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

Pablo Neira Ayuso says:

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

This is second pull request includes the conflict resolution patch that
resulted from the updates that we got for the conntrack template through
kmalloc. No changes with regards to the previously sent 15 patches.

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

1) Rework the existing nf_tables counter expression to make it per-cpu.

2) Prepare and factor out common packet duplication code from the TEE target so
   it can be reused from the new dup expression.

3) Add the new dup expression for the nf_tables IPv4 and IPv6 families.

4) Convert the nf_tables limit expression to use a token-based approach with
   64-bits precision.

5) Enhance the nf_tables limit expression to support limiting at packet byte.
   This comes after several preparation patches.

6) Add a burst parameter to indicate the amount of packets or bytes that can
   exceed the limiting.

7) Add netns support to nfacct, from Andreas Schultz.

8) Pass the nf_conn_zone structure instead of the zone ID in nf_tables to allow
   accessing more zone specific information, from Daniel Borkmann.

9) Allow to define zone per-direction to support netns containers with
   overlapping network addressing, also from Daniel.

10) Extend the CT target to allow setting the zone based on the skb->mark as a
   way to support simple mappings from iptables, also from Daniel.

11) Make the nf_tables payload expression aware of the fact that VLAN offload
    may have removed a vlan header, from Florian Westphal.
====================

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

7 files changed, 259 insertions, 9 deletions

diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig
index 2199a5db25e6..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
@@ -67,6 +73,12 @@ config NF_TABLES_ARP
 
 endif # NF_TABLES
 
+config NF_DUP_IPV4
+	tristate "Netfilter IPv4 packet duplication to alternate destination"
+	help
+	  This option enables the nf_dup_ipv4 core, which duplicates an IPv4
+	  packet to be rerouted to another destination.
+
 config NF_LOG_ARP
 	tristate "ARP packet logging"
 	default m if NETFILTER_ADVANCED=n
diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile
index 7fe6c703528f..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 
@@ -70,3 +71,5 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o
 
 # just filtering instance of ARP tables for now
 obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o
+
+obj-$(CONFIG_NF_DUP_IPV4) += nf_dup_ipv4.o
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index 30ad9554b5e9..8a2caaf3940b 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -280,7 +280,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len)
 		return -EINVAL;
 	}
 
-	h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
+	h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple);
 	if (h) {
 		struct sockaddr_in sin;
 		struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
index 80d5554b9a88..cdde3ec496e9 100644
--- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
+++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c
@@ -134,9 +134,11 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb,
 	struct nf_conntrack_tuple innertuple, origtuple;
 	const struct nf_conntrack_l4proto *innerproto;
 	const struct nf_conntrack_tuple_hash *h;
-	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
+	const struct nf_conntrack_zone *zone;
+	struct nf_conntrack_zone tmp;
 
 	NF_CT_ASSERT(skb->nfct == NULL);
+	zone = nf_ct_zone_tmpl(tmpl, skb, &tmp);
 
 	/* Are they talking about one of our connections? */
 	if (!nf_ct_get_tuplepr(skb,
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index b69e82bda215..9306ec4fab41 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -43,19 +43,22 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
 static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
 					      struct sk_buff *skb)
 {
-	u16 zone = NF_CT_DEFAULT_ZONE;
-
+	u16 zone_id = NF_CT_DEFAULT_ZONE_ID;
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-	if (skb->nfct)
-		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+	if (skb->nfct) {
+		enum ip_conntrack_info ctinfo;
+		const struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+
+		zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo));
+	}
 #endif
 	if (nf_bridge_in_prerouting(skb))
-		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
+		return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id;
 
 	if (hooknum == NF_INET_PRE_ROUTING)
-		return IP_DEFRAG_CONNTRACK_IN + zone;
+		return IP_DEFRAG_CONNTRACK_IN + zone_id;
 	else
-		return IP_DEFRAG_CONNTRACK_OUT + zone;
+		return IP_DEFRAG_CONNTRACK_OUT + zone_id;
 }
 
