aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4/fib_frontend.c
blob: b298255f6fdb5fc866c7214f0c04aff264f7e55e (plain) (blame)
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
/*
 * 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.
 *
 *		IPv4 Forwarding Information Base: FIB frontend.
 *
 * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 *
 *		This program is free software; you can redistribute it and/or
 *		modify it under the terms of the GNU General Public License
 *		as published by the Free Software Foundation; either version
 *		2 of the License, or (at your option) any later version.
 */

#include <linux/module.h>
#include <linux/uaccess.h>
#include <linux/bitops.h>
#include <linux/capability.h>
#include <linux/types.h>
#include <linux/kernel.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/inetdevice.h>
#include <linux/netdevice.h>
#include <linux/if_addr.h>
#include <linux/if_arp.h>
#include <linux/skbuff.h>
#include <linux/cache.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/slab.h>

#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/ip_fib.h>
#include <net/rtnetlink.h>
#include <net/xfrm.h>
#include <net/l3mdev.h>
#include <net/lwtunnel.h>
#include <trace/events/fib.h>

#ifndef CONFIG_IP_MULTIPLE_TABLES

static int __net_init fib4_rules_init(struct net *net)
{
	struct fib_table *local_table, *main_table;

	main_table  = fib_trie_table(RT_TABLE_MAIN, NULL);
	if (!main_table)
		return -ENOMEM;

	local_table = fib_trie_table(RT_TABLE_LOCAL, main_table);
	if (!local_table)
		goto fail;

	hlist_add_head_rcu(&local_table->tb_hlist,
				&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
	hlist_add_head_rcu(&main_table->tb_hlist,
				&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
	return 0;

fail:
	fib_free_table(main_table);
	return -ENOMEM;
}

static bool fib4_has_custom_rules(struct net *net)
{
	return false;
}
#else

struct fib_table *fib_new_table(struct net *net, u32 id)
{
	struct fib_table *tb, *alias = NULL;
	unsigned int h;

	if (id == 0)
		id = RT_TABLE_MAIN;
	tb = fib_get_table(net, id);
	if (tb)
		return tb;

	if (id == RT_TABLE_LOCAL && !net->ipv4.fib_has_custom_rules)
		alias = fib_new_table(net, RT_TABLE_MAIN);

	tb = fib_trie_table(id, alias);
	if (!tb)
		return NULL;

	switch (id) {
	case RT_TABLE_MAIN:
		rcu_assign_pointer(net->ipv4.fib_main, tb);
		break;
	case RT_TABLE_DEFAULT:
		rcu_assign_pointer(net->ipv4.fib_default, tb);
		break;
	default:
		break;
	}

	h = id & (FIB_TABLE_HASHSZ - 1);
	hlist_add_head_rcu(&tb->tb_hlist, &net->ipv4.fib_table_hash[h]);
	return tb;
}
EXPORT_SYMBOL_GPL(fib_new_table);

/* caller must hold either rtnl or rcu read lock */
struct fib_table *fib_get_table(struct net *net, u32 id)
{
	struct fib_table *tb;
	struct hlist_head *head;
	unsigned int h;

	if (id == 0)
		id = RT_TABLE_MAIN;
	h = id & (FIB_TABLE_HASHSZ - 1);

	head = &net->ipv4.fib_table_hash[h];
	hlist_for_each_entry_rcu(tb, head, tb_hlist) {
		if (tb->tb_id == id)
			return tb;
	}
	return NULL;
}

static bool fib4_has_custom_rules(struct net *net)
{
	return net->ipv4.fib_has_custom_rules;
}
#endif /* CONFIG_IP_MULTIPLE_TABLES */

static void fib_replace_table(struct net *net, struct fib_table *old,
			      struct fib_table *new)
{
#ifdef CONFIG_IP_MULTIPLE_TABLES
	switch (new->tb_id) {
	case RT_TABLE_MAIN:
		rcu_assign_pointer(net->ipv4.fib_main, new);
		break;
	case RT_TABLE_DEFAULT:
		rcu_assign_pointer(net->ipv4.fib_default, new);
		break;
	default:
		break;
	}

#endif
	/* replace the old table in the hlist */
	hlist_replace_rcu(&old->tb_hlist, &new->tb_hlist);
}

int fib_unmerge(struct net *net)
{
	struct fib_table *old, *new, *main_table;

	/* attempt to fetch local table if it has been allocated */
	old = fib_get_table(net, RT_TABLE_LOCAL);
	if (!old)
		return 0;

	new = fib_trie_unmerge(old);
	if (!new)
		return -ENOMEM;

	/* table is already unmerged */
	if (new == old)
		return 0;

	/* replace merged table with clean table */
	fib_replace_table(net, old, new);
	fib_free_table(old);

	/* attempt to fetch main table if it has been allocated */
	main_table = fib_get_table(net, RT_TABLE_MAIN);
	if (!main_table)
		return 0;

	/* flush local entries from main table */
	fib_table_flush_external(main_table);

	return 0;
}

static void fib_flush(struct net *net)
{
	int flushed = 0;
	unsigned int h;

	for (h = 0; h < FIB_TABLE_HASHSZ; h++) {
		struct hlist_head *head = &net->ipv4.fib_table_hash[h];
		struct hlist_node *tmp;
		struct fib_table *tb;

