btrfs: properly track when rescan worker is running

The qgroup_flags field is overloaded such that it reflects the on-disk
status of qgroups and the runtime state.  The BTRFS_QGROUP_STATUS_FLAG_RESCAN
flag is used to indicate that a rescan operation is in progress, but if
the file system is unmounted while a rescan is running, the rescan
operation is paused.  If the file system is then mounted read-only,
the flag will still be present but the rescan operation will not have
been resumed.  When we go to umount, btrfs_qgroup_wait_for_completion
will see the flag and interpret it to mean that the rescan worker is
still running and will wait for a completion that will never come.

This patch uses a separate flag to indicate when the worker is
running.  The locking and state surrounding the qgroup rescan worker
needs a lot of attention beyond this patch but this is enough to
avoid a hung umount.

Cc: <stable@vger.kernel.org> # v4.4+
Signed-off-by; Jeff Mahoney <jeffm@suse.com>
Reviewed-by: Qu Wenruo <quwenruo@cn.fujitsu.com>
Signed-off-by: David Sterba <dsterba@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>

fs/btrfs/ctree.h

@@ -1028,6 +1028,7 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *qgroup_rescan_workers;
 	struct completion qgroup_rescan_completion;
 	struct btrfs_work qgroup_rescan_work;
+	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
 
 	/* filesystem state */
 	unsigned long fs_state;

fs/btrfs/disk-io.c

@@ -2304,6 +2304,7 @@ static void btrfs_init_qgroup(struct btrfs_fs_info *fs_info)
 	fs_info->quota_enabled = 0;
 	fs_info->pending_quota_state = 0;
 	fs_info->qgroup_ulist = NULL;
+	fs_info->qgroup_rescan_running = false;
 	mutex_init(&fs_info->qgroup_rescan_lock);
 }
 

fs/btrfs/qgroup.c

@@ -2303,6 +2303,10 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	int err = -ENOMEM;
 	int ret = 0;
 
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	fs_info->qgroup_rescan_running = true;
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
+
 	path = btrfs_alloc_path();
 	if (!path)
 		goto out;
@@ -2369,6 +2373,9 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 	}
 
 done:
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	fs_info->qgroup_rescan_running = false;
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
 	complete_all(&fs_info->qgroup_rescan_completion);
 }
 
@@ -2494,7 +2501,7 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info)
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	spin_lock(&fs_info->qgroup_lock);
-	running = fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN;
+	running = fs_info->qgroup_rescan_running;
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);