1 // SPDX-License-Identifier: GPL-2.0-or-later
2 /*
3 * SR-IPv6 implementation
4 *
5 * Author:
6 * David Lebrun <david.lebrun@uclouvain.be>
7 */
8
9 #include <linux/types.h>
10 #include <linux/skbuff.h>
11 #include <linux/net.h>
12 #include <linux/module.h>
13 #include <net/ip.h>
14 #include <net/ip_tunnels.h>
15 #include <net/lwtunnel.h>
16 #include <net/netevent.h>
17 #include <net/netns/generic.h>
18 #include <net/ip6_fib.h>
19 #include <net/route.h>
20 #include <net/seg6.h>
21 #include <linux/seg6.h>
22 #include <linux/seg6_iptunnel.h>
23 #include <net/addrconf.h>
24 #include <net/ip6_route.h>
25 #include <net/dst_cache.h>
26 #ifdef CONFIG_IPV6_SEG6_HMAC
27 #include <net/seg6_hmac.h>
28 #endif
29 #include <linux/netfilter.h>
30
seg6_lwt_headroom(struct seg6_iptunnel_encap * tuninfo)31 static size_t seg6_lwt_headroom(struct seg6_iptunnel_encap *tuninfo)
32 {
33 int head = 0;
34
35 switch (tuninfo->mode) {
36 case SEG6_IPTUN_MODE_INLINE:
37 break;
38 case SEG6_IPTUN_MODE_ENCAP:
39 case SEG6_IPTUN_MODE_ENCAP_RED:
40 head = sizeof(struct ipv6hdr);
41 break;
42 case SEG6_IPTUN_MODE_L2ENCAP:
43 case SEG6_IPTUN_MODE_L2ENCAP_RED:
44 return 0;
45 }
46
47 return ((tuninfo->srh->hdrlen + 1) << 3) + head;
48 }
49
50 struct seg6_lwt {
51 struct dst_cache cache;
52 struct seg6_iptunnel_encap tuninfo[];
53 };
54
seg6_lwt_lwtunnel(struct lwtunnel_state * lwt)55 static inline struct seg6_lwt *seg6_lwt_lwtunnel(struct lwtunnel_state *lwt)
56 {
57 return (struct seg6_lwt *)lwt->data;
58 }
59
60 static inline struct seg6_iptunnel_encap *
seg6_encap_lwtunnel(struct lwtunnel_state * lwt)61 seg6_encap_lwtunnel(struct lwtunnel_state *lwt)
62 {
63 return seg6_lwt_lwtunnel(lwt)->tuninfo;
64 }
65
66 static const struct nla_policy seg6_iptunnel_policy[SEG6_IPTUNNEL_MAX + 1] = {
67 [SEG6_IPTUNNEL_SRH] = { .type = NLA_BINARY },
68 };
69
nla_put_srh(struct sk_buff * skb,int attrtype,struct seg6_iptunnel_encap * tuninfo)70 static int nla_put_srh(struct sk_buff *skb, int attrtype,
71 struct seg6_iptunnel_encap *tuninfo)
72 {
73 struct seg6_iptunnel_encap *data;
74 struct nlattr *nla;
75 int len;
76
77 len = SEG6_IPTUN_ENCAP_SIZE(tuninfo);
78
79 nla = nla_reserve(skb, attrtype, len);
80 if (!nla)
81 return -EMSGSIZE;
82
83 data = nla_data(nla);
84 memcpy(data, tuninfo, len);
85
86 return 0;
87 }
88
set_tun_src(struct net * net,struct net_device * dev,struct in6_addr * daddr,struct in6_addr * saddr)89 static void set_tun_src(struct net *net, struct net_device *dev,
90 struct in6_addr *daddr, struct in6_addr *saddr)
91 {
92 struct seg6_pernet_data *sdata = seg6_pernet(net);
93 struct in6_addr *tun_src;
94
95 rcu_read_lock();
96
97 tun_src = rcu_dereference(sdata->tun_src);
98
99 if (!ipv6_addr_any(tun_src)) {
100 memcpy(saddr, tun_src, sizeof(struct in6_addr));
101 } else {
102 ipv6_dev_get_saddr(net, dev, daddr, IPV6_PREFER_SRC_PUBLIC,
103 saddr);
104 }
105
106 rcu_read_unlock();
107 }
108
109 /* Compute flowlabel for outer IPv6 header */
seg6_make_flowlabel(struct net * net,struct sk_buff * skb,struct ipv6hdr * inner_hdr)110 static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb,
111 struct ipv6hdr *inner_hdr)
112 {
113 int do_flowlabel = net->ipv6.sysctl.seg6_flowlabel;
114 __be32 flowlabel = 0;
115 u32 hash;
116
117 if (do_flowlabel > 0) {
118 hash = skb_get_hash(skb);
119 hash = rol32(hash, 16);
