[PATCH] drm/panfrost: Handle resetting on timeout better

[PATCH] drm/panfrost: Handle resetting on timeout better

[Steven Price]

Panfrost uses multiple schedulers (one for each slot, so 2 in reality),
and on a timeout has to stop all the schedulers to safely perform a
reset. However more than one scheduler can trigger a timeout at the same
time. This race condition results in jobs being freed while they are
still in use.

When stopping other slots use cancel_delayed_work_sync() to ensure that
any timeout started for that slot has completed. Also use
mutex_trylock() to obtain reset_lock. This means that only one thread
attempts the reset, the other threads will simply complete without doing
anything (the first thread will wait for this in the call to
cancel_delayed_work_sync()).

While we're here and since the function is already dependent on
sched_job not being NULL, let's remove the unnecessary checks, along
with a commented out call to panfrost_core_dump() which has never
existed in mainline.

Signed-off-by: Steven Price <steven.price@arm.com>
---
This is a tidied up version of the patch orginally posted here:
http://lkml.kernel.org/r/26ae2a4d-8df1-e8db-3060-41638ed63e2a%40arm.com

 drivers/gpu/drm/panfrost/panfrost_job.c | 17 +++++++++++------
 1 file changed, 11 insertions(+), 6 deletions(-)

diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
index a58551668d9a..dcc9a7603685 100644
--- a/drivers/gpu/drm/panfrost/panfrost_job.c
+++ b/drivers/gpu/drm/panfrost/panfrost_job.c
@@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 		job_read(pfdev, JS_TAIL_LO(js)),
 		sched_job);
 
-	mutex_lock(&pfdev->reset_lock);
+	if (!mutex_trylock(&pfdev->reset_lock))
+		return;
 
-	for (i = 0; i < NUM_JOB_SLOTS; i++)
-		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
+	for (i = 0; i < NUM_JOB_SLOTS; i++) {
+		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
+
+		drm_sched_stop(sched, sched_job);
+		if (js != i)
+			/* Ensure any timeouts on other slots have finished */
+			cancel_delayed_work_sync(&sched->work_tdr);
+	}
 
-	if (sched_job)
-		drm_sched_increase_karma(sched_job);
+	drm_sched_increase_karma(sched_job);
 
 	spin_lock_irqsave(&pfdev->js->job_lock, flags);
 	for (i = 0; i < NUM_JOB_SLOTS; i++) {
@@ -398,7 +404,6 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
 	}
 	spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
 
-	/* panfrost_core_dump(pfdev); */
 
 	panfrost_devfreq_record_transition(pfdev, js);
 	panfrost_device_reset(pfdev);
-- 
2.20.1

Re: [PATCH] drm/panfrost: Handle resetting on timeout better

[Neil Armstrong]

Hi Steven,

On 07/10/2019 14:50, Steven Price wrote:
> Panfrost uses multiple schedulers (one for each slot, so 2 in reality),
> and on a timeout has to stop all the schedulers to safely perform a
> reset. However more than one scheduler can trigger a timeout at the same
> time. This race condition results in jobs being freed while they are
> still in use.
> 
> When stopping other slots use cancel_delayed_work_sync() to ensure that
> any timeout started for that slot has completed. Also use
> mutex_trylock() to obtain reset_lock. This means that only one thread
> attempts the reset, the other threads will simply complete without doing
> anything (the first thread will wait for this in the call to
> cancel_delayed_work_sync()).
> 
> While we're here and since the function is already dependent on
> sched_job not being NULL, let's remove the unnecessary checks, along
> with a commented out call to panfrost_core_dump() which has never
> existed in mainline.
> 

A Fixes: tags would be welcome here so it would be backported to v5.3

> Signed-off-by: Steven Price <steven.price@arm.com>
> ---
> This is a tidied up version of the patch orginally posted here:
> http://lkml.kernel.org/r/26ae2a4d-8df1-e8db-3060-41638ed63e2a%40arm.com
> 
>  drivers/gpu/drm/panfrost/panfrost_job.c | 17 +++++++++++------
>  1 file changed, 11 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
> index a58551668d9a..dcc9a7603685 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
> @@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
>  		job_read(pfdev, JS_TAIL_LO(js)),
>  		sched_job);
>  
> -	mutex_lock(&pfdev->reset_lock);
> +	if (!mutex_trylock(&pfdev->reset_lock))
> +		return;
>  
> -	for (i = 0; i < NUM_JOB_SLOTS; i++)
> -		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
> +	for (i = 0; i < NUM_JOB_SLOTS; i++) {
> +		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
> +
> +		drm_sched_stop(sched, sched_job);
> +		if (js != i)
> +			/* Ensure any timeouts on other slots have finished */
> +			cancel_delayed_work_sync(&sched->work_tdr);
> +	}
>  
> -	if (sched_job)
> -		drm_sched_increase_karma(sched_job);
> +	drm_sched_increase_karma(sched_job);

Indeed looks cleaner.

>  
>  	spin_lock_irqsave(&pfdev->js->job_lock, flags);
>  	for (i = 0; i < NUM_JOB_SLOTS; i++) {
> @@ -398,7 +404,6 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
>  	}
>  	spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
>  
> -	/* panfrost_core_dump(pfdev); */

This should be cleaned in another patch !

>  
>  	panfrost_devfreq_record_transition(pfdev, js);
>  	panfrost_device_reset(pfdev);
> 

Thanks,
Testing it right now with the last change removed (doesn't apply on v5.3 with it),
results in a few hours... or minutes !


Neil

Re: [PATCH] drm/panfrost: Handle resetting on timeout better

[Tomeu Vizoso]

On 10/7/19 6:09 AM, Neil Armstrong wrote:
> Hi Steven,
> 
> On 07/10/2019 14:50, Steven Price wrote:
>> Panfrost uses multiple schedulers (one for each slot, so 2 in reality),
>> and on a timeout has to stop all the schedulers to safely perform a
>> reset. However more than one scheduler can trigger a timeout at the same
>> time. This race condition results in jobs being freed while they are
>> still in use.
>>
>> When stopping other slots use cancel_delayed_work_sync() to ensure that
>> any timeout started for that slot has completed. Also use
>> mutex_trylock() to obtain reset_lock. This means that only one thread
>> attempts the reset, the other threads will simply complete without doing
>> anything (the first thread will wait for this in the call to
>> cancel_delayed_work_sync()).
>>
>> While we're here and since the function is already dependent on
>> sched_job not being NULL, let's remove the unnecessary checks, along
>> with a commented out call to panfrost_core_dump() which has never
>> existed in mainline.
>>
> 
> A Fixes: tags would be welcome here so it would be backported to v5.3
> 
>> Signed-off-by: Steven Price <steven.price@arm.com>
>> ---
>> This is a tidied up version of the patch orginally posted here:
>> http://lkml.kernel.org/r/26ae2a4d-8df1-e8db-3060-41638ed63e2a%40arm.com
>>
>>   drivers/gpu/drm/panfrost/panfrost_job.c | 17 +++++++++++------
>>   1 file changed, 11 insertions(+), 6 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
>> index a58551668d9a..dcc9a7603685 100644
>> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
>> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
>> @@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
>>   		job_read(pfdev, JS_TAIL_LO(js)),
>>   		sched_job);
>>   
>> -	mutex_lock(&pfdev->reset_lock);
>> +	if (!mutex_trylock(&pfdev->reset_lock))
>> +		return;
>>   
>> -	for (i = 0; i < NUM_JOB_SLOTS; i++)
>> -		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
>> +	for (i = 0; i < NUM_JOB_SLOTS; i++) {
>> +		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
>> +
>> +		drm_sched_stop(sched, sched_job);
>> +		if (js != i)
>> +			/* Ensure any timeouts on other slots have finished */
>> +			cancel_delayed_work_sync(&sched->work_tdr);
>> +	}
>>   
>> -	if (sched_job)
>> -		drm_sched_increase_karma(sched_job);
>> +	drm_sched_increase_karma(sched_job);
> 
> Indeed looks cleaner.
> 
>>   
>>   	spin_lock_irqsave(&pfdev->js->job_lock, flags);
>>   	for (i = 0; i < NUM_JOB_SLOTS; i++) {
>> @@ -398,7 +404,6 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
>>   	}
>>   	spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
>>   
>> -	/* panfrost_core_dump(pfdev); */
> 
> This should be cleaned in another patch !

