icmp.c

linux 内核源代码

/*
 *	Internet Control Message Protocol (ICMPv6)
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *
 *	$Id: icmp.c,v 1.38 2002/02/08 03:57:19 davem Exp $
 *
 *	Based on net/ipv4/icmp.c
 *
 *	RFC 1885
 *
 *	This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

/*
 *	Changes:
 *
 *	Andi Kleen		:	exception handling
 *	Andi Kleen			add rate limits. never reply to a icmp.
 *					add more length checks and other fixes.
 *	yoshfuji		:	ensure to sent parameter problem for
 *					fragments.
 *	YOSHIFUJI Hideaki @USAGI:	added sysctl for icmp rate limit.
 *	Randy Dunlap and
 *	YOSHIFUJI Hideaki @USAGI:	Per-interface statistics support
 *	Kazunori MIYAZAWA @USAGI:       change output process to use ip6_append_data
 */

#include <linux/module.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/in.h>
#include <linux/kernel.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/netfilter.h>

#ifdef CONFIG_SYSCTL
#include <linux/sysctl.h>
#endif

#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/icmpv6.h>

#include <net/ip.h>
#include <net/sock.h>

#include <net/ipv6.h>
#include <net/ip6_checksum.h>
#include <net/protocol.h>
#include <net/raw.h>
#include <net/rawv6.h>
#include <net/transp_v6.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/icmp.h>

#include <asm/uaccess.h>
#include <asm/system.h>

DEFINE_SNMP_STAT(struct icmpv6_mib, icmpv6_statistics) __read_mostly;
EXPORT_SYMBOL(icmpv6_statistics);
DEFINE_SNMP_STAT(struct icmpv6msg_mib, icmpv6msg_statistics) __read_mostly;
EXPORT_SYMBOL(icmpv6msg_statistics);

/*
 *	The ICMP socket(s). This is the most convenient way to flow control
 *	our ICMP output as well as maintain a clean interface throughout
 *	all layers. All Socketless IP sends will soon be gone.
 *
 *	On SMP we have one ICMP socket per-cpu.
 */
static DEFINE_PER_CPU(struct socket *, __icmpv6_socket) = NULL;
#define icmpv6_socket	__get_cpu_var(__icmpv6_socket)

static int icmpv6_rcv(struct sk_buff *skb);

static struct inet6_protocol icmpv6_protocol = {
	.handler	=	icmpv6_rcv,
	.flags		=	INET6_PROTO_FINAL,
};

static __inline__ int icmpv6_xmit_lock(void)
{
	local_bh_disable();

	if (unlikely(!spin_trylock(&icmpv6_socket->sk->sk_lock.slock))) {
		/* This can happen if the output path (f.e. SIT or
		 * ip6ip6 tunnel) signals dst_link_failure() for an
		 * outgoing ICMP6 packet.
		 */
		local_bh_enable();
		return 1;
	}
	return 0;
}

static __inline__ void icmpv6_xmit_unlock(void)
{
	spin_unlock_bh(&icmpv6_socket->sk->sk_lock.slock);
}

/*
 * Slightly more convenient version of icmpv6_send.
 */
void icmpv6_param_prob(struct sk_buff *skb, int code, int pos)
{
	icmpv6_send(skb, ICMPV6_PARAMPROB, code, pos, skb->dev);
	kfree_skb(skb);
}

/*
 * Figure out, may we reply to this packet with icmp error.
 *
 * We do not reply, if:
 *	- it was icmp error message.
 *	- it is truncated, so that it is known, that protocol is ICMPV6
 *	  (i.e. in the middle of some exthdr)
 *
 *	--ANK (980726)
 */

static int is_ineligible(struct sk_buff *skb)
{
	int ptr = (u8 *)(ipv6_hdr(skb) + 1) - skb->data;
	int len = skb->len - ptr;
	__u8 nexthdr = ipv6_hdr(skb)->nexthdr;

	if (len < 0)
		return 1;

	ptr = ipv6_skip_exthdr(skb, ptr, &nexthdr);
	if (ptr < 0)
		return 0;
	if (nexthdr == IPPROTO_ICMPV6) {
		u8 _type, *tp;
		tp = skb_header_pointer(skb,
			ptr+offsetof(struct icmp6hdr, icmp6_type),
			sizeof(_type), &_type);
		if (tp == NULL ||
		    !(*tp & ICMPV6_INFOMSG_MASK))
			return 1;
	}
	return 0;
}

static int sysctl_icmpv6_time __read_mostly = 1*HZ;

/*
 * Check the ICMP output rate limit
 */
static inline int icmpv6_xrlim_allow(struct sock *sk, int type,
				     struct flowi *fl)
{
	struct dst_entry *dst;
	int res = 0;

	/* Informational messages are not limited. */
	if (type & ICMPV6_INFOMSG_MASK)
		return 1;

	/* Do not limit pmtu discovery, it would break it. */
	if (type == ICMPV6_PKT_TOOBIG)
		return 1;

	/*
	 * Look up the output route.
	 * XXX: perhaps the expire for routing entries cloned by
	 * this lookup should be more aggressive (not longer than timeout).
	 */
	dst = ip6_route_output(sk, fl);
	if (dst->error) {
		IP6_INC_STATS(ip6_dst_idev(dst),
			      IPSTATS_MIB_OUTNOROUTES);
	} else if (dst->dev && (dst->dev->flags&IFF_LOOPBACK)) {
		res = 1;
	} else {
		struct rt6_info *rt = (struct rt6_info *)dst;
		int tmo = sysctl_icmpv6_time;

		/* Give more bandwidth to wider prefixes. */
		if (rt->rt6i_dst.plen < 128)
			tmo >>= ((128 - rt->rt6i_dst.plen)>>5);

		res = xrlim_allow(dst, tmo);
	}
	dst_release(dst);
	return res;
}

/*
 *	an inline helper for the "simple" if statement below
 *	checks if parameter problem report is caused by an
 *	unrecognized IPv6 option that has the Option Type
 *	highest-order two bits set to 10
 */

static __inline__ int opt_unrec(struct sk_buff *skb, __u32 offset)
{
	u8 _optval, *op;

	offset += skb_network_offset(skb);
	op = skb_header_pointer(skb, offset, sizeof(_optval), &_optval);
	if (op == NULL)
		return 1;
	return (*op & 0xC0) == 0x80;
}

static int icmpv6_push_pending_frames(struct sock *sk, struct flowi *fl, struct icmp6hdr *thdr, int len)
{
	struct sk_buff *skb;
	struct icmp6hdr *icmp6h;
	int err = 0;

	if ((skb = skb_peek(&sk->sk_write_queue)) == NULL)
		goto out;

	icmp6h = icmp6_hdr(skb);
	memcpy(icmp6h, thdr, sizeof(struct icmp6hdr));
	icmp6h->icmp6_cksum = 0;

	if (skb_queue_len(&sk->sk_write_queue) == 1) {
		skb->csum = csum_partial((char *)icmp6h,
					sizeof(struct icmp6hdr), skb->csum);
		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
						      &fl->fl6_dst,
						      len, fl->proto,
						      skb->csum);
	} else {
		__wsum tmp_csum = 0;

		skb_queue_walk(&sk->sk_write_queue, skb) {
			tmp_csum = csum_add(tmp_csum, skb->csum);
		}

		tmp_csum = csum_partial((char *)icmp6h,
					sizeof(struct icmp6hdr), tmp_csum);
		icmp6h->icmp6_cksum = csum_ipv6_magic(&fl->fl6_src,
						      &fl->fl6_dst,
						      len, fl->proto,
						      tmp_csum);
	}
	ip6_push_pending_frames(sk);
out:
	return err;
}

struct icmpv6_msg {
	struct sk_buff	*skb;
	int		offset;
	uint8_t		type;
};

static int icmpv6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb)
{
	struct icmpv6_msg *msg = (struct icmpv6_msg *) from;
	struct sk_buff *org_skb = msg->skb;
	__wsum csum = 0;

	csum = skb_copy_and_csum_bits(org_skb, msg->offset + offset,
				      to, len, csum);
	skb->csum = csum_block_add(skb->csum, csum, odd);
	if (!(msg->type & ICMPV6_INFOMSG_MASK))
		nf_ct_attach(skb, org_skb);
	return 0;
}

#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE)
static void mip6_addr_swap(struct sk_buff *skb)
{
	struct ipv6hdr *iph = ipv6_hdr(skb);
	struct inet6_skb_parm *opt = IP6CB(skb);
	struct ipv6_destopt_hao *hao;
	struct in6_addr tmp;
	int off;

	if (opt->dsthao) {
		off = ipv6_find_tlv(skb, opt->dsthao, IPV6_TLV_HAO);
		if (likely(off >= 0)) {
			hao = (struct ipv6_destopt_hao *)
					(skb_network_header(skb) + off);
			ipv6_addr_copy(&tmp, &iph->saddr);
			ipv6_addr_copy(&iph->saddr, &hao->addr);
			ipv6_addr_copy(&hao->addr, &tmp);
		}
	}
}
#else
static inline void mip6_addr_swap(struct sk_buff *skb) {}
#endif

/*
 *	Send an ICMP message in response to a packet in error
 */
void icmpv6_send(struct sk_buff *skb, int type, int code, __u32 info,
		 struct net_device *dev)
{
	struct inet6_dev *idev = NULL;
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct sock *sk;
	struct ipv6_pinfo *np;
	struct in6_addr *saddr = NULL;
	struct dst_entry *dst;
	struct icmp6hdr tmp_hdr;
	struct flowi fl;
	struct icmpv6_msg msg;
	int iif = 0;
	int addr_type = 0;
	int len;
	int hlimit, tclass;
	int err = 0;

	if ((u8 *)hdr < skb->head ||
	    (skb->network_header + sizeof(*hdr)) > skb->tail)
		return;

	/*
	 *	Make sure we respect the rules
	 *	i.e. RFC 1885 2.4(e)
	 *	Rule (e.1) is enforced by not using icmpv6_send
	 *	in any code that processes icmp errors.
	 */
	addr_type = ipv6_addr_type(&hdr->daddr);

	if (ipv6_chk_addr(&hdr->daddr, skb->dev, 0))
		saddr = &hdr->daddr;

	/*
	 *	Dest addr check
	 */

	if ((addr_type & IPV6_ADDR_MULTICAST || skb->pkt_type != PACKET_HOST)) {
		if (type != ICMPV6_PKT_TOOBIG &&
		    !(type == ICMPV6_PARAMPROB &&
		      code == ICMPV6_UNK_OPTION &&
		      (opt_unrec(skb, info))))
			return;

		saddr = NULL;
	}

	addr_type = ipv6_addr_type(&hdr->saddr);

	/*
	 *	Source addr check
	 */

	if (addr_type & IPV6_ADDR_LINKLOCAL)
		iif = skb->dev->ifindex;

	/*
	 *	Must not send error if the source does not uniquely
	 *	identify a single node (RFC2463 Section 2.4).
	 *	We check unspecified / multicast addresses here,
	 *	and anycast addresses will be checked later.
	 */
	if ((addr_type == IPV6_ADDR_ANY) || (addr_type & IPV6_ADDR_MULTICAST)) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: addr_any/mcast source\n");
		return;
	}

	/*
	 *	Never answer to a ICMP packet.
	 */
	if (is_ineligible(skb)) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: no reply to icmp error\n");
		return;
	}

	mip6_addr_swap(skb);

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_ICMPV6;
	ipv6_addr_copy(&fl.fl6_dst, &hdr->saddr);
	if (saddr)
		ipv6_addr_copy(&fl.fl6_src, saddr);
	fl.oif = iif;
	fl.fl_icmp_type = type;
	fl.fl_icmp_code = code;
	security_skb_classify_flow(skb, &fl);

	if (icmpv6_xmit_lock())
		return;

	sk = icmpv6_socket->sk;
	np = inet6_sk(sk);

	if (!icmpv6_xrlim_allow(sk, type, &fl))
		goto out;

	tmp_hdr.icmp6_type = type;
	tmp_hdr.icmp6_code = code;
	tmp_hdr.icmp6_cksum = 0;
	tmp_hdr.icmp6_pointer = htonl(info);

	if (!fl.oif && ipv6_addr_is_multicast(&fl.fl6_dst))
		fl.oif = np->mcast_oif;

	err = ip6_dst_lookup(sk, &dst, &fl);
	if (err)
		goto out;

	/*
	 * We won't send icmp if the destination is known
	 * anycast.
	 */
	if (((struct rt6_info *)dst)->rt6i_flags & RTF_ANYCAST) {
		LIMIT_NETDEBUG(KERN_DEBUG "icmpv6_send: acast source\n");
		goto out_dst_release;
	}

	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
		goto out;

	if (ipv6_addr_is_multicast(&fl.fl6_dst))
		hlimit = np->mcast_hops;
	else
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
	if (hlimit < 0)
		hlimit = ipv6_get_hoplimit(dst->dev);

	tclass = np->tclass;
	if (tclass < 0)
		tclass = 0;

	msg.skb = skb;
	msg.offset = skb_network_offset(skb);
	msg.type = type;

	len = skb->len - msg.offset;