[PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[jeffm]

From: Jeff Mahoney <jeffm@suse.com>

Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
ended up reintroducing the hang-on-unmount bug that the commit it
intended to fix addressed.

The race this time is between qgroup_rescan_init setting
->qgroup_rescan_running = true and the worker starting.  There are
many scenarios where we initialize the worker and never start it.  The
completion btrfs_ioctl_quota_rescan_wait waits for will never come.
This can happen even without involving error handling, since mounting
the file system read-only returns between initializing the worker and
queueing it.

The right place to do it is when we're queuing the worker.  The flag
really just means that btrfs_ioctl_quota_rescan_wait should wait for
a completion.

This patch introduces a new helper, queue_rescan_worker, that handles
the ->qgroup_rescan_running flag, including any races with umount.

While we're at it, ->qgroup_rescan_running is protected only by the
->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
to take the spinlock too.

Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/ctree.h  |  1 +
 fs/btrfs/qgroup.c | 40 ++++++++++++++++++++++++++++------------
 2 files changed, 29 insertions(+), 12 deletions(-)

diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index da308774b8a4..dbba615f4d0f 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -1045,6 +1045,7 @@ struct btrfs_fs_info {
 	struct btrfs_workqueue *qgroup_rescan_workers;
 	struct completion qgroup_rescan_completion;
 	struct btrfs_work qgroup_rescan_work;
+	/* qgroup rescan worker is running or queued to run */
 	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
 
 	/* filesystem state */
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index aa259d6986e1..be491b6c020a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2072,6 +2072,30 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
+static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
+{
+	mutex_lock(&fs_info->qgroup_rescan_lock);
+	if (btrfs_fs_closing(fs_info)) {
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+		return;
+	}
+	if (WARN_ON(fs_info->qgroup_rescan_running)) {
+		btrfs_warn(fs_info, "rescan worker already queued");
+		mutex_unlock(&fs_info->qgroup_rescan_lock);
+		return;
+	}
+
+	/*
+	 * Being queued is enough for btrfs_qgroup_wait_for_completion
+	 * to need to wait.
+	 */
+	fs_info->qgroup_rescan_running = true;
+	mutex_unlock(&fs_info->qgroup_rescan_lock);
+
+	btrfs_queue_work(fs_info->qgroup_rescan_workers,
+			 &fs_info->qgroup_rescan_work);
+}
+
 /*
  * called from commit_transaction. Writes all changed qgroups to disk.
  */
@@ -2123,8 +2147,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
 		ret = qgroup_rescan_init(fs_info, 0, 1);
 		if (!ret) {
 			qgroup_rescan_zero_tracking(fs_info);
-			btrfs_queue_work(fs_info->qgroup_rescan_workers,
-					 &fs_info->qgroup_rescan_work);
+			queue_rescan_worker(fs_info);
 		}
 		ret = 0;
 	}
@@ -2713,7 +2736,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 		sizeof(fs_info->qgroup_rescan_progress));
 	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
 	init_completion(&fs_info->qgroup_rescan_completion);
-	fs_info->qgroup_rescan_running = true;
 
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
@@ -2785,9 +2807,7 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
 
 	qgroup_rescan_zero_tracking(fs_info);
 
-	btrfs_queue_work(fs_info->qgroup_rescan_workers,
-			 &fs_info->qgroup_rescan_work);
-
+	queue_rescan_worker(fs_info);
 	return 0;
 }
 
@@ -2798,9 +2818,7 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
 	int ret = 0;
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
-	spin_lock(&fs_info->qgroup_lock);
 	running = fs_info->qgroup_rescan_running;
-	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
 	if (!running)
@@ -2819,12 +2837,10 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
  * this is only called from open_ctree where we're still single threaded, thus
  * locking is omitted here.
  */
-void
-btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
+void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
 {
 	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
-		btrfs_queue_work(fs_info->qgroup_rescan_workers,
-				 &fs_info->qgroup_rescan_work);
+		queue_rescan_worker(fs_info);
 }
 
 /*
-- 
2.12.3

[PATCH 2/3] btrfs: qgroups, remove unnecessary memset before btrfs_init_work

[jeffm]

From: Jeff Mahoney <jeffm@suse.com>

btrfs_init_work clears the work struct except for ->wq, so the memset
before calling btrfs_init_work in qgroup_rescan_init is unnecessary.

We'll also initialize ->wq in btrfs_init_work so that it's obvious.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/async-thread.c | 1 +
 fs/btrfs/qgroup.c       | 2 --
 2 files changed, 1 insertion(+), 2 deletions(-)

diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index d5540749f0e5..c614fb7b9b9d 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -354,6 +354,7 @@ void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
 	INIT_WORK(&work->normal_work, uniq_func);
 	INIT_LIST_HEAD(&work->ordered_list);
 	work->flags = 0;
+	work->wq = NULL;
 }
 
 static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index be491b6c020a..8de423a0c7e3 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2740,8 +2740,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
 	spin_unlock(&fs_info->qgroup_lock);
 	mutex_unlock(&fs_info->qgroup_rescan_lock);
 
-	memset(&fs_info->qgroup_rescan_work, 0,
-	       sizeof(fs_info->qgroup_rescan_work));
 	btrfs_init_work(&fs_info->qgroup_rescan_work,
 			btrfs_qgroup_rescan_helper,
 			btrfs_qgroup_rescan_worker, NULL, NULL);
-- 
2.12.3

Re: [PATCH 2/3] btrfs: qgroups, remove unnecessary memset before btrfs_init_work

[Nikolay Borisov]

On 26.04.2018 22:23, jeffm@suse.com wrote:
> From: Jeff Mahoney <jeffm@suse.com>
> 
> btrfs_init_work clears the work struct except for ->wq, so the memset
> before calling btrfs_init_work in qgroup_rescan_init is unnecessary.
> 
> We'll also initialize ->wq in btrfs_init_work so that it's obvious.
> 
> Signed-off-by: Jeff Mahoney <jeffm@suse.com>

Reviewed-by: Nikolay Borisov <nborisov@suse.com>

> ---
>  fs/btrfs/async-thread.c | 1 +
>  fs/btrfs/qgroup.c       | 2 --
>  2 files changed, 1 insertion(+), 2 deletions(-)
> 
> diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
> index d5540749f0e5..c614fb7b9b9d 100644
> --- a/fs/btrfs/async-thread.c
> +++ b/fs/btrfs/async-thread.c
> @@ -354,6 +354,7 @@ void btrfs_init_work(struct btrfs_work *work, btrfs_work_func_t uniq_func,
>  	INIT_WORK(&work->normal_work, uniq_func);
>  	INIT_LIST_HEAD(&work->ordered_list);
>  	work->flags = 0;
> +	work->wq = NULL;
>  }
>  
>  static inline void __btrfs_queue_work(struct __btrfs_workqueue *wq,
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index be491b6c020a..8de423a0c7e3 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2740,8 +2740,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
>  	spin_unlock(&fs_info->qgroup_lock);
>  	mutex_unlock(&fs_info->qgroup_rescan_lock);
>  
> -	memset(&fs_info->qgroup_rescan_work, 0,
> -	       sizeof(fs_info->qgroup_rescan_work));
>  	btrfs_init_work(&fs_info->qgroup_rescan_work,
>  			btrfs_qgroup_rescan_helper,
>  			btrfs_qgroup_rescan_worker, NULL, NULL);
> 

