12 files changed, 301 insertions, 31 deletions

diff --git a/include/net/netfilter/ipv6/nf_defrag_ipv6.h b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
new file mode 100644
index 000000000000..94dd54d76b48
--- /dev/null
+++ b/include/net/netfilter/ipv6/nf_defrag_ipv6.h
@@ -0,0 +1,6 @@
+#ifndef _NF_DEFRAG_IPV6_H
+#define _NF_DEFRAG_IPV6_H
+
+extern void nf_defrag_ipv6_enable(void);
+
+#endif /* _NF_DEFRAG_IPV6_H */
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index bde095f7e845..caf17db87dbc 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -75,7 +75,7 @@ struct nf_conntrack_helper;
 /* nf_conn feature for connections that have a helper */
 struct nf_conn_help {
 	/* Helper. if any */
-	struct nf_conntrack_helper *helper;
+	struct nf_conntrack_helper __rcu *helper;
 
 	union nf_conntrack_help help;
 
@@ -152,11 +152,7 @@ extern struct net init_net;
 
 static inline struct net *nf_ct_net(const struct nf_conn *ct)
 {
-#ifdef CONFIG_NET_NS
-	return ct->ct_net;
-#else
-	return &init_net;
-#endif
+	return read_pnet(&ct->ct_net);
 }
 
 /* Alter reply tuple (maybe alter helper). */
@@ -261,7 +257,12 @@ extern s16 (*nf_ct_nat_offset)(const struct nf_conn *ct,
 			       u32 seq);
 
 /* Fake conntrack entry for untracked connections */
-extern struct nf_conn nf_conntrack_untracked;
+DECLARE_PER_CPU(struct nf_conn, nf_conntrack_untracked);
+static inline struct nf_conn *nf_ct_untracked_get(void)
+{
+	return &__raw_get_cpu_var(nf_conntrack_untracked);
+}
+extern void nf_ct_untracked_status_or(unsigned long bits);
 
 /* Iterate over all conntracks: if iter returns true, it's deleted. */
 extern void
@@ -289,9 +290,9 @@ static inline int nf_ct_is_dying(struct nf_conn *ct)
 	return test_bit(IPS_DYING_BIT, &ct->status);
 }
 
-static inline int nf_ct_is_untracked(const struct sk_buff *skb)
+static inline int nf_ct_is_untracked(const struct nf_conn *ct)
 {
-	return (skb->nfct == &nf_conntrack_untracked.ct_general);
+	return test_bit(IPS_UNTRACKED_BIT, &ct->status);
 }
 
 extern int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp);
diff --git a/include/net/netfilter/nf_conntrack_acct.h b/include/net/netfilter/nf_conntrack_acct.h
index 03e218f0be43..4e9c63a20db2 100644
--- a/include/net/netfilter/nf_conntrack_acct.h
+++ b/include/net/netfilter/nf_conntrack_acct.h
@@ -45,6 +45,18 @@ struct nf_conn_counter *nf_ct_acct_ext_add(struct nf_conn *ct, gfp_t gfp)
 extern unsigned int
 seq_print_acct(struct seq_file *s, const struct nf_conn *ct, int dir);
 
+/* Check if connection tracking accounting is enabled */
+static inline bool nf_ct_acct_enabled(struct net *net)
+{
+	return net->ct.sysctl_acct != 0;
+}
+
+/* Enable/disable connection tracking accounting */
+static inline void nf_ct_set_acct(struct net *net, bool enable)
+{
+	net->ct.sysctl_acct = enable;
+}
+
 extern int nf_conntrack_acct_init(struct net *net);
 extern void nf_conntrack_acct_fini(struct net *net);
 
diff --git a/include/net/netfilter/nf_conntrack_core.h b/include/net/netfilter/nf_conntrack_core.h
index 3d7524fba194..aced085132e7 100644
--- a/include/net/netfilter/nf_conntrack_core.h
+++ b/include/net/netfilter/nf_conntrack_core.h
@@ -60,7 +60,7 @@ static inline int nf_conntrack_confirm(struct sk_buff *skb)
 	struct nf_conn *ct = (struct nf_conn *)skb->nfct;
 	int ret = NF_ACCEPT;
 
-	if (ct && ct != &nf_conntrack_untracked) {
+	if (ct && !nf_ct_is_untracked(ct)) {
 		if (!nf_ct_is_confirmed(ct))
 			ret = __nf_conntrack_confirm(skb);
 		if (likely(ret == NF_ACCEPT))
diff --git a/include/net/netfilter/nf_conntrack_expect.h b/include/net/netfilter/nf_conntrack_expect.h
index 11e815084fcf..0f8a8c587532 100644
--- a/include/net/netfilter/nf_conntrack_expect.h
+++ b/include/net/netfilter/nf_conntrack_expect.h
@@ -67,9 +67,6 @@ struct nf_conntrack_expect_policy {
 
