Re: [PATCH net-next 4/6] net: use core MTU range checking in core net infra

[Sabrina Dubroca]

2016-10-18, 22:33:31 -0400, Jarod Wilson wrote:
> geneve:
> - Merge __geneve_change_mtu back into geneve_change_mtu, set max_mtu
> - This one isn't quite as straight-forward as others, could use some
>   closer inspection and testing
> 
> macvlan:
> - set min/max_mtu
> 
> tun:
> - set min/max_mtu, remove tun_net_change_mtu
> 
> vxlan:
> - Merge __vxlan_change_mtu back into vxlan_change_mtu, set min/max_mtu
> - This one is also not as straight-forward and could use closer inspection
>   and testing from vxlan folks
> 
> bridge:
> - set max_mtu via br_min_mtu()
> 
> openvswitch:
> - set min/max_mtu, remove internal_dev_change_mtu
> - note: max_mtu wasn't checked previously, it's been set to 65535, which
>   is the largest possible size supported
> 
> sch_teql:
> - set min/max_mtu (note: max_mtu previously unchecked, used max of 65535)

Nothing for other virtual netdevices? (dummy, veth, bond, etc) Their
MTU is limited to 1500 now.  Also missing macsec and ip_gre, probably
others that are using ether_setup.


[...]
> diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c
> index 89a687f..81fc79a 100644
> --- a/net/bridge/br_device.c
> +++ b/net/bridge/br_device.c
> @@ -184,17 +184,15 @@ static struct rtnl_link_stats64 *br_get_stats64(struct net_device *dev,
>  
>  static int br_change_mtu(struct net_device *dev, int new_mtu)
>  {
> +#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
>  	struct net_bridge *br = netdev_priv(dev);
> -	if (new_mtu < 68 || new_mtu > br_min_mtu(br))
> -		return -EINVAL;
> -
> -	dev->mtu = new_mtu;
>  
> -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
>  	/* remember the MTU in the rtable for PMTU */
>  	dst_metric_set(&br->fake_rtable.dst, RTAX_MTU, new_mtu);
>  #endif
>  
> +	dev->mtu = new_mtu;
> +
>  	return 0;
>  }
>  
> @@ -390,6 +388,7 @@ void br_dev_setup(struct net_device *dev)
>  	dev->hw_features = COMMON_FEATURES | NETIF_F_HW_VLAN_CTAG_TX |
>  			   NETIF_F_HW_VLAN_STAG_TX;
>  	dev->vlan_features = COMMON_FEATURES;
> +	dev->max_mtu = br_min_mtu(br);

br_min_mtu uses br->port_list, which is only initialized a few lines
later (right after the spin_lock_init() at the end of the context of
this diff).

Besides, I don't think this works: br_min_mtu(br) changes when you add
and remove ports, or when you change the MTU of an enslaved
device. But this makes the max MTU for the bridge fixed (to 1500).

>  
>  	br->dev = dev;
>  	spin_lock_init(&br->lock);

> diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c
> index e7da290..d5d6cae 100644
> --- a/net/openvswitch/vport-internal_dev.c
> +++ b/net/openvswitch/vport-internal_dev.c
> @@ -89,15 +89,6 @@ static const struct ethtool_ops internal_dev_ethtool_ops = {
>  	.get_link	= ethtool_op_get_link,
>  };
>  
> -static int internal_dev_change_mtu(struct net_device *netdev, int new_mtu)
> -{
> -	if (new_mtu < 68)
> -		return -EINVAL;
> -
> -	netdev->mtu = new_mtu;
> -	return 0;
> -}
> -
>  static void internal_dev_destructor(struct net_device *dev)
>  {
>  	struct vport *vport = ovs_internal_dev_get_vport(dev);
> @@ -148,7 +139,6 @@ static const struct net_device_ops internal_dev_netdev_ops = {
>  	.ndo_stop = internal_dev_stop,
>  	.ndo_start_xmit = internal_dev_xmit,
>  	.ndo_set_mac_address = eth_mac_addr,
> -	.ndo_change_mtu = internal_dev_change_mtu,
>  	.ndo_get_stats64 = internal_get_stats,
>  	.ndo_set_rx_headroom = internal_set_rx_headroom,
>  };

vport-internal uses ether_setup, so the MTU is currently limited to
1500, no?


-- 
Sabrina