forked from kernel-patches/bpf
-
Notifications
You must be signed in to change notification settings - Fork 0
/
geneve.c
2034 lines (1722 loc) · 51.8 KB
/
geneve.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-only
/*
* GENEVE: Generic Network Virtualization Encapsulation
*
* Copyright (c) 2015 Red Hat, Inc.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/ethtool.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/etherdevice.h>
#include <linux/hash.h>
#include <net/ipv6_stubs.h>
#include <net/dst_metadata.h>
#include <net/gro_cells.h>
#include <net/rtnetlink.h>
#include <net/geneve.h>
#include <net/gro.h>
#include <net/protocol.h>
#define GENEVE_NETDEV_VER "0.6"
#define GENEVE_N_VID (1u << 24)
#define GENEVE_VID_MASK (GENEVE_N_VID - 1)
#define VNI_HASH_BITS 10
#define VNI_HASH_SIZE (1<<VNI_HASH_BITS)
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");
#define GENEVE_VER 0
#define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr))
#define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN)
#define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN)
/* per-network namespace private data for this module */
struct geneve_net {
struct list_head geneve_list;
struct list_head sock_list;
};
static unsigned int geneve_net_id;
struct geneve_dev_node {
struct hlist_node hlist;
struct geneve_dev *geneve;
};
struct geneve_config {
struct ip_tunnel_info info;
bool collect_md;
bool use_udp6_rx_checksums;
bool ttl_inherit;
enum ifla_geneve_df df;
bool inner_proto_inherit;
};
/* Pseudo network device */
struct geneve_dev {
struct geneve_dev_node hlist4; /* vni hash table for IPv4 socket */
#if IS_ENABLED(CONFIG_IPV6)
struct geneve_dev_node hlist6; /* vni hash table for IPv6 socket */
#endif
struct net *net; /* netns for packet i/o */
struct net_device *dev; /* netdev for geneve tunnel */
struct geneve_sock __rcu *sock4; /* IPv4 socket used for geneve tunnel */
#if IS_ENABLED(CONFIG_IPV6)
struct geneve_sock __rcu *sock6; /* IPv6 socket used for geneve tunnel */
#endif
struct list_head next; /* geneve's per namespace list */
struct gro_cells gro_cells;
struct geneve_config cfg;
};
struct geneve_sock {
bool collect_md;
struct list_head list;
struct socket *sock;
struct rcu_head rcu;
int refcnt;
struct hlist_head vni_list[VNI_HASH_SIZE];
};
static inline __u32 geneve_net_vni_hash(u8 vni[3])
{
__u32 vnid;
vnid = (vni[0] << 16) | (vni[1] << 8) | vni[2];
return hash_32(vnid, VNI_HASH_BITS);
}
static __be64 vni_to_tunnel_id(const __u8 *vni)
{
#ifdef __BIG_ENDIAN
return (vni[0] << 16) | (vni[1] << 8) | vni[2];
#else
return (__force __be64)(((__force u64)vni[0] << 40) |
((__force u64)vni[1] << 48) |
((__force u64)vni[2] << 56));
#endif
}
/* Convert 64 bit tunnel ID to 24 bit VNI. */
static void tunnel_id_to_vni(__be64 tun_id, __u8 *vni)
{
#ifdef __BIG_ENDIAN
vni[0] = (__force __u8)(tun_id >> 16);
vni[1] = (__force __u8)(tun_id >> 8);
vni[2] = (__force __u8)tun_id;
#else
vni[0] = (__force __u8)((__force u64)tun_id >> 40);
