aboutsummaryrefslogtreecommitdiffstats
path: root/sys/kern/kern_descrip.c
blob: 50888ce6820aadc726afeeb585b5cb8609a72aec (plain) (blame)
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
/*
 * Copyright (c) 1982, 1986, 1989, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 * (c) UNIX System Laboratories, Inc.
 * All or some portions of this file are derived from material licensed
 * to the University of California by American Telephone and Telegraph
 * Co. or Unix System Laboratories, Inc. and are reproduced herein with
 * the permission of UNIX System Laboratories, Inc.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)kern_descrip.c	8.6 (Berkeley) 4/19/94
 * $FreeBSD$
 */

#include "opt_compat.h"
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/malloc.h>
#include <sys/sysproto.h>
#include <sys/conf.h>
#include <sys/filedesc.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/vnode.h>
#include <sys/proc.h>
#include <sys/namei.h>
#include <sys/file.h>
#include <sys/stat.h>
#include <sys/filio.h>
#include <sys/fcntl.h>
#include <sys/unistd.h>
#include <sys/resourcevar.h>
#include <sys/event.h>

#include <vm/vm.h>
#include <vm/vm_extern.h>

static MALLOC_DEFINE(M_FILEDESC, "file desc", "Open file descriptor table");
MALLOC_DEFINE(M_FILE, "file", "Open file structure");
static MALLOC_DEFINE(M_SIGIO, "sigio", "sigio structures");

static	 d_open_t  fdopen;
#define NUMFDESC 64

#define CDEV_MAJOR 22
static struct cdevsw fildesc_cdevsw = {
	/* open */	fdopen,
	/* close */	noclose,
	/* read */	noread,
	/* write */	nowrite,
	/* ioctl */	noioctl,
	/* poll */	nopoll,
	/* mmap */	nommap,
	/* strategy */	nostrategy,
	/* name */	"FD",
	/* maj */	CDEV_MAJOR,
	/* dump */	nodump,
	/* psize */	nopsize,
	/* flags */	0,
	/* bmaj */	-1
};

static int do_dup __P((struct filedesc *fdp, int old, int new, register_t *retval, struct proc *p));
static int badfo_readwrite __P((struct file *fp, struct uio *uio,
    struct ucred *cred, int flags, struct proc *p));
static int badfo_ioctl __P((struct file *fp, u_long com, caddr_t data,
    struct proc *p));
static int badfo_poll __P((struct file *fp, int events,
    struct ucred *cred, struct proc *p));
static int badfo_kqfilter __P((struct file *fp, struct knote *kn));
static int badfo_stat __P((struct file *fp, struct stat *sb, struct proc *p));
static int badfo_close __P((struct file *fp, struct proc *p));

/*
 * Descriptor management.
 */
struct filelist filehead;	/* head of list of open files */
int nfiles;			/* actual number of open files */
extern int cmask;	

/*
 * System calls on descriptors.
 */
#ifndef _SYS_SYSPROTO_H_
struct getdtablesize_args {
	int	dummy;
};
#endif
/* ARGSUSED */
int
getdtablesize(p, uap)
	struct proc *p;
	struct getdtablesize_args *uap;
{

	p->p_retval[0] = 
	    min((int)p->p_rlimit[RLIMIT_NOFILE].rlim_cur, maxfilesperproc);
	return (0);
}

/*
 * Duplicate a file descriptor to a particular value.
 *
 * note: keep in mind that a potential race condition exists when closing
 * descriptors from a shared descriptor table (via rfork).
 */
#ifndef _SYS_SYSPROTO_H_
struct dup2_args {
	u_int	from;
	u_int	to;
};
#endif
/* ARGSUSED */
int
dup2(p, uap)
	struct proc *p;
	struct dup2_args *uap;
{
	register struct filedesc *fdp = p->p_fd;
	register u_int old = uap->from, new = uap->to;
	int i, error;

retry:
	if (old >= fdp->fd_nfiles ||
	    fdp->fd_ofiles[old] == NULL ||
	    new >= p->p_rlimit[RLIMIT_NOFILE].rlim_cur ||
	    new >= maxfilesperproc) {
		return (EBADF);
	}
	if (old == new) {
		p->p_retval[0] = new;
		return (0);
	}
	if (new >= fdp->fd_nfiles) {
		if ((error = fdalloc(p, new, &i)))
			return (error);
		/*
		 * fdalloc() may block, retest everything.
		 */
		goto retry;
	}
	return (do_dup(fdp, (int)old, (int)new, p->p_retval, p));
}

/*
 * Duplicate a file descriptor.
 */
#ifndef _SYS_SYSPROTO_H_
struct dup_args {
	u_int	fd;
};
#endif
/* ARGSUSED */
int
dup(p, uap)
	struct proc *p;
	struct dup_args *uap;
{
	register struct filedesc *fdp;
	u_int old;
	int new, error;

	old = uap->fd;
	fdp = p->p_fd;
	if (old >= fdp->fd_nfiles || fdp->fd_ofiles[old] == NULL)
		return (EBADF);
	if ((error = fdalloc(p, 0, &new)))
		return (error);
	return (do_dup(fdp, (int)old, new, p->p_retval, p));
}

