tcp_ipv6.c

/*
 *	TCP over IPv6
 *	Linux INET6 implementation 
 *
 *	Authors:
 *	Pedro Roque		<roque@di.fc.ul.pt>	
 *
 *	$Id: tcp_ipv6.c,v 1.144 2002/02/01 22:01:04 davem Exp $
 *
 *	Based on: 
 *	linux/net/ipv4/tcp.c
 *	linux/net/ipv4/tcp_input.c
 *	linux/net/ipv4/tcp_output.c
 *
 *	Fixes:
 *	Hideaki YOSHIFUJI	:	sin6_scope_id support
 *	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.
 *	YOSHIFUJI Hideaki @USAGI:	convert /proc/net/tcp6 to seq_file.
 *
 *	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.
 */

#include <linux/module.h>
#include <linux/config.h>
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/net.h>
#include <linux/jiffies.h>
#include <linux/in.h>
#include <linux/in6.h>
#include <linux/netdevice.h>
#include <linux/init.h>
#include <linux/jhash.h>
#include <linux/ipsec.h>
#include <linux/times.h>

#include <linux/ipv6.h>
#include <linux/icmpv6.h>
#include <linux/random.h>

#include <net/tcp.h>
#include <net/ndisc.h>
#include <net/inet6_hashtables.h>
#include <net/inet6_connection_sock.h>
#include <net/ipv6.h>
#include <net/transp_v6.h>
#include <net/addrconf.h>
#include <net/ip6_route.h>
#include <net/ip6_checksum.h>
#include <net/inet_ecn.h>
#include <net/protocol.h>
#include <net/xfrm.h>
#include <net/addrconf.h>
#include <net/snmp.h>
#include <net/dsfield.h>
#include <net/timewait_sock.h>

#include <asm/uaccess.h>

#include <linux/proc_fs.h>
#include <linux/seq_file.h>

/* Socket used for sending RSTs and ACKs */
static struct socket *tcp6_socket;

static void	tcp_v6_send_reset(struct sk_buff *skb);
static void	tcp_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req);
static void	tcp_v6_send_check(struct sock *sk, int len, 
				  struct sk_buff *skb);

static int	tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);

static struct inet_connection_sock_af_ops ipv6_mapped;
static struct inet_connection_sock_af_ops ipv6_specific;

static int tcp_v6_get_port(struct sock *sk, unsigned short snum)
{
	return inet_csk_get_port(&tcp_hashinfo, sk, snum,
				 inet6_csk_bind_conflict);
}

static void tcp_v6_hash(struct sock *sk)
{
	if (sk->sk_state != TCP_CLOSE) {
		if (inet_csk(sk)->icsk_af_ops == &ipv6_mapped) {
			tcp_prot.hash(sk);
			return;
		}
		local_bh_disable();
		__inet6_hash(&tcp_hashinfo, sk);
		local_bh_enable();
	}
}

static __inline__ u16 tcp_v6_check(struct tcphdr *th, int len,
				   struct in6_addr *saddr, 
				   struct in6_addr *daddr, 
				   unsigned long base)
{
	return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
}

static __u32 tcp_v6_init_sequence(struct sock *sk, struct sk_buff *skb)
{
	if (skb->protocol == htons(ETH_P_IPV6)) {
		return secure_tcpv6_sequence_number(skb->nh.ipv6h->daddr.s6_addr32,
						    skb->nh.ipv6h->saddr.s6_addr32,
						    skb->h.th->dest,
						    skb->h.th->source);
	} else {
		return secure_tcp_sequence_number(skb->nh.iph->daddr,
						  skb->nh.iph->saddr,
						  skb->h.th->dest,
						  skb->h.th->source);
	}
}

static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 
			  int addr_len)
{
	struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
 	struct inet_sock *inet = inet_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct in6_addr *saddr = NULL, *final_p = NULL, final;
	struct flowi fl;
	struct dst_entry *dst;
	int addr_type;
	int err;

	if (addr_len < SIN6_LEN_RFC2133) 
		return -EINVAL;

	if (usin->sin6_family != AF_INET6) 
		return(-EAFNOSUPPORT);

	memset(&fl, 0, sizeof(fl));

	if (np->sndflow) {
		fl.fl6_flowlabel = usin->sin6_flowinfo&IPV6_FLOWINFO_MASK;
		IP6_ECN_flow_init(fl.fl6_flowlabel);
		if (fl.fl6_flowlabel&IPV6_FLOWLABEL_MASK) {
			struct ip6_flowlabel *flowlabel;
			flowlabel = fl6_sock_lookup(sk, fl.fl6_flowlabel);
			if (flowlabel == NULL)
				return -EINVAL;
			ipv6_addr_copy(&usin->sin6_addr, &flowlabel->dst);
			fl6_sock_release(flowlabel);
		}
	}

	/*
  	 *	connect() to INADDR_ANY means loopback (BSD'ism).
  	 */
  	
  	if(ipv6_addr_any(&usin->sin6_addr))
		usin->sin6_addr.s6_addr[15] = 0x1; 

	addr_type = ipv6_addr_type(&usin->sin6_addr);

	if(addr_type & IPV6_ADDR_MULTICAST)
		return -ENETUNREACH;

	if (addr_type&IPV6_ADDR_LINKLOCAL) {
		if (addr_len >= sizeof(struct sockaddr_in6) &&
		    usin->sin6_scope_id) {
			/* If interface is set while binding, indices
			 * must coincide.
			 */
			if (sk->sk_bound_dev_if &&
			    sk->sk_bound_dev_if != usin->sin6_scope_id)
				return -EINVAL;

			sk->sk_bound_dev_if = usin->sin6_scope_id;
		}

		/* Connect to link-local address requires an interface */
		if (!sk->sk_bound_dev_if)
			return -EINVAL;
	}

	if (tp->rx_opt.ts_recent_stamp &&
	    !ipv6_addr_equal(&np->daddr, &usin->sin6_addr)) {
		tp->rx_opt.ts_recent = 0;
		tp->rx_opt.ts_recent_stamp = 0;
		tp->write_seq = 0;
	}

	ipv6_addr_copy(&np->daddr, &usin->sin6_addr);
	np->flow_label = fl.fl6_flowlabel;

	/*
	 *	TCP over IPv4
	 */

	if (addr_type == IPV6_ADDR_MAPPED) {
		u32 exthdrlen = icsk->icsk_ext_hdr_len;
		struct sockaddr_in sin;

		SOCK_DEBUG(sk, "connect: ipv4 mapped\n");

		if (__ipv6_only_sock(sk))
			return -ENETUNREACH;

		sin.sin_family = AF_INET;
		sin.sin_port = usin->sin6_port;
		sin.sin_addr.s_addr = usin->sin6_addr.s6_addr32[3];

		icsk->icsk_af_ops = &ipv6_mapped;
		sk->sk_backlog_rcv = tcp_v4_do_rcv;

		err = tcp_v4_connect(sk, (struct sockaddr *)&sin, sizeof(sin));

		if (err) {
			icsk->icsk_ext_hdr_len = exthdrlen;
			icsk->icsk_af_ops = &ipv6_specific;
			sk->sk_backlog_rcv = tcp_v6_do_rcv;
			goto failure;
		} else {
			ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF),
				      inet->saddr);
			ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF),
				      inet->rcv_saddr);
		}

		return err;
	}

	if (!ipv6_addr_any(&np->rcv_saddr))
		saddr = &np->rcv_saddr;

	fl.proto = IPPROTO_TCP;
	ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
	ipv6_addr_copy(&fl.fl6_src,
		       (saddr ? saddr : &np->saddr));
	fl.oif = sk->sk_bound_dev_if;
	fl.fl_ip_dport = usin->sin6_port;
	fl.fl_ip_sport = inet->sport;

	if (np->opt && np->opt->srcrt) {
		struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt;
		ipv6_addr_copy(&final, &fl.fl6_dst);
		ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
		final_p = &final;
	}

	err = ip6_dst_lookup(sk, &dst, &fl);
	if (err)
		goto failure;
	if (final_p)
		ipv6_addr_copy(&fl.fl6_dst, final_p);

	if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
		goto failure;

	if (saddr == NULL) {
		saddr = &fl.fl6_src;
		ipv6_addr_copy(&np->rcv_saddr, saddr);
	}

