summaryrefslogtreecommitdiff
path: root/sys/net/bpf.c
blob: affd0a4b56719dba5ac02c5b38c370ece5cede07 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
/*	$OpenBSD: bpf.c,v 1.155 2016/11/28 10:16:08 mpi Exp $	*/
/*	$NetBSD: bpf.c,v 1.33 1997/02/21 23:59:35 thorpej Exp $	*/

/*
 * Copyright (c) 1990, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 * Copyright (c) 2010, 2014 Henning Brauer <henning@openbsd.org>
 *
 * This code is derived from the Stanford/CMU enet packet filter,
 * (net/enet.c) distributed as part of 4.3BSD, and code contributed
 * to Berkeley by Steven McCanne and Van Jacobson both of Lawrence 
 * Berkeley Laboratory.
 *
 * 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.
 *
 *	@(#)bpf.c	8.2 (Berkeley) 3/28/94
 */

#include "bpfilter.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/proc.h>
#include <sys/signalvar.h>
#include <sys/ioctl.h>
#include <sys/conf.h>
#include <sys/vnode.h>
#include <sys/file.h>
#include <sys/socket.h>
#include <sys/poll.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>
#include <sys/rwlock.h>
#include <sys/atomic.h>
#include <sys/srp.h>
#include <sys/specdev.h>
#include <sys/selinfo.h>
#include <sys/task.h>

#include <net/if.h>
#include <net/bpf.h>
#include <net/bpfdesc.h>

#include <netinet/in.h>
#include <netinet/if_ether.h>

#include "vlan.h"
#if NVLAN > 0
#include <net/if_vlan_var.h>
#endif

#define BPF_BUFSIZE 32768

#define PRINET  26			/* interruptible */

/* from kern/kern_clock.c; incremented each clock tick. */
extern int ticks;

/*
 * The default read buffer size is patchable.
 */
int bpf_bufsize = BPF_BUFSIZE;
int bpf_maxbufsize = BPF_MAXBUFSIZE;

/*
 *  bpf_iflist is the list of interfaces; each corresponds to an ifnet
 *  bpf_d_list is the list of descriptors
 */
struct bpf_if	*bpf_iflist;
LIST_HEAD(, bpf_d) bpf_d_list;

int	bpf_allocbufs(struct bpf_d *);
void	bpf_ifname(struct ifnet *, struct ifreq *);
int	_bpf_mtap(caddr_t, const struct mbuf *, u_int,
	    void (*)(const void *, void *, size_t));
void	bpf_mcopy(const void *, void *, size_t);
int	bpf_movein(struct uio *, u_int, struct mbuf **,
	    struct sockaddr *, struct bpf_insn *);
int	bpf_setif(struct bpf_d *, struct ifreq *);
int	bpfpoll(dev_t, int, struct proc *);
int	bpfkqfilter(dev_t, struct knote *);
void	bpf_wakeup(struct bpf_d *);
void	bpf_wakeup_cb(void *);
void	bpf_catchpacket(struct bpf_d *, u_char *, size_t, size_t,
	    void (*)(const void *, void *, size_t), struct timeval *);
int	bpf_getdltlist(struct bpf_d *, struct bpf_dltlist *);
int	bpf_setdlt(struct bpf_d *, u_int);

void	filt_bpfrdetach(struct knote *);
int	filt_bpfread(struct knote *, long);

int	bpf_sysctl_locked(int *, u_int, void *, size_t *, void *, size_t);

struct bpf_d *bpfilter_lookup(int);

void	bpf_attachd(struct bpf_d *, struct bpf_if *);
void	bpf_detachd(struct bpf_d *);
void	bpf_resetd(struct bpf_d *);

/*
 * Reference count access to descriptor buffers
 */
void	bpf_get(struct bpf_d *);
void	bpf_put(struct bpf_d *);

/*
 * garbage collector srps
 */

void bpf_d_ref(void *, void *);
void bpf_d_unref(void *, void *);
struct srpl_rc bpf_d_rc = SRPL_RC_INITIALIZER(bpf_d_ref, bpf_d_unref, NULL);

void bpf_insn_dtor(void *, void *);
struct srp_gc bpf_insn_gc = SRP_GC_INITIALIZER(bpf_insn_dtor, NULL);

int
bpf_movein(struct uio *uio, u_int linktype, struct mbuf **mp,
    struct sockaddr *sockp, struct bpf_insn *filter)
{
	struct mbuf *m;
	struct m_tag *mtag;
	int error;
	u_int hlen;
	u_int len;
	u_int slen;

	/*
	 * Build a sockaddr based on the data link layer type.
	 * We do this at this level because the ethernet header
	 * is copied directly into the data field of the sockaddr.
	 * In the case of SLIP, there is no header and the packet
	 * is forwarded as is.
	 * Also, we are careful to leave room at the front of the mbuf
	 * for the link level header.
	 */
	switch (linktype) {

	case DLT_SLIP:
		sockp->sa_family = AF_INET;
		hlen = 0;
		break;

	case DLT_PPP:
		sockp->sa_family = AF_UNSPEC;
		hlen = 0;
		break;

	case DLT_EN10MB:
		sockp->sa_family = AF_UNSPEC;
		/* XXX Would MAXLINKHDR be better? */
		hlen = ETHER_HDR_LEN;
		break;

	case DLT_IEEE802_11:
	case DLT_IEEE802_11_RADIO:
		sockp->sa_family = AF_UNSPEC;
		hlen = 0;
		break;

	case DLT_RAW:
	case DLT_NULL:
		sockp->sa_family = AF_UNSPEC;
		hlen = 0;
		break;

	case DLT_LOOP:
		sockp->sa_family = AF_UNSPEC;
		hlen = sizeof(u_int32_t);
		break;

	default:
		return (EIO);
	}

	if (uio->uio_resid > MAXMCLBYTES)
		return (EIO);
	len = uio->uio_resid;

	MGETHDR(m, M_WAIT, MT_DATA);
	m->m_pkthdr.ph_ifidx = 0;
	m->m_pkthdr.len = len - hlen;

	if (len > MHLEN) {
		MCLGETI(m, M_WAIT, NULL, len);
		if ((m->m_flags & M_EXT) == 0) {
			error = ENOBUFS;
			goto bad;
		}
	}
	m->m_len = len;
	*mp = m;

	error = uiomove(mtod(m, caddr_t), len, uio);
	if (error)
		goto bad;

	slen = bpf_filter(filter, mtod(m, u_char *), len, len);
	if (slen < len) {
		error = EPERM;
		goto bad;
	}

	if (m->m_len < hlen) {
		error = EPERM;
		goto bad;
	}
	/*
	 * Make room for link header, and copy it to sockaddr
	 */
	if (hlen != 0) {
		if (linktype == DLT_LOOP) {
			u_int32_t af;

