From patchwork Fri Jul 29 15:33:01 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Abeni X-Patchwork-Id: 12932560 X-Patchwork-Delegate: matthieu.baerts@tessares.net 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 146C34A23 for ; Fri, 29 Jul 2022 15:33:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1659108835; 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=bOxjCT/a5P87RNatFo2lM2GkXg3NSBmm+aMpbukibtQ=; b=fnCt1ad34yhqTsL//opqkz/EJK0s1WbprzW6AMC+f1xjj3qK3YOqEve3krd8aT3qzINkuC F0UCAlKZLI/e5hLBweFKmygIhxjTQBsDGC4InGqHgu3CGzhuqoDAvOa5Cfc02ui7Nod7n6 i0tlnzY94cjbMsrwzclIoQnpRxznJLM= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-635-K-Gdf8SPPlqbakLZ3R-crw-1; Fri, 29 Jul 2022 11:33:53 -0400 X-MC-Unique: K-Gdf8SPPlqbakLZ3R-crw-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 38F9185A581 for ; Fri, 29 Jul 2022 15:33:53 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.39.192.205]) by smtp.corp.redhat.com (Postfix) with ESMTP id BD80418ECB for ; Fri, 29 Jul 2022 15:33:52 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-next 1/4] mptcp: move RCVPRUNE event later Date: Fri, 29 Jul 2022 17:33:01 +0200 Message-Id: <81be75dff29adfdc136035168f5bcd6d1378b0b4.1659107989.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 2.79 on 10.11.54.5 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 This clean the code a bit, and avoid skipping msk receive buffer update on some weird corner case. Signed-off-by: Paolo Abeni --- net/mptcp/protocol.c | 19 +++++-------------- 1 file changed, 5 insertions(+), 14 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 970da88cd04f..5af3d591a20b 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -642,6 +642,10 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk, } } + /* over limit? can't append more skbs to msk */ + if (__mptcp_rmem(sk) > sk_rbuf) + return true; + pr_debug("msk=%p ssk=%p", msk, ssk); tp = tcp_sk(ssk); do { @@ -786,8 +790,6 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) 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; /* The peer can send data while we are shutting down this * subflow at msk destruction time, but we must avoid enqueuing @@ -796,20 +798,9 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) if (unlikely(subflow->disposable)) return; - 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, Also, no need to wake-up*/ - if (__mptcp_rmem(sk) > sk_rbuf) { - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED); - return; - } - /* Wake-up the reader only for in-sequence data */ mptcp_data_lock(sk); - if (move_skbs_to_msk(msk, ssk)) + if (move_skbs_to_msk(mptcp_sk(sk), ssk)) sk->sk_data_ready(sk); mptcp_data_unlock(sk); From patchwork Fri Jul 29 15:33:02 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Abeni X-Patchwork-Id: 12932559 X-Patchwork-Delegate: matthieu.baerts@tessares.net 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 BB92C4A28 for ; Fri, 29 Jul 2022 15:33:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1659108835; 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=bNLfFuFWLjtQN+kAi5MaO4NDu794mtg+Vhw0dqUf3/c=; b=Cayvd+ArHAtCTUOa2UGuS8ZI9qPRkfvMaKO0+g9Xn4oeLscwhMRcA4sRG0hjBc2TGxT2uq sQU/NBGCwKNNDWtJJpqFcAWR0Zh7wdfUpj2hZvXh+PhxnlyBoOpdizEd6TgoVgOfFpFHA6 ddLy8YcWwShy4UAqR9gkrqrca4kpb7E= Received: from mimecast-mx02.redhat.com (mx3-rdu2.redhat.com [66.187.233.73]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-153-TKZESC_eM9m1JxROww0MMw-1; Fri, 29 Jul 2022 11:33:54 -0400 X-MC-Unique: TKZESC_eM9m1JxROww0MMw-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id EFA4C299E741 for ; Fri, 29 Jul 2022 15:33:53 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.39.192.205]) by smtp.corp.redhat.com (Postfix) with ESMTP id 7F95318ECB for ; Fri, 29 Jul 2022 15:33:53 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-next 2/4] mptcp: more accurate receive buffer updates Date: Fri, 29 Jul 2022 17:33:02 +0200 Message-Id: <63def511912bf79d6af065dccb155e9304932640.1659107989.