summaryrefslogtreecommitdiffstats
path: root/sys/net/if.c
blob: 288d944c476c75f1fcac762cb8990ac4d135ee6b (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
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
/*-
 * Copyright (c) 1980, 1986, 1993
 *	The Regents of the University of California.  All rights reserved.
 *
 * 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.
 *
 *	@(#)if.c	8.5 (Berkeley) 1/9/95
 * $FreeBSD$
 */

#include "opt_compat.h"
#include "opt_inet6.h"
#include "opt_inet.h"

#include <sys/param.h>
#include <sys/types.h>
#include <sys/conf.h>
#include <sys/malloc.h>
#include <sys/sbuf.h>
#include <sys/bus.h>
#include <sys/mbuf.h>
#include <sys/systm.h>
#include <sys/priv.h>
#include <sys/proc.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/protosw.h>
#include <sys/kernel.h>
#include <sys/lock.h>
#include <sys/refcount.h>
#include <sys/module.h>
#include <sys/rwlock.h>
#include <sys/sockio.h>
#include <sys/syslog.h>
#include <sys/sysctl.h>
#include <sys/taskqueue.h>
#include <sys/domain.h>
#include <sys/jail.h>
#include <sys/priv.h>

#include <machine/stdarg.h>
#include <vm/uma.h>

#include <net/if.h>
#include <net/if_arp.h>
#include <net/if_clone.h>
#include <net/if_dl.h>
#include <net/if_types.h>
#include <net/if_var.h>
#include <net/radix.h>
#include <net/route.h>
#include <net/vnet.h>

#if defined(INET) || defined(INET6)
#include <net/ethernet.h>
#include <netinet/in.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_carp.h>
#ifdef INET
#include <netinet/if_ether.h>
#endif /* INET */
#ifdef INET6
#include <netinet6/in6_var.h>
#include <netinet6/in6_ifattach.h>
#endif /* INET6 */
#endif /* INET || INET6 */

#include <security/mac/mac_framework.h>

#ifdef COMPAT_FREEBSD32
#include <sys/mount.h>
#include <compat/freebsd32/freebsd32.h>
#endif

struct ifindex_entry {
	struct  ifnet *ife_ifnet;
};

SYSCTL_NODE(_net, PF_LINK, link, CTLFLAG_RW, 0, "Link layers");
SYSCTL_NODE(_net_link, 0, generic, CTLFLAG_RW, 0, "Generic link-management");

TUNABLE_INT("net.link.ifqmaxlen", &ifqmaxlen);
SYSCTL_INT(_net_link, OID_AUTO, ifqmaxlen, CTLFLAG_RDTUN,
    &ifqmaxlen, 0, "max send queue size");

/* Log link state change events */
static int log_link_state_change = 1;

SYSCTL_INT(_net_link, OID_AUTO, log_link_state_change, CTLFLAG_RW,
	&log_link_state_change, 0,
	"log interface link state change events");

/* Interface description */
static unsigned int ifdescr_maxlen = 1024;
SYSCTL_UINT(_net, OID_AUTO, ifdescr_maxlen, CTLFLAG_RW,
	&ifdescr_maxlen, 0,
	"administrative maximum length for interface description");

static MALLOC_DEFINE(M_IFDESCR, "ifdescr", "ifnet descriptions");

/* global sx for non-critical path ifdescr */
static struct sx ifdescr_sx;
SX_SYSINIT(ifdescr_sx, &ifdescr_sx, "ifnet descr");

void	(*bridge_linkstate_p)(struct ifnet *ifp);
void	(*ng_ether_link_state_p)(struct ifnet *ifp, int state);
void	(*lagg_linkstate_p)(struct ifnet *ifp, int state);
/* These are external hooks for CARP. */
void	(*carp_linkstate_p)(struct ifnet *ifp);
void	(*carp_demote_adj_p)(int, char *);
int	(*carp_master_p)(struct ifaddr *);
#if defined(INET) || defined(INET6)
int	(*carp_forus_p)(struct ifnet *ifp, u_char *dhost);
int	(*carp_output_p)(struct ifnet *ifp, struct mbuf *m,
    const struct sockaddr *sa);
int	(*carp_ioctl_p)(struct ifreq *, u_long, struct thread *);   
int	(*carp_attach_p)(struct ifaddr *, int);
void	(*carp_detach_p)(struct ifaddr *);
#endif
#ifdef INET
int	(*carp_iamatch_p)(struct ifaddr *, uint8_t **);
#endif
#ifdef INET6
struct ifaddr *(*carp_iamatch6_p)(struct ifnet *ifp, struct in6_addr *taddr6);
caddr_t	(*carp_macmatch6_p)(struct ifnet *ifp, struct mbuf *m,
    const struct in6_addr *taddr);
#endif

struct mbuf *(*tbr_dequeue_ptr)(struct ifaltq *, int) = NULL;

/*
 * XXX: Style; these should be sorted alphabetically, and unprototyped
 * static functions should be prototyped. Currently they are sorted by
 * declaration order.
 */
static void	if_attachdomain(void *);
static void	if_attachdomain1(struct ifnet *);
static int	ifconf(u_long, caddr_t);
static void	if_freemulti(struct ifmultiaddr *);
static void	if_init(void *);
static void	if_grow(void);
static void	if_input_default(struct ifnet *, struct mbuf *);
static void	if_route(struct ifnet *, int flag, int fam);
static int	if_setflag(struct ifnet *, int, int, int *, int);
static int	if_transmit(struct ifnet *ifp, struct mbuf *m);
static void	if_unroute(struct ifnet *, int flag, int fam);
static void	link_rtrequest(int, struct rtentry *, struct rt_addrinfo *);
static int	if_rtdel(struct radix_node *, void *);
static int	ifhwioctl(u_long, struct ifnet *, caddr_t, struct thread *);
static int	if_delmulti_locked(struct ifnet *, struct ifmultiaddr *, int);
static void	do_link_state_change(void *, int);
static int	if_getgroup(struct ifgroupreq *, struct ifnet *);
static int	if_getgroupmembers(struct ifgroupreq *);
static void	if_delgroups(struct ifnet *);
static void	if_attach_internal(struct ifnet *, int, struct if_clone *);
static int	if_detach_internal(struct ifnet *, int, struct if_clone **);

#ifdef INET6
/*
 * XXX: declare here to avoid to include many inet6 related files..
 * should be more generalized?
 */
extern void	nd6_setmtu(struct ifnet *);
#endif

VNET_DEFINE(int, if_index);
int	ifqmaxlen = IFQ_MAXLEN;
VNET_DEFINE(struct ifnethead, ifnet);	/* depend on static init XXX */
VNET_DEFINE(struct ifgrouphead, ifg_head);

static VNET_DEFINE(int, if_indexlim) = 8;

/* Table of ifnet by index. */
VNET_DEFINE(struct ifindex_entry *, ifindex_table);

#define	V_if_indexlim		VNET(if_indexlim)
#define	V_ifindex_table		VNET(ifindex_table)

/*
 * The global network interface list (V_ifnet) and related state (such as
 * if_index, if_indexlim, and ifindex_table) are protected by an sxlock and
 * an rwlock.  Either may be acquired shared to stablize the list, but both
 * must be acquired writable to modify the list.  This model allows us to
 * both stablize the interface list during interrupt thread processing, but
 * also to stablize it over long-running ioctls, without introducing priority
 * inversions and deadlocks.
 */
struct rwlock ifnet_rwlock;
struct sx ifnet_sxlock;

/*
 * The allocation of network interfaces is a rather non-atomic affair; we
 * need to select an index before we are ready to expose the interface for
 * use, so will use this pointer value to indicate reservation.
 */
#define	IFNET_HOLD	(void *)(uintptr_t)(-1)

static	if_com_alloc_t *if_com_alloc[256];
static	if_com_free_t *if_com_free[256];

static MALLOC_DEFINE(M_IFNET, "ifnet", "interface internals");
MALLOC_DEFINE(M_IFADDR, "ifaddr", "interface address");
MALLOC_DEFINE(M_IFMADDR, "ether_multi", "link-level multicast address");

struct ifnet *
ifnet_byindex_locked(u_short idx)
{

	if (idx > V_if_index)
		return (NULL);
	if (V_ifindex_table[idx].ife_ifnet == IFNET_HOLD)
		return (NULL);
	return (V_ifindex_table[idx].ife_ifnet);
}

struct ifnet *
ifnet_byindex(u_short idx)
{
	struct ifnet *ifp;

	IFNET_RLOCK_NOSLEEP();
	ifp = ifnet_byindex_locked(idx);
	IFNET_RUNLOCK_NOSLEEP();
	return (ifp);
}

struct ifnet *
ifnet_byindex_ref(u_short idx)
{
	struct ifnet *ifp;

	IFNET_RLOCK_NOSLEEP();
	ifp = ifnet_byindex_locked(idx);
	if (ifp == NULL || (ifp->if_flags & IFF_DYING)) {
		IFNET_RUNLOCK_NOSLEEP();
		return (NULL);
	}
	if_ref(ifp);
	IFNET_RUNLOCK_NOSLEEP();
	return (ifp);
}

/*
 * Allocate an ifindex array entry; return 0 on success or an error on
 * failure.
 */
static int
ifindex_alloc_locked(u_short *idxp)
{
	u_short idx;

	IFNET_WLOCK_ASSERT();

retry:
	/*
	 * Try to find an empty slot below V_if_index.  If we fail, take the
	 * next slot.
	 */
	for (idx = 1; idx <= V_if_index; idx++) {
		if (V_ifindex_table[idx].ife_ifnet == NULL)
			break;
	}

	/* Catch if_index overflow. */
	if (idx < 1)
		return (ENOSPC);
	if (idx >= V_if_indexlim) {
		if_grow();
		goto retry;
	}
	if (idx > V_if_index)
		V_if_index = idx;
	*idxp = idx;
	return (0);
}

static void
ifindex_free_locked(u_short idx)
{

	IFNET_WLOCK_ASSERT();

	V_ifindex_table[idx].ife_ifnet = NULL;
	while (V_if_index > 0 &&
	    V_ifindex_table[V_if_index].ife_ifnet == NULL)
		V_if_index--;
}

static void
ifindex_free(u_short idx)
{

	IFNET_WLOCK();
	ifindex_free_locked(idx);
	IFNET_WUNLOCK();
}

static void
ifnet_setbyindex_locked(u_short idx, struct ifnet *ifp)
{

	IFNET_WLOCK_ASSERT();

	V_ifindex_table[idx].ife_ifnet = ifp;
}

static void
ifnet_setbyindex(u_short idx, struct ifnet *ifp)
{

	IFNET_WLOCK();
	ifnet_setbyindex_locked(idx, ifp);
	IFNET_WUNLOCK();
}

struct ifaddr *
ifaddr_byindex(u_short idx)
{
	struct ifaddr *ifa;

	IFNET_RLOCK_NOSLEEP();
	ifa = ifnet_byindex_locked(idx)->if_addr;
	if (ifa != NULL)
		ifa_ref(ifa);
	IFNET_RUNLOCK_NOSLEEP();
	return (ifa);
}

/*
 * Network interface utility routines.
 *
 * Routines with ifa_ifwith* names take sockaddr *'s as
 * parameters.
 */

static void
vnet_if_init(const void *unused __unused)
{

	TAILQ_INIT(&V_ifnet);
	TAILQ_INIT(&V_ifg_head);
	IFNET_WLOCK();
	if_grow();				/* create initial table */
	IFNET_WUNLOCK();
	vnet_if_clone_init();
}
VNET_SYSINIT(vnet_if_init, SI_SUB_INIT_IF, SI_ORDER_SECOND, vnet_if_init,
    NULL);

/* ARGSUSED*/
static void
if_init(void *dummy __unused)
{

	IFNET_LOCK_INIT();
	if_clone_init();
}
SYSINIT(interfaces, SI_SUB_INIT_IF, SI_ORDER_FIRST, if_init, NULL);


#ifdef VIMAGE
static void
vnet_if_uninit(const void *unused __unused)
{

	VNET_ASSERT(TAILQ_EMPTY(&V_ifnet), ("%s:%d tailq &V_ifnet=%p "
	    "not empty", __func__, __LINE__, &V_ifnet));
	VNET_ASSERT(TAILQ_EMPTY(&V_ifg_head), ("%s:%d tailq &V_ifg_head=%p "
	    "not empty", __func__, __LINE__, &V_ifg_head));

	free((caddr_t)V_ifindex_table, M_IFNET);
}
VNET_SYSUNINIT(vnet_if_uninit, SI_SUB_INIT_IF, SI_ORDER_FIRST,
    vnet_if_uninit, NULL);
#endif

static void
if_grow(void)
{
	int oldlim;
	u_int n;
	struct ifindex_entry *e;

	IFNET_WLOCK_ASSERT();
	oldlim = V_if_indexlim;
	IFNET_WUNLOCK();
	n = (oldlim << 1) * sizeof(*e);
	e = malloc(n, M_IFNET, M_WAITOK | M_ZERO);
	IFNET_WLOCK();
	if (V_if_indexlim != oldlim) {
		free(e, M_IFNET);
		return;
	}
	if (V_ifindex_table != NULL) {
		memcpy((caddr_t)e, (caddr_t)V_ifindex_table, n/2);
		free((caddr_t)V_ifindex_table, M_IFNET);
	}
	V_if_indexlim <<= 1;
	V_ifindex_table = e;
}

/*
 * Allocate a struct ifnet and an index for an interface.  A layer 2
 * common structure will also be allocated if an allocation routine is
 * registered for the passed type.
 */
struct ifnet *
if_alloc(u_char type)
{
	struct ifnet *ifp;
	u_short idx;

	ifp = malloc(sizeof(struct ifnet), M_IFNET, M_WAITOK|M_ZERO);
	IFNET_WLOCK();
	if (ifindex_alloc_locked(&idx) != 0) {
		IFNET_WUNLOCK();
		free(ifp, M_IFNET);
		return (NULL);
	}
	ifnet_setbyindex_locked(idx, IFNET_HOLD);
	IFNET_WUNLOCK();
	ifp->if_index = idx;
	ifp->if_type = type;
	ifp->if_alloctype = type;
	if (if_com_alloc[type] != NULL) {
		ifp->if_l2com = if_com_alloc[type](type, ifp);
		if (ifp->if_l2com == NULL) {
			free(ifp, M_IFNET);
			ifindex_free(idx);
			return (NULL);
		}
	}

	IF_ADDR_LOCK_INIT(ifp);
	TASK_INIT(&ifp->if_linktask, 0, do_link_state_change, ifp);
	ifp->if_afdata_initialized = 0;
	IF_AFDATA_LOCK_INIT(ifp);
	TAILQ_INIT(&ifp->if_addrhead);
	TAILQ_INIT(&ifp->if_multiaddrs);
	TAILQ_INIT(&ifp->if_groups);
#ifdef MAC
	mac_ifnet_init(ifp);
#endif
	ifq_init(&ifp->if_snd, ifp);

	refcount_init(&ifp->if_refcount, 1);	/* Index reference. */
	ifnet_setbyindex(ifp->if_index, ifp);
	return (ifp);
}

