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, 9 insertions, 21 deletions

diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c
index 2e9a5b5d1239..b08ba9538d12 100644
--- a/net/netfilter/ipvs/ip_vs_sync.c
+++ b/net/netfilter/ipvs/ip_vs_sync.c
@@ -1457,18 +1457,12 @@ static struct socket *make_send_sock(struct net *net, int id)
 	struct socket *sock;
 	int result;
 
-	/* First create a socket move it to right name space later */
-	result = sock_create_kern(&init_net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
+	/* First create a socket */
+	result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
 	if (result < 0) {
 		pr_err("Error during creation of socket; terminating\n");
 		return ERR_PTR(result);
 	}
-	/*
-	 * Kernel sockets that are a part of a namespace, should not
-	 * hold a reference to a namespace in order to allow to stop it.
-	 * After sk_change_net should be released using sk_release_kernel.
-	 */
-	sk_change_net(sock->sk, net);
 	result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn);
 	if (result < 0) {
 		pr_err("Error setting outbound mcast interface\n");
@@ -1497,7 +1491,7 @@ static struct socket *make_send_sock(struct net *net, int id)
 	return sock;
 
 error:
-	sk_release_kernel(sock->sk);
+	sock_release(sock);
 	return ERR_PTR(result);
 }
 
@@ -1518,17 +1512,11 @@ static struct socket *make_receive_sock(struct net *net, int id)
 	int result;
 
 	/* First create a socket */
-	result = sock_create_kern(&init_net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
+	result = sock_create_kern(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock);
 	if (result < 0) {
 		pr_err("Error during creation of socket; terminating\n");
 		return ERR_PTR(result);
 	}
-	/*
-	 * Kernel sockets that are a part of a namespace, should not
-	 * hold a reference to a namespace in order to allow to stop it.
-	 * After sk_change_net should be released using sk_release_kernel.
-	 */
-	sk_change_net(sock->sk, net);
 	/* it is equivalent to the REUSEADDR option in user-space */
 	sock->sk->sk_reuse = SK_CAN_REUSE;
 	result = sysctl_sync_sock_size(ipvs);
@@ -1554,7 +1542,7 @@ static struct socket *make_receive_sock(struct net *net, int id)
 	return sock;
 
 error:
-	sk_release_kernel(sock->sk);
+	sock_release(sock);
 	return ERR_PTR(result);
 }
 
@@ -1692,7 +1680,7 @@ done:
 		ip_vs_sync_buff_release(sb);
 
 	/* release the sending multicast socket */
-	sk_release_kernel(tinfo->sock->sk);
+	sock_release(tinfo->sock);
 	kfree(tinfo);
 
 	return 0;
@@ -1729,7 +1717,7 @@ static int sync_thread_backup(void *data)
 	}
 
 	/* release the sending multicast socket */
-	sk_release_kernel(tinfo->sock->sk);
+	sock_release(tinfo->sock);
 	kfree(tinfo->buf);
 	kfree(tinfo);
 
@@ -1854,11 +1842,11 @@ int start_sync_thread(struct net *net, int state, char *mcast_ifn, __u8 syncid)
 	return 0;
 
 outsocket:
-	sk_release_kernel(sock->sk);
+	sock_release(sock);
 
 outtinfo:
 	if (tinfo) {
-		sk_release_kernel(tinfo->sock->sk);
+		sock_release(tinfo->sock);
 		kfree(tinfo->buf);
 		kfree(tinfo);
 	}