From 9fdc779331bd3e0b2570c2bced396d53a04a33b9 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 23 Oct 2023 13:44:41 -0700 Subject: mptcp: ignore notsent_lowat setting at the subflow level Any latency related tuning taking action at the subflow level does not really affect the user-space, as only the main MPTCP socket is relevant. Anyway any limiting setting may foul the MPTCP scheduler, not being able to fully use the subflow-level cwin, leading to very poor b/w usage. Enforce notsent_lowat to be a no-op on every subflow. Note that TCP_NOTSENT_LOWAT is currently not supported, and properly dealing with that will require more invasive changes. Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau Link: https://lore.kernel.org/r/20231023-send-net-next-20231023-2-v1-8-9dc60939d371@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/sockopt.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'net/mptcp') diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index abf0645cb65d..72858d7d8974 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1452,6 +1452,12 @@ void mptcp_sockopt_sync_locked(struct mptcp_sock *msk, struct sock *ssk) ssk->sk_rcvlowat = 0; + /* subflows must ignore any latency-related settings: will not affect + * the user-space - only the msk is relevant - but will foul the + * mptcp scheduler + */ + tcp_sk(ssk)->notsent_lowat = UINT_MAX; + if (READ_ONCE(subflow->setsockopt_seq) != msk->setsockopt_seq) { sync_socket_options(msk, ssk); -- cgit v1.2.3