diff mbox series

[v5,13/27] drm/amdgpu: When filizing the fence driver. stop scheduler first.

Message ID 20210428151207.1212258-14-andrey.grodzovsky@amd.com (mailing list archive)
State Superseded
Headers show
Series RFC Support hot device unplug in amdgpu | expand

Commit Message

Andrey Grodzovsky April 28, 2021, 3:11 p.m. UTC
No point calling amdgpu_fence_wait_empty before stopping the
SW scheduler otherwise there is always a chance another job sneaked
in after the wait.

Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
---
 drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 9 +++++++--
 1 file changed, 7 insertions(+), 2 deletions(-)

Comments

Christian König April 29, 2021, 7:15 a.m. UTC | #1
Filizing the fences? You mean finishing the fences, don't you? :)

Am 28.04.21 um 17:11 schrieb Andrey Grodzovsky:
> No point calling amdgpu_fence_wait_empty before stopping the
> SW scheduler otherwise there is always a chance another job sneaked
> in after the wait.
>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 9 +++++++--
>   1 file changed, 7 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 34d51e962799..fd9282637549 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -533,6 +533,12 @@ void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
>   
>   		if (!ring || !ring->fence_drv.initialized)
>   			continue;
> +
> +		/* Stop any new job submissions from sched before flushing the ring */
> +		/* TODO Handle amdgpu_job_submit_direct and amdgpu_amdkfd_submit_ib */
> +		if (!ring->no_scheduler)
> +			drm_sched_fini(&ring->sched);
> +
>   		r = amdgpu_fence_wait_empty(ring);
>   		if (r) {
>   			/* no need to trigger GPU reset as we are unloading */
> @@ -541,8 +547,7 @@ void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
>   		if (ring->fence_drv.irq_src)
>   			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
>   				       ring->fence_drv.irq_type);
> -		if (!ring->no_scheduler)
> -			drm_sched_fini(&ring->sched);
> +
>   		del_timer_sync(&ring->fence_drv.fallback_timer);
>   	}
>   }
Andrey Grodzovsky April 29, 2021, 5:12 p.m. UTC | #2
On 2021-04-29 3:15 a.m., Christian König wrote:
> 
> Filizing the fences? You mean finishing the fences, don't you? :)

Yes, my bad.

Andrey

> 
> Am 28.04.21 um 17:11 schrieb Andrey Grodzovsky:
>> No point calling amdgpu_fence_wait_empty before stopping the
>> SW scheduler otherwise there is always a chance another job sneaked
>> in after the wait.
>>
>> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
>> ---
>>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 9 +++++++--
>>   1 file changed, 7 insertions(+), 2 deletions(-)
>>
>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c 
>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> index 34d51e962799..fd9282637549 100644
>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
>> @@ -533,6 +533,12 @@ void amdgpu_fence_driver_fini_hw(struct 
>> amdgpu_device *adev)
>>           if (!ring || !ring->fence_drv.initialized)
>>               continue;
>> +
>> +        /* Stop any new job submissions from sched before flushing 
>> the ring */
>> +        /* TODO Handle amdgpu_job_submit_direct and 
>> amdgpu_amdkfd_submit_ib */
>> +        if (!ring->no_scheduler)
>> +            drm_sched_fini(&ring->sched);
>> +
>>           r = amdgpu_fence_wait_empty(ring);
>>           if (r) {
>>               /* no need to trigger GPU reset as we are unloading */
>> @@ -541,8 +547,7 @@ void amdgpu_fence_driver_fini_hw(struct 
>> amdgpu_device *adev)
>>           if (ring->fence_drv.irq_src)
>>               amdgpu_irq_put(adev, ring->fence_drv.irq_src,
>>                          ring->fence_drv.irq_type);
>> -        if (!ring->no_scheduler)
>> -            drm_sched_fini(&ring->sched);
>> +
>>           del_timer_sync(&ring->fence_drv.fallback_timer);
>>       }
>>   }
>
diff mbox series

Patch

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 34d51e962799..fd9282637549 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -533,6 +533,12 @@  void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
 
 		if (!ring || !ring->fence_drv.initialized)
 			continue;
+
+		/* Stop any new job submissions from sched before flushing the ring */
+		/* TODO Handle amdgpu_job_submit_direct and amdgpu_amdkfd_submit_ib */
+		if (!ring->no_scheduler)
+			drm_sched_fini(&ring->sched);
+
 		r = amdgpu_fence_wait_empty(ring);
 		if (r) {
 			/* no need to trigger GPU reset as we are unloading */
@@ -541,8 +547,7 @@  void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
 		if (ring->fence_drv.irq_src)
 			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
 				       ring->fence_drv.irq_type);
-		if (!ring->no_scheduler)
-			drm_sched_fini(&ring->sched);
+
 		del_timer_sync(&ring->fence_drv.fallback_timer);
 	}
 }