1 // SPDX-License-Identifier: GPL-2.0-or-later
2 /*
3 * Neighbour Discovery for IPv6
4 * Linux INET6 implementation
5 *
6 * Authors:
7 * Pedro Roque <roque@di.fc.ul.pt>
8 * Mike Shaver <shaver@ingenia.com>
9 */
10
11 /*
12 * Changes:
13 *
14 * Alexey I. Froloff : RFC6106 (DNSSL) support
15 * Pierre Ynard : export userland ND options
16 * through netlink (RDNSS support)
17 * Lars Fenneberg : fixed MTU setting on receipt
18 * of an RA.
19 * Janos Farkas : kmalloc failure checks
20 * Alexey Kuznetsov : state machine reworked
21 * and moved to net/core.
22 * Pekka Savola : RFC2461 validation
23 * YOSHIFUJI Hideaki @USAGI : Verify ND options properly
24 */
25
26 #define pr_fmt(fmt) "ICMPv6: " fmt
27
28 #include <linux/module.h>
29 #include <linux/errno.h>
30 #include <linux/types.h>
31 #include <linux/socket.h>
32 #include <linux/sockios.h>
33 #include <linux/sched.h>
34 #include <linux/net.h>
35 #include <linux/in6.h>
36 #include <linux/route.h>
37 #include <linux/init.h>
38 #include <linux/rcupdate.h>
39 #include <linux/slab.h>
40 #ifdef CONFIG_SYSCTL
41 #include <linux/sysctl.h>
42 #endif
43
44 #include <linux/if_addr.h>
45 #include <linux/if_ether.h>
46 #include <linux/if_arp.h>
47 #include <linux/ipv6.h>
48 #include <linux/icmpv6.h>
49 #include <linux/jhash.h>
50
51 #include <net/sock.h>
52 #include <net/snmp.h>
53
54 #include <net/ipv6.h>
55 #include <net/protocol.h>
56 #include <net/ndisc.h>
57 #include <net/ip6_route.h>
58 #include <net/addrconf.h>
59 #include <net/icmp.h>
60
61 #include <net/netlink.h>
62 #include <linux/rtnetlink.h>
63
64 #include <net/flow.h>
65 #include <net/ip6_checksum.h>
66 #include <net/inet_common.h>
67 #include <linux/proc_fs.h>
68
69 #include <linux/netfilter.h>
70 #include <linux/netfilter_ipv6.h>
71
72 static u32 ndisc_hash(const void *pkey,
73 const struct net_device *dev,
74 __u32 *hash_rnd);
75 static bool ndisc_key_eq(const struct neighbour *neigh, const void *pkey);
76 static bool ndisc_allow_add(const struct net_device *dev,
77 struct netlink_ext_ack *extack);
78 static int ndisc_constructor(struct neighbour *neigh);
79 static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb);
80 static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb);
81 static int pndisc_constructor(struct pneigh_entry *n);
82 static void pndisc_destructor(struct pneigh_entry *n);
83 static void pndisc_redo(struct sk_buff *skb);
84 static int ndisc_is_multicast(const void *pkey);
85
86 static const struct neigh_ops ndisc_generic_ops = {
87 .family = AF_INET6,
88 .solicit = ndisc_solicit,
89 .error_report = ndisc_error_report,
90 .output = neigh_resolve_output,
91 .connected_output = neigh_connected_output,
92 };
93
94 static const struct neigh_ops ndisc_hh_ops = {
95 .family = AF_INET6,
96 .solicit = ndisc_solicit,
97 .error_report = ndisc_error_report,
98 .output = neigh_resolve_output,
99 .connected_output = neigh_resolve_output,
100 };
101
102
103 static const struct neigh_ops ndisc_direct_ops = {
104 .family = AF_INET6,
105 .output = neigh_direct_output,
106 .connected_output = neigh_direct_output,
107 };
108
109 struct neigh_table nd_tbl = {
110 .family = AF_INET6,
111 .key_len = sizeof(struct in6_addr),
112 .protocol = cpu_to_be16(ETH_P_IPV6),
113 .hash = ndisc_hash,
114 .key_eq = ndisc_key_eq,
115 .constructor = ndisc_constructor,
116 .pconstructor = pndisc_constructor,
117 .pdestructor = pndisc_destructor,
118 .proxy_redo = pndisc_redo,
119 .is_multicast = ndisc_is_multicast,
120 .allow_add = ndisc_allow_add,
121 .id = "ndisc_cache",
122 .parms = {
123 .tbl = &nd_tbl,
124 .reachable_time = ND_REACHABLE_TIME,
125 .data = {
126 [NEIGH_VAR_MCAST_PROBES] = 3,
127 [NEIGH_VAR_UCAST_PROBES] = 3,
128 [NEIGH_VAR_RETRANS_TIME] = ND_RETRANS_TIMER,
129 [NEIGH_VAR_BASE_REACHABLE_TIME] = ND_REACHABLE_TIME,
130 [NEIGH_VAR_DELAY_PROBE_TIME] = 5 * HZ,
131 [NEIGH_VAR_INTERVAL_PROBE_TIME_MS] = 5 * HZ,
132 [NEIGH_VAR_GC_STALETIME] = 60 * HZ,
133 [NEIGH_VAR_QUEUE_LEN_BYTES] = SK_WMEM_MAX,
134 [NEIGH_VAR_PROXY_QLEN] = 64,
135 [NEIGH_VAR_ANYCAST_DELAY] = 1 * HZ,
136 [NEIGH_VAR_PROXY_DELAY] = (8 * HZ) / 10,
137 },
138 },
139 .gc_interval = 30 * HZ,
140 .gc_thresh1 = 128,
141 .gc_thresh2 = 512,
142 .gc_thresh3 = 1024,
143 };
144 EXPORT_SYMBOL_GPL(nd_tbl);
145
__ndisc_fill_addr_option(struct sk_buff * skb,int type,const void * data,int data_len,int pad)146 void __ndisc_fill_addr_option(struct sk_buff *skb, int type, const void *data,
147 int data_len, int pad)
148 {
149 int space = __ndisc_opt_addr_space(data_len, pad);
150 u8 *opt = skb_put(skb, space);
151
152 opt[0] = type;
153 opt[1] = space>>3;
154
155 memset(opt + 2, 0, pad);
156 opt += pad;
157 space -= pad;
158
159 memcpy(opt+2, data, data_len);
160 data_len += 2;
161 opt += data_len;
162 space -= data_len;
163 if (space > 0)
164 memset(opt, 0, space);
165 }
166 EXPORT_SYMBOL_GPL(__ndisc_fill_addr_option);
167
ndisc_fill_addr_option(struct sk_buff * skb,int type,const void * data,u8 icmp6_type)168 static inline void ndisc_fill_addr_option(struct sk_buff *skb, int type,
169 const void *data, u8 icmp6_type)
170 {
171 __ndisc_fill_addr_option(skb, type, data, skb->dev->addr_len,
172 ndisc_addr_option_pad(skb->dev->type));
173 ndisc_ops_fill_addr_option(skb->dev, skb, icmp6_type);
174 }
175
ndisc_fill_redirect_addr_option(struct sk_buff * skb,void * ha,const u8 * ops_data)176 static inline void ndisc_fill_redirect_addr_option(struct sk_buff *skb,
177 void *ha,
178 const u8 *ops_data)
179 {
180 ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR, ha, NDISC_REDIRECT);
181 ndisc_ops_fill_redirect_addr_option(skb->dev, skb, ops_data);
182 }
183
ndisc_next_option(struct nd_opt_hdr * cur,struct nd_opt_hdr * end)184 static struct nd_opt_hdr *ndisc_next_option(struct nd_opt_hdr *cur,
185 struct nd_opt_hdr *end)
186 {
187 int type;
188 if (!cur || !end || cur >= end)
189 return NULL;
190 type = cur->nd_opt_type;
191 do {
192 cur = ((void *)cur) + (cur->nd_opt_len << 3);
193 } while (cur < end && cur->nd_opt_type != type);
194 return cur <= end && cur->nd_opt_type == type ? cur : NULL;
195 }
196
ndisc_is_useropt(const struct net_device * dev,struct nd_opt_hdr * opt)197 static inline int ndisc_is_useropt(const struct net_device *dev,
198 struct nd_opt_hdr *opt)
199 {
200 return opt->nd_opt_type == ND_OPT_RDNSS ||
201 opt->nd_opt_type == ND_OPT_DNSSL ||
202 opt->nd_opt_type == ND_OPT_CAPTIVE_PORTAL ||
203 opt->nd_opt_type == ND_OPT_PREF64 ||
204 ndisc_ops_is_useropt(dev, opt->nd_opt_type);
205 }
206
ndisc_next_useropt(const struct net_device * dev,struct nd_opt_hdr * cur,struct nd_opt_hdr * end)207 static struct nd_opt_hdr *ndisc_next_useropt(const struct net_device *dev,
208 struct nd_opt_hdr *cur,
209 struct nd_opt_hdr *end)
210 {
211 if (!cur || !end || cur >= end)
212 return NULL;
213 do {
214 cur = ((void *)cur) + (cur->nd_opt_len << 3);
215 } while (cur < end && !ndisc_is_useropt(dev, cur));
216 return cur <= end && ndisc_is_useropt(dev, cur) ? cur : NULL;
217 }
218
ndisc_parse_options(const struct net_device * dev,u8 * opt,int opt_len,struct ndisc_options * ndopts)219 struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
220 u8 *opt, int opt_len,
221 struct ndisc_options *ndopts)
222 {
223 struct nd_opt_hdr *nd_opt = (struct nd_opt_hdr *)opt;
224
225 if (!nd_opt || opt_len < 0 || !ndopts)
226 return NULL;
227 memset(ndopts, 0, sizeof(*ndopts));
228 while (opt_len) {
229 int l;
230 if (opt_len < sizeof(struct nd_opt_hdr))
231 return NULL;
232 l = nd_opt->nd_opt_len << 3;
233 if (opt_len < l || l == 0)
234 return NULL;
235 if (ndisc_ops_parse_options(dev, nd_opt, ndopts))
236 goto next_opt;
237 switch (nd_opt->nd_opt_type) {
238 case ND_OPT_SOURCE_LL_ADDR:
239 case ND_OPT_TARGET_LL_ADDR:
240 case ND_OPT_MTU:
241 case ND_OPT_NONCE:
242 case ND_OPT_REDIRECT_HDR:
243 if (ndopts->nd_opt_array[nd_opt->nd_opt_type]) {
244 ND_PRINTK(2, warn,
245 "%s: duplicated ND6 option found: type=%d\n",
246 __func__, nd_opt->nd_opt_type);
247 } else {
248 ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
249 }
250 break;
251 case ND_OPT_PREFIX_INFO:
252 ndopts->nd_opts_pi_end = nd_opt;
253 if (!ndopts->nd_opt_array[nd_opt->nd_opt_type])
254 ndopts->nd_opt_array[nd_opt->nd_opt_type] = nd_opt;
255 break;
256 #ifdef CONFIG_IPV6_ROUTE_INFO
257 case ND_OPT_ROUTE_INFO:
258 ndopts->nd_opts_ri_end = nd_opt;
259 if (!ndopts->nd_opts_ri)
260 ndopts->nd_opts_ri = nd_opt;
261 break;
262 #endif
263 default:
264 if (ndisc_is_useropt(dev, nd_opt)) {
265 ndopts->nd_useropts_end = nd_opt;
266 if (!ndopts->nd_useropts)
267 ndopts->nd_useropts = nd_opt;
268 } else {
269 /*
270 * Unknown options must be silently ignored,
271 * to accommodate future extension to the
272 * protocol.
