summaryrefslogtreecommitdiff
path: root/fs/nfsd/nfsctl.c
blob: a4ed8644d69c0f5050d8e11cc6b66686b7804084 (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
/*
 * linux/fs/nfsd/nfsctl.c
 *
 * Syscall interface to knfsd.
 *
 * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
 */

#include <linux/module.h>

#include <linux/linkage.h>
#include <linux/time.h>
#include <linux/errno.h>
#include <linux/fs.h>
#include <linux/namei.h>
#include <linux/fcntl.h>
#include <linux/net.h>
#include <linux/in.h>
#include <linux/syscalls.h>
#include <linux/unistd.h>
#include <linux/slab.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/pagemap.h>
#include <linux/init.h>
#include <linux/inet.h>
#include <linux/string.h>
#include <linux/smp_lock.h>
#include <linux/ctype.h>

#include <linux/nfs.h>
#include <linux/nfsd_idmap.h>
#include <linux/lockd/bind.h>
#include <linux/sunrpc/svc.h>
#include <linux/sunrpc/svcsock.h>
#include <linux/nfsd/nfsd.h>
#include <linux/nfsd/cache.h>
#include <linux/nfsd/xdr.h>
#include <linux/nfsd/syscall.h>
#include <linux/lockd/lockd.h>

#include <asm/uaccess.h>
#include <net/ipv6.h>

/*
 *	We have a single directory with 9 nodes in it.
 */
enum {
	NFSD_Root = 1,
	NFSD_Svc,
	NFSD_Add,
	NFSD_Del,
	NFSD_Export,
	NFSD_Unexport,
	NFSD_Getfd,
	NFSD_Getfs,
	NFSD_List,
	NFSD_Fh,
	NFSD_FO_UnlockIP,
	NFSD_FO_UnlockFS,
	NFSD_Threads,
	NFSD_Pool_Threads,
	NFSD_Versions,
	NFSD_Ports,
	NFSD_MaxBlkSize,
	/*
	 * The below MUST come last.  Otherwise we leave a hole in nfsd_files[]
	 * with !CONFIG_NFSD_V4 and simple_fill_super() goes oops
	 */
#ifdef CONFIG_NFSD_V4
	NFSD_Leasetime,
	NFSD_RecoveryDir,
#endif
};

/*
 * write() for these nodes.
 */
static ssize_t write_svc(struct file *file, char *buf, size_t size);
static ssize_t write_add(struct file *file, char *buf, size_t size);
static ssize_t write_del(struct file *file, char *buf, size_t size);
static ssize_t write_export(struct file *file, char *buf, size_t size);
static ssize_t write_unexport(struct file *file, char *buf, size_t size);
static ssize_t write_getfd(struct file *file, char *buf, size_t size);
static ssize_t write_getfs(struct file *file, char *buf, size_t size);
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);
#ifdef CONFIG_NFSD_V4
static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
#endif

static ssize_t (*write_op[])(struct file *, char *, size_t) = {
	[NFSD_Svc] = write_svc,
	[NFSD_Add] = write_add,
	[NFSD_Del] = write_del,
	[NFSD_Export] = write_export,
	[NFSD_Unexport] = write_unexport,
	[NFSD_Getfd] = write_getfd,
	[NFSD_Getfs] = write_getfs,
	[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,
#ifdef CONFIG_NFSD_V4
	[NFSD_Leasetime] = write_leasetime,
	[NFSD_RecoveryDir] = write_recoverydir,
#endif
};

static ssize_t nfsctl_transaction_write(struct file *file, const char __user *buf, size_t size, loff_t *pos)
{
	ino_t ino =  file->f_path.dentry->d_inode->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) {
		simple_transaction_set(file, rv);
		rv = size;
	}
	return rv;
}

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,
};

static int exports_open(struct inode *inode, struct file *file)
{
	return seq_open(file, &nfs_exports_op);
}

static const struct file_operations exports_operations = {
	.open		= exports_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= seq_release,
	.owner		= THIS_MODULE,
};

