Merge tag 'nfs-for-3.8-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs

Pull NFS client bugfixes from Trond Myklebust:

 - Error reporting in nfs_xdev_mount incorrectly maps all errors to
   ENOMEM

 - Fix an NFSv4 refcounting issue

 - Fix a mount failure when the server reboots during NFSv4 trunking
   discovery

 - NFSv4.1 mounts may need to run the lease recovery thread.

 - Don't silently fail setattr() requests on mountpoints

 - Fix a SUNRPC socket/transport livelock and priority queue issue

 - We must handle NFS4ERR_DELAY when resetting the NFSv4.1 session.

* tag 'nfs-for-3.8-4' of git://git.linux-nfs.org/projects/trondmy/linux-nfs:
  NFSv4.1: Handle NFS4ERR_DELAY when resetting the NFSv4.1 session
  SUNRPC: When changing the queue priority, ensure that we change the owner
  NFS: Don't silently fail setattr() requests on mountpoints
  NFSv4.1: Ensure that nfs41_walk_client_list() does start lease recovery
  NFSv4: Fix NFSv4 trunking discovery
  NFSv4: Fix NFSv4 reference counting for trunked sessions
  NFS: Fix error reporting in nfs_xdev_mount

5 files changed, 86 insertions, 58 deletions

diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index dd057bc6b65..fc8dc20fdeb 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -177,11 +177,31 @@ out_nofree:
 	return mnt;
 }
 
+static int
+nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+{
+	if (NFS_FH(dentry->d_inode)->size != 0)
+		return nfs_getattr(mnt, dentry, stat);
+	generic_fillattr(dentry->d_inode, stat);
+	return 0;
+}
+
+static int
+nfs_namespace_setattr(struct dentry *dentry, struct iattr *attr)
+{
+	if (NFS_FH(dentry->d_inode)->size != 0)
+		return nfs_setattr(dentry, attr);
+	return -EACCES;
+}
+
 const struct inode_operations nfs_mountpoint_inode_operations = {
 	.getattr	= nfs_getattr,
+	.setattr	= nfs_setattr,
 };
 
 const struct inode_operations nfs_referral_inode_operations = {
+	.getattr	= nfs_namespace_getattr,
+	.setattr	= nfs_namespace_setattr,
 };
 
 static void nfs_expire_automounts(struct work_struct *work)
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index acc34726812..2e9779b58b7 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -236,11 +236,10 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	error = nfs4_discover_server_trunking(clp, &old);
 	if (error < 0)
 		goto error;
+	nfs_put_client(clp);
 	if (clp != old) {
 		clp->cl_preserve_clid = true;
-		nfs_put_client(clp);
 		clp = old;
-		atomic_inc(&clp->cl_count);
 	}
 
 	return clp;
@@ -306,7 +305,7 @@ int nfs40_walk_client_list(struct nfs_client *new,
 		.clientid	= new->cl_clientid,
 		.confirm	= new->cl_confirm,
 	};
-	int status;
+	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) {
@@ -332,40 +331,33 @@ int nfs40_walk_client_list(struct nfs_client *new,
 
 		if (prev)
 			nfs_put_client(prev);
+		prev = pos;
 
 		status = nfs4_proc_setclientid_confirm(pos, &clid, cred);
-		if (status == 0) {
+		switch (status) {
+		case -NFS4ERR_STALE_CLIENTID:
+			break;
+		case 0:
 			nfs4_swap_callback_idents(pos, new);
 
-			nfs_put_client(pos);
+			prev = NULL;
 			*result = pos;
 			dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
 				__func__, pos, atomic_read(&pos->cl_count));
-			return 0;
-		}
-		if (status != -NFS4ERR_STALE_CLIENTID) {
-			nfs_put_client(pos);
-			dprintk("NFS: <-- %s status = %d, no result\n",
-				__func__, status);
-			return status;
+		default:
+			goto out;
 		}
 
 		spin_lock(&nn->nfs_client_lock);
-		prev = pos;
 	}
+	spin_unlock(&nn->nfs_client_lock);
 
-	/*
-	 * 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 match found. The server lost our clientid */
+out:
 	if (prev)
 		nfs_put_client(prev);
-	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;
 }
 
