1 // SPDX-License-Identifier: GPL-2.0-or-later
2 /*
3 * NET3: Implementation of the ICMP protocol layer.
4 *
5 * Alan Cox, <alan@lxorguk.ukuu.org.uk>
6 *
7 * Some of the function names and the icmp unreach table for this
8 * module were derived from [icmp.c 1.0.11 06/02/93] by
9 * Ross Biro, Fred N. van Kempen, Mark Evans, Alan Cox, Gerhard Koerting.
10 * Other than that this module is a complete rewrite.
11 *
12 * Fixes:
13 * Clemens Fruhwirth : introduce global icmp rate limiting
14 * with icmp type masking ability instead
15 * of broken per type icmp timeouts.
16 * Mike Shaver : RFC1122 checks.
17 * Alan Cox : Multicast ping reply as self.
18 * Alan Cox : Fix atomicity lockup in ip_build_xmit
19 * call.
20 * Alan Cox : Added 216,128 byte paths to the MTU
21 * code.
22 * Martin Mares : RFC1812 checks.
23 * Martin Mares : Can be configured to follow redirects
24 * if acting as a router _without_ a
25 * routing protocol (RFC 1812).
26 * Martin Mares : Echo requests may be configured to
27 * be ignored (RFC 1812).
28 * Martin Mares : Limitation of ICMP error message
29 * transmit rate (RFC 1812).
30 * Martin Mares : TOS and Precedence set correctly
31 * (RFC 1812).
32 * Martin Mares : Now copying as much data from the
33 * original packet as we can without
34 * exceeding 576 bytes (RFC 1812).
35 * Willy Konynenberg : Transparent proxying support.
36 * Keith Owens : RFC1191 correction for 4.2BSD based
37 * path MTU bug.
38 * Thomas Quinot : ICMP Dest Unreach codes up to 15 are
39 * valid (RFC 1812).
40 * Andi Kleen : Check all packet lengths properly
41 * and moved all kfree_skb() up to
42 * icmp_rcv.
43 * Andi Kleen : Move the rate limit bookkeeping
44 * into the dest entry and use a token
45 * bucket filter (thanks to ANK). Make
46 * the rates sysctl configurable.
47 * Yu Tianli : Fixed two ugly bugs in icmp_send
48 * - IP option length was accounted wrongly
49 * - ICMP header length was not accounted
50 * at all.
51 * Tristan Greaves : Added sysctl option to ignore bogus
52 * broadcast responses from broken routers.
53 *
54 * To Fix:
55 *
56 * - Should use skb_pull() instead of all the manual checking.
57 * This would also greatly simply some upper layer error handlers. --AK
58 */
59
60 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
61
62 #include <linux/module.h>
63 #include <linux/types.h>
64 #include <linux/jiffies.h>
65 #include <linux/kernel.h>
66 #include <linux/fcntl.h>
67 #include <linux/socket.h>
68 #include <linux/in.h>
69 #include <linux/inet.h>
70 #include <linux/inetdevice.h>
71 #include <linux/netdevice.h>
72 #include <linux/string.h>
73 #include <linux/netfilter_ipv4.h>
74 #include <linux/slab.h>
75 #include <net/snmp.h>
76 #include <net/ip.h>
77 #include <net/route.h>
78 #include <net/protocol.h>
79 #include <net/icmp.h>
80 #include <net/tcp.h>
81 #include <net/udp.h>
82 #include <net/raw.h>
83 #include <net/ping.h>
84 #include <linux/skbuff.h>
85 #include <net/sock.h>
86 #include <linux/errno.h>
87 #include <linux/timer.h>
88 #include <linux/init.h>
89 #include <linux/uaccess.h>
90 #include <net/checksum.h>
91 #include <net/xfrm.h>
92 #include <net/inet_common.h>
93 #include <net/ip_fib.h>
94 #include <net/l3mdev.h>
95
96 /*
97 * Build xmit assembly blocks
98 */
99
100 struct icmp_bxm {
101 struct sk_buff *skb;
102 int offset;
103 int data_len;
104
105 struct {
106 struct icmphdr icmph;
107 __be32 times[3];
108 } data;
109 int head_len;
110 struct ip_options_data replyopts;
111 };
112
113 /* An array of errno for error messages from dest unreach. */
114 /* RFC 1122: 3.2.2.1 States that NET_UNREACH, HOST_UNREACH and SR_FAILED MUST be considered 'transient errs'. */
115
116 const struct icmp_err icmp_err_convert[] = {
117 {
118 .errno = ENETUNREACH, /* ICMP_NET_UNREACH */
119 .fatal = 0,
120 },
121 {
122 .errno = EHOSTUNREACH, /* ICMP_HOST_UNREACH */
123 .fatal = 0,
124 },
125 {
126 .errno = ENOPROTOOPT /* ICMP_PROT_UNREACH */,
127 .fatal = 1,
128 },
129 {
130 .errno = ECONNREFUSED, /* ICMP_PORT_UNREACH */
131 .fatal = 1,
132 },
133 {
134 .errno = EMSGSIZE, /* ICMP_FRAG_NEEDED */
135 .fatal = 0,
136 },
137 {
138 .errno = EOPNOTSUPP, /* ICMP_SR_FAILED */
139 .fatal = 0,
140 },
141 {
142 .errno = ENETUNREACH, /* ICMP_NET_UNKNOWN */
143 .fatal = 1,
144 },
145 {
146 .errno = EHOSTDOWN, /* ICMP_HOST_UNKNOWN */
147 .fatal = 1,
148 },
149 {
150 .errno = ENONET, /* ICMP_HOST_ISOLATED */
151 .fatal = 1,
152 },
153 {
154 .errno = ENETUNREACH, /* ICMP_NET_ANO */
155 .fatal = 1,
156 },
157 {
158 .errno = EHOSTUNREACH, /* ICMP_HOST_ANO */
159 .fatal = 1,
160 },
161 {
162 .errno = ENETUNREACH, /* ICMP_NET_UNR_TOS */
163 .fatal = 0,
164 },
165 {
166 .errno = EHOSTUNREACH, /* ICMP_HOST_UNR_TOS */
167 .fatal = 0,
168 },
169 {
170 .errno = EHOSTUNREACH, /* ICMP_PKT_FILTERED */
171 .fatal = 1,
172 },
173 {
174 .errno = EHOSTUNREACH, /* ICMP_PREC_VIOLATION */
175 .fatal = 1,
176 },
177 {
178 .errno = EHOSTUNREACH, /* ICMP_PREC_CUTOFF */
179 .fatal = 1,
180 },
181 };
182 EXPORT_SYMBOL(icmp_err_convert);
183
184 /*
185 * ICMP control array. This specifies what to do with each ICMP.
