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 net-next, they are:

1) default CONFIG_NETFILTER_INGRESS to y for easier compile-testing of all
   options.

2) Allow to bind a table to net_device. This introduces the internal
   NFT_AF_NEEDS_DEV flag to perform a mandatory check for this binding.
   This is required by the next patch.

3) Add the 'netdev' table family, this new table allows you to create ingress
   filter basechains. This provides access to the existing nf_tables features
   from ingress.

4) Kill unused argument from compat_find_calc_{match,target} in ip_tables
   and ip6_tables, from Florian Westphal.
====================

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

4 files changed, 231 insertions, 5 deletions

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 1c78d7fb1da7..fbc8d15c7fda 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -3,6 +3,7 @@ menu "Core Netfilter Configuration"
 
 config NETFILTER_INGRESS
 	bool "Netfilter ingress support"
+	default y
 	select NET_INGRESS
 	help
 	  This allows you to classify packets from ingress using the Netfilter
@@ -455,6 +456,11 @@ config NF_TABLES_INET
 	help
 	  This option enables support for a mixed IPv4/IPv6 "inet" table.
 
+config NF_TABLES_NETDEV
+	tristate "Netfilter nf_tables netdev tables support"
+	help
+	  This option enables support for the "netdev" table.
+
 config NFT_EXTHDR
 	tristate "Netfilter nf_tables IPv6 exthdr module"
 	help
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index a87d8b8ec730..70d026d46fe7 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -75,6 +75,7 @@ nf_tables-objs += nft_bitwise.o nft_byteorder.o nft_payload.o
 
 obj-$(CONFIG_NF_TABLES)		+= nf_tables.o
 obj-$(CONFIG_NF_TABLES_INET)	+= nf_tables_inet.o
+obj-$(CONFIG_NF_TABLES_NETDEV)	+= nf_tables_netdev.o
 obj-$(CONFIG_NFT_COMPAT)	+= nft_compat.o
 obj-$(CONFIG_NFT_EXTHDR)	+= nft_exthdr.o
 obj-$(CONFIG_NFT_META)		+= nft_meta.o
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 34ded09317e7..4528f122bcd2 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -399,6 +399,8 @@ static const struct nla_policy nft_table_policy[NFTA_TABLE_MAX + 1] = {
 	[NFTA_TABLE_NAME]	= { .type = NLA_STRING,
 				    .len = NFT_TABLE_MAXNAMELEN - 1 },
 	[NFTA_TABLE_FLAGS]	= { .type = NLA_U32 },
+	[NFTA_TABLE_DEV]	= { .type = NLA_STRING,
+				    .len = IFNAMSIZ - 1 },
 };
 
 static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
@@ -423,6 +425,10 @@ static int nf_tables_fill_table_info(struct sk_buff *skb, struct net *net,
 	    nla_put_be32(skb, NFTA_TABLE_USE, htonl(table->use)))
 		goto nla_put_failure;
 
+	if (table->dev &&
+	    nla_put_string(skb, NFTA_TABLE_DEV, table->dev->name))
+		goto nla_put_failure;
+
 	nlmsg_end(skb, nlh);
 	return 0;
 
@@ -608,6 +614,11 @@ static int nf_tables_updtable(struct nft_ctx *ctx)
 	if (flags == ctx->table->flags)
 		return 0;
 
+	if ((ctx->afi->flags & NFT_AF_NEEDS_DEV) &&
+	    ctx->nla[NFTA_TABLE_DEV] &&
+	    nla_strcmp(ctx->nla[NFTA_TABLE_DEV], ctx->table->dev->name))
+		return -EOPNOTSUPP;
+
 	trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE,
 				sizeof(struct nft_trans_table));
 	if (trans == NULL)
@@ -645,6 +656,7 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 	struct nft_table *table;
 	struct net *net = sock_net(skb->sk);
 	int family = nfmsg->nfgen_family;
+	struct net_device *dev = NULL;
 	u32 flags = 0;
 	struct nft_ctx ctx;
 	int err;
@@ -679,30 +691,50 @@ static int nf_tables_newtable(struct sock *nlsk, struct sk_buff *skb,
 			return -EINVAL;
 	}
 
