1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
2852
2853
2854
2855
2856
2857
2858
2859
2860
2861
2862
2863
2864
2865
2866
2867
2868
2869
2870
2871
2872
2873
2874
2875
2876
2877
2878
2879
2880
2881
2882
2883
2884
2885
2886
2887
2888
2889
2890
2891
2892
2893
2894
2895
2896
2897
2898
2899
2900
2901
2902
2903
2904
2905
2906
2907
2908
2909
2910
2911
2912
2913
2914
2915
2916
2917
2918
2919
2920
2921
2922
2923
2924
2925
2926
2927
2928
2929
2930
2931
2932
2933
2934
2935
2936
2937
2938
2939
2940
2941
2942
2943
2944
2945
2946
2947
2948
2949
2950
2951
2952
2953
2954
2955
2956
2957
2958
2959
2960
2961
2962
2963
2964
2965
2966
2967
2968
2969
2970
2971
2972
2973
2974
2975
2976
2977
2978
2979
2980
2981
2982
2983
2984
2985
2986
2987
2988
2989
2990
2991
2992
2993
2994
2995
2996
2997
2998
2999
3000
3001
3002
3003
3004
3005
3006
3007
3008
3009
3010
3011
3012
3013
3014
3015
3016
3017
3018
3019
3020
3021
3022
3023
3024
3025
3026
3027
3028
3029
3030
3031
3032
3033
3034
3035
3036
3037
3038
3039
3040
3041
3042
3043
3044
3045
3046
3047
3048
3049
3050
3051
3052
3053
3054
3055
3056
3057
3058
3059
3060
3061
3062
3063
3064
3065
3066
3067
3068
3069
3070
3071
3072
3073
3074
3075
3076
3077
3078
3079
3080
3081
3082
3083
3084
3085
3086
3087
3088
3089
3090
3091
3092
3093
3094
3095
3096
3097
3098
3099
3100
3101
3102
3103
3104
3105
3106
3107
3108
3109
3110
3111
3112
3113
3114
3115
3116
3117
3118
3119
3120
3121
3122
3123
3124
3125
3126
3127
3128
3129
3130
3131
3132
3133
3134
3135
3136
3137
3138
3139
3140
3141
3142
3143
3144
3145
3146
3147
3148
3149
3150
3151
3152
3153
3154
3155
3156
3157
3158
3159
3160
3161
3162
3163
3164
3165
3166
3167
3168
3169
3170
3171
3172
3173
3174
3175
3176
3177
3178
3179
3180
3181
3182
3183
3184
3185
3186
3187
3188
3189
3190
3191
3192
3193
3194
3195
3196
3197
3198
3199
3200
3201
3202
3203
3204
3205
3206
3207
3208
3209
3210
3211
3212
3213
3214
3215
3216
3217
3218
3219
3220
3221
3222
3223
3224
3225
3226
3227
3228
3229
3230
3231
3232
3233
3234
3235
3236
3237
3238
3239
3240
3241
3242
3243
3244
3245
3246
3247
3248
3249
3250
3251
3252
3253
3254
3255
3256
3257
3258
3259
3260
3261
3262
3263
3264
3265
3266
3267
3268
3269
3270
3271
3272
3273
3274
3275
3276
3277
3278
3279
3280
3281
3282
3283
3284
3285
3286
3287
3288
3289
3290
3291
3292
3293
3294
3295
3296
3297
3298
3299
3300
3301
3302
3303
3304
3305
3306
3307
3308
3309
3310
3311
3312
3313
3314
3315
3316
3317
3318
3319
3320
3321
3322
3323
3324
3325
3326
3327
3328
3329
3330
3331
3332
3333
3334
3335
3336
3337
3338
3339
3340
3341
3342
3343
3344
3345
3346
3347
3348
3349
3350
3351
3352
3353
3354
3355
3356
3357
3358
3359
3360
3361
3362
3363
3364
3365
3366
3367
3368
3369
3370
3371
3372
3373
3374
3375
3376
3377
3378
3379
3380
3381
3382
3383
3384
3385
3386
3387
3388
3389
3390
3391
3392
3393
3394
3395
3396
3397
3398
3399
3400
3401
3402
3403
3404
3405
3406
3407
3408
3409
3410
3411
3412
3413
3414
3415
3416
3417
3418
3419
3420
3421
3422
3423
3424
3425
3426
3427
3428
3429
3430
3431
3432
3433
3434
3435
3436
3437
3438
3439
3440
3441
3442
3443
3444
3445
3446
3447
3448
3449
3450
3451
3452
3453
3454
3455
3456
3457
3458
3459
3460
3461
3462
3463
3464
3465
3466
3467
3468
3469
3470
3471
3472
3473
3474
3475
3476
3477
3478
3479
3480
3481
3482
3483
3484
3485
3486
3487
3488
3489
3490
3491
3492
3493
3494
3495
3496
3497
3498
3499
3500
3501
3502
3503
3504
3505
3506
3507
3508
3509
3510
3511
3512
3513
3514
3515
3516
3517
3518
3519
3520
3521
3522
3523
3524
3525
3526
3527
3528
3529
3530
3531
3532
3533
3534
3535
3536
3537
3538
3539
3540
3541
3542
3543
3544
3545
3546
3547
3548
3549
3550
3551
3552
3553
3554
3555
3556
3557
3558
3559
3560
3561
3562
3563
3564
3565
3566
3567
3568
3569
3570
3571
3572
3573
3574
3575
3576
3577
3578
3579
3580
3581
3582
3583
3584
3585
3586
3587
3588
3589
3590
3591
3592
3593
3594
3595
3596
3597
3598
3599
3600
3601
3602
3603
3604
3605
3606
3607
3608
3609
3610
3611
3612
3613
3614
3615
3616
3617
3618
3619
3620
3621
3622
3623
3624
3625
3626
3627
3628
3629
3630
3631
3632
3633
3634
3635
3636
3637
3638
3639
3640
3641
3642
3643
3644
3645
3646
3647
3648
3649
3650
3651
3652
3653
3654
3655
3656
3657
3658
3659
3660
3661
3662
3663
3664
3665
3666
3667
3668
3669
3670
3671
3672
3673
3674
3675
3676
3677
3678
3679
3680
3681
3682
3683
3684
3685
3686
3687
3688
3689
3690
3691
3692
3693
3694
3695
3696
3697
3698
3699
3700
3701
3702
3703
3704
3705
3706
3707
3708
3709
3710
3711
3712
3713
3714
3715
3716
3717
3718
3719
3720
3721
3722
3723
3724
3725
3726
3727
3728
3729
3730
3731
3732
3733
3734
3735
3736
3737
3738
3739
3740
3741
3742
3743
3744
3745
3746
3747
3748
3749
3750
3751
3752
3753
3754
3755
3756
3757
3758
3759
3760
3761
3762
3763
3764
3765
3766
3767
3768
3769
3770
3771
3772
3773
3774
3775
3776
3777
3778
3779
3780
3781
3782
3783
3784
3785
3786
3787
3788
3789
3790
3791
3792
3793
3794
3795
3796
3797
3798
3799
3800
3801
3802
3803
3804
3805
3806
3807
3808
3809
3810
3811
3812
3813
3814
3815
3816
3817
3818
3819
3820
3821
3822
3823
3824
3825
3826
3827
3828
3829
3830
3831
3832
3833
3834
3835
3836
3837
3838
3839
3840
3841
3842
3843
3844
3845
3846
3847
3848
3849
3850
3851
3852
3853
3854
3855
3856
3857
3858
3859
3860
3861
3862
3863
3864
3865
3866
3867
3868
3869
3870
3871
3872
3873
3874
3875
3876
3877
3878
3879
3880
3881
3882
3883
3884
3885
3886
3887
3888
3889
3890
3891
3892
3893
3894
3895
3896
3897
3898
3899
3900
3901
3902
3903
3904
3905
3906
3907
3908
3909
3910
3911
3912
3913
3914
3915
3916
3917
3918
3919
3920
3921
3922
3923
3924
3925
3926
3927
3928
3929
3930
3931
3932
3933
3934
3935
3936
3937
3938
3939
3940
3941
3942
3943
3944
3945
3946
3947
3948
3949
3950
3951
3952
3953
3954
3955
3956
3957
3958
3959
3960
3961
3962
3963
3964
3965
3966
3967
3968
3969
3970
3971
3972
3973
3974
3975
3976
3977
3978
3979
3980
3981
3982
3983
3984
3985
3986
3987
3988
3989
3990
3991
3992
3993
3994
3995
3996
3997
3998
3999
4000
4001
4002
4003
4004
4005
4006
4007
4008
4009
4010
4011
4012
4013
4014
4015
4016
4017
4018
4019
4020
4021
4022
4023
4024
4025
4026
4027
4028
4029
4030
4031
4032
4033
4034
4035
4036
4037
4038
4039
4040
4041
4042
4043
4044
4045
4046
4047
4048
4049
4050
4051
4052
4053
4054
4055
4056
4057
4058
4059
4060
4061
4062
4063
4064
4065
4066
4067
4068
4069
4070
4071
4072
4073
4074
4075
4076
4077
4078
4079
4080
4081
4082
4083
4084
4085
4086
4087
4088
4089
4090
4091
4092
4093
4094
4095
4096
4097
4098
4099
4100
4101
4102
4103
4104
4105
4106
4107
4108
4109
4110
4111
4112
4113
4114
4115
4116
4117
4118
4119
4120
4121
4122
4123
4124
4125
4126
4127
4128
4129
4130
4131
4132
4133
4134
4135
4136
4137
4138
4139
4140
4141
4142
4143
4144
4145
4146
4147
4148
4149
4150
4151
4152
4153
4154
4155
4156
4157
4158
4159
4160
4161
4162
4163
4164
4165
4166
4167
4168
4169
4170
4171
4172
4173
4174
4175
4176
4177
4178
4179
4180
4181
4182
4183
4184
4185
4186
4187
4188
4189
4190
4191
4192
4193
4194
4195
4196
4197
4198
4199
4200
4201
4202
4203
4204
4205
4206
4207
4208
4209
4210
4211
4212
4213
4214
4215
4216
4217
4218
4219
4220
4221
4222
4223
4224
4225
4226
4227
4228
4229
4230
4231
4232
4233
4234
4235
4236
4237
4238
4239
4240
4241
4242
4243
4244
4245
4246
4247
4248
4249
4250
4251
4252
4253
4254
4255
4256
4257
4258
4259
4260
4261
4262
4263
4264
4265
4266
4267
4268
4269
4270
4271
4272
4273
4274
4275
4276
4277
4278
4279
4280
4281
4282
4283
4284
4285
4286
4287
4288
4289
4290
4291
4292
4293
4294
4295
4296
4297
4298
4299
4300
4301
4302
4303
4304
4305
4306
4307
4308
4309
4310
4311
4312
4313
4314
4315
4316
4317
4318
4319
4320
4321
4322
4323
4324
4325
4326
4327
4328
4329
4330
4331
4332
4333
4334
4335
4336
4337
4338
4339
4340
4341
4342
4343
4344
4345
4346
4347
4348
4349
4350
4351
4352
4353
4354
4355
4356
4357
4358
4359
4360
4361
4362
4363
4364
4365
4366
4367
4368
4369
4370
4371
4372
4373
4374
4375
4376
4377
4378
4379
4380
4381
4382
4383
4384
4385
4386
4387
4388
4389
4390
4391
4392
4393
4394
4395
4396
4397
4398
4399
4400
4401
4402
4403
4404
4405
4406
4407
4408
4409
4410
4411
4412
4413
4414
4415
4416
|
/* $OpenBSD: tcp_input.c,v 1.240 2011/01/07 17:50:42 bluhm Exp $ */
/* $NetBSD: tcp_input.c,v 1.23 1996/02/13 23:43:44 christos Exp $ */
/*
* Copyright (c) 1982, 1986, 1988, 1990, 1993, 1994
* 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. 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.
*
* @(#)COPYRIGHT 1.1 (NRL) 17 January 1995
*
* NRL grants permission for redistribution and use in source and binary
* forms, with or without modification, of the software and documentation
* created at NRL 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 acknowledgements:
* This product includes software developed by the University of
* California, Berkeley and its contributors.
* This product includes software developed at the Information
* Technology Division, US Naval Research Laboratory.
* 4. Neither the name of the NRL nor the names of its contributors
* may be used to endorse or promote products derived from this software
* without specific prior written permission.
*
* THE SOFTWARE PROVIDED BY NRL IS PROVIDED BY NRL 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 NRL 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.
*
* The views and conclusions contained in the software and documentation
* are those of the authors and should not be interpreted as representing
* official policies, either expressed or implied, of the US Naval
* Research Laboratory (NRL).
*/
#include <sys/param.h>
#include <sys/systm.h>
#include <sys/mbuf.h>
#include <sys/protosw.h>
#include <sys/socket.h>
#include <sys/socketvar.h>
#include <sys/kernel.h>
#include <sys/pool.h>
#include <dev/rndvar.h>
#include <net/if.h>
#include <net/route.h>
#include <netinet/in.h>
#include <netinet/in_systm.h>
#include <netinet/ip.h>
#include <netinet/in_pcb.h>
#include <netinet/ip_var.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 <netinet/tcpip.h>
#include <netinet/tcp_debug.h>
#include "faith.h"
#if NFAITH > 0
#include <net/if_types.h>
#endif
#include "pf.h"
#if NPF > 0
#include <net/pfvar.h>
#endif
struct tcpiphdr tcp_saveti;
int tcp_mss_adv(struct ifnet *, int);
#ifdef INET6
#include <netinet6/in6_var.h>
#include <netinet6/nd6.h>
struct tcpipv6hdr tcp_saveti6;
/* for the packet header length in the mbuf */
#define M_PH_LEN(m) (((struct mbuf *)(m))->m_pkthdr.len)
#define M_V6_LEN(m) (M_PH_LEN(m) - sizeof(struct ip6_hdr))
#define M_V4_LEN(m) (M_PH_LEN(m) - sizeof(struct ip))
#endif /* INET6 */
int tcprexmtthresh = 3;
int tcptv_keep_init = TCPTV_KEEP_INIT;
extern u_long sb_max;
int tcp_rst_ppslim = 100; /* 100pps */
int tcp_rst_ppslim_count = 0;
struct timeval tcp_rst_ppslim_last;
int tcp_ackdrop_ppslim = 100; /* 100pps */
int tcp_ackdrop_ppslim_count = 0;
struct timeval tcp_ackdrop_ppslim_last;
#define TCP_PAWS_IDLE (24 * 24 * 60 * 60 * PR_SLOWHZ)
/* for modulo comparisons of timestamps */
#define TSTMP_LT(a,b) ((int)((a)-(b)) < 0)
#define TSTMP_GEQ(a,b) ((int)((a)-(b)) >= 0)
/* for TCP SACK comparisons */
#define SEQ_MIN(a,b) (SEQ_LT(a,b) ? (a) : (b))
#define SEQ_MAX(a,b) (SEQ_GT(a,b) ? (a) : (b))
/*
* Neighbor Discovery, Neighbor Unreachability Detection Upper layer hint.
*/
#ifdef INET6
#define ND6_HINT(tp) \
do { \
if (tp && tp->t_inpcb && (tp->t_inpcb->inp_flags & INP_IPV6) && \
tp->t_inpcb->inp_route6.ro_rt) { \
nd6_nud_hint(tp->t_inpcb->inp_route6.ro_rt, NULL, 0); \
} \
} while (0)
#else
#define ND6_HINT(tp)
#endif
#ifdef TCP_ECN
/*
* ECN (Explicit Congestion Notification) support based on RFC3168
* implementation note:
* snd_last is used to track a recovery phase.
* when cwnd is reduced, snd_last is set to snd_max.
* while snd_last > snd_una, the sender is in a recovery phase and
* its cwnd should not be reduced again.
* snd_last follows snd_una when not in a recovery phase.
*/
#endif
/*
* Macro to compute ACK transmission behavior. Delay the ACK unless
* we have already delayed an ACK (must send an ACK every two segments).
* We also ACK immediately if we received a PUSH and the ACK-on-PUSH
* option is enabled or when the packet is comming from a loopback
* interface.
*/
#define TCP_SETUP_ACK(tp, tiflags, m) \
do { \
if ((tp)->t_flags & TF_DELACK || \
(tcp_ack_on_push && (tiflags) & TH_PUSH) || \
(m && (m->m_flags & M_PKTHDR) && m->m_pkthdr.rcvif && \
(m->m_pkthdr.rcvif->if_flags & IFF_LOOPBACK))) \
tp->t_flags |= TF_ACKNOW; \
else \
TCP_SET_DELACK(tp); \
} while (0)
/*
* Insert segment ti into reassembly queue of tcp with
* control block tp. Return TH_FIN if reassembly now includes
* a segment with FIN. The macro form does 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).
*/
int
tcp_reass(struct tcpcb *tp, struct tcphdr *th, struct mbuf *m, int *tlen)
{
struct tcpqent *p, *q, *nq, *tiqe;
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, before we throw away any data.
