drivers: devfreq: change devfreq workqueue mechanism
diff mbox series

Message ID 1549046283-18242-1-git-send-email-l.luba@partner.samsung.com
State Not Applicable
Headers show
Series
  • drivers: devfreq: change devfreq workqueue mechanism
Related show

Commit Message

Lukasz Luba Feb. 1, 2019, 6:38 p.m. UTC
This patch removes devfreq's custom workqueue and uses system one.
It switches from queue_delayed_work() to schedule_delayed_work().
It also changes deferred work to delayed work, which is now not missed
when timer is put on CPU that entered idle state.
The devfreq framework governor was not called, thus changing the frequency
of the device did not happen.
Benchmarks for stressing Dynamic Memory Controller show x2
performance boost with this patch when 'simpleondemand_governor' is
responsible for monitoring the device load and frequency changes.
With this patch, the scheduled delayed work is done no mater CPUs' idle.
It also does not wake up the system when it enters suspend (this
functionality stays the same).
All of the drivers in devfreq which rely on periodic, guaranteed wakeup
intervals should benefit from it.

Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
---
 drivers/devfreq/devfreq.c | 27 +++++++--------------------
 1 file changed, 7 insertions(+), 20 deletions(-)

Comments

Matthias Kaehlcke Feb. 5, 2019, 12:39 a.m. UTC | #1
Hi Lukasz,

On Fri, Feb 01, 2019 at 07:38:03PM +0100, Lukasz Luba wrote:
> This patch removes devfreq's custom workqueue and uses system one.
> It switches from queue_delayed_work() to schedule_delayed_work().
> It also changes deferred work to delayed work, which is now not missed
> when timer is put on CPU that entered idle state.
> The devfreq framework governor was not called, thus changing the frequency
> of the device did not happen.
> Benchmarks for stressing Dynamic Memory Controller show x2
> performance boost with this patch when 'simpleondemand_governor' is
> responsible for monitoring the device load and frequency changes.
> With this patch, the scheduled delayed work is done no mater CPUs' idle.
> It also does not wake up the system when it enters suspend (this
> functionality stays the same).
> All of the drivers in devfreq which rely on periodic, guaranteed wakeup
> intervals should benefit from it.
> 
> Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
> ---
>  drivers/devfreq/devfreq.c | 27 +++++++--------------------
>  1 file changed, 7 insertions(+), 20 deletions(-)
> 
> diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
> index 0ae3de7..c200b3c 100644
> --- a/drivers/devfreq/devfreq.c
> +++ b/drivers/devfreq/devfreq.c
> @@ -31,13 +31,6 @@
>  
>  static struct class *devfreq_class;
>  
> -/*
> - * devfreq core provides delayed work based load monitoring helper
> - * functions. Governors can use these or can implement their own
> - * monitoring mechanism.
> - */
> -static struct workqueue_struct *devfreq_wq;
> -
>  /* The list of all device-devfreq governors */
>  static LIST_HEAD(devfreq_governor_list);
>  /* The list of all device-devfreq */
> @@ -391,8 +384,8 @@ static void devfreq_monitor(struct work_struct *work)
>  	if (err)
>  		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
>  
> -	queue_delayed_work(devfreq_wq, &devfreq->work,
> -				msecs_to_jiffies(devfreq->profile->polling_ms));
> +	schedule_delayed_work(&devfreq->work,
> +			      msecs_to_jiffies(devfreq->profile->polling_ms));
>  	mutex_unlock(&devfreq->lock);
>  }
>  
> @@ -407,9 +400,9 @@ static void devfreq_monitor(struct work_struct *work)
>   */
>  void devfreq_monitor_start(struct devfreq *devfreq)
>  {
> -	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
> +	INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
>  	if (devfreq->profile->polling_ms)
> -		queue_delayed_work(devfreq_wq, &devfreq->work,
> +		schedule_delayed_work(&devfreq->work,
>  			msecs_to_jiffies(devfreq->profile->polling_ms));
>  }
>  EXPORT_SYMBOL(devfreq_monitor_start);
> @@ -473,7 +466,7 @@ void devfreq_monitor_resume(struct devfreq *devfreq)
>  
>  	if (!delayed_work_pending(&devfreq->work) &&
>  			devfreq->profile->polling_ms)
> -		queue_delayed_work(devfreq_wq, &devfreq->work,
> +		schedule_delayed_work(&devfreq->work,
>  			msecs_to_jiffies(devfreq->profile->polling_ms));
>  
>  	devfreq->last_stat_updated = jiffies;
> @@ -516,7 +509,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
>  
>  	/* if current delay is zero, start polling with new delay */
>  	if (!cur_delay) {
> -		queue_delayed_work(devfreq_wq, &devfreq->work,
> +		schedule_delayed_work(&devfreq->work,
>  			msecs_to_jiffies(devfreq->profile->polling_ms));
>  		goto out;
>  	}
> @@ -527,7 +520,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
>  		cancel_delayed_work_sync(&devfreq->work);
>  		mutex_lock(&devfreq->lock);
>  		if (!devfreq->stop_polling)
> -			queue_delayed_work(devfreq_wq, &devfreq->work,
> +			schedule_delayed_work(&devfreq->work,
>  			      msecs_to_jiffies(devfreq->profile->polling_ms));
>  	}
>  out:
> @@ -1430,12 +1423,6 @@ static int __init devfreq_init(void)
>  		return PTR_ERR(devfreq_class);
>  	}
>  
> -	devfreq_wq = create_freezable_workqueue("devfreq_wq");
> -	if (!devfreq_wq) {
> -		class_destroy(devfreq_class);
> -		pr_err("%s: couldn't create workqueue\n", __FILE__);
> -		return -ENOMEM;
> -	}
>  	devfreq_class->dev_groups = devfreq_groups;
>  
>  	return 0;

