Merge master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6

include/linux/genetlink.h

+#ifndef __LINUX_GENERIC_NETLINK_H
+#define __LINUX_GENERIC_NETLINK_H
+
+#include <linux/netlink.h>
+
+#define GENL_NAMSIZ	16	/* length of family name */
+
+#define GENL_MIN_ID	NLMSG_MIN_TYPE
+#define GENL_MAX_ID	1023
+
+struct genlmsghdr {
+	__u8	cmd;
+	__u8	version;
+	__u16	reserved;
+};
+
+#define GENL_HDRLEN	NLMSG_ALIGN(sizeof(struct genlmsghdr))
+
+/*
+ * List of reserved static generic netlink identifiers:
+ */
+#define GENL_ID_GENERATE	0
+#define GENL_ID_CTRL		NLMSG_MIN_TYPE
+
+/**************************************************************************
+ * Controller
+ **************************************************************************/
+
+enum {
+	CTRL_CMD_UNSPEC,
+	CTRL_CMD_NEWFAMILY,
+	CTRL_CMD_DELFAMILY,
+	CTRL_CMD_GETFAMILY,
+	CTRL_CMD_NEWOPS,
+	CTRL_CMD_DELOPS,
+	CTRL_CMD_GETOPS,
+	__CTRL_CMD_MAX,
+};
+
+#define CTRL_CMD_MAX (__CTRL_CMD_MAX - 1)
+
+enum {
+	CTRL_ATTR_UNSPEC,
+	CTRL_ATTR_FAMILY_ID,
+	CTRL_ATTR_FAMILY_NAME,
+	__CTRL_ATTR_MAX,
+};
+
+#define CTRL_ATTR_MAX (__CTRL_ATTR_MAX - 1)
+
+#endif	/* __LINUX_GENERIC_NETLINK_H */

include/linux/netfilter/nf_conntrack_common.h

+#ifndef _NF_CONNTRACK_COMMON_H
+#define _NF_CONNTRACK_COMMON_H
+/* Connection state tracking for netfilter.  This is separated from,
+   but required by, the NAT layer; it can also be used by an iptables
+   extension. */
+enum ip_conntrack_info
+{
+	/* Part of an established connection (either direction). */
+	IP_CT_ESTABLISHED,
+
+	/* Like NEW, but related to an existing connection, or ICMP error
+	   (in either direction). */
+	IP_CT_RELATED,
+
+	/* Started a new connection to track (only
+           IP_CT_DIR_ORIGINAL); may be a retransmission. */
+	IP_CT_NEW,
+
+	/* >= this indicates reply direction */
+	IP_CT_IS_REPLY,
+
+	/* Number of distinct IP_CT types (no NEW in reply dirn). */
+	IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
+};
+
+/* Bitset representing status of connection. */
+enum ip_conntrack_status {
+	/* It's an expected connection: bit 0 set.  This bit never changed */
+	IPS_EXPECTED_BIT = 0,
+	IPS_EXPECTED = (1 << IPS_EXPECTED_BIT),
+
+	/* We've seen packets both ways: bit 1 set.  Can be set, not unset. */
+	IPS_SEEN_REPLY_BIT = 1,
+	IPS_SEEN_REPLY = (1 << IPS_SEEN_REPLY_BIT),
+
+	/* Conntrack should never be early-expired. */
+	IPS_ASSURED_BIT = 2,
+	IPS_ASSURED = (1 << IPS_ASSURED_BIT),
+
+	/* Connection is confirmed: originating packet has left box */
+	IPS_CONFIRMED_BIT = 3,
+	IPS_CONFIRMED = (1 << IPS_CONFIRMED_BIT),
+
+	/* Connection needs src nat in orig dir.  This bit never changed. */
+	IPS_SRC_NAT_BIT = 4,
+	IPS_SRC_NAT = (1 << IPS_SRC_NAT_BIT),
+
+	/* Connection needs dst nat in orig dir.  This bit never changed. */
+	IPS_DST_NAT_BIT = 5,
+	IPS_DST_NAT = (1 << IPS_DST_NAT_BIT),
+
+	/* Both together. */
+	IPS_NAT_MASK = (IPS_DST_NAT | IPS_SRC_NAT),
+
+	/* Connection needs TCP sequence adjusted. */
+	IPS_SEQ_ADJUST_BIT = 6,
+	IPS_SEQ_ADJUST = (1 << IPS_SEQ_ADJUST_BIT),
+
+	/* NAT initialization bits. */
+	IPS_SRC_NAT_DONE_BIT = 7,
+	IPS_SRC_NAT_DONE = (1 << IPS_SRC_NAT_DONE_BIT),
+
+	IPS_DST_NAT_DONE_BIT = 8,
+	IPS_DST_NAT_DONE = (1 << IPS_DST_NAT_DONE_BIT),
+
+	/* Both together */
+	IPS_NAT_DONE_MASK = (IPS_DST_NAT_DONE | IPS_SRC_NAT_DONE),
+
+	/* Connection is dying (removed from lists), can not be unset. */
+	IPS_DYING_BIT = 9,
+	IPS_DYING = (1 << IPS_DYING_BIT),
+};
+
+/* Connection tracking event bits */
+enum ip_conntrack_events
+{
+	/* New conntrack */
+	IPCT_NEW_BIT = 0,
+	IPCT_NEW = (1 << IPCT_NEW_BIT),
+
+	/* Expected connection */
+	IPCT_RELATED_BIT = 1,
+	IPCT_RELATED = (1 << IPCT_RELATED_BIT),
+
+	/* Destroyed conntrack */
+	IPCT_DESTROY_BIT = 2,
+	IPCT_DESTROY = (1 << IPCT_DESTROY_BIT),
+
+	/* Timer has been refreshed */
+	IPCT_REFRESH_BIT = 3,
+	IPCT_REFRESH = (1 << IPCT_REFRESH_BIT),
+
+	/* Status has changed */
+	IPCT_STATUS_BIT = 4,
+	IPCT_STATUS = (1 << IPCT_STATUS_BIT),
+
+	/* Update of protocol info */
+	IPCT_PROTOINFO_BIT = 5,
+	IPCT_PROTOINFO = (1 << IPCT_PROTOINFO_BIT),
+
+	/* Volatile protocol info */
+	IPCT_PROTOINFO_VOLATILE_BIT = 6,
+	IPCT_PROTOINFO_VOLATILE = (1 << IPCT_PROTOINFO_VOLATILE_BIT),
+
+	/* New helper for conntrack */
+	IPCT_HELPER_BIT = 7,
+	IPCT_HELPER = (1 << IPCT_HELPER_BIT),
+
+	/* Update of helper info */
+	IPCT_HELPINFO_BIT = 8,
+	IPCT_HELPINFO = (1 << IPCT_HELPINFO_BIT),
+
+	/* Volatile helper info */
+	IPCT_HELPINFO_VOLATILE_BIT = 9,
+	IPCT_HELPINFO_VOLATILE = (1 << IPCT_HELPINFO_VOLATILE_BIT),
+
+	/* NAT info */
+	IPCT_NATINFO_BIT = 10,
+	IPCT_NATINFO = (1 << IPCT_NATINFO_BIT),
+
+	/* Counter highest bit has been set */
+	IPCT_COUNTER_FILLING_BIT = 11,
+	IPCT_COUNTER_FILLING = (1 << IPCT_COUNTER_FILLING_BIT),
+};
+
+enum ip_conntrack_expect_events {
+	IPEXP_NEW_BIT = 0,
+	IPEXP_NEW = (1 << IPEXP_NEW_BIT),
+};
+
+#ifdef __KERNEL__
+struct ip_conntrack_counter
+{
+	u_int32_t packets;
+	u_int32_t bytes;
+};
+
+struct ip_conntrack_stat
+{
+	unsigned int searched;
+	unsigned int found;
+	unsigned int new;
+	unsigned int invalid;
+	unsigned int ignore;
+	unsigned int delete;
+	unsigned int delete_list;
+	unsigned int insert;
+	unsigned int insert_failed;
+	unsigned int drop;
+	unsigned int early_drop;
+	unsigned int error;
+	unsigned int expect_new;
+	unsigned int expect_create;
+	unsigned int expect_delete;
+};
+
+#endif /* __KERNEL__ */
+
+#endif /* _NF_CONNTRACK_COMMON_H */

include/linux/netfilter/nf_conntrack_ftp.h

+#ifndef _NF_CONNTRACK_FTP_H
+#define _NF_CONNTRACK_FTP_H
+/* FTP tracking. */
+
+/* This enum is exposed to userspace */
+enum ip_ct_ftp_type
+{
+	/* PORT command from client */
+	IP_CT_FTP_PORT,
+	/* PASV response from server */
+	IP_CT_FTP_PASV,
+	/* EPRT command from client */
+	IP_CT_FTP_EPRT,
+	/* EPSV response from server */
+	IP_CT_FTP_EPSV,
+};
+
+#ifdef __KERNEL__
+
+#define FTP_PORT	21
+
+#define NUM_SEQ_TO_REMEMBER 2
+/* This structure exists only once per master */
+struct ip_ct_ftp_master {
+	/* Valid seq positions for cmd matching after newline */
+	u_int32_t seq_aft_nl[IP_CT_DIR_MAX][NUM_SEQ_TO_REMEMBER];
+	/* 0 means seq_match_aft_nl not set */
+	int seq_aft_nl_num[IP_CT_DIR_MAX];
+};
+
+struct ip_conntrack_expect;
+
+/* For NAT to hook in when we find a packet which describes what other
+ * connection we should expect. */
+extern unsigned int (*ip_nat_ftp_hook)(struct sk_buff **pskb,
+				       enum ip_conntrack_info ctinfo,
+				       enum ip_ct_ftp_type type,
+				       unsigned int matchoff,
+				       unsigned int matchlen,
+				       struct ip_conntrack_expect *exp,
+				       u32 *seq);
+#endif /* __KERNEL__ */
+
+#endif /* _NF_CONNTRACK_FTP_H */

include/linux/netfilter/nf_conntrack_sctp.h

+#ifndef _NF_CONNTRACK_SCTP_H
+#define _NF_CONNTRACK_SCTP_H
+/* SCTP tracking. */
+
+#include <linux/netfilter/nf_conntrack_tuple_common.h>
+
+enum sctp_conntrack {
+	SCTP_CONNTRACK_NONE,
+	SCTP_CONNTRACK_CLOSED,
+	SCTP_CONNTRACK_COOKIE_WAIT,
+	SCTP_CONNTRACK_COOKIE_ECHOED,
+	SCTP_CONNTRACK_ESTABLISHED,
+	SCTP_CONNTRACK_SHUTDOWN_SENT,
+	SCTP_CONNTRACK_SHUTDOWN_RECD,
+	SCTP_CONNTRACK_SHUTDOWN_ACK_SENT,
+	SCTP_CONNTRACK_MAX
+};
+
+struct ip_ct_sctp
+{
+	enum sctp_conntrack state;
+
+	u_int32_t vtag[IP_CT_DIR_MAX];
+	u_int32_t ttag[IP_CT_DIR_MAX];
+};
+
+#endif /* _NF_CONNTRACK_SCTP_H */

include/linux/netfilter/nf_conntrack_tcp.h

+#ifndef _NF_CONNTRACK_TCP_H
+#define _NF_CONNTRACK_TCP_H
+/* TCP tracking. */
+
+/* This is exposed to userspace (ctnetlink) */
+enum tcp_conntrack {
+	TCP_CONNTRACK_NONE,
+	TCP_CONNTRACK_SYN_SENT,
+	TCP_CONNTRACK_SYN_RECV,
+	TCP_CONNTRACK_ESTABLISHED,
+	TCP_CONNTRACK_FIN_WAIT,
+	TCP_CONNTRACK_CLOSE_WAIT,
+	TCP_CONNTRACK_LAST_ACK,
+	TCP_CONNTRACK_TIME_WAIT,
+	TCP_CONNTRACK_CLOSE,
+	TCP_CONNTRACK_LISTEN,
+	TCP_CONNTRACK_MAX,
+	TCP_CONNTRACK_IGNORE
+};
+
+/* Window scaling is advertised by the sender */
+#define IP_CT_TCP_FLAG_WINDOW_SCALE		0x01
+
+/* SACK is permitted by the sender */
+#define IP_CT_TCP_FLAG_SACK_PERM		0x02
+
+/* This sender sent FIN first */
+#define IP_CT_TCP_FLAG_CLOSE_INIT		0x03
+
+#ifdef __KERNEL__
+
+struct ip_ct_tcp_state {
+	u_int32_t	td_end;		/* max of seq + len */
+	u_int32_t	td_maxend;	/* max of ack + max(win, 1) */
+	u_int32_t	td_maxwin;	/* max(win) */
+	u_int8_t	td_scale;	/* window scale factor */
+	u_int8_t	loose;		/* used when connection picked up from the middle */
+	u_int8_t	flags;		/* per direction options */
+};
+
+struct ip_ct_tcp
+{
+	struct ip_ct_tcp_state seen[2];	/* connection parameters per direction */
+	u_int8_t	state;		/* state of the connection (enum tcp_conntrack) */
+	/* For detecting stale connections */
+	u_int8_t	last_dir;	/* Direction of the last packet (enum ip_conntrack_dir) */
+	u_int8_t	retrans;	/* Number of retransmitted packets */
+	u_int8_t	last_index;	/* Index of the last packet */
+	u_int32_t	last_seq;	/* Last sequence number seen in dir */
+	u_int32_t	last_ack;	/* Last sequence number seen in opposite dir */
+	u_int32_t	last_end;	/* Last seq + len */
+};
+
+#endif /* __KERNEL__ */
+
+#endif /* _NF_CONNTRACK_TCP_H */

include/linux/netfilter/nf_conntrack_tuple_common.h

+#ifndef _NF_CONNTRACK_TUPLE_COMMON_H
+#define _NF_CONNTRACK_TUPLE_COMMON_H
+
+enum ip_conntrack_dir
+{
+	IP_CT_DIR_ORIGINAL,
+	IP_CT_DIR_REPLY,
+	IP_CT_DIR_MAX
+};
+
+#define CTINFO2DIR(ctinfo) ((ctinfo) >= IP_CT_IS_REPLY ? IP_CT_DIR_REPLY : IP_CT_DIR_ORIGINAL)
+
+#endif /* _NF_CONNTRACK_TUPLE_COMMON_H */

