forked from torvalds/linux
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathseg6_local.c
2310 lines (1837 loc) · 55.5 KB
/
seg6_local.c
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
// SPDX-License-Identifier: GPL-2.0-or-later
/*
* SR-IPv6 implementation
*
* Authors:
* David Lebrun <[email protected]>
* eBPF support: Mathieu Xhonneux <[email protected]>
*/
#include <linux/filter.h>
#include <linux/types.h>
#include <linux/skbuff.h>
#include <linux/net.h>
#include <linux/module.h>
#include <net/ip.h>
#include <net/lwtunnel.h>
#include <net/netevent.h>
#include <net/netns/generic.h>
#include <net/ip6_fib.h>
#include <net/route.h>
#include <net/seg6.h>
#include <linux/seg6.h>
#include <linux/seg6_local.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/dst_cache.h>
#include <net/ip_tunnels.h>
#ifdef CONFIG_IPV6_SEG6_HMAC
#include <net/seg6_hmac.h>
#endif
#include <net/seg6_local.h>
#include <linux/etherdevice.h>
#include <linux/bpf.h>
#include <linux/netfilter.h>
#define SEG6_F_ATTR(i) BIT(i)
struct seg6_local_lwt;
/* callbacks used for customizing the creation and destruction of a behavior */
struct seg6_local_lwtunnel_ops {
int (*build_state)(struct seg6_local_lwt *slwt, const void *cfg,
struct netlink_ext_ack *extack);
void (*destroy_state)(struct seg6_local_lwt *slwt);
};
struct seg6_action_desc {
int action;
unsigned long attrs;
/* The optattrs field is used for specifying all the optional
* attributes supported by a specific behavior.
* It means that if one of these attributes is not provided in the
* netlink message during the behavior creation, no errors will be
* returned to the userspace.
*
* Each attribute can be only of two types (mutually exclusive):
* 1) required or 2) optional.
* Every user MUST obey to this rule! If you set an attribute as
* required the same attribute CANNOT be set as optional and vice
* versa.
*/
unsigned long optattrs;
int (*input)(struct sk_buff *skb, struct seg6_local_lwt *slwt);
int static_headroom;
struct seg6_local_lwtunnel_ops slwt_ops;
};
struct bpf_lwt_prog {
struct bpf_prog *prog;
char *name;
};
/* default length values (expressed in bits) for both Locator-Block and
* Locator-Node Function.
*
* Both SEG6_LOCAL_LCBLOCK_DBITS and SEG6_LOCAL_LCNODE_FN_DBITS *must* be:
* i) greater than 0;
* ii) evenly divisible by 8. In other terms, the lengths of the
* Locator-Block and Locator-Node Function must be byte-aligned (we can
* relax this constraint in the future if really needed).
*
* Moreover, a third condition must hold:
* iii) SEG6_LOCAL_LCBLOCK_DBITS + SEG6_LOCAL_LCNODE_FN_DBITS <= 128.
*
* The correctness of SEG6_LOCAL_LCBLOCK_DBITS and SEG6_LOCAL_LCNODE_FN_DBITS
* values are checked during the kernel compilation. If the compilation stops,
* check the value of these parameters to see if they meet conditions (i), (ii)
* and (iii).
*/
#define SEG6_LOCAL_LCBLOCK_DBITS 32
#define SEG6_LOCAL_LCNODE_FN_DBITS 16
/* The following next_csid_chk_{cntr,lcblock,lcblock_fn}_bits macros can be
* used directly to check whether the lengths (in bits) of Locator-Block and
* Locator-Node Function are valid according to (i), (ii), (iii).
*/
#define next_csid_chk_cntr_bits(blen, flen) \
((blen) + (flen) > 128)
#define next_csid_chk_lcblock_bits(blen) \
({ \
typeof(blen) __tmp = blen; \
(!__tmp || __tmp > 120 || (__tmp & 0x07)); \
})
#define next_csid_chk_lcnode_fn_bits(flen) \
next_csid_chk_lcblock_bits(flen)
/* Supported Flavor operations are reported in this bitmask */
#define SEG6_LOCAL_FLV_SUPP_OPS (BIT(SEG6_LOCAL_FLV_OP_NEXT_CSID))
struct seg6_flavors_info {
/* Flavor operations */
__u32 flv_ops;
/* Locator-Block length, expressed in bits */
__u8 lcblock_bits;
/* Locator-Node Function length, expressed in bits*/
__u8 lcnode_func_bits;
};
enum seg6_end_dt_mode {
DT_INVALID_MODE = -EINVAL,
DT_LEGACY_MODE = 0,
DT_VRF_MODE = 1,
};
struct seg6_end_dt_info {
enum seg6_end_dt_mode mode;
struct net *net;
/* VRF device associated to the routing table used by the SRv6
* End.DT4/DT6 behavior for routing IPv4/IPv6 packets.
*/
int vrf_ifindex;
int vrf_table;
/* tunneled packet family (IPv4 or IPv6).
* Protocol and header length are inferred from family.
*/
u16 family;
};
struct pcpu_seg6_local_counters {
u64_stats_t packets;
u64_stats_t bytes;
u64_stats_t errors;
struct u64_stats_sync syncp;
};
/* This struct groups all the SRv6 Behavior counters supported so far.
*
* put_nla_counters() makes use of this data structure to collect all counter
* values after the per-CPU counter evaluation has been performed.
* Finally, each counter value (in seg6_local_counters) is stored in the
* corresponding netlink attribute and sent to user space.
*
* NB: we don't want to expose this structure to user space!
*/
struct seg6_local_counters {
__u64 packets;
__u64 bytes;
__u64 errors;
};
#define seg6_local_alloc_pcpu_counters(__gfp) \
__netdev_alloc_pcpu_stats(struct pcpu_seg6_local_counters, \
((__gfp) | __GFP_ZERO))
#define SEG6_F_LOCAL_COUNTERS SEG6_F_ATTR(SEG6_LOCAL_COUNTERS)
struct seg6_local_lwt {
int action;
struct ipv6_sr_hdr *srh;
int table;
struct in_addr nh4;
struct in6_addr nh6;
int iif;
int oif;
struct bpf_lwt_prog bpf;
#ifdef CONFIG_NET_L3_MASTER_DEV
struct seg6_end_dt_info dt_info;
#endif
struct seg6_flavors_info flv_info;
struct pcpu_seg6_local_counters __percpu *pcpu_counters;
int headroom;
struct seg6_action_desc *desc;
/* unlike the required attrs, we have to track the optional attributes
* that have been effectively parsed.
*/
unsigned long parsed_optattrs;
};
static struct seg6_local_lwt *seg6_local_lwtunnel(struct lwtunnel_state *lwt)
{
return (struct seg6_local_lwt *)lwt->data;
}
static struct ipv6_sr_hdr *get_and_validate_srh(struct sk_buff *skb)
{
struct ipv6_sr_hdr *srh;
srh = seg6_get_srh(skb, IP6_FH_F_SKIP_RH);
if (!srh)
return NULL;
#ifdef CONFIG_IPV6_SEG6_HMAC
if (!seg6_hmac_validate_skb(skb))
return NULL;
#endif
return srh;
}
static bool decap_and_validate(struct sk_buff *skb, int proto)
{
struct ipv6_sr_hdr *srh;
unsigned int off = 0;
srh = seg6_get_srh(skb, 0);
if (srh && srh->segments_left > 0)
return false;
#ifdef CONFIG_IPV6_SEG6_HMAC
if (srh && !seg6_hmac_validate_skb(skb))
return false;
#endif
if (ipv6_find_hdr(skb, &off, proto, NULL, NULL) < 0)
return false;
if (!pskb_pull(skb, off))
return false;
skb_postpull_rcsum(skb, skb_network_header(skb), off);
skb_reset_network_header(skb);
skb_reset_transport_header(skb);
if (iptunnel_pull_offloads(skb))
return false;
return true;
}
static void advance_nextseg(struct ipv6_sr_hdr *srh, struct in6_addr *daddr)
{
struct in6_addr *addr;
srh->segments_left--;
addr = srh->segments + srh->segments_left;
*daddr = *addr;
}
static int
seg6_lookup_any_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
u32 tbl_id, bool local_delivery)
{
struct net *net = dev_net(skb->dev);
struct ipv6hdr *hdr = ipv6_hdr(skb);
int flags = RT6_LOOKUP_F_HAS_SADDR;
struct dst_entry *dst = NULL;
struct rt6_info *rt;
struct flowi6 fl6;
int dev_flags = 0;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_iif = skb->dev->ifindex;
fl6.daddr = nhaddr ? *nhaddr : hdr->daddr;
fl6.saddr = hdr->saddr;
fl6.flowlabel = ip6_flowinfo(hdr);
fl6.flowi6_mark = skb->mark;
fl6.flowi6_proto = hdr->nexthdr;
if (nhaddr)
fl6.flowi6_flags = FLOWI_FLAG_KNOWN_NH;
if (!tbl_id) {
dst = ip6_route_input_lookup(net, skb->dev, &fl6, skb, flags);
} else {
struct fib6_table *table;
table = fib6_get_table(net, tbl_id);
if (!table)
goto out;
rt = ip6_pol_route(net, table, 0, &fl6, skb, flags);
dst = &rt->dst;
}
/* we want to discard traffic destined for local packet processing,
* if @local_delivery is set to false.
*/
if (!local_delivery)
dev_flags |= IFF_LOOPBACK;
if (dst && (dst->dev->flags & dev_flags) && !dst->error) {
dst_release(dst);
dst = NULL;
}
out:
if (!dst) {
rt = net->ipv6.ip6_blk_hole_entry;
dst = &rt->dst;
dst_hold(dst);
}
skb_dst_drop(skb);
skb_dst_set(skb, dst);
return dst->error;
}
int seg6_lookup_nexthop(struct sk_buff *skb,
struct in6_addr *nhaddr, u32 tbl_id)
{
return seg6_lookup_any_nexthop(skb, nhaddr, tbl_id, false);
}
static __u8 seg6_flv_lcblock_octects(const struct seg6_flavors_info *finfo)
{
return finfo->lcblock_bits >> 3;
}
static __u8 seg6_flv_lcnode_func_octects(const struct seg6_flavors_info *finfo)
{
return finfo->lcnode_func_bits >> 3;
}
static bool seg6_next_csid_is_arg_zero(const struct in6_addr *addr,
const struct seg6_flavors_info *finfo)
{
__u8 fnc_octects = seg6_flv_lcnode_func_octects(finfo);
__u8 blk_octects = seg6_flv_lcblock_octects(finfo);
__u8 arg_octects;
int i;
arg_octects = 16 - blk_octects - fnc_octects;
for (i = 0; i < arg_octects; ++i) {
if (addr->s6_addr[blk_octects + fnc_octects + i] != 0x00)
return false;
}
return true;
}
/* assume that DA.Argument length > 0 */
static void seg6_next_csid_advance_arg(struct in6_addr *addr,
const struct seg6_flavors_info *finfo)
{
__u8 fnc_octects = seg6_flv_lcnode_func_octects(finfo);
__u8 blk_octects = seg6_flv_lcblock_octects(finfo);
/* advance DA.Argument */
memmove(&addr->s6_addr[blk_octects],
&addr->s6_addr[blk_octects + fnc_octects],
16 - blk_octects - fnc_octects);
memset(&addr->s6_addr[16 - fnc_octects], 0x00, fnc_octects);
}
static int input_action_end_core(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int end_next_csid_core(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
const struct seg6_flavors_info *finfo = &slwt->flv_info;
struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
if (seg6_next_csid_is_arg_zero(daddr, finfo))
return input_action_end_core(skb, slwt);
/* update DA */
seg6_next_csid_advance_arg(daddr, finfo);
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
}
static bool seg6_next_csid_enabled(__u32 fops)
{
return fops & BIT(SEG6_LOCAL_FLV_OP_NEXT_CSID);
}
/* regular endpoint function */
static int input_action_end(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
const struct seg6_flavors_info *finfo = &slwt->flv_info;
if (seg6_next_csid_enabled(finfo->flv_ops))
return end_next_csid_core(skb, slwt);
return input_action_end_core(skb, slwt);
}
/* regular endpoint, and forward to specified nexthop */
static int input_action_end_x(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
seg6_lookup_nexthop(skb, &slwt->nh6, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int input_action_end_t(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
seg6_lookup_nexthop(skb, NULL, slwt->table);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
/* decapsulate and forward inner L2 frame on specified interface */
static int input_action_end_dx2(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct net *net = dev_net(skb->dev);
struct net_device *odev;
struct ethhdr *eth;
if (!decap_and_validate(skb, IPPROTO_ETHERNET))
goto drop;
if (!pskb_may_pull(skb, ETH_HLEN))
goto drop;
skb_reset_mac_header(skb);
eth = (struct ethhdr *)skb->data;
/* To determine the frame's protocol, we assume it is 802.3. This avoids
* a call to eth_type_trans(), which is not really relevant for our
* use case.
*/
if (!eth_proto_is_802_3(eth->h_proto))
goto drop;
odev = dev_get_by_index_rcu(net, slwt->oif);
if (!odev)
goto drop;
/* As we accept Ethernet frames, make sure the egress device is of
* the correct type.
*/
if (odev->type != ARPHRD_ETHER)
goto drop;
if (!(odev->flags & IFF_UP) || !netif_carrier_ok(odev))
goto drop;
skb_orphan(skb);
if (skb_warn_if_lro(skb))
goto drop;
skb_forward_csum(skb);
if (skb->len - ETH_HLEN > odev->mtu)
goto drop;
skb->dev = odev;
skb->protocol = eth->h_proto;
return dev_queue_xmit(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int input_action_end_dx6_finish(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
struct in6_addr *nhaddr = NULL;
struct seg6_local_lwt *slwt;
slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
/* The inner packet is not associated to any local interface,
* so we do not call netif_rx().
*
* If slwt->nh6 is set to ::, then lookup the nexthop for the
* inner packet's DA. Otherwise, use the specified nexthop.
*/
if (!ipv6_addr_any(&slwt->nh6))
nhaddr = &slwt->nh6;
seg6_lookup_nexthop(skb, nhaddr, 0);
return dst_input(skb);
}
/* decapsulate and forward to specified nexthop */
static int input_action_end_dx6(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
/* this function accepts IPv6 encapsulated packets, with either
* an SRH with SL=0, or no SRH.
*/
if (!decap_and_validate(skb, IPPROTO_IPV6))
goto drop;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
nf_reset_ct(skb);
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV6, NF_INET_PRE_ROUTING,
dev_net(skb->dev), NULL, skb, NULL,
skb_dst(skb)->dev, input_action_end_dx6_finish);
return input_action_end_dx6_finish(dev_net(skb->dev), NULL, skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int input_action_end_dx4_finish(struct net *net, struct sock *sk,
struct sk_buff *skb)
{
struct dst_entry *orig_dst = skb_dst(skb);
struct seg6_local_lwt *slwt;
struct iphdr *iph;
__be32 nhaddr;
int err;
slwt = seg6_local_lwtunnel(orig_dst->lwtstate);
iph = ip_hdr(skb);
nhaddr = slwt->nh4.s_addr ?: iph->daddr;
skb_dst_drop(skb);
err = ip_route_input(skb, nhaddr, iph->saddr, 0, skb->dev);
if (err) {
kfree_skb(skb);
return -EINVAL;
}
return dst_input(skb);
}
static int input_action_end_dx4(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
if (!decap_and_validate(skb, IPPROTO_IPIP))
goto drop;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto drop;
skb->protocol = htons(ETH_P_IP);
skb_set_transport_header(skb, sizeof(struct iphdr));
nf_reset_ct(skb);
if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING,
dev_net(skb->dev), NULL, skb, NULL,
skb_dst(skb)->dev, input_action_end_dx4_finish);
return input_action_end_dx4_finish(dev_net(skb->dev), NULL, skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
#ifdef CONFIG_NET_L3_MASTER_DEV
static struct net *fib6_config_get_net(const struct fib6_config *fib6_cfg)
{
const struct nl_info *nli = &fib6_cfg->fc_nlinfo;
return nli->nl_net;
}
static int __seg6_end_dt_vrf_build(struct seg6_local_lwt *slwt, const void *cfg,
u16 family, struct netlink_ext_ack *extack)
{
struct seg6_end_dt_info *info = &slwt->dt_info;
int vrf_ifindex;
struct net *net;
net = fib6_config_get_net(cfg);
/* note that vrf_table was already set by parse_nla_vrftable() */
vrf_ifindex = l3mdev_ifindex_lookup_by_table_id(L3MDEV_TYPE_VRF, net,
info->vrf_table);
if (vrf_ifindex < 0) {
if (vrf_ifindex == -EPERM) {
NL_SET_ERR_MSG(extack,
"Strict mode for VRF is disabled");
} else if (vrf_ifindex == -ENODEV) {
NL_SET_ERR_MSG(extack,
"Table has no associated VRF device");
} else {
pr_debug("seg6local: SRv6 End.DT* creation error=%d\n",
vrf_ifindex);
}
return vrf_ifindex;
}
info->net = net;
info->vrf_ifindex = vrf_ifindex;
info->family = family;
info->mode = DT_VRF_MODE;
return 0;
}
/* The SRv6 End.DT4/DT6 behavior extracts the inner (IPv4/IPv6) packet and
* routes the IPv4/IPv6 packet by looking at the configured routing table.
*
* In the SRv6 End.DT4/DT6 use case, we can receive traffic (IPv6+Segment
* Routing Header packets) from several interfaces and the outer IPv6
* destination address (DA) is used for retrieving the specific instance of the
* End.DT4/DT6 behavior that should process the packets.
*
* However, the inner IPv4/IPv6 packet is not really bound to any receiving
* interface and thus the End.DT4/DT6 sets the VRF (associated with the
* corresponding routing table) as the *receiving* interface.
* In other words, the End.DT4/DT6 processes a packet as if it has been received
* directly by the VRF (and not by one of its slave devices, if any).
* In this way, the VRF interface is used for routing the IPv4/IPv6 packet in
* according to the routing table configured by the End.DT4/DT6 instance.
*
* This design allows you to get some interesting features like:
* 1) the statistics on rx packets;
* 2) the possibility to install a packet sniffer on the receiving interface
* (the VRF one) for looking at the incoming packets;
* 3) the possibility to leverage the netfilter prerouting hook for the inner
* IPv4 packet.
*
* This function returns:
* - the sk_buff* when the VRF rcv handler has processed the packet correctly;
* - NULL when the skb is consumed by the VRF rcv handler;
* - a pointer which encodes a negative error number in case of error.
* Note that in this case, the function takes care of freeing the skb.
