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
|
/* $OpenBSD: ip_mroute.c,v 1.57 2010/04/20 22:05:43 tedu Exp $ */
/* $NetBSD: ip_mroute.c,v 1.85 2004/04/26 01:31:57 matt Exp $ */
/*
* Copyright (c) 1989 Stephen Deering
* Copyright (c) 1992, 1993
* The Regents of the University of California. All rights reserved.
*
* This code is derived from software contributed to Berkeley by
* Stephen Deering of Stanford University.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
* 1. Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* 2. Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* 3. Neither the name of the University nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
* IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
* ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
* FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
* DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
* OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
* HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
* LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
* OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
* SUCH DAMAGE.
*
* @(#)ip_mroute.c 8.2 (Berkeley) 11/15/93
*/
/*
* IP multicast forwarding procedures
*
* Written by David Waitzman, BBN Labs, August 1988.
* Modified by Steve Deering, Stanford, February 1989.
* Modified by Mark J. Steiglitz, Stanford, May, 1991
* Modified by Van Jacobson, LBL, January 1993
* Modified by Ajit Thyagarajan, PARC, August 1993
* Modified by Bill Fenner, PARC, April 1994
* Modified by Charles M. Hannum, NetBSD, May 1995.
* Modified by Ahmed Helmy, SGI, June 1996
* Modified by George Edmond Eddy (Rusty), ISI, February 1998
* Modified by Pavlin Radoslavov, USC/ISI, May 1998, August 1999, October 2000
* Modified by Hitoshi Asaeda, WIDE, August 2000
* Modified by Pavlin Radoslavov, ICSI, October 2002
*
* MROUTING Revision: 1.2
* and PIM-SMv2 and PIM-DM support, advanced API support,
* bandwidth metering and signaling
*/
#ifdef PIM
#define _PIM_VT 1
#endif
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/protosw.h>
#include <sys/errno.h>
#include <sys/time.h>
#include <sys/kernel.h>
#include <sys/ioctl.h>
#include <sys/syslog.h>
#include <sys/proc.h>
#include <sys/sysctl.h>
#include <sys/timeout.h>
#include <net/if.h>
#include <net/route.h>
#include <net/raw_cb.h>
#include <netinet/in.h>
#include <netinet/in_var.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/in_pcb.h>
#include <netinet/udp.h>
#include <netinet/igmp.h>
#include <netinet/igmp_var.h>
#include <netinet/ip_mroute.h>
#ifdef PIM
#include <netinet/pim.h>
#include <netinet/pim_var.h>
#endif
#include <sys/stdarg.h>
#define IP_MULTICASTOPTS 0
#define M_PULLUP(m, len) \
do { \
if ((m) && ((m)->m_flags & M_EXT || (m)->m_len < (len))) \
(m) = m_pullup((m), (len)); \
} while (/*CONSTCOND*/ 0)
/*
* Globals. All but ip_mrouter and ip_mrtproto could be static,
* except for netstat or debugging purposes.
*/
struct socket *ip_mrouter = NULL;
int ip_mrtproto = IGMP_DVMRP; /* for netstat only */
#define NO_RTE_FOUND 0x1
#define RTE_FOUND 0x2
#define MFCHASH(a, g) \
((((a).s_addr >> 20) ^ ((a).s_addr >> 10) ^ (a).s_addr ^ \
((g).s_addr >> 20) ^ ((g).s_addr >> 10) ^ (g).s_addr) & mfchash)
LIST_HEAD(mfchashhdr, mfc) *mfchashtbl;
u_long mfchash;
u_char nexpire[MFCTBLSIZ];
struct vif viftable[MAXVIFS];
struct mrtstat mrtstat;
u_int mrtdebug = 0; /* debug level */
#define DEBUG_MFC 0x02
#define DEBUG_FORWARD 0x04
#define DEBUG_EXPIRE 0x08
#define DEBUG_XMIT 0x10
#define DEBUG_PIM 0x20
#define VIFI_INVALID ((vifi_t) -1)
#ifdef RSVP_ISI
u_int rsvpdebug = 0; /* rsvp debug level */
extern struct socket *ip_rsvpd;
extern int rsvp_on;
#endif /* RSVP_ISI */
#define EXPIRE_TIMEOUT 250 /* 4x / second */
#define UPCALL_EXPIRE 6 /* number of timeouts */
struct timeout expire_upcalls_ch;
static int get_sg_cnt(struct sioc_sg_req *);
static int get_vif_cnt(struct sioc_vif_req *);
static int ip_mrouter_init(struct socket *, struct mbuf *);
static int get_version(struct mbuf *);
static int set_assert(struct mbuf *);
static int get_assert(struct mbuf *);
static int add_vif(struct mbuf *);
static int del_vif(struct mbuf *);
static void update_mfc_params(struct mfc *, struct mfcctl2 *);
static void init_mfc_params(struct mfc *, struct mfcctl2 *);
static void expire_mfc(struct mfc *);
static int add_mfc(struct mbuf *);
#ifdef UPCALL_TIMING
static void collate(struct timeval *);
#endif
static int del_mfc(struct mbuf *);
static int set_api_config(struct mbuf *); /* chose API capabilities */
static int get_api_support(struct mbuf *);
static int get_api_config(struct mbuf *);
static int socket_send(struct socket *, struct mbuf *,
struct sockaddr_in *);
static void expire_upcalls(void *);
#ifdef RSVP_ISI
static int ip_mdq(struct mbuf *, struct ifnet *, struct mfc *, vifi_t);
#else
static int ip_mdq(struct mbuf *, struct ifnet *, struct mfc *);
#endif
static void phyint_send(struct ip *, struct vif *, struct mbuf *);
static void encap_send(struct ip *, struct vif *, struct mbuf *);
static void send_packet(struct vif *, struct mbuf *);
/*
* Bandwidth monitoring
*/
static void free_bw_list(struct bw_meter *);
static int add_bw_upcall(struct mbuf *);
static int del_bw_upcall(struct mbuf *);
static void bw_meter_receive_packet(struct bw_meter *, int , struct timeval *);
static void bw_meter_prepare_upcall(struct bw_meter *, struct timeval *);
static void bw_upcalls_send(void);
static void schedule_bw_meter(struct bw_meter *, struct timeval *);
static void unschedule_bw_meter(struct bw_meter *);
static void bw_meter_process(void);
static void expire_bw_upcalls_send(void *);
static void expire_bw_meter_process(void *);
#ifdef PIM
static int pim_register_send(struct ip *, struct vif *,
struct mbuf *, struct mfc *);
static int pim_register_send_rp(struct ip *, struct vif *,
struct mbuf *, struct mfc *);
static int pim_register_send_upcall(struct ip *, struct vif *,
struct mbuf *, struct mfc *);
static struct mbuf *pim_register_prepare(struct ip *, struct mbuf *);
#endif
/*
* 'Interfaces' associated with decapsulator (so we can tell
* packets that went through it from ones that get reflected
* by a broken gateway). These interfaces are never linked into
* the system ifnet list & no routes point to them. I.e., packets
* can't be sent this way. They only exist as a placeholder for
* multicast source verification.
*/
#if 0
struct ifnet multicast_decap_if[MAXVIFS];
#endif
#define ENCAP_TTL 64
#define ENCAP_PROTO IPPROTO_IPIP /* 4 */
/* prototype IP hdr for encapsulated packets */
struct ip multicast_encap_iphdr = {
#if BYTE_ORDER == LITTLE_ENDIAN
sizeof(struct ip) >> 2, IPVERSION,
#else
IPVERSION, sizeof(struct ip) >> 2,
#endif
0, /* tos */
sizeof(struct ip), /* total length */
0, /* id */
0, /* frag offset */
ENCAP_TTL, ENCAP_PROTO,
0, /* checksum */
};
/*
* Bandwidth meter variables and constants
*/
/*
* Pending timeouts are stored in a hash table, the key being the
* expiration time. Periodically, the entries are analysed and processed.
*/
#define BW_METER_BUCKETS 1024
static struct bw_meter *bw_meter_timers[BW_METER_BUCKETS];
struct timeout bw_meter_ch;
#define BW_METER_PERIOD 1000 /* periodical handling of bw meters (in ms) */
/*
* Pending upcalls are stored in a vector which is flushed when
* full, or periodically
*/
static struct bw_upcall bw_upcalls[BW_UPCALLS_MAX];
static u_int bw_upcalls_n; /* # of pending upcalls */
struct timeout bw_upcalls_ch;
#define BW_UPCALLS_PERIOD 1000 /* periodical flush of bw upcalls (in ms) */
#ifdef PIM
struct pimstat pimstat;
/*
* Note: the PIM Register encapsulation adds the following in front of a
* data packet:
*
* struct pim_encap_hdr {
* struct ip ip;
* struct pim_encap_pimhdr pim;
* }
*
*/
struct pim_encap_pimhdr {
struct pim pim;
uint32_t flags;
};
static struct ip pim_encap_iphdr = {
#if BYTE_ORDER == LITTLE_ENDIAN
sizeof(struct ip) >> 2,
IPVERSION,
#else
IPVERSION,
sizeof(struct ip) >> 2,
#endif
0, /* tos */
sizeof(struct ip), /* total length */
0, /* id */
0, /* frag offset */
ENCAP_TTL,
IPPROTO_PIM,
0, /* checksum */
};
static struct pim_encap_pimhdr pim_encap_pimhdr = {
{
PIM_MAKE_VT(PIM_VERSION, PIM_REGISTER), /* PIM vers and message type */
0, /* reserved */
0, /* checksum */
},
0 /* flags */
};
static struct ifnet multicast_register_if;
static vifi_t reg_vif_num = VIFI_INVALID;
#endif /* PIM */
/*
* Private variables.
*/
static vifi_t numvifs = 0;
static int have_encap_tunnel = 0;
/*
* whether or not special PIM assert processing is enabled.
*/
static int pim_assert;
/*
* Rate limit for assert notification messages, in usec
*/
#define ASSERT_MSG_TIME 3000000
/*
* Kernel multicast routing API capabilities and setup.
* If more API capabilities are added to the kernel, they should be
* recorded in `mrt_api_support'.
*/
static const u_int32_t mrt_api_support = (MRT_MFC_FLAGS_DISABLE_WRONGVIF |
MRT_MFC_FLAGS_BORDER_VIF |
MRT_MFC_RP |
MRT_MFC_BW_UPCALL);
static u_int32_t mrt_api_config = 0;
/*
* Find a route for a given origin IP address and Multicast group address
* Type of service parameter to be added in the future!!!
* Statistics are updated by the caller if needed
* (mrtstat.mrts_mfc_lookups and mrtstat.mrts_mfc_misses)
*/
static struct mfc *
mfc_find(struct in_addr *o, struct in_addr *g)
{
struct mfc *rt;
LIST_FOREACH(rt, &mfchashtbl[MFCHASH(*o, *g)], mfc_hash) {
if (in_hosteq(rt->mfc_origin, *o) &&
in_hosteq(rt->mfc_mcastgrp, *g) &&
(rt->mfc_stall == NULL))
break;
}
return (rt);
}
/*
* Macros to compute elapsed time efficiently
* Borrowed from Van Jacobson's scheduling code
*/
#define TV_DELTA(a, b, delta) do { \
int xxs; \
delta = (a).tv_usec - (b).tv_usec; \
xxs = (a).tv_sec - (b).tv_sec; \
switch (xxs) { \
case 2: \
delta += 1000000; \
/* FALLTHROUGH */ \
case 1: \
delta += 1000000; \
/* FALLTHROUGH */ \
case 0: \
break; \
default: \
delta += (1000000 * xxs); \
break; \
} \
} while (/*CONSTCOND*/ 0)
#ifdef UPCALL_TIMING
u_int32_t upcall_data[51];
#endif /* UPCALL_TIMING */
/*
* Handle MRT setsockopt commands to modify the multicast routing tables.
