From nobody Mon May 6 15:36:58 2024 Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) (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 B47EE4A18 for ; Tue, 27 Sep 2022 19:35:28 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1664307328; x=1695843328; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=lj5Dh5PktHR1/wBlmoRV33Y7KeYrd1UcvZO77ytT+sA=; b=eTuvX17lmaYMcPjphRuWGQi9kg4A9mS4cNcIy3QTmbxfNU1EZ0ZrQerM RZmeCzv7pDq5Xt0mCE++OcLqy1mTtv585ezuI2lEX3cbSRLLix4FPQzlr XXWO5eicKhTqAB229MNfPjLAB6Cs1OxbJrRdYfb+QEY78Fj7x6abrpngs c9sAPnIHbjCepedqJmu/61vdaozoqgson9fg9Uqw0UAoGXDCjzYGNfk2k mkedf82Y9yAbGcmSkzsSQn3bCL0WhW9jhCQdnoiEcQh0rWtGCVft67T/t 3MOenvRJXFJB06jyeywstgKTzWGFfFteiY3X6c2FCP7iGAt+QgWmr+wu3 w==; X-IronPort-AV: E=McAfee;i="6500,9779,10483"; a="281782525" X-IronPort-AV: E=Sophos;i="5.93,350,1654585200"; d="scan'208";a="281782525" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga107.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Sep 2022 12:32:04 -0700 X-IronPort-AV: E=McAfee;i="6500,9779,10483"; a="652399449" X-IronPort-AV: E=Sophos;i="5.93,350,1654585200"; d="scan'208";a="652399449" Received: from soumiban-mobl1.amr.corp.intel.com (HELO mjmartin-desk2.intel.com) ([10.209.81.98]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Sep 2022 12:32:03 -0700 From: Mat Martineau To: netdev@vger.kernel.org Cc: Menglong Dong , davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com, fw@strlen.de, matthieu.baerts@tessares.net, mptcp@lists.linux.dev, stable@vger.kernel.org, Jiang Biao , Mengen Sun , Mat Martineau Subject: [PATCH net 1/2] mptcp: factor out __mptcp_close() without socket lock Date: Tue, 27 Sep 2022 12:31:57 -0700 Message-Id: <20220927193158.195729-2-mathew.j.martineau@linux.intel.com> X-Mailer: git-send-email 2.37.3 In-Reply-To: <20220927193158.195729-1-mathew.j.martineau@linux.intel.com> References: <20220927193158.195729-1-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: Menglong Dong Factor out __mptcp_close() from mptcp_close(). The caller of __mptcp_close() should hold the socket lock, and cancel mptcp work when __mptcp_close() returns true. This function will be used in the next commit. Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests") Fixes: 6aeed9045071 ("mptcp: fix race on unaccepted mptcp sockets") Cc: stable@vger.kernel.org Reviewed-by: Jiang Biao Reviewed-by: Mengen Sun Acked-by: Paolo Abeni Signed-off-by: Menglong Dong Signed-off-by: Mat Martineau --- net/mptcp/protocol.c | 14 ++++++++++++-- net/mptcp/protocol.h | 1 + 2 files changed, 13 insertions(+), 2 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 969b33a9dd64..f7690414320a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2802,13 +2802,12 @@ static void __mptcp_destroy_sock(struct sock *sk) sock_put(sk); } =20 -static void mptcp_close(struct sock *sk, long timeout) +bool __mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; struct mptcp_sock *msk =3D mptcp_sk(sk); bool do_cancel_work =3D false; =20 - lock_sock(sk); sk->sk_shutdown =3D SHUTDOWN_MASK; =20 if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) { @@ -2850,6 +2849,17 @@ static void mptcp_close(struct sock *sk, long timeou= t) } else { mptcp_reset_timeout(msk, 0); } + + return do_cancel_work; +} + +static void mptcp_close(struct sock *sk, long timeout) +{ + bool do_cancel_work; + + lock_sock(sk); + + do_cancel_work =3D __mptcp_close(sk, timeout); release_sock(sk); if (do_cancel_work) mptcp_cancel_work(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 132d50833df1..8f123d450c76 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -612,6 +612,7 @@ void mptcp_subflow_reset(struct sock *ssk); void mptcp_subflow_queue_clean(struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); +bool __mptcp_close(struct sock *sk, long timeout); =20 bool mptcp_addresses_equal(const struct mptcp_addr_info *a, const struct mptcp_addr_info *b, bool use_port); --=20 2.37.3 From nobody Mon May 6 15:36:58 2024 Received: from mga17.intel.com (mga17.intel.com [192.55.52.151]) (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 4E1394A27 for ; Tue, 27 Sep 2022 19:35:29 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1664307329; x=1695843329; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=+T+ojb/064eW50kyu/docWvls9bdSsjpGYD0DnSFSEU=; b=IC5JwMVIvXF39vJCP+iiAA+KoQllodjhxgxICCpqtXhJcTfdYkXmqAAj OEkTb/F4DlmGiiO7ja9nQpAYjsZnopzRfyw/82lgkNOcAxiHpcbIfOSMu OXB/mOkPYE/EVrnGLlSRNo08JjqKagalGcE/QwOlbMmbL/zSmCG7Ua3y1 LOZ4fVfl05Wj0r7PYzhlAQFDgoQcb6Vp1aZGOKziHxaLPpzaUUoojXJA+ fOLk/bUmZ6cHDhtFAFBsj9/luwXS30yXf+FiVBfkwiL2QBqTsU+U0mdlf G/4rP33KSO+3oUMyLN5MjwzMykxEXNS08IDLRK5FTgcTVoTRlyj20uKVu w==; X-IronPort-AV: E=McAfee;i="6500,9779,10483"; a="281782536" X-IronPort-AV: E=Sophos;i="5.93,350,1654585200"; d="scan'208";a="281782536" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga107.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Sep 2022 12:32:05 -0700 X-IronPort-AV: E=McAfee;i="6500,9779,10483"; a="652399450" X-IronPort-AV: E=Sophos;i="5.93,350,1654585200"; d="scan'208";a="652399450" Received: from soumiban-mobl1.amr.corp.intel.com (HELO mjmartin-desk2.intel.com) ([10.209.81.98]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 27 Sep 2022 12:32:03 -0700 From: Mat Martineau To: netdev@vger.kernel.org Cc: Menglong Dong , davem@davemloft.net, kuba@kernel.org, pabeni@redhat.com, edumazet@google.com, fw@strlen.de, matthieu.baerts@tessares.net, mptcp@lists.linux.dev, stable@vger.kernel.org, Jiang Biao , Mengen Sun , Mat Martineau Subject: [PATCH net 2/2] mptcp: fix unreleased socket in accept queue Date: Tue, 27 Sep 2022 12:31:58 -0700 Message-Id: <20220927193158.195729-3-mathew.j.martineau@linux.intel.com> X-Mailer: git-send-email 2.37.3 In-Reply-To: <20220927193158.195729-1-mathew.j.martineau@linux.intel.com> References: <20220927193158.195729-1-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: Menglong Dong The mptcp socket and its subflow sockets in accept queue can't be released after the process exit. While the release of a mptcp socket in listening state, the corresponding tcp socket will be released too. Meanwhile, the tcp socket in the unaccept queue will be released too. However, only init subflow is in the unaccept queue, and the joined subflow is not in the unaccept queue, which makes the joined subflow won't be released, and therefore the corresponding unaccepted mptcp socket will not be released to. This can be reproduced easily with following steps: 1. create 2 namespace and veth: $ ip netns add mptcp-client $ ip netns add mptcp-server $ sysctl -w net.ipv4.conf.all.rp_filter=3D0 $ ip netns exec mptcp-client sysctl -w net.mptcp.enabled=3D1 $ ip netns exec mptcp-server sysctl -w net.mptcp.enabled=3D1 $ ip link add red-client netns mptcp-client type veth peer red-server \ netns mptcp-server $ ip -n mptcp-server address add 10.0.0.1/24 dev red-server $ ip -n mptcp-server address add 192.168.0.1/24 dev red-server $ ip -n mptcp-client address add 10.0.0.2/24 dev red-client $ ip -n mptcp-client address add 192.168.0.2/24 dev red-client $ ip -n mptcp-server link set red-server up $ ip -n mptcp-client link set red-client up 2. configure the endpoint and limit for client and server: $ ip -n mptcp-server mptcp endpoint flush $ ip -n mptcp-server mptcp limits set subflow 2 add_addr_accepted 2 $ ip -n mptcp-client mptcp endpoint flush $ ip -n mptcp-client mptcp limits set subflow 2 add_addr_accepted 2 $ ip -n mptcp-client mptcp endpoint add 192.168.0.2 dev red-client id \ 1 subflow 3. listen and accept on a port, such as 9999. The nc command we used here is modified, which makes it use mptcp protocol by default. $ ip netns exec mptcp-server nc -l -k -p 9999 4. open another *two* terminal and use each of them to connect to the server with the following command: $ ip netns exec mptcp-client nc 10.0.0.1 9999 Input something after connect to trigger the connection of the second subflow. So that there are two established mptcp connections, with the second one still unaccepted. 