summaryrefslogtreecommitdiffstats
path: root/drivers/net/vrf.c
blob: 6b5a4d036d1533886654ff6de21a517bf9d9b4af (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
1050
1051
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
1088
1089
1090
1091
1092
1093
1094
1095
1096
1097
1098
1099
1100
1101
1102
1103
1104
1105
1106
1107
1108
1109
1110
1111
1112
1113
1114
1115
1116
1117
1118
1119
1120
1121
1122
1123
1124
1125
1126
1127
1128
1129
1130
1131
1132
1133
1134
1135
1136
1137
1138
1139
1140
1141
1142
1143
1144
1145
1146
1147
1148
1149
1150
1151
1152
1153
1154
1155
1156
1157
1158
1159
1160
1161
1162
1163
1164
1165
1166
1167
1168
1169
1170
1171
1172
1173
1174
1175
1176
1177
1178
1179
1180
1181
1182
1183
1184
1185
1186
1187
1188
1189
1190
1191
1192
1193
1194
1195
1196
1197
1198
1199
1200
1201
1202
1203
1204
1205
1206
1207
1208
1209
1210
1211
1212
1213
1214
1215
1216
1217
1218
1219
1220
1221
1222
1223
1224
1225
1226
1227
1228
1229
1230
1231
1232
1233
1234
1235
1236
1237
1238
1239
1240
1241
1242
1243
1244
1245
1246
1247
1248
1249
1250
1251
1252
1253
1254
1255
1256
1257
1258
1259
1260
1261
1262
1263
1264
1265
1266
1267
1268
1269
1270
1271
1272
1273
1274
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
1391
1392
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
1609
1610
1611
1612
1613
1614
1615
1616
1617
1618
1619
1620
1621
1622
1623
1624
1625
1626
1627
1628
1629
1630
1631
1632
1633
1634
1635
1636
1637
1638
1639
1640
1641
1642
1643
1644
1645
1646
1647
1648
1649
1650
1651
1652
1653
1654
1655
1656
1657
1658
1659
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
1711
1712
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
1743
1744
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
1801
1802
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
1906
1907
1908
1909
1910
1911
1912
1913
1914
1915
1916
1917
1918
1919
1920
1921
1922
1923
1924
1925
1926
1927
1928
1929
1930
1931
1932
1933
1934
1935
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
1991
1992
1993
1994
1995
1996
1997
1998
1999
2000
2001
2002
2003
2004
2005
2006
2007
2008
2009
2010
2011
2012
2013
2014
2015
2016
2017
2018
2019
2020
2021
2022
2023
2024
2025
2026
2027
2028
2029
2030
2031
2032
2033
2034
2035
2036
2037
2038
2039
2040
2041
2042
2043
2044
2045
2046
2047
2048
2049
2050
2051
2052
2053
2054
2055
2056
2057
2058
2059
2060
2061
2062
2063
2064
2065
2066
2067
2068
2069
2070
2071
2072
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * vrf.c: device driver to encapsulate a VRF space
 *
 * Copyright (c) 2015 Cumulus Networks. All rights reserved.
 * Copyright (c) 2015 Shrijeet Mukherjee <shm@cumulusnetworks.com>
 * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com>
 *
 * Based on dummy, team and ipvlan drivers
 */

#include <linux/ethtool.h>
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/ip.h>
#include <linux/init.h>
#include <linux/moduleparam.h>
#include <linux/netfilter.h>
#include <linux/rtnetlink.h>
#include <net/rtnetlink.h>
#include <linux/u64_stats_sync.h>
#include <linux/hashtable.h>
#include <linux/spinlock_types.h>

#include <linux/inetdevice.h>
#include <net/arp.h>
#include <net/ip.h>
#include <net/ip_fib.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#include <net/route.h>
#include <net/addrconf.h>
#include <net/l3mdev.h>
#include <net/fib_rules.h>
#include <net/sch_generic.h>
#include <net/netns/generic.h>
#include <net/netfilter/nf_conntrack.h>

#define DRV_NAME	"vrf"
#define DRV_VERSION	"1.1"

#define FIB_RULE_PREF  1000       /* default preference for FIB rules */

#define HT_MAP_BITS	4
#define HASH_INITVAL	((u32)0xcafef00d)

struct  vrf_map {
	DECLARE_HASHTABLE(ht, HT_MAP_BITS);
	spinlock_t vmap_lock;

	/* shared_tables:
	 * count how many distinct tables do not comply with the strict mode
	 * requirement.
	 * shared_tables value must be 0 in order to enable the strict mode.
	 *
	 * example of the evolution of shared_tables:
	 *                                                        | time
	 * add  vrf0 --> table 100        shared_tables = 0       | t0
	 * add  vrf1 --> table 101        shared_tables = 0       | t1
	 * add  vrf2 --> table 100        shared_tables = 1       | t2
	 * add  vrf3 --> table 100        shared_tables = 1       | t3
	 * add  vrf4 --> table 101        shared_tables = 2       v t4
	 *
	 * shared_tables is a "step function" (or "staircase function")
	 * and it is increased by one when the second vrf is associated to a
	 * table.
	 *
	 * at t2, vrf0 and vrf2 are bound to table 100: shared_tables = 1.
	 *
	 * at t3, another dev (vrf3) is bound to the same table 100 but the
	 * value of shared_tables is still 1.
	 * This means that no matter how many new vrfs will register on the
	 * table 100, the shared_tables will not increase (considering only
	 * table 100).
	 *
	 * at t4, vrf4 is bound to table 101, and shared_tables = 2.
	 *
	 * Looking at the value of shared_tables we can immediately know if
	 * the strict_mode can or cannot be enforced. Indeed, strict_mode
	 * can be enforced iff shared_tables = 0.
	 *
	 * Conversely, shared_tables is decreased when a vrf is de-associated
	 * from a table with exactly two associated vrfs.
	 */
	u32 shared_tables;

	bool strict_mode;
};

struct vrf_map_elem {
	struct hlist_node hnode;
	struct list_head vrf_list;  /* VRFs registered to this table */

	u32 table_id;
	int users;
	int ifindex;
};

static unsigned int vrf_net_id;

/* per netns vrf data */
struct netns_vrf {
	/* protected by rtnl lock */
	bool add_fib_rules;

	struct vrf_map vmap;
	struct ctl_table_header	*ctl_hdr;
};

struct net_vrf {
	struct rtable __rcu	*rth;
	struct rt6_info	__rcu	*rt6;
#if IS_ENABLED(CONFIG_IPV6)
	struct fib6_table	*fib6_table;
#endif
	u32                     tb_id;

	struct list_head	me_list;   /* entry in vrf_map_elem */
	int			ifindex;
};

struct pcpu_dstats {
	u64			tx_pkts;
	u64			tx_bytes;
	u64			tx_drps;
	u64			rx_pkts;
	u64			rx_bytes;
	u64			rx_drps;
	struct u64_stats_sync	syncp;
};

static void vrf_rx_stats(struct net_device *dev, int len)
{
	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);

	u64_stats_update_begin(&dstats->syncp);
	dstats->rx_pkts++;
	dstats->rx_bytes += len;
	u64_stats_update_end(&dstats->syncp);
}

static void vrf_tx_error(struct net_device *vrf_dev, struct sk_buff *skb)
{
	vrf_dev->stats.tx_errors++;
	kfree_skb(skb);
}

static void vrf_get_stats64(struct net_device *dev,
			    struct rtnl_link_stats64 *stats)
{
	int i;

	for_each_possible_cpu(i) {
		const struct pcpu_dstats *dstats;
		u64 tbytes, tpkts, tdrops, rbytes, rpkts;
		unsigned int start;

		dstats = per_cpu_ptr(dev->dstats, i);
		do {
			start = u64_stats_fetch_begin(&dstats->syncp);
			tbytes = dstats->tx_bytes;
			tpkts = dstats->tx_pkts;
			tdrops = dstats->tx_drps;
			rbytes = dstats->rx_bytes;
			rpkts = dstats->rx_pkts;
		} while (u64_stats_fetch_retry(&dstats->syncp, start));
		stats->tx_bytes += tbytes;
		stats->tx_packets += tpkts;
		stats->tx_dropped += tdrops;
		stats->rx_bytes += rbytes;
		stats->rx_packets += rpkts;
	}
}

static struct vrf_map *netns_vrf_map(struct net *net)
{
	struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id);

	return &nn_vrf->vmap;
}

static struct vrf_map *netns_vrf_map_by_dev(struct net_device *dev)
{
	return netns_vrf_map(dev_net(dev));
}

static int vrf_map_elem_get_vrf_ifindex(struct vrf_map_elem *me)
{
	struct list_head *me_head = &me->vrf_list;
	struct net_vrf *vrf;

	if (list_empty(me_head))
		return -ENODEV;

	vrf = list_first_entry(me_head, struct net_vrf, me_list);

	return vrf->ifindex;
}

static struct vrf_map_elem *vrf_map_elem_alloc(gfp_t flags)
{
	struct vrf_map_elem *me;

	me = kmalloc(sizeof(*me), flags);
	if (!me)
		return NULL;

	return me;
}

static void vrf_map_elem_free(struct vrf_map_elem *me)
{
	kfree(me);
}

static void vrf_map_elem_init(struct vrf_map_elem *me, int table_id,
			      int ifindex, int users)
{
	me->table_id = table_id;
	me->ifindex = ifindex;
	me->users = users;
	INIT_LIST_HEAD(&me->vrf_list);
}

static struct vrf_map_elem *vrf_map_lookup_elem(struct vrf_map *vmap,
						u32 table_id)
{
	struct vrf_map_elem *me;
	u32 key;

	key = jhash_1word(table_id, HASH_INITVAL);
	hash_for_each_possible(vmap->ht, me, hnode, key) {
		if (me->table_id == table_id)
			return me;
	}

	return NULL;
}

static void vrf_map_add_elem(struct vrf_map *vmap, struct vrf_map_elem *me)
{
	u32 table_id = me->table_id;
	u32 key;

	key = jhash_1word(table_id, HASH_INITVAL);
	hash_add(vmap->ht, &me->hnode, key);
}

static void vrf_map_del_elem(struct vrf_map_elem *me)
{
	hash_del(&me->hnode);
}

static void vrf_map_lock(struct vrf_map *vmap) __acquires(&vmap->vmap_lock)
{
	spin_lock(&vmap->vmap_lock);
}

static void vrf_map_unlock(struct vrf_map *vmap) __releases(&vmap->vmap_lock)
{
	spin_unlock(&vmap->vmap_lock);
}

/* called with rtnl lock held */
static int
vrf_map_register_dev(struct net_device *dev, struct netlink_ext_ack *extack)
{
	struct vrf_map *vmap = netns_vrf_map_by_dev(dev);
	struct net_vrf *vrf = netdev_priv(dev);
	struct vrf_map_elem *new_me, *me;
	u32 table_id = vrf->tb_id;
	bool free_new_me = false;
	int users;
	int res;

	/* we pre-allocate elements used in the spin-locked section (so that we
	 * keep the spinlock as short as possible).
	 */
	new_me = vrf_map_elem_alloc(GFP_KERNEL);
	if (!new_me)
		return -ENOMEM;

	vrf_map_elem_init(new_me, table_id, dev->ifindex, 0);

	vrf_map_lock(vmap);

	me = vrf_map_lookup_elem(vmap, table_id);
	if (!me) {
		me = new_me;
		vrf_map_add_elem(vmap, me);
		goto link_vrf;
	}

	/* we already have an entry in the vrf_map, so it means there is (at
	 * least) a vrf registered on the specific table.
	 */
	free_new_me = true;
	if (vmap->strict_mode) {
		/* vrfs cannot share the same table */
		NL_SET_ERR_MSG(extack, "Table is used by another VRF");
		res = -EBUSY;
		goto unlock;
	}

link_vrf:
	users = ++me->users;
	if (users == 2)
		++vmap->shared_tables;

	list_add(&vrf->me_list, &me->vrf_list);

	res = 0;

unlock:
	vrf_map_unlock(vmap);

	/* clean-up, if needed */
	if (free_new_me)
		vrf_map_elem_free(new_me);

	return res;
}

/* called with rtnl lock held */
static void vrf_map_unregister_dev(struct net_device *dev)
{
	struct vrf_map *vmap = netns_vrf_map_by_dev(dev);
	struct net_vrf *vrf = netdev_priv(dev);
	u32 table_id = vrf->tb_id;
	struct vrf_map_elem *me;
	int users;

	vrf_map_lock(vmap);

	me = vrf_map_lookup_elem(vmap, table_id);
	if (!me)
		goto unlock;

	list_del(&vrf->me_list);

	users = --me->users;
	if (users == 1) {
		--vmap->shared_tables;
	} else if (users == 0) {
		vrf_map_del_elem(me);

		/* no one will refer to this element anymore */
		vrf_map_elem_free(me);
	}

unlock:
	vrf_map_unlock(vmap);
}

/* return the vrf device index associated with the table_id */
static int vrf_ifindex_lookup_by_table_id(struct net *net, u32 table_id)
{
	struct vrf_map *vmap = netns_vrf_map(net);
	struct vrf_map_elem *me;
	int ifindex;

	vrf_map_lock(vmap);

	if (!vmap->strict_mode) {
		ifindex = -EPERM;
		goto unlock;
	}

	me = vrf_map_lookup_elem(vmap, table_id);
	if (!me) {
		ifindex = -ENODEV;
		goto unlock;
	}

	ifindex = vrf_map_elem_get_vrf_ifindex(me);

unlock:
	vrf_map_unlock(vmap);

	return ifindex;
}

/* by default VRF devices do not have a qdisc and are expected
 * to be created with only a single queue.
 */
static bool qdisc_tx_is_default(const struct net_device *dev)
{
	struct netdev_queue *txq;
	struct Qdisc *qdisc;

	if (dev->num_tx_queues > 1)
		return false;

	txq = netdev_get_tx_queue(dev, 0);
	qdisc = rcu_access_pointer(txq->qdisc);

	return !qdisc->enqueue;
}

/* Local traffic destined to local address. Reinsert the packet to rx
 * path, similar to loopback handling.
 */
static int vrf_local_xmit(struct sk_buff *skb, struct net_device *dev,
			  struct dst_entry *dst)
{
	int len = skb->len;

	skb_orphan(skb);

	skb_dst_set(skb, dst);

	/* set pkt_type to avoid skb hitting packet taps twice -
	 * once on Tx and again in Rx processing
	 */
	skb->pkt_type = PACKET_LOOPBACK;

	skb->protocol = eth_type_trans(skb, dev);

	if (likely(__netif_rx(skb) == NET_RX_SUCCESS))
		vrf_rx_stats(dev, len);
	else
		this_cpu_inc(dev->dstats->rx_drps);

	return NETDEV_TX_OK;
}

static void vrf_nf_set_untracked(struct sk_buff *skb)
{
	if (skb_get_nfct(skb) == 0)
		nf_ct_set(skb, NULL, IP_CT_UNTRACKED);
}

static void vrf_nf_reset_ct(struct sk_buff *skb)
{
	if (skb_get_nfct(skb) == IP_CT_UNTRACKED)
		nf_reset_ct(skb);
}

#if IS_ENABLED(CONFIG_IPV6)
static int vrf_ip6_local_out(struct net *net, struct sock *sk,
			     struct sk_buff *skb)
{
	int err;

	vrf_nf_reset_ct(skb);

	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net,
		      sk, skb, NULL, skb_dst(skb)->dev, dst_output);

	if (likely(err == 1))
		err = dst_output(net, sk, skb);

	return err;
}

static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
					   struct net_device *dev)
{
	const struct ipv6hdr *iph;
	struct net *net = dev_net(skb->dev);
	struct flowi6 fl6;
	int ret = NET_XMIT_DROP;
	struct dst_entry *dst;
	struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;

	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr)))
		goto err;

	iph = ipv6_hdr(skb);

	memset(&fl6, 0, sizeof(fl6));
	/* needed to match OIF rule */
	fl6.flowi6_l3mdev = dev->ifindex;
	fl6.flowi6_iif = LOOPBACK_IFINDEX;
	fl6.daddr = iph->daddr;
	fl6.saddr = iph->saddr;
	fl6.flowlabel = ip6_flowinfo(iph);
	fl6.flowi6_mark = skb->mark;
	fl6.flowi6_proto = iph->nexthdr;

	dst = ip6_dst_lookup_flow(net, NULL, &fl6, NULL);
	if (IS_ERR(dst) || dst == dst_null)
		goto err;

	skb_dst_drop(skb);

	/* if dst.dev is the VRF device again this is locally originated traffic
	 * destined to a local address. Short circuit to Rx path.
	 */
	if (dst->dev == dev)
		return vrf_local_xmit(skb, dev, dst);

	skb_dst_set(skb, dst);

	/* strip the ethernet header added for pass through VRF device */
	__skb_pull(skb, skb_network_offset(skb));

	memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
	ret = vrf_ip6_local_out(net, skb->sk, skb);
	if (unlikely(net_xmit_eval(ret)))
		dev->stats.tx_errors++;
	else
		ret = NET_XMIT_SUCCESS;

	return ret;
err:
	vrf_tx_error(dev, skb);
	return NET_XMIT_DROP;
}
#else
static netdev_tx_t vrf_process_v6_outbound(struct sk_buff *skb,
					   struct net_device *dev)
{
	vrf_tx_error(dev, skb);
	return NET_XMIT_DROP;
}
#endif

/* based on ip_local_out; can't use it b/c the dst is switched pointing to us */
static int vrf_ip_local_out(struct net *net, struct sock *sk,
			    struct sk_buff *skb)
{
	int err;

	vrf_nf_reset_ct(skb);

	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
		      skb, NULL, skb_dst(skb)->dev, dst_output);
	if (likely(err == 1))
		err = dst_output(net, sk, skb);

	return err;
}

static netdev_tx_t vrf_process_v4_outbound(struct sk_buff *skb,
					   struct net_device *vrf_dev)
{
	struct iphdr *ip4h;
	int ret = NET_XMIT_DROP;
	struct flowi4 fl4;
	struct net *net = dev_net(vrf_dev);
	struct rtable *rt;

	if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr)))
		goto err;

	ip4h = ip_hdr(skb);

	memset(&fl4, 0, sizeof(fl4));
	/* needed to match OIF rule */
	fl4.flowi4_l3mdev = vrf_dev->ifindex;
	fl4.flowi4_iif = LOOPBACK_IFINDEX;
	fl4.flowi4_tos = RT_TOS(ip4h->tos);
	fl4.flowi4_flags = FLOWI_FLAG_ANYSRC;
	fl4.flowi4_proto = ip4h->protocol;
	fl4.daddr = ip4h->daddr;
	fl4.saddr = ip4h->saddr;

	rt = ip_route_output_flow(net, &fl4, NULL);
	if (IS_ERR(rt))
		goto err;

	skb_dst_drop(skb);

	/* if dst.dev is the VRF device again this is locally originated traffic
	 * destined to a local address. Short circuit to Rx path.
	 */
	if (rt->dst.dev == vrf_dev)
		return vrf_local_xmit(skb, vrf_dev, &rt->dst);

	skb_dst_set(skb, &rt->dst);

	/* strip the ethernet header added for pass through VRF device */
	__skb_pull(skb, skb_network_offset(skb));

	if (!ip4h->saddr) {
		ip4h->saddr = inet_select_addr(skb_dst(skb)->dev, 0,
					       RT_SCOPE_LINK);
	}

	memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
	ret = vrf_ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
	if (unlikely(net_xmit_eval(ret)))
		vrf_dev->stats.tx_errors++;
	else
		ret = NET_XMIT_SUCCESS;

out:
	return ret;
err:
	vrf_tx_error(vrf_dev, skb);
	goto out;
}

static netdev_tx_t is_ip_tx_frame(struct sk_buff *skb, struct net_device *dev)
{
	switch (skb->protocol) {
	case htons(ETH_P_IP):
		return vrf_process_v4_outbound(skb, dev);
	case htons(ETH_P_IPV6):
		return vrf_process_v6_outbound(skb, dev);
	default:
		vrf_tx_error(dev, skb);
		return NET_XMIT_DROP;
	}
}

static netdev_tx_t vrf_xmit(struct sk_buff *skb, struct net_device *dev)
{
	int len = skb->len;
	netdev_tx_t ret = is_ip_tx_frame(skb, dev);

	if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) {
		struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);

		u64_stats_update_begin(&dstats->syncp);
		dstats->tx_pkts++;
		dstats->tx_bytes += len;
		u64_stats_update_end(&dstats->syncp);
	} else {
		this_cpu_inc(dev->dstats->tx_drps);
	}

	return ret;
}

static void vrf_finish_direct(struct sk_buff *skb)
{
	struct net_device *vrf_dev = skb->dev;

	if (!list_empty(&vrf_dev->ptype_all) &&
	    likely(skb_headroom(skb) >= ETH_HLEN)) {
		struct ethhdr *eth = skb_push(skb, ETH_HLEN);

		ether_addr_copy(eth->h_source, vrf_dev->dev_addr);
		eth_zero_addr(eth->h_dest);
		eth->h_proto = skb->protocol;

		rcu_read_lock_bh();
		dev_queue_xmit_nit(skb, vrf_dev);
		rcu_read_unlock_bh();

		skb_pull(skb, ETH_HLEN);
	}

	vrf_nf_reset_ct(skb);
}

#if IS_ENABLED(CONFIG_IPV6)
/* modelled after ip6_finish_output2 */
static int vrf_finish_output6(struct net *net, struct sock *sk,
			      struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct net_device *dev = dst->dev;
	const struct in6_addr *nexthop;
	struct neighbour *neigh;
	int ret;

	vrf_nf_reset_ct(skb);

	skb->protocol = htons(ETH_P_IPV6);
	skb->dev = dev;

	rcu_read_lock_bh();
	nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
	neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
	if (unlikely(!neigh))
		neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
	if (!IS_ERR(neigh)) {
		sock_confirm_neigh(skb, neigh);
		ret = neigh_output(neigh, skb, false);
		rcu_read_unlock_bh();
		return ret;
	}
	rcu_read_unlock_bh();

	IP6_INC_STATS(dev_net(dst->dev),
		      ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
	kfree_skb(skb);
	return -EINVAL;
}

/* modelled after ip6_output */
static int vrf_output6(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
			    net, sk, skb, NULL, skb_dst(skb)->dev,
			    vrf_finish_output6,
			    !(IP6CB(skb)->flags & IP6SKB_REROUTED));
}

/* set dst on skb to send packet to us via dev_xmit path. Allows
 * packet to go through device based features such as qdisc, netfilter
 * hooks and packet sockets with skb->dev set to vrf device.
 */
static struct sk_buff *vrf_ip6_out_redirect(struct net_device *vrf_dev,
					    struct sk_buff *skb)
{
	struct net_vrf *vrf = netdev_priv(vrf_dev);
	struct dst_entry *dst = NULL;
	struct rt6_info *rt6;

	rcu_read_lock();

	rt6 = rcu_dereference(vrf->rt6);
	if (likely(rt6)) {
		dst = &rt6->dst;
		dst_hold(dst);
	}

	rcu_read_unlock();

	if (unlikely(!dst)) {
		vrf_tx_error(vrf_dev, skb);
		return NULL;
	}

	skb_dst_drop(skb);
	skb_dst_set(skb, dst);

	return skb;
}

static int vrf_output6_direct_finish(struct net *net, struct sock *sk,
				     struct sk_buff *skb)
{
	vrf_finish_direct(skb);

	return vrf_ip6_local_out(net, sk, skb);
}

static int vrf_output6_direct(struct net *net, struct sock *sk,
			      struct sk_buff *skb)
{
	int err = 1;

	skb->protocol = htons(ETH_P_IPV6);

	if (!(IPCB(skb)->flags & IPSKB_REROUTED))
		err = nf_hook(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb,
			      NULL, skb->dev, vrf_output6_direct_finish);

	if (likely(err == 1))
		vrf_finish_direct(skb);

	return err;
}

static int vrf_ip6_out_direct_finish(struct net *net, struct sock *sk,
				     struct sk_buff *skb)
{
	int err;

	err = vrf_output6_direct(net, sk, skb);
	if (likely(err == 1))
		err = vrf_ip6_local_out(net, sk, skb);

	return err;
}

static struct sk_buff *vrf_ip6_out_direct(struct net_device *vrf_dev,
					  struct sock *sk,
					  struct sk_buff *skb)
{
	struct net *net = dev_net(vrf_dev);
	int err;

	skb->dev = vrf_dev;

	err = nf_hook(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk,
		      skb, NULL, vrf_dev, vrf_ip6_out_direct_finish);

	if (likely(err == 1))
		err = vrf_output6_direct(net, sk, skb);

	if (likely(err == 1))
		return skb;

	return NULL;
}

static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
				   struct sock *sk,
				   struct sk_buff *skb)
{
	/* don't divert link scope packets */
	if (rt6_need_strict(&ipv6_hdr(skb)->daddr))
		return skb;

	vrf_nf_set_untracked(skb);

	if (qdisc_tx_is_default(vrf_dev) ||
	    IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED)
		return vrf_ip6_out_direct(vrf_dev, sk, skb);

	return vrf_ip6_out_redirect(vrf_dev, skb);
}

/* holding rtnl */
static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
{
	struct rt6_info *rt6 = rtnl_dereference(vrf->rt6);
	struct net *net = dev_net(dev);
	struct dst_entry *dst;

	RCU_INIT_POINTER(vrf->rt6, NULL);
	synchronize_rcu();

	/* move dev in dst's to loopback so this VRF device can be deleted
	 * - based on dst_ifdown
	 */
	if (rt6) {
		dst = &rt6->dst;
		netdev_ref_replace(dst->dev, net->loopback_dev,
				   &dst->dev_tracker, GFP_KERNEL);
		dst->dev = net->loopback_dev;
		dst_release(dst);
	}
}

static int vrf_rt6_create(struct net_device *dev)
{
	int flags = DST_NOPOLICY | DST_NOXFRM;
	struct net_vrf *vrf = netdev_priv(dev);
	struct net *net = dev_net(dev);
	struct rt6_info *rt6;
	int rc = -ENOMEM;

	/* IPv6 can be CONFIG enabled and then disabled runtime */
	if (!ipv6_mod_enabled())
		return 0;

	vrf->fib6_table = fib6_new_table(net, vrf->tb_id);
	if (!vrf->fib6_table)
		goto out;

	/* create a dst for routing packets out a VRF device */
	rt6 = ip6_dst_alloc(net, dev, flags);
	if (!rt6)
		goto out;

	rt6->dst.output	= vrf_output6;

	rcu_assign_pointer(vrf->rt6, rt6);

	rc = 0;
out:
	return rc;
}
#else
static struct sk_buff *vrf_ip6_out(struct net_device *vrf_dev,
				   struct sock *sk,
				   struct sk_buff *skb)
{
	return skb;
}

static void vrf_rt6_release(struct net_device *dev, struct net_vrf *vrf)
{
}

static int vrf_rt6_create(struct net_device *dev)
{
	return 0;
}
#endif

/* modelled after ip_finish_output2 */
static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	struct rtable *rt = (struct rtable *)dst;
	struct net_device *dev = dst->dev;
	unsigned int hh_len = LL_RESERVED_SPACE(dev);
	struct neighbour *neigh;
	bool is_v6gw = false;

	vrf_nf_reset_ct(skb);

	/* Be paranoid, rather than too clever. */
	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
		skb = skb_expand_head(skb, hh_len);
		if (!skb) {
			dev->stats.tx_errors++;
			return -ENOMEM;
		}
	}

	rcu_read_lock_bh();

	neigh = ip_neigh_for_gw(rt, skb, &is_v6gw);
	if (!IS_ERR(neigh)) {
		int ret;

		sock_confirm_neigh(skb, neigh);
		/* if crossing protocols, can not use the cached header */
		ret = neigh_output(neigh, skb, is_v6gw);
		rcu_read_unlock_bh();
		return ret;
	}

	rcu_read_unlock_bh();
	vrf_tx_error(skb->dev, skb);
	return -EINVAL;
}

static int vrf_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	struct net_device *dev = skb_dst(skb)->dev;

	IP_UPD_PO_STATS(net, IPSTATS_MIB_OUT, skb->len);

	skb->dev = dev;
	skb->protocol = htons(ETH_P_IP);

	return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
			    net, sk, skb, NULL, dev,
			    vrf_finish_output,
			    !(IPCB(skb)->flags & IPSKB_REROUTED));
}

/* set dst on skb to send packet to us via dev_xmit path. Allows
 * packet to go through device based features such as qdisc, netfilter
 * hooks and packet sockets with skb->dev set to vrf device.
 */
static struct sk_buff *vrf_ip_out_redirect(struct net_device *vrf_dev,
					   struct sk_buff *skb)
{
	struct net_vrf *vrf = netdev_priv(vrf_dev);
	struct dst_entry *dst = NULL;
	struct rtable *rth;

	rcu_read_lock();

	rth = rcu_dereference(vrf->rth);
	if (likely(rth)) {
		dst = &rth->dst;
		dst_hold(dst);
	}

	rcu_read_unlock();

	if (unlikely(!dst)) {
		vrf_tx_error(vrf_dev, skb);
		return NULL;
	}

	skb_dst_drop(skb);
	skb_dst_set(skb, dst);

	return skb;
}

static int vrf_output_direct_finish(struct net *net, struct sock *sk,
				    struct sk_buff *skb)
{
	vrf_finish_direct(skb);

	return vrf_ip_local_out(net, sk, skb);
}

static int vrf_output_direct(struct net *net, struct sock *sk,
			     struct sk_buff *skb)
{
	int err = 1;

	skb->protocol = htons(ETH_P_IP);

	if (!(IPCB(skb)->flags & IPSKB_REROUTED))
		err = nf_hook(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb,
			      NULL, skb->dev, vrf_output_direct_finish);

	if (likely(err == 1))
		vrf_finish_direct(skb);

	return err;
}

static int vrf_ip_out_direct_finish(struct net *net, struct sock *sk,
				    struct sk_buff *skb)
{
	int err;

	err = vrf_output_direct(net, sk, skb);
	if (likely(err == 1))
		err = vrf_ip_local_out(net, sk, skb);

	return err;
}

static struct sk_buff *vrf_ip_out_direct(struct net_device *vrf_dev,
					 struct sock *sk,
					 struct sk_buff *skb)
{
	struct net *net = dev_net(vrf_dev);
	int err;

	skb->dev = vrf_dev;

	err = nf_hook(NFPROTO_IPV4, NF_INET_LOCAL_OUT, net, sk,
		      skb, NULL, vrf_dev, vrf_ip_out_direct_finish);

	if (likely(err == 1))
		err = vrf_output_direct(net, sk, skb);

	if (likely(err == 1))
		return skb;

	return NULL;
}

static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
				  struct sock *sk,
				  struct sk_buff *skb)
{
	/* don't divert multicast or local broadcast */
	if (ipv4_is_multicast(ip_hdr(skb)->daddr) ||
	    ipv4_is_lbcast(ip_hdr(skb)->daddr))
		return skb;

	vrf_nf_set_untracked(skb);

	if (qdisc_tx_is_default(vrf_dev) ||
	    IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED)
		return vrf_ip_out_direct(vrf_dev, sk, skb);

	return vrf_ip_out_redirect(vrf_dev, skb);
}

/* called with rcu lock held */
static struct sk_buff *vrf_l3_out(struct net_device *vrf_dev,
				  struct sock *sk,
				  struct sk_buff *skb,
				  u16 proto)
{
	switch (proto) {
	case AF_INET:
		return vrf_ip_out(vrf_dev, sk, skb);
	case AF_INET6:
		return vrf_ip6_out(vrf_dev, sk, skb);
	}

	return skb;
}

/* holding rtnl */
static void vrf_rtable_release(struct net_device *dev, struct net_vrf *vrf)
{
	struct rtable *rth = rtnl_dereference(vrf->rth);
	struct net *net = dev_net(dev);
	struct dst_entry *dst;

	RCU_INIT_POINTER(vrf->rth, NULL);
	synchronize_rcu();

	/* move dev in dst's to loopback so this VRF device can be deleted
	 * - based on dst_ifdown
	 */
	if (rth) {
		dst = &rth->dst;
		netdev_ref_replace(dst->dev, net->loopback_dev,
				   &dst->dev_tracker, GFP_KERNEL);
		dst->dev = net->loopback_dev;
		dst_release(dst);
	}
}

static int vrf_rtable_create(struct net_device *dev)
{
	struct net_vrf *vrf = netdev_priv(dev);
	struct rtable *rth;

	if (!fib_new_table(dev_net(dev), vrf->tb_id))
		return -ENOMEM;

	/* create a dst for routing packets out through a VRF device */
	rth = rt_dst_alloc(dev, 0, RTN_UNICAST, 1);
	if (!rth)
		return -ENOMEM;

	rth->dst.output	= vrf_output;

	rcu_assign_pointer(vrf->rth, rth);

	return 0;
}

/**************************** device handling ********************/

/* cycle interface to flush neighbor cache and move routes across tables */
static void cycle_netdev(struct net_device *dev,
			 struct netlink_ext_ack *extack)
{
	unsigned int flags = dev->flags;
	int ret;

	if (!netif_running(dev))
		return;

	ret = dev_change_flags(dev, flags & ~IFF_UP, extack);
	if (ret >= 0)
		ret = dev_change_flags(dev, flags, extack);

	if (ret < 0) {
		netdev_err(dev,
			   "Failed to cycle device %s; route tables might be wrong!\n",
			   dev->name);
	}
}

static int do_vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
			    struct netlink_ext_ack *extack)
{
	int ret;

	/* do not allow loopback device to be enslaved to a VRF.
	 * The vrf device acts as the loopback for the vrf.
	 */
	if (port_dev == dev_net(dev)->loopback_dev) {
		NL_SET_ERR_MSG(extack,
			       "Can not enslave loopback device to a VRF");
		return -EOPNOTSUPP;
	}

	port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
	ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL, extack);
	if (ret < 0)
		goto err;

	cycle_netdev(port_dev, extack);

	return 0;

err:
	port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;
	return ret;
}

static int vrf_add_slave(struct net_device *dev, struct net_device *port_dev,
			 struct netlink_ext_ack *extack)
{
	if (netif_is_l3_master(port_dev)) {
		NL_SET_ERR_MSG(extack,
			       "Can not enslave an L3 master device to a VRF");
		return -EINVAL;
	}

	if (netif_is_l3_slave(port_dev))
		return -EINVAL;

	return do_vrf_add_slave(dev, port_dev, extack);
}

/* inverse of do_vrf_add_slave */
static int do_vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
{
	netdev_upper_dev_unlink(port_dev, dev);
	port_dev->priv_flags &= ~IFF_L3MDEV_SLAVE;

	cycle_netdev(port_dev, NULL);

	return 0;
}

static int vrf_del_slave(struct net_device *dev, struct net_device *port_dev)
{
	return do_vrf_del_slave(dev, port_dev);
}

static void vrf_dev_uninit(struct net_device *dev)
{
	struct net_vrf *vrf = netdev_priv(dev);

	vrf_rtable_release(dev, vrf);
	vrf_rt6_release(dev, vrf);

	free_percpu(dev->dstats);
	dev->dstats = NULL;
}

static int vrf_dev_init(struct net_device *dev)
{
	struct net_vrf *vrf = netdev_priv(dev);

	dev->dstats = netdev_alloc_pcpu_stats(struct pcpu_dstats);
	if (!dev->dstats)
		goto out_nomem;

	/* create the default dst which points back to us */
	if (vrf_rtable_create(dev) != 0)
		goto out_stats;

	if (vrf_rt6_create(dev) != 0)
		goto out_rth;

	dev->flags = IFF_MASTER | IFF_NOARP;

	/* similarly, oper state is irrelevant; set to up to avoid confusion */
	dev->operstate = IF_OPER_UP;
	netdev_lockdep_set_classes(dev);
	return 0;

out_rth:
	vrf_rtable_release(dev, vrf);
out_stats:
	free_percpu(dev->dstats);
	dev->dstats = NULL;
out_nomem:
	return -ENOMEM;
}

static const struct net_device_ops vrf_netdev_ops = {
	.ndo_init		= vrf_dev_init,
	.ndo_uninit		= vrf_dev_uninit,
	.ndo_start_xmit		= vrf_xmit,
	.ndo_set_mac_address	= eth_mac_addr,
	.ndo_get_stats64	= vrf_get_stats64,
	.ndo_add_slave		= vrf_add_slave,
	.ndo_del_slave		= vrf_del_slave,
};

static u32 vrf_fib_table(const struct net_device *dev)
{
	struct net_vrf *vrf = netdev_priv(dev);

	return vrf->tb_id;
}

static int vrf_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	kfree_skb(skb);
	return 0;
}

static struct sk_buff *vrf_rcv_nfhook(u8 pf, unsigned int hook,
				      struct sk_buff *skb,
				      struct net_device *dev)
{
	struct net *net = dev_net(dev);

	if (nf_hook(pf, hook, net, NULL, skb, dev, NULL, vrf_rcv_finish) != 1)
		skb = NULL;    /* kfree_skb(skb) handled by nf code */

	return skb;
}

static int vrf_prepare_mac_header(struct sk_buff *skb,
				  struct net_device *vrf_dev, u16 proto)
{
	struct ethhdr *eth;
	int err;

	/* in general, we do not know if there is enough space in the head of
	 * the packet for hosting the mac header.
	 */
	err = skb_cow_head(skb, LL_RESERVED_SPACE(vrf_dev));
	if (unlikely(err))
		/* no space in the skb head */
		return -ENOBUFS;

	__skb_push(skb, ETH_HLEN);
	eth = (struct ethhdr *)skb->data;

	skb_reset_mac_header(skb);
	skb_reset_mac_len(skb);

	/* we set the ethernet destination and the source addresses to the
	 * address of the VRF device.
	 */
	ether_addr_copy(eth->h_dest, vrf_dev->dev_addr);
	ether_addr_copy(eth->h_source, vrf_dev->dev_addr);
	eth->h_proto = htons(proto);

	/* the destination address of the Ethernet frame corresponds to the
	 * address set on the VRF interface; therefore, the packet is intended
	 * to be processed locally.
	 */
	skb->protocol = eth->h_proto;
	skb->pkt_type = PACKET_HOST;

	skb_postpush_rcsum(skb, skb->data, ETH_HLEN);

	skb_pull_inline(skb, ETH_HLEN);

	return 0;
}

/* prepare and add the mac header to the packet if it was not set previously.
 * In this way, packet sniffers such as tcpdump can parse the packet correctly.
 * If the mac header was already set, the original mac header is left
 * untouched and the function returns immediately.
 */
static int vrf_add_mac_header_if_unset(struct sk_buff *skb,
				       struct net_device *vrf_dev,
				       u16 proto, struct net_device *orig_dev)
{
	if (skb_mac_header_was_set(skb) && dev_has_header(orig_dev))
		return 0;

	return vrf_prepare_mac_header(skb, vrf_dev, proto);
}

#if IS_ENABLED(CONFIG_IPV6)
/* neighbor handling is done with actual device; do not want
 * to flip skb->dev for those ndisc packets. This really fails
 * for multiple next protocols (e.g., NEXTHDR_HOP). But it is
 * a start.
 */
static bool ipv6_ndisc_frame(const struct sk_buff *skb)
{
	const struct ipv6hdr *iph = ipv6_hdr(skb);
	bool rc = false;

	if (iph->nexthdr == NEXTHDR_ICMP) {
		const struct icmp6hdr *icmph;
		struct icmp6hdr _icmph;

		icmph = skb_header_pointer(skb, sizeof(*iph),
					   sizeof(_icmph), &_icmph);
		if (!icmph)
			goto out;

		switch (icmph->icmp6_type) {
		case NDISC_ROUTER_SOLICITATION:
		case NDISC_ROUTER_ADVERTISEMENT:
		case NDISC_NEIGHBOUR_SOLICITATION:
		case NDISC_NEIGHBOUR_ADVERTISEMENT:
		case NDISC_REDIRECT:
			rc = true;
			break;
		}
	}

out:
	return rc;
}

static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
					     const struct net_device *dev,
					     struct flowi6 *fl6,
					     int ifindex,
					     const struct sk_buff *skb,
					     int flags)
{
	struct net_vrf *vrf = netdev_priv(dev);

	return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags);
}

static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,
			      int ifindex)
{
	const struct ipv6hdr *iph = ipv6_hdr(skb);
	struct flowi6 fl6 = {
		.flowi6_iif     = ifindex,
		.flowi6_mark    = skb->mark,
		.flowi6_proto   = iph->nexthdr,
		.daddr          = iph->daddr,
		.saddr          = iph->saddr,
		.flowlabel      = ip6_flowinfo(iph),
	};
	struct net *net = dev_net(vrf_dev);
	struct rt6_info *rt6;

	rt6 = vrf_ip6_route_lookup(net, vrf_dev, &fl6, ifindex, skb,
				   RT6_LOOKUP_F_HAS_SADDR | RT6_LOOKUP_F_IFACE);
	if (unlikely(!rt6))
		return;

	if (unlikely(&rt6->dst == &net->ipv6.ip6_null_entry->dst))
		return;

	skb_dst_set(skb, &rt6->dst);
}

static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
				   struct sk_buff *skb)
{
	int orig_iif = skb->skb_iif;
	bool need_strict = rt6_need_strict(&ipv6_hdr(skb)->daddr);
	bool is_ndisc = ipv6_ndisc_frame(skb);

	/* loopback, multicast & non-ND link-local traffic; do not push through
	 * packet taps again. Reset pkt_type for upper layers to process skb.
	 * For strict packets with a source LLA, determine the dst using the
	 * original ifindex.
	 */
	if (skb->pkt_type == PACKET_LOOPBACK || (need_strict && !is_ndisc)) {
		skb->dev = vrf_dev;
		skb->skb_iif = vrf_dev->ifindex;
		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;

		if (skb->pkt_type == PACKET_LOOPBACK)
			skb->pkt_type = PACKET_HOST;
		else if (ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)
			vrf_ip6_input_dst(skb, vrf_dev, orig_iif);

		goto out;
	}

	/* if packet is NDISC then keep the ingress interface */
	if (!is_ndisc) {
		struct net_device *orig_dev = skb->dev;

		vrf_rx_stats(vrf_dev, skb->len);
		skb->dev = vrf_dev;
		skb->skb_iif = vrf_dev->ifindex;

		if (!list_empty(&vrf_dev->ptype_all)) {
			int err;

			err = vrf_add_mac_header_if_unset(skb, vrf_dev,
							  ETH_P_IPV6,
							  orig_dev);
			if (likely(!err)) {
				skb_push(skb, skb->mac_len);
				dev_queue_xmit_nit(skb, vrf_dev);
				skb_pull(skb, skb->mac_len);
			}
		}

		IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
	}

	if (need_strict)
		vrf_ip6_input_dst(skb, vrf_dev, orig_iif);

	skb = vrf_rcv_nfhook(NFPROTO_IPV6, NF_INET_PRE_ROUTING, skb, vrf_dev);
out:
	return skb;
}

#else
static struct sk_buff *vrf_ip6_rcv(struct net_device *vrf_dev,
				   struct sk_buff *skb)
{
	return skb;
}
#endif

static struct sk_buff *vrf_ip_rcv(struct net_device *vrf_dev,
				  struct sk_buff *skb)
{
	struct net_device *orig_dev = skb->dev;

	skb->dev = vrf_dev;
	skb->skb_iif = vrf_dev->ifindex;
	IPCB(skb)->flags |= IPSKB_L3SLAVE;

	if (ipv4_is_multicast(ip_hdr(skb)->daddr))
		goto out;

	/* loopback traffic; do not push through packet taps again.
	 * Reset pkt_type for upper layers to process skb
	 */
	if (skb->pkt_type == PACKET_LOOPBACK) {
		skb->pkt_type = PACKET_HOST;
		goto out;
	}

	vrf_rx_stats(vrf_dev, skb->len);

	if (!list_empty(&vrf_dev->ptype_all)) {
		int err;

		err = vrf_add_mac_header_if_unset(skb, vrf_dev, ETH_P_IP,
						  orig_dev);
		if (likely(!err)) {
			skb_push(skb, skb->mac_len);
			dev_queue_xmit_nit(skb, vrf_dev);
			skb_pull(skb, skb->mac_len);
		}
	}

	skb = vrf_rcv_nfhook(NFPROTO_IPV4, NF_INET_PRE_ROUTING, skb, vrf_dev);
out:
	return skb;
}

/* called with rcu lock held */
static struct sk_buff *vrf_l3_rcv(struct net_device *vrf_dev,
				  struct sk_buff *skb,
				  u16 proto)
{
	switch (proto) {
	case AF_INET:
		return vrf_ip_rcv(vrf_dev, skb);
	case AF_INET6:
		return vrf_ip6_rcv(vrf_dev, skb);
	}

	return skb;
}

#if IS_ENABLED(CONFIG_IPV6)
/* send to link-local or multicast address via interface enslaved to
 * VRF device. Force lookup to VRF table without changing flow struct
 * Note: Caller to this function must hold rcu_read_lock() and no refcnt
 * is taken on the dst by this function.
 */
static struct dst_entry *vrf_link_scope_lookup(const struct net_device *dev,
					      struct flowi6 *fl6)
{
	struct net *net = dev_net(dev);
	int flags = RT6_LOOKUP_F_IFACE | RT6_LOOKUP_F_DST_NOREF;
	struct dst_entry *dst = NULL;
	struct rt6_info *rt;

	/* VRF device does not have a link-local address and
	 * sending packets to link-local or mcast addresses over
	 * a VRF device does not make sense
	 */
	if (fl6->flowi6_oif == dev->ifindex) {
		dst = &net->ipv6.ip6_null_entry->dst;
		return dst;
	}

	if (!ipv6_addr_any(&fl6->saddr))
		flags |= RT6_LOOKUP_F_HAS_SADDR;

	rt = vrf_ip6_route_lookup(net, dev, fl6, fl6->flowi6_oif, NULL, flags);
	if (rt)
		dst = &rt->dst;

	return dst;
}
#endif

static const struct l3mdev_ops vrf_l3mdev_ops = {
	.l3mdev_fib_table	= vrf_fib_table,
	.l3mdev_l3_rcv		= vrf_l3_rcv,
	.l3mdev_l3_out		= vrf_l3_out,
#if IS_ENABLED(CONFIG_IPV6)
	.l3mdev_link_scope_lookup = vrf_link_scope_lookup,
#endif
};

static void vrf_get_drvinfo(struct net_device *dev,
			    struct ethtool_drvinfo *info)
{
	strscpy(info->driver, DRV_NAME, sizeof(info->driver));
	strscpy(info->version, DRV_VERSION, sizeof(info->version));
}

static const struct ethtool_ops vrf_ethtool_ops = {
	.get_drvinfo	= vrf_get_drvinfo,
};

static inline size_t vrf_fib_rule_nl_size(void)
{
	size_t sz;

	sz  = NLMSG_ALIGN(sizeof(struct fib_rule_hdr));
	sz += nla_total_size(sizeof(u8));	/* FRA_L3MDEV */
	sz += nla_total_size(sizeof(u32));	/* FRA_PRIORITY */
	sz += nla_total_size(sizeof(u8));       /* FRA_PROTOCOL */

	return sz;
}

static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
{
	struct fib_rule_hdr *frh;
	struct nlmsghdr *nlh;
	struct sk_buff *skb;
	int err;

	if ((family == AF_INET6 || family == RTNL_FAMILY_IP6MR) &&
	    !ipv6_mod_enabled())
		return 0;

	skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL);
	if (!skb)
		return -ENOMEM;

	nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0);
	if (!nlh)
		goto nla_put_failure;

	/* rule only needs to appear once */
	nlh->nlmsg_flags |= NLM_F_EXCL;

	frh = nlmsg_data(nlh);
	memset(frh, 0, sizeof(*frh));
	frh->family = family;
	frh->action = FR_ACT_TO_TBL;

	if (nla_put_u8(skb, FRA_PROTOCOL, RTPROT_KERNEL))
		goto nla_put_failure;

	if (nla_put_u8(skb, FRA_L3MDEV, 1))
		goto nla_put_failure;

	if (nla_put_u32(skb, FRA_PRIORITY, FIB_RULE_PREF))
		goto nla_put_failure;

	nlmsg_end(skb, nlh);

	/* fib_nl_{new,del}rule handling looks for net from skb->sk */
	skb->sk = dev_net(dev)->rtnl;
	if (add_it) {
		err = fib_nl_newrule(skb, nlh, NULL);
		if (err == -EEXIST)
			err = 0;
	} else {
		err = fib_nl_delrule(skb, nlh, NULL);
		if (err == -ENOENT)
			err = 0;
	}
	nlmsg_free(skb);

	return err;

nla_put_failure:
	nlmsg_free(skb);

	return -EMSGSIZE;
}

static int vrf_add_fib_rules(const struct net_device *dev)
{
	int err;

	err = vrf_fib_rule(dev, AF_INET,  true);
	if (err < 0)
		goto out_err;

	err = vrf_fib_rule(dev, AF_INET6, true);
	if (err < 0)
		goto ipv6_err;

#if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES)
	err = vrf_fib_rule(dev, RTNL_FAMILY_IPMR, true);
	if (err < 0)
		goto ipmr_err;
#endif

#if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES)
	err = vrf_fib_rule(dev, RTNL_FAMILY_IP6MR, true);
	if (err < 0)
		goto ip6mr_err;
#endif

	return 0;

#if IS_ENABLED(CONFIG_IPV6_MROUTE_MULTIPLE_TABLES)
ip6mr_err:
	vrf_fib_rule(dev, RTNL_FAMILY_IPMR,  false);
#endif

#if IS_ENABLED(CONFIG_IP_MROUTE_MULTIPLE_TABLES)
ipmr_err:
	vrf_fib_rule(dev, AF_INET6,  false);
#endif

ipv6_err:
	vrf_fib_rule(dev, AF_INET,  false);

out_err:
	netdev_err(dev, "Failed to add FIB rules.\n");
	return err;
}

static void vrf_setup(struct net_device *dev)
{
	ether_setup(dev);

	/* Initialize the device structure. */
	dev->netdev_ops = &vrf_netdev_ops;
	dev->l3mdev_ops = &vrf_l3mdev_ops;
	dev->ethtool_ops = &vrf_ethtool_ops;
	dev->needs_free_netdev = true;

	/* Fill in device structure with ethernet-generic values. */
	eth_hw_addr_random(dev);

	/* don't acquire vrf device's netif_tx_lock when transmitting */
	dev->features |= NETIF_F_LLTX;

	/* don't allow vrf devices to change network namespaces. */
	dev->features |= NETIF_F_NETNS_LOCAL;

	/* does not make sense for a VLAN to be added to a vrf device */
	dev->features   |= NETIF_F_VLAN_CHALLENGED;

	/* enable offload features */
	dev->features   |= NETIF_F_GSO_SOFTWARE;
	dev->features   |= NETIF_F_RXCSUM | NETIF_F_HW_CSUM | NETIF_F_SCTP_CRC;
	dev->features   |= NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA;

	dev->hw_features = dev->features;
	dev->hw_enc_features = dev->features;

	/* default to no qdisc; user can add if desired */
	dev->priv_flags |= IFF_NO_QUEUE;
	dev->priv_flags |= IFF_NO_RX_HANDLER;
	dev->priv_flags |= IFF_LIVE_ADDR_CHANGE;

	/* VRF devices do not care about MTU, but if the MTU is set
	 * too low then the ipv4 and ipv6 protocols are disabled
	 * which breaks networking.
	 */
	dev->min_mtu = IPV6_MIN_MTU;
	dev->max_mtu = IP6_MAX_MTU;
	dev->mtu = dev->max_mtu;
}

static int vrf_validate(struct nlattr *tb[], struct nlattr *data[],
			struct netlink_ext_ack *extack)
{
	if (tb[IFLA_ADDRESS]) {
		if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) {
			NL_SET_ERR_MSG(extack, "Invalid hardware address");
			return -EINVAL;
		}
		if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) {
			NL_SET_ERR_MSG(extack, "Invalid hardware address");
			return -EADDRNOTAVAIL;
		}
	}
	return 0;
}

static void vrf_dellink(struct net_device *dev, struct list_head *head)
{
	struct net_device *port_dev;
	struct list_head *iter;

	netdev_for_each_lower_dev(dev, port_dev, iter)
		vrf_del_slave(dev, port_dev);

	vrf_map_unregister_dev(dev);

	unregister_netdevice_queue(dev, head);
}

static int vrf_newlink(struct net *src_net, struct net_device *dev,
		       struct nlattr *tb[], struct nlattr *data[],
		       struct netlink_ext_ack *extack)
{
	struct net_vrf *vrf = netdev_priv(dev);
	struct netns_vrf *nn_vrf;
	bool *add_fib_rules;
	struct net *net;
	int err;

	if (!data || !data[IFLA_VRF_TABLE]) {
		NL_SET_ERR_MSG(extack, "VRF table id is missing");
		return -EINVAL;
	}

	vrf->tb_id = nla_get_u32(data[IFLA_VRF_TABLE]);
	if (vrf->tb_id == RT_TABLE_UNSPEC) {
		NL_SET_ERR_MSG_ATTR(extack, data[IFLA_VRF_TABLE],
				    "Invalid VRF table id");
		return -EINVAL;
	}

	dev->priv_flags |= IFF_L3MDEV_MASTER;

	err = register_netdevice(dev);
	if (err)
		goto out;

