[NETFILTER]: Add nf_conntrack subsystem.

The existing connection tracking subsystem in netfilter can only
handle ipv4.  There were basically two choices present to add
connection tracking support for ipv6.  We could either duplicate all
of the ipv4 connection tracking code into an ipv6 counterpart, or (the
choice taken by these patches) we could design a generic layer that
could handle both ipv4 and ipv6 and thus requiring only one sub-protocol
(TCP, UDP, etc.) connection tracking helper module to be written.

In fact nf_conntrack is capable of working with any layer 3
protocol.

The existing ipv4 specific conntrack code could also not deal
with the pecularities of doing connection tracking on ipv6,
which is also cured here.  For example, these issues include:

1) ICMPv6 handling, which is used for neighbour discovery in
   ipv6 thus some messages such as these should not participate
   in connection tracking since effectively they are like ARP
   messages

2) fragmentation must be handled differently in ipv6, because
   the simplistic "defrag, connection track and NAT, refrag"
   (which the existing ipv4 connection tracking does) approach simply
   isn't feasible in ipv6

3) ipv6 extension header parsing must occur at the correct spots
   before and after connection tracking decisions, and there were
   no provisions for this in the existing connection tracking
   design

4) ipv6 has no need for stateful NAT

The ipv4 specific conntrack layer is kept around, until all of
the ipv4 specific conntrack helpers are ported over to nf_conntrack
and it is feature complete.  Once that occurs, the old conntrack
stuff will get placed into the feature-removal-schedule and we will
fully kill it off 6 months later.

Signed-off-by: Yasuyuki Kozakai <yasuyuki.kozakai@toshiba.co.jp>
Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: Arnaldo Carvalho de Melo <acme@mandriva.com>

1 files changed, 556 insertions, 0 deletions

diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
new file mode 100644
index 000000000000..e2c90b3a8074
--- /dev/null
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -0,0 +1,556 @@
+/*
+ * 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>
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- support Layer 3 protocol independent connection tracking.
+ *	  Based on the original ip_conntrack code which	had the following
+ *	  copyright information:
+ *		(C) 1999-2001 Paul `Rusty' Russell
+ *		(C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ *
+ * 23 Mar 2004: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- add get_features() to support various size of conntrack
+ *	  structures.
+ */
+
+#include <linux/config.h>
+#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 <linux/netfilter_ipv6.h>
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#include <net/netfilter/nf_conntrack_protocol.h>
+#include <net/netfilter/nf_conntrack_l3proto.h>
+#include <net/netfilter/nf_conntrack_core.h>
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+DECLARE_PER_CPU(struct ip_conntrack_stat, nf_conntrack_stat);
+
+static int ipv6_pkt_to_tuple(const struct sk_buff *skb, unsigned int nhoff,
+			     struct nf_conntrack_tuple *tuple)
+{
+	u_int32_t _addrs[8], *ap;
+
+	ap = skb_header_pointer(skb, nhoff + offsetof(struct ipv6hdr, saddr),
+				sizeof(_addrs), _addrs);
+	if (ap == NULL)
+		return 0;
+
+	memcpy(tuple->src.u3.ip6, ap, sizeof(tuple->src.u3.ip6));
+	memcpy(tuple->dst.u3.ip6, ap + 4, sizeof(tuple->dst.u3.ip6));
+
+	return 1;
+}
+
+static int 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 1;
+}
+
+static int ipv6_print_tuple(struct seq_file *s,
+			    const struct nf_conntrack_tuple *tuple)
+{
+	return seq_printf(s, "src=%x:%x:%x:%x:%x:%x:%x:%x dst=%x:%x:%x:%x:%x:%x:%x:%x ",
+			  NIP6(*((struct in6_addr *)tuple->src.u3.ip6)),
+			  NIP6(*((struct in6_addr *)tuple->dst.u3.ip6)));
+}
+
+static int ipv6_print_conntrack(struct seq_file *s,
+				const struct nf_conn *conntrack)
+{
+	return 0;
+}
+
+/*
+ * Based on ipv6_skip_exthdr() in net/ipv6/exthdr.c
+ *
+ * This function parses (probably truncated) exthdr set "hdr"
+ * of length "len". "nexthdrp" initially points to some place,
+ * where type of the first header can be found.
+ *
+ * It skips all well-known exthdrs, and returns pointer to the start
+ * of unparsable area i.e. the first header with unknown type.
+ * if success, *nexthdr is updated by type/protocol of this header.
+ *
+ * NOTES: - it may return pointer pointing beyond end of packet,
+ *          if the last recognized header is truncated in the middle.
+ *        - if packet is truncated, so that all parsed headers are skipped,
+ *          it returns -1.
+ *        - if packet is fragmented, return pointer of the fragment header.
+ *        - ESP is unparsable for now and considered like
+ *          normal payload protocol.
+ *        - Note also special handling of AUTH header. Thanks to IPsec wizards.
+ */
+
+int nf_ct_ipv6_skip_exthdr(struct sk_buff *skb, int start, u8 *nexthdrp,
+			   int len)
+{
+	u8 nexthdr = *nexthdrp;
+
+	while (ipv6_ext_hdr(nexthdr)) {
+		struct ipv6_opt_hdr hdr;
+		int hdrlen;
+
+		if (len < (int)sizeof(struct ipv6_opt_hdr))
+			return -1;
+		if (nexthdr == NEXTHDR_NONE)
+			break;
+		if (nexthdr == NEXTHDR_FRAGMENT)
+			break;
+		if (skb_copy_bits(skb, start, &hdr, sizeof(hdr)))
+			BUG();
+		if (nexthdr == NEXTHDR_AUTH)
+			hdrlen = (hdr.hdrlen+2)<<2;
+		else
+			hdrlen = ipv6_optlen(&hdr);
+
+		nexthdr = hdr.nexthdr;