/*
 * Do the actual work of freeing a struct ifnet, and layer 2 common
 * structure.  This call is made when the last reference to an
 * interface is released.
 */
static void
if_free_internal(struct ifnet *ifp)
{

	KASSERT((ifp->if_flags & IFF_DYING),
	    ("if_free_internal: interface not dying"));

	if (if_com_free[ifp->if_alloctype] != NULL)
		if_com_free[ifp->if_alloctype](ifp->if_l2com,
		    ifp->if_alloctype);

#ifdef MAC
	mac_ifnet_destroy(ifp);
#endif /* MAC */
	if (ifp->if_description != NULL)
		free(ifp->if_description, M_IFDESCR);
	IF_AFDATA_DESTROY(ifp);
	IF_ADDR_LOCK_DESTROY(ifp);
	ifq_delete(&ifp->if_snd);
	free(ifp, M_IFNET);
}

/*
 * Deregister an interface and free the associated storage.
 */
void
if_free(struct ifnet *ifp)
{

	ifp->if_flags |= IFF_DYING;			/* XXX: Locking */

	CURVNET_SET_QUIET(ifp->if_vnet);
	IFNET_WLOCK();
	KASSERT(ifp == ifnet_byindex_locked(ifp->if_index),
	    ("%s: freeing unallocated ifnet", ifp->if_xname));

	ifindex_free_locked(ifp->if_index);
	IFNET_WUNLOCK();

	if (refcount_release(&ifp->if_refcount))
		if_free_internal(ifp);
	CURVNET_RESTORE();
}

/*
 * Interfaces to keep an ifnet type-stable despite the possibility of the
 * driver calling if_free().  If there are additional references, we defer
 * freeing the underlying data structure.
 */
void
if_ref(struct ifnet *ifp)
{

	/* We don't assert the ifnet list lock here, but arguably should. */
	refcount_acquire(&ifp->if_refcount);
}

void
if_rele(struct ifnet *ifp)
{

	if (!refcount_release(&ifp->if_refcount))
		return;
	if_free_internal(ifp);
}

void
ifq_init(struct ifaltq *ifq, struct ifnet *ifp)
{
	
	mtx_init(&ifq->ifq_mtx, ifp->if_xname, "if send queue", MTX_DEF);

	if (ifq->ifq_maxlen == 0) 
		ifq->ifq_maxlen = ifqmaxlen;

	ifq->altq_type = 0;
	ifq->altq_disc = NULL;
	ifq->altq_flags &= ALTQF_CANTCHANGE;
	ifq->altq_tbr  = NULL;
	ifq->altq_ifp  = ifp;
}

void
ifq_delete(struct ifaltq *ifq)
{
	mtx_destroy(&ifq->ifq_mtx);
}

/*
 * Perform generic interface initalization tasks and attach the interface
 * to the list of "active" interfaces.  If vmove flag is set on entry
 * to if_attach_internal(), perform only a limited subset of initialization
 * tasks, given that we are moving from one vnet to another an ifnet which
 * has already been fully initialized.
 *
 * Note that if_detach_internal() removes group membership unconditionally
 * even when vmove flag is set, and if_attach_internal() adds only IFG_ALL.
 * Thus, when if_vmove() is applied to a cloned interface, group membership
 * is lost while a cloned one always joins a group whose name is
 * ifc->ifc_name.  To recover this after if_detach_internal() and
 * if_attach_internal(), the cloner should be specified to
 * if_attach_internal() via ifc.  If it is non-NULL, if_attach_internal()
 * attempts to join a group whose name is ifc->ifc_name.
 *
 * XXX:
 *  - The decision to return void and thus require this function to
 *    succeed is questionable.
 *  - We should probably do more sanity checking.  For instance we don't
 *    do anything to insure if_xname is unique or non-empty.
 */
void
if_attach(struct ifnet *ifp)
{

	if_attach_internal(ifp, 0, NULL);
}

/*
 * Compute the least common TSO limit.
 */
void
if_hw_tsomax_common(struct ifnet *ifp, struct ifnet_hw_tsomax *pmax)
{
	/*
	 * 1) If there is no limit currently, take the limit from
	 * the network adapter.
	 *
	 * 2) If the network adapter has a limit below the current
	 * limit, apply it.
	 */
	if (pmax->tsomaxbytes == 0 || (ifp->if_hw_tsomax != 0 &&
	    ifp->if_hw_tsomax < pmax->tsomaxbytes)) {
		pmax->tsomaxbytes = ifp->if_hw_tsomax;
	}
	if (pmax->tsomaxsegcount == 0 || (ifp->if_hw_tsomaxsegcount != 0 &&
	    ifp->if_hw_tsomaxsegcount < pmax->tsomaxsegcount)) {
		pmax->tsomaxsegcount = ifp->if_hw_tsomaxsegcount;
	}
	if (pmax->tsomaxsegsize == 0 || (ifp->if_hw_tsomaxsegsize != 0 &&
	    ifp->if_hw_tsomaxsegsize < pmax->tsomaxsegsize)) {
		pmax->tsomaxsegsize = ifp->if_hw_tsomaxsegsize;
	}
}

/*
 * Update TSO limit of a network adapter.
 *
 * Returns zero if no change. Else non-zero.
 */
int
if_hw_tsomax_update(struct ifnet *ifp, struct ifnet_hw_tsomax *pmax)
{
	int retval = 0;
	if (ifp->if_hw_tsomax != pmax->tsomaxbytes) {
		ifp->if_hw_tsomax = pmax->tsomaxbytes;
		retval++;
	}
	if (ifp->if_hw_tsomaxsegsize != pmax->tsomaxsegsize) {
		ifp->if_hw_tsomaxsegsize = pmax->tsomaxsegsize;
		retval++;
	}
	if (ifp->if_hw_tsomaxsegcount != pmax->tsomaxsegcount) {
		ifp->if_hw_tsomaxsegcount = pmax->tsomaxsegcount;
		retval++;
	}
	return (retval);
}

static void
if_attach_internal(struct ifnet *ifp, int vmove, struct if_clone *ifc)
{
	unsigned socksize, ifasize;
	int namelen, masklen;
	struct sockaddr_dl *sdl;
	struct ifaddr *ifa;

	if (ifp->if_index == 0 || ifp != ifnet_byindex(ifp->if_index))
		panic ("%s: BUG: if_attach called without if_alloc'd input()\n",
		    ifp->if_xname);

#ifdef VIMAGE
	ifp->if_vnet = curvnet;
	if (ifp->if_home_vnet == NULL)
		ifp->if_home_vnet = curvnet;
#endif

	if_addgroup(ifp, IFG_ALL);

	/* Restore group membership for cloned interfaces. */
	if (vmove && ifc != NULL)
		if_clone_addgroup(ifp, ifc);

	getmicrotime(&ifp->if_lastchange);
	ifp->if_data.ifi_epoch = time_uptime;
	ifp->if_data.ifi_datalen = sizeof(struct if_data);

	KASSERT((ifp->if_transmit == NULL && ifp->if_qflush == NULL) ||
	    (ifp->if_transmit != NULL && ifp->if_qflush != NULL),
	    ("transmit and qflush must both either be set or both be NULL"));
	if (ifp->if_transmit == NULL) {
		ifp->if_transmit = if_transmit;
		ifp->if_qflush = if_qflush;
	}
	if (ifp->if_input == NULL)
		ifp->if_input = if_input_default;

	if (!vmove) {
#ifdef MAC
		mac_ifnet_create(ifp);
#endif

		/*
		 * Create a Link Level name for this device.
		 */
		namelen = strlen(ifp->if_xname);
		/*
		 * Always save enough space for any possiable name so we
		 * can do a rename in place later.
		 */
		masklen = offsetof(struct sockaddr_dl, sdl_data[0]) + IFNAMSIZ;
		socksize = masklen + ifp->if_addrlen;
		if (socksize < sizeof(*sdl))
			socksize = sizeof(*sdl);
		socksize = roundup2(socksize, sizeof(long));
		ifasize = sizeof(*ifa) + 2 * socksize;
		ifa = malloc(ifasize, M_IFADDR, M_WAITOK | M_ZERO);
		ifa_init(ifa);
		sdl = (struct sockaddr_dl *)(ifa + 1);
		sdl->sdl_len = socksize;
		sdl->sdl_family = AF_LINK;
		bcopy(ifp->if_xname, sdl->sdl_data, namelen);
		sdl->sdl_nlen = namelen;
		sdl->sdl_index = ifp->if_index;
		sdl->sdl_type = ifp->if_type;
		ifp->if_addr = ifa;
		ifa->ifa_ifp = ifp;
		ifa->ifa_rtrequest = link_rtrequest;
		ifa->ifa_addr = (struct sockaddr *)sdl;
		sdl = (struct sockaddr_dl *)(socksize + (caddr_t)sdl);
		ifa->ifa_netmask = (struct sockaddr *)sdl;
		sdl->sdl_len = masklen;
		while (namelen != 0)
			sdl->sdl_data[--namelen] = 0xff;
		TAILQ_INSERT_HEAD(&ifp->if_addrhead, ifa, ifa_link);
		/* Reliably crash if used uninitialized. */
		ifp->if_broadcastaddr = NULL;

#if defined(INET) || defined(INET6)
		/* Use defaults for TSO, if nothing is set */
		if (ifp->if_hw_tsomax == 0 &&
		    ifp->if_hw_tsomaxsegcount == 0 &&
		    ifp->if_hw_tsomaxsegsize == 0) {
			/*
			 * The TSO defaults needs to be such that an
			 * NFS mbuf list of 35 mbufs totalling just
			 * below 64K works and that a chain of mbufs
			 * can be defragged into at most 32 segments:
			 */
			ifp->if_hw_tsomax = min(IP_MAXPACKET, (32 * MCLBYTES) -
			    (ETHER_HDR_LEN + ETHER_VLAN_ENCAP_LEN));
			ifp->if_hw_tsomaxsegcount = 35;
			ifp->if_hw_tsomaxsegsize = 2048;	/* 2K */

			/* XXX some drivers set IFCAP_TSO after ethernet attach */
			if (ifp->if_capabilities & IFCAP_TSO) {
				if_printf(ifp, "Using defaults for TSO: %u/%u/%u\n",
				    ifp->if_hw_tsomax,
				    ifp->if_hw_tsomaxsegcount,
				    ifp->if_hw_tsomaxsegsize);
			}
		}
#endif
	}
#ifdef VIMAGE
	else {
		/*
		 * Update the interface index in the link layer address
		 * of the interface.
		 */
		for (ifa = ifp->if_addr; ifa != NULL;
		    ifa = TAILQ_NEXT(ifa, ifa_link)) {
			if (ifa->ifa_addr->sa_family == AF_LINK) {
				sdl = (struct sockaddr_dl *)ifa->ifa_addr;
				sdl->sdl_index = ifp->if_index;
			}
		}
	}
#endif

	IFNET_WLOCK();
	TAILQ_INSERT_TAIL(&V_ifnet, ifp, if_link);
#ifdef VIMAGE
	curvnet->vnet_ifcnt++;
#endif
	IFNET_WUNLOCK();

	if (domain_init_status >= 2)
		if_attachdomain1(ifp);

	EVENTHANDLER_INVOKE(ifnet_arrival_event, ifp);
	if (IS_DEFAULT_VNET(curvnet))
		devctl_notify("IFNET", ifp->if_xname, "ATTACH", NULL);

	/* Announce the interface. */
	rt_ifannouncemsg(ifp, IFAN_ARRIVAL);
}

static void
if_attachdomain(void *dummy)
{
	struct ifnet *ifp;

	TAILQ_FOREACH(ifp, &V_ifnet, if_link)
		if_attachdomain1(ifp);
}
SYSINIT(domainifattach, SI_SUB_PROTO_IFATTACHDOMAIN, SI_ORDER_SECOND,
    if_attachdomain, NULL);

static void
if_attachdomain1(struct ifnet *ifp)
{
	struct domain *dp;

	/*
	 * Since dp->dom_ifattach calls malloc() with M_WAITOK, we
	 * cannot lock ifp->if_afdata initialization, entirely.
	 */
	if (IF_AFDATA_TRYLOCK(ifp) == 0)
		return;
	if (ifp->if_afdata_initialized >= domain_init_status) {
		IF_AFDATA_UNLOCK(ifp);
		log(LOG_WARNING, "%s called more than once on %s\n",
		    __func__, ifp->if_xname);
		return;
	}
	ifp->if_afdata_initialized = domain_init_status;
	IF_AFDATA_UNLOCK(ifp);

	/* address family dependent data region */
	bzero(ifp->if_afdata, sizeof(ifp->if_afdata));
	for (dp = domains; dp; dp = dp->dom_next) {
		if (dp->dom_ifattach)
			ifp->if_afdata[dp->dom_family] =
			    (*dp->dom_ifattach)(ifp);
	}
}

/*
 * Remove any unicast or broadcast network addresses from an interface.
 */
void
if_purgeaddrs(struct ifnet *ifp)
{
	struct ifaddr *ifa, *next;

	TAILQ_FOREACH_SAFE(ifa, &ifp->if_addrhead, ifa_link, next) {
		if (ifa->ifa_addr->sa_family == AF_LINK)
			continue;
#ifdef INET
		/* XXX: Ugly!! ad hoc just for INET */
		if (ifa->ifa_addr->sa_family == AF_INET) {
			struct ifaliasreq ifr;

			bzero(&ifr, sizeof(ifr));
			ifr.ifra_addr = *ifa->ifa_addr;
			if (ifa->ifa_dstaddr)
				ifr.ifra_broadaddr = *ifa->ifa_dstaddr;
			if (in_control(NULL, SIOCDIFADDR, (caddr_t)&ifr, ifp,
			    NULL) == 0)
				continue;
		}
#endif /* INET */
#ifdef INET6
		if (ifa->ifa_addr->sa_family == AF_INET6) {
			in6_purgeaddr(ifa);
			/* ifp_addrhead is already updated */
			continue;
		}
#endif /* INET6 */
		TAILQ_REMOVE(&ifp->if_addrhead, ifa, ifa_link);
		ifa_free(ifa);
	}
}

/*
 * Remove any multicast network addresses from an interface when an ifnet
 * is going away.
 */
static void
if_purgemaddrs(struct ifnet *ifp)
{
	struct ifmultiaddr *ifma;
	struct ifmultiaddr *next;

	IF_ADDR_WLOCK(ifp);
	TAILQ_FOREACH_SAFE(ifma, &ifp->if_multiaddrs, ifma_link, next)
		if_delmulti_locked(ifp, ifma, 1);
	IF_ADDR_WUNLOCK(ifp);
}

