DragonFlyBSD Kernel Audit
sys/net/bpf.c
← back
   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
/*
 * Copyright (c) 1990, 1991, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * 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
 *
 * $FreeBSD: src/sys/net/bpf.c,v 1.59.2.12 2002/04/14 21:41:48 luigi Exp $
 */

#include "use_bpf.h"

#include <sys/param.h>
#include <sys/systm.h>
#include <sys/uio.h>
#include <sys/conf.h>
#include <sys/device.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/time.h>
#include <sys/proc.h>
#include <sys/signalvar.h>
#include <sys/filio.h>
#include <sys/sockio.h>
#include <sys/ttycom.h>
#include <sys/filedesc.h>

#include <sys/event.h>

#include <sys/socket.h>
#include <sys/vnode.h>

#include <net/if.h>
#include <net/bpf.h>
#include <net/bpfdesc.h>
#include <net/netmsg2.h>
#include <net/netisr2.h>

#include <netinet/in.h>
#include <netinet/if_ether.h>
#include <sys/kernel.h>
#include <sys/sysctl.h>

#include <netproto/802_11/ieee80211_dragonfly.h>

#include <sys/devfs.h>

MALLOC_DEFINE(M_BPF, "BPF", "BPF data");
DEVFS_DEFINE_CLONE_BITMAP(bpf);

#if NBPF <= 1
#define BPF_PREALLOCATED_UNITS	4
#else
#define BPF_PREALLOCATED_UNITS	NBPF
#endif

#if NBPF > 0

struct netmsg_bpf_output {
	struct netmsg_base base;
	struct mbuf	*nm_mbuf;
	struct ifnet	*nm_ifp;
	struct sockaddr	*nm_dst;
	boolean_t 	nm_feedback;
};

/*
 * The default read buffer size is patchable.
 */
static int bpf_bufsize = BPF_DEFAULTBUFSIZE;
SYSCTL_INT(_debug, OID_AUTO, bpf_bufsize, CTLFLAG_RW,
   &bpf_bufsize, 0, "Current size of bpf buffer");
int bpf_maxbufsize = BPF_MAXBUFSIZE;
SYSCTL_INT(_debug, OID_AUTO, bpf_maxbufsize, CTLFLAG_RW,
   &bpf_maxbufsize, 0, "Maximum size of bpf buffer");

/*
 *  bpf_iflist is the list of interfaces; each corresponds to an ifnet
 */
static struct bpf_if	*bpf_iflist;

static struct lwkt_token bpf_token = LWKT_TOKEN_INITIALIZER(bpf_token);

static int	bpf_allocbufs(struct bpf_d *);
static void	bpf_attachd(struct bpf_d *d, struct bpf_if *bp);
static void	bpf_detachd(struct bpf_d *d);
static void	bpf_resetd(struct bpf_d *);
static void	bpf_freed(struct bpf_d *);
static void	bpf_mcopy(volatile const void *, volatile void *, size_t);
static int	bpf_movein(struct uio *, int, struct mbuf **,
			   struct sockaddr *, int *, struct bpf_insn *);
static int	bpf_setif(struct bpf_d *, struct ifreq *);
static void	bpf_timed_out(void *);
static void	bpf_wakeup(struct bpf_d *);
static void	catchpacket(struct bpf_d *, u_char *, u_int, u_int,
			    void (*)(volatile const void *,
				     volatile void *, size_t),
			    const struct timeval *);
static int	bpf_setf(struct bpf_d *, struct bpf_program *, u_long cmd);
static int	bpf_getdltlist(struct bpf_d *, struct bpf_dltlist *);
static int	bpf_setdlt(struct bpf_d *, u_int);
static void	bpf_drvinit(void *unused);
static void	bpf_filter_detach(struct knote *kn);
static int	bpf_filter_read(struct knote *kn, long hint);

static d_open_t		bpfopen;
static d_clone_t	bpfclone;
static d_close_t	bpfclose;
static d_read_t		bpfread;
static d_write_t	bpfwrite;
static d_ioctl_t	bpfioctl;
static d_kqfilter_t	bpfkqfilter;

#define CDEV_MAJOR 23
static struct dev_ops bpf_ops = {
	{ "bpf", 0, D_MPSAFE },
	.d_open =	bpfopen,
	.d_close =	bpfclose,
	.d_read =	bpfread,
	.d_write =	bpfwrite,
	.d_ioctl =	bpfioctl,
	.d_kqfilter =	bpfkqfilter
};


static int
bpf_movein(struct uio *uio, int linktype, struct mbuf **mp,
	   struct sockaddr *sockp, int *datlen, struct bpf_insn *wfilter)
{
	const struct ieee80211_bpf_params *p;
	struct mbuf *m;
	int error;
	int len;
	int hlen;
	int slen;

	*datlen = 0;
	*mp = NULL;

	/*
	 * 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_EN10MB:
		sockp->sa_family = AF_UNSPEC;
		/* XXX Would MAXLINKHDR be better? */
		hlen = sizeof(struct ether_header);
		break;