vni[1] = (__force __u8)((__force u64)tun_id >> 48);
vni[2] = (__force __u8)((__force u64)tun_id >> 56);
#endif
}
static bool eq_tun_id_and_vni(u8 *tun_id, u8 *vni)
{
return !memcmp(vni, &tun_id[5], 3);
}
static sa_family_t geneve_get_sk_family(struct geneve_sock *gs)
{
return gs->sock->sk->sk_family;
}
static struct geneve_dev *geneve_lookup(struct geneve_sock *gs,
__be32 addr, u8 vni[])
{
struct hlist_head *vni_list_head;
struct geneve_dev_node *node;
__u32 hash;
/* Find the device for this VNI */
hash = geneve_net_vni_hash(vni);
vni_list_head = &gs->vni_list[hash];
hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) &&
addr == node->geneve->cfg.info.key.u.ipv4.dst)
return node->geneve;
}
return NULL;
}
#if IS_ENABLED(CONFIG_IPV6)
static struct geneve_dev *geneve6_lookup(struct geneve_sock *gs,
struct in6_addr addr6, u8 vni[])
{
struct hlist_head *vni_list_head;
struct geneve_dev_node *node;
__u32 hash;
/* Find the device for this VNI */
hash = geneve_net_vni_hash(vni);
vni_list_head = &gs->vni_list[hash];
hlist_for_each_entry_rcu(node, vni_list_head, hlist) {
if (eq_tun_id_and_vni((u8 *)&node->geneve->cfg.info.key.tun_id, vni) &&
ipv6_addr_equal(&addr6, &node->geneve->cfg.info.key.u.ipv6.dst))
return node->geneve;
}
return NULL;
}
#endif
static inline struct genevehdr *geneve_hdr(const struct sk_buff *skb)
{
return (struct genevehdr *)(udp_hdr(skb) + 1);
}
static struct geneve_dev *geneve_lookup_skb(struct geneve_sock *gs,
struct sk_buff *skb)
{
static u8 zero_vni[3];
u8 *vni;
if (geneve_get_sk_family(gs) == AF_INET) {
struct iphdr *iph;
__be32 addr;
iph = ip_hdr(skb); /* outer IP header... */
if (gs->collect_md) {
vni = zero_vni;
addr = 0;
} else {
vni = geneve_hdr(skb)->vni;
addr = iph->saddr;
}
return geneve_lookup(gs, addr, vni);
#if IS_ENABLED(CONFIG_IPV6)
} else if (geneve_get_sk_family(gs) == AF_INET6) {
static struct in6_addr zero_addr6;
struct ipv6hdr *ip6h;
struct in6_addr addr6;
ip6h = ipv6_hdr(skb); /* outer IPv6 header... */
if (gs->collect_md) {
vni = zero_vni;
addr6 = zero_addr6;
} else {
vni = geneve_hdr(skb)->vni;
addr6 = ip6h->saddr;
}
return geneve6_lookup(gs, addr6, vni);
#endif
}
return NULL;
}
/* geneve receive/decap routine */
static void geneve_rx(struct geneve_dev *geneve, struct geneve_sock *gs,
struct sk_buff *skb)
{
struct genevehdr *gnvh = geneve_hdr(skb);
struct metadata_dst *tun_dst = NULL;
unsigned int len;
int err = 0;
void *oiph;
if (ip_tunnel_collect_metadata() || gs->collect_md) {
__be16 flags;
flags = TUNNEL_KEY | (gnvh->oam ? TUNNEL_OAM : 0) |
(gnvh->critical ? TUNNEL_CRIT_OPT : 0);
tun_dst = udp_tun_rx_dst(skb, geneve_get_sk_family(gs), flags,
vni_to_tunnel_id(gnvh->vni),
gnvh->opt_len * 4);
if (!tun_dst) {
geneve->dev->stats.rx_dropped++;
goto drop;
}
/* Update tunnel dst according to Geneve options. */
ip_tunnel_info_opts_set(&tun_dst->u.tun_info,
gnvh->options, gnvh->opt_len * 4,
TUNNEL_GENEVE_OPT);
} else {
/* Drop packets w/ critical options,
* since we don't support any...