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 2.79 on 10.11.54.5 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 mptcp_cleanup_rbuf() makes a significant effort to avoid acquiring the subflow socket lock, estimating if the tcp level cleanup could actually send an ack. Such estimate is a bit rough when accounting for receive window change, as it consider the msk available buffer space instead of the announced mptcp-level window. Let's consider the announced window instead, mirroring closely the plain TCP implementation. We need to lockless access a bunch of additional, tcp fields. Signed-off-by: Paolo Abeni Reported-by: kernel test robot Reported-by: kernel test robot --- include/net/mptcp.h | 2 ++ net/ipv4/tcp.c | 3 +++ net/mptcp/options.c | 1 - net/mptcp/protocol.c | 14 +++++++++++--- net/mptcp/protocol.h | 6 +++++- 5 files changed, 21 insertions(+), 5 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 7af7fd48acc7..4b6c66b73bf4 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -136,6 +136,7 @@ static inline bool rsk_drop_req(const struct request_sock *req) return tcp_rsk(req)->is_mptcp && tcp_rsk(req)->drop_req; } +void mptcp_receive_window(const struct sock *ssk, int *rwnd); void mptcp_space(const struct sock *ssk, int *space, int *full_space); bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb, unsigned int *size, struct mptcp_out_options *opts); @@ -284,6 +285,7 @@ static inline bool mptcp_skb_can_collapse(const struct sk_buff *to, return true; } +static inline void mptcp_receive_window(const struct sock *ssk, int *rwnd) { } static inline void mptcp_space(const struct sock *ssk, int *s, int *fs) { } static inline void mptcp_seq_show(struct seq_file *seq) { } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 970e9a2cca4a..9e2df51c0558 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1606,6 +1606,9 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied) if (copied > 0 && !time_to_ack && !(sk->sk_shutdown & RCV_SHUTDOWN)) { __u32 rcv_window_now = tcp_receive_window(tp); + if (is_tcpsk(sk)) + mptcp_receive_window(sk, &rcv_window_now); + /* Optimize, __tcp_select_window() is not cheap. */ if (2*rcv_window_now <= tp->window_clamp) { __u32 new_window = __tcp_select_window(sk); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 30d289044e71..563ef8fe5a85 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -604,7 +604,6 @@ static bool mptcp_established_options_dss(struct sock *sk, struct sk_buff *skb, } opts->ext_copy.use_ack = 1; opts->suboptions = OPTION_MPTCP_DSS; - WRITE_ONCE(msk->old_wspace, __mptcp_space((struct sock *)msk)); /* Add kind/length/subtype/flag overhead if mapping is not populated */ if (dss_size == 0) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5af3d591a20b..17e2dbe43639 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -535,6 +535,14 @@ static void mptcp_subflow_cleanup_rbuf(struct sock *ssk) unlock_sock_fast(ssk, slow); } +void mptcp_receive_window(const struct sock *ssk, int *rwnd) +{ + const struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + const struct sock *sk = subflow->conn; + + *rwnd = __mptcp_receive_window(mptcp_sk(sk)); +} + static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) { const struct inet_connection_sock *icsk = inet_csk(ssk); @@ -550,13 +558,13 @@ static bool mptcp_subflow_could_cleanup(const struct sock *ssk, bool rx_empty) static void mptcp_cleanup_rbuf(struct mptcp_sock *msk) { - int old_space = READ_ONCE(msk->old_wspace); + int cur_window = __mptcp_receive_window(msk); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; - int space = __mptcp_space(sk); + int new_window = __mptcp_space(sk); bool cleanup, rx_empty; - cleanup = (space > 0) && (space >= (old_space << 1)); + cleanup = new_window > 0 && new_window >= (cur_window << 1); rx_empty = !__mptcp_rmem(sk); mptcp_for_each_subflow(msk, subflow) { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 1bc9f6e77ddd..a54f42462a71 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -260,7 +260,6 @@ struct mptcp_sock { int rmem_fwd_alloc; struct sock *last_snd; int snd_burst; - int old_wspace; u64 recovery_snd_nxt; /* in recovery mode accept up to this seq; * recovery related fields are under data_lock * protection @@ -336,6 +335,11 @@ static inline int __mptcp_rmem(const struct sock *sk) return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released); } +static inline int __mptcp_receive_window(const struct mptcp_sock *msk) +{ + return atomic64_read(&msk->rcv_wnd_sent) - msk->ack_seq; +} + static inline int __mptcp_space(const struct sock *sk) { return tcp_win_from_space(sk, READ_ONCE(sk->sk_rcvbuf) - __mptcp_rmem(sk)); From patchwork Fri Jul 29 15:33:03 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Abeni X-Patchwork-Id: 12932562 X-Patchwork-Delegate: matthieu.baerts@tessares.net 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 5949A4A29 for ; Fri, 29 Jul 2022 15:33:57 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1659108836; 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=di1M1iI/C4rvUB+B/Yb9KszVmeyN1pzBSPraUBr5na0=; b=QOG15R1lcpJSXs6oVhrVb5dDCx6zJNqIw9KD/pKI8RhPGrVr5bU81j9A31mJ54foYeJzRi 3sUhmGLlz+PtEni3vj/7ZnEQOz8n4lA0TsTt/gebX8lHXELLrdbjun2Nv77Kp2uVjHfMYR oH/Zpo1p/HJNiyxHtTi1PXEwi9Q1iOI= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-460-2KXdJmfdNBqGFig2Sg9m3A-1; Fri, 29 Jul 2022 11:33:54 -0400 X-MC-Unique: 2KXdJmfdNBqGFig2Sg9m3A-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id B1D738032F0 for ; Fri, 29 Jul 2022 15:33:54 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.39.192.205]) by smtp.corp.redhat.com (Postfix) with ESMTP id 41C0790A11 for ; Fri, 29 Jul 2022 15:33:54 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-next 3/4] mptcp: move msk input path under full msk socket lock Date: Fri, 29 Jul 2022 17:33:03 +0200 Message-Id: <3fdd375269bc0bad45ccadfca268dcb3ac3389c1.1659107989.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 2.79 on 10.11.54.5 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 Signed-off-by: Paolo Abeni Reported-by: kernel test robot Reported-by: kernel test robot --- net/mptcp/protocol.c | 79 ++++++++++++++++++++------------------------ net/mptcp/protocol.h | 2 +- 2 files changed, 36 insertions(+), 45 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 17e2dbe43639..b9402a13a69d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -795,7 +795,7 @@ static bool move_skbs_to_msk(struct mptcp_sock *msk, struct sock *ssk) return moved > 0; } -void mptcp_data_ready(struct sock *sk, struct sock *ssk) +void __mptcp_data_ready(struct sock *sk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -807,10 +807,17 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk) return; /* Wake-up the reader only for in-sequence data */ - mptcp_data_lock(sk); if (move_skbs_to_msk(mptcp_sk(sk), ssk)) sk->sk_data_ready(sk); +} +void mptcp_data_ready(struct sock *sk, struct sock *ssk) +{ + mptcp_data_lock(sk); + if (!sock_owned_by_user(sk)) + __mptcp_data_ready(sk, ssk); + else + __set_bit(MPTCP_DEQUEUE, &mptcp_sk(sk)->cb_flags); mptcp_data_unlock(sk); } @@ -1059,6 +1066,7 @@ static void mptcp_clean_una_wakeup(struct sock *sk) mptcp_data_unlock(sk); } + static void mptcp_enter_memory_pressure(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1768,16 +1776,22 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) return copied ? : ret; } -static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, +static bool __mptcp_move_skbs(struct sock *sk); + +static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg, size_t len, int flags, struct scm_timestamping_internal *tss, int *cmsg_flags) { + struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; int copied = 0; - skb_queue_walk_safe(&msk->receive_queue, skb, tmp) { + if (skb_queue_empty(&sk->sk_receive_queue) && !__mptcp_move_skbs(sk)) + return 0; + + skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) { u32 offset = MPTCP_SKB_CB(skb)->offset; u32 data_len = skb->len - offset; u32 count = min_t(size_t, len - copied, data_len); @@ -1811,7 +1825,7 @@ static int __mptcp_recvmsg_mskq(struct mptcp_sock *msk, /* we will bulk release the skb memory later */ skb->destructor = NULL; WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); - __skb_unlink(skb, &msk->receive_queue); + __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); } @@ -1932,16 +1946,9 @@ static void __mptcp_update_rmem(struct sock *sk) WRITE_ONCE(msk->rmem_released, 0); } -static void __mptcp_splice_receive_queue(struct sock *sk) +static bool __mptcp_move_skbs(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); - - skb_queue_splice_tail_init(&sk->sk_receive_queue, &msk->receive_queue); -} - -static bool __mptcp_move_skbs(struct mptcp_sock *msk) -{ - struct sock *sk = (struct sock *)msk; unsigned int moved = 0; bool ret, done; @@ -1949,37 +1956,29 @@ static bool __mptcp_move_skbs(struct mptcp_sock *msk) struct sock *ssk = mptcp_subflow_recv_lookup(msk); bool slowpath; - /* we can have data pending in the subflows only if the msk - * receive buffer was full at subflow_data_ready() time, - * that is an unlikely slow path. - */ - if (likely(!ssk)) + if (unlikely(!ssk)) break; slowpath = lock_sock_fast(ssk); - mptcp_data_lock(sk); __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); - mptcp_data_unlock(sk); if (unlikely(ssk->sk_err)) __mptcp_error_report(sk); unlock_sock_fast(ssk, slowpath); } while (!done); - /* acquire the data lock only if some input data is pending */ ret = moved > 0; if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) || - !skb_queue_empty_lockless(&sk->sk_receive_queue)) { - mptcp_data_lock(sk); + !skb_queue_empty(&sk->sk_receive_queue)) { __mptcp_update_rmem(sk); ret |= __mptcp_ofo_queue(msk); - __mptcp_splice_receive_queue(sk); - mptcp_data_unlock(sk); } - if (ret) + if (ret) { + mptcp_cleanup_rbuf(msk); mptcp_check_data_fin((struct sock *)msk); - return !skb_queue_empty(&msk->receive_queue); + } + return ret; } static unsigned int mptcp_inq_hint(const struct sock *sk) @@ -1987,7 +1986,7 @@ static unsigned int mptcp_inq_hint(const struct sock *sk) const struct mptcp_sock *msk = mptcp_sk(sk); const struct sk_buff *skb; - skb = skb_peek(&msk->receive_queue); + skb = skb_peek(&sk->sk_receive_queue); if (skb) { u64 hint_val = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq; @@ -2033,7 +2032,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, while (copied < len) { int bytes_read; - bytes_read = __mptcp_recvmsg_mskq(msk, msg, len - copied, flags, &tss, &cmsg_flags); + bytes_read = __mptcp_recvmsg_mskq(sk, msg, len - copied, flags, &tss, &cmsg_flags); if (unlikely(bytes_read < 0)) { if (!copied) copied = bytes_read; @@ -2045,9 +2044,6 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, /* be sure to advertise window change */ mptcp_cleanup_rbuf(msk); - if (skb_queue_empty(&msk->receive_queue) && __mptcp_move_skbs(msk)) - continue; - /* only the master socket status is relevant here. The exit * conditions mirror closely tcp_recvmsg() */ @@ -2074,7 +2070,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, /* race breaker: the shutdown could be after the * previous receive queue check */ - if (__mptcp_move_skbs(msk)) + if (__mptcp_move_skbs(sk)) continue; break; } @@ -2111,9 +2107,8 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, } } - pr_debug("msk=%p rx queue empty=%d:%d copied=%d", - msk, skb_queue_empty_lockless(&sk->sk_receive_queue), - skb_queue_empty(&msk->receive_queue), copied); + pr_debug("msk=%p rx queue empty=%d copied=%d", + msk, skb_queue_empty(&sk->sk_receive_queue), copied); if (!