5. exit all the nc command, and check the tcp socket in server namespace. And you will find that there is one tcp socket in CLOSE_WAIT state and can't release forever. Fix this by closing all of the unaccepted mptcp socket in mptcp_subflow_queue_clean() with __mptcp_close(). Now, we can ensure that all unaccepted mptcp sockets will be cleaned by __mptcp_close() before they are released, so mptcp_sock_destruct(), which is used to clean the unaccepted mptcp socket, is not needed anymore. The selftests for mptcp is ran for this commit, and no new failures. Fixes: f296234c98a8 ("mptcp: Add handling of incoming MP_JOIN requests") Fixes: 6aeed9045071 ("mptcp: fix race on unaccepted mptcp sockets") Cc: stable@vger.kernel.org Reviewed-by: Jiang Biao Reviewed-by: Mengen Sun Acked-by: Paolo Abeni Signed-off-by: Menglong Dong Signed-off-by: Mat Martineau --- net/mptcp/protocol.c | 2 +- net/mptcp/protocol.h | 1 + net/mptcp/subflow.c | 33 +++++++-------------------------- 3 files changed, 9 insertions(+), 27 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index f7690414320a..f8897a70c11d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2662,7 +2662,7 @@ static void __mptcp_clear_xmit(struct sock *sk) dfrag_clear(sk, dfrag); } =20 -static void mptcp_cancel_work(struct sock *sk) +void mptcp_cancel_work(struct sock *sk) { struct mptcp_sock *msk =3D mptcp_sk(sk); =20 diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 8f123d450c76..8f372b8f059c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -613,6 +613,7 @@ void mptcp_subflow_queue_clean(struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); bool __mptcp_close(struct sock *sk, long timeout); +void mptcp_cancel_work(struct sock *sk); =20 bool mptcp_addresses_equal(const struct mptcp_addr_info *a, const struct mptcp_addr_info *b, bool use_port); diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c7d49fb6e7bd..07dd23d0fe04 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -602,30 +602,6 @@ static bool subflow_hmac_valid(const struct request_so= ck *req, return !crypto_memneq(hmac, mp_opt->hmac, MPTCPOPT_HMAC_LEN); } =20 -static void mptcp_sock_destruct(struct sock *sk) -{ - /* if new mptcp socket isn't accepted, it is free'd - * from the tcp listener sockets request queue, linked - * from req->sk. The tcp socket is released. - * This calls the ULP release function which will - * also remove the mptcp socket, via - * sock_put(ctx->conn). - * - * Problem is that the mptcp socket will be in - * ESTABLISHED state and will not have the SOCK_DEAD flag. - * Both result in warnings from inet_sock_destruct. - */ - if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { - sk->sk_state =3D TCP_CLOSE; - WARN_ON_ONCE(sk->sk_socket); - sock_orphan(sk); - } - - /* We don't need to clear msk->subflow, as it's still NULL at this point = */ - mptcp_destroy_common(mptcp_sk(sk), 0); - inet_sock_destruct(sk); -} - static void mptcp_force_close(struct sock *sk) { /* the msk is not yet exposed to user-space */ @@ -768,7 +744,6 @@ static struct sock *subflow_syn_recv_sock(const struct = sock *sk, /* new mpc subflow takes ownership of the newly * created mptcp socket */ - new_msk->sk_destruct =3D mptcp_sock_destruct; mptcp_sk(new_msk)->setsockopt_seq =3D ctx->setsockopt_seq; mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1); mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); @@ -1763,13 +1738,19 @@ void mptcp_subflow_queue_clean(struct sock *listene= r_ssk) =20 for (msk =3D head; msk; msk =3D next) { struct sock *sk =3D (struct sock *)msk; - bool slow; + bool slow, do_cancel_work; =20 + sock_hold(sk); slow =3D lock_sock_fast_nested(sk); next =3D msk->dl_next; msk->first =3D NULL; msk->dl_next =3D NULL; + + do_cancel_work =3D __mptcp_close(sk, 0); unlock_sock_fast(sk, slow); + if (do_cancel_work) + mptcp_cancel_work(sk); + sock_put(sk); } =20 /* we are still under the listener msk socket lock */ --=20 2.37.3