summaryrefslogtreecommitdiffstats
path: root/sys/net/bpf.c
blob: 5a2ab19160ee6da776e28d957c6455e3c6542b63 (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
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
/*-
 * 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.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *      @(#)bpf.c	8.4 (Berkeley) 1/9/95
 */

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

#include "opt_bpf.h"
#include "opt_netgraph.h"

#include <sys/types.h>
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/conf.h>
#include <sys/fcntl.h>
#include <sys/jail.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/time.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/signalvar.h>
#include <sys/filio.h>
#include <sys/sockio.h>
#include <sys/ttycom.h>
#include <sys/uio.h>
#include <sys/vimage.h>

#include <sys/event.h>
#include <sys/file.h>
#include <sys/poll.h>
#include <sys/proc.h>

#include <sys/socket.h>

#include <net/if.h>
#include <net/bpf.h>
#include <net/bpf_buffer.h>
#ifdef BPF_JITTER
#include <net/bpf_jitter.h>
#endif
#include <net/bpf_zerocopy.h>
#include <net/bpfdesc.h>

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

#include <net80211/ieee80211_freebsd.h>

#include <security/mac/mac_framework.h>

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

#if defined(DEV_BPF) || defined(NETGRAPH_BPF)

#define PRINET  26			/* interruptible */

/*
 * bpf_iflist is a list of BPF interface structures, each corresponding to a
 * specific DLT.  The same network interface might have several BPF interface
 * structures registered by different layers in the stack (i.e., 802.11
 * frames, ethernet frames, etc).
 */
static LIST_HEAD(, bpf_if)	bpf_iflist;
static struct mtx	bpf_mtx;		/* bpf global lock */
static int		bpf_bpfd_cnt;

static void	bpf_attachd(struct bpf_d *, struct bpf_if *);
static void	bpf_detachd(struct bpf_d *);
static void	bpf_freed(struct bpf_d *);
static int	bpf_movein(struct uio *, int, struct ifnet *, struct mbuf **,
		    struct sockaddr *, int *, struct bpf_insn *);
static int	bpf_setif(struct bpf_d *, struct ifreq *);
static void	bpf_timed_out(void *);
static __inline void
		bpf_wakeup(struct bpf_d *);
static void	catchpacket(struct bpf_d *, u_char *, u_int, u_int,
		    void (*)(struct bpf_d *, caddr_t, u_int, void *, u_int),
		    struct timeval *);
static void	reset_d(struct bpf_d *);
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	filt_bpfdetach(struct knote *);
static int	filt_bpfread(struct knote *, long);
static void	bpf_drvinit(void *);
static int	bpf_stats_sysctl(SYSCTL_HANDLER_ARGS);

SYSCTL_NODE(_net, OID_AUTO, bpf, CTLFLAG_RW, 0, "bpf sysctl");
int bpf_maxinsns = BPF_MAXINSNS;
SYSCTL_INT(_net_bpf, OID_AUTO, maxinsns, CTLFLAG_RW,
    &bpf_maxinsns, 0, "Maximum bpf program instructions");
static int bpf_zerocopy_enable = 0;
SYSCTL_INT(_net_bpf, OID_AUTO, zerocopy_enable, CTLFLAG_RW,
    &bpf_zerocopy_enable, 0, "Enable new zero-copy BPF buffer sessions");
SYSCTL_NODE(_net_bpf, OID_AUTO, stats, CTLFLAG_MPSAFE | CTLFLAG_RW,
    bpf_stats_sysctl, "bpf statistics portal");

static	d_open_t	bpfopen;
static	d_read_t	bpfread;
static	d_write_t	bpfwrite;
static	d_ioctl_t	bpfioctl;
static	d_poll_t	bpfpoll;
static	d_kqfilter_t	bpfkqfilter;

static struct cdevsw bpf_cdevsw = {
	.d_version =	D_VERSION,
	.d_open =	bpfopen,
	.d_read =	bpfread,
	.d_write =	bpfwrite,
	.d_ioctl =	bpfioctl,
	.d_poll =	bpfpoll,
	.d_name =	"bpf",
	.d_kqfilter =	bpfkqfilter,
};

static struct filterops bpfread_filtops =
	{ 1, NULL, filt_bpfdetach, filt_bpfread };

/*
 * Wrapper functions for various buffering methods.  If the set of buffer
 * modes expands, we will probably want to introduce a switch data structure
 * similar to protosw, et.
 */
static void
bpf_append_bytes(struct bpf_d *d, caddr_t buf, u_int offset, void *src,
    u_int len)
{

	BPFD_LOCK_ASSERT(d);

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_BUFFER:
		return (bpf_buffer_append_bytes(d, buf, offset, src, len));

	case BPF_BUFMODE_ZBUF:
		d->bd_zcopy++;
		return (bpf_zerocopy_append_bytes(d, buf, offset, src, len));

	default:
		panic("bpf_buf_append_bytes");
	}
}

static void
bpf_append_mbuf(struct bpf_d *d, caddr_t buf, u_int offset, void *src,
    u_int len)
{

	BPFD_LOCK_ASSERT(d);

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_BUFFER:
		return (bpf_buffer_append_mbuf(d, buf, offset, src, len));

	case BPF_BUFMODE_ZBUF:
		d->bd_zcopy++;
		return (bpf_zerocopy_append_mbuf(d, buf, offset, src, len));

	default:
		panic("bpf_buf_append_mbuf");
	}
}

/*
 * This function gets called when the free buffer is re-assigned.
 */
static void
bpf_buf_reclaimed(struct bpf_d *d)
{

	BPFD_LOCK_ASSERT(d);

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_BUFFER:
		return;

	case BPF_BUFMODE_ZBUF:
		bpf_zerocopy_buf_reclaimed(d);
		return;

	default:
		panic("bpf_buf_reclaimed");
	}
}

/*
 * If the buffer mechanism has a way to decide that a held buffer can be made
 * free, then it is exposed via the bpf_canfreebuf() interface.  (1) is
 * returned if the buffer can be discarded, (0) is returned if it cannot.
 */
static int
bpf_canfreebuf(struct bpf_d *d)
{

	BPFD_LOCK_ASSERT(d);

