[PATCH 20/29] netfilter: nft_tunnel: Add dst_cache support

[PATCH 20/29] netfilter: nft_tunnel: Add dst_cache support

[Pablo Neira Ayuso]

From: wenxu <wenxu@ucloud.cn>

The metadata_dst does not initialize the dst_cache field, this causes
problems to ip_md_tunnel_xmit() since it cannot use this cache, hence,
Triggering a route lookup for every packet.

Signed-off-by: wenxu <wenxu@ucloud.cn>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_tunnel.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
index ea28588c5eed..b113fcac94e1 100644
--- a/net/netfilter/nft_tunnel.c
+++ b/net/netfilter/nft_tunnel.c
@@ -406,6 +406,13 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
 		return -ENOMEM;
 
 	memcpy(&md->u.tun_info, &info, sizeof(info));
+#ifdef CONFIG_DST_CACHE
+	err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL);
+	if (err < 0) {
+		metadata_dst_free(md);
+		return err;
+	}
+#endif
 	ip_tunnel_info_opts_set(&md->u.tun_info, &priv->opts.u, priv->opts.len,
 				priv->opts.flags);
 	priv->md = md;
-- 
2.11.0

[PATCH 21/29] netfilter: convert the proto argument from u8 to u16

[Pablo Neira Ayuso]

From: Li RongQing <lirongqing@baidu.com>

The proto in struct xt_match and struct xt_target is u16, when
calling xt_check_target/match, their proto argument is u8,
and will cause truncation, it is harmless to ip packet, since
ip proto is u8

if a etable's match/target has proto that is u16, will cause
the check failure.

and convert be16 to short in bridge/netfilter/ebtables.c

Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h | 4 ++--
 net/bridge/netfilter/ebtables.c    | 6 +++---
 net/netfilter/x_tables.c           | 4 ++--
 3 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 9077b3ebea08..bf384b3eedb8 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -289,9 +289,9 @@ bool xt_find_jump_offset(const unsigned int *offsets,
 
 int xt_check_proc_name(const char *name, unsigned int size);
 
-int xt_check_match(struct xt_mtchk_param *, unsigned int size, u_int8_t proto,
+int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto,
 		   bool inv_proto);
-int xt_check_target(struct xt_tgchk_param *, unsigned int size, u_int8_t proto,
+int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto,
 		    bool inv_proto);
 
 int xt_match_to_user(const struct xt_entry_match *m,
diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c
index f77888ec93f1..eb15891f8b9f 100644
--- a/net/bridge/netfilter/ebtables.c
+++ b/net/bridge/netfilter/ebtables.c
@@ -381,7 +381,7 @@ ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par,
 	par->match     = match;
 	par->matchinfo = m->data;
 	ret = xt_check_match(par, m->match_size,
-	      e->ethproto, e->invflags & EBT_IPROTO);
+	      ntohs(e->ethproto), e->invflags & EBT_IPROTO);
 	if (ret < 0) {
 		module_put(match->me);
 		return ret;
@@ -418,7 +418,7 @@ ebt_check_watcher(struct ebt_entry_watcher *w, struct xt_tgchk_param *par,
 	par->target   = watcher;
 	par->targinfo = w->data;
 	ret = xt_check_target(par, w->watcher_size,
-	      e->ethproto, e->invflags & EBT_IPROTO);
+	      ntohs(e->ethproto), e->invflags & EBT_IPROTO);
 	if (ret < 0) {
 		module_put(watcher->me);
 		return ret;
@@ -744,7 +744,7 @@ ebt_check_entry(struct ebt_entry *e, struct net *net,
 	tgpar.target   = target;
 	tgpar.targinfo = t->data;
 	ret = xt_check_target(&tgpar, t->target_size,
-	      e->ethproto, e->invflags & EBT_IPROTO);
+	      ntohs(e->ethproto), e->invflags & EBT_IPROTO);
 	if (ret < 0) {
 		module_put(target->me);
 		goto cleanup_watchers;
diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c
index 13e1ac333fa4..e5e5c64df8d1 100644
--- a/net/netfilter/x_tables.c
+++ b/net/netfilter/x_tables.c
@@ -461,7 +461,7 @@ int xt_check_proc_name(const char *name, unsigned int size)
 EXPORT_SYMBOL(xt_check_proc_name);
 
 int xt_check_match(struct xt_mtchk_param *par,
-		   unsigned int size, u_int8_t proto, bool inv_proto)
+		   unsigned int size, u16 proto, bool inv_proto)
 {
 	int ret;
 
@@ -984,7 +984,7 @@ bool xt_find_jump_offset(const unsigned int *offsets,
 EXPORT_SYMBOL(xt_find_jump_offset);
 
 int xt_check_target(struct xt_tgchk_param *par,
-		    unsigned int size, u_int8_t proto, bool inv_proto)
+		    unsigned int size, u16 proto, bool inv_proto)
 {
 	int ret;
 
-- 
2.11.0

[PATCH 22/29] ipvs: get sctphdr by sctphoff in sctp_csum_check

[Pablo Neira Ayuso]

From: Xin Long <lucien.xin@gmail.com>

sctp_csum_check() is called by sctp_s/dnat_handler() where it calls
skb_make_writable() to ensure sctphdr to be linearized.

So there's no need to get sctphdr by calling skb_header_pointer()
in sctp_csum_check().

Signed-off-by: Xin Long <lucien.xin@gmail.com>
Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner@gmail.com>
Acked-by: Julian Anastasov <ja@ssi.bg>
Acked-by: Simon Horman <horms@verge.net.au>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/ipvs/ip_vs_proto_sctp.c | 7 ++-----
 1 file changed, 2 insertions(+), 5 deletions(-)

diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
index bc3d1625ecc8..b58ddb7dffd1 100644
--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
+++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
@@ -186,7 +186,7 @@ static int
 sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
 {
 	unsigned int sctphoff;
-	struct sctphdr *sh, _sctph;
+	struct sctphdr *sh;
 	__le32 cmp, val;
 
 #ifdef CONFIG_IP_VS_IPV6
@@ -196,10 +196,7 @@ sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp)
 #endif
 		sctphoff = ip_hdrlen(skb);
 
-	sh = skb_header_pointer(skb, sctphoff, sizeof(_sctph), &_sctph);
-	if (sh == NULL)
-		return 0;
-
+	sh = (struct sctphdr *)(skb->data + sctphoff);
 	cmp = sh->checksum;
 	val = sctp_compute_cksum(skb, sctphoff);
 
-- 
2.11.0

[PATCH 23/29] netfilter: bridge: Don't sabotage nf_hook calls for an l3mdev slave

[Pablo Neira Ayuso]

From: David Ahern <dsahern@gmail.com>

Followup to a173f066c7cf ("netfilter: bridge: Don't sabotage nf_hook
calls from an l3mdev"). Some packets (e.g., ndisc) do not have the skb
device flipped to the l3mdev (e.g., VRF) device. Update ip_sabotage_in
to not drop packets for slave devices too. Currently, neighbor
solicitation packets for 'dev -> bridge (addr) -> vrf' setups are getting
dropped. This patch enables IPv6 communications for bridges with an
address that are enslaved to a VRF.

Fixes: 73e20b761acf ("net: vrf: Add support for PREROUTING rules on vrf device")
Signed-off-by: David Ahern <dsahern@gmail.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/bridge/br_netfilter_hooks.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
index 40d058378b52..9d34de68571b 100644
--- a/net/bridge/br_netfilter_hooks.c
+++ b/net/bridge/br_netfilter_hooks.c
@@ -831,7 +831,8 @@ static unsigned int ip_sabotage_in(void *priv,
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 
 	if (nf_bridge && !nf_bridge->in_prerouting &&
-	    !netif_is_l3_master(skb->dev)) {
+	    !netif_is_l3_master(skb->dev) &&
+	    !netif_is_l3_slave(skb->dev)) {
 		state->okfn(state->net, state->sk, skb);
 		return NF_STOLEN;
 	}
-- 
2.11.0

[PATCH 24/29] netfilter: nf_tables: check the result of dereferencing base_chain->stats

[Pablo Neira Ayuso]

From: Li RongQing <lirongqing@baidu.com>

Check the result of dereferencing base_chain->stats, instead of result
of this_cpu_ptr with NULL.

base_chain->stats maybe be changed to NULL when a chain is updated and a
new NULL counter can be attached.

And we do not need to check returning of this_cpu_ptr since
base_chain->stats is from percpu allocator if it is non-NULL,
this_cpu_ptr returns a valid value.

And fix two sparse error by replacing rcu_access_pointer and
rcu_dereference with READ_ONCE under rcu_read_lock.

Thanks for Eric's help to finish this patch.

Fixes: 009240940e84c1 ("netfilter: nf_tables: don't assume chain stats are set when jumplabel is set")
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: Zhang Yu <zhangyu31@baidu.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_tables_core.c | 14 ++++++++------
 1 file changed, 8 insertions(+), 6 deletions(-)

diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c
index e56a94dff34e..d0f168c2670f 100644
--- a/net/netfilter/nf_tables_core.c
+++ b/net/netfilter/nf_tables_core.c
@@ -98,21 +98,23 @@ static noinline void nft_update_chain_stats(const struct nft_chain *chain,
 					    const struct nft_pktinfo *pkt)
 {
 	struct nft_base_chain *base_chain;
+	struct nft_stats __percpu *pstats;
 	struct nft_stats *stats;
 
 	base_chain = nft_base_chain(chain);
-	if (!rcu_access_pointer(base_chain->stats))
-		return;
 
-	local_bh_disable();
-	stats = this_cpu_ptr(rcu_dereference(base_chain->stats));
-	if (stats) {
+	rcu_read_lock();
+	pstats = READ_ONCE(base_chain->stats);
+	if (pstats) {
+		local_bh_disable();
+		stats = this_cpu_ptr(pstats);
 		u64_stats_update_begin(&stats->syncp);
 		stats->pkts++;
 		stats->bytes += pkt->skb->len;
 		u64_stats_update_end(&stats->syncp);
+		local_bh_enable();
 	}
-	local_bh_enable();
+	rcu_read_unlock();
 }
 
 struct nft_jumpstack {
-- 
2.11.0

[PATCH 25/29] netfilter: nf_conntrack: ensure that CONNTRACK_LOCKS is power of 2

[Pablo Neira Ayuso]

From: Li RongQing <lirongqing@baidu.com>

CONNTRACK_LOCKS is divisor when computer array index, if it is power of
2, compiler will optimize modulo operation as bitwise AND, or else
modulo will lower performance.

Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_conntrack_core.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index ff9313c579b4..82bfbeef46af 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -2480,6 +2480,7 @@ int nf_conntrack_init_net(struct net *net)
 	int cpu;
 
 	BUILD_BUG_ON(IP_CT_UNTRACKED == IP_CT_NUMBER);
+	BUILD_BUG_ON_NOT_POWER_OF_2(CONNTRACK_LOCKS);
 	atomic_set(&net->ct.count, 0);
 
 	net->ct.pcpu_lists = alloc_percpu(struct ct_pcpu);
-- 
2.11.0

Re: [PATCH 25/29] netfilter: nf_conntrack: ensure that CONNTRACK_LOCKS is power of 2

[Sergei Shtylyov]

Hello!

On 02.03.2019 21:37, Pablo Neira Ayuso wrote:

> From: Li RongQing <lirongqing@baidu.com>
> 
> CONNTRACK_LOCKS is divisor when computer array index, if it is power of

    Computing?

> 2, compiler will optimize modulo operation as bitwise AND, or else
> modulo will lower performance.
> 
> Suggested-by: Florian Westphal <fw@strlen.de>
> Signed-off-by: Li RongQing <lirongqing@baidu.com>
> Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
[...]

MBR, Sergei

[PATCH 26/29] netfilter: xt_IDLETIMER: fix sysfs callback function type

[Pablo Neira Ayuso]

From: Sami Tolvanen <samitolvanen@google.com>

Use struct device_attribute instead of struct idletimer_tg_attr, and
the correct callback function type to avoid indirect call mismatches
with Control Flow Integrity checking.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/xt_IDLETIMER.c | 14 ++++----------
 1 file changed, 4 insertions(+), 10 deletions(-)

diff --git a/net/netfilter/xt_IDLETIMER.c b/net/netfilter/xt_IDLETIMER.c
index eb4cbd244c3d..5f9b37e12801 100644
--- a/net/netfilter/xt_IDLETIMER.c
+++ b/net/netfilter/xt_IDLETIMER.c
@@ -41,19 +41,13 @@
 #include <linux/workqueue.h>
 #include <linux/sysfs.h>
 
-struct idletimer_tg_attr {
-	struct attribute attr;
-	ssize_t	(*show)(struct kobject *kobj,
-			struct attribute *attr, char *buf);
-};
-
 struct idletimer_tg {
 	struct list_head entry;
 	struct timer_list timer;
 	struct work_struct work;
 
 	struct kobject *kobj;
-	struct idletimer_tg_attr attr;
+	struct device_attribute attr;
 
 	unsigned int refcnt;
 };
@@ -76,15 +70,15 @@ struct idletimer_tg *__idletimer_tg_find_by_label(const char *label)
 	return NULL;
 }
 
-static ssize_t idletimer_tg_show(struct kobject *kobj, struct attribute *attr,
-				 char *buf)
+static ssize_t idletimer_tg_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
 {
 	struct idletimer_tg *timer;
 	unsigned long expires = 0;
 
 	mutex_lock(&list_mutex);
 
-	timer =	__idletimer_tg_find_by_label(attr->name);
+	timer =	__idletimer_tg_find_by_label(attr->attr.name);
 	if (timer)
 		expires = timer->timer.expires;
 
-- 
2.11.0

[PATCH 27/29] netfilter: nf_tables: nat: merge nft_redir protocol specific modules

[Pablo Neira Ayuso]

From: Florian Westphal <fw@strlen.de>

before:
 text	   data	    bss	    dec	    hex	filename
 990	    832	      0	   1822	    71e nft_redir.ko
 697	    896	      0	   1593	    639 nft_redir_ipv4.ko
 713	    896	      0	   1609	    649	nft_redir_ipv6.ko

after:
 text	   data	    bss	    dec	    hex	filename
 1910	    960	      0	   2870	    b36	nft_redir.ko

size is reduced, all helpers from nft_redir.ko can be made static.

