tcp: support TCP_RTO_MIN_US for set/getsockopt use

Support adjusting/reading RTO MIN for socket level by using set/getsockopt().

This new option has the same effect as TCP_BPF_RTO_MIN, which means it
doesn't affect RTAX_RTO_MIN usage (by using ip route...). Considering that
bpf option was implemented before this patch, so we need to use a standalone
new option for pure tcp set/getsockopt() use.

When the socket is created, its icsk_rto_min is set to the default
value that is controlled by sysctl_tcp_rto_min_us. Then if application
calls setsockopt() with TCP_RTO_MIN_US flag to pass a valid value, then
icsk_rto_min will be overridden in jiffies unit.

This patch adds WRITE_ONCE/READ_ONCE to avoid data-race around
icsk_rto_min.

Signed-off-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250317120314.41404-2-kerneljasonxing@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 16 insertions, 4 deletions

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 054561f8dcae..5c63ab928b97 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -1229,8 +1229,8 @@ tcp_pingpong_thresh - INTEGER
 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.
+	setting, followed by the TCP_BPF_RTO_MIN and TCP_RTO_MIN_US socket
+	options, followed by this tcp_rto_min_us sysctl.
 
 	The recommended practice is to use a value less or equal to 200000
 	microseconds.
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f8efe56bbccb..4450c384ef17 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -844,7 +844,7 @@ u32 tcp_delack_max(const struct sock *sk);
 static inline u32 tcp_rto_min(const struct sock *sk)
 {
 	const struct dst_entry *dst = __sk_dst_get(sk);
-	u32 rto_min = inet_csk(sk)->icsk_rto_min;
+	u32 rto_min = READ_ONCE(inet_csk(sk)->icsk_rto_min);
 
 	if (dst && dst_metric_locked(dst, RTAX_RTO_MIN))
 		rto_min = dst_metric_rtt(dst, RTAX_RTO_MIN);
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 92a2e79222ea..a126b3860e63 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -140,6 +140,7 @@ enum {
 
 #define TCP_IS_MPTCP		43	/* Is MPTCP being used? */
 #define TCP_RTO_MAX_MS		44	/* max rto time in ms */
+#define TCP_RTO_MIN_US		45	/* min rto time in us */
 
 #define TCP_REPAIR_ON		1
 #define TCP_REPAIR_OFF		0
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fde56d28f586..a8a1370d642e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3352,7 +3352,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_probes_out = 0;
 	icsk->icsk_probes_tstamp = 0;
 	icsk->icsk_rto = TCP_TIMEOUT_INIT;
-	icsk->icsk_rto_min = TCP_RTO_MIN;
+	WRITE_ONCE(icsk->icsk_rto_min, TCP_RTO_MIN);
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
 	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
@@ -3833,6 +3833,14 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 			return -EINVAL;
 		WRITE_ONCE(inet_csk(sk)->icsk_rto_max, msecs_to_jiffies(val));
 		return 0;
+	case TCP_RTO_MIN_US: {
+		int rto_min = usecs_to_jiffies(val);
+
+		if (rto_min > TCP_RTO_MIN || rto_min < TCP_TIMEOUT_MIN)
+			return -EINVAL;
+		WRITE_ONCE(inet_csk(sk)->icsk_rto_min, rto_min);
+		return 0;
+	}
 	}
 
 	sockopt_lock_sock(sk);
@@ -4672,6 +4680,9 @@ zerocopy_rcv_out:
 	case TCP_RTO_MAX_MS:
 		val = jiffies_to_msecs(tcp_rto_max(sk));
 		break;
+	case TCP_RTO_MIN_US:
+		val = jiffies_to_usecs(READ_ONCE(inet_csk(sk)->icsk_rto_min));
+		break;
 	default:
 		return -ENOPROTOOPT;
 	}