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

Pablo Neira Ayuso says:

====================
Netfilter updates for net-next

The following patchset contains Netfilter updates for your net-next
tree, they are:

1) Remove obsolete nf_log tracing from nf_tables, from Florian Westphal.

2) Add support for map lookups to numgen, random and hash expressions,
   from Laura Garcia.

3) Allow to register nat hooks for iptables and nftables at the same
   time. Patchset from Florian Westpha.

4) Timeout support for rbtree sets.

5) ip6_rpfilter works needs interface for link-local addresses, from
   Vincent Bernat.

6) Add nf_ct_hook and nf_nat_hook structures and use them.

7) Do not drop packets on packets raceing to insert conntrack entries
   into hashes, this is particularly a problem in nfqueue setups.

8) Address fallout from xt_osf separation to nf_osf, patches
   from Florian Westphal and Fernando Mancera.

9) Remove reference to struct nft_af_info, which doesn't exist anymore.
   From Taehee Yoo.

This batch comes with is a conflict between 25fd386e0bc0 ("netfilter:
core: add missing __rcu annotation") in your tree and 2c205dd3981f
("netfilter: add struct nf_nat_hook and use it") coming in this batch.
This conflict can be solved by leaving the __rcu tag on
__netfilter_net_init() - added by 25fd386e0bc0 - and remove all code
related to nf_nat_decode_session_hook - which is gone after
2c205dd3981f, as described by:

diff --cc net/netfilter/core.c
index e0ae4aae96f5,206fb2c4c319..168af54db975
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@@ -611,7 -580,13 +611,8 @@@ const struct nf_conntrack_zone nf_ct_zo
  EXPORT_SYMBOL_GPL(nf_ct_zone_dflt);
  #endif /* CONFIG_NF_CONNTRACK */

- static void __net_init __netfilter_net_init(struct nf_hook_entries **e, int max)
 -#ifdef CONFIG_NF_NAT_NEEDED
 -void (*nf_nat_decode_session_hook)(struct sk_buff *, struct flowi *);
 -EXPORT_SYMBOL(nf_nat_decode_session_hook);
 -#endif
 -
+ static void __net_init
+ __netfilter_net_init(struct nf_hook_entries __rcu **e, int max)
  {
  	int h;

I can also merge your net-next tree into nf-next, solve the conflict and
resend the pull request if you prefer so.
====================

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

4 files changed, 115 insertions, 162 deletions

diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 1ef37e2e2679..38ab97b0a2ec 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1783,6 +1783,8 @@ int ipt_register_table(struct net *net, const struct xt_table *table,
 
 	/* set res now, will see skbs right after nf_register_net_hooks */
 	WRITE_ONCE(*res, new_table);
+	if (!ops)
+		return 0;
 
 	ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks));
 	if (ret != 0) {
@@ -1800,7 +1802,8 @@ out_free:
 void ipt_unregister_table(struct net *net, struct xt_table *table,
 			  const struct nf_hook_ops *ops)
 {
-	nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
+	if (ops)
+		nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks));
 	__ipt_unregister_table(net, table);
 }
 
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 529d89ec31e8..a317445448bf 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -38,69 +38,58 @@ static unsigned int iptable_nat_do_chain(void *priv,
 	return ipt_do_table(skb, state, state->net->ipv4.nat_table);
 }
 
-static unsigned int iptable_nat_ipv4_fn(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_fn(priv, skb, state, iptable_nat_do_chain);
-}
-
-static unsigned int iptable_nat_ipv4_in(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_in(priv, skb, state, iptable_nat_do_chain);
-}
-
-static unsigned int iptable_nat_ipv4_out(void *priv,
-					 struct sk_buff *skb,
-					 const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_out(priv, skb, state, iptable_nat_do_chain);
-}
-
-static unsigned int iptable_nat_ipv4_local_fn(void *priv,
-					      struct sk_buff *skb,
-					      const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_local_fn(priv, skb, state, iptable_nat_do_chain);
-}
-
 static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
-	/* Before packet filtering, change destination */
 	{
-		.hook		= iptable_nat_ipv4_in,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_PRE_ROUTING,
 		.priority	= NF_IP_PRI_NAT_DST,
 	},
-	/* After packet filtering, change source */
 	{
-		.hook		= iptable_nat_ipv4_out,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_POST_ROUTING,
 		.priority	= NF_IP_PRI_NAT_SRC,
 	},
-	/* Before packet filtering, change destination */
 	{
-		.hook		= iptable_nat_ipv4_local_fn,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_LOCAL_OUT,
 		.priority	= NF_IP_PRI_NAT_DST,
 	},
-	/* After packet filtering, change source */
 	{
-		.hook		= iptable_nat_ipv4_fn,
+		.hook		= iptable_nat_do_chain,
 		.pf		= NFPROTO_IPV4,
-		.nat_hook	= true,
 		.hooknum	= NF_INET_LOCAL_IN,
 		.priority	= NF_IP_PRI_NAT_SRC,
 	},
 };
 
+static int ipt_nat_register_lookups(struct net *net)
+{
+	int i, ret;
+
+	for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++) {
+		ret = nf_nat_l3proto_ipv4_register_fn(net, &nf_nat_ipv4_ops[i]);
+		if (ret) {
+			while (i)
+				nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[--i]);
+
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static void ipt_nat_unregister_lookups(struct net *net)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(nf_nat_ipv4_ops); i++)
+		nf_nat_l3proto_ipv4_unregister_fn(net, &nf_nat_ipv4_ops[i]);
+}
+
 static int __net_init iptable_nat_table_init(struct net *net)
 {
 	struct ipt_replace *repl;
@@ -113,7 +102,18 @@ static int __net_init iptable_nat_table_init(struct net *net)
 	if (repl == NULL)
 		return -ENOMEM;
 	ret = ipt_register_table(net, &nf_nat_ipv4_table, repl,
-				 nf_nat_ipv4_ops, &net->ipv4.nat_table);
+				 NULL, &net->ipv4.nat_table);
+	if (ret < 0) {
+		kfree(repl);
+		return ret;
+	}
+
+	ret = ipt_nat_register_lookups(net);
+	if (ret < 0) {
+		ipt_unregister_table(net, net->ipv4.nat_table, NULL);
+		net->ipv4.nat_table = NULL;
+	}
+
 	kfree(repl);
 	return ret;
 }
@@ -122,7 +122,8 @@ static void __net_exit iptable_nat_net_exit(struct net *net)
 {
 	if (!net->ipv4.nat_table)
 		return;
-	ipt_unregister_table(net, net->ipv4.nat_table, nf_nat_ipv4_ops);
+	ipt_nat_unregister_lookups(net);
+	ipt_unregister_table(net, net->ipv4.nat_table, NULL);
 	net->ipv4.nat_table = NULL;
 }
 
diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
index 325e02956bf5..6115bf1ff6f0 100644
--- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c
@@ -241,33 +241,18 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb,
 }
 EXPORT_SYMBOL_GPL(nf_nat_icmp_reply_translation);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
-	       const struct nf_hook_state *state,
-	       unsigned int (*do_chain)(void *priv,
-					struct sk_buff *skb,
-					const struct nf_hook_state *state))
+	       const struct nf_hook_state *state)
 {
 	struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
-	struct nf_conn_nat *nat;
-	/* maniptype == SRC for postrouting. */
-	enum nf_nat_manip_type maniptype = HOOK2MANIP(state->hook);
 
 	ct = nf_ct_get(skb, &ctinfo);
-	/* Can't track?  It's not due to stress, or conntrack would
-	 * have dropped it.  Hence it's the user's responsibilty to
-	 * packet filter it out, or implement conntrack/NAT for that
-	 * protocol. 8) --RR
-	 */
 	if (!ct)
 		return NF_ACCEPT;
 
