tcp_input.c

linux 内核源代码

	struct tcp_sock *tp = tcp_sk(sk);
	unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);

	hint = min(hint, tp->rcv_wnd/2);
	hint = min(hint, TCP_MIN_RCVMSS);
	hint = max(hint, TCP_MIN_MSS);

	inet_csk(sk)->icsk_ack.rcv_mss = hint;
}

/* Receiver "autotuning" code.
 *
 * The algorithm for RTT estimation w/o timestamps is based on
 * Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL.
 * <http://www.lanl.gov/radiant/website/pubs/drs/lacsi2001.ps>
 *
 * More detail on this code can be found at
 * <http://www.psc.edu/~jheffner/senior_thesis.ps>,
 * though this reference is out of date.  A new paper
 * is pending.
 */
static void tcp_rcv_rtt_update(struct tcp_sock *tp, u32 sample, int win_dep)
{
	u32 new_sample = tp->rcv_rtt_est.rtt;
	long m = sample;

	if (m == 0)
		m = 1;

	if (new_sample != 0) {
		/* If we sample in larger samples in the non-timestamp
		 * case, we could grossly overestimate the RTT especially
		 * with chatty applications or bulk transfer apps which
		 * are stalled on filesystem I/O.
		 *
		 * Also, since we are only going for a minimum in the
		 * non-timestamp case, we do not smooth things out
		 * else with timestamps disabled convergence takes too
		 * long.
		 */
		if (!win_dep) {
			m -= (new_sample >> 3);
			new_sample += m;
		} else if (m < new_sample)
			new_sample = m << 3;
	} else {
		/* No previous measure. */
		new_sample = m << 3;
	}

	if (tp->rcv_rtt_est.rtt != new_sample)
		tp->rcv_rtt_est.rtt = new_sample;
}

static inline void tcp_rcv_rtt_measure(struct tcp_sock *tp)
{
	if (tp->rcv_rtt_est.time == 0)
		goto new_measure;
	if (before(tp->rcv_nxt, tp->rcv_rtt_est.seq))
		return;
	tcp_rcv_rtt_update(tp,
			   jiffies - tp->rcv_rtt_est.time,
			   1);

new_measure:
	tp->rcv_rtt_est.seq = tp->rcv_nxt + tp->rcv_wnd;
	tp->rcv_rtt_est.time = tcp_time_stamp;
}

static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, const struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	if (tp->rx_opt.rcv_tsecr &&
	    (TCP_SKB_CB(skb)->end_seq -
	     TCP_SKB_CB(skb)->seq >= inet_csk(sk)->icsk_ack.rcv_mss))
		tcp_rcv_rtt_update(tp, tcp_time_stamp - tp->rx_opt.rcv_tsecr, 0);
}

/*
 * This function should be called every time data is copied to user space.
 * It calculates the appropriate TCP receive buffer space.
 */
void tcp_rcv_space_adjust(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	int time;
	int space;

	if (tp->rcvq_space.time == 0)
		goto new_measure;

	time = tcp_time_stamp - tp->rcvq_space.time;
	if (time < (tp->rcv_rtt_est.rtt >> 3) ||
	    tp->rcv_rtt_est.rtt == 0)
		return;

	space = 2 * (tp->copied_seq - tp->rcvq_space.seq);

	space = max(tp->rcvq_space.space, space);

	if (tp->rcvq_space.space != space) {
		int rcvmem;

		tp->rcvq_space.space = space;

		if (sysctl_tcp_moderate_rcvbuf &&
		    !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
			int new_clamp = space;

			/* Receive space grows, normalize in order to
			 * take into account packet headers and sk_buff
			 * structure overhead.
			 */
			space /= tp->advmss;
			if (!space)
				space = 1;
			rcvmem = (tp->advmss + MAX_TCP_HEADER +
				  16 + sizeof(struct sk_buff));
			while (tcp_win_from_space(rcvmem) < tp->advmss)
				rcvmem += 128;
			space *= rcvmem;
			space = min(space, sysctl_tcp_rmem[2]);
			if (space > sk->sk_rcvbuf) {
				sk->sk_rcvbuf = space;

				/* Make the window clamp follow along.  */
				tp->window_clamp = new_clamp;
			}
		}
	}

new_measure:
	tp->rcvq_space.seq = tp->copied_seq;
	tp->rcvq_space.time = tcp_time_stamp;
}

/* There is something which you must keep in mind when you analyze the
 * behavior of the tp->ato delayed ack timeout interval.  When a
 * connection starts up, we want to ack as quickly as possible.  The
 * problem is that "good" TCP's do slow start at the beginning of data
 * transmission.  The means that until we send the first few ACK's the
 * sender will sit on his end and only queue most of his data, because
 * he can only send snd_cwnd unacked packets at any given time.  For
 * each ACK we send, he increments snd_cwnd and transmits more of his
 * queue.  -DaveM
 */
static void tcp_event_data_recv(struct sock *sk, struct sk_buff *skb)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct inet_connection_sock *icsk = inet_csk(sk);
	u32 now;

	inet_csk_schedule_ack(sk);

	tcp_measure_rcv_mss(sk, skb);

	tcp_rcv_rtt_measure(tp);

	now = tcp_time_stamp;

	if (!icsk->icsk_ack.ato) {
		/* The _first_ data packet received, initialize
		 * delayed ACK engine.
		 */
		tcp_incr_quickack(sk);
		icsk->icsk_ack.ato = TCP_ATO_MIN;
	} else {
		int m = now - icsk->icsk_ack.lrcvtime;

		if (m <= TCP_ATO_MIN/2) {
			/* The fastest case is the first. */
			icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + TCP_ATO_MIN / 2;
		} else if (m < icsk->icsk_ack.ato) {
			icsk->icsk_ack.ato = (icsk->icsk_ack.ato >> 1) + m;
			if (icsk->icsk_ack.ato > icsk->icsk_rto)
				icsk->icsk_ack.ato = icsk->icsk_rto;
		} else if (m > icsk->icsk_rto) {
			/* Too long gap. Apparently sender failed to
			 * restart window, so that we send ACKs quickly.
			 */
			tcp_incr_quickack(sk);
			sk_stream_mem_reclaim(sk);
		}
	}
	icsk->icsk_ack.lrcvtime = now;

	TCP_ECN_check_ce(tp, skb);

	if (skb->len >= 128)
		tcp_grow_window(sk, skb);
}

static u32 tcp_rto_min(struct sock *sk)
{
	struct dst_entry *dst = __sk_dst_get(sk);
	u32 rto_min = TCP_RTO_MIN;

	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
		rto_min = dst->metrics[RTAX_RTO_MIN-1];
	return rto_min;
}

/* Called to compute a smoothed rtt estimate. The data fed to this
 * routine either comes from timestamps, or from segments that were
 * known _not_ to have been retransmitted [see Karn/Partridge
 * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88
 * piece by Van Jacobson.
 * NOTE: the next three routines used to be one big routine.
 * To save cycles in the RFC 1323 implementation it was better to break
 * it up into three procedures. -- erics
 */
static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
{
	struct tcp_sock *tp = tcp_sk(sk);
	long m = mrtt; /* RTT */

	/*	The following amusing code comes from Jacobson's
	 *	article in SIGCOMM '88.  Note that rtt and mdev
	 *	are scaled versions of rtt and mean deviation.
	 *	This is designed to be as fast as possible
	 *	m stands for "measurement".
	 *
	 *	On a 1990 paper the rto value is changed to:
	 *	RTO = rtt + 4 * mdev
	 *
	 * Funny. This algorithm seems to be very broken.
	 * These formulae increase RTO, when it should be decreased, increase
	 * too slowly, when it should be increased quickly, decrease too quickly
	 * etc. I guess in BSD RTO takes ONE value, so that it is absolutely
	 * does not matter how to _calculate_ it. Seems, it was trap
	 * that VJ failed to avoid. 8)
	 */
	if (m == 0)
		m = 1;
	if (tp->srtt != 0) {
		m -= (tp->srtt >> 3);	/* m is now error in rtt est */
		tp->srtt += m;		/* rtt = 7/8 rtt + 1/8 new */
		if (m < 0) {
			m = -m;		/* m is now abs(error) */
			m -= (tp->mdev >> 2);   /* similar update on mdev */
			/* This is similar to one of Eifel findings.
			 * Eifel blocks mdev updates when rtt decreases.
			 * This solution is a bit different: we use finer gain
			 * for mdev in this case (alpha*beta).
			 * Like Eifel it also prevents growth of rto,
			 * but also it limits too fast rto decreases,
			 * happening in pure Eifel.
			 */
			if (m > 0)
				m >>= 3;
		} else {
			m -= (tp->mdev >> 2);   /* similar update on mdev */
		}
		tp->mdev += m;	    	/* mdev = 3/4 mdev + 1/4 new */
		if (tp->mdev > tp->mdev_max) {
			tp->mdev_max = tp->mdev;
			if (tp->mdev_max > tp->rttvar)
				tp->rttvar = tp->mdev_max;
		}
		if (after(tp->snd_una, tp->rtt_seq)) {
			if (tp->mdev_max < tp->rttvar)
				tp->rttvar -= (tp->rttvar-tp->mdev_max)>>2;
			tp->rtt_seq = tp->snd_nxt;
			tp->mdev_max = tcp_rto_min(sk);
		}
	} else {
		/* no previous measure. */
		tp->srtt = m<<3;	/* take the measured time to be rtt */
		tp->mdev = m<<1;	/* make sure rto = 3*rtt */
		tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk));
		tp->rtt_seq = tp->snd_nxt;
	}
}

/* Calculate rto without backoff.  This is the second half of Van Jacobson's
 * routine referred to above.
 */
static inline void tcp_set_rto(struct sock *sk)
{
	const struct tcp_sock *tp = tcp_sk(sk);
	/* Old crap is replaced with new one. 8)
	 *
	 * More seriously:
	 * 1. If rtt variance happened to be less 50msec, it is hallucination.
	 *    It cannot be less due to utterly erratic ACK generation made
	 *    at least by solaris and freebsd. "Erratic ACKs" has _nothing_
	 *    to do with delayed acks, because at cwnd>2 true delack timeout
	 *    is invisible. Actually, Linux-2.4 also generates erratic
	 *    ACKs in some circumstances.
	 */
	inet_csk(sk)->icsk_rto = (tp->srtt >> 3) + tp->rttvar;

	/* 2. Fixups made earlier cannot be right.
	 *    If we do not estimate RTO correctly without them,
	 *    all the algo is pure shit and should be replaced
	 *    with correct one. It is exactly, which we pretend to do.
	 */
}

/* NOTE: clamping at TCP_RTO_MIN is not required, current algo
 * guarantees that rto is higher.
 */
static inline void tcp_bound_rto(struct sock *sk)
{
	if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX)
		inet_csk(sk)->icsk_rto = TCP_RTO_MAX;
}

/* Save metrics learned by this TCP session.
   This function is called only, when TCP finishes successfully
   i.e. when it enters TIME-WAIT or goes from LAST-ACK to CLOSE.
 */
void tcp_update_metrics(struct sock *sk)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct dst_entry *dst = __sk_dst_get(sk);

	if (sysctl_tcp_nometrics_save)
		return;

	dst_confirm(dst);

	if (dst && (dst->flags&DST_HOST)) {
		const struct inet_connection_sock *icsk = inet_csk(sk);
		int m;

		if (icsk->icsk_backoff || !tp->srtt) {
			/* This session failed to estimate rtt. Why?
			 * Probably, no packets returned in time.
			 * Reset our results.
			 */
			if (!(dst_metric_locked(dst, RTAX_RTT)))
				dst->metrics[RTAX_RTT-1] = 0;
			return;
		}

		m = dst_metric(dst, RTAX_RTT) - tp->srtt;

		/* If newly calculated rtt larger than stored one,
		 * store new one. Otherwise, use EWMA. Remember,
		 * rtt overestimation is always better than underestimation.
		 */
		if (!(dst_metric_locked(dst, RTAX_RTT))) {
			if (m <= 0)
				dst->metrics[RTAX_RTT-1] = tp->srtt;
			else
				dst->metrics[RTAX_RTT-1] -= (m>>3);
		}

		if (!(dst_metric_locked(dst, RTAX_RTTVAR))) {
			if (m < 0)
				m = -m;

			/* Scale deviation to rttvar fixed point */
			m >>= 1;
			if (m < tp->mdev)
				m = tp->mdev;

			if (m >= dst_metric(dst, RTAX_RTTVAR))
				dst->metrics[RTAX_RTTVAR-1] = m;
			else
				dst->metrics[RTAX_RTTVAR-1] -=
					(dst->metrics[RTAX_RTTVAR-1] - m)>>2;
		}

		if (tp->snd_ssthresh >= 0xFFFF) {
			/* Slow start still did not finish. */
			if (dst_metric(dst, RTAX_SSTHRESH) &&
			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
			    (tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH))
				dst->metrics[RTAX_SSTHRESH-1] = tp->snd_cwnd >> 1;
			if (!dst_metric_locked(dst, RTAX_CWND) &&
			    tp->snd_cwnd > dst_metric(dst, RTAX_CWND))
				dst->metrics[RTAX_CWND-1] = tp->snd_cwnd;
		} else if (tp->snd_cwnd > tp->snd_ssthresh &&
			   icsk->icsk_ca_state == TCP_CA_Open) {
			/* Cong. avoidance phase, cwnd is reliable. */
			if (!dst_metric_locked(dst, RTAX_SSTHRESH))
				dst->metrics[RTAX_SSTHRESH-1] =
					max(tp->snd_cwnd >> 1, tp->snd_ssthresh);
			if (!dst_metric_locked(dst, RTAX_CWND))
				dst->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + tp->snd_cwnd) >> 1;
		} else {
			/* Else slow start did not finish, cwnd is non-sense,
			   ssthresh may be also invalid.
			 */
			if (!dst_metric_locked(dst, RTAX_CWND))
				dst->metrics[RTAX_CWND-1] = (dst->metrics[RTAX_CWND-1] + tp->snd_ssthresh) >> 1;
			if (dst->metrics[RTAX_SSTHRESH-1] &&
			    !dst_metric_locked(dst, RTAX_SSTHRESH) &&
			    tp->snd_ssthresh > dst->metrics[RTAX_SSTHRESH-1])
				dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh;
		}

		if (!dst_metric_locked(dst, RTAX_REORDERING)) {
			if (dst->metrics[RTAX_REORDERING-1] < tp->reordering &&
			    tp->reordering != sysctl_tcp_reordering)
				dst->metrics[RTAX_REORDERING-1] = tp->reordering;
		}
	}
}

/* Numbers are taken from RFC3390.
 *
 * John Heffner states:
 *
 *	The RFC specifies a window of no more than 4380 bytes
 *	unless 2*MSS > 4380.  Reading the pseudocode in the RFC
 *	is a bit misleading because they use a clamp at 4380 bytes
 *	rather than use a multiplier in the relevant range.
 */
__u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst)