forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvxlan.c
3356 lines (2787 loc) · 83.6 KB
/
vxlan.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
/*
* VXLAN: Virtual eXtensible Local Area Network
*
* Copyright (c) 2012-2013 Vyatta Inc.
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/if_ether.h>
#include <linux/ethtool.h>
#include <net/arp.h>
#include <net/ndisc.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/rtnetlink.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/vxlan.h>
#include <net/protocol.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ip6_tunnel.h>
#include <net/ip6_checksum.h>
#endif
#define VXLAN_VERSION "0.1"
#define PORT_HASH_BITS 8
#define PORT_HASH_SIZE (1<<PORT_HASH_BITS)
#define FDB_AGE_DEFAULT 300 /* 5 min */
#define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */
/* UDP port for VXLAN traffic.
* The IANA assigned port is 4789, but the Linux default is 8472
* for compatibility with early adopters.
*/
static unsigned short vxlan_port __read_mostly = 8472;
module_param_named(udp_port, vxlan_port, ushort, 0444);
MODULE_PARM_DESC(udp_port, "Destination UDP port");
static bool log_ecn_error = true;
module_param(log_ecn_error, bool, 0644);
MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static int vxlan_net_id;
static struct rtnl_link_ops vxlan_link_ops;
static const u8 all_zeros_mac[ETH_ALEN + 2];
static int vxlan_sock_add(struct vxlan_dev *vxlan);
/* per-network namespace private data for this module */
struct vxlan_net {
struct list_head vxlan_list;
struct hlist_head sock_list[PORT_HASH_SIZE];
spinlock_t sock_lock;
};
/* Forwarding table entry */
struct vxlan_fdb {
struct hlist_node hlist; /* linked list of entries */
struct rcu_head rcu;
unsigned long updated; /* jiffies */
unsigned long used;
struct list_head remotes;
u8 eth_addr[ETH_ALEN];
u16 state; /* see ndm_state */
u8 flags; /* see ndm_flags */
};
/* salt for hash table */
static u32 vxlan_salt __read_mostly;
static inline bool vxlan_collect_metadata(struct vxlan_sock *vs)
{
return vs->flags & VXLAN_F_COLLECT_METADATA ||
ip_tunnel_collect_metadata();
}
#if IS_ENABLED(CONFIG_IPV6)
static inline
bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
{
if (a->sa.sa_family != b->sa.sa_family)
return false;
if (a->sa.sa_family == AF_INET6)
return ipv6_addr_equal(&a->sin6.sin6_addr, &b->sin6.sin6_addr);
else
return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
}
static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
{
if (ipa->sa.sa_family == AF_INET6)
return ipv6_addr_any(&ipa->sin6.sin6_addr);
else
return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
}
static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
{
if (ipa->sa.sa_family == AF_INET6)
return ipv6_addr_is_multicast(&ipa->sin6.sin6_addr);
else
return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
}
static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
{
if (nla_len(nla) >= sizeof(struct in6_addr)) {
ip->sin6.sin6_addr = nla_get_in6_addr(nla);
ip->sa.sa_family = AF_INET6;
return 0;
} else if (nla_len(nla) >= sizeof(__be32)) {
ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
ip->sa.sa_family = AF_INET;
return 0;
} else {
return -EAFNOSUPPORT;
}
}
static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
const union vxlan_addr *ip)
{
if (ip->sa.sa_family == AF_INET6)
return nla_put_in6_addr(skb, attr, &ip->sin6.sin6_addr);
else
return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
}
#else /* !CONFIG_IPV6 */
static inline
bool vxlan_addr_equal(const union vxlan_addr *a, const union vxlan_addr *b)
{
return a->sin.sin_addr.s_addr == b->sin.sin_addr.s_addr;
}
static inline bool vxlan_addr_any(const union vxlan_addr *ipa)
{
return ipa->sin.sin_addr.s_addr == htonl(INADDR_ANY);
}
static inline bool vxlan_addr_multicast(const union vxlan_addr *ipa)
{
return IN_MULTICAST(ntohl(ipa->sin.sin_addr.s_addr));
}
static int vxlan_nla_get_addr(union vxlan_addr *ip, struct nlattr *nla)
{
if (nla_len(nla) >= sizeof(struct in6_addr)) {
return -EAFNOSUPPORT;
} else if (nla_len(nla) >= sizeof(__be32)) {
ip->sin.sin_addr.s_addr = nla_get_in_addr(nla);
ip->sa.sa_family = AF_INET;
return 0;
} else {
return -EAFNOSUPPORT;
}
}
static int vxlan_nla_put_addr(struct sk_buff *skb, int attr,
const union vxlan_addr *ip)
{
return nla_put_in_addr(skb, attr, ip->sin.sin_addr.s_addr);
}
#endif
/* Virtual Network hash table head */
static inline struct hlist_head *vni_head(struct vxlan_sock *vs, __be32 vni)
{
return &vs->vni_list[hash_32((__force u32)vni, VNI_HASH_BITS)];
}
/* Socket hash table head */
static inline struct hlist_head *vs_head(struct net *net, __be16 port)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
return &vn->sock_list[hash_32(ntohs(port), PORT_HASH_BITS)];
}
/* First remote destination for a forwarding entry.