273 */
274 ND_PRINTK(2, notice,
275 "%s: ignored unsupported option; type=%d, len=%d\n",
276 __func__,
277 nd_opt->nd_opt_type,
278 nd_opt->nd_opt_len);
279 }
280 }
281 next_opt:
282 opt_len -= l;
283 nd_opt = ((void *)nd_opt) + l;
284 }
285 return ndopts;
286 }
287
ndisc_mc_map(const struct in6_addr * addr,char * buf,struct net_device * dev,int dir)288 int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir)
289 {
290 switch (dev->type) {
291 case ARPHRD_ETHER:
292 case ARPHRD_IEEE802: /* Not sure. Check it later. --ANK */
293 case ARPHRD_FDDI:
294 ipv6_eth_mc_map(addr, buf);
295 return 0;
296 case ARPHRD_ARCNET:
297 ipv6_arcnet_mc_map(addr, buf);
298 return 0;
299 case ARPHRD_INFINIBAND:
300 ipv6_ib_mc_map(addr, dev->broadcast, buf);
301 return 0;
302 case ARPHRD_IPGRE:
303 return ipv6_ipgre_mc_map(addr, dev->broadcast, buf);
304 default:
305 if (dir) {
306 memcpy(buf, dev->broadcast, dev->addr_len);
307 return 0;
308 }
309 }
310 return -EINVAL;
311 }
312 EXPORT_SYMBOL(ndisc_mc_map);
313
ndisc_hash(const void * pkey,const struct net_device * dev,__u32 * hash_rnd)314 static u32 ndisc_hash(const void *pkey,
315 const struct net_device *dev,
316 __u32 *hash_rnd)
317 {
318 return ndisc_hashfn(pkey, dev, hash_rnd);
319 }
320
ndisc_key_eq(const struct neighbour * n,const void * pkey)321 static bool ndisc_key_eq(const struct neighbour *n, const void *pkey)
322 {
323 return neigh_key_eq128(n, pkey);
324 }
325
ndisc_constructor(struct neighbour * neigh)326 static int ndisc_constructor(struct neighbour *neigh)
327 {
328 struct in6_addr *addr = (struct in6_addr *)&neigh->primary_key;
329 struct net_device *dev = neigh->dev;
330 struct inet6_dev *in6_dev;
331 struct neigh_parms *parms;
332 bool is_multicast = ipv6_addr_is_multicast(addr);
333
334 in6_dev = in6_dev_get(dev);
335 if (!in6_dev) {
336 return -EINVAL;
337 }
338
339 parms = in6_dev->nd_parms;
340 __neigh_parms_put(neigh->parms);
341 neigh->parms = neigh_parms_clone(parms);
342
343 neigh->type = is_multicast ? RTN_MULTICAST : RTN_UNICAST;
344 if (!dev->header_ops) {
345 neigh->nud_state = NUD_NOARP;
346 neigh->ops = &ndisc_direct_ops;
347 neigh->output = neigh_direct_output;
348 } else {
349 if (is_multicast) {
350 neigh->nud_state = NUD_NOARP;
351 ndisc_mc_map(addr, neigh->ha, dev, 1);
352 } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) {
353 neigh->nud_state = NUD_NOARP;
354 memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
355 if (dev->flags&IFF_LOOPBACK)
356 neigh->type = RTN_LOCAL;
357 } else if (dev->flags&IFF_POINTOPOINT) {
358 neigh->nud_state = NUD_NOARP;
359 memcpy(neigh->ha, dev->broadcast, dev->addr_len);
360 }
361 if (dev->header_ops->cache)
362 neigh->ops = &ndisc_hh_ops;
363 else
364 neigh->ops = &ndisc_generic_ops;
365 if (neigh->nud_state&NUD_VALID)
366 neigh->output = neigh->ops->connected_output;
367 else
368 neigh->output = neigh->ops->output;
369 }
370 in6_dev_put(in6_dev);
371 return 0;
372 }
373
pndisc_constructor(struct pneigh_entry * n)374 static int pndisc_constructor(struct pneigh_entry *n)
375 {
376 struct in6_addr *addr = (struct in6_addr *)&n->key;
377 struct in6_addr maddr;
378 struct net_device *dev = n->dev;
379
380 if (!dev || !__in6_dev_get(dev))
381 return -EINVAL;
382 addrconf_addr_solict_mult(addr, &maddr);
383 ipv6_dev_mc_inc(dev, &maddr);
384 return 0;
385 }
386
pndisc_destructor(struct pneigh_entry * n)387 static void pndisc_destructor(struct pneigh_entry *n)
388 {
389 struct in6_addr *addr = (struct in6_addr *)&n->key;
390 struct in6_addr maddr;
391 struct net_device *dev = n->dev;
392
393 if (!dev || !__in6_dev_get(dev))
394 return;
395 addrconf_addr_solict_mult(addr, &maddr);
396 ipv6_dev_mc_dec(dev, &maddr);
397 }
398
399 /* called with rtnl held */
ndisc_allow_add(const struct net_device * dev,struct netlink_ext_ack * extack)400 static bool ndisc_allow_add(const struct net_device *dev,
401 struct netlink_ext_ack *extack)
402 {
403 struct inet6_dev *idev = __in6_dev_get(dev);
404
405 if (!idev || idev->cnf.disable_ipv6) {
406 NL_SET_ERR_MSG(extack, "IPv6 is disabled on this device");
407 return false;
408 }
409
410 return true;
411 }
412
ndisc_alloc_skb(struct net_device * dev,int len)413 static struct sk_buff *ndisc_alloc_skb(struct net_device *dev,
414 int len)
415 {
416 int hlen = LL_RESERVED_SPACE(dev);
417 int tlen = dev->needed_tailroom;
418 struct sock *sk = dev_net(dev)->ipv6.ndisc_sk;
419 struct sk_buff *skb;
420
421 skb = alloc_skb(hlen + sizeof(struct ipv6hdr) + len + tlen, GFP_ATOMIC);
422 if (!skb) {
423 ND_PRINTK(0, err, "ndisc: %s failed to allocate an skb\n",
424 __func__);
425 return NULL;
426 }
427
428 skb->protocol = htons(ETH_P_IPV6);
429 skb->dev = dev;
430
431 skb_reserve(skb, hlen + sizeof(struct ipv6hdr));
432 skb_reset_transport_header(skb);
433
434 /* Manually assign socket ownership as we avoid calling
435 * sock_alloc_send_pskb() to bypass wmem buffer limits
436 */
437 skb_set_owner_w(skb, sk);
438
439 return skb;
440 }
441
ip6_nd_hdr(struct sk_buff * skb,const struct in6_addr * saddr,const struct in6_addr * daddr,int hop_limit,int len)442 static void ip6_nd_hdr(struct sk_buff *skb,
443 const struct in6_addr *saddr,
444 const struct in6_addr *daddr,
445 int hop_limit, int len)
446 {
447 struct ipv6hdr *hdr;
448 struct inet6_dev *idev;
449 unsigned tclass;
450
451 rcu_read_lock();
452 idev = __in6_dev_get(skb->dev);
453 tclass = idev ? idev->cnf.ndisc_tclass : 0;
454 rcu_read_unlock();
455
456 skb_push(skb, sizeof(*hdr));
457 skb_reset_network_header(skb);
458 hdr = ipv6_hdr(skb);
459
460 ip6_flow_hdr(hdr, tclass, 0);
461
462 hdr->payload_len = htons(len);
463 hdr->nexthdr = IPPROTO_ICMPV6;
464 hdr->hop_limit = hop_limit;
465
466 hdr->saddr = *saddr;
467 hdr->daddr = *daddr;
468 }
469
ndisc_send_skb(struct sk_buff * skb,const struct in6_addr * daddr,const struct in6_addr * saddr)470 void ndisc_send_skb(struct sk_buff *skb, const struct in6_addr *daddr,
471 const struct in6_addr *saddr)
472 {
473 struct dst_entry *dst = skb_dst(skb);
474 struct net *net = dev_net(skb->dev);
475 struct sock *sk = net->ipv6.ndisc_sk;
476 struct inet6_dev *idev;
477 int err;
478 struct icmp6hdr *icmp6h = icmp6_hdr(skb);
479 u8 type;
480
481 type = icmp6h->icmp6_type;
482
483 if (!dst) {
484 struct flowi6 fl6;
485 int oif = skb->dev->ifindex;
486
487 icmpv6_flow_init(sk, &fl6, type, saddr, daddr, oif);
488 dst = icmp6_dst_alloc(skb->dev, &fl6);
489 if (IS_ERR(dst)) {
490 kfree_skb(skb);
491 return;
492 }
493
494 skb_dst_set(skb, dst);
495 }
496
497 icmp6h->icmp6_cksum = csum_ipv6_magic(saddr, daddr, skb->len,
498 IPPROTO_ICMPV6,
499 csum_partial(icmp6h,
500 skb->len, 0));
501
502 ip6_nd_hdr(skb, saddr, daddr, inet6_sk(sk)->hop_limit, skb->len);
503
504 rcu_read_lock();
505 idev = __in6_dev_get(dst->dev);
506 IP6_UPD_PO_STATS(net, idev, IPSTATS_MIB_OUT, skb->len);
507
508 err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT,
509 net, sk, skb, NULL, dst->dev,
510 dst_output);
511 if (!err) {
512 ICMP6MSGOUT_INC_STATS(net, idev, type);
513 ICMP6_INC_STATS(net, idev, ICMP6_MIB_OUTMSGS);
514 }
515
516 rcu_read_unlock();
517 }
518 EXPORT_SYMBOL(ndisc_send_skb);
519
ndisc_send_na(struct net_device * dev,const struct in6_addr * daddr,const struct in6_addr * solicited_addr,bool router,bool solicited,bool override,bool inc_opt)520 void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr,
521 const struct in6_addr *solicited_addr,
522 bool router, bool solicited, bool override, bool inc_opt)
523 {
524 struct sk_buff *skb;
525 struct in6_addr tmpaddr;
526 struct inet6_ifaddr *ifp;
527 const struct in6_addr *src_addr;
528 struct nd_msg *msg;
529 int optlen = 0;
530
531 /* for anycast or proxy, solicited_addr != src_addr */
532 ifp = ipv6_get_ifaddr(dev_net(dev), solicited_addr, dev, 1);
533 if (ifp) {
534 src_addr = solicited_addr;
535 if (ifp->flags & IFA_F_OPTIMISTIC)
536 override = false;
537 inc_opt |= ifp->idev->cnf.force_tllao;
538 in6_ifa_put(ifp);
539 } else {
540 if (ipv6_dev_get_saddr(dev_net(dev), dev, daddr,
541 inet6_sk(dev_net(dev)->ipv6.ndisc_sk)->srcprefs,
