summaryrefslogtreecommitdiff
path: root/net/ipv4/fib_semantics.c
blob: e9f56225e53fde93a5470ee32c26b21b99ca4655 (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
/*
 * 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: semantics.
 *
 * 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 <asm/uaccess.h>
#include <linux/bitops.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/jiffies.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_arp.h>
#include <linux/proc_fs.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/slab.h>

#include <net/arp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/tcp.h>
#include <net/sock.h>
#include <net/ip_fib.h>
#include <net/netlink.h>
#include <net/nexthop.h>
#include <net/lwtunnel.h>

#include "fib_lookup.h"

static DEFINE_SPINLOCK(fib_info_lock);
static struct hlist_head *fib_info_hash;
static struct hlist_head *fib_info_laddrhash;
static unsigned int fib_info_hash_size;
static unsigned int fib_info_cnt;

#define DEVINDEX_HASHBITS 8
#define DEVINDEX_HASHSIZE (1U << DEVINDEX_HASHBITS)
static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE];

#ifdef CONFIG_IP_ROUTE_MULTIPATH
u32 fib_multipath_secret __read_mostly;

#define for_nexthops(fi) {						\
	int nhsel; const struct fib_nh *nh;				\
	for (nhsel = 0, nh = (fi)->fib_nh;				\
	     nhsel < (fi)->fib_nhs;					\
	     nh++, nhsel++)

#define change_nexthops(fi) {						\
	int nhsel; struct fib_nh *nexthop_nh;				\
	for (nhsel = 0,	nexthop_nh = (struct fib_nh *)((fi)->fib_nh);	\
	     nhsel < (fi)->fib_nhs;					\
	     nexthop_nh++, nhsel++)

#else /* CONFIG_IP_ROUTE_MULTIPATH */

/* Hope, that gcc will optimize it to get rid of dummy loop */

#define for_nexthops(fi) {						\
	int nhsel; const struct fib_nh *nh = (fi)->fib_nh;		\
	for (nhsel = 0; nhsel < 1; nhsel++)

#define change_nexthops(fi) {						\
	int nhsel;							\
	struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh);	\
	for (nhsel = 0; nhsel < 1; nhsel++)

#endif /* CONFIG_IP_ROUTE_MULTIPATH */

#define endfor_nexthops(fi) }


const struct fib_prop fib_props[RTN_MAX + 1] = {
	[RTN_UNSPEC] = {
		.error	= 0,
		.scope	= RT_SCOPE_NOWHERE,
	},
	[RTN_UNICAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_LOCAL] = {
		.error	= 0,
		.scope	= RT_SCOPE_HOST,
	},
	[RTN_BROADCAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_LINK,
	},
	[RTN_ANYCAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_LINK,
	},
	[RTN_MULTICAST] = {
		.error	= 0,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_BLACKHOLE] = {
		.error	= -EINVAL,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_UNREACHABLE] = {
		.error	= -EHOSTUNREACH,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_PROHIBIT] = {
		.error	= -EACCES,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_THROW] = {
		.error	= -EAGAIN,
		.scope	= RT_SCOPE_UNIVERSE,
	},
	[RTN_NAT] = {
		.error	= -EINVAL,
		.scope	= RT_SCOPE_NOWHERE,
	},
	[RTN_XRESOLVE] = {
		.error	= -EINVAL,
		.scope	= RT_SCOPE_NOWHERE,
	},
};

static void rt_fibinfo_free(struct rtable __rcu **rtp)
{
	struct rtable *rt = rcu_dereference_protected(*rtp, 1);

	if (!rt)
		return;

	/* Not even needed : RCU_INIT_POINTER(*rtp, NULL);
	 * because we waited an RCU grace period before calling
	 * free_fib_info_rcu()
	 */

	dst_free(&rt->dst);
}

static void free_nh_exceptions(struct fib_nh *nh)
{
	struct fnhe_hash_bucket *hash;
	int i;

	hash = rcu_dereference_protected(nh->nh_exceptions, 1);
	if (!hash)
		return;
	for (i = 0; i < FNHE_HASH_SIZE; i++) {
		struct fib_nh_exception *fnhe;

		fnhe = rcu_dereference_protected(hash[i].chain, 1);
		while (fnhe) {
			struct fib_nh_exception *next;
			
			next = rcu_dereference_protected(fnhe->fnhe_next, 1);

			rt_fibinfo_free(&fnhe->fnhe_rth_input);
			rt_fibinfo_free(&fnhe->fnhe_rth_output);

			kfree(fnhe);

			fnhe = next;
		}
	}
	kfree(hash);
}

static void rt_fibinfo_free_cpus(struct rtable __rcu * __percpu *rtp)
{
	int cpu;

	if (!rtp)
		return;

	for_each_possible_cpu(cpu) {
		struct rtable *rt;

		rt = rcu_dereference_protected(*per_cpu_ptr(rtp, cpu), 1);
		if (rt)
			dst_free(&rt->dst);
	}
	free_percpu(rtp);
}

/* Release a nexthop info record */
static void free_fib_info_rcu(struct rcu_head *head)
{
	struct fib_info *fi = container_of(head, struct fib_info, rcu);

	change_nexthops(fi) {
		if (nexthop_nh->nh_dev)
			dev_put(nexthop_nh->nh_dev);
		lwtstate_put(nexthop_nh->nh_lwtstate);
		free_nh_exceptions(nexthop_nh);
		rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output);
		rt_fibinfo_free(&nexthop_nh->nh_rth_input);
	} endfor_nexthops(fi);

	if (fi->fib_metrics != (u32 *) dst_default_metrics)
		kfree(fi->fib_metrics);
	kfree(fi);
}

void free_fib_info(struct fib_info *fi)
{
	if (fi->fib_dead == 0) {
		pr_warn("Freeing alive fib_info %p\n", fi);
		return;
	}
	fib_info_cnt--;
#ifdef CONFIG_IP_ROUTE_CLASSID
	change_nexthops(fi) {
		if (nexthop_nh->nh_tclassid)
			fi->fib_net->ipv4.fib_num_tclassid_users--;
	} endfor_nexthops(fi);
#endif
	call_rcu(&fi->rcu, free_fib_info_rcu);
}

