summaryrefslogtreecommitdiff
path: root/net/ipv4/nexthop.c
blob: 511eaa94e2d161cb00579cca4dd3d5163bbacc98 (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
// SPDX-License-Identifier: GPL-2.0
/* Generic nexthop implementation
 *
 * Copyright (c) 2017-19 Cumulus Networks
 * Copyright (c) 2017-19 David Ahern <dsa@cumulusnetworks.com>
 */

#include <linux/nexthop.h>
#include <linux/rtnetlink.h>
#include <linux/slab.h>
#include <net/arp.h>
#include <net/ipv6_stubs.h>
#include <net/lwtunnel.h>
#include <net/ndisc.h>
#include <net/nexthop.h>
#include <net/route.h>
#include <net/sock.h>

static void remove_nexthop(struct net *net, struct nexthop *nh,
			   struct nl_info *nlinfo);

#define NH_DEV_HASHBITS  8
#define NH_DEV_HASHSIZE (1U << NH_DEV_HASHBITS)

static const struct nla_policy rtm_nh_policy[NHA_MAX + 1] = {
	[NHA_ID]		= { .type = NLA_U32 },
	[NHA_GROUP]		= { .type = NLA_BINARY },
	[NHA_GROUP_TYPE]	= { .type = NLA_U16 },
	[NHA_BLACKHOLE]		= { .type = NLA_FLAG },
	[NHA_OIF]		= { .type = NLA_U32 },
	[NHA_GATEWAY]		= { .type = NLA_BINARY },
	[NHA_ENCAP_TYPE]	= { .type = NLA_U16 },
	[NHA_ENCAP]		= { .type = NLA_NESTED },
	[NHA_GROUPS]		= { .type = NLA_FLAG },
	[NHA_MASTER]		= { .type = NLA_U32 },
};

static unsigned int nh_dev_hashfn(unsigned int val)
{
	unsigned int mask = NH_DEV_HASHSIZE - 1;

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

static void nexthop_devhash_add(struct net *net, struct nh_info *nhi)
{
	struct net_device *dev = nhi->fib_nhc.nhc_dev;
	struct hlist_head *head;
	unsigned int hash;

	WARN_ON(!dev);

	hash = nh_dev_hashfn(dev->ifindex);
	head = &net->nexthop.devhash[hash];
	hlist_add_head(&nhi->dev_hash, head);
}

static void nexthop_free_mpath(struct nexthop *nh)
{
	struct nh_group *nhg;
	int i;

	nhg = rcu_dereference_raw(nh->nh_grp);
	for (i = 0; i < nhg->num_nh; ++i)
		WARN_ON(nhg->nh_entries[i].nh);

	kfree(nhg);
}

static void nexthop_free_single(struct nexthop *nh)
{
	struct nh_info *nhi;

	nhi = rcu_dereference_raw(nh->nh_info);
	switch (nhi->family) {
	case AF_INET:
		fib_nh_release(nh->net, &nhi->fib_nh);
		break;
	case AF_INET6:
		ipv6_stub->fib6_nh_release(&nhi->fib6_nh);
		break;
	}
	kfree(nhi);
}

void nexthop_free_rcu(struct rcu_head *head)
{
	struct nexthop *nh = container_of(head, struct nexthop, rcu);

	if (nh->is_group)
		nexthop_free_mpath(nh);
	else
		nexthop_free_single(nh);

	kfree(nh);
}
EXPORT_SYMBOL_GPL(nexthop_free_rcu);

static struct nexthop *nexthop_alloc(void)
{
	struct nexthop *nh;

	nh = kzalloc(sizeof(struct nexthop), GFP_KERNEL);
	if (nh) {
		INIT_LIST_HEAD(&nh->fi_list);
		INIT_LIST_HEAD(&nh->f6i_list);
		INIT_LIST_HEAD(&nh->grp_list);
	}
	return nh;
}

static struct nh_group *nexthop_grp_alloc(u16 num_nh)
{
	size_t sz = offsetof(struct nexthop, nh_grp)
		    + sizeof(struct nh_group)
		    + sizeof(struct nh_grp_entry) * num_nh;
	struct nh_group *nhg;

	nhg = kzalloc(sz, GFP_KERNEL);
	if (nhg)
		nhg->num_nh = num_nh;

	return nhg;
}

static void nh_base_seq_inc(struct net *net)
{
	while (++net->nexthop.seq == 0)
		;
}

/* no reference taken; rcu lock or rtnl must be held */
struct nexthop *nexthop_find_by_id(struct net *net, u32 id)
{
	struct rb_node **pp, *parent = NULL, *next;

	pp = &net->nexthop.rb_root.rb_node;
	while (1) {
		struct nexthop *nh;

		next = rcu_dereference_raw(*pp);
		if (!next)
			break;
		parent = next;

		nh = rb_entry(parent, struct nexthop, rb_node);
		if (id < nh->id)
			pp = &next->rb_left;
		else if (id > nh->id)
			pp = &next->rb_right;
		else
			return nh;
	}
	return NULL;
}
EXPORT_SYMBOL_GPL(nexthop_find_by_id);

/* used for auto id allocation; called with rtnl held */
static u32 nh_find_unused_id(struct net *net)
{
	u32 id_start = net->nexthop.last_id_allocated;

	while (1) {
		net->nexthop.last_id_allocated++;
		if (net->nexthop.last_id_allocated == id_start)
			break;

		if (!nexthop_find_by_id(net, net->nexthop.last_id_allocated))
			return net->nexthop.last_id_allocated;
	}
	return 0;
}

static int nla_put_nh_group(struct sk_buff *skb, struct nh_group *nhg)
{
	struct nexthop_grp *p;
	size_t len = nhg->num_nh * sizeof(*p);
	struct nlattr *nla;
	u16 group_type = 0;
	int i;

	if (nhg->mpath)
		group_type = NEXTHOP_GRP_TYPE_MPATH;

	if (nla_put_u16(skb, NHA_GROUP_TYPE, group_type))
		goto nla_put_failure;

	nla = nla_reserve(skb, NHA_GROUP, len);
	if (!nla)
		goto nla_put_failure;

	p = nla_data(nla);
	for (i = 0; i < nhg->num_nh; ++i) {
		p->id = nhg->nh_entries[i].nh->id;
		p->weight = nhg->nh_entries[i].weight - 1;
		p += 1;
	}

	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

static int nh_fill_node(struct sk_buff *skb, struct nexthop *nh,
			int event, u32 portid, u32 seq, unsigned int nlflags)
{
	struct fib6_nh *fib6_nh;
	struct fib_nh *fib_nh;
	struct nlmsghdr *nlh;
	struct nh_info *nhi;
	struct nhmsg *nhm;

