vxlan, gre, geneve: Set a large MTU on ovs-created tunnel devices

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>

3 files changed, 27 insertions, 3 deletions

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7c51c4e1661f..56fdf4e0dce4 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1240,6 +1240,14 @@ 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 c7bd72e9b544..89e8861e05fc 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -943,17 +943,31 @@ 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 1605691d9414..de9cb19efb6a 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,
+                /* Don't restrict the packets that can be sent by MTU */
+                .mtu = IP_MAX_MTU,
         };
 
         if (!options) {