diff --git a/drivers/gpu/drm/i915/gvt/dmabuf.c b/drivers/gpu/drm/i915/gvt/dmabuf.c
index 6e3f56684f4e..51ed99a37803 100644
--- a/drivers/gpu/drm/i915/gvt/dmabuf.c
+++ b/drivers/gpu/drm/i915/gvt/dmabuf.c
@@ -170,20 +170,22 @@ static struct drm_i915_gem_object *vgpu_create_gem(struct drm_device *dev,
 		unsigned int tiling_mode = 0;
 		unsigned int stride = 0;
 
-		switch (info->drm_format_mod << 10) {
-		case PLANE_CTL_TILED_LINEAR:
+		switch (info->drm_format_mod) {
+		case DRM_FORMAT_MOD_LINEAR:
 			tiling_mode = I915_TILING_NONE;
 			break;
-		case PLANE_CTL_TILED_X:
+		case I915_FORMAT_MOD_X_TILED:
 			tiling_mode = I915_TILING_X;
 			stride = info->stride;
 			break;
-		case PLANE_CTL_TILED_Y:
+		case I915_FORMAT_MOD_Y_TILED:
+		case I915_FORMAT_MOD_Yf_TILED:
 			tiling_mode = I915_TILING_Y;
 			stride = info->stride;
 			break;
 		default:
-			gvt_dbg_core("not supported tiling mode\n");
+			gvt_dbg_core("invalid drm_format_mod %llx for tiling\n",
+				     info->drm_format_mod);
 		}
 		obj->tiling_and_stride = tiling_mode | stride;
 	} else {
@@ -222,9 +224,26 @@ static int vgpu_get_plane_info(struct drm_device *dev,
 		info->height = p.height;
 		info->stride = p.stride;
 		info->drm_format = p.drm_format;
-		info->drm_format_mod = p.tiled;
+
+		switch (p.tiled) {
+		case PLANE_CTL_TILED_LINEAR:
+			info->drm_format_mod = DRM_FORMAT_MOD_LINEAR;
+			break;
+		case PLANE_CTL_TILED_X:
+			info->drm_format_mod = I915_FORMAT_MOD_X_TILED;
+			break;
+		case PLANE_CTL_TILED_Y:
+			info->drm_format_mod = I915_FORMAT_MOD_Y_TILED;
+			break;
+		case PLANE_CTL_TILED_YF:
+			info->drm_format_mod = I915_FORMAT_MOD_Yf_TILED;
+			break;
+		default:
+			gvt_vgpu_err("invalid tiling mode: %x\n", p.tiled);
+		}
+
 		info->size = (((p.stride * p.height * p.bpp) / 8) +
-				(PAGE_SIZE - 1)) >> PAGE_SHIFT;
+			      (PAGE_SIZE - 1)) >> PAGE_SHIFT;
 	} else if (plane_id == DRM_PLANE_TYPE_CURSOR) {
 		ret = intel_vgpu_decode_cursor_plane(vgpu, &c);
 		if (ret)
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c
index face664be3e8..481896fb712a 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.c
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c
@@ -220,8 +220,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 	if (IS_SKYLAKE(dev_priv)
 		|| IS_KABYLAKE(dev_priv)
 		|| IS_BROXTON(dev_priv)) {
-		plane->tiled = (val & PLANE_CTL_TILED_MASK) >>
-		_PLANE_CTL_TILED_SHIFT;
+		plane->tiled = val & PLANE_CTL_TILED_MASK;
 		fmt = skl_format_to_drm(
 			val & PLANE_CTL_FORMAT_MASK,
 			val & PLANE_CTL_ORDER_RGBX,
@@ -260,7 +259,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu,
 		return  -EINVAL;
 	}
 
-	plane->stride = intel_vgpu_get_stride(vgpu, pipe, (plane->tiled << 10),
+	plane->stride = intel_vgpu_get_stride(vgpu, pipe, plane->tiled,
 		(IS_SKYLAKE(dev_priv)
 		|| IS_KABYLAKE(dev_priv)
 		|| IS_BROXTON(dev_priv)) ?
diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.h b/drivers/gpu/drm/i915/gvt/fb_decoder.h
index cb055f3c81a2..60c155085029 100644
--- a/drivers/gpu/drm/i915/gvt/fb_decoder.h
+++ b/drivers/gpu/drm/i915/gvt/fb_decoder.h
@@ -101,7 +101,7 @@ struct intel_gvt;
 /* color space conversion and gamma correction are not included */
 struct intel_vgpu_primary_plane_format {
 	u8	enabled;	/* plane is enabled */
-	u8	tiled;		/* X-tiled */
+	u32	tiled;		/* tiling mode: linear, X-tiled, Y tiled, etc */
 	u8	bpp;		/* bits per pixel */
 	u32	hw_format;	/* format field in the PRI_CTL register */
 	u32	drm_format;	/* format in DRM definition */
diff --git a/drivers/gpu/drm/i915/gvt/handlers.c b/drivers/gpu/drm/i915/gvt/handlers.c
index 7a58ca555197..72afa518edd9 100644
--- a/drivers/gpu/drm/i915/gvt/handlers.c
+++ b/drivers/gpu/drm/i915/gvt/handlers.c
@@ -1296,6 +1296,19 @@ static int power_well_ctl_mmio_write(struct intel_vgpu *vgpu,
 	return 0;
 }
 
+static int gen9_dbuf_ctl_mmio_write(struct intel_vgpu *vgpu,
+		unsigned int offset, void *p_data, unsigned int bytes)
+{
+	write_vreg(vgpu, offset, p_data, bytes);
+
+	if (vgpu_vreg(vgpu, offset) & DBUF_POWER_REQUEST)
+		vgpu_vreg(vgpu, offset) |= DBUF_POWER_STATE;
+	else
+		vgpu_vreg(vgpu, offset) &= ~DBUF_POWER_STATE;
+
+	return 0;
+}
+
 static int fpga_dbg_mmio_write(struct intel_vgpu *vgpu,
 	unsigned int offset, void *p_data, unsigned int bytes)
 {
@@ -1525,9 +1538,15 @@ static int bxt_phy_ctl_family_write(struct intel_vgpu *vgpu,
 	u32 v = *(u32 *)p_data;
 	u32 data = v & COMMON_RESET_DIS ? BXT_PHY_LANE_ENABLED : 0;
 
-	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data;
-	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data;
-	vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data;
+	switch (offset) {
+	case _PHY_CTL_FAMILY_EDP:
+		vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_A) = data;
+		break;
+	case _PHY_CTL_FAMILY_DDI:
+		vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_B) = data;
+		vgpu_vreg(vgpu, _BXT_PHY_CTL_DDI_C) = data;
+		break;
+	}
 
 	vgpu_vreg(vgpu, offset) = v;
 
@@ -2812,6 +2831,8 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_DH(HSW_PWR_WELL_CTL_DRIVER(SKL_DISP_PW_MISC_IO), D_SKL_PLUS, NULL,
 		skl_power_well_ctl_write);
 
+	MMIO_DH(DBUF_CTL, D_SKL_PLUS, NULL, gen9_dbuf_ctl_mmio_write);
+
 	MMIO_D(_MMIO(0xa210), D_SKL_PLUS);
 	MMIO_D(GEN9_MEDIA_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
 	MMIO_D(GEN9_RENDER_PG_IDLE_HYSTERESIS, D_SKL_PLUS);
@@ -2987,8 +3008,6 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 		NULL, gen9_trtte_write);
 	MMIO_DH(_MMIO(0x4dfc), D_SKL_PLUS, NULL, gen9_trtt_chicken_write);
 
-	MMIO_D(_MMIO(0x45008), D_SKL_PLUS);
-
 	MMIO_D(_MMIO(0x46430), D_SKL_PLUS);
 
 	MMIO_D(_MMIO(0x46520), D_SKL_PLUS);
@@ -3025,7 +3044,9 @@ static int init_skl_mmio_info(struct intel_gvt *gvt)
 	MMIO_D(_MMIO(0x44500), D_SKL_PLUS);
 	MMIO_DFH(GEN9_CSFE_CHICKEN1_RCS, D_SKL_PLUS, F_CMD_ACCESS, NULL, NULL);
 	MMIO_DFH(GEN8_HDC_CHICKEN1, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
-		NULL, NULL);
+		 NULL, NULL);
+	MMIO_DFH(GEN9_WM_CHICKEN3, D_SKL_PLUS, F_MODE_MASK | F_CMD_ACCESS,
+		 NULL, NULL);
 
 	MMIO_D(_MMIO(0x4ab8), D_KBL);
 	MMIO_D(_MMIO(0x2248), D_KBL | D_SKL);
diff --git a/drivers/gpu/drm/i915/gvt/mmio_context.c b/drivers/gpu/drm/i915/gvt/mmio_context.c
index 42e1e6bdcc2c..e872f4847fbe 100644
--- a/drivers/gpu/drm/i915/gvt/mmio_context.c
+++ b/drivers/gpu/drm/i915/gvt/mmio_context.c
@@ -562,11 +562,9 @@ void intel_gvt_switch_mmio(struct intel_vgpu *pre,
 	 * performace for batch mmio read/write, so we need
 	 * handle forcewake mannually.
 	 */
-	intel_runtime_pm_get(dev_priv);
 	intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
 	switch_mmio(pre, next, ring_id);
 	intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
-	intel_runtime_pm_put(dev_priv);
 }
 
