tcp_ipv4.c

/*
 * 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.
 *
 *		Implementation of the Transmission Control Protocol(TCP).
 *
 * Version:	$Id: tcp_ipv4.c,v 1.240 2002/02/01 22:01:04 davem Exp $
 *
 *		IPv4 specific functions
 *
 *
 *		code split from:
 *		linux/ipv4/tcp.c
 *		linux/ipv4/tcp_input.c
 *		linux/ipv4/tcp_output.c
 *
 *		See tcp.c for author information
 *
 *	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:
 *		David S. Miller	:	New socket lookup architecture.
 *					This code is dedicated to John Dyson.
 *		David S. Miller :	Change semantics of established hash,
 *					half is devoted to TIME_WAIT sockets
 *					and the rest go in the other half.
 *		Andi Kleen :		Add support for syncookies and fixed
 *					some bugs: ip options weren't passed to
 *					the TCP layer, missed a check for an
 *					ACK bit.
 *		Andi Kleen :		Implemented fast path mtu discovery.
 *	     				Fixed many serious bugs in the
 *					request_sock handling and moved
 *					most of it into the af independent code.
 *					Added tail drop and some other bugfixes.
 *					Added new listen sematics.
 *		Mike McLagan	:	Routing by source
 *	Juan Jose Ciarlante:		ip_dynaddr bits
 *		Andi Kleen:		various fixes.
 *	Vitaly E. Lavrov	:	Transparent proxy revived after year
 *					coma.
 *	Andi Kleen		:	Fix new listen.
 *	Andi Kleen		:	Fix accept error reporting.
 *	YOSHIFUJI Hideaki @USAGI and:	Support IPV6_V6ONLY socket option, which
 *	Alexey Kuznetsov		allow both IPv4 and IPv6 sockets to bind
 *					a single port at the same time.
 */

#include <linux/config.h>

#include <linux/types.h>
#include <linux/fcntl.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/cache.h>
#include <linux/jhash.h>
#include <linux/init.h>
#include <linux/times.h>

#include <net/icmp.h>
#include <net/inet_hashtables.h>
#include <net/tcp.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/xfrm.h>

#include <linux/inet.h>
#include <linux/ipv6.h>
#include <linux/stddef.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>

extern int sysctl_ip_dynaddr;
int sysctl_tcp_tw_reuse;
int sysctl_tcp_low_latency;

/* Check TCP sequence numbers in ICMP packets. */
#define ICMP_MIN_LENGTH 8

/* Socket used for sending RSTs */
static struct socket *tcp_socket;

void tcp_v4_send_check(struct sock *sk, struct tcphdr *th, int len,
		       struct sk_buff *skb);

struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
	.lhash_lock	= RW_LOCK_UNLOCKED,
	.lhash_users	= ATOMIC_INIT(0),
	.lhash_wait	= __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
	.portalloc_lock	= SPIN_LOCK_UNLOCKED,
	.port_rover	= 1024 - 1,
};

/*
 * This array holds the first and last local port number.
 * For high-usage systems, use sysctl to change this to
 * 32768-61000
 */
int sysctl_local_port_range[2] = { 1024, 4999 };

static inline int tcp_bind_conflict(struct sock *sk, struct inet_bind_bucket *tb)
{
	const u32 sk_rcv_saddr = inet_rcv_saddr(sk);
	struct sock *sk2;
	struct hlist_node *node;
	int reuse = sk->sk_reuse;

	sk_for_each_bound(sk2, node, &tb->owners) {
		if (sk != sk2 &&
		    !tcp_v6_ipv6only(sk2) &&
		    (!sk->sk_bound_dev_if ||
		     !sk2->sk_bound_dev_if ||
		     sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) {
			if (!reuse || !sk2->sk_reuse ||
			    sk2->sk_state == TCP_LISTEN) {
				const u32 sk2_rcv_saddr = inet_rcv_saddr(sk2);
				if (!sk2_rcv_saddr || !sk_rcv_saddr ||
				    sk2_rcv_saddr == sk_rcv_saddr)
					break;
			}
		}
	}
	return node != NULL;
}