/*
 * Detach an interface, removing it from the list of "active" interfaces.
 * If vmove flag is set on entry to if_detach_internal(), perform only a
 * limited subset of cleanup tasks, given that we are moving an ifnet from
 * one vnet to another, where it must be fully operational.
 *
 * XXXRW: There are some significant questions about event ordering, and
 * how to prevent things from starting to use the interface during detach.
 */
void
if_detach(struct ifnet *ifp)
{

	CURVNET_SET_QUIET(ifp->if_vnet);
	if_detach_internal(ifp, 0, NULL);
	CURVNET_RESTORE();
}

static int
if_detach_internal(struct ifnet *ifp, int vmove, struct if_clone **ifcp)
{
	struct ifaddr *ifa;
	struct radix_node_head	*rnh;
	int i, j;
	struct domain *dp;
 	struct ifnet *iter;
 	int found = 0;

	IFNET_WLOCK();
	TAILQ_FOREACH(iter, &V_ifnet, if_link)
		if (iter == ifp) {
			TAILQ_REMOVE(&V_ifnet, ifp, if_link);
			found = 1;
			break;
		}
#ifdef VIMAGE
	if (found)
		curvnet->vnet_ifcnt--;
#endif
	IFNET_WUNLOCK();
	if (!found) {
		/*
		 * While we would want to panic here, we cannot
		 * guarantee that the interface is indeed still on
		 * the list given we don't hold locks all the way.
		 */
		return (ENOENT);
#if 0
		if (vmove)
			panic("%s: ifp=%p not on the ifnet tailq %p",
			    __func__, ifp, &V_ifnet);
		else
			return; /* XXX this should panic as well? */
#endif
	}

	/* Check if this is a cloned interface or not. */
	if (vmove && ifcp != NULL)
		*ifcp = if_clone_findifc(ifp);

	/*
	 * Remove/wait for pending events.
	 */
	taskqueue_drain(taskqueue_swi, &ifp->if_linktask);

	/*
	 * Remove routes and flush queues.
	 */
	if_down(ifp);
#ifdef ALTQ
	if (ALTQ_IS_ENABLED(&ifp->if_snd))
		altq_disable(&ifp->if_snd);
	if (ALTQ_IS_ATTACHED(&ifp->if_snd))
		altq_detach(&ifp->if_snd);
#endif

	if_purgeaddrs(ifp);

#ifdef INET
	in_ifdetach(ifp);
#endif

#ifdef INET6
	/*
	 * Remove all IPv6 kernel structs related to ifp.  This should be done
	 * before removing routing entries below, since IPv6 interface direct
	 * routes are expected to be removed by the IPv6-specific kernel API.
	 * Otherwise, the kernel will detect some inconsistency and bark it.
	 */
	in6_ifdetach(ifp);
#endif
	if_purgemaddrs(ifp);

	if (!vmove) {
		/*
		 * Prevent further calls into the device driver via ifnet.
		 */
		if_dead(ifp);

		/*
		 * Remove link ifaddr pointer and maybe decrement if_index.
		 * Clean up all addresses.
		 */
		ifp->if_addr = NULL;

		/* We can now free link ifaddr. */
		if (!TAILQ_EMPTY(&ifp->if_addrhead)) {
			ifa = TAILQ_FIRST(&ifp->if_addrhead);
			TAILQ_REMOVE(&ifp->if_addrhead, ifa, ifa_link);
			ifa_free(ifa);
		}
	}

	/*
	 * Delete all remaining routes using this interface
	 * Unfortuneatly the only way to do this is to slog through
	 * the entire routing table looking for routes which point
	 * to this interface...oh well...
	 */
	for (i = 1; i <= AF_MAX; i++) {
		for (j = 0; j < rt_numfibs; j++) {
			rnh = rt_tables_get_rnh(j, i);
			if (rnh == NULL)
				continue;
			RADIX_NODE_HEAD_LOCK(rnh);
			(void) rnh->rnh_walktree(rnh, if_rtdel, ifp);
			RADIX_NODE_HEAD_UNLOCK(rnh);
		}
	}

	/* Announce that the interface is gone. */
	rt_ifannouncemsg(ifp, IFAN_DEPARTURE);
	EVENTHANDLER_INVOKE(ifnet_departure_event, ifp);
	if (IS_DEFAULT_VNET(curvnet))
		devctl_notify("IFNET", ifp->if_xname, "DETACH", NULL);
	if_delgroups(ifp);

	/*
	 * We cannot hold the lock over dom_ifdetach calls as they might
	 * sleep, for example trying to drain a callout, thus open up the
	 * theoretical race with re-attaching.
	 */
	IF_AFDATA_LOCK(ifp);
	i = ifp->if_afdata_initialized;
	ifp->if_afdata_initialized = 0;
	IF_AFDATA_UNLOCK(ifp);
	for (dp = domains; i > 0 && dp; dp = dp->dom_next) {
		if (dp->dom_ifdetach && ifp->if_afdata[dp->dom_family])
			(*dp->dom_ifdetach)(ifp,
			    ifp->if_afdata[dp->dom_family]);
	}

	return (0);
}

#ifdef VIMAGE
/*
 * if_vmove() performs a limited version of if_detach() in current
 * vnet and if_attach()es the ifnet to the vnet specified as 2nd arg.
 * An attempt is made to shrink if_index in current vnet, find an
 * unused if_index in target vnet and calls if_grow() if necessary,
 * and finally find an unused if_xname for the target vnet.
 */
void
if_vmove(struct ifnet *ifp, struct vnet *new_vnet)
{
	u_short idx;
	struct if_clone *ifc;
	int rc;

	/*
	 * Detach from current vnet, but preserve LLADDR info, do not
	 * mark as dead etc. so that the ifnet can be reattached later.
	 * If we cannot find it, we lost the race to someone else.
	 */
	rc = if_detach_internal(ifp, 1, &ifc);
	if (rc != 0)
		return;

	/*
	 * Unlink the ifnet from ifindex_table[] in current vnet, and shrink
	 * the if_index for that vnet if possible.
	 *
	 * NOTE: IFNET_WLOCK/IFNET_WUNLOCK() are assumed to be unvirtualized,
	 * or we'd lock on one vnet and unlock on another.
	 */
	IFNET_WLOCK();
	ifindex_free_locked(ifp->if_index);
	IFNET_WUNLOCK();

	/*
	 * Perform interface-specific reassignment tasks, if provided by
	 * the driver.
	 */
	if (ifp->if_reassign != NULL)
		ifp->if_reassign(ifp, new_vnet, NULL);

	/*
	 * Switch to the context of the target vnet.
	 */
	CURVNET_SET_QUIET(new_vnet);

	IFNET_WLOCK();
	if (ifindex_alloc_locked(&idx) != 0) {
		IFNET_WUNLOCK();
		panic("if_index overflow");
	}
	ifp->if_index = idx;
	ifnet_setbyindex_locked(ifp->if_index, ifp);
	IFNET_WUNLOCK();

	if_attach_internal(ifp, 1, ifc);

	CURVNET_RESTORE();
}

/*
 * Move an ifnet to or from another child prison/vnet, specified by the jail id.
 */
static int
if_vmove_loan(struct thread *td, struct ifnet *ifp, char *ifname, int jid)
{
	struct prison *pr;
	struct ifnet *difp;

	/* Try to find the prison within our visibility. */
	sx_slock(&allprison_lock);
	pr = prison_find_child(td->td_ucred->cr_prison, jid);
	sx_sunlock(&allprison_lock);
	if (pr == NULL)
		return (ENXIO);
	prison_hold_locked(pr);
	mtx_unlock(&pr->pr_mtx);

	/* Do not try to move the iface from and to the same prison. */
	if (pr->pr_vnet == ifp->if_vnet) {
		prison_free(pr);
		return (EEXIST);
	}

	/* Make sure the named iface does not exists in the dst. prison/vnet. */
	/* XXX Lock interfaces to avoid races. */
	CURVNET_SET_QUIET(pr->pr_vnet);
	difp = ifunit(ifname);
	CURVNET_RESTORE();
	if (difp != NULL) {
		prison_free(pr);
		return (EEXIST);
	}

	/* Move the interface into the child jail/vnet. */
	if_vmove(ifp, pr->pr_vnet);

	/* Report the new if_xname back to the userland. */
	sprintf(ifname, "%s", ifp->if_xname);

	prison_free(pr);
	return (0);
}

static int
if_vmove_reclaim(struct thread *td, char *ifname, int jid)
{
	struct prison *pr;
	struct vnet *vnet_dst;
	struct ifnet *ifp;

	/* Try to find the prison within our visibility. */
	sx_slock(&allprison_lock);
	pr = prison_find_child(td->td_ucred->cr_prison, jid);
	sx_sunlock(&allprison_lock);
	if (pr == NULL)
		return (ENXIO);
	prison_hold_locked(pr);
	mtx_unlock(&pr->pr_mtx);

	/* Make sure the named iface exists in the source prison/vnet. */
	CURVNET_SET(pr->pr_vnet);
	ifp = ifunit(ifname);		/* XXX Lock to avoid races. */
	if (ifp == NULL) {
		CURVNET_RESTORE();
		prison_free(pr);
		return (ENXIO);
	}

	/* Do not try to move the iface from and to the same prison. */
	vnet_dst = TD_TO_VNET(td);
	if (vnet_dst == ifp->if_vnet) {
		CURVNET_RESTORE();
		prison_free(pr);
		return (EEXIST);
	}

	/* Get interface back from child jail/vnet. */
	if_vmove(ifp, vnet_dst);
	CURVNET_RESTORE();

	/* Report the new if_xname back to the userland. */
	sprintf(ifname, "%s", ifp->if_xname);

	prison_free(pr);
	return (0);
}
#endif /* VIMAGE */

/*
 * Add a group to an interface
 */
int
if_addgroup(struct ifnet *ifp, const char *groupname)
{
	struct ifg_list		*ifgl;
	struct ifg_group	*ifg = NULL;
	struct ifg_member	*ifgm;
	int 			 new = 0;

	if (groupname[0] && groupname[strlen(groupname) - 1] >= '0' &&
	    groupname[strlen(groupname) - 1] <= '9')
		return (EINVAL);

	IFNET_WLOCK();
	TAILQ_FOREACH(ifgl, &ifp->if_groups, ifgl_next)
		if (!strcmp(ifgl->ifgl_group->ifg_group, groupname)) {
			IFNET_WUNLOCK();
			return (EEXIST);
		}

	if ((ifgl = (struct ifg_list *)malloc(sizeof(struct ifg_list), M_TEMP,
	    M_NOWAIT)) == NULL) {
	    	IFNET_WUNLOCK();
		return (ENOMEM);
	}

	if ((ifgm = (struct ifg_member *)malloc(sizeof(struct ifg_member),
	    M_TEMP, M_NOWAIT)) == NULL) {
		free(ifgl, M_TEMP);
		IFNET_WUNLOCK();
		return (ENOMEM);
	}

	TAILQ_FOREACH(ifg, &V_ifg_head, ifg_next)
		if (!strcmp(ifg->ifg_group, groupname))
			break;

	if (ifg == NULL) {
		if ((ifg = (struct ifg_group *)malloc(sizeof(struct ifg_group),
		    M_TEMP, M_NOWAIT)) == NULL) {
			free(ifgl, M_TEMP);
			free(ifgm, M_TEMP);
			IFNET_WUNLOCK();
			return (ENOMEM);
		}
		strlcpy(ifg->ifg_group, groupname, sizeof(ifg->ifg_group));
		ifg->ifg_refcnt = 0;
		TAILQ_INIT(&ifg->ifg_members);
		TAILQ_INSERT_TAIL(&V_ifg_head, ifg, ifg_next);
		new = 1;
	}

	ifg->ifg_refcnt++;
	ifgl->ifgl_group = ifg;
	ifgm->ifgm_ifp = ifp;

	IF_ADDR_WLOCK(ifp);
	TAILQ_INSERT_TAIL(&ifg->ifg_members, ifgm, ifgm_next);
	TAILQ_INSERT_TAIL(&ifp->if_groups, ifgl, ifgl_next);
	IF_ADDR_WUNLOCK(ifp);

	IFNET_WUNLOCK();

	if (new)
		EVENTHANDLER_INVOKE(group_attach_event, ifg);
	EVENTHANDLER_INVOKE(group_change_event, groupname);

	return (0);
}

/*
 * Remove a group from an interface
 */
int
if_delgroup(struct ifnet *ifp, const char *groupname)
{
	struct ifg_list		*ifgl;
	struct ifg_member	*ifgm;

	IFNET_WLOCK();
	TAILQ_FOREACH(ifgl, &ifp->if_groups, ifgl_next)
		if (!strcmp(ifgl->ifgl_group->ifg_group, groupname))
			break;
	if (ifgl == NULL) {
		IFNET_WUNLOCK();
		return (ENOENT);
	}

	IF_ADDR_WLOCK(ifp);
	TAILQ_REMOVE(&ifp->if_groups, ifgl, ifgl_next);
	IF_ADDR_WUNLOCK(ifp);

	TAILQ_FOREACH(ifgm, &ifgl->ifgl_group->ifg_members, ifgm_next)
		if (ifgm->ifgm_ifp == ifp)
			break;

	if (ifgm != NULL) {
		TAILQ_REMOVE(&ifgl->ifgl_group->ifg_members, ifgm, ifgm_next);
		free(ifgm, M_TEMP);
	}

	if (--ifgl->ifgl_group->ifg_refcnt == 0) {
		TAILQ_REMOVE(&V_ifg_head, ifgl->ifgl_group, ifg_next);
		IFNET_WUNLOCK();
		EVENTHANDLER_INVOKE(group_detach_event, ifgl->ifgl_group);
		free(ifgl->ifgl_group, M_TEMP);
	} else
		IFNET_WUNLOCK();

	free(ifgl, M_TEMP);

	EVENTHANDLER_INVOKE(group_change_event, groupname);

	return (0);
}

/*
 * Remove an interface from all groups
 */
static void
if_delgroups(struct ifnet *ifp)
{
	struct ifg_list		*ifgl;
	struct ifg_member	*ifgm;
	char groupname[IFNAMSIZ];

	IFNET_WLOCK();
	while (!TAILQ_EMPTY(&ifp->if_groups)) {
		ifgl = TAILQ_FIRST(&ifp->if_groups);

		strlcpy(groupname, ifgl->ifgl_group->ifg_group, IFNAMSIZ);

		IF_ADDR_WLOCK(ifp);
		TAILQ_REMOVE(&ifp->if_groups, ifgl, ifgl_next);
		IF_ADDR_WUNLOCK(ifp);

