Merge tag 'v4.1.35' into 4.1-2.0.x-imx

Linux 4.1.35

* tag 'v4.1.35': (98 commits)
  Linux 4.1.35
  xhci: fix usb2 resume timing and races.
  mm: remove gup_flags FOLL_WRITE games from __get_user_pages()
  timekeeping: Fix __ktime_get_fast_ns() regression
  time: Add cycles to nanoseconds translation
  Linux 4.1.34
  openrisc: fix the fix of copy_from_user()
  avr32: fix 'undefined reference to `___copy_from_user'
  fix memory leaks in tracing_buffers_splice_read()
  tracing: Move mutex to protect against resetting of seq data
  MIPS: SMP: Fix possibility of deadlock when bringing CPUs online
  MIPS: Fix pre-r6 emulation FPU initialisation
  btrfs: ensure that file descriptor used with subvol ioctls is a dir
  fix fault_in_multipages_...() on architectures with no-op access_ok()
  ocfs2: fix start offset to ocfs2_zero_range_for_truncate()
  fanotify: fix list corruption in fanotify_get_response()
  fsnotify: add a way to stop queueing events on group shutdown
  autofs: use dentry flags to block walks during expire
  autofs races
  ocfs2/dlm: fix race between convert and migration
  ...

Signed-off-by: Otavio Salvador <otavio@ossystems.com.br>

15 files changed, 172 insertions, 97 deletions

diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index 5b700ef1e59d..6196b5eaf9a5 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -79,9 +79,13 @@ struct autofs_info {
 };
 
 #define AUTOFS_INF_EXPIRING	(1<<0) /* dentry is in the process of expiring */
-#define AUTOFS_INF_NO_RCU	(1<<1) /* the dentry is being considered
+#define AUTOFS_INF_WANT_EXPIRE	(1<<1) /* the dentry is being considered
 					* for expiry, so RCU_walk is
-					* not permitted
+					* not permitted.  If it progresses to
+					* actual expiry attempt, the flag is
+					* not cleared when EXPIRING is set -
+					* in that case it gets cleared only
+					* when it comes to clearing EXPIRING.
 					*/
 #define AUTOFS_INF_PENDING	(1<<2) /* dentry pending mount */
 
diff --git a/fs/autofs4/expire.c b/fs/autofs4/expire.c
index 1cebc3c52fa5..7a5a598a2d94 100644
--- a/fs/autofs4/expire.c
+++ b/fs/autofs4/expire.c
@@ -315,19 +315,17 @@ struct dentry *autofs4_expire_direct(struct super_block *sb,
 	if (ino->flags & AUTOFS_INF_PENDING)
 		goto out;
 	if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
-		ino->flags |= AUTOFS_INF_NO_RCU;
+		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
 		spin_lock(&sbi->fs_lock);
 		if (!autofs4_direct_busy(mnt, root, timeout, do_now)) {
 			ino->flags |= AUTOFS_INF_EXPIRING;
-			smp_mb();
-			ino->flags &= ~AUTOFS_INF_NO_RCU;
 			init_completion(&ino->expire_complete);
 			spin_unlock(&sbi->fs_lock);
 			return root;
 		}
-		ino->flags &= ~AUTOFS_INF_NO_RCU;
+		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
 	}
 out:
 	spin_unlock(&sbi->fs_lock);
@@ -417,6 +415,7 @@ static struct dentry *should_expire(struct dentry *dentry,
 	}
 	return NULL;
 }
+
 /*
  * Find an eligible tree to time-out
  * A tree is eligible if :-
@@ -432,6 +431,7 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 	struct dentry *root = sb->s_root;
 	struct dentry *dentry;
 	struct dentry *expired;
+	struct dentry *found;
 	struct autofs_info *ino;
 
 	if (!root)
@@ -442,48 +442,54 @@ struct dentry *autofs4_expire_indirect(struct super_block *sb,
 
 	dentry = NULL;
 	while ((dentry = get_next_positive_subdir(dentry, root))) {
+		int flags = how;
+
 		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(dentry);
-		if (ino->flags & AUTOFS_INF_NO_RCU)
-			expired = NULL;
-		else
-			expired = should_expire(dentry, mnt, timeout, how);
-		if (!expired) {
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE) {
 			spin_unlock(&sbi->fs_lock);
 			continue;
 		}
+		spin_unlock(&sbi->fs_lock);
+
+		expired = should_expire(dentry, mnt, timeout, flags);
+		if (!expired)
+			continue;
+
+		spin_lock(&sbi->fs_lock);
 		ino = autofs4_dentry_ino(expired);
-		ino->flags |= AUTOFS_INF_NO_RCU;
+		ino->flags |= AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
 		synchronize_rcu();
-		spin_lock(&sbi->fs_lock);
-		if (should_expire(expired, mnt, timeout, how)) {
-			if (expired != dentry)
-				dput(dentry);
-			goto found;
-		}
 
-		ino->flags &= ~AUTOFS_INF_NO_RCU;
+		/* Make sure a reference is not taken on found if
+		 * things have changed.
+		 */
+		flags &= ~AUTOFS_EXP_LEAVES;
+		found = should_expire(expired, mnt, timeout, how);
+		if (!found || found != expired)
+			/* Something has changed, continue */
+			goto next;
+
 		if (expired != dentry)
-			dput(expired);
+			dput(dentry);
+
+		spin_lock(&sbi->fs_lock);
+		goto found;
+next:
+		spin_lock(&sbi->fs_lock);
+		ino->flags &= ~AUTOFS_INF_WANT_EXPIRE;
 		spin_unlock(&sbi->fs_lock);
+		if (expired != dentry)
+			dput(expired);
 	}
 	return NULL;
 
 found:
 	DPRINTK("returning %p %pd", expired, expired);
 	ino->flags |= AUTOFS_INF_EXPIRING;
-	smp_mb();
-	ino->flags &= ~AUTOFS_INF_NO_RCU;
 	init_completion(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
-	spin_lock(&sbi->lookup_lock);
-	spin_lock(&expired->d_parent->d_lock);
-	spin_lock_nested(&expired->d_lock, DENTRY_D_LOCK_NESTED);
-	list_move(&expired->d_parent->d_subdirs, &expired->d_child);
-	spin_unlock(&expired->d_lock);
-	spin_unlock(&expired->d_parent->d_lock);
-	spin_unlock(&sbi->lookup_lock);
 	return expired;
 }
 
@@ -492,15 +498,27 @@ int autofs4_expire_wait(struct dentry *dentry, int rcu_walk)
 	struct autofs_sb_info *sbi = autofs4_sbi(dentry->d_sb);
 	struct autofs_info *ino = autofs4_dentry_ino(dentry);
 	int status;
+	int state;
 
 	/* Block on any pending expire */
-	if (!(ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU)))
+	if (!(ino->flags & AUTOFS_INF_WANT_EXPIRE))
 		return 0;
 	if (rcu_walk)
 		return -ECHILD;
 
+retry:
 	spin_lock(&sbi->fs_lock);
-	if (ino->flags & AUTOFS_INF_EXPIRING) {
+	state = ino->flags & (AUTOFS_INF_WANT_EXPIRE | AUTOFS_INF_EXPIRING);
+	if (state == AUTOFS_INF_WANT_EXPIRE) {
+		spin_unlock(&sbi->fs_lock);
+		/*
+		 * Possibly being selected for expire, wait until
+		 * it's selected or not.
+		 */
+		schedule_timeout_uninterruptible(HZ/10);
+		goto retry;
+	}
+	if (state & AUTOFS_INF_EXPIRING) {
 		spin_unlock(&sbi->fs_lock);
 
 		DPRINTK("waiting for expire %p name=%pd", dentry, dentry);
@@ -551,7 +569,7 @@ int autofs4_expire_run(struct super_block *sb,
 	ino = autofs4_dentry_ino(dentry);
 	/* avoid rapid-fire expire attempts if expiry fails */
 	ino->last_used = now;
-	ino->flags &= ~AUTOFS_INF_EXPIRING;
+	ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
 	complete_all(&ino->expire_complete);
 	spin_unlock(&sbi->fs_lock);
 
