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

24 files changed, 1177 insertions, 240 deletions

diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index c2bac9cd0caf..2562d05dbaf5 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -357,6 +357,45 @@ config NETFILTER_XT_TARGET_DSCP
 
 	  To compile it as a module, choose M here.  If unsure, say N.
 
+config NETFILTER_XT_TARGET_HL
+	tristate '"HL" hoplimit target support'
+	depends on IP_NF_MANGLE || IP6_NF_MANGLE
+	depends on NETFILTER_ADVANCED
+	---help---
+	This option adds the "HL" (for IPv6) and "TTL" (for IPv4)
+	targets, which enable the user to change the
+	hoplimit/time-to-live value of the IP header.
+
+	While it is safe to decrement the hoplimit/TTL value, the
+	modules also allow to increment and set the hoplimit value of
+	the header to arbitrary values. This is EXTREMELY DANGEROUS
+	since you can easily create immortal packets that loop
+	forever on the network.
+
+config NETFILTER_XT_TARGET_LED
+	tristate '"LED" target support'
+	depends on LEDS_CLASS
+	depends on NETFILTER_ADVANCED
+	help
+	  This option adds a `LED' target, which allows you to blink LEDs in
+	  response to particular packets passing through your machine.
+
+	  This can be used to turn a spare LED into a network activity LED,
+	  which only flashes in response to FTP transfers, for example.  Or
+	  you could have an LED which lights up for a minute or two every time
+	  somebody connects to your machine via SSH.
+
+	  You will need support for the "led" class to make this work.
+
+	  To create an LED trigger for incoming SSH traffic:
+	    iptables -A INPUT -p tcp --dport 22 -j LED --led-trigger-id ssh --led-delay 1000
+
+	  Then attach the new trigger to an LED on your system:
+	    echo netfilter-ssh > /sys/class/leds/<ledname>/trigger
+
+	  For more information on the LEDs available on your system, see
+	  Documentation/leds-class.txt
+
 config NETFILTER_XT_TARGET_MARK
 	tristate '"MARK" target support'
 	default m if NETFILTER_ADVANCED=n
@@ -488,6 +527,22 @@ config NETFILTER_XT_TARGET_TCPOPTSTRIP
 	  This option adds a "TCPOPTSTRIP" target, which allows you to strip
 	  TCP options from TCP packets.
 
+config NETFILTER_XT_MATCH_CLUSTER
+	tristate '"cluster" match support'
+	depends on NF_CONNTRACK
+	depends on NETFILTER_ADVANCED
+	---help---
+	  This option allows you to build work-load-sharing clusters of
+	  network servers/stateful firewalls without having a dedicated
+	  load-balancing router/server/switch. Basically, this match returns
+	  true when the packet must be handled by this cluster node. Thus,
+	  all nodes see all packets and this match decides which node handles
+	  what packets. The work-load sharing algorithm is based on source
+	  address hashing.
+
+	  If you say Y or M here, try `iptables -m cluster --help` for
+	  more information.
+
 config NETFILTER_XT_MATCH_COMMENT
 	tristate  '"comment" match support'
 	depends on NETFILTER_ADVANCED
@@ -605,6 +660,14 @@ config NETFILTER_XT_MATCH_HELPER
 
 	  To compile it as a module, choose M here.  If unsure, say Y.
 
+config NETFILTER_XT_MATCH_HL
+	tristate '"hl" hoplimit/TTL match support'
+	depends on NETFILTER_ADVANCED
+	---help---
+	HL matching allows you to match packets based on the hoplimit
+	in the IPv6 header, or the time-to-live field in the IPv4
+	header of the packet.
+
 config NETFILTER_XT_MATCH_IPRANGE
 	tristate '"iprange" address range match support'
 	depends on NETFILTER_ADVANCED
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index da3d909e053f..6282060fbda9 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -45,6 +45,8 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_CLASSIFY) += xt_CLASSIFY.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CONNMARK) += xt_CONNMARK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_CONNSECMARK) += xt_CONNSECMARK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_DSCP) += xt_DSCP.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_HL) += xt_HL.o
+obj-$(CONFIG_NETFILTER_XT_TARGET_LED) += xt_LED.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_MARK) += xt_MARK.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_NFLOG) += xt_NFLOG.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_NFQUEUE) += xt_NFQUEUE.o
@@ -57,6 +59,7 @@ obj-$(CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP) += xt_TCPOPTSTRIP.o
 obj-$(CONFIG_NETFILTER_XT_TARGET_TRACE) += xt_TRACE.o
 
