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 fixes for you net tree,
they are:

1) There was a race condition between parallel save/swap and delete,
   which resulted a kernel crash due to the increase ref for save, swap,
   wrong ref decrease operations. Reported and fixed by Vishwanath Pai.

2) OVS should call into CT NAT for packets of new expected connections only
   when the conntrack state is persisted with the 'commit' option to the
   OVS CT action. From Jarno Rajahalme.

3) Resolve kconfig dependencies with new OVS NAT support. From Arnd Bergmann.

4) Early validation of entry->target_offset to make sure it doesn't take us
   out from the blob, from Florian Westphal.

5) Again early validation of entry->next_offset to make sure it doesn't take
   out from the blob, also from Florian.

6) Check that entry->target_offset is always of of sizeof(struct xt_entry)
   for unconditional entries, when checking both from check_underflow()
   and when checking for loops in mark_source_chains(), again from
   Florian.

7) Fix inconsistent behaviour in nfnetlink_queue when
   NFQA_CFG_F_FAIL_OPEN is set and netlink_unicast() fails due to buffer
   overrun, we have to reinject the packet as the user expects.

8) Enforce nul-terminated table names from getsockopt GET_ENTRIES
   requests.

9) Don't assume skb->sk is set from nft_bridge_reject and synproxy,
   this fixes a recent update of the code to namespaceify
   ip_default_ttl, patch from Liping Zhang.

This batch comes with four patches to validate x_tables blobs coming
from userspace. CONFIG_USERNS exposes the x_tables interface to
unpriviledged users and to be honest this interface never received the
attention for this move away from the CAP_NET_ADMIN domain. Florian is
working on another round with more patches with more sanity checks, so
expect a bit more Netfilter fixes in this development cycle than usual.
====================

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

2 files changed, 14 insertions, 11 deletions

diff --git a/net/openvswitch/Kconfig b/net/openvswitch/Kconfig
index 234a73344c6e..ce947292ae77 100644
--- a/net/openvswitch/Kconfig
+++ b/net/openvswitch/Kconfig
@@ -7,7 +7,9 @@ config OPENVSWITCH
 	depends on INET
 	depends on !NF_CONNTRACK || \
 		   (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \
-				     (!NF_NAT || NF_NAT)))
+				     (!NF_NAT || NF_NAT) && \
+				     (!NF_NAT_IPV4 || NF_NAT_IPV4) && \
+				     (!NF_NAT_IPV6 || NF_NAT_IPV6)))
 	select LIBCRC32C
 	select MPLS
 	select NET_MPLS_GSO
diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c
index f8a8d4390a8a..1b9d286756be 100644
--- a/net/openvswitch/conntrack.c
+++ b/net/openvswitch/conntrack.c
@@ -535,14 +535,15 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 	switch (ctinfo) {
 	case IP_CT_RELATED:
 	case IP_CT_RELATED_REPLY:
-		if (skb->protocol == htons(ETH_P_IP) &&
+		if (IS_ENABLED(CONFIG_NF_NAT_IPV4) &&
+		    skb->protocol == htons(ETH_P_IP) &&
 		    ip_hdr(skb)->protocol == IPPROTO_ICMP) {
 			if (!nf_nat_icmp_reply_translation(skb, ct, ctinfo,
 							   hooknum))
 				err = NF_DROP;
 			goto push;
-#if IS_ENABLED(CONFIG_NF_NAT_IPV6)
-		} else if (skb->protocol == htons(ETH_P_IPV6)) {
+		} else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) &&
+			   skb->protocol == htons(ETH_P_IPV6)) {
 			__be16 frag_off;
 			u8 nexthdr = ipv6_hdr(skb)->nexthdr;
 			int hdrlen = ipv6_skip_exthdr(skb,
@@ -557,7 +558,6 @@ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct,
 					err = NF_DROP;
 				goto push;
 			}
-#endif
 		}
 		/* Non-ICMP, fall thru to initialize if needed. */
 	case IP_CT_NEW:
@@ -664,11 +664,12 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key,
 
 	/* Determine NAT type.
 	 * Check if the NAT type can be deduced from the tracked connection.
-	 * Make sure expected traffic is NATted only when committing.
+	 * Make sure new expected connections (IP_CT_RELATED) are NATted only
+	 * when committing.
 	 */
 	if (info->nat & OVS_CT_NAT && ctinfo != IP_CT_NEW &&
 	    ct->status & IPS_NAT_MASK &&
-	    (!(ct->status & IPS_EXPECTED_BIT) || info->commit)) {
+	    (ctinfo != IP_CT_RELATED || info->commit)) {
 		/* NAT an established or related connection like before. */
 		if (CTINFO2DIR(ctinfo) == IP_CT_DIR_REPLY)
 			/* This is the REPLY direction for a connection
@@ -1239,7 +1240,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
 	}
 
 	if (info->range.flags & NF_NAT_RANGE_MAP_IPS) {
-		if (info->family == NFPROTO_IPV4) {
+		if (IS_ENABLED(CONFIG_NF_NAT_IPV4) &&
+		    info->family == NFPROTO_IPV4) {
 			if (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MIN,
 					    info->range.min_addr.ip) ||
 			    (info->range.max_addr.ip
@@ -1247,8 +1249,8 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
 			     (nla_put_in_addr(skb, OVS_NAT_ATTR_IP_MAX,
 					      info->range.max_addr.ip))))
 				return false;
-#if IS_ENABLED(CONFIG_NF_NAT_IPV6)
-		} else if (info->family == NFPROTO_IPV6) {
+		} else if (IS_ENABLED(CONFIG_NF_NAT_IPV6) &&
+			   info->family == NFPROTO_IPV6) {
 			if (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MIN,
 					     &info->range.min_addr.in6) ||
 			    (memcmp(&info->range.max_addr.in6,
@@ -1257,7 +1259,6 @@ static bool ovs_ct_nat_to_attr(const struct ovs_conntrack_info *info,
 			     (nla_put_in6_addr(skb, OVS_NAT_ATTR_IP_MAX,
 					       &info->range.max_addr.in6))))
 				return false;
-#endif
 		} else {
 			return false;
 		}