/* Obtain a reference to a local port for the given sock,
 * if snum is zero it means select any available local port.
 */
static int tcp_v4_get_port(struct sock *sk, unsigned short snum)
{
	struct inet_bind_hashbucket *head;
	struct hlist_node *node;
	struct inet_bind_bucket *tb;
	int ret;

	local_bh_disable();
	if (!snum) {
		int low = sysctl_local_port_range[0];
		int high = sysctl_local_port_range[1];
		int remaining = (high - low) + 1;
		int rover;

		spin_lock(&tcp_hashinfo.portalloc_lock);
		if (tcp_hashinfo.port_rover < low)
			rover = low;
		else
			rover = tcp_hashinfo.port_rover;
		do {
			rover++;
			if (rover > high)
				rover = low;
			head = &tcp_hashinfo.bhash[inet_bhashfn(rover, tcp_hashinfo.bhash_size)];
			spin_lock(&head->lock);
			inet_bind_bucket_for_each(tb, node, &head->chain)
				if (tb->port == rover)
					goto next;
			break;
		next:
			spin_unlock(&head->lock);
		} while (--remaining > 0);
		tcp_hashinfo.port_rover = rover;
		spin_unlock(&tcp_hashinfo.portalloc_lock);

		/* Exhausted local port range during search?  It is not
		 * possible for us to be holding one of the bind hash
		 * locks if this test triggers, because if 'remaining'
		 * drops to zero, we broke out of the do/while loop at
		 * the top level, not from the 'break;' statement.
		 */
		ret = 1;
		if (unlikely(remaining <= 0))
			goto fail;

		/* OK, here is the one we will use.  HEAD is
		 * non-NULL and we hold it's mutex.
		 */
		snum = rover;
	} else {
		head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)];
		spin_lock(&head->lock);
		inet_bind_bucket_for_each(tb, node, &head->chain)
			if (tb->port == snum)
				goto tb_found;
	}
	tb = NULL;
	goto tb_not_found;
tb_found:
	if (!hlist_empty(&tb->owners)) {
		if (sk->sk_reuse > 1)
			goto success;
		if (tb->fastreuse > 0 &&
		    sk->sk_reuse && sk->sk_state != TCP_LISTEN) {
			goto success;
		} else {
			ret = 1;
			if (tcp_bind_conflict(sk, tb))
				goto fail_unlock;
		}
	}
tb_not_found:
	ret = 1;
	if (!tb && (tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, snum)) == NULL)
		goto fail_unlock;
	if (hlist_empty(&tb->owners)) {
		if (sk->sk_reuse && sk->sk_state != TCP_LISTEN)
			tb->fastreuse = 1;
		else
			tb->fastreuse = 0;
	} else if (tb->fastreuse &&
		   (!sk->sk_reuse || sk->sk_state == TCP_LISTEN))
		tb->fastreuse = 0;
success:
	if (!inet_sk(sk)->bind_hash)
		inet_bind_hash(sk, tb, snum);
	BUG_TRAP(inet_sk(sk)->bind_hash == tb);
 	ret = 0;

fail_unlock:
	spin_unlock(&head->lock);
fail:
	local_bh_enable();
	return ret;
}

static void tcp_v4_hash(struct sock *sk)
{
	inet_hash(&tcp_hashinfo, sk);
}

void tcp_unhash(struct sock *sk)
{
	inet_unhash(&tcp_hashinfo, sk);
}

static inline __u32 tcp_v4_init_sequence(struct sock *sk, struct sk_buff *skb)
{
	return secure_tcp_sequence_number(skb->nh.iph->daddr,
					  skb->nh.iph->saddr,
					  skb->h.th->dest,
					  skb->h.th->source);
}

