1 // SPDX-License-Identifier: GPL-2.0-or-later
2 /*
3 * Internet Control Message Protocol (ICMPv6)
4 * Linux INET6 implementation
5 *
6 * Authors:
7 * Pedro Roque <roque@di.fc.ul.pt>
8 *
9 * Based on net/ipv4/icmp.c
10 *
11 * RFC 1885
12 */
13
14 /*
15 * Changes:
16 *
17 * Andi Kleen : exception handling
18 * Andi Kleen add rate limits. never reply to a icmp.
19 * add more length checks and other fixes.
20 * yoshfuji : ensure to sent parameter problem for
21 * fragments.
22 * YOSHIFUJI Hideaki @USAGI: added sysctl for icmp rate limit.
23 * Randy Dunlap and
24 * YOSHIFUJI Hideaki @USAGI: Per-interface statistics support
25 * Kazunori MIYAZAWA @USAGI: change output process to use ip6_append_data
26 */
27
28 #define pr_fmt(fmt) "IPv6: " fmt
29
30 #include <linux/module.h>
31 #include <linux/errno.h>
32 #include <linux/types.h>
33 #include <linux/socket.h>
34 #include <linux/in.h>
35 #include <linux/kernel.h>
36 #include <linux/sockios.h>
37 #include <linux/net.h>
38 #include <linux/skbuff.h>
39 #include <linux/init.h>
40 #include <linux/netfilter.h>
41 #include <linux/slab.h>
42
43 #ifdef CONFIG_SYSCTL
44 #include <linux/sysctl.h>
45 #endif
46
47 #include <linux/inet.h>
48 #include <linux/netdevice.h>
49 #include <linux/icmpv6.h>
50
51 #include <net/ip.h>
52 #include <net/sock.h>
53
54 #include <net/ipv6.h>
55 #include <net/ip6_checksum.h>
56 #include <net/ping.h>
57 #include <net/protocol.h>
58 #include <net/raw.h>
59 #include <net/rawv6.h>
60 #include <net/seg6.h>
61 #include <net/transp_v6.h>
62 #include <net/ip6_route.h>
63 #include <net/addrconf.h>
64 #include <net/icmp.h>
65 #include <net/xfrm.h>
66 #include <net/inet_common.h>
67 #include <net/dsfield.h>
68 #include <net/l3mdev.h>
69
70 #include <linux/uaccess.h>
71
72 static DEFINE_PER_CPU(struct sock *, ipv6_icmp_sk);
73
icmpv6_err(struct sk_buff * skb,struct inet6_skb_parm * opt,u8 type,u8 code,int offset,__be32 info)74 static int icmpv6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
75 u8 type, u8 code, int offset, __be32 info)
76 {
77 /* icmpv6_notify checks 8 bytes can be pulled, icmp6hdr is 8 bytes */
78 struct icmp6hdr *icmp6 = (struct icmp6hdr *) (skb->data + offset);
79 struct net *net = dev_net(skb->dev);
80
81 if (type == ICMPV6_PKT_TOOBIG)
82 ip6_update_pmtu(skb, net, info, skb->dev->ifindex, 0, sock_net_uid(net, NULL));
83 else if (type == NDISC_REDIRECT)
84 ip6_redirect(skb, net, skb->dev->ifindex, 0,
85 sock_net_uid(net, NULL));
86
87 if (!(type & ICMPV6_INFOMSG_MASK))
88 if (icmp6->icmp6_type == ICMPV6_ECHO_REQUEST)
89 ping_err(skb, offset, ntohl(info));
90
91 return 0;
92 }
93
94 static int icmpv6_rcv(struct sk_buff *skb);
95
96 static const struct inet6_protocol icmpv6_protocol = {
97 .handler = icmpv6_rcv,
98 .err_handler = icmpv6_err,
99 .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL,
100 };
101
102 /* Called with BH disabled */
icmpv6_xmit_lock(struct net * net)103 static struct sock *icmpv6_xmit_lock(struct net *net)
104 {
105 struct sock *sk;
106
107 sk = this_cpu_read(ipv6_icmp_sk);
108 if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
109 /* This can happen if the output path (f.e. SIT or
110 * ip6ip6 tunnel) signals dst_link_failure() for an
111 * outgoing ICMP6 packet.
112 */
113 return NULL;
114 }
115 sock_net_set(sk, net);
116 return sk;
117 }
118
icmpv6_xmit_unlock(struct sock * sk)119 static void icmpv6_xmit_unlock(struct sock *sk)
120 {
121 sock_net_set(sk, &init_net);
122 spin_unlock(&sk->sk_lock.slock);
123 }
124
125 /*
126 * Figure out, may we reply to this packet with icmp error.
127 *
128 * We do not reply, if:
129 * - it was icmp error message.
130 * - it is truncated, so that it is known, that protocol is ICMPV6
131 * (i.e. in the middle of some exthdr)
132 *
133 * --ANK (980726)
134 */
135
is_ineligible(const struct sk_buff * skb)136 static bool is_ineligible(const struct sk_buff *skb)
137 {
138 int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
139 int len = skb->len - ptr;
140 __u8 nexthdr = ipv6_hdr(skb)->nexthdr;
141 __be16 frag_off;
142
143 if (len < 0)
144 return true;
145
146 ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr, &frag_off);
147 if (ptr < 0)
148 return false;
149 if (nexthdr == IPPROTO_ICMPV6) {
150 u8 _type, *tp;
151 tp = skb_header_pointer(skb,
152 ptr+offsetof(struct icmp6hdr, icmp6_type),
153 sizeof(_type), &_type);
154
155 /* Based on RFC 8200, Section 4.5 Fragment Header, return
156 * false if this is a fragment packet with no icmp header info.
