[PATCH v4] media: mediatek: vcodec: Add to support VP9 inner racing mode

[Mingjia Zhang]

In order to reduce decoder latency, enable VP9 inner racing mode.
Send lat trans buffer information to core when trigger lat to work,
need not to wait until lat decode done.

Signed-off-by: Mingjia Zhang <mingjia.zhang@xxxxxxxxxxxx>
---
Changes from v3:

- CTS/GTS test pass
- Fluster result: Ran 275/303 tests successfully

Changes from v2:

- CTS/GTS test pass
- Fluster result: Ran 240/303 tests successfully

Changes from v1:

- CTS/GTS test pass
---
 .../vcodec/vdec/vdec_vp9_req_lat_if.c         | 87 ++++++++++---------
 1 file changed, 48 insertions(+), 39 deletions(-)

diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_req_lat_if.c
index 81de876d51267..baf7ecd54eda3 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_req_lat_if.c
+++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_vp9_req_lat_if.c
@@ -436,6 +436,7 @@ struct vdec_vp9_slice_ref {
  * @frame_ctx:		4 frame context according to VP9 Spec
  * @frame_ctx_helper:	4 frame context according to newest kernel spec
  * @dirty:		state of each frame context
+ * @local_vsi:		local instance vsi information
  * @init_vsi:		vsi used for initialized VP9 instance
  * @vsi:		vsi used for decoding/flush ...
  * @core_vsi:		vsi used for Core stage
@@ -482,6 +483,8 @@ struct vdec_vp9_slice_instance {
 	struct v4l2_vp9_frame_context frame_ctx_helper;
 	unsigned char dirty[4];
 
+	struct vdec_vp9_slice_vsi local_vsi;
+
 	/* MicroP vsi */
 	union {
 		struct vdec_vp9_slice_init_vsi *init_vsi;
@@ -1616,16 +1619,10 @@ static int vdec_vp9_slice_update_single(struct vdec_vp9_slice_instance *instance
 }
 
 static int vdec_vp9_slice_update_lat(struct vdec_vp9_slice_instance *instance,
-				     struct vdec_lat_buf *lat_buf,
-				     struct vdec_vp9_slice_pfc *pfc)
+				     struct vdec_vp9_slice_vsi *vsi)
 {
-	struct vdec_vp9_slice_vsi *vsi;
-
-	vsi = &pfc->vsi;
-	memcpy(&pfc->state[0], &vsi->state, sizeof(vsi->state));
-
 	mtk_vcodec_debug(instance, "Frame %u LAT CRC 0x%08x %lx %lx\n",
-			 pfc->seq, vsi->state.crc[0],
+			 (instance->seq - 1), vsi->state.crc[0],
 			 (unsigned long)vsi->trans.dma_addr,
 			 (unsigned long)vsi->trans.dma_addr_end);
 
@@ -2090,6 +2087,13 @@ static int vdec_vp9_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 		return ret;
 	}
 
+	if (IS_VDEC_INNER_RACING(ctx->dev->dec_capability)) {
+		vdec_vp9_slice_vsi_from_remote(vsi, instance->vsi, 0);
+		memcpy(&instance->local_vsi, vsi, sizeof(*vsi));
+		vdec_msg_queue_qbuf(&ctx->dev->msg_queue_core_ctx, lat_buf);
+		vsi = &instance->local_vsi;
+	}
+
 	if (instance->irq) {
 		ret = mtk_vcodec_wait_for_done_ctx(ctx,	MTK_INST_IRQ_RECEIVED,
 						   WAIT_INTR_TIMEOUT_MS, MTK_VDEC_LAT0);
@@ -2102,22 +2106,25 @@ static int vdec_vp9_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 	}
 
 	vdec_vp9_slice_vsi_from_remote(vsi, instance->vsi, 0);
-	ret = vdec_vp9_slice_update_lat(instance, lat_buf, pfc);
+	ret = vdec_vp9_slice_update_lat(instance, vsi);
 
-	/* LAT trans full, no more UBE or decode timeout */
-	if (ret) {
-		mtk_vcodec_err(instance, "VP9 decode error: %d\n", ret);
-		return ret;
-	}
+	if (!IS_VDEC_INNER_RACING(ctx->dev->dec_capability))
+		/* LAT trans full, no more UBE or decode timeout */
+		if (ret) {
+			mtk_vcodec_err(instance, "frame[%d] decode error: %d\n",
+				       ret, (instance->seq - 1));
+			return ret;
+		}
 
-	mtk_vcodec_debug(instance, "lat dma addr: 0x%lx 0x%lx\n",
-			 (unsigned long)pfc->vsi.trans.dma_addr,
-			 (unsigned long)pfc->vsi.trans.dma_addr_end);
 