/* called with local bh disabled */
static int __tcp_v4_check_established(struct sock *sk, __u16 lport,
				      struct inet_timewait_sock **twp)
{
	struct inet_sock *inet = inet_sk(sk);
	u32 daddr = inet->rcv_saddr;
	u32 saddr = inet->daddr;
	int dif = sk->sk_bound_dev_if;
	INET_ADDR_COOKIE(acookie, saddr, daddr)
	const __u32 ports = INET_COMBINED_PORTS(inet->dport, lport);
	const int hash = inet_ehashfn(daddr, lport, saddr, inet->dport, tcp_hashinfo.ehash_size);
	struct inet_ehash_bucket *head = &tcp_hashinfo.ehash[hash];
	struct sock *sk2;
	const struct hlist_node *node;
	struct inet_timewait_sock *tw;

	write_lock(&head->lock);

	/* Check TIME-WAIT sockets first. */
	sk_for_each(sk2, node, &(head + tcp_hashinfo.ehash_size)->chain) {
		tw = inet_twsk(sk2);

		if (INET_TW_MATCH(sk2, acookie, saddr, daddr, ports, dif)) {
			const struct tcp_timewait_sock *tcptw = tcp_twsk(sk2);
			struct tcp_sock *tp = tcp_sk(sk);

			/* With PAWS, it is safe from the viewpoint
			   of data integrity. Even without PAWS it
			   is safe provided sequence spaces do not
			   overlap i.e. at data rates <= 80Mbit/sec.

			   Actually, the idea is close to VJ's one,
			   only timestamp cache is held not per host,
			   but per port pair and TW bucket is used
			   as state holder.

			   If TW bucket has been already destroyed we
			   fall back to VJ's scheme and use initial
			   timestamp retrieved from peer table.
			 */
			if (tcptw->tw_ts_recent_stamp &&
			    (!twp || (sysctl_tcp_tw_reuse &&
				      xtime.tv_sec -
				      tcptw->tw_ts_recent_stamp > 1))) {
				tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2;
				if (tp->write_seq == 0)
					tp->write_seq = 1;
				tp->rx_opt.ts_recent	   = tcptw->tw_ts_recent;
				tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
				sock_hold(sk2);
				goto unique;
			} else
				goto not_unique;
		}
	}
	tw = NULL;

	/* And established part... */
	sk_for_each(sk2, node, &head->chain) {
		if (INET_MATCH(sk2, acookie, saddr, daddr, ports, dif))
			goto not_unique;
	}

unique:
	/* Must record num and sport now. Otherwise we will see
	 * in hash table socket with a funny identity. */
	inet->num = lport;
	inet->sport = htons(lport);
	sk->sk_hashent = hash;
	BUG_TRAP(sk_unhashed(sk));
	__sk_add_node(sk, &head->chain);
	sock_prot_inc_use(sk->sk_prot);
	write_unlock(&head->lock);

	if (twp) {
		*twp = tw;
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);
	} else if (tw) {
		/* Silly. Should hash-dance instead... */
		tcp_tw_deschedule(tw);
		NET_INC_STATS_BH(LINUX_MIB_TIMEWAITRECYCLED);

		inet_twsk_put(tw);
	}

	return 0;

not_unique:
	write_unlock(&head->lock);
	return -EADDRNOTAVAIL;
}

static inline u32 connect_port_offset(const struct sock *sk)
{
	const struct inet_sock *inet = inet_sk(sk);

	return secure_tcp_port_ephemeral(inet->rcv_saddr, inet->daddr, 
					 inet->dport);
}

/*
 * Bind a port for a connect operation and hash it.
 */
static inline int tcp_v4_hash_connect(struct sock *sk)
{
	const unsigned short snum = inet_sk(sk)->num;
 	struct inet_bind_hashbucket *head;
 	struct inet_bind_bucket *tb;
	int ret;

 	if (!snum) {
 		int low = sysctl_local_port_range[0];
 		int high = sysctl_local_port_range[1];
		int range = high - low;
 		int i;
		int port;
		static u32 hint;
		u32 offset = hint + connect_port_offset(sk);
		struct hlist_node *node;
 		struct inet_timewait_sock *tw = NULL;

 		local_bh_disable();
		for (i = 1; i <= range; i++) {
			port = low + (i + offset) % range;
 			head = &tcp_hashinfo.bhash[inet_bhashfn(port, tcp_hashinfo.bhash_size)];
 			spin_lock(&head->lock);

