Merge branch 'rds-tcp-netns'

Sowmini Varadhan says:

====================
RDS-TCP: Network namespace support

This patch series contains the set of changes to correctly set up
the infra for PF_RDS sockets that use TCP as the transport in multiple
network namespaces.

Patch 1 in the series is the minimal set of changes to allow
a single instance of RDS-TCP to run in any (i.e init_net or other) net
namespace.  The changes in this patch set ensure that the execution of
'modprobe [-r] rds_tcp' sets up the kernel TCP sockets
relative to the current netns, so that RDS applications can send/recv
packets from that netns, and the netns can later be deleted cleanly.

Patch 2 of the series further allows multiple RDS-TCP instances,
one per network namespace. The changes in this patch allows dynamic
creation/tear-down of RDS-TCP client and server sockets  across all
current and future namespaces.

v2 changes from RFC sent out earlier:
    David Ahern comments in patch 1, net_device notifier in patch 2,
    patch 3 broken off and submitted separately.
v3: Cong Wang review comments.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

net/rds/bind.c

@@ -185,7 +185,8 @@ int rds_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		ret = 0;
 		goto out;
 	}
-	trans = rds_trans_get_preferred(sin->sin_addr.s_addr);
+	trans = rds_trans_get_preferred(sock_net(sock->sk),
+					sin->sin_addr.s_addr);
 	if (!trans) {
 		ret = -EADDRNOTAVAIL;
 		rds_remove_bound(rs);

net/rds/connection.c

@@ -117,7 +117,8 @@ static void rds_conn_reset(struct rds_connection *conn)
  * For now they are not garbage collected once they're created.  They
  * are torn down as the module is removed, if ever.
  */
-static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
+static struct rds_connection *__rds_conn_create(struct net *net,
+						__be32 laddr, __be32 faddr,
 				       struct rds_transport *trans, gfp_t gfp,
 				       int is_outgoing)
 {
@@ -157,6 +158,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	conn->c_faddr = faddr;
 	spin_lock_init(&conn->c_lock);
 	conn->c_next_tx_seq = 1;
+	rds_conn_net_set(conn, net);
 
 	init_waitqueue_head(&conn->c_waitq);
 	INIT_LIST_HEAD(&conn->c_send_queue);
@@ -174,7 +176,7 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	 * can bind to the destination address then we'd rather the messages
 	 * flow through loopback rather than either transport.
 	 */
-	loop_trans = rds_trans_get_preferred(faddr);
+	loop_trans = rds_trans_get_preferred(net, faddr);
 	if (loop_trans) {
 		rds_trans_put(loop_trans);
 		conn->c_loopback = 1;
@@ -260,17 +262,19 @@ static struct rds_connection *__rds_conn_create(__be32 laddr, __be32 faddr,
 	return conn;
 }
 
-struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr,
+struct rds_connection *rds_conn_create(struct net *net,
+				       __be32 laddr, __be32 faddr,
 				       struct rds_transport *trans, gfp_t gfp)
 {
-	return __rds_conn_create(laddr, faddr, trans, gfp, 0);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, 0);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create);
 
-struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr,
+struct rds_connection *rds_conn_create_outgoing(struct net *net,
+						__be32 laddr, __be32 faddr,
 				       struct rds_transport *trans, gfp_t gfp)
 {
-	return __rds_conn_create(laddr, faddr, trans, gfp, 1);
+	return __rds_conn_create(net, laddr, faddr, trans, gfp, 1);
 }
 EXPORT_SYMBOL_GPL(rds_conn_create_outgoing);
 

net/rds/ib.c

@@ -317,7 +317,7 @@ static void rds_ib_ic_info(struct socket *sock, unsigned int len,
  * allowed to influence which paths have priority.  We could call userspace
  * asserting this policy "routing".
  */
-static int rds_ib_laddr_check(__be32 addr)
+static int rds_ib_laddr_check(struct net *net, __be32 addr)
 {
 	int ret;
 	struct rdma_cm_id *cm_id;

net/rds/ib_cm.c

@@ -448,8 +448,9 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id,
 		 (unsigned long long)be64_to_cpu(lguid),
 		 (unsigned long long)be64_to_cpu(fguid));
 