		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist)
			flushed += fib_table_flush(net, tb, false);
	}

	if (flushed)
		rt_cache_flush(net);
}

/*
 * Find address type as if only "dev" was present in the system. If
 * on_dev is NULL then all interfaces are taken into consideration.
 */
static inline unsigned int __inet_dev_addr_type(struct net *net,
						const struct net_device *dev,
						__be32 addr, u32 tb_id)
{
	struct flowi4		fl4 = { .daddr = addr };
	struct fib_result	res;
	unsigned int ret = RTN_BROADCAST;
	struct fib_table *table;

	if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr))
		return RTN_BROADCAST;
	if (ipv4_is_multicast(addr))
		return RTN_MULTICAST;

	rcu_read_lock();

	table = fib_get_table(net, tb_id);
	if (table) {
		ret = RTN_UNICAST;
		if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) {
			if (!dev || dev == res.fi->fib_dev)
				ret = res.type;
		}
	}

	rcu_read_unlock();
	return ret;
}

unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id)
{
	return __inet_dev_addr_type(net, NULL, addr, tb_id);
}
EXPORT_SYMBOL(inet_addr_type_table);

unsigned int inet_addr_type(struct net *net, __be32 addr)
{
	return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL);
}
EXPORT_SYMBOL(inet_addr_type);

unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev,
				__be32 addr)
{
	u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;

	return __inet_dev_addr_type(net, dev, addr, rt_table);
}
EXPORT_SYMBOL(inet_dev_addr_type);

/* inet_addr_type with dev == NULL but using the table from a dev
 * if one is associated
 */
unsigned int inet_addr_type_dev_table(struct net *net,
				      const struct net_device *dev,
				      __be32 addr)
{
	u32 rt_table = l3mdev_fib_table(dev) ? : RT_TABLE_LOCAL;

	return __inet_dev_addr_type(net, NULL, addr, rt_table);
}
EXPORT_SYMBOL(inet_addr_type_dev_table);

__be32 fib_compute_spec_dst(struct sk_buff *skb)
{
	struct net_device *dev = skb->dev;
	struct in_device *in_dev;
	struct fib_result res;
	struct rtable *rt;
	struct net *net;
	int scope;

	rt = skb_rtable(skb);
	if ((rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL)) ==
	    RTCF_LOCAL)
		return ip_hdr(skb)->daddr;

	in_dev = __in_dev_get_rcu(dev);

	net = dev_net(dev);

	scope = RT_SCOPE_UNIVERSE;
	if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
		bool vmark = in_dev && IN_DEV_SRC_VMARK(in_dev);
		struct flowi4 fl4 = {
			.flowi4_iif = LOOPBACK_IFINDEX,
			.flowi4_oif = l3mdev_master_ifindex_rcu(dev),
			.daddr = ip_hdr(skb)->saddr,
			.flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
			.flowi4_scope = scope,
			.flowi4_mark = vmark ? skb->mark : 0,
		};
		if (!fib_lookup(net, &fl4, &res, 0))
			return fib_result_prefsrc(net, &res);
	} else {
		scope = RT_SCOPE_LINK;
	}

	return inet_select_addr(dev, ip_hdr(skb)->saddr, scope);
}

bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev)
{
	bool dev_match = false;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	int ret;

	for (ret = 0; ret < fi->fib_nhs; ret++) {
		struct fib_nh *nh = &fi->fib_nh[ret];

		if (nh->fib_nh_dev == dev) {
			dev_match = true;
			break;
		} else if (l3mdev_master_ifindex_rcu(nh->fib_nh_dev) == dev->ifindex) {
			dev_match = true;
			break;
		}
	}
#else
	if (fi->fib_nh[0].fib_nh_dev == dev)
		dev_match = true;
#endif

	return dev_match;
}
EXPORT_SYMBOL_GPL(fib_info_nh_uses_dev);

/* Given (packet source, input interface) and optional (dst, oif, tos):
 * - (main) check, that source is valid i.e. not broadcast or our local
 *   address.
 * - figure out what "logical" interface this packet arrived
 *   and calculate "specific destination" address.
 * - check, that packet arrived from expected physical interface.
 * called with rcu_read_lock()
 */
static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
				 u8 tos, int oif, struct net_device *dev,
				 int rpf, struct in_device *idev, u32 *itag)
{
	struct net *net = dev_net(dev);
	struct flow_keys flkeys;
	int ret, no_addr;
	struct fib_result res;
	struct flowi4 fl4;
	bool dev_match;

	fl4.flowi4_oif = 0;
	fl4.flowi4_iif = l3mdev_master_ifindex_rcu(dev);
	if (!fl4.flowi4_iif)
		fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX;
	fl4.daddr = src;
	fl4.saddr = dst;
	fl4.flowi4_tos = tos;
	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
	fl4.flowi4_tun_key.tun_id = 0;
	fl4.flowi4_flags = 0;
	fl4.flowi4_uid = sock_net_uid(net, NULL);

	no_addr = idev->ifa_list == NULL;

	fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0;
	if (!fib4_rules_early_flow_dissect(net, skb, &fl4, &flkeys)) {
		fl4.flowi4_proto = 0;
		fl4.fl4_sport = 0;
		fl4.fl4_dport = 0;
	}

	if (fib_lookup(net, &fl4, &res, 0))
		goto last_resort;
	if (res.type != RTN_UNICAST &&
	    (res.type != RTN_LOCAL || !IN_DEV_ACCEPT_LOCAL(idev)))
		goto e_inval;
	fib_combine_itag(itag, &res);

	dev_match = fib_info_nh_uses_dev(res.fi, dev);
	if (dev_match) {
		ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
		return ret;
	}
	if (no_addr)
		goto last_resort;
	if (rpf == 1)
		goto e_rpf;
	fl4.flowi4_oif = dev->ifindex;

	ret = 0;
	if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
		if (res.type == RTN_UNICAST)
			ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
	}
	return ret;

last_resort:
	if (rpf)
		goto e_rpf;
	*itag = 0;
	return 0;

e_inval:
	return -EINVAL;
e_rpf:
	return -EXDEV;
}

/* Ignore rp_filter for packets protected by IPsec. */
int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst,
			u8 tos, int oif, struct net_device *dev,
			struct in_device *idev, u32 *itag)
{
	int r = secpath_exists(skb) ? 0 : IN_DEV_RPFILTER(idev);
	struct net *net = dev_net(dev);

