_Fh] = write_filehandle,
	[NFSD_FO_UnlockIP] = write_unlock_ip,
	[NFSD_FO_UnlockFS] = write_unlock_fs,
	[NFSD_Threads] = write_threads,
	[NFSD_Pool_Threads] = write_pool_threads,
	[NFSD_Versions] = write_versions,
	[NFSD_Ports] = write_ports,
	[NFSD_MaxBlkSize] = write_maxblksize,
	[NFSD_MaxConnections] = write_maxconn,
#ifdef CONFIG_NFSD_V4
	[NFSD_Leasetime] = write_leasetime,
	[NFSD_Gracetime] = write_gracetime,
#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
	[NFSD_RecoveryDir] = write_recoverydir,
#endif
	[NFSD_V4EndGrace] = write_v4_end_grace,
#endif
};

static ssize_t nfsctl_transaction_write(struct file *file, const char __user *buf, size_t size, loff_t *pos)
{
	ino_t ino =  file_inode(file)->i_ino;
	char *data;
	ssize_t rv;

	if (ino >= ARRAY_SIZE(write_op) || !write_op[ino])
		return -EINVAL;

	data = simple_transaction_get(file, buf, size);
	if (IS_ERR(data))
		return PTR_ERR(data);

	rv = write_op[ino](file, data, size);
	if (rv < 0)
		return rv;

	simple_transaction_set(file, rv);
	return size;
}

static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
{
	if (! file->private_data) {
		/* An attempt to read a transaction file without writing
		 * causes a 0-byte write so that the file can return
		 * state information
		 */
		ssize_t rv = nfsctl_transaction_write(file, buf, 0, pos);
		if (rv < 0)
			return rv;
	}
	return simple_transaction_read(file, buf, size, pos);
}

static const struct file_operations transaction_ops = {
	.write		= nfsctl_transaction_write,
	.read		= nfsctl_transaction_read,
	.release	= simple_transaction_release,
	.llseek		= default_llseek,
};

static int exports_net_open(struct net *net, struct file *file)
{
	int err;
	struct seq_file *seq;
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	err = seq_open(file, &nfs_exports_op);
	if (err)
		return err;

	seq = file->private_data;
	seq->private = nn->svc_export_cache;
	return 0;
}

static int exports_nfsd_open(struct inode *inode, struct file *file)
{
	return exports_net_open(inode->i_sb->s_fs_info, file);
}

static const struct file_operations exports_nfsd_operations = {
	.open		= exports_nfsd_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

static int export_features_show(struct seq_file *m, void *v)
{
	seq_printf(m, "0x%x 0x%x\n", NFSEXP_ALLFLAGS, NFSEXP_SECINFO_FLAGS);
	return 0;
}

DEFINE_SHOW_ATTRIBUTE(export_features);

static const struct file_operations pool_stats_operations = {
	.open		= nfsd_pool_stats_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
};

DEFINE_SHOW_ATTRIBUTE(nfsd_reply_cache_stats);

DEFINE_SHOW_ATTRIBUTE(nfsd_file_cache_stats);

/*----------------------------------------------------------------------------*/
/*
 * payload - write methods
 */

static inline struct net *netns(struct file *file)
{
	return file_inode(file)->i_sb->s_fs_info;
}

/*
 * write_unlock_ip - Release all locks used by a client
 *
 * Experimental.
 *
 * Input:
 *			buf:	'\n'-terminated C string containing a
 *				presentation format IP address
 *			size:	length of C string in @buf
 * Output:
 *	On success:	returns zero if all specified locks were released;
 *			returns one if one or more locks were not released
 *	On error:	return code is negative errno value
 */
static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
{
	struct sockaddr_storage address;
	struct sockaddr *sap = (struct sockaddr *)&address;
	size_t salen = sizeof(address);
	char *fo_path;
	struct net *net = netns(file);

	/* sanity check */
	if (size == 0)
		return -EINVAL;

	if (buf[size-1] != '\n')
		return -EINVAL;

	fo_path = buf;
	if (qword_get(&buf, fo_path, size) < 0)
		return -EINVAL;

	if (rpc_pton(net, fo_path, size, sap, salen) == 0)
		return -EINVAL;

	trace_nfsd_ctl_unlock_ip(net, buf);
	return nlmsvc_unlock_all_by_ip(sap);
}

/*
 * write_unlock_fs - Release all locks on a local file system
 *
 * Experimental.
 *
 * Input:
 *			buf:	'\n'-terminated C string containing the
 *				absolute pathname of a local file system
 *			size:	length of C string in @buf
 * Output:
 *	On success:	returns zero if all specified locks were released;
 *			returns one if one or more locks were not released
 *	On error:	return code is negative errno value
 */
static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size)
{
	struct path path;
	char *fo_path;
	int error;

	/* sanity check */
	if (size == 0)
		return -EINVAL;

	if (buf[size-1] != '\n')
		return -EINVAL;

	fo_path = buf;
	if (qword_get(&buf, fo_path, size) < 0)
		return -EINVAL;
	trace_nfsd_ctl_unlock_fs(netns(file), fo_path);
	error = kern_path(fo_path, 0, &path);
	if (error)
		return error;

	/*
	 * XXX: Needs better sanity checking.  Otherwise we could end up
	 * releasing locks on the wrong file system.
	 *
	 * For example:
	 * 1.  Does the path refer to a directory?
	 * 2.  Is that directory a mount point, or
	 * 3.  Is that directory the root of an exported file system?
	 */
	error = nlmsvc_unlock_all_by_sb(path.dentry->d_sb);
	nfsd4_revoke_states(netns(file), path.dentry->d_sb);

	path_put(&path);
	return error;
}

/*
 * write_filehandle - Get a variable-length NFS file handle by path
 *
 * On input, the buffer contains a '\n'-terminated C string comprised of
 * three alphanumeric words separated by whitespace.  The string may
 * contain escape sequences.
 *
 * Input:
 *			buf:
 *				domain:		client domain name
 *				path:		export pathname
 *				maxsize:	numeric maximum size of
 *						@buf
 *			size:	length of C string in @buf
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C
 *			string containing a ASCII hex text version
 *			of the NFS file handle;
 *			return code is the size in bytes of the string
 *	On error:	return code is negative errno value
 */
static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
{
	char *dname, *path;
	int maxsize;
	char *mesg = buf;
	int len;
	struct auth_domain *dom;
	struct knfsd_fh fh;

	if (size == 0)
		return -EINVAL;

	if (buf[size-1] != '\n')
		return -EINVAL;
	buf[size-1] = 0;

	dname = mesg;
	len = qword_get(&mesg, dname, size);
	if (len <= 0)
		return -EINVAL;

	path = dname+len+1;
	len = qword_get(&mesg, path, size);
	if (len <= 0)
		return -EINVAL;

	len = get_int(&mesg, &maxsize);
	if (len)
		return len;

	if (maxsize < NFS_FHSIZE)
		return -EINVAL;
	maxsize = min(maxsize, NFS3_FHSIZE);

	if (qword_get(&mesg, mesg, size) > 0)
		return -EINVAL;

	trace_nfsd_ctl_filehandle(netns(file), dname, path, maxsize);

	/* we have all the words, they are in buf.. */
	dom = unix_domain_find(dname);
	if (!dom)
		return -ENOMEM;

	len = exp_rootfh(netns(file), dom, path, &fh, maxsize);
	auth_domain_put(dom);
	if (len)
		return len;

	mesg = buf;
	len = SIMPLE_TRANSACTION_LIMIT;
	qword_addhex(&mesg, &len, fh.fh_raw, fh.fh_size);
	mesg[-1] = '\n';
	return mesg - buf;
}

/*
 * write_threads - Start NFSD, or report the current number of running threads
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C
 *			string numeric value representing the number of
 *			running NFSD threads;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero
 *
 * OR
 *
 * Input:
 *			buf:		C string containing an unsigned
 *					integer value representing the
 *					number of NFSD threads to start
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	NFS service is started;
 *			passed-in buffer filled with '\n'-terminated C
 *			string numeric value representing the number of
 *			running NFSD threads;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 */
static ssize_t write_threads(struct file *file, char *buf, size_t size)
{
	char *mesg = buf;
	int rv;
	struct net *net = netns(file);

	if (size > 0) {
		int newthreads;
		rv = get_int(&mesg, &newthreads);
		if (rv)
			return rv;
		if (newthreads < 0)
			return -EINVAL;
		trace_nfsd_ctl_threads(net, newthreads);
		mutex_lock(&nfsd_mutex);
		rv = nfsd_svc(newthreads, net, file->f_cred, NULL);
		mutex_unlock(&nfsd_mutex);
		if (rv < 0)
			return rv;
	} else
		rv = nfsd_nrthreads(net);

	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n", rv);
}

/*
 * write_pool_threads - Set or report the current number of threads per pool
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 *
 * OR
 *
 * Input:
 *			buf:		C string containing whitespace-
 *					separated unsigned integer values
 *					representing the number of NFSD
 *					threads to start in each pool
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C
 *			string containing integer values representing the
 *			number of NFSD threads in each pool;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 */
static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
{
	/* if size > 0, look for an array of number of threads per node
	 * and apply them  then write out number of threads per node as reply
	 */
	char *mesg = buf;
	int i;
	int rv;
	int len;
	int npools;
	int *nthreads;
	struct net *net = netns(file);

	mutex_lock(&nfsd_mutex);
	npools = nfsd_nrpools(net);
	if (npools == 0) {
		/*
		 * NFS is shut down.  The admin can start it by
		 * writing to the threads file but NOT the pool_threads
		 * file, sorry.  Report zero threads.
		 */
		mutex_unlock(&nfsd_mutex);
		strcpy(buf, "0\n");
		return strlen(buf);
	}

	nthreads = kcalloc(npools, sizeof(int), GFP_KERNEL);
	rv = -ENOMEM;
	if (nthreads == NULL)
		goto out_free;

	if (size > 0) {
		for (i = 0; i < npools; i++) {
			rv = get_int(&mesg, &nthreads[i]);
			if (rv == -ENOENT)
				break;		/* fewer numbers than pools */
			if (rv)
				goto out_free;	/* syntax error */
			rv = -EINVAL;
			if (nthreads[i] < 0)
				goto out_free;
			trace_nfsd_ctl_pool_threads(net, i, nthreads[i]);
		}
		rv = nfsd_set_nrthreads(i, nthreads, net);
		if (rv)
			goto out_free;
	}

	rv = nfsd_get_nrthreads(npools, nthreads, net);
	if (rv)
		goto out_free;

	mesg = buf;
	size = SIMPLE_TRANSACTION_LIMIT;
	for (i = 0; i < npools && size > 0; i++) {
		snprintf(mesg, size, "%d%c", nthreads[i], (i == npools-1 ? '\n' : ' '));
		len = strlen(mesg);
		size -= len;
		mesg += len;
	}
	rv = mesg - buf;
out_free:
	kfree(nthreads);
	mutex_unlock(&nfsd_mutex);
	return rv;
}

static ssize_t
nfsd_print_version_support(struct nfsd_net *nn, char *buf, int remaining,
		const char *sep, unsigned vers, int minor)
{
	const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u";
	bool supported = !!nfsd_vers(nn, vers, NFSD_TEST);

	if (vers == 4 && minor >= 0 &&
	    !nfsd_minorversion(nn, minor, NFSD_TEST))
		supported = false;
	if (minor == 0 && supported)
		/*
		 * special case for backward compatability.
		 * +4.0 is never reported, it is implied by
		 * +4, unless -4.0 is present.
		 */
		return 0;
	return snprintf(buf, remaining, format, sep,
			supported ? '+' : '-', vers, minor);
}

static ssize_t __write_versions(struct file *file, char *buf, size_t size)
{
	char *mesg = buf;
	char *vers, *minorp, sign;
	int len, num, remaining;
	ssize_t tlen = 0;
	char *sep;
	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);

	if (size > 0) {
		if (nn->nfsd_serv)
			/* Cannot change versions without updating
			 * nn->nfsd_serv->sv_xdrsize, and reallocing
			 * rq_argp and rq_resp
			 */
			return -EBUSY;
		if (buf[size-1] != '\n')
			return -EINVAL;
		buf[size-1] = 0;
		trace_nfsd_ctl_version(netns(file), buf);

		vers = mesg;
		len = qword_get(&mesg, vers, size);
		if (len <= 0) return -EINVAL;
		do {
			enum vers_op cmd;
			unsigned minor;
			sign = *vers;
			if (sign == '+' || sign == '-')
				num = simple_strtol((vers+1), &minorp, 0);
			else
				num = simple_strtol(vers, &minorp, 0);
			if (*minorp == '.') {
				if (num != 4)
					return -EINVAL;
				if (kstrtouint(minorp+1, 0, &minor) < 0)
					return -EINVAL;
			}

			cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET;
			switch(num) {
#ifdef CONFIG_NFSD_V2
			case 2:
#endif
			case 3:
				nfsd_vers(nn, num, cmd);
				break;
			case 4:
				if (*minorp == '.') {
					if (nfsd_minorversion(nn, minor, cmd) < 0)
						return -EINVAL;
				} else if ((cmd == NFSD_SET) != nfsd_vers(nn, num, NFSD_TEST)) {
					/*
					 * Either we have +4 and no minors are enabled,
					 * or we have -4 and at least one minor is enabled.
					 * In either case, propagate 'cmd' to all minors.
					 */
					minor = 0;
					while (nfsd_minorversion(nn, minor, cmd) >= 0)
						minor++;
				}
				break;
			default:
				/* Ignore requests to disable non-existent versions */
				if (cmd == NFSD_SET)
					return -EINVAL;
			}
			vers += len + 1;
		} while ((len = qword_get(&mesg, vers, size)) > 0);
		/* If all get turned off, turn them back on, as
		 * having no versions is BAD
		 */
		nfsd_reset_versions(nn);
	}

	/* Now write current state into reply buffer */
	sep = "";
	remaining = SIMPLE_TRANSACTION_LIMIT;
	for (num=2 ; num <= 4 ; num++) {
		int minor;
		if (!nfsd_vers(nn, num, NFSD_AVAIL))
			continue;

		minor = -1;
		do {
			len = nfsd_print_version_support(nn, buf, remaining,
					sep, num, minor);
			if (len >= remaining)
				goto out;
			remaining -= len;
			buf += len;
			tlen += len;
			minor++;
			if (len)
				sep = " ";
		} while (num == 4 && minor <= NFSD_SUPPORTED_MINOR_VERSION);
	}
out:
	len = snprintf(buf, remaining, "\n");
	if (len >= remaining)
		return -EINVAL;
	return tlen + len;
}

/*
 * write_versions - Set or report the available NFS protocol versions
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C
 *			string containing positive or negative integer
 *			values representing the current status of each
 *			protocol version;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 *
 * OR
 *
 * Input:
 *			buf:		C string containing whitespace-
 *					separated positive or negative
 *					integer values representing NFS
 *					protocol versions to enable ("+n")
 *					or disable ("-n")
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	status of zero or more protocol versions has
 *			been updated; passed-in buffer filled with
 *			'\n'-terminated C string containing positive
 *			or negative integer values representing the
 *			current status of each protocol version;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 */
static ssize_t write_versions(struct file *file, char *buf, size_t size)
{
	ssize_t rv;

	mutex_lock(&nfsd_mutex);
	rv = __write_versions(file, buf, size);
	mutex_unlock(&nfsd_mutex);
	return rv;
}