 #define NF_CT_EXPECT_CLASS_DEFAULT	0
 
-#define NF_CT_EXPECT_PERMANENT	0x1
-#define NF_CT_EXPECT_INACTIVE	0x2
-
 int nf_conntrack_expect_init(struct net *net);
 void nf_conntrack_expect_fini(struct net *net);
 
@@ -85,9 +82,16 @@ struct nf_conntrack_expect *
 nf_ct_find_expectation(struct net *net, u16 zone,
 		       const struct nf_conntrack_tuple *tuple);
 
-void nf_ct_unlink_expect(struct nf_conntrack_expect *exp);
+void nf_ct_unlink_expect_report(struct nf_conntrack_expect *exp,
+				u32 pid, int report);
+static inline void nf_ct_unlink_expect(struct nf_conntrack_expect *exp)
+{
+	nf_ct_unlink_expect_report(exp, 0, 0);
+}
+
 void nf_ct_remove_expectations(struct nf_conn *ct);
 void nf_ct_unexpect_related(struct nf_conntrack_expect *exp);
+void nf_ct_remove_userspace_expectations(void);
 
 /* Allocate space for an expectation: this is mandatory before calling
    nf_ct_expect_related.  You will have to call put afterwards. */
diff --git a/include/net/netfilter/nf_conntrack_extend.h b/include/net/netfilter/nf_conntrack_extend.h
index 32d15bd6efa3..0772d296dfdb 100644
--- a/include/net/netfilter/nf_conntrack_extend.h
+++ b/include/net/netfilter/nf_conntrack_extend.h
@@ -28,9 +28,14 @@ struct nf_ct_ext {
 	char data[0];
 };
 
-static inline int nf_ct_ext_exist(const struct nf_conn *ct, u8 id)
+static inline bool __nf_ct_ext_exist(const struct nf_ct_ext *ext, u8 id)
 {
-	return (ct->ext && ct->ext->offset[id]);
+	return !!ext->offset[id];
+}
+
+static inline bool nf_ct_ext_exist(const struct nf_conn *ct, u8 id)
+{
+	return (ct->ext && __nf_ct_ext_exist(ct->ext, id));
 }
 
 static inline void *__nf_ct_ext_find(const struct nf_conn *ct, u8 id)
diff --git a/include/net/netfilter/nf_nat_protocol.h b/include/net/netfilter/nf_nat_protocol.h
index c398017ccfa3..93cc90d28e66 100644
--- a/include/net/netfilter/nf_nat_protocol.h
+++ b/include/net/netfilter/nf_nat_protocol.h
@@ -27,9 +27,9 @@ struct nf_nat_protocol {
 
 	/* Alter the per-proto part of the tuple (depending on
 	   maniptype), to give a unique tuple in the given range if
-	   possible; return false if not.  Per-protocol part of tuple
-	   is initialized to the incoming packet. */
-	bool (*unique_tuple)(struct nf_conntrack_tuple *tuple,
+	   possible.  Per-protocol part of tuple is initialized to the
+	   incoming packet. */
+	void (*unique_tuple)(struct nf_conntrack_tuple *tuple,
 			     const struct nf_nat_range *range,
 			     enum nf_nat_manip_type maniptype,
 			     const struct nf_conn *ct);
@@ -45,9 +45,6 @@ struct nf_nat_protocol {
 extern int nf_nat_protocol_register(const struct nf_nat_protocol *proto);
 extern void nf_nat_protocol_unregister(const struct nf_nat_protocol *proto);
 
-extern const struct nf_nat_protocol *nf_nat_proto_find_get(u_int8_t protocol);
-extern void nf_nat_proto_put(const struct nf_nat_protocol *proto);
-
 /* Built-in protocols. */
 extern const struct nf_nat_protocol nf_nat_protocol_tcp;
 extern const struct nf_nat_protocol nf_nat_protocol_udp;
@@ -63,7 +60,7 @@ extern bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple,
 				  const union nf_conntrack_man_proto *min,
 				  const union nf_conntrack_man_proto *max);
 
