summaryrefslogtreecommitdiffstats
path: root/net/ipv6/route.c
blob: d9cb832be52919960b0d11e902372fd1f286ffc8 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
2073
2074
2075
2076
2077
2078
2079
2080
2081
2082
2083
2084
2085
2086
2087
2088
2089
2090
2091
2092
2093
2094
2095
2096
2097
2098
2099
2100
2101
2102
2103
2104
2105
2106
2107
2108
2109
2110
2111
2112
2113
2114
2115
2116
2117
2118
2119
2120
2121
2122
2123
2124
2125
2126
2127
2128
2129
2130
2131
2132
2133
2134
2135
2136
2137
2138
2139
2140
2141
2142
2143
2144
2145
2146
2147
2148
2149
2150
2151
2152
2153
2154
2155
2156
2157
2158
2159
2160
2161
2162
2163
2164
2165
2166
2167
2168
2169
2170
2171
2172
2173
2174
2175
2176
2177
2178
2179
2180
2181
2182
2183
2184
2185
2186
2187
2188
2189
2190
2191
2192
2193
2194
2195
2196
2197
2198
2199
2200
2201
2202
2203
2204
2205
2206
2207
2208
2209
2210
2211
2212
2213
2214
2215
2216
2217
2218
2219
2220
2221
2222
2223
2224
2225
2226
2227
2228
2229
2230
2231
2232
2233
2234
2235
2236
2237
2238
2239
2240
2241
2242
2243
2244
2245
2246
2247
2248
2249
2250
2251
2252
2253
2254
2255
2256
2257
2258
2259
2260
2261
2262
2263
2264
2265
2266
2267
2268
2269
2270
2271
2272
2273
2274
2275
2276
2277
2278
2279
2280
2281
2282
2283
2284
2285
2286
2287
2288
2289
2290
2291
2292
2293
2294
2295
2296
2297
2298
2299
2300
2301
2302
2303
2304
2305
2306
2307
2308
2309
2310
2311
2312
2313
2314
2315
2316
2317
2318
2319
2320
2321
2322
2323
2324
2325
2326
2327
2328
2329
2330
2331
2332
2333
2334
2335
2336
2337
2338
2339
2340
2341
2342
2343
2344
2345
2346
2347
2348
2349
2350
2351
2352
2353
2354
2355
2356
2357
2358
2359
2360
2361
2362
2363
2364
2365
2366
2367
2368
2369
2370
2371
2372
2373
2374
2375
2376
2377
2378
2379
2380
2381
2382
2383
2384
2385
2386
2387
2388
2389
2390
2391
2392
2393
2394
2395
2396
2397
2398
2399
2400
2401
2402
2403
2404
2405
2406
2407
2408
2409
2410
2411
2412
2413
2414
2415
2416
2417
2418
2419
2420
2421
2422
2423
2424
2425
2426
2427
2428
2429
2430
2431
2432
2433
2434
2435
2436
2437
2438
2439
2440
2441
2442
2443
2444
2445
2446
2447
2448
2449
2450
2451
2452
2453
2454
2455
2456
2457
2458
2459
2460
2461
2462
2463
2464
2465
2466
2467
2468
2469
2470
2471
2472
2473
2474
2475
2476
2477
2478
2479
2480
2481
2482
2483
2484
2485
2486
2487
2488
2489
2490
2491
2492
2493
2494
2495
2496
2497
2498
2499
2500
2501
2502
2503
2504
2505
2506
2507
2508
2509
2510
2511
2512
2513
2514
2515
2516
2517
2518
2519
2520
2521
2522
2523
2524
2525
2526
2527
2528
2529
2530
2531
2532
2533
2534
2535
2536
2537
2538
2539
2540
2541
2542
2543
2544
2545
2546
2547
2548
2549
2550
2551
2552
2553
2554
2555
2556
2557
2558
2559
2560
2561
2562
2563
2564
2565
2566
2567
2568
2569
2570
2571
2572
2573
2574
2575
2576
2577
2578
2579
2580
2581
2582
2583
2584
2585
2586
2587
2588
2589
2590
2591
2592
2593
2594
2595
2596
2597
2598
2599
2600
2601
2602
2603
2604
2605
2606
2607
2608
2609
2610
2611
2612
2613
2614
2615
2616
2617
2618
2619
2620
2621
2622
2623
2624
2625
2626
2627
2628
2629
2630
2631
2632
2633
2634
2635
2636
2637
2638
2639
2640
2641
2642
2643
2644
2645
2646
2647
2648
2649
2650
2651
2652
2653
2654
2655
2656
2657
2658
2659
2660
2661
2662
2663
2664
2665
2666
2667
2668
2669
2670
2671
2672
2673
2674
2675
2676
2677
2678
2679
2680
2681
2682
2683
2684
2685
2686
2687
2688
2689
2690
2691
2692
2693
2694
2695
2696
2697
2698
2699
2700
2701
2702
2703
2704
2705
2706
2707
2708
2709
2710
2711
2712
2713
2714
2715
2716
2717
2718
2719
2720
2721
2722
2723
2724
2725
2726
2727
2728
2729
2730
2731
2732
2733
2734
2735
2736
2737
2738
2739
2740
2741
2742
2743
2744
2745
2746
2747
2748
2749
2750
2751
2752
2753
2754
2755
2756
2757
2758
2759
2760
2761
2762
2763
2764
2765
2766
2767
2768
2769
2770
2771
2772
2773
2774
2775
2776
2777
2778
2779
2780
2781
2782
2783
2784
2785
2786
2787
2788
2789
2790
2791
2792
2793
2794
2795
2796
2797
2798
2799
2800
2801
2802
2803
2804
2805
2806
2807
2808
2809
2810
2811
2812
2813
2814
2815
2816
2817
2818
2819
2820
2821
2822
2823
2824
2825
2826
2827
2828
2829
2830
2831
2832
2833
2834
2835
2836
2837
2838
2839
2840
2841
2842
2843
2844
2845
2846
2847
2848
2849
2850
2851
/*
 *	Linux INET6 implementation
 *	FIB front-end.
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	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.
 */

/*	Changes:
 *
 *	YOSHIFUJI Hideaki @USAGI
 *		reworked default router selection.
 *		- respect outgoing interface
 *		- select from (probably) reachable routers (i.e.
 *		routers in REACHABLE, STALE, DELAY or PROBE states).
 *		- always select the same router if it is (probably)
 *		reachable.  otherwise, round-robin the list.
 *	Ville Nuorvala
 *		Fixed routing subtrees.
 */

#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/times.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/route.h>
#include <linux/netdevice.h>
#include <linux/in6.h>
#include <linux/mroute6.h>
#include <linux/init.h>
#include <linux/if_arp.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/nsproxy.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/snmp.h>
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/ndisc.h>
#include <net/addrconf.h>
#include <net/tcp.h>
#include <linux/rtnetlink.h>
#include <net/dst.h>
#include <net/xfrm.h>
#include <net/netevent.h>
#include <net/netlink.h>

#include <asm/uaccess.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

/* Set to 3 to get tracing. */
#define RT6_DEBUG 2

#if RT6_DEBUG >= 3
#define RDBG(x) printk x
#define RT6_TRACE(x...) printk(KERN_DEBUG x)
#else
#define RDBG(x)
#define RT6_TRACE(x...) do { ; } while (0)
#endif

#define CLONE_OFFLINK_ROUTE 0

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort);
static struct dst_entry	*ip6_dst_check(struct dst_entry *dst, u32 cookie);
static unsigned int	 ip6_default_advmss(const struct dst_entry *dst);
static struct dst_entry *ip6_negative_advice(struct dst_entry *);
static void		ip6_dst_destroy(struct dst_entry *);
static void		ip6_dst_ifdown(struct dst_entry *,
				       struct net_device *dev, int how);
static int		 ip6_dst_gc(struct dst_ops *ops);

static int		ip6_pkt_discard(struct sk_buff *skb);
static int		ip6_pkt_discard_out(struct sk_buff *skb);
static void		ip6_link_failure(struct sk_buff *skb);
static void		ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu);

#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_add_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref);
static struct rt6_info *rt6_get_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex);
#endif

static struct dst_ops ip6_dst_ops_template = {
	.family			=	AF_INET6,
	.protocol		=	cpu_to_be16(ETH_P_IPV6),
	.gc			=	ip6_dst_gc,
	.gc_thresh		=	1024,
	.check			=	ip6_dst_check,
	.default_advmss		=	ip6_default_advmss,
	.destroy		=	ip6_dst_destroy,
	.ifdown			=	ip6_dst_ifdown,
	.negative_advice	=	ip6_negative_advice,
	.link_failure		=	ip6_link_failure,
	.update_pmtu		=	ip6_rt_update_pmtu,
	.local_out		=	__ip6_local_out,
};

static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu)
{
}

static struct dst_ops ip6_dst_blackhole_ops = {
	.family			=	AF_INET6,
	.protocol		=	cpu_to_be16(ETH_P_IPV6),
	.destroy		=	ip6_dst_destroy,
	.check			=	ip6_dst_check,
	.update_pmtu		=	ip6_rt_blackhole_update_pmtu,
};

static struct rt6_info ip6_null_entry_template = {
	.dst = {
		.__refcnt	= ATOMIC_INIT(1),
		.__use		= 1,
		.obsolete	= -1,
		.error		= -ENETUNREACH,
		.input		= ip6_pkt_discard,
		.output		= ip6_pkt_discard_out,
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_protocol  = RTPROT_KERNEL,
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

#ifdef CONFIG_IPV6_MULTIPLE_TABLES

static int ip6_pkt_prohibit(struct sk_buff *skb);
static int ip6_pkt_prohibit_out(struct sk_buff *skb);

static struct rt6_info ip6_prohibit_entry_template = {
	.dst = {
		.__refcnt	= ATOMIC_INIT(1),
		.__use		= 1,
		.obsolete	= -1,
		.error		= -EACCES,
		.input		= ip6_pkt_prohibit,
		.output		= ip6_pkt_prohibit_out,
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_protocol  = RTPROT_KERNEL,
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

static struct rt6_info ip6_blk_hole_entry_template = {
	.dst = {
		.__refcnt	= ATOMIC_INIT(1),
		.__use		= 1,
		.obsolete	= -1,
		.error		= -EINVAL,
		.input		= dst_discard,
		.output		= dst_discard,
	},
	.rt6i_flags	= (RTF_REJECT | RTF_NONEXTHOP),
	.rt6i_protocol  = RTPROT_KERNEL,
	.rt6i_metric	= ~(u32) 0,
	.rt6i_ref	= ATOMIC_INIT(1),
};

#endif

/* allocate dst with ip6_dst_ops */
static inline struct rt6_info *ip6_dst_alloc(struct dst_ops *ops)
{
	return (struct rt6_info *)dst_alloc(ops);
}

static void ip6_dst_destroy(struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;
	struct inet_peer *peer = rt->rt6i_peer;

	if (idev != NULL) {
		rt->rt6i_idev = NULL;
		in6_dev_put(idev);
	}
	if (peer) {
		BUG_ON(!(rt->rt6i_flags & RTF_CACHE));
		rt->rt6i_peer = NULL;
		inet_putpeer(peer);
	}
}

void rt6_bind_peer(struct rt6_info *rt, int create)
{
	struct inet_peer *peer;

	if (WARN_ON(!(rt->rt6i_flags & RTF_CACHE)))
		return;

	peer = inet_getpeer_v6(&rt->rt6i_dst.addr, create);
	if (peer && cmpxchg(&rt->rt6i_peer, NULL, peer) != NULL)
		inet_putpeer(peer);
}

static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
			   int how)
{
	struct rt6_info *rt = (struct rt6_info *)dst;
	struct inet6_dev *idev = rt->rt6i_idev;
	struct net_device *loopback_dev =
		dev_net(dev)->loopback_dev;

	if (dev != loopback_dev && idev != NULL && idev->dev == dev) {
		struct inet6_dev *loopback_idev =
			in6_dev_get(loopback_dev);
		if (loopback_idev != NULL) {
			rt->rt6i_idev = loopback_idev;
			in6_dev_put(idev);
		}
	}
}

static __inline__ int rt6_check_expired(const struct rt6_info *rt)
{
	return (rt->rt6i_flags & RTF_EXPIRES) &&
		time_after(jiffies, rt->rt6i_expires);
}

static inline int rt6_need_strict(struct in6_addr *daddr)
{
	return ipv6_addr_type(daddr) &
		(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}

