summaryrefslogtreecommitdiffstats
path: root/sys/netinet/tcp_input.c
blob: c42d1ad981f456770cc4b495c0dcdb70309f243f (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
/*
 * Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994, 1995
 *	The Regents of the University of California.  All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 * 1. Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 * 2. Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 * 3. All advertising materials mentioning features or use of this software
 *    must display the following acknowledgement:
 *	This product includes software developed by the University of
 *	California, Berkeley and its contributors.
 * 4. Neither the name of the University nor the names of its contributors
 *    may be used to endorse or promote products derived from this software
 *    without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
 * ARE DISCLAIMED.  IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
 * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
 * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
 * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
 * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
 * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
 * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
 * SUCH DAMAGE.
 *
 *	@(#)tcp_input.c	8.12 (Berkeley) 5/24/95
 * $FreeBSD$
 */

#include "opt_ipfw.h"		/* for ipfw_fwd		*/
#include "opt_inet6.h"
#include "opt_ipsec.h"
#include "opt_mac.h"
#include "opt_tcpdebug.h"
#include "opt_tcp_input.h"

#include <sys/param.h>
#include <sys/kernel.h>
#include <sys/mac.h>
#include <sys/malloc.h>
#include <sys/mbuf.h>
#include <sys/proc.h>		/* for proc0 declaration */
#include <sys/protosw.h>
#include <sys/signalvar.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/sysctl.h>
#include <sys/syslog.h>
#include <sys/systm.h>

#include <machine/cpu.h>	/* before tcp_seq.h, for tcp_random18() */

#include <net/if.h>
#include <net/route.h>

#include <netinet/in.h>
#include <netinet/in_pcb.h>
#include <netinet/in_systm.h>
#include <netinet/in_var.h>
#include <netinet/ip.h>
#include <netinet/ip_icmp.h>	/* for ICMP_BANDLIM		*/
#include <netinet/icmp_var.h>	/* for ICMP_BANDLIM		*/
#include <netinet/ip_var.h>
#include <netinet/ip6.h>
#include <netinet/icmp6.h>
#include <netinet6/in6_pcb.h>
#include <netinet6/ip6_var.h>
#include <netinet6/nd6.h>
#include <netinet/tcp.h>
#include <netinet/tcp_fsm.h>
#include <netinet/tcp_seq.h>
#include <netinet/tcp_timer.h>
#include <netinet/tcp_var.h>
#include <netinet6/tcp6_var.h>
#include <netinet/tcpip.h>
#ifdef TCPDEBUG
#include <netinet/tcp_debug.h>
#endif /* TCPDEBUG */

#ifdef FAST_IPSEC
#include <netipsec/ipsec.h>
#include <netipsec/ipsec6.h>
#endif /*FAST_IPSEC*/

#ifdef IPSEC
#include <netinet6/ipsec.h>
#include <netinet6/ipsec6.h>
#include <netkey/key.h>
#endif /*IPSEC*/

#include <machine/in_cksum.h>

MALLOC_DEFINE(M_TSEGQ, "tseg_qent", "TCP segment queue entry");

static const int tcprexmtthresh = 3;
tcp_cc	tcp_ccgen;

struct	tcpstat tcpstat;
SYSCTL_STRUCT(_net_inet_tcp, TCPCTL_STATS, stats, CTLFLAG_RW,
    &tcpstat , tcpstat, "TCP statistics (struct tcpstat, netinet/tcp_var.h)");

static int log_in_vain = 0;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, log_in_vain, CTLFLAG_RW, 
    &log_in_vain, 0, "Log all incoming TCP connections");

static int blackhole = 0;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, blackhole, CTLFLAG_RW,
	&blackhole, 0, "Do not send RST when dropping refused connections");

int tcp_delack_enabled = 1;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, delayed_ack, CTLFLAG_RW, 
    &tcp_delack_enabled, 0, 
    "Delay ACK to try and piggyback it onto a data packet");

#ifdef TCP_DROP_SYNFIN
static int drop_synfin = 0;
SYSCTL_INT(_net_inet_tcp, OID_AUTO, drop_synfin, CTLFLAG_RW,
    &drop_synfin, 0, "Drop TCP packets with SYN+FIN set");
#endif

struct inpcbhead tcb;
#define	tcb6	tcb  /* for KAME src sync over BSD*'s */
struct inpcbinfo tcbinfo;
struct mtx	*tcbinfo_mtx;

static void	 tcp_dooptions(struct tcpopt *, u_char *, int, int);
static void	 tcp_pulloutofband(struct socket *,
		     struct tcphdr *, struct mbuf *, int);
static int	 tcp_reass(struct tcpcb *, struct tcphdr *, int *,
		     struct mbuf *);
static void	 tcp_xmit_timer(struct tcpcb *, int);
static void	 tcp_newreno_partial_ack(struct tcpcb *, struct tcphdr *);

/* Neighbor Discovery, Neighbor Unreachability Detection Upper layer hint. */
#ifdef INET6
#define ND6_HINT(tp) \
do { \
	if ((tp) && (tp)->t_inpcb && \
	    ((tp)->t_inpcb->inp_vflag & INP_IPV6) != 0 && \
	    (tp)->t_inpcb->in6p_route.ro_rt) \
		nd6_nud_hint((tp)->t_inpcb->in6p_route.ro_rt, NULL, 0); \
} while (0)
#else
#define ND6_HINT(tp)
#endif

/*
 * Indicate whether this ack should be delayed.  We can delay the ack if
 *	- delayed acks are enabled and
 *	- there is no delayed ack timer in progress and
 *	- our last ack wasn't a 0-sized window.  We never want to delay
 *	  the ack that opens up a 0-sized window.
 */
#define DELAY_ACK(tp) \
	(tcp_delack_enabled && !callout_pending(tp->tt_delack) && \
	(tp->t_flags & TF_RXWIN0SENT) == 0)

static int
tcp_reass(tp, th, tlenp, m)
	register struct tcpcb *tp;
	register struct tcphdr *th;
	int *tlenp;
	struct mbuf *m;
{
	struct tseg_qent *q;
	struct tseg_qent *p = NULL;
	struct tseg_qent *nq;
	struct tseg_qent *te;
	struct socket *so = tp->t_inpcb->inp_socket;
	int flags;

	/*
	 * Call with th==0 after become established to
	 * force pre-ESTABLISHED data up to user socket.
	 */
	if (th == 0)
		goto present;

	/* Allocate a new queue entry. If we can't, just drop the pkt. XXX */
	MALLOC(te, struct tseg_qent *, sizeof (struct tseg_qent), M_TSEGQ,
	       M_NOWAIT);
	if (te == NULL) {
		tcpstat.tcps_rcvmemdrop++;
		m_freem(m);
		return (0);
	}

	/*
	 * Find a segment which begins after this one does.
	 */
	LIST_FOREACH(q, &tp->t_segq, tqe_q) {
		if (SEQ_GT(q->tqe_th->th_seq, th->th_seq))
			break;
		p = q;
	}

	/*
	 * If there is a preceding segment, it may provide some of
	 * our data already.  If so, drop the data from the incoming
	 * segment.  If it provides all of our data, drop us.
	 */
	if (p != NULL) {
		register int i;
		/* conversion to int (in i) handles seq wraparound */
		i = p->tqe_th->th_seq + p->tqe_len - th->th_seq;
		if (i > 0) {
			if (i >= *tlenp) {
				tcpstat.tcps_rcvduppack++;
				tcpstat.tcps_rcvdupbyte += *tlenp;
				m_freem(m);
				FREE(te, M_TSEGQ);
				/*
				 * Try to present any queued data
				 * at the left window edge to the user.
				 * This is needed after the 3-WHS
				 * completes.
				 */
				goto present;	/* ??? */
			}
			m_adj(m, i);
			*tlenp -= i;
			th->th_seq += i;
		}
	}
	tcpstat.tcps_rcvoopack++;
	tcpstat.tcps_rcvoobyte += *tlenp;

	/*
	 * While we overlap succeeding segments trim them or,
	 * if they are completely covered, dequeue them.
	 */
	while (q) {
		register int i = (th->th_seq + *tlenp) - q->tqe_th->th_seq;
		if (i <= 0)
			break;
		if (i < q->tqe_len) {
			q->tqe_th->th_seq += i;
			q->tqe_len -= i;
			m_adj(q->tqe_m, i);
			break;
		}

		nq = LIST_NEXT(q, tqe_q);
		LIST_REMOVE(q, tqe_q);
		m_freem(q->tqe_m);
		FREE(q, M_TSEGQ);
		q = nq;
	}

	/* Insert the new segment queue entry into place. */
	te->tqe_m = m;
	te->tqe_th = th;
	te->tqe_len = *tlenp;

	if (p == NULL) {
		LIST_INSERT_HEAD(&tp->t_segq, te, tqe_q);
	} else {
		LIST_INSERT_AFTER(p, te, tqe_q);
	}

present:
	/*
	 * Present data to user, advancing rcv_nxt through
	 * completed sequence space.
	 */
	if (!TCPS_HAVEESTABLISHED(tp->t_state))
		return (0);
	q = LIST_FIRST(&tp->t_segq);
	if (!q || q->tqe_th->th_seq != tp->rcv_nxt)
		return (0);
	do {
		tp->rcv_nxt += q->tqe_len;
		flags = q->tqe_th->th_flags & TH_FIN;
		nq = LIST_NEXT(q, tqe_q);
		LIST_REMOVE(q, tqe_q);
		if (so->so_state & SS_CANTRCVMORE)
			m_freem(q->tqe_m);
		else
			sbappend(&so->so_rcv, q->tqe_m);
		FREE(q, M_TSEGQ);
		q = nq;
	} while (q && q->tqe_th->th_seq == tp->rcv_nxt);
	ND6_HINT(tp);
	sorwakeup(so);
	return (flags);
}

/*
 * TCP input routine, follows pages 65-76 of the
 * protocol specification dated September, 1981 very closely.
 */
#ifdef INET6
int
tcp6_input(mp, offp, proto)
	struct mbuf **mp;
	int *offp, proto;
{
	register struct mbuf *m = *mp;
	struct in6_ifaddr *ia6;

	IP6_EXTHDR_CHECK(m, *offp, sizeof(struct tcphdr), IPPROTO_DONE);

	/*
	 * draft-itojun-ipv6-tcp-to-anycast
	 * better place to put this in?
	 */
	ia6 = ip6_getdstifaddr(m);
	if (ia6 && (ia6->ia6_flags & IN6_IFF_ANYCAST)) {		
		struct ip6_hdr *ip6;

		ip6 = mtod(m, struct ip6_hdr *);
		icmp6_error(m, ICMP6_DST_UNREACH, ICMP6_DST_UNREACH_ADDR,
			    (caddr_t)&ip6->ip6_dst - (caddr_t)ip6);
		return IPPROTO_DONE;
	}

	tcp_input(m, *offp);
	return IPPROTO_DONE;
}
#endif

void
tcp_input(m, off0)
	register struct mbuf *m;
	int off0;
{
	register struct tcphdr *th;
	register struct ip *ip = NULL;
	register struct ipovly *ipov;
	register struct inpcb *inp = NULL;
	u_char *optp = NULL;
	int optlen = 0;
	int len, tlen, off;
	int drop_hdrlen;
	register struct tcpcb *tp = 0;
	register int thflags;
	struct socket *so = 0;
	int todrop, acked, ourfinisacked, needoutput = 0;
	u_long tiwin;
	struct tcpopt to;		/* options in this segment */
	struct rmxp_tao *taop;		/* pointer to our TAO cache entry */
	struct rmxp_tao	tao_noncached;	/* in case there's no cached entry */
	int headlocked = 0;
	struct sockaddr_in *next_hop = NULL;
	int rstreason; /* For badport_bandlim accounting purposes */

	struct ip6_hdr *ip6 = NULL;
#ifdef INET6
	int isipv6;
#else
	const int isipv6 = 0;
#endif

#ifdef TCPDEBUG
	/*
	 * The size of tcp_saveipgen must be the size of the max ip header,
	 * now IPv6.
	 */
	u_char tcp_saveipgen[40];
	struct tcphdr tcp_savetcp;
	short ostate = 0;
#endif

	/* Grab info from MT_TAG mbufs prepended to the chain. */
	for (;m && m->m_type == MT_TAG; m = m->m_next) { 
		if (m->_m_tag_id == PACKET_TAG_IPFORWARD)
			next_hop = (struct sockaddr_in *)m->m_hdr.mh_data;
	}
#ifdef INET6
	isipv6 = (mtod(m, struct ip *)->ip_v == 6) ? 1 : 0;
#endif
	bzero((char *)&to, sizeof(to));

	tcpstat.tcps_rcvtotal++;

	if (isipv6) {
		/* IP6_EXTHDR_CHECK() is already done at tcp6_input() */
		ip6 = mtod(m, struct ip6_hdr *);
		tlen = sizeof(*ip6) + ntohs(ip6->ip6_plen) - off0;
		if (in6_cksum(m, IPPROTO_TCP, off0, tlen)) {
			tcpstat.tcps_rcvbadsum++;
			goto drop;
		}
		th = (struct tcphdr *)((caddr_t)ip6 + off0);

		/*
		 * Be proactive about unspecified IPv6 address in source.
		 * As we use all-zero to indicate unbounded/unconnected pcb,
		 * unspecified IPv6 address can be used to confuse us.
		 *
		 * Note that packets with unspecified IPv6 destination is
		 * already dropped in ip6_input.
		 */
		if (IN6_IS_ADDR_UNSPECIFIED(&ip6->ip6_src)) {
			/* XXX stat */
			goto drop;
		}
	} else {
		/*
		 * Get IP and TCP header together in first mbuf.
		 * Note: IP leaves IP header in first mbuf.
		 */
		if (off0 > sizeof (struct ip)) {
			ip_stripoptions(m, (struct mbuf *)0);
			off0 = sizeof(struct ip);
		}
		if (m->m_len < sizeof (struct tcpiphdr)) {
			if ((m = m_pullup(m, sizeof (struct tcpiphdr))) == 0) {
				tcpstat.tcps_rcvshort++;
				return;
			}
		}
		ip = mtod(m, struct ip *);
		ipov = (struct ipovly *)ip;
		th = (struct tcphdr *)((caddr_t)ip + off0);
		tlen = ip->ip_len;

		if (m->m_pkthdr.csum_flags & CSUM_DATA_VALID) {
			if (m->m_pkthdr.csum_flags & CSUM_PSEUDO_HDR)
				th->th_sum = m->m_pkthdr.csum_data;
			else
				th->th_sum = in_pseudo(ip->ip_src.s_addr,
						ip->ip_dst.s_addr,
						htonl(m->m_pkthdr.csum_data +
							ip->ip_len +
							IPPROTO_TCP));
			th->th_sum ^= 0xffff;
		} else {
			/*
			 * Checksum extended TCP header and data.
			 */
			len = sizeof (struct ip) + tlen;
			bzero(ipov->ih_x1, sizeof(ipov->ih_x1));
			ipov->ih_len = (u_short)tlen;
			ipov->ih_len = htons(ipov->ih_len);
			th->th_sum = in_cksum(m, len);
		}
		if (th->th_sum) {
			tcpstat.tcps_rcvbadsum++;
			goto drop;
		}
#ifdef INET6
		/* Re-initialization for later version check */
		ip->ip_v = IPVERSION;
#endif
	}

	/*
	 * Check that TCP offset makes sense,
	 * pull out TCP options and adjust length.		XXX
	 */
	off = th->th_off << 2;
	if (off < sizeof (struct tcphdr) || off > tlen) {
		tcpstat.tcps_rcvbadoff++;
		goto drop;
	}
	tlen -= off;	/* tlen is used instead of ti->ti_len */
	if (off > sizeof (struct tcphdr)) {
		if (isipv6) {
			IP6_EXTHDR_CHECK(m, off0, off, );
			ip6 = mtod(m, struct ip6_hdr *);
			th = (struct tcphdr *)((caddr_t)ip6 + off0);
		} else {
			if (m->m_len < sizeof(struct ip) + off) {
				if ((m = m_pullup(m, sizeof (struct ip) + off))
						== 0) {
					tcpstat.tcps_rcvshort++;
					return;
				}
				ip = mtod(m, struct ip *);
				ipov = (struct ipovly *)ip;
				th = (struct tcphdr *)((caddr_t)ip + off0);
			}
		}
		optlen = off - sizeof (struct tcphdr);
		optp = (u_char *)(th + 1);
	}
	thflags = th->th_flags;

#ifdef TCP_DROP_SYNFIN
	/*
	 * If the drop_synfin option is enabled, drop all packets with
	 * both the SYN and FIN bits set. This prevents e.g. nmap from
	 * identifying the TCP/IP stack.
	 *
	 * This is a violation of the TCP specification.
	 */
	if (drop_synfin && (thflags & (TH_SYN|TH_FIN)) == (TH_SYN|TH_FIN))
		goto drop;
#endif

	/*
	 * Convert TCP protocol specific fields to host format.
	 */
	th->th_seq = ntohl(th->th_seq);
	th->th_ack = ntohl(th->th_ack);
	th->th_win = ntohs(th->th_win);
	th->th_urp = ntohs(th->th_urp);

	/*
	 * Delay droping TCP, IP headers, IPv6 ext headers, and TCP options,
	 * until after ip6_savecontrol() is called and before other functions
	 * which don't want those proto headers.
	 * Because ip6_savecontrol() is going to parse the mbuf to
	 * search for data to be passed up to user-land, it wants mbuf
	 * parameters to be unchanged.
	 * XXX: the call of ip6_savecontrol() has been obsoleted based on
	 * latest version of the advanced API (20020110).
	 */
	drop_hdrlen = off0 + off;

	/*
	 * Locate pcb for segment.
	 */
	INP_INFO_WLOCK(&tcbinfo);
	headlocked = 1;
findpcb:
	/* IPFIREWALL_FORWARD section */
	if (next_hop != NULL && isipv6 == 0) {	/* IPv6 support is not yet */
		/*
		 * Transparently forwarded. Pretend to be the destination.
		 * already got one like this? 
		 */
		inp = in_pcblookup_hash(&tcbinfo, ip->ip_src, th->th_sport,
					ip->ip_dst, th->th_dport,
					0, m->m_pkthdr.rcvif);
		if (!inp) {
			/* It's new.  Try find the ambushing socket. */
			inp = in_pcblookup_hash(&tcbinfo,
						ip->ip_src, th->th_sport,
						next_hop->sin_addr,
						next_hop->sin_port ?
						    ntohs(next_hop->sin_port) :
						    th->th_dport,
						1, m->m_pkthdr.rcvif);
		}
	} else {
		if (isipv6)
			inp = in6_pcblookup_hash(&tcbinfo,
						 &ip6->ip6_src, th->th_sport,
						 &ip6->ip6_dst, th->th_dport,
						 1, m->m_pkthdr.rcvif);
		else
			inp = in_pcblookup_hash(&tcbinfo,
						ip->ip_src, th->th_sport,
						ip->ip_dst, th->th_dport,
						1, m->m_pkthdr.rcvif);
      }

#ifdef IPSEC
	if (isipv6) {
		if (inp != NULL && ipsec6_in_reject_so(m, inp->inp_socket)) {
			ipsec6stat.in_polvio++;
			goto drop;
		}
	} else {
		if (inp != NULL && ipsec4_in_reject_so(m, inp->inp_socket)) {
			ipsecstat.in_polvio++;
			goto drop;
		}
	}
#endif
#ifdef FAST_IPSEC
	if (isipv6) {
		if (inp != NULL && ipsec6_in_reject(m, inp)) {
			goto drop;
		}
	} else
	if (inp != NULL && ipsec4_in_reject(m, inp)) {
		goto drop;
	}
#endif /*FAST_IPSEC*/

	/*
	 * If the state is CLOSED (i.e., TCB does not exist) then
	 * all data in the incoming segment is discarded.
	 * If the TCB exists but is in CLOSED state, it is embryonic,
	 * but should either do a listen or a connect soon.
	 */
	if (inp == NULL) {
		if (log_in_vain) {
#ifdef INET6
			char dbuf[INET6_ADDRSTRLEN+2], sbuf[INET6_ADDRSTRLEN+2];
#else
			char dbuf[4*sizeof "123"], sbuf[4*sizeof "123"];
#endif

			if (isipv6) {
				strcpy(dbuf, "[");
				strcpy(sbuf, "[");
				strcat(dbuf, ip6_sprintf(&ip6->ip6_dst));
				strcat(sbuf, ip6_sprintf(&ip6->ip6_src));
				strcat(dbuf, "]");
				strcat(sbuf, "]");
			} else {
				strcpy(dbuf, inet_ntoa(ip->ip_dst));
				strcpy(sbuf, inet_ntoa(ip->ip_src));
			}
			switch (log_in_vain) {
			case 1:
				if ((thflags & TH_SYN) == 0)
					break;
			case 2:
				log(LOG_INFO,
				    "Connection attempt to TCP %s:%d "
				    "from %s:%d flags:0x%02x\n",
				    dbuf, ntohs(th->th_dport), sbuf,
				    ntohs(th->th_sport), thflags);
				break;
			default:
				break;
			}
		}
		if (blackhole) { 
			switch (blackhole) {
			case 1:
				if (thflags & TH_SYN)
					goto drop;
				break;
			case 2:
				goto drop;
			default:
				goto drop;
			}
		}
		rstreason = BANDLIM_RST_CLOSEDPORT;
		goto dropwithreset;
	}
	INP_LOCK(inp);
	tp = intotcpcb(inp);
	if (tp == 0) {
		INP_UNLOCK(inp);
		rstreason = BANDLIM_RST_CLOSEDPORT;
		goto dropwithreset;
	}
	if (tp->t_state == TCPS_CLOSED)
		goto drop;

	/* Unscale the window into a 32-bit value. */
	if ((thflags & TH_SYN) == 0)
		tiwin = th->th_win << tp->snd_scale;
	else
		tiwin = th->th_win;

	so = inp->inp_socket;
#ifdef MAC
	if (mac_check_socket_deliver(so, m))
		goto drop;
#endif
#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG) {
		ostate = tp->t_state;
		if (isipv6)
			bcopy((char *)ip6, (char *)tcp_saveipgen, sizeof(*ip6));
		else
			bcopy((char *)ip, (char *)tcp_saveipgen, sizeof(*ip));
		tcp_savetcp = *th;
	}
#endif
	if (so->so_options & SO_ACCEPTCONN) {
		struct in_conninfo inc;

#ifdef INET6
		inc.inc_isipv6 = isipv6;
#endif
		if (isipv6) {
			inc.inc6_faddr = ip6->ip6_src;
			inc.inc6_laddr = ip6->ip6_dst;
			inc.inc6_route.ro_rt = NULL;		/* XXX */
		} else {
			inc.inc_faddr = ip->ip_src;
			inc.inc_laddr = ip->ip_dst;
			inc.inc_route.ro_rt = NULL;		/* XXX */
		}
		inc.inc_fport = th->th_sport;
		inc.inc_lport = th->th_dport;

	        /*
	         * If the state is LISTEN then ignore segment if it contains
		 * a RST.  If the segment contains an ACK then it is bad and
		 * send a RST.  If it does not contain a SYN then it is not
		 * interesting; drop it.
		 *
		 * If the state is SYN_RECEIVED (syncache) and seg contains
		 * an ACK, but not for our SYN/ACK, send a RST.  If the seg
		 * contains a RST, check the sequence number to see if it
		 * is a valid reset segment.
		 */
		if ((thflags & (TH_RST|TH_ACK|TH_SYN)) != TH_SYN) {
			if ((thflags & (TH_RST|TH_ACK|TH_SYN)) == TH_ACK) {
				if (!syncache_expand(&inc, th, &so, m)) {
					/*
					 * No syncache entry, or ACK was not
					 * for our SYN/ACK.  Send a RST.
					 */
					tcpstat.tcps_badsyn++;
					rstreason = BANDLIM_RST_OPENPORT;
					goto dropwithreset;
				}
				if (so == NULL) {
					/*
					 * Could not complete 3-way handshake,
					 * connection is being closed down, and
					 * syncache will free mbuf.
					 */
					INP_UNLOCK(inp);
					INP_INFO_WUNLOCK(&tcbinfo);
					return;
				}
				/*
				 * Socket is created in state SYN_RECEIVED.
				 * Continue processing segment.
				 */
				INP_UNLOCK(inp);
				inp = sotoinpcb(so);
				INP_LOCK(inp);
				tp = intotcpcb(inp);
				/*
				 * This is what would have happened in
				 * tcp_output() when the SYN,ACK was sent.
				 */
				tp->snd_up = tp->snd_una;
				tp->snd_max = tp->snd_nxt = tp->iss + 1;
				tp->last_ack_sent = tp->rcv_nxt;
/*
 * XXX possible bug - it doesn't appear that tp->snd_wnd is unscaled
 * until the _second_ ACK is received:
 *    rcv SYN (set wscale opts)	 --> send SYN/ACK, set snd_wnd = window.
 *    rcv ACK, calculate tiwin --> process SYN_RECEIVED, determine wscale,
 *        move to ESTAB, set snd_wnd to tiwin.
 */        
				tp->snd_wnd = tiwin;	/* unscaled */
				goto after_listen;
			}
			if (thflags & TH_RST) {
				syncache_chkrst(&inc, th);
				goto drop;
			}
			if (thflags & TH_ACK) {
				syncache_badack(&inc);
				tcpstat.tcps_badsyn++;
				rstreason = BANDLIM_RST_OPENPORT;
				goto dropwithreset;
			}
			goto drop;
		}

		/*
		 * Segment's flags are (SYN) or (SYN|FIN).
		 */
#ifdef INET6
		/*
		 * If deprecated address is forbidden,
		 * we do not accept SYN to deprecated interface
		 * address to prevent any new inbound connection from
		 * getting established.
		 * When we do not accept SYN, we send a TCP RST,
		 * with deprecated source address (instead of dropping
		 * it).  We compromise it as it is much better for peer
		 * to send a RST, and RST will be the final packet
		 * for the exchange.
		 *
		 * If we do not forbid deprecated addresses, we accept
		 * the SYN packet.  RFC2462 does not suggest dropping
		 * SYN in this case.
		 * If we decipher RFC2462 5.5.4, it says like this:
		 * 1. use of deprecated addr with existing
		 *    communication is okay - "SHOULD continue to be
		 *    used"
		 * 2. use of it with new communication:
		 *   (2a) "SHOULD NOT be used if alternate address
		 *        with sufficient scope is available"
		 *   (2b) nothing mentioned otherwise.
		 * Here we fall into (2b) case as we have no choice in
		 * our source address selection - we must obey the peer.
		 *
		 * The wording in RFC2462 is confusing, and there are
		 * multiple description text for deprecated address
		 * handling - worse, they are not exactly the same.
		 * I believe 5.5.4 is the best one, so we follow 5.5.4.
		 */
		if (isipv6 && !ip6_use_deprecated) {
			struct in6_ifaddr *ia6;

			if ((ia6 = ip6_getdstifaddr(m)) &&
			    (ia6->ia6_flags & IN6_IFF_DEPRECATED)) {
				INP_UNLOCK(inp);
				tp = NULL;
				rstreason = BANDLIM_RST_OPENPORT;
				goto dropwithreset;
			}
		}
#endif
		/*
		 * If it is from this socket, drop it, it must be forged.
		 * Don't bother responding if the destination was a broadcast.
		 */
		if (th->th_dport == th->th_sport) {
			if (isipv6) {
				if (IN6_ARE_ADDR_EQUAL(&ip6->ip6_dst,
						       &ip6->ip6_src))
					goto drop;
			} else {
				if (ip->ip_dst.s_addr == ip->ip_src.s_addr)
					goto drop;
			}
		}
		/*
		 * RFC1122 4.2.3.10, p. 104: discard bcast/mcast SYN
		 *
		 * Note that it is quite possible to receive unicast
		 * link-layer packets with a broadcast IP address. Use
		 * in_broadcast() to find them.
		 */
		if (m->m_flags & (M_BCAST|M_MCAST))
			goto drop;
		if (isipv6) {
			if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst) ||
			    IN6_IS_ADDR_MULTICAST(&ip6->ip6_src))
				goto drop;
		} else {
			if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) ||
			    IN_MULTICAST(ntohl(ip->ip_src.s_addr)) ||
			    ip->ip_src.s_addr == htonl(INADDR_BROADCAST) ||
			    in_broadcast(ip->ip_dst, m->m_pkthdr.rcvif))
				goto drop;
		}
		/*
		 * SYN appears to be valid; create compressed TCP state
		 * for syncache, or perform t/tcp connection.
		 */
		if (so->so_qlen <= so->so_qlimit) {
			tcp_dooptions(&to, optp, optlen, 1);
			if (!syncache_add(&inc, &to, th, &so, m))
				goto drop;
			if (so == NULL) {
				/*
				 * Entry added to syncache, mbuf used to
				 * send SYN,ACK packet.
				 */
				KASSERT(headlocked, ("headlocked"));
				INP_UNLOCK(inp);
				INP_INFO_WUNLOCK(&tcbinfo);
				return;
			}
			/*
			 * Segment passed TAO tests.
			 */
			INP_UNLOCK(inp);
			inp = sotoinpcb(so);
			INP_LOCK(inp);
			tp = intotcpcb(inp);
			tp->snd_wnd = tiwin;
			tp->t_starttime = ticks;
			tp->t_state = TCPS_ESTABLISHED;

			/*
			 * If there is a FIN, or if there is data and the
			 * connection is local, then delay SYN,ACK(SYN) in
			 * the hope of piggy-backing it on a response
			 * segment.  Otherwise must send ACK now in case
			 * the other side is slow starting.
			 */
			if (DELAY_ACK(tp) &&
			    ((thflags & TH_FIN) ||
			     (tlen != 0 &&
			      ((isipv6 && in6_localaddr(&inp->in6p_faddr)) ||
			       (!isipv6 && in_localaddr(inp->inp_faddr)))))) {
				callout_reset(tp->tt_delack, tcp_delacktime,  
						tcp_timer_delack, tp);  
				tp->t_flags |= TF_NEEDSYN;
			} else 
				tp->t_flags |= (TF_ACKNOW | TF_NEEDSYN);

			tcpstat.tcps_connects++;
			soisconnected(so);
			goto trimthenstep6;
		}
		goto drop;
	}
after_listen:

/* XXX temp debugging */
	/* should not happen - syncache should pick up these connections */
	if (tp->t_state == TCPS_LISTEN)
		panic("tcp_input: TCPS_LISTEN");

	/*
	 * Segment received on connection.
	 * Reset idle time and keep-alive timer.
	 */
	tp->t_rcvtime = ticks;
	if (TCPS_HAVEESTABLISHED(tp->t_state))
		callout_reset(tp->tt_keep, tcp_keepidle, tcp_timer_keep, tp);

	/*
	 * Process options.
	 * XXX this is tradtitional behavior, may need to be cleaned up.
	 */
	tcp_dooptions(&to, optp, optlen, thflags & TH_SYN);
	if (thflags & TH_SYN) {
		if (to.to_flags & TOF_SCALE) {
			tp->t_flags |= TF_RCVD_SCALE;
			tp->requested_s_scale = to.to_requested_s_scale;
		}
		if (to.to_flags & TOF_TS) {
			tp->t_flags |= TF_RCVD_TSTMP;
			tp->ts_recent = to.to_tsval;
			tp->ts_recent_age = ticks;
		}
		if (to.to_flags & (TOF_CC|TOF_CCNEW))
			tp->t_flags |= TF_RCVD_CC;
		if (to.to_flags & TOF_MSS)
			tcp_mss(tp, to.to_mss);
	}

	/*
	 * Header prediction: check for the two common cases
	 * of a uni-directional data xfer.  If the packet has
	 * no control flags, is in-sequence, the window didn't
	 * change and we're not retransmitting, it's a
	 * candidate.  If the length is zero and the ack moved
	 * forward, we're the sender side of the xfer.  Just
	 * free the data acked & wake any higher level process
	 * that was blocked waiting for space.  If the length
	 * is non-zero and the ack didn't move, we're the
	 * receiver side.  If we're getting packets in-order
	 * (the reassembly queue is empty), add the data to
	 * the socket buffer and note that we need a delayed ack.
	 * Make sure that the hidden state-flags are also off.
	 * Since we check for TCPS_ESTABLISHED above, it can only
	 * be TH_NEEDSYN.
	 */
	if (tp->t_state == TCPS_ESTABLISHED &&
	    (thflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) == TH_ACK &&
	    ((tp->t_flags & (TF_NEEDSYN|TF_NEEDFIN)) == 0) &&
	    ((to.to_flags & TOF_TS) == 0 ||
	     TSTMP_GEQ(to.to_tsval, tp->ts_recent)) &&
	    /*
	     * Using the CC option is compulsory if once started:
	     *   the segment is OK if no T/TCP was negotiated or
	     *   if the segment has a CC option equal to CCrecv
	     */
	    ((tp->t_flags & (TF_REQ_CC|TF_RCVD_CC)) != (TF_REQ_CC|TF_RCVD_CC) ||
	     ((to.to_flags & TOF_CC) != 0 && to.to_cc == tp->cc_recv)) &&
	    th->th_seq == tp->rcv_nxt &&
	    tiwin && tiwin == tp->snd_wnd &&
	    tp->snd_nxt == tp->snd_max) {

		/*
		 * If last ACK falls within this segment's sequence numbers,
		 * record the timestamp.
		 * NOTE that the test is modified according to the latest
		 * proposal of the tcplw@cray.com list (Braden 1993/04/26).
		 */
		if ((to.to_flags & TOF_TS) != 0 &&
		    SEQ_LEQ(th->th_seq, tp->last_ack_sent)) {
			tp->ts_recent_age = ticks;
			tp->ts_recent = to.to_tsval;
		}

		if (tlen == 0) {
			if (SEQ_GT(th->th_ack, tp->snd_una) &&
			    SEQ_LEQ(th->th_ack, tp->snd_max) &&
			    tp->snd_cwnd >= tp->snd_wnd &&
			    ((!tcp_do_newreno &&
			      tp->t_dupacks < tcprexmtthresh) ||
			     (tcp_do_newreno &&
			      !SEQ_LT(tp->snd_una, tp->snd_recover)))) {
				KASSERT(headlocked, ("headlocked"));
				INP_INFO_WUNLOCK(&tcbinfo);
				headlocked = 0;
				/*
				 * this is a pure ack for outstanding data.
				 */
				++tcpstat.tcps_predack;
				/*
				 * "bad retransmit" recovery
				 */
				if (tp->t_rxtshift == 1 &&
				    ticks < tp->t_badrxtwin) {
					++tcpstat.tcps_sndrexmitbad;
					tp->snd_cwnd = tp->snd_cwnd_prev;
					tp->snd_ssthresh =
					    tp->snd_ssthresh_prev;
					tp->snd_high = tp->snd_high_prev;
					tp->snd_nxt = tp->snd_max;
					tp->t_badrxtwin = 0;
				}

				/*
				 * Recalculate the transmit timer / rtt.
				 *
				 * Some boxes send broken timestamp replies
				 * during the SYN+ACK phase, ignore 
				 * timestamps of 0 or we could calculate a
				 * huge RTT and blow up the retransmit timer.
				 */
				if ((to.to_flags & TOF_TS) != 0 &&
				    to.to_tsecr) {
					tcp_xmit_timer(tp,
					    ticks - to.to_tsecr + 1);
				} else if (tp->t_rtttime &&
					    SEQ_GT(th->th_ack, tp->t_rtseq)) {
					tcp_xmit_timer(tp,
							ticks - tp->t_rtttime);
				}
				tcp_xmit_bandwidth_limit(tp, th->th_ack);
				acked = th->th_ack - tp->snd_una;
				tcpstat.tcps_rcvackpack++;
				tcpstat.tcps_rcvackbyte += acked;
				sbdrop(&so->so_snd, acked);
				if (SEQ_GT(tp->snd_una, tp->snd_high) &&
				    SEQ_LEQ(th->th_ack, tp->snd_high))
					tp->snd_high = th->th_ack - 1;
				tp->snd_una = tp->snd_recover = th->th_ack;
				/*
				 * pull snd_wl2 up to prevent seq wrap relative
				 * to th_ack.
				 */
				tp->snd_wl2 = th->th_ack;
				tp->t_dupacks = 0;
				m_freem(m);
				ND6_HINT(tp); /* some progress has been done */

				/*
				 * If all outstanding data are acked, stop
				 * retransmit timer, otherwise restart timer
				 * using current (possibly backed-off) value.
				 * If process is waiting for space,
				 * wakeup/selwakeup/signal.  If data
				 * are ready to send, let tcp_output
				 * decide between more output or persist.
				 */
				if (tp->snd_una == tp->snd_max)
					callout_stop(tp->tt_rexmt);
				else if (!callout_active(tp->tt_persist))
					callout_reset(tp->tt_rexmt, 
						      tp->t_rxtcur,
						      tcp_timer_rexmt, tp);

				sowwakeup(so);
				if (so->so_snd.sb_cc)
					(void) tcp_output(tp);
				INP_UNLOCK(inp);
				return;
			}
		} else if (th->th_ack == tp->snd_una &&
		    LIST_EMPTY(&tp->t_segq) &&
		    tlen <= sbspace(&so->so_rcv)) {
			KASSERT(headlocked, ("headlocked"));
			INP_INFO_WUNLOCK(&tcbinfo);
			headlocked = 0;
			/*
			 * this is a pure, in-sequence data packet
			 * with nothing on the reassembly queue and
			 * we have enough buffer space to take it.
			 */
			++tcpstat.tcps_preddat;
			tp->rcv_nxt += tlen;
			/*
			 * Pull snd_wl1 up to prevent seq wrap relative to
			 * th_seq.
			 */
			tp->snd_wl1 = th->th_seq;
			/*
			 * Pull rcv_up up to prevent seq wrap relative to
			 * rcv_nxt.
			 */
			tp->rcv_up = tp->rcv_nxt;
			tcpstat.tcps_rcvpack++;
			tcpstat.tcps_rcvbyte += tlen;
			ND6_HINT(tp);	/* some progress has been done */
			/*
			 * Add data to socket buffer.
			 */
			if (so->so_state & SS_CANTRCVMORE) {
				m_freem(m);
			} else {
				m_adj(m, drop_hdrlen);	/* delayed header drop */
				sbappend(&so->so_rcv, m);
			}
			sorwakeup(so);
			if (DELAY_ACK(tp)) {
	                        callout_reset(tp->tt_delack, tcp_delacktime,
	                            tcp_timer_delack, tp);
			} else {
				tp->t_flags |= TF_ACKNOW;
				tcp_output(tp);
			}
			INP_UNLOCK(inp);
			return;
		}
	}