	/* set the source address */
	ipv6_addr_copy(&np->saddr, saddr);
	inet->rcv_saddr = LOOPBACK4_IPV6;

	ip6_dst_store(sk, dst, NULL);
	sk->sk_route_caps = dst->dev->features &
		~(NETIF_F_IP_CSUM | NETIF_F_TSO);

	icsk->icsk_ext_hdr_len = 0;
	if (np->opt)
		icsk->icsk_ext_hdr_len = (np->opt->opt_flen +
					  np->opt->opt_nflen);

	tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);

	inet->dport = usin->sin6_port;

	tcp_set_state(sk, TCP_SYN_SENT);
	err = inet6_hash_connect(&tcp_death_row, sk);
	if (err)
		goto late_failure;

	if (!tp->write_seq)
		tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32,
							     np->daddr.s6_addr32,
							     inet->sport,
							     inet->dport);

	err = tcp_connect(sk);
	if (err)
		goto late_failure;

	return 0;

late_failure:
	tcp_set_state(sk, TCP_CLOSE);
	__sk_dst_reset(sk);
failure:
	inet->dport = 0;
	sk->sk_route_caps = 0;
	return err;
}

static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
		int type, int code, int offset, __u32 info)
{
	struct ipv6hdr *hdr = (struct ipv6hdr*)skb->data;
	const struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
	struct ipv6_pinfo *np;
	struct sock *sk;
	int err;
	struct tcp_sock *tp; 
	__u32 seq;

	sk = inet6_lookup(&tcp_hashinfo, &hdr->daddr, th->dest, &hdr->saddr,
			  th->source, skb->dev->ifindex);

	if (sk == NULL) {
		ICMP6_INC_STATS_BH(__in6_dev_get(skb->dev), ICMP6_MIB_INERRORS);
		return;
	}

	if (sk->sk_state == TCP_TIME_WAIT) {
		inet_twsk_put((struct inet_timewait_sock *)sk);
		return;
	}

	bh_lock_sock(sk);
	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_BH(LINUX_MIB_OUTOFWINDOWICMPS);
		goto out;
	}

	np = inet6_sk(sk);

	if (type == ICMPV6_PKT_TOOBIG) {
		struct dst_entry *dst = NULL;

		if (sock_owned_by_user(sk))
			goto out;
		if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE))
			goto out;

		/* icmp should have updated the destination cache entry */
		dst = __sk_dst_check(sk, np->dst_cookie);

		if (dst == NULL) {
			struct inet_sock *inet = inet_sk(sk);
			struct flowi fl;

			/* BUGGG_FUTURE: Again, it is not clear how
			   to handle rthdr case. Ignore this complexity
			   for now.
			 */
			memset(&fl, 0, sizeof(fl));
			fl.proto = IPPROTO_TCP;
			ipv6_addr_copy(&fl.fl6_dst, &np->daddr);
			ipv6_addr_copy(&fl.fl6_src, &np->saddr);
			fl.oif = sk->sk_bound_dev_if;
			fl.fl_ip_dport = inet->dport;
			fl.fl_ip_sport = inet->sport;

			if ((err = ip6_dst_lookup(sk, &dst, &fl))) {
				sk->sk_err_soft = -err;
				goto out;
			}

			if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0) {
				sk->sk_err_soft = -err;
				goto out;
			}

		} else
			dst_hold(dst);

		if (inet_csk(sk)->icsk_pmtu_cookie > dst_mtu(dst)) {
			tcp_sync_mss(sk, dst_mtu(dst));
			tcp_simple_retransmit(sk);
		} /* else let the usual retransmit timer handle it */
		dst_release(dst);
		goto out;
	}

	icmpv6_err_convert(type, code, &err);

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

		req = inet6_csk_search_req(sk, &prev, th->dest, &hdr->daddr,
					   &hdr->saddr, inet6_iif(skb));
		if (!req)
			goto out;

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

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

		inet_csk_reqsk_queue_drop(sk, req, prev);
		goto out;

	case TCP_SYN_SENT:
	case TCP_SYN_RECV:  /* Cannot happen.
			       It can, it SYNs are crossed. --ANK */ 
		if (!sock_owned_by_user(sk)) {
			TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
			sk->sk_err = err;
			sk->sk_error_report(sk);		/* Wake people up to see the error (see connect in sock.c) */

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

	if (!sock_owned_by_user(sk) && np->recverr) {
		sk->sk_err = err;
		sk->sk_error_report(sk);
	} else
		sk->sk_err_soft = err;

