Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
Netfilter/nftables/IPVS fixes for net

The following patchset contains Netfilter/IPVS fixes, mostly nftables
fixes, most relevantly they are:

* Fix a crash in the h323 conntrack NAT helper due to expectation list
  corruption, from Alexey Dobriyan.

* A couple of RCU race fixes for conntrack, one manifests by hitting BUG_ON
  in nf_nat_setup_info() and the destroy path, patches from Andrey Vagin and
  me.

* Dump direction attribute in nft_ct only if it is set, from Arturo
  Borrero.

* Fix IPVS bug in its own connection tracking system that may lead to
  copying only 4 bytes of the IPv6 address when initializing the
  ip_vs_conn object, from Michal Kubecek.

* Fix -EBUSY errors in nftables when deleting the rules, chain and tables
  in a row due mixture of asynchronous and synchronous object releasing,
  from me.

* Three fixes for the nf_tables set infrastructure when using intervals and
  mappings, from me.

* Four patches to fixing the nf_tables log, reject and ct expressions from
  the new inet table, from Patrick McHardy.

* Fix memory overrun in the map that is used to dynamically allocate names
  from anonymous sets, also from Patrick.

* Fix a potential oops if you dump a set with NFPROTO_UNSPEC and a table
  name, from Patrick McHardy.
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

include/net/netfilter/nf_conntrack.h

@@ -284,6 +284,8 @@ extern unsigned int nf_conntrack_max;
 extern unsigned int nf_conntrack_hash_rnd;
 void init_nf_conntrack_hash_rnd(void);
 
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl);
+
 #define NF_CT_STAT_INC(net, count)	  __this_cpu_inc((net)->ct.stat->count)
 #define NF_CT_STAT_INC_ATOMIC(net, count) this_cpu_inc((net)->ct.stat->count)
 

include/net/netfilter/nf_tables.h

@@ -252,6 +252,7 @@ void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set,
  *	@owner: module reference
  *	@policy: netlink attribute policy
  *	@maxattr: highest netlink attribute number
+ *	@family: address family for AF-specific types
  */
 struct nft_expr_type {
 	const struct nft_expr_ops	*(*select_ops)(const struct nft_ctx *,
@@ -262,6 +263,7 @@ struct nft_expr_type {
 	struct module			*owner;
 	const struct nla_policy		*policy;
 	unsigned int			maxattr;
+	u8				family;
 };
 
 /**
@@ -320,7 +322,6 @@ static inline void *nft_expr_priv(const struct nft_expr *expr)
  *	struct nft_rule - nf_tables rule
  *
  *	@list: used internally
- *	@rcu_head: used internally for rcu
  *	@handle: rule handle
  *	@genmask: generation mask
  *	@dlen: length of expression data
@@ -328,7 +329,6 @@ static inline void *nft_expr_priv(const struct nft_expr *expr)
  */
 struct nft_rule {
 	struct list_head		list;
-	struct rcu_head			rcu_head;
 	u64				handle:46,
 					genmask:2,
 					dlen:16;
@@ -389,7 +389,6 @@ enum nft_chain_flags {
  *
  *	@rules: list of rules in the chain
  *	@list: used internally
- *	@rcu_head: used internally
  *	@net: net namespace that this chain belongs to
  *	@table: table that this chain belongs to
  *	@handle: chain handle
@@ -401,7 +400,6 @@ enum nft_chain_flags {
 struct nft_chain {
 	struct list_head		rules;
 	struct list_head		list;
-	struct rcu_head			rcu_head;
 	struct net			*net;
 	struct nft_table		*table;
 	u64				handle;
@@ -529,6 +527,9 @@ void nft_unregister_expr(struct nft_expr_type *);
 #define MODULE_ALIAS_NFT_CHAIN(family, name) \
 	MODULE_ALIAS("nft-chain-" __stringify(family) "-" name)
 
+#define MODULE_ALIAS_NFT_AF_EXPR(family, name) \
+	MODULE_ALIAS("nft-expr-" __stringify(family) "-" name)
+
 #define MODULE_ALIAS_NFT_EXPR(name) \
 	MODULE_ALIAS("nft-expr-" name)
 

include/net/netfilter/nft_reject.h

+#ifndef _NFT_REJECT_H_
+#define _NFT_REJECT_H_
+
+struct nft_reject {
+	enum nft_reject_types	type:8;
+	u8			icmp_code;
+};
+
+extern const struct nla_policy nft_reject_policy[];
+
+int nft_reject_init(const struct nft_ctx *ctx,
+		    const struct nft_expr *expr,
+		    const struct nlattr * const tb[]);
+
+int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr);
+
+void nft_reject_ipv4_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt);
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt);
+
+#endif

net/ipv4/netfilter/Kconfig

@@ -61,6 +61,11 @@ config NFT_CHAIN_NAT_IPV4
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
 
