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 semantics.
 *		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/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/transp_v6.h>
#include <net/ipv6.h>
#include <net/inet_common.h>
#include <net/timewait_sock.h>
#include <net/xfrm.h>
#include <net/netdma.h>

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

#include <linux/crypto.h>
#include <linux/scatterlist.h>

int sysctl_tcp_tw_reuse __read_mostly;
int sysctl_tcp_low_latency __read_mostly;

/* 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, int len, struct sk_buff *skb);

#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk,
						   __be32 addr);
static int tcp_v4_do_calc_md5_hash(char *md5_hash, struct tcp_md5sig_key *key,
				   __be32 saddr, __be32 daddr,
				   struct tcphdr *th, int protocol,
				   int tcplen);
#endif

struct inet_hashinfo __cacheline_aligned tcp_hashinfo = {
	.lhash_lock  = __RW_LOCK_UNLOCKED(tcp_hashinfo.lhash_lock),
	.lhash_users = ATOMIC_INIT(0),
	.lhash_wait  = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait),
};

static int tcp_v4_get_port(struct sock *sk, unsigned short snum)
{
	return inet_csk_get_port(&tcp_hashinfo, sk, snum,
				 inet_csk_bind_conflict);
}

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 sk_buff *skb)
{
	return secure_tcp_sequence_number(skb->nh.iph->daddr,
					  skb->nh.iph->saddr,
					  skb->h.th->dest,
					  skb->h.th->source);
}

int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
	const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
	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 == NULL || (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(sktw);
		return 1;
	}

	return 0;
}

EXPORT_SYMBOL_GPL(tcp_twsk_unique);

/* 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;
	__be32 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, 1);
	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 (tcp_death_row.sysctl_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 != NULL &&
		    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;

	inet_csk(sk)->icsk_ext_hdr_len = 0;
	if (inet->opt)
		inet_csk(sk)->icsk_ext_hdr_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 = inet_hash_connect(&tcp_death_row, sk);
	if (err)
		goto failure;

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

	/* OK, now commit destination to socket.  */
	sk->sk_gso_type = SKB_GSO_TCPV4;
	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;
}

/*
 * This routine does path mtu discovery as defined in RFC1191.
 */
static void do_pmtu_discovery(struct sock *sk, struct iphdr *iph, u32 mtu)
{
	struct dst_entry *dst;
	struct inet_sock *inet = inet_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 &&
	    inet_csk(sk)->icsk_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, inet_iif(skb));
	if (!sk) {
		ICMP_INC_STATS_BH(ICMP_MIB_INERRORS);
		return;
	}
	if (sk->sk_state == TCP_TIME_WAIT) {
		inet_twsk_put(inet_twsk(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_BH(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 = inet_csk_search_req(sk, &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().
		 */
		inet_csk_reqsk_queue_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)) {
			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, int len, struct sk_buff *skb)
{
	struct inet_sock *inet = inet_sk(sk);
	struct tcphdr *th = skb->h.th;

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

int tcp_v4_gso_send_check(struct sk_buff *skb)
{
	struct iphdr *iph;
	struct tcphdr *th;

	if (!pskb_may_pull(skb, sizeof(*th)))
		return -EINVAL;

	iph = skb->nh.iph;
	th = skb->h.th;

	th->check = 0;
	th->check = ~tcp_v4_check(skb->len, iph->saddr, iph->daddr, 0);
	skb->csum_offset = offsetof(struct tcphdr, check);
	skb->ip_summed = CHECKSUM_PARTIAL;
	return 0;
}

/*
 *	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 sock *sk, struct sk_buff *skb)
{
	struct tcphdr *th = skb->h.th;
	struct {
		struct tcphdr th;
#ifdef CONFIG_TCP_MD5SIG
		__be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)];
#endif
	} rep;
	struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
#endif

	/* 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(&rep, 0, sizeof(rep));
	rep.th.dest   = th->source;
	rep.th.source = th->dest;
	rep.th.doff   = sizeof(struct tcphdr) / 4;
	rep.th.rst    = 1;

	if (th->ack) {
		rep.th.seq = th->ack_seq;
	} else {
		rep.th.ack = 1;
		rep.th.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 *)&rep;
	arg.iov[0].iov_len  = sizeof(rep.th);

#ifdef CONFIG_TCP_MD5SIG
	key = sk ? tcp_v4_md5_do_lookup(sk, skb->nh.iph->daddr) : NULL;
	if (key) {
		rep.opt[0] = htonl((TCPOPT_NOP << 24) |
				   (TCPOPT_NOP << 16) |
				   (TCPOPT_MD5SIG << 8) |
				   TCPOLEN_MD5SIG);
		/* Update length and the length the header thinks exists */
		arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
		rep.th.doff = arg.iov[0].iov_len / 4;

		tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[1],
					key,
					skb->nh.iph->daddr,
					skb->nh.iph->saddr,
					&rep.th, IPPROTO_TCP,
					arg.iov[0].iov_len);
	}
#endif
	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, arg.iov[0].iov_len);

	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 tcp_timewait_sock *twsk,
			    struct sk_buff *skb, u32 seq, u32 ack,
			    u32 win, u32 ts)
{
	struct tcphdr *th = skb->h.th;
	struct {
		struct tcphdr th;
		__be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2)
#ifdef CONFIG_TCP_MD5SIG
			   + (TCPOLEN_MD5SIG_ALIGNED >> 2)
#endif
			];
	} rep;
	struct ip_reply_arg arg;
#ifdef CONFIG_TCP_MD5SIG
	struct tcp_md5sig_key *key;
	struct tcp_md5sig_key tw_key;
#endif

	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.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
				   (TCPOPT_TIMESTAMP << 8) |
				   TCPOLEN_TIMESTAMP);
		rep.opt[1] = htonl(tcp_time_stamp);
		rep.opt[2] = htonl(ts);
		arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
	}

	/* 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);

#ifdef CONFIG_TCP_MD5SIG
	/*
	 * The SKB holds an imcoming packet, but may not have a valid ->sk
	 * pointer. This is especially the case when we're dealing with a
	 * TIME_WAIT ack, because the sk structure is long gone, and only
	 * the tcp_timewait_sock remains. So the md5 key is stashed in that
	 * structure, and we use it in preference.  I believe that (twsk ||
	 * skb->sk) holds true, but we program defensively.
	 */
	if (!twsk && skb->sk) {
		key = tcp_v4_md5_do_lookup(skb->sk, skb->nh.iph->daddr);
	} else if (twsk && twsk->tw_md5_keylen) {
		tw_key.key = twsk->tw_md5_key;
		tw_key.keylen = twsk->tw_md5_keylen;
		key = &tw_key;
	} else
		key = NULL;

	if (key) {
		int offset = (ts) ? 3 : 0;

		rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |
					  (TCPOPT_NOP << 16) |
					  (TCPOPT_MD5SIG << 8) |
					  TCPOLEN_MD5SIG);
		arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED;
		rep.th.doff = arg.iov[0].iov_len/4;

		tcp_v4_do_calc_md5_hash((__u8 *)&rep.opt[offset],
					key,
					skb->nh.iph->daddr,
					skb->nh.iph->saddr,
					&rep.th, IPPROTO_TCP,
					arg.iov[0].iov_len);
	}
#endif
	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);
	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);

	tcp_v4_send_ack(tcptw, 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(NULL, skb, tcp_rsk(req)->snt_isn + 1,
			tcp_rsk(req)->rcv_isn + 1, req->rcv_wnd,
			req->ts_recent);
}

