tcp_ipv6.c

linux 内核源代码

/*
 *	TCP over IPv6
 *	Linux INET6 implementation
 *
 *	Authors:
 *	Pedro Roque		<[e-mail]>
 *
 *	$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/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/snmp.h>
#include <net/dsfield.h>
#include <net/timewait_sock.h>
#include <net/netdma.h>

#include <asm/uaccess.h>

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

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

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

static void	tcp_v6_send_reset(struct sock *sk, 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;
#ifdef CONFIG_TCP_MD5SIG
static struct tcp_sock_af_ops tcp_sock_ipv6_specific;
static struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
#endif

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__ __sum16 tcp_v6_check(struct tcphdr *th, int len,
				   struct in6_addr *saddr,
				   struct in6_addr *daddr,
				   __wsum base)
{
	return csum_ipv6_magic(saddr, daddr, len, IPPROTO_TCP, base);
}

static __u32 tcp_v6_init_sequence(struct sk_buff *skb)
{
	return secure_tcpv6_sequence_number(ipv6_hdr(skb)->daddr.s6_addr32,
					    ipv6_hdr(skb)->saddr.s6_addr32,
					    tcp_hdr(skb)->dest,
					    tcp_hdr(skb)->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;
#ifdef CONFIG_TCP_MD5SIG
		tp->af_specific = &tcp_sock_ipv6_mapped_specific;
#endif

		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;
#ifdef CONFIG_TCP_MD5SIG
			tp->af_specific = &tcp_sock_ipv6_specific;
#endif
			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;
	}

	security_sk_classify_flow(sk, &fl);

	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, 1)) < 0) {
		if (err == -EREMOTE)
			err = ip6_dst_blackhole(sk, &dst, &fl);
		if (err < 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;

	sk->sk_gso_type = SKB_GSO_TCPV6;
	__ip6_dst_store(sk, dst, NULL, NULL);

	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, __be32 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(inet_twsk(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;
			security_skb_classify_flow(skb, &fl);

			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)) {
			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;
	security_req_classify_flow(req, &fl);

	if (dst == NULL) {
		opt = np->opt;
		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 = tcp_hdr(skb);

		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);
		err = net_xmit_eval(err);
	}

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);
}

#ifdef CONFIG_TCP_MD5SIG
static struct tcp_md5sig_key *tcp_v6_md5_do_lookup(struct sock *sk,
						   struct in6_addr *addr)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int i;

	BUG_ON(tp == NULL);

	if (!tp->md5sig_info || !tp->md5sig_info->entries6)
		return NULL;

	for (i = 0; i < tp->md5sig_info->entries6; i++) {
		if (ipv6_addr_cmp(&tp->md5sig_info->keys6[i].addr, addr) == 0)
			return &tp->md5sig_info->keys6[i].base;
	}
	return NULL;