tcp_output.c

linux 内核源代码

	TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(skb)->seq;
	TCP_SKB_CB(nskb)->end_seq = TCP_SKB_CB(skb)->seq + probe_size;
	TCP_SKB_CB(nskb)->flags = TCPCB_FLAG_ACK;
	TCP_SKB_CB(nskb)->sacked = 0;
	nskb->csum = 0;
	nskb->ip_summed = skb->ip_summed;

	len = 0;
	while (len < probe_size) {
		next = tcp_write_queue_next(sk, skb);

		copy = min_t(int, skb->len, probe_size - len);
		if (nskb->ip_summed)
			skb_copy_bits(skb, 0, skb_put(nskb, copy), copy);
		else
			nskb->csum = skb_copy_and_csum_bits(skb, 0,
					 skb_put(nskb, copy), copy, nskb->csum);

		if (skb->len <= copy) {
			/* We've eaten all the data from this skb.
			 * Throw it away. */
			TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags;
			tcp_unlink_write_queue(skb, sk);
			sk_stream_free_skb(sk, skb);
		} else {
			TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags &
						   ~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
			if (!skb_shinfo(skb)->nr_frags) {
				skb_pull(skb, copy);
				if (skb->ip_summed != CHECKSUM_PARTIAL)
					skb->csum = csum_partial(skb->data, skb->len, 0);
			} else {
				__pskb_trim_head(skb, copy);
				tcp_set_skb_tso_segs(sk, skb, mss_now);
			}
			TCP_SKB_CB(skb)->seq += copy;
		}

		len += copy;
		skb = next;
	}
	tcp_init_tso_segs(sk, nskb, nskb->len);

	/* We're ready to send.  If this fails, the probe will
	 * be resegmented into mss-sized pieces by tcp_write_xmit(). */
	TCP_SKB_CB(nskb)->when = tcp_time_stamp;
	if (!tcp_transmit_skb(sk, nskb, 1, GFP_ATOMIC)) {
		/* Decrement cwnd here because we are sending
		* effectively two packets. */
		tp->snd_cwnd--;
		update_send_head(sk, nskb);

		icsk->icsk_mtup.probe_size = tcp_mss_to_mtu(sk, nskb->len);
		tp->mtu_probe.probe_seq_start = TCP_SKB_CB(nskb)->seq;
		tp->mtu_probe.probe_seq_end = TCP_SKB_CB(nskb)->end_seq;

		return 1;
	}

	return -1;
}


/* This routine writes packets to the network.  It advances the
 * send_head.  This happens as incoming acks open up the remote
 * window for us.
 *
 * Returns 1, if no segments are in flight and we have queued segments, but
 * cannot send anything now because of SWS or another problem.
 */
static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int tso_segs, sent_pkts;
	int cwnd_quota;
	int result;

	/* If we are closed, the bytes will have to remain here.
	 * In time closedown will finish, we empty the write queue and all
	 * will be happy.
	 */
	if (unlikely(sk->sk_state == TCP_CLOSE))
		return 0;

	sent_pkts = 0;

	/* Do MTU probing. */
	if ((result = tcp_mtu_probe(sk)) == 0) {
		return 0;
	} else if (result > 0) {
		sent_pkts = 1;
	}

	while ((skb = tcp_send_head(sk))) {
		unsigned int limit;

		tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
		BUG_ON(!tso_segs);

		cwnd_quota = tcp_cwnd_test(tp, skb);
		if (!cwnd_quota)
			break;

		if (unlikely(!tcp_snd_wnd_test(tp, skb, mss_now)))
			break;

		if (tso_segs == 1) {
			if (unlikely(!tcp_nagle_test(tp, skb, mss_now,
						     (tcp_skb_is_last(sk, skb) ?
						      nonagle : TCP_NAGLE_PUSH))))
				break;
		} else {
			if (tcp_tso_should_defer(sk, skb))
				break;
		}

		limit = mss_now;
		if (tso_segs > 1) {
			limit = tcp_window_allows(tp, skb,
						  mss_now, cwnd_quota);

			if (skb->len < limit) {
				unsigned int trim = skb->len % mss_now;

				if (trim)
					limit = skb->len - trim;
			}
		}

		if (skb->len > limit &&
		    unlikely(tso_fragment(sk, skb, limit, mss_now)))
			break;

		TCP_SKB_CB(skb)->when = tcp_time_stamp;

		if (unlikely(tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC)))
			break;

		/* Advance the send_head.  This one is sent out.
		 * This call will increment packets_out.
		 */
		update_send_head(sk, skb);

		tcp_minshall_update(tp, mss_now, skb);
		sent_pkts++;
	}

	if (likely(sent_pkts)) {
		tcp_cwnd_validate(sk);
		return 0;
	}
	return !tp->packets_out && tcp_send_head(sk);
}

/* Push out any pending frames which were held back due to
 * TCP_CORK or attempt at coalescing tiny packets.
 * The socket must be locked by the caller.
 */
void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,
			       int nonagle)
{
	struct sk_buff *skb = tcp_send_head(sk);

	if (skb) {
		if (tcp_write_xmit(sk, cur_mss, nonagle))
			tcp_check_probe_timer(sk);
	}
}