 			/* Does not bother with rcv_saddr checks,
 			 * because the established check is already
 			 * unique enough.
 			 */
			inet_bind_bucket_for_each(tb, node, &head->chain) {
 				if (tb->port == port) {
 					BUG_TRAP(!hlist_empty(&tb->owners));
 					if (tb->fastreuse >= 0)
 						goto next_port;
 					if (!__tcp_v4_check_established(sk,
									port,
									&tw))
 						goto ok;
 					goto next_port;
 				}
 			}

 			tb = inet_bind_bucket_create(tcp_hashinfo.bind_bucket_cachep, head, port);
 			if (!tb) {
 				spin_unlock(&head->lock);
 				break;
 			}
 			tb->fastreuse = -1;
 			goto ok;

 		next_port:
 			spin_unlock(&head->lock);
 		}
 		local_bh_enable();

 		return -EADDRNOTAVAIL;

ok:
		hint += i;

 		/* Head lock still held and bh's disabled */
 		inet_bind_hash(sk, tb, port);
		if (sk_unhashed(sk)) {
 			inet_sk(sk)->sport = htons(port);
 			__inet_hash(&tcp_hashinfo, sk, 0);
 		}
 		spin_unlock(&head->lock);

 		if (tw) {
 			tcp_tw_deschedule(tw);
 			inet_twsk_put(tw);
 		}

		ret = 0;
		goto out;
 	}

 	head = &tcp_hashinfo.bhash[inet_bhashfn(snum, tcp_hashinfo.bhash_size)];
 	tb  = inet_sk(sk)->bind_hash;
	spin_lock_bh(&head->lock);
	if (sk_head(&tb->owners) == sk && !sk->sk_bind_node.next) {
		__inet_hash(&tcp_hashinfo, sk, 0);
		spin_unlock_bh(&head->lock);
		return 0;
	} else {
		spin_unlock(&head->lock);
		/* No definite answer... Walk to established hash table */
		ret = __tcp_v4_check_established(sk, snum, NULL);
out:
		local_bh_enable();
		return ret;
	}
}

/* This will initiate an outgoing connection. */
int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
	struct inet_sock *inet = inet_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sockaddr_in *usin = (struct sockaddr_in *)uaddr;
	struct rtable *rt;
	u32 daddr, nexthop;
	int tmp;
	int err;

	if (addr_len < sizeof(struct sockaddr_in))
		return -EINVAL;

	if (usin->sin_family != AF_INET)
		return -EAFNOSUPPORT;

	nexthop = daddr = usin->sin_addr.s_addr;
	if (inet->opt && inet->opt->srr) {
		if (!daddr)
			return -EINVAL;
		nexthop = inet->opt->faddr;
	}

	tmp = ip_route_connect(&rt, nexthop, inet->saddr,
			       RT_CONN_FLAGS(sk), sk->sk_bound_dev_if,
			       IPPROTO_TCP,
			       inet->sport, usin->sin_port, sk);
	if (tmp < 0)
		return tmp;

	if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) {
		ip_rt_put(rt);
		return -ENETUNREACH;
	}

	if (!inet->opt || !inet->opt->srr)
		daddr = rt->rt_dst;

	if (!inet->saddr)
		inet->saddr = rt->rt_src;
	inet->rcv_saddr = inet->saddr;

	if (tp->rx_opt.ts_recent_stamp && inet->daddr != daddr) {
		/* Reset inherited state */
		tp->rx_opt.ts_recent	   = 0;
		tp->rx_opt.ts_recent_stamp = 0;
		tp->write_seq		   = 0;
	}

	if (sysctl_tcp_tw_recycle &&
	    !tp->rx_opt.ts_recent_stamp && rt->rt_dst == daddr) {
		struct inet_peer *peer = rt_get_peer(rt);

		/* VJ's idea. We save last timestamp seen from
		 * the destination in peer table, when entering state TIME-WAIT
		 * and initialize rx_opt.ts_recent from it, when trying new connection.
		 */

		if (peer && peer->tcp_ts_stamp + TCP_PAWS_MSL >= xtime.tv_sec) {
			tp->rx_opt.ts_recent_stamp = peer->tcp_ts_stamp;
			tp->rx_opt.ts_recent = peer->tcp_ts;
		}
	}

	inet->dport = usin->sin_port;
	inet->daddr = daddr;

	tp->ext_header_len = 0;
	if (inet->opt)
		tp->ext_header_len = inet->opt->optlen;

	tp->rx_opt.mss_clamp = 536;

	/* Socket identity is still unknown (sport may be zero).
	 * However we set state to SYN-SENT and not releasing socket
	 * lock select source port, enter ourselves into the hash tables and
	 * complete initialization after this.
	 */
	tcp_set_state(sk, TCP_SYN_SENT);
	err = tcp_v4_hash_connect(sk);
	if (err)
		goto failure;

	err = ip_route_newports(&rt, inet->sport, inet->dport, sk);
	if (err)
		goto failure;

	/* OK, now commit destination to socket.  */
	sk_setup_caps(sk, &rt->u.dst);

	if (!tp->write_seq)
		tp->write_seq = secure_tcp_sequence_number(inet->saddr,
							   inet->daddr,
							   inet->sport,
							   usin->sin_port);

	inet->id = tp->write_seq ^ jiffies;

	err = tcp_connect(sk);
	rt = NULL;
	if (err)
		goto failure;

	return 0;

failure:
	/* This unhashes the socket and releases the local port, if necessary. */
	tcp_set_state(sk, TCP_CLOSE);
	ip_rt_put(rt);
	sk->sk_route_caps = 0;
	inet->dport = 0;
	return err;
}

static __inline__ int tcp_v4_iif(struct sk_buff *skb)
{
	return ((struct rtable *)skb->dst)->rt_iif;
}

static __inline__ u32 tcp_v4_synq_hash(u32 raddr, u16 rport, u32 rnd)
{
	return (jhash_2words(raddr, (u32) rport, rnd) & (TCP_SYNQ_HSIZE - 1));
}

static struct request_sock *tcp_v4_search_req(struct tcp_sock *tp,
					      struct request_sock ***prevp,
					      __u16 rport,
					      __u32 raddr, __u32 laddr)
{
	struct listen_sock *lopt = tp->accept_queue.listen_opt;
	struct request_sock *req, **prev;

	for (prev = &lopt->syn_table[tcp_v4_synq_hash(raddr, rport, lopt->hash_rnd)];
	     (req = *prev) != NULL;
	     prev = &req->dl_next) {
		const struct inet_request_sock *ireq = inet_rsk(req);

		if (ireq->rmt_port == rport &&
		    ireq->rmt_addr == raddr &&
		    ireq->loc_addr == laddr &&
		    TCP_INET_FAMILY(req->rsk_ops->family)) {
			BUG_TRAP(!req->sk);
			*prevp = prev;
			break;
		}
	}

	return req;
}

static void tcp_v4_synq_add(struct sock *sk, struct request_sock *req)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct listen_sock *lopt = tp->accept_queue.listen_opt;
	u32 h = tcp_v4_synq_hash(inet_rsk(req)->rmt_addr, inet_rsk(req)->rmt_port, lopt->hash_rnd);

	reqsk_queue_hash_req(&tp->accept_queue, h, req, TCP_TIMEOUT_INIT);
	tcp_synq_added(sk);
}


/*
 * This routine does path mtu discovery as defined in RFC1191.
 */
static inline void do_pmtu_discovery(struct sock *sk, struct iphdr *iph,
				     u32 mtu)
{
	struct dst_entry *dst;
	struct inet_sock *inet = inet_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);

