Initial commit; kernel source import

net/ipv6/netfilter/Kconfig

@@ -0,0 +1,225 @@
+#
+# IP netfilter configuration
+#
+
+menu "IPv6: Netfilter Configuration"
+	depends on INET && IPV6 && NETFILTER
+
+config NF_DEFRAG_IPV6
+	tristate
+	default n
+
+config NF_CONNTRACK_IPV6
+	tristate "IPv6 connection tracking support"
+	depends on INET && IPV6 && NF_CONNTRACK
+	default m if NETFILTER_ADVANCED=n
+	select NF_DEFRAG_IPV6
+	---help---
+	  Connection tracking keeps a record of what packets have passed
+	  through your machine, in order to figure out how they are related
+	  into connections.
+
+	  This is IPv6 support on Layer 3 independent connection tracking.
+	  Layer 3 independent connection tracking is experimental scheme
+	  which generalize ip_conntrack to support other layer 3 protocols.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_IPTABLES
+	tristate "IP6 tables support (required for filtering)"
+	depends on INET && IPV6
+	select NETFILTER_XTABLES
+	default m if NETFILTER_ADVANCED=n
+	help
+	  ip6tables is a general, extensible packet identification framework.
+	  Currently only the packet filtering and packet mangling subsystem
+	  for IPv6 use this, but connection tracking is going to follow.
+	  Say 'Y' or 'M' here if you want to use either of those.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+if IP6_NF_IPTABLES
+
+# The simple matches.
+config IP6_NF_MATCH_AH
+	tristate '"ah" match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  This module allows one to match AH packets.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_EUI64
+	tristate '"eui64" address check'
+	depends on NETFILTER_ADVANCED
+	help
+	  This module performs checking on the IPv6 source address
+	  Compares the last 64 bits with the EUI64 (delivered
+	  from the MAC address) address
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_FRAG
+	tristate '"frag" Fragmentation header match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  frag matching allows you to match packets based on the fragmentation
+	  header of the packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_OPTS
+	tristate '"hbh" hop-by-hop and "dst" opts header match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  This allows one to match packets based on the hop-by-hop
+	  and destination options headers of a packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_HL
+	tristate '"hl" hoplimit match support'
+	depends on NETFILTER_ADVANCED
+	select NETFILTER_XT_MATCH_HL
+	---help---
+	This is a backwards-compat option for the user's convenience
+	(e.g. when running oldconfig). It selects
+	CONFIG_NETFILTER_XT_MATCH_HL.
+
+config IP6_NF_MATCH_IPV6HEADER
+	tristate '"ipv6header" IPv6 Extension Headers Match'
+	default m if NETFILTER_ADVANCED=n
+	help
+	  This module allows one to match packets based upon
+	  the ipv6 extension headers.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_MH
+	tristate '"mh" match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  This module allows one to match MH packets.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MATCH_RPFILTER
+	tristate '"rpfilter" reverse path filter match support'
+	depends on NETFILTER_ADVANCED && (IP6_NF_MANGLE || IP6_NF_RAW)
+	---help---
+	  This option allows you to match packets whose replies would
+	  go out via the interface the packet came in.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+	  The module will be called ip6t_rpfilter.
+
+config IP6_NF_MATCH_RT
+	tristate '"rt" Routing header match support'
+	depends on NETFILTER_ADVANCED
+	help
+	  rt matching allows you to match packets based on the routing
+	  header of the packet.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+# The targets
+config IP6_NF_TARGET_HL
+	tristate '"HL" hoplimit target support'
+	depends on NETFILTER_ADVANCED && IP6_NF_MANGLE
+	select NETFILTER_XT_TARGET_HL
+	---help---
+	This is a backwards-compatible option for the user's convenience
+	(e.g. when running oldconfig). It selects
+	CONFIG_NETFILTER_XT_TARGET_HL.
+
+config IP6_NF_FILTER
+	tristate "Packet filtering"
+	default m if NETFILTER_ADVANCED=n
+	help
+	  Packet filtering defines a table `filter', which has a series of
+	  rules for simple packet filtering at local input, forwarding and
+	  local output.  See the man page for iptables(8).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_TARGET_REJECT
+	tristate "REJECT target support"
+	depends on IP6_NF_FILTER
+	default m if NETFILTER_ADVANCED=n
+	help
+	  The REJECT target allows a filtering rule to specify that an ICMPv6
+	  error should be issued in response to an incoming packet, rather
+	  than silently being dropped.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_MANGLE
+	tristate "Packet mangling"
+	default m if NETFILTER_ADVANCED=n
+	help
+	  This option adds a `mangle' table to iptables: see the man page for
+	  iptables(8).  This table is used for various packet alterations
+	  which can effect how the packet is routed.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_RAW
+	tristate  'raw table support (required for TRACE)'
+	help
+	  This option adds a `raw' table to ip6tables. This table is the very
+	  first in the netfilter framework and hooks in at the PREROUTING
+	  and OUTPUT chains.
+
+	  If you want to compile it as a module, say M here and read
+	  <file:Documentation/kbuild/modules.txt>.  If unsure, say `N'.
+
+# security table for MAC policy
+config IP6_NF_SECURITY
+       tristate "Security table"
+       depends on SECURITY
+       depends on NETFILTER_ADVANCED
+       help
+         This option adds a `security' table to iptables, for use
+         with Mandatory Access Control (MAC) policy.
+
+         If unsure, say N.
+
+config NF_NAT_IPV6
+	tristate "IPv6 NAT"
+	depends on NF_CONNTRACK_IPV6
+	depends on NETFILTER_ADVANCED
+	select NF_NAT
+	help
+	  The IPv6 NAT option allows masquerading, port forwarding and other
+	  forms of full Network Address Port Translation. It is controlled by
+	  the `nat' table in ip6tables, see the man page for ip6tables(8).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+if NF_NAT_IPV6
+
+config IP6_NF_TARGET_MASQUERADE
+	tristate "MASQUERADE target support"
+	help
+	  Masquerading is a special case of NAT: all outgoing connections are
+	  changed to seem to come from a particular interface's address, and
+	  if the interface goes down, those connections are lost.  This is
+	  only useful for dialup accounts with dynamic IP address (ie. your IP
+	  address will be different on next dialup).
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+config IP6_NF_TARGET_NPT
+	tristate "NPT (Network Prefix translation) target support"
+	help
+	  This option adds the `SNPT' and `DNPT' target, which perform
+	  stateless IPv6-to-IPv6 Network Prefix Translation per RFC 6296.
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
+endif # NF_NAT_IPV6
+
+endif # IP6_NF_IPTABLES
+
+endmenu
+

net/ipv6/netfilter/Makefile

@@ -0,0 +1,39 @@
+#
+# Makefile for the netfilter modules on top of IPv6.
+#
+
+# Link order matters here.
+obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o
+obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o
+obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o
+obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
+obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o
+obj-$(CONFIG_NF_NAT_IPV6) += ip6table_nat.o
+
+# objects for l3 independent conntrack
+nf_conntrack_ipv6-y  :=  nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o
+
+# l3 independent conntrack
+obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o nf_defrag_ipv6.o
+
+nf_nat_ipv6-y		:= nf_nat_l3proto_ipv6.o nf_nat_proto_icmpv6.o
+obj-$(CONFIG_NF_NAT_IPV6) += nf_nat_ipv6.o
+
+# defrag
+nf_defrag_ipv6-y := nf_defrag_ipv6_hooks.o nf_conntrack_reasm.o
+obj-$(CONFIG_NF_DEFRAG_IPV6) += nf_defrag_ipv6.o
+
+# matches
+obj-$(CONFIG_IP6_NF_MATCH_AH) += ip6t_ah.o
+obj-$(CONFIG_IP6_NF_MATCH_EUI64) += ip6t_eui64.o
+obj-$(CONFIG_IP6_NF_MATCH_FRAG) += ip6t_frag.o
+obj-$(CONFIG_IP6_NF_MATCH_IPV6HEADER) += ip6t_ipv6header.o
+obj-$(CONFIG_IP6_NF_MATCH_MH) += ip6t_mh.o
+obj-$(CONFIG_IP6_NF_MATCH_OPTS) += ip6t_hbh.o
+obj-$(CONFIG_IP6_NF_MATCH_RPFILTER) += ip6t_rpfilter.o
+obj-$(CONFIG_IP6_NF_MATCH_RT) += ip6t_rt.o
+
+# targets
+obj-$(CONFIG_IP6_NF_TARGET_MASQUERADE) += ip6t_MASQUERADE.o
+obj-$(CONFIG_IP6_NF_TARGET_NPT) += ip6t_NPT.o
+obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o

net/ipv6/netfilter/ip6t_MASQUERADE.c

@@ -0,0 +1,135 @@
+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * 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.
+ *
+ * Based on Rusty Russell's IPv6 MASQUERADE target. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+
+static unsigned int
+masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+	enum ip_conntrack_info ctinfo;
+	struct in6_addr src;
+	struct nf_conn *ct;
+	struct nf_nat_range newrange;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED ||
+			    ctinfo == IP_CT_RELATED_REPLY));
+
+	if (ipv6_dev_get_saddr(dev_net(par->out), par->out,
+			       &ipv6_hdr(skb)->daddr, 0, &src) < 0)
+		return NF_DROP;
+
+	nfct_nat(ct)->masq_index = par->out->ifindex;
+
+	newrange.flags		= range->flags | NF_NAT_RANGE_MAP_IPS;
+	newrange.min_addr.in6	= src;
+	newrange.max_addr.in6	= src;
+	newrange.min_proto	= range->min_proto;
+	newrange.max_proto	= range->max_proto;
+
+	return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC);
+}
+
+static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par)
+{
+	const struct nf_nat_range *range = par->targinfo;
+
+	if (range->flags & NF_NAT_RANGE_MAP_IPS)
+		return -EINVAL;
+	return 0;
+}
+
+static int device_cmp(struct nf_conn *ct, void *ifindex)
+{
+	const struct nf_conn_nat *nat = nfct_nat(ct);
+
+	if (!nat)
+		return 0;
+	if (nf_ct_l3num(ct) != NFPROTO_IPV6)
+		return 0;
+	return nat->masq_index == (int)(long)ifindex;
+}
+
+static int masq_device_event(struct notifier_block *this,
+			     unsigned long event, void *ptr)
+{
+	const struct net_device *dev = ptr;
+	struct net *net = dev_net(dev);
+
+	if (event == NETDEV_DOWN)
+		nf_ct_iterate_cleanup(net, device_cmp,
+				      (void *)(long)dev->ifindex);
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block masq_dev_notifier = {
+	.notifier_call	= masq_device_event,
+};
+
+static int masq_inet_event(struct notifier_block *this,
+			   unsigned long event, void *ptr)
+{
+	struct inet6_ifaddr *ifa = ptr;
+
+	return masq_device_event(this, event, ifa->idev->dev);
+}
+
+static struct notifier_block masq_inet_notifier = {
+	.notifier_call	= masq_inet_event,
+};
+
+static struct xt_target masquerade_tg6_reg __read_mostly = {
+	.name		= "MASQUERADE",
+	.family		= NFPROTO_IPV6,
+	.checkentry	= masquerade_tg6_checkentry,
+	.target		= masquerade_tg6,
+	.targetsize	= sizeof(struct nf_nat_range),
+	.table		= "nat",
+	.hooks		= 1 << NF_INET_POST_ROUTING,
+	.me		= THIS_MODULE,
+};
+
+static int __init masquerade_tg6_init(void)
+{
+	int err;
+
+	err = xt_register_target(&masquerade_tg6_reg);
+	if (err == 0) {
+		register_netdevice_notifier(&masq_dev_notifier);
+		register_inet6addr_notifier(&masq_inet_notifier);
+	}
+
+	return err;
+}
+static void __exit masquerade_tg6_exit(void)
+{
+	unregister_inet6addr_notifier(&masq_inet_notifier);
+	unregister_netdevice_notifier(&masq_dev_notifier);
+	xt_unregister_target(&masquerade_tg6_reg);
+}
+
+module_init(masquerade_tg6_init);
+module_exit(masquerade_tg6_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_DESCRIPTION("Xtables: automatic address SNAT");

net/ipv6/netfilter/ip6t_NPT.c

@@ -0,0 +1,153 @@
+/*
+ * Copyright (c) 2011, 2012 Patrick McHardy <kaber@trash.net>
+ *
+ * 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/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv6/ip6t_NPT.h>
+#include <linux/netfilter/x_tables.h>
+
+static int ip6t_npt_checkentry(const struct xt_tgchk_param *par)
+{
+	struct ip6t_npt_tginfo *npt = par->targinfo;
+	struct in6_addr pfx;
+	__wsum src_sum, dst_sum;
+
+	if (npt->src_pfx_len > 64 || npt->dst_pfx_len > 64)
+		return -EINVAL;
+
+	/* Ensure that LSB of prefix is zero */
+	ipv6_addr_prefix(&pfx, &npt->src_pfx.in6, npt->src_pfx_len);
+	if (!ipv6_addr_equal(&pfx, &npt->src_pfx.in6))
+		return -EINVAL;
+	ipv6_addr_prefix(&pfx, &npt->dst_pfx.in6, npt->dst_pfx_len);
+	if (!ipv6_addr_equal(&pfx, &npt->dst_pfx.in6))
+		return -EINVAL;
+
+	src_sum = csum_partial(&npt->src_pfx.in6, sizeof(npt->src_pfx.in6), 0);
+	dst_sum = csum_partial(&npt->dst_pfx.in6, sizeof(npt->dst_pfx.in6), 0);
+
+	npt->adjustment = ~csum_fold(csum_sub(src_sum, dst_sum));
+	return 0;
+}
+
+static bool ip6t_npt_map_pfx(const struct ip6t_npt_tginfo *npt,
+			     struct in6_addr *addr)
+{
+	unsigned int pfx_len;
+	unsigned int i, idx;
+	__be32 mask;
+	__sum16 sum;
+
+	pfx_len = max(npt->src_pfx_len, npt->dst_pfx_len);
+	for (i = 0; i < pfx_len; i += 32) {
+		if (pfx_len - i >= 32)
+			mask = 0;
+		else
+			mask = htonl((1 << (i - pfx_len + 32)) - 1);
+
+		idx = i / 32;
+		addr->s6_addr32[idx] &= mask;
+		addr->s6_addr32[idx] |= ~mask & npt->dst_pfx.in6.s6_addr32[idx];
+	}
+
+	if (pfx_len <= 48)
+		idx = 3;
+	else {
+		for (idx = 4; idx < ARRAY_SIZE(addr->s6_addr16); idx++) {
+			if ((__force __sum16)addr->s6_addr16[idx] !=
+			    CSUM_MANGLED_0)
+				break;
+		}
+		if (idx == ARRAY_SIZE(addr->s6_addr16))
+			return false;
+	}
+
+	sum = ~csum_fold(csum_add(csum_unfold((__force __sum16)addr->s6_addr16[idx]),
+				  csum_unfold(npt->adjustment)));
+	if (sum == CSUM_MANGLED_0)
+		sum = 0;
+	*(__force __sum16 *)&addr->s6_addr16[idx] = sum;
+
+	return true;
+}
+
+static unsigned int
+ip6t_snpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ip6t_npt_tginfo *npt = par->targinfo;
+
+	if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->saddr)) {
+		icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
+			    offsetof(struct ipv6hdr, saddr));
+		return NF_DROP;
+	}
+	return XT_CONTINUE;
+}
+
+static unsigned int
+ip6t_dnpt_tg(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ip6t_npt_tginfo *npt = par->targinfo;
+
+	if (!ip6t_npt_map_pfx(npt, &ipv6_hdr(skb)->daddr)) {
+		icmpv6_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD,
+			    offsetof(struct ipv6hdr, daddr));
+		return NF_DROP;
+	}
+	return XT_CONTINUE;
+}
+
+static struct xt_target ip6t_npt_target_reg[] __read_mostly = {
+	{
+		.name		= "SNPT",
+		.table		= "mangle",
+		.target		= ip6t_snpt_tg,
+		.targetsize	= sizeof(struct ip6t_npt_tginfo),
+		.checkentry	= ip6t_npt_checkentry,
+		.family		= NFPROTO_IPV6,
+		.hooks		= (1 << NF_INET_LOCAL_IN) |
+				  (1 << NF_INET_POST_ROUTING),
+		.me		= THIS_MODULE,
+	},
+	{
+		.name		= "DNPT",
+		.table		= "mangle",
+		.target		= ip6t_dnpt_tg,
+		.targetsize	= sizeof(struct ip6t_npt_tginfo),
+		.checkentry	= ip6t_npt_checkentry,
+		.family		= NFPROTO_IPV6,
+		.hooks		= (1 << NF_INET_PRE_ROUTING) |
+				  (1 << NF_INET_LOCAL_OUT),
+		.me		= THIS_MODULE,
+	},
+};
+
+static int __init ip6t_npt_init(void)
+{
+	return xt_register_targets(ip6t_npt_target_reg,
+				   ARRAY_SIZE(ip6t_npt_target_reg));
+}
+
+static void __exit ip6t_npt_exit(void)
+{
+	xt_unregister_targets(ip6t_npt_target_reg,
+			      ARRAY_SIZE(ip6t_npt_target_reg));
+}
+
+module_init(ip6t_npt_init);
+module_exit(ip6t_npt_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("IPv6-to-IPv6 Network Prefix Translation (RFC 6296)");
+MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>");
+MODULE_ALIAS("ip6t_SNPT");
+MODULE_ALIAS("ip6t_DNPT");

