aboutsummaryrefslogtreecommitdiff
path: root/sys/kern/sys_generic.c
blob: 0573d542af39f4210c489024e6132191bbc2070f (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
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
/*-
 * SPDX-License-Identifier: BSD-3-Clause
 *
 * Copyright (c) 1982, 1986, 1989, 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. 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.
 *
 *	@(#)sys_generic.c	8.5 (Berkeley) 1/21/94
 */

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

#include "opt_capsicum.h"
#include "opt_ktrace.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/sysproto.h>
#include <sys/capsicum.h>
#include <sys/filedesc.h>
#include <sys/filio.h>
#include <sys/fcntl.h>
#include <sys/file.h>
#include <sys/lock.h>
#include <sys/proc.h>
#include <sys/signalvar.h>
#include <sys/socketvar.h>
#include <sys/uio.h>
#include <sys/kernel.h>
#include <sys/ktr.h>
#include <sys/limits.h>
#include <sys/malloc.h>
#include <sys/poll.h>
#include <sys/resourcevar.h>
#include <sys/selinfo.h>
#include <sys/sleepqueue.h>
#include <sys/syscallsubr.h>
#include <sys/sysctl.h>
#include <sys/sysent.h>
#include <sys/vnode.h>
#include <sys/bio.h>
#include <sys/buf.h>
#include <sys/condvar.h>
#ifdef KTRACE
#include <sys/ktrace.h>
#endif

#include <security/audit/audit.h>

/*
 * The following macro defines how many bytes will be allocated from
 * the stack instead of memory allocated when passing the IOCTL data
 * structures from userspace and to the kernel. Some IOCTLs having
 * small data structures are used very frequently and this small
 * buffer on the stack gives a significant speedup improvement for
 * those requests. The value of this define should be greater or equal
 * to 64 bytes and should also be power of two. The data structure is
 * currently hard-aligned to a 8-byte boundary on the stack. This
 * should currently be sufficient for all supported platforms.
 */
#define	SYS_IOCTL_SMALL_SIZE	128	/* bytes */
#define	SYS_IOCTL_SMALL_ALIGN	8	/* bytes */

#ifdef __LP64__
static int iosize_max_clamp = 0;
SYSCTL_INT(_debug, OID_AUTO, iosize_max_clamp, CTLFLAG_RW,
    &iosize_max_clamp, 0, "Clamp max i/o size to INT_MAX");
static int devfs_iosize_max_clamp = 1;
SYSCTL_INT(_debug, OID_AUTO, devfs_iosize_max_clamp, CTLFLAG_RW,
    &devfs_iosize_max_clamp, 0, "Clamp max i/o size to INT_MAX for devices");
#endif

/*
 * Assert that the return value of read(2) and write(2) syscalls fits
 * into a register.  If not, an architecture will need to provide the
 * usermode wrappers to reconstruct the result.
 */
CTASSERT(sizeof(register_t) >= sizeof(size_t));

static MALLOC_DEFINE(M_IOCTLOPS, "ioctlops", "ioctl data buffer");
static MALLOC_DEFINE(M_SELECT, "select", "select() buffer");
MALLOC_DEFINE(M_IOV, "iov", "large iov's");

static int	pollout(struct thread *, struct pollfd *, struct pollfd *,
		    u_int);
static int	pollscan(struct thread *, struct pollfd *, u_int);
static int	pollrescan(struct thread *);
static int	selscan(struct thread *, fd_mask **, fd_mask **, int);
static int	selrescan(struct thread *, fd_mask **, fd_mask **);
static void	selfdalloc(struct thread *, void *);
static void	selfdfree(struct seltd *, struct selfd *);
static int	dofileread(struct thread *, int, struct file *, struct uio *,
		    off_t, int);
static int	dofilewrite(struct thread *, int, struct file *, struct uio *,
		    off_t, int);
static void	doselwakeup(struct selinfo *, int);
static void	seltdinit(struct thread *);
static int	seltdwait(struct thread *, sbintime_t, sbintime_t);
static void	seltdclear(struct thread *);

/*
 * One seltd per-thread allocated on demand as needed.
 *
 *	t - protected by st_mtx
 * 	k - Only accessed by curthread or read-only
 */
struct seltd {
	STAILQ_HEAD(, selfd)	st_selq;	/* (k) List of selfds. */
	struct selfd		*st_free1;	/* (k) free fd for read set. */
	struct selfd		*st_free2;	/* (k) free fd for write set. */
	struct mtx		st_mtx;		/* Protects struct seltd */
	struct cv		st_wait;	/* (t) Wait channel. */
	int			st_flags;	/* (t) SELTD_ flags. */
};

#define	SELTD_PENDING	0x0001			/* We have pending events. */
#define	SELTD_RESCAN	0x0002			/* Doing a rescan. */

/*
 * One selfd allocated per-thread per-file-descriptor.
 *	f - protected by sf_mtx
 */
struct selfd {
	STAILQ_ENTRY(selfd)	sf_link;	/* (k) fds owned by this td. */
	TAILQ_ENTRY(selfd)	sf_threads;	/* (f) fds on this selinfo. */
	struct selinfo		*sf_si;		/* (f) selinfo when linked. */
	struct mtx		*sf_mtx;	/* Pointer to selinfo mtx. */
	struct seltd		*sf_td;		/* (k) owning seltd. */
	void			*sf_cookie;	/* (k) fd or pollfd. */
	u_int			sf_refs;
};

static uma_zone_t selfd_zone;
static struct mtx_pool *mtxpool_select;

#ifdef __LP64__
size_t
devfs_iosize_max(void)
{

	return (devfs_iosize_max_clamp || SV_CURPROC_FLAG(SV_ILP32) ?
	    INT_MAX : SSIZE_MAX);
}

size_t
iosize_max(void)
{

	return (iosize_max_clamp || SV_CURPROC_FLAG(SV_ILP32) ?
	    INT_MAX : SSIZE_MAX);
}
#endif

#ifndef _SYS_SYSPROTO_H_
struct read_args {
	int	fd;
	void	*buf;
	size_t	nbyte;
};
#endif
int
sys_read(struct thread *td, struct read_args *uap)
{
	struct uio auio;
	struct iovec aiov;
	int error;

	if (uap->nbyte > IOSIZE_MAX)
		return (EINVAL);
	aiov.iov_base = uap->buf;
	aiov.iov_len = uap->nbyte;
	auio.uio_iov = &aiov;
	auio.uio_iovcnt = 1;
	auio.uio_resid = uap->nbyte;
	auio.uio_segflg = UIO_USERSPACE;
	error = kern_readv(td, uap->fd, &auio);
	return (error);
}

