NFSv4: Fix NFSv4 trunking discovery

If walking the list in nfs4[01]_walk_client_list fails, then the most
likely explanation is that the server dropped the clientid before we
actually managed to confirm it. As long as our nfs_client is the very
last one in the list to be tested, the caller can be assured that this
is the case when the final return value is NFS4ERR_STALE_CLIENTID.

Reported-by: Ben Greear <greearb@candelatech.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
Cc: Chuck Lever <chuck.lever@oracle.com>
Cc: stable@vger.kernel.org [>=3.7]
Tested-by: Ben Greear <greearb@candelatech.com>

2 files changed, 9 insertions, 25 deletions

diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 65a290a..2f21f17 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -352,14 +352,8 @@ int nfs40_walk_client_list(struct nfs_client *new,
 	}
 	spin_unlock(&nn->nfs_client_lock);
 
+	/* No match found. The server lost our clientid */
 out:
-	/*
-	 * No matching nfs_client found.  This should be impossible,
-	 * because the new nfs_client has already been added to
-	 * nfs_client_list by nfs_get_client().
-	 *
-	 * Don't BUG(), since the caller is holding a mutex.
-	 */
 	if (prev)
 		nfs_put_client(prev);
 	dprintk("NFS: <-- %s status = %d\n", __func__, status);
@@ -430,7 +424,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 {
 	struct nfs_net *nn = net_generic(new->cl_net, nfs_net_id);
 	struct nfs_client *pos, *n, *prev = NULL;
-	int error;
+	int status = -NFS4ERR_STALE_CLIENTID;
 
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry_safe(pos, n, &nn->nfs_client_list, cl_share_link) {
@@ -446,8 +440,8 @@ int nfs41_walk_client_list(struct nfs_client *new,
 				nfs_put_client(prev);
 			prev = pos;
 
-			error = nfs_wait_client_init_complete(pos);
-			if (error < 0) {
+			status = nfs_wait_client_init_complete(pos);
+			if (status < 0) {
 				nfs_put_client(pos);
 				spin_lock(&nn->nfs_client_lock);
 				continue;
@@ -480,16 +474,10 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		return 0;
 	}
 
-	/*
-	 * No matching nfs_client found.  This should be impossible,
-	 * because the new nfs_client has already been added to
-	 * nfs_client_list by nfs_get_client().
-	 *
-	 * Don't BUG(), since the caller is holding a mutex.
-	 */
+	/* No matching nfs_client found. */
 	spin_unlock(&nn->nfs_client_lock);
-	pr_err("NFS: %s Error: no matching nfs_client found\n", __func__);
-	return -NFS4ERR_STALE_CLIENTID;
+	dprintk("NFS: <-- %s status = %d\n", __func__, status);
+	return status;
 }
 #endif	/* CONFIG_NFS_V4_1 */
 
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 9448c57..f72561ca 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -136,16 +136,11 @@ int nfs40_discover_server_trunking(struct nfs_client *clp,
 	clp->cl_confirm = clid.confirm;
 
 	status = nfs40_walk_client_list(clp, result, cred);
-	switch (status) {
-	case -NFS4ERR_STALE_CLIENTID:
-		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
-	case 0:
+	if (status == 0) {
 		/* Sustain the lease, even if it's empty.  If the clientid4
 		 * goes stale it's of no use for trunking discovery. */
 		nfs4_schedule_state_renewal(*result);
-		break;
 	}
-
 out:
 	return status;
 }
@@ -1863,6 +1858,7 @@ again:
 	case -ETIMEDOUT:
 	case -EAGAIN:
 		ssleep(1);
+	case -NFS4ERR_STALE_CLIENTID:
 		dprintk("NFS: %s after status %d, retrying\n",
 			__func__, status);
 		goto again;