include/linux/netfilter_ipv4/ip_conntrack.h

 #ifndef _IP_CONNTRACK_H
 #define _IP_CONNTRACK_H
-/* Connection state tracking for netfilter.  This is separated from,
-   but required by, the NAT layer; it can also be used by an iptables
-   extension. */
-enum ip_conntrack_info
-{
-	/* Part of an established connection (either direction). */
-	IP_CT_ESTABLISHED,
-
-	/* Like NEW, but related to an existing connection, or ICMP error
-	   (in either direction). */
-	IP_CT_RELATED,
-
-	/* Started a new connection to track (only
-           IP_CT_DIR_ORIGINAL); may be a retransmission. */
-	IP_CT_NEW,
-
-	/* >= this indicates reply direction */
-	IP_CT_IS_REPLY,
-
-	/* Number of distinct IP_CT types (no NEW in reply dirn). */
-	IP_CT_NUMBER = IP_CT_IS_REPLY * 2 - 1
-};
-
-/* Bitset representing status of connection. */
-enum ip_conntrack_status {
-	/* It's an expected connection: bit 0 set.  This bit never changed */
-	IPS_EXPECTED_BIT = 0,
-	IPS_EXPECTED = (1 << IPS_EXPECTED_BIT),
-
-	/* We've seen packets both ways: bit 1 set.  Can be set, not unset. */
-	IPS_SEEN_REPLY_BIT = 1,
-	IPS_SEEN_REPLY = (1 << IPS_SEEN_REPLY_BIT),
-
-	/* Conntrack should never be early-expired. */
-	IPS_ASSURED_BIT = 2,
-	IPS_ASSURED = (1 << IPS_ASSURED_BIT),
-
-	/* Connection is confirmed: originating packet has left box */
-	IPS_CONFIRMED_BIT = 3,
-	IPS_CONFIRMED = (1 << IPS_CONFIRMED_BIT),
-
-	/* Connection needs src nat in orig dir.  This bit never changed. */
-	IPS_SRC_NAT_BIT = 4,
-	IPS_SRC_NAT = (1 << IPS_SRC_NAT_BIT),
-
-	/* Connection needs dst nat in orig dir.  This bit never changed. */
-	IPS_DST_NAT_BIT = 5,
-	IPS_DST_NAT = (1 << IPS_DST_NAT_BIT),
-
-	/* Both together. */
-	IPS_NAT_MASK = (IPS_DST_NAT | IPS_SRC_NAT),
-
-	/* Connection needs TCP sequence adjusted. */
-	IPS_SEQ_ADJUST_BIT = 6,
-	IPS_SEQ_ADJUST = (1 << IPS_SEQ_ADJUST_BIT),
-
-	/* NAT initialization bits. */
-	IPS_SRC_NAT_DONE_BIT = 7,
-	IPS_SRC_NAT_DONE = (1 << IPS_SRC_NAT_DONE_BIT),
-
-	IPS_DST_NAT_DONE_BIT = 8,
-	IPS_DST_NAT_DONE = (1 << IPS_DST_NAT_DONE_BIT),
-
-	/* Both together */
-	IPS_NAT_DONE_MASK = (IPS_DST_NAT_DONE | IPS_SRC_NAT_DONE),
-
-	/* Connection is dying (removed from lists), can not be unset. */
-	IPS_DYING_BIT = 9,
-	IPS_DYING = (1 << IPS_DYING_BIT),
-};
-
-/* Connection tracking event bits */
-enum ip_conntrack_events
-{
-	/* New conntrack */
-	IPCT_NEW_BIT = 0,
-	IPCT_NEW = (1 << IPCT_NEW_BIT),
-
-	/* Expected connection */
-	IPCT_RELATED_BIT = 1,
-	IPCT_RELATED = (1 << IPCT_RELATED_BIT),
-
-	/* Destroyed conntrack */
-	IPCT_DESTROY_BIT = 2,
-	IPCT_DESTROY = (1 << IPCT_DESTROY_BIT),
-
-	/* Timer has been refreshed */
-	IPCT_REFRESH_BIT = 3,
-	IPCT_REFRESH = (1 << IPCT_REFRESH_BIT),
-
-	/* Status has changed */
-	IPCT_STATUS_BIT = 4,
-	IPCT_STATUS = (1 << IPCT_STATUS_BIT),
-
-	/* Update of protocol info */
-	IPCT_PROTOINFO_BIT = 5,
-	IPCT_PROTOINFO = (1 << IPCT_PROTOINFO_BIT),
-
-	/* Volatile protocol info */
-	IPCT_PROTOINFO_VOLATILE_BIT = 6,
-	IPCT_PROTOINFO_VOLATILE = (1 << IPCT_PROTOINFO_VOLATILE_BIT),
-
-	/* New helper for conntrack */
-	IPCT_HELPER_BIT = 7,
-	IPCT_HELPER = (1 << IPCT_HELPER_BIT),
-
-	/* Update of helper info */
-	IPCT_HELPINFO_BIT = 8,
-	IPCT_HELPINFO = (1 << IPCT_HELPINFO_BIT),
-
-	/* Volatile helper info */
-	IPCT_HELPINFO_VOLATILE_BIT = 9,
-	IPCT_HELPINFO_VOLATILE = (1 << IPCT_HELPINFO_VOLATILE_BIT),
 
-	/* NAT info */
-	IPCT_NATINFO_BIT = 10,
-	IPCT_NATINFO = (1 << IPCT_NATINFO_BIT),
-
-	/* Counter highest bit has been set */
-	IPCT_COUNTER_FILLING_BIT = 11,
-	IPCT_COUNTER_FILLING = (1 << IPCT_COUNTER_FILLING_BIT),
-};
-
-enum ip_conntrack_expect_events {
-	IPEXP_NEW_BIT = 0,
-	IPEXP_NEW = (1 << IPEXP_NEW_BIT),
-};
+#include <linux/netfilter/nf_conntrack_common.h>
 
 #ifdef __KERNEL__
 #include <linux/config.h>
@@ -194,12 +69,6 @@ do {									\
 #define IP_NF_ASSERT(x)
 #endif
 
-struct ip_conntrack_counter
-{
-	u_int32_t packets;
-	u_int32_t bytes;
-};
-
 struct ip_conntrack_helper;
 
 struct ip_conntrack
@@ -426,25 +295,6 @@ static inline int is_dying(struct ip_conntrack *ct)
 
 extern unsigned int ip_conntrack_htable_size;
  
-struct ip_conntrack_stat
-{
-	unsigned int searched;
-	unsigned int found;
-	unsigned int new;
-	unsigned int invalid;
-	unsigned int ignore;
-	unsigned int delete;
-	unsigned int delete_list;
-	unsigned int insert;
-	unsigned int insert_failed;
-	unsigned int drop;
-	unsigned int early_drop;
-	unsigned int error;
-	unsigned int expect_new;
-	unsigned int expect_create;
-	unsigned int expect_delete;
-};
-
 #define CONNTRACK_STAT_INC(count) (__get_cpu_var(ip_conntrack_stat).count++)
 
 #ifdef CONFIG_IP_NF_CONNTRACK_EVENTS

include/linux/netfilter_ipv4/ip_conntrack_ftp.h

 #ifndef _IP_CONNTRACK_FTP_H
 #define _IP_CONNTRACK_FTP_H
-/* FTP tracking. */
 
-#ifdef __KERNEL__
+#include <linux/netfilter/nf_conntrack_ftp.h>
 
-#define FTP_PORT	21
-
-#endif /* __KERNEL__ */
-
-enum ip_ct_ftp_type
-{
-	/* PORT command from client */
-	IP_CT_FTP_PORT,
-	/* PASV response from server */
-	IP_CT_FTP_PASV,
-	/* EPRT command from client */
-	IP_CT_FTP_EPRT,
-	/* EPSV response from server */
-	IP_CT_FTP_EPSV,
-};
-
-#define NUM_SEQ_TO_REMEMBER 2
-/* This structure exists only once per master */
-struct ip_ct_ftp_master {
-	/* Valid seq positions for cmd matching after newline */
-	u_int32_t seq_aft_nl[IP_CT_DIR_MAX][NUM_SEQ_TO_REMEMBER];
-	/* 0 means seq_match_aft_nl not set */
-	int seq_aft_nl_num[IP_CT_DIR_MAX];
-};
-
-struct ip_conntrack_expect;
-
-/* For NAT to hook in when we find a packet which describes what other
- * connection we should expect. */
-extern unsigned int (*ip_nat_ftp_hook)(struct sk_buff **pskb,
-				       enum ip_conntrack_info ctinfo,
-				       enum ip_ct_ftp_type type,
-				       unsigned int matchoff,
-				       unsigned int matchlen,
-				       struct ip_conntrack_expect *exp,
-				       u32 *seq);
 #endif /* _IP_CONNTRACK_FTP_H */

include/linux/netfilter_ipv4/ip_conntrack_icmp.h

 #ifndef _IP_CONNTRACK_ICMP_H
 #define _IP_CONNTRACK_ICMP_H
-/* ICMP tracking. */
-#include <asm/atomic.h>
 
-struct ip_ct_icmp
-{
-	/* Optimization: when number in == number out, forget immediately. */
-	atomic_t count;
-};
+#include <net/netfilter/ipv4/nf_conntrack_icmp.h>
+
 #endif /* _IP_CONNTRACK_ICMP_H */

include/linux/netfilter_ipv4/ip_conntrack_sctp.h

 #ifndef _IP_CONNTRACK_SCTP_H
 #define _IP_CONNTRACK_SCTP_H
-/* SCTP tracking. */
 
-enum sctp_conntrack {
-	SCTP_CONNTRACK_NONE,
-	SCTP_CONNTRACK_CLOSED,
-	SCTP_CONNTRACK_COOKIE_WAIT,
-	SCTP_CONNTRACK_COOKIE_ECHOED,
-	SCTP_CONNTRACK_ESTABLISHED,
-	SCTP_CONNTRACK_SHUTDOWN_SENT,
-	SCTP_CONNTRACK_SHUTDOWN_RECD,
-	SCTP_CONNTRACK_SHUTDOWN_ACK_SENT,
-	SCTP_CONNTRACK_MAX
-};
-
-struct ip_ct_sctp
-{
-	enum sctp_conntrack state;
-
-	u_int32_t vtag[IP_CT_DIR_MAX];
-	u_int32_t ttag[IP_CT_DIR_MAX];
-};
+#include <linux/netfilter/nf_conntrack_sctp.h>
 
 #endif /* _IP_CONNTRACK_SCTP_H */

include/linux/netfilter_ipv4/ip_conntrack_tcp.h

 #ifndef _IP_CONNTRACK_TCP_H
 #define _IP_CONNTRACK_TCP_H
-/* TCP tracking. */
 
-enum tcp_conntrack {
-	TCP_CONNTRACK_NONE,
-	TCP_CONNTRACK_SYN_SENT,
-	TCP_CONNTRACK_SYN_RECV,
-	TCP_CONNTRACK_ESTABLISHED,
-	TCP_CONNTRACK_FIN_WAIT,
-	TCP_CONNTRACK_CLOSE_WAIT,
-	TCP_CONNTRACK_LAST_ACK,
-	TCP_CONNTRACK_TIME_WAIT,
-	TCP_CONNTRACK_CLOSE,
-	TCP_CONNTRACK_LISTEN,
-	TCP_CONNTRACK_MAX,
-	TCP_CONNTRACK_IGNORE
-};
-
-/* Window scaling is advertised by the sender */
-#define IP_CT_TCP_FLAG_WINDOW_SCALE		0x01
-
-/* SACK is permitted by the sender */
-#define IP_CT_TCP_FLAG_SACK_PERM		0x02
-
-/* This sender sent FIN first */
-#define IP_CT_TCP_FLAG_CLOSE_INIT		0x03
-
-struct ip_ct_tcp_state {
-	u_int32_t	td_end;		/* max of seq + len */
-	u_int32_t	td_maxend;	/* max of ack + max(win, 1) */
-	u_int32_t	td_maxwin;	/* max(win) */
-	u_int8_t	td_scale;	/* window scale factor */
-	u_int8_t	loose;		/* used when connection picked up from the middle */
-	u_int8_t	flags;		/* per direction options */
-};
-
-struct ip_ct_tcp
-{
-	struct ip_ct_tcp_state seen[2];	/* connection parameters per direction */
-	u_int8_t	state;		/* state of the connection (enum tcp_conntrack) */
-	/* For detecting stale connections */
-	u_int8_t	last_dir;	/* Direction of the last packet (enum ip_conntrack_dir) */
-	u_int8_t	retrans;	/* Number of retransmitted packets */
-	u_int8_t	last_index;	/* Index of the last packet */
-	u_int32_t	last_seq;	/* Last sequence number seen in dir */
-	u_int32_t	last_ack;	/* Last sequence number seen in opposite dir */
-	u_int32_t	last_end;	/* Last seq + len */
-};
+#include <linux/netfilter/nf_conntrack_tcp.h>
 
 #endif /* _IP_CONNTRACK_TCP_H */

include/linux/netfilter_ipv4/ip_conntrack_tuple.h

@@ -2,6 +2,7 @@
 #define _IP_CONNTRACK_TUPLE_H
 
 #include <linux/types.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
@@ -88,13 +89,6 @@ struct ip_conntrack_tuple
 		(tuple)->dst.u.all = 0;				\
 	} while (0)
 
-enum ip_conntrack_dir
-{
-	IP_CT_DIR_ORIGINAL,
-	IP_CT_DIR_REPLY,
-	IP_CT_DIR_MAX
-};
-
 #ifdef __KERNEL__
 
 #define DUMP_TUPLE(tp)						\
@@ -103,8 +97,6 @@ DEBUGP("tuple %p: %u %u.%u.%u.%u:%hu -> %u.%u.%u.%u:%hu\n",	\
        NIPQUAD((tp)->src.ip), ntohs((tp)->src.u.all),		\
        NIPQUAD((tp)->dst.ip), ntohs((tp)->dst.u.all))
 