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

/**
 * write_svc - Start kernel's NFSD server
 *
 * Deprecated.  /proc/fs/nfsd/threads is preferred.
 * Function remains to support old versions of nfs-utils.
 *
 * Input:
 *			buf:	struct nfsctl_svc
 *				svc_port:	port number of this
 *						server's listener
 *				svc_nthreads:	number of threads to start
 *			size:	size in bytes of passed in nfsctl_svc
 * Output:
 *	On success:	returns zero
 *	On error:	return code is negative errno value
 */
static ssize_t write_svc(struct file *file, char *buf, size_t size)
{
	struct nfsctl_svc *data;
	if (size < sizeof(*data))
		return -EINVAL;
	data = (struct nfsctl_svc*) buf;
	return nfsd_svc(data->svc_port, data->svc_nthreads);
}

/**
 * write_add - Add or modify client entry in auth unix cache
 *
 * Deprecated.  /proc/net/rpc/auth.unix.ip is preferred.
 * Function remains to support old versions of nfs-utils.
 *
 * Input:
 *			buf:	struct nfsctl_client
 *				cl_ident:	'\0'-terminated C string
 *						containing domain name
 *						of client
 *				cl_naddr:	no. of items in cl_addrlist
 *				cl_addrlist:	array of client addresses
 *				cl_fhkeytype:	ignored
 *				cl_fhkeylen:	ignored
 *				cl_fhkey:	ignored
 *			size:	size in bytes of passed in nfsctl_client
 * Output:
 *	On success:	returns zero
 *	On error:	return code is negative errno value
 *
 * Note: Only AF_INET client addresses are passed in, since
 * nfsctl_client.cl_addrlist contains only in_addr fields for addresses.
 */
static ssize_t write_add(struct file *file, char *buf, size_t size)
{
	struct nfsctl_client *data;
	if (size < sizeof(*data))
		return -EINVAL;
	data = (struct nfsctl_client *)buf;
	return exp_addclient(data);
}

/**
 * write_del - Remove client from auth unix cache
 *
 * Deprecated.  /proc/net/rpc/auth.unix.ip is preferred.
 * Function remains to support old versions of nfs-utils.
 *
 * Input:
 *			buf:	struct nfsctl_client
 *				cl_ident:	'\0'-terminated C string
 *						containing domain name
 *						of client
 *				cl_naddr:	ignored
 *				cl_addrlist:	ignored
 *				cl_fhkeytype:	ignored
 *				cl_fhkeylen:	ignored
 *				cl_fhkey:	ignored
 *			size:	size in bytes of passed in nfsctl_client
 * Output:
 *	On success:	returns zero
 *	On error:	return code is negative errno value
 *
 * Note: Only AF_INET client addresses are passed in, since
 * nfsctl_client.cl_addrlist contains only in_addr fields for addresses.
 */
static ssize_t write_del(struct file *file, char *buf, size_t size)
{
	struct nfsctl_client *data;
	if (size < sizeof(*data))
		return -EINVAL;
	data = (struct nfsctl_client *)buf;
	return exp_delclient(data);
}

/**
 * write_export - Export part or all of a local file system
 *
 * Deprecated.  /proc/net/rpc/{nfsd.export,nfsd.fh} are preferred.
 * Function remains to support old versions of nfs-utils.
 *
 * Input:
 *			buf:	struct nfsctl_export
 *				ex_client:	'\0'-terminated C string
 *						containing domain name
 *						of client allowed to access
 *						this export
 *				ex_path:	'\0'-terminated C string
 *						containing pathname of
 *						directory in local file system
 *				ex_dev:		fsid to use for this export
 *				ex_ino:		ignored
 *				ex_flags:	export flags for this export
 *				ex_anon_uid:	UID to use for anonymous
 *						requests
 *				ex_anon_gid:	GID to use for anonymous
 *						requests
 *			size:	size in bytes of passed in nfsctl_export
 * Output:
 *	On success:	returns zero
 *	On error:	return code is negative errno value
 */
static ssize_t write_export(struct file *file, char *buf, size_t size)
{
	struct nfsctl_export *data;
	if (size < sizeof(*data))
		return -EINVAL;
	data = (struct nfsctl_export*)buf;
	return exp_export(data);
}