			/* the link header indicates the address family */
			KASSERT(hlen == sizeof(u_int32_t));
			memcpy(&af, m->m_data, hlen);
			sockp->sa_family = ntohl(af);
		} else
			memcpy(sockp->sa_data, m->m_data, hlen);
		m->m_len -= hlen;
		m->m_data += hlen; /* XXX */
	}

	/*
	 * Prepend the data link type as a mbuf tag
	 */
	mtag = m_tag_get(PACKET_TAG_DLT, sizeof(u_int), M_WAIT);
	*(u_int *)(mtag + 1) = linktype;
	m_tag_prepend(m, mtag);

	return (0);
 bad:
	m_freem(m);
	return (error);
}

/*
 * Attach file to the bpf interface, i.e. make d listen on bp.
 * Must be called at splnet.
 */
void
bpf_attachd(struct bpf_d *d, struct bpf_if *bp)
{
	/*
	 * Point d at bp, and add d to the interface's list of listeners.
	 * Finally, point the driver's bpf cookie at the interface so
	 * it will divert packets to bpf.
	 */

	d->bd_bif = bp;

	KERNEL_ASSERT_LOCKED();
	SRPL_INSERT_HEAD_LOCKED(&bpf_d_rc, &bp->bif_dlist, d, bd_next);

	*bp->bif_driverp = bp;
}

/*
 * Detach a file from its interface.
 */
void
bpf_detachd(struct bpf_d *d)
{
	struct bpf_if *bp;

	bp = d->bd_bif;
	/* Not attached. */
	if (bp == NULL)
		return;

	/* Remove ``d'' from the interface's descriptor list. */
	KERNEL_ASSERT_LOCKED();
	SRPL_REMOVE_LOCKED(&bpf_d_rc, &bp->bif_dlist, d, bpf_d, bd_next);

	if (SRPL_EMPTY_LOCKED(&bp->bif_dlist)) {
		/*
		 * Let the driver know that there are no more listeners.
		 */
		*bp->bif_driverp = NULL;
	}

	d->bd_bif = NULL;

	/*
	 * Check if this descriptor had requested promiscuous mode.
	 * If so, turn it off.
	 */
	if (d->bd_promisc) {
		int error;

		d->bd_promisc = 0;
		error = ifpromisc(bp->bif_ifp, 0);
		if (error && !(error == EINVAL || error == ENODEV))
			/*
			 * Something is really wrong if we were able to put
			 * the driver into promiscuous mode, but can't
			 * take it out.
			 */
			panic("bpf: ifpromisc failed");
	}
}

void
bpfilterattach(int n)
{
	LIST_INIT(&bpf_d_list);
}

/*
 * Open ethernet device.  Returns ENXIO for illegal minor device number,
 * EBUSY if file is open by another process.
 */
int
bpfopen(dev_t dev, int flag, int mode, struct proc *p)
{
	struct bpf_d *bd;
	int unit = minor(dev);

	if (unit & ((1 << CLONE_SHIFT) - 1))
		return (ENXIO);

	KASSERT(bpfilter_lookup(unit) == NULL);

	/* create on demand */
	if ((bd = malloc(sizeof(*bd), M_DEVBUF, M_NOWAIT|M_ZERO)) == NULL)
		return (EBUSY);

	/* Mark "free" and do most initialization. */
	bd->bd_unit = unit;
	bd->bd_bufsize = bpf_bufsize;
	bd->bd_sig = SIGIO;
	task_set(&bd->bd_wake_task, bpf_wakeup_cb, bd);

	if (flag & FNONBLOCK)
		bd->bd_rtout = -1;

	bpf_get(bd);
	LIST_INSERT_HEAD(&bpf_d_list, bd, bd_list);

	return (0);
}

/*
 * Close the descriptor by detaching it from its interface,
 * deallocating its buffers, and marking it free.
 */
int
bpfclose(dev_t dev, int flag, int mode, struct proc *p)
{
	struct bpf_d *d;
	int s;

	d = bpfilter_lookup(minor(dev));
	s = splnet();
	bpf_detachd(d);
	bpf_wakeup(d);
	LIST_REMOVE(d, bd_list);
	bpf_put(d);
	splx(s);

	return (0);
}

/*
 * Rotate the packet buffers in descriptor d.  Move the store buffer
 * into the hold slot, and the free buffer into the store slot.
 * Zero the length of the new store buffer.
 */
#define ROTATE_BUFFERS(d) \
	(d)->bd_hbuf = (d)->bd_sbuf; \
	(d)->bd_hlen = (d)->bd_slen; \
	(d)->bd_sbuf = (d)->bd_fbuf; \
	(d)->bd_slen = 0; \
	(d)->bd_fbuf = 0;
/*
 *  bpfread - read next chunk of packets from buffers
 */
int
bpfread(dev_t dev, struct uio *uio, int ioflag)
{
	struct bpf_d *d;
	int error;
	int s;

	d = bpfilter_lookup(minor(dev));
	if (d->bd_bif == NULL)
		return (ENXIO);

	s = splnet();
	bpf_get(d);

	/*
	 * Restrict application to use a buffer the same size as
	 * as kernel buffers.
	 */
	if (uio->uio_resid != d->bd_bufsize) {
		error = EINVAL;
		goto out;
	}

	/*
	 * If there's a timeout, bd_rdStart is tagged when we start the read.
	 * we can then figure out when we're done reading.
	 */
	if (d->bd_rtout != -1 && d->bd_rdStart == 0)
		d->bd_rdStart = ticks;
	else
		d->bd_rdStart = 0;