/*
 * Zero-length write.  Return a list of NFSD's current listener
 * transports.
 */
static ssize_t __write_ports_names(char *buf, struct net *net)
{
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	if (nn->nfsd_serv == NULL)
		return 0;
	return svc_xprt_names(nn->nfsd_serv, buf, SIMPLE_TRANSACTION_LIMIT);
}

/*
 * A single 'fd' number was written, in which case it must be for
 * a socket of a supported family/protocol, and we use it as an
 * nfsd listener.
 */
static ssize_t __write_ports_addfd(char *buf, struct net *net, const struct cred *cred)
{
	char *mesg = buf;
	int fd, err;
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
	struct svc_serv *serv;

	err = get_int(&mesg, &fd);
	if (err != 0 || fd < 0)
		return -EINVAL;
	trace_nfsd_ctl_ports_addfd(net, fd);

	err = nfsd_create_serv(net);
	if (err != 0)
		return err;

	serv = nn->nfsd_serv;
	err = svc_addsock(serv, net, fd, buf, SIMPLE_TRANSACTION_LIMIT, cred);

	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
		nfsd_destroy_serv(net);

	return err;
}

/*
 * A transport listener is added by writing its transport name and
 * a port number.
 */
static ssize_t __write_ports_addxprt(char *buf, struct net *net, const struct cred *cred)
{
	char transport[16];
	struct svc_xprt *xprt;
	int port, err;
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
	struct svc_serv *serv;

	if (sscanf(buf, "%15s %5u", transport, &port) != 2)
		return -EINVAL;

	if (port < 1 || port > USHRT_MAX)
		return -EINVAL;
	trace_nfsd_ctl_ports_addxprt(net, transport, port);

	err = nfsd_create_serv(net);
	if (err != 0)
		return err;

	serv = nn->nfsd_serv;
	err = svc_xprt_create(serv, transport, net,
			      PF_INET, port, SVC_SOCK_ANONYMOUS, cred);
	if (err < 0)
		goto out_err;

	err = svc_xprt_create(serv, transport, net,
			      PF_INET6, port, SVC_SOCK_ANONYMOUS, cred);
	if (err < 0 && err != -EAFNOSUPPORT)
		goto out_close;

	return 0;
out_close:
	xprt = svc_find_xprt(serv, transport, net, PF_INET, port);
	if (xprt != NULL) {
		svc_xprt_close(xprt);
		svc_xprt_put(xprt);
	}
out_err:
	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
		nfsd_destroy_serv(net);

	return err;
}

static ssize_t __write_ports(struct file *file, char *buf, size_t size,
			     struct net *net)
{
	if (size == 0)
		return __write_ports_names(buf, net);

	if (isdigit(buf[0]))
		return __write_ports_addfd(buf, net, file->f_cred);

	if (isalpha(buf[0]))
		return __write_ports_addxprt(buf, net, file->f_cred);

	return -EINVAL;
}

/*
 * write_ports - Pass a socket file descriptor or transport name to listen on
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 * Output:
 *	On success:	passed-in buffer filled with a '\n'-terminated C
 *			string containing a whitespace-separated list of
 *			named NFSD listeners;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 *
 * OR
 *
 * Input:
 *			buf:		C string containing an unsigned
 *					integer value representing a bound
 *					but unconnected socket that is to be
 *					used as an NFSD listener; listen(3)
 *					must be called for a SOCK_STREAM
 *					socket, otherwise it is ignored
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	NFS service is started;
 *			passed-in buffer filled with a '\n'-terminated C
 *			string containing a unique alphanumeric name of
 *			the listener;
 *			return code is the size in bytes of the string
 *	On error:	return code is a negative errno value
 *
 * OR
 *
 * Input:
 *			buf:		C string containing a transport
 *					name and an unsigned integer value
 *					representing the port to listen on,
 *					separated by whitespace
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	returns zero; NFS service is started
 *	On error:	return code is a negative errno value
 */
static ssize_t write_ports(struct file *file, char *buf, size_t size)
{
	ssize_t rv;

	mutex_lock(&nfsd_mutex);
	rv = __write_ports(file, buf, size, netns(file));
	mutex_unlock(&nfsd_mutex);
	return rv;
}


int nfsd_max_blksize;

/*
 * write_maxblksize - Set or report the current NFS blksize
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 *
 * OR
 *
 * Input:
 *			buf:		C string containing an unsigned
 *					integer value representing the new
 *					NFS blksize
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C string
 *			containing numeric value of the current NFS blksize
 *			setting;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 */
static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
{
	char *mesg = buf;
	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);

	if (size > 0) {
		int bsize;
		int rv = get_int(&mesg, &bsize);
		if (rv)
			return rv;
		trace_nfsd_ctl_maxblksize(netns(file), bsize);

		/* force bsize into allowed range and
		 * required alignment.
		 */
		bsize = max_t(int, bsize, 1024);
		bsize = min_t(int, bsize, NFSSVC_MAXBLKSIZE);
		bsize &= ~(1024-1);
		mutex_lock(&nfsd_mutex);
		if (nn->nfsd_serv) {
			mutex_unlock(&nfsd_mutex);
			return -EBUSY;
		}
		nfsd_max_blksize = bsize;
		mutex_unlock(&nfsd_mutex);
	}

	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%d\n",
							nfsd_max_blksize);
}

/*
 * write_maxconn - Set or report the current max number of connections
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 * OR
 *
 * Input:
 *			buf:		C string containing an unsigned
 *					integer value representing the new
 *					number of max connections
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C string
 *			containing numeric value of max_connections setting
 *			for this net namespace;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 */
static ssize_t write_maxconn(struct file *file, char *buf, size_t size)
{
	char *mesg = buf;
	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);
	unsigned int maxconn = nn->max_connections;

	if (size > 0) {
		int rv = get_uint(&mesg, &maxconn);

		if (rv)
			return rv;
		trace_nfsd_ctl_maxconn(netns(file), maxconn);
		nn->max_connections = maxconn;
	}

	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%u\n", maxconn);
}

#ifdef CONFIG_NFSD_V4
static ssize_t __nfsd4_write_time(struct file *file, char *buf, size_t size,
				  time64_t *time, struct nfsd_net *nn)
{
	struct dentry *dentry = file_dentry(file);
	char *mesg = buf;
	int rv, i;

	if (size > 0) {
		if (nn->nfsd_serv)
			return -EBUSY;
		rv = get_int(&mesg, &i);
		if (rv)
			return rv;
		trace_nfsd_ctl_time(netns(file), dentry->d_name.name,
				    dentry->d_name.len, i);

		/*
		 * Some sanity checking.  We don't have a reason for
		 * these particular numbers, but problems with the
		 * extremes are:
		 *	- Too short: the briefest network outage may
		 *	  cause clients to lose all their locks.  Also,
		 *	  the frequent polling may be wasteful.
		 *	- Too long: do you really want reboot recovery
		 *	  to take more than an hour?  Or to make other
		 *	  clients wait an hour before being able to
		 *	  revoke a dead client's locks?
		 */
		if (i < 10 || i > 3600)
			return -EINVAL;
		*time = i;
	}

	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%lld\n", *time);
}

static ssize_t nfsd4_write_time(struct file *file, char *buf, size_t size,
				time64_t *time, struct nfsd_net *nn)
{
	ssize_t rv;

	mutex_lock(&nfsd_mutex);
	rv = __nfsd4_write_time(file, buf, size, time, nn);
	mutex_unlock(&nfsd_mutex);
	return rv;
}

/*
 * write_leasetime - Set or report the current NFSv4 lease time
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 *
 * OR
 *
 * Input:
 *			buf:		C string containing an unsigned
 *					integer value representing the new
 *					NFSv4 lease expiry time
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C
 *			string containing unsigned integer value of the
 *			current lease expiry time;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 */
static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
{
	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);
	return nfsd4_write_time(file, buf, size, &nn->nfsd4_lease, nn);
}