/**
 * write_unexport - Unexport a previously exported file system
 *
 * Deprecated.  /proc/net/rpc/{nfsd.export,nfsd.fh} are preferred.
 * Function remains to support old versions of nfs-utils.
 *
 * Input:
 *			buf:	struct nfsctl_export
 *				ex_client:	'\0'-terminated C string
 *						containing domain name
 *						of client no longer allowed
 *						to access this export
 *				ex_path:	'\0'-terminated C string
 *						containing pathname of
 *						directory in local file system
 *				ex_dev:		ignored
 *				ex_ino:		ignored
 *				ex_flags:	ignored
 *				ex_anon_uid:	ignored
 *				ex_anon_gid:	ignored
 *			size:	size in bytes of passed in nfsctl_export
 * Output:
 *	On success:	returns zero
 *	On error:	return code is negative errno value
 */
static ssize_t write_unexport(struct file *file, char *buf, size_t size)
{
	struct nfsctl_export *data;

	if (size < sizeof(*data))
		return -EINVAL;
	data = (struct nfsctl_export*)buf;
	return exp_unexport(data);
}

/**
 * write_getfs - Get a variable-length NFS file handle by path
 *
 * Deprecated.  /proc/fs/nfsd/filehandle is preferred.
 * Function remains to support old versions of nfs-utils.
 *
 * Input:
 *			buf:	struct nfsctl_fsparm
 *				gd_addr:	socket address of client
 *				gd_path:	'\0'-terminated C string
 *						containing pathname of
 *						directory in local file system
 *				gd_maxlen:	maximum size of returned file
 *						handle
 *			size:	size in bytes of passed in nfsctl_fsparm
 * Output:
 *	On success:	passed-in buffer filled with a knfsd_fh structure
 *			(a variable-length raw NFS file handle);
 *			return code is the size in bytes of the file handle
 *	On error:	return code is negative errno value
 *
 * Note: Only AF_INET client addresses are passed in, since gd_addr
 * is the same size as a struct sockaddr_in.
 */
static ssize_t write_getfs(struct file *file, char *buf, size_t size)
{
	struct nfsctl_fsparm *data;
	struct sockaddr_in *sin;
	struct auth_domain *clp;
	int err = 0;
	struct knfsd_fh *res;
	struct in6_addr in6;

	if (size < sizeof(*data))
		return -EINVAL;
	data = (struct nfsctl_fsparm*)buf;
	err = -EPROTONOSUPPORT;
	if (data->gd_addr.sa_family != AF_INET)
		goto out;
	sin = (struct sockaddr_in *)&data->gd_addr;
	if (data->gd_maxlen > NFS3_FHSIZE)
		data->gd_maxlen = NFS3_FHSIZE;

	res = (struct knfsd_fh*)buf;

	exp_readlock();

	ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);

	clp = auth_unix_lookup(&in6);
	if (!clp)
		err = -EPERM;
	else {
		err = exp_rootfh(clp, data->gd_path, res, data->gd_maxlen);
		auth_domain_put(clp);
	}
	exp_readunlock();
	if (err == 0)
		err = res->fh_size + offsetof(struct knfsd_fh, fh_base);
 out:
	return err;
}

/**
 * write_getfd - Get a fixed-length NFS file handle by path (used by mountd)
 *
 * Deprecated.  /proc/fs/nfsd/filehandle is preferred.
 * Function remains to support old versions of nfs-utils.
 *
 * Input:
 *			buf:	struct nfsctl_fdparm
 *				gd_addr:	socket address of client
 *				gd_path:	'\0'-terminated C string
 *						containing pathname of
 *						directory in local file system
 *				gd_version:	fdparm structure version
 *			size:	size in bytes of passed in nfsctl_fdparm
 * Output:
 *	On success:	passed-in buffer filled with nfsctl_res
 *			(a fixed-length raw NFS file handle);
 *			return code is the size in bytes of the file handle
 *	On error:	return code is negative errno value
 *
 * Note: Only AF_INET client addresses are passed in, since gd_addr
 * is the same size as a struct sockaddr_in.
 */
static ssize_t write_getfd(struct file *file, char *buf, size_t size)
{
	struct nfsctl_fdparm *data;
	struct sockaddr_in *sin;
	struct auth_domain *clp;
	int err = 0;
	struct knfsd_fh fh;
	char *res;
	struct in6_addr in6;

	if (size < sizeof(*data))
		return -EINVAL;
	data = (struct nfsctl_fdparm*)buf;
	err = -EPROTONOSUPPORT;
	if (data->gd_addr.sa_family != AF_INET)
		goto out;
	err = -EINVAL;
	if (data->gd_version < 2 || data->gd_version > NFSSVC_MAXVERS)
		goto out;

	res = buf;
	sin = (struct sockaddr_in *)&data->gd_addr;
	exp_readlock();

	ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);

	clp = auth_unix_lookup(&in6);
	if (!clp)
		err = -EPERM;
	else {
		err = exp_rootfh(clp, data->gd_path, &fh, NFS_FHSIZE);
		auth_domain_put(clp);
	}
	exp_readunlock();

	if (err == 0) {
		memset(res,0, NFS_FHSIZE);
		memcpy(res, &fh.fh_base, fh.fh_size);
		err = NFS_FHSIZE;
	}
 out:
	return err;
}

/**
 * write_unlock_ip - Release all locks used by a client
 *
 * Experimental.
 *
 * Input:
 *			buf:	'\n'-terminated C string containing a
 *				presentation format IPv4 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
 *
 * Note: Only AF_INET client addresses are passed in
 */
static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
{
	struct sockaddr_in sin = {
		.sin_family	= AF_INET,
	};
	int b1, b2, b3, b4;
	char c;
	char *fo_path;

	/* 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;

	/* get ipv4 address */
	if (sscanf(fo_path, "%u.%u.%u.%u%c", &b1, &b2, &b3, &b4, &c) != 4)
		return -EINVAL;
	if (b1 > 255 || b2 > 255 || b3 > 255 || b4 > 255)
		return -EINVAL;
	sin.sin_addr.s_addr = htonl((b1 << 24) | (b2 << 16) | (b3 << 8) | b4);

	return nlmsvc_unlock_all_by_ip((struct sockaddr *)&sin);
}

/**
 * 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;

	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.mnt->mnt_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 uninitialized_var(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;
	if (maxsize > NFS3_FHSIZE)
		maxsize = NFS3_FHSIZE;

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

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

	len = exp_rootfh(dom, path, &fh,  maxsize);
	auth_domain_put(dom);
	if (len)
		return len;
	
	mesg = buf;
	len = SIMPLE_TRANSACTION_LIMIT;
	qword_addhex(&mesg, &len, (char*)&fh.fh_base, 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;
	if (size > 0) {
		int newthreads;
		rv = get_int(&mesg, &newthreads);
		if (rv)
			return rv;
		if (newthreads < 0)
			return -EINVAL;
		rv = nfsd_svc(NFS_PORT, newthreads);
		if (rv)
			return rv;
	}
	sprintf(buf, "%d\n", nfsd_nrthreads());
	return strlen(buf);
}

/**
 * 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;

	mutex_lock(&nfsd_mutex);
	npools = nfsd_nrpools();
	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;
		}
		rv = nfsd_set_nrthreads(i, nthreads);
		if (rv)
			goto out_free;
	}

	rv = nfsd_get_nrthreads(npools, nthreads);
	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;
	}

	mutex_unlock(&nfsd_mutex);
	return (mesg-buf);

out_free:
	kfree(nthreads);
	mutex_unlock(&nfsd_mutex);
	return rv;
}

static ssize_t __write_versions(struct file *file, char *buf, size_t size)
{
	char *mesg = buf;
	char *vers, sign;
	int len, num;
	ssize_t tlen = 0;
	char *sep;

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

		vers = mesg;
		len = qword_get(&mesg, vers, size);
		if (len <= 0) return -EINVAL;
		do {
			sign = *vers;
			if (sign == '+' || sign == '-')
				num = simple_strtol((vers+1), NULL, 0);
			else
				num = simple_strtol(vers, NULL, 0);
			switch(num) {
			case 2:
			case 3:
			case 4:
				nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET);
				break;
			default:
				return -EINVAL;
			}
			vers += len + 1;
			tlen += len;
		} 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();
	}
	/* Now write current state into reply buffer */
	len = 0;
	sep = "";
	for (num=2 ; num <= 4 ; num++)
		if (nfsd_vers(num, NFSD_AVAIL)) {
			len += sprintf(buf+len, "%s%c%d", sep,
				       nfsd_vers(num, NFSD_TEST)?'+':'-',
				       num);
			sep = " ";
		}
	len += sprintf(buf+len, "\n");
	return 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;
}

static ssize_t __write_ports(struct file *file, char *buf, size_t size)
{
	if (size == 0) {
		int len = 0;