	if (!r && !fib_num_tclassid_users(net) &&
	    (dev->ifindex != oif || !IN_DEV_TX_REDIRECTS(idev))) {
		if (IN_DEV_ACCEPT_LOCAL(idev))
			goto ok;
		/* with custom local routes in place, checking local addresses
		 * only will be too optimistic, with custom rules, checking
		 * local addresses only can be too strict, e.g. due to vrf
		 */
		if (net->ipv4.fib_has_custom_local_routes ||
		    fib4_has_custom_rules(net))
			goto full_check;
		if (inet_lookup_ifaddr_rcu(net, src))
			return -EINVAL;

ok:
		*itag = 0;
		return 0;
	}

full_check:
	return __fib_validate_source(skb, src, dst, tos, oif, dev, r, idev, itag);
}

static inline __be32 sk_extract_addr(struct sockaddr *addr)
{
	return ((struct sockaddr_in *) addr)->sin_addr.s_addr;
}

static int put_rtax(struct nlattr *mx, int len, int type, u32 value)
{
	struct nlattr *nla;

	nla = (struct nlattr *) ((char *) mx + len);
	nla->nla_type = type;
	nla->nla_len = nla_attr_size(4);
	*(u32 *) nla_data(nla) = value;

	return len + nla_total_size(4);
}

static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
				 struct fib_config *cfg)
{
	__be32 addr;
	int plen;

	memset(cfg, 0, sizeof(*cfg));
	cfg->fc_nlinfo.nl_net = net;

	if (rt->rt_dst.sa_family != AF_INET)
		return -EAFNOSUPPORT;

	/*
	 * Check mask for validity:
	 * a) it must be contiguous.
	 * b) destination must have all host bits clear.
	 * c) if application forgot to set correct family (AF_INET),
	 *    reject request unless it is absolutely clear i.e.
	 *    both family and mask are zero.
	 */
	plen = 32;
	addr = sk_extract_addr(&rt->rt_dst);
	if (!(rt->rt_flags & RTF_HOST)) {
		__be32 mask = sk_extract_addr(&rt->rt_genmask);

		if (rt->rt_genmask.sa_family != AF_INET) {
			if (mask || rt->rt_genmask.sa_family)
				return -EAFNOSUPPORT;
		}

		if (bad_mask(mask, addr))
			return -EINVAL;

		plen = inet_mask_len(mask);
	}

	cfg->fc_dst_len = plen;
	cfg->fc_dst = addr;

	if (cmd != SIOCDELRT) {
		cfg->fc_nlflags = NLM_F_CREATE;
		cfg->fc_protocol = RTPROT_BOOT;
	}

	if (rt->rt_metric)
		cfg->fc_priority = rt->rt_metric - 1;

	if (rt->rt_flags & RTF_REJECT) {
		cfg->fc_scope = RT_SCOPE_HOST;
		cfg->fc_type = RTN_UNREACHABLE;
		return 0;
	}

	cfg->fc_scope = RT_SCOPE_NOWHERE;
	cfg->fc_type = RTN_UNICAST;

	if (rt->rt_dev) {
		char *colon;
		struct net_device *dev;
		char devname[IFNAMSIZ];

		if (copy_from_user(devname, rt->rt_dev, IFNAMSIZ-1))
			return -EFAULT;

		devname[IFNAMSIZ-1] = 0;
		colon = strchr(devname, ':');
		if (colon)
			*colon = 0;
		dev = __dev_get_by_name(net, devname);
		if (!dev)
			return -ENODEV;
		cfg->fc_oif = dev->ifindex;
		cfg->fc_table = l3mdev_fib_table(dev);
		if (colon) {
			struct in_ifaddr *ifa;
			struct in_device *in_dev = __in_dev_get_rtnl(dev);
			if (!in_dev)
				return -ENODEV;
			*colon = ':';
			for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next)
				if (strcmp(ifa->ifa_label, devname) == 0)
					break;
			if (!ifa)
				return -ENODEV;
			cfg->fc_prefsrc = ifa->ifa_local;
		}
	}

	addr = sk_extract_addr(&rt->rt_gateway);
	if (rt->rt_gateway.sa_family == AF_INET && addr) {
		unsigned int addr_type;

		cfg->fc_gw4 = addr;
		cfg->fc_gw_family = AF_INET;
		addr_type = inet_addr_type_table(net, addr, cfg->fc_table);
		if (rt->rt_flags & RTF_GATEWAY &&
		    addr_type == RTN_UNICAST)
			cfg->fc_scope = RT_SCOPE_UNIVERSE;
	}

	if (cmd == SIOCDELRT)
		return 0;

	if (rt->rt_flags & RTF_GATEWAY && !cfg->fc_gw_family)
		return -EINVAL;

	if (cfg->fc_scope == RT_SCOPE_NOWHERE)
		cfg->fc_scope = RT_SCOPE_LINK;

	if (rt->rt_flags & (RTF_MTU | RTF_WINDOW | RTF_IRTT)) {
		struct nlattr *mx;
		int len = 0;

		mx = kcalloc(3, nla_total_size(4), GFP_KERNEL);
		if (!mx)
			return -ENOMEM;

		if (rt->rt_flags & RTF_MTU)
			len = put_rtax(mx, len, RTAX_ADVMSS, rt->rt_mtu - 40);

		if (rt->rt_flags & RTF_WINDOW)
			len = put_rtax(mx, len, RTAX_WINDOW, rt->rt_window);

		if (rt->rt_flags & RTF_IRTT)
			len = put_rtax(mx, len, RTAX_RTT, rt->rt_irtt << 3);

		cfg->fc_mx = mx;
		cfg->fc_mx_len = len;
	}

	return 0;
}

/*
 * Handle IP routing ioctl calls.
 * These are used to manipulate the routing tables
 */
int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt)
{
	struct fib_config cfg;
	int err;

	switch (cmd) {
	case SIOCADDRT:		/* Add a route */
	case SIOCDELRT:		/* Delete a route */
		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
			return -EPERM;

		rtnl_lock();
		err = rtentry_to_fib_config(net, cmd, rt, &cfg);
		if (err == 0) {
			struct fib_table *tb;

			if (cmd == SIOCDELRT) {
				tb = fib_get_table(net, cfg.fc_table);
				if (tb)
					err = fib_table_delete(net, tb, &cfg,
							       NULL);
				else
					err = -ESRCH;
			} else {
				tb = fib_new_table(net, cfg.fc_table);
				if (tb)
					err = fib_table_insert(net, tb,
							       &cfg, NULL);
				else
					err = -ENOBUFS;
			}

