openvswitch: Support conntrack zone limit

Currently, nf_conntrack_max is used to limit the maximum number of
conntrack entries in the conntrack table for every network namespace.
For the VMs and containers that reside in the same namespace,
they share the same conntrack table, and the total # of conntrack entries
for all the VMs and containers are limited by nf_conntrack_max.  In this
case, if one of the VM/container abuses the usage the conntrack entries,
it blocks the others from committing valid conntrack entries into the
conntrack table.  Even if we can possibly put the VM in different network
namespace, the current nf_conntrack_max configuration is kind of rigid
that we cannot limit different VM/container to have different # conntrack
entries.

To address the aforementioned issue, this patch proposes to have a
fine-grained mechanism that could further limit the # of conntrack entries
per-zone.  For example, we can designate different zone to different VM,
and set conntrack limit to each zone.  By providing this isolation, a
mis-behaved VM only consumes the conntrack entries in its own zone, and
it will not influence other well-behaved VMs.  Moreover, the users can
set various conntrack limit to different zone based on their preference.

The proposed implementation utilizes Netfilter's nf_conncount backend
to count the number of connections in a particular zone.  If the number of
connection is above a configured limitation, ovs will return ENOMEM to the
userspace.  If userspace does not configure the zone limit, the limit
defaults to zero that is no limitation, which is backward compatible to
the behavior without this patch.

The following high leve APIs are provided to the userspace:
  - OVS_CT_LIMIT_CMD_SET:
    * set default connection limit for all zones
    * set the connection limit for a particular zone
  - OVS_CT_LIMIT_CMD_DEL:
    * remove the connection limit for a particular zone
  - OVS_CT_LIMIT_CMD_GET:
    * get the default connection limit for all zones
    * get the connection limit for a particular zone
Signed-off-by: Yi-Hung Wei <yihung.wei@gmail.com>
Acked-by: Pravin B Shelar <pshelar@ovn.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

net/openvswitch/Kconfig

@@ -9,7 +9,8 @@ config OPENVSWITCH
 		   (NF_CONNTRACK && ((!NF_DEFRAG_IPV6 || NF_DEFRAG_IPV6) && \
 				     (!NF_NAT || NF_NAT) && \
 				     (!NF_NAT_IPV4 || NF_NAT_IPV4) && \
-				     (!NF_NAT_IPV6 || NF_NAT_IPV6)))
+				     (!NF_NAT_IPV6 || NF_NAT_IPV6) && \
+				     (!NETFILTER_CONNCOUNT || NETFILTER_CONNCOUNT)))
 	select LIBCRC32C
 	select MPLS
 	select NET_MPLS_GSO

net/openvswitch/conntrack.h

@@ -17,10 +17,11 @@
 #include "flow.h"
 
 struct ovs_conntrack_info;
+struct ovs_ct_limit_info;
 enum ovs_key_attr;
 
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-void ovs_ct_init(struct net *);
+int ovs_ct_init(struct net *);
 void ovs_ct_exit(struct net *);
 bool ovs_ct_verify(struct net *, enum ovs_key_attr attr);
 int ovs_ct_copy_action(struct net *, const struct nlattr *,
@@ -44,7 +45,7 @@ void ovs_ct_free_action(const struct nlattr *a);
 #else
 #include <linux/errno.h>
 
-static inline void ovs_ct_init(struct net *net) { }
+static inline int ovs_ct_init(struct net *net) { return 0; }
 
 static inline void ovs_ct_exit(struct net *net) { }
 
@@ -104,4 +105,8 @@ static inline void ovs_ct_free_action(const struct nlattr *a) { }
 
 #define CT_SUPPORTED_MASK 0
 #endif /* CONFIG_NF_CONNTRACK */
+
+#if IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+extern struct genl_family dp_ct_limit_genl_family;
+#endif
 #endif /* ovs_conntrack.h */

net/openvswitch/datapath.c

@@ -2288,6 +2288,9 @@ static struct genl_family * const dp_genl_families[] = {
 	&dp_flow_genl_family,
 	&dp_packet_genl_family,
 	&dp_meter_genl_family,
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+	&dp_ct_limit_genl_family,
+#endif
 };
 
 static void dp_unregister_genl(int n_families)
@@ -2323,8 +2326,7 @@ static int __net_init ovs_init_net(struct net *net)
 
 	INIT_LIST_HEAD(&ovs_net->dps);
 	INIT_WORK(&ovs_net->dp_notify_work, ovs_dp_notify_wq);
-	ovs_ct_init(net);
-	return 0;
+	return ovs_ct_init(net);
 }
 
 static void __net_exit list_vports_from_net(struct net *net, struct net *dnet,
@@ -2469,3 +2471,4 @@ MODULE_ALIAS_GENL_FAMILY(OVS_VPORT_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_FLOW_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_PACKET_FAMILY);
 MODULE_ALIAS_GENL_FAMILY(OVS_METER_FAMILY);
+MODULE_ALIAS_GENL_FAMILY(OVS_CT_LIMIT_FAMILY);

net/openvswitch/datapath.h

@@ -144,6 +144,9 @@ struct dp_upcall_info {
 struct ovs_net {
 	struct list_head dps;
 	struct work_struct dp_notify_work;
+#if	IS_ENABLED(CONFIG_NETFILTER_CONNCOUNT)
+	struct ovs_ct_limit_info *ct_limit_info;
+#endif
 
 	/* Module reference for configuring conntrack. */
 	bool xt_label;