* Guaranteed to be non-NULL because remotes are never deleted.
*/
static inline struct vxlan_rdst *first_remote_rcu(struct vxlan_fdb *fdb)
{
return list_entry_rcu(fdb->remotes.next, struct vxlan_rdst, list);
}
static inline struct vxlan_rdst *first_remote_rtnl(struct vxlan_fdb *fdb)
{
return list_first_entry(&fdb->remotes, struct vxlan_rdst, list);
}
/* Find VXLAN socket based on network namespace, address family and UDP port
* and enabled unshareable flags.
*/
static struct vxlan_sock *vxlan_find_sock(struct net *net, sa_family_t family,
__be16 port, u32 flags)
{
struct vxlan_sock *vs;
flags &= VXLAN_F_RCV_FLAGS;
hlist_for_each_entry_rcu(vs, vs_head(net, port), hlist) {
if (inet_sk(vs->sock->sk)->inet_sport == port &&
vxlan_get_sk_family(vs) == family &&
vs->flags == flags)
return vs;
}
return NULL;
}
static struct vxlan_dev *vxlan_vs_find_vni(struct vxlan_sock *vs, __be32 vni)
{
struct vxlan_dev *vxlan;
/* For flow based devices, map all packets to VNI 0 */
if (vs->flags & VXLAN_F_COLLECT_METADATA)
vni = 0;
hlist_for_each_entry_rcu(vxlan, vni_head(vs, vni), hlist) {
if (vxlan->default_dst.remote_vni == vni)
return vxlan;
}
return NULL;
}
/* Look up VNI in a per net namespace table */
static struct vxlan_dev *vxlan_find_vni(struct net *net, __be32 vni,
sa_family_t family, __be16 port,
u32 flags)
{
struct vxlan_sock *vs;
vs = vxlan_find_sock(net, family, port, flags);
if (!vs)
return NULL;
return vxlan_vs_find_vni(vs, vni);
}
/* Fill in neighbour message in skbuff. */
static int vxlan_fdb_info(struct sk_buff *skb, struct vxlan_dev *vxlan,
const struct vxlan_fdb *fdb,
u32 portid, u32 seq, int type, unsigned int flags,
const struct vxlan_rdst *rdst)
{
unsigned long now = jiffies;
struct nda_cacheinfo ci;
struct nlmsghdr *nlh;
struct ndmsg *ndm;
bool send_ip, send_eth;
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
if (nlh == NULL)
return -EMSGSIZE;
ndm = nlmsg_data(nlh);
memset(ndm, 0, sizeof(*ndm));
send_eth = send_ip = true;
if (type == RTM_GETNEIGH) {
ndm->ndm_family = AF_INET;
send_ip = !vxlan_addr_any(&rdst->remote_ip);
send_eth = !is_zero_ether_addr(fdb->eth_addr);
} else
ndm->ndm_family = AF_BRIDGE;
ndm->ndm_state = fdb->state;
ndm->ndm_ifindex = vxlan->dev->ifindex;
ndm->ndm_flags = fdb->flags;
ndm->ndm_type = RTN_UNICAST;
if (!net_eq(dev_net(vxlan->dev), vxlan->net) &&
nla_put_s32(skb, NDA_LINK_NETNSID,
peernet2id_alloc(dev_net(vxlan->dev), vxlan->net)))
goto nla_put_failure;
if (send_eth && nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
goto nla_put_failure;
if (send_ip && vxlan_nla_put_addr(skb, NDA_DST, &rdst->remote_ip))
goto nla_put_failure;
if (rdst->remote_port && rdst->remote_port != vxlan->cfg.dst_port &&
nla_put_be16(skb, NDA_PORT, rdst->remote_port))
goto nla_put_failure;
if (rdst->remote_vni != vxlan->default_dst.remote_vni &&
nla_put_u32(skb, NDA_VNI, be32_to_cpu(rdst->remote_vni)))
goto nla_put_failure;
if (rdst->remote_ifindex &&
nla_put_u32(skb, NDA_IFINDEX, rdst->remote_ifindex))
goto nla_put_failure;
ci.ndm_used = jiffies_to_clock_t(now - fdb->used);
ci.ndm_confirmed = 0;
