net: split rt_genid for ipv4 and ipv6

Current net name space has only one genid for both IPv4 and IPv6, it has below
drawbacks:

- Add/delete an IPv4 address will invalidate all IPv6 routing table entries.
- Insert/remove XFRM policy will also invalidate both IPv4/IPv6 routing table
  entries even when the policy is only applied for one address family.

Thus, this patch attempt to split one genid for two to cater for IPv4 and IPv6
separately in a fine granularity.

Signed-off-by: Fan Du <fan.du@windriver.com>
Acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

include/net/net_namespace.h

@@ -119,7 +119,6 @@ struct net {
 	struct netns_ipvs	*ipvs;
 #endif
 	struct sock		*diag_nlsk;
-	atomic_t		rt_genid;
 	atomic_t		fnhe_genid;
 };
 
@@ -333,14 +332,42 @@ static inline void unregister_net_sysctl_table(struct ctl_table_header *header)
 }
 #endif
 
-static inline int rt_genid(struct net *net)
+static inline int rt_genid_ipv4(struct net *net)
 {
-	return atomic_read(&net->rt_genid);
+	return atomic_read(&net->ipv4.rt_genid);
 }
 
-static inline void rt_genid_bump(struct net *net)
+static inline void rt_genid_bump_ipv4(struct net *net)
 {
-	atomic_inc(&net->rt_genid);
+	atomic_inc(&net->ipv4.rt_genid);
+}
+
+#if IS_ENABLED(CONFIG_IPV6)
+static inline int rt_genid_ipv6(struct net *net)
+{
+	return atomic_read(&net->ipv6.rt_genid);
+}
+
+static inline void rt_genid_bump_ipv6(struct net *net)
+{
+	atomic_inc(&net->ipv6.rt_genid);
+}
+#else
+static inline int rt_genid_ipv6(struct net *net)
+{
+	return 0;
+}
+
+static inline void rt_genid_bump_ipv6(struct net *net)
+{
+}
+#endif
+
+/* For callers who don't really care about whether it's IPv4 or IPv6 */
+static inline void rt_genid_bump_all(struct net *net)
+{
+	rt_genid_bump_ipv4(net);
+	rt_genid_bump_ipv6(net);
 }
 
 static inline int fnhe_genid(struct net *net)

include/net/netns/ipv4.h

@@ -77,5 +77,6 @@ struct netns_ipv4 {
 	struct fib_rules_ops	*mr_rules_ops;
 #endif
 #endif
+	atomic_t	rt_genid;
 };
 #endif

include/net/netns/ipv6.h

@@ -72,6 +72,7 @@ struct netns_ipv6 {
 #endif
 #endif
 	atomic_t		dev_addr_genid;
+	atomic_t		rt_genid;
 };
 
 #if IS_ENABLED(CONFIG_NF_DEFRAG_IPV6)

net/ipv4/route.c

@@ -435,12 +435,12 @@ static inline int ip_rt_proc_init(void)
 
 static inline bool rt_is_expired(const struct rtable *rth)
 {
-	return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
+	return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev));
 }
 
 void rt_cache_flush(struct net *net)
 {
-	rt_genid_bump(net);
+	rt_genid_bump_ipv4(net);
 }
 
 static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
@@ -1458,7 +1458,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
 #endif
 	rth->dst.output = ip_rt_bug;
 
-	rth->rt_genid	= rt_genid(dev_net(dev));
+	rth->rt_genid	= rt_genid_ipv4(dev_net(dev));
 	rth->rt_flags	= RTCF_MULTICAST;
 	rth->rt_type	= RTN_MULTICAST;
 	rth->rt_is_input= 1;
@@ -1589,7 +1589,7 @@ static int __mkroute_input(struct sk_buff *skb,
 		goto cleanup;
 	}
 
-	rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
+	rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev));
 	rth->rt_flags = flags;
 	rth->rt_type = res->type;
 	rth->rt_is_input = 1;
@@ -1760,7 +1760,7 @@ out:	return err;
 	rth->dst.tclassid = itag;
 #endif
 
-	rth->rt_genid = rt_genid(net);
+	rth->rt_genid = rt_genid_ipv4(net);
 	rth->rt_flags 	= flags|RTCF_LOCAL;
 	rth->rt_type	= res.type;
 	rth->rt_is_input = 1;
@@ -1945,7 +1945,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 
 	rth->dst.output = ip_output;
 
-	rth->rt_genid = rt_genid(dev_net(dev_out));
+	rth->rt_genid = rt_genid_ipv4(dev_net(dev_out));
 	rth->rt_flags	= flags;
 	rth->rt_type	= type;
 	rth->rt_is_input = 0;
@@ -2227,7 +2227,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
 		rt->rt_iif = ort->rt_iif;
 		rt->rt_pmtu = ort->rt_pmtu;
 
-		rt->rt_genid = rt_genid(net);
+		rt->rt_genid = rt_genid_ipv4(net);
 		rt->rt_flags = ort->rt_flags;
 		rt->rt_type = ort->rt_type;
 		rt->rt_gateway = ort->rt_gateway;
@@ -2665,7 +2665,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
 
 static __net_init int rt_genid_init(struct net *net)
 {
-	atomic_set(&net->rt_genid, 0);
+	atomic_set(&net->ipv4.rt_genid, 0);
 	atomic_set(&net->fnhe_genid, 0);
 	get_random_bytes(&net->ipv4.dev_addr_genid,
 			 sizeof(net->ipv4.dev_addr_genid));

net/ipv6/af_inet6.c

@@ -766,6 +766,7 @@ static int __net_init inet6_net_init(struct net *net)
 
 	net->ipv6.sysctl.bindv6only = 0;
 	net->ipv6.sysctl.icmpv6_time = 1*HZ;
+	atomic_set(&net->ipv6.rt_genid, 0);
 
 	err = ipv6_init_mibs(net);
 	if (err)

net/ipv6/route.c

@@ -283,7 +283,7 @@ static inline struct rt6_info *ip6_dst_alloc(struct net *net,
 
 		memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
 		rt6_init_peer(rt, table ? &table->tb6_peers : net->ipv6.peers);
-		rt->rt6i_genid = rt_genid(net);
+		rt->rt6i_genid = rt_genid_ipv6(net);
 		INIT_LIST_HEAD(&rt->rt6i_siblings);
 	}
 	return rt;
@@ -1061,7 +1061,7 @@ static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie)
 	 * DST_OBSOLETE_FORCE_CHK which forces validation calls down
 	 * into this function always.
 	 */
-	if (rt->rt6i_genid != rt_genid(dev_net(rt->dst.dev)))
+	if (rt->rt6i_genid != rt_genid_ipv6(dev_net(rt->dst.dev)))
 		return NULL;
 
 	if (rt->rt6i_node && (rt->rt6i_node->fn_sernum == cookie))

net/xfrm/xfrm_policy.c

@@ -660,7 +660,13 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl)
 	xfrm_pol_hold(policy);
 	net->xfrm.policy_count[dir]++;
 	atomic_inc(&flow_cache_genid);
-	rt_genid_bump(net);
+
+	/* After previous checking, family can either be AF_INET or AF_INET6 */
+	if (policy->family == AF_INET)
+		rt_genid_bump_ipv4(net);
+	else
+		rt_genid_bump_ipv6(net);
+
 	if (delpol) {
 		xfrm_policy_requeue(delpol, policy);
 		__xfrm_policy_unlink(delpol, dir);

security/selinux/include/xfrm.h

@@ -50,8 +50,13 @@ int selinux_xfrm_decode_session(struct sk_buff *skb, u32 *sid, int ckall);
 
 static inline void selinux_xfrm_notify_policyload(void)
 {
+	struct net *net;
+
 	atomic_inc(&flow_cache_genid);
-	rt_genid_bump(&init_net);
+	rtnl_lock();
+	for_each_net(net)
+		rt_genid_bump_all(net);
+	rtnl_unlock();
 }
 #else
 static inline int selinux_xfrm_enabled(void)