157 */
158 if (!tp && frag_off != 0)
159 return false;
160 else if (!tp || !(*tp & ICMPV6_INFOMSG_MASK))
161 return true;
162 }
163 return false;
164 }
165
icmpv6_mask_allow(struct net * net,int type)166 static bool icmpv6_mask_allow(struct net *net, int type)
167 {
168 if (type > ICMPV6_MSG_MAX)
169 return true;
170
171 /* Limit if icmp type is set in ratemask. */
172 if (!test_bit(type, net->ipv6.sysctl.icmpv6_ratemask))
173 return true;
174
175 return false;
176 }
177
icmpv6_global_allow(struct net * net,int type)178 static bool icmpv6_global_allow(struct net *net, int type)
179 {
180 if (icmpv6_mask_allow(net, type))
181 return true;
182
183 if (icmp_global_allow())
184 return true;
185
186 __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
187 return false;
188 }
189
190 /*
191 * Check the ICMP output rate limit
192 */
icmpv6_xrlim_allow(struct sock * sk,u8 type,struct flowi6 * fl6)193 static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
194 struct flowi6 *fl6)
195 {
196 struct net *net = sock_net(sk);
197 struct dst_entry *dst;
198 bool res = false;
199
200 if (icmpv6_mask_allow(net, type))
201 return true;
202
203 /*
204 * Look up the output route.
205 * XXX: perhaps the expire for routing entries cloned by
206 * this lookup should be more aggressive (not longer than timeout).
207 */
208 dst = ip6_route_output(net, sk, fl6);
209 if (dst->error) {
210 IP6_INC_STATS(net, ip6_dst_idev(dst),
211 IPSTATS_MIB_OUTNOROUTES);
212 } else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
213 res = true;
214 } else {
215 struct rt6_info *rt = (struct rt6_info *)dst;
216 int tmo = net->ipv6.sysctl.icmpv6_time;
217 struct inet_peer *peer;
218
219 /* Give more bandwidth to wider prefixes. */
220 if (rt->rt6i_dst.plen < 128)
221 tmo >>= ((128 - rt->rt6i_dst.plen)>>5);
222
223 peer = inet_getpeer_v6(net->ipv6.peers, &fl6->daddr, 1);
224 res = inet_peer_xrlim_allow(peer, tmo);
225 if (peer)
226 inet_putpeer(peer);
227 }
228 if (!res)
229 __ICMP6_INC_STATS(net, ip6_dst_idev(dst),
230 ICMP6_MIB_RATELIMITHOST);
231 dst_release(dst);
232 return res;
233 }
234
icmpv6_rt_has_prefsrc(struct sock * sk,u8 type,struct flowi6 * fl6)235 static bool icmpv6_rt_has_prefsrc(struct sock *sk, u8 type,
236 struct flowi6 *fl6)
237 {
238 struct net *net = sock_net(sk);
239 struct dst_entry *dst;
240 bool res = false;
241
242 dst = ip6_route_output(net, sk, fl6);
243 if (!dst->error) {
244 struct rt6_info *rt = (struct rt6_info *)dst;
245 struct in6_addr prefsrc;
246
247 rt6_get_prefsrc(rt, &prefsrc);
248 res = !ipv6_addr_any(&prefsrc);
249 }
250 dst_release(dst);
251 return res;
252 }
253
254 /*
255 * an inline helper for the "simple" if statement below
256 * checks if parameter problem report is caused by an
257 * unrecognized IPv6 option that has the Option Type
258 * highest-order two bits set to 10
259 */
260
opt_unrec(struct sk_buff * skb,__u32 offset)261 static bool opt_unrec(struct sk_buff *skb, __u32 offset)
262 {
263 u8 _optval, *op;
264
265 offset += skb_network_offset(skb);
266 op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
267 if (!op)
268 return true;
269 return (*op & 0xC0) == 0x80;
270 }
271
icmpv6_push_pending_frames(struct sock * sk,struct flowi6 * fl6,struct icmp6hdr * thdr,int len)272 void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6,
273 struct icmp6hdr *thdr, int len)
274 {
275 struct sk_buff *skb;
276 struct icmp6hdr *icmp6h;
277
278 skb = skb_peek(&sk->sk_write_queue);
279 if (!skb)
280 return;
281
282 icmp6h = icmp6_hdr(skb);
283 memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
284 icmp6h->icmp6_cksum = 0;
285
286 if (skb_queue_len(&sk->sk_write_queue) == 1) {
287 skb->csum = csum_partial(icmp6h,
288 sizeof(struct icmp6hdr), skb->csum);
289 icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
290 &fl6->daddr,
291 len, fl6->flowi6_proto,
292 skb->csum);
293 } else {
294 __wsum tmp_csum = 0;
295
296 skb_queue_walk(&sk->sk_write_queue, skb) {
297 tmp_csum = csum_add(tmp_csum, skb->csum);
298 }
299
300 tmp_csum = csum_partial(icmp6h,
301 sizeof(struct icmp6hdr), tmp_csum);
302 icmp6h->icmp6_cksum = csum_ipv6_magic(&fl6->saddr,
303 &fl6->daddr,
304 len, fl6->flowi6_proto,
305 tmp_csum);
306 }
307 ip6_push_pending_frames(sk);
308 }
309
310 struct icmpv6_msg {
311 struct sk_buff *skb;
312 int offset;
313 uint8_t type;
314 };
315
icmpv6_getfrag(void * from,char * to,int offset,int len,int odd,struct sk_buff * skb)316 static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
317 {
