[NETFILTER]: Add ctnetlink subsystem

Add ctnetlink subsystem for userspace-access to ip_conntrack table.
This allows reading and updating of existing entries, as well as
creating new ones (and new expect's) via nfnetlink.

Please note the 'strange' byte order: nfattr (tag+length) are in host
byte order, while the payload is always guaranteed to be in network
byte order.  This allows a simple userspace process to encapsulate netlink
messages into arch-independent udp packets by just processing/swapping the
headers and not knowing anything about the actual payload.

Signed-off-by: Harald Welte <laforge@netfilter.org>
Signed-off-by: Patrick McHardy <kaber@trash.net>
Signed-off-by: David S. Miller <davem@davemloft.net>

7 files changed, 210 insertions, 18 deletions

diff --git a/include/linux/netfilter/nfnetlink.h b/include/linux/netfilter/nfnetlink.h
index 8f1bfb8d650b..ace7a7be0742 100644
--- a/include/linux/netfilter/nfnetlink.h
+++ b/include/linux/netfilter/nfnetlink.h
@@ -56,7 +56,7 @@ struct nfgenmsg {
         u_int16_t res_id;               /* resource id */
 } __attribute__ ((packed));
 
-#define NFNETLINK_V1    1
+#define NFNETLINK_V0    0
 
 #define NFM_NFA(n)      ((struct nfattr *)(((char *)(n)) \
         + NLMSG_ALIGN(sizeof(struct nfgenmsg))))
@@ -81,6 +81,7 @@ enum nfnl_subsys_id {
 
