summaryrefslogtreecommitdiffstats
path: root/net/ipv4/route.c
blob: cacf36b71d1db7d0dd87f47de5501d0728a00689 (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
/*
 * 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.
 *
 * Version:	$Id: route.c,v 1.91 2000/10/03 07:29:00 anton Exp $
 *
 * Authors:	Ross Biro, <bir7@leland.Stanford.Edu>
 *		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. Splitted 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
 *
 *		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/config.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/mm.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/skbuff.h>
#include <linux/rtnetlink.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 <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>
#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#define IP_MAX_MTU	0xFFF0

#define RT_GC_TIMEOUT (300*HZ)

int ip_rt_min_delay = 2*HZ;
int ip_rt_max_delay = 10*HZ;
int ip_rt_max_size;
int ip_rt_gc_timeout = RT_GC_TIMEOUT;
int ip_rt_gc_interval = 60*HZ;
int ip_rt_gc_min_interval = 5*HZ;
int ip_rt_redirect_number = 9;
int ip_rt_redirect_load = HZ/50;
int ip_rt_redirect_silence = ((HZ/50) << (9+1));
int ip_rt_error_cost = HZ;
int ip_rt_error_burst = 5*HZ;
int ip_rt_gc_elasticity = 8;
int ip_rt_mtu_expires = 10*60*HZ;
int ip_rt_min_pmtu = 512+20+20;
int ip_rt_min_advmss = 536;

static unsigned long rt_deadline;

#define RTprint(a...)	printk(KERN_DEBUG a)

static struct timer_list rt_flush_timer;
static struct timer_list rt_periodic_timer;

/*
 *	Interface to generic destination cache.
 */

static struct dst_entry * ipv4_dst_check(struct dst_entry * dst, u32);
static struct dst_entry * ipv4_dst_reroute(struct dst_entry * dst,
					   struct sk_buff *);
static void		  ipv4_dst_destroy(struct dst_entry * dst);
static struct dst_entry * ipv4_negative_advice(struct dst_entry *);
static void		  ipv4_link_failure(struct sk_buff *skb);
static int rt_garbage_collect(void);


struct dst_ops ipv4_dst_ops =
{
	AF_INET,
	__constant_htons(ETH_P_IP),
	0,

	rt_garbage_collect,
	ipv4_dst_check,
	ipv4_dst_reroute,
	ipv4_dst_destroy,
	ipv4_negative_advice,
	ipv4_link_failure,
	sizeof(struct rtable),
};

#ifdef CONFIG_INET_ECN
#define ECN_OR_COST(class)	TC_PRIO_##class
#else
#define ECN_OR_COST(class)	TC_PRIO_FILLER
#endif

__u8 ip_tos2prio[16] = {
	TC_PRIO_BESTEFFORT,
	ECN_OR_COST(FILLER),
	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) A BH protected rwlocks protect 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	*chain;
	rwlock_t	lock;
} __attribute__((__aligned__(8)));

static struct rt_hash_bucket 	*rt_hash_table;
static unsigned			rt_hash_mask;
static int			rt_hash_log;

static int rt_intern_hash(unsigned hash, struct rtable * rth, struct rtable ** res);

static __inline__ unsigned rt_hash_code(u32 daddr, u32 saddr, u8 tos)
{
	unsigned hash = ((daddr&0xF0F0F0F0)>>4)|((daddr&0x0F0F0F0F)<<4);
	hash ^= saddr^tos;
	hash ^= (hash>>16);
	return (hash^(hash>>8)) & rt_hash_mask;
}

static int rt_cache_get_info(char *buffer, char **start, off_t offset, int length)
{
	int len=0;
	off_t pos=0;
	char temp[129];
	struct rtable *r;
	int i;

	pos = 128;

	if (offset<128)	{
		sprintf(buffer,"%-127s\n", "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\tMetric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\tHHUptod\tSpecDst");
		len = 128;
  	}
	
	for (i = rt_hash_mask; i>=0; i--) {
		read_lock_bh(&rt_hash_table[i].lock);
		for (r = rt_hash_table[i].chain; r; r = r->u.rt_next) {
			/*
			 *	Spin through entries until we are ready
			 */
			pos += 128;

			if (pos <= offset) {
				len = 0;
				continue;
			}
			sprintf(temp, "%s\t%08lX\t%08lX\t%8X\t%d\t%u\t%d\t%08lX\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X",
				r->u.dst.dev ? r->u.dst.dev->name : "*",
				(unsigned long)r->rt_dst,
				(unsigned long)r->rt_gateway,
				r->rt_flags,
				atomic_read(&r->u.dst.__refcnt),
				r->u.dst.__use,
				0,
				(unsigned long)r->rt_src, (int)r->u.dst.advmss + 40,
				r->u.dst.window,
				(int)((r->u.dst.rtt>>3) + r->u.dst.rttvar),
				r->key.tos,
				r->u.dst.hh ? atomic_read(&r->u.dst.hh->hh_refcnt) : -1,
				r->u.dst.hh ? (r->u.dst.hh->hh_output == dev_queue_xmit) : 0,
				r->rt_spec_dst);
			sprintf(buffer+len,"%-127s\n",temp);
			len += 128;
			if (pos >= offset+length) {
				read_unlock_bh(&rt_hash_table[i].lock);
				goto done;
			}
		}
		read_unlock_bh(&rt_hash_table[i].lock);
        }

done:
  	*start = buffer+len-(pos-offset);
  	len = pos-offset;
  	if (len>length)
  		len = length;
  	return len;
}
  
static __inline__ void rt_free(struct rtable *rt)
{
	dst_free(&rt->u.dst);
}

static __inline__ void rt_drop(struct rtable *rt)
{
	ip_rt_put(rt);
	dst_free(&rt->u.dst);
}

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))
		&& rth->key.iif && rth->u.rt_next);
}

static __inline__ int rt_valuable(struct rtable *rth)
{
	return ((rth->rt_flags&(RTCF_REDIRECTED|RTCF_NOTIFY))
		|| rth->u.dst.expires);
}

static __inline__ int rt_may_expire(struct rtable *rth, int tmo1, int tmo2)
{
	int age;

	if (atomic_read(&rth->u.dst.__refcnt))
		return 0;

	if (rth->u.dst.expires && (long)(rth->u.dst.expires - jiffies) <= 0)
		return 1;

	age = jiffies - rth->u.dst.lastuse;
	if (age <= tmo1 && !rt_fast_clean(rth))
		return 0;
	if (age <= tmo2 && rt_valuable(rth))
		return 0;
	return 1;
}

/* This runs via a timer and thus is always in BH context. */
static void SMP_TIMER_NAME(rt_check_expire)(unsigned long dummy)
{
	int i, t;
	static int rover;
	struct rtable *rth, **rthp;
	unsigned long now = jiffies;

	i = rover;

	for (t=(ip_rt_gc_interval<<rt_hash_log); t>=0; t -= ip_rt_gc_timeout) {
		unsigned tmo = ip_rt_gc_timeout;

		i = (i + 1) & rt_hash_mask;
		rthp = &rt_hash_table[i].chain;

		write_lock(&rt_hash_table[i].lock);
		while ((rth = *rthp) != NULL) {
			if (rth->u.dst.expires) {
				/* Entry is expired even if it is in use */
				if ((long)(now - rth->u.dst.expires) <= 0) {
					tmo >>= 1;
					rthp = &rth->u.rt_next;
					continue;
				}
			} else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) {
				tmo >>= 1;
				rthp = &rth->u.rt_next;
				continue;
			}

			/*
			 * Cleanup aged off entries.
			 */
			*rthp = rth->u.rt_next;
			rt_free(rth);
		}
		write_unlock(&rt_hash_table[i].lock);

		/* Fallback loop breaker. */
		if ((jiffies - now) > 0)
			break;
	}
	rover = i;
	mod_timer(&rt_periodic_timer, now + ip_rt_gc_interval);
}

SMP_TIMER_DEFINE(rt_check_expire, rt_gc_task);

/* This can run from both BH and non-BH contexts, the latter
 * in the case of a forced flush event.
 */
static void SMP_TIMER_NAME(rt_run_flush)(unsigned long dummy)
{
	int i;
	struct rtable * rth, * next;

	rt_deadline = 0;

	for (i=rt_hash_mask; i>=0; i--) {
		write_lock_bh(&rt_hash_table[i].lock);
		rth = rt_hash_table[i].chain;
		if (rth)
			rt_hash_table[i].chain = NULL;
		write_unlock_bh(&rt_hash_table[i].lock);

		for (; rth; rth=next) {
			next = rth->u.rt_next;
			rt_free(rth);
		}
	}
}

SMP_TIMER_DEFINE(rt_run_flush, rt_cache_flush_task);
  
static spinlock_t rt_flush_lock = SPIN_LOCK_UNLOCKED;

void rt_cache_flush(int delay)
{
	unsigned long now = jiffies;
	int user_mode = !in_softirq();

	if (delay < 0)
		delay = ip_rt_min_delay;

	spin_lock_bh(&rt_flush_lock);

	if (del_timer(&rt_flush_timer) && delay > 0 && rt_deadline) {
		long tmo = (long)(rt_deadline - now);

		/* If flush timer is already running
		   and flush request is not immediate (delay > 0):

		   if deadline is not achieved, prolongate timer to "delay",
		   otherwise fire it at deadline time.
		 */

		if (user_mode && tmo < ip_rt_max_delay-ip_rt_min_delay)
			tmo = 0;
		
		if (delay > tmo)
			delay = tmo;
	}

	if (delay <= 0) {
		spin_unlock_bh(&rt_flush_lock);
		SMP_TIMER_NAME(rt_run_flush)(0);
		return;
	}

	if (rt_deadline == 0)
		rt_deadline = now + ip_rt_max_delay;

	mod_timer(&rt_flush_timer, now+delay);
	spin_unlock_bh(&rt_flush_lock);
}

/*
   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(void)
{
	static unsigned expire = RT_GC_TIMEOUT;
	static unsigned long last_gc;
	static int rover;
	static int equilibrium;
	struct rtable *rth, **rthp;
	unsigned long now = jiffies;
	int goal;

	/*
	 * Garbage collection is pretty expensive,
	 * do not make it too frequently.
	 */
	if (now - last_gc < ip_rt_gc_min_interval &&
	    atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
		return 0;

	/* Calculate number of entries, which we want to expire now. */
	goal = atomic_read(&ipv4_dst_ops.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 = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
		if (goal > 0) {
			equilibrium += min(goal/2, rt_hash_mask+1);
			goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium;
		}
	} else {
		/* We are in dangerous area. Try to reduce cache really
		 * aggressively.
		 */
		goal = max(goal/2, rt_hash_mask+1);
		equilibrium = atomic_read(&ipv4_dst_ops.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 tmo = expire;

			k = (k + 1) & rt_hash_mask;
			rthp = &rt_hash_table[k].chain;
			write_lock_bh(&rt_hash_table[k].lock);
			while ((rth = *rthp) != NULL) {
				if (!rt_may_expire(rth, tmo, expire)) {
					tmo >>= 1;
					rthp = &rth->u.rt_next;
					continue;
				}
				*rthp = rth->u.rt_next;
				rt_free(rth);
				goal--;
			}
			write_unlock_bh(&rt_hash_table[k].lock);
			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.
		 */

		if (expire == 0)
			break;

		expire >>= 1;
#if RT_CACHE_DEBUG >= 2
		printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire, atomic_read(&ipv4_dst_ops.entries), goal, i);
#endif

		if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
			return 0;
	} while (!in_softirq() && jiffies - now < 1);

	if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size)
		return 0;
	if (net_ratelimit())
		printk("dst cache overflow\n");
	return 1;

work_done:
	expire += ip_rt_gc_min_interval;
	if (expire > ip_rt_gc_timeout ||
	    atomic_read(&ipv4_dst_ops.entries) < ipv4_dst_ops.gc_thresh)
		expire = ip_rt_gc_timeout;
#if RT_CACHE_DEBUG >= 2
	printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire, atomic_read(&ipv4_dst_ops.entries), goal, rover);
#endif
	return 0;
}

static int rt_intern_hash(unsigned hash, struct rtable * rt, struct rtable ** rp)
{
	struct rtable	*rth, **rthp;
	unsigned long	now = jiffies;
	int attempts = !in_softirq();

restart:
	rthp = &rt_hash_table[hash].chain;

	write_lock_bh(&rt_hash_table[hash].lock);
	while ((rth = *rthp) != NULL) {
		if (memcmp(&rth->key, &rt->key, sizeof(rt->key)) == 0) {
			/* Put it first */
			*rthp = rth->u.rt_next;
			rth->u.rt_next = rt_hash_table[hash].chain;
			rt_hash_table[hash].chain = rth;

			rth->u.dst.__use++;
			dst_hold(&rth->u.dst);
			rth->u.dst.lastuse = now;
			write_unlock_bh(&rt_hash_table[hash].lock);

			rt_drop(rt);
			*rp = rth;
			return 0;
		}

		rthp = &rth->u.rt_next;
	}

	/* Try to bind route to arp only if it is output
	   route or unicast forwarding path.
	 */
	if (rt->rt_type == RTN_UNICAST || rt->key.iif == 0) {
		int err = arp_bind_neighbour(&rt->u.dst);
		if (err) {
			write_unlock_bh(&rt_hash_table[hash].lock);

			if (err != -ENOBUFS) {
				rt_drop(rt);
				return 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();
				ip_rt_gc_min_interval = saved_int;
				ip_rt_gc_elasticity = saved_elasticity;
				goto restart;
			}

			if (net_ratelimit())
				printk("Neighbour table overflow.\n");
			rt_drop(rt);
			return -ENOBUFS;
		}
	}

	rt->u.rt_next = rt_hash_table[hash].chain;
#if RT_CACHE_DEBUG >= 2
	if (rt->u.rt_next) {
		struct rtable * trt;
		printk("rt_cache @%02x: %u.%u.%u.%u", hash, NIPQUAD(rt->rt_dst));
		for (trt=rt->u.rt_next; trt; trt=trt->u.rt_next)
			printk(" . %u.%u.%u.%u", NIPQUAD(trt->rt_dst));
		printk("\n");
	}
#endif
	rt_hash_table[hash].chain = rt;
	write_unlock_bh(&rt_hash_table[hash].lock);
	*rp = rt;
	return 0;
}

void rt_bind_peer(struct rtable *rt, int create)
{
	static spinlock_t rt_peer_lock = SPIN_LOCK_UNLOCKED;
	struct inet_peer *peer;

	peer = inet_getpeer(rt->rt_dst, create);

	spin_lock_bh(&rt_peer_lock);
	if (rt->peer == NULL) {
		rt->peer = peer;
		peer = NULL;
	}
	spin_unlock_bh(&rt_peer_lock);
	if (peer)
		inet_putpeer(peer);
}

/*
 * 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 spinlock_t ip_fb_id_lock = SPIN_LOCK_UNLOCKED;
	static u32 ip_fallback_id;
	u32 salt;

	spin_lock_bh(&ip_fb_id_lock);
	salt = secure_ip_id(ip_fallback_id ^ iph->daddr);
	iph->id = salt & 0xFFFF;
	ip_fallback_id = salt;
	spin_unlock_bh(&ip_fb_id_lock);
}

void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst)
{
	struct rtable *rt = (struct rtable *) dst;

	if (rt) {
		if (rt->peer == NULL)
			rt_bind_peer(rt, 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 = inet_getid(rt->peer);
			return;
		}
	} else {
		printk(KERN_DEBUG "rt_bind_peer(0) @%p\n", NET_CALLER(iph));
	}

	ip_select_fb_ident(iph);
}

static void rt_del(unsigned hash, struct rtable *rt)
{
	struct rtable **rthp;

	write_lock_bh(&rt_hash_table[hash].lock);
	ip_rt_put(rt);
	for (rthp = &rt_hash_table[hash].chain; *rthp; rthp = &(*rthp)->u.rt_next) {
		if (*rthp == rt) {
			*rthp = rt->u.rt_next;
			rt_free(rt);
			break;
		}
	}
	write_unlock_bh(&rt_hash_table[hash].lock);
}

void ip_rt_redirect(u32 old_gw, u32 daddr, u32 new_gw,
		    u32 saddr, u8 tos, struct net_device *dev)
{
	int i, k;
	struct in_device *in_dev = in_dev_get(dev);
	struct rtable *rth, **rthp;
	u32  skeys[2] = { saddr, 0 };
	int  ikeys[2] = { dev->ifindex, 0 };