If I understand correctly this changes three things:

1. use system workqueue instead of custom one

should be fine with the cwmq's we have nowadays


2. use non-freezable workqueue

  ``WQ_FREEZABLE``
    A freezable wq participates in the freeze phase of the system
    suspend operations.  Work items on the wq are drained and no
    new work item starts execution until thawed.

I'm not entirely sure what the impact of this is.

I imagine suspend is potentially quicker because the wq isn't drained,
but could works that execute during the suspend phase be a problem?


3. use delayed work instead of deferrable work

I hadn't come across deferrable work yet:

  "Add a new deferrable delayed work init.  This can be used to schedule work
  that are 'unimportant' when CPU is idle and can be called later, when CPU
  eventually comes out of idle."

  28287033e124 ("Add a new deferrable delayed work init")

The commit message mentions that frequency changes were missed due to
deferred works being scheduled on an idle CPU. The change to a delayed
work seems reasonable to me.

It could make sense to split this change into two patches, one for the
change from deferrable to delayed work, and another for custom workqueue
to system workqueue (and possibly even a third, transitory change for
freezable to non-freezable, if it's confirmed that that's the right
thing to do).

Cheers

Matthias
Lukasz Luba Feb. 11, 2019, 10:05 a.m. UTC | #2
Hi Matthias,

My apologize for late response, I did not have access to mailbox.
Thank you for review, please check the comments below.