120 flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
121 } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) {
122 flowlabel = ip6_flowlabel(inner_hdr);
123 }
124 return flowlabel;
125 }
126
127 /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */
seg6_do_srh_encap(struct sk_buff * skb,struct ipv6_sr_hdr * osrh,int proto)128 int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto)
129 {
130 struct dst_entry *dst = skb_dst(skb);
131 struct net *net = dev_net(dst->dev);
132 struct ipv6hdr *hdr, *inner_hdr;
133 struct ipv6_sr_hdr *isrh;
134 int hdrlen, tot_len, err;
135 __be32 flowlabel;
136
137 hdrlen = (osrh->hdrlen + 1) << 3;
138 tot_len = hdrlen + sizeof(*hdr);
139
140 err = skb_cow_head(skb, tot_len + skb->mac_len);
141 if (unlikely(err))
142 return err;
143
144 inner_hdr = ipv6_hdr(skb);
145 flowlabel = seg6_make_flowlabel(net, skb, inner_hdr);
146
147 skb_push(skb, tot_len);
148 skb_reset_network_header(skb);
149 skb_mac_header_rebuild(skb);
150 hdr = ipv6_hdr(skb);
151
152 /* inherit tc, flowlabel and hlim
153 * hlim will be decremented in ip6_forward() afterwards and
154 * decapsulation will overwrite inner hlim with outer hlim
155 */
156
157 if (skb->protocol == htons(ETH_P_IPV6)) {
158 ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)),
159 flowlabel);
160 hdr->hop_limit = inner_hdr->hop_limit;
161 } else {
162 ip6_flow_hdr(hdr, 0, flowlabel);
163 hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
164
165 memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
166
167 /* the control block has been erased, so we have to set the
168 * iif once again.
169 * We read the receiving interface index directly from the
170 * skb->skb_iif as it is done in the IPv4 receiving path (i.e.:
171 * ip_rcv_core(...)).
172 */
173 IP6CB(skb)->iif = skb->skb_iif;
174 }
175
176 hdr->nexthdr = NEXTHDR_ROUTING;
177
178 isrh = (void *)hdr + sizeof(*hdr);
179 memcpy(isrh, osrh, hdrlen);
180
181 isrh->nexthdr = proto;
182
183 hdr->daddr = isrh->segments[isrh->first_segment];
184 set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
185
186 #ifdef CONFIG_IPV6_SEG6_HMAC
187 if (sr_has_hmac(isrh)) {
188 err = seg6_push_hmac(net, &hdr->saddr, isrh);
189 if (unlikely(err))
190 return err;
191 }
192 #endif
193
194 hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
195
196 skb_postpush_rcsum(skb, hdr, tot_len);
197
198 return 0;
199 }
200 EXPORT_SYMBOL_GPL(seg6_do_srh_encap);
201
202 /* encapsulate an IPv6 packet within an outer IPv6 header with reduced SRH */
seg6_do_srh_encap_red(struct sk_buff * skb,struct ipv6_sr_hdr * osrh,int proto)203 static int seg6_do_srh_encap_red(struct sk_buff *skb,
204 struct ipv6_sr_hdr *osrh, int proto)
205 {
206 __u8 first_seg = osrh->first_segment;
207 struct dst_entry *dst = skb_dst(skb);
208 struct net *net = dev_net(dst->dev);
209 struct ipv6hdr *hdr, *inner_hdr;
210 int hdrlen = ipv6_optlen(osrh);
211 int red_tlv_offset, tlv_offset;
212 struct ipv6_sr_hdr *isrh;
213 bool skip_srh = false;
214 __be32 flowlabel;
215 int tot_len, err;
216 int red_hdrlen;
217 int tlvs_len;
218
219 if (first_seg > 0) {
220 red_hdrlen = hdrlen - sizeof(struct in6_addr);
221 } else {
222 /* NOTE: if tag/flags and/or other TLVs are introduced in the
223 * seg6_iptunnel infrastructure, they should be considered when
224 * deciding to skip the SRH.
