[PATCH v2, 7/7] media: mtk-vcodec: Add to support H264 inner racing mode

[Yunfei Dong <yunfei.dong@mediatek.com>]

In order to reduce decoder latency, enable H264 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: Yunfei Dong <yunfei.dong@mediatek.com>
---
 .../platform/mtk-vcodec/mtk_vcodec_dec_drv.c  |  4 +++
 .../platform/mtk-vcodec/mtk_vcodec_dec_pm.c   | 34 +++++++++++++++++++
 .../platform/mtk-vcodec/mtk_vcodec_drv.h      | 10 ++++++
 .../mtk-vcodec/vdec/vdec_h264_req_multi_if.c  | 23 ++++++++++---
 4 files changed, 66 insertions(+), 5 deletions(-)

diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
index 938bf14e4e8c..099dc28b7445 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
@@ -390,6 +390,10 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 		}
 	}
 
+	atomic_set(&dev->dec_active_cnt, 0);
+	memset(dev->vdec_racing_info, 0 , sizeof(dev->vdec_racing_info));
+	mutex_init(&dev->dec_racing_info_mutex);
+
 	if (dev->vdec_pdata->uses_stateless_api) {
 		dev->mdev_dec.dev = &pdev->dev;
 		strscpy(dev->mdev_dec.model, MTK_VCODEC_DEC_NAME,
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_pm.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_pm.c
index 76e1442fc6f9..065d14a3d11f 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_pm.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_pm.c
@@ -173,6 +173,34 @@ static void mtk_vcodec_dec_disable_irq(struct mtk_vcodec_dev *vdec_dev, int hw_i
 	}
 }
 
+static void mtk_vcodec_load_racing_info(struct mtk_vcodec_ctx *ctx)
+{
+	void __iomem *vdec_racing_addr;
+	int j;
+
+	mutex_lock(&ctx->dev->dec_racing_info_mutex);
+	if (atomic_inc_return(&ctx->dev->dec_active_cnt) == 1) {
+		vdec_racing_addr = ctx->dev->reg_base[VDEC_MISC] + 0x100;
+		for (j = 0; j < 132; j++)
+			writel(ctx->dev->vdec_racing_info[j], vdec_racing_addr + j * 4);
+	}
+	mutex_unlock(&ctx->dev->dec_racing_info_mutex);
+}
+
+static void mtk_vcodec_record_racing_info(struct mtk_vcodec_ctx *ctx)
+{
+	void __iomem *vdec_racing_addr;
+	int j;
+
+	mutex_lock(&ctx->dev->dec_racing_info_mutex);
+	if (atomic_dec_and_test(&ctx->dev->dec_active_cnt)) {
+		vdec_racing_addr = ctx->dev->reg_base[VDEC_MISC] + 0x100;
+		for (j = 0; j < 132; j++)
+			ctx->dev->vdec_racing_info[j] = readl(vdec_racing_addr + j * 4);
+	}
+	mutex_unlock(&ctx->dev->dec_racing_info_mutex);
+}
+
 static struct mtk_vcodec_pm *mtk_vcodec_dec_get_pm(struct mtk_vcodec_dev *vdec_dev,
 						   int hw_idx)
 {
@@ -243,11 +271,17 @@ void mtk_vcodec_dec_enable_hardware(struct mtk_vcodec_ctx *ctx, int hw_idx)
 	mtk_vcodec_dec_child_dev_on(ctx->dev, hw_idx);
 
 	mtk_vcodec_dec_enable_irq(ctx->dev, hw_idx);
+
+	if (IS_VDEC_INNER_RACING(ctx->dev->dec_capability))
+		mtk_vcodec_load_racing_info(ctx);
 }
 EXPORT_SYMBOL_GPL(mtk_vcodec_dec_enable_hardware);
 
 void mtk_vcodec_dec_disable_hardware(struct mtk_vcodec_ctx *ctx, int hw_idx)
 {
+	if (IS_VDEC_INNER_RACING(ctx->dev->dec_capability))
+		mtk_vcodec_record_racing_info(ctx);
+
 	mtk_vcodec_dec_disable_irq(ctx->dev, hw_idx);
 
 	mtk_vcodec_dec_child_dev_off(ctx->dev, hw_idx);
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
index 363b999dd709..4d6ace869b5a 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
@@ -28,6 +28,7 @@
 #define MTK_V4L2_BENCHMARK	0
 #define WAIT_INTR_TIMEOUT_MS	1000
 #define IS_VDEC_LAT_ARCH(hw_arch) ((hw_arch) >= MTK_VDEC_LAT_SINGLE_CORE)
+#define IS_VDEC_INNER_RACING(capability) (capability & MTK_VCODEC_INNER_RACING)
 