*/
int
ip_mrouter_set(struct socket *so, int optname, struct mbuf **m)
{
int error;
if (optname != MRT_INIT && so != ip_mrouter)
error = ENOPROTOOPT;
else
switch (optname) {
case MRT_INIT:
error = ip_mrouter_init(so, *m);
break;
case MRT_DONE:
error = ip_mrouter_done();
break;
case MRT_ADD_VIF:
error = add_vif(*m);
break;
case MRT_DEL_VIF:
error = del_vif(*m);
break;
case MRT_ADD_MFC:
error = add_mfc(*m);
break;
case MRT_DEL_MFC:
error = del_mfc(*m);
break;
case MRT_ASSERT:
error = set_assert(*m);
break;
case MRT_API_CONFIG:
error = set_api_config(*m);
break;
case MRT_ADD_BW_UPCALL:
error = add_bw_upcall(*m);
break;
case MRT_DEL_BW_UPCALL:
error = del_bw_upcall(*m);
break;
default:
error = ENOPROTOOPT;
break;
}
if (*m)
m_free(*m);
return (error);
}
/*
* Handle MRT getsockopt commands
*/
int
ip_mrouter_get(struct socket *so, int optname, struct mbuf **m)
{
int error;
if (so != ip_mrouter)
error = ENOPROTOOPT;
else {
*m = m_get(M_WAIT, MT_SOOPTS);
switch (optname) {
case MRT_VERSION:
error = get_version(*m);
break;
case MRT_ASSERT:
error = get_assert(*m);
break;
case MRT_API_SUPPORT:
error = get_api_support(*m);
break;
case MRT_API_CONFIG:
error = get_api_config(*m);
break;
default:
error = ENOPROTOOPT;
break;
}
if (error)
m_free(*m);
}
return (error);
}
/*
* Handle ioctl commands to obtain information from the cache
*/
int
mrt_ioctl(struct socket *so, u_long cmd, caddr_t data)
{
int error;
if (so != ip_mrouter)
error = EINVAL;
else
switch (cmd) {
case SIOCGETVIFCNT:
error = get_vif_cnt((struct sioc_vif_req *)data);
break;
case SIOCGETSGCNT:
error = get_sg_cnt((struct sioc_sg_req *)data);
break;
default:
error = ENOTTY;
break;
}
return (error);
}
/*
* returns the packet, byte, rpf-failure count for the source group provided
*/
static int
get_sg_cnt(struct sioc_sg_req *req)
{
int s;
struct mfc *rt;
s = splsoftnet();
rt = mfc_find(&req->src, &req->grp);
if (rt == NULL) {
splx(s);
req->pktcnt = req->bytecnt = req->wrong_if = 0xffffffff;
return (EADDRNOTAVAIL);
}
req->pktcnt = rt->mfc_pkt_cnt;
req->bytecnt = rt->mfc_byte_cnt;
req->wrong_if = rt->mfc_wrong_if;
splx(s);
return (0);
}
/*
* returns the input and output packet and byte counts on the vif provided
*/
static int
get_vif_cnt(struct sioc_vif_req *req)
{
vifi_t vifi = req->vifi;
if (vifi >= numvifs)
return (EINVAL);
req->icount = viftable[vifi].v_pkt_in;
req->ocount = viftable[vifi].v_pkt_out;
req->ibytes = viftable[vifi].v_bytes_in;
req->obytes = viftable[vifi].v_bytes_out;
return (0);
}
/*
* Enable multicast routing
*/
static int
ip_mrouter_init(struct socket *so, struct mbuf *m)
{
int *v;
if (mrtdebug)
log(LOG_DEBUG,
"ip_mrouter_init: so_type = %d, pr_protocol = %d\n",
so->so_type, so->so_proto->pr_protocol);
if (so->so_type != SOCK_RAW ||
so->so_proto->pr_protocol != IPPROTO_IGMP)
return (EOPNOTSUPP);
if (m == NULL || m->m_len < sizeof(int))
return (EINVAL);
v = mtod(m, int *);
if (*v != 1)
return (EINVAL);
if (ip_mrouter != NULL)
return (EADDRINUSE);
ip_mrouter = so;
mfchashtbl = hashinit(MFCTBLSIZ, M_MRTABLE, M_WAITOK, &mfchash);
bzero((caddr_t)nexpire, sizeof(nexpire));
pim_assert = 0;
timeout_set(&expire_upcalls_ch, expire_upcalls, NULL);
timeout_add_msec(&expire_upcalls_ch, EXPIRE_TIMEOUT);
timeout_set(&bw_upcalls_ch, expire_bw_upcalls_send, NULL);
timeout_add_msec(&bw_upcalls_ch, BW_UPCALLS_PERIOD);
timeout_set(&bw_meter_ch, expire_bw_meter_process, NULL);
timeout_add_msec(&bw_meter_ch, BW_METER_PERIOD);
if (mrtdebug)
log(LOG_DEBUG, "ip_mrouter_init\n");
return (0);
}
/*
* Disable multicast routing
*/
int
ip_mrouter_done()
{
vifi_t vifi;
struct vif *vifp;
int i;
int s;
s = splsoftnet();
/* Clear out all the vifs currently in use. */
for (vifi = 0; vifi < numvifs; vifi++) {
vifp = &viftable[vifi];
if (!in_nullhost(vifp->v_lcl_addr))
reset_vif(vifp);
}
numvifs = 0;
pim_assert = 0;
mrt_api_config = 0;
timeout_del(&expire_upcalls_ch);
timeout_del(&bw_upcalls_ch);
timeout_del(&bw_meter_ch);
/*
* Free all multicast forwarding cache entries.
*/
for (i = 0; i < MFCTBLSIZ; i++) {
struct mfc *rt, *nrt;
for (rt = LIST_FIRST(&mfchashtbl[i]); rt; rt = nrt) {
nrt = LIST_NEXT(rt, mfc_hash);
expire_mfc(rt);
}
}
bzero((caddr_t)nexpire, sizeof(nexpire));
free(mfchashtbl, M_MRTABLE);
mfchashtbl = NULL;
bw_upcalls_n = 0;
bzero(bw_meter_timers, sizeof(bw_meter_timers));
/* Reset de-encapsulation cache. */
have_encap_tunnel = 0;
ip_mrouter = NULL;
splx(s);
if (mrtdebug)
log(LOG_DEBUG, "ip_mrouter_done\n");
return (0);
}
void
ip_mrouter_detach(struct ifnet *ifp)
{
int vifi, i;
struct vif *vifp;
struct mfc *rt;
struct rtdetq *rte;
/* XXX not sure about side effect to userland routing daemon */
for (vifi = 0; vifi < numvifs; vifi++) {
vifp = &viftable[vifi];
if (vifp->v_ifp == ifp)
reset_vif(vifp);
}
for (i = 0; i < MFCTBLSIZ; i++) {
if (nexpire[i] == 0)
continue;
LIST_FOREACH(rt, &mfchashtbl[i], mfc_hash) {
for (rte = rt->mfc_stall; rte; rte = rte->next) {
if (rte->ifp == ifp)
rte->ifp = NULL;
}
}
}
}
static int
get_version(struct mbuf *m)
{
int *v = mtod(m, int *);
*v = 0x0305; /* XXX !!!! */
m->m_len = sizeof(int);
return (0);
}
/*
* Set PIM assert processing global
*/
static int
set_assert(struct mbuf *m)
{
int *i;
if (m == NULL || m->m_len < sizeof(int))
return (EINVAL);
i = mtod(m, int *);
pim_assert = !!*i;
return (0);
}
/*
* Get PIM assert processing global
*/
static int
get_assert(struct mbuf *m)
{
int *i = mtod(m, int *);
*i = pim_assert;
m->m_len = sizeof(int);
return (0);
}
/*
* Configure API capabilities
*/
static int
set_api_config(struct mbuf *m)
{
int i;
u_int32_t *apival;
if (m == NULL || m->m_len < sizeof(u_int32_t))
return (EINVAL);
apival = mtod(m, u_int32_t *);
/*
* We can set the API capabilities only if it is the first operation
* after MRT_INIT. I.e.:
* - there are no vifs installed
* - pim_assert is not enabled
* - the MFC table is empty
*/
if (numvifs > 0) {
*apival = 0;
return (EPERM);
}
if (pim_assert) {
*apival = 0;
return (EPERM);
}
for (i = 0; i < MFCTBLSIZ; i++) {
if (LIST_FIRST(&mfchashtbl[i]) != NULL) {
*apival = 0;
return (EPERM);
}
}
mrt_api_config = *apival & mrt_api_support;
*apival = mrt_api_config;
return (0);
}
/*
* Get API capabilities
*/
static int
get_api_support(struct mbuf *m)
{
u_int32_t *apival;
if (m == NULL || m->m_len < sizeof(u_int32_t))
return (EINVAL);
apival = mtod(m, u_int32_t *);
*apival = mrt_api_support;
return (0);
}
/*
* Get API configured capabilities
*/
static int
get_api_config(struct mbuf *m)
{
u_int32_t *apival;
if (m == NULL || m->m_len < sizeof(u_int32_t))
return (EINVAL);
apival = mtod(m, u_int32_t *);
*apival = mrt_api_config;
return (0);
}
static struct sockaddr_in sin = { sizeof(sin), AF_INET };
/*
* Add a vif to the vif table
*/
static int
add_vif(struct mbuf *m)
{
struct vifctl *vifcp;
struct vif *vifp;
struct ifaddr *ifa;
struct ifnet *ifp;
struct ifreq ifr;
int error, s;
if (m == NULL || m->m_len < sizeof(struct vifctl))
return (EINVAL);
vifcp = mtod(m, struct vifctl *);
if (vifcp->vifc_vifi >= MAXVIFS)
return (EINVAL);
if (in_nullhost(vifcp->vifc_lcl_addr))
return (EADDRNOTAVAIL);
vifp = &viftable[vifcp->vifc_vifi];
if (!in_nullhost(vifp->v_lcl_addr))
return (EADDRINUSE);
/* Find the interface with an address in AF_INET family. */
#ifdef PIM
if (vifcp->vifc_flags & VIFF_REGISTER) {
/*
* XXX: Because VIFF_REGISTER does not really need a valid
* local interface (e.g. it could be 127.0.0.2), we don't
* check its address.
