tcp_ipv6.c

Linux Kernel 2.6.9 for OMAP1710

static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, 
			  int addr_len)
{
	struct sockaddr_in6 *usin = (struct sockaddr_in6 *) uaddr;
	struct inet_opt *inet = inet_sk(sk);
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct tcp_opt *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->ts_recent_stamp &&
	    ipv6_addr_cmp(&np->daddr, &usin->sin6_addr)) {
		tp->ts_recent = 0;
		tp->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 = tp->ext_header_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];

		tp->af_specific = &ipv6_mapped;
		sk->sk_backlog_rcv = tcp_v4_do_rcv;

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

		if (err) {
			tp->ext_header_len = exthdrlen;
			tp->af_specific = &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) {
		dst_release(dst);
		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);

	tp->ext_header_len = 0;
	if (np->opt)
		tp->ext_header_len = np->opt->opt_flen + np->opt->opt_nflen;
	tp->ext2_header_len = dst->header_len;

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

	inet->dport = usin->sin6_port;

	tcp_set_state(sk, TCP_SYN_SENT);
	err = tcp_v6_hash_connect(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;
	struct tcphdr *th = (struct tcphdr *)(skb->data+offset);
	struct ipv6_pinfo *np;
	struct sock *sk;
	int err;
	struct tcp_opt *tp; 
	__u32 seq;

	sk = tcp_v6_lookup(&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) {
		tcp_tw_put((struct tcp_tw_bucket*)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_opt *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 (tp->pmtu_cookie > dst_pmtu(dst)) {
			tcp_sync_mss(sk, dst_pmtu(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 open_request */
	switch (sk->sk_state) {
		struct open_request *req, **prev;
	case TCP_LISTEN:
		if (sock_owned_by_user(sk))
			goto out;

		req = tcp_v6_search_req(tp, &prev, th->dest, &hdr->daddr,
					&hdr->saddr, tcp_v6_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 != req->snt_isn) {
			NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
			goto out;
		}

		tcp_synq_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 open_request *req,
			      struct dst_entry *dst)
{
	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, &req->af.v6_req.rmt_addr);
	ipv6_addr_copy(&fl.fl6_src, &req->af.v6_req.loc_addr);
	fl.fl6_flowlabel = 0;
	fl.oif = req->af.v6_req.iif;
	fl.fl_ip_dport = req->rmt_port;
	fl.fl_ip_sport = inet_sk(sk)->sport;

	if (dst == NULL) {
		opt = np->opt;
		if (opt == NULL &&
		    np->rxopt.bits.srcrt == 2 &&
		    req->af.v6_req.pktopts) {
			struct sk_buff *pktopts = req->af.v6_req.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,
					 &req->af.v6_req.loc_addr, &req->af.v6_req.rmt_addr,
					 csum_partial((char *)th, skb->len, skb->csum));

		ipv6_addr_copy(&fl.fl6_dst, &req->af.v6_req.rmt_addr);
		err = ip6_xmit(sk, skb, &fl, opt, 0);
		if (err == NET_XMIT_CN)
			err = 0;
	}

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

static void tcp_v6_or_free(struct open_request *req)
{
	if (req->af.v6_req.pktopts)
		kfree_skb(req->af.v6_req.pktopts);
}

static struct or_calltable or_ipv6 = {
	.family		=	AF_INET6,
	.rtx_syn_ack	=	tcp_v6_send_synack,
	.send_ack	=	tcp_v6_or_send_ack,
	.destructor	=	tcp_v6_or_free,
	.send_reset	=	tcp_v6_send_reset
};

static int ipv6_opt_accepted(struct sock *sk, struct sk_buff *skb)
{
	struct ipv6_pinfo *np = inet6_sk(sk);
	struct inet6_skb_parm *opt = IP6CB(skb);

	if (np->rxopt.all) {
		if ((opt->hop && np->rxopt.bits.hopopts) ||
		    ((IPV6_FLOWINFO_MASK&*(u32*)skb->nh.raw) &&
		     np->rxopt.bits.rxflow) ||
		    (opt->srcrt && np->rxopt.bits.srcrt) ||
		    ((opt->dst1 || opt->dst0) && np->rxopt.bits.dstopts))
			return 1;
	}
	return 0;
}


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

	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 = tcp_v6_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) {
			dst_release(buff->dst);
			return;
		}

		ip6_xmit(NULL, 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);