*/
if (gnvh->critical) {
geneve->dev->stats.rx_frame_errors++;
geneve->dev->stats.rx_errors++;
goto drop;
}
}
if (tun_dst)
skb_dst_set(skb, &tun_dst->dst);
if (gnvh->proto_type == htons(ETH_P_TEB)) {
skb_reset_mac_header(skb);
skb->protocol = eth_type_trans(skb, geneve->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
/* Ignore packet loops (and multicast echo) */
if (ether_addr_equal(eth_hdr(skb)->h_source,
geneve->dev->dev_addr)) {
geneve->dev->stats.rx_errors++;
goto drop;
}
} else {
skb_reset_mac_header(skb);
skb->dev = geneve->dev;
skb->pkt_type = PACKET_HOST;
}
oiph = skb_network_header(skb);
skb_reset_network_header(skb);
if (geneve_get_sk_family(gs) == AF_INET)
err = IP_ECN_decapsulate(oiph, skb);
#if IS_ENABLED(CONFIG_IPV6)
else
err = IP6_ECN_decapsulate(oiph, skb);
#endif
if (unlikely(err)) {
if (log_ecn_error) {
if (geneve_get_sk_family(gs) == AF_INET)
net_info_ratelimited("non-ECT from %pI4 "
"with TOS=%#x\n",
&((struct iphdr *)oiph)->saddr,
((struct iphdr *)oiph)->tos);
#if IS_ENABLED(CONFIG_IPV6)
else
net_info_ratelimited("non-ECT from %pI6\n",
&((struct ipv6hdr *)oiph)->saddr);
#endif
}
if (err > 1) {
++geneve->dev->stats.rx_frame_errors;
++geneve->dev->stats.rx_errors;
goto drop;
}
}
len = skb->len;
err = gro_cells_receive(&geneve->gro_cells, skb);
if (likely(err == NET_RX_SUCCESS))
dev_sw_netstats_rx_add(geneve->dev, len);
return;
drop:
/* Consume bad packet */
kfree_skb(skb);
}
/* Setup stats when device is created */
static int geneve_init(struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
int err;
dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats);
if (!dev->tstats)
return -ENOMEM;
err = gro_cells_init(&geneve->gro_cells, dev);
if (err) {
free_percpu(dev->tstats);
return err;
}
err = dst_cache_init(&geneve->cfg.info.dst_cache, GFP_KERNEL);
if (err) {
free_percpu(dev->tstats);
gro_cells_destroy(&geneve->gro_cells);
return err;
}
return 0;
}
static void geneve_uninit(struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
dst_cache_destroy(&geneve->cfg.info.dst_cache);
gro_cells_destroy(&geneve->gro_cells);
free_percpu(dev->tstats);
}
/* Callback from net/ipv4/udp.c to receive packets */
static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
{
struct genevehdr *geneveh;
struct geneve_dev *geneve;
struct geneve_sock *gs;
__be16 inner_proto;
int opts_len;
/* Need UDP and Geneve header to be present */
if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN)))
goto drop;
/* Return packets with reserved bits set */
geneveh = geneve_hdr(skb);
if (unlikely(geneveh->ver != GENEVE_VER))
goto drop;
inner_proto = geneveh->proto_type;
if (unlikely((inner_proto != htons(ETH_P_TEB) &&
inner_proto != htons(ETH_P_IP) &&
inner_proto != htons(ETH_P_IPV6))))
goto drop;
gs = rcu_dereference_sk_user_data(sk);
if (!gs)
goto drop;
geneve = geneve_lookup_skb(gs, skb);
if (!geneve)
goto drop;
if (unlikely((!geneve->cfg.inner_proto_inherit &&
inner_proto != htons(ETH_P_TEB)))) {
geneve->dev->stats.rx_dropped++;
goto drop;
}
opts_len = geneveh->opt_len * 4;
if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, inner_proto,
!net_eq(geneve->net, dev_net(geneve->dev)))) {
geneve->dev->stats.rx_dropped++;
goto drop;
}
geneve_rx(geneve, gs, skb);
return 0;
drop:
/* Consume bad packet */
kfree_skb(skb);
return 0;
}
/* Callback from net/ipv{4,6}/udp.c to check that we have a tunnel for errors */
static int geneve_udp_encap_err_lookup(struct sock *sk, struct sk_buff *skb)
{
struct genevehdr *geneveh;
struct geneve_sock *gs;
u8 zero_vni[3] = { 0 };
u8 *vni = zero_vni;
if (!pskb_may_pull(skb, skb_transport_offset(skb) + GENEVE_BASE_HLEN))
return -EINVAL;
geneveh = geneve_hdr(skb);
if (geneveh->ver != GENEVE_VER)
return -EINVAL;
if (geneveh->proto_type != htons(ETH_P_TEB))
return -EINVAL;
gs = rcu_dereference_sk_user_data(sk);
if (!gs)
return -ENOENT;
if (geneve_get_sk_family(gs) == AF_INET) {
struct iphdr *iph = ip_hdr(skb);
__be32 addr4 = 0;
if (!gs->collect_md) {
vni = geneve_hdr(skb)->vni;
addr4 = iph->daddr;
}
return geneve_lookup(gs, addr4, vni) ? 0 : -ENOENT;
}
#if IS_ENABLED(CONFIG_IPV6)
if (geneve_get_sk_family(gs) == AF_INET6) {
struct ipv6hdr *ip6h = ipv6_hdr(skb);
struct in6_addr addr6;
memset(&addr6, 0, sizeof(struct in6_addr));
if (!gs->collect_md) {
vni = geneve_hdr(skb)->vni;
addr6 = ip6h->daddr;
}
return geneve6_lookup(gs, addr6, vni) ? 0 : -ENOENT;
}
#endif
return -EPFNOSUPPORT;
}
static struct socket *geneve_create_sock(struct net *net, bool ipv6,
__be16 port, bool ipv6_rx_csum)
{
struct socket *sock;
struct udp_port_cfg udp_conf;
int err;
memset(&udp_conf, 0, sizeof(udp_conf));
if (ipv6) {
udp_conf.family = AF_INET6;
udp_conf.ipv6_v6only = 1;
udp_conf.use_udp6_rx_checksums = ipv6_rx_csum;
} else {
udp_conf.family = AF_INET;
udp_conf.local_ip.s_addr = htonl(INADDR_ANY);
}
udp_conf.local_udp_port = port;
/* Open UDP socket */
err = udp_sock_create(net, &udp_conf, &sock);
if (err < 0)
return ERR_PTR(err);
udp_allow_gso(sock->sk);
return sock;
}
static int geneve_hlen(struct genevehdr *gh)
{
return sizeof(*gh) + gh->opt_len * 4;
}
static struct sk_buff *geneve_gro_receive(struct sock *sk,
struct list_head *head,
struct sk_buff *skb)
{
struct sk_buff *pp = NULL;
struct sk_buff *p;
struct genevehdr *gh, *gh2;
unsigned int hlen, gh_len, off_gnv;
const struct packet_offload *ptype;
__be16 type;
int flush = 1;
off_gnv = skb_gro_offset(skb);
hlen = off_gnv + sizeof(*gh);
gh = skb_gro_header(skb, hlen, off_gnv);
if (unlikely(!gh))
goto out;
if (gh->ver != GENEVE_VER || gh->oam)
goto out;
gh_len = geneve_hlen(gh);
hlen = off_gnv + gh_len;
if (skb_gro_header_hard(skb, hlen)) {
gh = skb_gro_header_slow(skb, hlen, off_gnv);
if (unlikely(!gh))
goto out;
}
