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

Conflicts:
	net/netfilter/nf_conntrack_proto_tcp.c

The conflict had to do with overlapping changes dealing with
fixing the use of an "s32" to hold the value returned by
NAT_OFFSET().

Pablo Neira Ayuso says:

====================
The following batch contains Netfilter/IPVS updates for your net-next tree.
More specifically, they are:

* Trivial typo fix in xt_addrtype, from Phil Oester.

* Remove net_ratelimit in the conntrack logging for consistency with other
  logging subsystem, from Patrick McHardy.

* Remove unneeded includes from the recently added xt_connlabel support, from
  Florian Westphal.

* Allow to update conntracks via nfqueue, don't need NFQA_CFG_F_CONNTRACK for
  this, from Florian Westphal.

* Remove tproxy core, now that we have socket early demux, from Florian
  Westphal.

* A couple of patches to refactor conntrack event reporting to save a good
  bunch of lines, from Florian Westphal.

* Fix missing locking in NAT sequence adjustment, it did not manifested in
  any known bug so far, from Patrick McHardy.

* Change sequence number adjustment variable to 32 bits, to delay the
  possible early overflow in long standing connections, also from Patrick.

* Comestic cleanups for IPVS, from Dragos Foianu.

* Fix possible null dereference in IPVS in the SH scheduler, from Daniel
  Borkmann.

* Allow to attach conntrack expectations via nfqueue. Before this patch, you
  had to use ctnetlink instead, thus, we save the conntrack lookup.

* Export xt_rpfilter and xt_HMARK header files, from Nicolas Dichtel.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

Documentation/networking/tproxy.txt

@@ -2,9 +2,8 @@ Transparent proxy support
 =========================
 
 This feature adds Linux 2.2-like transparent proxy support to current kernels.
-To use it, enable NETFILTER_TPROXY, the socket match and the TPROXY target in
-your kernel config. You will need policy routing too, so be sure to enable that
-as well.
+To use it, enable the socket match and the TPROXY target in your kernel config.
+You will need policy routing too, so be sure to enable that as well.
 
 
 1. Making non-local sockets work

include/linux/netfilter.h

@@ -314,8 +314,8 @@ nf_nat_decode_session(struct sk_buff *skb, struct flowi *fl, u_int8_t family)
 #endif /*CONFIG_NETFILTER*/
 
 #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE)
-extern void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu;
-extern void nf_ct_attach(struct sk_buff *, struct sk_buff *);
+extern void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu;
+extern void nf_ct_attach(struct sk_buff *, const struct sk_buff *);
 extern void (*nf_ct_destroy)(struct nf_conntrack *) __rcu;
 
 struct nf_conn;
@@ -325,12 +325,14 @@ struct nfq_ct_hook {
 	size_t (*build_size)(const struct nf_conn *ct);
 	int (*build)(struct sk_buff *skb, struct nf_conn *ct);
 	int (*parse)(const struct nlattr *attr, struct nf_conn *ct);
+	int (*attach_expect)(const struct nlattr *attr, struct nf_conn *ct,
+			     u32 portid, u32 report);
 };
 extern struct nfq_ct_hook __rcu *nfq_ct_hook;
 
 struct nfq_ct_nat_hook {
 	void (*seq_adjust)(struct sk_buff *skb, struct nf_conn *ct,
-			   u32 ctinfo, int off);
+			   u32 ctinfo, s32 off);
 };
 extern struct nfq_ct_nat_hook __rcu *nfq_ct_nat_hook;
 #else

include/net/netfilter/nf_conntrack.h

@@ -181,8 +181,7 @@ __nf_conntrack_find(struct net *net, u16 zone,
 		    const struct nf_conntrack_tuple *tuple);
 
 extern int nf_conntrack_hash_check_insert(struct nf_conn *ct);
-extern void nf_ct_delete_from_lists(struct nf_conn *ct);
-extern void nf_ct_dying_timeout(struct nf_conn *ct);
+bool nf_ct_delete(struct nf_conn *ct, u32 pid, int report);
 
 extern void nf_conntrack_flush_report(struct net *net, u32 portid, int report);
 
@@ -235,7 +234,7 @@ static inline bool nf_ct_kill(struct nf_conn *ct)
 }
 
 /* These are for NAT.  Icky. */
-extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
+extern s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 			       enum ip_conntrack_dir dir,
 			       u32 seq);
 
@@ -249,7 +248,9 @@ extern void nf_ct_untracked_status_or(unsigned long bits);
 
 /* Iterate over all conntracks: if iter returns true, it's deleted. */
 extern void
-nf_ct_iterate_cleanup(struct net *net, int (*iter)(struct nf_conn *i, void *data), void *data);
+nf_ct_iterate_cleanup(struct net *net,
+		      int (*iter)(struct nf_conn *i, void *data),
+		      void *data, u32 portid, int report);
 extern void nf_conntrack_free(struct nf_conn *ct);
 extern struct nf_conn *
 nf_conntrack_alloc(struct net *net, u16 zone,

include/net/netfilter/nf_conntrack_l4proto.h

@@ -148,17 +148,10 @@ extern int nf_ct_port_nlattr_tuple_size(void);
 extern const struct nla_policy nf_ct_port_nla_policy[];
 
 #ifdef CONFIG_SYSCTL
-#ifdef DEBUG_INVALID_PACKETS
 #define LOG_INVALID(net, proto)				\
 	((net)->ct.sysctl_log_invalid == (proto) ||	\
 	 (net)->ct.sysctl_log_invalid == IPPROTO_RAW)
 #else
-#define LOG_INVALID(net, proto)				\
-	(((net)->ct.sysctl_log_invalid == (proto) ||	\
-	  (net)->ct.sysctl_log_invalid == IPPROTO_RAW)	\
-	 && net_ratelimit())
-#endif
-#else
 static inline int LOG_INVALID(struct net *net, int proto) { return 0; }
 #endif /* CONFIG_SYSCTL */
 

include/net/netfilter/nf_nat.h

@@ -19,7 +19,7 @@ struct nf_nat_seq {
 	u_int32_t correction_pos;
 
 	/* sequence number offset before and after last modification */
-	int16_t offset_before, offset_after;
+	int32_t offset_before, offset_after;
 };
 
 #include <linux/list.h>

include/net/netfilter/nf_nat_helper.h

@@ -41,7 +41,7 @@ extern int nf_nat_mangle_udp_packet(struct sk_buff *skb,
 
 extern void nf_nat_set_seq_adjust(struct nf_conn *ct,
 				  enum ip_conntrack_info ctinfo,
-				  __be32 seq, s16 off);
+				  __be32 seq, s32 off);
 extern int nf_nat_seq_adjust(struct sk_buff *skb,
 			     struct nf_conn *ct,
 			     enum ip_conntrack_info ctinfo,
@@ -56,11 +56,11 @@ extern int (*nf_nat_seq_adjust_hook)(struct sk_buff *skb,
 extern void nf_nat_follow_master(struct nf_conn *ct,
 				 struct nf_conntrack_expect *this);
 
-extern s16 nf_nat_get_offset(const struct nf_conn *ct,
+extern s32 nf_nat_get_offset(const struct nf_conn *ct,
 			     enum ip_conntrack_dir dir,
 			     u32 seq);
 
 extern void nf_nat_tcp_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
-				  u32 dir, int off);
+				  u32 dir, s32 off);
 