		TAILQ_FOREACH(ifgm, &ifgl->ifgl_group->ifg_members, ifgm_next)
			if (ifgm->ifgm_ifp == ifp)
				break;

		if (ifgm != NULL) {
			TAILQ_REMOVE(&ifgl->ifgl_group->ifg_members, ifgm,
			    ifgm_next);
			free(ifgm, M_TEMP);
		}

		if (--ifgl->ifgl_group->ifg_refcnt == 0) {
			TAILQ_REMOVE(&V_ifg_head, ifgl->ifgl_group, ifg_next);
			IFNET_WUNLOCK();
			EVENTHANDLER_INVOKE(group_detach_event,
			    ifgl->ifgl_group);
			free(ifgl->ifgl_group, M_TEMP);
		} else
			IFNET_WUNLOCK();

		free(ifgl, M_TEMP);

		EVENTHANDLER_INVOKE(group_change_event, groupname);

		IFNET_WLOCK();
	}
	IFNET_WUNLOCK();
}

/*
 * Stores all groups from an interface in memory pointed
 * to by data
 */
static int
if_getgroup(struct ifgroupreq *data, struct ifnet *ifp)
{
	int			 len, error;
	struct ifg_list		*ifgl;
	struct ifg_req		 ifgrq, *ifgp;
	struct ifgroupreq	*ifgr = data;

	if (ifgr->ifgr_len == 0) {
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifgl, &ifp->if_groups, ifgl_next)
			ifgr->ifgr_len += sizeof(struct ifg_req);
		IF_ADDR_RUNLOCK(ifp);
		return (0);
	}

	len = ifgr->ifgr_len;
	ifgp = ifgr->ifgr_groups;
	/* XXX: wire */
	IF_ADDR_RLOCK(ifp);
	TAILQ_FOREACH(ifgl, &ifp->if_groups, ifgl_next) {
		if (len < sizeof(ifgrq)) {
			IF_ADDR_RUNLOCK(ifp);
			return (EINVAL);
		}
		bzero(&ifgrq, sizeof ifgrq);
		strlcpy(ifgrq.ifgrq_group, ifgl->ifgl_group->ifg_group,
		    sizeof(ifgrq.ifgrq_group));
		if ((error = copyout(&ifgrq, ifgp, sizeof(struct ifg_req)))) {
		    	IF_ADDR_RUNLOCK(ifp);
			return (error);
		}
		len -= sizeof(ifgrq);
		ifgp++;
	}
	IF_ADDR_RUNLOCK(ifp);

	return (0);
}

/*
 * Stores all members of a group in memory pointed to by data
 */
static int
if_getgroupmembers(struct ifgroupreq *data)
{
	struct ifgroupreq	*ifgr = data;
	struct ifg_group	*ifg;
	struct ifg_member	*ifgm;
	struct ifg_req		 ifgrq, *ifgp;
	int			 len, error;

	IFNET_RLOCK();
	TAILQ_FOREACH(ifg, &V_ifg_head, ifg_next)
		if (!strcmp(ifg->ifg_group, ifgr->ifgr_name))
			break;
	if (ifg == NULL) {
		IFNET_RUNLOCK();
		return (ENOENT);
	}

	if (ifgr->ifgr_len == 0) {
		TAILQ_FOREACH(ifgm, &ifg->ifg_members, ifgm_next)
			ifgr->ifgr_len += sizeof(ifgrq);
		IFNET_RUNLOCK();
		return (0);
	}

	len = ifgr->ifgr_len;
	ifgp = ifgr->ifgr_groups;
	TAILQ_FOREACH(ifgm, &ifg->ifg_members, ifgm_next) {
		if (len < sizeof(ifgrq)) {
			IFNET_RUNLOCK();
			return (EINVAL);
		}
		bzero(&ifgrq, sizeof ifgrq);
		strlcpy(ifgrq.ifgrq_member, ifgm->ifgm_ifp->if_xname,
		    sizeof(ifgrq.ifgrq_member));
		if ((error = copyout(&ifgrq, ifgp, sizeof(struct ifg_req)))) {
			IFNET_RUNLOCK();
			return (error);
		}
		len -= sizeof(ifgrq);
		ifgp++;
	}
	IFNET_RUNLOCK();

	return (0);
}

/*
 * Delete Routes for a Network Interface
 *
 * Called for each routing entry via the rnh->rnh_walktree() call above
 * to delete all route entries referencing a detaching network interface.
 *
 * Arguments:
 *	rn	pointer to node in the routing table
 *	arg	argument passed to rnh->rnh_walktree() - detaching interface
 *
 * Returns:
 *	0	successful
 *	errno	failed - reason indicated
 *
 */
static int
if_rtdel(struct radix_node *rn, void *arg)
{
	struct rtentry	*rt = (struct rtentry *)rn;
	struct ifnet	*ifp = arg;
	int		err;

	if (rt->rt_ifp == ifp) {

		/*
		 * Protect (sorta) against walktree recursion problems
		 * with cloned routes
		 */
		if ((rt->rt_flags & RTF_UP) == 0)
			return (0);

		err = rtrequest_fib(RTM_DELETE, rt_key(rt), rt->rt_gateway,
				rt_mask(rt),
				rt->rt_flags|RTF_RNH_LOCKED|RTF_PINNED,
				(struct rtentry **) NULL, rt->rt_fibnum);
		if (err) {
			log(LOG_WARNING, "if_rtdel: error %d\n", err);
		}
	}

	return (0);
}

/*
 * A compatibility function returns ifnet counter values.
 */
uint64_t
if_get_counter_default(struct ifnet *ifp, ift_counter cnt)
{

	KASSERT(cnt < IFCOUNTERS, ("%s: invalid cnt %d", __func__, cnt));
	switch (cnt) {
	case IFCOUNTER_IPACKETS:
		return (ifp->if_ipackets);
	case IFCOUNTER_IERRORS:
		return (ifp->if_ierrors);
	case IFCOUNTER_OPACKETS:
		return (ifp->if_opackets);
	case IFCOUNTER_OERRORS:
		return (ifp->if_oerrors);
	case IFCOUNTER_COLLISIONS:
		return (ifp->if_collisions);
	case IFCOUNTER_IBYTES:
		return (ifp->if_ibytes);
	case IFCOUNTER_OBYTES:
		return (ifp->if_obytes);
	case IFCOUNTER_IMCASTS:
		return (ifp->if_imcasts);
	case IFCOUNTER_OMCASTS:
		return (ifp->if_omcasts);
	case IFCOUNTER_IQDROPS:
		return (ifp->if_iqdrops);
#ifdef _IFI_OQDROPS
	case IFCOUNTER_OQDROPS:
		return (ifp->if_oqdrops);
#endif
	case IFCOUNTER_NOPROTO:
		return (ifp->if_noproto);
	default:
		break;
	};
	return (0);
}

/*
 * Increase an ifnet counter. Usually used for counters shared
 * between the stack and a driver, but function supports them all.
 */
void
if_inc_counter(struct ifnet *ifp, ift_counter cnt, int64_t inc)
{

	KASSERT(cnt < IFCOUNTERS, ("%s: invalid cnt %d", __func__, cnt));
	switch (cnt) {
	case IFCOUNTER_IPACKETS:
		ifp->if_ipackets += inc;
		break;
	case IFCOUNTER_IERRORS:
		ifp->if_ierrors += inc;
		break;
	case IFCOUNTER_OPACKETS:
		ifp->if_opackets += inc;
		break;
	case IFCOUNTER_OERRORS:
		ifp->if_oerrors += inc;
		break;
	case IFCOUNTER_COLLISIONS:
		ifp->if_collisions += inc;
		break;
	case IFCOUNTER_IBYTES:
		ifp->if_ibytes += inc;
		break;
	case IFCOUNTER_OBYTES:
		ifp->if_obytes += inc;
		break;
	case IFCOUNTER_IMCASTS:
		ifp->if_imcasts += inc;
		break;
	case IFCOUNTER_OMCASTS:
		ifp->if_omcasts += inc;
		break;
	case IFCOUNTER_IQDROPS:
		ifp->if_iqdrops += inc;
		break;
#ifdef _IFI_OQDROPS
	case IFCOUNTER_OQDROPS:
		ifp->if_oqdrops += inc;
		break;
#endif
	case IFCOUNTER_NOPROTO:
		ifp->if_noproto += inc;
		break;
	default:
		break;
	};
}

/*
 * Wrapper functions for struct ifnet address list locking macros.  These are
 * used by kernel modules to avoid encoding programming interface or binary
 * interface assumptions that may be violated when kernel-internal locking
 * approaches change.
 */
void
if_addr_rlock(struct ifnet *ifp)
{

	IF_ADDR_RLOCK(ifp);
}

void
if_addr_runlock(struct ifnet *ifp)
{

	IF_ADDR_RUNLOCK(ifp);
}

void
if_maddr_rlock(struct ifnet *ifp)
{

	IF_ADDR_RLOCK(ifp);
}

void
if_maddr_runlock(struct ifnet *ifp)
{

	IF_ADDR_RUNLOCK(ifp);
}

/*
 * Initialization, destruction and refcounting functions for ifaddrs.
 */
void
ifa_init(struct ifaddr *ifa)
{

	mtx_init(&ifa->ifa_mtx, "ifaddr", NULL, MTX_DEF);
	refcount_init(&ifa->ifa_refcnt, 1);
	ifa->if_data.ifi_datalen = sizeof(ifa->if_data);
}

void
ifa_ref(struct ifaddr *ifa)
{

	refcount_acquire(&ifa->ifa_refcnt);
}

void
ifa_free(struct ifaddr *ifa)
{

	if (refcount_release(&ifa->ifa_refcnt)) {
		mtx_destroy(&ifa->ifa_mtx);
		free(ifa, M_IFADDR);
	}
}

int
ifa_add_loopback_route(struct ifaddr *ifa, struct sockaddr *ia)
{
	int error = 0;
	struct rtentry *rt = NULL;
	struct rt_addrinfo info;
	static struct sockaddr_dl null_sdl = {sizeof(null_sdl), AF_LINK};

	bzero(&info, sizeof(info));
	info.rti_ifp = V_loif;
	info.rti_flags = ifa->ifa_flags | RTF_HOST | RTF_STATIC;
	info.rti_info[RTAX_DST] = ia;
	info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&null_sdl;
	error = rtrequest1_fib(RTM_ADD, &info, &rt, ifa->ifa_ifp->if_fib);

	if (error == 0 && rt != NULL) {
		RT_LOCK(rt);
		((struct sockaddr_dl *)rt->rt_gateway)->sdl_type  =
			ifa->ifa_ifp->if_type;
		((struct sockaddr_dl *)rt->rt_gateway)->sdl_index =
			ifa->ifa_ifp->if_index;
		RT_REMREF(rt);
		RT_UNLOCK(rt);
	} else if (error != 0)
		log(LOG_DEBUG, "%s: insertion failed: %u\n", __func__, error);

	return (error);
}

int
ifa_del_loopback_route(struct ifaddr *ifa, struct sockaddr *ia)
{
	int error = 0;
	struct rt_addrinfo info;
	struct sockaddr_dl null_sdl;

	bzero(&null_sdl, sizeof(null_sdl));
	null_sdl.sdl_len = sizeof(null_sdl);
	null_sdl.sdl_family = AF_LINK;
	null_sdl.sdl_type = ifa->ifa_ifp->if_type;
	null_sdl.sdl_index = ifa->ifa_ifp->if_index;
	bzero(&info, sizeof(info));
	info.rti_flags = ifa->ifa_flags | RTF_HOST | RTF_STATIC;
	info.rti_info[RTAX_DST] = ia;
	info.rti_info[RTAX_GATEWAY] = (struct sockaddr *)&null_sdl;
	error = rtrequest1_fib(RTM_DELETE, &info, NULL, ifa->ifa_ifp->if_fib);

	if (error != 0)
		log(LOG_DEBUG, "%s: deletion failed: %u\n", __func__, error);

	return (error);
}

/*
 * XXX: Because sockaddr_dl has deeper structure than the sockaddr
 * structs used to represent other address families, it is necessary
 * to perform a different comparison.
 */

#define	sa_equal(a1, a2)	\
	(bcmp((a1), (a2), ((a1))->sa_len) == 0)

#define	sa_dl_equal(a1, a2)	\
	((((struct sockaddr_dl *)(a1))->sdl_len ==			\
	 ((struct sockaddr_dl *)(a2))->sdl_len) &&			\
	 (bcmp(LLADDR((struct sockaddr_dl *)(a1)),			\
	       LLADDR((struct sockaddr_dl *)(a2)),			\
	       ((struct sockaddr_dl *)(a1))->sdl_alen) == 0))

/*
 * Locate an interface based on a complete address.
 */
/*ARGSUSED*/
static struct ifaddr *
ifa_ifwithaddr_internal(struct sockaddr *addr, int getref)
{
	struct ifnet *ifp;
	struct ifaddr *ifa;

	IFNET_RLOCK_NOSLEEP();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != addr->sa_family)
				continue;
			if (sa_equal(addr, ifa->ifa_addr)) {
				if (getref)
					ifa_ref(ifa);
				IF_ADDR_RUNLOCK(ifp);
				goto done;
			}
			/* IP6 doesn't have broadcast */
			if ((ifp->if_flags & IFF_BROADCAST) &&
			    ifa->ifa_broadaddr &&
			    ifa->ifa_broadaddr->sa_len != 0 &&
			    sa_equal(ifa->ifa_broadaddr, addr)) {
				if (getref)
					ifa_ref(ifa);
				IF_ADDR_RUNLOCK(ifp);
				goto done;
			}
		}
		IF_ADDR_RUNLOCK(ifp);
	}
	ifa = NULL;
done:
	IFNET_RUNLOCK_NOSLEEP();
	return (ifa);
}

struct ifaddr *
ifa_ifwithaddr(struct sockaddr *addr)
{

	return (ifa_ifwithaddr_internal(addr, 1));
}

int
ifa_ifwithaddr_check(struct sockaddr *addr)
{

	return (ifa_ifwithaddr_internal(addr, 0) != NULL);
}

/*
 * Locate an interface based on the broadcast address.
 */
/* ARGSUSED */
struct ifaddr *
ifa_ifwithbroadaddr(struct sockaddr *addr)
{
	struct ifnet *ifp;
	struct ifaddr *ifa;

	IFNET_RLOCK_NOSLEEP();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != addr->sa_family)
				continue;
			if ((ifp->if_flags & IFF_BROADCAST) &&
			    ifa->ifa_broadaddr &&
			    ifa->ifa_broadaddr->sa_len != 0 &&
			    sa_equal(ifa->ifa_broadaddr, addr)) {
				ifa_ref(ifa);
				IF_ADDR_RUNLOCK(ifp);
				goto done;
			}
		}
		IF_ADDR_RUNLOCK(ifp);
	}
	ifa = NULL;
done:
	IFNET_RUNLOCK_NOSLEEP();
	return (ifa);
}

/*
 * Locate the point to point interface with a given destination address.
 */
/*ARGSUSED*/
struct ifaddr *
ifa_ifwithdstaddr_fib(struct sockaddr *addr, int fibnum)
{
	struct ifnet *ifp;
	struct ifaddr *ifa;