225 */
226 skip_srh = !sr_has_hmac(osrh);
227
228 red_hdrlen = skip_srh ? 0 : hdrlen;
229 }
230
231 tot_len = red_hdrlen + sizeof(struct ipv6hdr);
232
233 err = skb_cow_head(skb, tot_len + skb->mac_len);
234 if (unlikely(err))
235 return err;
236
237 inner_hdr = ipv6_hdr(skb);
238 flowlabel = seg6_make_flowlabel(net, skb, inner_hdr);
239
240 skb_push(skb, tot_len);
241 skb_reset_network_header(skb);
242 skb_mac_header_rebuild(skb);
243 hdr = ipv6_hdr(skb);
244
245 /* based on seg6_do_srh_encap() */
246 if (skb->protocol == htons(ETH_P_IPV6)) {
247 ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)),
248 flowlabel);
249 hdr->hop_limit = inner_hdr->hop_limit;
250 } else {
251 ip6_flow_hdr(hdr, 0, flowlabel);
252 hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb));
253
254 memset(IP6CB(skb), 0, sizeof(*IP6CB(skb)));
255 IP6CB(skb)->iif = skb->skb_iif;
256 }
257
258 /* no matter if we have to skip the SRH or not, the first segment
259 * always comes in the pushed IPv6 header.
260 */
261 hdr->daddr = osrh->segments[first_seg];
262
263 if (skip_srh) {
264 hdr->nexthdr = proto;
265
266 set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
267 goto out;
268 }
269
270 /* we cannot skip the SRH, slow path */
271
272 hdr->nexthdr = NEXTHDR_ROUTING;
273 isrh = (void *)hdr + sizeof(struct ipv6hdr);
274
275 if (unlikely(!first_seg)) {
276 /* this is a very rare case; we have only one SID but
277 * we cannot skip the SRH since we are carrying some
278 * other info.
279 */
280 memcpy(isrh, osrh, hdrlen);
281 goto srcaddr;
282 }
283
284 tlv_offset = sizeof(*osrh) + (first_seg + 1) * sizeof(struct in6_addr);
285 red_tlv_offset = tlv_offset - sizeof(struct in6_addr);
286
287 memcpy(isrh, osrh, red_tlv_offset);
288
289 tlvs_len = hdrlen - tlv_offset;
290 if (unlikely(tlvs_len > 0)) {
291 const void *s = (const void *)osrh + tlv_offset;
292 void *d = (void *)isrh + red_tlv_offset;
293
294 memcpy(d, s, tlvs_len);
295 }
296
297 --isrh->first_segment;
298 isrh->hdrlen -= 2;
299
300 srcaddr:
301 isrh->nexthdr = proto;
302 set_tun_src(net, dst->dev, &hdr->daddr, &hdr->saddr);
303
304 #ifdef CONFIG_IPV6_SEG6_HMAC
305 if (unlikely(!skip_srh && sr_has_hmac(isrh))) {
306 err = seg6_push_hmac(net, &hdr->saddr, isrh);
307 if (unlikely(err))
308 return err;
309 }
310 #endif
311
312 out:
313 hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
314
315 skb_postpush_rcsum(skb, hdr, tot_len);
316
317 return 0;
318 }
319
320 /* insert an SRH within an IPv6 packet, just after the IPv6 header */
seg6_do_srh_inline(struct sk_buff * skb,struct ipv6_sr_hdr * osrh)321 int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh)
322 {
323 struct ipv6hdr *hdr, *oldhdr;
324 struct ipv6_sr_hdr *isrh;
325 int hdrlen, err;
326
327 hdrlen = (osrh->hdrlen + 1) << 3;
328
329 err = skb_cow_head(skb, hdrlen + skb->mac_len);
330 if (unlikely(err))
331 return err;
332
