forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
ip_gre.c
1802 lines (1500 loc) · 43.4 KB
/
ip_gre.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
/*
* Linux NET3: GRE over IP protocol decoder.
*
* Authors: Alexey Kuznetsov ([email protected])
*
* 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.
*
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/capability.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/slab.h>
#include <asm/uaccess.h>
#include <linux/skbuff.h>
#include <linux/netdevice.h>
#include <linux/in.h>
#include <linux/tcp.h>
#include <linux/udp.h>
#include <linux/if_arp.h>
#include <linux/mroute.h>
#include <linux/init.h>
#include <linux/in6.h>
#include <linux/inetdevice.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/etherdevice.h>
#include <linux/if_ether.h>
#include <net/sock.h>
#include <net/ip.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <net/ipip.h>
#include <net/arp.h>
#include <net/checksum.h>
#include <net/dsfield.h>
#include <net/inet_ecn.h>
#include <net/xfrm.h>
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
#include <net/gre.h>
#if IS_ENABLED(CONFIG_IPV6)
#include <net/ipv6.h>
#include <net/ip6_fib.h>
#include <net/ip6_route.h>
#endif
/*
Problems & solutions
--------------------
1. The most important issue is detecting local dead loops.
They would cause complete host lockup in transmit, which
would be "resolved" by stack overflow or, if queueing is enabled,
with infinite looping in net_bh.
We cannot track such dead loops during route installation,
it is infeasible task. The most general solutions would be
to keep skb->encapsulation counter (sort of local ttl),
and silently drop packet when it expires. It is a good
solution, but it supposes maintaining new variable in ALL
skb, even if no tunneling is used.
Current solution: xmit_recursion breaks dead loops. This is a percpu
counter, since when we enter the first ndo_xmit(), cpu migration is
forbidden. We force an exit if this counter reaches RECURSION_LIMIT
2. Networking dead loops would not kill routers, but would really
kill network. IP hop limit plays role of "t->recursion" in this case,
if we copy it from packet being encapsulated to upper header.
It is very good solution, but it introduces two problems:
- Routing protocols, using packets with ttl=1 (OSPF, RIP2),
do not work over tunnels.
- traceroute does not work. I planned to relay ICMP from tunnel,
so that this problem would be solved and traceroute output
would even more informative. This idea appeared to be wrong:
only Linux complies to rfc1812 now (yes, guys, Linux is the only
true router now :-)), all routers (at least, in neighbourhood of mine)
return only 8 bytes of payload. It is the end.
Hence, if we want that OSPF worked or traceroute said something reasonable,
we should search for another solution.
One of them is to parse packet trying to detect inner encapsulation
made by our node. It is difficult or even impossible, especially,
taking into account fragmentation. TO be short, ttl is not solution at all.
Current solution: The solution was UNEXPECTEDLY SIMPLE.
We force DF flag on tunnels with preconfigured hop limit,
that is ALL. :-) Well, it does not remove the problem completely,
but exponential growth of network traffic is changed to linear
(branches, that exceed pmtu are pruned) and tunnel mtu
rapidly degrades to value <68, where looping stops.
Yes, it is not good if there exists a router in the loop,
which does not force DF, even when encapsulating packets have DF set.
But it is not our problem! Nobody could accuse us, we made
all that we could make. Even if it is your gated who injected
fatal route to network, even if it were you who configured
fatal static route: you are innocent. :-)
3. Really, ipv4/ipip.c, ipv4/ip_gre.c and ipv6/sit.c contain
practically identical code. It would be good to glue them
together, but it is not very evident, how to make them modular.
sit is integral part of IPv6, ipip and gre are naturally modular.
We could extract common parts (hash table, ioctl etc)
to a separate module (ip_tunnel.c).
Alexey Kuznetsov.
*/
static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
static void ipgre_tunnel_setup(struct net_device *dev);
static int ipgre_tunnel_bind_dev(struct net_device *dev);
/* Fallback tunnel: no source, no destination, no key, no options */
#define HASH_SIZE 16
static int ipgre_net_id __read_mostly;
struct ipgre_net {
struct ip_tunnel __rcu *tunnels[4][HASH_SIZE];
struct net_device *fb_tunnel_dev;
};
/* Tunnel hash table */
/*
4 hash tables:
3: (remote,local)
2: (remote,*)
1: (*,local)
0: (*,*)
We require exact key match i.e. if a key is present in packet
it will match only tunnel with the same key; if it is not present,
it will match only keyless tunnel.
All keysless packets, if not matched configured keyless tunnels
will match fallback tunnel.
*/
#define HASH(addr) (((__force u32)addr^((__force u32)addr>>4))&0xF)
#define tunnels_r_l tunnels[3]
#define tunnels_r tunnels[2]
#define tunnels_l tunnels[1]
#define tunnels_wc tunnels[0]
/*
* Locking : hash tables are protected by RCU and RTNL
*/
#define for_each_ip_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
/* often modified stats are per cpu, other are shared (netdev->stats) */
struct pcpu_tstats {
u64 rx_packets;
u64 rx_bytes;
u64 tx_packets;
u64 tx_bytes;
struct u64_stats_sync syncp;
};
static struct rtnl_link_stats64 *ipgre_get_stats64(struct net_device *dev,
struct rtnl_link_stats64 *tot)
{
int i;
for_each_possible_cpu(i) {
const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i);
u64 rx_packets, rx_bytes, tx_packets, tx_bytes;
unsigned int start;
do {
start = u64_stats_fetch_begin_bh(&tstats->syncp);
rx_packets = tstats->rx_packets;
tx_packets = tstats->tx_packets;
rx_bytes = tstats->rx_bytes;
tx_bytes = tstats->tx_bytes;
} while (u64_stats_fetch_retry_bh(&tstats->syncp, start));
tot->rx_packets += rx_packets;
tot->tx_packets += tx_packets;
tot->rx_bytes += rx_bytes;
tot->tx_bytes += tx_bytes;
}
tot->multicast = dev->stats.multicast;
tot->rx_crc_errors = dev->stats.rx_crc_errors;
tot->rx_fifo_errors = dev->stats.rx_fifo_errors;
tot->rx_length_errors = dev->stats.rx_length_errors;
tot->rx_errors = dev->stats.rx_errors;
tot->tx_fifo_errors = dev->stats.tx_fifo_errors;
tot->tx_carrier_errors = dev->stats.tx_carrier_errors;
tot->tx_dropped = dev->stats.tx_dropped;
tot->tx_aborted_errors = dev->stats.tx_aborted_errors;
tot->tx_errors = dev->stats.tx_errors;
return tot;
}
/* Given src, dst and key, find appropriate for input tunnel. */
static struct ip_tunnel *ipgre_tunnel_lookup(struct net_device *dev,
__be32 remote, __be32 local,
__be32 key, __be16 gre_proto)
{
struct net *net = dev_net(dev);
int link = dev->ifindex;
unsigned int h0 = HASH(remote);
unsigned int h1 = HASH(key);
struct ip_tunnel *t, *cand = NULL;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
int dev_type = (gre_proto == htons(ETH_P_TEB)) ?
ARPHRD_ETHER : ARPHRD_IPGRE;
int score, cand_score = 4;
for_each_ip_tunnel_rcu(ign->tunnels_r_l[h0 ^ h1]) {
if (local != t->parms.iph.saddr ||
remote != t->parms.iph.daddr ||
key != t->parms.i_key ||
!(t->dev->flags & IFF_UP))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
for_each_ip_tunnel_rcu(ign->tunnels_r[h0 ^ h1]) {
if (remote != t->parms.iph.daddr ||
key != t->parms.i_key ||
!(t->dev->flags & IFF_UP))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
for_each_ip_tunnel_rcu(ign->tunnels_l[h1]) {
if ((local != t->parms.iph.saddr &&
(local != t->parms.iph.daddr ||
!ipv4_is_multicast(local))) ||
key != t->parms.i_key ||
!(t->dev->flags & IFF_UP))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
for_each_ip_tunnel_rcu(ign->tunnels_wc[h1]) {
if (t->parms.i_key != key ||
!(t->dev->flags & IFF_UP))
continue;
if (t->dev->type != ARPHRD_IPGRE &&
t->dev->type != dev_type)
continue;
score = 0;
if (t->parms.link != link)
score |= 1;
if (t->dev->type != dev_type)
score |= 2;
if (score == 0)
return t;
if (score < cand_score) {
cand = t;
cand_score = score;
}
}
if (cand != NULL)
return cand;
dev = ign->fb_tunnel_dev;
if (dev->flags & IFF_UP)
return netdev_priv(dev);
return NULL;
}
static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign,
struct ip_tunnel_parm *parms)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
unsigned int h = HASH(key);
int prio = 0;
if (local)
prio |= 1;
if (remote && !ipv4_is_multicast(remote)) {
prio |= 2;
h ^= HASH(remote);
}
return &ign->tunnels[prio][h];
}
static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign,