	/*
	 * If the hold buffer is empty, then do a timed sleep, which
	 * ends when the timeout expires or when enough packets
	 * have arrived to fill the store buffer.
	 */
	while (d->bd_hbuf == NULL) {
		if (d->bd_bif == NULL) {
			/* interface is gone */
			if (d->bd_slen == 0) {
				error = EIO;
				goto out;
			}
			ROTATE_BUFFERS(d);
			break;
		}
		if (d->bd_immediate && d->bd_slen != 0) {
			/*
			 * A packet(s) either arrived since the previous
			 * read or arrived while we were asleep.
			 * Rotate the buffers and return what's here.
			 */
			ROTATE_BUFFERS(d);
			break;
		}
		if (d->bd_rtout == -1) {
			/* User requested non-blocking I/O */
			error = EWOULDBLOCK;
		} else {
			if ((d->bd_rdStart + d->bd_rtout) < ticks) {
				error = tsleep((caddr_t)d, PRINET|PCATCH, "bpf",
				    d->bd_rtout);
			} else
				error = EWOULDBLOCK;
		}
		if (error == EINTR || error == ERESTART)
			goto out;
		if (error == EWOULDBLOCK) {
			/*
			 * On a timeout, return what's in the buffer,
			 * which may be nothing.  If there is something
			 * in the store buffer, we can rotate the buffers.
			 */
			if (d->bd_hbuf != NULL)
				/*
				 * We filled up the buffer in between
				 * getting the timeout and arriving
				 * here, so we don't need to rotate.
				 */
				break;

			if (d->bd_slen == 0) {
				error = 0;
				goto out;
			}
			ROTATE_BUFFERS(d);
			break;
		}
	}
	/*
	 * At this point, we know we have something in the hold slot.
	 */
	splx(s);

	/*
	 * Move data from hold buffer into user space.
	 * We know the entire buffer is transferred since
	 * we checked above that the read buffer is bpf_bufsize bytes.
	 */
	error = uiomove(d->bd_hbuf, d->bd_hlen, uio);

	s = splnet();
	d->bd_fbuf = d->bd_hbuf;
	d->bd_hbuf = NULL;
	d->bd_hlen = 0;
out:
	bpf_put(d);
	splx(s);

	return (error);
}


/*
 * If there are processes sleeping on this descriptor, wake them up.
 */
void
bpf_wakeup(struct bpf_d *d)
{
	/*
	 * As long as csignal() and selwakeup() need to be protected
	 * by the KERNEL_LOCK() we have to delay the wakeup to
	 * another context to keep the hot path KERNEL_LOCK()-free.
	 */
	bpf_get(d);
	if (!task_add(systq, &d->bd_wake_task))
		bpf_put(d);
}

void
bpf_wakeup_cb(void *xd)
{
	struct bpf_d *d = xd;

	KERNEL_ASSERT_LOCKED();

	wakeup(d);
	if (d->bd_async && d->bd_sig)
		csignal(d->bd_pgid, d->bd_sig, d->bd_siguid, d->bd_sigeuid);

	selwakeup(&d->bd_sel);
	bpf_put(d);
}

int
bpfwrite(dev_t dev, struct uio *uio, int ioflag)
{
	struct bpf_d *d;
	struct ifnet *ifp;
	struct mbuf *m;
	struct bpf_program *bf;
	struct bpf_insn *fcode = NULL;
	int error, s;
	struct sockaddr_storage dst;
	u_int dlt;

	d = bpfilter_lookup(minor(dev));
	if (d->bd_bif == NULL)
		return (ENXIO);

	bpf_get(d);
	ifp = d->bd_bif->bif_ifp;

	if ((ifp->if_flags & IFF_UP) == 0) {
		error = ENETDOWN;
		goto out;
	}

	if (uio->uio_resid == 0) {
		error = 0;
		goto out;
	}

	KERNEL_ASSERT_LOCKED(); /* for accessing bd_wfilter */
	bf = srp_get_locked(&d->bd_wfilter);
	if (bf != NULL)
		fcode = bf->bf_insns;

	dlt = d->bd_bif->bif_dlt;

	error = bpf_movein(uio, dlt, &m, (struct sockaddr *)&dst, fcode);
	if (error)
		goto out;

	if (m->m_pkthdr.len > ifp->if_mtu) {
		m_freem(m);
		error = EMSGSIZE;
		goto out;
	}

	m->m_pkthdr.ph_rtableid = ifp->if_rdomain;
	m->m_pkthdr.pf.prio = ifp->if_llprio;

	if (d->bd_hdrcmplt && dst.ss_family == AF_UNSPEC)
		dst.ss_family = pseudo_AF_HDRCMPLT;

	s = splsoftnet();
	error = ifp->if_output(ifp, m, (struct sockaddr *)&dst, NULL);
	splx(s);

out:
	bpf_put(d);
	return (error);
}

/*
 * Reset a descriptor by flushing its packet buffer and clearing the
 * receive and drop counts.  Should be called at splnet.
 */
void
bpf_resetd(struct bpf_d *d)
{
	if (d->bd_hbuf) {
		/* Free the hold buffer. */
		d->bd_fbuf = d->bd_hbuf;
		d->bd_hbuf = NULL;
	}
	d->bd_slen = 0;
	d->bd_hlen = 0;
	d->bd_rcount = 0;
	d->bd_dcount = 0;
}

/*
 *  FIONREAD		Check for read packet available.
 *  BIOCGBLEN		Get buffer len [for read()].
 *  BIOCSETF		Set ethernet read filter.
 *  BIOCFLUSH		Flush read packet buffer.
 *  BIOCPROMISC		Put interface into promiscuous mode.
 *  BIOCGDLTLIST	Get supported link layer types.
 *  BIOCGDLT		Get link layer type.
 *  BIOCSDLT		Set link layer type.
 *  BIOCGETIF		Get interface name.
 *  BIOCSETIF		Set interface.
 *  BIOCSRTIMEOUT	Set read timeout.
 *  BIOCGRTIMEOUT	Get read timeout.
 *  BIOCGSTATS		Get packet stats.
 *  BIOCIMMEDIATE	Set immediate mode.
 *  BIOCVERSION		Get filter language version.
 *  BIOCGHDRCMPLT	Get "header already complete" flag
 *  BIOCSHDRCMPLT	Set "header already complete" flag
 */
int
bpfioctl(dev_t dev, u_long cmd, caddr_t addr, int flag, struct proc *p)
{
	struct bpf_d *d;
	int s, error = 0;

	d = bpfilter_lookup(minor(dev));
	if (d->bd_locked && suser(p, 0) != 0) {
		/* list of allowed ioctls when locked and not root */
		switch (cmd) {
		case BIOCGBLEN:
		case BIOCFLUSH:
		case BIOCGDLT:
		case BIOCGDLTLIST:
		case BIOCGETIF:
		case BIOCGRTIMEOUT:
		case BIOCGSTATS:
		case BIOCVERSION:
		case BIOCGRSIG:
		case BIOCGHDRCMPLT:
		case FIONREAD:
		case BIOCLOCK:
		case BIOCSRTIMEOUT:
		case BIOCIMMEDIATE:
		case TIOCGPGRP:
		case BIOCGDIRFILT:
			break;
		default:
			return (EPERM);
		}
	}

	switch (cmd) {

	default:
		error = EINVAL;
		break;

