Merge v6.5-rc1 into drm-misc-fixes

Boris needs 6.5-rc1 in drm-misc-fixes to prevent a conflict.

Signed-off-by: Maxime Ripard <mripard@kernel.org>

19 files changed, 3874 insertions, 100 deletions

diff --git a/drivers/media/platform/mediatek/vcodec/Makefile b/drivers/media/platform/mediatek/vcodec/Makefile
index 93e7a343b5b0..5f4c30fec85a 100644
--- a/drivers/media/platform/mediatek/vcodec/Makefile
+++ b/drivers/media/platform/mediatek/vcodec/Makefile
@@ -10,9 +10,11 @@ mtk-vcodec-dec-y := vdec/vdec_h264_if.o \
 		vdec/vdec_vp8_req_if.o \
 		vdec/vdec_vp9_if.o \
 		vdec/vdec_vp9_req_lat_if.o \
+		vdec/vdec_av1_req_lat_if.o \
 		vdec/vdec_h264_req_if.o \
 		vdec/vdec_h264_req_common.o \
 		vdec/vdec_h264_req_multi_if.o \
+		vdec/vdec_hevc_req_multi_if.o \
 		mtk_vcodec_dec_drv.o \
 		vdec_drv_if.o \
 		vdec_vpu_if.o \
@@ -44,3 +46,9 @@ endif
 ifneq ($(CONFIG_VIDEO_MEDIATEK_VCODEC_SCP),)
 mtk-vcodec-common-y += mtk_vcodec_fw_scp.o
 endif
+
+ifneq ($(CONFIG_DEBUG_FS),)
+obj-$(CONFIG_VIDEO_MEDIATEK_VCODEC) += mtk-vcodec-dbgfs.o
+
+mtk-vcodec-dbgfs-y := mtk_vcodec_dbgfs.o
+endif
\ No newline at end of file
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dbgfs.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dbgfs.c
new file mode 100644
index 000000000000..b5cdbbfcc388
--- /dev/null
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dbgfs.c
@@ -0,0 +1,215 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 MediaTek Inc.
+ * Author: Yunfei Dong <yunfei.dong@mediatek.com>
+ */
+
+#include <linux/debugfs.h>
+
+#include "mtk_vcodec_dbgfs.h"
+#include "mtk_vcodec_drv.h"
+#include "mtk_vcodec_util.h"
+
+static void mtk_vdec_dbgfs_get_format_type(struct mtk_vcodec_ctx *ctx, char *buf,
+					   int *used, int total)
+{
+	int curr_len;
+
+	switch (ctx->current_codec) {
+	case V4L2_PIX_FMT_H264_SLICE:
+		curr_len = snprintf(buf + *used, total - *used,
+				    "\toutput format: h264 slice\n");
+		break;
+	case V4L2_PIX_FMT_VP8_FRAME:
+		curr_len = snprintf(buf + *used, total - *used,
+				    "\toutput format: vp8 slice\n");
+		break;
+	case V4L2_PIX_FMT_VP9_FRAME:
+		curr_len = snprintf(buf + *used, total - *used,
+				    "\toutput format: vp9 slice\n");
+		break;
+	default:
+		curr_len = snprintf(buf + *used, total - *used,
+				    "\tunsupported output format: 0x%x\n",
+				    ctx->current_codec);
+	}
+	*used += curr_len;
+
+	switch (ctx->capture_fourcc) {
+	case V4L2_PIX_FMT_MM21:
+		curr_len = snprintf(buf + *used, total - *used,
+				    "\tcapture format: MM21\n");
+		break;
+	case V4L2_PIX_FMT_MT21C:
+		curr_len = snprintf(buf + *used, total - *used,
+				    "\tcapture format: MT21C\n");
+		break;
+	default:
+		curr_len = snprintf(buf + *used, total - *used,
+				    "\tunsupported capture format: 0x%x\n",
+				    ctx->capture_fourcc);
+	}
+	*used += curr_len;
+}
+
+static void mtk_vdec_dbgfs_get_help(char *buf, int *used, int total)
+{
+	int curr_len;
+
+	curr_len = snprintf(buf + *used, total - *used,
+			    "help: (1: echo -'info' > vdec 2: cat vdec)\n");
+	*used += curr_len;
+
+	curr_len = snprintf(buf + *used, total - *used,
+			    "\t-picinfo: get resolution\n");
+	*used += curr_len;
+
+	curr_len = snprintf(buf + *used, total - *used,
+			    "\t-format: get output & capture queue format\n");
+	*used += curr_len;
+}
+
+static ssize_t mtk_vdec_dbgfs_write(struct file *filp, const char __user *ubuf,
+				    size_t count, loff_t *ppos)
+{
+	struct mtk_vcodec_dev *vcodec_dev = filp->private_data;
+	struct mtk_vcodec_dbgfs *dbgfs = &vcodec_dev->dbgfs;
+
+	mutex_lock(&dbgfs->dbgfs_lock);
+	dbgfs->buf_size = simple_write_to_buffer(dbgfs->dbgfs_buf, sizeof(dbgfs->dbgfs_buf),
+						 ppos, ubuf, count);
+	mutex_unlock(&dbgfs->dbgfs_lock);
+	if (dbgfs->buf_size > 0)
+		return count;
+
+	return dbgfs->buf_size;
+}
+
+static ssize_t mtk_vdec_dbgfs_read(struct file *filp, char __user *ubuf,
+				   size_t count, loff_t *ppos)
+{
+	struct mtk_vcodec_dev *vcodec_dev = filp->private_data;
+	struct mtk_vcodec_dbgfs *dbgfs = &vcodec_dev->dbgfs;
+	struct mtk_vcodec_dbgfs_inst *dbgfs_inst;
+	struct mtk_vcodec_ctx *ctx;
+	int total_len = 200 * (dbgfs->inst_count == 0 ? 1 : dbgfs->inst_count);
+	int used_len = 0, curr_len, ret;
+	bool dbgfs_index[MTK_VDEC_DBGFS_MAX] = {0};
+	char *buf = kmalloc(total_len, GFP_KERNEL);
+
+	if (!buf)
+		return -ENOMEM;
+
+	if (strstr(dbgfs->dbgfs_buf, "-help") || dbgfs->buf_size == 1) {
+		mtk_vdec_dbgfs_get_help(buf, &used_len, total_len);
+		goto read_buffer;
+	}
+
+	if (strstr(dbgfs->dbgfs_buf, "-picinfo"))
+		dbgfs_index[MTK_VDEC_DBGFS_PICINFO] = true;
+
+	if (strstr(dbgfs->dbgfs_buf, "-format"))
+		dbgfs_index[MTK_VDEC_DBGFS_FORMAT] = true;
+
+	mutex_lock(&dbgfs->dbgfs_lock);
+	list_for_each_entry(dbgfs_inst, &dbgfs->dbgfs_head, node) {
+		ctx = dbgfs_inst->vcodec_ctx;
+
+		curr_len = snprintf(buf + used_len, total_len - used_len,
+				    "inst[%d]:\n ", ctx->id);
+		used_len += curr_len;
+
+		if (dbgfs_index[MTK_VDEC_DBGFS_PICINFO]) {
+			curr_len = snprintf(buf + used_len, total_len - used_len,
+					    "\treal(%dx%d)=>align(%dx%d)\n",
+					    ctx->picinfo.pic_w, ctx->picinfo.pic_h,
+					    ctx->picinfo.buf_w, ctx->picinfo.buf_h);
+			used_len += curr_len;
+		}
+
+		if (dbgfs_index[MTK_VDEC_DBGFS_FORMAT])
+			mtk_vdec_dbgfs_get_format_type(ctx, buf, &used_len, total_len);
+	}
+	mutex_unlock(&dbgfs->dbgfs_lock);
+read_buffer:
+	ret = simple_read_from_buffer(ubuf, count, ppos, buf, used_len);
+	kfree(buf);
+	return ret;
+}
+
+static const struct file_operations vdec_fops = {
+	.open = simple_open,
+	.write = mtk_vdec_dbgfs_write,
+	.read = mtk_vdec_dbgfs_read,
+};
+
+void mtk_vcodec_dbgfs_create(struct mtk_vcodec_ctx *ctx)
+{
+	struct mtk_vcodec_dbgfs_inst *dbgfs_inst;
+	struct mtk_vcodec_dev *vcodec_dev = ctx->dev;
+
+	dbgfs_inst = kzalloc(sizeof(*dbgfs_inst), GFP_KERNEL);
+	if (!dbgfs_inst)
+		return;
+
+	list_add_tail(&dbgfs_inst->node, &vcodec_dev->dbgfs.dbgfs_head);
+
+	vcodec_dev->dbgfs.inst_count++;
+
+	dbgfs_inst->inst_id = ctx->id;
+	dbgfs_inst->vcodec_ctx = ctx;
+}
+EXPORT_SYMBOL_GPL(mtk_vcodec_dbgfs_create);
+
+void mtk_vcodec_dbgfs_remove(struct mtk_vcodec_dev *vcodec_dev, int ctx_id)
+{
+	struct mtk_vcodec_dbgfs_inst *dbgfs_inst;
+
+	list_for_each_entry(dbgfs_inst, &vcodec_dev->dbgfs.dbgfs_head, node) {
+		if (dbgfs_inst->inst_id == ctx_id) {
+			vcodec_dev->dbgfs.inst_count--;
+			break;
+		}
+	}
+
+	if (dbgfs_inst) {
+		list_del(&dbgfs_inst->node);
+		kfree(dbgfs_inst);
+	}
+}
+EXPORT_SYMBOL_GPL(mtk_vcodec_dbgfs_remove);
+
+void mtk_vcodec_dbgfs_init(struct mtk_vcodec_dev *vcodec_dev, bool is_encode)
+{
+	struct dentry *vcodec_root;
+
+	if (is_encode)
+		vcodec_dev->dbgfs.vcodec_root = debugfs_create_dir("vcodec-enc", NULL);
+	else
+		vcodec_dev->dbgfs.vcodec_root = debugfs_create_dir("vcodec-dec", NULL);
+	if (IS_ERR(vcodec_dev->dbgfs.vcodec_root))
+		dev_err(&vcodec_dev->plat_dev->dev, "create vcodec dir err:%d\n",
+			IS_ERR(vcodec_dev->dbgfs.vcodec_root));
+
+	vcodec_root = vcodec_dev->dbgfs.vcodec_root;
+	debugfs_create_x32("mtk_v4l2_dbg_level", 0644, vcodec_root, &mtk_v4l2_dbg_level);
+	debugfs_create_x32("mtk_vcodec_dbg", 0644, vcodec_root, &mtk_vcodec_dbg);
+
+	vcodec_dev->dbgfs.inst_count = 0;
+	if (is_encode)
+		return;
+
+	INIT_LIST_HEAD(&vcodec_dev->dbgfs.dbgfs_head);
+	debugfs_create_file("vdec", 0200, vcodec_root, vcodec_dev, &vdec_fops);
+	mutex_init(&vcodec_dev->dbgfs.dbgfs_lock);
+}
+EXPORT_SYMBOL_GPL(mtk_vcodec_dbgfs_init);
+
+void mtk_vcodec_dbgfs_deinit(struct mtk_vcodec_dev *vcodec_dev)
+{
+	debugfs_remove_recursive(vcodec_dev->dbgfs.vcodec_root);
+}
+EXPORT_SYMBOL_GPL(mtk_vcodec_dbgfs_deinit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_DESCRIPTION("Mediatek video codec driver");
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dbgfs.h b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dbgfs.h
new file mode 100644
index 000000000000..241ff8197e73
--- /dev/null
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dbgfs.h
@@ -0,0 +1,74 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (c) 2023 MediaTek Inc.
+ * Author: Yunfei Dong <yunfei.dong@mediatek.com>
+ */
+
+#ifndef __MTK_VCODEC_DBGFS_H__
+#define __MTK_VCODEC_DBGFS_H__
+
+struct mtk_vcodec_dev;
+struct mtk_vcodec_ctx;
+
+/*
+ * enum mtk_vdec_dbgfs_log_index  - used to get different debug information
+ */
+enum mtk_vdec_dbgfs_log_index {
+	MTK_VDEC_DBGFS_PICINFO,
+	MTK_VDEC_DBGFS_FORMAT,
+	MTK_VDEC_DBGFS_MAX,
+};
+
+/**
+ * struct mtk_vcodec_dbgfs_inst  - debugfs information for each inst
+ * @node:       list node for each inst
+ * @vcodec_ctx: struct mtk_vcodec_ctx
+ * @inst_id:    index of the context that the same with ctx->id
+ */
+struct mtk_vcodec_dbgfs_inst {
+	struct list_head node;
+	struct mtk_vcodec_ctx *vcodec_ctx;
+	int inst_id;
+};
+
+/**
+ * struct mtk_vcodec_dbgfs  - dbgfs information
+ * @dbgfs_head:  list head used to link each instance
+ * @vcodec_root: vcodec dbgfs entry
+ * @dbgfs_lock:  dbgfs lock used to protect dbgfs_buf
+ * @dbgfs_buf:   dbgfs buf used to store dbgfs cmd
+ * @buf_size:    buffer size of dbgfs
+ * @inst_count:  the count of total instance
+ */
+struct mtk_vcodec_dbgfs {
+	struct list_head dbgfs_head;
+	struct dentry *vcodec_root;
+	struct mutex dbgfs_lock;
+	char dbgfs_buf[1024];
+	int buf_size;
+	int inst_count;
+};
+
+#if defined(CONFIG_DEBUG_FS)
+void mtk_vcodec_dbgfs_create(struct mtk_vcodec_ctx *ctx);
+void mtk_vcodec_dbgfs_remove(struct mtk_vcodec_dev *vcodec_dev, int ctx_id);
+void mtk_vcodec_dbgfs_init(struct mtk_vcodec_dev *vcodec_dev, bool is_encode);
+void mtk_vcodec_dbgfs_deinit(struct mtk_vcodec_dev *vcodec_dev);
+#else
+static inline void mtk_vcodec_dbgfs_create(struct mtk_vcodec_ctx *ctx)
+{
+}
+
+static inline void mtk_vcodec_dbgfs_remove(struct mtk_vcodec_dev *vcodec_dev, int ctx_id)
+{
+}
+
+static inline void mtk_vcodec_dbgfs_init(struct mtk_vcodec_dev *vcodec_dev, bool is_encode)
+{
+}
+
+static inline void mtk_vcodec_dbgfs_deinit(struct mtk_vcodec_dev *vcodec_dev)
+{
+}
+#endif
+#endif
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c
index 9c652beb3f19..d41f2121b94f 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_drv.c
@@ -215,6 +215,7 @@ static int fops_vcodec_open(struct file *file)
 	ctx->dev->vdec_pdata->init_vdec_params(ctx);
 
 	list_add(&ctx->list, &dev->ctx_list);
+	mtk_vcodec_dbgfs_create(ctx);
 
 	mutex_unlock(&dev->dev_mutex);
 	mtk_v4l2_debug(0, "%s decoder [%d]", dev_name(&dev->plat_dev->dev),
@@ -256,6 +257,7 @@ static int fops_vcodec_release(struct file *file)
 	v4l2_fh_exit(&ctx->fh);
 	v4l2_ctrl_handler_free(&ctx->ctrl_hdl);
 
+	mtk_vcodec_dbgfs_remove(dev, ctx->id);
 	list_del_init(&ctx->list);
 	kfree(ctx);
 	mutex_unlock(&dev->dev_mutex);
@@ -310,7 +312,6 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 	}
 
 	if (IS_VDEC_LAT_ARCH(dev->vdec_pdata->hw_arch)) {
-		vdec_msg_queue_init_ctx(&dev->msg_queue_core_ctx, MTK_VDEC_CORE);
 		dev->core_workqueue =
 			alloc_ordered_workqueue("core-decoder",
 						WQ_MEM_RECLAIM | WQ_FREEZABLE);
@@ -423,6 +424,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 		mtk_v4l2_debug(0, "media registered as /dev/media%d", vfd_dec->minor);
 	}
 
+	mtk_vcodec_dbgfs_init(dev, false);
 	mtk_v4l2_debug(0, "decoder registered as /dev/video%d", vfd_dec->minor);
 
 	return 0;
@@ -498,6 +500,7 @@ static void mtk_vcodec_dec_remove(struct platform_device *pdev)
 	if (dev->vfd_dec)
 		video_unregister_device(dev->vfd_dec);
 
+	mtk_vcodec_dbgfs_deinit(dev);
 	v4l2_device_unregister(&dev->v4l2_dev);
 	if (!dev->vdec_pdata->is_subdev_supported)
 		pm_runtime_disable(dev->pm.dev);
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_hw.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_hw.c
index b753bf54ebd9..e1cb2f8dca33 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_hw.c
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_hw.c
@@ -148,20 +148,21 @@ static int mtk_vdec_hw_probe(struct platform_device *pdev)
 	ret = mtk_vcodec_init_dec_clk(pdev, &subdev_dev->pm);
 	if (ret)
 		return ret;
-	pm_runtime_enable(&pdev->dev);
+
+	ret = devm_pm_runtime_enable(&pdev->dev);
+	if (ret)
+		return ret;
 
 	of_id = of_match_device(mtk_vdec_hw_match, dev);
 	if (!of_id) {
 		dev_err(dev, "Can't get vdec subdev id.\n");
-		ret = -EINVAL;
-		goto err;
+		return -EINVAL;
 	}
 
 	hw_idx = (enum mtk_vdec_hw_id)(uintptr_t)of_id->data;
 	if (hw_idx >= MTK_VDEC_HW_MAX) {
 		dev_err(dev, "Hardware index %d not correct.\n", hw_idx);
-		ret = -EINVAL;
-		goto err;
+		return -EINVAL;
 	}
 
 	main_dev->subdev_dev[hw_idx] = subdev_dev;
@@ -173,14 +174,14 @@ static int mtk_vdec_hw_probe(struct platform_device *pdev)
 	if (IS_SUPPORT_VDEC_HW_IRQ(hw_idx)) {
 		ret = mtk_vdec_hw_init_irq(subdev_dev);
 		if (ret)
-			goto err;
+			return ret;
 	}
 
 	subdev_dev->reg_base[VDEC_HW_MISC] =
 		devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR((__force void *)subdev_dev->reg_base[VDEC_HW_MISC])) {
 		ret = PTR_ERR((__force void *)subdev_dev->reg_base[VDEC_HW_MISC]);
-		goto err;
+		return ret;
 	}
 
 	if (!main_dev->subdev_prob_done)
@@ -188,21 +189,10 @@ static int mtk_vdec_hw_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, subdev_dev);
 	return 0;
-err:
-	pm_runtime_disable(subdev_dev->pm.dev);
-	return ret;
-}
-
-static int mtk_vdec_hw_remove(struct platform_device *pdev)
-{
-	pm_runtime_disable(&pdev->dev);
-
-	return 0;
 }
 
 static struct platform_driver mtk_vdec_driver = {
 	.probe	= mtk_vdec_hw_probe,
-	.remove = mtk_vdec_hw_remove,
 	.driver	= {
 		.name	= "mtk-vdec-comp",
 		.of_match_table = mtk_vdec_hw_match,
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c
index 3000db975e5f..db1e14a1bd6c 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_dec_stateless.c
@@ -107,11 +107,103 @@ static const struct mtk_stateless_control mtk_stateless_controls[] = {
 		},
 		.codec_type = V4L2_PIX_FMT_VP9_FRAME,
 	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_HEVC_SPS,
+		},
+		.codec_type = V4L2_PIX_FMT_HEVC_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_HEVC_PPS,
+		},
+		.codec_type = V4L2_PIX_FMT_HEVC_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_HEVC_SCALING_MATRIX,
+		},
+		.codec_type = V4L2_PIX_FMT_HEVC_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_HEVC_DECODE_PARAMS,
+		},
+		.codec_type = V4L2_PIX_FMT_HEVC_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_MPEG_VIDEO_HEVC_PROFILE,
+			.def = V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN,
+			.max = V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN_10,
+			.menu_skip_mask =
+				BIT(V4L2_MPEG_VIDEO_HEVC_PROFILE_MAIN_STILL_PICTURE),
+		},
+		.codec_type = V4L2_PIX_FMT_HEVC_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_HEVC_DECODE_MODE,
+			.min = V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED,
+			.def = V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED,
+			.max = V4L2_STATELESS_HEVC_DECODE_MODE_FRAME_BASED,
+		},
+		.codec_type = V4L2_PIX_FMT_HEVC_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_HEVC_START_CODE,
+			.min = V4L2_STATELESS_HEVC_START_CODE_ANNEX_B,
+			.def = V4L2_STATELESS_HEVC_START_CODE_ANNEX_B,
+			.max = V4L2_STATELESS_HEVC_START_CODE_ANNEX_B,
+		},
+		.codec_type = V4L2_PIX_FMT_HEVC_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_AV1_SEQUENCE,
+
+		},
+		.codec_type = V4L2_PIX_FMT_AV1_FRAME,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_AV1_FRAME,
+
+		},
+		.codec_type = V4L2_PIX_FMT_AV1_FRAME,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_AV1_TILE_GROUP_ENTRY,
+			.dims = { V4L2_AV1_MAX_TILE_COUNT },
+
+		},
+		.codec_type = V4L2_PIX_FMT_AV1_FRAME,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_MPEG_VIDEO_AV1_PROFILE,
+			.min = V4L2_MPEG_VIDEO_AV1_PROFILE_MAIN,
+			.def = V4L2_MPEG_VIDEO_AV1_PROFILE_MAIN,
+			.max = V4L2_MPEG_VIDEO_AV1_PROFILE_MAIN,
+		},
+		.codec_type = V4L2_PIX_FMT_AV1_FRAME,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_MPEG_VIDEO_AV1_LEVEL,
+			.min = V4L2_MPEG_VIDEO_AV1_LEVEL_2_0,
+			.def = V4L2_MPEG_VIDEO_AV1_LEVEL_4_0,
+			.max = V4L2_MPEG_VIDEO_AV1_LEVEL_5_1,
+		},
+		.codec_type = V4L2_PIX_FMT_AV1_FRAME,
+	},
 };
 
 #define NUM_CTRLS ARRAY_SIZE(mtk_stateless_controls)
 
-static struct mtk_video_fmt mtk_video_formats[5];
+static struct mtk_video_fmt mtk_video_formats[7];
 
 static struct mtk_video_fmt default_out_format;
 static struct mtk_video_fmt default_cap_format;
@@ -240,7 +332,7 @@ static void mtk_vdec_worker(struct work_struct *work)
 		mtk_v4l2_err("vb2 buffer media request is NULL");
 
 	ret = vdec_if_decode(ctx, bs_src, NULL, &res_chg);
-	if (ret) {
+	if (ret && ret != -EAGAIN) {
 		mtk_v4l2_err(" <===[%d], src_buf[%d] sz=0x%zx pts=%llu vdec_if_decode() ret=%d res_chg=%d===>",
 			     ctx->id, vb2_src->index, bs_src->size,
 			     vb2_src->timestamp, ret, res_chg);
@@ -356,6 +448,8 @@ static void mtk_vcodec_add_formats(unsigned int fourcc,
 	case V4L2_PIX_FMT_H264_SLICE:
 	case V4L2_PIX_FMT_VP8_FRAME:
 	case V4L2_PIX_FMT_VP9_FRAME:
+	case V4L2_PIX_FMT_HEVC_SLICE:
+	case V4L2_PIX_FMT_AV1_FRAME:
 		mtk_video_formats[count_formats].fourcc = fourcc;
 		mtk_video_formats[count_formats].type = MTK_FMT_DEC;
 		mtk_video_formats[count_formats].num_planes = 1;
@@ -412,6 +506,14 @@ static void mtk_vcodec_get_supported_formats(struct mtk_vcodec_ctx *ctx)
 		mtk_vcodec_add_formats(V4L2_PIX_FMT_VP9_FRAME, ctx);
 		out_format_count++;
 	}
+	if (ctx->dev->dec_capability & MTK_VDEC_FORMAT_HEVC_FRAME) {
+		mtk_vcodec_add_formats(V4L2_PIX_FMT_HEVC_SLICE, ctx);
+		out_format_count++;
+	}
+	if (ctx->dev->dec_capability & MTK_VDEC_FORMAT_AV1_FRAME) {
+		mtk_vcodec_add_formats(V4L2_PIX_FMT_AV1_FRAME, ctx);
+		out_format_count++;
+	}
 
 	if (cap_format_count)
 		default_cap_format = mtk_video_formats[cap_format_count - 1];
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h
index 9acab54fd650..f17d67e781c9 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_drv.h
@@ -16,6 +16,7 @@
 #include <media/v4l2-mem2mem.h>
 #include <media/videobuf2-core.h>
 
+#include "mtk_vcodec_dbgfs.h"
 #include "mtk_vcodec_util.h"
 #include "vdec_msg_queue.h"
 
@@ -347,6 +348,8 @@ enum mtk_vdec_format_types {
 	MTK_VDEC_FORMAT_H264_SLICE = 0x100,
 	MTK_VDEC_FORMAT_VP8_FRAME = 0x200,
 	MTK_VDEC_FORMAT_VP9_FRAME = 0x400,
+	MTK_VDEC_FORMAT_AV1_FRAME = 0x800,
+	MTK_VDEC_FORMAT_HEVC_FRAME = 0x1000,
 	MTK_VCODEC_INNER_RACING = 0x20000,
 };
 
