From patchwork Wed Sep 27 03:35:40 2017 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Haishuang Yan X-Patchwork-Id: 818914 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Authentication-Results: ozlabs.org; spf=none (mailfrom) smtp.mailfrom=vger.kernel.org (client-ip=209.132.180.67; helo=vger.kernel.org; envelope-from=netdev-owner@vger.kernel.org; receiver=) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 3y23RC1sFkz9t4Z for ; Wed, 27 Sep 2017 13:37:11 +1000 (AEST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1031747AbdI0DgD (ORCPT ); Tue, 26 Sep 2017 23:36:03 -0400 Received: from cmccmta2.chinamobile.com ([221.176.66.80]:19310 "EHLO cmccmta2.chinamobile.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1030881AbdI0Df7 (ORCPT ); Tue, 26 Sep 2017 23:35:59 -0400 Received: from spf.mail.chinamobile.com (unknown[172.16.121.3]) by rmmx-syy-dmz-app06-12006 (RichMail) with SMTP id 2ee659cb1c9a9c3-6cf85; Wed, 27 Sep 2017 11:35:54 +0800 (CST) X-RM-TRANSID: 2ee659cb1c9a9c3-6cf85 X-RM-SPAM-FLAG: 00000000 Received: from localhost (unknown[223.105.0.240]) by rmsmtp-syy-appsvr02-12002 (RichMail) with SMTP id 2ee259cb1c99de2-f6818; Wed, 27 Sep 2017 11:35:54 +0800 (CST) X-RM-TRANSID: 2ee259cb1c99de2-f6818 From: Haishuang Yan To: "David S. Miller" , Alexey Kuznetsov , Eric Dumazet , Wei Wang , Luca BRUNO Cc: netdev@vger.kernel.org, linux-kernel@vger.kernel.org, Haishuang Yan Subject: [PATCH v5 1/4] ipv4: Namespaceify tcp_fastopen knob Date: Wed, 27 Sep 2017 11:35:40 +0800 Message-Id: <1506483343-11544-1-git-send-email-yanhaishuang@cmss.chinamobile.com> X-Mailer: git-send-email 1.8.3.1 Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org Different namespace application might require enable TCP Fast Open feature independently of the host. This patch series continues making more of the TCP Fast Open related sysctl knobs be per net-namespace. Reported-by: Luca BRUNO Signed-off-by: Haishuang Yan --- Changes since v5: * Splite patch #2 into two changes * Fix potential leak issue * Fix typo error * Split the patches to be per-sysctl * Remove unrelated change by mistake --- include/net/netns/ipv4.h | 1 + include/net/tcp.h | 1 - net/ipv4/af_inet.c | 7 ++++--- net/ipv4/sysctl_net_ipv4.c | 14 +++++++------- net/ipv4/tcp.c | 4 ++-- net/ipv4/tcp_fastopen.c | 11 +++++------ net/ipv4/tcp_ipv4.c | 2 ++ 7 files changed, 21 insertions(+), 19 deletions(-) diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 20d061c..ce6dde0 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -127,6 +127,7 @@ struct netns_ipv4 { int sysctl_tcp_timestamps; struct inet_timewait_death_row tcp_death_row; int sysctl_max_syn_backlog; + int sysctl_tcp_fastopen; #ifdef CONFIG_NET_L3_MASTER_DEV int sysctl_udp_l3mdev_accept; diff --git a/include/net/tcp.h b/include/net/tcp.h index b510f28..f628967 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -240,7 +240,6 @@ /* sysctl variables for tcp */ -extern int sysctl_tcp_fastopen; extern int sysctl_tcp_retrans_collapse; extern int sysctl_tcp_stdurg; extern int sysctl_tcp_rfc1337; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index e31108e..ddd126d 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -195,7 +195,7 @@ int inet_listen(struct socket *sock, int backlog) { struct sock *sk = sock->sk; unsigned char old_state; - int err; + int err, tcp_fastopen; lock_sock(sk); @@ -217,8 +217,9 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - if ((sysctl_tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && - (sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && + (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { fastopen_queue_tune(sk, backlog); tcp_fastopen_init_key_once(true); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0d3c038..e31e853c 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -401,13 +401,6 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl, .proc_handler = proc_dointvec }, { - .procname = "tcp_fastopen", - .data = &sysctl_tcp_fastopen, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { .procname = "tcp_fastopen_key", .mode = 0600, .maxlen = ((TCP_FASTOPEN_KEY_LENGTH * 2) + 10), @@ -1085,6 +1078,13 @@ static int proc_tcp_available_ulp(struct ctl_table *ctl, .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_fastopen", + .data = &init_net.ipv4.sysctl_tcp_fastopen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_ROUTE_MULTIPATH { .procname = "fib_multipath_use_neigh", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5091402..dac56c4 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1126,7 +1126,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -2759,7 +2759,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index e3c3322..31b08ec 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -9,8 +9,6 @@ #include #include -int sysctl_tcp_fastopen __read_mostly = TFO_CLIENT_ENABLE; - struct tcp_fastopen_context __rcu *tcp_fastopen_ctx; static DEFINE_SPINLOCK(tcp_fastopen_ctx_lock); @@ -279,21 +277,22 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc) { - struct tcp_fastopen_cookie valid_foc = { .len = -1 }; bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; + int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); - if (!((sysctl_tcp_fastopen & TFO_SERVER_ENABLE) && + if (!((tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; return NULL; } - if (syn_data && (sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) + if (syn_data && (tcp_fastopen & TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len >= 0 && /* Client presents or requests a cookie */ @@ -347,7 +346,7 @@ bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, return false; } - if (sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { + if (sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_NO_COOKIE) { cookie->len = -1; return true; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index d9416b5..88409b1 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2472,6 +2472,8 @@ static int __net_init tcp_sk_init(struct net *net) net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; + net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; + return 0; fail: tcp_sk_exit(net);