From nobody Fri Dec 19 19:11:27 2025 Received: from mga02.intel.com (mga02.intel.com [134.134.136.20]) (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 B0ECB5A79 for ; Fri, 30 Sep 2022 16:00:30 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1664553630; x=1696089630; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=z66rPEvAFA1BnW04dg1ABSJlUprM6g9uqaqeJgn885M=; b=ZLkaKdRElMvFLLuUZ6ORglcm9lnprkTwkLlN4dwJQPhVP49hEnfM0Bb/ jMFehKtJe6AX31BIs3dFeh4XucMjdSVc5wOGyrqn8KatKznCl0SeeZ1WP tcKDrZ30IR/t0sV+eWnb94PkXi2b2hjZtPN0J5wDHIOmoGWMDqEpoNnqZ b9Ei0UF5ldQ1KCdJznYynQi5sCf2qt/OW4Zi4mT3XC6Re3ABZc9v4QfZ2 T9tLE1SvnvarS5hawsSyQleJl/H0VnVjt9Yk/5SDN009e0QURlGvYQGt+ NCrlLxM/d6tSqWOjj0DuEGTjQHBFaqTu0irvjUJNaJM+4hT8mLT+mSSfm w==; X-IronPort-AV: E=McAfee;i="6500,9779,10486"; a="289383896" X-IronPort-AV: E=Sophos;i="5.93,358,1654585200"; d="scan'208";a="289383896" Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga101.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 30 Sep 2022 09:00:28 -0700 X-IronPort-AV: E=McAfee;i="6500,9779,10486"; a="655996109" X-IronPort-AV: E=Sophos;i="5.93,358,1654585200"; d="scan'208";a="655996109" Received: from cmforest-mobl1.amr.corp.intel.com (HELO mjmartin-desk2.intel.com) ([10.251.22.5]) by orsmga001-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 30 Sep 2022 09:00:27 -0700 From: Mat Martineau To: netdev@vger.kernel.org Cc: Paolo Abeni , davem@davemloft.net, kuba@kernel.org, edumazet@google.com, matthieu.baerts@tessares.net, mptcp@lists.linux.dev, Mat Martineau Subject: [PATCH net-next 2/4] mptcp: use fastclose on more edge scenarios Date: Fri, 30 Sep 2022 08:59:32 -0700 Message-Id: <20220930155934.404466-3-mathew.j.martineau@linux.intel.com> X-Mailer: git-send-email 2.37.3 In-Reply-To: <20220930155934.404466-1-mathew.j.martineau@linux.intel.com> References: <20220930155934.404466-1-mathew.j.martineau@linux.intel.com> Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Paolo Abeni Daire reported a user-space application hang-up when the peer is forcibly closed before the data transfer completion. The relevant application expects the peer to either do an application-level clean shutdown or a transport-level connection reset. We can accommodate a such user by extending the fastclose usage: at fd close time, if the msk socket has some unread data, and at FIN_WAIT timeout. Note that at MPTCP close time we must ensure that the TCP subflows will reset: set the linger socket option to a suitable value. Reviewed-by: Matthieu Baerts Reviewed-by: Mat Martineau Signed-off-by: Paolo Abeni Signed-off-by: Mat Martineau --- net/mptcp/protocol.c | 63 +++++++++++++++++++++++++++++++------------- 1 file changed, 44 insertions(+), 19 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index cad0346c9281..acf44075ba40 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2313,8 +2313,14 @@ static void __mptcp_close_ssk(struct sock *sk, struc= t sock *ssk, =20 lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); =20 - if (flags & MPTCP_CF_FASTCLOSE) + if (flags & MPTCP_CF_FASTCLOSE) { + /* be sure to force the tcp_disconnect() path, + * to generate the egress reset + */ + ssk->sk_lingertime =3D 0; + sock_set_flag(ssk, SOCK_LINGER); subflow->send_fastclose =3D 1; + } =20 need_push =3D (flags & MPTCP_CF_PUSH) && __mptcp_retransmit_pending_data(= sk); if (!dispose_it) { @@ -2577,6 +2583,16 @@ static void mptcp_mp_fail_no_response(struct mptcp_s= ock *msk) mptcp_reset_timeout(msk, 0); } =20 +static void mptcp_do_fastclose(struct sock *sk) +{ + struct mptcp_subflow_context *subflow, *tmp; + struct mptcp_sock *msk =3D mptcp_sk(sk); + + mptcp_for_each_subflow_safe(msk, subflow, tmp) + __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), + subflow, MPTCP_CF_FASTCLOSE); +} + static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk =3D container_of(work, struct mptcp_sock, work); @@ -2605,11 +2621,15 @@ static void mptcp_worker(struct work_struct *work) * closed, but we need the msk around to reply to incoming DATA_FIN, * even if it is orphaned and in FIN_WAIT2 state */ - if (sock_flag(sk, SOCK_DEAD) && - (mptcp_check_close_timeout(sk) || sk->sk_state =3D=3D TCP_CLOSE)) { - inet_sk_state_store(sk, TCP_CLOSE); - __mptcp_destroy_sock(sk); - goto unlock; + if (sock_flag(sk, SOCK_DEAD)) { + if (mptcp_check_close_timeout(sk)) { + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_do_fastclose(sk); + } + if (sk->sk_state =3D=3D TCP_CLOSE) { + __mptcp_destroy_sock(sk); + goto unlock; + } } =20 if (test_and_clear_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags)) @@ -2850,6 +2870,18 @@ static void __mptcp_destroy_sock(struct sock *sk) sock_put(sk); } =20 +static __poll_t mptcp_check_readable(struct mptcp_sock *msk) +{ + /* Concurrent splices from sk_receive_queue into receive_queue will + * always show at least one non-empty queue when checked in this order. + */ + if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) && + skb_queue_empty_lockless(&msk->receive_queue)) + return 0; + + return EPOLLIN | EPOLLRDNORM; +} + bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; @@ -2863,8 +2895,13 @@ bool __mptcp_close(struct sock *sk, long timeout) goto cleanup; } =20 - if (mptcp_close_state(sk)) + if (mptcp_check_readable(msk)) { + /* the msk has read data, do the MPTCP equivalent of TCP reset */ + inet_sk_state_store(sk, TCP_CLOSE); + mptcp_do_fastclose(sk); + } else if (mptcp_close_state(sk)) { __mptcp_wr_shutdown(sk); + } =20 sk_stream_wait_close(sk, timeout); =20 @@ -3681,18 +3718,6 @@ static int mptcp_stream_accept(struct socket *sock, = struct socket *newsock, return err; } =20 -static __poll_t mptcp_check_readable(struct mptcp_sock *msk) -{ - /* Concurrent splices from sk_receive_queue into receive_queue will - * always show at least one non-empty queue when checked in this order. - */ - if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue) && - skb_queue_empty_lockless(&msk->receive_queue)) - return 0; - - return EPOLLIN | EPOLLRDNORM; -} - static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) { struct sock *sk =3D (struct sock *)msk; --=20 2.37.3