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

	nhm = nlmsg_data(nlh);
	nhm->nh_family = AF_UNSPEC;
	nhm->nh_flags = nh->nh_flags;
	nhm->nh_protocol = nh->protocol;
	nhm->nh_scope = 0;
	nhm->resvd = 0;

	if (nla_put_u32(skb, NHA_ID, nh->id))
		goto nla_put_failure;

	if (nh->is_group) {
		struct nh_group *nhg = rtnl_dereference(nh->nh_grp);

		if (nla_put_nh_group(skb, nhg))
			goto nla_put_failure;
		goto out;
	}

	nhi = rtnl_dereference(nh->nh_info);
	nhm->nh_family = nhi->family;
	if (nhi->reject_nh) {
		if (nla_put_flag(skb, NHA_BLACKHOLE))
			goto nla_put_failure;
		goto out;
	} else {
		const struct net_device *dev;

		dev = nhi->fib_nhc.nhc_dev;
		if (dev && nla_put_u32(skb, NHA_OIF, dev->ifindex))
			goto nla_put_failure;
	}

	nhm->nh_scope = nhi->fib_nhc.nhc_scope;
	switch (nhi->family) {
	case AF_INET:
		fib_nh = &nhi->fib_nh;
		if (fib_nh->fib_nh_gw_family &&
		    nla_put_u32(skb, NHA_GATEWAY, fib_nh->fib_nh_gw4))
			goto nla_put_failure;
		break;

	case AF_INET6:
		fib6_nh = &nhi->fib6_nh;
		if (fib6_nh->fib_nh_gw_family &&
		    nla_put_in6_addr(skb, NHA_GATEWAY, &fib6_nh->fib_nh_gw6))
			goto nla_put_failure;
		break;
	}

	if (nhi->fib_nhc.nhc_lwtstate &&
	    lwtunnel_fill_encap(skb, nhi->fib_nhc.nhc_lwtstate,
				NHA_ENCAP, NHA_ENCAP_TYPE) < 0)
		goto nla_put_failure;

out:
	nlmsg_end(skb, nlh);
	return 0;

nla_put_failure:
	return -EMSGSIZE;
}

static size_t nh_nlmsg_size_grp(struct nexthop *nh)
{
	struct nh_group *nhg = rtnl_dereference(nh->nh_grp);
	size_t sz = sizeof(struct nexthop_grp) * nhg->num_nh;

	return nla_total_size(sz) +
	       nla_total_size(2);  /* NHA_GROUP_TYPE */
}

static size_t nh_nlmsg_size_single(struct nexthop *nh)
{
	struct nh_info *nhi = rtnl_dereference(nh->nh_info);
	size_t sz;

	/* covers NHA_BLACKHOLE since NHA_OIF and BLACKHOLE
	 * are mutually exclusive
	 */
	sz = nla_total_size(4);  /* NHA_OIF */

	switch (nhi->family) {
	case AF_INET:
		if (nhi->fib_nh.fib_nh_gw_family)
			sz += nla_total_size(4);  /* NHA_GATEWAY */
		break;

	case AF_INET6:
		/* NHA_GATEWAY */
		if (nhi->fib6_nh.fib_nh_gw_family)
			sz += nla_total_size(sizeof(const struct in6_addr));
		break;
	}

	if (nhi->fib_nhc.nhc_lwtstate) {
		sz += lwtunnel_get_encap_size(nhi->fib_nhc.nhc_lwtstate);
		sz += nla_total_size(2);  /* NHA_ENCAP_TYPE */
	}

	return sz;
}

static size_t nh_nlmsg_size(struct nexthop *nh)
{
	size_t sz = nla_total_size(4);    /* NHA_ID */

	if (nh->is_group)
		sz += nh_nlmsg_size_grp(nh);
	else
		sz += nh_nlmsg_size_single(nh);

	return sz;
}

static void nexthop_notify(int event, struct nexthop *nh, struct nl_info *info)
{
	unsigned int nlflags = info->nlh ? info->nlh->nlmsg_flags : 0;
	u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0;
	struct sk_buff *skb;
	int err = -ENOBUFS;

	skb = nlmsg_new(nh_nlmsg_size(nh), gfp_any());
	if (!skb)
		goto errout;

	err = nh_fill_node(skb, nh, event, info->portid, seq, nlflags);
	if (err < 0) {
		/* -EMSGSIZE implies BUG in nh_nlmsg_size() */
		WARN_ON(err == -EMSGSIZE);
		kfree_skb(skb);
		goto errout;
	}

	rtnl_notify(skb, info->nl_net, info->portid, RTNLGRP_NEXTHOP,
		    info->nlh, gfp_any());
	return;
errout:
	if (err < 0)
		rtnl_set_sk_err(info->nl_net, RTNLGRP_NEXTHOP, err);
}

static bool valid_group_nh(struct nexthop *nh, unsigned int npaths,
			   struct netlink_ext_ack *extack)
{
	if (nh->is_group) {
		struct nh_group *nhg = rtnl_dereference(nh->nh_grp);

		/* nested multipath (group within a group) is not
		 * supported
		 */
		if (nhg->mpath) {
			NL_SET_ERR_MSG(extack,
				       "Multipath group can not be a nexthop within a group");
			return false;
		}
	} else {
		struct nh_info *nhi = rtnl_dereference(nh->nh_info);

		if (nhi->reject_nh && npaths > 1) {
			NL_SET_ERR_MSG(extack,
				       "Blackhole nexthop can not be used in a group with more than 1 path");
			return false;
		}
	}

	return true;
}

static int nh_check_attr_group(struct net *net, struct nlattr *tb[],
			       struct netlink_ext_ack *extack)
{
	unsigned int len = nla_len(tb[NHA_GROUP]);
	struct nexthop_grp *nhg;
	unsigned int i, j;

	if (len & (sizeof(struct nexthop_grp) - 1)) {
		NL_SET_ERR_MSG(extack,
			       "Invalid length for nexthop group attribute");
		return -EINVAL;
	}

	/* convert len to number of nexthop ids */
	len /= sizeof(*nhg);

	nhg = nla_data(tb[NHA_GROUP]);
	for (i = 0; i < len; ++i) {
		if (nhg[i].resvd1 || nhg[i].resvd2) {
			NL_SET_ERR_MSG(extack, "Reserved fields in nexthop_grp must be 0");
			return -EINVAL;
		}
		if (nhg[i].weight > 254) {
			NL_SET_ERR_MSG(extack, "Invalid value for weight");
			return -EINVAL;
		}
		for (j = i + 1; j < len; ++j) {
			if (nhg[i].id == nhg[j].id) {
				NL_SET_ERR_MSG(extack, "Nexthop id can not be used twice in a group");
				return -EINVAL;
			}
		}
	}

	nhg = nla_data(tb[NHA_GROUP]);
	for (i = 0; i < len; ++i) {
		struct nexthop *nh;

		nh = nexthop_find_by_id(net, nhg[i].id);
		if (!nh) {
			NL_SET_ERR_MSG(extack, "Invalid nexthop id");
			return -EINVAL;
		}
		if (!valid_group_nh(nh, len, extack))
			return -EINVAL;
	}
	for (i = NHA_GROUP + 1; i < __NHA_MAX; ++i) {
		if (!tb[i])
			continue;