/*
 * write_gracetime - Set or report current NFSv4 grace period time
 *
 * As above, but sets the time of the NFSv4 grace period.
 *
 * Note this should never be set to less than the *previous*
 * lease-period time, but we don't try to enforce this.  (In the common
 * case (a new boot), we don't know what the previous lease time was
 * anyway.)
 */
static ssize_t write_gracetime(struct file *file, char *buf, size_t size)
{
	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);
	return nfsd4_write_time(file, buf, size, &nn->nfsd4_grace, nn);
}

#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size,
				   struct nfsd_net *nn)
{
	char *mesg = buf;
	char *recdir;
	int len, status;

	if (size > 0) {
		if (nn->nfsd_serv)
			return -EBUSY;
		if (size > PATH_MAX || buf[size-1] != '\n')
			return -EINVAL;
		buf[size-1] = 0;

		recdir = mesg;
		len = qword_get(&mesg, recdir, size);
		if (len <= 0)
			return -EINVAL;
		trace_nfsd_ctl_recoverydir(netns(file), recdir);

		status = nfs4_reset_recoverydir(recdir);
		if (status)
			return status;
	}

	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%s\n",
							nfs4_recoverydir());
}

/*
 * write_recoverydir - Set or report the pathname of the recovery directory
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 *
 * OR
 *
 * Input:
 *			buf:		C string containing the pathname
 *					of the directory on a local file
 *					system containing permanent NFSv4
 *					recovery data
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	passed-in buffer filled with '\n'-terminated C string
 *			containing the current recovery pathname setting;
 *			return code is the size in bytes of the string
 *	On error:	return code is zero or a negative errno value
 */
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
{
	ssize_t rv;
	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);

	mutex_lock(&nfsd_mutex);
	rv = __write_recoverydir(file, buf, size, nn);
	mutex_unlock(&nfsd_mutex);
	return rv;
}
#endif

/*
 * write_v4_end_grace - release grace period for nfsd's v4.x lock manager
 *
 * Input:
 *			buf:		ignored
 *			size:		zero
 * OR
 *
 * Input:
 *			buf:		any value
 *			size:		non-zero length of C string in @buf
 * Output:
 *			passed-in buffer filled with "Y" or "N" with a newline
 *			and NULL-terminated C string. This indicates whether
 *			the grace period has ended in the current net
 *			namespace. Return code is the size in bytes of the
 *			string. Writing a string that starts with 'Y', 'y', or
 *			'1' to the file will end the grace period for nfsd's v4
 *			lock manager.
 */
static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size)
{
	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);

	if (size > 0) {
		switch(buf[0]) {
		case 'Y':
		case 'y':
		case '1':
			if (!nn->nfsd_serv)
				return -EBUSY;
			trace_nfsd_end_grace(netns(file));
			nfsd4_end_grace(nn);
			break;
		default:
			return -EINVAL;
		}
	}

	return scnprintf(buf, SIMPLE_TRANSACTION_LIMIT, "%c\n",
			 nn->grace_ended ? 'Y' : 'N');
}

#endif

/*----------------------------------------------------------------------------*/
/*
 *	populating the filesystem.
 */

/* Basically copying rpc_get_inode. */
static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode)
{
	struct inode *inode = new_inode(sb);
	if (!inode)
		return NULL;
	/* Following advice from simple_fill_super documentation: */
	inode->i_ino = iunique(sb, NFSD_MaxReserved);
	inode->i_mode = mode;
	simple_inode_init_ts(inode);
	switch (mode & S_IFMT) {
	case S_IFDIR:
		inode->i_fop = &simple_dir_operations;
		inode->i_op = &simple_dir_inode_operations;
		inc_nlink(inode);
		break;
	case S_IFLNK:
		inode->i_op = &simple_symlink_inode_operations;
		break;
	default:
		break;
	}
	return inode;
}

static int __nfsd_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode, struct nfsdfs_client *ncl)
{
	struct inode *inode;

	inode = nfsd_get_inode(dir->i_sb, mode);
	if (!inode)
		return -ENOMEM;
	if (ncl) {
		inode->i_private = ncl;
		kref_get(&ncl->cl_ref);
	}
	d_add(dentry, inode);
	inc_nlink(dir);
	fsnotify_mkdir(dir, dentry);
	return 0;
}

static struct dentry *nfsd_mkdir(struct dentry *parent, struct nfsdfs_client *ncl, char *name)
{
	struct inode *dir = parent->d_inode;
	struct dentry *dentry;
	int ret = -ENOMEM;

	inode_lock(dir);
	dentry = d_alloc_name(parent, name);
	if (!dentry)
		goto out_err;
	ret = __nfsd_mkdir(d_inode(parent), dentry, S_IFDIR | 0600, ncl);
	if (ret)
		goto out_err;
out:
	inode_unlock(dir);
	return dentry;
out_err:
	dput(dentry);
	dentry = ERR_PTR(ret);
	goto out;
}

#if IS_ENABLED(CONFIG_SUNRPC_GSS)
static int __nfsd_symlink(struct inode *dir, struct dentry *dentry,
			  umode_t mode, const char *content)
{
	struct inode *inode;

	inode = nfsd_get_inode(dir->i_sb, mode);
	if (!inode)
		return -ENOMEM;

	inode->i_link = (char *)content;
	inode->i_size = strlen(content);

	d_add(dentry, inode);
	inc_nlink(dir);
	fsnotify_create(dir, dentry);
	return 0;
}

/*
 * @content is assumed to be a NUL-terminated string that lives
 * longer than the symlink itself.
 */
static void _nfsd_symlink(struct dentry *parent, const char *name,
			  const char *content)
{
	struct inode *dir = parent->d_inode;
	struct dentry *dentry;
	int ret;

	inode_lock(dir);
	dentry = d_alloc_name(parent, name);
	if (!dentry)
		goto out;
	ret = __nfsd_symlink(d_inode(parent), dentry, S_IFLNK | 0777, content);
	if (ret)
		dput(dentry);
out:
	inode_unlock(dir);
}
#else
static inline void _nfsd_symlink(struct dentry *parent, const char *name,
				 const char *content)
{
}

#endif

static void clear_ncl(struct dentry *dentry)
{
	struct inode *inode = d_inode(dentry);
	struct nfsdfs_client *ncl = inode->i_private;

	spin_lock(&inode->i_lock);
	inode->i_private = NULL;
	spin_unlock(&inode->i_lock);
	kref_put(&ncl->cl_ref, ncl->cl_release);
}

struct nfsdfs_client *get_nfsdfs_client(struct inode *inode)
{
	struct nfsdfs_client *nc;

	spin_lock(&inode->i_lock);
	nc = inode->i_private;
	if (nc)
		kref_get(&nc->cl_ref);
	spin_unlock(&inode->i_lock);
	return nc;
}

/* XXX: cut'n'paste from simple_fill_super; figure out if we could share
 * code instead. */
static  int nfsdfs_create_files(struct dentry *root,
				const struct tree_descr *files,
				struct nfsdfs_client *ncl,
				struct dentry **fdentries)
{
	struct inode *dir = d_inode(root);
	struct inode *inode;
	struct dentry *dentry;
	int i;

	inode_lock(dir);
	for (i = 0; files->name && files->name[0]; i++, files++) {
		dentry = d_alloc_name(root, files->name);
		if (!dentry)
			goto out;
		inode = nfsd_get_inode(d_inode(root)->i_sb,
					S_IFREG | files->mode);
		if (!inode) {
			dput(dentry);
			goto out;
		}
		kref_get(&ncl->cl_ref);
		inode->i_fop = files->ops;
		inode->i_private = ncl;
		d_add(dentry, inode);
		fsnotify_create(dir, dentry);
		if (fdentries)
			fdentries[i] = dentry;
	}
	inode_unlock(dir);
	return 0;
out:
	inode_unlock(dir);
	return -ENOMEM;
}