/*
 *	Route lookup. Any table->tb6_lock is implied.
 */

static inline struct rt6_info *rt6_device_match(struct net *net,
						    struct rt6_info *rt,
						    struct in6_addr *saddr,
						    int oif,
						    int flags)
{
	struct rt6_info *local = NULL;
	struct rt6_info *sprt;

	if (!oif && ipv6_addr_any(saddr))
		goto out;

	for (sprt = rt; sprt; sprt = sprt->dst.rt6_next) {
		struct net_device *dev = sprt->rt6i_dev;

		if (oif) {
			if (dev->ifindex == oif)
				return sprt;
			if (dev->flags & IFF_LOOPBACK) {
				if (sprt->rt6i_idev == NULL ||
				    sprt->rt6i_idev->dev->ifindex != oif) {
					if (flags & RT6_LOOKUP_F_IFACE && oif)
						continue;
					if (local && (!oif ||
						      local->rt6i_idev->dev->ifindex == oif))
						continue;
				}
				local = sprt;
			}
		} else {
			if (ipv6_chk_addr(net, saddr, dev,
					  flags & RT6_LOOKUP_F_IFACE))
				return sprt;
		}
	}

	if (oif) {
		if (local)
			return local;

		if (flags & RT6_LOOKUP_F_IFACE)
			return net->ipv6.ip6_null_entry;
	}
out:
	return rt;
}

#ifdef CONFIG_IPV6_ROUTER_PREF
static void rt6_probe(struct rt6_info *rt)
{
	struct neighbour *neigh = rt ? rt->rt6i_nexthop : NULL;
	/*
	 * Okay, this does not seem to be appropriate
	 * for now, however, we need to check if it
	 * is really so; aka Router Reachability Probing.
	 *
	 * Router Reachability Probe MUST be rate-limited
	 * to no more than one per minute.
	 */
	if (!neigh || (neigh->nud_state & NUD_VALID))
		return;
	read_lock_bh(&neigh->lock);
	if (!(neigh->nud_state & NUD_VALID) &&
	    time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
		struct in6_addr mcaddr;
		struct in6_addr *target;

		neigh->updated = jiffies;
		read_unlock_bh(&neigh->lock);

		target = (struct in6_addr *)&neigh->primary_key;
		addrconf_addr_solict_mult(target, &mcaddr);
		ndisc_send_ns(rt->rt6i_dev, NULL, target, &mcaddr, NULL);
	} else
		read_unlock_bh(&neigh->lock);
}
#else
static inline void rt6_probe(struct rt6_info *rt)
{
}
#endif

/*
 * Default Router Selection (RFC 2461 6.3.6)
 */
static inline int rt6_check_dev(struct rt6_info *rt, int oif)
{
	struct net_device *dev = rt->rt6i_dev;
	if (!oif || dev->ifindex == oif)
		return 2;
	if ((dev->flags & IFF_LOOPBACK) &&
	    rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif)
		return 1;
	return 0;
}

static inline int rt6_check_neigh(struct rt6_info *rt)
{
	struct neighbour *neigh = rt->rt6i_nexthop;
	int m;
	if (rt->rt6i_flags & RTF_NONEXTHOP ||
	    !(rt->rt6i_flags & RTF_GATEWAY))
		m = 1;
	else if (neigh) {
		read_lock_bh(&neigh->lock);
		if (neigh->nud_state & NUD_VALID)
			m = 2;
#ifdef CONFIG_IPV6_ROUTER_PREF
		else if (neigh->nud_state & NUD_FAILED)
			m = 0;
#endif
		else
			m = 1;
		read_unlock_bh(&neigh->lock);
	} else
		m = 0;
	return m;
}

static int rt6_score_route(struct rt6_info *rt, int oif,
			   int strict)
{
	int m, n;

	m = rt6_check_dev(rt, oif);
	if (!m && (strict & RT6_LOOKUP_F_IFACE))
		return -1;
#ifdef CONFIG_IPV6_ROUTER_PREF
	m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2;
#endif
	n = rt6_check_neigh(rt);
	if (!n && (strict & RT6_LOOKUP_F_REACHABLE))
		return -1;
	return m;
}

static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict,
				   int *mpri, struct rt6_info *match)
{
	int m;

	if (rt6_check_expired(rt))
		goto out;

	m = rt6_score_route(rt, oif, strict);
	if (m < 0)
		goto out;

	if (m > *mpri) {
		if (strict & RT6_LOOKUP_F_REACHABLE)
			rt6_probe(match);
		*mpri = m;
		match = rt;
	} else if (strict & RT6_LOOKUP_F_REACHABLE) {
		rt6_probe(rt);
	}

out:
	return match;
}

static struct rt6_info *find_rr_leaf(struct fib6_node *fn,
				     struct rt6_info *rr_head,
				     u32 metric, int oif, int strict)
{
	struct rt6_info *rt, *match;
	int mpri = -1;

	match = NULL;
	for (rt = rr_head; rt && rt->rt6i_metric == metric;
	     rt = rt->dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);
	for (rt = fn->leaf; rt && rt != rr_head && rt->rt6i_metric == metric;
	     rt = rt->dst.rt6_next)
		match = find_match(rt, oif, strict, &mpri, match);

	return match;
}

static struct rt6_info *rt6_select(struct fib6_node *fn, int oif, int strict)
{
	struct rt6_info *match, *rt0;
	struct net *net;

	RT6_TRACE("%s(fn->leaf=%p, oif=%d)\n",
		  __func__, fn->leaf, oif);

	rt0 = fn->rr_ptr;
	if (!rt0)
		fn->rr_ptr = rt0 = fn->leaf;

	match = find_rr_leaf(fn, rt0, rt0->rt6i_metric, oif, strict);

	if (!match &&
	    (strict & RT6_LOOKUP_F_REACHABLE)) {
		struct rt6_info *next = rt0->dst.rt6_next;

		/* no entries matched; do round-robin */
		if (!next || next->rt6i_metric != rt0->rt6i_metric)
			next = fn->leaf;

		if (next != rt0)
			fn->rr_ptr = next;
	}

	RT6_TRACE("%s() => %p\n",
		  __func__, match);

	net = dev_net(rt0->rt6i_dev);
	return match ? match : net->ipv6.ip6_null_entry;
}

#ifdef CONFIG_IPV6_ROUTE_INFO
int rt6_route_rcv(struct net_device *dev, u8 *opt, int len,
		  struct in6_addr *gwaddr)
{
	struct net *net = dev_net(dev);
	struct route_info *rinfo = (struct route_info *) opt;
	struct in6_addr prefix_buf, *prefix;
	unsigned int pref;
	unsigned long lifetime;
	struct rt6_info *rt;

	if (len < sizeof(struct route_info)) {
		return -EINVAL;
	}

	/* Sanity check for prefix_len and length */
	if (rinfo->length > 3) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 128) {
		return -EINVAL;
	} else if (rinfo->prefix_len > 64) {
		if (rinfo->length < 2) {
			return -EINVAL;
		}
	} else if (rinfo->prefix_len > 0) {
		if (rinfo->length < 1) {
			return -EINVAL;
		}
	}

	pref = rinfo->route_pref;
	if (pref == ICMPV6_ROUTER_PREF_INVALID)
		return -EINVAL;

	lifetime = addrconf_timeout_fixup(ntohl(rinfo->lifetime), HZ);

	if (rinfo->length == 3)
		prefix = (struct in6_addr *)rinfo->prefix;
	else {
		/* this function is safe */
		ipv6_addr_prefix(&prefix_buf,
				 (struct in6_addr *)rinfo->prefix,
				 rinfo->prefix_len);
		prefix = &prefix_buf;
	}

	rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr,
				dev->ifindex);

	if (rt && !lifetime) {
		ip6_del_rt(rt);
		rt = NULL;
	}

	if (!rt && lifetime)
		rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev->ifindex,
					pref);
	else if (rt)
		rt->rt6i_flags = RTF_ROUTEINFO |
				 (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);

	if (rt) {
		if (!addrconf_finite_timeout(lifetime)) {
			rt->rt6i_flags &= ~RTF_EXPIRES;
		} else {
			rt->rt6i_expires = jiffies + HZ * lifetime;
			rt->rt6i_flags |= RTF_EXPIRES;
		}
		dst_release(&rt->dst);
	}
	return 0;
}
#endif

#define BACKTRACK(__net, saddr)			\
do { \
	if (rt == __net->ipv6.ip6_null_entry) {	\
		struct fib6_node *pn; \
		while (1) { \
			if (fn->fn_flags & RTN_TL_ROOT) \
				goto out; \
			pn = fn->parent; \
			if (FIB6_SUBTREE(pn) && FIB6_SUBTREE(pn) != fn) \
				fn = fib6_lookup(FIB6_SUBTREE(pn), NULL, saddr); \
			else \
				fn = pn; \
			if (fn->fn_flags & RTN_RTINFO) \
				goto restart; \
		} \
	} \
} while(0)

static struct rt6_info *ip6_pol_route_lookup(struct net *net,
					     struct fib6_table *table,
					     struct flowi *fl, int flags)
{
	struct fib6_node *fn;
	struct rt6_info *rt;

	read_lock_bh(&table->tb6_lock);
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
	rt = fn->leaf;
	rt = rt6_device_match(net, rt, &fl->fl6_src, fl->oif, flags);
	BACKTRACK(net, &fl->fl6_src);
out:
	dst_use(&rt->dst, jiffies);
	read_unlock_bh(&table->tb6_lock);
	return rt;

}

struct rt6_info *rt6_lookup(struct net *net, const struct in6_addr *daddr,
			    const struct in6_addr *saddr, int oif, int strict)
{
	struct flowi fl = {
		.oif = oif,
		.fl6_dst = *daddr,
	};
	struct dst_entry *dst;
	int flags = strict ? RT6_LOOKUP_F_IFACE : 0;

	if (saddr) {
		memcpy(&fl.fl6_src, saddr, sizeof(*saddr));
		flags |= RT6_LOOKUP_F_HAS_SADDR;
	}

	dst = fib6_rule_lookup(net, &fl, flags, ip6_pol_route_lookup);
	if (dst->error == 0)
		return (struct rt6_info *) dst;

	dst_release(dst);

	return NULL;
}

EXPORT_SYMBOL(rt6_lookup);

/* ip6_ins_rt is called with FREE table->tb6_lock.
   It takes new route entry, the addition fails by any reason the
   route is freed. In any case, if caller does not hold it, it may
   be destroyed.
 */

static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info)
{
	int err;
	struct fib6_table *table;

	table = rt->rt6i_table;
	write_lock_bh(&table->tb6_lock);
	err = fib6_add(&table->tb6_root, rt, info);
	write_unlock_bh(&table->tb6_lock);

	return err;
}

int ip6_ins_rt(struct rt6_info *rt)
{
	struct nl_info info = {
		.nl_net = dev_net(rt->rt6i_dev),
	};
	return __ip6_ins_rt(rt, &info);
}

static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort, struct in6_addr *daddr,
				      struct in6_addr *saddr)
{
	struct rt6_info *rt;

	/*
	 *	Clone the route.
	 */

	rt = ip6_rt_copy(ort);

	if (rt) {
		struct neighbour *neigh;
		int attempts = !in_softirq();

		if (!(rt->rt6i_flags&RTF_GATEWAY)) {
			if (rt->rt6i_dst.plen != 128 &&
			    ipv6_addr_equal(&rt->rt6i_dst.addr, daddr))
				rt->rt6i_flags |= RTF_ANYCAST;
			ipv6_addr_copy(&rt->rt6i_gateway, daddr);
		}

		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		rt->dst.flags |= DST_HOST;

#ifdef CONFIG_IPV6_SUBTREES
		if (rt->rt6i_src.plen && saddr) {
			ipv6_addr_copy(&rt->rt6i_src.addr, saddr);
			rt->rt6i_src.plen = 128;
		}
#endif

	retry:
		neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
		if (IS_ERR(neigh)) {
			struct net *net = dev_net(rt->rt6i_dev);
			int saved_rt_min_interval =
				net->ipv6.sysctl.ip6_rt_gc_min_interval;
			int saved_rt_elasticity =
				net->ipv6.sysctl.ip6_rt_gc_elasticity;

			if (attempts-- > 0) {
				net->ipv6.sysctl.ip6_rt_gc_elasticity = 1;
				net->ipv6.sysctl.ip6_rt_gc_min_interval = 0;

				ip6_dst_gc(&net->ipv6.ip6_dst_ops);

				net->ipv6.sysctl.ip6_rt_gc_elasticity =
					saved_rt_elasticity;
				net->ipv6.sysctl.ip6_rt_gc_min_interval =
					saved_rt_min_interval;
				goto retry;
			}

			if (net_ratelimit())
				printk(KERN_WARNING
				       "ipv6: Neighbour table overflow.\n");
			dst_free(&rt->dst);
			return NULL;
		}
		rt->rt6i_nexthop = neigh;

	}

	return rt;
}

static struct rt6_info *rt6_alloc_clone(struct rt6_info *ort, struct in6_addr *daddr)
{
	struct rt6_info *rt = ip6_rt_copy(ort);
	if (rt) {
		ipv6_addr_copy(&rt->rt6i_dst.addr, daddr);
		rt->rt6i_dst.plen = 128;
		rt->rt6i_flags |= RTF_CACHE;
		rt->dst.flags |= DST_HOST;
		rt->rt6i_nexthop = neigh_clone(ort->rt6i_nexthop);
	}
	return rt;
}

static struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, int oif,
				      struct flowi *fl, int flags)
{
	struct fib6_node *fn;
	struct rt6_info *rt, *nrt;
	int strict = 0;
	int attempts = 3;
	int err;
	int reachable = net->ipv6.devconf_all->forwarding ? 0 : RT6_LOOKUP_F_REACHABLE;

	strict |= flags & RT6_LOOKUP_F_IFACE;

relookup:
	read_lock_bh(&table->tb6_lock);

restart_2:
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);

restart:
	rt = rt6_select(fn, oif, strict | reachable);

	BACKTRACK(net, &fl->fl6_src);
	if (rt == net->ipv6.ip6_null_entry ||
	    rt->rt6i_flags & RTF_CACHE)
		goto out;

	dst_hold(&rt->dst);
	read_unlock_bh(&table->tb6_lock);

	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, &fl->fl6_dst, &fl->fl6_src);
	else {
#if CLONE_OFFLINK_ROUTE
		nrt = rt6_alloc_clone(rt, &fl->fl6_dst);
#else
		goto out2;
#endif
	}

	dst_release(&rt->dst);
	rt = nrt ? : net->ipv6.ip6_null_entry;

	dst_hold(&rt->dst);
	if (nrt) {
		err = ip6_ins_rt(nrt);
		if (!err)
			goto out2;
	}

	if (--attempts <= 0)
		goto out2;

	/*
	 * Race condition! In the gap, when table->tb6_lock was
	 * released someone could insert this route.  Relookup.
	 */
	dst_release(&rt->dst);
	goto relookup;

out:
	if (reachable) {
		reachable = 0;
		goto restart_2;
	}
	dst_hold(&rt->dst);
	read_unlock_bh(&table->tb6_lock);
out2:
	rt->dst.lastuse = jiffies;
	rt->dst.__use++;

	return rt;
}

static struct rt6_info *ip6_pol_route_input(struct net *net, struct fib6_table *table,
					    struct flowi *fl, int flags)
{
	return ip6_pol_route(net, table, fl->iif, fl, flags);
}

void ip6_route_input(struct sk_buff *skb)
{
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct net *net = dev_net(skb->dev);
	int flags = RT6_LOOKUP_F_HAS_SADDR;
	struct flowi fl = {
		.iif = skb->dev->ifindex,
		.fl6_dst = iph->daddr,
		.fl6_src = iph->saddr,
		.fl6_flowlabel = (* (__be32 *) iph)&IPV6_FLOWINFO_MASK,
		.mark = skb->mark,
		.proto = iph->nexthdr,
	};

	if (rt6_need_strict(&iph->daddr) && skb->dev->type != ARPHRD_PIMREG)
		flags |= RT6_LOOKUP_F_IFACE;

	skb_dst_set(skb, fib6_rule_lookup(net, &fl, flags, ip6_pol_route_input));
}

static struct rt6_info *ip6_pol_route_output(struct net *net, struct fib6_table *table,
					     struct flowi *fl, int flags)
{
	return ip6_pol_route(net, table, fl->oif, fl, flags);
}

struct dst_entry * ip6_route_output(struct net *net, struct sock *sk,
				    struct flowi *fl)
{
	int flags = 0;

	if ((sk && sk->sk_bound_dev_if) || rt6_need_strict(&fl->fl6_dst))
		flags |= RT6_LOOKUP_F_IFACE;

	if (!ipv6_addr_any(&fl->fl6_src))
		flags |= RT6_LOOKUP_F_HAS_SADDR;
	else if (sk)
		flags |= rt6_srcprefs2flags(inet6_sk(sk)->srcprefs);

	return fib6_rule_lookup(net, fl, flags, ip6_pol_route_output);
}

EXPORT_SYMBOL(ip6_route_output);

int ip6_dst_blackhole(struct sock *sk, struct dst_entry **dstp, struct flowi *fl)
{
	struct rt6_info *ort = (struct rt6_info *) *dstp;
	struct rt6_info *rt = (struct rt6_info *)
		dst_alloc(&ip6_dst_blackhole_ops);
	struct dst_entry *new = NULL;

	if (rt) {
		new = &rt->dst;

		atomic_set(&new->__refcnt, 1);
		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->rt6i_idev = ort->rt6i_idev;
		if (rt->rt6i_idev)
			in6_dev_hold(rt->rt6i_idev);
		rt->rt6i_expires = 0;

		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
		rt->rt6i_metric = 0;

		memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
		memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif

		dst_free(new);
	}

	dst_release(*dstp);
	*dstp = new;
	return new ? 0 : -ENOMEM;
}
EXPORT_SYMBOL_GPL(ip6_dst_blackhole);

/*
 *	Destination cache support functions
 */

static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
{
	struct rt6_info *rt;

	rt = (struct rt6_info *) dst;

	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))
		return dst;

	return NULL;
}

static struct dst_entry *ip6_negative_advice(struct dst_entry *dst)
{
	struct rt6_info *rt = (struct rt6_info *) dst;

	if (rt) {
		if (rt->rt6i_flags & RTF_CACHE) {
			if (rt6_check_expired(rt)) {
				ip6_del_rt(rt);
				dst = NULL;
			}
		} else {
			dst_release(dst);
			dst = NULL;
		}
	}
	return dst;
}

static void ip6_link_failure(struct sk_buff *skb)
{
	struct rt6_info *rt;

	icmpv6_send(skb, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH, 0);

	rt = (struct rt6_info *) skb_dst(skb);
	if (rt) {
		if (rt->rt6i_flags&RTF_CACHE) {
			dst_set_expires(&rt->dst, 0);
			rt->rt6i_flags |= RTF_EXPIRES;
		} else if (rt->rt6i_node && (rt->rt6i_flags & RTF_DEFAULT))
			rt->rt6i_node->fn_sernum = -1;
	}
}

static void ip6_rt_update_pmtu(struct dst_entry *dst, u32 mtu)
{
	struct rt6_info *rt6 = (struct rt6_info*)dst;

	if (mtu < dst_mtu(dst) && rt6->rt6i_dst.plen == 128) {
		rt6->rt6i_flags |= RTF_MODIFIED;
		if (mtu < IPV6_MIN_MTU) {
			u32 features = dst_metric(dst, RTAX_FEATURES);
			mtu = IPV6_MIN_MTU;
			features |= RTAX_FEATURE_ALLFRAG;
			dst_metric_set(dst, RTAX_FEATURES, features);
		}
		dst_metric_set(dst, RTAX_MTU, mtu);
		call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst);
	}
}

static int ipv6_get_mtu(struct net_device *dev);

static unsigned int ip6_default_advmss(const struct dst_entry *dst)
{
	struct net_device *dev = dst->dev;
	unsigned int mtu = dst_mtu(dst);
	struct net *net = dev_net(dev);

	mtu -= sizeof(struct ipv6hdr) + sizeof(struct tcphdr);

	if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
		mtu = net->ipv6.sysctl.ip6_rt_min_advmss;

	/*
	 * Maximal non-jumbo IPv6 payload is IPV6_MAXPLEN and
	 * corresponding MSS is IPV6_MAXPLEN - tcp_header_size.
	 * IPV6_MAXPLEN is also valid and means: "any MSS,
	 * rely only on pmtu discovery"
	 */
	if (mtu > IPV6_MAXPLEN - sizeof(struct tcphdr))
		mtu = IPV6_MAXPLEN;
	return mtu;
}

static struct dst_entry *icmp6_dst_gc_list;
static DEFINE_SPINLOCK(icmp6_dst_lock);

struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
				  struct neighbour *neigh,
				  const struct in6_addr *addr)
{
	struct rt6_info *rt;
	struct inet6_dev *idev = in6_dev_get(dev);
	struct net *net = dev_net(dev);

	if (unlikely(idev == NULL))
		return NULL;

	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
	if (unlikely(rt == NULL)) {
		in6_dev_put(idev);
		goto out;
	}

	dev_hold(dev);
	if (neigh)
		neigh_hold(neigh);
	else {
		neigh = ndisc_get_neigh(dev, addr);
		if (IS_ERR(neigh))
			neigh = NULL;
	}

	rt->rt6i_dev	  = dev;
	rt->rt6i_idev     = idev;
	rt->rt6i_nexthop  = neigh;
	atomic_set(&rt->dst.__refcnt, 1);
	dst_metric_set(&rt->dst, RTAX_HOPLIMIT, 255);
	dst_metric_set(&rt->dst, RTAX_MTU, ipv6_get_mtu(rt->rt6i_dev));
	rt->dst.output  = ip6_output;

#if 0	/* there's no chance to use these for ndisc */
	rt->dst.flags   = ipv6_addr_type(addr) & IPV6_ADDR_UNICAST
				? DST_HOST
				: 0;
	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;
#endif

	spin_lock_bh(&icmp6_dst_lock);
	rt->dst.next = icmp6_dst_gc_list;
	icmp6_dst_gc_list = &rt->dst;
	spin_unlock_bh(&icmp6_dst_lock);

	fib6_force_start_gc(net);

out:
	return &rt->dst;
}

int icmp6_dst_gc(void)
{
	struct dst_entry *dst, *next, **pprev;
	int more = 0;

	next = NULL;

	spin_lock_bh(&icmp6_dst_lock);
	pprev = &icmp6_dst_gc_list;

	while ((dst = *pprev) != NULL) {
		if (!atomic_read(&dst->__refcnt)) {
			*pprev = dst->next;
			dst_free(dst);
		} else {
			pprev = &dst->next;
			++more;
		}
	}

	spin_unlock_bh(&icmp6_dst_lock);

	return more;
}

static void icmp6_clean_all(int (*func)(struct rt6_info *rt, void *arg),
			    void *arg)
{
	struct dst_entry *dst, **pprev;

	spin_lock_bh(&icmp6_dst_lock);
	pprev = &icmp6_dst_gc_list;
	while ((dst = *pprev) != NULL) {
		struct rt6_info *rt = (struct rt6_info *) dst;
		if (func(rt, arg)) {
			*pprev = dst->next;
			dst_free(dst);
		} else {
			pprev = &dst->next;
		}
	}
	spin_unlock_bh(&icmp6_dst_lock);
}

static int ip6_dst_gc(struct dst_ops *ops)
{
	unsigned long now = jiffies;
	struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops);
	int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval;
	int rt_max_size = net->ipv6.sysctl.ip6_rt_max_size;
	int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
	int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
	unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
	int entries;

	entries = dst_entries_get_fast(ops);
	if (time_after(rt_last_gc + rt_min_interval, now) &&
	    entries <= rt_max_size)
		goto out;

	net->ipv6.ip6_rt_gc_expire++;
	fib6_run_gc(net->ipv6.ip6_rt_gc_expire, net);
	net->ipv6.ip6_rt_last_gc = now;
	entries = dst_entries_get_slow(ops);
	if (entries < ops->gc_thresh)
		net->ipv6.ip6_rt_gc_expire = rt_gc_timeout>>1;
out:
	net->ipv6.ip6_rt_gc_expire -= net->ipv6.ip6_rt_gc_expire>>rt_elasticity;
	return entries > rt_max_size;
}

/* Clean host part of a prefix. Not necessary in radix tree,
   but results in cleaner routing tables.

   Remove it only when all the things will work!
 */

static int ipv6_get_mtu(struct net_device *dev)
{
	int mtu = IPV6_MIN_MTU;
	struct inet6_dev *idev;

	rcu_read_lock();
	idev = __in6_dev_get(dev);
	if (idev)
		mtu = idev->cnf.mtu6;
	rcu_read_unlock();
	return mtu;
}

int ip6_dst_hoplimit(struct dst_entry *dst)
{
	int hoplimit = dst_metric_raw(dst, RTAX_HOPLIMIT);
	if (hoplimit == 0) {
		struct net_device *dev = dst->dev;
		struct inet6_dev *idev;

		rcu_read_lock();
		idev = __in6_dev_get(dev);
		if (idev)
			hoplimit = idev->cnf.hop_limit;
		else
			hoplimit = dev_net(dev)->ipv6.devconf_all->hop_limit;
		rcu_read_unlock();
	}
	return hoplimit;
}
EXPORT_SYMBOL(ip6_dst_hoplimit);

/*
 *
 */

int ip6_route_add(struct fib6_config *cfg)
{
	int err;
	struct net *net = cfg->fc_nlinfo.nl_net;
	struct rt6_info *rt = NULL;
	struct net_device *dev = NULL;
	struct inet6_dev *idev = NULL;
	struct fib6_table *table;
	int addr_type;

	if (cfg->fc_dst_len > 128 || cfg->fc_src_len > 128)
		return -EINVAL;
#ifndef CONFIG_IPV6_SUBTREES
	if (cfg->fc_src_len)
		return -EINVAL;
#endif
	if (cfg->fc_ifindex) {
		err = -ENODEV;
		dev = dev_get_by_index(net, cfg->fc_ifindex);
		if (!dev)
			goto out;
		idev = in6_dev_get(dev);
		if (!idev)
			goto out;
	}

	if (cfg->fc_metric == 0)
		cfg->fc_metric = IP6_RT_PRIO_USER;

	table = fib6_new_table(net, cfg->fc_table);
	if (table == NULL) {
		err = -ENOBUFS;
		goto out;
	}

	rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);

	if (rt == NULL) {
		err = -ENOMEM;
		goto out;
	}

	rt->dst.obsolete = -1;
	rt->rt6i_expires = (cfg->fc_flags & RTF_EXPIRES) ?
				jiffies + clock_t_to_jiffies(cfg->fc_expires) :
				0;

	if (cfg->fc_protocol == RTPROT_UNSPEC)
		cfg->fc_protocol = RTPROT_BOOT;
	rt->rt6i_protocol = cfg->fc_protocol;

	addr_type = ipv6_addr_type(&cfg->fc_dst);

	if (addr_type & IPV6_ADDR_MULTICAST)
		rt->dst.input = ip6_mc_input;
	else if (cfg->fc_flags & RTF_LOCAL)
		rt->dst.input = ip6_input;
	else
		rt->dst.input = ip6_forward;

	rt->dst.output = ip6_output;

	ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len);
	rt->rt6i_dst.plen = cfg->fc_dst_len;
	if (rt->rt6i_dst.plen == 128)
	       rt->dst.flags = DST_HOST;

#ifdef CONFIG_IPV6_SUBTREES
	ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len);
	rt->rt6i_src.plen = cfg->fc_src_len;
#endif

	rt->rt6i_metric = cfg->fc_metric;

	/* We cannot add true routes via loopback here,
	   they would result in kernel looping; promote them to reject routes
	 */
	if ((cfg->fc_flags & RTF_REJECT) ||
	    (dev && (dev->flags&IFF_LOOPBACK) && !(addr_type&IPV6_ADDR_LOOPBACK)
					      && !(cfg->fc_flags&RTF_LOCAL))) {
		/* hold loopback dev/idev if we haven't done so. */
		if (dev != net->loopback_dev) {
			if (dev) {
				dev_put(dev);
				in6_dev_put(idev);
			}
			dev = net->loopback_dev;
			dev_hold(dev);
			idev = in6_dev_get(dev);
			if (!idev) {
				err = -ENODEV;
				goto out;
			}
		}
		rt->dst.output = ip6_pkt_discard_out;
		rt->dst.input = ip6_pkt_discard;
		rt->dst.error = -ENETUNREACH;
		rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP;
		goto install_route;
	}

	if (cfg->fc_flags & RTF_GATEWAY) {
		struct in6_addr *gw_addr;
		int gwa_type;

		gw_addr = &cfg->fc_gateway;
		ipv6_addr_copy(&rt->rt6i_gateway, gw_addr);
		gwa_type = ipv6_addr_type(gw_addr);

		if (gwa_type != (IPV6_ADDR_LINKLOCAL|IPV6_ADDR_UNICAST)) {
			struct rt6_info *grt;

			/* IPv6 strictly inhibits using not link-local
			   addresses as nexthop address.
			   Otherwise, router will not able to send redirects.
			   It is very good, but in some (rare!) circumstances
			   (SIT, PtP, NBMA NOARP links) it is handy to allow
			   some exceptions. --ANK
			 */
			err = -EINVAL;
			if (!(gwa_type&IPV6_ADDR_UNICAST))
				goto out;

			grt = rt6_lookup(net, gw_addr, NULL, cfg->fc_ifindex, 1);

			err = -EHOSTUNREACH;
			if (grt == NULL)
				goto out;
			if (dev) {
				if (dev != grt->rt6i_dev) {
					dst_release(&grt->dst);
					goto out;
				}
			} else {
				dev = grt->rt6i_dev;
				idev = grt->rt6i_idev;
				dev_hold(dev);
				in6_dev_hold(grt->rt6i_idev);
			}
			if (!(grt->rt6i_flags&RTF_GATEWAY))
				err = 0;
			dst_release(&grt->dst);

			if (err)
				goto out;
		}
		err = -EINVAL;
		if (dev == NULL || (dev->flags&IFF_LOOPBACK))
			goto out;
	}

	err = -ENODEV;
	if (dev == NULL)
		goto out;

	if (cfg->fc_flags & (RTF_GATEWAY | RTF_NONEXTHOP)) {
		rt->rt6i_nexthop = __neigh_lookup_errno(&nd_tbl, &rt->rt6i_gateway, dev);
		if (IS_ERR(rt->rt6i_nexthop)) {
			err = PTR_ERR(rt->rt6i_nexthop);
			rt->rt6i_nexthop = NULL;
			goto out;
		}
	}

	rt->rt6i_flags = cfg->fc_flags;

install_route:
	if (cfg->fc_mx) {
		struct nlattr *nla;
		int remaining;

		nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
			int type = nla_type(nla);

			if (type) {
				if (type > RTAX_MAX) {
					err = -EINVAL;
					goto out;
				}

				dst_metric_set(&rt->dst, type, nla_get_u32(nla));
			}
		}
	}

	if (!dst_mtu(&rt->dst))
		dst_metric_set(&rt->dst, RTAX_MTU, ipv6_get_mtu(dev));
	rt->dst.dev = dev;
	rt->rt6i_idev = idev;
	rt->rt6i_table = table;

	cfg->fc_nlinfo.nl_net = dev_net(dev);

	return __ip6_ins_rt(rt, &cfg->fc_nlinfo);

out:
	if (dev)
		dev_put(dev);
	if (idev)
		in6_dev_put(idev);
	if (rt)
		dst_free(&rt->dst);
	return err;
}

static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info)
{
	int err;
	struct fib6_table *table;
	struct net *net = dev_net(rt->rt6i_dev);

	if (rt == net->ipv6.ip6_null_entry)
		return -ENOENT;

	table = rt->rt6i_table;
	write_lock_bh(&table->tb6_lock);

	err = fib6_del(rt, info);
	dst_release(&rt->dst);

	write_unlock_bh(&table->tb6_lock);

	return err;
}

int ip6_del_rt(struct rt6_info *rt)
{
	struct nl_info info = {
		.nl_net = dev_net(rt->rt6i_dev),
	};
	return __ip6_del_rt(rt, &info);
}

static int ip6_route_del(struct fib6_config *cfg)
{
	struct fib6_table *table;
	struct fib6_node *fn;
	struct rt6_info *rt;
	int err = -ESRCH;

	table = fib6_get_table(cfg->fc_nlinfo.nl_net, cfg->fc_table);
	if (table == NULL)
		return err;

	read_lock_bh(&table->tb6_lock);

	fn = fib6_locate(&table->tb6_root,
			 &cfg->fc_dst, cfg->fc_dst_len,
			 &cfg->fc_src, cfg->fc_src_len);

	if (fn) {
		for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
			if (cfg->fc_ifindex &&
			    (rt->rt6i_dev == NULL ||
			     rt->rt6i_dev->ifindex != cfg->fc_ifindex))
				continue;
			if (cfg->fc_flags & RTF_GATEWAY &&
			    !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway))
				continue;
			if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric)
				continue;
			dst_hold(&rt->dst);
			read_unlock_bh(&table->tb6_lock);

			return __ip6_del_rt(rt, &cfg->fc_nlinfo);
		}
	}
	read_unlock_bh(&table->tb6_lock);

	return err;
}

/*
 *	Handle redirects
 */
struct ip6rd_flowi {
	struct flowi fl;
	struct in6_addr gateway;
};

static struct rt6_info *__ip6_route_redirect(struct net *net,
					     struct fib6_table *table,
					     struct flowi *fl,
					     int flags)
{
	struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl;
	struct rt6_info *rt;
	struct fib6_node *fn;

	/*
	 * Get the "current" route for this destination and
	 * check if the redirect has come from approriate router.
	 *
	 * RFC 2461 specifies that redirects should only be
	 * accepted if they come from the nexthop to the target.
	 * Due to the way the routes are chosen, this notion
	 * is a bit fuzzy and one might need to check all possible
	 * routes.
	 */

	read_lock_bh(&table->tb6_lock);
	fn = fib6_lookup(&table->tb6_root, &fl->fl6_dst, &fl->fl6_src);
restart:
	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
		/*
		 * Current route is on-link; redirect is always invalid.
		 *
		 * Seems, previous statement is not true. It could
		 * be node, which looks for us as on-link (f.e. proxy ndisc)
		 * But then router serving it might decide, that we should
		 * know truth 8)8) --ANK (980726).
		 */
		if (rt6_check_expired(rt))
			continue;
		if (!(rt->rt6i_flags & RTF_GATEWAY))
			continue;
		if (fl->oif != rt->rt6i_dev->ifindex)
			continue;
		if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway))
			continue;
		break;
	}

	if (!rt)
		rt = net->ipv6.ip6_null_entry;
	BACKTRACK(net, &fl->fl6_src);
out:
	dst_hold(&rt->dst);

	read_unlock_bh(&table->tb6_lock);

	return rt;
};

static struct rt6_info *ip6_route_redirect(struct in6_addr *dest,
					   struct in6_addr *src,
					   struct in6_addr *gateway,
					   struct net_device *dev)
{
	int flags = RT6_LOOKUP_F_HAS_SADDR;
	struct net *net = dev_net(dev);
	struct ip6rd_flowi rdfl = {
		.fl = {
			.oif = dev->ifindex,
			.fl6_dst = *dest,
			.fl6_src = *src,
		},
	};

	ipv6_addr_copy(&rdfl.gateway, gateway);

	if (rt6_need_strict(dest))
		flags |= RT6_LOOKUP_F_IFACE;

	return (struct rt6_info *)fib6_rule_lookup(net, (struct flowi *)&rdfl,
						   flags, __ip6_route_redirect);
}

void rt6_redirect(struct in6_addr *dest, struct in6_addr *src,
		  struct in6_addr *saddr,
		  struct neighbour *neigh, u8 *lladdr, int on_link)
{
	struct rt6_info *rt, *nrt = NULL;
	struct netevent_redirect netevent;
	struct net *net = dev_net(neigh->dev);

	rt = ip6_route_redirect(dest, src, saddr, neigh->dev);

	if (rt == net->ipv6.ip6_null_entry) {
		if (net_ratelimit())
			printk(KERN_DEBUG "rt6_redirect: source isn't a valid nexthop "
			       "for redirect target\n");
		goto out;
	}

	/*
	 *	We have finally decided to accept it.
	 */

	neigh_update(neigh, lladdr, NUD_STALE,
		     NEIGH_UPDATE_F_WEAK_OVERRIDE|
		     NEIGH_UPDATE_F_OVERRIDE|
		     (on_link ? 0 : (NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
				     NEIGH_UPDATE_F_ISROUTER))
		     );

	/*
	 * Redirect received -> path was valid.
	 * Look, redirects are sent only in response to data packets,
	 * so that this nexthop apparently is reachable. --ANK
	 */
	dst_confirm(&rt->dst);

	/* Duplicate redirect: silently ignore. */
	if (neigh == rt->dst.neighbour)
		goto out;

	nrt = ip6_rt_copy(rt);
	if (nrt == NULL)
		goto out;

	nrt->rt6i_flags = RTF_GATEWAY|RTF_UP|RTF_DYNAMIC|RTF_CACHE;
	if (on_link)
		nrt->rt6i_flags &= ~RTF_GATEWAY;

	ipv6_addr_copy(&nrt->rt6i_dst.addr, dest);
	nrt->rt6i_dst.plen = 128;
	nrt->dst.flags |= DST_HOST;

	ipv6_addr_copy(&nrt->rt6i_gateway, (struct in6_addr*)neigh->primary_key);
	nrt->rt6i_nexthop = neigh_clone(neigh);
	/* Reset pmtu, it may be better */
	dst_metric_set(&nrt->dst, RTAX_MTU, ipv6_get_mtu(neigh->dev));

	if (ip6_ins_rt(nrt))
		goto out;

	netevent.old = &rt->dst;
	netevent.new = &nrt->dst;
	call_netevent_notifiers(NETEVENT_REDIRECT, &netevent);

	if (rt->rt6i_flags&RTF_CACHE) {
		ip6_del_rt(rt);
		return;
	}

out:
	dst_release(&rt->dst);
}

/*
 *	Handle ICMP "packet too big" messages
 *	i.e. Path MTU discovery
 */

static void rt6_do_pmtu_disc(struct in6_addr *daddr, struct in6_addr *saddr,
			     struct net *net, u32 pmtu, int ifindex)
{
	struct rt6_info *rt, *nrt;
	int allfrag = 0;

	rt = rt6_lookup(net, daddr, saddr, ifindex, 0);
	if (rt == NULL)
		return;

	if (pmtu >= dst_mtu(&rt->dst))
		goto out;

	if (pmtu < IPV6_MIN_MTU) {
		/*
		 * According to RFC2460, PMTU is set to the IPv6 Minimum Link
		 * MTU (1280) and a fragment header should always be included
		 * after a node receiving Too Big message reporting PMTU is
		 * less than the IPv6 Minimum Link MTU.
		 */
		pmtu = IPV6_MIN_MTU;
		allfrag = 1;
	}

	/* New mtu received -> path was valid.
	   They are sent only in response to data packets,
	   so that this nexthop apparently is reachable. --ANK
	 */
	dst_confirm(&rt->dst);

	/* Host route. If it is static, it would be better
	   not to override it, but add new one, so that
	   when cache entry will expire old pmtu
	   would return automatically.
	 */
	if (rt->rt6i_flags & RTF_CACHE) {
		dst_metric_set(&rt->dst, RTAX_MTU, pmtu);
		if (allfrag) {
			u32 features = dst_metric(&rt->dst, RTAX_FEATURES);
			features |= RTAX_FEATURE_ALLFRAG;
			dst_metric_set(&rt->dst, RTAX_FEATURES, features);
		}
		dst_set_expires(&rt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
		rt->rt6i_flags |= RTF_MODIFIED|RTF_EXPIRES;
		goto out;
	}

	/* Network route.
	   Two cases are possible:
	   1. It is connected route. Action: COW
	   2. It is gatewayed route or NONEXTHOP route. Action: clone it.
	 */
	if (!rt->rt6i_nexthop && !(rt->rt6i_flags & RTF_NONEXTHOP))
		nrt = rt6_alloc_cow(rt, daddr, saddr);
	else
		nrt = rt6_alloc_clone(rt, daddr);

	if (nrt) {
		dst_metric_set(&nrt->dst, RTAX_MTU, pmtu);
		if (allfrag) {
			u32 features = dst_metric(&nrt->dst, RTAX_FEATURES);
			features |= RTAX_FEATURE_ALLFRAG;
			dst_metric_set(&nrt->dst, RTAX_FEATURES, features);
		}

		/* According to RFC 1981, detecting PMTU increase shouldn't be
		 * happened within 5 mins, the recommended timer is 10 mins.
		 * Here this route expiration time is set to ip6_rt_mtu_expires
		 * which is 10 mins. After 10 mins the decreased pmtu is expired
		 * and detecting PMTU increase will be automatically happened.
		 */
		dst_set_expires(&nrt->dst, net->ipv6.sysctl.ip6_rt_mtu_expires);
		nrt->rt6i_flags |= RTF_DYNAMIC|RTF_EXPIRES;

		ip6_ins_rt(nrt);
	}
out:
	dst_release(&rt->dst);
}

void rt6_pmtu_discovery(struct in6_addr *daddr, struct in6_addr *saddr,
			struct net_device *dev, u32 pmtu)
{
	struct net *net = dev_net(dev);

	/*
	 * RFC 1981 states that a node "MUST reduce the size of the packets it
	 * is sending along the path" that caused the Packet Too Big message.
	 * Since it's not possible in the general case to determine which
	 * interface was used to send the original packet, we update the MTU
	 * on the interface that will be used to send future packets. We also
	 * update the MTU on the interface that received the Packet Too Big in
	 * case the original packet was forced out that interface with
	 * SO_BINDTODEVICE or similar. This is the next best thing to the
	 * correct behaviour, which would be to update the MTU on all
	 * interfaces.
	 */
	rt6_do_pmtu_disc(daddr, saddr, net, pmtu, 0);
	rt6_do_pmtu_disc(daddr, saddr, net, pmtu, dev->ifindex);
}

/*
 *	Misc support functions
 */

static struct rt6_info * ip6_rt_copy(struct rt6_info *ort)
{
	struct net *net = dev_net(ort->rt6i_dev);
	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);

	if (rt) {
		rt->dst.input = ort->dst.input;
		rt->dst.output = ort->dst.output;

		dst_copy_metrics(&rt->dst, &ort->dst);
		rt->dst.error = ort->dst.error;
		rt->dst.dev = ort->dst.dev;
		if (rt->dst.dev)
			dev_hold(rt->dst.dev);
		rt->rt6i_idev = ort->rt6i_idev;
		if (rt->rt6i_idev)
			in6_dev_hold(rt->rt6i_idev);
		rt->dst.lastuse = jiffies;
		rt->rt6i_expires = 0;

		ipv6_addr_copy(&rt->rt6i_gateway, &ort->rt6i_gateway);
		rt->rt6i_flags = ort->rt6i_flags & ~RTF_EXPIRES;
		rt->rt6i_metric = 0;

		memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key));
#ifdef CONFIG_IPV6_SUBTREES
		memcpy(&rt->rt6i_src, &ort->rt6i_src, sizeof(struct rt6key));
#endif
		rt->rt6i_table = ort->rt6i_table;
	}
	return rt;
}

#ifdef CONFIG_IPV6_ROUTE_INFO
static struct rt6_info *rt6_get_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex)
{
	struct fib6_node *fn;
	struct rt6_info *rt = NULL;
	struct fib6_table *table;

	table = fib6_get_table(net, RT6_TABLE_INFO);
	if (table == NULL)
		return NULL;

	write_lock_bh(&table->tb6_lock);
	fn = fib6_locate(&table->tb6_root, prefix ,prefixlen, NULL, 0);
	if (!fn)
		goto out;

	for (rt = fn->leaf; rt; rt = rt->dst.rt6_next) {
		if (rt->rt6i_dev->ifindex != ifindex)
			continue;
		if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY))
			continue;
		if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr))
			continue;
		dst_hold(&rt->dst);
		break;
	}
out:
	write_unlock_bh(&table->tb6_lock);
	return rt;
}

static struct rt6_info *rt6_add_route_info(struct net *net,
					   struct in6_addr *prefix, int prefixlen,
					   struct in6_addr *gwaddr, int ifindex,
					   unsigned pref)
{
	struct fib6_config cfg = {
		.fc_table	= RT6_TABLE_INFO,
		.fc_metric	= IP6_RT_PRIO_USER,
		.fc_ifindex	= ifindex,
		.fc_dst_len	= prefixlen,
		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO |
				  RTF_UP | RTF_PREF(pref),
		.fc_nlinfo.pid = 0,
		.fc_nlinfo.nlh = NULL,
		.fc_nlinfo.nl_net = net,
	};

	ipv6_addr_copy(&cfg.fc_dst, prefix);
	ipv6_addr_copy(&cfg.fc_gateway, gwaddr);

