From patchwork Sun Jan 30 18:02:55 2022 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Tony Lu X-Patchwork-Id: 12729937 X-Patchwork-Delegate: kuba@kernel.org Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id AF4A3C433EF for ; Sun, 30 Jan 2022 18:03:12 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1355774AbiA3SDJ (ORCPT ); Sun, 30 Jan 2022 13:03:09 -0500 Received: from out30-57.freemail.mail.aliyun.com ([115.124.30.57]:57639 "EHLO out30-57.freemail.mail.aliyun.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1354844AbiA3SDI (ORCPT ); Sun, 30 Jan 2022 13:03:08 -0500 X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R731e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=e01e04394;MF=tonylu@linux.alibaba.com;NM=1;PH=DS;RN=5;SR=0;TI=SMTPD_---0V3BCr70_1643565784; Received: from localhost(mailfrom:tonylu@linux.alibaba.com fp:SMTPD_---0V3BCr70_1643565784) by smtp.aliyun-inc.com(127.0.0.1); Mon, 31 Jan 2022 02:03:05 +0800 From: Tony Lu To: kgraul@linux.ibm.com, kuba@kernel.org, davem@davemloft.net Cc: netdev@vger.kernel.org, linux-s390@vger.kernel.org Subject: [PATCH net-next 1/3] net/smc: Send directly when TCP_CORK is cleared Date: Mon, 31 Jan 2022 02:02:55 +0800 Message-Id: <20220130180256.28303-2-tonylu@linux.alibaba.com> X-Mailer: git-send-email 2.35.0 In-Reply-To: <20220130180256.28303-1-tonylu@linux.alibaba.com> References: <20220130180256.28303-1-tonylu@linux.alibaba.com> MIME-Version: 1.0 Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org X-Patchwork-Delegate: kuba@kernel.org According to the man page of TCP_CORK [1], if set, don't send out partial frames. All queued partial frames are sent when option is cleared again. When applications call setsockopt to disable TCP_CORK, this call is protected by lock_sock(), and tries to mod_delayed_work() to 0, in order to send pending data right now. However, the delayed work smc_tx_work is also protected by lock_sock(). There introduces lock contention for sending data. To fix it, send pending data directly which acts like TCP, without lock_sock() protected in the context of setsockopt (already lock_sock()ed), and cancel unnecessary dealyed work, which is protected by lock. [1] https://linux.die.net/man/7/tcp Signed-off-by: Tony Lu --- net/smc/af_smc.c | 4 ++-- net/smc/smc_tx.c | 25 +++++++++++++++---------- net/smc/smc_tx.h | 1 + 3 files changed, 18 insertions(+), 12 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index ffab9cee747d..ef021ec6b361 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -2600,8 +2600,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_state != SMC_CLOSED) { if (!val) { SMC_STAT_INC(smc, cork_cnt); - mod_delayed_work(smc->conn.lgr->tx_wq, - &smc->conn.tx_work, 0); + smc_tx_pending(&smc->conn); + cancel_delayed_work(&smc->conn.tx_work); } } break; diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index be241d53020f..7b0b6e24582f 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -597,27 +597,32 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) return rc; } -/* Wakeup sndbuf consumers from process context - * since there is more data to transmit - */ -void smc_tx_work(struct work_struct *work) +void smc_tx_pending(struct smc_connection *conn) { - struct smc_connection *conn = container_of(to_delayed_work(work), - struct smc_connection, - tx_work); struct smc_sock *smc = container_of(conn, struct smc_sock, conn); int rc; - lock_sock(&smc->sk); if (smc->sk.sk_err) - goto out; + return; rc = smc_tx_sndbuf_nonempty(conn); if (!rc && conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) conn->local_rx_ctrl.prod_flags.write_blocked = 0; +} + +/* Wakeup sndbuf consumers from process context + * since there is more data to transmit + */ +void smc_tx_work(struct work_struct *work) +{ + struct smc_connection *conn = container_of(to_delayed_work(work), + struct smc_connection, + tx_work); + struct smc_sock *smc = container_of(conn, struct smc_sock, conn); -out: + lock_sock(&smc->sk); + smc_tx_pending(conn); release_sock(&smc->sk); } diff --git a/net/smc/smc_tx.h b/net/smc/smc_tx.h index 07e6ad76224a..a59f370b8b43 100644 --- a/net/smc/smc_tx.h +++ b/net/smc/smc_tx.h @@ -27,6 +27,7 @@ static inline int smc_tx_prepared_sends(struct smc_connection *conn) return smc_curs_diff(conn->sndbuf_desc->len, &sent, &prep); } +void smc_tx_pending(struct smc_connection *conn); void smc_tx_work(struct work_struct *work); void smc_tx_init(struct smc_sock *smc); int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len);