[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, 354 insertions, 0 deletions

diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
new file mode 100644
index 0000000000000..cc4825610795a
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack.h
@@ -0,0 +1,354 @@
+/*
+ * Connection state tracking for netfilter.  This is separated from,
+ * but required by, the (future) NAT layer; it can also be used by an iptables
+ * extension.
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- generalize L3 protocol dependent part.
+ *
+ * Derived from include/linux/netfiter_ipv4/ip_conntrack.h
+ */
+
+#ifndef _NF_CONNTRACK_H
+#define _NF_CONNTRACK_H
+
+#include <linux/netfilter/nf_conntrack_common.h>
+
+#ifdef __KERNEL__
+#include <linux/config.h>
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <asm/atomic.h>
+
+#include <linux/netfilter/nf_conntrack_tcp.h>
+#include <linux/netfilter/nf_conntrack_sctp.h>
+#include <net/netfilter/ipv4/nf_conntrack_icmp.h>
+#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
+
+#include <net/netfilter/nf_conntrack_tuple.h>
+
+/* per conntrack: protocol private data */
+union nf_conntrack_proto {
+	/* insert conntrack proto private data here */
+	struct ip_ct_sctp sctp;
+	struct ip_ct_tcp tcp;
+	struct ip_ct_icmp icmp;
+	struct nf_ct_icmpv6 icmpv6;
+};
+
+union nf_conntrack_expect_proto {
+	/* insert expect proto private data here */
+};
+
+/* Add protocol helper include file here */
+#include <linux/netfilter/nf_conntrack_ftp.h>
+
+/* per conntrack: application helper private data */
+union nf_conntrack_help {
+	/* insert conntrack helper private data (master) here */
+	struct ip_ct_ftp_master ct_ftp_info;
+};
+
+#include <linux/types.h>
+#include <linux/skbuff.h>
+
+#ifdef CONFIG_NETFILTER_DEBUG
+#define NF_CT_ASSERT(x)							\
+do {									\
+	if (!(x))							\
+		/* Wooah!  I'm tripping my conntrack in a frenzy of	\
+		   netplay... */					\
+		printk("NF_CT_ASSERT: %s:%i(%s)\n",			\
+		       __FILE__, __LINE__, __FUNCTION__);		\
+} while(0)
+#else
+#define NF_CT_ASSERT(x)
+#endif
+
+struct nf_conntrack_helper;
+
+#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
+struct nf_conn
+{
+	/* Usage count in here is 1 for hash table/destruct timer, 1 per skb,
+           plus 1 for any connection(s) we are `master' for */
+	struct nf_conntrack ct_general;
+
+	/* XXX should I move this to the tail ? - Y.K */
+	/* These are my tuples; original and reply */
+	struct nf_conntrack_tuple_hash tuplehash[IP_CT_DIR_MAX];
+
+	/* Have we seen traffic both ways yet? (bitset) */
+	unsigned long status;
+
+	/* Timer function; drops refcnt when it goes off. */
+	struct timer_list timeout;
+
+#ifdef CONFIG_NF_CT_ACCT
+	/* Accounting Information (same cache line as other written members) */
+	struct ip_conntrack_counter counters[IP_CT_DIR_MAX];
+#endif
+	/* If we were expected by an expectation, this will be it */
+	struct nf_conn *master;
+	
+	/* Current number of expected connections */
+	unsigned int expecting;
+
+	/* Helper. if any */
+	struct nf_conntrack_helper *helper;
+
+	/* features - nat, helper, ... used by allocating system */
+	u_int32_t features;
+
+	/* Storage reserved for other modules: */
+
+	union nf_conntrack_proto proto;
+
+#if defined(CONFIG_NF_CONNTRACK_MARK)
+	u_int32_t mark;
+#endif
+
+	/* These members are dynamically allocated. */
+
+	union nf_conntrack_help *help;
+
+	/* Layer 3 dependent members. (ex: NAT) */
+	union {
+		struct nf_conntrack_ipv4 *ipv4;
+	} l3proto;
+	void *data[0];
+};
+
+struct nf_conntrack_expect