net/ipv6/netfilter/ip6t_REJECT.c

@@ -0,0 +1,264 @@
+/*
+ * IP6 tables REJECT target module
+ * Linux INET6 implementation
+ *
+ * Copyright (C)2003 USAGI/WIDE Project
+ *
+ * Authors:
+ *	Yasuyuki Kozakai	<yasuyuki.kozakai@toshiba.co.jp>
+ *
+ * Copyright (c) 2005-2007 Patrick McHardy <kaber@trash.net>
+ *
+ * Based on net/ipv4/netfilter/ipt_REJECT.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/gfp.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/icmpv6.h>
+#include <linux/netdevice.h>
+#include <net/ipv6.h>
+#include <net/tcp.h>
+#include <net/icmp.h>
+#include <net/ip6_checksum.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+#include <net/flow.h>
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_REJECT.h>
+
+MODULE_AUTHOR("Yasuyuki KOZAKAI <yasuyuki.kozakai@toshiba.co.jp>");
+MODULE_DESCRIPTION("Xtables: packet \"rejection\" target for IPv6");
+MODULE_LICENSE("GPL");
+
+/* Send RST reply */
+static void send_reset(struct net *net, struct sk_buff *oldskb)
+{
+	struct sk_buff *nskb;
+	struct tcphdr otcph, *tcph;
+	unsigned int otcplen, hh_len;
+	int tcphoff, needs_ack;
+	const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
+	struct ipv6hdr *ip6h;
+#define DEFAULT_TOS_VALUE	0x0U
+	const __u8 tclass = DEFAULT_TOS_VALUE;
+	struct dst_entry *dst = NULL;
+	u8 proto;
+	__be16 frag_off;
+	struct flowi6 fl6;
+
+	if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
+	    (!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
+		pr_debug("addr is not unicast.\n");
+		return;
+	}
+
+	proto = oip6h->nexthdr;
+	tcphoff = ipv6_skip_exthdr(oldskb, ((u8*)(oip6h+1) - oldskb->data), &proto, &frag_off);
+
+	if ((tcphoff < 0) || (tcphoff > oldskb->len)) {
+		pr_debug("Cannot get TCP header.\n");
+		return;
+	}
+
+	otcplen = oldskb->len - tcphoff;
+
+	/* IP header checks: fragment, too short. */
+	if (proto != IPPROTO_TCP || otcplen < sizeof(struct tcphdr)) {
+		pr_debug("proto(%d) != IPPROTO_TCP, "
+			 "or too short. otcplen = %d\n",
+			 proto, otcplen);
+		return;
+	}
+
+	if (skb_copy_bits(oldskb, tcphoff, &otcph, sizeof(struct tcphdr)))
+		BUG();
+
+	/* No RST for RST. */
+	if (otcph.rst) {
+		pr_debug("RST is set\n");
+		return;
+	}
+
+	/* Check checksum. */
+	if (csum_ipv6_magic(&oip6h->saddr, &oip6h->daddr, otcplen, IPPROTO_TCP,
+			    skb_checksum(oldskb, tcphoff, otcplen, 0))) {
+		pr_debug("TCP checksum is invalid\n");
+		return;
+	}
+
+	memset(&fl6, 0, sizeof(fl6));
+	fl6.flowi6_proto = IPPROTO_TCP;
+	fl6.saddr = oip6h->daddr;
+	fl6.daddr = oip6h->saddr;
+	fl6.fl6_sport = otcph.dest;
+	fl6.fl6_dport = otcph.source;
+	security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
+	dst = ip6_route_output(net, NULL, &fl6);
+	if (dst == NULL || dst->error) {
+		dst_release(dst);
+		return;
+	}
+	dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
+	if (IS_ERR(dst))
+		return;
+
+	hh_len = (dst->dev->hard_header_len + 15)&~15;
+	nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+			 + sizeof(struct tcphdr) + dst->trailer_len,
+			 GFP_ATOMIC);
+
+	if (!nskb) {
+		net_dbg_ratelimited("cannot alloc skb\n");
+		dst_release(dst);
+		return;
+	}
+
+	skb_dst_set(nskb, dst);
+
+	skb_reserve(nskb, hh_len + dst->header_len);
+
+	skb_put(nskb, sizeof(struct ipv6hdr));
+	skb_reset_network_header(nskb);
+	ip6h = ipv6_hdr(nskb);
+	ip6_flow_hdr(ip6h, tclass, 0);
+	ip6h->hop_limit = ip6_dst_hoplimit(dst);
+	ip6h->nexthdr = IPPROTO_TCP;
+	ip6h->saddr = oip6h->daddr;
+	ip6h->daddr = oip6h->saddr;
+
+	skb_reset_transport_header(nskb);
+	tcph = (struct tcphdr *)skb_put(nskb, sizeof(struct tcphdr));
+	/* Truncate to length (no data) */
+	tcph->doff = sizeof(struct tcphdr)/4;
+	tcph->source = otcph.dest;
+	tcph->dest = otcph.source;
+
+	if (otcph.ack) {
+		needs_ack = 0;
+		tcph->seq = otcph.ack_seq;
+		tcph->ack_seq = 0;
+	} else {
+		needs_ack = 1;
+		tcph->ack_seq = htonl(ntohl(otcph.seq) + otcph.syn + otcph.fin
+				      + otcplen - (otcph.doff<<2));
+		tcph->seq = 0;
+	}
+
+	/* Reset flags */
+	((u_int8_t *)tcph)[13] = 0;
+	tcph->rst = 1;
+	tcph->ack = needs_ack;
+	tcph->window = 0;
+	tcph->urg_ptr = 0;
+	tcph->check = 0;
+
+	/* Adjust TCP checksum */
+	tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
+				      &ipv6_hdr(nskb)->daddr,
+				      sizeof(struct tcphdr), IPPROTO_TCP,
+				      csum_partial(tcph,
+						   sizeof(struct tcphdr), 0));
+
+	nf_ct_attach(nskb, oldskb);
+
+	ip6_local_out(nskb);
+}
+
+static inline void
+send_unreach(struct net *net, struct sk_buff *skb_in, unsigned char code,
+	     unsigned int hooknum)
+{
+	if (hooknum == NF_INET_LOCAL_OUT && skb_in->dev == NULL)
+		skb_in->dev = net->loopback_dev;
+
+	icmpv6_send(skb_in, ICMPV6_DEST_UNREACH, code, 0);
+}
+
+static unsigned int
+reject_tg6(struct sk_buff *skb, const struct xt_action_param *par)
+{
+	const struct ip6t_reject_info *reject = par->targinfo;
+	struct net *net = dev_net((par->in != NULL) ? par->in : par->out);
+
+	pr_debug("%s: medium point\n", __func__);
+	switch (reject->with) {
+	case IP6T_ICMP6_NO_ROUTE:
+		send_unreach(net, skb, ICMPV6_NOROUTE, par->hooknum);
+		break;
+	case IP6T_ICMP6_ADM_PROHIBITED:
+		send_unreach(net, skb, ICMPV6_ADM_PROHIBITED, par->hooknum);
+		break;
+	case IP6T_ICMP6_NOT_NEIGHBOUR:
+		send_unreach(net, skb, ICMPV6_NOT_NEIGHBOUR, par->hooknum);
+		break;
+	case IP6T_ICMP6_ADDR_UNREACH:
+		send_unreach(net, skb, ICMPV6_ADDR_UNREACH, par->hooknum);
+		break;
+	case IP6T_ICMP6_PORT_UNREACH:
+		send_unreach(net, skb, ICMPV6_PORT_UNREACH, par->hooknum);
+		break;
+	case IP6T_ICMP6_ECHOREPLY:
+		/* Do nothing */
+		break;
+	case IP6T_TCP_RESET:
+		send_reset(net, skb);
+		break;
+	default:
+		net_info_ratelimited("case %u not handled yet\n", reject->with);
+		break;
+	}
+
+	return NF_DROP;
+}
+
+static int reject_tg6_check(const struct xt_tgchk_param *par)
+{
+	const struct ip6t_reject_info *rejinfo = par->targinfo;
+	const struct ip6t_entry *e = par->entryinfo;
+
+	if (rejinfo->with == IP6T_ICMP6_ECHOREPLY) {
+		pr_info("ECHOREPLY is not supported.\n");
+		return -EINVAL;
+	} else if (rejinfo->with == IP6T_TCP_RESET) {
+		/* Must specify that it's a TCP packet */
+		if (e->ipv6.proto != IPPROTO_TCP ||
+		    (e->ipv6.invflags & XT_INV_PROTO)) {
+			pr_info("TCP_RESET illegal for non-tcp\n");
+			return -EINVAL;
+		}
+	}
+	return 0;
+}
+
+static struct xt_target reject_tg6_reg __read_mostly = {
+	.name		= "REJECT",
+	.family		= NFPROTO_IPV6,
+	.target		= reject_tg6,
+	.targetsize	= sizeof(struct ip6t_reject_info),
+	.table		= "filter",
+	.hooks		= (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD) |
+			  (1 << NF_INET_LOCAL_OUT),
+	.checkentry	= reject_tg6_check,
+	.me		= THIS_MODULE
+};
+
+static int __init reject_tg6_init(void)
+{
+	return xt_register_target(&reject_tg6_reg);
+}
+
+static void __exit reject_tg6_exit(void)
+{
+	xt_unregister_target(&reject_tg6_reg);
+}
+
+module_init(reject_tg6_init);
+module_exit(reject_tg6_exit);

net/ipv6/netfilter/ip6t_ah.c

@@ -0,0 +1,121 @@
+/* Kernel module to match AH parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * 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.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_ah.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: IPv6 IPsec-AH match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+/* Returns 1 if the spi is matched by the range, 0 otherwise */
+static inline bool
+spi_match(u_int32_t min, u_int32_t max, u_int32_t spi, bool invert)
+{
+	bool r;
+
+	pr_debug("spi_match:%c 0x%x <= 0x%x <= 0x%x\n",
+		 invert ? '!' : ' ', min, spi, max);
+	r = (spi >= min && spi <= max) ^ invert;
+	pr_debug(" result %s\n", r ? "PASS" : "FAILED");
+	return r;
+}
+
+static bool ah_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct ip_auth_hdr _ah;
+	const struct ip_auth_hdr *ah;
+	const struct ip6t_ah *ahinfo = par->matchinfo;
+	unsigned int ptr = 0;
+	unsigned int hdrlen = 0;
+	int err;
+
+	err = ipv6_find_hdr(skb, &ptr, NEXTHDR_AUTH, NULL, NULL);
+	if (err < 0) {
+		if (err != -ENOENT)
+			par->hotdrop = true;
+		return false;
+	}
+
+	ah = skb_header_pointer(skb, ptr, sizeof(_ah), &_ah);
+	if (ah == NULL) {
+		par->hotdrop = true;
+		return false;
+	}
+
+	hdrlen = (ah->hdrlen + 2) << 2;
+
+	pr_debug("IPv6 AH LEN %u %u ", hdrlen, ah->hdrlen);
+	pr_debug("RES %04X ", ah->reserved);
+	pr_debug("SPI %u %08X\n", ntohl(ah->spi), ntohl(ah->spi));
+
+	pr_debug("IPv6 AH spi %02X ",
+		 spi_match(ahinfo->spis[0], ahinfo->spis[1],
+			   ntohl(ah->spi),
+			   !!(ahinfo->invflags & IP6T_AH_INV_SPI)));
+	pr_debug("len %02X %04X %02X ",
+		 ahinfo->hdrlen, hdrlen,
+		 (!ahinfo->hdrlen ||
+		  (ahinfo->hdrlen == hdrlen) ^
+		  !!(ahinfo->invflags & IP6T_AH_INV_LEN)));
+	pr_debug("res %02X %04X %02X\n",
+		 ahinfo->hdrres, ah->reserved,
+		 !(ahinfo->hdrres && ah->reserved));
+
+	return (ah != NULL) &&
+		spi_match(ahinfo->spis[0], ahinfo->spis[1],
+			  ntohl(ah->spi),
+			  !!(ahinfo->invflags & IP6T_AH_INV_SPI)) &&
+		(!ahinfo->hdrlen ||
+		 (ahinfo->hdrlen == hdrlen) ^
+		 !!(ahinfo->invflags & IP6T_AH_INV_LEN)) &&
+		!(ahinfo->hdrres && ah->reserved);
+}
+
+static int ah_mt6_check(const struct xt_mtchk_param *par)
+{
+	const struct ip6t_ah *ahinfo = par->matchinfo;
+
+	if (ahinfo->invflags & ~IP6T_AH_INV_MASK) {
+		pr_debug("unknown flags %X\n", ahinfo->invflags);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct xt_match ah_mt6_reg __read_mostly = {
+	.name		= "ah",
+	.family		= NFPROTO_IPV6,
+	.match		= ah_mt6,
+	.matchsize	= sizeof(struct ip6t_ah),
+	.checkentry	= ah_mt6_check,
+	.me		= THIS_MODULE,
+};
+
+static int __init ah_mt6_init(void)
+{
+	return xt_register_match(&ah_mt6_reg);
+}
+
+static void __exit ah_mt6_exit(void)
+{
+	xt_unregister_match(&ah_mt6_reg);
+}
+
+module_init(ah_mt6_init);
+module_exit(ah_mt6_exit);

net/ipv6/netfilter/ip6t_eui64.c

@@ -0,0 +1,74 @@
+/* Kernel module to match EUI64 address parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * 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/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/if_ether.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+
+MODULE_DESCRIPTION("Xtables: IPv6 EUI64 address match");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+static bool
+eui64_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	unsigned char eui64[8];
+
+	if (!(skb_mac_header(skb) >= skb->head &&
+	      skb_mac_header(skb) + ETH_HLEN <= skb->data) &&
+	    par->fragoff != 0) {
+		par->hotdrop = true;
+		return false;
+	}
+
+	memset(eui64, 0, sizeof(eui64));
+
+	if (eth_hdr(skb)->h_proto == htons(ETH_P_IPV6)) {
+		if (ipv6_hdr(skb)->version == 0x6) {
+			memcpy(eui64, eth_hdr(skb)->h_source, 3);
+			memcpy(eui64 + 5, eth_hdr(skb)->h_source + 3, 3);
+			eui64[3] = 0xff;
+			eui64[4] = 0xfe;
+			eui64[0] ^= 0x02;
+
+			if (!memcmp(ipv6_hdr(skb)->saddr.s6_addr + 8, eui64,
+				    sizeof(eui64)))
+				return true;
+		}
+	}
+
+	return false;
+}
+
+static struct xt_match eui64_mt6_reg __read_mostly = {
+	.name		= "eui64",
+	.family		= NFPROTO_IPV6,
+	.match		= eui64_mt6,
+	.matchsize	= sizeof(int),
+	.hooks		= (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) |
+			  (1 << NF_INET_FORWARD),
+	.me		= THIS_MODULE,
+};
+
+static int __init eui64_mt6_init(void)
+{
+	return xt_register_match(&eui64_mt6_reg);
+}
+
+static void __exit eui64_mt6_exit(void)
+{
+	xt_unregister_match(&eui64_mt6_reg);
+}
+
+module_init(eui64_mt6_init);
+module_exit(eui64_mt6_exit);

net/ipv6/netfilter/ip6t_frag.c

@@ -0,0 +1,136 @@
+/* Kernel module to match FRAG parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * 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.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_frag.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: IPv6 fragment match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+/* Returns 1 if the id is matched by the range, 0 otherwise */
+static inline bool
+id_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert)
+{
+	bool r;
+	pr_debug("id_match:%c 0x%x <= 0x%x <= 0x%x\n", invert ? '!' : ' ',
+		 min, id, max);
+	r = (id >= min && id <= max) ^ invert;
+	pr_debug(" result %s\n", r ? "PASS" : "FAILED");
+	return r;
+}
+
+static bool
+frag_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct frag_hdr _frag;
+	const struct frag_hdr *fh;
+	const struct ip6t_frag *fraginfo = par->matchinfo;
+	unsigned int ptr = 0;
+	int err;
+
+	err = ipv6_find_hdr(skb, &ptr, NEXTHDR_FRAGMENT, NULL, NULL);
+	if (err < 0) {
+		if (err != -ENOENT)
+			par->hotdrop = true;
+		return false;
+	}
+
+	fh = skb_header_pointer(skb, ptr, sizeof(_frag), &_frag);
+	if (fh == NULL) {
+		par->hotdrop = true;
+		return false;
+	}
+
+	pr_debug("INFO %04X ", fh->frag_off);
+	pr_debug("OFFSET %04X ", ntohs(fh->frag_off) & ~0x7);
+	pr_debug("RES %02X %04X", fh->reserved, ntohs(fh->frag_off) & 0x6);
+	pr_debug("MF %04X ", fh->frag_off & htons(IP6_MF));
+	pr_debug("ID %u %08X\n", ntohl(fh->identification),
+		 ntohl(fh->identification));
+
+	pr_debug("IPv6 FRAG id %02X ",
+		 id_match(fraginfo->ids[0], fraginfo->ids[1],
+			  ntohl(fh->identification),
+			  !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)));
+	pr_debug("res %02X %02X%04X %02X ",
+		 fraginfo->flags & IP6T_FRAG_RES, fh->reserved,
+		 ntohs(fh->frag_off) & 0x6,
+		 !((fraginfo->flags & IP6T_FRAG_RES) &&
+		   (fh->reserved || (ntohs(fh->frag_off) & 0x06))));
+	pr_debug("first %02X %02X %02X ",
+		 fraginfo->flags & IP6T_FRAG_FST,
+		 ntohs(fh->frag_off) & ~0x7,
+		 !((fraginfo->flags & IP6T_FRAG_FST) &&
+		   (ntohs(fh->frag_off) & ~0x7)));
+	pr_debug("mf %02X %02X %02X ",
+		 fraginfo->flags & IP6T_FRAG_MF,
+		 ntohs(fh->frag_off) & IP6_MF,
+		 !((fraginfo->flags & IP6T_FRAG_MF) &&
+		   !((ntohs(fh->frag_off) & IP6_MF))));
+	pr_debug("last %02X %02X %02X\n",
+		 fraginfo->flags & IP6T_FRAG_NMF,
+		 ntohs(fh->frag_off) & IP6_MF,
+		 !((fraginfo->flags & IP6T_FRAG_NMF) &&
+		   (ntohs(fh->frag_off) & IP6_MF)));
+
+	return (fh != NULL) &&
+		id_match(fraginfo->ids[0], fraginfo->ids[1],
+			 ntohl(fh->identification),
+			 !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) &&
+		!((fraginfo->flags & IP6T_FRAG_RES) &&
+		  (fh->reserved || (ntohs(fh->frag_off) & 0x6))) &&
+		!((fraginfo->flags & IP6T_FRAG_FST) &&
+		  (ntohs(fh->frag_off) & ~0x7)) &&
+		!((fraginfo->flags & IP6T_FRAG_MF) &&
+		  !(ntohs(fh->frag_off) & IP6_MF)) &&
+		!((fraginfo->flags & IP6T_FRAG_NMF) &&
+		  (ntohs(fh->frag_off) & IP6_MF));
+}
+
+static int frag_mt6_check(const struct xt_mtchk_param *par)
+{
+	const struct ip6t_frag *fraginfo = par->matchinfo;
+
+	if (fraginfo->invflags & ~IP6T_FRAG_INV_MASK) {
+		pr_debug("unknown flags %X\n", fraginfo->invflags);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static struct xt_match frag_mt6_reg __read_mostly = {
+	.name		= "frag",
+	.family		= NFPROTO_IPV6,
+	.match		= frag_mt6,
+	.matchsize	= sizeof(struct ip6t_frag),
+	.checkentry	= frag_mt6_check,
+	.me		= THIS_MODULE,
+};
+
+static int __init frag_mt6_init(void)
+{
+	return xt_register_match(&frag_mt6_reg);
+}
+
+static void __exit frag_mt6_exit(void)
+{
+	xt_unregister_match(&frag_mt6_reg);
+}
+
+module_init(frag_mt6_init);
+module_exit(frag_mt6_exit);