/* on success, returns positive number unique to that client. */
struct dentry *nfsd_client_mkdir(struct nfsd_net *nn,
				 struct nfsdfs_client *ncl, u32 id,
				 const struct tree_descr *files,
				 struct dentry **fdentries)
{
	struct dentry *dentry;
	char name[11];
	int ret;

	sprintf(name, "%u", id);

	dentry = nfsd_mkdir(nn->nfsd_client_dir, ncl, name);
	if (IS_ERR(dentry)) /* XXX: tossing errors? */
		return NULL;
	ret = nfsdfs_create_files(dentry, files, ncl, fdentries);
	if (ret) {
		nfsd_client_rmdir(dentry);
		return NULL;
	}
	return dentry;
}

/* Taken from __rpc_rmdir: */
void nfsd_client_rmdir(struct dentry *dentry)
{
	simple_recursive_removal(dentry, clear_ncl);
}

static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc)
{
	struct nfsd_net *nn = net_generic(current->nsproxy->net_ns,
							nfsd_net_id);
	struct dentry *dentry;
	int ret;

	static const struct tree_descr nfsd_files[] = {
		[NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO},
		/* Per-export io stats use same ops as exports file */
		[NFSD_Export_Stats] = {"export_stats", &exports_nfsd_operations, S_IRUGO},
		[NFSD_Export_features] = {"export_features",
					&export_features_fops, S_IRUGO},
		[NFSD_FO_UnlockIP] = {"unlock_ip",
					&transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_FO_UnlockFS] = {"unlock_filesystem",
					&transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_Fh] = {"filehandle", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_Pool_Stats] = {"pool_stats", &pool_stats_operations, S_IRUGO},
		[NFSD_Reply_Cache_Stats] = {"reply_cache_stats",
					&nfsd_reply_cache_stats_fops, S_IRUGO},
		[NFSD_Versions] = {"versions", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_Ports] = {"portlist", &transaction_ops, S_IWUSR|S_IRUGO},
		[NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO},
		[NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO},
		[NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO},
#ifdef CONFIG_NFSD_V4
		[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR},
#ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
		[NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR},
#endif
		[NFSD_V4EndGrace] = {"v4_end_grace", &transaction_ops, S_IWUSR|S_IRUGO},
#endif
		/* last one */ {""}
	};

	ret = simple_fill_super(sb, 0x6e667364, nfsd_files);
	if (ret)
		return ret;
	_nfsd_symlink(sb->s_root, "supported_krb5_enctypes",
		      "/proc/net/rpc/gss_krb5_enctypes");
	dentry = nfsd_mkdir(sb->s_root, NULL, "clients");
	if (IS_ERR(dentry))
		return PTR_ERR(dentry);
	nn->nfsd_client_dir = dentry;
	return 0;
}

static int nfsd_fs_get_tree(struct fs_context *fc)
{
	return get_tree_keyed(fc, nfsd_fill_super, get_net(fc->net_ns));
}

static void nfsd_fs_free_fc(struct fs_context *fc)
{
	if (fc->s_fs_info)
		put_net(fc->s_fs_info);
}

static const struct fs_context_operations nfsd_fs_context_ops = {
	.free		= nfsd_fs_free_fc,
	.get_tree	= nfsd_fs_get_tree,
};

static int nfsd_init_fs_context(struct fs_context *fc)
{
	put_user_ns(fc->user_ns);
	fc->user_ns = get_user_ns(fc->net_ns->user_ns);
	fc->ops = &nfsd_fs_context_ops;
	return 0;
}

static void nfsd_umount(struct super_block *sb)
{
	struct net *net = sb->s_fs_info;

	nfsd_shutdown_threads(net);

	kill_litter_super(sb);
	put_net(net);
}

static struct file_system_type nfsd_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfsd",
	.init_fs_context = nfsd_init_fs_context,
	.kill_sb	= nfsd_umount,
};
MODULE_ALIAS_FS("nfsd");

#ifdef CONFIG_PROC_FS

static int exports_proc_open(struct inode *inode, struct file *file)
{
	return exports_net_open(current->nsproxy->net_ns, file);
}

static const struct proc_ops exports_proc_ops = {
	.proc_open	= exports_proc_open,
	.proc_read	= seq_read,
	.proc_lseek	= seq_lseek,
	.proc_release	= seq_release,
};

static int create_proc_exports_entry(void)
{
	struct proc_dir_entry *entry;

	entry = proc_mkdir("fs/nfs", NULL);
	if (!entry)
		return -ENOMEM;
	entry = proc_create("exports", 0, entry, &exports_proc_ops);
	if (!entry) {
		remove_proc_entry("fs/nfs", NULL);
		return -ENOMEM;
	}
	return 0;
}
#else /* CONFIG_PROC_FS */
static int create_proc_exports_entry(void)
{
	return 0;
}
#endif

unsigned int nfsd_net_id;

static int nfsd_genl_rpc_status_compose_msg(struct sk_buff *skb,
					    struct netlink_callback *cb,
					    struct nfsd_genl_rqstp *rqstp)
{
	void *hdr;
	u32 i;

	hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq,
			  &nfsd_nl_family, 0, NFSD_CMD_RPC_STATUS_GET);
	if (!hdr)
		return -ENOBUFS;

	if (nla_put_be32(skb, NFSD_A_RPC_STATUS_XID, rqstp->rq_xid) ||
	    nla_put_u32(skb, NFSD_A_RPC_STATUS_FLAGS, rqstp->rq_flags) ||
	    nla_put_u32(skb, NFSD_A_RPC_STATUS_PROG, rqstp->rq_prog) ||
	    nla_put_u32(skb, NFSD_A_RPC_STATUS_PROC, rqstp->rq_proc) ||
	    nla_put_u8(skb, NFSD_A_RPC_STATUS_VERSION, rqstp->rq_vers) ||
	    nla_put_s64(skb, NFSD_A_RPC_STATUS_SERVICE_TIME,
			ktime_to_us(rqstp->rq_stime),
			NFSD_A_RPC_STATUS_PAD))
		return -ENOBUFS;

	switch (rqstp->rq_saddr.sa_family) {
	case AF_INET: {
		const struct sockaddr_in *s_in, *d_in;

		s_in = (const struct sockaddr_in *)&rqstp->rq_saddr;
		d_in = (const struct sockaddr_in *)&rqstp->rq_daddr;
		if (nla_put_in_addr(skb, NFSD_A_RPC_STATUS_SADDR4,
				    s_in->sin_addr.s_addr) ||
		    nla_put_in_addr(skb, NFSD_A_RPC_STATUS_DADDR4,
				    d_in->sin_addr.s_addr) ||
		    nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT,
				 s_in->sin_port) ||
		    nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT,
				 d_in->sin_port))
			return -ENOBUFS;
		break;
	}
	case AF_INET6: {
		const struct sockaddr_in6 *s_in, *d_in;

		s_in = (const struct sockaddr_in6 *)&rqstp->rq_saddr;
		d_in = (const struct sockaddr_in6 *)&rqstp->rq_daddr;
		if (nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_SADDR6,
				     &s_in->sin6_addr) ||
		    nla_put_in6_addr(skb, NFSD_A_RPC_STATUS_DADDR6,
				     &d_in->sin6_addr) ||
		    nla_put_be16(skb, NFSD_A_RPC_STATUS_SPORT,
				 s_in->sin6_port) ||
		    nla_put_be16(skb, NFSD_A_RPC_STATUS_DPORT,
				 d_in->sin6_port))
			return -ENOBUFS;
		break;
	}
	}