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


static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
			      struct dst_entry *dst)
{
	struct inet6_request_sock *treq = inet6_rsk(req);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct sk_buff * skb;
	struct ipv6_txoptions *opt = NULL;
	struct in6_addr * final_p = NULL, final;
	struct flowi fl;
	int err = -1;

	memset(&fl, 0, sizeof(fl));
	fl.proto = IPPROTO_TCP;
	ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
	ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
	fl.fl6_flowlabel = 0;
	fl.oif = treq->iif;
	fl.fl_ip_dport = inet_rsk(req)->rmt_port;
	fl.fl_ip_sport = inet_sk(sk)->sport;

	if (dst == NULL) {
		opt = np->opt;
		if (opt == NULL &&
		    np->rxopt.bits.osrcrt == 2 &&
		    treq->pktopts) {
			struct sk_buff *pktopts = treq->pktopts;
			struct inet6_skb_parm *rxopt = IP6CB(pktopts);
			if (rxopt->srcrt)
				opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr*)(pktopts->nh.raw + rxopt->srcrt));
		}

		if (opt && opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}

		err = ip6_dst_lookup(sk, &dst, &fl);
		if (err)
			goto done;
		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);
		if ((err = xfrm_lookup(&dst, &fl, sk, 0)) < 0)
			goto done;
	}

	skb = tcp_make_synack(sk, dst, req);
	if (skb) {
		struct tcphdr *th = skb->h.th;

		th->check = tcp_v6_check(th, skb->len,
					 &treq->loc_addr, &treq->rmt_addr,
					 csum_partial((char *)th, skb->len, skb->csum));

		ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
		err = ip6_xmit(sk, skb, &fl, opt, 0);
		if (err == NET_XMIT_CN)
			err = 0;
	}

done:
        if (opt && opt != np->opt)
		sock_kfree_s(sk, opt, opt->tot_len);
	dst_release(dst);
	return err;
}

static void tcp_v6_reqsk_destructor(struct request_sock *req)
{
	if (inet6_rsk(req)->pktopts)
		kfree_skb(inet6_rsk(req)->pktopts);
}

static struct request_sock_ops tcp6_request_sock_ops = {
	.family		=	AF_INET6,
	.obj_size	=	sizeof(struct tcp6_request_sock),
	.rtx_syn_ack	=	tcp_v6_send_synack,
	.send_ack	=	tcp_v6_reqsk_send_ack,
	.destructor	=	tcp_v6_reqsk_destructor,
	.send_reset	=	tcp_v6_send_reset
};

static struct timewait_sock_ops tcp6_timewait_sock_ops = {
	.twsk_obj_size	= sizeof(struct tcp6_timewait_sock),
	.twsk_unique	= tcp_twsk_unique,
};

static void tcp_v6_send_check(struct sock *sk, int len, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct tcphdr *th = skb->h.th;

	if (skb->ip_summed == CHECKSUM_HW) {
		th->check = ~csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP,  0);
		skb->csum = offsetof(struct tcphdr, check);
	} else {
		th->check = csum_ipv6_magic(&np->saddr, &np->daddr, len, IPPROTO_TCP, 
					    csum_partial((char *)th, th->doff<<2, 
							 skb->csum));
	}
}


static void tcp_v6_send_reset(struct sk_buff *skb)
{
	struct tcphdr *th = skb->h.th, *t1; 
	struct sk_buff *buff;
	struct flowi fl;

	if (th->rst)
		return;

	if (!ipv6_unicast_destination(skb))
		return; 

	/*
	 * We need to grab some memory, and put together an RST,
	 * and then put it into the queue to be sent.
	 */

	buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr),
			 GFP_ATOMIC);
	if (buff == NULL) 
	  	return;

	skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + sizeof(struct tcphdr));

	t1 = (struct tcphdr *) skb_push(buff,sizeof(struct tcphdr));

	/* Swap the send and the receive. */
	memset(t1, 0, sizeof(*t1));
	t1->dest = th->source;
	t1->source = th->dest;
	t1->doff = sizeof(*t1)/4;
	t1->rst = 1;
  
	if(th->ack) {
	  	t1->seq = th->ack_seq;
	} else {
		t1->ack = 1;
		t1->ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin
				    + skb->len - (th->doff<<2));
	}

	buff->csum = csum_partial((char *)t1, sizeof(*t1), 0);

	memset(&fl, 0, sizeof(fl));
	ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
	ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr);

	t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst,
				    sizeof(*t1), IPPROTO_TCP,
				    buff->csum);

	fl.proto = IPPROTO_TCP;
	fl.oif = inet6_iif(skb);
	fl.fl_ip_dport = t1->dest;
	fl.fl_ip_sport = t1->source;