* If we can't, just drop the packet. XXX
*/
tiqe = pool_get(&tcpqe_pool, PR_NOWAIT);
if (tiqe == NULL) {
tiqe = TAILQ_LAST(&tp->t_segq, tcpqehead);
if (tiqe != NULL && th->th_seq == tp->rcv_nxt) {
/* Reuse last entry since new segment fills a hole */
m_freem(tiqe->tcpqe_m);
TAILQ_REMOVE(&tp->t_segq, tiqe, tcpqe_q);
}
if (tiqe == NULL || th->th_seq != tp->rcv_nxt) {
/* Flush segment queue for this connection */
tcp_freeq(tp);
tcpstat.tcps_rcvmemdrop++;
m_freem(m);
return (0);
}
}
/*
* Find a segment which begins after this one does.
*/
for (p = NULL, q = TAILQ_FIRST(&tp->t_segq); q != NULL;
p = q, q = TAILQ_NEXT(q, tcpqe_q))
if (SEQ_GT(q->tcpqe_tcp->th_seq, th->th_seq))
break;
/*
* 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) {
struct tcphdr *phdr = p->tcpqe_tcp;
int i;
/* conversion to int (in i) handles seq wraparound */
i = phdr->th_seq + phdr->th_reseqlen - th->th_seq;
if (i > 0) {
if (i >= *tlen) {
tcpstat.tcps_rcvduppack++;
tcpstat.tcps_rcvdupbyte += *tlen;
m_freem(m);
pool_put(&tcpqe_pool, tiqe);
return (0);
}
m_adj(m, i);
*tlen -= i;
th->th_seq += i;
}
}
tcpstat.tcps_rcvoopack++;
tcpstat.tcps_rcvoobyte += *tlen;
/*
* While we overlap succeeding segments trim them or,
* if they are completely covered, dequeue them.
*/
for (; q != NULL; q = nq) {
struct tcphdr *qhdr = q->tcpqe_tcp;
int i = (th->th_seq + *tlen) - qhdr->th_seq;
if (i <= 0)
break;
if (i < qhdr->th_reseqlen) {
qhdr->th_seq += i;
qhdr->th_reseqlen -= i;
m_adj(q->tcpqe_m, i);
break;
}
nq = TAILQ_NEXT(q, tcpqe_q);
m_freem(q->tcpqe_m);
TAILQ_REMOVE(&tp->t_segq, q, tcpqe_q);
pool_put(&tcpqe_pool, q);
}
/* Insert the new segment queue entry into place. */
tiqe->tcpqe_m = m;
th->th_reseqlen = *tlen;
tiqe->tcpqe_tcp = th;
if (p == NULL) {
TAILQ_INSERT_HEAD(&tp->t_segq, tiqe, tcpqe_q);
} else {
TAILQ_INSERT_AFTER(&tp->t_segq, p, tiqe, tcpqe_q);
}
present:
/*
* Present data to user, advancing rcv_nxt through
* completed sequence space.
*/
if (TCPS_HAVEESTABLISHED(tp->t_state) == 0)
return (0);
q = TAILQ_FIRST(&tp->t_segq);
if (q == NULL || q->tcpqe_tcp->th_seq != tp->rcv_nxt)
return (0);
if (tp->t_state == TCPS_SYN_RECEIVED && q->tcpqe_tcp->th_reseqlen)
return (0);
do {
tp->rcv_nxt += q->tcpqe_tcp->th_reseqlen;
flags = q->tcpqe_tcp->th_flags & TH_FIN;
nq = TAILQ_NEXT(q, tcpqe_q);
TAILQ_REMOVE(&tp->t_segq, q, tcpqe_q);
ND6_HINT(tp);
if (so->so_state & SS_CANTRCVMORE)
m_freem(q->tcpqe_m);
else
sbappendstream(&so->so_rcv, q->tcpqe_m);
pool_put(&tcpqe_pool, q);
q = nq;
} while (q != NULL && q->tcpqe_tcp->th_seq == tp->rcv_nxt);
tp->t_flags |= TF_BLOCKOUTPUT;
sorwakeup(so);
tp->t_flags &= ~TF_BLOCKOUTPUT;
return (flags);
}
#ifdef INET6
int
tcp6_input(struct mbuf **mp, int *offp, int proto)
{
struct mbuf *m = *mp;
#if NFAITH > 0
if (m->m_pkthdr.rcvif) {
if (m->m_pkthdr.rcvif->if_type == IFT_FAITH) {
/* XXX send icmp6 host/port unreach? */
m_freem(m);
return IPPROTO_DONE;
}
}
#endif
tcp_input(m, *offp, proto);
return IPPROTO_DONE;
}
#endif
/*
* TCP input routine, follows pages 65-76 of the
* protocol specification dated September, 1981 very closely.
*/
void
tcp_input(struct mbuf *m, ...)
{
struct ip *ip;
struct inpcb *inp = NULL;
u_int8_t *optp = NULL;
int optlen = 0;
int tlen, off;
struct tcpcb *tp = 0;
int tiflags;
struct socket *so = NULL;
int todrop, acked, ourfinisacked;
int hdroptlen = 0;
short ostate = 0;
tcp_seq iss, *reuse = NULL;
u_long tiwin;
struct tcp_opt_info opti;
int iphlen;
va_list ap;
struct tcphdr *th;
#ifdef INET6
struct ip6_hdr *ip6 = NULL;
#endif /* INET6 */
#ifdef IPSEC
struct m_tag *mtag;
struct tdb_ident *tdbi;
struct tdb *tdb;
int error, s;
#endif /* IPSEC */
int af;
#ifdef TCP_ECN
u_char iptos;
#endif
va_start(ap, m);
iphlen = va_arg(ap, int);
va_end(ap);
tcpstat.tcps_rcvtotal++;
opti.ts_present = 0;
opti.maxseg = 0;
/*
* RFC1122 4.2.3.10, p. 104: discard bcast/mcast SYN
* See below for AF specific multicast.
*/
if (m->m_flags & (M_BCAST|M_MCAST))
goto drop;
/*
* Before we do ANYTHING, we have to figure out if it's TCP/IPv6 or
* TCP/IPv4.
*/
switch (mtod(m, struct ip *)->ip_v) {
#ifdef INET6
case 6:
af = AF_INET6;
break;
#endif
case 4:
af = AF_INET;
break;
default:
m_freem(m);
return; /*EAFNOSUPPORT*/
}
/*
* Get IP and TCP header together in first mbuf.
* Note: IP leaves IP header in first mbuf.
*/
switch (af) {
case AF_INET:
#ifdef DIAGNOSTIC
if (iphlen < sizeof(struct ip)) {
m_freem(m);
return;
}
#endif /* DIAGNOSTIC */
break;
#ifdef INET6
case AF_INET6:
#ifdef DIAGNOSTIC
if (iphlen < sizeof(struct ip6_hdr)) {
m_freem(m);
return;
}
#endif /* DIAGNOSTIC */
break;
#endif
default:
m_freem(m);
return;
}
IP6_EXTHDR_GET(th, struct tcphdr *, m, iphlen, sizeof(*th));
if (!th) {
tcpstat.tcps_rcvshort++;
return;
}
tlen = m->m_pkthdr.len - iphlen;
ip = NULL;
#ifdef INET6
ip6 = NULL;
#endif
switch (af) {
case AF_INET:
ip = mtod(m, struct ip *);
if (IN_MULTICAST(ip->ip_dst.s_addr) ||
in_broadcast(ip->ip_dst, m->m_pkthdr.rcvif))
goto drop;
#ifdef TCP_ECN
/* save ip_tos before clearing it for checksum */
iptos = ip->ip_tos;
#endif
/*
* Checksum extended TCP header and data.
*/
if ((m->m_pkthdr.csum_flags & M_TCP_CSUM_IN_OK) == 0) {
if (m->m_pkthdr.csum_flags & M_TCP_CSUM_IN_BAD) {
tcpstat.tcps_inhwcsum++;
tcpstat.tcps_rcvbadsum++;
goto drop;
}
if (in4_cksum(m, IPPROTO_TCP, iphlen, tlen) != 0) {
tcpstat.tcps_rcvbadsum++;
goto drop;
}
} else {
m->m_pkthdr.csum_flags &= ~M_TCP_CSUM_IN_OK;
tcpstat.tcps_inhwcsum++;
}
break;
#ifdef INET6
case AF_INET6:
ip6 = mtod(m, struct ip6_hdr *);
#ifdef TCP_ECN
iptos = (ntohl(ip6->ip6_flow) >> 20) & 0xff;
#endif
/* Be proactive about malicious use of IPv4 mapped address */
if (IN6_IS_ADDR_V4MAPPED(&ip6->ip6_src) ||
IN6_IS_ADDR_V4MAPPED(&ip6->ip6_dst)) {
/* XXX stat */
goto drop;
}
/*
* 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;
}
/* Discard packets to multicast */
if (IN6_IS_ADDR_MULTICAST(&ip6->ip6_dst)) {
/* XXX stat */
goto drop;
}
/*
* Checksum extended TCP header and data.
*/
if ((m->m_pkthdr.csum_flags & M_TCP_CSUM_IN_OK) == 0) {
if (m->m_pkthdr.csum_flags & M_TCP_CSUM_IN_BAD) {
tcpstat.tcps_inhwcsum++;
tcpstat.tcps_rcvbadsum++;
goto drop;
}
if (in6_cksum(m, IPPROTO_TCP, sizeof(struct ip6_hdr),
tlen)) {
tcpstat.tcps_rcvbadsum++;
goto drop;
}
} else {
m->m_pkthdr.csum_flags &= ~M_TCP_CSUM_IN_OK;
tcpstat.tcps_inhwcsum++;
}
break;
#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;
if (off > sizeof(struct tcphdr)) {
IP6_EXTHDR_GET(th, struct tcphdr *, m, iphlen, off);
if (!th) {
tcpstat.tcps_rcvshort++;
return;
}
optlen = off - sizeof(struct tcphdr);
optp = (u_int8_t *)(th + 1);
/*
* Do quick retrieval of timestamp options ("options
* prediction?"). If timestamp is the only option and it's
* formatted as recommended in RFC 1323 appendix A, we
* quickly get the values now and not bother calling
* tcp_dooptions(), etc.
*/
if ((optlen == TCPOLEN_TSTAMP_APPA ||
(optlen > TCPOLEN_TSTAMP_APPA &&
optp[TCPOLEN_TSTAMP_APPA] == TCPOPT_EOL)) &&
*(u_int32_t *)optp == htonl(TCPOPT_TSTAMP_HDR) &&
(th->th_flags & TH_SYN) == 0) {
opti.ts_present = 1;
opti.ts_val = ntohl(*(u_int32_t *)(optp + 4));
opti.ts_ecr = ntohl(*(u_int32_t *)(optp + 8));
optp = NULL; /* we've parsed the options */
}
}
tiflags = th->th_flags;
/*
* Convert TCP protocol specific fields to host format.
*/
NTOHL(th->th_seq);
NTOHL(th->th_ack);
NTOHS(th->th_win);
NTOHS(th->th_urp);
/*
* Locate pcb for segment.
*/
#if NPF > 0
if (m->m_pkthdr.pf.statekey)
inp = ((struct pf_state_key *)m->m_pkthdr.pf.statekey)->inp;
#endif
findpcb:
if (inp == NULL) {
switch (af) {
#ifdef INET6
case AF_INET6:
inp = in6_pcbhashlookup(&tcbtable, &ip6->ip6_src,
th->th_sport, &ip6->ip6_dst, th->th_dport);
break;
#endif
case AF_INET:
inp = in_pcbhashlookup(&tcbtable, ip->ip_src,
th->th_sport, ip->ip_dst, th->th_dport,
m->m_pkthdr.rdomain);
break;
}
#if NPF > 0
if (m->m_pkthdr.pf.statekey && inp) {
((struct pf_state_key *)m->m_pkthdr.pf.statekey)->inp =
inp;
inp->inp_pf_sk = m->m_pkthdr.pf.statekey;
}
#endif
}
if (inp == NULL) {
int inpl_flags = 0;
if (m->m_pkthdr.pf.flags & PF_TAG_TRANSLATE_LOCALHOST)
inpl_flags = INPLOOKUP_WILDCARD;
++tcpstat.tcps_pcbhashmiss;
switch (af) {
#ifdef INET6
case AF_INET6:
inp = in6_pcblookup_listen(&tcbtable,
&ip6->ip6_dst, th->th_dport, inpl_flags, m);
break;
#endif /* INET6 */
case AF_INET:
inp = in_pcblookup_listen(&tcbtable,
ip->ip_dst, th->th_dport, inpl_flags, m,
m->m_pkthdr.rdomain);
break;
}
/*
* 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 == 0) {
++tcpstat.tcps_noport;
goto dropwithreset_ratelim;
}
}
/* Check the minimum TTL for socket. */
if (inp->inp_ip_minttl && inp->inp_ip_minttl > ip->ip_ttl)
goto drop;
tp = intotcpcb(inp);
if (tp == 0)
goto dropwithreset_ratelim;
if (tp->t_state == TCPS_CLOSED)
goto drop;
/* Unscale the window into a 32-bit value. */
if ((tiflags & TH_SYN) == 0)
tiwin = th->th_win << tp->snd_scale;
else
tiwin = th->th_win;
so = inp->inp_socket;
if (so->so_options & (SO_DEBUG|SO_ACCEPTCONN)) {
union syn_cache_sa src;
union syn_cache_sa dst;
bzero(&src, sizeof(src));
bzero(&dst, sizeof(dst));
switch (af) {
#ifdef INET
case AF_INET:
src.sin.sin_len = sizeof(struct sockaddr_in);
src.sin.sin_family = AF_INET;
src.sin.sin_addr = ip->ip_src;
src.sin.sin_port = th->th_sport;
dst.sin.sin_len = sizeof(struct sockaddr_in);
dst.sin.sin_family = AF_INET;
dst.sin.sin_addr = ip->ip_dst;
dst.sin.sin_port = th->th_dport;
break;
#endif
#ifdef INET6
case AF_INET6:
src.sin6.sin6_len = sizeof(struct sockaddr_in6);
src.sin6.sin6_family = AF_INET6;
src.sin6.sin6_addr = ip6->ip6_src;
src.sin6.sin6_port = th->th_sport;
dst.sin6.sin6_len = sizeof(struct sockaddr_in6);
dst.sin6.sin6_family = AF_INET6;
dst.sin6.sin6_addr = ip6->ip6_dst;
dst.sin6.sin6_port = th->th_dport;
break;
#endif /* INET6 */
default:
goto badsyn; /*sanity*/
}
if (so->so_options & SO_DEBUG) {
ostate = tp->t_state;
switch (af) {
#ifdef INET6
case AF_INET6:
bcopy(ip6, &tcp_saveti6.ti6_i, sizeof(*ip6));
bcopy(th, &tcp_saveti6.ti6_t, sizeof(*th));
break;
#endif
case AF_INET:
bcopy(ip, &tcp_saveti.ti_i, sizeof(*ip));
bcopy(th, &tcp_saveti.ti_t, sizeof(*th));
break;
}
}
if (so->so_options & SO_ACCEPTCONN) {
if ((tiflags & (TH_RST|TH_ACK|TH_SYN)) != TH_SYN) {
if (tiflags & TH_RST) {
syn_cache_reset(&src.sa, &dst.sa, th,
inp->inp_rtableid);
} else if ((tiflags & (TH_ACK|TH_SYN)) ==
(TH_ACK|TH_SYN)) {
/*
* Received a SYN,ACK. This should
* never happen while we are in
* LISTEN. Send an RST.
*/
goto badsyn;
} else if (tiflags & TH_ACK) {
so = syn_cache_get(&src.sa, &dst.sa,
th, iphlen, tlen, so, m);
if (so == NULL) {
/*
* We don't have a SYN for
* this ACK; send an RST.
*/
goto badsyn;
} else if (so ==
(struct socket *)(-1)) {
/*
* We were unable to create
* the connection. If the
* 3-way handshake was
* completed, and RST has
* been sent to the peer.
* Since the mbuf might be
* in use for the reply,
* do not free it.
*/
m = NULL;
} else {
/*
* We have created a
* full-blown connection.
*/
tp = NULL;
inp = (struct inpcb *)so->so_pcb;
tp = intotcpcb(inp);
if (tp == NULL)
goto badsyn; /*XXX*/
goto after_listen;
}
} else {
/*
* None of RST, SYN or ACK was set.
* This is an invalid packet for a
* TCB in LISTEN state. Send a RST.
*/
goto badsyn;
}
} else {
/*
* Received a SYN.
*/
#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 (ip6 && !ip6_use_deprecated) {
struct in6_ifaddr *ia6;
if ((ia6 = in6ifa_ifpwithaddr(m->m_pkthdr.rcvif,
&ip6->ip6_dst)) &&
(ia6->ia6_flags & IN6_IFF_DEPRECATED)) {
tp = NULL;
goto dropwithreset;
}
}
#endif
/*
* LISTEN socket received a SYN
* from itself? This can't possibly
* be valid; drop the packet.
*/
if (th->th_dport == th->th_sport) {
switch (af) {
#ifdef INET6
case AF_INET6:
if (IN6_ARE_ADDR_EQUAL(&ip6->ip6_src,
&ip6->ip6_dst)) {
tcpstat.tcps_badsyn++;
goto drop;
}
break;
#endif /* INET6 */
case AF_INET:
if (ip->ip_dst.s_addr == ip->ip_src.s_addr) {
tcpstat.tcps_badsyn++;
goto drop;
}
break;
}
}
/*
* SYN looks ok; create compressed TCP
* state for it.
*/
if (so->so_qlen <= so->so_qlimit &&
syn_cache_add(&src.sa, &dst.sa, th, iphlen,
so, m, optp, optlen, &opti, reuse))
m = NULL;
}
goto drop;
}
}
after_listen:
#ifdef DIAGNOSTIC
/*
* Should not happen now that all embryonic connections
* are handled with compressed state.
*/
if (tp->t_state == TCPS_LISTEN)
panic("tcp_input: TCPS_LISTEN");
#endif
#if NPF > 0
if (m->m_pkthdr.pf.statekey) {
((struct pf_state_key *)m->m_pkthdr.pf.statekey)->inp = inp;
inp->inp_pf_sk = m->m_pkthdr.pf.statekey;
}
#endif
#ifdef IPSEC
/* Find most recent IPsec tag */
mtag = m_tag_find(m, PACKET_TAG_IPSEC_IN_DONE, NULL);
s = splnet();
if (mtag != NULL) {
tdbi = (struct tdb_ident *)(mtag + 1);
tdb = gettdb(tdbi->rdomain, tdbi->spi,
&tdbi->dst, tdbi->proto);
} else
tdb = NULL;
ipsp_spd_lookup(m, af, iphlen, &error, IPSP_DIRECTION_IN,
tdb, inp);
if (error) {
splx(s);
goto drop;
}
/* Latch SA */
if (inp->inp_tdb_in != tdb) {
if (tdb) {
tdb_add_inp(tdb, inp, 1);
if (inp->inp_ipo == NULL) {
inp->inp_ipo = ipsec_add_policy(inp, af,
IPSP_DIRECTION_OUT);
if (inp->inp_ipo == NULL) {
splx(s);
goto drop;
}
}
if (inp->inp_ipo->ipo_dstid == NULL &&
tdb->tdb_srcid != NULL) {
inp->inp_ipo->ipo_dstid = tdb->tdb_srcid;
tdb->tdb_srcid->ref_count++;
}
if (inp->inp_ipsec_remotecred == NULL &&
tdb->tdb_remote_cred != NULL) {
inp->inp_ipsec_remotecred =
tdb->tdb_remote_cred;
tdb->tdb_remote_cred->ref_count++;
}
if (inp->inp_ipsec_remoteauth == NULL &&
tdb->tdb_remote_auth != NULL) {
inp->inp_ipsec_remoteauth =
tdb->tdb_remote_auth;
tdb->tdb_remote_auth->ref_count++;
}
} else { /* Just reset */
TAILQ_REMOVE(&inp->inp_tdb_in->tdb_inp_in, inp,
inp_tdb_in_next);
inp->inp_tdb_in = NULL;
}
}
splx(s);
#endif /* IPSEC */
/*
* Segment received on connection.
* Reset idle time and keep-alive timer.
*/
tp->t_rcvtime = tcp_now;
if (TCPS_HAVEESTABLISHED(tp->t_state))
TCP_TIMER_ARM(tp, TCPT_KEEP, tcp_keepidle);
#ifdef TCP_SACK
if (tp->sack_enable)
tcp_del_sackholes(tp, th); /* Delete stale SACK holes */
#endif /* TCP_SACK */
/*
* Process options.
*/
#ifdef TCP_SIGNATURE
if (optp || (tp->t_flags & TF_SIGNATURE))
#else
if (optp)
#endif
if (tcp_dooptions(tp, optp, optlen, th, m, iphlen, &opti,
m->m_pkthdr.rdomain))
goto drop;
if (opti.ts_present && opti.ts_ecr) {
int rtt_test;
/* subtract out the tcp timestamp modulator */
opti.ts_ecr -= tp->ts_modulate;
/* make sure ts_ecr is sensible */
rtt_test = tcp_now - opti.ts_ecr;
if (rtt_test < 0 || rtt_test > TCP_RTT_MAX)
opti.ts_ecr = 0;
}
#ifdef TCP_ECN
/* if congestion experienced, set ECE bit in subsequent packets. */
if ((iptos & IPTOS_ECN_MASK) == IPTOS_ECN_CE) {
tp->t_flags |= TF_RCVD_CE;
tcpstat.tcps_ecn_rcvce++;
}
#endif
/*
* 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.
*/
if (tp->t_state == TCPS_ESTABLISHED &&
#ifdef TCP_ECN
(tiflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ECE|TH_CWR|TH_ACK)) == TH_ACK &&
#else
(tiflags & (TH_SYN|TH_FIN|TH_RST|TH_URG|TH_ACK)) == TH_ACK &&
#endif
(!opti.ts_present || TSTMP_GEQ(opti.ts_val, tp->ts_recent)) &&
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.
* Fix from Braden, see Stevens p. 870
*/
if (opti.ts_present && SEQ_LEQ(th->th_seq, tp->last_ack_sent)) {
tp->ts_recent_age = tcp_now;
tp->ts_recent = opti.ts_val;
}
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 &&
tp->t_dupacks == 0) {
/*
* this is a pure ack for outstanding data.
*/
++tcpstat.tcps_predack;
if (opti.ts_present && opti.ts_ecr)
tcp_xmit_timer(tp, tcp_now - opti.ts_ecr);
else if (tp->t_rtttime &&
SEQ_GT(th->th_ack, tp->t_rtseq))
tcp_xmit_timer(tp,
tcp_now - tp->t_rtttime);
acked = th->th_ack - tp->snd_una;
tcpstat.tcps_rcvackpack++;
tcpstat.tcps_rcvackbyte += acked;
ND6_HINT(tp);
sbdrop(&so->so_snd, acked);
/*
* If we had a pending ICMP message that
* referres to data that have just been
* acknowledged, disregard the recorded ICMP
* message.
*/
if ((tp->t_flags & TF_PMTUD_PEND) &&
SEQ_GT(th->th_ack, tp->t_pmtud_th_seq))
tp->t_flags &= ~TF_PMTUD_PEND;
/*
* Keep track of the largest chunk of data
* acknowledged since last PMTU update
*/
if (tp->t_pmtud_mss_acked < acked)
tp->t_pmtud_mss_acked = acked;
tp->snd_una = th->th_ack;
#if defined(TCP_SACK) || defined(TCP_ECN)
/*
* We want snd_last to track snd_una so
* as to avoid sequence wraparound problems
* for very large transfers.
*/
#ifdef TCP_ECN
if (SEQ_GT(tp->snd_una, tp->snd_last))
#endif
tp->snd_last = tp->snd_una;
#endif /* TCP_SACK */
#if defined(TCP_SACK) && defined(TCP_FACK)
tp->snd_fack = tp->snd_una;
tp->retran_data = 0;
#endif /* TCP_FACK */
m_freem(m);
/*
* 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)
TCP_TIMER_DISARM(tp, TCPT_REXMT);
else if (TCP_TIMER_ISARMED(tp, TCPT_PERSIST) == 0)
TCP_TIMER_ARM(tp, TCPT_REXMT, tp->t_rxtcur);
tcp_update_sndspace(tp);
if (sb_notify(&so->so_snd)) {
tp->t_flags |= TF_BLOCKOUTPUT;
sowwakeup(so);
tp->t_flags &= ~TF_BLOCKOUTPUT;
}
if (so->so_snd.sb_cc ||
tp->t_flags & TF_NEEDOUTPUT)
(void) tcp_output(tp);
return;
}
} else if (th->th_ack == tp->snd_una &&
TAILQ_EMPTY(&tp->t_segq) &&
tlen <= sbspace(&so->so_rcv)) {
/*
* This is a pure, in-sequence data packet
* with nothing on the reassembly queue and
* we have enough buffer space to take it.
*/
#ifdef TCP_SACK
/* Clean receiver SACK report if present */
if (tp->sack_enable && tp->rcv_numsacks)
tcp_clean_sackreport(tp);
#endif /* TCP_SACK */
++tcpstat.tcps_preddat;
tp->rcv_nxt += tlen;
tcpstat.tcps_rcvpack++;
tcpstat.tcps_rcvbyte += tlen;
ND6_HINT(tp);
TCP_SETUP_ACK(tp, tiflags, m);
/*
* Drop TCP, IP headers and TCP options then add data
* to socket buffer.
*/
if (so->so_state & SS_CANTRCVMORE)
m_freem(m);
else {
if (opti.ts_present && opti.ts_ecr) {
if (tp->rfbuf_ts < opti.ts_ecr &&
opti.ts_ecr - tp->rfbuf_ts < hz) {
tcp_update_rcvspace(tp);
/* Start over with next RTT. */
tp->rfbuf_cnt = 0;
tp->rfbuf_ts = 0;
} else
tp->rfbuf_cnt += tlen;
}
m_adj(m, iphlen + off);
sbappendstream(&so->so_rcv, m);
}
tp->t_flags |= TF_BLOCKOUTPUT;
sorwakeup(so);
tp->t_flags &= ~TF_BLOCKOUTPUT;
if (tp->t_flags & (TF_ACKNOW|TF_NEEDOUTPUT))
(void) tcp_output(tp);
return;
}
}
/*
* Compute mbuf offset to TCP data segment.
*/
hdroptlen = iphlen + off;
/*
* 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));
}
/* Reset receive buffer auto scaling when not in bulk receive mode. */
tp->rfbuf_cnt = 0;
tp->rfbuf_ts = 0;
switch (tp->t_state) {
/*
* If the state is SYN_RECEIVED:
* if seg contains SYN/ACK, send an RST.
* if seg contains an ACK, but not for our SYN/ACK, send an RST
*/
case TCPS_SYN_RECEIVED:
if (tiflags & TH_ACK) {
if (tiflags & TH_SYN) {
tcpstat.tcps_badsyn++;
goto dropwithreset;
}
if (SEQ_LEQ(th->th_ack, tp->snd_una) ||
SEQ_GT(th->th_ack, tp->snd_max))
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 ((tiflags & TH_ACK) &&
(SEQ_LEQ(th->th_ack, tp->iss) ||
SEQ_GT(th->th_ack, tp->snd_max)))
goto dropwithreset;
if (tiflags & TH_RST) {
#ifdef TCP_ECN
/* if ECN is enabled, fall back to non-ecn at rexmit */
if (tcp_do_ecn && !(tp->t_flags & TF_DISABLE_ECN))
goto drop;
#endif
if (tiflags & TH_ACK)
tp = tcp_drop(tp, ECONNREFUSED);
goto drop;
}
if ((tiflags & TH_SYN) == 0)
goto drop;
if (tiflags & TH_ACK) {
tp->snd_una = th->th_ack;
if (SEQ_LT(tp->snd_nxt, tp->snd_una))
tp->snd_nxt = tp->snd_una;
}
TCP_TIMER_DISARM(tp, TCPT_REXMT);
tp->irs = th->th_seq;
tcp_mss(tp, opti.maxseg);
/* Reset initial window to 1 segment for retransmit */
if (tp->t_rxtshift > 0)
tp->snd_cwnd = tp->t_maxseg;
tcp_rcvseqinit(tp);
tp->t_flags |= TF_ACKNOW;
#ifdef TCP_SACK
/*
* If we've sent a SACK_PERMITTED option, and the peer
* also replied with one, then TF_SACK_PERMIT should have
* been set in tcp_dooptions(). If it was not, disable SACKs.
*/
if (tp->sack_enable)
tp->sack_enable = tp->t_flags & TF_SACK_PERMIT;
#endif
#ifdef TCP_ECN
/*
* if ECE is set but CWR is not set for SYN-ACK, or
* both ECE and CWR are set for simultaneous open,
* peer is ECN capable.
*/
if (tcp_do_ecn) {
if ((tiflags & (TH_ACK|TH_ECE|TH_CWR))
== (TH_ACK|TH_ECE) ||
(tiflags & (TH_ACK|TH_ECE|TH_CWR))
== (TH_ECE|TH_CWR)) {
tp->t_flags |= TF_ECN_PERMIT;
tiflags &= ~(TH_ECE|TH_CWR);
tcpstat.tcps_ecn_accepts++;
}
}
#endif
if (tiflags & TH_ACK && SEQ_GT(tp->snd_una, tp->iss)) {
tcpstat.tcps_connects++;
soisconnected(so);
tp->t_state = TCPS_ESTABLISHED;
TCP_TIMER_ARM(tp, TCPT_KEEP, tcp_keepidle);
/* 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;
}
(void) tcp_reass(tp, (struct tcphdr *)0,
(struct mbuf *)0, &tlen);
/*
* if we didn't have to retransmit the SYN,
* use its rtt as our initial srtt & rtt var.
*/
if (tp->t_rtttime)
tcp_xmit_timer(tp, tcp_now - tp->t_rtttime);
/*
* Since new data was acked (the SYN), open the
* congestion window by one MSS. We do this
* here, because we won't go through the normal
* ACK processing below. And since this is the
* start of the connection, we know we are in
* the exponential phase of slow-start.
*/
tp->snd_cwnd += tp->t_maxseg;
} else
tp->t_state = TCPS_SYN_RECEIVED;
#if 0
trimthenstep6:
#endif
/*
* 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;
tiflags &= ~TH_FIN;
tcpstat.tcps_rcvpackafterwin++;
tcpstat.tcps_rcvbyteafterwin += todrop;
}
tp->snd_wl1 = th->th_seq - 1;
tp->rcv_up = th->th_seq;
goto step6;
/*
* If a new connection request is received while in TIME_WAIT,
* drop the old connection and start over if the if the
* timestamp or the sequence numbers are above the previous
* ones.
*/
case TCPS_TIME_WAIT:
if (((tiflags & (TH_SYN|TH_ACK)) == TH_SYN) &&
((opti.ts_present &&
TSTMP_LT(tp->ts_recent, opti.ts_val)) ||
SEQ_GT(th->th_seq, tp->rcv_nxt))) {
/*
* Advance the iss by at least 32768, but
* clear the msb in order to make sure
* that SEG_LT(snd_nxt, iss).
*/
iss = tp->snd_nxt +
((arc4random() & 0x7fffffff) | 0x8000);
reuse = &iss;
tp = tcp_close(tp);
inp = NULL;
goto findpcb;
}
}
/*
* States other than LISTEN or SYN_SENT.
* First check timestamp, 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.
*
* RFC 1323 PAWS: If we have a timestamp reply on this segment
* and it's less than opti.ts_recent, drop it.
*/
if (opti.ts_present && (tiflags & TH_RST) == 0 && tp->ts_recent &&
TSTMP_LT(opti.ts_val, tp->ts_recent)) {
/* Check to see if ts_recent is over 24 days old. */
if ((int)(tcp_now - 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++;
goto dropafterack;
}
}
todrop = tp->rcv_nxt - th->th_seq;
if (todrop > 0) {
if (tiflags & TH_SYN) {
tiflags &= ~TH_SYN;
th->th_seq++;
if (th->th_urp > 1)
th->th_urp--;
else
tiflags &= ~TH_URG;
todrop--;
}
if (todrop > tlen ||
(todrop == tlen && (tiflags & TH_FIN) == 0)) {
/*
* Any valid FIN must be to the left of the
* window. At this point, FIN must be a
* duplicate or out-of-sequence, so drop it.
*/
tiflags &= ~TH_FIN;
/*
* Send ACK to resynchronize, and drop any data,
* but keep on processing for RST or ACK.
*/
tp->t_flags |= TF_ACKNOW;
tcpstat.tcps_rcvdupbyte += todrop = tlen;
tcpstat.tcps_rcvduppack++;
} else {
tcpstat.tcps_rcvpartduppack++;
tcpstat.tcps_rcvpartdupbyte += todrop;
}
hdroptlen += todrop; /* drop from head afterwards */
th->th_seq += todrop;
tlen -= todrop;
if (th->th_urp > todrop)
th->th_urp -= todrop;
else {
tiflags &= ~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++;
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 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;
tiflags &= ~(TH_PUSH|TH_FIN);
}
/*
* If last ACK falls within this segment's sequence numbers,
* record its timestamp if it's more recent.
* Cf fix from Braden, see Stevens p. 870
*/
if (opti.ts_present && TSTMP_GEQ(opti.ts_val, tp->ts_recent) &&
SEQ_LEQ(th->th_seq, tp->last_ack_sent)) {
if (SEQ_LEQ(tp->last_ack_sent, th->th_seq + tlen +
((tiflags & (TH_SYN|TH_FIN)) != 0)))
tp->ts_recent = opti.ts_val;
else
tp->ts_recent = 0;
tp->ts_recent_age = tcp_now;
}
/*
* If the RST bit is set 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_WAIT2, CLOSE_WAIT STATES:
* Inform user that connection was reset, and close tcb.
* CLOSING, LAST_ACK, TIME_WAIT STATES
* Close the tcb.
*/
if (tiflags & TH_RST) {
if (th->th_seq != tp->last_ack_sent &&
th->th_seq != tp->rcv_nxt &&
th->th_seq != (tp->rcv_nxt + 1))
goto drop;
switch (tp->t_state) {
case TCPS_SYN_RECEIVED:
#ifdef TCP_ECN
/* if ECN is enabled, fall back to non-ecn at rexmit */
if (tcp_do_ecn && !(tp->t_flags & TF_DISABLE_ECN))
goto drop;
#endif
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);
goto drop;
case TCPS_CLOSING:
case TCPS_LAST_ACK:
case TCPS_TIME_WAIT:
tp = tcp_close(tp);
goto drop;
}
}
/*
* If a SYN is in the window, then this is an
* error and we ACK and drop the packet.
*/
if (tiflags & TH_SYN)
goto dropafterack_ratelim;
/*
* If the ACK bit is off we drop the segment and return.
*/
if ((tiflags & TH_ACK) == 0) {
if (tp->t_flags & TF_ACKNOW)
goto dropafterack;
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);
tp->t_state = TCPS_ESTABLISHED;
TCP_TIMER_ARM(tp, TCPT_KEEP, tcp_keepidle);
/* 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;
tiwin = th->th_win << tp->snd_scale;
}
(void) tcp_reass(tp, (struct tcphdr *)0, (struct mbuf *)0,
&tlen);
tp->snd_wl1 = th->th_seq - 1;
/* fall into ... */
/*
* 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:
#ifdef TCP_ECN
/*
* if we receive ECE and are not already in recovery phase,
* reduce cwnd by half but don't slow-start.
* advance snd_last to snd_max not to reduce cwnd again
* until all outstanding packets are acked.
*/
if (tcp_do_ecn && (tiflags & TH_ECE)) {
if ((tp->t_flags & TF_ECN_PERMIT) &&
SEQ_GEQ(tp->snd_una, tp->snd_last)) {
u_int win;
win = min(tp->snd_wnd, tp->snd_cwnd) / tp->t_maxseg;
if (win > 1) {
tp->snd_ssthresh = win / 2 * tp->t_maxseg;
tp->snd_cwnd = tp->snd_ssthresh;
tp->snd_last = tp->snd_max;
tp->t_flags |= TF_SEND_CWR;
tcpstat.tcps_cwr_ecn++;
}
}
tcpstat.tcps_ecn_rcvece++;
}
/*
* if we receive CWR, we know that the peer has reduced
* its congestion window. stop sending ecn-echo.
*/
if ((tiflags & TH_CWR)) {
tp->t_flags &= ~TF_RCVD_CE;
tcpstat.tcps_ecn_rcvcwr++;
}
#endif /* TCP_ECN */
if (SEQ_LEQ(th->th_ack, tp->snd_una)) {
/*
* Duplicate/old ACK processing.
* Increments t_dupacks:
* Pure duplicate (same seq/ack/window, no data)
* Doesn't affect t_dupacks:
* Data packets.
* Normal window updates (window opens)
* Resets t_dupacks:
* New data ACKed.
* Window shrinks
* Old ACK
*/
if (tlen) {
/* Drop very old ACKs unless th_seq matches */
if (th->th_seq != tp->rcv_nxt &&
SEQ_LT(th->th_ack,
tp->snd_una - tp->max_sndwnd)) {
tcpstat.tcps_rcvacktooold++;
goto drop;
}
break;
}
/*
* If we get an old ACK, there is probably packet
* reordering going on. Be conservative and reset
* t_dupacks so that we are less aggressive in
* doing a fast retransmit.
*/
if (th->th_ack != tp->snd_una) {
tp->t_dupacks = 0;
break;
}
if (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
* threshold 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 (TCP_TIMER_ISARMED(tp, TCPT_REXMT) == 0)
tp->t_dupacks = 0;
#if defined(TCP_SACK) && defined(TCP_FACK)
/*
* In FACK, can enter fast rec. if the receiver
* reports a reass. queue longer than 3 segs.
*/
else if (++tp->t_dupacks == tcprexmtthresh ||
((SEQ_GT(tp->snd_fack, tcprexmtthresh *
tp->t_maxseg + tp->snd_una)) &&
SEQ_GT(tp->snd_una, tp->snd_last))) {
#else
else if (++tp->t_dupacks == tcprexmtthresh) {
#endif /* TCP_FACK */
tcp_seq onxt = tp->snd_nxt;
u_long win =
ulmin(tp->snd_wnd, tp->snd_cwnd) /
2 / tp->t_maxseg;
#if defined(TCP_SACK) || defined(TCP_ECN)
if (SEQ_LT(th->th_ack, tp->snd_last)){
/*
* False fast retx after
* timeout. Do not cut window.
*/
tp->t_dupacks = 0;
goto drop;
}
#endif
if (win < 2)
win = 2;
tp->snd_ssthresh = win * tp->t_maxseg;
#ifdef TCP_SACK
tp->snd_last = tp->snd_max;
if (tp->sack_enable) {
TCP_TIMER_DISARM(tp, TCPT_REXMT);
tp->t_rtttime = 0;
#ifdef TCP_ECN
tp->t_flags |= TF_SEND_CWR;
#endif
tcpstat.tcps_cwr_frecovery++;
tcpstat.tcps_sack_recovery_episode++;
#if defined(TCP_SACK) && defined(TCP_FACK)
tp->t_dupacks = tcprexmtthresh;
(void) tcp_output(tp);
/*
* During FR, snd_cwnd is held
* constant for FACK.
*/
tp->snd_cwnd = tp->snd_ssthresh;
#else
/*
* tcp_output() will send
* oldest SACK-eligible rtx.
*/
(void) tcp_output(tp);
tp->snd_cwnd = tp->snd_ssthresh+
tp->t_maxseg * tp->t_dupacks;
#endif /* TCP_FACK */
goto drop;
}
#endif /* TCP_SACK */
TCP_TIMER_DISARM(tp, TCPT_REXMT);
tp->t_rtttime = 0;
tp->snd_nxt = th->th_ack;
tp->snd_cwnd = tp->t_maxseg;
#ifdef TCP_ECN
tp->t_flags |= TF_SEND_CWR;
#endif
tcpstat.tcps_cwr_frecovery++;
tcpstat.tcps_sndrexmitfast++;
(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 if (tp->t_dupacks > tcprexmtthresh) {
#if defined(TCP_SACK) && defined(TCP_FACK)
/*
* while (awnd < cwnd)
* sendsomething();
*/
if (tp->sack_enable) {
if (tp->snd_awnd < tp->snd_cwnd)
tcp_output(tp);
goto drop;
}
#endif /* TCP_FACK */
tp->snd_cwnd += tp->t_maxseg;
(void) tcp_output(tp);
goto drop;
}
} else if (tiwin < tp->snd_wnd) {
/*
* The window was retracted! Previous dup
* ACKs may have been due to packets arriving
* after the shrunken window, not a missing
* packet, so play it safe and reset t_dupacks
*/
tp->t_dupacks = 0;
}
break;
}
/*
* If the congestion window was inflated to account
* for the other side's cached packets, retract it.
*/
#if defined(TCP_SACK)
if (tp->sack_enable) {
if (tp->t_dupacks >= tcprexmtthresh) {
/* Check for a partial ACK */
if (tcp_sack_partialack(tp, th)) {
#if defined(TCP_SACK) && defined(TCP_FACK)
/* Force call to tcp_output */
if (tp->snd_awnd < tp->snd_cwnd)
tp->t_flags |= TF_NEEDOUTPUT;
#else
tp->snd_cwnd += tp->t_maxseg;
tp->t_flags |= TF_NEEDOUTPUT;
#endif /* TCP_FACK */
} else {
/* Out of fast recovery */
tp->snd_cwnd = tp->snd_ssthresh;
if (tcp_seq_subtract(tp->snd_max,
th->th_ack) < tp->snd_ssthresh)
tp->snd_cwnd =
tcp_seq_subtract(tp->snd_max,
th->th_ack);
tp->t_dupacks = 0;
#if defined(TCP_SACK) && defined(TCP_FACK)
if (SEQ_GT(th->th_ack, tp->snd_fack))
tp->snd_fack = th->th_ack;
#endif /* TCP_FACK */
}
}
} else {
if (tp->t_dupacks >= tcprexmtthresh &&
!tcp_newreno(tp, th)) {
/* Out of fast recovery */
tp->snd_cwnd = tp->snd_ssthresh;
if (tcp_seq_subtract(tp->snd_max, th->th_ack) <
tp->snd_ssthresh)
tp->snd_cwnd =
tcp_seq_subtract(tp->snd_max,
th->th_ack);
tp->t_dupacks = 0;
}
}
if (tp->t_dupacks < tcprexmtthresh)
tp->t_dupacks = 0;
#else /* else no TCP_SACK */
if (tp->t_dupacks >= tcprexmtthresh &&
tp->snd_cwnd > tp->snd_ssthresh)
tp->snd_cwnd = tp->snd_ssthresh;
tp->t_dupacks = 0;
#endif
if (SEQ_GT(th->th_ack, tp->snd_max)) {
tcpstat.tcps_rcvacktoomuch++;
goto dropafterack_ratelim;
}
acked = th->th_ack - tp->snd_una;
tcpstat.tcps_rcvackpack++;
tcpstat.tcps_rcvackbyte += acked;
/*
* 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.
*/
if (opti.ts_present && opti.ts_ecr)
tcp_xmit_timer(tp, tcp_now - opti.ts_ecr);
else if (tp->t_rtttime && SEQ_GT(th->th_ack, tp->t_rtseq))
tcp_xmit_timer(tp, tcp_now - tp->t_rtttime);
/*
* 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) {
TCP_TIMER_DISARM(tp, TCPT_REXMT);
tp->t_flags |= TF_NEEDOUTPUT;
} else if (TCP_TIMER_ISARMED(tp, TCPT_PERSIST) == 0)
TCP_TIMER_ARM(tp, TCPT_REXMT, tp->t_rxtcur);
/*
* 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).
*/
{
u_int cw = tp->snd_cwnd;
u_int incr = tp->t_maxseg;
if (cw > tp->snd_ssthresh)
incr = incr * incr / cw;
#if defined (TCP_SACK)
if (tp->t_dupacks < tcprexmtthresh)
#endif
tp->snd_cwnd = ulmin(cw + incr, TCP_MAXWIN<<tp->snd_scale);
}
ND6_HINT(tp);
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;
}
tcp_update_sndspace(tp);
if (sb_notify(&so->so_snd)) {
tp->t_flags |= TF_BLOCKOUTPUT;
sowwakeup(so);
tp->t_flags &= ~TF_BLOCKOUTPUT;
}
/*
* If we had a pending ICMP message that referred to data
* that have just been acknowledged, disregard the recorded
* ICMP message.
*/
if ((tp->t_flags & TF_PMTUD_PEND) &&
SEQ_GT(th->th_ack, tp->t_pmtud_th_seq))
tp->t_flags &= ~TF_PMTUD_PEND;
/*
* Keep track of the largest chunk of data acknowledged
* since last PMTU update
*/
if (tp->t_pmtud_mss_acked < acked)
tp->t_pmtud_mss_acked = acked;
tp->snd_una = th->th_ack;
#ifdef TCP_ECN
/* sync snd_last with snd_una */
if (SEQ_GT(tp->snd_una, tp->snd_last))
tp->snd_last = tp->snd_una;
#endif
if (SEQ_LT(tp->snd_nxt, tp->snd_una))
tp->snd_nxt = tp->snd_una;
#if defined (TCP_SACK) && defined (TCP_FACK)
if (SEQ_GT(tp->snd_una, tp->snd_fack)) {
tp->snd_fack = tp->snd_una;
/* Update snd_awnd for partial ACK
* without any SACK blocks.
*/
tp->snd_awnd = tcp_seq_subtract(tp->snd_nxt,
tp->snd_fack) + tp->retran_data;
}
#endif
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);
TCP_TIMER_ARM(tp, TCPT_2MSL, tcp_maxidle);
}
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);
TCP_TIMER_ARM(tp, TCPT_2MSL, 2 * TCPTV_MSL);
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:
TCP_TIMER_ARM(tp, TCPT_2MSL, 2 * TCPTV_MSL);
goto dropafterack;
}
}
step6:
/*
* Update window information.
* Don't look at window if no ACK: TAC's send garbage on first SYN.
*/
if ((tiflags & 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;
tp->t_flags |= TF_NEEDOUTPUT;
}
/*
* Process segments with URG.
*/
if ((tiflags & 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 */
tiflags &= ~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_int16_t) tlen
#ifdef SO_OOBINLINE
&& (so->so_options & SO_OOBINLINE) == 0
#endif
)
tcp_pulloutofband(so, th->th_urp, m, hdroptlen);
} 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 */
/*
* 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 || (tiflags & TH_FIN)) &&
TCPS_HAVERCVDFIN(tp->t_state) == 0) {
#ifdef TCP_SACK
tcp_seq laststart = th->th_seq;
tcp_seq lastend = th->th_seq + tlen;
#endif
if (th->th_seq == tp->rcv_nxt && TAILQ_EMPTY(&tp->t_segq) &&
tp->t_state == TCPS_ESTABLISHED) {
TCP_SETUP_ACK(tp, tiflags, m);
tp->rcv_nxt += tlen;
tiflags = 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 {
m_adj(m, hdroptlen);
sbappendstream(&so->so_rcv, m);
}
tp->t_flags |= TF_BLOCKOUTPUT;
sorwakeup(so);
tp->t_flags &= ~TF_BLOCKOUTPUT;
} else {
m_adj(m, hdroptlen);
tiflags = tcp_reass(tp, th, m, &tlen);
tp->t_flags |= TF_ACKNOW;
}
#ifdef TCP_SACK
if (tp->sack_enable)
tcp_update_sack_list(tp, laststart, lastend);
#endif
/*
* variable len never referenced again in modern BSD,
* so why bother computing it ??
*/
#if 0
/*
* 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);
#endif /* 0 */
} else {
m_freem(m);
tiflags &= ~TH_FIN;
}
/*
* If FIN is received ACK the FIN and let the user know
* that the connection is closing. Ignore a FIN received before
* the connection is fully established.
*/
if ((tiflags & TH_FIN) && TCPS_HAVEESTABLISHED(tp->t_state)) {
if (TCPS_HAVERCVDFIN(tp->t_state) == 0) {
socantrcvmore(so);
tp->t_flags |= TF_ACKNOW;
tp->rcv_nxt++;
}
switch (tp->t_state) {
/*
* In ESTABLISHED STATE enter the CLOSE_WAIT state.
*/
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);
TCP_TIMER_ARM(tp, TCPT_2MSL, 2 * TCPTV_MSL);
soisdisconnected(so);
break;
/*
* In TIME_WAIT state restart the 2 MSL time_wait timer.
*/
case TCPS_TIME_WAIT:
TCP_TIMER_ARM(tp, TCPT_2MSL, 2 * TCPTV_MSL);
break;
}
}
if (so->so_options & SO_DEBUG) {
switch (tp->pf) {
#ifdef INET6
case PF_INET6:
tcp_trace(TA_INPUT, ostate, tp, (caddr_t) &tcp_saveti6,
0, tlen);
break;
#endif /* INET6 */
case PF_INET:
tcp_trace(TA_INPUT, ostate, tp, (caddr_t) &tcp_saveti,
0, tlen);
break;
}
}
/*
* Return any desired output.
*/
if (tp->t_flags & (TF_ACKNOW|TF_NEEDOUTPUT))
(void) tcp_output(tp);
return;
badsyn:
/*
* Received a bad SYN. Increment counters and dropwithreset.
*/
tcpstat.tcps_badsyn++;
tp = NULL;
goto dropwithreset;
dropafterack_ratelim:
if (ppsratecheck(&tcp_ackdrop_ppslim_last, &tcp_ackdrop_ppslim_count,
tcp_ackdrop_ppslim) == 0) {
/* XXX stat */
goto drop;
}
/* ...fall into dropafterack... */
dropafterack:
/*
* Generate an ACK dropping incoming segment if it occupies
* sequence space, where the ACK reflects our state.
*/
if (tiflags & TH_RST)
goto drop;
m_freem(m);
tp->t_flags |= TF_ACKNOW;
(void) tcp_output(tp);
return;
dropwithreset_ratelim:
/*
* We may want to rate-limit RSTs in certain situations,
* particularly if we are sending an RST in response to
* an attempt to connect to or otherwise communicate with
* a port for which we have no socket.