/*
 * Positioned read system call
 */
#ifndef _SYS_SYSPROTO_H_
struct pread_args {
	int	fd;
	void	*buf;
	size_t	nbyte;
	int	pad;
	off_t	offset;
};
#endif
int
sys_pread(struct thread *td, struct pread_args *uap)
{

	return (kern_pread(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}

int
kern_pread(struct thread *td, int fd, void *buf, size_t nbyte, off_t offset)
{
	struct uio auio;
	struct iovec aiov;
	int error;

	if (nbyte > IOSIZE_MAX)
		return (EINVAL);
	aiov.iov_base = buf;
	aiov.iov_len = nbyte;
	auio.uio_iov = &aiov;
	auio.uio_iovcnt = 1;
	auio.uio_resid = nbyte;
	auio.uio_segflg = UIO_USERSPACE;
	error = kern_preadv(td, fd, &auio, offset);
	return (error);
}

#if defined(COMPAT_FREEBSD6)
int
freebsd6_pread(struct thread *td, struct freebsd6_pread_args *uap)
{

	return (kern_pread(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}
#endif

/*
 * Scatter read system call.
 */
#ifndef _SYS_SYSPROTO_H_
struct readv_args {
	int	fd;
	struct	iovec *iovp;
	u_int	iovcnt;
};
#endif
int
sys_readv(struct thread *td, struct readv_args *uap)
{
	struct uio *auio;
	int error;

	error = copyinuio(uap->iovp, uap->iovcnt, &auio);
	if (error)
		return (error);
	error = kern_readv(td, uap->fd, auio);
	free(auio, M_IOV);
	return (error);
}

int
kern_readv(struct thread *td, int fd, struct uio *auio)
{
	struct file *fp;
	int error;

	error = fget_read(td, fd, &cap_read_rights, &fp);
	if (error)
		return (error);
	error = dofileread(td, fd, fp, auio, (off_t)-1, 0);
	fdrop(fp, td);
	return (error);
}

/*
 * Scatter positioned read system call.
 */
#ifndef _SYS_SYSPROTO_H_
struct preadv_args {
	int	fd;
	struct	iovec *iovp;
	u_int	iovcnt;
	off_t	offset;
};
#endif
int
sys_preadv(struct thread *td, struct preadv_args *uap)
{
	struct uio *auio;
	int error;

	error = copyinuio(uap->iovp, uap->iovcnt, &auio);
	if (error)
		return (error);
	error = kern_preadv(td, uap->fd, auio, uap->offset);
	free(auio, M_IOV);
	return (error);
}

int
kern_preadv(struct thread *td, int fd, struct uio *auio, off_t offset)
{
	struct file *fp;
	int error;

	error = fget_read(td, fd, &cap_pread_rights, &fp);
	if (error)
		return (error);
	if (!(fp->f_ops->fo_flags & DFLAG_SEEKABLE))
		error = ESPIPE;
	else if (offset < 0 &&
	    (fp->f_vnode == NULL || fp->f_vnode->v_type != VCHR))
		error = EINVAL;
	else
		error = dofileread(td, fd, fp, auio, offset, FOF_OFFSET);
	fdrop(fp, td);
	return (error);
}

/*
 * Common code for readv and preadv that reads data in
 * from a file using the passed in uio, offset, and flags.
 */
static int
dofileread(struct thread *td, int fd, struct file *fp, struct uio *auio,
    off_t offset, int flags)
{
	ssize_t cnt;
	int error;
#ifdef KTRACE
	struct uio *ktruio = NULL;
#endif

	AUDIT_ARG_FD(fd);

	/* Finish zero length reads right here */
	if (auio->uio_resid == 0) {
		td->td_retval[0] = 0;
		return (0);
	}
	auio->uio_rw = UIO_READ;
	auio->uio_offset = offset;
	auio->uio_td = td;
#ifdef KTRACE
	if (KTRPOINT(td, KTR_GENIO)) 
		ktruio = cloneuio(auio);
#endif
	cnt = auio->uio_resid;
	if ((error = fo_read(fp, auio, td->td_ucred, flags, td))) {
		if (auio->uio_resid != cnt && (error == ERESTART ||
		    error == EINTR || error == EWOULDBLOCK))
			error = 0;
	}
	cnt -= auio->uio_resid;
#ifdef KTRACE
	if (ktruio != NULL) {
		ktruio->uio_resid = cnt;
		ktrgenio(fd, UIO_READ, ktruio, error);
	}
#endif
	td->td_retval[0] = cnt;
	return (error);
}

#ifndef _SYS_SYSPROTO_H_
struct write_args {
	int	fd;
	const void *buf;
	size_t	nbyte;
};
#endif
int
sys_write(struct thread *td, struct write_args *uap)
{
	struct uio auio;
	struct iovec aiov;
	int error;

	if (uap->nbyte > IOSIZE_MAX)
		return (EINVAL);
	aiov.iov_base = (void *)(uintptr_t)uap->buf;
	aiov.iov_len = uap->nbyte;
	auio.uio_iov = &aiov;
	auio.uio_iovcnt = 1;
	auio.uio_resid = uap->nbyte;
	auio.uio_segflg = UIO_USERSPACE;
	error = kern_writev(td, uap->fd, &auio);
	return (error);
}

/*
 * Positioned write system call.
 */
#ifndef _SYS_SYSPROTO_H_
struct pwrite_args {
	int	fd;
	const void *buf;
	size_t	nbyte;
	int	pad;
	off_t	offset;
};
#endif
int
sys_pwrite(struct thread *td, struct pwrite_args *uap)
{

	return (kern_pwrite(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}

int
kern_pwrite(struct thread *td, int fd, const void *buf, size_t nbyte,
    off_t offset)
{
	struct uio auio;
	struct iovec aiov;
	int error;

	if (nbyte > IOSIZE_MAX)
		return (EINVAL);
	aiov.iov_base = (void *)(uintptr_t)buf;
	aiov.iov_len = nbyte;
	auio.uio_iov = &aiov;
	auio.uio_iovcnt = 1;
	auio.uio_resid = nbyte;
	auio.uio_segflg = UIO_USERSPACE;
	error = kern_pwritev(td, fd, &auio, offset);
	return (error);
}

#if defined(COMPAT_FREEBSD6)
int
freebsd6_pwrite(struct thread *td, struct freebsd6_pwrite_args *uap)
{

	return (kern_pwrite(td, uap->fd, uap->buf, uap->nbyte, uap->offset));
}
#endif

/*
 * Gather write system call.
 */
#ifndef _SYS_SYSPROTO_H_
struct writev_args {
	int	fd;
	struct	iovec *iovp;
	u_int	iovcnt;
};
#endif
int
sys_writev(struct thread *td, struct writev_args *uap)
{
	struct uio *auio;
	int error;

	error = copyinuio(uap->iovp, uap->iovcnt, &auio);
	if (error)
		return (error);
	error = kern_writev(td, uap->fd, auio);
	free(auio, M_IOV);
	return (error);
}

int
kern_writev(struct thread *td, int fd, struct uio *auio)
{
	struct file *fp;
	int error;

	error = fget_write(td, fd, &cap_write_rights, &fp);
	if (error)
		return (error);
	error = dofilewrite(td, fd, fp, auio, (off_t)-1, 0);
	fdrop(fp, td);
	return (error);
}