	/* sk = NULL, but it is safe for now. RST socket required. */
	if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {

		if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) {
			ip6_xmit(tcp6_socket->sk, buff, &fl, NULL, 0);
			TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
			TCP_INC_STATS_BH(TCP_MIB_OUTRSTS);
			return;
		}
	}

	kfree_skb(buff);
}

static void tcp_v6_send_ack(struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 ts)
{
	struct tcphdr *th = skb->h.th, *t1;
	struct sk_buff *buff;
	struct flowi fl;
	int tot_len = sizeof(struct tcphdr);

	if (ts)
		tot_len += 3*4;

	buff = alloc_skb(MAX_HEADER + sizeof(struct ipv6hdr) + tot_len,
			 GFP_ATOMIC);
	if (buff == NULL)
		return;

	skb_reserve(buff, MAX_HEADER + sizeof(struct ipv6hdr) + tot_len);

	t1 = (struct tcphdr *) skb_push(buff,tot_len);

	/* Swap the send and the receive. */
	memset(t1, 0, sizeof(*t1));
	t1->dest = th->source;
	t1->source = th->dest;
	t1->doff = tot_len/4;
	t1->seq = htonl(seq);
	t1->ack_seq = htonl(ack);
	t1->ack = 1;
	t1->window = htons(win);
	
	if (ts) {
		u32 *ptr = (u32*)(t1 + 1);
		*ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
			       (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
		*ptr++ = htonl(tcp_time_stamp);
		*ptr = htonl(ts);
	}

	buff->csum = csum_partial((char *)t1, tot_len, 0);

	memset(&fl, 0, sizeof(fl));
	ipv6_addr_copy(&fl.fl6_dst, &skb->nh.ipv6h->saddr);
	ipv6_addr_copy(&fl.fl6_src, &skb->nh.ipv6h->daddr);

	t1->check = csum_ipv6_magic(&fl.fl6_src, &fl.fl6_dst,
				    tot_len, IPPROTO_TCP,
				    buff->csum);

	fl.proto = IPPROTO_TCP;
	fl.oif = inet6_iif(skb);
	fl.fl_ip_dport = t1->dest;
	fl.fl_ip_sport = t1->source;

	if (!ip6_dst_lookup(NULL, &buff->dst, &fl)) {
		if (xfrm_lookup(&buff->dst, &fl, NULL, 0) >= 0) {
			ip6_xmit(tcp6_socket->sk, buff, &fl, NULL, 0);
			TCP_INC_STATS_BH(TCP_MIB_OUTSEGS);
			return;
		}
	}

	kfree_skb(buff);
}

static void tcp_v6_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_v6_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_v6_reqsk_send_ack(struct sk_buff *skb, struct request_sock *req)
{
	tcp_v6_send_ack(skb, tcp_rsk(req)->snt_isn + 1, tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd, req->ts_recent);
}


static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
{
	struct request_sock *req, **prev;
	const struct tcphdr *th = skb->h.th;
	struct sock *nsk;

	/* Find possible connection requests. */
	req = inet6_csk_search_req(sk, &prev, th->source,
				   &skb->nh.ipv6h->saddr,
				   &skb->nh.ipv6h->daddr, inet6_iif(skb));
	if (req)
		return tcp_check_req(sk, skb, req, prev);

	nsk = __inet6_lookup_established(&tcp_hashinfo, &skb->nh.ipv6h->saddr,
					 th->source, &skb->nh.ipv6h->daddr,
					 ntohs(th->dest), inet6_iif(skb));

	if (nsk) {
		if (nsk->sk_state != TCP_TIME_WAIT) {
			bh_lock_sock(nsk);
			return nsk;
		}
		inet_twsk_put((struct inet_timewait_sock *)nsk);
		return NULL;
	}

#if 0 /*def CONFIG_SYN_COOKIES*/
	if (!th->rst && !th->syn && th->ack)
		sk = cookie_v6_check(sk, skb, &(IPCB(skb)->opt));
#endif
	return sk;
}

/* FIXME: this is substantially similar to the ipv4 code.
 * Can some kind of merge be done? -- erics
 */
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
	struct inet6_request_sock *treq;
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct tcp_options_received tmp_opt;
	struct tcp_sock *tp = tcp_sk(sk);
	struct request_sock *req = NULL;
	__u32 isn = TCP_SKB_CB(skb)->when;

	if (skb->protocol == htons(ETH_P_IP))
		return tcp_v4_conn_request(sk, skb);

	if (!ipv6_unicast_destination(skb))
		goto drop; 

	/*
	 *	There are no SYN attacks on IPv6, yet...	
	 */
	if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
		if (net_ratelimit())
			printk(KERN_INFO "TCPv6: dropping request, synflood is possible\n");
		goto drop;		
	}

	if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
		goto drop;

	req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
	if (req == NULL)
		goto drop;

	tcp_clear_options(&tmp_opt);
	tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
	tmp_opt.user_mss = tp->rx_opt.user_mss;

	tcp_parse_options(skb, &tmp_opt, 0);

	tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
	tcp_openreq_init(req, &tmp_opt, skb);

	treq = inet6_rsk(req);
	ipv6_addr_copy(&treq->rmt_addr, &skb->nh.ipv6h->saddr);
	ipv6_addr_copy(&treq->loc_addr, &skb->nh.ipv6h->daddr);
	TCP_ECN_create_request(req, skb->h.th);
	treq->pktopts = NULL;
	if (ipv6_opt_accepted(sk, skb) ||
	    np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
	    np->rxopt.bits.rxhlim || np->rxopt.bits.rxohlim) {
		atomic_inc(&skb->users);
		treq->pktopts = skb;
	}
	treq->iif = sk->sk_bound_dev_if;

	/* So that link locals have meaning */
	if (!sk->sk_bound_dev_if &&
	    ipv6_addr_type(&treq->rmt_addr) & IPV6_ADDR_LINKLOCAL)
		treq->iif = inet6_iif(skb);

	if (isn == 0) 
		isn = tcp_v6_init_sequence(sk,skb);

	tcp_rsk(req)->snt_isn = isn;

	if (tcp_v6_send_synack(sk, req, NULL))
		goto drop;

	inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
	return 0;

drop:
	if (req)
		reqsk_free(req);

	TCP_INC_STATS_BH(TCP_MIB_ATTEMPTFAILS);
	return 0; /* don't send reset */
}

static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb,
					  struct request_sock *req,
					  struct dst_entry *dst)
{
	struct inet6_request_sock *treq = inet6_rsk(req);
	struct ipv6_pinfo *newnp, *np = inet6_sk(sk);
	struct tcp6_sock *newtcp6sk;
	struct inet_sock *newinet;
	struct tcp_sock *newtp;
	struct sock *newsk;
	struct ipv6_txoptions *opt;

	if (skb->protocol == htons(ETH_P_IP)) {
		/*
		 *	v6 mapped
		 */

		newsk = tcp_v4_syn_recv_sock(sk, skb, req, dst);

		if (newsk == NULL) 
			return NULL;

		newtcp6sk = (struct tcp6_sock *)newsk;
		inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;

		newinet = inet_sk(newsk);
		newnp = inet6_sk(newsk);
		newtp = tcp_sk(newsk);

		memcpy(newnp, np, sizeof(struct ipv6_pinfo));

		ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF),
			      newinet->daddr);

		ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF),
			      newinet->saddr);

		ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr);

		inet_csk(newsk)->icsk_af_ops = &ipv6_mapped;
		newsk->sk_backlog_rcv = tcp_v4_do_rcv;
		newnp->pktoptions  = NULL;
		newnp->opt	   = NULL;
		newnp->mcast_oif   = inet6_iif(skb);
		newnp->mcast_hops  = skb->nh.ipv6h->hop_limit;

		/*
		 * No need to charge this sock to the relevant IPv6 refcnt debug socks count
		 * here, tcp_create_openreq_child now does this for us, see the comment in
		 * that function for the gory details. -acme
		 */

