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

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
......@@ -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 =
......
......@@ -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
......@@ -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]);
}
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment