From 96939cec994070aa5df852c10fad5fc303a97ea3 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:52:20 +0200 Subject: [PATCH 1/5] mptcp: set remote_deny_join_id0 on SYN recv When a SYN containing the 'C' flag (deny join id0) was received, this piece of information was not propagated to the path-manager. Even if this flag is mainly set on the server side, a client can also tell the server it cannot try to establish new subflows to the client's initial IP address and port. The server's PM should then record such info when received, and before sending events about the new connection. Fixes: df377be38725 ("mptcp: add deny_join_id0 in mptcp_options_received") Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-1-40171884ade8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 3f1b62a9fe88..f31a3a79531a 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -883,6 +883,10 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, ctx->subflow_id = 1; owner = mptcp_sk(ctx->conn); + + if (mp_opt.deny_join_id0) + WRITE_ONCE(owner->pm.remote_deny_join_id0, true); + mptcp_pm_new_connection(owner, child, 1); /* with OoO packets we can reach here without ingress From 2293c57484ae64c9a3c847c8807db8c26a3a4d41 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:52:21 +0200 Subject: [PATCH 2/5] mptcp: pm: nl: announce deny-join-id0 flag During the connection establishment, a peer can tell the other one that it cannot establish new subflows to the initial IP address and port by setting the 'C' flag [1]. Doing so makes sense when the sender is behind a strict NAT, operating behind a legacy Layer 4 load balancer, or using anycast IP address for example. When this 'C' flag is set, the path-managers must then not try to establish new subflows to the other peer's initial IP address and port. The in-kernel PM has access to this info, but the userspace PM didn't. The RFC8684 [1] is strict about that: (...) therefore the receiver MUST NOT try to open any additional subflows toward this address and port. So it is important to tell the userspace about that as it is responsible for the respect of this flag. When a new connection is created and established, the Netlink events now contain the existing but not currently used 'flags' attribute. When MPTCP_PM_EV_FLAG_DENY_JOIN_ID0 is set, it means no other subflows to the initial IP address and port -- info that are also part of the event -- can be established. Link: https://datatracker.ietf.org/doc/html/rfc8684#section-3.1-20.6 [1] Fixes: 702c2f646d42 ("mptcp: netlink: allow userspace-driven subflow establishment") Reported-by: Marek Majkowski Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/532 Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-2-40171884ade8@kernel.org Signed-off-by: Jakub Kicinski --- Documentation/netlink/specs/mptcp_pm.yaml | 4 ++-- include/uapi/linux/mptcp.h | 2 ++ include/uapi/linux/mptcp_pm.h | 4 ++-- net/mptcp/pm_netlink.c | 7 +++++++ 4 files changed, 13 insertions(+), 4 deletions(-) diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml index d15335684ec3..d1b4829b580a 100644 --- a/Documentation/netlink/specs/mptcp_pm.yaml +++ b/Documentation/netlink/specs/mptcp_pm.yaml @@ -28,13 +28,13 @@ definitions: traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, server-side. + dport, server-side, [flags]. - name: established doc: >- A MPTCP connection is established (can start new subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, sport, - dport, server-side. + dport, server-side, [flags]. - name: closed doc: >- diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 67d015df8893..5fd5b4cf75ca 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -31,6 +31,8 @@ #define MPTCP_INFO_FLAG_FALLBACK _BITUL(0) #define MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED _BITUL(1) +#define MPTCP_PM_EV_FLAG_DENY_JOIN_ID0 _BITUL(0) + #define MPTCP_PM_ADDR_FLAG_SIGNAL (1 << 0) #define MPTCP_PM_ADDR_FLAG_SUBFLOW (1 << 1) #define MPTCP_PM_ADDR_FLAG_BACKUP (1 << 2) diff --git a/include/uapi/linux/mptcp_pm.h b/include/uapi/linux/mptcp_pm.h index 6ac84b2f636c..7359d34da446 100644 --- a/include/uapi/linux/mptcp_pm.h +++ b/include/uapi/linux/mptcp_pm.h @@ -16,10 +16,10 @@ * good time to allocate memory and send ADD_ADDR if needed. Depending on the * traffic-patterns it can take a long time until the MPTCP_EVENT_ESTABLISHED * is sent. Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_ESTABLISHED: A MPTCP connection is established (can start new * subflows). Attributes: token, family, saddr4 | saddr6, daddr4 | daddr6, - * sport, dport, server-side. + * sport, dport, server-side, [flags]. * @MPTCP_EVENT_CLOSED: A MPTCP connection has stopped. Attribute: token. * @MPTCP_EVENT_ANNOUNCED: A new address has been announced by the peer. * Attributes: token, rem_id, family, daddr4 | daddr6 [, dport]. diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 50aaf259959a..ce7d42d3bd00 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -408,6 +408,7 @@ static int mptcp_event_created(struct sk_buff *skb, const struct sock *ssk) { int err = nla_put_u32(skb, MPTCP_ATTR_TOKEN, READ_ONCE(msk->token)); + u16 flags = 0; if (err) return err; @@ -415,6 +416,12 @@ static int mptcp_event_created(struct sk_buff *skb, if (nla_put_u8(skb, MPTCP_ATTR_SERVER_SIDE, READ_ONCE(msk->pm.server_side))) return -EMSGSIZE; + if (READ_ONCE(msk->pm.remote_deny_join_id0)) + flags |= MPTCP_PM_EV_FLAG_DENY_JOIN_ID0; + + if (flags && nla_put_u16(skb, MPTCP_ATTR_FLAGS, flags)) + return -EMSGSIZE; + return mptcp_event_add_subflow(skb, ssk); } From 24733e193a0d68f20d220e86da0362460c9aa812 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:52:22 +0200 Subject: [PATCH 3/5] selftests: mptcp: userspace pm: validate deny-join-id0 flag The previous commit adds the MPTCP_PM_EV_FLAG_DENY_JOIN_ID0 flag. Make sure it is correctly announced by the other peer when it has been received. pm_nl_ctl will now display 'deny_join_id0:1' when monitoring the events, and when this flag was set by the other peer. The 'Fixes' tag here below is the same as the one from the previous commit: this patch here is not fixing anything wrong in the selftests, but it validates the previous fix for an issue introduced by this commit ID. Fixes: 702c2f646d42 ("mptcp: netlink: allow userspace-driven subflow establishment") Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-3-40171884ade8@kernel.org Signed-off-by: Jakub Kicinski --- tools/testing/selftests/net/mptcp/pm_nl_ctl.c | 7 +++++++ tools/testing/selftests/net/mptcp/userspace_pm.sh | 14 +++++++++++--- 2 files changed, 18 insertions(+), 3 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c index 994a556f46c1..93fea3442216 100644 --- a/tools/testing/selftests/net/mptcp/pm_nl_ctl.c +++ b/tools/testing/selftests/net/mptcp/pm_nl_ctl.c @@ -188,6 +188,13 @@ static int capture_events(int fd, int event_group) fprintf(stderr, ",error:%u", *(__u8 *)RTA_DATA(attrs)); else if (attrs->rta_type == MPTCP_ATTR_SERVER_SIDE) fprintf(stderr, ",server_side:%u", *(__u8 *)RTA_DATA(attrs)); + else if (attrs->rta_type == MPTCP_ATTR_FLAGS) { + __u16 flags = *(__u16 *)RTA_DATA(attrs); + + /* only print when present, easier */ + if (flags & MPTCP_PM_EV_FLAG_DENY_JOIN_ID0) + fprintf(stderr, ",deny_join_id0:1"); + } attrs = RTA_NEXT(attrs, msg_len); } diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 970c329735ff..3d45991f24ed 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -201,6 +201,9 @@ make_connection() is_v6="v4" fi + # set this on the client side only: will not affect the rest + ip netns exec "$ns2" sysctl -q net.mptcp.allow_join_initial_addr_port=0 + :>"$client_evts" :>"$server_evts" @@ -223,23 +226,28 @@ make_connection() local client_token local client_port local client_serverside + local client_nojoin local server_token local server_serverside + local server_nojoin client_token=$(mptcp_lib_evts_get_info token "$client_evts") client_port=$(mptcp_lib_evts_get_info sport "$client_evts") client_serverside=$(mptcp_lib_evts_get_info server_side "$client_evts") + client_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$client_evts") server_token=$(mptcp_lib_evts_get_info token "$server_evts") server_serverside=$(mptcp_lib_evts_get_info server_side "$server_evts") + server_nojoin=$(mptcp_lib_evts_get_info deny_join_id0 "$server_evts") print_test "Established IP${is_v6} MPTCP Connection ns2 => ns1" - if [ "$client_token" != "" ] && [ "$server_token" != "" ] && [ "$client_serverside" = 0 ] && - [ "$server_serverside" = 1 ] + if [ "${client_token}" != "" ] && [ "${server_token}" != "" ] && + [ "${client_serverside}" = 0 ] && [ "${server_serverside}" = 1 ] && + [ "${client_nojoin:-0}" = 0 ] && [ "${server_nojoin:-0}" = 1 ] then test_pass print_title "Connection info: ${client_addr}:${client_port} -> ${connect_addr}:${app_port}" else - test_fail "Expected tokens (c:${client_token} - s:${server_token}) and server (c:${client_serverside} - s:${server_serverside})" + test_fail "Expected tokens (c:${client_token} - s:${server_token}), server (c:${client_serverside} - s:${server_serverside}), nojoin (c:${client_nojoin} - s:${server_nojoin})" mptcp_lib_result_print_all_tap exit ${KSFT_FAIL} fi From 92da495cb65719583aa06bc946aeb18a10e1e6e2 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 12 Sep 2025 14:52:23 +0200 Subject: [PATCH 4/5] mptcp: tfo: record 'deny join id0' info When TFO is used, the check to see if the 'C' flag (deny join id0) was set was bypassed. This flag can be set when TFO is used, so the check should also be done when TFO is used. Note that the set_fully_established label is also used when a 4th ACK is received. In this case, deny_join_id0 will not be set. Fixes: dfc8d0603033 ("mptcp: implement delayed seq generation for passive fastopen") Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-4-40171884ade8@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 2a8ea28442b2..1103b3341a70 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -985,13 +985,13 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, return false; } - if (mp_opt->deny_join_id0) - WRITE_ONCE(msk->pm.remote_deny_join_id0, true); - if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); set_fully_established: + if (mp_opt->deny_join_id0) + WRITE_ONCE(msk->pm.remote_deny_join_id0, true); + mptcp_data_lock((struct sock *)msk); __mptcp_subflow_fully_established(msk, subflow, mp_opt); mptcp_data_unlock((struct sock *)msk); From b86418beade11d45540a2d20c4ec1128849b6c27 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 12 Sep 2025 14:52:24 +0200 Subject: [PATCH 5/5] selftests: mptcp: sockopt: fix error messages This patch fixes several issues in the error reporting of the MPTCP sockopt selftest: 1. Fix diff not printed: The error messages for counter mismatches had the actual difference ('diff') as argument, but it was missing in the format string. Displaying it makes the debugging easier. 2. Fix variable usage: The error check for 'mptcpi_bytes_acked' incorrectly used 'ret2' (sent bytes) for both the expected value and the difference calculation. It now correctly uses 'ret' (received bytes), which is the expected value for bytes_acked. 3. Fix off-by-one in diff: The calculation for the 'mptcpi_rcv_delta' diff was 's.mptcpi_rcv_delta - ret', which is off-by-one. It has been corrected to 's.mptcpi_rcv_delta - (ret + 1)' to match the expected value in the condition above it. Fixes: 5dcff89e1455 ("selftests: mptcp: explicitly tests aggregate counters") Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-5-40171884ade8@kernel.org Signed-off-by: Jakub Kicinski --- .../testing/selftests/net/mptcp/mptcp_sockopt.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c index e934dd26a59d..112c07c4c37a 100644 --- a/tools/testing/selftests/net/mptcp/mptcp_sockopt.c +++ b/tools/testing/selftests/net/mptcp/mptcp_sockopt.c @@ -667,22 +667,26 @@ static void process_one_client(int fd, int pipefd) do_getsockopts(&s, fd, ret, ret2); if (s.mptcpi_rcv_delta != (uint64_t)ret + 1) - xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64, s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - ret); + xerror("mptcpi_rcv_delta %" PRIu64 ", expect %" PRIu64 ", diff %" PRId64, + s.mptcpi_rcv_delta, ret + 1, s.mptcpi_rcv_delta - (ret + 1)); /* be nice when running on top of older kernel */ if (s.pkt_stats_avail) { if (s.last_sample.mptcpi_bytes_sent != ret2) - xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_sent %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_sent, ret2, s.last_sample.mptcpi_bytes_sent - ret2); if (s.last_sample.mptcpi_bytes_received != ret) - xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64, + xerror("mptcpi_bytes_received %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, s.last_sample.mptcpi_bytes_received, ret, s.last_sample.mptcpi_bytes_received - ret); if (s.last_sample.mptcpi_bytes_acked != ret) - xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64, - s.last_sample.mptcpi_bytes_acked, ret2, - s.last_sample.mptcpi_bytes_acked - ret2); + xerror("mptcpi_bytes_acked %" PRIu64 ", expect %" PRIu64 + ", diff %" PRId64, + s.last_sample.mptcpi_bytes_acked, ret, + s.last_sample.mptcpi_bytes_acked - ret); } close(fd);