(flags & MSG_PEEK)) mptcp_rcv_space_adjust(msk, copied); @@ -2566,7 +2561,6 @@ static int __mptcp_init_sock(struct sock *sk) INIT_LIST_HEAD(&msk->join_list); INIT_LIST_HEAD(&msk->rtx_queue); INIT_WORK(&msk->work, mptcp_worker); - __skb_queue_head_init(&msk->receive_queue); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; msk->rmem_fwd_alloc = 0; @@ -3048,12 +3042,8 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, flags); - /* move to sk_receive_queue, sk_stream_kill_queues will purge it */ - mptcp_data_lock(sk); - skb_queue_splice_tail_init(&msk->receive_queue, &sk->sk_receive_queue); __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); - mptcp_data_unlock(sk); /* move all the rx fwd alloc into the sk_mem_reclaim_final in * inet_sock_destruct() will dispose it @@ -3135,6 +3125,8 @@ static void mptcp_release_cb(struct sock *sk) __mptcp_flush_join_list(sk); if (flags & BIT(MPTCP_PUSH_PENDING)) __mptcp_push_pending(sk, 0); + if ((flags & BIT(MPTCP_DEQUEUE)) && __mptcp_move_skbs(sk)) + sk->sk_data_ready(sk); if (flags & BIT(MPTCP_RETRANSMIT)) __mptcp_retrans(sk); @@ -3383,7 +3375,7 @@ static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg) return -EINVAL; lock_sock(sk); - __mptcp_move_skbs(msk); + __mptcp_move_skbs(sk); answ = mptcp_inq_hint(sk); release_sock(sk); break; @@ -3619,8 +3611,7 @@ 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)) + if (skb_queue_empty_lockless(&((struct sock *)msk)->sk_receive_queue)) return 0; return EPOLLIN | EPOLLRDNORM; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index a54f42462a71..99c710e1ff5c 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -125,6 +125,7 @@ #define MPTCP_FLUSH_JOIN_LIST 5 #define MPTCP_CONNECTED 6 #define MPTCP_RESET_SCHEDULER 7 +#define MPTCP_DEQUEUE 8 static inline bool before64(__u64 seq1, __u64 seq2) { @@ -288,7 +289,6 @@ struct mptcp_sock { struct work_struct work; struct sk_buff *ooo_last_skb; struct rb_root out_of_order_queue; - struct sk_buff_head receive_queue; struct list_head conn_list; struct list_head rtx_queue; struct mptcp_data_frag *first_pending; From patchwork Fri Jul 29 15:33:04 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Paolo Abeni X-Patchwork-Id: 12932561 X-Patchwork-Delegate: matthieu.baerts@tessares.net 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 81B754C67 for ; Fri, 29 Jul 2022 15:33:58 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1659108837; 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=RcD0XgS5CQtJH05z28AzMNQ3avH8pEU8s6cv8rKq/v8=; b=RAv2dT6m1Og8di+PRBGO41c8ZbLvuSEsPniQSdpjplVgq37V6SBVod0MIr6w4E1pExB9S6 tOlL67xNR45foMUBspD6m8XNtycUA1OEYAb5OiVcgJ0vHXS3hki6WKl8URAAAUwbY6mIV5 OkaOjElUpu5WRrCP2/DZhGSkfmoIVMI= Received: from mimecast-mx02.redhat.com (mimecast-mx02.redhat.com [66.187.233.88]) by relay.mimecast.com with ESMTP with STARTTLS (version=TLSv1.2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id us-mta-661-oqqT7AVoPTqNet3IpM13Hw-1; Fri, 29 Jul 2022 11:33:55 -0400 X-MC-Unique: oqqT7AVoPTqNet3IpM13Hw-1 Received: from smtp.corp.redhat.com (int-mx05.intmail.prod.int.rdu2.redhat.com [10.11.54.5]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx02.redhat.com (Postfix) with ESMTPS id 75F3E811E7A for ; Fri, 29 Jul 2022 15:33:55 +0000 (UTC) Received: from gerbillo.redhat.com (unknown [10.39.192.205]) by smtp.corp.redhat.com (Postfix) with ESMTP id 041F490A00 for ; Fri, 29 Jul 2022 15:33:54 +0000 (UTC) From: Paolo Abeni To: mptcp@lists.linux.dev Subject: [PATCH mptcp-next 4/4] mptcp: use common helper for rmem memory accounting Date: Fri, 29 Jul 2022 17:33:04 +0200 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 2.79 on 10.11.54.5 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 Signed-off-by: Paolo Abeni --- net/mptcp/protocol.c | 112 ++++--------------------------------------- net/mptcp/protocol.h | 