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

	case DLT_ATM_RFC1483:
		/*
		 * en atm driver requires 4-byte atm pseudo header.
		 * though it isn't standard, vpi:vci needs to be
		 * specified anyway.
		 */
		sockp->sa_family = AF_UNSPEC;
		hlen = 12;	/* XXX 4(ATM_PH) + 3(LLC) + 5(SNAP) */
		break;

	case DLT_PPP:
		sockp->sa_family = AF_UNSPEC;
		hlen = 4;	/* This should match PPP_HDRLEN */
		break;

	case DLT_IEEE802_11:		/* IEEE 802.11 wireless */
		sockp->sa_family = AF_IEEE80211;
		hlen = 0;
		break;

	case DLT_IEEE802_11_RADIO:	/* IEEE 802.11 wireless w/ phy params */
		sockp->sa_family = AF_IEEE80211;
		sockp->sa_len = 12;	/* XXX != 0 */
		hlen = sizeof(struct ieee80211_bpf_params);
		break;

	default:
		return(EIO);
	}

	len = uio->uio_resid;
	*datlen = len - hlen;
	if ((unsigned)len > MCLBYTES)
		return(EIO);

	m = m_getl(len, M_WAITOK, MT_DATA, M_PKTHDR, NULL);
	m->m_pkthdr.len = m->m_len = len;
	m->m_pkthdr.rcvif = NULL;
	*mp = m;

	if (m->m_len < hlen) {
		error = EPERM;
		goto bad;
	}

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

	slen = bpf_filter(wfilter, mtod(m, u_char *), len, len);
	if (slen == 0) {
		error = EPERM;
		goto bad;
	}

	/*
	 * Make room for link header, and copy it to sockaddr.
	 */
	if (hlen != 0) {
		if (sockp->sa_family == AF_IEEE80211) {
			/*
			 * Collect true length from the parameter header
			 * NB: sockp is known to be zero'd so if we do a
			 *     short copy unspecified parameters will be
			 *     zero.
			 * NB: packet may not be aligned after stripping
			 *     bpf params
			 * XXX check ibp_vers
			 */
			p = mtod(m, const struct ieee80211_bpf_params *);
			hlen = p->ibp_len;
			if (hlen > sizeof(sockp->sa_data)) {
				error = EINVAL;
				goto bad;
			}
		}
		bcopy(m->m_data, sockp->sa_data, hlen);
		m->m_pkthdr.len -= hlen;
		m->m_len -= hlen;
		m->m_data += hlen; /* XXX */
	}
	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 splimp.
 */
static 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.
	 */
	lwkt_gettoken(&bpf_token);
	d->bd_bif = bp;
	SLIST_INSERT_HEAD(&bp->bif_dlist, d, bd_next);
	*bp->bif_driverp = bp;

	EVENTHANDLER_INVOKE(bpf_track, bp->bif_ifp, bp->bif_dlt, 1);
	lwkt_reltoken(&bpf_token);
}

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

	lwkt_gettoken(&bpf_token);
	bp = d->bd_bif;
	ifp = bp->bif_ifp;

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

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

	EVENTHANDLER_INVOKE(bpf_track, ifp, bp->bif_dlt, 0);

	/*
	 * Check if this descriptor had requested promiscuous mode.
	 * If so, turn it off.
	 */
	if (d->bd_promisc) {
		d->bd_promisc = 0;
		error = ifpromisc(ifp, 0);
		if (error != 0 && error != ENXIO) {
			/*
			 * ENXIO can happen if a pccard is unplugged,
			 * Something is really wrong if we were able to put
			 * the driver into promiscuous mode, but can't
			 * take it out.
			 */
			if_printf(ifp, "bpf_detach: ifpromisc failed(%d)\n",
				  error);
		}
	}
	lwkt_reltoken(&bpf_token);
}

/*
 * Open ethernet device.  Returns ENXIO for illegal minor device number,
 * EBUSY if file is open by another process.
 */
/* ARGSUSED */
static int
bpfopen(struct dev_open_args *ap)
{
	cdev_t dev = ap->a_head.a_dev;
	struct bpf_d *d;

	lwkt_gettoken(&bpf_token);
	if (ap->a_cred->cr_prison) {
		lwkt_reltoken(&bpf_token);
		return(EPERM);
	}

	d = dev->si_drv1;
	/*
	 * Each minor can be opened by only one process.  If the requested
	 * minor is in use, return EBUSY.
	 */
	if (d != NULL) {
		lwkt_reltoken(&bpf_token);
		return(EBUSY);
	}

	d = kmalloc(sizeof *d, M_BPF, M_WAITOK | M_ZERO);
	dev->si_drv1 = d;
	d->bd_bufsize = bpf_bufsize;
	d->bd_sig = SIGIO;
	d->bd_seesent = 1;
	d->bd_feedback = 0;
	callout_init(&d->bd_callout);
	lwkt_reltoken(&bpf_token);

