icmp.c

linux 内核源代码

					.tos = RT_TOS(tos)
				}
			},
			.proto = IPPROTO_ICMP,
			.uli_u = {
				.icmpt = {
					.type = type,
					.code = code
				}
			}
		};
		security_skb_classify_flow(skb_in, &fl);
		if (ip_route_output_key(&rt, &fl))
			goto out_unlock;
	}

	if (!icmpv4_xrlim_allow(rt, type, code))
		goto ende;

	/* RFC says return as much as we can without exceeding 576 bytes. */

	room = dst_mtu(&rt->u.dst);
	if (room > 576)
		room = 576;
	room -= sizeof(struct iphdr) + icmp_param.replyopts.optlen;
	room -= sizeof(struct icmphdr);

	icmp_param.data_len = skb_in->len - icmp_param.offset;
	if (icmp_param.data_len > room)
		icmp_param.data_len = room;
	icmp_param.head_len = sizeof(struct icmphdr);

	icmp_push_reply(&icmp_param, &ipc, rt);
ende:
	ip_rt_put(rt);
out_unlock:
	icmp_xmit_unlock();
out:;
}


/*
 *	Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH.
 */

static void icmp_unreach(struct sk_buff *skb)
{
	struct iphdr *iph;
	struct icmphdr *icmph;
	int hash, protocol;
	struct net_protocol *ipprot;
	struct sock *raw_sk;
	u32 info = 0;

	/*
	 *	Incomplete header ?
	 * 	Only checks for the IP header, there should be an
	 *	additional check for longer headers in upper levels.
	 */

	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
		goto out_err;

	icmph = icmp_hdr(skb);
	iph   = (struct iphdr *)skb->data;

	if (iph->ihl < 5) /* Mangled header, drop. */
		goto out_err;

	if (icmph->type == ICMP_DEST_UNREACH) {
		switch (icmph->code & 15) {
		case ICMP_NET_UNREACH:
		case ICMP_HOST_UNREACH:
		case ICMP_PROT_UNREACH:
		case ICMP_PORT_UNREACH:
			break;
		case ICMP_FRAG_NEEDED:
			if (ipv4_config.no_pmtu_disc) {
				LIMIT_NETDEBUG(KERN_INFO "ICMP: %u.%u.%u.%u: "
							 "fragmentation needed "
							 "and DF set.\n",
					       NIPQUAD(iph->daddr));
			} else {
				info = ip_rt_frag_needed(iph,
						     ntohs(icmph->un.frag.mtu));
				if (!info)
					goto out;
			}
			break;
		case ICMP_SR_FAILED:
			LIMIT_NETDEBUG(KERN_INFO "ICMP: %u.%u.%u.%u: Source "
						 "Route Failed.\n",
				       NIPQUAD(iph->daddr));
			break;
		default:
			break;
		}
		if (icmph->code > NR_ICMP_UNREACH)
			goto out;
	} else if (icmph->type == ICMP_PARAMETERPROB)
		info = ntohl(icmph->un.gateway) >> 24;

	/*
	 *	Throw it at our lower layers
	 *
	 *	RFC 1122: 3.2.2 MUST extract the protocol ID from the passed
	 *		  header.
	 *	RFC 1122: 3.2.2.1 MUST pass ICMP unreach messages to the
	 *		  transport layer.
	 *	RFC 1122: 3.2.2.2 MUST pass ICMP time expired messages to
	 *		  transport layer.
	 */

	/*
	 *	Check the other end isnt violating RFC 1122. Some routers send
	 *	bogus responses to broadcast frames. If you see this message
	 *	first check your netmask matches at both ends, if it does then
	 *	get the other vendor to fix their kit.
	 */

	if (!sysctl_icmp_ignore_bogus_error_responses &&
	    inet_addr_type(iph->daddr) == RTN_BROADCAST) {
		if (net_ratelimit())
			printk(KERN_WARNING "%u.%u.%u.%u sent an invalid ICMP "
					    "type %u, code %u "
					    "error to a broadcast: %u.%u.%u.%u on %s\n",
			       NIPQUAD(ip_hdr(skb)->saddr),
			       icmph->type, icmph->code,
			       NIPQUAD(iph->daddr),
			       skb->dev->name);
		goto out;
	}

	/* Checkin full IP header plus 8 bytes of protocol to
	 * avoid additional coding at protocol handlers.
	 */
	if (!pskb_may_pull(skb, iph->ihl * 4 + 8))
		goto out;

	iph = (struct iphdr *)skb->data;
	protocol = iph->protocol;

	/*
	 *	Deliver ICMP message to raw sockets. Pretty useless feature?
	 */

	/* Note: See raw.c and net/raw.h, RAWV4_HTABLE_SIZE==MAX_INET_PROTOS */
	hash = protocol & (MAX_INET_PROTOS - 1);
	read_lock(&raw_v4_lock);
	if ((raw_sk = sk_head(&raw_v4_htable[hash])) != NULL) {
		while ((raw_sk = __raw_v4_lookup(raw_sk, protocol, iph->daddr,
						 iph->saddr,
						 skb->dev->ifindex)) != NULL) {
			raw_err(raw_sk, skb, info);
			raw_sk = sk_next(raw_sk);
			iph = (struct iphdr *)skb->data;
		}
	}
	read_unlock(&raw_v4_lock);

	rcu_read_lock();
	ipprot = rcu_dereference(inet_protos[hash]);
	if (ipprot && ipprot->err_handler)
		ipprot->err_handler(skb, info);
	rcu_read_unlock();

out:
	return;
out_err:
	ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
	goto out;
}


/*
 *	Handle ICMP_REDIRECT.
 */

static void icmp_redirect(struct sk_buff *skb)
{
	struct iphdr *iph;

	if (skb->len < sizeof(struct iphdr))
		goto out_err;

	/*
	 *	Get the copied header of the packet that caused the redirect
	 */
	if (!pskb_may_pull(skb, sizeof(struct iphdr)))
		goto out;

	iph = (struct iphdr *)skb->data;

	switch (icmp_hdr(skb)->code & 7) {
	case ICMP_REDIR_NET:
	case ICMP_REDIR_NETTOS:
		/*
		 * As per RFC recommendations now handle it as a host redirect.
		 */
	case ICMP_REDIR_HOST:
	case ICMP_REDIR_HOSTTOS:
		ip_rt_redirect(ip_hdr(skb)->saddr, iph->daddr,
			       icmp_hdr(skb)->un.gateway,
			       iph->saddr, skb->dev);
		break;
	}
out:
	return;
out_err:
	ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
	goto out;
}

/*
 *	Handle ICMP_ECHO ("ping") requests.
 *
 *	RFC 1122: 3.2.2.6 MUST have an echo server that answers ICMP echo
 *		  requests.
 *	RFC 1122: 3.2.2.6 Data received in the ICMP_ECHO request MUST be
 *		  included in the reply.
 *	RFC 1812: 4.3.3.6 SHOULD have a config option for silently ignoring
 *		  echo requests, MUST have default=NOT.
 *	See also WRT handling of options once they are done and working.
 */

static void icmp_echo(struct sk_buff *skb)
{
	if (!sysctl_icmp_echo_ignore_all) {
		struct icmp_bxm icmp_param;

		icmp_param.data.icmph	   = *icmp_hdr(skb);
		icmp_param.data.icmph.type = ICMP_ECHOREPLY;
		icmp_param.skb		   = skb;
		icmp_param.offset	   = 0;
		icmp_param.data_len	   = skb->len;
		icmp_param.head_len	   = sizeof(struct icmphdr);
		icmp_reply(&icmp_param, skb);
	}
}

/*
 *	Handle ICMP Timestamp requests.
 *	RFC 1122: 3.2.2.8 MAY implement ICMP timestamp requests.
 *		  SHOULD be in the kernel for minimum random latency.
 *		  MUST be accurate to a few minutes.
 *		  MUST be updated at least at 15Hz.
 */
static void icmp_timestamp(struct sk_buff *skb)
{
	struct timeval tv;
	struct icmp_bxm icmp_param;
	/*
	 *	Too short.
	 */
	if (skb->len < 4)
		goto out_err;

	/*
	 *	Fill in the current time as ms since midnight UT:
	 */
	do_gettimeofday(&tv);
	icmp_param.data.times[1] = htonl((tv.tv_sec % 86400) * 1000 +
					 tv.tv_usec / 1000);
	icmp_param.data.times[2] = icmp_param.data.times[1];
	if (skb_copy_bits(skb, 0, &icmp_param.data.times[0], 4))
		BUG();
	icmp_param.data.icmph	   = *icmp_hdr(skb);
	icmp_param.data.icmph.type = ICMP_TIMESTAMPREPLY;
	icmp_param.data.icmph.code = 0;
	icmp_param.skb		   = skb;
	icmp_param.offset	   = 0;
	icmp_param.data_len	   = 0;
	icmp_param.head_len	   = sizeof(struct icmphdr) + 12;
	icmp_reply(&icmp_param, skb);
out:
	return;
out_err:
	ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
	goto out;
}


/*
 *	Handle ICMP_ADDRESS_MASK requests.  (RFC950)
 *
 * RFC1122 (3.2.2.9).  A host MUST only send replies to
 * ADDRESS_MASK requests if it's been configured as an address mask
 * agent.  Receiving a request doesn't constitute implicit permission to
 * act as one. Of course, implementing this correctly requires (SHOULD)
 * a way to turn the functionality on and off.  Another one for sysctl(),
 * I guess. -- MS
 *
 * RFC1812 (4.3.3.9).	A router MUST implement it.
 *			A router SHOULD have switch turning it on/off.
 *		      	This switch MUST be ON by default.
 *
 * Gratuitous replies, zero-source replies are not implemented,
 * that complies with RFC. DO NOT implement them!!! All the idea
 * of broadcast addrmask replies as specified in RFC950 is broken.
 * The problem is that it is not uncommon to have several prefixes
 * on one physical interface. Moreover, addrmask agent can even be
 * not aware of existing another prefixes.
 * If source is zero, addrmask agent cannot choose correct prefix.
 * Gratuitous mask announcements suffer from the same problem.
 * RFC1812 explains it, but still allows to use ADDRMASK,
 * that is pretty silly. --ANK
 *
 * All these rules are so bizarre, that I removed kernel addrmask
 * support at all. It is wrong, it is obsolete, nobody uses it in
 * any case. --ANK
 *
 * Furthermore you can do it with a usermode address agent program
 * anyway...
 */

static void icmp_address(struct sk_buff *skb)
{
#if 0
	if (net_ratelimit())
		printk(KERN_DEBUG "a guy asks for address mask. Who is it?\n");
#endif
}

/*
 * RFC1812 (4.3.3.9).	A router SHOULD listen all replies, and complain
 *			loudly if an inconsistency is found.
 */

static void icmp_address_reply(struct sk_buff *skb)
{
	struct rtable *rt = (struct rtable *)skb->dst;
	struct net_device *dev = skb->dev;
	struct in_device *in_dev;
	struct in_ifaddr *ifa;

	if (skb->len < 4 || !(rt->rt_flags&RTCF_DIRECTSRC))
		goto out;

	in_dev = in_dev_get(dev);
	if (!in_dev)
		goto out;
	rcu_read_lock();
	if (in_dev->ifa_list &&
	    IN_DEV_LOG_MARTIANS(in_dev) &&
	    IN_DEV_FORWARD(in_dev)) {
		__be32 _mask, *mp;

		mp = skb_header_pointer(skb, 0, sizeof(_mask), &_mask);
		BUG_ON(mp == NULL);
		for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
			if (*mp == ifa->ifa_mask &&
			    inet_ifa_match(rt->rt_src, ifa))
				break;
		}
		if (!ifa && net_ratelimit()) {
			printk(KERN_INFO "Wrong address mask %u.%u.%u.%u from "
					 "%s/%u.%u.%u.%u\n",
			       NIPQUAD(*mp), dev->name, NIPQUAD(rt->rt_src));
		}
	}
	rcu_read_unlock();
	in_dev_put(in_dev);
out:;
}

static void icmp_discard(struct sk_buff *skb)
{
}

/*
 *	Deal with incoming ICMP packets.
 */
int icmp_rcv(struct sk_buff *skb)
{
	struct icmphdr *icmph;
	struct rtable *rt = (struct rtable *)skb->dst;

	ICMP_INC_STATS_BH(ICMP_MIB_INMSGS);

	switch (skb->ip_summed) {
	case CHECKSUM_COMPLETE:
		if (!csum_fold(skb->csum))
			break;
		/* fall through */
	case CHECKSUM_NONE:
		skb->csum = 0;
		if (__skb_checksum_complete(skb))
			goto error;
	}

	if (!pskb_pull(skb, sizeof(struct icmphdr)))
		goto error;

	icmph = icmp_hdr(skb);

	ICMPMSGIN_INC_STATS_BH(icmph->type);
	/*
	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
	 *
	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
	 *		  discarded.
	 */
	if (icmph->type > NR_ICMP_TYPES)
		goto error;


	/*
	 *	Parse the ICMP message
	 */

	if (rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) {
		/*
		 *	RFC 1122: 3.2.2.6 An ICMP_ECHO to broadcast MAY be
		 *	  silently ignored (we let user decide with a sysctl).
		 *	RFC 1122: 3.2.2.8 An ICMP_TIMESTAMP MAY be silently
		 *	  discarded if to broadcast/multicast.
		 */
		if ((icmph->type == ICMP_ECHO ||
		     icmph->type == ICMP_TIMESTAMP) &&
		    sysctl_icmp_echo_ignore_broadcasts) {
			goto error;
		}
		if (icmph->type != ICMP_ECHO &&
		    icmph->type != ICMP_TIMESTAMP &&
		    icmph->type != ICMP_ADDRESS &&
		    icmph->type != ICMP_ADDRESSREPLY) {
			goto error;
		}
	}

	icmp_pointers[icmph->type].handler(skb);

drop:
	kfree_skb(skb);
	return 0;
error:
	ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
	goto drop;
}

/*
 *	This table is the definition of how we handle ICMP.
 */
static const struct icmp_control icmp_pointers[NR_ICMP_TYPES + 1] = {
	[ICMP_ECHOREPLY] = {
		.handler = icmp_discard,
	},
	[1] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[2] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[ICMP_DEST_UNREACH] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_SOURCE_QUENCH] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_REDIRECT] = {
		.handler = icmp_redirect,
		.error = 1,
	},
	[6] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[7] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[ICMP_ECHO] = {
		.handler = icmp_echo,
	},
	[9] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[10] = {
		.handler = icmp_discard,
		.error = 1,
	},
	[ICMP_TIME_EXCEEDED] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_PARAMETERPROB] = {
		.handler = icmp_unreach,
		.error = 1,
	},
	[ICMP_TIMESTAMP] = {
		.handler = icmp_timestamp,
	},
	[ICMP_TIMESTAMPREPLY] = {
		.handler = icmp_discard,
	},
	[ICMP_INFO_REQUEST] = {
		.handler = icmp_discard,
	},
	[ICMP_INFO_REPLY] = {
		.handler = icmp_discard,
	},
	[ICMP_ADDRESS] = {
		.handler = icmp_address,
	},
	[ICMP_ADDRESSREPLY] = {
		.handler = icmp_address_reply,
	},
};

void __init icmp_init(struct net_proto_family *ops)
{
	struct inet_sock *inet;
	int i;

	for_each_possible_cpu(i) {
		int err;

		err = sock_create_kern(PF_INET, SOCK_RAW, IPPROTO_ICMP,
				       &per_cpu(__icmp_socket, i));

		if (err < 0)
			panic("Failed to create the ICMP control socket.\n");

		per_cpu(__icmp_socket, i)->sk->sk_allocation = GFP_ATOMIC;

		/* Enough space for 2 64K ICMP packets, including
		 * sk_buff struct overhead.
		 */
		per_cpu(__icmp_socket, i)->sk->sk_sndbuf =
			(2 * ((64 * 1024) + sizeof(struct sk_buff)));

		inet = inet_sk(per_cpu(__icmp_socket, i)->sk);
		inet->uc_ttl = -1;
		inet->pmtudisc = IP_PMTUDISC_DONT;

		/* Unhash it so that IP input processing does not even
		 * see it, we do not wish this socket to see incoming
		 * packets.
		 */
		per_cpu(__icmp_socket, i)->sk->sk_prot->unhash(per_cpu(__icmp_socket, i)->sk);
	}
}

EXPORT_SYMBOL(icmp_err_convert);
EXPORT_SYMBOL(icmp_send);
EXPORT_SYMBOL(icmp_statistics);
EXPORT_SYMBOL(xrlim_allow);