[PATCH 2/2] drm/amdgpu: fix assigning nil entry in compute_prio_sched

Christian König christian.koenig at amd.com
Tue Mar 10 11:42:43 UTC 2020


Am 10.03.20 um 12:27 schrieb Nirmoy Das:
> If there is no high priority compute queue then set normal
> priority sched array to compute_prio_sched[AMDGPU_GFX_PIPE_PRIO_HIGH]

Please move that patch to the beginning of the series since it is a bug fix.

Thanks,
Christian.

>
> Signed-off-by: Nirmoy Das <nirmoy.das at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c | 16 ++++++++++++----
>   1 file changed, 12 insertions(+), 4 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> index 99875dd633e6..01faeb8b4ef2 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
> @@ -478,10 +478,18 @@ static void amdgpu_ring_init_compute_sched(struct amdgpu_device *adev)
>   	adev->gfx.num_compute_sched[i] = num_compute_sched_normal;
>   
>   	i = AMDGPU_GFX_PIPE_PRIO_HIGH;
> -	adev->gfx.compute_prio_sched[i] =
> -		&adev->gfx.compute_sched[num_compute_sched_high - 1];
> -	adev->gfx.num_compute_sched[i] =
> -		adev->gfx.num_compute_rings - num_compute_sched_normal;
> +	if (num_compute_sched_high == (AMDGPU_MAX_COMPUTE_RINGS - 1)) {
> +		/* When compute has no high priority rings then use */
> +		/* normal priority sched array */
> +		adev->gfx.compute_prio_sched[i] = &adev->gfx.compute_sched[0];
> +		adev->gfx.num_compute_sched[i] = num_compute_sched_normal;
> +	} else {
> +
> +		adev->gfx.compute_prio_sched[i] =
> +			&adev->gfx.compute_sched[num_compute_sched_high - 1];
> +		adev->gfx.num_compute_sched[i] =
> +			adev->gfx.num_compute_rings - num_compute_sched_normal;
> +	}
>   }
>   
>   /**



More information about the amd-gfx mailing list