[PATCH 3/3] drm/xe/oa: Allow preemption to be disabled on the stream exec queue

[Souza, Jose]

On Tue, 2024-06-25 at 13:15 -0700, Ashutosh Dixit wrote:
> Mesa VK_KHR_performance_query use case requires preemption to be disabled
> for the stream exec queue. Implement this functionality here based on the
> new set_no_preempt and clear_no_preempt exec queue ops.

Is this planned to land in the same Kernel version as the other OA patches?
If not would be nice to have some flag indicating that this feature is supported in running kernel, like we have in i915.

uAPI looks good to me, will implement on Mesa tomorrow.

thank you

Acked-by: José Roberto de Souza <jose.souza at intel.com>

> 
> Signed-off-by: Ashutosh Dixit <ashutosh.dixit at intel.com>
> ---
>  drivers/gpu/drm/xe/xe_oa.c       | 33 +++++++++++++++++++++++++++++++-
>  drivers/gpu/drm/xe/xe_oa_types.h |  3 +++
>  include/uapi/drm/xe_drm.h        |  6 ++++++
>  3 files changed, 41 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/gpu/drm/xe/xe_oa.c b/drivers/gpu/drm/xe/xe_oa.c
> index a68659fd5386..6453c36c4539 100644
> --- a/drivers/gpu/drm/xe/xe_oa.c
> +++ b/drivers/gpu/drm/xe/xe_oa.c
> @@ -80,6 +80,7 @@ struct xe_oa_open_param {
>  	int engine_instance;
>  	struct xe_exec_queue *exec_q;
>  	struct xe_hw_engine *hwe;
> +	bool no_preempt;
>  };
>  
>  struct xe_oa_config_bo {
> @@ -1018,6 +1019,13 @@ static int xe_oa_enable_locked(struct xe_oa_stream *stream)
>  	if (stream->enabled)
>  		return 0;
>  
> +	if (stream->no_preempt) {
> +		int ret = stream->exec_q->ops->set_no_preempt(stream->exec_q);
> +
> +		if (ret)
> +			return ret;
> +	}
> +
>  	xe_oa_stream_enable(stream);
>  
>  	stream->enabled = true;
> @@ -1026,13 +1034,18 @@ static int xe_oa_enable_locked(struct xe_oa_stream *stream)
>  
>  static int xe_oa_disable_locked(struct xe_oa_stream *stream)
>  {
> +	int ret = 0;
> +
>  	if (!stream->enabled)
>  		return 0;
>  
>  	xe_oa_stream_disable(stream);
>  
> +	if (stream->no_preempt)
> +		ret = stream->exec_q->ops->clear_no_preempt(stream->exec_q);
> +
>  	stream->enabled = false;
> -	return 0;
> +	return ret;
>  }
>  
>  static long xe_oa_config_locked(struct xe_oa_stream *stream, u64 arg)
> @@ -1307,6 +1320,7 @@ static int xe_oa_stream_init(struct xe_oa_stream *stream,
>  	stream->sample = param->sample;
>  	stream->periodic = param->period_exponent > 0;
>  	stream->period_exponent = param->period_exponent;
> +	stream->no_preempt = param->no_preempt;
>  
>  	/*
>  	 * For Xe2+, when overrun mode is enabled, there are no partial reports at the end
> @@ -1651,6 +1665,13 @@ static int xe_oa_set_prop_engine_instance(struct xe_oa *oa, u64 value,
>  	return 0;
>  }
>  
> +static int xe_oa_set_no_preempt(struct xe_oa *oa, u64 value,
> +				struct xe_oa_open_param *param)
> +{
> +	param->no_preempt = value;
> +	return 0;
> +}
> +
>  typedef int (*xe_oa_set_property_fn)(struct xe_oa *oa, u64 value,
>  				     struct xe_oa_open_param *param);
>  static const xe_oa_set_property_fn xe_oa_set_property_funcs[] = {
> @@ -1662,6 +1683,7 @@ static const xe_oa_set_property_fn xe_oa_set_property_funcs[] = {
>  	[DRM_XE_OA_PROPERTY_OA_DISABLED] = xe_oa_set_prop_disabled,
>  	[DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID] = xe_oa_set_prop_exec_queue_id,
>  	[DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE] = xe_oa_set_prop_engine_instance,
> +	[DRM_XE_OA_PROPERTY_NO_PREEMPT] = xe_oa_set_no_preempt,
>  };
>  
>  static int xe_oa_user_ext_set_property(struct xe_oa *oa, u64 extension,
> @@ -1766,6 +1788,15 @@ int xe_oa_stream_open_ioctl(struct drm_device *dev, u64 data, struct drm_file *f
>  	if (param.exec_q && !param.sample)
>  		privileged_op = false;
>  
> +	if (param.no_preempt) {
> +		if (!param.exec_q) {
> +			drm_dbg(&oa->xe->drm, "Preemption disable without exec_q!\n");
> +			ret = -EINVAL;
> +			goto err_exec_q;
> +		}
> +		privileged_op = true;
> +	}
> +
>  	if (privileged_op && xe_perf_stream_paranoid && !perfmon_capable()) {
>  		drm_dbg(&oa->xe->drm, "Insufficient privileges to open xe perf stream\n");
>  		ret = -EACCES;
> diff --git a/drivers/gpu/drm/xe/xe_oa_types.h b/drivers/gpu/drm/xe/xe_oa_types.h
> index 706d45577dae..540c3ec53a6d 100644
> --- a/drivers/gpu/drm/xe/xe_oa_types.h
> +++ b/drivers/gpu/drm/xe/xe_oa_types.h
> @@ -235,5 +235,8 @@ struct xe_oa_stream {
>  
>  	/** @oa_status: temporary storage for oa_status register value */
>  	u32 oa_status;
> +
> +	/** @no_preempt: Whether preemption and timeslicing is disabled for stream exec_q */
> +	u32 no_preempt;
>  };
>  #endif
> diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
> index b410553faa9b..12eaa8532b5c 100644
> --- a/include/uapi/drm/xe_drm.h
> +++ b/include/uapi/drm/xe_drm.h
> @@ -1611,6 +1611,12 @@ enum drm_xe_oa_property_id {
>  	 * pass along with @DRM_XE_OA_PROPERTY_EXEC_QUEUE_ID or will default to 0.
>  	 */
>  	DRM_XE_OA_PROPERTY_OA_ENGINE_INSTANCE,
> +
> +	/**
> +	 * @DRM_XE_OA_PROPERTY_NO_PREEMPT: Allow preemption and timeslicing
> +	 * to be disabled for the stream exec queue.
> +	 */
> +	DRM_XE_OA_PROPERTY_NO_PREEMPT,
>  };
>  
>  /**