	return(0);
}

static int
bpfclone(struct dev_clone_args *ap)
{
	int unit;

	unit = devfs_clone_bitmap_get(&DEVFS_CLONE_BITMAP(bpf), 0);
	ap->a_dev = make_only_dev(&bpf_ops, unit, 0, 0, 0600, "bpf%d", unit);

	return 0;
}

/*
 * Close the descriptor by detaching it from its interface,
 * deallocating its buffers, and marking it free.
 */
/* ARGSUSED */
static int
bpfclose(struct dev_close_args *ap)
{
	cdev_t dev = ap->a_head.a_dev;
	struct bpf_d *d = dev->si_drv1;
	int unit;

	lwkt_gettoken(&bpf_token);
	funsetown(&d->bd_sigio);
	if (d->bd_state == BPF_WAITING)
		callout_stop(&d->bd_callout);
	d->bd_state = BPF_IDLE;
	if (d->bd_bif != NULL)
		bpf_detachd(d);
	bpf_freed(d);
	dev->si_drv1 = NULL;

	unit = dev->si_uminor;
	if (unit >= BPF_PREALLOCATED_UNITS) {
		destroy_dev(dev);
		devfs_clone_bitmap_put(&DEVFS_CLONE_BITMAP(bpf), unit);
	}
	kfree(d, M_BPF);
	lwkt_reltoken(&bpf_token);

	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 = NULL;
/*
 *  bpfread - read next chunk of packets from buffers
 */
static int
bpfread(struct dev_read_args *ap)
{
	cdev_t dev = ap->a_head.a_dev;
	struct bpf_d *d = dev->si_drv1;
	int timed_out;
	int error;

	lwkt_gettoken(&bpf_token);
	/*
	 * Restrict application to use a buffer the same size as
	 * as kernel buffers.
	 */
	if (ap->a_uio->uio_resid != d->bd_bufsize) {
		lwkt_reltoken(&bpf_token);
		return(EINVAL);
	}

	if (d->bd_state == BPF_WAITING)
		callout_stop(&d->bd_callout);
	timed_out = (d->bd_state == BPF_TIMED_OUT);
	d->bd_state = BPF_IDLE;
	/*
	 * 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_immediate || (ap->a_ioflag & IO_NDELAY) || timed_out)
		    && d->bd_slen != 0) {
			/*
			 * A packet(s) either arrived since the previous,
			 * We're in immediate mode, or are reading
			 * in non-blocking mode, and 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;
		}

		/*
		 * No data is available, check to see if the bpf device
		 * is still pointed at a real interface.  If not, return
		 * ENXIO so that the userland process knows to rebind
		 * it before using it again.
		 */
		if (d->bd_bif == NULL) {
			lwkt_reltoken(&bpf_token);
			return(ENXIO);
		}

		if (ap->a_ioflag & IO_NDELAY) {
			lwkt_reltoken(&bpf_token);
			return(EWOULDBLOCK);
		}
		error = tsleep(d, PCATCH, "bpf", d->bd_rtout);
		if (error == EINTR || error == ERESTART) {
			lwkt_reltoken(&bpf_token);
			return(error);
		}
		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)
				/*
				 * 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) {
				lwkt_reltoken(&bpf_token);
				return(0);
			}
			ROTATE_BUFFERS(d);
			break;
		}
	}
	/*
	 * At this point, we know we have something in the hold slot.
	 */

	/*
	 * 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, ap->a_uio);

	d->bd_fbuf = d->bd_hbuf;
	d->bd_hbuf = NULL;
	d->bd_hlen = 0;
	lwkt_reltoken(&bpf_token);

	return(error);
}


/*
 * If there are processes sleeping on this descriptor, wake them up.
 */
static void
bpf_wakeup(struct bpf_d *d)
{
	if (d->bd_state == BPF_WAITING) {
		callout_stop(&d->bd_callout);
		d->bd_state = BPF_IDLE;
	}
	wakeup(d);
	if (d->bd_async && d->bd_sig && d->bd_sigio)
		pgsigio(d->bd_sigio, d->bd_sig, 0);

	KNOTE(&d->bd_kq.ki_note, 0);
}

static void
bpf_timed_out(void *arg)
{
	struct bpf_d *d = (struct bpf_d *)arg;

	if (d->bd_state == BPF_WAITING) {
		d->bd_state = BPF_TIMED_OUT;
		if (d->bd_slen != 0)
			bpf_wakeup(d);
	}
}

static void
bpf_output_dispatch(netmsg_t msg)
{
	struct netmsg_bpf_output *bmsg = (struct netmsg_bpf_output *)msg;
	struct ifnet *ifp = bmsg->nm_ifp;
	struct mbuf *mc = NULL;
	int error;

	if (bmsg->nm_feedback) {
		mc = m_dup(bmsg->nm_mbuf, M_NOWAIT);
		if (mc != NULL)
			mc->m_pkthdr.rcvif = ifp;
	}