list_for_each_entry(p, head, list) {
if (!NAPI_GRO_CB(p)->same_flow)
continue;
gh2 = (struct genevehdr *)(p->data + off_gnv);
if (gh->opt_len != gh2->opt_len ||
memcmp(gh, gh2, gh_len)) {
NAPI_GRO_CB(p)->same_flow = 0;
continue;
}
}
skb_gro_pull(skb, gh_len);
skb_gro_postpull_rcsum(skb, gh, gh_len);
type = gh->proto_type;
if (likely(type == htons(ETH_P_TEB)))
return call_gro_receive(eth_gro_receive, head, skb);
ptype = gro_find_receive_by_type(type);
if (!ptype)
goto out;
pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
flush = 0;
out:
skb_gro_flush_final(skb, pp, flush);
return pp;
}
static int geneve_gro_complete(struct sock *sk, struct sk_buff *skb,
int nhoff)
{
struct genevehdr *gh;
struct packet_offload *ptype;
__be16 type;
int gh_len;
int err = -ENOSYS;
gh = (struct genevehdr *)(skb->data + nhoff);
gh_len = geneve_hlen(gh);
type = gh->proto_type;
/* since skb->encapsulation is set, eth_gro_complete() sets the inner mac header */
if (likely(type == htons(ETH_P_TEB)))
return eth_gro_complete(skb, nhoff + gh_len);
ptype = gro_find_complete_by_type(type);
if (ptype)
err = ptype->callbacks.gro_complete(skb, nhoff + gh_len);
skb_set_inner_mac_header(skb, nhoff + gh_len);
return err;
}
/* Create new listen socket if needed */
static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port,
bool ipv6, bool ipv6_rx_csum)
{
struct geneve_net *gn = net_generic(net, geneve_net_id);
struct geneve_sock *gs;
struct socket *sock;
struct udp_tunnel_sock_cfg tunnel_cfg;
int h;
gs = kzalloc(sizeof(*gs), GFP_KERNEL);
if (!gs)
return ERR_PTR(-ENOMEM);
sock = geneve_create_sock(net, ipv6, port, ipv6_rx_csum);
if (IS_ERR(sock)) {
kfree(gs);
return ERR_CAST(sock);
}
gs->sock = sock;
gs->refcnt = 1;
for (h = 0; h < VNI_HASH_SIZE; ++h)
INIT_HLIST_HEAD(&gs->vni_list[h]);
/* Initialize the geneve udp offloads structure */
udp_tunnel_notify_add_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE);
/* Mark socket as an encapsulation socket */
memset(&tunnel_cfg, 0, sizeof(tunnel_cfg));
tunnel_cfg.sk_user_data = gs;
tunnel_cfg.encap_type = 1;
tunnel_cfg.gro_receive = geneve_gro_receive;
tunnel_cfg.gro_complete = geneve_gro_complete;
tunnel_cfg.encap_rcv = geneve_udp_encap_recv;
tunnel_cfg.encap_err_lookup = geneve_udp_encap_err_lookup;
tunnel_cfg.encap_destroy = NULL;
setup_udp_tunnel_sock(net, sock, &tunnel_cfg);
list_add(&gs->list, &gn->sock_list);
return gs;
}
static void __geneve_sock_release(struct geneve_sock *gs)
{
if (!gs || --gs->refcnt)
return;
list_del(&gs->list);
udp_tunnel_notify_del_rx_port(gs->sock, UDP_TUNNEL_TYPE_GENEVE);
udp_tunnel_sock_release(gs->sock);
kfree_rcu(gs, rcu);
}
static void geneve_sock_release(struct geneve_dev *geneve)
{
struct geneve_sock *gs4 = rtnl_dereference(geneve->sock4);
#if IS_ENABLED(CONFIG_IPV6)
struct geneve_sock *gs6 = rtnl_dereference(geneve->sock6);
rcu_assign_pointer(geneve->sock6, NULL);
