cregit-Linux how code gets into the kernel

Release 4.11 net/ipv4/tcp_timer.c

Directory: net/ipv4
/*
 * 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).
 *
 * Authors:     Ross Biro
 *              Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG>
 *              Mark Evans, <evansmp@uhura.aston.ac.uk>
 *              Corey Minyard <wf-rch!minyard@relay.EU.net>
 *              Florian La Roche, <flla@stud.uni-sb.de>
 *              Charles Hedrick, <hedrick@klinzhai.rutgers.edu>
 *              Linus Torvalds, <torvalds@cs.helsinki.fi>
 *              Alan Cox, <gw4pts@gw4pts.ampr.org>
 *              Matthew Dillon, <dillon@apollo.west.oic.com>
 *              Arnt Gulbrandsen, <agulbra@nvg.unit.no>
 *              Jorge Cwik, <jorge@laser.satlink.net>
 */

#include <linux/module.h>
#include <linux/gfp.h>
#include <net/tcp.h>


int sysctl_tcp_thin_linear_timeouts __read_mostly;

/**
 *  tcp_write_err() - close socket and save error info
 *  @sk:  The socket the error has appeared on.
 *
 *  Returns: Nothing (void)
 */




static void tcp_write_err(struct sock *sk)
{
	sk->sk_err = sk->sk_err_soft ? : ETIMEDOUT;
	sk->sk_error_report(sk);

	tcp_done(sk);
	__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)3477.27%555.56%


Pavel Emelyanov511.36%111.11%


Arnaldo Carvalho de Melo36.82%111.11%


Eric Dumazet12.27%111.11%


Hideaki Yoshifuji / 吉藤英明12.27%111.11%


Total44100.00%9100.00%



/**
 *  tcp_out_of_resources() - Close socket if out of resources
 *  @sk:        pointer to current socket
 *  @do_reset:  send a last packet with reset flag
 *
 *  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.
 *
 *  Criteria 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, bool do_reset)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int shift = 0;

	/* 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)
		shift++;

	/* If some dubious ICMP arrived, penalize even more. */
	if (sk->sk_err_soft)
		shift++;

	if (tcp_check_oom(sk, shift)) {
		/* 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 = true;
		if (do_reset)
			tcp_send_active_reset(sk, GFP_ATOMIC);
		tcp_done(sk);
		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONMEMORY);
		return 1;
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)11482.01%215.38%


David S. Miller107.19%215.38%


Pavel Emelyanov75.04%215.38%


Arnaldo Carvalho de Melo21.44%215.38%


Yuchung Cheng21.44%17.69%


Hideaki Yoshifuji / 吉藤英明21.44%215.38%


Arun Sharma10.72%17.69%


Eric Dumazet10.72%17.69%


Total139100.00%13100.00%



/**
 *  tcp_orphan_retries() - Returns maximal number of retries on an orphaned socket
 *  @sk:    Pointer to the current socket.
 *  @alive: bool, socket alive state
 */



static int tcp_orphan_retries(struct sock *sk, bool alive)
{
	int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */

	/* We know from an ICMP that something is wrong. */
	if (sk->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;
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)4884.21%125.00%


Nikolay Borisov712.28%125.00%


Richard Sailer11.75%125.00%


Arnaldo Carvalho de Melo11.75%125.00%


Total57100.00%4100.00%






static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
{
	struct net *net = sock_net(sk);

	/* Black hole detection */
	if (net->ipv4.sysctl_tcp_mtu_probing) {
		if (!icsk->icsk_mtup.enabled) {
			icsk->icsk_mtup.enabled = 1;
			icsk->icsk_mtup.probe_timestamp = tcp_time_stamp;
			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
		} else {
			struct net *net = sock_net(sk);
			struct tcp_sock *tp = tcp_sk(sk);
			int mss;

			mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
			mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
			mss = max(mss, 68 - tp->tcp_header_len);
			icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
			tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
		}
	}
}



Contributors
PersonTokensPropCommitsCommitProp
John Heffner9055.56%111.11%


Fan Du3622.22%222.22%


Eric Dumazet2716.67%222.22%


Linus Torvalds (pre-git)42.47%222.22%


David S. Miller31.85%111.11%


Arnaldo Carvalho de Melo21.23%111.11%


Total162100.00%9100.00%



/**
 *  retransmits_timed_out() - returns true if this connection has timed out
 *  @sk:       The current socket
 *  @boundary: max number of retransmissions
 *  @timeout:  A custom timeout value.
 *             If set to 0 the default timeout is calculated and used.
 *             Using TCP_RTO_MIN and the number of unsuccessful retransmits.
 *  @syn_set:  true if the SYN Bit was set.
 *
 * The default "timeout" value this function can calculate and use
 * is equivalent to the timeout of a TCP Connection
 * after "boundary" unsuccessful, exponentially backed-off
 * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if
 * syn_set flag is set.
 *
 */



static bool retransmits_timed_out(struct sock *sk,
				  unsigned int boundary,
				  unsigned int timeout,
				  bool syn_set)
{
	unsigned int linear_backoff_thresh, start_ts;
	unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN;

	if (!inet_csk(sk)->icsk_retransmits)
		return false;

	start_ts = tcp_sk(sk)->retrans_stamp;
	if (unlikely(!start_ts))
		start_ts = tcp_skb_timestamp(tcp_write_queue_head(sk));

	if (likely(timeout == 0)) {
		linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base);

		if (boundary <= linear_backoff_thresh)
			timeout = ((2 << boundary) - 1) * rto_base;
		else
			timeout = ((2 << linear_backoff_thresh) - 1) * rto_base +
				(boundary - linear_backoff_thresh) * TCP_RTO_MAX;
	}
	return (tcp_time_stamp - start_ts) >= timeout;
}


Contributors
PersonTokensPropCommitsCommitProp
Damian Lukowski12382.00%240.00%


Jerry Chu1610.67%120.00%


Eric Dumazet106.67%120.00%


David S. Miller10.67%120.00%


Total150100.00%5100.00%



/* A write timeout has occurred. Process the after effects. */



static int tcp_write_timeout(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct net *net = sock_net(sk);
	int retry_until;
	bool do_reset, syn_set = false;

	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
		if (icsk->icsk_retransmits) {
			dst_negative_advice(sk);
			if (tp->syn_fastopen || tp->syn_data)
				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
			if (tp->syn_data && icsk->icsk_retransmits == 1)
				NET_INC_STATS(sock_net(sk),
					      LINUX_MIB_TCPFASTOPENACTIVEFAIL);
		} else if (!tp->syn_data && !tp->syn_fastopen) {
			sk_rethink_txhash(sk);
		}
		retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
		syn_set = true;
	} else {
		if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0, 0)) {
			/* Some middle-boxes may black-hole Fast Open _after_
                         * the handshake. Therefore we conservatively disable
                         * Fast Open on this path on recurring timeouts with
                         * few or zero bytes acked after Fast Open.
                         */
			if (tp->syn_data_acked &&
			    tp->bytes_acked <= tp->rx_opt.mss_clamp) {
				tcp_fastopen_cache_set(sk, 0, NULL, true, 0);
				if (icsk->icsk_retransmits == net->ipv4.sysctl_tcp_retries1)
					NET_INC_STATS(sock_net(sk),
						      LINUX_MIB_TCPFASTOPENACTIVEFAIL);
			}
			/* Black hole detection */
			tcp_mtu_probing(icsk, sk);

			dst_negative_advice(sk);
		} else {
			sk_rethink_txhash(sk);
		}

		retry_until = net->ipv4.sysctl_tcp_retries2;
		if (sock_flag(sk, SOCK_DEAD)) {
			const bool alive = icsk->icsk_rto < TCP_RTO_MAX;

			retry_until = tcp_orphan_retries(sk, alive);
			do_reset = alive ||
				!retransmits_timed_out(sk, retry_until, 0, 0);

			if (tcp_out_of_resources(sk, do_reset))
				return 1;
		}
	}

	if (retransmits_timed_out(sk, retry_until,
				  syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) {
		/* Has it gone just too far? */
		tcp_write_err(sk);
		return 1;
	}
	return 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Yuchung Cheng10328.61%414.81%


Eric Dumazet7721.39%27.41%


Linus Torvalds (pre-git)6116.94%622.22%


Damian Lukowski339.17%27.41%


Lawrence Brakmo287.78%13.70%


Nikolay Borisov267.22%311.11%


Jerry Chu113.06%13.70%


David S. Miller61.67%13.70%


Arnaldo Carvalho de Melo61.67%27.41%


James Morris20.56%13.70%


Krishna Kumar20.56%13.70%


Daniel Lee20.56%13.70%


Rusty Russell20.56%13.70%


Richard Sailer10.28%13.70%


Total360100.00%27100.00%



/* Called with BH disabled */



void tcp_delack_timer_handler(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	sk_mem_reclaim_partial(sk);

