Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/kaber/nf-next-2.6

include/linux/netfilter/Kbuild

@@ -33,6 +33,7 @@ header-y += xt_limit.h
 header-y += xt_mac.h
 header-y += xt_mark.h
 header-y += xt_multiport.h
+header-y += xt_osf.h
 header-y += xt_owner.h
 header-y += xt_pkttype.h
 header-y += xt_quota.h

include/linux/netfilter/nf_conntrack_common.h

@@ -75,75 +75,6 @@ enum ip_conntrack_status {
 	IPS_FIXED_TIMEOUT = (1 << IPS_FIXED_TIMEOUT_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, unused */
-	IPCT_COUNTER_FILLING_BIT = 11,
-	IPCT_COUNTER_FILLING = (1 << IPCT_COUNTER_FILLING_BIT),
-
-	/* Mark is set */
-	IPCT_MARK_BIT = 12,
-	IPCT_MARK = (1 << IPCT_MARK_BIT),
-
-	/* NAT sequence adjustment */
-	IPCT_NATSEQADJ_BIT = 13,
-	IPCT_NATSEQADJ = (1 << IPCT_NATSEQADJ_BIT),
-
-	/* Secmark is set */
-	IPCT_SECMARK_BIT = 14,
-	IPCT_SECMARK = (1 << IPCT_SECMARK_BIT),
-};
-
-enum ip_conntrack_expect_events {
-	IPEXP_NEW_BIT = 0,
-	IPEXP_NEW = (1 << IPEXP_NEW_BIT),
-};
-
 #ifdef __KERNEL__
 struct ip_conntrack_stat
 {

include/linux/netfilter/nf_conntrack_tcp.h

@@ -15,7 +15,8 @@ enum tcp_conntrack {
 	TCP_CONNTRACK_LAST_ACK,
 	TCP_CONNTRACK_TIME_WAIT,
 	TCP_CONNTRACK_CLOSE,
-	TCP_CONNTRACK_LISTEN,
+	TCP_CONNTRACK_LISTEN,	/* obsolete */
+#define TCP_CONNTRACK_SYN_SENT2	TCP_CONNTRACK_LISTEN
 	TCP_CONNTRACK_MAX,
 	TCP_CONNTRACK_IGNORE
 };

include/linux/netfilter/nfnetlink.h

@@ -46,7 +46,8 @@ struct nfgenmsg {
 #define NFNL_SUBSYS_CTNETLINK_EXP	2
 #define NFNL_SUBSYS_QUEUE		3
 #define NFNL_SUBSYS_ULOG		4
-#define NFNL_SUBSYS_COUNT		5
+#define NFNL_SUBSYS_OSF			5
+#define NFNL_SUBSYS_COUNT		6
 
 #ifdef __KERNEL__
 
@@ -75,7 +76,7 @@ extern int nfnetlink_subsys_unregister(const struct nfnetlink_subsystem *n);
 
 extern int nfnetlink_has_listeners(unsigned int group);
 extern int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, 
-			  int echo);
+			  int echo, gfp_t flags);
 extern void nfnetlink_set_err(u32 pid, u32 group, int error);
 extern int nfnetlink_unicast(struct sk_buff *skb, u_int32_t pid, int flags);
 

include/linux/netfilter/nfnetlink_conntrack.h

@@ -101,6 +101,7 @@ enum ctattr_protoinfo_dccp {
 	CTA_PROTOINFO_DCCP_UNSPEC,
 	CTA_PROTOINFO_DCCP_STATE,
 	CTA_PROTOINFO_DCCP_ROLE,
+	CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ,
 	__CTA_PROTOINFO_DCCP_MAX,
 };
 #define CTA_PROTOINFO_DCCP_MAX (__CTA_PROTOINFO_DCCP_MAX - 1)

include/linux/netfilter/x_tables.h

@@ -184,9 +184,10 @@ struct xt_counters_info
  * @matchinfo:	per-match data
  * @fragoff:	packet is a fragment, this is the data offset
  * @thoff:	position of transport header relative to skb->data
- * @hotdrop:	drop packet if we had inspection problems
+ * @hook:	hook number given packet came from
  * @family:	Actual NFPROTO_* through which the function is invoked
  * 		(helpful when match->family == NFPROTO_UNSPEC)
+ * @hotdrop:	drop packet if we had inspection problems
  */
 struct xt_match_param {
 	const struct net_device *in, *out;
@@ -194,8 +195,9 @@ struct xt_match_param {
 	const void *matchinfo;
 	int fragoff;
 	unsigned int thoff;
-	bool *hotdrop;
+	unsigned int hooknum;
 	u_int8_t family;
+	bool *hotdrop;
 };
 
 /**

include/linux/netfilter/xt_NFQUEUE.h

@@ -15,4 +15,9 @@ struct xt_NFQ_info {
 	__u16 queuenum;
 };
 
+struct xt_NFQ_info_v1 {
+	__u16 queuenum;
+	__u16 queues_total;
+};
+
 #endif /* _XT_NFQ_TARGET_H */

include/linux/netfilter/xt_osf.h

@@ -0,0 +1,133 @@
+/*
+ * Copyright (c) 2003+ Evgeniy Polyakov <johnpol@2ka.mxt.ru>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _XT_OSF_H
+#define _XT_OSF_H
+
+#define MAXGENRELEN		32
+
+#define XT_OSF_GENRE		(1<<0)
+#define	XT_OSF_TTL		(1<<1)
+#define XT_OSF_LOG		(1<<2)
+#define XT_OSF_INVERT		(1<<3)
+
+#define XT_OSF_LOGLEVEL_ALL	0	/* log all matched fingerprints */
+#define XT_OSF_LOGLEVEL_FIRST	1	/* log only the first matced fingerprint */
+#define XT_OSF_LOGLEVEL_ALL_KNOWN	2 /* do not log unknown packets */
+
+#define XT_OSF_TTL_TRUE		0	/* True ip and fingerprint TTL comparison */
+#define XT_OSF_TTL_LESS		1	/* Check if ip TTL is less than fingerprint one */
+#define XT_OSF_TTL_NOCHECK	2	/* Do not compare ip and fingerprint TTL at all */
+
+struct xt_osf_info {
+	char			genre[MAXGENRELEN];
+	__u32			len;
+	__u32			flags;
+	__u32			loglevel;
+	__u32			ttl;
+};
+
+/*
+ * Wildcard MSS (kind of).
+ * It is used to implement a state machine for the different wildcard values
+ * of the MSS and window sizes.
+ */
+struct xt_osf_wc {
+	__u32			wc;
+	__u32			val;
+};
+
+/*
+ * This struct represents IANA options
+ * http://www.iana.org/assignments/tcp-parameters
+ */
+struct xt_osf_opt {
+	__u16			kind, length;
+	struct xt_osf_wc	wc;
+};
+
+struct xt_osf_user_finger {
+	struct xt_osf_wc	wss;
+
+	__u8			ttl, df;
+	__u16			ss, mss;
+	__u16			opt_num;
+
+	char			genre[MAXGENRELEN];
+	char			version[MAXGENRELEN];
+	char			subtype[MAXGENRELEN];
+
+	/* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */
+	struct xt_osf_opt	opt[MAX_IPOPTLEN];
+};
+
+struct xt_osf_nlmsg {
+	struct xt_osf_user_finger	f;
+	struct iphdr		ip;
+	struct tcphdr		tcp;
+};
+
+/* Defines for IANA option kinds */
+
+enum iana_options {
+	OSFOPT_EOL = 0,		/* End of options */
+	OSFOPT_NOP, 		/* NOP */
+	OSFOPT_MSS, 		/* Maximum segment size */
+	OSFOPT_WSO, 		/* Window scale option */
+	OSFOPT_SACKP,		/* SACK permitted */
+	OSFOPT_SACK,		/* SACK */
+	OSFOPT_ECHO,
+	OSFOPT_ECHOREPLY,
+	OSFOPT_TS,		/* Timestamp option */
+	OSFOPT_POCP,		/* Partial Order Connection Permitted */
+	OSFOPT_POSP,		/* Partial Order Service Profile */
+
+	/* Others are not used in the current OSF */
+	OSFOPT_EMPTY = 255,
+};
+
+/*
+ * Initial window size option state machine: multiple of mss, mtu or
+ * plain numeric value. Can also be made as plain numeric value which
+ * is not a multiple of specified value.
+ */
+enum xt_osf_window_size_options {
+	OSF_WSS_PLAIN	= 0,
+	OSF_WSS_MSS,
+	OSF_WSS_MTU,
+	OSF_WSS_MODULO,
+	OSF_WSS_MAX,
+};
+
+/*
+ * Add/remove fingerprint from the kernel.
+ */
+enum xt_osf_msg_types {
+	OSF_MSG_ADD,
+	OSF_MSG_REMOVE,
+	OSF_MSG_MAX,
+};
+
+enum xt_osf_attr_type {
+	OSF_ATTR_UNSPEC,
+	OSF_ATTR_FINGER,
+	OSF_ATTR_MAX,
+};
+
+#endif				/* _XT_OSF_H */

include/linux/netfilter/xt_socket.h

@@ -0,0 +1,12 @@
+#ifndef _XT_SOCKET_H
+#define _XT_SOCKET_H
+
+enum {
+	XT_SOCKET_TRANSPARENT = 1 << 0,
+};
+
+struct xt_socket_mtinfo1 {
+	__u8 flags;
+};
+
+#endif /* _XT_SOCKET_H */

include/net/netfilter/ipv4/nf_conntrack_icmp.h

@@ -1,11 +0,0 @@
-#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/ipv6/nf_conntrack_icmpv6.h

@@ -9,7 +9,6 @@
 
 #ifndef _NF_CONNTRACK_ICMPV6_H
 #define _NF_CONNTRACK_ICMPV6_H
-#include <asm/atomic.h>
 
 #ifndef ICMPV6_NI_QUERY
 #define ICMPV6_NI_QUERY 139
@@ -18,10 +17,4 @@
 #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.h

@@ -23,7 +23,6 @@
 #include <linux/netfilter/nf_conntrack_dccp.h>
 #include <linux/netfilter/nf_conntrack_sctp.h>
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
-#include <net/netfilter/ipv4/nf_conntrack_icmp.h>
 #include <net/netfilter/ipv6/nf_conntrack_icmpv6.h>
 
 #include <net/netfilter/nf_conntrack_tuple.h>
@@ -34,8 +33,6 @@ union nf_conntrack_proto {
 	struct nf_ct_dccp dccp;
 	struct ip_ct_sctp sctp;
 	struct ip_ct_tcp tcp;
-	struct ip_ct_icmp icmp;
-	struct nf_ct_icmpv6 icmpv6;
 	struct nf_ct_gre gre;
 };
 
@@ -96,6 +93,8 @@ struct nf_conn {
            plus 1 for any connection(s) we are `master' for */
 	struct nf_conntrack ct_general;
 
+	spinlock_t lock;
+
 	/* XXX should I move this to the tail ? - Y.K */
 	/* These are my tuples; original and reply */
 	struct nf_conntrack_tuple_hash tuplehash[IP_CT_DIR_MAX];
@@ -144,6 +143,8 @@ static inline u_int8_t nf_ct_protonum(const struct nf_conn *ct)
 	return ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum;
 }
 
+#define nf_ct_tuple(ct, dir) (&(ct)->tuplehash[dir].tuple)
+
 /* get master conntrack via master expectation */
 #define master_ct(conntr) (conntr->master)
 
@@ -201,7 +202,7 @@ __nf_conntrack_find(struct net *net, const struct nf_conntrack_tuple *tuple);
 
 extern void nf_conntrack_hash_insert(struct nf_conn *ct);
 
-extern void nf_conntrack_flush(struct net *net, u32 pid, int report);
+extern void nf_conntrack_flush_report(struct net *net, u32 pid, int report);
 
 extern bool nf_ct_get_tuplepr(const struct sk_buff *skb,
 			      unsigned int nhoff, u_int16_t l3num,

include/net/netfilter/nf_conntrack_ecache.h

@@ -6,11 +6,55 @@
 #define _NF_CONNTRACK_ECACHE_H
 #include <net/netfilter/nf_conntrack.h>
 
-#include <linux/notifier.h>
 #include <linux/interrupt.h>
 #include <net/net_namespace.h>
 #include <net/netfilter/nf_conntrack_expect.h>
 
+/* 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),
+
+	/* Status has changed */
+	IPCT_STATUS_BIT = 3,
+	IPCT_STATUS = (1 << IPCT_STATUS_BIT),
+
+	/* Update of protocol info */
+	IPCT_PROTOINFO_BIT = 4,
+	IPCT_PROTOINFO = (1 << IPCT_PROTOINFO_BIT),
+
+	/* New helper for conntrack */
+	IPCT_HELPER_BIT = 5,
+	IPCT_HELPER = (1 << IPCT_HELPER_BIT),
+
+	/* Mark is set */
+	IPCT_MARK_BIT = 6,
+	IPCT_MARK = (1 << IPCT_MARK_BIT),
+
+	/* NAT sequence adjustment */
+	IPCT_NATSEQADJ_BIT = 7,
+	IPCT_NATSEQADJ = (1 << IPCT_NATSEQADJ_BIT),
+
+	/* Secmark is set */
+	IPCT_SECMARK_BIT = 8,
+	IPCT_SECMARK = (1 << IPCT_SECMARK_BIT),
+};
+
+enum ip_conntrack_expect_events {
+	IPEXP_NEW_BIT = 0,
+	IPEXP_NEW = (1 << IPEXP_NEW_BIT),
+};
+
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
 struct nf_conntrack_ecache {
 	struct nf_conn *ct;
@@ -24,9 +68,13 @@ struct nf_ct_event {
 	int report;
 };
 
-extern struct atomic_notifier_head nf_conntrack_chain;
-extern int nf_conntrack_register_notifier(struct notifier_block *nb);
-extern int nf_conntrack_unregister_notifier(struct notifier_block *nb);
+struct nf_ct_event_notifier {
+	int (*fcn)(unsigned int events, struct nf_ct_event *item);
+};
+
+extern struct nf_ct_event_notifier *nf_conntrack_event_cb;
+extern int nf_conntrack_register_notifier(struct nf_ct_event_notifier *nb);
+extern void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *nb);
 
 extern void nf_ct_deliver_cached_events(const struct nf_conn *ct);
 extern void __nf_ct_event_cache_init(struct nf_conn *ct);
@@ -52,13 +100,23 @@ nf_conntrack_event_report(enum ip_conntrack_events event,
 			  u32 pid,
 			  int report)
 {
-	struct nf_ct_event item = {
-		.ct 	= ct,
-		.pid	= pid,
-		.report = report
-	};
-	if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct))
-		atomic_notifier_call_chain(&nf_conntrack_chain, event, &item);
+	struct nf_ct_event_notifier *notify;
+
+	rcu_read_lock();
+	notify = rcu_dereference(nf_conntrack_event_cb);
+	if (notify == NULL)
+		goto out_unlock;
+
+	if (nf_ct_is_confirmed(ct) && !nf_ct_is_dying(ct)) {
+		struct nf_ct_event item = {
+			.ct 	= ct,
+			.pid	= pid,
+			.report = report
+		};
+		notify->fcn(event, &item);
+	}
+out_unlock:
+	rcu_read_unlock();
 }
 
 static inline void
@@ -73,9 +131,13 @@ struct nf_exp_event {
 	int report;
 };
 
-extern struct atomic_notifier_head nf_ct_expect_chain;
-extern int nf_ct_expect_register_notifier(struct notifier_block *nb);
-extern int nf_ct_expect_unregister_notifier(struct notifier_block *nb);
+struct nf_exp_event_notifier {
+	int (*fcn)(unsigned int events, struct nf_exp_event *item);
+};
+
+extern struct nf_exp_event_notifier *nf_expect_event_cb;
+extern int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *nb);
+extern void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *nb);
 
 static inline void
 nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
@@ -83,12 +145,23 @@ nf_ct_expect_event_report(enum ip_conntrack_expect_events event,
 			  u32 pid,
 			  int report)
 {
-	struct nf_exp_event item = {
-		.exp	= exp,
-		.pid	= pid,
-		.report = report
-	};
-	atomic_notifier_call_chain(&nf_ct_expect_chain, event, &item);
+	struct nf_exp_event_notifier *notify;
+
+	rcu_read_lock();
+	notify = rcu_dereference(nf_expect_event_cb);
+	if (notify == NULL)
+		goto out_unlock;
+
+	{
+		struct nf_exp_event item = {
+			.exp	= exp,
+			.pid	= pid,
+			.report = report
+		};
+		notify->fcn(event, &item);
+	}
+out_unlock:
+	rcu_read_unlock();
 }
 
 static inline void

include/net/netfilter/nf_conntrack_l4proto.h

@@ -59,11 +59,11 @@ struct nf_conntrack_l4proto
 			   const struct nf_conntrack_tuple *);
 
 	/* Print out the private part of the conntrack. */
-	int (*print_conntrack)(struct seq_file *s, const struct nf_conn *);
+	int (*print_conntrack)(struct seq_file *s, struct nf_conn *);
 
 	/* convert protoinfo to nfnetink attributes */
 	int (*to_nlattr)(struct sk_buff *skb, struct nlattr *nla,
-			 const struct nf_conn *ct);
+			 struct nf_conn *ct);
 	/* Calculate protoinfo nlattr size */
 	int (*nlattr_size)(void);
 

include/net/netlink.h

@@ -939,6 +939,15 @@ static inline u64 nla_get_u64(const struct nlattr *nla)
 	return tmp;
 }
 
+/**
+ * nla_get_be64 - return payload of __be64 attribute
+ * @nla: __be64 netlink attribute
+ */
+static inline __be64 nla_get_be64(const struct nlattr *nla)
+{
+	return *(__be64 *) nla_data(nla);
+}
+
 /**
  * nla_get_flag - return payload of flag attribute
  * @nla: flag netlink attribute

net/bridge/netfilter/ebtables.c

@@ -142,6 +142,12 @@ static inline int ebt_basic_match(struct ebt_entry *e, struct ethhdr *h,
 	return 0;
 }
 
+static inline __pure
+struct ebt_entry *ebt_next_entry(const struct ebt_entry *entry)
+{
+	return (void *)entry + entry->next_offset;
+}
+
 /* Do some firewalling */
 unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb,
    const struct net_device *in, const struct net_device *out,
@@ -164,7 +170,7 @@ unsigned int ebt_do_table (unsigned int hook, struct sk_buff *skb,
 	mtpar.in      = tgpar.in  = in;
 	mtpar.out     = tgpar.out = out;
 	mtpar.hotdrop = &hotdrop;
-	tgpar.hooknum = hook;
+	mtpar.hooknum = tgpar.hooknum = hook;
 
 	read_lock_bh(&table->lock);
 	private = table->private;
@@ -249,8 +255,7 @@ letsreturn:
 		/* jump to a udc */
 		cs[sp].n = i + 1;
 		cs[sp].chaininfo = chaininfo;
-		cs[sp].e = (struct ebt_entry *)
-		   (((char *)point) + point->next_offset);
+		cs[sp].e = ebt_next_entry(point);
 		i = 0;
 		chaininfo = (struct ebt_entries *) (base + verdict);
 #ifdef CONFIG_NETFILTER_DEBUG
@@ -266,8 +271,7 @@ letsreturn:
 		sp++;
 		continue;
 letscontinue:
-		point = (struct ebt_entry *)
-		   (((char *)point) + point->next_offset);
+		point = ebt_next_entry(point);
 		i++;
 	}
 
@@ -787,7 +791,7 @@ static int check_chainloops(struct ebt_entries *chain, struct ebt_cl_stack *cl_s
 			/* this can't be 0, so the loop test is correct */
 			cl_s[i].cs.n = pos + 1;
 			pos = 0;
-			cl_s[i].cs.e = ((void *)e + e->next_offset);
+			cl_s[i].cs.e = ebt_next_entry(e);
 			e = (struct ebt_entry *)(hlp2->data);
 			nentries = hlp2->nentries;
 			cl_s[i].from = chain_nr;
@@ -797,7 +801,7 @@ static int check_chainloops(struct ebt_entries *chain, struct ebt_cl_stack *cl_s
 			continue;
 		}
 letscontinue:
-		e = (void *)e + e->next_offset;
+		e = ebt_next_entry(e);
 		pos++;
 	}
 	return 0;

net/ipv4/netfilter/arp_tables.c

@@ -231,6 +231,12 @@ static inline struct arpt_entry *get_entry(void *base, unsigned int offset)
 	return (struct arpt_entry *)(base + offset);
 }
 
+static inline __pure
+struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry)
+{
+	return (void *)entry + entry->next_offset;
+}
+
 unsigned int arpt_do_table(struct sk_buff *skb,
 			   unsigned int hook,
 			   const struct net_device *in,
@@ -267,67 +273,64 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 
 	arp = arp_hdr(skb);
 	do {
-		if (arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) {
-			struct arpt_entry_target *t;
-			int hdr_len;
-
-			hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
-				(2 * skb->dev->addr_len);
+		struct arpt_entry_target *t;
+		int hdr_len;
 
-			ADD_COUNTER(e->counters, hdr_len, 1);
+		if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) {
+			e = arpt_next_entry(e);
+			continue;
+		}
 
-			t = arpt_get_target(e);
+		hdr_len = sizeof(*arp) + (2 * sizeof(struct in_addr)) +
+			(2 * skb->dev->addr_len);
+		ADD_COUNTER(e->counters, hdr_len, 1);
 
-			/* Standard target? */
-			if (!t->u.kernel.target->target) {
-				int v;
+		t = arpt_get_target(e);
 
-				v = ((struct arpt_standard_target *)t)->verdict;
-				if (v < 0) {
-					/* Pop from stack? */
-					if (v != ARPT_RETURN) {
-						verdict = (unsigned)(-v) - 1;
-						break;
-					}
-					e = back;
-					back = get_entry(table_base,
-							 back->comefrom);
-					continue;
-				}
-				if (table_base + v
-				    != (void *)e + e->next_offset) {
-					/* Save old back ptr in next entry */
-					struct arpt_entry *next
-						= (void *)e + e->next_offset;
-					next->comefrom =
-						(void *)back - table_base;
-
-					/* set back pointer to next entry */
-					back = next;
-				}
+		/* Standard target? */
+		if (!t->u.kernel.target->target) {
+			int v;
 
-				e = get_entry(table_base, v);
-			} else {
-				/* Targets which reenter must return
-				 * abs. verdicts
-				 */
-				tgpar.target   = t->u.kernel.target;
-				tgpar.targinfo = t->data;
-				verdict = t->u.kernel.target->target(skb,
-								     &tgpar);
-
-				/* Target might have changed stuff. */
-				arp = arp_hdr(skb);
-
-				if (verdict == ARPT_CONTINUE)
-					e = (void *)e + e->next_offset;
-				else
-					/* Verdict */
+			v = ((struct arpt_standard_target *)t)->verdict;
+			if (v < 0) {
+				/* Pop from stack? */
+				if (v != ARPT_RETURN) {
+					verdict = (unsigned)(-v) - 1;
 					break;
+				}
+				e = back;
+				back = get_entry(table_base, back->comefrom);
+				continue;
 			}
-		} else {
-			e = (void *)e + e->next_offset;
+			if (table_base + v
+			    != arpt_next_entry(e)) {
+				/* Save old back ptr in next entry */
+				struct arpt_entry *next = arpt_next_entry(e);
+				next->comefrom = (void *)back - table_base;
+
+				/* set back pointer to next entry */
+				back = next;
+			}
+
+			e = get_entry(table_base, v);
+			continue;
 		}
+
+		/* Targets which reenter must return
+		 * abs. verdicts
+		 */
+		tgpar.target   = t->u.kernel.target;
+		tgpar.targinfo = t->data;
+		verdict = t->u.kernel.target->target(skb, &tgpar);
+
+		/* Target might have changed stuff. */
+		arp = arp_hdr(skb);
+
+		if (verdict == ARPT_CONTINUE)
+			e = arpt_next_entry(e);
+		else
+			/* Verdict */
+			break;
 	} while (!hotdrop);
 	xt_info_rdunlock_bh();
 

net/ipv4/netfilter/ip_queue.c

@@ -596,7 +596,7 @@ static int __init ip_queue_init(void)
 #ifdef CONFIG_SYSCTL
 	ipq_sysctl_header = register_sysctl_paths(net_ipv4_ctl_path, ipq_table);
 #endif
-	status = nf_register_queue_handler(PF_INET, &nfqh);
+	status = nf_register_queue_handler(NFPROTO_IPV4, &nfqh);
 	if (status < 0) {
 		printk(KERN_ERR "ip_queue: failed to register queue handler\n");
 		goto cleanup_sysctl;

net/ipv4/netfilter/ip_tables.c

@@ -238,8 +238,8 @@ static struct nf_loginfo trace_loginfo = {
 /* Mildly perf critical (only if packet tracing is on) */
 static inline int
 get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e,
-		      char *hookname, char **chainname,
-		      char **comment, unsigned int *rulenum)
+		      const char *hookname, const char **chainname,
+		      const char **comment, unsigned int *rulenum)
 {
 	struct ipt_standard_target *t = (void *)ipt_get_target(s);
 
@@ -257,8 +257,8 @@ get_chainname_rulenum(struct ipt_entry *s, struct ipt_entry *e,
 		   && unconditional(&s->ip)) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
-				? (char *)comments[NF_IP_TRACE_COMMENT_POLICY]
-				: (char *)comments[NF_IP_TRACE_COMMENT_RETURN];
+				? comments[NF_IP_TRACE_COMMENT_POLICY]
+				: comments[NF_IP_TRACE_COMMENT_RETURN];
 		}
 		return 1;
 	} else
@@ -277,14 +277,14 @@ static void trace_packet(struct sk_buff *skb,
 {
 	void *table_base;
 	const struct ipt_entry *root;
-	char *hookname, *chainname, *comment;
+	const char *hookname, *chainname, *comment;
 	unsigned int rulenum = 0;
 
-	table_base = (void *)private->entries[smp_processor_id()];
+	table_base = private->entries[smp_processor_id()];
 	root = get_entry(table_base, private->hook_entry[hook]);
 
-	hookname = chainname = (char *)hooknames[hook];
-	comment = (char *)comments[NF_IP_TRACE_COMMENT_RULE];
+	hookname = chainname = hooknames[hook];
+	comment = comments[NF_IP_TRACE_COMMENT_RULE];
 
 	IPT_ENTRY_ITERATE(root,
 			  private->size - private->hook_entry[hook],
@@ -297,6 +297,12 @@ static void trace_packet(struct sk_buff *skb,
 }
 #endif
 
+static inline __pure
+struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry)
+{
+	return (void *)entry + entry->next_offset;
+}
+
 /* Returns one of the generic firewall policies, like NF_ACCEPT. */
 unsigned int
 ipt_do_table(struct sk_buff *skb,
@@ -305,6 +311,8 @@ ipt_do_table(struct sk_buff *skb,
 	     const struct net_device *out,
 	     struct xt_table *table)
 {
+#define tb_comefrom ((struct ipt_entry *)table_base)->comefrom
+
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	const struct iphdr *ip;
 	u_int16_t datalen;
@@ -335,7 +343,7 @@ ipt_do_table(struct sk_buff *skb,
 	mtpar.in      = tgpar.in  = in;
 	mtpar.out     = tgpar.out = out;
 	mtpar.family  = tgpar.family = NFPROTO_IPV4;
-	tgpar.hooknum = hook;
+	mtpar.hooknum = tgpar.hooknum = hook;
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
 	xt_info_rdlock_bh();
@@ -348,92 +356,84 @@ ipt_do_table(struct sk_buff *skb,
 	back = get_entry(table_base, private->underflow[hook]);
 
 	do {
+		struct ipt_entry_target *t;
+
 		IP_NF_ASSERT(e);
 		IP_NF_ASSERT(back);
-		if (ip_packet_match(ip, indev, outdev,
-		    &e->ip, mtpar.fragoff)) {
-			struct ipt_entry_target *t;
-
-			if (IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0)
-				goto no_match;
+		if (!ip_packet_match(ip, indev, outdev,
+		    &e->ip, mtpar.fragoff) ||
+		    IPT_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) {
+			e = ipt_next_entry(e);
+			continue;
+		}
 
-			ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
+		ADD_COUNTER(e->counters, ntohs(ip->tot_len), 1);
 
-			t = ipt_get_target(e);
-			IP_NF_ASSERT(t->u.kernel.target);
+		t = ipt_get_target(e);
+		IP_NF_ASSERT(t->u.kernel.target);
 
 #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
     defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
-			/* The packet is traced: log it */
-			if (unlikely(skb->nf_trace))
-				trace_packet(skb, hook, in, out,
-					     table->name, private, e);
+		/* The packet is traced: log it */
+		if (unlikely(skb->nf_trace))
+			trace_packet(skb, hook, in, out,
+				     table->name, private, e);
 #endif
-			/* Standard target? */
-			if (!t->u.kernel.target->target) {
-				int v;
-
-				v = ((struct ipt_standard_target *)t)->verdict;
-				if (v < 0) {
-					/* Pop from stack? */
-					if (v != IPT_RETURN) {
-						verdict = (unsigned)(-v) - 1;
-						break;
-					}
-					e = back;
-					back = get_entry(table_base,
-							 back->comefrom);
-					continue;
-				}
-				if (table_base + v != (void *)e + e->next_offset
-				    && !(e->ip.flags & IPT_F_GOTO)) {
-					/* Save old back ptr in next entry */
-					struct ipt_entry *next
-						= (void *)e + e->next_offset;
-					next->comefrom
-						= (void *)back - table_base;
-					/* set back pointer to next entry */
-					back = next;
+		/* Standard target? */
+		if (!t->u.kernel.target->target) {
+			int v;
+
+			v = ((struct ipt_standard_target *)t)->verdict;
+			if (v < 0) {
+				/* Pop from stack? */
+				if (v != IPT_RETURN) {
+					verdict = (unsigned)(-v) - 1;
+					break;
 				}
+				e = back;
+				back = get_entry(table_base, back->comefrom);
+				continue;
+			}
+			if (table_base + v != ipt_next_entry(e)
+			    && !(e->ip.flags & IPT_F_GOTO)) {
+				/* Save old back ptr in next entry */
+				struct ipt_entry *next = ipt_next_entry(e);
+				next->comefrom = (void *)back - table_base;
+				/* set back pointer to next entry */
+				back = next;
+			}
+
+			e = get_entry(table_base, v);
+			continue;
+		}
+
+		/* Targets which reenter must return
+		   abs. verdicts */
+		tgpar.target   = t->u.kernel.target;
+		tgpar.targinfo = t->data;
+
 
-				e = get_entry(table_base, v);
-			} else {
-				/* Targets which reenter must return
-				   abs. verdicts */
-				tgpar.target   = t->u.kernel.target;
-				tgpar.targinfo = t->data;
 #ifdef CONFIG_NETFILTER_DEBUG
-				((struct ipt_entry *)table_base)->comefrom
-					= 0xeeeeeeec;
+		tb_comefrom = 0xeeeeeeec;
 #endif
-				verdict = t->u.kernel.target->target(skb,
-								     &tgpar);
+		verdict = t->u.kernel.target->target(skb, &tgpar);
 #ifdef CONFIG_NETFILTER_DEBUG
-				if (((struct ipt_entry *)table_base)->comefrom
-				    != 0xeeeeeeec
-				    && verdict == IPT_CONTINUE) {
-					printk("Target %s reentered!\n",
-					       t->u.kernel.target->name);
-					verdict = NF_DROP;
-				}
-				((struct ipt_entry *)table_base)->comefrom
-					= 0x57acc001;
+		if (tb_comefrom != 0xeeeeeeec && verdict == IPT_CONTINUE) {
+			printk("Target %s reentered!\n",
+			       t->u.kernel.target->name);
+			verdict = NF_DROP;
+		}
+		tb_comefrom = 0x57acc001;
 #endif
-				/* Target might have changed stuff. */
-				ip = ip_hdr(skb);
-				datalen = skb->len - ip->ihl * 4;
-
-				if (verdict == IPT_CONTINUE)
-					e = (void *)e + e->next_offset;
-				else
-					/* Verdict */
-					break;
-			}
-		} else {
+		/* Target might have changed stuff. */
+		ip = ip_hdr(skb);
+		datalen = skb->len - ip->ihl * 4;
 
-		no_match:
-			e = (void *)e + e->next_offset;
-		}
+		if (verdict == IPT_CONTINUE)
+			e = ipt_next_entry(e);
+		else
+			/* Verdict */
+			break;
 	} while (!hotdrop);
 	xt_info_rdunlock_bh();
 
