From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752749AbcFVXTl (ORCPT ); Wed, 22 Jun 2016 19:19:41 -0400 Received: from mail.linuxfoundation.org ([140.211.169.12]:46254 "EHLO mail.linuxfoundation.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752271AbcFVWlt (ORCPT ); Wed, 22 Jun 2016 18:41:49 -0400 From: Greg Kroah-Hartman To: linux-kernel@vger.kernel.org Cc: Greg Kroah-Hartman , stable@vger.kernel.org, David Wragg , "David S. Miller" Subject: [PATCH 4.4 21/75] vxlan, gre, geneve: Set a large MTU on ovs-created tunnel devices Date: Wed, 22 Jun 2016 15:40:43 -0700 Message-Id: <20160622223501.115189345@linuxfoundation.org> X-Mailer: git-send-email 2.9.0 In-Reply-To: <20160622223500.055133765@linuxfoundation.org> References: <20160622223500.055133765@linuxfoundation.org> User-Agent: quilt/0.64 MIME-Version: 1.0 Content-Type: text/plain; charset=ISO-8859-15 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 4.4-stable review patch. If anyone has any objections, please let me know. ------------------ From: David Wragg [ Upstream commit 7e059158d57b79159eaf1f504825d19866ef2c42 ] Prior to 4.3, openvswitch tunnel vports (vxlan, gre and geneve) could transmit vxlan packets of any size, constrained only by the ability to send out the resulting packets. 4.3 introduced netdevs corresponding to tunnel vports. These netdevs have an MTU, which limits the size of a packet that can be successfully encapsulated. The default MTU values are low (1500 or less), which is awkwardly small in the context of physical networks supporting jumbo frames, and leads to a conspicuous change in behaviour for userspace. Instead, set the MTU on openvswitch-created netdevs to be the relevant maximum (i.e. the maximum IP packet size minus any relevant overhead), effectively restoring the behaviour prior to 4.3. Signed-off-by: David Wragg Signed-off-by: David S. Miller Signed-off-by: Greg Kroah-Hartman --- drivers/net/geneve.c | 18 ++++++++++++++---- drivers/net/vxlan.c | 11 ++++++++--- include/net/ip_tunnels.h | 1 + net/ipv4/ip_gre.c | 8 ++++++++ net/ipv4/ip_tunnel.c | 20 +++++++++++++++++--- net/openvswitch/vport-vxlan.c | 2 ++ 6 files changed, 50 insertions(+), 10 deletions(-) --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -1356,11 +1356,21 @@ struct net_device *geneve_dev_create_fb( err = geneve_configure(net, dev, &geneve_remote_unspec, 0, 0, 0, htons(dst_port), true); - if (err) { - free_netdev(dev); - return ERR_PTR(err); - } + if (err) + goto err; + + /* openvswitch users expect packet sizes to be unrestricted, + * so set the largest MTU we can. + */ + err = geneve_change_mtu(dev, IP_MAX_MTU); + if (err) + goto err; + return dev; + + err: + free_netdev(dev); + return ERR_PTR(err); } EXPORT_SYMBOL_GPL(geneve_dev_create_fb); --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2776,6 +2776,7 @@ static int vxlan_dev_configure(struct ne int err; bool use_ipv6 = false; __be16 default_port = vxlan->cfg.dst_port; + struct net_device *lowerdev = NULL; vxlan->net = src_net; @@ -2796,9 +2797,7 @@ static int vxlan_dev_configure(struct ne } if (conf->remote_ifindex) { - struct net_device *lowerdev - = __dev_get_by_index(src_net, conf->remote_ifindex); - + lowerdev = __dev_get_by_index(src_net, conf->remote_ifindex); dst->remote_ifindex = conf->remote_ifindex; if (!lowerdev) { @@ -2822,6 +2821,12 @@ static int vxlan_dev_configure(struct ne needed_headroom = lowerdev->hard_header_len; } + if (conf->mtu) { + err = __vxlan_change_mtu(dev, lowerdev, dst, conf->mtu, false); + if (err) + return err; + } + if (use_ipv6 || conf->flags & VXLAN_F_COLLECT_METADATA) needed_headroom += VXLAN6_HEADROOM; else --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -230,6 +230,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, int ip_tunnel_ioctl(struct net_device *dev, struct ip_tunnel_parm *p, int cmd); int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t, u8 *protocol, struct flowi4 *fl4); +int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict); int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu); struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1247,6 +1247,14 @@ struct net_device *gretap_fb_dev_create( err = ipgre_newlink(net, dev, tb, NULL); if (err < 0) goto out; + + /* openvswitch users expect packet sizes to be unrestricted, + * so set the largest MTU we can. + */ + err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); + if (err) + goto out; + return dev; out: free_netdev(dev); --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -948,17 +948,31 @@ done: } EXPORT_SYMBOL_GPL(ip_tunnel_ioctl); -int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict) { struct ip_tunnel *tunnel = netdev_priv(dev); int t_hlen = tunnel->hlen + sizeof(struct iphdr); + int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen; - if (new_mtu < 68 || - new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen) + if (new_mtu < 68) return -EINVAL; + + if (new_mtu > max_mtu) { + if (strict) + return -EINVAL; + + new_mtu = max_mtu; + } + dev->mtu = new_mtu; return 0; } +EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu); + +int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu) +{ + return __ip_tunnel_change_mtu(dev, new_mtu, true); +} EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu); static void ip_tunnel_dev_free(struct net_device *dev) --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -91,6 +91,8 @@ static struct vport *vxlan_tnl_create(co struct vxlan_config conf = { .no_share = true, .flags = VXLAN_F_COLLECT_METADATA | VXLAN_F_UDP_ZERO_CSUM6_RX, + /* Don't restrict the packets that can be sent by MTU */ + .mtu = IP_MAX_MTU, }; if (!options) {