forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathvxlan.c
1310 lines (1071 loc) · 31.1 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 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.
*
* TODO
* - use IANA UDP port number (when defined)
* - IPv6 (not in RFC)
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/rculist.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/udp.h>
#include <linux/igmp.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <linux/hash.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/rtnetlink.h>
#include <net/route.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#define VXLAN_VERSION "0.1"
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
#define FDB_HASH_BITS 8
#define FDB_HASH_SIZE (1<<FDB_HASH_BITS)
#define FDB_AGE_DEFAULT 300 /* 5 min */
#define FDB_AGE_INTERVAL (10 * HZ) /* rescan interval */
#define VXLAN_N_VID (1u << 24)
#define VXLAN_VID_MASK (VXLAN_N_VID - 1)
/* IP header + UDP + VXLAN + Ethernet header */
#define VXLAN_HEADROOM (20 + 8 + 8 + 14)
#define VXLAN_FLAGS 0x08000000 /* struct vxlanhdr.vx_flags required value. */
/* VXLAN protocol header */
struct vxlanhdr {
__be32 vx_flags;
__be32 vx_vni;
};
/* UDP port for VXLAN traffic. */
static unsigned int vxlan_port __read_mostly = 8472;
module_param_named(udp_port, vxlan_port, uint, 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");
/* per-net private data for this module */
static unsigned int vxlan_net_id;
struct vxlan_net {
struct socket *sock; /* UDP encap socket */
struct hlist_head vni_list[VNI_HASH_SIZE];
};
/* 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;
__be32 remote_ip;
u16 state; /* see ndm_state */
u8 eth_addr[ETH_ALEN];
};
/* Per-cpu network traffic stats */
struct vxlan_stats {
u64 rx_packets;
u64 rx_bytes;
u64 tx_packets;
u64 tx_bytes;
struct u64_stats_sync syncp;
};
/* Pseudo network device */
struct vxlan_dev {
struct hlist_node hlist;
struct net_device *dev;
struct vxlan_stats __percpu *stats;
__u32 vni; /* virtual network id */
__be32 gaddr; /* multicast group */
__be32 saddr; /* source address */
unsigned int link; /* link to multicast over */
__u16 port_min; /* source port range */
__u16 port_max;
__u8 tos; /* TOS override */
__u8 ttl;
bool learn;
unsigned long age_interval;
struct timer_list age_timer;
spinlock_t hash_lock;
unsigned int addrcnt;
unsigned int addrmax;
unsigned int addrexceeded;
struct hlist_head fdb_head[FDB_HASH_SIZE];
};
/* salt for hash table */
static u32 vxlan_salt __read_mostly;
static inline struct hlist_head *vni_head(struct net *net, u32 id)
{
struct vxlan_net *vn = net_generic(net, vxlan_net_id);
return &vn->vni_list[hash_32(id, VNI_HASH_BITS)];
}
/* Look up VNI in a per net namespace table */
static struct vxlan_dev *vxlan_find_vni(struct net *net, u32 id)
{
struct vxlan_dev *vxlan;
struct hlist_node *node;
hlist_for_each_entry_rcu(vxlan, node, vni_head(net, id), hlist) {
if (vxlan->vni == id)
return vxlan;
}
return NULL;
}
/* 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)
{
unsigned long now = jiffies;
struct nda_cacheinfo ci;
struct nlmsghdr *nlh;
struct ndmsg *ndm;
nlh = nlmsg_put(skb, portid, seq, type, sizeof(*ndm), flags);
if (nlh == NULL)
return -EMSGSIZE;
ndm = nlmsg_data(nlh);
memset(ndm, 0, sizeof(*ndm));
ndm->ndm_family = AF_BRIDGE;
ndm->ndm_state = fdb->state;
ndm->ndm_ifindex = vxlan->dev->ifindex;
ndm->ndm_flags = NTF_SELF;
ndm->ndm_type = NDA_DST;
if (nla_put(skb, NDA_LLADDR, ETH_ALEN, &fdb->eth_addr))
goto nla_put_failure;
if (nla_put_be32(skb, NDA_DST, fdb->remote_ip))
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;
return nlmsg_end(skb, nlh);
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(__be32)) /* NDA_DST */
+ nla_total_size(sizeof(struct nda_cacheinfo));
}
static void vxlan_fdb_notify(struct vxlan_dev *vxlan,
const struct vxlan_fdb *fdb, 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);
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);
}
/* 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;
struct hlist_node *node;
hlist_for_each_entry_rcu(f, node, head, hlist) {
if (compare_ether_addr(mac, f->eth_addr) == 0)
return f;
}
return NULL;
}
/* Add new entry to forwarding table -- assumes lock held */
static int vxlan_fdb_create(struct vxlan_dev *vxlan,
const u8 *mac, __be32 ip,
__u16 state, __u16 flags)
{
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;
}
} else {
if (!(flags & NLM_F_CREATE))
return -ENOENT;
if (vxlan->addrmax && vxlan->addrcnt >= vxlan->addrmax)
return -ENOSPC;
netdev_dbg(vxlan->dev, "add %pM -> %pI4\n", mac, &ip);
f = kmalloc(sizeof(*f), GFP_ATOMIC);
if (!f)
return -ENOMEM;
notify = 1;
f->remote_ip = ip;
f->state = state;
f->updated = f->used = jiffies;
memcpy(f->eth_addr, mac, ETH_ALEN);
++vxlan->addrcnt;
hlist_add_head_rcu(&f->hlist,
vxlan_fdb_head(vxlan, mac));
}
if (notify)
vxlan_fdb_notify(vxlan, f, RTM_NEWNEIGH);
return 0;
}
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, RTM_DELNEIGH);
hlist_del_rcu(&f->hlist);
kfree_rcu(f, rcu);
}
/* 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 flags)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
__be32 ip;
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;
if (nla_len(tb[NDA_DST]) != sizeof(__be32))
return -EAFNOSUPPORT;
ip = nla_get_be32(tb[NDA_DST]);
spin_lock_bh(&vxlan->hash_lock);
err = vxlan_fdb_create(vxlan, addr, ip, ndm->ndm_state, flags);
spin_unlock_bh(&vxlan->hash_lock);
return err;
}
/* Delete entry (via netlink) */
static int vxlan_fdb_delete(struct ndmsg *ndm, struct net_device *dev,
const unsigned char *addr)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
int err = -ENOENT;
spin_lock_bh(&vxlan->hash_lock);
f = vxlan_find_mac(vxlan, addr);
if (f) {
vxlan_fdb_destroy(vxlan, f);
err = 0;
}
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, int idx)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
unsigned int h;
for (h = 0; h < FDB_HASH_SIZE; ++h) {
struct vxlan_fdb *f;
struct hlist_node *n;
int err;
hlist_for_each_entry_rcu(f, n, &vxlan->fdb_head[h], hlist) {
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);
if (err < 0)
break;
skip:
++idx;
}
}
return idx;
}
/* Watch incoming packets to learn mapping between Ethernet address
* and Tunnel endpoint.