542 &tmpaddr))
543 return;
544 src_addr = &tmpaddr;
545 }
546
547 if (!dev->addr_len)
548 inc_opt = false;
549 if (inc_opt)
550 optlen += ndisc_opt_addr_space(dev,
551 NDISC_NEIGHBOUR_ADVERTISEMENT);
552
553 skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
554 if (!skb)
555 return;
556
557 msg = skb_put(skb, sizeof(*msg));
558 *msg = (struct nd_msg) {
559 .icmph = {
560 .icmp6_type = NDISC_NEIGHBOUR_ADVERTISEMENT,
561 .icmp6_router = router,
562 .icmp6_solicited = solicited,
563 .icmp6_override = override,
564 },
565 .target = *solicited_addr,
566 };
567
568 if (inc_opt)
569 ndisc_fill_addr_option(skb, ND_OPT_TARGET_LL_ADDR,
570 dev->dev_addr,
571 NDISC_NEIGHBOUR_ADVERTISEMENT);
572
573 ndisc_send_skb(skb, daddr, src_addr);
574 }
575
ndisc_send_unsol_na(struct net_device * dev)576 static void ndisc_send_unsol_na(struct net_device *dev)
577 {
578 struct inet6_dev *idev;
579 struct inet6_ifaddr *ifa;
580
581 idev = in6_dev_get(dev);
582 if (!idev)
583 return;
584
585 read_lock_bh(&idev->lock);
586 list_for_each_entry(ifa, &idev->addr_list, if_list) {
587 /* skip tentative addresses until dad completes */
588 if (ifa->flags & IFA_F_TENTATIVE &&
589 !(ifa->flags & IFA_F_OPTIMISTIC))
590 continue;
591
592 ndisc_send_na(dev, &in6addr_linklocal_allnodes, &ifa->addr,
593 /*router=*/ !!idev->cnf.forwarding,
594 /*solicited=*/ false, /*override=*/ true,
595 /*inc_opt=*/ true);
596 }
597 read_unlock_bh(&idev->lock);
598
599 in6_dev_put(idev);
600 }
601
ndisc_ns_create(struct net_device * dev,const struct in6_addr * solicit,const struct in6_addr * saddr,u64 nonce)602 struct sk_buff *ndisc_ns_create(struct net_device *dev, const struct in6_addr *solicit,
603 const struct in6_addr *saddr, u64 nonce)
604 {
605 int inc_opt = dev->addr_len;
606 struct sk_buff *skb;
607 struct nd_msg *msg;
608 int optlen = 0;
609
610 if (!saddr)
611 return NULL;
612
613 if (ipv6_addr_any(saddr))
614 inc_opt = false;
615 if (inc_opt)
616 optlen += ndisc_opt_addr_space(dev,
617 NDISC_NEIGHBOUR_SOLICITATION);
618 if (nonce != 0)
619 optlen += 8;
620
621 skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
622 if (!skb)
623 return NULL;
624
625 msg = skb_put(skb, sizeof(*msg));
626 *msg = (struct nd_msg) {
627 .icmph = {
628 .icmp6_type = NDISC_NEIGHBOUR_SOLICITATION,
629 },
630 .target = *solicit,
631 };
632
633 if (inc_opt)
634 ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
635 dev->dev_addr,
636 NDISC_NEIGHBOUR_SOLICITATION);
637 if (nonce != 0) {
638 u8 *opt = skb_put(skb, 8);
639
640 opt[0] = ND_OPT_NONCE;
641 opt[1] = 8 >> 3;
642 memcpy(opt + 2, &nonce, 6);
643 }
644
645 return skb;
646 }
647 EXPORT_SYMBOL(ndisc_ns_create);
648
ndisc_send_ns(struct net_device * dev,const struct in6_addr * solicit,const struct in6_addr * daddr,const struct in6_addr * saddr,u64 nonce)649 void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit,
650 const struct in6_addr *daddr, const struct in6_addr *saddr,
651 u64 nonce)
652 {
653 struct in6_addr addr_buf;
654 struct sk_buff *skb;
655
656 if (!saddr) {
657 if (ipv6_get_lladdr(dev, &addr_buf,
658 (IFA_F_TENTATIVE | IFA_F_OPTIMISTIC)))
659 return;
660 saddr = &addr_buf;
661 }
662
663 skb = ndisc_ns_create(dev, solicit, saddr, nonce);
664
665 if (skb)
666 ndisc_send_skb(skb, daddr, saddr);
667 }
668
ndisc_send_rs(struct net_device * dev,const struct in6_addr * saddr,const struct in6_addr * daddr)669 void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr,
670 const struct in6_addr *daddr)
671 {
672 struct sk_buff *skb;
673 struct rs_msg *msg;
674 int send_sllao = dev->addr_len;
675 int optlen = 0;
676
677 #ifdef CONFIG_IPV6_OPTIMISTIC_DAD
678 /*
679 * According to section 2.2 of RFC 4429, we must not
680 * send router solicitations with a sllao from
681 * optimistic addresses, but we may send the solicitation
682 * if we don't include the sllao. So here we check
683 * if our address is optimistic, and if so, we
684 * suppress the inclusion of the sllao.
685 */
686 if (send_sllao) {
687 struct inet6_ifaddr *ifp = ipv6_get_ifaddr(dev_net(dev), saddr,
688 dev, 1);
689 if (ifp) {
690 if (ifp->flags & IFA_F_OPTIMISTIC) {
691 send_sllao = 0;
692 }
693 in6_ifa_put(ifp);
694 } else {
695 send_sllao = 0;
696 }
697 }
698 #endif
699 if (send_sllao)
700 optlen += ndisc_opt_addr_space(dev, NDISC_ROUTER_SOLICITATION);
701
702 skb = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
703 if (!skb)
704 return;
705
706 msg = skb_put(skb, sizeof(*msg));
707 *msg = (struct rs_msg) {
708 .icmph = {
709 .icmp6_type = NDISC_ROUTER_SOLICITATION,
710 },
711 };
712
713 if (send_sllao)
714 ndisc_fill_addr_option(skb, ND_OPT_SOURCE_LL_ADDR,
715 dev->dev_addr,
716 NDISC_ROUTER_SOLICITATION);
717
718 ndisc_send_skb(skb, daddr, saddr);
719 }
720
721
ndisc_error_report(struct neighbour * neigh,struct sk_buff * skb)722 static void ndisc_error_report(struct neighbour *neigh, struct sk_buff *skb)
723 {
724 /*
725 * "The sender MUST return an ICMP
726 * destination unreachable"
727 */
728 dst_link_failure(skb);
729 kfree_skb(skb);
730 }
731
732 /* Called with locked neigh: either read or both */
733
ndisc_solicit(struct neighbour * neigh,struct sk_buff * skb)734 static void ndisc_solicit(struct neighbour *neigh, struct sk_buff *skb)
735 {
736 struct in6_addr *saddr = NULL;
737 struct in6_addr mcaddr;
738 struct net_device *dev = neigh->dev;
739 struct in6_addr *target = (struct in6_addr *)&neigh->primary_key;
740 int probes = atomic_read(&neigh->probes);
741
742 if (skb && ipv6_chk_addr_and_flags(dev_net(dev), &ipv6_hdr(skb)->saddr,
743 dev, false, 1,
744 IFA_F_TENTATIVE|IFA_F_OPTIMISTIC))
745 saddr = &ipv6_hdr(skb)->saddr;
746 probes -= NEIGH_VAR(neigh->parms, UCAST_PROBES);
747 if (probes < 0) {
748 if (!(neigh->nud_state & NUD_VALID)) {
749 ND_PRINTK(1, dbg,
750 "%s: trying to ucast probe in NUD_INVALID: %pI6\n",
751 __func__, target);
752 }
753 ndisc_send_ns(dev, target, target, saddr, 0);
754 } else if ((probes -= NEIGH_VAR(neigh->parms, APP_PROBES)) < 0) {
755 neigh_app_ns(neigh);
756 } else {
757 addrconf_addr_solict_mult(target, &mcaddr);
758 ndisc_send_ns(dev, target, &mcaddr, saddr, 0);
759 }
760 }
761
pndisc_is_router(const void * pkey,struct net_device * dev)762 static int pndisc_is_router(const void *pkey,
763 struct net_device *dev)
764 {
765 struct pneigh_entry *n;
766 int ret = -1;
767
768 read_lock_bh(&nd_tbl.lock);
769 n = __pneigh_lookup(&nd_tbl, dev_net(dev), pkey, dev);
770 if (n)
771 ret = !!(n->flags & NTF_ROUTER);
772 read_unlock_bh(&nd_tbl.lock);
773
774 return ret;
775 }
776
ndisc_update(const struct net_device * dev,struct neighbour * neigh,const u8 * lladdr,u8 new,u32 flags,u8 icmp6_type,struct ndisc_options * ndopts)777 void ndisc_update(const struct net_device *dev, struct neighbour *neigh,
778 const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type,
779 struct ndisc_options *ndopts)
780 {
781 neigh_update(neigh, lladdr, new, flags, 0);
782 /* report ndisc ops about neighbour update */
783 ndisc_ops_update(dev, neigh, flags, icmp6_type, ndopts);
784 }
785
ndisc_recv_ns(struct sk_buff * skb)786 static enum skb_drop_reason ndisc_recv_ns(struct sk_buff *skb)
787 {
788 struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
789 const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
790 const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
791 u8 *lladdr = NULL;
792 u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
793 offsetof(struct nd_msg, opt));
794 struct ndisc_options ndopts;
795 struct net_device *dev = skb->dev;
796 struct inet6_ifaddr *ifp;
797 struct inet6_dev *idev = NULL;
798 struct neighbour *neigh;
799 int dad = ipv6_addr_any(saddr);
800 int is_router = -1;
801 SKB_DR(reason);
802 u64 nonce = 0;
803 bool inc;
804
805 if (skb->len < sizeof(struct nd_msg))
806 return SKB_DROP_REASON_PKT_TOO_SMALL;
807
808 if (ipv6_addr_is_multicast(&msg->target)) {
809 ND_PRINTK(2, warn, "NS: multicast target address\n");
810 return reason;
811 }
812
813 /*
814 * RFC2461 7.1.1:
815 * DAD has to be destined for solicited node multicast address.
816 */
817 if (dad && !ipv6_addr_is_solict_mult(daddr)) {
818 ND_PRINTK(2, warn, "NS: bad DAD packet (wrong destination)\n");
819 return reason;
820 }
821
822 if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts))
823 return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
824
825 if (ndopts.nd_opts_src_lladdr) {
826 lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr, dev);
827 if (!lladdr) {
828 ND_PRINTK(2, warn,
829 "NS: invalid link-layer address length\n");
830 return reason;
831 }
832
833 /* RFC2461 7.1.1:
834 * If the IP source address is the unspecified address,
835 * there MUST NOT be source link-layer address option
836 * in the message.
837 */
838 if (dad) {
839 ND_PRINTK(2, warn,
840 "NS: bad DAD packet (link-layer address option)\n");
841 return reason;
842 }
843 }
844 if (ndopts.nd_opts_nonce && ndopts.nd_opts_nonce->nd_opt_len == 1)
845 memcpy(&nonce, (u8 *)(ndopts.nd_opts_nonce + 1), 6);
846
847 inc = ipv6_addr_is_multicast(daddr);
848
849 ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
850 if (ifp) {
851 have_ifp:
852 if (ifp->flags & (IFA_F_TENTATIVE|IFA_F_OPTIMISTIC)) {
853 if (dad) {
854 if (nonce != 0 && ifp->dad_nonce == nonce) {
855 u8 *np = (u8 *)&nonce;
856 /* Matching nonce if looped back */
857 ND_PRINTK(2, notice,
858 "%s: IPv6 DAD loopback for address %pI6c nonce %pM ignored\n",
859 ifp->idev->dev->name,
860 &ifp->addr, np);
861 goto out;
862 }
863 /*
864 * We are colliding with another node
865 * who is doing DAD
866 * so fail our DAD process
867 */
868 addrconf_dad_failure(skb, ifp);
869 return reason;
870 } else {
871 /*
872 * This is not a dad solicitation.
873 * If we are an optimistic node,
874 * we should respond.
875 * Otherwise, we should ignore it.
876 */
877 if (!(ifp->flags & IFA_F_OPTIMISTIC))
878 goto out;
879 }
880 }
881
882 idev = ifp->idev;
883 } else {
884 struct net *net = dev_net(dev);
885
886 /* perhaps an address on the master device */
887 if (netif_is_l3_slave(dev)) {
888 struct net_device *mdev;
889
890 mdev = netdev_master_upper_dev_get_rcu(dev);
891 if (mdev) {
892 ifp = ipv6_get_ifaddr(net, &msg->target, mdev, 1);
893 if (ifp)
894 goto have_ifp;
895 }
896 }
897
898 idev = in6_dev_get(dev);
899 if (!idev) {
900 /* XXX: count this drop? */
901 return reason;
902 }
903
904 if (ipv6_chk_acast_addr(net, dev, &msg->target) ||
905 (idev->cnf.forwarding &&
906 (net->ipv6.devconf_all->proxy_ndp || idev->cnf.proxy_ndp) &&
907 (is_router = pndisc_is_router(&msg->target, dev)) >= 0)) {
908 if (!(NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED) &&
909 skb->pkt_type != PACKET_HOST &&
910 inc &&
911 NEIGH_VAR(idev->nd_parms, PROXY_DELAY) != 0) {
912 /*
913 * for anycast or proxy,
914 * sender should delay its response
915 * by a random time between 0 and
916 * MAX_ANYCAST_DELAY_TIME seconds.
917 * (RFC2461) -- yoshfuji
918 */
919 struct sk_buff *n = skb_clone(skb, GFP_ATOMIC);
920 if (n)
921 pneigh_enqueue(&nd_tbl, idev->nd_parms, n);
922 goto out;
923 }
924 } else {
925 SKB_DR_SET(reason, IPV6_NDISC_NS_OTHERHOST);
926 goto out;
927 }
928 }
929
930 if (is_router < 0)
931 is_router = idev->cnf.forwarding;
932
933 if (dad) {
934 ndisc_send_na(dev, &in6addr_linklocal_allnodes, &msg->target,
935 !!is_router, false, (ifp != NULL), true);
936 goto out;
937 }
938
939 if (inc)
940 NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_mcast);
941 else
942 NEIGH_CACHE_STAT_INC(&nd_tbl, rcv_probes_ucast);
943
944 /*
945 * update / create cache entry
946 * for the source address
947 */
948 neigh = __neigh_lookup(&nd_tbl, saddr, dev,
949 !inc || lladdr || !dev->addr_len);
950 if (neigh)
951 ndisc_update(dev, neigh, lladdr, NUD_STALE,
952 NEIGH_UPDATE_F_WEAK_OVERRIDE|
953 NEIGH_UPDATE_F_OVERRIDE,
954 NDISC_NEIGHBOUR_SOLICITATION, &ndopts);
955 if (neigh || !dev->header_ops) {
956 ndisc_send_na(dev, saddr, &msg->target, !!is_router,
957 true, (ifp != NULL && inc), inc);
958 if (neigh)
959 neigh_release(neigh);
960 reason = SKB_CONSUMED;
961 }
962
963 out:
964 if (ifp)
965 in6_ifa_put(ifp);
966 else
967 in6_dev_put(idev);
968 return reason;
969 }
970
accept_untracked_na(struct net_device * dev,struct in6_addr * saddr)971 static int accept_untracked_na(struct net_device *dev, struct in6_addr *saddr)
972 {
973 struct inet6_dev *idev = __in6_dev_get(dev);
974
975 switch (idev->cnf.accept_untracked_na) {
976 case 0: /* Don't accept untracked na (absent in neighbor cache) */
977 return 0;
978 case 1: /* Create new entries from na if currently untracked */
979 return 1;
980 case 2: /* Create new entries from untracked na only if saddr is in the
981 * same subnet as an address configured on the interface that
982 * received the na
983 */
984 return !!ipv6_chk_prefix(saddr, dev);
985 default:
986 return 0;
987 }
988 }
989
ndisc_recv_na(struct sk_buff * skb)990 static enum skb_drop_reason ndisc_recv_na(struct sk_buff *skb)
991 {
992 struct nd_msg *msg = (struct nd_msg *)skb_transport_header(skb);
993 struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
994 const struct in6_addr *daddr = &ipv6_hdr(skb)->daddr;
995 u8 *lladdr = NULL;
996 u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
997 offsetof(struct nd_msg, opt));
998 struct ndisc_options ndopts;
999 struct net_device *dev = skb->dev;
1000 struct inet6_dev *idev = __in6_dev_get(dev);
1001 struct inet6_ifaddr *ifp;
1002 struct neighbour *neigh;
1003 SKB_DR(reason);
1004 u8 new_state;
1005
1006 if (skb->len < sizeof(struct nd_msg))
1007 return SKB_DROP_REASON_PKT_TOO_SMALL;
1008
1009 if (ipv6_addr_is_multicast(&msg->target)) {
1010 ND_PRINTK(2, warn, "NA: target address is multicast\n");
1011 return reason;
1012 }
1013
1014 if (ipv6_addr_is_multicast(daddr) &&
1015 msg->icmph.icmp6_solicited) {
1016 ND_PRINTK(2, warn, "NA: solicited NA is multicasted\n");
1017 return reason;
1018 }
1019
1020 /* For some 802.11 wireless deployments (and possibly other networks),
1021 * there will be a NA proxy and unsolicitd packets are attacks
1022 * and thus should not be accepted.
1023 * drop_unsolicited_na takes precedence over accept_untracked_na
1024 */
1025 if (!msg->icmph.icmp6_solicited && idev &&
1026 idev->cnf.drop_unsolicited_na)
1027 return reason;
1028
1029 if (!ndisc_parse_options(dev, msg->opt, ndoptlen, &ndopts))
1030 return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
1031
1032 if (ndopts.nd_opts_tgt_lladdr) {
1033 lladdr = ndisc_opt_addr_data(ndopts.nd_opts_tgt_lladdr, dev);
1034 if (!lladdr) {
1035 ND_PRINTK(2, warn,
1036 "NA: invalid link-layer address length\n");
1037 return reason;
1038 }
1039 }
1040 ifp = ipv6_get_ifaddr(dev_net(dev), &msg->target, dev, 1);
1041 if (ifp) {
1042 if (skb->pkt_type != PACKET_LOOPBACK
1043 && (ifp->flags & IFA_F_TENTATIVE)) {
1044 addrconf_dad_failure(skb, ifp);
1045 return reason;
1046 }
1047 /* What should we make now? The advertisement
1048 is invalid, but ndisc specs say nothing
1049 about it. It could be misconfiguration, or
1050 an smart proxy agent tries to help us :-)
1051
1052 We should not print the error if NA has been
1053 received from loopback - it is just our own
1054 unsolicited advertisement.