 # matches
+obj-$(CONFIG_NETFILTER_XT_MATCH_CLUSTER) += xt_cluster.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_COMMENT) += xt_comment.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CONNBYTES) += xt_connbytes.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_CONNLIMIT) += xt_connlimit.o
@@ -67,6 +70,7 @@ obj-$(CONFIG_NETFILTER_XT_MATCH_DSCP) += xt_dscp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_ESP) += xt_esp.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HASHLIMIT) += xt_hashlimit.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_HELPER) += xt_helper.o
+obj-$(CONFIG_NETFILTER_XT_MATCH_HL) += xt_hl.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_IPRANGE) += xt_iprange.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_LENGTH) += xt_length.o
 obj-$(CONFIG_NETFILTER_XT_MATCH_LIMIT) += xt_limit.o
diff --git a/net/netfilter/core.c b/net/netfilter/core.c
index a90ac83c5918..5bb34737501f 100644
--- a/net/netfilter/core.c
+++ b/net/netfilter/core.c
@@ -174,7 +174,6 @@ next_hook:
 			     outdev, &elem, okfn, hook_thresh);
 	if (verdict == NF_ACCEPT || verdict == NF_STOP) {
 		ret = 1;
-		goto unlock;
 	} else if (verdict == NF_DROP) {
 		kfree_skb(skb);
 		ret = -EPERM;
@@ -183,7 +182,6 @@ next_hook:
 			      verdict >> NF_VERDICT_BITS))
 			goto next_hook;
 	}
-unlock:
 	rcu_read_unlock();
 	return ret;
 }
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index f4935e344b61..dfb447b584da 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -54,7 +54,7 @@ EXPORT_SYMBOL_GPL(nf_conntrack_lock);
 unsigned int nf_conntrack_htable_size __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_htable_size);
 
-int nf_conntrack_max __read_mostly;
+unsigned int nf_conntrack_max __read_mostly;
 EXPORT_SYMBOL_GPL(nf_conntrack_max);
 
 struct nf_conn nf_conntrack_untracked __read_mostly;
@@ -472,7 +472,8 @@ struct nf_conn *nf_conntrack_alloc(struct net *net,
 	struct nf_conn *ct;
 
 	if (unlikely(!nf_conntrack_hash_rnd_initted)) {
-		get_random_bytes(&nf_conntrack_hash_rnd, 4);
+		get_random_bytes(&nf_conntrack_hash_rnd,
+				sizeof(nf_conntrack_hash_rnd));
 		nf_conntrack_hash_rnd_initted = 1;
 	}
 
@@ -516,16 +517,17 @@ EXPORT_SYMBOL_GPL(nf_conntrack_alloc);
 static void nf_conntrack_free_rcu(struct rcu_head *head)
 {
 	struct nf_conn *ct = container_of(head, struct nf_conn, rcu);
-	struct net *net = nf_ct_net(ct);
 
 	nf_ct_ext_free(ct);
 	kmem_cache_free(nf_conntrack_cachep, ct);
-	atomic_dec(&net->ct.count);
 }
 
 void nf_conntrack_free(struct nf_conn *ct)
 {
+	struct net *net = nf_ct_net(ct);
+
 	nf_ct_ext_destroy(ct);
+	atomic_dec(&net->ct.count);
 	call_rcu(&ct->rcu, nf_conntrack_free_rcu);
 }
 EXPORT_SYMBOL_GPL(nf_conntrack_free);
@@ -733,6 +735,8 @@ nf_conntrack_in(struct net *net, u_int8_t pf, unsigned int hooknum,
 		nf_conntrack_put(skb->nfct);
 		skb->nfct = NULL;
 		NF_CT_STAT_INC_ATOMIC(net, invalid);
+		if (ret == -NF_DROP)
+			NF_CT_STAT_INC_ATOMIC(net, drop);
 		return -ret;
 	}
 
