From nobody Sun May 19 11:06:53 2024 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (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 906DB17735 for ; Mon, 15 Jan 2024 15:16:55 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="K2ATIuqC" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1705331814; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=40IVMdXobO+Gs4HXo+JLXHijtGK669Uqy9VpZjnqPcs=; b=K2ATIuqCEJJTvz1vCYajZkoCPbOWQ1x8eY2vZK0PL8NzRwKLN2om4UMovjbuTvTnzoHlpr FY0KXkfotWhwJVHT6GqdXpCgwuehzW+cZHOrzfoLJe1Lu4OKUYFwEEpyB7EZpKph7UG/a0 CsLC8/gqirM/uX31XMgvM4kmuAWDawc= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-548-g60aTGb-Mcy_lg00juuICw-1; Mon, 15 Jan 2024 10:16:48 -0500 X-MC-Unique: g60aTGb-Mcy_lg00juuICw-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.rdu2.redhat.com [10.11.54.7]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id E1024811E9C for ; Mon, 15 Jan 2024 15:16:47 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.45.225.49]) by smtp.corp.redhat.com (Postfix) with ESMTP id 70E8E1C060B3 for ; Mon, 15 Jan 2024 15:16:47 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-net 1/4] mptcp: drop the push_pending field Date: Mon, 15 Jan 2024 16:16:30 +0100 Message-ID: <8363fd6542b179fdc30b42e78c922b0201c9f3fd.1705331716.git.pabeni@redhat.com> In-Reply-To: References: Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.7 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8"; x-default="true" Such field is there to avoid acquiring the data lock in a few spots, but if adds complexity to the already non trivial locking schema. All the relevant call sites (mptcp-level reinjection, set socket optins), are slow-path, drop such field in favor of 'cb_flags', adding the relevant locking. Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau --- net/mptcp/protocol.c | 12 ++++++------ net/mptcp/protocol.h | 1 - 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e570c7e2b18c..5129e1235cc5 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1505,8 +1505,11 @@ static void mptcp_update_post_push(struct mptcp_sock= *msk, =20 void mptcp_check_and_set_pending(struct sock *sk) { - if (mptcp_send_head(sk)) - mptcp_sk(sk)->push_pending |=3D BIT(MPTCP_PUSH_PENDING); + if (mptcp_send_head(sk)) { + mptcp_data_lock(sk); + mptcp_sk(sk)->cb_flags |=3D BIT(MPTCP_PUSH_PENDING); + mptcp_data_unlock(sk); + } } =20 static int __subflow_push_pending(struct sock *sk, struct sock *ssk, @@ -3145,7 +3148,6 @@ static int mptcp_disconnect(struct sock *sk, int flag= s) mptcp_destroy_common(msk, MPTCP_CF_FASTCLOSE); WRITE_ONCE(msk->flags, 0); msk->cb_flags =3D 0; - msk->push_pending =3D 0; msk->recovery =3D false; msk->can_ack =3D false; msk->fully_established =3D false; @@ -3333,8 +3335,7 @@ static void mptcp_release_cb(struct sock *sk) struct mptcp_sock *msk =3D mptcp_sk(sk); =20 for (;;) { - unsigned long flags =3D (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED) | - msk->push_pending; + unsigned long flags =3D (msk->cb_flags & MPTCP_FLAGS_PROCESS_CTX_NEED); struct list_head join_list; =20 if (!flags) @@ -3350,7 +3351,6 @@ static void mptcp_release_cb(struct sock *sk) * datapath acquires the msk socket spinlock while helding * the subflow socket lock */ - msk->push_pending =3D 0; msk->cb_flags &=3D ~flags; spin_unlock_bh(&sk->sk_lock.slock); =20 diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index f7b9c1b995df..ebb32b7563be 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -286,7 +286,6 @@ struct mptcp_sock { int rmem_released; unsigned long flags; unsigned long cb_flags; - unsigned long push_pending; bool recovery; /* closing subflow write queue reinjected */ bool can_ack; bool fully_established; --=20 2.43.0 From nobody Sun May 19 11:06:53 2024 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (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 44B26175B6 for ; Mon, 15 Jan 2024 15:16:52 