Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
netfilter fixes for net

The following patchset contains netfilter updates for your net tree,
they are:

1) Fix refcount leak when dumping the dying/unconfirmed conntrack lists,
   from Florian Westphal.

2) Fix crash in NAT when removing a netnamespace, also from Florian.

3) Fix a crash in IPVS when trying to remove an estimator out of the
   sysctl scope, from Julian Anastasov.

4) Add zone attribute to the routing to calculate the message size in
   ctnetlink events, from Ken-ichirou MATSUZAWA.

5) Another fix for the dying/unconfirmed list which was preventing to
   dump more than one memory page of entries (~17 entries in x86_64).

6) Fix missing RCU-safe list insertion in the rule replacement code
   in nf_tables.

7) Since the new transaction infrastructure is in place, we have to
   upgrade the chain use counter from u16 to u32 to avoid overflow
   after more than 2^16 rules are added.

8) Fix refcount leak when replacing rule in nf_tables. This problem
   was also introduced in new transaction.

9) Call the ->destroy() callback when releasing nft-xt rules to fix
   module refcount leaks.

10) Set the family in the netlink messages that contain set elements
    in nf_tables to make it consistent with other object types.

11) Don't dump NAT port information if it is unset in nft_nat.

12) Update the MAINTAINERS file, I have merged the ebtables entry
    into netfilter. While at it, also removed the netfilter users
    mailing list, the development list should be enough.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 82 insertions, 18 deletions

diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index c42e83d2751..581a6584ed0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -3778,6 +3778,7 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net)
 	cancel_delayed_work_sync(&ipvs->defense_work);
 	cancel_work_sync(&ipvs->defense_work.work);
 	unregister_net_sysctl_table(ipvs->sysctl_hdr);
+	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 }
 
 #else
@@ -3840,7 +3841,6 @@ void __net_exit ip_vs_control_net_cleanup(struct net *net)
 	struct netns_ipvs *ipvs = net_ipvs(net);
 
 	ip_vs_trash_cleanup(net);
-	ip_vs_stop_estimator(net, &ipvs->tot_stats);
 	ip_vs_control_net_cleanup_sysctl(net);
 	remove_proc_entry("ip_vs_stats_percpu", net->proc_net);
 	remove_proc_entry("ip_vs_stats", net->proc_net);
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 58579634427..300ed1eec72 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -597,6 +597,9 @@ ctnetlink_nlmsg_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
 #endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
+#endif
 	       + ctnetlink_proto_size(ct)
 	       + ctnetlink_label_size(ct)
 	       ;
@@ -1150,7 +1153,7 @@ static int ctnetlink_done_list(struct netlink_callback *cb)
 static int
 ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying)
 {
-	struct nf_conn *ct, *last = NULL;
+	struct nf_conn *ct, *last;
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
 	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
@@ -1163,8 +1166,7 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 	if (cb->args[2])
 		return 0;
 
-	if (cb->args[0] == nr_cpu_ids)
-		return 0;
+	last = (struct nf_conn *)cb->args[1];
 
 	for (cpu = cb->args[0]; cpu < nr_cpu_ids; cpu++) {
 		struct ct_pcpu *pcpu;
@@ -1174,7 +1176,6 @@ ctnetlink_dump_list(struct sk_buff *skb, struct netlink_callback *cb, bool dying
 
 		pcpu = per_cpu_ptr(net->ct.pcpu_lists, cpu);
 		spin_lock_bh(&pcpu->lock);
-		last = (struct nf_conn *)cb->args[1];
 		list = dying ? &pcpu->dying : &pcpu->unconfirmed;
 restart:
 		hlist_nulls_for_each_entry(h, n, list, hnnode) {
@@ -1193,7 +1194,9 @@ restart:
 						  ct);
 			rcu_read_unlock();
 			if (res < 0) {
-				nf_conntrack_get(&ct->ct_general);
+				if (!atomic_inc_not_zero(&ct->ct_general.use))
+					continue;
+				cb->args[0] = cpu;
 				cb->args[1] = (unsigned long)ct;
 				spin_unlock_bh(&pcpu->lock);
 				goto out;
@@ -1202,10 +1205,10 @@ restart:
 		if (cb->args[1]) {
 			cb->args[1] = 0;
 			goto restart;
-		} else
-			cb->args[2] = 1;
+		}
 		spin_unlock_bh(&pcpu->lock);
 	}
+	cb->args[2] = 1;
 out:
 	if (last)
 		nf_ct_put(last);
@@ -2040,6 +2043,9 @@ ctnetlink_nfqueue_build_size(const struct nf_conn *ct)
 #ifdef CONFIG_NF_CONNTRACK_MARK
 	       + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
 #endif
+#ifdef CONFIG_NF_CONNTRACK_ZONES
+	       + nla_total_size(sizeof(u_int16_t)) /* CTA_ZONE */
+#endif
 	       + ctnetlink_proto_size(ct)
 	       ;
 }
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index 09096a670c4..a49907b1dab 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -525,6 +525,39 @@ static int nf_nat_proto_remove(struct nf_conn *i, void *data)
 	return i->status & IPS_NAT_MASK ? 1 : 0;
 }
 
+static int nf_nat_proto_clean(struct nf_conn *ct, void *data)
+{
+	struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (nf_nat_proto_remove(ct, data))
+		return 1;
+
+	if (!nat || !nat->ct)
+		return 0;
+
+	/* This netns is being destroyed, and conntrack has nat null binding.
+	 * Remove it from bysource hash, as the table will be freed soon.
+	 *
+	 * Else, when the conntrack is destoyed, nf_nat_cleanup_conntrack()
+	 * will delete entry from already-freed table.
+	 */
+	if (!del_timer(&ct->timeout))
+		return 1;
+
+	spin_lock_bh(&nf_nat_lock);
+	hlist_del_rcu(&nat->bysource);
+	ct->status &= ~IPS_NAT_DONE_MASK;
+	nat->ct = NULL;
+	spin_unlock_bh(&nf_nat_lock);
+
+	add_timer(&ct->timeout);
+
+	/* don't delete conntrack.  Although that would make things a lot
+	 * simpler, we'd end up flushing all conntracks on nat rmmod.
+	 */
+	return 0;
+}
+
 static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
 {
 	struct nf_nat_proto_clean clean = {
@@ -795,7 +828,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	struct nf_nat_proto_clean clean = {};
 
-	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0);
+	nf_ct_iterate_cleanup(net, nf_nat_proto_clean, &clean, 0, 0);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 624e083125b..ab4566cfcbe 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -1730,6 +1730,9 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 		if (!create || nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EINVAL;
 		handle = nf_tables_alloc_handle(table);
+
+		if (chain->use == UINT_MAX)
+			return -EOVERFLOW;
 	}
 
 	if (nla[NFTA_RULE_POSITION]) {
@@ -1789,14 +1792,15 @@ static int nf_tables_newrule(struct sock *nlsk, struct sk_buff *skb,
 
 	if (nlh->nlmsg_flags & NLM_F_REPLACE) {
 		if (nft_rule_is_active_next(net, old_rule)) {
-			trans = nft_trans_rule_add(&ctx, NFT_MSG_NEWRULE,
+			trans = nft_trans_rule_add(&ctx, NFT_MSG_DELRULE,
 						   old_rule);
 			if (trans == NULL) {
 				err = -ENOMEM;
 				goto err2;
 			}
 			nft_rule_disactivate_next(net, old_rule);
-			list_add_tail(&rule->list, &old_rule->list);
+			chain->use--;
+			list_add_tail_rcu(&rule->list, &old_rule->list);
 		} else {
 			err = -ENOENT;
 			goto err2;
@@ -1826,6 +1830,7 @@ err3:
 		list_del_rcu(&nft_trans_rule(trans)->list);
 		nft_rule_clear(net, nft_trans_rule(trans));
 		nft_trans_destroy(trans);
+		chain->use++;
 	}
 err2:
 	nf_tables_rule_destroy(&ctx, rule);
@@ -2845,7 +2850,7 @@ static int nf_tables_dump_set(struct sk_buff *skb, struct netlink_callback *cb)
 		goto nla_put_failure;
 
 	nfmsg = nlmsg_data(nlh);
-	nfmsg->nfgen_family = NFPROTO_UNSPEC;
+	nfmsg->nfgen_family = ctx.afi->family;
 	nfmsg->version      = NFNETLINK_V0;
 	nfmsg->res_id       = 0;
 
diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
index 8a779be832f..1840989092e 100644
--- a/net/netfilter/nft_compat.c
+++ b/net/netfilter/nft_compat.c
@@ -195,6 +195,15 @@ static void
 nft_target_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	struct xt_target *target = expr->ops->data;
+	void *info = nft_expr_priv(expr);
+	struct xt_tgdtor_param par;
+
+	par.net = ctx->net;
+	par.target = target;
+	par.targinfo = info;
+	par.family = ctx->afi->family;
+	if (par.target->destroy != NULL)
+		par.target->destroy(&par);
 
 	module_put(target->me);
 }
@@ -382,6 +391,15 @@ static void
 nft_match_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
 {
 	struct xt_match *match = expr->ops->data;
+	void *info = nft_expr_priv(expr);
+	struct xt_mtdtor_param par;
+
+	par.net = ctx->net;
+	par.match = match;
+	par.matchinfo = info;
+	par.family = ctx->afi->family;
+	if (par.match->destroy != NULL)
+		par.match->destroy(&par);
 
 	module_put(match->me);
 }
diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c
index a0195d28bcf..79ff58cd36d 100644
--- a/net/netfilter/nft_nat.c
+++ b/net/netfilter/nft_nat.c
@@ -175,12 +175,14 @@ static int nft_nat_dump(struct sk_buff *skb, const struct nft_expr *expr)
 	if (nla_put_be32(skb,
 			 NFTA_NAT_REG_ADDR_MAX, htonl(priv->sreg_addr_max)))
 		goto nla_put_failure;
-	if (nla_put_be32(skb,
-			 NFTA_NAT_REG_PROTO_MIN, htonl(priv->sreg_proto_min)))
-		goto nla_put_failure;
-	if (nla_put_be32(skb,
-			 NFTA_NAT_REG_PROTO_MAX, htonl(priv->sreg_proto_max)))
-		goto nla_put_failure;
+	if (priv->sreg_proto_min) {
+		if (nla_put_be32(skb, NFTA_NAT_REG_PROTO_MIN,
+				 htonl(priv->sreg_proto_min)))
+			goto nla_put_failure;
+		if (nla_put_be32(skb, NFTA_NAT_REG_PROTO_MAX,
+				 htonl(priv->sreg_proto_max)))
+			goto nla_put_failure;
+	}
 	return 0;
 
 nla_put_failure: