tcp_timer.c

Linux Kernel 2.6.9 for OMAP1710

		 * connection. If the socket is an orphan, time it out,
		 * we cannot allow such beasts to hang infinitely.
		 */
#ifdef TCP_DEBUG
		if (net_ratelimit()) {
			struct inet_opt *inet = inet_sk(sk);
			printk(KERN_DEBUG "TCP: Treason uncloaked! Peer %u.%u.%u.%u:%u/%u shrinks window %u:%u. Repaired.\n",
			       NIPQUAD(inet->daddr), htons(inet->dport),
			       inet->num, tp->snd_una, tp->snd_nxt);
		}
#endif
		if (tcp_time_stamp - tp->rcv_tstamp > TCP_RTO_MAX) {
			tcp_write_err(sk);
			goto out;
		}
		tcp_enter_loss(sk, 0);
		tcp_retransmit_skb(sk, skb_peek(&sk->sk_write_queue));
		__sk_dst_reset(sk);
		goto out_reset_timer;
	}

	if (tcp_write_timeout(sk))
		goto out;

	if (tp->retransmits == 0) {
		if (tp->ca_state == TCP_CA_Disorder || tp->ca_state == TCP_CA_Recovery) {
			if (tp->sack_ok) {
				if (tp->ca_state == TCP_CA_Recovery)
					NET_INC_STATS_BH(LINUX_MIB_TCPSACKRECOVERYFAIL);
				else
					NET_INC_STATS_BH(LINUX_MIB_TCPSACKFAILURES);
			} else {
				if (tp->ca_state == TCP_CA_Recovery)
					NET_INC_STATS_BH(LINUX_MIB_TCPRENORECOVERYFAIL);
				else
					NET_INC_STATS_BH(LINUX_MIB_TCPRENOFAILURES);
			}
		} else if (tp->ca_state == TCP_CA_Loss) {
			NET_INC_STATS_BH(LINUX_MIB_TCPLOSSFAILURES);
		} else {
			NET_INC_STATS_BH(LINUX_MIB_TCPTIMEOUTS);
		}
	}

	if (tcp_use_frto(sk)) {
		tcp_enter_frto(sk);
	} else {
		tcp_enter_loss(sk, 0);
	}

	if (tcp_retransmit_skb(sk, skb_peek(&sk->sk_write_queue)) > 0) {
		/* Retransmission failed because of local congestion,
		 * do not backoff.
		 */
		if (!tp->retransmits)
			tp->retransmits=1;
		tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS,
				     min(tp->rto, TCP_RESOURCE_PROBE_INTERVAL));
		goto out;
	}

	/* Increase the timeout each time we retransmit.  Note that
	 * we do not increase the rtt estimate.  rto is initialized
	 * from rtt, but increases here.  Jacobson (SIGCOMM 88) suggests
	 * that doubling rto each time is the least we can get away with.
	 * In KA9Q, Karn uses this for the first few times, and then
	 * goes to quadratic.  netBSD doubles, but only goes up to *64,
	 * and clamps at 1 to 64 sec afterwards.  Note that 120 sec is
	 * defined in the protocol as the maximum possible RTT.  I guess
	 * we'll have to use something other than TCP to talk to the
	 * University of Mars.
	 *
	 * PAWS allows us longer timeouts and large windows, so once
	 * implemented ftp to mars will work nicely. We will have to fix
	 * the 120 second clamps though!
	 */
	tp->backoff++;
	tp->retransmits++;

out_reset_timer:
	tp->rto = min(tp->rto << 1, TCP_RTO_MAX);
	tcp_reset_xmit_timer(sk, TCP_TIME_RETRANS, tp->rto);
	if (tp->retransmits > sysctl_tcp_retries1)
		__sk_dst_reset(sk);

out:;
}

static void tcp_write_timer(unsigned long data)
{
	struct sock *sk = (struct sock*)data;
	struct tcp_opt *tp = tcp_sk(sk);
	int event;

	bh_lock_sock(sk);
	if (sock_owned_by_user(sk)) {
		/* Try again later */
		sk_reset_timer(sk, &tp->retransmit_timer, jiffies + (HZ / 20));
		goto out_unlock;
	}

	if (sk->sk_state == TCP_CLOSE || !tp->pending)
		goto out;

	if (time_after(tp->timeout, jiffies)) {
		sk_reset_timer(sk, &tp->retransmit_timer, tp->timeout);
		goto out;
	}

	event = tp->pending;
	tp->pending = 0;

	switch (event) {
	case TCP_TIME_RETRANS:
		tcp_retransmit_timer(sk);
		break;
	case TCP_TIME_PROBE0:
		tcp_probe_timer(sk);
		break;
	}
	TCP_CHECK_TIMER(sk);

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

/*
 *	Timer for listening sockets
 */

static void tcp_synack_timer(struct sock *sk)
{
	struct tcp_opt *tp = tcp_sk(sk);
	struct tcp_listen_opt *lopt = tp->listen_opt;
	int max_retries = tp->syn_retries ? : sysctl_tcp_synack_retries;
	int thresh = max_retries;
	unsigned long now = jiffies;
	struct open_request **reqp, *req;
	int i, budget;

	if (lopt == NULL || lopt->qlen == 0)
		return;