ci.ndm_updated = jiffies_to_clock_t(now - fdb->updated);
ci.ndm_refcnt = 0;
if (nla_put(skb, NDA_CACHEINFO, sizeof(ci), &ci))
goto nla_put_failure;
nlmsg_end(skb, nlh);
return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
return -EMSGSIZE;
}
static inline size_t vxlan_nlmsg_size(void)
{
return NLMSG_ALIGN(sizeof(struct ndmsg))
+ nla_total_size(ETH_ALEN) /* NDA_LLADDR */
+ nla_total_size(sizeof(struct in6_addr)) /* NDA_DST */
+ nla_total_size(sizeof(__be16)) /* NDA_PORT */
+ nla_total_size(sizeof(__be32)) /* NDA_VNI */
+ nla_total_size(sizeof(__u32)) /* NDA_IFINDEX */
+ nla_total_size(sizeof(__s32)) /* NDA_LINK_NETNSID */
+ nla_total_size(sizeof(struct nda_cacheinfo));
}
static void vxlan_fdb_notify(struct vxlan_dev *vxlan, struct vxlan_fdb *fdb,
struct vxlan_rdst *rd, int type)
{
struct net *net = dev_net(vxlan->dev);
struct sk_buff *skb;
int err = -ENOBUFS;
skb = nlmsg_new(vxlan_nlmsg_size(), GFP_ATOMIC);
if (skb == NULL)
goto errout;
err = vxlan_fdb_info(skb, vxlan, fdb, 0, 0, type, 0, rd);
if (err < 0) {
/* -EMSGSIZE implies BUG in vxlan_nlmsg_size() */
WARN_ON(err == -EMSGSIZE);
kfree_skb(skb);
goto errout;
}
rtnl_notify(skb, net, 0, RTNLGRP_NEIGH, NULL, GFP_ATOMIC);
return;
errout:
if (err < 0)
rtnl_set_sk_err(net, RTNLGRP_NEIGH, err);
}
static void vxlan_ip_miss(struct net_device *dev, union vxlan_addr *ipa)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb f = {
.state = NUD_STALE,
};
struct vxlan_rdst remote = {
.remote_ip = *ipa, /* goes to NDA_DST */
.remote_vni = cpu_to_be32(VXLAN_N_VID),
};
vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH);
}
static void vxlan_fdb_miss(struct vxlan_dev *vxlan, const u8 eth_addr[ETH_ALEN])
{
struct vxlan_fdb f = {
.state = NUD_STALE,
};
struct vxlan_rdst remote = { };
memcpy(f.eth_addr, eth_addr, ETH_ALEN);
vxlan_fdb_notify(vxlan, &f, &remote, RTM_GETNEIGH);
}
/* Hash Ethernet address */
static u32 eth_hash(const unsigned char *addr)
{
u64 value = get_unaligned((u64 *)addr);
/* only want 6 bytes */
#ifdef __BIG_ENDIAN
value >>= 16;
#else
value <<= 16;
#endif
return hash_64(value, FDB_HASH_BITS);
}
/* Hash chain to use given mac address */
static inline struct hlist_head *vxlan_fdb_head(struct vxlan_dev *vxlan,
const u8 *mac)
{
return &vxlan->fdb_head[eth_hash(mac)];
}
/* Look up Ethernet address in forwarding table */
static struct vxlan_fdb *__vxlan_find_mac(struct vxlan_dev *vxlan,
const u8 *mac)
{
struct hlist_head *head = vxlan_fdb_head(vxlan, mac);
struct vxlan_fdb *f;
hlist_for_each_entry_rcu(f, head, hlist) {
if (ether_addr_equal(mac, f->eth_addr))
return f;
}
return NULL;
}
static struct vxlan_fdb *vxlan_find_mac(struct vxlan_dev *vxlan,
const u8 *mac)
{
struct vxlan_fdb *f;
f = __vxlan_find_mac(vxlan, mac);
if (f)
f->used = jiffies;
return f;
}
/* caller should hold vxlan->hash_lock */
static struct vxlan_rdst *vxlan_fdb_find_rdst(struct vxlan_fdb *f,
union vxlan_addr *ip, __be16 port,
__be32 vni, __u32 ifindex)
{
struct vxlan_rdst *rd;
list_for_each_entry(rd, &f->remotes, list) {
if (vxlan_addr_equal(&rd->remote_ip, ip) &&
rd->remote_port == port &&
rd->remote_vni == vni &&
