transport.c

在linux环境下的流控制传输协议（sctp）的源代码

	}
	if (dst) {
		transport->pathmtu = dst_mtu(dst);

		/* Initialize sk->sk_rcv_saddr, if the transport is the
		 * association's active path for getsockname().
		 */
		if (asoc && (transport == asoc->peer.active_path))
			opt->pf->af->to_sk_saddr(&transport->saddr,
						 asoc->base.sk);
	} else
		transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT;
}

/* Hold a reference to a transport.  */
void sctp_transport_hold(struct sctp_transport *transport)
{
	atomic_inc(&transport->refcnt);
}

/* Release a reference to a transport and clean up
 * if there are no more references.
 */
void sctp_transport_put(struct sctp_transport *transport)
{
	if (atomic_dec_and_test(&transport->refcnt))
		sctp_transport_destroy(transport);
}

/* Update transport's RTO based on the newly calculated RTT. */
void sctp_transport_update_rto(struct sctp_transport *tp, __u32 rtt)
{
	/* Check for valid transport.  */
	SCTP_ASSERT(tp, "NULL transport", return);

	/* We should not be doing any RTO updates unless rto_pending is set.  */
	SCTP_ASSERT(tp->rto_pending, "rto_pending not set", return);

	if (tp->rttvar || tp->srtt) {
		/* 6.3.1 C3) When a new RTT measurement R' is made, set
		 * RTTVAR <- (1 - RTO.Beta) * RTTVAR + RTO.Beta * |SRTT - R'|
		 * SRTT <- (1 - RTO.Alpha) * SRTT + RTO.Alpha * R'
		 */

		/* Note:  The above algorithm has been rewritten to
		 * express rto_beta and rto_alpha as inverse powers
		 * of two.
		 * For example, assuming the default value of RTO.Alpha of
		 * 1/8, rto_alpha would be expressed as 3.
		 */
		tp->rttvar = tp->rttvar - (tp->rttvar >> sctp_rto_beta)
			+ ((abs(tp->srtt - rtt)) >> sctp_rto_beta);
		tp->srtt = tp->srtt - (tp->srtt >> sctp_rto_alpha)
			+ (rtt >> sctp_rto_alpha);
	} else {
		/* 6.3.1 C2) When the first RTT measurement R is made, set
		 * SRTT <- R, RTTVAR <- R/2.
		 */
		tp->srtt = rtt;
		tp->rttvar = rtt >> 1;
	}

	/* 6.3.1 G1) Whenever RTTVAR is computed, if RTTVAR = 0, then
	 * adjust RTTVAR <- G, where G is the CLOCK GRANULARITY.
	 */
	if (tp->rttvar == 0)
		tp->rttvar = SCTP_CLOCK_GRANULARITY;

	/* 6.3.1 C3) After the computation, update RTO <- SRTT + 4 * RTTVAR. */
	tp->rto = tp->srtt + (tp->rttvar << 2);

	/* 6.3.1 C6) Whenever RTO is computed, if it is less than RTO.Min
	 * seconds then it is rounded up to RTO.Min seconds.
	 */
	if (tp->rto < tp->asoc->rto_min)
		tp->rto = tp->asoc->rto_min;

	/* 6.3.1 C7) A maximum value may be placed on RTO provided it is
	 * at least RTO.max seconds.
	 */
	if (tp->rto > tp->asoc->rto_max)
		tp->rto = tp->asoc->rto_max;

	tp->rtt = rtt;
	tp->last_rto = tp->rto;

	/* Reset rto_pending so that a new RTT measurement is started when a
	 * new data chunk is sent.
	 */
	tp->rto_pending = 0;

	SCTP_DEBUG_PRINTK("%s: transport: %p, rtt: %d, srtt: %d "
			  "rttvar: %d, rto: %ld\n", __FUNCTION__,
			  tp, rtt, tp->srtt, tp->rttvar, tp->rto);
}

