[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, 190 insertions, 0 deletions

diff --git a/include/net/netfilter/nf_conntrack_tuple.h b/include/net/netfilter/nf_conntrack_tuple.h
new file mode 100644
index 0000000000000..14ce790e5c65c
--- /dev/null
+++ b/include/net/netfilter/nf_conntrack_tuple.h
@@ -0,0 +1,190 @@
+/*
+ * Definitions and Declarations for tuple.
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- generalize L3 protocol dependent part.
+ *
+ * Derived from include/linux/netfiter_ipv4/ip_conntrack_tuple.h
+ */
+
+#ifndef _NF_CONNTRACK_TUPLE_H
+#define _NF_CONNTRACK_TUPLE_H
+
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+
+/* A `tuple' is a structure containing the information to uniquely
+  identify a connection.  ie. if two packets have the same tuple, they
+  are in the same connection; if not, they are not.
+
+  We divide the structure along "manipulatable" and
+  "non-manipulatable" lines, for the benefit of the NAT code.
+*/
+
+#define NF_CT_TUPLE_L3SIZE	4
+
+/* The l3 protocol-specific manipulable parts of the tuple: always in
+   network order! */
+union nf_conntrack_man_l3proto {
+	u_int32_t all[NF_CT_TUPLE_L3SIZE];
+	u_int32_t ip;
+	u_int32_t ip6[4];
+};
+
+/* The protocol-specific manipulable parts of the tuple: always in
+   network order! */
+union nf_conntrack_man_proto
+{
+	/* Add other protocols here. */
+	u_int16_t all;
+
+	struct {
+		u_int16_t port;
+	} tcp;
+	struct {
+		u_int16_t port;
+	} udp;
+	struct {
+		u_int16_t id;
+	} icmp;
+	struct {
+		u_int16_t port;
+	} sctp;
+};
+
+/* The manipulable part of the tuple. */
+struct nf_conntrack_man
+{
+	union nf_conntrack_man_l3proto u3;
+	union nf_conntrack_man_proto u;
+	/* Layer 3 protocol */
+	u_int16_t l3num;
+};
+
+/* This contains the information to distinguish a connection. */
+struct nf_conntrack_tuple
+{
+	struct nf_conntrack_man src;
+
+	/* These are the parts of the tuple which are fixed. */
+	struct {
+		union {
+			u_int32_t all[NF_CT_TUPLE_L3SIZE];
+			u_int32_t ip;
+			u_int32_t ip6[4];
+		} u3;
+		union {
+			/* Add other protocols here. */
+			u_int16_t all;
+
+			struct {
+				u_int16_t port;
+			} tcp;
+			struct {
+				u_int16_t port;
+			} udp;
+			struct {
+				u_int8_t type, code;
+			} icmp;
+			struct {
+				u_int16_t port;
+			} sctp;
+		} u;
+
+		/* The protocol. */
+		u_int8_t protonum;
+
+		/* The direction (for tuplehash) */
+		u_int8_t dir;
+	} dst;
+};
+
+/* This is optimized opposed to a memset of the whole structure.  Everything we
+ * really care about is the  source/destination unions */
+#define NF_CT_TUPLE_U_BLANK(tuple)                              	\
+        do {                                                    	\
+                (tuple)->src.u.all = 0;                         	\
+                (tuple)->dst.u.all = 0;                         	\
+		memset(&(tuple)->src.u3, 0, sizeof((tuple)->src.u3));	\
+		memset(&(tuple)->dst.u3, 0, sizeof((tuple)->dst.u3));	\
+        } while (0)
+
+#ifdef __KERNEL__
+
+#define NF_CT_DUMP_TUPLE(tp)						    \
+DEBUGP("tuple %p: %u %u %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x %hu -> %04x:%04x:%04x:%04x:%04x:%04x:%04x:%04x %hu\n",					    \
+	(tp), (tp)->src.l3num, (tp)->dst.protonum,			    \
+	NIP6(*(struct in6_addr *)(tp)->src.u3.all), ntohs((tp)->src.u.all), \
+	NIP6(*(struct in6_addr *)(tp)->dst.u3.all), ntohs((tp)->dst.u.all))
+
+/* If we're the first tuple, it's the original dir. */
+#define NF_CT_DIRECTION(h)						\
+	((enum ip_conntrack_dir)(h)->tuple.dst.dir)
+
+/* Connections have two entries in the hash table: one for each way */
+struct nf_conntrack_tuple_hash
+{
+	struct list_head list;
+
+	struct nf_conntrack_tuple tuple;
+};
+
+#endif /* __KERNEL__ */
+
+static inline int nf_ct_tuple_src_equal(const struct nf_conntrack_tuple *t1,
+				        const struct nf_conntrack_tuple *t2)
+{ 
+	return (t1->src.u3.all[0] == t2->src.u3.all[0] &&
+		t1->src.u3.all[1] == t2->src.u3.all[1] &&
+		t1->src.u3.all[2] == t2->src.u3.all[2] &&
+		t1->src.u3.all[3] == t2->src.u3.all[3] &&
+		t1->src.u.all == t2->src.u.all &&
+		t1->src.l3num == t2->src.l3num &&
+		t1->dst.protonum == t2->dst.protonum);
+}
+
+static inline int nf_ct_tuple_dst_equal(const struct nf_conntrack_tuple *t1,
+				        const struct nf_conntrack_tuple *t2)
+{
+	return (t1->dst.u3.all[0] == t2->dst.u3.all[0] &&
+		t1->dst.u3.all[1] == t2->dst.u3.all[1] &&
+		t1->dst.u3.all[2] == t2->dst.u3.all[2] &&
+		t1->dst.u3.all[3] == t2->dst.u3.all[3] &&
+		t1->dst.u.all == t2->dst.u.all &&
+		t1->src.l3num == t2->src.l3num &&
+		t1->dst.protonum == t2->dst.protonum);
+}
+
+static inline int nf_ct_tuple_equal(const struct nf_conntrack_tuple *t1,
+				    const struct nf_conntrack_tuple *t2)
+{
+	return nf_ct_tuple_src_equal(t1, t2) && nf_ct_tuple_dst_equal(t1, t2);
+}
+
+static inline int nf_ct_tuple_mask_cmp(const struct nf_conntrack_tuple *t,
+				       const struct nf_conntrack_tuple *tuple,
+				       const struct nf_conntrack_tuple *mask)
+{
+	int count = 0;
+
+        for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
+                if ((t->src.u3.all[count] ^ tuple->src.u3.all[count]) &
+                    mask->src.u3.all[count])
+                        return 0;
+        }
+
+        for (count = 0; count < NF_CT_TUPLE_L3SIZE; count++){
+                if ((t->dst.u3.all[count] ^ tuple->dst.u3.all[count]) &
+                    mask->dst.u3.all[count])
+                        return 0;
+        }
+
+        if ((t->src.u.all ^ tuple->src.u.all) & mask->src.u.all ||
+            (t->dst.u.all ^ tuple->dst.u.all) & mask->dst.u.all ||
+            (t->src.l3num ^ tuple->src.l3num) & mask->src.l3num ||
+            (t->dst.protonum ^ tuple->dst.protonum) & mask->dst.protonum)
+                return 0;
+
+        return 1;
+}
+
+#endif /* _NF_CONNTRACK_TUPLE_H */