*/
static void vxlan_snoop(struct net_device *dev,
__be32 src_ip, const u8 *src_mac)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_fdb *f;
int err;
f = vxlan_find_mac(vxlan, src_mac);
if (likely(f)) {
f->used = jiffies;
if (likely(f->remote_ip == src_ip))
return;
if (net_ratelimit())
netdev_info(dev,
"%pM migrated from %pI4 to %pI4\n",
src_mac, &f->remote_ip, &src_ip);
f->remote_ip = src_ip;
f->updated = jiffies;
} else {
/* learned new entry */
spin_lock(&vxlan->hash_lock);
err = vxlan_fdb_create(vxlan, src_mac, src_ip,
NUD_REACHABLE,
NLM_F_EXCL|NLM_F_CREATE);
spin_unlock(&vxlan->hash_lock);
}
}
/* See if multicast group is already in use by other ID */
static bool vxlan_group_used(struct vxlan_net *vn,
const struct vxlan_dev *this)
{
const struct vxlan_dev *vxlan;
struct hlist_node *node;
unsigned h;
for (h = 0; h < VNI_HASH_SIZE; ++h)
hlist_for_each_entry(vxlan, node, &vn->vni_list[h], hlist) {
if (vxlan == this)
continue;
if (!netif_running(vxlan->dev))
continue;
if (vxlan->gaddr == this->gaddr)
return true;
}
return false;
}
/* kernel equivalent to IP_ADD_MEMBERSHIP */
static int vxlan_join_group(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct sock *sk = vn->sock->sk;
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = vxlan->gaddr,
};
int err;
/* Already a member of group */
if (vxlan_group_used(vn, vxlan))
return 0;
/* Need to drop RTNL to call multicast join */
rtnl_unlock();
lock_sock(sk);
err = ip_mc_join_group(sk, &mreq);
release_sock(sk);
rtnl_lock();
return err;
}
/* kernel equivalent to IP_DROP_MEMBERSHIP */
static int vxlan_leave_group(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
int err = 0;
struct sock *sk = vn->sock->sk;
struct ip_mreqn mreq = {
.imr_multiaddr.s_addr = vxlan->gaddr,
};
/* Only leave group when last vxlan is done. */
if (vxlan_group_used(vn, vxlan))
return 0;
/* Need to drop RTNL to call multicast leave */
rtnl_unlock();
lock_sock(sk);
err = ip_mc_leave_group(sk, &mreq);
release_sock(sk);
rtnl_lock();
return err;
}
/* Callback from net/ipv4/udp.c to receive packets */
static int vxlan_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct iphdr *oip;
struct vxlanhdr *vxh;
struct vxlan_dev *vxlan;
struct vxlan_stats *stats;
__u32 vni;
int err;
/* pop off outer UDP header */
__skb_pull(skb, sizeof(struct udphdr));
/* Need Vxlan and inner Ethernet header to be present */
if (!pskb_may_pull(skb, sizeof(struct vxlanhdr)))
goto error;
/* Drop packets with reserved bits set */
vxh = (struct vxlanhdr *) skb->data;
if (vxh->vx_flags != htonl(VXLAN_FLAGS) ||
(vxh->vx_vni & htonl(0xff))) {
netdev_dbg(skb->dev, "invalid vxlan flags=%#x vni=%#x\n",
ntohl(vxh->vx_flags), ntohl(vxh->vx_vni));
goto error;
}
__skb_pull(skb, sizeof(struct vxlanhdr));
/* Is this VNI defined? */
vni = ntohl(vxh->vx_vni) >> 8;
vxlan = vxlan_find_vni(sock_net(sk), vni);
if (!vxlan) {
netdev_dbg(skb->dev, "unknown vni %d\n", vni);
goto drop;
}
if (!pskb_may_pull(skb, ETH_HLEN)) {
vxlan->dev->stats.rx_length_errors++;
vxlan->dev->stats.rx_errors++;
goto drop;
}
/* Re-examine inner Ethernet packet */
oip = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, vxlan->dev);
/* Ignore packet loops (and multicast echo) */
if (compare_ether_addr(eth_hdr(skb)->h_source,
vxlan->dev->dev_addr) == 0)
goto drop;
if (vxlan->learn)
vxlan_snoop(skb->dev, oip->saddr, eth_hdr(skb)->h_source);
__skb_tunnel_rx(skb, vxlan->dev);
skb_reset_network_header(skb);
skb->ip_summed = CHECKSUM_NONE;
err = IP_ECN_decapsulate(oip, skb);
if (unlikely(err)) {
if (log_ecn_error)
net_info_ratelimited("non-ECT from %pI4 with TOS=%#x\n",
&oip->saddr, oip->tos);
if (err > 1) {
++vxlan->dev->stats.rx_frame_errors;
++vxlan->dev->stats.rx_errors;
goto drop;
}
}
stats = this_cpu_ptr(vxlan->stats);
u64_stats_update_begin(&stats->syncp);
stats->rx_packets++;
stats->rx_bytes += skb->len;
u64_stats_update_end(&stats->syncp);
netif_rx(skb);
return 0;
error:
/* Put UDP header back */
__skb_push(skb, sizeof(struct udphdr));
return 1;
drop:
/* Consume bad packet */
kfree_skb(skb);
return 0;
}
/* Extract dsfield from inner protocol */
static inline u8 vxlan_get_dsfield(const struct iphdr *iph,
const struct sk_buff *skb)
{
if (skb->protocol == htons(ETH_P_IP))
return iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
return ipv6_get_dsfield((const struct ipv6hdr *)iph);
else
return 0;
}
/* Propogate ECN bits out */
static inline u8 vxlan_ecn_encap(u8 tos,
const struct iphdr *iph,
const struct sk_buff *skb)
{
u8 inner = vxlan_get_dsfield(iph, skb);
return INET_ECN_encapsulate(tos, inner);
}
static __be32 vxlan_find_dst(struct vxlan_dev *vxlan, struct sk_buff *skb)
{
const struct ethhdr *eth = (struct ethhdr *) skb->data;
const struct vxlan_fdb *f;
if (is_multicast_ether_addr(eth->h_dest))
return vxlan->gaddr;
f = vxlan_find_mac(vxlan, eth->h_dest);
if (f)
return f->remote_ip;
else
return vxlan->gaddr;
}
static void vxlan_sock_free(struct sk_buff *skb)
{
sock_put(skb->sk);
}
/* On transmit, associate with the tunnel socket */
static void vxlan_set_owner(struct net_device *dev, struct sk_buff *skb)
{
struct vxlan_net *vn = net_generic(dev_net(dev), vxlan_net_id);
struct sock *sk = vn->sock->sk;
skb_orphan(skb);
sock_hold(sk);
skb->sk = sk;
skb->destructor = vxlan_sock_free;
}
/* Compute source port for outgoing packet
* first choice to use L4 flow hash since it will spread
* better and maybe available from hardware
* secondary choice is to use jhash on the Ethernet header
*/
static u16 vxlan_src_port(const struct vxlan_dev *vxlan, struct sk_buff *skb)
{
unsigned int range = (vxlan->port_max - vxlan->port_min) + 1;
u32 hash;
hash = skb_get_rxhash(skb);
if (!hash)
hash = jhash(skb->data, 2 * ETH_ALEN,
(__force u32) skb->protocol);
return (((u64) hash * range) >> 32) + vxlan->port_min;
}
/* Transmit local packets over Vxlan
*
* Outer IP header inherits ECN and DF from inner header.
* Outer UDP destination is the VXLAN assigned port.
* source port is based on hash of flow
*/
static netdev_tx_t vxlan_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct rtable *rt;
const struct iphdr *old_iph;
struct iphdr *iph;
struct vxlanhdr *vxh;
struct udphdr *uh;
struct flowi4 fl4;
unsigned int pkt_len = skb->len;
__be32 dst;
__u16 src_port;
__be16 df = 0;
__u8 tos, ttl;
int err;
dst = vxlan_find_dst(vxlan, skb);
if (!dst)
goto drop;
/* Need space for new headers (invalidates iph ptr) */
if (skb_cow_head(skb, VXLAN_HEADROOM))
goto drop;
old_iph = ip_hdr(skb);
ttl = vxlan->ttl;
if (!ttl && IN_MULTICAST(ntohl(dst)))
ttl = 1;
