xref: /kernel/linux/linux-5.10/net/ipv4/ping.c (revision 8c2ecf20)
1// SPDX-License-Identifier: GPL-2.0-or-later
2/*
3 * INET		An implementation of the TCP/IP protocol suite for the LINUX
4 *		operating system.  INET is implemented using the  BSD Socket
5 *		interface as the means of communication with the user level.
6 *
7 *		"Ping" sockets
8 *
9 * Based on ipv4/udp.c code.
10 *
11 * Authors:	Vasiliy Kulikov / Openwall (for Linux 2.6),
12 *		Pavel Kankovsky (for Linux 2.4.32)
13 *
14 * Pavel gave all rights to bugs to Vasiliy,
15 * none of the bugs are Pavel's now.
16 */
17
18#include <linux/uaccess.h>
19#include <linux/types.h>
20#include <linux/fcntl.h>
21#include <linux/socket.h>
22#include <linux/sockios.h>
23#include <linux/in.h>
24#include <linux/errno.h>
25#include <linux/timer.h>
26#include <linux/mm.h>
27#include <linux/inet.h>
28#include <linux/netdevice.h>
29#include <net/snmp.h>
30#include <net/ip.h>
31#include <net/icmp.h>
32#include <net/protocol.h>
33#include <linux/skbuff.h>
34#include <linux/proc_fs.h>
35#include <linux/export.h>
36#include <net/sock.h>
37#include <net/ping.h>
38#include <net/udp.h>
39#include <net/route.h>
40#include <net/inet_common.h>
41#include <net/checksum.h>
42
43#if IS_ENABLED(CONFIG_IPV6)
44#include <linux/in6.h>
45#include <linux/icmpv6.h>
46#include <net/addrconf.h>
47#include <net/ipv6.h>
48#include <net/transp_v6.h>
49#endif
50
51struct ping_table {
52	struct hlist_nulls_head	hash[PING_HTABLE_SIZE];
53	rwlock_t		lock;
54};
55
56static struct ping_table ping_table;
57struct pingv6_ops pingv6_ops;
58EXPORT_SYMBOL_GPL(pingv6_ops);
59
60static u16 ping_port_rover;
61
62static inline u32 ping_hashfn(const struct net *net, u32 num, u32 mask)
63{
64	u32 res = (num + net_hash_mix(net)) & mask;
65
66	pr_debug("hash(%u) = %u\n", num, res);
67	return res;
68}
69EXPORT_SYMBOL_GPL(ping_hash);
70
71static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
72					     struct net *net, unsigned int num)
73{
74	return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
75}
76
77int ping_get_port(struct sock *sk, unsigned short ident)
78{
79	struct hlist_nulls_node *node;
80	struct hlist_nulls_head *hlist;
81	struct inet_sock *isk, *isk2;
82	struct sock *sk2 = NULL;
83
84	isk = inet_sk(sk);
85	write_lock_bh(&ping_table.lock);
86	if (ident == 0) {
87		u32 i;
88		u16 result = ping_port_rover + 1;
89
90		for (i = 0; i < (1L << 16); i++, result++) {
91			if (!result)
92				result++; /* avoid zero */
93			hlist = ping_hashslot(&ping_table, sock_net(sk),
94					    result);
95			ping_portaddr_for_each_entry(sk2, node, hlist) {
96				isk2 = inet_sk(sk2);
97
98				if (isk2->inet_num == result)
99					goto next_port;
100			}
101
102			/* found */
103			ping_port_rover = ident = result;
104			break;
105next_port:
106			;
107		}
108		if (i >= (1L << 16))
109			goto fail;
110	} else {
111		hlist = ping_hashslot(&ping_table, sock_net(sk), ident);
112		ping_portaddr_for_each_entry(sk2, node, hlist) {
113			isk2 = inet_sk(sk2);
114
115			/* BUG? Why is this reuse and not reuseaddr? ping.c
116			 * doesn't turn off SO_REUSEADDR, and it doesn't expect
117			 * that other ping processes can steal its packets.
118			 */
119			if ((isk2->inet_num == ident) &&
120			    (sk2 != sk) &&
121			    (!sk2->sk_reuse || !sk->sk_reuse))
122				goto fail;
123		}
124	}
125
126	pr_debug("found port/ident = %d\n", ident);
127	isk->inet_num = ident;
128	if (sk_unhashed(sk)) {
129		pr_debug("was not hashed\n");
130		sock_hold(sk);
131		hlist_nulls_add_head(&sk->sk_nulls_node, hlist);
132		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1);
133	}
134	write_unlock_bh(&ping_table.lock);
135	return 0;
136
137fail:
138	write_unlock_bh(&ping_table.lock);
139	return 1;
140}
141EXPORT_SYMBOL_GPL(ping_get_port);
142
143int ping_hash(struct sock *sk)
144{
145	pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
146	BUG(); /* "Please do not press this button again." */
147
148	return 0;
149}
150
151void ping_unhash(struct sock *sk)
152{
153	struct inet_sock *isk = inet_sk(sk);
154
155	pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
156	write_lock_bh(&ping_table.lock);
157	if (sk_hashed(sk)) {
158		hlist_nulls_del(&sk->sk_nulls_node);
159		sk_nulls_node_init(&sk->sk_nulls_node);
160		sock_put(sk);
161		isk->inet_num = 0;
162		isk->inet_sport = 0;
163		sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
164	}
165	write_unlock_bh(&ping_table.lock);
166}
167EXPORT_SYMBOL_GPL(ping_unhash);
168
169static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
170{
171	struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident);
172	struct sock *sk = NULL;
173	struct inet_sock *isk;
174	struct hlist_nulls_node *hnode;
175	int dif, sdif;
176
177	if (skb->protocol == htons(ETH_P_IP)) {
178		dif = inet_iif(skb);
179		sdif = inet_sdif(skb);
180		pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
181			 (int)ident, &ip_hdr(skb)->daddr, dif);
182#if IS_ENABLED(CONFIG_IPV6)
183	} else if (skb->protocol == htons(ETH_P_IPV6)) {
184		dif = inet6_iif(skb);
185		sdif = inet6_sdif(skb);
186		pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
187			 (int)ident, &ipv6_hdr(skb)->daddr, dif);
188#endif
189	} else {
190		return NULL;
191	}
192
193	read_lock_bh(&ping_table.lock);
194
195	ping_portaddr_for_each_entry(sk, hnode, hslot) {
196		isk = inet_sk(sk);
197
198		pr_debug("iterate\n");
199		if (isk->inet_num != ident)
200			continue;
201
202		if (skb->protocol == htons(ETH_P_IP) &&
203		    sk->sk_family == AF_INET) {
204			pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk,
205				 (int) isk->inet_num, &isk->inet_rcv_saddr,
206				 sk->sk_bound_dev_if);
207
208			if (isk->inet_rcv_saddr &&
209			    isk->inet_rcv_saddr != ip_hdr(skb)->daddr)
210				continue;
211#if IS_ENABLED(CONFIG_IPV6)
212		} else if (skb->protocol == htons(ETH_P_IPV6) &&
213			   sk->sk_family == AF_INET6) {
214
215			pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
216				 (int) isk->inet_num,
217				 &sk->sk_v6_rcv_saddr,
218				 sk->sk_bound_dev_if);
219
220			if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) &&
221			    !ipv6_addr_equal(&sk->sk_v6_rcv_saddr,
222					     &ipv6_hdr(skb)->daddr))
223				continue;
224#endif
225		} else {
226			continue;
227		}
228
229		if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif &&
230		    sk->sk_bound_dev_if != sdif)
231			continue;
232
233		sock_hold(sk);
234		goto exit;
235	}
236
237	sk = NULL;
238exit:
239	read_unlock_bh(&ping_table.lock);
240
241	return sk;
242}
243
244static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
245					  kgid_t *high)
246{
247	kgid_t *data = net->ipv4.ping_group_range.range;
248	unsigned int seq;
249
250	do {
251		seq = read_seqbegin(&net->ipv4.ping_group_range.lock);
252
253		*low = data[0];
254		*high = data[1];
255	} while (read_seqretry(&net->ipv4.ping_group_range.lock, seq));
256}
257
258
259int ping_init_sock(struct sock *sk)
260{
261	struct net *net = sock_net(sk);
262	kgid_t group = current_egid();
263	struct group_info *group_info;
264	int i;
265	kgid_t low, high;
266	int ret = 0;
267
268	if (sk->sk_family == AF_INET6)
269		sk->sk_ipv6only = 1;
270
271	inet_get_ping_group_range_net(net, &low, &high);
272	if (gid_lte(low, group) && gid_lte(group, high))
273		return 0;
274
275	group_info = get_current_groups();
276	for (i = 0; i < group_info->ngroups; i++) {
277		kgid_t gid = group_info->gid[i];
278
279		if (gid_lte(low, gid) && gid_lte(gid, high))
280			goto out_release_group;
281	}
282
283	ret = -EACCES;
284
285out_release_group:
286	put_group_info(group_info);
287	return ret;
288}
289EXPORT_SYMBOL_GPL(ping_init_sock);
290
291void ping_close(struct sock *sk, long timeout)
292{
293	pr_debug("ping_close(sk=%p,sk->num=%u)\n",
294		 inet_sk(sk), inet_sk(sk)->inet_num);
295	pr_debug("isk->refcnt = %d\n", refcount_read(&sk->sk_refcnt));
296
297	sk_common_release(sk);
298}
299EXPORT_SYMBOL_GPL(ping_close);
300
301/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
302static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