@@ -1103,7 +1107,7 @@ int nf_conntrack_set_hashsize(const char *val, struct kernel_param *kp)
 
 	/* We have to rehahs for the new table anyway, so we also can
 	 * use a newrandom seed */
-	get_random_bytes(&rnd, 4);
+	get_random_bytes(&rnd, sizeof(rnd));
 
 	/* Lookups in the old hash might happen in parallel, which means we
 	 * might get false negatives during connection lookup. New connections
diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c
index 3a8a34a6d37c..357ba39d4c8d 100644
--- a/net/netfilter/nf_conntrack_expect.c
+++ b/net/netfilter/nf_conntrack_expect.c
@@ -72,7 +72,8 @@ static unsigned int nf_ct_expect_dst_hash(const struct nf_conntrack_tuple *tuple
 	unsigned int hash;
 
 	if (unlikely(!nf_ct_expect_hash_rnd_initted)) {
-		get_random_bytes(&nf_ct_expect_hash_rnd, 4);
+		get_random_bytes(&nf_ct_expect_hash_rnd,
+				 sizeof(nf_ct_expect_hash_rnd));
 		nf_ct_expect_hash_rnd_initted = 1;
 	}
 
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index ed6d873ad384..7a16bd462f82 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -518,6 +518,7 @@ static int ctnetlink_conntrack_event(struct notifier_block *this,
 nla_put_failure:
 	rcu_read_unlock();
 nlmsg_failure:
+	nfnetlink_set_err(0, group, -ENOBUFS);
 	kfree_skb(skb);
 	return NOTIFY_DONE;
 }
@@ -599,7 +600,8 @@ ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple)
 
 	nla_parse_nested(tb, CTA_IP_MAX, attr, NULL);
 
-	l3proto = nf_ct_l3proto_find_get(tuple->src.l3num);
+	rcu_read_lock();
+	l3proto = __nf_ct_l3proto_find(tuple->src.l3num);
 
 	if (likely(l3proto->nlattr_to_tuple)) {
 		ret = nla_validate_nested(attr, CTA_IP_MAX,
@@ -608,7 +610,7 @@ ctnetlink_parse_tuple_ip(struct nlattr *attr, struct nf_conntrack_tuple *tuple)
 			ret = l3proto->nlattr_to_tuple(tb, tuple);
 	}
 
-	nf_ct_l3proto_put(l3proto);
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -633,7 +635,8 @@ ctnetlink_parse_tuple_proto(struct nlattr *attr,
 		return -EINVAL;
 	tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]);
 
-	l4proto = nf_ct_l4proto_find_get(tuple->src.l3num, tuple->dst.protonum);
+	rcu_read_lock();
+	l4proto = __nf_ct_l4proto_find(tuple->src.l3num, tuple->dst.protonum);
 
 	if (likely(l4proto->nlattr_to_tuple)) {
 		ret = nla_validate_nested(attr, CTA_PROTO_MAX,
@@ -642,7 +645,7 @@ ctnetlink_parse_tuple_proto(struct nlattr *attr,
 			ret = l4proto->nlattr_to_tuple(tb, tuple);
 	}
 
-	nf_ct_l4proto_put(l4proto);
+	rcu_read_unlock();
 
 	return ret;
 }
@@ -989,10 +992,11 @@ ctnetlink_change_protoinfo(struct nf_conn *ct, struct nlattr *cda[])
 
 	nla_parse_nested(tb, CTA_PROTOINFO_MAX, attr, NULL);
 
-	l4proto = nf_ct_l4proto_find_get(nf_ct_l3num(ct), nf_ct_protonum(ct));
+	rcu_read_lock();
+	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
 	if (l4proto->from_nlattr)
 		err = l4proto->from_nlattr(tb, ct);
-	nf_ct_l4proto_put(l4proto);
+	rcu_read_unlock();
 
 	return err;
 }
@@ -1062,6 +1066,10 @@ ctnetlink_change_conntrack(struct nf_conn *ct, struct nlattr *cda[])
 {
 	int err;
 