+config NFT_REJECT_IPV4
+	depends on NF_TABLES_IPV4
+	default NFT_REJECT
+	tristate
+
 config NF_TABLES_ARP
 	depends on NF_TABLES
 	tristate "ARP nf_tables support"

net/ipv4/netfilter/Makefile

@@ -30,6 +30,7 @@ obj-$(CONFIG_NF_NAT_PROTO_GRE) += nf_nat_proto_gre.o
 obj-$(CONFIG_NF_TABLES_IPV4) += nf_tables_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV4) += nft_chain_route_ipv4.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
+obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 

net/ipv4/netfilter/nf_nat_h323.c

@@ -229,7 +229,10 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct,
 			ret = nf_ct_expect_related(rtcp_exp);
 			if (ret == 0)
 				break;
-			else if (ret != -EBUSY) {
+			else if (ret == -EBUSY) {
+				nf_ct_unexpect_related(rtp_exp);
+				continue;
+			} else if (ret < 0) {
 				nf_ct_unexpect_related(rtp_exp);
 				nated_port = 0;
 				break;

net/ipv4/netfilter/nft_reject_ipv4.c

+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/icmp.h>
+#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/nft_reject.h>
+
+void nft_reject_ipv4_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		nf_send_unreach(pkt->skb, priv->icmp_code);
+		break;
+	case NFT_REJECT_TCP_RST:
+		nf_send_reset(pkt->skb, pkt->ops->hooknum);
+		break;
+	}
+
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv4_eval);
+
+static struct nft_expr_type nft_reject_ipv4_type;
+static const struct nft_expr_ops nft_reject_ipv4_ops = {
+	.type		= &nft_reject_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_ipv4_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "reject",
+	.ops		= &nft_reject_ipv4_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_reject_ipv4_type);
+}
+
+static void __exit nft_reject_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_ipv4_type);
+}
+
+module_init(nft_reject_ipv4_module_init);
+module_exit(nft_reject_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "reject");

net/ipv6/netfilter/Kconfig

@@ -50,6 +50,11 @@ config NFT_CHAIN_NAT_IPV6
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
 
+config NFT_REJECT_IPV6
+	depends on NF_TABLES_IPV6
+	default NFT_REJECT
+	tristate
+
 config IP6_NF_IPTABLES
 	tristate "IP6 tables support (required for filtering)"
 	depends on INET && IPV6

net/ipv6/netfilter/Makefile

@@ -27,6 +27,7 @@ obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
 obj-$(CONFIG_NF_TABLES_IPV6) += nf_tables_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
+obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 
 # matches
 obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o

net/ipv6/netfilter/nft_reject_ipv6.c

+/*
+ * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
+ * Copyright (c) 2013 Eric Leblond <eric@regit.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * Development of this code funded by Astaro AG (http://www.astaro.com/)
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+#include <net/netfilter/ipv6/nf_reject.h>
+
+void nft_reject_ipv6_eval(const struct nft_expr *expr,
+			  struct nft_data data[NFT_REG_MAX + 1],
+			  const struct nft_pktinfo *pkt)
+{
+	struct nft_reject *priv = nft_expr_priv(expr);
+	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
+
+	switch (priv->type) {
+	case NFT_REJECT_ICMP_UNREACH:
+		nf_send_unreach6(net, pkt->skb, priv->icmp_code,
+				 pkt->ops->hooknum);
+		break;
+	case NFT_REJECT_TCP_RST:
+		nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
+		break;
+	}
+
+	data[NFT_REG_VERDICT].verdict = NF_DROP;
+}
+EXPORT_SYMBOL_GPL(nft_reject_ipv6_eval);
+
+static struct nft_expr_type nft_reject_ipv6_type;
+static const struct nft_expr_ops nft_reject_ipv6_ops = {
+	.type		= &nft_reject_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_ipv6_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "reject",
+	.ops		= &nft_reject_ipv6_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_ipv6_module_init(void)
+{
+	return nft_register_expr(&nft_reject_ipv6_type);
+}
+
+static void __exit nft_reject_ipv6_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_ipv6_type);
+}
+
+module_init(nft_reject_ipv6_module_init);
+module_exit(nft_reject_ipv6_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "reject");

net/netfilter/Kconfig

@@ -513,7 +513,6 @@ config NFT_QUEUE
 
 config NFT_REJECT
 	depends on NF_TABLES
-	depends on NF_TABLES_IPV6 || !NF_TABLES_IPV6
 	default m if NETFILTER_ADVANCED=n
 	tristate "Netfilter nf_tables reject support"
 	help
@@ -521,6 +520,11 @@ config NFT_REJECT
 	  explicitly deny and notify via TCP reset/ICMP informational errors
 	  unallowed traffic.
 
+config NFT_REJECT_INET
+	depends on NF_TABLES_INET
+	default NFT_REJECT
+	tristate
+
 config NFT_COMPAT
 	depends on NF_TABLES
 	depends on NETFILTER_XTABLES

net/netfilter/Makefile

@@ -79,6 +79,7 @@ obj-$(CONFIG_NFT_LIMIT)		+= nft_limit.o
 obj-$(CONFIG_NFT_NAT)		+= nft_nat.o
 obj-$(CONFIG_NFT_QUEUE)		+= nft_queue.o
 obj-$(CONFIG_NFT_REJECT) 	+= nft_reject.o
+obj-$(CONFIG_NFT_REJECT_INET)	+= nft_reject_inet.o
 obj-$(CONFIG_NFT_RBTREE)	+= nft_rbtree.o
 obj-$(CONFIG_NFT_HASH)		+= nft_hash.o
 obj-$(CONFIG_NFT_COUNTER)	+= nft_counter.o

net/netfilter/ipvs/ip_vs_conn.c

@@ -871,11 +871,11 @@ ip_vs_conn_new(const struct ip_vs_conn_param *p,
 	cp->protocol	   = p->protocol;
 	ip_vs_addr_set(p->af, &cp->caddr, p->caddr);
 	cp->cport	   = p->cport;
-	ip_vs_addr_set(p->af, &cp->vaddr, p->vaddr);
-	cp->vport	   = p->vport;
-	/* proto should only be IPPROTO_IP if d_addr is a fwmark */
+	/* proto should only be IPPROTO_IP if p->vaddr is a fwmark */
 	ip_vs_addr_set(p->protocol == IPPROTO_IP ? AF_UNSPEC : p->af,
-		       &cp->daddr, daddr);
+		       &cp->vaddr, p->vaddr);
+	cp->vport	   = p->vport;
+	ip_vs_addr_set(p->af, &cp->daddr, daddr);
 	cp->dport          = dport;
 	cp->flags	   = flags;
 	cp->fwmark         = fwmark;

net/netfilter/nf_conntrack_core.c

@@ -312,6 +312,21 @@ static void death_by_timeout(unsigned long ul_conntrack)
 	nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
 }
 
+static inline bool
+nf_ct_key_equal(struct nf_conntrack_tuple_hash *h,
+			const struct nf_conntrack_tuple *tuple,
+			u16 zone)
+{
+	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
+
+	/* A conntrack can be recreated with the equal tuple,
+	 * so we need to check that the conntrack is confirmed
+	 */
+	return nf_ct_tuple_equal(tuple, &h->tuple) &&
+		nf_ct_zone(ct) == zone &&
+		nf_ct_is_confirmed(ct);
+}
+
 /*
  * Warning :
  * - Caller must take a reference on returned object
@@ -333,8 +348,7 @@ ____nf_conntrack_find(struct net *net, u16 zone,
 	local_bh_disable();
 begin:
 	hlist_nulls_for_each_entry_rcu(h, n, &net->ct.hash[bucket], hnnode) {
-		if (nf_ct_tuple_equal(tuple, &h->tuple) &&
-		    nf_ct_zone(nf_ct_tuplehash_to_ctrack(h)) == zone) {
+		if (nf_ct_key_equal(h, tuple, zone)) {
 			NF_CT_STAT_INC(net, found);
 			local_bh_enable();
 			return h;
@@ -372,8 +386,7 @@ __nf_conntrack_find_get(struct net *net, u16 zone,
 			     !atomic_inc_not_zero(&ct->ct_general.use)))
 			h = NULL;
 		else {
-			if (unlikely(!nf_ct_tuple_equal(tuple, &h->tuple) ||
-				     nf_ct_zone(ct) != zone)) {
+			if (unlikely(!nf_ct_key_equal(h, tuple, zone))) {
 				nf_ct_put(ct);
 				goto begin;
 			}
@@ -435,7 +448,9 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 			goto out;
 
 	add_timer(&ct->timeout);
-	nf_conntrack_get(&ct->ct_general);
+	smp_wmb();
+	/* The caller holds a reference to this object */
+	atomic_set(&ct->ct_general.use, 2);
 	__nf_conntrack_hash_insert(ct, hash, repl_hash);
 	NF_CT_STAT_INC(net, insert);
 	spin_unlock_bh(&nf_conntrack_lock);
@@ -449,6 +464,21 @@ nf_conntrack_hash_check_insert(struct nf_conn *ct)
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_hash_check_insert);
 
+/* deletion from this larval template list happens via nf_ct_put() */
+void nf_conntrack_tmpl_insert(struct net *net, struct nf_conn *tmpl)
+{
+	__set_bit(IPS_TEMPLATE_BIT, &tmpl->status);
+	__set_bit(IPS_CONFIRMED_BIT, &tmpl->status);
+	nf_conntrack_get(&tmpl->ct_general);
+
+	spin_lock_bh(&nf_conntrack_lock);
+	/* Overload tuple linked list to put us in template list. */
+	hlist_nulls_add_head_rcu(&tmpl->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
+				 &net->ct.tmpl);
+	spin_unlock_bh(&nf_conntrack_lock);
+}
+EXPORT_SYMBOL_GPL(nf_conntrack_tmpl_insert);
+
 /* Confirm a connection given skb; places it in hash table */
 int
 __nf_conntrack_confirm(struct sk_buff *skb)
@@ -720,11 +750,10 @@ __nf_conntrack_alloc(struct net *net, u16 zone,
 		nf_ct_zone->id = zone;
 	}
 #endif
-	/*
-	 * changes to lookup keys must be done before setting refcnt to 1
+	/* Because we use RCU lookups, we set ct_general.use to zero before
+	 * this is inserted in any list.
 	 */
-	smp_wmb();
-	atomic_set(&ct->ct_general.use, 1);
+	atomic_set(&ct->ct_general.use, 0);
 	return ct;
 
 #ifdef CONFIG_NF_CONNTRACK_ZONES
@@ -748,6 +777,11 @@ void nf_conntrack_free(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 
+	/* A freed object has refcnt == 0, that's
+	 * the golden rule for SLAB_DESTROY_BY_RCU
+	 */
+	NF_CT_ASSERT(atomic_read(&ct->ct_general.use) == 0);
+
 	nf_ct_ext_destroy(ct);
 	nf_ct_ext_free(ct);
 	kmem_cache_free(net->ct.nf_conntrack_cachep, ct);
@@ -843,6 +877,9 @@ init_conntrack(struct net *net, struct nf_conn *tmpl,
 		NF_CT_STAT_INC(net, new);
 	}
 
+	/* Now it is inserted into the unconfirmed list, bump refcount */
+	nf_conntrack_get(&ct->ct_general);
+
 	/* Overload tuple linked list to put us in unconfirmed list. */
 	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
 		       &net->ct.unconfirmed);

net/netfilter/nf_synproxy_core.c

@@ -363,9 +363,8 @@ static int __net_init synproxy_net_init(struct net *net)
 		goto err2;
 	if (!nfct_synproxy_ext_add(ct))
 		goto err2;
-	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
-	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
 
+	nf_conntrack_tmpl_insert(net, ct);
 	snet->tmpl = ct;
 
 	snet->stats = alloc_percpu(struct synproxy_stats);
@@ -390,7 +389,7 @@ static void __net_exit synproxy_net_exit(struct net *net)
 {
 	struct synproxy_net *snet = synproxy_pernet(net);
 
-	nf_conntrack_free(snet->tmpl);
+	nf_ct_put(snet->tmpl);
 	synproxy_proc_exit(net);
 	free_percpu(snet->stats);
 }

net/netfilter/nf_tables_api.c

@@ -1008,10 +1008,8 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 	return 0;
 }
 
-static void nf_tables_rcu_chain_destroy(struct rcu_head *head)
+static void nf_tables_chain_destroy(struct nft_chain *chain)
 {
-	struct nft_chain *chain = container_of(head, struct nft_chain, rcu_head);
-
 	BUG_ON(chain->use > 0);
 
 	if (chain->flags & NFT_BASE_CHAIN) {
@@ -1045,7 +1043,7 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 	if (IS_ERR(chain))
 		return PTR_ERR(chain);
 
-	if (!list_empty(&chain->rules))
+	if (!list_empty(&chain->rules) || chain->use > 0)
 		return -EBUSY;
 
 	list_del(&chain->list);
@@ -1059,7 +1057,9 @@ static int nf_tables_delchain(struct sock *nlsk, struct sk_buff *skb,
 			       family);
 
 	/* Make sure all rule references are gone before this is released */
-	call_rcu(&chain->rcu_head, nf_tables_rcu_chain_destroy);
+	synchronize_rcu();
+
+	nf_tables_chain_destroy(chain);
 	return 0;
 }
 
@@ -1114,35 +1114,45 @@ void nft_unregister_expr(struct nft_expr_type *type)
 }
 EXPORT_SYMBOL_GPL(nft_unregister_expr);
 
-static const struct nft_expr_type *__nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *__nft_expr_type_get(u8 family,
+						       struct nlattr *nla)
 {
 	const struct nft_expr_type *type;
 
 	list_for_each_entry(type, &nf_tables_expressions, list) {
-		if (!nla_strcmp(nla, type->name))
+		if (!nla_strcmp(nla, type->name) &&
+		    (!type->family || type->family == family))
 			return type;
 	}
 	return NULL;
 }
 
-static const struct nft_expr_type *nft_expr_type_get(struct nlattr *nla)
+static const struct nft_expr_type *nft_expr_type_get(u8 family,
+						     struct nlattr *nla)
 {
 	const struct nft_expr_type *type;
 
 	if (nla == NULL)
 		return ERR_PTR(-EINVAL);
 