 #endif

include/net/netfilter/nf_tproxy_core.h

-#ifndef _NF_TPROXY_CORE_H
-#define _NF_TPROXY_CORE_H
-
-#include <linux/types.h>
-#include <linux/in.h>
-#include <linux/skbuff.h>
-#include <net/sock.h>
-#include <net/inet_hashtables.h>
-#include <net/inet6_hashtables.h>
-#include <net/tcp.h>
-
-#define NFT_LOOKUP_ANY         0
-#define NFT_LOOKUP_LISTENER    1
-#define NFT_LOOKUP_ESTABLISHED 2
-
-/* look up and get a reference to a matching socket */
-
-
-/* This function is used by the 'TPROXY' target and the 'socket'
- * match. The following lookups are supported:
- *
- * Explicit TProxy target rule
- * ===========================
- *
- * This is used when the user wants to intercept a connection matching
- * an explicit iptables rule. In this case the sockets are assumed
- * matching in preference order:
- *
- *   - match: if there's a fully established connection matching the
- *     _packet_ tuple, it is returned, assuming the redirection
- *     already took place and we process a packet belonging to an
- *     established connection
- *
- *   - match: if there's a listening socket matching the redirection
- *     (e.g. on-port & on-ip of the connection), it is returned,
- *     regardless if it was bound to 0.0.0.0 or an explicit
- *     address. The reasoning is that if there's an explicit rule, it
- *     does not really matter if the listener is bound to an interface
- *     or to 0. The user already stated that he wants redirection
- *     (since he added the rule).
- *
- * "socket" match based redirection (no specific rule)
- * ===================================================
- *
- * There are connections with dynamic endpoints (e.g. FTP data
- * connection) that the user is unable to add explicit rules
- * for. These are taken care of by a generic "socket" rule. It is
- * assumed that the proxy application is trusted to open such
- * connections without explicit iptables rule (except of course the
- * generic 'socket' rule). In this case the following sockets are
- * matched in preference order:
- *
- *   - match: if there's a fully established connection matching the
- *     _packet_ tuple
- *
- *   - match: if there's a non-zero bound listener (possibly with a
- *     non-local address) We don't accept zero-bound listeners, since
- *     then local services could intercept traffic going through the
- *     box.
- *
- * Please note that there's an overlap between what a TPROXY target
- * and a socket match will match. Normally if you have both rules the
- * "socket" match will be the first one, effectively all packets
- * belonging to established connections going through that one.
- */
-static inline struct sock *
-nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
-		      const __be32 saddr, const __be32 daddr,
-		      const __be16 sport, const __be16 dport,
-		      const struct net_device *in, int lookup_type)
-{
-	struct sock *sk;
-
-	/* look up socket */
-	switch (protocol) {
-	case IPPROTO_TCP:
-		switch (lookup_type) {
-		case NFT_LOOKUP_ANY:
-			sk = __inet_lookup(net, &tcp_hashinfo,
-					   saddr, sport, daddr, dport,
-					   in->ifindex);
-			break;
-		case NFT_LOOKUP_LISTENER:
-			sk = inet_lookup_listener(net, &tcp_hashinfo,
-						    saddr, sport,
-						    daddr, dport,
-						    in->ifindex);
-
-			/* NOTE: we return listeners even if bound to
-			 * 0.0.0.0, those are filtered out in
-			 * xt_socket, since xt_TPROXY needs 0 bound
-			 * listeners too */
-
-			break;
-		case NFT_LOOKUP_ESTABLISHED:
-			sk = inet_lookup_established(net, &tcp_hashinfo,
-						    saddr, sport, daddr, dport,
-						    in->ifindex);
-			break;
-		default:
-			WARN_ON(1);
-			sk = NULL;
-			break;
-		}
-		break;
-	case IPPROTO_UDP:
-		sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
-				     in->ifindex);
-		if (sk && lookup_type != NFT_LOOKUP_ANY) {
-			int connected = (sk->sk_state == TCP_ESTABLISHED);
-			int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);
-
-			/* NOTE: we return listeners even if bound to
-			 * 0.0.0.0, those are filtered out in
-			 * xt_socket, since xt_TPROXY needs 0 bound
-			 * listeners too */
-			if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
-			    (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
-				sock_put(sk);
-				sk = NULL;
-			}
-		}
-		break;
-	default:
-		WARN_ON(1);
-		sk = NULL;
-	}
-
-	pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
-		 protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);
-
-	return sk;
-}
-
-#if IS_ENABLED(CONFIG_IPV6)
-static inline struct sock *
-nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
-		      const struct in6_addr *saddr, const struct in6_addr *daddr,
-		      const __be16 sport, const __be16 dport,
-		      const struct net_device *in, int lookup_type)
-{
-	struct sock *sk;
-
-	/* look up socket */
-	switch (protocol) {
-	case IPPROTO_TCP:
-		switch (lookup_type) {
-		case NFT_LOOKUP_ANY:
-			sk = inet6_lookup(net, &tcp_hashinfo,
-					  saddr, sport, daddr, dport,
-					  in->ifindex);
-			break;
-		case NFT_LOOKUP_LISTENER:
-			sk = inet6_lookup_listener(net, &tcp_hashinfo,
-						   saddr, sport,
-						   daddr, ntohs(dport),
-						   in->ifindex);
-
-			/* NOTE: we return listeners even if bound to
-			 * 0.0.0.0, those are filtered out in
-			 * xt_socket, since xt_TPROXY needs 0 bound
-			 * listeners too */
-
-			break;
-		case NFT_LOOKUP_ESTABLISHED:
-			sk = __inet6_lookup_established(net, &tcp_hashinfo,
-							saddr, sport, daddr, ntohs(dport),
-							in->ifindex);
-			break;
-		default:
-			WARN_ON(1);
-			sk = NULL;
-			break;
-		}
-		break;
-	case IPPROTO_UDP:
-		sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
-				     in->ifindex);
-		if (sk && lookup_type != NFT_LOOKUP_ANY) {
-			int connected = (sk->sk_state == TCP_ESTABLISHED);
-			int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr);
-
-			/* NOTE: we return listeners even if bound to
-			 * 0.0.0.0, those are filtered out in
-			 * xt_socket, since xt_TPROXY needs 0 bound
-			 * listeners too */
-			if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
-			    (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
-				sock_put(sk);
-				sk = NULL;
-			}
-		}
-		break;
-	default:
-		WARN_ON(1);
-		sk = NULL;
-	}
-
-	pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n",
-		 protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk);
-
-	return sk;
-}
-#endif
-
-/* assign a socket to the skb -- consumes sk */
-void
-nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk);
-
-#endif

include/net/netfilter/nfnetlink_queue.h

@@ -15,6 +15,8 @@ int nfqnl_ct_put(struct sk_buff *skb, struct nf_conn *ct,
 		 enum ip_conntrack_info ctinfo);
 void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
 			 enum ip_conntrack_info ctinfo, int diff);
+int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr,
+			u32 portid, u32 report);
 #else
 inline struct nf_conn *
 nfqnl_ct_get(struct sk_buff *entskb, size_t *size, enum ip_conntrack_info *ctinfo)
@@ -39,5 +41,11 @@ inline void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
 				enum ip_conntrack_info ctinfo, int diff)
 {
 }
+
+inline int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr,
+			       u32 portid, u32 report)
+{
+	return 0;
+}
 #endif /* NF_CONNTRACK */
 #endif

include/uapi/linux/netfilter/Kbuild

@@ -22,6 +22,7 @@ header-y += xt_CONNMARK.h
 header-y += xt_CONNSECMARK.h
 header-y += xt_CT.h
 header-y += xt_DSCP.h
+header-y += xt_HMARK.h
 header-y += xt_IDLETIMER.h
 header-y += xt_LED.h
 header-y += xt_LOG.h
@@ -68,6 +69,7 @@ header-y += xt_quota.h
 header-y += xt_rateest.h
 header-y += xt_realm.h
 header-y += xt_recent.h
+header-y += xt_rpfilter.h
 header-y += xt_sctp.h
 header-y += xt_set.h
 header-y += xt_socket.h

include/uapi/linux/netfilter/nfnetlink_queue.h

@@ -46,6 +46,7 @@ enum nfqnl_attr_type {
 	NFQA_CT_INFO,			/* enum ip_conntrack_info */
 	NFQA_CAP_LEN,			/* __u32 length of captured packet */
 	NFQA_SKB_INFO,			/* __u32 skb meta information */
+	NFQA_EXP,			/* nf_conntrack_netlink.h */
 
 	__NFQA_MAX
 };

net/ipv4/netfilter/ipt_MASQUERADE.c

@@ -118,7 +118,7 @@ static int masq_device_event(struct notifier_block *this,
 		NF_CT_ASSERT(dev->ifindex != 0);
 
