Merge branch 'tcp-rto-min-us'

Kevin Yang says:

====================
tcp: add sysctl_tcp_rto_min_us

Adding a sysctl knob to allow user to specify a default
rto_min at socket init time.

After this patch series, the rto_min will has multiple sources:
route option has the highest precedence, followed by the
TCP_BPF_RTO_MIN socket option, followed by this new
tcp_rto_min_us sysctl.

v3:
    fix typo, simplify min/max_t to min/max

v2:
    fit line width to 80 column.

v2: https://lore.kernel.org/netdev/20240530153436.2202800-1-yyd@google.com/
v1: https://lore.kernel.org/netdev/20240528171320.1332292-1-yyd@google.com/
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/ip-sysctl.rst

@@ -1196,6 +1196,19 @@ tcp_pingpong_thresh - INTEGER
 
 	Default: 1
 
+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
 =============
 

include/net/netns/ipv4.h

@@ -170,6 +170,7 @@ struct netns_ipv4 {
 	u8 sysctl_tcp_sack;
 	u8 sysctl_tcp_window_scaling;
 	u8 sysctl_tcp_timestamps;
+	int sysctl_tcp_rto_min_us;
 	u8 sysctl_tcp_recovery;
 	u8 sysctl_tcp_thin_linear_timeouts;
 	u8 sysctl_tcp_slow_start_after_idle;

net/ipv4/sysctl_net_ipv4.c

@@ -1503,6 +1503,14 @@ static struct ctl_table ipv4_net_table[] = {
 		.proc_handler	= proc_dou8vec_minmax,
 		.extra1		= SYSCTL_ONE,
 	},
+	{
+		.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,
+	},
 };
 
 static __net_init int ipv4_sysctl_init_net(struct net *net)

net/ipv4/tcp.c

@@ -420,6 +420,7 @@ 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;
@@ -428,7 +429,8 @@ 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);

net/ipv4/tcp_ipv4.c

@@ -3502,6 +3502,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_shrink_window = 0;
 
 	net->ipv4.sysctl_tcp_pingpong_thresh = 1;
+	net->ipv4.sysctl_tcp_rto_min_us = jiffies_to_usecs(TCP_RTO_MIN);
 
 	return 0;
 }

net/ipv4/tcp_output.c

@@ -4163,16 +4163,9 @@ EXPORT_SYMBOL(tcp_connect);
 
 u32 tcp_delack_max(const struct sock *sk)
 {
-	const struct dst_entry *dst = __sk_dst_get(sk);
-	u32 delack_max = inet_csk(sk)->icsk_delack_max;
-
-	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN)) {
-		u32 rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
-		u32 delack_from_rto_min = max_t(int, 1, rto_min - 1);
+	u32 delack_from_rto_min = max(tcp_rto_min(sk), 2) - 1;
 
-		delack_max = min_t(u32, delack_max, delack_from_rto_min);
-	}
-	return delack_max;
+	return min(inet_csk(sk)->icsk_delack_max, delack_from_rto_min);
 }
 
 /* Send out a delayed ack, the caller does the policy checking