-	type = __nft_expr_type_get(nla);
+	type = __nft_expr_type_get(family, nla);
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
 #ifdef CONFIG_MODULES
 	if (type == NULL) {
+		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
+		request_module("nft-expr-%u-%.*s", family,
+			       nla_len(nla), (char *)nla_data(nla));
+		nfnl_lock(NFNL_SUBSYS_NFTABLES);
+		if (__nft_expr_type_get(family, nla))
+			return ERR_PTR(-EAGAIN);
+
 		nfnl_unlock(NFNL_SUBSYS_NFTABLES);
 		request_module("nft-expr-%.*s",
 			       nla_len(nla), (char *)nla_data(nla));
 		nfnl_lock(NFNL_SUBSYS_NFTABLES);
-		if (__nft_expr_type_get(nla))
+		if (__nft_expr_type_get(family, nla))
 			return ERR_PTR(-EAGAIN);
 	}
 #endif
@@ -1193,7 +1203,7 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx,
 	if (err < 0)
 		return err;
 
-	type = nft_expr_type_get(tb[NFTA_EXPR_NAME]);
+	type = nft_expr_type_get(ctx->afi->family, tb[NFTA_EXPR_NAME]);
 	if (IS_ERR(type))
 		return PTR_ERR(type);
 
@@ -1521,9 +1531,8 @@ static int nf_tables_getrule(struct sock *nlsk, struct sk_buff *skb,
 	return err;
 }
 
-static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
+static void nf_tables_rule_destroy(struct nft_rule *rule)
 {
-	struct nft_rule *rule = container_of(head, struct nft_rule, rcu_head);
 	struct nft_expr *expr;
 
 	/*
@@ -1538,11 +1547,6 @@ static void nf_tables_rcu_rule_destroy(struct rcu_head *head)
 	kfree(rule);
 }
 
-static void nf_tables_rule_destroy(struct nft_rule *rule)
-{
-	call_rcu(&rule->rcu_head, nf_tables_rcu_rule_destroy);
-}
-
 #define NFT_RULE_MAXEXPRS	128
 
 static struct nft_expr_info *info;
@@ -1809,9 +1813,6 @@ static int nf_tables_commit(struct sk_buff *skb)
 	synchronize_rcu();
 
 	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		/* Delete this rule from the dirty list */
-		list_del(&rupd->list);
-
 		/* This rule was inactive in the past and just became active.
 		 * Clear the next bit of the genmask since its meaning has
 		 * changed, now it is the future.
@@ -1822,6 +1823,7 @@ static int nf_tables_commit(struct sk_buff *skb)
 					      rupd->chain, rupd->rule,
 					      NFT_MSG_NEWRULE, 0,
 					      rupd->family);
+			list_del(&rupd->list);
 			kfree(rupd);
 			continue;
 		}
@@ -1831,7 +1833,15 @@ static int nf_tables_commit(struct sk_buff *skb)
 		nf_tables_rule_notify(skb, rupd->nlh, rupd->table, rupd->chain,
 				      rupd->rule, NFT_MSG_DELRULE, 0,
 				      rupd->family);
+	}
+
+	/* Make sure we don't see any packet traversing old rules */
+	synchronize_rcu();
+
+	/* Now we can safely release unused old rules */
+	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
 		nf_tables_rule_destroy(rupd->rule);
+		list_del(&rupd->list);
 		kfree(rupd);
 	}
 
@@ -1844,20 +1854,26 @@ static int nf_tables_abort(struct sk_buff *skb)
 	struct nft_rule_trans *rupd, *tmp;
 
 	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
-		/* Delete all rules from the dirty list */
-		list_del(&rupd->list);
-
 		if (!nft_rule_is_active_next(net, rupd->rule)) {
 			nft_rule_clear(net, rupd->rule);
+			list_del(&rupd->list);
 			kfree(rupd);
 			continue;
 		}
 
 		/* This rule is inactive, get rid of it */
 		list_del_rcu(&rupd->rule->list);
+	}
+
+	/* Make sure we don't see any packet accessing aborted rules */
+	synchronize_rcu();
+
+	list_for_each_entry_safe(rupd, tmp, &net->nft.commit_list, list) {
 		nf_tables_rule_destroy(rupd->rule);
+		list_del(&rupd->list);
 		kfree(rupd);
 	}
+
 	return 0;
 }
 
@@ -1943,6 +1959,9 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx,
 	}
 
 	if (nla[NFTA_SET_TABLE] != NULL) {
+		if (afi == NULL)
+			return -EAFNOSUPPORT;
+
 		table = nf_tables_table_lookup(afi, nla[NFTA_SET_TABLE]);
 		if (IS_ERR(table))
 			return PTR_ERR(table);
@@ -1989,13 +2008,13 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set,
 
 			if (!sscanf(i->name, name, &tmp))
 				continue;
-			if (tmp < 0 || tmp > BITS_PER_LONG * PAGE_SIZE)
+			if (tmp < 0 || tmp >= BITS_PER_BYTE * PAGE_SIZE)
 				continue;
 
 			set_bit(tmp, inuse);
 		}
 
-		n = find_first_zero_bit(inuse, BITS_PER_LONG * PAGE_SIZE);
+		n = find_first_zero_bit(inuse, BITS_PER_BYTE * PAGE_SIZE);
 		free_page((unsigned long)inuse);
 	}
 