@@ -444,6 +444,8 @@ ipt_do_table(struct sk_buff *skb,
 		return NF_DROP;
 	else return verdict;
 #endif
+
+#undef tb_comefrom
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -2158,7 +2160,7 @@ static bool icmp_checkentry(const struct xt_mtchk_param *par)
 static struct xt_target ipt_standard_target __read_mostly = {
 	.name		= IPT_STANDARD_TARGET,
 	.targetsize	= sizeof(int),
-	.family		= AF_INET,
+	.family		= NFPROTO_IPV4,
 #ifdef CONFIG_COMPAT
 	.compatsize	= sizeof(compat_int_t),
 	.compat_from_user = compat_standard_from_user,
@@ -2170,7 +2172,7 @@ static struct xt_target ipt_error_target __read_mostly = {
 	.name		= IPT_ERROR_TARGET,
 	.target		= ipt_error,
 	.targetsize	= IPT_FUNCTION_MAXNAMELEN,
-	.family		= AF_INET,
+	.family		= NFPROTO_IPV4,
 };
 
 static struct nf_sockopt_ops ipt_sockopts = {
@@ -2196,17 +2198,17 @@ static struct xt_match icmp_matchstruct __read_mostly = {
 	.matchsize	= sizeof(struct ipt_icmp),
 	.checkentry	= icmp_checkentry,
 	.proto		= IPPROTO_ICMP,
-	.family		= AF_INET,
+	.family		= NFPROTO_IPV4,
 };
 
 static int __net_init ip_tables_net_init(struct net *net)
 {
-	return xt_proto_init(net, AF_INET);
+	return xt_proto_init(net, NFPROTO_IPV4);
 }
 
 static void __net_exit ip_tables_net_exit(struct net *net)
 {
-	xt_proto_fini(net, AF_INET);
+	xt_proto_fini(net, NFPROTO_IPV4);
 }
 
 static struct pernet_operations ip_tables_net_ops = {

net/ipv4/netfilter/ipt_MASQUERADE.c

@@ -27,9 +27,6 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>");
 MODULE_DESCRIPTION("Xtables: automatic-address SNAT");
 
-/* Lock protects masq region inside conntrack */
-static DEFINE_RWLOCK(masq_lock);
-
 /* FIXME: Multiple targets. --RR */
 static bool masquerade_tg_check(const struct xt_tgchk_param *par)
 {
@@ -79,9 +76,7 @@ masquerade_tg(struct sk_buff *skb, const struct xt_target_param *par)
 		return NF_DROP;
 	}
 
-	write_lock_bh(&masq_lock);
 	nat->masq_index = par->out->ifindex;
-	write_unlock_bh(&masq_lock);
 
 	/* Transfer from original range. */
 	newrange = ((struct nf_nat_range)
@@ -97,16 +92,11 @@ static int
 device_cmp(struct nf_conn *i, void *ifindex)
 {
 	const struct nf_conn_nat *nat = nfct_nat(i);
-	int ret;
 
 	if (!nat)
 		return 0;
 
-	read_lock_bh(&masq_lock);
-	ret = (nat->masq_index == (int)(long)ifindex);
-	read_unlock_bh(&masq_lock);
-
-	return ret;
+	return nat->masq_index == (int)(long)ifindex;
 }
 
 static int masq_device_event(struct notifier_block *this,

net/ipv4/netfilter/nf_conntrack_proto_icmp.c

@@ -82,18 +82,10 @@ static int icmp_packet(struct nf_conn *ct,
 		       u_int8_t 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))
-			nf_ct_kill_acct(ct, ctinfo, skb);
-	} else {
-		atomic_inc(&ct->proto.icmp.count);
-		nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct);
-		nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
-	}
+	/* Do not immediately delete the connection after the first
+	   successful reply to avoid excessive conntrackd traffic
+	   and also to handle correctly ICMP echo reply duplicates. */
+	nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmp_timeout);
 
 	return NF_ACCEPT;
 }
@@ -117,7 +109,6 @@ static bool icmp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		nf_ct_dump_tuple_ip(&ct->tuplehash[0].tuple);
 		return false;
 	}
-	atomic_set(&ct->proto.icmp.count, 0);
 	return true;
 }
 

net/ipv6/netfilter/ip6_queue.c

@@ -598,7 +598,7 @@ static int __init ip6_queue_init(void)
 #ifdef CONFIG_SYSCTL
 	ipq_sysctl_header = register_sysctl_paths(net_ipv6_ctl_path, ipq_table);
 #endif
-	status = nf_register_queue_handler(PF_INET6, &nfqh);
+	status = nf_register_queue_handler(NFPROTO_IPV6, &nfqh);
 	if (status < 0) {
 		printk(KERN_ERR "ip6_queue: failed to register queue handler\n");
 		goto cleanup_sysctl;

net/ipv6/netfilter/ip6_tables.c

@@ -270,8 +270,8 @@ static struct nf_loginfo trace_loginfo = {
 /* Mildly perf critical (only if packet tracing is on) */
 static inline int
 get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e,
-		      char *hookname, char **chainname,
-		      char **comment, unsigned int *rulenum)
+		      const char *hookname, const char **chainname,
+		      const char **comment, unsigned int *rulenum)
 {
 	struct ip6t_standard_target *t = (void *)ip6t_get_target(s);
 
@@ -289,8 +289,8 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e,
 		   && unconditional(&s->ipv6)) {
 			/* Tail of chains: STANDARD target (return/policy) */
 			*comment = *chainname == hookname
-				? (char *)comments[NF_IP6_TRACE_COMMENT_POLICY]
-				: (char *)comments[NF_IP6_TRACE_COMMENT_RETURN];
+				? comments[NF_IP6_TRACE_COMMENT_POLICY]
+				: comments[NF_IP6_TRACE_COMMENT_RETURN];
 		}
 		return 1;
 	} else
@@ -309,14 +309,14 @@ static void trace_packet(struct sk_buff *skb,
 {
 	void *table_base;
 	const struct ip6t_entry *root;
-	char *hookname, *chainname, *comment;
+	const char *hookname, *chainname, *comment;
 	unsigned int rulenum = 0;
 
-	table_base = (void *)private->entries[smp_processor_id()];
+	table_base = private->entries[smp_processor_id()];
 	root = get_entry(table_base, private->hook_entry[hook]);
 
-	hookname = chainname = (char *)hooknames[hook];
-	comment = (char *)comments[NF_IP6_TRACE_COMMENT_RULE];
+	hookname = chainname = hooknames[hook];
+	comment = comments[NF_IP6_TRACE_COMMENT_RULE];
 
 	IP6T_ENTRY_ITERATE(root,
 			   private->size - private->hook_entry[hook],
@@ -329,6 +329,12 @@ static void trace_packet(struct sk_buff *skb,
 }
 #endif
 
+static inline __pure struct ip6t_entry *
+ip6t_next_entry(const struct ip6t_entry *entry)
+{
+	return (void *)entry + entry->next_offset;
+}
+
 /* Returns one of the generic firewall policies, like NF_ACCEPT. */
 unsigned int
 ip6t_do_table(struct sk_buff *skb,
@@ -337,6 +343,8 @@ ip6t_do_table(struct sk_buff *skb,
 	      const struct net_device *out,
 	      struct xt_table *table)
 {
+#define tb_comefrom ((struct ip6t_entry *)table_base)->comefrom
+
 	static const char nulldevname[IFNAMSIZ] __attribute__((aligned(sizeof(long))));
 	bool hotdrop = false;
 	/* Initializing verdict to NF_DROP keeps gcc happy. */
@@ -361,7 +369,7 @@ ip6t_do_table(struct sk_buff *skb,
 	mtpar.in      = tgpar.in  = in;
 	mtpar.out     = tgpar.out = out;
 	mtpar.family  = tgpar.family = NFPROTO_IPV6;
-	tgpar.hooknum = hook;
+	mtpar.hooknum = tgpar.hooknum = hook;
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
 
@@ -375,96 +383,86 @@ ip6t_do_table(struct sk_buff *skb,
 	back = get_entry(table_base, private->underflow[hook]);
 
 	do {
+		struct ip6t_entry_target *t;
+
 		IP_NF_ASSERT(e);
 		IP_NF_ASSERT(back);
-		if (ip6_packet_match(skb, indev, outdev, &e->ipv6,
-			&mtpar.thoff, &mtpar.fragoff, &hotdrop)) {
-			struct ip6t_entry_target *t;
-
-			if (IP6T_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0)
-				goto no_match;
+		if (!ip6_packet_match(skb, indev, outdev, &e->ipv6,
+		    &mtpar.thoff, &mtpar.fragoff, &hotdrop) ||
+		    IP6T_MATCH_ITERATE(e, do_match, skb, &mtpar) != 0) {
+			e = ip6t_next_entry(e);
+			continue;
+		}
 
-			ADD_COUNTER(e->counters,
-				    ntohs(ipv6_hdr(skb)->payload_len) +
-				    sizeof(struct ipv6hdr), 1);
+		ADD_COUNTER(e->counters,
+			    ntohs(ipv6_hdr(skb)->payload_len) +
+			    sizeof(struct ipv6hdr), 1);
 
-			t = ip6t_get_target(e);
-			IP_NF_ASSERT(t->u.kernel.target);
+		t = ip6t_get_target(e);
+		IP_NF_ASSERT(t->u.kernel.target);
 
 #if defined(CONFIG_NETFILTER_XT_TARGET_TRACE) || \
     defined(CONFIG_NETFILTER_XT_TARGET_TRACE_MODULE)
-			/* The packet is traced: log it */
-			if (unlikely(skb->nf_trace))
-				trace_packet(skb, hook, in, out,
-					     table->name, private, e);
+		/* The packet is traced: log it */
+		if (unlikely(skb->nf_trace))
+			trace_packet(skb, hook, in, out,
+				     table->name, private, e);
 #endif
-			/* Standard target? */
-			if (!t->u.kernel.target->target) {
-				int v;
-
-				v = ((struct ip6t_standard_target *)t)->verdict;
-				if (v < 0) {
-					/* Pop from stack? */
-					if (v != IP6T_RETURN) {
-						verdict = (unsigned)(-v) - 1;
-						break;
-					}
-					e = back;
-					back = get_entry(table_base,
-							 back->comefrom);
-					continue;
-				}
-				if (table_base + v != (void *)e + e->next_offset
-				    && !(e->ipv6.flags & IP6T_F_GOTO)) {
-					/* Save old back ptr in next entry */
-					struct ip6t_entry *next
-						= (void *)e + e->next_offset;
-					next->comefrom
-						= (void *)back - table_base;
-					/* set back pointer to next entry */
-					back = next;
+		/* Standard target? */
+		if (!t->u.kernel.target->target) {
+			int v;
+
+			v = ((struct ip6t_standard_target *)t)->verdict;
+			if (v < 0) {
+				/* Pop from stack? */
+				if (v != IP6T_RETURN) {
+					verdict = (unsigned)(-v) - 1;
+					break;
 				}
+				e = back;
+				back = get_entry(table_base, back->comefrom);
+				continue;
+			}
+			if (table_base + v != ip6t_next_entry(e)
+			    && !(e->ipv6.flags & IP6T_F_GOTO)) {
+				/* Save old back ptr in next entry */
+				struct ip6t_entry *next = ip6t_next_entry(e);
+				next->comefrom = (void *)back - table_base;
+				/* set back pointer to next entry */
+				back = next;
+			}
 
-				e = get_entry(table_base, v);
-			} else {
-				/* Targets which reenter must return
-				   abs. verdicts */
-				tgpar.target   = t->u.kernel.target;
-				tgpar.targinfo = t->data;
+			e = get_entry(table_base, v);
+			continue;
+		}
 
-#ifdef CONFIG_NETFILTER_DEBUG
-				((struct ip6t_entry *)table_base)->comefrom
-					= 0xeeeeeeec;
-#endif
-				verdict = t->u.kernel.target->target(skb,
-								     &tgpar);
+		/* Targets which reenter must return
+		   abs. verdicts */
+		tgpar.target   = t->u.kernel.target;
+		tgpar.targinfo = t->data;
 
 #ifdef CONFIG_NETFILTER_DEBUG
-				if (((struct ip6t_entry *)table_base)->comefrom
-				    != 0xeeeeeeec
-				    && verdict == IP6T_CONTINUE) {
-					printk("Target %s reentered!\n",
-					       t->u.kernel.target->name);
-					verdict = NF_DROP;
-				}
-				((struct ip6t_entry *)table_base)->comefrom
-					= 0x57acc001;
+		tb_comefrom = 0xeeeeeeec;
 #endif
-				if (verdict == IP6T_CONTINUE)
-					e = (void *)e + e->next_offset;
-				else
-					/* Verdict */
-					break;
-			}
-		} else {
+		verdict = t->u.kernel.target->target(skb, &tgpar);
 
-		no_match:
-			e = (void *)e + e->next_offset;
+#ifdef CONFIG_NETFILTER_DEBUG
+		if (tb_comefrom != 0xeeeeeeec && verdict == IP6T_CONTINUE) {
+			printk("Target %s reentered!\n",
+			       t->u.kernel.target->name);
+			verdict = NF_DROP;
 		}
+		tb_comefrom = 0x57acc001;
+#endif
+		if (verdict == IP6T_CONTINUE)
+			e = ip6t_next_entry(e);
+		else
+			/* Verdict */
+			break;
 	} while (!hotdrop);
 
 #ifdef CONFIG_NETFILTER_DEBUG
-	((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON;
+	tb_comefrom = NETFILTER_LINK_POISON;
 #endif
 	xt_info_rdunlock_bh();
 
@@ -475,6 +473,8 @@ ip6t_do_table(struct sk_buff *skb,
 		return NF_DROP;
 	else return verdict;
 #endif
+
+#undef tb_comefrom
 }
 
 /* Figures out from what hook each rule can be called: returns 0 if
@@ -2191,7 +2191,7 @@ static bool icmp6_checkentry(const struct xt_mtchk_param *par)
 static struct xt_target ip6t_standard_target __read_mostly = {
 	.name		= IP6T_STANDARD_TARGET,
 	.targetsize	= sizeof(int),
-	.family		= AF_INET6,
+	.family		= NFPROTO_IPV6,
 #ifdef CONFIG_COMPAT
 	.compatsize	= sizeof(compat_int_t),
 	.compat_from_user = compat_standard_from_user,
@@ -2203,7 +2203,7 @@ static struct xt_target ip6t_error_target __read_mostly = {
 	.name		= IP6T_ERROR_TARGET,
 	.target		= ip6t_error,
 	.targetsize	= IP6T_FUNCTION_MAXNAMELEN,
-	.family		= AF_INET6,
+	.family		= NFPROTO_IPV6,
 };
 
 static struct nf_sockopt_ops ip6t_sockopts = {
@@ -2229,17 +2229,17 @@ static struct xt_match icmp6_matchstruct __read_mostly = {
 	.matchsize	= sizeof(struct ip6t_icmp),
 	.checkentry	= icmp6_checkentry,
 	.proto		= IPPROTO_ICMPV6,
-	.family		= AF_INET6,
+	.family		= NFPROTO_IPV6,
 };
 
 static int __net_init ip6_tables_net_init(struct net *net)
 {
-	return xt_proto_init(net, AF_INET6);
+	return xt_proto_init(net, NFPROTO_IPV6);
 }
 
 static void __net_exit ip6_tables_net_exit(struct net *net)
 {
-	xt_proto_fini(net, AF_INET6);
+	xt_proto_fini(net, NFPROTO_IPV6);
 }
 
 static struct pernet_operations ip6_tables_net_ops = {

net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c

@@ -95,18 +95,10 @@ static int icmpv6_packet(struct nf_conn *ct,
 		       u_int8_t 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))
-			nf_ct_kill_acct(ct, ctinfo, skb);
-	} else {
-		atomic_inc(&ct->proto.icmp.count);
-		nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct);
-		nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout);
-	}
+	/* Do not immediately delete the connection after the first
+	   successful reply to avoid excessive conntrackd traffic
+	   and also to handle correctly ICMP echo reply duplicates. */
+	nf_ct_refresh_acct(ct, ctinfo, skb, nf_ct_icmpv6_timeout);
 
 	return NF_ACCEPT;
 }
@@ -132,7 +124,6 @@ static bool icmpv6_new(struct nf_conn *ct, const struct sk_buff *skb,
 				      type + 128);
 		return false;
 	}
-	atomic_set(&ct->proto.icmp.count, 0);
 	return true;
 }
 

net/netfilter/Kconfig

@@ -917,6 +917,19 @@ config NETFILTER_XT_MATCH_U32
 
 	  Details and examples are in the kernel module source.
 
+config NETFILTER_XT_MATCH_OSF
+	tristate '"osf" Passive OS fingerprint match'
+	depends on NETFILTER_ADVANCED && NETFILTER_NETLINK
+	help
+	  This option selects the Passive OS Fingerprinting match module
+	  that allows to passively match the remote operating system by
+	  analyzing incoming TCP SYN packets.
+
+	  Rules and loading software can be downloaded from
+	  http://www.ioremap.net/projects/osf
+
+	  To compile it as a module, choose M here.  If unsure, say N.
+
 endif # NETFILTER_XTABLES
 
 endmenu

net/netfilter/Makefile

@@ -77,6 +77,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_MAC) += xt_mac.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_MARK) += xt_mark.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_MULTIPORT) += xt_multiport.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_OSF) += xt_osf.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_OWNER) += xt_owner.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PHYSDEV) += xt_physdev.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_PKTTYPE) += xt_pkttype.o

net/netfilter/nf_conntrack_core.c

@@ -398,11 +398,7 @@ __nf_conntrack_confirm(struct sk_buff *skb)
 	help = nfct_help(ct);
 	if (help && help->helper)
 		nf_conntrack_event_cache(IPCT_HELPER, ct);
-#ifdef CONFIG_NF_NAT_NEEDED
-	if (test_bit(IPS_SRC_NAT_DONE_BIT, &ct->status) ||
-	    test_bit(IPS_DST_NAT_DONE_BIT, &ct->status))
-		nf_conntrack_event_cache(IPCT_NATINFO, ct);
-#endif
+
 	nf_conntrack_event_cache(master_ct(ct) ?
 				 IPCT_RELATED : IPCT_NEW, ct);
 	return NF_ACCEPT;
@@ -523,6 +519,7 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
 		return ERR_PTR(-ENOMEM);
 	}
 
+	spin_lock_init(&ct->lock);
 	atomic_set(&ct->ct_general.use, 1);
 	ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple = *orig;
 	ct->tuplehash[IP_CT_DIR_REPLY].tuple = *repl;
@@ -807,8 +804,6 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 			  unsigned long extra_jiffies,
 			  int do_acct)
 {
-	int event = 0;
-
 	NF_CT_ASSERT(ct->timeout.data == (unsigned long)ct);
 	NF_CT_ASSERT(skb);
 
@@ -821,7 +816,6 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 	/* If not in hash table, timer will not be active yet */
 	if (!nf_ct_is_confirmed(ct)) {
 		ct->timeout.expires = extra_jiffies;
-		event = IPCT_REFRESH;
 	} else {
 		unsigned long newtime = jiffies + extra_jiffies;
 
@@ -832,7 +826,6 @@ void __nf_ct_refresh_acct(struct nf_conn *ct,
 		    && del_timer(&ct->timeout)) {
 			ct->timeout.expires = newtime;
 			add_timer(&ct->timeout);
-			event = IPCT_REFRESH;
 		}
 	}
 
@@ -849,10 +842,6 @@ acct:
 	}
 
 	spin_unlock_bh(&nf_conntrack_lock);
-
-	/* must be unlocked when calling event cache */
-	if (event)
-		nf_conntrack_event_cache(event, ct);
 }
 EXPORT_SYMBOL_GPL(__nf_ct_refresh_acct);
 
@@ -1001,7 +990,7 @@ struct __nf_ct_flush_report {
 	int report;
 };
 
-static int kill_all(struct nf_conn *i, void *data)
+static int kill_report(struct nf_conn *i, void *data)
 {
 	struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data;
 
@@ -1013,6 +1002,11 @@ static int kill_all(struct nf_conn *i, void *data)
 	return 1;
 }
 
+static int kill_all(struct nf_conn *i, void *data)
+{
+	return 1;
+}
+
 void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size)
 {
 	if (vmalloced)
@@ -1023,15 +1017,15 @@ void nf_ct_free_hashtable(void *hash, int vmalloced, unsigned int size)
 }
 EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
 
-void nf_conntrack_flush(struct net *net, u32 pid, int report)
+void nf_conntrack_flush_report(struct net *net, u32 pid, int report)
 {
 	struct __nf_ct_flush_report fr = {
 		.pid 	= pid,
 		.report = report,
 	};
-	nf_ct_iterate_cleanup(net, kill_all, &fr);
+	nf_ct_iterate_cleanup(net, kill_report, &fr);
 }
-EXPORT_SYMBOL_GPL(nf_conntrack_flush);
+EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
 
 static void nf_conntrack_cleanup_init_net(void)
 {
@@ -1045,7 +1039,7 @@ static void nf_conntrack_cleanup_net(struct net *net)
 	nf_ct_event_cache_flush(net);
 	nf_conntrack_ecache_fini(net);
  i_see_dead_people:
-	nf_conntrack_flush(net, 0, 0);
+	nf_ct_iterate_cleanup(net, kill_all, NULL);
 	if (atomic_read(&net->ct.count) != 0) {
 		schedule();
 		goto i_see_dead_people;

net/netfilter/nf_conntrack_ecache.c

@@ -16,24 +16,32 @@
 #include <linux/stddef.h>
 #include <linux/err.h>
 #include <linux/percpu.h>
-#include <linux/notifier.h>
 #include <linux/kernel.h>
 #include <linux/netdevice.h>
 
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_core.h>
 
-ATOMIC_NOTIFIER_HEAD(nf_conntrack_chain);
-EXPORT_SYMBOL_GPL(nf_conntrack_chain);
+static DEFINE_MUTEX(nf_ct_ecache_mutex);
 
-ATOMIC_NOTIFIER_HEAD(nf_ct_expect_chain);
-EXPORT_SYMBOL_GPL(nf_ct_expect_chain);
+struct nf_ct_event_notifier *nf_conntrack_event_cb __read_mostly;
+EXPORT_SYMBOL_GPL(nf_conntrack_event_cb);
+
+struct nf_exp_event_notifier *nf_expect_event_cb __read_mostly;
+EXPORT_SYMBOL_GPL(nf_expect_event_cb);
 
 /* deliver cached events and clear cache entry - must be called with locally
  * disabled softirqs */
 static inline void
 __nf_ct_deliver_cached_events(struct nf_conntrack_ecache *ecache)
 {
+	struct nf_ct_event_notifier *notify;
+
+	rcu_read_lock();
+	notify = rcu_dereference(nf_conntrack_event_cb);
+	if (notify == NULL)
+		goto out_unlock;
+
 	if (nf_ct_is_confirmed(ecache->ct) && !nf_ct_is_dying(ecache->ct)
 	    && ecache->events) {
 		struct nf_ct_event item = {
@@ -42,14 +50,15 @@ __nf_ct_deliver_cached_events(struct nf_conntrack_ecache *ecache)
 			.report	= 0
 		};
 
-		atomic_notifier_call_chain(&nf_conntrack_chain,
-					   ecache->events,
-					   &item);
+		notify->fcn(ecache->events, &item);
 	}
 
 	ecache->events = 0;
 	nf_ct_put(ecache->ct);
 	ecache->ct = NULL;
+
+out_unlock:
+	rcu_read_unlock();
 }
 
 /* Deliver all cached events for a particular conntrack. This is called
@@ -111,26 +120,68 @@ void nf_conntrack_ecache_fini(struct net *net)
 	free_percpu(net->ct.ecache);
 }
 
-int nf_conntrack_register_notifier(struct notifier_block *nb)
+int nf_conntrack_register_notifier(struct nf_ct_event_notifier *new)
 {
-	return atomic_notifier_chain_register(&nf_conntrack_chain, nb);
+	int ret = 0;
+	struct nf_ct_event_notifier *notify;
+
+	mutex_lock(&nf_ct_ecache_mutex);
+	notify = rcu_dereference(nf_conntrack_event_cb);
+	if (notify != NULL) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	rcu_assign_pointer(nf_conntrack_event_cb, new);
+	mutex_unlock(&nf_ct_ecache_mutex);
+	return ret;
+
+out_unlock:
+	mutex_unlock(&nf_ct_ecache_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_register_notifier);
 
-int nf_conntrack_unregister_notifier(struct notifier_block *nb)
+void nf_conntrack_unregister_notifier(struct nf_ct_event_notifier *new)
 {
-	return atomic_notifier_chain_unregister(&nf_conntrack_chain, nb);
+	struct nf_ct_event_notifier *notify;
+
+	mutex_lock(&nf_ct_ecache_mutex);
+	notify = rcu_dereference(nf_conntrack_event_cb);
+	BUG_ON(notify != new);
+	rcu_assign_pointer(nf_conntrack_event_cb, NULL);
+	mutex_unlock(&nf_ct_ecache_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_unregister_notifier);
 
-int nf_ct_expect_register_notifier(struct notifier_block *nb)
+int nf_ct_expect_register_notifier(struct nf_exp_event_notifier *new)
 {
-	return atomic_notifier_chain_register(&nf_ct_expect_chain, nb);
+	int ret = 0;
+	struct nf_exp_event_notifier *notify;
+
+	mutex_lock(&nf_ct_ecache_mutex);
+	notify = rcu_dereference(nf_expect_event_cb);
+	if (notify != NULL) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+	rcu_assign_pointer(nf_expect_event_cb, new);
+	mutex_unlock(&nf_ct_ecache_mutex);
+	return ret;
+
+out_unlock:
+	mutex_unlock(&nf_ct_ecache_mutex);
+	return ret;
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_register_notifier);
 
-int nf_ct_expect_unregister_notifier(struct notifier_block *nb)
+void nf_ct_expect_unregister_notifier(struct nf_exp_event_notifier *new)
 {
-	return atomic_notifier_chain_unregister(&nf_ct_expect_chain, nb);
+	struct nf_exp_event_notifier *notify;
+
+	mutex_lock(&nf_ct_ecache_mutex);
+	notify = rcu_dereference(nf_expect_event_cb);
+	BUG_ON(notify != new);
+	rcu_assign_pointer(nf_expect_event_cb, NULL);
+	mutex_unlock(&nf_ct_ecache_mutex);
 }
 EXPORT_SYMBOL_GPL(nf_ct_expect_unregister_notifier);

net/netfilter/nf_conntrack_ftp.c

@@ -338,11 +338,9 @@ static void update_nl_seq(struct nf_conn *ct, u32 nl_seq,
 
 	if (info->seq_aft_nl_num[dir] < NUM_SEQ_TO_REMEMBER) {
 		info->seq_aft_nl[dir][info->seq_aft_nl_num[dir]++] = nl_seq;
-		nf_conntrack_event_cache(IPCT_HELPINFO_VOLATILE, ct);
 	} else if (oldest != NUM_SEQ_TO_REMEMBER &&
 		   after(nl_seq, info->seq_aft_nl[dir][oldest])) {
 		info->seq_aft_nl[dir][oldest] = nl_seq;
-		nf_conntrack_event_cache(IPCT_HELPINFO_VOLATILE, ct);
 	}
 }
 

net/netfilter/nf_conntrack_netlink.c

@@ -27,7 +27,6 @@
 #include <linux/netlink.h>
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
-#include <linux/notifier.h>
 
 #include <linux/netfilter.h>
 #include <net/netlink.h>
@@ -144,7 +143,7 @@ nla_put_failure:
 }
 
 static inline int
-ctnetlink_dump_protoinfo(struct sk_buff *skb, const struct nf_conn *ct)
+ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct)
 {
 	struct nf_conntrack_l4proto *l4proto;
 	struct nlattr *nest_proto;
@@ -346,23 +345,21 @@ nla_put_failure:
 	return -1;
 }
 
-#define tuple(ct, dir) (&(ct)->tuplehash[dir].tuple)
-
 static int
 ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
-		    int event, int nowait,
-		    const struct nf_conn *ct)
+		    int event, struct nf_conn *ct)
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 	struct nlattr *nest_parms;
-	unsigned char *b = skb_tail_pointer(skb);
+	unsigned int flags = pid ? NLM_F_MULTI : 0;
 
 	event |= NFNL_SUBSYS_CTNETLINK << 8;
-	nlh    = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg));
-	nfmsg  = NLMSG_DATA(nlh);
+	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
+	if (nlh == NULL)
+		goto nlmsg_failure;
 
-	nlh->nlmsg_flags    = (nowait && pid) ? NLM_F_MULTI : 0;
+	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family = nf_ct_l3num(ct);
 	nfmsg->version      = NFNETLINK_V0;
 	nfmsg->res_id	    = 0;
@@ -370,14 +367,14 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
 	if (!nest_parms)
 		goto nla_put_failure;
-	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
+	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
 	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
 	if (!nest_parms)
 		goto nla_put_failure;
-	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
+	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
@@ -395,104 +392,81 @@ ctnetlink_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 	    ctnetlink_dump_nat_seq_adj(skb, ct) < 0)
 		goto nla_put_failure;
 
-	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+	nlmsg_end(skb, nlh);
 	return skb->len;
 
 nlmsg_failure:
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nlmsg_cancel(skb, nlh);
 	return -1;
 }
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-/*
- * The general structure of a ctnetlink event is
- *
- *  CTA_TUPLE_ORIG
- *    <l3/l4-proto-attributes>
- *  CTA_TUPLE_REPLY
- *    <l3/l4-proto-attributes>
- *  CTA_ID
- *  ...
- *  CTA_PROTOINFO
- *    <l4-proto-attributes>
- *  CTA_TUPLE_MASTER
- *    <l3/l4-proto-attributes>
- *
- * Therefore the formular is
- *
- *   size = sizeof(headers) + sizeof(generic_nlas) + 3 * sizeof(tuple_nlas)
- *		+ sizeof(protoinfo_nlas)
- */
-static struct sk_buff *
-ctnetlink_alloc_skb(const struct nf_conntrack_tuple *tuple, gfp_t gfp)
+static inline size_t
+ctnetlink_proto_size(const struct nf_conn *ct)
 {
 	struct nf_conntrack_l3proto *l3proto;
 	struct nf_conntrack_l4proto *l4proto;
-	int len;
-
-#define NLA_TYPE_SIZE(type)		nla_total_size(sizeof(type))
-
-	/* proto independant part */
-	len = NLMSG_SPACE(sizeof(struct nfgenmsg))
-		+ 3 * nla_total_size(0)		/* CTA_TUPLE_ORIG|REPL|MASTER */
-		+ 3 * nla_total_size(0)		/* CTA_TUPLE_IP */
-		+ 3 * nla_total_size(0)		/* CTA_TUPLE_PROTO */
-		+ 3 * NLA_TYPE_SIZE(u_int8_t)	/* CTA_PROTO_NUM */
-		+ NLA_TYPE_SIZE(u_int32_t)	/* CTA_ID */
-		+ NLA_TYPE_SIZE(u_int32_t)	/* CTA_STATUS */
+	size_t len = 0;
+
+	rcu_read_lock();
+	l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
+	len += l3proto->nla_size;
+
+	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
+	len += l4proto->nla_size;
+	rcu_read_unlock();
+
+	return len;
+}
+
+static inline size_t
+ctnetlink_nlmsg_size(const struct nf_conn *ct)
+{
+	return NLMSG_ALIGN(sizeof(struct nfgenmsg))
+	       + 3 * nla_total_size(0) /* CTA_TUPLE_ORIG|REPL|MASTER */
+	       + 3 * nla_total_size(0) /* CTA_TUPLE_IP */
+	       + 3 * nla_total_size(0) /* CTA_TUPLE_PROTO */
+	       + 3 * nla_total_size(sizeof(u_int8_t)) /* CTA_PROTO_NUM */
+	       + nla_total_size(sizeof(u_int32_t)) /* CTA_ID */
+	       + nla_total_size(sizeof(u_int32_t)) /* CTA_STATUS */
 #ifdef CONFIG_NF_CT_ACCT
-		+ 2 * nla_total_size(0)		/* CTA_COUNTERS_ORIG|REPL */
-		+ 2 * NLA_TYPE_SIZE(uint64_t)	/* CTA_COUNTERS_PACKETS */
-		+ 2 * NLA_TYPE_SIZE(uint64_t)	/* CTA_COUNTERS_BYTES */
+	       + 2 * nla_total_size(0) /* CTA_COUNTERS_ORIG|REPL */
+	       + 2 * nla_total_size(sizeof(uint64_t)) /* CTA_COUNTERS_PACKETS */
+	       + 2 * nla_total_size(sizeof(uint64_t)) /* CTA_COUNTERS_BYTES */
 #endif
-		+ NLA_TYPE_SIZE(u_int32_t)	/* CTA_TIMEOUT */
-		+ nla_total_size(0)		/* CTA_PROTOINFO */
-		+ nla_total_size(0)		/* CTA_HELP */
-		+ nla_total_size(NF_CT_HELPER_NAME_LEN)	/* CTA_HELP_NAME */
+	       + nla_total_size(sizeof(u_int32_t)) /* CTA_TIMEOUT */
+	       + nla_total_size(0) /* CTA_PROTOINFO */
+	       + nla_total_size(0) /* CTA_HELP */
+	       + nla_total_size(NF_CT_HELPER_NAME_LEN) /* CTA_HELP_NAME */
 #ifdef CONFIG_NF_CONNTRACK_SECMARK
-		+ NLA_TYPE_SIZE(u_int32_t)	/* CTA_SECMARK */
+	       + nla_total_size(sizeof(u_int32_t)) /* CTA_SECMARK */
 #endif
 #ifdef CONFIG_NF_NAT_NEEDED
-		+ 2 * nla_total_size(0)		/* CTA_NAT_SEQ_ADJ_ORIG|REPL */
-		+ 2 * NLA_TYPE_SIZE(u_int32_t)	/* CTA_NAT_SEQ_CORRECTION_POS */
-		+ 2 * NLA_TYPE_SIZE(u_int32_t)	/* CTA_NAT_SEQ_CORRECTION_BEFORE */
-		+ 2 * NLA_TYPE_SIZE(u_int32_t)	/* CTA_NAT_SEQ_CORRECTION_AFTER */
+	       + 2 * nla_total_size(0) /* CTA_NAT_SEQ_ADJ_ORIG|REPL */
+	       + 6 * nla_total_size(sizeof(u_int32_t)) /* CTA_NAT_SEQ_OFFSET */
 #endif
 #ifdef CONFIG_NF_CONNTRACK_MARK
-		+ NLA_TYPE_SIZE(u_int32_t)	/* CTA_MARK */
+	       + nla_total_size(sizeof(u_int32_t)) /* CTA_MARK */
 #endif
-		;
-
-#undef NLA_TYPE_SIZE
-
-	rcu_read_lock();
-	l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
-	len += l3proto->nla_size;
-
-	l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum);
-	len += l4proto->nla_size;
-	rcu_read_unlock();
-
-	return alloc_skb(len, gfp);
+	       + ctnetlink_proto_size(ct)
+	       ;
 }
 