4 +- 2 files changed, 9 insertions(+), 107 deletions(-) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index b9402a13a69d..130afd239ecf 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -131,11 +131,6 @@ static void mptcp_drop(struct sock *sk, struct sk_buff *skb) __kfree_skb(skb); } -static void mptcp_rmem_charge(struct sock *sk, int size) -{ - mptcp_sk(sk)->rmem_fwd_alloc -= size; -} - static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, struct sk_buff *from) { @@ -152,7 +147,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to, MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq; kfree_skb_partial(from, fragstolen); atomic_add(delta, &sk->sk_rmem_alloc); - mptcp_rmem_charge(sk, delta); + sk->sk_forward_alloc -= delta; return true; } @@ -165,44 +160,6 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, return mptcp_try_coalesce((struct sock *)msk, to, from); } -static void __mptcp_rmem_reclaim(struct sock *sk, int amount) -{ - amount >>= PAGE_SHIFT; - mptcp_sk(sk)->rmem_fwd_alloc -= amount << PAGE_SHIFT; - __sk_mem_reduce_allocated(sk, amount); -} - -static void mptcp_rmem_uncharge(struct sock *sk, int size) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - int reclaimable; - - msk->rmem_fwd_alloc += size; - reclaimable = msk->rmem_fwd_alloc - sk_unused_reserved_mem(sk); - - /* see sk_mem_uncharge() for the rationale behind the following schema */ - if (unlikely(reclaimable >= PAGE_SIZE)) - __mptcp_rmem_reclaim(sk, reclaimable); -} - -static void mptcp_rfree(struct sk_buff *skb) -{ - unsigned int len = skb->truesize; - struct sock *sk = skb->sk; - - atomic_sub(len, &sk->sk_rmem_alloc); - mptcp_rmem_uncharge(sk, len); -} - -static void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk) -{ - skb_orphan(skb); - skb->sk = sk; - skb->destructor = mptcp_rfree; - atomic_add(skb->truesize, &sk->sk_rmem_alloc); - mptcp_rmem_charge(sk, skb->truesize); -} - /* "inspired" by tcp_data_queue_ofo(), main differences: * - use mptcp seqs * - don't cope with sacks @@ -315,25 +272,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) end: skb_condense(skb); - mptcp_set_owner_r(skb, sk); -} - -static bool mptcp_rmem_schedule(struct sock *sk, struct sock *ssk, int size) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - int amt, amount; - - if (size <= msk->rmem_fwd_alloc) - return true; - - size -= msk->rmem_fwd_alloc; - amt = sk_mem_pages(size); - amount = amt << PAGE_SHIFT; - if (!__sk_mem_raise_allocated(sk, size, amt, SK_MEM_RECV)) - return false; - - msk->rmem_fwd_alloc += amount; - return true; + skb_set_owner_r(skb, sk); } static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, @@ -350,8 +289,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, skb_ext_reset(skb); skb_orphan(skb); - /* try to fetch required memory from subflow */ - if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) + if (!sk_rmem_schedule(sk, skb, skb->truesize)) goto drop; has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp; @@ -372,7 +310,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, if (tail && mptcp_try_coalesce(sk, tail, skb)) return true; - mptcp_set_owner_r(skb, sk); + skb_set_owner_r(skb, sk); __skb_queue_tail(&sk->sk_receive_queue, skb); return true; } else if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq)) { @@ -1784,7 +1722,6 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, struct scm_timestamping_internal *tss, int *cmsg_flags) { - struct mptcp_sock *msk = mptcp_sk(sk); struct sk_buff *skb, *tmp; int copied = 0; @@ -1822,9 +1759,10 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, } if (!