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_ZBUF:
		return (bpf_zerocopy_canfreebuf(d));
	}
	return (0);
}

/*
 * Allow the buffer model to indicate that the current store buffer is
 * immutable, regardless of the appearance of space.  Return (1) if the
 * buffer is writable, and (0) if not.
 */
static int
bpf_canwritebuf(struct bpf_d *d)
{

	BPFD_LOCK_ASSERT(d);

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_ZBUF:
		return (bpf_zerocopy_canwritebuf(d));
	}
	return (1);
}

/*
 * Notify buffer model that an attempt to write to the store buffer has
 * resulted in a dropped packet, in which case the buffer may be considered
 * full.
 */
static void
bpf_buffull(struct bpf_d *d)
{

	BPFD_LOCK_ASSERT(d);

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_ZBUF:
		bpf_zerocopy_buffull(d);
		break;
	}
}

/*
 * Notify the buffer model that a buffer has moved into the hold position.
 */
void
bpf_bufheld(struct bpf_d *d)
{

	BPFD_LOCK_ASSERT(d);

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_ZBUF:
		bpf_zerocopy_bufheld(d);
		break;
	}
}

static void
bpf_free(struct bpf_d *d)
{

	switch (d->bd_bufmode) {
	case BPF_BUFMODE_BUFFER:
		return (bpf_buffer_free(d));

	case BPF_BUFMODE_ZBUF:
		return (bpf_zerocopy_free(d));

	default:
		panic("bpf_buf_free");
	}
}

static int
bpf_uiomove(struct bpf_d *d, caddr_t buf, u_int len, struct uio *uio)
{

	if (d->bd_bufmode != BPF_BUFMODE_BUFFER)
		return (EOPNOTSUPP);
	return (bpf_buffer_uiomove(d, buf, len, uio));
}

static int
bpf_ioctl_sblen(struct bpf_d *d, u_int *i)
{

	if (d->bd_bufmode != BPF_BUFMODE_BUFFER)
		return (EOPNOTSUPP);
	return (bpf_buffer_ioctl_sblen(d, i));
}

static int
bpf_ioctl_getzmax(struct thread *td, struct bpf_d *d, size_t *i)
{

	if (d->bd_bufmode != BPF_BUFMODE_ZBUF)
		return (EOPNOTSUPP);
	return (bpf_zerocopy_ioctl_getzmax(td, d, i));
}

static int
bpf_ioctl_rotzbuf(struct thread *td, struct bpf_d *d, struct bpf_zbuf *bz)
{

	if (d->bd_bufmode != BPF_BUFMODE_ZBUF)
		return (EOPNOTSUPP);
	return (bpf_zerocopy_ioctl_rotzbuf(td, d, bz));
}

static int
bpf_ioctl_setzbuf(struct thread *td, struct bpf_d *d, struct bpf_zbuf *bz)
{

	if (d->bd_bufmode != BPF_BUFMODE_ZBUF)
		return (EOPNOTSUPP);
	return (bpf_zerocopy_ioctl_setzbuf(td, d, bz));
}

/*
 * General BPF functions.
 */
static int
bpf_movein(struct uio *uio, int linktype, struct ifnet *ifp, struct mbuf **mp,
    struct sockaddr *sockp, int *hdrlen, struct bpf_insn *wfilter)
{
	const struct ieee80211_bpf_params *p;
	struct ether_header *eh;
	struct mbuf *m;
	int error;
	int len;
	int hlen;
	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_EN10MB:
		sockp->sa_family = AF_UNSPEC;
		/* XXX Would MAXLINKHDR be better? */
		hlen = ETHER_HDR_LEN;
		break;

	case DLT_FDDI:
		sockp->sa_family = AF_IMPLINK;
		hlen = 0;
		break;

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

	case DLT_NULL:
		/*
		 * null interface types require a 4 byte pseudo header which
		 * corresponds to the address family of the packet.
		 */
		sockp->sa_family = AF_UNSPEC;
		hlen = 4;
		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;

	if (len - hlen > ifp->if_mtu)
		return (EMSGSIZE);

	if ((unsigned)len > MJUM16BYTES)
		return (EIO);

	if (len <= MHLEN)
		MGETHDR(m, M_WAIT, MT_DATA);
	else if (len <= MCLBYTES)
		m = m_getcl(M_WAIT, MT_DATA, M_PKTHDR);
	else
		m = m_getjcl(M_WAIT, MT_DATA, M_PKTHDR,
#if (MJUMPAGESIZE > MCLBYTES)
		    len <= MJUMPAGESIZE ? MJUMPAGESIZE :
#endif
		    (len <= MJUM9BYTES ? MJUM9BYTES : MJUM16BYTES));
	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;
	}

	/* Check for multicast destination */
	switch (linktype) {
	case DLT_EN10MB:
		eh = mtod(m, struct ether_header *);
		if (ETHER_IS_MULTICAST(eh->ether_dhost)) {
			if (bcmp(ifp->if_broadcastaddr, eh->ether_dhost,
			    ETHER_ADDR_LEN) == 0)
				m->m_flags |= M_BCAST;
			else
				m->m_flags |= M_MCAST;
		}
		break;
	}

	/*
	 * 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);
	}
	*hdrlen = hlen;

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

/*
 * Attach file to the bpf interface, i.e. make d listen on bp.
 */
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.
	 */
	BPFIF_LOCK(bp);
	d->bd_bif = bp;
	LIST_INSERT_HEAD(&bp->bif_dlist, d, bd_next);

	bpf_bpfd_cnt++;
	BPFIF_UNLOCK(bp);

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

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

	bp = d->bd_bif;
	BPFIF_LOCK(bp);
	BPFD_LOCK(d);
	ifp = d->bd_bif->bif_ifp;

	/*
	 * Remove d from the interface's descriptor list.
	 */
	LIST_REMOVE(d, bd_next);

	bpf_bpfd_cnt--;
	d->bd_bif = NULL;
	BPFD_UNLOCK(d);
	BPFIF_UNLOCK(bp);

	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;
		CURVNET_SET(ifp->if_vnet);
		error = ifpromisc(ifp, 0);
		CURVNET_RESTORE();
		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(bp->bif_ifp,
				"bpf_detach: ifpromisc failed (%d)\n", error);
		}
	}
}

/*
 * Close the descriptor by detaching it from its interface,
 * deallocating its buffers, and marking it free.
 */
static void
bpf_dtor(void *data)
{
	struct bpf_d *d = data;

	BPFD_LOCK(d);
	if (d->bd_state == BPF_WAITING)
		callout_stop(&d->bd_callout);
	d->bd_state = BPF_IDLE;
	BPFD_UNLOCK(d);
	funsetown(&d->bd_sigio);
	mtx_lock(&bpf_mtx);
	if (d->bd_bif)
		bpf_detachd(d);
	mtx_unlock(&bpf_mtx);
	selwakeuppri(&d->bd_sel, PRINET);
#ifdef MAC
	mac_bpfdesc_destroy(d);
#endif /* MAC */
	knlist_destroy(&d->bd_sel.si_note);
	bpf_freed(d);
	free(d, M_BPF);
}

/*
 * Open ethernet device.  Returns ENXIO for illegal minor device number,
 * EBUSY if file is open by another process.
 */
/* ARGSUSED */
static	int
bpfopen(struct cdev *dev, int flags, int fmt, struct thread *td)
{
	struct bpf_d *d;
	int error;

	d = malloc(sizeof(*d), M_BPF, M_WAITOK | M_ZERO);
	error = devfs_set_cdevpriv(d, bpf_dtor);
	if (error != 0) {
		free(d, M_BPF);
		return (error);
	}

	/*
	 * For historical reasons, perform a one-time initialization call to
	 * the buffer routines, even though we're not yet committed to a
	 * particular buffer method.
	 */
	bpf_buffer_init(d);
	d->bd_bufmode = BPF_BUFMODE_BUFFER;
	d->bd_sig = SIGIO;
	d->bd_direction = BPF_D_INOUT;
	d->bd_pid = td->td_proc->p_pid;
#ifdef MAC
	mac_bpfdesc_init(d);
	mac_bpfdesc_create(td->td_ucred, d);
#endif
	mtx_init(&d->bd_mtx, devtoname(dev), "bpf cdev lock", MTX_DEF);
	callout_init(&d->bd_callout, CALLOUT_MPSAFE);
	knlist_init_mtx(&d->bd_sel.si_note, &d->bd_mtx);

	return (0);
}

/*
 *  bpfread - read next chunk of packets from buffers
 */
static	int
bpfread(struct cdev *dev, struct uio *uio, int ioflag)
{
	struct bpf_d *d;
	int timed_out;
	int error;

	error = devfs_get_cdevpriv((void **)&d);
	if (error != 0)
		return (error);

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

	BPFD_LOCK(d);
	d->bd_pid = curthread->td_proc->p_pid;
	if (d->bd_bufmode != BPF_BUFMODE_BUFFER) {
		BPFD_UNLOCK(d);
		return (EOPNOTSUPP);
	}
	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 || timed_out) && 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;
		}

		/*
		 * 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) {
			BPFD_UNLOCK(d);
			return (ENXIO);
		}

		if (ioflag & O_NONBLOCK) {
			BPFD_UNLOCK(d);
			return (EWOULDBLOCK);
		}
		error = msleep(d, &d->bd_mtx, PRINET|PCATCH,
		     "bpf", d->bd_rtout);
		if (error == EINTR || error == ERESTART) {
			BPFD_UNLOCK(d);
			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) {
				BPFD_UNLOCK(d);
				return (0);
			}
			ROTATE_BUFFERS(d);
			break;
		}
	}
	/*
	 * At this point, we know we have something in the hold slot.
	 */
	BPFD_UNLOCK(d);

	/*
	 * 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.
	 *
	 * XXXRW: More synchronization needed here: what if a second thread
	 * issues a read on the same fd at the same time?  Don't want this
	 * getting invalidated.
	 */
	error = bpf_uiomove(d, d->bd_hbuf, d->bd_hlen, uio);

	BPFD_LOCK(d);
	d->bd_fbuf = d->bd_hbuf;
	d->bd_hbuf = NULL;
	d->bd_hlen = 0;
	bpf_buf_reclaimed(d);
	BPFD_UNLOCK(d);

	return (error);
}

/*
 * If there are processes sleeping on this descriptor, wake them up.
 */
static __inline void
bpf_wakeup(struct bpf_d *d)
{

	BPFD_LOCK_ASSERT(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);

	selwakeuppri(&d->bd_sel, PRINET);
	KNOTE_LOCKED(&d->bd_sel.si_note, 0);
}

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

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

static int
bpf_ready(struct bpf_d *d)
{

	BPFD_LOCK_ASSERT(d);

	if (!bpf_canfreebuf(d) && d->bd_hlen != 0)
		return (1);
	if ((d->bd_immediate || d->bd_state == BPF_TIMED_OUT) &&
	    d->bd_slen != 0)
		return (1);
	return (0);
}

static int
bpfwrite(struct cdev *dev, struct uio *uio, int ioflag)
{
	struct bpf_d *d;
	struct ifnet *ifp;
	struct mbuf *m, *mc;
	struct sockaddr dst;
	int error, hlen;

	error = devfs_get_cdevpriv((void **)&d);
	if (error != 0)
		return (error);

	d->bd_pid = curthread->td_proc->p_pid;
	d->bd_wcount++;
	if (d->bd_bif == NULL) {
		d->bd_wdcount++;
		return (ENXIO);
	}

	ifp = d->bd_bif->bif_ifp;

	if ((ifp->if_flags & IFF_UP) == 0) {
		d->bd_wdcount++;
		return (ENETDOWN);
	}

	if (uio->uio_resid == 0) {
		d->bd_wdcount++;
		return (0);
	}

	bzero(&dst, sizeof(dst));
	m = NULL;
	hlen = 0;
	error = bpf_movein(uio, (int)d->bd_bif->bif_dlt, ifp,
	    &m, &dst, &hlen, d->bd_wfilter);
	if (error) {
		d->bd_wdcount++;
		return (error);
	}
	d->bd_wfcount++;
	if (d->bd_hdrcmplt)
		dst.sa_family = pseudo_AF_HDRCMPLT;

