netfilter: nf_tables: add compatibility layer for x_tables

This patch adds the x_tables compatibility layer. This allows you
to use existing x_tables matches and targets from nf_tables.

This compatibility later allows us to use existing matches/targets
for features that are still missing in nf_tables. We can progressively
replace them with native nf_tables extensions. It also provides the
userspace compatibility software that allows you to express the
rule-set using the iptables syntax but using the nf_tables kernel
components.

In order to get this compatibility layer working, I've done the
following things:

* add NFNL_SUBSYS_NFT_COMPAT: this new nfnetlink subsystem is used
to query the x_tables match/target revision, so we don't need to
use the native x_table getsockopt interface.

* emulate xt structures: this required extending the struct nft_pktinfo
to include the fragment offset, which is already obtained from
ip[6]_tables and that is used by some matches/targets.

* add support for default policy to base chains, required to emulate
  x_tables.

* add NFTA_CHAIN_USE attribute to obtain the number of references to
  chains, required by x_tables emulation.

* add chain packet/byte counters using per-cpu.

* support 32-64 bits compat.

For historical reasons, this patch includes the following patches
that were posted in the netfilter-devel mailing list.

From Pablo Neira Ayuso:
* nf_tables: add default policy to base chains
* netfilter: nf_tables: add NFTA_CHAIN_USE attribute
* nf_tables: nft_compat: private data of target and matches in contiguous area
* nf_tables: validate hooks for compat match/target
* nf_tables: nft_compat: release cached matches/targets
* nf_tables: x_tables support as a compile time option
* nf_tables: fix alias for xtables over nftables module
* nf_tables: add packet and byte counters per chain
* nf_tables: fix per-chain counter stats if no counters are passed
* nf_tables: don't bump chain stats
* nf_tables: add protocol and flags for xtables over nf_tables
* nf_tables: add ip[6]t_entry emulation
* nf_tables: move specific layer 3 compat code to nf_tables_ipv[4|6]
* nf_tables: support 32bits-64bits x_tables compat
* nf_tables: fix compilation if CONFIG_COMPAT is disabled

From Patrick McHardy:
* nf_tables: move policy to struct nft_base_chain
* nf_tables: send notifications for base chain policy changes

From Alexander Primak:
* nf_tables: remove the duplicate NF_INET_LOCAL_OUT

From Nicolas Dichtel:
* nf_tables: fix compilation when nf-netlink is a module

Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

2 files changed, 34 insertions, 7 deletions

diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c
index 3631d6238e6f..42f905a808a3 100644
--- a/net/ipv6/netfilter/nf_tables_ipv6.c
+++ b/net/ipv6/netfilter/nf_tables_ipv6.c
@@ -14,6 +14,7 @@
 #include <linux/ipv6.h>
 #include <linux/netfilter_ipv6.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv6.h>
 
 static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
 				    struct sk_buff *skb,
@@ -21,14 +22,18 @@ static unsigned int nft_ipv6_output(const struct nf_hook_ops *ops,
 				    const struct net_device *out,
 				    int (*okfn)(struct sk_buff *))
 {
+	struct nft_pktinfo pkt;
+
 	if (unlikely(skb->len < sizeof(struct ipv6hdr))) {
 		if (net_ratelimit())
 			pr_info("nf_tables_ipv6: ignoring short SOCK_RAW "
 				"packet\n");
 		return NF_ACCEPT;
 	}
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+		return NF_DROP;
 
-	return nft_do_chain(ops, skb, in, out, okfn);
+	return nft_do_chain_pktinfo(&pkt, ops);
 }
 
 static struct nft_af_info nft_af_ipv6 __read_mostly = {
@@ -40,6 +45,22 @@ static struct nft_af_info nft_af_ipv6 __read_mostly = {
 	},
 };
 
+static unsigned int
+nft_do_chain_ipv6(const struct nf_hook_ops *ops,
+		  struct sk_buff *skb,
+		  const struct net_device *in,
+		  const struct net_device *out,
+		  int (*okfn)(struct sk_buff *))
+{
+	struct nft_pktinfo pkt;
+
+	/* malformed packet, drop it */
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+		return NF_DROP;
+
+	return nft_do_chain_pktinfo(&pkt, ops);
+}
+
 static struct nf_chain_type filter_ipv6 = {
 	.family		= NFPROTO_IPV6,
 	.name		= "filter",
@@ -50,11 +71,11 @@ static struct nf_chain_type filter_ipv6 = {
 			  (1 << NF_INET_PRE_ROUTING) |
 			  (1 << NF_INET_POST_ROUTING),
 	.fn		= {
-		[NF_INET_LOCAL_IN]	= nft_do_chain,
-		[NF_INET_LOCAL_OUT]	= nft_do_chain,
-		[NF_INET_FORWARD]	= nft_do_chain,
-		[NF_INET_PRE_ROUTING]	= nft_do_chain,
-		[NF_INET_POST_ROUTING]	= nft_do_chain,
+		[NF_INET_LOCAL_IN]	= nft_do_chain_ipv6,
+		[NF_INET_LOCAL_OUT]	= nft_ipv6_output,
+		[NF_INET_FORWARD]	= nft_do_chain_ipv6,
+		[NF_INET_PRE_ROUTING]	= nft_do_chain_ipv6,
+		[NF_INET_POST_ROUTING]	= nft_do_chain_ipv6,
 	},
 };
 
diff --git a/net/ipv6/netfilter/nft_chain_route_ipv6.c b/net/ipv6/netfilter/nft_chain_route_ipv6.c
index 4cdc992fa067..3fe40f0456ad 100644
--- a/net/ipv6/netfilter/nft_chain_route_ipv6.c
+++ b/net/ipv6/netfilter/nft_chain_route_ipv6.c
@@ -19,6 +19,7 @@
 #include <linux/netfilter/nfnetlink.h>
 #include <linux/netfilter/nf_tables.h>
 #include <net/netfilter/nf_tables.h>
+#include <net/netfilter/nf_tables_ipv6.h>
 #include <net/route.h>
 
 static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
@@ -28,10 +29,15 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 					int (*okfn)(struct sk_buff *))
 {
 	unsigned int ret;
+	struct nft_pktinfo pkt;
 	struct in6_addr saddr, daddr;
 	u_int8_t hop_limit;
 	u32 mark, flowlabel;
 
+	/* malformed packet, drop it */
+	if (nft_set_pktinfo_ipv6(&pkt, ops, skb, in, out) < 0)
+		return NF_DROP;
+
 	/* save source/dest address, mark, hoplimit, flowlabel, priority */
 	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
 	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
@@ -41,7 +47,7 @@ static unsigned int nf_route_table_hook(const struct nf_hook_ops *ops,
 	/* flowlabel and prio (includes version, which shouldn't change either */
 	flowlabel = *((u32 *)ipv6_hdr(skb));
 
-	ret = nft_do_chain(ops, skb, in, out, okfn);
+	ret = nft_do_chain_pktinfo(&pkt, ops);
 	if (ret != NF_DROP && ret != NF_QUEUE &&
 	    (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) ||
 	     memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) ||