summaryrefslogtreecommitdiffstats
path: root/sys/netinet/ip_fw2.c
blob: 57aa13c897f2ba263bf40eac96a0394d83fcba72 (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
/*-
 * Copyright (c) 2002 Luigi Rizzo, Universita` di Pisa
 *
 * 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.
 *
 * THIS SOFTWARE IS PROVIDED BY THE AUTHOR 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 AUTHOR 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.
 *
 * $FreeBSD$
 */

#define        DEB(x)
#define        DDB(x) x

/*
 * Implement IP packet firewall (new version)
 */

#if !defined(KLD_MODULE)
#include "opt_ipfw.h"
#include "opt_ipdn.h"
#include "opt_inet.h"
#include "opt_ipsec.h"
#ifndef INET
#error IPFIREWALL requires INET.
#endif /* INET */
#endif

#define IPFW2	1
#if IPFW2
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/condvar.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/kernel.h>
#include <sys/jail.h>
#include <sys/module.h>
#include <sys/proc.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/ucred.h>
#include <net/if.h>
#include <net/radix.h>
#include <net/route.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/in_pcb.h>
#include <netinet/ip.h>
#include <netinet/ip_var.h>
#include <netinet/ip_icmp.h>
#include <netinet/ip_fw.h>
#include <netinet/ip_divert.h>
#include <netinet/ip_dummynet.h>
#include <netinet/tcp.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#include <netinet/tcpip.h>
#include <netinet/udp.h>
#include <netinet/udp_var.h>

#include <netgraph/ng_ipfw.h>

#include <altq/if_altq.h>

#ifdef IPSEC
#include <netinet6/ipsec.h>
#endif

#include <netinet/if_ether.h> /* XXX for ETHERTYPE_IP */

#include <machine/in_cksum.h>	/* XXX for in_cksum */

/*
 * set_disable contains one bit per set value (0..31).
 * If the bit is set, all rules with the corresponding set
 * are disabled. Set RESVD_SET(31) is reserved for the default rule
 * and rules that are not deleted by the flush command,
 * and CANNOT be disabled.
 * Rules in set RESVD_SET can only be deleted explicitly.
 */
static u_int32_t set_disable;

static int fw_verbose;
static int verbose_limit;

static struct callout ipfw_timeout;
static uma_zone_t ipfw_dyn_rule_zone;
#define	IPFW_DEFAULT_RULE	65535

/*
 * Data structure to cache our ucred related
 * information. This structure only gets used if
 * the user specified UID/GID based constraints in
 * a firewall rule.
 */
struct ip_fw_ugid {
	gid_t		fw_groups[NGROUPS];
	int		fw_ngroups;
	uid_t		fw_uid;
	int		fw_prid;
};

struct ip_fw_chain {
	struct ip_fw	*rules;		/* list of rules */
	struct ip_fw	*reap;		/* list of rules to reap */
	struct mtx	mtx;		/* lock guarding rule list */
	int		busy_count;	/* busy count for rw locks */
	int		want_write;
	struct cv	cv;
};
#define	IPFW_LOCK_INIT(_chain) \
	mtx_init(&(_chain)->mtx, "IPFW static rules", NULL, \
		MTX_DEF | MTX_RECURSE)
#define	IPFW_LOCK_DESTROY(_chain)	mtx_destroy(&(_chain)->mtx)
#define	IPFW_WLOCK_ASSERT(_chain)	do {				\
	mtx_assert(&(_chain)->mtx, MA_OWNED);				\
	NET_ASSERT_GIANT();						\
} while (0)

static __inline void
IPFW_RLOCK(struct ip_fw_chain *chain)
{
	mtx_lock(&chain->mtx);
	chain->busy_count++;
	mtx_unlock(&chain->mtx);
}

static __inline void
IPFW_RUNLOCK(struct ip_fw_chain *chain)
{
	mtx_lock(&chain->mtx);
	chain->busy_count--;
	if (chain->busy_count == 0 && chain->want_write)
		cv_signal(&chain->cv);
	mtx_unlock(&chain->mtx);
}

static __inline void
IPFW_WLOCK(struct ip_fw_chain *chain)
{
	mtx_lock(&chain->mtx);
	chain->want_write++;
	while (chain->busy_count > 0)
		cv_wait(&chain->cv, &chain->mtx);
}

static __inline void
IPFW_WUNLOCK(struct ip_fw_chain *chain)
{
	chain->want_write--;
	cv_signal(&chain->cv);
	mtx_unlock(&chain->mtx);
}

/*
 * list of rules for layer 3
 */
static struct ip_fw_chain layer3_chain;

MALLOC_DEFINE(M_IPFW, "IpFw/IpAcct", "IpFw/IpAcct chain's");
MALLOC_DEFINE(M_IPFW_TBL, "ipfw_tbl", "IpFw tables");

struct table_entry {
	struct radix_node	rn[2];
	struct sockaddr_in	addr, mask;
	u_int32_t		value;
};

#define	IPFW_TABLES_MAX		128
static struct {
	struct radix_node_head	*rnh;
	int			modified;
} ipfw_tables[IPFW_TABLES_MAX];

static int fw_debug = 1;
static int autoinc_step = 100; /* bounded to 1..1000 in add_rule() */

#ifdef SYSCTL_NODE
SYSCTL_NODE(_net_inet_ip, OID_AUTO, fw, CTLFLAG_RW, 0, "Firewall");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, enable,
    CTLFLAG_RW | CTLFLAG_SECURE3,
    &fw_enable, 0, "Enable ipfw");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, autoinc_step, CTLFLAG_RW,
    &autoinc_step, 0, "Rule number autincrement step");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, one_pass,
    CTLFLAG_RW | CTLFLAG_SECURE3,
    &fw_one_pass, 0,
    "Only do a single pass through ipfw when using dummynet(4)");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, debug, CTLFLAG_RW,
    &fw_debug, 0, "Enable printing of debug ip_fw statements");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, verbose,
    CTLFLAG_RW | CTLFLAG_SECURE3,
    &fw_verbose, 0, "Log matches to ipfw rules");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, verbose_limit, CTLFLAG_RW,
    &verbose_limit, 0, "Set upper limit of matches of ipfw rules logged");

/*
 * Description of dynamic rules.
 *
 * Dynamic rules are stored in lists accessed through a hash table
 * (ipfw_dyn_v) whose size is curr_dyn_buckets. This value can
 * be modified through the sysctl variable dyn_buckets which is
 * updated when the table becomes empty.
 *
 * XXX currently there is only one list, ipfw_dyn.
 *
 * When a packet is received, its address fields are first masked
 * with the mask defined for the rule, then hashed, then matched
 * against the entries in the corresponding list.
 * Dynamic rules can be used for different purposes:
 *  + stateful rules;
 *  + enforcing limits on the number of sessions;
 *  + in-kernel NAT (not implemented yet)
 *
 * The lifetime of dynamic rules is regulated by dyn_*_lifetime,
 * measured in seconds and depending on the flags.
 *
 * The total number of dynamic rules is stored in dyn_count.
 * The max number of dynamic rules is dyn_max. When we reach
 * the maximum number of rules we do not create anymore. This is
 * done to avoid consuming too much memory, but also too much
 * time when searching on each packet (ideally, we should try instead
 * to put a limit on the length of the list on each bucket...).
 *
 * Each dynamic rule holds a pointer to the parent ipfw rule so
 * we know what action to perform. Dynamic rules are removed when
 * the parent rule is deleted. XXX we should make them survive.
 *
 * There are some limitations with dynamic rules -- we do not
 * obey the 'randomized match', and we do not do multiple
 * passes through the firewall. XXX check the latter!!!
 */
static ipfw_dyn_rule **ipfw_dyn_v = NULL;
static u_int32_t dyn_buckets = 256; /* must be power of 2 */
static u_int32_t curr_dyn_buckets = 256; /* must be power of 2 */

static struct mtx ipfw_dyn_mtx;		/* mutex guarding dynamic rules */
#define	IPFW_DYN_LOCK_INIT() \
	mtx_init(&ipfw_dyn_mtx, "IPFW dynamic rules", NULL, MTX_DEF)
#define	IPFW_DYN_LOCK_DESTROY()	mtx_destroy(&ipfw_dyn_mtx)
#define	IPFW_DYN_LOCK()		mtx_lock(&ipfw_dyn_mtx)
#define	IPFW_DYN_UNLOCK()	mtx_unlock(&ipfw_dyn_mtx)
#define	IPFW_DYN_LOCK_ASSERT()	mtx_assert(&ipfw_dyn_mtx, MA_OWNED)

/*
 * Timeouts for various events in handing dynamic rules.
 */
static u_int32_t dyn_ack_lifetime = 300;
static u_int32_t dyn_syn_lifetime = 20;
static u_int32_t dyn_fin_lifetime = 1;
static u_int32_t dyn_rst_lifetime = 1;
static u_int32_t dyn_udp_lifetime = 10;
static u_int32_t dyn_short_lifetime = 5;

/*
 * Keepalives are sent if dyn_keepalive is set. They are sent every
 * dyn_keepalive_period seconds, in the last dyn_keepalive_interval
 * seconds of lifetime of a rule.
 * dyn_rst_lifetime and dyn_fin_lifetime should be strictly lower
 * than dyn_keepalive_period.
 */

static u_int32_t dyn_keepalive_interval = 20;
static u_int32_t dyn_keepalive_period = 5;
static u_int32_t dyn_keepalive = 1;	/* do send keepalives */

static u_int32_t static_count;	/* # of static rules */
static u_int32_t static_len;	/* size in bytes of static rules */
static u_int32_t dyn_count;		/* # of dynamic rules */
static u_int32_t dyn_max = 4096;	/* max # of dynamic rules */

SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_buckets, CTLFLAG_RW,
    &dyn_buckets, 0, "Number of dyn. buckets");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, curr_dyn_buckets, CTLFLAG_RD,
    &curr_dyn_buckets, 0, "Current Number of dyn. buckets");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_count, CTLFLAG_RD,
    &dyn_count, 0, "Number of dyn. rules");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_max, CTLFLAG_RW,
    &dyn_max, 0, "Max number of dyn. rules");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, static_count, CTLFLAG_RD,
    &static_count, 0, "Number of static rules");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_ack_lifetime, CTLFLAG_RW,
    &dyn_ack_lifetime, 0, "Lifetime of dyn. rules for acks");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_syn_lifetime, CTLFLAG_RW,
    &dyn_syn_lifetime, 0, "Lifetime of dyn. rules for syn");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_fin_lifetime, CTLFLAG_RW,
    &dyn_fin_lifetime, 0, "Lifetime of dyn. rules for fin");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_rst_lifetime, CTLFLAG_RW,
    &dyn_rst_lifetime, 0, "Lifetime of dyn. rules for rst");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_udp_lifetime, CTLFLAG_RW,
    &dyn_udp_lifetime, 0, "Lifetime of dyn. rules for UDP");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_short_lifetime, CTLFLAG_RW,
    &dyn_short_lifetime, 0, "Lifetime of dyn. rules for other situations");
SYSCTL_INT(_net_inet_ip_fw, OID_AUTO, dyn_keepalive, CTLFLAG_RW,
    &dyn_keepalive, 0, "Enable keepalives for dyn. rules");

#endif /* SYSCTL_NODE */


/*
 * This macro maps an ip pointer into a layer3 header pointer of type T
 */
#define	L3HDR(T, ip) ((T *)((u_int32_t *)(ip) + (ip)->ip_hl))

static __inline int
icmptype_match(struct ip *ip, ipfw_insn_u32 *cmd)
{
	int type = L3HDR(struct icmp,ip)->icmp_type;

	return (type <= ICMP_MAXTYPE && (cmd->d[0] & (1<<type)) );
}

#define TT	( (1 << ICMP_ECHO) | (1 << ICMP_ROUTERSOLICIT) | \
    (1 << ICMP_TSTAMP) | (1 << ICMP_IREQ) | (1 << ICMP_MASKREQ) )

static int
is_icmp_query(struct ip *ip)
{
	int type = L3HDR(struct icmp, ip)->icmp_type;
	return (type <= ICMP_MAXTYPE && (TT & (1<<type)) );
}
#undef TT

/*
 * The following checks use two arrays of 8 or 16 bits to store the
 * bits that we want set or clear, respectively. They are in the
 * low and high half of cmd->arg1 or cmd->d[0].
 *
 * We scan options and store the bits we find set. We succeed if
 *
 *	(want_set & ~bits) == 0 && (want_clear & ~bits) == want_clear
 *
 * The code is sometimes optimized not to store additional variables.
 */

static int
flags_match(ipfw_insn *cmd, u_int8_t bits)
{
	u_char want_clear;
	bits = ~bits;

	if ( ((cmd->arg1 & 0xff) & bits) != 0)
		return 0; /* some bits we want set were clear */
	want_clear = (cmd->arg1 >> 8) & 0xff;
	if ( (want_clear & bits) != want_clear)
		return 0; /* some bits we want clear were set */
	return 1;
}

static int
ipopts_match(struct ip *ip, ipfw_insn *cmd)
{
	int optlen, bits = 0;
	u_char *cp = (u_char *)(ip + 1);
	int x = (ip->ip_hl << 2) - sizeof (struct ip);

	for (; x > 0; x -= optlen, cp += optlen) {
		int opt = cp[IPOPT_OPTVAL];

		if (opt == IPOPT_EOL)
			break;
		if (opt == IPOPT_NOP)
			optlen = 1;
		else {
			optlen = cp[IPOPT_OLEN];
			if (optlen <= 0 || optlen > x)
				return 0; /* invalid or truncated */
		}
		switch (opt) {

		default:
			break;

		case IPOPT_LSRR:
			bits |= IP_FW_IPOPT_LSRR;
			break;

		case IPOPT_SSRR:
			bits |= IP_FW_IPOPT_SSRR;
			break;

		case IPOPT_RR:
			bits |= IP_FW_IPOPT_RR;
			break;

		case IPOPT_TS:
			bits |= IP_FW_IPOPT_TS;
			break;
		}
	}
	return (flags_match(cmd, bits));
}

static int
tcpopts_match(struct ip *ip, ipfw_insn *cmd)
{
	int optlen, bits = 0;
	struct tcphdr *tcp = L3HDR(struct tcphdr,ip);
	u_char *cp = (u_char *)(tcp + 1);
	int x = (tcp->th_off << 2) - sizeof(struct tcphdr);

	for (; x > 0; x -= optlen, cp += optlen) {
		int opt = cp[0];
		if (opt == TCPOPT_EOL)
			break;
		if (opt == TCPOPT_NOP)
			optlen = 1;
		else {
			optlen = cp[1];
			if (optlen <= 0)
				break;
		}

		switch (opt) {

		default:
			break;

		case TCPOPT_MAXSEG:
			bits |= IP_FW_TCPOPT_MSS;
			break;

		case TCPOPT_WINDOW:
			bits |= IP_FW_TCPOPT_WINDOW;
			break;

		case TCPOPT_SACK_PERMITTED:
		case TCPOPT_SACK:
			bits |= IP_FW_TCPOPT_SACK;
			break;

		case TCPOPT_TIMESTAMP:
			bits |= IP_FW_TCPOPT_TS;
			break;