			/* allocated by rtentry_to_fib_config() */
			kfree(cfg.fc_mx);
		}
		rtnl_unlock();
		return err;
	}
	return -EINVAL;
}

const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = {
	[RTA_DST]		= { .type = NLA_U32 },
	[RTA_SRC]		= { .type = NLA_U32 },
	[RTA_IIF]		= { .type = NLA_U32 },
	[RTA_OIF]		= { .type = NLA_U32 },
	[RTA_GATEWAY]		= { .type = NLA_U32 },
	[RTA_PRIORITY]		= { .type = NLA_U32 },
	[RTA_PREFSRC]		= { .type = NLA_U32 },
	[RTA_METRICS]		= { .type = NLA_NESTED },
	[RTA_MULTIPATH]		= { .len = sizeof(struct rtnexthop) },
	[RTA_FLOW]		= { .type = NLA_U32 },
	[RTA_ENCAP_TYPE]	= { .type = NLA_U16 },
	[RTA_ENCAP]		= { .type = NLA_NESTED },
	[RTA_UID]		= { .type = NLA_U32 },
	[RTA_MARK]		= { .type = NLA_U32 },
	[RTA_TABLE]		= { .type = NLA_U32 },
	[RTA_IP_PROTO]		= { .type = NLA_U8 },
	[RTA_SPORT]		= { .type = NLA_U16 },
	[RTA_DPORT]		= { .type = NLA_U16 },
};

int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla,
		    struct netlink_ext_ack *extack)
{
	struct rtvia *via;
	int alen;

	if (nla_len(nla) < offsetof(struct rtvia, rtvia_addr)) {
		NL_SET_ERR_MSG(extack, "Invalid attribute length for RTA_VIA");
		return -EINVAL;
	}

	via = nla_data(nla);
	alen = nla_len(nla) - offsetof(struct rtvia, rtvia_addr);

	switch (via->rtvia_family) {
	case AF_INET:
		if (alen != sizeof(__be32)) {
			NL_SET_ERR_MSG(extack, "Invalid IPv4 address in RTA_VIA");
			return -EINVAL;
		}
		cfg->fc_gw_family = AF_INET;
		cfg->fc_gw4 = *((__be32 *)via->rtvia_addr);
		break;
	case AF_INET6:
#ifdef CONFIG_IPV6
		if (alen != sizeof(struct in6_addr)) {
			NL_SET_ERR_MSG(extack, "Invalid IPv6 address in RTA_VIA");
			return -EINVAL;
		}
		cfg->fc_gw_family = AF_INET6;
		cfg->fc_gw6 = *((struct in6_addr *)via->rtvia_addr);
#else
		NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel");
		return -EINVAL;
#endif
		break;
	default:
		NL_SET_ERR_MSG(extack, "Unsupported address family in RTA_VIA");
		return -EINVAL;
	}

	return 0;
}

static int rtm_to_fib_config(struct net *net, struct sk_buff *skb,
			     struct nlmsghdr *nlh, struct fib_config *cfg,
			     struct netlink_ext_ack *extack)
{
	bool has_gw = false, has_via = false;
	struct nlattr *attr;
	int err, remaining;
	struct rtmsg *rtm;

	err = nlmsg_validate_deprecated(nlh, sizeof(*rtm), RTA_MAX,
					rtm_ipv4_policy, extack);
	if (err < 0)
		goto errout;

	memset(cfg, 0, sizeof(*cfg));

	rtm = nlmsg_data(nlh);
	cfg->fc_dst_len = rtm->rtm_dst_len;
	cfg->fc_tos = rtm->rtm_tos;
	cfg->fc_table = rtm->rtm_table;
	cfg->fc_protocol = rtm->rtm_protocol;
	cfg->fc_scope = rtm->rtm_scope;
	cfg->fc_type = rtm->rtm_type;
	cfg->fc_flags = rtm->rtm_flags;
	cfg->fc_nlflags = nlh->nlmsg_flags;

	cfg->fc_nlinfo.portid = NETLINK_CB(skb).portid;
	cfg->fc_nlinfo.nlh = nlh;
	cfg->fc_nlinfo.nl_net = net;

	if (cfg->fc_type > RTN_MAX) {
		NL_SET_ERR_MSG(extack, "Invalid route type");
		err = -EINVAL;
		goto errout;
	}

	nlmsg_for_each_attr(attr, nlh, sizeof(struct rtmsg), remaining) {
		switch (nla_type(attr)) {
		case RTA_DST:
			cfg->fc_dst = nla_get_be32(attr);
			break;
		case RTA_OIF:
			cfg->fc_oif = nla_get_u32(attr);
			break;
		case RTA_GATEWAY:
			has_gw = true;
			cfg->fc_gw4 = nla_get_be32(attr);
			if (cfg->fc_gw4)
				cfg->fc_gw_family = AF_INET;
			break;
		case RTA_VIA:
			has_via = true;
			err = fib_gw_from_via(cfg, attr, extack);
			if (err)
				goto errout;
			break;
		case RTA_PRIORITY:
			cfg->fc_priority = nla_get_u32(attr);
			break;
		case RTA_PREFSRC:
			cfg->fc_prefsrc = nla_get_be32(attr);
			break;
		case RTA_METRICS:
			cfg->fc_mx = nla_data(attr);
			cfg->fc_mx_len = nla_len(attr);
			break;
		case RTA_MULTIPATH:
			err = lwtunnel_valid_encap_type_attr(nla_data(attr),
							     nla_len(attr),
							     extack);
			if (err < 0)
				goto errout;
			cfg->fc_mp = nla_data(attr);
			cfg->fc_mp_len = nla_len(attr);
			break;
		case RTA_FLOW:
			cfg->fc_flow = nla_get_u32(attr);
			break;
		case RTA_TABLE:
			cfg->fc_table = nla_get_u32(attr);
			break;
		case RTA_ENCAP:
			cfg->fc_encap = attr;
			break;
		case RTA_ENCAP_TYPE:
			cfg->fc_encap_type = nla_get_u16(attr);
			err = lwtunnel_valid_encap_type(cfg->fc_encap_type,
							extack);
			if (err < 0)
				goto errout;
			break;
		}
	}