	/* Normally all the openreqs are young and become mature
	 * (i.e. converted to established socket) for first timeout.
	 * If synack was not acknowledged for 3 seconds, it means
	 * one of the following things: synack was lost, ack was lost,
	 * rtt is high or nobody planned to ack (i.e. synflood).
	 * When server is a bit loaded, queue is populated with old
	 * open requests, reducing effective size of queue.
	 * When server is well loaded, queue size reduces to zero
	 * after several minutes of work. It is not synflood,
	 * it is normal operation. The solution is pruning
	 * too old entries overriding normal timeout, when
	 * situation becomes dangerous.
	 *
	 * Essentially, we reserve half of room for young
	 * embrions; and abort old ones without pity, if old
	 * ones are about to clog our table.
	 */
	if (lopt->qlen>>(lopt->max_qlen_log-1)) {
		int young = (lopt->qlen_young<<1);

		while (thresh > 2) {
			if (lopt->qlen < young)
				break;
			thresh--;
			young <<= 1;
		}
	}

	if (tp->defer_accept)
		max_retries = tp->defer_accept;

	budget = 2*(TCP_SYNQ_HSIZE/(TCP_TIMEOUT_INIT/TCP_SYNQ_INTERVAL));
	i = lopt->clock_hand;

	do {
		reqp=&lopt->syn_table[i];
		while ((req = *reqp) != NULL) {
			if (time_after_eq(now, req->expires)) {
				if ((req->retrans < thresh ||
				     (req->acked && req->retrans < max_retries))
				    && !req->class->rtx_syn_ack(sk, req, NULL)) {
					unsigned long timeo;

					if (req->retrans++ == 0)
						lopt->qlen_young--;
					timeo = min((TCP_TIMEOUT_INIT << req->retrans),
						    TCP_RTO_MAX);
					req->expires = now + timeo;
					reqp = &req->dl_next;
					continue;
				}

				/* Drop this request */
				write_lock(&tp->syn_wait_lock);
				*reqp = req->dl_next;
				write_unlock(&tp->syn_wait_lock);
				lopt->qlen--;
				if (req->retrans == 0)
					lopt->qlen_young--;
				tcp_openreq_free(req);
				continue;
			}
			reqp = &req->dl_next;
		}

		i = (i+1)&(TCP_SYNQ_HSIZE-1);

	} while (--budget > 0);

	lopt->clock_hand = i;

	if (lopt->qlen)
		tcp_reset_keepalive_timer(sk, TCP_SYNQ_INTERVAL);
}

void tcp_delete_keepalive_timer (struct sock *sk)
{
	sk_stop_timer(sk, &sk->sk_timer);
}

void tcp_reset_keepalive_timer (struct sock *sk, unsigned long len)
{
	sk_reset_timer(sk, &sk->sk_timer, jiffies + len);
}

void tcp_set_keepalive(struct sock *sk, int val)
{
	if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))
		return;

	if (val && !sock_flag(sk, SOCK_KEEPOPEN))
		tcp_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
	else if (!val)
		tcp_delete_keepalive_timer(sk);
}


static void tcp_keepalive_timer (unsigned long data)
{
	struct sock *sk = (struct sock *) data;
	struct tcp_opt *tp = tcp_sk(sk);
	__u32 elapsed;

	/* Only process if socket is not in use. */
	bh_lock_sock(sk);
	if (sock_owned_by_user(sk)) {
		/* Try again later. */ 
		tcp_reset_keepalive_timer (sk, HZ/20);
		goto out;
	}

	if (sk->sk_state == TCP_LISTEN) {
		tcp_synack_timer(sk);
		goto out;
	}

	if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
		if (tp->linger2 >= 0) {
			int tmo = tcp_fin_time(tp) - TCP_TIMEWAIT_LEN;

			if (tmo > 0) {
				tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
				goto out;
			}
		}
		tcp_send_active_reset(sk, GFP_ATOMIC);
		goto death;
	}

	if (!sock_flag(sk, SOCK_KEEPOPEN) || sk->sk_state == TCP_CLOSE)
		goto out;

	elapsed = keepalive_time_when(tp);

	/* It is alive without keepalive 8) */
	if (tcp_get_pcount(&tp->packets_out) || sk->sk_send_head)
		goto resched;

	elapsed = tcp_time_stamp - tp->rcv_tstamp;

	if (elapsed >= keepalive_time_when(tp)) {
		if ((!tp->keepalive_probes && tp->probes_out >= sysctl_tcp_keepalive_probes) ||
		     (tp->keepalive_probes && tp->probes_out >= tp->keepalive_probes)) {
			tcp_send_active_reset(sk, GFP_ATOMIC);
			tcp_write_err(sk);
			goto out;
		}
		if (tcp_write_wakeup(sk) <= 0) {
			tp->probes_out++;
			elapsed = keepalive_intvl_when(tp);
		} else {
			/* If keepalive was lost due to local congestion,
			 * try harder.
			 */
			elapsed = TCP_RESOURCE_PROBE_INTERVAL;
		}
	} else {
		/* It is tp->rcv_tstamp + keepalive_time_when(tp) */
		elapsed = keepalive_time_when(tp) - elapsed;
	}

	TCP_CHECK_TIMER(sk);
	sk_stream_mem_reclaim(sk);

resched:
	tcp_reset_keepalive_timer (sk, elapsed);
	goto out;

death:	
	tcp_done(sk);

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

EXPORT_SYMBOL(tcp_clear_xmit_timers);
EXPORT_SYMBOL(tcp_delete_keepalive_timer);
EXPORT_SYMBOL(tcp_init_xmit_timers);
EXPORT_SYMBOL(tcp_reset_keepalive_timer);