@@ -461,7 +464,6 @@ struct mtk_vcodec_enc_pdata {
  * @enc_capability: used to identify encode capability
  *
  * @core_workqueue: queue used for core hardware decode
- * @msg_queue_core_ctx: msg queue context used for core workqueue
  *
  * @subdev_dev: subdev hardware device
  * @subdev_prob_done: check whether all used hw device is prob done
@@ -470,6 +472,7 @@ struct mtk_vcodec_enc_pdata {
  * @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
+ * @dbgfs: debug log related information
  */
 struct mtk_vcodec_dev {
 	struct v4l2_device v4l2_dev;
@@ -510,7 +513,6 @@ struct mtk_vcodec_dev {
 	unsigned int enc_capability;
 
 	struct workqueue_struct *core_workqueue;
-	struct vdec_msg_queue_ctx msg_queue_core_ctx;
 
 	void *subdev_dev[MTK_VDEC_HW_MAX];
 	int (*subdev_prob_done)(struct mtk_vcodec_dev *vdec_dev);
@@ -520,6 +522,8 @@ struct mtk_vcodec_dev {
 	u32 vdec_racing_info[132];
 	/* Protects access to vdec_racing_info data */
 	struct mutex dec_racing_info_mutex;
+
+	struct mtk_vcodec_dbgfs dbgfs;
 };
 
 static inline struct mtk_vcodec_ctx *fh_to_ctx(struct v4l2_fh *fh)
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c
index db65e77bd373..9ff439a50f53 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc.c
@@ -505,13 +505,13 @@ static int vidioc_venc_s_fmt_out(struct file *file, void *priv,
 		f->fmt.pix.pixelformat = fmt->fourcc;
 	}
 
-	q_data->visible_width = f->fmt.pix_mp.width;
-	q_data->visible_height = f->fmt.pix_mp.height;
-	q_data->fmt = fmt;
-	ret = vidioc_try_fmt_out(ctx, f, q_data->fmt);
+	ret = vidioc_try_fmt_out(ctx, f, fmt);
 	if (ret)
 		return ret;
 
+	q_data->fmt = fmt;
+	q_data->visible_width = f->fmt.pix_mp.width;
+	q_data->visible_height = f->fmt.pix_mp.height;
 	q_data->coded_width = f->fmt.pix_mp.width;
 	q_data->coded_height = f->fmt.pix_mp.height;
 
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c
index 168004a08888..5df0a22ff3b5 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_enc_drv.c
@@ -358,6 +358,7 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 		goto err_enc_reg;
 	}
 
+	mtk_vcodec_dbgfs_init(dev, true);
 	mtk_v4l2_debug(0, "encoder %d registered as /dev/video%d",
 		       dev->venc_pdata->core_id, vfd_enc->num);
 
@@ -468,6 +469,7 @@ static void mtk_vcodec_enc_remove(struct platform_device *pdev)
 	if (dev->vfd_enc)
 		video_unregister_device(dev->vfd_enc);
 
+	mtk_vcodec_dbgfs_deinit(dev);
 	v4l2_device_unregister(&dev->v4l2_dev);
 	pm_runtime_disable(dev->pm.dev);
 	mtk_vcodec_fw_release(dev->fw_handler);
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.c b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.c
index ace78c4b5b9e..f214e6f67005 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.c
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.c
@@ -13,6 +13,14 @@
 #include "mtk_vcodec_drv.h"
 #include "mtk_vcodec_util.h"
 
+#if defined(CONFIG_DEBUG_FS)
+int mtk_vcodec_dbg;
+EXPORT_SYMBOL(mtk_vcodec_dbg);
+
+int mtk_v4l2_dbg_level;
+EXPORT_SYMBOL(mtk_v4l2_dbg_level);
+#endif
+
 void __iomem *mtk_vcodec_get_reg_addr(struct mtk_vcodec_ctx *data,
 					unsigned int reg_idx)
 {
diff --git a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.h b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.h
index 71956627a0e2..88d389b65f13 100644
--- a/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.h
+++ b/drivers/media/platform/mediatek/vcodec/mtk_vcodec_util.h
@@ -35,15 +35,35 @@ struct mtk_vcodec_dev;
 	pr_err("[MTK_VCODEC][ERROR][%d]: " fmt "\n",		\
 	       ((struct mtk_vcodec_ctx *)(h)->ctx)->id, ##args)
 
+#if defined(CONFIG_DEBUG_FS)
+extern int mtk_v4l2_dbg_level;
+extern int mtk_vcodec_dbg;
 
-#define mtk_v4l2_debug(level, fmt, args...) pr_debug(fmt, ##args)
+#define mtk_v4l2_debug(level, fmt, args...)				\
+	do {								\
+		if (mtk_v4l2_dbg_level >= (level))			\
+			pr_debug("[MTK_V4L2] %s, %d: " fmt "\n",        \
+				 __func__, __LINE__, ##args);	        \
+	} while (0)
 
-#define mtk_v4l2_debug_enter()  mtk_v4l2_debug(3, "+")
-#define mtk_v4l2_debug_leave()  mtk_v4l2_debug(3, "-")
+#define mtk_vcodec_debug(h, fmt, args...)				                      \
+	do {								                      \
+		if (mtk_vcodec_dbg)					                      \
+			dev_dbg(&(((struct mtk_vcodec_ctx *)(h)->ctx)->dev->plat_dev->dev),   \
+				"[MTK_VCODEC][%d]: %s, %d " fmt "\n",                         \
+				((struct mtk_vcodec_ctx *)(h)->ctx)->id,                      \
+				__func__, __LINE__, ##args);                                  \
+	} while (0)
+#else
+#define mtk_v4l2_debug(level, fmt, args...) pr_debug(fmt, ##args)
 
 #define mtk_vcodec_debug(h, fmt, args...)			\
 	pr_debug("[MTK_VCODEC][%d]: " fmt "\n",			\
 		((struct mtk_vcodec_ctx *)(h)->ctx)->id, ##args)
+#endif
+
+#define mtk_v4l2_debug_enter()  mtk_v4l2_debug(3, "+")
+#define mtk_v4l2_debug_leave()  mtk_v4l2_debug(3, "-")
 
 #define mtk_vcodec_debug_enter(h)  mtk_vcodec_debug(h, "+")
 #define mtk_vcodec_debug_leave(h)  mtk_vcodec_debug(h, "-")
diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_av1_req_lat_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_av1_req_lat_if.c
new file mode 100644
index 000000000000..404a1a23fd40
--- /dev/null
+++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_av1_req_lat_if.c
@@ -0,0 +1,2207 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 MediaTek Inc.
+ * Author: Xiaoyong Lu <xiaoyong.lu@mediatek.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "../mtk_vcodec_util.h"
+#include "../mtk_vcodec_dec.h"
+#include "../mtk_vcodec_intr.h"
+#include "../vdec_drv_base.h"
+#include "../vdec_drv_if.h"
+#include "../vdec_vpu_if.h"
+
+#define AV1_MAX_FRAME_BUF_COUNT		(V4L2_AV1_TOTAL_REFS_PER_FRAME + 1)
+#define AV1_TILE_BUF_SIZE		64
+#define AV1_SCALE_SUBPEL_BITS		10
+#define AV1_REF_SCALE_SHIFT		14
+#define AV1_REF_NO_SCALE		BIT(AV1_REF_SCALE_SHIFT)
+#define AV1_REF_INVALID_SCALE		-1
+#define AV1_CDF_TABLE_BUFFER_SIZE	16384
+#define AV1_PRIMARY_REF_NONE		7
+
+#define AV1_INVALID_IDX			-1
+
+#define AV1_DIV_ROUND_UP_POW2(value, n)			\
+({							\
+	typeof(n) _n  = n;				\
+	typeof(value) _value = value;			\
+	(_value + (BIT(_n) >> 1)) >> _n;		\
+})
+
+#define AV1_DIV_ROUND_UP_POW2_SIGNED(value, n)				\
+({									\
+	typeof(n) _n_  = n;						\
+	typeof(value) _value_ = value;					\
+	(((_value_) < 0) ? -AV1_DIV_ROUND_UP_POW2(-(_value_), (_n_))	\
+		: AV1_DIV_ROUND_UP_POW2((_value_), (_n_)));		\
+})
+
+#define BIT_FLAG(x, bit)		(!!((x)->flags & (bit)))
+#define SEGMENTATION_FLAG(x, name)	(!!((x)->flags & V4L2_AV1_SEGMENTATION_FLAG_##name))
+#define QUANT_FLAG(x, name)		(!!((x)->flags & V4L2_AV1_QUANTIZATION_FLAG_##name))
+#define SEQUENCE_FLAG(x, name)		(!!((x)->flags & V4L2_AV1_SEQUENCE_FLAG_##name))
+#define FH_FLAG(x, name)		(!!((x)->flags & V4L2_AV1_FRAME_FLAG_##name))
+
+#define MINQ 0
+#define MAXQ 255
+
+#define DIV_LUT_PREC_BITS 14
+#define DIV_LUT_BITS 8
+#define DIV_LUT_NUM BIT(DIV_LUT_BITS)
+#define WARP_PARAM_REDUCE_BITS 6
+#define WARPEDMODEL_PREC_BITS 16
+
+#define SEG_LVL_ALT_Q 0
+#define SECONDARY_FILTER_STRENGTH_NUM_BITS 2
+
+static const short div_lut[DIV_LUT_NUM + 1] = {
+	16384, 16320, 16257, 16194, 16132, 16070, 16009, 15948, 15888, 15828, 15768,
+	15709, 15650, 15592, 15534, 15477, 15420, 15364, 15308, 15252, 15197, 15142,
+	15087, 15033, 14980, 14926, 14873, 14821, 14769, 14717, 14665, 14614, 14564,
+	14513, 14463, 14413, 14364, 14315, 14266, 14218, 14170, 14122, 14075, 14028,
+	13981, 13935, 13888, 13843, 13797, 13752, 13707, 13662, 13618, 13574, 13530,
+	13487, 13443, 13400, 13358, 13315, 13273, 13231, 13190, 13148, 13107, 13066,
+	13026, 12985, 12945, 12906, 12866, 12827, 12788, 12749, 12710, 12672, 12633,
+	12596, 12558, 12520, 12483, 12446, 12409, 12373, 12336, 12300, 12264, 12228,
+	12193, 12157, 12122, 12087, 12053, 12018, 11984, 11950, 11916, 11882, 11848,
+	11815, 11782, 11749, 11716, 11683, 11651, 11619, 11586, 11555, 11523, 11491,
+	11460, 11429, 11398, 11367, 11336, 11305, 11275, 11245, 11215, 11185, 11155,
+	11125, 11096, 11067, 11038, 11009, 10980, 10951, 10923, 10894, 10866, 10838,
+	10810, 10782, 10755, 10727, 10700, 10673, 10645, 10618, 10592, 10565, 10538,
+	10512, 10486, 10460, 10434, 10408, 10382, 10356, 10331, 10305, 10280, 10255,
+	10230, 10205, 10180, 10156, 10131, 10107, 10082, 10058, 10034, 10010, 9986,
+	9963,  9939,  9916,  9892,  9869,  9846,  9823,  9800,  9777,  9754,  9732,
+	9709,  9687,  9664,  9642,  9620,  9598,  9576,  9554,  9533,  9511,  9489,
+	9468,  9447,  9425,  9404,  9383,  9362,  9341,  9321,  9300,  9279,  9259,
+	9239,  9218,  9198,  9178,  9158,  9138,  9118,  9098,  9079,  9059,  9039,
+	9020,  9001,  8981,  8962,  8943,  8924,  8905,  8886,  8867,  8849,  8830,
+	8812,  8793,  8775,  8756,  8738,  8720,  8702,  8684,  8666,  8648,  8630,
+	8613,  8595,  8577,  8560,  8542,  8525,  8508,  8490,  8473,  8456,  8439,
+	8422,  8405,  8389,  8372,  8355,  8339,  8322,  8306,  8289,  8273,  8257,
+	8240,  8224,  8208,  8192,
+};
+
+/**
+ * struct vdec_av1_slice_init_vsi - VSI used to initialize instance
+ * @architecture:	architecture type
+ * @reserved:		reserved
+ * @core_vsi:		for core vsi
+ * @cdf_table_addr:	cdf table addr
+ * @cdf_table_size:	cdf table size
+ * @iq_table_addr:	iq table addr
+ * @iq_table_size:	iq table size
+ * @vsi_size:		share vsi structure size
+ */
+struct vdec_av1_slice_init_vsi {
+	u32 architecture;
+	u32 reserved;
+	u64 core_vsi;
+	u64 cdf_table_addr;
+	u32 cdf_table_size;
+	u64 iq_table_addr;
+	u32 iq_table_size;
+	u32 vsi_size;
+};
+
+/**
+ * struct vdec_av1_slice_mem - memory address and size
+ * @buf:		dma_addr padding
+ * @dma_addr:		buffer address
+ * @size:		buffer size
+ * @dma_addr_end:	buffer end address
+ * @padding:		for padding
+ */
+struct vdec_av1_slice_mem {
+	union {
+		u64 buf;
+		dma_addr_t dma_addr;
+	};
+	union {
+		size_t size;
+		dma_addr_t dma_addr_end;
+		u64 padding;
+	};
+};
+
+/**
+ * struct vdec_av1_slice_state - decoding state
+ * @err                   : err type for decode
+ * @full                  : transcoded buffer is full or not
+ * @timeout               : decode timeout or not
+ * @perf                  : performance enable
+ * @crc                   : hw checksum
+ * @out_size              : hw output size
+ */
+struct vdec_av1_slice_state {
+	int err;
+	u32 full;
+	u32 timeout;
+	u32 perf;
+	u32 crc[16];
+	u32 out_size;
+};
+
+/*
+ * enum vdec_av1_slice_resolution_level - resolution level
+ */
+enum vdec_av1_slice_resolution_level {
+	AV1_RES_NONE,
+	AV1_RES_FHD,
+	AV1_RES_4K,
+	AV1_RES_8K,
+};
+
+/*
+ * enum vdec_av1_slice_frame_type - av1 frame type
+ */
+enum vdec_av1_slice_frame_type {
+	AV1_KEY_FRAME = 0,
+	AV1_INTER_FRAME,
+	AV1_INTRA_ONLY_FRAME,
+	AV1_SWITCH_FRAME,
+	AV1_FRAME_TYPES,
+};
+
+/*
+ * enum vdec_av1_slice_reference_mode - reference mode type
+ */
+enum vdec_av1_slice_reference_mode {
+	AV1_SINGLE_REFERENCE = 0,
+	AV1_COMPOUND_REFERENCE,
+	AV1_REFERENCE_MODE_SELECT,
+	AV1_REFERENCE_MODES,
+};
+
+/**
+ * struct vdec_av1_slice_tile_group - info for each tile
+ * @num_tiles:			tile number
+ * @tile_size:			input size for each tile
+ * @tile_start_offset:		tile offset to input buffer
+ */
+struct vdec_av1_slice_tile_group {
+	u32 num_tiles;
+	u32 tile_size[V4L2_AV1_MAX_TILE_COUNT];
+	u32 tile_start_offset[V4L2_AV1_MAX_TILE_COUNT];
+};
+
+/**
+ * struct vdec_av1_slice_scale_factors - scale info for each ref frame
+ * @is_scaled:  frame is scaled or not
+ * @x_scale:    frame width scale coefficient
+ * @y_scale:    frame height scale coefficient
+ * @x_step:     width step for x_scale
+ * @y_step:     height step for y_scale
+ */
+struct vdec_av1_slice_scale_factors {
+	u8 is_scaled;
+	int x_scale;
+	int y_scale;
+	int x_step;
+	int y_step;
+};
+
+/**
+ * struct vdec_av1_slice_frame_refs - ref frame info
+ * @ref_fb_idx:         ref slot index
+ * @ref_map_idx:        ref frame index
+ * @scale_factors:      scale factors for each ref frame
+ */
+struct vdec_av1_slice_frame_refs {
+	int ref_fb_idx;
+	int ref_map_idx;
+	struct vdec_av1_slice_scale_factors scale_factors;
+};
+
+/**
+ * struct vdec_av1_slice_gm - AV1 Global Motion parameters
+ * @wmtype:     The type of global motion transform used
+ * @wmmat:      gm_params
+ * @alpha:      alpha info
+ * @beta:       beta info
+ * @gamma:      gamma info
+ * @delta:      delta info
+ * @invalid:    is invalid or not
+ */
+struct vdec_av1_slice_gm {
+	int wmtype;
+	int wmmat[8];
+	short alpha;
+	short beta;
+	short gamma;
+	short delta;
+	char invalid;
+};
+
+/**
+ * struct vdec_av1_slice_sm - AV1 Skip Mode parameters
+ * @skip_mode_allowed:  Skip Mode is allowed or not
+ * @skip_mode_present:  specified that the skip_mode will be present or not
+ * @skip_mode_frame:    specifies the frames to use for compound prediction
+ */
+struct vdec_av1_slice_sm {
+	u8 skip_mode_allowed;
+	u8 skip_mode_present;
+	int skip_mode_frame[2];
+};
+
+/**
+ * struct vdec_av1_slice_seg - AV1 Segmentation params
+ * @segmentation_enabled:        this frame makes use of the segmentation tool or not
+ * @segmentation_update_map:     segmentation map are updated during the decoding frame
+ * @segmentation_temporal_update:segmentation map are coded relative the existing segmentaion map
+ * @segmentation_update_data:    new parameters are about to be specified for each segment
+ * @feature_data:                specifies the feature data for a segment feature
+ * @feature_enabled_mask:        the corresponding feature value is coded or not.
+ * @segid_preskip:               segment id will be read before the skip syntax element.
+ * @last_active_segid:           the highest numbered segment id that has some enabled feature
+ */
+struct vdec_av1_slice_seg {
+	u8 segmentation_enabled;
+	u8 segmentation_update_map;
+	u8 segmentation_temporal_update;
+	u8 segmentation_update_data;
+	int feature_data[V4L2_AV1_MAX_SEGMENTS][V4L2_AV1_SEG_LVL_MAX];
+	u16 feature_enabled_mask[V4L2_AV1_MAX_SEGMENTS];
+	int segid_preskip;
+	int last_active_segid;
+};
+
+/**
+ * struct vdec_av1_slice_delta_q_lf - AV1 Loop Filter delta parameters
+ * @delta_q_present:    specified whether quantizer index delta values are present
+ * @delta_q_res:        specifies the left shift which should be applied to decoded quantizer index
+ * @delta_lf_present:   specifies whether loop filter delta values are present
+ * @delta_lf_res:       specifies the left shift which should be applied to decoded
+ *                      loop filter delta values
+ * @delta_lf_multi:     specifies that separate loop filter deltas are sent for horizontal
+ *                      luma edges,vertical luma edges,the u edges, and the v edges.
+ */
+struct vdec_av1_slice_delta_q_lf {
+	u8 delta_q_present;
+	u8 delta_q_res;
+	u8 delta_lf_present;
+	u8 delta_lf_res;
+	u8 delta_lf_multi;
+};
+
+/**
+ * struct vdec_av1_slice_quantization - AV1 Quantization params
+ * @base_q_idx:         indicates the base frame qindex. This is used for Y AC
+ *                      coefficients and as the base value for the other quantizers.
+ * @qindex:             qindex
+ * @delta_qydc:         indicates the Y DC quantizer relative to base_q_idx
+ * @delta_qudc:         indicates the U DC quantizer relative to base_q_idx.
+ * @delta_quac:         indicates the U AC quantizer relative to base_q_idx
+ * @delta_qvdc:         indicates the V DC quantizer relative to base_q_idx
+ * @delta_qvac:         indicates the V AC quantizer relative to base_q_idx
+ * @using_qmatrix:      specifies that the quantizer matrix will be used to
+ *                      compute quantizers
+ * @qm_y:               specifies the level in the quantizer matrix that should
+ *                      be used for luma plane decoding
+ * @qm_u:               specifies the level in the quantizer matrix that should
+ *                      be used for chroma U plane decoding.
+ * @qm_v:               specifies the level in the quantizer matrix that should be
+ *                      used for chroma V plane decoding
+ */
+struct vdec_av1_slice_quantization {
+	int base_q_idx;
+	int qindex[V4L2_AV1_MAX_SEGMENTS];
+	int delta_qydc;
+	int delta_qudc;
+	int delta_quac;
+	int delta_qvdc;
+	int delta_qvac;
+	u8 using_qmatrix;
+	u8 qm_y;
+	u8 qm_u;
+	u8 qm_v;
+};
+
+/**
+ * struct vdec_av1_slice_lr - AV1 Loop Restauration parameters
+ * @use_lr:                     whether to use loop restoration
+ * @use_chroma_lr:              whether to use chroma loop restoration
+ * @frame_restoration_type:     specifies the type of restoration used for each plane
+ * @loop_restoration_size:      pecifies the size of loop restoration units in units
+ *                              of samples in the current plane
+ */
+struct vdec_av1_slice_lr {
+	u8 use_lr;
+	u8 use_chroma_lr;
+	u8 frame_restoration_type[V4L2_AV1_NUM_PLANES_MAX];
+	u32 loop_restoration_size[V4L2_AV1_NUM_PLANES_MAX];
+};
+
+/**
+ * struct vdec_av1_slice_loop_filter - AV1 Loop filter parameters
+ * @loop_filter_level:          an array containing loop filter strength values.
+ * @loop_filter_ref_deltas:     contains the adjustment needed for the filter
+ *                              level based on the chosen reference frame
+ * @loop_filter_mode_deltas:    contains the adjustment needed for the filter
+ *                              level based on the chosen mode
+ * @loop_filter_sharpness:      indicates the sharpness level. The loop_filter_level
+ *                              and loop_filter_sharpness together determine when
+ *                              a block edge is filtered, and by how much the
+ *                              filtering can change the sample values
+ * @loop_filter_delta_enabled:  filetr level depends on the mode and reference
+ *                              frame used to predict a block
+ */
+struct vdec_av1_slice_loop_filter {
+	u8 loop_filter_level[4];
+	int loop_filter_ref_deltas[V4L2_AV1_TOTAL_REFS_PER_FRAME];
+	int loop_filter_mode_deltas[2];
+	u8 loop_filter_sharpness;
+	u8 loop_filter_delta_enabled;
+};
+
+/**
+ * struct vdec_av1_slice_cdef - AV1 CDEF parameters
+ * @cdef_damping:       controls the amount of damping in the deringing filter
+ * @cdef_y_strength:    specifies the strength of the primary filter and secondary filter
+ * @cdef_uv_strength:   specifies the strength of the primary filter and secondary filter
+ * @cdef_bits:          specifies the number of bits needed to specify which
+ *                      CDEF filter to apply
+ */
+struct vdec_av1_slice_cdef {
+	u8 cdef_damping;
+	u8 cdef_y_strength[8];
+	u8 cdef_uv_strength[8];
+	u8 cdef_bits;
+};
+
+/**
+ * struct vdec_av1_slice_mfmv - AV1 mfmv parameters
+ * @mfmv_valid_ref:     mfmv_valid_ref
+ * @mfmv_dir:           mfmv_dir
+ * @mfmv_ref_to_cur:    mfmv_ref_to_cur
+ * @mfmv_ref_frame_idx: mfmv_ref_frame_idx
+ * @mfmv_count:         mfmv_count
+ */
+struct vdec_av1_slice_mfmv {
+	u32 mfmv_valid_ref[3];
+	u32 mfmv_dir[3];
+	int mfmv_ref_to_cur[3];
+	int mfmv_ref_frame_idx[3];
+	int mfmv_count;
+};
+
+/**
+ * struct vdec_av1_slice_tile - AV1 Tile info
+ * @tile_cols:                  specifies the number of tiles across the frame
+ * @tile_rows:                  pecifies the number of tiles down the frame
+ * @mi_col_starts:              an array specifying the start column
+ * @mi_row_starts:              an array specifying the start row
+ * @context_update_tile_id:     specifies which tile to use for the CDF update
+ * @uniform_tile_spacing_flag:  tiles are uniformly spaced across the frame
+ *                              or the tile sizes are coded
+ */
+struct vdec_av1_slice_tile {
+	u8 tile_cols;
+	u8 tile_rows;
+	int mi_col_starts[V4L2_AV1_MAX_TILE_COLS + 1];
+	int mi_row_starts[V4L2_AV1_MAX_TILE_ROWS + 1];
+	u8 context_update_tile_id;
+	u8 uniform_tile_spacing_flag;
+};
+
+/**
+ * struct vdec_av1_slice_uncompressed_header - Represents an AV1 Frame Header OBU
+ * @use_ref_frame_mvs:          use_ref_frame_mvs flag
+ * @order_hint:                 specifies OrderHintBits least significant bits of the expected
+ * @gm:                         global motion param
+ * @upscaled_width:             the upscaled width
+ * @frame_width:                frame's width
+ * @frame_height:               frame's height
+ * @reduced_tx_set:             frame is restricted to a reduced subset of the full
+ *                              set of transform types
+ * @tx_mode:                    specifies how the transform size is determined
+ * @uniform_tile_spacing_flag:  tiles are uniformly spaced across the frame
+ *                              or the tile sizes are coded
+ * @interpolation_filter:       specifies the filter selection used for performing inter prediction
+ * @allow_warped_motion:        motion_mode may be present or not
+ * @is_motion_mode_switchable : euqlt to 0 specifies that only the SIMPLE motion mode will be used
+ * @reference_mode :            frame reference mode selected
+ * @allow_high_precision_mv:    specifies that motion vectors are specified to
+ *                              quarter pel precision or to eighth pel precision
+ * @allow_intra_bc:             ubducates that intra block copy may be used in this frame
+ * @force_integer_mv:           specifies motion vectors will always be integers or
+ *                              can contain fractional bits
+ * @allow_screen_content_tools: intra blocks may use palette encoding
+ * @error_resilient_mode:       error resislent mode is enable/disable
+ * @frame_type:                 specifies the AV1 frame type
+ * @primary_ref_frame:          specifies which reference frame contains the CDF values
+ *                              and other state that should be loaded at the start of the frame
+ *                              slots will be updated with the current frame after it is decoded
+ * @disable_frame_end_update_cdf:indicates the end of frame CDF update is disable or enable
+ * @disable_cdf_update:         specified whether the CDF update in the symbol
+ *                              decoding process should be disables
+ * @skip_mode:                  av1 skip mode parameters
+ * @seg:                        av1 segmentaon parameters
+ * @delta_q_lf:                 av1 delta loop fileter
+ * @quant:                      av1 Quantization params
+ * @lr:                         av1 Loop Restauration parameters
+ * @superres_denom:             the denominator for the upscaling ratio
+ * @loop_filter:                av1 Loop filter parameters
+ * @cdef:                       av1 CDEF parameters
+ * @mfmv:                       av1 mfmv parameters
+ * @tile:                       av1 Tile info
+ * @frame_is_intra:             intra frame
+ * @loss_less_array:            loss less array
+ * @coded_loss_less:            coded lsss less
+ * @mi_rows:                    size of mi unit in rows
+ * @mi_cols:                    size of mi unit in cols
+ */
+struct vdec_av1_slice_uncompressed_header {
+	u8 use_ref_frame_mvs;
+	int order_hint;
+	struct vdec_av1_slice_gm gm[V4L2_AV1_TOTAL_REFS_PER_FRAME];
+	u32 upscaled_width;
+	u32 frame_width;
+	u32 frame_height;
+	u8 reduced_tx_set;
+	u8 tx_mode;
+	u8 uniform_tile_spacing_flag;
+	u8 interpolation_filter;
+	u8 allow_warped_motion;
+	u8 is_motion_mode_switchable;
+	u8 reference_mode;
+	u8 allow_high_precision_mv;
+	u8 allow_intra_bc;
+	u8 force_integer_mv;
+	u8 allow_screen_content_tools;
+	u8 error_resilient_mode;
+	u8 frame_type;
+	u8 primary_ref_frame;
+	u8 disable_frame_end_update_cdf;
+	u32 disable_cdf_update;
+	struct vdec_av1_slice_sm skip_mode;
+	struct vdec_av1_slice_seg seg;
+	struct vdec_av1_slice_delta_q_lf delta_q_lf;
+	struct vdec_av1_slice_quantization quant;
+	struct vdec_av1_slice_lr lr;
+	u32 superres_denom;
+	struct vdec_av1_slice_loop_filter loop_filter;
+	struct vdec_av1_slice_cdef cdef;
+	struct vdec_av1_slice_mfmv mfmv;
+	struct vdec_av1_slice_tile tile;
+	u8 frame_is_intra;
+	u8 loss_less_array[V4L2_AV1_MAX_SEGMENTS];
+	u8 coded_loss_less;
+	u32 mi_rows;
+	u32 mi_cols;
+};
+
+/**
+ * struct vdec_av1_slice_seq_header - Represents an AV1 Sequence OBU
+ * @bitdepth:                   the bitdepth to use for the sequence
+ * @enable_superres:            specifies whether the use_superres syntax element may be present
+ * @enable_filter_intra:        specifies the use_filter_intra syntax element may be present
+ * @enable_intra_edge_filter:   whether the intra edge filtering process should be enabled
+ * @enable_interintra_compound: specifies the mode info fo rinter blocks may
+ *                              contain the syntax element interintra
+ * @enable_masked_compound:     specifies the mode info fo rinter blocks may
+ *                              contain the syntax element compound_type
+ * @enable_dual_filter:         the inter prediction filter type may be specified independently
+ * @enable_jnt_comp:            distance weights process may be used for inter prediction
+ * @mono_chrome:                indicates the video does not contain U and V color planes
+ * @enable_order_hint:          tools based on the values of order hints may be used
+ * @order_hint_bits:            the number of bits used for the order_hint field at each frame
+ * @use_128x128_superblock:     indicates superblocks contain 128*128 luma samples
+ * @subsampling_x:              the chroma subsamling format
+ * @subsampling_y:              the chroma subsamling format
+ * @max_frame_width:            the maximum frame width for the frames represented by sequence
+ * @max_frame_height:           the maximum frame height for the frames represented by sequence
+ */
+struct vdec_av1_slice_seq_header {
+	u8 bitdepth;
+	u8 enable_superres;
+	u8 enable_filter_intra;
+	u8 enable_intra_edge_filter;
+	u8 enable_interintra_compound;
+	u8 enable_masked_compound;
+	u8 enable_dual_filter;
+	u8 enable_jnt_comp;
+	u8 mono_chrome;
+	u8 enable_order_hint;
+	u8 order_hint_bits;
+	u8 use_128x128_superblock;
+	u8 subsampling_x;
+	u8 subsampling_y;
+	u32 max_frame_width;
+	u32 max_frame_height;
+};
+
+/**
+ * struct vdec_av1_slice_frame - Represents current Frame info
+ * @uh:                         uncompressed header info
+ * @seq:                        sequence header info
+ * @large_scale_tile:           is large scale mode
+ * @cur_ts:                     current frame timestamp
+ * @prev_fb_idx:                prev slot id
+ * @ref_frame_sign_bias:        arrays for ref_frame sign bias
+ * @order_hints:                arrays for ref_frame order hint
+ * @ref_frame_valid:            arrays for valid ref_frame
+ * @ref_frame_map:              map to slot frame info
+ * @frame_refs:                 ref_frame info
+ */
+struct vdec_av1_slice_frame {
+	struct vdec_av1_slice_uncompressed_header uh;
+	struct vdec_av1_slice_seq_header seq;
+	u8 large_scale_tile;
+	u64 cur_ts;
+	int prev_fb_idx;
+	u8 ref_frame_sign_bias[V4L2_AV1_TOTAL_REFS_PER_FRAME];
+	u32 order_hints[V4L2_AV1_REFS_PER_FRAME];
+	u32 ref_frame_valid[V4L2_AV1_REFS_PER_FRAME];
+	int ref_frame_map[V4L2_AV1_TOTAL_REFS_PER_FRAME];
+	struct vdec_av1_slice_frame_refs frame_refs[V4L2_AV1_REFS_PER_FRAME];
+};
+
+/**
+ * struct vdec_av1_slice_work_buffer - work buffer for lat
+ * @mv_addr:    mv buffer memory info
+ * @cdf_addr:   cdf buffer memory info
+ * @segid_addr: segid buffer memory info
+ */
+struct vdec_av1_slice_work_buffer {
+	struct vdec_av1_slice_mem mv_addr;
+	struct vdec_av1_slice_mem cdf_addr;
+	struct vdec_av1_slice_mem segid_addr;
+};
+
+/**
+ * struct vdec_av1_slice_frame_info - frame info for each slot
+ * @frame_type:         frame type
+ * @frame_is_intra:     is intra frame
+ * @order_hint:         order hint
+ * @order_hints:        referece frame order hint
+ * @upscaled_width:     upscale width
+ * @pic_pitch:          buffer pitch
+ * @frame_width:        frane width
+ * @frame_height:       frame height
+ * @mi_rows:            rows in mode info
+ * @mi_cols:            cols in mode info
+ * @ref_count:          mark to reference frame counts
+ */
+struct vdec_av1_slice_frame_info {
+	u8 frame_type;
+	u8 frame_is_intra;
+	int order_hint;
+	u32 order_hints[V4L2_AV1_REFS_PER_FRAME];
+	u32 upscaled_width;
+	u32 pic_pitch;
+	u32 frame_width;
+	u32 frame_height;
+	u32 mi_rows;
+	u32 mi_cols;
+	int ref_count;
+};
+
+/**
+ * struct vdec_av1_slice_slot - slot info that needs to be saved in the global instance
+ * @frame_info: frame info for each slot
+ * @timestamp:  time stamp info
+ */
+struct vdec_av1_slice_slot {
+	struct vdec_av1_slice_frame_info frame_info[AV1_MAX_FRAME_BUF_COUNT];
+	u64 timestamp[AV1_MAX_FRAME_BUF_COUNT];
+};
+
+/**
+ * struct vdec_av1_slice_fb - frame buffer for decoding
+ * @y:  current y buffer address info
+ * @c:  current c buffer address info
+ */
+struct vdec_av1_slice_fb {
+	struct vdec_av1_slice_mem y;
+	struct vdec_av1_slice_mem c;
+};
+
+/**
+ * struct vdec_av1_slice_vsi - exchange frame information between Main CPU and MicroP
+ * @bs:			input buffer info
+ * @work_buffer:	working buffe for hw
+ * @cdf_table:		cdf_table buffer
+ * @cdf_tmp:		cdf temp buffer
+ * @rd_mv:		mv buffer for lat output , core input
+ * @ube:		ube buffer
+ * @trans:		transcoded buffer
+ * @err_map:		err map buffer
+ * @row_info:		row info buffer
+ * @fb:			current y/c buffer
+ * @ref:		ref y/c buffer
+ * @iq_table:		iq table buffer
+ * @tile:		tile buffer
+ * @slots:		slots info for each frame
+ * @slot_id:		current frame slot id
+ * @frame:		current frame info
+ * @state:		status after decode done
+ * @cur_lst_tile_id:	tile id for large scale
+ */
+struct vdec_av1_slice_vsi {
+	/* lat */
+	struct vdec_av1_slice_mem bs;
+	struct vdec_av1_slice_work_buffer work_buffer[AV1_MAX_FRAME_BUF_COUNT];
+	struct vdec_av1_slice_mem cdf_table;
+	struct vdec_av1_slice_mem cdf_tmp;
+	/* LAT stage's output, Core stage's input */
+	struct vdec_av1_slice_mem rd_mv;
+	struct vdec_av1_slice_mem ube;
+	struct vdec_av1_slice_mem trans;
+	struct vdec_av1_slice_mem err_map;
+	struct vdec_av1_slice_mem row_info;
+	/* core */
+	struct vdec_av1_slice_fb fb;
+	struct vdec_av1_slice_fb ref[V4L2_AV1_REFS_PER_FRAME];
+	struct vdec_av1_slice_mem iq_table;