 /*
  * enum mtk_hw_reg_idx - MTK hw register base index
@@ -360,6 +361,7 @@ enum mtk_vdec_format_types {
 	MTK_VDEC_FORMAT_H264_SLICE = 0x100,
 	MTK_VDEC_FORMAT_VP8_FRAME = 0x200,
 	MTK_VDEC_FORMAT_VP9_FRAME = 0x400,
+	MTK_VCODEC_INNER_RACING = 0x20000,
 };
 
 /**
@@ -480,6 +482,10 @@ struct mtk_vcodec_enc_pdata {
  * @subdev_dev: subdev hardware device
  * @subdev_prob_done: check whether all used hw device is prob done
  * @subdev_bitmap: used to record hardware is ready or not
+ *
+ * @dec_active_cnt: used to mark whether need to record register value
+ * @vdec_racing_info: record register value
+ * @dec_racing_info_mutex: mutex lock used for inner racing mode
  */
 struct mtk_vcodec_dev {
 	struct v4l2_device v4l2_dev;
@@ -525,6 +531,10 @@ struct mtk_vcodec_dev {
 	void *subdev_dev[MTK_VDEC_HW_MAX];
 	int (*subdev_prob_done)(struct mtk_vcodec_dev *vdec_dev);
 	DECLARE_BITMAP(subdev_bitmap, MTK_VDEC_HW_MAX);
+
+	atomic_t dec_active_cnt;
+	u32 vdec_racing_info[132];
+	struct mutex dec_racing_info_mutex;
 };
 
 static inline struct mtk_vcodec_ctx *fh_to_ctx(struct v4l2_fh *fh)
diff --git a/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_multi_if.c b/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_multi_if.c
index 5541edbafed2..988d1d12d5c8 100644
--- a/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_multi_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_multi_if.c
@@ -617,6 +617,17 @@ static int vdec_h264_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 		goto err_free_fb_out;
 	}
 
+	share_info->trans_end = inst->ctx->msg_queue.wdma_addr.dma_addr +
+		inst->vsi->wdma_end_addr_offset;
+	share_info->trans_start = inst->ctx->msg_queue.wdma_wptr_addr;
+	share_info->nal_info = inst->vsi->dec.nal_info;
+
+	if (IS_VDEC_INNER_RACING(inst->ctx->dev->dec_capability)) {
+		memcpy(&share_info->h264_slice_params, &inst->vsi->h264_slice_params,
+		       sizeof(share_info->h264_slice_params));
+		vdec_msg_queue_qbuf(&inst->ctx->dev->msg_queue_core_ctx, lat_buf);
+	}
+
 	/* wait decoder done interrupt */
 	timeout = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED,
 					       WAIT_INTR_TIMEOUT_MS, MTK_VDEC_LAT0);
@@ -630,14 +641,16 @@ static int vdec_h264_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 
 	share_info->trans_end = inst->ctx->msg_queue.wdma_addr.dma_addr +
 		inst->vsi->wdma_end_addr_offset;
-	share_info->trans_start = inst->ctx->msg_queue.wdma_wptr_addr;
-	share_info->nal_info = inst->vsi->dec.nal_info;
 	vdec_msg_queue_update_ube_wptr(&lat_buf->ctx->msg_queue,
 				       share_info->trans_end);
 
-	memcpy(&share_info->h264_slice_params, &inst->vsi->h264_slice_params,
-	       sizeof(share_info->h264_slice_params));
-	vdec_msg_queue_qbuf(&inst->ctx->dev->msg_queue_core_ctx, lat_buf);
+	if (!IS_VDEC_INNER_RACING(inst->ctx->dev->dec_capability)) {
+		memcpy(&share_info->h264_slice_params, &inst->vsi->h264_slice_params,
+		       sizeof(share_info->h264_slice_params));
+		vdec_msg_queue_qbuf(&inst->ctx->dev->msg_queue_core_ctx, lat_buf);
+	}
+	mtk_vcodec_debug(inst, "lat crc: 0x%x 0x%x 0x%x", inst->vsi->dec.crc[0],
+			 inst->vsi->dec.crc[1], inst->vsi->dec.crc[2]);
 	inst->slice_dec_num++;
 
 err_free_fb_out:
-- 
2.25.1