333 oldhdr = ipv6_hdr(skb);
334
335 skb_pull(skb, sizeof(struct ipv6hdr));
336 skb_postpull_rcsum(skb, skb_network_header(skb),
337 sizeof(struct ipv6hdr));
338
339 skb_push(skb, sizeof(struct ipv6hdr) + hdrlen);
340 skb_reset_network_header(skb);
341 skb_mac_header_rebuild(skb);
342
343 hdr = ipv6_hdr(skb);
344
345 memmove(hdr, oldhdr, sizeof(*hdr));
346
347 isrh = (void *)hdr + sizeof(*hdr);
348 memcpy(isrh, osrh, hdrlen);
349
350 isrh->nexthdr = hdr->nexthdr;
351 hdr->nexthdr = NEXTHDR_ROUTING;
352
353 isrh->segments[0] = hdr->daddr;
354 hdr->daddr = isrh->segments[isrh->first_segment];
355
356 #ifdef CONFIG_IPV6_SEG6_HMAC
357 if (sr_has_hmac(isrh)) {
358 struct net *net = dev_net(skb_dst(skb)->dev);
359
360 err = seg6_push_hmac(net, &hdr->saddr, isrh);
361 if (unlikely(err))
362 return err;
363 }
364 #endif
365
366 hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr));
367
368 skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen);
369
370 return 0;
371 }
372 EXPORT_SYMBOL_GPL(seg6_do_srh_inline);
373
seg6_do_srh(struct sk_buff * skb)374 static int seg6_do_srh(struct sk_buff *skb)
375 {
376 struct dst_entry *dst = skb_dst(skb);
377 struct seg6_iptunnel_encap *tinfo;
378 int proto, err = 0;
379
380 tinfo = seg6_encap_lwtunnel(dst->lwtstate);
381
382 switch (tinfo->mode) {
383 case SEG6_IPTUN_MODE_INLINE:
384 if (skb->protocol != htons(ETH_P_IPV6))
385 return -EINVAL;
386
387 err = seg6_do_srh_inline(skb, tinfo->srh);
388 if (err)
389 return err;
390 break;
391 case SEG6_IPTUN_MODE_ENCAP:
392 case SEG6_IPTUN_MODE_ENCAP_RED:
393 err = iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6);
394 if (err)
395 return err;
396
397 if (skb->protocol == htons(ETH_P_IPV6))
398 proto = IPPROTO_IPV6;
399 else if (skb->protocol == htons(ETH_P_IP))
400 proto = IPPROTO_IPIP;
401 else
402 return -EINVAL;
403
404 if (tinfo->mode == SEG6_IPTUN_MODE_ENCAP)
405 err = seg6_do_srh_encap(skb, tinfo->srh, proto);
406 else
407 err = seg6_do_srh_encap_red(skb, tinfo->srh, proto);
408
409 if (err)
410 return err;
411
412 skb_set_inner_transport_header(skb, skb_transport_offset(skb));
413 skb_set_inner_protocol(skb, skb->protocol);
414 skb->protocol = htons(ETH_P_IPV6);
415 break;
416 case SEG6_IPTUN_MODE_L2ENCAP:
417 case SEG6_IPTUN_MODE_L2ENCAP_RED:
418 if (!skb_mac_header_was_set(skb))
419 return -EINVAL;
420
421 if (pskb_expand_head(skb, skb->mac_len, 0, GFP_ATOMIC) < 0)
422 return -ENOMEM;
423
424 skb_mac_header_rebuild(skb);
425 skb_push(skb, skb->mac_len);
426
427 if (tinfo->mode == SEG6_IPTUN_MODE_L2ENCAP)
428 err = seg6_do_srh_encap(skb, tinfo->srh,
429 IPPROTO_ETHERNET);
430 else
431 err = seg6_do_srh_encap_red(skb, tinfo->srh,
432 IPPROTO_ETHERNET);
433
434 if (err)
435 return err;
436
437 skb->protocol = htons(ETH_P_IPV6);
438 break;
439 }
440
441 skb_set_transport_header(skb, sizeof(struct ipv6hdr));
442 nf_reset_ct(skb);
443
444 return 0;
445 }
446
