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
|
/*
* INET An implementation of the TCP/IP protocol suite for the LINUX
* operating system. INET is implemented using the BSD Socket
* interface as the means of communication with the user level.
*
* ROUTE - implementation of the IP router.
*
* Authors: Ross Biro
* Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
* Alan Cox, <gw4pts@gw4pts.ampr.org>
* Linus Torvalds, <Linus.Torvalds@helsinki.fi>
* Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
*
* Fixes:
* Alan Cox : Verify area fixes.
* Alan Cox : cli() protects routing changes
* Rui Oliveira : ICMP routing table updates
* (rco@di.uminho.pt) Routing table insertion and update
* Linus Torvalds : Rewrote bits to be sensible
* Alan Cox : Added BSD route gw semantics
* Alan Cox : Super /proc >4K
* Alan Cox : MTU in route table
* Alan Cox : MSS actually. Also added the window
* clamper.
* Sam Lantinga : Fixed route matching in rt_del()
* Alan Cox : Routing cache support.
* Alan Cox : Removed compatibility cruft.
* Alan Cox : RTF_REJECT support.
* Alan Cox : TCP irtt support.
* Jonathan Naylor : Added Metric support.
* Miquel van Smoorenburg : BSD API fixes.
* Miquel van Smoorenburg : Metrics.
* Alan Cox : Use __u32 properly
* Alan Cox : Aligned routing errors more closely with BSD
* our system is still very different.
* Alan Cox : Faster /proc handling
* Alexey Kuznetsov : Massive rework to support tree based routing,
* routing caches and better behaviour.
*
* Olaf Erb : irtt wasn't being copied right.
* Bjorn Ekwall : Kerneld route support.
* Alan Cox : Multicast fixed (I hope)
* Pavel Krauz : Limited broadcast fixed
* Mike McLagan : Routing by source
* Alexey Kuznetsov : End of old history. Split to fib.c and
* route.c and rewritten from scratch.
* Andi Kleen : Load-limit warning messages.
* Vitaly E. Lavrov : Transparent proxy revived after year coma.
* Vitaly E. Lavrov : Race condition in ip_route_input_slow.
* Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow.
* Vladimir V. Ivanov : IP rule info (flowid) is really useful.
* Marc Boucher : routing by fwmark
* Robert Olsson : Added rt_cache statistics
* Arnaldo C. Melo : Convert proc stuff to seq_file
* Eric Dumazet : hashed spinlocks and rt_check_expire() fixes.
* Ilia Sotnikov : Ignore TOS on PMTUD and Redirect
* Ilia Sotnikov : Removed TOS from hash calculations
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#include <linux/module.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/bootmem.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/errno.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/proc_fs.h>
#include <linux/init.h>
#include <linux/workqueue.h>
#include <linux/skbuff.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/pkt_sched.h>
#include <linux/mroute.h>
#include <linux/netfilter_ipv4.h>
#include <linux/random.h>
#include <linux/jhash.h>
#include <linux/rcupdate.h>
#include <linux/times.h>
#include <linux/slab.h>
#include <net/dst.h>
#include <net/net_namespace.h>
#include <net/protocol.h>
#include <net/ip.h>
#include <net/route.h>
#include <net/inetpeer.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/arp.h>
#include <net/tcp.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/rtnetlink.h>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif
#include <net/atmclip.h>
#include <net/secure_seq.h>
#define RT_FL_TOS(oldflp4) \
((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
#define IP_MAX_MTU 0xFFF0
#define RT_GC_TIMEOUT (300*HZ)
static int ip_rt_max_size;
static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
static int ip_rt_redirect_number __read_mostly = 9;
static int ip_rt_redirect_load __read_mostly = HZ / 50;
static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1));
static int ip_rt_error_cost __read_mostly = HZ;
static int ip_rt_error_burst __read_mostly = 5 * HZ;
static int ip_rt_gc_elasticity __read_mostly = 8;
static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
static int rt_chain_length_max __read_mostly = 20;
static int redirect_genid;
/*
* Interface to generic destination cache.
*/
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int ipv4_default_advmss(const struct dst_entry *dst);
static unsigned int ipv4_mtu(const struct dst_entry *dst);
static void ipv4_dst_destroy(struct dst_entry *dst);
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
static void ipv4_link_failure(struct sk_buff *skb);
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu);
static int rt_garbage_collect(struct dst_ops *ops);
static void ipv4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
int how)
{
}
static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old)
{
struct rtable *rt = (struct rtable *) dst;
struct inet_peer *peer;
u32 *p = NULL;
if (!rt->peer)
rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
if (peer) {
u32 *old_p = __DST_METRICS_PTR(old);
unsigned long prev, new;
p = peer->metrics;
if (inet_metrics_new(peer))
memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
new = (unsigned long) p;
prev = cmpxchg(&dst->_metrics, old, new);
if (prev != old) {
p = __DST_METRICS_PTR(prev);
if (prev & DST_METRICS_READ_ONLY)
p = NULL;
} else {
if (rt->fi) {
fib_info_put(rt->fi);
rt->fi = NULL;
}
}
}
return p;
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr);
static struct dst_ops ipv4_dst_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.gc = rt_garbage_collect,
.check = ipv4_dst_check,
.default_advmss = ipv4_default_advmss,
.mtu = ipv4_mtu,
.cow_metrics = ipv4_cow_metrics,
.destroy = ipv4_dst_destroy,
.ifdown = ipv4_dst_ifdown,
.negative_advice = ipv4_negative_advice,
.link_failure = ipv4_link_failure,
.update_pmtu = ip_rt_update_pmtu,
.local_out = __ip_local_out,
.neigh_lookup = ipv4_neigh_lookup,
};
#define ECN_OR_COST(class) TC_PRIO_##class
const __u8 ip_tos2prio[16] = {
TC_PRIO_BESTEFFORT,
ECN_OR_COST(BESTEFFORT),
TC_PRIO_BESTEFFORT,
ECN_OR_COST(BESTEFFORT),
TC_PRIO_BULK,
ECN_OR_COST(BULK),
TC_PRIO_BULK,
ECN_OR_COST(BULK),
TC_PRIO_INTERACTIVE,
ECN_OR_COST(INTERACTIVE),
TC_PRIO_INTERACTIVE,
ECN_OR_COST(INTERACTIVE),
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK),
TC_PRIO_INTERACTIVE_BULK,
ECN_OR_COST(INTERACTIVE_BULK)
};
/*
* Route cache.
*/
/* The locking scheme is rather straight forward:
*
* 1) Read-Copy Update protects the buckets of the central route hash.
* 2) Only writers remove entries, and they hold the lock
* as they look at rtable reference counts.
* 3) Only readers acquire references to rtable entries,
* they do so with atomic increments and with the
* lock held.
*/
struct rt_hash_bucket {
struct rtable __rcu *chain;
};
#if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \
defined(CONFIG_PROVE_LOCKING)
/*
* Instead of using one spinlock for each rt_hash_bucket, we use a table of spinlocks
* The size of this table is a power of two and depends on the number of CPUS.
* (on lockdep we have a quite big spinlock_t, so keep the size down there)
*/
#ifdef CONFIG_LOCKDEP
# define RT_HASH_LOCK_SZ 256
#else
# if NR_CPUS >= 32
# define RT_HASH_LOCK_SZ 4096
# elif NR_CPUS >= 16
# define RT_HASH_LOCK_SZ 2048
# elif NR_CPUS >= 8
# define RT_HASH_LOCK_SZ 1024
# elif NR_CPUS >= 4
# define RT_HASH_LOCK_SZ 512
# else
# define RT_HASH_LOCK_SZ 256
# endif
#endif
static spinlock_t *rt_hash_locks;
# define rt_hash_lock_addr(slot) &rt_hash_locks[(slot) & (RT_HASH_LOCK_SZ - 1)]
static __init void rt_hash_lock_init(void)
{
int i;
rt_hash_locks = kmalloc(sizeof(spinlock_t) * RT_HASH_LOCK_SZ,
GFP_KERNEL);
if (!rt_hash_locks)
panic("IP: failed to allocate rt_hash_locks\n");
for (i = 0; i < RT_HASH_LOCK_SZ; i++)
spin_lock_init(&rt_hash_locks[i]);
}
#else
# define rt_hash_lock_addr(slot) NULL
static inline void rt_hash_lock_init(void)
{
}
#endif
static struct rt_hash_bucket *rt_hash_table __read_mostly;
static unsigned rt_hash_mask __read_mostly;
static unsigned int rt_hash_log __read_mostly;
static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat);
#define RT_CACHE_STAT_INC(field) __this_cpu_inc(rt_cache_stat.field)
static inline unsigned int rt_hash(__be32 daddr, __be32 saddr, int idx,
int genid)
{
return jhash_3words((__force u32)daddr, (__force u32)saddr,
idx, genid)
& rt_hash_mask;
}
static inline int rt_genid(struct net *net)
{
return atomic_read(&net->ipv4.rt_genid);
}
#ifdef CONFIG_PROC_FS
struct rt_cache_iter_state {
struct seq_net_private p;
int bucket;
int genid;
};
static struct rtable *rt_cache_get_first(struct seq_file *seq)
{
struct rt_cache_iter_state *st = seq->private;
struct rtable *r = NULL;
for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) {
if (!rcu_access_pointer(rt_hash_table[st->bucket].chain))
continue;
rcu_read_lock_bh();
r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
while (r) {
if (dev_net(r->dst.dev) == seq_file_net(seq) &&
r->rt_genid == st->genid)
return r;
r = rcu_dereference_bh(r->dst.rt_next);
}
rcu_read_unlock_bh();
}
return r;
}
static struct rtable *__rt_cache_get_next(struct seq_file *seq,
struct rtable *r)
{
struct rt_cache_iter_state *st = seq->private;
r = rcu_dereference_bh(r->dst.rt_next);
while (!r) {
rcu_read_unlock_bh();
do {
if (--st->bucket < 0)
return NULL;
} while (!rcu_access_pointer(rt_hash_table[st->bucket].chain));
rcu_read_lock_bh();
r = rcu_dereference_bh(rt_hash_table[st->bucket].chain);
}
return r;
}
static struct rtable *rt_cache_get_next(struct seq_file *seq,
struct rtable *r)
{
struct rt_cache_iter_state *st = seq->private;
while ((r = __rt_cache_get_next(seq, r)) != NULL) {
if (dev_net(r->dst.dev) != seq_file_net(seq))
continue;
if (r->rt_genid == st->genid)
break;
}
return r;
}
static struct rtable *rt_cache_get_idx(struct seq_file *seq, loff_t pos)
{
struct rtable *r = rt_cache_get_first(seq);
if (r)
while (pos && (r = rt_cache_get_next(seq, r)))
--pos;
return pos ? NULL : r;
}
static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos)
{