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nft_redir.h   |  22 ------
 net/ipv4/netfilter/Kconfig          |   8 --
 net/ipv4/netfilter/Makefile         |   1 -
 net/ipv4/netfilter/nft_redir_ipv4.c |  82 -------------------
 net/ipv6/netfilter/Kconfig          |   8 --
 net/ipv6/netfilter/Makefile         |   1 -
 net/ipv6/netfilter/nft_redir_ipv6.c |  83 -------------------
 net/netfilter/Kconfig               |   1 +
 net/netfilter/nft_redir.c           | 154 +++++++++++++++++++++++++++++++++---
 9 files changed, 143 insertions(+), 217 deletions(-)
 delete mode 100644 include/net/netfilter/nft_redir.h
 delete mode 100644 net/ipv4/netfilter/nft_redir_ipv4.c
 delete mode 100644 net/ipv6/netfilter/nft_redir_ipv6.c

diff --git a/include/net/netfilter/nft_redir.h b/include/net/netfilter/nft_redir.h
deleted file mode 100644
index 4a970737c03c..000000000000
--- a/include/net/netfilter/nft_redir.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NFT_REDIR_H_
-#define _NFT_REDIR_H_
-
-struct nft_redir {
-	enum nft_registers	sreg_proto_min:8;
-	enum nft_registers	sreg_proto_max:8;
-	u16			flags;
-};
-
-extern const struct nla_policy nft_redir_policy[];
-
-int nft_redir_init(const struct nft_ctx *ctx,
-		   const struct nft_expr *expr,
-		   const struct nlattr * const tb[]);
-
-int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr);
-
-int nft_redir_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		       const struct nft_data **data);
-
-#endif /* _NFT_REDIR_H_ */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 8688461ed077..12cc3f7d7733 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -115,14 +115,6 @@ config NFT_MASQ_IPV4
 	  This is the expression that provides IPv4 masquerading support for
 	  nf_tables.
 
-config NFT_REDIR_IPV4
-	tristate "IPv4 redirect support for nf_tables"
-	depends on NF_TABLES_IPV4
-	depends on NFT_REDIR
-	select NF_NAT_REDIRECT
-	help
-	  This is the expression that provides IPv4 redirect support for
-	  nf_tables.
 endif # NF_TABLES
 
 config NF_NAT_SNMP_BASIC
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index b2cdf705fdf1..5558caf92578 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -29,7 +29,6 @@ obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NFT_FIB_IPV4) += nft_fib_ipv4.o
 obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
-obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
 obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
 
 # flow table support
diff --git a/net/ipv4/netfilter/nft_redir_ipv4.c b/net/ipv4/netfilter/nft_redir_ipv4.c
deleted file mode 100644
index 5120be1d3118..000000000000
--- a/net/ipv4/netfilter/nft_redir_ipv4.c
+++ /dev/null
@@ -1,82 +0,0 @@
-/*
- * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.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.
- */
-
-#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/nf_nat.h>
-#include <net/netfilter/nf_nat_redirect.h>
-#include <net/netfilter/nft_redir.h>
-
-static void nft_redir_ipv4_eval(const struct nft_expr *expr,
-				struct nft_regs *regs,
-				const struct nft_pktinfo *pkt)
-{
-	struct nft_redir *priv = nft_expr_priv(expr);
-	struct nf_nat_ipv4_multi_range_compat mr;
-
-	memset(&mr, 0, sizeof(mr));
-	if (priv->sreg_proto_min) {
-		mr.range[0].min.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_min]);
-		mr.range[0].max.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_max]);
-		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-	}
-
-	mr.range[0].flags |= priv->flags;
-
-	regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, nft_hook(pkt));
-}
-
-static void
-nft_redir_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
-{
-	nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
-}
-
-static struct nft_expr_type nft_redir_ipv4_type;
-static const struct nft_expr_ops nft_redir_ipv4_ops = {
-	.type		= &nft_redir_ipv4_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
-	.eval		= nft_redir_ipv4_eval,
-	.init		= nft_redir_init,
-	.destroy	= nft_redir_ipv4_destroy,
-	.dump		= nft_redir_dump,
-	.validate	= nft_redir_validate,
-};
-
-static struct nft_expr_type nft_redir_ipv4_type __read_mostly = {
-	.family		= NFPROTO_IPV4,
-	.name		= "redir",
-	.ops		= &nft_redir_ipv4_ops,
-	.policy		= nft_redir_policy,
-	.maxattr	= NFTA_REDIR_MAX,
-	.owner		= THIS_MODULE,
-};
-
-static int __init nft_redir_ipv4_module_init(void)
-{
-	return nft_register_expr(&nft_redir_ipv4_type);
-}
-
-static void __exit nft_redir_ipv4_module_exit(void)
-{
-	nft_unregister_expr(&nft_redir_ipv4_type);
-}
-
-module_init(nft_redir_ipv4_module_init);
-module_exit(nft_redir_ipv4_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
-MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "redir");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index a04a38166d8c..7e7cc411003a 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -49,14 +49,6 @@ config NFT_MASQ_IPV6
 	  This is the expression that provides IPv4 masquerading support for
 	  nf_tables.
 
-config NFT_REDIR_IPV6
-	tristate "IPv6 redirect support for nf_tables"
-	depends on NFT_REDIR
-	select NF_NAT_REDIRECT
-	help
-	  This is the expression that provides IPv4 redirect support for
-	  nf_tables.
-
 endif # NF_NAT
 
 config NFT_REJECT_IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index afb880427133..42a80d03245a 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -31,7 +31,6 @@ obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
 obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
-obj-$(CONFIG_NFT_REDIR_IPV6) += nft_redir_ipv6.o
 obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
 obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
 
diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c
deleted file mode 100644
index 74269865acc8..000000000000
--- a/net/ipv6/netfilter/nft_redir_ipv6.c
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.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.
- */
-
-#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/nf_nat.h>
-#include <net/netfilter/nft_redir.h>
-#include <net/netfilter/nf_nat_redirect.h>
-
-static void nft_redir_ipv6_eval(const struct nft_expr *expr,
-				struct nft_regs *regs,
-				const struct nft_pktinfo *pkt)
-{
-	struct nft_redir *priv = nft_expr_priv(expr);
-	struct nf_nat_range2 range;
-
-	memset(&range, 0, sizeof(range));
-	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_min]);
-		range.max_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_max]);
-		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
-	}
-
-	range.flags |= priv->flags;
-
-	regs->verdict.code =
-		nf_nat_redirect_ipv6(pkt->skb, &range, nft_hook(pkt));
-}
-
-static void
-nft_redir_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
-{
-	nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
-}
-
-static struct nft_expr_type nft_redir_ipv6_type;
-static const struct nft_expr_ops nft_redir_ipv6_ops = {
-	.type		= &nft_redir_ipv6_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
-	.eval		= nft_redir_ipv6_eval,
-	.init		= nft_redir_init,
-	.destroy	= nft_redir_ipv6_destroy,
-	.dump		= nft_redir_dump,
-	.validate	= nft_redir_validate,
-};
-
-static struct nft_expr_type nft_redir_ipv6_type __read_mostly = {
-	.family		= NFPROTO_IPV6,
-	.name		= "redir",
-	.ops		= &nft_redir_ipv6_ops,
-	.policy		= nft_redir_policy,
-	.maxattr	= NFTA_REDIR_MAX,
-	.owner		= THIS_MODULE,
-};
-
-static int __init nft_redir_ipv6_module_init(void)
-{
-	return nft_register_expr(&nft_redir_ipv6_type);
-}
-
-static void __exit nft_redir_ipv6_module_exit(void)
-{
-	nft_unregister_expr(&nft_redir_ipv6_type);
-}
-
-module_init(nft_redir_ipv6_module_init);
-module_exit(nft_redir_ipv6_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
-MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 5beb51d39dc2..73857f9fdb25 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -541,6 +541,7 @@ config NFT_REDIR
 	depends on NF_CONNTRACK
 	depends on NF_NAT
 	tristate "Netfilter nf_tables redirect support"
+	select NF_NAT_REDIRECT
 	help
 	  This options adds the "redirect" expression that you can use
 	  to perform NAT in the redirect flavour.
diff --git a/net/netfilter/nft_redir.c b/net/netfilter/nft_redir.c
index c64cbe78dee7..f8092926f704 100644
--- a/net/netfilter/nft_redir.c
+++ b/net/netfilter/nft_redir.c
@@ -13,19 +13,24 @@
 #include <linux/netfilter.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_redirect.h>
 #include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nft_redir.h>
 
-const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = {
+struct nft_redir {
+	enum nft_registers	sreg_proto_min:8;
+	enum nft_registers	sreg_proto_max:8;
+	u16			flags;
+};
+
+static const struct nla_policy nft_redir_policy[NFTA_REDIR_MAX + 1] = {
 	[NFTA_REDIR_REG_PROTO_MIN]	= { .type = NLA_U32 },
 	[NFTA_REDIR_REG_PROTO_MAX]	= { .type = NLA_U32 },
 	[NFTA_REDIR_FLAGS]		= { .type = NLA_U32 },
 };
-EXPORT_SYMBOL_GPL(nft_redir_policy);
 
-int nft_redir_validate(const struct nft_ctx *ctx,
-		       const struct nft_expr *expr,
-		       const struct nft_data **data)
+static int nft_redir_validate(const struct nft_ctx *ctx,
+			      const struct nft_expr *expr,
+			      const struct nft_data **data)
 {
 	int err;
 
@@ -37,11 +42,10 @@ int nft_redir_validate(const struct nft_ctx *ctx,
 					(1 << NF_INET_PRE_ROUTING) |
 					(1 << NF_INET_LOCAL_OUT));
 }
-EXPORT_SYMBOL_GPL(nft_redir_validate);
 
-int nft_redir_init(const struct nft_ctx *ctx,
-		   const struct nft_expr *expr,
-		   const struct nlattr * const tb[])
+static int nft_redir_init(const struct nft_ctx *ctx,
+			  const struct nft_expr *expr,
+			  const struct nlattr * const tb[])
 {
 	struct nft_redir *priv = nft_expr_priv(expr);
 	unsigned int plen;
@@ -77,7 +81,6 @@ int nft_redir_init(const struct nft_ctx *ctx,
 
 	return nf_ct_netns_get(ctx->net, ctx->family);
 }
-EXPORT_SYMBOL_GPL(nft_redir_init);
 
 int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
@@ -101,7 +104,134 @@ int nft_redir_dump(struct sk_buff *skb, const struct nft_expr *expr)
 nla_put_failure:
 	return -1;
 }
-EXPORT_SYMBOL_GPL(nft_redir_dump);
+
+static void nft_redir_ipv4_eval(const struct nft_expr *expr,
+				struct nft_regs *regs,
+				const struct nft_pktinfo *pkt)
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	struct nf_nat_ipv4_multi_range_compat mr;
+
+	memset(&mr, 0, sizeof(mr));
+	if (priv->sreg_proto_min) {
+		mr.range[0].min.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		mr.range[0].max.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
+		mr.range[0].flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	mr.range[0].flags |= priv->flags;
+
+	regs->verdict.code = nf_nat_redirect_ipv4(pkt->skb, &mr, nft_hook(pkt));
+}
+
+static void
+nft_redir_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+	nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
+}
+
+static struct nft_expr_type nft_redir_ipv4_type;
+static const struct nft_expr_ops nft_redir_ipv4_ops = {
+	.type		= &nft_redir_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+	.eval		= nft_redir_ipv4_eval,
+	.init		= nft_redir_init,
+	.destroy	= nft_redir_ipv4_destroy,
+	.dump		= nft_redir_dump,
+	.validate	= nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "redir",
+	.ops		= &nft_redir_ipv4_ops,
+	.policy		= nft_redir_policy,
+	.maxattr	= NFTA_REDIR_MAX,
+	.owner		= THIS_MODULE,
+};
+
+#ifdef CONFIG_NF_TABLES_IPV6
+static void nft_redir_ipv6_eval(const struct nft_expr *expr,
+				struct nft_regs *regs,
+				const struct nft_pktinfo *pkt)
+{
+	struct nft_redir *priv = nft_expr_priv(expr);
+	struct nf_nat_range2 range;
+
+	memset(&range, 0, sizeof(range));
+	if (priv->sreg_proto_min) {
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
+		range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED;
+	}
+
+	range.flags |= priv->flags;
+
+	regs->verdict.code =
+		nf_nat_redirect_ipv6(pkt->skb, &range, nft_hook(pkt));
+}
+
+static void
+nft_redir_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+	nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
+}
+
+static struct nft_expr_type nft_redir_ipv6_type;
+static const struct nft_expr_ops nft_redir_ipv6_ops = {
+	.type		= &nft_redir_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_redir)),
+	.eval		= nft_redir_ipv6_eval,
+	.init		= nft_redir_init,
+	.destroy	= nft_redir_ipv6_destroy,
+	.dump		= nft_redir_dump,
+	.validate	= nft_redir_validate,
+};
+
+static struct nft_expr_type nft_redir_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "redir",
+	.ops		= &nft_redir_ipv6_ops,
+	.policy		= nft_redir_policy,
+	.maxattr	= NFTA_REDIR_MAX,
+	.owner		= THIS_MODULE,
+};
+#endif
+
+static int __init nft_redir_module_init(void)
+{
+	int ret = nft_register_expr(&nft_redir_ipv4_type);
+
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_NF_TABLES_IPV6
+	ret = nft_register_expr(&nft_redir_ipv6_type);
+	if (ret) {
+		nft_unregister_expr(&nft_redir_ipv4_type);
+		return ret;
+	}
+#endif
+
+	return ret;
+}
+
+static void __exit nft_redir_module_exit(void)
+{
+	nft_unregister_expr(&nft_redir_ipv4_type);
+#ifdef CONFIG_NF_TABLES_IPV6
+	nft_unregister_expr(&nft_redir_ipv6_type);
+#endif
+}
+
+module_init(nft_redir_module_init);
+module_exit(nft_redir_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET4, "redir");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "redir");
-- 
2.11.0

[PATCH 28/29] netfilter: nf_tables: nat: merge nft_masq protocol specific modules

[Pablo Neira Ayuso]

From: Florian Westphal <fw@strlen.de>

The family specific masq modules are way too small to warrant
an extra module, just place all of them in nft_masq.

before:
  text	   data	    bss	    dec	    hex	filename
   1001	    832	      0	   1833	    729	nft_masq.ko
    766	    896	      0	   1662	    67e	nft_masq_ipv4.ko
    764	    896	      0	   1660	    67c	nft_masq_ipv6.ko

after:
   2010	    960	      0	   2970	    b9a	nft_masq.ko

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/net/netfilter/nft_masq.h   |  22 -----
 net/ipv4/netfilter/Kconfig         |   9 --
 net/ipv4/netfilter/Makefile        |   1 -
 net/ipv4/netfilter/nft_masq_ipv4.c |  90 -------------------
 net/ipv6/netfilter/Kconfig         |   9 --
 net/ipv6/netfilter/Makefile        |   1 -
 net/ipv6/netfilter/nft_masq_ipv6.c |  91 -------------------
 net/netfilter/Kconfig              |   1 +
 net/netfilter/nft_masq.c           | 180 ++++++++++++++++++++++++++++++++++---
 9 files changed, 168 insertions(+), 236 deletions(-)
 delete mode 100644 include/net/netfilter/nft_masq.h
 delete mode 100644 net/ipv4/netfilter/nft_masq_ipv4.c
 delete mode 100644 net/ipv6/netfilter/nft_masq_ipv6.c