186 */
187
188 struct icmp_control {
189 enum skb_drop_reason (*handler)(struct sk_buff *skb);
190 short error; /* This ICMP is classed as an error message */
191 };
192
193 static const struct icmp_control icmp_pointers[NR_ICMP_TYPES+1];
194
195 static DEFINE_PER_CPU(struct sock *, ipv4_icmp_sk);
196
197 /* Called with BH disabled */
icmp_xmit_lock(struct net * net)198 static inline struct sock *icmp_xmit_lock(struct net *net)
199 {
200 struct sock *sk;
201
202 sk = this_cpu_read(ipv4_icmp_sk);
203
204 if (unlikely(!spin_trylock(&sk->sk_lock.slock))) {
205 /* This can happen if the output path signals a
206 * dst_link_failure() for an outgoing ICMP packet.
207 */
208 return NULL;
209 }
210 sock_net_set(sk, net);
211 return sk;
212 }
213
icmp_xmit_unlock(struct sock * sk)214 static inline void icmp_xmit_unlock(struct sock *sk)
215 {
216 sock_net_set(sk, &init_net);
217 spin_unlock(&sk->sk_lock.slock);
218 }
219
220 int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
221 int sysctl_icmp_msgs_burst __read_mostly = 50;
222
223 static struct {
224 spinlock_t lock;
225 u32 credit;
226 u32 stamp;
227 } icmp_global = {
228 .lock = __SPIN_LOCK_UNLOCKED(icmp_global.lock),
229 };
230
231 /**
232 * icmp_global_allow - Are we allowed to send one more ICMP message ?
233 *
234 * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec.
235 * Returns false if we reached the limit and can not send another packet.
236 * Note: called with BH disabled
237 */
icmp_global_allow(void)238 bool icmp_global_allow(void)
239 {
240 u32 credit, delta, incr = 0, now = (u32)jiffies;
241 bool rc = false;
242
243 /* Check if token bucket is empty and cannot be refilled
244 * without taking the spinlock. The READ_ONCE() are paired
245 * with the following WRITE_ONCE() in this same function.
246 */
247 if (!READ_ONCE(icmp_global.credit)) {
248 delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ);
249 if (delta < HZ / 50)
250 return false;
251 }
252
253 spin_lock(&icmp_global.lock);
254 delta = min_t(u32, now - icmp_global.stamp, HZ);
255 if (delta >= HZ / 50) {
256 incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
257 if (incr)
258 WRITE_ONCE(icmp_global.stamp, now);
259 }
260 credit = min_t(u32, icmp_global.credit + incr,
261 READ_ONCE(sysctl_icmp_msgs_burst));
262 if (credit) {
263 /* We want to use a credit of one in average, but need to randomize
264 * it for security reasons.
265 */
266 credit = max_t(int, credit - get_random_u32_below(3), 0);
267 rc = true;
268 }
269 WRITE_ONCE(icmp_global.credit, credit);
270 spin_unlock(&icmp_global.lock);
271 return rc;
272 }
273 EXPORT_SYMBOL(icmp_global_allow);
274
icmpv4_mask_allow(struct net * net,int type,int code)275 static bool icmpv4_mask_allow(struct net *net, int type, int code)
276 {
277 if (type > NR_ICMP_TYPES)
278 return true;
279
280 /* Don't limit PMTU discovery. */
281 if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
282 return true;
283
284 /* Limit if icmp type is enabled in ratemask. */
285 if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask)))
286 return true;
287
288 return false;
289 }
290
icmpv4_global_allow(struct net * net,int type,int code)291 static bool icmpv4_global_allow(struct net *net, int type, int code)
292 {
293 if (icmpv4_mask_allow(net, type, code))
294 return true;
295
296 if (icmp_global_allow())
297 return true;
298
299 __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
300 return false;
301 }
302
303 /*
304 * Send an ICMP frame.
305 */
306
icmpv4_xrlim_allow(struct net * net,struct rtable * rt,struct flowi4 * fl4,int type,int code)307 static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
308 struct flowi4 *fl4, int type, int code)
309 {
310 struct dst_entry *dst = &rt->dst;
311 struct inet_peer *peer;
312 bool rc = true;
313 int vif;
314
315 if (icmpv4_mask_allow(net, type, code))
316 goto out;
317
318 /* No rate limit on loopback */
319 if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
320 goto out;
321
322 vif = l3mdev_master_ifindex(dst->dev);
323 peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
324 rc = inet_peer_xrlim_allow(peer,
325 READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
326 if (peer)
327 inet_putpeer(peer);
328 out:
329 if (!rc)
330 __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST);
331 return rc;
332 }
333
334 /*
335 * Maintain the counters used in the SNMP statistics for outgoing ICMP
336 */
icmp_out_count(struct net * net,unsigned char type)337 void icmp_out_count(struct net *net, unsigned char type)
338 {
339 ICMPMSGOUT_INC_STATS(net, type);
340 ICMP_INC_STATS(net, ICMP_MIB_OUTMSGS);
341 }
342
343 /*
344 * Checksum each fragment, and on the first include the headers and final
345 * checksum.
346 */
icmp_glue_bits(void * from,char * to,int offset,int len,int odd,struct sk_buff * skb)347 static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd,
348 struct sk_buff *skb)
349 {
350 struct icmp_bxm *icmp_param = from;
351 __wsum csum;
352
353 csum = skb_copy_and_csum_bits(icmp_param->skb,
354 icmp_param->offset + offset,
355 to, len);
356
357 skb->csum = csum_block_add(skb->csum, csum, odd);
358 if (icmp_pointers[icmp_param->data.icmph.type].error)
359 nf_ct_attach(skb, icmp_param->skb);
360 return 0;
361 }
362
icmp_push_reply(struct sock * sk,struct icmp_bxm * icmp_param,struct flowi4 * fl4,struct ipcm_cookie * ipc,struct rtable ** rt)363 static void icmp_push_reply(struct sock *sk,
364 struct icmp_bxm *icmp_param,
365 struct flowi4 *fl4,
366 struct ipcm_cookie *ipc, struct rtable **rt)
367 {
368 struct sk_buff *skb;
369
370 if (ip_append_data(sk, fl4, icmp_glue_bits, icmp_param,
371 icmp_param->data_len+icmp_param->head_len,
372 icmp_param->head_len,
373 ipc, rt, MSG_DONTWAIT) < 0) {
374 __ICMP_INC_STATS(sock_net(sk), ICMP_MIB_OUTERRORS);
375 ip_flush_pending_frames(sk);
376 } else if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) {
377 struct icmphdr *icmph = icmp_hdr(skb);
378 __wsum csum;
379 struct sk_buff *skb1;
380
381 csum = csum_partial_copy_nocheck((void *)&icmp_param->data,
382 (char *)icmph,
383 icmp_param->head_len);
384 skb_queue_walk(&sk->sk_write_queue, skb1) {
385 csum = csum_add(csum, skb1->csum);
386 }
387 icmph->checksum = csum_fold(csum);
388 skb->ip_summed = CHECKSUM_NONE;
389 ip_push_pending_frames(sk, fl4);
390 }
391 }
392
393 /*
394 * Driving logic for building and sending ICMP messages.