	/*
	 * Calculate amount of space in receive window,
	 * and then do TCP input processing.
	 * Receive window is amount of space in rcv queue,
	 * but not less than advertised window.
	 */
	{ int win;

	win = sbspace(&so->so_rcv);
	if (win < 0)
		win = 0;
	tp->rcv_wnd = imax(win, (int)(tp->rcv_adv - tp->rcv_nxt));
	}

	switch (tp->t_state) {

	/*
	 * If the state is SYN_RECEIVED:
	 *	if seg contains an ACK, but not for our SYN/ACK, send a RST.
	 */
	case TCPS_SYN_RECEIVED:
		if ((thflags & TH_ACK) &&
		    (SEQ_LEQ(th->th_ack, tp->snd_una) ||
		     SEQ_GT(th->th_ack, tp->snd_max))) {
				rstreason = BANDLIM_RST_OPENPORT;
				goto dropwithreset;
		}
		break;

	/*
	 * If the state is SYN_SENT:
	 *	if seg contains an ACK, but not for our SYN, drop the input.
	 *	if seg contains a RST, then drop the connection.
	 *	if seg does not contain SYN, then drop it.
	 * Otherwise this is an acceptable SYN segment
	 *	initialize tp->rcv_nxt and tp->irs
	 *	if seg contains ack then advance tp->snd_una
	 *	if SYN has been acked change to ESTABLISHED else SYN_RCVD state
	 *	arrange for segment to be acked (eventually)
	 *	continue processing rest of data/controls, beginning with URG
	 */
	case TCPS_SYN_SENT:
		if ((taop = tcp_gettaocache(&inp->inp_inc)) == NULL) {
			taop = &tao_noncached;
			bzero(taop, sizeof(*taop));
		}

		if ((thflags & TH_ACK) &&
		    (SEQ_LEQ(th->th_ack, tp->iss) ||
		     SEQ_GT(th->th_ack, tp->snd_max))) {
			/*
			 * If we have a cached CCsent for the remote host,
			 * hence we haven't just crashed and restarted,
			 * do not send a RST.  This may be a retransmission
			 * from the other side after our earlier ACK was lost.
			 * Our new SYN, when it arrives, will serve as the
			 * needed ACK.
			 */
			if (taop->tao_ccsent != 0)
				goto drop;
			else {
				rstreason = BANDLIM_UNLIMITED;
				goto dropwithreset;
			}
		}
		if (thflags & TH_RST) {
			if (thflags & TH_ACK)
				tp = tcp_drop(tp, ECONNREFUSED);
			goto drop;
		}
		if ((thflags & TH_SYN) == 0)
			goto drop;
		tp->snd_wnd = th->th_win;	/* initial send window */
		tp->cc_recv = to.to_cc;		/* foreign CC */

		tp->irs = th->th_seq;
		tcp_rcvseqinit(tp);
		if (thflags & TH_ACK) {
			/*
			 * Our SYN was acked.  If segment contains CC.ECHO
			 * option, check it to make sure this segment really
			 * matches our SYN.  If not, just drop it as old
			 * duplicate, but send an RST if we're still playing
			 * by the old rules.  If no CC.ECHO option, make sure
			 * we don't get fooled into using T/TCP.
			 */
			if (to.to_flags & TOF_CCECHO) {
				if (tp->cc_send != to.to_ccecho) {
					if (taop->tao_ccsent != 0)
						goto drop;
					else {
						rstreason = BANDLIM_UNLIMITED;
						goto dropwithreset;
					}
				}
			} else
				tp->t_flags &= ~TF_RCVD_CC;
			tcpstat.tcps_connects++;
			soisconnected(so);
#ifdef MAC
			mac_set_socket_peer_from_mbuf(m, so);
#endif
			/* Do window scaling on this connection? */
			if ((tp->t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) ==
				(TF_RCVD_SCALE|TF_REQ_SCALE)) {
				tp->snd_scale = tp->requested_s_scale;
				tp->rcv_scale = tp->request_r_scale;
			}
			/* Segment is acceptable, update cache if undefined. */
			if (taop->tao_ccsent == 0)
				taop->tao_ccsent = to.to_ccecho;

			tp->rcv_adv += tp->rcv_wnd;
			tp->snd_una++;		/* SYN is acked */
			/*
			 * If there's data, delay ACK; if there's also a FIN
			 * ACKNOW will be turned on later.
			 */
			if (DELAY_ACK(tp) && tlen != 0)
                                callout_reset(tp->tt_delack, tcp_delacktime,  
                                    tcp_timer_delack, tp);  
			else
				tp->t_flags |= TF_ACKNOW;
			/*
			 * Received <SYN,ACK> in SYN_SENT[*] state.
			 * Transitions:
			 *	SYN_SENT  --> ESTABLISHED
			 *	SYN_SENT* --> FIN_WAIT_1
			 */
			tp->t_starttime = ticks;
			if (tp->t_flags & TF_NEEDFIN) {
				tp->t_state = TCPS_FIN_WAIT_1;
				tp->t_flags &= ~TF_NEEDFIN;
				thflags &= ~TH_SYN;
			} else {
				tp->t_state = TCPS_ESTABLISHED;
				callout_reset(tp->tt_keep, tcp_keepidle,
					      tcp_timer_keep, tp);
			}
		} else {
			/*
		 	 * Received initial SYN in SYN-SENT[*] state =>
		 	 * simultaneous open.  If segment contains CC option
		 	 * and there is a cached CC, apply TAO test.
		 	 * If it succeeds, connection is * half-synchronized.
		 	 * Otherwise, do 3-way handshake:
		 	 *        SYN-SENT -> SYN-RECEIVED
		 	 *        SYN-SENT* -> SYN-RECEIVED*
		 	 * If there was no CC option, clear cached CC value.
		 	 */
			tp->t_flags |= TF_ACKNOW;
			callout_stop(tp->tt_rexmt);
			if (to.to_flags & TOF_CC) {
				if (taop->tao_cc != 0 &&
				    CC_GT(to.to_cc, taop->tao_cc)) {
					/*
					 * update cache and make transition:
					 *        SYN-SENT -> ESTABLISHED*
					 *        SYN-SENT* -> FIN-WAIT-1*
					 */
					taop->tao_cc = to.to_cc;
					tp->t_starttime = ticks;
					if (tp->t_flags & TF_NEEDFIN) {
						tp->t_state = TCPS_FIN_WAIT_1;
						tp->t_flags &= ~TF_NEEDFIN;
					} else {
						tp->t_state = TCPS_ESTABLISHED;
						callout_reset(tp->tt_keep,
							      tcp_keepidle,
							      tcp_timer_keep,
							      tp);
					}
					tp->t_flags |= TF_NEEDSYN;
				} else
					tp->t_state = TCPS_SYN_RECEIVED;
			} else {
				/* CC.NEW or no option => invalidate cache */
				taop->tao_cc = 0;
				tp->t_state = TCPS_SYN_RECEIVED;
			}
		}

trimthenstep6:
		/*
		 * Advance th->th_seq to correspond to first data byte.
		 * If data, trim to stay within window,
		 * dropping FIN if necessary.
		 */
		th->th_seq++;
		if (tlen > tp->rcv_wnd) {
			todrop = tlen - tp->rcv_wnd;
			m_adj(m, -todrop);
			tlen = tp->rcv_wnd;
			thflags &= ~TH_FIN;
			tcpstat.tcps_rcvpackafterwin++;
			tcpstat.tcps_rcvbyteafterwin += todrop;
		}
		tp->snd_wl1 = th->th_seq - 1;
		tp->rcv_up = th->th_seq;
		/*
		 * Client side of transaction: already sent SYN and data.
		 * If the remote host used T/TCP to validate the SYN,
		 * our data will be ACK'd; if so, enter normal data segment
		 * processing in the middle of step 5, ack processing.
		 * Otherwise, goto step 6.
		 */
 		if (thflags & TH_ACK)
			goto process_ACK;

		goto step6;

	/*
	 * If the state is LAST_ACK or CLOSING or TIME_WAIT:
	 *	if segment contains a SYN and CC [not CC.NEW] option:
	 *              if state == TIME_WAIT and connection duration > MSL,
	 *                  drop packet and send RST;
	 *
	 *		if SEG.CC > CCrecv then is new SYN, and can implicitly
	 *		    ack the FIN (and data) in retransmission queue.
	 *                  Complete close and delete TCPCB.  Then reprocess
	 *                  segment, hoping to find new TCPCB in LISTEN state;
	 *
	 *		else must be old SYN; drop it.
	 *      else do normal processing.
	 */
	case TCPS_LAST_ACK:
	case TCPS_CLOSING:
	case TCPS_TIME_WAIT:
		if ((thflags & TH_SYN) &&
		    (to.to_flags & TOF_CC) && tp->cc_recv != 0) {
			if (tp->t_state == TCPS_TIME_WAIT &&
					(ticks - tp->t_starttime) > tcp_msl) {
				rstreason = BANDLIM_UNLIMITED;
				goto dropwithreset;
			}
			if (CC_GT(to.to_cc, tp->cc_recv)) {
				tp = tcp_close(tp);
				goto findpcb;
			}
			else
				goto drop;
		}
 		break;  /* continue normal processing */
	}

	/*
	 * States other than LISTEN or SYN_SENT.
	 * First check the RST flag and sequence number since reset segments
	 * are exempt from the timestamp and connection count tests.  This
	 * fixes a bug introduced by the Stevens, vol. 2, p. 960 bugfix
	 * below which allowed reset segments in half the sequence space
	 * to fall though and be processed (which gives forged reset
	 * segments with a random sequence number a 50 percent chance of
	 * killing a connection).
	 * Then check timestamp, if present.
	 * Then check the connection count, if present.
	 * Then check that at least some bytes of segment are within
	 * receive window.  If segment begins before rcv_nxt,
	 * drop leading data (and SYN); if nothing left, just ack.
	 *
	 *
	 * If the RST bit is set, check the sequence number to see
	 * if this is a valid reset segment.
	 * RFC 793 page 37:
	 *   In all states except SYN-SENT, all reset (RST) segments
	 *   are validated by checking their SEQ-fields.  A reset is
	 *   valid if its sequence number is in the window.
	 * Note: this does not take into account delayed ACKs, so
	 *   we should test against last_ack_sent instead of rcv_nxt.
	 *   The sequence number in the reset segment is normally an
	 *   echo of our outgoing acknowlegement numbers, but some hosts
	 *   send a reset with the sequence number at the rightmost edge
	 *   of our receive window, and we have to handle this case.
	 * If we have multiple segments in flight, the intial reset
	 * segment sequence numbers will be to the left of last_ack_sent,
	 * but they will eventually catch up.
	 * In any case, it never made sense to trim reset segments to
	 * fit the receive window since RFC 1122 says:
	 *   4.2.2.12  RST Segment: RFC-793 Section 3.4
	 *
	 *    A TCP SHOULD allow a received RST segment to include data.
	 *
	 *    DISCUSSION
	 *         It has been suggested that a RST segment could contain
	 *         ASCII text that encoded and explained the cause of the
	 *         RST.  No standard has yet been established for such
	 *         data.
	 *
	 * If the reset segment passes the sequence number test examine
	 * the state:
	 *    SYN_RECEIVED STATE:
	 *	If passive open, return to LISTEN state.
	 *	If active open, inform user that connection was refused.
	 *    ESTABLISHED, FIN_WAIT_1, FIN_WAIT_2, CLOSE_WAIT STATES:
	 *	Inform user that connection was reset, and close tcb.
	 *    CLOSING, LAST_ACK STATES:
	 *	Close the tcb.
	 *    TIME_WAIT STATE:
	 *	Drop the segment - see Stevens, vol. 2, p. 964 and
	 *      RFC 1337.
	 */
	if (thflags & TH_RST) {
		if (SEQ_GEQ(th->th_seq, tp->last_ack_sent) &&
		    SEQ_LT(th->th_seq, tp->last_ack_sent + tp->rcv_wnd)) {
			switch (tp->t_state) {

			case TCPS_SYN_RECEIVED:
				so->so_error = ECONNREFUSED;
				goto close;

			case TCPS_ESTABLISHED:
			case TCPS_FIN_WAIT_1:
			case TCPS_FIN_WAIT_2:
			case TCPS_CLOSE_WAIT:
				so->so_error = ECONNRESET;
			close:
				tp->t_state = TCPS_CLOSED;
				tcpstat.tcps_drops++;
				tp = tcp_close(tp);
				break;

			case TCPS_CLOSING:
			case TCPS_LAST_ACK:
				tp = tcp_close(tp);
				break;

			case TCPS_TIME_WAIT:
				break;
			}
		}
		goto drop;
	}

	/*
	 * RFC 1323 PAWS: If we have a timestamp reply on this segment
	 * and it's less than ts_recent, drop it.
	 */
	if ((to.to_flags & TOF_TS) != 0 && tp->ts_recent &&
	    TSTMP_LT(to.to_tsval, tp->ts_recent)) {

