ip6_output.c

linux 内核源代码

/*
 *	IPv6 output functions
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *
 *	$Id: ip6_output.c,v 1.34 2002/02/01 22:01:04 davem Exp $
 *
 *	Based on linux/net/ipv4/ip_output.c
 *
 *	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:
 *	A.N.Kuznetsov	:	airthmetics in fragmentation.
 *				extension headers are implemented.
 *				route changes now work.
 *				ip6_forward does not confuse sniffers.
 *				etc.
 *
 *      H. von Brand    :       Added missing #include <linux/string.h>
 *	Imran Patel	: 	frag id should be in NBO
 *      Kazunori MIYAZAWA @USAGI
 *			:       add ip6_append_data and related functions
 *				for datagram xmit
 */

#include <linux/errno.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/socket.h>
#include <linux/net.h>
#include <linux/netdevice.h>
#include <linux/if_arp.h>
#include <linux/in6.h>
#include <linux/tcp.h>
#include <linux/route.h>
#include <linux/module.h>

#include <linux/netfilter.h>
#include <linux/netfilter_ipv6.h>

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

#include <net/ipv6.h>
#include <net/ndisc.h>
#include <net/protocol.h>
#include <net/ip6_route.h>
#include <net/addrconf.h>
#include <net/rawv6.h>
#include <net/icmp.h>
#include <net/xfrm.h>
#include <net/checksum.h>

static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *));

static __inline__ void ipv6_select_ident(struct sk_buff *skb, struct frag_hdr *fhdr)
{
	static u32 ipv6_fragmentation_id = 1;
	static DEFINE_SPINLOCK(ip6_id_lock);

	spin_lock_bh(&ip6_id_lock);
	fhdr->identification = htonl(ipv6_fragmentation_id);
	if (++ipv6_fragmentation_id == 0)
		ipv6_fragmentation_id = 1;
	spin_unlock_bh(&ip6_id_lock);
}

static int ip6_output_finish(struct sk_buff *skb)
{
	struct dst_entry *dst = skb->dst;

	if (dst->hh)
		return neigh_hh_output(dst->hh, skb);
	else if (dst->neighbour)
		return dst->neighbour->output(skb);

	IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES);
	kfree_skb(skb);
	return -EINVAL;

}

/* dev_loopback_xmit for use with netfilter. */
static int ip6_dev_loopback_xmit(struct sk_buff *newskb)
{
	skb_reset_mac_header(newskb);
	__skb_pull(newskb, skb_network_offset(newskb));
	newskb->pkt_type = PACKET_LOOPBACK;
	newskb->ip_summed = CHECKSUM_UNNECESSARY;
	BUG_TRAP(newskb->dst);

	netif_rx(newskb);
	return 0;
}


static int ip6_output2(struct sk_buff *skb)
{
	struct dst_entry *dst = skb->dst;
	struct net_device *dev = dst->dev;

	skb->protocol = htons(ETH_P_IPV6);
	skb->dev = dev;

	if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr)) {
		struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL;
		struct inet6_dev *idev = ip6_dst_idev(skb->dst);

		if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) &&
		    ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
					&ipv6_hdr(skb)->saddr)) {
			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);

			/* Do not check for IFF_ALLMULTI; multicast routing
			   is not supported in any case.
			 */
			if (newskb)
				NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, newskb, NULL,
					newskb->dev,
					ip6_dev_loopback_xmit);

			if (ipv6_hdr(skb)->hop_limit == 0) {
				IP6_INC_STATS(idev, IPSTATS_MIB_OUTDISCARDS);
				kfree_skb(skb);
				return 0;
			}
		}

		IP6_INC_STATS(idev, IPSTATS_MIB_OUTMCASTPKTS);
	}

	return NF_HOOK(PF_INET6, NF_IP6_POST_ROUTING, skb,NULL, skb->dev,ip6_output_finish);
}

static inline int ip6_skb_dst_mtu(struct sk_buff *skb)
{
	struct ipv6_pinfo *np = skb->sk ? inet6_sk(skb->sk) : NULL;

	return (np && np->pmtudisc == IPV6_PMTUDISC_PROBE) ?
	       skb->dst->dev->mtu : dst_mtu(skb->dst);
}

int ip6_output(struct sk_buff *skb)
{
	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
				dst_allfrag(skb->dst))
		return ip6_fragment(skb, ip6_output2);
	else
		return ip6_output2(skb);
}

/*
 *	xmit an sk_buff (used by TCP)
 */

int ip6_xmit(struct sock *sk, struct sk_buff *skb, struct flowi *fl,
	     struct ipv6_txoptions *opt, int ipfragok)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct in6_addr *first_hop = &fl->fl6_dst;
	struct dst_entry *dst = skb->dst;
	struct ipv6hdr *hdr;
	u8  proto = fl->proto;
	int seg_len = skb->len;
	int hlimit, tclass;
	u32 mtu;

	if (opt) {
		unsigned int head_room;

		/* First: exthdrs may take lots of space (~8K for now)
		   MAX_HEADER is not enough.
		 */
		head_room = opt->opt_nflen + opt->opt_flen;
		seg_len += head_room;
		head_room += sizeof(struct ipv6hdr) + LL_RESERVED_SPACE(dst->dev);

		if (skb_headroom(skb) < head_room) {
			struct sk_buff *skb2 = skb_realloc_headroom(skb, head_room);
			if (skb2 == NULL) {
				IP6_INC_STATS(ip6_dst_idev(skb->dst),
					      IPSTATS_MIB_OUTDISCARDS);
				kfree_skb(skb);
				return -ENOBUFS;
			}
			kfree_skb(skb);
			skb = skb2;
			if (sk)
				skb_set_owner_w(skb, sk);
		}
		if (opt->opt_flen)
			ipv6_push_frag_opts(skb, opt, &proto);
		if (opt->opt_nflen)
			ipv6_push_nfrag_opts(skb, opt, &proto, &first_hop);
	}

	skb_push(skb, sizeof(struct ipv6hdr));
	skb_reset_network_header(skb);
	hdr = ipv6_hdr(skb);

	/*
	 *	Fill in the IPv6 header
	 */

	hlimit = -1;
	if (np)
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = dst_metric(dst, RTAX_HOPLIMIT);
	if (hlimit < 0)
		hlimit = ipv6_get_hoplimit(dst->dev);

	tclass = -1;
	if (np)
		tclass = np->tclass;
	if (tclass < 0)
		tclass = 0;

	*(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | fl->fl6_flowlabel;

	hdr->payload_len = htons(seg_len);
	hdr->nexthdr = proto;
	hdr->hop_limit = hlimit;

	ipv6_addr_copy(&hdr->saddr, &fl->fl6_src);
	ipv6_addr_copy(&hdr->daddr, first_hop);

	skb->priority = sk->sk_priority;

	mtu = dst_mtu(dst);
	if ((skb->len <= mtu) || ipfragok || skb_is_gso(skb)) {
		IP6_INC_STATS(ip6_dst_idev(skb->dst),
			      IPSTATS_MIB_OUTREQUESTS);
		return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev,
				dst_output);
	}

	if (net_ratelimit())
		printk(KERN_DEBUG "IPv6: sending pkt_too_big to self\n");
	skb->dev = dst->dev;
	icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, skb->dev);
	IP6_INC_STATS(ip6_dst_idev(skb->dst), IPSTATS_MIB_FRAGFAILS);
	kfree_skb(skb);
	return -EMSGSIZE;
}

EXPORT_SYMBOL(ip6_xmit);

/*
 *	To avoid extra problems ND packets are send through this
 *	routine. It's code duplication but I really want to avoid
 *	extra checks since ipv6_build_header is used by TCP (which
 *	is for us performance critical)
 */

int ip6_nd_hdr(struct sock *sk, struct sk_buff *skb, struct net_device *dev,
	       struct in6_addr *saddr, struct in6_addr *daddr,
	       int proto, int len)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct ipv6hdr *hdr;
	int totlen;

	skb->protocol = htons(ETH_P_IPV6);
	skb->dev = dev;

	totlen = len + sizeof(struct ipv6hdr);

	skb_reset_network_header(skb);
	skb_put(skb, sizeof(struct ipv6hdr));
	hdr = ipv6_hdr(skb);

	*(__be32*)hdr = htonl(0x60000000);

	hdr->payload_len = htons(len);
	hdr->nexthdr = proto;
	hdr->hop_limit = np->hop_limit;

	ipv6_addr_copy(&hdr->saddr, saddr);
	ipv6_addr_copy(&hdr->daddr, daddr);

	return 0;
}

static int ip6_call_ra_chain(struct sk_buff *skb, int sel)
{
	struct ip6_ra_chain *ra;
	struct sock *last = NULL;

	read_lock(&ip6_ra_lock);
	for (ra = ip6_ra_chain; ra; ra = ra->next) {
		struct sock *sk = ra->sk;
		if (sk && ra->sel == sel &&
		    (!sk->sk_bound_dev_if ||
		     sk->sk_bound_dev_if == skb->dev->ifindex)) {
			if (last) {
				struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
				if (skb2)
					rawv6_rcv(last, skb2);
			}
			last = sk;
		}
	}

	if (last) {
		rawv6_rcv(last, skb);
		read_unlock(&ip6_ra_lock);
		return 1;
	}
	read_unlock(&ip6_ra_lock);
	return 0;
}

static int ip6_forward_proxy_check(struct sk_buff *skb)
{
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	u8 nexthdr = hdr->nexthdr;
	int offset;

	if (ipv6_ext_hdr(nexthdr)) {
		offset = ipv6_skip_exthdr(skb, sizeof(*hdr), &nexthdr);
		if (offset < 0)
			return 0;
	} else
		offset = sizeof(struct ipv6hdr);

	if (nexthdr == IPPROTO_ICMPV6) {
		struct icmp6hdr *icmp6;

		if (!pskb_may_pull(skb, (skb_network_header(skb) +
					 offset + 1 - skb->data)))
			return 0;

		icmp6 = (struct icmp6hdr *)(skb_network_header(skb) + offset);

		switch (icmp6->icmp6_type) {
		case NDISC_ROUTER_SOLICITATION:
		case NDISC_ROUTER_ADVERTISEMENT:
		case NDISC_NEIGHBOUR_SOLICITATION:
		case NDISC_NEIGHBOUR_ADVERTISEMENT:
		case NDISC_REDIRECT:
			/* For reaction involving unicast neighbor discovery
			 * message destined to the proxied address, pass it to
			 * input function.
			 */
			return 1;
		default:
			break;
		}
	}

	/*
	 * The proxying router can't forward traffic sent to a link-local
	 * address, so signal the sender and discard the packet. This
	 * behavior is clarified by the MIPv6 specification.
	 */
	if (ipv6_addr_type(&hdr->daddr) & IPV6_ADDR_LINKLOCAL) {
		dst_link_failure(skb);
		return -1;
	}

	return 0;
}

static inline int ip6_forward_finish(struct sk_buff *skb)
{
	return dst_output(skb);
}

int ip6_forward(struct sk_buff *skb)
{
	struct dst_entry *dst = skb->dst;
	struct ipv6hdr *hdr = ipv6_hdr(skb);
	struct inet6_skb_parm *opt = IP6CB(skb);

	if (ipv6_devconf.forwarding == 0)
		goto error;

	if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) {
		IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	skb_forward_csum(skb);

	/*
	 *	We DO NOT make any processing on
	 *	RA packets, pushing them to user level AS IS
	 *	without ane WARRANTY that application will be able
	 *	to interpret them. The reason is that we
	 *	cannot make anything clever here.
	 *
	 *	We are not end-node, so that if packet contains
	 *	AH/ESP, we cannot make anything.
	 *	Defragmentation also would be mistake, RA packets
	 *	cannot be fragmented, because there is no warranty
	 *	that different fragments will go along one path. --ANK
	 */
	if (opt->ra) {
		u8 *ptr = skb_network_header(skb) + opt->ra;
		if (ip6_call_ra_chain(skb, (ptr[2]<<8) + ptr[3]))
			return 0;
	}

	/*
	 *	check and decrement ttl
	 */
	if (hdr->hop_limit <= 1) {
		/* Force OUTPUT device used as source address */
		skb->dev = dst->dev;
		icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT,
			    0, skb->dev);
		IP6_INC_STATS_BH(ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS);

		kfree_skb(skb);
		return -ETIMEDOUT;
	}

	/* XXX: idev->cnf.proxy_ndp? */
	if (ipv6_devconf.proxy_ndp &&
	    pneigh_lookup(&nd_tbl, &hdr->daddr, skb->dev, 0)) {
		int proxied = ip6_forward_proxy_check(skb);
		if (proxied > 0)
			return ip6_input(skb);
		else if (proxied < 0) {
			IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
			goto drop;
		}
	}

	if (!xfrm6_route_forward(skb)) {
		IP6_INC_STATS(ip6_dst_idev(dst), IPSTATS_MIB_INDISCARDS);
		goto drop;
	}
	dst = skb->dst;

	/* IPv6 specs say nothing about it, but it is clear that we cannot
	   send redirects to source routed frames.
	   We don't send redirects to frames decapsulated from IPsec.
	 */
	if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0 &&
	    !skb->sp) {
		struct in6_addr *target = NULL;
		struct rt6_info *rt;
		struct neighbour *n = dst->neighbour;

		/*
		 *	incoming and outgoing devices are the same
		 *	send a redirect.
		 */

		rt = (struct rt6_info *) dst;
		if ((rt->rt6i_flags & RTF_GATEWAY))
			target = (struct in6_addr*)&n->primary_key;
		else
			target = &hdr->daddr;

		/* Limit redirects both by destination (here)
		   and by source (inside ndisc_send_redirect)
		 */
		if (xrlim_allow(dst, 1*HZ))
			ndisc_send_redirect(skb, n, target);
	} else {
		int addrtype = ipv6_addr_type(&hdr->saddr);

		/* This check is security critical. */
		if (addrtype & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK))
			goto error;
		if (addrtype & IPV6_ADDR_LINKLOCAL) {
			icmpv6_send(skb, ICMPV6_DEST_UNREACH,
				ICMPV6_NOT_NEIGHBOUR, 0, skb->dev);
			goto error;
		}
	}

	if (skb->len > dst_mtu(dst)) {
		/* Again, force OUTPUT device used as source address */
		skb->dev = dst->dev;
		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_mtu(dst), skb->dev);