	/*
	 * The driver frees the mbuf.
	 */
	error = ifp->if_output(ifp, bmsg->nm_mbuf, bmsg->nm_dst, NULL);
	lwkt_replymsg(&msg->lmsg, error);

	if (mc != NULL) {
		if (error == 0) {
			mc->m_flags &= ~M_HASH;
			(*ifp->if_input)(ifp, mc, NULL, -1);
		} else {
			m_freem(mc);
		}
	}
}

static int
bpfwrite(struct dev_write_args *ap)
{
	cdev_t dev = ap->a_head.a_dev;
	struct bpf_d *d = dev->si_drv1;
	struct ifnet *ifp;
	struct mbuf *m;
	int error, ret;
	struct sockaddr dst;
	int datlen;
	struct netmsg_bpf_output bmsg;

	lwkt_gettoken(&bpf_token);
	if (d->bd_bif == NULL) {
		lwkt_reltoken(&bpf_token);
		return(ENXIO);
	}

	ifp = d->bd_bif->bif_ifp;

	if (ap->a_uio->uio_resid == 0) {
		lwkt_reltoken(&bpf_token);
		return(0);
	}

	error = bpf_movein(ap->a_uio, (int)d->bd_bif->bif_dlt, &m,
			   &dst, &datlen, d->bd_wfilter);
	if (error) {
		lwkt_reltoken(&bpf_token);
		return(error);
	}

	if (datlen > ifp->if_mtu) {
		m_freem(m);
		lwkt_reltoken(&bpf_token);
		return(EMSGSIZE);
	}

	if (d->bd_hdrcmplt)
		dst.sa_family = pseudo_AF_HDRCMPLT;

	netmsg_init(&bmsg.base, NULL, &curthread->td_msgport,
		    0, bpf_output_dispatch);
	bmsg.nm_mbuf = m;
	bmsg.nm_ifp = ifp;
	bmsg.nm_dst = &dst;

	if (d->bd_feedback)
		bmsg.nm_feedback = TRUE;
	else
		bmsg.nm_feedback = FALSE;

	ret = lwkt_domsg(netisr_cpuport(0), &bmsg.base.lmsg, 0);

	lwkt_reltoken(&bpf_token);

	return ret;
}

/*
 * Reset a descriptor by flushing its packet buffer and clearing the
 * receive and drop counts.  Should be called at splimp.
 */
static 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.
 *  SIOCGIFADDR		Get interface address - convenient hook to driver.
 *  BIOCGBLEN		Get buffer len [for read()].
 *  BIOCSETF		Set ethernet read filter.
 *  BIOCSETWF		Set ethernet write filter.
 *  BIOCFLUSH		Flush read packet buffer.
 *  BIOCPROMISC		Put interface into promiscuous mode.
 *  BIOCGDLT		Get 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
 *  BIOCSFEEDBACK	Set packet feedback mode.
 *  BIOCGFEEDBACK	Get packet feedback mode.
 *  BIOCGSEESENT	Get "see packets sent" flag
 *  BIOCSSEESENT	Set "see packets sent" flag
 *  BIOCLOCK		Set "locked" flag
 */
/* ARGSUSED */
static int
bpfioctl(struct dev_ioctl_args *ap)
{
	cdev_t dev = ap->a_head.a_dev;
	struct bpf_d *d = dev->si_drv1;
	int error = 0;

	lwkt_gettoken(&bpf_token);
	if (d->bd_state == BPF_WAITING)
		callout_stop(&d->bd_callout);
	d->bd_state = BPF_IDLE;

	if (d->bd_locked == 1) {
		switch (ap->a_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:
			break;
		default:
			lwkt_reltoken(&bpf_token);
			return (EPERM);
		}
	}
	switch (ap->a_cmd) {
	default:
		error = EINVAL;
		break;

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

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

			*(int *)ap->a_data = n;
			break;
		}

	case SIOCGIFADDR:
		{
			struct ifnet *ifp;

			if (d->bd_bif == NULL) {
				error = EINVAL;
			} else {
				ifp = d->bd_bif->bif_ifp;
				ifnet_serialize_all(ifp);
				error = ifp->if_ioctl(ifp, ap->a_cmd,
						      ap->a_data, ap->a_cred);
				ifnet_deserialize_all(ifp);
			}
			break;
		}

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

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

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

	/*
	 * Set link layer read filter.
	 */
	case BIOCSETF:
	case BIOCSETWF:
		error = bpf_setf(d, (struct bpf_program *)ap->a_data,
			ap->a_cmd);
		break;

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

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

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

	/*
	 * Get a list of supported data link types.
	 */
	case BIOCGDLTLIST:
		if (d->bd_bif == NULL) {
			error = EINVAL;
		} else {
			error = bpf_getdltlist(d,
				(struct bpf_dltlist *)ap->a_data);
		}
		break;

	/*
	 * Set data link type.
	 */
	case BIOCSDLT:
		if (d->bd_bif == NULL)
			error = EINVAL;
		else
			error = bpf_setdlt(d, *(u_int *)ap->a_data);
		break;

