NFSv4.1: Don't loop forever in nfs4_proc_create_session

If a server for some reason keeps sending NFS4ERR_DELAY errors, we can end
up looping forever inside nfs4_proc_create_session, and so the usual
mechanisms for detecting if the nfs_client is dead don't work.

Fix this by ensuring that we loop inside the nfs4_state_manager thread
instead.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

1 files changed, 31 insertions, 15 deletions

diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 4dfb34b..4a810c8 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -64,10 +64,15 @@ static LIST_HEAD(nfs4_clientid_list);
 
 int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 {
-	struct nfs4_setclientid_res clid;
+	struct nfs4_setclientid_res clid = {
+		.clientid = clp->cl_clientid,
+		.confirm = clp->cl_confirm,
+	};
 	unsigned short port;
 	int status;
 
+	if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
+		goto do_confirm;
 	port = nfs_callback_tcpport;
 	if (clp->cl_addr.ss_family == AF_INET6)
 		port = nfs_callback_tcpport6;
@@ -75,10 +80,14 @@ int nfs4_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 	status = nfs4_proc_setclientid(clp, NFS4_CALLBACK, port, cred, &clid);
 	if (status != 0)
 		goto out;
+	clp->cl_clientid = clid.clientid;
+	clp->cl_confirm = clid.confirm;
+	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+do_confirm:
 	status = nfs4_proc_setclientid_confirm(clp, &clid, cred);
 	if (status != 0)
 		goto out;
-	clp->cl_clientid = clid.clientid;
+	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 	nfs4_schedule_state_renewal(clp);
 out:
 	return status;
@@ -230,13 +239,18 @@ int nfs41_init_clientid(struct nfs_client *clp, struct rpc_cred *cred)
 {
 	int status;
 
+	if (test_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state))
+		goto do_confirm;
 	nfs4_begin_drain_session(clp);
 	status = nfs4_proc_exchange_id(clp, cred);
 	if (status != 0)
 		goto out;
+	set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+do_confirm:
 	status = nfs4_proc_create_session(clp);
 	if (status != 0)
 		goto out;
+	clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
 	nfs41_setup_state_renewal(clp);
 	nfs_mark_client_ready(clp, NFS_CS_READY);
 out:
@@ -1584,20 +1598,22 @@ static int nfs4_recall_slot(struct nfs_client *clp) { return 0; }
  */
 static void nfs4_set_lease_expired(struct nfs_client *clp, int status)
 {
-	if (nfs4_has_session(clp)) {
-		switch (status) {
-		case -NFS4ERR_DELAY:
-		case -NFS4ERR_CLID_INUSE:
-		case -EAGAIN:
-			break;
+	switch (status) {
+	case -NFS4ERR_CLID_INUSE:
+	case -NFS4ERR_STALE_CLIENTID:
+		clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+		break;
+	case -NFS4ERR_DELAY:
+	case -EAGAIN:
+		ssleep(1);
+		break;
 
-		case -EKEYEXPIRED:
-			nfs4_warn_keyexpired(clp->cl_hostname);
-		case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
-					 * in nfs4_exchange_id */
-		default:
-			return;
-		}
+	case -EKEYEXPIRED:
+		nfs4_warn_keyexpired(clp->cl_hostname);
+	case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery
+				 * in nfs4_exchange_id */
+	default:
+		return;
 	}
 	set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state);
 }