1055 */
1056 if (skb->pkt_type != PACKET_LOOPBACK)
1057 ND_PRINTK(1, warn,
1058 "NA: %pM advertised our address %pI6c on %s!\n",
1059 eth_hdr(skb)->h_source, &ifp->addr, ifp->idev->dev->name);
1060 in6_ifa_put(ifp);
1061 return reason;
1062 }
1063
1064 neigh = neigh_lookup(&nd_tbl, &msg->target, dev);
1065
1066 /* RFC 9131 updates original Neighbour Discovery RFC 4861.
1067 * NAs with Target LL Address option without a corresponding
1068 * entry in the neighbour cache can now create a STALE neighbour
1069 * cache entry on routers.
1070 *
1071 * entry accept fwding solicited behaviour
1072 * ------- ------ ------ --------- ----------------------
1073 * present X X 0 Set state to STALE
1074 * present X X 1 Set state to REACHABLE
1075 * absent 0 X X Do nothing
1076 * absent 1 0 X Do nothing
1077 * absent 1 1 X Add a new STALE entry
1078 *
1079 * Note that we don't do a (daddr == all-routers-mcast) check.
1080 */
1081 new_state = msg->icmph.icmp6_solicited ? NUD_REACHABLE : NUD_STALE;
1082 if (!neigh && lladdr && idev && idev->cnf.forwarding) {
1083 if (accept_untracked_na(dev, saddr)) {
1084 neigh = neigh_create(&nd_tbl, &msg->target, dev);
1085 new_state = NUD_STALE;
1086 }
1087 }
1088
1089 if (neigh && !IS_ERR(neigh)) {
1090 u8 old_flags = neigh->flags;
1091 struct net *net = dev_net(dev);
1092
1093 if (neigh->nud_state & NUD_FAILED)
1094 goto out;
1095
1096 /*
1097 * Don't update the neighbor cache entry on a proxy NA from
1098 * ourselves because either the proxied node is off link or it
1099 * has already sent a NA to us.
1100 */
1101 if (lladdr && !memcmp(lladdr, dev->dev_addr, dev->addr_len) &&
1102 net->ipv6.devconf_all->forwarding && net->ipv6.devconf_all->proxy_ndp &&
1103 pneigh_lookup(&nd_tbl, net, &msg->target, dev, 0)) {
1104 /* XXX: idev->cnf.proxy_ndp */
1105 goto out;
1106 }
1107
1108 ndisc_update(dev, neigh, lladdr,
1109 new_state,
1110 NEIGH_UPDATE_F_WEAK_OVERRIDE|
1111 (msg->icmph.icmp6_override ? NEIGH_UPDATE_F_OVERRIDE : 0)|
1112 NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
1113 (msg->icmph.icmp6_router ? NEIGH_UPDATE_F_ISROUTER : 0),
1114 NDISC_NEIGHBOUR_ADVERTISEMENT, &ndopts);
1115
1116 if ((old_flags & ~neigh->flags) & NTF_ROUTER) {
1117 /*
1118 * Change: router to host
1119 */
1120 rt6_clean_tohost(dev_net(dev), saddr);
1121 }
1122 reason = SKB_CONSUMED;
1123 out:
1124 neigh_release(neigh);
1125 }
1126 return reason;
1127 }
1128
ndisc_recv_rs(struct sk_buff * skb)1129 static enum skb_drop_reason ndisc_recv_rs(struct sk_buff *skb)
1130 {
1131 struct rs_msg *rs_msg = (struct rs_msg *)skb_transport_header(skb);
1132 unsigned long ndoptlen = skb->len - sizeof(*rs_msg);
1133 struct neighbour *neigh;
1134 struct inet6_dev *idev;
1135 const struct in6_addr *saddr = &ipv6_hdr(skb)->saddr;
1136 struct ndisc_options ndopts;
1137 u8 *lladdr = NULL;
1138 SKB_DR(reason);
1139
1140 if (skb->len < sizeof(*rs_msg))
1141 return SKB_DROP_REASON_PKT_TOO_SMALL;
1142
1143 idev = __in6_dev_get(skb->dev);
1144 if (!idev) {
1145 ND_PRINTK(1, err, "RS: can't find in6 device\n");
1146 return reason;
1147 }
1148
1149 /* Don't accept RS if we're not in router mode */
1150 if (!idev->cnf.forwarding)
1151 goto out;
1152
1153 /*
1154 * Don't update NCE if src = ::;
1155 * this implies that the source node has no ip address assigned yet.
1156 */
1157 if (ipv6_addr_any(saddr))
1158 goto out;
1159
1160 /* Parse ND options */
1161 if (!ndisc_parse_options(skb->dev, rs_msg->opt, ndoptlen, &ndopts))
1162 return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
1163
1164 if (ndopts.nd_opts_src_lladdr) {
1165 lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
1166 skb->dev);
1167 if (!lladdr)
1168 goto out;
1169 }
1170
1171 neigh = __neigh_lookup(&nd_tbl, saddr, skb->dev, 1);
1172 if (neigh) {
1173 ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
1174 NEIGH_UPDATE_F_WEAK_OVERRIDE|
1175 NEIGH_UPDATE_F_OVERRIDE|
1176 NEIGH_UPDATE_F_OVERRIDE_ISROUTER,
1177 NDISC_ROUTER_SOLICITATION, &ndopts);
1178 neigh_release(neigh);
1179 reason = SKB_CONSUMED;
1180 }
1181 out:
1182 return reason;
1183 }
1184
ndisc_ra_useropt(struct sk_buff * ra,struct nd_opt_hdr * opt)1185 static void ndisc_ra_useropt(struct sk_buff *ra, struct nd_opt_hdr *opt)
1186 {
1187 struct icmp6hdr *icmp6h = (struct icmp6hdr *)skb_transport_header(ra);
1188 struct sk_buff *skb;
1189 struct nlmsghdr *nlh;
1190 struct nduseroptmsg *ndmsg;
1191 struct net *net = dev_net(ra->dev);
1192 int err;
1193 int base_size = NLMSG_ALIGN(sizeof(struct nduseroptmsg)
1194 + (opt->nd_opt_len << 3));
1195 size_t msg_size = base_size + nla_total_size(sizeof(struct in6_addr));
1196
1197 skb = nlmsg_new(msg_size, GFP_ATOMIC);
1198 if (!skb) {
1199 err = -ENOBUFS;
1200 goto errout;
1201 }
1202
1203 nlh = nlmsg_put(skb, 0, 0, RTM_NEWNDUSEROPT, base_size, 0);
1204 if (!nlh) {
1205 goto nla_put_failure;
1206 }
1207
1208 ndmsg = nlmsg_data(nlh);
1209 ndmsg->nduseropt_family = AF_INET6;
1210 ndmsg->nduseropt_ifindex = ra->dev->ifindex;
1211 ndmsg->nduseropt_icmp_type = icmp6h->icmp6_type;
1212 ndmsg->nduseropt_icmp_code = icmp6h->icmp6_code;
1213 ndmsg->nduseropt_opts_len = opt->nd_opt_len << 3;
1214
1215 memcpy(ndmsg + 1, opt, opt->nd_opt_len << 3);
1216
1217 if (nla_put_in6_addr(skb, NDUSEROPT_SRCADDR, &ipv6_hdr(ra)->saddr))
1218 goto nla_put_failure;
1219 nlmsg_end(skb, nlh);
1220
1221 rtnl_notify(skb, net, 0, RTNLGRP_ND_USEROPT, NULL, GFP_ATOMIC);
1222 return;
1223
1224 nla_put_failure:
1225 nlmsg_free(skb);
1226 err = -EMSGSIZE;
1227 errout:
1228 rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err);
1229 }
1230
ndisc_router_discovery(struct sk_buff * skb)1231 static enum skb_drop_reason ndisc_router_discovery(struct sk_buff *skb)
1232 {
1233 struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
1234 bool send_ifinfo_notify = false;
1235 struct neighbour *neigh = NULL;
1236 struct ndisc_options ndopts;
1237 struct fib6_info *rt = NULL;
1238 struct inet6_dev *in6_dev;
1239 u32 defrtr_usr_metric;
1240 unsigned int pref = 0;
1241 __u32 old_if_flags;
1242 struct net *net;
1243 SKB_DR(reason);
1244 int lifetime;
1245 int optlen;
1246
1247 __u8 *opt = (__u8 *)(ra_msg + 1);
1248
1249 optlen = (skb_tail_pointer(skb) - skb_transport_header(skb)) -
1250 sizeof(struct ra_msg);
1251
1252 ND_PRINTK(2, info,
1253 "RA: %s, dev: %s\n",
1254 __func__, skb->dev->name);
1255 if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
1256 ND_PRINTK(2, warn, "RA: source address is not link-local\n");
1257 return reason;
1258 }
1259 if (optlen < 0)
1260 return SKB_DROP_REASON_PKT_TOO_SMALL;
1261
1262 #ifdef CONFIG_IPV6_NDISC_NODETYPE
1263 if (skb->ndisc_nodetype == NDISC_NODETYPE_HOST) {
1264 ND_PRINTK(2, warn, "RA: from host or unauthorized router\n");
1265 return reason;
1266 }
1267 #endif
1268
1269 /*
1270 * set the RA_RECV flag in the interface
1271 */
1272
1273 in6_dev = __in6_dev_get(skb->dev);
1274 if (!in6_dev) {
1275 ND_PRINTK(0, err, "RA: can't find inet6 device for %s\n",
1276 skb->dev->name);
1277 return reason;
1278 }
1279
1280 if (!ndisc_parse_options(skb->dev, opt, optlen, &ndopts))
1281 return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
1282
1283 if (!ipv6_accept_ra(in6_dev)) {
1284 ND_PRINTK(2, info,
1285 "RA: %s, did not accept ra for dev: %s\n",
1286 __func__, skb->dev->name);
1287 goto skip_linkparms;
1288 }
1289
1290 #ifdef CONFIG_IPV6_NDISC_NODETYPE
1291 /* skip link-specific parameters from interior routers */
1292 if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) {
1293 ND_PRINTK(2, info,
1294 "RA: %s, nodetype is NODEFAULT, dev: %s\n",
1295 __func__, skb->dev->name);
1296 goto skip_linkparms;
1297 }
1298 #endif
1299
1300 if (in6_dev->if_flags & IF_RS_SENT) {
1301 /*
1302 * flag that an RA was received after an RS was sent
1303 * out on this interface.