303				struct sockaddr *uaddr, int addr_len)
304{
305	struct net *net = sock_net(sk);
306	if (sk->sk_family == AF_INET) {
307		struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
308		u32 tb_id = RT_TABLE_LOCAL;
309		int chk_addr_ret;
310
311		if (addr_len < sizeof(*addr))
312			return -EINVAL;
313
314		if (addr->sin_family != AF_INET &&
315		    !(addr->sin_family == AF_UNSPEC &&
316		      addr->sin_addr.s_addr == htonl(INADDR_ANY)))
317			return -EAFNOSUPPORT;
318
319		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
320			 sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
321
322		if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
323			chk_addr_ret = RTN_LOCAL;
324		else {
325			tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
326			chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
327		}
328
329		if ((!inet_can_nonlocal_bind(net, isk) &&
330		     chk_addr_ret != RTN_LOCAL) ||
331		    chk_addr_ret == RTN_MULTICAST ||
332		    chk_addr_ret == RTN_BROADCAST)
333			return -EADDRNOTAVAIL;
334
335#if IS_ENABLED(CONFIG_IPV6)
336	} else if (sk->sk_family == AF_INET6) {
337		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
338		int addr_type, scoped, has_addr;
339		struct net_device *dev = NULL;
340
341		if (addr_len < sizeof(*addr))
342			return -EINVAL;
343
344		if (addr->sin6_family != AF_INET6)
345			return -EAFNOSUPPORT;
346
347		pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
348			 sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
349
350		addr_type = ipv6_addr_type(&addr->sin6_addr);
351		scoped = __ipv6_addr_needs_scope_id(addr_type);
352		if ((addr_type != IPV6_ADDR_ANY &&
353		     !(addr_type & IPV6_ADDR_UNICAST)) ||
354		    (scoped && !addr->sin6_scope_id))
355			return -EINVAL;
356
357		rcu_read_lock();
358		if (addr->sin6_scope_id) {
359			dev = dev_get_by_index_rcu(net, addr->sin6_scope_id);
360			if (!dev) {
361				rcu_read_unlock();
362				return -ENODEV;
363			}
364		}
365
366		if (!dev && sk->sk_bound_dev_if) {
367			dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
368			if (!dev) {
369				rcu_read_unlock();
370				return -ENODEV;
371			}
372		}
373		has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
374						    scoped);
375		rcu_read_unlock();
376
377		if (!(ipv6_can_nonlocal_bind(net, isk) || has_addr ||
378		      addr_type == IPV6_ADDR_ANY))
379			return -EADDRNOTAVAIL;
380
381		if (scoped)
382			sk->sk_bound_dev_if = addr->sin6_scope_id;
383#endif
384	} else {
385		return -EAFNOSUPPORT;
386	}
387	return 0;
388}
389
390static void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
391{
392	if (saddr->sa_family == AF_INET) {
393		struct inet_sock *isk = inet_sk(sk);
394		struct sockaddr_in *addr = (struct sockaddr_in *) saddr;
395		isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
396#if IS_ENABLED(CONFIG_IPV6)
397	} else if (saddr->sa_family == AF_INET6) {
398		struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
399		struct ipv6_pinfo *np = inet6_sk(sk);
400		sk->sk_v6_rcv_saddr = np->saddr = addr->sin6_addr;
401#endif
402	}
403}
404
405/*
406 * We need our own bind because there are no privileged id's == local ports.
407 * Moreover, we don't allow binding to multi- and broadcast addresses.
408 */
409
410int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
411{
412	struct inet_sock *isk = inet_sk(sk);
413	unsigned short snum;
414	int err;
415	int dif = sk->sk_bound_dev_if;
416
417	err = ping_check_bind_addr(sk, isk, uaddr, addr_len);
418	if (err)
419		return err;
420
421	lock_sock(sk);
422
423	err = -EINVAL;
424	if (isk->inet_num != 0)
425		goto out;
426
427	err = -EADDRINUSE;
428	snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
429	if (ping_get_port(sk, snum) != 0) {
430		/* Restore possibly modified sk->sk_bound_dev_if by ping_check_bind_addr(). */
431		sk->sk_bound_dev_if = dif;
432		goto out;
433	}
434	ping_set_saddr(sk, uaddr);
435
436	pr_debug("after bind(): num = %hu, dif = %d\n",
437		 isk->inet_num,
438		 sk->sk_bound_dev_if);
439
440	err = 0;
441	if (sk->sk_family == AF_INET && isk->inet_rcv_saddr)
442		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
443#if IS_ENABLED(CONFIG_IPV6)
444	if (sk->sk_family == AF_INET6 && !ipv6_addr_any(&sk->sk_v6_rcv_saddr))
445		sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
446#endif
447
448	if (snum)
449		sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
450	isk->inet_sport = htons(isk->inet_num);
451	isk->inet_daddr = 0;
452	isk->inet_dport = 0;
453
454#if IS_ENABLED(CONFIG_IPV6)
455	if (sk->sk_family == AF_INET6)
456		memset(&sk->sk_v6_daddr, 0, sizeof(sk->sk_v6_daddr));
457#endif
458
459	sk_dst_reset(sk);
460out:
461	release_sock(sk);
462	pr_debug("ping_v4_bind -> %d\n", err);
463	return err;
464}
465EXPORT_SYMBOL_GPL(ping_bind);
466
467/*
468 * Is this a supported type of ICMP message?