seg6_input_finish(struct net * net,struct sock * sk,struct sk_buff * skb)447 static int seg6_input_finish(struct net *net, struct sock *sk,
448 struct sk_buff *skb)
449 {
450 return dst_input(skb);
451 }
452
seg6_input_core(struct net * net,struct sock * sk,struct sk_buff * skb)453 static int seg6_input_core(struct net *net, struct sock *sk,
454 struct sk_buff *skb)
455 {
456 struct dst_entry *orig_dst = skb_dst(skb);
457 struct dst_entry *dst = NULL;
458 struct seg6_lwt *slwt;
459 int err;
460
461 err = seg6_do_srh(skb);
462 if (unlikely(err)) {
463 kfree_skb(skb);
464 return err;
465 }
466
467 slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
468
469 preempt_disable();
470 dst = dst_cache_get(&slwt->cache);
471 preempt_enable();
472
473 skb_dst_drop(skb);
474
475 if (!dst) {
476 ip6_route_input(skb);
477 dst = skb_dst(skb);
478 if (!dst->error) {
479 preempt_disable();
480 dst_cache_set_ip6(&slwt->cache, dst,
481 &ipv6_hdr(skb)->saddr);
482 preempt_enable();
483 }
484 } else {
485 skb_dst_set(skb, dst);
486 }
487
488 err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
489 if (unlikely(err))
490 return err;
491
492 if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
493 return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
494 dev_net(skb->dev), NULL, skb, NULL,
495 skb_dst(skb)->dev, seg6_input_finish);
496
497 return seg6_input_finish(dev_net(skb->dev), NULL, skb);
498 }
499
seg6_input_nf(struct sk_buff * skb)500 static int seg6_input_nf(struct sk_buff *skb)
501 {
502 struct net_device *dev = skb_dst(skb)->dev;
503 struct net *net = dev_net(skb->dev);
504
505 switch (skb->protocol) {
506 case htons(ETH_P_IP):
507 return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, NULL,
508 skb, NULL, dev, seg6_input_core);
509 case htons(ETH_P_IPV6):
510 return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, NULL,
511 skb, NULL, dev, seg6_input_core);
512 }
513
514 return -EINVAL;
515 }
516
seg6_input(struct sk_buff * skb)517 static int seg6_input(struct sk_buff *skb)
518 {
519 if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
520 return seg6_input_nf(skb);
521
522 return seg6_input_core(dev_net(skb->dev), NULL, skb);
523 }
524
seg6_output_core(struct net * net,struct sock * sk,struct sk_buff * skb)525 static int seg6_output_core(struct net *net, struct sock *sk,
526 struct sk_buff *skb)
527 {
528 struct dst_entry *orig_dst = skb_dst(skb);
529 struct dst_entry *dst = NULL;
530 struct seg6_lwt *slwt;
531 int err;
532
533 err = seg6_do_srh(skb);
534 if (unlikely(err))
535 goto drop;
536
537 slwt = seg6_lwt_lwtunnel(orig_dst->lwtstate);
538
539 preempt_disable();
540 dst = dst_cache_get(&slwt->cache);
541 preempt_enable();
542
543 if (unlikely(!dst)) {
544 struct ipv6hdr *hdr = ipv6_hdr(skb);
545 struct flowi6 fl6;
546
547 memset(&fl6, 0, sizeof(fl6));
548 fl6.daddr = hdr->daddr;
549 fl6.saddr = hdr->saddr;
