netfilter: nf_conntrack: speed up module removal path if netns in use

The patch introduces nf_conntrack_cleanup_net_list(), which cleanups
nf_conntrack for a list of netns and calls synchronize_net() only once
for them all. This should reduce netns destruction time.

I've measured cleanup time for 1k dummy net ns. Here are the results:

 <without the patch>
 # modprobe nf_conntrack
 # time modprobe -r nf_conntrack

 real	0m10.337s
 user	0m0.000s
 sys	0m0.376s

 <with the patch>
 # modprobe nf_conntrack
 # time modprobe -r nf_conntrack

 real    0m5.661s
 user    0m0.000s
 sys     0m0.216s
Signed-off-by: Vladimir Davydov <vdavydov@parallels.com>
Cc: Patrick McHardy <kaber@trash.net>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: "Eric W. Biederman" <ebiederm@xmission.com>
Acked-by: Gao feng <gaofeng@cn.fujitsu.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>

include/net/netfilter/nf_conntrack_core.h

@@ -27,6 +27,7 @@ extern unsigned int nf_conntrack_in(struct net *net,
 
 extern int nf_conntrack_init_net(struct net *net);
 extern void nf_conntrack_cleanup_net(struct net *net);
+extern void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list);
 
 extern int nf_conntrack_proto_pernet_init(struct net *net);
 extern void nf_conntrack_proto_pernet_fini(struct net *net);

net/netfilter/nf_conntrack_core.c

@@ -1365,20 +1365,37 @@ void nf_conntrack_cleanup_end(void)
  */
 void nf_conntrack_cleanup_net(struct net *net)
 {
+	LIST_HEAD(single);
+
+	list_add(&net->exit_list, &single);
+	nf_conntrack_cleanup_net_list(&single);
+}
+
+void nf_conntrack_cleanup_net_list(struct list_head *net_exit_list)
+{
+	int busy;
+	struct net *net;
+
 	/*
 	 * This makes sure all current packets have passed through
 	 *  netfilter framework.  Roll on, two-stage module
 	 *  delete...
 	 */
 	synchronize_net();
- i_see_dead_people:
+i_see_dead_people:
+	busy = 0;
+	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_ct_iterate_cleanup(net, kill_all, NULL);
 		nf_ct_release_dying_list(net);
-	if (atomic_read(&net->ct.count) != 0) {
+		if (atomic_read(&net->ct.count) != 0)
+			busy = 1;
+	}
+	if (busy) {
 		schedule();
 		goto i_see_dead_people;
 	}
 
+	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_ct_free_hashtable(net->ct.hash, net->ct.htable_size);
 		nf_conntrack_proto_pernet_fini(net);
 		nf_conntrack_helper_pernet_fini(net);
@@ -1389,6 +1406,7 @@ void nf_conntrack_cleanup_net(struct net *net)
 		kmem_cache_destroy(net->ct.nf_conntrack_cachep);
 		kfree(net->ct.slabname);
 		free_percpu(net->ct.stat);
+	}
 }
 
 void *nf_ct_alloc_hashtable(unsigned int *sizep, int nulls)

net/netfilter/nf_conntrack_standalone.c

@@ -545,16 +545,20 @@ static int nf_conntrack_pernet_init(struct net *net)
 	return ret;
 }
 
-static void nf_conntrack_pernet_exit(struct net *net)
+static void nf_conntrack_pernet_exit(struct list_head *net_exit_list)
 {
+	struct net *net;
+
+	list_for_each_entry(net, net_exit_list, exit_list) {
 		nf_conntrack_standalone_fini_sysctl(net);
 		nf_conntrack_standalone_fini_proc(net);
-	nf_conntrack_cleanup_net(net);
+	}
+	nf_conntrack_cleanup_net_list(net_exit_list);
 }
 
 static struct pernet_operations nf_conntrack_net_ops = {
 	.init		= nf_conntrack_pernet_init,
-	.exit = nf_conntrack_pernet_exit,
+	.exit_batch	= nf_conntrack_pernet_exit,
 };
 
 static int __init nf_conntrack_standalone_init(void)