	/*
	 * Get interface name.
	 */
	case BIOCGETIF:
		if (d->bd_bif == NULL) {
			error = EINVAL;
		} else {
			struct ifnet *const ifp = d->bd_bif->bif_ifp;
			struct ifreq *const ifr = (struct ifreq *)ap->a_data;

			strlcpy(ifr->ifr_name, ifp->if_xname,
				sizeof ifr->ifr_name);
		}
		break;

	/*
	 * Set interface.
	 */
	case BIOCSETIF:
		error = bpf_setif(d, (struct ifreq *)ap->a_data);
		break;

	/*
	 * Set read timeout.
	 */
	case BIOCSRTIMEOUT:
		{
			struct timeval *tv = (struct timeval *)ap->a_data;

			/*
			 * Subtract 1 tick from tvtohz() since this isn't
			 * a one-shot timer.
			 */
			if ((error = itimerfix(tv)) == 0)
				d->bd_rtout = tvtohz_low(tv);
			break;
		}

	/*
	 * Get read timeout.
	 */
	case BIOCGRTIMEOUT:
		{
			struct timeval *tv = (struct timeval *)ap->a_data;

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

	/*
	 * Get packet stats.
	 */
	case BIOCGSTATS:
		{
			struct bpf_stat *bs = (struct bpf_stat *)ap->a_data;

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

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

	case BIOCVERSION:
		{
			struct bpf_version *bv = (struct bpf_version *)ap->a_data;

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

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

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

	/*
	 * Get "see sent packets" flag
	 */
	case BIOCGSEESENT:
		*(u_int *)ap->a_data = d->bd_seesent;
		break;

	/*
	 * Set "see sent packets" flag
	 */
	case BIOCSSEESENT:
		d->bd_seesent = *(u_int *)ap->a_data;
		break;

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

	/*
	 * Set "feed packets from bpf back to input" mode
	 */
	case BIOCSFEEDBACK:
		d->bd_feedback = *(int *)ap->a_data;
		break;

	/*
	 * Get "feed packets from bpf back to input" mode
	 */
	case BIOCGFEEDBACK:
		*(u_int *)ap->a_data = d->bd_feedback;
		break;

	case FIOSETOWN:
		error = fsetown(*(int *)ap->a_data, &d->bd_sigio);
		break;

	case FIOGETOWN:
		*(int *)ap->a_data = fgetown(&d->bd_sigio);
		break;

	/* This is deprecated, FIOSETOWN should be used instead. */
	case TIOCSPGRP:
		error = fsetown(-(*(int *)ap->a_data), &d->bd_sigio);
		break;

	/* This is deprecated, FIOGETOWN should be used instead. */
	case TIOCGPGRP:
		*(int *)ap->a_data = -fgetown(&d->bd_sigio);
		break;

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

			sig = *(u_int *)ap->a_data;

			if (sig >= NSIG)
				error = EINVAL;
			else
				d->bd_sig = sig;
			break;
		}
	case BIOCGRSIG:
		*(u_int *)ap->a_data = d->bd_sig;
		break;
	case BIOCLOCK:
		d->bd_locked = 1;
		break;
	}
	lwkt_reltoken(&bpf_token);

	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.
 */
static int
bpf_setf(struct bpf_d *d, struct bpf_program *fp, u_long cmd)
{
	struct bpf_insn *fcode, *old;
	u_int wfilter, flen, size;

	if (cmd == BIOCSETWF) {
		old = d->bd_wfilter;
		wfilter = 1;
	} else {
		wfilter = 0;
		old = d->bd_rfilter;
	}
	if (fp->bf_insns == NULL) {
		if (fp->bf_len != 0)
			return(EINVAL);
		if (wfilter)
			d->bd_wfilter = NULL;
		else
			d->bd_rfilter = NULL;
		bpf_resetd(d);
		if (old != NULL)
			kfree(old, M_BPF);
		return(0);
	}
	flen = fp->bf_len;
	if (flen > BPF_MAXINSNS)
		return(EINVAL);

	size = flen * sizeof *fp->bf_insns;
	fcode = (struct bpf_insn *)kmalloc(size, M_BPF, M_WAITOK);
	if (copyin(fp->bf_insns, fcode, size) == 0 &&
	    bpf_validate(fcode, (int)flen)) {
		if (wfilter)
			d->bd_wfilter = fcode;
		else
			d->bd_rfilter = fcode;
		bpf_resetd(d);
		if (old != NULL)
			kfree(old, M_BPF);

		return(0);
	}
	kfree(fcode, M_BPF);
	return(EINVAL);
}

/*
 * 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.
 */
static int
bpf_setif(struct bpf_d *d, struct ifreq *ifr)
{
	struct bpf_if *bp;
	int error;
	struct ifnet *theywant;

	ifnet_lock();

	theywant = ifunit(ifr->ifr_name);
	if (theywant == NULL) {
		ifnet_unlock();
		return(ENXIO);
	}

	/*
	 * 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 || ifp != theywant)
			continue;
		/* skip additional entry */
		if (bp->bif_driverp != &ifp->if_bpf)
			continue;
		/*
		 * We found the requested interface.
		 * Allocate the packet buffers if we need to.
		 * If we're already attached to requested interface,
		 * just flush the buffer.
		 */
		if (d->bd_sbuf == NULL) {
			error = bpf_allocbufs(d);
			if (error != 0) {
				ifnet_unlock();
				return(error);
			}
		}
		if (bp != d->bd_bif) {
			if (d->bd_bif != NULL) {
				/*
				 * Detach if attached to something else.
				 */
				bpf_detachd(d);
			}

			bpf_attachd(d, bp);
		}
		bpf_resetd(d);

		ifnet_unlock();
		return(0);
	}

	ifnet_unlock();

	/* Not found. */
	return(ENXIO);
}

static struct filterops bpf_read_filtops =
	{ FILTEROP_ISFD, NULL, bpf_filter_detach, bpf_filter_read };

static int
bpfkqfilter(struct dev_kqfilter_args *ap)
{
	cdev_t dev = ap->a_head.a_dev;
	struct knote *kn = ap->a_kn;
	struct klist *klist;
	struct bpf_d *d;

	lwkt_gettoken(&bpf_token);
	d = dev->si_drv1;
	if (d->bd_bif == NULL) {
		ap->a_result = 1;
		lwkt_reltoken(&bpf_token);
		return (0);
	}

	ap->a_result = 0;
	switch (kn->kn_filter) {
	case EVFILT_READ:
		kn->kn_fop = &bpf_read_filtops;
		kn->kn_hook = (caddr_t)d;
		break;
	default:
		ap->a_result = EOPNOTSUPP;
		lwkt_reltoken(&bpf_token);
		return (0);
	}

	klist = &d->bd_kq.ki_note;
	knote_insert(klist, kn);
	lwkt_reltoken(&bpf_token);

	return (0);
}

static void
bpf_filter_detach(struct knote *kn)
{
	struct klist *klist;
	struct bpf_d *d;

	d = (struct bpf_d *)kn->kn_hook;
	klist = &d->bd_kq.ki_note;
	knote_remove(klist, kn);
}

static int
bpf_filter_read(struct knote *kn, long hint)
{
	struct bpf_d *d;
	int ready = 0;

	d = (struct bpf_d *)kn->kn_hook;
	if (d->bd_hlen != 0 ||
	    ((d->bd_immediate || d->bd_state == BPF_TIMED_OUT) &&
	    d->bd_slen != 0)) {
		ready = 1;
	} else {
		/* Start the read timeout if necessary. */
		if (d->bd_rtout > 0 && d->bd_state == BPF_IDLE) {
			callout_reset(&d->bd_callout, d->bd_rtout,
			    bpf_timed_out, d);
			d->bd_state = BPF_WAITING;
		}
	}

	return (ready);
}


/*
 * Process the packet pkt of length pktlen.  The packet is parsed
 * by each listener's filter, and if accepted, stashed into the
 * corresponding buffer.
 */
void
bpf_tap(struct bpf_if *bp, u_char *pkt, u_int pktlen)
{
	struct bpf_d *d;
	struct timeval tv;
	int gottime = 0;
	u_int slen;

	lwkt_gettoken(&bpf_token);
	/* Re-check */
	if (bp == NULL) {
		lwkt_reltoken(&bpf_token);
		return;
	}

	/*
	 * Note that the ipl does not have to be raised at this point.
	 * The only problem that could arise here is that if two different
	 * interfaces shared any data.  This is not the case.
	 */
	SLIST_FOREACH(d, &bp->bif_dlist, bd_next) {
		++d->bd_rcount;
		slen = bpf_filter(d->bd_rfilter, pkt, pktlen, pktlen);
		if (slen != 0) {
			if (!gottime) {
				microtime(&tv);
				gottime = 1;
			}
			catchpacket(d, pkt, pktlen, slen, _bcopy, &tv);
		}
	}
	lwkt_reltoken(&bpf_token);
}

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

/*
 * Process the packet in the mbuf chain m.  The packet is parsed by each
 * listener's filter, and if accepted, stashed into the corresponding
 * buffer.
 */
void
bpf_mtap(struct bpf_if *bp, struct mbuf *m)
{
	struct bpf_d *d;
	u_int pktlen, slen;
	struct timeval tv;
	int gottime = 0;

	lwkt_gettoken(&bpf_token);
	/* Re-check */
	if (bp == NULL) {
		lwkt_reltoken(&bpf_token);
		return;
	}

	/* Don't compute pktlen, if no descriptor is attached. */
	if (SLIST_EMPTY(&bp->bif_dlist)) {
		lwkt_reltoken(&bpf_token);
		return;
	}

	pktlen = m_lengthm(m, NULL);

	SLIST_FOREACH(d, &bp->bif_dlist, bd_next) {
		if (!d->bd_seesent && (m->m_pkthdr.rcvif == NULL))
			continue;
		++d->bd_rcount;
		slen = bpf_filter(d->bd_rfilter, (u_char *)m, pktlen, 0);
		if (slen != 0) {
			if (!gottime) {
				microtime(&tv);
				gottime = 1;
			}
			catchpacket(d, (u_char *)m, pktlen, slen, bpf_mcopy,
				    &tv);
		}
	}
	lwkt_reltoken(&bpf_token);
}

/*
 * 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.
 */
void
bpf_mtap_hdr(struct bpf_if *arg, caddr_t data, u_int dlen, struct mbuf *m,
    u_int direction)
{
	struct m_hdr mh;

	mh.mh_flags = 0;
	mh.mh_next = m;
	mh.mh_len = dlen;
	mh.mh_data = data;

	bpf_mtap(arg, (struct mbuf *) &mh);
}

void
bpf_mtap_family(struct bpf_if *bp, struct mbuf *m, sa_family_t family)
{
	u_int family4;

	KKASSERT(family != AF_UNSPEC);

	family4 = (u_int)family;
	bpf_ptap(bp, m, &family4, sizeof(family4));
}

/*
 * Process the packet in the mbuf chain m with the header in m prepended.
 * The packet is parsed by each listener's filter, and if accepted,
 * stashed into the corresponding buffer.
 */
void
bpf_ptap(struct bpf_if *bp, struct mbuf *m, const void *data, u_int dlen)
{
	struct mbuf mb;

	/*
	 * Craft on-stack mbuf suitable for passing to bpf_mtap.
	 * Note that we cut corners here; we only setup what's
	 * absolutely needed--this mbuf should never go anywhere else.
	 */
	mb.m_next = m;
	mb.m_data = __DECONST(void *, data); /* LINTED */
	mb.m_len = dlen;
	mb.m_pkthdr.rcvif = m->m_pkthdr.rcvif;

	bpf_mtap(bp, &mb);
}

/*
 * Move the packet data from interface memory (pkt) into the
 * store buffer.  Return 1 if it's time to wakeup a listener (buffer full),
 * otherwise 0.  "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.
 */
static void
catchpacket(struct bpf_d *d, u_char *pkt, u_int pktlen, u_int snaplen,
	    void (*cpfn)(volatile const void *, volatile void *, size_t),
	    const struct timeval *tv)
{
	struct bpf_hdr *hp;
	int totlen, curlen;
	int hdrlen = d->bd_bif->bif_hdrlen;
	int wakeup = 0;
	/*
	 * 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);
		wakeup = 1;
		curlen = 0;
	} else if (d->bd_immediate || d->bd_state == BPF_TIMED_OUT) {
		/*
		 * Immediate mode is set, or the read timeout has
		 * already expired during a select call.  A packet
		 * arrived, so the reader should be woken up.
		 */
		wakeup = 1;
	}

	/*
	 * Append the bpf header.
	 */
	hp = (struct bpf_hdr *)(d->bd_sbuf + curlen);
	hp->bh_tstamp = *tv;
	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 (wakeup)
		bpf_wakeup(d);
}

/*
 * Initialize all nonzero fields of a descriptor.
 */
static int
bpf_allocbufs(struct bpf_d *d)
{
	d->bd_fbuf = kmalloc(d->bd_bufsize, M_BPF, M_WAITOK);
	d->bd_sbuf = kmalloc(d->bd_bufsize, M_BPF, M_WAITOK);
	d->bd_slen = 0;
	d->bd_hlen = 0;
	return(0);
}

/*
 * Free buffers and packet filter program currently in use by a descriptor.
 * Called on close.
 */
static void
bpf_freed(struct bpf_d *d)
{
	/*
	 * We don't need to lock out interrupts since this descriptor has
	 * been detached from its interface and it yet hasn't been marked
	 * free.
	 */
	if (d->bd_sbuf != NULL) {
		kfree(d->bd_sbuf, M_BPF);
		if (d->bd_hbuf != NULL)
			kfree(d->bd_hbuf, M_BPF);
		if (d->bd_fbuf != NULL)
			kfree(d->bd_fbuf, M_BPF);
	}
	if (d->bd_rfilter)
		kfree(d->bd_rfilter, M_BPF);
	if (d->bd_wfilter)
		kfree(d->bd_wfilter, M_BPF);
}

/*
 * Attach an interface to bpf.  ifp is a pointer to the structure
 * defining the interface to be attached, dlt is the link layer type,
 * and hdrlen is the fixed size of the link header (variable length
 * headers are not yet supported).
 */
void
bpfattach(struct ifnet *ifp, u_int dlt, u_int hdrlen)
{
	bpfattach_dlt(ifp, dlt, hdrlen, &ifp->if_bpf);
}

void
bpfattach_dlt(struct ifnet *ifp, u_int dlt, u_int hdrlen, struct bpf_if **driverp)
{
	struct bpf_if *bp;

	bp = kmalloc(sizeof *bp, M_BPF, M_WAITOK | M_ZERO);

	lwkt_gettoken(&bpf_token);