-	vdec_msg_queue_update_ube_wptr(&ctx->msg_queue,
-				       vsi->trans.dma_addr_end +
-				       ctx->msg_queue.wdma_addr.dma_addr);
-	vdec_msg_queue_qbuf(&ctx->dev->msg_queue_core_ctx, lat_buf);
+	vsi->trans.dma_addr_end += ctx->msg_queue.wdma_addr.dma_addr;
+	vdec_msg_queue_update_ube_wptr(&ctx->msg_queue, vsi->trans.dma_addr_end);
+	if (!IS_VDEC_INNER_RACING(ctx->dev->dec_capability))
+		vdec_msg_queue_qbuf(&ctx->dev->msg_queue_core_ctx, lat_buf);
+
+	mtk_vcodec_debug(instance, "lat trans end addr(0x%lx), ube start addr(0x%lx)\n",
+			 (unsigned long)vsi->trans.dma_addr_end,
+			 (unsigned long)ctx->msg_queue.wdma_addr.dma_addr);
 
 	return 0;
 }
@@ -2139,40 +2146,40 @@ static int vdec_vp9_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 static int vdec_vp9_slice_core_decode(struct vdec_lat_buf *lat_buf)
 {
 	struct vdec_vp9_slice_instance *instance;
-	struct vdec_vp9_slice_pfc *pfc;
+	struct vdec_vp9_slice_pfc *pfc = NULL;
 	struct mtk_vcodec_ctx *ctx = NULL;
 	struct vdec_fb *fb = NULL;
 	int ret = -EINVAL;
 
 	if (!lat_buf)
-		goto err;
+		return -EINVAL;
 
 	pfc = lat_buf->private_data;
 	ctx = lat_buf->ctx;
 	if (!pfc || !ctx)
-		goto err;
+		return -EINVAL;
 
 	instance = ctx->drv_handle;
 	if (!instance)
-		goto err;
+		return -EINVAL;
 
 	fb = ctx->dev->vdec_pdata->get_cap_buffer(ctx);
 	if (!fb) {
 		ret = -EBUSY;
-		goto err;
+		goto vdec_dec_end;
 	}
 
 	ret = vdec_vp9_slice_setup_core(instance, fb, lat_buf, pfc);
 	if (ret) {
 		mtk_vcodec_err(instance, "vdec_vp9_slice_setup_core\n");
-		goto err;
+		goto vdec_dec_end;
 	}
 	vdec_vp9_slice_vsi_to_remote(&pfc->vsi, instance->core_vsi);
 
 	ret = vpu_dec_core(&instance->vpu);
 	if (ret) {
 		mtk_vcodec_err(instance, "vpu_dec_core\n");
-		goto err;
+		goto vdec_dec_end;
 	}
 
 	if (instance->irq) {
@@ -2190,25 +2197,27 @@ static int vdec_vp9_slice_core_decode(struct vdec_lat_buf *lat_buf)
 	ret = vdec_vp9_slice_update_core(instance, lat_buf, pfc);
 	if (ret) {
 		mtk_vcodec_err(instance, "vdec_vp9_slice_update_core\n");
-		goto err;
+		goto vdec_dec_end;
 	}
 
-	pfc->vsi.trans.dma_addr_end += ctx->msg_queue.wdma_addr.dma_addr;
 	mtk_vcodec_debug(instance, "core dma_addr_end 0x%lx\n",
 			 (unsigned long)pfc->vsi.trans.dma_addr_end);
-	vdec_msg_queue_update_ube_rptr(&ctx->msg_queue, pfc->vsi.trans.dma_addr_end);
-	ctx->dev->vdec_pdata->cap_to_disp(ctx, 0, lat_buf->src_buf_req);
-
-	return 0;
 
-err:
-	if (ctx && pfc) {
-		/* always update read pointer */
-		vdec_msg_queue_update_ube_rptr(&ctx->msg_queue, pfc->vsi.trans.dma_addr_end);
+vdec_dec_end:
+	/* always update read pointer */
+	if (IS_VDEC_INNER_RACING(ctx->dev->dec_capability))
+		vdec_msg_queue_update_ube_rptr(&ctx->msg_queue,
+					       pfc->vsi.trans.dma_addr);
+	else
+		vdec_msg_queue_update_ube_rptr(&ctx->msg_queue,
+					       pfc->vsi.trans.dma_addr_end);
 
+	if (ret)
 		if (fb)
 			ctx->dev->vdec_pdata->cap_to_disp(ctx, 1, lat_buf->src_buf_req);
-	}
+	else
+		ctx->dev->vdec_pdata->cap_to_disp(ctx, 0, lat_buf->src_buf_req);
+
 	return ret;
 }
 
-- 
2.18.0