	if (d->bd_feedback) {
		mc = m_dup(m, M_DONTWAIT);
		if (mc != NULL)
			mc->m_pkthdr.rcvif = ifp;
		/* Set M_PROMISC for outgoing packets to be discarded. */
		if (d->bd_direction == BPF_D_INOUT)
			m->m_flags |= M_PROMISC;
	} else
		mc = NULL;

	m->m_pkthdr.len -= hlen;
	m->m_len -= hlen;
	m->m_data += hlen;	/* XXX */

	CURVNET_SET(ifp->if_vnet);
#ifdef MAC
	BPFD_LOCK(d);
	mac_bpfdesc_create_mbuf(d, m);
	if (mc != NULL)
		mac_bpfdesc_create_mbuf(d, mc);
	BPFD_UNLOCK(d);
#endif

	error = (*ifp->if_output)(ifp, m, &dst, NULL);
	if (error)
		d->bd_wdcount++;

	if (mc != NULL) {
		if (error == 0)
			(*ifp->if_input)(ifp, mc);
		else
			m_freem(mc);
	}
	CURVNET_RESTORE();

	return (error);
}

/*
 * Reset a descriptor by flushing its packet buffer and clearing the receive
 * and drop counts.  This is doable for kernel-only buffers, but with
 * zero-copy buffers, we can't write to (or rotate) buffers that are
 * currently owned by userspace.  It would be nice if we could encapsulate
 * this logic in the buffer code rather than here.
 */
static void
reset_d(struct bpf_d *d)
{

	mtx_assert(&d->bd_mtx, MA_OWNED);

	if ((d->bd_hbuf != NULL) &&
	    (d->bd_bufmode != BPF_BUFMODE_ZBUF || bpf_canfreebuf(d))) {
		/* Free the hold buffer. */
		d->bd_fbuf = d->bd_hbuf;
		d->bd_hbuf = NULL;
		d->bd_hlen = 0;
		bpf_buf_reclaimed(d);
	}
	if (bpf_canwritebuf(d))
		d->bd_slen = 0;
	d->bd_rcount = 0;
	d->bd_dcount = 0;
	d->bd_fcount = 0;
	d->bd_wcount = 0;
	d->bd_wfcount = 0;
	d->bd_wdcount = 0;
	d->bd_zcopy = 0;
}

/*
 *  FIONREAD		Check for read packet available.
 *  SIOCGIFADDR		Get interface address - convenient hook to driver.
 *  BIOCGBLEN		Get buffer len [for read()].
 *  BIOCSETF		Set read filter.
 *  BIOCSETFNR		Set read filter without resetting descriptor.
 *  BIOCSETWF		Set 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
 *  BIOCGDIRECTION	Get packet direction flag
 *  BIOCSDIRECTION	Set packet direction flag
 *  BIOCLOCK		Set "locked" flag
 *  BIOCFEEDBACK	Set packet feedback mode.
 *  BIOCSETZBUF		Set current zero-copy buffer locations.
 *  BIOCGETZMAX		Get maximum zero-copy buffer size.
 *  BIOCROTZBUF		Force rotation of zero-copy buffer
 *  BIOCSETBUFMODE	Set buffer mode.
 *  BIOCGETBUFMODE	Get current buffer mode.
 */
/* ARGSUSED */
static	int
bpfioctl(struct cdev *dev, u_long cmd, caddr_t addr, int flags,
    struct thread *td)
{
	struct bpf_d *d;
	int error;

	error = devfs_get_cdevpriv((void **)&d);
	if (error != 0)
		return (error);

	/*
	 * Refresh PID associated with this descriptor.
	 */
	BPFD_LOCK(d);
	d->bd_pid = td->td_proc->p_pid;
	if (d->bd_state == BPF_WAITING)
		callout_stop(&d->bd_callout);
	d->bd_state = BPF_IDLE;
	BPFD_UNLOCK(d);

	if (d->bd_locked == 1) {
		switch (cmd) {
		case BIOCGBLEN:
		case BIOCFLUSH:
		case BIOCGDLT:
		case BIOCGDLTLIST:
		case BIOCGETIF:
		case BIOCGRTIMEOUT:
		case BIOCGSTATS:
		case BIOCVERSION:
		case BIOCGRSIG:
		case BIOCGHDRCMPLT:
		case BIOCFEEDBACK:
		case FIONREAD:
		case BIOCLOCK:
		case BIOCSRTIMEOUT:
		case BIOCIMMEDIATE:
		case TIOCGPGRP:
		case BIOCROTZBUF:
			break;
		default:
			return (EPERM);
		}
	}
	CURVNET_SET(TD_TO_VNET(td));
	switch (cmd) {

	default:
		error = EINVAL;
		break;

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

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

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

	case SIOCGIFADDR:
		{
			struct ifnet *ifp;

			if (d->bd_bif == NULL)
				error = EINVAL;
			else {
				ifp = d->bd_bif->bif_ifp;
				error = (*ifp->if_ioctl)(ifp, cmd, addr);
			}
			break;
		}

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

	/*
	 * Set buffer length.
	 */
	case BIOCSBLEN:
		error = bpf_ioctl_sblen(d, (u_int *)addr);
		break;

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

	/*
	 * Flush read packet buffer.
	 */
	case BIOCFLUSH:
		BPFD_LOCK(d);
		reset_d(d);
		BPFD_UNLOCK(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 current data link type.
	 */
	case BIOCGDLT:
		if (d->bd_bif == NULL)
			error = EINVAL;
		else
			*(u_int *)addr = 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 *)addr);
		break;

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

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

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

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

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

			/* XXXCSJP overflow */
			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;
		}

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

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

	/*
	 * Get packet direction flag
	 */
	case BIOCGDIRECTION:
		*(u_int *)addr = d->bd_direction;
		break;

	/*
	 * Set packet direction flag
	 */
	case BIOCSDIRECTION:
		{
			u_int	direction;

			direction = *(u_int *)addr;
			switch (direction) {
			case BPF_D_IN:
			case BPF_D_INOUT:
			case BPF_D_OUT:
				d->bd_direction = direction;
				break;
			default:
				error = EINVAL;
			}
		}
		break;

	case BIOCFEEDBACK:
		d->bd_feedback = *(u_int *)addr;
		break;

	case BIOCLOCK:
		d->bd_locked = 1;
		break;

	case FIONBIO:		/* Non-blocking I/O */
		break;