void fib_release_info(struct fib_info *fi)
{
	spin_lock_bh(&fib_info_lock);
	if (fi && --fi->fib_treeref == 0) {
		hlist_del(&fi->fib_hash);
		if (fi->fib_prefsrc)
			hlist_del(&fi->fib_lhash);
		change_nexthops(fi) {
			if (!nexthop_nh->nh_dev)
				continue;
			hlist_del(&nexthop_nh->nh_hash);
		} endfor_nexthops(fi)
		fi->fib_dead = 1;
		fib_info_put(fi);
	}
	spin_unlock_bh(&fib_info_lock);
}

static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi)
{
	const struct fib_nh *onh = ofi->fib_nh;

	for_nexthops(fi) {
		if (nh->nh_oif != onh->nh_oif ||
		    nh->nh_gw  != onh->nh_gw ||
		    nh->nh_scope != onh->nh_scope ||
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		    nh->nh_weight != onh->nh_weight ||
#endif
#ifdef CONFIG_IP_ROUTE_CLASSID
		    nh->nh_tclassid != onh->nh_tclassid ||
#endif
		    lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) ||
		    ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK))
			return -1;
		onh++;
	} endfor_nexthops(fi);
	return 0;
}

static inline unsigned int fib_devindex_hashfn(unsigned int val)
{
	unsigned int mask = DEVINDEX_HASHSIZE - 1;

	return (val ^
		(val >> DEVINDEX_HASHBITS) ^
		(val >> (DEVINDEX_HASHBITS * 2))) & mask;
}

static inline unsigned int fib_info_hashfn(const struct fib_info *fi)
{
	unsigned int mask = (fib_info_hash_size - 1);
	unsigned int val = fi->fib_nhs;

	val ^= (fi->fib_protocol << 8) | fi->fib_scope;
	val ^= (__force u32)fi->fib_prefsrc;
	val ^= fi->fib_priority;
	for_nexthops(fi) {
		val ^= fib_devindex_hashfn(nh->nh_oif);
	} endfor_nexthops(fi)

	return (val ^ (val >> 7) ^ (val >> 12)) & mask;
}

static struct fib_info *fib_find_info(const struct fib_info *nfi)
{
	struct hlist_head *head;
	struct fib_info *fi;
	unsigned int hash;

	hash = fib_info_hashfn(nfi);
	head = &fib_info_hash[hash];

	hlist_for_each_entry(fi, head, fib_hash) {
		if (!net_eq(fi->fib_net, nfi->fib_net))
			continue;
		if (fi->fib_nhs != nfi->fib_nhs)
			continue;
		if (nfi->fib_protocol == fi->fib_protocol &&
		    nfi->fib_scope == fi->fib_scope &&
		    nfi->fib_prefsrc == fi->fib_prefsrc &&
		    nfi->fib_priority == fi->fib_priority &&
		    nfi->fib_type == fi->fib_type &&
		    memcmp(nfi->fib_metrics, fi->fib_metrics,
			   sizeof(u32) * RTAX_MAX) == 0 &&
		    !((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_COMPARE_MASK) &&
		    (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0))
			return fi;
	}

	return NULL;
}

/* Check, that the gateway is already configured.
 * Used only by redirect accept routine.
 */
int ip_fib_check_default(__be32 gw, struct net_device *dev)
{
	struct hlist_head *head;
	struct fib_nh *nh;
	unsigned int hash;

	spin_lock(&fib_info_lock);

	hash = fib_devindex_hashfn(dev->ifindex);
	head = &fib_info_devhash[hash];
	hlist_for_each_entry(nh, head, nh_hash) {
		if (nh->nh_dev == dev &&
		    nh->nh_gw == gw &&
		    !(nh->nh_flags & RTNH_F_DEAD)) {
			spin_unlock(&fib_info_lock);
			return 0;
		}
	}

	spin_unlock(&fib_info_lock);

	return -1;
}

static inline size_t fib_nlmsg_size(struct fib_info *fi)
{
	size_t payload = NLMSG_ALIGN(sizeof(struct rtmsg))
			 + nla_total_size(4) /* RTA_TABLE */
			 + nla_total_size(4) /* RTA_DST */
			 + nla_total_size(4) /* RTA_PRIORITY */
			 + nla_total_size(4) /* RTA_PREFSRC */
			 + nla_total_size(TCP_CA_NAME_MAX); /* RTAX_CC_ALGO */

	/* space for nested metrics */
	payload += nla_total_size((RTAX_MAX * nla_total_size(4)));

	if (fi->fib_nhs) {
		size_t nh_encapsize = 0;
		/* Also handles the special case fib_nhs == 1 */

		/* each nexthop is packed in an attribute */
		size_t nhsize = nla_total_size(sizeof(struct rtnexthop));

		/* may contain flow and gateway attribute */
		nhsize += 2 * nla_total_size(4);

		/* grab encap info */
		for_nexthops(fi) {
			if (nh->nh_lwtstate) {
				/* RTA_ENCAP_TYPE */
				nh_encapsize += lwtunnel_get_encap_size(
						nh->nh_lwtstate);
				/* RTA_ENCAP */
				nh_encapsize +=  nla_total_size(2);
			}
		} endfor_nexthops(fi);

		/* all nexthops are packed in a nested attribute */
		payload += nla_total_size((fi->fib_nhs * nhsize) +
					  nh_encapsize);

	}

	return payload;
}

void rtmsg_fib(int event, __be32 key, struct fib_alias *fa,
	       int dst_len, u32 tb_id, const struct nl_info *info,
	       unsigned int nlm_flags)
{
	struct sk_buff *skb;
	u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
	int err = -ENOBUFS;

	skb = nlmsg_new(fib_nlmsg_size(fa->fa_info), GFP_KERNEL);
	if (!skb)
		goto errout;

	err = fib_dump_info(skb, info->portid, seq, event, tb_id,
			    fa->fa_type, key, dst_len,
			    fa->fa_tos, fa->fa_info, nlm_flags);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in fib_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}
	rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_IPV4_ROUTE,
		    info->nlh, GFP_KERNEL);
	return;
errout:
	if (err < 0)
		rtnl_set_sk_err(info->nl_net, RTNLGRP_IPV4_ROUTE, err);
}

static int fib_detect_death(struct fib_info *fi, int order,
			    struct fib_info **last_resort, int *last_idx,
			    int dflt)
{
	struct neighbour *n;
	int state = NUD_NONE;

	n = neigh_lookup(&arp_tbl, &fi->fib_nh[0].nh_gw, fi->fib_dev);
	if (n) {
		state = n->nud_state;
		neigh_release(n);
	} else {
		return 0;
	}
	if (state == NUD_REACHABLE)
		return 0;
	if ((state & NUD_VALID) && order != dflt)
		return 0;
	if ((state & NUD_VALID) ||
	    (*last_idx < 0 && order > dflt && state != NUD_INCOMPLETE)) {
		*last_resort = fi;
		*last_idx = order;
	}
	return 1;
}