struct rt_cache_iter_state *st = seq->private;
if (*pos)
return rt_cache_get_idx(seq, *pos - 1);
st->genid = rt_genid(seq_file_net(seq));
return SEQ_START_TOKEN;
}
static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct rtable *r;
if (v == SEQ_START_TOKEN)
r = rt_cache_get_first(seq);
else
r = rt_cache_get_next(seq, v);
++*pos;
return r;
}
static void rt_cache_seq_stop(struct seq_file *seq, void *v)
{
if (v && v != SEQ_START_TOKEN)
rcu_read_unlock_bh();
}
static int rt_cache_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_printf(seq, "%-127s\n",
"Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t"
"Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t"
"HHUptod\tSpecDst");
else {
struct rtable *r = v;
struct neighbour *n;
int len, HHUptod;
rcu_read_lock();
n = dst_get_neighbour(&r->dst);
HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0;
rcu_read_unlock();
seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t"
"%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n",
r->dst.dev ? r->dst.dev->name : "*",
(__force u32)r->rt_dst,
(__force u32)r->rt_gateway,
r->rt_flags, atomic_read(&r->dst.__refcnt),
r->dst.__use, 0, (__force u32)r->rt_src,
dst_metric_advmss(&r->dst) + 40,
dst_metric(&r->dst, RTAX_WINDOW),
(int)((dst_metric(&r->dst, RTAX_RTT) >> 3) +
dst_metric(&r->dst, RTAX_RTTVAR)),
r->rt_key_tos,
-1,
HHUptod,
r->rt_spec_dst, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
}
return 0;
}
static const struct seq_operations rt_cache_seq_ops = {
.start = rt_cache_seq_start,
.next = rt_cache_seq_next,
.stop = rt_cache_seq_stop,
.show = rt_cache_seq_show,
};
static int rt_cache_seq_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &rt_cache_seq_ops,
sizeof(struct rt_cache_iter_state));
}
static const struct file_operations rt_cache_seq_fops = {
.owner = THIS_MODULE,
.open = rt_cache_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_net,
};
static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos)
{
int cpu;
if (*pos == 0)
return SEQ_START_TOKEN;
for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
return NULL;
}
static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
int cpu;
for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) {
if (!cpu_possible(cpu))
continue;
*pos = cpu+1;
return &per_cpu(rt_cache_stat, cpu);
}
return NULL;
}
static void rt_cpu_seq_stop(struct seq_file *seq, void *v)
{
}
static int rt_cpu_seq_show(struct seq_file *seq, void *v)
{
struct rt_cache_stat *st = v;
if (v == SEQ_START_TOKEN) {
seq_printf(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n");
return 0;
}
seq_printf(seq,"%08x %08x %08x %08x %08x %08x %08x %08x "
" %08x %08x %08x %08x %08x %08x %08x %08x %08x \n",
dst_entries_get_slow(&ipv4_dst_ops),
st->in_hit,
st->in_slow_tot,
st->in_slow_mc,
st->in_no_route,
st->in_brd,
st->in_martian_dst,
st->in_martian_src,
st->out_hit,
st->out_slow_tot,
st->out_slow_mc,
st->gc_total,
st->gc_ignored,
st->gc_goal_miss,
st->gc_dst_overflow,
st->in_hlist_search,
st->out_hlist_search
);
return 0;
}
static const struct seq_operations rt_cpu_seq_ops = {
.start = rt_cpu_seq_start,
.next = rt_cpu_seq_next,
.stop = rt_cpu_seq_stop,
.show = rt_cpu_seq_show,
};
static int rt_cpu_seq_open(struct inode *inode, struct file *file)
{
return seq_open(file, &rt_cpu_seq_ops);
}
static const struct file_operations rt_cpu_seq_fops = {
.owner = THIS_MODULE,
.open = rt_cpu_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release,
};
#ifdef CONFIG_IP_ROUTE_CLASSID
static int rt_acct_proc_show(struct seq_file *m, void *v)
{
struct ip_rt_acct *dst, *src;
unsigned int i, j;
dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL);
if (!dst)
return -ENOMEM;
for_each_possible_cpu(i) {
src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i);
for (j = 0; j < 256; j++) {
dst[j].o_bytes += src[j].o_bytes;
dst[j].o_packets += src[j].o_packets;
dst[j].i_bytes += src[j].i_bytes;
dst[j].i_packets += src[j].i_packets;
}
}
seq_write(m, dst, 256 * sizeof(struct ip_rt_acct));
kfree(dst);
return 0;
}
static int rt_acct_proc_open(struct inode *inode, struct file *file)
{
return single_open(file, rt_acct_proc_show, NULL);
}
static const struct file_operations rt_acct_proc_fops = {
.owner = THIS_MODULE,
.open = rt_acct_proc_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
};
#endif
static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
pde = proc_net_fops_create(net, "rt_cache", S_IRUGO,
&rt_cache_seq_fops);
if (!pde)
goto err1;
pde = proc_create("rt_cache", S_IRUGO,
net->proc_net_stat, &rt_cpu_seq_fops);
if (!pde)
goto err2;
#ifdef CONFIG_IP_ROUTE_CLASSID
pde = proc_create("rt_acct", 0, net->proc_net, &rt_acct_proc_fops);
if (!pde)
goto err3;
#endif
return 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
err3:
remove_proc_entry("rt_cache", net->proc_net_stat);
#endif
err2:
remove_proc_entry("rt_cache", net->proc_net);
err1:
return -ENOMEM;
}
static void __net_exit ip_rt_do_proc_exit(struct net *net)
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
#ifdef CONFIG_IP_ROUTE_CLASSID
remove_proc_entry("rt_acct", net->proc_net);
#endif
}
static struct pernet_operations ip_rt_proc_ops __net_initdata = {
.init = ip_rt_do_proc_init,
.exit = ip_rt_do_proc_exit,
};
static int __init ip_rt_proc_init(void)
{
return register_pernet_subsys(&ip_rt_proc_ops);
}
#else
static inline int ip_rt_proc_init(void)
{
return 0;
}
#endif /* CONFIG_PROC_FS */
static inline void rt_free(struct rtable *rt)
{
call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
}
static inline void rt_drop(struct rtable *rt)
{
ip_rt_put(rt);
call_rcu_bh(&rt->dst.rcu_head, dst_rcu_free);
}
static inline int rt_fast_clean(struct rtable *rth)
{
/* Kill broadcast/multicast entries very aggresively, if they
collide in hash table with more useful entries */
return (rth->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) &&
rt_is_input_route(rth) && rth->dst.rt_next;
}
static inline int rt_valuable(struct rtable *rth)
{
return (rth->rt_flags & (RTCF_REDIRECTED | RTCF_NOTIFY)) ||
(rth->peer && rth->peer->pmtu_expires);
}
static int rt_may_expire(struct rtable *rth, unsigned long tmo1, unsigned long tmo2)
{
unsigned long age;
int ret = 0;
if (atomic_read(&rth->dst.__refcnt))
goto out;
age = jiffies - rth->dst.lastuse;
if ((age <= tmo1 && !rt_fast_clean(rth)) ||
(age <= tmo2 && rt_valuable(rth)))
goto out;
ret = 1;
out: return ret;
}
/* Bits of score are:
* 31: very valuable
* 30: not quite useless
* 29..0: usage counter
*/
static inline u32 rt_score(struct rtable *rt)
{
u32 score = jiffies - rt->dst.lastuse;
score = ~score & ~(3<<30);
if (rt_valuable(rt))
score |= (1<<31);
if (rt_is_output_route(rt) ||
!(rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST|RTCF_LOCAL)))
score |= (1<<30);
return score;
}
static inline bool rt_caching(const struct net *net)
{
return net->ipv4.current_rt_cache_rebuild_count <=
net->ipv4.sysctl_rt_cache_rebuild_count;
}
static inline bool compare_hash_inputs(const struct rtable *rt1,
const struct rtable *rt2)
{
return ((((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
(rt1->rt_route_iif ^ rt2->rt_route_iif)) == 0);
}
static inline int compare_keys(struct rtable *rt1, struct rtable *rt2)
{
return (((__force u32)rt1->rt_key_dst ^ (__force u32)rt2->rt_key_dst) |
((__force u32)rt1->rt_key_src ^ (__force u32)rt2->rt_key_src) |
(rt1->rt_mark ^ rt2->rt_mark) |
(rt1->rt_key_tos ^ rt2->rt_key_tos) |
(rt1->rt_route_iif ^ rt2->rt_route_iif) |
(rt1->rt_oif ^ rt2->rt_oif)) == 0;
}
static inline int compare_netns(struct rtable *rt1, struct rtable *rt2)
{
return net_eq(dev_net(rt1->dst.dev), dev_net(rt2->dst.dev));
}
static inline int rt_is_expired(struct rtable *rth)
{
return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
}
/*
* Perform a full scan of hash table and free all entries.
* Can be called by a softirq or a process.
* In the later case, we want to be reschedule if necessary
*/
static void rt_do_flush(struct net *net, int process_context)
{
unsigned int i;
struct rtable *rth, *next;
for (i = 0; i <= rt_hash_mask; i++) {
struct rtable __rcu **pprev;
struct rtable *list;
if (process_context && need_resched())
cond_resched();
rth = rcu_access_pointer(rt_hash_table[i].chain);
if (!rth)
continue;
spin_lock_bh(rt_hash_lock_addr(i));
list = NULL;
pprev = &rt_hash_table[i].chain;
rth = rcu_dereference_protected(*pprev,
lockdep_is_held(rt_hash_lock_addr(i)));
while (rth) {
next = rcu_dereference_protected(rth->dst.rt_next,
lockdep_is_held(rt_hash_lock_addr(i)));
if (!net ||
net_eq(dev_net(rth->dst.dev), net)) {
rcu_assign_pointer(*pprev, next);
rcu_assign_pointer(rth->dst.rt_next, list);
list = rth;
} else {
pprev = &rth->dst.rt_next;
}
rth = next;
}
spin_unlock_bh(rt_hash_lock_addr(i));
for (; list; list = next) {
next = rcu_dereference_protected(list->dst.rt_next, 1);
rt_free(list);
}
}
}
/*
* While freeing expired entries, we compute average chain length
* and standard deviation, using fixed-point arithmetic.
* This to have an estimation of rt_chain_length_max
* rt_chain_length_max = max(elasticity, AVG + 4*SD)
* We use 3 bits for frational part, and 29 (or 61) for magnitude.
*/
#define FRACT_BITS 3
#define ONE (1UL << FRACT_BITS)
/*
* Given a hash chain and an item in this hash chain,
* find if a previous entry has the same hash_inputs
* (but differs on tos, mark or oif)
* Returns 0 if an alias is found.
* Returns ONE if rth has no alias before itself.
*/
static int has_noalias(const struct rtable *head, const struct rtable *rth)
{
const struct rtable *aux = head;
while (aux != rth) {
if (compare_hash_inputs(aux, rth))
return 0;
aux = rcu_dereference_protected(aux->dst.rt_next, 1);
}
return ONE;
}
/*
* Perturbation of rt_genid by a small quantity [1..256]
* Using 8 bits of shuffling ensure we can call rt_cache_invalidate()
* many times (2^24) without giving recent rt_genid.
* Jenkins hash is strong enough that litle changes of rt_genid are OK.
