tcp_ipv4.c

Linux Kernel 2.6.9 for OMAP1710

	newinet->rcv_saddr    = req->af.v4_req.loc_addr;
	newinet->saddr	      = req->af.v4_req.loc_addr;
	newinet->opt	      = req->af.v4_req.opt;
	req->af.v4_req.opt    = NULL;
	newinet->mc_index     = tcp_v4_iif(skb);
	newinet->mc_ttl	      = skb->nh.iph->ttl;
	newtp->ext_header_len = 0;
	if (newinet->opt)
		newtp->ext_header_len = newinet->opt->optlen;
	newtp->ext2_header_len = dst->header_len;
	newinet->id = newtp->write_seq ^ jiffies;

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

	__tcp_v4_hash(newsk, 0);
	__tcp_inherit_port(sk, newsk);

	return newsk;

exit_overflow:
	NET_INC_STATS_BH(LINUX_MIB_LISTENOVERFLOWS);
exit:
	NET_INC_STATS_BH(LINUX_MIB_LISTENDROPS);
	dst_release(dst);
	return NULL;
}

static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
{
	struct tcphdr *th = skb->h.th;
	struct iphdr *iph = skb->nh.iph;
	struct tcp_opt *tp = tcp_sk(sk);
	struct sock *nsk;
	struct open_request **prev;
	/* Find possible connection requests. */
	struct open_request *req = tcp_v4_search_req(tp, &prev, th->source,
						     iph->saddr, iph->daddr);
	if (req)
		return tcp_check_req(sk, skb, req, prev);

	nsk = __tcp_v4_lookup_established(skb->nh.iph->saddr,
					  th->source,
					  skb->nh.iph->daddr,
					  ntohs(th->dest),
					  tcp_v4_iif(skb));

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

#ifdef CONFIG_SYN_COOKIES
	if (!th->rst && !th->syn && th->ack)
		sk = cookie_v4_check(sk, skb, &(IPCB(skb)->opt));
#endif
	return sk;
}

static int tcp_v4_checksum_init(struct sk_buff *skb)
{
	if (skb->ip_summed == CHECKSUM_HW) {
		skb->ip_summed = CHECKSUM_UNNECESSARY;
		if (!tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr,
				  skb->nh.iph->daddr, skb->csum))
			return 0;

		NETDEBUG(if (net_ratelimit())
				printk(KERN_DEBUG "hw tcp v4 csum failed\n"));
		skb->ip_summed = CHECKSUM_NONE;
	}
	if (skb->len <= 76) {
		if (tcp_v4_check(skb->h.th, skb->len, skb->nh.iph->saddr,
				 skb->nh.iph->daddr,
				 skb_checksum(skb, 0, skb->len, 0)))
			return -1;
		skb->ip_summed = CHECKSUM_UNNECESSARY;
	} else {
		skb->csum = ~tcp_v4_check(skb->h.th, skb->len,
					  skb->nh.iph->saddr,
					  skb->nh.iph->daddr, 0);
	}
	return 0;
}


/* The socket must have it's spinlock held when we get
 * here.
 *
 * We have a potential double-lock case here, so even when
 * doing backlog processing we use the BH locking scheme.
 * This is because we cannot sleep with the original spinlock
 * held.
 */
int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
{
	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
		TCP_CHECK_TIMER(sk);
		if (tcp_rcv_established(sk, skb, skb->h.th, skb->len))
			goto reset;
		TCP_CHECK_TIMER(sk);
		return 0;
	}

	if (skb->len < (skb->h.th->doff << 2) || tcp_checksum_complete(skb))
		goto csum_err;

	if (sk->sk_state == TCP_LISTEN) {
		struct sock *nsk = tcp_v4_hnd_req(sk, skb);
		if (!nsk)
			goto discard;

		if (nsk != sk) {
			if (tcp_child_process(sk, nsk, skb))
				goto reset;
			return 0;
		}
	}