550 fl6.flowlabel = ip6_flowinfo(hdr);
551 fl6.flowi6_mark = skb->mark;
552 fl6.flowi6_proto = hdr->nexthdr;
553
554 dst = ip6_route_output(net, NULL, &fl6);
555 if (dst->error) {
556 err = dst->error;
557 dst_release(dst);
558 goto drop;
559 }
560
561 preempt_disable();
562 dst_cache_set_ip6(&slwt->cache, dst, &fl6.saddr);
563 preempt_enable();
564 }
565
566 skb_dst_drop(skb);
567 skb_dst_set(skb, dst);
568
569 err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
570 if (unlikely(err))
571 goto drop;
572
573 if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
574 return NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb,
575 NULL, skb_dst(skb)->dev, dst_output);
576
577 return dst_output(net, sk, skb);
578 drop:
579 kfree_skb(skb);
580 return err;
581 }
582
seg6_output_nf(struct net * net,struct sock * sk,struct sk_buff * skb)583 static int seg6_output_nf(struct net *net, struct sock *sk, struct sk_buff *skb)
584 {
585 struct net_device *dev = skb_dst(skb)->dev;
586
587 switch (skb->protocol) {
588 case htons(ETH_P_IP):
589 return NF_HOOK(NFPROTO_IPV4, NF_INET_POST_ROUTING, net, sk, skb,
590 NULL, dev, seg6_output_core);
591 case htons(ETH_P_IPV6):
592 return NF_HOOK(NFPROTO_IPV6, NF_INET_POST_ROUTING, net, sk, skb,
593 NULL, dev, seg6_output_core);
594 }
595
596 return -EINVAL;
597 }
598
seg6_output(struct net * net,struct sock * sk,struct sk_buff * skb)599 static int seg6_output(struct net *net, struct sock *sk, struct sk_buff *skb)
600 {
601 if (static_branch_unlikely(&nf_hooks_lwtunnel_enabled))
602 return seg6_output_nf(net, sk, skb);
603
604 return seg6_output_core(net, sk, skb);
605 }
606
seg6_build_state(struct net * net,struct nlattr * nla,unsigned int family,const void * cfg,struct lwtunnel_state ** ts,struct netlink_ext_ack * extack)607 static int seg6_build_state(struct net *net, struct nlattr *nla,
608 unsigned int family, const void *cfg,
609 struct lwtunnel_state **ts,
610 struct netlink_ext_ack *extack)
611 {
612 struct nlattr *tb[SEG6_IPTUNNEL_MAX + 1];
613 struct seg6_iptunnel_encap *tuninfo;
614 struct lwtunnel_state *newts;
615 int tuninfo_len, min_size;
616 struct seg6_lwt *slwt;
617 int err;
618
619 if (family != AF_INET && family != AF_INET6)
620 return -EINVAL;
621
622 err = nla_parse_nested_deprecated(tb, SEG6_IPTUNNEL_MAX, nla,
623 seg6_iptunnel_policy, extack);
624
625 if (err < 0)
626 return err;
627
628 if (!tb[SEG6_IPTUNNEL_SRH])
629 return -EINVAL;
630
631 tuninfo = nla_data(tb[SEG6_IPTUNNEL_SRH]);
632 tuninfo_len = nla_len(tb[SEG6_IPTUNNEL_SRH]);
633
634 /* tuninfo must contain at least the iptunnel encap structure,
635 * the SRH and one segment
636 */
637 min_size = sizeof(*tuninfo) + sizeof(struct ipv6_sr_hdr) +
638 sizeof(struct in6_addr);
639 if (tuninfo_len < min_size)
640 return -EINVAL;
641
642 switch (tuninfo->mode) {
643 case SEG6_IPTUN_MODE_INLINE:
644 if (family != AF_INET6)