 #ifdef __KERNEL__
 
+#include <linux/netlink.h>
 #include <linux/capability.h>
 
 struct nfnl_callback
diff --git a/include/linux/netfilter/nfnetlink_conntrack.h b/include/linux/netfilter/nfnetlink_conntrack.h
new file mode 100644
index 000000000000..fb528e0e3bd9
--- /dev/null
+++ b/include/linux/netfilter/nfnetlink_conntrack.h
@@ -0,0 +1,123 @@
+#ifndef _IPCONNTRACK_NETLINK_H
+#define _IPCONNTRACK_NETLINK_H
+#include <linux/netfilter/nfnetlink.h>
+
+enum cntl_msg_types {
+        IPCTNL_MSG_CT_NEW,
+        IPCTNL_MSG_CT_GET,
+        IPCTNL_MSG_CT_DELETE,
+        IPCTNL_MSG_CT_GET_CTRZERO,
+
+        IPCTNL_MSG_MAX
+};
+
+enum ctnl_exp_msg_types {
+        IPCTNL_MSG_EXP_NEW,
+        IPCTNL_MSG_EXP_GET,
+        IPCTNL_MSG_EXP_DELETE,
+
+        IPCTNL_MSG_EXP_MAX
+};
+
+
+enum ctattr_type {
+        CTA_UNSPEC,
+        CTA_TUPLE_ORIG,
+        CTA_TUPLE_REPLY,
+        CTA_STATUS,
+        CTA_PROTOINFO,
+        CTA_HELP,
+        CTA_NAT,
+        CTA_TIMEOUT,
+        CTA_MARK,
+        CTA_COUNTERS_ORIG,
+        CTA_COUNTERS_REPLY,
+        CTA_USE,
+        CTA_EXPECT,
+        CTA_ID,
+        __CTA_MAX
+};
+#define CTA_MAX (__CTA_MAX - 1)
+
+enum ctattr_tuple {
+        CTA_TUPLE_UNSPEC,
+        CTA_TUPLE_IP,
+        CTA_TUPLE_PROTO,
+        __CTA_TUPLE_MAX
+};
+#define CTA_TUPLE_MAX (__CTA_TUPLE_MAX - 1)
+
+enum ctattr_ip {
+        CTA_IP_UNSPEC,
+        CTA_IP_V4_SRC,
+        CTA_IP_V4_DST,
+        CTA_IP_V6_SRC,
+        CTA_IP_V6_DST,
+        __CTA_IP_MAX
+};
+#define CTA_IP_MAX (__CTA_IP_MAX - 1)
+
+enum ctattr_l4proto {
+        CTA_PROTO_UNSPEC,
+        CTA_PROTO_NUM,
+        CTA_PROTO_SRC_PORT,
+        CTA_PROTO_DST_PORT,
+        CTA_PROTO_ICMP_ID,
+        CTA_PROTO_ICMP_TYPE,
+        CTA_PROTO_ICMP_CODE,
+        __CTA_PROTO_MAX
+};
+#define CTA_PROTO_MAX (__CTA_PROTO_MAX - 1)
+
+enum ctattr_protoinfo {
+        CTA_PROTOINFO_UNSPEC,
+        CTA_PROTOINFO_TCP_STATE,
+        __CTA_PROTOINFO_MAX
+};
+#define CTA_PROTOINFO_MAX (__CTA_PROTOINFO_MAX - 1)
+
+enum ctattr_counters {
+        CTA_COUNTERS_UNSPEC,
+        CTA_COUNTERS_PACKETS,
+        CTA_COUNTERS_BYTES,
+        __CTA_COUNTERS_MAX
+};
+#define CTA_COUNTERS_MAX (__CTA_COUNTERS_MAX - 1)
+
+enum ctattr_nat {
+        CTA_NAT_UNSPEC,
+        CTA_NAT_MINIP,
+        CTA_NAT_MAXIP,
+        CTA_NAT_PROTO,
+        __CTA_NAT_MAX
+};
+#define CTA_NAT_MAX (__CTA_NAT_MAX - 1)
+
+enum ctattr_protonat {
+        CTA_PROTONAT_UNSPEC,
+        CTA_PROTONAT_PORT_MIN,
+        CTA_PROTONAT_PORT_MAX,
+        __CTA_PROTONAT_MAX
+};
+#define CTA_PROTONAT_MAX (__CTA_PROTONAT_MAX - 1)
+
+enum ctattr_expect {
+        CTA_EXPECT_UNSPEC,
+        CTA_EXPECT_TUPLE,
+        CTA_EXPECT_MASK,
+        CTA_EXPECT_TIMEOUT,
+        CTA_EXPECT_ID,
+        __CTA_EXPECT_MAX
+};
+#define CTA_EXPECT_MAX (__CTA_EXPECT_MAX - 1)
+
+enum ctattr_help {
+        CTA_HELP_UNSPEC,
+        CTA_HELP_NAME,
+        __CTA_HELP_MAX
+};
+#define CTA_HELP_MAX (__CTA_HELP_MAX - 1)
+
+#define CTA_HELP_MAXNAMESIZE    32
+
+#endif /* _IPCONNTRACK_NETLINK_H */
diff --git a/include/linux/netfilter_ipv4/ip_conntrack.h b/include/linux/netfilter_ipv4/ip_conntrack.h
index ae1270c97b50..ff2c1c6001f9 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack.h
@@ -209,6 +209,9 @@ struct ip_conntrack
         /* Current number of expected connections */
         unsigned int expecting;
 
+        /* Unique ID that identifies this conntrack*/
+        unsigned int id;
+
         /* Helper, if any. */
         struct ip_conntrack_helper *helper;
 
@@ -257,6 +260,9 @@ struct ip_conntrack_expect
         /* Usage count. */
         atomic_t use;
 
+        /* Unique ID */
+        unsigned int id;
+
 #ifdef CONFIG_IP_NF_NAT_NEEDED
         /* This is the original per-proto part, used to map the
          * expected connection the way the recipient expects. */
@@ -296,7 +302,12 @@ ip_conntrack_get(const struct sk_buff *skb, enum ip_conntrack_info *ctinfo)
 }
 
 /* decrement reference count on a conntrack */
-extern void ip_conntrack_put(struct ip_conntrack *ct);
+static inline void
+ip_conntrack_put(struct ip_conntrack *ct)
+{
+        IP_NF_ASSERT(ct);
+        nf_conntrack_put(&ct->ct_general);
+}
 
 /* call to create an explicit dependency on ip_conntrack. */
 extern void need_ip_conntrack(void);
@@ -331,6 +342,39 @@ extern void
 ip_ct_iterate_cleanup(int (*iter)(struct ip_conntrack *i, void *data),
                       void *data);
 