318 struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
319 struct sk_buff *org_skb = msg->skb;
320 __wsum csum;
321
322 csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
323 to, len);
324 skb->csum = csum_block_add(skb->csum, csum, odd);
325 if (!(msg->type & ICMPV6_INFOMSG_MASK))
326 nf_ct_attach(skb, org_skb);
327 return 0;
328 }
329
330 #if IS_ENABLED(CONFIG_IPV6_MIP6)
mip6_addr_swap(struct sk_buff * skb,const struct inet6_skb_parm * opt)331 static void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt)
332 {
333 struct ipv6hdr *iph = ipv6_hdr(skb);
334 struct ipv6_destopt_hao *hao;
335 int off;
336
337 if (opt->dsthao) {
338 off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
339 if (likely(off >= 0)) {
340 hao = (struct ipv6_destopt_hao *)
341 (skb_network_header(skb) + off);
342 swap(iph->saddr, hao->addr);
343 }
344 }
345 }
346 #else
mip6_addr_swap(struct sk_buff * skb,const struct inet6_skb_parm * opt)347 static inline void mip6_addr_swap(struct sk_buff *skb, const struct inet6_skb_parm *opt) {}
348 #endif
349
icmpv6_route_lookup(struct net * net,struct sk_buff * skb,struct sock * sk,struct flowi6 * fl6)350 static struct dst_entry *icmpv6_route_lookup(struct net *net,
351 struct sk_buff *skb,
352 struct sock *sk,
353 struct flowi6 *fl6)
354 {
355 struct dst_entry *dst, *dst2;
356 struct flowi6 fl2;
357 int err;
358
359 err = ip6_dst_lookup(net, sk, &dst, fl6);
360 if (err)
361 return ERR_PTR(err);
362
363 /*
364 * We won't send icmp if the destination is known
365 * anycast.
366 */
367 if (ipv6_anycast_destination(dst, &fl6->daddr)) {
368 net_dbg_ratelimited("icmp6_send: acast source\n");
369 dst_release(dst);
370 return ERR_PTR(-EINVAL);
371 }
372
373 /* No need to clone since we're just using its address. */
374 dst2 = dst;
375
376 dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), sk, 0);
377 if (!IS_ERR(dst)) {
378 if (dst != dst2)
379 return dst;
380 } else {
381 if (PTR_ERR(dst) == -EPERM)
382 dst = NULL;
383 else
384 return dst;
385 }
386
387 err = xfrm_decode_session_reverse(skb, flowi6_to_flowi(&fl2), AF_INET6);
388 if (err)
389 goto relookup_failed;
390
391 err = ip6_dst_lookup(net, sk, &dst2, &fl2);
392 if (err)
393 goto relookup_failed;
394
395 dst2 = xfrm_lookup(net, dst2, flowi6_to_flowi(&fl2), sk, XFRM_LOOKUP_ICMP);
396 if (!IS_ERR(dst2)) {
397 dst_release(dst);
398 dst = dst2;
399 } else {
400 err = PTR_ERR(dst2);
401 if (err == -EPERM) {
402 dst_release(dst);
403 return dst2;
404 } else
405 goto relookup_failed;
406 }
407
408 relookup_failed:
409 if (dst)
410 return dst;
411 return ERR_PTR(err);
412 }
413
icmp6_dev(const struct sk_buff * skb)414 static struct net_device *icmp6_dev(const struct sk_buff *skb)
415 {
416 struct net_device *dev = skb->dev;
417
418 /* for local traffic to local address, skb dev is the loopback
419 * device. Check if there is a dst attached to the skb and if so
420 * get the real device index. Same is needed for replies to a link
421 * local address on a device enslaved to an L3 master device
422 */
423 if (unlikely(dev->ifindex == LOOPBACK_IFINDEX || netif_is_l3_master(skb->dev))) {
424 const struct rt6_info *rt6 = skb_rt6_info(skb);
425
426 if (rt6)
427 dev = rt6->rt6i_idev->dev;
428 }
429
430 return dev;
431 }
432
icmp6_iif(const struct sk_buff * skb)433 static int icmp6_iif(const struct sk_buff *skb)
434 {
435 return icmp6_dev(skb)->ifindex;
436 }
437
438 /*
439 * Send an ICMP message in response to a packet in error
440 */
icmp6_send(struct sk_buff * skb,u8 type,u8 code,__u32 info,const struct in6_addr * force_saddr,const struct inet6_skb_parm * parm)441 void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
442 const struct in6_addr *force_saddr,
443 const struct inet6_skb_parm *parm)
444 {
445 struct inet6_dev *idev = NULL;
446 struct ipv6hdr *hdr = ipv6_hdr(skb);
447 struct sock *sk;
448 struct net *net;
449 struct ipv6_pinfo *np;
450 const struct in6_addr *saddr = NULL;
451 struct dst_entry *dst;
452 struct icmp6hdr tmp_hdr;
453 struct flowi6 fl6;
454 struct icmpv6_msg msg;
455 struct ipcm6_cookie ipc6;
456 int iif = 0;
457 int addr_type = 0;
458 int len;
459 u32 mark;
460
461 if ((u8 *)hdr < skb->head ||
462 (skb_network_header(skb) + sizeof(*hdr)) > skb_tail_pointer(skb))
463 return;
464
465 if (!skb->dev)
466 return;
467 net = dev_net(skb->dev);
468 mark = IP6_REPLY_MARK(net, skb->mark);
469 /*
470 * Make sure we respect the rules
471 * i.e. RFC 1885 2.4(e)
472 * Rule (e.1) is enforced by not using icmp6_send
473 * in any code that processes icmp errors.
