ip_output.c

linux 内核源代码

/*
 * INET		An implementation of the TCP/IP protocol suite for the LINUX
 *		operating system.  INET is implemented using the  BSD Socket
 *		interface as the means of communication with the user level.
 *
 *		The Internet Protocol (IP) output module.
 *
 * Version:	$Id: ip_output.c,v 1.100 2002/02/01 22:01:03 davem Exp $
 *
 * Authors:	Ross Biro
 *		Fred N. van Kempen, <[e-mail]>
 *		Donald Becker, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *		Richard Underwood
 *		Stefan Becker, <[e-mail]>
 *		Jorge Cwik, <[e-mail]>
 *		Arnt Gulbrandsen, <[e-mail]>
 *		Hirokazu Takahashi, <[e-mail]>
 *
 *	See ip_input.c for original log
 *
 *	Fixes:
 *		Alan Cox	:	Missing nonblock feature in ip_build_xmit.
 *		Mike Kilburn	:	htons() missing in ip_build_xmit.
 *		Bradford Johnson:	Fix faulty handling of some frames when
 *					no route is found.
 *		Alexander Demenshin:	Missing sk/skb free in ip_queue_xmit
 *					(in case if packet not accepted by
 *					output firewall rules)
 *		Mike McLagan	:	Routing by source
 *		Alexey Kuznetsov:	use new route cache
 *		Andi Kleen:		Fix broken PMTU recovery and remove
 *					some redundant tests.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year coma.
 *		Andi Kleen	: 	Replace ip_reply with ip_send_reply.
 *		Andi Kleen	:	Split fast and slow ip_build_xmit path
 *					for decreased register pressure on x86
 *					and more readibility.
 *		Marc Boucher	:	When call_out_firewall returns FW_QUEUE,
 *					silently drop skb instead of failing with -EPERM.
 *		Detlev Wengorz	:	Copy protocol for fragments.
 *		Hirokazu Takahashi:	HW checksumming for outgoing UDP
 *					datagrams.
 *		Hirokazu Takahashi:	sendfile() on UDP works now.
 */

#include <asm/uaccess.h>
#include <asm/system.h>
#include <linux/module.h>
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/highmem.h>

#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/in.h>
#include <linux/inet.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/proc_fs.h>
#include <linux/stat.h>
#include <linux/init.h>

#include <net/snmp.h>
#include <net/ip.h>
#include <net/protocol.h>
#include <net/route.h>
#include <net/xfrm.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/arp.h>
#include <net/icmp.h>
#include <net/checksum.h>
#include <net/inetpeer.h>
#include <linux/igmp.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_bridge.h>
#include <linux/mroute.h>
#include <linux/netlink.h>
#include <linux/tcp.h>

int sysctl_ip_default_ttl __read_mostly = IPDEFTTL;

/* Generate a checksum for an outgoing IP datagram. */
__inline__ void ip_send_check(struct iphdr *iph)
{
	iph->check = 0;
	iph->check = ip_fast_csum((unsigned char *)iph, iph->ihl);
}

/* dev_loopback_xmit for use with netfilter. */
static int ip_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 inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst)
{
	int ttl = inet->uc_ttl;

	if (ttl < 0)
		ttl = dst_metric(dst, RTAX_HOPLIMIT);
	return ttl;
}

/*
 *		Add an ip header to a skbuff and send it out.
 *
 */
int ip_build_and_send_pkt(struct sk_buff *skb, struct sock *sk,
			  __be32 saddr, __be32 daddr, struct ip_options *opt)
{
	struct inet_sock *inet = inet_sk(sk);
	struct rtable *rt = (struct rtable *)skb->dst;
	struct iphdr *iph;

	/* Build the IP header. */
	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	iph->version  = 4;
	iph->ihl      = 5;
	iph->tos      = inet->tos;
	if (ip_dont_fragment(sk, &rt->u.dst))
		iph->frag_off = htons(IP_DF);
	else
		iph->frag_off = 0;
	iph->ttl      = ip_select_ttl(inet, &rt->u.dst);
	iph->daddr    = rt->rt_dst;
	iph->saddr    = rt->rt_src;
	iph->protocol = sk->sk_protocol;
	iph->tot_len  = htons(skb->len);
	ip_select_ident(iph, &rt->u.dst, sk);

	if (opt && opt->optlen) {
		iph->ihl += opt->optlen>>2;
		ip_options_build(skb, opt, daddr, rt, 0);
	}
	ip_send_check(iph);

	skb->priority = sk->sk_priority;

	/* Send it out. */
	return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
		       dst_output);
}

EXPORT_SYMBOL_GPL(ip_build_and_send_pkt);

static inline int ip_finish_output2(struct sk_buff *skb)
{
	struct dst_entry *dst = skb->dst;
	struct rtable *rt = (struct rtable *)dst;
	struct net_device *dev = dst->dev;
	unsigned int hh_len = LL_RESERVED_SPACE(dev);

	if (rt->rt_type == RTN_MULTICAST)
		IP_INC_STATS(IPSTATS_MIB_OUTMCASTPKTS);
	else if (rt->rt_type == RTN_BROADCAST)
		IP_INC_STATS(IPSTATS_MIB_OUTBCASTPKTS);

	/* Be paranoid, rather than too clever. */
	if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) {
		struct sk_buff *skb2;

		skb2 = skb_realloc_headroom(skb, LL_RESERVED_SPACE(dev));
		if (skb2 == NULL) {
			kfree_skb(skb);
			return -ENOMEM;
		}
		if (skb->sk)
			skb_set_owner_w(skb2, skb->sk);
		kfree_skb(skb);
		skb = skb2;
	}

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

	if (net_ratelimit())
		printk(KERN_DEBUG "ip_finish_output2: No header cache and no neighbour!\n");
	kfree_skb(skb);
	return -EINVAL;
}

static inline int ip_skb_dst_mtu(struct sk_buff *skb)
{
	struct inet_sock *inet = skb->sk ? inet_sk(skb->sk) : NULL;

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

static int ip_finish_output(struct sk_buff *skb)
{
#if defined(CONFIG_NETFILTER) && defined(CONFIG_XFRM)
	/* Policy lookup after SNAT yielded a new policy */
	if (skb->dst->xfrm != NULL) {
		IPCB(skb)->flags |= IPSKB_REROUTED;
		return dst_output(skb);
	}
#endif
	if (skb->len > ip_skb_dst_mtu(skb) && !skb_is_gso(skb))
		return ip_fragment(skb, ip_finish_output2);
	else
		return ip_finish_output2(skb);
}

int ip_mc_output(struct sk_buff *skb)
{
	struct sock *sk = skb->sk;
	struct rtable *rt = (struct rtable*)skb->dst;
	struct net_device *dev = rt->u.dst.dev;

	/*
	 *	If the indicated interface is up and running, send the packet.
	 */
	IP_INC_STATS(IPSTATS_MIB_OUTREQUESTS);

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

	/*
	 *	Multicasts are looped back for other local users
	 */

	if (rt->rt_flags&RTCF_MULTICAST) {
		if ((!sk || inet_sk(sk)->mc_loop)
#ifdef CONFIG_IP_MROUTE
		/* Small optimization: do not loopback not local frames,
		   which returned after forwarding; they will be  dropped
		   by ip_mr_input in any case.
		   Note, that local frames are looped back to be delivered
		   to local recipients.

		   This check is duplicated in ip_mr_input at the moment.
		 */
		    && ((rt->rt_flags&RTCF_LOCAL) || !(IPCB(skb)->flags&IPSKB_FORWARDED))
#endif
		) {
			struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
			if (newskb)
				NF_HOOK(PF_INET, NF_IP_POST_ROUTING, newskb, NULL,
					newskb->dev,
					ip_dev_loopback_xmit);
		}

		/* Multicasts with ttl 0 must not go beyond the host */

		if (ip_hdr(skb)->ttl == 0) {
			kfree_skb(skb);
			return 0;
		}
	}

	if (rt->rt_flags&RTCF_BROADCAST) {
		struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC);
		if (newskb)
			NF_HOOK(PF_INET, NF_IP_POST_ROUTING, newskb, NULL,
				newskb->dev, ip_dev_loopback_xmit);
	}

	return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, skb->dev,
			    ip_finish_output,
			    !(IPCB(skb)->flags & IPSKB_REROUTED));
}

int ip_output(struct sk_buff *skb)
{
	struct net_device *dev = skb->dst->dev;

	IP_INC_STATS(IPSTATS_MIB_OUTREQUESTS);

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

	return NF_HOOK_COND(PF_INET, NF_IP_POST_ROUTING, skb, NULL, dev,
			    ip_finish_output,
			    !(IPCB(skb)->flags & IPSKB_REROUTED));
}

int ip_queue_xmit(struct sk_buff *skb, int ipfragok)
{
	struct sock *sk = skb->sk;
	struct inet_sock *inet = inet_sk(sk);
	struct ip_options *opt = inet->opt;
	struct rtable *rt;
	struct iphdr *iph;

	/* Skip all of this if the packet is already routed,
	 * f.e. by something like SCTP.
	 */
	rt = (struct rtable *) skb->dst;
	if (rt != NULL)
		goto packet_routed;

	/* Make sure we can route this packet. */
	rt = (struct rtable *)__sk_dst_check(sk, 0);
	if (rt == NULL) {
		__be32 daddr;

		/* Use correct destination address if we have options. */
		daddr = inet->daddr;
		if(opt && opt->srr)
			daddr = opt->faddr;