645 return -EINVAL;
646
647 break;
648 case SEG6_IPTUN_MODE_ENCAP:
649 break;
650 case SEG6_IPTUN_MODE_L2ENCAP:
651 break;
652 case SEG6_IPTUN_MODE_ENCAP_RED:
653 break;
654 case SEG6_IPTUN_MODE_L2ENCAP_RED:
655 break;
656 default:
657 return -EINVAL;
658 }
659
660 /* verify that SRH is consistent */
661 if (!seg6_validate_srh(tuninfo->srh, tuninfo_len - sizeof(*tuninfo), false))
662 return -EINVAL;
663
664 newts = lwtunnel_state_alloc(tuninfo_len + sizeof(*slwt));
665 if (!newts)
666 return -ENOMEM;
667
668 slwt = seg6_lwt_lwtunnel(newts);
669
670 err = dst_cache_init(&slwt->cache, GFP_ATOMIC);
671 if (err) {
672 kfree(newts);
673 return err;
674 }
675
676 memcpy(&slwt->tuninfo, tuninfo, tuninfo_len);
677
678 newts->type = LWTUNNEL_ENCAP_SEG6;
679 newts->flags |= LWTUNNEL_STATE_INPUT_REDIRECT;
680
681 if (tuninfo->mode != SEG6_IPTUN_MODE_L2ENCAP)
682 newts->flags |= LWTUNNEL_STATE_OUTPUT_REDIRECT;
683
684 newts->headroom = seg6_lwt_headroom(tuninfo);
685
686 *ts = newts;
687
688 return 0;
689 }
690
seg6_destroy_state(struct lwtunnel_state * lwt)691 static void seg6_destroy_state(struct lwtunnel_state *lwt)
692 {
693 dst_cache_destroy(&seg6_lwt_lwtunnel(lwt)->cache);
694 }
695
seg6_fill_encap_info(struct sk_buff * skb,struct lwtunnel_state * lwtstate)696 static int seg6_fill_encap_info(struct sk_buff *skb,
697 struct lwtunnel_state *lwtstate)
698 {
699 struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
700
701 if (nla_put_srh(skb, SEG6_IPTUNNEL_SRH, tuninfo))
702 return -EMSGSIZE;
703
704 return 0;
705 }
706
seg6_encap_nlsize(struct lwtunnel_state * lwtstate)707 static int seg6_encap_nlsize(struct lwtunnel_state *lwtstate)
708 {
709 struct seg6_iptunnel_encap *tuninfo = seg6_encap_lwtunnel(lwtstate);
710
711 return nla_total_size(SEG6_IPTUN_ENCAP_SIZE(tuninfo));
712 }
713
seg6_encap_cmp(struct lwtunnel_state * a,struct lwtunnel_state * b)714 static int seg6_encap_cmp(struct lwtunnel_state *a, struct lwtunnel_state *b)
715 {
716 struct seg6_iptunnel_encap *a_hdr = seg6_encap_lwtunnel(a);
717 struct seg6_iptunnel_encap *b_hdr = seg6_encap_lwtunnel(b);
718 int len = SEG6_IPTUN_ENCAP_SIZE(a_hdr);
719
720 if (len != SEG6_IPTUN_ENCAP_SIZE(b_hdr))
721 return 1;
722
723 return memcmp(a_hdr, b_hdr, len);
724 }
725
726 static const struct lwtunnel_encap_ops seg6_iptun_ops = {
727 .build_state = seg6_build_state,
728 .destroy_state = seg6_destroy_state,
729 .output = seg6_output,
730 .input = seg6_input,
731 .fill_encap = seg6_fill_encap_info,
732 .get_encap_size = seg6_encap_nlsize,
733 .cmp_encap = seg6_encap_cmp,
734 .owner = THIS_MODULE,
735 };
736
seg6_iptunnel_init(void)737 int __init seg6_iptunnel_init(void)
738 {
739 return lwtunnel_encap_add_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
740 }
741
seg6_iptunnel_exit(void)742 void seg6_iptunnel_exit(void)
743 {
744 lwtunnel_encap_del_ops(&seg6_iptun_ops, LWTUNNEL_ENCAP_SEG6);
745 }
746