Seems to me that this should be some kind of TODO, see 
etnaviv_core_dump() for the kind of things we could be doing.

Maybe we can delete this line and mention this in the TODO file?

Cheers,

Tomeu

>>   
>>   	panfrost_devfreq_record_transition(pfdev, js);
>>   	panfrost_device_reset(pfdev);
>>
> 
> Thanks,
> Testing it right now with the last change removed (doesn't apply on v5.3 with it),
> results in a few hours... or minutes !
> 
> 
> Neil
> 

Re: [PATCH] drm/panfrost: Handle resetting on timeout better

[Steven Price]

On 07/10/2019 17:14, Tomeu Vizoso wrote:
> On 10/7/19 6:09 AM, Neil Armstrong wrote:
>> Hi Steven,
>>
>> On 07/10/2019 14:50, Steven Price wrote:
>>> Panfrost uses multiple schedulers (one for each slot, so 2 in reality),
>>> and on a timeout has to stop all the schedulers to safely perform a
>>> reset. However more than one scheduler can trigger a timeout at the same
>>> time. This race condition results in jobs being freed while they are
>>> still in use.
>>>
>>> When stopping other slots use cancel_delayed_work_sync() to ensure that
>>> any timeout started for that slot has completed. Also use
>>> mutex_trylock() to obtain reset_lock. This means that only one thread
>>> attempts the reset, the other threads will simply complete without doing
>>> anything (the first thread will wait for this in the call to
>>> cancel_delayed_work_sync()).
>>>
>>> While we're here and since the function is already dependent on
>>> sched_job not being NULL, let's remove the unnecessary checks, along
>>> with a commented out call to panfrost_core_dump() which has never
>>> existed in mainline.
>>>
>>
>> A Fixes: tags would be welcome here so it would be backported to v5.3
>>
>>> Signed-off-by: Steven Price <steven.price@arm.com>
>>> ---
>>> This is a tidied up version of the patch orginally posted here:
>>> http://lkml.kernel.org/r/26ae2a4d-8df1-e8db-3060-41638ed63e2a%40arm.com
>>>
>>>   drivers/gpu/drm/panfrost/panfrost_job.c | 17 +++++++++++------
>>>   1 file changed, 11 insertions(+), 6 deletions(-)
>>>
>>> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c
>>> b/drivers/gpu/drm/panfrost/panfrost_job.c
>>> index a58551668d9a..dcc9a7603685 100644
>>> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
>>> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
>>> @@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct
>>> drm_sched_job *sched_job)
>>>           job_read(pfdev, JS_TAIL_LO(js)),
>>>           sched_job);
>>>   -    mutex_lock(&pfdev->reset_lock);
>>> +    if (!mutex_trylock(&pfdev->reset_lock))
>>> +        return;
>>>   -    for (i = 0; i < NUM_JOB_SLOTS; i++)
>>> -        drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
>>> +    for (i = 0; i < NUM_JOB_SLOTS; i++) {
>>> +        struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
>>> +
>>> +        drm_sched_stop(sched, sched_job);
>>> +        if (js != i)
>>> +            /* Ensure any timeouts on other slots have finished */
>>> +            cancel_delayed_work_sync(&sched->work_tdr);
>>> +    }
>>>   -    if (sched_job)
>>> -        drm_sched_increase_karma(sched_job);
>>> +    drm_sched_increase_karma(sched_job);
>>
>> Indeed looks cleaner.
>>
>>>         spin_lock_irqsave(&pfdev->js->job_lock, flags);
>>>       for (i = 0; i < NUM_JOB_SLOTS; i++) {
>>> @@ -398,7 +404,6 @@ static void panfrost_job_timedout(struct
>>> drm_sched_job *sched_job)
>>>       }
>>>       spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
>>>   -    /* panfrost_core_dump(pfdev); */
>>
>> This should be cleaned in another patch !
> 
> Seems to me that this should be some kind of TODO, see
> etnaviv_core_dump() for the kind of things we could be doing.
> 
> Maybe we can delete this line and mention this in the TODO file?

Fair enough - I'll split this into a separate patch and add an entry to
the TODO file. kbase has a mechanism to "dump on job fault" [1],[2] so
we could do something similar.

Steve

[1]
https://gitlab.freedesktop.org/panfrost/mali_kbase/blob/master/driver/product/kernel/drivers/gpu/arm/midgard/backend/gpu/mali_kbase_debug_job_fault_backend.c

[2]
https://gitlab.freedesktop.org/panfrost/mali_kbase/blob/master/driver/product/kernel/drivers/gpu/arm/midgard/mali_kbase_debug_job_fault.c

> Cheers,
> 
> Tomeu
> 
>>>         panfrost_devfreq_record_transition(pfdev, js);
>>>       panfrost_device_reset(pfdev);
>>>
>>
>> Thanks,
>> Testing it right now with the last change removed (doesn't apply on
>> v5.3 with it),
>> results in a few hours... or minutes !
>>
>>
>> Neil
>>
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH] drm/panfrost: Handle resetting on timeout better

[Neil Armstrong]

On 07/10/2019 14:50, Steven Price wrote:
> Panfrost uses multiple schedulers (one for each slot, so 2 in reality),
> and on a timeout has to stop all the schedulers to safely perform a
> reset. However more than one scheduler can trigger a timeout at the same
> time. This race condition results in jobs being freed while they are
> still in use.
> 
> When stopping other slots use cancel_delayed_work_sync() to ensure that
> any timeout started for that slot has completed. Also use
> mutex_trylock() to obtain reset_lock. This means that only one thread
> attempts the reset, the other threads will simply complete without doing
> anything (the first thread will wait for this in the call to
> cancel_delayed_work_sync()).
> 
> While we're here and since the function is already dependent on
> sched_job not being NULL, let's remove the unnecessary checks, along
> with a commented out call to panfrost_core_dump() which has never
> existed in mainline.
> 
> Signed-off-by: Steven Price <steven.price@arm.com>
> ---
> This is a tidied up version of the patch orginally posted here:
> http://lkml.kernel.org/r/26ae2a4d-8df1-e8db-3060-41638ed63e2a%40arm.com
> 
>  drivers/gpu/drm/panfrost/panfrost_job.c | 17 +++++++++++------
>  1 file changed, 11 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/panfrost/panfrost_job.c b/drivers/gpu/drm/panfrost/panfrost_job.c
> index a58551668d9a..dcc9a7603685 100644
> --- a/drivers/gpu/drm/panfrost/panfrost_job.c
> +++ b/drivers/gpu/drm/panfrost/panfrost_job.c
> @@ -381,13 +381,19 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
>  		job_read(pfdev, JS_TAIL_LO(js)),
>  		sched_job);
>  
> -	mutex_lock(&pfdev->reset_lock);
> +	if (!mutex_trylock(&pfdev->reset_lock))
> +		return;
>  
> -	for (i = 0; i < NUM_JOB_SLOTS; i++)
> -		drm_sched_stop(&pfdev->js->queue[i].sched, sched_job);
> +	for (i = 0; i < NUM_JOB_SLOTS; i++) {
> +		struct drm_gpu_scheduler *sched = &pfdev->js->queue[i].sched;
> +
> +		drm_sched_stop(sched, sched_job);
> +		if (js != i)
> +			/* Ensure any timeouts on other slots have finished */
> +			cancel_delayed_work_sync(&sched->work_tdr);
> +	}
>  
> -	if (sched_job)
> -		drm_sched_increase_karma(sched_job);
> +	drm_sched_increase_karma(sched_job);
>  
>  	spin_lock_irqsave(&pfdev->js->job_lock, flags);
>  	for (i = 0; i < NUM_JOB_SLOTS; i++) {
> @@ -398,7 +404,6 @@ static void panfrost_job_timedout(struct drm_sched_job *sched_job)
>  	}
>  	spin_unlock_irqrestore(&pfdev->js->job_lock, flags);
>  
> -	/* panfrost_core_dump(pfdev); */
>  
>  	panfrost_devfreq_record_transition(pfdev, js);
>  	panfrost_device_reset(pfdev);
> 

It ran successfully 10 dEQP tests without crashing the Amlogic S912 with Mali T820:
Tested-by: Neil Armstrong <narmstrong@baylibre.com>