The sockmap feature allows bpf syscall from userspace, or based
on bpf sockops, replacing the sk_prot of sockets during protocol stack
processing with sockmap's custom read/write interfaces.
'''
tcp_rcv_state_process()
syn_recv_sock()/subflow_syn_recv_sock()
tcp_init_transfer(BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB)
bpf_skops_established <== sockops
bpf_sock_map_update(sk) <== call bpf helper
tcp_bpf_update_proto() <== update sk_prot
'''
When the server has MPTCP enabled but the client sends a TCP SYN
without MPTCP, subflow_syn_recv_sock() performs a fallback on the
subflow, replacing the subflow sk's sk_prot with the native sk_prot.
'''
subflow_syn_recv_sock()
subflow_ulp_fallback()
subflow_drop_ctx()
mptcp_subflow_ops_undo_override()
'''
Then, this subflow can be normally used by sockmap, which replaces the
native sk_prot with sockmap's custom sk_prot. The issue occurs when the
user executes accept::mptcp_stream_accept::mptcp_fallback_tcp_ops().
Here, it uses sk->sk_prot to compare with the native sk_prot, but this
is incorrect when sockmap is used, as we may incorrectly set
sk->sk_socket->ops.
This fix uses the more generic sk_family for the comparison instead.
Additionally, this also prevents a WARNING from occurring:
result from ./scripts/decode_stacktrace.sh:
------------[ cut here ]------------
WARNING: CPU: 0 PID: 337 at net/mptcp/protocol.c:68 mptcp_stream_accept \
(net/mptcp/protocol.c:4005)
Modules linked in:
...
PKRU: 55555554
Call Trace:
<TASK>
do_accept (net/socket.c:1989)
__sys_accept4 (net/socket.c:2028 net/socket.c:2057)
__x64_sys_accept (net/socket.c:2067)
x64_sys_call (arch/x86/entry/syscall_64.c:41)
do_syscall_64 (arch/x86/entry/syscall_64.c:63 arch/x86/entry/syscall_64.c:94)
entry_SYSCALL_64_after_hwframe (arch/x86/entry/entry_64.S:130)
RIP: 0033:0x7f87ac92b83d
---[ end trace 0000000000000000 ]---
Fixes: 0b4f33def7 ("mptcp: fix tcp fallback crash")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Jakub Sitnicki <jakub@cloudflare.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20251111060307.194196-3-jiayuan.chen@linux.dev
The sockmap feature allows bpf syscall from userspace, or based on bpf
sockops, replacing the sk_prot of sockets during protocol stack processing
with sockmap's custom read/write interfaces.
'''
tcp_rcv_state_process()
subflow_syn_recv_sock()
tcp_init_transfer(BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB)
bpf_skops_established <== sockops
bpf_sock_map_update(sk) <== call bpf helper
tcp_bpf_update_proto() <== update sk_prot
'''
Consider two scenarios:
1. When the server has MPTCP enabled and the client also requests MPTCP,
the sk passed to the BPF program is a subflow sk. Since subflows only
handle partial data, replacing their sk_prot is meaningless and will
cause traffic disruption.
2. When the server has MPTCP enabled but the client sends a TCP SYN
without MPTCP, subflow_syn_recv_sock() performs a fallback on the
subflow, replacing the subflow sk's sk_prot with the native sk_prot.
'''
subflow_ulp_fallback()
subflow_drop_ctx()
mptcp_subflow_ops_undo_override()
'''
Subsequently, accept::mptcp_stream_accept::mptcp_fallback_tcp_ops()
converts the subflow to plain TCP.
For the first case, we should prevent it from being combined with sockmap
by setting sk_prot->psock_update_sk_prot to NULL, which will be blocked by
sockmap's own flow.
For the second case, since subflow_syn_recv_sock() has already restored
sk_prot to native tcp_prot/tcpv6_prot, no further action is needed.
Fixes: cec37a6e41 ("mptcp: Handle MP_CAPABLE options for outgoing connections")
Signed-off-by: Jiayuan Chen <jiayuan.chen@linux.dev>
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Cc: <stable@vger.kernel.org>
Link: https://patch.msgid.link/20251111060307.194196-2-jiayuan.chen@linux.dev
Accessing the transmit queue without owning the msk socket lock is
inherently racy, hence __mptcp_check_push() could actually quit early
even when there is pending data.
That in turn could cause unexpected tx lock and timeout.
Dropping the early check avoids the race, implicitly relaying on later
tests under the relevant lock. With such change, all the other
mptcp_send_head() call sites are now under the msk socket lock and we
can additionally drop the now unneeded annotation on the transmit head
pointer accesses.
Fixes: 6e628cd3a8 ("mptcp: use mptcp release_cb for delayed tasks")
Cc: stable@vger.kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Reviewed-by: Geliang Tang <geliang@kernel.org>
Tested-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20251028-net-mptcp-send-timeout-v1-1-38ffff5a9ec8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
The special C-flag case expects the ADD_ADDR to be received when
switching to 'fully-established'. But for various reasons, the ADD_ADDR
could be sent after the "4th ACK", and the special case doesn't work.
On NIPA, the new test validating this special case for the C-flag failed
a few times, e.g.
102 default limits, server deny join id 0
syn rx [FAIL] got 0 JOIN[s] syn rx expected 2
Server ns stats
(...)
MPTcpExtAddAddrTx 1
MPTcpExtEchoAdd 1
Client ns stats
(...)
MPTcpExtAddAddr 1
MPTcpExtEchoAddTx 1
synack rx [FAIL] got 0 JOIN[s] synack rx expected 2
ack rx [FAIL] got 0 JOIN[s] ack rx expected 2
join Rx [FAIL] see above
syn tx [FAIL] got 0 JOIN[s] syn tx expected 2
join Tx [FAIL] see above
I had a suspicion about what the issue could be: the ADD_ADDR might have
been received after the switch to the 'fully-established' state. The
issue was not easy to reproduce. The packet capture shown that the
ADD_ADDR can indeed be sent with a delay, and the client would not try
to establish subflows to it as expected.
A simple fix is not to mark the endpoints as 'used' in the C-flag case,
when looking at creating subflows to the remote initial IP address and
port. In this case, there is no need to try.
Note: newly added fullmesh endpoints will still continue to be used as
expected, thanks to the conditions behind mptcp_pm_add_addr_c_flag_case.
Fixes: 4b1ff850e0 ("mptcp: pm: in-kernel: usable client side with C-flag")
Cc: stable@vger.kernel.org
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20251020-net-mptcp-c-flag-late-add-addr-v1-1-8207030cb0e8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently, upon the reception of an ADD_ADDR (and when the fullmesh flag
is not used), the in-kernel PM will create new subflows using the local
address the routing configuration will pick.
It would be easier to pick local addresses from a selected list of
endpoints, and use it only once, than relying on routing rules.
Use case: both the client (C) and the server (S) have two addresses (a
and b). The client establishes the connection between C(a) and S(a).
Once established, the server announces its additional address S(b). Once
received, the client connects to it using its second address C(b).
Compared to a situation without the 'laminar' endpoint for C(b), the
client didn't use this address C(b) to establish a subflow to the
server's primary address S(a). So at the end, we have:
C S
C(a) --- S(a)
C(b) --- S(b)
In case of a 3rd address on each side (C(c) and S(c)), upon the
reception of an ADD_ADDR with S(c), the client should not pick C(b)
because it has already been used. C(c) should then be used.
Note that this situation is currently possible if C doesn't add any
endpoint, but configure the routing in order to pick C(b) for the route
to S(b), and pick C(c) for the route to S(c). That doesn't sound very
practical because it means knowing in advance the IP addresses that
will be used and announced by the server.
'laminar', like the idea of laminar flows: the different subflows don't
mix with each other on an endpoint, unlike the "turbulent" way traffic
is mixed by 'fullmesh'.
In the code, the new endpoint type is added. Similar to the other
subflow types, an MPTCP_INFO counter is added. While at it, hole are now
commented in struct mptcp_info, to remember next time that these holes
can no longer be used.
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/503
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250925-net-next-mptcp-c-flag-laminar-v1-15-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When receiving an ADD_ADDR right after the 3WHS, the connection will
switch to 'fully established'. It means the MPTCP worker will be called
to treat two events, in this order: ADD_ADDR_RECEIVED, PM_ESTABLISHED.
The MPTCP endpoints cannot have the ID 0, because it is reserved to the
address and port used by the initial subflow. To be able to deal with
this case in different places, msk->mpc_endpoint_id contains the
endpoint ID linked to the initial subflow. This variable was only set
when treating the first PM_ESTABLISHED event, after ADD_ADDR_RECEIVED.
That's why in fill_local_addresses_vec(), the endpoint addresses were
compared with the one of the initial subflow, instead of only comparing
the IDs.
Instead, msk->mpc_endpoint_id is now set when treating ADD_ADDR_RECEIVED
as well, if needed, then the IDs can be compared.
To be able to do so, the code doing that is now in a dedicated helper,
and called from the functions linked to the two actions.
While at it, mptcp_endp_get_local_id() has also been moved up, next to
this new helper, because they are linked, and to be able to use it in
fill_local_addresses_vec() in the next commit.
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250925-net-next-mptcp-c-flag-laminar-v1-14-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
All the 'unsigned int' variables from the 'pm_nl_pernet' structure are
bounded to MPTCP_PM_ADDR_MAX, currently set to 8. The endpoint ID is
also bounded by the protocol to 8-bit. MPTCP_PM_ADDR_MAX, if extended
later, will never over 8-bit.
So no need to use 'unsigned int' variables, 'u8' is enough.
Note that the exposed counters in MPTCP_INFO are already limited to
8-bit, same for pm->extra_subflows, and others. So it seems even better
to limit them to 8-bit.
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250925-net-next-mptcp-c-flag-laminar-v1-13-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
A few variables linked to the in-kernel Path-Manager are confusing, and
it would help current and future developers, to clarify them.
One of them is 'local_addr_max', which in fact represents the maximum
number of 'subflow' endpoints that can be used to create new subflows,
and not the number of local addresses that have been used to create
subflows.
While at it, add an additional name for the corresponding variable in
MPTCP INFO: mptcpi_endp_subflow_max. Not to break the current uAPI, the
new name is added as a 'define' pointing to the former name. This will
then also help userspace devs.
Also move the variable and function next to the other 'endp_X_max' ones.
No functional changes intended.
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-v1-9-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
A few variables linked to the in-kernel Path-Manager are confusing, and
it would help current and future developers, to clarify them.
One of them is 'add_addr_accept_max', which in fact represents the limit
of ADD_ADDR that can be accepted: the limit set via 'ip mptcp limit
add_addr_accepted X' for example. It is not linked to the maximum number
of accepted ADD_ADDR.
While at it, add an additional name for the corresponding variable in
MPTCP INFO: mptcpi_limit_add_addr_accepted. Not to break the current
uAPI, the new name is added as a 'define' pointing to the former name.
This will then also help userspace devs.
No functional changes intended.
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-v1-8-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
A few variables linked to the in-kernel Path-Manager are confusing, and
it would help current and future developers, to clarify them.
One of them is 'add_addr_signal_max', which in fact represents the
maximum number of 'signal' endpoints that can be used to announced
addresses, and not the number of ADD_ADDR that can be signalled.
While at it, add an additional name for the corresponding variable in
MPTCP INFO: mptcpi_endp_signal_max. Not to break the current uAPI, the
new name is added as a 'define' pointing to the former name. This will
then also help userspace devs.
No functional changes intended.
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-v1-7-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
A few variables linked to the in-kernel Path-Manager are confusing, and
it would help current and future developers, to clarify them.
One of them is 'subflows_max', which in fact represents the limit of
extra subflows: the limit set via 'ip mptcp limit subflows X' for
example. It is not linked to the maximum number of created / possible
subflows.
While at it, add an additional name for the corresponding variable in
MPTCP INFO: mptcpi_limit_extra_subflows. Not to break the current uAPI,
the new name is added as a 'define' pointing to the former name. This
will then also help userspace devs.
No functional changes intended.
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-v1-6-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
A few variables linked to the Path-Managers are confusing, and it would
help current and future developers, to clarify them.
One of them is 'subflows', which in fact represents the number of extra
subflows: all the additional subflows created after the initial one, and
not the total number of subflows.
While at it, add an additional name for the corresponding variable in
MPTCP INFO: mptcpi_extra_subflows. Not to break the current uAPI, the
new name is added as a 'define' pointing to the former name. This will
then also help userspace devs.
No functional changes intended.
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-v1-5-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Before this modification, this function was quite long with many levels
of indentations.
Each case can be split in a dedicated function: fullmesh, non-fullmesh.
To remove one level of indentation, msk->pm.subflows >= subflows_max is
now checked after having added one subflow, and stops the loop if it is
no longer possible to add new subflows. This is fine to do this because
this function should only be called if msk->pm.subflows < subflows_max.
No functional changes intended.
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-v1-4-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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: df377be387 ("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-ad126cc47c6b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
This attribute is a boolean. No need to add it to set it to 'false'.
Indeed, the default value when this attribute is not set is naturally
'false'. A few bytes can then be saved by not adding this attribute if
the connection is not on the server side.
This prepares the future deprecation of its attribute, in favour of a
new flag.
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250919-net-next-mptcp-server-side-flag-v1-1-a97a5d561a8b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR (net-6.17-rc7).
No conflicts.
Adjacent changes:
drivers/net/ethernet/mellanox/mlx5/core/en/fs.h
9536fbe10c ("net/mlx5e: Add PSP steering in local NIC RX")
7601a0a462 ("net/mlx5e: Add a miss level for ipsec crypto offload")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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: dfc8d06030 ("mptcp: implement delayed seq generation for passive fastopen")
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-4-40171884ade8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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: 702c2f646d ("mptcp: netlink: allow userspace-driven subflow establishment")
Reported-by: Marek Majkowski <marek@cloudflare.com>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/532
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-2-40171884ade8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
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: df377be387 ("mptcp: add deny_join_id0 in mptcp_options_received")
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250912-net-mptcp-pm-uspace-deny_join_id0-v1-1-40171884ade8@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
When the MPTCP DATA FIN have been ACKed, there is no more MPTCP related
metadata to exchange, and all subflows can be safely shutdown.
Before this patch, the subflows were actually terminated at 'close()'
time. That's certainly fine most of the time, but not when the userspace
'shutdown()' a connection, without close()ing it. When doing so, the
subflows were staying in LAST_ACK state on one side -- and consequently
in FIN_WAIT2 on the other side -- until the 'close()' of the MPTCP
socket.
Now, when the DATA FIN have been ACKed, all subflows are shutdown. A
consequence of this is that the TCP 'FIN' flag can be set earlier now,
but the end result is the same. This affects the packetdrill tests
looking at the end of the MPTCP connections, but for a good reason.
Note that tcp_shutdown() will check the subflow state, so no need to do
that again before calling it.
Fixes: 3721b9b646 ("mptcp: Track received DATA_FIN sequence number and add related helpers")
Cc: stable@vger.kernel.org
Fixes: 16a9a9da17 ("mptcp: Add helper to process acks of DATA_FIN")
Reviewed-by: Mat Martineau <martineau@kernel.org>
Reviewed-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250912-net-mptcp-fix-sft-connect-v1-1-d40e77cbbf02@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Cross-merge networking fixes after downstream PR (net-6.17-rc6).
Conflicts:
net/netfilter/nft_set_pipapo.c
net/netfilter/nft_set_pipapo_avx2.c
c4eaca2e10 ("netfilter: nft_set_pipapo: don't check genbit from packetpath lookups")
84c1da7b38 ("netfilter: nft_set_pipapo: use avx2 algorithm for insertions too")
Only trivial adjacent changes (in a doc and a Makefile).
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Currently the ADD_ADDR option is retransmitted with a fixed timeout. This
patch makes the retransmission timeout adaptive by using the maximum RTO
among all the subflows, while still capping it at the configured maximum
value (add_addr_timeout_max). This improves responsiveness when
establishing new subflows.
Specifically:
1. Adds mptcp_adjust_add_addr_timeout() helper to compute the adaptive
timeout.
2. Uses maximum subflow RTO (icsk_rto) when available.
3. Applies exponential backoff based on retransmission count.
4. Maintains fallback to configured max timeout when no RTO data exists.
This slightly changes the behaviour of the MPTCP "add_addr_timeout"
sysctl knob to be used as a maximum instead of a fixed value. But this
is seen as an improvement: the ADD_ADDR might be sent quicker than
before to improve the overall MPTCP connection. Also, the default
value is set to 2 min, which was already way too long, and caused the
ADD_ADDR not to be retransmitted for connections shorter than 2 minutes.
Suggested-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/576
Reviewed-by: Christoph Paasch <cpaasch@openai.com>
Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250907-net-next-mptcp-add_addr-retrans-adapt-v1-1-824cc805772b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Users reported a scenario where MPTCP connections that were configured
with SO_KEEPALIVE prior to connect would fail to enable their keepalives
if MTPCP fell back to TCP mode.
After investigating, this affects keepalives for any connection where
sync_socket_options is called on a socket that is in the closed or
listening state. Joins are handled properly. For connects,
sync_socket_options is called when the socket is still in the closed
state. The tcp_set_keepalive() function does not act on sockets that
are closed or listening, hence keepalive is not immediately enabled.
Since the SO_KEEPOPEN flag is absent, it is not enabled later in the
connect sequence via tcp_finish_connect. Setting the keepalive via
sockopt after connect does work, but would not address any subsequently
created flows.
Fortunately, the fix here is straight-forward: set SOCK_KEEPOPEN on the
subflow when calling sync_socket_options.
The fix was valdidated both by using tcpdump to observe keepalive
packets not being sent before the fix, and being sent after the fix. It
was also possible to observe via ss that the keepalive timer was not
enabled on these sockets before the fix, but was enabled afterwards.
Fixes: 1b3e7ede13 ("mptcp: setsockopt: handle SO_KEEPALIVE and SO_PRIORITY")
Cc: stable@vger.kernel.org
Signed-off-by: Krister Johansen <kjlx@templeofstupid.com>
Reviewed-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/aL8dYfPZrwedCIh9@templeofstupid.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Accelerated Receive Flow Steering (aRFS) relies on sockets recording
their RX flow hash into the rps_sock_flow_table so that incoming packets
are steered to the CPU where the application runs.
With MPTCP, the application interacts with the parent MPTCP socket while
data is carried over per-subflow TCP sockets. Without recording these
subflows, aRFS cannot steer interrupts and RX processing for the flows
to the desired CPU.
Record all subflows in the RPS table by calling sock_rps_record_flow()
for each subflow at the start of mptcp_sendmsg(), mptcp_recvmsg() and
mptcp_stream_accept(), by using the new helper
mptcp_rps_record_subflows().
It does not by itself improve throughput, but ensures that IRQ and RX
processing are directed to the right CPU, which is a
prerequisite for effective aRFS.
Signed-off-by: Christoph Paasch <cpaasch@openai.com>
Reviewed-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250902-net-next-mptcp-misc-feat-6-18-v2-4-fa02bb3188b1@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Jiayuan Chen
Paolo Abeni
Eric Dumazet
Matthieu Baerts (NGI0)
Jakub Kicinski
Kuniyuki Iwashima
Geliang Tang
Krister Johansen
Christoph Paasch