 #ifdef CONFIG_NFS_V4_1
@@ -432,7 +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) {
@@ -448,14 +440,17 @@ 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) {
+			nfs4_schedule_lease_recovery(pos);
+			status = nfs_wait_client_init_complete(pos);
+			if (status < 0) {
 				nfs_put_client(pos);
 				spin_lock(&nn->nfs_client_lock);
 				continue;
 			}
-
+			status = pos->cl_cons_state;
 			spin_lock(&nn->nfs_client_lock);
+			if (status < 0)
+				continue;
 		}
 
 		if (pos->rpc_ops != new->rpc_ops)
@@ -473,6 +468,7 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		if (!nfs4_match_serverowners(pos, new))
 			continue;
 
+		atomic_inc(&pos->cl_count);
 		spin_unlock(&nn->nfs_client_lock);
 		dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
 			__func__, pos, atomic_read(&pos->cl_count));
@@ -481,16 +477,10 @@ 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 9448c579d41..e61f68d5ef2 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;
@@ -2022,8 +2018,18 @@ static int nfs4_reset_session(struct nfs_client *clp)
 	nfs4_begin_drain_session(clp);
 	cred = nfs4_get_exchange_id_cred(clp);
 	status = nfs4_proc_destroy_session(clp->cl_session, cred);
-	if (status && status != -NFS4ERR_BADSESSION &&
-	    status != -NFS4ERR_DEADSESSION) {
+	switch (status) {
+	case 0:
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+		break;
+	case -NFS4ERR_BACK_CHAN_BUSY:
+	case -NFS4ERR_DELAY:
+		set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+		status = 0;
+		ssleep(1);
+		goto out;
+	default:
 		status = nfs4_recovery_handle_error(clp, status);
 		goto out;
 	}
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 2e7e8c878e5..b056b162872 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -2589,27 +2589,23 @@ nfs_xdev_mount(struct file_system_type *fs_type, int flags,
 	struct nfs_server *server;
 	struct dentry *mntroot = ERR_PTR(-ENOMEM);
 	struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod;
-	int error;
 
-	dprintk("--> nfs_xdev_mount_common()\n");
+	dprintk("--> nfs_xdev_mount()\n");
 
 	mount_info.mntfh = mount_info.cloned->fh;
 
 	/* create a new volume representation */
 	server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor);
-	if (IS_ERR(server)) {
-		error = PTR_ERR(server);
-		goto out_err;
-	}
 
-	mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, nfs_mod);
-	dprintk("<-- nfs_xdev_mount_common() = 0\n");
-out:
-	return mntroot;
+	if (IS_ERR(server))
+		mntroot = ERR_CAST(server);
+	else
+		mntroot = nfs_fs_mount_common(server, flags,
+				dev_name, &mount_info, nfs_mod);
 
-out_err:
-	dprintk("<-- nfs_xdev_mount_common() = %d [error]\n", error);
-	goto out;
+	dprintk("<-- nfs_xdev_mount() = %ld\n",
+			IS_ERR(mntroot) ? PTR_ERR(mntroot) : 0L);
+	return mntroot;
 }
 
 #if IS_ENABLED(CONFIG_NFS_V4)
diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
index bfa31714581..fb20f25ddec 100644
--- a/net/sunrpc/sched.c
+++ b/net/sunrpc/sched.c
@@ -98,9 +98,25 @@ __rpc_add_timer(struct rpc_wait_queue *queue, struct rpc_task *task)
 	list_add(&task->u.tk_wait.timer_list, &queue->timer_list.list);
 }
 
+static void rpc_rotate_queue_owner(struct rpc_wait_queue *queue)
+{
+	struct list_head *q = &queue->tasks[queue->priority];
+	struct rpc_task *task;
+
+	if (!list_empty(q)) {
+		task = list_first_entry(q, struct rpc_task, u.tk_wait.list);
+		if (task->tk_owner == queue->owner)
+			list_move_tail(&task->u.tk_wait.list, q);
+	}
+}
+
 static void rpc_set_waitqueue_priority(struct rpc_wait_queue *queue, int priority)
 {
-	queue->priority = priority;
+	if (queue->priority != priority) {
+		/* Fairness: rotate the list when changing priority */
+		rpc_rotate_queue_owner(queue);
+		queue->priority = priority;
+	}
 }
 
 static void rpc_set_waitqueue_owner(struct rpc_wait_queue *queue, pid_t pid)