tcp: add tcp_reset_xmit_timer() helper

With EDT model, SRTT no longer is inflated by pacing delays.

This means that RTO and some other xmit timers might be setup
incorrectly. This is particularly visible with either :

- Very small enforced pacing rates (SO_MAX_PACING_RATE)
- Reduced rto (from the default 200 ms)

This can lead to TCP flows aborts in the worst case,
or spurious retransmits in other cases.

For example, this session gets far more throughput
than the requested 80kbit :

$ netperf -H 127.0.0.2 -l 100 -- -q 10000
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 127.0.0.2 () port 0 AF_INET
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

540000 262144 262144    104.00      2.66

With the fix :

$ netperf -H 127.0.0.2 -l 100 -- -q 10000
MIGRATED TCP STREAM TEST from 0.0.0.0 (0.0.0.0) port 0 AF_INET to 127.0.0.2 () port 0 AF_INET
Recv   Send    Send
Socket Socket  Message  Elapsed
Size   Size    Size     Time     Throughput
bytes  bytes   bytes    secs.    10^6bits/sec

540000 262144 262144    104.00      0.12

EDT allows for better control of rtx timers, since TCP has
a better idea of the earliest departure time of each skb
in the rtx queue. We only have to eventually add to the
timer the difference of the EDT time with current time.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 14 insertions, 12 deletions

diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 188980c58f87..2868ef28ce52 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2979,8 +2979,8 @@ void tcp_rearm_rto(struct sock *sk)
 			 */
 			rto = usecs_to_jiffies(max_t(int, delta_us, 1));
 		}
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
-					  TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS, rto,
+				     TCP_RTO_MAX, tcp_rtx_queue_head(sk));
 	}
 }
 
@@ -3255,8 +3255,8 @@ static void tcp_ack_probe(struct sock *sk)
 	} else {
 		unsigned long when = tcp_probe0_when(sk, TCP_RTO_MAX);
 
-		inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-					  when, TCP_RTO_MAX);
+		tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+				     when, TCP_RTO_MAX, NULL);
 	}
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c07990a35ff3..9c34b97d365d 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2455,8 +2455,8 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
 	if (rto_delta_us > 0)
 		timeout = min_t(u32, timeout, usecs_to_jiffies(rto_delta_us));
 
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout,
-				  TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_LOSS_PROBE, timeout,
+			     TCP_RTO_MAX, NULL);
 	return true;
 }
 
@@ -3020,9 +3020,10 @@ void tcp_xmit_retransmit_queue(struct sock *sk)
 
 		if (skb == rtx_head &&
 		    icsk->icsk_pending != ICSK_TIME_REO_TIMEOUT)
-			inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
-						  inet_csk(sk)->icsk_rto,
-						  TCP_RTO_MAX);
+			tcp_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
+					     inet_csk(sk)->icsk_rto,
+					     TCP_RTO_MAX,
+					     skb);
 	}
 }
 
@@ -3752,9 +3753,10 @@ void tcp_send_probe0(struct sock *sk)
 			icsk->icsk_probes_out = 1;
 		probe_max = TCP_RESOURCE_PROBE_INTERVAL;
 	}
-	inet_csk_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
-				  tcp_probe0_when(sk, probe_max),
-				  TCP_RTO_MAX);
+	tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0,
+			     tcp_probe0_when(sk, probe_max),
+			     TCP_RTO_MAX,
+			     NULL);
 }
 
 int tcp_rtx_synack(const struct sock *sk, struct request_sock *req)