474 */
475 addr_type = ipv6_addr_type(&hdr->daddr);
476
477 if (ipv6_chk_addr(net, &hdr->daddr, skb->dev, 0) ||
478 ipv6_chk_acast_addr_src(net, skb->dev, &hdr->daddr))
479 saddr = &hdr->daddr;
480
481 /*
482 * Dest addr check
483 */
484
485 if (addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST) {
486 if (type != ICMPV6_PKT_TOOBIG &&
487 !(type == ICMPV6_PARAMPROB &&
488 code == ICMPV6_UNK_OPTION &&
489 (opt_unrec(skb, info))))
490 return;
491
492 saddr = NULL;
493 }
494
495 addr_type = ipv6_addr_type(&hdr->saddr);
496
497 /*
498 * Source addr check
499 */
500
501 if (__ipv6_addr_needs_scope_id(addr_type)) {
502 iif = icmp6_iif(skb);
503 } else {
504 /*
505 * The source device is used for looking up which routing table
506 * to use for sending an ICMP error.
507 */
508 iif = l3mdev_master_ifindex(skb->dev);
509 }
510
511 /*
512 * Must not send error if the source does not uniquely
513 * identify a single node (RFC2463 Section 2.4).
514 * We check unspecified / multicast addresses here,
515 * and anycast addresses will be checked later.
516 */
517 if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
518 net_dbg_ratelimited("icmp6_send: addr_any/mcast source [%pI6c > %pI6c]\n",
519 &hdr->saddr, &hdr->daddr);
520 return;
521 }
522
523 /*
524 * Never answer to a ICMP packet.
525 */
526 if (is_ineligible(skb)) {
527 net_dbg_ratelimited("icmp6_send: no reply to icmp error [%pI6c > %pI6c]\n",
528 &hdr->saddr, &hdr->daddr);
529 return;
530 }
531
532 /* Needed by both icmp_global_allow and icmpv6_xmit_lock */
533 local_bh_disable();
534
535 /* Check global sysctl_icmp_msgs_per_sec ratelimit */
536 if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
537 goto out_bh_enable;
538
539 mip6_addr_swap(skb, parm);
540
541 sk = icmpv6_xmit_lock(net);
542 if (!sk)
543 goto out_bh_enable;
544
545 memset(&fl6, 0, sizeof(fl6));
546 fl6.flowi6_proto = IPPROTO_ICMPV6;
547 fl6.daddr = hdr->saddr;
548 if (force_saddr)
549 saddr = force_saddr;
550 if (saddr) {
551 fl6.saddr = *saddr;
552 } else if (!icmpv6_rt_has_prefsrc(sk, type, &fl6)) {
553 /* select a more meaningful saddr from input if */
554 struct net_device *in_netdev;
555
556 in_netdev = dev_get_by_index(net, parm->iif);
557 if (in_netdev) {
558 ipv6_dev_get_saddr(net, in_netdev, &fl6.daddr,
559 inet6_sk(sk)->srcprefs,
560 &fl6.saddr);
561 dev_put(in_netdev);
562 }
563 }
564 fl6.flowi6_mark = mark;
565 fl6.flowi6_oif = iif;
566 fl6.fl6_icmp_type = type;
567 fl6.fl6_icmp_code = code;
568 fl6.flowi6_uid = sock_net_uid(net, NULL);
569 fl6.mp_hash = rt6_multipath_hash(net, &fl6, skb, NULL);
570 security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
571
572 np = inet6_sk(sk);
573
574 if (!icmpv6_xrlim_allow(sk, type, &fl6))
575 goto out;
576
577 tmp_hdr.icmp6_type = type;
578 tmp_hdr.icmp6_code = code;
579 tmp_hdr.icmp6_cksum = 0;
580 tmp_hdr.icmp6_pointer = htonl(info);
581
582 if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
583 fl6.flowi6_oif = np->mcast_oif;
584 else if (!fl6.flowi6_oif)
585 fl6.flowi6_oif = np->ucast_oif;
586
587 ipcm6_init_sk(&ipc6, np);
588 ipc6.sockc.mark = mark;
589 fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel);
590
591 dst = icmpv6_route_lookup(net, skb, sk, &fl6);
592 if (IS_ERR(dst))
593 goto out;
594
595 ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
596
597 msg.skb = skb;
598 msg.offset = skb_network_offset(skb);
599 msg.type = type;
600
601 len = skb->len - msg.offset;
602 len = min_t(unsigned int, len, IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(struct icmp6hdr));
603 if (len < 0) {
604 net_dbg_ratelimited("icmp: len problem [%pI6c > %pI6c]\n",
605 &hdr->saddr, &hdr->daddr);
606 goto out_dst_release;
607 }
608
609 rcu_read_lock();
610 idev = __in6_dev_get(skb->dev);
611
612 if (ip6_append_data(sk, icmpv6_getfrag, &msg,
613 len + sizeof(struct icmp6hdr),
614 sizeof(struct icmp6hdr),
615 &ipc6, &fl6, (struct rt6_info *)dst,
616 MSG_DONTWAIT)) {
617 ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
618 ip6_flush_pending_frames(sk);
619 } else {
620 icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
621 len + sizeof(struct icmp6hdr));
622 }
623 rcu_read_unlock();
624 out_dst_release:
625 dst_release(dst);
626 out:
627 icmpv6_xmit_unlock(sk);
628 out_bh_enable:
629 local_bh_enable();
630 }
631 EXPORT_SYMBOL(icmp6_send);
632
633 /* Slightly more convenient version of icmp6_send with drop reasons.
