Merge branch 'tcp-default-RACK-loss-recovery'

Yuchung Cheng says:

====================
tcp: default RACK loss recovery

This patch set implements the features correspond to the
draft-ietf-tcpm-rack-03 version of the RACK draft.
https://datatracker.ietf.org/meeting/101/materials/slides-101-tcpm-update-on-tcp-rack-00

1. SACK: implement equivalent DUPACK threshold heuristic in RACK to
   replace existing RFC6675 recovery (tcp_mark_head_lost).

2. Non-SACK: simplify RFC6582 NewReno implementation

3. RTO: apply RACK's time-based approach to avoid spuriouly
   marking very recently sent packets lost.

4. with (1)(2)(3), make RACK the exclusive fast recovery mechanism to
   mark losses based on time on S/ACK. Tail loss probe and F-RTO remain
   enabled by default as complementary mechanisms to send probes in
   CA_Open and CA_Loss states. The probes would solicit S/ACKs to trigger
   RACK time-based loss detection.

All Google web and internal servers have been running RACK-only mode
(4) for a while now. a/b experiments indicate RACK/TLP on average
reduces recovery latency by 10% compared to RFC6675. RFC6675
is default-off now but can be enabled by disabling RACK (sysctl
net.ipv4.tcp_recovery=0) for unseen issues.
====================

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

1 files changed, 53 insertions, 46 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b188e0d75edd..0bf032839548 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1917,19 +1917,54 @@ static inline void tcp_init_undo(struct tcp_sock *tp)
 	tp->undo_retrans = tp->retrans_out ? : -1;
 }
 
-/* Enter Loss state. If we detect SACK reneging, forget all SACK information
+static bool tcp_is_rack(const struct sock *sk)
+{
+	return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+}
+
+/* If we detect SACK reneging, forget all SACK information
  * and reset tags completely, otherwise preserve SACKs. If receiver
  * dropped its ofo queue, we will know this due to reneging detection.
  */
+static void tcp_timeout_mark_lost(struct sock *sk)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+	struct sk_buff *skb, *head;
+	bool is_reneg;			/* is receiver reneging on SACKs? */
+
+	head = tcp_rtx_queue_head(sk);
+	is_reneg = head && (TCP_SKB_CB(head)->sacked & TCPCB_SACKED_ACKED);
+	if (is_reneg) {
+		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
+		tp->sacked_out = 0;
+		/* Mark SACK reneging until we recover from this loss event. */
+		tp->is_sack_reneg = 1;
+	} else if (tcp_is_reno(tp)) {
+		tcp_reset_reno_sack(tp);
+	}
+
+	skb = head;
+	skb_rbtree_walk_from(skb) {
+		if (is_reneg)
+			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
+		else if (tcp_is_rack(sk) && skb != head &&
+			 tcp_rack_skb_timeout(tp, skb, 0) > 0)
+			continue; /* Don't mark recently sent ones lost yet */
+		tcp_mark_skb_lost(sk, skb);
+	}
+	tcp_verify_left_out(tp);
+	tcp_clear_all_retrans_hints(tp);
+}
+
+/* Enter Loss state. */
 void tcp_enter_loss(struct sock *sk)
 {
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
-	struct sk_buff *skb;
 	bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
-	bool is_reneg;			/* is receiver reneging on SACKs? */
-	bool mark_lost;
+
+	tcp_timeout_mark_lost(sk);
 
 	/* Reduce ssthresh if it has not yet been made inside this window. */
 	if (icsk->icsk_ca_state <= TCP_CA_Disorder ||
@@ -1941,40 +1976,10 @@ void tcp_enter_loss(struct sock *sk)
 		tcp_ca_event(sk, CA_EVENT_LOSS);
 		tcp_init_undo(tp);
 	}
-	tp->snd_cwnd	   = 1;
+	tp->snd_cwnd	   = tcp_packets_in_flight(tp) + 1;
 	tp->snd_cwnd_cnt   = 0;
 	tp->snd_cwnd_stamp = tcp_jiffies32;
 