(flags & MSG_PEEK)) { - /* we will bulk release the skb memory later */ + /* avoid the indirect call, we know the destructor is sock_wfree */ skb->destructor = NULL; - WRITE_ONCE(msk->rmem_released, msk->rmem_released + skb->truesize); + atomic_sub(skb->truesize, &sk->sk_rmem_alloc); + sk_mem_uncharge(sk, skb->truesize); __skb_unlink(skb, &sk->sk_receive_queue); __kfree_skb(skb); } @@ -1934,18 +1872,6 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) msk->rcvq_space.time = mstamp; } -static void __mptcp_update_rmem(struct sock *sk) -{ - struct mptcp_sock *msk = mptcp_sk(sk); - - if (!msk->rmem_released) - return; - - atomic_sub(msk->rmem_released, &sk->sk_rmem_alloc); - mptcp_rmem_uncharge(sk, msk->rmem_released); - WRITE_ONCE(msk->rmem_released, 0); -} - static bool __mptcp_move_skbs(struct sock *sk) { struct mptcp_sock *msk = mptcp_sk(sk); @@ -1960,7 +1886,6 @@ static bool __mptcp_move_skbs(struct sock *sk) break; slowpath = lock_sock_fast(ssk); - __mptcp_update_rmem(sk); done = __mptcp_move_skbs_from_subflow(msk, ssk, &moved); if (unlikely(ssk->sk_err)) @@ -1969,11 +1894,7 @@ static bool __mptcp_move_skbs(struct sock *sk) } while (!done); ret = moved > 0; - if (!RB_EMPTY_ROOT(&msk->out_of_order_queue) || - !skb_queue_empty(&sk->sk_receive_queue)) { - __mptcp_update_rmem(sk); - ret |= __mptcp_ofo_queue(msk); - } + ret |= __mptcp_ofo_queue(msk); if (ret) { mptcp_cleanup_rbuf(msk); mptcp_check_data_fin((struct sock *)msk); @@ -2563,8 +2484,6 @@ static int __mptcp_init_sock(struct sock *sk) INIT_WORK(&msk->work, mptcp_worker); msk->out_of_order_queue = RB_ROOT; msk->first_pending = NULL; - msk->rmem_fwd_alloc = 0; - WRITE_ONCE(msk->rmem_released, 0); msk->timer_ival = TCP_RTO_MIN; msk->first = NULL; @@ -2776,8 +2695,6 @@ static void __mptcp_destroy_sock(struct sock *sk) sk->sk_prot->destroy(sk); - WARN_ON_ONCE(msk->rmem_fwd_alloc); - WARN_ON_ONCE(msk->rmem_released); sk_stream_kill_queues(sk); xfrm_sk_free_policy(sk); @@ -3045,11 +2962,6 @@ void mptcp_destroy_common(struct mptcp_sock *msk, unsigned int flags) __skb_queue_purge(&sk->sk_receive_queue); skb_rbtree_purge(&msk->out_of_order_queue); - /* move all the rx fwd alloc into the sk_mem_reclaim_final in - * inet_sock_destruct() will dispose it - */ - sk->sk_forward_alloc += msk->rmem_fwd_alloc; - msk->rmem_fwd_alloc = 0; mptcp_token_destroy(msk); mptcp_pm_free_anno_list(msk); mptcp_free_local_addr_list(msk); @@ -3147,8 +3059,6 @@ static void mptcp_release_cb(struct sock *sk) if (__test_and_clear_bit(MPTCP_RESET_SCHEDULER, &msk->cb_flags)) msk->last_snd = NULL; } - - __mptcp_update_rmem(sk); } /* MP_JOIN client subflow must wait for 4th ack before sending any data: @@ -3329,11 +3239,6 @@ static void mptcp_shutdown(struct sock *sk, int how) __mptcp_wr_shutdown(sk); } -static int mptcp_forward_alloc_get(const struct sock *sk) -{ - return sk->sk_forward_alloc + mptcp_sk(sk)->rmem_fwd_alloc; -} - static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) { const struct sock *sk = (void *)msk; @@ -3414,7 +3319,6 @@ static struct proto mptcp_prot = { .hash = mptcp_hash, .unhash = mptcp_unhash, .get_port = mptcp_get_port, - .forward_alloc_get = mptcp_forward_alloc_get, .sockets_allocated = &mptcp_sockets_allocated, .memory_allocated = &tcp_memory_allocated, diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 99c710e1ff5c..9ddee7eac00d 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -258,7 +258,6 @@ struct mptcp_sock { u64 ack_seq; atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; - int rmem_fwd_alloc; struct sock *last_snd; int snd_burst; u64 recovery_snd_nxt; /* in recovery mode accept up to this seq; @@ -269,7 +268,6 @@ struct mptcp_sock { u64 wnd_end; unsigned long timer_ival; u32 token; - int rmem_released; unsigned long flags; unsigned long cb_flags; unsigned long push_pending; @@ -332,7 +330,7 @@ static inline struct mptcp_sock *mptcp_sk(const struct sock *sk) */ static inline int __mptcp_rmem(const struct sock *sk) { - return atomic_read(&sk->sk_rmem_alloc) - READ_ONCE(mptcp_sk(sk)->rmem_released); + return atomic_read(&sk->sk_rmem_alloc); } static inline int __mptcp_receive_window(const struct mptcp_sock *msk)