+	/* only allow NAT changes and master assignation for new conntracks */
+	if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST] || cda[CTA_TUPLE_MASTER])
+		return -EOPNOTSUPP;
+
 	if (cda[CTA_HELP]) {
 		err = ctnetlink_change_helper(ct, cda);
 		if (err < 0)
@@ -1124,13 +1132,11 @@ ctnetlink_event_report(struct nf_conn *ct, u32 pid, int report)
 				  report);
 }
 
-static int
+static struct nf_conn *
 ctnetlink_create_conntrack(struct nlattr *cda[],
 			   struct nf_conntrack_tuple *otuple,
 			   struct nf_conntrack_tuple *rtuple,
-			   struct nf_conn *master_ct,
-			   u32 pid,
-			   int report)
+			   u8 u3)
 {
 	struct nf_conn *ct;
 	int err = -EINVAL;
@@ -1138,10 +1144,10 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
 
 	ct = nf_conntrack_alloc(&init_net, otuple, rtuple, GFP_ATOMIC);
 	if (IS_ERR(ct))
-		return -ENOMEM;
+		return ERR_PTR(-ENOMEM);
 
 	if (!cda[CTA_TIMEOUT])
-		goto err;
+		goto err1;
 	ct->timeout.expires = ntohl(nla_get_be32(cda[CTA_TIMEOUT]));
 
 	ct->timeout.expires = jiffies + ct->timeout.expires * HZ;
@@ -1152,10 +1158,8 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
  		char *helpname;
  
  		err = ctnetlink_parse_help(cda[CTA_HELP], &helpname);
- 		if (err < 0) {
-			rcu_read_unlock();
-			goto err;
-		}
+ 		if (err < 0)
+			goto err2;
 
 		helper = __nf_conntrack_helper_find_byname(helpname);
 		if (helper == NULL) {
@@ -1163,28 +1167,26 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
 #ifdef CONFIG_MODULES
 			if (request_module("nfct-helper-%s", helpname) < 0) {
 				err = -EOPNOTSUPP;
-				goto err;
+				goto err1;
 			}
 
 			rcu_read_lock();
 			helper = __nf_conntrack_helper_find_byname(helpname);
 			if (helper) {
-				rcu_read_unlock();
 				err = -EAGAIN;
-				goto err;
+				goto err2;
 			}
 			rcu_read_unlock();
 #endif
 			err = -EOPNOTSUPP;
-			goto err;
+			goto err1;
 		} else {
 			struct nf_conn_help *help;
 
 			help = nf_ct_helper_ext_add(ct, GFP_ATOMIC);
 			if (help == NULL) {
-				rcu_read_unlock();
 				err = -ENOMEM;
-				goto err;
+				goto err2;
 			}
 
 			/* not in hash table yet so not strictly necessary */
@@ -1193,44 +1195,34 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
 	} else {
 		/* try an implicit helper assignation */
 		err = __nf_ct_try_assign_helper(ct, GFP_ATOMIC);
-		if (err < 0) {
-			rcu_read_unlock();
-			goto err;
-		}
+		if (err < 0)
+			goto err2;
 	}
 
 	if (cda[CTA_STATUS]) {
 		err = ctnetlink_change_status(ct, cda);
-		if (err < 0) {
-			rcu_read_unlock();
-			goto err;
-		}
+		if (err < 0)
+			goto err2;
 	}
 
 	if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
 		err = ctnetlink_change_nat(ct, cda);
-		if (err < 0) {
-			rcu_read_unlock();
-			goto err;
-		}
+		if (err < 0)
+			goto err2;
 	}
 
 #ifdef CONFIG_NF_NAT_NEEDED
 	if (cda[CTA_NAT_SEQ_ADJ_ORIG] || cda[CTA_NAT_SEQ_ADJ_REPLY]) {
 		err = ctnetlink_change_nat_seq_adj(ct, cda);
-		if (err < 0) {
-			rcu_read_unlock();
-			goto err;
-		}
+		if (err < 0)
+			goto err2;
 	}
 #endif
 
 	if (cda[CTA_PROTOINFO]) {
 		err = ctnetlink_change_protoinfo(ct, cda);
-		if (err < 0) {
-			rcu_read_unlock();
-			goto err;
-		}
+		if (err < 0)
+			goto err2;
 	}
 
 	nf_ct_acct_ext_add(ct, GFP_ATOMIC);
@@ -1241,23 +1233,37 @@ ctnetlink_create_conntrack(struct nlattr *cda[],
 #endif
 
