ipvs: do not keep dest_dst if dev is going down

There is race between the netdev notifier ip_vs_dst_event()
and the code that caches dst with dev that is going down.
As the FIB can be notified for the closed device after our
handler finishes, it is possible valid route to be returned
and cached resuling in a leaked dev reference until the dest
is not removed.

To prevent new dest_dst to be attached to dest just after the
handler dropped the old one, add a netif_running() check
to make sure the notifier handler is not currently running
for device that is closing.

Fixes: 7a4f076 ("IPVS: init and cleanup restructuring")
Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Florian Westphal <fw@strlen.de>

Author: Julian Anastasov

net/netfilter/ipvs/ip_vs_xmit.c

@@ -294,6 +294,12 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs,
 	return true;
 }
 
+/* rt has device that is down */
+static bool rt_dev_is_down(const struct net_device *dev)
+{
+	return dev && !netif_running(dev);
+}
+
 /* Get route to destination or remote server */
 static int
 __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
@@ -309,9 +315,11 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 
 	if (dest) {
 		dest_dst = __ip_vs_dst_check(dest);
-		if (likely(dest_dst))
+		if (likely(dest_dst)) {
 			rt = dst_rtable(dest_dst->dst_cache);
-		else {
+			if (ret_saddr)
+				*ret_saddr = dest_dst->dst_saddr.ip;
+		} else {
 			dest_dst = ip_vs_dest_dst_alloc();
 			spin_lock_bh(&dest->dst_lock);
 			if (!dest_dst) {
@@ -327,14 +335,22 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 				ip_vs_dest_dst_free(dest_dst);
 				goto err_unreach;
 			}
-			__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
+			/* It is forbidden to attach dest->dest_dst if
+			 * device is going down.
+			 */
+			if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)))
+				__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
+			else
+				noref = 0;
 			spin_unlock_bh(&dest->dst_lock);
 			IP_VS_DBG(10, "new dst %pI4, src %pI4, refcnt=%d\n",
 				  &dest->addr.ip, &dest_dst->dst_saddr.ip,
 				  rcuref_read(&rt->dst.__rcuref));
+			if (ret_saddr)
+				*ret_saddr = dest_dst->dst_saddr.ip;
+			if (!noref)
+				ip_vs_dest_dst_free(dest_dst);
 		}
-		if (ret_saddr)
-			*ret_saddr = dest_dst->dst_saddr.ip;
 	} else {
 		noref = 0;
 
@@ -471,9 +487,11 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 
 	if (dest) {
 		dest_dst = __ip_vs_dst_check(dest);
-		if (likely(dest_dst))
+		if (likely(dest_dst)) {
 			rt = dst_rt6_info(dest_dst->dst_cache);
-		else {
+			if (ret_saddr)
+				*ret_saddr = dest_dst->dst_saddr.in6;
+		} else {
 			u32 cookie;
 
 			dest_dst = ip_vs_dest_dst_alloc();
@@ -494,14 +512,22 @@ __ip_vs_get_out_rt_v6(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 			}
 			rt = dst_rt6_info(dst);
 			cookie = rt6_get_cookie(rt);
-			__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
+			/* It is forbidden to attach dest->dest_dst if
+			 * device is going down.
+			 */
+			if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)))
+				__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
+			else
+				noref = 0;
 			spin_unlock_bh(&dest->dst_lock);
 			IP_VS_DBG(10, "new dst %pI6, src %pI6, refcnt=%d\n",
 				  &dest->addr.in6, &dest_dst->dst_saddr.in6,
 				  rcuref_read(&rt->dst.__rcuref));
+			if (ret_saddr)
+				*ret_saddr = dest_dst->dst_saddr.in6;
+			if (!noref)
+				ip_vs_dest_dst_free(dest_dst);
 		}
-		if (ret_saddr)
-			*ret_saddr = dest_dst->dst_saddr.in6;
 	} else {
 		noref = 0;
 		dst = __ip_vs_route_output_v6(net, daddr, ret_saddr, do_xfrm,