	SLIST_INIT(&bp->bif_dlist);
	bp->bif_ifp = ifp;
	bp->bif_dlt = dlt;
	bp->bif_driverp = driverp;
	*bp->bif_driverp = NULL;

	bp->bif_next = bpf_iflist;
	bpf_iflist = bp;

	/*
	 * 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;

	lwkt_reltoken(&bpf_token);

	if (bootverbose)
		if_printf(ifp, "bpf attached\n");
}

/*
 * Detach bpf from an interface.  This involves detaching each descriptor
 * associated with the interface, and leaving bd_bif NULL.  Notify each
 * descriptor as it's detached so that any sleepers wake up and get
 * ENXIO.
 */
void
bpfdetach(struct ifnet *ifp)
{
	struct bpf_if *bp, *bp_prev;
	struct bpf_d *d;

	lwkt_gettoken(&bpf_token);

	/* Locate BPF interface information */
	bp_prev = NULL;
	for (bp = bpf_iflist; bp != NULL; bp = bp->bif_next) {
		if (ifp == bp->bif_ifp)
			break;
		bp_prev = bp;
	}

	/* Interface wasn't attached */
	if (bp->bif_ifp == NULL) {
		lwkt_reltoken(&bpf_token);
		kprintf("bpfdetach: %s was not attached\n", ifp->if_xname);
		return;
	}

	while ((d = SLIST_FIRST(&bp->bif_dlist)) != NULL) {
		bpf_detachd(d);
		bpf_wakeup(d);
	}

	if (bp_prev != NULL)
		bp_prev->bif_next = bp->bif_next;
	else
		bpf_iflist = bp->bif_next;

	kfree(bp, M_BPF);

	lwkt_reltoken(&bpf_token);
}

/*
 * Get a list of available data link type of the interface.
 */
static 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));
		}
		n++;
	}
	bfl->bfl_len = n;
	return(error);
}

/*
 * Set the data link type of a BPF instance.
 */
static int
bpf_setdlt(struct bpf_d *d, u_int dlt)
{
	int error, opromisc;
	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) {
		opromisc = d->bd_promisc;
		bpf_detachd(d);
		bpf_attachd(d, bp);
		bpf_resetd(d);
		if (opromisc) {
			error = ifpromisc(bp->bif_ifp, 1);
			if (error) {
				if_printf(bp->bif_ifp,
					"bpf_setdlt: ifpromisc failed (%d)\n",
					error);
			} else {
				d->bd_promisc = 1;
			}
		}
	}
	return(bp == NULL ? EINVAL : 0);
}

void
bpf_gettoken(void)
{
	lwkt_gettoken(&bpf_token);
}

void
bpf_reltoken(void)
{
	lwkt_reltoken(&bpf_token);
}

static void
bpf_drvinit(void *unused)
{
	int i;

	make_autoclone_dev(&bpf_ops, &DEVFS_CLONE_BITMAP(bpf),
		bpfclone, 0, 0, 0600, "bpf");
	for (i = 0; i < BPF_PREALLOCATED_UNITS; i++) {
		make_dev(&bpf_ops, i, 0, 0, 0600, "bpf%d", i);
		devfs_clone_bitmap_set(&DEVFS_CLONE_BITMAP(bpf), i);
	}
}

static void
bpf_drvuninit(void *unused)
{
	devfs_clone_handler_del("bpf");
	dev_ops_remove_all(&bpf_ops);
	devfs_clone_bitmap_uninit(&DEVFS_CLONE_BITMAP(bpf));
}

SYSINIT(bpfdev, SI_SUB_DRIVERS, SI_ORDER_MIDDLE+CDEV_MAJOR, bpf_drvinit, NULL);
SYSUNINIT(bpfdev, SI_SUB_DRIVERS,SI_ORDER_MIDDLE+CDEV_MAJOR,bpf_drvuninit, NULL);

#else /* !BPF */
/*
 * NOP stubs to allow bpf-using drivers to load and function.
 *
 * A 'better' implementation would allow the core bpf functionality
 * to be loaded at runtime.
 */

void
bpf_tap(struct bpf_if *bp, u_char *pkt, u_int pktlen)
{
}

void
bpf_mtap(struct bpf_if *bp, struct mbuf *m)
{
}

void
bpf_ptap(struct bpf_if *bp, struct mbuf *m, const void *data, u_int dlen)
{
}

void
bpfattach(struct ifnet *ifp, u_int dlt, u_int hdrlen)
{
}

void
bpfattach_dlt(struct ifnet *ifp, u_int dlt, u_int hdrlen, struct bpf_if **driverp)
{
}

void
bpfdetach(struct ifnet *ifp)
{
}

u_int
bpf_filter(const struct bpf_insn *pc, u_char *p, u_int wirelen, u_int buflen)
{
	return -1;	/* "no filter" behaviour */
}

void
bpf_gettoken(void)
{
}

void
bpf_reltoken(void)
{
}

#endif /* !BPF */