395 */
396
icmp_reply(struct icmp_bxm * icmp_param,struct sk_buff * skb)397 static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
398 {
399 struct ipcm_cookie ipc;
400 struct rtable *rt = skb_rtable(skb);
401 struct net *net = dev_net(rt->dst.dev);
402 struct flowi4 fl4;
403 struct sock *sk;
404 struct inet_sock *inet;
405 __be32 daddr, saddr;
406 u32 mark = IP4_REPLY_MARK(net, skb->mark);
407 int type = icmp_param->data.icmph.type;
408 int code = icmp_param->data.icmph.code;
409
410 if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb))
411 return;
412
413 /* Needed by both icmp_global_allow and icmp_xmit_lock */
414 local_bh_disable();
415
416 /* global icmp_msgs_per_sec */
417 if (!icmpv4_global_allow(net, type, code))
418 goto out_bh_enable;
419
420 sk = icmp_xmit_lock(net);
421 if (!sk)
422 goto out_bh_enable;
423 inet = inet_sk(sk);
424
425 icmp_param->data.icmph.checksum = 0;
426
427 ipcm_init(&ipc);
428 inet->tos = ip_hdr(skb)->tos;
429 ipc.sockc.mark = mark;
430 daddr = ipc.addr = ip_hdr(skb)->saddr;
431 saddr = fib_compute_spec_dst(skb);
432
433 if (icmp_param->replyopts.opt.opt.optlen) {
434 ipc.opt = &icmp_param->replyopts.opt;
435 if (ipc.opt->opt.srr)
436 daddr = icmp_param->replyopts.opt.opt.faddr;
437 }
438 memset(&fl4, 0, sizeof(fl4));
439 fl4.daddr = daddr;
440 fl4.saddr = saddr;
441 fl4.flowi4_mark = mark;
442 fl4.flowi4_uid = sock_net_uid(net, NULL);
443 fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
444 fl4.flowi4_proto = IPPROTO_ICMP;
445 fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
446 security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
447 rt = ip_route_output_key(net, &fl4);
448 if (IS_ERR(rt))
449 goto out_unlock;
450 if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
451 icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt);
452 ip_rt_put(rt);
453 out_unlock:
454 icmp_xmit_unlock(sk);
455 out_bh_enable:
456 local_bh_enable();
457 }
458
459 /*
460 * The device used for looking up which routing table to use for sending an ICMP
461 * error is preferably the source whenever it is set, which should ensure the
462 * icmp error can be sent to the source host, else lookup using the routing
463 * table of the destination device, else use the main routing table (index 0).
464 */
icmp_get_route_lookup_dev(struct sk_buff * skb)465 static struct net_device *icmp_get_route_lookup_dev(struct sk_buff *skb)
466 {
467 struct net_device *route_lookup_dev = NULL;
468
469 if (skb->dev)
470 route_lookup_dev = skb->dev;
471 else if (skb_dst(skb))
472 route_lookup_dev = skb_dst(skb)->dev;
473 return route_lookup_dev;
474 }
475
icmp_route_lookup(struct net * net,struct flowi4 * fl4,struct sk_buff * skb_in,const struct iphdr * iph,__be32 saddr,u8 tos,u32 mark,int type,int code,struct icmp_bxm * param)476 static struct rtable *icmp_route_lookup(struct net *net,
477 struct flowi4 *fl4,
478 struct sk_buff *skb_in,
479 const struct iphdr *iph,
480 __be32 saddr, u8 tos, u32 mark,
481 int type, int code,
482 struct icmp_bxm *param)
483 {
484 struct net_device *route_lookup_dev;
485 struct rtable *rt, *rt2;
486 struct flowi4 fl4_dec;
487 int err;
488
489 memset(fl4, 0, sizeof(*fl4));
490 fl4->daddr = (param->replyopts.opt.opt.srr ?
491 param->replyopts.opt.opt.faddr : iph->saddr);
492 fl4->saddr = saddr;
493 fl4->flowi4_mark = mark;
494 fl4->flowi4_uid = sock_net_uid(net, NULL);
495 fl4->flowi4_tos = RT_TOS(tos);
496 fl4->flowi4_proto = IPPROTO_ICMP;
497 fl4->fl4_icmp_type = type;
498 fl4->fl4_icmp_code = code;
499 route_lookup_dev = icmp_get_route_lookup_dev(skb_in);
500 fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev);
501
502 security_skb_classify_flow(skb_in, flowi4_to_flowi_common(fl4));
503 rt = ip_route_output_key_hash(net, fl4, skb_in);
504 if (IS_ERR(rt))
505 return rt;
506
507 /* No need to clone since we're just using its address. */
508 rt2 = rt;
509
510 rt = (struct rtable *) xfrm_lookup(net, &rt->dst,
511 flowi4_to_flowi(fl4), NULL, 0);
512 if (!IS_ERR(rt)) {
513 if (rt != rt2)
514 return rt;
515 } else if (PTR_ERR(rt) == -EPERM) {
516 rt = NULL;
517 } else
518 return rt;
519
520 err = xfrm_decode_session_reverse(skb_in, flowi4_to_flowi(&fl4_dec), AF_INET);
521 if (err)
522 goto relookup_failed;
523
524 if (inet_addr_type_dev_table(net, route_lookup_dev,
525 fl4_dec.saddr) == RTN_LOCAL) {
526 rt2 = __ip_route_output_key(net, &fl4_dec);
527 if (IS_ERR(rt2))
528 err = PTR_ERR(rt2);
529 } else {
530 struct flowi4 fl4_2 = {};
531 unsigned long orefdst;
532
533 fl4_2.daddr = fl4_dec.saddr;
534 rt2 = ip_route_output_key(net, &fl4_2);
535 if (IS_ERR(rt2)) {
536 err = PTR_ERR(rt2);
537 goto relookup_failed;
538 }
539 /* Ugh! */
540 orefdst = skb_in->_skb_refdst; /* save old refdst */
541 skb_dst_set(skb_in, NULL);
542 err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr,
543 RT_TOS(tos), rt2->dst.dev);
544
545 dst_release(&rt2->dst);
546 rt2 = skb_rtable(skb_in);
547 skb_in->_skb_refdst = orefdst; /* restore old refdst */
548 }
549
550 if (err)
551 goto relookup_failed;
552
553 rt2 = (struct rtable *) xfrm_lookup(net, &rt2->dst,
554 flowi4_to_flowi(&fl4_dec), NULL,
555 XFRM_LOOKUP_ICMP);
556 if (!IS_ERR(rt2)) {
557 dst_release(&rt->dst);
558 memcpy(fl4, &fl4_dec, sizeof(*fl4));
559 rt = rt2;
560 } else if (PTR_ERR(rt2) == -EPERM) {
561 if (rt)
562 dst_release(&rt->dst);
563 return rt2;
564 } else {
565 err = PTR_ERR(rt2);
566 goto relookup_failed;
567 }
568 return rt;
569
570 relookup_failed:
571 if (rt)
572 return rt;
573 return ERR_PTR(err);
574 }
575
576 /*
577 * Send an ICMP message in response to a situation
578 *
579 * RFC 1122: 3.2.2 MUST send at least the IP header and 8 bytes of header.
