[PATCH 07/11] drm/amdgpu/gfx11: add support for disable_kq

[Khatri, Sunil]

Reviewed-by: Sunil Khatri <sunil.khatri at amd.com>

On 3/6/2025 2:17 AM, Alex Deucher wrote:
> Plumb in support for disabling kernel queues in
> GFX11.  We have to bring up a GFX queue briefly in
> order to initialize the clear state.  After that
> we can disable it.
>
> Signed-off-by: Alex Deucher <alexander.deucher at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 77 +++++++++++++++++---------
>   1 file changed, 51 insertions(+), 26 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
> index 3e49c0f399e02..e18100c5faa2a 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
> @@ -1128,6 +1128,10 @@ static int gfx_v11_0_gfx_ring_init(struct amdgpu_device *adev, int ring_id,
>   
>   	ring->ring_obj = NULL;
>   	ring->use_doorbell = true;
> +	if (adev->gfx.disable_kq) {
> +		ring->no_scheduler = true;
> +		ring->no_user_submission = true;
> +	}
>   
>   	if (!ring_id)
>   		ring->doorbell_index = adev->doorbell_index.gfx_ring0 << 1;
> @@ -1709,21 +1713,23 @@ static int gfx_v11_0_sw_init(struct amdgpu_ip_block *ip_block)
>   		}
>   	}
>   
> -	ring_id = 0;
> -	/* set up the compute queues - allocate horizontally across pipes */
> -	for (i = 0; i < adev->gfx.mec.num_mec; ++i) {
> -		for (j = 0; j < adev->gfx.mec.num_queue_per_pipe; j++) {
> -			for (k = 0; k < adev->gfx.mec.num_pipe_per_mec; k++) {
> -				if (!amdgpu_gfx_is_mec_queue_enabled(adev, 0, i,
> -								     k, j))
> -					continue;
> +	if (!adev->gfx.disable_kq) {
> +		ring_id = 0;
> +		/* set up the compute queues - allocate horizontally across pipes */
> +		for (i = 0; i < adev->gfx.mec.num_mec; ++i) {
> +			for (j = 0; j < adev->gfx.mec.num_queue_per_pipe; j++) {
> +				for (k = 0; k < adev->gfx.mec.num_pipe_per_mec; k++) {
> +					if (!amdgpu_gfx_is_mec_queue_enabled(adev, 0, i,
> +									     k, j))
> +						continue;
>   
> -				r = gfx_v11_0_compute_ring_init(adev, ring_id,
> -								i, k, j);
> -				if (r)
> -					return r;
> +					r = gfx_v11_0_compute_ring_init(adev, ring_id,
> +									i, k, j);
> +					if (r)
> +						return r;
>   
> -				ring_id++;
> +					ring_id++;
> +				}
>   			}
>   		}
>   	}
> @@ -1823,8 +1829,10 @@ static int gfx_v11_0_sw_fini(struct amdgpu_ip_block *ip_block)
>   
>   	for (i = 0; i < adev->gfx.num_gfx_rings; i++)
>   		amdgpu_ring_fini(&adev->gfx.gfx_ring[i]);
> -	for (i = 0; i < adev->gfx.num_compute_rings; i++)
> -		amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
> +	if (!adev->gfx.disable_kq) {
> +		for (i = 0; i < adev->gfx.num_compute_rings; i++)
> +			amdgpu_ring_fini(&adev->gfx.compute_ring[i]);
> +	}
>   
>   	amdgpu_gfx_mqd_sw_fini(adev, 0);
>   
> @@ -4489,6 +4497,9 @@ static int gfx_v11_0_kcq_resume(struct amdgpu_device *adev)
>   	if (!amdgpu_async_gfx_ring)
>   		gfx_v11_0_cp_compute_enable(adev, true);
>   
> +	if (adev->gfx.disable_kq)
> +		return 0;
> +
>   	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
>   		ring = &adev->gfx.compute_ring[i];
>   
> @@ -4561,18 +4572,29 @@ static int gfx_v11_0_cp_resume(struct amdgpu_device *adev)
>   			return r;
>   	}
>   
> -	for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
> -		ring = &adev->gfx.gfx_ring[i];
> -		r = amdgpu_ring_test_helper(ring);
> -		if (r)
> -			return r;
> -	}
> +	if (adev->gfx.disable_kq) {
> +		for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
> +			ring = &adev->gfx.gfx_ring[i];
> +			/* we don't want to set ring->ready */
> +			r = amdgpu_ring_test_ring(ring);
> +			if (r)
> +				return r;
> +		}
> +		amdgpu_gfx_disable_kgq(adev, 0);
> +	} else {
> +		for (i = 0; i < adev->gfx.num_gfx_rings; i++) {
> +			ring = &adev->gfx.gfx_ring[i];
> +			r = amdgpu_ring_test_helper(ring);
> +			if (r)
> +				return r;
> +		}
>   
> -	for (i = 0; i < adev->gfx.num_compute_rings; i++) {
> -		ring = &adev->gfx.compute_ring[i];
> -		r = amdgpu_ring_test_helper(ring);
> -		if (r)
> -			return r;
> +		for (i = 0; i < adev->gfx.num_compute_rings; i++) {
> +			ring = &adev->gfx.compute_ring[i];
> +			r = amdgpu_ring_test_helper(ring);
> +			if (r)
> +				return r;
> +		}
>   	}
>   
>   	return 0;
> @@ -5111,6 +5133,9 @@ static int gfx_v11_0_early_init(struct amdgpu_ip_block *ip_block)
>   {
>   	struct amdgpu_device *adev = ip_block->adev;
>   
> +	if (amdgpu_disable_kq == 1)
> +		adev->gfx.disable_kq = true;
> +
>   	adev->gfx.funcs = &gfx_v11_0_gfx_funcs;
>   
>   	adev->gfx.num_gfx_rings = GFX11_NUM_GFX_RINGS;