-static int ctnetlink_conntrack_event(struct notifier_block *this,
-				     unsigned long events, void *ptr)
+static int
+ctnetlink_conntrack_event(unsigned int events, struct nf_ct_event *item)
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
 	struct nlattr *nest_parms;
-	struct nf_ct_event *item = (struct nf_ct_event *)ptr;
 	struct nf_conn *ct = item->ct;
 	struct sk_buff *skb;
 	unsigned int type;
-	sk_buff_data_t b;
 	unsigned int flags = 0, group;
 
 	/* ignore our fake conntrack entry */
 	if (ct == &nf_conntrack_untracked)
-		return NOTIFY_DONE;
+		return 0;
 
 	if (events & IPCT_DESTROY) {
 		type = IPCTNL_MSG_CT_DELETE;
@@ -501,26 +475,25 @@ static int ctnetlink_conntrack_event(struct notifier_block *this,
 		type = IPCTNL_MSG_CT_NEW;
 		flags = NLM_F_CREATE|NLM_F_EXCL;
 		group = NFNLGRP_CONNTRACK_NEW;
-	} else  if (events & (IPCT_STATUS | IPCT_PROTOINFO)) {
+	} else  if (events) {
 		type = IPCTNL_MSG_CT_NEW;
 		group = NFNLGRP_CONNTRACK_UPDATE;
 	} else
-		return NOTIFY_DONE;
+		return 0;
 
 	if (!item->report && !nfnetlink_has_listeners(group))
-		return NOTIFY_DONE;
+		return 0;
 
-	skb = ctnetlink_alloc_skb(tuple(ct, IP_CT_DIR_ORIGINAL), GFP_ATOMIC);
-	if (!skb)
+	skb = nlmsg_new(ctnetlink_nlmsg_size(ct), GFP_ATOMIC);
+	if (skb == NULL)
 		goto errout;
 
-	b = skb->tail;
-
 	type |= NFNL_SUBSYS_CTNETLINK << 8;
-	nlh   = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg));
-	nfmsg = NLMSG_DATA(nlh);
+	nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags);
+	if (nlh == NULL)
+		goto nlmsg_failure;
 
-	nlh->nlmsg_flags    = flags;
+	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family = nf_ct_l3num(ct);
 	nfmsg->version	= NFNETLINK_V0;
 	nfmsg->res_id	= 0;
@@ -529,14 +502,14 @@ static int ctnetlink_conntrack_event(struct notifier_block *this,
 	nest_parms = nla_nest_start(skb, CTA_TUPLE_ORIG | NLA_F_NESTED);
 	if (!nest_parms)
 		goto nla_put_failure;
-	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
+	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_ORIGINAL)) < 0)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
 	nest_parms = nla_nest_start(skb, CTA_TUPLE_REPLY | NLA_F_NESTED);
 	if (!nest_parms)
 		goto nla_put_failure;
-	if (ctnetlink_dump_tuples(skb, tuple(ct, IP_CT_DIR_REPLY)) < 0)
+	if (ctnetlink_dump_tuples(skb, nf_ct_tuple(ct, IP_CT_DIR_REPLY)) < 0)
 		goto nla_put_failure;
 	nla_nest_end(skb, nest_parms);
 
@@ -584,17 +557,18 @@ static int ctnetlink_conntrack_event(struct notifier_block *this,
 #endif
 	rcu_read_unlock();
 
-	nlh->nlmsg_len = skb->tail - b;
-	nfnetlink_send(skb, item->pid, group, item->report);
-	return NOTIFY_DONE;
+	nlmsg_end(skb, nlh);
+	nfnetlink_send(skb, item->pid, group, item->report, GFP_ATOMIC);
+	return 0;
 
 nla_put_failure:
 	rcu_read_unlock();
+	nlmsg_cancel(skb, nlh);
 nlmsg_failure:
 	kfree_skb(skb);
 errout:
 	nfnetlink_set_err(0, group, -ENOBUFS);
-	return NOTIFY_DONE;
+	return 0;
 }
 #endif /* CONFIG_NF_CONNTRACK_EVENTS */
 
@@ -611,7 +585,7 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 	struct nf_conn *ct, *last;
 	struct nf_conntrack_tuple_hash *h;
 	struct hlist_nulls_node *n;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	u_int8_t l3proto = nfmsg->nfgen_family;
 
 	rcu_read_lock();
@@ -637,8 +611,7 @@ restart:
 			}
 			if (ctnetlink_fill_info(skb, NETLINK_CB(cb->skb).pid,
 						cb->nlh->nlmsg_seq,
-						IPCTNL_MSG_CT_NEW,
-						1, ct) < 0) {
+						IPCTNL_MSG_CT_NEW, ct) < 0) {
 				cb->args[1] = (unsigned long)ct;
 				goto out;
 			}
@@ -792,7 +765,7 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_tuple_hash *h;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conn *ct;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
 	int err = 0;
 
@@ -802,9 +775,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 		err = ctnetlink_parse_tuple(cda, &tuple, CTA_TUPLE_REPLY, u3);
 	else {
 		/* Flush the whole table */
-		nf_conntrack_flush(&init_net, 
-				   NETLINK_CB(skb).pid, 
-				   nlmsg_report(nlh));
+		nf_conntrack_flush_report(&init_net,
+					 NETLINK_CB(skb).pid,
+					 nlmsg_report(nlh));
 		return 0;
 	}
 
@@ -847,7 +820,7 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_tuple tuple;
 	struct nf_conn *ct;
 	struct sk_buff *skb2 = NULL;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
 	int err = 0;
 
@@ -872,15 +845,15 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	ct = nf_ct_tuplehash_to_ctrack(h);
 
 	err = -ENOMEM;
-	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb2) {
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb2 == NULL) {
 		nf_ct_put(ct);
 		return -ENOMEM;
 	}
 
 	rcu_read_lock();
 	err = ctnetlink_fill_info(skb2, NETLINK_CB(skb).pid, nlh->nlmsg_seq,
-				  IPCTNL_MSG_CT_NEW, 1, ct);
+				  IPCTNL_MSG_CT_NEW, ct);
 	rcu_read_unlock();
 	nf_ct_put(ct);
 	if (err <= 0)
@@ -1325,7 +1298,7 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 {
 	struct nf_conntrack_tuple otuple, rtuple;
 	struct nf_conntrack_tuple_hash *h = NULL;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
 	int err = 0;
 
@@ -1503,19 +1476,18 @@ nla_put_failure:
 
 static int
 ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
-		    int event,
-		    int nowait,
-		    const struct nf_conntrack_expect *exp)
+			int event, const struct nf_conntrack_expect *exp)
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
-	unsigned char *b = skb_tail_pointer(skb);
+	unsigned int flags = pid ? NLM_F_MULTI : 0;
 
 	event |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
-	nlh    = NLMSG_PUT(skb, pid, seq, event, sizeof(struct nfgenmsg));
-	nfmsg  = NLMSG_DATA(nlh);
+	nlh = nlmsg_put(skb, pid, seq, event, sizeof(*nfmsg), flags);
+	if (nlh == NULL)
+		goto nlmsg_failure;
 
-	nlh->nlmsg_flags    = (nowait && pid) ? NLM_F_MULTI : 0;
+	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family = exp->tuple.src.l3num;
 	nfmsg->version	    = NFNETLINK_V0;
 	nfmsg->res_id	    = 0;
@@ -1523,49 +1495,46 @@ ctnetlink_exp_fill_info(struct sk_buff *skb, u32 pid, u32 seq,
 	if (ctnetlink_exp_dump_expect(skb, exp) < 0)
 		goto nla_put_failure;
 
-	nlh->nlmsg_len = skb_tail_pointer(skb) - b;
+	nlmsg_end(skb, nlh);
 	return skb->len;
 
 nlmsg_failure:
 nla_put_failure:
-	nlmsg_trim(skb, b);
+	nlmsg_cancel(skb, nlh);
 	return -1;
 }
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-static int ctnetlink_expect_event(struct notifier_block *this,
-				  unsigned long events, void *ptr)
+static int
+ctnetlink_expect_event(unsigned int events, struct nf_exp_event *item)
 {
 	struct nlmsghdr *nlh;
 	struct nfgenmsg *nfmsg;
-	struct nf_exp_event *item = (struct nf_exp_event *)ptr;
 	struct nf_conntrack_expect *exp = item->exp;
 	struct sk_buff *skb;
 	unsigned int type;
-	sk_buff_data_t b;
 	int flags = 0;
 
 	if (events & IPEXP_NEW) {
 		type = IPCTNL_MSG_EXP_NEW;
 		flags = NLM_F_CREATE|NLM_F_EXCL;
 	} else
-		return NOTIFY_DONE;
+		return 0;
 
 	if (!item->report &&
 	    !nfnetlink_has_listeners(NFNLGRP_CONNTRACK_EXP_NEW))
-		return NOTIFY_DONE;
+		return 0;
 
-	skb = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
-	if (!skb)
+	skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	if (skb == NULL)
 		goto errout;
 
-	b = skb->tail;
-
 	type |= NFNL_SUBSYS_CTNETLINK_EXP << 8;
-	nlh   = NLMSG_PUT(skb, item->pid, 0, type, sizeof(struct nfgenmsg));
-	nfmsg = NLMSG_DATA(nlh);
+	nlh = nlmsg_put(skb, item->pid, 0, type, sizeof(*nfmsg), flags);
+	if (nlh == NULL)
+		goto nlmsg_failure;
 
-	nlh->nlmsg_flags    = flags;
+	nfmsg = nlmsg_data(nlh);
 	nfmsg->nfgen_family = exp->tuple.src.l3num;
 	nfmsg->version	    = NFNETLINK_V0;
 	nfmsg->res_id	    = 0;
@@ -1575,17 +1544,19 @@ static int ctnetlink_expect_event(struct notifier_block *this,
 		goto nla_put_failure;
 	rcu_read_unlock();
 
-	nlh->nlmsg_len = skb->tail - b;
-	nfnetlink_send(skb, item->pid, NFNLGRP_CONNTRACK_EXP_NEW, item->report);
-	return NOTIFY_DONE;
+	nlmsg_end(skb, nlh);
+	nfnetlink_send(skb, item->pid, NFNLGRP_CONNTRACK_EXP_NEW,
+		       item->report, GFP_ATOMIC);
+	return 0;
 
 nla_put_failure:
 	rcu_read_unlock();
+	nlmsg_cancel(skb, nlh);
 nlmsg_failure:
 	kfree_skb(skb);
 errout:
 	nfnetlink_set_err(0, 0, -ENOBUFS);
-	return NOTIFY_DONE;
+	return 0;
 }
 #endif
 static int ctnetlink_exp_done(struct netlink_callback *cb)
@@ -1600,7 +1571,7 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct net *net = &init_net;
 	struct nf_conntrack_expect *exp, *last;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(cb->nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(cb->nlh);
 	struct hlist_node *n;
 	u_int8_t l3proto = nfmsg->nfgen_family;
 
@@ -1617,10 +1588,11 @@ restart:
 					continue;
 				cb->args[1] = 0;
 			}
-			if (ctnetlink_exp_fill_info(skb, NETLINK_CB(cb->skb).pid,
+			if (ctnetlink_exp_fill_info(skb,
+						    NETLINK_CB(cb->skb).pid,
 						    cb->nlh->nlmsg_seq,
 						    IPCTNL_MSG_EXP_NEW,
-						    1, exp) < 0) {
+						    exp) < 0) {
 				if (!atomic_inc_not_zero(&exp->use))
 					continue;
 				cb->args[1] = (unsigned long)exp;
@@ -1652,7 +1624,7 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_expect *exp;
 	struct sk_buff *skb2;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
 	int err = 0;
 
@@ -1683,14 +1655,13 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 	}
 
 	err = -ENOMEM;
-	skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL);
-	if (!skb2)
+	skb2 = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (skb2 == NULL)
 		goto out;
 
 	rcu_read_lock();
 	err = ctnetlink_exp_fill_info(skb2, NETLINK_CB(skb).pid,
-				      nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW,
-				      1, exp);
+				      nlh->nlmsg_seq, IPCTNL_MSG_EXP_NEW, exp);
 	rcu_read_unlock();
 	if (err <= 0)
 		goto free;
@@ -1713,7 +1684,7 @@ ctnetlink_del_expect(struct sock *ctnl, struct sk_buff *skb,
 	struct nf_conntrack_expect *exp;
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_helper *h;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	struct hlist_node *n, *next;
 	u_int8_t u3 = nfmsg->nfgen_family;
 	unsigned int i;
@@ -1854,7 +1825,7 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
 {
 	struct nf_conntrack_tuple tuple;
 	struct nf_conntrack_expect *exp;
-	struct nfgenmsg *nfmsg = NLMSG_DATA(nlh);
+	struct nfgenmsg *nfmsg = nlmsg_data(nlh);
 	u_int8_t u3 = nfmsg->nfgen_family;
 	int err = 0;
 
@@ -1891,12 +1862,12 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
 }
 
 #ifdef CONFIG_NF_CONNTRACK_EVENTS
-static struct notifier_block ctnl_notifier = {
-	.notifier_call	= ctnetlink_conntrack_event,
+static struct nf_ct_event_notifier ctnl_notifier = {
+	.fcn = ctnetlink_conntrack_event,
 };
 
-static struct notifier_block ctnl_notifier_exp = {
-	.notifier_call	= ctnetlink_expect_event,
+static struct nf_exp_event_notifier ctnl_notifier_exp = {
+	.fcn = ctnetlink_expect_event,
 };
 #endif
 

net/netfilter/nf_conntrack_proto_dccp.c

@@ -25,8 +25,6 @@
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_log.h>
 
-static DEFINE_RWLOCK(dccp_lock);
-
 /* Timeouts are based on values from RFC4340:
  *
  * - REQUEST:
@@ -492,7 +490,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 		return NF_ACCEPT;
 	}
 
-	write_lock_bh(&dccp_lock);
+	spin_lock_bh(&ct->lock);
 
 	role = ct->proto.dccp.role[dir];
 	old_state = ct->proto.dccp.state;
@@ -536,13 +534,13 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 		ct->proto.dccp.last_dir = dir;
 		ct->proto.dccp.last_pkt = type;
 
-		write_unlock_bh(&dccp_lock);
+		spin_unlock_bh(&ct->lock);
 		if (LOG_INVALID(net, IPPROTO_DCCP))
 			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
 				      "nf_ct_dccp: invalid packet ignored ");
 		return NF_ACCEPT;
 	case CT_DCCP_INVALID:
-		write_unlock_bh(&dccp_lock);
+		spin_unlock_bh(&ct->lock);
 		if (LOG_INVALID(net, IPPROTO_DCCP))
 			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
 				      "nf_ct_dccp: invalid state transition ");
@@ -552,7 +550,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 	ct->proto.dccp.last_dir = dir;
 	ct->proto.dccp.last_pkt = type;
 	ct->proto.dccp.state = new_state;
-	write_unlock_bh(&dccp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	if (new_state != old_state)
 		nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
@@ -621,36 +619,39 @@ static int dccp_print_tuple(struct seq_file *s,
 			  ntohs(tuple->dst.u.dccp.port));
 }
 
-static int dccp_print_conntrack(struct seq_file *s, const struct nf_conn *ct)
+static int dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	return seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
 }
 
 #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE)
 static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
-			  const struct nf_conn *ct)
+			  struct nf_conn *ct)
 {
 	struct nlattr *nest_parms;
 