		}
	}
	return (flags_match(cmd, bits));
}

static int
iface_match(struct ifnet *ifp, ipfw_insn_if *cmd)
{
	if (ifp == NULL)	/* no iface with this packet, match fails */
		return 0;
	/* Check by name or by IP address */
	if (cmd->name[0] != '\0') { /* match by name */
		/* Check name */
		if (cmd->p.glob) {
			if (fnmatch(cmd->name, ifp->if_xname, 0) == 0)
				return(1);
		} else {
			if (strncmp(ifp->if_xname, cmd->name, IFNAMSIZ) == 0)
				return(1);
		}
	} else {
		struct ifaddr *ia;

		/* XXX lock? */
		TAILQ_FOREACH(ia, &ifp->if_addrhead, ifa_link) {
			if (ia->ifa_addr == NULL)
				continue;
			if (ia->ifa_addr->sa_family != AF_INET)
				continue;
			if (cmd->p.ip.s_addr == ((struct sockaddr_in *)
			    (ia->ifa_addr))->sin_addr.s_addr)
				return(1);	/* match */
		}
	}
	return(0);	/* no match, fail ... */
}

/*
 * The verify_path function checks if a route to the src exists and
 * if it is reachable via ifp (when provided).
 * 
 * The 'verrevpath' option checks that the interface that an IP packet
 * arrives on is the same interface that traffic destined for the
 * packet's source address would be routed out of.  The 'versrcreach'
 * option just checks that the source address is reachable via any route
 * (except default) in the routing table.  These two are a measure to block
 * forged packets.  This is also commonly known as "anti-spoofing" or Unicast
 * Reverse Path Forwarding (Unicast RFP) in Cisco-ese. The name of the knobs
 * is purposely reminiscent of the Cisco IOS command,
 *
 *   ip verify unicast reverse-path
 *   ip verify unicast source reachable-via any
 *
 * which implements the same functionality. But note that syntax is
 * misleading. The check may be performed on all IP packets whether unicast,
 * multicast, or broadcast.
 */
static int
verify_path(struct in_addr src, struct ifnet *ifp)
{
	struct route ro;
	struct sockaddr_in *dst;

	bzero(&ro, sizeof(ro));

	dst = (struct sockaddr_in *)&(ro.ro_dst);
	dst->sin_family = AF_INET;
	dst->sin_len = sizeof(*dst);
	dst->sin_addr = src;
	rtalloc_ign(&ro, RTF_CLONING);

	if (ro.ro_rt == NULL)
		return 0;

	/* if ifp is provided, check for equality with rtentry */
	if (ifp != NULL && ro.ro_rt->rt_ifp != ifp) {
		RTFREE(ro.ro_rt);
		return 0;
	}

	/* if no ifp provided, check if rtentry is not default route */
	if (ifp == NULL &&
	     satosin(rt_key(ro.ro_rt))->sin_addr.s_addr == INADDR_ANY) {
		RTFREE(ro.ro_rt);
		return 0;
	}

	/* or if this is a blackhole/reject route */
	if (ifp == NULL && ro.ro_rt->rt_flags & (RTF_REJECT|RTF_BLACKHOLE)) {
		RTFREE(ro.ro_rt);
		return 0;
	}

	/* found valid route */
	RTFREE(ro.ro_rt);
	return 1;
}


static u_int64_t norule_counter;	/* counter for ipfw_log(NULL...) */

#define SNPARGS(buf, len) buf + len, sizeof(buf) > len ? sizeof(buf) - len : 0
#define SNP(buf) buf, sizeof(buf)

/*
 * We enter here when we have a rule with O_LOG.
 * XXX this function alone takes about 2Kbytes of code!
 */
static void
ipfw_log(struct ip_fw *f, u_int hlen, struct ether_header *eh,
	struct mbuf *m, struct ifnet *oif)
{
	char *action;
	int limit_reached = 0;
	char action2[40], proto[48], fragment[28];

	fragment[0] = '\0';
	proto[0] = '\0';

	if (f == NULL) {	/* bogus pkt */
		if (verbose_limit != 0 && norule_counter >= verbose_limit)
			return;
		norule_counter++;
		if (norule_counter == verbose_limit)
			limit_reached = verbose_limit;
		action = "Refuse";
	} else {	/* O_LOG is the first action, find the real one */
		ipfw_insn *cmd = ACTION_PTR(f);
		ipfw_insn_log *l = (ipfw_insn_log *)cmd;

		if (l->max_log != 0 && l->log_left == 0)
			return;
		l->log_left--;
		if (l->log_left == 0)
			limit_reached = l->max_log;
		cmd += F_LEN(cmd);	/* point to first action */
		if (cmd->opcode == O_ALTQ) {
			ipfw_insn_altq *altq = (ipfw_insn_altq *)cmd;

			snprintf(SNPARGS(action2, 0), "Altq %d",
				altq->qid);
			cmd += F_LEN(cmd);
		}
		if (cmd->opcode == O_PROB)
			cmd += F_LEN(cmd);

		action = action2;
		switch (cmd->opcode) {
		case O_DENY:
			action = "Deny";
			break;

		case O_REJECT:
			if (cmd->arg1==ICMP_REJECT_RST)
				action = "Reset";
			else if (cmd->arg1==ICMP_UNREACH_HOST)
				action = "Reject";
			else
				snprintf(SNPARGS(action2, 0), "Unreach %d",
					cmd->arg1);
			break;

		case O_ACCEPT:
			action = "Accept";
			break;
		case O_COUNT:
			action = "Count";
			break;
		case O_DIVERT:
			snprintf(SNPARGS(action2, 0), "Divert %d",
				cmd->arg1);
			break;
		case O_TEE:
			snprintf(SNPARGS(action2, 0), "Tee %d",
				cmd->arg1);
			break;
		case O_SKIPTO:
			snprintf(SNPARGS(action2, 0), "SkipTo %d",
				cmd->arg1);
			break;
		case O_PIPE:
			snprintf(SNPARGS(action2, 0), "Pipe %d",
				cmd->arg1);
			break;
		case O_QUEUE:
			snprintf(SNPARGS(action2, 0), "Queue %d",
				cmd->arg1);
			break;
		case O_FORWARD_IP: {
			ipfw_insn_sa *sa = (ipfw_insn_sa *)cmd;
			int len;

			len = snprintf(SNPARGS(action2, 0), "Forward to %s",
				inet_ntoa(sa->sa.sin_addr));
			if (sa->sa.sin_port)
				snprintf(SNPARGS(action2, len), ":%d",
				    sa->sa.sin_port);
			}
			break;
		case O_NETGRAPH:
			snprintf(SNPARGS(action2, 0), "Netgraph %d",
				cmd->arg1);
			break;
		case O_NGTEE:
			snprintf(SNPARGS(action2, 0), "Ngtee %d",
				cmd->arg1);
			break;
		default:
			action = "UNKNOWN";
			break;
		}
	}

	if (hlen == 0) {	/* non-ip */
		snprintf(SNPARGS(proto, 0), "MAC");
	} else {
		struct ip *ip = mtod(m, struct ip *);
		/* these three are all aliases to the same thing */
		struct icmp *const icmp = L3HDR(struct icmp, ip);
		struct tcphdr *const tcp = (struct tcphdr *)icmp;
		struct udphdr *const udp = (struct udphdr *)icmp;

		int ip_off, offset, ip_len;

		int len;

		if (eh != NULL) { /* layer 2 packets are as on the wire */
			ip_off = ntohs(ip->ip_off);
			ip_len = ntohs(ip->ip_len);
		} else {
			ip_off = ip->ip_off;
			ip_len = ip->ip_len;
		}
		offset = ip_off & IP_OFFMASK;
		switch (ip->ip_p) {
		case IPPROTO_TCP:
			len = snprintf(SNPARGS(proto, 0), "TCP %s",
			    inet_ntoa(ip->ip_src));
			if (offset == 0)
				snprintf(SNPARGS(proto, len), ":%d %s:%d",
				    ntohs(tcp->th_sport),
				    inet_ntoa(ip->ip_dst),
				    ntohs(tcp->th_dport));
			else
				snprintf(SNPARGS(proto, len), " %s",
				    inet_ntoa(ip->ip_dst));
			break;

		case IPPROTO_UDP:
			len = snprintf(SNPARGS(proto, 0), "UDP %s",
				inet_ntoa(ip->ip_src));
			if (offset == 0)
				snprintf(SNPARGS(proto, len), ":%d %s:%d",
				    ntohs(udp->uh_sport),
				    inet_ntoa(ip->ip_dst),
				    ntohs(udp->uh_dport));
			else
				snprintf(SNPARGS(proto, len), " %s",
				    inet_ntoa(ip->ip_dst));
			break;

		case IPPROTO_ICMP:
			if (offset == 0)
				len = snprintf(SNPARGS(proto, 0),
				    "ICMP:%u.%u ",
				    icmp->icmp_type, icmp->icmp_code);
			else
				len = snprintf(SNPARGS(proto, 0), "ICMP ");
			len += snprintf(SNPARGS(proto, len), "%s",
			    inet_ntoa(ip->ip_src));
			snprintf(SNPARGS(proto, len), " %s",
			    inet_ntoa(ip->ip_dst));
			break;

		default:
			len = snprintf(SNPARGS(proto, 0), "P:%d %s", ip->ip_p,
			    inet_ntoa(ip->ip_src));
			snprintf(SNPARGS(proto, len), " %s",
			    inet_ntoa(ip->ip_dst));
			break;
		}

		if (ip_off & (IP_MF | IP_OFFMASK))
			snprintf(SNPARGS(fragment, 0), " (frag %d:%d@%d%s)",
			     ntohs(ip->ip_id), ip_len - (ip->ip_hl << 2),
			     offset << 3,
			     (ip_off & IP_MF) ? "+" : "");
	}
	if (oif || m->m_pkthdr.rcvif)
		log(LOG_SECURITY | LOG_INFO,
		    "ipfw: %d %s %s %s via %s%s\n",
		    f ? f->rulenum : -1,
		    action, proto, oif ? "out" : "in",
		    oif ? oif->if_xname : m->m_pkthdr.rcvif->if_xname,
		    fragment);
	else
		log(LOG_SECURITY | LOG_INFO,
		    "ipfw: %d %s %s [no if info]%s\n",
		    f ? f->rulenum : -1,
		    action, proto, fragment);
	if (limit_reached)
		log(LOG_SECURITY | LOG_NOTICE,
		    "ipfw: limit %d reached on entry %d\n",
		    limit_reached, f ? f->rulenum : -1);
}

/*
 * IMPORTANT: the hash function for dynamic rules must be commutative
 * in source and destination (ip,port), because rules are bidirectional
 * and we want to find both in the same bucket.
 */
static __inline int
hash_packet(struct ipfw_flow_id *id)
{
	u_int32_t i;

	i = (id->dst_ip) ^ (id->src_ip) ^ (id->dst_port) ^ (id->src_port);
	i &= (curr_dyn_buckets - 1);
	return i;
}

/**
 * unlink a dynamic rule from a chain. prev is a pointer to
 * the previous one, q is a pointer to the rule to delete,
 * head is a pointer to the head of the queue.
 * Modifies q and potentially also head.
 */
#define UNLINK_DYN_RULE(prev, head, q) {				\
	ipfw_dyn_rule *old_q = q;					\
									\
	/* remove a refcount to the parent */				\
	if (q->dyn_type == O_LIMIT)					\
		q->parent->count--;					\
	DEB(printf("ipfw: unlink entry 0x%08x %d -> 0x%08x %d, %d left\n",\
		(q->id.src_ip), (q->id.src_port),			\
		(q->id.dst_ip), (q->id.dst_port), dyn_count-1 ); )	\
	if (prev != NULL)						\
		prev->next = q = q->next;				\
	else								\
		head = q = q->next;					\
	dyn_count--;							\
	uma_zfree(ipfw_dyn_rule_zone, old_q); }

#define TIME_LEQ(a,b)       ((int)((a)-(b)) <= 0)

/**
 * Remove dynamic rules pointing to "rule", or all of them if rule == NULL.
 *
 * If keep_me == NULL, rules are deleted even if not expired,
 * otherwise only expired rules are removed.
 *
 * The value of the second parameter is also used to point to identify
 * a rule we absolutely do not want to remove (e.g. because we are
 * holding a reference to it -- this is the case with O_LIMIT_PARENT
 * rules). The pointer is only used for comparison, so any non-null
 * value will do.
 */
static void
remove_dyn_rule(struct ip_fw *rule, ipfw_dyn_rule *keep_me)
{
	static u_int32_t last_remove = 0;

#define FORCE (keep_me == NULL)

	ipfw_dyn_rule *prev, *q;
	int i, pass = 0, max_pass = 0;

	IPFW_DYN_LOCK_ASSERT();

	if (ipfw_dyn_v == NULL || dyn_count == 0)
		return;
	/* do not expire more than once per second, it is useless */
	if (!FORCE && last_remove == time_second)
		return;
	last_remove = time_second;

	/*
	 * because O_LIMIT refer to parent rules, during the first pass only
	 * remove child and mark any pending LIMIT_PARENT, and remove
	 * them in a second pass.
	 */
next_pass:
	for (i = 0 ; i < curr_dyn_buckets ; i++) {
		for (prev=NULL, q = ipfw_dyn_v[i] ; q ; ) {
			/*
			 * Logic can become complex here, so we split tests.
			 */
			if (q == keep_me)
				goto next;
			if (rule != NULL && rule != q->rule)
				goto next; /* not the one we are looking for */
			if (q->dyn_type == O_LIMIT_PARENT) {
				/*
				 * handle parent in the second pass,
				 * record we need one.
				 */
				max_pass = 1;
				if (pass == 0)
					goto next;
				if (FORCE && q->count != 0 ) {
					/* XXX should not happen! */
					printf("ipfw: OUCH! cannot remove rule,"
					     " count %d\n", q->count);
				}
			} else {
				if (!FORCE &&
				    !TIME_LEQ( q->expire, time_second ))
					goto next;
			}
             if (q->dyn_type != O_LIMIT_PARENT || !q->count) {
                     UNLINK_DYN_RULE(prev, ipfw_dyn_v[i], q);
                     continue;
             }
next:
			prev=q;
			q=q->next;
		}
	}
	if (pass++ < max_pass)
		goto next_pass;
}


