nfs: Referrals should use the same proto setting as their parent

Helen Chao <helen.chao@oracle.com> noticed that when a user
traverses a referral on an NFS/RDMA mount, the resulting submount
always uses TCP.

This behavior does not match the vers= setting when traversing
a referral (vers=4.1 is preserved). It also does not match the
behavior of crossing from the pseudofs into a real filesystem
(proto=rdma is preserved in that case).

The Linux NFS client does not currently support the
fs_locations_info attribute. The situation is similar for all
NFSv4 servers I know of. Therefore until the community has broad
support for fs_locations_info, when following a referral:

 - First try to connect with RPC-over-RDMA. This will fail quickly
   if the client has no RDMA-capable interfaces.

 - If connecting with RPC-over-RDMA fails, or the RPC-over-RDMA
   transport is not available, use TCP.

Reported-by: Helen Chao <helen.chao@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>

2 files changed, 20 insertions, 5 deletions

diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 65a7e5da508c..507f1f534b16 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -1123,19 +1123,36 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 	/* Initialise the client representation from the parent server */
 	nfs_server_copy_userdata(server, parent_server);
 
-	/* Get a client representation.
-	 * Note: NFSv4 always uses TCP, */
+	/* Get a client representation */
+#ifdef CONFIG_SUNRPC_XPRT_RDMA
+	rpc_set_port(data->addr, NFS_RDMA_PORT);
 	error = nfs4_set_client(server, data->hostname,
 				data->addr,
 				data->addrlen,
 				parent_client->cl_ipaddr,
-				rpc_protocol(parent_server->client),
+				XPRT_TRANSPORT_RDMA,
+				parent_server->client->cl_timeout,
+				parent_client->cl_mvops->minor_version,
+				parent_client->cl_net);
+	if (!error)
+		goto init_server;
+#endif	/* CONFIG_SUNRPC_XPRT_RDMA */
+
+	rpc_set_port(data->addr, NFS_PORT);
+	error = nfs4_set_client(server, data->hostname,
+				data->addr,
+				data->addrlen,
+				parent_client->cl_ipaddr,
+				XPRT_TRANSPORT_TCP,
 				parent_server->client->cl_timeout,
 				parent_client->cl_mvops->minor_version,
 				parent_client->cl_net);
 	if (error < 0)
 		goto error;
 
+#ifdef CONFIG_SUNRPC_XPRT_RDMA
+init_server:
+#endif
 	error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor);
 	if (error < 0)
 		goto error;
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 8c3f327d858d..24f06dcc2b08 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -270,8 +270,6 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 		if (mountdata->addrlen == 0)
 			continue;
 
-		rpc_set_port(mountdata->addr, NFS_PORT);
-
 		memcpy(page2, buf->data, buf->len);
 		page2[buf->len] = '\0';
 		mountdata->hostname = page2;