Delay struct net freeing while there's a sysfs instance refering to it

	* new refcount in struct net, controlling actual freeing of the memory
	* new method in kobj_ns_type_operations (->drop_ns())
	* ->current_ns() semantics change - it's supposed to be followed by
corresponding ->drop_ns().  For struct net in case of CONFIG_NET_NS it bumps
the new refcount; net_drop_ns() decrements it and calls net_free() if the
last reference has been dropped.  Method renamed to ->grab_current_ns().
	* old net_free() callers call net_drop_ns() instead.
	* sysfs_exit_ns() is gone, along with a large part of callchain
leading to it; now that the references stored in ->ns[...] stay valid we
do not need to hunt them down and replace them with NULL.  That fixes
problems in sysfs_lookup() and sysfs_readdir(), along with getting rid
of sb->s_instances abuse.

	Note that struct net *shutdown* logics has not changed - net_cleanup()
is called exactly when it used to be called.  The only thing postponed by
having a sysfs instance refering to that struct net is actual freeing of
memory occupied by struct net.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

1 files changed, 10 insertions, 2 deletions

diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 6c6b86d0da15..cdcbc3cb00a9 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -128,6 +128,7 @@ static __net_init int setup_net(struct net *net)
         LIST_HEAD(net_exit_list);
 
         atomic_set(&net->count, 1);
+        atomic_set(&net->passive, 1);
 
 #ifdef NETNS_REFCNT_DEBUG
         atomic_set(&net->use_count, 0);
@@ -210,6 +211,13 @@ static void net_free(struct net *net)
         kmem_cache_free(net_cachep, net);
 }
 
+void net_drop_ns(void *p)
+{
+        struct net *ns = p;
+        if (ns && atomic_dec_and_test(&ns->passive))
+                net_free(ns);
+}
+
 struct net *copy_net_ns(unsigned long flags, struct net *old_net)
 {
         struct net *net;
@@ -230,7 +238,7 @@ struct net *copy_net_ns(unsigned long flags, struct net *old_net)
         }
         mutex_unlock(&net_mutex);
         if (rv < 0) {
-                net_free(net);
+                net_drop_ns(net);
                 return ERR_PTR(rv);
         }
         return net;
@@ -286,7 +294,7 @@ static void cleanup_net(struct work_struct *work)
         /* Finally it is safe to free my network namespace structure */
         list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
                 list_del_init(&net->exit_list);
-                net_free(net);
+                net_drop_ns(net);
         }
 }
 static DECLARE_WORK(net_cleanup_work, cleanup_net);