On 2/5/19 1:39 AM, Matthias Kaehlcke wrote:
> Hi Lukasz,
> 
> On Fri, Feb 01, 2019 at 07:38:03PM +0100, Lukasz Luba wrote:
>> This patch removes devfreq's custom workqueue and uses system one.
>> It switches from queue_delayed_work() to schedule_delayed_work().
>> It also changes deferred work to delayed work, which is now not missed
>> when timer is put on CPU that entered idle state.
>> The devfreq framework governor was not called, thus changing the frequency
>> of the device did not happen.
>> Benchmarks for stressing Dynamic Memory Controller show x2
>> performance boost with this patch when 'simpleondemand_governor' is
>> responsible for monitoring the device load and frequency changes.
>> With this patch, the scheduled delayed work is done no mater CPUs' idle.
>> It also does not wake up the system when it enters suspend (this
>> functionality stays the same).
>> All of the drivers in devfreq which rely on periodic, guaranteed wakeup
>> intervals should benefit from it.
>>
>> Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
>> ---
>>   drivers/devfreq/devfreq.c | 27 +++++++--------------------
>>   1 file changed, 7 insertions(+), 20 deletions(-)
>>
>> diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
>> index 0ae3de7..c200b3c 100644
>> --- a/drivers/devfreq/devfreq.c
>> +++ b/drivers/devfreq/devfreq.c
>> @@ -31,13 +31,6 @@
>>   
>>   static struct class *devfreq_class;
>>   
>> -/*
>> - * devfreq core provides delayed work based load monitoring helper
>> - * functions. Governors can use these or can implement their own
>> - * monitoring mechanism.
>> - */
>> -static struct workqueue_struct *devfreq_wq;
>> -
>>   /* The list of all device-devfreq governors */
>>   static LIST_HEAD(devfreq_governor_list);
>>   /* The list of all device-devfreq */
>> @@ -391,8 +384,8 @@ static void devfreq_monitor(struct work_struct *work)
>>   	if (err)
>>   		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
>>   
>> -	queue_delayed_work(devfreq_wq, &devfreq->work,
>> -				msecs_to_jiffies(devfreq->profile->polling_ms));
>> +	schedule_delayed_work(&devfreq->work,
>> +			      msecs_to_jiffies(devfreq->profile->polling_ms));
>>   	mutex_unlock(&devfreq->lock);
>>   }
>>   
>> @@ -407,9 +400,9 @@ static void devfreq_monitor(struct work_struct *work)
>>    */
>>   void devfreq_monitor_start(struct devfreq *devfreq)
>>   {
>> -	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
>> +	INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
>>   	if (devfreq->profile->polling_ms)
>> -		queue_delayed_work(devfreq_wq, &devfreq->work,
>> +		schedule_delayed_work(&devfreq->work,
>>   			msecs_to_jiffies(devfreq->profile->polling_ms));
>>   }
>>   EXPORT_SYMBOL(devfreq_monitor_start);
>> @@ -473,7 +466,7 @@ void devfreq_monitor_resume(struct devfreq *devfreq)
>>   
>>   	if (!delayed_work_pending(&devfreq->work) &&
>>   			devfreq->profile->polling_ms)
>> -		queue_delayed_work(devfreq_wq, &devfreq->work,
>> +		schedule_delayed_work(&devfreq->work,
>>   			msecs_to_jiffies(devfreq->profile->polling_ms));
>>   
>>   	devfreq->last_stat_updated = jiffies;
>> @@ -516,7 +509,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
>>   
>>   	/* if current delay is zero, start polling with new delay */
>>   	if (!cur_delay) {
>> -		queue_delayed_work(devfreq_wq, &devfreq->work,
>> +		schedule_delayed_work(&devfreq->work,
>>   			msecs_to_jiffies(devfreq->profile->polling_ms));
>>   		goto out;
>>   	}
>> @@ -527,7 +520,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
>>   		cancel_delayed_work_sync(&devfreq->work);
>>   		mutex_lock(&devfreq->lock);
>>   		if (!devfreq->stop_polling)
>> -			queue_delayed_work(devfreq_wq, &devfreq->work,
>> +			schedule_delayed_work(&devfreq->work,
>>   			      msecs_to_jiffies(devfreq->profile->polling_ms));
>>   	}
>>   out:
>> @@ -1430,12 +1423,6 @@ static int __init devfreq_init(void)
>>   		return PTR_ERR(devfreq_class);
>>   	}
>>   
>> -	devfreq_wq = create_freezable_workqueue("devfreq_wq");
>> -	if (!devfreq_wq) {
>> -		class_destroy(devfreq_class);
>> -		pr_err("%s: couldn't create workqueue\n", __FILE__);
>> -		return -ENOMEM;
>> -	}
>>   	devfreq_class->dev_groups = devfreq_groups;
>>   
>>   	return 0;
> 
> If I understand correctly this changes three things:
> 
> 1. use system workqueue instead of custom one
> 
> should be fine with the cwmq's we have nowadays
> 
> 
> 2. use non-freezable workqueue
> 
>    ``WQ_FREEZABLE``
>      A freezable wq participates in the freeze phase of the system
>      suspend operations.  Work items on the wq are drained and no
>      new work item starts execution until thawed.
> 
> I'm not entirely sure what the impact of this is.
> 
> I imagine suspend is potentially quicker because the wq isn't drained,
> but could works that execute during the suspend phase be a problem?
I did not check if the suspend is quicker, but I will try to simulate
and check these scenarios.
I just wanted to get rid of another workqueue in the system.

> 
> 
> 3. use delayed work instead of deferrable work
> 
> I hadn't come across deferrable work yet:
Me neither, but using it to run governors is not the best idea.
> 
>    "Add a new deferrable delayed work init.  This can be used to schedule work
>    that are 'unimportant' when CPU is idle and can be called later, when CPU
>    eventually comes out of idle."
> 
>    28287033e124 ("Add a new deferrable delayed work init")
> 
> The commit message mentions that frequency changes were missed due to
> deferred works being scheduled on an idle CPU. The change to a delayed
> work seems reasonable to me.
It is not only the Dynamic Memory Controller and DRAM affected.
The drivers for GPUs, Network on Chip, cache L3 rely on it.
They all are missing opportunity to check the HW state and react.

> 
> It could make sense to split this change into two patches, one for the
> change from deferrable to delayed work, and another for custom workqueue
> to system workqueue (and possibly even a third, transitory change for
> freezable to non-freezable, if it's confirmed that that's the right
> thing to do).
OK, I will split the patch into two: one with delayed work and one with
regular system workqueue.
I thought that one patch would be simpler to apply to stable tree if needed.

Regards,
Lukasz
> 
> Cheers
> 
> Matthias
> 
>
Matthias Kaehlcke Feb. 11, 2019, 8:54 p.m. UTC | #3
Hi Lukasz,

On Mon, Feb 11, 2019 at 11:05:27AM +0100, Lukasz Luba wrote:
> Hi Matthias,
> 
> My apologize for late response, I did not have access to mailbox.
> Thank you for review, please check the comments below.
> 
> On 2/5/19 1:39 AM, Matthias Kaehlcke wrote:
> > Hi Lukasz,
> > 
> > On Fri, Feb 01, 2019 at 07:38:03PM +0100, Lukasz Luba wrote:
> >> This patch removes devfreq's custom workqueue and uses system one.
> >> It switches from queue_delayed_work() to schedule_delayed_work().
> >> It also changes deferred work to delayed work, which is now not missed
> >> when timer is put on CPU that entered idle state.
> >> The devfreq framework governor was not called, thus changing the frequency
> >> of the device did not happen.
> >> Benchmarks for stressing Dynamic Memory Controller show x2
> >> performance boost with this patch when 'simpleondemand_governor' is
> >> responsible for monitoring the device load and frequency changes.
> >> With this patch, the scheduled delayed work is done no mater CPUs' idle.
> >> It also does not wake up the system when it enters suspend (this
> >> functionality stays the same).
> >> All of the drivers in devfreq which rely on periodic, guaranteed wakeup
> >> intervals should benefit from it.
> >>
> >> Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
> >> ---
> >>   drivers/devfreq/devfreq.c | 27 +++++++--------------------
> >>   1 file changed, 7 insertions(+), 20 deletions(-)
> >>
> >> diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
> >> index 0ae3de7..c200b3c 100644
> >> --- a/drivers/devfreq/devfreq.c
> >> +++ b/drivers/devfreq/devfreq.c
> >> @@ -31,13 +31,6 @@
> >>   
> >>   static struct class *devfreq_class;
> >>   
> >> -/*
> >> - * devfreq core provides delayed work based load monitoring helper
> >> - * functions. Governors can use these or can implement their own
> >> - * monitoring mechanism.
> >> - */
> >> -static struct workqueue_struct *devfreq_wq;
> >> -
> >>   /* The list of all device-devfreq governors */
> >>   static LIST_HEAD(devfreq_governor_list);
> >>   /* The list of all device-devfreq */
> >> @@ -391,8 +384,8 @@ static void devfreq_monitor(struct work_struct *work)
> >>   	if (err)
> >>   		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
> >>   
> >> -	queue_delayed_work(devfreq_wq, &devfreq->work,
> >> -				msecs_to_jiffies(devfreq->profile->polling_ms));
> >> +	schedule_delayed_work(&devfreq->work,
> >> +			      msecs_to_jiffies(devfreq->profile->polling_ms));
> >>   	mutex_unlock(&devfreq->lock);
> >>   }
> >>   
> >> @@ -407,9 +400,9 @@ static void devfreq_monitor(struct work_struct *work)
> >>    */
> >>   void devfreq_monitor_start(struct devfreq *devfreq)
> >>   {
> >> -	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
> >> +	INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
> >>   	if (devfreq->profile->polling_ms)
> >> -		queue_delayed_work(devfreq_wq, &devfreq->work,
> >> +		schedule_delayed_work(&devfreq->work,
> >>   			msecs_to_jiffies(devfreq->profile->polling_ms));
> >>   }
> >>   EXPORT_SYMBOL(devfreq_monitor_start);
> >> @@ -473,7 +466,7 @@ void devfreq_monitor_resume(struct devfreq *devfreq)
> >>   
> >>   	if (!delayed_work_pending(&devfreq->work) &&
> >>   			devfreq->profile->polling_ms)
> >> -		queue_delayed_work(devfreq_wq, &devfreq->work,
> >> +		schedule_delayed_work(&devfreq->work,
> >>   			msecs_to_jiffies(devfreq->profile->polling_ms));
> >>   
> >>   	devfreq->last_stat_updated = jiffies;
> >> @@ -516,7 +509,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
> >>   
> >>   	/* if current delay is zero, start polling with new delay */
> >>   	if (!cur_delay) {
> >> -		queue_delayed_work(devfreq_wq, &devfreq->work,
> >> +		schedule_delayed_work(&devfreq->work,
> >>   			msecs_to_jiffies(devfreq->profile->polling_ms));
> >>   		goto out;
> >>   	}
> >> @@ -527,7 +520,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
> >>   		cancel_delayed_work_sync(&devfreq->work);
> >>   		mutex_lock(&devfreq->lock);
> >>   		if (!devfreq->stop_polling)
> >> -			queue_delayed_work(devfreq_wq, &devfreq->work,
> >> +			schedule_delayed_work(&devfreq->work,
> >>   			      msecs_to_jiffies(devfreq->profile->polling_ms));
> >>   	}
> >>   out:
> >> @@ -1430,12 +1423,6 @@ static int __init devfreq_init(void)
> >>   		return PTR_ERR(devfreq_class);
> >>   	}
> >>   
> >> -	devfreq_wq = create_freezable_workqueue("devfreq_wq");
> >> -	if (!devfreq_wq) {
> >> -		class_destroy(devfreq_class);
> >> -		pr_err("%s: couldn't create workqueue\n", __FILE__);
> >> -		return -ENOMEM;
> >> -	}
> >>   	devfreq_class->dev_groups = devfreq_groups;
> >>   
> >>   	return 0;
> > 
> > If I understand correctly this changes three things:
> > 
> > 1. use system workqueue instead of custom one
> > 
> > should be fine with the cwmq's we have nowadays
> > 
> > 
> > 2. use non-freezable workqueue
> > 
> >    ``WQ_FREEZABLE``
> >      A freezable wq participates in the freeze phase of the system
> >      suspend operations.  Work items on the wq are drained and no
> >      new work item starts execution until thawed.
> > 
> > I'm not entirely sure what the impact of this is.
> > 
> > I imagine suspend is potentially quicker because the wq isn't drained,
> > but could works that execute during the suspend phase be a problem?
> I did not check if the suspend is quicker, but I will try to simulate
> and check these scenarios.
> I just wanted to get rid of another workqueue in the system.