469 */
470
471static inline int ping_supported(int family, int type, int code)
472{
473	return (family == AF_INET && type == ICMP_ECHO && code == 0) ||
474	       (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0);
475}
476
477/*
478 * This routine is called by the ICMP module when it gets some
479 * sort of error condition.
480 */
481
482void ping_err(struct sk_buff *skb, int offset, u32 info)
483{
484	int family;
485	struct icmphdr *icmph;
486	struct inet_sock *inet_sock;
487	int type;
488	int code;
489	struct net *net = dev_net(skb->dev);
490	struct sock *sk;
491	int harderr;
492	int err;
493
494	if (skb->protocol == htons(ETH_P_IP)) {
495		family = AF_INET;
496		type = icmp_hdr(skb)->type;
497		code = icmp_hdr(skb)->code;
498		icmph = (struct icmphdr *)(skb->data + offset);
499	} else if (skb->protocol == htons(ETH_P_IPV6)) {
500		family = AF_INET6;
501		type = icmp6_hdr(skb)->icmp6_type;
502		code = icmp6_hdr(skb)->icmp6_code;
503		icmph = (struct icmphdr *) (skb->data + offset);
504	} else {
505		BUG();
506	}
507
508	/* We assume the packet has already been checked by icmp_unreach */
509
510	if (!ping_supported(family, icmph->type, icmph->code))
511		return;
512
513	pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n",
514		 skb->protocol, type, code, ntohs(icmph->un.echo.id),
515		 ntohs(icmph->un.echo.sequence));
516
517	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
518	if (!sk) {
519		pr_debug("no socket, dropping\n");
520		return;	/* No socket for error */
521	}
522	pr_debug("err on socket %p\n", sk);
523
524	err = 0;
525	harderr = 0;
526	inet_sock = inet_sk(sk);
527
528	if (skb->protocol == htons(ETH_P_IP)) {
529		switch (type) {
530		default:
531		case ICMP_TIME_EXCEEDED:
532			err = EHOSTUNREACH;
533			break;
534		case ICMP_SOURCE_QUENCH:
535			/* This is not a real error but ping wants to see it.
536			 * Report it with some fake errno.
537			 */
538			err = EREMOTEIO;
539			break;
540		case ICMP_PARAMETERPROB:
541			err = EPROTO;
542			harderr = 1;
543			break;
544		case ICMP_DEST_UNREACH:
545			if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
546				ipv4_sk_update_pmtu(skb, sk, info);
547				if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
548					err = EMSGSIZE;
549					harderr = 1;
550					break;
551				}
552				goto out;
553			}
554			err = EHOSTUNREACH;
555			if (code <= NR_ICMP_UNREACH) {
556				harderr = icmp_err_convert[code].fatal;
557				err = icmp_err_convert[code].errno;
558			}
559			break;
560		case ICMP_REDIRECT:
561			/* See ICMP_SOURCE_QUENCH */
562			ipv4_sk_redirect(skb, sk);
563			err = EREMOTEIO;
564			break;
565		}
566#if IS_ENABLED(CONFIG_IPV6)
567	} else if (skb->protocol == htons(ETH_P_IPV6)) {
568		harderr = pingv6_ops.icmpv6_err_convert(type, code, &err);
569#endif
570	}
571
572	/*
573	 *      RFC1122: OK.  Passes ICMP errors back to application, as per
574	 *	4.1.3.3.
575	 */
576	if ((family == AF_INET && !inet_sock->recverr) ||
577	    (family == AF_INET6 && !inet6_sk(sk)->recverr)) {
578		if (!harderr || sk->sk_state != TCP_ESTABLISHED)
579			goto out;
580	} else {
581		if (family == AF_INET) {
582			ip_icmp_error(sk, skb, err, 0 /* no remote port */,
583				      info, (u8 *)icmph);
584#if IS_ENABLED(CONFIG_IPV6)
585		} else if (family == AF_INET6) {
586			pingv6_ops.ipv6_icmp_error(sk, skb, err, 0,
587						   info, (u8 *)icmph);
588#endif
589		}
590	}
591	sk->sk_err = err;
592	sk->sk_error_report(sk);
593out:
594	sock_put(sk);
595}
596EXPORT_SYMBOL_GPL(ping_err);
597
598/*
599 *	Copy and checksum an ICMP Echo packet from user space into a buffer
600 *	starting from the payload.