/* Send _single_ skb sitting at the send head. This function requires
 * true push pending frames to setup probe timer etc.
 */
void tcp_push_one(struct sock *sk, unsigned int mss_now)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb = tcp_send_head(sk);
	unsigned int tso_segs, cwnd_quota;

	BUG_ON(!skb || skb->len < mss_now);

	tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
	cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH);

	if (likely(cwnd_quota)) {
		unsigned int limit;

		BUG_ON(!tso_segs);

		limit = mss_now;
		if (tso_segs > 1) {
			limit = tcp_window_allows(tp, skb,
						  mss_now, cwnd_quota);

			if (skb->len < limit) {
				unsigned int trim = skb->len % mss_now;

				if (trim)
					limit = skb->len - trim;
			}
		}

		if (skb->len > limit &&
		    unlikely(tso_fragment(sk, skb, limit, mss_now)))
			return;

		/* Send it out now. */
		TCP_SKB_CB(skb)->when = tcp_time_stamp;

		if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) {
			update_send_head(sk, skb);
			tcp_cwnd_validate(sk);
			return;
		}
	}
}

/* This function returns the amount that we can raise the
 * usable window based on the following constraints
 *
 * 1. The window can never be shrunk once it is offered (RFC 793)
 * 2. We limit memory per socket
 *
 * RFC 1122:
 * "the suggested [SWS] avoidance algorithm for the receiver is to keep
 *  RECV.NEXT + RCV.WIN fixed until:
 *  RCV.BUFF - RCV.USER - RCV.WINDOW >= min(1/2 RCV.BUFF, MSS)"
 *
 * i.e. don't raise the right edge of the window until you can raise
 * it at least MSS bytes.
 *
 * Unfortunately, the recommended algorithm breaks header prediction,
 * since header prediction assumes th->window stays fixed.
 *
 * Strictly speaking, keeping th->window fixed violates the receiver
 * side SWS prevention criteria. The problem is that under this rule
 * a stream of single byte packets will cause the right side of the
 * window to always advance by a single byte.
 *
 * Of course, if the sender implements sender side SWS prevention
 * then this will not be a problem.
 *
 * BSD seems to make the following compromise:
 *
 *	If the free space is less than the 1/4 of the maximum
 *	space available and the free space is less than 1/2 mss,
 *	then set the window to 0.
 *	[ Actually, bsd uses MSS and 1/4 of maximal _window_ ]
 *	Otherwise, just prevent the window from shrinking
 *	and from being larger than the largest representable value.
 *
 * This prevents incremental opening of the window in the regime
 * where TCP is limited by the speed of the reader side taking
 * data out of the TCP receive queue. It does nothing about
 * those cases where the window is constrained on the sender side
 * because the pipeline is full.
 *
 * BSD also seems to "accidentally" limit itself to windows that are a
 * multiple of MSS, at least until the free space gets quite small.
 * This would appear to be a side effect of the mbuf implementation.
 * Combining these two algorithms results in the observed behavior
 * of having a fixed window size at almost all times.
 *
 * Below we obtain similar behavior by forcing the offered window to
 * a multiple of the mss when it is feasible to do so.
 *
 * Note, we don't "adjust" for TIMESTAMP or SACK option bytes.
 * Regular options like TIMESTAMP are taken into account.
 */
u32 __tcp_select_window(struct sock *sk)
{
	struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	/* MSS for the peer's data.  Previous versions used mss_clamp
	 * here.  I don't know if the value based on our guesses
	 * of peer's MSS is better for the performance.  It's more correct
	 * but may be worse for the performance because of rcv_mss
	 * fluctuations.  --SAW  1998/11/1
	 */
	int mss = icsk->icsk_ack.rcv_mss;
	int free_space = tcp_space(sk);
	int full_space = min_t(int, tp->window_clamp, tcp_full_space(sk));
	int window;

	if (mss > full_space)
		mss = full_space;

	if (free_space < full_space/2) {
		icsk->icsk_ack.quick = 0;

		if (tcp_memory_pressure)
			tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U*tp->advmss);

		if (free_space < mss)
			return 0;
	}

	if (free_space > tp->rcv_ssthresh)
		free_space = tp->rcv_ssthresh;

	/* Don't do rounding if we are using window scaling, since the
	 * scaled window will not line up with the MSS boundary anyway.
	 */
	window = tp->rcv_wnd;
	if (tp->rx_opt.rcv_wscale) {
		window = free_space;

		/* Advertise enough space so that it won't get scaled away.
		 * Import case: prevent zero window announcement if
		 * 1<<rcv_wscale > mss.
		 */
		if (((window >> tp->rx_opt.rcv_wscale) << tp->rx_opt.rcv_wscale) != window)
			window = (((window >> tp->rx_opt.rcv_wscale) + 1)
				  << tp->rx_opt.rcv_wscale);
	} else {
		/* Get the largest window that is a nice multiple of mss.
		 * Window clamp already applied above.
		 * If our current window offering is within 1 mss of the
		 * free space we just keep it. This prevents the divide
		 * and multiply from happening most of the time.
		 * We also don't do any window rounding when the free space
		 * is too small.
		 */
		if (window <= free_space - mss || window > free_space)
			window = (free_space/mss)*mss;
		else if (mss == full_space &&
			 free_space > window + full_space/2)
			window = free_space;
	}

	return window;
}

/* Attempt to collapse two adjacent SKB's during retransmission. */
static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, int mss_now)
{
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *next_skb = tcp_write_queue_next(sk, skb);

	/* The first test we must make is that neither of these two
	 * SKB's are still referenced by someone else.
	 */
	if (!skb_cloned(skb) && !skb_cloned(next_skb)) {
		int skb_size = skb->len, next_skb_size = next_skb->len;
		u16 flags = TCP_SKB_CB(skb)->flags;

		/* Also punt if next skb has been SACK'd. */
		if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED)
			return;

		/* Next skb is out of window. */
		if (after(TCP_SKB_CB(next_skb)->end_seq, tp->snd_una+tp->snd_wnd))
			return;

		/* Punt if not enough space exists in the first SKB for
		 * the data in the second, or the total combined payload
		 * would exceed the MSS.
		 */
		if ((next_skb_size > skb_tailroom(skb)) ||
		    ((skb_size + next_skb_size) > mss_now))
			return;

		BUG_ON(tcp_skb_pcount(skb) != 1 ||
		       tcp_skb_pcount(next_skb) != 1);

		if (WARN_ON(tcp_is_sack(tp) && tp->sacked_out &&
		    (TCP_SKB_CB(next_skb)->seq == tp->highest_sack)))
			return;

		/* Ok.	We will be able to collapse the packet. */
		tcp_unlink_write_queue(next_skb, sk);

		skb_copy_from_linear_data(next_skb,
					  skb_put(skb, next_skb_size),
					  next_skb_size);

		if (next_skb->ip_summed == CHECKSUM_PARTIAL)
			skb->ip_summed = CHECKSUM_PARTIAL;

		if (skb->ip_summed != CHECKSUM_PARTIAL)
			skb->csum = csum_block_add(skb->csum, next_skb->csum, skb_size);

		/* Update sequence range on original skb. */
		TCP_SKB_CB(skb)->end_seq = TCP_SKB_CB(next_skb)->end_seq;

		/* Merge over control information. */
		flags |= TCP_SKB_CB(next_skb)->flags; /* This moves PSH/FIN etc. over */
		TCP_SKB_CB(skb)->flags = flags;

		/* All done, get rid of second SKB and account for it so
		 * packet counting does not break.
		 */
		TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked&(TCPCB_EVER_RETRANS|TCPCB_AT_TAIL);
		if (TCP_SKB_CB(next_skb)->sacked&TCPCB_SACKED_RETRANS)
			tp->retrans_out -= tcp_skb_pcount(next_skb);
		if (TCP_SKB_CB(next_skb)->sacked&TCPCB_LOST)
			tp->lost_out -= tcp_skb_pcount(next_skb);
		/* Reno case is special. Sigh... */
		if (tcp_is_reno(tp) && tp->sacked_out)
			tcp_dec_pcount_approx(&tp->sacked_out, next_skb);

		tcp_adjust_fackets_out(tp, next_skb, tcp_skb_pcount(next_skb));
		tp->packets_out -= tcp_skb_pcount(next_skb);

		/* changed transmit queue under us so clear hints */
		tcp_clear_retrans_hints_partial(tp);
		/* manually tune sacktag skb hint */
		if (tp->fastpath_skb_hint == next_skb) {
			tp->fastpath_skb_hint = skb;
			tp->fastpath_cnt_hint -= tcp_skb_pcount(skb);
		}

		sk_stream_free_skb(sk, next_skb);
	}
}

/* Do a simple retransmit without using the backoff mechanisms in
 * tcp_timer. This is used for path mtu discovery.
 * The socket is already locked here.
 */
void tcp_simple_retransmit(struct sock *sk)
{
	const struct inet_connection_sock *icsk = inet_csk(sk);
	struct tcp_sock *tp = tcp_sk(sk);
	struct sk_buff *skb;
	unsigned int mss = tcp_current_mss(sk, 0);
	int lost = 0;

	tcp_for_write_queue(skb, sk) {
		if (skb == tcp_send_head(sk))
			break;
		if (skb->len > mss &&
		    !(TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_ACKED)) {
			if (TCP_SKB_CB(skb)->sacked&TCPCB_SACKED_RETRANS) {
				TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS;
				tp->retrans_out -= tcp_skb_pcount(skb);
			}
			if (!(TCP_SKB_CB(skb)->sacked&TCPCB_LOST)) {
				TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
				tp->lost_out += tcp_skb_pcount(skb);
				lost = 1;
			}
		}
	}

	tcp_clear_all_retrans_hints(tp);

	if (!lost)