diff options
| author | David Wragg <david@weave.works> | 2016-06-03 18:58:15 -0400 |
|---|---|---|
| committer | Greg Kroah-Hartman <gregkh@linuxfoundation.org> | 2016-06-24 10:18:18 -0700 |
| commit | ce9c0dba5bf3ad4a25a9dc202e36e74d904df61d (patch) | |
| tree | 14ca25b6aa9083e1a5f8c0477c9679940e00f6bc /net | |
| parent | 51d7c394605bd5d72e76745def0002dd938ec48b (diff) | |
vxlan, gre, geneve: Set a large MTU on ovs-created tunnel devices
[ 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 <david@weave.works>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Diffstat (limited to 'net')
| -rw-r--r-- | net/ipv4/ip_gre.c | 8 | ||||
| -rw-r--r-- | net/ipv4/ip_tunnel.c | 20 | ||||
| -rw-r--r-- | net/openvswitch/vport-vxlan.c | 2 |
3 files changed, 27 insertions, 3 deletions
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 7dc962b89fa1..3e4184088082 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -1247,6 +1247,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name, 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); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index ce30c8b72457..3310ac75e3f3 100644 --- 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) diff --git a/net/openvswitch/vport-vxlan.c b/net/openvswitch/vport-vxlan.c index d933cb89efac..5eb7694348b5 100644 --- a/net/openvswitch/vport-vxlan.c +++ b/net/openvswitch/vport-vxlan.c @@ -91,6 +91,8 @@ static struct vport *vxlan_tnl_create(const struct vport_parms *parms) 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) { |