	if (has_gw && has_via) {
		NL_SET_ERR_MSG(extack,
			       "Nexthop configuration can not contain both GATEWAY and VIA");
		goto errout;
	}

	return 0;
errout:
	return err;
}

static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh,
			     struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct fib_config cfg;
	struct fib_table *tb;
	int err;

	err = rtm_to_fib_config(net, skb, nlh, &cfg, extack);
	if (err < 0)
		goto errout;

	tb = fib_get_table(net, cfg.fc_table);
	if (!tb) {
		NL_SET_ERR_MSG(extack, "FIB table does not exist");
		err = -ESRCH;
		goto errout;
	}

	err = fib_table_delete(net, tb, &cfg, extack);
errout:
	return err;
}

static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh,
			     struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct fib_config cfg;
	struct fib_table *tb;
	int err;

	err = rtm_to_fib_config(net, skb, nlh, &cfg, extack);
	if (err < 0)
		goto errout;

	tb = fib_new_table(net, cfg.fc_table);
	if (!tb) {
		err = -ENOBUFS;
		goto errout;
	}

	err = fib_table_insert(net, tb, &cfg, extack);
	if (!err && cfg.fc_type == RTN_LOCAL)
		net->ipv4.fib_has_custom_local_routes = true;
errout:
	return err;
}

int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
			  struct fib_dump_filter *filter,
			  struct netlink_callback *cb)
{
	struct netlink_ext_ack *extack = cb->extack;
	struct nlattr *tb[RTA_MAX + 1];
	struct rtmsg *rtm;
	int err, i;

	ASSERT_RTNL();

	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) {
		NL_SET_ERR_MSG(extack, "Invalid header for FIB dump request");
		return -EINVAL;
	}

	rtm = nlmsg_data(nlh);
	if (rtm->rtm_dst_len || rtm->rtm_src_len  || rtm->rtm_tos   ||
	    rtm->rtm_scope) {
		NL_SET_ERR_MSG(extack, "Invalid values in header for FIB dump request");
		return -EINVAL;
	}
	if (rtm->rtm_flags & ~(RTM_F_CLONED | RTM_F_PREFIX)) {
		NL_SET_ERR_MSG(extack, "Invalid flags for FIB dump request");
		return -EINVAL;
	}

	filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
	filter->flags    = rtm->rtm_flags;
	filter->protocol = rtm->rtm_protocol;
	filter->rt_type  = rtm->rtm_type;
	filter->table_id = rtm->rtm_table;

	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX,
					    rtm_ipv4_policy, extack);
	if (err < 0)
		return err;

	for (i = 0; i <= RTA_MAX; ++i) {
		int ifindex;

		if (!tb[i])
			continue;

		switch (i) {
		case RTA_TABLE:
			filter->table_id = nla_get_u32(tb[i]);
			break;
		case RTA_OIF:
			ifindex = nla_get_u32(tb[i]);
			filter->dev = __dev_get_by_index(net, ifindex);
			if (!filter->dev)
				return -ENODEV;
			break;
		default:
			NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request");
			return -EINVAL;
		}
	}

	if (filter->flags || filter->protocol || filter->rt_type ||
	    filter->table_id || filter->dev) {
		filter->filter_set = 1;
		cb->answer_flags = NLM_F_DUMP_FILTERED;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(ip_valid_fib_dump_req);

static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
{
	const struct nlmsghdr *nlh = cb->nlh;
	struct net *net = sock_net(skb->sk);
	struct fib_dump_filter filter = {};
	unsigned int h, s_h;
	unsigned int e = 0, s_e;
	struct fib_table *tb;
	struct hlist_head *head;
	int dumped = 0, err;

	if (cb->strict_check) {
		err = ip_valid_fib_dump_req(net, nlh, &filter, cb);
		if (err < 0)
			return err;
	} else if (nlmsg_len(nlh) >= sizeof(struct rtmsg)) {
		struct rtmsg *rtm = nlmsg_data(nlh);

		filter.flags = rtm->rtm_flags & (RTM_F_PREFIX | RTM_F_CLONED);
	}

	/* fib entries are never clones and ipv4 does not use prefix flag */
	if (filter.flags & (RTM_F_PREFIX | RTM_F_CLONED))
		return skb->len;

	if (filter.table_id) {
		tb = fib_get_table(net, filter.table_id);
		if (!tb) {
			if (filter.dump_all_families)
				return skb->len;

			NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
			return -ENOENT;
		}

		err = fib_table_dump(tb, skb, cb, &filter);
		return skb->len ? : err;
	}

	s_h = cb->args[0];
	s_e = cb->args[1];

	rcu_read_lock();

	for (h = s_h; h < FIB_TABLE_HASHSZ; h++, s_e = 0) {
		e = 0;
		head = &net->ipv4.fib_table_hash[h];
		hlist_for_each_entry_rcu(tb, head, tb_hlist) {
			if (e < s_e)
				goto next;
			if (dumped)
				memset(&cb->args[2], 0, sizeof(cb->args) -
						 2 * sizeof(cb->args[0]));
			err = fib_table_dump(tb, skb, cb, &filter);
			if (err < 0) {
				if (likely(skb->len))
					goto out;

				goto out_err;
			}
			dumped = 1;
next:
			e++;
		}
	}
out:
	err = skb->len;
out_err:
	rcu_read_unlock();

	cb->args[1] = e;
	cb->args[0] = h;