#ifdef CONFIG_IP_ROUTE_MULTIPATH

static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining)
{
	int nhs = 0;

	while (rtnh_ok(rtnh, remaining)) {
		nhs++;
		rtnh = rtnh_next(rtnh, &remaining);
	}

	/* leftover implies invalid nexthop configuration, discard it */
	return remaining > 0 ? 0 : nhs;
}

static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
		       int remaining, struct fib_config *cfg)
{
	struct net *net = cfg->fc_nlinfo.nl_net;
	int ret;

	change_nexthops(fi) {
		int attrlen;

		if (!rtnh_ok(rtnh, remaining))
			return -EINVAL;

		if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
			return -EINVAL;

		nexthop_nh->nh_flags =
			(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
		nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
		nexthop_nh->nh_weight = rtnh->rtnh_hops + 1;

		attrlen = rtnh_attrlen(rtnh);
		if (attrlen > 0) {
			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);

			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
			nexthop_nh->nh_gw = nla ? nla_get_in_addr(nla) : 0;
#ifdef CONFIG_IP_ROUTE_CLASSID
			nla = nla_find(attrs, attrlen, RTA_FLOW);
			nexthop_nh->nh_tclassid = nla ? nla_get_u32(nla) : 0;
			if (nexthop_nh->nh_tclassid)
				fi->fib_net->ipv4.fib_num_tclassid_users++;
#endif
			nla = nla_find(attrs, attrlen, RTA_ENCAP);
			if (nla) {
				struct lwtunnel_state *lwtstate;
				struct net_device *dev = NULL;
				struct nlattr *nla_entype;

				nla_entype = nla_find(attrs, attrlen,
						      RTA_ENCAP_TYPE);
				if (!nla_entype)
					goto err_inval;
				if (cfg->fc_oif)
					dev = __dev_get_by_index(net, cfg->fc_oif);
				ret = lwtunnel_build_state(dev, nla_get_u16(
							   nla_entype),
							   nla,  AF_INET, cfg,
							   &lwtstate);
				if (ret)
					goto errout;
				nexthop_nh->nh_lwtstate =
					lwtstate_get(lwtstate);
			}
		}

		rtnh = rtnh_next(rtnh, &remaining);
	} endfor_nexthops(fi);

	return 0;

err_inval:
	ret = -EINVAL;

errout:
	return ret;
}

static void fib_rebalance(struct fib_info *fi)
{
	int total;
	int w;
	struct in_device *in_dev;

	if (fi->fib_nhs < 2)
		return;

	total = 0;
	for_nexthops(fi) {
		if (nh->nh_flags & RTNH_F_DEAD)
			continue;

		in_dev = __in_dev_get_rtnl(nh->nh_dev);

		if (in_dev &&
		    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
		    nh->nh_flags & RTNH_F_LINKDOWN)
			continue;

		total += nh->nh_weight;
	} endfor_nexthops(fi);

	w = 0;
	change_nexthops(fi) {
		int upper_bound;

		in_dev = __in_dev_get_rtnl(nexthop_nh->nh_dev);

		if (nexthop_nh->nh_flags & RTNH_F_DEAD) {
			upper_bound = -1;
		} else if (in_dev &&
			   IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev) &&
			   nexthop_nh->nh_flags & RTNH_F_LINKDOWN) {
			upper_bound = -1;
		} else {
			w += nexthop_nh->nh_weight;
			upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31,
							    total) - 1;
		}

		atomic_set(&nexthop_nh->nh_upper_bound, upper_bound);
	} endfor_nexthops(fi);

	net_get_random_once(&fib_multipath_secret,
			    sizeof(fib_multipath_secret));
}

static inline void fib_add_weight(struct fib_info *fi,
				  const struct fib_nh *nh)
{
	fi->fib_weight += nh->nh_weight;
}

#else /* CONFIG_IP_ROUTE_MULTIPATH */

#define fib_rebalance(fi) do { } while (0)
#define fib_add_weight(fi, nh) do { } while (0)

#endif /* CONFIG_IP_ROUTE_MULTIPATH */

static int fib_encap_match(struct net *net, u16 encap_type,
			   struct nlattr *encap,
			   int oif, const struct fib_nh *nh,
			   const struct fib_config *cfg)
{
	struct lwtunnel_state *lwtstate;
	struct net_device *dev = NULL;
	int ret, result = 0;

	if (encap_type == LWTUNNEL_ENCAP_NONE)
		return 0;

	if (oif)
		dev = __dev_get_by_index(net, oif);
	ret = lwtunnel_build_state(dev, encap_type, encap,
				   AF_INET, cfg, &lwtstate);
	if (!ret) {
		result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate);
		lwtstate_free(lwtstate);
	}

	return result;
}

int fib_nh_match(struct fib_config *cfg, struct fib_info *fi)
{
	struct net *net = cfg->fc_nlinfo.nl_net;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	struct rtnexthop *rtnh;
	int remaining;
#endif

	if (cfg->fc_priority && cfg->fc_priority != fi->fib_priority)
		return 1;

	if (cfg->fc_oif || cfg->fc_gw) {
		if (cfg->fc_encap) {
			if (fib_encap_match(net, cfg->fc_encap_type,
					    cfg->fc_encap, cfg->fc_oif,
					    fi->fib_nh, cfg))
			    return 1;
		}
		if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) &&
		    (!cfg->fc_gw  || cfg->fc_gw == fi->fib_nh->nh_gw))
			return 0;
		return 1;
	}