		/* It is tricky place. Until this moment IPv4 tcp
		   worked with IPv6 icsk.icsk_af_ops.
		   Sync it now.
		 */
		tcp_sync_mss(newsk, inet_csk(newsk)->icsk_pmtu_cookie);

		return newsk;
	}

	opt = np->opt;

	if (sk_acceptq_is_full(sk))
		goto out_overflow;

	if (np->rxopt.bits.osrcrt == 2 &&
	    opt == NULL && treq->pktopts) {
		struct inet6_skb_parm *rxopt = IP6CB(treq->pktopts);
		if (rxopt->srcrt)
			opt = ipv6_invert_rthdr(sk, (struct ipv6_rt_hdr *)(treq->pktopts->nh.raw + rxopt->srcrt));
	}

	if (dst == NULL) {
		struct in6_addr *final_p = NULL, final;
		struct flowi fl;

		memset(&fl, 0, sizeof(fl));
		fl.proto = IPPROTO_TCP;
		ipv6_addr_copy(&fl.fl6_dst, &treq->rmt_addr);
		if (opt && opt->srcrt) {
			struct rt0_hdr *rt0 = (struct rt0_hdr *) opt->srcrt;
			ipv6_addr_copy(&final, &fl.fl6_dst);
			ipv6_addr_copy(&fl.fl6_dst, rt0->addr);
			final_p = &final;
		}
		ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr);
		fl.oif = sk->sk_bound_dev_if;
		fl.fl_ip_dport = inet_rsk(req)->rmt_port;
		fl.fl_ip_sport = inet_sk(sk)->sport;

		if (ip6_dst_lookup(sk, &dst, &fl))
			goto out;

		if (final_p)
			ipv6_addr_copy(&fl.fl6_dst, final_p);

		if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0)
			goto out;
	} 

	newsk = tcp_create_openreq_child(sk, req, skb);
	if (newsk == NULL)
		goto out;

	/*
	 * No need to charge this sock to the relevant IPv6 refcnt debug socks
	 * count here, tcp_create_openreq_child now does this for us, see the
	 * comment in that function for the gory details. -acme
	 */

	ip6_dst_store(newsk, dst, NULL);
	newsk->sk_route_caps = dst->dev->features &
		~(NETIF_F_IP_CSUM | NETIF_F_TSO);

	newtcp6sk = (struct tcp6_sock *)newsk;
	inet_sk(newsk)->pinet6 = &newtcp6sk->inet6;

	newtp = tcp_sk(newsk);
	newinet = inet_sk(newsk);
	newnp = inet6_sk(newsk);

	memcpy(newnp, np, sizeof(struct ipv6_pinfo));

	ipv6_addr_copy(&newnp->daddr, &treq->rmt_addr);
	ipv6_addr_copy(&newnp->saddr, &treq->loc_addr);
	ipv6_addr_copy(&newnp->rcv_saddr, &treq->loc_addr);
	newsk->sk_bound_dev_if = treq->iif;

	/* Now IPv6 options... 

	   First: no IPv4 options.
	 */
	newinet->opt = NULL;

	/* Clone RX bits */
	newnp->rxopt.all = np->rxopt.all;

	/* Clone pktoptions received with SYN */
	newnp->pktoptions = NULL;
	if (treq->pktopts != NULL) {
		newnp->pktoptions = skb_clone(treq->pktopts, GFP_ATOMIC);
		kfree_skb(treq->pktopts);
		treq->pktopts = NULL;
		if (newnp->pktoptions)
			skb_set_owner_r(newnp->pktoptions, newsk);
	}
	newnp->opt	  = NULL;
	newnp->mcast_oif  = inet6_iif(skb);
	newnp->mcast_hops = skb->nh.ipv6h->hop_limit;

	/* Clone native IPv6 options from listening socket (if any)

	   Yes, keeping reference count would be much more clever,
	   but we make one more one thing there: reattach optmem
	   to newsk.
	 */
	if (opt) {
		newnp->opt = ipv6_dup_options(newsk, opt);
		if (opt != np->opt)
			sock_kfree_s(sk, opt, opt->tot_len);
	}

	inet_csk(newsk)->icsk_ext_hdr_len = 0;
	if (newnp->opt)
		inet_csk(newsk)->icsk_ext_hdr_len = (newnp->opt->opt_nflen +
						     newnp->opt->opt_flen);

	tcp_mtup_init(newsk);
	tcp_sync_mss(newsk, dst_mtu(dst));
	newtp->advmss = dst_metric(dst, RTAX_ADVMSS);
	tcp_initialize_rcv_mss(newsk);

	newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6;

	__inet6_hash(&tcp_hashinfo, newsk);
	inet_inherit_port(&tcp_hashinfo, sk, newsk);

	return newsk;