Bonding drivers generate specific events during failover that trigger
switch updates. When a veth device is attached to a bridge with a
bond interface, we want external switches to learn about the veth
devices as well.
Example:
| veth_a2 | veth_b2 | veth_c2 |
------o-----------o----------o------
\ | /
o o o
veth_a1 veth_b1 veth_c1
-------------------------
| bridge |
-------------------------
bond0
/ \
eth0 eth1
In case of failover from eth0 to eth1, the netdev_notifier needs to be
propagated, so e.g. veth_a2 can re-announce its MAC address to the
external hardware attached to eth1.
Without this patch we have seen cases where recovery after bond failover
took an unacceptable amount of time (depending on timeout settings in the
network).
Due to the symmetric nature of veth special care is required to avoid
endless notification loops. Therefore we only notify from a veth
bridgeport to a peer that is not a bridgeport.
References:
Same handling as for macvlan:
commit 4c9912556867 ("macvlan: Support bonding events")
and vlan:
commit 4aa5dee4d999 ("net: convert resend IGMP to notifier event")
Alternatives:
Propagate notifier events to all ports of a bridge. IIUC, this was
rejected in https://www.spinics.net/lists/netdev/msg717292.html
It also seems difficult to avoid re-bouncing the notifier.
Signed-off-by: Alexandra Winter <wintera@xxxxxxxxxxxxx>
---
drivers/net/veth.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 53 insertions(+)
diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index d29fb9759cc9..74b074453197 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -1579,6 +1579,57 @@ static void veth_setup(struct net_device *dev)
dev->mpls_features = NETIF_F_HW_CSUM | NETIF_F_GSO_SOFTWARE;
}
+static bool netif_is_veth(const struct net_device *dev)
+{
+ return (dev->netdev_ops == &veth_netdev_ops);
+}
+
+static void veth_notify_peer(unsigned long event, const struct net_device *dev)
+{
+ struct net_device *peer;
+ struct veth_priv *priv;
+
+ priv = netdev_priv(dev);
+ peer = rtnl_dereference(priv->peer);
+ /* avoid re-bounce between 2 bridges */
+ if (!netif_is_bridge_port(peer))
+ call_netdevice_notifiers(event, peer);
+}
+
+/* Called under rtnl_lock */
+static int veth_device_event(struct notifier_block *unused,
+ unsigned long event, void *ptr)
+{
+ struct net_device *dev, *lower;
+ struct list_head *iter;
+
+ dev = netdev_notifier_info_to_dev(ptr);
+
+ switch (event) {
+ case NETDEV_NOTIFY_PEERS:
+ case NETDEV_BONDING_FAILOVER:
+ case NETDEV_RESEND_IGMP:
+ /* propagate to peer of a bridge attached veth */
+ if (netif_is_bridge_master(dev)) {
+ iter = &dev->adj_list.lower;
+ lower = netdev_next_lower_dev_rcu(dev, &iter);
+ while (lower) {
+ if (netif_is_veth(lower))
+ veth_notify_peer(event, lower);
+ lower = netdev_next_lower_dev_rcu(dev, &iter);
+ }
+ }
+ break;
+ default:
+ break;
+ }
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block veth_notifier_block __read_mostly = {
+ .notifier_call = veth_device_event,
+};
+
/*
* netlink interface
*/
@@ -1824,12 +1875,14 @@ static struct rtnl_link_ops veth_link_ops = {
static __init int veth_init(void)
{
+ register_netdevice_notifier(&veth_notifier_block);
return rtnl_link_register(&veth_link_ops);
}
static __exit void veth_exit(void)
{
rtnl_link_unregister(&veth_link_ops);
+ unregister_netdevice_notifier(&veth_notifier_block);
}
module_init(veth_init);
--
2.32.0