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (!cfg->fc_mp)
		return 0;

	rtnh = cfg->fc_mp;
	remaining = cfg->fc_mp_len;

	for_nexthops(fi) {
		int attrlen;

		if (!rtnh_ok(rtnh, remaining))
			return -EINVAL;

		if (rtnh->rtnh_ifindex && rtnh->rtnh_ifindex != nh->nh_oif)
			return 1;

		attrlen = rtnh_attrlen(rtnh);
		if (attrlen > 0) {
			struct nlattr *nla, *attrs = rtnh_attrs(rtnh);

			nla = nla_find(attrs, attrlen, RTA_GATEWAY);
			if (nla && nla_get_in_addr(nla) != nh->nh_gw)
				return 1;
#ifdef CONFIG_IP_ROUTE_CLASSID
			nla = nla_find(attrs, attrlen, RTA_FLOW);
			if (nla && nla_get_u32(nla) != nh->nh_tclassid)
				return 1;
#endif
		}

		rtnh = rtnh_next(rtnh, &remaining);
	} endfor_nexthops(fi);
#endif
	return 0;
}


/*
 * Picture
 * -------
 *
 * Semantics of nexthop is very messy by historical reasons.
 * We have to take into account, that:
 * a) gateway can be actually local interface address,
 *    so that gatewayed route is direct.
 * b) gateway must be on-link address, possibly
 *    described not by an ifaddr, but also by a direct route.
 * c) If both gateway and interface are specified, they should not
 *    contradict.
 * d) If we use tunnel routes, gateway could be not on-link.
 *
 * Attempt to reconcile all of these (alas, self-contradictory) conditions
 * results in pretty ugly and hairy code with obscure logic.
 *
 * I chose to generalized it instead, so that the size
 * of code does not increase practically, but it becomes
 * much more general.
 * Every prefix is assigned a "scope" value: "host" is local address,
 * "link" is direct route,
 * [ ... "site" ... "interior" ... ]
 * and "universe" is true gateway route with global meaning.
 *
 * Every prefix refers to a set of "nexthop"s (gw, oif),
 * where gw must have narrower scope. This recursion stops
 * when gw has LOCAL scope or if "nexthop" is declared ONLINK,
 * which means that gw is forced to be on link.
 *
 * Code is still hairy, but now it is apparently logically
 * consistent and very flexible. F.e. as by-product it allows
 * to co-exists in peace independent exterior and interior
 * routing processes.
 *
 * Normally it looks as following.
 *
 * {universe prefix}  -> (gw, oif) [scope link]
 *		  |
 *		  |-> {link prefix} -> (gw, oif) [scope local]
 *					|
 *					|-> {local prefix} (terminal node)
 */
static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi,
			struct fib_nh *nh)
{
	int err = 0;
	struct net *net;
	struct net_device *dev;

	net = cfg->fc_nlinfo.nl_net;
	if (nh->nh_gw) {
		struct fib_result res;

		if (nh->nh_flags & RTNH_F_ONLINK) {
			unsigned int addr_type;

			if (cfg->fc_scope >= RT_SCOPE_LINK)
				return -EINVAL;
			dev = __dev_get_by_index(net, nh->nh_oif);
			if (!dev)
				return -ENODEV;
			if (!(dev->flags & IFF_UP))
				return -ENETDOWN;
			addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw);
			if (addr_type != RTN_UNICAST)
				return -EINVAL;
			if (!netif_carrier_ok(dev))
				nh->nh_flags |= RTNH_F_LINKDOWN;
			nh->nh_dev = dev;
			dev_hold(dev);
			nh->nh_scope = RT_SCOPE_LINK;
			return 0;
		}
		rcu_read_lock();
		{
			struct fib_table *tbl = NULL;
			struct flowi4 fl4 = {
				.daddr = nh->nh_gw,
				.flowi4_scope = cfg->fc_scope + 1,
				.flowi4_oif = nh->nh_oif,
				.flowi4_iif = LOOPBACK_IFINDEX,
			};

			/* It is not necessary, but requires a bit of thinking */
			if (fl4.flowi4_scope < RT_SCOPE_LINK)
				fl4.flowi4_scope = RT_SCOPE_LINK;

			if (cfg->fc_table)
				tbl = fib_get_table(net, cfg->fc_table);

			if (tbl)
				err = fib_table_lookup(tbl, &fl4, &res,
						       FIB_LOOKUP_IGNORE_LINKSTATE |
						       FIB_LOOKUP_NOREF);

			/* on error or if no table given do full lookup. This
			 * is needed for example when nexthops are in the local
			 * table rather than the given table
			 */
			if (!tbl || err) {
				err = fib_lookup(net, &fl4, &res,
						 FIB_LOOKUP_IGNORE_LINKSTATE);
			}

			if (err) {
				rcu_read_unlock();
				return err;
			}
		}
		err = -EINVAL;
		if (res.type != RTN_UNICAST && res.type != RTN_LOCAL)
			goto out;
		nh->nh_scope = res.scope;
		nh->nh_oif = FIB_RES_OIF(res);
		nh->nh_dev = dev = FIB_RES_DEV(res);
		if (!dev)
			goto out;
		dev_hold(dev);
		if (!netif_carrier_ok(dev))
			nh->nh_flags |= RTNH_F_LINKDOWN;
		err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN;
	} else {
		struct in_device *in_dev;

		if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK))
			return -EINVAL;

		rcu_read_lock();
		err = -ENODEV;
		in_dev = inetdev_by_index(net, nh->nh_oif);
		if (!in_dev)
			goto out;
		err = -ENETDOWN;
		if (!(in_dev->dev->flags & IFF_UP))
			goto out;
		nh->nh_dev = in_dev->dev;
		dev_hold(nh->nh_dev);
		nh->nh_scope = RT_SCOPE_HOST;
		if (!netif_carrier_ok(nh->nh_dev))
			nh->nh_flags |= RTNH_F_LINKDOWN;
		err = 0;
	}
out:
	rcu_read_unlock();
	return err;
}

static inline unsigned int fib_laddr_hashfn(__be32 val)
{
	unsigned int mask = (fib_info_hash_size - 1);

