netfilter: ipset: fix performance regression in swap operation

The patch "netfilter: ipset: fix race condition between swap/destroy
and kernel side add/del/test", commit 28628fa9 fixes a race condition.
But the synchronize_rcu() added to the swap function unnecessarily slows
it down: it can safely be moved to destroy and use call_rcu() instead.

Eric Dumazet pointed out that simply calling the destroy functions as
rcu callback does not work: sets with timeout use garbage collectors
which need cancelling at destroy which can wait. Therefore the destroy
functions are split into two: cancelling garbage collectors safely at
executing the command received by netlink and moving the remaining
part only into the rcu callback.

Link: https://lore.kernel.org/lkml/C0829B10-EAA6-4809-874E-E1E9C05A8D84@automattic.com/
Fixes: 28628fa952fe ("netfilter: ipset: fix race condition between swap/destroy and kernel side add/del/test")
Reported-by: Ale Crismani <ale.crismani@automattic.com>
Reported-by: David Wang <00107082@163.com>
Tested-by: David Wang <00107082@163.com>
Signed-off-by: Jozsef Kadlecsik <kadlec@netfilter.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

1 files changed, 28 insertions, 9 deletions

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 4c133e06be1d..bcaad9c009fe 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -1182,6 +1182,14 @@ ip_set_destroy_set(struct ip_set *set)
 	kfree(set);
 }
 
+static void
+ip_set_destroy_set_rcu(struct rcu_head *head)
+{
+	struct ip_set *set = container_of(head, struct ip_set, rcu);
+
+	ip_set_destroy_set(set);
+}
+
 static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			  const struct nlattr * const attr[])
 {
@@ -1193,8 +1201,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
-	/* Must wait for flush to be really finished in list:set */
-	rcu_barrier();
 
 	/* Commands are serialized and references are
 	 * protected by the ip_set_ref_lock.
@@ -1206,8 +1212,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	 * counter, so if it's already zero, we can proceed
 	 * without holding the lock.
 	 */
-	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
+		/* Must wait for flush to be really finished in list:set */
+		rcu_barrier();
+		read_lock_bh(&ip_set_ref_lock);
 		for (i = 0; i < inst->ip_set_max; i++) {
 			s = ip_set(inst, i);
 			if (s && (s->ref || s->ref_netlink)) {
@@ -1221,6 +1229,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			s = ip_set(inst, i);
 			if (s) {
 				ip_set(inst, i) = NULL;
+				/* Must cancel garbage collectors */
+				s->variant->cancel_gc(s);
 				ip_set_destroy_set(s);
 			}
 		}
@@ -1228,6 +1238,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 		inst->is_destroyed = false;
 	} else {
 		u32 flags = flag_exist(info->nlh);
+		u16 features = 0;
+
+		read_lock_bh(&ip_set_ref_lock);
 		s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
 				    &i);
 		if (!s) {
@@ -1238,10 +1251,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			ret = -IPSET_ERR_BUSY;
 			goto out;
 		}
+		features = s->type->features;
 		ip_set(inst, i) = NULL;
 		read_unlock_bh(&ip_set_ref_lock);
-
-		ip_set_destroy_set(s);
+		if (features & IPSET_TYPE_NAME) {
+			/* Must wait for flush to be really finished  */
+			rcu_barrier();
+		}
+		/* Must cancel garbage collectors */
+		s->variant->cancel_gc(s);
+		call_rcu(&s->rcu, ip_set_destroy_set_rcu);
 	}
 	return 0;
 out:
@@ -1394,9 +1413,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
-	/* Make sure all readers of the old set pointers are completed. */
-	synchronize_rcu();
-
 	return 0;
 }
 
@@ -2409,8 +2425,11 @@ ip_set_fini(void)
 {
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-
 	unregister_pernet_subsys(&ip_set_net_ops);
+
+	/* Wait for call_rcu() in destroy */
+	rcu_barrier();
+
 	pr_debug("these are the famous last words\n");
 }