Merge git://git.kernel.org/pub/scm/linux/kernel/git/pablo/nf

Pablo Neira Ayuso says:

====================
Netfilter fixes for net

The following patchset contains Netfilter updates for your net tree,
they are:

1) Dump only conntrack that belong to this namespace via /proc file.
   This is some fallout from the conversion to single conntrack table
   for all netns, patch from Liping Zhang.

2) Missing MODULE_ALIAS_NF_LOGGER() for the ARP family that prevents
   module autoloading, also from Liping Zhang.

3) Report overquota event to the right netnamespace, again from Liping.

4) Fix tproxy listener sk refcount that leads to crash, from
   Eric Dumazet.

5) Fix racy refcounting on object deletion from nfnetlink and rule
   removal both for nfacct and cttimeout, from Liping Zhang.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

6 files changed, 29 insertions, 15 deletions

diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 958a145..9f267c3 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -205,6 +205,7 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(hash);
 	const struct nf_conntrack_l3proto *l3proto;
 	const struct nf_conntrack_l4proto *l4proto;
+	struct net *net = seq_file_net(s);
 	int ret = 0;
 
 	NF_CT_ASSERT(ct);
@@ -215,6 +216,9 @@ static int ct_seq_show(struct seq_file *s, void *v)
 	if (NF_CT_DIRECTION(hash))
 		goto release;
 
+	if (!net_eq(nf_ct_net(ct), net))
+		goto release;
+
 	l3proto = __nf_ct_l3proto_find(nf_ct_l3num(ct));
 	NF_CT_ASSERT(l3proto);
 	l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), nf_ct_protonum(ct));
diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c
index 1b4de4b..70eb2f6a 100644
--- a/net/netfilter/nfnetlink_acct.c
+++ b/net/netfilter/nfnetlink_acct.c
@@ -326,14 +326,14 @@ static int nfnl_acct_try_del(struct nf_acct *cur)
 {
 	int ret = 0;
 
-	/* we want to avoid races with nfnl_acct_find_get. */
-	if (atomic_dec_and_test(&cur->refcnt)) {
+	/* We want to avoid races with nfnl_acct_put. So only when the current
+	 * refcnt is 1, we decrease it to 0.
+	 */
+	if (atomic_cmpxchg(&cur->refcnt, 1, 0) == 1) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&cur->head);
 		kfree_rcu(cur, rcu_head);
 	} else {
-		/* still in use, restore reference counter. */
-		atomic_inc(&cur->refcnt);
 		ret = -EBUSY;
 	}
 	return ret;
@@ -443,7 +443,7 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct)
 }
 EXPORT_SYMBOL_GPL(nfnl_acct_update);
 
-static void nfnl_overquota_report(struct nf_acct *nfacct)
+static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct)
 {
 	int ret;
 	struct sk_buff *skb;
@@ -458,11 +458,12 @@ static void nfnl_overquota_report(struct nf_acct *nfacct)
 		kfree_skb(skb);
 		return;
 	}
-	netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
+	netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA,
 			  GFP_ATOMIC);
 }
 
-int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct)
+int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb,
+			struct nf_acct *nfacct)
 {
 	u64 now;
 	u64 *quota;
@@ -480,7 +481,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct)
 
 	if (now >= *quota &&
 	    !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) {
-		nfnl_overquota_report(nfacct);
+		nfnl_overquota_report(net, nfacct);
 	}
 
 	return ret;
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index 4cdcd96..68216cd 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -330,16 +330,16 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout)
 {
 	int ret = 0;
 
-	/* we want to avoid races with nf_ct_timeout_find_get. */
-	if (atomic_dec_and_test(&timeout->refcnt)) {
+	/* We want to avoid races with ctnl_timeout_put. So only when the
+	 * current refcnt is 1, we decrease it to 0.
+	 */
+	if (atomic_cmpxchg(&timeout->refcnt, 1, 0) == 1) {
 		/* We are protected by nfnl mutex. */
 		list_del_rcu(&timeout->head);
 		nf_ct_l4proto_put(timeout->l4proto);
 		ctnl_untimeout(net, timeout);
 		kfree_rcu(timeout, rcu_head);
 	} else {
-		/* still in use, restore reference counter. */
-		atomic_inc(&timeout->refcnt);
 		ret = -EBUSY;
 	}
 	return ret;
@@ -543,7 +543,9 @@ err:
 
 static void ctnl_timeout_put(struct ctnl_timeout *timeout)
 {
-	atomic_dec(&timeout->refcnt);
+	if (atomic_dec_and_test(&timeout->refcnt))
+		kfree_rcu(timeout, rcu_head);
+
 	module_put(THIS_MODULE);
 }
 #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
@@ -591,7 +593,9 @@ static void __net_exit cttimeout_net_exit(struct net *net)
 	list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) {
 		list_del_rcu(&cur->head);
 		nf_ct_l4proto_put(cur->l4proto);
-		kfree_rcu(cur, rcu_head);
+
+		if (atomic_dec_and_test(&cur->refcnt))
+			kfree_rcu(cur, rcu_head);
 	}
 }
 
diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c
index cbcfdfb..6577db5 100644
--- a/net/netfilter/nfnetlink_log.c
+++ b/net/netfilter/nfnetlink_log.c
@@ -1147,6 +1147,7 @@ MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG);
 MODULE_ALIAS_NF_LOGGER(AF_INET, 1);
 MODULE_ALIAS_NF_LOGGER(AF_INET6, 1);
 MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1);
+MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */
 
 module_init(nfnetlink_log_init);
 module_exit(nfnetlink_log_fini);
diff --git a/net/netfilter/xt_TPROXY.c b/net/netfilter/xt_TPROXY.c
index 7f4414d..663c4c3 100644
--- a/net/netfilter/xt_TPROXY.c
+++ b/net/netfilter/xt_TPROXY.c
@@ -127,6 +127,8 @@ nf_tproxy_get_sock_v4(struct net *net, struct sk_buff *skb, void *hp,
 						    daddr, dport,
 						    in->ifindex);
 
+			if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+				sk = NULL;
 			/* 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
@@ -195,6 +197,8 @@ nf_tproxy_get_sock_v6(struct net *net, struct sk_buff *skb, int thoff, void *hp,
 						   daddr, ntohs(dport),
 						   in->ifindex);
 
+			if (sk && !atomic_inc_not_zero(&sk->sk_refcnt))
+				sk = NULL;
 			/* 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
diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c
index 3048a7e..cf32759 100644
--- a/net/netfilter/xt_nfacct.c
+++ b/net/netfilter/xt_nfacct.c
@@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par)
 
 	nfnl_acct_update(skb, info->nfacct);
 
-	overquota = nfnl_acct_overquota(skb, info->nfacct);
+	overquota = nfnl_acct_overquota(par->net, skb, info->nfacct);
 
 	return overquota == NFACCT_UNDERQUOTA ? false : true;
 }