	return ((__force u32)val ^
		((__force u32)val >> 7) ^
		((__force u32)val >> 14)) & mask;
}

static struct hlist_head *fib_info_hash_alloc(int bytes)
{
	if (bytes <= PAGE_SIZE)
		return kzalloc(bytes, GFP_KERNEL);
	else
		return (struct hlist_head *)
			__get_free_pages(GFP_KERNEL | __GFP_ZERO,
					 get_order(bytes));
}

static void fib_info_hash_free(struct hlist_head *hash, int bytes)
{
	if (!hash)
		return;

	if (bytes <= PAGE_SIZE)
		kfree(hash);
	else
		free_pages((unsigned long) hash, get_order(bytes));
}

static void fib_info_hash_move(struct hlist_head *new_info_hash,
			       struct hlist_head *new_laddrhash,
			       unsigned int new_size)
{
	struct hlist_head *old_info_hash, *old_laddrhash;
	unsigned int old_size = fib_info_hash_size;
	unsigned int i, bytes;

	spin_lock_bh(&fib_info_lock);
	old_info_hash = fib_info_hash;
	old_laddrhash = fib_info_laddrhash;
	fib_info_hash_size = new_size;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *head = &fib_info_hash[i];
		struct hlist_node *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, n, head, fib_hash) {
			struct hlist_head *dest;
			unsigned int new_hash;

			new_hash = fib_info_hashfn(fi);
			dest = &new_info_hash[new_hash];
			hlist_add_head(&fi->fib_hash, dest);
		}
	}
	fib_info_hash = new_info_hash;

	for (i = 0; i < old_size; i++) {
		struct hlist_head *lhead = &fib_info_laddrhash[i];
		struct hlist_node *n;
		struct fib_info *fi;

		hlist_for_each_entry_safe(fi, n, lhead, fib_lhash) {
			struct hlist_head *ldest;
			unsigned int new_hash;

			new_hash = fib_laddr_hashfn(fi->fib_prefsrc);
			ldest = &new_laddrhash[new_hash];
			hlist_add_head(&fi->fib_lhash, ldest);
		}
	}
	fib_info_laddrhash = new_laddrhash;

	spin_unlock_bh(&fib_info_lock);

	bytes = old_size * sizeof(struct hlist_head *);
	fib_info_hash_free(old_info_hash, bytes);
	fib_info_hash_free(old_laddrhash, bytes);
}

__be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh)
{
	nh->nh_saddr = inet_select_addr(nh->nh_dev,
					nh->nh_gw,
					nh->nh_parent->fib_scope);
	nh->nh_saddr_genid = atomic_read(&net->ipv4.dev_addr_genid);

	return nh->nh_saddr;
}

static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
{
	if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst ||
	    fib_prefsrc != cfg->fc_dst) {
		u32 tb_id = cfg->fc_table;
		int rc;

		if (tb_id == RT_TABLE_MAIN)
			tb_id = RT_TABLE_LOCAL;

		rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
					  fib_prefsrc, tb_id);

		if (rc != RTN_LOCAL && tb_id != RT_TABLE_LOCAL) {
			rc = inet_addr_type_table(cfg->fc_nlinfo.nl_net,
						  fib_prefsrc, RT_TABLE_LOCAL);
		}

		if (rc != RTN_LOCAL)
			return false;
	}
	return true;
}

static int
fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
{
	bool ecn_ca = false;
	struct nlattr *nla;
	int remaining;

	if (!cfg->fc_mx)
		return 0;

	nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
		int type = nla_type(nla);
		u32 val;

		if (!type)
			continue;
		if (type > RTAX_MAX)
			return -EINVAL;

		if (type == RTAX_CC_ALGO) {
			char tmp[TCP_CA_NAME_MAX];

			nla_strlcpy(tmp, nla, sizeof(tmp));
			val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
			if (val == TCP_CA_UNSPEC)
				return -EINVAL;
		} else {
			val = nla_get_u32(nla);
		}
		if (type == RTAX_ADVMSS && val > 65535 - 40)
			val = 65535 - 40;
		if (type == RTAX_MTU && val > 65535 - 15)
			val = 65535 - 15;
		if (type == RTAX_HOPLIMIT && val > 255)
			val = 255;
		if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
			return -EINVAL;
		fi->fib_metrics[type - 1] = val;
	}

	if (ecn_ca)
		fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;

	return 0;
}

struct fib_info *fib_create_info(struct fib_config *cfg)
{
	int err;
	struct fib_info *fi = NULL;
	struct fib_info *ofi;
	int nhs = 1;
	struct net *net = cfg->fc_nlinfo.nl_net;

	if (cfg->fc_type > RTN_MAX)
		goto err_inval;

	/* Fast check to catch the most weird cases */
	if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
		goto err_inval;

	if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
		goto err_inval;

#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (cfg->fc_mp) {
		nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
		if (nhs == 0)
			goto err_inval;
	}
#endif

	err = -ENOBUFS;
	if (fib_info_cnt >= fib_info_hash_size) {
		unsigned int new_size = fib_info_hash_size << 1;
		struct hlist_head *new_info_hash;
		struct hlist_head *new_laddrhash;
		unsigned int bytes;

		if (!new_size)
			new_size = 16;
		bytes = new_size * sizeof(struct hlist_head *);
		new_info_hash = fib_info_hash_alloc(bytes);
		new_laddrhash = fib_info_hash_alloc(bytes);
		if (!new_info_hash || !new_laddrhash) {
			fib_info_hash_free(new_info_hash, bytes);
			fib_info_hash_free(new_laddrhash, bytes);
		} else
			fib_info_hash_move(new_info_hash, new_laddrhash, new_size);

		if (!fib_info_hash_size)
			goto failure;
	}

	fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL);
	if (!fi)
		goto failure;
	fib_info_cnt++;
	if (cfg->fc_mx) {
		fi->fib_metrics = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL);
		if (!fi->fib_metrics)
			goto failure;
	} else
		fi->fib_metrics = (u32 *) dst_default_metrics;