-	read_lock_bh(&dccp_lock);
+	spin_lock_bh(&ct->lock);
 	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP | NLA_F_NESTED);
 	if (!nest_parms)
 		goto nla_put_failure;
 	NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state);
 	NLA_PUT_U8(skb, CTA_PROTOINFO_DCCP_ROLE,
 		   ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]);
+	NLA_PUT_BE64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ,
+		     cpu_to_be64(ct->proto.dccp.handshake_seq));
 	nla_nest_end(skb, nest_parms);
-	read_unlock_bh(&dccp_lock);
+	spin_unlock_bh(&ct->lock);
 	return 0;
 
 nla_put_failure:
-	read_unlock_bh(&dccp_lock);
+	spin_unlock_bh(&ct->lock);
 	return -1;
 }
 
 static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = {
 	[CTA_PROTOINFO_DCCP_STATE]	= { .type = NLA_U8 },
 	[CTA_PROTOINFO_DCCP_ROLE]	= { .type = NLA_U8 },
+	[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ] = { .type = NLA_U64 },
 };
 
 static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
@@ -674,7 +675,7 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
 		return -EINVAL;
 	}
 
-	write_lock_bh(&dccp_lock);
+	spin_lock_bh(&ct->lock);
 	ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]);
 	if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) {
 		ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
@@ -683,7 +684,11 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
 		ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER;
 		ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT;
 	}
-	write_unlock_bh(&dccp_lock);
+	if (tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]) {
+		ct->proto.dccp.handshake_seq =
+		be64_to_cpu(nla_get_be64(tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]));
+	}
+	spin_unlock_bh(&ct->lock);
 	return 0;
 }
 

net/netfilter/nf_conntrack_proto_gre.c

@@ -219,8 +219,7 @@ static int gre_print_tuple(struct seq_file *s,
 }
 
 /* print private data for conntrack */
-static int gre_print_conntrack(struct seq_file *s,
-			       const struct nf_conn *ct)
+static int gre_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	return seq_printf(s, "timeout=%u, stream_timeout=%u ",
 			  (ct->proto.gre.timeout / HZ),

net/netfilter/nf_conntrack_proto_sctp.c

@@ -25,9 +25,6 @@
 #include <net/netfilter/nf_conntrack_l4proto.h>
 #include <net/netfilter/nf_conntrack_ecache.h>
 
-/* Protects ct->proto.sctp */
-static DEFINE_RWLOCK(sctp_lock);
-
 /* FIXME: Examine ipfilter's timeouts and conntrack transitions more
    closely.  They're more complex. --RR
 
@@ -164,13 +161,13 @@ static int sctp_print_tuple(struct seq_file *s,
 }
 
 /* Print out the private part of the conntrack. */
-static int sctp_print_conntrack(struct seq_file *s, const struct nf_conn *ct)
+static int sctp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	enum sctp_conntrack state;
 
-	read_lock_bh(&sctp_lock);
+	spin_lock_bh(&ct->lock);
 	state = ct->proto.sctp.state;
-	read_unlock_bh(&sctp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	return seq_printf(s, "%s ", sctp_conntrack_names[state]);
 }
@@ -318,7 +315,7 @@ static int sctp_packet(struct nf_conn *ct,
 	}
 
 	old_state = new_state = SCTP_CONNTRACK_NONE;
-	write_lock_bh(&sctp_lock);
+	spin_lock_bh(&ct->lock);
 	for_each_sctp_chunk (skb, sch, _sch, offset, dataoff, count) {
 		/* Special cases of Verification tag check (Sec 8.5.1) */
 		if (sch->type == SCTP_CID_INIT) {
@@ -371,7 +368,7 @@ static int sctp_packet(struct nf_conn *ct,
 		if (old_state != new_state)
 			nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
 	}
-	write_unlock_bh(&sctp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	nf_ct_refresh_acct(ct, ctinfo, skb, sctp_timeouts[new_state]);
 
@@ -386,7 +383,7 @@ static int sctp_packet(struct nf_conn *ct,
 	return NF_ACCEPT;
 
 out_unlock:
-	write_unlock_bh(&sctp_lock);
+	spin_unlock_bh(&ct->lock);
 out:
 	return -NF_ACCEPT;
 }
@@ -469,11 +466,11 @@ static bool sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
 static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
-			  const struct nf_conn *ct)
+			  struct nf_conn *ct)
 {
 	struct nlattr *nest_parms;
 
-	read_lock_bh(&sctp_lock);
+	spin_lock_bh(&ct->lock);
 	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_SCTP | NLA_F_NESTED);
 	if (!nest_parms)
 		goto nla_put_failure;
@@ -488,14 +485,14 @@ static int sctp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 		     CTA_PROTOINFO_SCTP_VTAG_REPLY,
 		     ct->proto.sctp.vtag[IP_CT_DIR_REPLY]);
 
-	read_unlock_bh(&sctp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	nla_nest_end(skb, nest_parms);
 
 	return 0;
 
 nla_put_failure:
-	read_unlock_bh(&sctp_lock);
+	spin_unlock_bh(&ct->lock);
 	return -1;
 }
 
@@ -527,13 +524,13 @@ static int nlattr_to_sctp(struct nlattr *cda[], struct nf_conn *ct)
 	    !tb[CTA_PROTOINFO_SCTP_VTAG_REPLY])
 		return -EINVAL;
 
-	write_lock_bh(&sctp_lock);
+	spin_lock_bh(&ct->lock);
 	ct->proto.sctp.state = nla_get_u8(tb[CTA_PROTOINFO_SCTP_STATE]);
 	ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] =
 		nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_ORIGINAL]);
 	ct->proto.sctp.vtag[IP_CT_DIR_REPLY] =
 		nla_get_be32(tb[CTA_PROTOINFO_SCTP_VTAG_REPLY]);
-	write_unlock_bh(&sctp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	return 0;
 }

net/netfilter/nf_conntrack_proto_tcp.c

@@ -29,9 +29,6 @@
 #include <net/netfilter/ipv4/nf_conntrack_ipv4.h>
 #include <net/netfilter/ipv6/nf_conntrack_ipv6.h>
 
-/* Protects ct->proto.tcp */
-static DEFINE_RWLOCK(tcp_lock);
-
 /* "Be conservative in what you do,
     be liberal in what you accept from others."
     If it's non-zero, we mark only out of window RST segments as INVALID. */
@@ -59,7 +56,7 @@ static const char *const tcp_conntrack_names[] = {
 	"LAST_ACK",
 	"TIME_WAIT",
 	"CLOSE",
-	"LISTEN"
+	"SYN_SENT2",
 };
 
 #define SECS * HZ
@@ -82,6 +79,7 @@ static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = {
 	[TCP_CONNTRACK_LAST_ACK]	= 30 SECS,
 	[TCP_CONNTRACK_TIME_WAIT]	= 2 MINS,
 	[TCP_CONNTRACK_CLOSE]		= 10 SECS,
+	[TCP_CONNTRACK_SYN_SENT2]	= 2 MINS,
 };
 
 #define sNO TCP_CONNTRACK_NONE
@@ -93,7 +91,7 @@ static unsigned int tcp_timeouts[TCP_CONNTRACK_MAX] __read_mostly = {
 #define sLA TCP_CONNTRACK_LAST_ACK
 #define sTW TCP_CONNTRACK_TIME_WAIT
 #define sCL TCP_CONNTRACK_CLOSE
-#define sLI TCP_CONNTRACK_LISTEN
+#define sS2 TCP_CONNTRACK_SYN_SENT2
 #define sIV TCP_CONNTRACK_MAX
 #define sIG TCP_CONNTRACK_IGNORE
 
@@ -123,6 +121,7 @@ enum tcp_bit_set {
  *
  * NONE:	initial state
  * SYN_SENT:	SYN-only packet seen
+ * SYN_SENT2:	SYN-only packet seen from reply dir, simultaneous open
  * SYN_RECV:	SYN-ACK packet seen
  * ESTABLISHED:	ACK packet seen
  * FIN_WAIT:	FIN packet seen
@@ -131,26 +130,24 @@ enum tcp_bit_set {
  * TIME_WAIT:	last ACK seen
  * CLOSE:	closed connection (RST)
  *
- * LISTEN state is not used.
- *
  * Packets marked as IGNORED (sIG):
  *	if they may be either invalid or valid
  *	and the receiver may send back a connection
  *	closing RST or a SYN/ACK.
  *
  * Packets marked as INVALID (sIV):
- *	if they are invalid
- *	or we do not support the request (simultaneous open)
+ *	if we regard them as truly invalid packets
  */
 static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
 	{
 /* ORIGINAL */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*syn*/	   { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sIV },
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
+/*syn*/	   { sSS, sSS, sIG, sIG, sIG, sIG, sIG, sSS, sSS, sS2 },
 /*
  *	sNO -> sSS	Initialize a new connection
  *	sSS -> sSS	Retransmitted SYN
- *	sSR -> sIG	Late retransmitted SYN?
+ *	sS2 -> sS2	Late retransmitted SYN
+ *	sSR -> sIG
  *	sES -> sIG	Error: SYNs in window outside the SYN_SENT state
  *			are errors. Receiver will reply with RST
  *			and close the connection.
@@ -161,22 +158,30 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sTW -> sSS	Reopened connection (RFC 1122).
  *	sCL -> sSS
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*synack*/ { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV },
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
+/*synack*/ { sIV, sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG, sSR },
 /*
- * A SYN/ACK from the client is always invalid:
- *	- either it tries to set up a simultaneous open, which is
- *	  not supported;
- *	- or the firewall has just been inserted between the two hosts
- *	  during the session set-up. The SYN will be retransmitted
- *	  by the true client (or it'll time out).
+ *	sNO -> sIV	Too late and no reason to do anything
+ *	sSS -> sIV	Client can't send SYN and then SYN/ACK
+ *	sS2 -> sSR	SYN/ACK sent to SYN2 in simultaneous open
+ *	sSR -> sIG
+ *	sES -> sIG	Error: SYNs in window outside the SYN_SENT state
+ *			are errors. Receiver will reply with RST
+ *			and close the connection.
+ *			Or we are not in sync and hold a dead connection.
+ *	sFW -> sIG
+ *	sCW -> sIG
+ *	sLA -> sIG
+ *	sTW -> sIG
+ *	sCL -> sIG
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
 /*fin*/    { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV },
 /*
  *	sNO -> sIV	Too late and no reason to do anything...
  *	sSS -> sIV	Client migth not send FIN in this state:
  *			we enforce waiting for a SYN/ACK reply first.
+ *	sS2 -> sIV
  *	sSR -> sFW	Close started.
  *	sES -> sFW
  *	sFW -> sLA	FIN seen in both directions, waiting for
@@ -187,11 +192,12 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sTW -> sTW
  *	sCL -> sCL
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
 /*ack*/	   { sES, sIV, sES, sES, sCW, sCW, sTW, sTW, sCL, sIV },
 /*
  *	sNO -> sES	Assumed.
  *	sSS -> sIV	ACK is invalid: we haven't seen a SYN/ACK yet.
+ *	sS2 -> sIV
  *	sSR -> sES	Established state is reached.
  *	sES -> sES	:-)
  *	sFW -> sCW	Normal close request answered by ACK.
@@ -200,29 +206,31 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sTW -> sTW	Retransmitted last ACK. Remain in the same state.
  *	sCL -> sCL
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*rst*/    { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV },
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
+/*rst*/    { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL },
 /*none*/   { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }
 	},
 	{
 /* REPLY */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*syn*/	   { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV },
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
+/*syn*/	   { sIV, sS2, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sS2 },
 /*
  *	sNO -> sIV	Never reached.
- *	sSS -> sIV	Simultaneous open, not supported
- *	sSR -> sIV	Simultaneous open, not supported.
- *	sES -> sIV	Server may not initiate a connection.
+ *	sSS -> sS2	Simultaneous open
+ *	sS2 -> sS2	Retransmitted simultaneous SYN
+ *	sSR -> sIV	Invalid SYN packets sent by the server
+ *	sES -> sIV
  *	sFW -> sIV
  *	sCW -> sIV
  *	sLA -> sIV
  *	sTW -> sIV	Reopened connection, but server may not do it.
  *	sCL -> sIV
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sIV },
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
+/*synack*/ { sIV, sSR, sSR, sIG, sIG, sIG, sIG, sIG, sIG, sSR },
 /*
  *	sSS -> sSR	Standard open.
+ *	sS2 -> sSR	Simultaneous open
  *	sSR -> sSR	Retransmitted SYN/ACK.
  *	sES -> sIG	Late retransmitted SYN/ACK?
  *	sFW -> sIG	Might be SYN/ACK answering ignored SYN
@@ -231,10 +239,11 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sTW -> sIG
  *	sCL -> sIG
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
 /*fin*/    { sIV, sIV, sFW, sFW, sLA, sLA, sLA, sTW, sCL, sIV },
 /*
  *	sSS -> sIV	Server might not send FIN in this state.
+ *	sS2 -> sIV
  *	sSR -> sFW	Close started.
  *	sES -> sFW
  *	sFW -> sLA	FIN seen in both directions.
@@ -243,10 +252,11 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sTW -> sTW
  *	sCL -> sCL
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*ack*/	   { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIV },
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
+/*ack*/	   { sIV, sIG, sSR, sES, sCW, sCW, sTW, sTW, sCL, sIG },
 /*
  *	sSS -> sIG	Might be a half-open connection.
+ *	sS2 -> sIG
  *	sSR -> sSR	Might answer late resent SYN.
  *	sES -> sES	:-)
  *	sFW -> sCW	Normal close request answered by ACK.
@@ -255,8 +265,8 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = {
  *	sTW -> sTW	Retransmitted last ACK.
  *	sCL -> sCL
  */
-/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sLI	*/
-/*rst*/    { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV },
+/* 	     sNO, sSS, sSR, sES, sFW, sCW, sLA, sTW, sCL, sS2	*/
+/*rst*/    { sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL },
 /*none*/   { sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV }
 	}
 };
@@ -296,13 +306,13 @@ static int tcp_print_tuple(struct seq_file *s,
 }
 
 /* Print out the private part of the conntrack. */
-static int tcp_print_conntrack(struct seq_file *s, const struct nf_conn *ct)
+static int tcp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
 {
 	enum tcp_conntrack state;
 
-	read_lock_bh(&tcp_lock);
+	spin_lock_bh(&ct->lock);
 	state = ct->proto.tcp.state;
-	read_unlock_bh(&tcp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	return seq_printf(s, "%s ", tcp_conntrack_names[state]);
 }
@@ -521,13 +531,14 @@ static bool tcp_in_window(const struct nf_conn *ct,
 		 receiver->td_end, receiver->td_maxend, receiver->td_maxwin,
 		 receiver->td_scale);
 
-	if (sender->td_end == 0) {
+	if (sender->td_maxwin == 0) {
 		/*
 		 * Initialize sender data.
 		 */
-		if (tcph->syn && tcph->ack) {
+		if (tcph->syn) {
 			/*
-			 * Outgoing SYN-ACK in reply to a SYN.
+			 * SYN-ACK in reply to a SYN
+			 * or SYN from reply direction in simultaneous open.
 			 */
 			sender->td_end =
 			sender->td_maxend = end;
@@ -543,6 +554,9 @@ static bool tcp_in_window(const struct nf_conn *ct,
 			      && receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE))
 				sender->td_scale =
 				receiver->td_scale = 0;
+			if (!tcph->ack)
+				/* Simultaneous open */
+				return true;
 		} else {
 			/*
 			 * We are in the middle of a connection,
@@ -716,14 +730,14 @@ void nf_conntrack_tcp_update(const struct sk_buff *skb,
 
 	end = segment_seq_plus_len(ntohl(tcph->seq), skb->len, dataoff, tcph);
 
-	write_lock_bh(&tcp_lock);
+	spin_lock_bh(&ct->lock);
 	/*
 	 * We have to worry for the ack in the reply packet only...
 	 */
 	if (after(end, ct->proto.tcp.seen[dir].td_end))
 		ct->proto.tcp.seen[dir].td_end = end;
 	ct->proto.tcp.last_end = end;
-	write_unlock_bh(&tcp_lock);
+	spin_unlock_bh(&ct->lock);
 	pr_debug("tcp_update: sender end=%u maxend=%u maxwin=%u scale=%i "
 		 "receiver end=%u maxend=%u maxwin=%u scale=%i\n",
 		 sender->td_end, sender->td_maxend, sender->td_maxwin,
@@ -832,7 +846,7 @@ static int tcp_packet(struct nf_conn *ct,
 	th = skb_header_pointer(skb, dataoff, sizeof(_tcph), &_tcph);
 	BUG_ON(th == NULL);
 
-	write_lock_bh(&tcp_lock);
+	spin_lock_bh(&ct->lock);
 	old_state = ct->proto.tcp.state;
 	dir = CTINFO2DIR(ctinfo);
 	index = get_conntrack_index(th);
@@ -862,7 +876,7 @@ static int tcp_packet(struct nf_conn *ct,
 		        && ct->proto.tcp.last_index == TCP_RST_SET)) {
 			/* Attempt to reopen a closed/aborted connection.
 			 * Delete this connection and look up again. */
-			write_unlock_bh(&tcp_lock);
+			spin_unlock_bh(&ct->lock);
 
