forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
vrf.c
2066 lines (1652 loc) · 46.8 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
// 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 <[email protected]>
* Copyright (c) 2015 David Ahern <[email protected]>
*
* 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_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;
}
}
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_oif = 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;
fl6.flowi6_flags = FLOWI_FLAG_SKIP_NH_OIF;
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_oif = vrf_dev->ifindex;
fl4.flowi4_iif = LOOPBACK_IFINDEX;
fl4.flowi4_tos = RT_TOS(ip4h->tos);
fl4.flowi4_flags = FLOWI_FLAG_ANYSRC | FLOWI_FLAG_SKIP_NH_OIF;
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;
dev_replace_track(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;