diff --git a/include/net/netfilter/nft_masq.h b/include/net/netfilter/nft_masq.h
deleted file mode 100644
index e51ab3815797..000000000000
--- a/include/net/netfilter/nft_masq.h
+++ /dev/null
@@ -1,22 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NFT_MASQ_H_
-#define _NFT_MASQ_H_
-
-struct nft_masq {
-	u32			flags;
-	enum nft_registers      sreg_proto_min:8;
-	enum nft_registers      sreg_proto_max:8;
-};
-
-extern const struct nla_policy nft_masq_policy[];
-
-int nft_masq_init(const struct nft_ctx *ctx,
-		  const struct nft_expr *expr,
-		  const struct nlattr * const tb[]);
-
-int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr);
-
-int nft_masq_validate(const struct nft_ctx *ctx, const struct nft_expr *expr,
-		      const struct nft_data **data);
-
-#endif /* _NFT_MASQ_H_ */
diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 12cc3f7d7733..71c291a86245 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -106,15 +106,6 @@ config NFT_CHAIN_NAT_IPV4
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
 
-config NFT_MASQ_IPV4
-	tristate "IPv4 masquerading support for nf_tables"
-	depends on NF_TABLES_IPV4
-	depends on NFT_MASQ
-	select NF_NAT_MASQUERADE
-	help
-	  This is the expression that provides IPv4 masquerading support for
-	  nf_tables.
-
 endif # NF_TABLES
 
 config NF_NAT_SNMP_BASIC
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 5558caf92578..1ae24d71d3cc 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -28,7 +28,6 @@ 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_NFT_FIB_IPV4) += nft_fib_ipv4.o
-obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
 obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
 
 # flow table support
diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c
deleted file mode 100644
index 6847de1d1db8..000000000000
--- a/net/ipv4/netfilter/nft_masq_ipv4.c
+++ /dev/null
@@ -1,90 +0,0 @@
-/*
- * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.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.
- */
-
-#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_masq.h>
-#include <net/netfilter/ipv4/nf_nat_masquerade.h>
-
-static void nft_masq_ipv4_eval(const struct nft_expr *expr,
-			       struct nft_regs *regs,
-			       const struct nft_pktinfo *pkt)
-{
-	struct nft_masq *priv = nft_expr_priv(expr);
-	struct nf_nat_range2 range;
-
-	memset(&range, 0, sizeof(range));
-	range.flags = priv->flags;
-	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_min]);
-		range.max_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_max]);
-	}
-	regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
-						    &range, nft_out(pkt));
-}
-
-static void
-nft_masq_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
-{
-	nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
-}
-
-static struct nft_expr_type nft_masq_ipv4_type;
-static const struct nft_expr_ops nft_masq_ipv4_ops = {
-	.type		= &nft_masq_ipv4_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
-	.eval		= nft_masq_ipv4_eval,
-	.init		= nft_masq_init,
-	.destroy	= nft_masq_ipv4_destroy,
-	.dump		= nft_masq_dump,
-	.validate	= nft_masq_validate,
-};
-
-static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
-	.family		= NFPROTO_IPV4,
-	.name		= "masq",
-	.ops		= &nft_masq_ipv4_ops,
-	.policy		= nft_masq_policy,
-	.maxattr	= NFTA_MASQ_MAX,
-	.owner		= THIS_MODULE,
-};
-
-static int __init nft_masq_ipv4_module_init(void)
-{
-	int ret;
-
-	ret = nft_register_expr(&nft_masq_ipv4_type);
-	if (ret < 0)
-		return ret;
-
-	ret = nf_nat_masquerade_ipv4_register_notifier();
-	if (ret)
-		nft_unregister_expr(&nft_masq_ipv4_type);
-
-	return ret;
-}
-
-static void __exit nft_masq_ipv4_module_exit(void)
-{
-	nft_unregister_expr(&nft_masq_ipv4_type);
-	nf_nat_masquerade_ipv4_unregister_notifier();
-}
-
-module_init(nft_masq_ipv4_module_init);
-module_exit(nft_masq_ipv4_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org");
-MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index 7e7cc411003a..b95351a5cb83 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -40,15 +40,6 @@ config NFT_CHAIN_NAT_IPV6
 	  chain type is used to perform Network Address Translation (NAT)
 	  packet transformations such as the source, destination address and
 	  source and destination ports.
-
-config NFT_MASQ_IPV6
-	tristate "IPv6 masquerade support for nf_tables"
-	depends on NFT_MASQ
-	select NF_NAT_MASQUERADE
-	help
-	  This is the expression that provides IPv4 masquerading support for
-	  nf_tables.
-
 endif # NF_NAT
 
 config NFT_REJECT_IPV6
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 42a80d03245a..06c1829f8ffc 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -30,7 +30,6 @@ obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o
 obj-$(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
-obj-$(CONFIG_NFT_MASQ_IPV6) += nft_masq_ipv6.o
 obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
 obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
 
diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c
deleted file mode 100644
index e06c82e9dfcd..000000000000
--- a/net/ipv6/netfilter/nft_masq_ipv6.c
+++ /dev/null
@@ -1,91 +0,0 @@
-/*
- * Copyright (c) 2014 Arturo Borrero Gonzalez <arturo@debian.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.
- */
-
-#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/nf_nat.h>
-#include <net/netfilter/nft_masq.h>
-#include <net/netfilter/ipv6/nf_nat_masquerade.h>
-
-static void nft_masq_ipv6_eval(const struct nft_expr *expr,
-			       struct nft_regs *regs,
-			       const struct nft_pktinfo *pkt)
-{
-	struct nft_masq *priv = nft_expr_priv(expr);
-	struct nf_nat_range2 range;
-
-	memset(&range, 0, sizeof(range));
-	range.flags = priv->flags;
-	if (priv->sreg_proto_min) {
-		range.min_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_min]);
-		range.max_proto.all = (__force __be16)nft_reg_load16(
-			&regs->data[priv->sreg_proto_max]);
-	}
-	regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range,
-						    nft_out(pkt));
-}
-
-static void
-nft_masq_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
-{
-	nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
-}
-
-static struct nft_expr_type nft_masq_ipv6_type;
-static const struct nft_expr_ops nft_masq_ipv6_ops = {
-	.type		= &nft_masq_ipv6_type,
-	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
-	.eval		= nft_masq_ipv6_eval,
-	.init		= nft_masq_init,
-	.destroy	= nft_masq_ipv6_destroy,
-	.dump		= nft_masq_dump,
-	.validate	= nft_masq_validate,
-};
-
-static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
-	.family		= NFPROTO_IPV6,
-	.name		= "masq",
-	.ops		= &nft_masq_ipv6_ops,
-	.policy		= nft_masq_policy,
-	.maxattr	= NFTA_MASQ_MAX,
-	.owner		= THIS_MODULE,
-};
-
-static int __init nft_masq_ipv6_module_init(void)
-{
-	int ret;
-
-	ret = nft_register_expr(&nft_masq_ipv6_type);
-	if (ret < 0)
-		return ret;
-
-	ret = nf_nat_masquerade_ipv6_register_notifier();
-	if (ret)
-		nft_unregister_expr(&nft_masq_ipv6_type);
-
-	return ret;
-}
-
-static void __exit nft_masq_ipv6_module_exit(void)
-{
-	nft_unregister_expr(&nft_masq_ipv6_type);
-	nf_nat_masquerade_ipv6_unregister_notifier();
-}
-
-module_init(nft_masq_ipv6_module_init);
-module_exit(nft_masq_ipv6_module_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
-MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 73857f9fdb25..537f23a8ed52 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -532,6 +532,7 @@ config NFT_LIMIT
 config NFT_MASQ
 	depends on NF_CONNTRACK
 	depends on NF_NAT
+	select NF_NAT_MASQUERADE
 	tristate "Netfilter nf_tables masquerade support"
 	help
 	  This option adds the "masquerade" expression that you can use
diff --git a/net/netfilter/nft_masq.c b/net/netfilter/nft_masq.c
index 9d8655bc1bea..bee156eaa400 100644
--- a/net/netfilter/nft_masq.c
+++ b/net/netfilter/nft_masq.c
@@ -14,18 +14,24 @@
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
 #include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nft_masq.h>
+#include <net/netfilter/ipv4/nf_nat_masquerade.h>
+#include <net/netfilter/ipv6/nf_nat_masquerade.h>
 
-const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
+struct nft_masq {
+	u32			flags;
+	enum nft_registers      sreg_proto_min:8;
+	enum nft_registers      sreg_proto_max:8;
+};
+
+static const struct nla_policy nft_masq_policy[NFTA_MASQ_MAX + 1] = {
 	[NFTA_MASQ_FLAGS]		= { .type = NLA_U32 },
 	[NFTA_MASQ_REG_PROTO_MIN]	= { .type = NLA_U32 },
 	[NFTA_MASQ_REG_PROTO_MAX]	= { .type = NLA_U32 },
 };
-EXPORT_SYMBOL_GPL(nft_masq_policy);
 
-int nft_masq_validate(const struct nft_ctx *ctx,
-		      const struct nft_expr *expr,
-		      const struct nft_data **data)
+static int nft_masq_validate(const struct nft_ctx *ctx,
+			     const struct nft_expr *expr,
+			     const struct nft_data **data)
 {
 	int err;
 
@@ -36,11 +42,10 @@ int nft_masq_validate(const struct nft_ctx *ctx,
 	return nft_chain_validate_hooks(ctx->chain,
 				        (1 << NF_INET_POST_ROUTING));
 }
-EXPORT_SYMBOL_GPL(nft_masq_validate);
 
-int nft_masq_init(const struct nft_ctx *ctx,
-		  const struct nft_expr *expr,
-		  const struct nlattr * const tb[])
+static int nft_masq_init(const struct nft_ctx *ctx,
+			 const struct nft_expr *expr,
+			 const struct nlattr * const tb[])
 {
 	u32 plen = FIELD_SIZEOF(struct nf_nat_range, min_addr.all);
 	struct nft_masq *priv = nft_expr_priv(expr);
@@ -75,9 +80,8 @@ int nft_masq_init(const struct nft_ctx *ctx,
 
 	return nf_ct_netns_get(ctx->net, ctx->family);
 }
-EXPORT_SYMBOL_GPL(nft_masq_init);
 
-int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr)
+static int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr)
 {
 	const struct nft_masq *priv = nft_expr_priv(expr);
 
@@ -98,7 +102,157 @@ int nft_masq_dump(struct sk_buff *skb, const struct nft_expr *expr)
 nla_put_failure:
 	return -1;
 }
-EXPORT_SYMBOL_GPL(nft_masq_dump);
+
+static void nft_masq_ipv4_eval(const struct nft_expr *expr,
+			       struct nft_regs *regs,
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range2 range;
+
+	memset(&range, 0, sizeof(range));
+	range.flags = priv->flags;
+	if (priv->sreg_proto_min) {
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
+	}
+	regs->verdict.code = nf_nat_masquerade_ipv4(pkt->skb, nft_hook(pkt),
+						    &range, nft_out(pkt));
+}
+
+static void
+nft_masq_ipv4_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+	nf_ct_netns_put(ctx->net, NFPROTO_IPV4);
+}
+
+static struct nft_expr_type nft_masq_ipv4_type;
+static const struct nft_expr_ops nft_masq_ipv4_ops = {
+	.type		= &nft_masq_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv4_eval,
+	.init		= nft_masq_init,
+	.destroy	= nft_masq_ipv4_destroy,
+	.dump		= nft_masq_dump,
+	.validate	= nft_masq_validate,
+};
+
+static struct nft_expr_type nft_masq_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv4_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+#ifdef CONFIG_NF_TABLES_IPV6
+static void nft_masq_ipv6_eval(const struct nft_expr *expr,
+			       struct nft_regs *regs,
+			       const struct nft_pktinfo *pkt)
+{
+	struct nft_masq *priv = nft_expr_priv(expr);
+	struct nf_nat_range2 range;
+
+	memset(&range, 0, sizeof(range));
+	range.flags = priv->flags;
+	if (priv->sreg_proto_min) {
+		range.min_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_min]);
+		range.max_proto.all = (__force __be16)nft_reg_load16(
+			&regs->data[priv->sreg_proto_max]);
+	}
+	regs->verdict.code = nf_nat_masquerade_ipv6(pkt->skb, &range,
+						    nft_out(pkt));
+}
+
+static void
+nft_masq_ipv6_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr)
+{
+	nf_ct_netns_put(ctx->net, NFPROTO_IPV6);
+}
+
+static struct nft_expr_type nft_masq_ipv6_type;
+static const struct nft_expr_ops nft_masq_ipv6_ops = {
+	.type		= &nft_masq_ipv6_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_masq)),
+	.eval		= nft_masq_ipv6_eval,
+	.init		= nft_masq_init,
+	.destroy	= nft_masq_ipv6_destroy,
+	.dump		= nft_masq_dump,
+	.validate	= nft_masq_validate,
+};
+
+static struct nft_expr_type nft_masq_ipv6_type __read_mostly = {
+	.family		= NFPROTO_IPV6,
+	.name		= "masq",
+	.ops		= &nft_masq_ipv6_ops,
+	.policy		= nft_masq_policy,
+	.maxattr	= NFTA_MASQ_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_masq_module_init_ipv6(void)
+{
+	int ret = nft_register_expr(&nft_masq_ipv6_type);
+
+	if (ret)
+		return ret;
+
+	ret = nf_nat_masquerade_ipv6_register_notifier();
+	if (ret < 0)
+		nft_unregister_expr(&nft_masq_ipv6_type);
+
+	return ret;
+}
+
+static void nft_masq_module_exit_ipv6(void)
+{
+	nft_unregister_expr(&nft_masq_ipv6_type);
+	nf_nat_masquerade_ipv6_unregister_notifier();
+}
+#else
+static inline int nft_masq_module_init_ipv6(void) { return 0; }
+static inline void nft_masq_module_exit_ipv6(void) {}
+#endif
+
+static int __init nft_masq_module_init(void)
+{
+	int ret;
+
+	ret = nft_masq_module_init_ipv6();
+	if (ret < 0)
+		return ret;
+
+	ret = nft_register_expr(&nft_masq_ipv4_type);
+	if (ret < 0) {
+		nft_masq_module_exit_ipv6();
+		return ret;
+	}
+
+	ret = nf_nat_masquerade_ipv4_register_notifier();
+	if (ret < 0) {
+		nft_masq_module_exit_ipv6();
+		nft_unregister_expr(&nft_masq_ipv4_type);
+		return ret;
+	}
+
+	return ret;
+}
+
+static void __exit nft_masq_module_exit(void)
+{
+	nft_masq_module_exit_ipv6();
+	nft_unregister_expr(&nft_masq_ipv4_type);
+	nf_nat_masquerade_ipv4_unregister_notifier();
+}
+
+module_init(nft_masq_module_init);
+module_exit(nft_masq_module_exit);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Arturo Borrero Gonzalez <arturo@debian.org>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET6, "masq");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "masq");
-- 
2.11.0

[PATCH 29/29] netfilter: nf_tables: merge ipv4 and ipv6 nat chain types

[Pablo Neira Ayuso]

From: Florian Westphal <fw@strlen.de>

Merge the ipv4 and ipv6 nat chain type. This is the last
missing piece which allows to provide inet family support
for nat in a follow patch.