+	if (afi->flags & NFT_AF_NEEDS_DEV) {
+		char ifname[IFNAMSIZ];
+
+		if (!nla[NFTA_TABLE_DEV])
+			return -EOPNOTSUPP;
+
+		nla_strlcpy(ifname, nla[NFTA_TABLE_DEV], IFNAMSIZ);
+		dev = dev_get_by_name(net, ifname);
+		if (!dev)
+			return -ENOENT;
+	} else if (nla[NFTA_TABLE_DEV]) {
+		return -EOPNOTSUPP;
+	}
+
+	err = -EAFNOSUPPORT;
 	if (!try_module_get(afi->owner))
-		return -EAFNOSUPPORT;
+		goto err1;
 
 	err = -ENOMEM;
 	table = kzalloc(sizeof(*table), GFP_KERNEL);
 	if (table == NULL)
-		goto err1;
+		goto err2;
 
 	nla_strlcpy(table->name, name, NFT_TABLE_MAXNAMELEN);
 	INIT_LIST_HEAD(&table->chains);
 	INIT_LIST_HEAD(&table->sets);
 	table->flags = flags;
+	table->dev   = dev;
 
 	nft_ctx_init(&ctx, skb, nlh, afi, table, NULL, nla);
 	err = nft_trans_table_add(&ctx, NFT_MSG_NEWTABLE);
 	if (err < 0)
-		goto err2;
+		goto err3;
 
 	list_add_tail_rcu(&table->list, &afi->tables);
 	return 0;
-err2:
+err3:
 	kfree(table);
-err1:
+err2:
 	module_put(afi->owner);
+err1:
+	if (dev != NULL)
+		dev_put(dev);
+
 	return err;
 }
 
@@ -806,6 +838,9 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx)
 {
 	BUG_ON(ctx->table->use > 0);
 