580 * MAY send more (we do).
581 * MUST NOT change this header information.
582 * MUST NOT reply to a multicast/broadcast IP address.
583 * MUST NOT reply to a multicast/broadcast MAC address.
584 * MUST reply to only the first fragment.
585 */
586
__icmp_send(struct sk_buff * skb_in,int type,int code,__be32 info,const struct ip_options * opt)587 void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
588 const struct ip_options *opt)
589 {
590 struct iphdr *iph;
591 int room;
592 struct icmp_bxm icmp_param;
593 struct rtable *rt = skb_rtable(skb_in);
594 struct ipcm_cookie ipc;
595 struct flowi4 fl4;
596 __be32 saddr;
597 u8 tos;
598 u32 mark;
599 struct net *net;
600 struct sock *sk;
601
602 if (!rt)
603 goto out;
604
605 if (rt->dst.dev)
606 net = dev_net(rt->dst.dev);
607 else if (skb_in->dev)
608 net = dev_net(skb_in->dev);
609 else
610 goto out;
611
612 /*
613 * Find the original header. It is expected to be valid, of course.
614 * Check this, icmp_send is called from the most obscure devices
615 * sometimes.
616 */
617 iph = ip_hdr(skb_in);
618
619 if ((u8 *)iph < skb_in->head ||
620 (skb_network_header(skb_in) + sizeof(*iph)) >
621 skb_tail_pointer(skb_in))
622 goto out;
623
624 /*
625 * No replies to physical multicast/broadcast
626 */
627 if (skb_in->pkt_type != PACKET_HOST)
628 goto out;
629
630 /*
631 * Now check at the protocol level
632 */
633 if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
634 goto out;
635
636 /*
637 * Only reply to fragment 0. We byte re-order the constant
638 * mask for efficiency.
639 */
640 if (iph->frag_off & htons(IP_OFFSET))
641 goto out;
642
643 /*
644 * If we send an ICMP error to an ICMP error a mess would result..
645 */
646 if (icmp_pointers[type].error) {
647 /*
648 * We are an error, check if we are replying to an
649 * ICMP error
650 */
651 if (iph->protocol == IPPROTO_ICMP) {
652 u8 _inner_type, *itp;
653
654 itp = skb_header_pointer(skb_in,
655 skb_network_header(skb_in) +
656 (iph->ihl << 2) +
657 offsetof(struct icmphdr,
658 type) -
659 skb_in->data,
660 sizeof(_inner_type),
661 &_inner_type);
662 if (!itp)
663 goto out;
664
665 /*
666 * Assume any unknown ICMP type is an error. This
667 * isn't specified by the RFC, but think about it..
668 */
669 if (*itp > NR_ICMP_TYPES ||
670 icmp_pointers[*itp].error)
671 goto out;
672 }
673 }
674
675 /* Needed by both icmp_global_allow and icmp_xmit_lock */
676 local_bh_disable();
677
678 /* Check global sysctl_icmp_msgs_per_sec ratelimit, unless
679 * incoming dev is loopback. If outgoing dev change to not be
680 * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow)
681 */
682 if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) &&
683 !icmpv4_global_allow(net, type, code))
684 goto out_bh_enable;
685
686 sk = icmp_xmit_lock(net);
687 if (!sk)
688 goto out_bh_enable;
689
690 /*
691 * Construct source address and options.
692 */
693
694 saddr = iph->daddr;
695 if (!(rt->rt_flags & RTCF_LOCAL)) {
696 struct net_device *dev = NULL;
697
698 rcu_read_lock();
699 if (rt_is_input_route(rt) &&
700 READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr))
701 dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
702
703 if (dev)
704 saddr = inet_select_addr(dev, iph->saddr,
705 RT_SCOPE_LINK);
706 else
707 saddr = 0;
708 rcu_read_unlock();
709 }
710
711 tos = icmp_pointers[type].error ? (RT_TOS(iph->tos) |
712 IPTOS_PREC_INTERNETCONTROL) :
713 iph->tos;
714 mark = IP4_REPLY_MARK(net, skb_in->mark);
715
716 if (__ip_options_echo(net, &icmp_param.replyopts.opt.opt, skb_in, opt))
717 goto out_unlock;
718
719
720 /*
721 * Prepare data for ICMP header.
722 */
723
724 icmp_param.data.icmph.type = type;
725 icmp_param.data.icmph.code = code;
726 icmp_param.data.icmph.un.gateway = info;
727 icmp_param.data.icmph.checksum = 0;
728 icmp_param.skb = skb_in;
729 icmp_param.offset = skb_network_offset(skb_in);
730 inet_sk(sk)->tos = tos;
731 ipcm_init(&ipc);
732 ipc.addr = iph->saddr;
733 ipc.opt = &icmp_param.replyopts.opt;
734 ipc.sockc.mark = mark;
735
736 rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos, mark,
737 type, code, &icmp_param);
738 if (IS_ERR(rt))
739 goto out_unlock;
740
741 /* peer icmp_ratelimit */
742 if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code))
743 goto ende;
744
745 /* RFC says return as much as we can without exceeding 576 bytes. */
746
747 room = dst_mtu(&rt->dst);
748 if (room > 576)
749 room = 576;
750 room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
751 room -= sizeof(struct icmphdr);
752
753 icmp_param.data_len = skb_in->len - icmp_param.offset;
754 if (icmp_param.data_len > room)
755 icmp_param.data_len = room;
756 icmp_param.head_len = sizeof(struct icmphdr);
757
758 /* if we don't have a source address at this point, fall back to the
759 * dummy address instead of sending out a packet with a source address
760 * of 0.0.0.0
761 */
762 if (!fl4.saddr)
763 fl4.saddr = htonl(INADDR_DUMMY);
764
765 icmp_push_reply(sk, &icmp_param, &fl4, &ipc, &rt);
766 ende:
767 ip_rt_put(rt);
768 out_unlock:
769 icmp_xmit_unlock(sk);
770 out_bh_enable:
771 local_bh_enable();
772 out:;
773 }
774 EXPORT_SYMBOL(__icmp_send);
775
776 #if IS_ENABLED(CONFIG_NF_NAT)
777 #include <net/netfilter/nf_conntrack.h>
icmp_ndo_send(struct sk_buff * skb_in,int type,int code,__be32 info)778 void icmp_ndo_send(struct sk_buff *skb_in, int type, int code, __be32 info)
779 {
780 struct sk_buff *cloned_skb = NULL;
781 struct ip_options opts = { 0 };
782 enum ip_conntrack_info ctinfo;
783 struct nf_conn *ct;
784 __be32 orig_ip;
785
786 ct = nf_ct_get(skb_in, &ctinfo);
787 if (!ct || !(ct->status & IPS_SRC_NAT)) {
788 __icmp_send(skb_in, type, code, info, &opts);
789 return;
790 }
791
792 if (skb_shared(skb_in))
793 skb_in = cloned_skb = skb_clone(skb_in, GFP_ATOMIC);
794
795 if (unlikely(!skb_in || skb_network_header(skb_in) < skb_in->head ||
796 (skb_network_header(skb_in) + sizeof(struct iphdr)) >
797 skb_tail_pointer(skb_in) || skb_ensure_writable(skb_in,
798 skb_network_offset(skb_in) + sizeof(struct iphdr))))
799 goto out;
800
801 orig_ip = ip_hdr(skb_in)->saddr;
802 ip_hdr(skb_in)->saddr = ct->tuplehash[0].tuple.src.u3.ip;
803 __icmp_send(skb_in, type, code, info, &opts);
804 ip_hdr(skb_in)->saddr = orig_ip;
805 out:
806 consume_skb(cloned_skb);
807 }
808 EXPORT_SYMBOL(icmp_ndo_send);
809 #endif
810
icmp_socket_deliver(struct sk_buff * skb,u32 info)811 static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
812 {
813 const struct iphdr *iph = (const struct iphdr *)skb->data;
814 const struct net_protocol *ipprot;
815 int protocol = iph->protocol;
816
817 /* Checkin full IP header plus 8 bytes of protocol to
818 * avoid additional coding at protocol handlers.