rd->remote_ifindex == ifindex)
return rd;
}
return NULL;
}
/* Replace destination of unicast mac */
static int vxlan_fdb_replace(struct vxlan_fdb *f,
union vxlan_addr *ip, __be16 port, __be32 vni,
__u32 ifindex)
{
struct vxlan_rdst *rd;
rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex);
if (rd)
return 0;
rd = list_first_entry_or_null(&f->remotes, struct vxlan_rdst, list);
if (!rd)
return 0;
dst_cache_reset(&rd->dst_cache);
rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
rd->remote_ifindex = ifindex;
return 1;
}
/* Add/update destinations for multicast */
static int vxlan_fdb_append(struct vxlan_fdb *f,
union vxlan_addr *ip, __be16 port, __be32 vni,
__u32 ifindex, struct vxlan_rdst **rdp)
{
struct vxlan_rdst *rd;
rd = vxlan_fdb_find_rdst(f, ip, port, vni, ifindex);
if (rd)
return 0;
rd = kmalloc(sizeof(*rd), GFP_ATOMIC);
if (rd == NULL)
return -ENOBUFS;
if (dst_cache_init(&rd->dst_cache, GFP_ATOMIC)) {
kfree(rd);
return -ENOBUFS;
}
rd->remote_ip = *ip;
rd->remote_port = port;
rd->remote_vni = vni;
rd->remote_ifindex = ifindex;
list_add_tail_rcu(&rd->list, &f->remotes);
*rdp = rd;
return 1;
}
static struct vxlanhdr *vxlan_gro_remcsum(struct sk_buff *skb,
unsigned int off,
struct vxlanhdr *vh, size_t hdrlen,
__be32 vni_field,
struct gro_remcsum *grc,
bool nopartial)
{
size_t start, offset;
if (skb->remcsum_offload)
return vh;
if (!NAPI_GRO_CB(skb)->csum_valid)
return NULL;
start = vxlan_rco_start(vni_field);
offset = start + vxlan_rco_offset(vni_field);
vh = skb_gro_remcsum_process(skb, (void *)vh, off, hdrlen,
start, offset, grc, nopartial);
skb->remcsum_offload = 1;
return vh;
}
static struct sk_buff **vxlan_gro_receive(struct sock *sk,
struct sk_buff **head,
struct sk_buff *skb)
{
struct sk_buff *p, **pp = NULL;
struct vxlanhdr *vh, *vh2;
unsigned int hlen, off_vx;
int flush = 1;
struct vxlan_sock *vs = rcu_dereference_sk_user_data(sk);
__be32 flags;
struct gro_remcsum grc;
skb_gro_remcsum_init(&grc);
off_vx = skb_gro_offset(skb);
hlen = off_vx + sizeof(*vh);
vh = skb_gro_header_fast(skb, off_vx);
if (skb_gro_header_hard(skb, hlen)) {
vh = skb_gro_header_slow(skb, hlen, off_vx);
if (unlikely(!vh))
goto out;
}
skb_gro_postpull_rcsum(skb, vh, sizeof(struct vxlanhdr));
flags = vh->vx_flags;
if ((flags & VXLAN_HF_RCO) && (vs->flags & VXLAN_F_REMCSUM_RX)) {
vh = vxlan_gro_remcsum(skb, off_vx, vh, sizeof(struct vxlanhdr),
vh->vx_vni, &grc,
!!(vs->flags &
VXLAN_F_REMCSUM_NOPARTIAL));
if (!vh)
goto out;
}
skb_gro_pull(skb, sizeof(struct vxlanhdr)); /* pull vxlan header */
for (p = *head; p; p = p->next) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
vh2 = (struct vxlanhdr *)(p->data + off_vx);
if (vh->vx_flags != vh2->vx_flags ||
vh->vx_vni != vh2->vx_vni) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
pp = eth_gro_receive(head, skb);
flush = 0;
out:
skb_gro_remcsum_cleanup(skb, &grc);
NAPI_GRO_CB(skb)->flush |= flush;
return pp;
}
static int vxlan_gro_complete(struct sock *sk, struct sk_buff *skb, int nhoff)
{
/* Sets 'skb->inner_mac_header' since we are always called with
* 'skb->encapsulation' set.
*/
return eth_gro_complete(skb, nhoff + sizeof(struct vxlanhdr));
}
/* Add new entry to forwarding table -- assumes lock held */
static int vxlan_fdb_create(struct vxlan_dev *vxlan,
const u8 *mac, union vxlan_addr *ip,
__u16 state, __u16 flags,
__be16 port, __be32 vni, __u32 ifindex,
__u8 ndm_flags)
{
struct vxlan_rdst *rd = NULL;
struct vxlan_fdb *f;
int notify = 0;
f = __vxlan_find_mac(vxlan, mac);
if (f) {
if (flags & NLM_F_EXCL) {
netdev_dbg(vxlan->dev,
"lost race to create %pM\n", mac);
return -EEXIST;
}
if (f->state != state) {
f->state = state;
f->updated = jiffies;
notify = 1;
}
if (f->flags != ndm_flags) {
f->flags = ndm_flags;
f->updated = jiffies;
notify = 1;
}
if ((flags & NLM_F_REPLACE)) {
/* Only change unicasts */
if (!(is_multicast_ether_addr(f->eth_addr) ||
is_zero_ether_addr(f->eth_addr))) {
notify |= vxlan_fdb_replace(f, ip, port, vni,
ifindex);
} else
return -EOPNOTSUPP;
}
if ((flags & NLM_F_APPEND) &&
(is_multicast_ether_addr(f->eth_addr) ||
is_zero_ether_addr(f->eth_addr))) {
int rc = vxlan_fdb_append(f, ip, port, vni, ifindex,
&rd);
if (rc < 0)
return rc;
notify |= rc;
}
} else {
if (!(flags & NLM_F_CREATE))
return -ENOENT;
if (vxlan->cfg.addrmax &&
vxlan->addrcnt >= vxlan->cfg.addrmax)
return -ENOSPC;
/* Disallow replace to add a multicast entry */
if ((flags & NLM_F_REPLACE) &&
(is_multicast_ether_addr(mac) || is_zero_ether_addr(mac)))
return -EOPNOTSUPP;
netdev_dbg(vxlan->dev, "add %pM -> %pIS\n", mac, ip);
f = kmalloc(sizeof(*f), GFP_ATOMIC);
if (!f)
return -ENOMEM;
notify = 1;
f->state = state;
f->flags = ndm_flags;
f->updated = f->used = jiffies;
INIT_LIST_HEAD(&f->remotes);
memcpy(f->eth_addr, mac, ETH_ALEN);
vxlan_fdb_append(f, ip, port, vni, ifindex, &rd);
++vxlan->addrcnt;
hlist_add_head_rcu(&f->hlist,
vxlan_fdb_head(vxlan, mac));
}
if (notify) {
if (rd == NULL)
rd = first_remote_rtnl(f);
vxlan_fdb_notify(vxlan, f, rd, RTM_NEWNEIGH);
}
return 0;
}
static void vxlan_fdb_free(struct rcu_head *head)
{
struct vxlan_fdb *f = container_of(head, struct vxlan_fdb, rcu);
struct vxlan_rdst *rd, *nd;
list_for_each_entry_safe(rd, nd, &f->remotes, list) {
dst_cache_destroy(&rd->dst_cache);
kfree(rd);
}
kfree(f);
}
static void vxlan_fdb_destroy(struct vxlan_dev *vxlan, struct vxlan_fdb *f)
{
netdev_dbg(vxlan->dev,
"delete %pM\n", f->eth_addr);
--vxlan->addrcnt;
vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_DELNEIGH);
hlist_del_rcu(&f->hlist);
call_rcu(&f->rcu, vxlan_fdb_free);
}
static int vxlan_fdb_parse(struct nlattr *tb[], struct vxlan_dev *vxlan,
union vxlan_addr *ip, __be16 *port, __be32 *vni,
u32 *ifindex)
{
struct net *net = dev_net(vxlan->dev);
int err;
if (tb[NDA_DST]) {
err = vxlan_nla_get_addr(ip, tb[NDA_DST]);
if (err)
return err;
} else {
union vxlan_addr *remote = &vxlan->default_dst.remote_ip;
if (remote->sa.sa_family == AF_INET) {
ip->sin.sin_addr.s_addr = htonl(INADDR_ANY);
ip->sa.sa_family = AF_INET;
#if IS_ENABLED(CONFIG_IPV6)
} else {
ip->sin6.sin6_addr = in6addr_any;
ip->sa.sa_family = AF_INET6;
#endif
}
}
if (tb[NDA_PORT]) {
if (nla_len(tb[NDA_PORT]) != sizeof(__be16))
return -EINVAL;
*port = nla_get_be16(tb[NDA_PORT]);
} else {
*port = vxlan->cfg.dst_port;
}
if (tb[NDA_VNI]) {
if (nla_len(tb[NDA_VNI]) != sizeof(u32))
return -EINVAL;
*vni = cpu_to_be32(nla_get_u32(tb[NDA_VNI]));
} else {
*vni = vxlan->default_dst.remote_vni;
}
if (tb[NDA_IFINDEX]) {
struct net_device *tdev;
if (nla_len(tb[NDA_IFINDEX]) != sizeof(u32))
return -EINVAL;
*ifindex = nla_get_u32(tb[NDA_IFINDEX]);
tdev = __dev_get_by_index(net, *ifindex);
if (!tdev)
return -EADDRNOTAVAIL;
} else {
*ifindex = 0;
}
return 0;
}
/* Add static entry (via netlink) */
static int vxlan_fdb_add(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid, u16 flags)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
/* struct net *net = dev_net(vxlan->dev); */
union vxlan_addr ip;
__be16 port;
__be32 vni;
u32 ifindex;
int err;
if (!(ndm->ndm_state & (NUD_PERMANENT|NUD_REACHABLE))) {
pr_info("RTM_NEWNEIGH with invalid state %#x\n",
ndm->ndm_state);
return -EINVAL;
}
if (tb[NDA_DST] == NULL)
return -EINVAL;
err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex);
if (err)
return err;
if (vxlan->default_dst.remote_ip.sa.sa_family != ip.sa.sa_family)
return -EAFNOSUPPORT;
spin_lock_bh(&vxlan->hash_lock);
err = vxlan_fdb_create(vxlan, addr, &ip, ndm->ndm_state, flags,
port, vni, ifindex, ndm->ndm_flags);
spin_unlock_bh(&vxlan->hash_lock);
return err;
}
/* Delete entry (via netlink) */
static int vxlan_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[],
struct net_device *dev,
const unsigned char *addr, u16 vid)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
struct vxlan_rdst *rd = NULL;
union vxlan_addr ip;
__be16 port;
__be32 vni;
u32 ifindex;
int err;
err = vxlan_fdb_parse(tb, vxlan, &ip, &port, &vni, &ifindex);
if (err)
return err;
err = -ENOENT;
spin_lock_bh(&vxlan->hash_lock);
f = vxlan_find_mac(vxlan, addr);
if (!f)
goto out;
if (!vxlan_addr_any(&ip)) {
rd = vxlan_fdb_find_rdst(f, &ip, port, vni, ifindex);
if (!rd)
goto out;
}
err = 0;
/* remove a destination if it's not the only one on the list,
* otherwise destroy the fdb entry
*/
if (rd && !list_is_singular(&f->remotes)) {
list_del_rcu(&rd->list);
vxlan_fdb_notify(vxlan, f, rd, RTM_DELNEIGH);
kfree_rcu(rd, rcu);
goto out;
}
vxlan_fdb_destroy(vxlan, f);
out:
spin_unlock_bh(&vxlan->hash_lock);
return err;
}
/* Dump forwarding table */
static int vxlan_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
struct net_device *dev,
struct net_device *filter_dev, int idx)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
unsigned int h;
for (h = 0; h < FDB_HASH_SIZE; ++h) {
struct vxlan_fdb *f;
int err;
hlist_for_each_entry_rcu(f, &vxlan->fdb_head[h], hlist) {
struct vxlan_rdst *rd;
list_for_each_entry_rcu(rd, &f->remotes, list) {
if (idx < cb->args[0])
goto skip;
err = vxlan_fdb_info(skb, vxlan, f,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
RTM_NEWNEIGH,
NLM_F_MULTI, rd);
if (err < 0) {
cb->args[1] = err;
goto out;
}
skip:
++idx;
}
}
}
out:
return idx;
}
/* Watch incoming packets to learn mapping between Ethernet address
* and Tunnel endpoint.
* Return true if packet is bogus and should be dropped.
*/
static bool vxlan_snoop(struct net_device *dev,
union vxlan_addr *src_ip, const u8 *src_mac)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
f = vxlan_find_mac(vxlan, src_mac);
if (likely(f)) {
struct vxlan_rdst *rdst = first_remote_rcu(f);
if (likely(vxlan_addr_equal(&rdst->remote_ip, src_ip)))
return false;
/* Don't migrate static entries, drop packets */
if (f->state & NUD_NOARP)
return true;
if (net_ratelimit())
netdev_info(dev,
"%pM migrated from %pIS to %pIS\n",
src_mac, &rdst->remote_ip.sa, &src_ip->sa);
rdst->remote_ip = *src_ip;
f->updated = jiffies;
vxlan_fdb_notify(vxlan, f, rdst, RTM_NEWNEIGH);
} else {
/* learned new entry */
spin_lock(&vxlan->hash_lock);
/* close off race between vxlan_flush and incoming packets */
if (netif_running(dev))
vxlan_fdb_create(vxlan, src_mac, src_ip,
NUD_REACHABLE,
NLM_F_EXCL|NLM_F_CREATE,
vxlan->cfg.dst_port,
vxlan->default_dst.remote_vni,
0, NTF_SELF);
spin_unlock(&vxlan->hash_lock);
}
return false;
}
/* See if multicast group is already in use by other ID */
static bool vxlan_group_used(struct vxlan_net *vn, struct vxlan_dev *dev)
{
struct vxlan_dev *vxlan;
unsigned short family = dev->default_dst.remote_ip.sa.sa_family;
/* The vxlan_sock is only used by dev, leaving group has
* no effect on other vxlan devices.
*/
if (family == AF_INET && dev->vn4_sock &&
atomic_read(&dev->vn4_sock->refcnt) == 1)
return false;
#if IS_ENABLED(CONFIG_IPV6)
if (family == AF_INET6 && dev->vn6_sock &&
atomic_read(&dev->vn6_sock->refcnt) == 1)
return false;
#endif
list_for_each_entry(vxlan, &vn->vxlan_list, next) {
if (!netif_running(vxlan->dev) || vxlan == dev)
continue;
if (family == AF_INET && vxlan->vn4_sock != dev->vn4_sock)
continue;
#if IS_ENABLED(CONFIG_IPV6)
if (family == AF_INET6 && vxlan->vn6_sock != dev->vn6_sock)
continue;
#endif
if (!vxlan_addr_equal(&vxlan->default_dst.remote_ip,
&dev->default_dst.remote_ip))
continue;
if (vxlan->default_dst.remote_ifindex !=
dev->default_dst.remote_ifindex)
continue;
return true;
}
return false;
}
static bool __vxlan_sock_release_prep(struct vxlan_sock *vs)
{
struct vxlan_net *vn;
if (!vs)
return false;
if (!atomic_dec_and_test(&vs->refcnt))
return false;
vn = net_generic(sock_net(vs->sock->sk), vxlan_net_id);
spin_lock(&vn->sock_lock);
hlist_del_rcu(&vs->hlist);
udp_tunnel_notify_del_rx_port(vs->sock,