	/* We are not interested in TCP_LISTEN and open_requests (SYN-ACKs
	 * send out by Linux are always <576bytes so they should go through
	 * unfragmented).
	 */
	if (sk->sk_state == TCP_LISTEN)
		return;

	/* We don't check in the destentry if pmtu discovery is forbidden
	 * on this route. We just assume that no packet_to_big packets
	 * are send back when pmtu discovery is not active.
     	 * There is a small race when the user changes this flag in the
	 * route, but I think that's acceptable.
	 */
	if ((dst = __sk_dst_check(sk, 0)) == NULL)
		return;

	dst->ops->update_pmtu(dst, mtu);

	/* Something is about to be wrong... Remember soft error
	 * for the case, if this connection will not able to recover.
	 */
	if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst))
		sk->sk_err_soft = EMSGSIZE;

	mtu = dst_mtu(dst);

	if (inet->pmtudisc != IP_PMTUDISC_DONT &&
	    tp->pmtu_cookie > mtu) {
		tcp_sync_mss(sk, mtu);

		/* Resend the TCP packet because it's
		 * clear that the old packet has been
		 * dropped. This is the new "fast" path mtu
		 * discovery.
		 */
		tcp_simple_retransmit(sk);
	} /* else let the usual retransmit timer handle it */
}

/*
 * This routine is called by the ICMP module when it gets some
 * sort of error condition.  If err < 0 then the socket should
 * be closed and the error returned to the user.  If err > 0
 * it's just the icmp type << 8 | icmp code.  After adjustment
 * header points to the first 8 bytes of the tcp header.  We need
 * to find the appropriate port.
 *
 * The locking strategy used here is very "optimistic". When
 * someone else accesses the socket the ICMP is just dropped
 * and for some paths there is no check at all.
 * A more general error queue to queue errors for later handling
 * is probably better.
 *
 */

void tcp_v4_err(struct sk_buff *skb, u32 info)
{
	struct iphdr *iph = (struct iphdr *)skb->data;
	struct tcphdr *th = (struct tcphdr *)(skb->data + (iph->ihl << 2));
	struct tcp_sock *tp;
	struct inet_sock *inet;
	int type = skb->h.icmph->type;
	int code = skb->h.icmph->code;
	struct sock *sk;
	__u32 seq;
	int err;

	if (skb->len < (iph->ihl << 2) + 8) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;
	}

	sk = inet_lookup(&tcp_hashinfo, iph->daddr, th->dest, iph->saddr,
			 th->source, tcp_v4_iif(skb));
	if (!sk) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;
	}
	if (sk->sk_state == TCP_TIME_WAIT) {
		inet_twsk_put((struct inet_timewait_sock *)sk);
		return;
	}

	bh_lock_sock(sk);
	/* If too many ICMPs get dropped on busy
	 * servers this needs to be solved differently.
	 */
	if (sock_owned_by_user(sk))
		NET_INC_STATS_BH(LINUX_MIB_LOCKDROPPEDICMPS);

	if (sk->sk_state == TCP_CLOSE)
		goto out;

	tp = tcp_sk(sk);
	seq = ntohl(th->seq);
	if (sk->sk_state != TCP_LISTEN &&
	    !between(seq, tp->snd_una, tp->snd_nxt)) {
		NET_INC_STATS(LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	switch (type) {
	case ICMP_SOURCE_QUENCH:
		/* Just silently ignore these. */
		goto out;
	case ICMP_PARAMETERPROB:
		err = EPROTO;
		break;
	case ICMP_DEST_UNREACH:
		if (code > NR_ICMP_UNREACH)
			goto out;

		if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
			if (!sock_owned_by_user(sk))
				do_pmtu_discovery(sk, iph, info);
			goto out;
		}

		err = icmp_err_convert[code].errno;
		break;
	case ICMP_TIME_EXCEEDED:
		err = EHOSTUNREACH;
		break;
	default:
		goto out;
	}

	switch (sk->sk_state) {
		struct request_sock *req, **prev;
	case TCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;

		req = tcp_v4_search_req(tp, &prev, th->dest,
					iph->daddr, iph->saddr);
		if (!req)
			goto out;