-extern bool nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
+extern void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 				      const struct nf_nat_range *range,
 				      enum nf_nat_manip_type maniptype,
 				      const struct nf_conn *ct,
diff --git a/include/net/netfilter/nf_nat_rule.h b/include/net/netfilter/nf_nat_rule.h
index e4a18ae361c6..2890bdc4cd92 100644
--- a/include/net/netfilter/nf_nat_rule.h
+++ b/include/net/netfilter/nf_nat_rule.h
@@ -12,6 +12,4 @@ extern int nf_nat_rule_find(struct sk_buff *skb,
 			    const struct net_device *out,
 			    struct nf_conn *ct);
 
-extern unsigned int
-alloc_null_binding(struct nf_conn *ct, unsigned int hooknum);
 #endif /* _NF_NAT_RULE_H */
diff --git a/include/net/netfilter/nf_tproxy_core.h b/include/net/netfilter/nf_tproxy_core.h
index 208b46f4d6d2..cd85b3bc8327 100644
--- a/include/net/netfilter/nf_tproxy_core.h
+++ b/include/net/netfilter/nf_tproxy_core.h
@@ -5,15 +5,201 @@
 #include <linux/in.h>
 #include <linux/skbuff.h>
 #include <net/sock.h>
-#include <net/inet_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 */
-extern struct sock *
+
+
+/* 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, bool listening);
+		      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,
+						    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 defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+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,
+						   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
 
 static inline void
 nf_tproxy_put_sock(struct sock *sk)
diff --git a/include/net/netfilter/nfnetlink_log.h b/include/net/netfilter/nfnetlink_log.h
index b0569ff0775e..e2dec42c2db2 100644
--- a/include/net/netfilter/nfnetlink_log.h
+++ b/include/net/netfilter/nfnetlink_log.h
@@ -10,5 +10,7 @@ nfulnl_log_packet(u_int8_t pf,
 		  const struct nf_loginfo *li_user,
 		  const char *prefix);
 
+#define NFULNL_COPY_DISABLED    0xff
+
 #endif /* _KER_NFNETLINK_LOG_H */
 
diff --git a/include/net/netfilter/xt_log.h b/include/net/netfilter/xt_log.h
new file mode 100644
index 000000000000..0dfb34a5b53c
--- /dev/null
+++ b/include/net/netfilter/xt_log.h
@@ -0,0 +1,54 @@
+#define S_SIZE (1024 - (sizeof(unsigned int) + 1))
+
+struct sbuff {
+	unsigned int	count;
+	char		buf[S_SIZE + 1];
+};
+static struct sbuff emergency, *emergency_ptr = &emergency;
+
+static int sb_add(struct sbuff *m, const char *f, ...)
+{
+	va_list args;
+	int len;
+
+	if (likely(m->count < S_SIZE)) {
+		va_start(args, f);
+		len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args);
+		va_end(args);
+		if (likely(m->count + len < S_SIZE)) {
+			m->count += len;
+			return 0;
+		}
+	}
+	m->count = S_SIZE;
+	printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n");
+	return -1;
+}
+
+static struct sbuff *sb_open(void)
+{
+	struct sbuff *m = kmalloc(sizeof(*m), GFP_ATOMIC);
+
+	if (unlikely(!m)) {
+		local_bh_disable();
+		do {
+			m = xchg(&emergency_ptr, NULL);
+		} while (!m);
+	}
+	m->count = 0;
+	return m;
+}
+
+static void sb_close(struct sbuff *m)
+{
+	m->buf[m->count] = 0;
+	printk("%s\n", m->buf);
+
+	if (likely(m != &emergency))
+		kfree(m);
+	else {
+		xchg(&emergency_ptr, m);
+		local_bh_enable();
+	}
+}
+
diff --git a/include/net/netfilter/xt_rateest.h b/include/net/netfilter/xt_rateest.h
index ddbf37e19616..5a2978d1cb22 100644
--- a/include/net/netfilter/xt_rateest.h
+++ b/include/net/netfilter/xt_rateest.h
@@ -2,13 +2,18 @@
 #define _XT_RATEEST_H
 
 struct xt_rateest {
+	/* keep lock and bstats on same cache line to speedup xt_rateest_tg() */
+	struct gnet_stats_basic_packed	bstats;
+	spinlock_t			lock;
+	/* keep rstats and lock on same cache line to speedup xt_rateest_mt() */
+	struct gnet_stats_rate_est	rstats;
+
+	/* following fields not accessed in hot path */
 	struct hlist_node		list;
 	char				name[IFNAMSIZ];
 	unsigned int			refcnt;
-	spinlock_t			lock;
 	struct gnet_estimator		params;
-	struct gnet_stats_rate_est	rstats;
-	struct gnet_stats_basic_packed	bstats;
+	struct rcu_head			rcu;
 };
 
 extern struct xt_rateest *xt_rateest_lookup(const char *name);