819 */
820 if (!pskb_may_pull(skb, iph->ihl * 4 + 8)) {
821 __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
822 return;
823 }
824
825 raw_icmp_error(skb, protocol, info);
826
827 ipprot = rcu_dereference(inet_protos[protocol]);
828 if (ipprot && ipprot->err_handler)
829 ipprot->err_handler(skb, info);
830 }
831
icmp_tag_validation(int proto)832 static bool icmp_tag_validation(int proto)
833 {
834 bool ok;
835
836 rcu_read_lock();
837 ok = rcu_dereference(inet_protos[proto])->icmp_strict_tag_validation;
838 rcu_read_unlock();
839 return ok;
840 }
841
842 /*
843 * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEEDED, ICMP_QUENCH, and
844 * ICMP_PARAMETERPROB.
845 */
846
icmp_unreach(struct sk_buff * skb)847 static enum skb_drop_reason icmp_unreach(struct sk_buff *skb)
848 {
849 enum skb_drop_reason reason = SKB_NOT_DROPPED_YET;
850 const struct iphdr *iph;
851 struct icmphdr *icmph;
852 struct net *net;
853 u32 info = 0;
854
855 net = dev_net(skb_dst(skb)->dev);
856
857 /*
858 * Incomplete header ?
859 * Only checks for the IP header, there should be an
860 * additional check for longer headers in upper levels.
861 */
862
863 if (!pskb_may_pull(skb, sizeof(struct iphdr)))
864 goto out_err;
865
866 icmph = icmp_hdr(skb);
867 iph = (const struct iphdr *)skb->data;
868
869 if (iph->ihl < 5) { /* Mangled header, drop. */
870 reason = SKB_DROP_REASON_IP_INHDR;
871 goto out_err;
872 }
873
874 switch (icmph->type) {
875 case ICMP_DEST_UNREACH:
876 switch (icmph->code & 15) {
877 case ICMP_NET_UNREACH:
878 case ICMP_HOST_UNREACH:
879 case ICMP_PROT_UNREACH:
880 case ICMP_PORT_UNREACH:
881 break;
882 case ICMP_FRAG_NEEDED:
883 /* for documentation of the ip_no_pmtu_disc
884 * values please see
885 * Documentation/networking/ip-sysctl.rst
886 */
887 switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) {
888 default:
889 net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
890 &iph->daddr);
891 break;
892 case 2:
893 goto out;
894 case 3:
895 if (!icmp_tag_validation(iph->protocol))
896 goto out;
897 fallthrough;
898 case 0:
899 info = ntohs(icmph->un.frag.mtu);
900 }
901 break;
902 case ICMP_SR_FAILED:
903 net_dbg_ratelimited("%pI4: Source Route Failed\n",
904 &iph->daddr);
905 break;
906 default:
907 break;
908 }
909 if (icmph->code > NR_ICMP_UNREACH)
910 goto out;
911 break;
912 case ICMP_PARAMETERPROB:
913 info = ntohl(icmph->un.gateway) >> 24;
914 break;
915 case ICMP_TIME_EXCEEDED:
916 __ICMP_INC_STATS(net, ICMP_MIB_INTIMEEXCDS);
917 if (icmph->code == ICMP_EXC_FRAGTIME)
918 goto out;
919 break;
920 }
921
922 /*
923 * Throw it at our lower layers
924 *
925 * RFC 1122: 3.2.2 MUST extract the protocol ID from the passed
926 * header.
927 * RFC 1122: 3.2.2.1 MUST pass ICMP unreach messages to the
928 * transport layer.
929 * RFC 1122: 3.2.2.2 MUST pass ICMP time expired messages to
930 * transport layer.
931 */
932
933 /*
934 * Check the other end isn't violating RFC 1122. Some routers send
935 * bogus responses to broadcast frames. If you see this message
936 * first check your netmask matches at both ends, if it does then
937 * get the other vendor to fix their kit.
938 */
939
940 if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) &&
941 inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) {
942 net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n",
943 &ip_hdr(skb)->saddr,
944 icmph->type, icmph->code,
945 &iph->daddr, skb->dev->name);
946 goto out;
947 }
948
949 icmp_socket_deliver(skb, info);
950
951 out:
952 return reason;
953 out_err:
954 __ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
955 return reason ?: SKB_DROP_REASON_NOT_SPECIFIED;
956 }
957
958
959 /*
960 * Handle ICMP_REDIRECT.
961 */
962
icmp_redirect(struct sk_buff * skb)963 static enum skb_drop_reason icmp_redirect(struct sk_buff *skb)
964 {
965 if (skb->len < sizeof(struct iphdr)) {
966 __ICMP_INC_STATS(dev_net(skb->dev), ICMP_MIB_INERRORS);
967 return SKB_DROP_REASON_PKT_TOO_SMALL;
968 }
969
970 if (!pskb_may_pull(skb, sizeof(struct iphdr))) {
971 /* there aught to be a stat */
972 return SKB_DROP_REASON_NOMEM;
973 }
974
975 icmp_socket_deliver(skb, ntohl(icmp_hdr(skb)->un.gateway));
976 return SKB_NOT_DROPPED_YET;
977 }
978
979 /*
980 * Handle ICMP_ECHO ("ping") and ICMP_EXT_ECHO ("PROBE") requests.
981 *
982 * RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
983 * requests.