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

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

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

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

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

	case BIOCGETBUFMODE:
		*(u_int *)addr = d->bd_bufmode;
		break;

	case BIOCSETBUFMODE:
		/*
		 * Allow the buffering mode to be changed as long as we
		 * haven't yet committed to a particular mode.  Our
		 * definition of commitment, for now, is whether or not a
		 * buffer has been allocated or an interface attached, since
		 * that's the point where things get tricky.
		 */
		switch (*(u_int *)addr) {
		case BPF_BUFMODE_BUFFER:
			break;

		case BPF_BUFMODE_ZBUF:
			if (bpf_zerocopy_enable)
				break;
			/* FALLSTHROUGH */

		default:
			return (EINVAL);
		}

		BPFD_LOCK(d);
		if (d->bd_sbuf != NULL || d->bd_hbuf != NULL ||
		    d->bd_fbuf != NULL || d->bd_bif != NULL) {
			BPFD_UNLOCK(d);
			return (EBUSY);
		}
		d->bd_bufmode = *(u_int *)addr;
		BPFD_UNLOCK(d);
		break;

	case BIOCGETZMAX:
		return (bpf_ioctl_getzmax(td, d, (size_t *)addr));

	case BIOCSETZBUF:
		return (bpf_ioctl_setzbuf(td, d, (struct bpf_zbuf *)addr));

	case BIOCROTZBUF:
		return (bpf_ioctl_rotzbuf(td, d, (struct bpf_zbuf *)addr));
	}
	CURVNET_RESTORE();
	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;
#ifdef BPF_JITTER
	bpf_jit_filter *ofunc;
#endif

	if (cmd == BIOCSETWF) {
		old = d->bd_wfilter;
		wfilter = 1;
#ifdef BPF_JITTER
		ofunc = NULL;
#endif
	} else {
		wfilter = 0;
		old = d->bd_rfilter;
#ifdef BPF_JITTER
		ofunc = d->bd_bfilter;
#endif
	}
	if (fp->bf_insns == NULL) {
		if (fp->bf_len != 0)
			return (EINVAL);
		BPFD_LOCK(d);
		if (wfilter)
			d->bd_wfilter = NULL;
		else {
			d->bd_rfilter = NULL;
#ifdef BPF_JITTER
			d->bd_bfilter = NULL;
#endif
			if (cmd == BIOCSETF)
				reset_d(d);
		}
		BPFD_UNLOCK(d);
		if (old != NULL)
			free((caddr_t)old, M_BPF);
#ifdef BPF_JITTER
		if (ofunc != NULL)
			bpf_destroy_jit_filter(ofunc);
#endif
		return (0);
	}
	flen = fp->bf_len;
	if (flen > bpf_maxinsns)
		return (EINVAL);

	size = flen * sizeof(*fp->bf_insns);
	fcode = (struct bpf_insn *)malloc(size, M_BPF, M_WAITOK);
	if (copyin((caddr_t)fp->bf_insns, (caddr_t)fcode, size) == 0 &&
	    bpf_validate(fcode, (int)flen)) {
		BPFD_LOCK(d);
		if (wfilter)
			d->bd_wfilter = fcode;
		else {
			d->bd_rfilter = fcode;
#ifdef BPF_JITTER
			d->bd_bfilter = bpf_jitter(fcode, flen);
#endif
			if (cmd == BIOCSETF)
				reset_d(d);
		}
		BPFD_UNLOCK(d);
		if (old != NULL)
			free((caddr_t)old, M_BPF);
#ifdef BPF_JITTER
		if (ofunc != NULL)
			bpf_destroy_jit_filter(ofunc);
#endif

		return (0);
	}
	free((caddr_t)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;
	struct ifnet *theywant;

	theywant = ifunit(ifr->ifr_name);
	if (theywant == NULL || theywant->if_bpf == NULL)
		return (ENXIO);

	bp = theywant->if_bpf;

	/*
	 * Behavior here depends on the buffering model.  If we're using
	 * kernel memory buffers, then we can allocate them here.  If we're
	 * using zero-copy, then the user process must have registered
	 * buffers by the time we get here.  If not, return an error.
	 *
	 * XXXRW: There are locking issues here with multi-threaded use: what
	 * if two threads try to set the interface at once?
	 */
	switch (d->bd_bufmode) {
	case BPF_BUFMODE_BUFFER:
		if (d->bd_sbuf == NULL)
			bpf_buffer_alloc(d);
		KASSERT(d->bd_sbuf != NULL, ("bpf_setif: bd_sbuf NULL"));
		break;

	case BPF_BUFMODE_ZBUF:
		if (d->bd_sbuf == NULL)
			return (EINVAL);
		break;

	default:
		panic("bpf_setif: bufmode %d", d->bd_bufmode);
	}
	if (bp != d->bd_bif) {
		if (d->bd_bif)
			/*
			 * Detach if attached to something else.
			 */
			bpf_detachd(d);

		bpf_attachd(d, bp);
	}
	BPFD_LOCK(d);
	reset_d(d);
	BPFD_UNLOCK(d);
	return (0);
}

/*
 * Support for select() and poll() system calls
 *
 * Return true iff the specific operation will not block indefinitely.
 * Otherwise, return false but make a note that a selwakeup() must be done.
 */
static int
bpfpoll(struct cdev *dev, int events, struct thread *td)
{
	struct bpf_d *d;
	int revents;

	if (devfs_get_cdevpriv((void **)&d) != 0 || d->bd_bif == NULL)
		return (events &
		    (POLLHUP|POLLIN|POLLRDNORM|POLLOUT|POLLWRNORM));

	/*
	 * Refresh PID associated with this descriptor.
	 */
	revents = events & (POLLOUT | POLLWRNORM);
	BPFD_LOCK(d);
	d->bd_pid = td->td_proc->p_pid;
	if (events & (POLLIN | POLLRDNORM)) {
		if (bpf_ready(d))
			revents |= events & (POLLIN | POLLRDNORM);
		else {
			selrecord(td, &d->bd_sel);
			/* 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;
			}
		}
	}
	BPFD_UNLOCK(d);
	return (revents);
}

/*
 * Support for kevent() system call.  Register EVFILT_READ filters and
 * reject all others.
 */
int
bpfkqfilter(struct cdev *dev, struct knote *kn)
{
	struct bpf_d *d;

	if (devfs_get_cdevpriv((void **)&d) != 0 ||
	    kn->kn_filter != EVFILT_READ)
		return (1);

	/*
	 * Refresh PID associated with this descriptor.
	 */
	BPFD_LOCK(d);
	d->bd_pid = curthread->td_proc->p_pid;
	kn->kn_fop = &bpfread_filtops;
	kn->kn_hook = d;
	knlist_add(&d->bd_sel.si_note, kn, 1);
	BPFD_UNLOCK(d);

	return (0);
}

static void
filt_bpfdetach(struct knote *kn)
{
	struct bpf_d *d = (struct bpf_d *)kn->kn_hook;

	knlist_remove(&d->bd_sel.si_note, kn, 0);
}

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

	BPFD_LOCK_ASSERT(d);
	ready = bpf_ready(d);
	if (ready) {
		kn->kn_data = d->bd_slen;
		if (d->bd_hbuf)
			kn->kn_data += d->bd_hlen;
	}
	else 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);
}

/*
 * Incoming linkage from device drivers.  Process the packet pkt, of length
 * pktlen, which is stored in a contiguous buffer.  The packet is parsed
 * by each process' 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;
	u_int slen;
	int gottime;
	struct timeval tv;

	gottime = 0;
	BPFIF_LOCK(bp);
	LIST_FOREACH(d, &bp->bif_dlist, bd_next) {
		BPFD_LOCK(d);
		++d->bd_rcount;
		/*
		 * NB: We dont call BPF_CHECK_DIRECTION() here since there is no
		 * way for the caller to indiciate to us whether this packet
		 * is inbound or outbound.  In the bpf_mtap() routines, we use
		 * the interface pointers on the mbuf to figure it out.
		 */
#ifdef BPF_JITTER
		if (bpf_jitter_enable != 0 && d->bd_bfilter != NULL)
			slen = (*(d->bd_bfilter->func))(pkt, pktlen, pktlen);
		else
#endif
		slen = bpf_filter(d->bd_rfilter, pkt, pktlen, pktlen);
		if (slen != 0) {
			d->bd_fcount++;
			if (!gottime) {
				microtime(&tv);
				gottime = 1;
			}
#ifdef MAC
			if (mac_bpfdesc_check_receive(d, bp->bif_ifp) == 0)
#endif
				catchpacket(d, pkt, pktlen, slen,
				    bpf_append_bytes, &tv);
		}
		BPFD_UNLOCK(d);
	}
	BPFIF_UNLOCK(bp);
}

#define	BPF_CHECK_DIRECTION(d, r, i)				\
	    (((d)->bd_direction == BPF_D_IN && (r) != (i)) ||	\
	    ((d)->bd_direction == BPF_D_OUT && (r) == (i)))

/*
 * Incoming linkage from device drivers, when packet is in an mbuf chain.
 */
void
bpf_mtap(struct bpf_if *bp, struct mbuf *m)
{
	struct bpf_d *d;
	u_int pktlen, slen;
	int gottime;
	struct timeval tv;

	/* Skip outgoing duplicate packets. */
	if ((m->m_flags & M_PROMISC) != 0 && m->m_pkthdr.rcvif == NULL) {
		m->m_flags &= ~M_PROMISC;
		return;
	}

	gottime = 0;

	pktlen = m_length(m, NULL);

	BPFIF_LOCK(bp);
	LIST_FOREACH(d, &bp->bif_dlist, bd_next) {
		if (BPF_CHECK_DIRECTION(d, m->m_pkthdr.rcvif, bp->bif_ifp))
			continue;
		BPFD_LOCK(d);
		++d->bd_rcount;
#ifdef BPF_JITTER
		/* XXX We cannot handle multiple mbufs. */
		if (bpf_jitter_enable != 0 && d->bd_bfilter != NULL &&
		    m->m_next == NULL)
			slen = (*(d->bd_bfilter->func))(mtod(m, u_char *),
			    pktlen, pktlen);
		else
#endif
		slen = bpf_filter(d->bd_rfilter, (u_char *)m, pktlen, 0);
		if (slen != 0) {
			d->bd_fcount++;
			if (!gottime) {
				microtime(&tv);
				gottime = 1;
			}
#ifdef MAC
			if (mac_bpfdesc_check_receive(d, bp->bif_ifp) == 0)
#endif
				catchpacket(d, (u_char *)m, pktlen, slen,
				    bpf_append_mbuf, &tv);
		}
		BPFD_UNLOCK(d);
	}
	BPFIF_UNLOCK(bp);
}

/*
 * Incoming linkage from device drivers, when packet is in
 * an mbuf chain and to be prepended by a contiguous header.
 */
void
bpf_mtap2(struct bpf_if *bp, void *data, u_int dlen, struct mbuf *m)
{
	struct mbuf mb;
	struct bpf_d *d;
	u_int pktlen, slen;
	int gottime;
	struct timeval tv;

	/* Skip outgoing duplicate packets. */
	if ((m->m_flags & M_PROMISC) != 0 && m->m_pkthdr.rcvif == NULL) {
		m->m_flags &= ~M_PROMISC;
		return;
	}

	gottime = 0;

	pktlen = m_length(m, NULL);
	/*
	 * Craft on-stack mbuf suitable for passing to bpf_filter.
	 * 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 = data;
	mb.m_len = dlen;
	pktlen += dlen;

