Merge branch 'mptcp-make-add_addr-retransmission-timeout-adaptive'

Matthieu Baerts says:

====================
mptcp: make ADD_ADDR retransmission timeout adaptive

Currently, the MPTCP ADD_ADDR notifications are retransmitted after a
fixed timeout controlled by the net.mptcp.add_addr_timeout sysctl knob,
if the corresponding "echo" packets are not received before. This can be
too slow (or too quick), especially with a too cautious default value
set to 2 minutes.

- Patch 1: make ADD_ADDR retransmission timeout adaptive, using the
  TCP's retransmission timeout. The corresponding sysctl knob is now
  used as a maximum value.

- Patch 2: now that these ADD_ADDR retransmissions can happen faster,
  all MPTCP Join subtests checking ADD_ADDR counters accept more
  ADD_ADDR than expected (if any). This is aligned with the previous
  behaviour, when the ADD_ADDR RTO was lowered down to 1 second.

- Patch 3: Some CIs have reported that some MPTCP Join signalling tests
  were unstable. It seems that it is due to the time it can take in slow
  environments to send a bunch of ADD_ADDR notifications and wait each
  time for their echo reply. Use a longer transfer to avoid such errors.

v1: https://lore.kernel.org/d5397026-92eb-4a43-9534-954b43ab9305@kernel.org
====================

Link: https://patch.msgid.link/20250907-net-next-mptcp-add_addr-retrans-adapt-v1-0-824cc805772b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 40 insertions, 21 deletions

diff --git a/Documentation/networking/mptcp-sysctl.rst b/Documentation/networking/mptcp-sysctl.rst
index 1683c139821e..1eb6af26b4a7 100644
--- a/Documentation/networking/mptcp-sysctl.rst
+++ b/Documentation/networking/mptcp-sysctl.rst
@@ -8,9 +8,11 @@ MPTCP Sysfs variables
 ===============================
 
 add_addr_timeout - INTEGER (seconds)
-	Set the timeout after which an ADD_ADDR control message will be
-	resent to an MPTCP peer that has not acknowledged a previous
-	ADD_ADDR message.
+	Set the maximum value of timeout after which an ADD_ADDR control message
+	will be resent to an MPTCP peer that has not acknowledged a previous
+	ADD_ADDR message. A dynamically estimated retransmission timeout based
+	on the estimated connection round-trip-time is used if this value is
+	lower than the maximum one.
 
 	Do not retransmit if set to 0.
 
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 136a380602ca..204e1f61212e 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -268,6 +268,27 @@ int mptcp_pm_mp_prio_send_ack(struct mptcp_sock *msk,
 	return -EINVAL;
 }
 
+static unsigned int mptcp_adjust_add_addr_timeout(struct mptcp_sock *msk)
+{
+	const struct net *net = sock_net((struct sock *)msk);
+	unsigned int rto = mptcp_get_add_addr_timeout(net);
+	struct mptcp_subflow_context *subflow;
+	unsigned int max = 0;
+
+	mptcp_for_each_subflow(msk, subflow) {
+		struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+		struct inet_connection_sock *icsk = inet_csk(ssk);
+
+		if (icsk->icsk_rto > max)
+			max = icsk->icsk_rto;
+	}
+
+	if (max && max < rto)
+		rto = max;
+
+	return rto;
+}
+
 static void mptcp_pm_add_timer(struct timer_list *timer)
 {
 	struct mptcp_pm_add_entry *entry = timer_container_of(entry, timer,
@@ -292,7 +313,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 		goto out;
 	}
 
-	timeout = mptcp_get_add_addr_timeout(sock_net(sk));
+	timeout = mptcp_adjust_add_addr_timeout(msk);
 	if (!timeout)
 		goto out;
 
@@ -307,7 +328,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
 
 	if (entry->retrans_times < ADD_ADDR_RETRANS_MAX)
 		sk_reset_timer(sk, timer,
-			       jiffies + timeout);
+			       jiffies + (timeout << entry->retrans_times));
 
 	spin_unlock_bh(&msk->pm.lock);
 