		/* Check to see if ts_recent is over 24 days old.  */
		if ((int)(ticks - tp->ts_recent_age) > TCP_PAWS_IDLE) {
			/*
			 * Invalidate ts_recent.  If this segment updates
			 * ts_recent, the age will be reset later and ts_recent
			 * will get a valid value.  If it does not, setting
			 * ts_recent to zero will at least satisfy the
			 * requirement that zero be placed in the timestamp
			 * echo reply when ts_recent isn't valid.  The
			 * age isn't reset until we get a valid ts_recent
			 * because we don't want out-of-order segments to be
			 * dropped when ts_recent is old.
			 */
			tp->ts_recent = 0;
		} else {
			tcpstat.tcps_rcvduppack++;
			tcpstat.tcps_rcvdupbyte += tlen;
			tcpstat.tcps_pawsdrop++;
			if (tlen)
				goto dropafterack;
			goto drop;
		}
	}

	/*
	 * T/TCP mechanism
	 *   If T/TCP was negotiated and the segment doesn't have CC,
	 *   or if its CC is wrong then drop the segment.
	 *   RST segments do not have to comply with this.
	 */
	if ((tp->t_flags & (TF_REQ_CC|TF_RCVD_CC)) == (TF_REQ_CC|TF_RCVD_CC) &&
	    ((to.to_flags & TOF_CC) == 0 || tp->cc_recv != to.to_cc))
 		goto dropafterack;

	/*
	 * In the SYN-RECEIVED state, validate that the packet belongs to
	 * this connection before trimming the data to fit the receive
	 * window.  Check the sequence number versus IRS since we know
	 * the sequence numbers haven't wrapped.  This is a partial fix
	 * for the "LAND" DoS attack.
	 */
	if (tp->t_state == TCPS_SYN_RECEIVED && SEQ_LT(th->th_seq, tp->irs)) {
		rstreason = BANDLIM_RST_OPENPORT;
		goto dropwithreset;
	}

	todrop = tp->rcv_nxt - th->th_seq;
	if (todrop > 0) {
		if (thflags & TH_SYN) {
			thflags &= ~TH_SYN;
			th->th_seq++;
			if (th->th_urp > 1)
				th->th_urp--;
			else
				thflags &= ~TH_URG;
			todrop--;
		}
		/*
		 * Following if statement from Stevens, vol. 2, p. 960.
		 */
		if (todrop > tlen
		    || (todrop == tlen && (thflags & TH_FIN) == 0)) {
			/*
			 * Any valid FIN must be to the left of the window.
			 * At this point the FIN must be a duplicate or out
			 * of sequence; drop it.
			 */
			thflags &= ~TH_FIN;

			/*
			 * Send an ACK to resynchronize and drop any data.
			 * But keep on processing for RST or ACK.
			 */
			tp->t_flags |= TF_ACKNOW;
			todrop = tlen;
			tcpstat.tcps_rcvduppack++;
			tcpstat.tcps_rcvdupbyte += todrop;
		} else {
			tcpstat.tcps_rcvpartduppack++;
			tcpstat.tcps_rcvpartdupbyte += todrop;
		}
		drop_hdrlen += todrop;	/* drop from the top afterwards */
		th->th_seq += todrop;
		tlen -= todrop;
		if (th->th_urp > todrop)
			th->th_urp -= todrop;
		else {
			thflags &= ~TH_URG;
			th->th_urp = 0;
		}
	}

	/*
	 * If new data are received on a connection after the
	 * user processes are gone, then RST the other end.
	 */
	if ((so->so_state & SS_NOFDREF) &&
	    tp->t_state > TCPS_CLOSE_WAIT && tlen) {
		tp = tcp_close(tp);
		tcpstat.tcps_rcvafterclose++;
		rstreason = BANDLIM_UNLIMITED;
		goto dropwithreset;
	}

	/*
	 * If segment ends after window, drop trailing data
	 * (and PUSH and FIN); if nothing left, just ACK.
	 */
	todrop = (th->th_seq+tlen) - (tp->rcv_nxt+tp->rcv_wnd);
	if (todrop > 0) {
		tcpstat.tcps_rcvpackafterwin++;
		if (todrop >= tlen) {
			tcpstat.tcps_rcvbyteafterwin += tlen;
			/*
			 * If a new connection request is received
			 * while in TIME_WAIT, drop the old connection
			 * and start over if the sequence numbers
			 * are above the previous ones.
			 */
			if (thflags & TH_SYN &&
			    tp->t_state == TCPS_TIME_WAIT &&
			    SEQ_GT(th->th_seq, tp->rcv_nxt)) {
				tp = tcp_close(tp);
				goto findpcb;
			}
			/*
			 * If window is closed can only take segments at
			 * window edge, and have to drop data and PUSH from
			 * incoming segments.  Continue processing, but
			 * remember to ack.  Otherwise, drop segment
			 * and ack.
			 */
			if (tp->rcv_wnd == 0 && th->th_seq == tp->rcv_nxt) {
				tp->t_flags |= TF_ACKNOW;
				tcpstat.tcps_rcvwinprobe++;
			} else
				goto dropafterack;
		} else
			tcpstat.tcps_rcvbyteafterwin += todrop;
		m_adj(m, -todrop);
		tlen -= todrop;
		thflags &= ~(TH_PUSH|TH_FIN);
	}

	/*
	 * If last ACK falls within this segment's sequence numbers,
	 * record its timestamp.
	 * NOTE that the test is modified according to the latest
	 * proposal of the tcplw@cray.com list (Braden 1993/04/26).
	 */
	if ((to.to_flags & TOF_TS) != 0 &&
	    SEQ_LEQ(th->th_seq, tp->last_ack_sent)) {
		tp->ts_recent_age = ticks;
		tp->ts_recent = to.to_tsval;
	}

	/*
	 * If a SYN is in the window, then this is an
	 * error and we send an RST and drop the connection.
	 */
	if (thflags & TH_SYN) {
		tp = tcp_drop(tp, ECONNRESET);
		rstreason = BANDLIM_UNLIMITED;
		goto dropwithreset;
	}

	/*
	 * If the ACK bit is off:  if in SYN-RECEIVED state or SENDSYN
	 * flag is on (half-synchronized state), then queue data for
	 * later processing; else drop segment and return.
	 */
	if ((thflags & TH_ACK) == 0) {
		if (tp->t_state == TCPS_SYN_RECEIVED ||
		    (tp->t_flags & TF_NEEDSYN))
			goto step6;
		else
			goto drop;
	}

	/*
	 * Ack processing.
	 */
	switch (tp->t_state) {

	/*
	 * In SYN_RECEIVED state, the ack ACKs our SYN, so enter
	 * ESTABLISHED state and continue processing.
	 * The ACK was checked above.
	 */
	case TCPS_SYN_RECEIVED:

		tcpstat.tcps_connects++;
		soisconnected(so);
		/* Do window scaling? */
		if ((tp->t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) ==
			(TF_RCVD_SCALE|TF_REQ_SCALE)) {
			tp->snd_scale = tp->requested_s_scale;
			tp->rcv_scale = tp->request_r_scale;
		}
		/*
		 * Upon successful completion of 3-way handshake,
		 * update cache.CC if it was undefined, pass any queued
		 * data to the user, and advance state appropriately.
		 */
		if ((taop = tcp_gettaocache(&inp->inp_inc)) != NULL &&
		    taop->tao_cc == 0)
			taop->tao_cc = tp->cc_recv;

		/*
		 * Make transitions:
		 *      SYN-RECEIVED  -> ESTABLISHED
		 *      SYN-RECEIVED* -> FIN-WAIT-1
		 */
		tp->t_starttime = ticks;
		if (tp->t_flags & TF_NEEDFIN) {
			tp->t_state = TCPS_FIN_WAIT_1;
			tp->t_flags &= ~TF_NEEDFIN;
		} else {
			tp->t_state = TCPS_ESTABLISHED;
			callout_reset(tp->tt_keep, tcp_keepidle, 
				      tcp_timer_keep, tp);
		}
		/*
		 * If segment contains data or ACK, will call tcp_reass()
		 * later; if not, do so now to pass queued data to user.
		 */
		if (tlen == 0 && (thflags & TH_FIN) == 0)
			(void) tcp_reass(tp, (struct tcphdr *)0, 0,
			    (struct mbuf *)0);
		tp->snd_wl1 = th->th_seq - 1;
		/* FALLTHROUGH */

	/*
	 * In ESTABLISHED state: drop duplicate ACKs; ACK out of range
	 * ACKs.  If the ack is in the range
	 *	tp->snd_una < th->th_ack <= tp->snd_max
	 * then advance tp->snd_una to th->th_ack and drop
	 * data from the retransmission queue.  If this ACK reflects
	 * more up to date window information we update our window information.
	 */
	case TCPS_ESTABLISHED:
	case TCPS_FIN_WAIT_1:
	case TCPS_FIN_WAIT_2:
	case TCPS_CLOSE_WAIT:
	case TCPS_CLOSING:
	case TCPS_LAST_ACK:
	case TCPS_TIME_WAIT:

		if (SEQ_LEQ(th->th_ack, tp->snd_una)) {
			if (tlen == 0 && tiwin == tp->snd_wnd) {
				tcpstat.tcps_rcvdupack++;
				/*
				 * If we have outstanding data (other than
				 * a window probe), this is a completely
				 * duplicate ack (ie, window info didn't
				 * change), the ack is the biggest we've
				 * seen and we've seen exactly our rexmt
				 * threshhold of them, assume a packet
				 * has been dropped and retransmit it.
				 * Kludge snd_nxt & the congestion
				 * window so we send only this one
				 * packet.
				 *
				 * We know we're losing at the current
				 * window size so do congestion avoidance
				 * (set ssthresh to half the current window
				 * and pull our congestion window back to
				 * the new ssthresh).
				 *
				 * Dup acks mean that packets have left the
				 * network (they're now cached at the receiver)
				 * so bump cwnd by the amount in the receiver
				 * to keep a constant cwnd packets in the
				 * network.
				 */
				if (!callout_active(tp->tt_rexmt) ||
				    th->th_ack != tp->snd_una)
					tp->t_dupacks = 0;
				else if (++tp->t_dupacks > tcprexmtthresh ||
					 (tcp_do_newreno &&
					  SEQ_LT(tp->snd_una,
					  	 tp->snd_recover))) {
					tp->snd_cwnd += tp->t_maxseg;
					(void) tcp_output(tp);
					goto drop;
				} else if (tp->t_dupacks == tcprexmtthresh) {
					tcp_seq onxt = tp->snd_nxt;
					u_int win;
					if (tcp_do_newreno &&
					    SEQ_LEQ(th->th_ack, tp->snd_high)) {
						tp->t_dupacks = 0;
						break;
					}
					win = min(tp->snd_wnd, tp->snd_cwnd) /
					    2 / tp->t_maxseg;
					if (win < 2)
						win = 2;
					tp->snd_ssthresh = win * tp->t_maxseg;
					tp->snd_recover = tp->snd_max;
					callout_stop(tp->tt_rexmt);
					tp->t_rtttime = 0;
					tp->snd_nxt = th->th_ack;
					tp->snd_cwnd = tp->t_maxseg;
					(void) tcp_output(tp);
					tp->snd_cwnd = tp->snd_ssthresh +
						tp->t_maxseg * tp->t_dupacks;
					if (SEQ_GT(onxt, tp->snd_nxt))
						tp->snd_nxt = onxt;
					goto drop;
				}
			} else
				tp->t_dupacks = 0;
			break;
		}

		KASSERT(SEQ_GT(th->th_ack, tp->snd_una), ("th_ack <= snd_una"));