 			/* Only repeat if we can actually remove the timer.
 			 * Destruction may already be in progress in process
@@ -898,7 +912,7 @@ static int tcp_packet(struct nf_conn *ct,
 			 * that the client cannot but retransmit its SYN and
 			 * thus initiate a clean new session.
 			 */
-			write_unlock_bh(&tcp_lock);
+			spin_unlock_bh(&ct->lock);
 			if (LOG_INVALID(net, IPPROTO_TCP))
 				nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
 					  "nf_ct_tcp: killing out of sync session ");
@@ -911,7 +925,7 @@ static int tcp_packet(struct nf_conn *ct,
 		ct->proto.tcp.last_end =
 		    segment_seq_plus_len(ntohl(th->seq), skb->len, dataoff, th);
 
-		write_unlock_bh(&tcp_lock);
+		spin_unlock_bh(&ct->lock);
 		if (LOG_INVALID(net, IPPROTO_TCP))
 			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
 				  "nf_ct_tcp: invalid packet ignored ");
@@ -920,7 +934,7 @@ static int tcp_packet(struct nf_conn *ct,
 		/* Invalid packet */
 		pr_debug("nf_ct_tcp: Invalid dir=%i index=%u ostate=%u\n",
 			 dir, get_conntrack_index(th), old_state);
-		write_unlock_bh(&tcp_lock);
+		spin_unlock_bh(&ct->lock);
 		if (LOG_INVALID(net, IPPROTO_TCP))
 			nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
 				  "nf_ct_tcp: invalid state ");
@@ -930,7 +944,7 @@ static int tcp_packet(struct nf_conn *ct,
 		    && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET)
 		    && before(ntohl(th->seq), ct->proto.tcp.seen[!dir].td_maxack)) {
 			/* Invalid RST  */
-			write_unlock_bh(&tcp_lock);
+			spin_unlock_bh(&ct->lock);
 			if (LOG_INVALID(net, IPPROTO_TCP))
 				nf_log_packet(pf, 0, skb, NULL, NULL, NULL,
 					  "nf_ct_tcp: invalid RST ");
@@ -961,7 +975,7 @@ static int tcp_packet(struct nf_conn *ct,
 
 	if (!tcp_in_window(ct, &ct->proto.tcp, dir, index,
 			   skb, dataoff, th, pf)) {
-		write_unlock_bh(&tcp_lock);
+		spin_unlock_bh(&ct->lock);
 		return -NF_ACCEPT;
 	}
      in_window:
@@ -990,9 +1004,8 @@ static int tcp_packet(struct nf_conn *ct,
 		timeout = nf_ct_tcp_timeout_unacknowledged;
 	else
 		timeout = tcp_timeouts[new_state];
-	write_unlock_bh(&tcp_lock);
+	spin_unlock_bh(&ct->lock);
 
-	nf_conntrack_event_cache(IPCT_PROTOINFO_VOLATILE, ct);
 	if (new_state != old_state)
 		nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
 
@@ -1086,7 +1099,7 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 
 	ct->proto.tcp.seen[1].td_end = 0;
 	ct->proto.tcp.seen[1].td_maxend = 0;
-	ct->proto.tcp.seen[1].td_maxwin = 1;
+	ct->proto.tcp.seen[1].td_maxwin = 0;
 	ct->proto.tcp.seen[1].td_scale = 0;
 
 	/* tcp_packet will set them */
@@ -1108,12 +1121,12 @@ static bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb,
 #include <linux/netfilter/nfnetlink_conntrack.h>
 
 static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
-			 const struct nf_conn *ct)
+			 struct nf_conn *ct)
 {
 	struct nlattr *nest_parms;
 	struct nf_ct_tcp_flags tmp = {};
 
-	read_lock_bh(&tcp_lock);
+	spin_lock_bh(&ct->lock);
 	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_TCP | NLA_F_NESTED);
 	if (!nest_parms)
 		goto nla_put_failure;
@@ -1133,14 +1146,14 @@ static int tcp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
 	tmp.flags = ct->proto.tcp.seen[1].flags;
 	NLA_PUT(skb, CTA_PROTOINFO_TCP_FLAGS_REPLY,
 		sizeof(struct nf_ct_tcp_flags), &tmp);
-	read_unlock_bh(&tcp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	nla_nest_end(skb, nest_parms);
 
 	return 0;
 
 nla_put_failure:
-	read_unlock_bh(&tcp_lock);
+	spin_unlock_bh(&ct->lock);
 	return -1;
 }
 
@@ -1171,7 +1184,7 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
 	    nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]) >= TCP_CONNTRACK_MAX)
 		return -EINVAL;
 
-	write_lock_bh(&tcp_lock);
+	spin_lock_bh(&ct->lock);
 	if (tb[CTA_PROTOINFO_TCP_STATE])
 		ct->proto.tcp.state = nla_get_u8(tb[CTA_PROTOINFO_TCP_STATE]);
 
@@ -1198,7 +1211,7 @@ static int nlattr_to_tcp(struct nlattr *cda[], struct nf_conn *ct)
 		ct->proto.tcp.seen[1].td_scale =
 			nla_get_u8(tb[CTA_PROTOINFO_TCP_WSCALE_REPLY]);
 	}
-	write_unlock_bh(&tcp_lock);
+	spin_unlock_bh(&ct->lock);
 
 	return 0;
 }
@@ -1327,6 +1340,13 @@ static struct ctl_table tcp_compat_sysctl_table[] = {
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
 	},
+	{
+		.procname	= "ip_conntrack_tcp_timeout_syn_sent2",
+		.data		= &tcp_timeouts[TCP_CONNTRACK_SYN_SENT2],
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
 	{
 		.procname	= "ip_conntrack_tcp_timeout_syn_recv",
 		.data		= &tcp_timeouts[TCP_CONNTRACK_SYN_RECV],

net/netfilter/nf_queue.c

@@ -204,10 +204,10 @@ int nf_queue(struct sk_buff *skb,
 				  queuenum);
 
 	switch (pf) {
-	case AF_INET:
+	case NFPROTO_IPV4:
 		skb->protocol = htons(ETH_P_IP);
 		break;
-	case AF_INET6:
+	case NFPROTO_IPV6:
 		skb->protocol = htons(ETH_P_IPV6);
 		break;
 	}

net/netfilter/nfnetlink.c

@@ -107,9 +107,10 @@ int nfnetlink_has_listeners(unsigned int group)
 }
 EXPORT_SYMBOL_GPL(nfnetlink_has_listeners);
 
-int nfnetlink_send(struct sk_buff *skb, u32 pid, unsigned group, int echo)
+int nfnetlink_send(struct sk_buff *skb, u32 pid,
+		   unsigned group, int echo, gfp_t flags)
 {
-	return nlmsg_notify(nfnl, skb, pid, group, echo, gfp_any());
+	return nlmsg_notify(nfnl, skb, pid, group, echo, flags);
 }
 EXPORT_SYMBOL_GPL(nfnetlink_send);
 
@@ -136,7 +137,7 @@ static int nfnetlink_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
 		return -EPERM;
 
 	/* All the messages must at least contain nfgenmsg */
-	if (nlh->nlmsg_len < NLMSG_SPACE(sizeof(struct nfgenmsg)))
+	if (nlh->nlmsg_len < NLMSG_LENGTH(sizeof(struct nfgenmsg)))
 		return 0;
 
 	type = nlh->nlmsg_type;
@@ -160,19 +161,14 @@ replay:
 	{
 		int min_len = NLMSG_SPACE(sizeof(struct nfgenmsg));
 		u_int8_t cb_id = NFNL_MSG_TYPE(nlh->nlmsg_type);
-		u_int16_t attr_count = ss->cb[cb_id].attr_count;
-		struct nlattr *cda[attr_count+1];
-
-		if (likely(nlh->nlmsg_len >= min_len)) {
-			struct nlattr *attr = (void *)nlh + NLMSG_ALIGN(min_len);
-			int attrlen = nlh->nlmsg_len - NLMSG_ALIGN(min_len);
-
-			err = nla_parse(cda, attr_count, attr, attrlen,
-					ss->cb[cb_id].policy);
-			if (err < 0)
-				return err;
-		} else
-			return -EINVAL;
+		struct nlattr *cda[ss->cb[cb_id].attr_count + 1];
+		struct nlattr *attr = (void *)nlh + min_len;
+		int attrlen = nlh->nlmsg_len - min_len;
+
+		err = nla_parse(cda, ss->cb[cb_id].attr_count,
+				attr, attrlen, ss->cb[cb_id].policy);
+		if (err < 0)
+			return err;
 
 		err = nc->call(nfnl, skb, nlh, cda);
 		if (err == -EAGAIN)

net/netfilter/x_tables.c

@@ -329,6 +329,32 @@ int xt_find_revision(u8 af, const char *name, u8 revision, int target,
 }
 EXPORT_SYMBOL_GPL(xt_find_revision);
 
+static char *textify_hooks(char *buf, size_t size, unsigned int mask)
+{
+	static const char *const names[] = {
+		"PREROUTING", "INPUT", "FORWARD",
+		"OUTPUT", "POSTROUTING", "BROUTING",
+	};
+	unsigned int i;
+	char *p = buf;
+	bool np = false;
+	int res;
+
+	*p = '\0';
+	for (i = 0; i < ARRAY_SIZE(names); ++i) {
+		if (!(mask & (1 << i)))
+			continue;
+		res = snprintf(p, size, "%s%s", np ? "/" : "", names[i]);
+		if (res > 0) {
+			size -= res;
+			p += res;
+		}
+		np = true;
+	}
+
+	return buf;
+}
+
 int xt_check_match(struct xt_mtchk_param *par,
 		   unsigned int size, u_int8_t proto, bool inv_proto)
 {
@@ -351,9 +377,13 @@ int xt_check_match(struct xt_mtchk_param *par,
 		return -EINVAL;
 	}
 	if (par->match->hooks && (par->hook_mask & ~par->match->hooks) != 0) {
-		printk("%s_tables: %s match: bad hook_mask %#x/%#x\n",
+		char used[64], allow[64];
+
+		printk("%s_tables: %s match: used from hooks %s, but only "
+		       "valid from %s\n",
 		       xt_prefix[par->family], par->match->name,
-		       par->hook_mask, par->match->hooks);
+		       textify_hooks(used, sizeof(used), par->hook_mask),
+		       textify_hooks(allow, sizeof(allow), par->match->hooks));
 		return -EINVAL;
 	}
 	if (par->match->proto && (par->match->proto != proto || inv_proto)) {
@@ -497,9 +527,13 @@ int xt_check_target(struct xt_tgchk_param *par,
 		return -EINVAL;
 	}
 	if (par->target->hooks && (par->hook_mask & ~par->target->hooks) != 0) {
-		printk("%s_tables: %s target: bad hook_mask %#x/%#x\n",
+		char used[64], allow[64];
+
+		printk("%s_tables: %s target: used from hooks %s, but only "
+		       "usable from %s\n",
 		       xt_prefix[par->family], par->target->name,
-		       par->hook_mask, par->target->hooks);
+		       textify_hooks(used, sizeof(used), par->hook_mask),
+		       textify_hooks(allow, sizeof(allow), par->target->hooks));
 		return -EINVAL;
 	}
 	if (par->target->proto && (par->target->proto != proto || inv_proto)) {

net/netfilter/xt_NFQUEUE.c

@@ -11,6 +11,10 @@
 #include <linux/module.h>
 #include <linux/skbuff.h>
 
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/jhash.h>
+
 #include <linux/netfilter.h>
 #include <linux/netfilter_arp.h>
 #include <linux/netfilter/x_tables.h>
@@ -23,6 +27,8 @@ MODULE_ALIAS("ipt_NFQUEUE");
 MODULE_ALIAS("ip6t_NFQUEUE");
 MODULE_ALIAS("arpt_NFQUEUE");
 
+static u32 jhash_initval __read_mostly;
+
 static unsigned int
 nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par)
 {
@@ -31,32 +37,105 @@ nfqueue_tg(struct sk_buff *skb, const struct xt_target_param *par)
 	return NF_QUEUE_NR(tinfo->queuenum);
 }
 
+static u32 hash_v4(const struct sk_buff *skb)
+{
+	const struct iphdr *iph = ip_hdr(skb);
+	u32 ipaddr;
+
+	/* packets in either direction go into same queue */
+	ipaddr = iph->saddr ^ iph->daddr;
+
+	return jhash_2words(ipaddr, iph->protocol, jhash_initval);
+}
+
+static unsigned int
+nfqueue_tg4_v1(struct sk_buff *skb, const struct xt_target_param *par)
+{
+	const struct xt_NFQ_info_v1 *info = par->targinfo;
+	u32 queue = info->queuenum;
+
+	if (info->queues_total > 1)
+		queue = hash_v4(skb) % info->queues_total + queue;
+	return NF_QUEUE_NR(queue);
+}
+
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
+static u32 hash_v6(const struct sk_buff *skb)
+{
+	const struct ipv6hdr *ip6h = ipv6_hdr(skb);
+	u32 addr[4];
+
+	addr[0] = ip6h->saddr.s6_addr32[0] ^ ip6h->daddr.s6_addr32[0];
+	addr[1] = ip6h->saddr.s6_addr32[1] ^ ip6h->daddr.s6_addr32[1];
+	addr[2] = ip6h->saddr.s6_addr32[2] ^ ip6h->daddr.s6_addr32[2];
+	addr[3] = ip6h->saddr.s6_addr32[3] ^ ip6h->daddr.s6_addr32[3];
+
+	return jhash2(addr, ARRAY_SIZE(addr), jhash_initval);
+}
+
+static unsigned int
+nfqueue_tg6_v1(struct sk_buff *skb, const struct xt_target_param *par)
+{
+	const struct xt_NFQ_info_v1 *info = par->targinfo;
+	u32 queue = info->queuenum;
+
+	if (info->queues_total > 1)
+		queue = hash_v6(skb) % info->queues_total + queue;
+	return NF_QUEUE_NR(queue);
+}
+#endif
+
+static bool nfqueue_tg_v1_check(const struct xt_tgchk_param *par)
+{
+	const struct xt_NFQ_info_v1 *info = par->targinfo;
+	u32 maxid;
+
+	if (info->queues_total == 0) {
+		pr_err("NFQUEUE: number of total queues is 0\n");
+		return false;
+	}
+	maxid = info->queues_total - 1 + info->queuenum;
+	if (maxid > 0xffff) {
+		pr_err("NFQUEUE: number of queues (%u) out of range (got %u)\n",
+		       info->queues_total, maxid);
+		return false;
+	}
+	return true;
+}
+
 static struct xt_target nfqueue_tg_reg[] __read_mostly = {
 	{
 		.name		= "NFQUEUE",
-		.family		= NFPROTO_IPV4,
+		.family		= NFPROTO_UNSPEC,
 		.target		= nfqueue_tg,
 		.targetsize	= sizeof(struct xt_NFQ_info),
 		.me		= THIS_MODULE,
 	},
 	{
 		.name		= "NFQUEUE",
-		.family		= NFPROTO_IPV6,
-		.target		= nfqueue_tg,
-		.targetsize	= sizeof(struct xt_NFQ_info),
+		.revision	= 1,
+		.family		= NFPROTO_IPV4,
+		.checkentry	= nfqueue_tg_v1_check,
+		.target		= nfqueue_tg4_v1,
+		.targetsize	= sizeof(struct xt_NFQ_info_v1),
 		.me		= THIS_MODULE,
 	},
+#if defined(CONFIG_IP6_NF_IPTABLES) || defined(CONFIG_IP6_NF_IPTABLES_MODULE)
 	{
 		.name		= "NFQUEUE",
-		.family		= NFPROTO_ARP,
-		.target		= nfqueue_tg,
-		.targetsize	= sizeof(struct xt_NFQ_info),
+		.revision	= 1,
+		.family		= NFPROTO_IPV6,
+		.checkentry	= nfqueue_tg_v1_check,
+		.target		= nfqueue_tg6_v1,
+		.targetsize	= sizeof(struct xt_NFQ_info_v1),
 		.me		= THIS_MODULE,
 	},
+#endif
 };
 
 static int __init nfqueue_tg_init(void)
 {
+	get_random_bytes(&jhash_initval, sizeof(jhash_initval));
 	return xt_register_targets(nfqueue_tg_reg, ARRAY_SIZE(nfqueue_tg_reg));
 }
 

net/netfilter/xt_osf.c

@@ -0,0 +1,428 @@
+/*
+ * Copyright (c) 2003+ Evgeniy Polyakov <zbr@ioremap.net>
+ *
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+
+#include <linux/if.h>
+#include <linux/inetdevice.h>
+#include <linux/ip.h>
+#include <linux/list.h>
+#include <linux/rculist.h>
+#include <linux/skbuff.h>
+#include <linux/slab.h>
+#include <linux/tcp.h>
+
+#include <net/ip.h>
+#include <net/tcp.h>
+
+#include <linux/netfilter/nfnetlink.h>
+#include <linux/netfilter/x_tables.h>
+#include <net/netfilter/nf_log.h>
+#include <linux/netfilter/xt_osf.h>
+
+struct xt_osf_finger {
+	struct rcu_head			rcu_head;
+	struct list_head		finger_entry;
+	struct xt_osf_user_finger	finger;
+};
+
+enum osf_fmatch_states {
+	/* Packet does not match the fingerprint */
+	FMATCH_WRONG = 0,
+	/* Packet matches the fingerprint */
+	FMATCH_OK,
+	/* Options do not match the fingerprint, but header does */
+	FMATCH_OPT_WRONG,
+};
+
+/*
+ * Indexed by dont-fragment bit.
+ * It is the only constant value in the fingerprint.
+ */
+static struct list_head xt_osf_fingers[2];
+
+static const struct nla_policy xt_osf_policy[OSF_ATTR_MAX + 1] = {
+	[OSF_ATTR_FINGER]	= { .len = sizeof(struct xt_osf_user_finger) },
+};
+
+static void xt_osf_finger_free_rcu(struct rcu_head *rcu_head)
+{
+	struct xt_osf_finger *f = container_of(rcu_head, struct xt_osf_finger, rcu_head);
+
+	kfree(f);
+}
+
+static int xt_osf_add_callback(struct sock *ctnl, struct sk_buff *skb,
+			struct nlmsghdr *nlh, struct nlattr *osf_attrs[])
+{
+	struct xt_osf_user_finger *f;
+	struct xt_osf_finger *kf = NULL, *sf;
+	int err = 0;
+
+	if (!osf_attrs[OSF_ATTR_FINGER])
+		return -EINVAL;
+
+	if (!(nlh->nlmsg_flags & NLM_F_CREATE))
+		return -EINVAL;
+
+	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
+
+	kf = kmalloc(sizeof(struct xt_osf_finger), GFP_KERNEL);
+	if (!kf)
+		return -ENOMEM;
+
+	memcpy(&kf->finger, f, sizeof(struct xt_osf_user_finger));
+
+	list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) {
+		if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger)))
+			continue;
+
+		kfree(kf);
+		kf = NULL;
+
+		if (nlh->nlmsg_flags & NLM_F_EXCL)
+			err = -EEXIST;
+		break;
+	}
+
+	/*
+	 * We are protected by nfnl mutex.
+	 */
+	if (kf)
+		list_add_tail_rcu(&kf->finger_entry, &xt_osf_fingers[!!f->df]);
+
+	return err;
+}
+
+static int xt_osf_remove_callback(struct sock *ctnl, struct sk_buff *skb,
+			struct nlmsghdr *nlh, struct nlattr *osf_attrs[])
+{
+	struct xt_osf_user_finger *f;
+	struct xt_osf_finger *sf;
+	int err = ENOENT;
+
+	if (!osf_attrs[OSF_ATTR_FINGER])
+		return -EINVAL;
+
+	f = nla_data(osf_attrs[OSF_ATTR_FINGER]);
+
+	list_for_each_entry(sf, &xt_osf_fingers[!!f->df], finger_entry) {
+		if (memcmp(&sf->finger, f, sizeof(struct xt_osf_user_finger)))
+			continue;
+
+		/*
+		 * We are protected by nfnl mutex.
+		 */
+		list_del_rcu(&sf->finger_entry);
+		call_rcu(&sf->rcu_head, xt_osf_finger_free_rcu);
+
+		err = 0;
+		break;
+	}
+
+	return err;
+}
+
+static const struct nfnl_callback xt_osf_nfnetlink_callbacks[OSF_MSG_MAX] = {
+	[OSF_MSG_ADD]	= {
+		.call		= xt_osf_add_callback,
+		.attr_count	= OSF_ATTR_MAX,
+		.policy		= xt_osf_policy,
+	},
+	[OSF_MSG_REMOVE]	= {
+		.call		= xt_osf_remove_callback,
+		.attr_count	= OSF_ATTR_MAX,
+		.policy		= xt_osf_policy,
+	},
+};
+
+static const struct nfnetlink_subsystem xt_osf_nfnetlink = {
+	.name			= "osf",
+	.subsys_id		= NFNL_SUBSYS_OSF,
+	.cb_count		= OSF_MSG_MAX,
+	.cb			= xt_osf_nfnetlink_callbacks,
+};
+
+static inline int xt_osf_ttl(const struct sk_buff *skb, const struct xt_osf_info *info,
+			    unsigned char f_ttl)
+{
+	const struct iphdr *ip = ip_hdr(skb);
+
+	if (info->flags & XT_OSF_TTL) {
+		if (info->ttl == XT_OSF_TTL_TRUE)
+			return ip->ttl == f_ttl;
+		if (info->ttl == XT_OSF_TTL_NOCHECK)
+			return 1;
+		else if (ip->ttl <= f_ttl)
+			return 1;
+		else {
+			struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+			int ret = 0;
+
+			for_ifa(in_dev) {
+				if (inet_ifa_match(ip->saddr, ifa)) {
+					ret = (ip->ttl == f_ttl);
+					break;
+				}
+			}
+			endfor_ifa(in_dev);
+
+			return ret;
+		}
+	}
+
+	return ip->ttl == f_ttl;
+}
+
+static bool xt_osf_match_packet(const struct sk_buff *skb,
+		const struct xt_match_param *p)
+{
+	const struct xt_osf_info *info = p->matchinfo;
+	const struct iphdr *ip = ip_hdr(skb);
+	const struct tcphdr *tcp;
+	struct tcphdr _tcph;
+	int fmatch = FMATCH_WRONG, fcount = 0;
+	unsigned int optsize = 0, check_WSS = 0;
+	u16 window, totlen, mss = 0;
+	bool df;
+	const unsigned char *optp = NULL, *_optp = NULL;
+	unsigned char opts[MAX_IPOPTLEN];
+	const struct xt_osf_finger *kf;
+	const struct xt_osf_user_finger *f;
+
+	if (!info)
+		return false;
+
+	tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph);
+	if (!tcp)
+		return false;
+
+	if (!tcp->syn)
+		return false;
+
+	totlen = ntohs(ip->tot_len);
+	df = ntohs(ip->frag_off) & IP_DF;
+	window = ntohs(tcp->window);
+
+	if (tcp->doff * 4 > sizeof(struct tcphdr)) {
+		optsize = tcp->doff * 4 - sizeof(struct tcphdr);
+
+		_optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) +
+				sizeof(struct tcphdr), optsize, opts);
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) {
+		f = &kf->finger;
+
+		if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre))
+			continue;
+
+		optp = _optp;
+		fmatch = FMATCH_WRONG;
+
+		if (totlen == f->ss && xt_osf_ttl(skb, info, f->ttl)) {
+			int foptsize, optnum;
+
+			/*
+			 * Should not happen if userspace parser was written correctly.
+			 */
+			if (f->wss.wc >= OSF_WSS_MAX)
+				continue;
+
+			/* Check options */
+
+			foptsize = 0;
+			for (optnum = 0; optnum < f->opt_num; ++optnum)
+				foptsize += f->opt[optnum].length;
+
+			if (foptsize > MAX_IPOPTLEN ||
+				optsize > MAX_IPOPTLEN ||
+				optsize != foptsize)
+				continue;
+
+			check_WSS = f->wss.wc;
+
+			for (optnum = 0; optnum < f->opt_num; ++optnum) {
+				if (f->opt[optnum].kind == (*optp)) {
+					__u32 len = f->opt[optnum].length;
+					const __u8 *optend = optp + len;
+					int loop_cont = 0;
+
+					fmatch = FMATCH_OK;
+
+					switch (*optp) {
+					case OSFOPT_MSS:
+						mss = optp[3];
+						mss <<= 8;
+						mss |= optp[2];
+
+						mss = ntohs(mss);
+						break;
+					case OSFOPT_TS:
+						loop_cont = 1;
+						break;
+					}
+
+					optp = optend;
+				} else
+					fmatch = FMATCH_OPT_WRONG;
+
+				if (fmatch != FMATCH_OK)
+					break;
+			}
+
+			if (fmatch != FMATCH_OPT_WRONG) {
+				fmatch = FMATCH_WRONG;
+
+				switch (check_WSS) {
+				case OSF_WSS_PLAIN:
+					if (f->wss.val == 0 || window == f->wss.val)
+						fmatch = FMATCH_OK;
+					break;
+				case OSF_WSS_MSS:
+					/*
+					 * Some smart modems decrease mangle MSS to 
+					 * SMART_MSS_2, so we check standard, decreased
+					 * and the one provided in the fingerprint MSS
+					 * values.
+					 */
+#define SMART_MSS_1	1460
+#define SMART_MSS_2	1448
+					if (window == f->wss.val * mss ||
+					    window == f->wss.val * SMART_MSS_1 ||
+					    window == f->wss.val * SMART_MSS_2)
+						fmatch = FMATCH_OK;
+					break;
+				case OSF_WSS_MTU:
+					if (window == f->wss.val * (mss + 40) ||
+					    window == f->wss.val * (SMART_MSS_1 + 40) ||
+					    window == f->wss.val * (SMART_MSS_2 + 40))
+						fmatch = FMATCH_OK;
+					break;
+				case OSF_WSS_MODULO:
+					if ((window % f->wss.val) == 0)
+						fmatch = FMATCH_OK;
+					break;
+				}
+			}
+
+			if (fmatch != FMATCH_OK)
+				continue;
+
+			fcount++;
+
+			if (info->flags & XT_OSF_LOG)
+				nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+					"%s [%s:%s] : %pi4:%d -> %pi4:%d hops=%d\n",
+					f->genre, f->version, f->subtype,
+					&ip->saddr, ntohs(tcp->source),
+					&ip->daddr, ntohs(tcp->dest),
+					f->ttl - ip->ttl);
+
+			if ((info->flags & XT_OSF_LOG) &&
+			    info->loglevel == XT_OSF_LOGLEVEL_FIRST)
+				break;
+		}
+	}
+	rcu_read_unlock();
+
+	if (!fcount && (info->flags & XT_OSF_LOG))
+		nf_log_packet(p->hooknum, 0, skb, p->in, p->out, NULL,
+			"Remote OS is not known: %pi4:%u -> %pi4:%u\n",
+				&ip->saddr, ntohs(tcp->source),
+				&ip->daddr, ntohs(tcp->dest));
+
+	if (fcount)
+		fmatch = FMATCH_OK;
+
+	return fmatch == FMATCH_OK;
+}
+
+static struct xt_match xt_osf_match = {
+	.name 		= "osf",
+	.revision	= 0,
+	.family		= NFPROTO_IPV4,
+	.proto		= IPPROTO_TCP,
+	.hooks      	= (1 << NF_INET_LOCAL_IN) |
+				(1 << NF_INET_PRE_ROUTING) |
+				(1 << NF_INET_FORWARD),
+	.match 		= xt_osf_match_packet,
+	.matchsize	= sizeof(struct xt_osf_info),
+	.me		= THIS_MODULE,
+};
+
+static int __init xt_osf_init(void)
+{
+	int err = -EINVAL;
+	int i;
+
+	for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i)
+		INIT_LIST_HEAD(&xt_osf_fingers[i]);
+
+	err = nfnetlink_subsys_register(&xt_osf_nfnetlink);
+	if (err < 0) {
+		printk(KERN_ERR "Failed (%d) to register OSF nsfnetlink helper.\n", err);
+		goto err_out_exit;
+	}
+
+	err = xt_register_match(&xt_osf_match);
+	if (err) {
+		printk(KERN_ERR "Failed (%d) to register OS fingerprint "
+				"matching module.\n", err);
+		goto err_out_remove;
+	}
+
+	return 0;
+
+err_out_remove:
+	nfnetlink_subsys_unregister(&xt_osf_nfnetlink);
+err_out_exit:
+	return err;
+}
+
+static void __exit xt_osf_fini(void)
+{
+	struct xt_osf_finger *f;
+	int i;
+
+	nfnetlink_subsys_unregister(&xt_osf_nfnetlink);
+	xt_unregister_match(&xt_osf_match);
+
+	rcu_read_lock();
+	for (i=0; i<ARRAY_SIZE(xt_osf_fingers); ++i) {
+
+		list_for_each_entry_rcu(f, &xt_osf_fingers[i], finger_entry) {
+			list_del_rcu(&f->finger_entry);
+			call_rcu(&f->rcu_head, xt_osf_finger_free_rcu);
+		}
+	}
+	rcu_read_unlock();
+
+	rcu_barrier();
+}
+
+module_init(xt_osf_init);
+module_exit(xt_osf_fini);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Evgeniy Polyakov <zbr@ioremap.net>");
+MODULE_DESCRIPTION("Passive OS fingerprint matching.");
+MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_OSF);

net/netfilter/xt_socket.c

@@ -22,6 +22,8 @@
 #include <net/netfilter/nf_tproxy_core.h>
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
 
+#include <linux/netfilter/xt_socket.h>
+
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
 #define XT_SOCKET_HAVE_CONNTRACK 1
 #include <net/netfilter/nf_conntrack.h>
@@ -86,7 +88,8 @@ extract_icmp_fields(const struct sk_buff *skb,
 
 
 static bool
-socket_mt(const struct sk_buff *skb, const struct xt_match_param *par)
+socket_match(const struct sk_buff *skb, const struct xt_match_param *par,
+	     const struct xt_socket_mtinfo1 *info)
 {
 	const struct iphdr *iph = ip_hdr(skb);
 	struct udphdr _hdr, *hp = NULL;
@@ -141,10 +144,24 @@ socket_mt(const struct sk_buff *skb, const struct xt_match_param *par)
 	sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol,
 				   saddr, daddr, sport, dport, par->in, false);
 	if (sk != NULL) {
-		bool wildcard = (sk->sk_state != TCP_TIME_WAIT && inet_sk(sk)->rcv_saddr == 0);
+		bool wildcard;
+		bool transparent = true;
+
+		/* Ignore sockets listening on INADDR_ANY */
+		wildcard = (sk->sk_state != TCP_TIME_WAIT &&
+			    inet_sk(sk)->rcv_saddr == 0);
+
+		/* Ignore non-transparent sockets,
+		   if XT_SOCKET_TRANSPARENT is used */
+		if (info && info->flags & XT_SOCKET_TRANSPARENT)
+			transparent = ((sk->sk_state != TCP_TIME_WAIT &&
+					inet_sk(sk)->transparent) ||
+				       (sk->sk_state == TCP_TIME_WAIT &&
+					inet_twsk(sk)->tw_transparent));
 
 		nf_tproxy_put_sock(sk);
-		if (wildcard)
+
+		if (wildcard || !transparent)
 			sk = NULL;
 	}
 
@@ -157,23 +174,47 @@ socket_mt(const struct sk_buff *skb, const struct xt_match_param *par)
 	return (sk != NULL);
 }
 
-static struct xt_match socket_mt_reg __read_mostly = {
-	.name		= "socket",
-	.family		= AF_INET,
-	.match		= socket_mt,
-	.hooks		= 1 << NF_INET_PRE_ROUTING,
-	.me		= THIS_MODULE,
+static bool
+socket_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+	return socket_match(skb, par, NULL);
+}
+
+static bool
+socket_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par)
+{
+	return socket_match(skb, par, par->matchinfo);
+}
+
+static struct xt_match socket_mt_reg[] __read_mostly = {
+	{
+		.name		= "socket",
+		.revision	= 0,
+		.family		= NFPROTO_IPV4,
+		.match		= socket_mt_v0,
+		.hooks		= 1 << NF_INET_PRE_ROUTING,
+		.me		= THIS_MODULE,
+	},
+	{
+		.name		= "socket",
+		.revision	= 1,
+		.family		= NFPROTO_IPV4,
+		.match		= socket_mt_v1,
+		.matchsize	= sizeof(struct xt_socket_mtinfo1),
+		.hooks		= 1 << NF_INET_PRE_ROUTING,
+		.me		= THIS_MODULE,
+	},
 };
 
 static int __init socket_mt_init(void)
 {
 	nf_defrag_ipv4_enable();
-	return xt_register_match(&socket_mt_reg);
+	return xt_register_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg));
 }
 
 static void __exit socket_mt_exit(void)
 {
-	xt_unregister_match(&socket_mt_reg);
+	xt_unregister_matches(socket_mt_reg, ARRAY_SIZE(socket_mt_reg));
 }
 
 module_init(socket_mt_init);