	/* We should treat it as a default route if prefix length is 0. */
	if (!prefixlen)
		cfg.fc_flags |= RTF_DEFAULT;

	ip6_route_add(&cfg);

	return rt6_get_route_info(net, prefix, prefixlen, gwaddr, ifindex);
}
#endif

struct rt6_info *rt6_get_dflt_router(struct in6_addr *addr, struct net_device *dev)
{
	struct rt6_info *rt;
	struct fib6_table *table;

	table = fib6_get_table(dev_net(dev), RT6_TABLE_DFLT);
	if (table == NULL)
		return NULL;

	write_lock_bh(&table->tb6_lock);
	for (rt = table->tb6_root.leaf; rt; rt=rt->dst.rt6_next) {
		if (dev == rt->rt6i_dev &&
		    ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) &&
		    ipv6_addr_equal(&rt->rt6i_gateway, addr))
			break;
	}
	if (rt)
		dst_hold(&rt->dst);
	write_unlock_bh(&table->tb6_lock);
	return rt;
}

struct rt6_info *rt6_add_dflt_router(struct in6_addr *gwaddr,
				     struct net_device *dev,
				     unsigned int pref)
{
	struct fib6_config cfg = {
		.fc_table	= RT6_TABLE_DFLT,
		.fc_metric	= IP6_RT_PRIO_USER,
		.fc_ifindex	= dev->ifindex,
		.fc_flags	= RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT |
				  RTF_UP | RTF_EXPIRES | RTF_PREF(pref),
		.fc_nlinfo.pid = 0,
		.fc_nlinfo.nlh = NULL,
		.fc_nlinfo.nl_net = dev_net(dev),
	};

	ipv6_addr_copy(&cfg.fc_gateway, gwaddr);

	ip6_route_add(&cfg);

	return rt6_get_dflt_router(gwaddr, dev);
}

void rt6_purge_dflt_routers(struct net *net)
{
	struct rt6_info *rt;
	struct fib6_table *table;

	/* NOTE: Keep consistent with rt6_get_dflt_router */
	table = fib6_get_table(net, RT6_TABLE_DFLT);
	if (table == NULL)
		return;

restart:
	read_lock_bh(&table->tb6_lock);
	for (rt = table->tb6_root.leaf; rt; rt = rt->dst.rt6_next) {
		if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) {
			dst_hold(&rt->dst);
			read_unlock_bh(&table->tb6_lock);
			ip6_del_rt(rt);
			goto restart;
		}
	}
	read_unlock_bh(&table->tb6_lock);
}

static void rtmsg_to_fib6_config(struct net *net,
				 struct in6_rtmsg *rtmsg,
				 struct fib6_config *cfg)
{
	memset(cfg, 0, sizeof(*cfg));

	cfg->fc_table = RT6_TABLE_MAIN;
	cfg->fc_ifindex = rtmsg->rtmsg_ifindex;
	cfg->fc_metric = rtmsg->rtmsg_metric;
	cfg->fc_expires = rtmsg->rtmsg_info;
	cfg->fc_dst_len = rtmsg->rtmsg_dst_len;
	cfg->fc_src_len = rtmsg->rtmsg_src_len;
	cfg->fc_flags = rtmsg->rtmsg_flags;

	cfg->fc_nlinfo.nl_net = net;

	ipv6_addr_copy(&cfg->fc_dst, &rtmsg->rtmsg_dst);
	ipv6_addr_copy(&cfg->fc_src, &rtmsg->rtmsg_src);
	ipv6_addr_copy(&cfg->fc_gateway, &rtmsg->rtmsg_gateway);
}

int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg)
{
	struct fib6_config cfg;
	struct in6_rtmsg rtmsg;
	int err;

	switch(cmd) {
	case SIOCADDRT:		/* Add a route */
	case SIOCDELRT:		/* Delete a route */
		if (!capable(CAP_NET_ADMIN))
			return -EPERM;
		err = copy_from_user(&rtmsg, arg,
				     sizeof(struct in6_rtmsg));
		if (err)
			return -EFAULT;

		rtmsg_to_fib6_config(net, &rtmsg, &cfg);

		rtnl_lock();
		switch (cmd) {
		case SIOCADDRT:
			err = ip6_route_add(&cfg);
			break;
		case SIOCDELRT:
			err = ip6_route_del(&cfg);
			break;
		default:
			err = -EINVAL;
		}
		rtnl_unlock();

		return err;
	}

	return -EINVAL;
}

/*
 *	Drop the packet on the floor
 */

static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes)
{
	int type;
	struct dst_entry *dst = skb_dst(skb);
	switch (ipstats_mib_noroutes) {
	case IPSTATS_MIB_INNOROUTES:
		type = ipv6_addr_type(&ipv6_hdr(skb)->daddr);
		if (type == IPV6_ADDR_ANY) {
			IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
				      IPSTATS_MIB_INADDRERRORS);
			break;
		}
		/* FALLTHROUGH */
	case IPSTATS_MIB_OUTNOROUTES:
		IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst),
			      ipstats_mib_noroutes);
		break;
	}
	icmpv6_send(skb, ICMPV6_DEST_UNREACH, code, 0);
	kfree_skb(skb);
	return 0;
}

static int ip6_pkt_discard(struct sk_buff *skb)
{
	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_INNOROUTES);
}

static int ip6_pkt_discard_out(struct sk_buff *skb)
{
	skb->dev = skb_dst(skb)->dev;
	return ip6_pkt_drop(skb, ICMPV6_NOROUTE, IPSTATS_MIB_OUTNOROUTES);
}

#ifdef CONFIG_IPV6_MULTIPLE_TABLES

static int ip6_pkt_prohibit(struct sk_buff *skb)
{
	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_INNOROUTES);
}

static int ip6_pkt_prohibit_out(struct sk_buff *skb)
{
	skb->dev = skb_dst(skb)->dev;
	return ip6_pkt_drop(skb, ICMPV6_ADM_PROHIBITED, IPSTATS_MIB_OUTNOROUTES);
}

#endif

/*
 *	Allocate a dst for local (unicast / anycast) address.
 */

struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
				    const struct in6_addr *addr,
				    int anycast)
{
	struct net *net = dev_net(idev->dev);
	struct rt6_info *rt = ip6_dst_alloc(&net->ipv6.ip6_dst_ops);
	struct neighbour *neigh;

	if (rt == NULL) {
		if (net_ratelimit())
			pr_warning("IPv6:  Maximum number of routes reached,"
				   " consider increasing route/max_size.\n");
		return ERR_PTR(-ENOMEM);
	}

	dev_hold(net->loopback_dev);
	in6_dev_hold(idev);

	rt->dst.flags = DST_HOST;
	rt->dst.input = ip6_input;
	rt->dst.output = ip6_output;
	rt->rt6i_dev = net->loopback_dev;
	rt->rt6i_idev = idev;
	dst_metric_set(&rt->dst, RTAX_MTU, ipv6_get_mtu(rt->rt6i_dev));
	dst_metric_set(&rt->dst, RTAX_HOPLIMIT, -1);
	rt->dst.obsolete = -1;

	rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP;
	if (anycast)
		rt->rt6i_flags |= RTF_ANYCAST;
	else
		rt->rt6i_flags |= RTF_LOCAL;
	neigh = ndisc_get_neigh(rt->rt6i_dev, &rt->rt6i_gateway);
	if (IS_ERR(neigh)) {
		dst_free(&rt->dst);

		/* We are casting this because that is the return
		 * value type.  But an errno encoded pointer is the
		 * same regardless of the underlying pointer type,
		 * and that's what we are returning.  So this is OK.
		 */
		return (struct rt6_info *) neigh;
	}
	rt->rt6i_nexthop = neigh;

	ipv6_addr_copy(&rt->rt6i_dst.addr, addr);
	rt->rt6i_dst.plen = 128;
	rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);

	atomic_set(&rt->dst.__refcnt, 1);

	return rt;
}

struct arg_dev_net {
	struct net_device *dev;
	struct net *net;
};

static int fib6_ifdown(struct rt6_info *rt, void *arg)
{
	struct net_device *dev = ((struct arg_dev_net *)arg)->dev;
	struct net *net = ((struct arg_dev_net *)arg)->net;

	if (((void *)rt->rt6i_dev == dev || dev == NULL) &&
	    rt != net->ipv6.ip6_null_entry) {
		RT6_TRACE("deleted by ifdown %p\n", rt);
		return -1;
	}
	return 0;
}

void rt6_ifdown(struct net *net, struct net_device *dev)
{
	struct arg_dev_net adn = {
		.dev = dev,
		.net = net,
	};

	fib6_clean_all(net, fib6_ifdown, 0, &adn);
	icmp6_clean_all(fib6_ifdown, &adn);
}

struct rt6_mtu_change_arg
{
	struct net_device *dev;
	unsigned mtu;
};

static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg;
	struct inet6_dev *idev;

	/* In IPv6 pmtu discovery is not optional,
	   so that RTAX_MTU lock cannot disable it.
	   We still use this lock to block changes
	   caused by addrconf/ndisc.
	*/

	idev = __in6_dev_get(arg->dev);
	if (idev == NULL)
		return 0;

	/* For administrative MTU increase, there is no way to discover
	   IPv6 PMTU increase, so PMTU increase should be updated here.
	   Since RFC 1981 doesn't include administrative MTU increase
	   update PMTU increase is a MUST. (i.e. jumbo frame)
	 */
	/*
	   If new MTU is less than route PMTU, this new MTU will be the
	   lowest MTU in the path, update the route PMTU to reflect PMTU
	   decreases; if new MTU is greater than route PMTU, and the
	   old MTU is the lowest MTU in the path, update the route PMTU
	   to reflect the increase. In this case if the other nodes' MTU
	   also have the lowest MTU, TOO BIG MESSAGE will be lead to
	   PMTU discouvery.
	 */
	if (rt->rt6i_dev == arg->dev &&
	    !dst_metric_locked(&rt->dst, RTAX_MTU) &&
	    (dst_mtu(&rt->dst) >= arg->mtu ||
	     (dst_mtu(&rt->dst) < arg->mtu &&
	      dst_mtu(&rt->dst) == idev->cnf.mtu6))) {
		dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu);
	}
	return 0;
}

void rt6_mtu_change(struct net_device *dev, unsigned mtu)
{
	struct rt6_mtu_change_arg arg = {
		.dev = dev,
		.mtu = mtu,
	};

	fib6_clean_all(dev_net(dev), rt6_mtu_change_route, 0, &arg);
}

static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = {
	[RTA_GATEWAY]           = { .len = sizeof(struct in6_addr) },
	[RTA_OIF]               = { .type = NLA_U32 },
	[RTA_IIF]		= { .type = NLA_U32 },
	[RTA_PRIORITY]          = { .type = NLA_U32 },
	[RTA_METRICS]           = { .type = NLA_NESTED },
};

static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh,
			      struct fib6_config *cfg)
{
	struct rtmsg *rtm;
	struct nlattr *tb[RTA_MAX+1];
	int err;

