path: root/net/ipv6/ip6_output.c

/*
 *	IPv6 output functions
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>
 *
 *	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/kernel.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>
#include <linux/mroute6.h>

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

int __ip6_local_out(struct sk_buff *skb)
{
	int len;

	len = skb->len - sizeof(struct ipv6hdr);
	if (len > IPV6_MAXPLEN)
		len = 0;
	ipv6_hdr(skb)->payload_len = htons(len);

	return nf_hook(PF_INET6, NF_INET_LOCAL_OUT, skb, NULL, skb_dst(skb)->dev,
		       dst_output);
}

int ip6_local_out(struct sk_buff *skb)
{
	int err;

	err = __ip6_local_out(skb);
	if (likely(err == 1))
		err = dst_output(skb);

	return err;
}
EXPORT_SYMBOL_GPL(ip6_local_out);

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

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

	IP6_INC_STATS_BH(dev_net(dst->dev),
			 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;
	WARN_ON(!skb_dst(newskb));

	netif_rx(newskb);
	return 0;
}


static int ip6_output2(struct sk_buff *skb)
{
	struct dst_entry *dst = skb_dst(skb);
	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(skb));

		if (!(dev->flags & IFF_LOOPBACK) && (!np || np->mc_loop) &&
		    ((mroute6_socket(dev_net(dev)) &&
		     !(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
		     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_INET_POST_ROUTING, newskb,
					NULL, newskb->dev,
					ip6_dev_loopback_xmit);

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

		IP6_UPD_PO_STATS(dev_net(dev), idev, IPSTATS_MIB_OUTMCAST,
				skb->len);
	}

	return NF_HOOK(PF_INET6, NF_INET_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(skb)->dev->mtu : dst_mtu(skb_dst(skb));
}

int ip6_output(struct sk_buff *skb)
{
	struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
	if (unlikely(idev->cnf.disable_ipv6)) {
		IP6_INC_STATS(dev_net(skb_dst(skb)->dev), idev,
			      IPSTATS_MIB_OUTDISCARDS);
		kfree_skb(skb);
		return 0;
	}

	if ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) ||
				dst_allfrag(skb_dst(skb)))
		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 net *net = sock_net(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct in6_addr *first_hop = &fl->fl6_dst;
	struct dst_entry *dst = skb_dst(skb);
	struct ipv6hdr *hdr;
	u8  proto = fl->proto;
	int seg_len = skb->len;
	int hlimit = -1;
	int tclass = 0;
	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(net, ip6_dst_idev(skb_dst(skb)),
					      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);

	/* Allow local fragmentation. */
	if (ipfragok)
		skb->local_df = 1;

	/*
	 *	Fill in the IPv6 header
	 */
	if (np) {
		tclass = np->tclass;
		hlimit = np->hop_limit;
	}
	if (hlimit < 0)
		hlimit = ip6_dst_hoplimit(dst);

	*(__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;
	skb->mark = sk->sk_mark;

	mtu = dst_mtu(dst);
	if ((skb->len <= mtu) || skb->local_df || skb_is_gso(skb)) {
		IP6_UPD_PO_STATS(net, ip6_dst_idev(skb_dst(skb)),
			      IPSTATS_MIB_OUT, skb->len);
		return NF_HOOK(PF_INET6, NF_INET_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(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_FRAGFAILS);
	kfree_skb(skb);
	r