	BPFIF_LOCK(bp);
	LIST_FOREACH(d, &bp->bif_dlist, bd_next) {
		if (BPF_CHECK_DIRECTION(d, m->m_pkthdr.rcvif, bp->bif_ifp))
			continue;
		BPFD_LOCK(d);
		++d->bd_rcount;
		slen = bpf_filter(d->bd_rfilter, (u_char *)&mb, pktlen, 0);
		if (slen != 0) {
			d->bd_fcount++;
			if (!gottime) {
				microtime(&tv);
				gottime = 1;
			}
#ifdef MAC
			if (mac_bpfdesc_check_receive(d, bp->bif_ifp) == 0)
#endif
				catchpacket(d, (u_char *)&mb, pktlen, slen,
				    bpf_append_mbuf, &tv);
		}
		BPFD_UNLOCK(d);
	}
	BPFIF_UNLOCK(bp);
}

#undef	BPF_CHECK_DIRECTION

/*
 * Move the packet data from interface memory (pkt) into the
 * store buffer.  "cpfn" is the routine called to do the actual data
 * transfer.  bcopy is passed in to copy contiguous chunks, while
 * bpf_append_mbuf 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)(struct bpf_d *, caddr_t, u_int, void *, u_int),
    struct timeval *tv)
{
	struct bpf_hdr hdr;
	int totlen, curlen;
	int hdrlen = d->bd_bif->bif_hdrlen;
	int do_wakeup = 0;

	BPFD_LOCK_ASSERT(d);

	/*
	 * Detect whether user space has released a buffer back to us, and if
	 * so, move it from being a hold buffer to a free buffer.  This may
	 * not be the best place to do it (for example, we might only want to
	 * run this check if we need the space), but for now it's a reliable
	 * spot to do it.
	 */
	if (d->bd_fbuf == NULL && bpf_canfreebuf(d)) {
		d->bd_fbuf = d->bd_hbuf;
		d->bd_hbuf = NULL;
		d->bd_hlen = 0;
		bpf_buf_reclaimed(d);
	}

	/*
	 * 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.
	 *
	 * Drop the packet if there's no room and no hope of room
	 * If the packet would overflow the storage buffer or the storage
	 * buffer is considered immutable by the buffer model, try to rotate
	 * the buffer and wakeup pending processes.
	 */
	curlen = BPF_WORDALIGN(d->bd_slen);
	if (curlen + totlen > d->bd_bufsize || !bpf_canwritebuf(d)) {
		if (d->bd_fbuf == NULL) {
			/*
			 * There's no room in the store buffer, and no
			 * prospect of room, so drop the packet.  Notify the
			 * buffer model.
			 */
			bpf_buffull(d);
			++d->bd_dcount;
			return;
		}
		ROTATE_BUFFERS(d);
		do_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.
		 */
		do_wakeup = 1;

	/*
	 * Append the bpf header.  Note we append the actual header size, but
	 * move forward the length of the header plus padding.
	 */
	bzero(&hdr, sizeof(hdr));
	hdr.bh_tstamp = *tv;
	hdr.bh_datalen = pktlen;
	hdr.bh_hdrlen = hdrlen;
	hdr.bh_caplen = totlen - hdrlen;
	bpf_append_bytes(d, d->bd_sbuf, curlen, &hdr, sizeof(hdr));

	/*
	 * Copy the packet data into the store buffer and update its length.
	 */
	(*cpfn)(d, d->bd_sbuf, curlen + hdrlen, pkt, hdr.bh_caplen);
	d->bd_slen = curlen + totlen;

	if (do_wakeup)
		bpf_wakeup(d);
}

/*
 * Free buffers 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.
	 */
	bpf_free(d);
	if (d->bd_rfilter) {
		free((caddr_t)d->bd_rfilter, M_BPF);
#ifdef BPF_JITTER
		bpf_destroy_jit_filter(d->bd_bfilter);
#endif
	}
	if (d->bd_wfilter)
		free((caddr_t)d->bd_wfilter, M_BPF);
	mtx_destroy(&d->bd_mtx);
}

/*
 * Attach an interface to bpf.  dlt is the link layer type; hdrlen is the
 * fixed size of the link header (variable length headers not yet supported).
 */
void
bpfattach(struct ifnet *ifp, u_int dlt, u_int hdrlen)
{

	bpfattach2(ifp, dlt, hdrlen, &ifp->if_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 supporrted).
 */
void
bpfattach2(struct ifnet *ifp, u_int dlt, u_int hdrlen, struct bpf_if **driverp)
{
	struct bpf_if *bp;

	bp = malloc(sizeof(*bp), M_BPF, M_NOWAIT | M_ZERO);
	if (bp == NULL)
		panic("bpfattach");

	LIST_INIT(&bp->bif_dlist);
	bp->bif_ifp = ifp;
	bp->bif_dlt = dlt;
	mtx_init(&bp->bif_mtx, "bpf interface lock", NULL, MTX_DEF);
	KASSERT(*driverp == NULL, ("bpfattach2: driverp already initialized"));
	*driverp = bp;

	mtx_lock(&bpf_mtx);
	LIST_INSERT_HEAD(&bpf_iflist, bp, bif_next);
	mtx_unlock(&bpf_mtx);

	/*
	 * 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;

	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;
	struct bpf_d	*d;

	/* Locate BPF interface information */
	mtx_lock(&bpf_mtx);
	LIST_FOREACH(bp, &bpf_iflist, bif_next) {
		if (ifp == bp->bif_ifp)
			break;
	}

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

	LIST_REMOVE(bp, bif_next);
	mtx_unlock(&bpf_mtx);

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

	mtx_destroy(&bp->bif_mtx);
	free(bp, M_BPF);
}

/*
 * 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;
	mtx_lock(&bpf_mtx);
	LIST_FOREACH(bp, &bpf_iflist, bif_next) {
		if (bp->bif_ifp != ifp)
			continue;
		if (bfl->bfl_list != NULL) {
			if (n >= bfl->bfl_len) {
				mtx_unlock(&bpf_mtx);
				return (ENOMEM);
			}
			error = copyout(&bp->bif_dlt,
			    bfl->bfl_list + n, sizeof(u_int));
		}
		n++;
	}
	mtx_unlock(&bpf_mtx);
	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;
	mtx_lock(&bpf_mtx);
	LIST_FOREACH(bp, &bpf_iflist, bif_next) {
		if (bp->bif_ifp == ifp && bp->bif_dlt == dlt)
			break;
	}
	mtx_unlock(&bpf_mtx);
	if (bp != NULL) {
		opromisc = d->bd_promisc;
		bpf_detachd(d);
		bpf_attachd(d, bp);
		BPFD_LOCK(d);
		reset_d(d);
		BPFD_UNLOCK(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);
}

static void
bpf_drvinit(void *unused)
{
	struct cdev *dev;

	mtx_init(&bpf_mtx, "bpf global lock", NULL, MTX_DEF);
	LIST_INIT(&bpf_iflist);

	dev = make_dev(&bpf_cdevsw, 0, UID_ROOT, GID_WHEEL, 0600, "bpf");
	/* For compatibility */
	make_dev_alias(dev, "bpf0");

