Merge branch 'mptcp-prevent-mpc-handshake-on-port-based-signal-endpoints'

Matthieu Baerts says:

====================
mptcp: prevent MPC handshake on port-based signal endpoints

MPTCP connection requests toward a listening socket created by the
in-kernel PM for a port based signal endpoint will never be accepted,
they need to be explicitly rejected.

- Patch 1: Explicitly reject such requests. A fix for >= v5.12.

- Patch 2: Cover this case in the MPTCP selftests to avoid regressions.
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
v1: https://lore.kernel.org/20240908180620.822579-1-xiyou.wangcong@gmail.com

Link: https://lore.kernel.org/a5289a0d-2557-40b8-9575-6f1a0bbf06e4@redhat.com
====================

Link: https://patch.msgid.link/20241014-net-mptcp-mpc-port-endp-v2-0-7faea8e6b6ae@kernel.orgSigned-off-by: Jakub Kicinski <kuba@kernel.org>

net/mptcp/mib.c

@@ -17,6 +17,7 @@ static const struct snmp_mib mptcp_snmp_list[] = {
 	SNMP_MIB_ITEM("MPCapableFallbackSYNACK", MPTCP_MIB_MPCAPABLEACTIVEFALLBACK),
 	SNMP_MIB_ITEM("MPCapableSYNTXDrop", MPTCP_MIB_MPCAPABLEACTIVEDROP),
 	SNMP_MIB_ITEM("MPCapableSYNTXDisabled", MPTCP_MIB_MPCAPABLEACTIVEDISABLED),
+	SNMP_MIB_ITEM("MPCapableEndpAttempt", MPTCP_MIB_MPCAPABLEENDPATTEMPT),
 	SNMP_MIB_ITEM("MPFallbackTokenInit", MPTCP_MIB_TOKENFALLBACKINIT),
 	SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
 	SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),

net/mptcp/mib.h

@@ -12,6 +12,7 @@ enum linux_mptcp_mib_field {
 	MPTCP_MIB_MPCAPABLEACTIVEFALLBACK, /* Client-side fallback during 3-way handshake */
 	MPTCP_MIB_MPCAPABLEACTIVEDROP,	/* Client-side fallback due to a MPC drop */
 	MPTCP_MIB_MPCAPABLEACTIVEDISABLED, /* Client-side disabled due to past issues */
+	MPTCP_MIB_MPCAPABLEENDPATTEMPT,	/* Prohibited MPC to port-based endp */
 	MPTCP_MIB_TOKENFALLBACKINIT,	/* Could not init/allocate token */
 	MPTCP_MIB_RETRANSSEGS,		/* Segments retransmitted at the MPTCP-level */
 	MPTCP_MIB_JOINNOTOKEN,		/* Received MP_JOIN but the token was not found */

net/mptcp/pm_netlink.c

@@ -1121,6 +1121,7 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk,
 	 */
 	inet_sk_state_store(newsk, TCP_LISTEN);
 	lock_sock(ssk);
+	WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true);
 	err = __inet_listen_sk(ssk, backlog);
 	if (!err)
 		mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED);

net/mptcp/protocol.h

@@ -535,6 +535,7 @@ struct mptcp_subflow_context {
 		__unused : 8;
 	bool	data_avail;
 	bool	scheduled;
+	bool	pm_listener;	    /* a listener managed by the kernel PM? */
 	u32	remote_nonce;
 	u64	thmac;
 	u32	local_nonce;

net/mptcp/subflow.c

@@ -132,6 +132,13 @@ static void subflow_add_reset_reason(struct sk_buff *skb, u8 reason)
 	}
 }
 
+static int subflow_reset_req_endp(struct request_sock *req, struct sk_buff *skb)
+{
+	SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEENDPATTEMPT);
+	subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT);
+	return -EPERM;
+}
+
 /* Init mptcp request socket.
  *
  * Returns an error code if a JOIN has failed and a TCP reset
@@ -165,6 +172,8 @@ static int subflow_check_req(struct request_sock *req,
 	if (opt_mp_capable) {
 		SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVE);
 
+		if (unlikely(listener->pm_listener))
+			return subflow_reset_req_endp(req, skb);
 		if (opt_mp_join)
 			return 0;
 	} else if (opt_mp_join) {
@@ -172,6 +181,8 @@ static int subflow_check_req(struct request_sock *req,
 
 		if (mp_opt.backup)
 			SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
+	} else if (unlikely(listener->pm_listener)) {
+		return subflow_reset_req_endp(req, skb);
 	}
 
 	if (opt_mp_capable && listener->request_mptcp) {

tools/testing/selftests/net/mptcp/mptcp_join.sh

@@ -23,6 +23,7 @@ tmpfile=""
 cout=""
 err=""
 capout=""
+cappid=""
 ns1=""
 ns2=""
 iptables="iptables"
@@ -887,40 +888,62 @@ check_cestab()
 	fi
 }
 
-do_transfer()
+cond_start_capture()
 {
-	local listener_ns="$1"
-	local connector_ns="$2"
-	local cl_proto="$3"
-	local srv_proto="$4"
-	local connect_addr="$5"
-
-	local port=$((10000 + MPTCP_LIB_TEST_COUNTER - 1))
-	local cappid
-	local FAILING_LINKS=${FAILING_LINKS:-""}
-	local fastclose=${fastclose:-""}
-	local speed=${speed:-"fast"}
+	local ns="$1"
 
-	:> "$cout"
-	:> "$sout"
 	:> "$capout"
 
 	if $capture; then
-		local capuser
-		if [ -z $SUDO_USER ] ; then
+		local capuser capfile
+		if [ -z $SUDO_USER ]; then
 			capuser=""
 		else
 			capuser="-Z $SUDO_USER"
 		fi
 
-		capfile=$(printf "mp_join-%02u-%s.pcap" "$MPTCP_LIB_TEST_COUNTER" "${listener_ns}")
+		capfile=$(printf "mp_join-%02u-%s.pcap" "$MPTCP_LIB_TEST_COUNTER" "$ns")
 
 		echo "Capturing traffic for test $MPTCP_LIB_TEST_COUNTER into $capfile"
-		ip netns exec ${listener_ns} tcpdump -i any -s 65535 -B 32768 $capuser -w $capfile > "$capout" 2>&1 &
+		ip netns exec "$ns" tcpdump -i any -s 65535 -B 32768 $capuser -w "$capfile" > "$capout" 2>&1 &
 		cappid=$!
 
 		sleep 1
 	fi
+}
+
+cond_stop_capture()
+{
+	if $capture; then
+		sleep 1
+		kill $cappid
+		cat "$capout"
+	fi
+}
+
+get_port()
+{
+	echo "$((10000 + MPTCP_LIB_TEST_COUNTER - 1))"
+}
+
+do_transfer()
+{
+	local listener_ns="$1"
+	local connector_ns="$2"
+	local cl_proto="$3"
+	local srv_proto="$4"
+	local connect_addr="$5"
+	local port
+
+	local FAILING_LINKS=${FAILING_LINKS:-""}
+	local fastclose=${fastclose:-""}
+	local speed=${speed:-"fast"}
+	port=$(get_port)
+
+	:> "$cout"
+	:> "$sout"
+
+	cond_start_capture ${listener_ns}
 
 	NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
 		nstat -n
@@ -1007,10 +1030,7 @@ do_transfer()
 	wait $spid
 	local rets=$?
 
-	if $capture; then
-	    sleep 1
-	    kill $cappid
-	fi
+	cond_stop_capture
 
 	NSTAT_HISTORY=/tmp/${listener_ns}.nstat ip netns exec ${listener_ns} \
 		nstat | grep Tcp > /tmp/${listener_ns}.out
@@ -1026,7 +1046,6 @@ do_transfer()
 		ip netns exec ${connector_ns} ss -Menita 1>&2 -o "dport = :$port"
 		cat /tmp/${connector_ns}.out
 
-		cat "$capout"
 		return 1
 	fi
 
@@ -1043,13 +1062,7 @@ do_transfer()
 	fi
 	rets=$?
 
-	if [ $retc -eq 0 ] && [ $rets -eq 0 ];then
-		cat "$capout"
-		return 0
-	fi
-
-	cat "$capout"
-	return 1
+	[ $retc -eq 0 ] && [ $rets -eq 0 ]
 }
 
 make_file()
@@ -2873,6 +2886,32 @@ verify_listener_events()
 	fail_test
 }
 
+chk_mpc_endp_attempt()
+{
+	local retl=$1
+	local attempts=$2
+
+	print_check "Connect"
+
+	if [ ${retl} = 124 ]; then
+		fail_test "timeout on connect"
+	elif [ ${retl} = 0 ]; then
+		fail_test "unexpected successful connect"
+	else
+		print_ok
+
+		print_check "Attempts"
+		count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPCapableEndpAttempt")
+		if [ -z "$count" ]; then
+			print_skip
+		elif [ "$count" != "$attempts" ]; then
+			fail_test "got ${count} MPC attempt[s] on port-based endpoint, expected ${attempts}"
+		else
+			print_ok
+		fi
+	fi
+}
+
 add_addr_ports_tests()
 {
 	# signal address with port
@@ -2963,6 +3002,22 @@ add_addr_ports_tests()
 		chk_join_nr 2 2 2
 		chk_add_nr 2 2 2
 	fi
+
+	if reset "port-based signal endpoint must not accept mpc"; then
+		local port retl count
+		port=$(get_port)
+
+		cond_start_capture ${ns1}
+		pm_nl_add_endpoint ${ns1} 10.0.2.1 flags signal port ${port}
+		mptcp_lib_wait_local_port_listen ${ns1} ${port}
+
+		timeout 1 ip netns exec ${ns2} \
+			./mptcp_connect -t ${timeout_poll} -p $port -s MPTCP 10.0.2.1 >/dev/null 2>&1
+		retl=$?
+		cond_stop_capture
+
+		chk_mpc_endp_attempt ${retl} 1
+	fi
 }
 
 syncookies_tests()