		/*
		 * If the congestion window was inflated to account
		 * for the other side's cached packets, retract it.
		 */
		if (tcp_do_newreno) {
			if (SEQ_LT(tp->snd_una, tp->snd_recover)) {
				if (SEQ_LT(th->th_ack, tp->snd_recover)) {
					tcp_newreno_partial_ack(tp, th);
				} else {
					/*
					 * Window inflation should have left us
					 * with approximately snd_ssthresh
					 * outstanding data.
					 * But in case we would be inclined to
					 * send a burst, better to do it via
					 * the slow start mechanism.
					 */
					if (SEQ_GT(th->th_ack +
							tp->snd_ssthresh,
						   tp->snd_max))
						tp->snd_cwnd = tp->snd_max -
								th->th_ack +
								tp->t_maxseg;
					else
						tp->snd_cwnd = tp->snd_ssthresh;
				}
			}
                } else {
                        if (tp->t_dupacks >= tcprexmtthresh &&
                            tp->snd_cwnd > tp->snd_ssthresh)
				tp->snd_cwnd = tp->snd_ssthresh;
                }
		tp->t_dupacks = 0;
		if (SEQ_GT(th->th_ack, tp->snd_max)) {
			tcpstat.tcps_rcvacktoomuch++;
			goto dropafterack;
		}
		/*
		 * If we reach this point, ACK is not a duplicate,
		 *     i.e., it ACKs something we sent.
		 */
		if (tp->t_flags & TF_NEEDSYN) {
			/*
			 * T/TCP: Connection was half-synchronized, and our
			 * SYN has been ACK'd (so connection is now fully
			 * synchronized).  Go to non-starred state,
			 * increment snd_una for ACK of SYN, and check if
			 * we can do window scaling.
			 */
			tp->t_flags &= ~TF_NEEDSYN;
			tp->snd_una++;
			/* Do window scaling? */
			if ((tp->t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) ==
				(TF_RCVD_SCALE|TF_REQ_SCALE)) {
				tp->snd_scale = tp->requested_s_scale;
				tp->rcv_scale = tp->request_r_scale;
			}
		}

process_ACK:
		acked = th->th_ack - tp->snd_una;
		tcpstat.tcps_rcvackpack++;
		tcpstat.tcps_rcvackbyte += acked;

		/*
		 * If we just performed our first retransmit, and the ACK
		 * arrives within our recovery window, then it was a mistake
		 * to do the retransmit in the first place.  Recover our
		 * original cwnd and ssthresh, and proceed to transmit where
		 * we left off.
		 */
		if (tp->t_rxtshift == 1 && ticks < tp->t_badrxtwin) {
			++tcpstat.tcps_sndrexmitbad;
			tp->snd_cwnd = tp->snd_cwnd_prev;
			tp->snd_ssthresh = tp->snd_ssthresh_prev;
			tp->snd_high = tp->snd_high_prev;
			tp->snd_nxt = tp->snd_max;
			tp->t_badrxtwin = 0;	/* XXX probably not required */ 
		}

		/*
		 * If we have a timestamp reply, update smoothed
		 * round trip time.  If no timestamp is present but
		 * transmit timer is running and timed sequence
		 * number was acked, update smoothed round trip time.
		 * Since we now have an rtt measurement, cancel the
		 * timer backoff (cf., Phil Karn's retransmit alg.).
		 * Recompute the initial retransmit timer.
		 *
		 * Some boxes send broken timestamp replies
		 * during the SYN+ACK phase, ignore 
		 * timestamps of 0 or we could calculate a
		 * huge RTT and blow up the retransmit timer.
		 */
		if ((to.to_flags & TOF_TS) != 0 &&
		    to.to_tsecr) {
			tcp_xmit_timer(tp, ticks - to.to_tsecr + 1);
		} else if (tp->t_rtttime && SEQ_GT(th->th_ack, tp->t_rtseq)) {
			tcp_xmit_timer(tp, ticks - tp->t_rtttime);
		}
		tcp_xmit_bandwidth_limit(tp, th->th_ack);

		/*
		 * If all outstanding data is acked, stop retransmit
		 * timer and remember to restart (more output or persist).
		 * If there is more data to be acked, restart retransmit
		 * timer, using current (possibly backed-off) value.
		 */
		if (th->th_ack == tp->snd_max) {
			callout_stop(tp->tt_rexmt);
			needoutput = 1;
		} else if (!callout_active(tp->tt_persist))
			callout_reset(tp->tt_rexmt, tp->t_rxtcur,
				      tcp_timer_rexmt, tp);

		/*
		 * If no data (only SYN) was ACK'd,
		 *    skip rest of ACK processing.
		 */
		if (acked == 0)
			goto step6;

		/*
		 * When new data is acked, open the congestion window.
		 * If the window gives us less than ssthresh packets
		 * in flight, open exponentially (maxseg per packet).
		 * Otherwise open linearly: maxseg per window
		 * (maxseg^2 / cwnd per packet).
		 */
		if (!tcp_do_newreno || SEQ_GEQ(tp->snd_una, tp->snd_recover)) {
			register u_int cw = tp->snd_cwnd;
			register u_int incr = tp->t_maxseg;
			if (cw > tp->snd_ssthresh)
				incr = incr * incr / cw;
			tp->snd_cwnd = min(cw+incr, TCP_MAXWIN<<tp->snd_scale);
		}
		if (acked > so->so_snd.sb_cc) {
			tp->snd_wnd -= so->so_snd.sb_cc;
			sbdrop(&so->so_snd, (int)so->so_snd.sb_cc);
			ourfinisacked = 1;
		} else {
			sbdrop(&so->so_snd, acked);
			tp->snd_wnd -= acked;
			ourfinisacked = 0;
		}
		sowwakeup(so);
		/* detect una wraparound */
		if (SEQ_GEQ(tp->snd_una, tp->snd_recover) &&
		    SEQ_LT(th->th_ack, tp->snd_recover))
			tp->snd_recover = th->th_ack;
		if (SEQ_GT(tp->snd_una, tp->snd_high) &&
		    SEQ_LEQ(th->th_ack, tp->snd_high))
			tp->snd_high = th->th_ack - 1;
		tp->snd_una = th->th_ack;
		if (SEQ_LT(tp->snd_nxt, tp->snd_una))
			tp->snd_nxt = tp->snd_una;

		switch (tp->t_state) {

		/*
		 * In FIN_WAIT_1 STATE in addition to the processing
		 * for the ESTABLISHED state if our FIN is now acknowledged
		 * then enter FIN_WAIT_2.
		 */
		case TCPS_FIN_WAIT_1:
			if (ourfinisacked) {
				/*
				 * If we can't receive any more
				 * data, then closing user can proceed.
				 * Starting the timer is contrary to the
				 * specification, but if we don't get a FIN
				 * we'll hang forever.
				 */
				if (so->so_state & SS_CANTRCVMORE) {
					soisdisconnected(so);
					callout_reset(tp->tt_2msl, tcp_maxidle,
						      tcp_timer_2msl, tp);
				}
				tp->t_state = TCPS_FIN_WAIT_2;
			}
			break;

	 	/*
		 * In CLOSING STATE in addition to the processing for
		 * the ESTABLISHED state if the ACK acknowledges our FIN
		 * then enter the TIME-WAIT state, otherwise ignore
		 * the segment.
		 */
		case TCPS_CLOSING:
			if (ourfinisacked) {
				tp->t_state = TCPS_TIME_WAIT;
				tcp_canceltimers(tp);
				/* Shorten TIME_WAIT [RFC-1644, p.28] */
				if (tp->cc_recv != 0 &&
				    (ticks - tp->t_starttime) < tcp_msl)
					callout_reset(tp->tt_2msl,
						      tp->t_rxtcur *
						      TCPTV_TWTRUNC,
						      tcp_timer_2msl, tp);
				else
					callout_reset(tp->tt_2msl, 2 * tcp_msl,
						      tcp_timer_2msl, tp);
				soisdisconnected(so);
			}
			break;

		/*
		 * In LAST_ACK, we may still be waiting for data to drain
		 * and/or to be acked, as well as for the ack of our FIN.
		 * If our FIN is now acknowledged, delete the TCB,
		 * enter the closed state and return.
		 */
		case TCPS_LAST_ACK:
			if (ourfinisacked) {
				tp = tcp_close(tp);
				goto drop;
			}
			break;

		/*
		 * In TIME_WAIT state the only thing that should arrive
		 * is a retransmission of the remote FIN.  Acknowledge
		 * it and restart the finack timer.
		 */
		case TCPS_TIME_WAIT:
			callout_reset(tp->tt_2msl, 2 * tcp_msl,
				      tcp_timer_2msl, tp);
			goto dropafterack;
		}
	}

step6:
	/*
	 * Update window information.
	 * Don't look at window if no ACK: TAC's send garbage on first SYN.
	 */
	if ((thflags & TH_ACK) &&
	    (SEQ_LT(tp->snd_wl1, th->th_seq) ||
	    (tp->snd_wl1 == th->th_seq && (SEQ_LT(tp->snd_wl2, th->th_ack) ||
	     (tp->snd_wl2 == th->th_ack && tiwin > tp->snd_wnd))))) {
		/* keep track of pure window updates */
		if (tlen == 0 &&
		    tp->snd_wl2 == th->th_ack && tiwin > tp->snd_wnd)
			tcpstat.tcps_rcvwinupd++;
		tp->snd_wnd = tiwin;
		tp->snd_wl1 = th->th_seq;
		tp->snd_wl2 = th->th_ack;
		if (tp->snd_wnd > tp->max_sndwnd)
			tp->max_sndwnd = tp->snd_wnd;
		needoutput = 1;
	}

	/*
	 * Process segments with URG.
	 */
	if ((thflags & TH_URG) && th->th_urp &&
	    TCPS_HAVERCVDFIN(tp->t_state) == 0) {
		/*
		 * This is a kludge, but if we receive and accept
		 * random urgent pointers, we'll crash in
		 * soreceive.  It's hard to imagine someone
		 * actually wanting to send this much urgent data.
		 */
		if (th->th_urp + so->so_rcv.sb_cc > sb_max) {
			th->th_urp = 0;			/* XXX */
			thflags &= ~TH_URG;		/* XXX */
			goto dodata;			/* XXX */
		}
		/*
		 * If this segment advances the known urgent pointer,
		 * then mark the data stream.  This should not happen
		 * in CLOSE_WAIT, CLOSING, LAST_ACK or TIME_WAIT STATES since
		 * a FIN has been received from the remote side.
		 * In these states we ignore the URG.
		 *
		 * According to RFC961 (Assigned Protocols),
		 * the urgent pointer points to the last octet
		 * of urgent data.  We continue, however,
		 * to consider it to indicate the first octet
		 * of data past the urgent section as the original
		 * spec states (in one of two places).
		 */
		if (SEQ_GT(th->th_seq+th->th_urp, tp->rcv_up)) {
			tp->rcv_up = th->th_seq + th->th_urp;
			so->so_oobmark = so->so_rcv.sb_cc +
			    (tp->rcv_up - tp->rcv_nxt) - 1;
			if (so->so_oobmark == 0)
				so->so_state |= SS_RCVATMARK;
			sohasoutofband(so);
			tp->t_oobflags &= ~(TCPOOB_HAVEDATA | TCPOOB_HADDATA);
		}
		/*
		 * Remove out of band data so doesn't get presented to user.
		 * This can happen independent of advancing the URG pointer,
		 * but if two URG's are pending at once, some out-of-band
		 * data may creep in... ick.
		 */
		if (th->th_urp <= (u_long)tlen &&
		    !(so->so_options & SO_OOBINLINE)) {
			/* hdr drop is delayed */
			tcp_pulloutofband(so, th, m, drop_hdrlen);
		}
	} else {
		/*
		 * If no out of band data is expected,
		 * pull receive urgent pointer along
		 * with the receive window.
		 */
		if (SEQ_GT(tp->rcv_nxt, tp->rcv_up))
			tp->rcv_up = tp->rcv_nxt;
	}
dodata:							/* XXX */
	KASSERT(headlocked, ("headlocked"));
	INP_INFO_WUNLOCK(&tcbinfo);
	headlocked = 0;
	/*
	 * Process the segment text, merging it into the TCP sequencing queue,
	 * and arranging for acknowledgment of receipt if necessary.
	 * This process logically involves adjusting tp->rcv_wnd as data
	 * is presented to the user (this happens in tcp_usrreq.c,
	 * case PRU_RCVD).  If a FIN has already been received on this
	 * connection then we just ignore the text.
	 */
	if ((tlen || (thflags & TH_FIN)) &&
	    TCPS_HAVERCVDFIN(tp->t_state) == 0) {
		m_adj(m, drop_hdrlen);	/* delayed header drop */
		/*
		 * Insert segment which includes th into TCP reassembly queue
		 * with control block tp.  Set thflags to whether reassembly now
		 * includes a segment with FIN.  This handles the common case
		 * inline (segment is the next to be received on an established
		 * connection, and the queue is empty), avoiding linkage into
		 * and removal from the queue and repetition of various
		 * conversions.
		 * Set DELACK for segments received in order, but ack
		 * immediately when segments are out of order (so
		 * fast retransmit can work).
		 */
		if (th->th_seq == tp->rcv_nxt &&
		    LIST_EMPTY(&tp->t_segq) &&
		    TCPS_HAVEESTABLISHED(tp->t_state)) {
			if (DELAY_ACK(tp))
				callout_reset(tp->tt_delack, tcp_delacktime,
					      tcp_timer_delack, tp);
			else
				tp->t_flags |= TF_ACKNOW;
			tp->rcv_nxt += tlen;
			thflags = th->th_flags & TH_FIN;
			tcpstat.tcps_rcvpack++;
			tcpstat.tcps_rcvbyte += tlen;
			ND6_HINT(tp);
			if (so->so_state & SS_CANTRCVMORE)
				m_freem(m);
			else
				sbappend(&so->so_rcv, m);
			sorwakeup(so);
		} else {
			thflags = tcp_reass(tp, th, &tlen, m);
			tp->t_flags |= TF_ACKNOW;
		}