+	/* lat and core share*/
+	struct vdec_av1_slice_mem tile;
+	struct vdec_av1_slice_slot slots;
+	s8 slot_id;
+	struct vdec_av1_slice_frame frame;
+	struct vdec_av1_slice_state state;
+	u32 cur_lst_tile_id;
+};
+
+/**
+ * struct vdec_av1_slice_pfc - per-frame context that contains a local vsi.
+ *                             pass it from lat to core
+ * @vsi:        local vsi. copy to/from remote vsi before/after decoding
+ * @ref_idx:    reference buffer timestamp
+ * @seq:        picture sequence
+ */
+struct vdec_av1_slice_pfc {
+	struct vdec_av1_slice_vsi vsi;
+	u64 ref_idx[V4L2_AV1_REFS_PER_FRAME];
+	int seq;
+};
+
+/**
+ * struct vdec_av1_slice_instance - represent one av1 instance
+ * @ctx:                pointer to codec's context
+ * @vpu:                VPU instance
+ * @iq_table:           iq table buffer
+ * @cdf_table:          cdf table buffer
+ * @mv:                 mv working buffer
+ * @cdf:                cdf working buffer
+ * @seg:                segmentation working buffer
+ * @cdf_temp:           cdf temp buffer
+ * @tile:               tile buffer
+ * @slots:              slots info
+ * @tile_group:         tile_group entry
+ * @level:              level of current resolution
+ * @width:              width of last picture
+ * @height:             height of last picture
+ * @frame_type:         frame_type of last picture
+ * @irq_enabled:        irq to Main CPU or MicroP
+ * @inneracing_mode:    is inneracing mode
+ * @init_vsi:           vsi used for initialized AV1 instance
+ * @vsi:                vsi used for decoding/flush ...
+ * @core_vsi:           vsi used for Core stage
+ * @seq:                global picture sequence
+ */
+struct vdec_av1_slice_instance {
+	struct mtk_vcodec_ctx *ctx;
+	struct vdec_vpu_inst vpu;
+
+	struct mtk_vcodec_mem iq_table;
+	struct mtk_vcodec_mem cdf_table;
+
+	struct mtk_vcodec_mem mv[AV1_MAX_FRAME_BUF_COUNT];
+	struct mtk_vcodec_mem cdf[AV1_MAX_FRAME_BUF_COUNT];
+	struct mtk_vcodec_mem seg[AV1_MAX_FRAME_BUF_COUNT];
+	struct mtk_vcodec_mem cdf_temp;
+	struct mtk_vcodec_mem tile;
+	struct vdec_av1_slice_slot slots;
+	struct vdec_av1_slice_tile_group tile_group;
+
+	/* for resolution change and get_pic_info */
+	enum vdec_av1_slice_resolution_level level;
+	u32 width;
+	u32 height;
+
+	u32 frame_type;
+	u32 irq_enabled;
+	u32 inneracing_mode;
+
+	/* MicroP vsi */
+	union {
+		struct vdec_av1_slice_init_vsi *init_vsi;
+		struct vdec_av1_slice_vsi *vsi;
+	};
+	struct vdec_av1_slice_vsi *core_vsi;
+	int seq;
+};
+
+static int vdec_av1_slice_core_decode(struct vdec_lat_buf *lat_buf);
+
+static inline int vdec_av1_slice_get_msb(u32 n)
+{
+	if (n == 0)
+		return 0;
+	return 31 ^ __builtin_clz(n);
+}
+
+static inline bool vdec_av1_slice_need_scale(u32 ref_width, u32 ref_height,
+					     u32 this_width, u32 this_height)
+{
+	return ((this_width << 1) >= ref_width) &&
+		((this_height << 1) >= ref_height) &&
+		(this_width <= (ref_width << 4)) &&
+		(this_height <= (ref_height << 4));
+}
+
+static void *vdec_av1_get_ctrl_ptr(struct mtk_vcodec_ctx *ctx, int id)
+{
+	struct v4l2_ctrl *ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, id);
+
+	if (!ctrl)
+		return ERR_PTR(-EINVAL);
+
+	return ctrl->p_cur.p;
+}
+
+static int vdec_av1_slice_init_cdf_table(struct vdec_av1_slice_instance *instance)
+{
+	u8 *remote_cdf_table;
+	struct mtk_vcodec_ctx *ctx;
+	struct vdec_av1_slice_init_vsi *vsi;
+	int ret;
+
+	ctx = instance->ctx;
+	vsi = instance->vpu.vsi;
+	remote_cdf_table = mtk_vcodec_fw_map_dm_addr(ctx->dev->fw_handler,
+						     (u32)vsi->cdf_table_addr);
+	if (IS_ERR(remote_cdf_table)) {
+		mtk_vcodec_err(instance, "failed to map cdf table\n");
+		return PTR_ERR(remote_cdf_table);
+	}
+
+	mtk_vcodec_debug(instance, "map cdf table to 0x%p\n",
+			 remote_cdf_table);
+
+	if (instance->cdf_table.va)
+		mtk_vcodec_mem_free(ctx, &instance->cdf_table);
+	instance->cdf_table.size = vsi->cdf_table_size;
+
+	ret = mtk_vcodec_mem_alloc(ctx, &instance->cdf_table);
+	if (ret)
+		return ret;
+
+	memcpy(instance->cdf_table.va, remote_cdf_table, vsi->cdf_table_size);
+
+	return 0;
+}
+
+static int vdec_av1_slice_init_iq_table(struct vdec_av1_slice_instance *instance)
+{
+	u8 *remote_iq_table;
+	struct mtk_vcodec_ctx *ctx;
+	struct vdec_av1_slice_init_vsi *vsi;
+	int ret;
+
+	ctx = instance->ctx;
+	vsi = instance->vpu.vsi;
+	remote_iq_table = mtk_vcodec_fw_map_dm_addr(ctx->dev->fw_handler,
+						    (u32)vsi->iq_table_addr);
+	if (IS_ERR(remote_iq_table)) {
+		mtk_vcodec_err(instance, "failed to map iq table\n");
+		return PTR_ERR(remote_iq_table);
+	}
+
+	mtk_vcodec_debug(instance, "map iq table to 0x%p\n", remote_iq_table);
+
+	if (instance->iq_table.va)
+		mtk_vcodec_mem_free(ctx, &instance->iq_table);
+	instance->iq_table.size = vsi->iq_table_size;
+
+	ret = mtk_vcodec_mem_alloc(ctx, &instance->iq_table);
+	if (ret)
+		return ret;
+
+	memcpy(instance->iq_table.va, remote_iq_table, vsi->iq_table_size);
+
+	return 0;
+}
+
+static int vdec_av1_slice_get_new_slot(struct vdec_av1_slice_vsi *vsi)
+{
+	struct vdec_av1_slice_slot *slots = &vsi->slots;
+	int new_slot_idx = AV1_INVALID_IDX;
+	int i;
+
+	for (i = 0; i < AV1_MAX_FRAME_BUF_COUNT; i++) {
+		if (slots->frame_info[i].ref_count == 0) {
+			new_slot_idx = i;
+			break;
+		}
+	}
+
+	if (new_slot_idx != AV1_INVALID_IDX) {
+		slots->frame_info[new_slot_idx].ref_count++;
+		slots->timestamp[new_slot_idx] = vsi->frame.cur_ts;
+	}
+
+	return new_slot_idx;
+}
+
+static inline void vdec_av1_slice_clear_fb(struct vdec_av1_slice_frame_info *frame_info)
+{
+	memset((void *)frame_info, 0, sizeof(struct vdec_av1_slice_frame_info));
+}
+
+static void vdec_av1_slice_decrease_ref_count(struct vdec_av1_slice_slot *slots, int fb_idx)
+{
+	struct vdec_av1_slice_frame_info *frame_info = slots->frame_info;
+
+	frame_info[fb_idx].ref_count--;
+	if (frame_info[fb_idx].ref_count < 0) {
+		frame_info[fb_idx].ref_count = 0;
+		mtk_v4l2_err("av1_error: %s() fb_idx %d decrease ref_count error\n",
+			     __func__, fb_idx);
+	}
+
+	vdec_av1_slice_clear_fb(&frame_info[fb_idx]);
+}
+
+static void vdec_av1_slice_cleanup_slots(struct vdec_av1_slice_slot *slots,
+					 struct vdec_av1_slice_frame *frame,
+					 struct v4l2_ctrl_av1_frame *ctrl_fh)
+{
+	int slot_id, ref_id;
+
+	for (ref_id = 0; ref_id < V4L2_AV1_TOTAL_REFS_PER_FRAME; ref_id++)
+		frame->ref_frame_map[ref_id] = AV1_INVALID_IDX;
+
+	for (slot_id = 0; slot_id < AV1_MAX_FRAME_BUF_COUNT; slot_id++) {
+		u64 timestamp = slots->timestamp[slot_id];
+		bool ref_used = false;
+
+		/* ignored unused slots */
+		if (slots->frame_info[slot_id].ref_count == 0)
+			continue;
+
+		for (ref_id = 0; ref_id < V4L2_AV1_TOTAL_REFS_PER_FRAME; ref_id++) {
+			if (ctrl_fh->reference_frame_ts[ref_id] == timestamp) {
+				frame->ref_frame_map[ref_id] = slot_id;
+				ref_used = true;
+			}
+		}
+
+		if (!ref_used)
+			vdec_av1_slice_decrease_ref_count(slots, slot_id);
+	}
+}
+
+static void vdec_av1_slice_setup_slot(struct vdec_av1_slice_instance *instance,
+				      struct vdec_av1_slice_vsi *vsi,
+				      struct v4l2_ctrl_av1_frame *ctrl_fh)
+{
+	struct vdec_av1_slice_frame_info *cur_frame_info;
+	struct vdec_av1_slice_uncompressed_header *uh = &vsi->frame.uh;
+	int ref_id;
+
+	memcpy(&vsi->slots, &instance->slots, sizeof(instance->slots));
+	vdec_av1_slice_cleanup_slots(&vsi->slots, &vsi->frame, ctrl_fh);
+	vsi->slot_id = vdec_av1_slice_get_new_slot(vsi);
+
+	if (vsi->slot_id == AV1_INVALID_IDX) {
+		mtk_v4l2_err("warning:av1 get invalid index slot\n");
+		vsi->slot_id = 0;
+	}
+	cur_frame_info = &vsi->slots.frame_info[vsi->slot_id];
+	cur_frame_info->frame_type = uh->frame_type;
+	cur_frame_info->frame_is_intra = ((uh->frame_type == AV1_INTRA_ONLY_FRAME) ||
+					  (uh->frame_type == AV1_KEY_FRAME));
+	cur_frame_info->order_hint = uh->order_hint;
+	cur_frame_info->upscaled_width = uh->upscaled_width;
+	cur_frame_info->pic_pitch = 0;
+	cur_frame_info->frame_width = uh->frame_width;
+	cur_frame_info->frame_height = uh->frame_height;
+	cur_frame_info->mi_cols = ((uh->frame_width + 7) >> 3) << 1;
+	cur_frame_info->mi_rows = ((uh->frame_height + 7) >> 3) << 1;
+
+	/* ensure current frame is properly mapped if referenced */
+	for (ref_id = 0; ref_id < V4L2_AV1_TOTAL_REFS_PER_FRAME; ref_id++) {
+		u64 timestamp = vsi->slots.timestamp[vsi->slot_id];
+
+		if (ctrl_fh->reference_frame_ts[ref_id] == timestamp)
+			vsi->frame.ref_frame_map[ref_id] = vsi->slot_id;
+	}
+}
+
+static int vdec_av1_slice_alloc_working_buffer(struct vdec_av1_slice_instance *instance,
+					       struct vdec_av1_slice_vsi *vsi)
+{
+	struct mtk_vcodec_ctx *ctx = instance->ctx;
+	enum vdec_av1_slice_resolution_level level;
+	u32 max_sb_w, max_sb_h, max_w, max_h, w, h;
+	int i, ret;
+
+	w = vsi->frame.uh.frame_width;
+	h = vsi->frame.uh.frame_height;
+
+	if (w > VCODEC_DEC_4K_CODED_WIDTH || h > VCODEC_DEC_4K_CODED_HEIGHT)
+		/* 8K */
+		return -EINVAL;
+
+	if (w > MTK_VDEC_MAX_W || h > MTK_VDEC_MAX_H) {
+		/* 4K */
+		level = AV1_RES_4K;
+		max_w = VCODEC_DEC_4K_CODED_WIDTH;
+		max_h = VCODEC_DEC_4K_CODED_HEIGHT;
+	} else {
+		/* FHD */
+		level = AV1_RES_FHD;
+		max_w = MTK_VDEC_MAX_W;
+		max_h = MTK_VDEC_MAX_H;
+	}
+
+	if (level == instance->level)
+		return 0;
+
+	mtk_vcodec_debug(instance, "resolution level changed from %u to %u, %ux%u",
+			 instance->level, level, w, h);
+
+	max_sb_w = DIV_ROUND_UP(max_w, 128);
+	max_sb_h = DIV_ROUND_UP(max_h, 128);
+
+	for (i = 0; i < AV1_MAX_FRAME_BUF_COUNT; i++) {
+		if (instance->mv[i].va)
+			mtk_vcodec_mem_free(ctx, &instance->mv[i]);
+		instance->mv[i].size = max_sb_w * max_sb_h * SZ_1K;
+		ret = mtk_vcodec_mem_alloc(ctx, &instance->mv[i]);
+		if (ret)
+			goto err;
+
+		if (instance->seg[i].va)
+			mtk_vcodec_mem_free(ctx, &instance->seg[i]);
+		instance->seg[i].size = max_sb_w * max_sb_h * 512;
+		ret = mtk_vcodec_mem_alloc(ctx, &instance->seg[i]);
+		if (ret)
+			goto err;
+
+		if (instance->cdf[i].va)
+			mtk_vcodec_mem_free(ctx, &instance->cdf[i]);
+		instance->cdf[i].size = AV1_CDF_TABLE_BUFFER_SIZE;
+		ret = mtk_vcodec_mem_alloc(ctx, &instance->cdf[i]);
+		if (ret)
+			goto err;
+	}
+
+	if (!instance->cdf_temp.va) {
+		instance->cdf_temp.size = (SZ_1K * 16 * 100);
+		ret = mtk_vcodec_mem_alloc(ctx, &instance->cdf_temp);
+		if (ret)
+			goto err;
+		vsi->cdf_tmp.buf = instance->cdf_temp.dma_addr;
+		vsi->cdf_tmp.size = instance->cdf_temp.size;
+	}
+
+	if (instance->tile.va)
+		mtk_vcodec_mem_free(ctx, &instance->tile);
+
+	instance->tile.size = AV1_TILE_BUF_SIZE * V4L2_AV1_MAX_TILE_COUNT;
+	ret = mtk_vcodec_mem_alloc(ctx, &instance->tile);
+	if (ret)
+		goto err;
+
+	instance->level = level;
+	return 0;
+
+err:
+	instance->level = AV1_RES_NONE;
+	return ret;
+}
+
+static void vdec_av1_slice_free_working_buffer(struct vdec_av1_slice_instance *instance)
+{
+	struct mtk_vcodec_ctx *ctx = instance->ctx;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(instance->mv); i++)
+		mtk_vcodec_mem_free(ctx, &instance->mv[i]);
+
+	for (i = 0; i < ARRAY_SIZE(instance->seg); i++)
+		mtk_vcodec_mem_free(ctx, &instance->seg[i]);
+
+	for (i = 0; i < ARRAY_SIZE(instance->cdf); i++)
+		mtk_vcodec_mem_free(ctx, &instance->cdf[i]);
+
+	mtk_vcodec_mem_free(ctx, &instance->tile);
+	mtk_vcodec_mem_free(ctx, &instance->cdf_temp);
+	mtk_vcodec_mem_free(ctx, &instance->cdf_table);
+	mtk_vcodec_mem_free(ctx, &instance->iq_table);
+
+	instance->level = AV1_RES_NONE;
+}
+
+static inline void vdec_av1_slice_vsi_from_remote(struct vdec_av1_slice_vsi *vsi,
+						  struct vdec_av1_slice_vsi *remote_vsi)
+{
+	memcpy(&vsi->trans, &remote_vsi->trans, sizeof(vsi->trans));
+	memcpy(&vsi->state, &remote_vsi->state, sizeof(vsi->state));
+}
+
+static inline void vdec_av1_slice_vsi_to_remote(struct vdec_av1_slice_vsi *vsi,
+						struct vdec_av1_slice_vsi *remote_vsi)
+{
+	memcpy(remote_vsi, vsi, sizeof(*vsi));
+}
+
+static int vdec_av1_slice_setup_lat_from_src_buf(struct vdec_av1_slice_instance *instance,
+						 struct vdec_av1_slice_vsi *vsi,
+						 struct vdec_lat_buf *lat_buf)
+{
+	struct vb2_v4l2_buffer *src;
+	struct vb2_v4l2_buffer *dst;
+
+	src = v4l2_m2m_next_src_buf(instance->ctx->m2m_ctx);
+	if (!src)
+		return -EINVAL;
+
+	lat_buf->src_buf_req = src->vb2_buf.req_obj.req;
+	dst = &lat_buf->ts_info;
+	v4l2_m2m_buf_copy_metadata(src, dst, true);
+	vsi->frame.cur_ts = dst->vb2_buf.timestamp;
+
+	return 0;
+}
+
+static short vdec_av1_slice_resolve_divisor_32(u32 D, short *shift)
+{
+	int f;
+	int e;
+
+	*shift = vdec_av1_slice_get_msb(D);
+	/* e is obtained from D after resetting the most significant 1 bit. */
+	e = D - ((u32)1 << *shift);
+	/* Get the most significant DIV_LUT_BITS (8) bits of e into f */
+	if (*shift > DIV_LUT_BITS)
+		f = AV1_DIV_ROUND_UP_POW2(e, *shift - DIV_LUT_BITS);
+	else
+		f = e << (DIV_LUT_BITS - *shift);
+	if (f > DIV_LUT_NUM)
+		return -1;
+	*shift += DIV_LUT_PREC_BITS;
+	/* Use f as lookup into the precomputed table of multipliers */
+	return div_lut[f];
+}
+
+static void vdec_av1_slice_get_shear_params(struct vdec_av1_slice_gm *gm_params)
+{
+	const int *mat = gm_params->wmmat;
+	short shift;
+	short y;
+	long long gv, dv;
+
+	if (gm_params->wmmat[2] <= 0)
+		return;
+
+	gm_params->alpha = clamp_val(mat[2] - (1 << WARPEDMODEL_PREC_BITS), S16_MIN, S16_MAX);
+	gm_params->beta = clamp_val(mat[3], S16_MIN, S16_MAX);
+
+	y = vdec_av1_slice_resolve_divisor_32(abs(mat[2]), &shift) * (mat[2] < 0 ? -1 : 1);
+
+	gv = ((long long)mat[4] * (1 << WARPEDMODEL_PREC_BITS)) * y;
+	gm_params->gamma = clamp_val((int)AV1_DIV_ROUND_UP_POW2_SIGNED(gv, shift),
+				     S16_MIN, S16_MAX);
+
+	dv = ((long long)mat[3] * mat[4]) * y;
+	gm_params->delta = clamp_val(mat[5] - (int)AV1_DIV_ROUND_UP_POW2_SIGNED(dv, shift) -
+				     (1 << WARPEDMODEL_PREC_BITS), S16_MIN, S16_MAX);
+
+	gm_params->alpha = AV1_DIV_ROUND_UP_POW2_SIGNED(gm_params->alpha, WARP_PARAM_REDUCE_BITS) *
+							(1 << WARP_PARAM_REDUCE_BITS);
+	gm_params->beta = AV1_DIV_ROUND_UP_POW2_SIGNED(gm_params->beta, WARP_PARAM_REDUCE_BITS) *
+						       (1 << WARP_PARAM_REDUCE_BITS);
+	gm_params->gamma = AV1_DIV_ROUND_UP_POW2_SIGNED(gm_params->gamma, WARP_PARAM_REDUCE_BITS) *
+							(1 << WARP_PARAM_REDUCE_BITS);
+	gm_params->delta = AV1_DIV_ROUND_UP_POW2_SIGNED(gm_params->delta, WARP_PARAM_REDUCE_BITS) *
+							(1 << WARP_PARAM_REDUCE_BITS);
+}
+
+static void vdec_av1_slice_setup_gm(struct vdec_av1_slice_gm *gm,
+				    struct v4l2_av1_global_motion *ctrl_gm)
+{
+	u32 i, j;
+
+	for (i = 0; i < V4L2_AV1_TOTAL_REFS_PER_FRAME; i++) {
+		gm[i].wmtype = ctrl_gm->type[i];
+		for (j = 0; j < 6; j++)
+			gm[i].wmmat[j] = ctrl_gm->params[i][j];
+
+		gm[i].invalid = !!(ctrl_gm->invalid & BIT(i));
+		gm[i].alpha = 0;
+		gm[i].beta = 0;
+		gm[i].gamma = 0;
+		gm[i].delta = 0;
+		if (gm[i].wmtype <= V4L2_AV1_WARP_MODEL_AFFINE)
+			vdec_av1_slice_get_shear_params(&gm[i]);
+	}
+}
+
+static void vdec_av1_slice_setup_seg(struct vdec_av1_slice_seg *seg,
+				     struct v4l2_av1_segmentation *ctrl_seg)
+{
+	u32 i, j;
+
+	seg->segmentation_enabled = SEGMENTATION_FLAG(ctrl_seg, ENABLED);
+	seg->segmentation_update_map = SEGMENTATION_FLAG(ctrl_seg, UPDATE_MAP);
+	seg->segmentation_temporal_update = SEGMENTATION_FLAG(ctrl_seg, TEMPORAL_UPDATE);
+	seg->segmentation_update_data = SEGMENTATION_FLAG(ctrl_seg, UPDATE_DATA);
+	seg->segid_preskip = SEGMENTATION_FLAG(ctrl_seg, SEG_ID_PRE_SKIP);
+	seg->last_active_segid = ctrl_seg->last_active_seg_id;
+
+	for (i = 0; i < V4L2_AV1_MAX_SEGMENTS; i++) {
+		seg->feature_enabled_mask[i] = ctrl_seg->feature_enabled[i];
+		for (j = 0; j < V4L2_AV1_SEG_LVL_MAX; j++)
+			seg->feature_data[i][j] = ctrl_seg->feature_data[i][j];
+	}
+}
+
+static void vdec_av1_slice_setup_quant(struct vdec_av1_slice_quantization *quant,
+				       struct v4l2_av1_quantization *ctrl_quant)
+{
+	quant->base_q_idx = ctrl_quant->base_q_idx;
+	quant->delta_qydc = ctrl_quant->delta_q_y_dc;
+	quant->delta_qudc = ctrl_quant->delta_q_u_dc;
+	quant->delta_quac = ctrl_quant->delta_q_u_ac;
+	quant->delta_qvdc = ctrl_quant->delta_q_v_dc;
+	quant->delta_qvac = ctrl_quant->delta_q_v_ac;
+	quant->qm_y = ctrl_quant->qm_y;
+	quant->qm_u = ctrl_quant->qm_u;
+	quant->qm_v = ctrl_quant->qm_v;
+	quant->using_qmatrix = QUANT_FLAG(ctrl_quant, USING_QMATRIX);
+}
+
+static int vdec_av1_slice_get_qindex(struct vdec_av1_slice_uncompressed_header *uh,
+				     int segmentation_id)
+{
+	struct vdec_av1_slice_seg *seg = &uh->seg;
+	struct vdec_av1_slice_quantization *quant = &uh->quant;
+	int data = 0, qindex = 0;
+
+	if (seg->segmentation_enabled &&
+	    (seg->feature_enabled_mask[segmentation_id] & BIT(SEG_LVL_ALT_Q))) {
+		data = seg->feature_data[segmentation_id][SEG_LVL_ALT_Q];
+		qindex = quant->base_q_idx + data;
+		return clamp_val(qindex, 0, MAXQ);
+	}
+
+	return quant->base_q_idx;
+}
+
+static void vdec_av1_slice_setup_lr(struct vdec_av1_slice_lr *lr,
+				    struct v4l2_av1_loop_restoration  *ctrl_lr)
+{
+	int i;
+
+	lr->use_lr = 0;
+	lr->use_chroma_lr = 0;
+	for (i = 0; i < V4L2_AV1_NUM_PLANES_MAX; i++) {
+		lr->frame_restoration_type[i] = ctrl_lr->frame_restoration_type[i];
+		lr->loop_restoration_size[i] = ctrl_lr->loop_restoration_size[i];
+		if (lr->frame_restoration_type[i]) {
+			lr->use_lr = 1;
+			if (i > 0)
+				lr->use_chroma_lr = 1;
+		}
+	}
+}
+
+static void vdec_av1_slice_setup_lf(struct vdec_av1_slice_loop_filter *lf,
+				    struct v4l2_av1_loop_filter *ctrl_lf)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(lf->loop_filter_level); i++)
+		lf->loop_filter_level[i] = ctrl_lf->level[i];
+
+	for (i = 0; i < V4L2_AV1_TOTAL_REFS_PER_FRAME; i++)
+		lf->loop_filter_ref_deltas[i] = ctrl_lf->ref_deltas[i];
+
+	for (i = 0; i < ARRAY_SIZE(lf->loop_filter_mode_deltas); i++)
+		lf->loop_filter_mode_deltas[i] = ctrl_lf->mode_deltas[i];
+
+	lf->loop_filter_sharpness = ctrl_lf->sharpness;
+	lf->loop_filter_delta_enabled =
+		   BIT_FLAG(ctrl_lf, V4L2_AV1_LOOP_FILTER_FLAG_DELTA_ENABLED);
+}
+
+static void vdec_av1_slice_setup_cdef(struct vdec_av1_slice_cdef *cdef,
+				      struct v4l2_av1_cdef *ctrl_cdef)
+{
+	int i;
+
+	cdef->cdef_damping = ctrl_cdef->damping_minus_3 + 3;
+	cdef->cdef_bits = ctrl_cdef->bits;
+
+	for (i = 0; i < V4L2_AV1_CDEF_MAX; i++) {
+		if (ctrl_cdef->y_sec_strength[i] == 4)
+			ctrl_cdef->y_sec_strength[i] -= 1;
+
+		if (ctrl_cdef->uv_sec_strength[i] == 4)
+			ctrl_cdef->uv_sec_strength[i] -= 1;
+
+		cdef->cdef_y_strength[i] =
+			ctrl_cdef->y_pri_strength[i] << SECONDARY_FILTER_STRENGTH_NUM_BITS |
+			ctrl_cdef->y_sec_strength[i];
+		cdef->cdef_uv_strength[i] =
+			ctrl_cdef->uv_pri_strength[i] << SECONDARY_FILTER_STRENGTH_NUM_BITS |
+			ctrl_cdef->uv_sec_strength[i];
+	}
+}
+
+static void vdec_av1_slice_setup_seq(struct vdec_av1_slice_seq_header *seq,
+				     struct v4l2_ctrl_av1_sequence *ctrl_seq)
+{
+	seq->bitdepth = ctrl_seq->bit_depth;
+	seq->max_frame_width = ctrl_seq->max_frame_width_minus_1 + 1;
+	seq->max_frame_height = ctrl_seq->max_frame_height_minus_1 + 1;
+	seq->enable_superres = SEQUENCE_FLAG(ctrl_seq, ENABLE_SUPERRES);
+	seq->enable_filter_intra = SEQUENCE_FLAG(ctrl_seq, ENABLE_FILTER_INTRA);
+	seq->enable_intra_edge_filter = SEQUENCE_FLAG(ctrl_seq, ENABLE_INTRA_EDGE_FILTER);
+	seq->enable_interintra_compound = SEQUENCE_FLAG(ctrl_seq, ENABLE_INTERINTRA_COMPOUND);
+	seq->enable_masked_compound = SEQUENCE_FLAG(ctrl_seq, ENABLE_MASKED_COMPOUND);
+	seq->enable_dual_filter = SEQUENCE_FLAG(ctrl_seq, ENABLE_DUAL_FILTER);
+	seq->enable_jnt_comp = SEQUENCE_FLAG(ctrl_seq, ENABLE_JNT_COMP);
+	seq->mono_chrome = SEQUENCE_FLAG(ctrl_seq, MONO_CHROME);
+	seq->enable_order_hint = SEQUENCE_FLAG(ctrl_seq, ENABLE_ORDER_HINT);
+	seq->order_hint_bits = ctrl_seq->order_hint_bits;
+	seq->use_128x128_superblock = SEQUENCE_FLAG(ctrl_seq, USE_128X128_SUPERBLOCK);
+	seq->subsampling_x = SEQUENCE_FLAG(ctrl_seq, SUBSAMPLING_X);
+	seq->subsampling_y = SEQUENCE_FLAG(ctrl_seq, SUBSAMPLING_Y);
+}
+
+static void vdec_av1_slice_setup_tile(struct vdec_av1_slice_frame *frame,
+				      struct v4l2_av1_tile_info *ctrl_tile)
+{
+	struct vdec_av1_slice_seq_header *seq = &frame->seq;
+	struct vdec_av1_slice_tile *tile = &frame->uh.tile;
+	u32 mib_size_log2 = seq->use_128x128_superblock ? 5 : 4;
+	int i;
+
+	tile->tile_cols = ctrl_tile->tile_cols;
+	tile->tile_rows = ctrl_tile->tile_rows;
+	tile->context_update_tile_id = ctrl_tile->context_update_tile_id;
+	tile->uniform_tile_spacing_flag =
+		BIT_FLAG(ctrl_tile, V4L2_AV1_TILE_INFO_FLAG_UNIFORM_TILE_SPACING);
+
+	for (i = 0; i < tile->tile_cols + 1; i++)
+		tile->mi_col_starts[i] =
+			ALIGN(ctrl_tile->mi_col_starts[i], BIT(mib_size_log2)) >> mib_size_log2;
+
+	for (i = 0; i < tile->tile_rows + 1; i++)
+		tile->mi_row_starts[i] =
+			ALIGN(ctrl_tile->mi_row_starts[i], BIT(mib_size_log2)) >> mib_size_log2;
+}
+
+static void vdec_av1_slice_setup_uh(struct vdec_av1_slice_instance *instance,
+				    struct vdec_av1_slice_frame *frame,
+				    struct v4l2_ctrl_av1_frame *ctrl_fh)
+{
+	struct vdec_av1_slice_uncompressed_header *uh = &frame->uh;
+	int i;
+
+	uh->use_ref_frame_mvs = FH_FLAG(ctrl_fh, USE_REF_FRAME_MVS);
+	uh->order_hint = ctrl_fh->order_hint;
+	vdec_av1_slice_setup_gm(uh->gm, &ctrl_fh->global_motion);
+	uh->upscaled_width = ctrl_fh->upscaled_width;
+	uh->frame_width = ctrl_fh->frame_width_minus_1 + 1;
+	uh->frame_height = ctrl_fh->frame_height_minus_1 + 1;
+	uh->mi_cols = ((uh->frame_width + 7) >> 3) << 1;
+	uh->mi_rows = ((uh->frame_height + 7) >> 3) << 1;
+	uh->reduced_tx_set = FH_FLAG(ctrl_fh, REDUCED_TX_SET);
+	uh->tx_mode = ctrl_fh->tx_mode;
+	uh->uniform_tile_spacing_flag =
+		BIT_FLAG(&ctrl_fh->tile_info, V4L2_AV1_TILE_INFO_FLAG_UNIFORM_TILE_SPACING);
+	uh->interpolation_filter = ctrl_fh->interpolation_filter;
+	uh->allow_warped_motion = FH_FLAG(ctrl_fh, ALLOW_WARPED_MOTION);
+	uh->is_motion_mode_switchable = FH_FLAG(ctrl_fh, IS_MOTION_MODE_SWITCHABLE);
+	uh->frame_type = ctrl_fh->frame_type;
+	uh->frame_is_intra = (uh->frame_type == V4L2_AV1_INTRA_ONLY_FRAME ||
+			      uh->frame_type == V4L2_AV1_KEY_FRAME);
+
+	if (!uh->frame_is_intra && FH_FLAG(ctrl_fh, REFERENCE_SELECT))
+		uh->reference_mode = AV1_REFERENCE_MODE_SELECT;
+	else
+		uh->reference_mode = AV1_SINGLE_REFERENCE;
+
+	uh->allow_high_precision_mv = FH_FLAG(ctrl_fh, ALLOW_HIGH_PRECISION_MV);
+	uh->allow_intra_bc = FH_FLAG(ctrl_fh, ALLOW_INTRABC);
+	uh->force_integer_mv = FH_FLAG(ctrl_fh, FORCE_INTEGER_MV);
+	uh->allow_screen_content_tools = FH_FLAG(ctrl_fh, ALLOW_SCREEN_CONTENT_TOOLS);
+	uh->error_resilient_mode = FH_FLAG(ctrl_fh, ERROR_RESILIENT_MODE);
+	uh->primary_ref_frame = ctrl_fh->primary_ref_frame;
+	uh->disable_frame_end_update_cdf =
+			FH_FLAG(ctrl_fh, DISABLE_FRAME_END_UPDATE_CDF);
+	uh->disable_cdf_update = FH_FLAG(ctrl_fh, DISABLE_CDF_UPDATE);
+	uh->skip_mode.skip_mode_present = FH_FLAG(ctrl_fh, SKIP_MODE_PRESENT);
+	uh->skip_mode.skip_mode_frame[0] =
+		ctrl_fh->skip_mode_frame[0] - V4L2_AV1_REF_LAST_FRAME;
+	uh->skip_mode.skip_mode_frame[1] =
+		ctrl_fh->skip_mode_frame[1] - V4L2_AV1_REF_LAST_FRAME;
+	uh->skip_mode.skip_mode_allowed = ctrl_fh->skip_mode_frame[0] ? 1 : 0;
+
+	vdec_av1_slice_setup_seg(&uh->seg, &ctrl_fh->segmentation);
+	uh->delta_q_lf.delta_q_present = QUANT_FLAG(&ctrl_fh->quantization, DELTA_Q_PRESENT);
+	uh->delta_q_lf.delta_q_res = 1 << ctrl_fh->quantization.delta_q_res;
+	uh->delta_q_lf.delta_lf_present =
+		BIT_FLAG(&ctrl_fh->loop_filter, V4L2_AV1_LOOP_FILTER_FLAG_DELTA_LF_PRESENT);
+	uh->delta_q_lf.delta_lf_res = ctrl_fh->loop_filter.delta_lf_res;
+	uh->delta_q_lf.delta_lf_multi =
+		BIT_FLAG(&ctrl_fh->loop_filter, V4L2_AV1_LOOP_FILTER_FLAG_DELTA_LF_MULTI);
+	vdec_av1_slice_setup_quant(&uh->quant, &ctrl_fh->quantization);
+
+	uh->coded_loss_less = 1;
+	for (i = 0; i < V4L2_AV1_MAX_SEGMENTS; i++) {
+		uh->quant.qindex[i] = vdec_av1_slice_get_qindex(uh, i);
+		uh->loss_less_array[i] =
+			(uh->quant.qindex[i] == 0 && uh->quant.delta_qydc == 0 &&
+			uh->quant.delta_quac == 0 && uh->quant.delta_qudc == 0 &&
+			uh->quant.delta_qvac == 0 && uh->quant.delta_qvdc == 0);
+
+		if (!uh->loss_less_array[i])
+			uh->coded_loss_less = 0;
+	}
+
+	vdec_av1_slice_setup_lr(&uh->lr, &ctrl_fh->loop_restoration);
+	uh->superres_denom = ctrl_fh->superres_denom;
+	vdec_av1_slice_setup_lf(&uh->loop_filter, &ctrl_fh->loop_filter);
+	vdec_av1_slice_setup_cdef(&uh->cdef, &ctrl_fh->cdef);
+	vdec_av1_slice_setup_tile(frame, &ctrl_fh->tile_info);
+}
+
+static int vdec_av1_slice_setup_tile_group(struct vdec_av1_slice_instance *instance,
+					   struct vdec_av1_slice_vsi *vsi)
+{
+	struct v4l2_ctrl_av1_tile_group_entry *ctrl_tge;
+	struct vdec_av1_slice_tile_group *tile_group = &instance->tile_group;
+	struct vdec_av1_slice_uncompressed_header *uh = &vsi->frame.uh;
+	struct vdec_av1_slice_tile *tile = &uh->tile;
+	struct v4l2_ctrl *ctrl;
+	u32 tge_size;
+	int i;
+
+	ctrl = v4l2_ctrl_find(&instance->ctx->ctrl_hdl, V4L2_CID_STATELESS_AV1_TILE_GROUP_ENTRY);
+	if (!ctrl)
+		return -EINVAL;
+
+	tge_size = ctrl->elems;
+	ctrl_tge = (struct v4l2_ctrl_av1_tile_group_entry *)ctrl->p_cur.p;
+
+	tile_group->num_tiles = tile->tile_cols * tile->tile_rows;
+
+	if (tile_group->num_tiles != tge_size ||
+	    tile_group->num_tiles > V4L2_AV1_MAX_TILE_COUNT) {
+		mtk_vcodec_err(instance, "invalid tge_size %d, tile_num:%d\n",
+			       tge_size, tile_group->num_tiles);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < tge_size; i++) {
+		if (i != ctrl_tge[i].tile_row * vsi->frame.uh.tile.tile_cols +
+		    ctrl_tge[i].tile_col) {
+			mtk_vcodec_err(instance, "invalid tge info %d, %d %d %d\n",
+				       i, ctrl_tge[i].tile_row, ctrl_tge[i].tile_col,
+				       vsi->frame.uh.tile.tile_rows);
+			return -EINVAL;
+		}
+		tile_group->tile_size[i] = ctrl_tge[i].tile_size;
+		tile_group->tile_start_offset[i] = ctrl_tge[i].tile_offset;
+	}
+
+	return 0;
+}
+
+static inline void vdec_av1_slice_setup_state(struct vdec_av1_slice_vsi *vsi)
+{
+	memset(&vsi->state, 0, sizeof(vsi->state));
+}
+
+static void vdec_av1_slice_setup_scale_factors(struct vdec_av1_slice_frame_refs *frame_ref,
+					       struct vdec_av1_slice_frame_info *ref_frame_info,
+					       struct vdec_av1_slice_uncompressed_header *uh)
+{
+	struct vdec_av1_slice_scale_factors *scale_factors = &frame_ref->scale_factors;
+	u32 ref_upscaled_width = ref_frame_info->upscaled_width;
+	u32 ref_frame_height = ref_frame_info->frame_height;
+	u32 frame_width = uh->frame_width;
+	u32 frame_height = uh->frame_height;
+
+	if (!vdec_av1_slice_need_scale(ref_upscaled_width, ref_frame_height,
+				       frame_width, frame_height)) {
+		scale_factors->x_scale = -1;
+		scale_factors->y_scale = -1;
+		scale_factors->is_scaled = 0;
+		return;
+	}
+
+	scale_factors->x_scale =
+		((ref_upscaled_width << AV1_REF_SCALE_SHIFT) + (frame_width >> 1)) / frame_width;
+	scale_factors->y_scale =
+		((ref_frame_height << AV1_REF_SCALE_SHIFT) + (frame_height >> 1)) / frame_height;
+	scale_factors->is_scaled =
+		(scale_factors->x_scale != AV1_REF_INVALID_SCALE) &&
+		(scale_factors->y_scale != AV1_REF_INVALID_SCALE) &&
+		(scale_factors->x_scale != AV1_REF_NO_SCALE ||
+		 scale_factors->y_scale != AV1_REF_NO_SCALE);
+	scale_factors->x_step =
+		AV1_DIV_ROUND_UP_POW2(scale_factors->x_scale,
+				      AV1_REF_SCALE_SHIFT - AV1_SCALE_SUBPEL_BITS);
+	scale_factors->y_step =
+		AV1_DIV_ROUND_UP_POW2(scale_factors->y_scale,
+				      AV1_REF_SCALE_SHIFT - AV1_SCALE_SUBPEL_BITS);
+}
+
+static unsigned char vdec_av1_slice_get_sign_bias(int a,
+						  int b,
+						  u8 enable_order_hint,
+						  u8 order_hint_bits)
+{
+	int diff = 0;
+	int m = 0;
+	unsigned char result = 0;
+
+	if (!enable_order_hint)
+		return 0;
+
+	diff = a - b;
+	m = 1 << (order_hint_bits - 1);
+	diff = (diff & (m - 1)) - (diff & m);
+
+	if (diff > 0)
+		result = 1;
+
+	return result;
+}
+
+static void vdec_av1_slice_setup_ref(struct vdec_av1_slice_pfc *pfc,
+				     struct v4l2_ctrl_av1_frame *ctrl_fh)
+{
+	struct vdec_av1_slice_vsi *vsi = &pfc->vsi;
+	struct vdec_av1_slice_frame *frame = &vsi->frame;
+	struct vdec_av1_slice_slot *slots = &vsi->slots;
+	struct vdec_av1_slice_uncompressed_header *uh = &frame->uh;
+	struct vdec_av1_slice_seq_header *seq = &frame->seq;
+	struct vdec_av1_slice_frame_info *cur_frame_info =
+		&slots->frame_info[vsi->slot_id];
+	struct vdec_av1_slice_frame_info *frame_info;
+	int i, slot_id;
+
+	if (uh->frame_is_intra)
+		return;
+
+	for (i = 0; i < V4L2_AV1_REFS_PER_FRAME; i++) {
+		int ref_idx = ctrl_fh->ref_frame_idx[i];
+
+		pfc->ref_idx[i] = ctrl_fh->reference_frame_ts[ref_idx];
+		slot_id = frame->ref_frame_map[ref_idx];
+		frame_info = &slots->frame_info[slot_id];
+		if (slot_id == AV1_INVALID_IDX) {
+			mtk_v4l2_err("cannot match reference[%d] 0x%llx\n", i,
+				     ctrl_fh->reference_frame_ts[ref_idx]);
+			frame->order_hints[i] = 0;
+			frame->ref_frame_valid[i] = 0;
+			continue;
+		}
+
+		frame->frame_refs[i].ref_fb_idx = slot_id;
+		vdec_av1_slice_setup_scale_factors(&frame->frame_refs[i],
+						   frame_info, uh);
+		if (!seq->enable_order_hint)
+			frame->ref_frame_sign_bias[i + 1] = 0;
+		else
+			frame->ref_frame_sign_bias[i + 1] =
+				vdec_av1_slice_get_sign_bias(frame_info->order_hint,
+							     uh->order_hint,
+							     seq->enable_order_hint,
+							     seq->order_hint_bits);
+
+		frame->order_hints[i] = ctrl_fh->order_hints[i + 1];
+		cur_frame_info->order_hints[i] = frame->order_hints[i];
+		frame->ref_frame_valid[i] = 1;
+	}
+}
+
+static void vdec_av1_slice_get_previous(struct vdec_av1_slice_vsi *vsi)
+{
+	struct vdec_av1_slice_frame *frame = &vsi->frame;
+
+	if (frame->uh.primary_ref_frame == AV1_PRIMARY_REF_NONE)
+		frame->prev_fb_idx = AV1_INVALID_IDX;
+	else
+		frame->prev_fb_idx = frame->frame_refs[frame->uh.primary_ref_frame].ref_fb_idx;
+}
+
+static inline void vdec_av1_slice_setup_operating_mode(struct vdec_av1_slice_instance *instance,
+						       struct vdec_av1_slice_frame *frame)
+{
+	frame->large_scale_tile = 0;
+}
+
+static int vdec_av1_slice_setup_pfc(struct vdec_av1_slice_instance *instance,
+				    struct vdec_av1_slice_pfc *pfc)
+{
+	struct v4l2_ctrl_av1_frame *ctrl_fh;
+	struct v4l2_ctrl_av1_sequence *ctrl_seq;
+	struct vdec_av1_slice_vsi *vsi = &pfc->vsi;
+	int ret = 0;
+
+	/* frame header */
+	ctrl_fh = (struct v4l2_ctrl_av1_frame *)
+		  vdec_av1_get_ctrl_ptr(instance->ctx,
+					V4L2_CID_STATELESS_AV1_FRAME);
+	if (IS_ERR(ctrl_fh))
+		return PTR_ERR(ctrl_fh);
+
+	ctrl_seq = (struct v4l2_ctrl_av1_sequence *)
+		   vdec_av1_get_ctrl_ptr(instance->ctx,
+					 V4L2_CID_STATELESS_AV1_SEQUENCE);
+	if (IS_ERR(ctrl_seq))
+		return PTR_ERR(ctrl_seq);
+
+	/* setup vsi information */
+	vdec_av1_slice_setup_seq(&vsi->frame.seq, ctrl_seq);
+	vdec_av1_slice_setup_uh(instance, &vsi->frame, ctrl_fh);
+	vdec_av1_slice_setup_operating_mode(instance, &vsi->frame);
+
+	vdec_av1_slice_setup_state(vsi);
+	vdec_av1_slice_setup_slot(instance, vsi, ctrl_fh);
+	vdec_av1_slice_setup_ref(pfc, ctrl_fh);
+	vdec_av1_slice_get_previous(vsi);
+
+	pfc->seq = instance->seq;
+	instance->seq++;
+
+	return ret;
+}
+
+static void vdec_av1_slice_setup_lat_buffer(struct vdec_av1_slice_instance *instance,
+					    struct vdec_av1_slice_vsi *vsi,
+					    struct mtk_vcodec_mem *bs,
+					    struct vdec_lat_buf *lat_buf)
+{
+	struct vdec_av1_slice_work_buffer *work_buffer;
+	int i;
+
+	vsi->bs.dma_addr = bs->dma_addr;
+	vsi->bs.size = bs->size;
+
+	vsi->ube.dma_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr;
+	vsi->ube.size = lat_buf->ctx->msg_queue.wdma_addr.size;
+	vsi->trans.dma_addr = lat_buf->ctx->msg_queue.wdma_wptr_addr;
+	/* used to store trans end */
+	vsi->trans.dma_addr_end = lat_buf->ctx->msg_queue.wdma_rptr_addr;
+	vsi->err_map.dma_addr = lat_buf->wdma_err_addr.dma_addr;
+	vsi->err_map.size = lat_buf->wdma_err_addr.size;
+	vsi->rd_mv.dma_addr = lat_buf->rd_mv_addr.dma_addr;
+	vsi->rd_mv.size = lat_buf->rd_mv_addr.size;
+
+	vsi->row_info.buf = 0;
+	vsi->row_info.size = 0;
+
+	work_buffer = vsi->work_buffer;
+
+	for (i = 0; i < AV1_MAX_FRAME_BUF_COUNT; i++) {
+		work_buffer[i].mv_addr.buf = instance->mv[i].dma_addr;
+		work_buffer[i].mv_addr.size = instance->mv[i].size;
+		work_buffer[i].segid_addr.buf = instance->seg[i].dma_addr;
+		work_buffer[i].segid_addr.size = instance->seg[i].size;
+		work_buffer[i].cdf_addr.buf = instance->cdf[i].dma_addr;
+		work_buffer[i].cdf_addr.size = instance->cdf[i].size;
+	}
+
+	vsi->cdf_tmp.buf = instance->cdf_temp.dma_addr;
+	vsi->cdf_tmp.size = instance->cdf_temp.size;
+
+	vsi->tile.buf = instance->tile.dma_addr;
+	vsi->tile.size = instance->tile.size;
+	memcpy(lat_buf->tile_addr.va, instance->tile.va, 64 * instance->tile_group.num_tiles);
+
+	vsi->cdf_table.buf = instance->cdf_table.dma_addr;
+	vsi->cdf_table.size = instance->cdf_table.size;
+	vsi->iq_table.buf = instance->iq_table.dma_addr;
+	vsi->iq_table.size = instance->iq_table.size;
+}
+
+static void vdec_av1_slice_setup_seg_buffer(struct vdec_av1_slice_instance *instance,
+					    struct vdec_av1_slice_vsi *vsi)
+{
+	struct vdec_av1_slice_uncompressed_header *uh = &vsi->frame.uh;
+	struct mtk_vcodec_mem *buf;
+
+	/* reset segment buffer */
+	if (uh->primary_ref_frame == AV1_PRIMARY_REF_NONE || !uh->seg.segmentation_enabled) {
+		mtk_vcodec_debug(instance, "reset seg %d\n", vsi->slot_id);
+		if (vsi->slot_id != AV1_INVALID_IDX) {
+			buf = &instance->seg[vsi->slot_id];
+			memset(buf->va, 0, buf->size);
+		}
+	}
+}
+
+static void vdec_av1_slice_setup_tile_buffer(struct vdec_av1_slice_instance *instance,
+					     struct vdec_av1_slice_vsi *vsi,
+					     struct mtk_vcodec_mem *bs)
+{
+	struct vdec_av1_slice_tile_group *tile_group = &instance->tile_group;
+	struct vdec_av1_slice_uncompressed_header *uh = &vsi->frame.uh;
+	struct vdec_av1_slice_tile *tile = &uh->tile;
+	u32 tile_num, tile_row, tile_col;
+	u32 allow_update_cdf = 0;
+	u32 sb_boundary_x_m1 = 0, sb_boundary_y_m1 = 0;
+	int tile_info_base;
+	u32 tile_buf_pa;
+	u32 *tile_info_buf = instance->tile.va;
+	u32 pa = (u32)bs->dma_addr;
+
+	if (uh->disable_cdf_update == 0)
+		allow_update_cdf = 1;
+
+	for (tile_num = 0; tile_num < tile_group->num_tiles; tile_num++) {
+		/* each uint32 takes place of 4 bytes */
+		tile_info_base = (AV1_TILE_BUF_SIZE * tile_num) >> 2;
+		tile_row = tile_num / tile->tile_cols;
+		tile_col = tile_num % tile->tile_cols;
+		tile_info_buf[tile_info_base + 0] = (tile_group->tile_size[tile_num] << 3);
+		tile_buf_pa = pa + tile_group->tile_start_offset[tile_num];
+
+		tile_info_buf[tile_info_base + 1] = (tile_buf_pa >> 4) << 4;
+		tile_info_buf[tile_info_base + 2] = (tile_buf_pa % 16) << 3;
+
+		sb_boundary_x_m1 =
+			(tile->mi_col_starts[tile_col + 1] - tile->mi_col_starts[tile_col] - 1) &
+			0x3f;
+		sb_boundary_y_m1 =
+			(tile->mi_row_starts[tile_row + 1] - tile->mi_row_starts[tile_row] - 1) &
+			0x1ff;
+
+		tile_info_buf[tile_info_base + 3] = (sb_boundary_y_m1 << 7) | sb_boundary_x_m1;
+		tile_info_buf[tile_info_base + 4] = ((allow_update_cdf << 18) | (1 << 16));
+
+		if (tile_num == tile->context_update_tile_id &&
+		    uh->disable_frame_end_update_cdf == 0)
+			tile_info_buf[tile_info_base + 4] |= (1 << 17);
+
+		mtk_vcodec_debug(instance, "// tile buf %d pos(%dx%d) offset 0x%x\n",
+				 tile_num, tile_row, tile_col, tile_info_base);
+		mtk_vcodec_debug(instance, "// %08x %08x %08x %08x\n",
+				 tile_info_buf[tile_info_base + 0],
+				 tile_info_buf[tile_info_base + 1],
+				 tile_info_buf[tile_info_base + 2],
+				 tile_info_buf[tile_info_base + 3]);
+		mtk_vcodec_debug(instance, "// %08x %08x %08x %08x\n",
+				 tile_info_buf[tile_info_base + 4],
+				 tile_info_buf[tile_info_base + 5],
+				 tile_info_buf[tile_info_base + 6],
+				 tile_info_buf[tile_info_base + 7]);
+	}
+}
+
+static int vdec_av1_slice_setup_lat(struct vdec_av1_slice_instance *instance,
+				    struct mtk_vcodec_mem *bs,
+				    struct vdec_lat_buf *lat_buf,
+				    struct vdec_av1_slice_pfc *pfc)
+{
+	struct vdec_av1_slice_vsi *vsi = &pfc->vsi;
+	int ret;
+
+	ret = vdec_av1_slice_setup_lat_from_src_buf(instance, vsi, lat_buf);
+	if (ret)
+		return ret;
+
+	ret = vdec_av1_slice_setup_pfc(instance, pfc);
+	if (ret)
+		return ret;
+
+	ret = vdec_av1_slice_setup_tile_group(instance, vsi);
+	if (ret)
+		return ret;
+
+	ret = vdec_av1_slice_alloc_working_buffer(instance, vsi);
+	if (ret)
+		return ret;
+
+	vdec_av1_slice_setup_seg_buffer(instance, vsi);
+	vdec_av1_slice_setup_tile_buffer(instance, vsi, bs);
+	vdec_av1_slice_setup_lat_buffer(instance, vsi, bs, lat_buf);
+
+	return 0;
+}
+
+static int vdec_av1_slice_update_lat(struct vdec_av1_slice_instance *instance,
+				     struct vdec_lat_buf *lat_buf,
+				     struct vdec_av1_slice_pfc *pfc)
+{
+	struct vdec_av1_slice_vsi *vsi;
+
+	vsi = &pfc->vsi;
+	mtk_vcodec_debug(instance, "frame %u LAT CRC 0x%08x, output size is %d\n",
+			 pfc->seq, vsi->state.crc[0], vsi->state.out_size);
+
+	/* buffer full, need to re-decode */
+	if (vsi->state.full) {
+		/* buffer not enough */
+		if (vsi->trans.dma_addr_end - vsi->trans.dma_addr == vsi->ube.size)
+			return -ENOMEM;
+		return -EAGAIN;
+	}
+
+	instance->width = vsi->frame.uh.upscaled_width;
+	instance->height = vsi->frame.uh.frame_height;
+	instance->frame_type = vsi->frame.uh.frame_type;
+
+	return 0;
+}
+
+static int vdec_av1_slice_setup_core_to_dst_buf(struct vdec_av1_slice_instance *instance,
+						struct vdec_lat_buf *lat_buf)
+{
+	struct vb2_v4l2_buffer *dst;
+
+	dst = v4l2_m2m_next_dst_buf(instance->ctx->m2m_ctx);
+	if (!dst)
+		return -EINVAL;
+
+	v4l2_m2m_buf_copy_metadata(&lat_buf->ts_info, dst, true);
+
+	return 0;
+}
+
+static int vdec_av1_slice_setup_core_buffer(struct vdec_av1_slice_instance *instance,
+					    struct vdec_av1_slice_pfc *pfc,
+					    struct vdec_av1_slice_vsi *vsi,
+					    struct vdec_fb *fb,
+					    struct vdec_lat_buf *lat_buf)
+{
+	struct vb2_buffer *vb;
+	struct vb2_queue *vq;
+	int w, h, plane, size;
+	int i;
+
+	plane = instance->ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes;
+	w = vsi->frame.uh.upscaled_width;
+	h = vsi->frame.uh.frame_height;
+	size = ALIGN(w, VCODEC_DEC_ALIGNED_64) * ALIGN(h, VCODEC_DEC_ALIGNED_64);
+
+	/* frame buffer */
+	vsi->fb.y.dma_addr = fb->base_y.dma_addr;
+	if (plane == 1)
+		vsi->fb.c.dma_addr = fb->base_y.dma_addr + size;
+	else
+		vsi->fb.c.dma_addr = fb->base_c.dma_addr;
+
+	/* reference buffers */
+	vq = v4l2_m2m_get_vq(instance->ctx->m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE);
+	if (!vq)
+		return -EINVAL;
+
+	/* get current output buffer */
+	vb = &v4l2_m2m_next_dst_buf(instance->ctx->m2m_ctx)->vb2_buf;
+	if (!vb)
+		return -EINVAL;
+
+	/* get buffer address from vb2buf */
+	for (i = 0; i < V4L2_AV1_REFS_PER_FRAME; i++) {
+		struct vdec_av1_slice_fb *vref = &vsi->ref[i];
+
+		vb = vb2_find_buffer(vq, pfc->ref_idx[i]);
+		if (!vb) {
+			memset(vref, 0, sizeof(*vref));
+			continue;
+		}
+
+		vref->y.dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
+		if (plane == 1)
+			vref->c.dma_addr = vref->y.dma_addr + size;
+		else
+			vref->c.dma_addr = vb2_dma_contig_plane_dma_addr(vb, 1);
+	}
+	vsi->tile.dma_addr = lat_buf->tile_addr.dma_addr;
+	vsi->tile.size = lat_buf->tile_addr.size;
+
+	return 0;
+}
+
+static int vdec_av1_slice_setup_core(struct vdec_av1_slice_instance *instance,
+				     struct vdec_fb *fb,
+				     struct vdec_lat_buf *lat_buf,
+				     struct vdec_av1_slice_pfc *pfc)
+{
+	struct vdec_av1_slice_vsi *vsi = &pfc->vsi;
+	int ret;
+
+	ret = vdec_av1_slice_setup_core_to_dst_buf(instance, lat_buf);
+	if (ret)
+		return ret;
+
+	ret = vdec_av1_slice_setup_core_buffer(instance, pfc, vsi, fb, lat_buf);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int vdec_av1_slice_update_core(struct vdec_av1_slice_instance *instance,
+				      struct vdec_lat_buf *lat_buf,
+				      struct vdec_av1_slice_pfc *pfc)
+{
+	struct vdec_av1_slice_vsi *vsi = instance->core_vsi;
+
+	mtk_vcodec_debug(instance, "frame %u Y_CRC %08x %08x %08x %08x\n",
+			 pfc->seq, vsi->state.crc[0], vsi->state.crc[1],
+			 vsi->state.crc[2], vsi->state.crc[3]);
+	mtk_vcodec_debug(instance, "frame %u C_CRC %08x %08x %08x %08x\n",
+			 pfc->seq, vsi->state.crc[8], vsi->state.crc[9],
+			 vsi->state.crc[10], vsi->state.crc[11]);
+
+	return 0;
+}
+
+static int vdec_av1_slice_init(struct mtk_vcodec_ctx *ctx)
+{
+	struct vdec_av1_slice_instance *instance;
+	struct vdec_av1_slice_init_vsi *vsi;
+	int ret;
+
+	instance = kzalloc(sizeof(*instance), GFP_KERNEL);
+	if (!instance)
+		return -ENOMEM;
+
+	instance->ctx = ctx;
+	instance->vpu.id = SCP_IPI_VDEC_LAT;
+	instance->vpu.core_id = SCP_IPI_VDEC_CORE;
+	instance->vpu.ctx = ctx;
+	instance->vpu.codec_type = ctx->current_codec;
+
+	ret = vpu_dec_init(&instance->vpu);
+	if (ret) {
+		mtk_vcodec_err(instance, "failed to init vpu dec, ret %d\n", ret);
+		goto error_vpu_init;
+	}
+
+	/* init vsi and global flags */
+	vsi = instance->vpu.vsi;
+	if (!vsi) {
+		mtk_vcodec_err(instance, "failed to get AV1 vsi\n");
+		ret = -EINVAL;
+		goto error_vsi;
+	}
+	instance->init_vsi = vsi;
+	instance->core_vsi = mtk_vcodec_fw_map_dm_addr(ctx->dev->fw_handler, (u32)vsi->core_vsi);
+
+	if (!instance->core_vsi) {
+		mtk_vcodec_err(instance, "failed to get AV1 core vsi\n");
+		ret = -EINVAL;
+		goto error_vsi;
+	}
+
+	if (vsi->vsi_size != sizeof(struct vdec_av1_slice_vsi))
+		mtk_vcodec_err(instance, "remote vsi size 0x%x mismatch! expected: 0x%zx\n",
+			       vsi->vsi_size, sizeof(struct vdec_av1_slice_vsi));
+
+	instance->irq_enabled = 1;
+	instance->inneracing_mode = IS_VDEC_INNER_RACING(instance->ctx->dev->dec_capability);
+
+	mtk_vcodec_debug(instance, "vsi 0x%p core_vsi 0x%llx 0x%p, inneracing_mode %d\n",
+			 vsi, vsi->core_vsi, instance->core_vsi, instance->inneracing_mode);
+
+	ret = vdec_av1_slice_init_cdf_table(instance);
+	if (ret)
+		goto error_vsi;
+
+	ret = vdec_av1_slice_init_iq_table(instance);
+	if (ret)
+		goto error_vsi;
+
+	ctx->drv_handle = instance;
+
+	return 0;
+error_vsi:
+	vpu_dec_deinit(&instance->vpu);
+error_vpu_init:
+	kfree(instance);
+
+	return ret;
+}
+
+static void vdec_av1_slice_deinit(void *h_vdec)
+{
+	struct vdec_av1_slice_instance *instance = h_vdec;
+
+	if (!instance)
+		return;
+	mtk_vcodec_debug(instance, "h_vdec 0x%p\n", h_vdec);
+	vpu_dec_deinit(&instance->vpu);
+	vdec_av1_slice_free_working_buffer(instance);
+	vdec_msg_queue_deinit(&instance->ctx->msg_queue, instance->ctx);
+	kfree(instance);
+}
+
+static int vdec_av1_slice_flush(void *h_vdec, struct mtk_vcodec_mem *bs,
+				struct vdec_fb *fb, bool *res_chg)
+{
+	struct vdec_av1_slice_instance *instance = h_vdec;
+	int i;
+
+	mtk_vcodec_debug(instance, "flush ...\n");
+
+	vdec_msg_queue_wait_lat_buf_full(&instance->ctx->msg_queue);
+
+	for (i = 0; i < AV1_MAX_FRAME_BUF_COUNT; i++)
+		vdec_av1_slice_clear_fb(&instance->slots.frame_info[i]);
+
+	return vpu_dec_reset(&instance->vpu);
+}
+
+static void vdec_av1_slice_get_pic_info(struct vdec_av1_slice_instance *instance)
+{
+	struct mtk_vcodec_ctx *ctx = instance->ctx;
+	u32 data[3];
+
+	mtk_vcodec_debug(instance, "w %u h %u\n", ctx->picinfo.pic_w, ctx->picinfo.pic_h);
+
+	data[0] = ctx->picinfo.pic_w;
+	data[1] = ctx->picinfo.pic_h;
+	data[2] = ctx->capture_fourcc;
+	vpu_dec_get_param(&instance->vpu, data, 3, GET_PARAM_PIC_INFO);
+
+	ctx->picinfo.buf_w = ALIGN(ctx->picinfo.pic_w, VCODEC_DEC_ALIGNED_64);
+	ctx->picinfo.buf_h = ALIGN(ctx->picinfo.pic_h, VCODEC_DEC_ALIGNED_64);
+	ctx->picinfo.fb_sz[0] = instance->vpu.fb_sz[0];
+	ctx->picinfo.fb_sz[1] = instance->vpu.fb_sz[1];
+}
+
+static inline void vdec_av1_slice_get_dpb_size(struct vdec_av1_slice_instance *instance,
+					       u32 *dpb_sz)
+{
+	/* refer av1 specification */
+	*dpb_sz = V4L2_AV1_TOTAL_REFS_PER_FRAME + 1;
+}
+
+static void vdec_av1_slice_get_crop_info(struct vdec_av1_slice_instance *instance,
+					 struct v4l2_rect *cr)
+{
+	struct mtk_vcodec_ctx *ctx = instance->ctx;
+
+	cr->left = 0;
+	cr->top = 0;
+	cr->width = ctx->picinfo.pic_w;
+	cr->height = ctx->picinfo.pic_h;
+
+	mtk_vcodec_debug(instance, "l=%d, t=%d, w=%d, h=%d\n",
+			 cr->left, cr->top, cr->width, cr->height);
+}
+
+static int vdec_av1_slice_get_param(void *h_vdec, enum vdec_get_param_type type, void *out)
+{
+	struct vdec_av1_slice_instance *instance = h_vdec;
+
+	switch (type) {
+	case GET_PARAM_PIC_INFO:
+		vdec_av1_slice_get_pic_info(instance);
+		break;
+	case GET_PARAM_DPB_SIZE:
+		vdec_av1_slice_get_dpb_size(instance, out);
+		break;
+	case GET_PARAM_CROP_INFO:
+		vdec_av1_slice_get_crop_info(instance, out);
+		break;
+	default:
+		mtk_vcodec_err(instance, "invalid get parameter type=%d\n", type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int vdec_av1_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+				     struct vdec_fb *fb, bool *res_chg)
+{
+	struct vdec_av1_slice_instance *instance = h_vdec;
+	struct vdec_lat_buf *lat_buf;
+	struct vdec_av1_slice_pfc *pfc;
+	struct vdec_av1_slice_vsi *vsi;
+	struct mtk_vcodec_ctx *ctx;
+	int ret;
+
+	if (!instance || !instance->ctx)
+		return -EINVAL;
+
+	ctx = instance->ctx;
+	/* init msgQ for the first time */
+	if (vdec_msg_queue_init(&ctx->msg_queue, ctx,
+				vdec_av1_slice_core_decode, sizeof(*pfc))) {
+		mtk_vcodec_err(instance, "failed to init AV1 msg queue\n");
+		return -ENOMEM;
+	}
+
+	/* bs NULL means flush decoder */
+	if (!bs)
+		return vdec_av1_slice_flush(h_vdec, bs, fb, res_chg);
+
+	lat_buf = vdec_msg_queue_dqbuf(&ctx->msg_queue.lat_ctx);
+	if (!lat_buf) {
+		mtk_vcodec_err(instance, "failed to get AV1 lat buf\n");
+		return -EAGAIN;
+	}
+	pfc = (struct vdec_av1_slice_pfc *)lat_buf->private_data;
+	if (!pfc) {
+		ret = -EINVAL;
+		goto err_free_fb_out;
+	}
+	vsi = &pfc->vsi;
+
+	ret = vdec_av1_slice_setup_lat(instance, bs, lat_buf, pfc);
+	if (ret) {
+		mtk_vcodec_err(instance, "failed to setup AV1 lat ret %d\n", ret);
+		goto err_free_fb_out;
+	}
+
+	vdec_av1_slice_vsi_to_remote(vsi, instance->vsi);
+	ret = vpu_dec_start(&instance->vpu, NULL, 0);
+	if (ret) {
+		mtk_vcodec_err(instance, "failed to dec AV1 ret %d\n", ret);
+		goto err_free_fb_out;
+	}
+	if (instance->inneracing_mode)
+		vdec_msg_queue_qbuf(&ctx->msg_queue.core_ctx, lat_buf);
+
+	if (instance->irq_enabled) {
+		ret = mtk_vcodec_wait_for_done_ctx(ctx, MTK_INST_IRQ_RECEIVED,
+						   WAIT_INTR_TIMEOUT_MS,
+						   MTK_VDEC_LAT0);
+		/* update remote vsi if decode timeout */
+		if (ret) {
+			mtk_vcodec_err(instance, "AV1 Frame %d decode timeout %d\n", pfc->seq, ret);
+			WRITE_ONCE(instance->vsi->state.timeout, 1);
+		}
+		vpu_dec_end(&instance->vpu);
+	}
+
+	vdec_av1_slice_vsi_from_remote(vsi, instance->vsi);
+	ret = vdec_av1_slice_update_lat(instance, lat_buf, pfc);
+
+	/* LAT trans full, re-decode */
+	if (ret == -EAGAIN) {
+		mtk_vcodec_err(instance, "AV1 Frame %d trans full\n", pfc->seq);
+		if (!instance->inneracing_mode)
+			vdec_msg_queue_qbuf(&ctx->msg_queue.lat_ctx, lat_buf);
+		return 0;
+	}
+
+	/* LAT trans full, no more UBE or decode timeout */
+	if (ret == -ENOMEM || vsi->state.timeout) {
+		mtk_vcodec_err(instance, "AV1 Frame %d insufficient buffer or timeout\n", pfc->seq);
+		if (!instance->inneracing_mode)
+			vdec_msg_queue_qbuf(&ctx->msg_queue.lat_ctx, lat_buf);
+		return -EBUSY;
+	}
+	vsi->trans.dma_addr_end += ctx->msg_queue.wdma_addr.dma_addr;
+	mtk_vcodec_debug(instance, "lat dma 1 0x%pad 0x%pad\n",
+			 &pfc->vsi.trans.dma_addr, &pfc->vsi.trans.dma_addr_end);
+
+	vdec_msg_queue_update_ube_wptr(&ctx->msg_queue, vsi->trans.dma_addr_end);
+
+	if (!instance->inneracing_mode)
+		vdec_msg_queue_qbuf(&ctx->msg_queue.core_ctx, lat_buf);
+	memcpy(&instance->slots, &vsi->slots, sizeof(instance->slots));
+
+	return 0;
+
+err_free_fb_out:
+	vdec_msg_queue_qbuf(&ctx->msg_queue.lat_ctx, lat_buf);
+
+	if (pfc)
+		mtk_vcodec_err(instance, "slice dec number: %d err: %d", pfc->seq, ret);
+
+	return ret;
+}
+
+static int vdec_av1_slice_core_decode(struct vdec_lat_buf *lat_buf)
+{
+	struct vdec_av1_slice_instance *instance;
+	struct vdec_av1_slice_pfc *pfc;
+	struct mtk_vcodec_ctx *ctx = NULL;
+	struct vdec_fb *fb = NULL;
+	int ret = -EINVAL;
+
+	if (!lat_buf)
+		return -EINVAL;
+
+	pfc = lat_buf->private_data;
+	ctx = lat_buf->ctx;
+	if (!pfc || !ctx)
+		return -EINVAL;
+
+	instance = ctx->drv_handle;
+	if (!instance)
+		goto err;
+
+	fb = ctx->dev->vdec_pdata->get_cap_buffer(ctx);
+	if (!fb) {
+		ret = -EBUSY;
+		goto err;
+	}
+
+	ret = vdec_av1_slice_setup_core(instance, fb, lat_buf, pfc);
+	if (ret) {
+		mtk_vcodec_err(instance, "vdec_av1_slice_setup_core\n");
+		goto err;
+	}
+	vdec_av1_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;
+	}
+
+	if (instance->irq_enabled) {
+		ret = mtk_vcodec_wait_for_done_ctx(ctx, MTK_INST_IRQ_RECEIVED,
+						   WAIT_INTR_TIMEOUT_MS,
+						   MTK_VDEC_CORE);
+		/* update remote vsi if decode timeout */
+		if (ret) {
+			mtk_vcodec_err(instance, "AV1 frame %d core timeout\n", pfc->seq);
+			WRITE_ONCE(instance->vsi->state.timeout, 1);
+		}
+		vpu_dec_core_end(&instance->vpu);
+	}
+
+	ret = vdec_av1_slice_update_core(instance, lat_buf, pfc);
+	if (ret) {
+		mtk_vcodec_err(instance, "vdec_av1_slice_update_core\n");
+		goto err;
+	}
+
+	mtk_vcodec_debug(instance, "core dma_addr_end 0x%pad\n",
+			 &instance->core_vsi->trans.dma_addr_end);
+	vdec_msg_queue_update_ube_rptr(&ctx->msg_queue, instance->core_vsi->trans.dma_addr_end);
+
+	ctx->dev->vdec_pdata->cap_to_disp(ctx, 0, lat_buf->src_buf_req);
+
+	return 0;
+
+err:
+	/* always update read pointer */
+	vdec_msg_queue_update_ube_rptr(&ctx->msg_queue, pfc->vsi.trans.dma_addr_end);
+
+	if (fb)
+		ctx->dev->vdec_pdata->cap_to_disp(ctx, 1, lat_buf->src_buf_req);
+
+	return ret;
+}
+
+const struct vdec_common_if vdec_av1_slice_lat_if = {
+	.init		= vdec_av1_slice_init,
+	.decode		= vdec_av1_slice_lat_decode,
+	.get_param	= vdec_av1_slice_get_param,
+	.deinit		= vdec_av1_slice_deinit,
+};
diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c
index 999ce7ee5fdc..a7e8e3257b7f 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c
+++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_h264_req_multi_if.c
@@ -596,7 +596,7 @@ static int vdec_h264_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 
 	lat_buf = vdec_msg_queue_dqbuf(&inst->ctx->msg_queue.lat_ctx);
 	if (!lat_buf) {
-		mtk_vcodec_err(inst, "failed to get lat buffer");
+		mtk_vcodec_debug(inst, "failed to get lat buffer");
 		return -EAGAIN;
 	}
 	share_info = lat_buf->private_data;
@@ -672,7 +672,7 @@ static int vdec_h264_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 	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);
+		vdec_msg_queue_qbuf(&inst->ctx->msg_queue.core_ctx, lat_buf);
 	}
 
 	/* wait decoder done interrupt */
@@ -698,7 +698,7 @@ static int vdec_h264_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 	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);
+		vdec_msg_queue_qbuf(&inst->ctx->msg_queue.core_ctx, lat_buf);
 	}
 	mtk_vcodec_debug(inst, "dec num: %d lat crc: 0x%x 0x%x 0x%x", inst->slice_dec_num,
 			 inst->vsi->dec.crc[0], inst->vsi->dec.crc[1], inst->vsi->dec.crc[2]);
diff --git a/drivers/media/platform/mediatek/vcodec/vdec/vdec_hevc_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/vdec/vdec_hevc_req_multi_if.c
new file mode 100644
index 000000000000..1e6ab138b0bb
--- /dev/null
+++ b/drivers/media/platform/mediatek/vcodec/vdec/vdec_hevc_req_multi_if.c
@@ -0,0 +1,1097 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2023 MediaTek Inc.
+ * Author: Yunfei Dong <yunfei.dong@mediatek.com>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "../mtk_vcodec_util.h"
+#include "../mtk_vcodec_dec.h"
+#include "../mtk_vcodec_intr.h"
+#include "../vdec_drv_base.h"
+#include "../vdec_drv_if.h"
+#include "../vdec_vpu_if.h"
+
+/* the size used to store hevc wrap information */
+#define VDEC_HEVC_WRAP_SZ (532 * SZ_1K)
+
+#define HEVC_MAX_MV_NUM 32
+
+/* get used parameters for sps/pps */
+#define GET_HEVC_VDEC_FLAG(cond, flag) \
+	{ dst_param->cond = ((src_param->flags & (flag)) ? (1) : (0)); }
+#define GET_HEVC_VDEC_PARAM(param) \
+	{ dst_param->param = src_param->param; }
+
+/**
+ * enum vdec_hevc_core_dec_err_type  - core decode error type
+ *
+ * @TRANS_BUFFER_FULL: trans buffer is full
+ * @SLICE_HEADER_FULL: slice header buffer is full
+ */
+enum vdec_hevc_core_dec_err_type {
+	TRANS_BUFFER_FULL = 1,
+	SLICE_HEADER_FULL,
+};
+
+/**
+ * struct mtk_hevc_dpb_info  - hevc dpb information
+ *
+ * @y_dma_addr:     Y plane physical address
+ * @c_dma_addr:     CbCr plane physical address
+ * @reference_flag: reference picture flag (short/long term reference picture)
+ * @field:          field picture flag
+ */
+struct mtk_hevc_dpb_info {
+	dma_addr_t y_dma_addr;
+	dma_addr_t c_dma_addr;
+	int reference_flag;
+	int field;
+};
+
+/*
+ * struct mtk_hevc_sps_param  - parameters for sps
+ */
+struct mtk_hevc_sps_param {
+	unsigned char video_parameter_set_id;
+	unsigned char seq_parameter_set_id;
+	unsigned short pic_width_in_luma_samples;
+	unsigned short pic_height_in_luma_samples;
+	unsigned char bit_depth_luma_minus8;
+	unsigned char bit_depth_chroma_minus8;
+	unsigned char log2_max_pic_order_cnt_lsb_minus4;
+	unsigned char sps_max_dec_pic_buffering_minus1;
+	unsigned char sps_max_num_reorder_pics;
+	unsigned char sps_max_latency_increase_plus1;
+	unsigned char log2_min_luma_coding_block_size_minus3;
+	unsigned char log2_diff_max_min_luma_coding_block_size;
+	unsigned char log2_min_luma_transform_block_size_minus2;
+	unsigned char log2_diff_max_min_luma_transform_block_size;
+	unsigned char max_transform_hierarchy_depth_inter;
+	unsigned char max_transform_hierarchy_depth_intra;
+	unsigned char pcm_sample_bit_depth_luma_minus1;
+	unsigned char pcm_sample_bit_depth_chroma_minus1;
+	unsigned char log2_min_pcm_luma_coding_block_size_minus3;
+	unsigned char log2_diff_max_min_pcm_luma_coding_block_size;
+	unsigned char num_short_term_ref_pic_sets;
+	unsigned char num_long_term_ref_pics_sps;
+	unsigned char chroma_format_idc;
+	unsigned char sps_max_sub_layers_minus1;
+	unsigned char separate_colour_plane;
+	unsigned char scaling_list_enabled;
+	unsigned char amp_enabled;
+	unsigned char sample_adaptive_offset;
+	unsigned char pcm_enabled;
+	unsigned char pcm_loop_filter_disabled;
+	unsigned char long_term_ref_pics_enabled;
+	unsigned char sps_temporal_mvp_enabled;
+	unsigned char strong_intra_smoothing_enabled;
+	unsigned char reserved[5];
+};
+
+/*
+ * struct mtk_hevc_pps_param  - parameters for pps
+ */
+struct mtk_hevc_pps_param {
+	unsigned char pic_parameter_set_id;
+	unsigned char num_extra_slice_header_bits;
+	unsigned char num_ref_idx_l0_default_active_minus1;
+	unsigned char num_ref_idx_l1_default_active_minus1;
+	char init_qp_minus26;
+	unsigned char diff_cu_qp_delta_depth;
+	char pps_cb_qp_offset;
+	char pps_cr_qp_offset;
+	unsigned char num_tile_columns_minus1;
+	unsigned char num_tile_rows_minus1;
+	unsigned char column_width_minus1[20];
+	unsigned char row_height_minus1[22];
+	char pps_beta_offset_div2;
+	char pps_tc_offset_div2;
+	unsigned char log2_parallel_merge_level_minus2;
+	char dependent_slice_segment_enabled;
+	char output_flag_present;
+	char sign_data_hiding_enabled;
+	char cabac_init_present;
+	char constrained_intra_pred;
+	char transform_skip_enabled;
+	char cu_qp_delta_enabled;
+	char pps_slice_chroma_qp_offsets_present;
+	char weighted_pred;
+	char weighted_bipred;
+	char transquant_bypass_enabled;
+	char pps_flag_tiles_enabled;
+	char entropy_coding_sync_enabled;
+	char loop_filter_across_tiles_enabled;
+	char pps_loop_filter_across_slices_enabled;
+	char deblocking_filter_override_enabled;
+	char pps_disable_deflocking_filter;
+	char lists_modification_present;
+	char slice_segment_header_extersion_present;
+	char deblocking_filter_control_present;
+	char uniform_spacing;
+	char reserved[6];
+};
+
+/*
+ * struct mtk_hevc_slice_header_param  - parameters for slice header
+ */
+struct mtk_hevc_slice_header_param {
+	unsigned int	slice_type;
+	unsigned int	num_active_ref_layer_pics;
+	int		slice_qp;
+	int		slice_qp_delta_cb;
+	int		slice_qp_delta_cr;
+	int		num_ref_idx[3];
+	unsigned int	col_ref_idx;
+	unsigned int	five_minus_max_num_merge_cand;
+	int		slice_deblocking_filter_beta_offset_div2;
+	int		slice_deblocking_filter_tc_offset_div2;
+	unsigned char	sao_enable_flag;
+	unsigned char	sao_enable_flag_chroma;
+	unsigned char	cabac_init_flag;
+	unsigned char	slice_tmvp_flags_present;
+	unsigned char	col_from_l0_flag;
+	unsigned char	mvd_l1_zero_flag;
+	unsigned char	slice_loop_filter_across_slices_enabled_flag;
+	unsigned char	deblocking_filter_disable_flag;
+	unsigned int	slice_reg0;
+	unsigned int	slice_reg1;
+	unsigned int	slice_reg2;
+	unsigned int	num_rps_curr_temp_list;
+	unsigned int	ref_list_mode;
+	int		str_num_delta_pocs;
+	int		str_num_negtive_pos_pics;
+	int		num_long_term;
+	int		num_long_term_sps;
+	unsigned int	max_cu_width;
+	unsigned int	max_cu_height;
+	unsigned int	num_entry_point_offsets;
+	unsigned int    last_lcu_x_in_tile[17];
+	unsigned int    last_lcu_y_in_tile[17];
+	unsigned char   nal_unit_type;
+};
+
+/*
+ * struct slice_api_hevc_scaling_matrix  - parameters for scaling list
+ */
+struct slice_api_hevc_scaling_matrix {
+	unsigned char scaling_list_4x4[6][16];
+	unsigned char scaling_list_8x8[6][64];
+	unsigned char scaling_list_16x16[6][64];
+	unsigned char scaling_list_32x32[2][64];
+	unsigned char scaling_list_dc_coef_16x16[6];
+	unsigned char scaling_list_dc_coef_32x32[2];
+};
+
+/*
+ * struct slice_hevc_dpb_entry  - each dpb information
+ */
+struct slice_hevc_dpb_entry {
+	u64 timestamp;
+	unsigned char flags;
+	unsigned char field_pic;
+	int pic_order_cnt_val;
+};
+
+/*
+ * struct slice_api_hevc_decode_param - parameters for decode.
+ */
+struct slice_api_hevc_decode_param {
+	struct slice_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	int pic_order_cnt_val;
+	unsigned short short_term_ref_pic_set_size;
+	unsigned short long_term_ref_pic_set_size;
+	unsigned char num_active_dpb_entries;
+	unsigned char num_poc_st_curr_before;
+	unsigned char num_poc_st_curr_after;
+	unsigned char num_poc_lt_curr;
+	unsigned char poc_st_curr_before[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	unsigned char poc_st_curr_after[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	unsigned char poc_lt_curr[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+	unsigned char num_delta_pocs_of_ref_rps_idx;
+	int flags;
+};
+
+/**
+ * struct hevc_fb - hevc decode frame buffer information
+ *
+ * @vdec_fb_va: virtual address of struct vdec_fb
+ * @y_fb_dma:   dma address of Y frame buffer (luma)
+ * @c_fb_dma:   dma address of C frame buffer (chroma)
+ * @poc:        picture order count of frame buffer
+ * @reserved:   for 8 bytes alignment
+ */
+struct hevc_fb {
+	u64 vdec_fb_va;
+	u64 y_fb_dma;
+	u64 c_fb_dma;
+	s32 poc;
+	u32 reserved;
+};
+
+/**
+ * struct vdec_hevc_slice_lat_dec_param  - parameters for decode current frame
+ *
+ * @sps:            hevc sps syntax parameters
+ * @pps:            hevc pps syntax parameters
+ * @slice_header:   hevc slice header syntax parameters
+ * @scaling_matrix: hevc scaling list parameters
+ * @decode_params:  decoder parameters of each frame used for hardware decode
+ * @hevc_dpb_info:  dpb reference list
+ */
+struct vdec_hevc_slice_lat_dec_param {
+	struct mtk_hevc_sps_param sps;
+	struct mtk_hevc_pps_param pps;
+	struct mtk_hevc_slice_header_param slice_header;
+	struct slice_api_hevc_scaling_matrix scaling_matrix;
+	struct slice_api_hevc_decode_param decode_params;
+	struct mtk_hevc_dpb_info hevc_dpb_info[V4L2_HEVC_DPB_ENTRIES_NUM_MAX];
+};
+
+/**
+ * struct vdec_hevc_slice_info - decode information
+ *
+ * @wdma_end_addr_offset: wdma end address offset
+ * @timeout:              Decode timeout: 1 timeout, 0 no timeount
+ * @vdec_fb_va:           VDEC frame buffer struct virtual address
+ * @crc:                  Used to check whether hardware's status is right
+ */
+struct vdec_hevc_slice_info {
+	u64 wdma_end_addr_offset;
+	u64 timeout;
+	u64 vdec_fb_va;
+	u32 crc[8];
+};
+
+/*
+ * struct vdec_hevc_slice_mem - memory address and size
+ */
+struct vdec_hevc_slice_mem {
+	union {
+		u64 buf;
+		dma_addr_t dma_addr;
+	};
+	union {
+		size_t size;
+		dma_addr_t dma_addr_end;
+		u64 padding;
+	};
+};
+
+/**
+ * struct vdec_hevc_slice_fb - frame buffer for decoding
+ * @y:  current y buffer address info
+ * @c:  current c buffer address info
+ */
+struct vdec_hevc_slice_fb {
+	struct vdec_hevc_slice_mem y;
+	struct vdec_hevc_slice_mem c;
+};
+
+/**
+ * struct vdec_hevc_slice_vsi - shared memory for decode information exchange
+ *        between SCP and Host.
+ *
+ * @bs:                input buffer info
+ *
+ * @ube:               ube buffer
+ * @trans:             transcoded buffer
+ * @err_map:           err map buffer
+ * @slice_bc:          slice bc buffer
+ * @wrap:              temp buffer
+ *
+ * @fb:                current y/c buffer
+ * @mv_buf_dma:        HW working motion vector buffer
+ * @dec:               decode information (AP-R, VPU-W)
+ * @hevc_slice_params: decode parameters for hw used
+ */
+struct vdec_hevc_slice_vsi {
+	/* used in LAT stage */
+	struct vdec_hevc_slice_mem bs;
+
+	struct vdec_hevc_slice_mem ube;
+	struct vdec_hevc_slice_mem trans;
+	struct vdec_hevc_slice_mem err_map;
+	struct vdec_hevc_slice_mem slice_bc;
+	struct vdec_hevc_slice_mem wrap;
+
+	struct vdec_hevc_slice_fb fb;
+	struct vdec_hevc_slice_mem mv_buf_dma[HEVC_MAX_MV_NUM];
+	struct vdec_hevc_slice_info dec;
+	struct vdec_hevc_slice_lat_dec_param hevc_slice_params;
+};
+
+/**
+ * struct vdec_hevc_slice_share_info - shared information used to exchange
+ *                                     message between lat and core
+ *
+ * @sps:               sequence header information from user space
+ * @dec_params:        decoder params from user space
+ * @hevc_slice_params: decoder params used for hardware
+ * @trans:             trans buffer dma address
+ */
+struct vdec_hevc_slice_share_info {
+	struct v4l2_ctrl_hevc_sps sps;
+	struct v4l2_ctrl_hevc_decode_params dec_params;
+	struct vdec_hevc_slice_lat_dec_param hevc_slice_params;
+	struct vdec_hevc_slice_mem trans;
+};
+
+/**
+ * struct vdec_hevc_slice_inst - hevc decoder instance
+ *
+ * @slice_dec_num:      how many picture be decoded
+ * @ctx:                point to mtk_vcodec_ctx
+ * @mv_buf:             HW working motion vector buffer
+ * @vpu:                VPU instance
+ * @vsi:                vsi used for lat
+ * @vsi_core:           vsi used for core
+ * @wrap_addr:          wrap address used for hevc
+ *
+ * @hevc_slice_param:   the parameters that hardware use to decode
+ *
+ * @resolution_changed: resolution changed
+ * @realloc_mv_buf:     reallocate mv buffer
+ * @cap_num_planes:     number of capture queue plane
+ */
+struct vdec_hevc_slice_inst {
+	unsigned int slice_dec_num;
+	struct mtk_vcodec_ctx *ctx;
+	struct mtk_vcodec_mem mv_buf[HEVC_MAX_MV_NUM];
+	struct vdec_vpu_inst vpu;
+	struct vdec_hevc_slice_vsi *vsi;
+	struct vdec_hevc_slice_vsi *vsi_core;
+	struct mtk_vcodec_mem wrap_addr;
+
+	struct vdec_hevc_slice_lat_dec_param hevc_slice_param;
+
+	unsigned int resolution_changed;
+	unsigned int realloc_mv_buf;
+	unsigned int cap_num_planes;
+};
+
+static unsigned int vdec_hevc_get_mv_buf_size(unsigned int width, unsigned int height)
+{
+	const unsigned int unit_size = (width / 16) * (height / 16) + 8;
+
+	return 64 * unit_size;
+}
+
+static void *vdec_hevc_get_ctrl_ptr(struct mtk_vcodec_ctx *ctx, int id)
+{
+	struct v4l2_ctrl *ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, id);
+
+	if (!ctrl)
+		return ERR_PTR(-EINVAL);
+
+	return ctrl->p_cur.p;
+}
+
+static void vdec_hevc_fill_dpb_info(struct mtk_vcodec_ctx *ctx,
+				    struct slice_api_hevc_decode_param *decode_params,
+				    struct mtk_hevc_dpb_info *hevc_dpb_info)
+{
+	const struct slice_hevc_dpb_entry *dpb;
+	struct vb2_queue *vq;
+	struct vb2_buffer *vb;
+	int index;
+
+	vq = v4l2_m2m_get_vq(ctx->m2m_ctx, V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE);
+	for (index = 0; index < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; index++) {
+		dpb = &decode_params->dpb[index];
+		if (index >= decode_params->num_active_dpb_entries)
+			continue;
+
+		vb = vb2_find_buffer(vq, dpb->timestamp);
+		if (!vb) {
+			dev_err(&ctx->dev->plat_dev->dev,
+				"Reference invalid: dpb_index(%d) timestamp(%lld)",
+				index, dpb->timestamp);
+			continue;
+		}
+
+		hevc_dpb_info[index].field = dpb->field_pic;
+
+		hevc_dpb_info[index].y_dma_addr = vb2_dma_contig_plane_dma_addr(vb, 0);
+		if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2)
+			hevc_dpb_info[index].c_dma_addr = vb2_dma_contig_plane_dma_addr(vb, 1);
+		else
+			hevc_dpb_info[index].c_dma_addr =
+				hevc_dpb_info[index].y_dma_addr + ctx->picinfo.fb_sz[0];
+	}
+}
+
+static void vdec_hevc_copy_sps_params(struct mtk_hevc_sps_param *dst_param,
+				      const struct v4l2_ctrl_hevc_sps *src_param)
+{
+	GET_HEVC_VDEC_PARAM(video_parameter_set_id);
+	GET_HEVC_VDEC_PARAM(seq_parameter_set_id);
+	GET_HEVC_VDEC_PARAM(pic_width_in_luma_samples);
+	GET_HEVC_VDEC_PARAM(pic_height_in_luma_samples);
+	GET_HEVC_VDEC_PARAM(bit_depth_luma_minus8);
+	GET_HEVC_VDEC_PARAM(bit_depth_chroma_minus8);
+	GET_HEVC_VDEC_PARAM(log2_max_pic_order_cnt_lsb_minus4);
+	GET_HEVC_VDEC_PARAM(sps_max_dec_pic_buffering_minus1);
+	GET_HEVC_VDEC_PARAM(sps_max_num_reorder_pics);
+	GET_HEVC_VDEC_PARAM(sps_max_latency_increase_plus1);
+	GET_HEVC_VDEC_PARAM(log2_min_luma_coding_block_size_minus3);
+	GET_HEVC_VDEC_PARAM(log2_diff_max_min_luma_coding_block_size);
+	GET_HEVC_VDEC_PARAM(log2_min_luma_transform_block_size_minus2);
+	GET_HEVC_VDEC_PARAM(log2_diff_max_min_luma_transform_block_size);
+	GET_HEVC_VDEC_PARAM(max_transform_hierarchy_depth_inter);
+	GET_HEVC_VDEC_PARAM(max_transform_hierarchy_depth_intra);
+	GET_HEVC_VDEC_PARAM(pcm_sample_bit_depth_luma_minus1);
+	GET_HEVC_VDEC_PARAM(pcm_sample_bit_depth_chroma_minus1);
+	GET_HEVC_VDEC_PARAM(log2_min_pcm_luma_coding_block_size_minus3);
+	GET_HEVC_VDEC_PARAM(log2_diff_max_min_pcm_luma_coding_block_size);
+	GET_HEVC_VDEC_PARAM(num_short_term_ref_pic_sets);
+	GET_HEVC_VDEC_PARAM(num_long_term_ref_pics_sps);
+	GET_HEVC_VDEC_PARAM(chroma_format_idc);
+	GET_HEVC_VDEC_PARAM(sps_max_sub_layers_minus1);
+
+	GET_HEVC_VDEC_FLAG(separate_colour_plane,
+			   V4L2_HEVC_SPS_FLAG_SEPARATE_COLOUR_PLANE);
+	GET_HEVC_VDEC_FLAG(scaling_list_enabled,
+			   V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED);
+	GET_HEVC_VDEC_FLAG(amp_enabled,
+			   V4L2_HEVC_SPS_FLAG_AMP_ENABLED);
+	GET_HEVC_VDEC_FLAG(sample_adaptive_offset,
+			   V4L2_HEVC_SPS_FLAG_SAMPLE_ADAPTIVE_OFFSET);
+	GET_HEVC_VDEC_FLAG(pcm_enabled,
+			   V4L2_HEVC_SPS_FLAG_PCM_ENABLED);
+	GET_HEVC_VDEC_FLAG(pcm_loop_filter_disabled,
+			   V4L2_HEVC_SPS_FLAG_PCM_LOOP_FILTER_DISABLED);
+	GET_HEVC_VDEC_FLAG(long_term_ref_pics_enabled,
+			   V4L2_HEVC_SPS_FLAG_LONG_TERM_REF_PICS_PRESENT);
+	GET_HEVC_VDEC_FLAG(sps_temporal_mvp_enabled,
+			   V4L2_HEVC_SPS_FLAG_SPS_TEMPORAL_MVP_ENABLED);
+	GET_HEVC_VDEC_FLAG(strong_intra_smoothing_enabled,
+			   V4L2_HEVC_SPS_FLAG_STRONG_INTRA_SMOOTHING_ENABLED);
+}
+
+static void vdec_hevc_copy_pps_params(struct mtk_hevc_pps_param *dst_param,
+				      const struct v4l2_ctrl_hevc_pps *src_param)
+{
+	int i;
+
+	GET_HEVC_VDEC_PARAM(pic_parameter_set_id);
+	GET_HEVC_VDEC_PARAM(num_extra_slice_header_bits);
+	GET_HEVC_VDEC_PARAM(num_ref_idx_l0_default_active_minus1);
+	GET_HEVC_VDEC_PARAM(num_ref_idx_l1_default_active_minus1);
+	GET_HEVC_VDEC_PARAM(init_qp_minus26);
+	GET_HEVC_VDEC_PARAM(diff_cu_qp_delta_depth);
+	GET_HEVC_VDEC_PARAM(pps_cb_qp_offset);
+	GET_HEVC_VDEC_PARAM(pps_cr_qp_offset);
+	GET_HEVC_VDEC_PARAM(num_tile_columns_minus1);
+	GET_HEVC_VDEC_PARAM(num_tile_rows_minus1);
+	GET_HEVC_VDEC_PARAM(init_qp_minus26);
+	GET_HEVC_VDEC_PARAM(diff_cu_qp_delta_depth);
+	GET_HEVC_VDEC_PARAM(pic_parameter_set_id);
+	GET_HEVC_VDEC_PARAM(num_extra_slice_header_bits);
+	GET_HEVC_VDEC_PARAM(num_ref_idx_l0_default_active_minus1);
+	GET_HEVC_VDEC_PARAM(num_ref_idx_l1_default_active_minus1);
+	GET_HEVC_VDEC_PARAM(pps_beta_offset_div2);
+	GET_HEVC_VDEC_PARAM(pps_tc_offset_div2);
+	GET_HEVC_VDEC_PARAM(log2_parallel_merge_level_minus2);
+
+	for (i = 0; i < ARRAY_SIZE(src_param->column_width_minus1); i++)
+		GET_HEVC_VDEC_PARAM(column_width_minus1[i]);
+	for (i = 0; i < ARRAY_SIZE(src_param->row_height_minus1); i++)
+		GET_HEVC_VDEC_PARAM(row_height_minus1[i]);
+
+	GET_HEVC_VDEC_FLAG(dependent_slice_segment_enabled,
+			   V4L2_HEVC_PPS_FLAG_DEPENDENT_SLICE_SEGMENT_ENABLED);
+	GET_HEVC_VDEC_FLAG(output_flag_present,
+			   V4L2_HEVC_PPS_FLAG_OUTPUT_FLAG_PRESENT);
+	GET_HEVC_VDEC_FLAG(sign_data_hiding_enabled,
+			   V4L2_HEVC_PPS_FLAG_SIGN_DATA_HIDING_ENABLED);
+	GET_HEVC_VDEC_FLAG(cabac_init_present,
+			   V4L2_HEVC_PPS_FLAG_CABAC_INIT_PRESENT);
+	GET_HEVC_VDEC_FLAG(constrained_intra_pred,
+			   V4L2_HEVC_PPS_FLAG_CONSTRAINED_INTRA_PRED);
+	GET_HEVC_VDEC_FLAG(transform_skip_enabled,
+			   V4L2_HEVC_PPS_FLAG_TRANSFORM_SKIP_ENABLED);
+	GET_HEVC_VDEC_FLAG(cu_qp_delta_enabled,
+			   V4L2_HEVC_PPS_FLAG_CU_QP_DELTA_ENABLED);
+	GET_HEVC_VDEC_FLAG(pps_slice_chroma_qp_offsets_present,
+			   V4L2_HEVC_PPS_FLAG_PPS_SLICE_CHROMA_QP_OFFSETS_PRESENT);
+	GET_HEVC_VDEC_FLAG(weighted_pred,
+			   V4L2_HEVC_PPS_FLAG_WEIGHTED_PRED);
+	GET_HEVC_VDEC_FLAG(weighted_bipred,
+			   V4L2_HEVC_PPS_FLAG_WEIGHTED_BIPRED);
+	GET_HEVC_VDEC_FLAG(transquant_bypass_enabled,
+			   V4L2_HEVC_PPS_FLAG_TRANSQUANT_BYPASS_ENABLED);
+	GET_HEVC_VDEC_FLAG(pps_flag_tiles_enabled,
+			   V4L2_HEVC_PPS_FLAG_TILES_ENABLED);
+	GET_HEVC_VDEC_FLAG(entropy_coding_sync_enabled,
+			   V4L2_HEVC_PPS_FLAG_ENTROPY_CODING_SYNC_ENABLED);
+	GET_HEVC_VDEC_FLAG(loop_filter_across_tiles_enabled,
+			   V4L2_HEVC_PPS_FLAG_LOOP_FILTER_ACROSS_TILES_ENABLED);
+	GET_HEVC_VDEC_FLAG(pps_loop_filter_across_slices_enabled,
+			   V4L2_HEVC_PPS_FLAG_PPS_LOOP_FILTER_ACROSS_SLICES_ENABLED);
+	GET_HEVC_VDEC_FLAG(deblocking_filter_override_enabled,
+			   V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_OVERRIDE_ENABLED);
+	GET_HEVC_VDEC_FLAG(pps_disable_deflocking_filter,
+			   V4L2_HEVC_PPS_FLAG_PPS_DISABLE_DEBLOCKING_FILTER);
+	GET_HEVC_VDEC_FLAG(lists_modification_present,
+			   V4L2_HEVC_PPS_FLAG_LISTS_MODIFICATION_PRESENT);
+	GET_HEVC_VDEC_FLAG(slice_segment_header_extersion_present,
+			   V4L2_HEVC_PPS_FLAG_SLICE_SEGMENT_HEADER_EXTENSION_PRESENT);
+	GET_HEVC_VDEC_FLAG(deblocking_filter_control_present,
+			   V4L2_HEVC_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT);
+	GET_HEVC_VDEC_FLAG(uniform_spacing,
+			   V4L2_HEVC_PPS_FLAG_UNIFORM_SPACING);
+}
+
+static void vdec_hevc_copy_scaling_matrix(struct slice_api_hevc_scaling_matrix *dst_matrix,
+					  const struct v4l2_ctrl_hevc_scaling_matrix *src_matrix)
+{
+	memcpy(dst_matrix, src_matrix, sizeof(*src_matrix));
+}
+
+static void
+vdec_hevc_copy_decode_params(struct slice_api_hevc_decode_param *dst_param,
+			     const struct v4l2_ctrl_hevc_decode_params *src_param,
+			     const struct v4l2_hevc_dpb_entry dpb[V4L2_HEVC_DPB_ENTRIES_NUM_MAX])
+{
+	struct slice_hevc_dpb_entry *dst_entry;
+	const struct v4l2_hevc_dpb_entry *src_entry;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dst_param->dpb); i++) {
+		dst_entry = &dst_param->dpb[i];
+		src_entry = &dpb[i];
+
+		dst_entry->timestamp = src_entry->timestamp;
+		dst_entry->flags = src_entry->flags;
+		dst_entry->field_pic = src_entry->field_pic;
+		dst_entry->pic_order_cnt_val = src_entry->pic_order_cnt_val;
+
+		GET_HEVC_VDEC_PARAM(poc_st_curr_before[i]);
+		GET_HEVC_VDEC_PARAM(poc_st_curr_after[i]);
+		GET_HEVC_VDEC_PARAM(poc_lt_curr[i]);
+	}
+
+	GET_HEVC_VDEC_PARAM(pic_order_cnt_val);
+	GET_HEVC_VDEC_PARAM(short_term_ref_pic_set_size);
+	GET_HEVC_VDEC_PARAM(long_term_ref_pic_set_size);
+	GET_HEVC_VDEC_PARAM(num_active_dpb_entries);
+	GET_HEVC_VDEC_PARAM(num_poc_st_curr_before);
+	GET_HEVC_VDEC_PARAM(num_poc_st_curr_after);
+	GET_HEVC_VDEC_PARAM(num_delta_pocs_of_ref_rps_idx);
+	GET_HEVC_VDEC_PARAM(num_poc_lt_curr);
+	GET_HEVC_VDEC_PARAM(flags);
+}
+
+static int vdec_hevc_slice_fill_decode_parameters(struct vdec_hevc_slice_inst *inst,
+						  struct vdec_hevc_slice_share_info *share_info)
+{
+	struct vdec_hevc_slice_lat_dec_param *slice_param = &inst->vsi->hevc_slice_params;
+	const struct v4l2_ctrl_hevc_decode_params *dec_params;
+	const struct v4l2_ctrl_hevc_scaling_matrix *src_matrix;
+	const struct v4l2_ctrl_hevc_sps *sps;
+	const struct v4l2_ctrl_hevc_pps *pps;
+
+	dec_params =
+		vdec_hevc_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_HEVC_DECODE_PARAMS);
+	if (IS_ERR(dec_params))
+		return PTR_ERR(dec_params);
+
+	src_matrix =
+		vdec_hevc_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_HEVC_SCALING_MATRIX);
+	if (IS_ERR(src_matrix))
+		return PTR_ERR(src_matrix);
+
+	sps = vdec_hevc_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_HEVC_SPS);
+	if (IS_ERR(sps))
+		return PTR_ERR(sps);
+
+	pps = vdec_hevc_get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_HEVC_PPS);
+	if (IS_ERR(pps))
+		return PTR_ERR(pps);
+
+	vdec_hevc_copy_sps_params(&slice_param->sps, sps);
+	vdec_hevc_copy_pps_params(&slice_param->pps, pps);
+	vdec_hevc_copy_scaling_matrix(&slice_param->scaling_matrix, src_matrix);
+
+	memcpy(&share_info->sps, sps, sizeof(*sps));
+	memcpy(&share_info->dec_params, dec_params, sizeof(*dec_params));
+
+	slice_param->decode_params.num_poc_st_curr_before = dec_params->num_poc_st_curr_before;
+	slice_param->decode_params.num_poc_st_curr_after = dec_params->num_poc_st_curr_after;
+	slice_param->decode_params.num_poc_lt_curr = dec_params->num_poc_lt_curr;
+	slice_param->decode_params.num_delta_pocs_of_ref_rps_idx =
+		dec_params->num_delta_pocs_of_ref_rps_idx;
+
+	return 0;
+}
+
+static void vdec_hevc_slice_fill_decode_reflist(struct vdec_hevc_slice_inst *inst,
+						struct vdec_hevc_slice_lat_dec_param *slice_param,
+						struct vdec_hevc_slice_share_info *share_info)
+{
+	struct v4l2_ctrl_hevc_decode_params *dec_params = &share_info->dec_params;
+
+	vdec_hevc_copy_decode_params(&slice_param->decode_params, dec_params,
+				     share_info->dec_params.dpb);
+
+	vdec_hevc_fill_dpb_info(inst->ctx, &slice_param->decode_params,
+				slice_param->hevc_dpb_info);
+}
+
+static int vdec_hevc_slice_alloc_mv_buf(struct vdec_hevc_slice_inst *inst,
+					struct vdec_pic_info *pic)
+{
+	unsigned int buf_sz = vdec_hevc_get_mv_buf_size(pic->buf_w, pic->buf_h);
+	struct mtk_vcodec_mem *mem;
+	int i, err;
+
+	mtk_v4l2_debug(3, "allocate mv buffer size = 0x%x", buf_sz);
+	for (i = 0; i < HEVC_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		if (mem->va)
+			mtk_vcodec_mem_free(inst->ctx, mem);
+		mem->size = buf_sz;
+		err = mtk_vcodec_mem_alloc(inst->ctx, mem);
+		if (err) {
+			mtk_vcodec_err(inst, "failed to allocate mv buf");
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void vdec_hevc_slice_free_mv_buf(struct vdec_hevc_slice_inst *inst)
+{
+	int i;
+	struct mtk_vcodec_mem *mem;
+
+	for (i = 0; i < HEVC_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		if (mem->va)
+			mtk_vcodec_mem_free(inst->ctx, mem);
+	}
+}
+
+static void vdec_hevc_slice_get_pic_info(struct vdec_hevc_slice_inst *inst)
+{
+	struct mtk_vcodec_ctx *ctx = inst->ctx;
+	u32 data[3];
+
+	data[0] = ctx->picinfo.pic_w;
+	data[1] = ctx->picinfo.pic_h;
+	data[2] = ctx->capture_fourcc;
+	vpu_dec_get_param(&inst->vpu, data, 3, GET_PARAM_PIC_INFO);
+
+	ctx->picinfo.buf_w = ALIGN(ctx->picinfo.pic_w, VCODEC_DEC_ALIGNED_64);
+	ctx->picinfo.buf_h = ALIGN(ctx->picinfo.pic_h, VCODEC_DEC_ALIGNED_64);
+	ctx->picinfo.fb_sz[0] = inst->vpu.fb_sz[0];
+	ctx->picinfo.fb_sz[1] = inst->vpu.fb_sz[1];
+	inst->cap_num_planes =
+		ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes;
+
+	mtk_vcodec_debug(inst, "pic(%d, %d), buf(%d, %d)",
+			 ctx->picinfo.pic_w, ctx->picinfo.pic_h,
+			 ctx->picinfo.buf_w, ctx->picinfo.buf_h);
+	mtk_vcodec_debug(inst, "Y/C(%d, %d)", ctx->picinfo.fb_sz[0],
+			 ctx->picinfo.fb_sz[1]);
+
+	if (ctx->last_decoded_picinfo.pic_w != ctx->picinfo.pic_w ||
+	    ctx->last_decoded_picinfo.pic_h != ctx->picinfo.pic_h) {
+		inst->resolution_changed = true;
+		if (ctx->last_decoded_picinfo.buf_w != ctx->picinfo.buf_w ||
+		    ctx->last_decoded_picinfo.buf_h != ctx->picinfo.buf_h)
+			inst->realloc_mv_buf = true;
+
+		mtk_v4l2_debug(1, "resChg: (%d %d) : old(%d, %d) -> new(%d, %d)",
+			       inst->resolution_changed,
+			       inst->realloc_mv_buf,
+			       ctx->last_decoded_picinfo.pic_w,
+			       ctx->last_decoded_picinfo.pic_h,
+			       ctx->picinfo.pic_w, ctx->picinfo.pic_h);
+	}
+}
+
+static void vdec_hevc_slice_get_crop_info(struct vdec_hevc_slice_inst *inst,
+					  struct v4l2_rect *cr)
+{
+	cr->left = 0;
+	cr->top = 0;
+	cr->width = inst->ctx->picinfo.pic_w;
+	cr->height = inst->ctx->picinfo.pic_h;
+
+	mtk_vcodec_debug(inst, "l=%d, t=%d, w=%d, h=%d",
+			 cr->left, cr->top, cr->width, cr->height);
+}
+
+static int vdec_hevc_slice_setup_lat_buffer(struct vdec_hevc_slice_inst *inst,
+					    struct mtk_vcodec_mem *bs,
+					    struct vdec_lat_buf *lat_buf,
+					    bool *res_chg)
+{
+	struct mtk_vcodec_mem *mem;
+	struct mtk_video_dec_buf *src_buf_info;
+	struct vdec_hevc_slice_share_info *share_info;
+	int i, err;
+
+	inst->vsi->bs.dma_addr = (u64)bs->dma_addr;
+	inst->vsi->bs.size = bs->size;
+
+	src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer);
+	lat_buf->src_buf_req = src_buf_info->m2m_buf.vb.vb2_buf.req_obj.req;
+	v4l2_m2m_buf_copy_metadata(&src_buf_info->m2m_buf.vb, &lat_buf->ts_info, true);
+
+	*res_chg = inst->resolution_changed;
+	if (inst->resolution_changed) {
+		mtk_vcodec_debug(inst, "- resolution changed -");
+		if (inst->realloc_mv_buf) {
+			err = vdec_hevc_slice_alloc_mv_buf(inst, &inst->ctx->picinfo);
+			inst->realloc_mv_buf = false;
+			if (err)
+				return err;
+		}
+		inst->resolution_changed = false;
+	}
+
+	for (i = 0; i < HEVC_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		inst->vsi->mv_buf_dma[i].dma_addr = mem->dma_addr;
+		inst->vsi->mv_buf_dma[i].size = mem->size;
+	}
+
+	inst->vsi->ube.dma_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr;
+	inst->vsi->ube.size = lat_buf->ctx->msg_queue.wdma_addr.size;
+
+	inst->vsi->err_map.dma_addr = lat_buf->wdma_err_addr.dma_addr;
+	inst->vsi->err_map.size = lat_buf->wdma_err_addr.size;
+
+	inst->vsi->slice_bc.dma_addr = lat_buf->slice_bc_addr.dma_addr;
+	inst->vsi->slice_bc.size = lat_buf->slice_bc_addr.size;
+
+	inst->vsi->trans.dma_addr_end = inst->ctx->msg_queue.wdma_rptr_addr;
+	inst->vsi->trans.dma_addr = inst->ctx->msg_queue.wdma_wptr_addr;
+
+	share_info = lat_buf->private_data;
+	share_info->trans.dma_addr = inst->vsi->trans.dma_addr;
+	share_info->trans.dma_addr_end = inst->vsi->trans.dma_addr_end;
+
+	mtk_vcodec_debug(inst, "lat: ube addr/size(0x%llx 0x%llx) err:0x%llx",
+			 inst->vsi->ube.buf,
+			 inst->vsi->ube.padding,
+			 inst->vsi->err_map.buf);
+
+	mtk_vcodec_debug(inst, "slice addr/size(0x%llx 0x%llx) trans start/end((0x%llx 0x%llx))",
+			 inst->vsi->slice_bc.buf,
+			 inst->vsi->slice_bc.padding,
+			 inst->vsi->trans.buf,
+			 inst->vsi->trans.padding);
+
+	return 0;
+}
+
+static int vdec_hevc_slice_setup_core_buffer(struct vdec_hevc_slice_inst *inst,
+					     struct vdec_hevc_slice_share_info *share_info,
+					     struct vdec_lat_buf *lat_buf)
+{
+	struct mtk_vcodec_mem *mem;
+	struct mtk_vcodec_ctx *ctx = inst->ctx;
+	struct vb2_v4l2_buffer *vb2_v4l2;
+	struct vdec_fb *fb;
+	u64 y_fb_dma, c_fb_dma;
+	int i;
+
+	fb = ctx->dev->vdec_pdata->get_cap_buffer(ctx);
+	if (!fb) {
+		mtk_vcodec_err(inst, "fb buffer is NULL");
+		return -EBUSY;
+	}
+
+	y_fb_dma = (u64)fb->base_y.dma_addr;
+	if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 1)
+		c_fb_dma =
+			y_fb_dma + inst->ctx->picinfo.buf_w * inst->ctx->picinfo.buf_h;
+	else
+		c_fb_dma = (u64)fb->base_c.dma_addr;
+
+	mtk_vcodec_debug(inst, "[hevc-core] y/c addr = 0x%llx 0x%llx", y_fb_dma,
+			 c_fb_dma);
+
+	inst->vsi_core->fb.y.dma_addr = y_fb_dma;
+	inst->vsi_core->fb.y.size = ctx->picinfo.fb_sz[0];
+	inst->vsi_core->fb.c.dma_addr = c_fb_dma;
+	inst->vsi_core->fb.y.size = ctx->picinfo.fb_sz[1];
+
+	inst->vsi_core->dec.vdec_fb_va = (unsigned long)fb;
+
+	inst->vsi_core->ube.dma_addr = lat_buf->ctx->msg_queue.wdma_addr.dma_addr;
+	inst->vsi_core->ube.size = lat_buf->ctx->msg_queue.wdma_addr.size;
+
+	inst->vsi_core->err_map.dma_addr = lat_buf->wdma_err_addr.dma_addr;
+	inst->vsi_core->err_map.size = lat_buf->wdma_err_addr.size;
+
+	inst->vsi_core->slice_bc.dma_addr = lat_buf->slice_bc_addr.dma_addr;
+	inst->vsi_core->slice_bc.size = lat_buf->slice_bc_addr.size;
+
+	inst->vsi_core->trans.dma_addr = share_info->trans.dma_addr;
+	inst->vsi_core->trans.dma_addr_end = share_info->trans.dma_addr_end;
+
+	inst->vsi_core->wrap.dma_addr = inst->wrap_addr.dma_addr;
+	inst->vsi_core->wrap.size = inst->wrap_addr.size;
+
+	for (i = 0; i < HEVC_MAX_MV_NUM; i++) {
+		mem = &inst->mv_buf[i];
+		inst->vsi_core->mv_buf_dma[i].dma_addr = mem->dma_addr;
+		inst->vsi_core->mv_buf_dma[i].size = mem->size;
+	}
+
+	vb2_v4l2 = v4l2_m2m_next_dst_buf(ctx->m2m_ctx);
+	v4l2_m2m_buf_copy_metadata(&lat_buf->ts_info, vb2_v4l2, true);
+
+	return 0;
+}
+
+static int vdec_hevc_slice_init(struct mtk_vcodec_ctx *ctx)
+{
+	struct vdec_hevc_slice_inst *inst;
+	int err, vsi_size;
+
+	inst = kzalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	inst->ctx = ctx;
+
+	inst->vpu.id = SCP_IPI_VDEC_LAT;
+	inst->vpu.core_id = SCP_IPI_VDEC_CORE;
+	inst->vpu.ctx = ctx;
+	inst->vpu.codec_type = ctx->current_codec;
+	inst->vpu.capture_type = ctx->capture_fourcc;
+
+	ctx->drv_handle = inst;
+	err = vpu_dec_init(&inst->vpu);
+	if (err) {
+		mtk_vcodec_err(inst, "vdec_hevc init err=%d", err);
+		goto error_free_inst;
+	}
+
+	vsi_size = round_up(sizeof(struct vdec_hevc_slice_vsi), VCODEC_DEC_ALIGNED_64);
+	inst->vsi = inst->vpu.vsi;
+	inst->vsi_core =
+		(struct vdec_hevc_slice_vsi *)(((char *)inst->vpu.vsi) + vsi_size);
+
+	inst->resolution_changed = true;
+	inst->realloc_mv_buf = true;
+
+	inst->wrap_addr.size = VDEC_HEVC_WRAP_SZ;
+	err = mtk_vcodec_mem_alloc(ctx, &inst->wrap_addr);
+	if (err)
+		goto error_free_inst;
+
+	mtk_vcodec_debug(inst, "lat struct size = %d,%d,%d,%d vsi: %d\n",
+			 (int)sizeof(struct mtk_hevc_sps_param),
+			 (int)sizeof(struct mtk_hevc_pps_param),
+			 (int)sizeof(struct vdec_hevc_slice_lat_dec_param),
+			 (int)sizeof(struct mtk_hevc_dpb_info),
+			 vsi_size);
+	mtk_vcodec_debug(inst, "lat hevc instance >> %p, codec_type = 0x%x",
+			 inst, inst->vpu.codec_type);
+
+	return 0;
+error_free_inst:
+	kfree(inst);
+	return err;
+}
+
+static void vdec_hevc_slice_deinit(void *h_vdec)
+{
+	struct vdec_hevc_slice_inst *inst = h_vdec;
+	struct mtk_vcodec_mem *mem;
+
+	mtk_vcodec_debug_enter(inst);
+
+	vpu_dec_deinit(&inst->vpu);
+	vdec_hevc_slice_free_mv_buf(inst);
+
+	mem = &inst->wrap_addr;
+	if (mem->va)
+		mtk_vcodec_mem_free(inst->ctx, mem);
+
+	vdec_msg_queue_deinit(&inst->ctx->msg_queue, inst->ctx);
+	kfree(inst);
+}
+
+static int vdec_hevc_slice_core_decode(struct vdec_lat_buf *lat_buf)
+{
+	int err, timeout;
+	struct mtk_vcodec_ctx *ctx = lat_buf->ctx;
+	struct vdec_hevc_slice_inst *inst = ctx->drv_handle;
+	struct vdec_hevc_slice_share_info *share_info = lat_buf->private_data;
+	struct vdec_vpu_inst *vpu = &inst->vpu;
+
+	mtk_vcodec_debug(inst, "[hevc-core] vdec_hevc core decode");
+	memcpy(&inst->vsi_core->hevc_slice_params, &share_info->hevc_slice_params,
+	       sizeof(share_info->hevc_slice_params));
+
+	err = vdec_hevc_slice_setup_core_buffer(inst, share_info, lat_buf);
+	if (err)
+		goto vdec_dec_end;
+
+	vdec_hevc_slice_fill_decode_reflist(inst, &inst->vsi_core->hevc_slice_params,
+					    share_info);
+	err = vpu_dec_core(vpu);
+	if (err) {
+		mtk_vcodec_err(inst, "core decode err=%d", err);
+		goto vdec_dec_end;
+	}
+
+	/* wait decoder done interrupt */
+	timeout = mtk_vcodec_wait_for_done_ctx(inst->ctx, MTK_INST_IRQ_RECEIVED,
+					       WAIT_INTR_TIMEOUT_MS, MTK_VDEC_CORE);
+	if (timeout)
+		mtk_vcodec_err(inst, "core decode timeout: pic_%d",
+			       ctx->decoded_frame_cnt);
+	inst->vsi_core->dec.timeout = !!timeout;
+
+	vpu_dec_core_end(vpu);
+	mtk_vcodec_debug(inst, "pic[%d] crc: 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x 0x%x",
+			 ctx->decoded_frame_cnt,
+			 inst->vsi_core->dec.crc[0], inst->vsi_core->dec.crc[1],
+			 inst->vsi_core->dec.crc[2], inst->vsi_core->dec.crc[3],
+			 inst->vsi_core->dec.crc[4], inst->vsi_core->dec.crc[5],
+			 inst->vsi_core->dec.crc[6], inst->vsi_core->dec.crc[7]);
+
+vdec_dec_end:
+	vdec_msg_queue_update_ube_rptr(&lat_buf->ctx->msg_queue, share_info->trans.dma_addr_end);
+	ctx->dev->vdec_pdata->cap_to_disp(ctx, !!err, lat_buf->src_buf_req);
+	mtk_vcodec_debug(inst, "core decode done err=%d", err);
+	ctx->decoded_frame_cnt++;
+	return 0;
+}
+
+static int vdec_hevc_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+				      struct vdec_fb *fb, bool *res_chg)
+{
+	struct vdec_hevc_slice_inst *inst = h_vdec;
+	struct vdec_vpu_inst *vpu = &inst->vpu;
+	int err, timeout = 0;
+	unsigned int data[2];
+	struct vdec_lat_buf *lat_buf;
+	struct vdec_hevc_slice_share_info *share_info;
+
+	if (vdec_msg_queue_init(&inst->ctx->msg_queue, inst->ctx,
+				vdec_hevc_slice_core_decode,
+				sizeof(*share_info)))
+		return -ENOMEM;
+
+	/* bs NULL means flush decoder */
+	if (!bs) {
+		vdec_msg_queue_wait_lat_buf_full(&inst->ctx->msg_queue);
+		return vpu_dec_reset(vpu);
+	}
+
+	lat_buf = vdec_msg_queue_dqbuf(&inst->ctx->msg_queue.lat_ctx);
+	if (!lat_buf) {
+		mtk_vcodec_debug(inst, "failed to get lat buffer");
+		return -EAGAIN;
+	}
+
+	share_info = lat_buf->private_data;
+	err = vdec_hevc_slice_fill_decode_parameters(inst, share_info);
+	if (err)
+		goto err_free_fb_out;
+
+	err = vdec_hevc_slice_setup_lat_buffer(inst, bs, lat_buf, res_chg);
+	if (err)
+		goto err_free_fb_out;
+
+	err = vpu_dec_start(vpu, data, 2);
+	if (err) {
+		mtk_vcodec_debug(inst, "lat decode err: %d", err);
+		goto err_free_fb_out;
+	}
+
+	if (IS_VDEC_INNER_RACING(inst->ctx->dev->dec_capability)) {
+		memcpy(&share_info->hevc_slice_params, &inst->vsi->hevc_slice_params,
+		       sizeof(share_info->hevc_slice_params));
+		vdec_msg_queue_qbuf(&inst->ctx->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);
+	if (timeout)
+		mtk_vcodec_err(inst, "lat decode timeout: pic_%d", inst->slice_dec_num);
+	inst->vsi->dec.timeout = !!timeout;
+
+	err = vpu_dec_end(vpu);
+	if (err == SLICE_HEADER_FULL || err == TRANS_BUFFER_FULL) {
+		if (!IS_VDEC_INNER_RACING(inst->ctx->dev->dec_capability))
+			vdec_msg_queue_qbuf(&inst->ctx->msg_queue.lat_ctx, lat_buf);
+		inst->slice_dec_num++;
+		mtk_vcodec_err(inst, "lat dec fail: pic_%d err:%d", inst->slice_dec_num, err);
+		return -EINVAL;
+	}
+
+	share_info->trans.dma_addr_end = inst->ctx->msg_queue.wdma_addr.dma_addr +
+		inst->vsi->dec.wdma_end_addr_offset;
+	vdec_msg_queue_update_ube_wptr(&lat_buf->ctx->msg_queue, share_info->trans.dma_addr_end);
+
+	if (!IS_VDEC_INNER_RACING(inst->ctx->dev->dec_capability)) {
+		memcpy(&share_info->hevc_slice_params, &inst->vsi->hevc_slice_params,
+		       sizeof(share_info->hevc_slice_params));
+		vdec_msg_queue_qbuf(&inst->ctx->msg_queue.core_ctx, lat_buf);
+	}
+	mtk_vcodec_debug(inst, "dec num: %d lat crc: 0x%x 0x%x 0x%x", inst->slice_dec_num,
+			 inst->vsi->dec.crc[0], inst->vsi->dec.crc[1], inst->vsi->dec.crc[2]);
+
+	inst->slice_dec_num++;
+	return 0;
+err_free_fb_out:
+	vdec_msg_queue_qbuf(&inst->ctx->msg_queue.lat_ctx, lat_buf);
+	mtk_vcodec_err(inst, "slice dec number: %d err: %d", inst->slice_dec_num, err);
+	return err;
+}
+
+static int vdec_hevc_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+				  struct vdec_fb *unused, bool *res_chg)
+{
+	struct vdec_hevc_slice_inst *inst = h_vdec;
+
+	if (!h_vdec || inst->ctx->dev->vdec_pdata->hw_arch == MTK_VDEC_PURE_SINGLE_CORE)
+		return -EINVAL;
+
+	return vdec_hevc_slice_lat_decode(h_vdec, bs, unused, res_chg);
+}
+
+static int vdec_hevc_slice_get_param(void *h_vdec, enum vdec_get_param_type type,
+				     void *out)
+{
+	struct vdec_hevc_slice_inst *inst = h_vdec;
+
+	switch (type) {
+	case GET_PARAM_PIC_INFO:
+		vdec_hevc_slice_get_pic_info(inst);
+		break;
+	case GET_PARAM_DPB_SIZE:
+		*(unsigned int *)out = 6;
+		break;
+	case GET_PARAM_CROP_INFO:
+		vdec_hevc_slice_get_crop_info(inst, out);
+		break;
+	default:
+		mtk_vcodec_err(inst, "invalid get parameter type=%d", type);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+const struct vdec_common_if vdec_hevc_slice_multi_if = {
+	.init		= vdec_hevc_slice_init,
+	.decode		= vdec_hevc_slice_decode,
+	.get_param	= vdec_hevc_slice_get_param,
+	.deinit		= vdec_hevc_slice_deinit,
+};
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 cf16cf2807f0..c2f90848f498 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
@@ -2069,7 +2069,7 @@ static int vdec_vp9_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 
 	lat_buf = vdec_msg_queue_dqbuf(&instance->ctx->msg_queue.lat_ctx);
 	if (!lat_buf) {
-		mtk_vcodec_err(instance, "Failed to get VP9 lat buf\n");
+		mtk_vcodec_debug(instance, "Failed to get VP9 lat buf\n");
 		return -EAGAIN;
 	}
 	pfc = (struct vdec_vp9_slice_pfc *)lat_buf->private_data;
@@ -2119,7 +2119,7 @@ static int vdec_vp9_slice_lat_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
 	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);
+	vdec_msg_queue_qbuf(&ctx->msg_queue.core_ctx, lat_buf);
 
 	return 0;
 err_free_fb_out:
diff --git a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c
index f3807f03d880..06d393174cc2 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c
+++ b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.c
@@ -49,6 +49,14 @@ int vdec_if_init(struct mtk_vcodec_ctx *ctx, unsigned int fourcc)
 		ctx->dec_if = &vdec_vp9_slice_lat_if;
 		ctx->hw_id = IS_VDEC_LAT_ARCH(hw_arch) ? MTK_VDEC_LAT0 : MTK_VDEC_CORE;
 		break;
+	case V4L2_PIX_FMT_HEVC_SLICE:
+		ctx->dec_if = &vdec_hevc_slice_multi_if;
+		ctx->hw_id = MTK_VDEC_LAT0;
+		break;
+	case V4L2_PIX_FMT_AV1_FRAME:
+		ctx->dec_if = &vdec_av1_slice_lat_if;
+		ctx->hw_id = MTK_VDEC_LAT0;
+		break;
 	default:
 		return -EINVAL;
 	}
diff --git a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h
index 076306ff2dd4..a8da6a59a6a5 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h
+++ b/drivers/media/platform/mediatek/vcodec/vdec_drv_if.h
@@ -61,6 +61,8 @@ extern const struct vdec_common_if vdec_vp8_if;
 extern const struct vdec_common_if vdec_vp8_slice_if;
 extern const struct vdec_common_if vdec_vp9_if;
 extern const struct vdec_common_if vdec_vp9_slice_lat_if;
+extern const struct vdec_common_if vdec_hevc_slice_multi_if;
+extern const struct vdec_common_if vdec_av1_slice_lat_if;
 