+extern struct ip_conntrack_helper *
+__ip_conntrack_helper_find_byname(const char *);
+extern struct ip_conntrack_helper *
+ip_conntrack_helper_find_get(const struct ip_conntrack_tuple *tuple);
+extern void ip_conntrack_helper_put(struct ip_conntrack_helper *helper);
+
+extern struct ip_conntrack_protocol *
+__ip_conntrack_proto_find(u_int8_t protocol);
+extern struct ip_conntrack_protocol *
+ip_conntrack_proto_find_get(u_int8_t protocol);
+extern void ip_conntrack_proto_put(struct ip_conntrack_protocol *proto);
+
+extern void ip_ct_remove_expectations(struct ip_conntrack *ct);
+
+extern struct ip_conntrack *ip_conntrack_alloc(struct ip_conntrack_tuple *,
+                                               struct ip_conntrack_tuple *);
+
+extern void ip_conntrack_free(struct ip_conntrack *ct);
+
+extern void ip_conntrack_hash_insert(struct ip_conntrack *ct);
+
+extern struct ip_conntrack_expect *
+__ip_conntrack_expect_find(const struct ip_conntrack_tuple *tuple);
+
+extern struct ip_conntrack_expect *
+ip_conntrack_expect_find_get(const struct ip_conntrack_tuple *tuple);
+
+extern struct ip_conntrack_tuple_hash *
+__ip_conntrack_find(const struct ip_conntrack_tuple *tuple,
+                    const struct ip_conntrack *ignored_conntrack);
+
+extern void ip_conntrack_flush(void);
+
 /* It's confirmed if it is, or has been in the hash table. */
 static inline int is_confirmed(struct ip_conntrack *ct)
 {
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_core.h b/include/linux/netfilter_ipv4/ip_conntrack_core.h
index 46eeea1e2733..fbf6c3e41647 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_core.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_core.h
@@ -2,6 +2,9 @@
 #define _IP_CONNTRACK_CORE_H
 #include <linux/netfilter.h>
 
+#define MAX_IP_CT_PROTO 256
+extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO];
+
 /* This header is used to share core functionality between the
    standalone connection tracking module, and the compatibility layer's use
    of connection tracking. */
@@ -53,6 +56,8 @@ struct ip_conntrack_ecache;
 extern void __ip_ct_deliver_cached_events(struct ip_conntrack_ecache *ec);
 #endif
 
+extern void __ip_ct_expect_unlink_destroy(struct ip_conntrack_expect *exp);
+
 extern struct list_head *ip_conntrack_hash;
 extern struct list_head ip_conntrack_expect_list;
 extern rwlock_t ip_conntrack_lock;
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_helper.h b/include/linux/netfilter_ipv4/ip_conntrack_helper.h
index 3692daa93dec..8d69279ccfe4 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_helper.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_helper.h
@@ -24,6 +24,8 @@ struct ip_conntrack_helper
         int (*help)(struct sk_buff **pskb,
                     struct ip_conntrack *ct,
                     enum ip_conntrack_info conntrackinfo);
+
+        int (*to_nfattr)(struct sk_buff *skb, const struct ip_conntrack *ct);
 };
 
 extern int ip_conntrack_helper_register(struct ip_conntrack_helper *);
diff --git a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h
index e20b57c5e1b7..b6b99be8632a 100644
--- a/include/linux/netfilter_ipv4/ip_conntrack_protocol.h
+++ b/include/linux/netfilter_ipv4/ip_conntrack_protocol.h
@@ -2,6 +2,7 @@
 #ifndef _IP_CONNTRACK_PROTOCOL_H
 #define _IP_CONNTRACK_PROTOCOL_H
 #include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
 
 struct seq_file;
 
@@ -47,22 +48,22 @@ struct ip_conntrack_protocol
         int (*error)(struct sk_buff *skb, enum ip_conntrack_info *ctinfo,
                      unsigned int hooknum);
 
+        /* convert protoinfo to nfnetink attributes */
+        int (*to_nfattr)(struct sk_buff *skb, struct nfattr *nfa,
+                         const struct ip_conntrack *ct);
+
+        int (*tuple_to_nfattr)(struct sk_buff *skb,
+                               const struct ip_conntrack_tuple *t);
+        int (*nfattr_to_tuple)(struct nfattr *tb[],
+                               struct ip_conntrack_tuple *t);
+
         /* Module (if any) which this is connected to. */
         struct module *me;
 };
 