/*
 * Gather positioned write system call.
 */
#ifndef _SYS_SYSPROTO_H_
struct pwritev_args {
	int	fd;
	struct	iovec *iovp;
	u_int	iovcnt;
	off_t	offset;
};
#endif
int
sys_pwritev(struct thread *td, struct pwritev_args *uap)
{
	struct uio *auio;
	int error;

	error = copyinuio(uap->iovp, uap->iovcnt, &auio);
	if (error)
		return (error);
	error = kern_pwritev(td, uap->fd, auio, uap->offset);
	free(auio, M_IOV);
	return (error);
}

int
kern_pwritev(struct thread *td, int fd, struct uio *auio, off_t offset)
{
	struct file *fp;
	int error;

	error = fget_write(td, fd, &cap_pwrite_rights, &fp);
	if (error)
		return (error);
	if (!(fp->f_ops->fo_flags & DFLAG_SEEKABLE))
		error = ESPIPE;
	else if (offset < 0 &&
	    (fp->f_vnode == NULL || fp->f_vnode->v_type != VCHR))
		error = EINVAL;
	else
		error = dofilewrite(td, fd, fp, auio, offset, FOF_OFFSET);
	fdrop(fp, td);
	return (error);
}

/*
 * Common code for writev and pwritev that writes data to
 * a file using the passed in uio, offset, and flags.
 */
static int
dofilewrite(struct thread *td, int fd, struct file *fp, struct uio *auio,
    off_t offset, int flags)
{
	ssize_t cnt;
	int error;
#ifdef KTRACE
	struct uio *ktruio = NULL;
#endif

	AUDIT_ARG_FD(fd);
	auio->uio_rw = UIO_WRITE;
	auio->uio_td = td;
	auio->uio_offset = offset;
#ifdef KTRACE
	if (KTRPOINT(td, KTR_GENIO))
		ktruio = cloneuio(auio);
#endif
	cnt = auio->uio_resid;
	if ((error = fo_write(fp, auio, td->td_ucred, flags, td))) {
		if (auio->uio_resid != cnt && (error == ERESTART ||
		    error == EINTR || error == EWOULDBLOCK))
			error = 0;
		/* Socket layer is responsible for issuing SIGPIPE. */
		if (fp->f_type != DTYPE_SOCKET && error == EPIPE) {
			PROC_LOCK(td->td_proc);
			tdsignal(td, SIGPIPE);
			PROC_UNLOCK(td->td_proc);
		}
	}
	cnt -= auio->uio_resid;
#ifdef KTRACE
	if (ktruio != NULL) {
		ktruio->uio_resid = cnt;
		ktrgenio(fd, UIO_WRITE, ktruio, error);
	}
#endif
	td->td_retval[0] = cnt;
	return (error);
}

/*
 * Truncate a file given a file descriptor.
 *
 * Can't use fget_write() here, since must return EINVAL and not EBADF if the
 * descriptor isn't writable.
 */
int
kern_ftruncate(struct thread *td, int fd, off_t length)
{
	struct file *fp;
	int error;

	AUDIT_ARG_FD(fd);
	if (length < 0)
		return (EINVAL);
	error = fget(td, fd, &cap_ftruncate_rights, &fp);
	if (error)
		return (error);
	AUDIT_ARG_FILE(td->td_proc, fp);
	if (!(fp->f_flag & FWRITE)) {
		fdrop(fp, td);
		return (EINVAL);
	}
	error = fo_truncate(fp, length, td->td_ucred, td);
	fdrop(fp, td);
	return (error);
}

#ifndef _SYS_SYSPROTO_H_
struct ftruncate_args {
	int	fd;
	int	pad;
	off_t	length;
};
#endif
int
sys_ftruncate(struct thread *td, struct ftruncate_args *uap)
{

	return (kern_ftruncate(td, uap->fd, uap->length));
}

#if defined(COMPAT_43)
#ifndef _SYS_SYSPROTO_H_
struct oftruncate_args {
	int	fd;
	long	length;
};
#endif
int
oftruncate(struct thread *td, struct oftruncate_args *uap)
{

	return (kern_ftruncate(td, uap->fd, uap->length));
}
#endif /* COMPAT_43 */

#ifndef _SYS_SYSPROTO_H_
struct ioctl_args {
	int	fd;
	u_long	com;
	caddr_t	data;
};
#endif
/* ARGSUSED */
int
sys_ioctl(struct thread *td, struct ioctl_args *uap)
{
	u_char smalldata[SYS_IOCTL_SMALL_SIZE] __aligned(SYS_IOCTL_SMALL_ALIGN);
	uint32_t com;
	int arg, error;
	u_int size;
	caddr_t data;

#ifdef INVARIANTS
	if (uap->com > 0xffffffff) {
		printf(
		    "WARNING pid %d (%s): ioctl sign-extension ioctl %lx\n",
		    td->td_proc->p_pid, td->td_name, uap->com);
	}
#endif
	com = (uint32_t)uap->com;

	/*
	 * Interpret high order word to find amount of data to be
	 * copied to/from the user's address space.
	 */
	size = IOCPARM_LEN(com);
	if ((size > IOCPARM_MAX) ||
	    ((com & (IOC_VOID  | IOC_IN | IOC_OUT)) == 0) ||
#if defined(COMPAT_FREEBSD5) || defined(COMPAT_FREEBSD4) || defined(COMPAT_43)
	    ((com & IOC_OUT) && size == 0) ||
#else
	    ((com & (IOC_IN | IOC_OUT)) && size == 0) ||
#endif
	    ((com & IOC_VOID) && size > 0 && size != sizeof(int)))
		return (ENOTTY);

	if (size > 0) {
		if (com & IOC_VOID) {
			/* Integer argument. */
			arg = (intptr_t)uap->data;
			data = (void *)&arg;
			size = 0;
		} else {
			if (size > SYS_IOCTL_SMALL_SIZE)
				data = malloc((u_long)size, M_IOCTLOPS, M_WAITOK);
			else
				data = smalldata;
		}
	} else
		data = (void *)&uap->data;
	if (com & IOC_IN) {
		error = copyin(uap->data, data, (u_int)size);
		if (error != 0)
			goto out;
	} else if (com & IOC_OUT) {
		/*
		 * Zero the buffer so the user always
		 * gets back something deterministic.
		 */
		bzero(data, size);
	}

	error = kern_ioctl(td, uap->fd, com, data);

	if (error == 0 && (com & IOC_OUT))
		error = copyout(data, uap->data, (u_int)size);

out:
	if (size > SYS_IOCTL_SMALL_SIZE)
		free(data, M_IOCTLOPS);
	return (error);
}

int
kern_ioctl(struct thread *td, int fd, u_long com, caddr_t data)
{
	struct file *fp;
	struct filedesc *fdp;
	int error, tmp, locked;

	AUDIT_ARG_FD(fd);
	AUDIT_ARG_CMD(com);

	fdp = td->td_proc->p_fd;

	switch (com) {
	case FIONCLEX:
	case FIOCLEX:
		FILEDESC_XLOCK(fdp);
		locked = LA_XLOCKED;
		break;
	default:
#ifdef CAPABILITIES
		FILEDESC_SLOCK(fdp);
		locked = LA_SLOCKED;
#else
		locked = LA_UNLOCKED;
#endif
		break;
	}

#ifdef CAPABILITIES
	if ((fp = fget_locked(fdp, fd)) == NULL) {
		error = EBADF;
		goto out;
	}
	if ((error = cap_ioctl_check(fdp, fd, com)) != 0) {
		fp = NULL;	/* fhold() was not called yet */
		goto out;
	}
	if (!fhold(fp)) {
		error = EBADF;
		fp = NULL;
		goto out;
	}
	if (locked == LA_SLOCKED) {
		FILEDESC_SUNLOCK(fdp);
		locked = LA_UNLOCKED;
	}
#else
	error = fget(td, fd, &cap_ioctl_rights, &fp);
	if (error != 0) {
		fp = NULL;
		goto out;
	}
#endif
	if ((fp->f_flag & (FREAD | FWRITE)) == 0) {
		error = EBADF;
		goto out;
	}

	switch (com) {
	case FIONCLEX:
		fdp->fd_ofiles[fd].fde_flags &= ~UF_EXCLOSE;
		goto out;
	case FIOCLEX:
		fdp->fd_ofiles[fd].fde_flags |= UF_EXCLOSE;
		goto out;
	case FIONBIO:
		if ((tmp = *(int *)data))
			atomic_set_int(&fp->f_flag, FNONBLOCK);
		else
			atomic_clear_int(&fp->f_flag, FNONBLOCK);
		data = (void *)&tmp;
		break;
	case FIOASYNC:
		if ((tmp = *(int *)data))
			atomic_set_int(&fp->f_flag, FASYNC);
		else
			atomic_clear_int(&fp->f_flag, FASYNC);
		data = (void *)&tmp;
		break;
	}

	error = fo_ioctl(fp, com, data, td->td_ucred, td);
out:
	switch (locked) {
	case LA_XLOCKED:
		FILEDESC_XUNLOCK(fdp);
		break;
#ifdef CAPABILITIES
	case LA_SLOCKED:
		FILEDESC_SUNLOCK(fdp);
		break;
#endif
	default:
		FILEDESC_UNLOCK_ASSERT(fdp);
		break;
	}
	if (fp != NULL)
		fdrop(fp, td);
	return (error);
}

int
sys_posix_fallocate(struct thread *td, struct posix_fallocate_args *uap)
{
	int error;

	error = kern_posix_fallocate(td, uap->fd, uap->offset, uap->len);
	return (kern_posix_error(td, error));
}

int
kern_posix_fallocate(struct thread *td, int fd, off_t offset, off_t len)
{
	struct file *fp;
	int error;

	AUDIT_ARG_FD(fd);
	if (offset < 0 || len <= 0)
		return (EINVAL);
	/* Check for wrap. */
	if (offset > OFF_MAX - len)
		return (EFBIG);
	AUDIT_ARG_FD(fd);
	error = fget(td, fd, &cap_pwrite_rights, &fp);
	if (error != 0)
		return (error);
	AUDIT_ARG_FILE(td->td_proc, fp);
	if ((fp->f_ops->fo_flags & DFLAG_SEEKABLE) == 0) {
		error = ESPIPE;
		goto out;
	}
	if ((fp->f_flag & FWRITE) == 0) {
		error = EBADF;
		goto out;
	}

	error = fo_fallocate(fp, offset, len, td);
 out:
	fdrop(fp, td);
	return (error);
}

int
poll_no_poll(int events)
{
	/*
	 * Return true for read/write.  If the user asked for something
	 * special, return POLLNVAL, so that clients have a way of
	 * determining reliably whether or not the extended
	 * functionality is present without hard-coding knowledge
	 * of specific filesystem implementations.
	 */
	if (events & ~POLLSTANDARD)
		return (POLLNVAL);

	return (events & (POLLIN | POLLOUT | POLLRDNORM | POLLWRNORM));
}

int
sys_pselect(struct thread *td, struct pselect_args *uap)
{
	struct timespec ts;
	struct timeval tv, *tvp;
	sigset_t set, *uset;
	int error;

	if (uap->ts != NULL) {
		error = copyin(uap->ts, &ts, sizeof(ts));
		if (error != 0)
		    return (error);
		TIMESPEC_TO_TIMEVAL(&tv, &ts);
		tvp = &tv;
	} else
		tvp = NULL;
	if (uap->sm != NULL) {
		error = copyin(uap->sm, &set, sizeof(set));
		if (error != 0)
			return (error);
		uset = &set;
	} else
		uset = NULL;
	return (kern_pselect(td, uap->nd, uap->in, uap->ou, uap->ex, tvp,
	    uset, NFDBITS));
}

int
kern_pselect(struct thread *td, int nd, fd_set *in, fd_set *ou, fd_set *ex,
    struct timeval *tvp, sigset_t *uset, int abi_nfdbits)
{
	int error;

	if (uset != NULL) {
		error = kern_sigprocmask(td, SIG_SETMASK, uset,
		    &td->td_oldsigmask, 0);
		if (error != 0)
			return (error);
		td->td_pflags |= TDP_OLDMASK;
		/*
		 * Make sure that ast() is called on return to
		 * usermode and TDP_OLDMASK is cleared, restoring old
		 * sigmask.
		 */
		thread_lock(td);
		td->td_flags |= TDF_ASTPENDING;
		thread_unlock(td);
	}
	error = kern_select(td, nd, in, ou, ex, tvp, abi_nfdbits);
	return (error);
}

#ifndef _SYS_SYSPROTO_H_
struct select_args {
	int	nd;
	fd_set	*in, *ou, *ex;
	struct	timeval *tv;
};
#endif
int
sys_select(struct thread *td, struct select_args *uap)
{
	struct timeval tv, *tvp;
	int error;

	if (uap->tv != NULL) {
		error = copyin(uap->tv, &tv, sizeof(tv));
		if (error)
			return (error);
		tvp = &tv;
	} else
		tvp = NULL;

	return (kern_select(td, uap->nd, uap->in, uap->ou, uap->ex, tvp,
	    NFDBITS));
}

/*
 * In the unlikely case when user specified n greater then the last
 * open file descriptor, check that no bits are set after the last
 * valid fd.  We must return EBADF if any is set.
 *
 * There are applications that rely on the behaviour.
 *
 * nd is fd_nfiles.
 */
static int
select_check_badfd(fd_set *fd_in, int nd, int ndu, int abi_nfdbits)
{
	char *addr, *oaddr;
	int b, i, res;
	uint8_t bits;

	if (nd >= ndu || fd_in == NULL)
		return (0);

	oaddr = NULL;
	bits = 0; /* silence gcc */
	for (i = nd; i < ndu; i++) {
		b = i / NBBY;
#if BYTE_ORDER == LITTLE_ENDIAN
		addr = (char *)fd_in + b;
#else
		addr = (char *)fd_in;
		if (abi_nfdbits == NFDBITS) {
			addr += rounddown(b, sizeof(fd_mask)) +
			    sizeof(fd_mask) - 1 - b % sizeof(fd_mask);
		} else {
			addr += rounddown(b, sizeof(uint32_t)) +
			    sizeof(uint32_t) - 1 - b % sizeof(uint32_t);
		}
#endif
		if (addr != oaddr) {
			res = fubyte(addr);
			if (res == -1)
				return (EFAULT);
			oaddr = addr;
			bits = res;
		}
		if ((bits & (1 << (i % NBBY))) != 0)
			return (EBADF);
	}
	return (0);
}

int
kern_select(struct thread *td, int nd, fd_set *fd_in, fd_set *fd_ou,
    fd_set *fd_ex, struct timeval *tvp, int abi_nfdbits)
{
	struct filedesc *fdp;
	/*
	 * The magic 2048 here is chosen to be just enough for FD_SETSIZE
	 * infds with the new FD_SETSIZE of 1024, and more than enough for
	 * FD_SETSIZE infds, outfds and exceptfds with the old FD_SETSIZE
	 * of 256.
	 */
	fd_mask s_selbits[howmany(2048, NFDBITS)];
	fd_mask *ibits[3], *obits[3], *selbits, *sbp;
	struct timeval rtv;
	sbintime_t asbt, precision, rsbt;
	u_int nbufbytes, ncpbytes, ncpubytes, nfdbits;
	int error, lf, ndu;

	if (nd < 0)
		return (EINVAL);
	fdp = td->td_proc->p_fd;
	ndu = nd;
	lf = fdp->fd_nfiles;
	if (nd > lf)
		nd = lf;

	error = select_check_badfd(fd_in, nd, ndu, abi_nfdbits);
	if (error != 0)
		return (error);
	error = select_check_badfd(fd_ou, nd, ndu, abi_nfdbits);
	if (error != 0)
		return (error);
	error = select_check_badfd(fd_ex, nd, ndu, abi_nfdbits);
	if (error != 0)
		return (error);

	/*
	 * Allocate just enough bits for the non-null fd_sets.  Use the
	 * preallocated auto buffer if possible.
	 */
	nfdbits = roundup(nd, NFDBITS);
	ncpbytes = nfdbits / NBBY;
	ncpubytes = roundup(nd, abi_nfdbits) / NBBY;
	nbufbytes = 0;
	if (fd_in != NULL)
		nbufbytes += 2 * ncpbytes;
	if (fd_ou != NULL)
		nbufbytes += 2 * ncpbytes;
	if (fd_ex != NULL)
		nbufbytes += 2 * ncpbytes;
	if (nbufbytes <= sizeof s_selbits)
		selbits = &s_selbits[0];
	else
		selbits = malloc(nbufbytes, M_SELECT, M_WAITOK);

	/*
	 * Assign pointers into the bit buffers and fetch the input bits.
	 * Put the output buffers together so that they can be bzeroed
	 * together.
	 */
	sbp = selbits;
#define	getbits(name, x) \
	do {								\
		if (name == NULL) {					\
			ibits[x] = NULL;				\
			obits[x] = NULL;				\
		} else {						\
			ibits[x] = sbp + nbufbytes / 2 / sizeof *sbp;	\
			obits[x] = sbp;					\
			sbp += ncpbytes / sizeof *sbp;			\
			error = copyin(name, ibits[x], ncpubytes);	\
			if (error != 0)					\
				goto done;				\
			if (ncpbytes != ncpubytes)			\
				bzero((char *)ibits[x] + ncpubytes,	\
				    ncpbytes - ncpubytes);		\
		}							\
	} while (0)
	getbits(fd_in, 0);
	getbits(fd_ou, 1);
	getbits(fd_ex, 2);
#undef	getbits

#if BYTE_ORDER == BIG_ENDIAN && defined(__LP64__)
	/*
	 * XXX: swizzle_fdset assumes that if abi_nfdbits != NFDBITS,
	 * we are running under 32-bit emulation. This should be more
	 * generic.
	 */
#define swizzle_fdset(bits)						\
	if (abi_nfdbits != NFDBITS && bits != NULL) {			\
		int i;							\
		for (i = 0; i < ncpbytes / sizeof *sbp; i++)		\
			bits[i] = (bits[i] >> 32) | (bits[i] << 32);	\
	}
#else
#define swizzle_fdset(bits)
#endif

	/* Make sure the bit order makes it through an ABI transition */
	swizzle_fdset(ibits[0]);
	swizzle_fdset(ibits[1]);
	swizzle_fdset(ibits[2]);
	
	if (nbufbytes != 0)
		bzero(selbits, nbufbytes / 2);

	precision = 0;
	if (tvp != NULL) {
		rtv = *tvp;
		if (rtv.tv_sec < 0 || rtv.tv_usec < 0 ||
		    rtv.tv_usec >= 1000000) {
			error = EINVAL;
			goto done;
		}
		if (!timevalisset(&rtv))
			asbt = 0;
		else if (rtv.tv_sec <= INT32_MAX) {
			rsbt = tvtosbt(rtv);
			precision = rsbt;
			precision >>= tc_precexp;
			if (TIMESEL(&asbt, rsbt))
				asbt += tc_tick_sbt;
			if (asbt <= SBT_MAX - rsbt)
				asbt += rsbt;
			else
				asbt = -1;
		} else
			asbt = -1;
	} else
		asbt = -1;
	seltdinit(td);
	/* Iterate until the timeout expires or descriptors become ready. */
	for (;;) {
		error = selscan(td, ibits, obits, nd);
		if (error || td->td_retval[0] != 0)
			break;
		error = seltdwait(td, asbt, precision);
		if (error)
			break;
		error = selrescan(td, ibits, obits);
		if (error || td->td_retval[0] != 0)
			break;
	}
	seltdclear(td);

done:
	/* select is not restarted after signals... */
	if (error == ERESTART)
		error = EINTR;
	if (error == EWOULDBLOCK)
		error = 0;

	/* swizzle bit order back, if necessary */
	swizzle_fdset(obits[0]);
	swizzle_fdset(obits[1]);
	swizzle_fdset(obits[2]);
#undef swizzle_fdset

#define	putbits(name, x) \
	if (name && (error2 = copyout(obits[x], name, ncpubytes))) \
		error = error2;
	if (error == 0) {
		int error2;

		putbits(fd_in, 0);
		putbits(fd_ou, 1);
		putbits(fd_ex, 2);
#undef putbits
	}
	if (selbits != &s_selbits[0])
		free(selbits, M_SELECT);

	return (error);
}
/* 
 * Convert a select bit set to poll flags.
 *
 * The backend always returns POLLHUP/POLLERR if appropriate and we
 * return this as a set bit in any set.
 */
static int select_flags[3] = {
    POLLRDNORM | POLLHUP | POLLERR,
    POLLWRNORM | POLLHUP | POLLERR,
    POLLRDBAND | POLLERR
};

/*
 * Compute the fo_poll flags required for a fd given by the index and
 * bit position in the fd_mask array.
 */
static __inline int
selflags(fd_mask **ibits, int idx, fd_mask bit)
{
	int flags;
	int msk;

	flags = 0;
	for (msk = 0; msk < 3; msk++) {
		if (ibits[msk] == NULL)
			continue;
		if ((ibits[msk][idx] & bit) == 0)
			continue;
		flags |= select_flags[msk];
	}
	return (flags);
}

/*
 * Set the appropriate output bits given a mask of fired events and the
 * input bits originally requested.
 */
static __inline int
selsetbits(fd_mask **ibits, fd_mask **obits, int idx, fd_mask bit, int events)
{
	int msk;
	int n;

	n = 0;
	for (msk = 0; msk < 3; msk++) {
		if ((events & select_flags[msk]) == 0)
			continue;
		if (ibits[msk] == NULL)
			continue;
		if ((ibits[msk][idx] & bit) == 0)
			continue;
		/*
		 * XXX Check for a duplicate set.  This can occur because a
		 * socket calls selrecord() twice for each poll() call
		 * resulting in two selfds per real fd.  selrescan() will
		 * call selsetbits twice as a result.
		 */
		if ((obits[msk][idx] & bit) != 0)
			continue;
		obits[msk][idx] |= bit;
		n++;
	}

	return (n);
}

static __inline int
getselfd_cap(struct filedesc *fdp, int fd, struct file **fpp)
{

	return (fget_unlocked(fdp, fd, &cap_event_rights, fpp));
}

/*
 * Traverse the list of fds attached to this thread's seltd and check for
 * completion.
 */
static int
selrescan(struct thread *td, fd_mask **ibits, fd_mask **obits)
{
	struct filedesc *fdp;
	struct selinfo *si;
	struct seltd *stp;
	struct selfd *sfp;
	struct selfd *sfn;
	struct file *fp;
	fd_mask bit;
	int fd, ev, n, idx;
	int error;

	fdp = td->td_proc->p_fd;
	stp = td->td_sel;
	n = 0;
	STAILQ_FOREACH_SAFE(sfp, &stp->st_selq, sf_link, sfn) {
		fd = (int)(uintptr_t)sfp->sf_cookie;
		si = sfp->sf_si;
		selfdfree(stp, sfp);
		/* If the selinfo wasn't cleared the event didn't fire. */
		if (si != NULL)
			continue;
		error = getselfd_cap(fdp, fd, &fp);
		if (error)
			return (error);
		idx = fd / NFDBITS;
		bit = (fd_mask)1 << (fd % NFDBITS);
		ev = fo_poll(fp, selflags(ibits, idx, bit), td->td_ucred, td);
		fdrop(fp, td);
		if (ev != 0)
			n += selsetbits(ibits, obits, idx, bit, ev);
	}
	stp->st_flags = 0;
	td->td_retval[0] = n;
	return (0);
}

/*
 * Perform the initial filedescriptor scan and register ourselves with
 * each selinfo.
 */
static int
selscan(struct thread *td, fd_mask **ibits, fd_mask **obits, int nfd)
{
	struct filedesc *fdp;
	struct file *fp;
	fd_mask bit;
	int ev, flags, end, fd;
	int n, idx;
	int error;

	fdp = td->td_proc->p_fd;
	n = 0;
	for (idx = 0, fd = 0; fd < nfd; idx++) {
		end = imin(fd + NFDBITS, nfd);
		for (bit = 1; fd < end; bit <<= 1, fd++) {
			/* Compute the list of events we're interested in. */
			flags = selflags(ibits, idx, bit);
			if (flags == 0)
				continue;
			error = getselfd_cap(fdp, fd, &fp);
			if (error)
				return (error);
			selfdalloc(td, (void *)(uintptr_t)fd);
			ev = fo_poll(fp, flags, td->td_ucred, td);
			fdrop(fp, td);
			if (ev != 0)
				n += selsetbits(ibits, obits, idx, bit, ev);
		}
	}

	td->td_retval[0] = n;
	return (0);
}

int
sys_poll(struct thread *td, struct poll_args *uap)
{
	struct timespec ts, *tsp;

	if (uap->timeout != INFTIM) {
		if (uap->timeout < 0)
			return (EINVAL);
		ts.tv_sec = uap->timeout / 1000;
		ts.tv_nsec = (uap->timeout % 1000) * 1000000;
		tsp = &ts;
	} else
		tsp = NULL;

	return (kern_poll(td, uap->fds, uap->nfds, tsp, NULL));
}

int
kern_poll(struct thread *td, struct pollfd *ufds, u_int nfds,
    struct timespec *tsp, sigset_t *uset)
{
	struct pollfd *kfds;
	struct pollfd stackfds[32];
	sbintime_t sbt, precision, tmp;
	time_t over;
	struct timespec ts;
	int error;

	precision = 0;
	if (tsp != NULL) {
		if (tsp->tv_sec < 0)
			return (EINVAL);
		if (tsp->tv_nsec < 0 || tsp->tv_nsec >= 1000000000)
			return (EINVAL);
		if (tsp->tv_sec == 0 && tsp->tv_nsec == 0)
			sbt = 0;
		else {
			ts = *tsp;
			if (ts.tv_sec > INT32_MAX / 2) {
				over = ts.tv_sec - INT32_MAX / 2;
				ts.tv_sec -= over;
			} else
				over = 0;
			tmp = tstosbt(ts);
			precision = tmp;
			precision >>= tc_precexp;
			if (TIMESEL(&sbt, tmp))
				sbt += tc_tick_sbt;
			sbt += tmp;
		}
	} else
		sbt = -1;

	/*
	 * This is kinda bogus.  We have fd limits, but that is not
	 * really related to the size of the pollfd array.  Make sure
	 * we let the process use at least FD_SETSIZE entries and at
	 * least enough for the system-wide limits.  We want to be reasonably
	 * safe, but not overly restrictive.
	 */
	if (nfds > maxfilesperproc && nfds > FD_SETSIZE) 
		return (EINVAL);
	if (nfds > nitems(stackfds))
		kfds = mallocarray(nfds, sizeof(*kfds), M_TEMP, M_WAITOK);
	else
		kfds = stackfds;
	error = copyin(ufds, kfds, nfds * sizeof(*kfds));
	if (error)
		goto done;

	if (uset != NULL) {
		error = kern_sigprocmask(td, SIG_SETMASK, uset,
		    &td->td_oldsigmask, 0);
		if (error)
			goto done;
		td->td_pflags |= TDP_OLDMASK;
		/*
		 * Make sure that ast() is called on return to
		 * usermode and TDP_OLDMASK is cleared, restoring old
		 * sigmask.
		 */
		thread_lock(td);
		td->td_flags |= TDF_ASTPENDING;
		thread_unlock(td);
	}

	seltdinit(td);
	/* Iterate until the timeout expires or descriptors become ready. */
	for (;;) {
		error = pollscan(td, kfds, nfds);
		if (error || td->td_retval[0] != 0)
			break;
		error = seltdwait(td, sbt, precision);
		if (error)
			break;
		error = pollrescan(td);
		if (error || td->td_retval[0] != 0)
			break;
	}
	seltdclear(td);