+{
+	/* Internal linked list (global expectation list) */
+	struct list_head list;
+
+	/* We expect this tuple, with the following mask */
+	struct nf_conntrack_tuple tuple, mask;
+ 
+	/* Function to call after setup and insertion */
+	void (*expectfn)(struct nf_conn *new,
+			 struct nf_conntrack_expect *this);
+
+	/* The conntrack of the master connection */
+	struct nf_conn *master;
+
+	/* Timer function; deletes the expectation. */
+	struct timer_list timeout;
+
+	/* Usage count. */
+	atomic_t use;
+
+	/* Flags */
+	unsigned int flags;
+
+#ifdef CONFIG_NF_NAT_NEEDED
+	/* This is the original per-proto part, used to map the
+	 * expected connection the way the recipient expects. */
+	union nf_conntrack_manip_proto saved_proto;
+	/* Direction relative to the master connection. */
+	enum ip_conntrack_dir dir;
+#endif
+};
+
+#define NF_CT_EXPECT_PERMANENT 0x1
+
+static inline struct nf_conn *
+nf_ct_tuplehash_to_ctrack(const struct nf_conntrack_tuple_hash *hash)
+{
+	return container_of(hash, struct nf_conn,
+			    tuplehash[hash->tuple.dst.dir]);
+}
+
+/* get master conntrack via master expectation */
+#define master_ct(conntr) (conntr->master)
+
+/* Alter reply tuple (maybe alter helper). */
+extern void
+nf_conntrack_alter_reply(struct nf_conn *conntrack,
+			 const struct nf_conntrack_tuple *newreply);
+
+/* Is this tuple taken? (ignoring any belonging to the given
+   conntrack). */
+extern int
+nf_conntrack_tuple_taken(const struct nf_conntrack_tuple *tuple,
+			 const struct nf_conn *ignored_conntrack);
+
+/* Return conntrack_info and tuple hash for given skb. */
+static inline struct nf_conn *
+nf_ct_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo)
+{
+	*ctinfo = skb->nfctinfo;
+	return (struct nf_conn *)skb->nfct;
+}
+
+/* decrement reference count on a conntrack */
+static inline void nf_ct_put(struct nf_conn *ct)
+{
+	NF_CT_ASSERT(ct);
+	nf_conntrack_put(&ct->ct_general);
+}
+
+/* call to create an explicit dependency on nf_conntrack. */
+extern void need_nf_conntrack(void);
+
+extern int nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse,
+				const struct nf_conntrack_tuple *orig);
+
+extern void __nf_ct_refresh_acct(struct nf_conn *ct,
+				 enum ip_conntrack_info ctinfo,
+				 const struct sk_buff *skb,
+				 unsigned long extra_jiffies,
+				 int do_acct);
+
+/* Refresh conntrack for this many jiffies and do accounting */
+static inline void nf_ct_refresh_acct(struct nf_conn *ct,
+				      enum ip_conntrack_info ctinfo,
+				      const struct sk_buff *skb,
+				      unsigned long extra_jiffies)
+{
+	__nf_ct_refresh_acct(ct, ctinfo, skb, extra_jiffies, 1);
+}
+
+/* Refresh conntrack for this many jiffies */
+static inline void nf_ct_refresh(struct nf_conn *ct,
+				 const struct sk_buff *skb,
+				 unsigned long extra_jiffies)
+{
+	__nf_ct_refresh_acct(ct, 0, skb, extra_jiffies, 0);
+}
+
+/* These are for NAT.  Icky. */
+/* Update TCP window tracking data when NAT mangles the packet */
+extern void nf_conntrack_tcp_update(struct sk_buff *skb,
+				    unsigned int dataoff,
+				    struct nf_conn *conntrack,
+				    int dir);
+
+/* Call me when a conntrack is destroyed. */
+extern void (*nf_conntrack_destroyed)(struct nf_conn *conntrack);
+
+/* Fake conntrack entry for untracked connections */
+extern struct nf_conn nf_conntrack_untracked;
+
+extern int nf_ct_no_defrag;
+
+/* Iterate over all conntracks: if iter returns true, it's deleted. */
+extern void
+nf_ct_iterate_cleanup(int (*iter)(struct nf_conn *i, void *data), void *data);