Are you sure that freezable vs. non-freezable isn't a problem? I
suppose there was a reason WQ_FREEZABLE was chosen initially, so I
don't know if it is still valid.

> > 3. use delayed work instead of deferrable work
> > 
> > I hadn't come across deferrable work yet:
> Me neither, but using it to run governors is not the best idea.
> > 
> >    "Add a new deferrable delayed work init.  This can be used to schedule work
> >    that are 'unimportant' when CPU is idle and can be called later, when CPU
> >    eventually comes out of idle."
> > 
> >    28287033e124 ("Add a new deferrable delayed work init")
> > 
> > The commit message mentions that frequency changes were missed due to
> > deferred works being scheduled on an idle CPU. The change to a delayed
> > work seems reasonable to me.
> It is not only the Dynamic Memory Controller and DRAM affected.
> The drivers for GPUs, Network on Chip, cache L3 rely on it.
> They all are missing opportunity to check the HW state and react.
> 
> > 
> > It could make sense to split this change into two patches, one for the
> > change from deferrable to delayed work, and another for custom workqueue
> > to system workqueue (and possibly even a third, transitory change for
> > freezable to non-freezable, if it's confirmed that that's the right
> > thing to do).
> OK, I will split the patch into two: one with delayed work and one with
> regular system workqueue.
> I thought that one patch would be simpler to apply to stable tree if needed.

It's not strictly needed and preferences of different maintainers may
vary (I'm not a maintainer myself). Splitting up a patch may help
getting parts of it landed, while others are still under
discussion. E.g. in this case I'd expect 'deferrable => delayed work'
to be non-controversial (and IIUC it fixes the issue you want to
address), the same if probably true for 'custom workqueue => system
workqueue', however freezable vs. non-freezable might need more
discussion (though it probably won't be lengthy). And you separate the
fix of an actual problems from unrelated improvements, which IMO is
preferable, though there is no hard rule.

Applying a single (simple) patch to stable should indeed be slightly
less work, but I wouldn't expect a short series to cause a huge
overhead. And Greg/stable maintainers might chose to just to take the
one patch with the actual fix and not the 'improvements'.

Cheers

Matthias
Lukasz Luba Feb. 12, 2019, 11:01 a.m. UTC | #4
Hi Matthias,

On 2/11/19 9:54 PM, Matthias Kaehlcke wrote:
> Hi Lukasz,
> 
> On Mon, Feb 11, 2019 at 11:05:27AM +0100, Lukasz Luba wrote:
>> Hi Matthias,
>>
>> My apologize for late response, I did not have access to mailbox.
>> Thank you for review, please check the comments below.
>>
>> On 2/5/19 1:39 AM, Matthias Kaehlcke wrote:
>>> Hi Lukasz,
>>>
>>> On Fri, Feb 01, 2019 at 07:38:03PM +0100, Lukasz Luba wrote:
>>>> This patch removes devfreq's custom workqueue and uses system one.
>>>> It switches from queue_delayed_work() to schedule_delayed_work().
>>>> It also changes deferred work to delayed work, which is now not missed
>>>> when timer is put on CPU that entered idle state.
>>>> The devfreq framework governor was not called, thus changing the frequency
>>>> of the device did not happen.
>>>> Benchmarks for stressing Dynamic Memory Controller show x2
>>>> performance boost with this patch when 'simpleondemand_governor' is
>>>> responsible for monitoring the device load and frequency changes.
>>>> With this patch, the scheduled delayed work is done no mater CPUs' idle.
>>>> It also does not wake up the system when it enters suspend (this
>>>> functionality stays the same).
>>>> All of the drivers in devfreq which rely on periodic, guaranteed wakeup
>>>> intervals should benefit from it.
>>>>
>>>> Signed-off-by: Lukasz Luba <l.luba@partner.samsung.com>
>>>> ---
>>>>    drivers/devfreq/devfreq.c | 27 +++++++--------------------
>>>>    1 file changed, 7 insertions(+), 20 deletions(-)
>>>>
>>>> diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
>>>> index 0ae3de7..c200b3c 100644
>>>> --- a/drivers/devfreq/devfreq.c
>>>> +++ b/drivers/devfreq/devfreq.c
>>>> @@ -31,13 +31,6 @@
>>>>    
>>>>    static struct class *devfreq_class;
>>>>    
>>>> -/*
>>>> - * devfreq core provides delayed work based load monitoring helper
>>>> - * functions. Governors can use these or can implement their own
>>>> - * monitoring mechanism.
>>>> - */
>>>> -static struct workqueue_struct *devfreq_wq;
>>>> -
>>>>    /* The list of all device-devfreq governors */
>>>>    static LIST_HEAD(devfreq_governor_list);
>>>>    /* The list of all device-devfreq */
>>>> @@ -391,8 +384,8 @@ static void devfreq_monitor(struct work_struct *work)
>>>>    	if (err)
>>>>    		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
>>>>    
>>>> -	queue_delayed_work(devfreq_wq, &devfreq->work,
>>>> -				msecs_to_jiffies(devfreq->profile->polling_ms));
>>>> +	schedule_delayed_work(&devfreq->work,
>>>> +			      msecs_to_jiffies(devfreq->profile->polling_ms));
>>>>    	mutex_unlock(&devfreq->lock);
>>>>    }
>>>>    
>>>> @@ -407,9 +400,9 @@ static void devfreq_monitor(struct work_struct *work)
>>>>     */
>>>>    void devfreq_monitor_start(struct devfreq *devfreq)
>>>>    {
>>>> -	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
>>>> +	INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
>>>>    	if (devfreq->profile->polling_ms)
>>>> -		queue_delayed_work(devfreq_wq, &devfreq->work,
>>>> +		schedule_delayed_work(&devfreq->work,
>>>>    			msecs_to_jiffies(devfreq->profile->polling_ms));
>>>>    }
>>>>    EXPORT_SYMBOL(devfreq_monitor_start);
>>>> @@ -473,7 +466,7 @@ void devfreq_monitor_resume(struct devfreq *devfreq)
>>>>    
>>>>    	if (!delayed_work_pending(&devfreq->work) &&
>>>>    			devfreq->profile->polling_ms)
>>>> -		queue_delayed_work(devfreq_wq, &devfreq->work,
>>>> +		schedule_delayed_work(&devfreq->work,
>>>>    			msecs_to_jiffies(devfreq->profile->polling_ms));
>>>>    
>>>>    	devfreq->last_stat_updated = jiffies;
>>>> @@ -516,7 +509,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
>>>>    
>>>>    	/* if current delay is zero, start polling with new delay */
>>>>    	if (!cur_delay) {
>>>> -		queue_delayed_work(devfreq_wq, &devfreq->work,
>>>> +		schedule_delayed_work(&devfreq->work,
>>>>    			msecs_to_jiffies(devfreq->profile->polling_ms));
>>>>    		goto out;
>>>>    	}
>>>> @@ -527,7 +520,7 @@ void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
>>>>    		cancel_delayed_work_sync(&devfreq->work);
>>>>    		mutex_lock(&devfreq->lock);
>>>>    		if (!devfreq->stop_polling)
>>>> -			queue_delayed_work(devfreq_wq, &devfreq->work,
>>>> +			schedule_delayed_work(&devfreq->work,
>>>>    			      msecs_to_jiffies(devfreq->profile->polling_ms));
>>>>    	}
>>>>    out:
>>>> @@ -1430,12 +1423,6 @@ static int __init devfreq_init(void)
>>>>    		return PTR_ERR(devfreq_class);
>>>>    	}
>>>>    
>>>> -	devfreq_wq = create_freezable_workqueue("devfreq_wq");
>>>> -	if (!devfreq_wq) {
>>>> -		class_destroy(devfreq_class);
>>>> -		pr_err("%s: couldn't create workqueue\n", __FILE__);
>>>> -		return -ENOMEM;
>>>> -	}
>>>>    	devfreq_class->dev_groups = devfreq_groups;
>>>>    
>>>>    	return 0;
>>>
>>> If I understand correctly this changes three things:
>>>
>>> 1. use system workqueue instead of custom one
>>>
>>> should be fine with the cwmq's we have nowadays
>>>
>>>
>>> 2. use non-freezable workqueue
>>>
>>>     ``WQ_FREEZABLE``
>>>       A freezable wq participates in the freeze phase of the system
>>>       suspend operations.  Work items on the wq are drained and no
>>>       new work item starts execution until thawed.
>>>
>>> I'm not entirely sure what the impact of this is.
>>>
>>> I imagine suspend is potentially quicker because the wq isn't drained,
>>> but could works that execute during the suspend phase be a problem?
>> I did not check if the suspend is quicker, but I will try to simulate
>> and check these scenarios.
>> I just wanted to get rid of another workqueue in the system.
> 
> Are you sure that freezable vs. non-freezable isn't a problem? I
> suppose there was a reason WQ_FREEZABLE was chosen initially, so I
> don't know if it is still valid.
IMO there is no need to call governors for devfreq devices during
suspend. I have added new functionality in devfreq which sets
  frequency to a marked 'opp-suspend' during suspend.
Even if the devices does not choose the opp-suspend, the governor
calculation and OPP pick-up may be skipped during suspend.
> 
>>> 3. use delayed work instead of deferrable work
>>>
>>> I hadn't come across deferrable work yet:
>> Me neither, but using it to run governors is not the best idea.
>>>
>>>     "Add a new deferrable delayed work init.  This can be used to schedule work
>>>     that are 'unimportant' when CPU is idle and can be called later, when CPU
>>>     eventually comes out of idle."
>>>
>>>     28287033e124 ("Add a new deferrable delayed work init")
>>>
>>> The commit message mentions that frequency changes were missed due to
>>> deferred works being scheduled on an idle CPU. The change to a delayed
>>> work seems reasonable to me.
>> It is not only the Dynamic Memory Controller and DRAM affected.
>> The drivers for GPUs, Network on Chip, cache L3 rely on it.
>> They all are missing opportunity to check the HW state and react.
>>
>>>
>>> It could make sense to split this change into two patches, one for the
>>> change from deferrable to delayed work, and another for custom workqueue
>>> to system workqueue (and possibly even a third, transitory change for
>>> freezable to non-freezable, if it's confirmed that that's the right
>>> thing to do).
>> OK, I will split the patch into two: one with delayed work and one with
>> regular system workqueue.
>> I thought that one patch would be simpler to apply to stable tree if needed.
> 
> It's not strictly needed and preferences of different maintainers may
> vary (I'm not a maintainer myself). Splitting up a patch may help
> getting parts of it landed, while others are still under
> discussion. E.g. in this case I'd expect 'deferrable => delayed work'
> to be non-controversial (and IIUC it fixes the issue you want to
> address), the same if probably true for 'custom workqueue => system
> workqueue', however freezable vs. non-freezable might need more
> discussion (though it probably won't be lengthy). And you separate the
> fix of an actual problems from unrelated improvements, which IMO is
> preferable, though there is no hard rule.
> 
> Applying a single (simple) patch to stable should indeed be slightly
> less work, but I wouldn't expect a short series to cause a huge
> overhead. And Greg/stable maintainers might chose to just to take the
> one patch with the actual fix and not the 'improvements'.
Thank you for the explanation. As you recommended, I will keep the
changes in separate patches. It would be easer to verify an impact on
the system for some devfreq users like GPU developers.