*/
static void rt_cache_invalidate(struct net *net)
{
unsigned char shuffle;
get_random_bytes(&shuffle, sizeof(shuffle));
atomic_add(shuffle + 1U, &net->ipv4.rt_genid);
redirect_genid++;
}
/*
* delay < 0 : invalidate cache (fast : entries will be deleted later)
* delay >= 0 : invalidate & flush cache (can be long)
*/
void rt_cache_flush(struct net *net, int delay)
{
rt_cache_invalidate(net);
if (delay >= 0)
rt_do_flush(net, !in_softirq());
}
/* Flush previous cache invalidated entries from the cache */
void rt_cache_flush_batch(struct net *net)
{
rt_do_flush(net, !in_softirq());
}
static void rt_emergency_hash_rebuild(struct net *net)
{
if (net_ratelimit())
printk(KERN_WARNING "Route hash chain too long!\n");
rt_cache_invalidate(net);
}
/*
Short description of GC goals.
We want to build algorithm, which will keep routing cache
at some equilibrium point, when number of aged off entries
is kept approximately equal to newly generated ones.
Current expiration strength is variable "expire".
We try to adjust it dynamically, so that if networking
is idle expires is large enough to keep enough of warm entries,
and when load increases it reduces to limit cache size.
*/
static int rt_garbage_collect(struct dst_ops *ops)
{
static unsigned long expire = RT_GC_TIMEOUT;
static unsigned long last_gc;
static int rover;
static int equilibrium;
struct rtable *rth;
struct rtable __rcu **rthp;
unsigned long now = jiffies;
int goal;
int entries = dst_entries_get_fast(&ipv4_dst_ops);
/*
* Garbage collection is pretty expensive,
* do not make it too frequently.
*/
RT_CACHE_STAT_INC(gc_total);
if (now - last_gc < ip_rt_gc_min_interval &&
entries < ip_rt_max_size) {
RT_CACHE_STAT_INC(gc_ignored);
goto out;
}
entries = dst_entries_get_slow(&ipv4_dst_ops);
/* Calculate number of entries, which we want to expire now. */
goal = entries - (ip_rt_gc_elasticity << rt_hash_log);
if (goal <= 0) {
if (equilibrium < ipv4_dst_ops.gc_thresh)
equilibrium = ipv4_dst_ops.gc_thresh;
goal = entries - equilibrium;
if (goal > 0) {
equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1);
goal = entries - equilibrium;
}
} else {
/* We are in dangerous area. Try to reduce cache really
* aggressively.
*/
goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1);
equilibrium = entries - goal;
}
if (now - last_gc >= ip_rt_gc_min_interval)
last_gc = now;
if (goal <= 0) {
equilibrium += goal;
goto work_done;
}
do {
int i, k;
for (i = rt_hash_mask, k = rover; i >= 0; i--) {
unsigned long tmo = expire;
k = (k + 1) & rt_hash_mask;
rthp = &rt_hash_table[k].chain;
spin_lock_bh(rt_hash_lock_addr(k));
while ((rth = rcu_dereference_protected(*rthp,
lockdep_is_held(rt_hash_lock_addr(k)))) != NULL) {
if (!rt_is_expired(rth) &&
!rt_may_expire(rth, tmo, expire)) {
tmo >>= 1;
rthp = &rth->dst.rt_next;
continue;
}
*rthp = rth->dst.rt_next;
rt_free(rth);
goal--;
}
spin_unlock_bh(rt_hash_lock_addr(k));
if (goal <= 0)
break;
}
rover = k;
if (goal <= 0)
goto work_done;
/* Goal is not achieved. We stop process if:
- if expire reduced to zero. Otherwise, expire is halfed.
- if table is not full.
- if we are called from interrupt.
- jiffies check is just fallback/debug loop breaker.
We will not spin here for long time in any case.
*/
RT_CACHE_STAT_INC(gc_goal_miss);
if (expire == 0)
break;
expire >>= 1;
if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
goto out;
} while (!in_softirq() && time_before_eq(jiffies, now));
if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size)
goto out;
if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size)
goto out;
if (net_ratelimit())
printk(KERN_WARNING "dst cache overflow\n");
RT_CACHE_STAT_INC(gc_dst_overflow);
return 1;
work_done:
expire += ip_rt_gc_min_interval;
if (expire > ip_rt_gc_timeout ||
dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh ||
dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh)
expire = ip_rt_gc_timeout;
out: return 0;
}
/*
* Returns number of entries in a hash chain that have different hash_inputs
*/
static int slow_chain_length(const struct rtable *head)
{
int length = 0;
const struct rtable *rth = head;
while (rth) {
length += has_noalias(head, rth);
rth = rcu_dereference_protected(rth->dst.rt_next, 1);
}
return length >> FRACT_BITS;
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr)
{
struct neigh_table *tbl = &arp_tbl;
static const __be32 inaddr_any = 0;
struct net_device *dev = dst->dev;
const __be32 *pkey = daddr;
struct neighbour *n;
#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
if (dev->type == ARPHRD_ATM)
tbl = clip_tbl_hook;
#endif
if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
pkey = &inaddr_any;
n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey);
if (n)
return n;
return neigh_create(tbl, pkey, dev);
}
static int rt_bind_neighbour(struct rtable *rt)
{
struct neighbour *n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
if (IS_ERR(n))
return PTR_ERR(n);
dst_set_neighbour(&rt->dst, n);
return 0;
}
static struct rtable *rt_intern_hash(unsigned hash, struct rtable *rt,
struct sk_buff *skb, int ifindex)
{
struct rtable *rth, *cand;
struct rtable __rcu **rthp, **candp;
unsigned long now;
u32 min_score;
int chain_length;
int attempts = !in_softirq();
restart:
chain_length = 0;
min_score = ~(u32)0;
cand = NULL;
candp = NULL;
now = jiffies;
if (!rt_caching(dev_net(rt->dst.dev))) {
/*
* If we're not caching, just tell the caller we
* were successful and don't touch the route. The
* caller hold the sole reference to the cache entry, and
* it will be released when the caller is done with it.
* If we drop it here, the callers have no way to resolve routes
* when we're not caching. Instead, just point *rp at rt, so
* the caller gets a single use out of the route
* Note that we do rt_free on this new route entry, so that
* once its refcount hits zero, we are still able to reap it
* (Thanks Alexey)
* Note: To avoid expensive rcu stuff for this uncached dst,
* we set DST_NOCACHE so that dst_release() can free dst without
* waiting a grace period.
*/
rt->dst.flags |= DST_NOCACHE;
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
int err = rt_bind_neighbour(rt);
if (err) {
if (net_ratelimit())
printk(KERN_WARNING
"Neighbour table failure & not caching routes.\n");
ip_rt_put(rt);
return ERR_PTR(err);
}
}
goto skip_hashing;
}
rthp = &rt_hash_table[hash].chain;
spin_lock_bh(rt_hash_lock_addr(hash));
while ((rth = rcu_dereference_protected(*rthp,
lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
if (rt_is_expired(rth)) {
*rthp = rth->dst.rt_next;
rt_free(rth);
continue;
}
if (compare_keys(rth, rt) && compare_netns(rth, rt)) {
/* Put it first */
*rthp = rth->dst.rt_next;
/*
* Since lookup is lockfree, the deletion
* must be visible to another weakly ordered CPU before
* the insertion at the start of the hash chain.
*/
rcu_assign_pointer(rth->dst.rt_next,
rt_hash_table[hash].chain);
/*
* Since lookup is lockfree, the update writes
* must be ordered for consistency on SMP.
*/
rcu_assign_pointer(rt_hash_table[hash].chain, rth);
dst_use(&rth->dst, now);
spin_unlock_bh(rt_hash_lock_addr(hash));
rt_drop(rt);
if (skb)
skb_dst_set(skb, &rth->dst);
return rth;
}
if (!atomic_read(&rth->dst.__refcnt)) {
u32 score = rt_score(rth);
if (score <= min_score) {
cand = rth;
candp = rthp;
min_score = score;
}
}
chain_length++;
rthp = &rth->dst.rt_next;
}
if (cand) {
/* ip_rt_gc_elasticity used to be average length of chain
* length, when exceeded gc becomes really aggressive.
*
* The second limit is less certain. At the moment it allows
* only 2 entries per bucket. We will see.
*/
if (chain_length > ip_rt_gc_elasticity) {
*candp = cand->dst.rt_next;
rt_free(cand);
}
} else {
if (chain_length > rt_chain_length_max &&
slow_chain_length(rt_hash_table[hash].chain) > rt_chain_length_max) {
struct net *net = dev_net(rt->dst.dev);
int num = ++net->ipv4.current_rt_cache_rebuild_count;
if (!rt_caching(net)) {
printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n",
rt->dst.dev->name, num);
}
rt_emergency_hash_rebuild(net);
spin_unlock_bh(rt_hash_lock_addr(hash));
hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
ifindex, rt_genid(net));
goto restart;
}
}
/* Try to bind route to arp only if it is output
route or unicast forwarding path.
*/
if (rt->rt_type == RTN_UNICAST || rt_is_output_route(rt)) {
int err = rt_bind_neighbour(rt);
if (err) {
spin_unlock_bh(rt_hash_lock_addr(hash));
if (err != -ENOBUFS) {
rt_drop(rt);
return ERR_PTR(err);
}
/* Neighbour tables are full and nothing
can be released. Try to shrink route cache,
it is most likely it holds some neighbour records.
*/
if (attempts-- > 0) {
int saved_elasticity = ip_rt_gc_elasticity;
int saved_int = ip_rt_gc_min_interval;
ip_rt_gc_elasticity = 1;
ip_rt_gc_min_interval = 0;
rt_garbage_collect(&ipv4_dst_ops);
ip_rt_gc_min_interval = saved_int;
ip_rt_gc_elasticity = saved_elasticity;
goto restart;
}
if (net_ratelimit())
printk(KERN_WARNING "ipv4: Neighbour table overflow.\n");
rt_drop(rt);
return ERR_PTR(-ENOBUFS);
}
}
rt->dst.rt_next = rt_hash_table[hash].chain;
/*
* Since lookup is lockfree, we must make sure
* previous writes to rt are committed to memory
* before making rt visible to other CPUS.
*/
rcu_assign_pointer(rt_hash_table[hash].chain, rt);
spin_unlock_bh(rt_hash_lock_addr(hash));
skip_hashing:
if (skb)
skb_dst_set(skb, &rt->dst);
return rt;
}
static atomic_t __rt_peer_genid = ATOMIC_INIT(0);
static u32 rt_peer_genid(void)
{
return atomic_read(&__rt_peer_genid);
}
void rt_bind_peer(struct rtable *rt, __be32 daddr, int create)
{
struct inet_peer *peer;
peer = inet_getpeer_v4(daddr, create);
if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL)
inet_putpeer(peer);
else
rt->rt_peer_genid = rt_peer_genid();
}
/*
* Peer allocation may fail only in serious out-of-memory conditions. However
* we still can generate some output.
* Random ID selection looks a bit dangerous because we have no chances to
* select ID being unique in a reasonable period of time.
* But broken packet identifier may be better than no packet at all.