*/
if (ppsratecheck(&tcp_rst_ppslim_last, &tcp_rst_ppslim_count,
tcp_rst_ppslim) == 0) {
/* XXX stat */
goto drop;
}
/* ...fall into dropwithreset... */
dropwithreset:
/*
* Generate a RST, dropping incoming segment.
* Make ACK acceptable to originator of segment.
* Don't bother to respond to RST.
*/
if (tiflags & TH_RST)
goto drop;
if (tiflags & TH_ACK) {
tcp_respond(tp, mtod(m, caddr_t), th, (tcp_seq)0, th->th_ack,
TH_RST, 0);
} else {
if (tiflags & TH_SYN)
tlen++;
tcp_respond(tp, mtod(m, caddr_t), th, th->th_seq + tlen,
(tcp_seq)0, TH_RST|TH_ACK, 0);
}
m_freem(m);
return;
drop:
/*
* Drop space held by incoming segment and return.
*/
if (tp && (tp->t_inpcb->inp_socket->so_options & SO_DEBUG)) {
switch (tp->pf) {
#ifdef INET6
case PF_INET6:
tcp_trace(TA_DROP, ostate, tp, (caddr_t) &tcp_saveti6,
0, tlen);
break;
#endif /* INET6 */
case PF_INET:
tcp_trace(TA_DROP, ostate, tp, (caddr_t) &tcp_saveti,
0, tlen);
break;
}
}
m_freem(m);
return;
}
int
tcp_dooptions(struct tcpcb *tp, u_char *cp, int cnt, struct tcphdr *th,
struct mbuf *m, int iphlen, struct tcp_opt_info *oi,
u_int rtableid)
{
u_int16_t mss = 0;
int opt, optlen;
#ifdef TCP_SIGNATURE
caddr_t sigp = NULL;
struct tdb *tdb = NULL;
#endif /* TCP_SIGNATURE */
for (; cp && 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) {
default:
continue;
case TCPOPT_MAXSEG:
if (optlen != TCPOLEN_MAXSEG)
continue;
if (!(th->th_flags & TH_SYN))
continue;
if (TCPS_HAVERCVDSYN(tp->t_state))
continue;
bcopy((char *) cp + 2, (char *) &mss, sizeof(mss));
NTOHS(mss);
oi->maxseg = mss;
break;
case TCPOPT_WINDOW:
if (optlen != TCPOLEN_WINDOW)
continue;
if (!(th->th_flags & TH_SYN))
continue;
if (TCPS_HAVERCVDSYN(tp->t_state))
continue;
tp->t_flags |= TF_RCVD_SCALE;
tp->requested_s_scale = min(cp[2], TCP_MAX_WINSHIFT);
break;
case TCPOPT_TIMESTAMP:
if (optlen != TCPOLEN_TIMESTAMP)
continue;
oi->ts_present = 1;
bcopy(cp + 2, &oi->ts_val, sizeof(oi->ts_val));
NTOHL(oi->ts_val);
bcopy(cp + 6, &oi->ts_ecr, sizeof(oi->ts_ecr));
NTOHL(oi->ts_ecr);
if (!(th->th_flags & TH_SYN))
continue;
if (TCPS_HAVERCVDSYN(tp->t_state))
continue;
/*
* A timestamp received in a SYN makes
* it ok to send timestamp requests and replies.
*/
tp->t_flags |= TF_RCVD_TSTMP;
tp->ts_recent = oi->ts_val;
tp->ts_recent_age = tcp_now;
break;
#ifdef TCP_SACK
case TCPOPT_SACK_PERMITTED:
if (!tp->sack_enable || optlen!=TCPOLEN_SACK_PERMITTED)
continue;
if (!(th->th_flags & TH_SYN))
continue;
if (TCPS_HAVERCVDSYN(tp->t_state))
continue;
/* MUST only be set on SYN */
tp->t_flags |= TF_SACK_PERMIT;
break;
case TCPOPT_SACK:
tcp_sack_option(tp, th, cp, optlen);
break;
#endif
#ifdef TCP_SIGNATURE
case TCPOPT_SIGNATURE:
if (optlen != TCPOLEN_SIGNATURE)
continue;
if (sigp && timingsafe_bcmp(sigp, cp + 2, 16))
return (-1);
sigp = cp + 2;
break;
#endif /* TCP_SIGNATURE */
}
}
#ifdef TCP_SIGNATURE
if (tp->t_flags & TF_SIGNATURE) {
union sockaddr_union src, dst;
memset(&src, 0, sizeof(union sockaddr_union));
memset(&dst, 0, sizeof(union sockaddr_union));
switch (tp->pf) {
case 0:
#ifdef INET
case AF_INET:
src.sa.sa_len = sizeof(struct sockaddr_in);
src.sa.sa_family = AF_INET;
src.sin.sin_addr = mtod(m, struct ip *)->ip_src;
dst.sa.sa_len = sizeof(struct sockaddr_in);
dst.sa.sa_family = AF_INET;
dst.sin.sin_addr = mtod(m, struct ip *)->ip_dst;
break;
#endif
#ifdef INET6
case AF_INET6:
src.sa.sa_len = sizeof(struct sockaddr_in6);
src.sa.sa_family = AF_INET6;
src.sin6.sin6_addr = mtod(m, struct ip6_hdr *)->ip6_src;
dst.sa.sa_len = sizeof(struct sockaddr_in6);
dst.sa.sa_family = AF_INET6;
dst.sin6.sin6_addr = mtod(m, struct ip6_hdr *)->ip6_dst;
break;
#endif /* INET6 */
}
tdb = gettdbbysrcdst(rtable_l2(rtableid),
0, &src, &dst, IPPROTO_TCP);
/*
* We don't have an SA for this peer, so we turn off
* TF_SIGNATURE on the listen socket
*/
if (tdb == NULL && tp->t_state == TCPS_LISTEN)
tp->t_flags &= ~TF_SIGNATURE;
}
if ((sigp ? TF_SIGNATURE : 0) ^ (tp->t_flags & TF_SIGNATURE)) {
tcpstat.tcps_rcvbadsig++;
return (-1);
}
if (sigp) {
char sig[16];
if (tdb == NULL) {
tcpstat.tcps_rcvbadsig++;
return (-1);
}
if (tcp_signature(tdb, tp->pf, m, th, iphlen, 1, sig) < 0)
return (-1);
if (timingsafe_bcmp(sig, sigp, 16)) {
tcpstat.tcps_rcvbadsig++;
return (-1);
}
tcpstat.tcps_rcvgoodsig++;
}
#endif /* TCP_SIGNATURE */
return (0);
}
#if defined(TCP_SACK)
u_long
tcp_seq_subtract(u_long a, u_long b)
{
return ((long)(a - b));
}
#endif
#ifdef TCP_SACK
/*
* This function is called upon receipt of new valid data (while not in header
* prediction mode), and it updates the ordered list of sacks.
*/
void
tcp_update_sack_list(struct tcpcb *tp, tcp_seq rcv_laststart,
tcp_seq rcv_lastend)
{
/*
* First reported block MUST be the most recent one. Subsequent
* blocks SHOULD be in the order in which they arrived at the
* receiver. These two conditions make the implementation fully
* compliant with RFC 2018.
*/
int i, j = 0, count = 0, lastpos = -1;
struct sackblk sack, firstsack, temp[MAX_SACK_BLKS];
/* First clean up current list of sacks */
for (i = 0; i < tp->rcv_numsacks; i++) {
sack = tp->sackblks[i];
if (sack.start == 0 && sack.end == 0) {
count++; /* count = number of blocks to be discarded */
continue;
}
if (SEQ_LEQ(sack.end, tp->rcv_nxt)) {
tp->sackblks[i].start = tp->sackblks[i].end = 0;
count++;
} else {
temp[j].start = tp->sackblks[i].start;
temp[j++].end = tp->sackblks[i].end;
}
}
tp->rcv_numsacks -= count;
if (tp->rcv_numsacks == 0) { /* no sack blocks currently (fast path) */
tcp_clean_sackreport(tp);
if (SEQ_LT(tp->rcv_nxt, rcv_laststart)) {
/* ==> need first sack block */
tp->sackblks[0].start = rcv_laststart;
tp->sackblks[0].end = rcv_lastend;
tp->rcv_numsacks = 1;
}
return;
}
/* Otherwise, sack blocks are already present. */
for (i = 0; i < tp->rcv_numsacks; i++)
tp->sackblks[i] = temp[i]; /* first copy back sack list */
if (SEQ_GEQ(tp->rcv_nxt, rcv_lastend))
return; /* sack list remains unchanged */
/*
* From here, segment just received should be (part of) the 1st sack.
* Go through list, possibly coalescing sack block entries.
*/
firstsack.start = rcv_laststart;
firstsack.end = rcv_lastend;
for (i = 0; i < tp->rcv_numsacks; i++) {
sack = tp->sackblks[i];
if (SEQ_LT(sack.end, firstsack.start) ||
SEQ_GT(sack.start, firstsack.end))
continue; /* no overlap */
if (sack.start == firstsack.start && sack.end == firstsack.end){
/*
* identical block; delete it here since we will
* move it to the front of the list.
*/
tp->sackblks[i].start = tp->sackblks[i].end = 0;
lastpos = i; /* last posn with a zero entry */
continue;
}
if (SEQ_LEQ(sack.start, firstsack.start))
firstsack.start = sack.start; /* merge blocks */
if (SEQ_GEQ(sack.end, firstsack.end))
firstsack.end = sack.end; /* merge blocks */
tp->sackblks[i].start = tp->sackblks[i].end = 0;
lastpos = i; /* last posn with a zero entry */
}
if (lastpos != -1) { /* at least one merge */
for (i = 0, j = 1; i < tp->rcv_numsacks; i++) {
sack = tp->sackblks[i];
if (sack.start == 0 && sack.end == 0)
continue;
temp[j++] = sack;
}
tp->rcv_numsacks = j; /* including first blk (added later) */
for (i = 1; i < tp->rcv_numsacks; i++) /* now copy back */
tp->sackblks[i] = temp[i];
} else { /* no merges -- shift sacks by 1 */
if (tp->rcv_numsacks < MAX_SACK_BLKS)
tp->rcv_numsacks++;
for (i = tp->rcv_numsacks-1; i > 0; i--)
tp->sackblks[i] = tp->sackblks[i-1];
}
tp->sackblks[0] = firstsack;
return;
}
/*
* Process the TCP SACK option. tp->snd_holes is an ordered list
* of holes (oldest to newest, in terms of the sequence space).
*/
void
tcp_sack_option(struct tcpcb *tp, struct tcphdr *th, u_char *cp, int optlen)
{
int tmp_olen;
u_char *tmp_cp;
struct sackhole *cur, *p, *temp;
if (!tp->sack_enable)
return;
/* SACK without ACK doesn't make sense. */
if ((th->th_flags & TH_ACK) == 0)
return;
/* Make sure the ACK on this segment is in [snd_una, snd_max]. */
if (SEQ_LT(th->th_ack, tp->snd_una) ||
SEQ_GT(th->th_ack, tp->snd_max))
return;
/* Note: TCPOLEN_SACK must be 2*sizeof(tcp_seq) */
if (optlen <= 2 || (optlen - 2) % TCPOLEN_SACK != 0)
return;
/* Note: TCPOLEN_SACK must be 2*sizeof(tcp_seq) */
tmp_cp = cp + 2;
tmp_olen = optlen - 2;
tcpstat.tcps_sack_rcv_opts++;
if (tp->snd_numholes < 0)
tp->snd_numholes = 0;
if (tp->t_maxseg == 0)
panic("tcp_sack_option"); /* Should never happen */
while (tmp_olen > 0) {
struct sackblk sack;
bcopy(tmp_cp, (char *) &(sack.start), sizeof(tcp_seq));
NTOHL(sack.start);
bcopy(tmp_cp + sizeof(tcp_seq),
(char *) &(sack.end), sizeof(tcp_seq));
NTOHL(sack.end);
tmp_olen -= TCPOLEN_SACK;
tmp_cp += TCPOLEN_SACK;
if (SEQ_LEQ(sack.end, sack.start))
continue; /* bad SACK fields */
if (SEQ_LEQ(sack.end, tp->snd_una))
continue; /* old block */
#if defined(TCP_SACK) && defined(TCP_FACK)
/* Updates snd_fack. */
if (SEQ_GT(sack.end, tp->snd_fack))
tp->snd_fack = sack.end;
#endif /* TCP_FACK */
if (SEQ_GT(th->th_ack, tp->snd_una)) {
if (SEQ_LT(sack.start, th->th_ack))
continue;
}
if (SEQ_GT(sack.end, tp->snd_max))
continue;
if (tp->snd_holes == NULL) { /* first hole */
tp->snd_holes = (struct sackhole *)
pool_get(&sackhl_pool, PR_NOWAIT);
if (tp->snd_holes == NULL) {
/* ENOBUFS, so ignore SACKed block for now*/
goto done;
}
cur = tp->snd_holes;
cur->start = th->th_ack;
cur->end = sack.start;
cur->rxmit = cur->start;
cur->next = NULL;
tp->snd_numholes = 1;
tp->rcv_lastsack = sack.end;
/*
* dups is at least one. If more data has been
* SACKed, it can be greater than one.
*/
cur->dups = min(tcprexmtthresh,
((sack.end - cur->end)/tp->t_maxseg));
if (cur->dups < 1)
cur->dups = 1;
continue; /* with next sack block */
}
/* Go thru list of holes: p = previous, cur = current */
p = cur = tp->snd_holes;
while (cur) {
if (SEQ_LEQ(sack.end, cur->start))
/* SACKs data before the current hole */
break; /* no use going through more holes */
if (SEQ_GEQ(sack.start, cur->end)) {
/* SACKs data beyond the current hole */
cur->dups++;
if (((sack.end - cur->end)/tp->t_maxseg) >=
tcprexmtthresh)
cur->dups = tcprexmtthresh;
p = cur;
cur = cur->next;
continue;
}
if (SEQ_LEQ(sack.start, cur->start)) {
/* Data acks at least the beginning of hole */
#if defined(TCP_SACK) && defined(TCP_FACK)
if (SEQ_GT(sack.end, cur->rxmit))
tp->retran_data -=
tcp_seq_subtract(cur->rxmit,
cur->start);
else
tp->retran_data -=
tcp_seq_subtract(sack.end,
cur->start);
#endif /* TCP_FACK */
if (SEQ_GEQ(sack.end, cur->end)) {
/* Acks entire hole, so delete hole */
if (p != cur) {
p->next = cur->next;
pool_put(&sackhl_pool, cur);
cur = p->next;
} else {
cur = cur->next;
pool_put(&sackhl_pool, p);
p = cur;
tp->snd_holes = p;
}
tp->snd_numholes--;
continue;
}
/* otherwise, move start of hole forward */
cur->start = sack.end;
cur->rxmit = SEQ_MAX(cur->rxmit, cur->start);
p = cur;
cur = cur->next;
continue;
}
/* move end of hole backward */
if (SEQ_GEQ(sack.end, cur->end)) {
#if defined(TCP_SACK) && defined(TCP_FACK)
if (SEQ_GT(cur->rxmit, sack.start))
tp->retran_data -=
tcp_seq_subtract(cur->rxmit,
sack.start);
#endif /* TCP_FACK */
cur->end = sack.start;
cur->rxmit = SEQ_MIN(cur->rxmit, cur->end);
cur->dups++;
if (((sack.end - cur->end)/tp->t_maxseg) >=
tcprexmtthresh)
cur->dups = tcprexmtthresh;
p = cur;
cur = cur->next;
continue;
}
if (SEQ_LT(cur->start, sack.start) &&
SEQ_GT(cur->end, sack.end)) {
/*
* ACKs some data in middle of a hole; need to
* split current hole
*/
temp = (struct sackhole *)
pool_get(&sackhl_pool, PR_NOWAIT);
if (temp == NULL)
goto done; /* ENOBUFS */
#if defined(TCP_SACK) && defined(TCP_FACK)
if (SEQ_GT(cur->rxmit, sack.end))
tp->retran_data -=
tcp_seq_subtract(sack.end,
sack.start);
else if (SEQ_GT(cur->rxmit, sack.start))
tp->retran_data -=
tcp_seq_subtract(cur->rxmit,
sack.start);
#endif /* TCP_FACK */
temp->next = cur->next;
temp->start = sack.end;
temp->end = cur->end;
temp->dups = cur->dups;
temp->rxmit = SEQ_MAX(cur->rxmit, temp->start);
cur->end = sack.start;
cur->rxmit = SEQ_MIN(cur->rxmit, cur->end);
cur->dups++;
if (((sack.end - cur->end)/tp->t_maxseg) >=
tcprexmtthresh)
cur->dups = tcprexmtthresh;
cur->next = temp;
p = temp;
cur = p->next;
tp->snd_numholes++;
}
}
/* At this point, p points to the last hole on the list */
if (SEQ_LT(tp->rcv_lastsack, sack.start)) {
/*
* Need to append new hole at end.