+	if (ctx->table->dev)
+		dev_put(ctx->table->dev);
+
 	kfree(ctx->table);
 	module_put(ctx->afi->owner);
 }
@@ -1361,6 +1396,7 @@ static int nf_tables_newchain(struct sock *nlsk, struct sk_buff *skb,
 			ops->priority	= priority;
 			ops->priv	= chain;
 			ops->hook	= afi->hooks[ops->hooknum];
+			ops->dev	= table->dev;
 			if (hookfn)
 				ops->hook = hookfn;
 			if (afi->hook_ops_init)
diff --git a/net/netfilter/nf_tables_netdev.c b/net/netfilter/nf_tables_netdev.c
new file mode 100644
index 000000000000..04cb17057f46
--- /dev/null
+++ b/net/netfilter/nf_tables_netdev.c
@@ -0,0 +1,183 @@
+/*
+ * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.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/init.h>
+#include <linux/module.h>
+#include <net/netfilter/nf_tables.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/netfilter/nf_tables_ipv4.h>
+#include <net/netfilter/nf_tables_ipv6.h>
+
+static inline void
+nft_netdev_set_pktinfo_ipv4(struct nft_pktinfo *pkt,
+			    const struct nf_hook_ops *ops, struct sk_buff *skb,
+			    const struct nf_hook_state *state)
+{
+	struct iphdr *iph, _iph;
+	u32 len, thoff;
+
+	nft_set_pktinfo(pkt, ops, skb, state);
+
+	iph = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*iph),
+				 &_iph);
+	if (!iph)
+		return;
+
+	iph = ip_hdr(skb);
+	if (iph->ihl < 5 || iph->version != 4)
+		return;
+
+	len = ntohs(iph->tot_len);
+	thoff = iph->ihl * 4;
+	if (skb->len < len)
+		return;
+	else if (len < thoff)
+		return;
+
+	pkt->tprot = iph->protocol;
+	pkt->xt.thoff = thoff;
+	pkt->xt.fragoff = ntohs(iph->frag_off) & IP_OFFSET;
+}
+
+static inline void
+__nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
+			      const struct nf_hook_ops *ops,
+			      struct sk_buff *skb,
+			      const struct nf_hook_state *state)
+{
+#if IS_ENABLED(CONFIG_IPV6)
+	struct ipv6hdr *ip6h, _ip6h;
+	unsigned int thoff = 0;
+	unsigned short frag_off;
+	int protohdr;
+	u32 pkt_len;
+
+	ip6h = skb_header_pointer(skb, skb_network_offset(skb), sizeof(*ip6h),
+				  &_ip6h);
+	if (!ip6h)
+		return;
+
+	if (ip6h->version != 6)
+		return;
+
+	pkt_len = ntohs(ip6h->payload_len);
+	if (pkt_len + sizeof(*ip6h) > skb->len)
+		return;
+
+	protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, NULL);
+	if (protohdr < 0)
+                return;
+
+	pkt->tprot = protohdr;
+	pkt->xt.thoff = thoff;
+	pkt->xt.fragoff = frag_off;
+#endif
+}
+
+static inline void nft_netdev_set_pktinfo_ipv6(struct nft_pktinfo *pkt,
+					       const struct nf_hook_ops *ops,
+					       struct sk_buff *skb,
+					       const struct nf_hook_state *state)
+{
+	nft_set_pktinfo(pkt, ops, skb, state);
+	__nft_netdev_set_pktinfo_ipv6(pkt, ops, skb, state);
+}
+
+static unsigned int
+nft_do_chain_netdev(const struct nf_hook_ops *ops, struct sk_buff *skb,
+		    const struct nf_hook_state *state)
+{
+	struct nft_pktinfo pkt;
+
+	switch (eth_hdr(skb)->h_proto) {
+	case htons(ETH_P_IP):
+		nft_netdev_set_pktinfo_ipv4(&pkt, ops, skb, state);
+		break;
+	case htons(ETH_P_IPV6):
+		nft_netdev_set_pktinfo_ipv6(&pkt, ops, skb, state);
+		break;
+	default:
+		nft_set_pktinfo(&pkt, ops, skb, state);
+		break;
+	}
+
+	return nft_do_chain(&pkt, ops);
+}
+
+static struct nft_af_info nft_af_netdev __read_mostly = {
+	.family		= NFPROTO_NETDEV,
+	.nhooks		= NF_NETDEV_NUMHOOKS,
+	.owner		= THIS_MODULE,
+	.flags		= NFT_AF_NEEDS_DEV,
+	.nops		= 1,
+	.hooks		= {
+		[NF_NETDEV_INGRESS]	= nft_do_chain_netdev,
+	},
+};
+
+static int nf_tables_netdev_init_net(struct net *net)
+{
+	net->nft.netdev = kmalloc(sizeof(struct nft_af_info), GFP_KERNEL);
+	if (net->nft.netdev == NULL)
+		return -ENOMEM;
+
+	memcpy(net->nft.netdev, &nft_af_netdev, sizeof(nft_af_netdev));
+
+	if (nft_register_afinfo(net, net->nft.netdev) < 0)
+		goto err;
+
+	return 0;
+err:
+	kfree(net->nft.netdev);
+	return -ENOMEM;
+}
+
+static void nf_tables_netdev_exit_net(struct net *net)
+{
+	nft_unregister_afinfo(net->nft.netdev);
+	kfree(net->nft.netdev);
+}
+
+static struct pernet_operations nf_tables_netdev_net_ops = {
+	.init	= nf_tables_netdev_init_net,
+	.exit	= nf_tables_netdev_exit_net,
+};
+
+static const struct nf_chain_type nft_filter_chain_netdev = {
+	.name		= "filter",
+	.type		= NFT_CHAIN_T_DEFAULT,
+	.family		= NFPROTO_NETDEV,
+	.owner		= THIS_MODULE,
+	.hook_mask	= (1 << NF_NETDEV_INGRESS),
+};
+
+static int __init nf_tables_netdev_init(void)
+{
+	int ret;
+
+	nft_register_chain_type(&nft_filter_chain_netdev);
+	ret = register_pernet_subsys(&nf_tables_netdev_net_ops);
+	if (ret < 0)
+		nft_unregister_chain_type(&nft_filter_chain_netdev);
+
+	return ret;
+}
+
+static void __exit nf_tables_netdev_exit(void)
+{
+	unregister_pernet_subsys(&nf_tables_netdev_net_ops);
+	nft_unregister_chain_type(&nft_filter_chain_netdev);
+}
+
+module_init(nf_tables_netdev_init);
+module_exit(nf_tables_netdev_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NFT_FAMILY(5); /* NFPROTO_NETDEV */