	/*
	 * Check for read packet available.
	 */
	case FIONREAD:
		{
			int n;

			s = splnet();
			n = d->bd_slen;
			if (d->bd_hbuf)
				n += d->bd_hlen;
			splx(s);

			*(int *)addr = n;
			break;
		}

	/*
	 * Get buffer len [for read()].
	 */
	case BIOCGBLEN:
		*(u_int *)addr = d->bd_bufsize;
		break;

	/*
	 * Set buffer length.
	 */
	case BIOCSBLEN:
		if (d->bd_bif != NULL)
			error = EINVAL;
		else {
			u_int size = *(u_int *)addr;

			if (size > bpf_maxbufsize)
				*(u_int *)addr = size = bpf_maxbufsize;
			else if (size < BPF_MINBUFSIZE)
				*(u_int *)addr = size = BPF_MINBUFSIZE;
			d->bd_bufsize = size;
		}
		break;

	/*
	 * Set link layer read filter.
	 */
	case BIOCSETF:
		error = bpf_setf(d, (struct bpf_program *)addr, 0);
		break;

	/*
	 * Set link layer write filter.
	 */
	case BIOCSETWF:
		error = bpf_setf(d, (struct bpf_program *)addr, 1);
		break;

	/*
	 * Flush read packet buffer.
	 */
	case BIOCFLUSH:
		s = splnet();
		bpf_resetd(d);
		splx(s);
		break;

	/*
	 * Put interface into promiscuous mode.
	 */
	case BIOCPROMISC:
		if (d->bd_bif == NULL) {
			/*
			 * No interface attached yet.
			 */
			error = EINVAL;
			break;
		}
		s = splnet();
		if (d->bd_promisc == 0) {
			error = ifpromisc(d->bd_bif->bif_ifp, 1);
			if (error == 0)
				d->bd_promisc = 1;
		}
		splx(s);
		break;

	/*
	 * Get a list of supported device parameters.
	 */
	case BIOCGDLTLIST:
		if (d->bd_bif == NULL)
			error = EINVAL;
		else
			error = bpf_getdltlist(d, (struct bpf_dltlist *)addr);
		break;

	/*
	 * Get device parameters.
	 */
	case BIOCGDLT:
		if (d->bd_bif == NULL)
			error = EINVAL;
		else
			*(u_int *)addr = d->bd_bif->bif_dlt;
		break;

	/*
	 * Set device parameters.
	 */
	case BIOCSDLT:
		if (d->bd_bif == NULL)
			error = EINVAL;
		else
			error = bpf_setdlt(d, *(u_int *)addr);
		break;

	/*
	 * Set interface name.
	 */
	case BIOCGETIF:
		if (d->bd_bif == NULL)
			error = EINVAL;
		else
			bpf_ifname(d->bd_bif->bif_ifp, (struct ifreq *)addr);
		break;

	/*
	 * Set interface.
	 */
	case BIOCSETIF:
		error = bpf_setif(d, (struct ifreq *)addr);
		break;

	/*
	 * Set read timeout.
	 */
	case BIOCSRTIMEOUT:
		{
			struct timeval *tv = (struct timeval *)addr;

			/* Compute number of ticks. */
			d->bd_rtout = tv->tv_sec * hz + tv->tv_usec / tick;
			if (d->bd_rtout == 0 && tv->tv_usec != 0)
				d->bd_rtout = 1;
			break;
		}

	/*
	 * Get read timeout.
	 */
	case BIOCGRTIMEOUT:
		{
			struct timeval *tv = (struct timeval *)addr;

			tv->tv_sec = d->bd_rtout / hz;
			tv->tv_usec = (d->bd_rtout % hz) * tick;
			break;
		}

	/*
	 * Get packet stats.
	 */
	case BIOCGSTATS:
		{
			struct bpf_stat *bs = (struct bpf_stat *)addr;

			bs->bs_recv = d->bd_rcount;
			bs->bs_drop = d->bd_dcount;
			break;
		}

	/*
	 * Set immediate mode.
	 */
	case BIOCIMMEDIATE:
		d->bd_immediate = *(u_int *)addr;
		break;

	case BIOCVERSION:
		{
			struct bpf_version *bv = (struct bpf_version *)addr;

			bv->bv_major = BPF_MAJOR_VERSION;
			bv->bv_minor = BPF_MINOR_VERSION;
			break;
		}

	case BIOCGHDRCMPLT:	/* get "header already complete" flag */
		*(u_int *)addr = d->bd_hdrcmplt;
		break;

	case BIOCSHDRCMPLT:	/* set "header already complete" flag */
		d->bd_hdrcmplt = *(u_int *)addr ? 1 : 0;
		break;

	case BIOCLOCK:		/* set "locked" flag (no reset) */
		d->bd_locked = 1;
		break;

	case BIOCGFILDROP:	/* get "filter-drop" flag */
		*(u_int *)addr = d->bd_fildrop;
		break;

	case BIOCSFILDROP:	/* set "filter-drop" flag */
		d->bd_fildrop = *(u_int *)addr ? 1 : 0;
		break;

	case BIOCGDIRFILT:	/* get direction filter */
		*(u_int *)addr = d->bd_dirfilt;
		break;

	case BIOCSDIRFILT:	/* set direction filter */
		d->bd_dirfilt = (*(u_int *)addr) &
		    (BPF_DIRECTION_IN|BPF_DIRECTION_OUT);
		break;

	case FIONBIO:		/* Non-blocking I/O */
		if (*(int *)addr)
			d->bd_rtout = -1;
		else
			d->bd_rtout = 0;
		break;

	case FIOASYNC:		/* Send signal on receive packets */
		d->bd_async = *(int *)addr;
		break;