	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
	if (err < 0)
		goto errout;

	err = -EINVAL;
	rtm = nlmsg_data(nlh);
	memset(cfg, 0, sizeof(*cfg));

	cfg->fc_table = rtm->rtm_table;
	cfg->fc_dst_len = rtm->rtm_dst_len;
	cfg->fc_src_len = rtm->rtm_src_len;
	cfg->fc_flags = RTF_UP;
	cfg->fc_protocol = rtm->rtm_protocol;

	if (rtm->rtm_type == RTN_UNREACHABLE)
		cfg->fc_flags |= RTF_REJECT;

	if (rtm->rtm_type == RTN_LOCAL)
		cfg->fc_flags |= RTF_LOCAL;

	cfg->fc_nlinfo.pid = NETLINK_CB(skb).pid;
	cfg->fc_nlinfo.nlh = nlh;
	cfg->fc_nlinfo.nl_net = sock_net(skb->sk);

	if (tb[RTA_GATEWAY]) {
		nla_memcpy(&cfg->fc_gateway, tb[RTA_GATEWAY], 16);
		cfg->fc_flags |= RTF_GATEWAY;
	}

	if (tb[RTA_DST]) {
		int plen = (rtm->rtm_dst_len + 7) >> 3;

		if (nla_len(tb[RTA_DST]) < plen)
			goto errout;

		nla_memcpy(&cfg->fc_dst, tb[RTA_DST], plen);
	}

	if (tb[RTA_SRC]) {
		int plen = (rtm->rtm_src_len + 7) >> 3;

		if (nla_len(tb[RTA_SRC]) < plen)
			goto errout;

		nla_memcpy(&cfg->fc_src, tb[RTA_SRC], plen);
	}

	if (tb[RTA_OIF])
		cfg->fc_ifindex = nla_get_u32(tb[RTA_OIF]);

	if (tb[RTA_PRIORITY])
		cfg->fc_metric = nla_get_u32(tb[RTA_PRIORITY]);

	if (tb[RTA_METRICS]) {
		cfg->fc_mx = nla_data(tb[RTA_METRICS]);
		cfg->fc_mx_len = nla_len(tb[RTA_METRICS]);
	}

	if (tb[RTA_TABLE])
		cfg->fc_table = nla_get_u32(tb[RTA_TABLE]);

	err = 0;
errout:
	return err;
}

static int inet6_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct fib6_config cfg;
	int err;

	err = rtm_to_fib6_config(skb, nlh, &cfg);
	if (err < 0)
		return err;

	return ip6_route_del(&cfg);
}

static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
{
	struct fib6_config cfg;
	int err;

	err = rtm_to_fib6_config(skb, nlh, &cfg);
	if (err < 0)
		return err;

	return ip6_route_add(&cfg);
}

static inline size_t rt6_nlmsg_size(void)
{
	return NLMSG_ALIGN(sizeof(struct rtmsg))
	       + nla_total_size(16) /* RTA_SRC */
	       + nla_total_size(16) /* RTA_DST */
	       + nla_total_size(16) /* RTA_GATEWAY */
	       + nla_total_size(16) /* RTA_PREFSRC */
	       + nla_total_size(4) /* RTA_TABLE */
	       + nla_total_size(4) /* RTA_IIF */
	       + nla_total_size(4) /* RTA_OIF */
	       + nla_total_size(4) /* RTA_PRIORITY */
	       + RTAX_MAX * nla_total_size(4) /* RTA_METRICS */
	       + nla_total_size(sizeof(struct rta_cacheinfo));
}

static int rt6_fill_node(struct net *net,
			 struct sk_buff *skb, struct rt6_info *rt,
			 struct in6_addr *dst, struct in6_addr *src,
			 int iif, int type, u32 pid, u32 seq,
			 int prefix, int nowait, unsigned int flags)
{
	struct rtmsg *rtm;
	struct nlmsghdr *nlh;
	long expires;
	u32 table;

	if (prefix) {	/* user wants prefix routes only */
		if (!(rt->rt6i_flags & RTF_PREFIX_RT)) {
			/* success since this is not a prefix route */
			return 1;
		}
	}

	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*rtm), flags);
	if (nlh == NULL)
		return -EMSGSIZE;

	rtm = nlmsg_data(nlh);
	rtm->rtm_family = AF_INET6;
	rtm->rtm_dst_len = rt->rt6i_dst.plen;
	rtm->rtm_src_len = rt->rt6i_src.plen;
	rtm->rtm_tos = 0;
	if (rt->rt6i_table)
		table = rt->rt6i_table->tb6_id;
	else
		table = RT6_TABLE_UNSPEC;
	rtm->rtm_table = table;
	NLA_PUT_U32(skb, RTA_TABLE, table);
	if (rt->rt6i_flags&RTF_REJECT)
		rtm->rtm_type = RTN_UNREACHABLE;
	else if (rt->rt6i_flags&RTF_LOCAL)
		rtm->rtm_type = RTN_LOCAL;
	else if (rt->rt6i_dev && (rt->rt6i_dev->flags&IFF_LOOPBACK))
		rtm->rtm_type = RTN_LOCAL;
	else
		rtm->rtm_type = RTN_UNICAST;
	rtm->rtm_flags = 0;
	rtm->rtm_scope = RT_SCOPE_UNIVERSE;
	rtm->rtm_protocol = rt->rt6i_protocol;
	if (rt->rt6i_flags&RTF_DYNAMIC)
		rtm->rtm_protocol = RTPROT_REDIRECT;
	else if (rt->rt6i_flags & RTF_ADDRCONF)
		rtm->rtm_protocol = RTPROT_KERNEL;
	else if (rt->rt6i_flags&RTF_DEFAULT)
		rtm->rtm_protocol = RTPROT_RA;

	if (rt->rt6i_flags&RTF_CACHE)
		rtm->rtm_flags |= RTM_F_CLONED;

	if (dst) {
		NLA_PUT(skb, RTA_DST, 16, dst);
		rtm->rtm_dst_len = 128;
	} else if (rtm->rtm_dst_len)
		NLA_PUT(skb, RTA_DST, 16, &rt->rt6i_dst.addr);
#ifdef CONFIG_IPV6_SUBTREES
	if (src) {
		NLA_PUT(skb, RTA_SRC, 16, src);
		rtm->rtm_src_len = 128;
	} else if (rtm->rtm_src_len)
		NLA_PUT(skb, RTA_SRC, 16, &rt->rt6i_src.addr);
#endif
	if (iif) {
#ifdef CONFIG_IPV6_MROUTE
		if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) {
			int err = ip6mr_get_route(net, skb, rtm, nowait);
			if (err <= 0) {
				if (!nowait) {
					if (err == 0)
						return 0;
					goto nla_put_failure;
				} else {
					if (err == -EMSGSIZE)
						goto nla_put_failure;
				}
			}
		} else
#endif
			NLA_PUT_U32(skb, RTA_IIF, iif);
	} else if (dst) {
		struct inet6_dev *idev = ip6_dst_idev(&rt->dst);
		struct in6_addr saddr_buf;
		if (ipv6_dev_get_saddr(net, idev ? idev->dev : NULL,
				       dst, 0, &saddr_buf) == 0)
			NLA_PUT(skb, RTA_PREFSRC, 16, &saddr_buf);
	}

	if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0)
		goto nla_put_failure;

	if (rt->dst.neighbour)
		NLA_PUT(skb, RTA_GATEWAY, 16, &rt->dst.neighbour->primary_key);

	if (rt->dst.dev)
		NLA_PUT_U32(skb, RTA_OIF, rt->rt6i_dev->ifindex);

	NLA_PUT_U32(skb, RTA_PRIORITY, rt->rt6i_metric);

	if (!(rt->rt6i_flags & RTF_EXPIRES))
		expires = 0;
	else if (rt->rt6i_expires - jiffies < INT_MAX)
		expires = rt->rt6i_expires - jiffies;
	else
		expires = INT_MAX;

	if (rtnl_put_cacheinfo(skb, &rt->dst, 0, 0, 0,
			       expires, rt->dst.error) < 0)
		goto nla_put_failure;

	return nlmsg_end(skb, nlh);

nla_put_failure:
	nlmsg_cancel(skb, nlh);
	return -EMSGSIZE;
}

int rt6_dump_route(struct rt6_info *rt, void *p_arg)
{
	struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg;
	int prefix;

	if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) {
		struct rtmsg *rtm = nlmsg_data(arg->cb->nlh);
		prefix = (rtm->rtm_flags & RTM_F_PREFIX) != 0;
	} else
		prefix = 0;

	return rt6_fill_node(arg->net,
		     arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE,
		     NETLINK_CB(arg->cb->skb).pid, arg->cb->nlh->nlmsg_seq,
		     prefix, 0, NLM_F_MULTI);
}

static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
	struct net *net = sock_net(in_skb->sk);
	struct nlattr *tb[RTA_MAX+1];
	struct rt6_info *rt;
	struct sk_buff *skb;
	struct rtmsg *rtm;
	struct flowi fl;
	int err, iif = 0;

	err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy);
	if (err < 0)
		goto errout;

	err = -EINVAL;
	memset(&fl, 0, sizeof(fl));

	if (tb[RTA_SRC]) {
		if (nla_len(tb[RTA_SRC]) < sizeof(struct in6_addr))
			goto errout;

		ipv6_addr_copy(&fl.fl6_src, nla_data(tb[RTA_SRC]));
	}

	if (tb[RTA_DST]) {
		if (nla_len(tb[RTA_DST]) < sizeof(struct in6_addr))
			goto errout;

		ipv6_addr_copy(&fl.fl6_dst, nla_data(tb[RTA_DST]));
	}

	if (tb[RTA_IIF])
		iif = nla_get_u32(tb[RTA_IIF]);

	if (tb[RTA_OIF])
		fl.oif = nla_get_u32(tb[RTA_OIF]);

	if (iif) {
		struct net_device *dev;
		dev = __dev_get_by_index(net, iif);
		if (!dev) {
			err = -ENODEV;
			goto errout;
		}
	}

	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_reserve(skb, MAX_HEADER + sizeof(struct ipv6hdr));

	rt = (struct rt6_info*) ip6_route_output(net, NULL, &fl);
	skb_dst_set(skb, &rt->dst);

	err = rt6_fill_node(net, skb, rt, &fl.fl6_dst, &fl.fl6_src, iif,
			    RTM_NEWROUTE, NETLINK_CB(in_skb).pid,
			    nlh->nlmsg_seq, 0, 0, 0);
	if (err < 0) {
		kfree_skb(skb);
		goto errout;
	}

	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).pid);
errout:
	return err;
}

void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info)
{
	struct sk_buff *skb;
	struct net *net = info->nl_net;
	u32 seq;
	int err;

	err = -ENOBUFS;
	seq = info->nlh != NULL ? info->nlh->nlmsg_seq : 0;

	skb = nlmsg_new(rt6_nlmsg_size(), gfp_any());
	if (skb == NULL)
		goto errout;

	err = rt6_fill_node(net, skb, rt, NULL, NULL, 0,
				event, info->pid, seq, 0, 0, 0);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in rt6_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	rtnl_notify(skb, net, info->pid, RTNLGRP_IPV6_ROUTE,
		    info->nlh, gfp_any());
	return;
errout:
	if (err < 0)
		rtnl_set_sk_err(net, RTNLGRP_IPV6_ROUTE, err);
}

static int ip6_route_dev_notify(struct notifier_block *this,
				unsigned long event, void *data)
{
	struct net_device *dev = (struct net_device *)data;
	struct net *net = dev_net(dev);

	if (event == NETDEV_REGISTER && (dev->flags & IFF_LOOPBACK)) {
		net->ipv6.ip6_null_entry->dst.dev = dev;
		net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
		net->ipv6.ip6_prohibit_entry->dst.dev = dev;
		net->ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(dev);
		net->ipv6.ip6_blk_hole_entry->dst.dev = dev;
		net->ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(dev);
#endif
	}

	return NOTIFY_OK;
}

/*
 *	/proc
 */

#ifdef CONFIG_PROC_FS

struct rt6_proc_arg
{
	char *buffer;
	int offset;
	int length;
	int skip;
	int len;
};

static int rt6_info_route(struct rt6_info *rt, void *p_arg)
{
	struct seq_file *m = p_arg;

	seq_printf(m, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);