/*
 * The file control system call.
 */
#ifndef _SYS_SYSPROTO_H_
struct fcntl_args {
	int	fd;
	int	cmd;
	long	arg;
};
#endif
/* ARGSUSED */
int
fcntl(p, uap)
	struct proc *p;
	register struct fcntl_args *uap;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file *fp;
	register char *pop;
	struct vnode *vp;
	int i, tmp, error, flg = F_POSIX;
	struct flock fl;
	u_int newmin;

	if ((unsigned)uap->fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[uap->fd]) == NULL)
		return (EBADF);
	pop = &fdp->fd_ofileflags[uap->fd];

	switch (uap->cmd) {
	case F_DUPFD:
		newmin = uap->arg;
		if (newmin >= p->p_rlimit[RLIMIT_NOFILE].rlim_cur ||
		    newmin >= maxfilesperproc)
			return (EINVAL);
		if ((error = fdalloc(p, newmin, &i)))
			return (error);
		return (do_dup(fdp, uap->fd, i, p->p_retval, p));

	case F_GETFD:
		p->p_retval[0] = (*pop & UF_EXCLOSE) ? FD_CLOEXEC : 0;
		return (0);

	case F_SETFD:
		*pop = (*pop &~ UF_EXCLOSE) |
		    (uap->arg & FD_CLOEXEC ? UF_EXCLOSE : 0);
		return (0);

	case F_GETFL:
		p->p_retval[0] = OFLAGS(fp->f_flag);
		return (0);

	case F_SETFL:
		fhold(fp);
		fp->f_flag &= ~FCNTLFLAGS;
		fp->f_flag |= FFLAGS(uap->arg & ~O_ACCMODE) & FCNTLFLAGS;
		tmp = fp->f_flag & FNONBLOCK;
		error = fo_ioctl(fp, FIONBIO, (caddr_t)&tmp, p);
		if (error) {
			fdrop(fp, p);
			return (error);
		}
		tmp = fp->f_flag & FASYNC;
		error = fo_ioctl(fp, FIOASYNC, (caddr_t)&tmp, p);
		if (!error) {
			fdrop(fp, p);
			return (0);
		}
		fp->f_flag &= ~FNONBLOCK;
		tmp = 0;
		(void)fo_ioctl(fp, FIONBIO, (caddr_t)&tmp, p);
		fdrop(fp, p);
		return (error);

	case F_GETOWN:
		fhold(fp);
		error = fo_ioctl(fp, FIOGETOWN, (caddr_t)p->p_retval, p);
		fdrop(fp, p);
		return(error);

	case F_SETOWN:
		fhold(fp);
		error = fo_ioctl(fp, FIOSETOWN, (caddr_t)&uap->arg, p);
		fdrop(fp, p);
		return(error);

	case F_SETLKW:
		flg |= F_WAIT;
		/* Fall into F_SETLK */

	case F_SETLK:
		if (fp->f_type != DTYPE_VNODE)
			return (EBADF);
		vp = (struct vnode *)fp->f_data;

		/*
		 * copyin/lockop may block
		 */
		fhold(fp);
		/* Copy in the lock structure */
		error = copyin((caddr_t)(intptr_t)uap->arg, (caddr_t)&fl,
		    sizeof(fl));
		if (error) {
			fdrop(fp, p);
			return (error);
		}
		if (fl.l_whence == SEEK_CUR)
			fl.l_start += fp->f_offset;

		switch (fl.l_type) {
		case F_RDLCK:
			if ((fp->f_flag & FREAD) == 0) {
				error = EBADF;
				break;
			}
			p->p_flag |= P_ADVLOCK;
			error = VOP_ADVLOCK(vp, (caddr_t)p->p_leader, F_SETLK,
			    &fl, flg);
			break;
		case F_WRLCK:
			if ((fp->f_flag & FWRITE) == 0) {
				error = EBADF;
				break;
			}
			p->p_flag |= P_ADVLOCK;
			error = VOP_ADVLOCK(vp, (caddr_t)p->p_leader, F_SETLK,
			    &fl, flg);
			break;
		case F_UNLCK:
			error = VOP_ADVLOCK(vp, (caddr_t)p->p_leader, F_UNLCK,
				&fl, F_POSIX);
			break;
		default:
			error = EINVAL;
			break;
		}
		fdrop(fp, p);
		return(error);

	case F_GETLK:
		if (fp->f_type != DTYPE_VNODE)
			return (EBADF);
		vp = (struct vnode *)fp->f_data;
		/*
		 * copyin/lockop may block
		 */
		fhold(fp);
		/* Copy in the lock structure */
		error = copyin((caddr_t)(intptr_t)uap->arg, (caddr_t)&fl,
		    sizeof(fl));
		if (error) {
			fdrop(fp, p);
			return (error);
		}
		if (fl.l_type != F_RDLCK && fl.l_type != F_WRLCK &&
		    fl.l_type != F_UNLCK) {
			fdrop(fp, p);
			return (EINVAL);
		}
		if (fl.l_whence == SEEK_CUR)
			fl.l_start += fp->f_offset;
		error = VOP_ADVLOCK(vp, (caddr_t)p->p_leader, F_GETLK,
			    &fl, F_POSIX);
		fdrop(fp, p);
		if (error == 0) {
			error = copyout((caddr_t)&fl,
				    (caddr_t)(intptr_t)uap->arg, sizeof(fl));
		}
		return(error);
	default:
		return (EINVAL);
	}
	/* NOTREACHED */
}

/*
 * Common code for dup, dup2, and fcntl(F_DUPFD).
 */
static int
do_dup(fdp, old, new, retval, p)
	register struct filedesc *fdp;
	register int old, new;
	register_t *retval;
	struct proc *p;
{
	struct file *fp;
	struct file *delfp;

	/*
	 * Save info on the descriptor being overwritten.  We have
	 * to do the unmap now, but we cannot close it without
	 * introducing an ownership race for the slot.
	 */
	delfp = fdp->fd_ofiles[new];
#if 0
	if (delfp && (fdp->fd_ofileflags[new] & UF_MAPPED))
		(void) munmapfd(p, new);
#endif

	/*
	 * Duplicate the source descriptor, update lastfile
	 */
	fp = fdp->fd_ofiles[old];
	fdp->fd_ofiles[new] = fp;
	fdp->fd_ofileflags[new] = fdp->fd_ofileflags[old] &~ UF_EXCLOSE;
	fhold(fp);
	if (new > fdp->fd_lastfile)
		fdp->fd_lastfile = new;
	*retval = new;

	/*
	 * If we dup'd over a valid file, we now own the reference to it
	 * and must dispose of it using closef() semantics (as if a
	 * close() were performed on it).
	 */
	if (delfp)
		(void) closef(delfp, p);
	return (0);
}