-#define CTINFO2DIR(ctinfo) ((ctinfo) >= IP_CT_IS_REPLY ? IP_CT_DIR_REPLY : IP_CT_DIR_ORIGINAL)
-
 /* If we're the first tuple, it's the original dir. */
 #define DIRECTION(h) ((enum ip_conntrack_dir)(h)->tuple.dst.dir)
 

include/linux/netfilter_ipv6.h

@@ -59,6 +59,7 @@
 
 enum nf_ip6_hook_priorities {
 	NF_IP6_PRI_FIRST = INT_MIN,
+	NF_IP6_PRI_CONNTRACK_DEFRAG = -400,
 	NF_IP6_PRI_SELINUX_FIRST = -225,
 	NF_IP6_PRI_CONNTRACK = -200,
 	NF_IP6_PRI_BRIDGE_SABOTAGE_FORWARD = -175,

include/linux/netlink.h

@@ -71,7 +71,8 @@ struct nlmsghdr
 
 #define NLMSG_ALIGNTO	4
 #define NLMSG_ALIGN(len) ( ((len)+NLMSG_ALIGNTO-1) & ~(NLMSG_ALIGNTO-1) )
-#define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(sizeof(struct nlmsghdr)))
+#define NLMSG_HDRLEN	 ((int) NLMSG_ALIGN(sizeof(struct nlmsghdr)))
+#define NLMSG_LENGTH(len) ((len)+NLMSG_ALIGN(NLMSG_HDRLEN))
 #define NLMSG_SPACE(len) NLMSG_ALIGN(NLMSG_LENGTH(len))
 #define NLMSG_DATA(nlh)  ((void*)(((char*)nlh) + NLMSG_LENGTH(0)))
 #define NLMSG_NEXT(nlh,len)	 ((len) -= NLMSG_ALIGN((nlh)->nlmsg_len), \
@@ -86,6 +87,8 @@ struct nlmsghdr
 #define NLMSG_DONE		0x3	/* End of a dump	*/
 #define NLMSG_OVERRUN		0x4	/* Data lost		*/
 
+#define NLMSG_MIN_TYPE		0x10	/* < 0x10: reserved control messages */
+
 struct nlmsgerr
 {
 	int		error;
@@ -108,6 +111,25 @@ enum {
 	NETLINK_CONNECTED,
 };
 
+/*
+ *  <------- NLA_HDRLEN ------> <-- NLA_ALIGN(payload)-->
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ * |        Header       | Pad |     Payload       | Pad |
+ * |   (struct nlattr)   | ing |                   | ing |
+ * +---------------------+- - -+- - - - - - - - - -+- - -+
+ *  <-------------- nlattr->nla_len -------------->
+ */
+
+struct nlattr
+{
+	__u16           nla_len;
+	__u16           nla_type;
+};
+
+#define NLA_ALIGNTO		4
+#define NLA_ALIGN(len)		(((len) + NLA_ALIGNTO - 1) & ~(NLA_ALIGNTO - 1))
+#define NLA_HDRLEN		((int) NLA_ALIGN(sizeof(struct nlattr)))
+
 #ifdef __KERNEL__
 
 #include <linux/capability.h>

include/linux/skbuff.h

@@ -274,6 +274,9 @@ struct sk_buff {
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	__u8			ipvs_property:1;
 #endif
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	struct sk_buff		*nfct_reasm;
+#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	struct nf_bridge_info	*nf_bridge;
 #endif
@@ -1313,10 +1316,26 @@ static inline void nf_conntrack_get(struct nf_conntrack *nfct)
 	if (nfct)
 		atomic_inc(&nfct->use);
 }
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+static inline void nf_conntrack_get_reasm(struct sk_buff *skb)
+{
+	if (skb)
+		atomic_inc(&skb->users);
+}
+static inline void nf_conntrack_put_reasm(struct sk_buff *skb)
+{
+	if (skb)
+		kfree_skb(skb);
+}
+#endif
 static inline void nf_reset(struct sk_buff *skb)
 {
 	nf_conntrack_put(skb->nfct);
 	skb->nfct = NULL;
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	nf_conntrack_put_reasm(skb->nfct_reasm);
+	skb->nfct_reasm = NULL;
+#endif
 }
 
 #ifdef CONFIG_BRIDGE_NETFILTER

include/linux/sysctl.h

@@ -205,6 +205,7 @@ enum
 	NET_ECONET=16,
 	NET_SCTP=17,
 	NET_LLC=18,
+	NET_NETFILTER=19,
 };
 
 /* /proc/sys/kernel/random */
@@ -270,6 +271,42 @@ enum
 	NET_UNIX_MAX_DGRAM_QLEN=3,
 };
 
+/* /proc/sys/net/netfilter */
+enum
+{
+	NET_NF_CONNTRACK_MAX=1,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_SENT=2,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_SYN_RECV=3,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_ESTABLISHED=4,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_FIN_WAIT=5,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE_WAIT=6,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_LAST_ACK=7,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_TIME_WAIT=8,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_CLOSE=9,
+	NET_NF_CONNTRACK_UDP_TIMEOUT=10,
+	NET_NF_CONNTRACK_UDP_TIMEOUT_STREAM=11,
+	NET_NF_CONNTRACK_ICMP_TIMEOUT=12,
+	NET_NF_CONNTRACK_GENERIC_TIMEOUT=13,
+	NET_NF_CONNTRACK_BUCKETS=14,
+	NET_NF_CONNTRACK_LOG_INVALID=15,
+	NET_NF_CONNTRACK_TCP_TIMEOUT_MAX_RETRANS=16,
+	NET_NF_CONNTRACK_TCP_LOOSE=17,
+	NET_NF_CONNTRACK_TCP_BE_LIBERAL=18,
+	NET_NF_CONNTRACK_TCP_MAX_RETRANS=19,
+	NET_NF_CONNTRACK_SCTP_TIMEOUT_CLOSED=20,
+	NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_WAIT=21,
+	NET_NF_CONNTRACK_SCTP_TIMEOUT_COOKIE_ECHOED=22,
+	NET_NF_CONNTRACK_SCTP_TIMEOUT_ESTABLISHED=23,
+	NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_SENT=24,
+	NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_RECD=25,
+	NET_NF_CONNTRACK_SCTP_TIMEOUT_SHUTDOWN_ACK_SENT=26,
+	NET_NF_CONNTRACK_COUNT=27,
+	NET_NF_CONNTRACK_ICMPV6_TIMEOUT=28,
+	NET_NF_CONNTRACK_FRAG6_TIMEOUT=29,
+	NET_NF_CONNTRACK_FRAG6_LOW_THRESH=30,
+	NET_NF_CONNTRACK_FRAG6_HIGH_THRESH=31,
+};
+
 /* /proc/sys/net/ipv4 */
 enum
 {

include/net/genetlink.h

+#ifndef __NET_GENERIC_NETLINK_H
+#define __NET_GENERIC_NETLINK_H
+
+#include <linux/genetlink.h>
+#include <net/netlink.h>
+
+/**
+ * struct genl_family - generic netlink family
+ * @id: protocol family idenfitier
+ * @hdrsize: length of user specific header in bytes
+ * @name: name of family
+ * @version: protocol version
+ * @maxattr: maximum number of attributes supported
+ * @attrbuf: buffer to store parsed attributes
+ * @ops_list: list of all assigned operations
+ * @family_list: family list
+ */
+struct genl_family
+{
+	unsigned int		id;
+	unsigned int		hdrsize;
+	char			name[GENL_NAMSIZ];
+	unsigned int		version;
+	unsigned int		maxattr;
+	struct module *		owner;
+	struct nlattr **	attrbuf;	/* private */
+	struct list_head	ops_list;	/* private */
+	struct list_head	family_list;	/* private */
+};
+
+#define GENL_ADMIN_PERM		0x01
+
+/**
+ * struct genl_info - receiving information
+ * @snd_seq: sending sequence number
+ * @snd_pid: netlink pid of sender
+ * @nlhdr: netlink message header
+ * @genlhdr: generic netlink message header
+ * @userhdr: user specific header
+ * @attrs: netlink attributes
+ */
+struct genl_info
+{
+	u32			snd_seq;
+	u32			snd_pid;
+	struct nlmsghdr *	nlhdr;
+	struct genlmsghdr *	genlhdr;
+	void *			userhdr;
+	struct nlattr **	attrs;
+};
+
+/**
+ * struct genl_ops - generic netlink operations
+ * @cmd: command identifier
+ * @flags: flags
+ * @policy: attribute validation policy
+ * @doit: standard command callback
+ * @dumpit: callback for dumpers
+ * @ops_list: operations list
+ */
+struct genl_ops
+{
+	unsigned int		cmd;
+	unsigned int		flags;
+	struct nla_policy	*policy;
+	int		       (*doit)(struct sk_buff *skb,
+				       struct genl_info *info);
+	int		       (*dumpit)(struct sk_buff *skb,
+					 struct netlink_callback *cb);
+	struct list_head	ops_list;
+};
+
+extern int genl_register_family(struct genl_family *family);
+extern int genl_unregister_family(struct genl_family *family);
+extern int genl_register_ops(struct genl_family *, struct genl_ops *ops);
+extern int genl_unregister_ops(struct genl_family *, struct genl_ops *ops);
+
+extern struct sock *genl_sock;
+
+/**
+ * genlmsg_put - Add generic netlink header to netlink message
+ * @skb: socket buffer holding the message
+ * @pid: netlink pid the message is addressed to
+ * @seq: sequence number (usually the one of the sender)
+ * @type: netlink message type
+ * @hdrlen: length of the user specific header
+ * @flags netlink message flags
+ * @cmd: generic netlink command
+ * @version: version
+ *
+ * Returns pointer to user specific header
+ */
+static inline void *genlmsg_put(struct sk_buff *skb, u32 pid, u32 seq,
+				int type, int hdrlen, int flags,
+				u8 cmd, u8 version)
+{
+	struct nlmsghdr *nlh;
+	struct genlmsghdr *hdr;
+
+	nlh = nlmsg_put(skb, pid, seq, type, GENL_HDRLEN + hdrlen, flags);
+	if (nlh == NULL)
+		return NULL;
+
+	hdr = nlmsg_data(nlh);
+	hdr->cmd = cmd;
+	hdr->version = version;
+	hdr->reserved = 0;
+
+	return (char *) hdr + GENL_HDRLEN;
+}
+
+/**
+ * genlmsg_end - Finalize a generic netlink message
+ * @skb: socket buffer the message is stored in
+ * @hdr: user specific header
+ */
+static inline int genlmsg_end(struct sk_buff *skb, void *hdr)
+{
+	return nlmsg_end(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN);
+}
+
+/**
+ * genlmsg_cancel - Cancel construction of a generic netlink message
+ * @skb: socket buffer the message is stored in
+ * @hdr: generic netlink message header
+ */
+static inline int genlmsg_cancel(struct sk_buff *skb, void *hdr)
+{
+	return nlmsg_cancel(skb, hdr - GENL_HDRLEN - NLMSG_HDRLEN);
+}
+
+/**
+ * genlmsg_multicast - multicast a netlink message
+ * @skb: netlink message as socket buffer
+ * @pid: own netlink pid to avoid sending to yourself
+ * @group: multicast group id
+ */
+static inline int genlmsg_multicast(struct sk_buff *skb, u32 pid,
+				    unsigned int group)
+{
+	return nlmsg_multicast(genl_sock, skb, pid, group);
+}
+
+/**
+ * genlmsg_unicast - unicast a netlink message
+ * @skb: netlink message as socket buffer
+ * @pid: netlink pid of the destination socket
+ */
+static inline int genlmsg_unicast(struct sk_buff *skb, u32 pid)
+{
+	return nlmsg_unicast(genl_sock, skb, pid);
+}
+
+#endif	/* __NET_GENERIC_NETLINK_H */

include/net/netfilter/ipv4/nf_conntrack_icmp.h

+#ifndef _NF_CONNTRACK_ICMP_H
+#define _NF_CONNTRACK_ICMP_H
+/* ICMP tracking. */
+#include <asm/atomic.h>
+
+struct ip_ct_icmp
+{
+	/* Optimization: when number in == number out, forget immediately. */
+	atomic_t count;
+};
+#endif /* _NF_CONNTRACK_ICMP_H */

include/net/netfilter/ipv4/nf_conntrack_ipv4.h

+/*
+ * IPv4 support for nf_conntrack.
+ *
+ * 23 Mar 2004: Yasuyuki Kozakai @ USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- move L3 protocol dependent part from include/linux/netfilter_ipv4/
+ *	  ip_conntarck.h
+ */
+
+#ifndef _NF_CONNTRACK_IPV4_H
+#define _NF_CONNTRACK_IPV4_H
+
+#ifdef CONFIG_IP_NF_NAT_NEEDED
+#include <linux/netfilter_ipv4/ip_nat.h>
+
+/* per conntrack: nat application helper private data */
+union ip_conntrack_nat_help {
+        /* insert nat helper private data here */
+};
+
+struct nf_conntrack_ipv4_nat {
+	struct ip_nat_info info;
+	union ip_conntrack_nat_help help;
+#if defined(CONFIG_IP_NF_TARGET_MASQUERADE) || \
+	defined(CONFIG_IP_NF_TARGET_MASQUERADE_MODULE)
+	int masq_index;
+#endif
+};
+#endif /* CONFIG_IP_NF_NAT_NEEDED */
+
+struct nf_conntrack_ipv4 {
+#ifdef CONFIG_IP_NF_NAT_NEEDED
+	struct nf_conntrack_ipv4_nat *nat;
+#endif
+};
+
+/* Returns new sk_buff, or NULL */
+struct sk_buff *
+nf_ct_ipv4_ct_gather_frags(struct sk_buff *skb);
+
+/* call to create an explicit dependency on nf_conntrack_l3proto_ipv4. */
+extern void need_ip_conntrack(void);
+
+#endif /*_NF_CONNTRACK_IPV4_H*/

include/net/netfilter/ipv6/nf_conntrack_icmpv6.h

+/*
+ * ICMPv6 tracking.
+ *
+ * 21 Apl 2004: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- separated from nf_conntrack_icmp.h
+ *
+ * Derived from include/linux/netfiter_ipv4/ip_conntrack_icmp.h
+ */
+
+#ifndef _NF_CONNTRACK_ICMPV6_H
+#define _NF_CONNTRACK_ICMPV6_H
+#include <asm/atomic.h>
+
+#ifndef ICMPV6_NI_QUERY
+#define ICMPV6_NI_QUERY 139
+#endif
+#ifndef ICMPV6_NI_REPLY
+#define ICMPV6_NI_REPLY 140
+#endif
+
+struct nf_ct_icmpv6
+{
+	/* Optimization: when number in == number out, forget immediately. */
+	atomic_t count;
+};
+
+#endif /* _NF_CONNTRACK_ICMPV6_H */

include/net/netfilter/nf_conntrack_compat.h

+#ifndef _NF_CONNTRACK_COMPAT_H
+#define _NF_CONNTRACK_COMPAT_H
+
+#ifdef __KERNEL__
+
+#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE)
+
+#include <linux/netfilter_ipv4/ip_conntrack.h>
+
+#ifdef CONFIG_IP_NF_CONNTRACK_MARK
+static inline u_int32_t *nf_ct_get_mark(const struct sk_buff *skb,
+					u_int32_t *ctinfo)
+{
+	struct ip_conntrack *ct = ip_conntrack_get(skb, ctinfo);
+
+	if (ct)
+		return &ct->mark;
+	else
+		return NULL;
+}
+#endif /* CONFIG_IP_NF_CONNTRACK_MARK */
+
+#ifdef CONFIG_IP_NF_CT_ACCT
+static inline struct ip_conntrack_counter *
+nf_ct_get_counters(const struct sk_buff *skb)
+{
+	enum ip_conntrack_info ctinfo;
+	struct ip_conntrack *ct = ip_conntrack_get(skb, &ctinfo);
+
+	if (ct)
+		return ct->counters;
+	else
+		return NULL;
+}
+#endif /* CONFIG_IP_NF_CT_ACCT */
+
+static inline int nf_ct_is_untracked(const struct sk_buff *skb)
+{
+	return (skb->nfct == &ip_conntrack_untracked.ct_general);
+}
+
+static inline void nf_ct_untrack(struct sk_buff *skb)
+{
+	skb->nfct = &ip_conntrack_untracked.ct_general;
+}
+
+static inline int nf_ct_get_ctinfo(const struct sk_buff *skb,
+				   enum ip_conntrack_info *ctinfo)
+{
+	struct ip_conntrack *ct = ip_conntrack_get(skb, ctinfo);
+	return (ct != NULL);
+}
+
+#else /* CONFIG_IP_NF_CONNTRACK */
+
+#include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
+#include <net/netfilter/nf_conntrack.h>
+
+#ifdef CONFIG_NF_CONNTRACK_MARK
+
+static inline u_int32_t *nf_ct_get_mark(const struct sk_buff *skb,
+					u_int32_t *ctinfo)
+{
+	struct nf_conn *ct = nf_ct_get(skb, ctinfo);
+
+	if (ct)
+		return &ct->mark;
+	else
+		return NULL;
+}
+#endif /* CONFIG_NF_CONNTRACK_MARK */
+
+#ifdef CONFIG_NF_CT_ACCT
+static inline struct ip_conntrack_counter *
+nf_ct_get_counters(const struct sk_buff *skb)
+{
+	enum ip_conntrack_info ctinfo;
+	struct nf_conn *ct = nf_ct_get(skb, &ctinfo);
+
+	if (ct)
+		return ct->counters;
+	else
+		return NULL;
+}
+#endif /* CONFIG_NF_CT_ACCT */
+
+static inline int nf_ct_is_untracked(const struct sk_buff *skb)
+{
+	return (skb->nfct == &nf_conntrack_untracked.ct_general);
+}
+
+static inline void nf_ct_untrack(struct sk_buff *skb)
+{
+	skb->nfct = &nf_conntrack_untracked.ct_general;
+}
+
+static inline int nf_ct_get_ctinfo(const struct sk_buff *skb,
+				   enum ip_conntrack_info *ctinfo)
+{
+	struct nf_conn *ct = nf_ct_get(skb, ctinfo);
+	return (ct != NULL);
+}
+
+#endif /* CONFIG_IP_NF_CONNTRACK */
+
+#endif /* __KERNEL__ */
+
+#endif /* _NF_CONNTRACK_COMPAT_H */

include/net/netfilter/nf_conntrack_core.h

+/*
+ * This header is used to share core functionality between the
+ * standalone connection tracking module, and the compatibility layer's use
+ * of connection tracking.
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- generalize L3 protocol dependent part.
+ *
+ * Derived from include/linux/netfiter_ipv4/ip_conntrack_core.h
+ */
+
+#ifndef _NF_CONNTRACK_CORE_H
+#define _NF_CONNTRACK_CORE_H
+
+#include <linux/netfilter.h>
+
+/* This header is used to share core functionality between the
+   standalone connection tracking module, and the compatibility layer's use
+   of connection tracking. */
+extern unsigned int nf_conntrack_in(int pf,
+				    unsigned int hooknum,
+				    struct sk_buff **pskb);
+
+extern int nf_conntrack_init(void);
+extern void nf_conntrack_cleanup(void);
+
+struct nf_conntrack_l3proto;
+extern struct nf_conntrack_l3proto *nf_ct_find_l3proto(u_int16_t pf);
+/* Like above, but you already have conntrack read lock. */
+extern struct nf_conntrack_l3proto *__nf_ct_find_l3proto(u_int16_t l3proto);
+
+struct nf_conntrack_protocol;
+
+extern int
+nf_ct_get_tuple(const struct sk_buff *skb,
+		unsigned int nhoff,
+		unsigned int dataoff,
+		u_int16_t l3num,
+		u_int8_t protonum,
+		struct nf_conntrack_tuple *tuple,
+		const struct nf_conntrack_l3proto *l3proto,
+		const struct nf_conntrack_protocol *protocol);
+
+extern int
+nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse,
+		   const struct nf_conntrack_tuple *orig,
+		   const struct nf_conntrack_l3proto *l3proto,
+		   const struct nf_conntrack_protocol *protocol);
+
+/* Find a connection corresponding to a tuple. */
+extern struct nf_conntrack_tuple_hash *
+nf_conntrack_find_get(const struct nf_conntrack_tuple *tuple,
+		      const struct nf_conn *ignored_conntrack);
+
+extern int __nf_conntrack_confirm(struct sk_buff **pskb);
+
+/* Confirm a connection: returns NF_DROP if packet must be dropped. */
+static inline int nf_conntrack_confirm(struct sk_buff **pskb)
+{
+	struct nf_conn *ct = (struct nf_conn *)(*pskb)->nfct;
+	int ret = NF_ACCEPT;
+
+	if (ct) {
+		if (!nf_ct_is_confirmed(ct))
+			ret = __nf_conntrack_confirm(pskb);
+		nf_ct_deliver_cached_events(ct);
+	}
+	return ret;
+}
+
+extern void __nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb);
+
+extern struct list_head *nf_conntrack_hash;
+extern struct list_head nf_conntrack_expect_list;
+extern rwlock_t nf_conntrack_lock ;
+#endif /* _NF_CONNTRACK_CORE_H */

include/net/netfilter/nf_conntrack_helper.h

+/*
+ * connection tracking helpers.
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- generalize L3 protocol dependent part.
+ *
+ * Derived from include/linux/netfiter_ipv4/ip_conntrack_helper.h
+ */
+
+#ifndef _NF_CONNTRACK_HELPER_H
+#define _NF_CONNTRACK_HELPER_H
+#include <net/netfilter/nf_conntrack.h>
+
+struct module;
+
+struct nf_conntrack_helper
+{	
+	struct list_head list; 		/* Internal use. */
+
+	const char *name;		/* name of the module */
+	struct module *me;		/* pointer to self */
+	unsigned int max_expected;	/* Maximum number of concurrent 
+					 * expected connections */
+	unsigned int timeout;		/* timeout for expecteds */
+
+	/* Mask of things we will help (compared against server response) */
+	struct nf_conntrack_tuple tuple;
+	struct nf_conntrack_tuple mask;
+	
+	/* Function to call when data passes; return verdict, or -1 to
+           invalidate. */
+	int (*help)(struct sk_buff **pskb,
+		    unsigned int protoff,
+		    struct nf_conn *ct,
+		    enum ip_conntrack_info conntrackinfo);
+};
+
+extern int nf_conntrack_helper_register(struct nf_conntrack_helper *);
+extern void nf_conntrack_helper_unregister(struct nf_conntrack_helper *);
+
+/* Allocate space for an expectation: this is mandatory before calling
+   nf_conntrack_expect_related.  You will have to call put afterwards. */
+extern struct nf_conntrack_expect *
+nf_conntrack_expect_alloc(struct nf_conn *master);
+extern void nf_conntrack_expect_put(struct nf_conntrack_expect *exp);
+
+/* Add an expected connection: can have more than one per connection */
+extern int nf_conntrack_expect_related(struct nf_conntrack_expect *exp);
+extern void nf_conntrack_unexpect_related(struct nf_conntrack_expect *exp);
+
+#endif /*_NF_CONNTRACK_HELPER_H*/

include/net/netfilter/nf_conntrack_l3proto.h

+/*
+ * Copyright (C)2003,2004 USAGI/WIDE Project
+ *
+ * Header for use in defining a given L3 protocol for connection tracking.
+ *
+ * Author:
+ *	Yasuyuki Kozakai @USAGI	<yasuyuki.kozakai@toshiba.co.jp>
+ *
+ * Derived from include/netfilter_ipv4/ip_conntrack_protocol.h
+ */
+
+#ifndef _NF_CONNTRACK_L3PROTO_H
+#define _NF_CONNTRACK_L3PROTO_H
+#include <linux/seq_file.h>
+#include <net/netfilter/nf_conntrack.h>
+
+struct nf_conntrack_l3proto
+{
+	/* Next pointer. */
+	struct list_head list;
+
+	/* L3 Protocol Family number. ex) PF_INET */
+	u_int16_t l3proto;
+
+	/* Protocol name */
+	const char *name;
+
+	/*
+	 * Try to fill in the third arg: nhoff is offset of l3 proto
+         * hdr.  Return true if possible.
+	 */
+	int (*pkt_to_tuple)(const struct sk_buff *skb, unsigned int nhoff,
+			    struct nf_conntrack_tuple *tuple);
+
+	/*
+	 * Invert the per-proto part of the tuple: ie. turn xmit into reply.
+	 * Some packets can't be inverted: return 0 in that case.
+	 */
+	int (*invert_tuple)(struct nf_conntrack_tuple *inverse,
+			    const struct nf_conntrack_tuple *orig);
+
+	/* Print out the per-protocol part of the tuple. */
+	int (*print_tuple)(struct seq_file *s,
+			   const struct nf_conntrack_tuple *);
+
+	/* Print out the private part of the conntrack. */
+	int (*print_conntrack)(struct seq_file *s, const struct nf_conn *);
+
+	/* Returns verdict for packet, or -1 for invalid. */
+	int (*packet)(struct nf_conn *conntrack,
+		      const struct sk_buff *skb,
+		      enum ip_conntrack_info ctinfo);
+
+	/*
+	 * Called when a new connection for this protocol found;
+	 * returns TRUE if it's OK.  If so, packet() called next.
+	 */
+	int (*new)(struct nf_conn *conntrack, const struct sk_buff *skb);
+
+	/* Called when a conntrack entry is destroyed */
+	void (*destroy)(struct nf_conn *conntrack);
+
+	/*
+	 * Called before tracking. 
+	 *	*dataoff: offset of protocol header (TCP, UDP,...) in *pskb
+	 *	*protonum: protocol number
+	 */
+	int (*prepare)(struct sk_buff **pskb, unsigned int hooknum,
+		       unsigned int *dataoff, u_int8_t *protonum);
+
+	u_int32_t (*get_features)(const struct nf_conntrack_tuple *tuple);
+
+	/* Module (if any) which this is connected to. */
+	struct module *me;
+};
+
+extern struct nf_conntrack_l3proto *nf_ct_l3protos[AF_MAX];
+
+/* Protocol registration. */
+extern int nf_conntrack_l3proto_register(struct nf_conntrack_l3proto *proto);
+extern void nf_conntrack_l3proto_unregister(struct nf_conntrack_l3proto *proto);
+
+static inline struct nf_conntrack_l3proto *
+nf_ct_find_l3proto(u_int16_t l3proto)
+{
+	return nf_ct_l3protos[l3proto];
+}
+
+/* Existing built-in protocols */
+extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
+extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6;
+extern struct nf_conntrack_l3proto nf_conntrack_generic_l3proto;
+#endif /*_NF_CONNTRACK_L3PROTO_H*/