601 */
602
603int ping_getfrag(void *from, char *to,
604		 int offset, int fraglen, int odd, struct sk_buff *skb)
605{
606	struct pingfakehdr *pfh = (struct pingfakehdr *)from;
607
608	if (offset == 0) {
609		fraglen -= sizeof(struct icmphdr);
610		if (fraglen < 0)
611			BUG();
612		if (!csum_and_copy_from_iter_full(to + sizeof(struct icmphdr),
613			    fraglen, &pfh->wcheck,
614			    &pfh->msg->msg_iter))
615			return -EFAULT;
616	} else if (offset < sizeof(struct icmphdr)) {
617			BUG();
618	} else {
619		if (!csum_and_copy_from_iter_full(to, fraglen, &pfh->wcheck,
620					    &pfh->msg->msg_iter))
621			return -EFAULT;
622	}
623
624#if IS_ENABLED(CONFIG_IPV6)
625	/* For IPv6, checksum each skb as we go along, as expected by
626	 * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in
627	 * wcheck, it will be finalized in ping_v4_push_pending_frames.
628	 */
629	if (pfh->family == AF_INET6) {
630		skb->csum = pfh->wcheck;
631		skb->ip_summed = CHECKSUM_NONE;
632		pfh->wcheck = 0;
633	}
634#endif
635
636	return 0;
637}
638EXPORT_SYMBOL_GPL(ping_getfrag);
639
640static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
641				       struct flowi4 *fl4)
642{
643	struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
644
645	if (!skb)
646		return 0;
647	pfh->wcheck = csum_partial((char *)&pfh->icmph,
648		sizeof(struct icmphdr), pfh->wcheck);
649	pfh->icmph.checksum = csum_fold(pfh->wcheck);
650	memcpy(icmp_hdr(skb), &pfh->icmph, sizeof(struct icmphdr));
651	skb->ip_summed = CHECKSUM_NONE;
652	return ip_push_pending_frames(sk, fl4);
653}
654
655int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
656			void *user_icmph, size_t icmph_len)
657{
658	u8 type, code;
659
660	if (len > 0xFFFF)
661		return -EMSGSIZE;
662
663	/* Must have at least a full ICMP header. */
664	if (len < icmph_len)
665		return -EINVAL;
666
667	/*
668	 *	Check the flags.
669	 */
670
671	/* Mirror BSD error message compatibility */
672	if (msg->msg_flags & MSG_OOB)
673		return -EOPNOTSUPP;
674
675	/*
676	 *	Fetch the ICMP header provided by the userland.
677	 *	iovec is modified! The ICMP header is consumed.
678	 */
679	if (memcpy_from_msg(user_icmph, msg, icmph_len))
680		return -EFAULT;
681
682	if (family == AF_INET) {
683		type = ((struct icmphdr *) user_icmph)->type;
684		code = ((struct icmphdr *) user_icmph)->code;
685#if IS_ENABLED(CONFIG_IPV6)
686	} else if (family == AF_INET6) {
687		type = ((struct icmp6hdr *) user_icmph)->icmp6_type;
688		code = ((struct icmp6hdr *) user_icmph)->icmp6_code;
689#endif
690	} else {
691		BUG();
692	}
693
694	if (!ping_supported(family, type, code))
695		return -EINVAL;
696
697	return 0;
698}
699EXPORT_SYMBOL_GPL(ping_common_sendmsg);
700
701static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
702{
703	struct net *net = sock_net(sk);
704	struct flowi4 fl4;
705	struct inet_sock *inet = inet_sk(sk);
706	struct ipcm_cookie ipc;
707	struct icmphdr user_icmph;
708	struct pingfakehdr pfh;
709	struct rtable *rt = NULL;
710	struct ip_options_data opt_copy;
711	int free = 0;
712	__be32 saddr, daddr, faddr;
713	u8  tos;
714	int err;
715
716	pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
717
718	err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph,
719				  sizeof(user_icmph));
720	if (err)
721		return err;
722
723	/*
724	 *	Get and verify the address.
725	 */
726
727	if (msg->msg_name) {
728		DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name);
729		if (msg->msg_namelen < sizeof(*usin))
730			return -EINVAL;
731		if (usin->sin_family != AF_INET)
732			return -EAFNOSUPPORT;
733		daddr = usin->sin_addr.s_addr;
734		/* no remote port */
735	} else {
736		if (sk->sk_state != TCP_ESTABLISHED)
737			return -EDESTADDRREQ;
738		daddr = inet->inet_daddr;
739		/* no remote port */
740	}
741
742	ipcm_init_sk(&ipc, inet);
743
744	if (msg->msg_controllen) {
745		err = ip_cmsg_send(sk, msg, &ipc, false);
746		if (unlikely(err)) {
747			kfree(ipc.opt);
748			return err;
749		}
750		if (ipc.opt)
751			free = 1;
752	}
753	if (!ipc.opt) {
754		struct ip_options_rcu *inet_opt;
755
756		rcu_read_lock();
757		inet_opt = rcu_dereference(inet->inet_opt);
758		if (inet_opt) {
759			memcpy(&opt_copy, inet_opt,
760			       sizeof(*inet_opt) + inet_opt->opt.optlen);
761			ipc.opt = &opt_copy.opt;
762		}
763		rcu_read_unlock();
764	}
765
766	saddr = ipc.addr;
767	ipc.addr = faddr = daddr;
768
769	if (ipc.opt && ipc.opt->opt.srr) {
770		if (!daddr) {
771			err = -EINVAL;
772			goto out_free;
773		}
774		faddr = ipc.opt->opt.faddr;
775	}
776	tos = get_rttos(&ipc, inet);
777	if (sock_flag(sk, SOCK_LOCALROUTE) ||
778	    (msg->msg_flags & MSG_DONTROUTE) ||
779	    (ipc.opt && ipc.opt->opt.is_strictroute)) {
780		tos |= RTO_ONLINK;
781	}
782
783	if (ipv4_is_multicast(daddr)) {
784		if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif))
785			ipc.oif = inet->mc_index;
786		if (!saddr)
787			saddr = inet->mc_addr;
788	} else if (!ipc.oif)
789		ipc.oif = inet->uc_index;
790
791	flowi4_init_output(&fl4, ipc.oif, ipc.sockc.mark, tos,
792			   RT_SCOPE_UNIVERSE, sk->sk_protocol,
793			   inet_sk_flowi_flags(sk), faddr, saddr, 0, 0,
794			   sk->sk_uid);
795
796	fl4.fl4_icmp_type = user_icmph.type;
797	fl4.fl4_icmp_code = user_icmph.code;
798
799	security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
800	rt = ip_route_output_flow(net, &fl4, sk);
801	if (IS_ERR(rt)) {
802		err = PTR_ERR(rt);
803		rt = NULL;
804		if (err == -ENETUNREACH)
805			IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES);
806		goto out;
807	}
808
809	err = -EACCES;
810	if ((rt->rt_flags & RTCF_BROADCAST) &&
811	    !sock_flag(sk, SOCK_BROADCAST))
812		goto out;
813
814	if (msg->msg_flags & MSG_CONFIRM)
815		goto do_confirm;
816back_from_confirm:
817
818	if (!ipc.addr)
819		ipc.addr = fl4.daddr;
820
821	lock_sock(sk);
822
823	pfh.icmph.type = user_icmph.type; /* already checked */
824	pfh.icmph.code = user_icmph.code; /* ditto */
825	pfh.icmph.checksum = 0;
826	pfh.icmph.un.echo.id = inet->inet_sport;
827	pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
828	pfh.msg = msg;
829	pfh.wcheck = 0;
830	pfh.family = AF_INET;
831
832	err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len,
833			0, &ipc, &rt, msg->msg_flags);
834	if (err)
835		ip_flush_pending_frames(sk);
836	else
837		err = ping_v4_push_pending_frames(sk, &pfh, &fl4);
838	release_sock(sk);
839
840out:
841	ip_rt_put(rt);
842out_free:
843	if (free)
844		kfree(ipc.opt);
845	if (!err) {
846		icmp_out_count(sock_net(sk), user_icmph.type);
847		return len;
848	}
849	return err;
850
851do_confirm:
852	if (msg->msg_flags & MSG_PROBE)
853		dst_confirm_neigh(&rt->dst, &fl4.daddr);
854	if (!(msg->msg_flags & MSG_PROBE) || len)
855		goto back_from_confirm;
856	err = 0;
857	goto out;
858}
859
860int ping_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
861		 int flags, int *addr_len)
862{
863	struct inet_sock *isk = inet_sk(sk);
864	int family = sk->sk_family;
865	struct sk_buff *skb;
866	int copied, err;
867
868	pr_debug("ping_recvmsg(sk=%p,sk->num=%u)\n", isk, isk->inet_num);
869
870	err = -EOPNOTSUPP;
871	if (flags & MSG_OOB)
872		goto out;
873
874	if (flags & MSG_ERRQUEUE)
875		return inet_recv_error(sk, msg, len, addr_len);
876
877	skb = skb_recv_datagram(sk, flags, noblock, &err);
878	if (!skb)
879		goto out;
880
881	copied = skb->len;
882	if (copied > len) {
883		msg->msg_flags |= MSG_TRUNC;
884		copied = len;
885	}
886
887	/* Don't bother checking the checksum */
