From: Ping Gao <ping.a.gao@intel.com>
Date: Wed, 29 Mar 2017 16:36:40 +0000 (+0800)
Subject: drm/i915/gvt: control the scheduler by timeslice usage
X-Git-Tag: v4.12~21^2~4^2~11^2~9
X-Git-Url: http://review.tizen.org/git/?a=commitdiff_plain;h=b35f34d1da4e77637869c8041a355da810f69fb6;p=platform%2Fkernel%2Flinux-exynos.git

drm/i915/gvt: control the scheduler by timeslice usage

The timeslice usage will determine vGPU whether has chance to
schedule or not at every vGPU switch checkpoint.

Signed-off-by: Ping Gao <ping.a.gao@intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Zhenyu Wang <zhenyuw@linux.intel.com>
---

diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index dd5b38c..f849591 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -187,8 +187,11 @@ static struct intel_vgpu *find_busy_vgpu(struct gvt_sched_data *sched_data)
 		if (!vgpu_has_pending_workload(vgpu_data->vgpu))
 			continue;
 
-		vgpu = vgpu_data->vgpu;
-		break;
+		/* Return the vGPU only if it has time slice left */
+		if (vgpu_data->left_ts > 0) {
+			vgpu = vgpu_data->vgpu;
+			break;
+		}
 	}
 
 	return vgpu;
@@ -223,6 +226,8 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data)
 				&sched_data->lru_runq_head);
 
 		gvt_dbg_sched("pick next vgpu %d\n", vgpu->id);
+	} else {
+		scheduler->next_vgpu = gvt->idle_vgpu;
 	}
 out:
 	if (scheduler->next_vgpu) {