tos = vxlan->tos;
if (tos == 1)
tos = vxlan_get_dsfield(old_iph, skb);
src_port = vxlan_src_port(vxlan, skb);
memset(&fl4, 0, sizeof(fl4));
fl4.flowi4_oif = vxlan->link;
fl4.flowi4_tos = RT_TOS(tos);
fl4.daddr = dst;
fl4.saddr = vxlan->saddr;
rt = ip_route_output_key(dev_net(dev), &fl4);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n", &dst);
dev->stats.tx_carrier_errors++;
goto tx_error;
}
if (rt->dst.dev == dev) {
netdev_dbg(dev, "circular route to %pI4\n", &dst);
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED |
IPSKB_REROUTED);
skb_dst_drop(skb);
skb_dst_set(skb, &rt->dst);
vxh = (struct vxlanhdr *) __skb_push(skb, sizeof(*vxh));
vxh->vx_flags = htonl(VXLAN_FLAGS);
vxh->vx_vni = htonl(vxlan->vni << 8);
__skb_push(skb, sizeof(*uh));
skb_reset_transport_header(skb);
uh = udp_hdr(skb);
uh->dest = htons(vxlan_port);
uh->source = htons(src_port);
uh->len = htons(skb->len);
uh->check = 0;
__skb_push(skb, sizeof(*iph));
skb_reset_network_header(skb);
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = IPPROTO_UDP;
iph->tos = vxlan_ecn_encap(tos, old_iph, skb);
iph->daddr = dst;
iph->saddr = fl4.saddr;
iph->ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
vxlan_set_owner(dev, skb);
/* See __IPTUNNEL_XMIT */
skb->ip_summed = CHECKSUM_NONE;
ip_select_ident(iph, &rt->dst, NULL);
err = ip_local_out(skb);
if (likely(net_xmit_eval(err) == 0)) {
struct vxlan_stats *stats = this_cpu_ptr(vxlan->stats);
u64_stats_update_begin(&stats->syncp);
stats->tx_packets++;
stats->tx_bytes += pkt_len;
u64_stats_update_end(&stats->syncp);
} else {
dev->stats.tx_errors++;
dev->stats.tx_aborted_errors++;
}
return NETDEV_TX_OK;
drop:
dev->stats.tx_dropped++;
goto tx_free;
tx_error:
dev->stats.tx_errors++;
tx_free:
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
/* Walk the forwarding table and purge stale entries */
static void vxlan_cleanup(unsigned long arg)
{
struct vxlan_dev *vxlan = (struct vxlan_dev *) arg;
unsigned long next_timer = jiffies + FDB_AGE_INTERVAL;
unsigned int h;
if (!netif_running(vxlan->dev))
return;
spin_lock_bh(&vxlan->hash_lock);
for (h = 0; h < FDB_HASH_SIZE; ++h) {
struct hlist_node *p, *n;
hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
struct vxlan_fdb *f
= container_of(p, struct vxlan_fdb, hlist);
unsigned long timeout;
if (f->state & NUD_PERMANENT)
continue;
timeout = f->used + vxlan->age_interval * HZ;
if (time_before_eq(timeout, jiffies)) {
netdev_dbg(vxlan->dev,
"garbage collect %pM\n",
f->eth_addr);
f->state = NUD_STALE;
vxlan_fdb_destroy(vxlan, f);
} else if (time_before(timeout, next_timer))
next_timer = timeout;
}
}
spin_unlock_bh(&vxlan->hash_lock);
mod_timer(&vxlan->age_timer, next_timer);
}
/* Setup stats when device is created */
static int vxlan_init(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
vxlan->stats = alloc_percpu(struct vxlan_stats);
if (!vxlan->stats)
return -ENOMEM;
return 0;
}
/* Start ageing timer and join group when device is brought up */
static int vxlan_open(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
int err;
if (vxlan->gaddr) {
err = vxlan_join_group(dev);
if (err)
return err;
}
if (vxlan->age_interval)
mod_timer(&vxlan->age_timer, jiffies + FDB_AGE_INTERVAL);
return 0;
}
/* Purge the forwarding table */
static void vxlan_flush(struct vxlan_dev *vxlan)
{
unsigned h;
spin_lock_bh(&vxlan->hash_lock);
for (h = 0; h < FDB_HASH_SIZE; ++h) {
struct hlist_node *p, *n;
hlist_for_each_safe(p, n, &vxlan->fdb_head[h]) {
struct vxlan_fdb *f
= container_of(p, struct vxlan_fdb, hlist);
vxlan_fdb_destroy(vxlan, f);
}
}
spin_unlock_bh(&vxlan->hash_lock);
}
/* Cleanup timer and forwarding table on shutdown */
static int vxlan_stop(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
if (vxlan->gaddr)
vxlan_leave_group(dev);
del_timer_sync(&vxlan->age_timer);
vxlan_flush(vxlan);
return 0;
}
/* Merge per-cpu statistics */
static struct rtnl_link_stats64 *vxlan_stats64(struct net_device *dev,
struct rtnl_link_stats64 *stats)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
struct vxlan_stats tmp, sum = { 0 };
unsigned int cpu;
for_each_possible_cpu(cpu) {
unsigned int start;
const struct vxlan_stats *stats
= per_cpu_ptr(vxlan->stats, cpu);
do {
start = u64_stats_fetch_begin_bh(&stats->syncp);
memcpy(&tmp, stats, sizeof(tmp));
} while (u64_stats_fetch_retry_bh(&stats->syncp, start));
sum.tx_bytes += tmp.tx_bytes;
sum.tx_packets += tmp.tx_packets;
sum.rx_bytes += tmp.rx_bytes;
sum.rx_packets += tmp.rx_packets;
}
stats->tx_bytes = sum.tx_bytes;
stats->tx_packets = sum.tx_packets;
stats->rx_bytes = sum.rx_bytes;
stats->rx_packets = sum.rx_packets;
stats->multicast = dev->stats.multicast;
stats->rx_length_errors = dev->stats.rx_length_errors;
stats->rx_frame_errors = dev->stats.rx_frame_errors;
stats->rx_errors = dev->stats.rx_errors;
stats->tx_dropped = dev->stats.tx_dropped;
stats->tx_carrier_errors = dev->stats.tx_carrier_errors;
stats->tx_aborted_errors = dev->stats.tx_aborted_errors;
stats->collisions = dev->stats.collisions;
stats->tx_errors = dev->stats.tx_errors;
return stats;
}
/* Stub, nothing needs to be done. */
static void vxlan_set_multicast_list(struct net_device *dev)
{
}
static const struct net_device_ops vxlan_netdev_ops = {
.ndo_init = vxlan_init,
.ndo_open = vxlan_open,
.ndo_stop = vxlan_stop,
.ndo_start_xmit = vxlan_xmit,
.ndo_get_stats64 = vxlan_stats64,
.ndo_set_rx_mode = vxlan_set_multicast_list,
.ndo_change_mtu = eth_change_mtu,
.ndo_validate_addr = eth_validate_addr,
.ndo_set_mac_address = eth_mac_addr,
.ndo_fdb_add = vxlan_fdb_add,
.ndo_fdb_del = vxlan_fdb_delete,
.ndo_fdb_dump = vxlan_fdb_dump,
};
/* Info for udev, that this is a virtual tunnel endpoint */
static struct device_type vxlan_type = {
.name = "vxlan",
};
static void vxlan_free(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
free_percpu(vxlan->stats);
free_netdev(dev);
}
/* Initialize the device structure. */
static void vxlan_setup(struct net_device *dev)
{
struct vxlan_dev *vxlan = netdev_priv(dev);
unsigned h;
int low, high;
eth_hw_addr_random(dev);
ether_setup(dev);
dev->hard_header_len = ETH_HLEN + VXLAN_HEADROOM;
dev->netdev_ops = &vxlan_netdev_ops;
dev->destructor = vxlan_free;
SET_NETDEV_DEVTYPE(dev, &vxlan_type);
dev->tx_queue_len = 0;
dev->features |= NETIF_F_LLTX;
dev->features |= NETIF_F_NETNS_LOCAL;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
spin_lock_init(&vxlan->hash_lock);
init_timer_deferrable(&vxlan->age_timer);
vxlan->age_timer.function = vxlan_cleanup;
vxlan->age_timer.data = (unsigned long) vxlan;