888	err = skb_copy_datagram_msg(skb, 0, msg, copied);
889	if (err)
890		goto done;
891
892	sock_recv_timestamp(msg, sk, skb);
893
894	/* Copy the address and add cmsg data. */
895	if (family == AF_INET) {
896		DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name);
897
898		if (sin) {
899			sin->sin_family = AF_INET;
900			sin->sin_port = 0 /* skb->h.uh->source */;
901			sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
902			memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
903			*addr_len = sizeof(*sin);
904		}
905
906		if (isk->cmsg_flags)
907			ip_cmsg_recv(msg, skb);
908
909#if IS_ENABLED(CONFIG_IPV6)
910	} else if (family == AF_INET6) {
911		struct ipv6_pinfo *np = inet6_sk(sk);
912		struct ipv6hdr *ip6 = ipv6_hdr(skb);
913		DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name);
914
915		if (sin6) {
916			sin6->sin6_family = AF_INET6;
917			sin6->sin6_port = 0;
918			sin6->sin6_addr = ip6->saddr;
919			sin6->sin6_flowinfo = 0;
920			if (np->sndflow)
921				sin6->sin6_flowinfo = ip6_flowinfo(ip6);
922			sin6->sin6_scope_id =
923				ipv6_iface_scope_id(&sin6->sin6_addr,
924						    inet6_iif(skb));
925			*addr_len = sizeof(*sin6);
926		}
927
928		if (inet6_sk(sk)->rxopt.all)
929			pingv6_ops.ip6_datagram_recv_common_ctl(sk, msg, skb);
930		if (skb->protocol == htons(ETH_P_IPV6) &&
931		    inet6_sk(sk)->rxopt.all)
932			pingv6_ops.ip6_datagram_recv_specific_ctl(sk, msg, skb);
933		else if (skb->protocol == htons(ETH_P_IP) && isk->cmsg_flags)
934			ip_cmsg_recv(msg, skb);
935#endif
936	} else {
937		BUG();
938	}
939
940	err = copied;
941
942done:
943	skb_free_datagram(sk, skb);
944out:
945	pr_debug("ping_recvmsg -> %d\n", err);
946	return err;
947}
948EXPORT_SYMBOL_GPL(ping_recvmsg);
949
950int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
951{
952	pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
953		 inet_sk(sk), inet_sk(sk)->inet_num, skb);
954	if (sock_queue_rcv_skb(sk, skb) < 0) {
955		kfree_skb(skb);
956		pr_debug("ping_queue_rcv_skb -> failed\n");
957		return -1;
958	}
959	return 0;
960}
961EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
962
963
964/*
965 *	All we need to do is get the socket.
966 */
967
968bool ping_rcv(struct sk_buff *skb)
969{
970	struct sock *sk;
971	struct net *net = dev_net(skb->dev);
972	struct icmphdr *icmph = icmp_hdr(skb);
973	bool rc = false;
974
975	/* We assume the packet has already been checked by icmp_rcv */
976
977	pr_debug("ping_rcv(skb=%p,id=%04x,seq=%04x)\n",
978		 skb, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence));
979
980	/* Push ICMP header back */
981	skb_push(skb, skb->data - (u8 *)icmph);
982
983	sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
984	if (sk) {
985		struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
986
987		pr_debug("rcv on socket %p\n", sk);
988		if (skb2 && !ping_queue_rcv_skb(sk, skb2))
989			rc = true;
990		sock_put(sk);
991	}
992
993	if (!rc)
994		pr_debug("no socket, dropping\n");
995
996	return rc;
997}
998EXPORT_SYMBOL_GPL(ping_rcv);
999
1000struct proto ping_prot = {
1001	.name =		"PING",
1002	.owner =	THIS_MODULE,
1003	.init =		ping_init_sock,
1004	.close =	ping_close,
1005	.connect =	ip4_datagram_connect,
1006	.disconnect =	__udp_disconnect,
1007	.setsockopt =	ip_setsockopt,
1008	.getsockopt =	ip_getsockopt,
1009	.sendmsg =	ping_v4_sendmsg,
1010	.recvmsg =	ping_recvmsg,
1011	.bind =		ping_bind,
1012	.backlog_rcv =	ping_queue_rcv_skb,
1013	.release_cb =	ip4_datagram_release_cb,
1014	.hash =		ping_hash,
1015	.unhash =	ping_unhash,
1016	.get_port =	ping_get_port,
1017	.obj_size =	sizeof(struct inet_sock),
1018};
1019EXPORT_SYMBOL(ping_prot);
1020
1021#ifdef CONFIG_PROC_FS
1022
1023static struct sock *ping_get_first(struct seq_file *seq, int start)
1024{
1025	struct sock *sk;
1026	struct ping_iter_state *state = seq->private;
1027	struct net *net = seq_file_net(seq);
1028
1029	for (state->bucket = start; state->bucket < PING_HTABLE_SIZE;
1030	     ++state->bucket) {
1031		struct hlist_nulls_node *node;
1032		struct hlist_nulls_head *hslot;
1033
1034		hslot = &ping_table.hash[state->bucket];
1035
1036		if (hlist_nulls_empty(hslot))