		/*
		 * Note the amount of data that peer has sent into
		 * our window, in order to estimate the sender's
		 * buffer size.
		 */
		len = so->so_rcv.sb_hiwat - (tp->rcv_adv - tp->rcv_nxt);
	} else {
		m_freem(m);
		thflags &= ~TH_FIN;
	}

	/*
	 * If FIN is received ACK the FIN and let the user know
	 * that the connection is closing.
	 */
	if (thflags & TH_FIN) {
		if (TCPS_HAVERCVDFIN(tp->t_state) == 0) {
			socantrcvmore(so);
			/*
			 * If connection is half-synchronized
			 * (ie NEEDSYN flag on) then delay ACK,
			 * so it may be piggybacked when SYN is sent.
			 * Otherwise, since we received a FIN then no
			 * more input can be expected, send ACK now.
			 */
			if (DELAY_ACK(tp) && (tp->t_flags & TF_NEEDSYN))
                                callout_reset(tp->tt_delack, tcp_delacktime,  
                                    tcp_timer_delack, tp);  
			else
				tp->t_flags |= TF_ACKNOW;
			tp->rcv_nxt++;
		}
		switch (tp->t_state) {

	 	/*
		 * In SYN_RECEIVED and ESTABLISHED STATES
		 * enter the CLOSE_WAIT state.
		 */
		case TCPS_SYN_RECEIVED:
			tp->t_starttime = ticks;
			/*FALLTHROUGH*/
		case TCPS_ESTABLISHED:
			tp->t_state = TCPS_CLOSE_WAIT;
			break;

	 	/*
		 * If still in FIN_WAIT_1 STATE FIN has not been acked so
		 * enter the CLOSING state.
		 */
		case TCPS_FIN_WAIT_1:
			tp->t_state = TCPS_CLOSING;
			break;

	 	/*
		 * In FIN_WAIT_2 state enter the TIME_WAIT state,
		 * starting the time-wait timer, turning off the other
		 * standard timers.
		 */
		case TCPS_FIN_WAIT_2:
			tp->t_state = TCPS_TIME_WAIT;
			tcp_canceltimers(tp);
			/* Shorten TIME_WAIT [RFC-1644, p.28] */
			if (tp->cc_recv != 0 &&
			    (ticks - tp->t_starttime) < tcp_msl) {
				callout_reset(tp->tt_2msl,
					      tp->t_rxtcur * TCPTV_TWTRUNC,
					      tcp_timer_2msl, tp);
				/* For transaction client, force ACK now. */
				tp->t_flags |= TF_ACKNOW;
			}
			else
				callout_reset(tp->tt_2msl, 2 * tcp_msl,
					      tcp_timer_2msl, tp);
			soisdisconnected(so);
			break;

		/*
		 * In TIME_WAIT state restart the 2 MSL time_wait timer.
		 */
		case TCPS_TIME_WAIT:
			callout_reset(tp->tt_2msl, 2 * tcp_msl,
				      tcp_timer_2msl, tp);
			break;
		}
	}
#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG)
		tcp_trace(TA_INPUT, ostate, tp, (void *)tcp_saveipgen,
			  &tcp_savetcp, 0);
#endif

	/*
	 * Return any desired output.
	 */
	if (needoutput || (tp->t_flags & TF_ACKNOW))
		(void) tcp_output(tp);
	INP_UNLOCK(inp);
	return;

dropafterack:
	/*
	 * Generate an ACK dropping incoming segment if it occupies
	 * sequence space, where the ACK reflects our state.
	 *
	 * We can now skip the test for the RST flag since all
	 * paths to this code happen after packets containing
	 * RST have been dropped.
	 *
	 * In the SYN-RECEIVED state, don't send an ACK unless the
	 * segment we received passes the SYN-RECEIVED ACK test.
	 * If it fails send a RST.  This breaks the loop in the
	 * "LAND" DoS attack, and also prevents an ACK storm
	 * between two listening ports that have been sent forged
	 * SYN segments, each with the source address of the other.
	 */
	if (tp->t_state == TCPS_SYN_RECEIVED && (thflags & TH_ACK) &&
	    (SEQ_GT(tp->snd_una, th->th_ack) ||
	     SEQ_GT(th->th_ack, tp->snd_max)) ) {
		rstreason = BANDLIM_RST_OPENPORT;
		goto dropwithreset;
	}
#ifdef TCPDEBUG
	if (so->so_options & SO_DEBUG)
		tcp_trace(TA_DROP, ostate, tp, (void *)tcp_saveipgen,
			  &tcp_savetcp, 0);
#endif
	if (headlocked)
		INP_INFO_WUNLOCK(&tcbinfo);
	m_freem(m);
	tp->t_flags |= TF_ACKNOW;
	(void) tcp_output(tp);
	INP_UNLOCK(inp);
	return;

dropwithreset:
	/*
	 * Generate a RST, dropping incoming segment.
	 * Make ACK acceptable to originator of segment.
	 * Don't bother to respond if destination was broadcast/multicast.
	 */
	if ((thflags & TH_RST) || m->m_flags & (M_BCAST|M_MCAST))
		goto drop;
	if (isipv6) {
		if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst) ||
		    IN6_IS_ADDR_MULTICAST(&ip6->ip6_src))
			goto drop;
	} else {
		if (IN_MULTICAST(ntohl(ip->ip_dst.s_addr)) ||
		    IN_MULTICAST(ntohl(ip->ip_src.s_addr)) ||
	    	    ip->ip_src.s_addr == htonl(INADDR_BROADCAST) ||
	    	    in_broadcast(ip->ip_dst, m->m_pkthdr.rcvif))
			goto drop;
	}
	/* IPv6 anycast check is done at tcp6_input() */

	/*
	 * Perform bandwidth limiting.
	 */
	if (badport_bandlim(rstreason) < 0)
		goto drop;
 
#ifdef TCPDEBUG
	if (tp == 0 || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_DROP, ostate, tp, (void *)tcp_saveipgen,
			  &tcp_savetcp, 0);
#endif

	if (tp)
		INP_UNLOCK(inp);

	if (thflags & TH_ACK)
		/* mtod() below is safe as long as hdr dropping is delayed */
		tcp_respond(tp, mtod(m, void *), th, m, (tcp_seq)0, th->th_ack,
			    TH_RST);
	else {
		if (thflags & TH_SYN)
			tlen++;
		/* mtod() below is safe as long as hdr dropping is delayed */
		tcp_respond(tp, mtod(m, void *), th, m, th->th_seq+tlen,
			    (tcp_seq)0, TH_RST|TH_ACK);
	}
	if (headlocked)
		INP_INFO_WUNLOCK(&tcbinfo);
	return;

drop:
	/*
	 * Drop space held by incoming segment and return.
	 */
#ifdef TCPDEBUG
	if (tp == 0 || (tp->t_inpcb->inp_socket->so_options & SO_DEBUG))
		tcp_trace(TA_DROP, ostate, tp, (void *)tcp_saveipgen,
			  &tcp_savetcp, 0);
#endif
	if (tp)
		INP_UNLOCK(inp);
	m_freem(m);
	if (headlocked)
		INP_INFO_WUNLOCK(&tcbinfo);
	return;
}

/*
 * Parse TCP options and place in tcpopt.
 */
static void
tcp_dooptions(to, cp, cnt, is_syn)
	struct tcpopt *to;
	u_char *cp;
	int cnt;
{
	int opt, optlen;

	to->to_flags = 0;
	for (; cnt > 0; cnt -= optlen, cp += optlen) {
		opt = cp[0];
		if (opt == TCPOPT_EOL)
			break;
		if (opt == TCPOPT_NOP)
			optlen = 1;
		else {
			if (cnt < 2)
				break;
			optlen = cp[1];
			if (optlen < 2 || optlen > cnt)
				break;
		}
		switch (opt) {
		case TCPOPT_MAXSEG:
			if (optlen != TCPOLEN_MAXSEG)
				continue;
			if (!is_syn)
				continue;
			to->to_flags |= TOF_MSS;
			bcopy((char *)cp + 2,
			    (char *)&to->to_mss, sizeof(to->to_mss));
			to->to_mss = ntohs(to->to_mss);
			break;
		case TCPOPT_WINDOW:
			if (optlen != TCPOLEN_WINDOW)
				continue;
			if (! is_syn)
				continue;
			to->to_flags |= TOF_SCALE;
			to->to_requested_s_scale = min(cp[2], TCP_MAX_WINSHIFT);
			break;
		case TCPOPT_TIMESTAMP:
			if (optlen != TCPOLEN_TIMESTAMP)
				continue;
			to->to_flags |= TOF_TS;
			bcopy((char *)cp + 2,
			    (char *)&to->to_tsval, sizeof(to->to_tsval));
			to->to_tsval = ntohl(to->to_tsval);
			bcopy((char *)cp + 6,
			    (char *)&to->to_tsecr, sizeof(to->to_tsecr));
			to->to_tsecr = ntohl(to->to_tsecr);
			break;
		case TCPOPT_CC:
			if (optlen != TCPOLEN_CC)
				continue;
			to->to_flags |= TOF_CC;
			bcopy((char *)cp + 2,
			    (char *)&to->to_cc, sizeof(to->to_cc));
			to->to_cc = ntohl(to->to_cc);
			break;
		case TCPOPT_CCNEW:
			if (optlen != TCPOLEN_CC)
				continue;
			if (!is_syn)
				continue;
			to->to_flags |= TOF_CCNEW;
			bcopy((char *)cp + 2,
			    (char *)&to->to_cc, sizeof(to->to_cc));
			to->to_cc = ntohl(to->to_cc);
			break;
		case TCPOPT_CCECHO:
			if (optlen != TCPOLEN_CC)
				continue;
			if (!is_syn)
				continue;
			to->to_flags |= TOF_CCECHO;
			bcopy((char *)cp + 2,
			    (char *)&to->to_ccecho, sizeof(to->to_ccecho));
			to->to_ccecho = ntohl(to->to_ccecho);
			break;
		default:
			continue;
		}
	}
}

/*
 * Pull out of band byte out of a segment so
 * it doesn't appear in the user's data queue.
 * It is still reflected in the segment length for
 * sequencing purposes.
 */
static void
tcp_pulloutofband(so, th, m, off)
	struct socket *so;
	struct tcphdr *th;
	register struct mbuf *m;
	int off;		/* delayed to be droped hdrlen */
{
	int cnt = off + th->th_urp - 1;

	while (cnt >= 0) {
		if (m->m_len > cnt) {
			char *cp = mtod(m, caddr_t) + cnt;
			struct tcpcb *tp = sototcpcb(so);

			tp->t_iobc = *cp;
			tp->t_oobflags |= TCPOOB_HAVEDATA;
			bcopy(cp+1, cp, (unsigned)(m->m_len - cnt - 1));
			m->m_len--;
			if (m->m_flags & M_PKTHDR)
				m->m_pkthdr.len--;
			return;
		}
		cnt -= m->m_len;
		m = m->m_next;
		if (m == 0)
			break;
	}
	panic("tcp_pulloutofband");
}

/*
 * Collect new round-trip time estimate
 * and update averages and current timeout.
 */
static void
tcp_xmit_timer(tp, rtt)
	register struct tcpcb *tp;
	int rtt;
{
	register int delta;

	tcpstat.tcps_rttupdated++;
	tp->t_rttupdated++;
	if (tp->t_srtt != 0) {
		/*
		 * srtt is stored as fixed point with 5 bits after the
		 * binary point (i.e., scaled by 8).  The following magic
		 * is equivalent to the smoothing algorithm in rfc793 with
		 * an alpha of .875 (srtt = rtt/8 + srtt*7/8 in fixed
		 * point).  Adjust rtt to origin 0.
		 */
		delta = ((rtt - 1) << TCP_DELTA_SHIFT)
			- (tp->t_srtt >> (TCP_RTT_SHIFT - TCP_DELTA_SHIFT));

		if ((tp->t_srtt += delta) <= 0)
			tp->t_srtt = 1;