 		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex);
+				      (void *)(long)dev->ifindex, 0, 0);
 	}
 
 	return NOTIFY_DONE;

net/ipv6/netfilter/ip6t_MASQUERADE.c

@@ -76,7 +76,7 @@ static int masq_device_event(struct notifier_block *this,
 
 	if (event == NETDEV_DOWN)
 		nf_ct_iterate_cleanup(net, device_cmp,
-				      (void *)(long)dev->ifindex);
+				      (void *)(long)dev->ifindex, 0, 0);
 
 	return NOTIFY_DONE;
 }

net/netfilter/Kconfig

@@ -410,20 +410,6 @@ config NF_NAT_TFTP
 
 endif # NF_CONNTRACK
 
-# transparent proxy support
-config NETFILTER_TPROXY
-	tristate "Transparent proxying support"
-	depends on IP_NF_MANGLE
-	depends on NETFILTER_ADVANCED
-	help
-	  This option enables transparent proxying support, that is,
-	  support for handling non-locally bound IPv4 TCP and UDP sockets.
-	  For it to work you will have to configure certain iptables rules
-	  and use policy routing. For more information on how to set it up
-	  see Documentation/networking/tproxy.txt.
-
-	  To compile it as a module, choose M here.  If unsure, say N.
-
 config NETFILTER_XTABLES
 	tristate "Netfilter Xtables support (required for ip_tables)"
 	default m if NETFILTER_ADVANCED=n
@@ -720,10 +706,10 @@ config NETFILTER_XT_TARGET_TEE
 	this clone be rerouted to another nexthop.
 
 config NETFILTER_XT_TARGET_TPROXY
-	tristate '"TPROXY" target support'
-	depends on NETFILTER_TPROXY
+	tristate '"TPROXY" target transparent proxying support'
 	depends on NETFILTER_XTABLES
 	depends on NETFILTER_ADVANCED
+	depends on IP_NF_MANGLE
 	select NF_DEFRAG_IPV4
 	select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES
 	help
@@ -731,6 +717,9 @@ config NETFILTER_XT_TARGET_TPROXY
 	  REDIRECT.  It can only be used in the mangle table and is useful
 	  to redirect traffic to a transparent proxy.  It does _not_ depend
 	  on Netfilter connection tracking and NAT, unlike REDIRECT.
+	  For it to work you will have to configure certain iptables rules
+	  and use policy routing. For more information on how to set it up
+	  see Documentation/networking/tproxy.txt.
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
@@ -1180,7 +1169,6 @@ config NETFILTER_XT_MATCH_SCTP
 
 config NETFILTER_XT_MATCH_SOCKET
 	tristate '"socket" match support'
-	depends on NETFILTER_TPROXY
 	depends on NETFILTER_XTABLES
 	depends on NETFILTER_ADVANCED
 	depends on !NF_CONNTRACK || NF_CONNTRACK

net/netfilter/Makefile

@@ -61,9 +61,6 @@ obj-$(CONFIG_NF_NAT_IRC) += nf_nat_irc.o
 obj-$(CONFIG_NF_NAT_SIP) += nf_nat_sip.o
 obj-$(CONFIG_NF_NAT_TFTP) += nf_nat_tftp.o
 
-# transparent proxy support
-obj-$(CONFIG_NETFILTER_TPROXY) += nf_tproxy_core.o
-
 # generic X tables 
 obj-$(CONFIG_NETFILTER_XTABLES) += x_tables.o xt_tcpudp.o
 

net/netfilter/core.c

@@ -234,12 +234,13 @@ EXPORT_SYMBOL(skb_make_writable);
 /* This does not belong here, but locally generated errors need it if connection
    tracking in use: without this, connection may not be in hash table, and hence
    manufactured ICMP or RST packets will not be associated with it. */
-void (*ip_ct_attach)(struct sk_buff *, struct sk_buff *) __rcu __read_mostly;
+void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *)
+		__rcu __read_mostly;
 EXPORT_SYMBOL(ip_ct_attach);
 
-void nf_ct_attach(struct sk_buff *new, struct sk_buff *skb)
+void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb)
 {
-	void (*attach)(struct sk_buff *, struct sk_buff *);
+	void (*attach)(struct sk_buff *, const struct sk_buff *);
 
 	if (skb->nfct) {
 		rcu_read_lock();

net/netfilter/ipvs/ip_vs_lblcr.c

@@ -414,7 +414,7 @@ static void ip_vs_lblcr_flush(struct ip_vs_service *svc)
 
 	spin_lock_bh(&svc->sched_lock);
 	tbl->dead = 1;
-	for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
+	for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) {
 		hlist_for_each_entry_safe(en, next, &tbl->bucket[i], list) {
 			ip_vs_lblcr_free(en);
 		}
@@ -440,7 +440,7 @@ static inline void ip_vs_lblcr_full_check(struct ip_vs_service *svc)
 	struct ip_vs_lblcr_entry *en;
 	struct hlist_node *next;
 
-	for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
+	for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
 
 		spin_lock(&svc->sched_lock);
@@ -495,7 +495,7 @@ static void ip_vs_lblcr_check_expire(unsigned long data)
 	if (goal > tbl->max_size/2)
 		goal = tbl->max_size/2;
 
-	for (i=0, j=tbl->rover; i<IP_VS_LBLCR_TAB_SIZE; i++) {
+	for (i = 0, j = tbl->rover; i < IP_VS_LBLCR_TAB_SIZE; i++) {
 		j = (j + 1) & IP_VS_LBLCR_TAB_MASK;
 
 		spin_lock(&svc->sched_lock);
@@ -536,7 +536,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc)
 	/*
 	 *    Initialize the hash buckets
 	 */
-	for (i=0; i<IP_VS_LBLCR_TAB_SIZE; i++) {
+	for (i = 0; i < IP_VS_LBLCR_TAB_SIZE; i++) {
 		INIT_HLIST_HEAD(&tbl->bucket[i]);
 	}
 	tbl->max_size = IP_VS_LBLCR_TAB_SIZE*16;

net/netfilter/ipvs/ip_vs_sh.c

@@ -269,14 +269,20 @@ ip_vs_sh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph)
 	switch (iph->protocol) {
 	case IPPROTO_TCP:
 		th = skb_header_pointer(skb, iph->len, sizeof(_tcph), &_tcph);
+		if (unlikely(th == NULL))
+			return 0;
 		port = th->source;
 		break;
 	case IPPROTO_UDP:
 		uh = skb_header_pointer(skb, iph->len, sizeof(_udph), &_udph);
+		if (unlikely(uh == NULL))
+			return 0;
 		port = uh->source;
 		break;
 	case IPPROTO_SCTP:
 		sh = skb_header_pointer(skb, iph->len, sizeof(_sctph), &_sctph);
+		if (unlikely(sh == NULL))
+			return 0;
 		port = sh->source;
 		break;
 	default:

net/netfilter/nf_conntrack_core.c

@@ -238,7 +238,7 @@ destroy_conntrack(struct nf_conntrack *nfct)
 	nf_conntrack_free(ct);
 }
 
-void nf_ct_delete_from_lists(struct nf_conn *ct)
+static void nf_ct_delete_from_lists(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 
@@ -253,7 +253,6 @@ void nf_ct_delete_from_lists(struct nf_conn *ct)
 			     &net->ct.dying);
 	spin_unlock_bh(&nf_conntrack_lock);
 }
-EXPORT_SYMBOL_GPL(nf_ct_delete_from_lists);
 
 static void death_by_event(unsigned long ul_conntrack)
 {
@@ -275,7 +274,7 @@ static void death_by_event(unsigned long ul_conntrack)
 	nf_ct_put(ct);
 }
 
-void nf_ct_dying_timeout(struct nf_conn *ct)
+static void nf_ct_dying_timeout(struct nf_conn *ct)
 {
 	struct net *net = nf_ct_net(ct);
 	struct nf_conntrack_ecache *ecache = nf_ct_ecache_find(ct);
@@ -288,27 +287,33 @@ void nf_ct_dying_timeout(struct nf_conn *ct)
 		(prandom_u32() % net->ct.sysctl_events_retry_timeout);
 	add_timer(&ecache->timeout);
 }
-EXPORT_SYMBOL_GPL(nf_ct_dying_timeout);
 
-static void death_by_timeout(unsigned long ul_conntrack)
+bool nf_ct_delete(struct nf_conn *ct, u32 portid, int report)
 {
-	struct nf_conn *ct = (void *)ul_conntrack;
 	struct nf_conn_tstamp *tstamp;
 
 	tstamp = nf_conn_tstamp_find(ct);
 	if (tstamp && tstamp->stop == 0)
 		tstamp->stop = ktime_to_ns(ktime_get_real());
 