1037			continue;
1038
1039		sk_nulls_for_each(sk, node, hslot) {
1040			if (net_eq(sock_net(sk), net) &&
1041			    sk->sk_family == state->family)
1042				goto found;
1043		}
1044	}
1045	sk = NULL;
1046found:
1047	return sk;
1048}
1049
1050static struct sock *ping_get_next(struct seq_file *seq, struct sock *sk)
1051{
1052	struct ping_iter_state *state = seq->private;
1053	struct net *net = seq_file_net(seq);
1054
1055	do {
1056		sk = sk_nulls_next(sk);
1057	} while (sk && (!net_eq(sock_net(sk), net)));
1058
1059	if (!sk)
1060		return ping_get_first(seq, state->bucket + 1);
1061	return sk;
1062}
1063
1064static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos)
1065{
1066	struct sock *sk = ping_get_first(seq, 0);
1067
1068	if (sk)
1069		while (pos && (sk = ping_get_next(seq, sk)) != NULL)
1070			--pos;
1071	return pos ? NULL : sk;
1072}
1073
1074void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family)
1075	__acquires(ping_table.lock)
1076{
1077	struct ping_iter_state *state = seq->private;
1078	state->bucket = 0;
1079	state->family = family;
1080
1081	read_lock_bh(&ping_table.lock);
1082
1083	return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
1084}
1085EXPORT_SYMBOL_GPL(ping_seq_start);
1086
1087static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos)
1088{
1089	return ping_seq_start(seq, pos, AF_INET);
1090}
1091
1092void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
1093{
1094	struct sock *sk;
1095
1096	if (v == SEQ_START_TOKEN)
1097		sk = ping_get_idx(seq, 0);
1098	else
1099		sk = ping_get_next(seq, v);
1100
1101	++*pos;
1102	return sk;
1103}
1104EXPORT_SYMBOL_GPL(ping_seq_next);
1105
1106void ping_seq_stop(struct seq_file *seq, void *v)
1107	__releases(ping_table.lock)
1108{
1109	read_unlock_bh(&ping_table.lock);
1110}
1111EXPORT_SYMBOL_GPL(ping_seq_stop);
1112
1113static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
1114		int bucket)
1115{
1116	struct inet_sock *inet = inet_sk(sp);
1117	__be32 dest = inet->inet_daddr;
1118	__be32 src = inet->inet_rcv_saddr;
1119	__u16 destp = ntohs(inet->inet_dport);
1120	__u16 srcp = ntohs(inet->inet_sport);
1121
1122	seq_printf(f, "%5d: %08X:%04X %08X:%04X"
1123		" %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u",
1124		bucket, src, srcp, dest, destp, sp->sk_state,
1125		sk_wmem_alloc_get(sp),
1126		sk_rmem_alloc_get(sp),
1127		0, 0L, 0,
1128		from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)),
1129		0, sock_i_ino(sp),
1130		refcount_read(&sp->sk_refcnt), sp,
1131		atomic_read(&sp->sk_drops));
1132}
1133
1134static int ping_v4_seq_show(struct seq_file *seq, void *v)
1135{
1136	seq_setwidth(seq, 127);
1137	if (v == SEQ_START_TOKEN)
1138		seq_puts(seq, "  sl  local_address rem_address   st tx_queue "
1139			   "rx_queue tr tm->when retrnsmt   uid  timeout "
1140			   "inode ref pointer drops");
1141	else {
1142		struct ping_iter_state *state = seq->private;
1143
1144		ping_v4_format_sock(v, seq, state->bucket);
1145	}
1146	seq_pad(seq, '\n');
1147	return 0;
1148}
1149
1150static const struct seq_operations ping_v4_seq_ops = {
1151	.start		= ping_v4_seq_start,
1152	.show		= ping_v4_seq_show,
1153	.next		= ping_seq_next,
1154	.stop		= ping_seq_stop,
1155};
1156
1157static int __net_init ping_v4_proc_init_net(struct net *net)
1158{
1159	if (!proc_create_net("icmp", 0444, net->proc_net, &ping_v4_seq_ops,
1160			sizeof(struct ping_iter_state)))
1161		return -ENOMEM;
1162	return 0;
1163}
1164
1165static void __net_exit ping_v4_proc_exit_net(struct net *net)
1166{
1167	remove_proc_entry("icmp", net->proc_net);
1168}
1169
1170static struct pernet_operations ping_v4_net_ops = {
1171	.init = ping_v4_proc_init_net,
1172	.exit = ping_v4_proc_exit_net,
1173};
1174
1175int __init ping_proc_init(void)
1176{
1177	return register_pernet_subsys(&ping_v4_net_ops);
1178}
1179
1180void ping_proc_exit(void)
1181{
1182	unregister_pernet_subsys(&ping_v4_net_ops);
1183}
1184
1185#endif
1186
1187void __init ping_init(void)
1188{
1189	int i;
1190
1191	for (i = 0; i < PING_HTABLE_SIZE; i++)
1192		INIT_HLIST_NULLS_HEAD(&ping_table.hash[i], i);
1193	rwlock_init(&ping_table.lock);
1194}
1195