		/*
		 * We accumulate a smoothed rtt variance (actually, a
		 * smoothed mean difference), then set the retransmit
		 * timer to smoothed rtt + 4 times the smoothed variance.
		 * rttvar is stored as fixed point with 4 bits after the
		 * binary point (scaled by 16).  The following is
		 * equivalent to rfc793 smoothing with an alpha of .75
		 * (rttvar = rttvar*3/4 + |delta| / 4).  This replaces
		 * rfc793's wired-in beta.
		 */
		if (delta < 0)
			delta = -delta;
		delta -= tp->t_rttvar >> (TCP_RTTVAR_SHIFT - TCP_DELTA_SHIFT);
		if ((tp->t_rttvar += delta) <= 0)
			tp->t_rttvar = 1;
		if (tp->t_rttbest > tp->t_srtt + tp->t_rttvar)
		    tp->t_rttbest = tp->t_srtt + tp->t_rttvar;
	} else {
		/*
		 * No rtt measurement yet - use the unsmoothed rtt.
		 * Set the variance to half the rtt (so our first
		 * retransmit happens at 3*rtt).
		 */
		tp->t_srtt = rtt << TCP_RTT_SHIFT;
		tp->t_rttvar = rtt << (TCP_RTTVAR_SHIFT - 1);
		tp->t_rttbest = tp->t_srtt + tp->t_rttvar;
	}
	tp->t_rtttime = 0;
	tp->t_rxtshift = 0;

	/*
	 * the retransmit should happen at rtt + 4 * rttvar.
	 * Because of the way we do the smoothing, srtt and rttvar
	 * will each average +1/2 tick of bias.  When we compute
	 * the retransmit timer, we want 1/2 tick of rounding and
	 * 1 extra tick because of +-1/2 tick uncertainty in the
	 * firing of the timer.  The bias will give us exactly the
	 * 1.5 tick we need.  But, because the bias is
	 * statistical, we have to test that we don't drop below
	 * the minimum feasible timer (which is 2 ticks).
	 */
	TCPT_RANGESET(tp->t_rxtcur, TCP_REXMTVAL(tp),
		      max(tp->t_rttmin, rtt + 2), TCPTV_REXMTMAX);

	/*
	 * We received an ack for a packet that wasn't retransmitted;
	 * it is probably safe to discard any error indications we've
	 * received recently.  This isn't quite right, but close enough
	 * for now (a route might have failed after we sent a segment,
	 * and the return path might not be symmetrical).
	 */
	tp->t_softerror = 0;
}

/*
 * Determine a reasonable value for maxseg size.
 * If the route is known, check route for mtu.
 * If none, use an mss that can be handled on the outgoing
 * interface without forcing IP to fragment; if bigger than
 * an mbuf cluster (MCLBYTES), round down to nearest multiple of MCLBYTES
 * to utilize large mbufs.  If no route is found, route has no mtu,
 * or the destination isn't local, use a default, hopefully conservative
 * size (usually 512 or the default IP max size, but no more than the mtu
 * of the interface), as we can't discover anything about intervening
 * gateways or networks.  We also initialize the congestion/slow start
 * window to be a single segment if the destination isn't local.
 * While looking at the routing entry, we also initialize other path-dependent
 * parameters from pre-set or cached values in the routing entry.
 *
 * Also take into account the space needed for options that we
 * send regularly.  Make maxseg shorter by that amount to assure
 * that we can send maxseg amount of data even when the options
 * are present.  Store the upper limit of the length of options plus
 * data in maxopd.
 *
 * NOTE that this routine is only called when we process an incoming
 * segment, for outgoing segments only tcp_mssopt is called.
 *
 * In case of T/TCP, we call this routine during implicit connection
 * setup as well (offer = -1), to initialize maxseg from the cached
 * MSS of our peer.
 */
void
tcp_mss(tp, offer)
	struct tcpcb *tp;
	int offer;
{
	register struct rtentry *rt;
	struct ifnet *ifp;
	register int rtt, mss;
	u_long bufsize;
	struct inpcb *inp = tp->t_inpcb;
	struct socket *so;
	struct rmxp_tao *taop;
	int origoffer = offer;
#ifdef INET6
	int isipv6 = ((inp->inp_vflag & INP_IPV6) != 0) ? 1 : 0;
	size_t min_protoh = isipv6 ?
			    sizeof (struct ip6_hdr) + sizeof (struct tcphdr) :
			    sizeof (struct tcpiphdr);
#else
	const int isipv6 = 0;
	const size_t min_protoh = sizeof (struct tcpiphdr);
#endif

	if (isipv6)
		rt = tcp_rtlookup6(&inp->inp_inc);
	else
		rt = tcp_rtlookup(&inp->inp_inc);
	if (rt == NULL) {
		tp->t_maxopd = tp->t_maxseg =
				isipv6 ? tcp_v6mssdflt : tcp_mssdflt;
		return;
	}
	ifp = rt->rt_ifp;
	so = inp->inp_socket;

	taop = rmx_taop(rt->rt_rmx);
	/*
	 * Offer == -1 means that we didn't receive SYN yet,
	 * use cached value in that case;
	 */
	if (offer == -1)
		offer = taop->tao_mssopt;
	/*
	 * Offer == 0 means that there was no MSS on the SYN segment,
	 * in this case we use tcp_mssdflt.
	 */
	if (offer == 0)
		offer = isipv6 ? tcp_v6mssdflt : tcp_mssdflt;
	else
		/*
		 * Sanity check: make sure that maxopd will be large
		 * enough to allow some data on segments even is the
		 * all the option space is used (40bytes).  Otherwise
		 * funny things may happen in tcp_output.
		 */
		offer = max(offer, 64);
	taop->tao_mssopt = offer;

	/*
	 * While we're here, check if there's an initial rtt
	 * or rttvar.  Convert from the route-table units
	 * to scaled multiples of the slow timeout timer.
	 */
	if (tp->t_srtt == 0 && (rtt = rt->rt_rmx.rmx_rtt)) {
		/*
		 * XXX the lock bit for RTT indicates that the value
		 * is also a minimum value; this is subject to time.
		 */
		if (rt->rt_rmx.rmx_locks & RTV_RTT)
			tp->t_rttmin = rtt / (RTM_RTTUNIT / hz);
		tp->t_srtt = rtt / (RTM_RTTUNIT / (hz * TCP_RTT_SCALE));
		tp->t_rttbest = tp->t_srtt + TCP_RTT_SCALE;
		tcpstat.tcps_usedrtt++;
		if (rt->rt_rmx.rmx_rttvar) {
			tp->t_rttvar = rt->rt_rmx.rmx_rttvar /
			    (RTM_RTTUNIT / (hz * TCP_RTTVAR_SCALE));
			tcpstat.tcps_usedrttvar++;
		} else {
			/* default variation is +- 1 rtt */
			tp->t_rttvar =
			    tp->t_srtt * TCP_RTTVAR_SCALE / TCP_RTT_SCALE;
		}
		TCPT_RANGESET(tp->t_rxtcur,
			      ((tp->t_srtt >> 2) + tp->t_rttvar) >> 1,
			      tp->t_rttmin, TCPTV_REXMTMAX);
	}
	/*
	 * if there's an mtu associated with the route, use it
	 * else, use the link mtu.
	 */
	if (rt->rt_rmx.rmx_mtu)
		mss = rt->rt_rmx.rmx_mtu - min_protoh;
	else {
		if (isipv6) {
			mss = nd_ifinfo[rt->rt_ifp->if_index].linkmtu -
				min_protoh;
			if (!in6_localaddr(&inp->in6p_faddr))
				mss = min(mss, tcp_v6mssdflt);
		} else {
			mss = ifp->if_mtu - min_protoh;
			if (!in_localaddr(inp->inp_faddr))
				mss = min(mss, tcp_mssdflt);
		}
	}
	mss = min(mss, offer);
	/*
	 * maxopd stores the maximum length of data AND options
	 * in a segment; maxseg is the amount of data in a normal
	 * segment.  We need to store this value (maxopd) apart
	 * from maxseg, because now every segment carries options
	 * and thus we normally have somewhat less data in segments.
	 */
	tp->t_maxopd = mss;

	/*
	 * In case of T/TCP, origoffer==-1 indicates, that no segments
	 * were received yet.  In this case we just guess, otherwise
	 * we do the same as before T/TCP.
	 */
 	if ((tp->t_flags & (TF_REQ_TSTMP|TF_NOOPT)) == TF_REQ_TSTMP &&
	    (origoffer == -1 ||
	     (tp->t_flags & TF_RCVD_TSTMP) == TF_RCVD_TSTMP))
		mss -= TCPOLEN_TSTAMP_APPA;
 	if ((tp->t_flags & (TF_REQ_CC|TF_NOOPT)) == TF_REQ_CC &&
	    (origoffer == -1 ||
	     (tp->t_flags & TF_RCVD_CC) == TF_RCVD_CC))
		mss -= TCPOLEN_CC_APPA;

#if	(MCLBYTES & (MCLBYTES - 1)) == 0
		if (mss > MCLBYTES)
			mss &= ~(MCLBYTES-1);
#else
		if (mss > MCLBYTES)
			mss = mss / MCLBYTES * MCLBYTES;
#endif
	/*
	 * If there's a pipesize, change the socket buffer
	 * to that size.  Make the socket buffers an integral
	 * number of mss units; if the mss is larger than
	 * the socket buffer, decrease the mss.
	 */
#ifdef RTV_SPIPE
	if ((bufsize = rt->rt_rmx.rmx_sendpipe) == 0)
#endif
		bufsize = so->so_snd.sb_hiwat;
	if (bufsize < mss)
		mss = bufsize;
	else {
		bufsize = roundup(bufsize, mss);
		if (bufsize > sb_max)
			bufsize = sb_max;
		if (bufsize > so->so_snd.sb_hiwat)
			(void)sbreserve(&so->so_snd, bufsize, so, NULL);
	}
	tp->t_maxseg = mss;

#ifdef RTV_RPIPE
	if ((bufsize = rt->rt_rmx.rmx_recvpipe) == 0)
#endif
		bufsize = so->so_rcv.sb_hiwat;
	if (bufsize > mss) {
		bufsize = roundup(bufsize, mss);
		if (bufsize > sb_max)
			bufsize = sb_max;
		if (bufsize > so->so_rcv.sb_hiwat)
			(void)sbreserve(&so->so_rcv, bufsize, so, NULL);
	}

	/*
	 * Set the slow-start flight size depending on whether this
	 * is a local network or not.
	 */
	if ((isipv6 && in6_localaddr(&inp->in6p_faddr)) ||
	    (!isipv6 && in_localaddr(inp->inp_faddr)))
		tp->snd_cwnd = mss * ss_fltsz_local;
	else 
		tp->snd_cwnd = mss * ss_fltsz;

	if (rt->rt_rmx.rmx_ssthresh) {
		/*
		 * There's some sort of gateway or interface
		 * buffer limit on the path.  Use this to set
		 * the slow start threshhold, but set the
		 * threshold to no less than 2*mss.
		 */
		tp->snd_ssthresh = max(2 * mss, rt->rt_rmx.rmx_ssthresh);
		tcpstat.tcps_usedssthresh++;
	}
}

/*
 * Determine the MSS option to send on an outgoing SYN.
 */
int
tcp_mssopt(tp)
	struct tcpcb *tp;
{
	struct rtentry *rt;
#ifdef INET6
	int isipv6 = ((tp->t_inpcb->inp_vflag & INP_IPV6) != 0) ? 1 : 0;
	size_t min_protoh = isipv6 ?
			    sizeof (struct ip6_hdr) + sizeof (struct tcphdr) :
			    sizeof (struct tcpiphdr);
#else
	const int isipv6 = 0;
	const size_t min_protoh = sizeof (struct tcpiphdr);
#endif

	if (isipv6)
		rt = tcp_rtlookup6(&tp->t_inpcb->inp_inc);
	else
		rt = tcp_rtlookup(&tp->t_inpcb->inp_inc);
	if (rt == NULL)
		return (isipv6 ? tcp_v6mssdflt : tcp_mssdflt);

	return (rt->rt_ifp->if_mtu - min_protoh);
}


/*
 * On a partial ack arrives, force the retransmission of the
 * next unacknowledged segment.  Do not clear tp->t_dupacks.
 * By setting snd_nxt to ti_ack, this forces retransmission timer to
 * be started again.
 */
static void
tcp_newreno_partial_ack(tp, th)
	struct tcpcb *tp;
	struct tcphdr *th;
{
	tcp_seq onxt = tp->snd_nxt;
	u_long  ocwnd = tp->snd_cwnd;

	callout_stop(tp->tt_rexmt);
	tp->t_rtttime = 0;
	tp->snd_nxt = th->th_ack;
	/*
	 * Set snd_cwnd to one segment beyond acknowledged offset.
	 * (tp->snd_una has not yet been updated when this function is called.)
	 */
	tp->snd_cwnd = tp->t_maxseg + (th->th_ack - tp->snd_una);
	tp->t_flags |= TF_ACKNOW;
	(void) tcp_output(tp);
	tp->snd_cwnd = ocwnd;
	if (SEQ_GT(onxt, tp->snd_nxt))
		tp->snd_nxt = onxt;
	/*
	 * Partial window deflation.  Relies on fact that tp->snd_una
	 * not updated yet.
	 */
	tp->snd_cwnd -= (th->th_ack - tp->snd_una - tp->t_maxseg);
}
OpenPOWER on IntegriCloud