	fi->fib_net = net;
	fi->fib_protocol = cfg->fc_protocol;
	fi->fib_scope = cfg->fc_scope;
	fi->fib_flags = cfg->fc_flags;
	fi->fib_priority = cfg->fc_priority;
	fi->fib_prefsrc = cfg->fc_prefsrc;
	fi->fib_type = cfg->fc_type;
	fi->fib_tb_id = cfg->fc_table;

	fi->fib_nhs = nhs;
	change_nexthops(fi) {
		nexthop_nh->nh_parent = fi;
		nexthop_nh->nh_pcpu_rth_output = alloc_percpu(struct rtable __rcu *);
		if (!nexthop_nh->nh_pcpu_rth_output)
			goto failure;
	} endfor_nexthops(fi)

	err = fib_convert_metrics(fi, cfg);
	if (err)
		goto failure;

	if (cfg->fc_mp) {
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		err = fib_get_nhs(fi, cfg->fc_mp, cfg->fc_mp_len, cfg);
		if (err != 0)
			goto failure;
		if (cfg->fc_oif && fi->fib_nh->nh_oif != cfg->fc_oif)
			goto err_inval;
		if (cfg->fc_gw && fi->fib_nh->nh_gw != cfg->fc_gw)
			goto err_inval;
#ifdef CONFIG_IP_ROUTE_CLASSID
		if (cfg->fc_flow && fi->fib_nh->nh_tclassid != cfg->fc_flow)
			goto err_inval;
#endif
#else
		goto err_inval;
#endif
	} else {
		struct fib_nh *nh = fi->fib_nh;

		if (cfg->fc_encap) {
			struct lwtunnel_state *lwtstate;
			struct net_device *dev = NULL;

			if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE)
				goto err_inval;
			if (cfg->fc_oif)
				dev = __dev_get_by_index(net, cfg->fc_oif);
			err = lwtunnel_build_state(dev, cfg->fc_encap_type,
						   cfg->fc_encap, AF_INET, cfg,
						   &lwtstate);
			if (err)
				goto failure;

			nh->nh_lwtstate = lwtstate_get(lwtstate);
		}
		nh->nh_oif = cfg->fc_oif;
		nh->nh_gw = cfg->fc_gw;
		nh->nh_flags = cfg->fc_flags;
#ifdef CONFIG_IP_ROUTE_CLASSID
		nh->nh_tclassid = cfg->fc_flow;
		if (nh->nh_tclassid)
			fi->fib_net->ipv4.fib_num_tclassid_users++;
#endif
#ifdef CONFIG_IP_ROUTE_MULTIPATH
		nh->nh_weight = 1;
#endif
	}

	if (fib_props[cfg->fc_type].error) {
		if (cfg->fc_gw || cfg->fc_oif || cfg->fc_mp)
			goto err_inval;
		goto link_it;
	} else {
		switch (cfg->fc_type) {
		case RTN_UNICAST:
		case RTN_LOCAL:
		case RTN_BROADCAST:
		case RTN_ANYCAST:
		case RTN_MULTICAST:
			break;
		default:
			goto err_inval;
		}
	}

	if (cfg->fc_scope > RT_SCOPE_HOST)
		goto err_inval;

	if (cfg->fc_scope == RT_SCOPE_HOST) {
		struct fib_nh *nh = fi->fib_nh;

		/* Local address is added. */
		if (nhs != 1 || nh->nh_gw)
			goto err_inval;
		nh->nh_scope = RT_SCOPE_NOWHERE;
		nh->nh_dev = dev_get_by_index(net, fi->fib_nh->nh_oif);
		err = -ENODEV;
		if (!nh->nh_dev)
			goto failure;
	} else {
		int linkdown = 0;

		change_nexthops(fi) {
			err = fib_check_nh(cfg, fi, nexthop_nh);
			if (err != 0)
				goto failure;
			if (nexthop_nh->nh_flags & RTNH_F_LINKDOWN)
				linkdown++;
		} endfor_nexthops(fi)
		if (linkdown == fi->fib_nhs)
			fi->fib_flags |= RTNH_F_LINKDOWN;
	}

	if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc))
		goto err_inval;

	change_nexthops(fi) {
		fib_info_update_nh_saddr(net, nexthop_nh);
		fib_add_weight(fi, nexthop_nh);
	} endfor_nexthops(fi)

	fib_rebalance(fi);

link_it:
	ofi = fib_find_info(fi);
	if (ofi) {
		fi->fib_dead = 1;
		free_fib_info(fi);
		ofi->fib_treeref++;
		return ofi;
	}

	fi->fib_treeref++;
	atomic_inc(&fi->fib_clntref);
	spin_lock_bh(&fib_info_lock);
	hlist_add_head(&fi->fib_hash,
		       &fib_info_hash[fib_info_hashfn(fi)]);
	if (fi->fib_prefsrc) {
		struct hlist_head *head;

		head = &fib_info_laddrhash[fib_laddr_hashfn(fi->fib_prefsrc)];
		hlist_add_head(&fi->fib_lhash, head);
	}
	change_nexthops(fi) {
		struct hlist_head *head;
		unsigned int hash;

		if (!nexthop_nh->nh_dev)
			continue;
		hash = fib_devindex_hashfn(nexthop_nh->nh_dev->ifindex);
		head = &fib_info_devhash[hash];
		hlist_add_head(&nexthop_nh->nh_hash, head);
	} endfor_nexthops(fi)
	spin_unlock_bh(&fib_info_lock);
	return fi;

err_inval:
	err = -EINVAL;

failure:
	if (fi) {
		fi->fib_dead = 1;
		free_fib_info(fi);
	}

	return ERR_PTR(err);
}

int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
		  u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos,
		  struct fib_info *fi, unsigned int flags)
{
	struct nlmsghdr *nlh;
	struct rtmsg *rtm;

	nlh = nlmsg_put(skb, portid, seq, event, sizeof(*rtm), flags);
	if (!nlh)
		return -EMSGSIZE;

	rtm = nlmsg_data(nlh);
	rtm->rtm_family = AF_INET;
	rtm->rtm_dst_len = dst_len;
	rtm->rtm_src_len = 0;
	rtm->rtm_tos = tos;
	if (tb_id < 256)
		rtm->rtm_table = tb_id;
	else
		rtm->rtm_table = RT_TABLE_COMPAT;
	if (nla_put_u32(skb, RTA_TABLE, tb_id))
		goto nla_put_failure;
	rtm->rtm_type = type;
	rtm->rtm_flags = fi->fib_flags;
	rtm->rtm_scope = fi->fib_scope;
	rtm->rtm_protocol = fi->fib_protocol;

