If we want to steer interrupts to the right CPU-core with aRFS, we need
to record the subflows in the RPS-table.

This patchset achieves this by iterating over the subflows and calling
sock_rps_record_flow().

Patch 1/2 adds a helper (rfs_is_needed()) to allow checking whether RFS
is enabled before iterating over the subflows. The helper allows to
rework the code in rps.h to make it more streamlined.

Signed-off-by: Christoph Paasch <cpaasch@openai.com>
---
Changes in v2:
- Introduce patch 1/2 which adds rfs_is_needed (Matthieu Baerts <matttbe@kernel.org>)
- Use helper rfs_is_needed() to decide whether or not to iterate over
  subflows (Matthieu Baerts <matttbe@kernel.org>)
- Also call mptcp_rps_record_subflows() in mptcp_stream_accept (Matthieu Baerts <matttbe@kernel.org>)
- Link to v1: https://lore.kernel.org/r/20250807-b4-mptcp_perf-v1-1-e89cc14179cc@openai.com

---
Christoph Paasch (2):
      net: Add rfs_needed() helper
      mptcp: record subflows in RPS table

 include/net/rps.h    | 85 ++++++++++++++++++++++++++++++++++------------------
 net/mptcp/protocol.c | 21 +++++++++++++
 2 files changed, 77 insertions(+), 29 deletions(-)
---
base-commit: 4a7f79b50b675c068ff94cd750d5a9f03fd3a0fa
change-id: 20250731-b4-mptcp_perf-02912dd4f65b

Best regards,
-- 
Christoph Paasch <cpaasch@openai.com>

Hi Christoph,

On 26/08/2025 06:30, Christoph Paasch via B4 Relay wrote:
> If we want to steer interrupts to the right CPU-core with aRFS, we need
> to record the subflows in the RPS-table.
> 
> This patchset achieves this by iterating over the subflows and calling
> sock_rps_record_flow().
> 
> Patch 1/2 adds a helper (rfs_is_needed()) to allow checking whether RFS
> is enabled before iterating over the subflows. The helper allows to
> rework the code in rps.h to make it more streamlined.
> 
> Signed-off-by: Christoph Paasch <cpaasch@openai.com>
> ---
> Changes in v2:
> - Introduce patch 1/2 which adds rfs_is_needed (Matthieu Baerts <matttbe@kernel.org>)
> - Use helper rfs_is_needed() to decide whether or not to iterate over
>   subflows (Matthieu Baerts <matttbe@kernel.org>)
> - Also call mptcp_rps_record_subflows() in mptcp_stream_accept (Matthieu Baerts <matttbe@kernel.org>)
> - Link to v1: https://lore.kernel.org/r/20250807-b4-mptcp_perf-v1-1-e89cc14179cc@openai.com

Thank you for the v2! Now in our tree:

New patches for t/upstream:
- 1c7ddd7d3342: net: Add rfs_needed() helper
- aad318234d86: mptcp: record subflows in RPS table
- Results: 78b25ad0d158..569dfa7d27f3 (export)

Tests are now in progress:

- export:
https://github.com/multipath-tcp/mptcp_net-next/commit/140a217afe2c0b073a315f27c784d071fecbeea5/checks

Cheers,
Matt
-- 
Sponsored by the NGI0 Core fund.

Hi Christoph,

Thank you for your modifications, that's great!

Our CI did some validations and here is its report:

- KVM Validation: normal: Unstable: 1 failed test(s): selftest_mptcp_connect 🔴
- KVM Validation: debug: Unstable: 2 failed test(s): selftest_mptcp_connect_checksum selftest_mptcp_join 🔴
- KVM Validation: btf-normal (only bpftest_all): Unstable: 1 failed test(s): bpftest_test_progs-no_alu32_mptcp 🔴
- KVM Validation: btf-debug (only bpftest_all): Success! ✅
- Task: https://github.com/multipath-tcp/mptcp_net-next/actions/runs/17228284455

Initiator: Patchew Applier
Commits: https://github.com/multipath-tcp/mptcp_net-next/commits/5039da03db6a
Patchwork: https://patchwork.kernel.org/project/mptcp/list/?series=995486


If there are some issues, you can reproduce them using the same environment as
the one used by the CI thanks to a docker image, e.g.:

    $ cd [kernel source code]
    $ docker run -v "${PWD}:${PWD}:rw" -w "${PWD}" --privileged --rm -it \
        --pull always mptcp/mptcp-upstream-virtme-docker:latest \
        auto-normal

For more details:

    https://github.com/multipath-tcp/mptcp-upstream-virtme-docker


Please note that despite all the efforts that have been already done to have a
stable tests suite when executed on a public CI like here, it is possible some
reported issues are not due to your modifications. Still, do not hesitate to
help us improve that ;-)

Cheers,
MPTCP GH Action bot
Bot operated by Matthieu Baerts (NGI0 Core)