634 */
icmpv6_param_prob_reason(struct sk_buff * skb,u8 code,int pos,enum skb_drop_reason reason)635 void icmpv6_param_prob_reason(struct sk_buff *skb, u8 code, int pos,
636 enum skb_drop_reason reason)
637 {
638 icmp6_send(skb, ICMPV6_PARAMPROB, code, pos, NULL, IP6CB(skb));
639 kfree_skb_reason(skb, reason);
640 }
641
642 /* Generate icmpv6 with type/code ICMPV6_DEST_UNREACH/ICMPV6_ADDR_UNREACH
643 * if sufficient data bytes are available
644 * @nhs is the size of the tunnel header(s) :
645 * Either an IPv4 header for SIT encap
646 * an IPv4 header + GRE header for GRE encap
647 */
ip6_err_gen_icmpv6_unreach(struct sk_buff * skb,int nhs,int type,unsigned int data_len)648 int ip6_err_gen_icmpv6_unreach(struct sk_buff *skb, int nhs, int type,
649 unsigned int data_len)
650 {
651 struct in6_addr temp_saddr;
652 struct rt6_info *rt;
653 struct sk_buff *skb2;
654 u32 info = 0;
655
656 if (!pskb_may_pull(skb, nhs + sizeof(struct ipv6hdr) + 8))
657 return 1;
658
659 /* RFC 4884 (partial) support for ICMP extensions */
660 if (data_len < 128 || (data_len & 7) || skb->len < data_len)
661 data_len = 0;
662
663 skb2 = data_len ? skb_copy(skb, GFP_ATOMIC) : skb_clone(skb, GFP_ATOMIC);
664
665 if (!skb2)
666 return 1;
667
668 skb_dst_drop(skb2);
669 skb_pull(skb2, nhs);
670 skb_reset_network_header(skb2);
671
672 rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0,
673 skb, 0);
674
675 if (rt && rt->dst.dev)
676 skb2->dev = rt->dst.dev;
677
678 ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, &temp_saddr);
679
680 if (data_len) {
681 /* RFC 4884 (partial) support :
682 * insert 0 padding at the end, before the extensions
683 */
684 __skb_push(skb2, nhs);
685 skb_reset_network_header(skb2);
686 memmove(skb2->data, skb2->data + nhs, data_len - nhs);
687 memset(skb2->data + data_len - nhs, 0, nhs);
688 /* RFC 4884 4.5 : Length is measured in 64-bit words,
689 * and stored in reserved[0]
690 */
691 info = (data_len/8) << 24;
692 }
693 if (type == ICMP_TIME_EXCEEDED)
694 icmp6_send(skb2, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
695 info, &temp_saddr, IP6CB(skb2));
696 else
697 icmp6_send(skb2, ICMPV6_DEST_UNREACH, ICMPV6_ADDR_UNREACH,
698 info, &temp_saddr, IP6CB(skb2));
699 if (rt)
700 ip6_rt_put(rt);
701
702 kfree_skb(skb2);
703
704 return 0;
705 }
706 EXPORT_SYMBOL(ip6_err_gen_icmpv6_unreach);
707
icmpv6_echo_reply(struct sk_buff * skb)708 static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
709 {
710 struct net *net = dev_net(skb->dev);
711 struct sock *sk;
712 struct inet6_dev *idev;
713 struct ipv6_pinfo *np;
714 const struct in6_addr *saddr = NULL;
715 struct icmp6hdr *icmph = icmp6_hdr(skb);
716 struct icmp6hdr tmp_hdr;
717 struct flowi6 fl6;
718 struct icmpv6_msg msg;
719 struct dst_entry *dst;
720 struct ipcm6_cookie ipc6;
721 u32 mark = IP6_REPLY_MARK(net, skb->mark);
722 SKB_DR(reason);
723 bool acast;
724 u8 type;
725
726 if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) &&
727 net->ipv6.sysctl.icmpv6_echo_ignore_multicast)
728 return reason;
729
730 saddr = &ipv6_hdr(skb)->daddr;
731
732 acast = ipv6_anycast_destination(skb_dst(skb), saddr);
733 if (acast && net->ipv6.sysctl.icmpv6_echo_ignore_anycast)
734 return reason;
735
736 if (!ipv6_unicast_destination(skb) &&
737 !(net->ipv6.sysctl.anycast_src_echo_reply && acast))
738 saddr = NULL;
739
740 if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST)
741 type = ICMPV6_EXT_ECHO_REPLY;
742 else
743 type = ICMPV6_ECHO_REPLY;
744
745 memcpy(&tmp_hdr, icmph, sizeof(tmp_hdr));
746 tmp_hdr.icmp6_type = type;
747
748 memset(&fl6, 0, sizeof(fl6));
749 if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES)
750 fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb));
751
752 fl6.flowi6_proto = IPPROTO_ICMPV6;
753 fl6.daddr = ipv6_hdr(skb)->saddr;
754 if (saddr)
755 fl6.saddr = *saddr;
756 fl6.flowi6_oif = icmp6_iif(skb);
757 fl6.fl6_icmp_type = type;
758 fl6.flowi6_mark = mark;
759 fl6.flowi6_uid = sock_net_uid(net, NULL);
760 security_skb_classify_flow(skb, flowi6_to_flowi_common(&fl6));
761
762 local_bh_disable();
763 sk = icmpv6_xmit_lock(net);
764 if (!sk)
765 goto out_bh_enable;
766 np = inet6_sk(sk);
767
768 if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr))