*/
static void ip_select_fb_ident(struct iphdr *iph)
{
static DEFINE_SPINLOCK(ip_fb_id_lock);
static u32 ip_fallback_id;
u32 salt;
spin_lock_bh(&ip_fb_id_lock);
salt = secure_ip_id((__force __be32)ip_fallback_id ^ iph->daddr);
iph->id = htons(salt & 0xFFFF);
ip_fallback_id = salt;
spin_unlock_bh(&ip_fb_id_lock);
}
void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more)
{
struct rtable *rt = (struct rtable *) dst;
if (rt) {
if (rt->peer == NULL)
rt_bind_peer(rt, rt->rt_dst, 1);
/* If peer is attached to destination, it is never detached,
so that we need not to grab a lock to dereference it.
*/
if (rt->peer) {
iph->id = htons(inet_getid(rt->peer, more));
return;
}
} else
printk(KERN_DEBUG "rt_bind_peer(0) @%p\n",
__builtin_return_address(0));
ip_select_fb_ident(iph);
}
EXPORT_SYMBOL(__ip_select_ident);
static void rt_del(unsigned hash, struct rtable *rt)
{
struct rtable __rcu **rthp;
struct rtable *aux;
rthp = &rt_hash_table[hash].chain;
spin_lock_bh(rt_hash_lock_addr(hash));
ip_rt_put(rt);
while ((aux = rcu_dereference_protected(*rthp,
lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) {
if (aux == rt || rt_is_expired(aux)) {
*rthp = aux->dst.rt_next;
rt_free(aux);
continue;
}
rthp = &aux->dst.rt_next;
}
spin_unlock_bh(rt_hash_lock_addr(hash));
}
static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer)
{
struct rtable *rt = (struct rtable *) dst;
__be32 orig_gw = rt->rt_gateway;
struct neighbour *n, *old_n;
dst_confirm(&rt->dst);
rt->rt_gateway = peer->redirect_learned.a4;
n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway);
if (IS_ERR(n))
return PTR_ERR(n);
old_n = xchg(&rt->dst._neighbour, n);
if (old_n)
neigh_release(old_n);
if (!n || !(n->nud_state & NUD_VALID)) {
if (n)
neigh_event_send(n, NULL);
rt->rt_gateway = orig_gw;
return -EAGAIN;
} else {
rt->rt_flags |= RTCF_REDIRECTED;
call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n);
}
return 0;
}
/* called in rcu_read_lock() section */
void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw,
__be32 saddr, struct net_device *dev)
{
int s, i;
struct in_device *in_dev = __in_dev_get_rcu(dev);
__be32 skeys[2] = { saddr, 0 };
int ikeys[2] = { dev->ifindex, 0 };
struct inet_peer *peer;
struct net *net;
if (!in_dev)
return;
net = dev_net(dev);
if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) ||
ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) ||
ipv4_is_zeronet(new_gw))
goto reject_redirect;
if (!IN_DEV_SHARED_MEDIA(in_dev)) {
if (!inet_addr_onlink(in_dev, new_gw, old_gw))
goto reject_redirect;
if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev))
goto reject_redirect;
} else {
if (inet_addr_type(net, new_gw) != RTN_UNICAST)
goto reject_redirect;
}
for (s = 0; s < 2; s++) {
for (i = 0; i < 2; i++) {
unsigned int hash;
struct rtable __rcu **rthp;
struct rtable *rt;
hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net));
rthp = &rt_hash_table[hash].chain;
while ((rt = rcu_dereference(*rthp)) != NULL) {
rthp = &rt->dst.rt_next;
if (rt->rt_key_dst != daddr ||
rt->rt_key_src != skeys[s] ||
rt->rt_oif != ikeys[i] ||
rt_is_input_route(rt) ||
rt_is_expired(rt) ||
!net_eq(dev_net(rt->dst.dev), net) ||
rt->dst.error ||
rt->dst.dev != dev ||
rt->rt_gateway != old_gw)
continue;
if (!rt->peer)
rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
if (peer) {
if (peer->redirect_learned.a4 != new_gw ||
peer->redirect_genid != redirect_genid) {
peer->redirect_learned.a4 = new_gw;
peer->redirect_genid = redirect_genid;
atomic_inc(&__rt_peer_genid);
}
check_peer_redir(&rt->dst, peer);
}
}
}
}
return;
reject_redirect:
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
printk(KERN_INFO "Redirect from %pI4 on %s about %pI4 ignored.\n"
" Advised path = %pI4 -> %pI4\n",
&old_gw, dev->name, &new_gw,
&saddr, &daddr);
#endif
;
}
static bool peer_pmtu_expired(struct inet_peer *peer)
{
unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
return orig &&
time_after_eq(jiffies, orig) &&
cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
}
static bool peer_pmtu_cleaned(struct inet_peer *peer)
{
unsigned long orig = ACCESS_ONCE(peer->pmtu_expires);
return orig &&
cmpxchg(&peer->pmtu_expires, orig, 0) == orig;
}
static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *)dst;
struct dst_entry *ret = dst;
if (rt) {
if (dst->obsolete > 0) {
ip_rt_put(rt);
ret = NULL;
} else if (rt->rt_flags & RTCF_REDIRECTED) {
unsigned hash = rt_hash(rt->rt_key_dst, rt->rt_key_src,
rt->rt_oif,
rt_genid(dev_net(dst->dev)));
rt_del(hash, rt);
ret = NULL;
} else if (rt->peer && peer_pmtu_expired(rt->peer)) {
dst_metric_set(dst, RTAX_MTU, rt->peer->pmtu_orig);
}
}
return ret;
}
/*
* Algorithm:
* 1. The first ip_rt_redirect_number redirects are sent
* with exponential backoff, then we stop sending them at all,
* assuming that the host ignores our redirects.
* 2. If we did not see packets requiring redirects
* during ip_rt_redirect_silence, we assume that the host
* forgot redirected route and start to send redirects again.
*
* This algorithm is much cheaper and more intelligent than dumb load limiting
* in icmp.c.
*
* NOTE. Do not forget to inhibit load limiting for redirects (redundant)
* and "frag. need" (breaks PMTU discovery) in icmp.c.
*/
void ip_rt_send_redirect(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct in_device *in_dev;
struct inet_peer *peer;
int log_martians;
rcu_read_lock();
in_dev = __in_dev_get_rcu(rt->dst.dev);
if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) {
rcu_read_unlock();
return;
}
log_martians = IN_DEV_LOG_MARTIANS(in_dev);
rcu_read_unlock();
if (!rt->peer)
rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
if (!peer) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
return;
}
/* No redirected packets during ip_rt_redirect_silence;
* reset the algorithm.
*/
if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence))
peer->rate_tokens = 0;
/* Too many ignored redirects; do not send anything
* set dst.rate_last to the last seen redirected packet.
*/
if (peer->rate_tokens >= ip_rt_redirect_number) {
peer->rate_last = jiffies;
return;
}
/* Check for load limit; set rate_last to the latest sent
* redirect.
*/
if (peer->rate_tokens == 0 ||
time_after(jiffies,
(peer->rate_last +
(ip_rt_redirect_load << peer->rate_tokens)))) {
icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
peer->rate_last = jiffies;
++peer->rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (log_martians &&
peer->rate_tokens == ip_rt_redirect_number &&
net_ratelimit())
printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n",
&ip_hdr(skb)->saddr, rt->rt_iif,
&rt->rt_dst, &rt->rt_gateway);
#endif
}
}
static int ip_error(struct sk_buff *skb)
{
struct rtable *rt = skb_rtable(skb);
struct inet_peer *peer;
unsigned long now;
bool send;
int code;
switch (rt->dst.error) {
case EINVAL:
default:
goto out;
case EHOSTUNREACH:
code = ICMP_HOST_UNREACH;
break;
case ENETUNREACH:
code = ICMP_NET_UNREACH;
IP_INC_STATS_BH(dev_net(rt->dst.dev),
IPSTATS_MIB_INNOROUTES);
break;
case EACCES:
code = ICMP_PKT_FILTERED;
break;
}
if (!rt->peer)
rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
send = true;
if (peer) {
now = jiffies;
peer->rate_tokens += now - peer->rate_last;
if (peer->rate_tokens > ip_rt_error_burst)
peer->rate_tokens = ip_rt_error_burst;
peer->rate_last = now;
if (peer->rate_tokens >= ip_rt_error_cost)
peer->rate_tokens -= ip_rt_error_cost;
else
send = false;
}
if (send)
icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
out: kfree_skb(skb);
return 0;
}
/*
* The last two values are not from the RFC but
* are needed for AMPRnet AX.25 paths.
*/
static const unsigned short mtu_plateau[] =
{32000, 17914, 8166, 4352, 2002, 1492, 576, 296, 216, 128 };
static inline unsigned short guess_mtu(unsigned short old_mtu)
{
int i;
for (i = 0; i < ARRAY_SIZE(mtu_plateau); i++)
if (old_mtu > mtu_plateau[i])
return mtu_plateau[i];
return 68;
}
unsigned short ip_rt_frag_needed(struct net *net, const struct iphdr *iph,
unsigned short new_mtu,
struct net_device *dev)
{
unsigned short old_mtu = ntohs(iph->tot_len);
unsigned short est_mtu = 0;
struct inet_peer *peer;
peer = inet_getpeer_v4(iph->daddr, 1);
if (peer) {
unsigned short mtu = new_mtu;
if (new_mtu < 68 || new_mtu >= old_mtu) {
/* BSD 4.2 derived systems incorrectly adjust
* tot_len by the IP header length, and report
* a zero MTU in the ICMP message.
*/
if (mtu == 0 &&
old_mtu >= 68 + (iph->ihl << 2))
old_mtu -= iph->ihl << 2;
mtu = guess_mtu(old_mtu);
}
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
if (!peer->pmtu_expires || mtu < peer->pmtu_learned) {
unsigned long pmtu_expires;
pmtu_expires = jiffies + ip_rt_mtu_expires;
if (!pmtu_expires)
pmtu_expires = 1UL;
est_mtu = mtu;
peer->pmtu_learned = mtu;
peer->pmtu_expires = pmtu_expires;
atomic_inc(&__rt_peer_genid);
}
inet_putpeer(peer);
}
return est_mtu ? : new_mtu;
}
static void check_peer_pmtu(struct dst_entry *dst, struct inet_peer *peer)
{
unsigned long expires = ACCESS_ONCE(peer->pmtu_expires);
if (!expires)
return;
if (time_before(jiffies, expires)) {
u32 orig_dst_mtu = dst_mtu(dst);
if (peer->pmtu_learned < orig_dst_mtu) {
if (!peer->pmtu_orig)
peer->pmtu_orig = dst_metric_raw(dst, RTAX_MTU);
dst_metric_set(dst, RTAX_MTU, peer->pmtu_learned);
}
} else if (cmpxchg(&peer->pmtu_expires, expires, 0) == expires)
dst_metric_set(dst, RTAX_MTU, peer->pmtu_orig);
}
static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
struct rtable *rt = (struct rtable *) dst;
struct inet_peer *peer;
dst_confirm(dst);
if (!rt->peer)
rt_bind_peer(rt, rt->rt_dst, 1);
peer = rt->peer;
if (peer) {
unsigned long pmtu_expires = ACCESS_ONCE(peer->pmtu_expires);
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
if (!pmtu_expires || mtu < peer->pmtu_learned) {
pmtu_expires = jiffies + ip_rt_mtu_expires;
if (!pmtu_expires)
pmtu_expires = 1UL;
peer->pmtu_learned = mtu;
peer->pmtu_expires = pmtu_expires;
atomic_inc(&__rt_peer_genid);
rt->rt_peer_genid = rt_peer_genid();
}
check_peer_pmtu(dst, peer);
}
}
static struct rtable *ipv4_validate_peer(struct rtable *rt)
{
if (rt->rt_peer_genid != rt_peer_genid()) {
struct inet_peer *peer;
if (!rt->peer)
rt_bind_peer(rt, rt->rt_dst, 0);
peer = rt->peer;
if (peer) {
check_peer_pmtu(&rt->dst, peer);
if (peer->redirect_genid != redirect_genid)
peer->redirect_learned.a4 = 0;
if (peer->redirect_learned.a4 &&
peer->redirect_learned.a4 != rt->rt_gateway) {
if (check_peer_redir(&rt->dst, peer))
return NULL;
}
}
rt->rt_peer_genid = rt_peer_genid();
}
return rt;
}
static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
{
struct rtable *rt = (struct rtable *) dst;
if (rt_is_expired(rt))
return NULL;
dst = (struct dst_entry *) ipv4_validate_peer(rt);
return dst;
}
static void ipv4_dst_destroy(struct dst_entry *dst)
{
struct rtable *rt = (struct rtable *) dst;
struct inet_peer *peer = rt->peer;
if (rt->fi) {
fib_info_put(rt->fi);
rt->fi = NULL;
}
if (peer) {
rt->peer = NULL;
inet_putpeer(peer);
}
}
static void ipv4_link_failure(struct sk_buff *skb)
{
struct rtable *rt;
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0);
rt = skb_rtable(skb);
if (rt && rt->peer && peer_pmtu_cleaned(rt->peer))
dst_metric_set(&rt->dst, RTAX_MTU, rt->peer->pmtu_orig);
}
static int ip_rt_bug(struct sk_buff *skb)
{
printk(KERN_DEBUG "ip_rt_bug: %pI4 -> %pI4, %s\n",
&ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr,
skb->dev ? skb->dev->name : "?");
kfree_skb(skb);
WARN_ON(1);
return 0;
}
/*
We do not cache source address of outgoing interface,
because it is used only by IP RR, TS and SRR options,
so that it out of fast path.
BTW remember: "addr" is allowed to be not aligned
in IP options!
*/
void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
{
__be32 src;
if (rt_is_output_route(rt))
src = ip_hdr(skb)->saddr;
else {
struct fib_result res;
struct flowi4 fl4;
struct iphdr *iph;
iph = ip_hdr(skb);
memset(&fl4, 0, sizeof(fl4));
fl4.daddr = iph->daddr;
fl4.saddr = iph->saddr;
fl4.flowi4_tos = RT_TOS(iph->tos);
fl4.flowi4_oif = rt->dst.dev->ifindex;
fl4.flowi4_iif = skb->dev->ifindex;
fl4.flowi4_mark = skb->mark;
rcu_read_lock();
if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res) == 0)
src = FIB_RES_PREFSRC(dev_net(rt->dst.dev), res);
else
src = inet_select_addr(rt->dst.dev, rt->rt_gateway,
RT_SCOPE_UNIVERSE);
rcu_read_unlock();
}
memcpy(addr, &src, 4);
}
#ifdef CONFIG_IP_ROUTE_CLASSID
static void set_class_tag(struct rtable *rt, u32 tag)
{
if (!(rt->dst.tclassid & 0xFFFF))
rt->dst.tclassid |= tag & 0xFFFF;
if (!(rt->dst.tclassid & 0xFFFF0000))
rt->dst.tclassid |= tag & 0xFFFF0000;
}
#endif
static unsigned int ipv4_default_advmss(const struct dst_entry *dst)
{
unsigned int advmss = dst_metric_raw(dst, RTAX_ADVMSS);
if (advmss == 0) {
advmss = max_t(unsigned int, dst->dev->mtu - 40,
ip_rt_min_advmss);
if (advmss > 65535 - 40)
advmss = 65535 - 40;
}
return advmss;
}
static unsigned int ipv4_mtu(const struct dst_entry *dst)
{
const struct rtable *rt = (const struct rtable *) dst;
unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
if (mtu && rt_is_output_route(rt))
return mtu;
mtu = dst->dev->mtu;
if (unlikely(dst_metric_locked(dst, RTAX_MTU))) {
if (rt->rt_gateway != rt->rt_dst && mtu > 576)
mtu = 576;
}
if (mtu > IP_MAX_MTU)
mtu = IP_MAX_MTU;
return mtu;
}
static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4,
struct fib_info *fi)
{
struct inet_peer *peer;
int create = 0;
/* If a peer entry exists for this destination, we must hook
* it up in order to get at cached metrics.
*/
if (fl4 && (fl4->flowi4_flags & FLOWI_FLAG_PRECOW_METRICS))
create = 1;
rt->peer = peer = inet_getpeer_v4(rt->rt_dst, create);
if (peer) {
rt->rt_peer_genid = rt_peer_genid();
if (inet_metrics_new(peer))
memcpy(peer->metrics, fi->fib_metrics,
sizeof(u32) * RTAX_MAX);
dst_init_metrics(&rt->dst, peer->metrics, false);
check_peer_pmtu(&rt->dst, peer);
if (peer->redirect_genid != redirect_genid)
peer->redirect_learned.a4 = 0;
if (peer->redirect_learned.a4 &&
peer->redirect_learned.a4 != rt->rt_gateway) {
rt->rt_gateway = peer->redirect_learned.a4;
rt->rt_flags |= RTCF_REDIRECTED;
}
} else {
if (fi->fib_metrics != (u32 *) dst_default_metrics) {
rt->fi = fi;
atomic_inc(&fi->fib_clntref);
}
dst_init_metrics(&rt->dst, fi->fib_metrics, true);
}
}
static void rt_set_nexthop(struct rtable *rt, const struct flowi4 *fl4,
const struct fib_result *res,
struct fib_info *fi, u16 type, u32 itag)
{
struct dst_entry *dst = &rt->dst;
if (fi) {
if (FIB_RES_GW(*res) &&
FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
rt->rt_gateway = FIB_RES_GW(*res);
rt_init_metrics(rt, fl4, fi);
#ifdef CONFIG_IP_ROUTE_CLASSID
dst->tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
}
if (dst_mtu(dst) > IP_MAX_MTU)
dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU);
if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40)
dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40);
#ifdef CONFIG_IP_ROUTE_CLASSID
#ifdef CONFIG_IP_MULTIPLE_TABLES
set_class_tag(rt, fib_rules_tclass(res));
#endif
set_class_tag(rt, itag);
#endif
}
static struct rtable *rt_dst_alloc(struct net_device *dev,
bool nopolicy, bool noxfrm)
{
return dst_alloc(&ipv4_dst_ops, dev, 1, -1,
DST_HOST |
(nopolicy ? DST_NOPOLICY : 0) |
(noxfrm ? DST_NOXFRM : 0));
}
/* called in rcu_read_lock() section */
static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, int our)
{
unsigned int hash;
struct rtable *rth;
__be32 spec_dst;
struct in_device *in_dev = __in_dev_get_rcu(dev);
u32 itag = 0;
int err;
/* Primary sanity checks. */
if (in_dev == NULL)
return -EINVAL;
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
ipv4_is_loopback(saddr) || skb->protocol != htons(ETH_P_IP))
goto e_inval;
if (ipv4_is_zeronet(saddr)) {
if (!ipv4_is_local_multicast(daddr))
goto e_inval;
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
} else {
err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst,
&itag);
if (err < 0)
goto e_err;
}
rth = rt_dst_alloc(init_net.loopback_dev,
IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
rth->dst.output = ip_rt_bug;
rth->rt_key_dst = daddr;
rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(dev_net(dev));
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
rth->rt_key_tos = tos;
rth->rt_dst = daddr;
rth->rt_src = saddr;
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
rth->peer = NULL;
rth->fi = NULL;
if (our) {
rth->dst.input= ip_local_deliver;
rth->rt_flags |= RTCF_LOCAL;
}
#ifdef CONFIG_IP_MROUTE
if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev))
rth->dst.input = ip_mr_input;
#endif
RT_CACHE_STAT_INC(in_slow_mc);
hash = rt_hash(daddr, saddr, dev->ifindex, rt_genid(dev_net(dev)));
rth = rt_intern_hash(hash, rth, skb, dev->ifindex);
return IS_ERR(rth) ? PTR_ERR(rth) : 0;
e_nobufs:
return -ENOBUFS;
e_inval:
return -EINVAL;
e_err:
return err;
}
static void ip_handle_martian_source(struct net_device *dev,
struct in_device *in_dev,
struct sk_buff *skb,
__be32 daddr,
__be32 saddr)
{
RT_CACHE_STAT_INC(in_martian_src);
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) {
/*
* RFC1812 recommendation, if source is martian,
* the only hint is MAC header.
*/
printk(KERN_WARNING "martian source %pI4 from %pI4, on dev %s\n",
&daddr, &saddr, dev->name);
if (dev->hard_header_len && skb_mac_header_was_set(skb)) {
int i;
const unsigned char *p = skb_mac_header(skb);
printk(KERN_WARNING "ll header: ");
for (i = 0; i < dev->hard_header_len; i++, p++) {
printk("%02x", *p);
if (i < (dev->hard_header_len - 1))
printk(":");
}
printk("\n");
}
}
#endif
}
/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
const struct fib_result *res,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos,
struct rtable **result)
{
struct rtable *rth;
int err;
struct in_device *out_dev;
unsigned int flags = 0;
__be32 spec_dst;
u32 itag;
/* get a working reference to the output device */
out_dev = __in_dev_get_rcu(FIB_RES_DEV(*res));
if (out_dev == NULL) {
if (net_ratelimit())
printk(KERN_CRIT "Bug in ip_route_input" \
"_slow(). Please, report\n");
return -EINVAL;
}
err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, &spec_dst, &itag);
if (err < 0) {
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
goto cleanup;
}
if (err)
flags |= RTCF_DIRECTSRC;
if (out_dev == in_dev && err &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
flags |= RTCF_DOREDIRECT;
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
* invalid for proxy arp. DNAT routes are always valid.
*
* Proxy arp feature have been extended to allow, ARP
* replies back to the same interface, to support
* Private VLAN switch technologies. See arp.c.
*/
if (out_dev == in_dev &&
IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) {
err = -EINVAL;
goto cleanup;
}
}
rth = rt_dst_alloc(out_dev->dev,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
}
rth->rt_key_dst = daddr;
rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
rth->rt_flags = flags;
rth->rt_type = res->type;
rth->rt_key_tos = tos;
rth->rt_dst = daddr;
rth->rt_src = saddr;
rth->rt_route_iif = in_dev->dev->ifindex;
rth->rt_iif = in_dev->dev->ifindex;
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
rth->peer = NULL;
rth->fi = NULL;
rth->dst.input = ip_forward;
rth->dst.output = ip_output;
rt_set_nexthop(rth, NULL, res, res->fi, res->type, itag);
*result = rth;
err = 0;
cleanup:
return err;
}
static int ip_mkroute_input(struct sk_buff *skb,
struct fib_result *res,
const struct flowi4 *fl4,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos)
{
struct rtable* rth = NULL;
int err;
unsigned hash;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1)
fib_select_multipath(res);
#endif
/* create a routing cache entry */
err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth);
if (err)
return err;
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl4->flowi4_iif,
rt_genid(dev_net(rth->dst.dev)));
rth = rt_intern_hash(hash, rth, skb, fl4->flowi4_iif);
if (IS_ERR(rth))
return PTR_ERR(rth);
return 0;
}
/*
* NOTE. We drop all the packets that has local source
* addresses, because every properly looped back packet
* must have correct destination already attached by output routine.
*
* Such approach solves two big problems:
* 1. Not simplex devices are handled properly.
* 2. IP spoofing attempts are filtered with 100% of guarantee.
* called with rcu_read_lock()
*/
static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev)
{
struct fib_result res;
struct in_device *in_dev = __in_dev_get_rcu(dev);
struct flowi4 fl4;
unsigned flags = 0;
u32 itag = 0;
struct rtable * rth;
unsigned hash;
__be32 spec_dst;
int err = -EINVAL;
struct net * net = dev_net(dev);
/* IP on this device is disabled. */
if (!in_dev)
goto out;
/* Check for the most weird martians, which can be not detected
by fib_lookup.
*/
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
ipv4_is_loopback(saddr))
goto martian_source;
if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0))
goto brd_input;
/* Accept zero addresses only to limited broadcast;
* I even do not know to fix it or not. Waiting for complains :-)
*/
if (ipv4_is_zeronet(saddr))
goto martian_source;
if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr))
goto martian_destination;
/*
* Now we are ready to route packet.
*/
fl4.flowi4_oif = 0;
fl4.flowi4_iif = dev->ifindex;
fl4.flowi4_mark = skb->mark;
fl4.flowi4_tos = tos;
fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
fl4.daddr = daddr;
fl4.saddr = saddr;
err = fib_lookup(net, &fl4, &res);
if (err != 0) {
if (!IN_DEV_FORWARD(in_dev))
goto e_hostunreach;
goto no_route;
}
RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_BROADCAST)
goto brd_input;
if (res.type == RTN_LOCAL) {
err = fib_validate_source(skb, saddr, daddr, tos,
net->loopback_dev->ifindex,
dev, &spec_dst, &itag);
if (err < 0)
goto martian_source_keep_err;
if (err)
flags |= RTCF_DIRECTSRC;
spec_dst = daddr;
goto local_input;
}
if (!IN_DEV_FORWARD(in_dev))
goto e_hostunreach;
if (res.type != RTN_UNICAST)
goto martian_destination;
err = ip_mkroute_input(skb, &res, &fl4, in_dev, daddr, saddr, tos);
out: return err;
brd_input:
if (skb->protocol != htons(ETH_P_IP))
goto e_inval;
if (ipv4_is_zeronet(saddr))
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
else {
err = fib_validate_source(skb, saddr, 0, tos, 0, dev, &spec_dst,
&itag);
if (err < 0)
goto martian_source_keep_err;
if (err)
flags |= RTCF_DIRECTSRC;
}
flags |= RTCF_BROADCAST;
res.type = RTN_BROADCAST;
RT_CACHE_STAT_INC(in_brd);
local_input:
rth = rt_dst_alloc(net->loopback_dev,
IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
if (!rth)
goto e_nobufs;
rth->dst.input= ip_local_deliver;
rth->dst.output= ip_rt_bug;
#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
rth->rt_key_dst = daddr;
rth->rt_key_src = saddr;
rth->rt_genid = rt_genid(net);
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
rth->rt_key_tos = tos;
rth->rt_dst = daddr;
rth->rt_src = saddr;
#ifdef CONFIG_IP_ROUTE_CLASSID
rth->dst.tclassid = itag;
#endif
rth->rt_route_iif = dev->ifindex;
rth->rt_iif = dev->ifindex;
rth->rt_oif = 0;
rth->rt_mark = skb->mark;
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->rt_peer_genid = 0;
rth->peer = NULL;
rth->fi = NULL;
if (res.type == RTN_UNREACHABLE) {
rth->dst.input= ip_error;
rth->dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
hash = rt_hash(daddr, saddr, fl4.flowi4_iif, rt_genid(net));
rth = rt_intern_hash(hash, rth, skb, fl4.flowi4_iif);
err = 0;
if (IS_ERR(rth))
err = PTR_ERR(rth);
goto out;
no_route:
RT_CACHE_STAT_INC(in_no_route);
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
res.type = RTN_UNREACHABLE;
if (err == -ESRCH)
err = -ENETUNREACH;
goto local_input;
/*
* Do not cache martian addresses: they should be logged (RFC1812)
*/
martian_destination:
RT_CACHE_STAT_INC(in_martian_dst);
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
printk(KERN_WARNING "martian destination %pI4 from %pI4, dev %s\n",
&daddr, &saddr, dev->name);
#endif
e_hostunreach:
err = -EHOSTUNREACH;
goto out;
e_inval:
err = -EINVAL;
goto out;
e_nobufs:
err = -ENOBUFS;
goto out;
martian_source:
err = -EINVAL;
martian_source_keep_err:
ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
goto out;
}
int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev, bool noref)
{
struct rtable * rth;
unsigned hash;
int iif = dev->ifindex;
struct net *net;
int res;
net = dev_net(dev);
rcu_read_lock();
if (!rt_caching(net))
goto skip_cache;
tos &= IPTOS_RT_MASK;
hash = rt_hash(daddr, saddr, iif, rt_genid(net));
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
rth = rcu_dereference(rth->dst.rt_next)) {
if ((((__force u32)rth->rt_key_dst ^ (__force u32)daddr) |
((__force u32)rth->rt_key_src ^ (__force u32)saddr) |
(rth->rt_route_iif ^ iif) |
(rth->rt_key_tos ^ tos)) == 0 &&
rth->rt_mark == skb->mark &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
rth = ipv4_validate_peer(rth);
if (!rth)
continue;
if (noref) {
dst_use_noref(&rth->dst, jiffies);
skb_dst_set_noref(skb, &rth->dst);
} else {
dst_use(&rth->dst, jiffies);
skb_dst_set(skb, &rth->dst);
}
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
return 0;
}
RT_CACHE_STAT_INC(in_hlist_search);
}
skip_cache:
/* Multicast recognition logic is moved from route cache to here.
The problem was that too many Ethernet cards have broken/missing
hardware multicast filters :-( As result the host on multicasting
network acquires a lot of useless route cache entries, sort of
SDR messages from all the world. Now we try to get rid of them.
Really, provided software IP multicast filter is organized
reasonably (at least, hashed), it does not result in a slowdown
comparing with route cache reject entries.
Note, that multicast routers are not affected, because
route cache entry is created eventually.
*/
if (ipv4_is_multicast(daddr)) {
struct in_device *in_dev = __in_dev_get_rcu(dev);
if (in_dev) {
int our = ip_check_mc_rcu(in_dev, daddr, saddr,
ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
||
(!ipv4_is_local_multicast(daddr) &&
IN_DEV_MFORWARD(in_dev))
#endif
) {
int res = ip_route_input_mc(skb, daddr, saddr,
tos, dev, our);
rcu_read_unlock();
return res;
}
}
rcu_read_unlock();
return -EINVAL;
}
res = ip_route_input_slow(skb, daddr, saddr, tos, dev);
rcu_read_unlock();
return res;
}
EXPORT_SYMBOL(ip_route_input_common);
/* called with rcu_read_lock() */
static struct rtable *__mkroute_output(const struct fib_result *res,
const struct flowi4 *fl4,
__be32 orig_daddr, __be32 orig_saddr,
int orig_oif, __u8 orig_rtos,
struct net_device *dev_out,
unsigned int flags)
{
struct fib_info *fi = res->fi;
struct in_device *in_dev;
u16 type = res->type;
struct rtable *rth;
if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK))
return ERR_PTR(-EINVAL);
if (ipv4_is_lbcast(fl4->daddr))
type = RTN_BROADCAST;
else if (ipv4_is_multicast(fl4->daddr))
type = RTN_MULTICAST;
else if (ipv4_is_zeronet(fl4->daddr))
return ERR_PTR(-EINVAL);
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
in_dev = __in_dev_get_rcu(dev_out);
if (!in_dev)
return ERR_PTR(-EINVAL);
if (type == RTN_BROADCAST) {
flags |= RTCF_BROADCAST | RTCF_LOCAL;
fi = NULL;
} else if (type == RTN_MULTICAST) {
flags |= RTCF_MULTICAST | RTCF_LOCAL;
if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
fl4->flowi4_proto))
flags &= ~RTCF_LOCAL;
/* If multicast route do not exist use
* default one, but do not gateway in this case.
* Yes, it is hack.
*/
if (fi && res->prefixlen < 4)
fi = NULL;
}
rth = rt_dst_alloc(dev_out,
IN_DEV_CONF_GET(in_dev, NOPOLICY),
IN_DEV_CONF_GET(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
rth->dst.output = ip_output;
rth->rt_key_dst = orig_daddr;
rth->rt_key_src = orig_saddr;
rth->rt_genid = rt_genid(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
rth->rt_key_tos = orig_rtos;
rth->rt_dst = fl4->daddr;
rth->rt_src = fl4->saddr;
rth->rt_route_iif = 0;
rth->rt_iif = orig_oif ? : dev_out->ifindex;
rth->rt_oif = orig_oif;
rth->rt_mark = fl4->flowi4_mark;
rth->rt_gateway = fl4->daddr;
rth->rt_spec_dst= fl4->saddr;
rth->rt_peer_genid = 0;
rth->peer = NULL;
rth->fi = NULL;
RT_CACHE_STAT_INC(out_slow_tot);
if (flags & RTCF_LOCAL) {
rth->dst.input = ip_local_deliver;
rth->rt_spec_dst = fl4->daddr;
}
if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
rth->rt_spec_dst = fl4->saddr;
if (flags & RTCF_LOCAL &&
!(dev_out->flags & IFF_LOOPBACK)) {
rth->dst.output = ip_mc_output;
RT_CACHE_STAT_INC(out_slow_mc);
}
#ifdef CONFIG_IP_MROUTE
if (type == RTN_MULTICAST) {
if (IN_DEV_MFORWARD(in_dev) &&
!ipv4_is_local_multicast(fl4->daddr)) {
rth->dst.input = ip_mr_input;
rth->dst.output = ip_mc_output;
}
}
#endif
}
rt_set_nexthop(rth, fl4, res, fi, type, 0);
return rth;
}
/*
* Major route resolver routine.