include/net/netfilter/nf_conntrack_protocol.h

+/*
+ * Header for use in defining a given protocol for connection tracking.
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- generalized L3 protocol dependent part.
+ *
+ * Derived from include/linux/netfiter_ipv4/ip_conntrack_protcol.h
+ */
+
+#ifndef _NF_CONNTRACK_PROTOCOL_H
+#define _NF_CONNTRACK_PROTOCOL_H
+#include <net/netfilter/nf_conntrack.h>
+
+struct seq_file;
+
+struct nf_conntrack_protocol
+{
+	/* Next pointer. */
+	struct list_head list;
+
+	/* L3 Protocol number. */
+	u_int16_t l3proto;
+
+	/* Protocol number. */
+	u_int8_t proto;
+
+	/* Protocol name */
+	const char *name;
+
+	/* Try to fill in the third arg: dataoff is offset past network protocol
+           hdr.  Return true if possible. */
+	int (*pkt_to_tuple)(const struct sk_buff *skb,
+			    unsigned int dataoff,
+			    struct nf_conntrack_tuple *tuple);
+
+	/* Invert the per-proto part of the tuple: ie. turn xmit into reply.
+	 * Some packets can't be inverted: return 0 in that case.
+	 */
+	int (*invert_tuple)(struct nf_conntrack_tuple *inverse,
+			    const struct nf_conntrack_tuple *orig);
+
+	/* Print out the per-protocol part of the tuple. Return like seq_* */
+	int (*print_tuple)(struct seq_file *s,
+			   const struct nf_conntrack_tuple *);
+
+	/* Print out the private part of the conntrack. */
+	int (*print_conntrack)(struct seq_file *s, const struct nf_conn *);
+
+	/* Returns verdict for packet, or -1 for invalid. */
+	int (*packet)(struct nf_conn *conntrack,
+		      const struct sk_buff *skb,
+		      unsigned int dataoff,
+		      enum ip_conntrack_info ctinfo,
+		      int pf,
+		      unsigned int hooknum);
+
+	/* Called when a new connection for this protocol found;
+	 * returns TRUE if it's OK.  If so, packet() called next. */
+	int (*new)(struct nf_conn *conntrack, const struct sk_buff *skb,
+		   unsigned int dataoff);
+
+	/* Called when a conntrack entry is destroyed */
+	void (*destroy)(struct nf_conn *conntrack);
+
+	int (*error)(struct sk_buff *skb, unsigned int dataoff,
+		     enum ip_conntrack_info *ctinfo,
+		     int pf, unsigned int hooknum);
+
+	/* Module (if any) which this is connected to. */
+	struct module *me;
+};
+
+/* Existing built-in protocols */
+extern struct nf_conntrack_protocol nf_conntrack_protocol_tcp6;
+extern struct nf_conntrack_protocol nf_conntrack_protocol_udp4;
+extern struct nf_conntrack_protocol nf_conntrack_protocol_udp6;
+extern struct nf_conntrack_protocol nf_conntrack_generic_protocol;
+
+#define MAX_NF_CT_PROTO 256
+extern struct nf_conntrack_protocol **nf_ct_protos[PF_MAX];
+
+extern struct nf_conntrack_protocol *
+nf_ct_find_proto(u_int16_t l3proto, u_int8_t protocol);
+
+/* Protocol registration. */
+extern int nf_conntrack_protocol_register(struct nf_conntrack_protocol *proto);
+extern void nf_conntrack_protocol_unregister(struct nf_conntrack_protocol *proto);
+
+/* Log invalid packets */
+extern unsigned int nf_ct_log_invalid;
+
+#ifdef CONFIG_SYSCTL
+#ifdef DEBUG_INVALID_PACKETS
+#define LOG_INVALID(proto) \
+	(nf_ct_log_invalid == (proto) || nf_ct_log_invalid == IPPROTO_RAW)
+#else
+#define LOG_INVALID(proto) \
+	((nf_ct_log_invalid == (proto) || nf_ct_log_invalid == IPPROTO_RAW) \
+	 && net_ratelimit())
+#endif
+#else
+#define LOG_INVALID(proto) 0
+#endif /* CONFIG_SYSCTL */
+
+#endif /*_NF_CONNTRACK_PROTOCOL_H*/

include/net/netfilter/nf_conntrack_tuple.h

+/*
+ * 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 */

net/core/rtnetlink.c

@@ -49,6 +49,7 @@
 #include <net/udp.h>
 #include <net/sock.h>
 #include <net/pkt_sched.h>
+#include <net/netlink.h>
 
 DECLARE_MUTEX(rtnl_sem);
 
@@ -462,11 +463,6 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
 	netlink_broadcast(rtnl, skb, 0, RTNLGRP_LINK, GFP_KERNEL);
 }
 
-static int rtnetlink_done(struct netlink_callback *cb)
-{
-	return 0;
-}
-
 /* Protected by RTNL sempahore.  */
 static struct rtattr **rta_buf;
 static int rtattr_max;
@@ -524,8 +520,6 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp)
 	}
 
 	if (kind == 2 && nlh->nlmsg_flags&NLM_F_DUMP) {
-		u32 rlen;
-
 		if (link->dumpit == NULL)
 			link = &(rtnetlink_links[PF_UNSPEC][type]);
 
@@ -533,14 +527,11 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp)
 			goto err_inval;
 
 		if ((*errp = netlink_dump_start(rtnl, skb, nlh,
-						link->dumpit,
-						rtnetlink_done)) != 0) {
+						link->dumpit, NULL)) != 0) {
 			return -1;
 		}
-		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
-		if (rlen > skb->len)
-			rlen = skb->len;
-		skb_pull(skb, rlen);
+
+		netlink_queue_skip(nlh, skb);
 		return -1;
 	}
 
@@ -579,75 +570,13 @@ rtnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh, int *errp)
 	return -1;
 }
 
-/* 
- * Process one packet of messages.
- * Malformed skbs with wrong lengths of messages are discarded silently.
- */
-
-static inline int rtnetlink_rcv_skb(struct sk_buff *skb)
-{
-	int err;
-	struct nlmsghdr * nlh;
-
-	while (skb->len >= NLMSG_SPACE(0)) {
-		u32 rlen;
-
-		nlh = (struct nlmsghdr *)skb->data;
-		if (nlh->nlmsg_len < sizeof(*nlh) || skb->len < nlh->nlmsg_len)
-			return 0;
-		rlen = NLMSG_ALIGN(nlh->nlmsg_len);
-		if (rlen > skb->len)
-			rlen = skb->len;
-		if (rtnetlink_rcv_msg(skb, nlh, &err)) {
-			/* Not error, but we must interrupt processing here:
-			 *   Note, that in this case we do not pull message
-			 *   from skb, it will be processed later.
-			 */
-			if (err == 0)
-				return -1;
-			netlink_ack(skb, nlh, err);
-		} else if (nlh->nlmsg_flags&NLM_F_ACK)
-			netlink_ack(skb, nlh, 0);
-		skb_pull(skb, rlen);
-	}
-
-	return 0;
-}
-
-/*
- *  rtnetlink input queue processing routine:
- *	- process as much as there was in the queue upon entry.
- *	- feed skbs to rtnetlink_rcv_skb, until it refuse a message,
- *	  that will occur, when a dump started.
- */
-
 static void rtnetlink_rcv(struct sock *sk, int len)
 {
-	unsigned int qlen = skb_queue_len(&sk->sk_receive_queue);
+	unsigned int qlen = 0;
 
 	do {
-		struct sk_buff *skb;
-
 		rtnl_lock();
-
-		if (qlen > skb_queue_len(&sk->sk_receive_queue))
-			qlen = skb_queue_len(&sk->sk_receive_queue);
-
-		for (; qlen; qlen--) {
-			skb = skb_dequeue(&sk->sk_receive_queue);
-			if (rtnetlink_rcv_skb(skb)) {
-				if (skb->len)
-					skb_queue_head(&sk->sk_receive_queue,
-						       skb);
-				else {
-					kfree_skb(skb);
-					qlen--;
-				}
-				break;
-			}
-			kfree_skb(skb);
-		}
-
+		netlink_run_queue(sk, &qlen, &rtnetlink_rcv_msg);
 		up(&rtnl_sem);
 
 		netdev_run_todo();

net/core/skbuff.c

@@ -336,6 +336,9 @@ void __kfree_skb(struct sk_buff *skb)
 	}
 #ifdef CONFIG_NETFILTER
 	nf_conntrack_put(skb->nfct);
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	nf_conntrack_put_reasm(skb->nfct_reasm);
+#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(skb->nf_bridge);
 #endif
@@ -414,9 +417,17 @@ struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t gfp_mask)
 	C(nfct);
 	nf_conntrack_get(skb->nfct);
 	C(nfctinfo);
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	C(nfct_reasm);
+	nf_conntrack_get_reasm(skb->nfct_reasm);
+#endif
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	C(ipvs_property);
 #endif
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	C(nfct_reasm);
+	nf_conntrack_get_reasm(skb->nfct_reasm);
+#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	C(nf_bridge);
 	nf_bridge_get(skb->nf_bridge);
@@ -474,6 +485,10 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old)
 	new->nfct	= old->nfct;
 	nf_conntrack_get(old->nfct);
 	new->nfctinfo	= old->nfctinfo;
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	new->nfct_reasm = old->nfct_reasm;
+	nf_conntrack_get_reasm(old->nfct_reasm);
+#endif
 #if defined(CONFIG_IP_VS) || defined(CONFIG_IP_VS_MODULE)
 	new->ipvs_property = old->ipvs_property;
 #endif

net/ipv4/inet_diag.c

@@ -724,12 +724,6 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
 	return skb->len;
 }
 
-static int inet_diag_dump_done(struct netlink_callback *cb)
-{
-	return 0;
-}
-
-
 static __inline__ int
 inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 {
@@ -760,8 +754,7 @@ inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 				goto err_inval;
 		}
 		return netlink_dump_start(idiagnl, skb, nlh,
-					  inet_diag_dump,
-					  inet_diag_dump_done);
+					  inet_diag_dump, NULL);
 	} else {
 		return inet_diag_get_exact(skb, nlh);
 	}

net/ipv4/netfilter/Kconfig

@@ -5,6 +5,20 @@
 menu "IP: Netfilter Configuration"
 	depends on INET && NETFILTER
 
+config NF_CONNTRACK_IPV4
+	tristate "IPv4 support for new connection tracking (EXPERIMENTAL)"
+	depends on EXPERIMENTAL && NF_CONNTRACK
+	---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 IPv4 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.
+
 # connection tracking, helpers and protocols
 config IP_NF_CONNTRACK
 	tristate "Connection tracking (required for masq/NAT)"
@@ -317,7 +331,8 @@ config IP_NF_MATCH_TCPMSS
 
 config IP_NF_MATCH_HELPER
 	tristate "Helper match support"
-	depends on IP_NF_CONNTRACK && IP_NF_IPTABLES
+	depends on IP_NF_IPTABLES
+	depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4
 	help
 	  Helper matching allows you to match packets in dynamic connections
 	  tracked by a conntrack-helper, ie. ip_conntrack_ftp
@@ -326,7 +341,8 @@ config IP_NF_MATCH_HELPER
 
 config IP_NF_MATCH_STATE
 	tristate "Connection state match support"
-	depends on IP_NF_CONNTRACK && IP_NF_IPTABLES
+	depends on IP_NF_IPTABLES
+	depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4
 	help
 	  Connection state matching allows you to match packets based on their
 	  relationship to a tracked connection (ie. previous packets).  This
@@ -336,7 +352,8 @@ config IP_NF_MATCH_STATE
 
 config IP_NF_MATCH_CONNTRACK
 	tristate "Connection tracking match support"
-	depends on IP_NF_CONNTRACK && IP_NF_IPTABLES
+	depends on IP_NF_IPTABLES
+	depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4
 	help
 	  This is a general conntrack match module, a superset of the state match.
 
@@ -422,7 +439,8 @@ config IP_NF_MATCH_COMMENT
 
 config IP_NF_MATCH_CONNMARK
 	tristate  'Connection mark match support'
-	depends on IP_NF_CONNTRACK_MARK && IP_NF_IPTABLES
+	depends on IP_NF_IPTABLES
+	depends on IP_NF_CONNTRACK_MARK || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4)
 	help
 	  This option adds a `connmark' match, which allows you to match the
 	  connection mark value previously set for the session by `CONNMARK'. 
@@ -433,7 +451,8 @@ config IP_NF_MATCH_CONNMARK
 
 config IP_NF_MATCH_CONNBYTES
 	tristate  'Connection byte/packet counter match support'
-	depends on IP_NF_CT_ACCT && IP_NF_IPTABLES
+	depends on IP_NF_IPTABLES
+	depends on IP_NF_CT_ACCT || (NF_CT_ACCT && NF_CONNTRACK_IPV4)
 	help
 	  This option adds a `connbytes' match, which allows you to match the
 	  number of bytes and/or packets for each direction within a connection.
@@ -747,7 +766,8 @@ config IP_NF_TARGET_TTL
 
 config IP_NF_TARGET_CONNMARK
 	tristate  'CONNMARK target support'
-	depends on IP_NF_CONNTRACK_MARK && IP_NF_MANGLE
+	depends on IP_NF_MANGLE
+	depends on IP_NF_CONNTRACK_MARK || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4)
 	help
 	  This option adds a `CONNMARK' target, which allows one to manipulate
 	  the connection mark value.  Similar to the MARK target, but
@@ -759,7 +779,8 @@ config IP_NF_TARGET_CONNMARK
 
 config IP_NF_TARGET_CLUSTERIP
 	tristate "CLUSTERIP target support (EXPERIMENTAL)"
-	depends on IP_NF_CONNTRACK_MARK && IP_NF_IPTABLES && EXPERIMENTAL
+	depends on IP_NF_IPTABLES && EXPERIMENTAL
+	depends on IP_NF_CONNTRACK_MARK || (NF_CONNTRACK_MARK && NF_CONNTRACK_IPV4)
 	help
 	  The CLUSTERIP target allows you to build load-balancing clusters of
 	  network servers without having a dedicated load-balancing
@@ -782,7 +803,7 @@ config IP_NF_RAW
 config IP_NF_TARGET_NOTRACK
 	tristate  'NOTRACK target support'
 	depends on IP_NF_RAW
-	depends on IP_NF_CONNTRACK
+	depends on IP_NF_CONNTRACK || NF_CONNTRACK_IPV4
 	help
 	  The NOTRACK target allows a select rule to specify
 	  which packets *not* to enter the conntrack/NAT

net/ipv4/netfilter/Makefile

@@ -103,3 +103,9 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o
 obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o
 
 obj-$(CONFIG_IP_NF_QUEUE) += ip_queue.o
+
+# objects for l3 independent conntrack
+nf_conntrack_ipv4-objs  :=  nf_conntrack_l3proto_ipv4.o nf_conntrack_proto_icmp.o
+
+# l3 independent conntrack
+obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o

net/ipv4/netfilter/ip_conntrack_netlink.c

@@ -1376,7 +1376,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 				ip_conntrack_expect_put(exp);
 			}
 		}
-		write_unlock(&ip_conntrack_lock);
+		write_unlock_bh(&ip_conntrack_lock);
 	} else {
 		/* This basically means we have to flush everything*/
 		write_lock_bh(&ip_conntrack_lock);

net/ipv4/netfilter/ipt_CLUSTERIP.c

@@ -29,7 +29,7 @@
 
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_CLUSTERIP.h>
-#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <net/netfilter/nf_conntrack_compat.h>
 
 #define CLUSTERIP_VERSION "0.8"
 
@@ -316,14 +316,14 @@ target(struct sk_buff **pskb,
 {
 	const struct ipt_clusterip_tgt_info *cipinfo = targinfo;
 	enum ip_conntrack_info ctinfo;
-	struct ip_conntrack *ct = ip_conntrack_get((*pskb), &ctinfo);
-	u_int32_t hash;
+	u_int32_t *mark, hash;
 
 	/* don't need to clusterip_config_get() here, since refcount
 	 * is only decremented by destroy() - and ip_tables guarantees
 	 * that the ->target() function isn't called after ->destroy() */
 
-	if (!ct) {
+	mark = nf_ct_get_mark((*pskb), &ctinfo);
+	if (mark == NULL) {
 		printk(KERN_ERR "CLUSTERIP: no conntrack!\n");
 			/* FIXME: need to drop invalid ones, since replies
 			 * to outgoing connections of other nodes will be 
@@ -346,7 +346,7 @@ target(struct sk_buff **pskb,
 
 	switch (ctinfo) {
 		case IP_CT_NEW:
-			ct->mark = hash;
+			*mark = hash;
 			break;
 		case IP_CT_RELATED:
 		case IP_CT_RELATED+IP_CT_IS_REPLY:
@@ -363,7 +363,7 @@ target(struct sk_buff **pskb,
 #ifdef DEBUG_CLUSTERP
 	DUMP_TUPLE(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
 #endif
-	DEBUGP("hash=%u ct_hash=%u ", hash, ct->mark);
+	DEBUGP("hash=%u ct_hash=%u ", hash, *mark);
 	if (!clusterip_responsible(cipinfo->config, hash)) {
 		DEBUGP("not responsible\n");
 		return NF_DROP;

net/ipv4/netfilter/ipt_CONNMARK.c

@@ -29,7 +29,7 @@ MODULE_LICENSE("GPL");
 
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_CONNMARK.h>
-#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <net/netfilter/nf_conntrack_compat.h>
 
 static unsigned int
 target(struct sk_buff **pskb,
@@ -43,24 +43,24 @@ target(struct sk_buff **pskb,
 	u_int32_t diff;
 	u_int32_t nfmark;
 	u_int32_t newmark;
+	u_int32_t ctinfo;
+	u_int32_t *ctmark = nf_ct_get_mark(*pskb, &ctinfo);
 
-	enum ip_conntrack_info ctinfo;
-	struct ip_conntrack *ct = ip_conntrack_get((*pskb), &ctinfo);
-	if (ct) {
+	if (ctmark) {
 	    switch(markinfo->mode) {
 	    case IPT_CONNMARK_SET:
-		newmark = (ct->mark & ~markinfo->mask) | markinfo->mark;
-		if (newmark != ct->mark)
-		    ct->mark = newmark;
+		newmark = (*ctmark & ~markinfo->mask) | markinfo->mark;
+		if (newmark != *ctmark)
+		    *ctmark = newmark;
 		break;
 	    case IPT_CONNMARK_SAVE:
-		newmark = (ct->mark & ~markinfo->mask) | ((*pskb)->nfmark & markinfo->mask);
-		if (ct->mark != newmark)
-		    ct->mark = newmark;
+		newmark = (*ctmark & ~markinfo->mask) | ((*pskb)->nfmark & markinfo->mask);
+		if (*ctmark != newmark)
+		    *ctmark = newmark;
 		break;
 	    case IPT_CONNMARK_RESTORE:
 		nfmark = (*pskb)->nfmark;
-		diff = (ct->mark ^ nfmark) & markinfo->mask;
+		diff = (*ctmark ^ nfmark) & markinfo->mask;
 		if (diff != 0)
 		    (*pskb)->nfmark = nfmark ^ diff;
 		break;

net/ipv4/netfilter/ipt_NOTRACK.c

@@ -5,7 +5,7 @@
 #include <linux/skbuff.h>
 
 #include <linux/netfilter_ipv4/ip_tables.h>
-#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <net/netfilter/nf_conntrack_compat.h>
 
 static unsigned int
 target(struct sk_buff **pskb,
@@ -23,7 +23,7 @@ target(struct sk_buff **pskb,
 	   If there is a real ct entry correspondig to this packet, 
 	   it'll hang aroun till timing out. We don't deal with it
 	   for performance reasons. JK */
-	(*pskb)->nfct = &ip_conntrack_untracked.ct_general;
+	nf_ct_untrack(*pskb);
 	(*pskb)->nfctinfo = IP_CT_NEW;
 	nf_conntrack_get((*pskb)->nfct);
 

net/ipv4/netfilter/ipt_connbytes.c

@@ -10,7 +10,7 @@
  */
 #include <linux/module.h>
 #include <linux/skbuff.h>
-#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <net/netfilter/nf_conntrack_compat.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_connbytes.h>
 
@@ -46,60 +46,59 @@ match(const struct sk_buff *skb,
       int *hotdrop)
 {
 	const struct ipt_connbytes_info *sinfo = matchinfo;
-	enum ip_conntrack_info ctinfo;
-	struct ip_conntrack *ct;
 	u_int64_t what = 0;	/* initialize to make gcc happy */
+	const struct ip_conntrack_counter *counters;
 
-	if (!(ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo)))
+	if (!(counters = nf_ct_get_counters(skb)))
 		return 0; /* no match */
 
 	switch (sinfo->what) {
 	case IPT_CONNBYTES_PKTS:
 		switch (sinfo->direction) {
 		case IPT_CONNBYTES_DIR_ORIGINAL:
-			what = ct->counters[IP_CT_DIR_ORIGINAL].packets;
+			what = counters[IP_CT_DIR_ORIGINAL].packets;
 			break;
 		case IPT_CONNBYTES_DIR_REPLY:
-			what = ct->counters[IP_CT_DIR_REPLY].packets;
+			what = counters[IP_CT_DIR_REPLY].packets;
 			break;
 		case IPT_CONNBYTES_DIR_BOTH:
-			what = ct->counters[IP_CT_DIR_ORIGINAL].packets;
-			what += ct->counters[IP_CT_DIR_REPLY].packets;
+			what = counters[IP_CT_DIR_ORIGINAL].packets;
+			what += counters[IP_CT_DIR_REPLY].packets;
 			break;
 		}
 		break;
 	case IPT_CONNBYTES_BYTES:
 		switch (sinfo->direction) {
 		case IPT_CONNBYTES_DIR_ORIGINAL:
-			what = ct->counters[IP_CT_DIR_ORIGINAL].bytes;
+			what = counters[IP_CT_DIR_ORIGINAL].bytes;
 			break;
 		case IPT_CONNBYTES_DIR_REPLY:
-			what = ct->counters[IP_CT_DIR_REPLY].bytes;
+			what = counters[IP_CT_DIR_REPLY].bytes;
 			break;
 		case IPT_CONNBYTES_DIR_BOTH:
-			what = ct->counters[IP_CT_DIR_ORIGINAL].bytes;
-			what += ct->counters[IP_CT_DIR_REPLY].bytes;
+			what = counters[IP_CT_DIR_ORIGINAL].bytes;
+			what += counters[IP_CT_DIR_REPLY].bytes;
 			break;
 		}
 		break;
 	case IPT_CONNBYTES_AVGPKT:
 		switch (sinfo->direction) {
 		case IPT_CONNBYTES_DIR_ORIGINAL:
-			what = div64_64(ct->counters[IP_CT_DIR_ORIGINAL].bytes,
-					ct->counters[IP_CT_DIR_ORIGINAL].packets);
+			what = div64_64(counters[IP_CT_DIR_ORIGINAL].bytes,
+					counters[IP_CT_DIR_ORIGINAL].packets);
 			break;
 		case IPT_CONNBYTES_DIR_REPLY:
-			what = div64_64(ct->counters[IP_CT_DIR_REPLY].bytes,
-					ct->counters[IP_CT_DIR_REPLY].packets);
+			what = div64_64(counters[IP_CT_DIR_REPLY].bytes,
+					counters[IP_CT_DIR_REPLY].packets);
 			break;
 		case IPT_CONNBYTES_DIR_BOTH:
 			{
 				u_int64_t bytes;
 				u_int64_t pkts;
-				bytes = ct->counters[IP_CT_DIR_ORIGINAL].bytes +
-					ct->counters[IP_CT_DIR_REPLY].bytes;
-				pkts = ct->counters[IP_CT_DIR_ORIGINAL].packets+
-					ct->counters[IP_CT_DIR_REPLY].packets;
+				bytes = counters[IP_CT_DIR_ORIGINAL].bytes +
+					counters[IP_CT_DIR_REPLY].bytes;
+				pkts = counters[IP_CT_DIR_ORIGINAL].packets+
+					counters[IP_CT_DIR_REPLY].packets;
 
 				/* FIXME_THEORETICAL: what to do if sum
 				 * overflows ? */

net/ipv4/netfilter/ipt_connmark.c

@@ -28,7 +28,7 @@ MODULE_LICENSE("GPL");
 
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_connmark.h>
-#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <net/netfilter/nf_conntrack_compat.h>
 
 static int
 match(const struct sk_buff *skb,
@@ -39,12 +39,12 @@ match(const struct sk_buff *skb,
       int *hotdrop)
 {
 	const struct ipt_connmark_info *info = matchinfo;
-	enum ip_conntrack_info ctinfo;
-	struct ip_conntrack *ct = ip_conntrack_get((struct sk_buff *)skb, &ctinfo);
-	if (!ct)
+	u_int32_t ctinfo;
+	const u_int32_t *ctmark = nf_ct_get_mark(skb, &ctinfo);
+	if (!ctmark)
 		return 0;
 
-	return ((ct->mark & info->mask) == info->mark) ^ info->invert;
+	return (((*ctmark) & info->mask) == info->mark) ^ info->invert;
 }
 
 static int

net/ipv4/netfilter/ipt_conntrack.c

@@ -10,7 +10,14 @@
 
 #include <linux/module.h>
 #include <linux/skbuff.h>
+
+#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE)
 #include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <linux/netfilter_ipv4/ip_conntrack_tuple.h>
+#else
+#include <net/netfilter/nf_conntrack.h>
+#endif
+
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_conntrack.h>
 
@@ -18,6 +25,8 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Marc Boucher <marc@mbsi.ca>");
 MODULE_DESCRIPTION("iptables connection tracking match module");
 
+#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE)
+
 static int
 match(const struct sk_buff *skb,
       const struct net_device *in,
@@ -102,6 +111,93 @@ match(const struct sk_buff *skb,
 	return 1;
 }
 
+#else /* CONFIG_IP_NF_CONNTRACK */
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      int *hotdrop)
+{
+	const struct ipt_conntrack_info *sinfo = matchinfo;
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	unsigned int statebit;
+
+	ct = nf_ct_get((struct sk_buff *)skb, &ctinfo);
+
+#define FWINV(bool,invflg) ((bool) ^ !!(sinfo->invflags & invflg))
+
+	if (ct == &nf_conntrack_untracked)
+		statebit = IPT_CONNTRACK_STATE_UNTRACKED;
+	else if (ct)
+ 		statebit = IPT_CONNTRACK_STATE_BIT(ctinfo);
+ 	else
+ 		statebit = IPT_CONNTRACK_STATE_INVALID;
+ 
+	if(sinfo->flags & IPT_CONNTRACK_STATE) {
+		if (ct) {
+			if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip !=
+			    ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip)
+				statebit |= IPT_CONNTRACK_STATE_SNAT;
+
+			if(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip !=
+			    ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip)
+				statebit |= IPT_CONNTRACK_STATE_DNAT;
+		}
+
+		if (FWINV((statebit & sinfo->statemask) == 0, IPT_CONNTRACK_STATE))
+			return 0;
+	}
+
+	if(sinfo->flags & IPT_CONNTRACK_PROTO) {
+		if (!ct || FWINV(ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.protonum, IPT_CONNTRACK_PROTO))
+                	return 0;
+	}
+
+	if(sinfo->flags & IPT_CONNTRACK_ORIGSRC) {
+		if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].src.ip, IPT_CONNTRACK_ORIGSRC))
+			return 0;
+	}
+
+	if(sinfo->flags & IPT_CONNTRACK_ORIGDST) {
+		if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_ORIGINAL].s_addr) != sinfo->tuple[IP_CT_DIR_ORIGINAL].dst.ip, IPT_CONNTRACK_ORIGDST))
+			return 0;
+	}
+
+	if(sinfo->flags & IPT_CONNTRACK_REPLSRC) {
+		if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip&sinfo->sipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].src.ip, IPT_CONNTRACK_REPLSRC))
+			return 0;
+	}
+
+	if(sinfo->flags & IPT_CONNTRACK_REPLDST) {
+		if (!ct || FWINV((ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip&sinfo->dipmsk[IP_CT_DIR_REPLY].s_addr) != sinfo->tuple[IP_CT_DIR_REPLY].dst.ip, IPT_CONNTRACK_REPLDST))
+			return 0;
+	}
+
+	if(sinfo->flags & IPT_CONNTRACK_STATUS) {
+		if (!ct || FWINV((ct->status & sinfo->statusmask) == 0, IPT_CONNTRACK_STATUS))
+			return 0;
+	}
+
+	if(sinfo->flags & IPT_CONNTRACK_EXPIRES) {
+		unsigned long expires;
+
+		if(!ct)
+			return 0;
+
+		expires = timer_pending(&ct->timeout) ? (ct->timeout.expires - jiffies)/HZ : 0;
+
+		if (FWINV(!(expires >= sinfo->expires_min && expires <= sinfo->expires_max), IPT_CONNTRACK_EXPIRES))
+			return 0;
+	}
+
+	return 1;
+}
+
+#endif /* CONFIG_NF_IP_CONNTRACK */
+
 static int check(const char *tablename,
 		 const struct ipt_ip *ip,
 		 void *matchinfo,

net/ipv4/netfilter/ipt_helper.c

@@ -13,9 +13,15 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 #include <linux/netfilter.h>
+#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE)
 #include <linux/netfilter_ipv4/ip_conntrack.h>
 #include <linux/netfilter_ipv4/ip_conntrack_core.h>
 #include <linux/netfilter_ipv4/ip_conntrack_helper.h>
+#else
+#include <net/netfilter/nf_conntrack.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/nf_conntrack_helper.h>
+#endif
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_helper.h>
 
@@ -29,6 +35,7 @@ MODULE_DESCRIPTION("iptables helper match module");
 #define DEBUGP(format, args...)
 #endif
 
+#if defined(CONFIG_IP_NF_CONNTRACK) || defined(CONFIG_IP_NF_CONNTRACK_MODULE)
 static int
 match(const struct sk_buff *skb,
       const struct net_device *in,
@@ -73,6 +80,53 @@ match(const struct sk_buff *skb,
 	return ret;
 }
 