	/*
	 * N.B.  ioctl (FIOSETOWN) and fcntl (F_SETOWN) both end up doing
	 * the equivalent of a TIOCSPGRP and hence end up here.  *However*
	 * TIOCSPGRP's arg is a process group if it's positive and a process
	 * id if it's negative.  This is exactly the opposite of what the
	 * other two functions want!  Therefore there is code in ioctl and
	 * fcntl to negate the arg before calling here.
	 */
	case TIOCSPGRP:		/* Process or group to send signals to */
		d->bd_pgid = *(int *)addr;
		d->bd_siguid = p->p_ucred->cr_ruid;
		d->bd_sigeuid = p->p_ucred->cr_uid;
		break;

	case TIOCGPGRP:
		*(int *)addr = d->bd_pgid;
		break;

	case BIOCSRSIG:		/* Set receive signal */
		{
			u_int sig;

			sig = *(u_int *)addr;

			if (sig >= NSIG)
				error = EINVAL;
			else
				d->bd_sig = sig;
			break;
		}
	case BIOCGRSIG:
		*(u_int *)addr = d->bd_sig;
		break;
	}
	return (error);
}

/*
 * Set d's packet filter program to fp.  If this file already has a filter,
 * free it and replace it.  Returns EINVAL for bogus requests.
 */
int
bpf_setf(struct bpf_d *d, struct bpf_program *fp, int wf)
{
	struct bpf_program *bf;
	struct srp *filter;
	struct bpf_insn *fcode;
	u_int flen, size;
	int s;

	KERNEL_ASSERT_LOCKED();
	filter = wf ? &d->bd_wfilter : &d->bd_rfilter;

	if (fp->bf_insns == 0) {
		if (fp->bf_len != 0)
			return (EINVAL);
		srp_update_locked(&bpf_insn_gc, filter, NULL);
		s = splnet();
		bpf_resetd(d);
		splx(s);
		return (0);
	}
	flen = fp->bf_len;
	if (flen > BPF_MAXINSNS)
		return (EINVAL);

	fcode = mallocarray(flen, sizeof(*fp->bf_insns), M_DEVBUF,
	    M_WAITOK | M_CANFAIL);
	if (fcode == NULL)
		return (ENOMEM);

	size = flen * sizeof(*fp->bf_insns);
	if (copyin(fp->bf_insns, fcode, size) != 0 ||
	    bpf_validate(fcode, (int)flen) == 0) {
		free(fcode, M_DEVBUF, size);
		return (EINVAL);
	}

	bf = malloc(sizeof(*bf), M_DEVBUF, M_WAITOK);
	bf->bf_len = flen;
	bf->bf_insns = fcode;

	srp_update_locked(&bpf_insn_gc, filter, bf);

	s = splnet();
	bpf_resetd(d);
	splx(s);
	return (0);
}

/*
 * Detach a file from its current interface (if attached at all) and attach
 * to the interface indicated by the name stored in ifr.
 * Return an errno or 0.
 */
int
bpf_setif(struct bpf_d *d, struct ifreq *ifr)
{
	struct bpf_if *bp, *candidate = NULL;
	int error = 0;
	int s;

	/*
	 * Look through attached interfaces for the named one.
	 */
	for (bp = bpf_iflist; bp != NULL; bp = bp->bif_next) {
		struct ifnet *ifp = bp->bif_ifp;

		if (ifp == NULL ||
		    strcmp(ifp->if_xname, ifr->ifr_name) != 0)
			continue;

		if (candidate == NULL || candidate->bif_dlt > bp->bif_dlt)
			candidate = bp;
	}

	/* Not found. */
	if (candidate == NULL)
		return (ENXIO);

	/*
	 * Allocate the packet buffers if we need to.
	 * If we're already attached to requested interface,
	 * just flush the buffer.
	 */
	s = splnet();
	if (d->bd_sbuf == NULL) {
		if ((error = bpf_allocbufs(d)))
			goto out;
	}
	if (candidate != d->bd_bif) {
		/*
		 * Detach if attached to something else.
		 */
		bpf_detachd(d);
		bpf_attachd(d, candidate);
	}
	bpf_resetd(d);
out:
	splx(s);
	return (error);
}

/*
 * Copy the interface name to the ifreq.
 */
void
bpf_ifname(struct ifnet *ifp, struct ifreq *ifr)
{
	bcopy(ifp->if_xname, ifr->ifr_name, IFNAMSIZ);
}

/*
 * Support for poll() system call
 */
int
bpfpoll(dev_t dev, int events, struct proc *p)
{
	struct bpf_d *d;
	int s, revents;

	/*
	 * An imitation of the FIONREAD ioctl code.
	 */
	d = bpfilter_lookup(minor(dev));

	/*
	 * XXX The USB stack manages it to trigger some race condition
	 * which causes bpfilter_lookup to return NULL when a USB device
	 * gets detached while it is up and has an open bpf handler (e.g.
	 * dhclient).  We still should recheck if we can fix the root
	 * cause of this issue.
	 */
	if (d == NULL)
		return (POLLERR);

	/* Always ready to write data */
	revents = events & (POLLOUT | POLLWRNORM);

	if (events & (POLLIN | POLLRDNORM)) {
		s = splnet();
		if (d->bd_hlen != 0 || (d->bd_immediate && d->bd_slen != 0))
			revents |= events & (POLLIN | POLLRDNORM);
		else {
			/*
			 * if there's a timeout, mark the time we
			 * started waiting.
			 */
			if (d->bd_rtout != -1 && d->bd_rdStart == 0)
				d->bd_rdStart = ticks;
			selrecord(p, &d->bd_sel);
		}
		splx(s);
	}
	return (revents);
}

struct filterops bpfread_filtops =
	{ 1, NULL, filt_bpfrdetach, filt_bpfread };

int
bpfkqfilter(dev_t dev, struct knote *kn)
{
	struct bpf_d *d;
	struct klist *klist;
	int s;

	d = bpfilter_lookup(minor(dev));
	switch (kn->kn_filter) {
	case EVFILT_READ:
		klist = &d->bd_sel.si_note;
		kn->kn_fop = &bpfread_filtops;
		break;
	default:
		return (EINVAL);
	}

	kn->kn_hook = d;

	s = splnet();
	bpf_get(d);
	SLIST_INSERT_HEAD(klist, kn, kn_selnext);
	if (d->bd_rtout != -1 && d->bd_rdStart == 0)
		d->bd_rdStart = ticks;
	splx(s);

	return (0);
}

void
filt_bpfrdetach(struct knote *kn)
{
	struct bpf_d *d = kn->kn_hook;
	int s;

	s = splnet();
	SLIST_REMOVE(&d->bd_sel.si_note, kn, knote, kn_selnext);
	bpf_put(d);
	splx(s);
}

int
filt_bpfread(struct knote *kn, long hint)
{
	struct bpf_d *d = kn->kn_hook;

	kn->kn_data = d->bd_hlen;
	if (d->bd_immediate)
		kn->kn_data += d->bd_slen;
	return (kn->kn_data > 0);
}