		{
			struct flowi fl = { .oif = sk->sk_bound_dev_if,
					    .nl_u = { .ip4_u =
						      { .daddr = daddr,
							.saddr = inet->saddr,
							.tos = RT_CONN_FLAGS(sk) } },
					    .proto = sk->sk_protocol,
					    .uli_u = { .ports =
						       { .sport = inet->sport,
							 .dport = inet->dport } } };

			/* If this fails, retransmit mechanism of transport layer will
			 * keep trying until route appears or the connection times
			 * itself out.
			 */
			security_sk_classify_flow(sk, &fl);
			if (ip_route_output_flow(&rt, &fl, sk, 0))
				goto no_route;
		}
		sk_setup_caps(sk, &rt->u.dst);
	}
	skb->dst = dst_clone(&rt->u.dst);

packet_routed:
	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway)
		goto no_route;

	/* OK, we know where to send it, allocate and build IP header. */
	skb_push(skb, sizeof(struct iphdr) + (opt ? opt->optlen : 0));
	skb_reset_network_header(skb);
	iph = ip_hdr(skb);
	*((__be16 *)iph) = htons((4 << 12) | (5 << 8) | (inet->tos & 0xff));
	iph->tot_len = htons(skb->len);
	if (ip_dont_fragment(sk, &rt->u.dst) && !ipfragok)
		iph->frag_off = htons(IP_DF);
	else
		iph->frag_off = 0;
	iph->ttl      = ip_select_ttl(inet, &rt->u.dst);
	iph->protocol = sk->sk_protocol;
	iph->saddr    = rt->rt_src;
	iph->daddr    = rt->rt_dst;
	/* Transport layer set skb->h.foo itself. */

	if (opt && opt->optlen) {
		iph->ihl += opt->optlen >> 2;
		ip_options_build(skb, opt, inet->daddr, rt, 0);
	}

	ip_select_ident_more(iph, &rt->u.dst, sk,
			     (skb_shinfo(skb)->gso_segs ?: 1) - 1);

	/* Add an IP checksum. */
	ip_send_check(iph);

	skb->priority = sk->sk_priority;

	return NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL, rt->u.dst.dev,
		       dst_output);

no_route:
	IP_INC_STATS(IPSTATS_MIB_OUTNOROUTES);
	kfree_skb(skb);
	return -EHOSTUNREACH;
}


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

	/* Copy the flags to each fragment. */
	IPCB(to)->flags = IPCB(from)->flags;

#ifdef CONFIG_NET_SCHED
	to->tc_index = from->tc_index;
#endif
	nf_copy(to, from);
#if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
    defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
	to->nf_trace = from->nf_trace;
#endif
#if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
	to->ipvs_property = from->ipvs_property;
#endif
	skb_copy_secmark(to, from);
}

/*
 *	This IP datagram is too large to be sent in one piece.  Break it up into
 *	smaller pieces (each of size equal to IP header plus
 *	a block of the data of the original IP data part) that will yet fit in a
 *	single device frame, and queue such a frame for sending.
 */

int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*))
{
	struct iphdr *iph;
	int raw = 0;
	int ptr;
	struct net_device *dev;
	struct sk_buff *skb2;
	unsigned int mtu, hlen, left, len, ll_rs, pad;
	int offset;
	__be16 not_last_frag;
	struct rtable *rt = (struct rtable*)skb->dst;
	int err = 0;

	dev = rt->u.dst.dev;

	/*
	 *	Point into the IP datagram header.
	 */

	iph = ip_hdr(skb);

	if (unlikely((iph->frag_off & htons(IP_DF)) && !skb->local_df)) {
		IP_INC_STATS(IPSTATS_MIB_FRAGFAILS);
		icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
			  htonl(ip_skb_dst_mtu(skb)));
		kfree_skb(skb);
		return -EMSGSIZE;
	}

	/*
	 *	Setup starting values.
	 */

	hlen = iph->ihl * 4;
	mtu = dst_mtu(&rt->u.dst) - hlen;	/* Size of data space */
	IPCB(skb)->flags |= IPSKB_FRAG_COMPLETE;

	/* When frag_list is given, use it. First, check its validity:
	 * some transformers could create wrong frag_list or break existing
	 * one, it is not prohibited. In this case fall back to copying.
	 *
	 * LATER: this step can be merged to real generation of fragments,
	 * we can switch to copy when see the first bad fragment.
	 */
	if (skb_shinfo(skb)->frag_list) {
		struct sk_buff *frag;
		int first_len = skb_pagelen(skb);

		if (first_len - hlen > mtu ||
		    ((first_len - hlen) & 7) ||
		    (iph->frag_off & htons(IP_MF|IP_OFFSET)) ||
		    skb_cloned(skb))
			goto slow_path;

		for (frag = skb_shinfo(skb)->frag_list; frag; frag = frag->next) {
			/* Correct geometry. */