 /**
diff --git a/drivers/gpu/drm/i915/gvt/sched_policy.c b/drivers/gpu/drm/i915/gvt/sched_policy.c
index 09d7bb72b4ff..c32e7d5e8629 100644
--- a/drivers/gpu/drm/i915/gvt/sched_policy.c
+++ b/drivers/gpu/drm/i915/gvt/sched_policy.c
@@ -47,11 +47,15 @@ static bool vgpu_has_pending_workload(struct intel_vgpu *vgpu)
 	return false;
 }
 
+/* We give 2 seconds higher prio for vGPU during start */
+#define GVT_SCHED_VGPU_PRI_TIME  2
+
 struct vgpu_sched_data {
 	struct list_head lru_list;
 	struct intel_vgpu *vgpu;
 	bool active;
-
+	bool pri_sched;
+	ktime_t pri_time;
 	ktime_t sched_in_time;
 	ktime_t sched_time;
 	ktime_t left_ts;
@@ -183,6 +187,14 @@ static struct intel_vgpu *find_busy_vgpu(struct gvt_sched_data *sched_data)
 		if (!vgpu_has_pending_workload(vgpu_data->vgpu))
 			continue;
 
+		if (vgpu_data->pri_sched) {
+			if (ktime_before(ktime_get(), vgpu_data->pri_time)) {
+				vgpu = vgpu_data->vgpu;
+				break;
+			} else
+				vgpu_data->pri_sched = false;
+		}
+
 		/* Return the vGPU only if it has time slice left */
 		if (vgpu_data->left_ts > 0) {
 			vgpu = vgpu_data->vgpu;
@@ -202,6 +214,7 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data)
 	struct intel_gvt_workload_scheduler *scheduler = &gvt->scheduler;
 	struct vgpu_sched_data *vgpu_data;
 	struct intel_vgpu *vgpu = NULL;
+
 	/* no active vgpu or has already had a target */
 	if (list_empty(&sched_data->lru_runq_head) || scheduler->next_vgpu)
 		goto out;
@@ -209,12 +222,13 @@ static void tbs_sched_func(struct gvt_sched_data *sched_data)
 	vgpu = find_busy_vgpu(sched_data);
 	if (vgpu) {
 		scheduler->next_vgpu = vgpu;
-
-		/* Move the last used vGPU to the tail of lru_list */
 		vgpu_data = vgpu->sched_data;
-		list_del_init(&vgpu_data->lru_list);
-		list_add_tail(&vgpu_data->lru_list,
-				&sched_data->lru_runq_head);
+		if (!vgpu_data->pri_sched) {
+			/* Move the last used vGPU to the tail of lru_list */
+			list_del_init(&vgpu_data->lru_list);
+			list_add_tail(&vgpu_data->lru_list,
+				      &sched_data->lru_runq_head);
+		}
 	} else {
 		scheduler->next_vgpu = gvt->idle_vgpu;
 	}
@@ -328,11 +342,17 @@ static void tbs_sched_start_schedule(struct intel_vgpu *vgpu)
 {
 	struct gvt_sched_data *sched_data = vgpu->gvt->scheduler.sched_data;
 	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+	ktime_t now;
 
 	if (!list_empty(&vgpu_data->lru_list))
 		return;
 
-	list_add_tail(&vgpu_data->lru_list, &sched_data->lru_runq_head);
+	now = ktime_get();
+	vgpu_data->pri_time = ktime_add(now,
+					ktime_set(GVT_SCHED_VGPU_PRI_TIME, 0));
+	vgpu_data->pri_sched = true;
+
+	list_add(&vgpu_data->lru_list, &sched_data->lru_runq_head);
 
 	if (!hrtimer_active(&sched_data->timer))
 		hrtimer_start(&sched_data->timer, ktime_add_ns(ktime_get(),
@@ -426,6 +446,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 		&vgpu->gvt->scheduler;
 	int ring_id;
 	struct vgpu_sched_data *vgpu_data = vgpu->sched_data;
+	struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv;
 
 	if (!vgpu_data->active)
 		return;
@@ -444,6 +465,7 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 		scheduler->current_vgpu = NULL;
 	}
 
+	intel_runtime_pm_get(dev_priv);
 	spin_lock_bh(&scheduler->mmio_context_lock);
 	for (ring_id = 0; ring_id < I915_NUM_ENGINES; ring_id++) {
 		if (scheduler->engine_owner[ring_id] == vgpu) {
@@ -452,5 +474,6 @@ void intel_vgpu_stop_schedule(struct intel_vgpu *vgpu)
 		}
 	}
 	spin_unlock_bh(&scheduler->mmio_context_lock);
+	intel_runtime_pm_put(dev_priv);
 	mutex_unlock(&vgpu->gvt->sched_lock);
 }