#ifdef CONFIG_IPV6_SUBTREES
	seq_printf(m, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen);
#else
	seq_puts(m, "00000000000000000000000000000000 00 ");
#endif

	if (rt->rt6i_nexthop) {
		seq_printf(m, "%pi6", rt->rt6i_nexthop->primary_key);
	} else {
		seq_puts(m, "00000000000000000000000000000000");
	}
	seq_printf(m, " %08x %08x %08x %08x %8s\n",
		   rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
		   rt->dst.__use, rt->rt6i_flags,
		   rt->rt6i_dev ? rt->rt6i_dev->name : "");
	return 0;
}

static int ipv6_route_show(struct seq_file *m, void *v)
{
	struct net *net = (struct net *)m->private;
	fib6_clean_all(net, rt6_info_route, 0, m);
	return 0;
}

static int ipv6_route_open(struct inode *inode, struct file *file)
{
	return single_open_net(inode, file, ipv6_route_show);
}

static const struct file_operations ipv6_route_proc_fops = {
	.owner		= THIS_MODULE,
	.open		= ipv6_route_open,
	.read		= seq_read,
	.llseek		= seq_lseek,
	.release	= single_release_net,
};

static int rt6_stats_seq_show(struct seq_file *seq, void *v)
{
	struct net *net = (struct net *)seq->private;
	seq_printf(seq, "%04x %04x %04x %04x %04x %04x %04x\n",
		   net->ipv6.rt6_stats->fib_nodes,
		   net->ipv6.rt6_stats->fib_route_nodes,
		   net->ipv6.rt6_stats->fib_rt_alloc,
		   net->ipv6.rt6_stats->fib_rt_entries,
		   net->ipv6.rt6_stats->fib_rt_cache,
		   dst_entries_get_slow(&net->ipv6.ip6_dst_ops),
		   net->ipv6.rt6_stats->fib_discarded_routes);

	return 0;
}

static int rt6_stats_seq_open(struct inode *inode, struct file *file)
{
	return single_open_net(inode, file, rt6_stats_seq_show);
}

static const struct file_operations rt6_stats_seq_fops = {
	.owner	 = THIS_MODULE,
	.open	 = rt6_stats_seq_open,
	.read	 = seq_read,
	.llseek	 = seq_lseek,
	.release = single_release_net,
};
#endif	/* CONFIG_PROC_FS */

#ifdef CONFIG_SYSCTL

static
int ipv6_sysctl_rtcache_flush(ctl_table *ctl, int write,
			      void __user *buffer, size_t *lenp, loff_t *ppos)
{
	struct net *net = current->nsproxy->net_ns;
	int delay = net->ipv6.sysctl.flush_delay;
	if (write) {
		proc_dointvec(ctl, write, buffer, lenp, ppos);
		fib6_run_gc(delay <= 0 ? ~0UL : (unsigned long)delay, net);
		return 0;
	} else
		return -EINVAL;
}

ctl_table ipv6_route_table_template[] = {
	{
		.procname	=	"flush",
		.data		=	&init_net.ipv6.sysctl.flush_delay,
		.maxlen		=	sizeof(int),
		.mode		=	0200,
		.proc_handler	=	ipv6_sysctl_rtcache_flush
	},
	{
		.procname	=	"gc_thresh",
		.data		=	&ip6_dst_ops_template.gc_thresh,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec,
	},
	{
		.procname	=	"max_size",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_max_size,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec,
	},
	{
		.procname	=	"gc_min_interval",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
	},
	{
		.procname	=	"gc_timeout",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_timeout,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
	},
	{
		.procname	=	"gc_interval",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
	},
	{
		.procname	=	"gc_elasticity",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec,
	},
	{
		.procname	=	"mtu_expires",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_mtu_expires,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_jiffies,
	},
	{
		.procname	=	"min_adv_mss",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_min_advmss,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec,
	},
	{
		.procname	=	"gc_min_interval_ms",
		.data		=	&init_net.ipv6.sysctl.ip6_rt_gc_min_interval,
		.maxlen		=	sizeof(int),
		.mode		=	0644,
		.proc_handler	=	proc_dointvec_ms_jiffies,
	},
	{ }
};

struct ctl_table * __net_init ipv6_route_sysctl_init(struct net *net)
{
	struct ctl_table *table;

	table = kmemdup(ipv6_route_table_template,
			sizeof(ipv6_route_table_template),
			GFP_KERNEL);

	if (table) {
		table[0].data = &net->ipv6.sysctl.flush_delay;
		table[1].data = &net->ipv6.ip6_dst_ops.gc_thresh;
		table[2].data = &net->ipv6.sysctl.ip6_rt_max_size;
		table[3].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
		table[4].data = &net->ipv6.sysctl.ip6_rt_gc_timeout;
		table[5].data = &net->ipv6.sysctl.ip6_rt_gc_interval;
		table[6].data = &net->ipv6.sysctl.ip6_rt_gc_elasticity;
		table[7].data = &net->ipv6.sysctl.ip6_rt_mtu_expires;
		table[8].data = &net->ipv6.sysctl.ip6_rt_min_advmss;
		table[9].data = &net->ipv6.sysctl.ip6_rt_gc_min_interval;
	}

	return table;
}
#endif

static int __net_init ip6_route_net_init(struct net *net)
{
	int ret = -ENOMEM;

	memcpy(&net->ipv6.ip6_dst_ops, &ip6_dst_ops_template,
	       sizeof(net->ipv6.ip6_dst_ops));

	if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0)
		goto out_ip6_dst_ops;

	net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template,
					   sizeof(*net->ipv6.ip6_null_entry),
					   GFP_KERNEL);
	if (!net->ipv6.ip6_null_entry)
		goto out_ip6_dst_entries;
	net->ipv6.ip6_null_entry->dst.path =
		(struct dst_entry *)net->ipv6.ip6_null_entry;
	net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops;
	dst_metric_set(&net->ipv6.ip6_null_entry->dst, RTAX_HOPLIMIT, 255);

#ifdef CONFIG_IPV6_MULTIPLE_TABLES
	net->ipv6.ip6_prohibit_entry = kmemdup(&ip6_prohibit_entry_template,
					       sizeof(*net->ipv6.ip6_prohibit_entry),
					       GFP_KERNEL);
	if (!net->ipv6.ip6_prohibit_entry)
		goto out_ip6_null_entry;
	net->ipv6.ip6_prohibit_entry->dst.path =
		(struct dst_entry *)net->ipv6.ip6_prohibit_entry;
	net->ipv6.ip6_prohibit_entry->dst.ops = &net->ipv6.ip6_dst_ops;
	dst_metric_set(&net->ipv6.ip6_prohibit_entry->dst, RTAX_HOPLIMIT, 255);

	net->ipv6.ip6_blk_hole_entry = kmemdup(&ip6_blk_hole_entry_template,
					       sizeof(*net->ipv6.ip6_blk_hole_entry),
					       GFP_KERNEL);
	if (!net->ipv6.ip6_blk_hole_entry)
		goto out_ip6_prohibit_entry;
	net->ipv6.ip6_blk_hole_entry->dst.path =
		(struct dst_entry *)net->ipv6.ip6_blk_hole_entry;
	net->ipv6.ip6_blk_hole_entry->dst.ops = &net->ipv6.ip6_dst_ops;
	dst_metric_set(&net->ipv6.ip6_blk_hole_entry->dst, RTAX_HOPLIMIT, 255);
#endif

	net->ipv6.sysctl.flush_delay = 0;
	net->ipv6.sysctl.ip6_rt_max_size = 4096;
	net->ipv6.sysctl.ip6_rt_gc_min_interval = HZ / 2;
	net->ipv6.sysctl.ip6_rt_gc_timeout = 60*HZ;
	net->ipv6.sysctl.ip6_rt_gc_interval = 30*HZ;
	net->ipv6.sysctl.ip6_rt_gc_elasticity = 9;
	net->ipv6.sysctl.ip6_rt_mtu_expires = 10*60*HZ;
	net->ipv6.sysctl.ip6_rt_min_advmss = IPV6_MIN_MTU - 20 - 40;

#ifdef CONFIG_PROC_FS
	proc_net_fops_create(net, "ipv6_route", 0, &ipv6_route_proc_fops);
	proc_net_fops_create(net, "rt6_stats", S_IRUGO, &rt6_stats_seq_fops);
#endif
	net->ipv6.ip6_rt_gc_expire = 30*HZ;

	ret = 0;
out:
	return ret;

#ifdef CONFIG_IPV6_MULTIPLE_TABLES
out_ip6_prohibit_entry:
	kfree(net->ipv6.ip6_prohibit_entry);
out_ip6_null_entry:
	kfree(net->ipv6.ip6_null_entry);
#endif
out_ip6_dst_entries:
	dst_entries_destroy(&net->ipv6.ip6_dst_ops);
out_ip6_dst_ops:
	goto out;
}

static void __net_exit ip6_route_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
	proc_net_remove(net, "ipv6_route");
	proc_net_remove(net, "rt6_stats");
#endif
	kfree(net->ipv6.ip6_null_entry);
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
	kfree(net->ipv6.ip6_prohibit_entry);
	kfree(net->ipv6.ip6_blk_hole_entry);
#endif
	dst_entries_destroy(&net->ipv6.ip6_dst_ops);
}

static struct pernet_operations ip6_route_net_ops = {
	.init = ip6_route_net_init,
	.exit = ip6_route_net_exit,
};

static struct notifier_block ip6_route_dev_notifier = {
	.notifier_call = ip6_route_dev_notify,
	.priority = 0,
};

int __init ip6_route_init(void)
{
	int ret;

	ret = -ENOMEM;
	ip6_dst_ops_template.kmem_cachep =
		kmem_cache_create("ip6_dst_cache", sizeof(struct rt6_info), 0,
				  SLAB_HWCACHE_ALIGN, NULL);
	if (!ip6_dst_ops_template.kmem_cachep)
		goto out;

	ret = dst_entries_init(&ip6_dst_blackhole_ops);
	if (ret)
		goto out_kmem_cache;

	ret = register_pernet_subsys(&ip6_route_net_ops);
	if (ret)
		goto out_dst_entries;

	ip6_dst_blackhole_ops.kmem_cachep = ip6_dst_ops_template.kmem_cachep;

	/* Registering of the loopback is done before this portion of code,
	 * the loopback reference in rt6_info will not be taken, do it
	 * manually for init_net */
	init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev;
	init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
  #ifdef CONFIG_IPV6_MULTIPLE_TABLES
	init_net.ipv6.ip6_prohibit_entry->dst.dev = init_net.loopback_dev;
	init_net.ipv6.ip6_prohibit_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
	init_net.ipv6.ip6_blk_hole_entry->dst.dev = init_net.loopback_dev;
	init_net.ipv6.ip6_blk_hole_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev);
  #endif
	ret = fib6_init();
	if (ret)
		goto out_register_subsys;

	ret = xfrm6_init();
	if (ret)
		goto out_fib6_init;

	ret = fib6_rules_init();
	if (ret)
		goto xfrm6_init;

	ret = -ENOBUFS;
	if (__rtnl_register(PF_INET6, RTM_NEWROUTE, inet6_rtm_newroute, NULL) ||
	    __rtnl_register(PF_INET6, RTM_DELROUTE, inet6_rtm_delroute, NULL) ||
	    __rtnl_register(PF_INET6, RTM_GETROUTE, inet6_rtm_getroute, NULL))
		goto fib6_rules_init;

	ret = register_netdevice_notifier(&ip6_route_dev_notifier);
	if (ret)
		goto fib6_rules_init;

out:
	return ret;

fib6_rules_init:
	fib6_rules_cleanup();
xfrm6_init:
	xfrm6_fini();
out_fib6_init:
	fib6_gc_cleanup();
out_register_subsys:
	unregister_pernet_subsys(&ip6_route_net_ops);
out_dst_entries:
	dst_entries_destroy(&ip6_dst_blackhole_ops);
out_kmem_cache:
	kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
	goto out;
}

void ip6_route_cleanup(void)
{
	unregister_netdevice_notifier(&ip6_route_dev_notifier);
	fib6_rules_cleanup();
	xfrm6_fini();
	fib6_gc_cleanup();
	unregister_pernet_subsys(&ip6_route_net_ops);
	dst_entries_destroy(&ip6_dst_blackhole_ops);
	kmem_cache_destroy(ip6_dst_ops_template.kmem_cachep);
}
OpenPOWER on IntegriCloud