/* This routine updates the transport's cwnd and partial_bytes_acked
 * parameters based on the bytes acked in the received SACK.
 */
void sctp_transport_raise_cwnd(struct sctp_transport *transport,
			       __u32 sack_ctsn, __u32 bytes_acked)
{
	__u32 cwnd, ssthresh, flight_size, pba, pmtu;

	cwnd = transport->cwnd;
	flight_size = transport->flight_size;

	/* The appropriate cwnd increase algorithm is performed if, and only
	 * if the cumulative TSN has advanced and the congestion window is
	 * being fully utilized.
	 */
	if ((transport->asoc->ctsn_ack_point >= sack_ctsn) ||
	    (flight_size < cwnd))
		return;

	ssthresh = transport->ssthresh;
	pba = transport->partial_bytes_acked;
	pmtu = transport->asoc->pathmtu;

	if (cwnd <= ssthresh) {
		/* RFC 2960 7.2.1, sctpimpguide-05 2.14.2 When cwnd is less
		 * than or equal to ssthresh an SCTP endpoint MUST use the
		 * slow start algorithm to increase cwnd only if the current
		 * congestion window is being fully utilized and an incoming
		 * SACK advances the Cumulative TSN Ack Point. Only when these
		 * two conditions are met can the cwnd be increased otherwise
		 * the cwnd MUST not be increased. If these conditions are met
		 * then cwnd MUST be increased by at most the lesser of
		 * 1) the total size of the previously outstanding DATA
		 * chunk(s) acknowledged, and 2) the destination's path MTU.
		 */
		if (bytes_acked > pmtu)
			cwnd += pmtu;
		else
			cwnd += bytes_acked;
		SCTP_DEBUG_PRINTK("%s: SLOW START: transport: %p, "
				  "bytes_acked: %d, cwnd: %d, ssthresh: %d, "
				  "flight_size: %d, pba: %d\n",
				  __FUNCTION__,
				  transport, bytes_acked, cwnd,
				  ssthresh, flight_size, pba);
	} else {
		/* RFC 2960 7.2.2 Whenever cwnd is greater than ssthresh,
		 * upon each SACK arrival that advances the Cumulative TSN Ack
		 * Point, increase partial_bytes_acked by the total number of
		 * bytes of all new chunks acknowledged in that SACK including
		 * chunks acknowledged by the new Cumulative TSN Ack and by
		 * Gap Ack Blocks.
		 *
		 * When partial_bytes_acked is equal to or greater than cwnd
		 * and before the arrival of the SACK the sender had cwnd or
		 * more bytes of data outstanding (i.e., before arrival of the
		 * SACK, flightsize was greater than or equal to cwnd),
		 * increase cwnd by MTU, and reset partial_bytes_acked to
		 * (partial_bytes_acked - cwnd).
		 */
		pba += bytes_acked;
		if (pba >= cwnd) {
			cwnd += pmtu;
			pba = ((cwnd < pba) ? (pba - cwnd) : 0);
		}
		SCTP_DEBUG_PRINTK("%s: CONGESTION AVOIDANCE: "
				  "transport: %p, bytes_acked: %d, cwnd: %d, "
				  "ssthresh: %d, flight_size: %d, pba: %d\n",
				  __FUNCTION__,
				  transport, bytes_acked, cwnd,
				  ssthresh, flight_size, pba);
	}

	transport->cwnd = cwnd;
	transport->partial_bytes_acked = pba;
}

/* This routine is used to lower the transport's cwnd when congestion is
 * detected.
 */
void sctp_transport_lower_cwnd(struct sctp_transport *transport,
			       sctp_lower_cwnd_t reason)
{
	switch (reason) {
	case SCTP_LOWER_CWND_T3_RTX:
		/* RFC 2960 Section 7.2.3, sctpimpguide
		 * When the T3-rtx timer expires on an address, SCTP should
		 * perform slow start by:
		 *      ssthresh = max(cwnd/2, 4*MTU)
		 *      cwnd = 1*MTU
		 *      partial_bytes_acked = 0
		 */
		transport->ssthresh = max(transport->cwnd/2,
					  4*transport->asoc->pathmtu);
		transport->cwnd = transport->asoc->pathmtu;
		break;