		NL_SET_ERR_MSG(extack,
			       "No other attributes can be set in nexthop groups");
		return -EINVAL;
	}

	return 0;
}

static bool ipv6_good_nh(const struct fib6_nh *nh)
{
	int state = NUD_REACHABLE;
	struct neighbour *n;

	rcu_read_lock_bh();

	n = __ipv6_neigh_lookup_noref_stub(nh->fib_nh_dev, &nh->fib_nh_gw6);
	if (n)
		state = n->nud_state;

	rcu_read_unlock_bh();

	return !!(state & NUD_VALID);
}

static bool ipv4_good_nh(const struct fib_nh *nh)
{
	int state = NUD_REACHABLE;
	struct neighbour *n;

	rcu_read_lock_bh();

	n = __ipv4_neigh_lookup_noref(nh->fib_nh_dev,
				      (__force u32)nh->fib_nh_gw4);
	if (n)
		state = n->nud_state;

	rcu_read_unlock_bh();

	return !!(state & NUD_VALID);
}

struct nexthop *nexthop_select_path(struct nexthop *nh, int hash)
{
	struct nexthop *rc = NULL;
	struct nh_group *nhg;
	int i;

	if (!nh->is_group)
		return nh;

	nhg = rcu_dereference(nh->nh_grp);
	for (i = 0; i < nhg->num_nh; ++i) {
		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
		struct nh_info *nhi;

		if (hash > atomic_read(&nhge->upper_bound))
			continue;

		/* nexthops always check if it is good and does
		 * not rely on a sysctl for this behavior
		 */
		nhi = rcu_dereference(nhge->nh->nh_info);
		switch (nhi->family) {
		case AF_INET:
			if (ipv4_good_nh(&nhi->fib_nh))
				return nhge->nh;
			break;
		case AF_INET6:
			if (ipv6_good_nh(&nhi->fib6_nh))
				return nhge->nh;
			break;
		}

		if (!rc)
			rc = nhge->nh;
	}

	return rc;
}
EXPORT_SYMBOL_GPL(nexthop_select_path);

int nexthop_for_each_fib6_nh(struct nexthop *nh,
			     int (*cb)(struct fib6_nh *nh, void *arg),
			     void *arg)
{
	struct nh_info *nhi;
	int err;

	if (nh->is_group) {
		struct nh_group *nhg;
		int i;

		nhg = rcu_dereference_rtnl(nh->nh_grp);
		for (i = 0; i < nhg->num_nh; i++) {
			struct nh_grp_entry *nhge = &nhg->nh_entries[i];

			nhi = rcu_dereference_rtnl(nhge->nh->nh_info);
			err = cb(&nhi->fib6_nh, arg);
			if (err)
				return err;
		}
	} else {
		nhi = rcu_dereference_rtnl(nh->nh_info);
		err = cb(&nhi->fib6_nh, arg);
		if (err)
			return err;
	}

	return 0;
}
EXPORT_SYMBOL_GPL(nexthop_for_each_fib6_nh);

static int check_src_addr(const struct in6_addr *saddr,
			  struct netlink_ext_ack *extack)
{
	if (!ipv6_addr_any(saddr)) {
		NL_SET_ERR_MSG(extack, "IPv6 routes using source address can not use nexthop objects");
		return -EINVAL;
	}
	return 0;
}

int fib6_check_nexthop(struct nexthop *nh, struct fib6_config *cfg,
		       struct netlink_ext_ack *extack)
{
	struct nh_info *nhi;

	/* fib6_src is unique to a fib6_info and limits the ability to cache
	 * routes in fib6_nh within a nexthop that is potentially shared
	 * across multiple fib entries. If the config wants to use source
	 * routing it can not use nexthop objects. mlxsw also does not allow
	 * fib6_src on routes.
	 */
	if (cfg && check_src_addr(&cfg->fc_src, extack) < 0)
		return -EINVAL;

	if (nh->is_group) {
		struct nh_group *nhg;

		nhg = rtnl_dereference(nh->nh_grp);
		if (nhg->has_v4)
			goto no_v4_nh;
	} else {
		nhi = rtnl_dereference(nh->nh_info);
		if (nhi->family == AF_INET)
			goto no_v4_nh;
	}

	return 0;
no_v4_nh:
	NL_SET_ERR_MSG(extack, "IPv6 routes can not use an IPv4 nexthop");
	return -EINVAL;
}
EXPORT_SYMBOL_GPL(fib6_check_nexthop);

/* if existing nexthop has ipv6 routes linked to it, need
 * to verify this new spec works with ipv6
 */
static int fib6_check_nh_list(struct nexthop *old, struct nexthop *new,
			      struct netlink_ext_ack *extack)
{
	struct fib6_info *f6i;

	if (list_empty(&old->f6i_list))
		return 0;

	list_for_each_entry(f6i, &old->f6i_list, nh_list) {
		if (check_src_addr(&f6i->fib6_src.addr, extack) < 0)
			return -EINVAL;
	}

	return fib6_check_nexthop(new, NULL, extack);
}

static int nexthop_check_scope(struct nexthop *nh, u8 scope,
			       struct netlink_ext_ack *extack)
{
	struct nh_info *nhi;

	nhi = rtnl_dereference(nh->nh_info);
	if (scope == RT_SCOPE_HOST && nhi->fib_nhc.nhc_gw_family) {
		NL_SET_ERR_MSG(extack,
			       "Route with host scope can not have a gateway");
		return -EINVAL;
	}

	if (nhi->fib_nhc.nhc_flags & RTNH_F_ONLINK && scope >= RT_SCOPE_LINK) {
		NL_SET_ERR_MSG(extack, "Scope mismatch with nexthop");
		return -EINVAL;
	}

	return 0;
}

/* Invoked by fib add code to verify nexthop by id is ok with
 * config for prefix; parts of fib_check_nh not done when nexthop
 * object is used.
 */
int fib_check_nexthop(struct nexthop *nh, u8 scope,
		      struct netlink_ext_ack *extack)
{
	int err = 0;

	if (nh->is_group) {
		struct nh_group *nhg;

		if (scope == RT_SCOPE_HOST) {
			NL_SET_ERR_MSG(extack, "Route with host scope can not have multiple nexthops");
			err = -EINVAL;
			goto out;
		}

		nhg = rtnl_dereference(nh->nh_grp);
		/* all nexthops in a group have the same scope */
		err = nexthop_check_scope(nhg->nh_entries[0].nh, scope, extack);
	} else {
		err = nexthop_check_scope(nh, scope, extack);
	}
out:
	return err;
}

static int fib_check_nh_list(struct nexthop *old, struct nexthop *new,
			     struct netlink_ext_ack *extack)
{
	struct fib_info *fi;

	list_for_each_entry(fi, &old->fi_list, nh_list) {
		int err;

		err = fib_check_nexthop(new, fi->fib_scope, extack);
		if (err)
			return err;
	}
	return 0;
}

static void nh_group_rebalance(struct nh_group *nhg)
{
	int total = 0;
	int w = 0;
	int i;

	for (i = 0; i < nhg->num_nh; ++i)
		total += nhg->nh_entries[i].weight;

	for (i = 0; i < nhg->num_nh; ++i) {
		struct nh_grp_entry *nhge = &nhg->nh_entries[i];
		int upper_bound;

		w += nhge->weight;
		upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31, total) - 1;
		atomic_set(&nhge->upper_bound, upper_bound);
	}
}

static void remove_nh_grp_entry(struct nh_grp_entry *nhge,
				struct nh_group *nhg,
				struct nl_info *nlinfo)
{
	struct nexthop *nh = nhge->nh;
	struct nh_grp_entry *nhges;
	bool found = false;
	int i;

	WARN_ON(!nh);

	nhges = nhg->nh_entries;
	for (i = 0; i < nhg->num_nh; ++i) {
		if (found) {
			nhges[i-1].nh = nhges[i].nh;
			nhges[i-1].weight = nhges[i].weight;
			list_del(&nhges[i].nh_list);
			list_add(&nhges[i-1].nh_list, &nhges[i-1].nh->grp_list);
		} else if (nhg->nh_entries[i].nh == nh) {
			found = true;
		}
	}

	if (WARN_ON(!found))
		return;

	nhg->num_nh--;
	nhg->nh_entries[nhg->num_nh].nh = NULL;

	nh_group_rebalance(nhg);

	nexthop_put(nh);

	if (nlinfo)
		nexthop_notify(RTM_NEWNEXTHOP, nhge->nh_parent, nlinfo);
}

static void remove_nexthop_from_groups(struct net *net, struct nexthop *nh,
				       struct nl_info *nlinfo)
{
	struct nh_grp_entry *nhge, *tmp;

	list_for_each_entry_safe(nhge, tmp, &nh->grp_list, nh_list) {
		struct nh_group *nhg;

		list_del(&nhge->nh_list);
		nhg = rtnl_dereference(nhge->nh_parent->nh_grp);
		remove_nh_grp_entry(nhge, nhg, nlinfo);

		/* if this group has no more entries then remove it */
		if (!nhg->num_nh)
			remove_nexthop(net, nhge->nh_parent, nlinfo);
	}
}

static void remove_nexthop_group(struct nexthop *nh, struct nl_info *nlinfo)
{
	struct nh_group *nhg = rcu_dereference_rtnl(nh->nh_grp);
	int i, num_nh = nhg->num_nh;

	for (i = 0; i < num_nh; ++i) {
		struct nh_grp_entry *nhge = &nhg->nh_entries[i];

		if (WARN_ON(!nhge->nh))
			continue;

		list_del(&nhge->nh_list);
		nexthop_put(nhge->nh);
		nhge->nh = NULL;
		nhg->num_nh--;
	}
}

/* not called for nexthop replace */
static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
{
	struct fib6_info *f6i, *tmp;
	bool do_flush = false;
	struct fib_info *fi;

	list_for_each_entry(fi, &nh->fi_list, nh_list) {
		fi->fib_flags |= RTNH_F_DEAD;
		do_flush = true;
	}
	if (do_flush)
		fib_flush(net);

	/* ip6_del_rt removes the entry from this list hence the _safe */
	list_for_each_entry_safe(f6i, tmp, &nh->f6i_list, nh_list) {
		/* __ip6_del_rt does a release, so do a hold here */
		fib6_info_hold(f6i);
		ipv6_stub->ip6_del_rt(net, f6i);
	}
}

static void __remove_nexthop(struct net *net, struct nexthop *nh,
			     struct nl_info *nlinfo)
{
	__remove_nexthop_fib(net, nh);

	if (nh->is_group) {
		remove_nexthop_group(nh, nlinfo);
	} else {
		struct nh_info *nhi;

		nhi = rtnl_dereference(nh->nh_info);
		if (nhi->fib_nhc.nhc_dev)
			hlist_del(&nhi->dev_hash);

		remove_nexthop_from_groups(net, nh, nlinfo);
	}
}

static void remove_nexthop(struct net *net, struct nexthop *nh,
			   struct nl_info *nlinfo)
{
	/* remove from the tree */
	rb_erase(&nh->rb_node, &net->nexthop.rb_root);

	if (nlinfo)
		nexthop_notify(RTM_DELNEXTHOP, nh, nlinfo);

	__remove_nexthop(net, nh, nlinfo);
	nh_base_seq_inc(net);

	nexthop_put(nh);
}

/* if any FIB entries reference this nexthop, any dst entries
 * need to be regenerated
 */
static void nh_rt_cache_flush(struct net *net, struct nexthop *nh)
{
	struct fib6_info *f6i;

	if (!list_empty(&nh->fi_list))
		rt_cache_flush(net);

	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
		ipv6_stub->fib6_update_sernum(net, f6i);
}

static int replace_nexthop_grp(struct net *net, struct nexthop *old,
			       struct nexthop *new,
			       struct netlink_ext_ack *extack)
{
	struct nh_group *oldg, *newg;
	int i;

	if (!new->is_group) {
		NL_SET_ERR_MSG(extack, "Can not replace a nexthop group with a nexthop.");
		return -EINVAL;
	}

	oldg = rtnl_dereference(old->nh_grp);
	newg = rtnl_dereference(new->nh_grp);

	/* update parents - used by nexthop code for cleanup */
	for (i = 0; i < newg->num_nh; i++)
		newg->nh_entries[i].nh_parent = old;

	rcu_assign_pointer(old->nh_grp, newg);

	for (i = 0; i < oldg->num_nh; i++)
		oldg->nh_entries[i].nh_parent = new;

	rcu_assign_pointer(new->nh_grp, oldg);

	return 0;
}

static int replace_nexthop_single(struct net *net, struct nexthop *old,
				  struct nexthop *new,
				  struct netlink_ext_ack *extack)
{
	struct nh_info *oldi, *newi;

	if (new->is_group) {
		NL_SET_ERR_MSG(extack, "Can not replace a nexthop with a nexthop group.");
		return -EINVAL;
	}

	oldi = rtnl_dereference(old->nh_info);
	newi = rtnl_dereference(new->nh_info);

	newi->nh_parent = old;
	oldi->nh_parent = new;

	old->protocol = new->protocol;
	old->nh_flags = new->nh_flags;

	rcu_assign_pointer(old->nh_info, newi);
	rcu_assign_pointer(new->nh_info, oldi);

	return 0;
}

static void __nexthop_replace_notify(struct net *net, struct nexthop *nh,
				     struct nl_info *info)
{
	struct fib6_info *f6i;

	if (!list_empty(&nh->fi_list)) {
		struct fib_info *fi;

		/* expectation is a few fib_info per nexthop and then
		 * a lot of routes per fib_info. So mark the fib_info
		 * and then walk the fib tables once
		 */
		list_for_each_entry(fi, &nh->fi_list, nh_list)
			fi->nh_updated = true;

		fib_info_notify_update(net, info);

		list_for_each_entry(fi, &nh->fi_list, nh_list)
			fi->nh_updated = false;
	}

	list_for_each_entry(f6i, &nh->f6i_list, nh_list)
		ipv6_stub->fib6_rt_update(net, f6i, info);
}

/* send RTM_NEWROUTE with REPLACE flag set for all FIB entries
 * linked to this nexthop and for all groups that the nexthop
 * is a member of
 */
static void nexthop_replace_notify(struct net *net, struct nexthop *nh,
				   struct nl_info *info)
{
	struct nh_grp_entry *nhge;

	__nexthop_replace_notify(net, nh, info);

	list_for_each_entry(nhge, &nh->grp_list, nh_list)
		__nexthop_replace_notify(net, nhge->nh_parent, info);
}

static int replace_nexthop(struct net *net, struct nexthop *old,
			   struct nexthop *new, struct netlink_ext_ack *extack)
{
	bool new_is_reject = false;
	struct nh_grp_entry *nhge;
	int err;

	/* check that existing FIB entries are ok with the
	 * new nexthop definition
	 */
	err = fib_check_nh_list(old, new, extack);
	if (err)
		return err;

	err = fib6_check_nh_list(old, new, extack);
	if (err)
		return err;

	if (!new->is_group) {
		struct nh_info *nhi = rtnl_dereference(new->nh_info);

		new_is_reject = nhi->reject_nh;
	}

	list_for_each_entry(nhge, &old->grp_list, nh_list) {
		/* if new nexthop is a blackhole, any groups using this
		 * nexthop cannot have more than 1 path
		 */
		if (new_is_reject &&
		    nexthop_num_path(nhge->nh_parent) > 1) {
			NL_SET_ERR_MSG(extack, "Blackhole nexthop can not be a member of a group with more than one path");
			return -EINVAL;
		}

		err = fib_check_nh_list(nhge->nh_parent, new, extack);
		if (err)
			return err;

		err = fib6_check_nh_list(nhge->nh_parent, new, extack);
		if (err)
			return err;
	}

	if (old->is_group)
		err = replace_nexthop_grp(net, old, new, extack);
	else
		err = replace_nexthop_single(net, old, new, extack);

	if (!err) {
		nh_rt_cache_flush(net, old);

		__remove_nexthop(net, new, NULL);
		nexthop_put(new);
	}

	return err;
}

/* called with rtnl_lock held */
static int insert_nexthop(struct net *net, struct nexthop *new_nh,
			  struct nh_config *cfg, struct netlink_ext_ack *extack)
{
	struct rb_node **pp, *parent = NULL, *next;
	struct rb_root *root = &net->nexthop.rb_root;
	bool replace = !!(cfg->nlflags & NLM_F_REPLACE);
	bool create = !!(cfg->nlflags & NLM_F_CREATE);
	u32 new_id = new_nh->id;
	int replace_notify = 0;
	int rc = -EEXIST;

	pp = &root->rb_node;
	while (1) {
		struct nexthop *nh;

		next = rtnl_dereference(*pp);
		if (!next)
			break;

		parent = next;

		nh = rb_entry(parent, struct nexthop, rb_node);
		if (new_id < nh->id) {
			pp = &next->rb_left;
		} else if (new_id > nh->id) {
			pp = &next->rb_right;
		} else if (replace) {
			rc = replace_nexthop(net, nh, new_nh, extack);
			if (!rc) {
				new_nh = nh; /* send notification with old nh */
				replace_notify = 1;
			}
			goto out;
		} else {
			/* id already exists and not a replace */
			goto out;
		}
	}

	if (replace && !create) {
		NL_SET_ERR_MSG(extack, "Replace specified without create and no entry exists");
		rc = -ENOENT;
		goto out;
	}

	rb_link_node_rcu(&new_nh->rb_node, parent, pp);
	rb_insert_color(&new_nh->rb_node, root);
	rc = 0;
out:
	if (!rc) {
		nh_base_seq_inc(net);
		nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo);
		if (replace_notify)
			nexthop_replace_notify(net, new_nh, &cfg->nlinfo);
	}

	return rc;
}

/* rtnl */
/* remove all nexthops tied to a device being deleted */
static void nexthop_flush_dev(struct net_device *dev)
{
	unsigned int hash = nh_dev_hashfn(dev->ifindex);
	struct net *net = dev_net(dev);
	struct hlist_head *head = &net->nexthop.devhash[hash];
	struct hlist_node *n;
	struct nh_info *nhi;

	hlist_for_each_entry_safe(nhi, n, head, dev_hash) {
		if (nhi->fib_nhc.nhc_dev != dev)
			continue;

		remove_nexthop(net, nhi->nh_parent, NULL);
	}
}

/* rtnl; called when net namespace is deleted */
static void flush_all_nexthops(struct net *net)
{
	struct rb_root *root = &net->nexthop.rb_root;
	struct rb_node *node;
	struct nexthop *nh;

	while ((node = rb_first(root))) {
		nh = rb_entry(node, struct nexthop, rb_node);
		remove_nexthop(net, nh, NULL);
		cond_resched();
	}
}

static struct nexthop *nexthop_create_group(struct net *net,
					    struct nh_config *cfg)
{
	struct nlattr *grps_attr = cfg->nh_grp;
	struct nexthop_grp *entry = nla_data(grps_attr);
	struct nh_group *nhg;
	struct nexthop *nh;
	int i;

	nh = nexthop_alloc();
	if (!nh)
		return ERR_PTR(-ENOMEM);

	nh->is_group = 1;

	nhg = nexthop_grp_alloc(nla_len(grps_attr) / sizeof(*entry));
	if (!nhg) {
		kfree(nh);
		return ERR_PTR(-ENOMEM);
	}

	for (i = 0; i < nhg->num_nh; ++i) {
		struct nexthop *nhe;
		struct nh_info *nhi;

		nhe = nexthop_find_by_id(net, entry[i].id);
		if (!nexthop_get(nhe))
			goto out_no_nh;

		nhi = rtnl_dereference(nhe->nh_info);
		if (nhi->family == AF_INET)
			nhg->has_v4 = true;

		nhg->nh_entries[i].nh = nhe;
		nhg->nh_entries[i].weight = entry[i].weight + 1;
		list_add(&nhg->nh_entries[i].nh_list, &nhe->grp_list);
		nhg->nh_entries[i].nh_parent = nh;
	}

	if (cfg->nh_grp_type == NEXTHOP_GRP_TYPE_MPATH) {
		nhg->mpath = 1;
		nh_group_rebalance(nhg);
	}

	rcu_assign_pointer(nh->nh_grp, nhg);

	return nh;

out_no_nh:
	for (; i >= 0; --i)
		nexthop_put(nhg->nh_entries[i].nh);

	kfree(nhg);
	kfree(nh);

	return ERR_PTR(-ENOENT);
}

static int nh_create_ipv4(struct net *net, struct nexthop *nh,
			  struct nh_info *nhi, struct nh_config *cfg,
			  struct netlink_ext_ack *extack)
{
	struct fib_nh *fib_nh = &nhi->fib_nh;
	struct fib_config fib_cfg = {
		.fc_oif   = cfg->nh_ifindex,
		.fc_gw4   = cfg->gw.ipv4,
		.fc_gw_family = cfg->gw.ipv4 ? AF_INET : 0,
		.fc_flags = cfg->nh_flags,
		.fc_encap = cfg->nh_encap,
		.fc_encap_type = cfg->nh_encap_type,
	};
	u32 tb_id = l3mdev_fib_table(cfg->dev);
	int err;

	err = fib_nh_init(net, fib_nh, &fib_cfg, 1, extack);
	if (err) {
		fib_nh_release(net, fib_nh);
		goto out;
	}

	/* sets nh_dev if successful */
	err = fib_check_nh(net, fib_nh, tb_id, 0, extack);
	if (!err) {
		nh->nh_flags = fib_nh->fib_nh_flags;
		fib_info_update_nhc_saddr(net, &fib_nh->nh_common,
					  fib_nh->fib_nh_scope);
	} else {
		fib_nh_release(net, fib_nh);
	}
out:
	return err;
}

static int nh_create_ipv6(struct net *net,  struct nexthop *nh,
			  struct nh_info *nhi, struct nh_config *cfg,
			  struct netlink_ext_ack *extack)
{
	struct fib6_nh *fib6_nh = &nhi->fib6_nh;
	struct fib6_config fib6_cfg = {
		.fc_table = l3mdev_fib_table(cfg->dev),
		.fc_ifindex = cfg->nh_ifindex,
		.fc_gateway = cfg->gw.ipv6,
		.fc_flags = cfg->nh_flags,
		.fc_encap = cfg->nh_encap,
		.fc_encap_type = cfg->nh_encap_type,
	};
	int err;

	if (!ipv6_addr_any(&cfg->gw.ipv6))
		fib6_cfg.fc_flags |= RTF_GATEWAY;

	/* sets nh_dev if successful */
	err = ipv6_stub->fib6_nh_init(net, fib6_nh, &fib6_cfg, GFP_KERNEL,
				      extack);
	if (err)
		ipv6_stub->fib6_nh_release(fib6_nh);
	else
		nh->nh_flags = fib6_nh->fib_nh_flags;

	return err;
}

static struct nexthop *nexthop_create(struct net *net, struct nh_config *cfg,
				      struct netlink_ext_ack *extack)
{
	struct nh_info *nhi;
	struct nexthop *nh;
	int err = 0;

	nh = nexthop_alloc();
	if (!nh)
		return ERR_PTR(-ENOMEM);

	nhi = kzalloc(sizeof(*nhi), GFP_KERNEL);
	if (!nhi) {
		kfree(nh);
		return ERR_PTR(-ENOMEM);
	}

	nh->nh_flags = cfg->nh_flags;
	nh->net = net;

	nhi->nh_parent = nh;
	nhi->family = cfg->nh_family;
	nhi->fib_nhc.nhc_scope = RT_SCOPE_LINK;

	if (cfg->nh_blackhole) {
		nhi->reject_nh = 1;
		cfg->nh_ifindex = net->loopback_dev->ifindex;
	}

	switch (cfg->nh_family) {
	case AF_INET:
		err = nh_create_ipv4(net, nh, nhi, cfg, extack);
		break;
	case AF_INET6:
		err = nh_create_ipv6(net, nh, nhi, cfg, extack);
		break;
	}

	if (err) {
		kfree(nhi);
		kfree(nh);
		return ERR_PTR(err);
	}

	/* add the entry to the device based hash */
	nexthop_devhash_add(net, nhi);

	rcu_assign_pointer(nh->nh_info, nhi);

	return nh;
}

/* called with rtnl lock held */
static struct nexthop *nexthop_add(struct net *net, struct nh_config *cfg,
				   struct netlink_ext_ack *extack)
{
	struct nexthop *nh;
	int err;

	if (cfg->nlflags & NLM_F_REPLACE && !cfg->nh_id) {
		NL_SET_ERR_MSG(extack, "Replace requires nexthop id");
		return ERR_PTR(-EINVAL);
	}

	if (!cfg->nh_id) {
		cfg->nh_id = nh_find_unused_id(net);
		if (!cfg->nh_id) {
			NL_SET_ERR_MSG(extack, "No unused id");
			return ERR_PTR(-EINVAL);
		}
	}

	if (cfg->nh_grp)
		nh = nexthop_create_group(net, cfg);
	else
		nh = nexthop_create(net, cfg, extack);

	if (IS_ERR(nh))
		return nh;

	refcount_set(&nh->refcnt, 1);
	nh->id = cfg->nh_id;
	nh->protocol = cfg->nh_protocol;
	nh->net = net;

	err = insert_nexthop(net, nh, cfg, extack);
	if (err) {
		__remove_nexthop(net, nh, NULL);
		nexthop_put(nh);
		nh = ERR_PTR(err);
	}

	return nh;
}

static int rtm_to_nh_config(struct net *net, struct sk_buff *skb,
			    struct nlmsghdr *nlh, struct nh_config *cfg,
			    struct netlink_ext_ack *extack)
{
	struct nhmsg *nhm = nlmsg_data(nlh);
	struct nlattr *tb[NHA_MAX + 1];
	int err;

	err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy,
			  extack);
	if (err < 0)
		return err;

	err = -EINVAL;
	if (nhm->resvd || nhm->nh_scope) {
		NL_SET_ERR_MSG(extack, "Invalid values in ancillary header");
		goto out;
	}
	if (nhm->nh_flags & ~NEXTHOP_VALID_USER_FLAGS) {
		NL_SET_ERR_MSG(extack, "Invalid nexthop flags in ancillary header");
		goto out;
	}

	switch (nhm->nh_family) {
	case AF_INET:
	case AF_INET6:
		break;
	case AF_UNSPEC:
		if (tb[NHA_GROUP])
			break;
		/* fallthrough */
	default:
		NL_SET_ERR_MSG(extack, "Invalid address family");
		goto out;
	}

	if (tb[NHA_GROUPS] || tb[NHA_MASTER]) {
		NL_SET_ERR_MSG(extack, "Invalid attributes in request");
		goto out;
	}

	memset(cfg, 0, sizeof(*cfg));
	cfg->nlflags = nlh->nlmsg_flags;
	cfg->nlinfo.portid = NETLINK_CB(skb).portid;
	cfg->nlinfo.nlh = nlh;
	cfg->nlinfo.nl_net = net;

	cfg->nh_family = nhm->nh_family;
	cfg->nh_protocol = nhm->nh_protocol;
	cfg->nh_flags = nhm->nh_flags;

	if (tb[NHA_ID])
		cfg->nh_id = nla_get_u32(tb[NHA_ID]);

	if (tb[NHA_GROUP]) {
		if (nhm->nh_family != AF_UNSPEC) {
			NL_SET_ERR_MSG(extack, "Invalid family for group");
			goto out;
		}
		cfg->nh_grp = tb[NHA_GROUP];

		cfg->nh_grp_type = NEXTHOP_GRP_TYPE_MPATH;
		if (tb[NHA_GROUP_TYPE])
			cfg->nh_grp_type = nla_get_u16(tb[NHA_GROUP_TYPE]);

		if (cfg->nh_grp_type > NEXTHOP_GRP_TYPE_MAX) {
			NL_SET_ERR_MSG(extack, "Invalid group type");
			goto out;
		}
		err = nh_check_attr_group(net, tb, extack);

		/* no other attributes should be set */
		goto out;
	}

	if (tb[NHA_BLACKHOLE]) {
		if (tb[NHA_GATEWAY] || tb[NHA_OIF] ||
		    tb[NHA_ENCAP]   || tb[NHA_ENCAP_TYPE]) {
			NL_SET_ERR_MSG(extack, "Blackhole attribute can not be used with gateway or oif");
			goto out;
		}

		cfg->nh_blackhole = 1;
		err = 0;
		goto out;
	}

	if (!tb[NHA_OIF]) {
		NL_SET_ERR_MSG(extack, "Device attribute required for non-blackhole nexthops");
		goto out;
	}

	cfg->nh_ifindex = nla_get_u32(tb[NHA_OIF]);
	if (cfg->nh_ifindex)
		cfg->dev = __dev_get_by_index(net, cfg->nh_ifindex);

	if (!cfg->dev) {
		NL_SET_ERR_MSG(extack, "Invalid device index");
		goto out;
	} else if (!(cfg->dev->flags & IFF_UP)) {
		NL_SET_ERR_MSG(extack, "Nexthop device is not up");
		err = -ENETDOWN;
		goto out;
	} else if (!netif_carrier_ok(cfg->dev)) {
		NL_SET_ERR_MSG(extack, "Carrier for nexthop device is down");
		err = -ENETDOWN;
		goto out;
	}

	err = -EINVAL;
	if (tb[NHA_GATEWAY]) {
		struct nlattr *gwa = tb[NHA_GATEWAY];

		switch (cfg->nh_family) {
		case AF_INET:
			if (nla_len(gwa) != sizeof(u32)) {
				NL_SET_ERR_MSG(extack, "Invalid gateway");
				goto out;
			}
			cfg->gw.ipv4 = nla_get_be32(gwa);
			break;
		case AF_INET6:
			if (nla_len(gwa) != sizeof(struct in6_addr)) {
				NL_SET_ERR_MSG(extack, "Invalid gateway");
				goto out;
			}
			cfg->gw.ipv6 = nla_get_in6_addr(gwa);
			break;
		default:
			NL_SET_ERR_MSG(extack,
				       "Unknown address family for gateway");
			goto out;
		}
	} else {
		/* device only nexthop (no gateway) */
		if (cfg->nh_flags & RTNH_F_ONLINK) {
			NL_SET_ERR_MSG(extack,
				       "ONLINK flag can not be set for nexthop without a gateway");
			goto out;
		}
	}

	if (tb[NHA_ENCAP]) {
		cfg->nh_encap = tb[NHA_ENCAP];

		if (!tb[NHA_ENCAP_TYPE]) {
			NL_SET_ERR_MSG(extack, "LWT encapsulation type is missing");
			goto out;
		}

		cfg->nh_encap_type = nla_get_u16(tb[NHA_ENCAP_TYPE]);
		err = lwtunnel_valid_encap_type(cfg->nh_encap_type, extack);
		if (err < 0)
			goto out;

	} else if (tb[NHA_ENCAP_TYPE]) {
		NL_SET_ERR_MSG(extack, "LWT encapsulation attribute is missing");
		goto out;
	}


	err = 0;
out:
	return err;
}

/* rtnl */
static int rtm_new_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
			   struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nh_config cfg;
	struct nexthop *nh;
	int err;

	err = rtm_to_nh_config(net, skb, nlh, &cfg, extack);
	if (!err) {
		nh = nexthop_add(net, &cfg, extack);
		if (IS_ERR(nh))
			err = PTR_ERR(nh);
	}

	return err;
}

static int nh_valid_get_del_req(struct nlmsghdr *nlh, u32 *id,
				struct netlink_ext_ack *extack)
{
	struct nhmsg *nhm = nlmsg_data(nlh);
	struct nlattr *tb[NHA_MAX + 1];
	int err, i;

	err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy,
			  extack);
	if (err < 0)
		return err;

	err = -EINVAL;
	for (i = 0; i < __NHA_MAX; ++i) {
		if (!tb[i])
			continue;

		switch (i) {
		case NHA_ID:
			break;
		default:
			NL_SET_ERR_MSG_ATTR(extack, tb[i],
					    "Unexpected attribute in request");
			goto out;
		}
	}
	if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) {
		NL_SET_ERR_MSG(extack, "Invalid values in header");
		goto out;
	}

	if (!tb[NHA_ID]) {
		NL_SET_ERR_MSG(extack, "Nexthop id is missing");
		goto out;
	}

	*id = nla_get_u32(tb[NHA_ID]);
	if (!(*id))
		NL_SET_ERR_MSG(extack, "Invalid nexthop id");
	else
		err = 0;
out:
	return err;
}

/* rtnl */
static int rtm_del_nexthop(struct sk_buff *skb, struct nlmsghdr *nlh,
			   struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(skb->sk);
	struct nl_info nlinfo = {
		.nlh = nlh,
		.nl_net = net,
		.portid = NETLINK_CB(skb).portid,
	};
	struct nexthop *nh;
	int err;
	u32 id;

	err = nh_valid_get_del_req(nlh, &id, extack);
	if (err)
		return err;

	nh = nexthop_find_by_id(net, id);
	if (!nh)
		return -ENOENT;

	remove_nexthop(net, nh, &nlinfo);

	return 0;
}

/* rtnl */
static int rtm_get_nexthop(struct sk_buff *in_skb, struct nlmsghdr *nlh,
			   struct netlink_ext_ack *extack)
{
	struct net *net = sock_net(in_skb->sk);
	struct sk_buff *skb = NULL;
	struct nexthop *nh;
	int err;
	u32 id;

	err = nh_valid_get_del_req(nlh, &id, extack);
	if (err)
		return err;

	err = -ENOBUFS;
	skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
	if (!skb)
		goto out;

	err = -ENOENT;
	nh = nexthop_find_by_id(net, id);
	if (!nh)
		goto errout_free;

	err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP, NETLINK_CB(in_skb).portid,
			   nlh->nlmsg_seq, 0);
	if (err < 0) {
		WARN_ON(err == -EMSGSIZE);
		goto errout_free;
	}