/**
 * lookup a dynamic rule.
 */
static ipfw_dyn_rule *
lookup_dyn_rule_locked(struct ipfw_flow_id *pkt, int *match_direction,
	struct tcphdr *tcp)
{
	/*
	 * stateful ipfw extensions.
	 * Lookup into dynamic session queue
	 */
#define MATCH_REVERSE	0
#define MATCH_FORWARD	1
#define MATCH_NONE	2
#define MATCH_UNKNOWN	3
	int i, dir = MATCH_NONE;
	ipfw_dyn_rule *prev, *q=NULL;

	IPFW_DYN_LOCK_ASSERT();

	if (ipfw_dyn_v == NULL)
		goto done;	/* not found */
	i = hash_packet( pkt );
	for (prev=NULL, q = ipfw_dyn_v[i] ; q != NULL ; ) {
		if (q->dyn_type == O_LIMIT_PARENT && q->count)
			goto next;
		if (TIME_LEQ( q->expire, time_second)) { /* expire entry */
			UNLINK_DYN_RULE(prev, ipfw_dyn_v[i], q);
			continue;
		}
		if (pkt->proto == q->id.proto &&
		    q->dyn_type != O_LIMIT_PARENT) {
			if (pkt->src_ip == q->id.src_ip &&
			    pkt->dst_ip == q->id.dst_ip &&
			    pkt->src_port == q->id.src_port &&
			    pkt->dst_port == q->id.dst_port ) {
				dir = MATCH_FORWARD;
				break;
			}
			if (pkt->src_ip == q->id.dst_ip &&
			    pkt->dst_ip == q->id.src_ip &&
			    pkt->src_port == q->id.dst_port &&
			    pkt->dst_port == q->id.src_port ) {
				dir = MATCH_REVERSE;
				break;
			}
		}
next:
		prev = q;
		q = q->next;
	}
	if (q == NULL)
		goto done; /* q = NULL, not found */

	if ( prev != NULL) { /* found and not in front */
		prev->next = q->next;
		q->next = ipfw_dyn_v[i];
		ipfw_dyn_v[i] = q;
	}
	if (pkt->proto == IPPROTO_TCP) { /* update state according to flags */
		u_char flags = pkt->flags & (TH_FIN|TH_SYN|TH_RST);

#define BOTH_SYN	(TH_SYN | (TH_SYN << 8))
#define BOTH_FIN	(TH_FIN | (TH_FIN << 8))
		q->state |= (dir == MATCH_FORWARD ) ? flags : (flags << 8);
		switch (q->state) {
		case TH_SYN:				/* opening */
			q->expire = time_second + dyn_syn_lifetime;
			break;

		case BOTH_SYN:			/* move to established */
		case BOTH_SYN | TH_FIN :	/* one side tries to close */
		case BOTH_SYN | (TH_FIN << 8) :
 			if (tcp) {
#define _SEQ_GE(a,b) ((int)(a) - (int)(b) >= 0)
			    u_int32_t ack = ntohl(tcp->th_ack);
			    if (dir == MATCH_FORWARD) {
				if (q->ack_fwd == 0 || _SEQ_GE(ack, q->ack_fwd))
				    q->ack_fwd = ack;
				else { /* ignore out-of-sequence */
				    break;
				}
			    } else {
				if (q->ack_rev == 0 || _SEQ_GE(ack, q->ack_rev))
				    q->ack_rev = ack;
				else { /* ignore out-of-sequence */
				    break;
				}
			    }
			}
			q->expire = time_second + dyn_ack_lifetime;
			break;

		case BOTH_SYN | BOTH_FIN:	/* both sides closed */
			if (dyn_fin_lifetime >= dyn_keepalive_period)
				dyn_fin_lifetime = dyn_keepalive_period - 1;
			q->expire = time_second + dyn_fin_lifetime;
			break;

		default:
#if 0
			/*
			 * reset or some invalid combination, but can also
			 * occur if we use keep-state the wrong way.
			 */
			if ( (q->state & ((TH_RST << 8)|TH_RST)) == 0)
				printf("invalid state: 0x%x\n", q->state);
#endif
			if (dyn_rst_lifetime >= dyn_keepalive_period)
				dyn_rst_lifetime = dyn_keepalive_period - 1;
			q->expire = time_second + dyn_rst_lifetime;
			break;
		}
	} else if (pkt->proto == IPPROTO_UDP) {
		q->expire = time_second + dyn_udp_lifetime;
	} else {
		/* other protocols */
		q->expire = time_second + dyn_short_lifetime;
	}
done:
	if (match_direction)
		*match_direction = dir;
	return q;
}

static ipfw_dyn_rule *
lookup_dyn_rule(struct ipfw_flow_id *pkt, int *match_direction,
	struct tcphdr *tcp)
{
	ipfw_dyn_rule *q;

	IPFW_DYN_LOCK();
	q = lookup_dyn_rule_locked(pkt, match_direction, tcp);
	if (q == NULL)
		IPFW_DYN_UNLOCK();
	/* NB: return table locked when q is not NULL */
	return q;
}

static void
realloc_dynamic_table(void)
{
	IPFW_DYN_LOCK_ASSERT();

	/*
	 * Try reallocation, make sure we have a power of 2 and do
	 * not allow more than 64k entries. In case of overflow,
	 * default to 1024.
	 */

	if (dyn_buckets > 65536)
		dyn_buckets = 1024;
	if ((dyn_buckets & (dyn_buckets-1)) != 0) { /* not a power of 2 */
		dyn_buckets = curr_dyn_buckets; /* reset */
		return;
	}
	curr_dyn_buckets = dyn_buckets;
	if (ipfw_dyn_v != NULL)
		free(ipfw_dyn_v, M_IPFW);
	for (;;) {
		ipfw_dyn_v = malloc(curr_dyn_buckets * sizeof(ipfw_dyn_rule *),
		       M_IPFW, M_NOWAIT | M_ZERO);
		if (ipfw_dyn_v != NULL || curr_dyn_buckets <= 2)
			break;
		curr_dyn_buckets /= 2;
	}
}

/**
 * Install state of type 'type' for a dynamic session.
 * The hash table contains two type of rules:
 * - regular rules (O_KEEP_STATE)
 * - rules for sessions with limited number of sess per user
 *   (O_LIMIT). When they are created, the parent is
 *   increased by 1, and decreased on delete. In this case,
 *   the third parameter is the parent rule and not the chain.
 * - "parent" rules for the above (O_LIMIT_PARENT).
 */
static ipfw_dyn_rule *
add_dyn_rule(struct ipfw_flow_id *id, u_int8_t dyn_type, struct ip_fw *rule)
{
	ipfw_dyn_rule *r;
	int i;

	IPFW_DYN_LOCK_ASSERT();

	if (ipfw_dyn_v == NULL ||
	    (dyn_count == 0 && dyn_buckets != curr_dyn_buckets)) {
		realloc_dynamic_table();
		if (ipfw_dyn_v == NULL)
			return NULL; /* failed ! */
	}
	i = hash_packet(id);

	r = uma_zalloc(ipfw_dyn_rule_zone, M_NOWAIT | M_ZERO);
	if (r == NULL) {
		printf ("ipfw: sorry cannot allocate state\n");
		return NULL;
	}

	/* increase refcount on parent, and set pointer */
	if (dyn_type == O_LIMIT) {
		ipfw_dyn_rule *parent = (ipfw_dyn_rule *)rule;
		if ( parent->dyn_type != O_LIMIT_PARENT)
			panic("invalid parent");
		parent->count++;
		r->parent = parent;
		rule = parent->rule;
	}

	r->id = *id;
	r->expire = time_second + dyn_syn_lifetime;
	r->rule = rule;
	r->dyn_type = dyn_type;
	r->pcnt = r->bcnt = 0;
	r->count = 0;

	r->bucket = i;
	r->next = ipfw_dyn_v[i];
	ipfw_dyn_v[i] = r;
	dyn_count++;
	DEB(printf("ipfw: add dyn entry ty %d 0x%08x %d -> 0x%08x %d, total %d\n",
	   dyn_type,
	   (r->id.src_ip), (r->id.src_port),
	   (r->id.dst_ip), (r->id.dst_port),
	   dyn_count ); )
	return r;
}

/**
 * lookup dynamic parent rule using pkt and rule as search keys.
 * If the lookup fails, then install one.
 */
static ipfw_dyn_rule *
lookup_dyn_parent(struct ipfw_flow_id *pkt, struct ip_fw *rule)
{
	ipfw_dyn_rule *q;
	int i;

	IPFW_DYN_LOCK_ASSERT();

	if (ipfw_dyn_v) {
		i = hash_packet( pkt );
		for (q = ipfw_dyn_v[i] ; q != NULL ; q=q->next)
			if (q->dyn_type == O_LIMIT_PARENT &&
			    rule== q->rule &&
			    pkt->proto == q->id.proto &&
			    pkt->src_ip == q->id.src_ip &&
			    pkt->dst_ip == q->id.dst_ip &&
			    pkt->src_port == q->id.src_port &&
			    pkt->dst_port == q->id.dst_port) {
				q->expire = time_second + dyn_short_lifetime;
				DEB(printf("ipfw: lookup_dyn_parent found 0x%p\n",q);)
				return q;
			}
	}
	return add_dyn_rule(pkt, O_LIMIT_PARENT, rule);
}

/**
 * Install dynamic state for rule type cmd->o.opcode
 *
 * Returns 1 (failure) if state is not installed because of errors or because
 * session limitations are enforced.
 */
static int
install_state(struct ip_fw *rule, ipfw_insn_limit *cmd,
	struct ip_fw_args *args)
{
	static int last_log;

	ipfw_dyn_rule *q;

	DEB(printf("ipfw: install state type %d 0x%08x %u -> 0x%08x %u\n",
	    cmd->o.opcode,
	    (args->f_id.src_ip), (args->f_id.src_port),
	    (args->f_id.dst_ip), (args->f_id.dst_port) );)

	IPFW_DYN_LOCK();

	q = lookup_dyn_rule_locked(&args->f_id, NULL, NULL);

	if (q != NULL) { /* should never occur */
		if (last_log != time_second) {
			last_log = time_second;
			printf("ipfw: install_state: entry already present, done\n");
		}
		IPFW_DYN_UNLOCK();
		return 0;
	}

	if (dyn_count >= dyn_max)
		/*
		 * Run out of slots, try to remove any expired rule.
		 */
		remove_dyn_rule(NULL, (ipfw_dyn_rule *)1);

	if (dyn_count >= dyn_max) {
		if (last_log != time_second) {
			last_log = time_second;
			printf("ipfw: install_state: Too many dynamic rules\n");
		}
		IPFW_DYN_UNLOCK();
		return 1; /* cannot install, notify caller */
	}

	switch (cmd->o.opcode) {
	case O_KEEP_STATE: /* bidir rule */
		add_dyn_rule(&args->f_id, O_KEEP_STATE, rule);
		break;

	case O_LIMIT: /* limit number of sessions */
	    {
		u_int16_t limit_mask = cmd->limit_mask;
		struct ipfw_flow_id id;
		ipfw_dyn_rule *parent;

		DEB(printf("ipfw: installing dyn-limit rule %d\n",
		    cmd->conn_limit);)

		id.dst_ip = id.src_ip = 0;
		id.dst_port = id.src_port = 0;
		id.proto = args->f_id.proto;

		if (limit_mask & DYN_SRC_ADDR)
			id.src_ip = args->f_id.src_ip;
		if (limit_mask & DYN_DST_ADDR)
			id.dst_ip = args->f_id.dst_ip;
		if (limit_mask & DYN_SRC_PORT)
			id.src_port = args->f_id.src_port;
		if (limit_mask & DYN_DST_PORT)
			id.dst_port = args->f_id.dst_port;
		parent = lookup_dyn_parent(&id, rule);
		if (parent == NULL) {
			printf("ipfw: add parent failed\n");
			return 1;
		}
		if (parent->count >= cmd->conn_limit) {
			/*
			 * See if we can remove some expired rule.
			 */
			remove_dyn_rule(rule, parent);
			if (parent->count >= cmd->conn_limit) {
				if (fw_verbose && last_log != time_second) {
					last_log = time_second;
					log(LOG_SECURITY | LOG_DEBUG,
					    "drop session, too many entries\n");
				}
				IPFW_DYN_UNLOCK();
				return 1;
			}
		}
		add_dyn_rule(&args->f_id, O_LIMIT, (struct ip_fw *)parent);
	    }
		break;
	default:
		printf("ipfw: unknown dynamic rule type %u\n", cmd->o.opcode);
		IPFW_DYN_UNLOCK();
		return 1;
	}
	lookup_dyn_rule_locked(&args->f_id, NULL, NULL); /* XXX just set lifetime */
	IPFW_DYN_UNLOCK();
	return 0;
}

/*
 * Transmit a TCP packet, containing either a RST or a keepalive.
 * When flags & TH_RST, we are sending a RST packet, because of a
 * "reset" action matched the packet.
 * Otherwise we are sending a keepalive, and flags & TH_
 */
static void
send_pkt(struct ipfw_flow_id *id, u_int32_t seq, u_int32_t ack, int flags)
{
	struct mbuf *m;
	struct ip *ip;
	struct tcphdr *tcp;

	MGETHDR(m, M_DONTWAIT, MT_HEADER);
	if (m == 0)
		return;
	m->m_pkthdr.rcvif = (struct ifnet *)0;
	m->m_pkthdr.len = m->m_len = sizeof(struct ip) + sizeof(struct tcphdr);
	m->m_data += max_linkhdr;

	ip = mtod(m, struct ip *);
	bzero(ip, m->m_len);
	tcp = (struct tcphdr *)(ip + 1); /* no IP options */
	ip->ip_p = IPPROTO_TCP;
	tcp->th_off = 5;
	/*
	 * Assume we are sending a RST (or a keepalive in the reverse
	 * direction), swap src and destination addresses and ports.
	 */
	ip->ip_src.s_addr = htonl(id->dst_ip);
	ip->ip_dst.s_addr = htonl(id->src_ip);
	tcp->th_sport = htons(id->dst_port);
	tcp->th_dport = htons(id->src_port);
	if (flags & TH_RST) {	/* we are sending a RST */
		if (flags & TH_ACK) {
			tcp->th_seq = htonl(ack);
			tcp->th_ack = htonl(0);
			tcp->th_flags = TH_RST;
		} else {
			if (flags & TH_SYN)
				seq++;
			tcp->th_seq = htonl(0);
			tcp->th_ack = htonl(seq);
			tcp->th_flags = TH_RST | TH_ACK;
		}
	} else {
		/*
		 * We are sending a keepalive. flags & TH_SYN determines
		 * the direction, forward if set, reverse if clear.
		 * NOTE: seq and ack are always assumed to be correct
		 * as set by the caller. This may be confusing...
		 */
		if (flags & TH_SYN) {
			/*
			 * we have to rewrite the correct addresses!
			 */
			ip->ip_dst.s_addr = htonl(id->dst_ip);
			ip->ip_src.s_addr = htonl(id->src_ip);
			tcp->th_dport = htons(id->dst_port);
			tcp->th_sport = htons(id->src_port);
		}
		tcp->th_seq = htonl(seq);
		tcp->th_ack = htonl(ack);
		tcp->th_flags = TH_ACK;
	}
	/*
	 * set ip_len to the payload size so we can compute
	 * the tcp checksum on the pseudoheader
	 * XXX check this, could save a couple of words ?
	 */
	ip->ip_len = htons(sizeof(struct tcphdr));
	tcp->th_sum = in_cksum(m, m->m_pkthdr.len);
	/*
	 * now fill fields left out earlier
	 */
	ip->ip_ttl = ip_defttl;
	ip->ip_len = m->m_pkthdr.len;
	m->m_flags |= M_SKIP_FIREWALL;
	ip_output(m, NULL, NULL, 0, NULL, NULL);
}

/*
 * sends a reject message, consuming the mbuf passed as an argument.
 */
static void
send_reject(struct ip_fw_args *args, int code, int offset, int ip_len)
{

	if (code != ICMP_REJECT_RST) { /* Send an ICMP unreach */
		/* We need the IP header in host order for icmp_error(). */
		if (args->eh != NULL) {
			struct ip *ip = mtod(args->m, struct ip *);
			ip->ip_len = ntohs(ip->ip_len);
			ip->ip_off = ntohs(ip->ip_off);
		}
		icmp_error(args->m, ICMP_UNREACH, code, 0L, 0);
	} else if (offset == 0 && args->f_id.proto == IPPROTO_TCP) {
		struct tcphdr *const tcp =
		    L3HDR(struct tcphdr, mtod(args->m, struct ip *));
		if ( (tcp->th_flags & TH_RST) == 0)
			send_pkt(&(args->f_id), ntohl(tcp->th_seq),
				ntohl(tcp->th_ack),
				tcp->th_flags | TH_RST);
		m_freem(args->m);
	} else
		m_freem(args->m);
	args->m = NULL;
}

/**
 *
 * Given an ip_fw *, lookup_next_rule will return a pointer
 * to the next rule, which can be either the jump
 * target (for skipto instructions) or the next one in the list (in
 * all other cases including a missing jump target).
 * The result is also written in the "next_rule" field of the rule.
 * Backward jumps are not allowed, so start looking from the next
 * rule...
 *
 * This never returns NULL -- in case we do not have an exact match,
 * the next rule is returned. When the ruleset is changed,
 * pointers are flushed so we are always correct.
 */

static struct ip_fw *
lookup_next_rule(struct ip_fw *me)
{
	struct ip_fw *rule = NULL;
	ipfw_insn *cmd;

	/* look for action, in case it is a skipto */
	cmd = ACTION_PTR(me);
	if (cmd->opcode == O_LOG)
		cmd += F_LEN(cmd);
	if (cmd->opcode == O_ALTQ)
		cmd += F_LEN(cmd);
	if ( cmd->opcode == O_SKIPTO )
		for (rule = me->next; rule ; rule = rule->next)
			if (rule->rulenum >= cmd->arg1)
				break;
	if (rule == NULL)			/* failure or not a skipto */
		rule = me->next;
	me->next_rule = rule;
	return rule;
}

static void
init_tables(void)
{
	int i;

	for (i = 0; i < IPFW_TABLES_MAX; i++) {
		rn_inithead((void **)&ipfw_tables[i].rnh, 32);
		ipfw_tables[i].modified = 1;
	}
}

static int
add_table_entry(u_int16_t tbl, in_addr_t addr, u_int8_t mlen, u_int32_t value)
{
	struct radix_node_head *rnh;
	struct table_entry *ent;

	if (tbl >= IPFW_TABLES_MAX)
		return (EINVAL);
	rnh = ipfw_tables[tbl].rnh;
	ent = malloc(sizeof(*ent), M_IPFW_TBL, M_NOWAIT | M_ZERO);
	if (ent == NULL)
		return (ENOMEM);
	ent->value = value;
	ent->addr.sin_len = ent->mask.sin_len = 8;
	ent->mask.sin_addr.s_addr = htonl(mlen ? ~((1 << (32 - mlen)) - 1) : 0);
	ent->addr.sin_addr.s_addr = addr & ent->mask.sin_addr.s_addr;
	RADIX_NODE_HEAD_LOCK(rnh);
	if (rnh->rnh_addaddr(&ent->addr, &ent->mask, rnh, (void *)ent) ==
	    NULL) {
		RADIX_NODE_HEAD_UNLOCK(rnh);
		free(ent, M_IPFW_TBL);
		return (EEXIST);
	}
	ipfw_tables[tbl].modified = 1;
	RADIX_NODE_HEAD_UNLOCK(rnh);
	return (0);
}

static int
del_table_entry(u_int16_t tbl, in_addr_t addr, u_int8_t mlen)
{
	struct radix_node_head *rnh;
	struct table_entry *ent;
	struct sockaddr_in sa, mask;

	if (tbl >= IPFW_TABLES_MAX)
		return (EINVAL);
	rnh = ipfw_tables[tbl].rnh;
	sa.sin_len = mask.sin_len = 8;
	mask.sin_addr.s_addr = htonl(mlen ? ~((1 << (32 - mlen)) - 1) : 0);
	sa.sin_addr.s_addr = addr & mask.sin_addr.s_addr;
	RADIX_NODE_HEAD_LOCK(rnh);
	ent = (struct table_entry *)rnh->rnh_deladdr(&sa, &mask, rnh);
	if (ent == NULL) {
		RADIX_NODE_HEAD_UNLOCK(rnh);
		return (ESRCH);
	}
	ipfw_tables[tbl].modified = 1;
	RADIX_NODE_HEAD_UNLOCK(rnh);
	free(ent, M_IPFW_TBL);
	return (0);
}

static int
flush_table_entry(struct radix_node *rn, void *arg)
{
	struct radix_node_head * const rnh = arg;
	struct table_entry *ent;

	ent = (struct table_entry *)
	    rnh->rnh_deladdr(rn->rn_key, rn->rn_mask, rnh);
	if (ent != NULL)
		free(ent, M_IPFW_TBL);
	return (0);
}

static int
flush_table(u_int16_t tbl)
{
	struct radix_node_head *rnh;

	if (tbl >= IPFW_TABLES_MAX)
		return (EINVAL);
	rnh = ipfw_tables[tbl].rnh;
	RADIX_NODE_HEAD_LOCK(rnh);
	rnh->rnh_walktree(rnh, flush_table_entry, rnh);
	ipfw_tables[tbl].modified = 1;
	RADIX_NODE_HEAD_UNLOCK(rnh);
	return (0);
}

static void
flush_tables(void)
{
	u_int16_t tbl;

	for (tbl = 0; tbl < IPFW_TABLES_MAX; tbl++)
		flush_table(tbl);
}

static int
lookup_table(u_int16_t tbl, in_addr_t addr, u_int32_t *val)
{
	struct radix_node_head *rnh;
	struct table_entry *ent;
	struct sockaddr_in sa;
	static in_addr_t last_addr;
	static int last_tbl;
	static int last_match;
	static u_int32_t last_value;

	if (tbl >= IPFW_TABLES_MAX)
		return (0);
	if (tbl == last_tbl && addr == last_addr &&
	    !ipfw_tables[tbl].modified) {
		if (last_match)
			*val = last_value;
		return (last_match);
	}
	rnh = ipfw_tables[tbl].rnh;
	sa.sin_len = 8;
	sa.sin_addr.s_addr = addr;
	RADIX_NODE_HEAD_LOCK(rnh);
	ipfw_tables[tbl].modified = 0;
	ent = (struct table_entry *)(rnh->rnh_lookup(&sa, NULL, rnh));
	RADIX_NODE_HEAD_UNLOCK(rnh);
	last_addr = addr;
	last_tbl = tbl;
	if (ent != NULL) {
		last_value = *val = ent->value;
		last_match = 1;
		return (1);
	}
	last_match = 0;
	return (0);
}

static int
count_table_entry(struct radix_node *rn, void *arg)
{
	u_int32_t * const cnt = arg;

	(*cnt)++;
	return (0);
}

static int
count_table(u_int32_t tbl, u_int32_t *cnt)
{
	struct radix_node_head *rnh;

	if (tbl >= IPFW_TABLES_MAX)
		return (EINVAL);
	rnh = ipfw_tables[tbl].rnh;
	*cnt = 0;
	RADIX_NODE_HEAD_LOCK(rnh);
	rnh->rnh_walktree(rnh, count_table_entry, cnt);
	RADIX_NODE_HEAD_UNLOCK(rnh);
	return (0);
}

static int
dump_table_entry(struct radix_node *rn, void *arg)
{
	struct table_entry * const n = (struct table_entry *)rn;
	ipfw_table * const tbl = arg;
	ipfw_table_entry *ent;

	if (tbl->cnt == tbl->size)
		return (1);
	ent = &tbl->ent[tbl->cnt];
	ent->tbl = tbl->tbl;
	if (in_nullhost(n->mask.sin_addr))
		ent->masklen = 0;
	else
		ent->masklen = 33 - ffs(ntohl(n->mask.sin_addr.s_addr));
	ent->addr = n->addr.sin_addr.s_addr;
	ent->value = n->value;
	tbl->cnt++;
	return (0);
}

static int
dump_table(ipfw_table *tbl)
{
	struct radix_node_head *rnh;

	if (tbl->tbl >= IPFW_TABLES_MAX)
		return (EINVAL);
	rnh = ipfw_tables[tbl->tbl].rnh;
	tbl->cnt = 0;
	RADIX_NODE_HEAD_LOCK(rnh);
	rnh->rnh_walktree(rnh, dump_table_entry, tbl);
	RADIX_NODE_HEAD_UNLOCK(rnh);
	return (0);
}

static void
fill_ugid_cache(struct inpcb *inp, struct ip_fw_ugid *ugp)
{
	struct ucred *cr;

	if (inp->inp_socket != NULL) {
		cr = inp->inp_socket->so_cred;
		ugp->fw_prid = jailed(cr) ?
		    cr->cr_prison->pr_id : -1;
		ugp->fw_uid = cr->cr_uid;
		ugp->fw_ngroups = cr->cr_ngroups;
		bcopy(cr->cr_groups, ugp->fw_groups,
		    sizeof(ugp->fw_groups));
	}
}

static int
check_uidgid(ipfw_insn_u32 *insn,
	int proto, struct ifnet *oif,
	struct in_addr dst_ip, u_int16_t dst_port,
	struct in_addr src_ip, u_int16_t src_port,
	struct ip_fw_ugid *ugp, int *lookup, struct inpcb *inp)
{
	struct inpcbinfo *pi;
	int wildcard;
	struct inpcb *pcb;
	int match;
	gid_t *gp;

	/*
	 * Check to see if the UDP or TCP stack supplied us with
	 * the PCB. If so, rather then holding a lock and looking
	 * up the PCB, we can use the one that was supplied.
	 */
	if (inp && *lookup == 0) {
		INP_LOCK_ASSERT(inp);
		if (inp->inp_socket != NULL) {
			fill_ugid_cache(inp, ugp);
			*lookup = 1;
		}
	}
	/*
	 * If we have already been here and the packet has no
	 * PCB entry associated with it, then we can safely
	 * assume that this is a no match.
	 */
	if (*lookup == -1)
		return (0);
	if (proto == IPPROTO_TCP) {
		wildcard = 0;
		pi = &tcbinfo;
	} else if (proto == IPPROTO_UDP) {
		wildcard = 1;
		pi = &udbinfo;
	} else
		return 0;
	match = 0;
	if (*lookup == 0) {
		INP_INFO_RLOCK(pi);
		pcb =  (oif) ?
			in_pcblookup_hash(pi,
				dst_ip, htons(dst_port),
				src_ip, htons(src_port),
				wildcard, oif) :
			in_pcblookup_hash(pi,
				src_ip, htons(src_port),
				dst_ip, htons(dst_port),
				wildcard, NULL);
		if (pcb != NULL) {
			INP_LOCK(pcb);
			if (pcb->inp_socket != NULL) {
				fill_ugid_cache(pcb, ugp);
				*lookup = 1;
			}
			INP_UNLOCK(pcb);
		}
		INP_INFO_RUNLOCK(pi);
		if (*lookup == 0) {
			/*
			 * If the lookup did not yield any results, there
			 * is no sense in coming back and trying again. So
			 * we can set lookup to -1 and ensure that we wont
			 * bother the pcb system again.
			 */
			*lookup = -1;
			return (0);
		}
	} 
	if (insn->o.opcode == O_UID)
		match = (ugp->fw_uid == (uid_t)insn->d[0]);
	else if (insn->o.opcode == O_GID) {
		for (gp = ugp->fw_groups;
			gp < &ugp->fw_groups[ugp->fw_ngroups]; gp++)
			if (*gp == (gid_t)insn->d[0]) {
				match = 1;
				break;
			}
	} else if (insn->o.opcode == O_JAIL)
		match = (ugp->fw_prid == (int)insn->d[0]);
	return match;
}

/*
 * The main check routine for the firewall.
 *
 * All arguments are in args so we can modify them and return them
 * back to the caller.
 *
 * Parameters:
 *
 *	args->m	(in/out) The packet; we set to NULL when/if we nuke it.
 *		Starts with the IP header.
 *	args->eh (in)	Mac header if present, or NULL for layer3 packet.
 *	args->oif	Outgoing interface, or NULL if packet is incoming.
 *		The incoming interface is in the mbuf. (in)
 *	args->divert_rule (in/out)
 *		Skip up to the first rule past this rule number;
 *		upon return, non-zero port number for divert or tee.
 *
 *	args->rule	Pointer to the last matching rule (in/out)
 *	args->next_hop	Socket we are forwarding to (out).
 *	args->f_id	Addresses grabbed from the packet (out)
 * 	args->cookie	a cookie depending on rule action
 *
 * Return value:
 *
 *	IP_FW_PASS	the packet must be accepted
 *	IP_FW_DENY	the packet must be dropped
 *	IP_FW_DIVERT	divert packet, port in m_tag
 *	IP_FW_TEE	tee packet, port in m_tag
 *	IP_FW_DUMMYNET	to dummynet, pipe in args->cookie
 *	IP_FW_NETGRAPH	into netgraph, cookie args->cookie
 *
 */

int
ipfw_chk(struct ip_fw_args *args)
{
	/*
	 * Local variables hold state during the processing of a packet.
	 *
	 * IMPORTANT NOTE: to speed up the processing of rules, there
	 * are some assumption on the values of the variables, which
	 * are documented here. Should you change them, please check
	 * the implementation of the various instructions to make sure
	 * that they still work.
	 *
	 * args->eh	The MAC header. It is non-null for a layer2
	 *	packet, it is NULL for a layer-3 packet.
	 *
	 * m | args->m	Pointer to the mbuf, as received from the caller.
	 *	It may change if ipfw_chk() does an m_pullup, or if it
	 *	consumes the packet because it calls send_reject().
	 *	XXX This has to change, so that ipfw_chk() never modifies
	 *	or consumes the buffer.
	 * ip	is simply an alias of the value of m, and it is kept
	 *	in sync with it (the packet is	supposed to start with
	 *	the ip header).
	 */
	struct mbuf *m = args->m;
	struct ip *ip = mtod(m, struct ip *);

