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>

diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c
index d2031ce8baea3772f43578d7ab8d58e9c57c01aa..028e3873c3107960c55f0bcff71d860fac0cad6e 100644 (file)
--- a/drivers/net/geneve.c
+++ b/drivers/net/geneve.c
@@ -1453,11 +1453,21 @@ struct net_device *geneve_dev_create_fb(struct net *net, const char *name,
 
        err = geneve_configure(net, dev, &geneve_remote_unspec,
                               0, 0, 0, htons(dst_port), true, 0);
-       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);
 

diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c
index e992c6a05f86614386b260b1ce82c5bfdff1867a..a31cd954b308fcf9792df88ec4d1d06842a3b1a1 100644 (file)
--- a/drivers/net/vxlan.c
+++ b/drivers/net/vxlan.c
@@ -2779,6 +2779,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
        int err;
        bool use_ipv6 = false;
        __be16 default_port = vxlan->cfg.dst_port;
+       struct net_device *lowerdev = NULL;
 
        vxlan->net = src_net;
 
@@ -2799,9 +2800,7 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
        }
 
        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) {
@@ -2825,6 +2824,12 @@ static int vxlan_dev_configure(struct net *src_net, struct net_device *dev,
                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

diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h
index 6db96ea0144f0445c4e52c51cddcc3d25d60ccdd..dda9abf6b89c14afddf71562c763bdd6bb7d85c3 100644 (file)
--- a/include/net/ip_tunnels.h
+++ b/include/net/ip_tunnels.h
@@ -230,6 +230,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
 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,

diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7c51c4e1661f9aafc63829cf58b3b5ec28ed859e..56fdf4e0dce4ef4cb88e34096b4d06cae7de41c5 100644 (file)
--- 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 c7bd72e9b544848d10a490b010e0a30c4d5e4c21..89e8861e05fcb1d371c371c1784b89499b69d9df 100644 (file)
--- 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 1605691d94144aee0fc50ffb17be05eca2b59675..de9cb19efb6a3e2774624c29b2fe5c977ef92fe4 100644 (file)
--- 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) {