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>

11 files changed, 25 insertions, 228 deletions

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index de70f7b..e2cf786be 100644
--- a/include/linux/netfilter.h
+++ b/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
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 644d9c2..0c1288a 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/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,
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 914d8d9..b411d7b 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/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 */
 
diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h
index ad14a79..e244141 100644
--- a/include/net/netfilter/nf_nat.h
+++ b/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>
diff --git a/include/net/netfilter/nf_nat_helper.h b/include/net/netfilter/nf_nat_helper.h
index b4d6bfc..194c347 100644
--- a/include/net/netfilter/nf_nat_helper.h
+++ b/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
diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h
deleted file mode 100644
index 36d9379..0000000
--- a/include/net/netfilter/nf_tproxy_core.h
+++ /dev/null
@@ -1,210 +0,0 @@
-#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
diff --git a/include/net/netfilter/nfnetlink_queue.h b/include/net/netfilter/nfnetlink_queue.h
index 86267a5..aff88ba 100644
--- a/include/net/netfilter/nfnetlink_queue.h
+++ b/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
diff --git a/include/uapi/linux/netfilter/Kbuild b/include/uapi/linux/netfilter/Kbuild
index 4111577..1749154 100644
--- a/include/uapi/linux/netfilter/Kbuild
+++ b/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
diff --git a/include/uapi/linux/netfilter/nfnetlink_queue.h b/include/uapi/linux/netfilter/nfnetlink_queue.h
index 3a9b921..0132bad 100644
--- a/include/uapi/linux/netfilter/nfnetlink_queue.h
+++ b/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
 };
diff --git a/include/linux/netfilter/xt_HMARK.h b/include/uapi/linux/netfilter/xt_HMARK.h
index 826fc58..826fc58 100644
--- a/include/linux/netfilter/xt_HMARK.h
+++ b/include/uapi/linux/netfilter/xt_HMARK.h
diff --git a/include/linux/netfilter/xt_rpfilter.h b/include/uapi/linux/netfilter/xt_rpfilter.h
index 8358d4f..8358d4f 100644
--- a/include/linux/netfilter/xt_rpfilter.h
+++ b/include/uapi/linux/netfilter/xt_rpfilter.h