	/*
	 * For rules which contain uid/gid or jail constraints, cache
	 * a copy of the users credentials after the pcb lookup has been
	 * executed. This will speed up the processing of rules with
	 * these types of constraints, as well as decrease contention
	 * on pcb related locks.
	 */
	struct ip_fw_ugid fw_ugid_cache;
	int ugid_lookup = 0;

	/*
	 * divinput_flags	If non-zero, set to the IP_FW_DIVERT_*_FLAG
	 *	associated with a packet input on a divert socket.  This
	 *	will allow to distinguish traffic and its direction when
	 *	it originates from a divert socket.
	 */
	u_int divinput_flags = 0;

	/*
	 * oif | args->oif	If NULL, ipfw_chk has been called on the
	 *	inbound path (ether_input, bdg_forward, ip_input).
	 *	If non-NULL, ipfw_chk has been called on the outbound path
	 *	(ether_output, ip_output).
	 */
	struct ifnet *oif = args->oif;

	struct ip_fw *f = NULL;		/* matching rule */
	int retval = 0;

	/*
	 * hlen	The length of the IPv4 header.
	 *	hlen >0 means we have an IPv4 packet.
	 */
	u_int hlen = 0;		/* hlen >0 means we have an IP pkt */

	/*
	 * offset	The offset of a fragment. offset != 0 means that
	 *	we have a fragment at this offset of an IPv4 packet.
	 *	offset == 0 means that (if this is an IPv4 packet)
	 *	this is the first or only fragment.
	 */
	u_short offset = 0;

	/*
	 * Local copies of addresses. They are only valid if we have
	 * an IP packet.
	 *
	 * proto	The protocol. Set to 0 for non-ip packets,
	 *	or to the protocol read from the packet otherwise.
	 *	proto != 0 means that we have an IPv4 packet.
	 *
	 * src_port, dst_port	port numbers, in HOST format. Only
	 *	valid for TCP and UDP packets.
	 *
	 * src_ip, dst_ip	ip addresses, in NETWORK format.
	 *	Only valid for IPv4 packets.
	 */
	u_int8_t proto;
	u_int16_t src_port = 0, dst_port = 0;	/* NOTE: host format	*/
	struct in_addr src_ip, dst_ip;		/* NOTE: network format	*/
	u_int16_t ip_len=0;
	int pktlen;
	int dyn_dir = MATCH_UNKNOWN;
	ipfw_dyn_rule *q = NULL;
	struct ip_fw_chain *chain = &layer3_chain;
	struct m_tag *mtag;

	if (m->m_flags & M_SKIP_FIREWALL)
		return (IP_FW_PASS);	/* accept */
	/*
	 * dyn_dir = MATCH_UNKNOWN when rules unchecked,
	 * 	MATCH_NONE when checked and not matched (q = NULL),
	 *	MATCH_FORWARD or MATCH_REVERSE otherwise (q != NULL)
	 */

	pktlen = m->m_pkthdr.len;
	if (args->eh == NULL ||		/* layer 3 packet */
		( m->m_pkthdr.len >= sizeof(struct ip) &&
		    ntohs(args->eh->ether_type) == ETHERTYPE_IP))
			hlen = ip->ip_hl << 2;

	/*
	 * Collect parameters into local variables for faster matching.
	 */
	if (hlen == 0) {	/* do not grab addresses for non-ip pkts */
		proto = args->f_id.proto = 0;	/* mark f_id invalid */
		goto after_ip_checks;
	}

	proto = args->f_id.proto = ip->ip_p;
	src_ip = ip->ip_src;
	dst_ip = ip->ip_dst;
	if (args->eh != NULL) { /* layer 2 packets are as on the wire */
		offset = ntohs(ip->ip_off) & IP_OFFMASK;
		ip_len = ntohs(ip->ip_len);
	} else {
		offset = ip->ip_off & IP_OFFMASK;
		ip_len = ip->ip_len;
	}
	pktlen = ip_len < pktlen ? ip_len : pktlen;

#define PULLUP_TO(len)						\
		do {						\
			if ((m)->m_len < (len)) {		\
			    args->m = m = m_pullup(m, (len));	\
			    if (m == 0)				\
				goto pullup_failed;		\
			    ip = mtod(m, struct ip *);		\
			}					\
		} while (0)

	if (offset == 0) {
		switch (proto) {
		case IPPROTO_TCP:
		    {
			struct tcphdr *tcp;

			PULLUP_TO(hlen + sizeof(struct tcphdr));
			tcp = L3HDR(struct tcphdr, ip);
			dst_port = tcp->th_dport;
			src_port = tcp->th_sport;
			args->f_id.flags = tcp->th_flags;
			}
			break;

		case IPPROTO_UDP:
		    {
			struct udphdr *udp;

			PULLUP_TO(hlen + sizeof(struct udphdr));
			udp = L3HDR(struct udphdr, ip);
			dst_port = udp->uh_dport;
			src_port = udp->uh_sport;
			}
			break;

		case IPPROTO_ICMP:
			PULLUP_TO(hlen + 4);	/* type, code and checksum. */
			args->f_id.flags = L3HDR(struct icmp, ip)->icmp_type;
			break;

		default:
			break;
		}
#undef PULLUP_TO
	}

	args->f_id.src_ip = ntohl(src_ip.s_addr);
	args->f_id.dst_ip = ntohl(dst_ip.s_addr);
	args->f_id.src_port = src_port = ntohs(src_port);
	args->f_id.dst_port = dst_port = ntohs(dst_port);

after_ip_checks:
	IPFW_RLOCK(chain);
	mtag = m_tag_find(m, PACKET_TAG_DIVERT, NULL);
	if (args->rule) {
		/*
		 * Packet has already been tagged. Look for the next rule
		 * to restart processing.
		 *
		 * If fw_one_pass != 0 then just accept it.
		 * XXX should not happen here, but optimized out in
		 * the caller.
		 */
		if (fw_one_pass) {
			IPFW_RUNLOCK(chain);
			return (IP_FW_PASS);
		}

		f = args->rule->next_rule;
		if (f == NULL)
			f = lookup_next_rule(args->rule);
	} else {
		/*
		 * Find the starting rule. It can be either the first
		 * one, or the one after divert_rule if asked so.
		 */
		int skipto = mtag ? divert_cookie(mtag) : 0;

		f = chain->rules;
		if (args->eh == NULL && skipto != 0) {
			if (skipto >= IPFW_DEFAULT_RULE) {
				IPFW_RUNLOCK(chain);
				return (IP_FW_DENY); /* invalid */
			}
			while (f && f->rulenum <= skipto)
				f = f->next;
			if (f == NULL) {	/* drop packet */
				IPFW_RUNLOCK(chain);
				return (IP_FW_DENY);
			}
		}
	}
	/* reset divert rule to avoid confusion later */
	if (mtag) {
		divinput_flags = divert_info(mtag) &
		    (IP_FW_DIVERT_OUTPUT_FLAG | IP_FW_DIVERT_LOOPBACK_FLAG);
		m_tag_delete(m, mtag);
	}

	/*
	 * Now scan the rules, and parse microinstructions for each rule.
	 */
	for (; f; f = f->next) {
		int l, cmdlen;
		ipfw_insn *cmd;
		int skip_or; /* skip rest of OR block */

again:
		if (set_disable & (1 << f->set) )
			continue;

		skip_or = 0;
		for (l = f->cmd_len, cmd = f->cmd ; l > 0 ;
		    l -= cmdlen, cmd += cmdlen) {
			int match;

			/*
			 * check_body is a jump target used when we find a
			 * CHECK_STATE, and need to jump to the body of
			 * the target rule.
			 */

check_body:
			cmdlen = F_LEN(cmd);
			/*
			 * An OR block (insn_1 || .. || insn_n) has the
			 * F_OR bit set in all but the last instruction.
			 * The first match will set "skip_or", and cause
			 * the following instructions to be skipped until
			 * past the one with the F_OR bit clear.
			 */
			if (skip_or) {		/* skip this instruction */
				if ((cmd->len & F_OR) == 0)
					skip_or = 0;	/* next one is good */
				continue;
			}
			match = 0; /* set to 1 if we succeed */

			switch (cmd->opcode) {
			/*
			 * The first set of opcodes compares the packet's
			 * fields with some pattern, setting 'match' if a
			 * match is found. At the end of the loop there is
			 * logic to deal with F_NOT and F_OR flags associated
			 * with the opcode.
			 */
			case O_NOP:
				match = 1;
				break;

			case O_FORWARD_MAC:
				printf("ipfw: opcode %d unimplemented\n",
				    cmd->opcode);
				break;

			case O_GID:
			case O_UID:
			case O_JAIL:
				/*
				 * We only check offset == 0 && proto != 0,
				 * as this ensures that we have an IPv4
				 * packet with the ports info.
				 */
				if (offset!=0)
					break;
				if (proto == IPPROTO_TCP ||
				    proto == IPPROTO_UDP)
					match = check_uidgid(
						    (ipfw_insn_u32 *)cmd,
						    proto, oif,
						    dst_ip, dst_port,
						    src_ip, src_port, &fw_ugid_cache,
						    &ugid_lookup, args->inp);
				break;

			case O_RECV:
				match = iface_match(m->m_pkthdr.rcvif,
				    (ipfw_insn_if *)cmd);
				break;

			case O_XMIT:
				match = iface_match(oif, (ipfw_insn_if *)cmd);
				break;

			case O_VIA:
				match = iface_match(oif ? oif :
				    m->m_pkthdr.rcvif, (ipfw_insn_if *)cmd);
				break;

			case O_MACADDR2:
				if (args->eh != NULL) {	/* have MAC header */
					u_int32_t *want = (u_int32_t *)
						((ipfw_insn_mac *)cmd)->addr;
					u_int32_t *mask = (u_int32_t *)
						((ipfw_insn_mac *)cmd)->mask;
					u_int32_t *hdr = (u_int32_t *)args->eh;

					match =
					    ( want[0] == (hdr[0] & mask[0]) &&
					      want[1] == (hdr[1] & mask[1]) &&
					      want[2] == (hdr[2] & mask[2]) );
				}
				break;

			case O_MAC_TYPE:
				if (args->eh != NULL) {
					u_int16_t t =
					    ntohs(args->eh->ether_type);
					u_int16_t *p =
					    ((ipfw_insn_u16 *)cmd)->ports;
					int i;

					for (i = cmdlen - 1; !match && i>0;
					    i--, p += 2)
						match = (t>=p[0] && t<=p[1]);
				}
				break;

			case O_FRAG:
				match = (hlen > 0 && offset != 0);
				break;

			case O_IN:	/* "out" is "not in" */
				match = (oif == NULL);
				break;

			case O_LAYER2:
				match = (args->eh != NULL);
				break;

			case O_DIVERTED:
				match = (cmd->arg1 & 1 && divinput_flags &
				    IP_FW_DIVERT_LOOPBACK_FLAG) ||
					(cmd->arg1 & 2 && divinput_flags &
				    IP_FW_DIVERT_OUTPUT_FLAG);
				break;

			case O_PROTO:
				/*
				 * We do not allow an arg of 0 so the
				 * check of "proto" only suffices.
				 */
				match = (proto == cmd->arg1);
				break;

			case O_IP_SRC:
				match = (hlen > 0 &&
				    ((ipfw_insn_ip *)cmd)->addr.s_addr ==
				    src_ip.s_addr);
				break;

			case O_IP_SRC_LOOKUP:
			case O_IP_DST_LOOKUP:
				if (hlen > 0) {
				    uint32_t a =
					(cmd->opcode == O_IP_DST_LOOKUP) ?
					    dst_ip.s_addr : src_ip.s_addr;
				    uint32_t v;

				    match = lookup_table(cmd->arg1, a, &v);
				    if (!match)
					break;
				    if (cmdlen == F_INSN_SIZE(ipfw_insn_u32))
					match =
					    ((ipfw_insn_u32 *)cmd)->d[0] == v;
				}
				break;

			case O_IP_SRC_MASK:
			case O_IP_DST_MASK:
				if (hlen > 0) {
				    uint32_t a =
					(cmd->opcode == O_IP_DST_MASK) ?
					    dst_ip.s_addr : src_ip.s_addr;
				    uint32_t *p = ((ipfw_insn_u32 *)cmd)->d;
				    int i = cmdlen-1;

				    for (; !match && i>0; i-= 2, p+= 2)
					match = (p[0] == (a & p[1]));
				}
				break;

			case O_IP_SRC_ME:
				if (hlen > 0) {
					struct ifnet *tif;

					INADDR_TO_IFP(src_ip, tif);
					match = (tif != NULL);
				}
				break;

			case O_IP_DST_SET:
			case O_IP_SRC_SET:
				if (hlen > 0) {
					u_int32_t *d = (u_int32_t *)(cmd+1);
					u_int32_t addr =
					    cmd->opcode == O_IP_DST_SET ?
						args->f_id.dst_ip :
						args->f_id.src_ip;

					    if (addr < d[0])
						    break;
					    addr -= d[0]; /* subtract base */
					    match = (addr < cmd->arg1) &&
						( d[ 1 + (addr>>5)] &
						  (1<<(addr & 0x1f)) );
				}
				break;

			case O_IP_DST:
				match = (hlen > 0 &&
				    ((ipfw_insn_ip *)cmd)->addr.s_addr ==
				    dst_ip.s_addr);
				break;

			case O_IP_DST_ME:
				if (hlen > 0) {
					struct ifnet *tif;