		if (nfsd_serv)
			len = svc_xprt_names(nfsd_serv, buf, 0);
		return len;
	}
	/* Either a single 'fd' number is written, in which
	 * case it must be for a socket of a supported family/protocol,
	 * and we use it as an nfsd socket, or
	 * A '-' followed by the 'name' of a socket in which case
	 * we close the socket.
	 */
	if (isdigit(buf[0])) {
		char *mesg = buf;
		int fd;
		int err;
		err = get_int(&mesg, &fd);
		if (err)
			return -EINVAL;
		if (fd < 0)
			return -EINVAL;
		err = nfsd_create_serv();
		if (!err) {
			err = svc_addsock(nfsd_serv, fd, buf);
			if (err >= 0) {
				err = lockd_up();
				if (err < 0)
					svc_sock_names(buf+strlen(buf)+1, nfsd_serv, buf);
			}
			/* Decrease the count, but don't shutdown the
			 * the service
			 */
			nfsd_serv->sv_nrthreads--;
		}
		return err < 0 ? err : 0;
	}
	if (buf[0] == '-' && isdigit(buf[1])) {
		char *toclose = kstrdup(buf+1, GFP_KERNEL);
		int len = 0;
		if (!toclose)
			return -ENOMEM;
		if (nfsd_serv)
			len = svc_sock_names(buf, nfsd_serv, toclose);
		if (len >= 0)
			lockd_down();
		kfree(toclose);
		return len;
	}
	/*
	 * Add a transport listener by writing it's transport name
	 */
	if (isalpha(buf[0])) {
		int err;
		char transport[16];
		int port;
		if (sscanf(buf, "%15s %4d", transport, &port) == 2) {
			if (port < 1 || port > 65535)
				return -EINVAL;
			err = nfsd_create_serv();
			if (!err) {
				err = svc_create_xprt(nfsd_serv,
						      transport, PF_INET, port,
						      SVC_SOCK_ANONYMOUS);
				if (err == -ENOENT)
					/* Give a reasonable perror msg for
					 * bad transport string */
					err = -EPROTONOSUPPORT;
			}
			return err < 0 ? err : 0;
		}
	}
	/*
	 * Remove a transport by writing it's transport name and port number
	 */
	if (buf[0] == '-' && isalpha(buf[1])) {
		struct svc_xprt *xprt;
		int err = -EINVAL;
		char transport[16];
		int port;
		if (sscanf(&buf[1], "%15s %4d", transport, &port) == 2) {
			if (port < 1 || port > 65535)
				return -EINVAL;
			if (nfsd_serv) {
				xprt = svc_find_xprt(nfsd_serv, transport,
						     AF_UNSPEC, port);
				if (xprt) {
					svc_close_xprt(xprt);
					svc_xprt_put(xprt);
					err = 0;
				} else
					err = -ENOTCONN;
			}
			return err < 0 ? err : 0;
		}
	}
	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
 *			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 "-" followed
 *					by an integer value representing a
 *					previously passed in socket file
 *					descriptor
 *			size:		non-zero length of C string in @buf
 * Output:
 *	On success:	NFS service no longer listens on that socket;
 *			passed-in buffer filled with a '\n'-terminated C
 *			string containing a unique 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
 *
 * OR
 *
 * Input:
 *			buf:		C string containing a "-" followed
 *					by 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 no longer listens
 *			on that transport
 *	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);
	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;
	if (size > 0) {
		int bsize;
		int rv = get_int(&mesg, &bsize);
		if (rv)
			return rv;
		/* force bsize into allowed range and
		 * required alignment.
		 */
		if (bsize < 1024)
			bsize = 1024;
		if (bsize > NFSSVC_MAXBLKSIZE)
			bsize = NFSSVC_MAXBLKSIZE;
		bsize &= ~(1024-1);
		mutex_lock(&nfsd_mutex);
		if (nfsd_serv && nfsd_serv->sv_nrthreads) {
			mutex_unlock(&nfsd_mutex);
			return -EBUSY;
		}
		nfsd_max_blksize = bsize;
		mutex_unlock(&nfsd_mutex);
	}
	return sprintf(buf, "%d\n", nfsd_max_blksize);
}

