From b8dc6d6ce93142ccd4c976003bb6c25d63aac2ce Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Thu, 20 Jul 2023 20:47:50 +0200 Subject: mptcp: fix rcv buffer auto-tuning The MPTCP code uses the assumption that the tcp_win_from_space() helper does not use any TCP-specific field, and thus works correctly operating on an MPTCP socket. The commit dfa2f0483360 ("tcp: get rid of sysctl_tcp_adv_win_scale") broke such assumption, and as a consequence most MPTCP connections stall on zero-window event due to auto-tuning changing the rcv buffer size quite randomly. Address the issue syncing again the MPTCP auto-tuning code with the TCP one. To achieve that, factor out the windows size logic in socket independent helpers, and reuse them in mptcp_rcv_space_adjust(). The MPTCP level scaling_ratio is selected as the minimum one from the all the subflows, as a worst-case estimate. Fixes: dfa2f0483360 ("tcp: get rid of sysctl_tcp_adv_win_scale") Signed-off-by: Paolo Abeni Co-developed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Reviewed-by: Eric Dumazet Acked-by: Soheil Hassas Yeganeh Link: https://lore.kernel.org/r/20230720-upstream-net-next-20230720-mptcp-fix-rcv-buffer-auto-tuning-v1-1-175ef12b8380@tessares.net Signed-off-by: Jakub Kicinski --- include/net/tcp.h | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index d17cb8ab4c48..6ebf54992ffe 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1430,22 +1430,32 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 *window_clamp, int wscale_ok, __u8 *rcv_wscale, __u32 init_rcv_wnd); -static inline int tcp_win_from_space(const struct sock *sk, int space) +static inline int __tcp_win_from_space(u8 scaling_ratio, int space) { - s64 scaled_space = (s64)space * tcp_sk(sk)->scaling_ratio; + s64 scaled_space = (s64)space * scaling_ratio; return scaled_space >> TCP_RMEM_TO_WIN_SCALE; } -/* inverse of tcp_win_from_space() */ -static inline int tcp_space_from_win(const struct sock *sk, int win) +static inline int tcp_win_from_space(const struct sock *sk, int space) +{ + return __tcp_win_from_space(tcp_sk(sk)->scaling_ratio, space); +} + +/* inverse of __tcp_win_from_space() */ +static inline int __tcp_space_from_win(u8 scaling_ratio, int win) { u64 val = (u64)win << TCP_RMEM_TO_WIN_SCALE; - do_div(val, tcp_sk(sk)->scaling_ratio); + do_div(val, scaling_ratio); return val; } +static inline int tcp_space_from_win(const struct sock *sk, int win) +{ + return __tcp_space_from_win(tcp_sk(sk)->scaling_ratio, win); +} + static inline void tcp_scaling_ratio_init(struct sock *sk) { /* Assume a conservative default of 1200 bytes of payload per 4K page. -- cgit v1.2.3