					INADDR_TO_IFP(dst_ip, tif);
					match = (tif != NULL);
				}
				break;

			case O_IP_SRCPORT:
			case O_IP_DSTPORT:
				/*
				 * offset == 0 && proto != 0 is enough
				 * to guarantee that we have an IPv4
				 * packet with port info.
				 */
				if ((proto==IPPROTO_UDP || proto==IPPROTO_TCP)
				    && offset == 0) {
					u_int16_t x =
					    (cmd->opcode == O_IP_SRCPORT) ?
						src_port : dst_port ;
					u_int16_t *p =
					    ((ipfw_insn_u16 *)cmd)->ports;
					int i;

					for (i = cmdlen - 1; !match && i>0;
					    i--, p += 2)
						match = (x>=p[0] && x<=p[1]);
				}
				break;

			case O_ICMPTYPE:
				match = (offset == 0 && proto==IPPROTO_ICMP &&
				    icmptype_match(ip, (ipfw_insn_u32 *)cmd) );
				break;

			case O_IPOPT:
				match = (hlen > 0 && ipopts_match(ip, cmd) );
				break;

			case O_IPVER:
				match = (hlen > 0 && cmd->arg1 == ip->ip_v);
				break;

			case O_IPID:
			case O_IPLEN:
			case O_IPTTL:
				if (hlen > 0) {	/* only for IP packets */
				    uint16_t x;
				    uint16_t *p;
				    int i;

				    if (cmd->opcode == O_IPLEN)
					x = ip_len;
				    else if (cmd->opcode == O_IPTTL)
					x = ip->ip_ttl;
				    else /* must be IPID */
					x = ntohs(ip->ip_id);
				    if (cmdlen == 1) {
					match = (cmd->arg1 == x);
					break;
				    }
				    /* otherwise we have ranges */
				    p = ((ipfw_insn_u16 *)cmd)->ports;
				    i = cmdlen - 1;
				    for (; !match && i>0; i--, p += 2)
					match = (x >= p[0] && x <= p[1]);
				}
				break;

			case O_IPPRECEDENCE:
				match = (hlen > 0 &&
				    (cmd->arg1 == (ip->ip_tos & 0xe0)) );
				break;

			case O_IPTOS:
				match = (hlen > 0 &&
				    flags_match(cmd, ip->ip_tos));
				break;

			case O_TCPDATALEN:
				if (proto == IPPROTO_TCP && offset == 0) {
				    struct tcphdr *tcp;
				    uint16_t x;
				    uint16_t *p;
				    int i;

				    tcp = L3HDR(struct tcphdr,ip);
				    x = ip_len -
					((ip->ip_hl + tcp->th_off) << 2);
				    if (cmdlen == 1) {
					match = (cmd->arg1 == x);
					break;
				    }
				    /* otherwise we have ranges */
				    p = ((ipfw_insn_u16 *)cmd)->ports;
				    i = cmdlen - 1;
				    for (; !match && i>0; i--, p += 2)
					match = (x >= p[0] && x <= p[1]);
				}
				break;

			case O_TCPFLAGS:
				match = (proto == IPPROTO_TCP && offset == 0 &&
				    flags_match(cmd,
					L3HDR(struct tcphdr,ip)->th_flags));
				break;

			case O_TCPOPTS:
				match = (proto == IPPROTO_TCP && offset == 0 &&
				    tcpopts_match(ip, cmd));
				break;

			case O_TCPSEQ:
				match = (proto == IPPROTO_TCP && offset == 0 &&
				    ((ipfw_insn_u32 *)cmd)->d[0] ==
					L3HDR(struct tcphdr,ip)->th_seq);
				break;

			case O_TCPACK:
				match = (proto == IPPROTO_TCP && offset == 0 &&
				    ((ipfw_insn_u32 *)cmd)->d[0] ==
					L3HDR(struct tcphdr,ip)->th_ack);
				break;

			case O_TCPWIN:
				match = (proto == IPPROTO_TCP && offset == 0 &&
				    cmd->arg1 ==
					L3HDR(struct tcphdr,ip)->th_win);
				break;

			case O_ESTAB:
				/* reject packets which have SYN only */
				/* XXX should i also check for TH_ACK ? */
				match = (proto == IPPROTO_TCP && offset == 0 &&
				    (L3HDR(struct tcphdr,ip)->th_flags &
				     (TH_RST | TH_ACK | TH_SYN)) != TH_SYN);
				break;

			case O_ALTQ: {
				struct altq_tag *at;
				ipfw_insn_altq *altq = (ipfw_insn_altq *)cmd;

				match = 1;
				mtag = m_tag_get(PACKET_TAG_PF_QID,
						sizeof(struct altq_tag),
						M_NOWAIT);
				if (mtag == NULL) {
					/*
					 * Let the packet fall back to the
					 * default ALTQ.
					 */
					break;
				}
				at = (struct altq_tag *)(mtag+1);
				at->qid = altq->qid;
				if (hlen != 0)
					at->af = AF_INET;
				else
					at->af = AF_LINK;
				at->hdr = ip;
				m_tag_prepend(m, mtag);
				break;
			}

			case O_LOG:
				if (fw_verbose)
					ipfw_log(f, hlen, args->eh, m, oif);
				match = 1;
				break;

			case O_PROB:
				match = (random()<((ipfw_insn_u32 *)cmd)->d[0]);
				break;

			case O_VERREVPATH:
				/* Outgoing packets automatically pass/match */
				match = (hlen > 0 && ((oif != NULL) ||
				    (m->m_pkthdr.rcvif == NULL) ||
				    verify_path(src_ip, m->m_pkthdr.rcvif)));
				break;

			case O_VERSRCREACH:
				/* Outgoing packets automatically pass/match */
				match = (hlen > 0 && ((oif != NULL) ||
				     verify_path(src_ip, NULL)));
				break;

			case O_ANTISPOOF:
				/* Outgoing packets automatically pass/match */
				if (oif == NULL && hlen > 0 &&
				    in_localaddr(src_ip))
					match = verify_path(src_ip,
							m->m_pkthdr.rcvif);
				else
					match = 1;
				break;

			case O_IPSEC:
#ifdef FAST_IPSEC
				match = (m_tag_find(m,
				    PACKET_TAG_IPSEC_IN_DONE, NULL) != NULL);
#endif
#ifdef IPSEC
				match = (ipsec_getnhist(m) != 0);
#endif
				/* otherwise no match */
				break;

			/*
			 * The second set of opcodes represents 'actions',
			 * i.e. the terminal part of a rule once the packet
			 * matches all previous patterns.
			 * Typically there is only one action for each rule,
			 * and the opcode is stored at the end of the rule
			 * (but there are exceptions -- see below).
			 *
			 * In general, here we set retval and terminate the
			 * outer loop (would be a 'break 3' in some language,
			 * but we need to do a 'goto done').
			 *
			 * Exceptions:
			 * O_COUNT and O_SKIPTO actions:
			 *   instead of terminating, we jump to the next rule
			 *   ('goto next_rule', equivalent to a 'break 2'),
			 *   or to the SKIPTO target ('goto again' after
			 *   having set f, cmd and l), respectively.
			 *
			 * O_LOG and O_ALTQ action parameters:
			 *   perform some action and set match = 1;
			 *
			 * O_LIMIT and O_KEEP_STATE: these opcodes are
			 *   not real 'actions', and are stored right
			 *   before the 'action' part of the rule.
			 *   These opcodes try to install an entry in the
			 *   state tables; if successful, we continue with
			 *   the next opcode (match=1; break;), otherwise
			 *   the packet *   must be dropped
			 *   ('goto done' after setting retval);
			 *
			 * O_PROBE_STATE and O_CHECK_STATE: these opcodes
			 *   cause a lookup of the state table, and a jump
			 *   to the 'action' part of the parent rule
			 *   ('goto check_body') if an entry is found, or
			 *   (CHECK_STATE only) a jump to the next rule if
			 *   the entry is not found ('goto next_rule').
			 *   The result of the lookup is cached to make
			 *   further instances of these opcodes are
			 *   effectively NOPs.
			 */
			case O_LIMIT:
			case O_KEEP_STATE:
				if (install_state(f,
				    (ipfw_insn_limit *)cmd, args)) {
					retval = IP_FW_DENY;
					goto done; /* error/limit violation */
				}
				match = 1;
				break;

			case O_PROBE_STATE:
			case O_CHECK_STATE:
				/*
				 * dynamic rules are checked at the first
				 * keep-state or check-state occurrence,
				 * with the result being stored in dyn_dir.
				 * The compiler introduces a PROBE_STATE
				 * instruction for us when we have a
				 * KEEP_STATE (because PROBE_STATE needs
				 * to be run first).
				 */
				if (dyn_dir == MATCH_UNKNOWN &&
				    (q = lookup_dyn_rule(&args->f_id,
				     &dyn_dir, proto == IPPROTO_TCP ?
					L3HDR(struct tcphdr, ip) : NULL))
					!= NULL) {
					/*
					 * Found dynamic entry, update stats
					 * and jump to the 'action' part of
					 * the parent rule.
					 */
					q->pcnt++;
					q->bcnt += pktlen;
					f = q->rule;
					cmd = ACTION_PTR(f);
					l = f->cmd_len - f->act_ofs;
					IPFW_DYN_UNLOCK();
					goto check_body;
				}
				/*
				 * Dynamic entry not found. If CHECK_STATE,
				 * skip to next rule, if PROBE_STATE just
				 * ignore and continue with next opcode.
				 */
				if (cmd->opcode == O_CHECK_STATE)
					goto next_rule;
				match = 1;
				break;

			case O_ACCEPT:
				retval = 0;	/* accept */
				goto done;

			case O_PIPE:
			case O_QUEUE:
				args->rule = f; /* report matching rule */
				args->cookie = cmd->arg1;
				retval = IP_FW_DUMMYNET;
				goto done;

			case O_DIVERT:
			case O_TEE: {
				struct divert_tag *dt;

				if (args->eh) /* not on layer 2 */
					break;
				mtag = m_tag_get(PACKET_TAG_DIVERT,
						sizeof(struct divert_tag),
						M_NOWAIT);
				if (mtag == NULL) {
					/* XXX statistic */
					/* drop packet */
					IPFW_RUNLOCK(chain);
					return (IP_FW_DENY);
				}
				dt = (struct divert_tag *)(mtag+1);
				dt->cookie = f->rulenum;
				dt->info = cmd->arg1;
				m_tag_prepend(m, mtag);
				retval = (cmd->opcode == O_DIVERT) ?
				    IP_FW_DIVERT : IP_FW_TEE;
				goto done;
			}

			case O_COUNT:
			case O_SKIPTO:
				f->pcnt++;	/* update stats */
				f->bcnt += pktlen;
				f->timestamp = time_second;
				if (cmd->opcode == O_COUNT)
					goto next_rule;
				/* handle skipto */
				if (f->next_rule == NULL)
					lookup_next_rule(f);
				f = f->next_rule;
				goto again;

			case O_REJECT:
				/*
				 * Drop the packet and send a reject notice
				 * if the packet is not ICMP (or is an ICMP
				 * query), and it is not multicast/broadcast.
				 */
				if (hlen > 0 &&
				    (proto != IPPROTO_ICMP ||
				     is_icmp_query(ip)) &&
				    !(m->m_flags & (M_BCAST|M_MCAST)) &&
				    !IN_MULTICAST(ntohl(dst_ip.s_addr))) {
					send_reject(args, cmd->arg1,
					    offset,ip_len);
					m = args->m;
				}
				/* FALLTHROUGH */
			case O_DENY:
				retval = IP_FW_DENY;
				goto done;

			case O_FORWARD_IP:
				if (args->eh)	/* not valid on layer2 pkts */
					break;
				if (!q || dyn_dir == MATCH_FORWARD)
					args->next_hop =
					    &((ipfw_insn_sa *)cmd)->sa;
				retval = IP_FW_PASS;
				goto done;

			case O_NETGRAPH:
			case O_NGTEE:
				args->rule = f;	/* report matching rule */
				args->cookie = cmd->arg1;
				retval = (cmd->opcode == O_NETGRAPH) ?
				    IP_FW_NETGRAPH : IP_FW_NGTEE;
				goto done;

			default:
				panic("-- unknown opcode %d\n", cmd->opcode);
			} /* end of switch() on opcodes */

			if (cmd->len & F_NOT)
				match = !match;

			if (match) {
				if (cmd->len & F_OR)
					skip_or = 1;
			} else {
				if (!(cmd->len & F_OR)) /* not an OR block, */
					break;		/* try next rule    */
			}

		}	/* end of inner for, scan opcodes */

next_rule:;		/* try next rule		*/

	}		/* end of outer for, scan rules */
	printf("ipfw: ouch!, skip past end of rules, denying packet\n");
	IPFW_RUNLOCK(chain);
	return (IP_FW_DENY);

done:
	/* Update statistics */
	f->pcnt++;
	f->bcnt += pktlen;
	f->timestamp = time_second;
	IPFW_RUNLOCK(chain);
	return (retval);

pullup_failed:
	if (fw_verbose)
		printf("ipfw: pullup failed\n");
	return (IP_FW_DENY);
}

/*
 * When a rule is added/deleted, clear the next_rule pointers in all rules.
 * These will be reconstructed on the fly as packets are matched.
 */
static void
flush_rule_ptrs(struct ip_fw_chain *chain)
{
	struct ip_fw *rule;

	IPFW_WLOCK_ASSERT(chain);

	for (rule = chain->rules; rule; rule = rule->next)
		rule->next_rule = NULL;
}

/*
 * When pipes/queues are deleted, clear the "pipe_ptr" pointer to a given
 * pipe/queue, or to all of them (match == NULL).
 */
void
flush_pipe_ptrs(struct dn_flow_set *match)
{
	struct ip_fw *rule;

	IPFW_WLOCK(&layer3_chain);
	for (rule = layer3_chain.rules; rule; rule = rule->next) {
		ipfw_insn_pipe *cmd = (ipfw_insn_pipe *)ACTION_PTR(rule);

		if (cmd->o.opcode != O_PIPE && cmd->o.opcode != O_QUEUE)
			continue;
		/*
		 * XXX Use bcmp/bzero to handle pipe_ptr to overcome
		 * possible alignment problems on 64-bit architectures.
		 * This code is seldom used so we do not worry too
		 * much about efficiency.
		 */
		if (match == NULL ||
		    !bcmp(&cmd->pipe_ptr, &match, sizeof(match)) )
			bzero(&cmd->pipe_ptr, sizeof(cmd->pipe_ptr));
	}
	IPFW_WUNLOCK(&layer3_chain);
}

/*
 * Add a new rule to the list. Copy the rule into a malloc'ed area, then
 * possibly create a rule number and add the rule to the list.
 * Update the rule_number in the input struct so the caller knows it as well.
 */
static int
add_rule(struct ip_fw_chain *chain, struct ip_fw *input_rule)
{
	struct ip_fw *rule, *f, *prev;
	int l = RULESIZE(input_rule);

	if (chain->rules == NULL && input_rule->rulenum != IPFW_DEFAULT_RULE)
		return (EINVAL);

	rule = malloc(l, M_IPFW, M_NOWAIT | M_ZERO);
	if (rule == NULL)
		return (ENOSPC);

	bcopy(input_rule, rule, l);

	rule->next = NULL;
	rule->next_rule = NULL;

	rule->pcnt = 0;
	rule->bcnt = 0;
	rule->timestamp = 0;

	IPFW_WLOCK(chain);

	if (chain->rules == NULL) {	/* default rule */
		chain->rules = rule;
		goto done;
        }

	/*
	 * If rulenum is 0, find highest numbered rule before the
	 * default rule, and add autoinc_step
	 */
	if (autoinc_step < 1)
		autoinc_step = 1;
	else if (autoinc_step > 1000)
		autoinc_step = 1000;
	if (rule->rulenum == 0) {
		/*
		 * locate the highest numbered rule before default
		 */
		for (f = chain->rules; f; f = f->next) {
			if (f->rulenum == IPFW_DEFAULT_RULE)
				break;
			rule->rulenum = f->rulenum;
		}
		if (rule->rulenum < IPFW_DEFAULT_RULE - autoinc_step)
			rule->rulenum += autoinc_step;
		input_rule->rulenum = rule->rulenum;
	}

	/*
	 * Now insert the new rule in the right place in the sorted list.
	 */
	for (prev = NULL, f = chain->rules; f; prev = f, f = f->next) {
		if (f->rulenum > rule->rulenum) { /* found the location */
			if (prev) {
				rule->next = f;
				prev->next = rule;
			} else { /* head insert */
				rule->next = chain->rules;
				chain->rules = rule;
			}
			break;
		}
	}
	flush_rule_ptrs(chain);
done:
	static_count++;
	static_len += l;
	IPFW_WUNLOCK(chain);
	DEB(printf("ipfw: installed rule %d, static count now %d\n",
		rule->rulenum, static_count);)
	return (0);
}

/**
 * Remove a static rule (including derived * dynamic rules)
 * and place it on the ``reap list'' for later reclamation.
 * The caller is in charge of clearing rule pointers to avoid
 * dangling pointers.
 * @return a pointer to the next entry.
 * Arguments are not checked, so they better be correct.
 */
static struct ip_fw *
remove_rule(struct ip_fw_chain *chain, struct ip_fw *rule, struct ip_fw *prev)
{
	struct ip_fw *n;
	int l = RULESIZE(rule);

	IPFW_WLOCK_ASSERT(chain);

	n = rule->next;
	IPFW_DYN_LOCK();
	remove_dyn_rule(rule, NULL /* force removal */);
	IPFW_DYN_UNLOCK();
	if (prev == NULL)
		chain->rules = n;
	else
		prev->next = n;
	static_count--;
	static_len -= l;

	rule->next = chain->reap;
	chain->reap = rule;

	return n;
}

/**
 * Reclaim storage associated with a list of rules.  This is
 * typically the list created using remove_rule.
 */
static void
reap_rules(struct ip_fw *head)
{
	struct ip_fw *rule;

	while ((rule = head) != NULL) {
		head = head->next;
		if (DUMMYNET_LOADED)
			ip_dn_ruledel_ptr(rule);
		free(rule, M_IPFW);
	}
}

/*
 * Remove all rules from a chain (except rules in set RESVD_SET
 * unless kill_default = 1).  The caller is responsible for
 * reclaiming storage for the rules left in chain->reap.
 */
static void
free_chain(struct ip_fw_chain *chain, int kill_default)
{
	struct ip_fw *prev, *rule;

	IPFW_WLOCK_ASSERT(chain);

	flush_rule_ptrs(chain); /* more efficient to do outside the loop */
	for (prev = NULL, rule = chain->rules; rule ; )
		if (kill_default || rule->set != RESVD_SET)
			rule = remove_rule(chain, rule, prev);
		else {
			prev = rule;
			rule = rule->next;
		}
}

/**
 * Remove all rules with given number, and also do set manipulation.
 * Assumes chain != NULL && *chain != NULL.
 *
 * The argument is an u_int32_t. The low 16 bit are the rule or set number,
 * the next 8 bits are the new set, the top 8 bits are the command:
 *
 *	0	delete rules with given number
 *	1	delete rules with given set number
 *	2	move rules with given number to new set
 *	3	move rules with given set number to new set
 *	4	swap sets with given numbers
 */
static int
del_entry(struct ip_fw_chain *chain, u_int32_t arg)
{
	struct ip_fw *prev = NULL, *rule;
	u_int16_t rulenum;	/* rule or old_set */
	u_int8_t cmd, new_set;

	rulenum = arg & 0xffff;
	cmd = (arg >> 24) & 0xff;
	new_set = (arg >> 16) & 0xff;

	if (cmd > 4)
		return EINVAL;
	if (new_set > RESVD_SET)
		return EINVAL;
	if (cmd == 0 || cmd == 2) {
		if (rulenum >= IPFW_DEFAULT_RULE)
			return EINVAL;
	} else {
		if (rulenum > RESVD_SET)	/* old_set */
			return EINVAL;
	}

	IPFW_WLOCK(chain);
	rule = chain->rules;
	chain->reap = NULL;
	switch (cmd) {
	case 0:	/* delete rules with given number */
		/*
		 * locate first rule to delete
		 */
		for (; rule->rulenum < rulenum; prev = rule, rule = rule->next)
			;
		if (rule->rulenum != rulenum) {
			IPFW_WUNLOCK(chain);
			return EINVAL;
		}

		/*
		 * flush pointers outside the loop, then delete all matching
		 * rules. prev remains the same throughout the cycle.
		 */
		flush_rule_ptrs(chain);
		while (rule->rulenum == rulenum)
			rule = remove_rule(chain, rule, prev);
		break;

	case 1:	/* delete all rules with given set number */
		flush_rule_ptrs(chain);
		rule = chain->rules;
		while (rule->rulenum < IPFW_DEFAULT_RULE)
			if (rule->set == rulenum)
				rule = remove_rule(chain, rule, prev);
			else {
				prev = rule;
				rule = rule->next;
			}
		break;

	case 2:	/* move rules with given number to new set */
		rule = chain->rules;
		for (; rule->rulenum < IPFW_DEFAULT_RULE; rule = rule->next)
			if (rule->rulenum == rulenum)
				rule->set = new_set;
		break;

	case 3: /* move rules with given set number to new set */
		for (; rule->rulenum < IPFW_DEFAULT_RULE; rule = rule->next)
			if (rule->set == rulenum)
				rule->set = new_set;
		break;

	case 4: /* swap two sets */
		for (; rule->rulenum < IPFW_DEFAULT_RULE; rule = rule->next)
			if (rule->set == rulenum)
				rule->set = new_set;
			else if (rule->set == new_set)
				rule->set = rulenum;
		break;
	}
	/*
	 * Look for rules to reclaim.  We grab the list before
	 * releasing the lock then reclaim them w/o the lock to
	 * avoid a LOR with dummynet.
	 */
	rule = chain->reap;
	chain->reap = NULL;
	IPFW_WUNLOCK(chain);
	if (rule)
		reap_rules(rule);
	return 0;
}

/*
 * Clear counters for a specific rule.
 * The enclosing "table" is assumed locked.
 */
static void
clear_counters(struct ip_fw *rule, int log_only)
{
	ipfw_insn_log *l = (ipfw_insn_log *)ACTION_PTR(rule);

	if (log_only == 0) {
		rule->bcnt = rule->pcnt = 0;
		rule->timestamp = 0;
	}
	if (l->o.opcode == O_LOG)
		l->log_left = l->max_log;
}

/**
 * Reset some or all counters on firewall rules.
 * @arg frwl is null to clear all entries, or contains a specific
 * rule number.
 * @arg log_only is 1 if we only want to reset logs, zero otherwise.
 */
static int
zero_entry(struct ip_fw_chain *chain, int rulenum, int log_only)
{
	struct ip_fw *rule;
	char *msg;

	IPFW_WLOCK(chain);
	if (rulenum == 0) {
		norule_counter = 0;
		for (rule = chain->rules; rule; rule = rule->next)
			clear_counters(rule, log_only);
		msg = log_only ? "ipfw: All logging counts reset.\n" :
				"ipfw: Accounting cleared.\n";
	} else {
		int cleared = 0;
		/*
		 * We can have multiple rules with the same number, so we
		 * need to clear them all.
		 */
		for (rule = chain->rules; rule; rule = rule->next)
			if (rule->rulenum == rulenum) {
				while (rule && rule->rulenum == rulenum) {
					clear_counters(rule, log_only);
					rule = rule->next;
				}
				cleared = 1;
				break;
			}
		if (!cleared) {	/* we did not find any matching rules */
			IPFW_WUNLOCK(chain);
			return (EINVAL);
		}
		msg = log_only ? "ipfw: Entry %d logging count reset.\n" :
				"ipfw: Entry %d cleared.\n";
	}
	IPFW_WUNLOCK(chain);

	if (fw_verbose)
		log(LOG_SECURITY | LOG_NOTICE, msg, rulenum);
	return (0);
}

/*
 * Check validity of the structure before insert.
 * Fortunately rules are simple, so this mostly need to check rule sizes.
 */
static int
check_ipfw_struct(struct ip_fw *rule, int size)
{
	int l, cmdlen = 0;
	int have_action=0;
	ipfw_insn *cmd;

	if (size < sizeof(*rule)) {
		printf("ipfw: rule too short\n");
		return (EINVAL);
	}
	/* first, check for valid size */
	l = RULESIZE(rule);
	if (l != size) {
		printf("ipfw: size mismatch (have %d want %d)\n", size, l);
		return (EINVAL);
	}
	if (rule->act_ofs >= rule->cmd_len) {
		printf("ipfw: bogus action offset (%u > %u)\n",
		    rule->act_ofs, rule->cmd_len - 1);
		return (EINVAL);
	}
	/*
	 * Now go for the individual checks. Very simple ones, basically only
	 * instruction sizes.
	 */
	for (l = rule->cmd_len, cmd = rule->cmd ;
			l > 0 ; l -= cmdlen, cmd += cmdlen) {
		cmdlen = F_LEN(cmd);
		if (cmdlen > l) {
			printf("ipfw: opcode %d size truncated\n",
			    cmd->opcode);
			return EINVAL;
		}
		DEB(printf("ipfw: opcode %d\n", cmd->opcode);)
		switch (cmd->opcode) {
		case O_PROBE_STATE:
		case O_KEEP_STATE:
		case O_PROTO:
		case O_IP_SRC_ME:
		case O_IP_DST_ME:
		case O_LAYER2:
		case O_IN:
		case O_FRAG:
		case O_DIVERTED:
		case O_IPOPT:
		case O_IPTOS:
		case O_IPPRECEDENCE:
		case O_IPVER:
		case O_TCPWIN:
		case O_TCPFLAGS:
		case O_TCPOPTS:
		case O_ESTAB:
		case O_VERREVPATH:
		case O_VERSRCREACH:
		case O_ANTISPOOF:
		case O_IPSEC:
			if (cmdlen != F_INSN_SIZE(ipfw_insn))
				goto bad_size;
			break;

		case O_UID:
		case O_GID:
		case O_JAIL:
		case O_IP_SRC:
		case O_IP_DST:
		case O_TCPSEQ:
		case O_TCPACK:
		case O_PROB:
		case O_ICMPTYPE:
			if (cmdlen != F_INSN_SIZE(ipfw_insn_u32))
				goto bad_size;
			break;

		case O_LIMIT:
			if (cmdlen != F_INSN_SIZE(ipfw_insn_limit))
				goto bad_size;
			break;

		case O_LOG:
			if (cmdlen != F_INSN_SIZE(ipfw_insn_log))
				goto bad_size;

			((ipfw_insn_log *)cmd)->log_left =
			    ((ipfw_insn_log *)cmd)->max_log;

			break;

		case O_IP_SRC_MASK:
		case O_IP_DST_MASK:
			/* only odd command lengths */
			if ( !(cmdlen & 1) || cmdlen > 31)
				goto bad_size;
			break;

		case O_IP_SRC_SET:
		case O_IP_DST_SET:
			if (cmd->arg1 == 0 || cmd->arg1 > 256) {
				printf("ipfw: invalid set size %d\n",
					cmd->arg1);
				return EINVAL;
			}
			if (cmdlen != F_INSN_SIZE(ipfw_insn_u32) +
			    (cmd->arg1+31)/32 )
				goto bad_size;
			break;

		case O_IP_SRC_LOOKUP:
		case O_IP_DST_LOOKUP:
			if (cmd->arg1 >= IPFW_TABLES_MAX) {
				printf("ipfw: invalid table number %d\n",
				    cmd->arg1);
				return (EINVAL);
			}
			if (cmdlen != F_INSN_SIZE(ipfw_insn) &&
			    cmdlen != F_INSN_SIZE(ipfw_insn_u32))
				goto bad_size;
			break;

		case O_MACADDR2:
			if (cmdlen != F_INSN_SIZE(ipfw_insn_mac))
				goto bad_size;
			break;

		case O_NOP:
		case O_IPID:
		case O_IPTTL:
		case O_IPLEN:
		case O_TCPDATALEN:
			if (cmdlen < 1 || cmdlen > 31)
				goto bad_size;
			break;

		case O_MAC_TYPE:
		case O_IP_SRCPORT:
		case O_IP_DSTPORT: /* XXX artificial limit, 30 port pairs */
			if (cmdlen < 2 || cmdlen > 31)
				goto bad_size;
			break;

		case O_RECV:
		case O_XMIT:
		case O_VIA:
			if (cmdlen != F_INSN_SIZE(ipfw_insn_if))
				goto bad_size;
			break;

		case O_ALTQ:
			if (cmdlen != F_INSN_SIZE(ipfw_insn_altq))
				goto bad_size;
			break;

		case O_PIPE:
		case O_QUEUE:
			if (cmdlen != F_INSN_SIZE(ipfw_insn_pipe))
				goto bad_size;
			goto check_action;

		case O_FORWARD_IP:
#ifdef	IPFIREWALL_FORWARD
			if (cmdlen != F_INSN_SIZE(ipfw_insn_sa))
				goto bad_size;
			goto check_action;
#else
			return EINVAL;
#endif

		case O_DIVERT:
		case O_TEE:
			if (ip_divert_ptr == NULL)
				return EINVAL;
		case O_NETGRAPH:
		case O_NGTEE:
			if (!NG_IPFW_LOADED)
				return EINVAL;
		case O_FORWARD_MAC: /* XXX not implemented yet */
		case O_CHECK_STATE:
		case O_COUNT:
		case O_ACCEPT:
		case O_DENY:
		case O_REJECT:
		case O_SKIPTO:
			if (cmdlen != F_INSN_SIZE(ipfw_insn))
				goto bad_size;
check_action:
			if (have_action) {
				printf("ipfw: opcode %d, multiple actions"
					" not allowed\n",
					cmd->opcode);
				return EINVAL;
			}
			have_action = 1;
			if (l != cmdlen) {
				printf("ipfw: opcode %d, action must be"
					" last opcode\n",
					cmd->opcode);
				return EINVAL;
			}
			break;
		default:
			printf("ipfw: opcode %d, unknown opcode\n",
				cmd->opcode);
			return EINVAL;
		}
	}
	if (have_action == 0) {
		printf("ipfw: missing action\n");
		return EINVAL;
	}
	return 0;

bad_size:
	printf("ipfw: opcode %d size %d wrong\n",
		cmd->opcode, cmdlen);
	return EINVAL;
}