+extern void nf_conntrack_free(struct nf_conn *ct);
+extern struct nf_conn *
+nf_conntrack_alloc(const struct nf_conntrack_tuple *orig,
+		   const struct nf_conntrack_tuple *repl);
+
+/* It's confirmed if it is, or has been in the hash table. */
+static inline int nf_ct_is_confirmed(struct nf_conn *ct)
+{
+	return test_bit(IPS_CONFIRMED_BIT, &ct->status);
+}
+
+static inline int nf_ct_is_dying(struct nf_conn *ct)
+{
+	return test_bit(IPS_DYING_BIT, &ct->status);
+}
+
+extern unsigned int nf_conntrack_htable_size;
+
+#define NF_CT_STAT_INC(count) (__get_cpu_var(nf_conntrack_stat).count++)
+
+#ifdef CONFIG_NF_CONNTRACK_EVENTS
+#include <linux/notifier.h>
+#include <linux/interrupt.h>
+
+struct nf_conntrack_ecache {
+	struct nf_conn *ct;
+	unsigned int events;
+};
+DECLARE_PER_CPU(struct nf_conntrack_ecache, nf_conntrack_ecache);
+
+#define CONNTRACK_ECACHE(x)	(__get_cpu_var(nf_conntrack_ecache).x)
+
+extern struct notifier_block *nf_conntrack_chain;
+extern struct notifier_block *nf_conntrack_expect_chain;
+
+static inline int nf_conntrack_register_notifier(struct notifier_block *nb)
+{
+	return notifier_chain_register(&nf_conntrack_chain, nb);
+}
+
+static inline int nf_conntrack_unregister_notifier(struct notifier_block *nb)
+{
+	return notifier_chain_unregister(&nf_conntrack_chain, nb);
+}
+
+static inline int
+nf_conntrack_expect_register_notifier(struct notifier_block *nb)
+{
+	return notifier_chain_register(&nf_conntrack_expect_chain, nb);
+}
+
+static inline int
+nf_conntrack_expect_unregister_notifier(struct notifier_block *nb)
+{
+	return notifier_chain_unregister(&nf_conntrack_expect_chain, nb);
+}
+
+extern void nf_ct_deliver_cached_events(const struct nf_conn *ct);
+extern void __nf_ct_event_cache_init(struct nf_conn *ct);
+
+static inline void
+nf_conntrack_event_cache(enum ip_conntrack_events event,
+			 const struct sk_buff *skb)
+{
+	struct nf_conn *ct = (struct nf_conn *)skb->nfct;
+	struct nf_conntrack_ecache *ecache;
+
+	local_bh_disable();
+	ecache = &__get_cpu_var(nf_conntrack_ecache);
+	if (ct != ecache->ct)
+		__nf_ct_event_cache_init(ct);
+	ecache->events |= event;
+	local_bh_enable();
+}
+
+static inline void nf_conntrack_event(enum ip_conntrack_events event,
+				      struct nf_conn *ct)
+{
+	if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct))
+		notifier_call_chain(&nf_conntrack_chain, event, ct);
+}
+
+static inline void
+nf_conntrack_expect_event(enum ip_conntrack_expect_events event,
+			  struct nf_conntrack_expect *exp)
+{
+	notifier_call_chain(&nf_conntrack_expect_chain, event, exp);
+}
+#else /* CONFIG_NF_CONNTRACK_EVENTS */
+static inline void nf_conntrack_event_cache(enum ip_conntrack_events event,
+					    const struct sk_buff *skb) {}
+static inline void nf_conntrack_event(enum ip_conntrack_events event,
+				      struct nf_conn *ct) {}
+static inline void nf_ct_deliver_cached_events(const struct nf_conn *ct) {}
+static inline void
+nf_conntrack_expect_event(enum ip_conntrack_expect_events event,
+			  struct nf_conntrack_expect *exp) {}
+#endif /* CONFIG_NF_CONNTRACK_EVENTS */
+
+/* no helper, no nat */
+#define	NF_CT_F_BASIC	0
+/* for helper */
+#define	NF_CT_F_HELP	1
+/* for nat. */
+#define	NF_CT_F_NAT	2
+#define NF_CT_F_NUM	4
+
+extern int
+nf_conntrack_register_cache(u_int32_t features, const char *name, size_t size,
+			    int (*init_conntrack)(struct nf_conn *, u_int32_t));
+extern void
+nf_conntrack_unregister_cache(u_int32_t features);
+
+#endif /* __KERNEL__ */
+#endif /* _NF_CONNTRACK_H */