/*
 *	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 = inet_csk_route_req(sk, req)) == NULL)
		goto out;

	skb = tcp_make_synack(sk, dst, req);

	if (skb) {
		struct tcphdr *th = skb->h.th;

		th->check = tcp_v4_check(skb->len,
					 ireq->loc_addr,
					 ireq->rmt_addr,
					 csum_partial((char *)th, skb->len,
						      skb->csum));

		err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr,
					    ireq->rmt_addr,
					    ireq->opt);
		err = net_xmit_eval(err);
	}

out:
	dst_release(dst);
	return err;
}

/*
 *	IPv4 request_sock destructor.
 */
static void tcp_v4_reqsk_destructor(struct request_sock *req)
{
	kfree(inet_rsk(req)->opt);
}

#ifdef CONFIG_SYN_COOKIES
static void syn_flood_warning(struct sk_buff *skb)
{
	static unsigned long warntime;

	if (time_after(jiffies, (warntime + HZ * 60))) {
		warntime = jiffies;
		printk(KERN_INFO
		       "possible SYN flooding on port %d. Sending cookies.\n",
		       ntohs(skb->h.th->dest));
	}
}
#endif

/*
 * Save and compile IPv4 options into the request_sock if needed.
 */
static struct ip_options *tcp_v4_save_options(struct sock *sk,
					      struct sk_buff *skb)
{
	struct ip_options *opt = &(IPCB(skb)->opt);
	struct ip_options *dopt = NULL;

	if (opt && opt->optlen) {
		int opt_size = optlength(opt);
		dopt = kmalloc(opt_size, GFP_ATOMIC);
		if (dopt) {
			if (ip_options_echo(dopt, skb)) {
				kfree(dopt);
				dopt = NULL;
			}
		}
	}
	return dopt;
}

#ifdef CONFIG_TCP_MD5SIG
/*
 * RFC2385 MD5 checksumming requires a mapping of
 * IP address->MD5 Key.
 * We need to maintain these in the sk structure.
 */

/* Find the Key structure for an address.  */
static struct tcp_md5sig_key *
			tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int i;

	if (!tp->md5sig_info || !tp->md5sig_info->entries4)
		return NULL;
	for (i = 0; i < tp->md5sig_info->entries4; i++) {
		if (tp->md5sig_info->keys4[i].addr == addr)
			return (struct tcp_md5sig_key *)
						&tp->md5sig_info->keys4[i];
	}
	return NULL;
}

struct tcp_md5sig_key *tcp_v4_md5_lookup(struct sock *sk,
					 struct sock *addr_sk)
{
	return tcp_v4_md5_do_lookup(sk, inet_sk(addr_sk)->daddr);
}

EXPORT_SYMBOL(tcp_v4_md5_lookup);

static struct tcp_md5sig_key *tcp_v4_reqsk_md5_lookup(struct sock *sk,
						      struct request_sock *req)
{
	return tcp_v4_md5_do_lookup(sk, inet_rsk(req)->rmt_addr);
}

/* This can be called on a newly created socket, from other files */
int tcp_v4_md5_do_add(struct sock *sk, __be32 addr,
		      u8 *newkey, u8 newkeylen)
{
	/* Add Key to the list */
	struct tcp4_md5sig_key *key;
	struct tcp_sock *tp = tcp_sk(sk);
	struct tcp4_md5sig_key *keys;

	key = (struct tcp4_md5sig_key *)tcp_v4_md5_do_lookup(sk, addr);
	if (key) {
		/* Pre-existing entry - just update that one. */
		kfree(key->key);
		key->key = newkey;
		key->keylen = newkeylen;
	} else {
		struct tcp_md5sig_info *md5sig;

		if (!tp->md5sig_info) {
			tp->md5sig_info = kzalloc(sizeof(*tp->md5sig_info),
						  GFP_ATOMIC);
			if (!tp->md5sig_info) {
				kfree(newkey);
				return -ENOMEM;
			}
		}
		if (tcp_alloc_md5sig_pool() == NULL) {
			kfree(newkey);
			return -ENOMEM;
		}
		md5sig = tp->md5sig_info;

		if (md5sig->alloced4 == md5sig->entries4) {
			keys = kmalloc((sizeof(*keys) *
					(md5sig->entries4 + 1)), GFP_ATOMIC);
			if (!keys) {
				kfree(newkey);
				tcp_free_md5sig_pool();
				return -ENOMEM;
			}

			if (md5sig->entries4)
				memcpy(keys, md5sig->keys4,
				       sizeof(*keys) * md5sig->entries4);