*/
} else
#endif
{
sin.sin_addr = vifcp->vifc_lcl_addr;
ifa = ifa_ifwithaddr(sintosa(&sin), /* XXX */ 0);
if (ifa == NULL)
return (EADDRNOTAVAIL);
}
if (vifcp->vifc_flags & VIFF_TUNNEL) {
/* tunnels are no longer supported use gif(4) instead */
return (EOPNOTSUPP);
#ifdef PIM
} else if (vifcp->vifc_flags & VIFF_REGISTER) {
ifp = &multicast_register_if;
if (mrtdebug)
log(LOG_DEBUG, "Adding a register vif, ifp: %p\n",
(void *)ifp);
if (reg_vif_num == VIFI_INVALID) {
bzero(ifp, sizeof(*ifp));
snprintf(ifp->if_xname, sizeof ifp->if_xname,
"register_vif");
ifp->if_flags = IFF_LOOPBACK;
bzero(&vifp->v_route, sizeof(vifp->v_route));
reg_vif_num = vifcp->vifc_vifi;
}
#endif
} else {
/* Use the physical interface associated with the address. */
ifp = ifa->ifa_ifp;
/* Make sure the interface supports multicast. */
if ((ifp->if_flags & IFF_MULTICAST) == 0)
return (EOPNOTSUPP);
/* Enable promiscuous reception of all IP multicasts. */
satosin(&ifr.ifr_addr)->sin_len = sizeof(struct sockaddr_in);
satosin(&ifr.ifr_addr)->sin_family = AF_INET;
satosin(&ifr.ifr_addr)->sin_addr = zeroin_addr;
error = (*ifp->if_ioctl)(ifp, SIOCADDMULTI, (caddr_t)&ifr);
if (error)
return (error);
}
s = splsoftnet();
vifp->v_flags = vifcp->vifc_flags;
vifp->v_threshold = vifcp->vifc_threshold;
vifp->v_lcl_addr = vifcp->vifc_lcl_addr;
vifp->v_rmt_addr = vifcp->vifc_rmt_addr;
vifp->v_ifp = ifp;
/* Initialize per vif pkt counters. */
vifp->v_pkt_in = 0;
vifp->v_pkt_out = 0;
vifp->v_bytes_in = 0;
vifp->v_bytes_out = 0;
timeout_del(&vifp->v_repq_ch);
#ifdef RSVP_ISI
vifp->v_rsvp_on = 0;
vifp->v_rsvpd = NULL;
#endif /* RSVP_ISI */
splx(s);
/* Adjust numvifs up if the vifi is higher than numvifs. */
if (numvifs <= vifcp->vifc_vifi)
numvifs = vifcp->vifc_vifi + 1;
if (mrtdebug)
log(LOG_DEBUG, "add_vif #%d, lcladdr %x, %s %x, "
"thresh %x\n",
vifcp->vifc_vifi,
ntohl(vifcp->vifc_lcl_addr.s_addr),
(vifcp->vifc_flags & VIFF_TUNNEL) ? "rmtaddr" : "mask",
ntohl(vifcp->vifc_rmt_addr.s_addr),
vifcp->vifc_threshold);
return (0);
}
void
reset_vif(struct vif *vifp)
{
struct ifnet *ifp;
struct ifreq ifr;
if (vifp->v_flags & VIFF_TUNNEL) {
/* empty */
} else if (vifp->v_flags & VIFF_REGISTER) {
#ifdef PIM
reg_vif_num = VIFI_INVALID;
#endif
} else {
satosin(&ifr.ifr_addr)->sin_len = sizeof(struct sockaddr_in);
satosin(&ifr.ifr_addr)->sin_family = AF_INET;
satosin(&ifr.ifr_addr)->sin_addr = zeroin_addr;
ifp = vifp->v_ifp;
(*ifp->if_ioctl)(ifp, SIOCDELMULTI, (caddr_t)&ifr);
}
bzero((caddr_t)vifp, sizeof(*vifp));
}
/*
* Delete a vif from the vif table
*/
static int
del_vif(struct mbuf *m)
{
vifi_t *vifip;
struct vif *vifp;
vifi_t vifi;
int s;
if (m == NULL || m->m_len < sizeof(vifi_t))
return (EINVAL);
vifip = mtod(m, vifi_t *);
if (*vifip >= numvifs)
return (EINVAL);
vifp = &viftable[*vifip];
if (in_nullhost(vifp->v_lcl_addr))
return (EADDRNOTAVAIL);
s = splsoftnet();
reset_vif(vifp);
/* Adjust numvifs down */
for (vifi = numvifs; vifi > 0; vifi--)
if (!in_nullhost(viftable[vifi - 1].v_lcl_addr))
break;
numvifs = vifi;
splx(s);
if (mrtdebug)
log(LOG_DEBUG, "del_vif %d, numvifs %d\n", *vifip, numvifs);
return (0);
}
void
vif_delete(struct ifnet *ifp)
{
int i;
struct vif *vifp;
struct mfc *rt;
struct rtdetq *rte;
for (i = 0; i < numvifs; i++) {
vifp = &viftable[i];
if (vifp->v_ifp == ifp)
bzero((caddr_t)vifp, sizeof *vifp);
}
for (i = numvifs; i > 0; i--)
if (!in_nullhost(viftable[i - 1].v_lcl_addr))
break;
numvifs = i;
for (i = 0; i < MFCTBLSIZ; i++) {
if (nexpire[i] == 0)
continue;
LIST_FOREACH(rt, &mfchashtbl[i], mfc_hash) {
for (rte = rt->mfc_stall; rte; rte = rte->next) {
if (rte->ifp == ifp)
rte->ifp = NULL;
}
}
}
}
/*
* update an mfc entry without resetting counters and S,G addresses.
*/
static void
update_mfc_params(struct mfc *rt, struct mfcctl2 *mfccp)
{
int i;
rt->mfc_parent = mfccp->mfcc_parent;
for (i = 0; i < numvifs; i++) {
rt->mfc_ttls[i] = mfccp->mfcc_ttls[i];
rt->mfc_flags[i] = mfccp->mfcc_flags[i] & mrt_api_config &
MRT_MFC_FLAGS_ALL;
}
/* set the RP address */
if (mrt_api_config & MRT_MFC_RP)
rt->mfc_rp = mfccp->mfcc_rp;
else
rt->mfc_rp = zeroin_addr;
}
/*
* fully initialize an mfc entry from the parameter.
*/
static void
init_mfc_params(struct mfc *rt, struct mfcctl2 *mfccp)
{
rt->mfc_origin = mfccp->mfcc_origin;
rt->mfc_mcastgrp = mfccp->mfcc_mcastgrp;
update_mfc_params(rt, mfccp);
/* initialize pkt counters per src-grp */
rt->mfc_pkt_cnt = 0;
rt->mfc_byte_cnt = 0;
rt->mfc_wrong_if = 0;
timerclear(&rt->mfc_last_assert);
}
static void
expire_mfc(struct mfc *rt)
{
struct rtdetq *rte, *nrte;
free_bw_list(rt->mfc_bw_meter);
for (rte = rt->mfc_stall; rte != NULL; rte = nrte) {
nrte = rte->next;
m_freem(rte->m);
free(rte, M_MRTABLE);
}
LIST_REMOVE(rt, mfc_hash);
free(rt, M_MRTABLE);
}
/*
* Add an mfc entry
*/
static int
add_mfc(struct mbuf *m)
{
struct mfcctl2 mfcctl2;
struct mfcctl2 *mfccp;
struct mfc *rt;
u_int32_t hash = 0;
struct rtdetq *rte, *nrte;
u_short nstl;
int s;
int mfcctl_size = sizeof(struct mfcctl);
if (mrt_api_config & MRT_API_FLAGS_ALL)
mfcctl_size = sizeof(struct mfcctl2);
if (m == NULL || m->m_len < mfcctl_size)
return (EINVAL);
/*
* select data size depending on API version.
*/
if (mrt_api_config & MRT_API_FLAGS_ALL) {
struct mfcctl2 *mp2 = mtod(m, struct mfcctl2 *);
bcopy(mp2, (caddr_t)&mfcctl2, sizeof(*mp2));
} else {
struct mfcctl *mp = mtod(m, struct mfcctl *);
bcopy(mp, (caddr_t)&mfcctl2, sizeof(*mp));
bzero((caddr_t)&mfcctl2 + sizeof(struct mfcctl),
sizeof(mfcctl2) - sizeof(struct mfcctl));
}
mfccp = &mfcctl2;
s = splsoftnet();
rt = mfc_find(&mfccp->mfcc_origin, &mfccp->mfcc_mcastgrp);
/* If an entry already exists, just update the fields */
if (rt) {
if (mrtdebug & DEBUG_MFC)
log(LOG_DEBUG, "add_mfc update o %x g %x p %x\n",
ntohl(mfccp->mfcc_origin.s_addr),
ntohl(mfccp->mfcc_mcastgrp.s_addr),
mfccp->mfcc_parent);
update_mfc_params(rt, mfccp);
splx(s);
return (0);
}
/*
* Find the entry for which the upcall was made and update
*/
nstl = 0;
hash = MFCHASH(mfccp->mfcc_origin, mfccp->mfcc_mcastgrp);
LIST_FOREACH(rt, &mfchashtbl[hash], mfc_hash) {
if (in_hosteq(rt->mfc_origin, mfccp->mfcc_origin) &&
in_hosteq(rt->mfc_mcastgrp, mfccp->mfcc_mcastgrp) &&
rt->mfc_stall != NULL) {
if (nstl++)
log(LOG_ERR, "add_mfc %s o %x g %x "
"p %x dbx %p\n",
"multiple kernel entries",
ntohl(mfccp->mfcc_origin.s_addr),
ntohl(mfccp->mfcc_mcastgrp.s_addr),
mfccp->mfcc_parent, rt->mfc_stall);
if (mrtdebug & DEBUG_MFC)
log(LOG_DEBUG, "add_mfc o %x g %x "
"p %x dbg %p\n",
ntohl(mfccp->mfcc_origin.s_addr),
ntohl(mfccp->mfcc_mcastgrp.s_addr),
mfccp->mfcc_parent, rt->mfc_stall);
rte = rt->mfc_stall;
init_mfc_params(rt, mfccp);
rt->mfc_stall = NULL;
rt->mfc_expire = 0; /* Don't clean this guy up */
nexpire[hash]--;
/* free packets Qed at the end of this entry */
for (; rte != NULL; rte = nrte) {
nrte = rte->next;
if (rte->ifp) {
#ifdef RSVP_ISI
ip_mdq(rte->m, rte->ifp, rt, -1);
#else
ip_mdq(rte->m, rte->ifp, rt);
#endif /* RSVP_ISI */
}
m_freem(rte->m);
#ifdef UPCALL_TIMING
collate(&rte->t);
#endif /* UPCALL_TIMING */
free(rte, M_MRTABLE);
}
}
}
/*
* It is possible that an entry is being inserted without an upcall
*/
if (nstl == 0) {
/*
* No mfc; make a new one
*/
if (mrtdebug & DEBUG_MFC)
log(LOG_DEBUG, "add_mfc no upcall o %x g %x p %x\n",
ntohl(mfccp->mfcc_origin.s_addr),
ntohl(mfccp->mfcc_mcastgrp.s_addr),
mfccp->mfcc_parent);
LIST_FOREACH(rt, &mfchashtbl[hash], mfc_hash) {
if (in_hosteq(rt->mfc_origin, mfccp->mfcc_origin) &&
in_hosteq(rt->mfc_mcastgrp, mfccp->mfcc_mcastgrp)) {
init_mfc_params(rt, mfccp);
if (rt->mfc_expire)
nexpire[hash]--;
rt->mfc_expire = 0;
break; /* XXX */
}
}
if (rt == NULL) { /* no upcall, so make a new entry */
rt = (struct mfc *)malloc(sizeof(*rt), M_MRTABLE,
M_NOWAIT);
if (rt == NULL) {
splx(s);
return (ENOBUFS);
}
init_mfc_params(rt, mfccp);
rt->mfc_expire = 0;
rt->mfc_stall = NULL;
rt->mfc_bw_meter = NULL;
/* insert new entry at head of hash chain */
LIST_INSERT_HEAD(&mfchashtbl[hash], rt, mfc_hash);
}
}
splx(s);
return (0);
}
#ifdef UPCALL_TIMING
/*
* collect delay statistics on the upcalls
*/
static void
collate(struct timeval *t)
{
u_int32_t d;
struct timeval tp;
u_int32_t delta;
microtime(&tp);
if (timercmp(t, &tp, <)) {
TV_DELTA(tp, *t, delta);
d = delta >> 10;
if (d > 50)
d = 50;
++upcall_data[d];
}
}
#endif /* UPCALL_TIMING */
/*
* Delete an mfc entry
*/
static int
del_mfc(struct mbuf *m)
{
struct mfcctl2 mfcctl2;
struct mfcctl2 *mfccp;
struct mfc *rt;
int s;
int mfcctl_size = sizeof(struct mfcctl);
struct mfcctl *mp = mtod(m, struct mfcctl *);
/*
* XXX: for deleting MFC entries the information in entries
* of size "struct mfcctl" is sufficient.
*/
if (m == NULL || m->m_len < mfcctl_size)
return (EINVAL);
bcopy(mp, (caddr_t)&mfcctl2, sizeof(*mp));
bzero((caddr_t)&mfcctl2 + sizeof(struct mfcctl),
sizeof(mfcctl2) - sizeof(struct mfcctl));
mfccp = &mfcctl2;
if (mrtdebug & DEBUG_MFC)
log(LOG_DEBUG, "del_mfc origin %x mcastgrp %x\n",
ntohl(mfccp->mfcc_origin.s_addr),
ntohl(mfccp->mfcc_mcastgrp.s_addr));
s = splsoftnet();
rt = mfc_find(&mfccp->mfcc_origin, &mfccp->mfcc_mcastgrp);
if (rt == NULL) {
splx(s);
return (EADDRNOTAVAIL);
}
/*
* free the bw_meter entries
*/
free_bw_list(rt->mfc_bw_meter);
rt->mfc_bw_meter = NULL;
LIST_REMOVE(rt, mfc_hash);
free(rt, M_MRTABLE);
splx(s);
return (0);
}
static int
socket_send(struct socket *s, struct mbuf *mm, struct sockaddr_in *src)
{
if (s != NULL) {
if (sbappendaddr(&s->so_rcv, sintosa(src), mm,
(struct mbuf *)NULL) != 0) {
sorwakeup(s);
return (0);
}
}
m_freem(mm);
return (-1);
}
/*
* IP multicast forwarding function. This function assumes that the packet
* pointed to by "ip" has arrived on (or is about to be sent to) the interface
* pointed to by "ifp", and the packet is to be relayed to other networks
* that have members of the packet's destination IP multicast group.