984 * RFC 1122: 3.2.2.6 Data received in the ICMP_ECHO request MUST be
985 * included in the reply.
986 * RFC 1812: 4.3.3.6 SHOULD have a config option for silently ignoring
987 * echo requests, MUST have default=NOT.
988 * RFC 8335: 8 MUST have a config option to enable/disable ICMP
989 * Extended Echo Functionality, MUST be disabled by default
990 * See also WRT handling of options once they are done and working.
991 */
992
icmp_echo(struct sk_buff * skb)993 static enum skb_drop_reason icmp_echo(struct sk_buff *skb)
994 {
995 struct icmp_bxm icmp_param;
996 struct net *net;
997
998 net = dev_net(skb_dst(skb)->dev);
999 /* should there be an ICMP stat for ignored echos? */
1000 if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all))
1001 return SKB_NOT_DROPPED_YET;
1002
1003 icmp_param.data.icmph = *icmp_hdr(skb);
1004 icmp_param.skb = skb;
1005 icmp_param.offset = 0;
1006 icmp_param.data_len = skb->len;
1007 icmp_param.head_len = sizeof(struct icmphdr);
1008
1009 if (icmp_param.data.icmph.type == ICMP_ECHO)
1010 icmp_param.data.icmph.type = ICMP_ECHOREPLY;
1011 else if (!icmp_build_probe(skb, &icmp_param.data.icmph))
1012 return SKB_NOT_DROPPED_YET;
1013
1014 icmp_reply(&icmp_param, skb);
1015 return SKB_NOT_DROPPED_YET;
1016 }
1017
1018 /* Helper for icmp_echo and icmpv6_echo_reply.
1019 * Searches for net_device that matches PROBE interface identifier
1020 * and builds PROBE reply message in icmphdr.
1021 *
1022 * Returns false if PROBE responses are disabled via sysctl
1023 */
1024
icmp_build_probe(struct sk_buff * skb,struct icmphdr * icmphdr)1025 bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
1026 {
1027 struct icmp_ext_hdr *ext_hdr, _ext_hdr;
1028 struct icmp_ext_echo_iio *iio, _iio;
1029 struct net *net = dev_net(skb->dev);
1030 struct net_device *dev;
1031 char buff[IFNAMSIZ];
1032 u16 ident_len;
1033 u8 status;
1034
1035 if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
1036 return false;
1037
1038 /* We currently only support probing interfaces on the proxy node
1039 * Check to ensure L-bit is set
1040 */
1041 if (!(ntohs(icmphdr->un.echo.sequence) & 1))
1042 return false;
1043 /* Clear status bits in reply message */
1044 icmphdr->un.echo.sequence &= htons(0xFF00);
1045 if (icmphdr->type == ICMP_EXT_ECHO)
1046 icmphdr->type = ICMP_EXT_ECHOREPLY;
1047 else
1048 icmphdr->type = ICMPV6_EXT_ECHO_REPLY;
1049 ext_hdr = skb_header_pointer(skb, 0, sizeof(_ext_hdr), &_ext_hdr);
1050 /* Size of iio is class_type dependent.
1051 * Only check header here and assign length based on ctype in the switch statement
1052 */
1053 iio = skb_header_pointer(skb, sizeof(_ext_hdr), sizeof(iio->extobj_hdr), &_iio);
1054 if (!ext_hdr || !iio)
1055 goto send_mal_query;
1056 if (ntohs(iio->extobj_hdr.length) <= sizeof(iio->extobj_hdr) ||
1057 ntohs(iio->extobj_hdr.length) > sizeof(_iio))
1058 goto send_mal_query;
1059 ident_len = ntohs(iio->extobj_hdr.length) - sizeof(iio->extobj_hdr);
1060 iio = skb_header_pointer(skb, sizeof(_ext_hdr),
1061 sizeof(iio->extobj_hdr) + ident_len, &_iio);
1062 if (!iio)
1063 goto send_mal_query;
1064
1065 status = 0;
1066 dev = NULL;
1067 switch (iio->extobj_hdr.class_type) {
1068 case ICMP_EXT_ECHO_CTYPE_NAME:
1069 if (ident_len >= IFNAMSIZ)
1070 goto send_mal_query;
1071 memset(buff, 0, sizeof(buff));
1072 memcpy(buff, &iio->ident.name, ident_len);
1073 dev = dev_get_by_name(net, buff);
1074 break;
1075 case ICMP_EXT_ECHO_CTYPE_INDEX:
1076 if (ident_len != sizeof(iio->ident.ifindex))
1077 goto send_mal_query;
1078 dev = dev_get_by_index(net, ntohl(iio->ident.ifindex));
1079 break;
1080 case ICMP_EXT_ECHO_CTYPE_ADDR:
1081 if (ident_len < sizeof(iio->ident.addr.ctype3_hdr) ||
1082 ident_len != sizeof(iio->ident.addr.ctype3_hdr) +
1083 iio->ident.addr.ctype3_hdr.addrlen)
1084 goto send_mal_query;
1085 switch (ntohs(iio->ident.addr.ctype3_hdr.afi)) {
1086 case ICMP_AFI_IP:
1087 if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in_addr))
1088 goto send_mal_query;
1089 dev = ip_dev_find(net, iio->ident.addr.ip_addr.ipv4_addr);
1090 break;
1091 #if IS_ENABLED(CONFIG_IPV6)
1092 case ICMP_AFI_IP6:
1093 if (iio->ident.addr.ctype3_hdr.addrlen != sizeof(struct in6_addr))
1094 goto send_mal_query;
1095 dev = ipv6_stub->ipv6_dev_find(net, &iio->ident.addr.ip_addr.ipv6_addr, dev);
1096 dev_hold(dev);
1097 break;
1098 #endif
1099 default:
1100 goto send_mal_query;
1101 }
1102 break;
1103 default:
1104 goto send_mal_query;
1105 }
1106 if (!dev) {
1107 icmphdr->code = ICMP_EXT_CODE_NO_IF;
1108 return true;
1109 }
1110 /* Fill bits in reply message */
1111 if (dev->flags & IFF_UP)
1112 status |= ICMP_EXT_ECHOREPLY_ACTIVE;
1113 if (__in_dev_get_rcu(dev) && __in_dev_get_rcu(dev)->ifa_list)
1114 status |= ICMP_EXT_ECHOREPLY_IPV4;
1115 if (!list_empty(&rcu_dereference(dev->ip6_ptr)->addr_list))
1116 status |= ICMP_EXT_ECHOREPLY_IPV6;
1117 dev_put(dev);
1118 icmphdr->un.echo.sequence |= htons(status);
1119 return true;
1120 send_mal_query:
1121 icmphdr->code = ICMP_EXT_CODE_MAL_QUERY;
1122 return true;
1123 }
1124 EXPORT_SYMBOL_GPL(icmp_build_probe);
1125
1126 /*
1127 * Handle ICMP Timestamp requests.
1128 * RFC 1122: 3.2.2.8 MAY implement ICMP timestamp requests.
1129 * SHOULD be in the kernel for minimum random latency.
1130 * MUST be accurate to a few minutes.
1131 * MUST be updated at least at 15Hz.
1132 */
icmp_timestamp(struct sk_buff * skb)1133 static enum skb_drop_reason icmp_timestamp(struct sk_buff *skb)
1134 {
1135 struct icmp_bxm icmp_param;
1136 /*
1137 * Too short.
1138 */
1139 if (skb->len < 4)
1140 goto out_err;
1141
1142 /*
1143 * Fill in the current time as ms since midnight UT:
1144 */
1145 icmp_param.data.times[1] = inet_current_timestamp();
1146 icmp_param.data.times[2] = icmp_param.data.times[1];
1147
1148 BUG_ON(skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4));
1149
1150 icmp_param.data.icmph = *icmp_hdr(skb);
1151 icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY;
1152 icmp_param.data.icmph.code = 0;
1153 icmp_param.skb = skb;
1154 icmp_param.offset = 0;
1155 icmp_param.data_len = 0;
1156 icmp_param.head_len = sizeof(struct icmphdr) + 12;
1157 icmp_reply(&icmp_param, skb);
1158 return SKB_NOT_DROPPED_YET;
1159
1160 out_err:
1161 __ICMP_INC_STATS(dev_net(skb_dst(skb)->dev), ICMP_MIB_INERRORS);
1162 return SKB_DROP_REASON_PKT_TOO_SMALL;
1163 }
1164
icmp_discard(struct sk_buff * skb)1165 static enum skb_drop_reason icmp_discard(struct sk_buff *skb)
1166 {
1167 /* pretend it was a success */
1168 return SKB_NOT_DROPPED_YET;
1169 }
1170
1171 /*
1172 * Deal with incoming ICMP packets.
1173 */
icmp_rcv(struct sk_buff * skb)1174 int icmp_rcv(struct sk_buff *skb)
1175 {
1176 enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
1177 struct rtable *rt = skb_rtable(skb);
1178 struct net *net = dev_net(rt->dst.dev);
1179 struct icmphdr *icmph;
1180
1181 if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
1182 struct sec_path *sp = skb_sec_path(skb);
1183 int nh;
1184
1185 if (!(sp && sp->xvec[sp->len - 1]->props.flags &
1186 XFRM_STATE_ICMP)) {
1187 reason = SKB_DROP_REASON_XFRM_POLICY;
1188 goto drop;
1189 }
1190
1191 if (!pskb_may_pull(skb, sizeof(*icmph) + sizeof(struct iphdr)))
1192 goto drop;
1193
1194 nh = skb_network_offset(skb);
1195 skb_set_network_header(skb, sizeof(*icmph));
1196
1197 if (!xfrm4_policy_check_reverse(NULL, XFRM_POLICY_IN,
1198 skb)) {
1199 reason = SKB_DROP_REASON_XFRM_POLICY;
1200 goto drop;
1201 }
1202
1203 skb_set_network_header(skb, nh);
1204 }
1205
1206 __ICMP_INC_STATS(net, ICMP_MIB_INMSGS);
1207
1208 if (skb_checksum_simple_validate(skb))
1209 goto csum_error;
1210
1211 if (!pskb_pull(skb, sizeof(*icmph)))
1212 goto error;
1213
1214 icmph = icmp_hdr(skb);
1215
1216 ICMPMSGIN_INC_STATS(net, icmph->type);
1217
1218 /* Check for ICMP Extended Echo (PROBE) messages */
1219 if (icmph->type == ICMP_EXT_ECHO) {
1220 /* We can't use icmp_pointers[].handler() because it is an array of
1221 * size NR_ICMP_TYPES + 1 (19 elements) and PROBE has code 42.
1222 */
1223 reason = icmp_echo(skb);
1224 goto reason_check;
1225 }
1226
1227 if (icmph->type == ICMP_EXT_ECHOREPLY) {
1228 reason = ping_rcv(skb);
1229 goto reason_check;
1230 }
1231
1232 /*
1233 * 18 is the highest 'known' ICMP type. Anything else is a mystery
1234 *
1235 * RFC 1122: 3.2.2 Unknown ICMP messages types MUST be silently
1236 * discarded.
1237 */
1238 if (icmph->type > NR_ICMP_TYPES) {
1239 reason = SKB_DROP_REASON_UNHANDLED_PROTO;
1240 goto error;
1241 }
1242
1243 /*
1244 * Parse the ICMP message
1245 */
1246
1247 if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
1248 /*
1249 * RFC 1122: 3.2.2.6 An ICMP_ECHO to broadcast MAY be
1250 * silently ignored (we let user decide with a sysctl).
1251 * RFC 1122: 3.2.2.8 An ICMP_TIMESTAMP MAY be silently
1252 * discarded if to broadcast/multicast.
1253 */
1254 if ((icmph->type == ICMP_ECHO ||
1255 icmph->type == ICMP_TIMESTAMP) &&
1256 READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) {
1257 reason = SKB_DROP_REASON_INVALID_PROTO;
1258 goto error;
1259 }
1260 if (icmph->type != ICMP_ECHO &&
1261 icmph->type != ICMP_TIMESTAMP &&
1262 icmph->type != ICMP_ADDRESS &&
1263 icmph->type != ICMP_ADDRESSREPLY) {
1264 reason = SKB_DROP_REASON_INVALID_PROTO;
1265 goto error;
1266 }
1267 }
1268
1269 reason = icmp_pointers[icmph->type].handler(skb);
1270 reason_check:
1271 if (!reason) {
1272 consume_skb(skb);
1273 return NET_RX_SUCCESS;
1274 }
1275
1276 drop:
1277 kfree_skb_reason(skb, reason);
1278 return NET_RX_DROP;
1279 csum_error:
1280 reason = SKB_DROP_REASON_ICMP_CSUM;
1281 __ICMP_INC_STATS(net, ICMP_MIB_CSUMERRORS);
1282 error:
1283 __ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
1284 goto drop;
1285 }
1286
ip_icmp_error_rfc4884_validate(const struct sk_buff * skb,int off)1287 static bool ip_icmp_error_rfc4884_validate(const struct sk_buff *skb, int off)
1288 {
1289 struct icmp_extobj_hdr *objh, _objh;
1290 struct icmp_ext_hdr *exth, _exth;
1291 u16 olen;
1292
1293 exth = skb_header_pointer(skb, off, sizeof(_exth), &_exth);
1294 if (!exth)
1295 return false;
1296 if (exth->version != 2)
1297 return true;
1298
1299 if (exth->checksum &&
1300 csum_fold(skb_checksum(skb, off, skb->len - off, 0)))
1301 return false;
1302
1303 off += sizeof(_exth);
1304 while (off < skb->len) {
1305 objh = skb_header_pointer(skb, off, sizeof(_objh), &_objh);
1306 if (!objh)
1307 return false;
1308
1309 olen = ntohs(objh->length);
1310 if (olen < sizeof(_objh))
1311 return false;
1312
1313 off += olen;
1314 if (off > skb->len)
1315 return false;
1316 }
1317
1318 return true;
1319 }
1320
ip_icmp_error_rfc4884(const struct sk_buff * skb,struct sock_ee_data_rfc4884 * out,int thlen,int off)1321 void ip_icmp_error_rfc4884(const struct sk_buff *skb,
1322 struct sock_ee_data_rfc4884 *out,
1323 int thlen, int off)
1324 {
1325 int hlen;
1326
1327 /* original datagram headers: end of icmph to payload (skb->data) */
1328 hlen = -skb_transport_offset(skb) - thlen;
1329
1330 /* per rfc 4884: minimal datagram length of 128 bytes */
1331 if (off < 128 || off < hlen)
1332 return;
1333
1334 /* kernel has stripped headers: return payload offset in bytes */
1335 off -= hlen;
1336 if (off + sizeof(struct icmp_ext_hdr) > skb->len)
1337 return;
1338
1339 out->len = off;
1340
1341 if (!ip_icmp_error_rfc4884_validate(skb, off))
1342 out->flags |= SO_EE_RFC4884_FLAG_INVALID;
1343 }
1344 EXPORT_SYMBOL_GPL(ip_icmp_error_rfc4884);
1345
icmp_err(struct sk_buff * skb,u32 info)1346 int icmp_err(struct sk_buff *skb, u32 info)
1347 {
1348 struct iphdr *iph = (struct iphdr *)skb->data;
1349 int offset = iph->ihl<<2;
1350 struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
1351 int type = icmp_hdr(skb)->type;
1352 int code = icmp_hdr(skb)->code;
1353 struct net *net = dev_net(skb->dev);
1354
1355 /*
1356 * Use ping_err to handle all icmp errors except those
1357 * triggered by ICMP_ECHOREPLY which sent from kernel.
1358 */
1359 if (icmph->type != ICMP_ECHOREPLY) {
1360 ping_err(skb, offset, info);
1361 return 0;
1362 }
1363
1364 if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)
1365 ipv4_update_pmtu(skb, net, info, 0, IPPROTO_ICMP);
1366 else if (type == ICMP_REDIRECT)
1367 ipv4_redirect(skb, net, 0, IPPROTO_ICMP);
1368
1369 return 0;
1370 }
1371
1372 /*
1373 * This table is the definition of how we handle ICMP.
1374 */
1375 static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = {
1376 [ICMP_ECHOREPLY] = {
1377 .handler = ping_rcv,
1378 },
1379 [1] = {
1380 .handler = icmp_discard,
1381 .error = 1,
1382 },
1383 [2] = {
1384 .handler = icmp_discard,
1385 .error = 1,
1386 },
1387 [ICMP_DEST_UNREACH] = {
1388 .handler = icmp_unreach,
1389 .error = 1,
1390 },
1391 [ICMP_SOURCE_QUENCH] = {
1392 .handler = icmp_unreach,
1393 .error = 1,
1394 },
1395 [ICMP_REDIRECT] = {
1396 .handler = icmp_redirect,
1397 .error = 1,
1398 },
1399 [6] = {
1400 .handler = icmp_discard,
1401 .error = 1,
1402 },
1403 [7] = {
1404 .handler = icmp_discard,
1405 .error = 1,
1406 },
1407 [ICMP_ECHO] = {
1408 .handler = icmp_echo,
1409 },
1410 [9] = {
1411 .handler = icmp_discard,
1412 .error = 1,
1413 },
1414 [10] = {
1415 .handler = icmp_discard,
1416 .error = 1,
1417 },
1418 [ICMP_TIME_EXCEEDED] = {
1419 .handler = icmp_unreach,
1420 .error = 1,
1421 },
1422 [ICMP_PARAMETERPROB] = {
1423 .handler = icmp_unreach,
1424 .error = 1,
1425 },
1426 [ICMP_TIMESTAMP] = {
1427 .handler = icmp_timestamp,
1428 },
1429 [ICMP_TIMESTAMPREPLY] = {
1430 .handler = icmp_discard,
1431 },
1432 [ICMP_INFO_REQUEST] = {
1433 .handler = icmp_discard,
1434 },
1435 [ICMP_INFO_REPLY] = {
1436 .handler = icmp_discard,
1437 },
1438 [ICMP_ADDRESS] = {
1439 .handler = icmp_discard,
1440 },
1441 [ICMP_ADDRESSREPLY] = {
1442 .handler = icmp_discard,
1443 },
1444 };
1445
icmp_sk_init(struct net * net)1446 static int __net_init icmp_sk_init(struct net *net)
1447 {
1448 /* Control parameters for ECHO replies. */
1449 net->ipv4.sysctl_icmp_echo_ignore_all = 0;
1450 net->ipv4.sysctl_icmp_echo_enable_probe = 0;
1451 net->ipv4.sysctl_icmp_echo_ignore_broadcasts = 1;
1452
1453 /* Control parameter - ignore bogus broadcast responses? */
1454 net->ipv4.sysctl_icmp_ignore_bogus_error_responses = 1;
1455
1456 /*
1457 * Configurable global rate limit.
1458 *
1459 * ratelimit defines tokens/packet consumed for dst->rate_token
1460 * bucket ratemask defines which icmp types are ratelimited by
1461 * setting it's bit position.
1462 *
1463 * default:
1464 * dest unreachable (3), source quench (4),
1465 * time exceeded (11), parameter problem (12)
1466 */
1467
1468 net->ipv4.sysctl_icmp_ratelimit = 1 * HZ;
1469 net->ipv4.sysctl_icmp_ratemask = 0x1818;
1470 net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0;
1471
1472 return 0;
1473 }
1474
1475 static struct pernet_operations __net_initdata icmp_sk_ops = {
1476 .init = icmp_sk_init,
1477 };
1478
icmp_init(void)1479 int __init icmp_init(void)
1480 {
1481 int err, i;
1482
1483 for_each_possible_cpu(i) {
1484 struct sock *sk;
1485
1486 err = inet_ctl_sock_create(&sk, PF_INET,
1487 SOCK_RAW, IPPROTO_ICMP, &init_net);
1488 if (err < 0)
1489 return err;
1490
1491 per_cpu(ipv4_icmp_sk, i) = sk;
1492
1493 /* Enough space for 2 64K ICMP packets, including
1494 * sk_buff/skb_shared_info struct overhead.
1495 */
1496 sk->sk_sndbuf = 2 * SKB_TRUESIZE(64 * 1024);
1497
1498 /*
1499 * Speedup sock_wfree()
1500 */
1501 sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
1502 inet_sk(sk)->pmtudisc = IP_PMTUDISC_DONT;
1503 }
1504 return register_pernet_subsys(&icmp_sk_ops);
1505 }
1506