#endif
rcu_assign_pointer(geneve->sock4, NULL);
synchronize_net();
__geneve_sock_release(gs4);
#if IS_ENABLED(CONFIG_IPV6)
__geneve_sock_release(gs6);
#endif
}
static struct geneve_sock *geneve_find_sock(struct geneve_net *gn,
sa_family_t family,
__be16 dst_port)
{
struct geneve_sock *gs;
list_for_each_entry(gs, &gn->sock_list, list) {
if (inet_sk(gs->sock->sk)->inet_sport == dst_port &&
geneve_get_sk_family(gs) == family) {
return gs;
}
}
return NULL;
}
static int geneve_sock_add(struct geneve_dev *geneve, bool ipv6)
{
struct net *net = geneve->net;
struct geneve_net *gn = net_generic(net, geneve_net_id);
struct geneve_dev_node *node;
struct geneve_sock *gs;
__u8 vni[3];
__u32 hash;
gs = geneve_find_sock(gn, ipv6 ? AF_INET6 : AF_INET, geneve->cfg.info.key.tp_dst);
if (gs) {
gs->refcnt++;
goto out;
}
gs = geneve_socket_create(net, geneve->cfg.info.key.tp_dst, ipv6,
geneve->cfg.use_udp6_rx_checksums);
if (IS_ERR(gs))
return PTR_ERR(gs);
out:
gs->collect_md = geneve->cfg.collect_md;
#if IS_ENABLED(CONFIG_IPV6)
if (ipv6) {
rcu_assign_pointer(geneve->sock6, gs);
node = &geneve->hlist6;
} else
#endif
{
rcu_assign_pointer(geneve->sock4, gs);
node = &geneve->hlist4;
}
node->geneve = geneve;
tunnel_id_to_vni(geneve->cfg.info.key.tun_id, vni);
hash = geneve_net_vni_hash(vni);
hlist_add_head_rcu(&node->hlist, &gs->vni_list[hash]);
return 0;
}
static int geneve_open(struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
bool metadata = geneve->cfg.collect_md;
bool ipv4, ipv6;
int ret = 0;
ipv6 = geneve->cfg.info.mode & IP_TUNNEL_INFO_IPV6 || metadata;
ipv4 = !ipv6 || metadata;
#if IS_ENABLED(CONFIG_IPV6)
if (ipv6) {
ret = geneve_sock_add(geneve, true);
if (ret < 0 && ret != -EAFNOSUPPORT)
ipv4 = false;
}
#endif
if (ipv4)
ret = geneve_sock_add(geneve, false);
if (ret < 0)
geneve_sock_release(geneve);
return ret;
}
static int geneve_stop(struct net_device *dev)
{
struct geneve_dev *geneve = netdev_priv(dev);
hlist_del_init_rcu(&geneve->hlist4.hlist);
#if IS_ENABLED(CONFIG_IPV6)
hlist_del_init_rcu(&geneve->hlist6.hlist);
#endif
geneve_sock_release(geneve);
return 0;
}
static void geneve_build_header(struct genevehdr *geneveh,
const struct ip_tunnel_info *info,
__be16 inner_proto)
{
geneveh->ver = GENEVE_VER;
geneveh->opt_len = info->options_len / 4;
geneveh->oam = !!(info->key.tun_flags & TUNNEL_OAM);
geneveh->critical = !!(info->key.tun_flags & TUNNEL_CRIT_OPT);
geneveh->rsvd1 = 0;
tunnel_id_to_vni(info->key.tun_id, geneveh->vni);
geneveh->proto_type = inner_proto;
geneveh->rsvd2 = 0;
if (info->key.tun_flags & TUNNEL_GENEVE_OPT)
ip_tunnel_info_opts_get(geneveh->options, info);
}
static int geneve_build_skb(struct dst_entry *dst, struct sk_buff *skb,
const struct ip_tunnel_info *info,
bool xnet, int ip_hdr_len,
bool inner_proto_inherit)
{
bool udp_sum = !!(info->key.tun_flags & TUNNEL_CSUM);