	/* mapping between table_id and vrf;
	 * note: such binding could not be done in the dev init function
	 * because dev->ifindex id is not available yet.
	 */
	vrf->ifindex = dev->ifindex;

	err = vrf_map_register_dev(dev, extack);
	if (err) {
		unregister_netdevice(dev);
		goto out;
	}

	net = dev_net(dev);
	nn_vrf = net_generic(net, vrf_net_id);

	add_fib_rules = &nn_vrf->add_fib_rules;
	if (*add_fib_rules) {
		err = vrf_add_fib_rules(dev);
		if (err) {
			vrf_map_unregister_dev(dev);
			unregister_netdevice(dev);
			goto out;
		}
		*add_fib_rules = false;
	}

out:
	return err;
}

static size_t vrf_nl_getsize(const struct net_device *dev)
{
	return nla_total_size(sizeof(u32));  /* IFLA_VRF_TABLE */
}

static int vrf_fillinfo(struct sk_buff *skb,
			const struct net_device *dev)
{
	struct net_vrf *vrf = netdev_priv(dev);

	return nla_put_u32(skb, IFLA_VRF_TABLE, vrf->tb_id);
}

static size_t vrf_get_slave_size(const struct net_device *bond_dev,
				 const struct net_device *slave_dev)
{
	return nla_total_size(sizeof(u32));  /* IFLA_VRF_PORT_TABLE */
}

static int vrf_fill_slave_info(struct sk_buff *skb,
			       const struct net_device *vrf_dev,
			       const struct net_device *slave_dev)
{
	struct net_vrf *vrf = netdev_priv(vrf_dev);

	if (nla_put_u32(skb, IFLA_VRF_PORT_TABLE, vrf->tb_id))
		return -EMSGSIZE;

	return 0;
}

static const struct nla_policy vrf_nl_policy[IFLA_VRF_MAX + 1] = {
	[IFLA_VRF_TABLE] = { .type = NLA_U32 },
};

static struct rtnl_link_ops vrf_link_ops __read_mostly = {
	.kind		= DRV_NAME,
	.priv_size	= sizeof(struct net_vrf),

	.get_size	= vrf_nl_getsize,
	.policy		= vrf_nl_policy,
	.validate	= vrf_validate,
	.fill_info	= vrf_fillinfo,

	.get_slave_size  = vrf_get_slave_size,
	.fill_slave_info = vrf_fill_slave_info,

	.newlink	= vrf_newlink,
	.dellink	= vrf_dellink,
	.setup		= vrf_setup,
	.maxtype	= IFLA_VRF_MAX,
};

static int vrf_device_event(struct notifier_block *unused,
			    unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);

	/* only care about unregister events to drop slave references */
	if (event == NETDEV_UNREGISTER) {
		struct net_device *vrf_dev;

		if (!netif_is_l3_slave(dev))
			goto out;

		vrf_dev = netdev_master_upper_dev_get(dev);
		vrf_del_slave(vrf_dev, dev);
	}
out:
	return NOTIFY_DONE;
}

static struct notifier_block vrf_notifier_block __read_mostly = {
	.notifier_call = vrf_device_event,
};

static int vrf_map_init(struct vrf_map *vmap)
{
	spin_lock_init(&vmap->vmap_lock);
	hash_init(vmap->ht);

	vmap->strict_mode = false;

	return 0;
}

#ifdef CONFIG_SYSCTL
static bool vrf_strict_mode(struct vrf_map *vmap)
{
	bool strict_mode;

	vrf_map_lock(vmap);
	strict_mode = vmap->strict_mode;
	vrf_map_unlock(vmap);

	return strict_mode;
}

static int vrf_strict_mode_change(struct vrf_map *vmap, bool new_mode)
{
	bool *cur_mode;
	int res = 0;

	vrf_map_lock(vmap);

	cur_mode = &vmap->strict_mode;
	if (*cur_mode == new_mode)
		goto unlock;

	if (*cur_mode) {
		/* disable strict mode */
		*cur_mode = false;
	} else {
		if (vmap->shared_tables) {
			/* we cannot allow strict_mode because there are some
			 * vrfs that share one or more tables.
			 */
			res = -EBUSY;
			goto unlock;
		}

		/* no tables are shared among vrfs, so we can go back
		 * to 1:1 association between a vrf with its table.
		 */
		*cur_mode = true;
	}

unlock:
	vrf_map_unlock(vmap);

	return res;
}

static int vrf_shared_table_handler(struct ctl_table *table, int write,
				    void *buffer, size_t *lenp, loff_t *ppos)
{
	struct net *net = (struct net *)table->extra1;
	struct vrf_map *vmap = netns_vrf_map(net);
	int proc_strict_mode = 0;
	struct ctl_table tmp = {
		.procname	= table->procname,
		.data		= &proc_strict_mode,
		.maxlen		= sizeof(int),
		.mode		= table->mode,
		.extra1		= SYSCTL_ZERO,
		.extra2		= SYSCTL_ONE,
	};
	int ret;

	if (!write)
		proc_strict_mode = vrf_strict_mode(vmap);

	ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);

	if (write && ret == 0)
		ret = vrf_strict_mode_change(vmap, (bool)proc_strict_mode);

	return ret;
}

static const struct ctl_table vrf_table[] = {
	{
		.procname	= "strict_mode",
		.data		= NULL,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= vrf_shared_table_handler,
		/* set by the vrf_netns_init */
		.extra1		= NULL,
	},
	{ },
};

static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf)
{
	struct ctl_table *table;

	table = kmemdup(vrf_table, sizeof(vrf_table), GFP_KERNEL);
	if (!table)
		return -ENOMEM;

	/* init the extra1 parameter with the reference to current netns */
	table[0].extra1 = net;

	nn_vrf->ctl_hdr = register_net_sysctl(net, "net/vrf", table);
	if (!nn_vrf->ctl_hdr) {
		kfree(table);
		return -ENOMEM;
	}

	return 0;
}

static void vrf_netns_exit_sysctl(struct net *net)
{
	struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id);
	struct ctl_table *table;

	table = nn_vrf->ctl_hdr->ctl_table_arg;
	unregister_net_sysctl_table(nn_vrf->ctl_hdr);
	kfree(table);
}
#else
static int vrf_netns_init_sysctl(struct net *net, struct netns_vrf *nn_vrf)
{
	return 0;
}

static void vrf_netns_exit_sysctl(struct net *net)
{
}
#endif

/* Initialize per network namespace state */
static int __net_init vrf_netns_init(struct net *net)
{
	struct netns_vrf *nn_vrf = net_generic(net, vrf_net_id);

	nn_vrf->add_fib_rules = true;
	vrf_map_init(&nn_vrf->vmap);

	return vrf_netns_init_sysctl(net, nn_vrf);
}

static void __net_exit vrf_netns_exit(struct net *net)
{
	vrf_netns_exit_sysctl(net);
}

static struct pernet_operations vrf_net_ops __net_initdata = {
	.init = vrf_netns_init,
	.exit = vrf_netns_exit,
	.id   = &vrf_net_id,
	.size = sizeof(struct netns_vrf),
};

static int __init vrf_init_module(void)
{
	int rc;

	register_netdevice_notifier(&vrf_notifier_block);

	rc = register_pernet_subsys(&vrf_net_ops);
	if (rc < 0)
		goto error;

	rc = l3mdev_table_lookup_register(L3MDEV_TYPE_VRF,
					  vrf_ifindex_lookup_by_table_id);
	if (rc < 0)
		goto unreg_pernet;

	rc = rtnl_link_register(&vrf_link_ops);
	if (rc < 0)
		goto table_lookup_unreg;

	return 0;

table_lookup_unreg:
	l3mdev_table_lookup_unregister(L3MDEV_TYPE_VRF,
				       vrf_ifindex_lookup_by_table_id);

unreg_pernet:
	unregister_pernet_subsys(&vrf_net_ops);

error:
	unregister_netdevice_notifier(&vrf_notifier_block);
	return rc;
}

module_init(vrf_init_module);
MODULE_AUTHOR("Shrijeet Mukherjee, David Ahern");
MODULE_DESCRIPTION("Device driver to instantiate VRF domains");
MODULE_LICENSE("GPL");
MODULE_ALIAS_RTNL_LINK(DRV_NAME);
MODULE_VERSION(DRV_VERSION);