struct ip_tunnel *t)
{
return __ipgre_bucket(ign, &t->parms);
}
static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t);
rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
}
static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t)
{
struct ip_tunnel __rcu **tp;
struct ip_tunnel *iter;
for (tp = ipgre_bucket(ign, t);
(iter = rtnl_dereference(*tp)) != NULL;
tp = &iter->next) {
if (t == iter) {
rcu_assign_pointer(*tp, t->next);
break;
}
}
}
static struct ip_tunnel *ipgre_tunnel_find(struct net *net,
struct ip_tunnel_parm *parms,
int type)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
__be32 key = parms->i_key;
int link = parms->link;
struct ip_tunnel *t;
struct ip_tunnel __rcu **tp;
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
for (tp = __ipgre_bucket(ign, parms);
(t = rtnl_dereference(*tp)) != NULL;
tp = &t->next)
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
key == t->parms.i_key &&
link == t->parms.link &&
type == t->dev->type)
break;
return t;
}
static struct ip_tunnel *ipgre_tunnel_locate(struct net *net,
struct ip_tunnel_parm *parms, int create)
{
struct ip_tunnel *t, *nt;
struct net_device *dev;
char name[IFNAMSIZ];
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
t = ipgre_tunnel_find(net, parms, ARPHRD_IPGRE);
if (t || !create)
return t;
if (parms->name[0])
strlcpy(name, parms->name, IFNAMSIZ);
else
strcpy(name, "gre%d");
dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup);
if (!dev)
return NULL;
dev_net_set(dev, net);
nt = netdev_priv(dev);
nt->parms = *parms;
dev->rtnl_link_ops = &ipgre_link_ops;
dev->mtu = ipgre_tunnel_bind_dev(dev);
if (register_netdevice(dev) < 0)
goto failed_free;
/* Can use a lockless transmit, unless we generate output sequences */
if (!(nt->parms.o_flags & GRE_SEQ))
dev->features |= NETIF_F_LLTX;
dev_hold(dev);
ipgre_tunnel_link(ign, nt);
return nt;
failed_free:
free_netdev(dev);
return NULL;
}
static void ipgre_tunnel_uninit(struct net_device *dev)
{
struct net *net = dev_net(dev);
struct ipgre_net *ign = net_generic(net, ipgre_net_id);
ipgre_tunnel_unlink(ign, netdev_priv(dev));
dev_put(dev);
}
static void ipgre_err(struct sk_buff *skb, u32 info)
{
/* All the routers (except for Linux) return only
8 bytes of packet payload. It means, that precise relaying of
ICMP in the real Internet is absolutely infeasible.
Moreover, Cisco "wise men" put GRE key to the third word
in GRE header. It makes impossible maintaining even soft state for keyed
GRE tunnels with enabled checksum. Tell them "thank you".
Well, I wonder, rfc1812 was written by Cisco employee,
what the hell these idiots break standards established
by themselves???
*/
const struct iphdr *iph = (const struct iphdr *)skb->data;
__be16 *p = (__be16 *)(skb->data+(iph->ihl<<2));
int grehlen = (iph->ihl<<2) + 4;
const int type = icmp_hdr(skb)->type;
const int code = icmp_hdr(skb)->code;
struct ip_tunnel *t;
__be16 flags;
flags = p[0];
if (flags&(GRE_CSUM|GRE_KEY|GRE_SEQ|GRE_ROUTING|GRE_VERSION)) {
if (flags&(GRE_VERSION|GRE_ROUTING))
return;
if (flags&GRE_KEY) {
grehlen += 4;
if (flags&GRE_CSUM)
grehlen += 4;
}
}
/* If only 8 bytes returned, keyed message will be dropped here */
if (skb_headlen(skb) < grehlen)
return;
switch (type) {
default:
case ICMP_PARAMETERPROB:
return;
case ICMP_DEST_UNREACH:
switch (code) {
case ICMP_SR_FAILED:
case ICMP_PORT_UNREACH:
/* Impossible event. */
return;
default:
/* All others are translated to HOST_UNREACH.
rfc2003 contains "deep thoughts" about NET_UNREACH,
I believe they are just ether pollution. --ANK
*/
break;
}
break;
case ICMP_TIME_EXCEEDED:
if (code != ICMP_EXC_TTL)
return;
break;
case ICMP_REDIRECT:
break;
}
rcu_read_lock();
t = ipgre_tunnel_lookup(skb->dev, iph->daddr, iph->saddr,
flags & GRE_KEY ?
*(((__be32 *)p) + (grehlen / 4) - 1) : 0,
p[1]);
if (t == NULL)
goto out;
if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) {
ipv4_update_pmtu(skb, dev_net(skb->dev), info,
t->parms.link, 0, IPPROTO_GRE, 0);
goto out;
}
if (type == ICMP_REDIRECT) {
ipv4_redirect(skb, dev_net(skb->dev), t->parms.link, 0,
IPPROTO_GRE, 0);
goto out;
}
if (t->parms.iph.daddr == 0 ||
ipv4_is_multicast(t->parms.iph.daddr))
goto out;
if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED)
goto out;
if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO))
t->err_count++;
else
t->err_count = 1;
t->err_time = jiffies;
out:
rcu_read_unlock();
}
static inline void ipgre_ecn_decapsulate(const struct iphdr *iph, struct sk_buff *skb)
{
if (INET_ECN_is_ce(iph->tos)) {
if (skb->protocol == htons(ETH_P_IP)) {
IP_ECN_set_ce(ip_hdr(skb));
} else if (skb->protocol == htons(ETH_P_IPV6)) {
IP6_ECN_set_ce(ipv6_hdr(skb));
}
}
}
static inline u8
ipgre_ecn_encapsulate(u8 tos, const struct iphdr *old_iph, struct sk_buff *skb)
{
u8 inner = 0;
if (skb->protocol == htons(ETH_P_IP))
inner = old_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
inner = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
return INET_ECN_encapsulate(tos, inner);
}
static int ipgre_rcv(struct sk_buff *skb)
{
const struct iphdr *iph;
u8 *h;
__be16 flags;
__sum16 csum = 0;
__be32 key = 0;
u32 seqno = 0;
struct ip_tunnel *tunnel;
int offset = 4;
__be16 gre_proto;
if (!pskb_may_pull(skb, 16))
goto drop_nolock;
iph = ip_hdr(skb);
h = skb->data;
flags = *(__be16 *)h;
if (flags&(GRE_CSUM|GRE_KEY|GRE_ROUTING|GRE_SEQ|GRE_VERSION)) {
/* - Version must be 0.
- We do not support routing headers.
*/
if (flags&(GRE_VERSION|GRE_ROUTING))
goto drop_nolock;
if (flags&GRE_CSUM) {
switch (skb->ip_summed) {
case CHECKSUM_COMPLETE:
csum = csum_fold(skb->csum);
if (!csum)
break;
/* fall through */
case CHECKSUM_NONE:
skb->csum = 0;
csum = __skb_checksum_complete(skb);
skb->ip_summed = CHECKSUM_COMPLETE;
}
offset += 4;
}
if (flags&GRE_KEY) {
key = *(__be32 *)(h + offset);
offset += 4;
}
if (flags&GRE_SEQ) {
seqno = ntohl(*(__be32 *)(h + offset));
offset += 4;
}
}
gre_proto = *(__be16 *)(h + 2);
rcu_read_lock();
if ((tunnel = ipgre_tunnel_lookup(skb->dev,
iph->saddr, iph->daddr, key,
gre_proto))) {
struct pcpu_tstats *tstats;
secpath_reset(skb);
skb->protocol = gre_proto;
/* WCCP version 1 and 2 protocol decoding.
* - Change protocol to IP
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 && gre_proto == htons(ETH_P_WCCP)) {
skb->protocol = htons(ETH_P_IP);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
skb->mac_header = skb->network_header;
__pskb_pull(skb, offset);
skb_postpull_rcsum(skb, skb_transport_header(skb), offset);
skb->pkt_type = PACKET_HOST;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(iph->daddr)) {
/* Looped back packet, drop it! */
if (rt_is_output_route(skb_rtable(skb)))
goto drop;
tunnel->dev->stats.multicast++;
skb->pkt_type = PACKET_BROADCAST;
}
#endif
if (((flags&GRE_CSUM) && csum) ||
(!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) {
tunnel->dev->stats.rx_crc_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
if (tunnel->parms.i_flags&GRE_SEQ) {
if (!(flags&GRE_SEQ) ||
(tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) {
tunnel->dev->stats.rx_fifo_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
tunnel->i_seqno = seqno + 1;
}
/* Warning: All skb pointers will be invalidated! */
if (tunnel->dev->type == ARPHRD_ETHER) {
if (!pskb_may_pull(skb, ETH_HLEN)) {
tunnel->dev->stats.rx_length_errors++;
tunnel->dev->stats.rx_errors++;
goto drop;
}
iph = ip_hdr(skb);
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
}
tstats = this_cpu_ptr(tunnel->dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
__skb_tunnel_rx(skb, tunnel->dev);
skb_reset_network_header(skb);
ipgre_ecn_decapsulate(iph, skb);
netif_rx(skb);
rcu_read_unlock();
return 0;
}
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0);
drop:
rcu_read_unlock();
drop_nolock:
kfree_skb(skb);
return 0;
}
static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
struct pcpu_tstats *tstats;
const struct iphdr *old_iph = ip_hdr(skb);
const struct iphdr *tiph;
struct flowi4 fl4;
u8 tos;
__be16 df;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
unsigned int max_headroom; /* The extra header space needed */
int gre_hlen;
__be32 dst;
int mtu;
if (dev->type == ARPHRD_ETHER)
IPCB(skb)->flags = 0;
if (dev->header_ops && dev->type == ARPHRD_IPGRE) {
gre_hlen = 0;
tiph = (const struct iphdr *)skb->data;
} else {
gre_hlen = tunnel->hlen;
tiph = &tunnel->parms.iph;
}
if ((dst = tiph->daddr) == 0) {
/* NBMA tunnel */
if (skb_dst(skb) == NULL) {
dev->stats.tx_fifo_errors++;
goto tx_error;
}
if (skb->protocol == htons(ETH_P_IP)) {
rt = skb_rtable(skb);
dst = rt_nexthop(rt, old_iph->daddr);
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
const struct in6_addr *addr6;
struct neighbour *neigh;
bool do_tx_error_icmp;
int addr_type;
neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr);
if (neigh == NULL)
goto tx_error;
addr6 = (const struct in6_addr *)&neigh->primary_key;
addr_type = ipv6_addr_type(addr6);
if (addr_type == IPV6_ADDR_ANY) {
addr6 = &ipv6_hdr(skb)->daddr;
addr_type = ipv6_addr_type(addr6);
}
if ((addr_type & IPV6_ADDR_COMPATv4) == 0)
do_tx_error_icmp = true;
else {
do_tx_error_icmp = false;
dst = addr6->s6_addr32[3];
}
neigh_release(neigh);
if (do_tx_error_icmp)
goto tx_error_icmp;
}
#endif
else
goto tx_error;
}
tos = tiph->tos;
if (tos == 1) {
tos = 0;
if (skb->protocol == htons(ETH_P_IP))
tos = old_iph->tos;
else if (skb->protocol == htons(ETH_P_IPV6))
tos = ipv6_get_dsfield((const struct ipv6hdr *)old_iph);
}
rt = ip_route_output_gre(dev_net(dev), &fl4, dst, tiph->saddr,
tunnel->parms.o_key, RT_TOS(tos),
tunnel->parms.link);
if (IS_ERR(rt)) {
dev->stats.tx_carrier_errors++;
goto tx_error;
}
tdev = rt->dst.dev;
if (tdev == dev) {
ip_rt_put(rt);
dev->stats.collisions++;
goto tx_error;
}
df = tiph->frag_off;
if (df)
mtu = dst_mtu(&rt->dst) - dev->hard_header_len - tunnel->hlen;
else
mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
if (skb_dst(skb))
skb_dst(skb)->ops->update_pmtu(skb_dst(skb), NULL, skb, mtu);
if (skb->protocol == htons(ETH_P_IP)) {
df |= (old_iph->frag_off&htons(IP_DF));
if ((old_iph->frag_off&htons(IP_DF)) &&
mtu < ntohs(old_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
goto tx_error;
}
}
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6)) {
struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb);
if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) {
if ((tunnel->parms.iph.daddr &&
!ipv4_is_multicast(tunnel->parms.iph.daddr)) ||
rt6->rt6i_dst.plen == 128) {
rt6->rt6i_flags |= RTF_MODIFIED;
dst_metric_set(skb_dst(skb), RTAX_MTU, mtu);
}
}
if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
}
}
#endif
if (tunnel->err_count > 0) {
if (time_before(jiffies,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
dst_link_failure(skb);
} else
tunnel->err_count = 0;
}
max_headroom = LL_RESERVED_SPACE(tdev) + gre_hlen + rt->dst.header_len;
if (skb_headroom(skb) < max_headroom || skb_shared(skb)||
(skb_cloned(skb) && !skb_clone_writable(skb, 0))) {
struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom);
if (max_headroom > dev->needed_headroom)
dev->needed_headroom = max_headroom;
if (!new_skb) {
ip_rt_put(rt);
dev->stats.tx_dropped++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
if (skb->sk)
skb_set_owner_w(new_skb, skb->sk);
dev_kfree_skb(skb);
skb = new_skb;
old_iph = ip_hdr(skb);
}
skb_reset_transport_header(skb);
skb_push(skb, gre_hlen);
skb_reset_network_header(skb);
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);
/*
* Push down and install the IPIP header.
*/
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
iph->protocol = IPPROTO_GRE;
iph->tos = ipgre_ecn_encapsulate(tos, old_iph, skb);
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
if ((iph->ttl = tiph->ttl) == 0) {
if (skb->protocol == htons(ETH_P_IP))
iph->ttl = old_iph->ttl;
#if IS_ENABLED(CONFIG_IPV6)
else if (skb->protocol == htons(ETH_P_IPV6))
iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit;
#endif
else
iph->ttl = ip4_dst_hoplimit(&rt->dst);
}
((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags;
((__be16 *)(iph + 1))[1] = (dev->type == ARPHRD_ETHER) ?
htons(ETH_P_TEB) : skb->protocol;
if (tunnel->parms.o_flags&(GRE_KEY|GRE_CSUM|GRE_SEQ)) {
__be32 *ptr = (__be32 *)(((u8 *)iph) + tunnel->hlen - 4);
if (tunnel->parms.o_flags&GRE_SEQ) {
++tunnel->o_seqno;
*ptr = htonl(tunnel->o_seqno);
ptr--;
}
if (tunnel->parms.o_flags&GRE_KEY) {
*ptr = tunnel->parms.o_key;
ptr--;
}
if (tunnel->parms.o_flags&GRE_CSUM) {
*ptr = 0;
*(__sum16 *)ptr = ip_compute_csum((void *)(iph+1), skb->len - sizeof(struct iphdr));
}
}
nf_reset(skb);
tstats = this_cpu_ptr(dev->tstats);
__IPTUNNEL_XMIT(tstats, &dev->stats);
return NETDEV_TX_OK;
#if IS_ENABLED(CONFIG_IPV6)
tx_error_icmp:
dst_link_failure(skb);
#endif
tx_error:
dev->stats.tx_errors++;
dev_kfree_skb(skb);
return NETDEV_TX_OK;
}
static int ipgre_tunnel_bind_dev(struct net_device *dev)
{
struct net_device *tdev = NULL;
struct ip_tunnel *tunnel;
const struct iphdr *iph;
int hlen = LL_MAX_HEADER;
int mtu = ETH_DATA_LEN;
int addend = sizeof(struct iphdr) + 4;
tunnel = netdev_priv(dev);
iph = &tunnel->parms.iph;
/* Guess output device to choose reasonable mtu and needed_headroom */
if (iph->daddr) {
struct flowi4 fl4;
struct rtable *rt;
rt = ip_route_output_gre(dev_net(dev), &fl4,
iph->daddr, iph->saddr,
tunnel->parms.o_key,
RT_TOS(iph->tos),
tunnel->parms.link);
if (!IS_ERR(rt)) {
tdev = rt->dst.dev;
ip_rt_put(rt);
}
if (dev->type != ARPHRD_ETHER)
dev->flags |= IFF_POINTOPOINT;
}