+#else /* CONFIG_IP_NF_CONNTRACK */
+
+static int
+match(const struct sk_buff *skb,
+      const struct net_device *in,
+      const struct net_device *out,
+      const void *matchinfo,
+      int offset,
+      int *hotdrop)
+{
+	const struct ipt_helper_info *info = matchinfo;
+	struct nf_conn *ct;
+	enum ip_conntrack_info ctinfo;
+	int ret = info->invert;
+	
+	ct = nf_ct_get((struct sk_buff *)skb, &ctinfo);
+	if (!ct) {
+		DEBUGP("ipt_helper: Eek! invalid conntrack?\n");
+		return ret;
+	}
+
+	if (!ct->master) {
+		DEBUGP("ipt_helper: conntrack %p has no master\n", ct);
+		return ret;
+	}
+
+	read_lock_bh(&nf_conntrack_lock);
+	if (!ct->master->helper) {
+		DEBUGP("ipt_helper: master ct %p has no helper\n", 
+			exp->expectant);
+		goto out_unlock;
+	}
+
+	DEBUGP("master's name = %s , info->name = %s\n", 
+		ct->master->helper->name, info->name);
+
+	if (info->name[0] == '\0')
+		ret ^= 1;
+	else
+		ret ^= !strncmp(ct->master->helper->name, info->name, 
+		                strlen(ct->master->helper->name));
+out_unlock:
+	read_unlock_bh(&nf_conntrack_lock);
+	return ret;
+}
+#endif
+
 static int check(const char *tablename,
 		 const struct ipt_ip *ip,
 		 void *matchinfo,

net/ipv4/netfilter/ipt_state.c

@@ -10,7 +10,7 @@
 
 #include <linux/module.h>
 #include <linux/skbuff.h>
-#include <linux/netfilter_ipv4/ip_conntrack.h>
+#include <net/netfilter/nf_conntrack_compat.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
 #include <linux/netfilter_ipv4/ipt_state.h>
 
@@ -30,9 +30,9 @@ match(const struct sk_buff *skb,
 	enum ip_conntrack_info ctinfo;
 	unsigned int statebit;
 
-	if (skb->nfct == &ip_conntrack_untracked.ct_general)
+	if (nf_ct_is_untracked(skb))
 		statebit = IPT_STATE_UNTRACKED;
-	else if (!ip_conntrack_get(skb, &ctinfo))
+	else if (!nf_ct_get_ctinfo(skb, &ctinfo))
 		statebit = IPT_STATE_INVALID;
 	else
 		statebit = IPT_STATE_BIT(ctinfo);

net/ipv4/netfilter/nf_conntrack_proto_icmp.c

+/* (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.
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- enable working with Layer 3 protocol independent connection tracking.
+ *
+ * Derived from net/ipv4/netfilter/ip_conntrack_proto_icmp.c
+ */
+
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/timer.h>
+#include <linux/netfilter.h>
+#include <linux/in.h>
+#include <linux/icmp.h>
+#include <linux/seq_file.h>
+#include <net/ip.h>
+#include <net/checksum.h>
+#include <linux/netfilter_ipv4.h>
+#include <net/netfilter/nf_conntrack_tuple.h>
+#include <net/netfilter/nf_conntrack_protocol.h>
+#include <net/netfilter/nf_conntrack_core.h>
+
+unsigned long nf_ct_icmp_timeout = 30*HZ;
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+static int icmp_pkt_to_tuple(const struct sk_buff *skb,
+			     unsigned int dataoff,
+			     struct nf_conntrack_tuple *tuple)
+{
+	struct icmphdr _hdr, *hp;
+
+	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
+	if (hp == NULL)
+		return 0;
+
+	tuple->dst.u.icmp.type = hp->type;
+	tuple->src.u.icmp.id = hp->un.echo.id;
+	tuple->dst.u.icmp.code = hp->code;
+
+	return 1;
+}
+
+static int icmp_invert_tuple(struct nf_conntrack_tuple *tuple,
+			     const struct nf_conntrack_tuple *orig)
+{
+	/* Add 1; spaces filled with 0. */
+	static u_int8_t invmap[]
+		= { [ICMP_ECHO] = ICMP_ECHOREPLY + 1,
+		    [ICMP_ECHOREPLY] = ICMP_ECHO + 1,
+		    [ICMP_TIMESTAMP] = ICMP_TIMESTAMPREPLY + 1,
+		    [ICMP_TIMESTAMPREPLY] = ICMP_TIMESTAMP + 1,
+		    [ICMP_INFO_REQUEST] = ICMP_INFO_REPLY + 1,
+		    [ICMP_INFO_REPLY] = ICMP_INFO_REQUEST + 1,
+		    [ICMP_ADDRESS] = ICMP_ADDRESSREPLY + 1,
+		    [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1};
+
+	if (orig->dst.u.icmp.type >= sizeof(invmap)
+	    || !invmap[orig->dst.u.icmp.type])
+		return 0;
+
+	tuple->src.u.icmp.id = orig->src.u.icmp.id;
+	tuple->dst.u.icmp.type = invmap[orig->dst.u.icmp.type] - 1;
+	tuple->dst.u.icmp.code = orig->dst.u.icmp.code;
+	return 1;
+}
+
+/* Print out the per-protocol part of the tuple. */
+static int icmp_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));
+}
+
+/* Print out the private part of the conntrack. */
+static int icmp_print_conntrack(struct seq_file *s,
+				const struct nf_conn *conntrack)
+{
+	return 0;
+}
+
+/* Returns verdict for packet, or -1 for invalid. */
+static int icmp_packet(struct nf_conn *ct,
+		       const struct sk_buff *skb,
+		       unsigned int dataoff,
+		       enum ip_conntrack_info ctinfo,
+		       int pf,
+		       unsigned int hooknum)
+{
+	/* Try to delete connection immediately after all replies:
+           won't actually vanish as we still have skb, and del_timer
+           means this will only run once even if count hits zero twice
+           (theoretically possible with SMP) */
+	if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
+		if (atomic_dec_and_test(&ct->proto.icmp.count)
+		    && del_timer(&ct->timeout))
+			ct->timeout.function((unsigned long)ct);
+	} else {
+		atomic_inc(&ct->proto.icmp.count);
+		nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb);
+		nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
+	}
+
+	return NF_ACCEPT;
+}
+
+/* Called when a new connection for this protocol found. */
+static int icmp_new(struct nf_conn *conntrack,
+		    const struct sk_buff *skb, unsigned int dataoff)
+{
+	static u_int8_t valid_new[]
+		= { [ICMP_ECHO] = 1,
+		    [ICMP_TIMESTAMP] = 1,
+		    [ICMP_INFO_REQUEST] = 1,
+		    [ICMP_ADDRESS] = 1 };
+
+	if (conntrack->tuplehash[0].tuple.dst.u.icmp.type >= sizeof(valid_new)
+	    || !valid_new[conntrack->tuplehash[0].tuple.dst.u.icmp.type]) {
+		/* Can't create a new ICMP `conn' with this. */
+		DEBUGP("icmp: can't create new conn with type %u\n",
+		       conntrack->tuplehash[0].tuple.dst.u.icmp.type);
+		NF_CT_DUMP_TUPLE(&conntrack->tuplehash[0].tuple);
+		return 0;
+	}
+	atomic_set(&conntrack->proto.icmp.count, 0);
+	return 1;
+}
+
+extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv4;
+/* Returns conntrack if it dealt with ICMP, and filled in skb fields */
+static int
+icmp_error_message(struct sk_buff *skb,
+                 enum ip_conntrack_info *ctinfo,
+                 unsigned int hooknum)
+{
+	struct nf_conntrack_tuple innertuple, origtuple;
+	struct {
+		struct icmphdr icmp;
+		struct iphdr ip;
+	} _in, *inside;
+	struct nf_conntrack_protocol *innerproto;
+	struct nf_conntrack_tuple_hash *h;
+	int dataoff;
+
+	NF_CT_ASSERT(skb->nfct == NULL);
+
+	/* Not enough header? */
+	inside = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_in), &_in);
+	if (inside == NULL)
+		return -NF_ACCEPT;
+
+	/* Ignore ICMP's containing fragments (shouldn't happen) */
+	if (inside->ip.frag_off & htons(IP_OFFSET)) {
+		DEBUGP("icmp_error_message: fragment of proto %u\n",
+		       inside->ip.protocol);
+		return -NF_ACCEPT;
+	}
+
+	innerproto = nf_ct_find_proto(PF_INET, inside->ip.protocol);
+	dataoff = skb->nh.iph->ihl*4 + sizeof(inside->icmp);
+	/* Are they talking about one of our connections? */
+	if (!nf_ct_get_tuple(skb, dataoff, dataoff + inside->ip.ihl*4, PF_INET,
+			     inside->ip.protocol, &origtuple,
+			     &nf_conntrack_l3proto_ipv4, innerproto)) {
+		DEBUGP("icmp_error_message: ! get_tuple p=%u",
+		       inside->ip.protocol);
+		return -NF_ACCEPT;
+	}
+
+        /* Ordinarily, we'd expect the inverted tupleproto, but it's
+           been preserved inside the ICMP. */
+        if (!nf_ct_invert_tuple(&innertuple, &origtuple,
+				&nf_conntrack_l3proto_ipv4, innerproto)) {
+		DEBUGP("icmp_error_message: no match\n");
+		return -NF_ACCEPT;
+	}
+
+	*ctinfo = IP_CT_RELATED;
+
+	h = nf_conntrack_find_get(&innertuple, NULL);
+	if (!h) {
+		/* Locally generated ICMPs will match inverted if they
+		   haven't been SNAT'ed yet */
+		/* FIXME: NAT code has to handle half-done double NAT --RR */
+		if (hooknum == NF_IP_LOCAL_OUT)
+			h = nf_conntrack_find_get(&origtuple, NULL);
+
+		if (!h) {
+			DEBUGP("icmp_error_message: no match\n");
+			return -NF_ACCEPT;
+		}
+
+		/* Reverse direction from that found */
+		if (NF_CT_DIRECTION(h) == IP_CT_DIR_REPLY)
+			*ctinfo += IP_CT_IS_REPLY;
+	} 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;
+}
+
+/* Small and modified version of icmp_rcv */
+static int
+icmp_error(struct sk_buff *skb, unsigned int dataoff,
+	   enum ip_conntrack_info *ctinfo, int pf, unsigned int hooknum)
+{
+	struct icmphdr _ih, *icmph;
+
+	/* Not enough header? */
+	icmph = skb_header_pointer(skb, skb->nh.iph->ihl*4, sizeof(_ih), &_ih);
+	if (icmph == NULL) {
+		if (LOG_INVALID(IPPROTO_ICMP))
+			nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL,
+				      "nf_ct_icmp: short packet ");
+		return -NF_ACCEPT;
+	}
+
+	/* See ip_conntrack_proto_tcp.c */
+	if (hooknum != NF_IP_PRE_ROUTING)
+		goto checksum_skipped;
+
+	switch (skb->ip_summed) {
+	case CHECKSUM_HW:
+		if (!(u16)csum_fold(skb->csum))
+			break;
+		if (LOG_INVALID(IPPROTO_ICMP))
+			nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL,
+				      "nf_ct_icmp: bad HW ICMP checksum ");
+		return -NF_ACCEPT;
+	case CHECKSUM_NONE:
+		if ((u16)csum_fold(skb_checksum(skb, 0, skb->len, 0))) {
+			if (LOG_INVALID(IPPROTO_ICMP))
+				nf_log_packet(PF_INET, 0, skb, NULL, NULL,
+					      NULL,
+					      "nf_ct_icmp: bad ICMP checksum ");
+			return -NF_ACCEPT;
+		}
+	default:
+		break;
+	}
+
+checksum_skipped:
+	/*
+	 *	18 is the highest 'known' ICMP type. Anything else is a mystery
+	 *
+	 *	RFC 1122: 3.2.2  Unknown ICMP messages types MUST be silently
+	 *		  discarded.
+	 */
+	if (icmph->type > NR_ICMP_TYPES) {
+		if (LOG_INVALID(IPPROTO_ICMP))
+			nf_log_packet(PF_INET, 0, skb, NULL, NULL, NULL,
+				      "nf_ct_icmp: invalid ICMP type ");
+		return -NF_ACCEPT;
+	}
+
+	/* Need to track icmp error message? */
+	if (icmph->type != ICMP_DEST_UNREACH
+	    && icmph->type != ICMP_SOURCE_QUENCH
+	    && icmph->type != ICMP_TIME_EXCEEDED
+	    && icmph->type != ICMP_PARAMETERPROB
+	    && icmph->type != ICMP_REDIRECT)
+		return NF_ACCEPT;
+
+	return icmp_error_message(skb, ctinfo, hooknum);
+}
+
+struct nf_conntrack_protocol nf_conntrack_protocol_icmp =
+{
+	.list			= { NULL, NULL },
+	.l3proto		= PF_INET,
+	.proto			= IPPROTO_ICMP,
+	.name			= "icmp",
+	.pkt_to_tuple		= icmp_pkt_to_tuple,
+	.invert_tuple		= icmp_invert_tuple,
+	.print_tuple		= icmp_print_tuple,
+	.print_conntrack	= icmp_print_conntrack,
+	.packet			= icmp_packet,
+	.new			= icmp_new,
+	.error			= icmp_error,
+	.destroy		= NULL,
+	.me			= NULL
+};
+
+EXPORT_SYMBOL(nf_conntrack_protocol_icmp);

net/ipv6/ip6_input.c

@@ -176,6 +176,11 @@ static inline int ip6_input_finish(struct sk_buff *skb)
 		if (ipprot->flags & INET6_PROTO_FINAL) {
 			struct ipv6hdr *hdr;	
 
+			/* Free reference early: we don't need it any more,
+			   and it may hold ip_conntrack module loaded
+			   indefinitely. */
+			nf_reset(skb);
+
 			skb_postpull_rcsum(skb, skb->nh.raw,
 					   skb->h.raw - skb->nh.raw);
 			hdr = skb->nh.ipv6h;

net/ipv6/ip6_output.c

@@ -441,9 +441,15 @@ static void ip6_copy_metadata(struct sk_buff *to, struct sk_buff *from)
 #ifdef CONFIG_NETFILTER
 	to->nfmark = from->nfmark;
 	/* Connection association is same as pre-frag packet */
+	nf_conntrack_put(to->nfct);
 	to->nfct = from->nfct;
 	nf_conntrack_get(to->nfct);
 	to->nfctinfo = from->nfctinfo;
+#if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
+	nf_conntrack_put_reasm(to->nfct_reasm);
+	to->nfct_reasm = from->nfct_reasm;
+	nf_conntrack_get_reasm(to->nfct_reasm);
+#endif
 #ifdef CONFIG_BRIDGE_NETFILTER
 	nf_bridge_put(to->nf_bridge);
 	to->nf_bridge = from->nf_bridge;

net/ipv6/netfilter/Kconfig

@@ -278,5 +278,19 @@ config IP6_NF_RAW
 	  If you want to compile it as a module, say M here and read
 	  <file:Documentation/modules.txt>.  If unsure, say `N'.
 