 static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops,
diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c
new file mode 100644
index 000000000000..b5bb37564b0e
--- /dev/null
+++ b/net/ipv4/netfilter/nf_dup_ipv4.c
@@ -0,0 +1,120 @@
+/*
+ * (C) 2007 by Sebastian Claßen <sebastian.classen@freenet.ag>
+ * (C) 2007-2010 by Jan Engelhardt <jengelh@medozas.de>
+ *
+ * Extracted from xt_TEE.c
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 or later, as
+ * published by the Free Software Foundation.
+ */
+#include <linux/ip.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/route.h>
+#include <linux/skbuff.h>
+#include <net/checksum.h>
+#include <net/icmp.h>
+#include <net/ip.h>
+#include <net/route.h>
+#include <net/netfilter/ipv4/nf_dup_ipv4.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
+static struct net *pick_net(struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_NS
+	const struct dst_entry *dst;
+
+	if (skb->dev != NULL)
+		return dev_net(skb->dev);
+	dst = skb_dst(skb);
+	if (dst != NULL && dst->dev != NULL)
+		return dev_net(dst->dev);
+#endif
+	return &init_net;
+}
+
+static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw,
+			      int oif)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	struct net *net = pick_net(skb);
+	struct rtable *rt;
+	struct flowi4 fl4;
+
+	memset(&fl4, 0, sizeof(fl4));
+	if (oif != -1)
+		fl4.flowi4_oif = oif;
+
+	fl4.daddr = gw->s_addr;
+	fl4.flowi4_tos = RT_TOS(iph->tos);
+	fl4.flowi4_scope = RT_SCOPE_UNIVERSE;
+	fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH;
+	rt = ip_route_output_key(net, &fl4);
+	if (IS_ERR(rt))
+		return false;
+
+	skb_dst_drop(skb);
+	skb_dst_set(skb, &rt->dst);
+	skb->dev      = rt->dst.dev;
+	skb->protocol = htons(ETH_P_IP);
+
+	return true;
+}
+
+void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum,
+		 const struct in_addr *gw, int oif)
+{
+	struct iphdr *iph;
+
+	if (this_cpu_read(nf_skb_duplicated))
+		return;
+	/*
+	 * Copy the skb, and route the copy. Will later return %XT_CONTINUE for
+	 * the original skb, which should continue on its way as if nothing has
+	 * happened. The copy should be independently delivered to the gateway.
+	 */
+	skb = pskb_copy(skb, GFP_ATOMIC);
+	if (skb == NULL)
+		return;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	/* Avoid counting cloned packets towards the original connection. */
+	nf_conntrack_put(skb->nfct);
+	skb->nfct     = &nf_ct_untracked_get()->ct_general;
+	skb->nfctinfo = IP_CT_NEW;
+	nf_conntrack_get(skb->nfct);
+#endif
+	/*
+	 * If we are in PREROUTING/INPUT, the checksum must be recalculated
+	 * since the length could have changed as a result of defragmentation.
+	 *
+	 * We also decrease the TTL to mitigate potential loops between two
+	 * hosts.
+	 *
+	 * Set %IP_DF so that the original source is notified of a potentially
+	 * decreased MTU on the clone route. IPv6 does this too.
+	 */
+	iph = ip_hdr(skb);
+	iph->frag_off |= htons(IP_DF);
+	if (hooknum == NF_INET_PRE_ROUTING ||
+	    hooknum == NF_INET_LOCAL_IN)
+		--iph->ttl;
+	ip_send_check(iph);
+
+	if (nf_dup_ipv4_route(skb, gw, oif)) {
+		__this_cpu_write(nf_skb_duplicated, true);
+		ip_local_out(skb);
+		__this_cpu_write(nf_skb_duplicated, false);
+	} else {
+		kfree_skb(skb);
+	}
+}
+EXPORT_SYMBOL_GPL(nf_dup_ipv4);
+
+MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>");
+MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>");
+MODULE_DESCRIPTION("nf_dup_ipv4: Duplicate IPv4 packet");
+MODULE_LICENSE("GPL");
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");