RDS-TCP: Support multiple RDS-TCP listen endpoints, one per netns.

Register pernet subsys init/stop functions that will set up
and tear down per-net RDS-TCP listen endpoints. Unregister
pernet subusys functions on 'modprobe -r' to clean up these
end points.

Enable keepalive on both accept and connect socket endpoints.
The keepalive timer expiration will ensure that client socket
endpoints will be removed as appropriate from the netns when
an interface is removed from a namespace.

Register a device notifier callback that will clean up all
sockets (and thus avoid the need to wait for keepalive timeout)
when the loopback device is unregistered from the netns indicating
that the netns is getting deleted.

Signed-off-by: Sowmini Varadhan <sowmini.varadhan@oracle.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 8 insertions, 30 deletions

diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c
index 398ffe5fc1d8..444d78d0bd77 100644
--- a/net/rds/tcp_listen.c
+++ b/net/rds/tcp_listen.c
@@ -38,14 +38,7 @@
 #include "rds.h"
 #include "tcp.h"
 
-/*
- * cheesy, but simple..
- */
-static void rds_tcp_accept_worker(struct work_struct *work);
-static DECLARE_WORK(rds_tcp_listen_work, rds_tcp_accept_worker);
-static struct socket *rds_tcp_listen_sock;
-
-static int rds_tcp_keepalive(struct socket *sock)
+int rds_tcp_keepalive(struct socket *sock)
 {
 	/* values below based on xs_udp_default_timeout */
 	int keepidle = 5; /* send a probe 'keepidle' secs after last data */
@@ -77,7 +70,7 @@ bail:
 	return ret;
 }
 
-static int rds_tcp_accept_one(struct socket *sock)
+int rds_tcp_accept_one(struct socket *sock)
 {
 	struct socket *new_sock = NULL;
 	struct rds_connection *conn;
@@ -150,12 +143,6 @@ out:
 	return ret;
 }
 
-static void rds_tcp_accept_worker(struct work_struct *work)
-{
-	while (rds_tcp_accept_one(rds_tcp_listen_sock) == 0)
-		cond_resched();
-}
-
 void rds_tcp_listen_data_ready(struct sock *sk)
 {
 	void (*ready)(struct sock *sk);
@@ -176,26 +163,20 @@ void rds_tcp_listen_data_ready(struct sock *sk)
 	 * socket
 	 */
 	if (sk->sk_state == TCP_LISTEN)
-		queue_work(rds_wq, &rds_tcp_listen_work);
+		rds_tcp_accept_work(sk);
 
 out:
 	read_unlock(&sk->sk_callback_lock);
 	ready(sk);
 }
 
-int rds_tcp_listen_init(void)
+struct socket *rds_tcp_listen_init(struct net *net)
 {
 	struct sockaddr_in sin;
 	struct socket *sock = NULL;
 	int ret;
 
-	/* MUST call sock_create_kern directly so that we avoid get_net()
-	 * in sk_alloc(). Doing a get_net() will result in cleanup_net()
-	 * never getting invoked, which will leave sock and other things
-	 * in limbo.
-	 */
-	ret = sock_create_kern(current->nsproxy->net_ns, PF_INET,
-			       SOCK_STREAM, IPPROTO_TCP, &sock);
+	ret = sock_create_kern(net, PF_INET, SOCK_STREAM, IPPROTO_TCP, &sock);
 	if (ret < 0)
 		goto out;
 
@@ -219,17 +200,15 @@ int rds_tcp_listen_init(void)
 	if (ret < 0)
 		goto out;
 
-	rds_tcp_listen_sock = sock;
-	sock = NULL;
+	return sock;
 out:
 	if (sock)
 		sock_release(sock);
-	return ret;
+	return NULL;
 }
 
-void rds_tcp_listen_stop(void)
+void rds_tcp_listen_stop(struct socket *sock)
 {
-	struct socket *sock = rds_tcp_listen_sock;
 	struct sock *sk;
 
 	if (!sock)
@@ -250,5 +229,4 @@ void rds_tcp_listen_stop(void)
 	/* wait for accepts to stop and close the socket */
 	flush_workqueue(rds_wq);
 	sock_release(sock);
-	rds_tcp_listen_sock = NULL;
 }