ipvs: do not keep dest_dst after dest is removed

Before now dest->dest_dst is not released when server is moved into
dest_trash list after removal. As result, we can keep dst/dev
references for long time without actively using them.

It is better to avoid walking the dest_trash list when
ip_vs_dst_event() receives dev events. So, make sure we do not
hold dev references in dest_trash list. As packets can be flying
while server is being removed, check the IP_VS_DEST_F_AVAILABLE
flag in slow path to ensure we do not save new dev references to
removed servers.

Signed-off-by: Julian Anastasov <ja@ssi.bg>
Signed-off-by: Florian Westphal <fw@strlen.de>
Link: https://patch.msgid.link/20260224205048.4718-5-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

2 files changed, 16 insertions, 16 deletions

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index 2ef1f99dada6..7c0e2d9b5b98 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -809,7 +809,6 @@ static void ip_vs_dest_free(struct ip_vs_dest *dest)
 {
 	struct ip_vs_service *svc = rcu_dereference_protected(dest->svc, 1);
 
-	__ip_vs_dst_cache_reset(dest);
 	__ip_vs_svc_put(svc);
 	call_rcu(&dest->rcu_head, ip_vs_dest_rcu_free);
 }
@@ -1012,10 +1011,6 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 
 	dest->af = udest->af;
 
-	spin_lock_bh(&dest->dst_lock);
-	__ip_vs_dst_cache_reset(dest);
-	spin_unlock_bh(&dest->dst_lock);
-
 	if (add) {
 		list_add_rcu(&dest->n_list, &svc->destinations);
 		svc->num_dests++;
@@ -1023,6 +1018,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest,
 		if (sched && sched->add_dest)
 			sched->add_dest(svc, dest);
 	} else {
+		spin_lock_bh(&dest->dst_lock);
+		__ip_vs_dst_cache_reset(dest);
+		spin_unlock_bh(&dest->dst_lock);
+
 		sched = rcu_dereference_protected(svc->scheduler, 1);
 		if (sched && sched->upd_dest)
 			sched->upd_dest(svc, dest);
@@ -1257,6 +1256,10 @@ static void __ip_vs_unlink_dest(struct ip_vs_service *svc,
 {
 	dest->flags &= ~IP_VS_DEST_F_AVAILABLE;
 
+	spin_lock_bh(&dest->dst_lock);
+	__ip_vs_dst_cache_reset(dest);
+	spin_unlock_bh(&dest->dst_lock);
+
 	/*
 	 *  Remove it from the d-linked destination list.
 	 */
@@ -1747,13 +1750,6 @@ static int ip_vs_dst_event(struct notifier_block *this, unsigned long event,
 	}
 	rcu_read_unlock();
 
-	mutex_lock(&ipvs->service_mutex);
-	spin_lock_bh(&ipvs->dest_trash_lock);
-	list_for_each_entry(dest, &ipvs->dest_trash, t_list) {
-		ip_vs_forget_dev(dest, dev);
-	}
-	spin_unlock_bh(&ipvs->dest_trash_lock);
-	mutex_unlock(&ipvs->service_mutex);
 	return NOTIFY_DONE;
 }
 
diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c
index 4389bfe3050d..394b5b5f2ccd 100644
--- a/net/netfilter/ipvs/ip_vs_xmit.c
+++ b/net/netfilter/ipvs/ip_vs_xmit.c
@@ -336,9 +336,11 @@ __ip_vs_get_out_rt(struct netns_ipvs *ipvs, int skb_af, struct sk_buff *skb,
 				goto err_unreach;
 			}
 			/* It is forbidden to attach dest->dest_dst if
-			 * device is going down.
+			 * device is going down or if server is removed and
+			 * stored in dest_trash.
 			 */
-			if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)))
+			if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) &&
+			    dest->flags & IP_VS_DEST_F_AVAILABLE)
 				__ip_vs_dst_set(dest, dest_dst, &rt->dst, 0);
 			else
 				noref = 0;
@@ -513,9 +515,11 @@ __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);
 			/* It is forbidden to attach dest->dest_dst if
-			 * device is going down.
+			 * device is going down or if server is removed and
+			 * stored in dest_trash.
 			 */
-			if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)))
+			if (!rt_dev_is_down(dst_dev_rcu(&rt->dst)) &&
+			    dest->flags & IP_VS_DEST_F_AVAILABLE)
 				__ip_vs_dst_set(dest, dest_dst, &rt->dst, cookie);
 			else
 				noref = 0;