	for (i = 0; i < rqstp->rq_opcnt; i++)
		if (nla_put_u32(skb, NFSD_A_RPC_STATUS_COMPOUND_OPS,
				rqstp->rq_opnum[i]))
			return -ENOBUFS;

	genlmsg_end(skb, hdr);
	return 0;
}

/**
 * nfsd_nl_rpc_status_get_dumpit - Handle rpc_status_get dumpit
 * @skb: reply buffer
 * @cb: netlink metadata and command arguments
 *
 * Returns the size of the reply or a negative errno.
 */
int nfsd_nl_rpc_status_get_dumpit(struct sk_buff *skb,
				  struct netlink_callback *cb)
{
	int i, ret, rqstp_index = 0;
	struct nfsd_net *nn;

	mutex_lock(&nfsd_mutex);

	nn = net_generic(sock_net(skb->sk), nfsd_net_id);
	if (!nn->nfsd_serv) {
		ret = -ENODEV;
		goto out_unlock;
	}

	rcu_read_lock();

	for (i = 0; i < nn->nfsd_serv->sv_nrpools; i++) {
		struct svc_rqst *rqstp;

		if (i < cb->args[0]) /* already consumed */
			continue;

		rqstp_index = 0;
		list_for_each_entry_rcu(rqstp,
				&nn->nfsd_serv->sv_pools[i].sp_all_threads,
				rq_all) {
			struct nfsd_genl_rqstp genl_rqstp;
			unsigned int status_counter;

			if (rqstp_index++ < cb->args[1]) /* already consumed */
				continue;
			/*
			 * Acquire rq_status_counter before parsing the rqst
			 * fields. rq_status_counter is set to an odd value in
			 * order to notify the consumers the rqstp fields are
			 * meaningful.
			 */
			status_counter =
				smp_load_acquire(&rqstp->rq_status_counter);
			if (!(status_counter & 1))
				continue;

			genl_rqstp.rq_xid = rqstp->rq_xid;
			genl_rqstp.rq_flags = rqstp->rq_flags;
			genl_rqstp.rq_vers = rqstp->rq_vers;
			genl_rqstp.rq_prog = rqstp->rq_prog;
			genl_rqstp.rq_proc = rqstp->rq_proc;
			genl_rqstp.rq_stime = rqstp->rq_stime;
			genl_rqstp.rq_opcnt = 0;
			memcpy(&genl_rqstp.rq_daddr, svc_daddr(rqstp),
			       sizeof(struct sockaddr));
			memcpy(&genl_rqstp.rq_saddr, svc_addr(rqstp),
			       sizeof(struct sockaddr));

#ifdef CONFIG_NFSD_V4
			if (rqstp->rq_vers == NFS4_VERSION &&
			    rqstp->rq_proc == NFSPROC4_COMPOUND) {
				/* NFSv4 compound */
				struct nfsd4_compoundargs *args;
				int j;

				args = rqstp->rq_argp;
				genl_rqstp.rq_opcnt = args->opcnt;
				for (j = 0; j < genl_rqstp.rq_opcnt; j++)
					genl_rqstp.rq_opnum[j] =
						args->ops[j].opnum;
			}
#endif /* CONFIG_NFSD_V4 */

			/*
			 * Acquire rq_status_counter before reporting the rqst
			 * fields to the user.
			 */
			if (smp_load_acquire(&rqstp->rq_status_counter) !=
			    status_counter)
				continue;

			ret = nfsd_genl_rpc_status_compose_msg(skb, cb,
							       &genl_rqstp);
			if (ret)
				goto out;
		}
	}

	cb->args[0] = i;
	cb->args[1] = rqstp_index;
	ret = skb->len;
out:
	rcu_read_unlock();
out_unlock:
	mutex_unlock(&nfsd_mutex);

	return ret;
}

/**
 * nfsd_nl_threads_set_doit - set the number of running threads
 * @skb: reply buffer
 * @info: netlink metadata and command arguments
 *
 * Return 0 on success or a negative errno.
 */
int nfsd_nl_threads_set_doit(struct sk_buff *skb, struct genl_info *info)
{
	int nthreads = 0, count = 0, nrpools, ret = -EOPNOTSUPP, rem;
	struct net *net = genl_info_net(info);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
	const struct nlattr *attr;
	const char *scope = NULL;

	if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_THREADS))
		return -EINVAL;

	/* count number of SERVER_THREADS values */
	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
		if (nla_type(attr) == NFSD_A_SERVER_THREADS)
			count++;
	}

	mutex_lock(&nfsd_mutex);

	nrpools = nfsd_nrpools(net);
	if (nrpools && count > nrpools)
		count = nrpools;

	/* XXX: make this handle non-global pool-modes */
	if (count > 1)
		goto out_unlock;

	nthreads = nla_get_u32(info->attrs[NFSD_A_SERVER_THREADS]);
	if (info->attrs[NFSD_A_SERVER_GRACETIME] ||
	    info->attrs[NFSD_A_SERVER_LEASETIME] ||
	    info->attrs[NFSD_A_SERVER_SCOPE]) {
		ret = -EBUSY;
		if (nn->nfsd_serv && nn->nfsd_serv->sv_nrthreads)
			goto out_unlock;

		ret = -EINVAL;
		attr = info->attrs[NFSD_A_SERVER_GRACETIME];
		if (attr) {
			u32 gracetime = nla_get_u32(attr);

			if (gracetime < 10 || gracetime > 3600)
				goto out_unlock;

			nn->nfsd4_grace = gracetime;
		}

		attr = info->attrs[NFSD_A_SERVER_LEASETIME];
		if (attr) {
			u32 leasetime = nla_get_u32(attr);

			if (leasetime < 10 || leasetime > 3600)
				goto out_unlock;

			nn->nfsd4_lease = leasetime;
		}

		attr = info->attrs[NFSD_A_SERVER_SCOPE];
		if (attr)
			scope = nla_data(attr);
	}

	ret = nfsd_svc(nthreads, net, get_current_cred(), scope);

out_unlock:
	mutex_unlock(&nfsd_mutex);

	return ret == nthreads ? 0 : ret;
}

/**
 * nfsd_nl_threads_get_doit - get the number of running threads
 * @skb: reply buffer
 * @info: netlink metadata and command arguments
 *
 * Return 0 on success or a negative errno.
 */
int nfsd_nl_threads_get_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct net *net = genl_info_net(info);
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
	void *hdr;
	int err;

	skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	hdr = genlmsg_iput(skb, info);
	if (!hdr) {
		err = -EMSGSIZE;
		goto err_free_msg;
	}

	mutex_lock(&nfsd_mutex);

	err = nla_put_u32(skb, NFSD_A_SERVER_GRACETIME,
			  nn->nfsd4_grace) ||
	      nla_put_u32(skb, NFSD_A_SERVER_LEASETIME,
			  nn->nfsd4_lease) ||
	      nla_put_string(skb, NFSD_A_SERVER_SCOPE,
			  nn->nfsd_name);
	if (err)
		goto err_unlock;

	if (nn->nfsd_serv) {
		int i;

		for (i = 0; i < nfsd_nrpools(net); ++i) {
			struct svc_pool *sp = &nn->nfsd_serv->sv_pools[i];

			err = nla_put_u32(skb, NFSD_A_SERVER_THREADS,
					  atomic_read(&sp->sp_nrthreads));
			if (err)
				goto err_unlock;
		}
	} else {
		err = nla_put_u32(skb, NFSD_A_SERVER_THREADS, 0);
		if (err)
			goto err_unlock;
	}

	mutex_unlock(&nfsd_mutex);

	genlmsg_end(skb, hdr);

	return genlmsg_reply(skb, info);

err_unlock:
	mutex_unlock(&nfsd_mutex);
err_free_msg:
	nlmsg_free(skb);

	return err;
}

/**
 * nfsd_nl_version_set_doit - set the nfs enabled versions
 * @skb: reply buffer
 * @info: netlink metadata and command arguments
 *
 * Return 0 on success or a negative errno.
 */
int nfsd_nl_version_set_doit(struct sk_buff *skb, struct genl_info *info)
{
	const struct nlattr *attr;
	struct nfsd_net *nn;
	int i, rem;

	if (GENL_REQ_ATTR_CHECK(info, NFSD_A_SERVER_PROTO_VERSION))
		return -EINVAL;

	mutex_lock(&nfsd_mutex);

	nn = net_generic(genl_info_net(info), nfsd_net_id);
	if (nn->nfsd_serv) {
		mutex_unlock(&nfsd_mutex);
		return -EBUSY;
	}

	/* clear current supported versions. */
	nfsd_vers(nn, 2, NFSD_CLEAR);
	nfsd_vers(nn, 3, NFSD_CLEAR);
	for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++)
		nfsd_minorversion(nn, i, NFSD_CLEAR);

	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
		struct nlattr *tb[NFSD_A_VERSION_MAX + 1];
		u32 major, minor = 0;
		bool enabled;

		if (nla_type(attr) != NFSD_A_SERVER_PROTO_VERSION)
			continue;

		if (nla_parse_nested(tb, NFSD_A_VERSION_MAX, attr,
				     nfsd_version_nl_policy, info->extack) < 0)
			continue;

		if (!tb[NFSD_A_VERSION_MAJOR])
			continue;

		major = nla_get_u32(tb[NFSD_A_VERSION_MAJOR]);
		if (tb[NFSD_A_VERSION_MINOR])
			minor = nla_get_u32(tb[NFSD_A_VERSION_MINOR]);

		enabled = nla_get_flag(tb[NFSD_A_VERSION_ENABLED]);

		switch (major) {
		case 4:
			nfsd_minorversion(nn, minor, enabled ? NFSD_SET : NFSD_CLEAR);
			break;
		case 3:
		case 2:
			if (!minor)
				nfsd_vers(nn, major, enabled ? NFSD_SET : NFSD_CLEAR);
			break;
		default:
			break;
		}
	}

	mutex_unlock(&nfsd_mutex);

	return 0;
}

/**
 * nfsd_nl_version_get_doit - get the enabled status for all supported nfs versions
 * @skb: reply buffer
 * @info: netlink metadata and command arguments
 *
 * Return 0 on success or a negative errno.
 */
int nfsd_nl_version_get_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct nfsd_net *nn;
	int i, err;
	void *hdr;

	skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	hdr = genlmsg_iput(skb, info);
	if (!hdr) {
		err = -EMSGSIZE;
		goto err_free_msg;
	}

	mutex_lock(&nfsd_mutex);
	nn = net_generic(genl_info_net(info), nfsd_net_id);

	for (i = 2; i <= 4; i++) {
		int j;

		for (j = 0; j <= NFSD_SUPPORTED_MINOR_VERSION; j++) {
			struct nlattr *attr;

			/* Don't record any versions the kernel doesn't have
			 * compiled in
			 */
			if (!nfsd_support_version(i))
				continue;

			/* NFSv{2,3} does not support minor numbers */
			if (i < 4 && j)
				continue;

			attr = nla_nest_start(skb,
					      NFSD_A_SERVER_PROTO_VERSION);
			if (!attr) {
				err = -EINVAL;
				goto err_nfsd_unlock;
			}

			if (nla_put_u32(skb, NFSD_A_VERSION_MAJOR, i) ||
			    nla_put_u32(skb, NFSD_A_VERSION_MINOR, j)) {
				err = -EINVAL;
				goto err_nfsd_unlock;
			}

			/* Set the enabled flag if the version is enabled */
			if (nfsd_vers(nn, i, NFSD_TEST) &&
			    (i < 4 || nfsd_minorversion(nn, j, NFSD_TEST)) &&
			    nla_put_flag(skb, NFSD_A_VERSION_ENABLED)) {
				err = -EINVAL;
				goto err_nfsd_unlock;
			}

			nla_nest_end(skb, attr);
		}
	}

	mutex_unlock(&nfsd_mutex);
	genlmsg_end(skb, hdr);

	return genlmsg_reply(skb, info);

err_nfsd_unlock:
	mutex_unlock(&nfsd_mutex);
err_free_msg:
	nlmsg_free(skb);

	return err;
}

/**
 * nfsd_nl_listener_set_doit - set the nfs running sockets
 * @skb: reply buffer
 * @info: netlink metadata and command arguments
 *
 * Return 0 on success or a negative errno.
 */
int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct net *net = genl_info_net(info);
	struct svc_xprt *xprt, *tmp;
	const struct nlattr *attr;
	struct svc_serv *serv;
	LIST_HEAD(permsocks);
	struct nfsd_net *nn;
	int err, rem;

	mutex_lock(&nfsd_mutex);

	err = nfsd_create_serv(net);
	if (err) {
		mutex_unlock(&nfsd_mutex);
		return err;
	}

	nn = net_generic(net, nfsd_net_id);
	serv = nn->nfsd_serv;

	spin_lock_bh(&serv->sv_lock);

	/* Move all of the old listener sockets to a temp list */
	list_splice_init(&serv->sv_permsocks, &permsocks);

	/*
	 * Walk the list of server_socks from userland and move any that match
	 * back to sv_permsocks
	 */
	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
		struct nlattr *tb[NFSD_A_SOCK_MAX + 1];
		const char *xcl_name;
		struct sockaddr *sa;

		if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR)
			continue;

		if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr,
				     nfsd_sock_nl_policy, info->extack) < 0)
			continue;

		if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME])
			continue;

		if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa))
			continue;

		xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]);
		sa = nla_data(tb[NFSD_A_SOCK_ADDR]);

		/* Put back any matching sockets */
		list_for_each_entry_safe(xprt, tmp, &permsocks, xpt_list) {
			/* This shouldn't be possible */
			if (WARN_ON_ONCE(xprt->xpt_net != net)) {
				list_move(&xprt->xpt_list, &serv->sv_permsocks);
				continue;
			}

			/* If everything matches, put it back */
			if (!strcmp(xprt->xpt_class->xcl_name, xcl_name) &&
			    rpc_cmp_addr_port(sa, (struct sockaddr *)&xprt->xpt_local)) {
				list_move(&xprt->xpt_list, &serv->sv_permsocks);
				break;
			}
		}
	}

	/* For now, no removing old sockets while server is running */
	if (serv->sv_nrthreads && !list_empty(&permsocks)) {
		list_splice_init(&permsocks, &serv->sv_permsocks);
		spin_unlock_bh(&serv->sv_lock);
		err = -EBUSY;
		goto out_unlock_mtx;
	}

	/* Close the remaining sockets on the permsocks list */
	while (!list_empty(&permsocks)) {
		xprt = list_first_entry(&permsocks, struct svc_xprt, xpt_list);
		list_move(&xprt->xpt_list, &serv->sv_permsocks);

		/*
		 * Newly-created sockets are born with the BUSY bit set. Clear
		 * it if there are no threads, since nothing can pick it up
		 * in that case.
		 */
		if (!serv->sv_nrthreads)
			clear_bit(XPT_BUSY, &xprt->xpt_flags);

		set_bit(XPT_CLOSE, &xprt->xpt_flags);
		spin_unlock_bh(&serv->sv_lock);
		svc_xprt_close(xprt);
		spin_lock_bh(&serv->sv_lock);
	}

	spin_unlock_bh(&serv->sv_lock);