	return err;
}

/* Prepare and feed intra-kernel routing request.
 * Really, it should be netlink message, but :-( netlink
 * can be not configured, so that we feed it directly
 * to fib engine. It is legal, because all events occur
 * only when netlink is already locked.
 */
static void fib_magic(int cmd, int type, __be32 dst, int dst_len,
		      struct in_ifaddr *ifa, u32 rt_priority)
{
	struct net *net = dev_net(ifa->ifa_dev->dev);
	u32 tb_id = l3mdev_fib_table(ifa->ifa_dev->dev);
	struct fib_table *tb;
	struct fib_config cfg = {
		.fc_protocol = RTPROT_KERNEL,
		.fc_type = type,
		.fc_dst = dst,
		.fc_dst_len = dst_len,
		.fc_priority = rt_priority,
		.fc_prefsrc = ifa->ifa_local,
		.fc_oif = ifa->ifa_dev->dev->ifindex,
		.fc_nlflags = NLM_F_CREATE | NLM_F_APPEND,
		.fc_nlinfo = {
			.nl_net = net,
		},
	};

	if (!tb_id)
		tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL;

	tb = fib_new_table(net, tb_id);
	if (!tb)
		return;

	cfg.fc_table = tb->tb_id;

	if (type != RTN_LOCAL)
		cfg.fc_scope = RT_SCOPE_LINK;
	else
		cfg.fc_scope = RT_SCOPE_HOST;

	if (cmd == RTM_NEWROUTE)
		fib_table_insert(net, tb, &cfg, NULL);
	else
		fib_table_delete(net, tb, &cfg, NULL);
}

void fib_add_ifaddr(struct in_ifaddr *ifa)
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct net_device *dev = in_dev->dev;
	struct in_ifaddr *prim = ifa;
	__be32 mask = ifa->ifa_mask;
	__be32 addr = ifa->ifa_local;
	__be32 prefix = ifa->ifa_address & mask;

	if (ifa->ifa_flags & IFA_F_SECONDARY) {
		prim = inet_ifa_byprefix(in_dev, prefix, mask);
		if (!prim) {
			pr_warn("%s: bug: prim == NULL\n", __func__);
			return;
		}
	}

	fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim, 0);

	if (!(dev->flags & IFF_UP))
		return;

	/* Add broadcast address, if it is explicitly assigned. */
	if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
		fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32,
			  prim, 0);

	if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
	    (prefix != addr || ifa->ifa_prefixlen < 32)) {
		if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
			fib_magic(RTM_NEWROUTE,
				  dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
				  prefix, ifa->ifa_prefixlen, prim,
				  ifa->ifa_rt_priority);

		/* Add network specific broadcasts, when it takes a sense */
		if (ifa->ifa_prefixlen < 31) {
			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32,
				  prim, 0);
			fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
				  32, prim, 0);
		}
	}
}

void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric)
{
	__be32 prefix = ifa->ifa_address & ifa->ifa_mask;
	struct in_device *in_dev = ifa->ifa_dev;
	struct net_device *dev = in_dev->dev;

	if (!(dev->flags & IFF_UP) ||
	    ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) ||
	    ipv4_is_zeronet(prefix) ||
	    prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32)
		return;

	/* add the new */
	fib_magic(RTM_NEWROUTE,
		  dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
		  prefix, ifa->ifa_prefixlen, ifa, new_metric);

	/* delete the old */
	fib_magic(RTM_DELROUTE,
		  dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
		  prefix, ifa->ifa_prefixlen, ifa, ifa->ifa_rt_priority);
}

/* Delete primary or secondary address.
 * Optionally, on secondary address promotion consider the addresses
 * from subnet iprim as deleted, even if they are in device list.
 * In this case the secondary ifa can be in device list.
 */
void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
{
	struct in_device *in_dev = ifa->ifa_dev;
	struct net_device *dev = in_dev->dev;
	struct in_ifaddr *ifa1;
	struct in_ifaddr *prim = ifa, *prim1 = NULL;
	__be32 brd = ifa->ifa_address | ~ifa->ifa_mask;
	__be32 any = ifa->ifa_address & ifa->ifa_mask;
#define LOCAL_OK	1
#define BRD_OK		2
#define BRD0_OK		4
#define BRD1_OK		8
	unsigned int ok = 0;
	int subnet = 0;		/* Primary network */
	int gone = 1;		/* Address is missing */
	int same_prefsrc = 0;	/* Another primary with same IP */

	if (ifa->ifa_flags & IFA_F_SECONDARY) {
		prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
		if (!prim) {
			/* if the device has been deleted, we don't perform
			 * address promotion
			 */
			if (!in_dev->dead)
				pr_warn("%s: bug: prim == NULL\n", __func__);
			return;
		}
		if (iprim && iprim != prim) {
			pr_warn("%s: bug: iprim != prim\n", __func__);
			return;
		}
	} else if (!ipv4_is_zeronet(any) &&
		   (any != ifa->ifa_local || ifa->ifa_prefixlen < 32)) {
		if (!(ifa->ifa_flags & IFA_F_NOPREFIXROUTE))
			fib_magic(RTM_DELROUTE,
				  dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST,
				  any, ifa->ifa_prefixlen, prim, 0);
		subnet = 1;
	}

	if (in_dev->dead)
		goto no_promotions;

	/* Deletion is more complicated than add.
	 * We should take care of not to delete too much :-)
	 *
	 * Scan address list to be sure that addresses are really gone.
	 */

	for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) {
		if (ifa1 == ifa) {
			/* promotion, keep the IP */
			gone = 0;
			continue;
		}
		/* Ignore IFAs from our subnet */
		if (iprim && ifa1->ifa_mask == iprim->ifa_mask &&
		    inet_ifa_match(ifa1->ifa_address, iprim))
			continue;