	if (rtm->rtm_dst_len &&
	    nla_put_in_addr(skb, RTA_DST, dst))
		goto nla_put_failure;
	if (fi->fib_priority &&
	    nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority))
		goto nla_put_failure;
	if (rtnetlink_put_metrics(skb, fi->fib_metrics) < 0)
		goto nla_put_failure;

	if (fi->fib_prefsrc &&
	    nla_put_in_addr(skb, RTA_PREFSRC, fi->fib_prefsrc))
		goto nla_put_failure;
	if (fi->fib_nhs == 1) {
		struct in_device *in_dev;

		if (fi->fib_nh->nh_gw &&
		    nla_put_in_addr(skb, RTA_GATEWAY, fi->fib_nh->nh_gw))
			goto nla_put_failure;
		if (fi->fib_nh->nh_oif &&
		    nla_put_u32(skb, RTA_OIF, fi->fib_nh->nh_oif))
			goto nla_put_failure;
		if (fi->fib_nh->nh_flags & RTNH_F_LINKDOWN) {
			in_dev = __in_dev_get_rtnl(fi->fib_nh->nh_dev);
			if (in_dev &&
			    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
				rtm->rtm_flags |= RTNH_F_DEAD;
		}
#ifdef CONFIG_IP_ROUTE_CLASSID
		if (fi->fib_nh[0].nh_tclassid &&
		    nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid))
			goto nla_put_failure;
#endif
		if (fi->fib_nh->nh_lwtstate)
			lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate);
	}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (fi->fib_nhs > 1) {
		struct rtnexthop *rtnh;
		struct nlattr *mp;

		mp = nla_nest_start(skb, RTA_MULTIPATH);
		if (!mp)
			goto nla_put_failure;

		for_nexthops(fi) {
			struct in_device *in_dev;

			rtnh = nla_reserve_nohdr(skb, sizeof(*rtnh));
			if (!rtnh)
				goto nla_put_failure;

			rtnh->rtnh_flags = nh->nh_flags & 0xFF;
			if (nh->nh_flags & RTNH_F_LINKDOWN) {
				in_dev = __in_dev_get_rtnl(nh->nh_dev);
				if (in_dev &&
				    IN_DEV_IGNORE_ROUTES_WITH_LINKDOWN(in_dev))
					rtnh->rtnh_flags |= RTNH_F_DEAD;
			}
			rtnh->rtnh_hops = nh->nh_weight - 1;
			rtnh->rtnh_ifindex = nh->nh_oif;

			if (nh->nh_gw &&
			    nla_put_in_addr(skb, RTA_GATEWAY, nh->nh_gw))
				goto nla_put_failure;
#ifdef CONFIG_IP_ROUTE_CLASSID
			if (nh->nh_tclassid &&
			    nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid))
				goto nla_put_failure;
#endif
			if (nh->nh_lwtstate)
				lwtunnel_fill_encap(skb, nh->nh_lwtstate);
			/* length of rtnetlink header + attributes */
			rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh;
		} endfor_nexthops(fi);

		nla_nest_end(skb, mp);
	}
#endif
	nlmsg_end(skb, nlh);
	return 0;

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

/*
 * Update FIB if:
 * - local address disappeared -> we must delete all the entries
 *   referring to it.
 * - device went down -> we must shutdown all nexthops going via it.
 */
int fib_sync_down_addr(struct net_device *dev, __be32 local)
{
	int ret = 0;
	unsigned int hash = fib_laddr_hashfn(local);
	struct hlist_head *head = &fib_info_laddrhash[hash];
	struct net *net = dev_net(dev);
	int tb_id = l3mdev_fib_table(dev);
	struct fib_info *fi;

	if (!fib_info_laddrhash || local == 0)
		return 0;

	hlist_for_each_entry(fi, head, fib_lhash) {
		if (!net_eq(fi->fib_net, net) ||
		    fi->fib_tb_id != tb_id)
			continue;
		if (fi->fib_prefsrc == local) {
			fi->fib_flags |= RTNH_F_DEAD;
			ret++;
		}
	}
	return ret;
}

/* Event              force Flags           Description
 * NETDEV_CHANGE      0     LINKDOWN        Carrier OFF, not for scope host
 * NETDEV_DOWN        0     LINKDOWN|DEAD   Link down, not for scope host
 * NETDEV_DOWN        1     LINKDOWN|DEAD   Last address removed
 * NETDEV_UNREGISTER  1     LINKDOWN|DEAD   Device removed
 */
int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force)
{
	int ret = 0;
	int scope = RT_SCOPE_NOWHERE;
	struct fib_info *prev_fi = NULL;
	unsigned int hash = fib_devindex_hashfn(dev->ifindex);
	struct hlist_head *head = &fib_info_devhash[hash];
	struct fib_nh *nh;

	if (force)
		scope = -1;

	hlist_for_each_entry(nh, head, nh_hash) {
		struct fib_info *fi = nh->nh_parent;
		int dead;

		BUG_ON(!fi->fib_nhs);
		if (nh->nh_dev != dev || fi == prev_fi)
			continue;
		prev_fi = fi;
		dead = 0;
		change_nexthops(fi) {
			if (nexthop_nh->nh_flags & RTNH_F_DEAD)
				dead++;
			else if (nexthop_nh->nh_dev == dev &&
				 nexthop_nh->nh_scope != scope) {
				switch (event) {
				case NETDEV_DOWN:
				case NETDEV_UNREGISTER:
					nexthop_nh->nh_flags |= RTNH_F_DEAD;
					/* fall through */
				case NETDEV_CHANGE:
					nexthop_nh->nh_flags |= RTNH_F_LINKDOWN;
					break;
				}
				dead++;
			}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
			if (event == NETDEV_UNREGISTER &&
			    nexthop_nh->nh_dev == dev) {
				dead = fi->fib_nhs;
				break;
			}
#endif
		} endfor_nexthops(fi)
		if (dead == fi->fib_nhs) {
			switch (event) {
			case NETDEV_DOWN:
			case NETDEV_UNREGISTER:
				fi->fib_flags |= RTNH_F_DEAD;
				/* fall through */
			case NETDEV_CHANGE:
				fi->fib_flags |= RTNH_F_LINKDOWN;
				break;
			}
			ret++;
		}

