net: Modify sk_alloc to not reference count the netns of kernel sockets.

Now that sk_alloc knows when a kernel socket is being allocated modify
it to not reference count the network namespace of kernel sockets.

Keep track of if a socket needs reference counting by adding a flag to
struct sock called sk_net_refcnt.

Update all of the callers of sock_create_kern to stop using
sk_change_net and sk_release_kernel as those hacks are no longer
needed, to avoid reference counting a kernel socket.

Signed-off-by: "Eric W. Biederman" <ebiederm@xmission.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 6 insertions, 2 deletions

diff --git a/net/core/sock.c b/net/core/sock.c
index cbc3789b830c..9e8968e9ebeb 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1412,7 +1412,10 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
                  */
                 sk->sk_prot = sk->sk_prot_creator = prot;
                 sock_lock_init(sk);
-                sock_net_set(sk, get_net(net));
+                sk->sk_net_refcnt = kern ? 0 : 1;
+                if (likely(sk->sk_net_refcnt))
+                        get_net(net);
+                sock_net_set(sk, net);
                 atomic_set(&sk->sk_wmem_alloc, 1);
 
                 sock_update_classid(sk);
@@ -1446,7 +1449,8 @@ static void __sk_free(struct sock *sk)
         if (sk->sk_peer_cred)
                 put_cred(sk->sk_peer_cred);
         put_pid(sk->sk_peer_pid);
-        put_net(sock_net(sk));
+        if (likely(sk->sk_net_refcnt))
+                put_net(sock_net(sk));
         sk_prot_free(sk->sk_prot_creator, sk);
 }