-	conn = rds_conn_create(dp->dp_daddr, dp->dp_saddr, &rds_ib_transport,
-			       GFP_KERNEL);
+	/* RDS/IB is not currently netns aware, thus init_net */
+	conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr,
+			       &rds_ib_transport, GFP_KERNEL);
 	if (IS_ERR(conn)) {
 		rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn));
 		conn = NULL;

net/rds/iw.c

@@ -218,7 +218,7 @@ static void rds_iw_ic_info(struct socket *sock, unsigned int len,
  * allowed to influence which paths have priority.  We could call userspace
  * asserting this policy "routing".
  */
-static int rds_iw_laddr_check(__be32 addr)
+static int rds_iw_laddr_check(struct net *net, __be32 addr)
 {
 	int ret;
 	struct rdma_cm_id *cm_id;

net/rds/iw_cm.c

@@ -398,8 +398,9 @@ int rds_iw_cm_handle_connect(struct rdma_cm_id *cm_id,
 		 &dp->dp_saddr, &dp->dp_daddr,
 		 RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version));
 
-	conn = rds_conn_create(dp->dp_daddr, dp->dp_saddr, &rds_iw_transport,
-			       GFP_KERNEL);
+	/* RDS/IW is not currently netns aware, thus init_net */
+	conn = rds_conn_create(&init_net, dp->dp_daddr, dp->dp_saddr,
+			       &rds_iw_transport, GFP_KERNEL);
 	if (IS_ERR(conn)) {
 		rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn));
 		conn = NULL;

net/rds/rds.h

@@ -128,8 +128,21 @@ struct rds_connection {
 
 	/* Protocol version */
 	unsigned int		c_version;
+	possible_net_t		c_net;
 };
 
+static inline
+struct net *rds_conn_net(struct rds_connection *conn)
+{
+	return read_pnet(&conn->c_net);
+}
+
+static inline
+void rds_conn_net_set(struct rds_connection *conn, struct net *net)
+{
+	write_pnet(&conn->c_net, net);
+}
+
 #define RDS_FLAG_CONG_BITMAP	0x01
 #define RDS_FLAG_ACK_REQUIRED	0x02
 #define RDS_FLAG_RETRANSMITTED	0x04
@@ -417,7 +430,7 @@ struct rds_transport {
 	unsigned int		t_prefer_loopback:1;
 	unsigned int		t_type;
 
-	int (*laddr_check)(__be32 addr);
+	int (*laddr_check)(struct net *net, __be32 addr);
 	int (*conn_alloc)(struct rds_connection *conn, gfp_t gfp);
 	void (*conn_free)(void *data);
 	int (*conn_connect)(struct rds_connection *conn);
@@ -608,9 +621,11 @@ struct rds_message *rds_cong_update_alloc(struct rds_connection *conn);
 /* conn.c */
 int rds_conn_init(void);
 void rds_conn_exit(void);
-struct rds_connection *rds_conn_create(__be32 laddr, __be32 faddr,
+struct rds_connection *rds_conn_create(struct net *net,
+				       __be32 laddr, __be32 faddr,
 				       struct rds_transport *trans, gfp_t gfp);
-struct rds_connection *rds_conn_create_outgoing(__be32 laddr, __be32 faddr,
+struct rds_connection *rds_conn_create_outgoing(struct net *net,
+						__be32 laddr, __be32 faddr,
 			       struct rds_transport *trans, gfp_t gfp);
 void rds_conn_shutdown(struct rds_connection *conn);
 void rds_conn_destroy(struct rds_connection *conn);
@@ -795,7 +810,7 @@ void rds_connect_complete(struct rds_connection *conn);
 /* transport.c */
 int rds_trans_register(struct rds_transport *trans);
 void rds_trans_unregister(struct rds_transport *trans);
-struct rds_transport *rds_trans_get_preferred(__be32 addr);
+struct rds_transport *rds_trans_get_preferred(struct net *net, __be32 addr);
 void rds_trans_put(struct rds_transport *trans);
 unsigned int rds_trans_stats_info_copy(struct rds_info_iterator *iter,
 				       unsigned int avail);

net/rds/send.c

@@ -1023,7 +1023,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len)
 	if (rs->rs_conn && rs->rs_conn->c_faddr == daddr)
 		conn = rs->rs_conn;
 	else {
-		conn = rds_conn_create_outgoing(rs->rs_bound_addr, daddr,
+		conn = rds_conn_create_outgoing(sock_net(sock->sk),
+						rs->rs_bound_addr, daddr,
 					rs->rs_transport,
 					sock->sk->sk_allocation);
 		if (IS_ERR(conn)) {

net/rds/tcp.c

@@ -35,6 +35,9 @@
 #include <linux/in.h>
 #include <linux/module.h>
 #include <net/tcp.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/tcp.h>
 
 #include "rds.h"
 #include "tcp.h"
@@ -189,9 +192,9 @@ static void rds_tcp_tc_info(struct socket *sock, unsigned int len,
 	spin_unlock_irqrestore(&rds_tcp_tc_list_lock, flags);
 }
 
-static int rds_tcp_laddr_check(__be32 addr)
+static int rds_tcp_laddr_check(struct net *net, __be32 addr)
 {
-	if (inet_addr_type(&init_net, addr) == RTN_LOCAL)
+	if (inet_addr_type(net, addr) == RTN_LOCAL)
 		return 0;
 	return -EADDRNOTAVAIL;
 }
@@ -250,16 +253,7 @@ static void rds_tcp_destroy_conns(void)
 	}
 }
 
-static void rds_tcp_exit(void)
-{
-	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
-	rds_tcp_listen_stop();
-	rds_tcp_destroy_conns();
-	rds_trans_unregister(&rds_tcp_transport);
-	rds_tcp_recv_exit();
-	kmem_cache_destroy(rds_tcp_conn_slab);
-}
-module_exit(rds_tcp_exit);
+static void rds_tcp_exit(void);
 
 struct rds_transport rds_tcp_transport = {
 	.laddr_check		= rds_tcp_laddr_check,
@@ -281,6 +275,136 @@ struct rds_transport rds_tcp_transport = {
 	.t_prefer_loopback	= 1,
 };
 
