From 5684ab1a0effbfeb706f47d85785f653005b97b1 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Mon, 23 Oct 2023 13:44:38 -0700 Subject: mptcp: give rcvlowat some love The MPTCP protocol allow setting sk_rcvlowat, but the value there is currently ignored. Additionally, the default subflows sk_rcvlowat basically disables per subflow delayed ack: the MPTCP protocol move the incoming data from the subflows into the msk socket as soon as the TCP stacks invokes the subflow data_ready callback. Later, when __tcp_ack_snd_check() takes action, the subflow-level copied_seq matches rcv_nxt, and that mandate for an immediate ack. Let the mptcp receive path be aware of such threshold, explicitly tracking the amount of data available to be ready and checking vs sk_rcvlowat in mptcp_poll() and before waking-up readers. Additionally implement the set_rcvlowat() callback, to properly handle the rcvbuf auto-tuning on sk_rcvlowat changes. Finally to properly handle delayed ack, force the subflow level threshold to 0 and instead explicitly ask for an immediate ack when the msk level th is not reached. 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-v1-5-9dc60939d371@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/subflow.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'net/mptcp/subflow.c') diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index dbc7a52b322f..080b16426222 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1405,10 +1405,18 @@ static void subflow_data_ready(struct sock *sk) WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && !subflow->mp_join && !(state & TCPF_CLOSE)); - if (mptcp_subflow_data_available(sk)) + if (mptcp_subflow_data_available(sk)) { mptcp_data_ready(parent, sk); - else if (unlikely(sk->sk_err)) + + /* subflow-level lowat test are not relevant. + * respect the msk-level threshold eventually mandating an immediate ack + */ + if (mptcp_data_avail(msk) < parent->sk_rcvlowat && + (tcp_sk(sk)->rcv_nxt - tcp_sk(sk)->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + } else if (unlikely(sk->sk_err)) { subflow_error_report(sk); + } } static void subflow_write_space(struct sock *ssk) -- cgit