ip6_output.c

Linux Kernel 2.6.9 for OMAP1710

/*
 *	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/config.h>
#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/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 **pskb, 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 spinlock_t ip6_id_lock = SPIN_LOCK_UNLOCKED;

	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 inline int ip6_output_finish(struct sk_buff *skb)
{

	struct dst_entry *dst = skb->dst;
	struct hh_cache *hh = dst->hh;

	if (hh) {
		int hh_alen;

		read_lock_bh(&hh->hh_lock);
		hh_alen = HH_DATA_ALIGN(hh->hh_len);
		memcpy(skb->data - hh_alen, hh->hh_data, hh_alen);
		read_unlock_bh(&hh->hh_lock);
	        skb_push(skb, hh->hh_len);
		return hh->hh_output(skb);
	} else if (dst->neighbour)
		return dst->neighbour->output(skb);

	IP6_INC_STATS_BH(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)
{
	newskb->mac.raw = newskb->data;
	__skb_pull(newskb, newskb->nh.raw - newskb->data);
	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 **pskb)
{
	struct sk_buff *skb = *pskb;
	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(&skb->nh.ipv6h->daddr)) {
		struct ipv6_pinfo* np = skb->sk ? inet6_sk(skb->sk) : NULL;

		if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) &&
		    ipv6_chk_mcast_addr(dev, &skb->nh.ipv6h->daddr,
				&skb->nh.ipv6h->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 (skb->nh.ipv6h->hop_limit == 0) {
				IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
				kfree_skb(skb);
				return 0;
			}
		}

		IP6_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS);
	}

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

int ip6_output(struct sk_buff **pskb)
{
	struct sk_buff *skb = *pskb;

	if ((skb->len > dst_pmtu(skb->dst) || skb_shinfo(skb)->frag_list))
		return ip6_fragment(pskb, ip6_output2);
	else
		return ip6_output2(pskb);
}

#ifdef CONFIG_NETFILTER
int ip6_route_me_harder(struct sk_buff *skb)
{
	struct ipv6hdr *iph = skb->nh.ipv6h;
	struct dst_entry *dst;
	struct flowi fl = {
		.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0,
		.nl_u =
		{ .ip6_u =
		  { .daddr = iph->daddr,
		    .saddr = iph->saddr, } },
		.proto = iph->nexthdr,
	};

	dst = ip6_route_output(skb->sk, &fl);

	if (dst->error) {
		IP6_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
		LIMIT_NETDEBUG(
			printk(KERN_DEBUG "ip6_route_me_harder: No more route.\n"));
		dst_release(dst);
		return -EINVAL;
	}

	/* Drop old route. */
	dst_release(skb->dst);

	skb->dst = dst;
	return 0;
}
#endif

static inline int ip6_maybe_reroute(struct sk_buff *skb)
{
#ifdef CONFIG_NETFILTER
	if (skb->nfcache & NFC_ALTERED){
		if (ip6_route_me_harder(skb) != 0){
			kfree_skb(skb);
			return -EINVAL;
		}
	}
#endif /* CONFIG_NETFILTER */
	return dst_output(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 = sk ? inet6_sk(sk) : NULL;
	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;
	u32 mtu;

	if (opt) {
		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);
			kfree_skb(skb);
			skb = skb2;
			if (skb == NULL) {	
				IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
				return -ENOBUFS;
			}
			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);
	}

	hdr = skb->nh.ipv6h = (struct ipv6hdr*)skb_push(skb, sizeof(struct ipv6hdr));

	/*
	 *	Fill in the IPv6 header
	 */

	*(u32*)hdr = htonl(0x60000000) | fl->fl6_flowlabel;
	hlimit = -1;
	if (np)
		hlimit = np->hop_limit;
	if (hlimit < 0)
		hlimit = dst_metric(dst, RTAX_HOPLIMIT);

	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);

	mtu = dst_pmtu(dst);
	if ((skb->len <= mtu) || ipfragok) {
		IP6_INC_STATS(IPSTATS_MIB_OUTREQUESTS);
		return NF_HOOK(PF_INET6, NF_IP6_LOCAL_OUT, skb, NULL, dst->dev, ip6_maybe_reroute);
	}

	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(IPSTATS_MIB_FRAGFAILS);
	kfree_skb(skb);
	return -EMSGSIZE;
}

/*
 *	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);

	hdr = (struct ipv6hdr *) skb_put(skb, sizeof(struct ipv6hdr));
	skb->nh.ipv6h = hdr;

	*(u32*)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;
}

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) {
			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 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 = skb->nh.ipv6h;
	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(IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	skb->ip_summed = CHECKSUM_NONE;

	/*
	 *	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->nh.raw + 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);

		kfree_skb(skb);
		return -ETIMEDOUT;
	}

	if (!xfrm6_route_forward(skb)) {
		IP6_INC_STATS(IPSTATS_MIB_INDISCARDS);
		goto drop;
	}

	/* IPv6 specs say nothing about it, but it is clear that we cannot
	   send redirects to source routed frames.
	 */
	if (skb->dev == dst->dev && dst->neighbour && opt->srcrt == 0) {
		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 if (ipv6_addr_type(&hdr->saddr)&(IPV6_ADDR_MULTICAST|IPV6_ADDR_LOOPBACK
						|IPV6_ADDR_LINKLOCAL)) {
		/* This check is security critical. */
		goto error;
	}

	if (skb->len > dst_pmtu(dst)) {
		/* Again, force OUTPUT device used as source address */
		skb->dev = dst->dev;
		icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, dst_pmtu(dst), skb->dev);
		IP6_INC_STATS_BH(IPSTATS_MIB_INTOOBIGERRORS);
		IP6_INC_STATS_BH(IPSTATS_MIB_FRAGFAILS);
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	if (skb_cow(skb, dst->dev->hard_header_len)) {
		IP6_INC_STATS(IPSTATS_MIB_OUTDISCARDS);
		goto drop;
	}

	hdr = skb->nh.ipv6h;