		fib_rebalance(fi);
	}

	return ret;
}

/* Must be invoked inside of an RCU protected region.  */
void fib_select_default(const struct flowi4 *flp, struct fib_result *res)
{
	struct fib_info *fi = NULL, *last_resort = NULL;
	struct hlist_head *fa_head = res->fa_head;
	struct fib_table *tb = res->table;
	u8 slen = 32 - res->prefixlen;
	int order = -1, last_idx = -1;
	struct fib_alias *fa, *fa1 = NULL;
	u32 last_prio = res->fi->fib_priority;
	u8 last_tos = 0;

	hlist_for_each_entry_rcu(fa, fa_head, fa_list) {
		struct fib_info *next_fi = fa->fa_info;

		if (fa->fa_slen != slen)
			continue;
		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
			continue;
		if (fa->tb_id != tb->tb_id)
			continue;
		if (next_fi->fib_priority > last_prio &&
		    fa->fa_tos == last_tos) {
			if (last_tos)
				continue;
			break;
		}
		if (next_fi->fib_flags & RTNH_F_DEAD)
			continue;
		last_tos = fa->fa_tos;
		last_prio = next_fi->fib_priority;

		if (next_fi->fib_scope != res->scope ||
		    fa->fa_type != RTN_UNICAST)
			continue;
		if (!next_fi->fib_nh[0].nh_gw ||
		    next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK)
			continue;

		fib_alias_accessed(fa);

		if (!fi) {
			if (next_fi != res->fi)
				break;
			fa1 = fa;
		} else if (!fib_detect_death(fi, order, &last_resort,
					     &last_idx, fa1->fa_default)) {
			fib_result_assign(res, fi);
			fa1->fa_default = order;
			goto out;
		}
		fi = next_fi;
		order++;
	}

	if (order <= 0 || !fi) {
		if (fa1)
			fa1->fa_default = -1;
		goto out;
	}

	if (!fib_detect_death(fi, order, &last_resort, &last_idx,
			      fa1->fa_default)) {
		fib_result_assign(res, fi);
		fa1->fa_default = order;
		goto out;
	}

	if (last_idx >= 0)
		fib_result_assign(res, last_resort);
	fa1->fa_default = last_idx;
out:
	return;
}

/*
 * Dead device goes up. We wake up dead nexthops.
 * It takes sense only on multipath routes.
 */
int fib_sync_up(struct net_device *dev, unsigned int nh_flags)
{
	struct fib_info *prev_fi;
	unsigned int hash;
	struct hlist_head *head;
	struct fib_nh *nh;
	int ret;

	if (!(dev->flags & IFF_UP))
		return 0;

	if (nh_flags & RTNH_F_DEAD) {
		unsigned int flags = dev_get_flags(dev);

		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
			nh_flags |= RTNH_F_LINKDOWN;
	}

	prev_fi = NULL;
	hash = fib_devindex_hashfn(dev->ifindex);
	head = &fib_info_devhash[hash];
	ret = 0;

	hlist_for_each_entry(nh, head, nh_hash) {
		struct fib_info *fi = nh->nh_parent;
		int alive;

		BUG_ON(!fi->fib_nhs);
		if (nh->nh_dev != dev || fi == prev_fi)
			continue;

		prev_fi = fi;
		alive = 0;
		change_nexthops(fi) {
			if (!(nexthop_nh->nh_flags & nh_flags)) {
				alive++;
				continue;
			}
			if (!nexthop_nh->nh_dev ||
			    !(nexthop_nh->nh_dev->flags & IFF_UP))
				continue;
			if (nexthop_nh->nh_dev != dev ||
			    !__in_dev_get_rtnl(dev))
				continue;
			alive++;
			nexthop_nh->nh_flags &= ~nh_flags;
		} endfor_nexthops(fi)

		if (alive > 0) {
			fi->fib_flags &= ~nh_flags;
			ret++;
		}

		fib_rebalance(fi);
	}

	return ret;
}

#ifdef CONFIG_IP_ROUTE_MULTIPATH
static bool fib_good_nh(const struct fib_nh *nh)
{
	int state = NUD_REACHABLE;

	if (nh->nh_scope == RT_SCOPE_LINK) {
		struct neighbour *n;

		rcu_read_lock_bh();

		n = __ipv4_neigh_lookup_noref(nh->nh_dev, nh->nh_gw);
		if (n)
			state = n->nud_state;

		rcu_read_unlock_bh();
	}

	return !!(state & NUD_VALID);
}

void fib_select_multipath(struct fib_result *res, int hash)
{
	struct fib_info *fi = res->fi;
	struct net *net = fi->fib_net;
	bool first = false;

	for_nexthops(fi) {
		if (hash > atomic_read(&nh->nh_upper_bound))
			continue;

		if (!net->ipv4.sysctl_fib_multipath_use_neigh ||
		    fib_good_nh(nh)) {
			res->nh_sel = nhsel;
			return;
		}
		if (!first) {
			res->nh_sel = nhsel;
			first = true;
		}
	} endfor_nexthops(fi);
}
#endif

void fib_select_path(struct net *net, struct fib_result *res,
		     struct flowi4 *fl4, int mp_hash)
{
#ifdef CONFIG_IP_ROUTE_MULTIPATH
	if (res->fi->fib_nhs > 1 && fl4->flowi4_oif == 0) {
		if (mp_hash < 0)
			mp_hash = get_hash_from_flowi4(fl4) >> 1;

		fib_select_multipath(res, mp_hash);
	}
	else
#endif
	if (!res->prefixlen &&
	    res->table->tb_num_default > 1 &&
	    res->type == RTN_UNICAST && !fl4->flowi4_oif)
		fib_select_default(fl4, res);

	if (!fl4->saddr)
		fl4->saddr = FIB_RES_PREFSRC(net, *res);
}
EXPORT_SYMBOL_GPL(fib_select_path);