}

/*
 * Zero out the various packet counters associated with all of the bpf
 * descriptors.  At some point, we will probably want to get a bit more
 * granular and allow the user to specify descriptors to be zeroed.
 */
static void
bpf_zero_counters(void)
{
	struct bpf_if *bp;
	struct bpf_d *bd;

	mtx_lock(&bpf_mtx);
	LIST_FOREACH(bp, &bpf_iflist, bif_next) {
		BPFIF_LOCK(bp);
		LIST_FOREACH(bd, &bp->bif_dlist, bd_next) {
			BPFD_LOCK(bd);
			bd->bd_rcount = 0;
			bd->bd_dcount = 0;
			bd->bd_fcount = 0;
			bd->bd_wcount = 0;
			bd->bd_wfcount = 0;
			bd->bd_zcopy = 0;
			BPFD_UNLOCK(bd);
		}
		BPFIF_UNLOCK(bp);
	}
	mtx_unlock(&bpf_mtx);
}

static void
bpfstats_fill_xbpf(struct xbpf_d *d, struct bpf_d *bd)
{

	bzero(d, sizeof(*d));
	BPFD_LOCK_ASSERT(bd);
	d->bd_structsize = sizeof(*d);
	d->bd_immediate = bd->bd_immediate;
	d->bd_promisc = bd->bd_promisc;
	d->bd_hdrcmplt = bd->bd_hdrcmplt;
	d->bd_direction = bd->bd_direction;
	d->bd_feedback = bd->bd_feedback;
	d->bd_async = bd->bd_async;
	d->bd_rcount = bd->bd_rcount;
	d->bd_dcount = bd->bd_dcount;
	d->bd_fcount = bd->bd_fcount;
	d->bd_sig = bd->bd_sig;
	d->bd_slen = bd->bd_slen;
	d->bd_hlen = bd->bd_hlen;
	d->bd_bufsize = bd->bd_bufsize;
	d->bd_pid = bd->bd_pid;
	strlcpy(d->bd_ifname,
	    bd->bd_bif->bif_ifp->if_xname, IFNAMSIZ);
	d->bd_locked = bd->bd_locked;
	d->bd_wcount = bd->bd_wcount;
	d->bd_wdcount = bd->bd_wdcount;
	d->bd_wfcount = bd->bd_wfcount;
	d->bd_zcopy = bd->bd_zcopy;
	d->bd_bufmode = bd->bd_bufmode;
}

static int
bpf_stats_sysctl(SYSCTL_HANDLER_ARGS)
{
	struct xbpf_d *xbdbuf, *xbd, zerostats;
	int index, error;
	struct bpf_if *bp;
	struct bpf_d *bd;

	/*
	 * XXX This is not technically correct. It is possible for non
	 * privileged users to open bpf devices. It would make sense
	 * if the users who opened the devices were able to retrieve
	 * the statistics for them, too.
	 */
	error = priv_check(req->td, PRIV_NET_BPF);
	if (error)
		return (error);
	/*
	 * Check to see if the user is requesting that the counters be
	 * zeroed out.  Explicitly check that the supplied data is zeroed,
	 * as we aren't allowing the user to set the counters currently.
	 */
	if (req->newptr != NULL) {
		if (req->newlen != sizeof(zerostats))
			return (EINVAL);
		bzero(&zerostats, sizeof(zerostats));
		xbd = req->newptr;
		if (bcmp(xbd, &zerostats, sizeof(*xbd)) != 0)
			return (EINVAL);
		bpf_zero_counters();
		return (0);
	}
	if (req->oldptr == NULL)
		return (SYSCTL_OUT(req, 0, bpf_bpfd_cnt * sizeof(*xbd)));
	if (bpf_bpfd_cnt == 0)
		return (SYSCTL_OUT(req, 0, 0));
	xbdbuf = malloc(req->oldlen, M_BPF, M_WAITOK);
	mtx_lock(&bpf_mtx);
	if (req->oldlen < (bpf_bpfd_cnt * sizeof(*xbd))) {
		mtx_unlock(&bpf_mtx);
		free(xbdbuf, M_BPF);
		return (ENOMEM);
	}
	index = 0;
	LIST_FOREACH(bp, &bpf_iflist, bif_next) {
		BPFIF_LOCK(bp);
		LIST_FOREACH(bd, &bp->bif_dlist, bd_next) {
			xbd = &xbdbuf[index++];
			BPFD_LOCK(bd);
			bpfstats_fill_xbpf(xbd, bd);
			BPFD_UNLOCK(bd);
		}
		BPFIF_UNLOCK(bp);
	}
	mtx_unlock(&bpf_mtx);
	error = SYSCTL_OUT(req, xbdbuf, index * sizeof(*xbd));
	free(xbdbuf, M_BPF);
	return (error);
}

SYSINIT(bpfdev,SI_SUB_DRIVERS,SI_ORDER_MIDDLE,bpf_drvinit,NULL);

#else /* !DEV_BPF && !NETGRAPH_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.
 */
static struct bpf_if bp_null;

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_mtap2(struct bpf_if *bp, void *d, u_int l, struct mbuf *m)
{
}

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

	bpfattach2(ifp, dlt, hdrlen, &ifp->if_bpf);
}

void
bpfattach2(struct ifnet *ifp, u_int dlt, u_int hdrlen, struct bpf_if **driverp)
{

	*driverp = &bp_null;
}

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 */
}

int
bpf_validate(const struct bpf_insn *f, int len)
{
	return 0;		/* false */
}

#endif /* !DEV_BPF && !NETGRAPH_BPF */
OpenPOWER on IntegriCloud