	IFNET_RLOCK_NOSLEEP();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		if ((ifp->if_flags & IFF_POINTOPOINT) == 0)
			continue;
		if ((fibnum != RT_ALL_FIBS) && (ifp->if_fib != fibnum))
			continue;
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family != addr->sa_family)
				continue;
			if (ifa->ifa_dstaddr != NULL &&
			    sa_equal(addr, ifa->ifa_dstaddr)) {
				ifa_ref(ifa);
				IF_ADDR_RUNLOCK(ifp);
				goto done;
			}
		}
		IF_ADDR_RUNLOCK(ifp);
	}
	ifa = NULL;
done:
	IFNET_RUNLOCK_NOSLEEP();
	return (ifa);
}

struct ifaddr *
ifa_ifwithdstaddr(struct sockaddr *addr)
{

	return (ifa_ifwithdstaddr_fib(addr, RT_ALL_FIBS));
}

/*
 * Find an interface on a specific network.  If many, choice
 * is most specific found.
 */
struct ifaddr *
ifa_ifwithnet_fib(struct sockaddr *addr, int ignore_ptp, int fibnum)
{
	struct ifnet *ifp;
	struct ifaddr *ifa;
	struct ifaddr *ifa_maybe = NULL;
	u_int af = addr->sa_family;
	char *addr_data = addr->sa_data, *cplim;

	/*
	 * AF_LINK addresses can be looked up directly by their index number,
	 * so do that if we can.
	 */
	if (af == AF_LINK) {
	    struct sockaddr_dl *sdl = (struct sockaddr_dl *)addr;
	    if (sdl->sdl_index && sdl->sdl_index <= V_if_index)
		return (ifaddr_byindex(sdl->sdl_index));
	}

	/*
	 * Scan though each interface, looking for ones that have addresses
	 * in this address family and the requested fib.  Maintain a reference
	 * on ifa_maybe once we find one, as we release the IF_ADDR_RLOCK() that
	 * kept it stable when we move onto the next interface.
	 */
	IFNET_RLOCK_NOSLEEP();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		if ((fibnum != RT_ALL_FIBS) && (ifp->if_fib != fibnum))
			continue;
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			char *cp, *cp2, *cp3;

			if (ifa->ifa_addr->sa_family != af)
next:				continue;
			if (af == AF_INET && 
			    ifp->if_flags & IFF_POINTOPOINT && !ignore_ptp) {
				/*
				 * This is a bit broken as it doesn't
				 * take into account that the remote end may
				 * be a single node in the network we are
				 * looking for.
				 * The trouble is that we don't know the
				 * netmask for the remote end.
				 */
				if (ifa->ifa_dstaddr != NULL &&
				    sa_equal(addr, ifa->ifa_dstaddr)) {
					ifa_ref(ifa);
					IF_ADDR_RUNLOCK(ifp);
					goto done;
				}
			} else {
				/*
				 * if we have a special address handler,
				 * then use it instead of the generic one.
				 */
				if (ifa->ifa_claim_addr) {
					if ((*ifa->ifa_claim_addr)(ifa, addr)) {
						ifa_ref(ifa);
						IF_ADDR_RUNLOCK(ifp);
						goto done;
					}
					continue;
				}

				/*
				 * Scan all the bits in the ifa's address.
				 * If a bit dissagrees with what we are
				 * looking for, mask it with the netmask
				 * to see if it really matters.
				 * (A byte at a time)
				 */
				if (ifa->ifa_netmask == 0)
					continue;
				cp = addr_data;
				cp2 = ifa->ifa_addr->sa_data;
				cp3 = ifa->ifa_netmask->sa_data;
				cplim = ifa->ifa_netmask->sa_len
					+ (char *)ifa->ifa_netmask;
				while (cp3 < cplim)
					if ((*cp++ ^ *cp2++) & *cp3++)
						goto next; /* next address! */
				/*
				 * If the netmask of what we just found
				 * is more specific than what we had before
				 * (if we had one), or if the virtual status
				 * of new prefix is better than of the old one,
				 * then remember the new one before continuing
				 * to search for an even better one.
				 */
				if (ifa_maybe == NULL ||
				    ifa_preferred(ifa_maybe, ifa) ||
				    rn_refines((caddr_t)ifa->ifa_netmask,
				    (caddr_t)ifa_maybe->ifa_netmask)) {
					if (ifa_maybe != NULL)
						ifa_free(ifa_maybe);
					ifa_maybe = ifa;
					ifa_ref(ifa_maybe);
				}
			}
		}
		IF_ADDR_RUNLOCK(ifp);
	}
	ifa = ifa_maybe;
	ifa_maybe = NULL;
done:
	IFNET_RUNLOCK_NOSLEEP();
	if (ifa_maybe != NULL)
		ifa_free(ifa_maybe);
	return (ifa);
}

struct ifaddr *
ifa_ifwithnet(struct sockaddr *addr, int ignore_ptp)
{

	return (ifa_ifwithnet_fib(addr, ignore_ptp, RT_ALL_FIBS));
}

/*
 * Find an interface address specific to an interface best matching
 * a given address.
 */
struct ifaddr *
ifaof_ifpforaddr(struct sockaddr *addr, struct ifnet *ifp)
{
	struct ifaddr *ifa;
	char *cp, *cp2, *cp3;
	char *cplim;
	struct ifaddr *ifa_maybe = NULL;
	u_int af = addr->sa_family;

	if (af >= AF_MAX)
		return (NULL);
	IF_ADDR_RLOCK(ifp);
	TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
		if (ifa->ifa_addr->sa_family != af)
			continue;
		if (ifa_maybe == NULL)
			ifa_maybe = ifa;
		if (ifa->ifa_netmask == 0) {
			if (sa_equal(addr, ifa->ifa_addr) ||
			    (ifa->ifa_dstaddr &&
			    sa_equal(addr, ifa->ifa_dstaddr)))
				goto done;
			continue;
		}
		if (ifp->if_flags & IFF_POINTOPOINT) {
			if (sa_equal(addr, ifa->ifa_dstaddr))
				goto done;
		} else {
			cp = addr->sa_data;
			cp2 = ifa->ifa_addr->sa_data;
			cp3 = ifa->ifa_netmask->sa_data;
			cplim = ifa->ifa_netmask->sa_len + (char *)ifa->ifa_netmask;
			for (; cp3 < cplim; cp3++)
				if ((*cp++ ^ *cp2++) & *cp3)
					break;
			if (cp3 == cplim)
				goto done;
		}
	}
	ifa = ifa_maybe;
done:
	if (ifa != NULL)
		ifa_ref(ifa);
	IF_ADDR_RUNLOCK(ifp);
	return (ifa);
}

/*
 * See whether new ifa is better than current one:
 * 1) A non-virtual one is preferred over virtual.
 * 2) A virtual in master state preferred over any other state.
 *
 * Used in several address selecting functions.
 */
int
ifa_preferred(struct ifaddr *cur, struct ifaddr *next)
{

	return (cur->ifa_carp && (!next->ifa_carp ||
	    ((*carp_master_p)(next) && !(*carp_master_p)(cur))));
}

#include <net/if_llatbl.h>

/*
 * Default action when installing a route with a Link Level gateway.
 * Lookup an appropriate real ifa to point to.
 * This should be moved to /sys/net/link.c eventually.
 */
static void
link_rtrequest(int cmd, struct rtentry *rt, struct rt_addrinfo *info)
{
	struct ifaddr *ifa, *oifa;
	struct sockaddr *dst;
	struct ifnet *ifp;

	RT_LOCK_ASSERT(rt);

	if (cmd != RTM_ADD || ((ifa = rt->rt_ifa) == 0) ||
	    ((ifp = ifa->ifa_ifp) == 0) || ((dst = rt_key(rt)) == 0))
		return;
	ifa = ifaof_ifpforaddr(dst, ifp);
	if (ifa) {
		oifa = rt->rt_ifa;
		rt->rt_ifa = ifa;
		ifa_free(oifa);
		if (ifa->ifa_rtrequest && ifa->ifa_rtrequest != link_rtrequest)
			ifa->ifa_rtrequest(cmd, rt, info);
	}
}

/*
 * Mark an interface down and notify protocols of
 * the transition.
 */
static void
if_unroute(struct ifnet *ifp, int flag, int fam)
{
	struct ifaddr *ifa;

	KASSERT(flag == IFF_UP, ("if_unroute: flag != IFF_UP"));

	ifp->if_flags &= ~flag;
	getmicrotime(&ifp->if_lastchange);
	TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)
		if (fam == PF_UNSPEC || (fam == ifa->ifa_addr->sa_family))
			pfctlinput(PRC_IFDOWN, ifa->ifa_addr);
	ifp->if_qflush(ifp);

	if (ifp->if_carp)
		(*carp_linkstate_p)(ifp);
	rt_ifmsg(ifp);
}

/*
 * Mark an interface up and notify protocols of
 * the transition.
 */
static void
if_route(struct ifnet *ifp, int flag, int fam)
{
	struct ifaddr *ifa;

	KASSERT(flag == IFF_UP, ("if_route: flag != IFF_UP"));

	ifp->if_flags |= flag;
	getmicrotime(&ifp->if_lastchange);
	TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link)
		if (fam == PF_UNSPEC || (fam == ifa->ifa_addr->sa_family))
			pfctlinput(PRC_IFUP, ifa->ifa_addr);
	if (ifp->if_carp)
		(*carp_linkstate_p)(ifp);
	rt_ifmsg(ifp);
#ifdef INET6
	in6_if_up(ifp);
#endif
}

void	(*vlan_link_state_p)(struct ifnet *);	/* XXX: private from if_vlan */
void	(*vlan_trunk_cap_p)(struct ifnet *);		/* XXX: private from if_vlan */
struct ifnet *(*vlan_trunkdev_p)(struct ifnet *);
struct	ifnet *(*vlan_devat_p)(struct ifnet *, uint16_t);
int	(*vlan_tag_p)(struct ifnet *, uint16_t *);
int	(*vlan_setcookie_p)(struct ifnet *, void *);
void	*(*vlan_cookie_p)(struct ifnet *);

/*
 * Handle a change in the interface link state. To avoid LORs
 * between driver lock and upper layer locks, as well as possible
 * recursions, we post event to taskqueue, and all job
 * is done in static do_link_state_change().
 */
void
if_link_state_change(struct ifnet *ifp, int link_state)
{
	/* Return if state hasn't changed. */
	if (ifp->if_link_state == link_state)
		return;

	ifp->if_link_state = link_state;

	taskqueue_enqueue(taskqueue_swi, &ifp->if_linktask);
}

static void
do_link_state_change(void *arg, int pending)
{
	struct ifnet *ifp = (struct ifnet *)arg;
	int link_state = ifp->if_link_state;
	CURVNET_SET(ifp->if_vnet);

	/* Notify that the link state has changed. */
	rt_ifmsg(ifp);
	if (ifp->if_vlantrunk != NULL)
		(*vlan_link_state_p)(ifp);

	if ((ifp->if_type == IFT_ETHER || ifp->if_type == IFT_L2VLAN) &&
	    IFP2AC(ifp)->ac_netgraph != NULL)
		(*ng_ether_link_state_p)(ifp, link_state);
	if (ifp->if_carp)
		(*carp_linkstate_p)(ifp);
	if (ifp->if_bridge)
		(*bridge_linkstate_p)(ifp);
	if (ifp->if_lagg)
		(*lagg_linkstate_p)(ifp, link_state);

	if (IS_DEFAULT_VNET(curvnet))
		devctl_notify("IFNET", ifp->if_xname,
		    (link_state == LINK_STATE_UP) ? "LINK_UP" : "LINK_DOWN",
		    NULL);
	if (pending > 1)
		if_printf(ifp, "%d link states coalesced\n", pending);
	if (log_link_state_change)
		log(LOG_NOTICE, "%s: link state changed to %s\n", ifp->if_xname,
		    (link_state == LINK_STATE_UP) ? "UP" : "DOWN" );
	EVENTHANDLER_INVOKE(ifnet_link_event, ifp, ifp->if_link_state);
	CURVNET_RESTORE();
}

/*
 * Mark an interface down and notify protocols of
 * the transition.
 */
void
if_down(struct ifnet *ifp)
{

	if_unroute(ifp, IFF_UP, AF_UNSPEC);
}

/*
 * Mark an interface up and notify protocols of
 * the transition.
 */
void
if_up(struct ifnet *ifp)
{

	if_route(ifp, IFF_UP, AF_UNSPEC);
}

/*
 * Flush an interface queue.
 */
void
if_qflush(struct ifnet *ifp)
{
	struct mbuf *m, *n;
	struct ifaltq *ifq;
	
	ifq = &ifp->if_snd;
	IFQ_LOCK(ifq);
#ifdef ALTQ
	if (ALTQ_IS_ENABLED(ifq))
		ALTQ_PURGE(ifq);
#endif
	n = ifq->ifq_head;
	while ((m = n) != 0) {
		n = m->m_nextpkt;
		m_freem(m);
	}
	ifq->ifq_head = 0;
	ifq->ifq_tail = 0;
	ifq->ifq_len = 0;
	IFQ_UNLOCK(ifq);
}

/*
 * Map interface name to interface structure pointer, with or without
 * returning a reference.
 */
struct ifnet *
ifunit_ref(const char *name)
{
	struct ifnet *ifp;

	IFNET_RLOCK_NOSLEEP();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		if (strncmp(name, ifp->if_xname, IFNAMSIZ) == 0 &&
		    !(ifp->if_flags & IFF_DYING))
			break;
	}
	if (ifp != NULL)
		if_ref(ifp);
	IFNET_RUNLOCK_NOSLEEP();
	return (ifp);
}

struct ifnet *
ifunit(const char *name)
{
	struct ifnet *ifp;

	IFNET_RLOCK_NOSLEEP();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		if (strncmp(name, ifp->if_xname, IFNAMSIZ) == 0)
			break;
	}
	IFNET_RUNLOCK_NOSLEEP();
	return (ifp);
}

/*
 * Hardware specific interface ioctls.
 */
static int
ifhwioctl(u_long cmd, struct ifnet *ifp, caddr_t data, struct thread *td)
{
	struct ifreq *ifr;
	struct ifstat *ifs;
	int error = 0;
	int new_flags, temp_flags;
	size_t namelen, onamelen;
	size_t descrlen;
	char *descrbuf, *odescrbuf;
	char new_name[IFNAMSIZ];
	struct ifaddr *ifa;
	struct sockaddr_dl *sdl;

	ifr = (struct ifreq *)data;
	switch (cmd) {
	case SIOCGIFINDEX:
		ifr->ifr_index = ifp->if_index;
		break;

	case SIOCGIFFLAGS:
		temp_flags = ifp->if_flags | ifp->if_drv_flags;
		ifr->ifr_flags = temp_flags & 0xffff;
		ifr->ifr_flagshigh = temp_flags >> 16;
		break;

	case SIOCGIFCAP:
		ifr->ifr_reqcap = ifp->if_capabilities;
		ifr->ifr_curcap = ifp->if_capenable;
		break;