* Last hole is p (and it's not NULL).
*/
temp = (struct sackhole *)
pool_get(&sackhl_pool, PR_NOWAIT);
if (temp == NULL)
goto done; /* ENOBUFS */
temp->start = tp->rcv_lastsack;
temp->end = sack.start;
temp->dups = min(tcprexmtthresh,
((sack.end - sack.start)/tp->t_maxseg));
if (temp->dups < 1)
temp->dups = 1;
temp->rxmit = temp->start;
temp->next = 0;
p->next = temp;
tp->rcv_lastsack = sack.end;
tp->snd_numholes++;
}
}
done:
#if defined(TCP_SACK) && defined(TCP_FACK)
/*
* Update retran_data and snd_awnd. Go through the list of
* holes. Increment retran_data by (hole->rxmit - hole->start).
*/
tp->retran_data = 0;
cur = tp->snd_holes;
while (cur) {
tp->retran_data += cur->rxmit - cur->start;
cur = cur->next;
}
tp->snd_awnd = tcp_seq_subtract(tp->snd_nxt, tp->snd_fack) +
tp->retran_data;
#endif /* TCP_FACK */
return;
}
/*
* Delete stale (i.e, cumulatively ack'd) holes. Hole is deleted only if
* it is completely acked; otherwise, tcp_sack_option(), called from
* tcp_dooptions(), will fix up the hole.
*/
void
tcp_del_sackholes(struct tcpcb *tp, struct tcphdr *th)
{
if (tp->sack_enable && tp->t_state != TCPS_LISTEN) {
/* max because this could be an older ack just arrived */
tcp_seq lastack = SEQ_GT(th->th_ack, tp->snd_una) ?
th->th_ack : tp->snd_una;
struct sackhole *cur = tp->snd_holes;
struct sackhole *prev;
while (cur)
if (SEQ_LEQ(cur->end, lastack)) {
prev = cur;
cur = cur->next;
pool_put(&sackhl_pool, prev);
tp->snd_numholes--;
} else if (SEQ_LT(cur->start, lastack)) {
cur->start = lastack;
if (SEQ_LT(cur->rxmit, cur->start))
cur->rxmit = cur->start;
break;
} else
break;
tp->snd_holes = cur;
}
}
/*
* Delete all receiver-side SACK information.
*/
void
tcp_clean_sackreport(struct tcpcb *tp)
{
int i;
tp->rcv_numsacks = 0;
for (i = 0; i < MAX_SACK_BLKS; i++)
tp->sackblks[i].start = tp->sackblks[i].end=0;
}
/*
* Checks for partial ack. If partial ack arrives, turn off retransmission
* timer, deflate the window, do not clear tp->t_dupacks, and return 1.
* If the ack advances at least to tp->snd_last, return 0.
*/
int
tcp_sack_partialack(struct tcpcb *tp, struct tcphdr *th)
{
if (SEQ_LT(th->th_ack, tp->snd_last)) {
/* Turn off retx. timer (will start again next segment) */
TCP_TIMER_DISARM(tp, TCPT_REXMT);
tp->t_rtttime = 0;
#ifndef TCP_FACK
/*
* Partial window deflation. This statement relies on the
* fact that tp->snd_una has not been updated yet. In FACK
* hold snd_cwnd constant during fast recovery.
*/
if (tp->snd_cwnd > (th->th_ack - tp->snd_una)) {
tp->snd_cwnd -= th->th_ack - tp->snd_una;
tp->snd_cwnd += tp->t_maxseg;
} else
tp->snd_cwnd = tp->t_maxseg;
#endif
return (1);
}
return (0);
}
#endif /* TCP_SACK */
/*
* 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.
*/
void
tcp_pulloutofband(struct socket *so, u_int urgent, struct mbuf *m, int off)
{
int cnt = off + urgent - 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--;
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.
*/
void
tcp_xmit_timer(struct tcpcb *tp, int rtt)
{
short delta;
short rttmin;
if (rtt < 0)
rtt = 0;
else if (rtt > TCP_RTT_MAX)
rtt = TCP_RTT_MAX;
tcpstat.tcps_rttupdated++;
if (tp->t_srtt != 0) {
/*
* delta is fixed point with 2 (TCP_RTT_BASE_SHIFT) bits
* after the binary point (scaled by 4), whereas
* srtt is stored as fixed point with 5 bits after the
* binary point (i.e., scaled by 32). 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).
*/
delta = (rtt << TCP_RTT_BASE_SHIFT) -
(tp->t_srtt >> TCP_RTT_SHIFT);
if ((tp->t_srtt += delta) <= 0)
tp->t_srtt = 1 << TCP_RTT_BASE_SHIFT;
/*
* 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);
if ((tp->t_rttvar += delta) <= 0)
tp->t_rttvar = 1 << TCP_RTT_BASE_SHIFT;
} 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 + 1) << (TCP_RTT_SHIFT + TCP_RTT_BASE_SHIFT);
tp->t_rttvar = (rtt + 1) <<
(TCP_RTTVAR_SHIFT + TCP_RTT_BASE_SHIFT - 1);
}
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).
*/
rttmin = min(max(rtt + 2, tp->t_rttmin), TCPTV_REXMTMAX);
TCPT_RANGESET(tp->t_rxtcur, TCP_REXMTVAL(tp), rttmin, 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: offer == -1 indicates that the maxseg size changed due to
* Path MTU discovery.
*/
int
tcp_mss(struct tcpcb *tp, int offer)
{
struct rtentry *rt;
struct ifnet *ifp;
int mss, mssopt;
int iphlen;
struct inpcb *inp;
inp = tp->t_inpcb;
mssopt = mss = tcp_mssdflt;
rt = in_pcbrtentry(inp);
if (rt == NULL)
goto out;
ifp = rt->rt_ifp;
switch (tp->pf) {
#ifdef INET6
case AF_INET6:
iphlen = sizeof(struct ip6_hdr);
break;
#endif
case AF_INET:
iphlen = sizeof(struct ip);
break;
default:
/* the family does not support path MTU discovery */
goto out;
}
#ifdef RTV_MTU
/*
* if there's an mtu associated with the route and we support
* path MTU discovery for the underlying protocol family, use it.
*/
if (rt->rt_rmx.rmx_mtu) {
/*
* One may wish to lower MSS to take into account options,
* especially security-related options.
*/
if (tp->pf == AF_INET6 && rt->rt_rmx.rmx_mtu < IPV6_MMTU) {
/*
* RFC2460 section 5, last paragraph: if path MTU is
* smaller than 1280, use 1280 as packet size and
* attach fragment header.
*/
mss = IPV6_MMTU - iphlen - sizeof(struct ip6_frag) -
sizeof(struct tcphdr);
} else
mss = rt->rt_rmx.rmx_mtu - iphlen - sizeof(struct tcphdr);
} else
#endif /* RTV_MTU */
if (!ifp)
/*
* ifp may be null and rmx_mtu may be zero in certain
* v6 cases (e.g., if ND wasn't able to resolve the
* destination host.
*/
goto out;
else if (ifp->if_flags & IFF_LOOPBACK)
mss = ifp->if_mtu - iphlen - sizeof(struct tcphdr);
else if (tp->pf == AF_INET) {
if (ip_mtudisc)
mss = ifp->if_mtu - iphlen - sizeof(struct tcphdr);
else if (inp && in_localaddr(inp->inp_faddr, inp->inp_rtableid))
mss = ifp->if_mtu - iphlen - sizeof(struct tcphdr);
}
#ifdef INET6
else if (tp->pf == AF_INET6) {
/*
* for IPv6, path MTU discovery is always turned on,
* or the node must use packet size <= 1280.
*/
mss = IN6_LINKMTU(ifp) - iphlen - sizeof(struct tcphdr);
}
#endif /* INET6 */
/* Calculate the value that we offer in TCPOPT_MAXSEG */
if (offer != -1) {
#ifndef INET6
mssopt = ifp->if_mtu - iphlen - sizeof(struct tcphdr);
#else
if (tp->pf == AF_INET6)
mssopt = IN6_LINKMTU(ifp) - iphlen -
sizeof(struct tcphdr);
else
mssopt = ifp->if_mtu - iphlen - sizeof(struct tcphdr);
#endif
mssopt = max(tcp_mssdflt, mssopt);
}
out:
/*
* The current mss, t_maxseg, is initialized to the default value.
* If we compute a smaller value, reduce the current mss.
* If we compute a larger value, return it for use in sending
* a max seg size option, but don't store it for use
* unless we received an offer at least that large from peer.
*
* However, do not accept offers lower than the minimum of
* the interface MTU and 216.
*/
if (offer > 0)
tp->t_peermss = offer;
if (tp->t_peermss)
mss = min(mss, max(tp->t_peermss, 216));
/* sanity - at least max opt. space */
mss = max(mss, 64);
/*
* 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;
if ((tp->t_flags & (TF_REQ_TSTMP|TF_NOOPT)) == TF_REQ_TSTMP &&
(tp->t_flags & TF_RCVD_TSTMP) == TF_RCVD_TSTMP)
mss -= TCPOLEN_TSTAMP_APPA;
#ifdef TCP_SIGNATURE
if (tp->t_flags & TF_SIGNATURE)
mss -= TCPOLEN_SIGLEN;
#endif
if (offer == -1) {
/* mss changed due to Path MTU discovery */
tp->t_flags &= ~TF_PMTUD_PEND;
tp->t_pmtud_mtu_sent = 0;
tp->t_pmtud_mss_acked = 0;
if (mss < tp->t_maxseg) {
/*
* Follow suggestion in RFC 2414 to reduce the
* congestion window by the ratio of the old
* segment size to the new segment size.
*/
tp->snd_cwnd = ulmax((tp->snd_cwnd / tp->t_maxseg) *
mss, mss);
}
} else if (tcp_do_rfc3390) {
/* increase initial window */
tp->snd_cwnd = ulmin(4 * mss, ulmax(2 * mss, 4380));
} else
tp->snd_cwnd = mss;
tp->t_maxseg = mss;
return (offer != -1 ? mssopt : mss);
}
u_int
tcp_hdrsz(struct tcpcb *tp)
{
u_int hlen;
switch (tp->pf) {
#ifdef INET6
case AF_INET6:
hlen = sizeof(struct ip6_hdr);
break;
#endif
case AF_INET:
hlen = sizeof(struct ip);
break;
default:
hlen = 0;
break;
}
hlen += sizeof(struct tcphdr);
if ((tp->t_flags & (TF_REQ_TSTMP|TF_NOOPT)) == TF_REQ_TSTMP &&
(tp->t_flags & TF_RCVD_TSTMP) == TF_RCVD_TSTMP)
hlen += TCPOLEN_TSTAMP_APPA;
#ifdef TCP_SIGNATURE
if (tp->t_flags & TF_SIGNATURE)
hlen += TCPOLEN_SIGLEN;
#endif
return (hlen);
}
/*
* Set connection variables based on the effective MSS.
* We are passed the TCPCB for the actual connection. If we
* are the server, we are called by the compressed state engine
* when the 3-way handshake is complete. If we are the client,
* we are called when we receive the SYN,ACK from the server.
*
* NOTE: The t_maxseg value must be initialized in the TCPCB
* before this routine is called!
*/
void
tcp_mss_update(struct tcpcb *tp)
{
int mss;
u_long bufsize;
struct rtentry *rt;
struct socket *so;
so = tp->t_inpcb->inp_socket;
mss = tp->t_maxseg;
rt = in_pcbrtentry(tp->t_inpcb);
if (rt == NULL)
return;
bufsize = so->so_snd.sb_hiwat;
if (bufsize < mss) {
mss = bufsize;
/* Update t_maxseg and t_maxopd */
tcp_mss(tp, mss);
} else {
bufsize = roundup(bufsize, mss);
if (bufsize > sb_max)
bufsize = sb_max;
(void)sbreserve(&so->so_snd, bufsize);
}
bufsize = so->so_rcv.sb_hiwat;
if (bufsize > mss) {
bufsize = roundup(bufsize, mss);
if (bufsize > sb_max)
bufsize = sb_max;
(void)sbreserve(&so->so_rcv, bufsize);
}
}
#if defined (TCP_SACK)
/*
* Checks for partial ack. If partial ack arrives, force the retransmission
* of the next unacknowledged segment, do not clear tp->t_dupacks, and return
* 1. By setting snd_nxt to ti_ack, this forces retransmission timer to
* be started again. If the ack advances at least to tp->snd_last, return 0.
*/
int
tcp_newreno(struct tcpcb *tp, struct tcphdr *th)
{
if (SEQ_LT(th->th_ack, tp->snd_last)) {
/*
* snd_una has not been updated and the socket send buffer
* not yet drained of the acked data, so we have to leave
* snd_una as it was to get the correct data offset in
* tcp_output().
*/
tcp_seq onxt = tp->snd_nxt;
u_long ocwnd = tp->snd_cwnd;
TCP_TIMER_DISARM(tp, TCPT_REXMT);
tp->t_rtttime = 0;
tp->snd_nxt = th->th_ack;
/*
* Set snd_cwnd to one segment beyond acknowledged offset
* (tp->snd_una not yet updated when this function is called)
*/
tp->snd_cwnd = tp->t_maxseg + (th->th_ack - tp->snd_una);
(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.
*/
if (tp->snd_cwnd > th->th_ack - tp->snd_una)
tp->snd_cwnd -= th->th_ack - tp->snd_una;
else
tp->snd_cwnd = 0;
tp->snd_cwnd += tp->t_maxseg;
return 1;
}
return 0;
}
#endif /* TCP_SACK */
int
tcp_mss_adv(struct ifnet *ifp, int af)
{
int mss = 0;
int iphlen;
switch (af) {
case AF_INET:
if (ifp != NULL)
mss = ifp->if_mtu;
iphlen = sizeof(struct ip);
break;
#ifdef INET6
case AF_INET6:
if (ifp != NULL)
mss = IN6_LINKMTU(ifp);
iphlen = sizeof(struct ip6_hdr);
break;
#endif
}
mss = mss - iphlen - sizeof(struct tcphdr);
return (max(mss, tcp_mssdflt));
}
/*
* TCP compressed state engine. Currently used to hold compressed
* state for SYN_RECEIVED.
*/
u_long syn_cache_count;
u_int32_t syn_hash1, syn_hash2;
#define SYN_HASH(sa, sp, dp) \
((((sa)->s_addr^syn_hash1)*(((((u_int32_t)(dp))<<16) + \
((u_int32_t)(sp)))^syn_hash2)))
#ifndef INET6
#define SYN_HASHALL(hash, src, dst) \
do { \
hash = SYN_HASH(&((struct sockaddr_in *)(src))->sin_addr, \
((struct sockaddr_in *)(src))->sin_port, \
((struct sockaddr_in *)(dst))->sin_port); \
} while (/*CONSTCOND*/ 0)
#else
#define SYN_HASH6(sa, sp, dp) \
((((sa)->s6_addr32[0] ^ (sa)->s6_addr32[3] ^ syn_hash1) * \
(((((u_int32_t)(dp))<<16) + ((u_int32_t)(sp)))^syn_hash2)) \
& 0x7fffffff)
#define SYN_HASHALL(hash, src, dst) \
do { \
switch ((src)->sa_family) { \
case AF_INET: \
hash = SYN_HASH(&((struct sockaddr_in *)(src))->sin_addr, \
((struct sockaddr_in *)(src))->sin_port, \
((struct sockaddr_in *)(dst))->sin_port); \
break; \
case AF_INET6: \
hash = SYN_HASH6(&((struct sockaddr_in6 *)(src))->sin6_addr, \
((struct sockaddr_in6 *)(src))->sin6_port, \
((struct sockaddr_in6 *)(dst))->sin6_port); \
break; \
default: \
hash = 0; \
} \
} while (/*CONSTCOND*/0)
#endif /* INET6 */
#define SYN_CACHE_RM(sc) \
do { \
(sc)->sc_flags |= SCF_DEAD; \
TAILQ_REMOVE(&tcp_syn_cache[(sc)->sc_bucketidx].sch_bucket, \
(sc), sc_bucketq); \
(sc)->sc_tp = NULL; \
LIST_REMOVE((sc), sc_tpq); \
tcp_syn_cache[(sc)->sc_bucketidx].sch_length--; \
timeout_del(&(sc)->sc_timer); \
syn_cache_count--; \
} while (/*CONSTCOND*/0)
#define SYN_CACHE_PUT(sc) \
do { \
if ((sc)->sc_ipopts) \
(void) m_free((sc)->sc_ipopts); \
if ((sc)->sc_route4.ro_rt != NULL) \
RTFREE((sc)->sc_route4.ro_rt); \
timeout_set(&(sc)->sc_timer, syn_cache_reaper, (sc)); \
timeout_add(&(sc)->sc_timer, 0); \
} while (/*CONSTCOND*/0)
struct pool syn_cache_pool;
/*
* We don't estimate RTT with SYNs, so each packet starts with the default
* RTT and each timer step has a fixed timeout value.
