tcp_timer.c

嵌入式系统设计与实验教材二源码linux内核移植与编译

/*
 * 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_timer.c,v 1.87 2001/09/21 21:27:34 davem Exp $
 *
 * Authors:	Ross Biro, <[e-mail]>
 *		Fred N. van Kempen, <[e-mail]>
 *		Mark Evans, <[e-mail]>
 *		Corey Minyard <wf-rch![e-mail]>
 *		Florian La Roche, <[e-mail]>
 *		Charles Hedrick, <[e-mail]>
 *		Linus Torvalds, <[e-mail]>
 *		Alan Cox, <[e-mail]>
 *		Matthew Dillon, <[e-mail]>
 *		Arnt Gulbrandsen, <[e-mail]>
 *		Jorge Cwik, <[e-mail]>
 */

#include <net/tcp.h>

int sysctl_tcp_syn_retries = TCP_SYN_RETRIES; 
int sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; 
int sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME;
int sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES;
int sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL;
int sysctl_tcp_retries1 = TCP_RETR1;
int sysctl_tcp_retries2 = TCP_RETR2;
int sysctl_tcp_orphan_retries;

static void tcp_write_timer(unsigned long);
static void tcp_delack_timer(unsigned long);
static void tcp_keepalive_timer (unsigned long data);

const char timer_bug_msg[] = KERN_DEBUG "tcpbug: unknown timer value\n";

/*
 * Using different timers for retransmit, delayed acks and probes
 * We may wish use just one timer maintaining a list of expire jiffies 
 * to optimize.
 */

void tcp_init_xmit_timers(struct sock *sk)
{
	struct tcp_opt *tp = &sk->tp_pinfo.af_tcp;

	init_timer(&tp->retransmit_timer);
	tp->retransmit_timer.function=&tcp_write_timer;
	tp->retransmit_timer.data = (unsigned long) sk;
	tp->pending = 0;

	init_timer(&tp->delack_timer);
	tp->delack_timer.function=&tcp_delack_timer;
	tp->delack_timer.data = (unsigned long) sk;
	tp->ack.pending = 0;

	init_timer(&sk->timer);
	sk->timer.function=&tcp_keepalive_timer;
	sk->timer.data = (unsigned long) sk;
}

void tcp_clear_xmit_timers(struct sock *sk)
{
	struct tcp_opt *tp = &sk->tp_pinfo.af_tcp;

	tp->pending = 0;
	if (timer_pending(&tp->retransmit_timer) &&
	    del_timer(&tp->retransmit_timer))
		__sock_put(sk);

	tp->ack.pending = 0;
	tp->ack.blocked = 0;
	if (timer_pending(&tp->delack_timer) &&
	    del_timer(&tp->delack_timer))
		__sock_put(sk);

	if(timer_pending(&sk->timer) && del_timer(&sk->timer))
		__sock_put(sk);
}

static void tcp_write_err(struct sock *sk)
{
	sk->err = sk->err_soft ? : ETIMEDOUT;
	sk->error_report(sk);

	tcp_done(sk);
	NET_INC_STATS_BH(TCPAbortOnTimeout);
}

/* Do not allow orphaned sockets to eat all our resources.
 * This is direct violation of TCP specs, but it is required
 * to prevent DoS attacks. It is called when a retransmission timeout
 * or zero probe timeout occurs on orphaned socket.
 *
 * Criterium is still not confirmed experimentally and may change.
 * We kill the socket, if:
 * 1. If number of orphaned sockets exceeds an administratively configured
 *    limit.
 * 2. If we have strong memory pressure.
 */
static int tcp_out_of_resources(struct sock *sk, int do_reset)
{
	struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);
	int orphans = atomic_read(&tcp_orphan_count);

	/* If peer does not open window for long time, or did not transmit 
	 * anything for long time, penalize it. */
	if ((s32)(tcp_time_stamp - tp->lsndtime) > 2*TCP_RTO_MAX || !do_reset)
		orphans <<= 1;

	/* If some dubious ICMP arrived, penalize even more. */
	if (sk->err_soft)
		orphans <<= 1;

	if (orphans >= sysctl_tcp_max_orphans ||
	    (sk->wmem_queued > SOCK_MIN_SNDBUF &&
	     atomic_read(&tcp_memory_allocated) > sysctl_tcp_mem[2])) {
		if (net_ratelimit())
			printk(KERN_INFO "Out of socket memory\n");

		/* Catch exceptional cases, when connection requires reset.
		 *      1. Last segment was sent recently. */
		if ((s32)(tcp_time_stamp - tp->lsndtime) <= TCP_TIMEWAIT_LEN ||
		    /*  2. Window is closed. */
		    (!tp->snd_wnd && !tp->packets_out))
			do_reset = 1;
		if (do_reset)
			tcp_send_active_reset(sk, GFP_ATOMIC);
		tcp_done(sk);
		NET_INC_STATS_BH(TCPAbortOnMemory);
		return 1;
	}
	return 0;
}

/* Calculate maximal number or retries on an orphaned socket. */
static int tcp_orphan_retries(struct sock *sk, int alive)
{
	int retries = sysctl_tcp_orphan_retries; /* May be zero. */

	/* We know from an ICMP that something is wrong. */
	if (sk->err_soft && !alive)
		retries = 0;

	/* However, if socket sent something recently, select some safe
	 * number of retries. 8 corresponds to >100 seconds with minimal
	 * RTO of 200msec. */
	if (retries == 0 && alive)
		retries = 8;
	return retries;
}

/* A write timeout has occurred. Process the after effects. */
static int tcp_write_timeout(struct sock *sk)
{
	struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);
	int retry_until;

	if ((1<<sk->state)&(TCPF_SYN_SENT|TCPF_SYN_RECV)) {
		if (tp->retransmits)
			dst_negative_advice(&sk->dst_cache);
		retry_until = tp->syn_retries ? : sysctl_tcp_syn_retries;
	} else {
		if (tp->retransmits >= sysctl_tcp_retries1) {
			/* NOTE. draft-ietf-tcpimpl-pmtud-01.txt requires pmtu black
			   hole detection. :-(

			   It is place to make it. It is not made. I do not want
			   to make it. It is disguisting. It does not work in any
			   case. Let me to cite the same draft, which requires for
			   us to implement this:

   "The one security concern raised by this memo is that ICMP black holes
   are often caused by over-zealous security administrators who block
   all ICMP messages.  It is vitally important that those who design and
   deploy security systems understand the impact of strict filtering on
   upper-layer protocols.  The safest web site in the world is worthless
   if most TCP implementations cannot transfer data from it.  It would
   be far nicer to have all of the black holes fixed rather than fixing
   all of the TCP implementations."

                           Golden words :-).
		   */

			dst_negative_advice(&sk->dst_cache);
		}

		retry_until = sysctl_tcp_retries2;
		if (sk->dead) {
			int alive = (tp->rto < TCP_RTO_MAX);
 
			retry_until = tcp_orphan_retries(sk, alive);

			if (tcp_out_of_resources(sk, alive || tp->retransmits < retry_until))
				return 1;
		}
	}

	if (tp->retransmits >= retry_until) {
		/* Has it gone just too far? */
		tcp_write_err(sk);
		return 1;
	}
	return 0;
}

static void tcp_delack_timer(unsigned long data)
{
	struct sock *sk = (struct sock*)data;
	struct tcp_opt *tp = &(sk->tp_pinfo.af_tcp);

	bh_lock_sock(sk);
	if (sk->lock.users) {
		/* Try again later. */
		tp->ack.blocked = 1;
		NET_INC_STATS_BH(DelayedACKLocked);
		if (!mod_timer(&tp->delack_timer, jiffies + TCP_DELACK_MIN))
			sock_hold(sk);
		goto out_unlock;
	}

	tcp_mem_reclaim(sk);

	if (sk->state == TCP_CLOSE || !(tp->ack.pending&TCP_ACK_TIMER))
		goto out;

	if ((long)(tp->ack.timeout - jiffies) > 0) {
		if (!mod_timer(&tp->delack_timer, tp->ack.timeout))
			sock_hold(sk);
		goto out;
	}
	tp->ack.pending &= ~TCP_ACK_TIMER;

	if (skb_queue_len(&tp->ucopy.prequeue)) {
		struct sk_buff *skb;

		net_statistics[smp_processor_id()*2].TCPSchedulerFailed += skb_queue_len(&tp->ucopy.prequeue);

		while ((skb = __skb_dequeue(&tp->ucopy.prequeue)) != NULL)
			sk->backlog_rcv(sk, skb);

		tp->ucopy.memory = 0;
	}

	if (tcp_ack_scheduled(tp)) {
		if (!tp->ack.pingpong) {
			/* Delayed ACK missed: inflate ATO. */
			tp->ack.ato = min(tp->ack.ato << 1, tp->rto);
		} else {
			/* Delayed ACK missed: leave pingpong mode and
			 * deflate ATO.
			 */
			tp->ack.pingpong = 0;
			tp->ack.ato = TCP_ATO_MIN;
		}
		tcp_send_ack(sk);
		NET_INC_STATS_BH(DelayedACKs);
	}
	TCP_CHECK_TIMER(sk);

out:
	if (tcp_memory_pressure)
		tcp_mem_reclaim(sk);
out_unlock:
	bh_unlock_sock(sk);
	sock_put(sk);
}

static void tcp_probe_timer(struct sock *sk)
{
	struct tcp_opt *tp = &sk->tp_pinfo.af_tcp;
	int max_probes;

	if (tp->packets_out || !tp->send_head) {
		tp->probes_out = 0;
		return;
	}

	/* *WARNING* RFC 1122 forbids this
	 *
	 * It doesn't AFAIK, because we kill the retransmit timer -AK
	 *
	 * FIXME: We ought not to do it, Solaris 2.5 actually has fixing
	 * this behaviour in Solaris down as a bug fix. [AC]
	 *
	 * Let me to explain. probes_out is zeroed by incoming ACKs
	 * even if they advertise zero window. Hence, connection is killed only
	 * if we received no ACKs for normal connection timeout. It is not killed
	 * only because window stays zero for some time, window may be zero
	 * until armageddon and even later. We are in full accordance
	 * with RFCs, only probe timer combines both retransmission timeout
	 * and probe timeout in one bottle.				--ANK
	 */
	max_probes = sysctl_tcp_retries2;

	if (sk->dead) {
		int alive = ((tp->rto<<tp->backoff) < TCP_RTO_MAX);
 
		max_probes = tcp_orphan_retries(sk, alive);

		if (tcp_out_of_resources(sk, alive || tp->probes_out <= max_probes))
			return;
	}

	if (tp->probes_out > max_probes) {
		tcp_write_err(sk);
	} else {
		/* Only send another probe if we didn't close things up. */
		tcp_send_probe0(sk);
	}
}

/*
 *	The TCP retransmit timer.
 */

static void tcp_retransmit_timer(struct sock *sk)
{
	struct tcp_opt *tp = &sk->tp_pinfo.af_tcp;

	if (tp->packets_out == 0)
		goto out;