	tos &= IPTOS_RT_MASK;

	if (!in_dev)
		return;

	if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev)
	    || MULTICAST(new_gw) || BADCLASS(new_gw) || 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(new_gw) != RTN_UNICAST)
			goto reject_redirect;
	}

	for (i=0; i<2; i++) {
		for (k=0; k<2; k++) {
			unsigned hash = rt_hash_code(daddr, skeys[i]^(ikeys[k]<<5), tos);

			rthp=&rt_hash_table[hash].chain;

			read_lock(&rt_hash_table[hash].lock);
			while ( (rth = *rthp) != NULL) {
				struct rtable *rt;

				if (rth->key.dst != daddr ||
				    rth->key.src != skeys[i] ||
				    rth->key.tos != tos ||
				    rth->key.oif != ikeys[k] ||
				    rth->key.iif != 0) {
					rthp = &rth->u.rt_next;
					continue;
				}

				if (rth->rt_dst != daddr ||
				    rth->rt_src != saddr ||
				    rth->u.dst.error ||
				    rth->rt_gateway != old_gw ||
				    rth->u.dst.dev != dev)
					break;

				dst_clone(&rth->u.dst);
				read_unlock(&rt_hash_table[hash].lock);

				rt = dst_alloc(&ipv4_dst_ops);
				if (rt == NULL) {
					ip_rt_put(rth);
					in_dev_put(in_dev);
					return;
				}

				/*
				 * Copy all the information.
				 */
				*rt = *rth;
				rt->u.dst.__use = 1;
				atomic_set(&rt->u.dst.__refcnt, 1);
				if (rt->u.dst.dev)
					dev_hold(rt->u.dst.dev);
				rt->u.dst.lastuse = jiffies;
				rt->u.dst.neighbour = NULL;
				rt->u.dst.hh = NULL;
				rt->u.dst.obsolete = 0;

				rt->rt_flags |= RTCF_REDIRECTED;

				/* Gateway is different ... */
				rt->rt_gateway = new_gw;

				/* Redirect received -> path was valid */
				dst_confirm(&rth->u.dst);

				if (rt->peer)
					atomic_inc(&rt->peer->refcnt);

				if (arp_bind_neighbour(&rt->u.dst) ||
				    !(rt->u.dst.neighbour->nud_state&NUD_VALID)) {
					if (rt->u.dst.neighbour)
						neigh_event_send(rt->u.dst.neighbour, NULL);
					ip_rt_put(rth);
					rt_drop(rt);
					goto do_next;
				}

				rt_del(hash, rth);
				if (!rt_intern_hash(hash, rt, &rt))
					ip_rt_put(rt);
				goto do_next;
			}
			read_unlock(&rt_hash_table[hash].lock);
		do_next:
			;
		}
	}
	in_dev_put(in_dev);
	return;

reject_redirect:
#ifdef CONFIG_IP_ROUTE_VERBOSE
	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
		printk(KERN_INFO "Redirect from %u.%u.%u.%u on %s about %u.%u.%u.%u ignored.\n"
		       "  Advised path = %u.%u.%u.%u -> %u.%u.%u.%u, tos %02x\n",
		       NIPQUAD(old_gw), dev->name, NIPQUAD(new_gw),
		       NIPQUAD(saddr), NIPQUAD(daddr), tos);
#endif
	in_dev_put(in_dev);
}

static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst)
{
	struct rtable *rt = (struct rtable*)dst;

	if (rt != NULL) {
		if (dst->obsolete) {
			ip_rt_put(rt);
			return NULL;
		}
		if ((rt->rt_flags&RTCF_REDIRECTED) || rt->u.dst.expires) {
			unsigned hash = rt_hash_code(rt->key.dst, rt->key.src^(rt->key.oif<<5), rt->key.tos);
#if RT_CACHE_DEBUG >= 1
			printk(KERN_DEBUG "ip_rt_advice: redirect to %u.%u.%u.%u/%02x dropped\n",
				NIPQUAD(rt->rt_dst), rt->key.tos);
#endif
			rt_del(hash, rt);
			return NULL;
		}
	}
	return dst;
}

/*
 * 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 = (struct rtable*)skb->dst;
	struct in_device *in_dev = in_dev_get(rt->u.dst.dev);

	if (!in_dev)
		return;

	if (!IN_DEV_TX_REDIRECTS(in_dev))
		goto out;

	/* No redirected packets during ip_rt_redirect_silence;
	 * reset the algorithm.
	 */
	if (jiffies - rt->u.dst.rate_last > ip_rt_redirect_silence)
		rt->u.dst.rate_tokens = 0;

	/* Too many ignored redirects; do not send anything
	 * set u.dst.rate_last to the last seen redirected packet.
	 */
	if (rt->u.dst.rate_tokens >= ip_rt_redirect_number) {
		rt->u.dst.rate_last = jiffies;
		goto out;
	}

	/* Check for load limit; set rate_last to the latest sent
	 * redirect.
	 */
	if (jiffies - rt->u.dst.rate_last > (ip_rt_redirect_load<<rt->u.dst.rate_tokens)) {
		icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt->rt_gateway);
		rt->u.dst.rate_last = jiffies;
		++rt->u.dst.rate_tokens;
#ifdef CONFIG_IP_ROUTE_VERBOSE
		if (IN_DEV_LOG_MARTIANS(in_dev) &&
		    rt->u.dst.rate_tokens == ip_rt_redirect_number && net_ratelimit())
			printk(KERN_WARNING "host %u.%u.%u.%u/if%d ignores redirects for "
				"%u.%u.%u.%u to %u.%u.%u.%u.\n",
				NIPQUAD(rt->rt_src), rt->rt_iif,
				NIPQUAD(rt->rt_dst), NIPQUAD(rt->rt_gateway));
#endif
	}
out:
        in_dev_put(in_dev);
}

static int ip_error(struct sk_buff *skb)
{
	struct rtable *rt = (struct rtable*)skb->dst;
	unsigned long now;
	int code;

	switch (rt->u.dst.error) {
	case EINVAL:
	default:
		kfree_skb(skb);
		return 0;
	case EHOSTUNREACH:
		code = ICMP_HOST_UNREACH;
		break;
	case ENETUNREACH:
		code = ICMP_NET_UNREACH;
		break;
	case EACCES:
		code = ICMP_PKT_FILTERED;
		break;
	}

	now = jiffies;
	if ((rt->u.dst.rate_tokens += (now - rt->u.dst.rate_last)) > ip_rt_error_burst)
		rt->u.dst.rate_tokens = ip_rt_error_burst;
	rt->u.dst.rate_last = now;
	if (rt->u.dst.rate_tokens >= ip_rt_error_cost) {
		rt->u.dst.rate_tokens -= ip_rt_error_cost;
		icmp_send(skb, ICMP_DEST_UNREACH, code, 0);
	}

	kfree_skb(skb);
	return 0;
} 

/*
 *	The last two values are not from the RFC but
 *	are needed for AMPRnet AX.25 paths.
 */

static 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 < sizeof(mtu_plateau)/sizeof(mtu_plateau[0]); i++)
		if (old_mtu > mtu_plateau[i])
			return mtu_plateau[i];
	return 68;
}

unsigned short ip_rt_frag_needed(struct iphdr *iph, unsigned short new_mtu)
{
	int i;
	unsigned short old_mtu = ntohs(iph->tot_len);
	struct rtable *rth;
	u32  skeys[2] = { iph->saddr, 0, };
	u32  daddr = iph->daddr;
	u8   tos = iph->tos & IPTOS_RT_MASK;
	unsigned short est_mtu = 0;

	if (ipv4_config.no_pmtu_disc)
		return 0;

	for (i=0; i<2; i++) {
		unsigned hash = rt_hash_code(daddr, skeys[i], tos);

		read_lock(&rt_hash_table[hash].lock);
		for (rth = rt_hash_table[hash].chain; rth; rth = rth->u.rt_next) {
			if (rth->key.dst == daddr &&
			    rth->key.src == skeys[i] &&
			    rth->rt_dst == daddr &&
			    rth->rt_src == iph->saddr &&
			    rth->key.tos == tos &&
			    rth->key.iif == 0 &&
			    !(rth->u.dst.mxlock&(1<<RTAX_MTU))) {
				unsigned short mtu = new_mtu;

				if (new_mtu < 68 || new_mtu >= old_mtu) {

					/* BSD 4.2 compatibility hack :-( */
					if (mtu == 0 && old_mtu >= rth->u.dst.pmtu &&
					    old_mtu >= 68 + (iph->ihl<<2))
						old_mtu -= iph->ihl<<2;

					mtu = guess_mtu(old_mtu);
				}
				if (mtu <= rth->u.dst.pmtu) {
					if (mtu < rth->u.dst.pmtu) { 
						dst_confirm(&rth->u.dst);
						if (mtu < ip_rt_min_pmtu) {
							mtu = ip_rt_min_pmtu;
							rth->u.dst.mxlock |= (1<<RTAX_MTU);
						}
						rth->u.dst.pmtu = mtu;
						dst_set_expires(&rth->u.dst, ip_rt_mtu_expires);
					}
					est_mtu = mtu;
				}
			}
		}
		read_unlock(&rt_hash_table[hash].lock);
	}
	return est_mtu ? : new_mtu;
}

void ip_rt_update_pmtu(struct dst_entry *dst, unsigned mtu)
{
	if (dst->pmtu > mtu && mtu >= 68 &&
	    !(dst->mxlock&(1<<RTAX_MTU))) {
		if (mtu < ip_rt_min_pmtu) {
			mtu = ip_rt_min_pmtu;
			dst->mxlock |= (1<<RTAX_MTU);
		}
		dst->pmtu = mtu;
		dst_set_expires(dst, ip_rt_mtu_expires);
	}
}

static struct dst_entry * ipv4_dst_check(struct dst_entry * dst, u32 cookie)
{
	dst_release(dst);
	return NULL;
}

static struct dst_entry * ipv4_dst_reroute(struct dst_entry * dst,
					   struct sk_buff *skb)
{
	return NULL;
}

static void ipv4_dst_destroy(struct dst_entry * dst)
{
	struct rtable *rt = (struct rtable *) dst;
	struct inet_peer *peer = rt->peer;

	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 = (struct rtable *) skb->dst;
	if (rt)
		dst_set_expires(&rt->u.dst, 0);
}

static int ip_rt_bug(struct sk_buff *skb)
{
	printk(KERN_DEBUG "ip_rt_bug: %u.%u.%u.%u -> %u.%u.%u.%u, %s\n",
		NIPQUAD(skb->nh.iph->saddr), NIPQUAD(skb->nh.iph->daddr),
		skb->dev ? skb->dev->name : "?");
	kfree_skb(skb);
	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 rtable *rt)
{
	u32 src;
	struct fib_result res;

	if (rt->key.iif == 0)
		src = rt->rt_src;
	else if (fib_lookup(&rt->key, &res) == 0) {
#ifdef CONFIG_IP_ROUTE_NAT
		if (res.type == RTN_NAT)
			src = inet_select_addr(rt->u.dst.dev, rt->rt_gateway, RT_SCOPE_UNIVERSE);
		else
#endif
			src = FIB_RES_PREFSRC(res);
		fib_res_put(&res);
	} else
		src = inet_select_addr(rt->u.dst.dev, rt->rt_gateway, RT_SCOPE_UNIVERSE);
	memcpy(addr, &src, 4);
}

#ifdef CONFIG_NET_CLS_ROUTE
static void set_class_tag(struct rtable *rt, u32 tag)
{
	if (!(rt->u.dst.tclassid&0xFFFF))
		rt->u.dst.tclassid |= tag&0xFFFF;
	if (!(rt->u.dst.tclassid&0xFFFF0000))
		rt->u.dst.tclassid |= tag&0xFFFF0000;
}
#endif

static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag)
{
	struct fib_info *fi = res->fi;

	if (fi) {
		if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK)
			rt->rt_gateway = FIB_RES_GW(*res);
		memcpy(&rt->u.dst.mxlock, fi->fib_metrics, sizeof(fi->fib_metrics));
		if (fi->fib_mtu == 0) {
			rt->u.dst.pmtu = rt->u.dst.dev->mtu;
			if (rt->u.dst.mxlock&(1<<RTAX_MTU) &&
			    rt->rt_gateway != rt->rt_dst &&
			    rt->u.dst.pmtu > 576)
				rt->u.dst.pmtu = 576;
		}
#ifdef CONFIG_NET_CLS_ROUTE
		rt->u.dst.tclassid = FIB_RES_NH(*res).nh_tclassid;
#endif
	} else {
		rt->u.dst.pmtu	= rt->u.dst.dev->mtu;
	}
	if (rt->u.dst.pmtu > IP_MAX_MTU)
		rt->u.dst.pmtu = IP_MAX_MTU;
	if (rt->u.dst.advmss == 0)
		rt->u.dst.advmss = max(rt->u.dst.dev->mtu-40, ip_rt_min_advmss);
	if (rt->u.dst.advmss > 65535-40)
		rt->u.dst.advmss = 65535-40;

#ifdef CONFIG_NET_CLS_ROUTE
#ifdef CONFIG_IP_MULTIPLE_TABLES
	set_class_tag(rt, fib_rules_tclass(res));
#endif
	set_class_tag(rt, itag);
#endif
        rt->rt_type = res->type;
}

static int
ip_route_input_mc(struct sk_buff *skb, u32 daddr, u32 saddr,
		  u8 tos, struct net_device *dev, int our)
{
	unsigned hash;
	struct rtable *rth;
	u32 spec_dst;
	struct in_device *in_dev = in_dev_get(dev);
	u32 itag = 0;

	/* Primary sanity checks. */

	if (in_dev == NULL)
		return -EINVAL;

	if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr) ||
	    skb->protocol != __constant_htons(ETH_P_IP))
		goto e_inval;

	if (ZERONET(saddr)) {
		if (!LOCAL_MCAST(daddr))
			goto e_inval;
		spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
	} else if (fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, &itag) < 0)
		goto e_inval;

	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	rth->u.dst.output= ip_rt_bug;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
	rth->key.dst	= daddr;
	rth->rt_dst	= daddr;
	rth->key.tos	= tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	rth->key.fwmark	= skb->nfmark;
#endif
	rth->key.src	= saddr;
	rth->rt_src	= saddr;
#ifdef CONFIG_IP_ROUTE_NAT
	rth->rt_dst_map	= daddr;
	rth->rt_src_map	= saddr;
#endif
#ifdef CONFIG_NET_CLS_ROUTE
	rth->u.dst.tclassid = itag;
#endif
	rth->rt_iif	=
	rth->key.iif	= dev->ifindex;
	rth->u.dst.dev	= &loopback_dev;
	dev_hold(rth->u.dst.dev);
	rth->key.oif	= 0;
	rth->rt_gateway	= daddr;
	rth->rt_spec_dst= spec_dst;
	rth->rt_type	= RTN_MULTICAST;
	rth->rt_flags	= RTCF_MULTICAST;
	if (our) {
		rth->u.dst.input= ip_local_deliver;
		rth->rt_flags |= RTCF_LOCAL;
	}

#ifdef CONFIG_IP_MROUTE
	if (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
		rth->u.dst.input = ip_mr_input;
#endif

	in_dev_put(in_dev);
	hash = rt_hash_code(daddr, saddr^(dev->ifindex<<5), tos);
	return rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);

e_nobufs:
	in_dev_put(in_dev);
	return -ENOBUFS;

e_inval:
	in_dev_put(in_dev);
	return -EINVAL;
}

/*
 *	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.
 */

int ip_route_input_slow(struct sk_buff *skb, u32 daddr, u32 saddr,
			u8 tos, struct net_device *dev)
{
	struct rt_key	key;
	struct fib_result res;
	struct in_device *in_dev = in_dev_get(dev);
	struct in_device *out_dev = NULL;
	unsigned	flags = 0;
	u32		itag = 0;
	struct rtable * rth;
	unsigned	hash;
	u32		spec_dst;
	int		err = -EINVAL;
	int		free_res = 0;

	/*
	 *	IP on this device is disabled.
	 */

	if (!in_dev)
		return -EINVAL;

	key.dst = daddr;
	key.src = saddr;
	key.tos = tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	key.fwmark = skb->nfmark;
#endif
	key.iif = dev->ifindex;
	key.oif = 0;
	key.scope = RT_SCOPE_UNIVERSE;

	hash = rt_hash_code(daddr, saddr^(key.iif<<5), tos);

	/* Check for the most weird martians, which can be not detected
	   by fib_lookup.
	 */

	if (MULTICAST(saddr) || BADCLASS(saddr) || LOOPBACK(saddr))
		goto martian_source;

	if (daddr == 0xFFFFFFFF || (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 (ZERONET(saddr))
		goto martian_source;

	if (BADCLASS(daddr) || ZERONET(daddr) || LOOPBACK(daddr))
		goto martian_destination;

	/*
	 *	Now we are ready to route packet.
	 */
	if ((err = fib_lookup(&key, &res)) != 0) {
		if (!IN_DEV_FORWARD(in_dev))
			goto e_inval;
		goto no_route;
	}
	free_res = 1;

#ifdef CONFIG_IP_ROUTE_NAT
	/* Policy is applied before mapping destination,
	   but rerouting after map should be made with old source.
	 */

	if (1) {
		u32 src_map = saddr;
		if (res.r)
			src_map = fib_rules_policy(saddr, &res, &flags);

		if (res.type == RTN_NAT) {
			key.dst = fib_rules_map_destination(daddr, &res);
			fib_res_put(&res);
			free_res = 0;
			if (fib_lookup(&key, &res))
				goto e_inval;
			free_res = 1;
			if (res.type != RTN_UNICAST)
				goto e_inval;
			flags |= RTCF_DNAT;
		}
		key.src = src_map;
	}
#endif

	if (res.type == RTN_BROADCAST)
		goto brd_input;

	if (res.type == RTN_LOCAL) {
		int result;
		result = fib_validate_source(saddr, daddr, tos, loopback_dev.ifindex,
					     dev, &spec_dst, &itag);
		if (result < 0)
			goto martian_source;
		if (result)
			flags |= RTCF_DIRECTSRC;
		spec_dst = daddr;
		goto local_input;
	}

	if (!IN_DEV_FORWARD(in_dev))
		goto e_inval;
	if (res.type != RTN_UNICAST)
		goto martian_destination;

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (res.fi->fib_nhs > 1 && key.oif == 0)
		fib_select_multipath(&key, &res);
#endif
	out_dev = in_dev_get(FIB_RES_DEV(res));
	if (out_dev == NULL) {
		if (net_ratelimit())
			printk(KERN_CRIT "Bug in ip_route_input_slow(). Please, report\n");
		goto e_inval;
	}

	err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(res), dev, &spec_dst, &itag);
	if (err < 0)
		goto martian_source;

	if (err)
		flags |= RTCF_DIRECTSRC;

	if (out_dev == in_dev && err && !(flags&(RTCF_NAT|RTCF_MASQ)) &&
	    (IN_DEV_SHARED_MEDIA(out_dev)
	     || inet_addr_onlink(out_dev, saddr, FIB_RES_GW(res))))
		flags |= RTCF_DOREDIRECT;

	if (skb->protocol != __constant_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.
		 */
		if (out_dev == in_dev && !(flags&RTCF_DNAT))
			goto e_inval;
	}

	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
	rth->key.dst	= daddr;
	rth->rt_dst	= daddr;
	rth->key.tos	= tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	rth->key.fwmark	= skb->nfmark;
#endif
	rth->key.src	= saddr;
	rth->rt_src	= saddr;
	rth->rt_gateway	= daddr;
#ifdef CONFIG_IP_ROUTE_NAT
	rth->rt_src_map	= key.src;
	rth->rt_dst_map	= key.dst;
	if (flags&RTCF_DNAT)
		rth->rt_gateway	= key.dst;
#endif
	rth->rt_iif 	=
	rth->key.iif	= dev->ifindex;
	rth->u.dst.dev	= out_dev->dev;
	dev_hold(rth->u.dst.dev);
	rth->key.oif 	= 0;
	rth->rt_spec_dst= spec_dst;

	rth->u.dst.input = ip_forward;
	rth->u.dst.output = ip_output;

	rt_set_nexthop(rth, &res, itag);

	rth->rt_flags = flags;

#ifdef CONFIG_NET_FASTROUTE
	if (netdev_fastroute && !(flags&(RTCF_NAT|RTCF_MASQ|RTCF_DOREDIRECT))) {
		struct net_device *odev = rth->u.dst.dev;
		if (odev != dev &&
		    dev->accept_fastpath &&
		    odev->mtu >= dev->mtu &&
		    dev->accept_fastpath(dev, &rth->u.dst) == 0)
			rth->rt_flags |= RTCF_FAST;
	}
#endif

intern:
	err = rt_intern_hash(hash, rth, (struct rtable**)&skb->dst);
done:
	in_dev_put(in_dev);
	if (out_dev)
		in_dev_put(out_dev);
	if (free_res)
		fib_res_put(&res);
	return err;

brd_input:
	if (skb->protocol != __constant_htons(ETH_P_IP))
		goto e_inval;

	if (ZERONET(saddr)) {
		spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
	} else {
		err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst, &itag);
		if (err < 0)
			goto martian_source;
		if (err)
			flags |= RTCF_DIRECTSRC;
	}
	flags |= RTCF_BROADCAST;
	res.type = RTN_BROADCAST;

local_input:
	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	rth->u.dst.output= ip_rt_bug;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
	rth->key.dst	= daddr;
	rth->rt_dst	= daddr;
	rth->key.tos	= tos;
#ifdef CONFIG_IP_ROUTE_FWMARK
	rth->key.fwmark	= skb->nfmark;
#endif
	rth->key.src	= saddr;
	rth->rt_src	= saddr;
#ifdef CONFIG_IP_ROUTE_NAT
	rth->rt_dst_map	= key.dst;
	rth->rt_src_map	= key.src;
#endif
#ifdef CONFIG_NET_CLS_ROUTE
	rth->u.dst.tclassid = itag;
#endif
	rth->rt_iif	=
	rth->key.iif	= dev->ifindex;
	rth->u.dst.dev	= &loopback_dev;
	dev_hold(rth->u.dst.dev);
	rth->key.oif 	= 0;
	rth->rt_gateway	= daddr;
	rth->rt_spec_dst= spec_dst;
	rth->u.dst.input= ip_local_deliver;
	rth->rt_flags 	= flags|RTCF_LOCAL;
	if (res.type == RTN_UNREACHABLE) {
		rth->u.dst.input= ip_error;
		rth->u.dst.error= -err;
		rth->rt_flags 	&= ~RTCF_LOCAL;
	}
	rth->rt_type	= res.type;
	goto intern;

no_route:
	spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
	res.type = RTN_UNREACHABLE;
	goto local_input;

	/*
	 *	Do not cache martian addresses: they should be logged (RFC1812)
	 */
martian_destination:
#ifdef CONFIG_IP_ROUTE_VERBOSE
	if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
		printk(KERN_WARNING "martian destination %u.%u.%u.%u from %u.%u.%u.%u, dev %s\n",
			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
#endif
e_inval:
	err = -EINVAL;
	goto done;

e_nobufs:
	err = -ENOBUFS;
	goto done;

martian_source:
#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 %u.%u.%u.%u from %u.%u.%u.%u, on dev %s\n",
			NIPQUAD(daddr), NIPQUAD(saddr), dev->name);
		if (dev->hard_header_len) {
			int i;
			unsigned char *p = skb->mac.raw;
			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
	goto e_inval;
}

int ip_route_input(struct sk_buff *skb, u32 daddr, u32 saddr,
		   u8 tos, struct net_device *dev)
{
	struct rtable * rth;
	unsigned	hash;
	int iif = dev->ifindex;

	tos &= IPTOS_RT_MASK;
	hash = rt_hash_code(daddr, saddr^(iif<<5), tos);

	read_lock(&rt_hash_table[hash].lock);
	for (rth=rt_hash_table[hash].chain; rth; rth=rth->u.rt_next) {
		if (rth->key.dst == daddr &&
		    rth->key.src == saddr &&
		    rth->key.iif == iif &&
		    rth->key.oif == 0 &&
#ifdef CONFIG_IP_ROUTE_FWMARK
		    rth->key.fwmark == skb->nfmark &&
#endif
		    rth->key.tos == tos) {
			rth->u.dst.lastuse = jiffies;
			dst_hold(&rth->u.dst);
			rth->u.dst.__use++;
			read_unlock(&rt_hash_table[hash].lock);
			skb->dst = (struct dst_entry*)rth;
			return 0;
		}
	}
	read_unlock(&rt_hash_table[hash].lock);