-#define MAX_IP_CT_PROTO 256
-extern struct ip_conntrack_protocol *ip_ct_protos[MAX_IP_CT_PROTO];
-
 /* Protocol registration. */
 extern int ip_conntrack_protocol_register(struct ip_conntrack_protocol *proto);
 extern void ip_conntrack_protocol_unregister(struct ip_conntrack_protocol *proto);
-
-static inline struct ip_conntrack_protocol *ip_ct_find_proto(u_int8_t protocol)
-{
-        return ip_ct_protos[protocol];
-}
-
 /* Existing built-in protocols */
 extern struct ip_conntrack_protocol ip_conntrack_protocol_tcp;
 extern struct ip_conntrack_protocol ip_conntrack_protocol_udp;
@@ -73,6 +74,11 @@ extern int ip_conntrack_protocol_tcp_init(void);
 /* Log invalid packets */
 extern unsigned int ip_ct_log_invalid;
 
+extern int ip_ct_port_tuple_to_nfattr(struct sk_buff *,
+                                      const struct ip_conntrack_tuple *);
+extern int ip_ct_port_nfattr_to_tuple(struct nfattr *tb[],
+                                      struct ip_conntrack_tuple *);
+
 #ifdef CONFIG_SYSCTL
 #ifdef DEBUG_INVALID_PACKETS
 #define LOG_INVALID(proto) \
diff --git a/include/linux/netfilter_ipv4/ip_nat_protocol.h b/include/linux/netfilter_ipv4/ip_nat_protocol.h
index 129708c22386..ef63aa991a06 100644
--- a/include/linux/netfilter_ipv4/ip_nat_protocol.h
+++ b/include/linux/netfilter_ipv4/ip_nat_protocol.h
@@ -4,6 +4,9 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <linux/netfilter_ipv4/ip_nat.h>
+#include <linux/netfilter/nfnetlink_conntrack.h>
+
 struct iphdr;
 struct ip_nat_range;
 
@@ -15,6 +18,8 @@ struct ip_nat_protocol
         /* Protocol number. */
         unsigned int protonum;
 
+        struct module *me;
+
         /* Translate a packet to the target according to manip type.
            Return true if succeeded. */
         int (*manip_pkt)(struct sk_buff **pskb,
@@ -43,19 +48,20 @@ struct ip_nat_protocol
 
         unsigned int (*print_range)(char *buffer,
                                     const struct ip_nat_range *range);
-};
 
-#define MAX_IP_NAT_PROTO 256
-extern struct ip_nat_protocol *ip_nat_protos[MAX_IP_NAT_PROTO];
+        int (*range_to_nfattr)(struct sk_buff *skb,
+                               const struct ip_nat_range *range);
+
+        int (*nfattr_to_range)(struct nfattr *tb[],
+                               struct ip_nat_range *range);
+};
 
 /* Protocol registration. */
 extern int ip_nat_protocol_register(struct ip_nat_protocol *proto);
 extern void ip_nat_protocol_unregister(struct ip_nat_protocol *proto);
 
-static inline struct ip_nat_protocol *ip_nat_find_proto(u_int8_t protocol)
-{
-        return ip_nat_protos[protocol];
-}
+extern struct ip_nat_protocol *ip_nat_proto_find_get(u_int8_t protocol);
+extern void ip_nat_proto_put(struct ip_nat_protocol *proto);
 
 /* Built-in protocols. */
 extern struct ip_nat_protocol ip_nat_protocol_tcp;
@@ -67,4 +73,9 @@ extern int init_protocols(void) __init;
 extern void cleanup_protocols(void);
 extern struct ip_nat_protocol *find_nat_proto(u_int16_t protonum);
 
+extern int ip_nat_port_range_to_nfattr(struct sk_buff *skb,
+                                       const struct ip_nat_range *range);
+extern int ip_nat_port_nfattr_to_range(struct nfattr *tb[],
+                                       struct ip_nat_range *range);
+
 #endif /*_IP_NAT_PROTO_H*/