+config NF_CONNTRACK_IPV6
+	tristate "IPv6 support for new connection tracking (EXPERIMENTAL)"
+	depends on EXPERIMENTAL && NF_CONNTRACK
+	---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.
+
 endmenu
 

net/ipv6/netfilter/Makefile

@@ -27,3 +27,9 @@ obj-$(CONFIG_IP6_NF_TARGET_LOG) += ip6t_LOG.o
 obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
 obj-$(CONFIG_IP6_NF_MATCH_HL) += ip6t_hl.o
 obj-$(CONFIG_IP6_NF_TARGET_REJECT) += ip6t_REJECT.o
+
+# objects for l3 independent conntrack
+nf_conntrack_ipv6-objs  :=  nf_conntrack_l3proto_ipv6.o nf_conntrack_proto_icmpv6.o nf_conntrack_reasm.o
+
+# l3 independent conntrack
+obj-$(CONFIG_NF_CONNTRACK_IPV6) += nf_conntrack_ipv6.o

net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c

+/*
+ * 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>
+ *
+ * 16 Dec 2003: Yasuyuki Kozakai @USAGI <yasuyuki.kozakai@toshiba.co.jp>
+ *	- ICMPv6 tracking support. Derived from the original ip_conntrack code
+ *	  net/ipv4/netfilter/ip_conntrack_proto_icmp.c which had the following
+ *	  copyright information:
+ *		(C) 1999-2001 Paul `Rusty' Russell
+ *		(C) 2002-2004 Netfilter Core Team <coreteam@netfilter.org>
+ */
+
+#include <linux/types.h>
+#include <linux/sched.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_protocol.h>
+#include <net/netfilter/nf_conntrack_core.h>
+#include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
+
+unsigned long nf_ct_icmpv6_timeout = 30*HZ;
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(format, args...)
+#endif
+
+static int icmpv6_pkt_to_tuple(const struct sk_buff *skb,
+			       unsigned int dataoff,
+			       struct nf_conntrack_tuple *tuple)
+{
+	struct icmp6hdr _hdr, *hp;
+
+	hp = skb_header_pointer(skb, dataoff, sizeof(_hdr), &_hdr);
+	if (hp == NULL)
+		return 0;
+	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 1;
+}
+
+static int icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple,
+			       const struct nf_conntrack_tuple *orig)
+{
+	/* Add 1; spaces filled with 0. */
+	static 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_QUERY + 1,
+		[ICMPV6_NI_REPLY - 128]		= ICMPV6_NI_REPLY +1
+	};
+
+	__u8 type = orig->dst.u.icmp.type - 128;
+	if (type >= sizeof(invmap) || !invmap[type])
+		return 0;
+
+	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 1;
+}
+
+/* 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));
+}
+
+/* Print out the private part of the conntrack. */
+static int icmpv6_print_conntrack(struct seq_file *s,
+				  const struct nf_conn *conntrack)
+{
+	return 0;
+}
+
+/* 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,
+		       int pf,
+		       unsigned int hooknum)
+{
+	/* Try to delete connection immediately after all replies:
+           won't actually vanish as we still have skb, and del_timer
+           means this will only run once even if count hits zero twice
+           (theoretically possible with SMP) */
+	if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY) {
+		if (atomic_dec_and_test(&ct->proto.icmp.count)
+		    && del_timer(&ct->timeout))
+			ct->timeout.function((unsigned long)ct);
+	} else {
+		atomic_inc(&ct->proto.icmp.count);
+		nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, skb);
+		nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout);
+	}
+
+	return NF_ACCEPT;
+}
+
+/* Called when a new connection for this protocol found. */
+static int icmpv6_new(struct nf_conn *conntrack,
+		      const struct sk_buff *skb,
+		      unsigned int dataoff)
+{
+	static u_int8_t valid_new[] = {
+		[ICMPV6_ECHO_REQUEST - 128] = 1,
+		[ICMPV6_NI_QUERY - 128] = 1
+	};
+
+	if (conntrack->tuplehash[0].tuple.dst.u.icmp.type - 128 >= sizeof(valid_new)
+	    || !valid_new[conntrack->tuplehash[0].tuple.dst.u.icmp.type - 128]) {
+		/* Can't create a new ICMPv6 `conn' with this. */
+		DEBUGP("icmp: can't create new conn with type %u\n",
+		       conntrack->tuplehash[0].tuple.dst.u.icmp.type);
+		NF_CT_DUMP_TUPLE(&conntrack->tuplehash[0].tuple);
+		return 0;
+	}
+	atomic_set(&conntrack->proto.icmp.count, 0);
+	return 1;
+}
+
+extern int
+nf_ct_ipv6_skip_exthdr(struct sk_buff *skb, int start, u8 *nexthdrp, int len);
+extern struct nf_conntrack_l3proto nf_conntrack_l3proto_ipv6;
+static int
+icmpv6_error_message(struct sk_buff *skb,
+		     unsigned int icmp6off,
+		     enum ip_conntrack_info *ctinfo,
+		     unsigned int hooknum)
+{
+	struct nf_conntrack_tuple intuple, origtuple;
+	struct nf_conntrack_tuple_hash *h;
+	struct icmp6hdr _hdr, *hp;
+	unsigned int inip6off;
+	struct nf_conntrack_protocol *inproto;
+	u_int8_t inprotonum;
+	unsigned int inprotoff;
+
+	NF_CT_ASSERT(skb->nfct == NULL);
+
+	hp = skb_header_pointer(skb, icmp6off, sizeof(_hdr), &_hdr);
+	if (hp == NULL) {
+		DEBUGP("icmpv6_error: Can't get ICMPv6 hdr.\n");
+		return -NF_ACCEPT;
+	}
+
+	inip6off = icmp6off + sizeof(_hdr);
+	if (skb_copy_bits(skb, inip6off+offsetof(struct ipv6hdr, nexthdr),
+			  &inprotonum, sizeof(inprotonum)) != 0) {
+		DEBUGP("icmpv6_error: Can't get nexthdr in inner IPv6 header.\n");
+		return -NF_ACCEPT;
+	}
+	inprotoff = nf_ct_ipv6_skip_exthdr(skb,
+					   inip6off + sizeof(struct ipv6hdr),
+					   &inprotonum,
+					   skb->len - inip6off
+						    - sizeof(struct ipv6hdr));
+
+	if ((inprotoff < 0) || (inprotoff > skb->len) ||
+	    (inprotonum == NEXTHDR_FRAGMENT)) {
+		DEBUGP("icmpv6_error: Can't get protocol header in ICMPv6 payload.\n");
+		return -NF_ACCEPT;
+	}
+
+	inproto = nf_ct_find_proto(PF_INET6, inprotonum);
+
+	/* Are they talking about one of our connections? */
+	if (!nf_ct_get_tuple(skb, inip6off, inprotoff, PF_INET6, inprotonum,
+			     &origtuple, &nf_conntrack_l3proto_ipv6, inproto)) {
+		DEBUGP("icmpv6_error: Can't get tuple\n");
+		return -NF_ACCEPT;
+	}
+
+	/* 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)) {
+		DEBUGP("icmpv6_error: Can't invert tuple\n");
+		return -NF_ACCEPT;
+	}
+
+	*ctinfo = IP_CT_RELATED;
+
+	h = nf_conntrack_find_get(&intuple, NULL);
+	if (!h) {
+		DEBUGP("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 sk_buff *skb, unsigned int dataoff,
+	     enum ip_conntrack_info *ctinfo, int pf, unsigned int hooknum)
+{
+	struct icmp6hdr _ih, *icmp6h;
+
+	icmp6h = skb_header_pointer(skb, dataoff, sizeof(_ih), &_ih);
+	if (icmp6h == NULL) {
+		if (LOG_INVALID(IPPROTO_ICMPV6))
+		nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
+			      "nf_ct_icmpv6: short packet ");
+		return -NF_ACCEPT;
+	}
+
+	if (hooknum != NF_IP6_PRE_ROUTING)
+		goto skipped;
+
+	/* Ignore it if the checksum's bogus. */
+	if (csum_ipv6_magic(&skb->nh.ipv6h->saddr, &skb->nh.ipv6h->daddr,
+			    skb->len - dataoff, IPPROTO_ICMPV6,
+			    skb_checksum(skb, dataoff,
+					 skb->len - dataoff, 0))) {
+		nf_log_packet(PF_INET6, 0, skb, NULL, NULL, NULL,
+			      "nf_ct_icmpv6: ICMPv6 checksum failed\n");
+		return -NF_ACCEPT;
+	}
+
+skipped:
+
+	/* is not error message ? */
+	if (icmp6h->icmp6_type >= 128)
+		return NF_ACCEPT;
+
+	return icmpv6_error_message(skb, dataoff, ctinfo, hooknum);
+}
+
+struct nf_conntrack_protocol nf_conntrack_protocol_icmpv6 =
+{
+	.l3proto		= PF_INET6,
+	.proto			= IPPROTO_ICMPV6,
+	.name			= "icmpv6",
+	.pkt_to_tuple		= icmpv6_pkt_to_tuple,
+	.invert_tuple		= icmpv6_invert_tuple,
+	.print_tuple		= icmpv6_print_tuple,
+	.print_conntrack	= icmpv6_print_conntrack,
+	.packet			= icmpv6_packet,
+	.new			= icmpv6_new,
+	.error			= icmpv6_error,
+};
+
+EXPORT_SYMBOL(nf_conntrack_protocol_icmpv6);

net/ipv6/raw.c

@@ -174,9 +174,11 @@ int ipv6_raw_deliver(struct sk_buff *skb, int nexthdr)
 			struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC);
 
 			/* Not releasing hash table! */
-			if (clone)
+			if (clone) {
+				nf_reset(clone);
 				rawv6_rcv(sk, clone);
 			}
+		}
 		sk = __raw_v6_lookup(sk_next(sk), nexthdr, daddr, saddr,
 				     IP6CB(skb)->iif);
 	}

net/ipv6/route.c

@@ -1710,7 +1710,7 @@ static void fib6_dump_end(struct netlink_callback *cb)
 static int fib6_dump_done(struct netlink_callback *cb)
 {
 	fib6_dump_end(cb);
-	return cb->done(cb);
+	return cb->done ? cb->done(cb) : 0;
 }
 
 int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)

net/netfilter/Kconfig

+menu "Core Netfilter Configuration"
+	depends on NET && NETFILTER
+
 config NETFILTER_NETLINK
        tristate "Netfilter netlink interface"
        help
@@ -22,3 +25,74 @@ config NETFILTER_NETLINK_LOG
 	  and is also scheduled to replace the old syslog-based ipt_LOG
 	  and ip6t_LOG modules.
 
+config NF_CONNTRACK
+	tristate "Layer 3 Independent Connection tracking (EXPERIMENTAL)"
+	depends on EXPERIMENTAL && IP_NF_CONNTRACK=n
+	default n
+	---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.
+
+	  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 NF_CT_ACCT
+	bool "Connection tracking flow accounting"
+	depends on NF_CONNTRACK
+	help
+	  If this option is enabled, the connection tracking code will
+	  keep per-flow packet and byte counters.
+
+	  Those counters can be used for flow-based accounting or the
+	  `connbytes' match.
+
+	  If unsure, say `N'.
+
+config NF_CONNTRACK_MARK
+	bool  'Connection mark tracking support'
+	depends on NF_CONNTRACK
+	help
+	  This option enables support for connection marks, used by the
+	  `CONNMARK' target and `connmark' match. Similar to the mark value
+	  of packets, but this mark value is kept in the conntrack session
+	  instead of the individual packets.
+
+config NF_CONNTRACK_EVENTS
+	bool "Connection tracking events"
+	depends on NF_CONNTRACK
+	help
+	  If this option is enabled, the connection tracking code will
+	  provide a notifier chain that can be used by other kernel code
+	  to get notified aboutchanges in the connection tracking state.
+
+	  If unsure, say `N'.
+
+config NF_CT_PROTO_SCTP
+	tristate 'SCTP protocol on new connection tracking support (EXPERIMENTAL)'
+	depends on EXPERIMENTAL && NF_CONNTRACK
+	default n
+	help
+	  With this option enabled, the layer 3 independent connection
+	  tracking code will be able to do state tracking on SCTP connections.
+
+	  If you want to compile it as a module, say M here and read
+	  Documentation/modules.txt.  If unsure, say `N'.
+
+config NF_CONNTRACK_FTP
+	tristate "FTP support on new connection tracking (EXPERIMENTAL)"
+	depends on EXPERIMENTAL && NF_CONNTRACK
+	help
+	  Tracking FTP connections is problematic: special helpers are
+	  required for tracking them, and doing masquerading and other forms
+	  of Network Address Translation on them.
+
+	  This is FTP 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.
+
+endmenu

net/netfilter/Makefile

@@ -5,3 +5,11 @@ obj-$(CONFIG_NETFILTER) = netfilter.o
 obj-$(CONFIG_NETFILTER_NETLINK) += nfnetlink.o
 obj-$(CONFIG_NETFILTER_NETLINK_QUEUE) += nfnetlink_queue.o
 obj-$(CONFIG_NETFILTER_NETLINK_LOG) += nfnetlink_log.o
+
+nf_conntrack-objs	:= nf_conntrack_core.o nf_conntrack_standalone.o nf_conntrack_l3proto_generic.o nf_conntrack_proto_generic.o nf_conntrack_proto_tcp.o nf_conntrack_proto_udp.o
+
+obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o
+obj-$(CONFIG_NF_CONNTRACK_FTP) += nf_conntrack_ftp.o
+
+# SCTP protocol connection tracking
+obj-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o

net/netlink/Makefile

@@ -2,4 +2,4 @@
 # Makefile for the netlink driver.
 #
 
-obj-y  				:= af_netlink.o
+obj-y  				:= af_netlink.o attr.o genetlink.o