The kconfig knobs for ipv4/ipv6 nat chain are removed, the
nat chain type will be built unconditionally if NFT_NAT
expression is enabled.

Before:
   text	   data	    bss	    dec	    hex	filename
   1576     896       0    2472     9a8 nft_chain_nat_ipv4.ko
   1697     896       0    2593     a21 nft_chain_nat_ipv6.ko

After:
   text	   data	    bss	    dec	    hex	filename
   1832     896       0    2728     aa8 nft_chain_nat.ko

Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/ipv4/netfilter/Kconfig              |  13 ----
 net/ipv4/netfilter/Makefile             |   1 -
 net/ipv4/netfilter/nft_chain_nat_ipv4.c |  85 -------------------------
 net/ipv6/netfilter/Kconfig              |  11 ----
 net/ipv6/netfilter/Makefile             |   1 -
 net/ipv6/netfilter/nft_chain_nat_ipv6.c |  83 ------------------------
 net/netfilter/Kconfig                   |   1 +
 net/netfilter/Makefile                  |   2 +
 net/netfilter/nft_chain_nat.c           | 108 ++++++++++++++++++++++++++++++++
 9 files changed, 111 insertions(+), 194 deletions(-)
 delete mode 100644 net/ipv4/netfilter/nft_chain_nat_ipv4.c
 delete mode 100644 net/ipv6/netfilter/nft_chain_nat_ipv6.c
 create mode 100644 net/netfilter/nft_chain_nat.c

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 71c291a86245..c98391d49200 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -95,19 +95,6 @@ config NF_REJECT_IPV4
 	default m if NETFILTER_ADVANCED=n
 
 if NF_NAT
-
-if NF_TABLES
-config NFT_CHAIN_NAT_IPV4
-	depends on NF_TABLES_IPV4
-	tristate "IPv4 nf_tables nat chain support"
-	help
-	  This option enables the "nat" chain for IPv4 in nf_tables. This
-	  chain type is used to perform Network Address Translation (NAT)
-	  packet transformations such as the source, destination address and
-	  source and destination ports.
-
-endif # NF_TABLES
-
 config NF_NAT_SNMP_BASIC
 	tristate "Basic SNMP-ALG support"
 	depends on NF_CONNTRACK_SNMP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 1ae24d71d3cc..e241f5188ebe 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -25,7 +25,6 @@ $(obj)/nf_nat_snmp_basic_main.o: $(obj)/nf_nat_snmp_basic.asn1.h
 obj-$(CONFIG_NF_NAT_SNMP_BASIC) += nf_nat_snmp_basic.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_NFT_FIB_IPV4) += nft_fib_ipv4.o
 obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c
deleted file mode 100644
index 0d1ad5901aff..000000000000
--- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c
+++ /dev/null
@@ -1,85 +0,0 @@
-/*
- * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Pablo Neira Ayuso <pablo@netfilter.org>
- * Copyright (c) 2012 Intel Corporation
- *
- * 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/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv4.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv4.h>
-#include <net/ip.h>
-
-static unsigned int nft_nat_do_chain(void *priv,
-				     struct sk_buff *skb,
-				     const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv4(&pkt, skb);
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static int nft_nat_ipv4_reg(struct net *net, const struct nf_hook_ops *ops)
-{
-	return nf_nat_ipv4_register_fn(net, ops);
-}
-
-static void nft_nat_ipv4_unreg(struct net *net, const struct nf_hook_ops *ops)
-{
-	nf_nat_ipv4_unregister_fn(net, ops);
-}
-
-static const struct nft_chain_type nft_chain_nat_ipv4 = {
-	.name		= "nat",
-	.type		= NFT_CHAIN_T_NAT,
-	.family		= NFPROTO_IPV4,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
-			  (1 << NF_INET_POST_ROUTING) |
-			  (1 << NF_INET_LOCAL_OUT) |
-			  (1 << NF_INET_LOCAL_IN),
-	.hooks		= {
-		[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,
-	},
-	.ops_register = nft_nat_ipv4_reg,
-	.ops_unregister = nft_nat_ipv4_unreg,
-};
-
-static int __init nft_chain_nat_init(void)
-{
-	nft_register_chain_type(&nft_chain_nat_ipv4);
-
-	return 0;
-}
-
-static void __exit nft_chain_nat_exit(void)
-{
-	nft_unregister_chain_type(&nft_chain_nat_ipv4);
-}
-
-module_init(nft_chain_nat_init);
-module_exit(nft_chain_nat_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
diff --git a/net/ipv6/netfilter/Kconfig b/net/ipv6/netfilter/Kconfig
index b95351a5cb83..ddc99a1653aa 100644
--- a/net/ipv6/netfilter/Kconfig
+++ b/net/ipv6/netfilter/Kconfig
@@ -31,17 +31,6 @@ config NFT_CHAIN_ROUTE_IPV6
 	  fields such as the source, destination, flowlabel, hop-limit and
 	  the packet mark.
 
-if NF_NAT
-
-config NFT_CHAIN_NAT_IPV6
-	tristate "IPv6 nf_tables nat chain support"
-	help
-	  This option enables the "nat" chain for IPv6 in nf_tables. This
-	  chain type is used to perform Network Address Translation (NAT)
-	  packet transformations such as the source, destination address and
-	  source and destination ports.
-endif # NF_NAT
-
 config NFT_REJECT_IPV6
 	select NF_REJECT_IPV6
 	default NFT_REJECT
diff --git a/net/ipv6/netfilter/Makefile b/net/ipv6/netfilter/Makefile
index 06c1829f8ffc..3853c648ebaa 100644
--- a/net/ipv6/netfilter/Makefile
+++ b/net/ipv6/netfilter/Makefile
@@ -28,7 +28,6 @@ obj-$(CONFIG_NF_DUP_IPV6) += nf_dup_ipv6.o
 