-	nat = nfct_nat(ct);
-
-	switch (ctinfo) {
-	case IP_CT_RELATED:
-	case IP_CT_RELATED_REPLY:
+	if (ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY) {
 		if (ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
 							   state->hook))
@@ -275,76 +260,30 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb,
 			else
 				return NF_ACCEPT;
 		}
-		/* Only ICMPs can be IP_CT_IS_REPLY: */
-		/* fall through */
-	case IP_CT_NEW:
-		/* Seen it before?  This can happen for loopback, retrans,
-		 * or local packets.
-		 */
-		if (!nf_nat_initialized(ct, maniptype)) {
-			unsigned int ret;
-
-			ret = do_chain(priv, skb, state);
-			if (ret != NF_ACCEPT)
-				return ret;
-
-			if (nf_nat_initialized(ct, HOOK2MANIP(state->hook)))
-				break;
-
-			ret = nf_nat_alloc_null_binding(ct, state->hook);
-			if (ret != NF_ACCEPT)
-				return ret;
-		} else {
-			pr_debug("Already setup manip %s for ct %p\n",
-				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
-				 ct);
-			if (nf_nat_oif_changed(state->hook, ctinfo, nat,
-					       state->out))
-				goto oif_changed;
-		}
-		break;
-
-	default:
-		/* ESTABLISHED */
-		WARN_ON(ctinfo != IP_CT_ESTABLISHED &&
-			ctinfo != IP_CT_ESTABLISHED_REPLY);
-		if (nf_nat_oif_changed(state->hook, ctinfo, nat, state->out))
-			goto oif_changed;
 	}
 
-	return nf_nat_packet(ct, ctinfo, state->hook, skb);
-
-oif_changed:
-	nf_ct_kill_acct(ct, ctinfo, skb);
-	return NF_DROP;
+	return nf_nat_inet_fn(priv, skb, state);
 }
 EXPORT_SYMBOL_GPL(nf_nat_ipv4_fn);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_in(void *priv, struct sk_buff *skb,
-	       const struct nf_hook_state *state,
-	       unsigned int (*do_chain)(void *priv,
-					 struct sk_buff *skb,
-					 const struct nf_hook_state *state))
+	       const struct nf_hook_state *state)
 {
 	unsigned int ret;
 	__be32 daddr = ip_hdr(skb)->daddr;
 
-	ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
+	ret = nf_nat_ipv4_fn(priv, skb, state);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    daddr != ip_hdr(skb)->daddr)
 		skb_dst_drop(skb);
 
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_nat_ipv4_in);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
-		const struct nf_hook_state *state,
-		unsigned int (*do_chain)(void *priv,
-					  struct sk_buff *skb,
-					  const struct nf_hook_state *state))
+		const struct nf_hook_state *state)
 {
 #ifdef CONFIG_XFRM
 	const struct nf_conn *ct;
@@ -353,7 +292,7 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
 #endif
 	unsigned int ret;
 
-	ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
+	ret = nf_nat_ipv4_fn(priv, skb, state);
 #ifdef CONFIG_XFRM
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    !(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
@@ -373,21 +312,17 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb,
 #endif
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_nat_ipv4_out);
 
-unsigned int
+static unsigned int
 nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
-		     const struct nf_hook_state *state,
-		     unsigned int (*do_chain)(void *priv,
-					       struct sk_buff *skb,
-					       const struct nf_hook_state *state))
+		     const struct nf_hook_state *state)
 {
 	const struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
 	unsigned int ret;
 	int err;
 
-	ret = nf_nat_ipv4_fn(priv, skb, state, do_chain);
+	ret = nf_nat_ipv4_fn(priv, skb, state);
 	if (ret != NF_DROP && ret != NF_STOLEN &&
 	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
 		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
@@ -411,7 +346,49 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb,
 	}
 	return ret;
 }
-EXPORT_SYMBOL_GPL(nf_nat_ipv4_local_fn);
+
+static const struct nf_hook_ops nf_nat_ipv4_ops[] = {
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv4_in,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv4_out,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP_PRI_NAT_SRC,
+	},
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv4_local_fn,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv4_fn,
+		.pf		= NFPROTO_IPV4,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP_PRI_NAT_SRC,
+	},
+};
+
+int nf_nat_l3proto_ipv4_register_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+	return nf_nat_register_fn(net, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+}
+EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_register_fn);
+
+void nf_nat_l3proto_ipv4_unregister_fn(struct net *net, const struct nf_hook_ops *ops)
+{
+	nf_nat_unregister_fn(net, ops, ARRAY_SIZE(nf_nat_ipv4_ops));
+}
+EXPORT_SYMBOL_GPL(nf_nat_l3proto_ipv4_unregister_fn);
 
 static int __init nf_nat_l3proto_ipv4_init(void)
 {
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
index 285baccfbdea..a3c4ea303e3e 100644
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
@@ -27,8 +27,8 @@
 #include <net/ip.h>
 
 static unsigned int nft_nat_do_chain(void *priv,
-				      struct sk_buff *skb,
-				      const struct nf_hook_state *state)
+				     struct sk_buff *skb,
+				     const struct nf_hook_state *state)
 {
 	struct nft_pktinfo pkt;
 
@@ -38,42 +38,14 @@ static unsigned int nft_nat_do_chain(void *priv,
 	return nft_do_chain(&pkt, priv);
 }
 
-static unsigned int nft_nat_ipv4_fn(void *priv,
-				    struct sk_buff *skb,
-				    const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_fn(priv, skb, state, nft_nat_do_chain);
-}
-
-static unsigned int nft_nat_ipv4_in(void *priv,
-				    struct sk_buff *skb,
-				    const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_in(priv, skb, state, nft_nat_do_chain);
-}
-
-static unsigned int nft_nat_ipv4_out(void *priv,
-				     struct sk_buff *skb,
-				     const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_out(priv, skb, state, nft_nat_do_chain);
-}
-
-static unsigned int nft_nat_ipv4_local_fn(void *priv,
-					  struct sk_buff *skb,
-					  const struct nf_hook_state *state)
-{
-	return nf_nat_ipv4_local_fn(priv, skb, state, nft_nat_do_chain);
-}
-
-static int nft_nat_ipv4_init(struct nft_ctx *ctx)
+static int nft_nat_ipv4_reg(struct net *net, const struct nf_hook_ops *ops)
 {
-	return nf_ct_netns_get(ctx->net, ctx->family);
+	return nf_nat_l3proto_ipv4_register_fn(net, ops);
 }
 
-static void nft_nat_ipv4_free(struct nft_ctx *ctx)
+static void nft_nat_ipv4_unreg(struct net *net, const struct nf_hook_ops *ops)
 {
-	nf_ct_netns_put(ctx->net, ctx->family);
+	nf_nat_l3proto_ipv4_unregister_fn(net, ops);
 }
 
 static const struct nft_chain_type nft_chain_nat_ipv4 = {
@@ -86,13 +58,13 @@ static const struct nft_chain_type nft_chain_nat_ipv4 = {
 			  (1 << NF_INET_LOCAL_OUT) |
 			  (1 << NF_INET_LOCAL_IN),
 	.hooks		= {
-		[NF_INET_PRE_ROUTING]	= nft_nat_ipv4_in,
-		[NF_INET_POST_ROUTING]	= nft_nat_ipv4_out,
-		[NF_INET_LOCAL_OUT]	= nft_nat_ipv4_local_fn,
-		[NF_INET_LOCAL_IN]	= nft_nat_ipv4_fn,
+		[NF_INET_PRE_ROUTING]	= nft_nat_do_chain,
+		[NF_INET_POST_ROUTING]	= nft_nat_do_chain,
+		[NF_INET_LOCAL_OUT]	= nft_nat_do_chain,
+		[NF_INET_LOCAL_IN]	= nft_nat_do_chain,
 	},
-	.init		= nft_nat_ipv4_init,
-	.free		= nft_nat_ipv4_free,
+	.ops_register = nft_nat_ipv4_reg,
+	.ops_unregister = nft_nat_ipv4_unreg,
 };
 
 static int __init nft_chain_nat_init(void)