btrfs: explictly delete unused block groups in close_ctree and ro-remount

The cleaner thread may already be sleeping by the time we enter
close_ctree.  If that's the case, we'll skip removing any unused
block groups queued for removal, even during a normal umount.
They'll be cleaned up automatically at next mount, but users
expect a umount to be a clean synchronization point, especially
when used on thin-provisioned storage with -odiscard.  We also
explicitly remove unused block groups in the ro-remount path
for the same reason.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
Reviewed-by: Filipe Manana <fdmanana@suse.com>
Tested-by: Filipe Manana <fdmanana@suse.com>
Signed-off-by: Chris Mason <clm@fb.com>

fs/btrfs/disk-io.c

@@ -3767,6 +3767,15 @@ void close_ctree(struct btrfs_root *root)
 	cancel_work_sync(&fs_info->async_reclaim_work);
 
 	if (!(fs_info->sb->s_flags & MS_RDONLY)) {
+		/*
+		 * If the cleaner thread is stopped and there are
+		 * block groups queued for removal, the deletion will be
+		 * skipped when we quit the cleaner thread.
+		 */
+		mutex_lock(&root->fs_info->cleaner_mutex);
+		btrfs_delete_unused_bgs(root->fs_info);
+		mutex_unlock(&root->fs_info->cleaner_mutex);
+
 		ret = btrfs_commit_super(root);
 		if (ret)
 			btrfs_err(fs_info, "commit super ret %d", ret);

fs/btrfs/super.c

@@ -1650,6 +1650,17 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 
 		sb->s_flags |= MS_RDONLY;
 
+		/*
+		 * Setting MS_RDONLY will put the cleaner thread to
+		 * sleep at the next loop if it's already active.
+		 * If it's already asleep, we'll leave unused block
+		 * groups on disk until we're mounted read-write again
+		 * unless we clean them up here.
+		 */
+		mutex_lock(&root->fs_info->cleaner_mutex);
+		btrfs_delete_unused_bgs(fs_info);
+		mutex_unlock(&root->fs_info->cleaner_mutex);
+
 		btrfs_dev_replace_suspend_for_unmount(fs_info);
 		btrfs_scrub_cancel(fs_info);
 		btrfs_pause_balance(fs_info);