+static int rds_tcp_netid;
+
+/* per-network namespace private data for this module */
+struct rds_tcp_net {
+	struct socket *rds_tcp_listen_sock;
+	struct work_struct rds_tcp_accept_w;
+};
+
+static void rds_tcp_accept_worker(struct work_struct *work)
+{
+	struct rds_tcp_net *rtn = container_of(work,
+					       struct rds_tcp_net,
+					       rds_tcp_accept_w);
+
+	while (rds_tcp_accept_one(rtn->rds_tcp_listen_sock) == 0)
+		cond_resched();
+}
+
+void rds_tcp_accept_work(struct sock *sk)
+{
+	struct net *net = sock_net(sk);
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	queue_work(rds_wq, &rtn->rds_tcp_accept_w);
+}
+
+static __net_init int rds_tcp_init_net(struct net *net)
+{
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	rtn->rds_tcp_listen_sock = rds_tcp_listen_init(net);
+	if (!rtn->rds_tcp_listen_sock) {
+		pr_warn("could not set up listen sock\n");
+		return -EAFNOSUPPORT;
+	}
+	INIT_WORK(&rtn->rds_tcp_accept_w, rds_tcp_accept_worker);
+	return 0;
+}
+
+static void __net_exit rds_tcp_exit_net(struct net *net)
+{
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	/* If rds_tcp_exit_net() is called as a result of netns deletion,
+	 * the rds_tcp_kill_sock() device notifier would already have cleaned
+	 * up the listen socket, thus there is no work to do in this function.
+	 *
+	 * If rds_tcp_exit_net() is called as a result of module unload,
+	 * i.e., due to rds_tcp_exit() -> unregister_pernet_subsys(), then
+	 * we do need to clean up the listen socket here.
+	 */
+	if (rtn->rds_tcp_listen_sock) {
+		rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+		rtn->rds_tcp_listen_sock = NULL;
+		flush_work(&rtn->rds_tcp_accept_w);
+	}
+}
+
+static struct pernet_operations rds_tcp_net_ops = {
+	.init = rds_tcp_init_net,
+	.exit = rds_tcp_exit_net,
+	.id = &rds_tcp_netid,
+	.size = sizeof(struct rds_tcp_net),
+};
+
+static void rds_tcp_kill_sock(struct net *net)
+{
+	struct rds_tcp_connection *tc, *_tc;
+	struct sock *sk;
+	LIST_HEAD(tmp_list);
+	struct rds_tcp_net *rtn = net_generic(net, rds_tcp_netid);
+
+	rds_tcp_listen_stop(rtn->rds_tcp_listen_sock);
+	rtn->rds_tcp_listen_sock = NULL;
+	flush_work(&rtn->rds_tcp_accept_w);
+	spin_lock_irq(&rds_tcp_conn_lock);
+	list_for_each_entry_safe(tc, _tc, &rds_tcp_conn_list, t_tcp_node) {
+		struct net *c_net = read_pnet(&tc->conn->c_net);
+
+		if (net != c_net || !tc->t_sock)
+			continue;
+		list_move_tail(&tc->t_tcp_node, &tmp_list);
+	}
+	spin_unlock_irq(&rds_tcp_conn_lock);
+	list_for_each_entry_safe(tc, _tc, &tmp_list, t_tcp_node) {
+		sk = tc->t_sock->sk;
+		sk->sk_prot->disconnect(sk, 0);
+		tcp_done(sk);
+		if (tc->conn->c_passive)
+			rds_conn_destroy(tc->conn->c_passive);
+		rds_conn_destroy(tc->conn);
+	}
+}
+
+static int rds_tcp_dev_event(struct notifier_block *this,
+			     unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	/* rds-tcp registers as a pernet subys, so the ->exit will only
+	 * get invoked after network acitivity has quiesced. We need to
+	 * clean up all sockets  to quiesce network activity, and use
+	 * the unregistration of the per-net loopback device as a trigger
+	 * to start that cleanup.
+	 */
+	if (event == NETDEV_UNREGISTER_FINAL &&
+	    dev->ifindex == LOOPBACK_IFINDEX)
+		rds_tcp_kill_sock(dev_net(dev));
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block rds_tcp_dev_notifier = {
+	.notifier_call        = rds_tcp_dev_event,
+	.priority = -10, /* must be called after other network notifiers */
+};
+
+static void rds_tcp_exit(void)
+{
+	rds_info_deregister_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
+	unregister_pernet_subsys(&rds_tcp_net_ops);
+	if (unregister_netdevice_notifier(&rds_tcp_dev_notifier))
+		pr_warn("could not unregister rds_tcp_dev_notifier\n");
+	rds_tcp_destroy_conns();
+	rds_trans_unregister(&rds_tcp_transport);
+	rds_tcp_recv_exit();
+	kmem_cache_destroy(rds_tcp_conn_slab);
+}
+module_exit(rds_tcp_exit);
+
 static int rds_tcp_init(void)
 {
 	int ret;
@@ -293,6 +417,16 @@ static int rds_tcp_init(void)
 		goto out;
 	}
 
+	ret = register_netdevice_notifier(&rds_tcp_dev_notifier);
+	if (ret) {
+		pr_warn("could not register rds_tcp_dev_notifier\n");
+		goto out;
+	}
+
+	ret = register_pernet_subsys(&rds_tcp_net_ops);
+	if (ret)
+		goto out_slab;
+
 	ret = rds_tcp_recv_init();
 	if (ret)
 		goto out_slab;
@@ -301,19 +435,14 @@ static int rds_tcp_init(void)
 	if (ret)
 		goto out_recv;
 
-	ret = rds_tcp_listen_init();
-	if (ret)
-		goto out_register;
-
 	rds_info_register_func(RDS_INFO_TCP_SOCKETS, rds_tcp_tc_info);
 
 	goto out;
 
-out_register:
-	rds_trans_unregister(&rds_tcp_transport);
 out_recv:
 	rds_tcp_recv_exit();
 out_slab:
+	unregister_pernet_subsys(&rds_tcp_net_ops);
 	kmem_cache_destroy(rds_tcp_conn_slab);
 out:
 	return ret;