@@ -579,7 +597,7 @@ int autofs4_do_expire_multi(struct super_block *sb, struct vfsmount *mnt,
 		spin_lock(&sbi->fs_lock);
 		/* avoid rapid-fire expire attempts if expiry fails */
 		ino->last_used = now;
-		ino->flags &= ~AUTOFS_INF_EXPIRING;
+		ino->flags &= ~(AUTOFS_INF_EXPIRING|AUTOFS_INF_WANT_EXPIRE);
 		complete_all(&ino->expire_complete);
 		spin_unlock(&sbi->fs_lock);
 		dput(dentry);
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index c6d7d3dbd52a..7a54c6a867c8 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -455,7 +455,7 @@ static int autofs4_d_manage(struct dentry *dentry, bool rcu_walk)
 		 * a mount-trap.
 		 */
 		struct inode *inode;
-		if (ino->flags & (AUTOFS_INF_EXPIRING | AUTOFS_INF_NO_RCU))
+		if (ino->flags & AUTOFS_INF_WANT_EXPIRE)
 			return 0;
 		if (d_mountpoint(dentry))
 			return 0;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 2eca30adb3e3..ff742d30ba60 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -1610,6 +1610,9 @@ static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
 	int namelen;
 	int ret = 0;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	ret = mnt_want_write_file(file);
 	if (ret)
 		goto out;
@@ -1667,6 +1670,9 @@ static noinline int btrfs_ioctl_snap_create(struct file *file,
 	struct btrfs_ioctl_vol_args *vol_args;
 	int ret;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -1690,6 +1696,9 @@ static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
 	bool readonly = false;
 	struct btrfs_qgroup_inherit *inherit = NULL;
 
+	if (!S_ISDIR(file_inode(file)->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
@@ -2318,6 +2327,9 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	int ret;
 	int err = 0;
 
+	if (!S_ISDIR(dir->i_mode))
+		return -ENOTDIR;
+
 	vol_args = memdup_user(arg, sizeof(*vol_args));
 	if (IS_ERR(vol_args))
 		return PTR_ERR(vol_args);
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index 5c222f3c4841..bd3c92b4bcee 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -2748,6 +2748,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 
 	if (log_root_tree->log_transid_committed >= root_log_ctx.log_transid) {
 		blk_finish_plug(&plug);
+		list_del_init(&root_log_ctx.list);
 		mutex_unlock(&log_root_tree->log_mutex);
 		ret = root_log_ctx.log_ret;
 		goto out;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 2cb9e178d1c5..4196aa567784 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -637,7 +637,13 @@ resizefs_out:
 			goto encryption_policy_out;
 		}
 
+		err = mnt_want_write_file(filp);
+		if (err)
+			goto encryption_policy_out;
+
 		err = ext4_process_policy(&policy, inode);
+
+		mnt_drop_write_file(filp);
 encryption_policy_out:
 		return err;
 #else
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 5cae35490b37..d8f29ef2d819 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -540,13 +540,13 @@ void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos,
 	req->out.args[0].size = count;
 }
 
-static void fuse_release_user_pages(struct fuse_req *req, int write)
+static void fuse_release_user_pages(struct fuse_req *req, bool should_dirty)
 {
 	unsigned i;
 
 	for (i = 0; i < req->num_pages; i++) {
 		struct page *page = req->pages[i];
-		if (write)
+		if (should_dirty)
 			set_page_dirty_lock(page);
 		put_page(page);
 	}
@@ -1331,6 +1331,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 		       loff_t *ppos, int flags)
 {
 	int write = flags & FUSE_DIO_WRITE;
+	bool should_dirty = !write && iter_is_iovec(iter);
 	int cuse = flags & FUSE_DIO_CUSE;
 	struct file *file = io->file;
 	struct inode *inode = file->f_mapping->host;
@@ -1375,7 +1376,7 @@ ssize_t fuse_direct_io(struct fuse_io_priv *io, struct iov_iter *iter,
 			nres = fuse_send_read(req, io, pos, nbytes, owner);
 
 		if (!io->async)
-			fuse_release_user_pages(req, !write);
+			fuse_release_user_pages(req, should_dirty);
 		if (req->out.h.error) {
 			if (!res)
 				res = req->out.h.error;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index eef16ec0638a..319ba6814899 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -7281,12 +7281,20 @@ static int _nfs4_proc_create_session(struct nfs_client *clp,
 	status = rpc_call_sync(session->clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT);
 	trace_nfs4_create_session(clp, status);
 