	/* 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 (MULTICAST(daddr)) {
		struct in_device *in_dev;

		read_lock(&inetdev_lock);
		if ((in_dev = __in_dev_get(dev)) != NULL) {
			int our = ip_check_mc(in_dev, daddr);
			if (our
#ifdef CONFIG_IP_MROUTE
			    || (!LOCAL_MCAST(daddr) && IN_DEV_MFORWARD(in_dev))
#endif
			    ) {
				read_unlock(&inetdev_lock);
				return ip_route_input_mc(skb, daddr, saddr, tos, dev, our);
			}
		}
		read_unlock(&inetdev_lock);
		return -EINVAL;
	}
	return ip_route_input_slow(skb, daddr, saddr, tos, dev);
}

/*
 * Major route resolver routine.
 */

int ip_route_output_slow(struct rtable **rp, const struct rt_key *oldkey)
{
	struct rt_key key;
	struct fib_result res;
	unsigned flags = 0;
	struct rtable *rth;
	struct net_device *dev_out = NULL;
	unsigned hash;
	int free_res = 0;
	int err;
	u32 tos;

	tos = oldkey->tos & (IPTOS_RT_MASK|RTO_ONLINK);
	key.dst = oldkey->dst;
	key.src = oldkey->src;
	key.tos = tos&IPTOS_RT_MASK;
	key.iif = loopback_dev.ifindex;
	key.oif = oldkey->oif;
#ifdef CONFIG_IP_ROUTE_FWMARK
	key.fwmark = oldkey->fwmark;
#endif
	key.scope = (tos&RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE;
	res.fi = NULL;
#ifdef CONFIG_IP_MULTIPLE_TABLES
	res.r = NULL;
#endif

	if (oldkey->src) {
		if (MULTICAST(oldkey->src)
		    || BADCLASS(oldkey->src)
		    || ZERONET(oldkey->src))
			return -EINVAL;

		/* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */
		dev_out = ip_dev_find(oldkey->src);
		if (dev_out == NULL)
			return -EINVAL;

		/* I removed check for oif == dev_out->oif here.
		   It was wrong by three reasons:
		   1. ip_dev_find(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 (oldkey->oif == 0
		    && (MULTICAST(oldkey->dst) || oldkey->dst == 0xFFFFFFFF)) {
			/* 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.
			 */

			key.oif = dev_out->ifindex;
			goto make_route;
		}
		if (dev_out)
			dev_put(dev_out);
		dev_out = NULL;
	}
	if (oldkey->oif) {
		dev_out = dev_get_by_index(oldkey->oif);
		if (dev_out == NULL)
			return -ENODEV;
		if (__in_dev_get(dev_out) == NULL) {
			dev_put(dev_out);
			return -ENODEV;	/* Wrong error code */
		}

		if (LOCAL_MCAST(oldkey->dst) || oldkey->dst == 0xFFFFFFFF) {
			if (!key.src)
				key.src = inet_select_addr(dev_out, 0, RT_SCOPE_LINK);
			goto make_route;
		}
		if (!key.src) {
			if (MULTICAST(oldkey->dst))
				key.src = inet_select_addr(dev_out, 0, key.scope);
			else if (!oldkey->dst)
				key.src = inet_select_addr(dev_out, 0, RT_SCOPE_HOST);
		}
	}

	if (!key.dst) {
		key.dst = key.src;
		if (!key.dst)
			key.dst = key.src = htonl(INADDR_LOOPBACK);
		if (dev_out)
			dev_put(dev_out);
		dev_out = &loopback_dev;
		dev_hold(dev_out);
		key.oif = loopback_dev.ifindex;
		res.type = RTN_LOCAL;
		flags |= RTCF_LOCAL;
		goto make_route;
	}

	if (fib_lookup(&key, &res)) {
		res.fi = NULL;
		if (oldkey->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 (key.src == 0)
				key.src = inet_select_addr(dev_out, 0, RT_SCOPE_LINK);
			res.type = RTN_UNICAST;
			goto make_route;
		}
		if (dev_out)
			dev_put(dev_out);
		return -ENETUNREACH;
	}
	free_res = 1;

	if (res.type == RTN_NAT)
		goto e_inval;

	if (res.type == RTN_LOCAL) {
		if (!key.src)
			key.src = key.dst;
		if (dev_out)
			dev_put(dev_out);
		dev_out = &loopback_dev;
		dev_hold(dev_out);
		key.oif = dev_out->ifindex;
		if (res.fi)
			fib_info_put(res.fi);
		res.fi = NULL;
		flags |= RTCF_LOCAL;
		goto make_route;
	}

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (res.fi->fib_nhs > 1 && key.oif == 0)
		fib_select_multipath(&key, &res);
	else
#endif
	if (res.prefixlen==0 && res.type == RTN_UNICAST && key.oif == 0)
		fib_select_default(&key, &res);

	if (!key.src)
		key.src = FIB_RES_PREFSRC(res);

	if (dev_out)
		dev_put(dev_out);
	dev_out = FIB_RES_DEV(res);
	dev_hold(dev_out);
	key.oif = dev_out->ifindex;

make_route:
	if (LOOPBACK(key.src) && !(dev_out->flags&IFF_LOOPBACK))
		goto e_inval;

	if (key.dst == 0xFFFFFFFF)
		res.type = RTN_BROADCAST;
	else if (MULTICAST(key.dst))
		res.type = RTN_MULTICAST;
	else if (BADCLASS(key.dst) || ZERONET(key.dst))
		goto e_inval;

	if (dev_out->flags&IFF_LOOPBACK)
		flags |= RTCF_LOCAL;

	if (res.type == RTN_BROADCAST) {
		flags |= RTCF_BROADCAST|RTCF_LOCAL;
		if (res.fi) {
			fib_info_put(res.fi);
			res.fi = NULL;
		}
	} else if (res.type == RTN_MULTICAST) {
		flags |= RTCF_MULTICAST|RTCF_LOCAL;
		read_lock(&inetdev_lock);
		if (!__in_dev_get(dev_out) || !ip_check_mc(__in_dev_get(dev_out), oldkey->dst))
			flags &= ~RTCF_LOCAL;
		read_unlock(&inetdev_lock);
		/* If multicast route do not exist use
		   default one, but do not gateway in this case.
		   Yes, it is hack.
		 */
		if (res.fi && res.prefixlen < 4) {
			fib_info_put(res.fi);
			res.fi = NULL;
		}
	}

	rth = dst_alloc(&ipv4_dst_ops);
	if (!rth)
		goto e_nobufs;

	atomic_set(&rth->u.dst.__refcnt, 1);
	rth->u.dst.flags= DST_HOST;
	rth->key.dst	= oldkey->dst;
	rth->key.tos	= tos;
	rth->key.src	= oldkey->src;
	rth->key.iif	= 0;
	rth->key.oif	= oldkey->oif;
#ifdef CONFIG_IP_ROUTE_FWMARK
	rth->key.fwmark	= oldkey->fwmark;
#endif
	rth->rt_dst	= key.dst;
	rth->rt_src	= key.src;
#ifdef CONFIG_IP_ROUTE_NAT
	rth->rt_dst_map	= key.dst;
	rth->rt_src_map	= key.src;
#endif
	rth->rt_iif	= oldkey->oif ? : dev_out->ifindex;
	rth->u.dst.dev	= dev_out;
	dev_hold(dev_out);
	rth->rt_gateway = key.dst;
	rth->rt_spec_dst= key.src;

	rth->u.dst.output=ip_output;

	if (flags&RTCF_LOCAL) {
		rth->u.dst.input = ip_local_deliver;
		rth->rt_spec_dst = key.dst;
	}
	if (flags&(RTCF_BROADCAST|RTCF_MULTICAST)) {
		rth->rt_spec_dst = key.src;
		if (flags&RTCF_LOCAL && !(dev_out->flags&IFF_LOOPBACK))
			rth->u.dst.output = ip_mc_output;
#ifdef CONFIG_IP_MROUTE
		if (res.type == RTN_MULTICAST) {
			struct in_device *in_dev = in_dev_get(dev_out);
			if (in_dev) {
				if (IN_DEV_MFORWARD(in_dev) && !LOCAL_MCAST(oldkey->dst)) {
					rth->u.dst.input = ip_mr_input;
					rth->u.dst.output = ip_mc_output;
				}
				in_dev_put(in_dev);
			}
		}
#endif
	}

	rt_set_nexthop(rth, &res, 0);

	rth->rt_flags = flags;

	hash = rt_hash_code(oldkey->dst, oldkey->src^(oldkey->oif<<5), tos);
	err = rt_intern_hash(hash, rth, rp);
done:
	if (free_res)
		fib_res_put(&res);
	if (dev_out)
		dev_put(dev_out);
	return err;

e_inval:
	err = -EINVAL;
	goto done;
e_nobufs:
	err = -ENOBUFS;
	goto done;
}

int ip_route_output_key(struct rtable **rp, const struct rt_key *key)
{
	unsigned hash;
	struct rtable *rth;

	hash = rt_hash_code(key->dst, key->src^(key->oif<<5), key->tos);

	read_lock_bh(&rt_hash_table[hash].lock);
	for (rth=rt_hash_table[hash].chain; rth; rth=rth->u.rt_next) {
		if (rth->key.dst == key->dst &&
		    rth->key.src == key->src &&
		    rth->key.iif == 0 &&
		    rth->key.oif == key->oif &&
#ifdef CONFIG_IP_ROUTE_FWMARK
		    rth->key.fwmark == key->fwmark &&
#endif
		    !((rth->key.tos^key->tos)&(IPTOS_RT_MASK|RTO_ONLINK)) &&
		    ((key->tos&RTO_TPROXY) || !(rth->rt_flags&RTCF_TPROXY))
		) {
			rth->u.dst.lastuse = jiffies;
			dst_hold(&rth->u.dst);
			rth->u.dst.__use++;
			read_unlock_bh(&rt_hash_table[hash].lock);
			*rp = rth;
			return 0;
		}
	}
	read_unlock_bh(&rt_hash_table[hash].lock);

	return ip_route_output_slow(rp, key);
}	

#ifdef CONFIG_RTNETLINK

static int rt_fill_info(struct sk_buff *skb, u32 pid, u32 seq, int event, int nowait)
{
	struct rtable *rt = (struct rtable*)skb->dst;
	struct rtmsg *r;
	struct nlmsghdr  *nlh;
	unsigned char	 *b = skb->tail;
	struct rta_cacheinfo ci;
#ifdef CONFIG_IP_MROUTE
	struct rtattr *eptr;
#endif

	nlh = NLMSG_PUT(skb, pid, seq, event, sizeof(*r));
	r = NLMSG_DATA(nlh);
	nlh->nlmsg_flags = (nowait && pid) ? NLM_F_MULTI : 0;
	r->rtm_family = AF_INET;
	r->rtm_dst_len = 32;
	r->rtm_src_len = 0;
	r->rtm_tos = rt->key.tos;
	r->rtm_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;
	RTA_PUT(skb, RTA_DST, 4, &rt->rt_dst);
	if (rt->key.src) {
		r->rtm_src_len = 32;
		RTA_PUT(skb, RTA_SRC, 4, &rt->key.src);
	}
	if (rt->u.dst.dev)
		RTA_PUT(skb, RTA_OIF, sizeof(int), &rt->u.dst.dev->ifindex);
#ifdef CONFIG_NET_CLS_ROUTE
	if (rt->u.dst.tclassid)
		RTA_PUT(skb, RTA_FLOW, 4, &rt->u.dst.tclassid);
#endif
	if (rt->key.iif)
		RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_spec_dst);
	else if (rt->rt_src != rt->key.src)
		RTA_PUT(skb, RTA_PREFSRC, 4, &rt->rt_src);
	if (rt->rt_dst != rt->rt_gateway)
		RTA_PUT(skb, RTA_GATEWAY, 4, &rt->rt_gateway);
	if (rtnetlink_put_metrics(skb, &rt->u.dst.mxlock) < 0)
		goto rtattr_failure;
	ci.rta_lastuse = jiffies - rt->u.dst.lastuse;
	ci.rta_used = rt->u.dst.__use;
	ci.rta_clntref = atomic_read(&rt->u.dst.__refcnt);
	if (rt->u.dst.expires)
		ci.rta_expires = rt->u.dst.expires - jiffies;
	else
		ci.rta_expires = 0;
	ci.rta_error = rt->u.dst.error;
	ci.rta_id = 0;
	ci.rta_ts = 0;
	ci.rta_tsage = 0;
	if (rt->peer) {
		ci.rta_id = rt->peer->ip_id_count;
		if (rt->peer->tcp_ts_stamp) {
			ci.rta_ts = rt->peer->tcp_ts;
			ci.rta_tsage = xtime.tv_sec - rt->peer->tcp_ts_stamp;
		}
	}
#ifdef CONFIG_IP_MROUTE
	eptr = (struct rtattr*)skb->tail;
#endif
	RTA_PUT(skb, RTA_CACHEINFO, sizeof(ci), &ci);
	if (rt->key.iif) {
#ifdef CONFIG_IP_MROUTE
		u32 dst = rt->rt_dst;

		if (MULTICAST(dst) && !LOCAL_MCAST(dst) && ipv4_devconf.mc_forwarding) {
			int err = ipmr_get_route(skb, r, nowait);
			if (err <= 0) {
				if (!nowait) {
					if (err == 0)
						return 0;
					goto nlmsg_failure;
				} else {
					if (err == -EMSGSIZE)
						goto nlmsg_failure;
					((struct rta_cacheinfo*)RTA_DATA(eptr))->rta_error = err;
				}
			}
		} else
#endif
		{
			RTA_PUT(skb, RTA_IIF, sizeof(int), &rt->key.iif);
		}
	}

	nlh->nlmsg_len = skb->tail - b;
	return skb->len;

nlmsg_failure:
rtattr_failure:
	skb_trim(skb, b - skb->data);
	return -1;
}

int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void *arg)
{
	struct rtattr **rta = arg;
	struct rtmsg *rtm = NLMSG_DATA(nlh);
	struct rtable *rt = NULL;
	u32 dst = 0;
	u32 src = 0;
	int iif = 0;
	int err;
	struct sk_buff *skb;

	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (skb == NULL)
		return -ENOBUFS;

	/* Reserve room for dummy headers, this skb can pass
	   through good chunk of routing engine.
	 */
	skb->mac.raw = skb->data;
	skb_reserve(skb, MAX_HEADER + sizeof(struct iphdr));

	if (rta[RTA_SRC-1])
		memcpy(&src, RTA_DATA(rta[RTA_SRC-1]), 4);
	if (rta[RTA_DST-1])
		memcpy(&dst, RTA_DATA(rta[RTA_DST-1]), 4);
	if (rta[RTA_IIF-1])
		memcpy(&iif, RTA_DATA(rta[RTA_IIF-1]), sizeof(int));

	if (iif) {
		struct net_device *dev;
		dev = __dev_get_by_index(iif);
		if (!dev)
			return -ENODEV;
		skb->protocol = __constant_htons(ETH_P_IP);
		skb->dev = dev;
		local_bh_disable();
		err = ip_route_input(skb, dst, src, rtm->rtm_tos, dev);
		local_bh_enable();
		rt = (struct rtable*)skb->dst;
		if (!err && rt->u.dst.error)
			err = -rt->u.dst.error;
	} else {
		int oif = 0;
		if (rta[RTA_OIF-1])
			memcpy(&oif, RTA_DATA(rta[RTA_OIF-1]), sizeof(int));
		err = ip_route_output(&rt, dst, src, rtm->rtm_tos, oif);
	}
	if (err) {
		kfree_skb(skb);
		return err;
	}

	skb->dst = &rt->u.dst;
	if (rtm->rtm_flags & RTM_F_NOTIFY)
		rt->rt_flags |= RTCF_NOTIFY;