*/
static struct sk_buff *end_dt_vrf_rcv(struct sk_buff *skb, u16 family,
struct net_device *dev)
{
/* based on l3mdev_ip_rcv; we are only interested in the master */
if (unlikely(!netif_is_l3_master(dev) && !netif_has_l3_rx_handler(dev)))
goto drop;
if (unlikely(!dev->l3mdev_ops->l3mdev_l3_rcv))
goto drop;
/* the decap packet IPv4/IPv6 does not come with any mac header info.
* We must unset the mac header to allow the VRF device to rebuild it,
* just in case there is a sniffer attached on the device.
*/
skb_unset_mac_header(skb);
skb = dev->l3mdev_ops->l3mdev_l3_rcv(dev, skb, family);
if (!skb)
/* the skb buffer was consumed by the handler */
return NULL;
/* when a packet is received by a VRF or by one of its slaves, the
* master device reference is set into the skb.
*/
if (unlikely(skb->dev != dev || skb->skb_iif != dev->ifindex))
goto drop;
return skb;
drop:
kfree_skb(skb);
return ERR_PTR(-EINVAL);
}
static struct net_device *end_dt_get_vrf_rcu(struct sk_buff *skb,
struct seg6_end_dt_info *info)
{
int vrf_ifindex = info->vrf_ifindex;
struct net *net = info->net;
if (unlikely(vrf_ifindex < 0))
goto error;
if (unlikely(!net_eq(dev_net(skb->dev), net)))
goto error;
return dev_get_by_index_rcu(net, vrf_ifindex);
error:
return NULL;
}
static struct sk_buff *end_dt_vrf_core(struct sk_buff *skb,
struct seg6_local_lwt *slwt, u16 family)
{
struct seg6_end_dt_info *info = &slwt->dt_info;
struct net_device *vrf;
__be16 protocol;
int hdrlen;
vrf = end_dt_get_vrf_rcu(skb, info);
if (unlikely(!vrf))
goto drop;
switch (family) {
case AF_INET:
protocol = htons(ETH_P_IP);
hdrlen = sizeof(struct iphdr);
break;
case AF_INET6:
protocol = htons(ETH_P_IPV6);
hdrlen = sizeof(struct ipv6hdr);
break;
case AF_UNSPEC:
fallthrough;
default:
goto drop;
}
if (unlikely(info->family != AF_UNSPEC && info->family != family)) {
pr_warn_once("seg6local: SRv6 End.DT* family mismatch");
goto drop;
}
skb->protocol = protocol;
skb_dst_drop(skb);
skb_set_transport_header(skb, hdrlen);
nf_reset_ct(skb);
return end_dt_vrf_rcv(skb, family, vrf);
drop:
kfree_skb(skb);
return ERR_PTR(-EINVAL);
}
static int input_action_end_dt4(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct iphdr *iph;
int err;
if (!decap_and_validate(skb, IPPROTO_IPIP))
goto drop;
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto drop;
skb = end_dt_vrf_core(skb, slwt, AF_INET);
if (!skb)
/* packet has been processed and consumed by the VRF */
return 0;
if (IS_ERR(skb))
return PTR_ERR(skb);
iph = ip_hdr(skb);
err = ip_route_input(skb, iph->daddr, iph->saddr, 0, skb->dev);
if (unlikely(err))
goto drop;
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
static int seg6_end_dt4_build(struct seg6_local_lwt *slwt, const void *cfg,
struct netlink_ext_ack *extack)
{
return __seg6_end_dt_vrf_build(slwt, cfg, AF_INET, extack);
}
static enum
seg6_end_dt_mode seg6_end_dt6_parse_mode(struct seg6_local_lwt *slwt)
{
unsigned long parsed_optattrs = slwt->parsed_optattrs;
bool legacy, vrfmode;
legacy = !!(parsed_optattrs & SEG6_F_ATTR(SEG6_LOCAL_TABLE));
vrfmode = !!(parsed_optattrs & SEG6_F_ATTR(SEG6_LOCAL_VRFTABLE));
if (!(legacy ^ vrfmode))
/* both are absent or present: invalid DT6 mode */
