netfilter: nf_tables: add nft_dup expression

This new expression uses the nf_dup engine to clone packets to a given gateway.
Unlike xt_TEE, we use an index to indicate output interface which should be
fine at this stage.

Moreover, change to the preemtion-safe this_cpu_read(nf_skb_duplicated) from
nf_dup_ipv{4,6} to silence a lockdep splat.

Based on the original tee expression from Arturo Borrero Gonzalez, although
this patch has diverted quite a bit from this initial effort due to the
change to support maps.

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

4 files changed, 118 insertions, 1 deletions

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 0142ea259d7d..690d27d3f2f9 100644
--- a/net/ipv4/netfilter/Kconfig
+++ b/net/ipv4/netfilter/Kconfig
@@ -58,6 +58,12 @@ config NFT_REJECT_IPV4
 	default NFT_REJECT
 	tristate
 
+config NFT_DUP_IPV4
+	tristate "IPv4 nf_tables packet duplication support"
+	select NF_DUP_IPV4
+	help
+	  This module enables IPv4 packet duplication support for nf_tables.
+
 endif # NF_TABLES_IPV4
 
 config NF_TABLES_ARP
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 9136ffc2d474..87b073da14c9 100644
--- a/net/ipv4/netfilter/Makefile
+++ b/net/ipv4/netfilter/Makefile
@@ -41,6 +41,7 @@ obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o
 obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o
 obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o
 obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o
+obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o
 obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o
 
 # generic IP tables 
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
index eff85ab3f47d..b5bb37564b0e 100644
--- a/net/ipv4/netfilter/nf_dup_ipv4.c
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -69,7 +69,7 @@ void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum,
 {
 	struct iphdr *iph;
 
-	if (__this_cpu_read(nf_skb_duplicated))
+	if (this_cpu_read(nf_skb_duplicated))
 		return;
 	/*
 	 * Copy the skb, and route the copy. Will later return %XT_CONTINUE for
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
new file mode 100644
index 000000000000..25419fbddcb6
--- /dev/null
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -0,0 +1,110 @@
+/*
+ * 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/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/ipv4/nf_dup_ipv4.h>
+
+struct nft_dup_ipv4 {
+	enum nft_registers	sreg_addr:8;
+	enum nft_registers	sreg_dev:8;
+};
+
+static void nft_dup_ipv4_eval(const struct nft_expr *expr,
+			      struct nft_regs *regs,
+			      const struct nft_pktinfo *pkt)
+{
+	struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
+	struct in_addr gw = {
+		.s_addr = regs->data[priv->sreg_addr],
+	};
+	int oif = regs->data[priv->sreg_dev];
+
+	nf_dup_ipv4(pkt->skb, pkt->ops->hooknum, &gw, oif);
+}
+
+static int nft_dup_ipv4_init(const struct nft_ctx *ctx,
+			     const struct nft_expr *expr,
+			     const struct nlattr * const tb[])
+{
+	struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
+	int err;
+
+	if (tb[NFTA_DUP_SREG_ADDR] == NULL)
+		return -EINVAL;
+
+	priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]);
+	err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr));
+	if (err < 0)
+		return err;
+
+	if (tb[NFTA_DUP_SREG_DEV] != NULL) {
+		priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]);
+		return nft_validate_register_load(priv->sreg_dev, sizeof(int));
+	}
+	return 0;
+}
+
+static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
+{
+	struct nft_dup_ipv4 *priv = nft_expr_priv(expr);
+
+	if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) ||
+	    nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev))
+		goto nla_put_failure;
+
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static struct nft_expr_type nft_dup_ipv4_type;
+static const struct nft_expr_ops nft_dup_ipv4_ops = {
+	.type		= &nft_dup_ipv4_type,
+	.size		= NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv4)),
+	.eval		= nft_dup_ipv4_eval,
+	.init		= nft_dup_ipv4_init,
+	.dump		= nft_dup_ipv4_dump,
+};
+
+static const struct nla_policy nft_dup_ipv4_policy[NFTA_DUP_MAX + 1] = {
+	[NFTA_DUP_SREG_ADDR]	= { .type = NLA_U32 },
+	[NFTA_DUP_SREG_DEV]	= { .type = NLA_U32 },
+};
+
+static struct nft_expr_type nft_dup_ipv4_type __read_mostly = {
+	.family		= NFPROTO_IPV4,
+	.name		= "dup",
+	.ops		= &nft_dup_ipv4_ops,
+	.policy		= nft_dup_ipv4_policy,
+	.maxattr	= NFTA_DUP_MAX,
+	.owner		= THIS_MODULE,
+};
+
+static int __init nft_dup_ipv4_module_init(void)
+{
+	return nft_register_expr(&nft_dup_ipv4_type);
+}
+
+static void __exit nft_dup_ipv4_module_exit(void)
+{
+	nft_unregister_expr(&nft_dup_ipv4_type);
+}
+
+module_init(nft_dup_ipv4_module_init);
+module_exit(nft_dup_ipv4_module_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>");
+MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup");