From: Kalpan Jani The MPTCP-level retransmit timers (DATA_FIN retransmissions and the fallback timeout) used the hard-coded TCP_RTO_MIN / TCP_RTO_MAX constants, ignoring the tcp_rto_min_us and tcp_rto_max_ms sysctls. Make them follow the sysctls instead: seed icsk_rto_min / icsk_rto_max on the MPTCP socket from the per-netns sysctls in __mptcp_init_sock() -- the msk does not go through tcp_init_sock(), so these fields would otherwise stay zero -- and read them directly where the constants were used: - mptcp_set_datafin_timeout(): both the backoff cap computation and the resulting timer_ival. The two sysctls are validated independently, so rto_min > rto_max is a valid configuration; keep a max_t() guard so ilog2() is never called with 0. - __mptcp_set_timeout(): the fallback when no subflow timeout is available. The icsk fields are read directly instead of using the tcp_rto_min()/tcp_rto_max() helpers: the MPTCP socket does not perform routing lookups in these paths, so the rto_min route metric checked by tcp_rto_min() can never apply here. The TCP_RTO_MIN_US / TCP_RTO_MAX_MS socket options are not supported by MPTCP setsockopt() either; this can be revisited if they get supported on MPTCP sockets. The remaining uses of TCP_RTO_MAX in net/mptcp/ctrl.c (default add_addr_timeout) and net/mptcp/subflow.c (MP_FAIL timeout) are intentionally left unchanged: they use the constant as a default duration, not as an RTO bound on a retransmit timer. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/618 Signed-off-by: Kalpan Jani Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) --- net/mptcp/protocol.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index ec874d2ead6a..8f074d757743 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -581,17 +581,23 @@ static bool mptcp_pending_data_fin(struct sock *sk, u64 *seq) static void mptcp_set_datafin_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); + u32 rto_min = READ_ONCE(icsk->icsk_rto_min); + u32 rto_max = READ_ONCE(icsk->icsk_rto_max); u32 retransmits; + /* The sysctls are validated independently: rto_min > rto_max is + * possible, guard against ilog2(0). + */ retransmits = min_t(u32, icsk->icsk_retransmits, - ilog2(TCP_RTO_MAX / TCP_RTO_MIN)); + ilog2(max_t(u32, rto_max / rto_min, 1))); - mptcp_sk(sk)->timer_ival = TCP_RTO_MIN << retransmits; + mptcp_sk(sk)->timer_ival = rto_min << retransmits; } static void __mptcp_set_timeout(struct sock *sk, long tout) { - mptcp_sk(sk)->timer_ival = tout > 0 ? tout : TCP_RTO_MIN; + mptcp_sk(sk)->timer_ival = tout > 0 ? tout : + READ_ONCE(inet_csk(sk)->icsk_rto_min); } static long mptcp_timeout_from_subflow(const struct mptcp_subflow_context *subflow) @@ -3161,7 +3167,9 @@ static void mptcp_worker(struct work_struct *work) static void __mptcp_init_sock(struct sock *sk) { + struct inet_connection_sock *icsk = inet_csk(sk); struct mptcp_sock *msk = mptcp_sk(sk); + struct net *net = sock_net(sk); INIT_LIST_HEAD(&msk->conn_list); INIT_LIST_HEAD(&msk->join_list); @@ -3170,7 +3178,13 @@ static void __mptcp_init_sock(struct sock *sk) INIT_WORK(&msk->work, mptcp_worker); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; - msk->timer_ival = TCP_RTO_MIN; + + /* msk does not go through tcp_init_sock(); seed RTO bounds. */ + icsk->icsk_rto_min = + usecs_to_jiffies(READ_ONCE(net->ipv4.sysctl_tcp_rto_min_us)); + icsk->icsk_rto_max = + msecs_to_jiffies(READ_ONCE(net->ipv4.sysctl_tcp_rto_max_ms)); + msk->timer_ival = icsk->icsk_rto_min; msk->scaling_ratio = TCP_DEFAULT_SCALING_RATIO; msk->backlog_len = 0; mptcp_init_rtt_est(msk); -- 2.53.0