-	if (!test_bit(IPS_DYING_BIT, &ct->status) &&
-	    unlikely(nf_conntrack_event(IPCT_DESTROY, ct) < 0)) {
+	if (!nf_ct_is_dying(ct) &&
+	    unlikely(nf_conntrack_event_report(IPCT_DESTROY, ct,
+	    portid, report) < 0)) {
 		/* destroy event was not delivered */
 		nf_ct_delete_from_lists(ct);
 		nf_ct_dying_timeout(ct);
-		return;
+		return false;
 	}
 	set_bit(IPS_DYING_BIT, &ct->status);
 	nf_ct_delete_from_lists(ct);
 	nf_ct_put(ct);
+	return true;
+}
+EXPORT_SYMBOL_GPL(nf_ct_delete);
+
+static void death_by_timeout(unsigned long ul_conntrack)
+{
+	nf_ct_delete((struct nf_conn *)ul_conntrack, 0, 0);
 }
 
 /*
@@ -643,10 +648,7 @@ static noinline int early_drop(struct net *net, unsigned int hash)
 		return dropped;
 
 	if (del_timer(&ct->timeout)) {
-		death_by_timeout((unsigned long)ct);
-		/* Check if we indeed killed this entry. Reliable event
-		   delivery may have inserted it into the dying list. */
-		if (test_bit(IPS_DYING_BIT, &ct->status)) {
+		if (nf_ct_delete(ct, 0, 0)) {
 			dropped = 1;
 			NF_CT_STAT_INC_ATOMIC(net, early_drop);
 		}
@@ -1192,7 +1194,7 @@ EXPORT_SYMBOL_GPL(nf_ct_port_nlattr_tuple_size);
 #endif
 
 /* Used by ipt_REJECT and ip6t_REJECT. */
-static void nf_conntrack_attach(struct sk_buff *nskb, struct sk_buff *skb)
+static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb)
 {
 	struct nf_conn *ct;
 	enum ip_conntrack_info ctinfo;
@@ -1244,7 +1246,7 @@ get_next_corpse(struct net *net, int (*iter)(struct nf_conn *i, void *data),
 
 void nf_ct_iterate_cleanup(struct net *net,
 			   int (*iter)(struct nf_conn *i, void *data),
-			   void *data)
+			   void *data, u32 portid, int report)
 {
 	struct nf_conn *ct;
 	unsigned int bucket = 0;
@@ -1252,7 +1254,8 @@ void nf_ct_iterate_cleanup(struct net *net,
 	while ((ct = get_next_corpse(net, iter, data, &bucket)) != NULL) {
 		/* Time to push up daises... */
 		if (del_timer(&ct->timeout))
-			death_by_timeout((unsigned long)ct);
+			nf_ct_delete(ct, portid, report);
+
 		/* ... else the timer will get him soon. */
 
 		nf_ct_put(ct);
@@ -1260,30 +1263,6 @@ void nf_ct_iterate_cleanup(struct net *net,
 }
 EXPORT_SYMBOL_GPL(nf_ct_iterate_cleanup);
 
-struct __nf_ct_flush_report {
-	u32 portid;
-	int report;
-};
-
-static int kill_report(struct nf_conn *i, void *data)
-{
-	struct __nf_ct_flush_report *fr = (struct __nf_ct_flush_report *)data;
-	struct nf_conn_tstamp *tstamp;
-
-	tstamp = nf_conn_tstamp_find(i);
-	if (tstamp && tstamp->stop == 0)
-		tstamp->stop = ktime_to_ns(ktime_get_real());
-
-	/* If we fail to deliver the event, death_by_timeout() will retry */
-	if (nf_conntrack_event_report(IPCT_DESTROY, i,
-				      fr->portid, fr->report) < 0)
-		return 1;
-
-	/* Avoid the delivery of the destroy event in death_by_timeout(). */
-	set_bit(IPS_DYING_BIT, &i->status);
-	return 1;
-}
-
 static int kill_all(struct nf_conn *i, void *data)
 {
 	return 1;
@@ -1301,11 +1280,7 @@ EXPORT_SYMBOL_GPL(nf_ct_free_hashtable);
 
 void nf_conntrack_flush_report(struct net *net, u32 portid, int report)
 {
-	struct __nf_ct_flush_report fr = {
-		.portid	= portid,
-		.report = report,
-	};
-	nf_ct_iterate_cleanup(net, kill_report, &fr);
+	nf_ct_iterate_cleanup(net, kill_all, NULL, portid, report);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_flush_report);
 
@@ -1386,7 +1361,7 @@ void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
 i_see_dead_people:
 	busy = 0;
 	list_for_each_entry(net, net_exit_list, exit_list) {
-		nf_ct_iterate_cleanup(net, kill_all, NULL);
+		nf_ct_iterate_cleanup(net, kill_all, NULL, 0, 0);
 		nf_ct_release_dying_list(net);
 		if (atomic_read(&net->ct.count) != 0)
 			busy = 1;
@@ -1692,7 +1667,7 @@ int nf_conntrack_init_net(struct net *net)
 	return ret;
 }
 
-s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
+s32 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 			enum ip_conntrack_dir dir,
 			u32 seq);
 EXPORT_SYMBOL_GPL(nf_ct_nat_offset);

net/netfilter/nf_conntrack_labels.c

@@ -8,12 +8,8 @@
  * published by the Free Software Foundation.
  */
 
-#include <linux/ctype.h>
 #include <linux/export.h>
-#include <linux/jhash.h>
-#include <linux/spinlock.h>
 #include <linux/types.h>
-#include <linux/slab.h>
 
 #include <net/netfilter/nf_conntrack_ecache.h>
 #include <net/netfilter/nf_conntrack_labels.h>

net/netfilter/nf_conntrack_netlink.c

@@ -1038,21 +1038,9 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
 		}
 	}
 
-	if (del_timer(&ct->timeout)) {
-		if (nf_conntrack_event_report(IPCT_DESTROY, ct,
-					      NETLINK_CB(skb).portid,
-					      nlmsg_report(nlh)) < 0) {
-			nf_ct_delete_from_lists(ct);
-			/* we failed to report the event, try later */
-			nf_ct_dying_timeout(ct);
-			nf_ct_put(ct);
-			return 0;
-		}
-		/* death_by_timeout would report the event again */
-		set_bit(IPS_DYING_BIT, &ct->status);
-		nf_ct_delete_from_lists(ct);
-		nf_ct_put(ct);
-	}
+	if (del_timer(&ct->timeout))
+		nf_ct_delete(ct, NETLINK_CB(skb).portid, nlmsg_report(nlh));
+
 	nf_ct_put(ct);
 
 	return 0;
@@ -1999,6 +1987,27 @@ ctnetlink_stat_ct(struct sock *ctnl, struct sk_buff *skb,
 	return err == -EAGAIN ? -ENOBUFS : err;
 }
 
+static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
+	[CTA_EXPECT_MASTER]	= { .type = NLA_NESTED },
+	[CTA_EXPECT_TUPLE]	= { .type = NLA_NESTED },
+	[CTA_EXPECT_MASK]	= { .type = NLA_NESTED },
+	[CTA_EXPECT_TIMEOUT]	= { .type = NLA_U32 },
+	[CTA_EXPECT_ID]		= { .type = NLA_U32 },
+	[CTA_EXPECT_HELP_NAME]	= { .type = NLA_NUL_STRING,
+				    .len = NF_CT_HELPER_NAME_LEN - 1 },
+	[CTA_EXPECT_ZONE]	= { .type = NLA_U16 },
+	[CTA_EXPECT_FLAGS]	= { .type = NLA_U32 },
+	[CTA_EXPECT_CLASS]	= { .type = NLA_U32 },
+	[CTA_EXPECT_NAT]	= { .type = NLA_NESTED },
+	[CTA_EXPECT_FN]		= { .type = NLA_NUL_STRING },
+};
+
+static struct nf_conntrack_expect *
+ctnetlink_alloc_expect(const struct nlattr *const cda[], struct nf_conn *ct,
+		       struct nf_conntrack_helper *helper,
+		       struct nf_conntrack_tuple *tuple,
+		       struct nf_conntrack_tuple *mask);
+
 #ifdef CONFIG_NETFILTER_NETLINK_QUEUE_CT
 static size_t
 ctnetlink_nfqueue_build_size(const struct nf_conn *ct)
@@ -2139,10 +2148,69 @@ ctnetlink_nfqueue_parse(const struct nlattr *attr, struct nf_conn *ct)
 	return ret;
 }
 
