4.4-stable review patch. If anyone has any objections, please let me know.
------------------
From: Hangbin Liu liuhangbin@gmail.com
[ Upstream commit e8238fc2bd7b4c3c7554fa2df067e796610212fc ]
When we set a bond slave's master to bridge via ioctl, we only check the IFF_BRIDGE_PORT flag. Although we will find the slave's real master at netdev_master_upper_dev_link() later, it already does some settings and allocates some resources. It would be better to return as early as possible.
v1 -> v2: use netdev_master_upper_dev_get() instead of netdev_has_any_upper_dev() to check if we have a master, because not all upper devs are masters, e.g. vlan device.
Reported-by: syzbot+de73361ee4971b6e6f75@syzkaller.appspotmail.com Signed-off-by: Hangbin Liu liuhangbin@gmail.com Acked-by: Nikolay Aleksandrov nikolay@cumulusnetworks.com Signed-off-by: David S. Miller davem@davemloft.net Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org --- net/bridge/br_if.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)
--- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -456,8 +456,8 @@ int br_add_if(struct net_bridge *br, str if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) return -ELOOP;
- /* Device is already being bridged */ - if (br_port_exists(dev)) + /* Device has master upper dev */ + if (netdev_master_upper_dev_get(dev)) return -EBUSY;
/* No bridging devices that dislike that (e.g. wireless) */