@@ -348,7 +369,6 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 {
 	struct mptcp_pm_add_entry *add_entry = NULL;
 	struct sock *sk = (struct sock *)msk;
-	struct net *net = sock_net(sk);
 	unsigned int timeout;
 
 	lockdep_assert_held(&msk->pm.lock);
@@ -374,7 +394,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
 
 	timer_setup(&add_entry->add_timer, mptcp_pm_add_timer, 0);
 reset_timer:
-	timeout = mptcp_get_add_addr_timeout(net);
+	timeout = mptcp_adjust_add_addr_timeout(msk);
 	if (timeout)
 		sk_reset_timer(sk, &add_entry->add_timer, jiffies + timeout);
 
diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 2f046167a0b6..b41cebfa1f92 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -358,6 +358,7 @@ reset_with_add_addr_timeout()
 		tables="${ip6tables}"
 	fi
 
+	# set a maximum, to avoid too long timeout with exponential backoff
 	ip netns exec $ns1 sysctl -q net.mptcp.add_addr_timeout=1
 
 	if ! ip netns exec $ns2 $tables -A OUTPUT -p tcp \
@@ -1669,7 +1670,6 @@ chk_add_nr()
 	local tx=""
 	local rx=""
 	local count
-	local timeout
 
 	if [[ $ns_invert = "invert" ]]; then
 		ns_tx=$ns2
@@ -1678,15 +1678,13 @@ chk_add_nr()
 		rx=" server"
 	fi
 
-	timeout=$(ip netns exec ${ns_tx} sysctl -n net.mptcp.add_addr_timeout)
-
 	print_check "add addr rx${rx}"
 	count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtAddAddr")
 	if [ -z "$count" ]; then
 		print_skip
-	# if the test configured a short timeout tolerate greater then expected
-	# add addrs options, due to retransmissions
-	elif [ "$count" != "$add_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_nr" ]; }; then
+	# Tolerate more ADD_ADDR then expected (if any), due to retransmissions
+	elif [ "$count" != "$add_nr" ] &&
+	     { [ "$add_nr" -eq 0 ] || [ "$count" -lt "$add_nr" ]; }; then
 		fail_test "got $count ADD_ADDR[s] expected $add_nr"
 	else
 		print_ok
@@ -1774,18 +1772,15 @@ chk_add_tx_nr()
 {
 	local add_tx_nr=$1
 	local echo_tx_nr=$2
-	local timeout
 	local count
 
-	timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
-
 	print_check "add addr tx"
 	count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtAddAddrTx")
 	if [ -z "$count" ]; then
 		print_skip
-	# if the test configured a short timeout tolerate greater then expected
-	# add addrs options, due to retransmissions
-	elif [ "$count" != "$add_tx_nr" ] && { [ "$timeout" -gt 1 ] || [ "$count" -lt "$add_tx_nr" ]; }; then
+	# Tolerate more ADD_ADDR then expected (if any), due to retransmissions
+	elif [ "$count" != "$add_tx_nr" ] &&
+	     { [ "$add_tx_nr" -eq 0 ] || [ "$count" -lt "$add_tx_nr" ]; }; then
 		fail_test "got $count ADD_ADDR[s] TX, expected $add_tx_nr"
 	else
 		print_ok
@@ -2273,7 +2268,8 @@ signal_address_tests()
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.4.1 flags signal
 		pm_nl_set_limits $ns2 3 3
-		run_tests $ns1 $ns2 10.0.1.1
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3
 		chk_add_nr 3 3
 	fi
@@ -2285,7 +2281,8 @@ signal_address_tests()
 		pm_nl_add_endpoint $ns1 10.0.3.1 flags signal
 		pm_nl_add_endpoint $ns1 10.0.14.1 flags signal
 		pm_nl_set_limits $ns2 3 3
-		run_tests $ns1 $ns2 10.0.1.1
+		speed=slow \
+			run_tests $ns1 $ns2 10.0.1.1
 		join_syn_tx=3 \
 			chk_join_nr 1 1 1
 		chk_add_nr 3 3