+		len -= hdrlen;
+		start += hdrlen;
+	}
+
+	*nexthdrp = nexthdr;
+	return start;
+}
+
+static int
+ipv6_prepare(struct sk_buff **pskb, unsigned int hooknum, unsigned int *dataoff,
+	     u_int8_t *protonum)
+{
+	unsigned int extoff;
+	unsigned char pnum;
+	int protoff;
+
+	extoff = (u8*)((*pskb)->nh.ipv6h + 1) - (*pskb)->data;
+	pnum = (*pskb)->nh.ipv6h->nexthdr;
+
+	protoff = nf_ct_ipv6_skip_exthdr(*pskb, extoff, &pnum,
+					 (*pskb)->len - extoff);
+
+	/*
+	 * (protoff == (*pskb)->len) mean that the packet doesn't have no data
+	 * except of IPv6 & ext headers. but it's tracked anyway. - YK
+	 */
+	if ((protoff < 0) || (protoff > (*pskb)->len)) {
+		DEBUGP("ip6_conntrack_core: can't find proto in pkt\n");
+		NF_CT_STAT_INC(error);
+		NF_CT_STAT_INC(invalid);
+		return -NF_ACCEPT;
+	}
+
+	*dataoff = protoff;
+	*protonum = pnum;
+	return NF_ACCEPT;
+}
+
+static u_int32_t ipv6_get_features(const struct nf_conntrack_tuple *tuple)
+{
+	return NF_CT_F_BASIC;
+}
+
+static unsigned int ipv6_confirm(unsigned int hooknum,
+				 struct sk_buff **pskb,
+				 const struct net_device *in,
+				 const struct net_device *out,
+				 int (*okfn)(struct sk_buff *))
+{
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+
+	/* This is where we call the helper: as the packet goes out. */
+	ct = nf_ct_get(*pskb, &ctinfo);
+	if (ct && ct->helper) {
+		unsigned int ret, protoff;
+		unsigned int extoff = (u8*)((*pskb)->nh.ipv6h + 1)
+				      - (*pskb)->data;
+		unsigned char pnum = (*pskb)->nh.ipv6h->nexthdr;
+
+		protoff = nf_ct_ipv6_skip_exthdr(*pskb, extoff, &pnum,
+						 (*pskb)->len - extoff);
+		if (protoff < 0 || protoff > (*pskb)->len ||
+		    pnum == NEXTHDR_FRAGMENT) {
+			DEBUGP("proto header not found\n");
+			return NF_ACCEPT;
+		}
+
+		ret = ct->helper->help(pskb, protoff, ct, ctinfo);
+		if (ret != NF_ACCEPT)
+			return ret;
+	}
+
+	/* We've seen it coming out the other side: confirm it */
+
+	return nf_conntrack_confirm(pskb);
+}
+
+extern struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb);
+extern 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 *));
+static unsigned int ipv6_defrag(unsigned int hooknum,
+				struct sk_buff **pskb,
+				const struct net_device *in,
+				const struct net_device *out,
+				int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *reasm;
+
+	/* Previously seen (loopback)?  */
+	if ((*pskb)->nfct)
+		return NF_ACCEPT;
+
+	reasm = nf_ct_frag6_gather(*pskb);
+
+	/* queued */
+	if (reasm == NULL)
+		return NF_STOLEN;
+
+	/* error occured or not fragmented */
+	if (reasm == *pskb)
+		return NF_ACCEPT;
+
+	nf_ct_frag6_output(hooknum, reasm, (struct net_device *)in,
+			   (struct net_device *)out, okfn);
+
+	return NF_STOLEN;
+}
+
+static unsigned int ipv6_conntrack_in(unsigned int hooknum,
+				      struct sk_buff **pskb,
+				      const struct net_device *in,
+				      const struct net_device *out,
+				      int (*okfn)(struct sk_buff *))
+{
+	struct sk_buff *reasm = (*pskb)->nfct_reasm;
+
+	/* 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(PF_INET6, hooknum, &reasm);
+			if (ret != NF_ACCEPT)
+				return ret;
+		}
+		nf_conntrack_get(reasm->nfct);
+		(*pskb)->nfct = reasm->nfct;
+		return NF_ACCEPT;
+	}
+
+	return nf_conntrack_in(PF_INET6, hooknum, pskb);
+}
+
+static unsigned int ipv6_conntrack_local(unsigned int hooknum,
+					 struct sk_buff **pskb,
+					 const struct net_device *in,
+					 const struct net_device *out,
+					 int (*okfn)(struct sk_buff *))
+{
+	/* root is playing with raw sockets. */
+	if ((*pskb)->len < sizeof(struct ipv6hdr)) {
+		if (net_ratelimit())