Regards,
Lukasz
> 
> Cheers
> 
> Matthias
> 
>

Patch
diff mbox series

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index 0ae3de7..c200b3c 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -31,13 +31,6 @@ 
 
 static struct class *devfreq_class;
 
-/*
- * devfreq core provides delayed work based load monitoring helper
- * functions. Governors can use these or can implement their own
- * monitoring mechanism.
- */
-static struct workqueue_struct *devfreq_wq;
-
 /* The list of all device-devfreq governors */
 static LIST_HEAD(devfreq_governor_list);
 /* The list of all device-devfreq */
@@ -391,8 +384,8 @@  static void devfreq_monitor(struct work_struct *work)
 	if (err)
 		dev_err(&devfreq->dev, "dvfs failed with (%d) error\n", err);
 
-	queue_delayed_work(devfreq_wq, &devfreq->work,
-				msecs_to_jiffies(devfreq->profile->polling_ms));
+	schedule_delayed_work(&devfreq->work,
+			      msecs_to_jiffies(devfreq->profile->polling_ms));
 	mutex_unlock(&devfreq->lock);
 }
 
@@ -407,9 +400,9 @@  static void devfreq_monitor(struct work_struct *work)
  */
 void devfreq_monitor_start(struct devfreq *devfreq)
 {
-	INIT_DEFERRABLE_WORK(&devfreq->work, devfreq_monitor);
+	INIT_DELAYED_WORK(&devfreq->work, devfreq_monitor);
 	if (devfreq->profile->polling_ms)
-		queue_delayed_work(devfreq_wq, &devfreq->work,
+		schedule_delayed_work(&devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
 }
 EXPORT_SYMBOL(devfreq_monitor_start);
@@ -473,7 +466,7 @@  void devfreq_monitor_resume(struct devfreq *devfreq)
 
 	if (!delayed_work_pending(&devfreq->work) &&
 			devfreq->profile->polling_ms)
-		queue_delayed_work(devfreq_wq, &devfreq->work,
+		schedule_delayed_work(&devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
 
 	devfreq->last_stat_updated = jiffies;
@@ -516,7 +509,7 @@  void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
 
 	/* if current delay is zero, start polling with new delay */
 	if (!cur_delay) {
-		queue_delayed_work(devfreq_wq, &devfreq->work,
+		schedule_delayed_work(&devfreq->work,
 			msecs_to_jiffies(devfreq->profile->polling_ms));
 		goto out;
 	}
@@ -527,7 +520,7 @@  void devfreq_interval_update(struct devfreq *devfreq, unsigned int *delay)
 		cancel_delayed_work_sync(&devfreq->work);
 		mutex_lock(&devfreq->lock);
 		if (!devfreq->stop_polling)
-			queue_delayed_work(devfreq_wq, &devfreq->work,
+			schedule_delayed_work(&devfreq->work,
 			      msecs_to_jiffies(devfreq->profile->polling_ms));
 	}
 out:
@@ -1430,12 +1423,6 @@  static int __init devfreq_init(void)
 		return PTR_ERR(devfreq_class);
 	}
 
-	devfreq_wq = create_freezable_workqueue("devfreq_wq");
-	if (!devfreq_wq) {
-		class_destroy(devfreq_class);
-		pr_err("%s: couldn't create workqueue\n", __FILE__);
-		return -ENOMEM;
-	}
 	devfreq_class->dev_groups = devfreq_groups;
 
 	return 0;