#ifdef CONFIG_NFSD_V4
extern time_t nfs4_leasetime(void);

static ssize_t __write_leasetime(struct file *file, char *buf, size_t size)
{
	/* if size > 10 seconds, call
	 * nfs4_reset_lease() then write out the new lease (seconds) as reply
	 */
	char *mesg = buf;
	int rv, lease;

	if (size > 0) {
		if (nfsd_serv)
			return -EBUSY;
		rv = get_int(&mesg, &lease);
		if (rv)
			return rv;
		if (lease < 10 || lease > 3600)
			return -EINVAL;
		nfs4_reset_lease(lease);
	}
	sprintf(buf, "%ld\n", nfs4_lease_time());
	return strlen(buf);
}

/**
 * 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)
{
	ssize_t rv;

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

extern char *nfs4_recoverydir(void);

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

	if (size > 0) {
		if (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;

		status = nfs4_reset_recoverydir(recdir);
	}
	sprintf(buf, "%s\n", nfs4_recoverydir());
	return strlen(buf);
}

/**
 * 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;

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

#endif

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

static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
{
	static struct tree_descr nfsd_files[] = {
		[NFSD_Svc] = {".svc", &transaction_ops, S_IWUSR},
		[NFSD_Add] = {".add", &transaction_ops, S_IWUSR},
		[NFSD_Del] = {".del", &transaction_ops, S_IWUSR},
		[NFSD_Export] = {".export", &transaction_ops, S_IWUSR},
		[NFSD_Unexport] = {".unexport", &transaction_ops, S_IWUSR},
		[NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_List] = {"exports", &exports_operations, 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_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},
#ifdef CONFIG_NFSD_V4
		[NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR},
		[NFSD_RecoveryDir] = {"nfsv4recoverydir", &transaction_ops, S_IWUSR|S_IRUSR},
#endif
		/* last one */ {""}
	};
	return simple_fill_super(sb, 0x6e667364, nfsd_files);
}

static int nfsd_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	return get_sb_single(fs_type, flags, data, nfsd_fill_super, mnt);
}

static struct file_system_type nfsd_fs_type = {
	.owner		= THIS_MODULE,
	.name		= "nfsd",
	.get_sb		= nfsd_get_sb,
	.kill_sb	= kill_litter_super,
};

#ifdef CONFIG_PROC_FS
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_operations);
	if (!entry)
		return -ENOMEM;
	return 0;
}
#else /* CONFIG_PROC_FS */
static int create_proc_exports_entry(void)
{
	return 0;
}
#endif

static int __init init_nfsd(void)
{
	int retval;
	printk(KERN_INFO "Installing knfsd (copyright (C) 1996 okir@monad.swb.de).\n");

	retval = nfs4_state_init(); /* nfs4 locking state */
	if (retval)
		return retval;
	nfsd_stat_init();	/* Statistics */
	retval = nfsd_reply_cache_init();
	if (retval)
		goto out_free_stat;
	retval = nfsd_export_init();
	if (retval)
		goto out_free_cache;
	nfsd_lockd_init();	/* lockd->nfsd callbacks */
	retval = nfsd_idmap_init();
	if (retval)
		goto out_free_lockd;
	retval = create_proc_exports_entry();
	if (retval)
		goto out_free_idmap;
	retval = register_filesystem(&nfsd_fs_type);
	if (retval)
		goto out_free_all;
	return 0;
out_free_all:
	remove_proc_entry("fs/nfs/exports", NULL);
	remove_proc_entry("fs/nfs", NULL);
out_free_idmap:
	nfsd_idmap_shutdown();
out_free_lockd:
	nfsd_lockd_shutdown();
	nfsd_export_shutdown();
out_free_cache:
	nfsd_reply_cache_shutdown();
out_free_stat:
	nfsd_stat_shutdown();
	nfsd4_free_slabs();
	return retval;
}

static void __exit exit_nfsd(void)
{
	nfsd_export_shutdown();
	nfsd_reply_cache_shutdown();
	remove_proc_entry("fs/nfs/exports", NULL);
	remove_proc_entry("fs/nfs", NULL);
	nfsd_stat_shutdown();
	nfsd_lockd_shutdown();
	nfsd_idmap_shutdown();
	nfsd4_free_slabs();
	unregister_filesystem(&nfsd_fs_type);
}

MODULE_AUTHOR("Olaf Kirch <okir@monad.swb.de>");
MODULE_LICENSE("GPL");
module_init(init_nfsd)
module_exit(exit_nfsd)