		/* ICMPs are not backlogged, hence we cannot get
		   an established socket here.
		 */
		BUG_TRAP(!req->sk);

		if (seq != tcp_rsk(req)->snt_isn) {
			NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
			goto out;
		}

		/*
		 * Still in SYN_RECV, just remove it silently.
		 * There is no good way to pass the error to the newly
		 * created socket, and POSIX does not want network
		 * errors returned from accept().
		 */
		tcp_synq_drop(sk, req, prev);
		goto out;

	case TCP_SYN_SENT:
	case TCP_SYN_RECV:  /* Cannot happen.
			       It can f.e. if SYNs crossed.
			     */
		if (!sock_owned_by_user(sk)) {
			TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
			sk->sk_err = err;

			sk->sk_error_report(sk);

			tcp_done(sk);
		} else {
			sk->sk_err_soft = err;
		}
		goto out;
	}

	/* If we've already connected we will keep trying
	 * until we time out, or the user gives up.
	 *
	 * rfc1122 4.2.3.9 allows to consider as hard errors
	 * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too,
	 * but it is obsoleted by pmtu discovery).
	 *
	 * Note, that in modern internet, where routing is unreliable
	 * and in each dark corner broken firewalls sit, sending random
	 * errors ordered by their masters even this two messages finally lose
	 * their original sense (even Linux sends invalid PORT_UNREACHs)
	 *
	 * Now we are in compliance with RFCs.
	 *							--ANK (980905)
	 */

	inet = inet_sk(sk);
	if (!sock_owned_by_user(sk) && inet->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else	{ /* Only an error on timeout */
		sk->sk_err_soft = err;
	}

out:
	bh_unlock_sock(sk);
	sock_put(sk);
}

/* This routine computes an IPv4 TCP checksum. */
void tcp_v4_send_check(struct sock *sk, struct tcphdr *th, int len,
		       struct sk_buff *skb)
{
	struct inet_sock *inet = inet_sk(sk);

	if (skb->ip_summed == CHECKSUM_HW) {
		th->check = ~tcp_v4_check(th, len, inet->saddr, inet->daddr, 0);
		skb->csum = offsetof(struct tcphdr, check);
	} else {
		th->check = tcp_v4_check(th, len, inet->saddr, inet->daddr,
					 csum_partial((char *)th,
						      th->doff << 2,
						      skb->csum));
	}
}

/*
 *	This routine will send an RST to the other tcp.
 *
 *	Someone asks: why I NEVER use socket parameters (TOS, TTL etc.)
 *		      for reset.
 *	Answer: if a packet caused RST, it is not for a socket
 *		existing in our system, if it is matched to a socket,
 *		it is just duplicate segment or bug in other side's TCP.
 *		So that we build reply only basing on parameters
 *		arrived with segment.
 *	Exception: precedence violation. We do not implement it in any case.
 */

static void tcp_v4_send_reset(struct sk_buff *skb)
{
	struct tcphdr *th = skb->h.th;
	struct tcphdr rth;
	struct ip_reply_arg arg;

	/* Never send a reset in response to a reset. */
	if (th->rst)
		return;

	if (((struct rtable *)skb->dst)->rt_type != RTN_LOCAL)
		return;

	/* Swap the send and the receive. */
	memset(&rth, 0, sizeof(struct tcphdr));
	rth.dest   = th->source;
	rth.source = th->dest;
	rth.doff   = sizeof(struct tcphdr) / 4;
	rth.rst    = 1;

	if (th->ack) {
		rth.seq = th->ack_seq;
	} else {
		rth.ack = 1;
		rth.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin +
				    skb->len - (th->doff << 2));
	}

	memset(&arg, 0, sizeof arg);
	arg.iov[0].iov_base = (unsigned char *)&rth;
	arg.iov[0].iov_len  = sizeof rth;
	arg.csum = csum_tcpudp_nofold(skb->nh.iph->daddr,
				      skb->nh.iph->saddr, /*XXX*/
				      sizeof(struct tcphdr), IPPROTO_TCP, 0);
	arg.csumoffset = offsetof(struct tcphdr, check) / 2;

	ip_send_reply(tcp_socket->sk, skb, &arg, sizeof rth);

	TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
	TCP_INC_STATS_BH(TCP_MIB_OUTRSTS);
}

/* The code following below sending ACKs in SYN-RECV and TIME-WAIT states
   outside socket context is ugly, certainly. What can I do?
 */

static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
			    u32 win, u32 ts)
{
	struct tcphdr *th = skb->h.th;
	struct {
		struct tcphdr th;
		u32 tsopt[3];
	} rep;
	struct ip_reply_arg arg;

	memset(&rep.th, 0, sizeof(struct tcphdr));
	memset(&arg, 0, sizeof arg);

	arg.iov[0].iov_base = (unsigned char *)&rep;
	arg.iov[0].iov_len  = sizeof(rep.th);
	if (ts) {
		rep.tsopt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
				     (TCPOPT_TIMESTAMP << 8) |
				     TCPOLEN_TIMESTAMP);
		rep.tsopt[1] = htonl(tcp_time_stamp);
		rep.tsopt[2] = htonl(ts);
		arg.iov[0].iov_len = sizeof(rep);
	}

	/* Swap the send and the receive. */
	rep.th.dest    = th->source;
	rep.th.source  = th->dest;
	rep.th.doff    = arg.iov[0].iov_len / 4;
	rep.th.seq     = htonl(seq);
	rep.th.ack_seq = htonl(ack);
	rep.th.ack     = 1;
	rep.th.window  = htons(win);

	arg.csum = csum_tcpudp_nofold(skb->nh.iph->daddr,
				      skb->nh.iph->saddr, /*XXX*/
				      arg.iov[0].iov_len, IPPROTO_TCP, 0);
	arg.csumoffset = offsetof(struct tcphdr, check) / 2;

	ip_send_reply(tcp_socket->sk, skb, &arg, arg.iov[0].iov_len);

	TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
}

static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
{
	struct inet_timewait_sock *tw = inet_twsk(sk);
	const struct tcp_timewait_sock *tcptw = tcp_twsk(sk);

	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcptw->tw_ts_recent);

	inet_twsk_put(tw);
}

static void tcp_v4_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req)
{
	tcp_v4_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
			req->ts_recent);
}

static struct dst_entry* tcp_v4_route_req(struct sock *sk,
					  struct request_sock *req)
{
	struct rtable *rt;
	const struct inet_request_sock *ireq = inet_rsk(req);
	struct ip_options *opt = inet_rsk(req)->opt;
	struct flowi fl = { .oif = sk->sk_bound_dev_if,
			    .nl_u = { .ip4_u =
				      { .daddr = ((opt && opt->srr) ?
						  opt->faddr :
						  ireq->rmt_addr),
					.saddr = ireq->loc_addr,
					.tos = RT_CONN_FLAGS(sk) } },
			    .proto = IPPROTO_TCP,
			    .uli_u = { .ports =
				       { .sport = inet_sk(sk)->sport,
					 .dport = ireq->rmt_port } } };

	if (ip_route_output_flow(&rt, &fl, sk, 0)) {
		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
		return NULL;
	}
	if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) {
		ip_rt_put(rt);
		IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES);
		return NULL;
	}
	return &rt->u.dst;
}

/*
 *	Send a SYN-ACK after having received an ACK.
 *	This still operates on a request_sock only, not on a big
 *	socket.
 */
static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
			      struct dst_entry *dst)
{
	const struct inet_request_sock *ireq = inet_rsk(req);
	int err = -1;
	struct sk_buff * skb;

	/* First, grab a route. */
	if (!dst && (dst = tcp_v4_route_req(sk, req)) == NULL)
		goto out;