Re: [PATCH] amdgpu: Don't print L2 status if there's nothing to print

[Felix Kuehling <felix.kuehling@xxxxxxx>]

On 2024-10-18 16:21, Kent Russell wrote:
> If a 2nd fault comes in before the 1st is handled, the 1st fault will
> clear out the FAULT STATUS registers before the 2nd fault is handled.
> Thus we get a lot of zeroes. If status=0, just skip the L2 fault status
> information, to avoid confusion of why some VM fault status prints in
> dmesg are all zeroes.
>
> Signed-off-by: Kent Russell <kent.russell@xxxxxxx>

Reviewed-by: Felix Kuehling <felix.kuehling@xxxxxxx>


> ---
>   drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c | 5 ++++-
>   drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c | 5 ++++-
>   drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c | 5 ++++-
>   drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c  | 6 ++++++
>   4 files changed, 18 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> index 5cf2002fcba8..5fe7a1c74ff1 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v10_0.c
> @@ -175,7 +175,10 @@ static int gmc_v10_0_process_interrupt(struct amdgpu_device *adev,
>   			addr, entry->client_id,
>   			soc15_ih_clientid_name[entry->client_id]);
>   
> -	if (!amdgpu_sriov_vf(adev))
> +	/* Only print L2 fault status if the status register could be read and
> +	 * contains useful information
> +	 */
> +	if (status != 0)
>   		hub->vmhub_funcs->print_l2_protection_fault_status(adev,
>   								   status);
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
> index 4df4d73038f8..25a3dee27d81 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v11_0.c
> @@ -144,7 +144,10 @@ static int gmc_v11_0_process_interrupt(struct amdgpu_device *adev,
>   		dev_err(adev->dev, "  in page starting at address 0x%016llx from client %d\n",
>   				addr, entry->client_id);
>   
> -		if (!amdgpu_sriov_vf(adev))
> +		/* Only print L2 fault status if the status register could be read and
> +		 * contains useful information
> +		 */
> +		if (status != 0)
>   			hub->vmhub_funcs->print_l2_protection_fault_status(adev, status);
>   	}
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
> index e33f9e9058cc..3dee7474c06d 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v12_0.c
> @@ -137,7 +137,10 @@ static int gmc_v12_0_process_interrupt(struct amdgpu_device *adev,
>   		dev_err(adev->dev, "  in page starting at address 0x%016llx from client %d\n",
>   				addr, entry->client_id);
>   
> -		if (!amdgpu_sriov_vf(adev))
> +		/* Only print L2 fault status if the status register could be read and
> +		 * contains useful information
> +		 */
> +		if (status != 0)
>   			hub->vmhub_funcs->print_l2_protection_fault_status(adev, status);
>   	}
>   
> diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> index 010db0e58650..f43ded8a0aab 100644
> --- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> +++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
> @@ -672,6 +672,12 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
>   	    (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 4, 2)))
>   		return 0;
>   
> +	/* Only print L2 fault status if the status register could be read and
> +	 * contains useful information
> +	 */
> +	if (!status)
> +		return 0;
> +
>   	if (!amdgpu_sriov_vf(adev))
>   		WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
>