	err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
out:
	return err;
errout_free:
	kfree_skb(skb);
	goto out;
}

static bool nh_dump_filtered(struct nexthop *nh, int dev_idx, int master_idx,
			     bool group_filter, u8 family)
{
	const struct net_device *dev;
	const struct nh_info *nhi;

	if (group_filter && !nh->is_group)
		return true;

	if (!dev_idx && !master_idx && !family)
		return false;

	if (nh->is_group)
		return true;

	nhi = rtnl_dereference(nh->nh_info);
	if (family && nhi->family != family)
		return true;

	dev = nhi->fib_nhc.nhc_dev;
	if (dev_idx && (!dev || dev->ifindex != dev_idx))
		return true;

	if (master_idx) {
		struct net_device *master;

		if (!dev)
			return true;

		master = netdev_master_upper_dev_get((struct net_device *)dev);
		if (!master || master->ifindex != master_idx)
			return true;
	}

	return false;
}

static int nh_valid_dump_req(const struct nlmsghdr *nlh, int *dev_idx,
			     int *master_idx, bool *group_filter,
			     struct netlink_callback *cb)
{
	struct netlink_ext_ack *extack = cb->extack;
	struct nlattr *tb[NHA_MAX + 1];
	struct nhmsg *nhm;
	int err, i;
	u32 idx;

	err = nlmsg_parse(nlh, sizeof(*nhm), tb, NHA_MAX, rtm_nh_policy,
			  NULL);
	if (err < 0)
		return err;

	for (i = 0; i <= NHA_MAX; ++i) {
		if (!tb[i])
			continue;

		switch (i) {
		case NHA_OIF:
			idx = nla_get_u32(tb[i]);
			if (idx > INT_MAX) {
				NL_SET_ERR_MSG(extack, "Invalid device index");
				return -EINVAL;
			}
			*dev_idx = idx;
			break;
		case NHA_MASTER:
			idx = nla_get_u32(tb[i]);
			if (idx > INT_MAX) {
				NL_SET_ERR_MSG(extack, "Invalid master device index");
				return -EINVAL;
			}
			*master_idx = idx;
			break;
		case NHA_GROUPS:
			*group_filter = true;
			break;
		default:
			NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request");
			return -EINVAL;
		}
	}

	nhm = nlmsg_data(nlh);
	if (nhm->nh_protocol || nhm->resvd || nhm->nh_scope || nhm->nh_flags) {
		NL_SET_ERR_MSG(extack, "Invalid values in header for nexthop dump request");
		return -EINVAL;
	}

	return 0;
}

/* rtnl */
static int rtm_dump_nexthop(struct sk_buff *skb, struct netlink_callback *cb)
{
	struct nhmsg *nhm = nlmsg_data(cb->nlh);
	int dev_filter_idx = 0, master_idx = 0;
	struct net *net = sock_net(skb->sk);
	struct rb_root *root = &net->nexthop.rb_root;
	bool group_filter = false;
	struct rb_node *node;
	int idx = 0, s_idx;
	int err;

	err = nh_valid_dump_req(cb->nlh, &dev_filter_idx, &master_idx,
				&group_filter, cb);
	if (err < 0)
		return err;

	s_idx = cb->args[0];
	for (node = rb_first(root); node; node = rb_next(node)) {
		struct nexthop *nh;

		if (idx < s_idx)
			goto cont;

		nh = rb_entry(node, struct nexthop, rb_node);
		if (nh_dump_filtered(nh, dev_filter_idx, master_idx,
				     group_filter, nhm->nh_family))
			goto cont;

		err = nh_fill_node(skb, nh, RTM_NEWNEXTHOP,
				   NETLINK_CB(cb->skb).portid,
				   cb->nlh->nlmsg_seq, NLM_F_MULTI);
		if (err < 0) {
			if (likely(skb->len))
				goto out;

			goto out_err;
		}
cont:
		idx++;
	}

out:
	err = skb->len;
out_err:
	cb->args[0] = idx;
	cb->seq = net->nexthop.seq;
	nl_dump_check_consistent(cb, nlmsg_hdr(skb));

	return err;
}

static void nexthop_sync_mtu(struct net_device *dev, u32 orig_mtu)
{
	unsigned int hash = nh_dev_hashfn(dev->ifindex);
	struct net *net = dev_net(dev);
	struct hlist_head *head = &net->nexthop.devhash[hash];
	struct hlist_node *n;
	struct nh_info *nhi;

	hlist_for_each_entry_safe(nhi, n, head, dev_hash) {
		if (nhi->fib_nhc.nhc_dev == dev) {
			if (nhi->family == AF_INET)
				fib_nhc_update_mtu(&nhi->fib_nhc, dev->mtu,
						   orig_mtu);
		}
	}
}

/* rtnl */
static int nh_netdev_event(struct notifier_block *this,
			   unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
	struct netdev_notifier_info_ext *info_ext;

	switch (event) {
	case NETDEV_DOWN:
	case NETDEV_UNREGISTER:
		nexthop_flush_dev(dev);
		break;
	case NETDEV_CHANGE:
		if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP)))
			nexthop_flush_dev(dev);
		break;
	case NETDEV_CHANGEMTU:
		info_ext = ptr;
		nexthop_sync_mtu(dev, info_ext->ext.mtu);
		rt_cache_flush(dev_net(dev));
		break;
	}
	return NOTIFY_DONE;
}

static struct notifier_block nh_netdev_notifier = {
	.notifier_call = nh_netdev_event,
};

static void __net_exit nexthop_net_exit(struct net *net)
{
	rtnl_lock();
	flush_all_nexthops(net);
	rtnl_unlock();
	kfree(net->nexthop.devhash);
}

static int __net_init nexthop_net_init(struct net *net)
{
	size_t sz = sizeof(struct hlist_head) * NH_DEV_HASHSIZE;

	net->nexthop.rb_root = RB_ROOT;
	net->nexthop.devhash = kzalloc(sz, GFP_KERNEL);
	if (!net->nexthop.devhash)
		return -ENOMEM;

	return 0;
}

static struct pernet_operations nexthop_net_ops = {
	.init = nexthop_net_init,
	.exit = nexthop_net_exit,
};

static int __init nexthop_init(void)
{
	register_pernet_subsys(&nexthop_net_ops);

	register_netdevice_notifier(&nh_netdev_notifier);

	rtnl_register(PF_UNSPEC, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_DELNEXTHOP, rtm_del_nexthop, NULL, 0);
	rtnl_register(PF_UNSPEC, RTM_GETNEXTHOP, rtm_get_nexthop,
		      rtm_dump_nexthop, 0);

	rtnl_register(PF_INET, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0);
	rtnl_register(PF_INET, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0);

	rtnl_register(PF_INET6, RTM_NEWNEXTHOP, rtm_new_nexthop, NULL, 0);
	rtnl_register(PF_INET6, RTM_GETNEXTHOP, NULL, rtm_dump_nexthop, 0);

	return 0;
}
subsys_initcall(nexthop_init);