*
* The packet is returned unscathed to the caller, unless it is
* erroneous, in which case a non-zero return value tells the caller to
* discard it.
*/
#define IP_HDR_LEN 20 /* # bytes of fixed IP header (excluding options) */
#define TUNNEL_LEN 12 /* # bytes of IP option for tunnel encapsulation */
int
#ifdef RSVP_ISI
ip_mforward(struct mbuf *m, struct ifnet *ifp, struct ip_moptions *imo)
#else
ip_mforward(struct mbuf *m, struct ifnet *ifp)
#endif /* RSVP_ISI */
{
struct ip *ip = mtod(m, struct ip *);
struct mfc *rt;
static int srctun = 0;
struct mbuf *mm;
int s;
vifi_t vifi;
if (mrtdebug & DEBUG_FORWARD)
log(LOG_DEBUG, "ip_mforward: src %x, dst %x, ifp %p\n",
ntohl(ip->ip_src.s_addr), ntohl(ip->ip_dst.s_addr), ifp);
if (ip->ip_hl < (IP_HDR_LEN + TUNNEL_LEN) >> 2 ||
((u_char *)(ip + 1))[1] != IPOPT_LSRR) {
/*
* Packet arrived via a physical interface or
* an encapsulated tunnel or a register_vif.
*/
} else {
/*
* Packet arrived through a source-route tunnel.
* Source-route tunnels are no longer supported.
*/
if ((srctun++ % 1000) == 0)
log(LOG_ERR, "ip_mforward: received source-routed "
"packet from %x\n", ntohl(ip->ip_src.s_addr));
return (1);
}
#ifdef RSVP_ISI
if (imo && ((vifi = imo->imo_multicast_vif) < numvifs)) {
if (ip->ip_ttl < MAXTTL) {
/* compensate for -1 in *_send routines */
ip->ip_ttl++;
}
if (rsvpdebug && ip->ip_p == IPPROTO_RSVP) {
struct vif *vifp = viftable + vifi;
printf("Sending IPPROTO_RSVP from %x to %x on "
"vif %d (%s%s)\n",
ntohl(ip->ip_src), ntohl(ip->ip_dst), vifi,
(vifp->v_flags & VIFF_TUNNEL) ? "tunnel on " : "",
vifp->v_ifp->if_xname);
}
return (ip_mdq(m, ifp, (struct mfc *)NULL, vifi));
}
if (rsvpdebug && ip->ip_p == IPPROTO_RSVP) {
printf("Warning: IPPROTO_RSVP from %x to %x without "
"vif option\n", ntohl(ip->ip_src), ntohl(ip->ip_dst));
}
#endif /* RSVP_ISI */
/*
* Don't forward a packet with time-to-live of zero or one,
* or a packet destined to a local-only group.
*/
if (ip->ip_ttl <= 1 || IN_LOCAL_GROUP(ip->ip_dst.s_addr))
return (0);
/*
* Determine forwarding vifs from the forwarding cache table
*/
s = splsoftnet();
++mrtstat.mrts_mfc_lookups;
rt = mfc_find(&ip->ip_src, &ip->ip_dst);
/* Entry exists, so forward if necessary */
if (rt != NULL) {
splx(s);
#ifdef RSVP_ISI
return (ip_mdq(m, ifp, rt, -1));
#else
return (ip_mdq(m, ifp, rt));
#endif /* RSVP_ISI */
} else {
/*
* If we don't have a route for packet's origin,
* Make a copy of the packet & send message to routing daemon
*/
struct mbuf *mb0;
struct rtdetq *rte;
u_int32_t hash;
int hlen = ip->ip_hl << 2;
#ifdef UPCALL_TIMING
struct timeval tp;
microtime(&tp);
#endif /* UPCALL_TIMING */
++mrtstat.mrts_mfc_misses;
mrtstat.mrts_no_route++;
if (mrtdebug & (DEBUG_FORWARD | DEBUG_MFC))
log(LOG_DEBUG, "ip_mforward: no rte s %x g %x\n",
ntohl(ip->ip_src.s_addr),
ntohl(ip->ip_dst.s_addr));
/*
* Allocate mbufs early so that we don't do extra work if we are
* just going to fail anyway. Make sure to pullup the header so
* that other people can't step on it.
*/
rte = (struct rtdetq *)malloc(sizeof(*rte),
M_MRTABLE, M_NOWAIT);
if (rte == NULL) {
splx(s);
return (ENOBUFS);
}
mb0 = m_copy(m, 0, M_COPYALL);
M_PULLUP(mb0, hlen);
if (mb0 == NULL) {
free(rte, M_MRTABLE);
splx(s);
return (ENOBUFS);
}
/* is there an upcall waiting for this flow? */
hash = MFCHASH(ip->ip_src, ip->ip_dst);
LIST_FOREACH(rt, &mfchashtbl[hash], mfc_hash) {
if (in_hosteq(ip->ip_src, rt->mfc_origin) &&
in_hosteq(ip->ip_dst, rt->mfc_mcastgrp) &&
rt->mfc_stall != NULL)
break;
}
if (rt == NULL) {
int i;
struct igmpmsg *im;
/*
* Locate the vifi for the incoming interface for
* this packet.
* If none found, drop packet.
*/
for (vifi = 0; vifi < numvifs &&
viftable[vifi].v_ifp != ifp; vifi++)
;
if (vifi >= numvifs) /* vif not found, drop packet */
goto non_fatal;
/* no upcall, so make a new entry */
rt = (struct mfc *)malloc(sizeof(*rt),
M_MRTABLE, M_NOWAIT);
if (rt == NULL)
goto fail;
/*
* Make a copy of the header to send to the user level
* process
*/
mm = m_copy(m, 0, hlen);
M_PULLUP(mm, hlen);
if (mm == NULL)
goto fail1;
/*
* Send message to routing daemon to install
* a route into the kernel table
*/
im = mtod(mm, struct igmpmsg *);
im->im_msgtype = IGMPMSG_NOCACHE;
im->im_mbz = 0;
im->im_vif = vifi;
mrtstat.mrts_upcalls++;
sin.sin_addr = ip->ip_src;
if (socket_send(ip_mrouter, mm, &sin) < 0) {
log(LOG_WARNING, "ip_mforward: ip_mrouter "
"socket queue full\n");
++mrtstat.mrts_upq_sockfull;
fail1:
free(rt, M_MRTABLE);
fail:
free(rte, M_MRTABLE);
m_freem(mb0);
splx(s);
return (ENOBUFS);
}
/* insert new entry at head of hash chain */
rt->mfc_origin = ip->ip_src;
rt->mfc_mcastgrp = ip->ip_dst;
rt->mfc_pkt_cnt = 0;
rt->mfc_byte_cnt = 0;
rt->mfc_wrong_if = 0;
rt->mfc_expire = UPCALL_EXPIRE;
nexpire[hash]++;
for (i = 0; i < numvifs; i++) {
rt->mfc_ttls[i] = 0;
rt->mfc_flags[i] = 0;
}
rt->mfc_parent = -1;
/* clear the RP address */
rt->mfc_rp = zeroin_addr;
rt->mfc_bw_meter = NULL;
/* link into table */
LIST_INSERT_HEAD(&mfchashtbl[hash], rt, mfc_hash);
/* Add this entry to the end of the queue */
rt->mfc_stall = rte;
} else {
/* determine if q has overflowed */
struct rtdetq **p;
int npkts = 0;
/*
* XXX ouch! we need to append to the list, but we
* only have a pointer to the front, so we have to
* scan the entire list every time.
*/
for (p = &rt->mfc_stall; *p != NULL; p = &(*p)->next)
if (++npkts > MAX_UPQ) {
mrtstat.mrts_upq_ovflw++;
non_fatal:
free(rte, M_MRTABLE);
m_freem(mb0);
splx(s);
return (0);
}
/* Add this entry to the end of the queue */
*p = rte;
}
rte->next = NULL;
rte->m = mb0;
rte->ifp = ifp;
#ifdef UPCALL_TIMING
rte->t = tp;
#endif /* UPCALL_TIMING */
splx(s);
return (0);
}
}
/*ARGSUSED*/
static void
expire_upcalls(void *v)
{
int i;
int s;
s = splsoftnet();
for (i = 0; i < MFCTBLSIZ; i++) {
struct mfc *rt, *nrt;
if (nexpire[i] == 0)
continue;
for (rt = LIST_FIRST(&mfchashtbl[i]); rt; rt = nrt) {
nrt = LIST_NEXT(rt, mfc_hash);
if (rt->mfc_expire == 0 || --rt->mfc_expire > 0)
continue;
nexpire[i]--;
/*
* free the bw_meter entries
*/
while (rt->mfc_bw_meter != NULL) {
struct bw_meter *x = rt->mfc_bw_meter;
rt->mfc_bw_meter = x->bm_mfc_next;
free(x, M_BWMETER);
}
++mrtstat.mrts_cache_cleanups;
if (mrtdebug & DEBUG_EXPIRE)
log(LOG_DEBUG,
"expire_upcalls: expiring (%x %x)\n",
ntohl(rt->mfc_origin.s_addr),
ntohl(rt->mfc_mcastgrp.s_addr));
expire_mfc(rt);
}
}
splx(s);
timeout_add_msec(&expire_upcalls_ch, EXPIRE_TIMEOUT);
}
/*
* Packet forwarding routine once entry in the cache is made
*/
static int
#ifdef RSVP_ISI
ip_mdq(struct mbuf *m, struct ifnet *ifp, struct mfc *rt, vifi_t xmt_vif)
#else
ip_mdq(struct mbuf *m, struct ifnet *ifp, struct mfc *rt)
#endif /* RSVP_ISI */
{
struct ip *ip = mtod(m, struct ip *);
vifi_t vifi;
struct vif *vifp;
int plen = ntohs(ip->ip_len) - (ip->ip_hl << 2);
/*
* Macro to send packet on vif. Since RSVP packets don't get counted on
* input, they shouldn't get counted on output, so statistics keeping is
* separate.
*/
#define MC_SEND(ip, vifp, m) do { \
if ((vifp)->v_flags & VIFF_TUNNEL) \
encap_send((ip), (vifp), (m)); \
else \
phyint_send((ip), (vifp), (m)); \
} while (/*CONSTCOND*/ 0)
#ifdef RSVP_ISI
/*
* If xmt_vif is not -1, send on only the requested vif.
*
* (since vifi_t is u_short, -1 becomes MAXUSHORT, which > numvifs.
*/
if (xmt_vif < numvifs) {
#ifdef PIM
if (viftable[xmt_vif].v_flags & VIFF_REGISTER)
pim_register_send(ip, viftable + xmt_vif, m, rt);
else
#endif
MC_SEND(ip, viftable + xmt_vif, m);
return (1);
}
#endif /* RSVP_ISI */
/*
* Don't forward if it didn't arrive from the parent vif for its origin.
*/
vifi = rt->mfc_parent;
if ((vifi >= numvifs) || (viftable[vifi].v_ifp != ifp)) {
/* came in the wrong interface */
if (mrtdebug & DEBUG_FORWARD)
log(LOG_DEBUG, "wrong if: ifp %p vifi %d vififp %p\n",
ifp, vifi,
vifi >= numvifs ? 0 : viftable[vifi].v_ifp);
++mrtstat.mrts_wrong_if;
++rt->mfc_wrong_if;
/*
* If we are doing PIM assert processing, send a message
* to the routing daemon.
