Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit c130456c authored by Changbin Du's avatar Changbin Du Committed by Zhenyu Wang
Browse files

drm/i915/gvt: Kick scheduler when new workload queued 



The current schedule policy rely on a 1ms timer to execute workload. This
can introduce maximum 1ms unnecessary latency. This is especially bad for
small media workloads.

And I don't think we need this timer for QoS, but the change is not simply
remove the code. So I made a new API intel_gvt_kick_schedule() for future
change.

Signed-off-by: default avatarChangbin Du <changbin.du@intel.com>
Signed-off-by: default avatarZhenyu Wang <zhenyuw@linux.intel.com>
parent 59a716c6

drivers/gpu/drm/i915/gvt/sched_policy.c

+5 −0
Original line number Diff line number Diff line
@@ -372,6 +372,11 @@ void intel_vgpu_start_schedule(struct intel_vgpu *vgpu) 
	vgpu->gvt->scheduler.sched_ops->start_schedule(vgpu);

}



void intel_gvt_kick_schedule(struct intel_gvt *gvt)

{

	intel_gvt_request_service(gvt, INTEL_GVT_REQUEST_EVENT_SCHED);

}



void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)

{

	struct intel_gvt_workload_scheduler *scheduler =

drivers/gpu/drm/i915/gvt/sched_policy.h

+2 −0
Original line number Diff line number Diff line
@@ -57,4 +57,6 @@ void intel_vgpu_start_schedule(struct intel_vgpu *vgpu); 


void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu);



void intel_gvt_kick_schedule(struct intel_gvt *gvt);



#endif

drivers/gpu/drm/i915/gvt/scheduler.c

+1 −0
Original line number Diff line number Diff line
@@ -1337,5 +1337,6 @@ void intel_vgpu_queue_workload(struct intel_vgpu_workload *workload) 
{

	list_add_tail(&workload->list,

		workload_q_head(workload->vgpu, workload->ring_id));

	intel_gvt_kick_schedule(workload->vgpu->gvt);

	wake_up(&workload->vgpu->gvt->scheduler.waitq[workload->ring_id]);

}