[Patch V2] drm/amdgpu: Increase tlb flush timeout for sriov

[Christian König]

Am 10.08.22 um 10:50 schrieb Dusica Milinkovic:
> [Why]
> During multi-vf executing benchmark (Luxmark) observed kiq error timeout.
> It happenes because all of VFs do the tlb invalidation at the same time.
> Although each VF has the invalidate register set, from hardware side
> the invalidate requests are queue to execute.
>
> [How]
> In case of 12 VF increase timeout on 12*100ms
>
> Signed-off-by: Dusica Milinkovic <Dusica.Milinkovic at amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 6 +++++-
>   drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c  | 6 +++++-
>   2 files changed, 10 insertions(+), 2 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> index 9ae8cdaa033e..5743975efea5 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> @@ -419,6 +419,7 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
>   	uint32_t seq;
>   	uint16_t queried_pasid;
>   	bool ret;
> +	uint32_t sriov_usec_timeout = 1200000;  /* wait for 12 * 100ms for SRIOV */

Please put that as a define into some header and never ever write 
comments at the same line after a define.



>   	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
>   	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
>   
> @@ -437,7 +438,10 @@ static int gmc_v10_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
>   
>   		amdgpu_ring_commit(ring);
>   		spin_unlock(&adev->gfx.kiq.ring_lock);
> -		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
> +		if (amdgpu_sriov_vf(adev))
> +			r = amdgpu_fence_wait_polling(ring, seq, sriov_usec_timeout);
> +		else
> +			r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);

Don't duplicate the whole call, just change the parameter.

Regards,
Christian.

>   		if (r < 1) {
>   			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
>   			return -ETIME;
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index ab89d91975ab..bab26982b3f9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -896,6 +896,7 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
>   	uint32_t seq;
>   	uint16_t queried_pasid;
>   	bool ret;
> +	uint32_t sriov_usec_timeout = 1200000;  /* wait for 12 * 100ms for SRIOV */
>   	struct amdgpu_ring *ring = &adev->gfx.kiq.ring;
>   	struct amdgpu_kiq *kiq = &adev->gfx.kiq;
>   
> @@ -935,7 +936,10 @@ static int gmc_v9_0_flush_gpu_tlb_pasid(struct amdgpu_device *adev,
>   
>   		amdgpu_ring_commit(ring);
>   		spin_unlock(&adev->gfx.kiq.ring_lock);
> -		r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
> +		if (amdgpu_sriov_vf(adev))
> +			r = amdgpu_fence_wait_polling(ring, seq, sriov_usec_timeout);
> +		else
> +			r = amdgpu_fence_wait_polling(ring, seq, adev->usec_timeout);
>   		if (r < 1) {
>   			dev_err(adev->dev, "wait for kiq fence error: %ld.\n", r);
>   			up_read(&adev->reset_domain->sem);