*
* XXX: A PIM-SM router needs the WRONGVIF detection so it
* can complete the SPT switch, regardless of the type
* of interface (broadcast media, GRE tunnel, etc).
*/
if (pim_assert && (vifi < numvifs) && viftable[vifi].v_ifp) {
struct timeval now;
u_int32_t delta;
#ifdef PIM
if (ifp == &multicast_register_if)
pimstat.pims_rcv_registers_wrongiif++;
#endif
/* Get vifi for the incoming packet */
for (vifi = 0;
vifi < numvifs && viftable[vifi].v_ifp != ifp;
vifi++)
;
if (vifi >= numvifs) {
/* The iif is not found: ignore the packet. */
return (0);
}
if (rt->mfc_flags[vifi] &
MRT_MFC_FLAGS_DISABLE_WRONGVIF) {
/* WRONGVIF disabled: ignore the packet */
return (0);
}
microtime(&now);
TV_DELTA(rt->mfc_last_assert, now, delta);
if (delta > ASSERT_MSG_TIME) {
struct igmpmsg *im;
int hlen = ip->ip_hl << 2;
struct mbuf *mm = m_copy(m, 0, hlen);
M_PULLUP(mm, hlen);
if (mm == NULL)
return (ENOBUFS);
rt->mfc_last_assert = now;
im = mtod(mm, struct igmpmsg *);
im->im_msgtype = IGMPMSG_WRONGVIF;
im->im_mbz = 0;
im->im_vif = vifi;
mrtstat.mrts_upcalls++;
sin.sin_addr = im->im_src;
if (socket_send(ip_mrouter, mm, &sin) < 0) {
log(LOG_WARNING, "ip_mforward: "
"ip_mrouter socket queue full\n");
++mrtstat.mrts_upq_sockfull;
return (ENOBUFS);
}
}
}
return (0);
}
/* If I sourced this packet, it counts as output, else it was input. */
if (in_hosteq(ip->ip_src, viftable[vifi].v_lcl_addr)) {
viftable[vifi].v_pkt_out++;
viftable[vifi].v_bytes_out += plen;
} else {
viftable[vifi].v_pkt_in++;
viftable[vifi].v_bytes_in += plen;
}
rt->mfc_pkt_cnt++;
rt->mfc_byte_cnt += plen;
/*
* For each vif, decide if a copy of the packet should be forwarded.
* Forward if:
* - the ttl exceeds the vif's threshold
* - there are group members downstream on interface
*/
for (vifp = viftable, vifi = 0; vifi < numvifs; vifp++, vifi++)
if ((rt->mfc_ttls[vifi] > 0) &&
(ip->ip_ttl > rt->mfc_ttls[vifi])) {
vifp->v_pkt_out++;
vifp->v_bytes_out += plen;
#ifdef PIM
if (vifp->v_flags & VIFF_REGISTER)
pim_register_send(ip, vifp, m, rt);
else
#endif
MC_SEND(ip, vifp, m);
}
/*
* Perform upcall-related bw measuring.
*/
if (rt->mfc_bw_meter != NULL) {
struct bw_meter *x;
struct timeval now;
microtime(&now);
for (x = rt->mfc_bw_meter; x != NULL; x = x->bm_mfc_next)
bw_meter_receive_packet(x, plen, &now);
}
return (0);
}
#ifdef RSVP_ISI
/*
* check if a vif number is legal/ok. This is used by ip_output.
*/
int
legal_vif_num(int vif)
{
if (vif >= 0 && vif < numvifs)
return (1);
else
return (0);
}
#endif /* RSVP_ISI */
static void
phyint_send(struct ip *ip, struct vif *vifp, struct mbuf *m)
{
struct mbuf *mb_copy;
int hlen = ip->ip_hl << 2;
/*
* Make a new reference to the packet; make sure that
* the IP header is actually copied, not just referenced,
* so that ip_output() only scribbles on the copy.
*/
mb_copy = m_copy(m, 0, M_COPYALL);
M_PULLUP(mb_copy, hlen);
if (mb_copy == NULL)
return;
send_packet(vifp, mb_copy);
}
static void
encap_send(struct ip *ip, struct vif *vifp, struct mbuf *m)
{
struct mbuf *mb_copy;
struct ip *ip_copy;
int i, len = ntohs(ip->ip_len) + sizeof(multicast_encap_iphdr);
/* Take care of delayed checksums */
if (m->m_pkthdr.csum_flags & (M_TCPV4_CSUM_OUT | M_UDPV4_CSUM_OUT)) {
in_delayed_cksum(m);
m->m_pkthdr.csum_flags &=
~(M_UDPV4_CSUM_OUT | M_TCPV4_CSUM_OUT);
}
/*
* copy the old packet & pullup its IP header into the
* new mbuf so we can modify it. Try to fill the new
* mbuf since if we don't the ethernet driver will.
*/
MGETHDR(mb_copy, M_DONTWAIT, MT_DATA);
if (mb_copy == NULL)
return;
mb_copy->m_data += max_linkhdr;
mb_copy->m_pkthdr.len = len;
mb_copy->m_len = sizeof(multicast_encap_iphdr);
if ((mb_copy->m_next = m_copy(m, 0, M_COPYALL)) == NULL) {
m_freem(mb_copy);
return;
}
i = MHLEN - max_linkhdr;
if (i > len)
i = len;
mb_copy = m_pullup(mb_copy, i);
if (mb_copy == NULL)
return;
/*
* fill in the encapsulating IP header.
*/
ip_copy = mtod(mb_copy, struct ip *);
*ip_copy = multicast_encap_iphdr;
ip_copy->ip_id = htons(ip_randomid());
ip_copy->ip_len = htons(len);
ip_copy->ip_src = vifp->v_lcl_addr;
ip_copy->ip_dst = vifp->v_rmt_addr;
/*
* turn the encapsulated IP header back into a valid one.
*/
ip = (struct ip *)((caddr_t)ip_copy + sizeof(multicast_encap_iphdr));
--ip->ip_ttl;
ip->ip_sum = 0;
mb_copy->m_data += sizeof(multicast_encap_iphdr);
ip->ip_sum = in_cksum(mb_copy, ip->ip_hl << 2);
mb_copy->m_data -= sizeof(multicast_encap_iphdr);
send_packet(vifp, mb_copy);
}
static void
send_packet(struct vif *vifp, struct mbuf *m)
{
int error;
int s = splsoftnet();
if (vifp->v_flags & VIFF_TUNNEL) {
/* If tunnel options */
ip_output(m, (struct mbuf *)NULL, &vifp->v_route,
IP_FORWARDING, (struct ip_moptions *)NULL,
(struct inpcb *)NULL);
} else {
/*
* if physical interface option, extract the options
* and then send
*/
struct ip_moptions imo;
imo.imo_multicast_ifp = vifp->v_ifp;
imo.imo_multicast_ttl = mtod(m, struct ip *)->ip_ttl - IPTTLDEC;
imo.imo_multicast_loop = 1;
#ifdef RSVP_ISI
imo.imo_multicast_vif = -1;
#endif
error = ip_output(m, (struct mbuf *)NULL, (struct route *)NULL,
IP_FORWARDING|IP_MULTICASTOPTS, &imo,
(struct inpcb *)NULL);
if (mrtdebug & DEBUG_XMIT)
log(LOG_DEBUG, "phyint_send on vif %ld err %d\n",
(long)(vifp - viftable), error);
}
splx(s);
}
#ifdef RSVP_ISI
int
ip_rsvp_vif_init(struct socket *so, struct mbuf *m)
{
int vifi, s;
if (rsvpdebug)
printf("ip_rsvp_vif_init: so_type = %d, pr_protocol = %d\n",
so->so_type, so->so_proto->pr_protocol);
if (so->so_type != SOCK_RAW ||
so->so_proto->pr_protocol != IPPROTO_RSVP)
return (EOPNOTSUPP);
/* Check mbuf. */
if (m == NULL || m->m_len != sizeof(int)) {
return (EINVAL);
}
vifi = *(mtod(m, int *));
if (rsvpdebug)
printf("ip_rsvp_vif_init: vif = %d rsvp_on = %d\n",
vifi, rsvp_on);
s = splsoftnet();
/* Check vif. */
if (!legal_vif_num(vifi)) {
splx(s);
return (EADDRNOTAVAIL);
}
/* Check if socket is available. */
if (viftable[vifi].v_rsvpd != NULL) {
splx(s);
return (EADDRINUSE);
}
viftable[vifi].v_rsvpd = so;
/* This may seem silly, but we need to be sure we don't over-increment
* the RSVP counter, in case something slips up.
*/
if (!viftable[vifi].v_rsvp_on) {
viftable[vifi].v_rsvp_on = 1;
rsvp_on++;
}
splx(s);
return (0);
}
int
ip_rsvp_vif_done(struct socket *so, struct mbuf *m)
{
int vifi, s;
if (rsvpdebug)
printf("ip_rsvp_vif_done: so_type = %d, pr_protocol = %d\n",
so->so_type, so->so_proto->pr_protocol);
if (so->so_type != SOCK_RAW ||
so->so_proto->pr_protocol != IPPROTO_RSVP)
return (EOPNOTSUPP);
/* Check mbuf. */
if (m == NULL || m->m_len != sizeof(int)) {
return (EINVAL);
}
vifi = *(mtod(m, int *));
s = splsoftnet();
/* Check vif. */
if (!legal_vif_num(vifi)) {
splx(s);
return (EADDRNOTAVAIL);
}
if (rsvpdebug)
printf("ip_rsvp_vif_done: v_rsvpd = %x so = %x\n",
viftable[vifi].v_rsvpd, so);
viftable[vifi].v_rsvpd = NULL;
/*
* This may seem silly, but we need to be sure we don't over-decrement
* the RSVP counter, in case something slips up.
*/
if (viftable[vifi].v_rsvp_on) {
viftable[vifi].v_rsvp_on = 0;
rsvp_on--;
}
splx(s);
return (0);
}
void
ip_rsvp_force_done(struct socket *so)
{
int vifi, s;
/* Don't bother if it is not the right type of socket. */
if (so->so_type != SOCK_RAW ||
so->so_proto->pr_protocol != IPPROTO_RSVP)
return;
s = splsoftnet();
/*
* The socket may be attached to more than one vif...this
* is perfectly legal.
*/
for (vifi = 0; vifi < numvifs; vifi++) {
if (viftable[vifi].v_rsvpd == so) {
viftable[vifi].v_rsvpd = NULL;
/*
* This may seem silly, but we need to be sure we don't
* over-decrement the RSVP counter, in case something
* slips up.
*/
if (viftable[vifi].v_rsvp_on) {
viftable[vifi].v_rsvp_on = 0;
rsvp_on--;
}
}
}
splx(s);
return;
}
void
rsvp_input(struct mbuf *m, struct ifnet *ifp)
{
int vifi, s;
struct ip *ip = mtod(m, struct ip *);
static struct sockaddr_in rsvp_src = { sizeof(sin), AF_INET };
if (rsvpdebug)
printf("rsvp_input: rsvp_on %d\n", rsvp_on);
/*
* Can still get packets with rsvp_on = 0 if there is a local member
* of the group to which the RSVP packet is addressed. But in this
* case we want to throw the packet away.
*/
if (!rsvp_on) {
m_freem(m);
return;
}
/*
* If the old-style non-vif-associated socket is set, then use
* it and ignore the new ones.
*/
if (ip_rsvpd != NULL) {
if (rsvpdebug)
printf("rsvp_input: "
"Sending packet up old-style socket\n");
rip_input(m, 0); /*XXX*/
return;
}
s = splsoftnet();
if (rsvpdebug)
printf("rsvp_input: check vifs\n");
/* Find which vif the packet arrived on. */
for (vifi = 0; vifi < numvifs; vifi++) {
if (viftable[vifi].v_ifp == ifp)
break;
}
if (vifi == numvifs) {
/* Can't find vif packet arrived on. Drop packet. */
if (rsvpdebug)
printf("rsvp_input: "
"Can't find vif for packet...dropping it.\n");
m_freem(m);
splx(s);
return;
}
if (rsvpdebug)
printf("rsvp_input: check socket\n");
if (viftable[vifi].v_rsvpd == NULL) {
/*
* drop packet, since there is no specific socket for this
* interface
*/
if (rsvpdebug)
printf("rsvp_input: No socket defined for vif %d\n",
vifi);
m_freem(m);
splx(s);
return;
}
rsvp_src.sin_addr = ip->ip_src;
if (rsvpdebug && m)
printf("rsvp_input: m->m_len = %d, sbspace() = %d\n",
m->m_len, sbspace(&viftable[vifi].v_rsvpd->so_rcv));
if (socket_send(viftable[vifi].v_rsvpd, m, &rsvp_src) < 0)
if (rsvpdebug)
printf("rsvp_input: Failed to append to socket\n");
else
if (rsvpdebug)
printf("rsvp_input: send packet up\n");
splx(s);
}
#endif /* RSVP_ISI */
/*
* Code for bandwidth monitors
*/
/*
* Define common interface for timeval-related methods
*/
#define BW_TIMEVALCMP(tvp, uvp, cmp) timercmp((tvp), (uvp), cmp)
#define BW_TIMEVALDECR(vvp, uvp) timersub((vvp), (uvp), (vvp))
#define BW_TIMEVALADD(vvp, uvp) timeradd((vvp), (uvp), (vvp))
static uint32_t
compute_bw_meter_flags(struct bw_upcall *req)
{
uint32_t flags = 0;
if (req->bu_flags & BW_UPCALL_UNIT_PACKETS)
flags |= BW_METER_UNIT_PACKETS;
if (req->bu_flags & BW_UPCALL_UNIT_BYTES)
flags |= BW_METER_UNIT_BYTES;
if (req->bu_flags & BW_UPCALL_GEQ)
flags |= BW_METER_GEQ;
if (req->bu_flags & BW_UPCALL_LEQ)
flags |= BW_METER_LEQ;
return (flags);
}
/*
* Add a bw_meter entry
*/
static int
add_bw_upcall(struct mbuf *m)
{
int s;
struct mfc *mfc;
struct timeval delta = { BW_UPCALL_THRESHOLD_INTERVAL_MIN_SEC,
BW_UPCALL_THRESHOLD_INTERVAL_MIN_USEC };
struct timeval now;
struct bw_meter *x;
uint32_t flags;
struct bw_upcall *req;
if (m == NULL || m->m_len < sizeof(struct bw_upcall))
return (EINVAL);
req = mtod(m, struct bw_upcall *);
if (!(mrt_api_config & MRT_MFC_BW_UPCALL))
return (EOPNOTSUPP);
/* Test if the flags are valid */
if (!(req->bu_flags & (BW_UPCALL_UNIT_PACKETS | BW_UPCALL_UNIT_BYTES)))
return (EINVAL);
if (!(req->bu_flags & (BW_UPCALL_GEQ | BW_UPCALL_LEQ)))
return (EINVAL);
if ((req->bu_flags & (BW_UPCALL_GEQ | BW_UPCALL_LEQ))
== (BW_UPCALL_GEQ | BW_UPCALL_LEQ))
return (EINVAL);
/* Test if the threshold time interval is valid */
if (BW_TIMEVALCMP(&req->bu_threshold.b_time, &delta, <))
return (EINVAL);
flags = compute_bw_meter_flags(req);
/* Find if we have already same bw_meter entry */
s = splsoftnet();
mfc = mfc_find(&req->bu_src, &req->bu_dst);
if (mfc == NULL) {
splx(s);
return (EADDRNOTAVAIL);
}
for (x = mfc->mfc_bw_meter; x != NULL; x = x->bm_mfc_next) {
if ((BW_TIMEVALCMP(&x->bm_threshold.b_time,
&req->bu_threshold.b_time, ==)) &&
(x->bm_threshold.b_packets ==
req->bu_threshold.b_packets) &&
(x->bm_threshold.b_bytes == req->bu_threshold.b_bytes) &&
(x->bm_flags & BW_METER_USER_FLAGS) == flags) {
splx(s);
return (0); /* XXX Already installed */
}
}
/* Allocate the new bw_meter entry */
x = (struct bw_meter *)malloc(sizeof(*x), M_BWMETER, M_NOWAIT);
if (x == NULL) {
splx(s);
return (ENOBUFS);
}
/* Set the new bw_meter entry */
x->bm_threshold.b_time = req->bu_threshold.b_time;
microtime(&now);
x->bm_start_time = now;
x->bm_threshold.b_packets = req->bu_threshold.b_packets;
x->bm_threshold.b_bytes = req->bu_threshold.b_bytes;
x->bm_measured.b_packets = 0;
x->bm_measured.b_bytes = 0;
x->bm_flags = flags;
x->bm_time_next = NULL;
x->bm_time_hash = BW_METER_BUCKETS;
/* Add the new bw_meter entry to the front of entries for this MFC */
x->bm_mfc = mfc;
x->bm_mfc_next = mfc->mfc_bw_meter;
mfc->mfc_bw_meter = x;
schedule_bw_meter(x, &now);
splx(s);
return (0);
}
static void
free_bw_list(struct bw_meter *list)
{
while (list != NULL) {
struct bw_meter *x = list;
list = list->bm_mfc_next;
unschedule_bw_meter(x);
free(x, M_BWMETER);
}
}
/*
* Delete one or multiple bw_meter entries
*/
static int
del_bw_upcall(struct mbuf *m)
{
int s;
struct mfc *mfc;
struct bw_meter *x;
struct bw_upcall *req;
if (m == NULL || m->m_len < sizeof(struct bw_upcall))
return (EINVAL);
req = mtod(m, struct bw_upcall *);
if (!(mrt_api_config & MRT_MFC_BW_UPCALL))
return (EOPNOTSUPP);
s = splsoftnet();
/* Find the corresponding MFC entry */
mfc = mfc_find(&req->bu_src, &req->bu_dst);
if (mfc == NULL) {
splx(s);
return (EADDRNOTAVAIL);
} else if (req->bu_flags & BW_UPCALL_DELETE_ALL) {
/* Delete all bw_meter entries for this mfc */
struct bw_meter *list;
list = mfc->mfc_bw_meter;
mfc->mfc_bw_meter = NULL;
free_bw_list(list);
splx(s);
return (0);
} else { /* Delete a single bw_meter entry */
struct bw_meter *prev;
uint32_t flags = 0;
flags = compute_bw_meter_flags(req);
/* Find the bw_meter entry to delete */
for (prev = NULL, x = mfc->mfc_bw_meter; x != NULL;
prev = x, x = x->bm_mfc_next) {
if ((BW_TIMEVALCMP(&x->bm_threshold.b_time,
&req->bu_threshold.b_time, ==)) &&
(x->bm_threshold.b_packets ==
req->bu_threshold.b_packets) &&
(x->bm_threshold.b_bytes ==
req->bu_threshold.b_bytes) &&
(x->bm_flags & BW_METER_USER_FLAGS) == flags)
break;
}
if (x != NULL) { /* Delete entry from the list for this MFC */
if (prev != NULL) {
/* remove from middle */
prev->bm_mfc_next = x->bm_mfc_next;
} else {
/* new head of list */
x->bm_mfc->mfc_bw_meter = x->bm_mfc_next;
}
unschedule_bw_meter(x);
splx(s);
/* Free the bw_meter entry */
free(x, M_BWMETER);
return (0);
} else {
splx(s);
return (EINVAL);
}
}
/* NOTREACHED */
}
/*
* Perform bandwidth measurement processing that may result in an upcall
*/
static void
bw_meter_receive_packet(struct bw_meter *x, int plen, struct timeval *nowp)
{
struct timeval delta;
delta = *nowp;
BW_TIMEVALDECR(&delta, &x->bm_start_time);
if (x->bm_flags & BW_METER_GEQ) {
/* Processing for ">=" type of bw_meter entry */
if (BW_TIMEVALCMP(&delta, &x->bm_threshold.b_time, >)) {
/* Reset the bw_meter entry */
x->bm_start_time = *nowp;
x->bm_measured.b_packets = 0;
x->bm_measured.b_bytes = 0;
x->bm_flags &= ~BW_METER_UPCALL_DELIVERED;
}
/* Record that a packet is received */
x->bm_measured.b_packets++;
x->bm_measured.b_bytes += plen;
/* Test if we should deliver an upcall */
if (!(x->bm_flags & BW_METER_UPCALL_DELIVERED)) {
if (((x->bm_flags & BW_METER_UNIT_PACKETS) &&
(x->bm_measured.b_packets >=
x->bm_threshold.b_packets)) ||
((x->bm_flags & BW_METER_UNIT_BYTES) &&
(x->bm_measured.b_bytes >=
x->bm_threshold.b_bytes))) {
/* Prepare an upcall for delivery */
bw_meter_prepare_upcall(x, nowp);
x->bm_flags |= BW_METER_UPCALL_DELIVERED;
}
}
} else if (x->bm_flags & BW_METER_LEQ) {
/* Processing for "<=" type of bw_meter entry */
if (BW_TIMEVALCMP(&delta, &x->bm_threshold.b_time, >)) {
/*
* We are behind time with the multicast forwarding
* table scanning for "<=" type of bw_meter entries,
* so test now if we should deliver an upcall.
*/
if (((x->bm_flags & BW_METER_UNIT_PACKETS) &&
(x->bm_measured.b_packets <=
x->bm_threshold.b_packets)) ||
((x->bm_flags & BW_METER_UNIT_BYTES) &&
(x->bm_measured.b_bytes <=
x->bm_threshold.b_bytes))) {
/* Prepare an upcall for delivery */
bw_meter_prepare_upcall(x, nowp);
}
/* Reschedule the bw_meter entry */
unschedule_bw_meter(x);
schedule_bw_meter(x, nowp);
}
/* Record that a packet is received */
x->bm_measured.b_packets++;
x->bm_measured.b_bytes += plen;
/* Test if we should restart the measuring interval */
if ((x->bm_flags & BW_METER_UNIT_PACKETS &&
x->bm_measured.b_packets <= x->bm_threshold.b_packets) ||
(x->bm_flags & BW_METER_UNIT_BYTES &&
x->bm_measured.b_bytes <= x->bm_threshold.b_bytes)) {
/* Don't restart the measuring interval */
} else {
/* Do restart the measuring interval */
/*
* XXX: note that we don't unschedule and schedule,
* because this might be too much overhead per packet.
* Instead, when we process all entries for a given
* timer hash bin, we check whether it is really a
* timeout. If not, we reschedule at that time.
*/
x->bm_start_time = *nowp;
x->bm_measured.b_packets = 0;
x->bm_measured.b_bytes = 0;
x->bm_flags &= ~BW_METER_UPCALL_DELIVERED;
}
}
}
/*
* Prepare a bandwidth-related upcall
*/
static void
bw_meter_prepare_upcall(struct bw_meter *x, struct timeval *nowp)
{
struct timeval delta;
struct bw_upcall *u;
/* Compute the measured time interval */
delta = *nowp;
BW_TIMEVALDECR(&delta, &x->bm_start_time);
/* If there are too many pending upcalls, deliver them now */
if (bw_upcalls_n >= BW_UPCALLS_MAX)
bw_upcalls_send();
/* Set the bw_upcall entry */
u = &bw_upcalls[bw_upcalls_n++];
u->bu_src = x->bm_mfc->mfc_origin;
u->bu_dst = x->bm_mfc->mfc_mcastgrp;
u->bu_threshold.b_time = x->bm_threshold.b_time;
u->bu_threshold.b_packets = x->bm_threshold.b_packets;
u->bu_threshold.b_bytes = x->bm_threshold.b_bytes;
u->bu_measured.b_time = delta;
u->bu_measured.b_packets = x->bm_measured.b_packets;
u->bu_measured.b_bytes = x->bm_measured.b_bytes;
u->bu_flags = 0;
if (x->bm_flags & BW_METER_UNIT_PACKETS)
u->bu_flags |= BW_UPCALL_UNIT_PACKETS;
if (x->bm_flags & BW_METER_UNIT_BYTES)
u->bu_flags |= BW_UPCALL_UNIT_BYTES;
if (x->bm_flags & BW_METER_GEQ)
u->bu_flags |= BW_UPCALL_GEQ;
if (x->bm_flags & BW_METER_LEQ)
u->bu_flags |= BW_UPCALL_LEQ;
}
/*
* Send the pending bandwidth-related upcalls
*/
static void
bw_upcalls_send(void)
{
struct mbuf *m;
int len = bw_upcalls_n * sizeof(bw_upcalls[0]);
struct sockaddr_in k_igmpsrc = { sizeof k_igmpsrc, AF_INET };
static struct igmpmsg igmpmsg = {
0, /* unused1 */
0, /* unused2 */
IGMPMSG_BW_UPCALL, /* im_msgtype */
0, /* im_mbz */
0, /* im_vif */
0, /* unused3 */
{ 0 }, /* im_src */
{ 0 } }; /* im_dst */
if (bw_upcalls_n == 0)
return; /* No pending upcalls */
bw_upcalls_n = 0;
/*
* Allocate a new mbuf, initialize it with the header and
* the payload for the pending calls.
*/
MGETHDR(m, M_DONTWAIT, MT_HEADER);
if (m == NULL) {
log(LOG_WARNING, "bw_upcalls_send: cannot allocate mbuf\n");
return;
}
m->m_len = m->m_pkthdr.len = 0;
m_copyback(m, 0, sizeof(struct igmpmsg), (caddr_t)&igmpmsg);
m_copyback(m, sizeof(struct igmpmsg), len, (caddr_t)&bw_upcalls[0]);
/*
* Send the upcalls
* XXX do we need to set the address in k_igmpsrc ?
*/
mrtstat.mrts_upcalls++;
if (socket_send(ip_mrouter, m, &k_igmpsrc) < 0) {
log(LOG_WARNING,
"bw_upcalls_send: ip_mrouter socket queue full\n");
++mrtstat.mrts_upq_sockfull;
}
}
/*
* Compute the timeout hash value for the bw_meter entries
*/
#define BW_METER_TIMEHASH(bw_meter, hash) do { \
struct timeval next_timeval = (bw_meter)->bm_start_time; \
\
BW_TIMEVALADD(&next_timeval, &(bw_meter)->bm_threshold.b_time); \
(hash) = next_timeval.tv_sec; \
if (next_timeval.tv_usec) \
(hash)++; /* XXX: make sure we don't timeout early */ \
(hash) %= BW_METER_BUCKETS; \
} while (/*CONSTCOND*/ 0)
/*
* Schedule a timer to process periodically bw_meter entry of type "<="
* by linking the entry in the proper hash bucket.
*/
static void
schedule_bw_meter(struct bw_meter *x, struct timeval *nowp)
{
int time_hash;
if (!(x->bm_flags & BW_METER_LEQ))
return; /* XXX: we schedule timers only for "<=" entries */
/* Reset the bw_meter entry */
x->bm_start_time = *nowp;
x->bm_measured.b_packets = 0;
x->bm_measured.b_bytes = 0;
x->bm_flags &= ~BW_METER_UPCALL_DELIVERED;
/* Compute the timeout hash value and insert the entry */
BW_METER_TIMEHASH(x, time_hash);
x->bm_time_next = bw_meter_timers[time_hash];
bw_meter_timers[time_hash] = x;
x->bm_time_hash = time_hash;
}
/*
* Unschedule the periodic timer that processes bw_meter entry of type "<="
* by removing the entry from the proper hash bucket.
*/
static void
unschedule_bw_meter(struct bw_meter *x)
{
int time_hash;
struct bw_meter *prev, *tmp;
if (!(x->bm_flags & BW_METER_LEQ))
return; /* XXX: we schedule timers only for "<=" entries */
/* Compute the timeout hash value and delete the entry */
time_hash = x->bm_time_hash;
if (time_hash >= BW_METER_BUCKETS)
return; /* Entry was not scheduled */
for (prev = NULL, tmp = bw_meter_timers[time_hash];
tmp != NULL; prev = tmp, tmp = tmp->bm_time_next)
if (tmp == x)
break;
if (tmp == NULL)
panic("unschedule_bw_meter: bw_meter entry not found");
if (prev != NULL)
prev->bm_time_next = x->bm_time_next;
else
bw_meter_timers[time_hash] = x->bm_time_next;
x->bm_time_next = NULL;
x->bm_time_hash = BW_METER_BUCKETS;
}
/*
* Process all "<=" type of bw_meter that should be processed now,
* and for each entry prepare an upcall if necessary. Each processed
* entry is rescheduled again for the (periodic) processing.
*
* This is run periodically (once per second normally). On each round,
* all the potentially matching entries are in the hash slot that we are
* looking at.
*/
static void
bw_meter_process()
{
int s;
static uint32_t last_tv_sec; /* last time we processed this */
uint32_t loops;
int i;
struct timeval now, process_endtime;
microtime(&now);
if (last_tv_sec == now.tv_sec)
return; /* nothing to do */
loops = now.tv_sec - last_tv_sec;
last_tv_sec = now.tv_sec;
if (loops > BW_METER_BUCKETS)
loops = BW_METER_BUCKETS;
s = splsoftnet();
/*
* Process all bins of bw_meter entries from the one after the last
* processed to the current one. On entry, i points to the last bucket
* visited, so we need to increment i at the beginning of the loop.
*/
for (i = (now.tv_sec - loops) % BW_METER_BUCKETS; loops > 0; loops--) {
struct bw_meter *x, *tmp_list;
if (++i >= BW_METER_BUCKETS)
i = 0;
/* Disconnect the list of bw_meter entries from the bin */
tmp_list = bw_meter_timers[i];
bw_meter_timers[i] = NULL;
/* Process the list of bw_meter entries */
while (tmp_list != NULL) {
x = tmp_list;
tmp_list = tmp_list->bm_time_next;
/* Test if the time interval is over */
process_endtime = x->bm_start_time;
BW_TIMEVALADD(&process_endtime,
&x->bm_threshold.b_time);
if (BW_TIMEVALCMP(&process_endtime, &now, >)) {
/* Not yet: reschedule, but don't reset */
int time_hash;
BW_METER_TIMEHASH(x, time_hash);
if (time_hash == i &&
process_endtime.tv_sec == now.tv_sec) {
/*
* XXX: somehow the bin processing is
* a bit ahead of time. Put the entry
* in the next bin.
*/
if (++time_hash >= BW_METER_BUCKETS)
time_hash = 0;
}
x->bm_time_next = bw_meter_timers[time_hash];
bw_meter_timers[time_hash] = x;
x->bm_time_hash = time_hash;
continue;
}
/* Test if we should deliver an upcall */
if (((x->bm_flags & BW_METER_UNIT_PACKETS) &&
(x->bm_measured.b_packets <=
x->bm_threshold.b_packets)) ||
((x->bm_flags & BW_METER_UNIT_BYTES) &&
(x->bm_measured.b_bytes <=
x->bm_threshold.b_bytes))) {
/* Prepare an upcall for delivery */
bw_meter_prepare_upcall(x, &now);
}
/* Reschedule for next processing */
schedule_bw_meter(x, &now);
}
}
/* Send all upcalls that are pending delivery */
bw_upcalls_send();
splx(s);
}
/*
* A periodic function for sending all upcalls that are pending delivery
*/
static void
expire_bw_upcalls_send(void *unused)
{
int s;
s = splsoftnet();
bw_upcalls_send();
splx(s);
timeout_add_msec(&bw_upcalls_ch, BW_UPCALLS_PERIOD);
}
/*
* A periodic function for periodic scanning of the multicast forwarding
* table for processing all "<=" bw_meter entries.
*/
static void
expire_bw_meter_process(void *unused)
{
if (mrt_api_config & MRT_MFC_BW_UPCALL)
bw_meter_process();
timeout_add_msec(&bw_meter_ch, BW_METER_PERIOD);
}
/*
* End of bandwidth monitoring code
*/
#ifdef PIM
/*
* Send the packet up to the user daemon, or eventually do kernel encapsulation
*/
static int
pim_register_send(struct ip *ip, struct vif *vifp,
struct mbuf *m, struct mfc *rt)
{
struct mbuf *mb_copy, *mm;
if (mrtdebug & DEBUG_PIM)
log(LOG_DEBUG, "pim_register_send: ");
mb_copy = pim_register_prepare(ip, m);
if (mb_copy == NULL)
return (ENOBUFS);
/*
* Send all the fragments. Note that the mbuf for each fragment
* is freed by the sending machinery.
*/
for (mm = mb_copy; mm; mm = mb_copy) {
mb_copy = mm->m_nextpkt;
mm->m_nextpkt = NULL;
mm = m_pullup(mm, sizeof(struct ip));
if (mm != NULL) {
ip = mtod(mm, struct ip *);
if ((mrt_api_config & MRT_MFC_RP) &&
!in_nullhost(rt->mfc_rp)) {
pim_register_send_rp(ip, vifp, mm, rt);
} else {
pim_register_send_upcall(ip, vifp, mm, rt);
}
}
}
return (0);
}
/*
* Return a copy of the data packet that is ready for PIM Register
* encapsulation.
* XXX: Note that in the returned copy the IP header is a valid one.
*/
static struct mbuf *
pim_register_prepare(struct ip *ip, struct mbuf *m)
{
struct mbuf *mb_copy = NULL;
int mtu;
/* Take care of delayed checksums */
if (m->m_pkthdr.csum_flags & (M_TCPV4_CSUM_OUT | M_UDPV4_CSUM_OUT)) {
in_delayed_cksum(m);
m->m_pkthdr.csum_flags &=
~(M_UDPV4_CSUM_OUT | M_TCPV4_CSUM_OUT);
}
/*
* Copy the old packet & pullup its IP header into the
* new mbuf so we can modify it.
*/
mb_copy = m_copy(m, 0, M_COPYALL);
if (mb_copy == NULL)
return (NULL);
mb_copy = m_pullup(mb_copy, ip->ip_hl << 2);
if (mb_copy == NULL)
return (NULL);
/* take care of the TTL */
ip = mtod(mb_copy, struct ip *);
--ip->ip_ttl;
/* Compute the MTU after the PIM Register encapsulation */
mtu = 0xffff - sizeof(pim_encap_iphdr) - sizeof(pim_encap_pimhdr);
if (ntohs(ip->ip_len) <= mtu) {
/* Turn the IP header into a valid one */
ip->ip_sum = 0;
ip->ip_sum = in_cksum(mb_copy, ip->ip_hl << 2);
} else {
/* Fragment the packet */
if (ip_fragment(mb_copy, NULL, mtu) != 0) {
/* XXX: mb_copy was freed by ip_fragment() */
return (NULL);
}
}
return (mb_copy);
}
/*
* Send an upcall with the data packet to the user-level process.
*/
static int
pim_register_send_upcall(struct ip *ip, struct vif *vifp,
struct mbuf *mb_copy, struct mfc *rt)
{
struct mbuf *mb_first;
int len = ntohs(ip->ip_len);
struct igmpmsg *im;
struct sockaddr_in k_igmpsrc = { sizeof k_igmpsrc, AF_INET };
/* Add a new mbuf with an upcall header */
MGETHDR(mb_first, M_DONTWAIT, MT_HEADER);
if (mb_first == NULL) {
m_freem(mb_copy);
return (ENOBUFS);
}
mb_first->m_data += max_linkhdr;
mb_first->m_pkthdr.len = len + sizeof(struct igmpmsg);
mb_first->m_len = sizeof(struct igmpmsg);
mb_first->m_next = mb_copy;
/* Send message to routing daemon */
im = mtod(mb_first, struct igmpmsg *);
im->im_msgtype = IGMPMSG_WHOLEPKT;
im->im_mbz = 0;
im->im_vif = vifp - viftable;
im->im_src = ip->ip_src;
im->im_dst = ip->ip_dst;
k_igmpsrc.sin_addr = ip->ip_src;
mrtstat.mrts_upcalls++;
if (socket_send(ip_mrouter, mb_first, &k_igmpsrc) < 0) {
if (mrtdebug & DEBUG_PIM)
log(LOG_WARNING, "mcast: pim_register_send_upcall: "
"ip_mrouter socket queue full");
++mrtstat.mrts_upq_sockfull;
return (ENOBUFS);
}
/* Keep statistics */
pimstat.pims_snd_registers_msgs++;
pimstat.pims_snd_registers_bytes += len;
return (0);
}
/*
* Encapsulate the data packet in PIM Register message and send it to the RP.