	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
	    !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
		goto out;

	if (time_after(icsk->icsk_ack.timeout, jiffies)) {
		sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
		goto out;
	}
	icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER;

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

		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSCHEDULERFAILED);

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

		tp->ucopy.memory = 0;
	}

	if (inet_csk_ack_scheduled(sk)) {
		if (!icsk->icsk_ack.pingpong) {
			/* Delayed ACK missed: inflate ATO. */
			icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto);
		} else {
			/* Delayed ACK missed: leave pingpong mode and
                         * deflate ATO.
                         */
			icsk->icsk_ack.pingpong = 0;
			icsk->icsk_ack.ato      = TCP_ATO_MIN;
		}
		tcp_send_ack(sk);
		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKS);
	}

out:
	if (tcp_under_memory_pressure(sk))
		sk_mem_reclaim(sk);
}



Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)17666.67%728.00%


Arnaldo Carvalho de Melo4215.91%416.00%


Eric Dumazet197.20%416.00%


Pavel Emelyanov103.79%14.00%


David S. Miller83.03%416.00%


Glauber de Oliveira Costa31.14%14.00%


Hideaki Yoshifuji / 吉藤英明20.76%14.00%


Ravikiran G. Thirumalai20.76%14.00%


Linus Torvalds10.38%14.00%


Hideo Aoki10.38%14.00%


Total264100.00%25100.00%



/**
 *  tcp_delack_timer() - The TCP delayed ACK timeout handler
 *  @data:  Pointer to the current socket. (gets casted to struct sock *)
 *
 *  This function gets (indirectly) called when the kernel timer for a TCP packet
 *  of this socket expires. Calls tcp_delack_timer_handler() to do the actual work.
 *
 *  Returns: Nothing (void)
 */



static void tcp_delack_timer(unsigned long data)
{
	struct sock *sk = (struct sock *)data;

	bh_lock_sock(sk);
	if (!sock_owned_by_user(sk)) {
		tcp_delack_timer_handler(sk);
	} else {
		inet_csk(sk)->icsk_ack.blocked = 1;
		__NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOCKED);
		/* deleguate our work to tcp_release_cb() */
		if (!test_and_set_bit(TCP_DELACK_TIMER_DEFERRED, &sk->sk_tsq_flags))
			sock_hold(sk);
	}
	bh_unlock_sock(sk);
	sock_put(sk);
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Dumazet8488.42%457.14%


Linus Torvalds (pre-git)1111.58%342.86%


Total95100.00%7100.00%






static void tcp_probe_timer(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	int max_probes;
	u32 start_ts;

	if (tp->packets_out || !tcp_send_head(sk)) {
		icsk->icsk_probes_out = 0;
		return;
	}

	/* RFC 1122 4.2.2.17 requires the sender to stay open indefinitely as
         * long as the receiver continues to respond probes. We support this by
         * default and reset icsk_probes_out with incoming ACKs. But if the
         * socket is orphaned or the user specifies TCP_USER_TIMEOUT, we
         * kill the socket when the retry count and the time exceeds the
         * corresponding system limit. We also implement similar policy when
         * we use RTO to probe window in tcp_retransmit_timer().
         */
	start_ts = tcp_skb_timestamp(tcp_send_head(sk));
	if (!start_ts)
		skb_mstamp_get(&tcp_send_head(sk)->skb_mstamp);
	else if (icsk->icsk_user_timeout &&
		 (s32)(tcp_time_stamp - start_ts) > icsk->icsk_user_timeout)
		goto abort;

	max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
	if (sock_flag(sk, SOCK_DEAD)) {
		const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;

		max_probes = tcp_orphan_retries(sk, alive);
		if (!alive && icsk->icsk_backoff >= max_probes)
			goto abort;
		if (tcp_out_of_resources(sk, true))
			return;
	}