* called with rcu_read_lock();
*/
static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4)
{
struct net_device *dev_out = NULL;
__u8 tos = RT_FL_TOS(fl4);
unsigned int flags = 0;
struct fib_result res;
struct rtable *rth;
__be32 orig_daddr;
__be32 orig_saddr;
int orig_oif;
res.fi = NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
res.r = NULL;
#endif
orig_daddr = fl4->daddr;
orig_saddr = fl4->saddr;
orig_oif = fl4->flowi4_oif;
fl4->flowi4_iif = net->loopback_dev->ifindex;
fl4->flowi4_tos = tos & IPTOS_RT_MASK;
fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
rcu_read_lock();
if (fl4->saddr) {
rth = ERR_PTR(-EINVAL);
if (ipv4_is_multicast(fl4->saddr) ||
ipv4_is_lbcast(fl4->saddr) ||
ipv4_is_zeronet(fl4->saddr))
goto out;
/* I removed check for oif == dev_out->oif here.
It was wrong for two reasons:
1. ip_dev_find(net, saddr) can return wrong iface, if saddr
is assigned to multiple interfaces.
2. Moreover, we are allowed to send packets with saddr
of another iface. --ANK
*/
if (fl4->flowi4_oif == 0 &&
(ipv4_is_multicast(fl4->daddr) ||
ipv4_is_lbcast(fl4->daddr))) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
dev_out = __ip_dev_find(net, fl4->saddr, false);
if (dev_out == NULL)
goto out;
/* Special hack: user can direct multicasts
and limited broadcast via necessary interface
without fiddling with IP_MULTICAST_IF or IP_PKTINFO.
This hack is not just for fun, it allows
vic,vat and friends to work.
They bind socket to loopback, set ttl to zero
and expect that it will work.
From the viewpoint of routing cache they are broken,
because we are not allowed to build multicast path
with loopback source addr (look, routing cache
cannot know, that ttl is zero, so that packet
will not leave this host and route is valid).
Luckily, this hack is good workaround.
*/
fl4->flowi4_oif = dev_out->ifindex;
goto make_route;
}
if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) {
/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
if (!__ip_dev_find(net, fl4->saddr, false))
goto out;
}
}
if (fl4->flowi4_oif) {
dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif);
rth = ERR_PTR(-ENODEV);
if (dev_out == NULL)
goto out;
/* RACE: Check return value of inet_select_addr instead. */
if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) {
rth = ERR_PTR(-ENETUNREACH);
goto out;
}
if (ipv4_is_local_multicast(fl4->daddr) ||
ipv4_is_lbcast(fl4->daddr)) {
if (!fl4->saddr)
fl4->saddr = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
goto make_route;
}
if (fl4->saddr) {
if (ipv4_is_multicast(fl4->daddr))
fl4->saddr = inet_select_addr(dev_out, 0,
fl4->flowi4_scope);
else if (!fl4->daddr)
fl4->saddr = inet_select_addr(dev_out, 0,
RT_SCOPE_HOST);
}
}
if (!fl4->daddr) {
fl4->daddr = fl4->saddr;
if (!fl4->daddr)
fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK);
dev_out = net->loopback_dev;
fl4->flowi4_oif = net->loopback_dev->ifindex;
res.type = RTN_LOCAL;
flags |= RTCF_LOCAL;
goto make_route;
}
if (fib_lookup(net, fl4, &res)) {
res.fi = NULL;
if (fl4->flowi4_oif) {
/* Apparently, routing tables are wrong. Assume,
that the destination is on link.
WHY? DW.
Because we are allowed to send to iface
even if it has NO routes and NO assigned
addresses. When oif is specified, routing
tables are looked up with only one purpose:
to catch if destination is gatewayed, rather than
direct. Moreover, if MSG_DONTROUTE is set,
we send packet, ignoring both routing tables
and ifaddr state. --ANK
We could make it even if oif is unknown,
likely IPv6, but we do not.
*/
if (fl4->saddr == 0)
fl4->saddr = inet_select_addr(dev_out, 0,
RT_SCOPE_LINK);
res.type = RTN_UNICAST;
goto make_route;
}
rth = ERR_PTR(-ENETUNREACH);
goto out;
}
if (res.type == RTN_LOCAL) {
if (!fl4->saddr) {
if (res.fi->fib_prefsrc)
fl4->saddr = res.fi->fib_prefsrc;
else
fl4->saddr = fl4->daddr;
}
dev_out = net->loopback_dev;
fl4->flowi4_oif = dev_out->ifindex;
res.fi = NULL;
flags |= RTCF_LOCAL;
goto make_route;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res.fi->fib_nhs > 1 && fl4->flowi4_oif == 0)
fib_select_multipath(&res);
else
#endif
if (!res.prefixlen &&
res.table->tb_num_default > 1 &&
res.type == RTN_UNICAST && !fl4->flowi4_oif)
fib_select_default(&res);
if (!fl4->saddr)
fl4->saddr = FIB_RES_PREFSRC(net, res);
dev_out = FIB_RES_DEV(res);
fl4->flowi4_oif = dev_out->ifindex;
make_route:
rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif,
tos, dev_out, flags);
if (!IS_ERR(rth)) {
unsigned int hash;
hash = rt_hash(orig_daddr, orig_saddr, orig_oif,
rt_genid(dev_net(dev_out)));
rth = rt_intern_hash(hash, rth, NULL, orig_oif);
}
out:
rcu_read_unlock();
return rth;
}
struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4)
{
struct rtable *rth;
unsigned int hash;
if (!rt_caching(net))
goto slow_output;
hash = rt_hash(flp4->daddr, flp4->saddr, flp4->flowi4_oif, rt_genid(net));
rcu_read_lock_bh();
for (rth = rcu_dereference_bh(rt_hash_table[hash].chain); rth;
rth = rcu_dereference_bh(rth->dst.rt_next)) {
if (rth->rt_key_dst == flp4->daddr &&
rth->rt_key_src == flp4->saddr &&
rt_is_output_route(rth) &&
rth->rt_oif == flp4->flowi4_oif &&
rth->rt_mark == flp4->flowi4_mark &&
!((rth->rt_key_tos ^ flp4->flowi4_tos) &
(IPTOS_RT_MASK | RTO_ONLINK)) &&
net_eq(dev_net(rth->dst.dev), net) &&
!rt_is_expired(rth)) {
rth = ipv4_validate_peer(rth);
if (!rth)
continue;
dst_use(&rth->dst, jiffies);
RT_CACHE_STAT_INC(out_hit);
rcu_read_unlock_bh();
if (!flp4->saddr)
flp4->saddr = rth->rt_src;
if (!flp4->daddr)
flp4->daddr = rth->rt_dst;
return rth;
}
RT_CACHE_STAT_INC(out_hlist_search);
}
rcu_read_unlock_bh();
slow_output:
return ip_route_output_slow(net, flp4);
}
EXPORT_SYMBOL_GPL(__ip_route_output_key);
static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie)
{
return NULL;
}
static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst)
{
unsigned int mtu = dst_metric_raw(dst, RTAX_MTU);
return mtu ? : dst->dev->mtu;
}
static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}
static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst,
unsigned long old)
{
return NULL;
}
static struct dst_ops ipv4_dst_blackhole_ops = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.destroy = ipv4_dst_destroy,
.check = ipv4_blackhole_dst_check,
.mtu = ipv4_blackhole_mtu,
.default_advmss = ipv4_default_advmss,
.update_pmtu = ipv4_rt_blackhole_update_pmtu,
.cow_metrics = ipv4_rt_blackhole_cow_metrics,
.neigh_lookup = ipv4_neigh_lookup,
};
struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig)
{
struct rtable *rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, 0, 0);
struct rtable *ort = (struct rtable *) dst_orig;
if (rt) {
struct dst_entry *new = &rt->dst;
new->__use = 1;
new->input = dst_discard;
new->output = dst_discard;
dst_copy_metrics(new, &ort->dst);
new->dev = ort->dst.dev;
if (new->dev)
dev_hold(new->dev);
rt->rt_key_dst = ort->rt_key_dst;
rt->rt_key_src = ort->rt_key_src;
rt->rt_key_tos = ort->rt_key_tos;
rt->rt_route_iif = ort->rt_route_iif;
rt->rt_iif = ort->rt_iif;
rt->rt_oif = ort->rt_oif;
rt->rt_mark = ort->rt_mark;
rt->rt_genid = rt_genid(net);
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_dst = ort->rt_dst;
rt->rt_src = ort->rt_src;
rt->rt_gateway = ort->rt_gateway;
rt->rt_spec_dst = ort->rt_spec_dst;
rt->peer = ort->peer;
if (rt->peer)
atomic_inc(&rt->peer->refcnt);
rt->fi = ort->fi;
if (rt->fi)
atomic_inc(&rt->fi->fib_clntref);
dst_free(new);
}
dst_release(dst_orig);
return rt ? &rt->dst : ERR_PTR(-ENOMEM);
}
struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4,
struct sock *sk)
{
struct rtable *rt = __ip_route_output_key(net, flp4);
if (IS_ERR(rt))
return rt;
if (flp4->flowi4_proto)
rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
flowi4_to_flowi(flp4),
sk, 0);
return rt;
}
EXPORT_SYMBOL_GPL(ip_route_output_flow);
static int rt_fill_info(struct net *net,
struct sk_buff *skb, u32 pid, u32 seq, int event,
int nowait, unsigned int flags)
{
struct rtable *rt = skb_rtable(skb);
struct rtmsg *r;
struct nlmsghdr *nlh;
unsigned long expires = 0;
const struct inet_peer *peer = rt->peer;
u32 id = 0, ts = 0, tsage = 0, error;
nlh = nlmsg_put(skb, pid, seq, event, sizeof(*r), flags);
if (nlh == NULL)
return -EMSGSIZE;
r = nlmsg_data(nlh);
r->rtm_family = AF_INET;
r->rtm_dst_len = 32;
r->rtm_src_len = 0;
r->rtm_tos = rt->rt_key_tos;
r->rtm_table = RT_TABLE_MAIN;
NLA_PUT_U32(skb, RTA_TABLE, RT_TABLE_MAIN);
r->rtm_type = rt->rt_type;
r->rtm_scope = RT_SCOPE_UNIVERSE;
r->rtm_protocol = RTPROT_UNSPEC;
r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED;
if (rt->rt_flags & RTCF_NOTIFY)
r->rtm_flags |= RTM_F_NOTIFY;
NLA_PUT_BE32(skb, RTA_DST, rt->rt_dst);
if (rt->rt_key_src) {
r->rtm_src_len = 32;
NLA_PUT_BE32(skb, RTA_SRC, rt->rt_key_src);
}
if (rt->dst.dev)
NLA_PUT_U32(skb, RTA_OIF, rt->dst.dev->ifindex);
#ifdef CONFIG_IP_ROUTE_CLASSID
if (rt->dst.tclassid)
NLA_PUT_U32(skb, RTA_FLOW, rt->dst.tclassid);
#endif
if (rt_is_input_route(rt))
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_spec_dst);
else if (rt->rt_src != rt->rt_key_src)
NLA_PUT_BE32(skb, RTA_PREFSRC, rt->rt_src);
if (rt->rt_dst != rt->rt_gateway)
NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway);
if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
goto nla_put_failure;
if (rt->rt_mark)
NLA_PUT_BE32(skb, RTA_MARK, rt->rt_mark);
error = rt->dst.error;
if (peer) {
inet_peer_refcheck(rt->peer);
id = atomic_read(&peer->ip_id_count) & 0xffff;
if (peer->tcp_ts_stamp) {
ts = peer->tcp_ts;
tsage = get_seconds() - peer->tcp_ts_stamp;
}
expires = ACCESS_ONCE(peer->pmtu_expires);
if (expires) {
if (time_before(jiffies, expires))
expires -= jiffies;
else
expires = 0;
}
}
if (rt_is_input_route(rt)) {
#ifdef CONFIG_IP_MROUTE
__be32 dst = rt->rt_dst;
if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) &&
IPV4_DEVCONF_ALL(net, MC_FORWARDING)) {
int err = ipmr_get_route(net, skb,
rt->rt_src, rt->rt_dst,
r, nowait);
if (err <= 0) {
if (!nowait) {
if (err == 0)
return 0;
goto nla_put_failure;
} else {
if (err == -EMSGSIZE)
goto nla_put_failure;
error = err;
}
}
} else
#endif
NLA_PUT_U32(skb, RTA_IIF, rt->rt_iif);
}
if (rtnl_put_cacheinfo(skb, &rt->dst, id, ts, tsage,
expires, error) < 0)
goto nla_put_failure;
return nlmsg_end(skb, nlh);
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
struct net *net = sock_net(in_skb->sk);
struct rtmsg *rtm;
struct nlattr *tb[RTA_MAX+1];
struct rtable *rt = NULL;
__be32 dst = 0;
__be32 src = 0;
u32 iif;
int err;
int mark;
struct sk_buff *skb;
err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy);
if (err < 0)
goto errout;
rtm = nlmsg_data(nlh);
skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
if (skb == NULL) {
err = -ENOBUFS;
goto errout;
}
/* Reserve room for dummy headers, this skb can pass
through good chunk of routing engine.