 	/* setup master conntrack: this is a confirmed expectation */
-	if (master_ct) {
+	if (cda[CTA_TUPLE_MASTER]) {
+		struct nf_conntrack_tuple master;
+		struct nf_conntrack_tuple_hash *master_h;
+		struct nf_conn *master_ct;
+
+		err = ctnetlink_parse_tuple(cda, &master, CTA_TUPLE_MASTER, u3);
+		if (err < 0)
+			goto err2;
+
+		master_h = __nf_conntrack_find(&init_net, &master);
+		if (master_h == NULL) {
+			err = -ENOENT;
+			goto err2;
+		}
+		master_ct = nf_ct_tuplehash_to_ctrack(master_h);
+		nf_conntrack_get(&master_ct->ct_general);
 		__set_bit(IPS_EXPECTED_BIT, &ct->status);
 		ct->master = master_ct;
 	}
 
-	nf_conntrack_get(&ct->ct_general);
 	add_timer(&ct->timeout);
 	nf_conntrack_hash_insert(ct);
 	rcu_read_unlock();
-	ctnetlink_event_report(ct, pid, report);
-	nf_ct_put(ct);
 
-	return 0;
+	return ct;
 
-err:
+err2:
+	rcu_read_unlock();
+err1:
 	nf_conntrack_free(ct);
-	return err;
+	return ERR_PTR(err);
 }
 
 static int
@@ -1289,38 +1295,25 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 		h = __nf_conntrack_find(&init_net, &rtuple);
 
 	if (h == NULL) {
-		struct nf_conntrack_tuple master;
-		struct nf_conntrack_tuple_hash *master_h = NULL;
-		struct nf_conn *master_ct = NULL;
-
-		if (cda[CTA_TUPLE_MASTER]) {
-			err = ctnetlink_parse_tuple(cda,
-						    &master,
-						    CTA_TUPLE_MASTER,
-						    u3);
-			if (err < 0)
-				goto out_unlock;
+		err = -ENOENT;
+		if (nlh->nlmsg_flags & NLM_F_CREATE) {
+			struct nf_conn *ct;
 
-			master_h = __nf_conntrack_find(&init_net, &master);
-			if (master_h == NULL) {
-				err = -ENOENT;
+			ct = ctnetlink_create_conntrack(cda, &otuple,
+							&rtuple, u3);
+			if (IS_ERR(ct)) {
+				err = PTR_ERR(ct);
 				goto out_unlock;
 			}
-			master_ct = nf_ct_tuplehash_to_ctrack(master_h);
-			nf_conntrack_get(&master_ct->ct_general);
-		}
-
-		err = -ENOENT;
-		if (nlh->nlmsg_flags & NLM_F_CREATE)
-			err = ctnetlink_create_conntrack(cda,
-							 &otuple,
-							 &rtuple,
-							 master_ct,
-							 NETLINK_CB(skb).pid,
-							 nlmsg_report(nlh));
-		spin_unlock_bh(&nf_conntrack_lock);
-		if (err < 0 && master_ct)
-			nf_ct_put(master_ct);
+			err = 0;
+			nf_conntrack_get(&ct->ct_general);
+			spin_unlock_bh(&nf_conntrack_lock);
+			ctnetlink_event_report(ct,
+					       NETLINK_CB(skb).pid,
+					       nlmsg_report(nlh));
+			nf_ct_put(ct);
+		} else
+			spin_unlock_bh(&nf_conntrack_lock);
 
 		return err;
 	}
@@ -1332,17 +1325,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
 	if (!(nlh->nlmsg_flags & NLM_F_EXCL)) {
 		struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h);
 
