mptcp: sysctl: add syn_retrans_before_tcp_fallback

The number of SYN + MPC retransmissions before falling back to TCP was
fixed to 2. This is certainly a good default value, but having a fixed
number can be a problem in some environments.

The current behaviour means that if all packets are dropped, there will
be:

- The initial SYN + MPC

- 2 retransmissions with MPC

- The next ones will be without MPTCP.

So typically ~3 seconds before falling back to TCP. In some networks
where some temporally blackholes are unfortunately frequent, or when a
client tries to initiate connections while the network is not ready yet,
this can cause new connections not to have MPTCP connections.

In such environments, it is now possible to increase the number of SYN
retransmissions with MPTCP options to make sure MPTCP is used.

Interesting values are:

- 0: the first retransmission will be done without MPTCP options: quite
     aggressive, but also a higher risk of detecting false-positive
     MPTCP blackholes.

- >= 128: all SYN retransmissions will keep the MPTCP options: back to
          the < 6.12 behaviour.

The default behaviour is not changed here.

Reviewed-by: Mat Martineau <[email protected]>
Signed-off-by: Matthieu Baerts (NGI0) <[email protected]>
Link: https://patch.msgid.link/20250117-net-next-mptcp-syn_retrans_before_tcp_fallback-v1-1-ab4b187099b0@kernel.org
Signed-off-by: Jakub Kicinski <[email protected]>

Author: matttbe

Documentation/networking/mptcp-sysctl.rst

@@ -108,3 +108,19 @@ stale_loss_cnt - INTEGER
 	This is a per-namespace sysctl.
 
 	Default: 4
+
+syn_retrans_before_tcp_fallback - INTEGER
+	The number of SYN + MP_CAPABLE retransmissions before falling back to
+	TCP, i.e. dropping the MPTCP options. In other words, if all the packets
+	are dropped on the way, there will be:
+
+	* The initial SYN with MPTCP support
+	* This number of SYN retransmitted with MPTCP support
+	* The next SYN retransmissions will be without MPTCP support
+
+	0 means the first retransmission will be done without MPTCP options.
+	>= 128 means that all SYN retransmissions will keep the MPTCP options. A
+	lower number might increase false-positive MPTCP blackholes detections.
+	This is a per-namespace sysctl.
+
+	Default: 2

net/mptcp/ctrl.c

@@ -32,6 +32,7 @@ struct mptcp_pernet {
 	unsigned int close_timeout;
 	unsigned int stale_loss_cnt;
 	atomic_t active_disable_times;
+	u8 syn_retrans_before_tcp_fallback;
 	unsigned long active_disable_stamp;
 	u8 mptcp_enabled;
 	u8 checksum_enabled;
@@ -92,6 +93,7 @@ static void mptcp_pernet_set_defaults(struct mptcp_pernet *pernet)
 	pernet->mptcp_enabled = 1;
 	pernet->add_addr_timeout = TCP_RTO_MAX;
 	pernet->blackhole_timeout = 3600;
+	pernet->syn_retrans_before_tcp_fallback = 2;
 	atomic_set(&pernet->active_disable_times, 0);
 	pernet->close_timeout = TCP_TIMEWAIT_LEN;
 	pernet->checksum_enabled = 0;
@@ -245,6 +247,12 @@ static struct ctl_table mptcp_sysctl_table[] = {
 		.proc_handler = proc_blackhole_detect_timeout,
 		.extra1 = SYSCTL_ZERO,
 	},
+	{
+		.procname = "syn_retrans_before_tcp_fallback",
+		.maxlen = sizeof(u8),
+		.mode = 0644,
+		.proc_handler = proc_dou8vec_minmax,
+	},
 };
 
 static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
@@ -269,6 +277,7 @@ static int mptcp_pernet_new_table(struct net *net, struct mptcp_pernet *pernet)
 	/* table[7] is for available_schedulers which is read-only info */
 	table[8].data = &pernet->close_timeout;
 	table[9].data = &pernet->blackhole_timeout;
+	table[10].data = &pernet->syn_retrans_before_tcp_fallback;
 
 	hdr = register_net_sysctl_sz(net, MPTCP_SYSCTL_PATH, table,
 				     ARRAY_SIZE(mptcp_sysctl_table));
@@ -392,17 +401,21 @@ void mptcp_active_enable(struct sock *sk)
 void mptcp_active_detect_blackhole(struct sock *ssk, bool expired)
 {
 	struct mptcp_subflow_context *subflow;
-	u32 timeouts;
 
 	if (!sk_is_mptcp(ssk))
 		return;
 
-	timeouts = inet_csk(ssk)->icsk_retransmits;
 	subflow = mptcp_subflow_ctx(ssk);
 
 	if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) {
-		if (timeouts == 2 || (timeouts < 2 && expired)) {
-			MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPCAPABLEACTIVEDROP);
+		struct net *net = sock_net(ssk);
+		u8 timeouts, to_max;
+
+		timeouts = inet_csk(ssk)->icsk_retransmits;
+		to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback;
+
+		if (timeouts == to_max || (timeouts < to_max && expired)) {
+			MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP);
 			subflow->mpc_drop = 1;
 			mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow);
 		} else {