+	switch (status) {
+	case -NFS4ERR_STALE_CLIENTID:
+	case -NFS4ERR_DELAY:
+	case -ETIMEDOUT:
+	case -EACCES:
+	case -EAGAIN:
+		goto out;
+	};
+
+	clp->cl_seqid++;
 	if (!status) {
 		/* Verify the session's negotiated channel_attrs values */
 		status = nfs4_verify_channel_attrs(&args, &res);
 		/* Increment the clientid slot sequence id */
-		if (clp->cl_seqid == res.seqid)
-			clp->cl_seqid++;
 		if (status)
 			goto out;
 		nfs4_update_session(session, &res);
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index d2f97ecca6a5..e0e5f7c3c99f 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -67,18 +67,7 @@ static int fanotify_get_response(struct fsnotify_group *group,
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
-	wait_event(group->fanotify_data.access_waitq, event->response ||
-				atomic_read(&group->fanotify_data.bypass_perm));
-
-	if (!event->response) {	/* bypass_perm set */
-		/*
-		 * Event was canceled because group is being destroyed. Remove
-		 * it from group's event list because we are responsible for
-		 * freeing the permission event.
-		 */
-		fsnotify_remove_event(group, &event->fae.fse);
-		return 0;
-	}
+	wait_event(group->fanotify_data.access_waitq, event->response);
 
 	/* userspace responded, convert to something usable */
 	switch (event->response) {
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index cf275500a665..45ca844d1323 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -358,16 +358,20 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	struct fanotify_perm_event_info *event, *next;
+	struct fsnotify_event *fsn_event;
 
 	/*
-	 * There may be still new events arriving in the notification queue
-	 * but since userspace cannot use fanotify fd anymore, no event can
-	 * enter or leave access_list by now.
+	 * Stop new events from arriving in the notification queue. since
+	 * userspace cannot use fanotify fd anymore, no event can enter or
+	 * leave access_list by now either.
 	 */
-	spin_lock(&group->fanotify_data.access_lock);
-
-	atomic_inc(&group->fanotify_data.bypass_perm);
+	fsnotify_group_stop_queueing(group);
 
+	/*
+	 * Process all permission events on access_list and notification queue
+	 * and simulate reply from userspace.
+	 */
+	spin_lock(&group->fanotify_data.access_lock);
 	list_for_each_entry_safe(event, next, &group->fanotify_data.access_list,
 				 fae.fse.list) {
 		pr_debug("%s: found group=%p event=%p\n", __func__, group,
@@ -379,12 +383,21 @@ static int fanotify_release(struct inode *ignored, struct file *file)
 	spin_unlock(&group->fanotify_data.access_lock);
 
 	/*
-	 * Since bypass_perm is set, newly queued events will not wait for
-	 * access response. Wake up the already sleeping ones now.
-	 * synchronize_srcu() in fsnotify_destroy_group() will wait for all
-	 * processes sleeping in fanotify_handle_event() waiting for access
-	 * response and thus also for all permission events to be freed.
+	 * Destroy all non-permission events. For permission events just
+	 * dequeue them and set the response. They will be freed once the
+	 * response is consumed and fanotify_get_response() returns.
 	 */
+	mutex_lock(&group->notification_mutex);
+	while (!fsnotify_notify_queue_is_empty(group)) {
+		fsn_event = fsnotify_remove_first_event(group);
+		if (!(fsn_event->mask & FAN_ALL_PERM_EVENTS))
+			fsnotify_destroy_event(group, fsn_event);
+		else
+			FANOTIFY_PE(fsn_event)->response = FAN_ALLOW;
+	}
+	mutex_unlock(&group->notification_mutex);
+
+	/* Response for all permission events it set, wakeup waiters */
 	wake_up(&group->fanotify_data.access_waitq);
 #endif
 
@@ -751,7 +764,6 @@ SYSCALL_DEFINE2(fanotify_init, unsigned int, flags, unsigned int, event_f_flags)
 	spin_lock_init(&group->fanotify_data.access_lock);
 	init_waitqueue_head(&group->fanotify_data.access_waitq);
 	INIT_LIST_HEAD(&group->fanotify_data.access_list);
-	atomic_set(&group->fanotify_data.bypass_perm, 0);
 #endif
 	switch (flags & FAN_ALL_CLASS_BITS) {
 	case FAN_CLASS_NOTIF:
diff --git a/fs/notify/group.c b/fs/notify/group.c
index d16b62cb2854..18eb30c6bd8f 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -40,6 +40,17 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
 }
 
 /*
+ * Stop queueing new events for this group. Once this function returns
+ * fsnotify_add_event() will not add any new events to the group's queue.
+ */
+void fsnotify_group_stop_queueing(struct fsnotify_group *group)
+{
+	mutex_lock(&group->notification_mutex);
+	group->shutdown = true;
+	mutex_unlock(&group->notification_mutex);
+}
+
+/*
  * Trying to get rid of a group. Remove all marks, flush all events and release
  * the group reference.
  * Note that another thread calling fsnotify_clear_marks_by_group() may still
@@ -47,6 +58,14 @@ static void fsnotify_final_destroy_group(struct fsnotify_group *group)
  */
 void fsnotify_destroy_group(struct fsnotify_group *group)
 {
+	/*
+	 * Stop queueing new events. The code below is careful enough to not
+	 * require this but fanotify needs to stop queuing events even before
+	 * fsnotify_destroy_group() is called and this makes the other callers
+	 * of fsnotify_destroy_group() to see the same behavior.
+	 */
+	fsnotify_group_stop_queueing(group);
+
 	/* clear all inode marks for this group */
 	fsnotify_clear_marks_by_group(group);
 
diff --git a/fs/notify/notification.c b/fs/notify/notification.c
index a95d8e037aeb..e455e83ceeeb 100644
--- a/fs/notify/notification.c
+++ b/fs/notify/notification.c
@@ -82,7 +82,8 @@ void fsnotify_destroy_event(struct fsnotify_group *group,
  * Add an event to the group notification queue.  The group can later pull this
  * event off the queue to deal with.  The function returns 0 if the event was
  * added to the queue, 1 if the event was merged with some other queued event,
- * 2 if the queue of events has overflown.
+ * 2 if the event was not queued - either the queue of events has overflown
+ * or the group is shutting down.
  */
 int fsnotify_add_event(struct fsnotify_group *group,
 		       struct fsnotify_event *event,
@@ -96,6 +97,11 @@ int fsnotify_add_event(struct fsnotify_group *group,
 
 	mutex_lock(&group->notification_mutex);
 
+	if (group->shutdown) {
+		mutex_unlock(&group->notification_mutex);
+		return 2;
+	}
+
 	if (group->q_len >= group->max_events) {
 		ret = 2;
 		/* Queue overflow event only if it isn't already queued */
@@ -126,21 +132,6 @@ queue:
 }
 
 /*
- * Remove @event from group's notification queue. It is the responsibility of
- * the caller to destroy the event.
- */
-void fsnotify_remove_event(struct fsnotify_group *group,
-			   struct fsnotify_event *event)
-{
-	mutex_lock(&group->notification_mutex);
-	if (!list_empty(&event->list)) {
-		list_del_init(&event->list);
-		group->q_len--;
-	}
-	mutex_unlock(&group->notification_mutex);
-}
-
-/*
  * Remove and return the first event from the notification list.  It is the
  * responsibility of the caller to destroy the obtained event
  */
diff --git a/fs/ocfs2/dlm/dlmconvert.c b/fs/ocfs2/dlm/dlmconvert.c
index f90931335c6b..2e11658676eb 100644
--- a/fs/ocfs2/dlm/dlmconvert.c
+++ b/fs/ocfs2/dlm/dlmconvert.c
@@ -262,7 +262,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 				  struct dlm_lock *lock, int flags, int type)
 {
 	enum dlm_status status;
-	u8 old_owner = res->owner;
 
 	mlog(0, "type=%d, convert_type=%d, busy=%d\n", lock->ml.type,
 	     lock->ml.convert_type, res->state & DLM_LOCK_RES_IN_PROGRESS);
@@ -329,7 +328,6 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 
 	spin_lock(&res->spinlock);
 	res->state &= ~DLM_LOCK_RES_IN_PROGRESS;
-	lock->convert_pending = 0;
 	/* if it failed, move it back to granted queue.
 	 * if master returns DLM_NORMAL and then down before sending ast,
 	 * it may have already been moved to granted queue, reset to
@@ -338,12 +336,14 @@ enum dlm_status dlmconvert_remote(struct dlm_ctxt *dlm,
 		if (status != DLM_NOTQUEUED)
 			dlm_error(status);
 		dlm_revert_pending_convert(res, lock);
-	} else if ((res->state & DLM_LOCK_RES_RECOVERING) ||
-			(old_owner != res->owner)) {
-		mlog(0, "res %.*s is in recovering or has been recovered.\n",
-				res->lockname.len, res->lockname.name);
+	} else if (!lock->convert_pending) {
+		mlog(0, "%s: res %.*s, owner died and lock has been moved back "
+				"to granted list, retry convert.\n",
+				dlm->name, res->lockname.len, res->lockname.name);
 		status = DLM_RECOVERING;
 	}
+
+	lock->convert_pending = 0;
 bail:
 	spin_unlock(&res->spinlock);
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index 3f1ee404f40f..e00be7f509db 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1522,7 +1522,8 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 				       u64 start, u64 len)
 {
 	int ret = 0;
-	u64 tmpend, end = start + len;
+	u64 tmpend = 0;
+	u64 end = start + len;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	unsigned int csize = osb->s_clustersize;
 	handle_t *handle;
@@ -1554,18 +1555,31 @@ static int ocfs2_zero_partial_clusters(struct inode *inode,
 	}
 
 	/*
-	 * We want to get the byte offset of the end of the 1st cluster.
+	 * If start is on a cluster boundary and end is somewhere in another
+	 * cluster, we have not COWed the cluster starting at start, unless
+	 * end is also within the same cluster. So, in this case, we skip this
+	 * first call to ocfs2_zero_range_for_truncate() truncate and move on
+	 * to the next one.
 	 */
-	tmpend = (u64)osb->s_clustersize + (start & ~(osb->s_clustersize - 1));
-	if (tmpend > end)
-		tmpend = end;
+	if ((start & (csize - 1)) != 0) {
+		/*
+		 * We want to get the byte offset of the end of the 1st
+		 * cluster.
+		 */
+		tmpend = (u64)osb->s_clustersize +
+			(start & ~(osb->s_clustersize - 1));
+		if (tmpend > end)
+			tmpend = end;
 
-	trace_ocfs2_zero_partial_clusters_range1((unsigned long long)start,
-						 (unsigned long long)tmpend);
+		trace_ocfs2_zero_partial_clusters_range1(
+			(unsigned long long)start,
+			(unsigned long long)tmpend);
 
-	ret = ocfs2_zero_range_for_truncate(inode, handle, start, tmpend);
-	if (ret)
-		mlog_errno(ret);
+		ret = ocfs2_zero_range_for_truncate(inode, handle, start,
+						    tmpend);
+		if (ret)
+			mlog_errno(ret);
+	}
 
 	if (tmpend < end) {
 		/*
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index c9b740111526..f60b2c745d02 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -679,11 +679,11 @@ retry:
 			goto out_dput;
 
 		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_DEFAULT);
-		if (err && err != -ENODATA)
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
 			goto out_dput;
 
 		err = vfs_removexattr(work, XATTR_NAME_POSIX_ACL_ACCESS);
-		if (err && err != -ENODATA)
+		if (err && err != -ENODATA && err != -EOPNOTSUPP)
 			goto out_dput;
 
 		/* Clear any inherited mode bits */