#ifdef MAC
	case SIOCGIFMAC:
		error = mac_ifnet_ioctl_get(td->td_ucred, ifr, ifp);
		break;
#endif

	case SIOCGIFMETRIC:
		ifr->ifr_metric = ifp->if_metric;
		break;

	case SIOCGIFMTU:
		ifr->ifr_mtu = ifp->if_mtu;
		break;

	case SIOCGIFPHYS:
		ifr->ifr_phys = ifp->if_physical;
		break;

	case SIOCGIFDESCR:
		error = 0;
		sx_slock(&ifdescr_sx);
		if (ifp->if_description == NULL)
			error = ENOMSG;
		else {
			/* space for terminating nul */
			descrlen = strlen(ifp->if_description) + 1;
			if (ifr->ifr_buffer.length < descrlen)
				ifr->ifr_buffer.buffer = NULL;
			else
				error = copyout(ifp->if_description,
				    ifr->ifr_buffer.buffer, descrlen);
			ifr->ifr_buffer.length = descrlen;
		}
		sx_sunlock(&ifdescr_sx);
		break;

	case SIOCSIFDESCR:
		error = priv_check(td, PRIV_NET_SETIFDESCR);
		if (error)
			return (error);

		/*
		 * Copy only (length-1) bytes to make sure that
		 * if_description is always nul terminated.  The
		 * length parameter is supposed to count the
		 * terminating nul in.
		 */
		if (ifr->ifr_buffer.length > ifdescr_maxlen)
			return (ENAMETOOLONG);
		else if (ifr->ifr_buffer.length == 0)
			descrbuf = NULL;
		else {
			descrbuf = malloc(ifr->ifr_buffer.length, M_IFDESCR,
			    M_WAITOK | M_ZERO);
			error = copyin(ifr->ifr_buffer.buffer, descrbuf,
			    ifr->ifr_buffer.length - 1);
			if (error) {
				free(descrbuf, M_IFDESCR);
				break;
			}
		}

		sx_xlock(&ifdescr_sx);
		odescrbuf = ifp->if_description;
		ifp->if_description = descrbuf;
		sx_xunlock(&ifdescr_sx);

		getmicrotime(&ifp->if_lastchange);
		free(odescrbuf, M_IFDESCR);
		break;

	case SIOCGIFFIB:
		ifr->ifr_fib = ifp->if_fib;
		break;

	case SIOCSIFFIB:
		error = priv_check(td, PRIV_NET_SETIFFIB);
		if (error)
			return (error);
		if (ifr->ifr_fib >= rt_numfibs)
			return (EINVAL);

		ifp->if_fib = ifr->ifr_fib;
		break;

	case SIOCSIFFLAGS:
		error = priv_check(td, PRIV_NET_SETIFFLAGS);
		if (error)
			return (error);
		/*
		 * Currently, no driver owned flags pass the IFF_CANTCHANGE
		 * check, so we don't need special handling here yet.
		 */
		new_flags = (ifr->ifr_flags & 0xffff) |
		    (ifr->ifr_flagshigh << 16);
		if (ifp->if_flags & IFF_SMART) {
			/* Smart drivers twiddle their own routes */
		} else if (ifp->if_flags & IFF_UP &&
		    (new_flags & IFF_UP) == 0) {
			if_down(ifp);
		} else if (new_flags & IFF_UP &&
		    (ifp->if_flags & IFF_UP) == 0) {
			if_up(ifp);
		}
		/* See if permanently promiscuous mode bit is about to flip */
		if ((ifp->if_flags ^ new_flags) & IFF_PPROMISC) {
			if (new_flags & IFF_PPROMISC)
				ifp->if_flags |= IFF_PROMISC;
			else if (ifp->if_pcount == 0)
				ifp->if_flags &= ~IFF_PROMISC;
			log(LOG_INFO, "%s: permanently promiscuous mode %s\n",
			    ifp->if_xname,
			    (new_flags & IFF_PPROMISC) ? "enabled" : "disabled");
		}
		ifp->if_flags = (ifp->if_flags & IFF_CANTCHANGE) |
			(new_flags &~ IFF_CANTCHANGE);
		if (ifp->if_ioctl) {
			(void) (*ifp->if_ioctl)(ifp, cmd, data);
		}
		getmicrotime(&ifp->if_lastchange);
		break;

	case SIOCSIFCAP:
		error = priv_check(td, PRIV_NET_SETIFCAP);
		if (error)
			return (error);
		if (ifp->if_ioctl == NULL)
			return (EOPNOTSUPP);
		if (ifr->ifr_reqcap & ~ifp->if_capabilities)
			return (EINVAL);
		error = (*ifp->if_ioctl)(ifp, cmd, data);
		if (error == 0)
			getmicrotime(&ifp->if_lastchange);
		break;

#ifdef MAC
	case SIOCSIFMAC:
		error = mac_ifnet_ioctl_set(td->td_ucred, ifr, ifp);
		break;
#endif

	case SIOCSIFNAME:
		error = priv_check(td, PRIV_NET_SETIFNAME);
		if (error)
			return (error);
		error = copyinstr(ifr->ifr_data, new_name, IFNAMSIZ, NULL);
		if (error != 0)
			return (error);
		if (new_name[0] == '\0')
			return (EINVAL);
		if (ifunit(new_name) != NULL)
			return (EEXIST);

		/*
		 * XXX: Locking.  Nothing else seems to lock if_flags,
		 * and there are numerous other races with the
		 * ifunit() checks not being atomic with namespace
		 * changes (renames, vmoves, if_attach, etc).
		 */
		ifp->if_flags |= IFF_RENAMING;
		
		/* Announce the departure of the interface. */
		rt_ifannouncemsg(ifp, IFAN_DEPARTURE);
		EVENTHANDLER_INVOKE(ifnet_departure_event, ifp);

		log(LOG_INFO, "%s: changing name to '%s'\n",
		    ifp->if_xname, new_name);

		strlcpy(ifp->if_xname, new_name, sizeof(ifp->if_xname));
		ifa = ifp->if_addr;
		IFA_LOCK(ifa);
		sdl = (struct sockaddr_dl *)ifa->ifa_addr;
		namelen = strlen(new_name);
		onamelen = sdl->sdl_nlen;
		/*
		 * Move the address if needed.  This is safe because we
		 * allocate space for a name of length IFNAMSIZ when we
		 * create this in if_attach().
		 */
		if (namelen != onamelen) {
			bcopy(sdl->sdl_data + onamelen,
			    sdl->sdl_data + namelen, sdl->sdl_alen);
		}
		bcopy(new_name, sdl->sdl_data, namelen);
		sdl->sdl_nlen = namelen;
		sdl = (struct sockaddr_dl *)ifa->ifa_netmask;
		bzero(sdl->sdl_data, onamelen);
		while (namelen != 0)
			sdl->sdl_data[--namelen] = 0xff;
		IFA_UNLOCK(ifa);

		EVENTHANDLER_INVOKE(ifnet_arrival_event, ifp);
		/* Announce the return of the interface. */
		rt_ifannouncemsg(ifp, IFAN_ARRIVAL);

		ifp->if_flags &= ~IFF_RENAMING;
		break;

#ifdef VIMAGE
	case SIOCSIFVNET:
		error = priv_check(td, PRIV_NET_SETIFVNET);
		if (error)
			return (error);
		error = if_vmove_loan(td, ifp, ifr->ifr_name, ifr->ifr_jid);
		break;
#endif

	case SIOCSIFMETRIC:
		error = priv_check(td, PRIV_NET_SETIFMETRIC);
		if (error)
			return (error);
		ifp->if_metric = ifr->ifr_metric;
		getmicrotime(&ifp->if_lastchange);
		break;

	case SIOCSIFPHYS:
		error = priv_check(td, PRIV_NET_SETIFPHYS);
		if (error)
			return (error);
		if (ifp->if_ioctl == NULL)
			return (EOPNOTSUPP);
		error = (*ifp->if_ioctl)(ifp, cmd, data);
		if (error == 0)
			getmicrotime(&ifp->if_lastchange);
		break;

	case SIOCSIFMTU:
	{
		u_long oldmtu = ifp->if_mtu;

		error = priv_check(td, PRIV_NET_SETIFMTU);
		if (error)
			return (error);
		if (ifr->ifr_mtu < IF_MINMTU || ifr->ifr_mtu > IF_MAXMTU)
			return (EINVAL);
		if (ifp->if_ioctl == NULL)
			return (EOPNOTSUPP);
		error = (*ifp->if_ioctl)(ifp, cmd, data);
		if (error == 0) {
			getmicrotime(&ifp->if_lastchange);
			rt_ifmsg(ifp);
		}
		/*
		 * If the link MTU changed, do network layer specific procedure.
		 */
		if (ifp->if_mtu != oldmtu) {
#ifdef INET6
			nd6_setmtu(ifp);
#endif
		}
		break;
	}

	case SIOCADDMULTI:
	case SIOCDELMULTI:
		if (cmd == SIOCADDMULTI)
			error = priv_check(td, PRIV_NET_ADDMULTI);
		else
			error = priv_check(td, PRIV_NET_DELMULTI);
		if (error)
			return (error);

		/* Don't allow group membership on non-multicast interfaces. */
		if ((ifp->if_flags & IFF_MULTICAST) == 0)
			return (EOPNOTSUPP);

		/* Don't let users screw up protocols' entries. */
		if (ifr->ifr_addr.sa_family != AF_LINK)
			return (EINVAL);

		if (cmd == SIOCADDMULTI) {
			struct ifmultiaddr *ifma;

			/*
			 * Userland is only permitted to join groups once
			 * via the if_addmulti() KPI, because it cannot hold
			 * struct ifmultiaddr * between calls. It may also
			 * lose a race while we check if the membership
			 * already exists.
			 */
			IF_ADDR_RLOCK(ifp);
			ifma = if_findmulti(ifp, &ifr->ifr_addr);
			IF_ADDR_RUNLOCK(ifp);
			if (ifma != NULL)
				error = EADDRINUSE;
			else
				error = if_addmulti(ifp, &ifr->ifr_addr, &ifma);
		} else {
			error = if_delmulti(ifp, &ifr->ifr_addr);
		}
		if (error == 0)
			getmicrotime(&ifp->if_lastchange);
		break;

	case SIOCSIFPHYADDR:
	case SIOCDIFPHYADDR:
#ifdef INET6
	case SIOCSIFPHYADDR_IN6:
#endif
	case SIOCSLIFPHYADDR:
	case SIOCSIFMEDIA:
	case SIOCSIFGENERIC:
		error = priv_check(td, PRIV_NET_HWIOCTL);
		if (error)
			return (error);
		if (ifp->if_ioctl == NULL)
			return (EOPNOTSUPP);
		error = (*ifp->if_ioctl)(ifp, cmd, data);
		if (error == 0)
			getmicrotime(&ifp->if_lastchange);
		break;

	case SIOCGIFSTATUS:
		ifs = (struct ifstat *)data;
		ifs->ascii[0] = '\0';

	case SIOCGIFPSRCADDR:
	case SIOCGIFPDSTADDR:
	case SIOCGLIFPHYADDR:
	case SIOCGIFMEDIA:
	case SIOCGIFXMEDIA:
	case SIOCGIFGENERIC:
		if (ifp->if_ioctl == NULL)
			return (EOPNOTSUPP);
		error = (*ifp->if_ioctl)(ifp, cmd, data);
		break;

	case SIOCSIFLLADDR:
		error = priv_check(td, PRIV_NET_SETLLADDR);
		if (error)
			return (error);
		error = if_setlladdr(ifp,
		    ifr->ifr_addr.sa_data, ifr->ifr_addr.sa_len);
		EVENTHANDLER_INVOKE(iflladdr_event, ifp);
		break;

	case SIOCAIFGROUP:
	{
		struct ifgroupreq *ifgr = (struct ifgroupreq *)ifr;

		error = priv_check(td, PRIV_NET_ADDIFGROUP);
		if (error)
			return (error);
		if ((error = if_addgroup(ifp, ifgr->ifgr_group)))
			return (error);
		break;
	}

	case SIOCGIFGROUP:
		if ((error = if_getgroup((struct ifgroupreq *)ifr, ifp)))
			return (error);
		break;

	case SIOCDIFGROUP:
	{
		struct ifgroupreq *ifgr = (struct ifgroupreq *)ifr;

		error = priv_check(td, PRIV_NET_DELIFGROUP);
		if (error)
			return (error);
		if ((error = if_delgroup(ifp, ifgr->ifgr_group)))
			return (error);
		break;
	}

	default:
		error = ENOIOCTL;
		break;
	}
	return (error);
}

#ifdef COMPAT_FREEBSD32
struct ifconf32 {
	int32_t	ifc_len;
	union {
		uint32_t	ifcu_buf;
		uint32_t	ifcu_req;
	} ifc_ifcu;
};
#define	SIOCGIFCONF32	_IOWR('i', 36, struct ifconf32)
#endif

/*
 * Interface ioctls.
 */
int
ifioctl(struct socket *so, u_long cmd, caddr_t data, struct thread *td)
{
	struct ifnet *ifp;
	struct ifreq *ifr;
	int error;
	int oif_flags;

	CURVNET_SET(so->so_vnet);
	switch (cmd) {
	case SIOCGIFCONF:
	case OSIOCGIFCONF:
		error = ifconf(cmd, data);
		CURVNET_RESTORE();
		return (error);

#ifdef COMPAT_FREEBSD32
	case SIOCGIFCONF32:
		{
			struct ifconf32 *ifc32;
			struct ifconf ifc;

			ifc32 = (struct ifconf32 *)data;
			ifc.ifc_len = ifc32->ifc_len;
			ifc.ifc_buf = PTRIN(ifc32->ifc_buf);

			error = ifconf(SIOCGIFCONF, (void *)&ifc);
			CURVNET_RESTORE();
			if (error == 0)
				ifc32->ifc_len = ifc.ifc_len;
			return (error);
		}
#endif
	}
	ifr = (struct ifreq *)data;

	switch (cmd) {
#ifdef VIMAGE
	case SIOCSIFRVNET:
		error = priv_check(td, PRIV_NET_SETIFVNET);
		if (error == 0)
			error = if_vmove_reclaim(td, ifr->ifr_name,
			    ifr->ifr_jid);
		CURVNET_RESTORE();
		return (error);
#endif
	case SIOCIFCREATE:
	case SIOCIFCREATE2:
		error = priv_check(td, PRIV_NET_IFCREATE);
		if (error == 0)
			error = if_clone_create(ifr->ifr_name,
			    sizeof(ifr->ifr_name),
			    cmd == SIOCIFCREATE2 ? ifr->ifr_data : NULL);
		CURVNET_RESTORE();
		return (error);
	case SIOCIFDESTROY:
		error = priv_check(td, PRIV_NET_IFDESTROY);
		if (error == 0)
			error = if_clone_destroy(ifr->ifr_name);
		CURVNET_RESTORE();
		return (error);

	case SIOCIFGCLONERS:
		error = if_clone_list((struct if_clonereq *)data);
		CURVNET_RESTORE();
		return (error);
	case SIOCGIFGMEMB:
		error = if_getgroupmembers((struct ifgroupreq *)data);
		CURVNET_RESTORE();
		return (error);
#if defined(INET) || defined(INET6)
	case SIOCSVH:
	case SIOCGVH:
		if (carp_ioctl_p == NULL)
			error = EPROTONOSUPPORT;
		else
			error = (*carp_ioctl_p)(ifr, cmd, td);
		CURVNET_RESTORE();
		return (error);
#endif
	}

	ifp = ifunit_ref(ifr->ifr_name);
	if (ifp == NULL) {
		CURVNET_RESTORE();
		return (ENXIO);
	}

	error = ifhwioctl(cmd, ifp, data, td);
	if (error != ENOIOCTL) {
		if_rele(ifp);
		CURVNET_RESTORE();
		return (error);
	}

	oif_flags = ifp->if_flags;
	if (so->so_proto == NULL) {
		if_rele(ifp);
		CURVNET_RESTORE();
		return (EOPNOTSUPP);
	}