	case SCTP_LOWER_CWND_FAST_RTX:
		/* RFC 2960 7.2.4 Adjust the ssthresh and cwnd of the
		 * destination address(es) to which the missing DATA chunks
		 * were last sent, according to the formula described in
		 * Section 7.2.3.
		 *
		 * RFC 2960 7.2.3, sctpimpguide Upon detection of packet
		 * losses from SACK (see Section 7.2.4), An endpoint
		 * should do the following:
		 *      ssthresh = max(cwnd/2, 4*MTU)
		 *      cwnd = ssthresh
		 *      partial_bytes_acked = 0
		 */
		transport->ssthresh = max(transport->cwnd/2,
					  4*transport->asoc->pathmtu);
		transport->cwnd = transport->ssthresh;
		break;

	case SCTP_LOWER_CWND_ECNE:
		/* RFC 2481 Section 6.1.2.
		 * If the sender receives an ECN-Echo ACK packet
		 * then the sender knows that congestion was encountered in the
		 * network on the path from the sender to the receiver. The
		 * indication of congestion should be treated just as a
		 * congestion loss in non-ECN Capable TCP. That is, the TCP
		 * source halves the congestion window "cwnd" and reduces the
		 * slow start threshold "ssthresh".
		 * A critical condition is that TCP does not react to
		 * congestion indications more than once every window of
		 * data (or more loosely more than once every round-trip time).
		 */
		if ((jiffies - transport->last_time_ecne_reduced) >
		    transport->rtt) {
			transport->ssthresh = max(transport->cwnd/2,
						  4*transport->asoc->pathmtu);
			transport->cwnd = transport->ssthresh;
			transport->last_time_ecne_reduced = jiffies;
		}
		break;

	case SCTP_LOWER_CWND_INACTIVE:
		/* RFC 2960 Section 7.2.1, sctpimpguide
		 * When the endpoint does not transmit data on a given
		 * transport address, the cwnd of the transport address
		 * should be adjusted to max(cwnd/2, 4*MTU) per RTO.
		 * NOTE: Although the draft recommends that this check needs
		 * to be done every RTO interval, we do it every hearbeat
		 * interval.
		 */
		if ((jiffies - transport->last_time_used) > transport->rto)
			transport->cwnd = max(transport->cwnd/2,
						 4*transport->asoc->pathmtu);
		break;
	}

	transport->partial_bytes_acked = 0;
	SCTP_DEBUG_PRINTK("%s: transport: %p reason: %d cwnd: "
			  "%d ssthresh: %d\n", __FUNCTION__,
			  transport, reason,
			  transport->cwnd, transport->ssthresh);
}

/* What is the next timeout value for this transport? */
unsigned long sctp_transport_timeout(struct sctp_transport *t)
{
	unsigned long timeout;
	timeout = t->rto + sctp_jitter(t->rto);
	if (t->state != SCTP_UNCONFIRMED)
		timeout += t->hbinterval;
	timeout += jiffies;
	return timeout;
}

/* Reset transport variables to their initial values */
void sctp_transport_reset(struct sctp_transport *t)
{
	struct sctp_association *asoc = t->asoc;

	/* RFC 2960 (bis), Section 5.2.4
	 * All the congestion control parameters (e.g., cwnd, ssthresh)
	 * related to this peer MUST be reset to their initial values
	 * (see Section 6.2.1)
	 */
	t->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380));
	t->ssthresh = asoc->peer.i.a_rwnd;
	t->last_rto = t->rto = asoc->rto_initial;
	t->rtt = 0;
	t->srtt = 0;
	t->rttvar = 0;

	/* Reset these additional varibles so that we have a clean
	 * slate.
	 */
	t->partial_bytes_acked = 0;
	t->flight_size = 0;
	t->error_count = 0;
	t->rto_pending = 0;

	/* Initialize the state information for SFR-CACC */
	t->cacc.changeover_active = 0;
	t->cacc.cycling_changeover = 0;
	t->cacc.next_tsn_at_change = 0;
	t->cacc.cacc_saw_newack = 0;
}