	NETLINK_CB(skb).dst_pid = NETLINK_CB(in_skb).pid;

	err = rt_fill_info(skb, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, RTM_NEWROUTE, 0);
	if (err == 0)
		return 0;
	if (err < 0)
		return -EMSGSIZE;

	err = netlink_unicast(rtnl, skb, NETLINK_CB(in_skb).pid, MSG_DONTWAIT);
	if (err < 0)
		return err;
	return 0;
}


int ip_rt_dump(struct sk_buff *skb,  struct netlink_callback *cb)
{
	struct rtable *rt;
	int h, s_h;
	int idx, s_idx;

	s_h = cb->args[0];
	s_idx = idx = cb->args[1];
	for (h=0; h <= rt_hash_mask; h++) {
		if (h < s_h) continue;
		if (h > s_h)
			s_idx = 0;
		read_lock_bh(&rt_hash_table[h].lock);
		for (rt = rt_hash_table[h].chain, idx = 0; rt; rt = rt->u.rt_next, idx++) {
			if (idx < s_idx)
				continue;
			skb->dst = dst_clone(&rt->u.dst);
			if (rt_fill_info(skb, NETLINK_CB(cb->skb).pid,
					 cb->nlh->nlmsg_seq, RTM_NEWROUTE, 1) <= 0) {
				dst_release(xchg(&skb->dst, NULL));
				read_unlock_bh(&rt_hash_table[h].lock);
				goto done;
			}
			dst_release(xchg(&skb->dst, NULL));
		}
		read_unlock_bh(&rt_hash_table[h].lock);
	}

done:
	cb->args[0] = h;
	cb->args[1] = idx;
	return skb->len;
}

#endif /* CONFIG_RTNETLINK */

void ip_rt_multicast_event(struct in_device *in_dev)
{
	rt_cache_flush(0);
}



#ifdef CONFIG_SYSCTL

static int flush_delay;

static
int ipv4_sysctl_rtcache_flush(ctl_table *ctl, int write, struct file * filp,
			      void *buffer, size_t *lenp)
{
	if (write) {
		proc_dointvec(ctl, write, filp, buffer, lenp);
		rt_cache_flush(flush_delay);
		return 0;
	} else
		return -EINVAL;
}

static int ipv4_sysctl_rtcache_flush_strategy(ctl_table *table, int *name, int nlen,
			 void *oldval, size_t *oldlenp,
			 void *newval, size_t newlen, 
			 void **context)
{
	int delay;
	if (newlen != sizeof(int))
		return -EINVAL;
	if (get_user(delay,(int *)newval))
		return -EFAULT; 
	rt_cache_flush(delay); 
	return 0;
}

ctl_table ipv4_route_table[] = {
        {NET_IPV4_ROUTE_FLUSH, "flush",
         &flush_delay, sizeof(int), 0644, NULL,
         &ipv4_sysctl_rtcache_flush, &ipv4_sysctl_rtcache_flush_strategy },
	{NET_IPV4_ROUTE_MIN_DELAY, "min_delay",
         &ip_rt_min_delay, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_MAX_DELAY, "max_delay",
         &ip_rt_max_delay, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_GC_THRESH, "gc_thresh",
         &ipv4_dst_ops.gc_thresh, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_MAX_SIZE, "max_size",
         &ip_rt_max_size, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_GC_MIN_INTERVAL, "gc_min_interval",
         &ip_rt_gc_min_interval, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_GC_TIMEOUT, "gc_timeout",
         &ip_rt_gc_timeout, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_GC_INTERVAL, "gc_interval",
         &ip_rt_gc_interval, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_REDIRECT_LOAD, "redirect_load",
         &ip_rt_redirect_load, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_REDIRECT_NUMBER, "redirect_number",
         &ip_rt_redirect_number, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_REDIRECT_SILENCE, "redirect_silence",
         &ip_rt_redirect_silence, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_ERROR_COST, "error_cost",
         &ip_rt_error_cost, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_ERROR_BURST, "error_burst",
         &ip_rt_error_burst, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_GC_ELASTICITY, "gc_elasticity",
         &ip_rt_gc_elasticity, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_MTU_EXPIRES, "mtu_expires",
         &ip_rt_mtu_expires, sizeof(int), 0644, NULL,
         &proc_dointvec_jiffies, &sysctl_jiffies},
	{NET_IPV4_ROUTE_MIN_PMTU, "min_pmtu",
         &ip_rt_min_pmtu, sizeof(int), 0644, NULL,
         &proc_dointvec},
	{NET_IPV4_ROUTE_MIN_ADVMSS, "min_adv_mss",
         &ip_rt_min_advmss, sizeof(int), 0644, NULL,
         &proc_dointvec},
	 {0}
};
#endif

#ifdef CONFIG_NET_CLS_ROUTE
struct ip_rt_acct *ip_rt_acct;

static int ip_rt_acct_read(char *buffer, char **start, off_t offset,
			   int length, int *eof, void *data)
{
	*start=buffer;

	if ((offset&3) || (length&3))
		return -EIO;

	if (offset + length >= sizeof(struct ip_rt_acct)*256) {
		length = sizeof(struct ip_rt_acct)*256 - offset;
		*eof = 1;
	}
	if (length > 0) {
		u32 *dst = (u32*)buffer;
		u32 *src = (u32*)(((u8*)ip_rt_acct) + offset);

		memcpy(dst, src, length);

#ifdef CONFIG_SMP
		if (smp_num_cpus > 1 || cpu_logical_map(0) != 0) {
			int i;
			int cnt = length/4;

			for (i=0; i<smp_num_cpus; i++) {
				int cpu = cpu_logical_map(i);
				int k;

				if (cpu == 0)
					continue;

				src = (u32*)(((u8*)ip_rt_acct) + offset +
					     cpu*256*sizeof(struct ip_rt_acct));

				for (k=0; k<cnt; k++)
					dst[k] += src[k];
			}
		}
#endif
		return length;
	}
	return 0;
}
#endif

void __init ip_rt_init(void)
{
	int i, order, goal;

#ifdef CONFIG_NET_CLS_ROUTE
	for (order=0;
	     (PAGE_SIZE<<order) < 256*sizeof(ip_rt_acct)*NR_CPUS; order++)
		/* NOTHING */;
	ip_rt_acct = (struct ip_rt_acct *)__get_free_pages(GFP_KERNEL, order);
	if (!ip_rt_acct)
		panic("IP: failed to allocate ip_rt_acct\n");
	memset(ip_rt_acct, 0, PAGE_SIZE<<order);
#endif

	ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache",
						     sizeof(struct rtable),
						     0, SLAB_HWCACHE_ALIGN,
						     NULL, NULL);

	if (!ipv4_dst_ops.kmem_cachep)
		panic("IP: failed to allocate ip_dst_cache\n");

	goal = num_physpages >> (26 - PAGE_SHIFT);

	for (order = 0; (1UL << order) < goal; order++)
		/* NOTHING */;

	do {
		rt_hash_mask = (1UL << order) * PAGE_SIZE /
			sizeof(struct rt_hash_bucket);
		while (rt_hash_mask & (rt_hash_mask-1))
			rt_hash_mask--;
		rt_hash_table = (struct rt_hash_bucket *)
			__get_free_pages(GFP_ATOMIC, order);
	} while (rt_hash_table == NULL && --order > 0);

	if (!rt_hash_table)
		panic("Failed to allocate IP route cache hash table\n");

	printk("IP: routing cache hash table of %u buckets, %ldKbytes\n",
	       rt_hash_mask,
	       (long) (rt_hash_mask*sizeof(struct rt_hash_bucket))/1024);

	for (rt_hash_log=0; (1<<rt_hash_log) != rt_hash_mask; rt_hash_log++)
		/* NOTHING */;

	rt_hash_mask--;
	for (i = 0; i <= rt_hash_mask; i++) {
		rt_hash_table[i].lock = RW_LOCK_UNLOCKED;
		rt_hash_table[i].chain = NULL;
	}

	ipv4_dst_ops.gc_thresh = (rt_hash_mask+1);
	ip_rt_max_size = (rt_hash_mask+1)*16;

	devinet_init();
	ip_fib_init();

	rt_flush_timer.function = rt_run_flush;
	rt_periodic_timer.function = rt_check_expire;

	/* All the timers, started at system startup tend
	   to synchronize. Perturb it a bit.
	 */
	rt_periodic_timer.expires = jiffies + net_random()%ip_rt_gc_interval
		+ ip_rt_gc_interval;
	add_timer(&rt_periodic_timer);

	proc_net_create ("rt_cache", 0, rt_cache_get_info);
#ifdef CONFIG_NET_CLS_ROUTE
	create_proc_read_entry("net/rt_acct", 0, 0, ip_rt_acct_read, NULL);
#endif
}