-		/* we only allow nat config for new conntracks */
-		if (cda[CTA_NAT_SRC] || cda[CTA_NAT_DST]) {
-			err = -EOPNOTSUPP;
-			goto out_unlock;
-		}
-		/* can't link an existing conntrack to a master */
-		if (cda[CTA_TUPLE_MASTER]) {
-			err = -EOPNOTSUPP;
-			goto out_unlock;
-		}
-
 		err = ctnetlink_change_conntrack(ct, cda);
 		if (err == 0) {
 			nf_conntrack_get(&ct->ct_general);
@@ -1533,6 +1515,7 @@ static int ctnetlink_expect_event(struct notifier_block *this,
 nla_put_failure:
 	rcu_read_unlock();
 nlmsg_failure:
+	nfnetlink_set_err(0, 0, -ENOBUFS);
 	kfree_skb(skb);
 	return NOTIFY_DONE;
 }
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index 592d73344d46..9a62b4efa0e1 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -74,27 +74,6 @@ EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find);
 
 /* this is guaranteed to always return a valid protocol helper, since
  * it falls back to generic_protocol */
-struct nf_conntrack_l4proto *
-nf_ct_l4proto_find_get(u_int16_t l3proto, u_int8_t l4proto)
-{
-	struct nf_conntrack_l4proto *p;
-
-	rcu_read_lock();
-	p = __nf_ct_l4proto_find(l3proto, l4proto);
-	if (!try_module_get(p->me))
-		p = &nf_conntrack_l4proto_generic;
-	rcu_read_unlock();
-
-	return p;
-}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_find_get);
-
-void nf_ct_l4proto_put(struct nf_conntrack_l4proto *p)
-{
-	module_put(p->me);
-}
-EXPORT_SYMBOL_GPL(nf_ct_l4proto_put);
-
 struct nf_conntrack_l3proto *
 nf_ct_l3proto_find_get(u_int16_t l3proto)
 {
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
index 8fcf1762fabf..d3d5a7fd73ce 100644
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ b/net/netfilter/nf_conntrack_proto_dccp.c
@@ -16,6 +16,9 @@
 #include <linux/skbuff.h>
 #include <linux/dccp.h>
 
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
 #include <linux/netfilter/nfnetlink_conntrack.h>
 #include <net/netfilter/nf_conntrack.h>
 #include <net/netfilter/nf_conntrack_l4proto.h>
@@ -23,8 +26,6 @@
 
 static DEFINE_RWLOCK(dccp_lock);
 
-static int nf_ct_dccp_loose __read_mostly = 1;
-
 /* Timeouts are based on values from RFC4340:
  *
  * - REQUEST:
@@ -72,16 +73,6 @@ static int nf_ct_dccp_loose __read_mostly = 1;
 
 #define DCCP_MSL (2 * 60 * HZ)
 
-static unsigned int dccp_timeout[CT_DCCP_MAX + 1] __read_mostly = {
-	[CT_DCCP_REQUEST]	= 2 * DCCP_MSL,
-	[CT_DCCP_RESPOND]	= 4 * DCCP_MSL,
-	[CT_DCCP_PARTOPEN]	= 4 * DCCP_MSL,
-	[CT_DCCP_OPEN]		= 12 * 3600 * HZ,
-	[CT_DCCP_CLOSEREQ]	= 64 * HZ,
-	[CT_DCCP_CLOSING]	= 64 * HZ,
-	[CT_DCCP_TIMEWAIT]	= 2 * DCCP_MSL,
-};
-
 static const char * const dccp_state_names[] = {
 	[CT_DCCP_NONE]		= "NONE",
 	[CT_DCCP_REQUEST]	= "REQUEST",
@@ -393,6 +384,22 @@ dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] =
 	},
 };
 