[PATCH 3/3] btrfs: qgroup, don't try to insert status item after ENOMEM in rescan worker

[jeffm]

From: Jeff Mahoney <jeffm@suse.com>

If we fail to allocate memory for a path, don't bother trying to
insert the qgroup status item.  We haven't done anything yet and it'll
fail also.  Just print an error and be done with it.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/qgroup.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 8de423a0c7e3..4c0978bce5b9 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2648,7 +2648,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 			btrfs_end_transaction(trans);
 	}
 
-out:
 	btrfs_free_path(path);
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
@@ -2688,6 +2687,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 		btrfs_info(fs_info, "qgroup scan completed%s",
 			err > 0 ? " (inconsistency flag cleared)" : "");
 	} else {
+out:
 		btrfs_err(fs_info, "qgroup scan failed with %d", err);
 	}
 
-- 
2.12.3

Re: [PATCH 3/3] btrfs: qgroup, don't try to insert status item after ENOMEM in rescan worker

[Nikolay Borisov]

On 26.04.2018 22:23, jeffm@suse.com wrote:
> From: Jeff Mahoney <jeffm@suse.com>
> 
> If we fail to allocate memory for a path, don't bother trying to
> insert the qgroup status item.  We haven't done anything yet and it'll
> fail also.  Just print an error and be done with it.
> 
> Signed-off-by: Jeff Mahoney <jeffm@suse.com>

nit: So the code is correct however, having the out label there is
really ugly. What about on path alloc failure just have the print in the
if branch do goto done?


Reviewed-by: Nikolay Borisov <nborisov@suse.com>

> ---
>  fs/btrfs/qgroup.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index 8de423a0c7e3..4c0978bce5b9 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2648,7 +2648,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
>  			btrfs_end_transaction(trans);
>  	}
>  
> -out:
>  	btrfs_free_path(path);
>  
>  	mutex_lock(&fs_info->qgroup_rescan_lock);
> @@ -2688,6 +2687,7 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
>  		btrfs_info(fs_info, "qgroup scan completed%s",
>  			err > 0 ? " (inconsistency flag cleared)" : "");
>  	} else {
> +out:
>  		btrfs_err(fs_info, "qgroup scan failed with %d", err);
>  	}
>  
> 

Re: [PATCH 3/3] btrfs: qgroup, don't try to insert status item after ENOMEM in rescan worker

[David Sterba]

On Thu, Apr 26, 2018 at 11:39:50PM +0300, Nikolay Borisov wrote:
> On 26.04.2018 22:23, jeffm@suse.com wrote:
> > From: Jeff Mahoney <jeffm@suse.com>
> > 
> > If we fail to allocate memory for a path, don't bother trying to
> > insert the qgroup status item.  We haven't done anything yet and it'll
> > fail also.  Just print an error and be done with it.
> > 
> > Signed-off-by: Jeff Mahoney <jeffm@suse.com>
> 
> nit: So the code is correct however, having the out label there is
> really ugly. What about on path alloc failure just have the print in the
> if branch do goto done?

Yeah, I don't like jumping to the inner blocks either. I saw this in the
qgroup code so we should clean it up and not add new instances.

In this case, only the path allocation failure jumps to the out label,
so printing the message and then jump to done makes sense to me.
However, the message would have to be duplicated in the end, and I don't
see a better way without further restructuring the code.

Re: [PATCH 3/3] btrfs: qgroup, don't try to insert status item after ENOMEM in rescan worker

[Jeff Mahoney]

On 4/27/18 11:44 AM, David Sterba wrote:
> On Thu, Apr 26, 2018 at 11:39:50PM +0300, Nikolay Borisov wrote:
>> On 26.04.2018 22:23, jeffm@suse.com wrote:
>>> From: Jeff Mahoney <jeffm@suse.com>
>>>
>>> If we fail to allocate memory for a path, don't bother trying to
>>> insert the qgroup status item.  We haven't done anything yet and it'll
>>> fail also.  Just print an error and be done with it.
>>>
>>> Signed-off-by: Jeff Mahoney <jeffm@suse.com>
>>
>> nit: So the code is correct however, having the out label there is
>> really ugly. What about on path alloc failure just have the print in the
>> if branch do goto done?
> 
> Yeah, I don't like jumping to the inner blocks either. I saw this in the
> qgroup code so we should clean it up and not add new instances.
> 
> In this case, only the path allocation failure jumps to the out label,
> so printing the message and then jump to done makes sense to me.
> However, the message would have to be duplicated in the end, and I don't
> see a better way without further restructuring the code.
> 

It doesn't require major surgery.  The else can be disconnected.

-Jeff

-- 
Jeff Mahoney
SUSE Labs

[PATCH v2] btrfs: qgroup, don't try to insert status item after ENOMEM in rescan worker

[Jeff Mahoney]

If we fail to allocate memory for a path, don't bother trying to
insert the qgroup status item.  We haven't done anything yet and it'll
fail also.  Just print an error and be done with it.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/qgroup.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 8de423a0c7e3..b795bad54705 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2648,7 +2648,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 			btrfs_end_transaction(trans);
 	}
 
-out:
 	btrfs_free_path(path);
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
@@ -2684,13 +2683,13 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 
 	if (btrfs_fs_closing(fs_info)) {
 		btrfs_info(fs_info, "qgroup scan paused");
-	} else if (err >= 0) {
+		err = 0;
+	} else if (err >= 0)
 		btrfs_info(fs_info, "qgroup scan completed%s",
 			err > 0 ? " (inconsistency flag cleared)" : "");
-	} else {
+out:
+	if (err < 0)
 		btrfs_err(fs_info, "qgroup scan failed with %d", err);
-	}
-
 done:
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	fs_info->qgroup_rescan_running = false;
-- 
2.12.3

Re: [PATCH v2] btrfs: qgroup, don't try to insert status item after ENOMEM in rescan worker

[David Sterba]