/*
 * Copy the static and dynamic rules to the supplied buffer
 * and return the amount of space actually used.
 */
static size_t
ipfw_getrules(struct ip_fw_chain *chain, void *buf, size_t space)
{
	char *bp = buf;
	char *ep = bp + space;
	struct ip_fw *rule;
	int i;

	/* XXX this can take a long time and locking will block packet flow */
	IPFW_RLOCK(chain);
	for (rule = chain->rules; rule ; rule = rule->next) {
		/*
		 * Verify the entry fits in the buffer in case the
		 * rules changed between calculating buffer space and
		 * now.  This would be better done using a generation
		 * number but should suffice for now.
		 */
		i = RULESIZE(rule);
		if (bp + i <= ep) {
			bcopy(rule, bp, i);
			bcopy(&set_disable, &(((struct ip_fw *)bp)->next_rule),
			    sizeof(set_disable));
			bp += i;
		}
	}
	IPFW_RUNLOCK(chain);
	if (ipfw_dyn_v) {
		ipfw_dyn_rule *p, *last = NULL;

		IPFW_DYN_LOCK();
		for (i = 0 ; i < curr_dyn_buckets; i++)
			for (p = ipfw_dyn_v[i] ; p != NULL; p = p->next) {
				if (bp + sizeof *p <= ep) {
					ipfw_dyn_rule *dst =
						(ipfw_dyn_rule *)bp;
					bcopy(p, dst, sizeof *p);
					bcopy(&(p->rule->rulenum), &(dst->rule),
					    sizeof(p->rule->rulenum));
					/*
					 * store a non-null value in "next".
					 * The userland code will interpret a
					 * NULL here as a marker
					 * for the last dynamic rule.
					 */
					bcopy(&dst, &dst->next, sizeof(dst));
					last = dst;
					dst->expire =
					    TIME_LEQ(dst->expire, time_second) ?
						0 : dst->expire - time_second ;
					bp += sizeof(ipfw_dyn_rule);
				}
			}
		IPFW_DYN_UNLOCK();
		if (last != NULL) /* mark last dynamic rule */
			bzero(&last->next, sizeof(last));
	}
	return (bp - (char *)buf);
}


/**
 * {set|get}sockopt parser.
 */
static int
ipfw_ctl(struct sockopt *sopt)
{
#define	RULE_MAXSIZE	(256*sizeof(u_int32_t))
	int error, rule_num;
	size_t size;
	struct ip_fw *buf, *rule;
	u_int32_t rulenum[2];

	error = suser(sopt->sopt_td);
	if (error)
		return (error);

	/*
	 * Disallow modifications in really-really secure mode, but still allow
	 * the logging counters to be reset.
	 */
	if (sopt->sopt_name == IP_FW_ADD ||
	    (sopt->sopt_dir == SOPT_SET && sopt->sopt_name != IP_FW_RESETLOG)) {
#if __FreeBSD_version >= 500034
		error = securelevel_ge(sopt->sopt_td->td_ucred, 3);
		if (error)
			return (error);
#else /* FreeBSD 4.x */
		if (securelevel >= 3)
			return (EPERM);
#endif
	}

	error = 0;

	switch (sopt->sopt_name) {
	case IP_FW_GET:
		/*
		 * pass up a copy of the current rules. Static rules
		 * come first (the last of which has number IPFW_DEFAULT_RULE),
		 * followed by a possibly empty list of dynamic rule.
		 * The last dynamic rule has NULL in the "next" field.
		 *
		 * Note that the calculated size is used to bound the
		 * amount of data returned to the user.  The rule set may
		 * change between calculating the size and returning the
		 * data in which case we'll just return what fits.
		 */
		size = static_len;	/* size of static rules */
		if (ipfw_dyn_v)		/* add size of dyn.rules */
			size += (dyn_count * sizeof(ipfw_dyn_rule));

		/*
		 * XXX todo: if the user passes a short length just to know
		 * how much room is needed, do not bother filling up the
		 * buffer, just jump to the sooptcopyout.
		 */
		buf = malloc(size, M_TEMP, M_WAITOK);
		error = sooptcopyout(sopt, buf,
				ipfw_getrules(&layer3_chain, buf, size));
		free(buf, M_TEMP);
		break;

	case IP_FW_FLUSH:
		/*
		 * Normally we cannot release the lock on each iteration.
		 * We could do it here only because we start from the head all
		 * the times so there is no risk of missing some entries.
		 * On the other hand, the risk is that we end up with
		 * a very inconsistent ruleset, so better keep the lock
		 * around the whole cycle.
		 *
		 * XXX this code can be improved by resetting the head of
		 * the list to point to the default rule, and then freeing
		 * the old list without the need for a lock.
		 */

		IPFW_WLOCK(&layer3_chain);
		layer3_chain.reap = NULL;
		free_chain(&layer3_chain, 0 /* keep default rule */);
		rule = layer3_chain.reap, layer3_chain.reap = NULL;
		IPFW_WUNLOCK(&layer3_chain);
		if (layer3_chain.reap != NULL)
			reap_rules(rule);
		break;

	case IP_FW_ADD:
		rule = malloc(RULE_MAXSIZE, M_TEMP, M_WAITOK);
		error = sooptcopyin(sopt, rule, RULE_MAXSIZE,
			sizeof(struct ip_fw) );
		if (error == 0)
			error = check_ipfw_struct(rule, sopt->sopt_valsize);
		if (error == 0) {
			error = add_rule(&layer3_chain, rule);
			size = RULESIZE(rule);
			if (!error && sopt->sopt_dir == SOPT_GET)
				error = sooptcopyout(sopt, rule, size);
		}
		free(rule, M_TEMP);
		break;

	case IP_FW_DEL:
		/*
		 * IP_FW_DEL is used for deleting single rules or sets,
		 * and (ab)used to atomically manipulate sets. Argument size
		 * is used to distinguish between the two:
		 *    sizeof(u_int32_t)
		 *	delete single rule or set of rules,
		 *	or reassign rules (or sets) to a different set.
		 *    2*sizeof(u_int32_t)
		 *	atomic disable/enable sets.
		 *	first u_int32_t contains sets to be disabled,
		 *	second u_int32_t contains sets to be enabled.
		 */
		error = sooptcopyin(sopt, rulenum,
			2*sizeof(u_int32_t), sizeof(u_int32_t));
		if (error)
			break;
		size = sopt->sopt_valsize;
		if (size == sizeof(u_int32_t))	/* delete or reassign */
			error = del_entry(&layer3_chain, rulenum[0]);
		else if (size == 2*sizeof(u_int32_t)) /* set enable/disable */
			set_disable =
			    (set_disable | rulenum[0]) & ~rulenum[1] &
			    ~(1<<RESVD_SET); /* set RESVD_SET always enabled */
		else
			error = EINVAL;
		break;

	case IP_FW_ZERO:
	case IP_FW_RESETLOG: /* argument is an int, the rule number */
		rule_num = 0;
		if (sopt->sopt_val != 0) {
		    error = sooptcopyin(sopt, &rule_num,
			    sizeof(int), sizeof(int));
		    if (error)
			break;
		}
		error = zero_entry(&layer3_chain, rule_num,
			sopt->sopt_name == IP_FW_RESETLOG);
		break;

	case IP_FW_TABLE_ADD:
		{
			ipfw_table_entry ent;

			error = sooptcopyin(sopt, &ent,
			    sizeof(ent), sizeof(ent));
			if (error)
				break;
			error = add_table_entry(ent.tbl, ent.addr,
			    ent.masklen, ent.value);
		}
		break;

	case IP_FW_TABLE_DEL:
		{
			ipfw_table_entry ent;

			error = sooptcopyin(sopt, &ent,
			    sizeof(ent), sizeof(ent));
			if (error)
				break;
			error = del_table_entry(ent.tbl, ent.addr, ent.masklen);
		}
		break;

	case IP_FW_TABLE_FLUSH:
		{
			u_int16_t tbl;

			error = sooptcopyin(sopt, &tbl,
			    sizeof(tbl), sizeof(tbl));
			if (error)
				break;
			error = flush_table(tbl);
		}
		break;

	case IP_FW_TABLE_GETSIZE:
		{
			u_int32_t tbl, cnt;

			if ((error = sooptcopyin(sopt, &tbl, sizeof(tbl),
			    sizeof(tbl))))
				break;
			if ((error = count_table(tbl, &cnt)))
				break;
			error = sooptcopyout(sopt, &cnt, sizeof(cnt));
		}
		break;

	case IP_FW_TABLE_LIST:
		{
			ipfw_table *tbl;

			if (sopt->sopt_valsize < sizeof(*tbl)) {
				error = EINVAL;
				break;
			}
			size = sopt->sopt_valsize;
			tbl = malloc(size, M_TEMP, M_WAITOK);
			if (tbl == NULL) {
				error = ENOMEM;
				break;
			}
			error = sooptcopyin(sopt, tbl, size, sizeof(*tbl));
			if (error) {
				free(tbl, M_TEMP);
				break;
			}
			tbl->size = (size - sizeof(*tbl)) /
			    sizeof(ipfw_table_entry);
			error = dump_table(tbl);
			if (error) {
				free(tbl, M_TEMP);
				break;
			}
			error = sooptcopyout(sopt, tbl, size);
			free(tbl, M_TEMP);
		}
		break;

	default:
		printf("ipfw: ipfw_ctl invalid option %d\n", sopt->sopt_name);
		error = EINVAL;
	}

	return (error);
#undef RULE_MAXSIZE
}

/**
 * dummynet needs a reference to the default rule, because rules can be
 * deleted while packets hold a reference to them. When this happens,
 * dummynet changes the reference to the default rule (it could well be a
 * NULL pointer, but this way we do not need to check for the special
 * case, plus here he have info on the default behaviour).
 */
struct ip_fw *ip_fw_default_rule;

/*
 * This procedure is only used to handle keepalives. It is invoked
 * every dyn_keepalive_period
 */
static void
ipfw_tick(void * __unused unused)
{
	int i;
	ipfw_dyn_rule *q;

	if (dyn_keepalive == 0 || ipfw_dyn_v == NULL || dyn_count == 0)
		goto done;

	IPFW_DYN_LOCK();
	for (i = 0 ; i < curr_dyn_buckets ; i++) {
		for (q = ipfw_dyn_v[i] ; q ; q = q->next ) {
			if (q->dyn_type == O_LIMIT_PARENT)
				continue;
			if (q->id.proto != IPPROTO_TCP)
				continue;
			if ( (q->state & BOTH_SYN) != BOTH_SYN)
				continue;
			if (TIME_LEQ( time_second+dyn_keepalive_interval,
			    q->expire))
				continue;	/* too early */
			if (TIME_LEQ(q->expire, time_second))
				continue;	/* too late, rule expired */

			send_pkt(&(q->id), q->ack_rev - 1, q->ack_fwd, TH_SYN);
			send_pkt(&(q->id), q->ack_fwd - 1, q->ack_rev, 0);
		}
	}
	IPFW_DYN_UNLOCK();
done:
	callout_reset(&ipfw_timeout, dyn_keepalive_period*hz, ipfw_tick, NULL);
}

int
ipfw_init(void)
{
	struct ip_fw default_rule;
	int error;

	layer3_chain.rules = NULL;
	layer3_chain.want_write = 0;
	layer3_chain.busy_count = 0;
	cv_init(&layer3_chain.cv, "Condition variable for IPFW rw locks");
	IPFW_LOCK_INIT(&layer3_chain);
	ipfw_dyn_rule_zone = uma_zcreate("IPFW dynamic rule zone",
	    sizeof(ipfw_dyn_rule), NULL, NULL, NULL, NULL,
	    UMA_ALIGN_PTR, 0);
	IPFW_DYN_LOCK_INIT();
	callout_init(&ipfw_timeout, debug_mpsafenet ? CALLOUT_MPSAFE : 0);

	bzero(&default_rule, sizeof default_rule);

	default_rule.act_ofs = 0;
	default_rule.rulenum = IPFW_DEFAULT_RULE;
	default_rule.cmd_len = 1;
	default_rule.set = RESVD_SET;

	default_rule.cmd[0].len = 1;
	default_rule.cmd[0].opcode =
#ifdef IPFIREWALL_DEFAULT_TO_ACCEPT
				1 ? O_ACCEPT :
#endif
				O_DENY;

	error = add_rule(&layer3_chain, &default_rule);
	if (error != 0) {
		printf("ipfw2: error %u initializing default rule "
			"(support disabled)\n", error);
		IPFW_DYN_LOCK_DESTROY();
		IPFW_LOCK_DESTROY(&layer3_chain);
		return (error);
	}

	ip_fw_default_rule = layer3_chain.rules;
	printf("ipfw2 initialized, divert %s, "
		"rule-based forwarding "
#ifdef IPFIREWALL_FORWARD
		"enabled, "
#else
		"disabled, "
#endif
		"default to %s, logging ",
#ifdef IPDIVERT
		"enabled",
#else
		"loadable",
#endif
		default_rule.cmd[0].opcode == O_ACCEPT ? "accept" : "deny");

#ifdef IPFIREWALL_VERBOSE
	fw_verbose = 1;
#endif
#ifdef IPFIREWALL_VERBOSE_LIMIT
	verbose_limit = IPFIREWALL_VERBOSE_LIMIT;
#endif
	if (fw_verbose == 0)
		printf("disabled\n");
	else if (verbose_limit == 0)
		printf("unlimited\n");
	else
		printf("limited to %d packets/entry by default\n",
		    verbose_limit);

	init_tables();
	ip_fw_ctl_ptr = ipfw_ctl;
	ip_fw_chk_ptr = ipfw_chk;
	callout_reset(&ipfw_timeout, hz, ipfw_tick, NULL);

	return (0);
}

void
ipfw_destroy(void)
{
	struct ip_fw *reap;

	ip_fw_chk_ptr = NULL;
	ip_fw_ctl_ptr = NULL;
	callout_drain(&ipfw_timeout);
	IPFW_WLOCK(&layer3_chain);
	layer3_chain.reap = NULL;
	free_chain(&layer3_chain, 1 /* kill default rule */);
	reap = layer3_chain.reap, layer3_chain.reap = NULL;
	IPFW_WUNLOCK(&layer3_chain);
	if (reap != NULL)
		reap_rules(reap);
	flush_tables();
	IPFW_DYN_LOCK_DESTROY();
	uma_zdestroy(ipfw_dyn_rule_zone);
	IPFW_LOCK_DESTROY(&layer3_chain);
	printf("IP firewall unloaded\n");
}

#endif /* IPFW2 */
OpenPOWER on IntegriCloud