		/* Ignore ifa1 if it uses different primary IP (prefsrc) */
		if (ifa1->ifa_flags & IFA_F_SECONDARY) {
			/* Another address from our subnet? */
			if (ifa1->ifa_mask == prim->ifa_mask &&
			    inet_ifa_match(ifa1->ifa_address, prim))
				prim1 = prim;
			else {
				/* We reached the secondaries, so
				 * same_prefsrc should be determined.
				 */
				if (!same_prefsrc)
					continue;
				/* Search new prim1 if ifa1 is not
				 * using the current prim1
				 */
				if (!prim1 ||
				    ifa1->ifa_mask != prim1->ifa_mask ||
				    !inet_ifa_match(ifa1->ifa_address, prim1))
					prim1 = inet_ifa_byprefix(in_dev,
							ifa1->ifa_address,
							ifa1->ifa_mask);
				if (!prim1)
					continue;
				if (prim1->ifa_local != prim->ifa_local)
					continue;
			}
		} else {
			if (prim->ifa_local != ifa1->ifa_local)
				continue;
			prim1 = ifa1;
			if (prim != prim1)
				same_prefsrc = 1;
		}
		if (ifa->ifa_local == ifa1->ifa_local)
			ok |= LOCAL_OK;
		if (ifa->ifa_broadcast == ifa1->ifa_broadcast)
			ok |= BRD_OK;
		if (brd == ifa1->ifa_broadcast)
			ok |= BRD1_OK;
		if (any == ifa1->ifa_broadcast)
			ok |= BRD0_OK;
		/* primary has network specific broadcasts */
		if (prim1 == ifa1 && ifa1->ifa_prefixlen < 31) {
			__be32 brd1 = ifa1->ifa_address | ~ifa1->ifa_mask;
			__be32 any1 = ifa1->ifa_address & ifa1->ifa_mask;

			if (!ipv4_is_zeronet(any1)) {
				if (ifa->ifa_broadcast == brd1 ||
				    ifa->ifa_broadcast == any1)
					ok |= BRD_OK;
				if (brd == brd1 || brd == any1)
					ok |= BRD1_OK;
				if (any == brd1 || any == any1)
					ok |= BRD0_OK;
			}
		}
	}

no_promotions:
	if (!(ok & BRD_OK))
		fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32,
			  prim, 0);
	if (subnet && ifa->ifa_prefixlen < 31) {
		if (!(ok & BRD1_OK))
			fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32,
				  prim, 0);
		if (!(ok & BRD0_OK))
			fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32,
				  prim, 0);
	}
	if (!(ok & LOCAL_OK)) {
		unsigned int addr_type;

		fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim, 0);

		/* Check, that this local address finally disappeared. */
		addr_type = inet_addr_type_dev_table(dev_net(dev), dev,
						     ifa->ifa_local);
		if (gone && addr_type != RTN_LOCAL) {
			/* And the last, but not the least thing.
			 * We must flush stray FIB entries.
			 *
			 * First of all, we scan fib_info list searching
			 * for stray nexthop entries, then ignite fib_flush.
			 */
			if (fib_sync_down_addr(dev, ifa->ifa_local))
				fib_flush(dev_net(dev));
		}
	}
#undef LOCAL_OK
#undef BRD_OK
#undef BRD0_OK
#undef BRD1_OK
}

static void nl_fib_lookup(struct net *net, struct fib_result_nl *frn)
{

	struct fib_result       res;
	struct flowi4           fl4 = {
		.flowi4_mark = frn->fl_mark,
		.daddr = frn->fl_addr,
		.flowi4_tos = frn->fl_tos,
		.flowi4_scope = frn->fl_scope,
	};
	struct fib_table *tb;

	rcu_read_lock();

	tb = fib_get_table(net, frn->tb_id_in);

	frn->err = -ENOENT;
	if (tb) {
		local_bh_disable();

		frn->tb_id = tb->tb_id;
		frn->err = fib_table_lookup(tb, &fl4, &res, FIB_LOOKUP_NOREF);

		if (!frn->err) {
			frn->prefixlen = res.prefixlen;
			frn->nh_sel = res.nh_sel;
			frn->type = res.type;
			frn->scope = res.scope;
		}
		local_bh_enable();
	}

	rcu_read_unlock();
}

static void nl_fib_input(struct sk_buff *skb)
{
	struct net *net;
	struct fib_result_nl *frn;
	struct nlmsghdr *nlh;
	u32 portid;

	net = sock_net(skb->sk);
	nlh = nlmsg_hdr(skb);
	if (skb->len < nlmsg_total_size(sizeof(*frn)) ||
	    skb->len < nlh->nlmsg_len ||
	    nlmsg_len(nlh) < sizeof(*frn))
		return;

	skb = netlink_skb_clone(skb, GFP_KERNEL);
	if (!skb)
		return;
	nlh = nlmsg_hdr(skb);

	frn = (struct fib_result_nl *) nlmsg_data(nlh);
	nl_fib_lookup(net, frn);

	portid = NETLINK_CB(skb).portid;      /* netlink portid */
	NETLINK_CB(skb).portid = 0;        /* from kernel */
	NETLINK_CB(skb).dst_group = 0;  /* unicast */
	netlink_unicast(net->ipv4.fibnl, skb, portid, MSG_DONTWAIT);
}

static int __net_init nl_fib_lookup_init(struct net *net)
{
	struct sock *sk;
	struct netlink_kernel_cfg cfg = {
		.input	= nl_fib_input,
	};

	sk = netlink_kernel_create(net, NETLINK_FIB_LOOKUP, &cfg);
	if (!sk)
		return -EAFNOSUPPORT;
	net->ipv4.fibnl = sk;
	return 0;
}

static void nl_fib_lookup_exit(struct net *net)
{
	netlink_kernel_release(net->ipv4.fibnl);
	net->ipv4.fibnl = NULL;
}

static void fib_disable_ip(struct net_device *dev, unsigned long event,
			   bool force)
{
	if (fib_sync_down_dev(dev, event, force))
		fib_flush(dev_net(dev));
	else
		rt_cache_flush(dev_net(dev));
	arp_ifdown(dev);
}

