Merge branch 'tcp-RACK-fast-recovery'

Yuchung Cheng says:

====================
tcp: RACK fast recovery

The patch set enables RACK loss detection (draft-ietf-tcpm-rack-01)
to trigger fast recovery with a reordering timer.

Previously RACK has been running in auxiliary mode where it is
used to detect packet losses once the recovery has triggered by
other algorithms (e.g., FACK). By inspecting packet timestamps,
RACK can start ACK-driven repairs timely. A few similar heuristics
are no longer needed and are either removed or disabled to reduce
the complexity of the Linux TCP loss recovery engine:

  1. FACK (Forward Acknowledgement)
  2. Early Retransmit (RFC5827)
  3. thin_dupack (fast recovery on single DUPACK for thin-streams)
  4. NCR (Non-Congestion Robustness RFC4653) (RFC4653)
  5. Forward Retransmit

After this change, Linux's loss recovery algorithms consist of
  1. Conventional DUPACK threshold approach (RFC6675)
  2. RACK and Tail Loss Probe (draft-ietf-tcpm-rack-01)
  3. RTO plus F-RTO extension (RFC5682)

The patch set has been tested on Google servers extensively and
presented in several IETF meetings. The data suggests that RACK
successfully improves recovery performance:
https://www.ietf.org/proceedings/97/slides/slides-97-tcpm-draft-ietf-tcpm-rack-01.pdf
https://www.ietf.org/proceedings/96/slides/slides-96-tcpm-3.pdf
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 9 insertions, 66 deletions

diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 1d5331a1b1dc..9a1a1494b9dd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -76,10 +76,8 @@ static void tcp_event_new_data_sent(struct sock *sk, const struct sk_buff *skb)
 	tp->snd_nxt = TCP_SKB_CB(skb)->end_seq;
 
 	tp->packets_out += tcp_skb_pcount(skb);
-	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS ||
-	    icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) {
+	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);
-	}
 
 	NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
 		      tcp_skb_pcount(skb));
@@ -2289,8 +2287,6 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	u32 timeout, tlp_time_stamp, rto_time_stamp;
 	u32 rtt = usecs_to_jiffies(tp->srtt_us >> 3);
 
-	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_EARLY_RETRANS))
-		return false;
 	/* No consecutive loss probes. */
 	if (WARN_ON(icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)) {
 		tcp_rearm_rto(sk);
@@ -2309,8 +2305,9 @@ bool tcp_schedule_loss_probe(struct sock *sk)
 	/* Schedule a loss probe in 2*RTT for SACK capable connections
 	 * in Open state, that are either limited by cwnd or application.
 	 */
-	if (sysctl_tcp_early_retrans < 3 || !tp->packets_out ||
-	    !tcp_is_sack(tp) || inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
+	if ((sysctl_tcp_early_retrans != 3 && sysctl_tcp_early_retrans != 4) ||
+	    !tp->packets_out || !tcp_is_sack(tp) ||
+	    icsk->icsk_ca_state != TCP_CA_Open)
 		return false;
 
 	if ((tp->snd_cwnd > tcp_packets_in_flight(tp)) &&
@@ -2831,36 +2828,6 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
 	return err;
 }
 
-/* Check if we forward retransmits are possible in the current
- * window/congestion state.
- */
-static bool tcp_can_forward_retransmit(struct sock *sk)
-{
-	const struct inet_connection_sock *icsk = inet_csk(sk);
-	const struct tcp_sock *tp = tcp_sk(sk);
-
-	/* Forward retransmissions are possible only during Recovery. */
-	if (icsk->icsk_ca_state != TCP_CA_Recovery)
-		return false;
-
-	/* No forward retransmissions in Reno are possible. */
-	if (tcp_is_reno(tp))
-		return false;
-
-	/* Yeah, we have to make difficult choice between forward transmission
-	 * and retransmission... Both ways have their merits...
-	 *
-	 * For now we do not retransmit anything, while we have some new
-	 * segments to send. In the other cases, follow rule 3 for
-	 * NextSeg() specified in RFC3517.
-	 */
-
-	if (tcp_may_send_now(sk))
-		return false;
-
-	return true;
-}
-
 /* This gets called after a retransmit timeout, and the initially
  * retransmitted data is acknowledged.  It tries to continue
  * resending the rest of the retransmit queue, until either
@@ -2875,24 +2842,16 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
 	struct sk_buff *hole = NULL;
-	u32 max_segs, last_lost;
+	u32 max_segs;
 	int mib_idx;
-	int fwd_rexmitting = 0;
 
 	if (!tp->packets_out)
 		return;
 
-	if (!tp->lost_out)
-		tp->retransmit_high = tp->snd_una;
-
 	if (tp->retransmit_skb_hint) {
 		skb = tp->retransmit_skb_hint;
-		last_lost = TCP_SKB_CB(skb)->end_seq;
-		if (after(last_lost, tp->retransmit_high))
-			last_lost = tp->retransmit_high;
 	} else {
 		skb = tcp_write_queue_head(sk);
-		last_lost = tp->snd_una;
 	}
 
 	max_segs = tcp_tso_segs(sk, tcp_current_mss(sk));
@@ -2915,31 +2874,14 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 		 */
 		segs = min_t(int, segs, max_segs);
 
-		if (fwd_rexmitting) {
-begin_fwd:
-			if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp)))
-				break;
-			mib_idx = LINUX_MIB_TCPFORWARDRETRANS;
-
-		} else if (!before(TCP_SKB_CB(skb)->seq, tp->retransmit_high)) {
-			tp->retransmit_high = last_lost;
-			if (!tcp_can_forward_retransmit(sk))
-				break;
-			/* Backtrack if necessary to non-L'ed skb */
-			if (hole) {
-				skb = hole;
-				hole = NULL;
-			}
-			fwd_rexmitting = 1;
-			goto begin_fwd;
-
+		if (tp->retrans_out >= tp->lost_out) {
+			break;
 		} else if (!(sacked & TCPCB_LOST)) {
 			if (!hole && !(sacked & (TCPCB_SACKED_RETRANS|TCPCB_SACKED_ACKED)))
 				hole = skb;
 			continue;
 
 		} else {
-			last_lost = TCP_SKB_CB(skb)->end_seq;
 			if (icsk->icsk_ca_state != TCP_CA_Loss)
 				mib_idx = LINUX_MIB_TCPFASTRETRANS;
 			else
@@ -2960,7 +2902,8 @@ begin_fwd:
 		if (tcp_in_cwnd_reduction(sk))
 			tp->prr_out += tcp_skb_pcount(skb);
 
-		if (skb == tcp_write_queue_head(sk))
+		if (skb == tcp_write_queue_head(sk) &&
+		    icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT)
 			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
 						  inet_csk(sk)->icsk_rto,
 						  TCP_RTO_MAX);