@@ -2428,6 +2447,8 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_ctx ctx;
 	int err;
 
+	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
+		return -EAFNOSUPPORT;
 	if (nla[NFTA_SET_TABLE] == NULL)
 		return -EINVAL;
 
@@ -2435,9 +2456,6 @@ static int nf_tables_delset(struct sock *nlsk, struct sk_buff *skb,
 	if (err < 0)
 		return err;
 
-	if (nfmsg->nfgen_family == NFPROTO_UNSPEC)
-		return -EAFNOSUPPORT;
-
 	set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME]);
 	if (IS_ERR(set))
 		return PTR_ERR(set);
@@ -2723,6 +2741,9 @@ static int nft_add_set_elem(const struct nft_ctx *ctx, struct nft_set *set,
 		if (nla[NFTA_SET_ELEM_DATA] == NULL &&
 		    !(elem.flags & NFT_SET_ELEM_INTERVAL_END))
 			return -EINVAL;
+		if (nla[NFTA_SET_ELEM_DATA] != NULL &&
+		    elem.flags & NFT_SET_ELEM_INTERVAL_END)
+			return -EINVAL;
 	} else {
 		if (nla[NFTA_SET_ELEM_DATA] != NULL)
 			return -EINVAL;
@@ -2977,6 +2998,9 @@ static int nf_tables_loop_check_setelem(const struct nft_ctx *ctx,
 					const struct nft_set_iter *iter,
 					const struct nft_set_elem *elem)
 {
+	if (elem->flags & NFT_SET_ELEM_INTERVAL_END)
+		return 0;
+
 	switch (elem->data.verdict) {
 	case NFT_JUMP:
 	case NFT_GOTO:

net/netfilter/nf_tables_core.c

@@ -103,9 +103,9 @@ static struct nf_loginfo trace_loginfo = {
 	},
 };
 
-static inline void nft_trace_packet(const struct nft_pktinfo *pkt,
-				    const struct nft_chain *chain,
-				    int rulenum, enum nft_trace type)
+static void nft_trace_packet(const struct nft_pktinfo *pkt,
+			     const struct nft_chain *chain,
+			     int rulenum, enum nft_trace type)
 {
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 

net/netfilter/nft_ct.c

@@ -226,6 +226,7 @@ static int nft_ct_init_validate_get(const struct nft_expr *expr,
 		if (tb[NFTA_CT_DIRECTION] != NULL)
 			return -EINVAL;
 		break;
+	case NFT_CT_L3PROTOCOL:
 	case NFT_CT_PROTOCOL:
 	case NFT_CT_SRC:
 	case NFT_CT_DST:
@@ -311,8 +312,19 @@ static int nft_ct_get_dump(struct sk_buff *skb, const struct nft_expr *expr)
 		goto nla_put_failure;
 	if (nla_put_be32(skb, NFTA_CT_KEY, htonl(priv->key)))
 		goto nla_put_failure;
-	if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
-		goto nla_put_failure;
+
+	switch (priv->key) {
+	case NFT_CT_PROTOCOL:
+	case NFT_CT_SRC:
+	case NFT_CT_DST:
+	case NFT_CT_PROTO_SRC:
+	case NFT_CT_PROTO_DST:
+		if (nla_put_u8(skb, NFTA_CT_DIRECTION, priv->dir))
+			goto nla_put_failure;
+	default:
+		break;
+	}
+
 	return 0;
 
 nla_put_failure:

net/netfilter/nft_log.c

@@ -23,7 +23,6 @@ static const char *nft_log_null_prefix = "";
 struct nft_log {
 	struct nf_loginfo	loginfo;
 	char			*prefix;
-	int			family;
 };
 
 static void nft_log_eval(const struct nft_expr *expr,
@@ -33,7 +32,7 @@ static void nft_log_eval(const struct nft_expr *expr,
 	const struct nft_log *priv = nft_expr_priv(expr);
 	struct net *net = dev_net(pkt->in ? pkt->in : pkt->out);
 
-	nf_log_packet(net, priv->family, pkt->ops->hooknum, pkt->skb, pkt->in,
+	nf_log_packet(net, pkt->ops->pf, pkt->ops->hooknum, pkt->skb, pkt->in,
 		      pkt->out, &priv->loginfo, "%s", priv->prefix);
 }
 
@@ -52,8 +51,6 @@ static int nft_log_init(const struct nft_ctx *ctx,
 	struct nf_loginfo *li = &priv->loginfo;
 	const struct nlattr *nla;
 
-	priv->family = ctx->afi->family;
-
 	nla = tb[NFTA_LOG_PREFIX];
 	if (nla != NULL) {
 		priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);

net/netfilter/nft_queue.c

@@ -25,7 +25,6 @@ struct nft_queue {
 	u16	queuenum;
 	u16	queues_total;
 	u16	flags;
-	u8	family;
 };
 
 static void nft_queue_eval(const struct nft_expr *expr,
@@ -43,7 +42,7 @@ static void nft_queue_eval(const struct nft_expr *expr,
 			queue = priv->queuenum + cpu % priv->queues_total;
 		} else {
 			queue = nfqueue_hash(pkt->skb, queue,
-					     priv->queues_total, priv->family,
+					     priv->queues_total, pkt->ops->pf,
 					     jhash_initval);
 		}
 	}
@@ -71,7 +70,6 @@ static int nft_queue_init(const struct nft_ctx *ctx,
 		return -EINVAL;
 
 	init_hashrandom(&jhash_initval);
-	priv->family = ctx->afi->family;
 	priv->queuenum = ntohs(nla_get_be16(tb[NFTA_QUEUE_NUM]));
 
 	if (tb[NFTA_QUEUE_TOTAL] != NULL)

net/netfilter/nft_rbtree.c

@@ -69,8 +69,10 @@ static void nft_rbtree_elem_destroy(const struct nft_set *set,
 				    struct nft_rbtree_elem *rbe)
 {
 	nft_data_uninit(&rbe->key, NFT_DATA_VALUE);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 		nft_data_uninit(rbe->data, set->dtype);
+
 	kfree(rbe);
 }
 
@@ -108,7 +110,8 @@ static int nft_rbtree_insert(const struct nft_set *set,
 	int err;
 
 	size = sizeof(*rbe);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(elem->flags & NFT_SET_ELEM_INTERVAL_END))
 		size += sizeof(rbe->data[0]);
 
 	rbe = kzalloc(size, GFP_KERNEL);
@@ -117,7 +120,8 @@ static int nft_rbtree_insert(const struct nft_set *set,
 
 	rbe->flags = elem->flags;
 	nft_data_copy(&rbe->key, &elem->key);
-	if (set->flags & NFT_SET_MAP)
+	if (set->flags & NFT_SET_MAP &&
+	    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 		nft_data_copy(rbe->data, &elem->data);
 
 	err = __nft_rbtree_insert(set, rbe);
@@ -153,7 +157,8 @@ static int nft_rbtree_get(const struct nft_set *set, struct nft_set_elem *elem)
 			parent = parent->rb_right;
 		else {
 			elem->cookie = rbe;
-			if (set->flags & NFT_SET_MAP)
+			if (set->flags & NFT_SET_MAP &&
+			    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 				nft_data_copy(&elem->data, rbe->data);
 			elem->flags = rbe->flags;
 			return 0;
@@ -177,7 +182,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx,
 
 		rbe = rb_entry(node, struct nft_rbtree_elem, node);
 		nft_data_copy(&elem.key, &rbe->key);
-		if (set->flags & NFT_SET_MAP)
+		if (set->flags & NFT_SET_MAP &&
+		    !(rbe->flags & NFT_SET_ELEM_INTERVAL_END))
 			nft_data_copy(&elem.data, rbe->data);
 		elem.flags = rbe->flags;
 

net/netfilter/nft_reject.c

@@ -16,65 +16,23 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
-#include <net/icmp.h>
-#include <net/netfilter/ipv4/nf_reject.h>
+#include <net/netfilter/nft_reject.h>
 
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-#include <net/netfilter/ipv6/nf_reject.h>
-#endif
-
-struct nft_reject {
-	enum nft_reject_types	type:8;
-	u8			icmp_code;
-	u8			family;
-};
-
-static void nft_reject_eval(const struct nft_expr *expr,
-			      struct nft_data data[NFT_REG_MAX + 1],
-			      const struct nft_pktinfo *pkt)
-{
-	struct nft_reject *priv = nft_expr_priv(expr);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-	struct net *net = dev_net((pkt->in != NULL) ? pkt->in : pkt->out);
-#endif
-	switch (priv->type) {
-	case NFT_REJECT_ICMP_UNREACH:
-		if (priv->family == NFPROTO_IPV4)
-			nf_send_unreach(pkt->skb, priv->icmp_code);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-		else if (priv->family == NFPROTO_IPV6)
-			nf_send_unreach6(net, pkt->skb, priv->icmp_code,
-				      pkt->ops->hooknum);
-#endif
-		break;
-	case NFT_REJECT_TCP_RST:
-		if (priv->family == NFPROTO_IPV4)
-			nf_send_reset(pkt->skb, pkt->ops->hooknum);
-#if IS_ENABLED(CONFIG_NF_TABLES_IPV6)
-		else if (priv->family == NFPROTO_IPV6)
-			nf_send_reset6(net, pkt->skb, pkt->ops->hooknum);
-#endif
-		break;
-	}
-
-	data[NFT_REG_VERDICT].verdict = NF_DROP;
-}
-
-static const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
+const struct nla_policy nft_reject_policy[NFTA_REJECT_MAX + 1] = {
 	[NFTA_REJECT_TYPE]		= { .type = NLA_U32 },
 	[NFTA_REJECT_ICMP_CODE]		= { .type = NLA_U8 },
 };
+EXPORT_SYMBOL_GPL(nft_reject_policy);
 
-static int nft_reject_init(const struct nft_ctx *ctx,
-			   const struct nft_expr *expr,
-			   const struct nlattr * const tb[])
+int nft_reject_init(const struct nft_ctx *ctx,
+		    const struct nft_expr *expr,
+		    const struct nlattr * const tb[])
 {
 	struct nft_reject *priv = nft_expr_priv(expr);
 
 	if (tb[NFTA_REJECT_TYPE] == NULL)
 		return -EINVAL;
 
-	priv->family = ctx->afi->family;
 	priv->type = ntohl(nla_get_be32(tb[NFTA_REJECT_TYPE]));
 	switch (priv->type) {
 	case NFT_REJECT_ICMP_UNREACH:
@@ -89,8 +47,9 @@ static int nft_reject_init(const struct nft_ctx *ctx,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(nft_reject_init);
 
-static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
+int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_reject *priv = nft_expr_priv(expr);
 
@@ -109,37 +68,7 @@ static int nft_reject_dump(struct sk_buff *skb, const struct nft_expr *expr)
 nla_put_failure:
 	return -1;
 }
-
-static struct nft_expr_type nft_reject_type;
-static const struct nft_expr_ops nft_reject_ops = {
-	.type		= &nft_reject_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
-	.eval		= nft_reject_eval,
-	.init		= nft_reject_init,
-	.dump		= nft_reject_dump,
-};
-
-static struct nft_expr_type nft_reject_type __read_mostly = {
-	.name		= "reject",
-	.ops		= &nft_reject_ops,
-	.policy		= nft_reject_policy,
-	.maxattr	= NFTA_REJECT_MAX,
-	.owner		= THIS_MODULE,
-};
-
-static int __init nft_reject_module_init(void)
-{
-	return nft_register_expr(&nft_reject_type);
-}
-
-static void __exit nft_reject_module_exit(void)
-{
-	nft_unregister_expr(&nft_reject_type);
-}
-
-module_init(nft_reject_module_init);
-module_exit(nft_reject_module_exit);
+EXPORT_SYMBOL_GPL(nft_reject_dump);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_EXPR("reject");

net/netfilter/nft_reject_inet.c

+/*
+ * Copyright (c) 2014 Patrick McHardy <kaber@trash.net>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/netlink.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nft_reject.h>
+
+static void nft_reject_inet_eval(const struct nft_expr *expr,
+				 struct nft_data data[NFT_REG_MAX + 1],
+				 const struct nft_pktinfo *pkt)
+{
+	switch (pkt->ops->pf) {
+	case NFPROTO_IPV4:
+		nft_reject_ipv4_eval(expr, data, pkt);
+	case NFPROTO_IPV6:
+		nft_reject_ipv6_eval(expr, data, pkt);
+	}
+}
+
+static struct nft_expr_type nft_reject_inet_type;
+static const struct nft_expr_ops nft_reject_inet_ops = {
+	.type		= &nft_reject_inet_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_reject)),
+	.eval		= nft_reject_inet_eval,
+	.init		= nft_reject_init,
+	.dump		= nft_reject_dump,
+};
+
+static struct nft_expr_type nft_reject_inet_type __read_mostly = {
+	.family		= NFPROTO_INET,
+	.name		= "reject",
+	.ops		= &nft_reject_inet_ops,
+	.policy		= nft_reject_policy,
+	.maxattr	= NFTA_REJECT_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_reject_inet_module_init(void)
+{
+	return nft_register_expr(&nft_reject_inet_type);
+}
+
+static void __exit nft_reject_inet_module_exit(void)
+{
+	nft_unregister_expr(&nft_reject_inet_type);
+}
+
+module_init(nft_reject_inet_module_init);
+module_exit(nft_reject_inet_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS_NFT_AF_EXPR(1, "reject");

net/netfilter/xt_CT.c

@@ -228,12 +228,7 @@ static int xt_ct_tg_check(const struct xt_tgchk_param *par,
 			goto err3;
 	}
 
-	__set_bit(IPS_TEMPLATE_BIT, &ct->status);
-	__set_bit(IPS_CONFIRMED_BIT, &ct->status);
-
-	/* Overload tuple linked list to put us in template list. */
-	hlist_nulls_add_head_rcu(&ct->tuplehash[IP_CT_DIR_ORIGINAL].hnnode,
-				 &par->net->ct.tmpl);
+	nf_conntrack_tmpl_insert(par->net, ct);
 out:
 	info->ct = ct;
 	return 0;