+			printk("ipv6_conntrack_local: packet too short\n");
+		return NF_ACCEPT;
+	}
+	return ipv6_conntrack_in(hooknum, pskb, in, out, okfn);
+}
+
+/* Connection tracking may drop packets, but never alters them, so
+   make it the first hook. */
+static struct nf_hook_ops ipv6_conntrack_defrag_ops = {
+	.hook		= ipv6_defrag,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_PRE_ROUTING,
+	.priority	= NF_IP6_PRI_CONNTRACK_DEFRAG,
+};
+
+static struct nf_hook_ops ipv6_conntrack_in_ops = {
+	.hook		= ipv6_conntrack_in,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_PRE_ROUTING,
+	.priority	= NF_IP6_PRI_CONNTRACK,
+};
+
+static struct nf_hook_ops ipv6_conntrack_local_out_ops = {
+	.hook		= ipv6_conntrack_local,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_LOCAL_OUT,
+	.priority	= NF_IP6_PRI_CONNTRACK,
+};
+
+static struct nf_hook_ops ipv6_conntrack_defrag_local_out_ops = {
+	.hook		= ipv6_defrag,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_LOCAL_OUT,
+	.priority	= NF_IP6_PRI_CONNTRACK_DEFRAG,
+};
+
+/* Refragmenter; last chance. */
+static struct nf_hook_ops ipv6_conntrack_out_ops = {
+	.hook		= ipv6_confirm,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_POST_ROUTING,
+	.priority	= NF_IP6_PRI_LAST,
+};
+
+static struct nf_hook_ops ipv6_conntrack_local_in_ops = {
+	.hook		= ipv6_confirm,
+	.owner		= THIS_MODULE,
+	.pf		= PF_INET6,
+	.hooknum	= NF_IP6_LOCAL_IN,
+	.priority	= NF_IP6_PRI_LAST-1,
+};
+
+#ifdef CONFIG_SYSCTL
+
+/* From nf_conntrack_proto_icmpv6.c */
+extern unsigned long nf_ct_icmpv6_timeout;
+
+/* From nf_conntrack_frag6.c */
+extern unsigned long nf_ct_frag6_timeout;
+extern unsigned long nf_ct_frag6_low_thresh;
+extern unsigned long nf_ct_frag6_high_thresh;
+
+static struct ctl_table_header *nf_ct_ipv6_sysctl_header;
+
+static ctl_table nf_ct_sysctl_table[] = {
+	{
+		.ctl_name	= NET_NF_CONNTRACK_ICMPV6_TIMEOUT,
+		.procname	= "nf_conntrack_icmpv6_timeout",
+		.data		= &nf_ct_icmpv6_timeout,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+	},
+	{
+		.ctl_name	= NET_NF_CONNTRACK_FRAG6_TIMEOUT,
+		.procname	= "nf_conntrack_frag6_timeout",
+		.data		= &nf_ct_frag6_timeout,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+	},
+	{
+		.ctl_name	= NET_NF_CONNTRACK_FRAG6_LOW_THRESH,
+		.procname	= "nf_conntrack_frag6_low_thresh",
+		.data		= &nf_ct_frag6_low_thresh,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+	},
+	{
+		.ctl_name	= NET_NF_CONNTRACK_FRAG6_HIGH_THRESH,
+		.procname	= "nf_conntrack_frag6_high_thresh",
+		.data		= &nf_ct_frag6_high_thresh,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_jiffies,
+	},
+        { .ctl_name = 0 }
+};
+
+static ctl_table nf_ct_netfilter_table[] = {
+	{
+		.ctl_name	= NET_NETFILTER,
+		.procname	= "netfilter",
+		.mode		= 0555,
+		.child		= nf_ct_sysctl_table,
+	},
+	{ .ctl_name = 0 }
+};
+
+static ctl_table nf_ct_net_table[] = {
+	{
+		.ctl_name	= CTL_NET,
+		.procname	= "net",
+		.mode		= 0555,
+		.child		= nf_ct_netfilter_table,
+	},
+	{ .ctl_name = 0 }
+};
+#endif
+
+struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6 = {
+	.l3proto		= PF_INET6,
+	.name			= "ipv6",
+	.pkt_to_tuple		= ipv6_pkt_to_tuple,
+	.invert_tuple		= ipv6_invert_tuple,
+	.print_tuple		= ipv6_print_tuple,
+	.print_conntrack	= ipv6_print_conntrack,
+	.prepare		= ipv6_prepare,
+	.get_features		= ipv6_get_features,
+	.me			= THIS_MODULE,
+};
+
+extern struct nf_conntrack_protocol nf_conntrack_protocol_tcp6;
+extern struct nf_conntrack_protocol nf_conntrack_protocol_udp6;
+extern struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6;
+extern int nf_ct_frag6_init(void);
+extern void nf_ct_frag6_cleanup(void);
+static int init_or_cleanup(int init)
+{
+	int ret = 0;
+
+	if (!init) goto cleanup;
+
+	ret = nf_ct_frag6_init();
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't initialize frag6.\n");
+		goto cleanup_nothing;
+	}
+	ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_tcp6);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register tcp.\n");
+		goto cleanup_frag6;
+	}
+
+	ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_udp6);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register udp.\n");
+		goto cleanup_tcp;
+	}
+
+	ret = nf_conntrack_protocol_register(&nf_conntrack_protocol_icmpv6);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register icmpv6.\n");
+		goto cleanup_udp;
+	}
+
+	ret = nf_conntrack_l3proto_register(&nf_conntrack_l3proto_ipv6);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register ipv6\n");
+		goto cleanup_icmpv6;
+	}
+
+	ret = nf_register_hook(&ipv6_conntrack_defrag_ops);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register pre-routing defrag "
+		       "hook.\n");
+		goto cleanup_ipv6;
+	}
+
+	ret = nf_register_hook(&ipv6_conntrack_defrag_local_out_ops);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register local_out defrag "
+		       "hook.\n");
+		goto cleanup_defragops;
+	}
+
+	ret = nf_register_hook(&ipv6_conntrack_in_ops);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register pre-routing hook.\n");
+		goto cleanup_defraglocalops;
+	}
+
+	ret = nf_register_hook(&ipv6_conntrack_local_out_ops);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register local out hook.\n");
+		goto cleanup_inops;
+	}
+
+	ret = nf_register_hook(&ipv6_conntrack_out_ops);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register post-routing hook.\n");
+		goto cleanup_inandlocalops;
+	}
+
+	ret = nf_register_hook(&ipv6_conntrack_local_in_ops);
+	if (ret < 0) {
+		printk("nf_conntrack_ipv6: can't register local in hook.\n");
+		goto cleanup_inoutandlocalops;
+	}
+
+#ifdef CONFIG_SYSCTL
+	nf_ct_ipv6_sysctl_header = register_sysctl_table(nf_ct_net_table, 0);
+	if (nf_ct_ipv6_sysctl_header == NULL) {
+		printk("nf_conntrack: can't register to sysctl.\n");
+		ret = -ENOMEM;
+		goto cleanup_localinops;
+	}
+#endif
+	return ret;
+
+ cleanup:
+	synchronize_net();
+#ifdef CONFIG_SYSCTL
+ 	unregister_sysctl_table(nf_ct_ipv6_sysctl_header);
+ cleanup_localinops:
+#endif
+	nf_unregister_hook(&ipv6_conntrack_local_in_ops);
+ cleanup_inoutandlocalops:
+	nf_unregister_hook(&ipv6_conntrack_out_ops);
+ cleanup_inandlocalops:
+	nf_unregister_hook(&ipv6_conntrack_local_out_ops);
+ cleanup_inops:
+	nf_unregister_hook(&ipv6_conntrack_in_ops);
+ cleanup_defraglocalops:
+	nf_unregister_hook(&ipv6_conntrack_defrag_local_out_ops);
+ cleanup_defragops:
+	nf_unregister_hook(&ipv6_conntrack_defrag_ops);
+ cleanup_ipv6:
+	nf_conntrack_l3proto_unregister(&nf_conntrack_l3proto_ipv6);
+ cleanup_icmpv6:
+	nf_conntrack_protocol_unregister(&nf_conntrack_protocol_icmpv6);
+ cleanup_udp:
+	nf_conntrack_protocol_unregister(&nf_conntrack_protocol_udp6);
+ cleanup_tcp:
+	nf_conntrack_protocol_unregister(&nf_conntrack_protocol_tcp6);
+ cleanup_frag6:
+	nf_ct_frag6_cleanup();
+ cleanup_nothing:
+	return ret;
+}
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yasuyuki KOZAKAI @USAGI <yasuyuki.kozakai@toshiba.co.jp>");
+
+static int __init init(void)
+{
+	need_nf_conntrack();
+	return init_or_cleanup(1);
+}
+
+static void __exit fini(void)
+{
+	init_or_cleanup(0);
+}
+
+module_init(init);
+module_exit(fini);
+
+void need_ip6_conntrack(void)
+{
+}
+
+EXPORT_SYMBOL(need_ip6_conntrack);