done:
	/* poll is not restarted after signals... */
	if (error == ERESTART)
		error = EINTR;
	if (error == EWOULDBLOCK)
		error = 0;
	if (error == 0) {
		error = pollout(td, kfds, ufds, nfds);
		if (error)
			goto out;
	}
out:
	if (nfds > nitems(stackfds))
		free(kfds, M_TEMP);
	return (error);
}

int
sys_ppoll(struct thread *td, struct ppoll_args *uap)
{
	struct timespec ts, *tsp;
	sigset_t set, *ssp;
	int error;

	if (uap->ts != NULL) {
		error = copyin(uap->ts, &ts, sizeof(ts));
		if (error)
			return (error);
		tsp = &ts;
	} else
		tsp = NULL;
	if (uap->set != NULL) {
		error = copyin(uap->set, &set, sizeof(set));
		if (error)
			return (error);
		ssp = &set;
	} else
		ssp = NULL;
	/*
	 * fds is still a pointer to user space. kern_poll() will
	 * take care of copyin that array to the kernel space.
	 */

	return (kern_poll(td, uap->fds, uap->nfds, tsp, ssp));
}

static int
pollrescan(struct thread *td)
{
	struct seltd *stp;
	struct selfd *sfp;
	struct selfd *sfn;
	struct selinfo *si;
	struct filedesc *fdp;
	struct file *fp;
	struct pollfd *fd;
	int n;

	n = 0;
	fdp = td->td_proc->p_fd;
	stp = td->td_sel;
	FILEDESC_SLOCK(fdp);
	STAILQ_FOREACH_SAFE(sfp, &stp->st_selq, sf_link, sfn) {
		fd = (struct pollfd *)sfp->sf_cookie;
		si = sfp->sf_si;
		selfdfree(stp, sfp);
		/* If the selinfo wasn't cleared the event didn't fire. */
		if (si != NULL)
			continue;
		fp = fdp->fd_ofiles[fd->fd].fde_file;
#ifdef CAPABILITIES
		if (fp == NULL ||
		    cap_check(cap_rights(fdp, fd->fd), &cap_event_rights) != 0)
#else
		if (fp == NULL)
#endif
		{
			fd->revents = POLLNVAL;
			n++;
			continue;
		}

		/*
		 * Note: backend also returns POLLHUP and
		 * POLLERR if appropriate.
		 */
		fd->revents = fo_poll(fp, fd->events, td->td_ucred, td);
		if (fd->revents != 0)
			n++;
	}
	FILEDESC_SUNLOCK(fdp);
	stp->st_flags = 0;
	td->td_retval[0] = n;
	return (0);
}

static int
pollout(struct thread *td, struct pollfd *fds, struct pollfd *ufds, u_int nfd)
{
	int error = 0;
	u_int i = 0;
	u_int n = 0;

	for (i = 0; i < nfd; i++) {
		error = copyout(&fds->revents, &ufds->revents,
		    sizeof(ufds->revents));
		if (error)
			return (error);
		if (fds->revents != 0)
			n++;
		fds++;
		ufds++;
	}
	td->td_retval[0] = n;
	return (0);
}

static int
pollscan(struct thread *td, struct pollfd *fds, u_int nfd)
{
	struct filedesc *fdp = td->td_proc->p_fd;
	struct file *fp;
	int i, n = 0;

	FILEDESC_SLOCK(fdp);
	for (i = 0; i < nfd; i++, fds++) {
		if (fds->fd >= fdp->fd_nfiles) {
			fds->revents = POLLNVAL;
			n++;
		} else if (fds->fd < 0) {
			fds->revents = 0;
		} else {
			fp = fdp->fd_ofiles[fds->fd].fde_file;
#ifdef CAPABILITIES
			if (fp == NULL ||
			    cap_check(cap_rights(fdp, fds->fd), &cap_event_rights) != 0)
#else
			if (fp == NULL)
#endif
			{
				fds->revents = POLLNVAL;
				n++;
			} else {
				/*
				 * Note: backend also returns POLLHUP and
				 * POLLERR if appropriate.
				 */
				selfdalloc(td, fds);
				fds->revents = fo_poll(fp, fds->events,
				    td->td_ucred, td);
				/*
				 * POSIX requires POLLOUT to be never
				 * set simultaneously with POLLHUP.
				 */
				if ((fds->revents & POLLHUP) != 0)
					fds->revents &= ~POLLOUT;

				if (fds->revents != 0)
					n++;
			}
		}
	}
	FILEDESC_SUNLOCK(fdp);
	td->td_retval[0] = n;
	return (0);
}

/*
 * XXX This was created specifically to support netncp and netsmb.  This
 * allows the caller to specify a socket to wait for events on.  It returns
 * 0 if any events matched and an error otherwise.  There is no way to
 * determine which events fired.
 */
int
selsocket(struct socket *so, int events, struct timeval *tvp, struct thread *td)
{
	struct timeval rtv;
	sbintime_t asbt, precision, rsbt;
	int error;

	precision = 0;	/* stupid gcc! */
	if (tvp != NULL) {
		rtv = *tvp;
		if (rtv.tv_sec < 0 || rtv.tv_usec < 0 || 
		    rtv.tv_usec >= 1000000)
			return (EINVAL);
		if (!timevalisset(&rtv))
			asbt = 0;
		else if (rtv.tv_sec <= INT32_MAX) {
			rsbt = tvtosbt(rtv);
			precision = rsbt;
			precision >>= tc_precexp;
			if (TIMESEL(&asbt, rsbt))
				asbt += tc_tick_sbt;
			if (asbt <= SBT_MAX - rsbt)
				asbt += rsbt;
			else
				asbt = -1;
		} else
			asbt = -1;
	} else
		asbt = -1;
	seltdinit(td);
	/*
	 * Iterate until the timeout expires or the socket becomes ready.
	 */
	for (;;) {
		selfdalloc(td, NULL);
		error = sopoll(so, events, NULL, td);
		/* error here is actually the ready events. */
		if (error)
			return (0);
		error = seltdwait(td, asbt, precision);
		if (error)
			break;
	}
	seltdclear(td);
	/* XXX Duplicates ncp/smb behavior. */
	if (error == ERESTART)
		error = 0;
	return (error);
}

/*
 * Preallocate two selfds associated with 'cookie'.  Some fo_poll routines
 * have two select sets, one for read and another for write.
 */
static void
selfdalloc(struct thread *td, void *cookie)
{
	struct seltd *stp;

	stp = td->td_sel;
	if (stp->st_free1 == NULL)
		stp->st_free1 = uma_zalloc(selfd_zone, M_WAITOK|M_ZERO);
	stp->st_free1->sf_td = stp;
	stp->st_free1->sf_cookie = cookie;
	if (stp->st_free2 == NULL)
		stp->st_free2 = uma_zalloc(selfd_zone, M_WAITOK|M_ZERO);
	stp->st_free2->sf_td = stp;
	stp->st_free2->sf_cookie = cookie;
}

static void
selfdfree(struct seltd *stp, struct selfd *sfp)
{
	STAILQ_REMOVE(&stp->st_selq, sfp, selfd, sf_link);
	if (sfp->sf_si != NULL) {
		mtx_lock(sfp->sf_mtx);
		if (sfp->sf_si != NULL) {
			TAILQ_REMOVE(&sfp->sf_si->si_tdlist, sfp, sf_threads);
			refcount_release(&sfp->sf_refs);
		}
		mtx_unlock(sfp->sf_mtx);
	}
	if (refcount_release(&sfp->sf_refs))
		uma_zfree(selfd_zone, sfp);
}

