From ee60ad219f5c7c4fb2f047f88037770063ef785f Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 8 Mar 2019 14:50:54 +0800 Subject: route: set the deleted fnhe fnhe_daddr to 0 in ip_del_fnhe to fix a race The race occurs in __mkroute_output() when 2 threads lookup a dst: CPU A CPU B find_exception() find_exception() [fnhe expires] ip_del_fnhe() [fnhe is deleted] rt_bind_exception() In rt_bind_exception() it will bind a deleted fnhe with the new dst, and this dst will get no chance to be freed. It causes a dev defcnt leak and consecutive dmesg warnings: unregister_netdevice: waiting for ethX to become free. Usage count = 1 Especially thanks Jon to identify the issue. This patch fixes it by setting fnhe_daddr to 0 in ip_del_fnhe() to stop binding the deleted fnhe with a new dst when checking fnhe's fnhe_daddr and daddr in rt_bind_exception(). It works as both ip_del_fnhe() and rt_bind_exception() are protected by fnhe_lock and the fhne is freed by kfree_rcu(). Fixes: deed49df7390 ("route: check and remove route cache when we get route") Signed-off-by: Jon Maxwell Signed-off-by: Xin Long Reviewed-by: David Ahern Signed-off-by: David S. Miller --- net/ipv4/route.c | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'net') diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 8ca3642f0d9b..a5da63e5faa2 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1303,6 +1303,10 @@ static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + /* set fnhe_daddr to 0 to ensure it won't bind with + * new dsts in rt_bind_exception(). + */ + fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; -- cgit v1.2.3-59-g8ed1b