On Fri, Apr 27, 2018 at 12:11:00PM -0400, Jeff Mahoney wrote:
> If we fail to allocate memory for a path, don't bother trying to
> insert the qgroup status item.  We haven't done anything yet and it'll
> fail also.  Just print an error and be done with it.
> 
> Signed-off-by: Jeff Mahoney <jeffm@suse.com>
> ---
>  fs/btrfs/qgroup.c | 9 ++++-----
>  1 file changed, 4 insertions(+), 5 deletions(-)
> 
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index 8de423a0c7e3..b795bad54705 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2648,7 +2648,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
>  			btrfs_end_transaction(trans);
>  	}
>  
> -out:
>  	btrfs_free_path(path);
>  
>  	mutex_lock(&fs_info->qgroup_rescan_lock);
> @@ -2684,13 +2683,13 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
>  
>  	if (btrfs_fs_closing(fs_info)) {
>  		btrfs_info(fs_info, "qgroup scan paused");
> -	} else if (err >= 0) {
> +		err = 0;
> +	} else if (err >= 0)
>  		btrfs_info(fs_info, "qgroup scan completed%s",
>  			err > 0 ? " (inconsistency flag cleared)" : "");
> -	} else {
> +out:
> +	if (err < 0)
>  		btrfs_err(fs_info, "qgroup scan failed with %d", err);

Ah right, with the err = 0 in the fs_closing check we won't see both
messages reported, "qgroup scan paused" and "qgroup scan failed with %d".

Reviewed-by: David Sterba <dsterba@suse.com>

> -	}
> -
>  done:
>  	mutex_lock(&fs_info->qgroup_rescan_lock);
>  	fs_info->qgroup_rescan_running = false;
> -- 
> 2.12.3
> 
> 
> --
> 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

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Nikolay Borisov]

On 26.04.2018 22:23, jeffm@suse.com wrote:
> From: Jeff Mahoney <jeffm@suse.com>
> 
> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
> ended up reintroducing the hang-on-unmount bug that the commit it
> intended to fix addressed.
> 
> The race this time is between qgroup_rescan_init setting
> ->qgroup_rescan_running = true and the worker starting.  There are
> many scenarios where we initialize the worker and never start it.  The
> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
> This can happen even without involving error handling, since mounting
> the file system read-only returns between initializing the worker and
> queueing it.
> 
> The right place to do it is when we're queuing the worker.  The flag
> really just means that btrfs_ioctl_quota_rescan_wait should wait for
> a completion.
> 
> This patch introduces a new helper, queue_rescan_worker, that handles
> the ->qgroup_rescan_running flag, including any races with umount.
> 
> While we're at it, ->qgroup_rescan_running is protected only by the
> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
> to take the spinlock too.
> 
> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> Signed-off-by: Jeff Mahoney <jeffm@suse.com>


LGTM.

Reviewed-by: Nikolay Borisov <nborisov@suse.com>

> ---
>  fs/btrfs/ctree.h  |  1 +
>  fs/btrfs/qgroup.c | 40 ++++++++++++++++++++++++++++------------
>  2 files changed, 29 insertions(+), 12 deletions(-)
> 
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index da308774b8a4..dbba615f4d0f 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -1045,6 +1045,7 @@ struct btrfs_fs_info {
>  	struct btrfs_workqueue *qgroup_rescan_workers;
>  	struct completion qgroup_rescan_completion;
>  	struct btrfs_work qgroup_rescan_work;
> +	/* qgroup rescan worker is running or queued to run */
>  	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
>  
>  	/* filesystem state */
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index aa259d6986e1..be491b6c020a 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2072,6 +2072,30 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
>  	return ret;
>  }
>  
> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> +{
> +	mutex_lock(&fs_info->qgroup_rescan_lock);
> +	if (btrfs_fs_closing(fs_info)) {
> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
> +		return;
> +	}
> +	if (WARN_ON(fs_info->qgroup_rescan_running)) {
> +		btrfs_warn(fs_info, "rescan worker already queued");
> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
> +		return;
> +	}
> +
> +	/*
> +	 * Being queued is enough for btrfs_qgroup_wait_for_completion
> +	 * to need to wait.
> +	 */
> +	fs_info->qgroup_rescan_running = true;
> +	mutex_unlock(&fs_info->qgroup_rescan_lock);
> +
> +	btrfs_queue_work(fs_info->qgroup_rescan_workers,
> +			 &fs_info->qgroup_rescan_work);
> +}
> +
>  /*
>   * called from commit_transaction. Writes all changed qgroups to disk.
>   */
> @@ -2123,8 +2147,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
>  		ret = qgroup_rescan_init(fs_info, 0, 1);
>  		if (!ret) {
>  			qgroup_rescan_zero_tracking(fs_info);
> -			btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -					 &fs_info->qgroup_rescan_work);
> +			queue_rescan_worker(fs_info);
>  		}

So here it's not possible to race, since if qgroup_rescan_init returns 0
then we are guaranteed to queue the rescan.

>  		ret = 0;
>  	}
> @@ -2713,7 +2736,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
>  		sizeof(fs_info->qgroup_rescan_progress));
>  	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
>  	init_completion(&fs_info->qgroup_rescan_completion);
> -	fs_info->qgroup_rescan_running = true;
>  
>  	spin_unlock(&fs_info->qgroup_lock);
>  	mutex_unlock(&fs_info->qgroup_rescan_lock);
> @@ -2785,9 +2807,7 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
>  
>  	qgroup_rescan_zero_tracking(fs_info);
>  
> -	btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -			 &fs_info->qgroup_rescan_work);
> -
> +	queue_rescan_worker(fs_info);

Which leaves this to be the only problematic case, in case transaction
joining/commit fails, right?

>  	return 0;
>  }
>  
> @@ -2798,9 +2818,7 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>  	int ret = 0;
>  
>  	mutex_lock(&fs_info->qgroup_rescan_lock);
> -	spin_lock(&fs_info->qgroup_lock);
>  	running = fs_info->qgroup_rescan_running;
> -	spin_unlock(&fs_info->qgroup_lock);
>  	mutex_unlock(&fs_info->qgroup_rescan_lock);
>  
>  	if (!running)
> @@ -2819,12 +2837,10 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>   * this is only called from open_ctree where we're still single threaded, thus
>   * locking is omitted here.
>   */
> -void
> -btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
> +void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
>  {
>  	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
> -		btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -				 &fs_info->qgroup_rescan_work);
> +		queue_rescan_worker(fs_info);
>  }
>  
>  /*
> 

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Filipe Manana]

On Thu, Apr 26, 2018 at 8:23 PM,  <jeffm@suse.com> wrote:
> From: Jeff Mahoney <jeffm@suse.com>
>
> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
> ended up reintroducing the hang-on-unmount bug that the commit it
> intended to fix addressed.
>
> The race this time is between qgroup_rescan_init setting
> ->qgroup_rescan_running = true and the worker starting.  There are
> many scenarios where we initialize the worker and never start it.  The
> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
> This can happen even without involving error handling, since mounting
> the file system read-only returns between initializing the worker and
> queueing it.
>
> The right place to do it is when we're queuing the worker.  The flag
> really just means that btrfs_ioctl_quota_rescan_wait should wait for
> a completion.
>
> This patch introduces a new helper, queue_rescan_worker, that handles
> the ->qgroup_rescan_running flag, including any races with umount.
>
> While we're at it, ->qgroup_rescan_running is protected only by the
> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
> to take the spinlock too.
>
> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)

The commit id and subjects don't match:

commit d2c609b834d62f1e91f1635a27dca29f7806d3d6
Author: Jeff Mahoney <jeffm@suse.com>
Date:   Mon Aug 15 12:10:33 2016 -0400

    btrfs: properly track when rescan worker is running


> Signed-off-by: Jeff Mahoney <jeffm@suse.com>
> ---
>  fs/btrfs/ctree.h  |  1 +
>  fs/btrfs/qgroup.c | 40 ++++++++++++++++++++++++++++------------
>  2 files changed, 29 insertions(+), 12 deletions(-)
>
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index da308774b8a4..dbba615f4d0f 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -1045,6 +1045,7 @@ struct btrfs_fs_info {
>         struct btrfs_workqueue *qgroup_rescan_workers;
>         struct completion qgroup_rescan_completion;
>         struct btrfs_work qgroup_rescan_work;
> +       /* qgroup rescan worker is running or queued to run */
>         bool qgroup_rescan_running;     /* protected by qgroup_rescan_lock */
>
>         /* filesystem state */
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index aa259d6986e1..be491b6c020a 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2072,6 +2072,30 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
>         return ret;
>  }
>
> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> +{
> +       mutex_lock(&fs_info->qgroup_rescan_lock);
> +       if (btrfs_fs_closing(fs_info)) {
> +               mutex_unlock(&fs_info->qgroup_rescan_lock);
> +               return;
> +       }
> +       if (WARN_ON(fs_info->qgroup_rescan_running)) {
> +               btrfs_warn(fs_info, "rescan worker already queued");
> +               mutex_unlock(&fs_info->qgroup_rescan_lock);
> +               return;
> +       }
> +
> +       /*
> +        * Being queued is enough for btrfs_qgroup_wait_for_completion
> +        * to need to wait.
> +        */
> +       fs_info->qgroup_rescan_running = true;
> +       mutex_unlock(&fs_info->qgroup_rescan_lock);
> +
> +       btrfs_queue_work(fs_info->qgroup_rescan_workers,
> +                        &fs_info->qgroup_rescan_work);
> +}
> +
>  /*
>   * called from commit_transaction. Writes all changed qgroups to disk.
>   */
> @@ -2123,8 +2147,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
>                 ret = qgroup_rescan_init(fs_info, 0, 1);
>                 if (!ret) {
>                         qgroup_rescan_zero_tracking(fs_info);
> -                       btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -                                        &fs_info->qgroup_rescan_work);
> +                       queue_rescan_worker(fs_info);
>                 }
>                 ret = 0;
>         }
> @@ -2713,7 +2736,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
>                 sizeof(fs_info->qgroup_rescan_progress));
>         fs_info->qgroup_rescan_progress.objectid = progress_objectid;
>         init_completion(&fs_info->qgroup_rescan_completion);
> -       fs_info->qgroup_rescan_running = true;
>
>         spin_unlock(&fs_info->qgroup_lock);
>         mutex_unlock(&fs_info->qgroup_rescan_lock);
> @@ -2785,9 +2807,7 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
>
>         qgroup_rescan_zero_tracking(fs_info);
>
> -       btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -                        &fs_info->qgroup_rescan_work);
> -
> +       queue_rescan_worker(fs_info);
>         return 0;
>  }
>
> @@ -2798,9 +2818,7 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>         int ret = 0;
>
>         mutex_lock(&fs_info->qgroup_rescan_lock);
> -       spin_lock(&fs_info->qgroup_lock);
>         running = fs_info->qgroup_rescan_running;
> -       spin_unlock(&fs_info->qgroup_lock);
>         mutex_unlock(&fs_info->qgroup_rescan_lock);
>
>         if (!running)
> @@ -2819,12 +2837,10 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>   * this is only called from open_ctree where we're still single threaded, thus
>   * locking is omitted here.
>   */
> -void
> -btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
> +void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
>  {
>         if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
> -               btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -                                &fs_info->qgroup_rescan_work);
> +               queue_rescan_worker(fs_info);
>  }
>
>  /*
> --
> 2.12.3
>
> --
> 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



-- 
Filipe David Manana,

“Whether you think you can, or you think you can't — you're right.”

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Jeff Mahoney]

On 4/27/18 4:48 AM, Filipe Manana wrote:
> On Thu, Apr 26, 2018 at 8:23 PM,  <jeffm@suse.com> wrote:
>> From: Jeff Mahoney <jeffm@suse.com>
>>
>> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
>> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
>> ended up reintroducing the hang-on-unmount bug that the commit it
>> intended to fix addressed.
>>
>> The race this time is between qgroup_rescan_init setting
>> ->qgroup_rescan_running = true and the worker starting.  There are
>> many scenarios where we initialize the worker and never start it.  The
>> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
>> This can happen even without involving error handling, since mounting
>> the file system read-only returns between initializing the worker and
>> queueing it.
>>
>> The right place to do it is when we're queuing the worker.  The flag
>> really just means that btrfs_ioctl_quota_rescan_wait should wait for
>> a completion.
>>
>> This patch introduces a new helper, queue_rescan_worker, that handles
>> the ->qgroup_rescan_running flag, including any races with umount.
>>
>> While we're at it, ->qgroup_rescan_running is protected only by the
>> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
>> to take the spinlock too.
>>
>> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> 
> The commit id and subjects don't match:
> 
> commit d2c609b834d62f1e91f1635a27dca29f7806d3d6
> Author: Jeff Mahoney <jeffm@suse.com>
> Date:   Mon Aug 15 12:10:33 2016 -0400
> 
>     btrfs: properly track when rescan worker is running
> 


Thanks.  Fixed.

-Jeff

-- 
Jeff Mahoney
SUSE Labs

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[David Sterba]

On Thu, Apr 26, 2018 at 03:23:49PM -0400, jeffm@suse.com wrote:
> From: Jeff Mahoney <jeffm@suse.com>
> 
> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
> ended up reintroducing the hang-on-unmount bug that the commit it
> intended to fix addressed.
> 
> The race this time is between qgroup_rescan_init setting
> ->qgroup_rescan_running = true and the worker starting.  There are
> many scenarios where we initialize the worker and never start it.  The
> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
> This can happen even without involving error handling, since mounting
> the file system read-only returns between initializing the worker and
> queueing it.
> 
> The right place to do it is when we're queuing the worker.  The flag
> really just means that btrfs_ioctl_quota_rescan_wait should wait for
> a completion.
> 
> This patch introduces a new helper, queue_rescan_worker, that handles
> the ->qgroup_rescan_running flag, including any races with umount.
> 
> While we're at it, ->qgroup_rescan_running is protected only by the
> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
> to take the spinlock too.
> 
> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> Signed-off-by: Jeff Mahoney <jeffm@suse.com>

I've added this to misc-next as I'd like to push it to the next rc. The
Fixes is fixed.