+/* this module per-net specifics */
+static int dccp_net_id;
+struct dccp_net {
+	int dccp_loose;
+	unsigned int dccp_timeout[CT_DCCP_MAX + 1];
+#ifdef CONFIG_SYSCTL
+	struct ctl_table_header *sysctl_header;
+	struct ctl_table *sysctl_table;
+#endif
+};
+
+static inline struct dccp_net *dccp_pernet(struct net *net)
+{
+	return net_generic(net, dccp_net_id);
+}
+
 static bool dccp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff,
 			      struct nf_conntrack_tuple *tuple)
 {
@@ -419,6 +426,7 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 		     unsigned int dataoff)
 {
 	struct net *net = nf_ct_net(ct);
+	struct dccp_net *dn;
 	struct dccp_hdr _dh, *dh;
 	const char *msg;
 	u_int8_t state;
@@ -429,7 +437,8 @@ static bool dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
 	state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
 	switch (state) {
 	default:
-		if (nf_ct_dccp_loose == 0) {
+		dn = dccp_pernet(net);
+		if (dn->dccp_loose == 0) {
 			msg = "nf_ct_dccp: not picking up existing connection ";
 			goto out_invalid;
 		}
@@ -465,6 +474,7 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 		       u_int8_t pf, unsigned int hooknum)
 {
 	struct net *net = nf_ct_net(ct);
+	struct dccp_net *dn;
 	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
 	struct dccp_hdr _dh, *dh;
 	u_int8_t type, old_state, new_state;
@@ -542,7 +552,9 @@ static int dccp_packet(struct nf_conn *ct, const struct sk_buff *skb,
 	ct->proto.dccp.last_pkt = type;
 	ct->proto.dccp.state = new_state;
 	write_unlock_bh(&dccp_lock);
-	nf_ct_refresh_acct(ct, ctinfo, skb, dccp_timeout[new_state]);
+
+	dn = dccp_pernet(net);
+	nf_ct_refresh_acct(ct, ctinfo, skb, dn->dccp_timeout[new_state]);
 
 	return NF_ACCEPT;
 }
@@ -660,13 +672,11 @@ static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
 #endif
 
 #ifdef CONFIG_SYSCTL
-static unsigned int dccp_sysctl_table_users;
-static struct ctl_table_header *dccp_sysctl_header;
-static ctl_table dccp_sysctl_table[] = {
+/* template, data assigned later */
+static struct ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_timeout_request",
-		.data		= &dccp_timeout[CT_DCCP_REQUEST],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -674,7 +684,6 @@ static ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_timeout_respond",
-		.data		= &dccp_timeout[CT_DCCP_RESPOND],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -682,7 +691,6 @@ static ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_timeout_partopen",
-		.data		= &dccp_timeout[CT_DCCP_PARTOPEN],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -690,7 +698,6 @@ static ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_timeout_open",
-		.data		= &dccp_timeout[CT_DCCP_OPEN],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -698,7 +705,6 @@ static ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_timeout_closereq",
-		.data		= &dccp_timeout[CT_DCCP_CLOSEREQ],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -706,7 +712,6 @@ static ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_timeout_closing",
-		.data		= &dccp_timeout[CT_DCCP_CLOSING],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -714,7 +719,6 @@ static ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_timeout_timewait",
-		.data		= &dccp_timeout[CT_DCCP_TIMEWAIT],
 		.maxlen		= sizeof(unsigned int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_jiffies,
@@ -722,8 +726,7 @@ static ctl_table dccp_sysctl_table[] = {
 	{
 		.ctl_name	= CTL_UNNUMBERED,
 		.procname	= "nf_conntrack_dccp_loose",
-		.data		= &nf_ct_dccp_loose,
-		.maxlen		= sizeof(nf_ct_dccp_loose),
+		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec,
 	},
@@ -751,11 +754,6 @@ static struct nf_conntrack_l4proto dccp_proto4 __read_mostly = {
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
 	.nla_policy		= nf_ct_port_nla_policy,
 #endif
-#ifdef CONFIG_SYSCTL
-	.ctl_table_users	= &dccp_sysctl_table_users,
-	.ctl_table_header	= &dccp_sysctl_header,
-	.ctl_table		= dccp_sysctl_table,
-#endif
 };
 
 static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
@@ -776,34 +774,107 @@ static struct nf_conntrack_l4proto dccp_proto6 __read_mostly = {
 	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
 	.nla_policy		= nf_ct_port_nla_policy,
 #endif
+};
+
+static __net_init int dccp_net_init(struct net *net)
+{
+	struct dccp_net *dn;
+	int err;
+
+	dn = kmalloc(sizeof(*dn), GFP_KERNEL);
+	if (!dn)
+		return -ENOMEM;
+
+	/* default values */
+	dn->dccp_loose = 1;
+	dn->dccp_timeout[CT_DCCP_REQUEST]	= 2 * DCCP_MSL;
+	dn->dccp_timeout[CT_DCCP_RESPOND]	= 4 * DCCP_MSL;
+	dn->dccp_timeout[CT_DCCP_PARTOPEN]	= 4 * DCCP_MSL;
+	dn->dccp_timeout[CT_DCCP_OPEN]		= 12 * 3600 * HZ;
+	dn->dccp_timeout[CT_DCCP_CLOSEREQ]	= 64 * HZ;
+	dn->dccp_timeout[CT_DCCP_CLOSING]	= 64 * HZ;
+	dn->dccp_timeout[CT_DCCP_TIMEWAIT]	= 2 * DCCP_MSL;
+
+	err = net_assign_generic(net, dccp_net_id, dn);
+	if (err)
+		goto out;
+
 #ifdef CONFIG_SYSCTL
-	.ctl_table_users	= &dccp_sysctl_table_users,
-	.ctl_table_header	= &dccp_sysctl_header,
-	.ctl_table		= dccp_sysctl_table,
+	err = -ENOMEM;
+	dn->sysctl_table = kmemdup(dccp_sysctl_table,
+			sizeof(dccp_sysctl_table), GFP_KERNEL);
+	if (!dn->sysctl_table)
+		goto out;
+
+	dn->sysctl_table[0].data = &dn->dccp_timeout[CT_DCCP_REQUEST];
+	dn->sysctl_table[1].data = &dn->dccp_timeout[CT_DCCP_RESPOND];
+	dn->sysctl_table[2].data = &dn->dccp_timeout[CT_DCCP_PARTOPEN];
+	dn->sysctl_table[3].data = &dn->dccp_timeout[CT_DCCP_OPEN];
+	dn->sysctl_table[4].data = &dn->dccp_timeout[CT_DCCP_CLOSEREQ];
+	dn->sysctl_table[5].data = &dn->dccp_timeout[CT_DCCP_CLOSING];
+	dn->sysctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT];
+	dn->sysctl_table[7].data = &dn->dccp_loose;
+
+	dn->sysctl_header = register_net_sysctl_table(net,
+			nf_net_netfilter_sysctl_path, dn->sysctl_table);
+	if (!dn->sysctl_header) {
+		kfree(dn->sysctl_table);
+		goto out;
+	}
 #endif
+
+	return 0;
+
+out:
+	kfree(dn);
+	return err;
+}
+
+static __net_exit void dccp_net_exit(struct net *net)
+{
+	struct dccp_net *dn = dccp_pernet(net);
+#ifdef CONFIG_SYSCTL
+	unregister_net_sysctl_table(dn->sysctl_header);
+	kfree(dn->sysctl_table);
+#endif
+	kfree(dn);
+
+	net_assign_generic(net, dccp_net_id, NULL);
+}
+
+static struct pernet_operations dccp_net_ops = {
+	.init = dccp_net_init,
+	.exit = dccp_net_exit,
 };
 
 static int __init nf_conntrack_proto_dccp_init(void)
 {
 	int err;
 
-	err = nf_conntrack_l4proto_register(&dccp_proto4);
+	err = register_pernet_gen_subsys(&dccp_net_id, &dccp_net_ops);
 	if (err < 0)
 		goto err1;
 
-	err = nf_conntrack_l4proto_register(&dccp_proto6);
+	err = nf_conntrack_l4proto_register(&dccp_proto4);
 	if (err < 0)
 		goto err2;
+
+	err = nf_conntrack_l4proto_register(&dccp_proto6);
+	if (err < 0)
+		goto err3;
 	return 0;
 
-err2:
+err3:
 	nf_conntrack_l4proto_unregister(&dccp_proto4);
+err2:
+	unregister_pernet_gen_subsys(dccp_net_id, &dccp_net_ops);
 err1:
 	return err;
 }
 
 static void __exit nf_conntrack_proto_dccp_fini(void)
 {
+	unregister_pernet_gen_subsys(dccp_net_id, &dccp_net_ops);
 	nf_conntrack_l4proto_unregister(&dccp_proto6);
 	nf_conntrack