+static int ctnetlink_nfqueue_exp_parse(const struct nlattr * const *cda,
+				       const struct nf_conn *ct,
+				       struct nf_conntrack_tuple *tuple,
+				       struct nf_conntrack_tuple *mask)
+{
+	int err;
+
+	err = ctnetlink_parse_tuple(cda, tuple, CTA_EXPECT_TUPLE,
+				    nf_ct_l3num(ct));
+	if (err < 0)
+		return err;
+
+	return ctnetlink_parse_tuple(cda, mask, CTA_EXPECT_MASK,
+				     nf_ct_l3num(ct));
+}
+
+static int
+ctnetlink_nfqueue_attach_expect(const struct nlattr *attr, struct nf_conn *ct,
+				u32 portid, u32 report)
+{
+	struct nlattr *cda[CTA_EXPECT_MAX+1];
+	struct nf_conntrack_tuple tuple, mask;
+	struct nf_conntrack_helper *helper;
+	struct nf_conntrack_expect *exp;
+	int err;
+
+	err = nla_parse_nested(cda, CTA_EXPECT_MAX, attr, exp_nla_policy);
+	if (err < 0)
+		return err;
+
+	err = ctnetlink_nfqueue_exp_parse((const struct nlattr * const *)cda,
+					  ct, &tuple, &mask);
+	if (err < 0)
+		return err;
+
+	if (cda[CTA_EXPECT_HELP_NAME]) {
+		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
+
+		helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
+						    nf_ct_protonum(ct));
+		if (helper == NULL)
+			return -EOPNOTSUPP;
+	}
+
+	exp = ctnetlink_alloc_expect((const struct nlattr * const *)cda, ct,
+				     helper, &tuple, &mask);
+	if (IS_ERR(exp))
+		return PTR_ERR(exp);
+
+	err = nf_ct_expect_related_report(exp, portid, report);
+	if (err < 0) {
+		nf_ct_expect_put(exp);
+		return err;
+	}
+
+	return 0;
+}
+
 static struct nfq_ct_hook ctnetlink_nfqueue_hook = {
 	.build_size	= ctnetlink_nfqueue_build_size,
 	.build		= ctnetlink_nfqueue_build,
 	.parse		= ctnetlink_nfqueue_parse,
+	.attach_expect	= ctnetlink_nfqueue_attach_expect,
 };
 #endif /* CONFIG_NETFILTER_NETLINK_QUEUE_CT */
 
@@ -2510,21 +2578,6 @@ static int ctnetlink_dump_exp_ct(struct sock *ctnl, struct sk_buff *skb,
 	return err;
 }
 
-static const struct nla_policy exp_nla_policy[CTA_EXPECT_MAX+1] = {
-	[CTA_EXPECT_MASTER]	= { .type = NLA_NESTED },
-	[CTA_EXPECT_TUPLE]	= { .type = NLA_NESTED },
-	[CTA_EXPECT_MASK]	= { .type = NLA_NESTED },
-	[CTA_EXPECT_TIMEOUT]	= { .type = NLA_U32 },
-	[CTA_EXPECT_ID]		= { .type = NLA_U32 },
-	[CTA_EXPECT_HELP_NAME]	= { .type = NLA_NUL_STRING,
-				    .len = NF_CT_HELPER_NAME_LEN - 1 },
-	[CTA_EXPECT_ZONE]	= { .type = NLA_U16 },
-	[CTA_EXPECT_FLAGS]	= { .type = NLA_U32 },
-	[CTA_EXPECT_CLASS]	= { .type = NLA_U32 },
-	[CTA_EXPECT_NAT]	= { .type = NLA_NESTED },
-	[CTA_EXPECT_FN]		= { .type = NLA_NUL_STRING },
-};
-
 static int
 ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
 		     const struct nlmsghdr *nlh,
@@ -2747,76 +2800,26 @@ ctnetlink_parse_expect_nat(const struct nlattr *attr,
 #endif
 }
 
-static int
-ctnetlink_create_expect(struct net *net, u16 zone,
-			const struct nlattr * const cda[],
-			u_int8_t u3,
-			u32 portid, int report)
+static struct nf_conntrack_expect *
+ctnetlink_alloc_expect(const struct nlattr * const cda[], struct nf_conn *ct,
+		       struct nf_conntrack_helper *helper,
+		       struct nf_conntrack_tuple *tuple,
+		       struct nf_conntrack_tuple *mask)
 {
-	struct nf_conntrack_tuple tuple, mask, master_tuple;
-	struct nf_conntrack_tuple_hash *h = NULL;
+	u_int32_t class = 0;
 	struct nf_conntrack_expect *exp;
-	struct nf_conn *ct;
 	struct nf_conn_help *help;
-	struct nf_conntrack_helper *helper = NULL;
-	u_int32_t class = 0;
-	int err = 0;
-
-	/* caller guarantees that those three CTA_EXPECT_* exist */
-	err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
-	if (err < 0)
-		return err;
-	err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3);
-	if (err < 0)
-		return err;
-	err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3);
-	if (err < 0)
-		return err;
-
-	/* Look for master conntrack of this expectation */
-	h = nf_conntrack_find_get(net, zone, &master_tuple);
-	if (!h)
-		return -ENOENT;
-	ct = nf_ct_tuplehash_to_ctrack(h);
-
-	/* Look for helper of this expectation */
-	if (cda[CTA_EXPECT_HELP_NAME]) {
-		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
-
-		helper = __nf_conntrack_helper_find(helpname, nf_ct_l3num(ct),
-						    nf_ct_protonum(ct));
-		if (helper == NULL) {
-#ifdef CONFIG_MODULES
-			if (request_module("nfct-helper-%s", helpname) < 0) {
-				err = -EOPNOTSUPP;
-				goto out;
-			}
-
-			helper = __nf_conntrack_helper_find(helpname,
-							    nf_ct_l3num(ct),
-							    nf_ct_protonum(ct));
-			if (helper) {
-				err = -EAGAIN;
-				goto out;
-			}
-#endif
-			err = -EOPNOTSUPP;
-			goto out;
-		}
-	}
+	int err;
 
 	if (cda[CTA_EXPECT_CLASS] && helper) {
 		class = ntohl(nla_get_be32(cda[CTA_EXPECT_CLASS]));
-		if (class > helper->expect_class_max) {
-			err = -EINVAL;
-			goto out;
-		}
+		if (class > helper->expect_class_max)
+			return ERR_PTR(-EINVAL);
 	}
 	exp = nf_ct_expect_alloc(ct);
-	if (!exp) {
-		err = -ENOMEM;
-		goto out;
-	}
+	if (!exp)
+		return ERR_PTR(-ENOMEM);
+
 	help = nfct_help(ct);
 	if (!help) {
 		if (!cda[CTA_EXPECT_TIMEOUT]) {
@@ -2854,21 +2857,89 @@ ctnetlink_create_expect(struct net *net, u16 zone,
 	exp->class = class;
 	exp->master = ct;
 	exp->helper = helper;
-	memcpy(&exp->tuple, &tuple, sizeof(struct nf_conntrack_tuple));
-	memcpy(&exp->mask.src.u3, &mask.src.u3, sizeof(exp->mask.src.u3));
-	exp->mask.src.u.all = mask.src.u.all;
+	exp->tuple = *tuple;
+	exp->mask.src.u3 = mask->src.u3;
+	exp->mask.src.u.all = mask->src.u.all;
 
 	if (cda[CTA_EXPECT_NAT]) {
 		err = ctnetlink_parse_expect_nat(cda[CTA_EXPECT_NAT],
-						 exp, u3);
+						 exp, nf_ct_l3num(ct));
 		if (err < 0)
 			goto err_out;
 	}
-	err = nf_ct_expect_related_report(exp, portid, report);
+	return exp;
 err_out:
 	nf_ct_expect_put(exp);
-out:
-	nf_ct_put(nf_ct_tuplehash_to_ctrack(h));
+	return ERR_PTR(err);
+}
+
+static int
+ctnetlink_create_expect(struct net *net, u16 zone,
+			const struct nlattr * const cda[],
+			u_int8_t u3, u32 portid, int report)
+{
+	struct nf_conntrack_tuple tuple, mask, master_tuple;
+	struct nf_conntrack_tuple_hash *h = NULL;
+	struct nf_conntrack_helper *helper = NULL;
+	struct nf_conntrack_expect *exp;
+	struct nf_conn *ct;
+	int err;
+
+	/* caller guarantees that those three CTA_EXPECT_* exist */
+	err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE, u3);
+	if (err < 0)
+		return err;
+	err = ctnetlink_parse_tuple(cda, &mask, CTA_EXPECT_MASK, u3);
+	if (err < 0)
+		return err;
+	err = ctnetlink_parse_tuple(cda, &master_tuple, CTA_EXPECT_MASTER, u3);
+	if (err < 0)
+		return err;
+
+	/* Look for master conntrack of this expectation */
+	h = nf_conntrack_find_get(net, zone, &master_tuple);
+	if (!h)
+		return -ENOENT;
+	ct = nf_ct_tuplehash_to_ctrack(h);
+
+	if (cda[CTA_EXPECT_HELP_NAME]) {
+		const char *helpname = nla_data(cda[CTA_EXPECT_HELP_NAME]);
+
+		helper = __nf_conntrack_helper_find(helpname, u3,
+						    nf_ct_protonum(ct));
+		if (helper == NULL) {
+#ifdef CONFIG_MODULES
+			if (request_module("nfct-helper-%s", helpname) < 0) {
+				err = -EOPNOTSUPP;
+				goto err_ct;
+			}
+			helper = __nf_conntrack_helper_find(helpname, u3,
+							    nf_ct_protonum(ct));
+			if (helper) {
+				err = -EAGAIN;
+				goto err_ct;
+			}
+#endif
+			err = -EOPNOTSUPP;
+			goto err_ct;
+		}
+	}
+
+	exp = ctnetlink_alloc_expect(cda, ct, helper, &tuple, &mask);
+	if (IS_ERR(exp)) {
+		err = PTR_ERR(exp);
+		goto err_ct;
+	}
+
+	err = nf_ct_expect_related_report(exp, portid, report);
+	if (err < 0)
+		goto err_exp;
+
+	return 0;
+err_exp:
+	nf_ct_expect_put(exp);
+err_ct:
+	nf_ct_put(ct);
 	return err;
 }
 

net/netfilter/nf_conntrack_proto.c

@@ -281,7 +281,7 @@ void nf_ct_l3proto_pernet_unregister(struct net *net,
 	nf_ct_l3proto_unregister_sysctl(net, proto);
 
 	/* Remove all contrack entries for this protocol */
-	nf_ct_iterate_cleanup(net, kill_l3proto, proto);
+	nf_ct_iterate_cleanup(net, kill_l3proto, proto, 0, 0);
 }
 EXPORT_SYMBOL_GPL(nf_ct_l3proto_pernet_unregister);
 
@@ -476,7 +476,7 @@ void nf_ct_l4proto_pernet_unregister(struct net *net,
 	nf_ct_l4proto_unregister_sysctl(net, pn, l4proto);
 
 	/* Remove all contrack entries for this protocol */
-	nf_ct_iterate_cleanup(net, kill_l4proto, l4proto);
+	nf_ct_iterate_cleanup(net, kill_l4proto, l4proto, 0, 0);
 }
 EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister);
 

net/netfilter/nf_conntrack_proto_tcp.c

@@ -496,7 +496,7 @@ static void tcp_sack(const struct sk_buff *skb, unsigned int dataoff,
 }
 
 #ifdef CONFIG_NF_NAT_NEEDED
-static inline s16 nat_offset(const struct nf_conn *ct,
+static inline s32 nat_offset(const struct nf_conn *ct,
 			     enum ip_conntrack_dir dir,
 			     u32 seq)
 {
@@ -525,7 +525,7 @@ static bool tcp_in_window(const struct nf_conn *ct,
 	struct ip_ct_tcp_state *receiver = &state->seen[!dir];
 	const struct nf_conntrack_tuple *tuple = &ct->tuplehash[dir].tuple;
 	__u32 seq, ack, sack, end, win, swin;
-	s16 receiver_offset;
+	s32 receiver_offset;
 	bool res, in_recv_win;
 
 	/*

net/netfilter/nf_nat_core.c

@@ -497,7 +497,7 @@ static void nf_nat_l4proto_clean(u8 l3proto, u8 l4proto)
 
 	rtnl_lock();
 	for_each_net(net)
-		nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean);
+		nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0);
 	rtnl_unlock();
 }
 
@@ -511,7 +511,7 @@ static void nf_nat_l3proto_clean(u8 l3proto)
 	rtnl_lock();
 
 	for_each_net(net)
-		nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean);
+		nf_ct_iterate_cleanup(net, nf_nat_proto_remove, &clean, 0, 0);
 	rtnl_unlock();
 }
 
@@ -749,7 +749,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
 {
 	struct nf_nat_proto_clean clean = {};
 
-	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean);
+	nf_ct_iterate_cleanup(net, &nf_nat_proto_remove, &clean, 0, 0);
 	synchronize_rcu();
 	nf_ct_free_hashtable(net->ct.nat_bysource, net->ct.nat_htable_size);
 }

net/netfilter/nf_nat_helper.c

@@ -30,8 +30,6 @@
 	pr_debug("offset_before=%d, offset_after=%d, correction_pos=%u\n", \
 		 x->offset_before, x->offset_after, x->correction_pos);
 
-static DEFINE_SPINLOCK(nf_nat_seqofs_lock);
-
 /* Setup TCP sequence correction given this change at this sequence */
 static inline void
 adjust_tcp_sequence(u32 seq,
@@ -49,7 +47,7 @@ adjust_tcp_sequence(u32 seq,
 	pr_debug("adjust_tcp_sequence: Seq_offset before: ");
 	DUMP_OFFSET(this_way);
 
-	spin_lock_bh(&nf_nat_seqofs_lock);
+	spin_lock_bh(&ct->lock);
 
 	/* SYN adjust. If it's uninitialized, or this is after last
 	 * correction, record it: we don't handle more than one
@@ -61,31 +59,26 @@ adjust_tcp_sequence(u32 seq,
 		this_way->offset_before = this_way->offset_after;
 		this_way->offset_after += sizediff;
 	}
-	spin_unlock_bh(&nf_nat_seqofs_lock);
+	spin_unlock_bh(&ct->lock);
 
 	pr_debug("adjust_tcp_sequence: Seq_offset after: ");
 	DUMP_OFFSET(this_way);
 }
 
-/* Get the offset value, for conntrack */
-s16 nf_nat_get_offset(const struct nf_conn *ct,
+/* Get the offset value, for conntrack. Caller must have the conntrack locked */
+s32 nf_nat_get_offset(const struct nf_conn *ct,
 		      enum ip_conntrack_dir dir,
 		      u32 seq)
 {
 	struct nf_conn_nat *nat = nfct_nat(ct);
 	struct nf_nat_seq *this_way;
-	s16 offset;
 
 	if (!nat)
 		return 0;
 
 	this_way = &nat->seq[dir];
-	spin_lock_bh(&nf_nat_seqofs_lock);
-	offset = after(seq, this_way->correction_pos)
+	return after(seq, this_way->correction_pos)
 		 ? this_way->offset_after : this_way->offset_before;
-	spin_unlock_bh(&nf_nat_seqofs_lock);
-
-	return offset;
 }
 
 /* Frobs data inside this packet, which is linear. */
@@ -143,7 +136,7 @@ static int enlarge_skb(struct sk_buff *skb, unsigned int extra)
 }
 
 void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo,
-			   __be32 seq, s16 off)
+			   __be32 seq, s32 off)
 {
 	if (!off)
 		return;
@@ -370,9 +363,10 @@ nf_nat_seq_adjust(struct sk_buff *skb,
 	struct tcphdr *tcph;
 	int dir;
 	__be32 newseq, newack;
-	s16 seqoff, ackoff;
+	s32 seqoff, ackoff;
 	struct nf_conn_nat *nat = nfct_nat(ct);
 	struct nf_nat_seq *this_way, *other_way;
+	int res;
 
 	dir = CTINFO2DIR(ctinfo);
 
@@ -383,6 +377,7 @@ nf_nat_seq_adjust(struct sk_buff *skb,
 		return 0;
 
 	tcph = (void *)skb->data + protoff;
+	spin_lock_bh(&ct->lock);
 	if (after(ntohl(tcph->seq), this_way->correction_pos))
 		seqoff = this_way->offset_after;
 	else
@@ -407,7 +402,10 @@ nf_nat_seq_adjust(struct sk_buff *skb,
 	tcph->seq = newseq;
 	tcph->ack_seq = newack;
 
-	return nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo);
+	res = nf_nat_sack_adjust(skb, protoff, tcph, ct, ctinfo);
+	spin_unlock_bh(&ct->lock);
+
+	return res;
 }
 
 /* Setup NAT on this expected conntrack so it follows master. */

net/netfilter/nf_tproxy_core.c

-/*
- * Transparent proxy support for Linux/iptables
- *
- * Copyright (c) 2006-2007 BalaBit IT Ltd.
- * Author: Balazs Scheidler, Krisztian Kovacs
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- */
-
-#include <linux/module.h>
-
-#include <linux/net.h>
-#include <linux/if.h>
-#include <linux/netdevice.h>
-#include <net/udp.h>
-#include <net/netfilter/nf_tproxy_core.h>
-
-
-static void
-nf_tproxy_destructor(struct sk_buff *skb)
-{
-	struct sock *sk = skb->sk;
-
-	skb->sk = NULL;
-	skb->destructor = NULL;
-
-	if (sk)
-		sock_put(sk);
-}
-
-/* consumes sk */
-void
-nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
-{
-	/* assigning tw sockets complicates things; most
-	 * skb->sk->X checks would have to test sk->sk_state first */
-	if (sk->sk_state == TCP_TIME_WAIT) {
-		inet_twsk_put(inet_twsk(sk));
-		return;
-	}
-
-	skb_orphan(skb);
-	skb->sk = sk;
-	skb->destructor = nf_tproxy_destructor;
-}
-EXPORT_SYMBOL_GPL(nf_tproxy_assign_sock);
-
-static int __init nf_tproxy_init(void)
-{
-	pr_info("NF_TPROXY: Transparent proxy support initialized, version 4.1.0\n");
-	pr_info("NF_TPROXY: Copyright (c) 2006-2007 BalaBit IT Ltd.\n");
-	return 0;
-}
-
-module_init(nf_tproxy_init);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Krisztian Kovacs");
-MODULE_DESCRIPTION("Transparent proxy support core routines");

net/netfilter/nfnetlink_queue_core.c

@@ -862,6 +862,7 @@ static const struct nla_policy nfqa_verdict_policy[NFQA_MAX+1] = {
 	[NFQA_MARK]		= { .type = NLA_U32 },
 	[NFQA_PAYLOAD]		= { .type = NLA_UNSPEC },
 	[NFQA_CT]		= { .type = NLA_UNSPEC },
+	[NFQA_EXP]		= { .type = NLA_UNSPEC },
 };
 
 static const struct nla_policy nfqa_verdict_batch_policy[NFQA_MAX+1] = {
@@ -990,9 +991,14 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb,
 	if (entry == NULL)
 		return -ENOENT;
 
-	rcu_read_lock();
-	if (nfqa[NFQA_CT] && (queue->flags & NFQA_CFG_F_CONNTRACK))
+	if (nfqa[NFQA_CT]) {
 		ct = nfqnl_ct_parse(entry->skb, nfqa[NFQA_CT], &ctinfo);
+		if (ct && nfqa[NFQA_EXP]) {
+			nfqnl_attach_expect(ct, nfqa[NFQA_EXP],
+					    NETLINK_CB(skb).portid,
+					    nlmsg_report(nlh));
+		}
+	}
 
 	if (nfqa[NFQA_PAYLOAD]) {
 		u16 payload_len = nla_len(nfqa[NFQA_PAYLOAD]);
@@ -1005,7 +1011,6 @@ nfqnl_recv_verdict(struct sock *ctnl, struct sk_buff *skb,
 		if (ct)
 			nfqnl_ct_seq_adjust(skb, ct, ctinfo, diff);
 	}
-	rcu_read_unlock();
 
 	if (nfqa[NFQA_MARK])
 		entry->skb->mark = ntohl(nla_get_be32(nfqa[NFQA_MARK]));

net/netfilter/nfnetlink_queue_ct.c

@@ -96,3 +96,18 @@ void nfqnl_ct_seq_adjust(struct sk_buff *skb, struct nf_conn *ct,
 	if ((ct->status & IPS_NAT_MASK) && diff)
 		nfq_nat_ct->seq_adjust(skb, ct, ctinfo, diff);
 }
+
+int nfqnl_attach_expect(struct nf_conn *ct, const struct nlattr *attr,
+			u32 portid, u32 report)
+{
+	struct nfq_ct_hook *nfq_ct;
+
+	if (nf_ct_is_untracked(ct))
+		return 0;
+
+	nfq_ct = rcu_dereference(nfq_ct_hook);
+	if (nfq_ct == NULL)
+		return -EOPNOTSUPP;
+
+	return nfq_ct->attach_expect(attr, ct, portid, report);
+}

net/netfilter/xt_TPROXY.c

@@ -15,7 +15,9 @@
 #include <linux/ip.h>
 #include <net/checksum.h>
 #include <net/udp.h>
+#include <net/tcp.h>
 #include <net/inet_sock.h>
+#include <net/inet_hashtables.h>
 #include <linux/inetdevice.h>
 #include <linux/netfilter/x_tables.h>
 #include <linux/netfilter_ipv4/ip_tables.h>
@@ -26,13 +28,18 @@
 #define XT_TPROXY_HAVE_IPV6 1
 #include <net/if_inet6.h>
 #include <net/addrconf.h>
+#include <net/inet6_hashtables.h>
 #include <linux/netfilter_ipv6/ip6_tables.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #endif
 
-#include <net/netfilter/nf_tproxy_core.h>
 #include <linux/netfilter/xt_TPROXY.h>
 
+enum nf_tproxy_lookup_t {
+	 NFT_LOOKUP_LISTENER,
+	 NFT_LOOKUP_ESTABLISHED,
+};
+
 static bool tproxy_sk_is_transparent(struct sock *sk)
 {
 	if (sk->sk_state != TCP_TIME_WAIT) {
@@ -68,6 +75,157 @@ tproxy_laddr4(struct sk_buff *skb, __be32 user_laddr, __be32 daddr)
 	return laddr ? laddr : daddr;
 }
 
+/*
+ * This is used when the user wants to intercept a connection matching
+ * an explicit iptables rule. In this case the sockets are assumed
+ * matching in preference order:
+ *
+ *   - match: if there's a fully established connection matching the
+ *     _packet_ tuple, it is returned, assuming the redirection
+ *     already took place and we process a packet belonging to an
+ *     established connection
+ *
+ *   - match: if there's a listening socket matching the redirection
+ *     (e.g. on-port & on-ip of the connection), it is returned,
+ *     regardless if it was bound to 0.0.0.0 or an explicit
+ *     address. The reasoning is that if there's an explicit rule, it
+ *     does not really matter if the listener is bound to an interface
+ *     or to 0. The user already stated that he wants redirection
+ *     (since he added the rule).
+ *
+ * Please note that there's an overlap between what a TPROXY target
+ * and a socket match will match. Normally if you have both rules the
+ * "socket" match will be the first one, effectively all packets
+ * belonging to established connections going through that one.
+ */
+static inline struct sock *
+nf_tproxy_get_sock_v4(struct net *net, const u8 protocol,
+		      const __be32 saddr, const __be32 daddr,
+		      const __be16 sport, const __be16 dport,
+		      const struct net_device *in,
+		      const enum nf_tproxy_lookup_t lookup_type)
+{
+	struct sock *sk;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		switch (lookup_type) {
+		case NFT_LOOKUP_LISTENER:
+			sk = inet_lookup_listener(net, &tcp_hashinfo,
+						    saddr, sport,
+						    daddr, dport,
+						    in->ifindex);
+
+			/* NOTE: we return listeners even if bound to
+			 * 0.0.0.0, those are filtered out in
+			 * xt_socket, since xt_TPROXY needs 0 bound
+			 * listeners too
+			 */
+			break;
+		case NFT_LOOKUP_ESTABLISHED:
+			sk = inet_lookup_established(net, &tcp_hashinfo,
+						    saddr, sport, daddr, dport,
+						    in->ifindex);
+			break;
+		default:
+			BUG();
+		}
+		break;
+	case IPPROTO_UDP:
+		sk = udp4_lib_lookup(net, saddr, sport, daddr, dport,
+				     in->ifindex);
+		if (sk) {
+			int connected = (sk->sk_state == TCP_ESTABLISHED);
+			int wildcard = (inet_sk(sk)->inet_rcv_saddr == 0);
+
+			/* NOTE: we return listeners even if bound to
+			 * 0.0.0.0, those are filtered out in
+			 * xt_socket, since xt_TPROXY needs 0 bound
+			 * listeners too
+			 */
+			if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
+			    (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
+				sock_put(sk);
+				sk = NULL;
+			}
+		}
+		break;
+	default:
+		WARN_ON(1);
+		sk = NULL;
+	}
+
+	pr_debug("tproxy socket lookup: proto %u %08x:%u -> %08x:%u, lookup type: %d, sock %p\n",
+		 protocol, ntohl(saddr), ntohs(sport), ntohl(daddr), ntohs(dport), lookup_type, sk);
+
+	return sk;
+}
+
+#ifdef XT_TPROXY_HAVE_IPV6
+static inline struct sock *
+nf_tproxy_get_sock_v6(struct net *net, const u8 protocol,
+		      const struct in6_addr *saddr, const struct in6_addr *daddr,
+		      const __be16 sport, const __be16 dport,
+		      const struct net_device *in,
+		      const enum nf_tproxy_lookup_t lookup_type)
+{
+	struct sock *sk;
+
+	switch (protocol) {
+	case IPPROTO_TCP:
+		switch (lookup_type) {
+		case NFT_LOOKUP_LISTENER:
+			sk = inet6_lookup_listener(net, &tcp_hashinfo,
+						   saddr, sport,
+						   daddr, ntohs(dport),
+						   in->ifindex);
+
+			/* NOTE: we return listeners even if bound to
+			 * 0.0.0.0, those are filtered out in
+			 * xt_socket, since xt_TPROXY needs 0 bound
+			 * listeners too
+			 */
+			break;
+		case NFT_LOOKUP_ESTABLISHED:
+			sk = __inet6_lookup_established(net, &tcp_hashinfo,
+							saddr, sport, daddr, ntohs(dport),
+							in->ifindex);
+			break;
+		default:
+			BUG();
+		}
+		break;
+	case IPPROTO_UDP:
+		sk = udp6_lib_lookup(net, saddr, sport, daddr, dport,
+				     in->ifindex);
+		if (sk) {
+			int connected = (sk->sk_state == TCP_ESTABLISHED);
+			int wildcard = ipv6_addr_any(&inet6_sk(sk)->rcv_saddr);
+
+			/* NOTE: we return listeners even if bound to
+			 * 0.0.0.0, those are filtered out in
+			 * xt_socket, since xt_TPROXY needs 0 bound
+			 * listeners too
+			 */
+			if ((lookup_type == NFT_LOOKUP_ESTABLISHED && (!connected || wildcard)) ||
+			    (lookup_type == NFT_LOOKUP_LISTENER && connected)) {
+				sock_put(sk);
+				sk = NULL;
+			}
+		}
+		break;
+	default:
+		WARN_ON(1);
+		sk = NULL;
+	}
+
+	pr_debug("tproxy socket lookup: proto %u %pI6:%u -> %pI6:%u, lookup type: %d, sock %p\n",
+		 protocol, saddr, ntohs(sport), daddr, ntohs(dport), lookup_type, sk);
+
+	return sk;
+}
+#endif
+
 /**
  * tproxy_handle_time_wait4 - handle IPv4 TCP TIME_WAIT reopen redirections
  * @skb:	The skb being processed.
@@ -117,6 +275,15 @@ tproxy_handle_time_wait4(struct sk_buff *skb, __be32 laddr, __be16 lport,
 	return sk;
 }
 
+/* assign a socket to the skb -- consumes sk */
+static void
+nf_tproxy_assign_sock(struct sk_buff *skb, struct sock *sk)
+{
+	skb_orphan(skb);
+	skb->sk = sk;
+	skb->destructor = sock_edemux;
+}
+
 static unsigned int
 tproxy_tg4(struct sk_buff *skb, __be32 laddr, __be16 lport,
 	   u_int32_t mark_mask, u_int32_t mark_value)

net/netfilter/xt_addrtype.c

@@ -202,7 +202,7 @@ static int addrtype_mt_checkentry_v1(const struct xt_mtchk_param *par)
 			return -EINVAL;
 		}
 		if ((info->source | info->dest) >= XT_ADDRTYPE_PROHIBIT) {
-			pr_err("ipv6 PROHIBT (THROW, NAT ..) matching not supported\n");
+			pr_err("ipv6 PROHIBIT (THROW, NAT ..) matching not supported\n");
 			return -EINVAL;
 		}
 		if ((info->source | info->dest) & XT_ADDRTYPE_BROADCAST) {

net/netfilter/xt_socket.c

@@ -19,12 +19,12 @@
 #include <net/icmp.h>
 #include <net/sock.h>
 #include <net/inet_sock.h>
-#include <net/netfilter/nf_tproxy_core.h>
 #include <net/netfilter/ipv4/nf_defrag_ipv4.h>
 
 #if IS_ENABLED(CONFIG_IP6_NF_IPTABLES)
 #define XT_SOCKET_HAVE_IPV6 1
 #include <linux/netfilter_ipv6/ip6_tables.h>
+#include <net/inet6_hashtables.h>
 #include <net/netfilter/ipv6/nf_defrag_ipv6.h>
 #endif
 
@@ -101,6 +101,43 @@ extract_icmp4_fields(const struct sk_buff *skb,
 	return 0;
 }
 
+/* "socket" match based redirection (no specific rule)
+ * ===================================================
+ *
+ * There are connections with dynamic endpoints (e.g. FTP data
+ * connection) that the user is unable to add explicit rules
+ * for. These are taken care of by a generic "socket" rule. It is
+ * assumed that the proxy application is trusted to open such
+ * connections without explicit iptables rule (except of course the
+ * generic 'socket' rule). In this case the following sockets are
+ * matched in preference order:
+ *
+ *   - match: if there's a fully established connection matching the
+ *     _packet_ tuple
+ *
+ *   - match: if there's a non-zero bound listener (possibly with a
+ *     non-local address) We don't accept zero-bound listeners, since
+ *     then local services could intercept traffic going through the
+ *     box.
+ */
+static struct sock *
+xt_socket_get_sock_v4(struct net *net, const u8 protocol,
+		      const __be32 saddr, const __be32 daddr,
+		      const __be16 sport, const __be16 dport,
+		      const struct net_device *in)
+{
+	switch (protocol) {
+	case IPPROTO_TCP:
+		return __inet_lookup(net, &tcp_hashinfo,
+				     saddr, sport, daddr, dport,
+				     in->ifindex);
+	case IPPROTO_UDP:
+		return udp4_lib_lookup(net, saddr, sport, daddr, dport,
+				       in->ifindex);
+	}
+	return NULL;
+}
+
 static bool
 socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 	     const struct xt_socket_mtinfo1 *info)
@@ -156,9 +193,9 @@ socket_match(const struct sk_buff *skb, struct xt_action_param *par,
 #endif
 
 	if (!sk)
-		sk = nf_tproxy_get_sock_v4(dev_net(skb->dev), protocol,
+		sk = xt_socket_get_sock_v4(dev_net(skb->dev), protocol,
 					   saddr, daddr, sport, dport,
-					   par->in, NFT_LOOKUP_ANY);
+					   par->in);
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;
@@ -265,6 +302,25 @@ extract_icmp6_fields(const struct sk_buff *skb,
 	return 0;
 }
 
+static struct sock *
+xt_socket_get_sock_v6(struct net *net, const u8 protocol,
+		      const struct in6_addr *saddr, const struct in6_addr *daddr,
+		      const __be16 sport, const __be16 dport,
+		      const struct net_device *in)
+{
+	switch (protocol) {
+	case IPPROTO_TCP:
+		return inet6_lookup(net, &tcp_hashinfo,
+				    saddr, sport, daddr, dport,
+				    in->ifindex);
+	case IPPROTO_UDP:
+		return udp6_lib_lookup(net, saddr, sport, daddr, dport,
+				       in->ifindex);
+	}
+
+	return NULL;
+}
+
 static bool
 socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 {
@@ -302,9 +358,9 @@ socket_mt6_v1_v2(const struct sk_buff *skb, struct xt_action_param *par)
 	}
 
 	if (!sk)
-		sk = nf_tproxy_get_sock_v6(dev_net(skb->dev), tproto,
+		sk = xt_socket_get_sock_v6(dev_net(skb->dev), tproto,
 					   saddr, daddr, sport, dport,
-					   par->in, NFT_LOOKUP_ANY);
+					   par->in);
 	if (sk) {
 		bool wildcard;
 		bool transparent = true;