			/* Free old key list, and reference new one */
			if (md5sig->keys4)
				kfree(md5sig->keys4);
			md5sig->keys4 = keys;
			md5sig->alloced4++;
		}
		md5sig->entries4++;
		md5sig->keys4[md5sig->entries4 - 1].addr   = addr;
		md5sig->keys4[md5sig->entries4 - 1].key    = newkey;
		md5sig->keys4[md5sig->entries4 - 1].keylen = newkeylen;
	}
	return 0;
}

EXPORT_SYMBOL(tcp_v4_md5_do_add);

static int tcp_v4_md5_add_func(struct sock *sk, struct sock *addr_sk,
			       u8 *newkey, u8 newkeylen)
{
	return tcp_v4_md5_do_add(sk, inet_sk(addr_sk)->daddr,
				 newkey, newkeylen);
}

int tcp_v4_md5_do_del(struct sock *sk, __be32 addr)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int i;

	for (i = 0; i < tp->md5sig_info->entries4; i++) {
		if (tp->md5sig_info->keys4[i].addr == addr) {
			/* Free the key */
			kfree(tp->md5sig_info->keys4[i].key);
			tp->md5sig_info->entries4--;

			if (tp->md5sig_info->entries4 == 0) {
				kfree(tp->md5sig_info->keys4);
				tp->md5sig_info->keys4 = NULL;
				tp->md5sig_info->alloced4 = 0;
			} else if (tp->md5sig_info->entries4 != i) {
				/* Need to do some manipulation */
				memcpy(&tp->md5sig_info->keys4[i],
				       &tp->md5sig_info->keys4[i+1],
				       (tp->md5sig_info->entries4 - i) *
					sizeof(struct tcp4_md5sig_key));
			}
			tcp_free_md5sig_pool();
			return 0;
		}
	}
	return -ENOENT;
}

EXPORT_SYMBOL(tcp_v4_md5_do_del);

static void tcp_v4_clear_md5_list(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);

	/* Free each key, then the set of key keys,
	 * the crypto element, and then decrement our
	 * hold on the last resort crypto.
	 */
	if (tp->md5sig_info->entries4) {
		int i;
		for (i = 0; i < tp->md5sig_info->entries4; i++)
			kfree(tp->md5sig_info->keys4[i].key);
		tp->md5sig_info->entries4 = 0;
		tcp_free_md5sig_pool();
	}
	if (tp->md5sig_info->keys4) {
		kfree(tp->md5sig_info->keys4);
		tp->md5sig_info->keys4 = NULL;
		tp->md5sig_info->alloced4  = 0;
	}
}

static int tcp_v4_parse_md5_keys(struct sock *sk, char __user *optval,
				 int optlen)
{
	struct tcp_md5sig cmd;
	struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr;
	u8 *newkey;

	if (optlen < sizeof(cmd))
		return -EINVAL;

	if (copy_from_user(&cmd, optval, sizeof(cmd)))
		return -EFAULT;

	if (sin->sin_family != AF_INET)
		return -EINVAL;

	if (!cmd.tcpm_key || !cmd.tcpm_keylen) {
		if (!tcp_sk(sk)->md5sig_info)
			return -ENOENT;
		return tcp_v4_md5_do_del(sk, sin->sin_addr.s_addr);
	}

	if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN)
		return -EINVAL;

	if (!tcp_sk(sk)->md5sig_info) {
		struct tcp_sock *tp = tcp_sk(sk);
		struct tcp_md5sig_info *p = kzalloc(sizeof(*p), GFP_KERNEL);

		if (!p)
			return -EINVAL;