	/*
	 * Pass the request on to the socket control method, and if the
	 * latter returns EOPNOTSUPP, directly to the interface.
	 *
	 * Make an exception for the legacy SIOCSIF* requests.  Drivers
	 * trust SIOCSIFADDR et al to come from an already privileged
	 * layer, and do not perform any credentials checks or input
	 * validation.
	 */
#ifndef COMPAT_43
	error = ((*so->so_proto->pr_usrreqs->pru_control)(so, cmd,
								 data,
								 ifp, td));
	if (error == EOPNOTSUPP && ifp != NULL && ifp->if_ioctl != NULL &&
	    cmd != SIOCSIFADDR && cmd != SIOCSIFBRDADDR &&
	    cmd != SIOCSIFDSTADDR && cmd != SIOCSIFNETMASK)
		error = (*ifp->if_ioctl)(ifp, cmd, data);
#else
	{
		u_long ocmd = cmd;

		switch (cmd) {

		case SIOCSIFDSTADDR:
		case SIOCSIFADDR:
		case SIOCSIFBRDADDR:
		case SIOCSIFNETMASK:
#if BYTE_ORDER != BIG_ENDIAN
			if (ifr->ifr_addr.sa_family == 0 &&
			    ifr->ifr_addr.sa_len < 16) {
				ifr->ifr_addr.sa_family = ifr->ifr_addr.sa_len;
				ifr->ifr_addr.sa_len = 16;
			}
#else
			if (ifr->ifr_addr.sa_len == 0)
				ifr->ifr_addr.sa_len = 16;
#endif
			break;

		case OSIOCGIFADDR:
			cmd = SIOCGIFADDR;
			break;

		case OSIOCGIFDSTADDR:
			cmd = SIOCGIFDSTADDR;
			break;

		case OSIOCGIFBRDADDR:
			cmd = SIOCGIFBRDADDR;
			break;

		case OSIOCGIFNETMASK:
			cmd = SIOCGIFNETMASK;
		}
		error =  ((*so->so_proto->pr_usrreqs->pru_control)(so,
								   cmd,
								   data,
								   ifp, td));
		if (error == EOPNOTSUPP && ifp != NULL &&
		    ifp->if_ioctl != NULL &&
		    cmd != SIOCSIFADDR && cmd != SIOCSIFBRDADDR &&
		    cmd != SIOCSIFDSTADDR && cmd != SIOCSIFNETMASK)
			error = (*ifp->if_ioctl)(ifp, cmd, data);
		switch (ocmd) {

		case OSIOCGIFADDR:
		case OSIOCGIFDSTADDR:
		case OSIOCGIFBRDADDR:
		case OSIOCGIFNETMASK:
			*(u_short *)&ifr->ifr_addr = ifr->ifr_addr.sa_family;

		}
	}
#endif /* COMPAT_43 */

	if ((oif_flags ^ ifp->if_flags) & IFF_UP) {
#ifdef INET6
		if (ifp->if_flags & IFF_UP)
			in6_if_up(ifp);
#endif
	}
	if_rele(ifp);
	CURVNET_RESTORE();
	return (error);
}

/*
 * The code common to handling reference counted flags,
 * e.g., in ifpromisc() and if_allmulti().
 * The "pflag" argument can specify a permanent mode flag to check,
 * such as IFF_PPROMISC for promiscuous mode; should be 0 if none.
 *
 * Only to be used on stack-owned flags, not driver-owned flags.
 */
static int
if_setflag(struct ifnet *ifp, int flag, int pflag, int *refcount, int onswitch)
{
	struct ifreq ifr;
	int error;
	int oldflags, oldcount;

	/* Sanity checks to catch programming errors */
	KASSERT((flag & (IFF_DRV_OACTIVE|IFF_DRV_RUNNING)) == 0,
	    ("%s: setting driver-owned flag %d", __func__, flag));

	if (onswitch)
		KASSERT(*refcount >= 0,
		    ("%s: increment negative refcount %d for flag %d",
		    __func__, *refcount, flag));
	else
		KASSERT(*refcount > 0,
		    ("%s: decrement non-positive refcount %d for flag %d",
		    __func__, *refcount, flag));

	/* In case this mode is permanent, just touch refcount */
	if (ifp->if_flags & pflag) {
		*refcount += onswitch ? 1 : -1;
		return (0);
	}

	/* Save ifnet parameters for if_ioctl() may fail */
	oldcount = *refcount;
	oldflags = ifp->if_flags;
	
	/*
	 * See if we aren't the only and touching refcount is enough.
	 * Actually toggle interface flag if we are the first or last.
	 */
	if (onswitch) {
		if ((*refcount)++)
			return (0);
		ifp->if_flags |= flag;
	} else {
		if (--(*refcount))
			return (0);
		ifp->if_flags &= ~flag;
	}

	/* Call down the driver since we've changed interface flags */
	if (ifp->if_ioctl == NULL) {
		error = EOPNOTSUPP;
		goto recover;
	}
	ifr.ifr_flags = ifp->if_flags & 0xffff;
	ifr.ifr_flagshigh = ifp->if_flags >> 16;
	error = (*ifp->if_ioctl)(ifp, SIOCSIFFLAGS, (caddr_t)&ifr);
	if (error)
		goto recover;
	/* Notify userland that interface flags have changed */
	rt_ifmsg(ifp);
	return (0);

recover:
	/* Recover after driver error */
	*refcount = oldcount;
	ifp->if_flags = oldflags;
	return (error);
}

/*
 * Set/clear promiscuous mode on interface ifp based on the truth value
 * of pswitch.  The calls are reference counted so that only the first
 * "on" request actually has an effect, as does the final "off" request.
 * Results are undefined if the "off" and "on" requests are not matched.
 */
int
ifpromisc(struct ifnet *ifp, int pswitch)
{
	int error;
	int oldflags = ifp->if_flags;

	error = if_setflag(ifp, IFF_PROMISC, IFF_PPROMISC,
			   &ifp->if_pcount, pswitch);
	/* If promiscuous mode status has changed, log a message */
	if (error == 0 && ((ifp->if_flags ^ oldflags) & IFF_PROMISC))
		log(LOG_INFO, "%s: promiscuous mode %s\n",
		    ifp->if_xname,
		    (ifp->if_flags & IFF_PROMISC) ? "enabled" : "disabled");
	return (error);
}

/*
 * Return interface configuration
 * of system.  List may be used
 * in later ioctl's (above) to get
 * other information.
 */
/*ARGSUSED*/
static int
ifconf(u_long cmd, caddr_t data)
{
	struct ifconf *ifc = (struct ifconf *)data;
	struct ifnet *ifp;
	struct ifaddr *ifa;
	struct ifreq ifr;
	struct sbuf *sb;
	int error, full = 0, valid_len, max_len;

	/* Limit initial buffer size to MAXPHYS to avoid DoS from userspace. */
	max_len = MAXPHYS - 1;

	/* Prevent hostile input from being able to crash the system */
	if (ifc->ifc_len <= 0)
		return (EINVAL);

again:
	if (ifc->ifc_len <= max_len) {
		max_len = ifc->ifc_len;
		full = 1;
	}
	sb = sbuf_new(NULL, NULL, max_len + 1, SBUF_FIXEDLEN);
	max_len = 0;
	valid_len = 0;

	IFNET_RLOCK();
	TAILQ_FOREACH(ifp, &V_ifnet, if_link) {
		int addrs;

		/*
		 * Zero the ifr_name buffer to make sure we don't
		 * disclose the contents of the stack.
		 */
		memset(ifr.ifr_name, 0, sizeof(ifr.ifr_name));

		if (strlcpy(ifr.ifr_name, ifp->if_xname, sizeof(ifr.ifr_name))
		    >= sizeof(ifr.ifr_name)) {
			sbuf_delete(sb);
			IFNET_RUNLOCK();
			return (ENAMETOOLONG);
		}

		addrs = 0;
		IF_ADDR_RLOCK(ifp);
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			struct sockaddr *sa = ifa->ifa_addr;

			if (prison_if(curthread->td_ucred, sa) != 0)
				continue;
			addrs++;
#ifdef COMPAT_43
			if (cmd == OSIOCGIFCONF) {
				struct osockaddr *osa =
					 (struct osockaddr *)&ifr.ifr_addr;
				ifr.ifr_addr = *sa;
				osa->sa_family = sa->sa_family;
				sbuf_bcat(sb, &ifr, sizeof(ifr));
				max_len += sizeof(ifr);
			} else
#endif
			if (sa->sa_len <= sizeof(*sa)) {
				ifr.ifr_addr = *sa;
				sbuf_bcat(sb, &ifr, sizeof(ifr));
				max_len += sizeof(ifr);
			} else {
				sbuf_bcat(sb, &ifr,
				    offsetof(struct ifreq, ifr_addr));
				max_len += offsetof(struct ifreq, ifr_addr);
				sbuf_bcat(sb, sa, sa->sa_len);
				max_len += sa->sa_len;
			}

			if (sbuf_error(sb) == 0)
				valid_len = sbuf_len(sb);
		}
		IF_ADDR_RUNLOCK(ifp);
		if (addrs == 0) {
			bzero((caddr_t)&ifr.ifr_addr, sizeof(ifr.ifr_addr));
			sbuf_bcat(sb, &ifr, sizeof(ifr));
			max_len += sizeof(ifr);

			if (sbuf_error(sb) == 0)
				valid_len = sbuf_len(sb);
		}
	}
	IFNET_RUNLOCK();

	/*
	 * If we didn't allocate enough space (uncommon), try again.  If
	 * we have already allocated as much space as we are allowed,
	 * return what we've got.
	 */
	if (valid_len != max_len && !full) {
		sbuf_delete(sb);
		goto again;
	}

	ifc->ifc_len = valid_len;
	sbuf_finish(sb);
	error = copyout(sbuf_data(sb), ifc->ifc_req, ifc->ifc_len);
	sbuf_delete(sb);
	return (error);
}

/*
 * Just like ifpromisc(), but for all-multicast-reception mode.
 */
int
if_allmulti(struct ifnet *ifp, int onswitch)
{

	return (if_setflag(ifp, IFF_ALLMULTI, 0, &ifp->if_amcount, onswitch));
}

struct ifmultiaddr *
if_findmulti(struct ifnet *ifp, struct sockaddr *sa)
{
	struct ifmultiaddr *ifma;

	IF_ADDR_LOCK_ASSERT(ifp);

	TAILQ_FOREACH(ifma, &ifp->if_multiaddrs, ifma_link) {
		if (sa->sa_family == AF_LINK) {
			if (sa_dl_equal(ifma->ifma_addr, sa))
				break;
		} else {
			if (sa_equal(ifma->ifma_addr, sa))
				break;
		}
	}

	return ifma;
}

/*
 * Allocate a new ifmultiaddr and initialize based on passed arguments.  We
 * make copies of passed sockaddrs.  The ifmultiaddr will not be added to
 * the ifnet multicast address list here, so the caller must do that and
 * other setup work (such as notifying the device driver).  The reference
 * count is initialized to 1.
 */
static struct ifmultiaddr *
if_allocmulti(struct ifnet *ifp, struct sockaddr *sa, struct sockaddr *llsa,
    int mflags)
{
	struct ifmultiaddr *ifma;
	struct sockaddr *dupsa;

	ifma = malloc(sizeof *ifma, M_IFMADDR, mflags |
	    M_ZERO);
	if (ifma == NULL)
		return (NULL);

	dupsa = malloc(sa->sa_len, M_IFMADDR, mflags);
	if (dupsa == NULL) {
		free(ifma, M_IFMADDR);
		return (NULL);
	}
	bcopy(sa, dupsa, sa->sa_len);
	ifma->ifma_addr = dupsa;

	ifma->ifma_ifp = ifp;
	ifma->ifma_refcount = 1;
	ifma->ifma_protospec = NULL;

	if (llsa == NULL) {
		ifma->ifma_lladdr = NULL;
		return (ifma);
	}

	dupsa = malloc(llsa->sa_len, M_IFMADDR, mflags);
	if (dupsa == NULL) {
		free(ifma->ifma_addr, M_IFMADDR);
		free(ifma, M_IFMADDR);
		return (NULL);
	}
	bcopy(llsa, dupsa, llsa->sa_len);
	ifma->ifma_lladdr = dupsa;

	return (ifma);
}

/*
 * if_freemulti: free ifmultiaddr structure and possibly attached related
 * addresses.  The caller is responsible for implementing reference
 * counting, notifying the driver, handling routing messages, and releasing
 * any dependent link layer state.
 */
static void
if_freemulti(struct ifmultiaddr *ifma)
{

	KASSERT(ifma->ifma_refcount == 0, ("if_freemulti: refcount %d",
	    ifma->ifma_refcount));
	KASSERT(ifma->ifma_protospec == NULL,
	    ("if_freemulti: protospec not NULL"));

	if (ifma->ifma_lladdr != NULL)
		free(ifma->ifma_lladdr, M_IFMADDR);
	free(ifma->ifma_addr, M_IFMADDR);
	free(ifma, M_IFMADDR);
}

/*
 * Register an additional multicast address with a network interface.
 *
 * - If the address is already present, bump the reference count on the
 *   address and return.
 * - If the address is not link-layer, look up a link layer address.
 * - Allocate address structures for one or both addresses, and attach to the
 *   multicast address list on the interface.  If automatically adding a link
 *   layer address, the protocol address will own a reference to the link
 *   layer address, to be freed when it is freed.
 * - Notify the network device driver of an addition to the multicast address
 *   list.
 *
 * 'sa' points to caller-owned memory with the desired multicast address.
 *
 * 'retifma' will be used to return a pointer to the resulting multicast
 * address reference, if desired.
 */
int
if_addmulti(struct ifnet *ifp, struct sockaddr *sa,
    struct ifmultiaddr **retifma)
{
	struct ifmultiaddr *ifma, *ll_ifma;
	struct sockaddr *llsa;
	int error;