1304 */
1305 in6_dev->if_flags |= IF_RA_RCVD;
1306 }
1307
1308 /*
1309 * Remember the managed/otherconf flags from most recently
1310 * received RA message (RFC 2462) -- yoshfuji
1311 */
1312 old_if_flags = in6_dev->if_flags;
1313 in6_dev->if_flags = (in6_dev->if_flags & ~(IF_RA_MANAGED |
1314 IF_RA_OTHERCONF)) |
1315 (ra_msg->icmph.icmp6_addrconf_managed ?
1316 IF_RA_MANAGED : 0) |
1317 (ra_msg->icmph.icmp6_addrconf_other ?
1318 IF_RA_OTHERCONF : 0);
1319
1320 if (old_if_flags != in6_dev->if_flags)
1321 send_ifinfo_notify = true;
1322
1323 if (!in6_dev->cnf.accept_ra_defrtr) {
1324 ND_PRINTK(2, info,
1325 "RA: %s, defrtr is false for dev: %s\n",
1326 __func__, skb->dev->name);
1327 goto skip_defrtr;
1328 }
1329
1330 /* Do not accept RA with source-addr found on local machine unless
1331 * accept_ra_from_local is set to true.
1332 */
1333 net = dev_net(in6_dev->dev);
1334 if (!in6_dev->cnf.accept_ra_from_local &&
1335 ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) {
1336 ND_PRINTK(2, info,
1337 "RA from local address detected on dev: %s: default router ignored\n",
1338 skb->dev->name);
1339 goto skip_defrtr;
1340 }
1341
1342 lifetime = ntohs(ra_msg->icmph.icmp6_rt_lifetime);
1343
1344 #ifdef CONFIG_IPV6_ROUTER_PREF
1345 pref = ra_msg->icmph.icmp6_router_pref;
1346 /* 10b is handled as if it were 00b (medium) */
1347 if (pref == ICMPV6_ROUTER_PREF_INVALID ||
1348 !in6_dev->cnf.accept_ra_rtr_pref)
1349 pref = ICMPV6_ROUTER_PREF_MEDIUM;
1350 #endif
1351 /* routes added from RAs do not use nexthop objects */
1352 rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
1353 if (rt) {
1354 neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6,
1355 rt->fib6_nh->fib_nh_dev, NULL,
1356 &ipv6_hdr(skb)->saddr);
1357 if (!neigh) {
1358 ND_PRINTK(0, err,
1359 "RA: %s got default router without neighbour\n",
1360 __func__);
1361 fib6_info_release(rt);
1362 return reason;
1363 }
1364 }
1365 /* Set default route metric as specified by user */
1366 defrtr_usr_metric = in6_dev->cnf.ra_defrtr_metric;
1367 /* delete the route if lifetime is 0 or if metric needs change */
1368 if (rt && (lifetime == 0 || rt->fib6_metric != defrtr_usr_metric)) {
1369 ip6_del_rt(net, rt, false);
1370 rt = NULL;
1371 }
1372
1373 ND_PRINTK(3, info, "RA: rt: %p lifetime: %d, metric: %d, for dev: %s\n",
1374 rt, lifetime, defrtr_usr_metric, skb->dev->name);
1375 if (!rt && lifetime) {
1376 ND_PRINTK(3, info, "RA: adding default router\n");
1377
1378 if (neigh)
1379 neigh_release(neigh);
1380
1381 rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr,
1382 skb->dev, pref, defrtr_usr_metric);
1383 if (!rt) {
1384 ND_PRINTK(0, err,
1385 "RA: %s failed to add default route\n",
1386 __func__);
1387 return reason;
1388 }
1389
1390 neigh = ip6_neigh_lookup(&rt->fib6_nh->fib_nh_gw6,
1391 rt->fib6_nh->fib_nh_dev, NULL,
1392 &ipv6_hdr(skb)->saddr);
1393 if (!neigh) {
1394 ND_PRINTK(0, err,
1395 "RA: %s got default router without neighbour\n",
1396 __func__);
1397 fib6_info_release(rt);
1398 return reason;
1399 }
1400 neigh->flags |= NTF_ROUTER;
1401 } else if (rt && IPV6_EXTRACT_PREF(rt->fib6_flags) != pref) {
1402 struct nl_info nlinfo = {
1403 .nl_net = net,
1404 };
1405 rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref);
1406 inet6_rt_notify(RTM_NEWROUTE, rt, &nlinfo, NLM_F_REPLACE);
1407 }
1408
1409 if (rt)
1410 fib6_set_expires(rt, jiffies + (HZ * lifetime));
1411 if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
1412 ra_msg->icmph.icmp6_hop_limit) {
1413 if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
1414 in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
1415 fib6_metric_set(rt, RTAX_HOPLIMIT,
1416 ra_msg->icmph.icmp6_hop_limit);
1417 } else {
1418 ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
1419 }
1420 }
1421
1422 skip_defrtr:
1423
1424 /*
1425 * Update Reachable Time and Retrans Timer
1426 */
1427
1428 if (in6_dev->nd_parms) {
1429 unsigned long rtime = ntohl(ra_msg->retrans_timer);
1430
1431 if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/HZ) {
1432 rtime = (rtime*HZ)/1000;
1433 if (rtime < HZ/100)
1434 rtime = HZ/100;
1435 NEIGH_VAR_SET(in6_dev->nd_parms, RETRANS_TIME, rtime);
1436 in6_dev->tstamp = jiffies;
1437 send_ifinfo_notify = true;
1438 }
1439
1440 rtime = ntohl(ra_msg->reachable_time);
1441 if (rtime && rtime/1000 < MAX_SCHEDULE_TIMEOUT/(3*HZ)) {
1442 rtime = (rtime*HZ)/1000;
1443
1444 if (rtime < HZ/10)
1445 rtime = HZ/10;
1446
1447 if (rtime != NEIGH_VAR(in6_dev->nd_parms, BASE_REACHABLE_TIME)) {
1448 NEIGH_VAR_SET(in6_dev->nd_parms,
1449 BASE_REACHABLE_TIME, rtime);
1450 NEIGH_VAR_SET(in6_dev->nd_parms,
1451 GC_STALETIME, 3 * rtime);
1452 in6_dev->nd_parms->reachable_time = neigh_rand_reach_time(rtime);
1453 in6_dev->tstamp = jiffies;
1454 send_ifinfo_notify = true;
1455 }
1456 }
1457 }
1458
1459 skip_linkparms:
1460
1461 /*
1462 * Process options.
1463 */
1464
1465 if (!neigh)
1466 neigh = __neigh_lookup(&nd_tbl, &ipv6_hdr(skb)->saddr,
1467 skb->dev, 1);
1468 if (neigh) {
1469 u8 *lladdr = NULL;
1470 if (ndopts.nd_opts_src_lladdr) {
1471 lladdr = ndisc_opt_addr_data(ndopts.nd_opts_src_lladdr,
1472 skb->dev);
1473 if (!lladdr) {
1474 ND_PRINTK(2, warn,
1475 "RA: invalid link-layer address length\n");
1476 goto out;
1477 }
1478 }
1479 ndisc_update(skb->dev, neigh, lladdr, NUD_STALE,
1480 NEIGH_UPDATE_F_WEAK_OVERRIDE|
1481 NEIGH_UPDATE_F_OVERRIDE|
1482 NEIGH_UPDATE_F_OVERRIDE_ISROUTER|
1483 NEIGH_UPDATE_F_ISROUTER,
1484 NDISC_ROUTER_ADVERTISEMENT, &ndopts);
1485 reason = SKB_CONSUMED;
1486 }
1487
1488 if (!ipv6_accept_ra(in6_dev)) {
1489 ND_PRINTK(2, info,
1490 "RA: %s, accept_ra is false for dev: %s\n",
1491 __func__, skb->dev->name);
1492 goto out;
1493 }
1494
1495 #ifdef CONFIG_IPV6_ROUTE_INFO
1496 if (!in6_dev->cnf.accept_ra_from_local &&
1497 ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
1498 in6_dev->dev, 0)) {
1499 ND_PRINTK(2, info,
1500 "RA from local address detected on dev: %s: router info ignored.\n",
1501 skb->dev->name);
1502 goto skip_routeinfo;
1503 }
1504
1505 if (in6_dev->cnf.accept_ra_rtr_pref && ndopts.nd_opts_ri) {
1506 struct nd_opt_hdr *p;
1507 for (p = ndopts.nd_opts_ri;
1508 p;
1509 p = ndisc_next_option(p, ndopts.nd_opts_ri_end)) {
1510 struct route_info *ri = (struct route_info *)p;
1511 #ifdef CONFIG_IPV6_NDISC_NODETYPE
1512 if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT &&
1513 ri->prefix_len == 0)
1514 continue;
1515 #endif
1516 if (ri->prefix_len == 0 &&
1517 !in6_dev->cnf.accept_ra_defrtr)
1518 continue;
1519 if (ri->prefix_len < in6_dev->cnf.accept_ra_rt_info_min_plen)
1520 continue;
1521 if (ri->prefix_len > in6_dev->cnf.accept_ra_rt_info_max_plen)
1522 continue;
1523 rt6_route_rcv(skb->dev, (u8 *)p, (p->nd_opt_len) << 3,
1524 &ipv6_hdr(skb)->saddr);
1525 }
1526 }
1527
1528 skip_routeinfo:
1529 #endif
1530
1531 #ifdef CONFIG_IPV6_NDISC_NODETYPE
1532 /* skip link-specific ndopts from interior routers */
1533 if (skb->ndisc_nodetype == NDISC_NODETYPE_NODEFAULT) {
1534 ND_PRINTK(2, info,
1535 "RA: %s, nodetype is NODEFAULT (interior routes), dev: %s\n",
1536 __func__, skb->dev->name);
1537 goto out;
1538 }
1539 #endif
1540
1541 if (in6_dev->cnf.accept_ra_pinfo && ndopts.nd_opts_pi) {
1542 struct nd_opt_hdr *p;
1543 for (p = ndopts.nd_opts_pi;
1544 p;
1545 p = ndisc_next_option(p, ndopts.nd_opts_pi_end)) {
1546 addrconf_prefix_rcv(skb->dev, (u8 *)p,
1547 (p->nd_opt_len) << 3,
1548 ndopts.nd_opts_src_lladdr != NULL);
1549 }
1550 }
1551
1552 if (ndopts.nd_opts_mtu && in6_dev->cnf.accept_ra_mtu) {
1553 __be32 n;
1554 u32 mtu;
1555
1556 memcpy(&n, ((u8 *)(ndopts.nd_opts_mtu+1))+2, sizeof(mtu));
1557 mtu = ntohl(n);
1558
1559 if (in6_dev->ra_mtu != mtu) {
1560 in6_dev->ra_mtu = mtu;
1561 send_ifinfo_notify = true;
1562 }
1563
1564 if (mtu < IPV6_MIN_MTU || mtu > skb->dev->mtu) {
1565 ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu);
1566 } else if (in6_dev->cnf.mtu6 != mtu) {
1567 in6_dev->cnf.mtu6 = mtu;
1568 fib6_metric_set(rt, RTAX_MTU, mtu);
1569 rt6_mtu_change(skb->dev, mtu);
1570 }
1571 }
1572
1573 if (ndopts.nd_useropts) {
1574 struct nd_opt_hdr *p;
1575 for (p = ndopts.nd_useropts;
1576 p;
1577 p = ndisc_next_useropt(skb->dev, p,
1578 ndopts.nd_useropts_end)) {
1579 ndisc_ra_useropt(skb, p);
1580 }
1581 }
1582
1583 if (ndopts.nd_opts_tgt_lladdr || ndopts.nd_opts_rh) {
1584 ND_PRINTK(2, warn, "RA: invalid RA options\n");
1585 }
1586 out:
1587 /* Send a notify if RA changed managed/otherconf flags or
1588 * timer settings or ra_mtu value
1589 */
1590 if (send_ifinfo_notify)
1591 inet6_ifinfo_notify(RTM_NEWLINK, in6_dev);
1592
1593 fib6_info_release(rt);
1594 if (neigh)
1595 neigh_release(neigh);
1596 return reason;
1597 }
1598
ndisc_redirect_rcv(struct sk_buff * skb)1599 static enum skb_drop_reason ndisc_redirect_rcv(struct sk_buff *skb)
1600 {
1601 struct rd_msg *msg = (struct rd_msg *)skb_transport_header(skb);
1602 u32 ndoptlen = skb_tail_pointer(skb) - (skb_transport_header(skb) +
1603 offsetof(struct rd_msg, opt));
1604 struct ndisc_options ndopts;
1605 SKB_DR(reason);
1606 u8 *hdr;
1607
1608 #ifdef CONFIG_IPV6_NDISC_NODETYPE
1609 switch (skb->ndisc_nodetype) {
1610 case NDISC_NODETYPE_HOST:
1611 case NDISC_NODETYPE_NODEFAULT:
1612 ND_PRINTK(2, warn,
1613 "Redirect: from host or unauthorized router\n");
1614 return reason;
1615 }
1616 #endif
1617
1618 if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) {
1619 ND_PRINTK(2, warn,
1620 "Redirect: source address is not link-local\n");
1621 return reason;
1622 }
1623
1624 if (!ndisc_parse_options(skb->dev, msg->opt, ndoptlen, &ndopts))
1625 return SKB_DROP_REASON_IPV6_NDISC_BAD_OPTIONS;
1626
1627 if (!ndopts.nd_opts_rh) {
1628 ip6_redirect_no_header(skb, dev_net(skb->dev),
1629 skb->dev->ifindex);
1630 return reason;
1631 }
1632
1633 hdr = (u8 *)ndopts.nd_opts_rh;
1634 hdr += 8;
1635 if (!pskb_pull(skb, hdr - skb_transport_header(skb)))
1636 return SKB_DROP_REASON_PKT_TOO_SMALL;
1637
1638 return icmpv6_notify(skb, NDISC_REDIRECT, 0, 0);
1639 }
1640
ndisc_fill_redirect_hdr_option(struct sk_buff * skb,struct sk_buff * orig_skb,int rd_len)1641 static void ndisc_fill_redirect_hdr_option(struct sk_buff *skb,
1642 struct sk_buff *orig_skb,
1643 int rd_len)
1644 {
1645 u8 *opt = skb_put(skb, rd_len);
1646
1647 memset(opt, 0, 8);
1648 *(opt++) = ND_OPT_REDIRECT_HDR;
1649 *(opt++) = (rd_len >> 3);
1650 opt += 6;
1651
1652 skb_copy_bits(orig_skb, skb_network_offset(orig_skb), opt,
1653 rd_len - 8);
1654 }
1655
ndisc_send_redirect(struct sk_buff * skb,const struct in6_addr * target)1656 void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target)
1657 {
1658 struct net_device *dev = skb->dev;
1659 struct net *net = dev_net(dev);
1660 struct sock *sk = net->ipv6.ndisc_sk;
1661 int optlen = 0;
1662 struct inet_peer *peer;
1663 struct sk_buff *buff;
1664 struct rd_msg *msg;
1665 struct in6_addr saddr_buf;
1666 struct rt6_info *rt;
1667 struct dst_entry *dst;
1668 struct flowi6 fl6;
1669 int rd_len;
1670 u8 ha_buf[MAX_ADDR_LEN], *ha = NULL,
1671 ops_data_buf[NDISC_OPS_REDIRECT_DATA_SPACE], *ops_data = NULL;
1672 bool ret;
1673
1674 if (netif_is_l3_master(skb->dev)) {
1675 dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif);
1676 if (!dev)
1677 return;
1678 }
1679
1680 if (ipv6_get_lladdr(dev, &saddr_buf, IFA_F_TENTATIVE)) {
1681 ND_PRINTK(2, warn, "Redirect: no link-local address on %s\n",
1682 dev->name);
1683 return;
1684 }
1685
1686 if (!ipv6_addr_equal(&ipv6_hdr(skb)->daddr, target) &&
1687 ipv6_addr_type(target) != (IPV6_ADDR_UNICAST|IPV6_ADDR_LINKLOCAL)) {
1688 ND_PRINTK(2, warn,
1689 "Redirect: target address is not link-local unicast\n");
1690 return;
1691 }
1692
1693 icmpv6_flow_init(sk, &fl6, NDISC_REDIRECT,
1694 &saddr_buf, &ipv6_hdr(skb)->saddr, dev->ifindex);
1695
1696 dst = ip6_route_output(net, NULL, &fl6);
1697 if (dst->error) {
1698 dst_release(dst);
1699 return;
1700 }
1701 dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
1702 if (IS_ERR(dst))
1703 return;
1704
1705 rt = (struct rt6_info *) dst;
1706
1707 if (rt->rt6i_flags & RTF_GATEWAY) {
1708 ND_PRINTK(2, warn,
1709 "Redirect: destination is not a neighbour\n");
1710 goto release;
1711 }
1712 peer = inet_getpeer_v6(net->ipv6.peers, &ipv6_hdr(skb)->saddr, 1);
1713 ret = inet_peer_xrlim_allow(peer, 1*HZ);
1714 if (peer)
1715 inet_putpeer(peer);
1716 if (!ret)
1717 goto release;
1718
1719 if (dev->addr_len) {
1720 struct neighbour *neigh = dst_neigh_lookup(skb_dst(skb), target);
1721 if (!neigh) {
1722 ND_PRINTK(2, warn,
1723 "Redirect: no neigh for target address\n");
1724 goto release;
1725 }
1726
1727 read_lock_bh(&neigh->lock);
1728 if (neigh->nud_state & NUD_VALID) {
1729 memcpy(ha_buf, neigh->ha, dev->addr_len);
1730 read_unlock_bh(&neigh->lock);
1731 ha = ha_buf;
1732 optlen += ndisc_redirect_opt_addr_space(dev, neigh,
1733 ops_data_buf,
1734 &ops_data);
1735 } else
1736 read_unlock_bh(&neigh->lock);
1737
1738 neigh_release(neigh);
1739 }
1740
1741 rd_len = min_t(unsigned int,
1742 IPV6_MIN_MTU - sizeof(struct ipv6hdr) - sizeof(*msg) - optlen,
1743 skb->len + 8);
1744 rd_len &= ~0x7;
1745 optlen += rd_len;
1746
1747 buff = ndisc_alloc_skb(dev, sizeof(*msg) + optlen);
1748 if (!buff)
1749 goto release;
1750
1751 msg = skb_put(buff, sizeof(*msg));
1752 *msg = (struct rd_msg) {
1753 .icmph = {
1754 .icmp6_type = NDISC_REDIRECT,
1755 },
1756 .target = *target,
1757 .dest = ipv6_hdr(skb)->daddr,
1758 };
1759
1760 /*
1761 * include target_address option
1762 */
1763
1764 if (ha)
1765 ndisc_fill_redirect_addr_option(buff, ha, ops_data);
1766
1767 /*
1768 * build redirect option and copy skb over to the new packet.