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


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)8944.06%840.00%


Yuchung Cheng7034.65%15.00%


Arnaldo Carvalho de Melo2210.89%525.00%


Nikolay Borisov73.47%15.00%


David S. Miller62.97%210.00%


Eric Dumazet52.48%15.00%


James Morris20.99%15.00%


Richard Sailer10.50%15.00%


Total202100.00%20100.00%



/*
 *      Timer for Fast Open socket to retransmit SYNACK. Note that the
 *      sk here is the child socket, not the parent (listener) socket.
 */



static void tcp_fastopen_synack_timer(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	int max_retries = icsk->icsk_syn_retries ? :
	    sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
	struct request_sock *req;

	req = tcp_sk(sk)->fastopen_rsk;
	req->rsk_ops->syn_ack_timeout(req);

	if (req->num_timeout >= max_retries) {
		tcp_write_err(sk);
		return;
	}
	/* XXX (TFO) - Unlike regular SYN-ACK retransmit, we ignore error
         * returned from rtx_syn_ack() to make it more persistent like
         * regular retransmit because if the child socket has been accepted
         * it's not good to give up too easily.
         */
	inet_rtx_syn_ack(sk, req);
	req->num_timeout++;
	icsk->icsk_retransmits++;
	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
			  TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX);
}



Contributors
PersonTokensPropCommitsCommitProp
Jerry Chu9785.84%125.00%


Nikolay Borisov76.19%125.00%


Yuchung Cheng54.42%125.00%


Eric Dumazet43.54%125.00%


Total113100.00%4100.00%



/**
 *  tcp_retransmit_timer() - The TCP retransmit timeout handler
 *  @sk:  Pointer to the current socket.
 *
 *  This function gets called when the kernel timer for a TCP packet
 *  of this socket expires.
 *
 *  It handles retransmission, timer adjustment and other necesarry measures.
 *
 *  Returns: Nothing (void)
 */



void tcp_retransmit_timer(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct net *net = sock_net(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);

	if (tp->fastopen_rsk) {
		WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV &&
			     sk->sk_state != TCP_FIN_WAIT1);
		tcp_fastopen_synack_timer(sk);
		/* Before we receive ACK to our SYN-ACK don't retransmit
                 * anything else (e.g., data or FIN segments).
                 */
		return;
	}
	if (!tp->packets_out)
		goto out;

	WARN_ON(tcp_write_queue_empty(sk));

	tp->tlp_high_seq = 0;

	if (!tp->snd_wnd && !sock_flag(sk, SOCK_DEAD) &&
	    !((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV))) {
		/* Receiver dastardly shrinks window. Our retransmits
                 * become zero probes, but we should not timeout this
                 * connection. If the socket is an orphan, time it out,
                 * we cannot allow such beasts to hang infinitely.
                 */
		struct inet_sock *inet = inet_sk(sk);
		if (sk->sk_family == AF_INET) {
			net_dbg_ratelimited("Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
					    &inet->inet_daddr,
					    ntohs(inet->inet_dport),
					    inet->inet_num,
					    tp->snd_una, tp->snd_nxt);
		}
#if IS_ENABLED(CONFIG_IPV6)
		else if (sk->sk_family == AF_INET6) {
			net_dbg_ratelimited("Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n",
					    &sk->sk_v6_daddr,
					    ntohs(inet->inet_dport),
					    inet->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);
		tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1);
		__sk_dst_reset(sk);
		goto out_reset_timer;
	}

	if (tcp_write_timeout(sk))
		goto out;

	if (icsk->icsk_retransmits == 0) {
		int mib_idx;

		if (icsk->icsk_ca_state == TCP_CA_Recovery) {
			if (tcp_is_sack(tp))
				mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL;
			else
				mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL;
		} else if (icsk->icsk_ca_state == TCP_CA_Loss) {
			mib_idx = LINUX_MIB_TCPLOSSFAILURES;
		} else if ((icsk->icsk_ca_state == TCP_CA_Disorder) ||
			   tp->sacked_out) {
			if (tcp_is_sack(tp))
				mib_idx = LINUX_MIB_TCPSACKFAILURES;
			else
				mib_idx = LINUX_MIB_TCPRENOFAILURES;
		} else {
			mib_idx = LINUX_MIB_TCPTIMEOUTS;
		}
		__NET_INC_STATS(sock_net(sk), mib_idx);
	}

	tcp_enter_loss(sk);

	if (tcp_retransmit_skb(sk, tcp_write_queue_head(sk), 1) > 0) {
		/* Retransmission failed because of local congestion,
                 * do not backoff.
                 */
		if (!icsk->icsk_retransmits)
			icsk->icsk_retransmits = 1;
		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
					  min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL),
					  TCP_RTO_MAX);
		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!
         */
	icsk->icsk_backoff++;
	icsk->icsk_retransmits++;

out_reset_timer:
	/* If stream is thin, use linear timeouts. Since 'icsk_backoff' is
         * used to reset timer, set to 0. Recalculate 'icsk_rto' as this
         * might be increased if the stream oscillates between thin and thick,
         * thus the old value might already be too high compared to the value
         * set by 'tcp_set_rto' in tcp_input.c which resets the rto without
         * backoff. Limit to TCP_THIN_LINEAR_RETRIES before initiating
         * exponential backoff behaviour to avoid continue hammering
         * linear-timeout retransmissions into a black hole
         */
	if (sk->sk_state == TCP_ESTABLISHED &&
	    (tp->thin_lto || sysctl_tcp_thin_linear_timeouts) &&
	    tcp_stream_is_thin(tp) &&
	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
		icsk->icsk_backoff = 0;
		icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
	} else {
		/* Use normal (exponential) backoff */
		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
	}
	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
	if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0, 0))
		__sk_dst_reset(sk);

out:;
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)16328.85%818.60%


Linus Torvalds8114.34%24.65%


Andreas Petlund549.56%12.33%


Arnaldo Carvalho de Melo498.67%716.28%


Joe Perches447.79%24.65%


Hideaki Yoshifuji / 吉藤英明346.02%12.33%


Ilpo Järvinen315.49%49.30%


Jerry Chu305.31%36.98%


Pavel Emelyanov223.89%24.65%


David S. Miller193.36%511.63%


Nikolay Borisov142.48%12.33%


Damian Lukowski71.24%12.33%


Eric Dumazet61.06%36.98%


Nandita Dukkipati61.06%12.33%


Yuchung Cheng30.53%12.33%


James Morris20.35%12.33%


Total565100.00%43100.00%



/* Called with bottom-half processing disabled.
   Called by tcp_write_timer() */



void tcp_write_timer_handler(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	int event;

	if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) ||
	    !icsk->icsk_pending)
		goto out;

	if (time_after(icsk->icsk_timeout, jiffies)) {
		sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
		goto out;
	}

	event = icsk->icsk_pending;

	switch (event) {
	case ICSK_TIME_REO_TIMEOUT:
		tcp_rack_reo_timeout(sk);
		break;
	case ICSK_TIME_LOSS_PROBE:
		tcp_send_loss_probe(sk);
		break;
	case ICSK_TIME_RETRANS:
		icsk->icsk_pending = 0;
		tcp_retransmit_timer(sk);
		break;
	case ICSK_TIME_PROBE0:
		icsk->icsk_pending = 0;
		tcp_probe_timer(sk);
		break;
	}

out:
	sk_mem_reclaim(sk);
}


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)7652.05%19.09%


Nandita Dukkipati2114.38%19.09%


Arnaldo Carvalho de Melo1913.01%327.27%


Eric Dumazet1610.96%218.18%


Yuchung Cheng96.16%19.09%


David S. Miller42.74%218.18%


Hideo Aoki10.68%19.09%


Total146100.00%11100.00%






static void tcp_write_timer(unsigned long data)
{
	struct sock *sk = (struct sock *)data;

	bh_lock_sock(sk);
	if (!sock_owned_by_user(sk)) {
		tcp_write_timer_handler(sk);
	} else {
		/* delegate our work to tcp_release_cb() */
		if (!test_and_set_bit(TCP_WRITE_TIMER_DEFERRED, &sk->sk_tsq_flags))
			sock_hold(sk);
	}
	bh_unlock_sock(sk);
	sock_put(sk);
}


Contributors
PersonTokensPropCommitsCommitProp
Eric Dumazet6283.78%350.00%


Linus Torvalds (pre-git)1114.86%233.33%


Richard Sailer11.35%116.67%


Total74100.00%6100.00%






void tcp_syn_ack_timeout(const struct request_sock *req)
{
	struct net *net = read_pnet(&inet_rsk(req)->ireq_net);

	__NET_INC_STATS(net, LINUX_MIB_TCPTIMEOUTS);
}

Contributors
PersonTokensPropCommitsCommitProp
Octavian Purdila1750.00%133.33%


Eric Dumazet1750.00%266.67%


Total34100.00%3100.00%




EXPORT_SYMBOL(tcp_syn_ack_timeout);




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))
		inet_csk_reset_keepalive_timer(sk, keepalive_time_when(tcp_sk(sk)));
	else if (!val)
		inet_csk_delete_keepalive_timer(sk);
}

Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)5583.33%337.50%


Arnaldo Carvalho de Melo69.09%337.50%


David S. Miller34.55%112.50%


James Morris23.03%112.50%


Total66100.00%8100.00%




EXPORT_SYMBOL_GPL(tcp_set_keepalive);





static void tcp_keepalive_timer (unsigned long data)
{
	struct sock *sk = (struct sock *) data;
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *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. */
		inet_csk_reset_keepalive_timer (sk, HZ/20);
		goto out;
	}

	if (sk->sk_state == TCP_LISTEN) {
		pr_err("Hmm... keepalive on a LISTEN ???\n");
		goto out;
	}

	if (sk->sk_state == TCP_FIN_WAIT2 && sock_flag(sk, SOCK_DEAD)) {
		if (tp->linger2 >= 0) {
			const int tmo = tcp_fin_time(sk) - 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 (tp->packets_out || tcp_send_head(sk))
		goto resched;

	elapsed = keepalive_time_elapsed(tp);

	if (elapsed >= keepalive_time_when(tp)) {
		/* If the TCP_USER_TIMEOUT option is enabled, use that
                 * to determine when to timeout instead.
                 */
		if ((icsk->icsk_user_timeout != 0 &&
		    elapsed >= icsk->icsk_user_timeout &&
		    icsk->icsk_probes_out > 0) ||
		    (icsk->icsk_user_timeout == 0 &&
		    icsk->icsk_probes_out >= keepalive_probes(tp))) {
			tcp_send_active_reset(sk, GFP_ATOMIC);
			tcp_write_err(sk);
			goto out;
		}
		if (tcp_write_wakeup(sk, LINUX_MIB_TCPKEEPALIVE) <= 0) {
			icsk->icsk_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;
	}

	sk_mem_reclaim(sk);

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

death:
	tcp_done(sk);

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


Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)27577.03%420.00%


Jerry Chu298.12%15.00%


Arnaldo Carvalho de Melo298.12%630.00%


Eric Dumazet61.68%315.00%


David S. Miller61.68%210.00%


James Morris41.12%15.00%


Flavio Leitner41.12%15.00%


Benjamin LaHaise30.84%15.00%


Hideo Aoki10.28%15.00%


Total357100.00%20100.00%






void tcp_init_xmit_timers(struct sock *sk)
{
	inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer,
				  &tcp_keepalive_timer);
}

Contributors
PersonTokensPropCommitsCommitProp
Eric Dumazet24100.00%1100.00%


Total24100.00%1100.00%




Overall Contributors
PersonTokensPropCommitsCommitProp
Linus Torvalds (pre-git)112138.84%1816.07%


Eric Dumazet36112.51%1816.07%


Yuchung Cheng1926.65%87.14%


Jerry Chu1846.38%32.68%


Arnaldo Carvalho de Melo1846.38%108.93%


Damian Lukowski1635.65%32.68%


John Heffner903.12%10.89%


Linus Torvalds822.84%21.79%


David S. Miller662.29%108.93%


Nikolay Borisov612.11%54.46%


Andreas Petlund571.98%10.89%


Pavel Emelyanov441.52%32.68%


Joe Perches441.52%21.79%


Hideaki Yoshifuji / 吉藤英明391.35%32.68%


Fan Du361.25%21.79%


Ilpo Järvinen311.07%43.57%


Lawrence Brakmo280.97%10.89%


Nandita Dukkipati270.94%21.79%


Octavian Purdila220.76%10.89%


James Morris120.42%10.89%


Richard Sailer110.38%21.79%


Ursula Braun50.17%10.89%


Flavio Leitner40.14%10.89%


Tejun Heo30.10%10.89%


Glauber de Oliveira Costa30.10%10.89%


Hideo Aoki30.10%10.89%


Benjamin LaHaise30.10%10.89%


Krishna Kumar20.07%10.89%


Rusty Russell20.07%10.89%


Daniel Lee20.07%10.89%


Ravikiran G. Thirumalai20.07%10.89%


Adrian Bunk10.03%10.89%


Arun Sharma10.03%10.89%


Brian Haley0.00%00.00%


Total2886100.00%112100.00%


Directory: net/ipv4



Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with cregit.