*/
#define SYN_CACHE_TIMER_ARM(sc) \
do { \
TCPT_RANGESET((sc)->sc_rxtcur, \
TCPTV_SRTTDFLT * tcp_backoff[(sc)->sc_rxtshift], TCPTV_MIN, \
TCPTV_REXMTMAX); \
if (!timeout_initialized(&(sc)->sc_timer)) \
timeout_set(&(sc)->sc_timer, syn_cache_timer, (sc)); \
timeout_add(&(sc)->sc_timer, (sc)->sc_rxtcur * (hz / PR_SLOWHZ)); \
} while (/*CONSTCOND*/0)
#define SYN_CACHE_TIMESTAMP(sc) tcp_now + (sc)->sc_modulate
void
syn_cache_init()
{
int i;
/* Initialize the hash buckets. */
for (i = 0; i < tcp_syn_cache_size; i++)
TAILQ_INIT(&tcp_syn_cache[i].sch_bucket);
/* Initialize the syn cache pool. */
pool_init(&syn_cache_pool, sizeof(struct syn_cache), 0, 0, 0,
"synpl", NULL);
}
void
syn_cache_insert(struct syn_cache *sc, struct tcpcb *tp)
{
struct syn_cache_head *scp;
struct syn_cache *sc2;
int s;
/*
* If there are no entries in the hash table, reinitialize
* the hash secrets.
*/
if (syn_cache_count == 0) {
syn_hash1 = arc4random();
syn_hash2 = arc4random();
}
SYN_HASHALL(sc->sc_hash, &sc->sc_src.sa, &sc->sc_dst.sa);
sc->sc_bucketidx = sc->sc_hash % tcp_syn_cache_size;
scp = &tcp_syn_cache[sc->sc_bucketidx];
/*
* Make sure that we don't overflow the per-bucket
* limit or the total cache size limit.
*/
s = splsoftnet();
if (scp->sch_length >= tcp_syn_bucket_limit) {
tcpstat.tcps_sc_bucketoverflow++;
/*
* The bucket is full. Toss the oldest element in the
* bucket. This will be the first entry in the bucket.
*/
sc2 = TAILQ_FIRST(&scp->sch_bucket);
#ifdef DIAGNOSTIC
/*
* This should never happen; we should always find an
* entry in our bucket.
*/
if (sc2 == NULL)
panic("syn_cache_insert: bucketoverflow: impossible");
#endif
SYN_CACHE_RM(sc2);
SYN_CACHE_PUT(sc2);
} else if (syn_cache_count >= tcp_syn_cache_limit) {
struct syn_cache_head *scp2, *sce;
tcpstat.tcps_sc_overflowed++;
/*
* The cache is full. Toss the oldest entry in the
* first non-empty bucket we can find.
*
* XXX We would really like to toss the oldest
* entry in the cache, but we hope that this
* condition doesn't happen very often.
*/
scp2 = scp;
if (TAILQ_EMPTY(&scp2->sch_bucket)) {
sce = &tcp_syn_cache[tcp_syn_cache_size];
for (++scp2; scp2 != scp; scp2++) {
if (scp2 >= sce)
scp2 = &tcp_syn_cache[0];
if (! TAILQ_EMPTY(&scp2->sch_bucket))
break;
}
#ifdef DIAGNOSTIC
/*
* This should never happen; we should always find a
* non-empty bucket.
*/
if (scp2 == scp)
panic("syn_cache_insert: cacheoverflow: "
"impossible");
#endif
}
sc2 = TAILQ_FIRST(&scp2->sch_bucket);
SYN_CACHE_RM(sc2);
SYN_CACHE_PUT(sc2);
}
/*
* Initialize the entry's timer.
*/
sc->sc_rxttot = 0;
sc->sc_rxtshift = 0;
SYN_CACHE_TIMER_ARM(sc);
/* Link it from tcpcb entry */
LIST_INSERT_HEAD(&tp->t_sc, sc, sc_tpq);
/* Put it into the bucket. */
TAILQ_INSERT_TAIL(&scp->sch_bucket, sc, sc_bucketq);
scp->sch_length++;
syn_cache_count++;
tcpstat.tcps_sc_added++;
splx(s);
}
/*
* Walk the timer queues, looking for SYN,ACKs that need to be retransmitted.
* If we have retransmitted an entry the maximum number of times, expire
* that entry.
*/
void
syn_cache_timer(void *arg)
{
struct syn_cache *sc = arg;
int s;
s = splsoftnet();
if (sc->sc_flags & SCF_DEAD) {
splx(s);
return;
}
if (__predict_false(sc->sc_rxtshift == TCP_MAXRXTSHIFT)) {
/* Drop it -- too many retransmissions. */
goto dropit;
}
/*
* Compute the total amount of time this entry has
* been on a queue. If this entry has been on longer
* than the keep alive timer would allow, expire it.
*/
sc->sc_rxttot += sc->sc_rxtcur;
if (sc->sc_rxttot >= tcptv_keep_init)
goto dropit;
tcpstat.tcps_sc_retransmitted++;
(void) syn_cache_respond(sc, NULL);
/* Advance the timer back-off. */
sc->sc_rxtshift++;
SYN_CACHE_TIMER_ARM(sc);
splx(s);
return;
dropit:
tcpstat.tcps_sc_timed_out++;
SYN_CACHE_RM(sc);
SYN_CACHE_PUT(sc);
splx(s);
}
void
syn_cache_reaper(void *arg)
{
struct syn_cache *sc = arg;
int s;
s = splsoftnet();
pool_put(&syn_cache_pool, (sc));
splx(s);
return;
}
/*
* Remove syn cache created by the specified tcb entry,
* because this does not make sense to keep them
* (if there's no tcb entry, syn cache entry will never be used)
*/
void
syn_cache_cleanup(struct tcpcb *tp)
{
struct syn_cache *sc, *nsc;
int s;
s = splsoftnet();
for (sc = LIST_FIRST(&tp->t_sc); sc != NULL; sc = nsc) {
nsc = LIST_NEXT(sc, sc_tpq);
#ifdef DIAGNOSTIC
if (sc->sc_tp != tp)
panic("invalid sc_tp in syn_cache_cleanup");
#endif
SYN_CACHE_RM(sc);
SYN_CACHE_PUT(sc);
}
/* just for safety */
LIST_INIT(&tp->t_sc);
splx(s);
}
/*
* Find an entry in the syn cache.
*/
struct syn_cache *
syn_cache_lookup(struct sockaddr *src, struct sockaddr *dst,
struct syn_cache_head **headp, u_int rtableid)
{
struct syn_cache *sc;
struct syn_cache_head *scp;
u_int32_t hash;
int s;
SYN_HASHALL(hash, src, dst);
scp = &tcp_syn_cache[hash % tcp_syn_cache_size];
*headp = scp;
s = splsoftnet();
for (sc = TAILQ_FIRST(&scp->sch_bucket); sc != NULL;
sc = TAILQ_NEXT(sc, sc_bucketq)) {
if (sc->sc_hash != hash)
continue;
if (!bcmp(&sc->sc_src, src, src->sa_len) &&
!bcmp(&sc->sc_dst, dst, dst->sa_len) &&
rtable_l2(rtableid) == rtable_l2(sc->sc_rtableid)) {
splx(s);
return (sc);
}
}
splx(s);
return (NULL);
}
/*
* This function gets called when we receive an ACK for a
* socket in the LISTEN state. We look up the connection
* in the syn cache, and if its there, we pull it out of
* the cache and turn it into a full-blown connection in
* the SYN-RECEIVED state.
*
* The return values may not be immediately obvious, and their effects
* can be subtle, so here they are:
*
* NULL SYN was not found in cache; caller should drop the
* packet and send an RST.
*
* -1 We were unable to create the new connection, and are
* aborting it. An ACK,RST is being sent to the peer
* (unless we got screwey sequence numbners; see below),
* because the 3-way handshake has been completed. Caller
* should not free the mbuf, since we may be using it. If
* we are not, we will free it.
*
* Otherwise, the return value is a pointer to the new socket
* associated with the connection.
*/
struct socket *
syn_cache_get(struct sockaddr *src, struct sockaddr *dst, struct tcphdr *th,
u_int hlen, u_int tlen, struct socket *so, struct mbuf *m)
{
struct syn_cache *sc;
struct syn_cache_head *scp;
struct inpcb *inp = NULL;
struct tcpcb *tp = 0;
struct mbuf *am;
int s;
struct socket *oso;
s = splsoftnet();
if ((sc = syn_cache_lookup(src, dst, &scp,
sotoinpcb(so)->inp_rtableid)) == NULL) {
splx(s);
return (NULL);
}
/*
* Verify the sequence and ack numbers. Try getting the correct
* response again.
*/
if ((th->th_ack != sc->sc_iss + 1) ||
SEQ_LEQ(th->th_seq, sc->sc_irs) ||
SEQ_GT(th->th_seq, sc->sc_irs + 1 + sc->sc_win)) {
(void) syn_cache_respond(sc, m);
splx(s);
return ((struct socket *)(-1));
}
/* Remove this cache entry */
SYN_CACHE_RM(sc);
splx(s);
/*
* Ok, create the full blown connection, and set things up
* as they would have been set up if we had created the
* connection when the SYN arrived. If we can't create
* the connection, abort it.
*/
oso = so;
so = sonewconn(so, SS_ISCONNECTED);
if (so == NULL)
goto resetandabort;
inp = sotoinpcb(oso);
#ifdef IPSEC
/*
* We need to copy the required security levels
* from the old pcb. Ditto for any other
* IPsec-related information.
*/
{
struct inpcb *newinp = (struct inpcb *)so->so_pcb;
bcopy(inp->inp_seclevel, newinp->inp_seclevel,
sizeof(inp->inp_seclevel));
newinp->inp_secrequire = inp->inp_secrequire;
if (inp->inp_ipo != NULL) {
newinp->inp_ipo = inp->inp_ipo;
inp->inp_ipo->ipo_ref_count++;
}
if (inp->inp_ipsec_remotecred != NULL) {
newinp->inp_ipsec_remotecred = inp->inp_ipsec_remotecred;
inp->inp_ipsec_remotecred->ref_count++;
}
if (inp->inp_ipsec_remoteauth != NULL) {
newinp->inp_ipsec_remoteauth
= inp->inp_ipsec_remoteauth;
inp->inp_ipsec_remoteauth->ref_count++;
}
}
#endif /* IPSEC */
#ifdef INET6
/*
* inp still has the OLD in_pcb stuff, set the
* v6-related flags on the new guy, too.
*/
{
int flags = inp->inp_flags;
struct inpcb *oldinpcb = inp;
inp = (struct inpcb *)so->so_pcb;
inp->inp_flags |= (flags & INP_IPV6);
if ((inp->inp_flags & INP_IPV6) != 0) {
inp->inp_ipv6.ip6_hlim =
oldinpcb->inp_ipv6.ip6_hlim;
}
}
#else /* INET6 */
inp = (struct inpcb *)so->so_pcb;
#endif /* INET6 */
/* inherit rtable from listening socket */
inp->inp_rtableid = sc->sc_rtableid;
inp->inp_lport = th->th_dport;
switch (src->sa_family) {
#ifdef INET6
case AF_INET6:
inp->inp_laddr6 = ((struct sockaddr_in6 *)dst)->sin6_addr;
break;
#endif /* INET6 */
case AF_INET:
inp->inp_laddr = ((struct sockaddr_in *)dst)->sin_addr;
inp->inp_options = ip_srcroute();
if (inp->inp_options == NULL) {
inp->inp_options = sc->sc_ipopts;
sc->sc_ipopts = NULL;
}
break;
}
in_pcbrehash(inp);
/*
* Give the new socket our cached route reference.
*/
if (src->sa_family == AF_INET)
inp->inp_route = sc->sc_route4; /* struct assignment */
#ifdef INET6
else
inp->inp_route6 = sc->sc_route6;
#endif
sc->sc_route4.ro_rt = NULL;
am = m_get(M_DONTWAIT, MT_SONAME); /* XXX */
if (am == NULL)
goto resetandabort;
am->m_len = src->sa_len;
bcopy(src, mtod(am, caddr_t), src->sa_len);
switch (src->sa_family) {
case AF_INET:
/* drop IPv4 packet to AF_INET6 socket */
if (inp->inp_flags & INP_IPV6) {
(void) m_free(am);
goto resetandabort;
}
if (in_pcbconnect(inp, am)) {
(void) m_free(am);
goto resetandabort;
}
break;
#ifdef INET6
case AF_INET6:
if (in6_pcbconnect(inp, am)) {
(void) m_free(am);
goto resetandabort;
}
break;
#endif
}
(void) m_free(am);
tp = intotcpcb(inp);
tp->t_flags = sototcpcb(oso)->t_flags & TF_NODELAY;
if (sc->sc_request_r_scale != 15) {
tp->requested_s_scale = sc->sc_requested_s_scale;
tp->request_r_scale = sc->sc_request_r_scale;
tp->t_flags |= TF_REQ_SCALE|TF_RCVD_SCALE;
}
if (sc->sc_flags & SCF_TIMESTAMP)
tp->t_flags |= TF_REQ_TSTMP|TF_RCVD_TSTMP;
tp->t_template = tcp_template(tp);
if (tp->t_template == 0) {
tp = tcp_drop(tp, ENOBUFS); /* destroys socket */
so = NULL;
m_freem(m);
goto abort;
}
#ifdef TCP_SACK
tp->sack_enable = sc->sc_flags & SCF_SACK_PERMIT;
#endif
tp->ts_modulate = sc->sc_modulate;
tp->ts_recent = sc->sc_timestamp;
tp->iss = sc->sc_iss;
tp->irs = sc->sc_irs;
tcp_sendseqinit(tp);
#if defined (TCP_SACK) || defined(TCP_ECN)
tp->snd_last = tp->snd_una;
#endif /* TCP_SACK */
#if defined(TCP_SACK) && defined(TCP_FACK)
tp->snd_fack = tp->snd_una;
tp->retran_data = 0;
tp->snd_awnd = 0;
#endif /* TCP_FACK */
#ifdef TCP_ECN
if (sc->sc_flags & SCF_ECN_PERMIT) {
tp->t_flags |= TF_ECN_PERMIT;
tcpstat.tcps_ecn_accepts++;
}
#endif
#ifdef TCP_SACK
if (sc->sc_flags & SCF_SACK_PERMIT)
tp->t_flags |= TF_SACK_PERMIT;
#endif
#ifdef TCP_SIGNATURE
if (sc->sc_flags & SCF_SIGNATURE)
tp->t_flags |= TF_SIGNATURE;
#endif
tcp_rcvseqinit(tp);
tp->t_state = TCPS_SYN_RECEIVED;
tp->t_rcvtime = tcp_now;
TCP_TIMER_ARM(tp, TCPT_KEEP, tcptv_keep_init);
tcpstat.tcps_accepts++;
tcp_mss(tp, sc->sc_peermaxseg); /* sets t_maxseg */
if (sc->sc_peermaxseg)
tcp_mss_update(tp);
/* Reset initial window to 1 segment for retransmit */
if (sc->sc_rxtshift > 0)
tp->snd_cwnd = tp->t_maxseg;
tp->snd_wl1 = sc->sc_irs;
tp->rcv_up = sc->sc_irs + 1;
/*
* This is what whould 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;
TCP_TIMER_ARM(tp, TCPT_REXMT, tp->t_rxtcur);
if (sc->sc_win > 0 && SEQ_GT(tp->rcv_nxt + sc->sc_win, tp->rcv_adv))
tp->rcv_adv = tp->rcv_nxt + sc->sc_win;
tp->last_ack_sent = tp->rcv_nxt;
tcpstat.tcps_sc_completed++;
SYN_CACHE_PUT(sc);
return (so);
resetandabort:
tcp_respond(NULL, mtod(m, caddr_t), th, (tcp_seq)0, th->th_ack, TH_RST,
m->m_pkthdr.rdomain);
m_freem(m);
abort:
if (so != NULL)
(void) soabort(so);
SYN_CACHE_PUT(sc);
tcpstat.tcps_sc_aborted++;
return ((struct socket *)(-1));
}
/*
* This function is called when we get a RST for a
* non-existent connection, so that we can see if the
* connection is in the syn cache. If it is, zap it.
*/
void
syn_cache_reset(struct sockaddr *src, struct sockaddr *dst, struct tcphdr *th,
u_int rtableid)
{
struct syn_cache *sc;
struct syn_cache_head *scp;
int s = splsoftnet();
if ((sc = syn_cache_lookup(src, dst, &scp, rtableid)) == NULL) {
splx(s);
return;
}
if (SEQ_LT(th->th_seq, sc->sc_irs) ||
SEQ_GT(th->th_seq, sc->sc_irs+1)) {
splx(s);
return;
}
SYN_CACHE_RM(sc);
splx(s);
tcpstat.tcps_sc_reset++;
SYN_CACHE_PUT(sc);
}
void
syn_cache_unreach(struct sockaddr *src, struct sockaddr *dst, struct tcphdr *th,
u_int rtableid)
{
struct syn_cache *sc;
struct syn_cache_head *scp;
int s;
s = splsoftnet();
if ((sc = syn_cache_lookup(src, dst, &scp, rtableid)) == NULL) {
splx(s);
return;
}
/* If the sequence number != sc_iss, then it's a bogus ICMP msg */
if (ntohl (th->th_seq) != sc->sc_iss) {
splx(s);
return;
}
/*
* If we've retransmitted 3 times and this is our second error,
* we remove the entry. Otherwise, we allow it to continue on.