static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct in_ifaddr *ifa = (struct in_ifaddr *)ptr;
	struct net_device *dev = ifa->ifa_dev->dev;
	struct net *net = dev_net(dev);

	switch (event) {
	case NETDEV_UP:
		fib_add_ifaddr(ifa);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		fib_sync_up(dev, RTNH_F_DEAD);
#endif
		atomic_inc(&net->ipv4.dev_addr_genid);
		rt_cache_flush(dev_net(dev));
		break;
	case NETDEV_DOWN:
		fib_del_ifaddr(ifa, NULL);
		atomic_inc(&net->ipv4.dev_addr_genid);
		if (!ifa->ifa_dev->ifa_list) {
			/* Last address was deleted from this interface.
			 * Disable IP.
			 */
			fib_disable_ip(dev, event, true);
		} else {
			rt_cache_flush(dev_net(dev));
		}
		break;
	}
	return NOTIFY_DONE;
}

static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
	struct netdev_notifier_changeupper_info *upper_info = ptr;
	struct netdev_notifier_info_ext *info_ext = ptr;
	struct in_device *in_dev;
	struct net *net = dev_net(dev);
	unsigned int flags;

	if (event == NETDEV_UNREGISTER) {
		fib_disable_ip(dev, event, true);
		rt_flush_dev(dev);
		return NOTIFY_DONE;
	}

	in_dev = __in_dev_get_rtnl(dev);
	if (!in_dev)
		return NOTIFY_DONE;

	switch (event) {
	case NETDEV_UP:
		for_ifa(in_dev) {
			fib_add_ifaddr(ifa);
		} endfor_ifa(in_dev);
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		fib_sync_up(dev, RTNH_F_DEAD);
#endif
		atomic_inc(&net->ipv4.dev_addr_genid);
		rt_cache_flush(net);
		break;
	case NETDEV_DOWN:
		fib_disable_ip(dev, event, false);
		break;
	case NETDEV_CHANGE:
		flags = dev_get_flags(dev);
		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
			fib_sync_up(dev, RTNH_F_LINKDOWN);
		else
			fib_sync_down_dev(dev, event, false);
		rt_cache_flush(net);
		break;
	case NETDEV_CHANGEMTU:
		fib_sync_mtu(dev, info_ext->ext.mtu);
		rt_cache_flush(net);
		break;
	case NETDEV_CHANGEUPPER:
		upper_info = ptr;
		/* flush all routes if dev is linked to or unlinked from
		 * an L3 master device (e.g., VRF)
		 */
		if (upper_info->upper_dev &&
		    netif_is_l3_master(upper_info->upper_dev))
			fib_disable_ip(dev, NETDEV_DOWN, true);
		break;
	}
	return NOTIFY_DONE;
}

static struct notifier_block fib_inetaddr_notifier = {
	.notifier_call = fib_inetaddr_event,
};

static struct notifier_block fib_netdev_notifier = {
	.notifier_call = fib_netdev_event,
};

static int __net_init ip_fib_net_init(struct net *net)
{
	int err;
	size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ;

	err = fib4_notifier_init(net);
	if (err)
		return err;

	/* Avoid false sharing : Use at least a full cache line */
	size = max_t(size_t, size, L1_CACHE_BYTES);

	net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL);
	if (!net->ipv4.fib_table_hash) {
		err = -ENOMEM;
		goto err_table_hash_alloc;
	}

	err = fib4_rules_init(net);
	if (err < 0)
		goto err_rules_init;
	return 0;

err_rules_init:
	kfree(net->ipv4.fib_table_hash);
err_table_hash_alloc:
	fib4_notifier_exit(net);
	return err;
}

static void ip_fib_net_exit(struct net *net)
{
	int i;

	rtnl_lock();
#ifdef CONFIG_IP_MULTIPLE_TABLES
	RCU_INIT_POINTER(net->ipv4.fib_main, NULL);
	RCU_INIT_POINTER(net->ipv4.fib_default, NULL);
#endif
	/* Destroy the tables in reverse order to guarantee that the
	 * local table, ID 255, is destroyed before the main table, ID
	 * 254. This is necessary as the local table may contain
	 * references to data contained in the main table.
	 */
	for (i = FIB_TABLE_HASHSZ - 1; i >= 0; i--) {
		struct hlist_head *head = &net->ipv4.fib_table_hash[i];
		struct hlist_node *tmp;
		struct fib_table *tb;

		hlist_for_each_entry_safe(tb, tmp, head, tb_hlist) {
			hlist_del(&tb->tb_hlist);
			fib_table_flush(net, tb, true);
			fib_free_table(tb);
		}
	}

#ifdef CONFIG_IP_MULTIPLE_TABLES
	fib4_rules_exit(net);
#endif
	rtnl_unlock();
	kfree(net->ipv4.fib_table_hash);
	fib4_notifier_exit(net);
}

static int __net_init fib_net_init(struct net *net)
{
	int error;

#ifdef CONFIG_IP_ROUTE_CLASSID
	net->ipv4.fib_num_tclassid_users = 0;
#endif
	error = ip_fib_net_init(net);
	if (error < 0)
		goto out;
	error = nl_fib_lookup_init(net);
	if (error < 0)
		goto out_nlfl;
	error = fib_proc_init(net);
	if (error < 0)
		goto out_proc;
out:
	return error;

out_proc:
	nl_fib_lookup_exit(net);
out_nlfl:
	ip_fib_net_exit(net);
	goto out;
}

static void __net_exit fib_net_exit(struct net *net)
{
	fib_proc_exit(net);
	nl_fib_lookup_exit(net);
	ip_fib_net_exit(net);
}

static struct pernet_operations fib_net_ops = {
	.init = fib_net_init,
	.exit = fib_net_exit,
};

void __init ip_fib_init(void)
{
	fib_trie_init();

	register_pernet_subsys(&fib_net_ops);

	register_netdevice_notifier(&fib_netdev_notifier);
	register_inetaddr_notifier(&fib_inetaddr_notifier);

	rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL, 0);
	rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL, 0);
	rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib, 0);
}