ip_tunnel: restore binding to ifaces with a large mtu

After commit 76eb8788c753, the following conf is broken (note that the
default loopback mtu is 65536, ie IP_MAX_MTU + 1):

$ ip tunnel add gre1 mode gre local 10.125.0.1 remote 10.125.0.2 dev lo
add tunnel "gre0" failed: Invalid argument
$ ip l a type dummy
$ ip l s dummy1 up
$ ip l s dummy1 mtu 65535
$ ip tunnel add gre1 mode gre local 10.125.0.1 remote 10.125.0.2 dev dummy1
add tunnel "gre0" failed: Invalid argument

dev_set_mtu() doesn't allow to set a mtu which is too large.
First, let's cap the mtu returned by ip_tunnel_bind_dev(). Second, remove
the magic value 0xFFF8 and use IP_MAX_MTU instead.
0xFFF8 seems to be there for ages, I don't know why this value was used.

With a recent kernel, it's also possible to set a mtu > IP_MAX_MTU:
$ ip l s dummy1 mtu 66000
After that patch, it's also possible to bind an ip tunnel on that kind of
interface.

CC: Petr Machata <petrm@mellanox.com>
CC: Ido Schimmel <idosch@mellanox.com>
Link: https://git.kernel.org/pub/scm/linux/kernel/git/davem/netdev-vger-cvs.git/commit/?id=e5afd356a411a
Fixes: 76eb8788c753 ("ip_tunnel: Emit events for post-register MTU changes")
Signed-off-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Reviewed-by: Ido Schimmel <idosch@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 6b0e362cc99b5d3510ea7aa8db68dcb5c8eb675c..38d906baf1df837c5009b7487fb14f6a1c11acaa 100644 (file)
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -328,7 +328,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
 
        if (tdev) {
                hlen = tdev->hard_header_len + tdev->needed_headroom;
-               mtu = tdev->mtu;
+               mtu = min(tdev->mtu, IP_MAX_MTU);
        }
 
        dev->needed_headroom = t_hlen + hlen;
@@ -362,7 +362,7 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net,
        nt = netdev_priv(dev);
        t_hlen = nt->hlen + sizeof(struct iphdr);
        dev->min_mtu = ETH_MIN_MTU;
-       dev->max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
+       dev->max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
        ip_tunnel_add(itn, nt);
        return nt;
 
@@ -930,7 +930,7 @@ 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;
+       int max_mtu = IP_MAX_MTU - dev->hard_header_len - t_hlen;
 
        if (new_mtu < ETH_MIN_MTU)
                return -EINVAL;
@@ -1107,7 +1107,7 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[],
 
        mtu = ip_tunnel_bind_dev(dev);
        if (tb[IFLA_MTU]) {
-               unsigned int max = 0xfff8 - dev->hard_header_len - nt->hlen;
+               unsigned int max = IP_MAX_MTU - dev->hard_header_len - nt->hlen;
 
                mtu = clamp(dev->mtu, (unsigned int)ETH_MIN_MTU,
                            (unsigned int)(max - sizeof(struct iphdr)));