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="PdO17wa/" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1705331811; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=dqjthjaFFdHcHkZA01AKebv1RjaCFSHUn2HyjPTFQXI=; b=PdO17wa/OkMvSPnYnEY75+NKpALoAxTQKQ7eUa3MBvNcwSI1XcVgle0PbO1eXT5YGQCuCO gIc+R386l+T6EVHm1kLAPCoI04Lb/aHhVx2BEvZgys7mAVyaqWr+fPZQdmbdpiIBU3osdq ONvRy2upYMbuZS/KVPa/qaBbE6i3Pns= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-46-j1P6KS7ENmKMHjVAoaa0Aw-1; Mon, 15 Jan 2024 10:16:49 -0500 X-MC-Unique: j1P6KS7ENmKMHjVAoaa0Aw-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.rdu2.redhat.com [10.11.54.7]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id A7A529230EA for ; Mon, 15 Jan 2024 15:16:48 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.45.225.49]) by smtp.corp.redhat.com (Postfix) with ESMTP id 36BBB1C060B2 for ; Mon, 15 Jan 2024 15:16:48 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-net 2/4] mptcp: fix rcv space initialization Date: Mon, 15 Jan 2024 16:16:31 +0100 Message-ID: In-Reply-To: References: Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.7 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8"; x-default="true" mptcp_rcv_space_init() is supposed to happen under the msk socket lock, but active msk socket does that without such protection. Leverage the existing mptcp_propagate_state() helper to that extent. We need to ensure mptcp_rcv_space_init will happen before mptcp_rcv_space_adjust(), and the release_cb does not assure that: explicitly check for such condition. While at it, move the wnd_end initialization out of mptcp_rcv_space_init(), it never belonged there. Note that the race does not produce ill effect in practice, but change allows cleaning-up and defying better the locking model. Fixes: a6b118febbab ("mptcp: add receive buffer auto-tuning") Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau --- net/mptcp/protocol.c | 10 ++++++---- net/mptcp/protocol.h | 3 ++- net/mptcp/subflow.c | 4 ++-- 3 files changed, 10 insertions(+), 7 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5129e1235cc5..c41f49532a0a 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1963,6 +1963,9 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock = *msk, int copied) if (copied <=3D 0) return; =20 + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); + msk->rcvq_space.copied +=3D copied; =20 mstamp =3D div_u64(tcp_clock_ns(), NSEC_PER_USEC); @@ -3163,6 +3166,7 @@ static int mptcp_disconnect(struct sock *sk, int flag= s) msk->bytes_received =3D 0; msk->bytes_sent =3D 0; msk->bytes_retrans =3D 0; + msk->rcvspace_init =3D 0; =20 WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); @@ -3250,6 +3254,7 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, con= st struct sock *ssk) { const struct tcp_sock *tp =3D tcp_sk(ssk); =20 + msk->rcvspace_init =3D 1; msk->rcvq_space.copied =3D 0; msk->rcvq_space.rtt_us =3D 0; =20 @@ -3260,8 +3265,6 @@ void mptcp_rcv_space_init(struct mptcp_sock *msk, con= st struct sock *ssk) TCP_INIT_CWND * tp->advmss); if (msk->rcvq_space.space =3D=3D 0) msk->rcvq_space.space =3D TCP_INIT_CWND * TCP_MSS_DEFAULT; - - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); } =20 void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) @@ -3481,10 +3484,9 @@ void mptcp_finish_connect(struct sock *ssk) WRITE_ONCE(msk->write_seq, subflow->idsn + 1); WRITE_ONCE(msk->snd_nxt, msk->write_seq); WRITE_ONCE(msk->snd_una, msk->write_seq); + WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); =20 mptcp_pm_new_connection(msk, ssk, 0); - - mptcp_rcv_space_init(msk, ssk); } =20 void mptcp_sock_graft(struct sock *sk, struct socket *parent) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ebb32b7563be..385aa92926d7 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -304,7 +304,8 @@ struct mptcp_sock { nodelay:1, fastopening:1, in_accept_queue:1, - free_first:1; + free_first:1, + rcvspace_init:1; struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 90984b053adc..23f639e0d8c3 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -424,6 +424,8 @@ void __mptcp_sync_state(struct sock *sk, int state) struct mptcp_sock *msk =3D mptcp_sk(sk); =20 __mptcp_propagate_sndbuf(sk, msk->first); + if (!msk->rcvspace_init) + mptcp_rcv_space_init(msk, msk->first); if (sk->sk_state =3D=3D TCP_SYN_SENT) { mptcp_set_state(sk, state); sk->sk_state_change(sk); @@ -545,7 +547,6 @@ static void subflow_finish_connect(struct sock *sk, con= st struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_rcv_space_init(msk, sk); mptcp_propagate_state(parent, sk); } return; @@ -1744,7 +1745,6 @@ static void subflow_state_change(struct sock *sk) msk =3D mptcp_sk(parent); if (subflow_simultaneous_connect(sk)) { mptcp_do_fallback(sk); - mptcp_rcv_space_init(msk, sk); pr_fallback(msk); subflow->conn_finished =3D 1; mptcp_propagate_state(parent, sk); --=20 2.43.0 From nobody Sun May 19 11:06:53 2024 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.129.124]) (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 1CC8E171C1 for ; Mon, 15 Jan 2024 15:16:51 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="Dz5i37T0" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1705331811; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=dHPvcZhtt0MFRzvsCvtVKUWbmqLJByi6GhibAx3eHeA=; b=Dz5i37T0Kd4O4B9EeNzgBanbgj89qUv4JDaevcQWAw/KsBRh+4vCOpnF75PABdFBTfmb7y 1S1mQh12ud0c9IUdiXZyCLXh0UtUpBp2mZdBkcP0f6pe3zaiA6mlZEShIucLPtCntb6Vb3 7ipFGYDnTx1eJLpfdmaLNth61/aY1sM= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-471-S3WiIHMNMCGA88RbKmHbRg-1; Mon, 15 Jan 2024 10:16:49 -0500 X-MC-Unique: S3WiIHMNMCGA88RbKmHbRg-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.rdu2.redhat.com [10.11.54.7]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 6DDF828240E4 for ; Mon, 15 Jan 2024 15:16:49 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.45.225.49]) by smtp.corp.redhat.com (Postfix) with ESMTP id F0CE81C060B2 for ; Mon, 15 Jan 2024 15:16:48 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-net 3/4] mptcp: fix more tx path fields initialization Date: Mon, 15 Jan 2024 16:16:32 +0100 Message-ID: <2ebb639a44ec33784f79c0b2dcdfc688d3afb868.1705331716.git.pabeni@redhat.com> In-Reply-To: References: Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.7 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8"; x-default="true" The 'msk->write_seq' and 'msk->snd_nxt' are always updated under the msk socket lock, except at MPC handshake completiont time. Builds-up on the previous commit to move such init under the relevant lock. There are no known problems caused by the potential race, the primary goal is consistency. Fixes: 6d0060f600ad ("mptcp: Write MPTCP DSS headers to outgoing data packe= ts") Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau --- net/mptcp/protocol.c | 6 ++---- net/mptcp/subflow.c | 13 +++++++++++-- 2 files changed, 13 insertions(+), 6 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index c41f49532a0a..b7d1da7bcb50 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3481,10 +3481,8 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->write_seq, subflow->idsn + 1); - WRITE_ONCE(msk->snd_nxt, msk->write_seq); - WRITE_ONCE(msk->snd_una, msk->write_seq); - WRITE_ONCE(msk->wnd_end, msk->snd_nxt + tcp_sk(ssk)->snd_wnd); + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); =20 mptcp_pm_new_connection(msk, ssk, 0); } diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 23f639e0d8c3..fe5334cee477 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -421,12 +421,21 @@ static bool subflow_use_different_dport(struct mptcp_= sock *msk, const struct soc =20 void __mptcp_sync_state(struct sock *sk, int state) { + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk =3D mptcp_sk(sk); + struct sock *ssk =3D msk->first; =20 - __mptcp_propagate_sndbuf(sk, msk->first); + subflow =3D mptcp_subflow_ctx(ssk); + __mptcp_propagate_sndbuf(sk, ssk); if (!msk->rcvspace_init) - mptcp_rcv_space_init(msk, msk->first); + mptcp_rcv_space_init(msk, ssk); + if (sk->sk_state =3D=3D TCP_SYN_SENT) { + /* subflow->idsn is always available is TCP_SYN_SENT state, + * even for the FASTOPEN scenarios + */ + WRITE_ONCE(msk->write_seq, subflow->idsn + 1); + WRITE_ONCE(msk->snd_nxt, msk->write_seq); mptcp_set_state(sk, state); sk->sk_state_change(sk); } --=20 2.43.0 From nobody Sun May 19 11:06:53 2024 Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [170.10.133.124]) (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 4269E17735 for ; Mon, 15 Jan 2024 15:16:52 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=redhat.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=redhat.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="HsrfrIZU" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1705331812; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:mime-version:mime-version:content-type:content-type: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=sQCbg/oNqEeYaUooFlP00kT3nA6fl5AFmLqsdJWwxK4=; b=HsrfrIZUAkMqH3kwUAyEUEqxNdiMrJ6DzYIskqnbN5TohWJHNMP3LqITl3BBkv3EWZIle3 r+2Mm2+ukx+qTXY6eZpGVQKm9h/1nEV2viV7mGNr2cJYjnQChB5bDu3C3Pop+NvU7Oos63 X9uMVLGR8yTpmi3xwpOmm6msNwd0wk0= Received: from mimecast-mx02.redhat.com (mx-ext.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.3, cipher=TLS_AES_256_GCM_SHA384) id us-mta-562-4ct-8JI0O--d0BB70KbW0Q-1; Mon, 15 Jan 2024 10:16:50 -0500 X-MC-Unique: 4ct-8JI0O--d0BB70KbW0Q-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.rdu2.redhat.com [10.11.54.7]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature RSA-PSS (2048 bits) server-digest SHA256) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 33C733814586 for ; Mon, 15 Jan 2024 15:16:50 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.45.225.49]) by smtp.corp.redhat.com (Postfix) with ESMTP id B73251C060B2 for ; Mon, 15 Jan 2024 15:16:49 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-net 4/4] mptcp: corner case locking for rx path fields initialization Date: Mon, 15 Jan 2024 16:16:33 +0100 Message-ID: <56241fbd64982b15aed04269c8b963206661acea.1705331716.git.pabeni@redhat.com> In-Reply-To: References: Precedence: bulk X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Scanned-By: MIMEDefang 3.4.1 on 10.11.54.7 X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8"; x-default="true" Most MPTCP-level related fields are under the mptcp data lock protection, but are written one-off without such lock at MPC complete time, both for the client and the server Leverage the mptcp_propagate_state() infrastructure to move such initialization under the proper lock client-wise. The server side critical init steps are done by mptcp_subflow_fully_established(): ensure the caller properly held the relevant lock, and avoid acquiring the same lock in the nested scopes. There are no real potential races, as write access to such fields is implicitly serialized by the MPTCP state machine; the primary goal is consistency. Fixes: d22f4988ffec ("mptcp: process MP_CAPABLE data option") Signed-off-by: Paolo Abeni Reviewed-by: Mat Martineau --- net/mptcp/fastopen.c | 6 ++--- net/mptcp/options.c | 9 +++---- net/mptcp/protocol.c | 9 ++++--- net/mptcp/protocol.h | 9 +++---- net/mptcp/subflow.c | 56 +++++++++++++++++++++++++------------------- 5 files changed, 50 insertions(+), 39 deletions(-) diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 74698582a285..ad28da655f8b 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -59,13 +59,12 @@ void mptcp_fastopen_subflow_synack_set_params(struct mp= tcp_subflow_context *subf mptcp_data_unlock(sk); } =20 -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_su= bflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_= subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { struct sock *sk =3D (struct sock *)msk; struct sk_buff *skb; =20 - mptcp_data_lock(sk); skb =3D skb_peek_tail(&sk->sk_receive_queue); if (skb) { WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq); @@ -77,5 +76,4 @@ void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk= , struct mptcp_subflow_ } =20 pr_debug("msk=3D%p ack_seq=3D%llx", msk, msk->ack_seq); - mptcp_data_unlock(sk); } diff --git a/net/mptcp/options.c b/net/mptcp/options.c index d2527d189a79..e3e96a49f922 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -962,9 +962,7 @@ static bool check_fully_established(struct mptcp_sock *= msk, struct sock *ssk, /* subflows are fully established as soon as we get any * additional ack, including ADD_ADDR. */ - subflow->fully_established =3D 1; - WRITE_ONCE(msk->fully_established, true); - goto check_notify; + goto set_fully_established; } =20 /* If the first established packet does not contain MP_CAPABLE + data @@ -986,7 +984,10 @@ static bool check_fully_established(struct mptcp_sock = *msk, struct sock *ssk, set_fully_established: if (unlikely(!READ_ONCE(msk->pm.server_side))) pr_warn_once("bogus mpc option on established client sk"); - mptcp_subflow_fully_established(subflow, mp_opt); + + mptcp_data_lock((struct sock *)msk); + __mptcp_subflow_fully_established(msk, subflow, mp_opt); + mptcp_data_unlock((struct sock *)msk); =20 check_notify: /* if the subflow is not already linked into the conn_list, we can't diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b7d1da7bcb50..70108854ec9b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3189,6 +3189,7 @@ struct sock *mptcp_sk_clone_init(const struct sock *s= k, { struct mptcp_subflow_request_sock *subflow_req =3D mptcp_subflow_rsk(req); struct sock *nsk =3D sk_clone_lock(sk, GFP_ATOMIC); + struct mptcp_subflow_context *subflow; struct mptcp_sock *msk; =20 if (!nsk) @@ -3229,7 +3230,8 @@ struct sock *mptcp_sk_clone_init(const struct sock *s= k, =20 /* The msk maintain a ref to each subflow in the connections list */ WRITE_ONCE(msk->first, ssk); - list_add(&mptcp_subflow_ctx(ssk)->node, &msk->conn_list); + subflow =3D mptcp_subflow_ctx(ssk); + list_add(&subflow->node, &msk->conn_list); sock_hold(ssk); =20 /* new mpc subflow takes ownership of the newly @@ -3244,6 +3246,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *s= k, __mptcp_propagate_sndbuf(nsk, ssk); =20 mptcp_rcv_space_init(msk, ssk); + + if (mp_opt->suboptions & OPTION_MPTCP_MPC_ACK) + __mptcp_subflow_fully_established(msk, subflow, mp_opt); bh_unlock_sock(nsk); =20 /* note: the newly allocated socket refcount is 2 now */ @@ -3481,8 +3486,6 @@ void mptcp_finish_connect(struct sock *ssk) * accessing the field below */ WRITE_ONCE(msk->local_key, subflow->local_key); - WRITE_ONCE(msk->snd_una, subflow->idsn + 1); - WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); =20 mptcp_pm_new_connection(msk, ssk, 0); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 385aa92926d7..d442d876f465 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -622,8 +622,9 @@ unsigned int mptcp_stale_loss_cnt(const struct net *net= ); unsigned int mptcp_close_timeout(const struct sock *sk); int mptcp_get_pm_type(const struct net *net); const char *mptcp_get_scheduler(const struct net *net); -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt); bool __mptcp_retransmit_pending_data(struct sock *sk); void mptcp_check_and_set_pending(struct sock *sk); void __mptcp_push_pending(struct sock *sk, unsigned int flags); @@ -957,8 +958,8 @@ void mptcp_event_pm_listener(const struct sock *ssk, enum mptcp_event_type event); bool mptcp_userspace_pm_active(const struct mptcp_sock *msk); =20 -void mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_su= bflow_context *subflow, - const struct mptcp_options_received *mp_opt); +void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_= subflow_context *subflow, + const