	/*
	 * If the address is already present, return a new reference to it;
	 * otherwise, allocate storage and set up a new address.
	 */
	IF_ADDR_WLOCK(ifp);
	ifma = if_findmulti(ifp, sa);
	if (ifma != NULL) {
		ifma->ifma_refcount++;
		if (retifma != NULL)
			*retifma = ifma;
		IF_ADDR_WUNLOCK(ifp);
		return (0);
	}

	/*
	 * The address isn't already present; resolve the protocol address
	 * into a link layer address, and then look that up, bump its
	 * refcount or allocate an ifma for that also.  If 'llsa' was
	 * returned, we will need to free it later.
	 */
	llsa = NULL;
	ll_ifma = NULL;
	if (ifp->if_resolvemulti != NULL) {
		error = ifp->if_resolvemulti(ifp, &llsa, sa);
		if (error)
			goto unlock_out;
	}

	/*
	 * Allocate the new address.  Don't hook it up yet, as we may also
	 * need to allocate a link layer multicast address.
	 */
	ifma = if_allocmulti(ifp, sa, llsa, M_NOWAIT);
	if (ifma == NULL) {
		error = ENOMEM;
		goto free_llsa_out;
	}

	/*
	 * If a link layer address is found, we'll need to see if it's
	 * already present in the address list, or allocate is as well.
	 * When this block finishes, the link layer address will be on the
	 * list.
	 */
	if (llsa != NULL) {
		ll_ifma = if_findmulti(ifp, llsa);
		if (ll_ifma == NULL) {
			ll_ifma = if_allocmulti(ifp, llsa, NULL, M_NOWAIT);
			if (ll_ifma == NULL) {
				--ifma->ifma_refcount;
				if_freemulti(ifma);
				error = ENOMEM;
				goto free_llsa_out;
			}
			TAILQ_INSERT_HEAD(&ifp->if_multiaddrs, ll_ifma,
			    ifma_link);
		} else
			ll_ifma->ifma_refcount++;
		ifma->ifma_llifma = ll_ifma;
	}

	/*
	 * We now have a new multicast address, ifma, and possibly a new or
	 * referenced link layer address.  Add the primary address to the
	 * ifnet address list.
	 */
	TAILQ_INSERT_HEAD(&ifp->if_multiaddrs, ifma, ifma_link);

	if (retifma != NULL)
		*retifma = ifma;

	/*
	 * Must generate the message while holding the lock so that 'ifma'
	 * pointer is still valid.
	 */
	rt_newmaddrmsg(RTM_NEWMADDR, ifma);
	IF_ADDR_WUNLOCK(ifp);

	/*
	 * We are certain we have added something, so call down to the
	 * interface to let them know about it.
	 */
	if (ifp->if_ioctl != NULL) {
		(void) (*ifp->if_ioctl)(ifp, SIOCADDMULTI, 0);
	}

	if (llsa != NULL)
		free(llsa, M_IFMADDR);

	return (0);

free_llsa_out:
	if (llsa != NULL)
		free(llsa, M_IFMADDR);

unlock_out:
	IF_ADDR_WUNLOCK(ifp);
	return (error);
}

/*
 * Delete a multicast group membership by network-layer group address.
 *
 * Returns ENOENT if the entry could not be found. If ifp no longer
 * exists, results are undefined. This entry point should only be used
 * from subsystems which do appropriate locking to hold ifp for the
 * duration of the call.
 * Network-layer protocol domains must use if_delmulti_ifma().
 */
int
if_delmulti(struct ifnet *ifp, struct sockaddr *sa)
{
	struct ifmultiaddr *ifma;
	int lastref;
#ifdef INVARIANTS
	struct ifnet *oifp;

	IFNET_RLOCK_NOSLEEP();
	TAILQ_FOREACH(oifp, &V_ifnet, if_link)
		if (ifp == oifp)
			break;
	if (ifp != oifp)
		ifp = NULL;
	IFNET_RUNLOCK_NOSLEEP();

	KASSERT(ifp != NULL, ("%s: ifnet went away", __func__));
#endif
	if (ifp == NULL)
		return (ENOENT);

	IF_ADDR_WLOCK(ifp);
	lastref = 0;
	ifma = if_findmulti(ifp, sa);
	if (ifma != NULL)
		lastref = if_delmulti_locked(ifp, ifma, 0);
	IF_ADDR_WUNLOCK(ifp);

	if (ifma == NULL)
		return (ENOENT);

	if (lastref && ifp->if_ioctl != NULL) {
		(void)(*ifp->if_ioctl)(ifp, SIOCDELMULTI, 0);
	}

	return (0);
}

/*
 * Delete all multicast group membership for an interface.
 * Should be used to quickly flush all multicast filters.
 */
void
if_delallmulti(struct ifnet *ifp)
{
	struct ifmultiaddr *ifma;
	struct ifmultiaddr *next;

	IF_ADDR_WLOCK(ifp);
	TAILQ_FOREACH_SAFE(ifma, &ifp->if_multiaddrs, ifma_link, next)
		if_delmulti_locked(ifp, ifma, 0);
	IF_ADDR_WUNLOCK(ifp);
}

/*
 * Delete a multicast group membership by group membership pointer.
 * Network-layer protocol domains must use this routine.
 *
 * It is safe to call this routine if the ifp disappeared.
 */
void
if_delmulti_ifma(struct ifmultiaddr *ifma)
{
	struct ifnet *ifp;
	int lastref;

	ifp = ifma->ifma_ifp;
#ifdef DIAGNOSTIC
	if (ifp == NULL) {
		printf("%s: ifma_ifp seems to be detached\n", __func__);
	} else {
		struct ifnet *oifp;

		IFNET_RLOCK_NOSLEEP();
		TAILQ_FOREACH(oifp, &V_ifnet, if_link)
			if (ifp == oifp)
				break;
		if (ifp != oifp) {
			printf("%s: ifnet %p disappeared\n", __func__, ifp);
			ifp = NULL;
		}
		IFNET_RUNLOCK_NOSLEEP();
	}
#endif
	/*
	 * If and only if the ifnet instance exists: Acquire the address lock.
	 */
	if (ifp != NULL)
		IF_ADDR_WLOCK(ifp);

	lastref = if_delmulti_locked(ifp, ifma, 0);

	if (ifp != NULL) {
		/*
		 * If and only if the ifnet instance exists:
		 *  Release the address lock.
		 *  If the group was left: update the hardware hash filter.
		 */
		IF_ADDR_WUNLOCK(ifp);
		if (lastref && ifp->if_ioctl != NULL) {
			(void)(*ifp->if_ioctl)(ifp, SIOCDELMULTI, 0);
		}
	}
}

/*
 * Perform deletion of network-layer and/or link-layer multicast address.
 *
 * Return 0 if the reference count was decremented.
 * Return 1 if the final reference was released, indicating that the
 * hardware hash filter should be reprogrammed.
 */
static int
if_delmulti_locked(struct ifnet *ifp, struct ifmultiaddr *ifma, int detaching)
{
	struct ifmultiaddr *ll_ifma;

	if (ifp != NULL && ifma->ifma_ifp != NULL) {
		KASSERT(ifma->ifma_ifp == ifp,
		    ("%s: inconsistent ifp %p", __func__, ifp));
		IF_ADDR_WLOCK_ASSERT(ifp);
	}

	ifp = ifma->ifma_ifp;

	/*
	 * If the ifnet is detaching, null out references to ifnet,
	 * so that upper protocol layers will notice, and not attempt
	 * to obtain locks for an ifnet which no longer exists. The
	 * routing socket announcement must happen before the ifnet
	 * instance is detached from the system.
	 */
	if (detaching) {
#ifdef DIAGNOSTIC
		printf("%s: detaching ifnet instance %p\n", __func__, ifp);
#endif
		/*
		 * ifp may already be nulled out if we are being reentered
		 * to delete the ll_ifma.
		 */
		if (ifp != NULL) {
			rt_newmaddrmsg(RTM_DELMADDR, ifma);
			ifma->ifma_ifp = NULL;
		}
	}

	if (--ifma->ifma_refcount > 0)
		return 0;

	/*
	 * If this ifma is a network-layer ifma, a link-layer ifma may
	 * have been associated with it. Release it first if so.
	 */
	ll_ifma = ifma->ifma_llifma;
	if (ll_ifma != NULL) {
		KASSERT(ifma->ifma_lladdr != NULL,
		    ("%s: llifma w/o lladdr", __func__));
		if (detaching)
			ll_ifma->ifma_ifp = NULL;	/* XXX */
		if (--ll_ifma->ifma_refcount == 0) {
			if (ifp != NULL) {
				TAILQ_REMOVE(&ifp->if_multiaddrs, ll_ifma,
				    ifma_link);
			}
			if_freemulti(ll_ifma);
		}
	}

	if (ifp != NULL)
		TAILQ_REMOVE(&ifp->if_multiaddrs, ifma, ifma_link);

	if_freemulti(ifma);

	/*
	 * The last reference to this instance of struct ifmultiaddr
	 * was released; the hardware should be notified of this change.
	 */
	return 1;
}

/*
 * Set the link layer address on an interface.
 *
 * At this time we only support certain types of interfaces,
 * and we don't allow the length of the address to change.
 */
int
if_setlladdr(struct ifnet *ifp, const u_char *lladdr, int len)
{
	struct sockaddr_dl *sdl;
	struct ifaddr *ifa;
	struct ifreq ifr;

	IF_ADDR_RLOCK(ifp);
	ifa = ifp->if_addr;
	if (ifa == NULL) {
		IF_ADDR_RUNLOCK(ifp);
		return (EINVAL);
	}
	ifa_ref(ifa);
	IF_ADDR_RUNLOCK(ifp);
	sdl = (struct sockaddr_dl *)ifa->ifa_addr;
	if (sdl == NULL) {
		ifa_free(ifa);
		return (EINVAL);
	}
	if (len != sdl->sdl_alen) {	/* don't allow length to change */
		ifa_free(ifa);
		return (EINVAL);
	}
	switch (ifp->if_type) {
	case IFT_ETHER:
	case IFT_FDDI:
	case IFT_XETHER:
	case IFT_ISO88025:
	case IFT_L2VLAN:
	case IFT_BRIDGE:
	case IFT_ARCNET:
	case IFT_IEEE8023ADLAG:
	case IFT_IEEE80211:
		bcopy(lladdr, LLADDR(sdl), len);
		ifa_free(ifa);
		break;
	default:
		ifa_free(ifa);
		return (ENODEV);
	}

	/*
	 * If the interface is already up, we need
	 * to re-init it in order to reprogram its
	 * address filter.
	 */
	if ((ifp->if_flags & IFF_UP) != 0) {
		if (ifp->if_ioctl) {
			ifp->if_flags &= ~IFF_UP;
			ifr.ifr_flags = ifp->if_flags & 0xffff;
			ifr.ifr_flagshigh = ifp->if_flags >> 16;
			(*ifp->if_ioctl)(ifp, SIOCSIFFLAGS, (caddr_t)&ifr);
			ifp->if_flags |= IFF_UP;
			ifr.ifr_flags = ifp->if_flags & 0xffff;
			ifr.ifr_flagshigh = ifp->if_flags >> 16;
			(*ifp->if_ioctl)(ifp, SIOCSIFFLAGS, (caddr_t)&ifr);
		}
#ifdef INET
		/*
		 * Also send gratuitous ARPs to notify other nodes about
		 * the address change.
		 */
		TAILQ_FOREACH(ifa, &ifp->if_addrhead, ifa_link) {
			if (ifa->ifa_addr->sa_family == AF_INET)
				arp_ifinit(ifp, ifa);
		}
#endif
	}
	return (0);
}

/*
 * The name argument must be a pointer to storage which will last as
 * long as the interface does.  For physical devices, the result of
 * device_get_name(dev) is a good choice and for pseudo-devices a
 * static string works well.
 */
void
if_initname(struct ifnet *ifp, const char *name, int unit)
{
	ifp->if_dname = name;
	ifp->if_dunit = unit;
	if (unit != IF_DUNIT_NONE)
		snprintf(ifp->if_xname, IFNAMSIZ, "%s%d", name, unit);
	else
		strlcpy(ifp->if_xname, name, IFNAMSIZ);
}

int
if_printf(struct ifnet *ifp, const char * fmt, ...)
{
	va_list ap;
	int retval;

	retval = printf("%s: ", ifp->if_xname);
	va_start(ap, fmt);
	retval += vprintf(fmt, ap);
	va_end(ap);
	return (retval);
}

void
if_start(struct ifnet *ifp)
{

	(*(ifp)->if_start)(ifp);
}

/*
 * Backwards compatibility interface for drivers 
 * that have not implemented it
 */
static int
if_transmit(struct ifnet *ifp, struct mbuf *m)
{
	int error;

	IFQ_HANDOFF(ifp, m, error);
	return (error);
}

static void
if_input_default(struct ifnet *ifp __unused, struct mbuf *m)
{

	m_freem(m);
}

int
if_handoff(struct ifqueue *ifq, struct mbuf *m, struct ifnet *ifp, int adjust)
{
	int active = 0;

	IF_LOCK(ifq);
	if (_IF_QFULL(ifq)) {
		_IF_DROP(ifq);
		IF_UNLOCK(ifq);
		m_freem(m);
		return (0);
	}
	if (ifp != NULL) {
		ifp->if_obytes += m->m_pkthdr.len + adjust;
		if (m->m_flags & (M_BCAST|M_MCAST))
			ifp->if_omcasts++;
		active = ifp->if_drv_flags & IFF_DRV_OACTIVE;
	}
	_IF_ENQUEUE(ifq, m);
	IF_UNLOCK(ifq);
	if (ifp != NULL && !active)
		(*(ifp)->if_start)(ifp);
	return (1);
}

void
if_register_com_alloc(u_char type,
    if_com_alloc_t *a, if_com_free_t *f)
{
	
	KASSERT(if_com_alloc[type] == NULL,
	    ("if_register_com_alloc: %d already registered", type));
	KASSERT(if_com_free[type] == NULL,
	    ("if_register_com_alloc: %d free already registered", type));

	if_com_alloc[type] = a;
	if_com_free[type] = f;
}

void
if_deregister_com_alloc(u_char type)
{
	
	KASSERT(if_com_alloc[type] != NULL,
	    ("if_deregister_com_alloc: %d not registered", type));
	KASSERT(if_com_free[type] != NULL,
	    ("if_deregister_com_alloc: %d free not registered", type));
	if_com_alloc[type] = NULL;
	if_com_free[type] = NULL;
}
OpenPOWER on IntegriCloud