> +	/* qgroup rescan worker is running or queued to run */
>  	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */

Comments merged.

>  	/* filesystem state */
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index aa259d6986e1..be491b6c020a 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2072,6 +2072,30 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
>  	return ret;
>  }
>  
> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> +{

And this had to be moved upwards as there was earlier use of
btrfs_queue_work that matched following the hunk.

> +}
> +
>  /*
>   * called from commit_transaction. Writes all changed qgroups to disk.
>   */
> @@ -2123,8 +2147,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
>  		ret = qgroup_rescan_init(fs_info, 0, 1);
>  		if (!ret) {
>  			qgroup_rescan_zero_tracking(fs_info);
> -			btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -					 &fs_info->qgroup_rescan_work);
> +			queue_rescan_worker(fs_info);
>  		}
>  		ret = 0;
>  	}

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Jeff Mahoney]

On 4/27/18 11:56 AM, David Sterba wrote:
> On Thu, Apr 26, 2018 at 03:23:49PM -0400, jeffm@suse.com wrote:
>> From: Jeff Mahoney <jeffm@suse.com>
>>
>> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
>> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
>> ended up reintroducing the hang-on-unmount bug that the commit it
>> intended to fix addressed.
>>
>> The race this time is between qgroup_rescan_init setting
>> ->qgroup_rescan_running = true and the worker starting.  There are
>> many scenarios where we initialize the worker and never start it.  The
>> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
>> This can happen even without involving error handling, since mounting
>> the file system read-only returns between initializing the worker and
>> queueing it.
>>
>> The right place to do it is when we're queuing the worker.  The flag
>> really just means that btrfs_ioctl_quota_rescan_wait should wait for
>> a completion.
>>
>> This patch introduces a new helper, queue_rescan_worker, that handles
>> the ->qgroup_rescan_running flag, including any races with umount.
>>
>> While we're at it, ->qgroup_rescan_running is protected only by the
>> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
>> to take the spinlock too.
>>
>> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
>> Signed-off-by: Jeff Mahoney <jeffm@suse.com>
> 
> I've added this to misc-next as I'd like to push it to the next rc. The
> Fixes is fixed.
> 
>> +	/* qgroup rescan worker is running or queued to run */
>>  	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
> 
> Comments merged.

Thanks.

>>  	/* filesystem state */
>> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
>> index aa259d6986e1..be491b6c020a 100644
>> --- a/fs/btrfs/qgroup.c
>> +++ b/fs/btrfs/qgroup.c
>> @@ -2072,6 +2072,30 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
>>  	return ret;
>>  }
>>  
>> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
>> +{
> 
> And this had to be moved upwards as there was earlier use of
> btrfs_queue_work that matched following the hunk.

Weird.  That must be exactly the kind of mismerge artifact that we were
talking about the other day.  In my tree it's in the right spot.

-Jeff

-- 
Jeff Mahoney
SUSE Labs

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[David Sterba]

On Fri, Apr 27, 2018 at 12:02:13PM -0400, Jeff Mahoney wrote:
> >> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> >> +{
> > 
> > And this had to be moved upwards as there was earlier use of
> > btrfs_queue_work that matched following the hunk.
> 
> Weird.  That must be exactly the kind of mismerge artifact that we were
> talking about the other day.  In my tree it's in the right spot.

I've tried current master, upcoming pull request queue (misc-4.17, one
nonc-onflicting patch) and current misc-next. None of them applies the
patch cleanly and the function is still added after the first use, so
this would not compile.

The result can be found in
https://github.com/kdave/btrfs-devel/commits/ext/jeffm/qgroup-fixes

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Jeff Mahoney]

On 4/27/18 12:40 PM, David Sterba wrote:
> On Fri, Apr 27, 2018 at 12:02:13PM -0400, Jeff Mahoney wrote:
>>>> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
>>>> +{
>>>
>>> And this had to be moved upwards as there was earlier use of
>>> btrfs_queue_work that matched following the hunk.
>>
>> Weird.  That must be exactly the kind of mismerge artifact that we were
>> talking about the other day.  In my tree it's in the right spot.
> 
> I've tried current master, upcoming pull request queue (misc-4.17, one
> nonc-onflicting patch) and current misc-next. None of them applies the
> patch cleanly and the function is still added after the first use, so
> this would not compile.
> 
> The result can be found in
> https://github.com/kdave/btrfs-devel/commits/ext/jeffm/qgroup-fixes
> 

Thanks.  The "Fixes" is incorrect there.  I had the right commit message
but not the right commit id.  It should be:

8d9eddad1946 (Btrfs: fix qgroup rescan worker initialization)

-Jeff

-- 
Jeff Mahoney
SUSE Labs

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[David Sterba]

On Fri, Apr 27, 2018 at 03:32:14PM -0400, Jeff Mahoney wrote:
> On 4/27/18 12:40 PM, David Sterba wrote:
> > On Fri, Apr 27, 2018 at 12:02:13PM -0400, Jeff Mahoney wrote:
> >>>> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> >>>> +{
> >>>
> >>> And this had to be moved upwards as there was earlier use of
> >>> btrfs_queue_work that matched following the hunk.
> >>
> >> Weird.  That must be exactly the kind of mismerge artifact that we were
> >> talking about the other day.  In my tree it's in the right spot.
> > 
> > I've tried current master, upcoming pull request queue (misc-4.17, one
> > nonc-onflicting patch) and current misc-next. None of them applies the
> > patch cleanly and the function is still added after the first use, so
> > this would not compile.
> > 
> > The result can be found in
> > https://github.com/kdave/btrfs-devel/commits/ext/jeffm/qgroup-fixes
> > 
> 
> Thanks.  The "Fixes" is incorrect there.  I had the right commit message
> but not the right commit id.  It should be:
> 
> 8d9eddad1946 (Btrfs: fix qgroup rescan worker initialization)

I've updated the wrong part, subject instead of the commit id. Now
fixed.

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Noah Massey]

On Fri, Apr 27, 2018 at 11:56 AM, David Sterba <dsterba@suse.cz> wrote:
> On Thu, Apr 26, 2018 at 03:23:49PM -0400, jeffm@suse.com wrote:
>> From: Jeff Mahoney <jeffm@suse.com>
>>
>> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
>> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
>> ended up reintroducing the hang-on-unmount bug that the commit it
>> intended to fix addressed.
>>
>> The race this time is between qgroup_rescan_init setting
>> ->qgroup_rescan_running = true and the worker starting.  There are
>> many scenarios where we initialize the worker and never start it.  The
>> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
>> This can happen even without involving error handling, since mounting
>> the file system read-only returns between initializing the worker and
>> queueing it.
>>
>> The right place to do it is when we're queuing the worker.  The flag
>> really just means that btrfs_ioctl_quota_rescan_wait should wait for
>> a completion.
>>
>> This patch introduces a new helper, queue_rescan_worker, that handles
>> the ->qgroup_rescan_running flag, including any races with umount.
>>
>> While we're at it, ->qgroup_rescan_running is protected only by the
>> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
>> to take the spinlock too.
>>
>> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
>> Signed-off-by: Jeff Mahoney <jeffm@suse.com>
>
> I've added this to misc-next as I'd like to push it to the next rc. The
> Fixes is fixed.
>

I don't see it pushed to misc-next yet, but based on f89fbcd776, could
you update the reference in the first line of the commit to match the
Fixes line?

Thanks,
Noah

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[David Sterba]

On Fri, Apr 27, 2018 at 03:28:44PM -0400, Noah Massey wrote:
> On Fri, Apr 27, 2018 at 11:56 AM, David Sterba <dsterba@suse.cz> wrote:
> > On Thu, Apr 26, 2018 at 03:23:49PM -0400, jeffm@suse.com wrote:
> >> From: Jeff Mahoney <jeffm@suse.com>
> >>
> >> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
...
> >>
> >> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> >> Signed-off-by: Jeff Mahoney <jeffm@suse.com>
> >
> > I've added this to misc-next as I'd like to push it to the next rc. The
> > Fixes is fixed.
> >
> 
> I don't see it pushed to misc-next yet, but based on f89fbcd776, could
> you update the reference in the first line of the commit to match the
> Fixes line?

Fixed, thanks for the notice.

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Qu Wenruo]

[-- Attachment #1.1: Type: text/plain, Size: 5470 bytes --]



On 2018年04月27日 03:23, jeffm@suse.com wrote:
> From: Jeff Mahoney <jeffm@suse.com>
> 
> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
> ended up reintroducing the hang-on-unmount bug that the commit it
> intended to fix addressed.
> 
> The race this time is between qgroup_rescan_init setting
> ->qgroup_rescan_running = true and the worker starting.  There are
> many scenarios where we initialize the worker and never start it.  The
> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
> This can happen even without involving error handling, since mounting
> the file system read-only returns between initializing the worker and
> queueing it.
> 
> The right place to do it is when we're queuing the worker.  The flag
> really just means that btrfs_ioctl_quota_rescan_wait should wait for
> a completion.
> 
> This patch introduces a new helper, queue_rescan_worker, that handles
> the ->qgroup_rescan_running flag, including any races with umount.
> 
> While we're at it, ->qgroup_rescan_running is protected only by the
> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
> to take the spinlock too.
> 
> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
> Signed-off-by: Jeff Mahoney <jeffm@suse.com>

A little off-topic, (thanks Nikolay for reporting this) sometimes
btrfs/017 could report qgroup corruption, and it turns out it's related
to rescan racy, which double account existing tree blocks twice.
(One by btrfs quota enable, another by btrfs quota rescan -w)

Would this patch help in such case?

Thanks,
Qu

> ---
>  fs/btrfs/ctree.h  |  1 +
>  fs/btrfs/qgroup.c | 40 ++++++++++++++++++++++++++++------------
>  2 files changed, 29 insertions(+), 12 deletions(-)
> 
> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
> index da308774b8a4..dbba615f4d0f 100644
> --- a/fs/btrfs/ctree.h
> +++ b/fs/btrfs/ctree.h
> @@ -1045,6 +1045,7 @@ struct btrfs_fs_info {
>  	struct btrfs_workqueue *qgroup_rescan_workers;
>  	struct completion qgroup_rescan_completion;
>  	struct btrfs_work qgroup_rescan_work;
> +	/* qgroup rescan worker is running or queued to run */
>  	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
>  
>  	/* filesystem state */
> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
> index aa259d6986e1..be491b6c020a 100644
> --- a/fs/btrfs/qgroup.c
> +++ b/fs/btrfs/qgroup.c
> @@ -2072,6 +2072,30 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
>  	return ret;
>  }
>  
> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> +{
> +	mutex_lock(&fs_info->qgroup_rescan_lock);
> +	if (btrfs_fs_closing(fs_info)) {
> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
> +		return;
> +	}
> +	if (WARN_ON(fs_info->qgroup_rescan_running)) {
> +		btrfs_warn(fs_info, "rescan worker already queued");
> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
> +		return;
> +	}
> +
> +	/*
> +	 * Being queued is enough for btrfs_qgroup_wait_for_completion
> +	 * to need to wait.
> +	 */
> +	fs_info->qgroup_rescan_running = true;
> +	mutex_unlock(&fs_info->qgroup_rescan_lock);
> +
> +	btrfs_queue_work(fs_info->qgroup_rescan_workers,
> +			 &fs_info->qgroup_rescan_work);
> +}
> +
>  /*
>   * called from commit_transaction. Writes all changed qgroups to disk.
>   */
> @@ -2123,8 +2147,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
>  		ret = qgroup_rescan_init(fs_info, 0, 1);
>  		if (!ret) {
>  			qgroup_rescan_zero_tracking(fs_info);
> -			btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -					 &fs_info->qgroup_rescan_work);
> +			queue_rescan_worker(fs_info);
>  		}
>  		ret = 0;
>  	}
> @@ -2713,7 +2736,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
>  		sizeof(fs_info->qgroup_rescan_progress));
>  	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
>  	init_completion(&fs_info->qgroup_rescan_completion);
> -	fs_info->qgroup_rescan_running = true;
>  
>  	spin_unlock(&fs_info->qgroup_lock);
>  	mutex_unlock(&fs_info->qgroup_rescan_lock);
> @@ -2785,9 +2807,7 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
>  
>  	qgroup_rescan_zero_tracking(fs_info);
>  
> -	btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -			 &fs_info->qgroup_rescan_work);
> -
> +	queue_rescan_worker(fs_info);
>  	return 0;
>  }
>  
> @@ -2798,9 +2818,7 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>  	int ret = 0;
>  
>  	mutex_lock(&fs_info->qgroup_rescan_lock);
> -	spin_lock(&fs_info->qgroup_lock);
>  	running = fs_info->qgroup_rescan_running;
> -	spin_unlock(&fs_info->qgroup_lock);
>  	mutex_unlock(&fs_info->qgroup_rescan_lock);
>  
>  	if (!running)
> @@ -2819,12 +2837,10 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>   * this is only called from open_ctree where we're still single threaded, thus
>   * locking is omitted here.
>   */
> -void
> -btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
> +void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
>  {
>  	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
> -		btrfs_queue_work(fs_info->qgroup_rescan_workers,
> -				 &fs_info->qgroup_rescan_work);
> +		queue_rescan_worker(fs_info);
>  }
>  
>  /*
> 


[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 488 bytes --]

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Jeff Mahoney]

On 4/30/18 2:20 AM, Qu Wenruo wrote:
> 
> 
> On 2018年04月27日 03:23, jeffm@suse.com wrote:
>> From: Jeff Mahoney <jeffm@suse.com>
>>
>> Commit d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
>> fixed the issue with BTRFS_IOC_QUOTA_RESCAN_WAIT being racy, but
>> ended up reintroducing the hang-on-unmount bug that the commit it
>> intended to fix addressed.
>>
>> The race this time is between qgroup_rescan_init setting
>> ->qgroup_rescan_running = true and the worker starting.  There are
>> many scenarios where we initialize the worker and never start it.  The
>> completion btrfs_ioctl_quota_rescan_wait waits for will never come.
>> This can happen even without involving error handling, since mounting
>> the file system read-only returns between initializing the worker and
>> queueing it.
>>
>> The right place to do it is when we're queuing the worker.  The flag
>> really just means that btrfs_ioctl_quota_rescan_wait should wait for
>> a completion.
>>
>> This patch introduces a new helper, queue_rescan_worker, that handles
>> the ->qgroup_rescan_running flag, including any races with umount.
>>
>> While we're at it, ->qgroup_rescan_running is protected only by the
>> ->qgroup_rescan_mutex.  btrfs_ioctl_quota_rescan_wait doesn't need
>> to take the spinlock too.
>>
>> Fixes: d2c609b834d6 (Btrfs: fix qgroup rescan worker initialization)
>> Signed-off-by: Jeff Mahoney <jeffm@suse.com>
> 
> A little off-topic, (thanks Nikolay for reporting this) sometimes
> btrfs/017 could report qgroup corruption, and it turns out it's related
> to rescan racy, which double account existing tree blocks twice.
> (One by btrfs quota enable, another by btrfs quota rescan -w)
> 
> Would this patch help in such case?

It shouldn't.  This only fixes races between the rescan worker getting
initialized and running vs waiting for it to complete.

-Jeff

>>  fs/btrfs/ctree.h  |  1 +
>>  fs/btrfs/qgroup.c | 40 ++++++++++++++++++++++++++++------------
>>  2 files changed, 29 insertions(+), 12 deletions(-)
>>
>> diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
>> index da308774b8a4..dbba615f4d0f 100644
>> --- a/fs/btrfs/ctree.h
>> +++ b/fs/btrfs/ctree.h
>> @@ -1045,6 +1045,7 @@ struct btrfs_fs_info {
>>  	struct btrfs_workqueue *qgroup_rescan_workers;
>>  	struct completion qgroup_rescan_completion;
>>  	struct btrfs_work qgroup_rescan_work;
>> +	/* qgroup rescan worker is running or queued to run */
>>  	bool qgroup_rescan_running;	/* protected by qgroup_rescan_lock */
>>  
>>  	/* filesystem state */
>> diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
>> index aa259d6986e1..be491b6c020a 100644
>> --- a/fs/btrfs/qgroup.c
>> +++ b/fs/btrfs/qgroup.c
>> @@ -2072,6 +2072,30 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
>>  	return ret;
>>  }
>>  
>> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
>> +{
>> +	mutex_lock(&fs_info->qgroup_rescan_lock);
>> +	if (btrfs_fs_closing(fs_info)) {
>> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
>> +		return;
>> +	}
>> +	if (WARN_ON(fs_info->qgroup_rescan_running)) {
>> +		btrfs_warn(fs_info, "rescan worker already queued");
>> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
>> +		return;
>> +	}
>> +
>> +	/*
>> +	 * Being queued is enough for btrfs_qgroup_wait_for_completion
>> +	 * to need to wait.
>> +	 */
>> +	fs_info->qgroup_rescan_running = true;
>> +	mutex_unlock(&fs_info->qgroup_rescan_lock);
>> +
>> +	btrfs_queue_work(fs_info->qgroup_rescan_workers,
>> +			 &fs_info->qgroup_rescan_work);
>> +}
>> +
>>  /*
>>   * called from commit_transaction. Writes all changed qgroups to disk.
>>   */
>> @@ -2123,8 +2147,7 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans,
>>  		ret = qgroup_rescan_init(fs_info, 0, 1);
>>  		if (!ret) {
>>  			qgroup_rescan_zero_tracking(fs_info);
>> -			btrfs_queue_work(fs_info->qgroup_rescan_workers,
>> -					 &fs_info->qgroup_rescan_work);
>> +			queue_rescan_worker(fs_info);
>>  		}
>>  		ret = 0;
>>  	}
>> @@ -2713,7 +2736,6 @@ qgroup_rescan_init(struct btrfs_fs_info *fs_info, u64 progress_objectid,
>>  		sizeof(fs_info->qgroup_rescan_progress));
>>  	fs_info->qgroup_rescan_progress.objectid = progress_objectid;
>>  	init_completion(&fs_info->qgroup_rescan_completion);
>> -	fs_info->qgroup_rescan_running = true;
>>  
>>  	spin_unlock(&fs_info->qgroup_lock);
>>  	mutex_unlock(&fs_info->qgroup_rescan_lock);
>> @@ -2785,9 +2807,7 @@ btrfs_qgroup_rescan(struct btrfs_fs_info *fs_info)
>>  
>>  	qgroup_rescan_zero_tracking(fs_info);
>>  
>> -	btrfs_queue_work(fs_info->qgroup_rescan_workers,
>> -			 &fs_info->qgroup_rescan_work);
>> -
>> +	queue_rescan_worker(fs_info);
>>  	return 0;
>>  }
>>  
>> @@ -2798,9 +2818,7 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>>  	int ret = 0;
>>  
>>  	mutex_lock(&fs_info->qgroup_rescan_lock);
>> -	spin_lock(&fs_info->qgroup_lock);
>>  	running = fs_info->qgroup_rescan_running;
>> -	spin_unlock(&fs_info->qgroup_lock);
>>  	mutex_unlock(&fs_info->qgroup_rescan_lock);
>>  
>>  	if (!running)
>> @@ -2819,12 +2837,10 @@ int btrfs_qgroup_wait_for_completion(struct btrfs_fs_info *fs_info,
>>   * this is only called from open_ctree where we're still single threaded, thus
>>   * locking is omitted here.
>>   */
>> -void
>> -btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
>> +void btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
>>  {
>>  	if (fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_RESCAN)
>> -		btrfs_queue_work(fs_info->qgroup_rescan_workers,
>> -				 &fs_info->qgroup_rescan_work);
>> +		queue_rescan_worker(fs_info);
>>  }
>>  
>>  /*
>>
> 


-- 
Jeff Mahoney
SUSE Labs

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[David Sterba]

On Thu, Apr 26, 2018 at 03:23:49PM -0400, jeffm@suse.com wrote:
> From: Jeff Mahoney <jeffm@suse.com>
> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> +{
> +	mutex_lock(&fs_info->qgroup_rescan_lock);
> +	if (btrfs_fs_closing(fs_info)) {
> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
> +		return;
> +	}
> +	if (WARN_ON(fs_info->qgroup_rescan_running)) {

The warning is quite noisy, I see it after tests btrfs/ 017, 022, 124,
139, 153. Is it necessary for non-debugging builds?

The tested branch was full for-next so it could be your patchset
interacting with other fixes, but the warning noise level question still
stands.

> +		btrfs_warn(fs_info, "rescan worker already queued");
> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
> +		return;
> +	}
> +
> +	/*
> +	 * Being queued is enough for btrfs_qgroup_wait_for_completion
> +	 * to need to wait.
> +	 */
> +	fs_info->qgroup_rescan_running = true;
> +	mutex_unlock(&fs_info->qgroup_rescan_lock);
> +
> +	btrfs_queue_work(fs_info->qgroup_rescan_workers,
> +			 &fs_info->qgroup_rescan_work);
> +}

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[David Sterba]

On Wed, May 02, 2018 at 12:29:28PM +0200, David Sterba wrote:
> On Thu, Apr 26, 2018 at 03:23:49PM -0400, jeffm@suse.com wrote:
> > From: Jeff Mahoney <jeffm@suse.com>
> > +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
> > +{
> > +	mutex_lock(&fs_info->qgroup_rescan_lock);
> > +	if (btrfs_fs_closing(fs_info)) {
> > +		mutex_unlock(&fs_info->qgroup_rescan_lock);
> > +		return;
> > +	}
> > +	if (WARN_ON(fs_info->qgroup_rescan_running)) {
> 
> The warning is quite noisy, I see it after tests btrfs/ 017, 022, 124,
> 139, 153. Is it necessary for non-debugging builds?
> 
> The tested branch was full for-next so it could be your patchset
> interacting with other fixes, but the warning noise level question still
> stands.

So it must be something with the rest of misc-next or for-next patches,
current for 4.17 queue does show the warning at all, and the patch is ok
for merge.

Re: [PATCH 1/3] btrfs: qgroups, fix rescan worker running races

[Jeff Mahoney]

On 5/2/18 9:15 AM, David Sterba wrote:
> On Wed, May 02, 2018 at 12:29:28PM +0200, David Sterba wrote:
>> On Thu, Apr 26, 2018 at 03:23:49PM -0400, jeffm@suse.com wrote:
>>> From: Jeff Mahoney <jeffm@suse.com>
>>> +static void queue_rescan_worker(struct btrfs_fs_info *fs_info)
>>> +{
>>> +	mutex_lock(&fs_info->qgroup_rescan_lock);
>>> +	if (btrfs_fs_closing(fs_info)) {
>>> +		mutex_unlock(&fs_info->qgroup_rescan_lock);
>>> +		return;
>>> +	}
>>> +	if (WARN_ON(fs_info->qgroup_rescan_running)) {
>>
>> The warning is quite noisy, I see it after tests btrfs/ 017, 022, 124,
>> 139, 153. Is it necessary for non-debugging builds?
>>
>> The tested branch was full for-next so it could be your patchset
>> interacting with other fixes, but the warning noise level question still
>> stands.
> 
> So it must be something with the rest of misc-next or for-next patches,
> current for 4.17 queue does show the warning at all, and the patch is ok
> for merge.
>
You might have something that causes it to be more noisy but it looks
like it should be possible to hit on 4.16.  The warning is supposed to
detect and complain about multiple rescan threads starting.  What I
think it's doing here is (correctly) identifying a different race: at
the end of btrfs_qgroup_rescan_worker, we clear the rescan status flag,
drop the lock, commit the status item transaction, and then update
->qgroup_rescan_running.  If a rescan is requested before the lock is
reacquired, we'll try to start it up and then hit that warning.

So, the warning is doing its job.  Please hold off on merging this patch.

IMO the root cause is overloading fs_info->qgroup_flags to correspond to
the on-disk item and control runtime behavior.  I've been meaning to fix
that for a while, so I'll do that now.

-Jeff

-- 
Jeff Mahoney
SUSE Labs

[PATCH v3 0/3] btrfs: qgroup rescan races (part 1)

[jeffm]

From: Jeff Mahoney <jeffm@suse.com>

Hi Dave -

Here's the updated patchset for the rescan races.  This fixes the issue
where we'd try to start multiple workers.  It introduces a new "ready"
bool that we set during initialization and clear while queuing the worker.
The queuer is also now responsible for most of the initialization.

I have a separate patch set start that gets rid of the racy mess surrounding
the rescan worker startup.  We can handle it in btrfs_run_qgroups and
just set a flag to start it everywhere else.

-Jeff

---

Jeff Mahoney (3):
  btrfs: qgroups, fix rescan worker running races
  btrfs: qgroups, remove unnecessary memset before btrfs_init_work
  btrfs: qgroup, don't try to insert status item after ENOMEM in rescan
    worker

 fs/btrfs/async-thread.c |   1 +
 fs/btrfs/ctree.h        |   2 +
 fs/btrfs/qgroup.c       | 100 +++++++++++++++++++++++++++---------------------
 3 files changed, 60 insertions(+), 43 deletions(-)

-- 
2.12.3

[PATCH 3/3] btrfs: qgroup, don't try to insert status item after ENOMEM in rescan worker

[jeffm]

From: Jeff Mahoney <jeffm@suse.com>

If we fail to allocate memory for a path, don't bother trying to
insert the qgroup status item.  We haven't done anything yet and it'll
fail also.  Just print an error and be done with it.

Signed-off-by: Jeff Mahoney <jeffm@suse.com>
---
 fs/btrfs/qgroup.c | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 3d47700c6a30..44d5e3da835a 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -2666,7 +2666,6 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 			btrfs_end_transaction(trans);
 	}
 
-out:
 	btrfs_free_path(path);
 
 	mutex_lock(&fs_info->qgroup_rescan_lock);
@@ -2702,13 +2701,13 @@ static void btrfs_qgroup_rescan_worker(struct btrfs_work *work)
 
 	if (btrfs_fs_closing(fs_info)) {
 		btrfs_info(fs_info, "qgroup scan paused");
-	} else if (err >= 0) {
+		err = 0;
+	} else if (err >= 0)
 		btrfs_info(fs_info, "qgroup scan completed%s",
 			err > 0 ? " (inconsistency flag cleared)" : "");
-	} else {
+out:
+	if (err < 0)
 		btrfs_err(fs_info, "qgroup scan failed with %d", err);
-	}
-
 done:
 	mutex_lock(&fs_info->qgroup_rescan_lock);
 	fs_info->qgroup_rescan_running = false;
-- 
2.12.3