struct mptcp_options_received *mp_opt); void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context= *subflow, struct request_sock *req); =20 diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index fe5334cee477..52568227c229 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -441,20 +441,6 @@ void __mptcp_sync_state(struct sock *sk, int state) } } =20 -static void mptcp_propagate_state(struct sock *sk, struct sock *ssk) -{ - struct mptcp_sock *msk =3D mptcp_sk(sk); - - mptcp_data_lock(sk); - if (!sock_owned_by_user(sk)) { - __mptcp_sync_state(sk, ssk->sk_state); - } else { - msk->pending_state =3D ssk->sk_state; - __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); - } - mptcp_data_unlock(sk); -} - static void subflow_set_remote_key(struct mptcp_sock *msk, struct mptcp_subflow_context *subflow, const struct mptcp_options_received *mp_opt) @@ -476,6 +462,31 @@ static void subflow_set_remote_key(struct mptcp_sock *= msk, atomic64_set(&msk->rcv_wnd_sent, subflow->iasn); } =20 +static void mptcp_propagate_state(struct sock *sk, struct sock *ssk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) +{ + struct mptcp_sock *msk =3D mptcp_sk(sk); + + mptcp_data_lock(sk); + if (mp_opt) { + /* Options are available only in the non fallback cases + * avoid updating rx path fields otherwise + */ + WRITE_ONCE(msk->snd_una, subflow->idsn + 1); + WRITE_ONCE(msk->wnd_end, subflow->idsn + 1 + tcp_sk(ssk)->snd_wnd); + subflow_set_remote_key(msk, subflow, mp_opt); + } + + if (!sock_owned_by_user(sk)) { + __mptcp_sync_state(sk, ssk->sk_state); + } else { + msk->pending_state =3D ssk->sk_state; + __set_bit(MPTCP_SYNC_STATE, &msk->cb_flags); + } + mptcp_data_unlock(sk); +} + static void subflow_finish_connect(struct sock *sk, const struct sk_buff *= skb) { struct mptcp_subflow_context *subflow =3D mptcp_subflow_ctx(sk); @@ -510,10 +521,9 @@ static void subflow_finish_connect(struct sock *sk, co= nst struct sk_buff *skb) if (mp_opt.deny_join_id0) WRITE_ONCE(msk->pm.remote_deny_join_id0, true); subflow->mp_capable =3D 1; - subflow_set_remote_key(msk, subflow, &mp_opt); MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEACTIVEACK); mptcp_finish_connect(sk); - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, &mp_opt); } else if (subflow->request_join) { u8 hmac[SHA256_DIGEST_SIZE]; =20 @@ -556,7 +566,7 @@ static void subflow_finish_connect(struct sock *sk, con= st struct sk_buff *skb) } } else if (mptcp_check_fallback(sk)) { fallback: - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } return; =20 @@ -741,17 +751,16 @@ void mptcp_subflow_drop_ctx(struct sock *ssk) kfree_rcu(ctx, rcu); } =20 -void mptcp_subflow_fully_established(struct mptcp_subflow_context *subflow, - const struct mptcp_options_received *mp_opt) +void __mptcp_subflow_fully_established(struct mptcp_sock *msk, + struct mptcp_subflow_context *subflow, + const struct mptcp_options_received *mp_opt) { - struct mptcp_sock *msk =3D mptcp_sk(subflow->conn); - subflow_set_remote_key(msk, subflow, mp_opt); subflow->fully_established =3D 1; WRITE_ONCE(msk->fully_established, true); =20 if (subflow->is_mptfo) - mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); + __mptcp_fastopen_gen_msk_ackseq(msk, subflow, mp_opt); } =20 static struct sock *subflow_syn_recv_sock(const struct sock *sk, @@ -844,7 +853,6 @@ static struct sock *subflow_syn_recv_sock(const struct = sock *sk, * mpc option */ if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { - mptcp_subflow_fully_established(ctx, &mp_opt); mptcp_pm_fully_established(owner, child); ctx->pm_notified =3D 1; } @@ -1756,7 +1764,7 @@ static void subflow_state_change(struct sock *sk) mptcp_do_fallback(sk); pr_fallback(msk); subflow->conn_finished =3D 1; - mptcp_propagate_state(parent, sk); + mptcp_propagate_state(parent, sk, subflow, NULL); } =20 /* as recvmsg() does not acquire the subflow socket for ssk selection --=20 2.43.0