btrfs: properly track when rescan worker is running
diff mbox

Message ID cb4fecfa-9b40-d42c-8218-f0e7f7ac7fbb@suse.com
State Accepted
Headers show

Commit Message

Jeff Mahoney Aug. 15, 2016, 4:10 p.m. UTC
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>
---
 fs/btrfs/ctree.h   |    1 +
 fs/btrfs/disk-io.c |    1 +
 fs/btrfs/qgroup.c  |    9 ++++++++-
 3 files changed, 10 insertions(+), 1 deletion(-)

Comments

Qu Wenruo Aug. 16, 2016, 1:39 a.m. UTC | #1
At 08/16/2016 12:10 AM, Jeff Mahoney wrote:
> 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>

Looks good to me.

Would you mind to submit a test case for it?

Thanks,
Qu
> ---
>  fs/btrfs/ctree.h   |    1 +
>  fs/btrfs/disk-io.c |    1 +
>  fs/btrfs/qgroup.c  |    9 ++++++++-
>  3 files changed, 10 insertions(+), 1 deletion(-)
>
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -1771,6 +1771,7 @@ 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;
> --- a/fs/btrfs/disk-io.c
> +++ b/fs/btrfs/disk-io.c
> @@ -2275,6 +2275,7 @@ static void btrfs_init_qgroup(struct btr
>  	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);
>  }
>
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2302,6 +2302,10 @@ static void btrfs_qgroup_rescan_worker(s
>  	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;
> @@ -2368,6 +2372,9 @@ out:
>  	}
>
>  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(str
>
>  	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);
>
>


--
To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch
diff mbox

--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1771,6 +1771,7 @@  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;
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -2275,6 +2275,7 @@  static void btrfs_init_qgroup(struct btr
 	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);
 }
 
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2302,6 +2302,10 @@  static void btrfs_qgroup_rescan_worker(s
 	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;
@@ -2368,6 +2372,9 @@  out:
 	}
 
 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(str
 
 	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);