-	tp->retrans_out = 0;
-	tp->lost_out = 0;
-
-	if (tcp_is_reno(tp))
-		tcp_reset_reno_sack(tp);
-
-	skb = tcp_rtx_queue_head(sk);
-	is_reneg = skb && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED);
-	if (is_reneg) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSACKRENEGING);
-		tp->sacked_out = 0;
-		/* Mark SACK reneging until we recover from this loss event. */
-		tp->is_sack_reneg = 1;
-	}
-	tcp_clear_all_retrans_hints(tp);
-
-	skb_rbtree_walk_from(skb) {
-		mark_lost = (!(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) ||
-			     is_reneg);
-		if (mark_lost)
-			tcp_sum_lost(tp, skb);
-		TCP_SKB_CB(skb)->sacked &= (~TCPCB_TAGBITS)|TCPCB_SACKED_ACKED;
-		if (mark_lost) {
-			TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_ACKED;
-			TCP_SKB_CB(skb)->sacked |= TCPCB_LOST;
-			tp->lost_out += tcp_skb_pcount(skb);
-		}
-	}
-	tcp_verify_left_out(tp);
-
 	/* Timeout in disordered state after receiving substantial DUPACKs
 	 * suggests that the degree of reordering is over-estimated.
 	 */
@@ -2141,7 +2146,7 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
 		return true;
 
 	/* Not-A-Trick#2 : Classic rule... */
-	if (tcp_dupack_heuristics(tp) > tp->reordering)
+	if (!tcp_is_rack(sk) && tcp_dupack_heuristics(tp) > tp->reordering)
 		return true;
 
 	return false;
@@ -2218,9 +2223,7 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	if (tcp_is_reno(tp)) {
-		tcp_mark_head_lost(sk, 1, 1);
-	} else {
+	if (tcp_is_sack(tp)) {
 		int sacked_upto = tp->sacked_out - tp->reordering;
 		if (sacked_upto >= 0)
 			tcp_mark_head_lost(sk, sacked_upto, 0);
@@ -2718,12 +2721,16 @@ static bool tcp_try_undo_partial(struct sock *sk, u32 prior_snd_una)
 	return false;
 }
 
-static void tcp_rack_identify_loss(struct sock *sk, int *ack_flag)
+static void tcp_identify_packet_loss(struct sock *sk, int *ack_flag)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
-	/* Use RACK to detect loss */
-	if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION) {
+	if (tcp_rtx_queue_empty(sk))
+		return;
+
+	if (unlikely(tcp_is_reno(tp))) {
+		tcp_newreno_mark_lost(sk, *ack_flag & FLAG_SND_UNA_ADVANCED);
+	} else if (tcp_is_rack(sk)) {
 		u32 prior_retrans = tp->retrans_out;
 
 		tcp_rack_mark_lost(sk);
@@ -2819,11 +2826,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 			tcp_try_keep_open(sk);
 			return;
 		}
-		tcp_rack_identify_loss(sk, ack_flag);
+		tcp_identify_packet_loss(sk, ack_flag);
 		break;
 	case TCP_CA_Loss:
 		tcp_process_loss(sk, flag, is_dupack, rexmit);
-		tcp_rack_identify_loss(sk, ack_flag);
+		tcp_identify_packet_loss(sk, ack_flag);
 		if (!(icsk->icsk_ca_state == TCP_CA_Open ||
 		      (*ack_flag & FLAG_LOST_RETRANS)))
 			return;
@@ -2840,7 +2847,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		if (icsk->icsk_ca_state <= TCP_CA_Disorder)
 			tcp_try_undo_dsack(sk);
 
-		tcp_rack_identify_loss(sk, ack_flag);
+		tcp_identify_packet_loss(sk, ack_flag);
 		if (!tcp_time_to_recover(sk, flag)) {
 			tcp_try_to_open(sk, flag);
 			return;
@@ -2862,7 +2869,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una,
 		fast_rexmit = 1;
 	}
 
-	if (do_lost)
+	if (!tcp_is_rack(sk) && do_lost)
 		tcp_update_scoreboard(sk, fast_rexmit);
 	*rexmit = REXMIT_LOST;
 }