/*
 * If sigio is on the list associated with a process or process group,
 * disable signalling from the device, remove sigio from the list and
 * free sigio.
 */
void
funsetown(sigio)
	struct sigio *sigio;
{
	int s;

	if (sigio == NULL)
		return;
	s = splhigh();
	*(sigio->sio_myref) = NULL;
	splx(s);
	if (sigio->sio_pgid < 0) {
		SLIST_REMOVE(&sigio->sio_pgrp->pg_sigiolst, sigio,
			     sigio, sio_pgsigio);
	} else /* if ((*sigiop)->sio_pgid > 0) */ {
		SLIST_REMOVE(&sigio->sio_proc->p_sigiolst, sigio,
			     sigio, sio_pgsigio);
	}
	crfree(sigio->sio_ucred);
	FREE(sigio, M_SIGIO);
}

/* Free a list of sigio structures. */
void
funsetownlst(sigiolst)
	struct sigiolst *sigiolst;
{
	struct sigio *sigio;

	while ((sigio = SLIST_FIRST(sigiolst)) != NULL)
		funsetown(sigio);
}

/*
 * This is common code for FIOSETOWN ioctl called by fcntl(fd, F_SETOWN, arg).
 *
 * After permission checking, add a sigio structure to the sigio list for
 * the process or process group.
 */
int
fsetown(pgid, sigiop)
	pid_t pgid;
	struct sigio **sigiop;
{
	struct proc *proc;
	struct pgrp *pgrp;
	struct sigio *sigio;
	int s;

	if (pgid == 0) {
		funsetown(*sigiop);
		return (0);
	}
	if (pgid > 0) {
		proc = pfind(pgid);
		if (proc == NULL)
			return (ESRCH);

		/*
		 * Policy - Don't allow a process to FSETOWN a process
		 * in another session.
		 *
		 * Remove this test to allow maximum flexibility or
		 * restrict FSETOWN to the current process or process
		 * group for maximum safety.
		 */
		if (proc->p_session != curproc->p_session)
			return (EPERM);

		pgrp = NULL;
	} else /* if (pgid < 0) */ {
		pgrp = pgfind(-pgid);
		if (pgrp == NULL)
			return (ESRCH);

		/*
		 * Policy - Don't allow a process to FSETOWN a process
		 * in another session.
		 *
		 * Remove this test to allow maximum flexibility or
		 * restrict FSETOWN to the current process or process
		 * group for maximum safety.
		 */
		if (pgrp->pg_session != curproc->p_session)
			return (EPERM);

		proc = NULL;
	}
	funsetown(*sigiop);
	MALLOC(sigio, struct sigio *, sizeof(struct sigio), M_SIGIO, M_WAITOK);
	if (pgid > 0) {
		SLIST_INSERT_HEAD(&proc->p_sigiolst, sigio, sio_pgsigio);
		sigio->sio_proc = proc;
	} else {
		SLIST_INSERT_HEAD(&pgrp->pg_sigiolst, sigio, sio_pgsigio);
		sigio->sio_pgrp = pgrp;
	}
	sigio->sio_pgid = pgid;
	crhold(curproc->p_ucred);
	sigio->sio_ucred = curproc->p_ucred;
	/* It would be convenient if p_ruid was in ucred. */
	sigio->sio_ruid = curproc->p_cred->p_ruid;
	sigio->sio_myref = sigiop;
	s = splhigh();
	*sigiop = sigio;
	splx(s);
	return (0);
}

/*
 * This is common code for FIOGETOWN ioctl called by fcntl(fd, F_GETOWN, arg).
 */
pid_t
fgetown(sigio)
	struct sigio *sigio;
{
	return (sigio != NULL ? sigio->sio_pgid : 0);
}

/*
 * Close a file descriptor.
 */
#ifndef _SYS_SYSPROTO_H_
struct close_args {
        int     fd;
};
#endif
/* ARGSUSED */
int
close(p, uap)
	struct proc *p;
	struct close_args *uap;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file *fp;
	register int fd = uap->fd;

	if ((unsigned)fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[fd]) == NULL)
		return (EBADF);
#if 0
	if (fdp->fd_ofileflags[fd] & UF_MAPPED)
		(void) munmapfd(p, fd);
#endif
	fdp->fd_ofiles[fd] = NULL;
	fdp->fd_ofileflags[fd] = 0;

	/*
	 * we now hold the fp reference that used to be owned by the descriptor
	 * array.
	 */
	while (fdp->fd_lastfile > 0 && fdp->fd_ofiles[fdp->fd_lastfile] == NULL)
		fdp->fd_lastfile--;
	if (fd < fdp->fd_freefile)
		fdp->fd_freefile = fd;
	if (fd < fdp->fd_knlistsize)
		knote_fdclose(p, fd);
	return (closef(fp, p));
}

#if defined(COMPAT_43) || defined(COMPAT_SUNOS)
/*
 * Return status information about a file descriptor.
 */
#ifndef _SYS_SYSPROTO_H_
struct ofstat_args {
	int	fd;
	struct	ostat *sb;
};
#endif
/* ARGSUSED */
int
ofstat(p, uap)
	struct proc *p;
	register struct ofstat_args *uap;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file *fp;
	struct stat ub;
	struct ostat oub;
	int error;

	if ((unsigned)uap->fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[uap->fd]) == NULL)
		return (EBADF);
	fhold(fp);
	error = fo_stat(fp, &ub, p);
	if (error == 0) {
		cvtstat(&ub, &oub);
		error = copyout((caddr_t)&oub, (caddr_t)uap->sb, sizeof (oub));
	}
	fdrop(fp, p);
	return (error);
}
#endif /* COMPAT_43 || COMPAT_SUNOS */

/*
 * Return status information about a file descriptor.
 */
#ifndef _SYS_SYSPROTO_H_
struct fstat_args {
	int	fd;
	struct	stat *sb;
};
#endif
/* ARGSUSED */
int
fstat(p, uap)
	struct proc *p;
	register struct fstat_args *uap;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file *fp;
	struct stat ub;
	int error;

	if ((unsigned)uap->fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[uap->fd]) == NULL)
		return (EBADF);
	fhold(fp);
	error = fo_stat(fp, &ub, p);
	if (error == 0)
		error = copyout((caddr_t)&ub, (caddr_t)uap->sb, sizeof (ub));
	fdrop(fp, p);
	return (error);
}

/*
 * Return status information about a file descriptor.
 */
#ifndef _SYS_SYSPROTO_H_
struct nfstat_args {
	int	fd;
	struct	nstat *sb;
};
#endif
/* ARGSUSED */
int
nfstat(p, uap)
	struct proc *p;
	register struct nfstat_args *uap;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file *fp;
	struct stat ub;
	struct nstat nub;
	int error;

	if ((unsigned)uap->fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[uap->fd]) == NULL)
		return (EBADF);
	fhold(fp);
	error = fo_stat(fp, &ub, p);
	if (error == 0) {
		cvtnstat(&ub, &nub);
		error = copyout((caddr_t)&nub, (caddr_t)uap->sb, sizeof (nub));
	}
	fdrop(fp, p);
	return (error);
}

/*
 * Return pathconf information about a file descriptor.
 */
#ifndef _SYS_SYSPROTO_H_
struct fpathconf_args {
	int	fd;
	int	name;
};
#endif
/* ARGSUSED */
int
fpathconf(p, uap)
	struct proc *p;
	register struct fpathconf_args *uap;
{
	struct filedesc *fdp = p->p_fd;
	struct file *fp;
	struct vnode *vp;
	int error = 0;

	if ((unsigned)uap->fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[uap->fd]) == NULL)
		return (EBADF);

	fhold(fp);

	switch (fp->f_type) {
	case DTYPE_PIPE:
	case DTYPE_SOCKET:
		if (uap->name != _PC_PIPE_BUF) {
			error = EINVAL;
		} else {
			p->p_retval[0] = PIPE_BUF;
			error = 0;
		}
		break;
	case DTYPE_FIFO:
	case DTYPE_VNODE:
		vp = (struct vnode *)fp->f_data;
		error = VOP_PATHCONF(vp, uap->name, p->p_retval);
		break;
	default:
		error = EOPNOTSUPP;
		break;
	}
	fdrop(fp, p);
	return(error);
}

/*
 * Allocate a file descriptor for the process.
 */
static int fdexpand;
SYSCTL_INT(_debug, OID_AUTO, fdexpand, CTLFLAG_RD, &fdexpand, 0, "");

int
fdalloc(p, want, result)
	struct proc *p;
	int want;
	int *result;
{
	register struct filedesc *fdp = p->p_fd;
	register int i;
	int lim, last, nfiles;
	struct file **newofile;
	char *newofileflags;

	/*
	 * Search for a free descriptor starting at the higher
	 * of want or fd_freefile.  If that fails, consider
	 * expanding the ofile array.
	 */
	lim = min((int)p->p_rlimit[RLIMIT_NOFILE].rlim_cur, maxfilesperproc);
	for (;;) {
		last = min(fdp->fd_nfiles, lim);
		if ((i = want) < fdp->fd_freefile)
			i = fdp->fd_freefile;
		for (; i < last; i++) {
			if (fdp->fd_ofiles[i] == NULL) {
				fdp->fd_ofileflags[i] = 0;
				if (i > fdp->fd_lastfile)
					fdp->fd_lastfile = i;
				if (want <= fdp->fd_freefile)
					fdp->fd_freefile = i;
				*result = i;
				return (0);
			}
		}

		/*
		 * No space in current array.  Expand?
		 */
		if (fdp->fd_nfiles >= lim)
			return (EMFILE);
		if (fdp->fd_nfiles < NDEXTENT)
			nfiles = NDEXTENT;
		else
			nfiles = 2 * fdp->fd_nfiles;
		MALLOC(newofile, struct file **, nfiles * OFILESIZE,
		    M_FILEDESC, M_WAITOK);

		/*
		 * deal with file-table extend race that might have occured
		 * when malloc was blocked.
		 */
		if (fdp->fd_nfiles >= nfiles) {
			FREE(newofile, M_FILEDESC);
			continue;
		}
		newofileflags = (char *) &newofile[nfiles];
		/*
		 * Copy the existing ofile and ofileflags arrays
		 * and zero the new portion of each array.
		 */
		bcopy(fdp->fd_ofiles, newofile,
			(i = sizeof(struct file *) * fdp->fd_nfiles));
		bzero((char *)newofile + i, nfiles * sizeof(struct file *) - i);
		bcopy(fdp->fd_ofileflags, newofileflags,
			(i = sizeof(char) * fdp->fd_nfiles));
		bzero(newofileflags + i, nfiles * sizeof(char) - i);
		if (fdp->fd_nfiles > NDFILE)
			FREE(fdp->fd_ofiles, M_FILEDESC);
		fdp->fd_ofiles = newofile;
		fdp->fd_ofileflags = newofileflags;
		fdp->fd_nfiles = nfiles;
		fdexpand++;
	}
	return (0);
}

/*
 * Check to see whether n user file descriptors
 * are available to the process p.
 */
int
fdavail(p, n)
	struct proc *p;
	register int n;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file **fpp;
	register int i, lim, last;

	lim = min((int)p->p_rlimit[RLIMIT_NOFILE].rlim_cur, maxfilesperproc);
	if ((i = lim - fdp->fd_nfiles) > 0 && (n -= i) <= 0)
		return (1);

	last = min(fdp->fd_nfiles, lim);
	fpp = &fdp->fd_ofiles[fdp->fd_freefile];
	for (i = last - fdp->fd_freefile; --i >= 0; fpp++) {
		if (*fpp == NULL && --n <= 0)
			return (1);
	}
	return (0);
}

/*
 * Create a new open file structure and allocate
 * a file decriptor for the process that refers to it.
 */
int
falloc(p, resultfp, resultfd)
	register struct proc *p;
	struct file **resultfp;
	int *resultfd;
{
	register struct file *fp, *fq;
	int error, i;

	if (nfiles >= maxfiles) {
		tablefull("file");
		return (ENFILE);
	}
	/*
	 * Allocate a new file descriptor.
	 * If the process has file descriptor zero open, add to the list
	 * of open files at that point, otherwise put it at the front of
	 * the list of open files.
	 */
	nfiles++;
	MALLOC(fp, struct file *, sizeof(struct file), M_FILE, M_WAITOK);
	bzero(fp, sizeof(struct file));

	/*
	 * wait until after malloc (which may have blocked) returns before
	 * allocating the slot, else a race might have shrunk it if we had
	 * allocated it before the malloc.
	 */
	if ((error = fdalloc(p, 0, &i))) {
		nfiles--;
		FREE(fp, M_FILE);
		return (error);
	}
	fp->f_count = 1;
	fp->f_cred = p->p_ucred;
	fp->f_ops = &badfileops;
	fp->f_seqcount = 1;
	crhold(fp->f_cred);
	if ((fq = p->p_fd->fd_ofiles[0])) {
		LIST_INSERT_AFTER(fq, fp, f_list);
	} else {
		LIST_INSERT_HEAD(&filehead, fp, f_list);
	}
	p->p_fd->fd_ofiles[i] = fp;
	if (resultfp)
		*resultfp = fp;
	if (resultfd)
		*resultfd = i;
	return (0);
}

/*
 * Free a file descriptor.
 */
void
ffree(fp)
	register struct file *fp;
{
	KASSERT((fp->f_count == 0), ("ffree: fp_fcount not 0!"));
	LIST_REMOVE(fp, f_list);
	crfree(fp->f_cred);
	nfiles--;
	FREE(fp, M_FILE);
}

/*
 * Build a new filedesc structure.
 */
struct filedesc *
fdinit(p)
	struct proc *p;
{
	register struct filedesc0 *newfdp;
	register struct filedesc *fdp = p->p_fd;

	MALLOC(newfdp, struct filedesc0 *, sizeof(struct filedesc0),
	    M_FILEDESC, M_WAITOK);
	bzero(newfdp, sizeof(struct filedesc0));
	newfdp->fd_fd.fd_cdir = fdp->fd_cdir;
	if (newfdp->fd_fd.fd_cdir)
		VREF(newfdp->fd_fd.fd_cdir);
	newfdp->fd_fd.fd_rdir = fdp->fd_rdir;
	if (newfdp->fd_fd.fd_rdir)
		VREF(newfdp->fd_fd.fd_rdir);
	newfdp->fd_fd.fd_jdir = fdp->fd_jdir;
	if (newfdp->fd_fd.fd_jdir)
		VREF(newfdp->fd_fd.fd_jdir);

	/* Create the file descriptor table. */
	newfdp->fd_fd.fd_refcnt = 1;
	newfdp->fd_fd.fd_cmask = cmask;
	newfdp->fd_fd.fd_ofiles = newfdp->fd_dfiles;
	newfdp->fd_fd.fd_ofileflags = newfdp->fd_dfileflags;
	newfdp->fd_fd.fd_nfiles = NDFILE;
	newfdp->fd_fd.fd_knlistsize = -1;

	return (&newfdp->fd_fd);
}

/*
 * Share a filedesc structure.
 */
struct filedesc *
fdshare(p)
	struct proc *p;
{
	p->p_fd->fd_refcnt++;
	return (p->p_fd);
}

/*
 * Copy a filedesc structure.
 */
struct filedesc *
fdcopy(p)
	struct proc *p;
{
	register struct filedesc *newfdp, *fdp = p->p_fd;
	register struct file **fpp;
	register int i;

	/* Certain daemons might not have file descriptors. */
	if (fdp == NULL)
		return (NULL);

	MALLOC(newfdp, struct filedesc *, sizeof(struct filedesc0),
	    M_FILEDESC, M_WAITOK);
	bcopy(fdp, newfdp, sizeof(struct filedesc));
	if (newfdp->fd_cdir)
		VREF(newfdp->fd_cdir);
	if (newfdp->fd_rdir)
		VREF(newfdp->fd_rdir);
	if (newfdp->fd_jdir)
		VREF(newfdp->fd_jdir);
	newfdp->fd_refcnt = 1;

	/*
	 * If the number of open files fits in the internal arrays
	 * of the open file structure, use them, otherwise allocate
	 * additional memory for the number of descriptors currently
	 * in use.
	 */
	if (newfdp->fd_lastfile < NDFILE) {
		newfdp->fd_ofiles = ((struct filedesc0 *) newfdp)->fd_dfiles;
		newfdp->fd_ofileflags =
		    ((struct filedesc0 *) newfdp)->fd_dfileflags;
		i = NDFILE;
	} else {
		/*
		 * Compute the smallest multiple of NDEXTENT needed
		 * for the file descriptors currently in use,
		 * allowing the table to shrink.
		 */
		i = newfdp->fd_nfiles;
		while (i > 2 * NDEXTENT && i > newfdp->fd_lastfile * 2)
			i /= 2;
		MALLOC(newfdp->fd_ofiles, struct file **, i * OFILESIZE,
		    M_FILEDESC, M_WAITOK);
		newfdp->fd_ofileflags = (char *) &newfdp->fd_ofiles[i];
	}
	newfdp->fd_nfiles = i;
	bcopy(fdp->fd_ofiles, newfdp->fd_ofiles, i * sizeof(struct file **));
	bcopy(fdp->fd_ofileflags, newfdp->fd_ofileflags, i * sizeof(char));

	/*
	 * kq descriptors cannot be copied.
	 */
	if (newfdp->fd_knlistsize != -1) {
		fpp = &newfdp->fd_ofiles[newfdp->fd_lastfile];
		for (i = newfdp->fd_lastfile; i >= 0; i--, fpp--) {
			if (*fpp != NULL && (*fpp)->f_type == DTYPE_KQUEUE) {
				*fpp = NULL;
				if (i < newfdp->fd_freefile)
					newfdp->fd_freefile = i;
			}
			if (*fpp == NULL && i == newfdp->fd_lastfile && i > 0)
				newfdp->fd_lastfile--;
		}
		newfdp->fd_knlist = NULL;
		newfdp->fd_knlistsize = -1;
		newfdp->fd_knhash = NULL;
		newfdp->fd_knhashmask = 0;
	}

	fpp = newfdp->fd_ofiles;
	for (i = newfdp->fd_lastfile; i-- >= 0; fpp++) {
		if (*fpp != NULL)
			fhold(*fpp);
	}
	return (newfdp);
}

/*
 * Release a filedesc structure.
 */
void
fdfree(p)
	struct proc *p;
{
	register struct filedesc *fdp = p->p_fd;
	struct file **fpp;
	register int i;

	/* Certain daemons might not have file descriptors. */
	if (fdp == NULL)
		return;

	if (--fdp->fd_refcnt > 0)
		return;
	/*
	 * we are the last reference to the structure, we can
	 * safely assume it will not change out from under us.
	 */
	fpp = fdp->fd_ofiles;
	for (i = fdp->fd_lastfile; i-- >= 0; fpp++) {
		if (*fpp)
			(void) closef(*fpp, p);
	}
	if (fdp->fd_nfiles > NDFILE)
		FREE(fdp->fd_ofiles, M_FILEDESC);
	if (fdp->fd_cdir)
		vrele(fdp->fd_cdir);
	if (fdp->fd_rdir)
		vrele(fdp->fd_rdir);
	if (fdp->fd_jdir)
		vrele(fdp->fd_jdir);
	if (fdp->fd_knlist)
		FREE(fdp->fd_knlist, M_KQUEUE);
	if (fdp->fd_knhash)
		FREE(fdp->fd_knhash, M_KQUEUE);
	FREE(fdp, M_FILEDESC);
}

/*
 * For setugid programs, we don't want to people to use that setugidness
 * to generate error messages which write to a file which otherwise would
 * otherwise be off-limits to the process.
 *
 * This is a gross hack to plug the hole.  A better solution would involve
 * a special vop or other form of generalized access control mechanism.  We
 * go ahead and just reject all procfs file systems accesses as dangerous.
 *
 * Since setugidsafety calls this only for fd 0, 1 and 2, this check is
 * sufficient.  We also don't for check setugidness since we know we are.
 */
static int
is_unsafe(struct file *fp)
{
	if (fp->f_type == DTYPE_VNODE && 
	    ((struct vnode *)(fp->f_data))->v_tag == VT_PROCFS)
		return (1);
	return (0);
}

/*
 * Make this setguid thing safe, if at all possible.
 */
void
setugidsafety(p)
	struct proc *p;
{
	struct filedesc *fdp = p->p_fd;
	register int i;

	/* Certain daemons might not have file descriptors. */
	if (fdp == NULL)
		return;

	/*
	 * note: fdp->fd_ofiles may be reallocated out from under us while
	 * we are blocked in a close.  Be careful!
	 */
	for (i = 0; i <= fdp->fd_lastfile; i++) {
		if (i > 2)
			break;
		if (fdp->fd_ofiles[i] && is_unsafe(fdp->fd_ofiles[i])) {
			struct file *fp;

#if 0
			if ((fdp->fd_ofileflags[i] & UF_MAPPED) != 0)
				(void) munmapfd(p, i);
#endif
			if (i < fdp->fd_knlistsize)
				knote_fdclose(p, i);
			/*
			 * NULL-out descriptor prior to close to avoid
			 * a race while close blocks.
			 */
			fp = fdp->fd_ofiles[i];
			fdp->fd_ofiles[i] = NULL;
			fdp->fd_ofileflags[i] = 0;
			if (i < fdp->fd_freefile)
				fdp->fd_freefile = i;
			(void) closef(fp, p);
		}
	}
	while (fdp->fd_lastfile > 0 && fdp->fd_ofiles[fdp->fd_lastfile] == NULL)
		fdp->fd_lastfile--;
}

/*
 * Close any files on exec?
 */
void
fdcloseexec(p)
	struct proc *p;
{
	struct filedesc *fdp = p->p_fd;
	register int i;

	/* Certain daemons might not have file descriptors. */
	if (fdp == NULL)
		return;

	/*
	 * We cannot cache fd_ofiles or fd_ofileflags since operations
	 * may block and rip them out from under us.
	 */
	for (i = 0; i <= fdp->fd_lastfile; i++) {
		if (fdp->fd_ofiles[i] != NULL &&
		    (fdp->fd_ofileflags[i] & UF_EXCLOSE)) {
			struct file *fp;

#if 0
			if (fdp->fd_ofileflags[i] & UF_MAPPED)
				(void) munmapfd(p, i);
#endif
			if (i < fdp->fd_knlistsize)
				knote_fdclose(p, i);
			/*
			 * NULL-out descriptor prior to close to avoid
			 * a race while close blocks.
			 */
			fp = fdp->fd_ofiles[i];
			fdp->fd_ofiles[i] = NULL;
			fdp->fd_ofileflags[i] = 0;
			if (i < fdp->fd_freefile)
				fdp->fd_freefile = i;
			(void) closef(fp, p);
		}
	}
	while (fdp->fd_lastfile > 0 && fdp->fd_ofiles[fdp->fd_lastfile] == NULL)
		fdp->fd_lastfile--;
}

/*
 * It is unsafe for set[ug]id processes to be started with file
 * descriptors 0..2 closed, as these descriptors are given implicit
 * significance in the Standard C library.  fdcheckstd() will create a
 * descriptor referencing /dev/null for each of stdin, stdout, and
 * stderr that is not already open.
 */
int
fdcheckstd(p)
       struct proc *p;
{
       struct nameidata nd;
       struct filedesc *fdp;
       struct file *fp;
       register_t retval;
       int fd, i, error, flags, devnull;

       fdp = p->p_fd;
       if (fdp == NULL)
               return (0);
       devnull = -1;
       error = 0;
       for (i = 0; i < 3; i++) {
               if (fdp->fd_ofiles[i] != NULL)
                       continue;
               if (devnull < 0) {
                       error = falloc(p, &fp, &fd);
                       if (error != 0)
                               break;
                       NDINIT(&nd, LOOKUP, FOLLOW, UIO_SYSSPACE, "/dev/null",
                           p);
                       flags = FREAD | FWRITE;
                       error = vn_open(&nd, flags, 0);
                       if (error != 0) {
                               fdp->fd_ofiles[i] = NULL;
                               fdrop(fp, p);
                               break;
                       }
                       NDFREE(&nd, NDF_ONLY_PNBUF);
                       fp->f_data = (caddr_t)nd.ni_vp;
                       fp->f_flag = flags;
                       fp->f_ops = &vnops;
                       fp->f_type = DTYPE_VNODE;
                       VOP_UNLOCK(nd.ni_vp, 0, p);
                       devnull = fd;
               } else {
                       error = fdalloc(p, 0, &fd);
                       if (error != 0)
                               break;
                       error = do_dup(fdp, devnull, fd, &retval, p);
                       if (error != 0)
                               break;
               }
       }
       return (error);
}

/*
 * Internal form of close.
 * Decrement reference count on file structure.
 * Note: p may be NULL when closing a file
 * that was being passed in a message.
 */
int
closef(fp, p)
	register struct file *fp;
	register struct proc *p;
{
	struct vnode *vp;
	struct flock lf;

	if (fp == NULL)
		return (0);
	/*
	 * POSIX record locking dictates that any close releases ALL
	 * locks owned by this process.  This is handled by setting
	 * a flag in the unlock to free ONLY locks obeying POSIX
	 * semantics, and not to free BSD-style file locks.
	 * If the descriptor was in a message, POSIX-style locks
	 * aren't passed with the descriptor.
	 */
	if (p && (p->p_flag & P_ADVLOCK) && fp->f_type == DTYPE_VNODE) {
		lf.l_whence = SEEK_SET;
		lf.l_start = 0;
		lf.l_len = 0;
		lf.l_type = F_UNLCK;
		vp = (struct vnode *)fp->f_data;
		(void) VOP_ADVLOCK(vp, (caddr_t)p->p_leader, F_UNLCK, &lf, F_POSIX);
	}
	return (fdrop(fp, p));
}

int
fdrop(fp, p)
	struct file *fp;
	struct proc *p;
{
	struct flock lf;
	struct vnode *vp;
	int error;

	if (--fp->f_count > 0)
		return (0);
	if (fp->f_count < 0)
		panic("fdrop: count < 0");
	if ((fp->f_flag & FHASLOCK) && fp->f_type == DTYPE_VNODE) {
		lf.l_whence = SEEK_SET;
		lf.l_start = 0;
		lf.l_len = 0;
		lf.l_type = F_UNLCK;
		vp = (struct vnode *)fp->f_data;
		(void) VOP_ADVLOCK(vp, (caddr_t)fp, F_UNLCK, &lf, F_FLOCK);
	}
	if (fp->f_ops != &badfileops)
		error = fo_close(fp, p);
	else
		error = 0;
	ffree(fp);
	return (error);
}

/*
 * Apply an advisory lock on a file descriptor.
 *
 * Just attempt to get a record lock of the requested type on
 * the entire file (l_whence = SEEK_SET, l_start = 0, l_len = 0).
 */
#ifndef _SYS_SYSPROTO_H_
struct flock_args {
	int	fd;
	int	how;
};
#endif
/* ARGSUSED */
int
flock(p, uap)
	struct proc *p;
	register struct flock_args *uap;
{
	register struct filedesc *fdp = p->p_fd;
	register struct file *fp;
	struct vnode *vp;
	struct flock lf;

	if ((unsigned)uap->fd >= fdp->fd_nfiles ||
	    (fp = fdp->fd_ofiles[uap->fd]) == NULL)
		return (EBADF);
	if (fp->f_type != DTYPE_VNODE)
		return (EOPNOTSUPP);
	vp = (struct vnode *)fp->f_data;
	lf.l_whence = SEEK_SET;
	lf.l_start = 0;
	lf.l_len = 0;
	if (uap->how & LOCK_UN) {
		lf.l_type = F_UNLCK;
		fp->f_flag &= ~FHASLOCK;
		return (VOP_ADVLOCK(vp, (caddr_t)fp, F_UNLCK, &lf, F_FLOCK));
	}
	if (uap->how & LOCK_EX)
		lf.l_type = F_WRLCK;
	else if (uap->how & LOCK_SH)
		lf.l_type = F_RDLCK;
	else
		return (EBADF);
	fp->f_flag |= FHASLOCK;
	if (uap->how & LOCK_NB)
		return (VOP_ADVLOCK(vp, (caddr_t)fp, F_SETLK, &lf, F_FLOCK));
	return (VOP_ADVLOCK(vp, (caddr_t)fp, F_SETLK, &lf, F_FLOCK|F_WAIT));
}

/*
 * File Descriptor pseudo-device driver (/dev/fd/).
 *
 * Opening minor device N dup()s the file (if any) connected to file
 * descriptor N belonging to the calling process.  Note that this driver
 * consists of only the ``open()'' routine, because all subsequent
 * references to this file will be direct to the other driver.
 */
/* ARGSUSED */
static int
fdopen(dev, mode, type, p)
	dev_t dev;
	int mode, type;
	struct proc *p;
{

	/*
	 * XXX Kludge: set curproc->p_dupfd to contain the value of the
	 * the file descriptor being sought for duplication. The error
	 * return ensures that the vnode for this device will be released
	 * by vn_open. Open will detect this special error and take the
	 * actions in dupfdopen below. Other callers of vn_open or VOP_OPEN
	 * will simply report the error.
	 */
	p->p_dupfd = minor(dev);
	return (ENODEV);
}

/*
 * Duplicate the specified descriptor to a free descriptor.
 */
int
dupfdopen(p, fdp, indx, dfd, mode, error)
	struct proc *p;
	struct filedesc *fdp;
	int indx, dfd;
	int mode;
	int error;
{
	register struct file *wfp;
	struct file *fp;

	/*
	 * If the to-be-dup'd fd number is greater than the allowed number
	 * of file descriptors, or the fd to be dup'd has already been
	 * closed, then reject.
	 */
	if ((u_int)dfd >= fdp->fd_nfiles ||
	    (wfp = fdp->fd_ofiles[dfd]) == NULL) {
		return (EBADF);
	}

	/*
	 * There are two cases of interest here.
	 *
	 * For ENODEV simply dup (dfd) to file descriptor
	 * (indx) and return.
	 *
	 * For ENXIO steal away the file structure from (dfd) and
	 * store it in (indx).  (dfd) is effectively closed by
	 * this operation.
	 *
	 * Any other error code is just returned.
	 */
	switch (error) {
	case ENODEV:
		/*
		 * Check that the mode the file is being opened for is a
		 * subset of the mode of the existing descriptor.
		 */
		if (((mode & (FREAD|FWRITE)) | wfp->f_flag) != wfp->f_flag)
			return (EACCES);
		fp = fdp->fd_ofiles[indx];
#if 0
		if (fp && fdp->fd_ofileflags[indx] & UF_MAPPED)
			(void) munmapfd(p, indx);
#endif
		fdp->fd_ofiles[indx] = wfp;
		fdp->fd_ofileflags[indx] = fdp->fd_ofileflags[dfd];
		fhold(wfp);
		if (indx > fdp->fd_lastfile)
			fdp->fd_lastfile = indx;
		/*
		 * we now own the reference to fp that the ofiles[] array
		 * used to own.  Release it.
		 */
		if (fp)
			fdrop(fp, p);
		return (0);

	case ENXIO:
		/*
		 * Steal away the file pointer from dfd, and stuff it into indx.
		 */
		fp = fdp->fd_ofiles[indx];
#if 0
		if (fp && fdp->fd_ofileflags[indx] & UF_MAPPED)
			(void) munmapfd(p, indx);
#endif
		fdp->fd_ofiles[indx] = fdp->fd_ofiles[dfd];
		fdp->fd_ofiles[dfd] = NULL;
		fdp->fd_ofileflags[indx] = fdp->fd_ofileflags[dfd];
		fdp->fd_ofileflags[dfd] = 0;

		/*
		 * we now own the reference to fp that the ofiles[] array
		 * used to own.  Release it.
		 */
		if (fp)
			fdrop(fp, p);
		/*
		 * Complete the clean up of the filedesc structure by
		 * recomputing the various hints.
		 */
		if (indx > fdp->fd_lastfile) {
			fdp->fd_lastfile = indx;
		} else {
			while (fdp->fd_lastfile > 0 &&
			   fdp->fd_ofiles[fdp->fd_lastfile] == NULL) {
				fdp->fd_lastfile--;
			}
			if (dfd < fdp->fd_freefile)
				fdp->fd_freefile = dfd;
		}
		return (0);

	default:
		return (error);
	}
	/* NOTREACHED */
}

/*
 * Get file structures.
 */
static int
sysctl_kern_file(SYSCTL_HANDLER_ARGS)
{
	int error;
	struct file *fp;

	if (!req->oldptr) {
		/*
		 * overestimate by 10 files
		 */
		return (SYSCTL_OUT(req, 0, sizeof(filehead) + 
				(nfiles + 10) * sizeof(struct file)));
	}

	error = SYSCTL_OUT(req, (caddr_t)&filehead, sizeof(filehead));
	if (error)
		return (error);

	/*
	 * followed by an array of file structures
	 */
	LIST_FOREACH(fp, &filehead, f_list) {
		error = SYSCTL_OUT(req, (caddr_t)fp, sizeof (struct file));
		if (error)
			return (error);
	}
	return (0);
}

SYSCTL_PROC(_kern, KERN_FILE, file, CTLTYPE_OPAQUE|CTLFLAG_RD,
    0, 0, sysctl_kern_file, "S,file", "Entire file table");

SYSCTL_INT(_kern, KERN_MAXFILESPERPROC, maxfilesperproc, CTLFLAG_RW, 
    &maxfilesperproc, 0, "Maximum files allowed open per process");

SYSCTL_INT(_kern, KERN_MAXFILES, maxfiles, CTLFLAG_RW, 
    &maxfiles, 0, "Maximum number of files");

SYSCTL_INT(_kern, OID_AUTO, openfiles, CTLFLAG_RD, 
	&nfiles, 0, "System-wide number of open files");

static void
fildesc_drvinit(void *unused)
{
	int fd;

	for (fd = 0; fd < NUMFDESC; fd++)
		make_dev(&fildesc_cdevsw, fd,
		    UID_BIN, GID_BIN, 0666, "fd/%d", fd);
	make_dev(&fildesc_cdevsw, 0, UID_ROOT, GID_WHEEL, 0666, "stdin");
	make_dev(&fildesc_cdevsw, 1, UID_ROOT, GID_WHEEL, 0666, "stdout");
	make_dev(&fildesc_cdevsw, 2, UID_ROOT, GID_WHEEL, 0666, "stderr");
}

struct fileops badfileops = {
	badfo_readwrite,
	badfo_readwrite,
	badfo_ioctl,
	badfo_poll,
	badfo_kqfilter,
	badfo_stat,
	badfo_close
};

static int
badfo_readwrite(fp, uio, cred, flags, p)
	struct file *fp;
	struct uio *uio;
	struct ucred *cred;
	struct proc *p;
	int flags;
{

	return (EBADF);
}

static int
badfo_ioctl(fp, com, data, p)
	struct file *fp;
	u_long com;
	caddr_t data;
	struct proc *p;
{

	return (EBADF);
}

static int
badfo_poll(fp, events, cred, p)
	struct file *fp;
	int events;
	struct ucred *cred;
	struct proc *p;
{

	return (0);
}

static int
badfo_kqfilter(fp, kn)
	struct file *fp;
	struct knote *kn;
{

	return (0);
}

static int
badfo_stat(fp, sb, p)
	struct file *fp;
	struct stat *sb;
	struct proc *p;
{

	return (EBADF);
}

static int
badfo_close(fp, p)
	struct file *fp;
	struct proc *p;
{

	return (EBADF);
}

SYSINIT(fildescdev,SI_SUB_DRIVERS,SI_ORDER_MIDDLE+CDEV_MAJOR,
					fildesc_drvinit,NULL)