/*
 * Copy data from an mbuf chain into a buffer.  This code is derived
 * from m_copydata in sys/uipc_mbuf.c.
 */
void
bpf_mcopy(const void *src_arg, void *dst_arg, size_t len)
{
	const struct mbuf *m;
	u_int count;
	u_char *dst;

	m = src_arg;
	dst = dst_arg;
	while (len > 0) {
		if (m == NULL)
			panic("bpf_mcopy");
		count = min(m->m_len, len);
		bcopy(mtod(m, caddr_t), (caddr_t)dst, count);
		m = m->m_next;
		dst += count;
		len -= count;
	}
}

/*
 * like bpf_mtap, but copy fn can be given. used by various bpf_mtap*
 */
int
_bpf_mtap(caddr_t arg, const struct mbuf *m, u_int direction,
    void (*cpfn)(const void *, void *, size_t))
{
	struct bpf_if *bp = (struct bpf_if *)arg;
	struct srp_ref sr;
	struct bpf_d *d;
	size_t pktlen, slen;
	const struct mbuf *m0;
	struct timeval tv;
	int gottime = 0;
	int drop = 0;
	int s;

	if (m == NULL)
		return (0);

	if (cpfn == NULL)
		cpfn = bpf_mcopy;

	if (bp == NULL)
		return (0);

	pktlen = 0;
	for (m0 = m; m0 != NULL; m0 = m0->m_next)
		pktlen += m0->m_len;

	SRPL_FOREACH(d, &sr, &bp->bif_dlist, bd_next) {
		atomic_inc_long(&d->bd_rcount);

		if ((direction & d->bd_dirfilt) != 0)
			slen = 0;
		else {
			struct srp_ref bsr;
			struct bpf_program *bf;
			struct bpf_insn *fcode = NULL;

			bf = srp_enter(&bsr, &d->bd_rfilter);
			if (bf != NULL)
				fcode = bf->bf_insns;
			slen = bpf_mfilter(fcode, m, pktlen);
			srp_leave(&bsr);
		}

		if (slen > 0) {
			if (!gottime++)
				microtime(&tv);

			KERNEL_LOCK();
			s = splnet();
			bpf_catchpacket(d, (u_char *)m, pktlen, slen, cpfn,
			    &tv);
			splx(s);
			KERNEL_UNLOCK();

			if (d->bd_fildrop)
				drop = 1;
		}
	}
	SRPL_LEAVE(&sr);

	return (drop);
}

/*
 * Incoming linkage from device drivers, when packet is in an mbuf chain.
 */
int
bpf_mtap(caddr_t arg, const struct mbuf *m, u_int direction)
{
	return _bpf_mtap(arg, m, direction, NULL);
}

/*
 * Incoming linkage from device drivers, where we have a mbuf chain
 * but need to prepend some arbitrary header from a linear buffer.
 *
 * Con up a minimal dummy header to pacify bpf.  Allocate (only) a
 * struct m_hdr on the stack.  This is safe as bpf only reads from the
 * fields in this header that we initialize, and will not try to free
 * it or keep a pointer to it.
 */
int
bpf_mtap_hdr(caddr_t arg, caddr_t data, u_int dlen, const struct mbuf *m,
    u_int direction, void (*cpfn)(const void *, void *, size_t))
{
	struct m_hdr mh;
	const struct mbuf *m0;

	if (dlen > 0) {
		mh.mh_flags = 0;
		mh.mh_next = (struct mbuf *)m;
		mh.mh_len = dlen;
		mh.mh_data = data;
		m0 = (struct mbuf *)&mh;
	} else 
		m0 = m;

	return _bpf_mtap(arg, m0, direction, cpfn);
}

/*
 * Incoming linkage from device drivers, where we have a mbuf chain
 * but need to prepend the address family.
 *
 * Con up a minimal dummy header to pacify bpf.  We allocate (only) a
 * struct m_hdr on the stack.  This is safe as bpf only reads from the
 * fields in this header that we initialize, and will not try to free
 * it or keep a pointer to it.
 */
int
bpf_mtap_af(caddr_t arg, u_int32_t af, const struct mbuf *m, u_int direction)
{
	u_int32_t    afh;

	afh = htonl(af);

	return bpf_mtap_hdr(arg, (caddr_t)&afh, sizeof(afh),
	    m, direction, NULL);
}

/*
 * Incoming linkage from device drivers, where we have a mbuf chain
 * but need to prepend a VLAN encapsulation header.
 *
 * Con up a minimal dummy header to pacify bpf.  Allocate (only) a
 * struct m_hdr on the stack.  This is safe as bpf only reads from the
 * fields in this header that we initialize, and will not try to free
 * it or keep a pointer to it.
 */
int
bpf_mtap_ether(caddr_t arg, const struct mbuf *m, u_int direction)
{
#if NVLAN > 0
	struct ether_vlan_header evh;
	struct m_hdr mh;
	uint8_t prio;

	if ((m->m_flags & M_VLANTAG) == 0)
#endif
	{
		return bpf_mtap(arg, m, direction);
	}

#if NVLAN > 0
	KASSERT(m->m_len >= ETHER_HDR_LEN);

	prio = m->m_pkthdr.pf.prio;
	if (prio <= 1)
		prio = !prio;

	memcpy(&evh, mtod(m, char *), ETHER_HDR_LEN);
	evh.evl_proto = evh.evl_encap_proto;
	evh.evl_encap_proto = htons(ETHERTYPE_VLAN);
	evh.evl_tag = htons(m->m_pkthdr.ether_vtag |
	    (prio << EVL_PRIO_BITS));

	mh.mh_flags = 0;
	mh.mh_data = m->m_data + ETHER_HDR_LEN;
	mh.mh_len = m->m_len - ETHER_HDR_LEN;
	mh.mh_next = m->m_next;

	return bpf_mtap_hdr(arg, (caddr_t)&evh, sizeof(evh),
	    (struct mbuf *)&mh, direction, NULL);
#endif
}

/*
 * Move the packet data from interface memory (pkt) into the
 * store buffer.  Wake up listeners if needed.
 * "copy" is the routine called to do the actual data
 * transfer.  bcopy is passed in to copy contiguous chunks, while
 * bpf_mcopy is passed in to copy mbuf chains.  In the latter case,
 * pkt is really an mbuf.
 */
void
bpf_catchpacket(struct bpf_d *d, u_char *pkt, size_t pktlen, size_t snaplen,
    void (*cpfn)(const void *, void *, size_t), struct timeval *tv)
{
	struct bpf_hdr *hp;
	int totlen, curlen;
	int hdrlen, do_wakeup = 0;

	if (d->bd_bif == NULL)
		return;

	hdrlen = d->bd_bif->bif_hdrlen;

	/*
	 * Figure out how many bytes to move.  If the packet is
	 * greater or equal to the snapshot length, transfer that
	 * much.  Otherwise, transfer the whole packet (unless
	 * we hit the buffer size limit).
	 */
	totlen = hdrlen + min(snaplen, pktlen);
	if (totlen > d->bd_bufsize)
		totlen = d->bd_bufsize;

	/*
	 * Round up the end of the previous packet to the next longword.
	 */
	curlen = BPF_WORDALIGN(d->bd_slen);
	if (curlen + totlen > d->bd_bufsize) {
		/*
		 * This packet will overflow the storage buffer.
		 * Rotate the buffers if we can, then wakeup any
		 * pending reads.
		 */
		if (d->bd_fbuf == NULL) {
			/*
			 * We haven't completed the previous read yet,
			 * so drop the packet.
			 */
			++d->bd_dcount;
			return;
		}
		ROTATE_BUFFERS(d);
		do_wakeup = 1;
		curlen = 0;
	}

	/*
	 * Append the bpf header.
	 */
	hp = (struct bpf_hdr *)(d->bd_sbuf + curlen);
	hp->bh_tstamp.tv_sec = tv->tv_sec;
	hp->bh_tstamp.tv_usec = tv->tv_usec;
	hp->bh_datalen = pktlen;
	hp->bh_hdrlen = hdrlen;
	/*
	 * Copy the packet data into the store buffer and update its length.
	 */
	(*cpfn)(pkt, (u_char *)hp + hdrlen, (hp->bh_caplen = totlen - hdrlen));
	d->bd_slen = curlen + totlen;

	if (d->bd_immediate) {
		/*
		 * Immediate mode is set.  A packet arrived so any
		 * reads should be woken up.
		 */
		do_wakeup = 1;
	}

	if (d->bd_rdStart && (d->bd_rtout + d->bd_rdStart < ticks)) {
		/*
		 * we could be selecting on the bpf, and we
		 * may have timeouts set.  We got here by getting
		 * a packet, so wake up the reader.
		 */
		if (d->bd_fbuf != NULL) {
			d->bd_rdStart = 0;
			ROTATE_BUFFERS(d);
			do_wakeup = 1;
		}
	}

	if (do_wakeup)
		bpf_wakeup(d);
}

/*
 * Initialize all nonzero fields of a descriptor.
 */
int
bpf_allocbufs(struct bpf_d *d)
{
	d->bd_fbuf = malloc(d->bd_bufsize, M_DEVBUF, M_NOWAIT);
	if (d->bd_fbuf == NULL)
		return (ENOMEM);

	d->bd_sbuf = malloc(d->bd_bufsize, M_DEVBUF, M_NOWAIT);
	if (d->bd_sbuf == NULL) {
		free(d->bd_fbuf, M_DEVBUF, d->bd_bufsize);
		return (ENOMEM);
	}

	d->bd_slen = 0;
	d->bd_hlen = 0;

	return (0);
}

void
bpf_get(struct bpf_d *bd)
{
	bd->bd_ref++;
}

/*
 * Free buffers currently in use by a descriptor
 * when the reference count drops to zero.
 */
void
bpf_put(struct bpf_d *bd)
{
	if (--bd->bd_ref > 0)
		return;

	free(bd->bd_sbuf, M_DEVBUF, 0);
	free(bd->bd_hbuf, M_DEVBUF, 0);
	free(bd->bd_fbuf, M_DEVBUF, 0);
	KERNEL_ASSERT_LOCKED();
	srp_update_locked(&bpf_insn_gc, &bd->bd_rfilter, NULL);
	srp_update_locked(&bpf_insn_gc, &bd->bd_wfilter, NULL);

	free(bd, M_DEVBUF, sizeof(*bd));
}

/*
 * Attach an interface to bpf.  driverp is a pointer to a (struct bpf_if *)
 * in the driver's softc; dlt is the link layer type; hdrlen is the fixed
 * size of the link header (variable length headers not yet supported).
 */
void
bpfattach(caddr_t *driverp, struct ifnet *ifp, u_int dlt, u_int hdrlen)
{
	struct bpf_if *bp;

	if ((bp = malloc(sizeof(*bp), M_DEVBUF, M_NOWAIT)) == NULL)
		panic("bpfattach");
	SRPL_INIT(&bp->bif_dlist);
	bp->bif_driverp = (struct bpf_if **)driverp;
	bp->bif_ifp = ifp;
	bp->bif_dlt = dlt;

	bp->bif_next = bpf_iflist;
	bpf_iflist = bp;

	*bp->bif_driverp = NULL;

	/*
	 * Compute the length of the bpf header.  This is not necessarily
	 * equal to SIZEOF_BPF_HDR because we want to insert spacing such
	 * that the network layer header begins on a longword boundary (for
	 * performance reasons and to alleviate alignment restrictions).
	 */
	bp->bif_hdrlen = BPF_WORDALIGN(hdrlen + SIZEOF_BPF_HDR) - hdrlen;
}

/* Detach an interface from its attached bpf device.  */
void
bpfdetach(struct ifnet *ifp)
{
	struct bpf_if *bp, *nbp, **pbp = &bpf_iflist;
	struct bpf_d *bd;
	int maj;

	KERNEL_ASSERT_LOCKED();

	for (bp = bpf_iflist; bp; bp = nbp) {
		nbp= bp->bif_next;
		if (bp->bif_ifp == ifp) {
			*pbp = nbp;

