commit 4b1ff850e0c1aacc23e923ed22989b827b9808f9 upstream.
When servers set the C-flag in their MP_CAPABLE to tell clients not to create subflows to the initial address and port, clients will likely not use their other endpoints. That's because the in-kernel path-manager uses the 'subflow' endpoints to create subflows only to the initial address and port.
If the limits have not been modified to accept ADD_ADDR, the client doesn't try to establish new subflows. If the limits accept ADD_ADDR, the routing routes will be used to select the source IP.
The C-flag is typically set when the server is operating behind a legacy Layer 4 load balancer, or using anycast IP address. Clients having their different 'subflow' endpoints setup, don't end up creating multiple subflows as expected, and causing some deployment issues.
A special case is then added here: when servers set the C-flag in the MPC and directly sends an ADD_ADDR, this single ADD_ADDR is accepted. The 'subflows' endpoints will then be used with this new remote IP and port. This exception is only allowed when the ADD_ADDR is sent immediately after the 3WHS, and makes the client switching to the 'fully established' mode. After that, 'select_local_address()' will not be able to find any subflows, because 'id_avail_bitmap' will be filled in mptcp_pm_create_subflow_or_signal_addr(), when switching to 'fully established' mode.
Fixes: df377be38725 ("mptcp: add deny_join_id0 in mptcp_options_received") Cc: stable@vger.kernel.org Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/536 Reviewed-by: Geliang Tang geliang@kernel.org Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org Link: https://patch.msgid.link/20250925-net-next-mptcp-c-flag-laminar-v1-1-ad126cc... Signed-off-by: Jakub Kicinski kuba@kernel.org [ Conflict in pm.c, because commit 498d7d8b75f1 ("mptcp: pm: remove '_nl' from mptcp_pm_nl_is_init_remote_addr") renamed an helper in the context, and it is not in this version. The same new code can be applied at the same place. Conflict in pm_kernel.c, because the modified code has been moved from pm_netlink.c to pm_kernel.c in commit 8617e85e04bd ("mptcp: pm: split in-kernel PM specific code"), which is not in this version. The resolution is easy: simply by applying the patch where 'pm_kernel.c' has been replaced 'pm_netlink.c'. 'patch --merge' managed to apply this modified patch without creating any conflicts. ] Signed-off-by: Matthieu Baerts (NGI0) matttbe@kernel.org --- net/mptcp/pm.c | 7 ++++-- net/mptcp/pm_netlink.c | 50 +++++++++++++++++++++++++++++++++++++++++- net/mptcp/protocol.h | 8 +++++++ 3 files changed, 62 insertions(+), 3 deletions(-)
diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 2c8815daf5b0..1b7541206a70 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -226,9 +226,12 @@ void mptcp_pm_add_addr_received(const struct sock *ssk, } else { __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP); } - /* id0 should not have a different address */ + /* - id0 should not have a different address + * - special case for C-flag: linked to fill_local_addresses_vec() + */ } else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) || - (addr->id > 0 && !READ_ONCE(pm->accept_addr))) { + (addr->id > 0 && !READ_ONCE(pm->accept_addr) && + !mptcp_pm_add_addr_c_flag_case(msk))) { mptcp_pm_announce_addr(msk, addr, true); mptcp_pm_add_addr_send_ack(msk); } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) { diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 463c2e7956d5..8d5406515c30 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -674,10 +674,12 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; unsigned int subflows_max; + bool c_flag_case; int i = 0;
pernet = pm_nl_get_pernet_from_msk(msk); subflows_max = mptcp_pm_get_subflows_max(msk); + c_flag_case = remote->id && mptcp_pm_add_addr_c_flag_case(msk);
mptcp_local_address((struct sock_common *)msk, &mpc_addr);
@@ -690,12 +692,27 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, continue;
if (msk->pm.subflows < subflows_max) { + bool is_id0; + locals[i].addr = entry->addr; locals[i].flags = entry->flags; locals[i].ifindex = entry->ifindex;
+ is_id0 = mptcp_addresses_equal(&locals[i].addr, + &mpc_addr, + locals[i].addr.port); + + if (c_flag_case && + (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) { + __clear_bit(locals[i].addr.id, + msk->pm.id_avail_bitmap); + + if (!is_id0) + msk->pm.local_addr_used++; + } + /* Special case for ID0: set the correct ID */ - if (mptcp_addresses_equal(&locals[i].addr, &mpc_addr, locals[i].addr.port)) + if (is_id0) locals[i].addr.id = 0;
msk->pm.subflows++; @@ -704,6 +721,37 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, } rcu_read_unlock();
+ /* Special case: peer sets the C flag, accept one ADD_ADDR if default + * limits are used -- accepting no ADD_ADDR -- and use subflow endpoints + */ + if (!i && c_flag_case) { + unsigned int local_addr_max = mptcp_pm_get_local_addr_max(msk); + + while (msk->pm.local_addr_used < local_addr_max && + msk->pm.subflows < subflows_max) { + struct mptcp_pm_local *local = &locals[i]; + + if (!select_local_address(pernet, msk, local)) + break; + + __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); + + if (!mptcp_pm_addr_families_match(sk, &local->addr, + remote)) + continue; + + if (mptcp_addresses_equal(&local->addr, &mpc_addr, + local->addr.port)) + continue; + + msk->pm.local_addr_used++; + msk->pm.subflows++; + i++; + } + + return i; + } + /* If the array is empty, fill in the single * 'IPADDRANY' local address */ diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 6f191b125978..9653fee227ab 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1172,6 +1172,14 @@ static inline void mptcp_pm_close_subflow(struct mptcp_sock *msk) spin_unlock_bh(&msk->pm.lock); }
+static inline bool mptcp_pm_add_addr_c_flag_case(struct mptcp_sock *msk) +{ + return READ_ONCE(msk->pm.remote_deny_join_id0) && + msk->pm.local_addr_used == 0 && + mptcp_pm_get_add_addr_accept_max(msk) == 0 && + msk->pm.subflows < mptcp_pm_get_subflows_max(msk); +} + void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk);
static inline struct mptcp_ext *mptcp_get_ext(const struct sk_buff *skb)