net/ipv6/netfilter/ip6t_hbh.c

@@ -0,0 +1,215 @@
+/* Kernel module to match Hop-by-Hop and Destination parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * 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.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <asm/byteorder.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_opts.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: IPv6 Hop-By-Hop and Destination Header match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+MODULE_ALIAS("ip6t_dst");
+
+/*
+ *  (Type & 0xC0) >> 6
+ *	0	-> ignorable
+ *	1	-> must drop the packet
+ *	2	-> send ICMP PARM PROB regardless and drop packet
+ *	3	-> Send ICMP if not a multicast address and drop packet
+ *  (Type & 0x20) >> 5
+ *	0	-> invariant
+ *	1	-> can change the routing
+ *  (Type & 0x1F) Type
+ *	0	-> Pad1 (only 1 byte!)
+ *	1	-> PadN LENGTH info (total length = length + 2)
+ *	C0 | 2	-> JUMBO 4 x x x x ( xxxx > 64k )
+ *	5	-> RTALERT 2 x x
+ */
+
+static struct xt_match hbh_mt6_reg[] __read_mostly;
+
+static bool
+hbh_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct ipv6_opt_hdr _optsh;
+	const struct ipv6_opt_hdr *oh;
+	const struct ip6t_opts *optinfo = par->matchinfo;
+	unsigned int temp;
+	unsigned int ptr = 0;
+	unsigned int hdrlen = 0;
+	bool ret = false;
+	u8 _opttype;
+	u8 _optlen;
+	const u_int8_t *tp = NULL;
+	const u_int8_t *lp = NULL;
+	unsigned int optlen;
+	int err;
+
+	err = ipv6_find_hdr(skb, &ptr,
+			    (par->match == &hbh_mt6_reg[0]) ?
+			    NEXTHDR_HOP : NEXTHDR_DEST, NULL, NULL);
+	if (err < 0) {
+		if (err != -ENOENT)
+			par->hotdrop = true;
+		return false;
+	}
+
+	oh = skb_header_pointer(skb, ptr, sizeof(_optsh), &_optsh);
+	if (oh == NULL) {
+		par->hotdrop = true;
+		return false;
+	}
+
+	hdrlen = ipv6_optlen(oh);
+	if (skb->len - ptr < hdrlen) {
+		/* Packet smaller than it's length field */
+		return false;
+	}
+
+	pr_debug("IPv6 OPTS LEN %u %u ", hdrlen, oh->hdrlen);
+
+	pr_debug("len %02X %04X %02X ",
+		 optinfo->hdrlen, hdrlen,
+		 (!(optinfo->flags & IP6T_OPTS_LEN) ||
+		  ((optinfo->hdrlen == hdrlen) ^
+		   !!(optinfo->invflags & IP6T_OPTS_INV_LEN))));
+
+	ret = (oh != NULL) &&
+	      (!(optinfo->flags & IP6T_OPTS_LEN) ||
+	       ((optinfo->hdrlen == hdrlen) ^
+		!!(optinfo->invflags & IP6T_OPTS_INV_LEN)));
+
+	ptr += 2;
+	hdrlen -= 2;
+	if (!(optinfo->flags & IP6T_OPTS_OPTS)) {
+		return ret;
+	} else {
+		pr_debug("Strict ");
+		pr_debug("#%d ", optinfo->optsnr);
+		for (temp = 0; temp < optinfo->optsnr; temp++) {
+			/* type field exists ? */
+			if (hdrlen < 1)
+				break;
+			tp = skb_header_pointer(skb, ptr, sizeof(_opttype),
+						&_opttype);
+			if (tp == NULL)
+				break;
+
+			/* Type check */
+			if (*tp != (optinfo->opts[temp] & 0xFF00) >> 8) {
+				pr_debug("Tbad %02X %02X\n", *tp,
+					 (optinfo->opts[temp] & 0xFF00) >> 8);
+				return false;
+			} else {
+				pr_debug("Tok ");
+			}
+			/* Length check */
+			if (*tp) {
+				u16 spec_len;
+
+				/* length field exists ? */
+				if (hdrlen < 2)
+					break;
+				lp = skb_header_pointer(skb, ptr + 1,
+							sizeof(_optlen),
+							&_optlen);
+				if (lp == NULL)
+					break;
+				spec_len = optinfo->opts[temp] & 0x00FF;
+
+				if (spec_len != 0x00FF && spec_len != *lp) {
+					pr_debug("Lbad %02X %04X\n", *lp,
+						 spec_len);
+					return false;
+				}
+				pr_debug("Lok ");
+				optlen = *lp + 2;
+			} else {
+				pr_debug("Pad1\n");
+				optlen = 1;
+			}
+
+			/* Step to the next */
+			pr_debug("len%04X\n", optlen);
+
+			if ((ptr > skb->len - optlen || hdrlen < optlen) &&
+			    temp < optinfo->optsnr - 1) {
+				pr_debug("new pointer is too large!\n");
+				break;
+			}
+			ptr += optlen;
+			hdrlen -= optlen;
+		}
+		if (temp == optinfo->optsnr)
+			return ret;
+		else
+			return false;
+	}
+
+	return false;
+}
+
+static int hbh_mt6_check(const struct xt_mtchk_param *par)
+{
+	const struct ip6t_opts *optsinfo = par->matchinfo;
+
+	if (optsinfo->invflags & ~IP6T_OPTS_INV_MASK) {
+		pr_debug("unknown flags %X\n", optsinfo->invflags);
+		return -EINVAL;
+	}
+
+	if (optsinfo->flags & IP6T_OPTS_NSTRICT) {
+		pr_debug("Not strict - not implemented");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct xt_match hbh_mt6_reg[] __read_mostly = {
+	{
+		/* Note, hbh_mt6 relies on the order of hbh_mt6_reg */
+		.name		= "hbh",
+		.family		= NFPROTO_IPV6,
+		.match		= hbh_mt6,
+		.matchsize	= sizeof(struct ip6t_opts),
+		.checkentry	= hbh_mt6_check,
+		.me		= THIS_MODULE,
+	},
+	{
+		.name		= "dst",
+		.family		= NFPROTO_IPV6,
+		.match		= hbh_mt6,
+		.matchsize	= sizeof(struct ip6t_opts),
+		.checkentry	= hbh_mt6_check,
+		.me		= THIS_MODULE,
+	},
+};
+
+static int __init hbh_mt6_init(void)
+{
+	return xt_register_matches(hbh_mt6_reg, ARRAY_SIZE(hbh_mt6_reg));
+}
+
+static void __exit hbh_mt6_exit(void)
+{
+	xt_unregister_matches(hbh_mt6_reg, ARRAY_SIZE(hbh_mt6_reg));
+}
+
+module_init(hbh_mt6_init);
+module_exit(hbh_mt6_exit);

net/ipv6/netfilter/ip6t_ipv6header.c

@@ -0,0 +1,154 @@
+/* ipv6header match - matches IPv6 packets based
+   on whether they contain certain headers */
+
+/* Original idea: Brad Chapman
+ * Rewritten by: Andras Kis-Szabo <kisza@sch.bme.hu> */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * 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/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_ipv6header.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: IPv6 header types match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+static bool
+ipv6header_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct ip6t_ipv6header_info *info = par->matchinfo;
+	unsigned int temp;
+	int len;
+	u8 nexthdr;
+	unsigned int ptr;
+
+	/* Make sure this isn't an evil packet */
+
+	/* type of the 1st exthdr */
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+	/* pointer to the 1st exthdr */
+	ptr = sizeof(struct ipv6hdr);
+	/* available length */
+	len = skb->len - ptr;
+	temp = 0;
+
+	while (ip6t_ext_hdr(nexthdr)) {
+		const struct ipv6_opt_hdr *hp;
+		struct ipv6_opt_hdr _hdr;
+		int hdrlen;
+
+		/* No more exthdr -> evaluate */
+		if (nexthdr == NEXTHDR_NONE) {
+			temp |= MASK_NONE;
+			break;
+		}
+		/* Is there enough space for the next ext header? */
+		if (len < (int)sizeof(struct ipv6_opt_hdr))
+			return false;
+		/* ESP -> evaluate */
+		if (nexthdr == NEXTHDR_ESP) {
+			temp |= MASK_ESP;
+			break;
+		}
+
+		hp = skb_header_pointer(skb, ptr, sizeof(_hdr), &_hdr);
+		BUG_ON(hp == NULL);
+
+		/* Calculate the header length */
+		if (nexthdr == NEXTHDR_FRAGMENT)
+			hdrlen = 8;
+		else if (nexthdr == NEXTHDR_AUTH)
+			hdrlen = (hp->hdrlen + 2) << 2;
+		else
+			hdrlen = ipv6_optlen(hp);
+
+		/* set the flag */
+		switch (nexthdr) {
+		case NEXTHDR_HOP:
+			temp |= MASK_HOPOPTS;
+			break;
+		case NEXTHDR_ROUTING:
+			temp |= MASK_ROUTING;
+			break;
+		case NEXTHDR_FRAGMENT:
+			temp |= MASK_FRAGMENT;
+			break;
+		case NEXTHDR_AUTH:
+			temp |= MASK_AH;
+			break;
+		case NEXTHDR_DEST:
+			temp |= MASK_DSTOPTS;
+			break;
+		default:
+			return false;
+			break;
+		}
+
+		nexthdr = hp->nexthdr;
+		len -= hdrlen;
+		ptr += hdrlen;
+		if (ptr > skb->len)
+			break;
+	}
+
+	if (nexthdr != NEXTHDR_NONE && nexthdr != NEXTHDR_ESP)
+		temp |= MASK_PROTO;
+
+	if (info->modeflag)
+		return !((temp ^ info->matchflags ^ info->invflags)
+			 & info->matchflags);
+	else {
+		if (info->invflags)
+			return temp != info->matchflags;
+		else
+			return temp == info->matchflags;
+	}
+}
+
+static int ipv6header_mt6_check(const struct xt_mtchk_param *par)
+{
+	const struct ip6t_ipv6header_info *info = par->matchinfo;
+
+	/* invflags is 0 or 0xff in hard mode */
+	if ((!info->modeflag) && info->invflags != 0x00 &&
+	    info->invflags != 0xFF)
+		return -EINVAL;
+
+	return 0;
+}
+
+static struct xt_match ipv6header_mt6_reg __read_mostly = {
+	.name		= "ipv6header",
+	.family		= NFPROTO_IPV6,
+	.match		= ipv6header_mt6,
+	.matchsize	= sizeof(struct ip6t_ipv6header_info),
+	.checkentry	= ipv6header_mt6_check,
+	.destroy	= NULL,
+	.me		= THIS_MODULE,
+};
+
+static int __init ipv6header_mt6_init(void)
+{
+	return xt_register_match(&ipv6header_mt6_reg);
+}
+
+static void __exit ipv6header_mt6_exit(void)
+{
+	xt_unregister_match(&ipv6header_mt6_reg);
+}
+
+module_init(ipv6header_mt6_init);
+module_exit(ipv6header_mt6_exit);

net/ipv6/netfilter/ip6t_mh.c

@@ -0,0 +1,94 @@
+/*
+ * Copyright (C)2006 USAGI/WIDE Project
+ *
+ * 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.
+ *
+ * Author:
+ *	Masahide NAKAMURA @USAGI <masahide.nakamura.cz@hitachi.com>
+ *
+ * Based on net/netfilter/xt_tcpudp.c
+ *
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/types.h>
+#include <linux/module.h>
+#include <net/ip.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <net/mip6.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6t_mh.h>
+
+MODULE_DESCRIPTION("Xtables: IPv6 Mobility Header match");
+MODULE_LICENSE("GPL");
+
+/* Returns 1 if the type is matched by the range, 0 otherwise */
+static inline bool
+type_match(u_int8_t min, u_int8_t max, u_int8_t type, bool invert)
+{
+	return (type >= min && type <= max) ^ invert;
+}
+
+static bool mh_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct ip6_mh _mh;
+	const struct ip6_mh *mh;
+	const struct ip6t_mh *mhinfo = par->matchinfo;
+
+	/* Must not be a fragment. */
+	if (par->fragoff != 0)
+		return false;
+
+	mh = skb_header_pointer(skb, par->thoff, sizeof(_mh), &_mh);
+	if (mh == NULL) {
+		/* We've been asked to examine this packet, and we
+		   can't.  Hence, no choice but to drop. */
+		pr_debug("Dropping evil MH tinygram.\n");
+		par->hotdrop = true;
+		return false;
+	}
+
+	if (mh->ip6mh_proto != IPPROTO_NONE) {
+		pr_debug("Dropping invalid MH Payload Proto: %u\n",
+			 mh->ip6mh_proto);
+		par->hotdrop = true;
+		return false;
+	}
+
+	return type_match(mhinfo->types[0], mhinfo->types[1], mh->ip6mh_type,
+			  !!(mhinfo->invflags & IP6T_MH_INV_TYPE));
+}
+
+static int mh_mt6_check(const struct xt_mtchk_param *par)
+{
+	const struct ip6t_mh *mhinfo = par->matchinfo;
+
+	/* Must specify no unknown invflags */
+	return (mhinfo->invflags & ~IP6T_MH_INV_MASK) ? -EINVAL : 0;
+}
+
+static struct xt_match mh_mt6_reg __read_mostly = {
+	.name		= "mh",
+	.family		= NFPROTO_IPV6,
+	.checkentry	= mh_mt6_check,
+	.match		= mh_mt6,
+	.matchsize	= sizeof(struct ip6t_mh),
+	.proto		= IPPROTO_MH,
+	.me		= THIS_MODULE,
+};
+
+static int __init mh_mt6_init(void)
+{
+	return xt_register_match(&mh_mt6_reg);
+}
+
+static void __exit mh_mt6_exit(void)
+{
+	xt_unregister_match(&mh_mt6_reg);
+}
+
+module_init(mh_mt6_init);
+module_exit(mh_mt6_exit);

net/ipv6/netfilter/ip6t_rpfilter.c

@@ -0,0 +1,139 @@
+/*
+ * Copyright (c) 2011 Florian Westphal <fw@strlen.de>
+ *
+ * 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.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/netdevice.h>
+#include <linux/route.h>
+#include <net/ip6_fib.h>
+#include <net/ip6_route.h>
+
+#include <linux/netfilter/xt_rpfilter.h>
+#include <linux/netfilter/x_tables.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Florian Westphal <fw@strlen.de>");
+MODULE_DESCRIPTION("Xtables: IPv6 reverse path filter match");
+
+static bool rpfilter_addr_unicast(const struct in6_addr *addr)
+{
+	int addr_type = ipv6_addr_type(addr);
+	return addr_type & IPV6_ADDR_UNICAST;
+}
+
+static bool rpfilter_lookup_reverse6(const struct sk_buff *skb,
+				     const struct net_device *dev, u8 flags)
+{
+	struct rt6_info *rt;
+	struct ipv6hdr *iph = ipv6_hdr(skb);
+	bool ret = false;
+	struct flowi6 fl6 = {
+		.flowlabel = (* (__be32 *) iph) & IPV6_FLOWINFO_MASK,
+		.flowi6_proto = iph->nexthdr,
+		.daddr = iph->saddr,
+	};
+	int lookup_flags;
+
+	if (rpfilter_addr_unicast(&iph->daddr)) {
+		memcpy(&fl6.saddr, &iph->daddr, sizeof(struct in6_addr));
+		lookup_flags = RT6_LOOKUP_F_HAS_SADDR;
+	} else {
+		lookup_flags = 0;
+	}
+
+	fl6.flowi6_mark = flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0;
+	if ((flags & XT_RPFILTER_LOOSE) == 0) {
+		fl6.flowi6_oif = dev->ifindex;
+		lookup_flags |= RT6_LOOKUP_F_IFACE;
+	}
+
+	rt = (void *) ip6_route_lookup(dev_net(dev), &fl6, lookup_flags);
+	if (rt->dst.error)
+		goto out;
+
+	if (rt->rt6i_flags & (RTF_REJECT|RTF_ANYCAST))
+		goto out;
+
+	if (rt->rt6i_flags & RTF_LOCAL) {
+		ret = flags & XT_RPFILTER_ACCEPT_LOCAL;
+		goto out;
+	}
+
+	if (rt->rt6i_idev->dev == dev || (flags & XT_RPFILTER_LOOSE))
+		ret = true;
+ out:
+	ip6_rt_put(rt);
+	return ret;
+}
+
+static bool rpfilter_is_local(const struct sk_buff *skb)
+{
+	const struct rt6_info *rt = (const void *) skb_dst(skb);
+	return rt && (rt->rt6i_flags & RTF_LOCAL);
+}
+
+static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	const struct xt_rpfilter_info *info = par->matchinfo;
+	int saddrtype;
+	struct ipv6hdr *iph;
+	bool invert = info->flags & XT_RPFILTER_INVERT;
+
+	if (rpfilter_is_local(skb))
+		return true ^ invert;
+
+	iph = ipv6_hdr(skb);
+	saddrtype = ipv6_addr_type(&iph->saddr);
+	if (unlikely(saddrtype == IPV6_ADDR_ANY))
+		return true ^ invert; /* not routable: forward path will drop it */
+
+	return rpfilter_lookup_reverse6(skb, par->in, info->flags) ^ invert;
+}
+
+static int rpfilter_check(const struct xt_mtchk_param *par)
+{
+	const struct xt_rpfilter_info *info = par->matchinfo;
+	unsigned int options = ~XT_RPFILTER_OPTION_MASK;
+
+	if (info->flags & options) {
+		pr_info("unknown options encountered");
+		return -EINVAL;
+	}
+
+	if (strcmp(par->table, "mangle") != 0 &&
+	    strcmp(par->table, "raw") != 0) {
+		pr_info("match only valid in the \'raw\' "
+			"or \'mangle\' tables, not \'%s\'.\n", par->table);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct xt_match rpfilter_mt_reg __read_mostly = {
+	.name		= "rpfilter",
+	.family		= NFPROTO_IPV6,
+	.checkentry	= rpfilter_check,
+	.match		= rpfilter_mt,
+	.matchsize	= sizeof(struct xt_rpfilter_info),
+	.hooks		= (1 << NF_INET_PRE_ROUTING),
+	.me		= THIS_MODULE
+};
+
+static int __init rpfilter_mt_init(void)
+{
+	return xt_register_match(&rpfilter_mt_reg);
+}
+
+static void __exit rpfilter_mt_exit(void)
+{
+	xt_unregister_match(&rpfilter_mt_reg);
+}
+
+module_init(rpfilter_mt_init);
+module_exit(rpfilter_mt_exit);

net/ipv6/netfilter/ip6t_rt.c

@@ -0,0 +1,225 @@
+/* Kernel module to match ROUTING parameters. */
+
+/* (C) 2001-2002 Andras Kis-Szabo <kisza@sch.bme.hu>
+ *
+ * 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.
+ */
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/types.h>
+#include <net/checksum.h>
+#include <net/ipv6.h>
+
+#include <asm/byteorder.h>
+
+#include <linux/netfilter/x_tables.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/netfilter_ipv6/ip6t_rt.h>
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Xtables: IPv6 Routing Header match");
+MODULE_AUTHOR("Andras Kis-Szabo <kisza@sch.bme.hu>");
+
+/* Returns 1 if the id is matched by the range, 0 otherwise */
+static inline bool
+segsleft_match(u_int32_t min, u_int32_t max, u_int32_t id, bool invert)
+{
+	bool r;
+	pr_debug("segsleft_match:%c 0x%x <= 0x%x <= 0x%x\n",
+		 invert ? '!' : ' ', min, id, max);
+	r = (id >= min && id <= max) ^ invert;
+	pr_debug(" result %s\n", r ? "PASS" : "FAILED");
+	return r;
+}
+
+static bool rt_mt6(const struct sk_buff *skb, struct xt_action_param *par)
+{
+	struct ipv6_rt_hdr _route;
+	const struct ipv6_rt_hdr *rh;
+	const struct ip6t_rt *rtinfo = par->matchinfo;
+	unsigned int temp;
+	unsigned int ptr = 0;
+	unsigned int hdrlen = 0;
+	bool ret = false;
+	struct in6_addr _addr;
+	const struct in6_addr *ap;
+	int err;
+
+	err = ipv6_find_hdr(skb, &ptr, NEXTHDR_ROUTING, NULL, NULL);
+	if (err < 0) {
+		if (err != -ENOENT)
+			par->hotdrop = true;
+		return false;
+	}
+
+	rh = skb_header_pointer(skb, ptr, sizeof(_route), &_route);
+	if (rh == NULL) {
+		par->hotdrop = true;
+		return false;
+	}
+
+	hdrlen = ipv6_optlen(rh);
+	if (skb->len - ptr < hdrlen) {
+		/* Pcket smaller than its length field */
+		return false;
+	}
+
+	pr_debug("IPv6 RT LEN %u %u ", hdrlen, rh->hdrlen);
+	pr_debug("TYPE %04X ", rh->type);
+	pr_debug("SGS_LEFT %u %02X\n", rh->segments_left, rh->segments_left);
+
+	pr_debug("IPv6 RT segsleft %02X ",
+		 segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
+				rh->segments_left,
+				!!(rtinfo->invflags & IP6T_RT_INV_SGS)));
+	pr_debug("type %02X %02X %02X ",
+		 rtinfo->rt_type, rh->type,
+		 (!(rtinfo->flags & IP6T_RT_TYP) ||
+		  ((rtinfo->rt_type == rh->type) ^
+		   !!(rtinfo->invflags & IP6T_RT_INV_TYP))));
+	pr_debug("len %02X %04X %02X ",
+		 rtinfo->hdrlen, hdrlen,
+		 !(rtinfo->flags & IP6T_RT_LEN) ||
+		  ((rtinfo->hdrlen == hdrlen) ^
+		   !!(rtinfo->invflags & IP6T_RT_INV_LEN)));
+	pr_debug("res %02X %02X %02X ",
+		 rtinfo->flags & IP6T_RT_RES,
+		 ((const struct rt0_hdr *)rh)->reserved,
+		 !((rtinfo->flags & IP6T_RT_RES) &&
+		   (((const struct rt0_hdr *)rh)->reserved)));
+
+	ret = (rh != NULL) &&
+	      (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1],
+			      rh->segments_left,
+			      !!(rtinfo->invflags & IP6T_RT_INV_SGS))) &&
+	      (!(rtinfo->flags & IP6T_RT_LEN) ||
+	       ((rtinfo->hdrlen == hdrlen) ^
+		!!(rtinfo->invflags & IP6T_RT_INV_LEN))) &&
+	      (!(rtinfo->flags & IP6T_RT_TYP) ||
+	       ((rtinfo->rt_type == rh->type) ^
+		!!(rtinfo->invflags & IP6T_RT_INV_TYP)));
+
+	if (ret && (rtinfo->flags & IP6T_RT_RES)) {
+		const u_int32_t *rp;
+		u_int32_t _reserved;
+		rp = skb_header_pointer(skb,
+					ptr + offsetof(struct rt0_hdr,
+						       reserved),
+					sizeof(_reserved),
+					&_reserved);
+
+		ret = (*rp == 0);
+	}
+
+	pr_debug("#%d ", rtinfo->addrnr);
+	if (!(rtinfo->flags & IP6T_RT_FST)) {
+		return ret;
+	} else if (rtinfo->flags & IP6T_RT_FST_NSTRICT) {
+		pr_debug("Not strict ");
+		if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
+			pr_debug("There isn't enough space\n");
+			return false;
+		} else {
+			unsigned int i = 0;
+
+			pr_debug("#%d ", rtinfo->addrnr);
+			for (temp = 0;
+			     temp < (unsigned int)((hdrlen - 8) / 16);
+			     temp++) {
+				ap = skb_header_pointer(skb,
+							ptr
+							+ sizeof(struct rt0_hdr)
+							+ temp * sizeof(_addr),
+							sizeof(_addr),
+							&_addr);
+
+				BUG_ON(ap == NULL);
+
+				if (ipv6_addr_equal(ap, &rtinfo->addrs[i])) {
+					pr_debug("i=%d temp=%d;\n", i, temp);
+					i++;
+				}
+				if (i == rtinfo->addrnr)
+					break;
+			}
+			pr_debug("i=%d #%d\n", i, rtinfo->addrnr);
+			if (i == rtinfo->addrnr)
+				return ret;
+			else
+				return false;
+		}
+	} else {
+		pr_debug("Strict ");
+		if (rtinfo->addrnr > (unsigned int)((hdrlen - 8) / 16)) {
+			pr_debug("There isn't enough space\n");
+			return false;
+		} else {
+			pr_debug("#%d ", rtinfo->addrnr);
+			for (temp = 0; temp < rtinfo->addrnr; temp++) {
+				ap = skb_header_pointer(skb,
+							ptr
+							+ sizeof(struct rt0_hdr)
+							+ temp * sizeof(_addr),
+							sizeof(_addr),
+							&_addr);
+				BUG_ON(ap == NULL);
+
+				if (!ipv6_addr_equal(ap, &rtinfo->addrs[temp]))
+					break;
+			}
+			pr_debug("temp=%d #%d\n", temp, rtinfo->addrnr);
+			if (temp == rtinfo->addrnr &&
+			    temp == (unsigned int)((hdrlen - 8) / 16))
+				return ret;
+			else
+				return false;
+		}
+	}
+
+	return false;
+}
+
+static int rt_mt6_check(const struct xt_mtchk_param *par)
+{
+	const struct ip6t_rt *rtinfo = par->matchinfo;
+
+	if (rtinfo->invflags & ~IP6T_RT_INV_MASK) {
+		pr_debug("unknown flags %X\n", rtinfo->invflags);
+		return -EINVAL;
+	}
+	if ((rtinfo->flags & (IP6T_RT_RES | IP6T_RT_FST_MASK)) &&
+	    (!(rtinfo->flags & IP6T_RT_TYP) ||
+	     (rtinfo->rt_type != 0) ||
+	     (rtinfo->invflags & IP6T_RT_INV_TYP))) {
+		pr_debug("`--rt-type 0' required before `--rt-0-*'");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct xt_match rt_mt6_reg __read_mostly = {
+	.name		= "rt",
+	.family		= NFPROTO_IPV6,
+	.match		= rt_mt6,
+	.matchsize	= sizeof(struct ip6t_rt),
+	.checkentry	= rt_mt6_check,
+	.me		= THIS_MODULE,
+};
+
+static int __init rt_mt6_init(void)
+{
+	return xt_register_match(&rt_mt6_reg);
+}
+
+static void __exit rt_mt6_exit(void)
+{
+	xt_unregister_match(&rt_mt6_reg);
+}
+
+module_init(rt_mt6_init);
+module_exit(rt_mt6_exit);

net/ipv6/netfilter/ip6table_filter.c

@@ -0,0 +1,106 @@
+/*
+ * This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x.
+ *
+ * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
+ * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@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/module.h>
+#include <linux/moduleparam.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
+MODULE_DESCRIPTION("ip6tables filter table");
+
+#define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \
+			    (1 << NF_INET_FORWARD) | \
+			    (1 << NF_INET_LOCAL_OUT))
+
+static const struct xt_table packet_filter = {
+	.name		= "filter",
+	.valid_hooks	= FILTER_VALID_HOOKS,
+	.me		= THIS_MODULE,
+	.af		= NFPROTO_IPV6,
+	.priority	= NF_IP6_PRI_FILTER,
+};
+
+/* The work comes in here from netfilter.c. */
+static unsigned int
+ip6table_filter_hook(unsigned int hook, struct sk_buff *skb,
+		     const struct net_device *in, const struct net_device *out,
+		     int (*okfn)(struct sk_buff *))
+{
+	const struct net *net = dev_net((in != NULL) ? in : out);
+
+	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_filter);
+}
+
+static struct nf_hook_ops *filter_ops __read_mostly;
+
+/* Default to forward because I got too much mail already. */
+static bool forward = true;
+module_param(forward, bool, 0000);
+
+static int __net_init ip6table_filter_net_init(struct net *net)
+{
+	struct ip6t_replace *repl;
+
+	repl = ip6t_alloc_initial_table(&packet_filter);
+	if (repl == NULL)
+		return -ENOMEM;
+	/* Entry 1 is the FORWARD hook */
+	((struct ip6t_standard *)repl->entries)[1].target.verdict =
+		forward ? -NF_ACCEPT - 1 : -NF_DROP - 1;
+
+	net->ipv6.ip6table_filter =
+		ip6t_register_table(net, &packet_filter, repl);
+	kfree(repl);
+	return PTR_RET(net->ipv6.ip6table_filter);
+}
+
+static void __net_exit ip6table_filter_net_exit(struct net *net)
+{
+	ip6t_unregister_table(net, net->ipv6.ip6table_filter);
+}
+
+static struct pernet_operations ip6table_filter_net_ops = {
+	.init = ip6table_filter_net_init,
+	.exit = ip6table_filter_net_exit,
+};
+
+static int __init ip6table_filter_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&ip6table_filter_net_ops);
+	if (ret < 0)
+		return ret;
+
+	/* Register hooks */
+	filter_ops = xt_hook_link(&packet_filter, ip6table_filter_hook);
+	if (IS_ERR(filter_ops)) {
+		ret = PTR_ERR(filter_ops);
+		goto cleanup_table;
+	}
+
+	return ret;
+
+ cleanup_table:
+	unregister_pernet_subsys(&ip6table_filter_net_ops);
+	return ret;
+}
+
+static void __exit ip6table_filter_fini(void)
+{
+	xt_hook_unlink(&packet_filter, filter_ops);
+	unregister_pernet_subsys(&ip6table_filter_net_ops);
+}
+
+module_init(ip6table_filter_init);
+module_exit(ip6table_filter_fini);

net/ipv6/netfilter/ip6table_mangle.c

@@ -0,0 +1,146 @@
+/*
+ * IPv6 packet mangling table, a port of the IPv4 mangle table to IPv6
+ *
+ * Copyright (C) 2000-2001 by Harald Welte <laforge@gnumonks.org>
+ * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@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/module.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
+#include <net/ipv6.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
+MODULE_DESCRIPTION("ip6tables mangle table");
+
+#define MANGLE_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | \
+			    (1 << NF_INET_LOCAL_IN) | \
+			    (1 << NF_INET_FORWARD) | \
+			    (1 << NF_INET_LOCAL_OUT) | \
+			    (1 << NF_INET_POST_ROUTING))
+
+static const struct xt_table packet_mangler = {
+	.name		= "mangle",
+	.valid_hooks	= MANGLE_VALID_HOOKS,
+	.me		= THIS_MODULE,
+	.af		= NFPROTO_IPV6,
+	.priority	= NF_IP6_PRI_MANGLE,
+};
+
+static unsigned int
+ip6t_mangle_out(struct sk_buff *skb, const struct net_device *out)
+{
+	unsigned int ret;
+	struct in6_addr saddr, daddr;
+	u_int8_t hop_limit;
+	u_int32_t flowlabel, mark;
+	int err;
+#if 0
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct iphdr) ||
+	    ip_hdrlen(skb) < sizeof(struct iphdr)) {
+		net_warn_ratelimited("ip6t_hook: happy cracking\n");
+		return NF_ACCEPT;
+	}
+#endif
+
+	/* save source/dest address, mark, hoplimit, flowlabel, priority,  */
+	memcpy(&saddr, &ipv6_hdr(skb)->saddr, sizeof(saddr));
+	memcpy(&daddr, &ipv6_hdr(skb)->daddr, sizeof(daddr));
+	mark = skb->mark;
+	hop_limit = ipv6_hdr(skb)->hop_limit;
+
+	/* flowlabel and prio (includes version, which shouldn't change either */
+	flowlabel = *((u_int32_t *)ipv6_hdr(skb));
+
+	ret = ip6t_do_table(skb, NF_INET_LOCAL_OUT, NULL, out,
+			    dev_net(out)->ipv6.ip6table_mangle);
+
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (!ipv6_addr_equal(&ipv6_hdr(skb)->saddr, &saddr) ||
+	     !ipv6_addr_equal(&ipv6_hdr(skb)->daddr, &daddr) ||
+	     skb->mark != mark ||
+	     ipv6_hdr(skb)->hop_limit != hop_limit ||
+	     flowlabel != *((u_int32_t *)ipv6_hdr(skb)))) {
+		err = ip6_route_me_harder(skb);
+		if (err < 0)
+			ret = NF_DROP_ERR(err);
+	}
+
+	return ret;
+}
+
+/* The work comes in here from netfilter.c. */
+static unsigned int
+ip6table_mangle_hook(unsigned int hook, struct sk_buff *skb,
+		     const struct net_device *in, const struct net_device *out,
+		     int (*okfn)(struct sk_buff *))
+{
+	if (hook == NF_INET_LOCAL_OUT)
+		return ip6t_mangle_out(skb, out);
+	if (hook == NF_INET_POST_ROUTING)
+		return ip6t_do_table(skb, hook, in, out,
+				     dev_net(out)->ipv6.ip6table_mangle);
+	/* INPUT/FORWARD */
+	return ip6t_do_table(skb, hook, in, out,
+			     dev_net(in)->ipv6.ip6table_mangle);
+}
+
+static struct nf_hook_ops *mangle_ops __read_mostly;
+static int __net_init ip6table_mangle_net_init(struct net *net)
+{
+	struct ip6t_replace *repl;
+
+	repl = ip6t_alloc_initial_table(&packet_mangler);
+	if (repl == NULL)
+		return -ENOMEM;
+	net->ipv6.ip6table_mangle =
+		ip6t_register_table(net, &packet_mangler, repl);
+	kfree(repl);
+	return PTR_RET(net->ipv6.ip6table_mangle);
+}
+
+static void __net_exit ip6table_mangle_net_exit(struct net *net)
+{
+	ip6t_unregister_table(net, net->ipv6.ip6table_mangle);
+}
+
+static struct pernet_operations ip6table_mangle_net_ops = {
+	.init = ip6table_mangle_net_init,
+	.exit = ip6table_mangle_net_exit,
+};
+
+static int __init ip6table_mangle_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&ip6table_mangle_net_ops);
+	if (ret < 0)
+		return ret;
+
+	/* Register hooks */
+	mangle_ops = xt_hook_link(&packet_mangler, ip6table_mangle_hook);
+	if (IS_ERR(mangle_ops)) {
+		ret = PTR_ERR(mangle_ops);
+		goto cleanup_table;
+	}
+
+	return ret;
+
+ cleanup_table:
+	unregister_pernet_subsys(&ip6table_mangle_net_ops);
+	return ret;
+}
+
+static void __exit ip6table_mangle_fini(void)
+{
+	xt_hook_unlink(&packet_mangler, mangle_ops);
+	unregister_pernet_subsys(&ip6table_mangle_net_ops);
+}
+
+module_init(ip6table_mangle_init);
+module_exit(ip6table_mangle_fini);

net/ipv6/netfilter/ip6table_nat.c

@@ -0,0 +1,337 @@
+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * 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.
+ *
+ * Based on Rusty Russell's IPv4 NAT code. Development of IPv6 NAT
+ * funded by Astaro.
+ */
+
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+
+static const struct xt_table nf_nat_ipv6_table = {
+	.name		= "nat",
+	.valid_hooks	= (1 << NF_INET_PRE_ROUTING) |
+			  (1 << NF_INET_POST_ROUTING) |
+			  (1 << NF_INET_LOCAL_OUT) |
+			  (1 << NF_INET_LOCAL_IN),
+	.me		= THIS_MODULE,
+	.af		= NFPROTO_IPV6,
+};
+
+static unsigned int alloc_null_binding(struct nf_conn *ct, unsigned int hooknum)
+{
+	/* Force range to this IP; let proto decide mapping for
+	 * per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED).
+	 */
+	struct nf_nat_range range;
+
+	range.flags = 0;
+	pr_debug("Allocating NULL binding for %p (%pI6)\n", ct,
+		 HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ?
+		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip6 :
+		 &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip6);
+
+	return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum));
+}
+
+static unsigned int nf_nat_rule_find(struct sk_buff *skb, unsigned int hooknum,
+				     const struct net_device *in,
+				     const struct net_device *out,
+				     struct nf_conn *ct)
+{
+	struct net *net = nf_ct_net(ct);
+	unsigned int ret;
+
+	ret = ip6t_do_table(skb, hooknum, in, out, net->ipv6.ip6table_nat);
+	if (ret == NF_ACCEPT) {
+		if (!nf_nat_initialized(ct, HOOK2MANIP(hooknum)))
+			ret = alloc_null_binding(ct, hooknum);
+	}
+	return ret;
+}
+
+static unsigned int
+nf_nat_ipv6_fn(unsigned int hooknum,
+	       struct sk_buff *skb,
+	       const struct net_device *in,
+	       const struct net_device *out,
+	       int (*okfn)(struct sk_buff *))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn_nat *nat;
+	enum nf_nat_manip_type maniptype = HOOK2MANIP(hooknum);
+	__be16 frag_off;
+	int hdrlen;
+	u8 nexthdr;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	/* Can't track?  It's not due to stress, or conntrack would
+	 * have dropped it.  Hence it's the user's responsibilty to
+	 * packet filter it out, or implement conntrack/NAT for that
+	 * protocol. 8) --RR
+	 */
+	if (!ct)
+		return NF_ACCEPT;
+
+	/* Don't try to NAT if this packet is not conntracked */
+	if (nf_ct_is_untracked(ct))
+		return NF_ACCEPT;
+
+	nat = nfct_nat(ct);
+	if (!nat) {
+		/* NAT module was loaded late. */
+		if (nf_ct_is_confirmed(ct))
+			return NF_ACCEPT;
+		nat = nf_ct_ext_add(ct, NF_CT_EXT_NAT, GFP_ATOMIC);
+		if (nat == NULL) {
+			pr_debug("failed to add NAT extension\n");
+			return NF_ACCEPT;
+		}
+	}
+
+	switch (ctinfo) {
+	case IP_CT_RELATED:
+	case IP_CT_RELATED_REPLY:
+		nexthdr = ipv6_hdr(skb)->nexthdr;
+		hdrlen = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr),
+					  &nexthdr, &frag_off);
+
+		if (hdrlen >= 0 && nexthdr == IPPROTO_ICMPV6) {
+			if (!nf_nat_icmpv6_reply_translation(skb, ct, ctinfo,
+							     hooknum, hdrlen))
+				return NF_DROP;
+			else
+				return NF_ACCEPT;
+		}
+		/* Fall thru... (Only ICMPs can be IP_CT_IS_REPLY) */
+	case IP_CT_NEW:
+		/* Seen it before?  This can happen for loopback, retrans,
+		 * or local packets.
+		 */
+		if (!nf_nat_initialized(ct, maniptype)) {
+			unsigned int ret;
+
+			ret = nf_nat_rule_find(skb, hooknum, in, out, ct);
+			if (ret != NF_ACCEPT)
+				return ret;
+		} else {
+			pr_debug("Already setup manip %s for ct %p\n",
+				 maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST",
+				 ct);
+			if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+				goto oif_changed;
+		}
+		break;
+
+	default:
+		/* ESTABLISHED */
+		NF_CT_ASSERT(ctinfo == IP_CT_ESTABLISHED ||
+			     ctinfo == IP_CT_ESTABLISHED_REPLY);
+		if (nf_nat_oif_changed(hooknum, ctinfo, nat, out))
+			goto oif_changed;
+	}
+
+	return nf_nat_packet(ct, ctinfo, hooknum, skb);
+
+oif_changed:
+	nf_ct_kill_acct(ct, ctinfo, skb);
+	return NF_DROP;
+}
+
+static unsigned int
+nf_nat_ipv6_in(unsigned int hooknum,
+	       struct sk_buff *skb,
+	       const struct net_device *in,
+	       const struct net_device *out,
+	       int (*okfn)(struct sk_buff *))
+{
+	unsigned int ret;
+	struct in6_addr daddr = ipv6_hdr(skb)->daddr;
+
+	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    ipv6_addr_cmp(&daddr, &ipv6_hdr(skb)->daddr))
+		skb_dst_drop(skb);
+
+	return ret;
+}
+
+static unsigned int
+nf_nat_ipv6_out(unsigned int hooknum,
+		struct sk_buff *skb,
+		const struct net_device *in,
+		const struct net_device *out,
+		int (*okfn)(struct sk_buff *))
+{
+#ifdef CONFIG_XFRM
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int err;
+#endif
+	unsigned int ret;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+#ifdef CONFIG_XFRM
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    !(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.src.u3,
+				      &ct->tuplehash[!dir].tuple.dst.u3) ||
+		    (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
+		     ct->tuplehash[dir].tuple.src.u.all !=
+		     ct->tuplehash[!dir].tuple.dst.u.all)) {
+			err = nf_xfrm_me_harder(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+	}
+#endif
+	return ret;
+}
+
+static unsigned int
+nf_nat_ipv6_local_fn(unsigned int hooknum,
+		     struct sk_buff *skb,
+		     const struct net_device *in,
+		     const struct net_device *out,
+		     int (*okfn)(struct sk_buff *))
+{
+	const struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int ret;
+	int err;
+
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr))
+		return NF_ACCEPT;
+
+	ret = nf_nat_ipv6_fn(hooknum, skb, in, out, okfn);
+	if (ret != NF_DROP && ret != NF_STOLEN &&
+	    (ct = nf_ct_get(skb, &ctinfo)) != NULL) {
+		enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+
+		if (!nf_inet_addr_cmp(&ct->tuplehash[dir].tuple.dst.u3,
+				      &ct->tuplehash[!dir].tuple.src.u3)) {
+			err = ip6_route_me_harder(skb);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#ifdef CONFIG_XFRM
+		else if (!(IP6CB(skb)->flags & IP6SKB_XFRM_TRANSFORMED) &&
+			 ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMPV6 &&
+			 ct->tuplehash[dir].tuple.dst.u.all !=
+			 ct->tuplehash[!dir].tuple.src.u.all) {
+			err = nf_xfrm_me_harder(skb, AF_INET6);
+			if (err < 0)
+				ret = NF_DROP_ERR(err);
+		}
+#endif
+	}
+	return ret;
+}
+
+static struct nf_hook_ops nf_nat_ipv6_ops[] __read_mostly = {
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv6_in,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv6_out,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP6_PRI_NAT_SRC,
+	},
+	/* Before packet filtering, change destination */
+	{
+		.hook		= nf_nat_ipv6_local_fn,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_NAT_DST,
+	},
+	/* After packet filtering, change source */
+	{
+		.hook		= nf_nat_ipv6_fn,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP6_PRI_NAT_SRC,
+	},
+};
+
+static int __net_init ip6table_nat_net_init(struct net *net)
+{
+	struct ip6t_replace *repl;
+
+	repl = ip6t_alloc_initial_table(&nf_nat_ipv6_table);
+	if (repl == NULL)
+		return -ENOMEM;
+	net->ipv6.ip6table_nat = ip6t_register_table(net, &nf_nat_ipv6_table, repl);
+	kfree(repl);
+	return PTR_RET(net->ipv6.ip6table_nat);
+}
+
+static void __net_exit ip6table_nat_net_exit(struct net *net)
+{
+	ip6t_unregister_table(net, net->ipv6.ip6table_nat);
+}
+
+static struct pernet_operations ip6table_nat_net_ops = {
+	.init	= ip6table_nat_net_init,
+	.exit	= ip6table_nat_net_exit,
+};
+
+static int __init ip6table_nat_init(void)
+{
+	int err;
+
+	err = register_pernet_subsys(&ip6table_nat_net_ops);
+	if (err < 0)
+		goto err1;
+
+	err = nf_register_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+	if (err < 0)
+		goto err2;
+	return 0;
+
+err2:
+	unregister_pernet_subsys(&ip6table_nat_net_ops);
+err1:
+	return err;
+}
+
+static void __exit ip6table_nat_exit(void)
+{
+	nf_unregister_hooks(nf_nat_ipv6_ops, ARRAY_SIZE(nf_nat_ipv6_ops));
+	unregister_pernet_subsys(&ip6table_nat_net_ops);
+}
+
+module_init(ip6table_nat_init);
+module_exit(ip6table_nat_exit);
+
+MODULE_LICENSE("GPL");

net/ipv6/netfilter/ip6table_raw.c

@@ -0,0 +1,86 @@
+/*
+ * IPv6 raw table, a port of the IPv4 raw table to IPv6
+ *
+ * Copyright (C) 2003 Jozsef Kadlecsik <kadlec@blackhole.kfki.hu>
+ */
+#include <linux/module.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
+
+#define RAW_VALID_HOOKS ((1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT))
+
+static const struct xt_table packet_raw = {
+	.name = "raw",
+	.valid_hooks = RAW_VALID_HOOKS,
+	.me = THIS_MODULE,
+	.af = NFPROTO_IPV6,
+	.priority = NF_IP6_PRI_RAW,
+};
+
+/* The work comes in here from netfilter.c. */
+static unsigned int
+ip6table_raw_hook(unsigned int hook, struct sk_buff *skb,
+		  const struct net_device *in, const struct net_device *out,
+		  int (*okfn)(struct sk_buff *))
+{
+	const struct net *net = dev_net((in != NULL) ? in : out);
+
+	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_raw);
+}
+
+static struct nf_hook_ops *rawtable_ops __read_mostly;
+
+static int __net_init ip6table_raw_net_init(struct net *net)
+{
+	struct ip6t_replace *repl;
+
+	repl = ip6t_alloc_initial_table(&packet_raw);
+	if (repl == NULL)
+		return -ENOMEM;
+	net->ipv6.ip6table_raw =
+		ip6t_register_table(net, &packet_raw, repl);
+	kfree(repl);
+	return PTR_RET(net->ipv6.ip6table_raw);
+}
+
+static void __net_exit ip6table_raw_net_exit(struct net *net)
+{
+	ip6t_unregister_table(net, net->ipv6.ip6table_raw);
+}
+
+static struct pernet_operations ip6table_raw_net_ops = {
+	.init = ip6table_raw_net_init,
+	.exit = ip6table_raw_net_exit,
+};
+
+static int __init ip6table_raw_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&ip6table_raw_net_ops);
+	if (ret < 0)
+		return ret;
+
+	/* Register hooks */
+	rawtable_ops = xt_hook_link(&packet_raw, ip6table_raw_hook);
+	if (IS_ERR(rawtable_ops)) {
+		ret = PTR_ERR(rawtable_ops);
+		goto cleanup_table;
+	}
+
+	return ret;
+
+ cleanup_table:
+	unregister_pernet_subsys(&ip6table_raw_net_ops);
+	return ret;
+}
+
+static void __exit ip6table_raw_fini(void)
+{
+	xt_hook_unlink(&packet_raw, rawtable_ops);
+	unregister_pernet_subsys(&ip6table_raw_net_ops);
+}
+
+module_init(ip6table_raw_init);
+module_exit(ip6table_raw_fini);
+MODULE_LICENSE("GPL");

net/ipv6/netfilter/ip6table_security.c

@@ -0,0 +1,102 @@
+/*
+ * "security" table for IPv6
+ *
+ * This is for use by Mandatory Access Control (MAC) security models,
+ * which need to be able to manage security policy in separate context
+ * to DAC.
+ *
+ * Based on iptable_mangle.c
+ *
+ * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling
+ * Copyright (C) 2000-2004 Netfilter Core Team <coreteam <at> netfilter.org>
+ * Copyright (C) 2008 Red Hat, Inc., James Morris <jmorris <at> redhat.com>
+ *
+ * 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/module.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <linux/slab.h>
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("James Morris <jmorris <at> redhat.com>");
+MODULE_DESCRIPTION("ip6tables security table, for MAC rules");
+
+#define SECURITY_VALID_HOOKS	(1 << NF_INET_LOCAL_IN) | \
+				(1 << NF_INET_FORWARD) | \
+				(1 << NF_INET_LOCAL_OUT)
+
+static const struct xt_table security_table = {
+	.name		= "security",
+	.valid_hooks	= SECURITY_VALID_HOOKS,
+	.me		= THIS_MODULE,
+	.af		= NFPROTO_IPV6,
+	.priority	= NF_IP6_PRI_SECURITY,
+};
+
+static unsigned int
+ip6table_security_hook(unsigned int hook, struct sk_buff *skb,
+		       const struct net_device *in,
+		       const struct net_device *out,
+		       int (*okfn)(struct sk_buff *))
+{
+	const struct net *net = dev_net((in != NULL) ? in : out);
+
+	return ip6t_do_table(skb, hook, in, out, net->ipv6.ip6table_security);
+}
+
+static struct nf_hook_ops *sectbl_ops __read_mostly;
+
+static int __net_init ip6table_security_net_init(struct net *net)
+{
+	struct ip6t_replace *repl;
+
+	repl = ip6t_alloc_initial_table(&security_table);
+	if (repl == NULL)
+		return -ENOMEM;
+	net->ipv6.ip6table_security =
+		ip6t_register_table(net, &security_table, repl);
+	kfree(repl);
+	return PTR_RET(net->ipv6.ip6table_security);
+}
+
+static void __net_exit ip6table_security_net_exit(struct net *net)
+{
+	ip6t_unregister_table(net, net->ipv6.ip6table_security);
+}
+
+static struct pernet_operations ip6table_security_net_ops = {
+	.init = ip6table_security_net_init,
+	.exit = ip6table_security_net_exit,
+};
+
+static int __init ip6table_security_init(void)
+{
+	int ret;
+
+	ret = register_pernet_subsys(&ip6table_security_net_ops);
+	if (ret < 0)
+		return ret;
+
+	sectbl_ops = xt_hook_link(&security_table, ip6table_security_hook);
+	if (IS_ERR(sectbl_ops)) {
+		ret = PTR_ERR(sectbl_ops);
+		goto cleanup_table;
+	}
+
+	return ret;
+
+cleanup_table:
+	unregister_pernet_subsys(&ip6table_security_net_ops);
+	return ret;
+}
+
+static void __exit ip6table_security_fini(void)
+{
+	xt_hook_unlink(&security_table, sectbl_ops);
+	unregister_pernet_subsys(&ip6table_security_net_ops);
+}
+
+module_init(ip6table_security_init);
+module_exit(ip6table_security_fini);

net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c

@@ -0,0 +1,536 @@
+/*
+ * Copyright (C)2004 USAGI/WIDE Project
+ *
+ * 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.
+ *
+ * Author:
+ *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ */
+
+#include <linux/types.h>
+#include <linux/ipv6.h>
+#include <linux/in6.h>
+#include <linux/netfilter.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/icmp.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+#include <linux/netfilter_bridge.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_ipv6/ip6_tables.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_l3proto.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
+#include <net/netfilter/nf_nat_helper.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+#include <net/netfilter/nf_log.h>
+
+static bool ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
+			      struct nf_conntrack_tuple *tuple)
+{
+	const u_int32_t *ap;
+	u_int32_t _addrs[8];
+
+	ap = skb_header_pointer(skb, nhoff + offsetof(struct ipv6hdr, saddr),
+				sizeof(_addrs), _addrs);
+	if (ap == NULL)
+		return false;
+
+	memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
+	memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
+
+	return true;
+}
+
+static bool ipv6_invert_tuple(struct nf_conntrack_tuple *tuple,
+			      const struct nf_conntrack_tuple *orig)
+{
+	memcpy(tuple->src.u3.ip6, orig->dst.u3.ip6, sizeof(tuple->src.u3.ip6));
+	memcpy(tuple->dst.u3.ip6, orig->src.u3.ip6, sizeof(tuple->dst.u3.ip6));
+
+	return true;
+}
+
+static int ipv6_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
+{
+	return seq_printf(s, "src=%pI6 dst=%pI6 ",
+			  tuple->src.u3.ip6, tuple->dst.u3.ip6);
+}
+
+static int ipv6_get_l4proto(const struct sk_buff *skb, unsigned int nhoff,
+			    unsigned int *dataoff, u_int8_t *protonum)
+{
+	unsigned int extoff = nhoff + sizeof(struct ipv6hdr);
+	__be16 frag_off;
+	int protoff;
+	u8 nexthdr;
+
+	if (skb_copy_bits(skb, nhoff + offsetof(struct ipv6hdr, nexthdr),
+			  &nexthdr, sizeof(nexthdr)) != 0) {
+		pr_debug("ip6_conntrack_core: can't get nexthdr\n");
+		return -NF_ACCEPT;
+	}
+	protoff = ipv6_skip_exthdr(skb, extoff, &nexthdr, &frag_off);
+	/*
+	 * (protoff == skb->len) means the packet has not data, just
+	 * IPv6 and possibly extensions headers, but it is tracked anyway
+	 */
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		pr_debug("ip6_conntrack_core: can't find proto in pkt\n");
+		return -NF_ACCEPT;
+	}
+
+	*dataoff = protoff;
+	*protonum = nexthdr;
+	return NF_ACCEPT;
+}
+
+static unsigned int ipv6_helper(unsigned int hooknum,
+				struct sk_buff *skb,
+				const struct net_device *in,
+				const struct net_device *out,
+				int (*okfn)(struct sk_buff *))
+{
+	struct nf_conn *ct;
+	const struct nf_conn_help *help;
+	const struct nf_conntrack_helper *helper;
+	enum ip_conntrack_info ctinfo;
+	__be16 frag_off;
+	int protoff;
+	u8 nexthdr;
+
+	/* This is where we call the helper: as the packet goes out. */
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+		return NF_ACCEPT;
+
+	help = nfct_help(ct);
+	if (!help)
+		return NF_ACCEPT;
+	/* rcu_read_lock()ed by nf_hook_slow */
+	helper = rcu_dereference(help->helper);
+	if (!helper)
+		return NF_ACCEPT;
+
+	nexthdr = ipv6_hdr(skb)->nexthdr;
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr,
+				   &frag_off);
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		pr_debug("proto header not found\n");
+		return NF_ACCEPT;
+	}
+
+	return helper->help(skb, protoff, ct, ctinfo);
+}
+
+static unsigned int ipv6_confirm(unsigned int hooknum,
+				 struct sk_buff *skb,
+				 const struct net_device *in,
+				 const struct net_device *out,
+				 int (*okfn)(struct sk_buff *))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned char pnum = ipv6_hdr(skb)->nexthdr;
+	int protoff;
+	__be16 frag_off;
+
+	ct = nf_ct_get(skb, &ctinfo);
+	if (!ct || ctinfo == IP_CT_RELATED_REPLY)
+		goto out;
+
+	protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum,
+				   &frag_off);
+	if (protoff < 0 || (frag_off & htons(~0x7)) != 0) {
+		pr_debug("proto header not found\n");
+		goto out;
+	}
+
+	/* adjust seqs for loopback traffic only in outgoing direction */
+	if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) &&
+	    !nf_is_loopback_packet(skb)) {
+		typeof(nf_nat_seq_adjust_hook) seq_adjust;
+
+		seq_adjust = rcu_dereference(nf_nat_seq_adjust_hook);
+		if (!seq_adjust ||
+		    !seq_adjust(skb, ct, ctinfo, protoff)) {
+			NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop);
+			return NF_DROP;
+		}
+	}
+out:
+	/* We've seen it coming out the other side: confirm it */
+	return nf_conntrack_confirm(skb);
+}
+
+static unsigned int __ipv6_conntrack_in(struct net *net,
+					unsigned int hooknum,
+					struct sk_buff *skb,
+					const struct net_device *in,
+					const struct net_device *out,
+					int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *reasm = skb->nfct_reasm;
+	const struct nf_conn_help *help;
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+
+	/* This packet is fragmented and has reassembled packet. */
+	if (reasm) {
+		/* Reassembled packet isn't parsed yet ? */
+		if (!reasm->nfct) {
+			unsigned int ret;
+
+			ret = nf_conntrack_in(net, PF_INET6, hooknum, reasm);
+			if (ret != NF_ACCEPT)
+				return ret;
+		}
+
+		/* Conntrack helpers need the entire reassembled packet in the
+		 * POST_ROUTING hook. In case of unconfirmed connections NAT
+		 * might reassign a helper, so the entire packet is also
+		 * required.
+		 */
+		ct = nf_ct_get(reasm, &ctinfo);
+		if (ct != NULL && !nf_ct_is_untracked(ct)) {
+			help = nfct_help(ct);
+			if ((help && help->helper) || !nf_ct_is_confirmed(ct)) {
+				nf_conntrack_get_reasm(reasm);
+				NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, reasm,
+					       (struct net_device *)in,
+					       (struct net_device *)out,
+					       okfn, NF_IP6_PRI_CONNTRACK + 1);
+				return NF_DROP_ERR(-ECANCELED);
+			}
+		}
+
+		nf_conntrack_get(reasm->nfct);
+		skb->nfct = reasm->nfct;
+		skb->nfctinfo = reasm->nfctinfo;
+		return NF_ACCEPT;
+	}
+
+	return nf_conntrack_in(net, PF_INET6, hooknum, skb);
+}
+
+static unsigned int ipv6_conntrack_in(unsigned int hooknum,
+				      struct sk_buff *skb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      int (*okfn)(struct sk_buff *))
+{
+	return __ipv6_conntrack_in(dev_net(in), hooknum, skb, in, out, okfn);
+}
+
+static unsigned int ipv6_conntrack_local(unsigned int hooknum,
+					 struct sk_buff *skb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 int (*okfn)(struct sk_buff *))
+{
+	/* root is playing with raw sockets. */
+	if (skb->len < sizeof(struct ipv6hdr)) {
+		net_notice_ratelimited("ipv6_conntrack_local: packet too short\n");
+		return NF_ACCEPT;
+	}
+	return __ipv6_conntrack_in(dev_net(out), hooknum, skb, in, out, okfn);
+}
+
+static struct nf_hook_ops ipv6_conntrack_ops[] __read_mostly = {
+	{
+		.hook		= ipv6_conntrack_in,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_CONNTRACK,
+	},
+	{
+		.hook		= ipv6_conntrack_local,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_CONNTRACK,
+	},
+	{
+		.hook		= ipv6_helper,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
+	},
+	{
+		.hook		= ipv6_confirm,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_POST_ROUTING,
+		.priority	= NF_IP6_PRI_LAST,
+	},
+	{
+		.hook		= ipv6_helper,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP6_PRI_CONNTRACK_HELPER,
+	},
+	{
+		.hook		= ipv6_confirm,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_IN,
+		.priority	= NF_IP6_PRI_LAST-1,
+	},
+};
+
+static int
+ipv6_getorigdst(struct sock *sk, int optval, void __user *user, int *len)
+{
+	const struct inet_sock *inet = inet_sk(sk);
+	const struct ipv6_pinfo *inet6 = inet6_sk(sk);
+	const struct nf_conntrack_tuple_hash *h;
+	struct sockaddr_in6 sin6;
+	struct nf_conntrack_tuple tuple = { .src.l3num = NFPROTO_IPV6 };
+	struct nf_conn *ct;
+
+	tuple.src.u3.in6 = inet6->rcv_saddr;
+	tuple.src.u.tcp.port = inet->inet_sport;
+	tuple.dst.u3.in6 = inet6->daddr;
+	tuple.dst.u.tcp.port = inet->inet_dport;
+	tuple.dst.protonum = sk->sk_protocol;
+
+	if (sk->sk_protocol != IPPROTO_TCP && sk->sk_protocol != IPPROTO_SCTP)
+		return -ENOPROTOOPT;
+
+	if (*len < 0 || (unsigned int) *len < sizeof(sin6))
+		return -EINVAL;
+
+	h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple);
+	if (!h) {
+		pr_debug("IP6T_SO_ORIGINAL_DST: Can't find %pI6c/%u-%pI6c/%u.\n",
+			 &tuple.src.u3.ip6, ntohs(tuple.src.u.tcp.port),
+			 &tuple.dst.u3.ip6, ntohs(tuple.dst.u.tcp.port));
+		return -ENOENT;
+	}
+
+	ct = nf_ct_tuplehash_to_ctrack(h);
+
+	sin6.sin6_family = AF_INET6;
+	sin6.sin6_port = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port;
+	sin6.sin6_flowinfo = inet6->flow_label & IPV6_FLOWINFO_MASK;
+	memcpy(&sin6.sin6_addr,
+		&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6,
+					sizeof(sin6.sin6_addr));
+
+	nf_ct_put(ct);
+	sin6.sin6_scope_id = ipv6_iface_scope_id(&sin6.sin6_addr,
+						 sk->sk_bound_dev_if);
+	return copy_to_user(user, &sin6, sizeof(sin6)) ? -EFAULT : 0;
+}
+
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+
+static int ipv6_tuple_to_nlattr(struct sk_buff *skb,
+				const struct nf_conntrack_tuple *tuple)
+{
+	if (nla_put(skb, CTA_IP_V6_SRC, sizeof(u_int32_t) * 4,
+		    &tuple->src.u3.ip6) ||
+	    nla_put(skb, CTA_IP_V6_DST, sizeof(u_int32_t) * 4,
+		    &tuple->dst.u3.ip6))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static const struct nla_policy ipv6_nla_policy[CTA_IP_MAX+1] = {
+	[CTA_IP_V6_SRC]	= { .len = sizeof(u_int32_t)*4 },
+	[CTA_IP_V6_DST]	= { .len = sizeof(u_int32_t)*4 },
+};
+
+static int ipv6_nlattr_to_tuple(struct nlattr *tb[],
+				struct nf_conntrack_tuple *t)
+{
+	if (!tb[CTA_IP_V6_SRC] || !tb[CTA_IP_V6_DST])
+		return -EINVAL;
+
+	memcpy(&t->src.u3.ip6, nla_data(tb[CTA_IP_V6_SRC]),
+	       sizeof(u_int32_t) * 4);
+	memcpy(&t->dst.u3.ip6, nla_data(tb[CTA_IP_V6_DST]),
+	       sizeof(u_int32_t) * 4);
+
+	return 0;
+}
+
+static int ipv6_nlattr_tuple_size(void)
+{
+	return nla_policy_len(ipv6_nla_policy, CTA_IP_MAX + 1);
+}
+#endif
+
+struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 __read_mostly = {
+	.l3proto		= PF_INET6,
+	.name			= "ipv6",
+	.pkt_to_tuple		= ipv6_pkt_to_tuple,
+	.invert_tuple		= ipv6_invert_tuple,
+	.print_tuple		= ipv6_print_tuple,
+	.get_l4proto		= ipv6_get_l4proto,
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+	.tuple_to_nlattr	= ipv6_tuple_to_nlattr,
+	.nlattr_tuple_size	= ipv6_nlattr_tuple_size,
+	.nlattr_to_tuple	= ipv6_nlattr_to_tuple,
+	.nla_policy		= ipv6_nla_policy,
+#endif
+	.me			= THIS_MODULE,
+};
+
+MODULE_ALIAS("nf_conntrack-" __stringify(AF_INET6));
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>");
+
+static struct nf_sockopt_ops so_getorigdst6 = {
+	.pf		= NFPROTO_IPV6,
+	.get_optmin	= IP6T_SO_ORIGINAL_DST,
+	.get_optmax	= IP6T_SO_ORIGINAL_DST + 1,
+	.get		= ipv6_getorigdst,
+	.owner		= THIS_MODULE,
+};
+
+static int ipv6_net_init(struct net *net)
+{
+	int ret = 0;
+
+	ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_tcp6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_tcp6: pernet registration failed\n");
+		goto out;
+	}
+	ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_udp6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_udp6: pernet registration failed\n");
+		goto cleanup_tcp6;
+	}
+	ret = nf_ct_l4proto_pernet_register(net, &nf_conntrack_l4proto_icmpv6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_icmp6: pernet registration failed\n");
+		goto cleanup_udp6;
+	}
+	ret = nf_ct_l3proto_pernet_register(net, &nf_conntrack_l3proto_ipv6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_ipv6: pernet registration failed.\n");
+		goto cleanup_icmpv6;
+	}
+	return 0;
+ cleanup_icmpv6:
+	nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6);
+ cleanup_udp6:
+	nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6);
+ cleanup_tcp6:
+	nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6);
+ out:
+	return ret;
+}
+
+static void ipv6_net_exit(struct net *net)
+{
+	nf_ct_l3proto_pernet_unregister(net, &nf_conntrack_l3proto_ipv6);
+	nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_icmpv6);
+	nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_udp6);
+	nf_ct_l4proto_pernet_unregister(net, &nf_conntrack_l4proto_tcp6);
+}
+
+static struct pernet_operations ipv6_net_ops = {
+	.init = ipv6_net_init,
+	.exit = ipv6_net_exit,
+};
+
+static int __init nf_conntrack_l3proto_ipv6_init(void)
+{
+	int ret = 0;
+
+	need_conntrack();
+	nf_defrag_ipv6_enable();
+
+	ret = nf_register_sockopt(&so_getorigdst6);
+	if (ret < 0) {
+		pr_err("Unable to register netfilter socket option\n");
+		return ret;
+	}
+
+	ret = register_pernet_subsys(&ipv6_net_ops);
+	if (ret < 0)
+		goto cleanup_sockopt;
+
+	ret = nf_register_hooks(ipv6_conntrack_ops,
+				ARRAY_SIZE(ipv6_conntrack_ops));
+	if (ret < 0) {
+		pr_err("nf_conntrack_ipv6: can't register pre-routing defrag "
+		       "hook.\n");
+		goto cleanup_pernet;
+	}
+
+	ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_tcp6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_ipv6: can't register tcp6 proto.\n");
+		goto cleanup_hooks;
+	}
+
+	ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_udp6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_ipv6: can't register udp6 proto.\n");
+		goto cleanup_tcp6;
+	}
+
+	ret = nf_ct_l4proto_register(&nf_conntrack_l4proto_icmpv6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_ipv6: can't register icmpv6 proto.\n");
+		goto cleanup_udp6;
+	}
+
+	ret = nf_ct_l3proto_register(&nf_conntrack_l3proto_ipv6);
+	if (ret < 0) {
+		pr_err("nf_conntrack_ipv6: can't register ipv6 proto.\n");
+		goto cleanup_icmpv6;
+	}
+	return ret;
+
+ cleanup_icmpv6:
+	nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
+ cleanup_udp6:
+	nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
+ cleanup_tcp6:
+	nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
+ cleanup_hooks:
+	nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
+ cleanup_pernet:
+	unregister_pernet_subsys(&ipv6_net_ops);
+ cleanup_sockopt:
+	nf_unregister_sockopt(&so_getorigdst6);
+	return ret;
+}
+
+static void __exit nf_conntrack_l3proto_ipv6_fini(void)
+{
+	synchronize_net();
+	nf_ct_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
+	nf_ct_l4proto_unregister(&nf_conntrack_l4proto_tcp6);
+	nf_ct_l4proto_unregister(&nf_conntrack_l4proto_udp6);
+	nf_ct_l4proto_unregister(&nf_conntrack_l4proto_icmpv6);
+	nf_unregister_hooks(ipv6_conntrack_ops, ARRAY_SIZE(ipv6_conntrack_ops));
+	unregister_pernet_subsys(&ipv6_net_ops);
+	nf_unregister_sockopt(&so_getorigdst6);
+}
+
+module_init(nf_conntrack_l3proto_ipv6_init);
+module_exit(nf_conntrack_l3proto_ipv6_fini);