	/* Mangling hops number delayed to point after skb COW */
 
	hdr->hop_limit--;

	IP6_INC_STATS_BH(IPSTATS_MIB_OUTFORWDATAGRAMS);
	return NF_HOOK(PF_INET6,NF_IP6_FORWARD, skb, skb->dev, dst->dev, ip6_forward_finish);

error:
	IP6_INC_STATS_BH(IPSTATS_MIB_INADDRERRORS);
drop:
	kfree_skb(skb);
	return -EINVAL;
}

static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
{
	to->pkt_type = from->pkt_type;
	to->priority = from->priority;
	to->protocol = from->protocol;
	to->security = from->security;
	to->dst = dst_clone(from->dst);
	to->dev = from->dev;

#ifdef CONFIG_NET_SCHED
	to->tc_index = from->tc_index;
#endif
#ifdef CONFIG_NETFILTER
	to->nfmark = from->nfmark;
	/* Connection association is same as pre-frag packet */
	to->nfct = from->nfct;
	nf_conntrack_get(to->nfct);
	to->nfctinfo = from->nfctinfo;
#ifdef CONFIG_BRIDGE_NETFILTER
	nf_bridge_put(to->nf_bridge);
	to->nf_bridge = from->nf_bridge;
	nf_bridge_get(to->nf_bridge);
#endif
#ifdef CONFIG_NETFILTER_DEBUG
	to->nf_debug = from->nf_debug;
#endif
#endif
}

int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr)
{
	u16 offset = sizeof(struct ipv6hdr);
	struct ipv6_opt_hdr *exthdr = (struct ipv6_opt_hdr*)(skb->nh.ipv6h + 1);
	unsigned int packet_len = skb->tail - skb->nh.raw;
	int found_rhdr = 0;
	*nexthdr = &skb->nh.ipv6h->nexthdr;

	while (offset + 1 <= packet_len) {

		switch (**nexthdr) {

		case NEXTHDR_HOP:
		case NEXTHDR_ROUTING:
		case NEXTHDR_DEST:
			if (**nexthdr == NEXTHDR_ROUTING) found_rhdr = 1;
			if (**nexthdr == NEXTHDR_DEST && found_rhdr) return offset;
			offset += ipv6_optlen(exthdr);
			*nexthdr = &exthdr->nexthdr;
			exthdr = (struct ipv6_opt_hdr*)(skb->nh.raw + offset);
			break;
		default :
			return offset;
		}
	}

	return offset;
}

static int ip6_fragment(struct sk_buff **pskb, int (*output)(struct sk_buff**))
{
	struct net_device *dev;
	struct sk_buff *frag, *skb = *pskb;
	struct rt6_info *rt = (struct rt6_info*)skb->dst;
	struct ipv6hdr *tmp_hdr;
	struct frag_hdr *fh;
	unsigned int mtu, hlen, left, len;
	u32 frag_id = 0;
	int ptr, offset = 0, err=0;
	u8 *prevhdr, nexthdr = 0;

	dev = rt->u.dst.dev;
	hlen = ip6_find_1stfragopt(skb, &prevhdr);
	nexthdr = *prevhdr;

	mtu = dst_pmtu(&rt->u.dst) - hlen - sizeof(struct frag_hdr);

	if (skb_shinfo(skb)->frag_list) {
		int first_len = skb_pagelen(skb);

		if (first_len - hlen > mtu ||
		    ((first_len - hlen) & 7) ||
		    skb_cloned(skb))
			goto slow_path;

		for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
			/* Correct geometry. */
			if (frag->len > mtu ||
			    ((frag->len & 7) && frag->next) ||
			    skb_headroom(frag) < hlen)
			    goto slow_path;

			/* Correct socket ownership. */
			if (frag->sk == NULL)
				goto slow_path;

			/* Partially cloned skb? */
			if (skb_shared(frag))
				goto slow_path;
		}

		err = 0;
		offset = 0;
		frag = skb_shinfo(skb)->frag_list;
		skb_shinfo(skb)->frag_list = NULL;
		/* BUILD HEADER */

		tmp_hdr = kmalloc(hlen, GFP_ATOMIC);
		if (!tmp_hdr) {
			IP6_INC_STATS(IPSTATS_MIB_FRAGFAILS);
			return -ENOMEM;
		}

		*prevhdr = NEXTHDR_FRAGMENT;
		memcpy(tmp_hdr, skb->nh.raw, hlen);
		__skb_pull(skb, hlen);
		fh = (struct frag_hdr*)__skb_push(skb, sizeof(struct frag_hdr));
		skb->nh.raw = __skb_push(skb, hlen);
		memcpy(skb->nh.raw, tmp_hdr, hlen);

		ipv6_select_ident(skb, fh);
		fh->nexthdr = nexthdr;
		fh->reserved = 0;
		fh->frag_off = htons(IP6_MF);
		frag_id = fh->identification;

		first_len = skb_pagelen(skb);
		skb->data_len = first_len - skb_headlen(skb);
		skb->len = first_len;
		skb->nh.ipv6h->payload_len = htons(first_len - sizeof(struct ipv6hdr));
 

		for (;;) {
			/* Prepare header of the next frame,
			 * before previous one went down. */