*/
static int
pim_register_send_rp(struct ip *ip, struct vif *vifp,
struct mbuf *mb_copy, struct mfc *rt)
{
struct mbuf *mb_first;
struct ip *ip_outer;
struct pim_encap_pimhdr *pimhdr;
int len = ntohs(ip->ip_len);
vifi_t vifi = rt->mfc_parent;
if ((vifi >= numvifs) || in_nullhost(viftable[vifi].v_lcl_addr)) {
m_freem(mb_copy);
return (EADDRNOTAVAIL); /* The iif vif is invalid */
}
/* Add a new mbuf with the encapsulating header */
MGETHDR(mb_first, M_DONTWAIT, MT_HEADER);
if (mb_first == NULL) {
m_freem(mb_copy);
return (ENOBUFS);
}
mb_first->m_data += max_linkhdr;
mb_first->m_len = sizeof(pim_encap_iphdr) + sizeof(pim_encap_pimhdr);
mb_first->m_next = mb_copy;
mb_first->m_pkthdr.len = len + mb_first->m_len;
/* Fill in the encapsulating IP and PIM header */
ip_outer = mtod(mb_first, struct ip *);
*ip_outer = pim_encap_iphdr;
ip_outer->ip_id = htons(ip_randomid());
ip_outer->ip_len = htons(len + sizeof(pim_encap_iphdr) +
sizeof(pim_encap_pimhdr));
ip_outer->ip_src = viftable[vifi].v_lcl_addr;
ip_outer->ip_dst = rt->mfc_rp;
/*
* Copy the inner header TOS to the outer header, and take care of the
* IP_DF bit.
*/
ip_outer->ip_tos = ip->ip_tos;
if (ntohs(ip->ip_off) & IP_DF)
ip_outer->ip_off |= htons(IP_DF);
pimhdr = (struct pim_encap_pimhdr *)((caddr_t)ip_outer
+ sizeof(pim_encap_iphdr));
*pimhdr = pim_encap_pimhdr;
/* If the iif crosses a border, set the Border-bit */
if (rt->mfc_flags[vifi] & MRT_MFC_FLAGS_BORDER_VIF & mrt_api_config)
pimhdr->flags |= htonl(PIM_BORDER_REGISTER);
mb_first->m_data += sizeof(pim_encap_iphdr);
pimhdr->pim.pim_cksum = in_cksum(mb_first, sizeof(pim_encap_pimhdr));
mb_first->m_data -= sizeof(pim_encap_iphdr);
send_packet(vifp, mb_first);
/* Keep statistics */
pimstat.pims_snd_registers_msgs++;
pimstat.pims_snd_registers_bytes += len;
return (0);
}
/*
* PIM-SMv2 and PIM-DM messages processing.
* Receives and verifies the PIM control messages, and passes them
* up to the listening socket, using rip_input().
* The only message with special processing is the PIM_REGISTER message
* (used by PIM-SM): the PIM header is stripped off, and the inner packet
* is passed to if_simloop().
*/
void
pim_input(struct mbuf *m, ...)
{
struct ip *ip = mtod(m, struct ip *);
struct pim *pim;
int minlen;
int datalen;
int ip_tos;
int iphlen;
va_list ap;
va_start(ap, m);
iphlen = va_arg(ap, int);
va_end(ap);
datalen = ntohs(ip->ip_len) - iphlen;
/* Keep statistics */
pimstat.pims_rcv_total_msgs++;
pimstat.pims_rcv_total_bytes += datalen;
/* Validate lengths */
if (datalen < PIM_MINLEN) {
pimstat.pims_rcv_tooshort++;
log(LOG_ERR, "pim_input: packet size too small %d from %lx\n",
datalen, (u_long)ip->ip_src.s_addr);
m_freem(m);
return;
}
/*
* If the packet is at least as big as a REGISTER, go agead
* and grab the PIM REGISTER header size, to avoid another
* possible m_pullup() later.
*
* PIM_MINLEN == pimhdr + u_int32_t == 4 + 4 = 8
* PIM_REG_MINLEN == pimhdr + reghdr + encap_iphdr == 4 + 4 + 20 = 28
*/
minlen = iphlen + (datalen >= PIM_REG_MINLEN ?
PIM_REG_MINLEN : PIM_MINLEN);
/*
* Get the IP and PIM headers in contiguous memory, and
* possibly the PIM REGISTER header.
*/
if ((m->m_flags & M_EXT || m->m_len < minlen) &&
(m = m_pullup(m, minlen)) == NULL) {
log(LOG_ERR, "pim_input: m_pullup failure\n");
return;
}
/* m_pullup() may have given us a new mbuf so reset ip. */
ip = mtod(m, struct ip *);
ip_tos = ip->ip_tos;
/* adjust mbuf to point to the PIM header */
m->m_data += iphlen;
m->m_len -= iphlen;
pim = mtod(m, struct pim *);
/*
* Validate checksum. If PIM REGISTER, exclude the data packet.
*
* XXX: some older PIMv2 implementations don't make this distinction,
* so for compatibility reason perform the checksum over part of the
* message, and if error, then over the whole message.
*/
if (PIM_VT_T(pim->pim_vt) == PIM_REGISTER &&
in_cksum(m, PIM_MINLEN) == 0) {
/* do nothing, checksum okay */
} else if (in_cksum(m, datalen)) {
pimstat.pims_rcv_badsum++;
if (mrtdebug & DEBUG_PIM)
log(LOG_DEBUG, "pim_input: invalid checksum");
m_freem(m);
return;
}
/* PIM version check */
if (PIM_VT_V(pim->pim_vt) < PIM_VERSION) {
pimstat.pims_rcv_badversion++;
log(LOG_ERR, "pim_input: incorrect version %d, expecting %d\n",
PIM_VT_V(pim->pim_vt), PIM_VERSION);
m_freem(m);
return;
}
/* restore mbuf back to the outer IP */
m->m_data -= iphlen;
m->m_len += iphlen;
if (PIM_VT_T(pim->pim_vt) == PIM_REGISTER) {
/*
* Since this is a REGISTER, we'll make a copy of the register
* headers ip + pim + u_int32 + encap_ip, to be passed up to the
* routing daemon.
*/
int s;
struct sockaddr_in dst = { sizeof(dst), AF_INET };
struct mbuf *mcp;
struct ip *encap_ip;
u_int32_t *reghdr;
struct ifnet *vifp;
s = splsoftnet();
if ((reg_vif_num >= numvifs) || (reg_vif_num == VIFI_INVALID)) {
splx(s);
if (mrtdebug & DEBUG_PIM)
log(LOG_DEBUG, "pim_input: register vif "
"not set: %d\n", reg_vif_num);
m_freem(m);
return;
}
/* XXX need refcnt? */
vifp = viftable[reg_vif_num].v_ifp;
splx(s);
/* Validate length */
if (datalen < PIM_REG_MINLEN) {
pimstat.pims_rcv_tooshort++;
pimstat.pims_rcv_badregisters++;
log(LOG_ERR, "pim_input: register packet size "
"too small %d from %lx\n",
datalen, (u_long)ip->ip_src.s_addr);
m_freem(m);
return;
}
reghdr = (u_int32_t *)(pim + 1);
encap_ip = (struct ip *)(reghdr + 1);
if (mrtdebug & DEBUG_PIM) {
log(LOG_DEBUG, "pim_input[register], encap_ip: "
"%lx -> %lx, encap_ip len %d\n",
(u_long)ntohl(encap_ip->ip_src.s_addr),
(u_long)ntohl(encap_ip->ip_dst.s_addr),
ntohs(encap_ip->ip_len));
}
/* verify the version number of the inner packet */
if (encap_ip->ip_v != IPVERSION) {
pimstat.pims_rcv_badregisters++;
if (mrtdebug & DEBUG_PIM) {
log(LOG_DEBUG, "pim_input: invalid IP version"
" (%d) of the inner packet\n",
encap_ip->ip_v);
}
m_freem(m);
return;
}
/* verify the inner packet is destined to a mcast group */
if (!IN_MULTICAST(encap_ip->ip_dst.s_addr)) {
pimstat.pims_rcv_badregisters++;
if (mrtdebug & DEBUG_PIM)
log(LOG_DEBUG,
"pim_input: inner packet of register is"
" not multicast %lx\n",
(u_long)ntohl(encap_ip->ip_dst.s_addr));
m_freem(m);
return;
}
/* If a NULL_REGISTER, pass it to the daemon */
if ((ntohl(*reghdr) & PIM_NULL_REGISTER))
goto pim_input_to_daemon;
/*
* Copy the TOS from the outer IP header to the inner
* IP header.
*/
if (encap_ip->ip_tos != ip_tos) {
/* Outer TOS -> inner TOS */
encap_ip->ip_tos = ip_tos;
/* Recompute the inner header checksum. Sigh... */
/* adjust mbuf to point to the inner IP header */
m->m_data += (iphlen + PIM_MINLEN);
m->m_len -= (iphlen + PIM_MINLEN);
encap_ip->ip_sum = 0;
encap_ip->ip_sum = in_cksum(m, encap_ip->ip_hl << 2);
/* restore mbuf to point back to the outer IP header */
m->m_data -= (iphlen + PIM_MINLEN);
m->m_len += (iphlen + PIM_MINLEN);
}
/*
* Decapsulate the inner IP packet and loopback to forward it
* as a normal multicast packet. Also, make a copy of the
* outer_iphdr + pimhdr + reghdr + encap_iphdr
* to pass to the daemon later, so it can take the appropriate
* actions (e.g., send back PIM_REGISTER_STOP).
* XXX: here m->m_data points to the outer IP header.
*/
mcp = m_copy(m, 0, iphlen + PIM_REG_MINLEN);
if (mcp == NULL) {
log(LOG_ERR, "pim_input: pim register: could not "
"copy register head\n");
m_freem(m);
return;
}
/* Keep statistics */
/* XXX: registers_bytes include only the encap. mcast pkt */
pimstat.pims_rcv_registers_msgs++;
pimstat.pims_rcv_registers_bytes += ntohs(encap_ip->ip_len);
/* forward the inner ip packet; point m_data at the inner ip. */
m_adj(m, iphlen + PIM_MINLEN);
if (mrtdebug & DEBUG_PIM) {
log(LOG_DEBUG,
"pim_input: forwarding decapsulated register: "
"src %lx, dst %lx, vif %d\n",
(u_long)ntohl(encap_ip->ip_src.s_addr),
(u_long)ntohl(encap_ip->ip_dst.s_addr),
reg_vif_num);
}
/* NB: vifp was collected above; can it change on us? */
looutput(vifp, m, (struct sockaddr *)&dst,
(struct rtentry *)NULL);
/* prepare the register head to send to the mrouting daemon */
m = mcp;
}
pim_input_to_daemon:
/*
* Pass the PIM message up to the daemon; if it is a Register message,
* pass the 'head' only up to the daemon. This includes the
* outer IP header, PIM header, PIM-Register header and the
* inner IP header.
* XXX: the outer IP header pkt size of a Register is not adjust to
* reflect the fact that the inner multicast data is truncated.
*/
rip_input(m);
return;
}
/*
* Sysctl for pim variables.
*/
int
pim_sysctl(int *name, u_int namelen, void *oldp, size_t *oldlenp,
void *newp, size_t newlen)
{
/* All sysctl names at this level are terminal. */
if (namelen != 1)
return (ENOTDIR);
switch (name[0]) {
case PIMCTL_STATS:
if (newp != NULL)
return (EPERM);
return (sysctl_struct(oldp, oldlenp, newp, newlen,
&pimstat, sizeof(pimstat)));
default:
return (ENOPROTOOPT);
}
/* NOTREACHED */
}
#endif /* PIM */
|