Re: [V9 7/9] drm/amd/pm: add flood detection for wbrf events

["Lazar, Lijo" <lijo.lazar@amd.com>]

On 8/18/2023 8:56 AM, Evan Quan wrote:
> To protect PMFW from being overloaded.
> 
> Signed-off-by: Evan Quan <evan.quan@amd.com>
> Reviewed-by: Mario Limonciello <mario.limonciello@amd.com>
> ---
>   drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c     | 31 +++++++++++++++----
>   drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h |  7 +++++
>   2 files changed, 32 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
> index 704442ce1da3..6c8bcdc17a15 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
> +++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
> @@ -1318,7 +1318,8 @@ static int smu_wbrf_event_handler(struct notifier_block *nb,
>   
>   	switch (action) {
>   	case WBRF_CHANGED:
> -		smu_wbrf_handle_exclusion_ranges(smu);
> +		schedule_delayed_work(&smu->wbrf_delayed_work,
> +				      msecs_to_jiffies(SMU_WBRF_EVENT_HANDLING_PACE));
>   		break;
>   	default:
>   		return NOTIFY_DONE;
> @@ -1327,6 +1328,21 @@ static int smu_wbrf_event_handler(struct notifier_block *nb,
>   	return NOTIFY_OK;
>   }
>   
> +/**
> + * smu_wbrf_delayed_work_handler - callback on delayed work timer expired
> + *
> + * @work: struct work_struct pointer
> + *
> + * Flood is over and driver will consume the latest exclusion ranges.
> + */
> +static void smu_wbrf_delayed_work_handler(struct work_struct *work)
> +{
> +	struct smu_context *smu =
> +		container_of(work, struct smu_context, wbrf_delayed_work.work);
> +
> +	smu_wbrf_handle_exclusion_ranges(smu);
> +}
> +
>   /**
>    * smu_wbrf_support_check - check wbrf support
>    *
> @@ -1357,12 +1373,14 @@ static void smu_wbrf_support_check(struct smu_context *smu)
>    */
>   static int smu_wbrf_init(struct smu_context *smu)
>   {
> -	struct amdgpu_device *adev = smu->adev;
>   	int ret;
>   
>   	if (!smu->wbrf_supported)
>   		return 0;
>   
> +	INIT_DELAYED_WORK(&smu->wbrf_delayed_work,
> +			  smu_wbrf_delayed_work_handler);
> +

This is one-time and can be part of sw_init.

Thanks,
Lijo

>   	smu->wbrf_notifier.notifier_call = smu_wbrf_event_handler;
>   	ret = wbrf_register_notifier(&smu->wbrf_notifier);
>   	if (ret)
> @@ -1373,11 +1391,10 @@ static int smu_wbrf_init(struct smu_context *smu)
>   	 * before our driver loaded. To make sure our driver
>   	 * is awared of those exclusion ranges.
>   	 */
> -	ret = smu_wbrf_handle_exclusion_ranges(smu);
> -	if (ret)
> -		dev_err(adev->dev, "Failed to handle wbrf exclusion ranges\n");
> +	schedule_delayed_work(&smu->wbrf_delayed_work,
> +			      msecs_to_jiffies(SMU_WBRF_EVENT_HANDLING_PACE));
>   
> -	return ret;
> +	return 0;
>   }
>   
>   /**
> @@ -1393,6 +1410,8 @@ static void smu_wbrf_fini(struct smu_context *smu)
>   		return;
>   
>   	wbrf_unregister_notifier(&smu->wbrf_notifier);
> +
> +	cancel_delayed_work_sync(&smu->wbrf_delayed_work);
>   }
>   
>   static int smu_smc_hw_setup(struct smu_context *smu)
> diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
> index 244297979f92..4d5cb1b511e5 100644
> --- a/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
> +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/amdgpu_smu.h
> @@ -480,6 +480,12 @@ struct stb_context {
>   
>   #define WORKLOAD_POLICY_MAX 7
>   
> +/*
> + * Configure wbrf event handling pace as there can be only one
> + * event processed every SMU_WBRF_EVENT_HANDLING_PACE ms.
> + */
> +#define SMU_WBRF_EVENT_HANDLING_PACE	10
> +
>   struct smu_context
>   {
>   	struct amdgpu_device            *adev;
> @@ -581,6 +587,7 @@ struct smu_context
>   	/* data structures for wbrf feature support */
>   	bool				wbrf_supported;
>   	struct notifier_block		wbrf_notifier;
> +	struct delayed_work		wbrf_delayed_work;
>   };
>   
>   struct i2c_adapter;