	/* walk list of addrs again, open any that still don't exist */
	nlmsg_for_each_attr(attr, info->nlhdr, GENL_HDRLEN, rem) {
		struct nlattr *tb[NFSD_A_SOCK_MAX + 1];
		const char *xcl_name;
		struct sockaddr *sa;
		int ret;

		if (nla_type(attr) != NFSD_A_SERVER_SOCK_ADDR)
			continue;

		if (nla_parse_nested(tb, NFSD_A_SOCK_MAX, attr,
				     nfsd_sock_nl_policy, info->extack) < 0)
			continue;

		if (!tb[NFSD_A_SOCK_ADDR] || !tb[NFSD_A_SOCK_TRANSPORT_NAME])
			continue;

		if (nla_len(tb[NFSD_A_SOCK_ADDR]) < sizeof(*sa))
			continue;

		xcl_name = nla_data(tb[NFSD_A_SOCK_TRANSPORT_NAME]);
		sa = nla_data(tb[NFSD_A_SOCK_ADDR]);

		xprt = svc_find_listener(serv, xcl_name, net, sa);
		if (xprt) {
			svc_xprt_put(xprt);
			continue;
		}

		ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa,
					      SVC_SOCK_ANONYMOUS,
					      get_current_cred());
		/* always save the latest error */
		if (ret < 0)
			err = ret;
	}

	if (!serv->sv_nrthreads && list_empty(&nn->nfsd_serv->sv_permsocks))
		nfsd_destroy_serv(net);

out_unlock_mtx:
	mutex_unlock(&nfsd_mutex);

	return err;
}

/**
 * nfsd_nl_listener_get_doit - get the nfs running listeners
 * @skb: reply buffer
 * @info: netlink metadata and command arguments
 *
 * Return 0 on success or a negative errno.
 */
int nfsd_nl_listener_get_doit(struct sk_buff *skb, struct genl_info *info)
{
	struct svc_xprt *xprt;
	struct svc_serv *serv;
	struct nfsd_net *nn;
	void *hdr;
	int err;

	skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	hdr = genlmsg_iput(skb, info);
	if (!hdr) {
		err = -EMSGSIZE;
		goto err_free_msg;
	}

	mutex_lock(&nfsd_mutex);
	nn = net_generic(genl_info_net(info), nfsd_net_id);

	/* no nfs server? Just send empty socket list */
	if (!nn->nfsd_serv)
		goto out_unlock_mtx;

	serv = nn->nfsd_serv;
	spin_lock_bh(&serv->sv_lock);
	list_for_each_entry(xprt, &serv->sv_permsocks, xpt_list) {
		struct nlattr *attr;

		attr = nla_nest_start(skb, NFSD_A_SERVER_SOCK_ADDR);
		if (!attr) {
			err = -EINVAL;
			goto err_serv_unlock;
		}

		if (nla_put_string(skb, NFSD_A_SOCK_TRANSPORT_NAME,
				   xprt->xpt_class->xcl_name) ||
		    nla_put(skb, NFSD_A_SOCK_ADDR,
			    sizeof(struct sockaddr_storage),
			    &xprt->xpt_local)) {
			err = -EINVAL;
			goto err_serv_unlock;
		}

		nla_nest_end(skb, attr);
	}
	spin_unlock_bh(&serv->sv_lock);
out_unlock_mtx:
	mutex_unlock(&nfsd_mutex);
	genlmsg_end(skb, hdr);

	return genlmsg_reply(skb, info);

err_serv_unlock:
	spin_unlock_bh(&serv->sv_lock);
	mutex_unlock(&nfsd_mutex);
err_free_msg:
	nlmsg_free(skb);

	return err;
}

/**
 * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace
 * @net: a freshly-created network namespace
 *
 * This information stays around as long as the network namespace is
 * alive whether or not there is an NFSD instance running in the
 * namespace.
 *
 * Returns zero on success, or a negative errno otherwise.
 */
static __net_init int nfsd_net_init(struct net *net)
{
	int retval;
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	retval = nfsd_export_init(net);
	if (retval)
		goto out_export_error;
	retval = nfsd_idmap_init(net);
	if (retval)
		goto out_idmap_error;
	retval = percpu_counter_init_many(nn->counter, 0, GFP_KERNEL,
					  NFSD_STATS_COUNTERS_NUM);
	if (retval)
		goto out_repcache_error;
	memset(&nn->nfsd_svcstats, 0, sizeof(nn->nfsd_svcstats));
	nn->nfsd_svcstats.program = &nfsd_program;
	nn->nfsd_versions = NULL;
	nn->nfsd4_minorversions = NULL;
	nn->nfsd_info.mutex = &nfsd_mutex;
	nn->nfsd_serv = NULL;
	nfsd4_init_leases_net(nn);
	get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key));
	seqlock_init(&nn->writeverf_lock);
	nfsd_proc_stat_init(net);

	return 0;

out_repcache_error:
	nfsd_idmap_shutdown(net);
out_idmap_error:
	nfsd_export_shutdown(net);
out_export_error:
	return retval;
}

/**
 * nfsd_net_exit - Release the nfsd_net portion of a net namespace
 * @net: a network namespace that is about to be destroyed
 *
 */
static __net_exit void nfsd_net_exit(struct net *net)
{
	struct nfsd_net *nn = net_generic(net, nfsd_net_id);

	nfsd_proc_stat_shutdown(net);
	percpu_counter_destroy_many(nn->counter, NFSD_STATS_COUNTERS_NUM);
	nfsd_idmap_shutdown(net);
	nfsd_export_shutdown(net);
	nfsd_netns_free_versions(nn);
}

static struct pernet_operations nfsd_net_ops = {
	.init = nfsd_net_init,
	.exit = nfsd_net_exit,
	.id   = &nfsd_net_id,
	.size = sizeof(struct nfsd_net),
};

static int __init init_nfsd(void)
{
	int retval;

	retval = nfsd4_init_slabs();
	if (retval)
		return retval;
	retval = nfsd4_init_pnfs();
	if (retval)
		goto out_free_slabs;
	retval = nfsd_drc_slab_create();
	if (retval)
		goto out_free_pnfs;
	nfsd_lockd_init();	/* lockd->nfsd callbacks */
	retval = create_proc_exports_entry();
	if (retval)
		goto out_free_lockd;
	retval = register_pernet_subsys(&nfsd_net_ops);
	if (retval < 0)
		goto out_free_exports;
	retval = register_cld_notifier();
	if (retval)
		goto out_free_subsys;
	retval = nfsd4_create_laundry_wq();
	if (retval)
		goto out_free_cld;
	retval = register_filesystem(&nfsd_fs_type);
	if (retval)
		goto out_free_all;
	retval = genl_register_family(&nfsd_nl_family);
	if (retval)
		goto out_free_all;

	return 0;
out_free_all:
	nfsd4_destroy_laundry_wq();
out_free_cld:
	unregister_cld_notifier();
out_free_subsys:
	unregister_pernet_subsys(&nfsd_net_ops);
out_free_exports:
	remove_proc_entry("fs/nfs/exports", NULL);
	remove_proc_entry("fs/nfs", NULL);
out_free_lockd:
	nfsd_lockd_shutdown();
	nfsd_drc_slab_free();
out_free_pnfs:
	nfsd4_exit_pnfs();
out_free_slabs:
	nfsd4_free_slabs();
	return retval;
}

static void __exit exit_nfsd(void)
{
	genl_unregister_family(&nfsd_nl_family);
	unregister_filesystem(&nfsd_fs_type);
	nfsd4_destroy_laundry_wq();
	unregister_cld_notifier();
	unregister_pernet_subsys(&nfsd_net_ops);
	nfsd_drc_slab_free();
	remove_proc_entry("fs/nfs/exports", NULL);
	remove_proc_entry("fs/nfs", NULL);
	nfsd_lockd_shutdown();
	nfsd4_free_slabs();
	nfsd4_exit_pnfs();
}

MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
MODULE_DESCRIPTION("In-kernel NFS server");
MODULE_LICENSE("GPL");
module_init(init_nfsd)
module_exit(exit_nfsd)