*/
skb_reset_mac_header(skb);
skb_reset_network_header(skb);
/* Bugfix: need to give ip_route_input enough of an IP header to not gag. */
ip_hdr(skb)->protocol = IPPROTO_ICMP;
skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));
src = tb[RTA_SRC] ? nla_get_be32(tb[RTA_SRC]) : 0;
dst = tb[RTA_DST] ? nla_get_be32(tb[RTA_DST]) : 0;
iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0;
mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0;
if (iif) {
struct net_device *dev;
dev = __dev_get_by_index(net, iif);
if (dev == NULL) {
err = -ENODEV;
goto errout_free;
}
skb->protocol = htons(ETH_P_IP);
skb->dev = dev;
skb->mark = mark;
local_bh_disable();
err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
local_bh_enable();
rt = skb_rtable(skb);
if (err == 0 && rt->dst.error)
err = -rt->dst.error;
} else {
struct flowi4 fl4 = {
.daddr = dst,
.saddr = src,
.flowi4_tos = rtm->rtm_tos,
.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0,
.flowi4_mark = mark,
};
rt = ip_route_output_key(net, &fl4);
err = 0;
if (IS_ERR(rt))
err = PTR_ERR(rt);
}
if (err)
goto errout_free;
skb_dst_set(skb, &rt->dst);
if (rtm->rtm_flags & RTM_F_NOTIFY)
rt->rt_flags |= RTCF_NOTIFY;
err = rt_fill_info(net, skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq,
RTM_NEWROUTE, 0, 0);
if (err <= 0)
goto errout_free;
err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
errout:
return err;
errout_free:
kfree_skb(skb);
goto errout;
}
int ip_rt_dump(struct sk_buff *skb, struct netlink_callback *cb)
{
struct rtable *rt;
int h, s_h;
int idx, s_idx;
struct net *net;
net = sock_net(skb->sk);
s_h = cb->args[0];
if (s_h < 0)
s_h = 0;
s_idx = idx = cb->args[1];
for (h = s_h; h <= rt_hash_mask; h++, s_idx = 0) {
if (!rt_hash_table[h].chain)
continue;
rcu_read_lock_bh();
for (rt = rcu_dereference_bh(rt_hash_table[h].chain), idx = 0; rt;
rt = rcu_dereference_bh(rt->dst.rt_next), idx++) {
if (!net_eq(dev_net(rt->dst.dev), net) || idx < s_idx)
continue;
if (rt_is_expired(rt))
continue;
skb_dst_set_noref(skb, &rt->dst);
if (rt_fill_info(net, skb, NETLINK_CB(cb->skb).pid,
cb->nlh->nlmsg_seq, RTM_NEWROUTE,
1, NLM_F_MULTI) <= 0) {
skb_dst_drop(skb);
rcu_read_unlock_bh();
goto done;
}
skb_dst_drop(skb);
}
rcu_read_unlock_bh();
}
done:
cb->args[0] = h;
cb->args[1] = idx;
return skb->len;
}
void ip_rt_multicast_event(struct in_device *in_dev)
{
rt_cache_flush(dev_net(in_dev->dev), 0);
}
#ifdef CONFIG_SYSCTL
static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
if (write) {
int flush_delay;
ctl_table ctl;
struct net *net;
memcpy(&ctl, __ctl, sizeof(ctl));
ctl.data = &flush_delay;
proc_dointvec(&ctl, write, buffer, lenp, ppos);
net = (struct net *)__ctl->extra1;
rt_cache_flush(net, flush_delay);
return 0;
}
return -EINVAL;
}
static ctl_table ipv4_route_table[] = {
{
.procname = "gc_thresh",
.data = &ipv4_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "max_size",
.data = &ip_rt_max_size,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
/* Deprecated. Use gc_min_interval_ms */
.procname = "gc_min_interval",
.data = &ip_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "gc_min_interval_ms",
.data = &ip_rt_gc_min_interval,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_ms_jiffies,
},
{
.procname = "gc_timeout",
.data = &ip_rt_gc_timeout,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "redirect_load",
.data = &ip_rt_redirect_load,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "redirect_number",
.data = &ip_rt_redirect_number,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "redirect_silence",
.data = &ip_rt_redirect_silence,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "error_cost",
.data = &ip_rt_error_cost,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "error_burst",
.data = &ip_rt_error_burst,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "gc_elasticity",
.data = &ip_rt_gc_elasticity,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "mtu_expires",
.data = &ip_rt_mtu_expires,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec_jiffies,
},
{
.procname = "min_pmtu",
.data = &ip_rt_min_pmtu,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{
.procname = "min_adv_mss",
.data = &ip_rt_min_advmss,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
},
{ }
};
static struct ctl_table empty[1];
static struct ctl_table ipv4_skeleton[] =
{
{ .procname = "route",
.mode = 0555, .child = ipv4_route_table},
{ .procname = "neigh",
.mode = 0555, .child = empty},
{ }
};
static __net_initdata struct ctl_path ipv4_path[] = {
{ .procname = "net", },
{ .procname = "ipv4", },
{ },
};
static struct ctl_table ipv4_route_flush_table[] = {
{
.procname = "flush",
.maxlen = sizeof(int),
.mode = 0200,
.proc_handler = ipv4_sysctl_rtcache_flush,
},
{ },
};
static __net_initdata struct ctl_path ipv4_route_path[] = {
{ .procname = "net", },
{ .procname = "ipv4", },
{ .procname = "route", },
{ },
};
static __net_init int sysctl_route_net_init(struct net *net)
{
struct ctl_table *tbl;
tbl = ipv4_route_flush_table;
if (!net_eq(net, &init_net)) {
tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL);
if (tbl == NULL)
goto err_dup;
}
tbl[0].extra1 = net;
net->ipv4.route_hdr =
register_net_sysctl_table(net, ipv4_route_path, tbl);
if (net->ipv4.route_hdr == NULL)
goto err_reg;
return 0;
err_reg:
if (tbl != ipv4_route_flush_table)
kfree(tbl);
err_dup:
return -ENOMEM;
}
static __net_exit void sysctl_route_net_exit(struct net *net)
{
struct ctl_table *tbl;
tbl = net->ipv4.route_hdr->ctl_table_arg;
unregister_net_sysctl_table(net->ipv4.route_hdr);
BUG_ON(tbl == ipv4_route_flush_table);
kfree(tbl);
}
static __net_initdata struct pernet_operations sysctl_route_ops = {
.init = sysctl_route_net_init,
.exit = sysctl_route_net_exit,
};
#endif
static __net_init int rt_genid_init(struct net *net)
{
get_random_bytes(&net->ipv4.rt_genid,
sizeof(net->ipv4.rt_genid));
get_random_bytes(&net->ipv4.dev_addr_genid,
sizeof(net->ipv4.dev_addr_genid));
return 0;
}
static __net_initdata struct pernet_operations rt_genid_ops = {
.init = rt_genid_init,
};
#ifdef CONFIG_IP_ROUTE_CLASSID
struct ip_rt_acct __percpu *ip_rt_acct __read_mostly;
#endif /* CONFIG_IP_ROUTE_CLASSID */
static __initdata unsigned long rhash_entries;
static int __init set_rhash_entries(char *str)
{
if (!str)
return 0;
rhash_entries = simple_strtoul(str, &str, 0);
return 1;
}
__setup("rhash_entries=", set_rhash_entries);
int __init ip_rt_init(void)
{
int rc = 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct));
if (!ip_rt_acct)
panic("IP: failed to allocate ip_rt_acct\n");
#endif
ipv4_dst_ops.kmem_cachep =
kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0,
SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep;
if (dst_entries_init(&ipv4_dst_ops) < 0)
panic("IP: failed to allocate ipv4_dst_ops counter\n");
if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0)
panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n");
rt_hash_table = (struct rt_hash_bucket *)
alloc_large_system_hash("IP route cache",
sizeof(struct rt_hash_bucket),
rhash_entries,
(totalram_pages >= 128 * 1024) ?
15 : 17,
0,
&rt_hash_log,
&rt_hash_mask,
rhash_entries ? 0 : 512 * 1024);
memset(rt_hash_table, 0, (rt_hash_mask + 1) * sizeof(struct rt_hash_bucket));
rt_hash_lock_init();
ipv4_dst_ops.gc_thresh = (rt_hash_mask + 1);
ip_rt_max_size = (rt_hash_mask + 1) * 16;
devinet_init();
ip_fib_init();
if (ip_rt_proc_init())
printk(KERN_ERR "Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
xfrm4_init(ip_rt_max_size);
#endif
rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL);
#ifdef CONFIG_SYSCTL
register_pernet_subsys(&sysctl_route_ops);
#endif
register_pernet_subsys(&rt_genid_ops);
return rc;
}
#ifdef CONFIG_SYSCTL
/*
* We really need to sanitize the damn ipv4 init order, then all
* this nonsense will go away.
*/
void __init ip_static_sysctl_init(void)
{
register_sysctl_paths(ipv4_path, ipv4_skeleton);
}
#endif
|