return DT_INVALID_MODE;
return legacy ? DT_LEGACY_MODE : DT_VRF_MODE;
}
static enum seg6_end_dt_mode seg6_end_dt6_get_mode(struct seg6_local_lwt *slwt)
{
struct seg6_end_dt_info *info = &slwt->dt_info;
return info->mode;
}
static int seg6_end_dt6_build(struct seg6_local_lwt *slwt, const void *cfg,
struct netlink_ext_ack *extack)
{
enum seg6_end_dt_mode mode = seg6_end_dt6_parse_mode(slwt);
struct seg6_end_dt_info *info = &slwt->dt_info;
switch (mode) {
case DT_LEGACY_MODE:
info->mode = DT_LEGACY_MODE;
return 0;
case DT_VRF_MODE:
return __seg6_end_dt_vrf_build(slwt, cfg, AF_INET6, extack);
default:
NL_SET_ERR_MSG(extack, "table or vrftable must be specified");
return -EINVAL;
}
}
#endif
static int input_action_end_dt6(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
if (!decap_and_validate(skb, IPPROTO_IPV6))
goto drop;
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
#ifdef CONFIG_NET_L3_MASTER_DEV
if (seg6_end_dt6_get_mode(slwt) == DT_LEGACY_MODE)
goto legacy_mode;
/* DT6_VRF_MODE */
skb = end_dt_vrf_core(skb, slwt, AF_INET6);
if (!skb)
/* packet has been processed and consumed by the VRF */
return 0;
if (IS_ERR(skb))
return PTR_ERR(skb);
/* note: this time we do not need to specify the table because the VRF
* takes care of selecting the correct table.
*/
seg6_lookup_any_nexthop(skb, NULL, 0, true);
return dst_input(skb);
legacy_mode:
#endif
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_any_nexthop(skb, NULL, slwt->table, true);
return dst_input(skb);
drop:
kfree_skb(skb);
return -EINVAL;
}
#ifdef CONFIG_NET_L3_MASTER_DEV
static int seg6_end_dt46_build(struct seg6_local_lwt *slwt, const void *cfg,
struct netlink_ext_ack *extack)
{
return __seg6_end_dt_vrf_build(slwt, cfg, AF_UNSPEC, extack);
}
static int input_action_end_dt46(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
unsigned int off = 0;
int nexthdr;
nexthdr = ipv6_find_hdr(skb, &off, -1, NULL, NULL);
if (unlikely(nexthdr < 0))
goto drop;
switch (nexthdr) {
case IPPROTO_IPIP:
return input_action_end_dt4(skb, slwt);
case IPPROTO_IPV6:
return input_action_end_dt6(skb, slwt);
}
drop:
kfree_skb(skb);
return -EINVAL;
}
#endif
/* push an SRH on top of the current one */
static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
int err = -EINVAL;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
err = seg6_do_srh_inline(skb, slwt->srh);
if (err)
goto drop;
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return err;
}
/* encapsulate within an outer IPv6 header and a specified SRH */
static int input_action_end_b6_encap(struct sk_buff *skb,
struct seg6_local_lwt *slwt)
{
struct ipv6_sr_hdr *srh;
int err = -EINVAL;
srh = get_and_validate_srh(skb);
if (!srh)
goto drop;
advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
skb_reset_inner_headers(skb);
skb->encapsulation = 1;
err = seg6_do_srh_encap(skb, slwt->srh, IPPROTO_IPV6);
if (err)
goto drop;
skb_set_transport_header(skb, sizeof(struct ipv6hdr));
seg6_lookup_nexthop(skb, NULL, 0);
return dst_input(skb);
drop:
kfree_skb(skb);
return err;
}
DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
bool seg6_bpf_has_valid_srh(struct sk_buff *skb)
{
struct seg6_bpf_srh_state *srh_state =