769 fl6.flowi6_oif = np->mcast_oif;
770 else if (!fl6.flowi6_oif)
771 fl6.flowi6_oif = np->ucast_oif;
772
773 if (ip6_dst_lookup(net, sk, &dst, &fl6))
774 goto out;
775 dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), sk, 0);
776 if (IS_ERR(dst))
777 goto out;
778
779 /* Check the ratelimit */
780 if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY)) ||
781 !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6))
782 goto out_dst_release;
783
784 idev = __in6_dev_get(skb->dev);
785
786 msg.skb = skb;
787 msg.offset = 0;
788 msg.type = type;
789
790 ipcm6_init_sk(&ipc6, np);
791 ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst);
792 ipc6.tclass = ipv6_get_dsfield(ipv6_hdr(skb));
793 ipc6.sockc.mark = mark;
794
795 if (icmph->icmp6_type == ICMPV6_EXT_ECHO_REQUEST)
796 if (!icmp_build_probe(skb, (struct icmphdr *)&tmp_hdr))
797 goto out_dst_release;
798
799 if (ip6_append_data(sk, icmpv6_getfrag, &msg,
800 skb->len + sizeof(struct icmp6hdr),
801 sizeof(struct icmp6hdr), &ipc6, &fl6,
802 (struct rt6_info *)dst, MSG_DONTWAIT)) {
803 __ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTERRORS);
804 ip6_flush_pending_frames(sk);
805 } else {
806 icmpv6_push_pending_frames(sk, &fl6, &tmp_hdr,
807 skb->len + sizeof(struct icmp6hdr));
808 reason = SKB_CONSUMED;
809 }
810 out_dst_release:
811 dst_release(dst);
812 out:
813 icmpv6_xmit_unlock(sk);
814 out_bh_enable:
815 local_bh_enable();
816 return reason;
817 }
818
icmpv6_notify(struct sk_buff * skb,u8 type,u8 code,__be32 info)819 enum skb_drop_reason icmpv6_notify(struct sk_buff *skb, u8 type,
820 u8 code, __be32 info)
821 {
822 struct inet6_skb_parm *opt = IP6CB(skb);
823 struct net *net = dev_net(skb->dev);
824 const struct inet6_protocol *ipprot;
825 enum skb_drop_reason reason;
826 int inner_offset;
827 __be16 frag_off;
828 u8 nexthdr;
829
830 reason = pskb_may_pull_reason(skb, sizeof(struct ipv6hdr));
831 if (reason != SKB_NOT_DROPPED_YET)
832 goto out;
833
834 seg6_icmp_srh(skb, opt);
835
836 nexthdr = ((struct ipv6hdr *)skb->data)->nexthdr;
837 if (ipv6_ext_hdr(nexthdr)) {
838 /* now skip over extension headers */
839 inner_offset = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
840 &nexthdr, &frag_off);
841 if (inner_offset < 0) {
842 SKB_DR_SET(reason, IPV6_BAD_EXTHDR);
843 goto out;
844 }
845 } else {
846 inner_offset = sizeof(struct ipv6hdr);
847 }
848
849 /* Checkin header including 8 bytes of inner protocol header. */
850 reason = pskb_may_pull_reason(skb, inner_offset + 8);
851 if (reason != SKB_NOT_DROPPED_YET)
852 goto out;
853
854 /* BUGGG_FUTURE: we should try to parse exthdrs in this packet.
855 Without this we will not able f.e. to make source routed
856 pmtu discovery.
857 Corresponding argument (opt) to notifiers is already added.
858 --ANK (980726)
859 */
860
861 ipprot = rcu_dereference(inet6_protos[nexthdr]);
862 if (ipprot && ipprot->err_handler)
863 ipprot->err_handler(skb, opt, type, code, inner_offset, info);
864
865 raw6_icmp_error(skb, nexthdr, type, code, inner_offset, info);
866 return SKB_CONSUMED;
867
868 out:
869 __ICMP6_INC_STATS(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
870 return reason;
871 }
872
873 /*
874 * Handle icmp messages
875 */
876
icmpv6_rcv(struct sk_buff * skb)877 static int icmpv6_rcv(struct sk_buff *skb)
878 {
879 enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
880 struct net *net = dev_net(skb->dev);
881 struct net_device *dev = icmp6_dev(skb);
882 struct inet6_dev *idev = __in6_dev_get(dev);
883 const struct in6_addr *saddr, *daddr;
884 struct icmp6hdr *hdr;
885 u8 type;
886
887 if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) {
888 struct sec_path *sp = skb_sec_path(skb);
889 int nh;
890
891 if (!(sp && sp->xvec[sp->len - 1]->props.flags &
892 XFRM_STATE_ICMP)) {
893 reason = SKB_DROP_REASON_XFRM_POLICY;
894 goto drop_no_count;
895 }
896
897 if (!pskb_may_pull(skb, sizeof(*hdr) + sizeof(struct ipv6hdr)))
898 goto drop_no_count;
899
900 nh = skb_network_offset(skb);
901 skb_set_network_header(skb, sizeof(*hdr));
902
903 if (!xfrm6_policy_check_reverse(NULL, XFRM_POLICY_IN,
904 skb)) {
905 reason = SKB_DROP_REASON_XFRM_POLICY;
906 goto drop_no_count;
907 }
908