* This prevents us from incorrectly nuking an entry during a
* spurious network outage.
*
* See tcp_notify().
*/
if ((sc->sc_flags & SCF_UNREACH) == 0 || sc->sc_rxtshift < 3) {
sc->sc_flags |= SCF_UNREACH;
splx(s);
return;
}
SYN_CACHE_RM(sc);
splx(s);
tcpstat.tcps_sc_unreach++;
SYN_CACHE_PUT(sc);
}
/*
* Given a LISTEN socket and an inbound SYN request, add
* this to the syn cache, and send back a segment:
* <SEQ=ISS><ACK=RCV_NXT><CTL=SYN,ACK>
* to the source.
*
* IMPORTANT NOTE: We do _NOT_ ACK data that might accompany the SYN.
* Doing so would require that we hold onto the data and deliver it
* to the application. However, if we are the target of a SYN-flood
* DoS attack, an attacker could send data which would eventually
* consume all available buffer space if it were ACKed. By not ACKing
* the data, we avoid this DoS scenario.
*/
int
syn_cache_add(struct sockaddr *src, struct sockaddr *dst, struct tcphdr *th,
u_int iphlen, struct socket *so, struct mbuf *m, u_char *optp, int optlen,
struct tcp_opt_info *oi, tcp_seq *issp)
{
struct tcpcb tb, *tp;
long win;
struct syn_cache *sc;
struct syn_cache_head *scp;
struct mbuf *ipopts;
tp = sototcpcb(so);
/*
* RFC1122 4.2.3.10, p. 104: discard bcast/mcast SYN
*
* Note this check is performed in tcp_input() very early on.
*/
/*
* Initialize some local state.
*/
win = sbspace(&so->so_rcv);
if (win > TCP_MAXWIN)
win = TCP_MAXWIN;
#ifdef TCP_SIGNATURE
if (optp || (tp->t_flags & TF_SIGNATURE)) {
#else
if (optp) {
#endif
bzero(&tb, sizeof(tb));
tb.pf = tp->pf;
#ifdef TCP_SACK
tb.sack_enable = tp->sack_enable;
#endif
tb.t_flags = tcp_do_rfc1323 ? (TF_REQ_SCALE|TF_REQ_TSTMP) : 0;
#ifdef TCP_SIGNATURE
if (tp->t_flags & TF_SIGNATURE)
tb.t_flags |= TF_SIGNATURE;
#endif
tb.t_state = TCPS_LISTEN;
if (tcp_dooptions(&tb, optp, optlen, th, m, iphlen, oi,
sotoinpcb(so)->inp_rtableid))
return (0);
} else
tb.t_flags = 0;
switch (src->sa_family) {
#ifdef INET
case AF_INET:
/*
* Remember the IP options, if any.
*/
ipopts = ip_srcroute();
break;
#endif
default:
ipopts = NULL;
}
/*
* See if we already have an entry for this connection.
* If we do, resend the SYN,ACK. We do not count this
* as a retransmission (XXX though maybe we should).
*/
if ((sc = syn_cache_lookup(src, dst, &scp, sotoinpcb(so)->inp_rtableid))
!= NULL) {
tcpstat.tcps_sc_dupesyn++;
if (ipopts) {
/*
* If we were remembering a previous source route,
* forget it and use the new one we've been given.
*/
if (sc->sc_ipopts)
(void) m_free(sc->sc_ipopts);
sc->sc_ipopts = ipopts;
}
sc->sc_timestamp = tb.ts_recent;
if (syn_cache_respond(sc, m) == 0) {
tcpstat.tcps_sndacks++;
tcpstat.tcps_sndtotal++;
}
return (1);
}
sc = pool_get(&syn_cache_pool, PR_NOWAIT|PR_ZERO);
if (sc == NULL) {
if (ipopts)
(void) m_free(ipopts);
return (0);
}
/*
* Fill in the cache, and put the necessary IP and TCP
* options into the reply.
*/
bcopy(src, &sc->sc_src, src->sa_len);
bcopy(dst, &sc->sc_dst, dst->sa_len);
sc->sc_rtableid = sotoinpcb(so)->inp_rtableid;
sc->sc_flags = 0;
sc->sc_ipopts = ipopts;
sc->sc_irs = th->th_seq;
sc->sc_iss = issp ? *issp : arc4random();
sc->sc_peermaxseg = oi->maxseg;
sc->sc_ourmaxseg = tcp_mss_adv(m->m_flags & M_PKTHDR ?
m->m_pkthdr.rcvif : NULL, sc->sc_src.sa.sa_family);
sc->sc_win = win;
sc->sc_timestamp = tb.ts_recent;
if ((tb.t_flags & (TF_REQ_TSTMP|TF_RCVD_TSTMP)) ==
(TF_REQ_TSTMP|TF_RCVD_TSTMP)) {
sc->sc_flags |= SCF_TIMESTAMP;
sc->sc_modulate = arc4random();
}
if ((tb.t_flags & (TF_RCVD_SCALE|TF_REQ_SCALE)) ==
(TF_RCVD_SCALE|TF_REQ_SCALE)) {
sc->sc_requested_s_scale = tb.requested_s_scale;
sc->sc_request_r_scale = 0;
/*
* Pick the smallest possible scaling factor that
* will still allow us to scale up to sb_max.
*
* We do this because there are broken firewalls that
* will corrupt the window scale option, leading to
* the other endpoint believing that our advertised
* window is unscaled. At scale factors larger than
* 5 the unscaled window will drop below 1500 bytes,
* leading to serious problems when traversing these
* broken firewalls.
*
* With the default sbmax of 256K, a scale factor
* of 3 will be chosen by this algorithm. Those who
* choose a larger sbmax should watch out
* for the compatiblity problems mentioned above.
*
* RFC1323: The Window field in a SYN (i.e., a <SYN>
* or <SYN,ACK>) segment itself is never scaled.
*/
while (sc->sc_request_r_scale < TCP_MAX_WINSHIFT &&
(TCP_MAXWIN << sc->sc_request_r_scale) < sb_max)
sc->sc_request_r_scale++;
} else {
sc->sc_requested_s_scale = 15;
sc->sc_request_r_scale = 15;
}
#ifdef TCP_ECN
/*
* if both ECE and CWR flag bits are set, peer is ECN capable.
*/
if (tcp_do_ecn &&
(th->th_flags & (TH_ECE|TH_CWR)) == (TH_ECE|TH_CWR))
sc->sc_flags |= SCF_ECN_PERMIT;
#endif
#ifdef TCP_SACK
/*
* Set SCF_SACK_PERMIT if peer did send a SACK_PERMITTED option
* (i.e., if tcp_dooptions() did set TF_SACK_PERMIT).
*/
if (tb.sack_enable && (tb.t_flags & TF_SACK_PERMIT))
sc->sc_flags |= SCF_SACK_PERMIT;
#endif
#ifdef TCP_SIGNATURE
if (tb.t_flags & TF_SIGNATURE)
sc->sc_flags |= SCF_SIGNATURE;
#endif
sc->sc_tp = tp;
if (syn_cache_respond(sc, m) == 0) {
syn_cache_insert(sc, tp);
tcpstat.tcps_sndacks++;
tcpstat.tcps_sndtotal++;
} else {
SYN_CACHE_PUT(sc);
tcpstat.tcps_sc_dropped++;
}
return (1);
}
int
syn_cache_respond(struct syn_cache *sc, struct mbuf *m)
{
struct route *ro;
u_int8_t *optp;
int optlen, error;
u_int16_t tlen;
struct ip *ip = NULL;
#ifdef INET6
struct ip6_hdr *ip6 = NULL;
#endif
struct tcphdr *th;
u_int hlen;
struct inpcb *inp;
switch (sc->sc_src.sa.sa_family) {
case AF_INET:
hlen = sizeof(struct ip);
ro = &sc->sc_route4;
break;
#ifdef INET6
case AF_INET6:
hlen = sizeof(struct ip6_hdr);
ro = (struct route *)&sc->sc_route6;
break;
#endif
default:
if (m)
m_freem(m);
return (EAFNOSUPPORT);
}
/* Compute the size of the TCP options. */
optlen = 4 + (sc->sc_request_r_scale != 15 ? 4 : 0) +
#ifdef TCP_SACK
((sc->sc_flags & SCF_SACK_PERMIT) ? 4 : 0) +
#endif
#ifdef TCP_SIGNATURE
((sc->sc_flags & SCF_SIGNATURE) ? TCPOLEN_SIGLEN : 0) +
#endif
((sc->sc_flags & SCF_TIMESTAMP) ? TCPOLEN_TSTAMP_APPA : 0);
tlen = hlen + sizeof(struct tcphdr) + optlen;
/*
* Create the IP+TCP header from scratch.
*/
if (m)
m_freem(m);
#ifdef DIAGNOSTIC
if (max_linkhdr + tlen > MCLBYTES)
return (ENOBUFS);
#endif
MGETHDR(m, M_DONTWAIT, MT_DATA);
if (m && max_linkhdr + tlen > MHLEN) {
MCLGET(m, M_DONTWAIT);
if ((m->m_flags & M_EXT) == 0) {
m_freem(m);
m = NULL;
}
}
if (m == NULL)
return (ENOBUFS);
/* Fixup the mbuf. */
m->m_data += max_linkhdr;
m->m_len = m->m_pkthdr.len = tlen;
m->m_pkthdr.rcvif = NULL;
m->m_pkthdr.rdomain = sc->sc_rtableid;
memset(mtod(m, u_char *), 0, tlen);
switch (sc->sc_src.sa.sa_family) {
case AF_INET:
ip = mtod(m, struct ip *);
ip->ip_dst = sc->sc_src.sin.sin_addr;
ip->ip_src = sc->sc_dst.sin.sin_addr;
ip->ip_p = IPPROTO_TCP;
th = (struct tcphdr *)(ip + 1);
th->th_dport = sc->sc_src.sin.sin_port;
th->th_sport = sc->sc_dst.sin.sin_port;
break;
#ifdef INET6
case AF_INET6:
ip6 = mtod(m, struct ip6_hdr *);
ip6->ip6_dst = sc->sc_src.sin6.sin6_addr;
ip6->ip6_src = sc->sc_dst.sin6.sin6_addr;
ip6->ip6_nxt = IPPROTO_TCP;
/* ip6_plen will be updated in ip6_output() */
th = (struct tcphdr *)(ip6 + 1);
th->th_dport = sc->sc_src.sin6.sin6_port;
th->th_sport = sc->sc_dst.sin6.sin6_port;
break;
#endif
default:
th = NULL;
}
th->th_seq = htonl(sc->sc_iss);
th->th_ack = htonl(sc->sc_irs + 1);
th->th_off = (sizeof(struct tcphdr) + optlen) >> 2;
th->th_flags = TH_SYN|TH_ACK;
#ifdef TCP_ECN
/* Set ECE for SYN-ACK if peer supports ECN. */
if (tcp_do_ecn && (sc->sc_flags & SCF_ECN_PERMIT))
th->th_flags |= TH_ECE;
#endif
th->th_win = htons(sc->sc_win);
/* th_sum already 0 */
/* th_urp already 0 */
/* Tack on the TCP options. */
optp = (u_int8_t *)(th + 1);
*optp++ = TCPOPT_MAXSEG;
*optp++ = 4;
*optp++ = (sc->sc_ourmaxseg >> 8) & 0xff;
*optp++ = sc->sc_ourmaxseg & 0xff;
#ifdef TCP_SACK
/* Include SACK_PERMIT_HDR option if peer has already done so. */
if (sc->sc_flags & SCF_SACK_PERMIT) {
*((u_int32_t *)optp) = htonl(TCPOPT_SACK_PERMIT_HDR);
optp += 4;
}
#endif
if (sc->sc_request_r_scale != 15) {
*((u_int32_t *)optp) = htonl(TCPOPT_NOP << 24 |
TCPOPT_WINDOW << 16 | TCPOLEN_WINDOW << 8 |
sc->sc_request_r_scale);
optp += 4;
}
if (sc->sc_flags & SCF_TIMESTAMP) {
u_int32_t *lp = (u_int32_t *)(optp);
/* Form timestamp option as shown in appendix A of RFC 1323. */
*lp++ = htonl(TCPOPT_TSTAMP_HDR);
*lp++ = htonl(SYN_CACHE_TIMESTAMP(sc));
*lp = htonl(sc->sc_timestamp);
optp += TCPOLEN_TSTAMP_APPA;
}
#ifdef TCP_SIGNATURE
if (sc->sc_flags & SCF_SIGNATURE) {
union sockaddr_union src, dst;
struct tdb *tdb;
bzero(&src, sizeof(union sockaddr_union));
bzero(&dst, sizeof(union sockaddr_union));
src.sa.sa_len = sc->sc_src.sa.sa_len;
src.sa.sa_family = sc->sc_src.sa.sa_family;
dst.sa.sa_len = sc->sc_dst.sa.sa_len;
dst.sa.sa_family = sc->sc_dst.sa.sa_family;
switch (sc->sc_src.sa.sa_family) {
case 0: /*default to PF_INET*/
#ifdef INET
case AF_INET:
src.sin.sin_addr = mtod(m, struct ip *)->ip_src;
dst.sin.sin_addr = mtod(m, struct ip *)->ip_dst;
break;
#endif /* INET */
#ifdef INET6
case AF_INET6:
src.sin6.sin6_addr = mtod(m, struct ip6_hdr *)->ip6_src;
dst.sin6.sin6_addr = mtod(m, struct ip6_hdr *)->ip6_dst;
break;
#endif /* INET6 */
}
tdb = gettdbbysrcdst(rtable_l2(sc->sc_rtableid),
0, &src, &dst, IPPROTO_TCP);
if (tdb == NULL) {
if (m)
m_freem(m);
return (EPERM);
}
/* Send signature option */
*(optp++) = TCPOPT_SIGNATURE;
*(optp++) = TCPOLEN_SIGNATURE;
if (tcp_signature(tdb, sc->sc_src.sa.sa_family, m, th,
hlen, 0, optp) < 0) {
if (m)
m_freem(m);
return (EINVAL);
}
optp += 16;
/* Pad options list to the next 32 bit boundary and
* terminate it.
*/
*optp++ = TCPOPT_NOP;
*optp++ = TCPOPT_EOL;
}
#endif /* TCP_SIGNATURE */
/* Compute the packet's checksum. */
switch (sc->sc_src.sa.sa_family) {
case AF_INET:
ip->ip_len = htons(tlen - hlen);
th->th_sum = 0;
th->th_sum = in_cksum(m, tlen);
break;
#ifdef INET6
case AF_INET6:
ip6->ip6_plen = htons(tlen - hlen);
th->th_sum = 0;
th->th_sum = in6_cksum(m, IPPROTO_TCP, hlen, tlen - hlen);
break;
#endif
}
/* use IPsec policy and ttl from listening socket, on SYN ACK */
inp = sc->sc_tp ? sc->sc_tp->t_inpcb : NULL;
/*
* Fill in some straggling IP bits. Note the stack expects
* ip_len to be in host order, for convenience.
*/
switch (sc->sc_src.sa.sa_family) {
#ifdef INET
case AF_INET:
ip->ip_len = htons(tlen);
ip->ip_ttl = inp ? inp->inp_ip.ip_ttl : ip_defttl;
/* XXX tos? */
break;
#endif
#ifdef INET6
case AF_INET6:
ip6->ip6_vfc &= ~IPV6_VERSION_MASK;
ip6->ip6_vfc |= IPV6_VERSION;
ip6->ip6_plen = htons(tlen - hlen);
/* ip6_hlim will be initialized afterwards */
/* leave flowlabel = 0, it is legal and require no state mgmt */
break;
#endif
}
switch (sc->sc_src.sa.sa_family) {
#ifdef INET
case AF_INET:
error = ip_output(m, sc->sc_ipopts, ro,
(ip_mtudisc ? IP_MTUDISC : 0),
(struct ip_moptions *)NULL, inp);
break;
#endif
#ifdef INET6
case AF_INET6:
ip6->ip6_hlim = in6_selecthlim(NULL,
ro->ro_rt ? ro->ro_rt->rt_ifp : NULL);
error = ip6_output(m, NULL /*XXX*/, (struct route_in6 *)ro, 0,
(struct ip6_moptions *)0, NULL, NULL);
break;
#endif
default:
error = EAFNOSUPPORT;
break;
}
return (error);
}
|