forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvrf.c
1453 lines (1171 loc) · 32.8 KB
/
vrf.c
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
/*
* vrf.c: device driver to encapsulate a VRF space
*
* Copyright (c) 2015 Cumulus Networks. All rights reserved.
* Copyright (c) 2015 Shrijeet Mukherjee <[email protected]>
* Copyright (c) 2015 David Ahern <[email protected]>
*
* Based on dummy, team and ipvlan drivers
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*/
#include <linux/module.h>
#include <linux/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/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/netns/generic.h>
#define DRV_NAME "vrf"
#define DRV_VERSION "1.0"
#define FIB_RULE_PREF 1000 /* default preference for FIB rules */
static unsigned int vrf_net_id;
struct net_vrf {
struct rtable __rcu *rth;
struct rt6_info __rcu *rt6;
u32 tb_id;
};
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_irq(&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_irq(&dstats->syncp, start));
stats->tx_bytes += tbytes;
stats->tx_packets += tpkts;
stats->tx_dropped += tdrops;
stats->rx_bytes += rbytes;
stats->rx_packets += rpkts;
}
}
/* 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);
skb_dst_force(skb);
/* 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;
}
#if IS_ENABLED(CONFIG_IPV6)
static int vrf_ip6_local_out(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
int err;
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 = ipv6_hdr(skb);
struct net *net = dev_net(skb->dev);
struct flowi6 fl6 = {
/* needed to match OIF rule */
.flowi6_oif = dev->ifindex,
.flowi6_iif = LOOPBACK_IFINDEX,
.daddr = iph->daddr,
.saddr = iph->saddr,
.flowlabel = ip6_flowinfo(iph),
.flowi6_mark = skb->mark,
.flowi6_proto = iph->nexthdr,
.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF,
};
int ret = NET_XMIT_DROP;
struct dst_entry *dst;
struct dst_entry *dst_null = &net->ipv6.ip6_null_entry->dst;
dst = ip6_route_output(net, NULL, &fl6);
if (dst == dst_null)
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or 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));
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;
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 = ip_hdr(skb);
int ret = NET_XMIT_DROP;
struct flowi4 fl4 = {
/* needed to match OIF rule */
.flowi4_oif = vrf_dev->ifindex,
.flowi4_iif = LOOPBACK_IFINDEX,
.flowi4_tos = RT_TOS(ip4h->tos),
.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF,
.flowi4_proto = ip4h->protocol,
.daddr = ip4h->daddr,
.saddr = ip4h->saddr,
};
struct net *net = dev_net(vrf_dev);
struct rtable *rt;
rt = ip_route_output_flow(net, &fl4, NULL);
if (IS_ERR(rt))
goto err;
skb_dst_drop(skb);
/* if dst.dev is loopback or 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);
}
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 int vrf_finish_direct(struct net *net, struct sock *sk,
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);
}
return 1;
}
#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;
struct neighbour *neigh;
struct in6_addr *nexthop;
int ret;
nf_reset(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);
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(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
skb->protocol = htons(ETH_P_IPV6);
return NF_HOOK_COND(NFPROTO_IPV6, NF_INET_POST_ROUTING,
net, sk, skb, NULL, skb->dev,
vrf_finish_direct,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
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_output6_direct);
if (likely(err == 1))
err = vrf_output6_direct(net, sk, skb);
/* reset skb device */
if (likely(err == 1))
nf_reset(skb);
else
skb = NULL;
return skb;
}
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;
if (qdisc_tx_is_default(vrf_dev))
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;
dev_put(dst->dev);
dst->dev = net->loopback_dev;
dev_hold(dst->dev);
dst_release(dst);
}
}
static int vrf_rt6_create(struct net_device *dev)
{
int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM;
struct net_vrf *vrf = netdev_priv(dev);
struct net *net = dev_net(dev);
struct fib6_table *rt6i_table;
struct rt6_info *rt6;
int rc = -ENOMEM;
/* IPv6 can be CONFIG enabled and then disabled runtime */
if (!ipv6_mod_enabled())
return 0;
rt6i_table = fib6_new_table(net, vrf->tb_id);
if (!rt6i_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->rt6i_table = rt6i_table;
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;
u32 nexthop;
int ret = -EINVAL;
nf_reset(skb);
/* Be paranoid, rather than too clever. */
if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
struct sk_buff *skb2;
skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
if (!skb2) {
ret = -ENOMEM;
goto err;
}
if (skb->sk)
skb_set_owner_w(skb2, skb->sk);
consume_skb(skb);
skb = skb2;
}
rcu_read_lock_bh();
nexthop = (__force u32)rt_nexthop(rt, ip_hdr(skb)->daddr);
neigh = __ipv4_neigh_lookup_noref(dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&arp_tbl, &nexthop, dev, false);
if (!IS_ERR(neigh)) {
sock_confirm_neigh(skb, neigh);
ret = neigh_output(neigh, skb);
}
rcu_read_unlock_bh();
err:
if (unlikely(ret < 0))
vrf_tx_error(skb->dev, skb);
return ret;
}
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(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
skb->protocol = htons(ETH_P_IP);
return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING,
net, sk, skb, NULL, skb->dev,
vrf_finish_direct,
!(IPCB(skb)->flags & IPSKB_REROUTED));
}
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_output_direct);
if (likely(err == 1))
err = vrf_output_direct(net, sk, skb);
/* reset skb device */
if (likely(err == 1))
nf_reset(skb);
else
skb = NULL;
return skb;
}
static struct sk_buff *vrf_ip_out(struct net_device *vrf_dev,
struct sock *sk,
struct sk_buff *skb)
{
/* don't divert multicast */
if (ipv4_is_multicast(ip_hdr(skb)->daddr))
return skb;
if (qdisc_tx_is_default(vrf_dev))
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;
dev_put(dst->dev);
dst->dev = net->loopback_dev;
dev_hold(dst->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, 1, 0);
if (!rth)
return -ENOMEM;
rth->dst.output = vrf_output;
rth->rt_table_id = vrf->tb_id;
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)
{
unsigned int flags = dev->flags;
int ret;
if (!netif_running(dev))
return;
ret = dev_change_flags(dev, flags & ~IFF_UP);
if (ret >= 0)
ret = dev_change_flags(dev, flags);
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)
{
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)
return -EOPNOTSUPP;
port_dev->priv_flags |= IFF_L3MDEV_SLAVE;
ret = netdev_master_upper_dev_link(port_dev, dev, NULL, NULL);
if (ret < 0)
goto err;
cycle_netdev(port_dev);
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)
{
if (netif_is_l3_master(port_dev) || netif_is_l3_slave(port_dev))
return -EINVAL;
return do_vrf_add_slave(dev, port_dev);
}
/* 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);
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;
/* MTU is irrelevant for VRF device; set to 64k similar to lo */
dev->mtu = 64 * 1024;
/* 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_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;
}
#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,
int flags)
{
struct net_vrf *vrf = netdev_priv(dev);
struct fib6_table *table = NULL;
struct rt6_info *rt6;
rcu_read_lock();
/* fib6_table does not have a refcnt and can not be freed */
rt6 = rcu_dereference(vrf->rt6);
if (likely(rt6))
table = rt6->rt6i_table;
rcu_read_unlock();
if (!table)
return NULL;
return ip6_pol_route(net, table, ifindex, fl6, 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,
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;
/* 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->dev = vrf_dev;
skb->skb_iif = vrf_dev->ifindex;
IP6CB(skb)->flags |= IP6SKB_L3SLAVE;
skb->pkt_type = PACKET_HOST;
goto out;
}
/* if packet is NDISC or addressed to multicast or link-local
* then keep the ingress interface
*/