909 skb_set_network_header(skb, nh);
910 }
911
912 __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INMSGS);
913
914 saddr = &ipv6_hdr(skb)->saddr;
915 daddr = &ipv6_hdr(skb)->daddr;
916
917 if (skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo)) {
918 net_dbg_ratelimited("ICMPv6 checksum failed [%pI6c > %pI6c]\n",
919 saddr, daddr);
920 goto csum_error;
921 }
922
923 if (!pskb_pull(skb, sizeof(*hdr)))
924 goto discard_it;
925
926 hdr = icmp6_hdr(skb);
927
928 type = hdr->icmp6_type;
929
930 ICMP6MSGIN_INC_STATS(dev_net(dev), idev, type);
931
932 switch (type) {
933 case ICMPV6_ECHO_REQUEST:
934 if (!net->ipv6.sysctl.icmpv6_echo_ignore_all)
935 reason = icmpv6_echo_reply(skb);
936 break;
937 case ICMPV6_EXT_ECHO_REQUEST:
938 if (!net->ipv6.sysctl.icmpv6_echo_ignore_all &&
939 READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
940 reason = icmpv6_echo_reply(skb);
941 break;
942
943 case ICMPV6_ECHO_REPLY:
944 reason = ping_rcv(skb);
945 break;
946
947 case ICMPV6_EXT_ECHO_REPLY:
948 reason = ping_rcv(skb);
949 break;
950
951 case ICMPV6_PKT_TOOBIG:
952 /* BUGGG_FUTURE: if packet contains rthdr, we cannot update
953 standard destination cache. Seems, only "advanced"
954 destination cache will allow to solve this problem
955 --ANK (980726)
956 */
957 if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
958 goto discard_it;
959 hdr = icmp6_hdr(skb);
960
961 /* to notify */
962 fallthrough;
963 case ICMPV6_DEST_UNREACH:
964 case ICMPV6_TIME_EXCEED:
965 case ICMPV6_PARAMPROB:
966 reason = icmpv6_notify(skb, type, hdr->icmp6_code,
967 hdr->icmp6_mtu);
968 break;
969
970 case NDISC_ROUTER_SOLICITATION:
971 case NDISC_ROUTER_ADVERTISEMENT:
972 case NDISC_NEIGHBOUR_SOLICITATION:
973 case NDISC_NEIGHBOUR_ADVERTISEMENT:
974 case NDISC_REDIRECT:
975 reason = ndisc_rcv(skb);
976 break;
977
978 case ICMPV6_MGM_QUERY:
979 igmp6_event_query(skb);
980 return 0;
981
982 case ICMPV6_MGM_REPORT:
983 igmp6_event_report(skb);
984 return 0;
985
986 case ICMPV6_MGM_REDUCTION:
987 case ICMPV6_NI_QUERY:
988 case ICMPV6_NI_REPLY:
989 case ICMPV6_MLD2_REPORT:
990 case ICMPV6_DHAAD_REQUEST:
991 case ICMPV6_DHAAD_REPLY:
992 case ICMPV6_MOBILE_PREFIX_SOL:
993 case ICMPV6_MOBILE_PREFIX_ADV:
994 break;
995
996 default:
997 /* informational */
998 if (type & ICMPV6_INFOMSG_MASK)
999 break;
1000
1001 net_dbg_ratelimited("icmpv6: msg of unknown type [%pI6c > %pI6c]\n",
1002 saddr, daddr);
1003
1004 /*
1005 * error of unknown type.
1006 * must pass to upper level
1007 */
1008
1009 reason = icmpv6_notify(skb, type, hdr->icmp6_code,
1010 hdr->icmp6_mtu);
1011 }
1012
1013 /* until the v6 path can be better sorted assume failure and
1014 * preserve the status quo behaviour for the rest of the paths to here
1015 */
1016 if (reason)
1017 kfree_skb_reason(skb, reason);
1018 else
1019 consume_skb(skb);
1020
1021 return 0;
1022
1023 csum_error:
1024 reason = SKB_DROP_REASON_ICMP_CSUM;
1025 __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_CSUMERRORS);
1026 discard_it:
1027 __ICMP6_INC_STATS(dev_net(dev), idev, ICMP6_MIB_INERRORS);
1028 drop_no_count:
1029 kfree_skb_reason(skb, reason);
1030 return 0;
1031 }
1032
icmpv6_flow_init(struct sock * sk,struct flowi6 * fl6,u8 type,const struct in6_addr * saddr,const struct in6_addr * daddr,int oif)1033 void icmpv6_flow_init(struct sock *sk, struct flowi6 *fl6,
1034 u8 type,
1035 const struct in6_addr *saddr,
1036 const struct in6_addr *daddr,
1037 int oif)
1038 {
1039 memset(fl6, 0, sizeof(*fl6));
1040 fl6->saddr = *saddr;
1041 fl6->daddr = *daddr;
1042 fl6->flowi6_proto = IPPROTO_ICMPV6;
1043 fl6->fl6_icmp_type = type;
1044 fl6->fl6_icmp_code = 0;
1045 fl6->flowi6_oif = oif;
1046 security_sk_classify_flow(sk, flowi6_to_flowi_common(fl6));
1047 }
1048
icmpv6_init(void)1049 int __init icmpv6_init(void)
1050 {
1051 struct sock *sk;
1052 int err, i;
1053
1054 for_each_possible_cpu(i) {
1055 err = inet_ctl_sock_create(&sk, PF_INET6,
1056 SOCK_RAW, IPPROTO_ICMPV6, &init_net);
1057 if (err < 0) {
1058 pr_err("Failed to initialize the ICMP6 control socket (err %d)\n",
1059 err);
1060 return err;
1061 }
1062
1063 per_cpu(ipv6_icmp_sk, i) = sk;
1064
1065 /* Enough space for 2 64K ICMP packets, including
1066 * sk_buff struct overhead.
1067 */
1068 sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
1069 }
1070
1071 err = -EAGAIN;
1072 if (inet6_add_protocol(&icmpv6_protocol, IPPROTO_ICMPV6) < 0)
1073 goto fail;
1074
1075 err = inet6_register_icmp_sender(icmp6_send);
1076 if (err)
1077 goto sender_reg_err;
1078 return 0;
1079
1080 sender_reg_err:
1081 inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
1082 fail:
1083 pr_err("Failed to register ICMP6 protocol\n");
1084 return err;
1085 }
1086
icmpv6_cleanup(void)1087 void icmpv6_cleanup(void)
1088 {
1089 inet6_unregister_icmp_sender(icmp6_send);
1090 inet6_del_protocol(&icmpv6_protocol, IPPROTO_ICMPV6);
1091 }
1092
1093
1094 static const struct icmp6_err {
1095 int err;
1096 int fatal;
1097 } tab_unreach[] = {
1098 { /* NOROUTE */
1099 .err = ENETUNREACH,
1100 .fatal = 0,
1101 },
1102 { /* ADM_PROHIBITED */
1103 .err = EACCES,
1104 .fatal = 1,
1105 },
1106 { /* Was NOT_NEIGHBOUR, now reserved */
1107 .err = EHOSTUNREACH,
1108 .fatal = 0,
1109 },
1110 { /* ADDR_UNREACH */
1111 .err = EHOSTUNREACH,
1112 .fatal = 0,
1113 },
1114 { /* PORT_UNREACH */
1115 .err = ECONNREFUSED,
1116 .fatal = 1,
1117 },
1118 { /* POLICY_FAIL */
1119 .err = EACCES,
1120 .fatal = 1,
1121 },
1122 { /* REJECT_ROUTE */
1123 .err = EACCES,
1124 .fatal = 1,
1125 },
1126 };
1127
icmpv6_err_convert(u8 type,u8 code,int * err)1128 int icmpv6_err_convert(u8 type, u8 code, int *err)
1129 {
1130 int fatal = 0;
1131
1132 *err = EPROTO;
1133
1134 switch (type) {
1135 case ICMPV6_DEST_UNREACH:
1136 fatal = 1;
1137 if (code < ARRAY_SIZE(tab_unreach)) {
1138 *err = tab_unreach[code].err;
1139 fatal = tab_unreach[code].fatal;
1140 }
1141 break;
1142
1143 case ICMPV6_PKT_TOOBIG:
1144 *err = EMSGSIZE;
1145 break;
1146
1147 case ICMPV6_PARAMPROB:
1148 *err = EPROTO;
1149 fatal = 1;
1150 break;
1151
1152 case ICMPV6_TIME_EXCEED:
1153 *err = EHOSTUNREACH;
1154 break;
1155 }
1156
1157 return fatal;
1158 }
1159 EXPORT_SYMBOL(icmpv6_err_convert);
1160
1161 #ifdef CONFIG_SYSCTL
1162 static struct ctl_table ipv6_icmp_table_template[] = {
1163 {
1164 .procname = "ratelimit",
1165 .data = &init_net.ipv6.sysctl.icmpv6_time,
1166 .maxlen = sizeof(int),
1167 .mode = 0644,
1168 .proc_handler = proc_dointvec_ms_jiffies,
1169 },
1170 {
1171 .procname = "echo_ignore_all",
1172 .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_all,
1173 .maxlen = sizeof(u8),
1174 .mode = 0644,
1175 .proc_handler = proc_dou8vec_minmax,
1176 },
1177 {
1178 .procname = "echo_ignore_multicast",
1179 .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_multicast,
1180 .maxlen = sizeof(u8),
1181 .mode = 0644,
1182 .proc_handler = proc_dou8vec_minmax,
1183 },
1184 {
1185 .procname = "echo_ignore_anycast",
1186 .data = &init_net.ipv6.sysctl.icmpv6_echo_ignore_anycast,
1187 .maxlen = sizeof(u8),
1188 .mode = 0644,
1189 .proc_handler = proc_dou8vec_minmax,
1190 },
1191 {
1192 .procname = "ratemask",
1193 .data = &init_net.ipv6.sysctl.icmpv6_ratemask_ptr,
1194 .maxlen = ICMPV6_MSG_MAX + 1,
1195 .mode = 0644,
1196 .proc_handler = proc_do_large_bitmap,
1197 },
1198 { },
1199 };
1200
ipv6_icmp_sysctl_init(struct net * net)1201 struct ctl_table * __net_init ipv6_icmp_sysctl_init(struct net *net)
1202 {
1203 struct ctl_table *table;
1204
1205 table = kmemdup(ipv6_icmp_table_template,
1206 sizeof(ipv6_icmp_table_template),
1207 GFP_KERNEL);
1208
1209 if (table) {
1210 table[0].data = &net->ipv6.sysctl.icmpv6_time;
1211 table[1].data = &net->ipv6.sysctl.icmpv6_echo_ignore_all;
1212 table[2].data = &net->ipv6.sysctl.icmpv6_echo_ignore_multicast;
1213 table[3].data = &net->ipv6.sysctl.icmpv6_echo_ignore_anycast;
1214 table[4].data = &net->ipv6.sysctl.icmpv6_ratemask_ptr;
1215 }
1216 return table;
1217 }
1218 #endif
1219