From patchwork Thu May 27 16:27:37 2021 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Abeni X-Patchwork-Id: 1484726 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Authentication-Results: ozlabs.org; spf=pass (sender SPF authorized) smtp.mailfrom=lists.linux.dev (client-ip=147.75.69.165; helo=sjc.edge.kernel.org; envelope-from=mptcp+bounces-790-incoming=patchwork.ozlabs.org@lists.linux.dev; receiver=) Authentication-Results: ozlabs.org; dkim=pass (1024-bit key; unprotected) header.d=redhat.com header.i=@redhat.com header.a=rsa-sha256 header.s=mimecast20190719 header.b=DUc1iDpA; dkim-atps=neutral Received: from sjc.edge.kernel.org (sjc.edge.kernel.org [147.75.69.165]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id 4FrYC024k7z9sRK for ; Fri, 28 May 2021 02:27:56 +1000 (AEST) Received: from smtp.subspace.kernel.org (wormhole.subspace.kernel.org [52.25.139.140]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by sjc.edge.kernel.org (Postfix) with ESMTPS id 6C51F3E0F70 for ; Thu, 27 May 2021 16:27:53 +0000 (UTC) Received: from localhost.localdomain (localhost.localdomain [127.0.0.1]) by smtp.subspace.kernel.org (Postfix) with ESMTP id 264A16D0D; Thu, 27 May 2021 16:27:52 +0000 (UTC) X-Original-To: mptcp@lists.linux.dev Received: from us-smtp-delivery-124.mimecast.com (us-smtp-delivery-124.mimecast.com [216.205.24.124]) (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 7D9782FB1 for ; Thu, 27 May 2021 16:27:50 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1622132869; 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; bh=2px95p4hkcmnhkZllQEedDhQ66bSX1yRQo10KOeM1CA=; b=DUc1iDpAhB1qrXqq4SeE7jK/EKLom+iNjb+LUGGodSTgI8tWw62wGJIc6c1BPaOYWooo3J 1ZESe0rsKWZsX4PFjyc8ystW5EuuzNpf8uKHJ8/KQe46GXzrb2JeRsBwqB/V3LVgg0es0L U/KjAnSLja0L0mkJfT4nkCKGYsHpgOs= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-231-QQYDo93_Mja38vL8KKJ3Hw-1; Thu, 27 May 2021 12:27:47 -0400 X-MC-Unique: QQYDo93_Mja38vL8KKJ3Hw-1 Received: from smtp.corp.redhat.com (int-mx07.intmail.prod.int.phx2.redhat.com [10.5.11.22]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id BDE198030A0 for ; Thu, 27 May 2021 16:27:46 +0000 (UTC) Received: from gerbillo.redhat.com (ovpn-114-53.ams2.redhat.com [10.36.114.53]) by smtp.corp.redhat.com (Postfix) with ESMTP id 3480910013C1 for ; Thu, 27 May 2021 16:27:46 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-net] mptcp: wake-up readers only for in sequence data. Date: Thu, 27 May 2021 18:27:37 +0200 Message-Id: <5009954210af20796d1cf88ca630d19ec12e2132.1622132690.git.pabeni@redhat.com> X-Mailing-List: mptcp@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.84 on 10.5.11.22 Authentication-Results: relay.mimecast.com; auth=pass smtp.auth=CUSA124A263 smtp.mailfrom=pabeni@redhat.com X-Mimecast-Spam-Score: 0 X-Mimecast-Originator: redhat.com Currently we relay on the subflow->data_avail field, which is subject to races: ssk1 skb len = 500 DSS(seq=1, len=1000, off=0) # data_avail == MPTCP_SUBFLOW_DATA_AVAIL ssk2 skb len = 500 DSS(seq = 501, len=1000) # data_avail == MPTCP_SUBFLOW_DATA_AVAIL ssk1 skb len = 500 DSS(seq = 1, len=1000, off =500) # still data_avail == MPTCP_SUBFLOW_DATA_AVAIL, # as the skb is covered by a pre-existing map, # which was in-sequence at reception time. Instead we can explicitly check if some has been received in-sequence, propagating the info from __mptcp_move_skbs_from_subflow(). Additionally and the 'ONCE' annotation to the 'data_avail' memory access, as msk will read it outside the subflow socket lock. Fixes: 648ef4b88673 ("mptcp: Implement MPTCP receive path") Signed-off-by: Paolo Abeni --- net/mptcp/protocol.c | 29 +++++++++++------------------ net/mptcp/protocol.h | 1 - net/mptcp/subflow.c | 23 +++++++++-------------- 3 files changed, 20 insertions(+), 33 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 786f09d83d35..1e77d2defd28 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -681,13 +681,13 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) /* In most cases we will be able to lock the mptcp socket. If its already * owned, we need to defer to the work queue to avoid ABBA deadlock. */ -static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) +static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) { struct sock *sk = (struct sock *)msk; unsigned int moved = 0; if (inet_sk_state_load(sk) == TCP_CLOSE) - return; + return false; mptcp_data_lock(sk); @@ -702,6 +702,8 @@ static void move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) if (mptcp_pending_data_fin(sk, NULL)) mptcp_schedule_work(sk); mptcp_data_unlock(sk); + + return moved > 0; } void mptcp_data_ready(struct sock *sk, struct sock *ssk) @@ -709,7 +711,6 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct mptcp_sock *msk = mptcp_sk(sk); int sk_rbuf, ssk_rbuf; - bool wake; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing @@ -718,28 +719,20 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (unlikely(subflow->disposable)) return; - /* move_skbs_to_msk below can legitly clear the data_avail flag, - * but we will need later to properly woke the reader, cache its - * value - */ - wake = subflow->data_avail == MPTCP_SUBFLOW_DATA_AVAIL; - if (wake) - set_bit(MPTCP_DATA_READY, &msk->flags); - ssk_rbuf = READ_ONCE(ssk->sk_rcvbuf); sk_rbuf = READ_ONCE(sk->sk_rcvbuf); if (unlikely(ssk_rbuf > sk_rbuf)) sk_rbuf = ssk_rbuf; - /* over limit? can't append more skbs to msk */ + /* over limit? can't append more skbs to msk, Also, no need to wake-up*/ if (atomic_read(&sk->sk_rmem_alloc) > sk_rbuf) - goto wake; - - move_skbs_to_msk(msk, ssk); + return; -wake: - if (wake) + /* Wake-up the reader only for in-sequence data */ + if (move_skbs_to_msk(msk, ssk)) { + set_bit(MPTCP_DATA_READY, &msk->flags); sk->sk_data_ready(sk); + } } static bool mptcp_do_flush_join_list(struct mptcp_sock *msk) @@ -871,7 +864,7 @@ static struct sock *mptcp_subflow_recv_lookup(const struct mptcp_sock *msk) sock_owned_by_me(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->data_avail) + if (READ_ONCE(subflow->data_avail)) return mptcp_subflow_tcp_sock(subflow); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 74184296b6af..160c2ab09f19 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -373,7 +373,6 @@ mptcp_subflow_rsk(const struct request_sock *rsk) enum mptcp_data_avail { MPTCP_SUBFLOW_NODATA, MPTCP_SUBFLOW_DATA_AVAIL, - MPTCP_SUBFLOW_OOO_DATA }; struct mptcp_delegated_action { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 726bc3d083fa..783a542e5bb7 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -1098,7 +1098,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); if (subflow->data_avail) return true; @@ -1137,18 +1137,13 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, ack_seq); - if (ack_seq == old_ack) { - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; - break; - } else if (after64(ack_seq, old_ack)) { - subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA; - break; + if (unlikely(before64(ack_seq, old_ack))) { + mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + continue; } - /* only accept in-sequence mapping. Old values are spurious - * retransmission - */ - mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + break; } return true; @@ -1168,7 +1163,7 @@ static bool subflow_check_data_avail(struct sock *ssk) subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; tcp_send_active_reset(ssk, GFP_ATOMIC); - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); return false; } @@ -1178,7 +1173,7 @@ static bool subflow_check_data_avail(struct sock *ssk) subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); return true; } @@ -1190,7 +1185,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq,