tcp: make the first N SYN RTO backoffs linear

Currently the SYN RTO schedule follows an exponential backoff
scheme, which can be unnecessarily conservative in cases where
there are link failures. In such cases, it's better to
aggressively try to retransmit packets, so it takes routers
less time to find a repath with a working link.

We chose a default value for this sysctl of 4, to follow
the macOS and IOS backoff scheme of 1,1,1,1,1,2,4,8, ...
MacOS and IOS have used this backoff schedule for over
a decade, since before this 2009 IETF presentation
discussed the behavior:
https://www.ietf.org/proceedings/75/slides/tcpm-1.pdf

This commit makes the SYN RTO schedule start with a number of
linear backoffs given by the following sysctl:
* tcp_syn_linear_timeouts

This changes the SYN RTO scheme to be: init_rto_val for
tcp_syn_linear_timeouts, exp backoff starting at init_rto_val

For example if init_rto_val = 1 and tcp_syn_linear_timeouts = 2, our
backoff scheme would be: 1, 1, 1, 2, 4, 8, 16, ...

Signed-off-by: David Morley <morleyd@google.com>
Signed-off-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Tested-by: David Morley <morleyd@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://lore.kernel.org/r/20230509180558.2541885-1-morleyd.kernel@gmail.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

3 files changed, 24 insertions, 4 deletions

diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 40fe70fc2015..6ae3345a3bdf 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -34,6 +34,7 @@ static int ip_ttl_min = 1;
 static int ip_ttl_max = 255;
 static int tcp_syn_retries_min = 1;
 static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
+static int tcp_syn_linear_timeouts_max = MAX_TCP_SYNCNT;
 static int ip_ping_group_range_min[] = { 0, 0 };
 static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
 static u32 u32_max_div_HZ = UINT_MAX / HZ;
@@ -1470,6 +1471,15 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra1         = SYSCTL_ZERO,
 		.extra2         = &tcp_plb_max_cong_thresh,
 	},
+	{
+		.procname = "tcp_syn_linear_timeouts",
+		.data = &init_net.ipv4.sysctl_tcp_syn_linear_timeouts,
+		.maxlen = sizeof(u8),
+		.mode = 0644,
+		.proc_handler = proc_dou8vec_minmax,
+		.extra1 = SYSCTL_ZERO,
+		.extra2 = &tcp_syn_linear_timeouts_max,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 39bda2b1066e..db24ed8f8509 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3275,6 +3275,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	else
 		net->ipv4.tcp_congestion_control = &tcp_reno;
 
+	net->ipv4.sysctl_tcp_syn_linear_timeouts = 4;
 	return 0;
 }
 
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index b839c2f91292..0d93a2573807 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -234,14 +234,19 @@ static int tcp_write_timeout(struct sock *sk)
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct net *net = sock_net(sk);
 	bool expired = false, do_reset;
-	int retry_until;
+	int retry_until, max_retransmits;
 
 	if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
 		if (icsk->icsk_retransmits)
 			__dst_negative_advice(sk);
 		retry_until = icsk->icsk_syn_retries ? :
 			READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
-		expired = icsk->icsk_retransmits >= retry_until;
+
+		max_retransmits = retry_until;
+		if (sk->sk_state == TCP_SYN_SENT)
+			max_retransmits += READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts);
+
+		expired = icsk->icsk_retransmits >= max_retransmits;
 	} else {
 		if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) {
 			/* Black hole detection */
@@ -577,8 +582,12 @@ out_reset_timer:
 	    icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
 		icsk->icsk_backoff = 0;
 		icsk->icsk_rto = min(__tcp_set_rto(tp), TCP_RTO_MAX);
-	} else {
-		/* Use normal (exponential) backoff */
+	} else if (sk->sk_state != TCP_SYN_SENT ||
+		   icsk->icsk_backoff >
+		   READ_ONCE(net->ipv4.sysctl_tcp_syn_linear_timeouts)) {
+		/* Use normal (exponential) backoff unless linear timeouts are
+		 * activated.
+		 */
 		icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
 	}
 	inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,