[SRU][jammy:linux-gcp][PATCH 3/3] tcp: add sysctl_tcp_rto_min_us

[Vinicius Peixoto]

From: Kevin Yang <yyd at google.com>

Adding a sysctl knob to allow user to specify a default
rto_min at socket init time, other than using the hard
coded 200ms default rto_min.

Note that the rto_min route option has the highest precedence
for configuring this setting, followed by the TCP_BPF_RTO_MIN
socket option, followed by the tcp_rto_min_us sysctl.

Signed-off-by: Kevin Yang <yyd at google.com>
Reviewed-by: Neal Cardwell <ncardwell at google.com>
Reviewed-by: Yuchung Cheng <ycheng at google.com>
Reviewed-by: Eric Dumazet <edumazet at google.com>
Reviewed-by: Tony Lu <tonylu at linux.alibaba.com>
Reviewed-by: Jakub Kicinski <kuba at kernel.org>
Signed-off-by: David S. Miller <davem at davemloft.net>
(backported from commit f086edef71be7174a16c1ed67ac65a085cda28b1)
[vpeixoto: fixed conflicts in include/net/netns/ipv4.h due to missing
commits 18fd64d25422 ("netns-ipv4: reorganize netns_ipv4 fast path
variables"), and 1c106eb01cee ("net: ipv{6,4}: Remove the now
superfluous sentinel elements from ctl_table array"), as well as
context conflicts in net/ipv4/tcp_ipv4.c due to missing commits adding
other unrelated TCP sysctls.]
Signed-off-by: Vinicius Peixoto <vinicius.peixoto at canonical.com>
---
 Documentation/networking/ip-sysctl.rst | 13 +++++++++++++
 include/net/netns/ipv4.h               |  1 +
 net/ipv4/sysctl_net_ipv4.c             |  8 ++++++++
 net/ipv4/tcp.c                         |  4 +++-
 net/ipv4/tcp_ipv4.c                    |  2 ++
 5 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 7f75767a24f1..9c931bb5fdc3 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -999,6 +999,19 @@ tcp_rx_skb_cache - BOOLEAN
 
 	Default: 0 (disabled)
 
+tcp_rto_min_us - INTEGER
+	Minimal TCP retransmission timeout (in microseconds). Note that the
+	rto_min route option has the highest precedence for configuring this
+	setting, followed by the TCP_BPF_RTO_MIN socket option, followed by
+	this tcp_rto_min_us sysctl.
+
+	The recommended practice is to use a value less or equal to 200000
+	microseconds.
+
+	Possible Values: 1 - INT_MAX
+
+	Default: 200000
+
 UDP variables
 =============
 
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index d60a10cfc382..d35337cb7b87 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -137,6 +137,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_window_scaling;
 	u8 sysctl_tcp_timestamps;
 	u8 sysctl_tcp_early_retrans;
+	int sysctl_tcp_rto_min_us;
 	u8 sysctl_tcp_recovery;
 	u8 sysctl_tcp_thin_linear_timeouts;
 	u8 sysctl_tcp_slow_start_after_idle;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 1f22e72074fd..f3df0a77a27d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -1362,6 +1362,14 @@ static struct ctl_table ipv4_net_table[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= &two,
 	},
+	{
+		.procname	= "tcp_rto_min_us",
+		.data		= &init_net.ipv4.sysctl_tcp_rto_min_us,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+	},
 	{ }
 };
 
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 95398c10086c..e709031df533 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -417,6 +417,7 @@ void tcp_init_sock(struct sock *sk)
 {
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct tcp_sock *tp = tcp_sk(sk);
+	int rto_min_us;
 
 	tp->out_of_order_queue = RB_ROOT;
 	sk->tcp_rtx_queue = RB_ROOT;
@@ -425,7 +426,8 @@ void tcp_init_sock(struct sock *sk)
 	INIT_LIST_HEAD(&tp->tsorted_sent_queue);
 
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	icsk->icsk_rto_min = TCP_RTO_MIN;
+	rto_min_us = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rto_min_us);
+	icsk->icsk_rto_min = usecs_to_jiffies(rto_min_us);
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT);
 	minmax_reset(&tp->rtt_min, tcp_jiffies32, ~0U);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index e162bed1916a..37f017d6d82f 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -3217,6 +3217,8 @@ static int __net_init tcp_sk_init(struct net *net)
 	else
 		net->ipv4.tcp_congestion_control = &tcp_reno;
 
+	net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN);
+
 	return 0;
 }
 
-- 
2.43.0