 /**
  * vdec_if_init() - initialize decode driver
diff --git a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c
index f3073d1e7f42..f555341ae708 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c
+++ b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.c
@@ -20,6 +20,9 @@
 /* the size used to store avc error information */
 #define VDEC_ERR_MAP_SZ_AVC         (17 * SZ_1K)
 
+#define VDEC_RD_MV_BUFFER_SZ        (((SZ_4K * 2304 >> 4) + SZ_1K) << 1)
+#define VDEC_LAT_TILE_SZ            (64 * V4L2_AV1_MAX_TILE_COUNT)
+
 /* core will read the trans buffer which decoded by lat to decode again.
  * The trans buffer size of FHD and 4K bitstreams are different.
  */
@@ -71,7 +74,6 @@ static void vdec_msg_queue_dec(struct vdec_msg_queue *msg_queue, int hardware_in
 int vdec_msg_queue_qbuf(struct vdec_msg_queue_ctx *msg_ctx, struct vdec_lat_buf *buf)
 {
 	struct list_head *head;
-	int status;
 
 	head = vdec_get_buf_list(msg_ctx->hardware_index, buf);
 	if (!head) {
@@ -87,12 +89,9 @@ int vdec_msg_queue_qbuf(struct vdec_msg_queue_ctx *msg_ctx, struct vdec_lat_buf
 	if (msg_ctx->hardware_index != MTK_VDEC_CORE) {
 		wake_up_all(&msg_ctx->ready_to_use);
 	} else {
-		if (buf->ctx->msg_queue.core_work_cnt <
-			atomic_read(&buf->ctx->msg_queue.core_list_cnt)) {
-			status = queue_work(buf->ctx->dev->core_workqueue,
-					    &buf->ctx->msg_queue.core_work);
-			if (status)
-				buf->ctx->msg_queue.core_work_cnt++;
+		if (!(buf->ctx->msg_queue.status & CONTEXT_LIST_QUEUED)) {
+			queue_work(buf->ctx->dev->core_workqueue, &buf->ctx->msg_queue.core_work);
+			buf->ctx->msg_queue.status |= CONTEXT_LIST_QUEUED;
 		}
 	}
 
@@ -181,49 +180,23 @@ void vdec_msg_queue_update_ube_wptr(struct vdec_msg_queue *msg_queue, uint64_t u
 
 bool vdec_msg_queue_wait_lat_buf_full(struct vdec_msg_queue *msg_queue)
 {
-	struct vdec_lat_buf *buf, *tmp;
-	struct list_head *list_core[3];
-	struct vdec_msg_queue_ctx *core_ctx;
-	int ret, i, in_core_count = 0, count = 0;
-	long timeout_jiff;
-
-	core_ctx = &msg_queue->ctx->dev->msg_queue_core_ctx;
-	spin_lock(&core_ctx->ready_lock);
-	list_for_each_entry_safe(buf, tmp, &core_ctx->ready_queue, core_list) {
-		if (buf && buf->ctx == msg_queue->ctx) {
-			list_core[in_core_count++] = &buf->core_list;
-			list_del(&buf->core_list);
-		}
-	}
-
-	for (i = 0; i < in_core_count; i++) {
-		list_add(list_core[in_core_count - (1 + i)], &core_ctx->ready_queue);
-		queue_work(msg_queue->ctx->dev->core_workqueue, &msg_queue->core_work);
-	}
-	spin_unlock(&core_ctx->ready_lock);
-
-	timeout_jiff = msecs_to_jiffies(1000 * (NUM_BUFFER_COUNT + 2));
-	ret = wait_event_timeout(msg_queue->ctx->msg_queue.core_dec_done,
-				 msg_queue->lat_ctx.ready_num == NUM_BUFFER_COUNT,
-				 timeout_jiff);
-	if (ret) {
-		mtk_v4l2_debug(3, "success to get lat buf: %d",
-			       msg_queue->lat_ctx.ready_num);
+	if (atomic_read(&msg_queue->lat_list_cnt) == NUM_BUFFER_COUNT) {
+		mtk_v4l2_debug(3, "wait buf full: list(%d %d) ready_num:%d status:%d",
+			       atomic_read(&msg_queue->lat_list_cnt),
+			       atomic_read(&msg_queue->core_list_cnt),
+			       msg_queue->lat_ctx.ready_num,
+			       msg_queue->status);
 		return true;
 	}
 
-	spin_lock(&core_ctx->ready_lock);
-	list_for_each_entry_safe(buf, tmp, &core_ctx->ready_queue, core_list) {
-		if (buf && buf->ctx == msg_queue->ctx) {
-			count++;
-			list_del(&buf->core_list);
-		}
-	}
-	spin_unlock(&core_ctx->ready_lock);
+	msg_queue->flush_done = false;
+	vdec_msg_queue_qbuf(&msg_queue->core_ctx, &msg_queue->empty_lat_buf);
+	wait_event(msg_queue->core_dec_done, msg_queue->flush_done);
 
-	mtk_v4l2_err("failed with lat buf isn't full: list(%d %d) count:%d",
-		     atomic_read(&msg_queue->lat_list_cnt),
-		     atomic_read(&msg_queue->core_list_cnt), count);
+	mtk_v4l2_debug(3, "flush done => ready_num:%d status:%d list(%d %d)",
+		       msg_queue->lat_ctx.ready_num, msg_queue->status,
+		       atomic_read(&msg_queue->lat_list_cnt),
+		       atomic_read(&msg_queue->core_list_cnt));
 
 	return false;
 }
@@ -249,8 +222,18 @@ void vdec_msg_queue_deinit(struct vdec_msg_queue *msg_queue,
 		if (mem->va)
 			mtk_vcodec_mem_free(ctx, mem);
 
+		mem = &lat_buf->rd_mv_addr;
+		if (mem->va)
+			mtk_vcodec_mem_free(ctx, mem);
+
+		mem = &lat_buf->tile_addr;
+		if (mem->va)
+			mtk_vcodec_mem_free(ctx, mem);
+
 		kfree(lat_buf->private_data);
 	}
+
+	cancel_work_sync(&msg_queue->core_work);
 }
 
 static void vdec_msg_queue_core_work(struct work_struct *work)
@@ -261,12 +244,23 @@ static void vdec_msg_queue_core_work(struct work_struct *work)
 		container_of(msg_queue, struct mtk_vcodec_ctx, msg_queue);
 	struct mtk_vcodec_dev *dev = ctx->dev;
 	struct vdec_lat_buf *lat_buf;
-	int status;
 
-	lat_buf = vdec_msg_queue_dqbuf(&dev->msg_queue_core_ctx);
+	spin_lock(&msg_queue->core_ctx.ready_lock);
+	ctx->msg_queue.status &= ~CONTEXT_LIST_QUEUED;
+	spin_unlock(&msg_queue->core_ctx.ready_lock);
+
+	lat_buf = vdec_msg_queue_dqbuf(&msg_queue->core_ctx);
 	if (!lat_buf)
 		return;
 
+	if (lat_buf->is_last_frame) {
+		ctx->msg_queue.status = CONTEXT_LIST_DEC_DONE;
+		msg_queue->flush_done = true;
+		wake_up(&ctx->msg_queue.core_dec_done);
+
+		return;
+	}
+
 	ctx = lat_buf->ctx;
 	mtk_vcodec_dec_enable_hardware(ctx, MTK_VDEC_CORE);
 	mtk_vcodec_set_curr_ctx(dev, ctx, MTK_VDEC_CORE);
@@ -277,18 +271,13 @@ static void vdec_msg_queue_core_work(struct work_struct *work)
 	mtk_vcodec_dec_disable_hardware(ctx, MTK_VDEC_CORE);
 	vdec_msg_queue_qbuf(&ctx->msg_queue.lat_ctx, lat_buf);
 
-	wake_up_all(&ctx->msg_queue.core_dec_done);
-	spin_lock(&dev->msg_queue_core_ctx.ready_lock);
-	lat_buf->ctx->msg_queue.core_work_cnt--;
-
-	if (lat_buf->ctx->msg_queue.core_work_cnt <
-		atomic_read(&lat_buf->ctx->msg_queue.core_list_cnt)) {
-		status = queue_work(lat_buf->ctx->dev->core_workqueue,
-				    &lat_buf->ctx->msg_queue.core_work);
-		if (status)
-			lat_buf->ctx->msg_queue.core_work_cnt++;
+	if (!(ctx->msg_queue.status & CONTEXT_LIST_QUEUED) &&
+	    atomic_read(&msg_queue->core_list_cnt)) {
+		spin_lock(&msg_queue->core_ctx.ready_lock);
+		ctx->msg_queue.status |= CONTEXT_LIST_QUEUED;
+		spin_unlock(&msg_queue->core_ctx.ready_lock);
+		queue_work(ctx->dev->core_workqueue, &msg_queue->core_work);
 	}
-	spin_unlock(&dev->msg_queue_core_ctx.ready_lock);
 }
 
 int vdec_msg_queue_init(struct vdec_msg_queue *msg_queue,
@@ -302,14 +291,14 @@ int vdec_msg_queue_init(struct vdec_msg_queue *msg_queue,
 	if (msg_queue->wdma_addr.size)
 		return 0;
 
-	msg_queue->ctx = ctx;
-	msg_queue->core_work_cnt = 0;
 	vdec_msg_queue_init_ctx(&msg_queue->lat_ctx, MTK_VDEC_LAT0);
+	vdec_msg_queue_init_ctx(&msg_queue->core_ctx, MTK_VDEC_CORE);
 	INIT_WORK(&msg_queue->core_work, vdec_msg_queue_core_work);
 
 	atomic_set(&msg_queue->lat_list_cnt, 0);
 	atomic_set(&msg_queue->core_list_cnt, 0);
 	init_waitqueue_head(&msg_queue->core_dec_done);
+	msg_queue->status = CONTEXT_LIST_EMPTY;
 
 	msg_queue->wdma_addr.size =
 		vde_msg_queue_get_trans_size(ctx->picinfo.buf_w,
@@ -322,6 +311,10 @@ int vdec_msg_queue_init(struct vdec_msg_queue *msg_queue,
 	msg_queue->wdma_rptr_addr = msg_queue->wdma_addr.dma_addr;
 	msg_queue->wdma_wptr_addr = msg_queue->wdma_addr.dma_addr;
 
+	msg_queue->empty_lat_buf.ctx = ctx;
+	msg_queue->empty_lat_buf.core_decode = NULL;
+	msg_queue->empty_lat_buf.is_last_frame = true;
+
 	for (i = 0; i < NUM_BUFFER_COUNT; i++) {
 		lat_buf = &msg_queue->lat_buf[i];
 
@@ -339,6 +332,22 @@ int vdec_msg_queue_init(struct vdec_msg_queue *msg_queue,
 			goto mem_alloc_err;
 		}
 
+		if (ctx->current_codec == V4L2_PIX_FMT_AV1_FRAME) {
+			lat_buf->rd_mv_addr.size = VDEC_RD_MV_BUFFER_SZ;
+			err = mtk_vcodec_mem_alloc(ctx, &lat_buf->rd_mv_addr);
+			if (err) {
+				mtk_v4l2_err("failed to allocate rd_mv_addr buf[%d]", i);
+				return -ENOMEM;
+			}
+
+			lat_buf->tile_addr.size = VDEC_LAT_TILE_SZ;
+			err = mtk_vcodec_mem_alloc(ctx, &lat_buf->tile_addr);
+			if (err) {
+				mtk_v4l2_err("failed to allocate tile_addr buf[%d]", i);
+				return -ENOMEM;
+			}
+		}
+
 		lat_buf->private_data = kzalloc(private_size, GFP_KERNEL);
 		if (!lat_buf->private_data) {
 			err = -ENOMEM;
@@ -347,6 +356,7 @@ int vdec_msg_queue_init(struct vdec_msg_queue *msg_queue,
 
 		lat_buf->ctx = ctx;
 		lat_buf->core_decode = core_decode;
+		lat_buf->is_last_frame = false;
 		err = vdec_msg_queue_qbuf(&msg_queue->lat_ctx, lat_buf);
 		if (err) {
 			mtk_v4l2_err("failed to qbuf buf[%d]", i);
diff --git a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h
index a5d44bc97c16..2a745e902ad1 100644
--- a/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h
+++ b/drivers/media/platform/mediatek/vcodec/vdec_msg_queue.h
@@ -22,6 +22,18 @@ struct mtk_vcodec_dev;
 typedef int (*core_decode_cb_t)(struct vdec_lat_buf *lat_buf);
 
 /**
+ * enum core_ctx_status - Context decode status for core hardwre.
+ * @CONTEXT_LIST_EMPTY: No buffer queued on core hardware(must always be 0)
+ * @CONTEXT_LIST_QUEUED: Buffer queued to core work list
+ * @CONTEXT_LIST_DEC_DONE: context decode done
+ */
+enum core_ctx_status {
+	CONTEXT_LIST_EMPTY = 0,
+	CONTEXT_LIST_QUEUED,
+	CONTEXT_LIST_DEC_DONE,
+};
+
+/**
  * struct vdec_msg_queue_ctx - represents a queue for buffers ready to be processed
  * @ready_to_use: ready used queue used to signalize when get a job queue
  * @ready_queue: list of ready lat buffer queues
@@ -42,6 +54,8 @@ struct vdec_msg_queue_ctx {
  * struct vdec_lat_buf - lat buffer message used to store lat info for core decode
  * @wdma_err_addr: wdma error address used for lat hardware
  * @slice_bc_addr: slice bc address used for lat hardware
+ * @rd_mv_addr:	mv addr for av1 lat hardware output, core hardware input
+ * @tile_addr:	tile buffer for av1 core input
  * @ts_info: need to set timestamp from output to capture
  * @src_buf_req: output buffer media request object
  *
@@ -50,10 +64,14 @@ struct vdec_msg_queue_ctx {
  * @core_decode: different codec use different decode callback function
  * @lat_list: add lat buffer to lat head list
  * @core_list: add lat buffer to core head list
+ *
+ * @is_last_frame: meaning this buffer is the last frame
  */
 struct vdec_lat_buf {
 	struct mtk_vcodec_mem wdma_err_addr;
 	struct mtk_vcodec_mem slice_bc_addr;
+	struct mtk_vcodec_mem rd_mv_addr;
+	struct mtk_vcodec_mem tile_addr;
 	struct vb2_v4l2_buffer ts_info;
 	struct media_request *src_buf_req;
 
@@ -62,6 +80,8 @@ struct vdec_lat_buf {
 	core_decode_cb_t core_decode;
 	struct list_head lat_list;
 	struct list_head core_list;
+
+	bool is_last_frame;
 };
 
 /**
@@ -72,12 +92,14 @@ struct vdec_lat_buf {
  * @wdma_wptr_addr: ube write point
  * @core_work: core hardware work
  * @lat_ctx: used to store lat buffer list
- * @ctx: point to mtk_vcodec_ctx
+ * @core_ctx: used to store core buffer list
  *
  * @lat_list_cnt: used to record each instance lat list count
  * @core_list_cnt: used to record each instance core list count
+ * @flush_done: core flush done status
+ * @empty_lat_buf: the last lat buf used to flush decode
  * @core_dec_done: core work queue decode done event
- * @core_work_cnt: the number of core work in work queue
+ * @status: current context decode status for core hardware
  */
 struct vdec_msg_queue {
 	struct vdec_lat_buf lat_buf[NUM_BUFFER_COUNT];
@@ -88,12 +110,14 @@ struct vdec_msg_queue {
 
 	struct work_struct core_work;
 	struct vdec_msg_queue_ctx lat_ctx;
-	struct mtk_vcodec_ctx *ctx;
+	struct vdec_msg_queue_ctx core_ctx;
 
 	atomic_t lat_list_cnt;
 	atomic_t core_list_cnt;
+	bool flush_done;
+	struct vdec_lat_buf empty_lat_buf;
 	wait_queue_head_t core_dec_done;
-	int core_work_cnt;
+	int status;
 };
 
 /**