net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c

@@ -0,0 +1,396 @@
+/*
+ * Copyright (C)2003,2004 USAGI/WIDE Project
+ *
+ * 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.
+ *
+ * Author:
+ *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ */
+
+#include <linux/types.h>
+#include <linux/timer.h>
+#include <linux/module.h>
+#include <linux/netfilter.h>
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <linux/ipv6.h>
+#include <net/ipv6.h>
+#include <net/ip6_checksum.h>
+#include <linux/seq_file.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
+#include <net/netfilter/nf_log.h>
+
+static unsigned int nf_ct_icmpv6_timeout __read_mostly = 30*HZ;
+
+static inline struct nf_icmp_net *icmpv6_pernet(struct net *net)
+{
+	return &net->ct.nf_ct_proto.icmpv6;
+}
+
+static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb,
+				unsigned int dataoff,
+				struct nf_conntrack_tuple *tuple)
+{
+	const struct icmp6hdr *hp;
+	struct icmp6hdr _hdr;
+
+	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
+	if (hp == NULL)
+		return false;
+	tuple->dst.u.icmp.type = hp->icmp6_type;
+	tuple->src.u.icmp.id = hp->icmp6_identifier;
+	tuple->dst.u.icmp.code = hp->icmp6_code;
+
+	return true;
+}
+
+/* Add 1; spaces filled with 0. */
+static const u_int8_t invmap[] = {
+	[ICMPV6_ECHO_REQUEST - 128]	= ICMPV6_ECHO_REPLY + 1,
+	[ICMPV6_ECHO_REPLY - 128]	= ICMPV6_ECHO_REQUEST + 1,
+	[ICMPV6_NI_QUERY - 128]		= ICMPV6_NI_REPLY + 1,
+	[ICMPV6_NI_REPLY - 128]		= ICMPV6_NI_QUERY +1
+};
+
+static const u_int8_t noct_valid_new[] = {
+	[ICMPV6_MGM_QUERY - 130] = 1,
+	[ICMPV6_MGM_REPORT -130] = 1,
+	[ICMPV6_MGM_REDUCTION - 130] = 1,
+	[NDISC_ROUTER_SOLICITATION - 130] = 1,
+	[NDISC_ROUTER_ADVERTISEMENT - 130] = 1,
+	[NDISC_NEIGHBOUR_SOLICITATION - 130] = 1,
+	[NDISC_NEIGHBOUR_ADVERTISEMENT - 130] = 1,
+	[ICMPV6_MLD2_REPORT - 130] = 1
+};
+
+static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
+				const struct nf_conntrack_tuple *orig)
+{
+	int type = orig->dst.u.icmp.type - 128;
+	if (type < 0 || type >= sizeof(invmap) || !invmap[type])
+		return false;
+
+	tuple->src.u.icmp.id   = orig->src.u.icmp.id;
+	tuple->dst.u.icmp.type = invmap[type] - 1;
+	tuple->dst.u.icmp.code = orig->dst.u.icmp.code;
+	return true;
+}
+
+/* Print out the per-protocol part of the tuple. */
+static int icmpv6_print_tuple(struct seq_file *s,
+			      const struct nf_conntrack_tuple *tuple)
+{
+	return seq_printf(s, "type=%u code=%u id=%u ",
+			  tuple->dst.u.icmp.type,
+			  tuple->dst.u.icmp.code,
+			  ntohs(tuple->src.u.icmp.id));
+}
+
+static unsigned int *icmpv6_get_timeouts(struct net *net)
+{
+	return &icmpv6_pernet(net)->timeout;
+}
+
+/* Returns verdict for packet, or -1 for invalid. */
+static int icmpv6_packet(struct nf_conn *ct,
+		       const struct sk_buff *skb,
+		       unsigned int dataoff,
+		       enum ip_conntrack_info ctinfo,
+		       u_int8_t pf,
+		       unsigned int hooknum,
+		       unsigned int *timeout)
+{
+	/* Do not immediately delete the connection after the first
+	   successful reply to avoid excessive conntrackd traffic
+	   and also to handle correctly ICMP echo reply duplicates. */
+	nf_ct_refresh_acct(ct, ctinfo, skb, *timeout);
+
+	return NF_ACCEPT;
+}
+
+/* Called when a new connection for this protocol found. */
+static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
+		       unsigned int dataoff, unsigned int *timeouts)
+{
+	static const u_int8_t valid_new[] = {
+		[ICMPV6_ECHO_REQUEST - 128] = 1,
+		[ICMPV6_NI_QUERY - 128] = 1
+	};
+	int type = ct->tuplehash[0].tuple.dst.u.icmp.type - 128;
+
+	if (type < 0 || type >= sizeof(valid_new) || !valid_new[type]) {
+		/* Can't create a new ICMPv6 `conn' with this. */
+		pr_debug("icmpv6: can't create new conn with type %u\n",
+			 type + 128);
+		nf_ct_dump_tuple_ipv6(&ct->tuplehash[0].tuple);
+		if (LOG_INVALID(nf_ct_net(ct), IPPROTO_ICMPV6))
+			nf_log_packet(nf_ct_net(ct), PF_INET6, 0, skb, NULL,
+				      NULL, NULL,
+				      "nf_ct_icmpv6: invalid new with type %d ",
+				      type + 128);
+		return false;
+	}
+	return true;
+}
+
+static int
+icmpv6_error_message(struct net *net, struct nf_conn *tmpl,
+		     struct sk_buff *skb,
+		     unsigned int icmp6off,
+		     enum ip_conntrack_info *ctinfo,
+		     unsigned int hooknum)
+{
+	struct nf_conntrack_tuple intuple, origtuple;
+	const struct nf_conntrack_tuple_hash *h;
+	const struct nf_conntrack_l4proto *inproto;
+	u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE;
+
+	NF_CT_ASSERT(skb->nfct == NULL);
+
+	/* Are they talking about one of our connections? */
+	if (!nf_ct_get_tuplepr(skb,
+			       skb_network_offset(skb)
+				+ sizeof(struct ipv6hdr)
+				+ sizeof(struct icmp6hdr),
+			       PF_INET6, &origtuple)) {
+		pr_debug("icmpv6_error: Can't get tuple\n");
+		return -NF_ACCEPT;
+	}
+
+	/* rcu_read_lock()ed by nf_hook_slow */
+	inproto = __nf_ct_l4proto_find(PF_INET6, origtuple.dst.protonum);
+
+	/* Ordinarily, we'd expect the inverted tupleproto, but it's
+	   been preserved inside the ICMP. */
+	if (!nf_ct_invert_tuple(&intuple, &origtuple,
+				&nf_conntrack_l3proto_ipv6, inproto)) {
+		pr_debug("icmpv6_error: Can't invert tuple\n");
+		return -NF_ACCEPT;
+	}
+
+	*ctinfo = IP_CT_RELATED;
+
+	h = nf_conntrack_find_get(net, zone, &intuple);
+	if (!h) {
+		pr_debug("icmpv6_error: no match\n");
+		return -NF_ACCEPT;
+	} else {
+		if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+			*ctinfo += IP_CT_IS_REPLY;
+	}
+
+	/* Update skb to refer to this connection */
+	skb->nfct = &nf_ct_tuplehash_to_ctrack(h)->ct_general;
+	skb->nfctinfo = *ctinfo;
+	return NF_ACCEPT;
+}
+
+static int
+icmpv6_error(struct net *net, struct nf_conn *tmpl,
+	     struct sk_buff *skb, unsigned int dataoff,
+	     enum ip_conntrack_info *ctinfo, u_int8_t pf, unsigned int hooknum)
+{
+	const struct icmp6hdr *icmp6h;
+	struct icmp6hdr _ih;
+	int type;
+
+	icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
+	if (icmp6h == NULL) {
+		if (LOG_INVALID(net, IPPROTO_ICMPV6))
+			nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL,
+			      "nf_ct_icmpv6: short packet ");
+		return -NF_ACCEPT;
+	}
+
+	if (net->ct.sysctl_checksum && hooknum == NF_INET_PRE_ROUTING &&
+	    nf_ip6_checksum(skb, hooknum, dataoff, IPPROTO_ICMPV6)) {
+		if (LOG_INVALID(net, IPPROTO_ICMPV6))
+			nf_log_packet(net, PF_INET6, 0, skb, NULL, NULL, NULL,
+				      "nf_ct_icmpv6: ICMPv6 checksum failed ");
+		return -NF_ACCEPT;
+	}
+
+	type = icmp6h->icmp6_type - 130;
+	if (type >= 0 && type < sizeof(noct_valid_new) &&
+	    noct_valid_new[type]) {
+		skb->nfct = &nf_ct_untracked_get()->ct_general;
+		skb->nfctinfo = IP_CT_NEW;
+		nf_conntrack_get(skb->nfct);
+		return NF_ACCEPT;
+	}
+
+	/* is not error message ? */
+	if (icmp6h->icmp6_type >= 128)
+		return NF_ACCEPT;
+
+	return icmpv6_error_message(net, tmpl, skb, dataoff, ctinfo, hooknum);
+}
+
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+static int icmpv6_tuple_to_nlattr(struct sk_buff *skb,
+				  const struct nf_conntrack_tuple *t)
+{
+	if (nla_put_be16(skb, CTA_PROTO_ICMPV6_ID, t->src.u.icmp.id) ||
+	    nla_put_u8(skb, CTA_PROTO_ICMPV6_TYPE, t->dst.u.icmp.type) ||
+	    nla_put_u8(skb, CTA_PROTO_ICMPV6_CODE, t->dst.u.icmp.code))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -1;
+}
+
+static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = {
+	[CTA_PROTO_ICMPV6_TYPE]	= { .type = NLA_U8 },
+	[CTA_PROTO_ICMPV6_CODE]	= { .type = NLA_U8 },
+	[CTA_PROTO_ICMPV6_ID]	= { .type = NLA_U16 },
+};
+
+static int icmpv6_nlattr_to_tuple(struct nlattr *tb[],
+				struct nf_conntrack_tuple *tuple)
+{
+	if (!tb[CTA_PROTO_ICMPV6_TYPE] ||
+	    !tb[CTA_PROTO_ICMPV6_CODE] ||
+	    !tb[CTA_PROTO_ICMPV6_ID])
+		return -EINVAL;
+
+	tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]);
+	tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]);
+	tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]);
+
+	if (tuple->dst.u.icmp.type < 128 ||
+	    tuple->dst.u.icmp.type - 128 >= sizeof(invmap) ||
+	    !invmap[tuple->dst.u.icmp.type - 128])
+		return -EINVAL;
+
+	return 0;
+}
+
+static int icmpv6_nlattr_tuple_size(void)
+{
+	return nla_policy_len(icmpv6_nla_policy, CTA_PROTO_MAX + 1);
+}
+#endif
+
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/nfnetlink_cttimeout.h>
+
+static int icmpv6_timeout_nlattr_to_obj(struct nlattr *tb[],
+					struct net *net, void *data)
+{
+	unsigned int *timeout = data;
+	struct nf_icmp_net *in = icmpv6_pernet(net);
+
+	if (tb[CTA_TIMEOUT_ICMPV6_TIMEOUT]) {
+		*timeout =
+		    ntohl(nla_get_be32(tb[CTA_TIMEOUT_ICMPV6_TIMEOUT])) * HZ;
+	} else {
+		/* Set default ICMPv6 timeout. */
+		*timeout = in->timeout;
+	}
+	return 0;
+}
+
+static int
+icmpv6_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
+{
+	const unsigned int *timeout = data;
+
+	if (nla_put_be32(skb, CTA_TIMEOUT_ICMPV6_TIMEOUT, htonl(*timeout / HZ)))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	return -ENOSPC;
+}
+
+static const struct nla_policy
+icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = {
+	[CTA_TIMEOUT_ICMPV6_TIMEOUT]	= { .type = NLA_U32 },
+};
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table icmpv6_sysctl_table[] = {
+	{
+		.procname	= "nf_conntrack_icmpv6_timeout",
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{ }
+};
+#endif /* CONFIG_SYSCTL */
+
+static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn,
+				       struct nf_icmp_net *in)
+{
+#ifdef CONFIG_SYSCTL
+	pn->ctl_table = kmemdup(icmpv6_sysctl_table,
+				sizeof(icmpv6_sysctl_table),
+				GFP_KERNEL);
+	if (!pn->ctl_table)
+		return -ENOMEM;
+
+	pn->ctl_table[0].data = &in->timeout;
+#endif
+	return 0;
+}
+
+static int icmpv6_init_net(struct net *net, u_int16_t proto)
+{
+	struct nf_icmp_net *in = icmpv6_pernet(net);
+	struct nf_proto_net *pn = &in->pn;
+
+	in->timeout = nf_ct_icmpv6_timeout;
+
+	return icmpv6_kmemdup_sysctl_table(pn, in);
+}
+
+static struct nf_proto_net *icmpv6_get_net_proto(struct net *net)
+{
+	return &net->ct.nf_ct_proto.icmpv6.pn;
+}
+
+struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 __read_mostly =
+{
+	.l3proto		= PF_INET6,
+	.l4proto		= IPPROTO_ICMPV6,
+	.name			= "icmpv6",
+	.pkt_to_tuple		= icmpv6_pkt_to_tuple,
+	.invert_tuple		= icmpv6_invert_tuple,
+	.print_tuple		= icmpv6_print_tuple,
+	.packet			= icmpv6_packet,
+	.get_timeouts		= icmpv6_get_timeouts,
+	.new			= icmpv6_new,
+	.error			= icmpv6_error,
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+	.tuple_to_nlattr	= icmpv6_tuple_to_nlattr,
+	.nlattr_tuple_size	= icmpv6_nlattr_tuple_size,
+	.nlattr_to_tuple	= icmpv6_nlattr_to_tuple,
+	.nla_policy		= icmpv6_nla_policy,
+#endif
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK_TIMEOUT)
+	.ctnl_timeout		= {
+		.nlattr_to_obj	= icmpv6_timeout_nlattr_to_obj,
+		.obj_to_nlattr	= icmpv6_timeout_obj_to_nlattr,
+		.nlattr_max	= CTA_TIMEOUT_ICMP_MAX,
+		.obj_size	= sizeof(unsigned int),
+		.nla_policy	= icmpv6_timeout_nla_policy,
+	},
+#endif /* CONFIG_NF_CT_NETLINK_TIMEOUT */
+	.init_net		= icmpv6_init_net,
+	.get_net_proto		= icmpv6_get_net_proto,
+};

net/ipv6/netfilter/nf_conntrack_reasm.c

@@ -0,0 +1,697 @@
+/*
+ * IPv6 fragment reassembly for connection tracking
+ *
+ * Copyright (C)2004 USAGI/WIDE Project
+ *
+ * Author:
+ *	Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *
+ * Based on: net/ipv6/reassembly.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define pr_fmt(fmt) "IPv6-nf: " fmt
+
+#include <linux/errno.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/jiffies.h>
+#include <linux/net.h>
+#include <linux/list.h>
+#include <linux/netdevice.h>
+#include <linux/in6.h>
+#include <linux/ipv6.h>
+#include <linux/icmpv6.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+
+#include <net/sock.h>
+#include <net/snmp.h>
+#include <net/inet_frag.h>
+
+#include <net/ipv6.h>
+#include <net/protocol.h>
+#include <net/transp_v6.h>
+#include <net/rawv6.h>
+#include <net/ndisc.h>
+#include <net/addrconf.h>
+#include <net/inet_ecn.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
+#include <linux/sysctl.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+
+
+struct nf_ct_frag6_skb_cb
+{
+	struct inet6_skb_parm	h;
+	int			offset;
+	struct sk_buff		*orig;
+};
+
+#define NFCT_FRAG6_CB(skb)	((struct nf_ct_frag6_skb_cb*)((skb)->cb))
+
+static struct inet_frags nf_frags;
+
+#ifdef CONFIG_SYSCTL
+static struct ctl_table nf_ct_frag6_sysctl_table[] = {
+	{
+		.procname	= "nf_conntrack_frag6_timeout",
+		.data		= &init_net.nf_frag.frags.timeout,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "nf_conntrack_frag6_low_thresh",
+		.data		= &init_net.nf_frag.frags.low_thresh,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "nf_conntrack_frag6_high_thresh",
+		.data		= &init_net.nf_frag.frags.high_thresh,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{ }
+};
+
+static int nf_ct_frag6_sysctl_register(struct net *net)
+{
+	struct ctl_table *table;
+	struct ctl_table_header *hdr;
+
+	table = nf_ct_frag6_sysctl_table;
+	if (!net_eq(net, &init_net)) {
+		table = kmemdup(table, sizeof(nf_ct_frag6_sysctl_table),
+				GFP_KERNEL);
+		if (table == NULL)
+			goto err_alloc;
+
+		table[0].data = &net->nf_frag.frags.timeout;
+		table[1].data = &net->nf_frag.frags.low_thresh;
+		table[2].data = &net->nf_frag.frags.high_thresh;
+	}
+
+	hdr = register_net_sysctl(net, "net/netfilter", table);
+	if (hdr == NULL)
+		goto err_reg;
+
+	net->nf_frag.sysctl.frags_hdr = hdr;
+	return 0;
+
+err_reg:
+	if (!net_eq(net, &init_net))
+		kfree(table);
+err_alloc:
+	return -ENOMEM;
+}
+
+static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
+{
+	struct ctl_table *table;
+
+	table = net->nf_frag.sysctl.frags_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->nf_frag.sysctl.frags_hdr);
+	if (!net_eq(net, &init_net))
+		kfree(table);
+}
+
+#else
+static int nf_ct_frag6_sysctl_register(struct net *net)
+{
+	return 0;
+}
+static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net)
+{
+}
+#endif
+
+static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h)
+{
+	return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK);
+}
+
+static unsigned int nf_hashfn(struct inet_frag_queue *q)
+{
+	const struct frag_queue *nq;
+
+	nq = container_of(q, struct frag_queue, q);
+	return inet6_hash_frag(nq->id, &nq->saddr, &nq->daddr, nf_frags.rnd);
+}
+
+static void nf_skb_free(struct sk_buff *skb)
+{
+	if (NFCT_FRAG6_CB(skb)->orig)
+		kfree_skb(NFCT_FRAG6_CB(skb)->orig);
+}
+
+static void nf_ct_frag6_expire(unsigned long data)
+{
+	struct frag_queue *fq;
+	struct net *net;
+
+	fq = container_of((struct inet_frag_queue *)data, struct frag_queue, q);
+	net = container_of(fq->q.net, struct net, nf_frag.frags);
+
+	ip6_expire_frag_queue(net, fq, &nf_frags);
+}
+
+/* Creation primitives. */
+static inline struct frag_queue *fq_find(struct net *net, __be32 id,
+					 u32 user, struct in6_addr *src,
+					 struct in6_addr *dst, u8 ecn)
+{
+	struct inet_frag_queue *q;
+	struct ip6_create_arg arg;
+	unsigned int hash;
+
+	arg.id = id;
+	arg.user = user;
+	arg.src = src;
+	arg.dst = dst;
+	arg.ecn = ecn;
+
+	read_lock_bh(&nf_frags.lock);
+	hash = inet6_hash_frag(id, src, dst, nf_frags.rnd);
+
+	q = inet_frag_find(&net->nf_frag.frags, &nf_frags, &arg, hash);
+	local_bh_enable();
+	if (IS_ERR_OR_NULL(q)) {
+		inet_frag_maybe_warn_overflow(q, pr_fmt());
+		return NULL;
+	}
+	return container_of(q, struct frag_queue, q);
+}
+
+
+static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb,
+			     const struct frag_hdr *fhdr, int nhoff)
+{
+	struct sk_buff *prev, *next;
+	unsigned int payload_len;
+	int offset, end;
+	u8 ecn;
+
+	if (fq->q.last_in & INET_FRAG_COMPLETE) {
+		pr_debug("Already completed\n");
+		goto err;
+	}
+
+	payload_len = ntohs(ipv6_hdr(skb)->payload_len);
+
+	offset = ntohs(fhdr->frag_off) & ~0x7;
+	end = offset + (payload_len -
+			((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1)));
+
+	if ((unsigned int)end > IPV6_MAXPLEN) {
+		pr_debug("offset is too large.\n");
+		return -1;
+	}
+
+	ecn = ip6_frag_ecn(ipv6_hdr(skb));
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE) {
+		const unsigned char *nh = skb_network_header(skb);
+		skb->csum = csum_sub(skb->csum,
+				     csum_partial(nh, (u8 *)(fhdr + 1) - nh,
+						  0));
+	}
+
+	/* Is this the final fragment? */
+	if (!(fhdr->frag_off & htons(IP6_MF))) {
+		/* If we already have some bits beyond end
+		 * or have different end, the segment is corrupted.
+		 */
+		if (end < fq->q.len ||
+		    ((fq->q.last_in & INET_FRAG_LAST_IN) && end != fq->q.len)) {
+			pr_debug("already received last fragment\n");
+			goto err;
+		}
+		fq->q.last_in |= INET_FRAG_LAST_IN;
+		fq->q.len = end;
+	} else {
+		/* Check if the fragment is rounded to 8 bytes.
+		 * Required by the RFC.
+		 */
+		if (end & 0x7) {
+			/* RFC2460 says always send parameter problem in
+			 * this case. -DaveM
+			 */
+			pr_debug("end of fragment not rounded to 8 bytes.\n");
+			return -1;
+		}
+		if (end > fq->q.len) {
+			/* Some bits beyond end -> corruption. */
+			if (fq->q.last_in & INET_FRAG_LAST_IN) {
+				pr_debug("last packet already reached.\n");
+				goto err;
+			}
+			fq->q.len = end;
+		}
+	}
+
+	if (end == offset)
+		goto err;
+
+	/* Point into the IP datagram 'data' part. */
+	if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) {
+		pr_debug("queue: message is too short.\n");
+		goto err;
+	}
+	if (pskb_trim_rcsum(skb, end - offset)) {
+		pr_debug("Can't trim\n");
+		goto err;
+	}
+
+	/* Find out which fragments are in front and at the back of us
+	 * in the chain of fragments so far.  We must know where to put
+	 * this fragment, right?
+	 */
+	prev = fq->q.fragments_tail;
+	if (!prev || NFCT_FRAG6_CB(prev)->offset < offset) {
+		next = NULL;
+		goto found;
+	}
+	prev = NULL;
+	for (next = fq->q.fragments; next != NULL; next = next->next) {
+		if (NFCT_FRAG6_CB(next)->offset >= offset)
+			break;	/* bingo! */
+		prev = next;
+	}
+
+found:
+	/* RFC5722, Section 4:
+	 *                                  When reassembling an IPv6 datagram, if
+	 *   one or more its constituent fragments is determined to be an
+	 *   overlapping fragment, the entire datagram (and any constituent
+	 *   fragments, including those not yet received) MUST be silently
+	 *   discarded.
+	 */
+
+	/* Check for overlap with preceding fragment. */
+	if (prev &&
+	    (NFCT_FRAG6_CB(prev)->offset + prev->len) > offset)
+		goto discard_fq;
+
+	/* Look for overlap with succeeding segment. */
+	if (next && NFCT_FRAG6_CB(next)->offset < end)
+		goto discard_fq;
+
+	NFCT_FRAG6_CB(skb)->offset = offset;
+
+	/* Insert this fragment in the chain of fragments. */
+	skb->next = next;
+	if (!next)
+		fq->q.fragments_tail = skb;
+	if (prev)
+		prev->next = skb;
+	else
+		fq->q.fragments = skb;
+
+	if (skb->dev) {
+		fq->iif = skb->dev->ifindex;
+		skb->dev = NULL;
+	}
+	fq->q.stamp = skb->tstamp;
+	fq->q.meat += skb->len;
+	fq->ecn |= ecn;
+	if (payload_len > fq->q.max_size)
+		fq->q.max_size = payload_len;
+	add_frag_mem_limit(&fq->q, skb->truesize);
+
+	/* The first fragment.
+	 * nhoffset is obtained from the first fragment, of course.
+	 */
+	if (offset == 0) {
+		fq->nhoffset = nhoff;
+		fq->q.last_in |= INET_FRAG_FIRST_IN;
+	}
+
+	inet_frag_lru_move(&fq->q);
+	return 0;
+
+discard_fq:
+	inet_frag_kill(&fq->q, &nf_frags);
+err:
+	return -1;
+}
+
+/*
+ *	Check if this packet is complete.
+ *	Returns NULL on failure by any reason, and pointer
+ *	to current nexthdr field in reassembled frame.
+ *
+ *	It is called with locked fq, and caller must check that
+ *	queue is eligible for reassembly i.e. it is not COMPLETE,
+ *	the last and the first frames arrived and all the bits are here.
+ */
+static struct sk_buff *
+nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev)
+{
+	struct sk_buff *fp, *op, *head = fq->q.fragments;
+	int    payload_len;
+	u8 ecn;
+
+	inet_frag_kill(&fq->q, &nf_frags);
+
+	WARN_ON(head == NULL);
+	WARN_ON(NFCT_FRAG6_CB(head)->offset != 0);
+
+	ecn = ip_frag_ecn_table[fq->ecn];
+	if (unlikely(ecn == 0xff))
+		goto out_fail;
+
+	/* Unfragmented part is taken from the first segment. */
+	payload_len = ((head->data - skb_network_header(head)) -
+		       sizeof(struct ipv6hdr) + fq->q.len -
+		       sizeof(struct frag_hdr));
+	if (payload_len > IPV6_MAXPLEN) {
+		pr_debug("payload len is too large.\n");
+		goto out_oversize;
+	}
+
+	/* Head of list must not be cloned. */
+	if (skb_unclone(head, GFP_ATOMIC)) {
+		pr_debug("skb is cloned but can't expand head");
+		goto out_oom;
+	}
+
+	/* If the first fragment is fragmented itself, we split
+	 * it to two chunks: the first with data and paged part
+	 * and the second, holding only fragments. */
+	if (skb_has_frag_list(head)) {
+		struct sk_buff *clone;
+		int i, plen = 0;
+
+		clone = alloc_skb(0, GFP_ATOMIC);
+		if (clone == NULL)
+			goto out_oom;
+
+		clone->next = head->next;
+		head->next = clone;
+		skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list;
+		skb_frag_list_init(head);
+		for (i = 0; i < skb_shinfo(head)->nr_frags; i++)
+			plen += skb_frag_size(&skb_shinfo(head)->frags[i]);
+		clone->len = clone->data_len = head->data_len - plen;
+		head->data_len -= clone->len;
+		head->len -= clone->len;
+		clone->csum = 0;
+		clone->ip_summed = head->ip_summed;
+
+		NFCT_FRAG6_CB(clone)->orig = NULL;
+		add_frag_mem_limit(&fq->q, clone->truesize);
+	}
+
+	/* We have to remove fragment header from datagram and to relocate
+	 * header in order to calculate ICV correctly. */
+	skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0];
+	memmove(head->head + sizeof(struct frag_hdr), head->head,
+		(head->data - head->head) - sizeof(struct frag_hdr));
+	head->mac_header += sizeof(struct frag_hdr);
+	head->network_header += sizeof(struct frag_hdr);
+
+	skb_shinfo(head)->frag_list = head->next;
+	skb_reset_transport_header(head);
+	skb_push(head, head->data - skb_network_header(head));
+
+	for (fp=head->next; fp; fp = fp->next) {
+		head->data_len += fp->len;
+		head->len += fp->len;
+		if (head->ip_summed != fp->ip_summed)
+			head->ip_summed = CHECKSUM_NONE;
+		else if (head->ip_summed == CHECKSUM_COMPLETE)
+			head->csum = csum_add(head->csum, fp->csum);
+		head->truesize += fp->truesize;
+	}
+	sub_frag_mem_limit(&fq->q, head->truesize);
+
+	head->local_df = 1;
+	head->next = NULL;
+	head->dev = dev;
+	head->tstamp = fq->q.stamp;
+	ipv6_hdr(head)->payload_len = htons(payload_len);
+	ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn);
+	IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size;
+
+	/* Yes, and fold redundant checksum back. 8) */
+	if (head->ip_summed == CHECKSUM_COMPLETE)
+		head->csum = csum_partial(skb_network_header(head),
+					  skb_network_header_len(head),
+					  head->csum);
+
+	fq->q.fragments = NULL;
+	fq->q.fragments_tail = NULL;
+
+	/* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */
+	fp = skb_shinfo(head)->frag_list;
+	if (fp && NFCT_FRAG6_CB(fp)->orig == NULL)
+		/* at above code, head skb is divided into two skbs. */
+		fp = fp->next;
+
+	op = NFCT_FRAG6_CB(head)->orig;
+	for (; fp; fp = fp->next) {
+		struct sk_buff *orig = NFCT_FRAG6_CB(fp)->orig;
+
+		op->next = orig;
+		op = orig;
+		NFCT_FRAG6_CB(fp)->orig = NULL;
+	}
+
+	return head;
+
+out_oversize:
+	net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n",
+			    payload_len);
+	goto out_fail;
+out_oom:
+	net_dbg_ratelimited("nf_ct_frag6_reasm: no memory for reassembly\n");
+out_fail:
+	return NULL;
+}
+
+/*
+ * find the header just before Fragment Header.
+ *
+ * if success return 0 and set ...
+ * (*prevhdrp): the value of "Next Header Field" in the header
+ *		just before Fragment Header.
+ * (*prevhoff): the offset of "Next Header Field" in the header
+ *		just before Fragment Header.
+ * (*fhoff)   : the offset of Fragment Header.
+ *
+ * Based on ipv6_skip_hdr() in net/ipv6/exthdr.c
+ *
+ */
+static int
+find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
+{
+	u8 nexthdr = ipv6_hdr(skb)->nexthdr;
+	const int netoff = skb_network_offset(skb);
+	u8 prev_nhoff = netoff + offsetof(struct ipv6hdr, nexthdr);
+	int start = netoff + sizeof(struct ipv6hdr);
+	int len = skb->len - start;
+	u8 prevhdr = NEXTHDR_IPV6;
+
+	while (nexthdr != NEXTHDR_FRAGMENT) {
+		struct ipv6_opt_hdr hdr;
+		int hdrlen;
+
+		if (!ipv6_ext_hdr(nexthdr)) {
+			return -1;
+		}
+		if (nexthdr == NEXTHDR_NONE) {
+			pr_debug("next header is none\n");
+			return -1;
+		}
+		if (len < (int)sizeof(struct ipv6_opt_hdr)) {
+			pr_debug("too short\n");
+			return -1;
+		}
+		if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
+			BUG();
+		if (nexthdr == NEXTHDR_AUTH)
+			hdrlen = (hdr.hdrlen+2)<<2;
+		else
+			hdrlen = ipv6_optlen(&hdr);
+
+		prevhdr = nexthdr;
+		prev_nhoff = start;
+
+		nexthdr = hdr.nexthdr;
+		len -= hdrlen;
+		start += hdrlen;
+	}
+
+	if (len < 0)
+		return -1;
+
+	*prevhdrp = prevhdr;
+	*prevhoff = prev_nhoff;
+	*fhoff = start;
+
+	return 0;
+}
+
+struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
+{
+	struct sk_buff *clone;
+	struct net_device *dev = skb->dev;
+	struct net *net = skb_dst(skb) ? dev_net(skb_dst(skb)->dev)
+				       : dev_net(skb->dev);
+	struct frag_hdr *fhdr;
+	struct frag_queue *fq;
+	struct ipv6hdr *hdr;
+	int fhoff, nhoff;
+	u8 prevhdr;
+	struct sk_buff *ret_skb = NULL;
+
+	/* Jumbo payload inhibits frag. header */
+	if (ipv6_hdr(skb)->payload_len == 0) {
+		pr_debug("payload len = 0\n");
+		return skb;
+	}
+
+	if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0)
+		return skb;
+
+	clone = skb_clone(skb, GFP_ATOMIC);
+	if (clone == NULL) {
+		pr_debug("Can't clone skb\n");
+		return skb;
+	}
+
+	NFCT_FRAG6_CB(clone)->orig = skb;
+
+	if (!pskb_may_pull(clone, fhoff + sizeof(*fhdr))) {
+		pr_debug("message is too short.\n");
+		goto ret_orig;
+	}
+
+	skb_set_transport_header(clone, fhoff);
+	hdr = ipv6_hdr(clone);
+	fhdr = (struct frag_hdr *)skb_transport_header(clone);
+
+	local_bh_disable();
+	inet_frag_evictor(&net->nf_frag.frags, &nf_frags, false);
+	local_bh_enable();
+
+	fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr,
+		     ip6_frag_ecn(hdr));
+	if (fq == NULL) {
+		pr_debug("Can't find and can't create new queue\n");
+		goto ret_orig;
+	}
+
+	spin_lock_bh(&fq->q.lock);
+
+	if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) {
+		spin_unlock_bh(&fq->q.lock);
+		pr_debug("Can't insert skb to queue\n");
+		inet_frag_put(&fq->q, &nf_frags);
+		goto ret_orig;
+	}
+
+	if (fq->q.last_in == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) &&
+	    fq->q.meat == fq->q.len) {
+		ret_skb = nf_ct_frag6_reasm(fq, dev);
+		if (ret_skb == NULL)
+			pr_debug("Can't reassemble fragmented packets\n");
+	}
+	spin_unlock_bh(&fq->q.lock);
+
+	inet_frag_put(&fq->q, &nf_frags);
+	return ret_skb;
+
+ret_orig:
+	kfree_skb(clone);
+	return skb;
+}
+
+void nf_ct_frag6_output(unsigned int hooknum, struct sk_buff *skb,
+			struct net_device *in, struct net_device *out,
+			int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *s, *s2;
+	unsigned int ret = 0;
+
+	for (s = NFCT_FRAG6_CB(skb)->orig; s;) {
+		nf_conntrack_put_reasm(s->nfct_reasm);
+		nf_conntrack_get_reasm(skb);
+		s->nfct_reasm = skb;
+
+		s2 = s->next;
+		s->next = NULL;
+
+		if (ret != -ECANCELED)
+			ret = NF_HOOK_THRESH(NFPROTO_IPV6, hooknum, s,
+					     in, out, okfn,
+					     NF_IP6_PRI_CONNTRACK_DEFRAG + 1);
+		else
+			kfree_skb(s);
+
+		s = s2;
+	}
+	nf_conntrack_put_reasm(skb);
+}
+
+static int nf_ct_net_init(struct net *net)
+{
+	net->nf_frag.frags.high_thresh = IPV6_FRAG_HIGH_THRESH;
+	net->nf_frag.frags.low_thresh = IPV6_FRAG_LOW_THRESH;
+	net->nf_frag.frags.timeout = IPV6_FRAG_TIMEOUT;
+	inet_frags_init_net(&net->nf_frag.frags);
+
+	return nf_ct_frag6_sysctl_register(net);
+}
+
+static void nf_ct_net_exit(struct net *net)
+{
+	nf_ct_frags6_sysctl_unregister(net);
+	inet_frags_exit_net(&net->nf_frag.frags, &nf_frags);
+}
+
+static struct pernet_operations nf_ct_net_ops = {
+	.init = nf_ct_net_init,
+	.exit = nf_ct_net_exit,
+};
+
+int nf_ct_frag6_init(void)
+{
+	int ret = 0;
+
+	nf_frags.hashfn = nf_hashfn;
+	nf_frags.constructor = ip6_frag_init;
+	nf_frags.destructor = NULL;
+	nf_frags.skb_free = nf_skb_free;
+	nf_frags.qsize = sizeof(struct frag_queue);
+	nf_frags.match = ip6_frag_match;
+	nf_frags.frag_expire = nf_ct_frag6_expire;
+	nf_frags.secret_interval = 10 * 60 * HZ;
+	inet_frags_init(&nf_frags);
+
+	ret = register_pernet_subsys(&nf_ct_net_ops);
+	if (ret)
+		inet_frags_fini(&nf_frags);
+
+	return ret;
+}
+
+void nf_ct_frag6_cleanup(void)
+{
+	unregister_pernet_subsys(&nf_ct_net_ops);
+	inet_frags_fini(&nf_frags);
+}

net/ipv6/netfilter/nf_defrag_ipv6_hooks.c

@@ -0,0 +1,137 @@
+/* (C) 1999-2001 Paul `Rusty' Russell
+ * (C) 2002-2004 Netfilter Core Team <coreteam@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/types.h>
+#include <linux/ipv6.h>
+#include <linux/in6.h>
+#include <linux/netfilter.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/icmp.h>
+#include <linux/sysctl.h>
+#include <net/ipv6.h>
+#include <net/inet_frag.h>
+
+#include <linux/netfilter_ipv6.h>
+#include <linux/netfilter_bridge.h>
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_l4proto.h>
+#include <net/netfilter/nf_conntrack_l3proto.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
+#endif
+#include <net/netfilter/nf_conntrack_zones.h>
+#include <net/netfilter/ipv6/nf_defrag_ipv6.h>
+
+static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
+						struct sk_buff *skb)
+{
+	u16 zone = NF_CT_DEFAULT_ZONE;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	if (skb->nfct)
+		zone = nf_ct_zone((struct nf_conn *)skb->nfct);
+#endif
+
+#ifdef CONFIG_BRIDGE_NETFILTER
+	if (skb->nf_bridge &&
+	    skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
+		return IP6_DEFRAG_CONNTRACK_BRIDGE_IN + zone;
+#endif
+	if (hooknum == NF_INET_PRE_ROUTING)
+		return IP6_DEFRAG_CONNTRACK_IN + zone;
+	else
+		return IP6_DEFRAG_CONNTRACK_OUT + zone;
+
+}
+
+static unsigned int ipv6_defrag(unsigned int hooknum,
+				struct sk_buff *skb,
+				const struct net_device *in,
+				const struct net_device *out,
+				int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *reasm;
+
+#if IS_ENABLED(CONFIG_NF_CONNTRACK)
+	/* Previously seen (loopback)?	*/
+	if (skb->nfct && !nf_ct_is_template((struct nf_conn *)skb->nfct))
+		return NF_ACCEPT;
+#endif
+
+	reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb));
+	/* queued */
+	if (reasm == NULL)
+		return NF_STOLEN;
+
+	/* error occurred or not fragmented */
+	if (reasm == skb)
+		return NF_ACCEPT;
+
+	nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
+			   (struct net_device *)out, okfn);
+
+	return NF_STOLEN;
+}
+
+static struct nf_hook_ops ipv6_defrag_ops[] = {
+	{
+		.hook		= ipv6_defrag,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_PRE_ROUTING,
+		.priority	= NF_IP6_PRI_CONNTRACK_DEFRAG,
+	},
+	{
+		.hook		= ipv6_defrag,
+		.owner		= THIS_MODULE,
+		.pf		= NFPROTO_IPV6,
+		.hooknum	= NF_INET_LOCAL_OUT,
+		.priority	= NF_IP6_PRI_CONNTRACK_DEFRAG,
+	},
+};
+
+static int __init nf_defrag_init(void)
+{
+	int ret = 0;
+
+	ret = nf_ct_frag6_init();
+	if (ret < 0) {
+		pr_err("nf_defrag_ipv6: can't initialize frag6.\n");
+		return ret;
+	}
+	ret = nf_register_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops));
+	if (ret < 0) {
+		pr_err("nf_defrag_ipv6: can't register hooks\n");
+		goto cleanup_frag6;
+	}
+	return ret;
+
+cleanup_frag6:
+	nf_ct_frag6_cleanup();
+	return ret;
+
+}
+
+static void __exit nf_defrag_fini(void)
+{
+	nf_unregister_hooks(ipv6_defrag_ops, ARRAY_SIZE(ipv6_defrag_ops));
+	nf_ct_frag6_cleanup();
+}
+
+void nf_defrag_ipv6_enable(void)
+{
+}
+EXPORT_SYMBOL_GPL(nf_defrag_ipv6_enable);
+
+module_init(nf_defrag_init);
+module_exit(nf_defrag_fini);
+
+MODULE_LICENSE("GPL");

net/ipv6/netfilter/nf_nat_l3proto_ipv6.c

@@ -0,0 +1,288 @@
+/*
+ * Copyright (c) 2011 Patrick McHardy <kaber@trash.net>
+ *
+ * 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 IPv6 NAT funded by Astaro.
+ */
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/skbuff.h>
+#include <linux/ipv6.h>
+#include <linux/netfilter.h>
+#include <linux/netfilter_ipv6.h>
+#include <net/secure_seq.h>
+#include <net/checksum.h>
+#include <net/ip6_checksum.h>
+#include <net/ip6_route.h>
+#include <net/ipv6.h>
+
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/netfilter/nf_nat_l4proto.h>
+
+static const struct nf_nat_l3proto nf_nat_l3proto_ipv6;
+
+#ifdef CONFIG_XFRM
+static void nf_nat_ipv6_decode_session(struct sk_buff *skb,
+				       const struct nf_conn *ct,
+				       enum ip_conntrack_dir dir,
+				       unsigned long statusbit,
+				       struct flowi *fl)
+{
+	const struct nf_conntrack_tuple *t = &ct->tuplehash[dir].tuple;
+	struct flowi6 *fl6 = &fl->u.ip6;
+
+	if (ct->status & statusbit) {
+		fl6->daddr = t->dst.u3.in6;
+		if (t->dst.protonum == IPPROTO_TCP ||
+		    t->dst.protonum == IPPROTO_UDP ||
+		    t->dst.protonum == IPPROTO_UDPLITE ||
+		    t->dst.protonum == IPPROTO_DCCP ||
+		    t->dst.protonum == IPPROTO_SCTP)
+			fl6->fl6_dport = t->dst.u.all;
+	}
+
+	statusbit ^= IPS_NAT_MASK;
+
+	if (ct->status & statusbit) {
+		fl6->saddr = t->src.u3.in6;
+		if (t->dst.protonum == IPPROTO_TCP ||
+		    t->dst.protonum == IPPROTO_UDP ||
+		    t->dst.protonum == IPPROTO_UDPLITE ||
+		    t->dst.protonum == IPPROTO_DCCP ||
+		    t->dst.protonum == IPPROTO_SCTP)
+			fl6->fl6_sport = t->src.u.all;
+	}
+}
+#endif
+
+static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t,
+				 const struct nf_nat_range *range)
+{
+	return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 &&
+	       ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0;
+}
+
+static u32 nf_nat_ipv6_secure_port(const struct nf_conntrack_tuple *t,
+				   __be16 dport)
+{
+	return secure_ipv6_port_ephemeral(t->src.u3.ip6, t->dst.u3.ip6, dport);
+}
+
+static bool nf_nat_ipv6_manip_pkt(struct sk_buff *skb,
+				  unsigned int iphdroff,
+				  const struct nf_nat_l4proto *l4proto,
+				  const struct nf_conntrack_tuple *target,
+				  enum nf_nat_manip_type maniptype)
+{
+	struct ipv6hdr *ipv6h;
+	__be16 frag_off;
+	int hdroff;
+	u8 nexthdr;
+
+	if (!skb_make_writable(skb, iphdroff + sizeof(*ipv6h)))
+		return false;
+
+	ipv6h = (void *)skb->data + iphdroff;
+	nexthdr = ipv6h->nexthdr;
+	hdroff = ipv6_skip_exthdr(skb, iphdroff + sizeof(*ipv6h),
+				  &nexthdr, &frag_off);
+	if (hdroff < 0)
+		goto manip_addr;
+
+	if ((frag_off & htons(~0x7)) == 0 &&
+	    !l4proto->manip_pkt(skb, &nf_nat_l3proto_ipv6, iphdroff, hdroff,
+				target, maniptype))
+		return false;
+manip_addr:
+	if (maniptype == NF_NAT_MANIP_SRC)
+		ipv6h->saddr = target->src.u3.in6;
+	else
+		ipv6h->daddr = target->dst.u3.in6;
+
+	return true;
+}
+
+static void nf_nat_ipv6_csum_update(struct sk_buff *skb,
+				    unsigned int iphdroff, __sum16 *check,
+				    const struct nf_conntrack_tuple *t,
+				    enum nf_nat_manip_type maniptype)
+{
+	const struct ipv6hdr *ipv6h = (struct ipv6hdr *)(skb->data + iphdroff);
+	const struct in6_addr *oldip, *newip;
+
+	if (maniptype == NF_NAT_MANIP_SRC) {
+		oldip = &ipv6h->saddr;
+		newip = &t->src.u3.in6;
+	} else {
+		oldip = &ipv6h->daddr;
+		newip = &t->dst.u3.in6;
+	}
+	inet_proto_csum_replace16(check, skb, oldip->s6_addr32,
+				  newip->s6_addr32, 1);
+}
+
+static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb,
+				    u8 proto, void *data, __sum16 *check,
+				    int datalen, int oldlen)
+{
+	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		if (!(rt->rt6i_flags & RTF_LOCAL) &&
+		    (!skb->dev || skb->dev->features & NETIF_F_V6_CSUM)) {
+			skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->csum_start = skb_headroom(skb) +
+					  skb_network_offset(skb) +
+					  (data - (void *)skb->data);
+			skb->csum_offset = (void *)check - data;
+			*check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+						  datalen, proto, 0);
+		} else {
+			*check = 0;
+			*check = csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+						 datalen, proto,
+						 csum_partial(data, datalen,
+							      0));
+			if (proto == IPPROTO_UDP && !*check)
+				*check = CSUM_MANGLED_0;
+		}
+	} else
+		inet_proto_csum_replace2(check, skb,
+					 htons(oldlen), htons(datalen), 1);
+}
+
+static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[],
+				       struct nf_nat_range *range)
+{
+	if (tb[CTA_NAT_V6_MINIP]) {
+		nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP],
+			   sizeof(struct in6_addr));
+		range->flags |= NF_NAT_RANGE_MAP_IPS;
+	}
+
+	if (tb[CTA_NAT_V6_MAXIP])
+		nla_memcpy(&range->max_addr.ip6, tb[CTA_NAT_V6_MAXIP],
+			   sizeof(struct in6_addr));
+	else
+		range->max_addr = range->min_addr;
+
+	return 0;
+}
+
+static const struct nf_nat_l3proto nf_nat_l3proto_ipv6 = {
+	.l3proto		= NFPROTO_IPV6,
+	.secure_port		= nf_nat_ipv6_secure_port,
+	.in_range		= nf_nat_ipv6_in_range,
+	.manip_pkt		= nf_nat_ipv6_manip_pkt,
+	.csum_update		= nf_nat_ipv6_csum_update,
+	.csum_recalc		= nf_nat_ipv6_csum_recalc,
+	.nlattr_to_range	= nf_nat_ipv6_nlattr_to_range,
+#ifdef CONFIG_XFRM
+	.decode_session	= nf_nat_ipv6_decode_session,
+#endif
+};
+
+int nf_nat_icmpv6_reply_translation(struct sk_buff *skb,
+				    struct nf_conn *ct,
+				    enum ip_conntrack_info ctinfo,
+				    unsigned int hooknum,
+				    unsigned int hdrlen)
+{
+	struct {
+		struct icmp6hdr	icmp6;
+		struct ipv6hdr	ip6;
+	} *inside;
+	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
+	enum nf_nat_manip_type manip = HOOK2MANIP(hooknum);
+	const struct nf_nat_l4proto *l4proto;
+	struct nf_conntrack_tuple target;
+	unsigned long statusbit;
+
+	NF_CT_ASSERT(ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY);
+
+	if (!skb_make_writable(skb, hdrlen + sizeof(*inside)))
+		return 0;
+	if (nf_ip6_checksum(skb, hooknum, hdrlen, IPPROTO_ICMPV6))
+		return 0;
+
+	inside = (void *)skb->data + hdrlen;
+	if (inside->icmp6.icmp6_type == NDISC_REDIRECT) {
+		if ((ct->status & IPS_NAT_DONE_MASK) != IPS_NAT_DONE_MASK)
+			return 0;
+		if (ct->status & IPS_NAT_MASK)
+			return 0;
+	}
+
+	if (manip == NF_NAT_MANIP_SRC)
+		statusbit = IPS_SRC_NAT;
+	else
+		statusbit = IPS_DST_NAT;
+
+	/* Invert if this is reply direction */
+	if (dir == IP_CT_DIR_REPLY)
+		statusbit ^= IPS_NAT_MASK;
+
+	if (!(ct->status & statusbit))
+		return 1;
+
+	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, inside->ip6.nexthdr);
+	if (!nf_nat_ipv6_manip_pkt(skb, hdrlen + sizeof(inside->icmp6),
+				   l4proto, &ct->tuplehash[!dir].tuple, !manip))
+		return 0;
+
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+		inside = (void *)skb->data + hdrlen;
+		inside->icmp6.icmp6_cksum = 0;
+		inside->icmp6.icmp6_cksum =
+			csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr,
+					skb->len - hdrlen, IPPROTO_ICMPV6,
+					csum_partial(&inside->icmp6,
+						     skb->len - hdrlen, 0));
+	}
+
+	nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple);
+	l4proto = __nf_nat_l4proto_find(NFPROTO_IPV6, IPPROTO_ICMPV6);
+	if (!nf_nat_ipv6_manip_pkt(skb, 0, l4proto, &target, manip))
+		return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL_GPL(nf_nat_icmpv6_reply_translation);
+
+static int __init nf_nat_l3proto_ipv6_init(void)
+{
+	int err;
+
+	err = nf_nat_l4proto_register(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
+	if (err < 0)
+		goto err1;
+	err = nf_nat_l3proto_register(&nf_nat_l3proto_ipv6);
+	if (err < 0)
+		goto err2;
+	return err;
+
+err2:
+	nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
+err1:
+	return err;
+}
+
+static void __exit nf_nat_l3proto_ipv6_exit(void)
+{
+	nf_nat_l3proto_unregister(&nf_nat_l3proto_ipv6);
+	nf_nat_l4proto_unregister(NFPROTO_IPV6, &nf_nat_l4proto_icmpv6);
+}
+
+MODULE_LICENSE("GPL");
+MODULE_ALIAS("nf-nat-" __stringify(AF_INET6));
+
+module_init(nf_nat_l3proto_ipv6_init);
+module_exit(nf_nat_l3proto_ipv6_exit);

net/ipv6/netfilter/nf_nat_proto_icmpv6.c

@@ -0,0 +1,90 @@
+/*
+ * Copyright (c) 2011 Patrick Mchardy <kaber@trash.net>
+ *
+ * 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.
+ *
+ * Based on Rusty Russell's IPv4 ICMP NAT code. Development of IPv6
+ * NAT funded by Astaro.
+ */
+
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/icmpv6.h>
+
+#include <linux/netfilter.h>
+#include <net/netfilter/nf_nat.h>
+#include <net/netfilter/nf_nat_core.h>
+#include <net/netfilter/nf_nat_l3proto.h>
+#include <net/netfilter/nf_nat_l4proto.h>
+
+static bool
+icmpv6_in_range(const struct nf_conntrack_tuple *tuple,
+		enum nf_nat_manip_type maniptype,
+		const union nf_conntrack_man_proto *min,
+		const union nf_conntrack_man_proto *max)
+{
+	return ntohs(tuple->src.u.icmp.id) >= ntohs(min->icmp.id) &&
+	       ntohs(tuple->src.u.icmp.id) <= ntohs(max->icmp.id);
+}
+
+static void
+icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto,
+		    struct nf_conntrack_tuple *tuple,
+		    const struct nf_nat_range *range,
+		    enum nf_nat_manip_type maniptype,
+		    const struct nf_conn *ct)
+{
+	static u16 id;
+	unsigned int range_size;
+	unsigned int i;
+
+	range_size = ntohs(range->max_proto.icmp.id) -
+		     ntohs(range->min_proto.icmp.id) + 1;
+
+	if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED))
+		range_size = 0xffff;
+
+	for (i = 0; ; ++id) {
+		tuple->src.u.icmp.id = htons(ntohs(range->min_proto.icmp.id) +
+					     (id % range_size));
+		if (++i == range_size || !nf_nat_used_tuple(tuple, ct))
+			return;
+	}
+}
+
+static bool
+icmpv6_manip_pkt(struct sk_buff *skb,
+		 const struct nf_nat_l3proto *l3proto,
+		 unsigned int iphdroff, unsigned int hdroff,
+		 const struct nf_conntrack_tuple *tuple,
+		 enum nf_nat_manip_type maniptype)
+{
+	struct icmp6hdr *hdr;
+
+	if (!skb_make_writable(skb, hdroff + sizeof(*hdr)))
+		return false;
+
+	hdr = (struct icmp6hdr *)(skb->data + hdroff);
+	l3proto->csum_update(skb, iphdroff, &hdr->icmp6_cksum,
+			     tuple, maniptype);
+	if (hdr->icmp6_code == ICMPV6_ECHO_REQUEST ||
+	    hdr->icmp6_code == ICMPV6_ECHO_REPLY) {
+		inet_proto_csum_replace2(&hdr->icmp6_cksum, skb,
+					 hdr->icmp6_identifier,
+					 tuple->src.u.icmp.id, 0);
+		hdr->icmp6_identifier = tuple->src.u.icmp.id;
+	}
+	return true;
+}
+
+const struct nf_nat_l4proto nf_nat_l4proto_icmpv6 = {
+	.l4proto		= IPPROTO_ICMPV6,
+	.manip_pkt		= icmpv6_manip_pkt,
+	.in_range		= icmpv6_in_range,
+	.unique_tuple		= icmpv6_unique_tuple,
+#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
+	.nlattr_to_range	= nf_nat_l4proto_nlattr_to_range,
+#endif
+};