From patchwork Mon Sep 6 13:10:45 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Florian Westphal X-Patchwork-Id: 12476963 X-Patchwork-Delegate: matthieu.baerts@tessares.net Received: from Chamillionaire.breakpoint.cc (Chamillionaire.breakpoint.cc [193.142.43.52]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 047753FC1 for ; Mon, 6 Sep 2021 13:11:00 +0000 (UTC) Received: from fw by Chamillionaire.breakpoint.cc with local (Exim 4.92) (envelope-from ) id 1mNEOo-0001oQ-8i; Mon, 06 Sep 2021 15:10:58 +0200 From: Florian Westphal To: Cc: Florian Westphal Subject: [PATCH mptcp-next v2 2/2] mptcp: re-arm retransmit timer if data is pending Date: Mon, 6 Sep 2021 15:10:45 +0200 Message-Id: <20210906131045.18513-3-fw@strlen.de> X-Mailer: git-send-email 2.32.0 In-Reply-To: <20210906131045.18513-1-fw@strlen.de> References: <20210906131045.18513-1-fw@strlen.de> Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 The retransmit head will be NULL in case there is no in-flight data (meaning all data injected into network has been acked). In that case the retransmit timer is stopped. This is only correct if there is no more pending, not-yet-sent data. If there is, the retransmit timer needs to set the PENDING bit again so that mptcp tries to send the remaining (new) data once a subflow can accept more data. Also, mptcp_subflow_get_retrans() has to be called unconditionally. This function checks for subflows that have become unresponsive and marks them as stale, so in the case where the rtx queue is empty, subflows will never be marked stale which prevents available backup subflows from becoming eligible for transmit. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/226 Signed-off-by: Florian Westphal Acked-by: Paolo Abeni --- Changes in v2: - drop reset-pending conditional in __mptcp_push_pending, retrans timer already takes care of this (Paolo) - rename patch subject - add a 'closes' tag to commit message net/mptcp/protocol.c | 21 ++++++++++++++++++--- 1 file changed, 18 insertions(+), 3 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c0e0ee4cb24f..73cb5d053785 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1105,7 +1105,8 @@ static void __mptcp_clean_una(struct sock *sk) if (cleaned && tcp_under_memory_pressure(sk)) __mptcp_mem_reclaim_partial(sk); - if (snd_una == READ_ONCE(msk->snd_nxt) && !msk->recovery) { + if (snd_una == READ_ONCE(msk->snd_nxt) && + snd_una == READ_ONCE(msk->write_seq)) { if (mptcp_timer_pending(sk) && !mptcp_data_fin_enabled(msk)) mptcp_stop_timer(sk); } else { @@ -1547,6 +1548,13 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, msk->snd_nxt = snd_nxt_new; } +static void mptcp_check_and_set_pending(struct sock *sk) +{ + if (mptcp_send_head(sk) && + !test_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags)) + set_bit(MPTCP_PUSH_PENDING, &mptcp_sk(sk)->flags); +} + void __mptcp_push_pending(struct sock *sk, unsigned int flags) { struct sock *prev_ssk = NULL, *ssk = NULL; @@ -2414,6 +2422,9 @@ static void __mptcp_retrans(struct sock *sk) int ret; mptcp_clean_una_wakeup(sk); + + /* first check ssk: need to kick "stale" logic */ + ssk = mptcp_subflow_get_retrans(msk); dfrag = mptcp_rtx_head(sk); if (!dfrag) { if (mptcp_data_fin_enabled(msk)) { @@ -2426,10 +2437,12 @@ static void __mptcp_retrans(struct sock *sk) goto reset_timer; } - return; + if (!mptcp_send_head(sk)) + return; + + goto reset_timer; } - ssk = mptcp_subflow_get_retrans(msk); if (!ssk) goto reset_timer; @@ -2456,6 +2469,8 @@ static void __mptcp_retrans(struct sock *sk) release_sock(ssk); reset_timer: + mptcp_check_and_set_pending(sk); + if (!mptcp_timer_pending(sk)) mptcp_reset_timer(sk); }