Commit e03c5128 authored by David S. Miller's avatar David S. Miller
Browse files

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: default avatarDavid S. Miller <davem@davemloft.net>
parents 1ebd08a7 467fa153

net/rds/bind.c

+2 −1
Original line number Diff line number Diff line
@@ -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

+10 −6
Original line number Diff line number Diff line
@@ -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 @@ new_conn: 
	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 @@ new_conn: 
	 * 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 @@ out: 
	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

+1 −1
Original line number Diff line number Diff line
@@ -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

+3 −2
Original line number Diff line number Diff line
@@ -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

+1 −1
Original line number Diff line number Diff line
@@ -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;

CRA Git | Maintained and supported by SUSTech CRA and CCSE