			/* Locate the major number. */
			for (maj = 0; maj < nchrdev; maj++)
				if (cdevsw[maj].d_open == bpfopen)
					break;

			while ((bd = SRPL_FIRST_LOCKED(&bp->bif_dlist)))
				vdevgone(maj, bd->bd_unit, bd->bd_unit, VCHR);

			free(bp, M_DEVBUF, sizeof *bp);
		} else
			pbp = &bp->bif_next;
	}
	ifp->if_bpf = NULL;
}

int
bpf_sysctl_locked(int *name, u_int namelen, void *oldp, size_t *oldlenp,
    void *newp, size_t newlen)
{
	int newval;
	int error;

	switch (name[0]) {
	case NET_BPF_BUFSIZE:
		newval = bpf_bufsize;
		error = sysctl_int(oldp, oldlenp, newp, newlen, &newval);
		if (error)
			return (error);
		if (newval < BPF_MINBUFSIZE || newval > bpf_maxbufsize)
			return (EINVAL);
		bpf_bufsize = newval;
		break;
	case NET_BPF_MAXBUFSIZE:
		newval = bpf_maxbufsize;
		error = sysctl_int(oldp, oldlenp, newp, newlen, &newval);
		if (error)
			return (error);
		if (newval < BPF_MINBUFSIZE)
			return (EINVAL);
		bpf_maxbufsize = newval;
		break;
	default:
		return (EOPNOTSUPP);
	}
	return (0);
}

int
bpf_sysctl(int *name, u_int namelen, void *oldp, size_t *oldlenp, void *newp,
    size_t newlen)
{
	static struct rwlock bpf_sysctl_lk = RWLOCK_INITIALIZER("bpfsz");
	int flags = RW_INTR;
	int error;

	if (namelen != 1)
		return (ENOTDIR);

	flags |= (newp == NULL) ? RW_READ : RW_WRITE;

	error = rw_enter(&bpf_sysctl_lk, flags);
	if (error != 0)
		return (error);

	error = bpf_sysctl_locked(name, namelen, oldp, oldlenp, newp, newlen);

	rw_exit(&bpf_sysctl_lk);

	return (error);
}

struct bpf_d *
bpfilter_lookup(int unit)
{
	struct bpf_d *bd;

	LIST_FOREACH(bd, &bpf_d_list, bd_list)
		if (bd->bd_unit == unit)
			return (bd);
	return (NULL);
}

/*
 * Get a list of available data link type of the interface.
 */
int
bpf_getdltlist(struct bpf_d *d, struct bpf_dltlist *bfl)
{
	int n, error;
	struct ifnet *ifp;
	struct bpf_if *bp;

	ifp = d->bd_bif->bif_ifp;
	n = 0;
	error = 0;
	for (bp = bpf_iflist; bp != NULL; bp = bp->bif_next) {
		if (bp->bif_ifp != ifp)
			continue;
		if (bfl->bfl_list != NULL) {
			if (n >= bfl->bfl_len)
				return (ENOMEM);
			error = copyout(&bp->bif_dlt,
			    bfl->bfl_list + n, sizeof(u_int));
			if (error)
				break;
		}
		n++;
	}

	bfl->bfl_len = n;
	return (error);
}

/*
 * Set the data link type of a BPF instance.
 */
int
bpf_setdlt(struct bpf_d *d, u_int dlt)
{
	int s;
	struct ifnet *ifp;
	struct bpf_if *bp;

	if (d->bd_bif->bif_dlt == dlt)
		return (0);
	ifp = d->bd_bif->bif_ifp;
	for (bp = bpf_iflist; bp != NULL; bp = bp->bif_next) {
		if (bp->bif_ifp == ifp && bp->bif_dlt == dlt)
			break;
	}
	if (bp == NULL)
		return (EINVAL);
	s = splnet();
	bpf_detachd(d);
	bpf_attachd(d, bp);
	bpf_resetd(d);
	splx(s);
	return (0);
}

void
bpf_d_ref(void *null, void *d)
{
	bpf_get(d);
}

void
bpf_d_unref(void *null, void *d)
{
	bpf_put(d);
}

void
bpf_insn_dtor(void *null, void *f)
{
	struct bpf_program *bf = f;
	struct bpf_insn *insns = bf->bf_insns;

	free(insns, M_DEVBUF, bf->bf_len * sizeof(*insns));
	free(bf, M_DEVBUF, sizeof(*bf));
}

u_int32_t	bpf_mbuf_ldw(const void *, u_int32_t, int *);
u_int32_t	bpf_mbuf_ldh(const void *, u_int32_t, int *);
u_int32_t	bpf_mbuf_ldb(const void *, u_int32_t, int *);

int		bpf_mbuf_copy(const struct mbuf *, u_int32_t,
		    void *, u_int32_t);

const struct bpf_ops bpf_mbuf_ops = {
	bpf_mbuf_ldw,
	bpf_mbuf_ldh,
	bpf_mbuf_ldb,
};

int
bpf_mbuf_copy(const struct mbuf *m, u_int32_t off, void *buf, u_int32_t len)
{
	u_int8_t *cp = buf;
	u_int32_t count;

	while (off >= m->m_len) {
		off -= m->m_len;

		m = m->m_next;
		if (m == NULL)
			return (-1);
	}

	for (;;) {
		count = min(m->m_len - off, len);
		
		memcpy(cp, m->m_data + off, count);
		len -= count;

		if (len == 0)
			return (0);

		m = m->m_next;
		if (m == NULL)
			break;

		cp += count;
		off = 0;
	}

	return (-1);
}

u_int32_t
bpf_mbuf_ldw(const void *m0, u_int32_t k, int *err)
{
	u_int32_t v;

	if (bpf_mbuf_copy(m0, k, &v, sizeof(v)) != 0) {
		*err = 1;
		return (0);
	}

	*err = 0;
	return ntohl(v);
}

u_int32_t
bpf_mbuf_ldh(const void *m0, u_int32_t k, int *err)
{
	u_int16_t v;

	if (bpf_mbuf_copy(m0, k, &v, sizeof(v)) != 0) {
		*err = 1;
		return (0);
	}

	*err = 0;
	return ntohs(v);
}

u_int32_t
bpf_mbuf_ldb(const void *m0, u_int32_t k, int *err)
{
	const struct mbuf *m = m0;

	while (k >= m->m_len) {
		k -= m->m_len;

		m = m->m_next;
		if (m == NULL) {
			*err = 1;
			return (0);
		}
	}

	*err = 0;
	return (m->m_data[k]);
}

u_int
bpf_mfilter(const struct bpf_insn *pc, const struct mbuf *m, u_int wirelen)
{
	return _bpf_filter(pc, &bpf_mbuf_ops, m, wirelen);
}