ipvlan: call dev_change_flags when ipvlan mode is reset

After we change the ipvlan mode from l3 to l2, or vice versa, we only
reset IFF_NOARP flag, but don't flush the ARP table cache, which will
cause eth->h_dest to be equal to eth->h_source in ipvlan_xmit_mode_l2().
Then the message will not come out of host.

Here is the reproducer on local host:

ip link set eth1 up
ip addr add 192.168.1.1/24 dev eth1
ip link add link eth1 ipvlan1 type ipvlan mode l3

ip netns add net1
ip link set ipvlan1 netns net1
ip netns exec net1 ip link set ipvlan1 up
ip netns exec net1 ip addr add 192.168.2.1/24 dev ipvlan1

ip route add 192.168.2.0/24 via 192.168.1.2
ping 192.168.2.2 -c 2

ip netns exec net1 ip link set ipvlan1 type ipvlan mode l2
ping 192.168.2.2 -c 2

Add the same configuration on remote host. After we set the mode to l2,
we could find that the src/dst MAC addresses are the same on eth1:

21:26:06.648565 00:b7:13:ad:d3:05 > 00:b7:13:ad:d3:05, ethertype IPv4 (0x0800), length 98: (tos 0x0, ttl 64, id 58356, offset 0, flags [DF], proto ICMP (1), length 84)
    192.168.2.1 > 192.168.2.2: ICMP echo request, id 22686, seq 1, length 64

Fix this by calling dev_change_flags(), which will call netdevice notifier
with flag change info.

v2:
a) As pointed out by Wang Cong, check return value for dev_change_flags() when
change dev flags.
b) As suggested by Stefano and Sabrina, move flags setting before l3mdev_ops.
So we don't need to redo ipvlan_{, un}register_nf_hook() again in err path.

Reported-by: Jianlin Shi <[email protected]>
Reviewed-by: Stefano Brivio <[email protected]>
Reviewed-by: Sabrina Dubroca <[email protected]>
Fixes: 2ad7bf3 ("ipvlan: Initial check-in of the IPVLAN driver.")
Signed-off-by: Hangbin Liu <[email protected]>
Signed-off-by: David S. Miller <[email protected]>

Author: liuhangbin

drivers/net/ipvlan/ipvlan_main.c

@@ -75,32 +75,52 @@ static int ipvlan_set_port_mode(struct ipvl_port *port, u16 nval)
 {
 	struct ipvl_dev *ipvlan;
 	struct net_device *mdev = port->dev;
-	int err = 0;
+	unsigned int flags;
+	int err;
 
 	ASSERT_RTNL();
 	if (port->mode != nval) {
+		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
+			flags = ipvlan->dev->flags;
+			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S) {
+				err = dev_change_flags(ipvlan->dev,
+						       flags | IFF_NOARP);
+			} else {
+				err = dev_change_flags(ipvlan->dev,
+						       flags & ~IFF_NOARP);
+			}
+			if (unlikely(err))
+				goto fail;
+		}
 		if (nval == IPVLAN_MODE_L3S) {
 			/* New mode is L3S */
 			err = ipvlan_register_nf_hook(read_pnet(&port->pnet));
 			if (!err) {
 				mdev->l3mdev_ops = &ipvl_l3mdev_ops;
 				mdev->priv_flags |= IFF_L3MDEV_MASTER;
 			} else
-				return err;
+				goto fail;
 		} else if (port->mode == IPVLAN_MODE_L3S) {
 			/* Old mode was L3S */
 			mdev->priv_flags &= ~IFF_L3MDEV_MASTER;
 			ipvlan_unregister_nf_hook(read_pnet(&port->pnet));
 			mdev->l3mdev_ops = NULL;
 		}
-		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			if (nval == IPVLAN_MODE_L3 || nval == IPVLAN_MODE_L3S)
-				ipvlan->dev->flags |= IFF_NOARP;
-			else
-				ipvlan->dev->flags &= ~IFF_NOARP;
-		}
 		port->mode = nval;
 	}
+	return 0;
+
+fail:
+	/* Undo the flags changes that have been done so far. */
+	list_for_each_entry_continue_reverse(ipvlan, &port->ipvlans, pnode) {
+		flags = ipvlan->dev->flags;
+		if (port->mode == IPVLAN_MODE_L3 ||
+		    port->mode == IPVLAN_MODE_L3S)
+			dev_change_flags(ipvlan->dev, flags | IFF_NOARP);
+		else
+			dev_change_flags(ipvlan->dev, flags & ~IFF_NOARP);
+	}
+
 	return err;
 }