	TCP_CHECK_TIMER(sk);
	if (tcp_rcv_state_process(sk, skb, skb->h.th, skb->len))
		goto reset;
	TCP_CHECK_TIMER(sk);
	return 0;

reset:
	tcp_v4_send_reset(skb);
discard:
	kfree_skb(skb);
	/* Be careful here. If this function gets more complicated and
	 * gcc suffers from register pressure on the x86, sk (in %ebx)
	 * might be destroyed here. This current version compiles correctly,
	 * but you have been warned.
	 */
	return 0;

csum_err:
	TCP_INC_STATS_BH(TCP_MIB_INERRS);
	goto discard;
}

/*
 *	From tcp_input.c
 */

int tcp_v4_rcv(struct sk_buff *skb)
{
	struct tcphdr *th;
	struct sock *sk;
	int ret;

	if (skb->pkt_type != PACKET_HOST)
		goto discard_it;

	/* Count it even if it's bad */
	TCP_INC_STATS_BH(TCP_MIB_INSEGS);

	if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
		goto discard_it;

	th = skb->h.th;

	if (th->doff < sizeof(struct tcphdr) / 4)
		goto bad_packet;
	if (!pskb_may_pull(skb, th->doff * 4))
		goto discard_it;

	/* An explanation is required here, I think.
	 * Packet length and doff are validated by header prediction,
	 * provided case of th->doff==0 is elimineted.
	 * So, we defer the checks. */
	if ((skb->ip_summed != CHECKSUM_UNNECESSARY &&
	     tcp_v4_checksum_init(skb) < 0))
		goto bad_packet;

	th = skb->h.th;
	TCP_SKB_CB(skb)->seq = ntohl(th->seq);
	TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin +
				    skb->len - th->doff * 4);
	TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq);
	TCP_SKB_CB(skb)->when	 = 0;
	TCP_SKB_CB(skb)->flags	 = skb->nh.iph->tos;
	TCP_SKB_CB(skb)->sacked	 = 0;

	sk = __tcp_v4_lookup(skb->nh.iph->saddr, th->source,
			     skb->nh.iph->daddr, ntohs(th->dest),
			     tcp_v4_iif(skb));

	if (!sk)
		goto no_tcp_socket;

process:
	if (sk->sk_state == TCP_TIME_WAIT)
		goto do_time_wait;

	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
		goto discard_and_relse;

	if (sk_filter(sk, skb, 0))
		goto discard_and_relse;

	skb->dev = NULL;

	bh_lock_sock(sk);
	ret = 0;
	if (!sock_owned_by_user(sk)) {
		if (!tcp_prequeue(sk, skb))
			ret = tcp_v4_do_rcv(sk, skb);
	} else
		sk_add_backlog(sk, skb);
	bh_unlock_sock(sk);

	sock_put(sk);

	return ret;

no_tcp_socket:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
		goto discard_it;

	if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
bad_packet:
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
	} else {
		tcp_v4_send_reset(skb);
	}

discard_it:
	/* Discard frame. */
	kfree_skb(skb);
  	return 0;

discard_and_relse:
	sock_put(sk);
	goto discard_it;

do_time_wait:
	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
		tcp_tw_put((struct tcp_tw_bucket *) sk);
		goto discard_it;
	}

	if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
		TCP_INC_STATS_BH(TCP_MIB_INERRS);
		tcp_tw_put((struct tcp_tw_bucket *) sk);
		goto discard_it;
	}
	switch (tcp_timewait_state_process((struct tcp_tw_bucket *)sk,
					   skb, th, skb->len)) {
	case TCP_TW_SYN: {
		struct sock *sk2 = tcp_v4_lookup_listener(skb->nh.iph->daddr,
							  ntohs(th->dest),
							  tcp_v4_iif(skb));
		if (sk2) {
			tcp_tw_deschedule((struct tcp_tw_bucket *)sk);
			tcp_tw_put((struct tcp_tw_bucket *)sk);
			sk = sk2;
			goto process;
		}
		/* Fall through to ACK */
	}
	case TCP_TW_ACK:
		tcp_v4_timewait_ack(sk, skb);
		break;
	case TCP_TW_RST:
		goto no_tcp_socket;
	case TCP_TW_SUCCESS:;
	}
	goto discard_it;
}

/* With per-bucket locks this operation is not-atomic, so that
 * this version is not worse.
 */
static void __tcp_v4_rehash(struct sock *sk)
{
	sk->sk_prot->unhash(sk);
	sk->sk_prot->hash(sk);
}

static int tcp_v4_reselect_saddr(struct sock *sk)
{
	struct inet_opt *inet = inet_sk(sk);
	int err;
	struct rtable *rt;
	__u32 old_saddr = inet->saddr;
	__u32 new_saddr;
	__u32 daddr = inet->daddr;

	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;

	/* Query new route. */
	err = ip_route_connect(&rt, daddr, 0,
			       RT_TOS(inet->tos) | sk->sk_localroute,
			       sk->sk_bound_dev_if,
			       IPPROTO_TCP,
			       inet->sport, inet->dport, sk);
	if (err)
		return err;

	__sk_dst_set(sk, &rt->u.dst);
	tcp_v4_setup_caps(sk, &rt->u.dst);
	tcp_sk(sk)->ext2_header_len = rt->u.dst.header_len;

	new_saddr = rt->rt_src;

	if (new_saddr == old_saddr)
		return 0;

	if (sysctl_ip_dynaddr > 1) {
		printk(KERN_INFO "tcp_v4_rebuild_header(): shifting inet->"
				 "saddr from %d.%d.%d.%d to %d.%d.%d.%d\n",
		       NIPQUAD(old_saddr),
		       NIPQUAD(new_saddr));
	}

	inet->saddr = new_saddr;
	inet->rcv_saddr = new_saddr;

	/* XXX The only one ugly spot where we need to
	 * XXX really change the sockets identity after
	 * XXX it has entered the hashes. -DaveM
	 *
	 * Besides that, it does not check for connection
	 * uniqueness. Wait for troubles.
	 */
	__tcp_v4_rehash(sk);
	return 0;
}

int tcp_v4_rebuild_header(struct sock *sk)
{
	struct inet_opt *inet = inet_sk(sk);
	struct rtable *rt = (struct rtable *)__sk_dst_check(sk, 0);
	u32 daddr;
	int err;

	/* Route is OK, nothing to do. */
	if (rt)
		return 0;

	/* Reroute. */
	daddr = inet->daddr;
	if (inet->opt && inet->opt->srr)
		daddr = inet->opt->faddr;

	{
		struct flowi fl = { .oif = sk->sk_bound_dev_if,
				    .nl_u = { .ip4_u =
					      { .daddr = daddr,
						.saddr = inet->saddr,
						.tos = RT_CONN_FLAGS(sk) } },
				    .proto = IPPROTO_TCP,
				    .uli_u = { .ports =
					       { .sport = inet->sport,
						 .dport = inet->dport } } };
						
		err = ip_route_output_flow(&rt, &fl, sk, 0);
	}
	if (!err) {
		__sk_dst_set(sk, &rt->u.dst);
		tcp_v4_setup_caps(sk, &rt->u.dst);
		tcp_sk(sk)->ext2_header_len = rt->u.dst.header_len;
		return 0;
	}

	/* Routing failed... */
	sk->sk_route_caps = 0;

	if (!sysctl_ip_dynaddr ||
	    sk->sk_state != TCP_SYN_SENT ||
	    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
	    (err = tcp_v4_reselect_saddr(sk)) != 0)
		sk->sk_err_soft = -err;

	return err;
}

static void v4_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr)
{
	struct sockaddr_in *sin = (struct sockaddr_in *) uaddr;
	struct inet_opt *inet = inet_sk(sk);

	sin->sin_family		= AF_INET;
	sin->sin_addr.s_addr	= inet->daddr;
	sin->sin_port		= inet->dport;
}

/* VJ's idea. Save last timestamp seen from this destination
 * and hold it at least for normal timewait interval to use for duplicate
 * segment detection in subsequent connections, before they enter synchronized
 * state.
 */

int tcp_v4_remember_stamp(struct sock *sk)
{
	struct inet_opt *inet = inet_sk(sk);
	struct tcp_opt *tp = tcp_sk(sk);
	struct rtable *rt = (struct rtable *)__sk_dst_get(sk);
	struct inet_peer *peer = NULL;
	int release_it = 0;

	if (!rt || rt->rt_dst != inet->daddr) {
		peer = inet_getpeer(inet->daddr, 1);
		release_it = 1;
	} else {
		if (!rt->peer)
			rt_bind_peer(rt, 1);
		peer = rt->peer;
	}

	if (peer) {
		if ((s32)(peer->tcp_ts - tp->ts_recent) <= 0 ||
		    (peer->tcp_ts_stamp + TCP_PAWS_MSL < xtime.tv_sec &&
		     peer->tcp_ts_stamp <= tp->ts_recent_stamp)) {
			peer->tcp_ts_stamp = tp->ts_recent_stamp;
			peer->tcp_ts = tp->ts_recent;
		}
		if (release_it)
			inet_putpeer(peer);
		return 1;
	}

	return 0;
}

int tcp_v4_tw_remember_stamp(struct tcp_tw_bucket *tw)
{
	struct inet_peer *peer = NULL;

	peer = inet_getpeer(tw->tw_daddr, 1);

	if (peer) {
		if ((s32)(peer->tcp_ts - tw->tw_ts_recent) <= 0 ||
		    (peer->tcp_ts_stamp + TCP_PAWS_MSL < xtime.tv_sec &&
		     peer->tcp_ts_stamp <= tw->tw_ts_recent_stamp)) {
			peer->tcp_ts_stamp = tw->tw_ts_recent_stamp;
			peer->tcp_ts = tw->tw_ts_recent;
		}
		inet_putpeer(peer);
		return 1;
	}

	return 0;
}

struct tcp_func ipv4_specific = {
	.queue_xmit	=	ip_queue_xmit,
	.send_check	=	tcp_v4_send_check,
	.rebuild_header	=	tcp_v4_rebuild_header,
	.conn_request	=	tcp_v4_conn_request,
	.syn_recv_sock	=	tcp_v4_syn_recv_sock,
	.remember_stamp	=	tcp_v4_remember_stamp,
	.net_header_len	=	sizeof(struct iphdr),
	.setsockopt	=	ip_setsockopt,
	.getsockopt	=	ip_getsockopt,
	.addr2sockaddr	=	v4_addr2sockaddr,
	.sockaddr_len	=	sizeof(struct sockaddr_in),
};

/* NOTE: A lot of things set to zero explicitly by call to
 *       sk_alloc() so need not be done here.
 */
static int tcp_v4_init_sock(struct sock *sk)
{
	struct tcp_opt *tp = tcp_sk(sk);

	skb_queue_head_init(&tp->out_of_order_queue);
	tcp_init_xmit_timers(sk);
	tcp_prequeue_init(tp);

	tp->rto  = TCP_TIMEOUT_INIT;
	tp->mdev = TCP_TIMEOUT_INIT;

	/* So many TCP implementations out there (incorrectly) count the
	 * initial SYN frame in their delayed-ACK and congestion control
	 * algorithms that we must have the following bandaid to talk
	 * efficiently to them.  -DaveM
	 */
	tp->snd_cwnd = 2;

	/* See draft-stevens-tcpca-spec-01 for discussion of the
	 * initialization of these values.
	 */
	tp->snd_ssthresh = 0x7fffffff;	/* Infinity */
	tp->snd_cwnd_clamp = ~0;
	tp->mss_cache_std = tp->mss_cache = 536;

	tp->reordering = sysctl_tcp_reordering;

	sk->sk_state = TCP_CLOSE;

	sk->sk_write_space = sk_stream_write_space;
	sk->sk_use_write_queue = 1;

	tp->af_specific = &ipv4_specific;

	sk->sk_sndbuf = sysctl_tcp_wmem[1];
	sk->sk_rcvbuf = sysctl_tcp_rmem[1];

	atomic_inc(&tcp_sockets_allocated);

	return 0;
}

int tcp_v4_destroy_sock(struct sock *sk)
{
	struct tcp_opt *tp = tcp_sk(sk);

	tcp_clear_xmit_timers(sk);

	/* Cleanup up the write buffer. */
  	sk_stream_writequeue_purge(sk);

	/* Cleans up our, hopefully empty, out_of_order_queue. */
  	__skb_queue_purge(&tp->out_of_order_queue);

	/* Clean prequeue, it must be empty really */
	__skb_queue_purge(&tp->ucopy.prequeue);

	/* Clean up a referenced TCP bind bucket. */