 # nf_tables
 obj-$(CONFIG_NFT_CHAIN_ROUTE_IPV6) += nft_chain_route_ipv6.o
-obj-$(CONFIG_NFT_CHAIN_NAT_IPV6) += nft_chain_nat_ipv6.o
 obj-$(CONFIG_NFT_REJECT_IPV6) += nft_reject_ipv6.o
 obj-$(CONFIG_NFT_DUP_IPV6) += nft_dup_ipv6.o
 obj-$(CONFIG_NFT_FIB_IPV6) += nft_fib_ipv6.o
diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c
deleted file mode 100644
index e66bfd0b3d15..000000000000
--- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c
+++ /dev/null
@@ -1,83 +0,0 @@
-/*
- * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
- * Copyright (c) 2012 Intel Corporation
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms and conditions of the GNU General Public License,
- * version 2, as published by the Free Software Foundation.
- *
- */
-
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/list.h>
-#include <linux/skbuff.h>
-#include <linux/ip.h>
-#include <linux/netfilter.h>
-#include <linux/netfilter_ipv6.h>
-#include <linux/netfilter/nf_tables.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_nat.h>
-#include <net/netfilter/nf_tables.h>
-#include <net/netfilter/nf_tables_ipv6.h>
-#include <net/ipv6.h>
-
-static unsigned int nft_nat_do_chain(void *priv,
-				     struct sk_buff *skb,
-				     const struct nf_hook_state *state)
-{
-	struct nft_pktinfo pkt;
-
-	nft_set_pktinfo(&pkt, skb, state);
-	nft_set_pktinfo_ipv6(&pkt, skb);
-
-	return nft_do_chain(&pkt, priv);
-}
-
-static int nft_nat_ipv6_reg(struct net *net, const struct nf_hook_ops *ops)
-{
-	return nf_nat_ipv6_register_fn(net, ops);
-}
-
-static void nft_nat_ipv6_unreg(struct net *net, const struct nf_hook_ops *ops)
-{
-	nf_nat_ipv6_unregister_fn(net, ops);
-}
-
-static const struct nft_chain_type nft_chain_nat_ipv6 = {
-	.name		= "nat",
-	.type		= NFT_CHAIN_T_NAT,
-	.family		= NFPROTO_IPV6,
-	.owner		= THIS_MODULE,
-	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
-			  (1 << NF_INET_POST_ROUTING) |
-			  (1 << NF_INET_LOCAL_OUT) |
-			  (1 << NF_INET_LOCAL_IN),
-	.hooks		= {
-		[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,
-	},
-	.ops_register		= nft_nat_ipv6_reg,
-	.ops_unregister		= nft_nat_ipv6_unreg,
-};
-
-static int __init nft_chain_nat_ipv6_init(void)
-{
-	nft_register_chain_type(&nft_chain_nat_ipv6);
-
-	return 0;
-}
-
-static void __exit nft_chain_nat_ipv6_exit(void)
-{
-	nft_unregister_chain_type(&nft_chain_nat_ipv6);
-}
-
-module_init(nft_chain_nat_ipv6_init);
-module_exit(nft_chain_nat_ipv6_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>");
-MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat");
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 537f23a8ed52..d43ffb09939b 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -550,6 +550,7 @@ config NFT_REDIR
 config NFT_NAT
 	depends on NF_CONNTRACK
 	select NF_NAT
+	depends on NF_TABLES_IPV4 || NF_TABLES_IPV6
 	tristate "Netfilter nf_tables nat module"
 	help
 	  This option adds the "nat" expression that you can use to perform
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index c7910706f8dd..4894a85cdd0b 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -110,6 +110,8 @@ obj-$(CONFIG_NFT_OSF)		+= nft_osf.o
 obj-$(CONFIG_NFT_TPROXY)	+= nft_tproxy.o
 obj-$(CONFIG_NFT_XFRM)		+= nft_xfrm.o
 
+obj-$(CONFIG_NFT_NAT)		+= nft_chain_nat.o
+
 # nf_tables netdev
 obj-$(CONFIG_NFT_DUP_NETDEV)	+= nft_dup_netdev.o
 obj-$(CONFIG_NFT_FWD_NETDEV)	+= nft_fwd_netdev.o
diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c
new file mode 100644
index 000000000000..ee4852088d50
--- /dev/null
+++ b/net/netfilter/nft_chain_nat.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/module.h>
+#include <linux/netfilter/nf_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+
+static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb,
+				     const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	nft_set_pktinfo(&pkt, skb, state);
+
+	switch (state->pf) {
+#ifdef CONFIG_NF_TABLES_IPV4
+	case NFPROTO_IPV4:
+		nft_set_pktinfo_ipv4(&pkt, skb);
+		break;
+#endif
+#ifdef CONFIG_NF_TABLES_IPV6
+	case NFPROTO_IPV6:
+		nft_set_pktinfo_ipv6(&pkt, skb);
+		break;
+#endif
+	default:
+		break;
+	}
+
+	return nft_do_chain(&pkt, priv);
+}
+
+#ifdef CONFIG_NF_TABLES_IPV4
+static const struct nft_chain_type nft_chain_nat_ipv4 = {
+	.name		= "nat",
+	.type		= NFT_CHAIN_T_NAT,
+	.family		= NFPROTO_IPV4,
+	.owner		= THIS_MODULE,
+	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.hooks		= {
+		[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,
+	},
+	.ops_register = nf_nat_ipv4_register_fn,
+	.ops_unregister = nf_nat_ipv4_unregister_fn,
+};
+#endif
+
+#ifdef CONFIG_NF_TABLES_IPV6
+static const struct nft_chain_type nft_chain_nat_ipv6 = {
+	.name		= "nat",
+	.type		= NFT_CHAIN_T_NAT,
+	.family		= NFPROTO_IPV6,
+	.owner		= THIS_MODULE,
+	.hook_mask	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.hooks		= {
+		[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,
+	},
+	.ops_register		= nf_nat_ipv6_register_fn,
+	.ops_unregister		= nf_nat_ipv6_unregister_fn,
+};
+#endif
+
+static int __init nft_chain_nat_init(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV6
+	nft_register_chain_type(&nft_chain_nat_ipv6);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV4
+	nft_register_chain_type(&nft_chain_nat_ipv4);
+#endif
+
+	return 0;
+}
+
+static void __exit nft_chain_nat_exit(void)
+{
+#ifdef CONFIG_NF_TABLES_IPV4
+	nft_unregister_chain_type(&nft_chain_nat_ipv4);
+#endif
+#ifdef CONFIG_NF_TABLES_IPV6
+	nft_unregister_chain_type(&nft_chain_nat_ipv6);
+#endif
+}
+
+module_init(nft_chain_nat_init);
+module_exit(nft_chain_nat_exit);
+
+MODULE_LICENSE("GPL");
+#ifdef CONFIG_NF_TABLES_IPV4
+MODULE_ALIAS_NFT_CHAIN(AF_INET, "nat");
+#endif
+#ifdef CONFIG_NF_TABLES_IPV6
+MODULE_ALIAS_NFT_CHAIN(AF_INET6, "nat");
+#endif
-- 
2.11.0

Re: [PATCH 29/29] netfilter: nf_tables: merge ipv4 and ipv6 nat chain types

[Reindl Harald]

Am 02.03.19 um 19:37 schrieb Pablo Neira Ayuso:
> From: Florian Westphal <fw@strlen.de>
> 
> Merge the ipv4 and ipv6 nat chain type. This is the last
> missing piece which allows to provide inet family support
> for nat in a follow patch.
> 
> The kconfig knobs for ipv4/ipv6 nat chain are removed, the
> nat chain type will be built unconditionally if NFT_NAT
> expression is enabled.
> 
> Before:
>    text	   data	    bss	    dec	    hex	filename
>    1576     896       0    2472     9a8 nft_chain_nat_ipv4.ko
>    1697     896       0    2593     a21 nft_chain_nat_ipv6.ko
> 
> After:
>    text	   data	    bss	    dec	    hex	filename
>    1832     896       0    2728     aa8 nft_chain_nat.ko

there are similar *probably* low hanging fruits with 5.7

"ip6_udp_tunnel" and "nf_defrag_ipv6" are unconditionally loaded even on
pure ipv4 setups and the two ipv6 sepcific rehect modules only when ipv6
is in use

3,5K udp_tunnel.ko.xz
2,5K ip6_udp_tunnel.ko.xz

2,4K nf_defrag_ipv4.ko.xz
6,7K nf_defrag_ipv6.ko.xz

2.3K ipt_REJECT.ko.xz
2.3K ip6t_REJECT.ko.xz

3.1K nf_reject_ipv4.ko.xz
4.1K nf_reject_ipv6.ko.x