1 files changed, 53 insertions, 27 deletions

diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c
index 16ae770f049d..544106475d4f 100644
--- a/net/netfilter/ipset/ip_set_core.c
+++ b/net/netfilter/ipset/ip_set_core.c
@@ -61,6 +61,8 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_IPSET);
 	ip_set_dereference((inst)->ip_set_list)[id]
 #define ip_set_ref_netlink(inst,id)	\
 	rcu_dereference_raw((inst)->ip_set_list)[id]
+#define ip_set_dereference_nfnl(p)	\
+	rcu_dereference_check(p, lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET))
 
 /* The set types are implemented in modules and registered set types
  * can be found in ip_set_type_list. Adding/deleting types is
@@ -530,6 +532,14 @@ __ip_set_put(struct ip_set *set)
 /* set->ref can be swapped out by ip_set_swap, netlink events (like dump) need
  * a separate reference counter
  */
+static void
+__ip_set_get_netlink(struct ip_set *set)
+{
+	write_lock_bh(&ip_set_ref_lock);
+	set->ref_netlink++;
+	write_unlock_bh(&ip_set_ref_lock);
+}
+
 static inline void
 __ip_set_put_netlink(struct ip_set *set)
 {
@@ -548,15 +558,10 @@ __ip_set_put_netlink(struct ip_set *set)
 static inline struct ip_set *
 ip_set_rcu_get(struct net *net, ip_set_id_t index)
 {
-	struct ip_set *set;
 	struct ip_set_net *inst = ip_set_pernet(net);
 
-	rcu_read_lock();
-	/* ip_set_list itself needs to be protected */
-	set = rcu_dereference(inst->ip_set_list)[index];
-	rcu_read_unlock();
-
-	return set;
+	/* ip_set_list and the set pointer need to be protected */
+	return ip_set_dereference_nfnl(inst->ip_set_list)[index];
 }
 
 static inline void
@@ -811,20 +816,9 @@ static struct nlmsghdr *
 start_msg(struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags,
 	  enum ipset_cmd cmd)
 {
-	struct nlmsghdr *nlh;
-	struct nfgenmsg *nfmsg;
-
-	nlh = nlmsg_put(skb, portid, seq, nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd),
-			sizeof(*nfmsg), flags);
-	if (!nlh)
-		return NULL;
-
-	nfmsg = nlmsg_data(nlh);
-	nfmsg->nfgen_family = NFPROTO_IPV4;
-	nfmsg->version = NFNETLINK_V0;
-	nfmsg->res_id = 0;
-
-	return nlh;
+	return nfnl_msg_put(skb, portid, seq,
+			    nfnl_msg_type(NFNL_SUBSYS_IPSET, cmd), flags,
+			    NFPROTO_IPV4, NFNETLINK_V0, 0);
 }
 
 /* Create a set */
@@ -1012,6 +1006,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl,
 	return ret;
 
 cleanup:
+	set->variant->cancel_gc(set);
 	set->variant->destroy(set);
 put_out:
 	module_put(set->type->me);
@@ -1040,6 +1035,14 @@ 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 net *net, struct sock *ctnl,
 			  struct sk_buff *skb, const struct nlmsghdr *nlh,
 			  const struct nlattr * const attr[],
@@ -1053,8 +1056,6 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl,
 	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.
@@ -1066,8 +1067,10 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl,
 	 * 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)) {
@@ -1081,12 +1084,17 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl,
 			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);
 			}
 		}
 		/* Modified by ip_set_destroy() only, which is serialized */
 		inst->is_destroyed = false;
 	} else {
+		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) {
@@ -1096,10 +1104,16 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl,
 			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:
@@ -1539,6 +1553,14 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set,
 	bool eexist = flags & IPSET_FLAG_EXIST, retried = false;
 
 	do {
+		if (retried) {
+			__ip_set_get_netlink(set);
+			nfnl_unlock(NFNL_SUBSYS_IPSET);
+			cond_resched();
+			nfnl_lock(NFNL_SUBSYS_IPSET);
+			__ip_set_put_netlink(set);
+		}
+
 		ip_set_lock(set);
 		ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried);
 		ip_set_unlock(set);
@@ -2215,6 +2237,7 @@ ip_set_net_exit(struct net *net)
 		set = ip_set(inst, i);
 		if (set) {
 			ip_set(inst, i) = NULL;
+			set->variant->cancel_gc(set);
 			ip_set_destroy_set(set);
 		}
 	}
@@ -2262,8 +2285,11 @@ 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");
 }