/* Drain the waiters tied to all the selfd belonging the specified selinfo. */
void
seldrain(struct selinfo *sip)
{

	/*
	 * This feature is already provided by doselwakeup(), thus it is
	 * enough to go for it.
	 * Eventually, the context, should take care to avoid races
	 * between thread calling select()/poll() and file descriptor
	 * detaching, but, again, the races are just the same as
	 * selwakeup().
	 */
        doselwakeup(sip, -1);
}

/*
 * Record a select request.
 */
void
selrecord(struct thread *selector, struct selinfo *sip)
{
	struct selfd *sfp;
	struct seltd *stp;
	struct mtx *mtxp;

	stp = selector->td_sel;
	/*
	 * Don't record when doing a rescan.
	 */
	if (stp->st_flags & SELTD_RESCAN)
		return;
	/*
	 * Grab one of the preallocated descriptors.
	 */
	sfp = NULL;
	if ((sfp = stp->st_free1) != NULL)
		stp->st_free1 = NULL;
	else if ((sfp = stp->st_free2) != NULL)
		stp->st_free2 = NULL;
	else
		panic("selrecord: No free selfd on selq");
	mtxp = sip->si_mtx;
	if (mtxp == NULL)
		mtxp = mtx_pool_find(mtxpool_select, sip);
	/*
	 * Initialize the sfp and queue it in the thread.
	 */
	sfp->sf_si = sip;
	sfp->sf_mtx = mtxp;
	refcount_init(&sfp->sf_refs, 2);
	STAILQ_INSERT_TAIL(&stp->st_selq, sfp, sf_link);
	/*
	 * Now that we've locked the sip, check for initialization.
	 */
	mtx_lock(mtxp);
	if (sip->si_mtx == NULL) {
		sip->si_mtx = mtxp;
		TAILQ_INIT(&sip->si_tdlist);
	}
	/*
	 * Add this thread to the list of selfds listening on this selinfo.
	 */
	TAILQ_INSERT_TAIL(&sip->si_tdlist, sfp, sf_threads);
	mtx_unlock(sip->si_mtx);
}

/* Wake up a selecting thread. */
void
selwakeup(struct selinfo *sip)
{
	doselwakeup(sip, -1);
}

/* Wake up a selecting thread, and set its priority. */
void
selwakeuppri(struct selinfo *sip, int pri)
{
	doselwakeup(sip, pri);
}

/*
 * Do a wakeup when a selectable event occurs.
 */
static void
doselwakeup(struct selinfo *sip, int pri)
{
	struct selfd *sfp;
	struct selfd *sfn;
	struct seltd *stp;

	/* If it's not initialized there can't be any waiters. */
	if (sip->si_mtx == NULL)
		return;
	/*
	 * Locking the selinfo locks all selfds associated with it.
	 */
	mtx_lock(sip->si_mtx);
	TAILQ_FOREACH_SAFE(sfp, &sip->si_tdlist, sf_threads, sfn) {
		/*
		 * Once we remove this sfp from the list and clear the
		 * sf_si seltdclear will know to ignore this si.
		 */
		TAILQ_REMOVE(&sip->si_tdlist, sfp, sf_threads);
		sfp->sf_si = NULL;
		stp = sfp->sf_td;
		mtx_lock(&stp->st_mtx);
		stp->st_flags |= SELTD_PENDING;
		cv_broadcastpri(&stp->st_wait, pri);
		mtx_unlock(&stp->st_mtx);
		if (refcount_release(&sfp->sf_refs))
			uma_zfree(selfd_zone, sfp);
	}
	mtx_unlock(sip->si_mtx);
}

static void
seltdinit(struct thread *td)
{
	struct seltd *stp;

	if ((stp = td->td_sel) != NULL)
		goto out;
	td->td_sel = stp = malloc(sizeof(*stp), M_SELECT, M_WAITOK|M_ZERO);
	mtx_init(&stp->st_mtx, "sellck", NULL, MTX_DEF);
	cv_init(&stp->st_wait, "select");
out:
	stp->st_flags = 0;
	STAILQ_INIT(&stp->st_selq);
}

static int
seltdwait(struct thread *td, sbintime_t sbt, sbintime_t precision)
{
	struct seltd *stp;
	int error;

	stp = td->td_sel;
	/*
	 * An event of interest may occur while we do not hold the seltd
	 * locked so check the pending flag before we sleep.
	 */
	mtx_lock(&stp->st_mtx);
	/*
	 * Any further calls to selrecord will be a rescan.
	 */
	stp->st_flags |= SELTD_RESCAN;
	if (stp->st_flags & SELTD_PENDING) {
		mtx_unlock(&stp->st_mtx);
		return (0);
	}
	if (sbt == 0)
		error = EWOULDBLOCK;
	else if (sbt != -1)
		error = cv_timedwait_sig_sbt(&stp->st_wait, &stp->st_mtx,
		    sbt, precision, C_ABSOLUTE);
	else
		error = cv_wait_sig(&stp->st_wait, &stp->st_mtx);
	mtx_unlock(&stp->st_mtx);

	return (error);
}

void
seltdfini(struct thread *td)
{
	struct seltd *stp;

	stp = td->td_sel;
	if (stp == NULL)
		return;
	if (stp->st_free1)
		uma_zfree(selfd_zone, stp->st_free1);
	if (stp->st_free2)
		uma_zfree(selfd_zone, stp->st_free2);
	td->td_sel = NULL;
	cv_destroy(&stp->st_wait);
	mtx_destroy(&stp->st_mtx);
	free(stp, M_SELECT);
}

/*
 * Remove the references to the thread from all of the objects we were
 * polling.
 */
static void
seltdclear(struct thread *td)
{
	struct seltd *stp;
	struct selfd *sfp;
	struct selfd *sfn;

	stp = td->td_sel;
	STAILQ_FOREACH_SAFE(sfp, &stp->st_selq, sf_link, sfn)
		selfdfree(stp, sfp);
	stp->st_flags = 0;
}

static void selectinit(void *);
SYSINIT(select, SI_SUB_SYSCALLS, SI_ORDER_ANY, selectinit, NULL);
static void
selectinit(void *dummy __unused)
{

	selfd_zone = uma_zcreate("selfd", sizeof(struct selfd), NULL, NULL,
	    NULL, NULL, UMA_ALIGN_PTR, 0);
	mtxpool_select = mtx_pool_create("select mtxpool", 128, MTX_DEF);
}

/*
 * Set up a syscall return value that follows the convention specified for
 * posix_* functions.
 */
int
kern_posix_error(struct thread *td, int error)
{

	if (error <= 0)
		return (error);
	td->td_errno = error;
	td->td_pflags |= TDP_NERRNO;
	td->td_retval[0] = error;
	return (0);
}