struct genevehdr *gnvh;
__be16 inner_proto;
int min_headroom;
int err;
skb_reset_mac_header(skb);
skb_scrub_packet(skb, xnet);
min_headroom = LL_RESERVED_SPACE(dst->dev) + dst->header_len +
GENEVE_BASE_HLEN + info->options_len + ip_hdr_len;
err = skb_cow_head(skb, min_headroom);
if (unlikely(err))
goto free_dst;
err = udp_tunnel_handle_offloads(skb, udp_sum);
if (err)
goto free_dst;
gnvh = __skb_push(skb, sizeof(*gnvh) + info->options_len);
inner_proto = inner_proto_inherit ? skb->protocol : htons(ETH_P_TEB);
geneve_build_header(gnvh, info, inner_proto);
skb_set_inner_protocol(skb, inner_proto);
return 0;
free_dst:
dst_release(dst);
return err;
}
static struct rtable *geneve_get_v4_rt(struct sk_buff *skb,
struct net_device *dev,
struct geneve_sock *gs4,
struct flowi4 *fl4,
const struct ip_tunnel_info *info,
__be16 dport, __be16 sport,
__u8 *full_tos)
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
struct dst_cache *dst_cache;
struct rtable *rt = NULL;
__u8 tos;
if (!gs4)
return ERR_PTR(-EIO);
memset(fl4, 0, sizeof(*fl4));
fl4->flowi4_mark = skb->mark;
fl4->flowi4_proto = IPPROTO_UDP;
fl4->daddr = info->key.u.ipv4.dst;
fl4->saddr = info->key.u.ipv4.src;
fl4->fl4_dport = dport;
fl4->fl4_sport = sport;
fl4->flowi4_flags = info->key.flow_flags;
tos = info->key.tos;
if ((tos == 1) && !geneve->cfg.collect_md) {
tos = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
use_cache = false;
}
fl4->flowi4_tos = RT_TOS(tos);
if (full_tos)
*full_tos = tos;
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
rt = dst_cache_get_ip4(dst_cache, &fl4->saddr);
if (rt)
return rt;
}
rt = ip_route_output_key(geneve->net, fl4);
if (IS_ERR(rt)) {
netdev_dbg(dev, "no route to %pI4\n", &fl4->daddr);
return ERR_PTR(-ENETUNREACH);
}
if (rt->dst.dev == dev) { /* is this necessary? */
netdev_dbg(dev, "circular route to %pI4\n", &fl4->daddr);
ip_rt_put(rt);
return ERR_PTR(-ELOOP);
}
if (use_cache)
dst_cache_set_ip4(dst_cache, &rt->dst, fl4->saddr);
return rt;
}
#if IS_ENABLED(CONFIG_IPV6)
static struct dst_entry *geneve_get_v6_dst(struct sk_buff *skb,
struct net_device *dev,
struct geneve_sock *gs6,
struct flowi6 *fl6,
const struct ip_tunnel_info *info,
__be16 dport, __be16 sport)
{
bool use_cache = ip_tunnel_dst_cache_usable(skb, info);
struct geneve_dev *geneve = netdev_priv(dev);
struct dst_entry *dst = NULL;
struct dst_cache *dst_cache;
__u8 prio;
if (!gs6)
return ERR_PTR(-EIO);
memset(fl6, 0, sizeof(*fl6));
fl6->flowi6_mark = skb->mark;
fl6->flowi6_proto = IPPROTO_UDP;
fl6->daddr = info->key.u.ipv6.dst;
fl6->saddr = info->key.u.ipv6.src;
fl6->fl6_dport = dport;
fl6->fl6_sport = sport;
prio = info->key.tos;
if ((prio == 1) && !geneve->cfg.collect_md) {
prio = ip_tunnel_get_dsfield(ip_hdr(skb), skb);
use_cache = false;
}
fl6->flowlabel = ip6_make_flowinfo(prio, info->key.label);
dst_cache = (struct dst_cache *)&info->dst_cache;
if (use_cache) {
dst = dst_cache_get_ip6(dst_cache, &fl6->saddr);
if (dst)
return dst;
}
dst = ipv6_stub->ipv6_dst_lookup_flow(geneve->net, gs6->sock->sk, fl6,
NULL);
if (IS_ERR(dst)) {
netdev_dbg(dev, "no route to %pI6\n", &fl6->daddr);
return ERR_PTR(-ENETUNREACH);
}
if (dst->dev == dev) { /* is this necessary? */
netdev_dbg(dev, "circular route to %pI6\n", &fl6->daddr);
dst_release(dst);
return ERR_PTR(-ELOOP);
}
if (use_cache)
dst_cache_set_ip6(dst_cache, dst, &fl6->saddr);
return dst;
}
#endif
static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev,
struct geneve_dev *geneve,
const struct ip_tunnel_info *info)
{
bool xnet = !net_eq(geneve->net, dev_net(geneve->dev));
struct geneve_sock *gs4 = rcu_dereference(geneve->sock4);
const struct ip_tunnel_key *key = &info->key;
struct rtable *rt;
struct flowi4 fl4;
__u8 full_tos;
__u8 tos, ttl;
__be16 df = 0;
__be16 sport;
int err;
if (!pskb_inet_may_pull(skb))
return -EINVAL;
sport = udp_flow_src_port(geneve->net, skb, 1, USHRT_MAX, true);
rt = geneve_get_v4_rt(skb, dev, gs4, &fl4, info,
geneve->cfg.info.key.tp_dst, sport, &full_tos);
if (IS_ERR(rt))
return PTR_ERR(rt);
err = skb_tunnel_check_pmtu(skb, &rt->dst,
GENEVE_IPV4_HLEN + info->options_len,
netif_is_any_bridge_port(dev));
if (err < 0) {
dst_release(&rt->dst);
return err;
} else if (err) {
struct ip_tunnel_info *info;
info = skb_tunnel_info(skb);
if (info) {
struct ip_tunnel_info *unclone;
unclone = skb_tunnel_info_unclone(skb);
if (unlikely(!unclone)) {
dst_release(&rt->dst);
return -ENOMEM;
}
unclone->key.u.ipv4.dst = fl4.saddr;
unclone->key.u.ipv4.src = fl4.daddr;
}
if (!pskb_may_pull(skb, ETH_HLEN)) {
dst_release(&rt->dst);
return -EINVAL;
}
skb->protocol = eth_type_trans(skb, geneve->dev);
__netif_rx(skb);
dst_release(&rt->dst);
return -EMSGSIZE;
}
if (geneve->cfg.collect_md) {
tos = ip_tunnel_ecn_encap(key->tos, ip_hdr(skb), skb);
ttl = key->ttl;
df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0;
} else {
tos = ip_tunnel_ecn_encap(full_tos, ip_hdr(skb), skb);
if (geneve->cfg.ttl_inherit)
ttl = ip_tunnel_get_ttl(ip_hdr(skb), skb);
else
ttl = key->ttl;
ttl = ttl ? : ip4_dst_hoplimit(&rt->dst);
if (geneve->cfg.df == GENEVE_DF_SET) {
df = htons(IP_DF);
} else if (geneve->cfg.df == GENEVE_DF_INHERIT) {
struct ethhdr *eth = eth_hdr(skb);
if (ntohs(eth->h_proto) == ETH_P_IPV6) {
df = htons(IP_DF);
} else if (ntohs(eth->h_proto) == ETH_P_IP) {
struct iphdr *iph = ip_hdr(skb);
if (iph->frag_off & htons(IP_DF))
df = htons(IP_DF);
}
}
}
err = geneve_build_skb(&rt->dst, skb, info, xnet, sizeof(struct iphdr),
geneve->cfg.inner_proto_inherit);
if (unlikely(err))
return err;
udp_tunnel_xmit_skb(rt, gs4->sock->sk, skb, fl4.saddr, fl4.daddr,
tos, ttl, df, sport, geneve->cfg.info.key.tp_dst,
!net_eq(geneve->net, dev_net(geneve->dev)),
!(info->key.tun_flags & TUNNEL_CSUM));
return 0;