1769 */
1770
1771 if (rd_len)
1772 ndisc_fill_redirect_hdr_option(buff, skb, rd_len);
1773
1774 skb_dst_set(buff, dst);
1775 ndisc_send_skb(buff, &ipv6_hdr(skb)->saddr, &saddr_buf);
1776 return;
1777
1778 release:
1779 dst_release(dst);
1780 }
1781
pndisc_redo(struct sk_buff * skb)1782 static void pndisc_redo(struct sk_buff *skb)
1783 {
1784 enum skb_drop_reason reason = ndisc_recv_ns(skb);
1785
1786 kfree_skb_reason(skb, reason);
1787 }
1788
ndisc_is_multicast(const void * pkey)1789 static int ndisc_is_multicast(const void *pkey)
1790 {
1791 return ipv6_addr_is_multicast((struct in6_addr *)pkey);
1792 }
1793
ndisc_suppress_frag_ndisc(struct sk_buff * skb)1794 static bool ndisc_suppress_frag_ndisc(struct sk_buff *skb)
1795 {
1796 struct inet6_dev *idev = __in6_dev_get(skb->dev);
1797
1798 if (!idev)
1799 return true;
1800 if (IP6CB(skb)->flags & IP6SKB_FRAGMENTED &&
1801 idev->cnf.suppress_frag_ndisc) {
1802 net_warn_ratelimited("Received fragmented ndisc packet. Carefully consider disabling suppress_frag_ndisc.\n");
1803 return true;
1804 }
1805 return false;
1806 }
1807
ndisc_rcv(struct sk_buff * skb)1808 enum skb_drop_reason ndisc_rcv(struct sk_buff *skb)
1809 {
1810 struct nd_msg *msg;
1811 SKB_DR(reason);
1812
1813 if (ndisc_suppress_frag_ndisc(skb))
1814 return SKB_DROP_REASON_IPV6_NDISC_FRAG;
1815
1816 if (skb_linearize(skb))
1817 return SKB_DROP_REASON_NOMEM;
1818
1819 msg = (struct nd_msg *)skb_transport_header(skb);
1820
1821 __skb_push(skb, skb->data - skb_transport_header(skb));
1822
1823 if (ipv6_hdr(skb)->hop_limit != 255) {
1824 ND_PRINTK(2, warn, "NDISC: invalid hop-limit: %d\n",
1825 ipv6_hdr(skb)->hop_limit);
1826 return SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT;
1827 }
1828
1829 if (msg->icmph.icmp6_code != 0) {
1830 ND_PRINTK(2, warn, "NDISC: invalid ICMPv6 code: %d\n",
1831 msg->icmph.icmp6_code);
1832 return SKB_DROP_REASON_IPV6_NDISC_BAD_CODE;
1833 }
1834
1835 switch (msg->icmph.icmp6_type) {
1836 case NDISC_NEIGHBOUR_SOLICITATION:
1837 memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
1838 reason = ndisc_recv_ns(skb);
1839 break;
1840
1841 case NDISC_NEIGHBOUR_ADVERTISEMENT:
1842 reason = ndisc_recv_na(skb);
1843 break;
1844
1845 case NDISC_ROUTER_SOLICITATION:
1846 reason = ndisc_recv_rs(skb);
1847 break;
1848
1849 case NDISC_ROUTER_ADVERTISEMENT:
1850 reason = ndisc_router_discovery(skb);
1851 break;
1852
1853 case NDISC_REDIRECT:
1854 reason = ndisc_redirect_rcv(skb);
1855 break;
1856 }
1857
1858 return reason;
1859 }
1860
ndisc_netdev_event(struct notifier_block * this,unsigned long event,void * ptr)1861 static int ndisc_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
1862 {
1863 struct net_device *dev = netdev_notifier_info_to_dev(ptr);
1864 struct netdev_notifier_change_info *change_info;
1865 struct net *net = dev_net(dev);
1866 struct inet6_dev *idev;
1867 bool evict_nocarrier;
1868
1869 switch (event) {
1870 case NETDEV_CHANGEADDR:
1871 neigh_changeaddr(&nd_tbl, dev);
1872 fib6_run_gc(0, net, false);
1873 fallthrough;
1874 case NETDEV_UP:
1875 idev = in6_dev_get(dev);
1876 if (!idev)
1877 break;
1878 if (idev->cnf.ndisc_notify ||
1879 net->ipv6.devconf_all->ndisc_notify)
1880 ndisc_send_unsol_na(dev);
1881 in6_dev_put(idev);
1882 break;
1883 case NETDEV_CHANGE:
1884 idev = in6_dev_get(dev);
1885 if (!idev)
1886 evict_nocarrier = true;
1887 else {
1888 evict_nocarrier = idev->cnf.ndisc_evict_nocarrier &&
1889 net->ipv6.devconf_all->ndisc_evict_nocarrier;
1890 in6_dev_put(idev);
1891 }
1892
1893 change_info = ptr;
1894 if (change_info->flags_changed & IFF_NOARP)
1895 neigh_changeaddr(&nd_tbl, dev);
1896 if (evict_nocarrier && !netif_carrier_ok(dev))
1897 neigh_carrier_down(&nd_tbl, dev);
1898 break;
1899 case NETDEV_DOWN:
1900 neigh_ifdown(&nd_tbl, dev);
1901 fib6_run_gc(0, net, false);
1902 break;
1903 case NETDEV_NOTIFY_PEERS:
1904 ndisc_send_unsol_na(dev);
1905 break;
1906 default:
1907 break;
1908 }
1909
1910 return NOTIFY_DONE;
1911 }
1912
1913 static struct notifier_block ndisc_netdev_notifier = {
1914 .notifier_call = ndisc_netdev_event,
1915 .priority = ADDRCONF_NOTIFY_PRIORITY - 5,
1916 };
1917
1918 #ifdef CONFIG_SYSCTL
ndisc_warn_deprecated_sysctl(struct ctl_table * ctl,const char * func,const char * dev_name)1919 static void ndisc_warn_deprecated_sysctl(struct ctl_table *ctl,
1920 const char *func, const char *dev_name)
1921 {
1922 static char warncomm[TASK_COMM_LEN];
1923 static int warned;
1924 if (strcmp(warncomm, current->comm) && warned < 5) {
1925 strcpy(warncomm, current->comm);
1926 pr_warn("process `%s' is using deprecated sysctl (%s) net.ipv6.neigh.%s.%s - use net.ipv6.neigh.%s.%s_ms instead\n",
1927 warncomm, func,
1928 dev_name, ctl->procname,
1929 dev_name, ctl->procname);
1930 warned++;
1931 }
1932 }
1933
ndisc_ifinfo_sysctl_change(struct ctl_table * ctl,int write,void * buffer,size_t * lenp,loff_t * ppos)1934 int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void *buffer,
1935 size_t *lenp, loff_t *ppos)
1936 {
1937 struct net_device *dev = ctl->extra1;
1938 struct inet6_dev *idev;
1939 int ret;
1940
1941 if ((strcmp(ctl->procname, "retrans_time") == 0) ||
1942 (strcmp(ctl->procname, "base_reachable_time") == 0))
1943 ndisc_warn_deprecated_sysctl(ctl, "syscall", dev ? dev->name : "default");
1944
1945 if (strcmp(ctl->procname, "retrans_time") == 0)
1946 ret = neigh_proc_dointvec(ctl, write, buffer, lenp, ppos);
1947
1948 else if (strcmp(ctl->procname, "base_reachable_time") == 0)
1949 ret = neigh_proc_dointvec_jiffies(ctl, write,
1950 buffer, lenp, ppos);
1951
1952 else if ((strcmp(ctl->procname, "retrans_time_ms") == 0) ||
1953 (strcmp(ctl->procname, "base_reachable_time_ms") == 0))
1954 ret = neigh_proc_dointvec_ms_jiffies(ctl, write,
1955 buffer, lenp, ppos);
1956 else
1957 ret = -1;
1958
1959 if (write && ret == 0 && dev && (idev = in6_dev_get(dev)) != NULL) {
1960 if (ctl->data == &NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME))
1961 idev->nd_parms->reachable_time =
1962 neigh_rand_reach_time(NEIGH_VAR(idev->nd_parms, BASE_REACHABLE_TIME));
1963 idev->tstamp = jiffies;
1964 inet6_ifinfo_notify(RTM_NEWLINK, idev);
1965 in6_dev_put(idev);
1966 }
1967 return ret;
1968 }
1969
1970
1971 #endif
1972
ndisc_net_init(struct net * net)1973 static int __net_init ndisc_net_init(struct net *net)
1974 {
1975 struct ipv6_pinfo *np;
1976 struct sock *sk;
1977 int err;
1978
1979 err = inet_ctl_sock_create(&sk, PF_INET6,
1980 SOCK_RAW, IPPROTO_ICMPV6, net);
1981 if (err < 0) {
1982 ND_PRINTK(0, err,
1983 "NDISC: Failed to initialize the control socket (err %d)\n",
1984 err);
1985 return err;
1986 }
1987
1988 net->ipv6.ndisc_sk = sk;
1989
1990 np = inet6_sk(sk);
1991 np->hop_limit = 255;
1992 /* Do not loopback ndisc messages */
1993 np->mc_loop = 0;
1994
1995 return 0;
1996 }
1997
ndisc_net_exit(struct net * net)1998 static void __net_exit ndisc_net_exit(struct net *net)
1999 {
2000 inet_ctl_sock_destroy(net->ipv6.ndisc_sk);
2001 }
2002
2003 static struct pernet_operations ndisc_net_ops = {
2004 .init = ndisc_net_init,
2005 .exit = ndisc_net_exit,
2006 };
2007
ndisc_init(void)2008 int __init ndisc_init(void)
2009 {
2010 int err;
2011
2012 err = register_pernet_subsys(&ndisc_net_ops);
2013 if (err)
2014 return err;
2015 /*
2016 * Initialize the neighbour table
2017 */
2018 neigh_table_init(NEIGH_ND_TABLE, &nd_tbl);
2019
2020 #ifdef CONFIG_SYSCTL
2021 err = neigh_sysctl_register(NULL, &nd_tbl.parms,
2022 ndisc_ifinfo_sysctl_change);
2023 if (err)
2024 goto out_unregister_pernet;
2025 out:
2026 #endif
2027 return err;
2028
2029 #ifdef CONFIG_SYSCTL
2030 out_unregister_pernet:
2031 unregister_pernet_subsys(&ndisc_net_ops);
2032 goto out;
2033 #endif
2034 }
2035
ndisc_late_init(void)2036 int __init ndisc_late_init(void)
2037 {
2038 return register_netdevice_notifier(&ndisc_netdev_notifier);
2039 }
2040
ndisc_late_cleanup(void)2041 void ndisc_late_cleanup(void)
2042 {
2043 unregister_netdevice_notifier(&ndisc_netdev_notifier);
2044 }
2045
ndisc_cleanup(void)2046 void ndisc_cleanup(void)
2047 {
2048 #ifdef CONFIG_SYSCTL
2049 neigh_sysctl_unregister(&nd_tbl.parms);
2050 #endif
2051 neigh_table_clear(NEIGH_ND_TABLE, &nd_tbl);
2052 unregister_pernet_subsys(&ndisc_net_ops);
2053 }
2054