[PATCH v2 0/8] media: mtk-vcodec: vdec: support for MT8183

[PATCH v2 0/8] media: mtk-vcodec: vdec: support for MT8183

[Alexandre Courbot]

Here is the second version is this patchset, although there has been such a
delay after the first one that probably nobody remembers it has even been sent.

This series adds support for the stateless API into mtk-vcodec, by first
separating the stateful ops into their own source file, and introducing a new
set of ops suitable for stateless decoding. As such, support for stateful
decoders should remain completely unaffected.

This series has been tested with both MT8183 and MT8173. Decoding was working
for both chips, and in the case of MT8173 no regression has been spotted.

v4l2-compliance is also passing, minor a problem when testing requests on
MT8183: the test tries to call S_EXT_CTRLS on the first available control,
which happens to be V4L2_CID_MIN_BUFFERS_FOR_CAPTURE. Since this control is
read-only, the driver returns -EACCESS. I suppose this is a problem with
v4l2-compliance and not the driver.

Alexandre Courbot (4):
  media: mtk-vcodec: vdec: handle firmware version field
  media: mtk-vcodec: support version 2 of decoder firmware ABI
  media: add Mediatek's MM21 format
  dt-bindings: media: document mediatek,mt8183-vcodec-dec

Yunfei Dong (4):
  media: mtk-vcodec: vdec: support stateless API
  media: mtk-vcodec: vdec: support stateless H.264 decoding
  media: mtk-vcodec: vdec: add media device if using stateless api
  media: mtk-vcodec: enable MT8183 decoder

 .../bindings/media/mediatek-vcodec.txt        |   1 +
 .../media/v4l/pixfmt-reserved.rst             |   7 +
 drivers/media/platform/Kconfig                |   2 +
 drivers/media/platform/mtk-vcodec/Makefile    |   2 +
 .../platform/mtk-vcodec/mtk_vcodec_dec.c      |  66 +-
 .../platform/mtk-vcodec/mtk_vcodec_dec.h      |   9 +-
 .../platform/mtk-vcodec/mtk_vcodec_dec_drv.c  |  44 +
 .../mtk-vcodec/mtk_vcodec_dec_stateful.c      |   1 +
 .../mtk-vcodec/mtk_vcodec_dec_stateless.c     | 427 +++++++++
 .../platform/mtk-vcodec/mtk_vcodec_drv.h      |   9 +
 .../mtk-vcodec/vdec/vdec_h264_req_if.c        | 808 ++++++++++++++++++
 .../media/platform/mtk-vcodec/vdec_drv_if.c   |   3 +
 .../media/platform/mtk-vcodec/vdec_drv_if.h   |   1 +
 .../media/platform/mtk-vcodec/vdec_ipi_msg.h  |  23 +-
 .../media/platform/mtk-vcodec/vdec_vpu_if.c   |  43 +-
 .../media/platform/mtk-vcodec/vdec_vpu_if.h   |   5 +
 drivers/media/v4l2-core/v4l2-ioctl.c          |   1 +
 include/uapi/linux/videodev2.h                |   1 +
 18 files changed, 1442 insertions(+), 11 deletions(-)
 create mode 100644 drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateless.c
 create mode 100644 drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_if.c

--
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 1/8] media: mtk-vcodec: vdec: handle firmware version field

[Alexandre Courbot]

Firmwares for decoders newer than MT8173 will include an ABI version
number in their initialization ack message. Add the capacity to manage
it and make initialization fail if the firmware ABI is of a version that
we don't support.

For MT8173, this ABI version field does not exist ; thus ignore it on
this chip. There should only be one firmware version available for it
anyway.

Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 .../mtk-vcodec/mtk_vcodec_dec_stateful.c      |  1 +
 .../platform/mtk-vcodec/mtk_vcodec_drv.h      |  4 ++++
 .../media/platform/mtk-vcodec/vdec_ipi_msg.h  |  5 +++++
 .../media/platform/mtk-vcodec/vdec_vpu_if.c   | 21 +++++++++++++++++--
 4 files changed, 29 insertions(+), 2 deletions(-)

diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateful.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateful.c
index 48b7524bc8fb..f9db7ef19c28 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateful.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateful.c
@@ -620,6 +620,7 @@ static struct vb2_ops mtk_vdec_frame_vb2_ops = {
 };
 
 const struct mtk_vcodec_dec_pdata mtk_vdec_8173_pdata = {
+	.chip = MTK_MT8173,
 	.init_vdec_params = mtk_init_vdec_params,
 	.ctrls_setup = mtk_vcodec_dec_ctrls_setup,
 	.vdec_vb2_ops = &mtk_vdec_frame_vb2_ops,
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
index 9221c17a176b..60bc39efa20d 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
@@ -322,6 +322,8 @@ enum mtk_chip {
  * @vdec_framesizes: supported video decoder frame sizes
  * @num_framesizes: count of video decoder frame sizes
  *
+ * @chip: chip this decoder is compatible with
+ *
  * @uses_stateless_api: whether the decoder uses the stateless API with requests
  */
 
@@ -341,6 +343,8 @@ struct mtk_vcodec_dec_pdata {
 	const struct mtk_codec_framesizes *vdec_framesizes;
 	const int num_framesizes;
 
+	enum mtk_chip chip;
+
 	bool uses_stateless_api;
 };
 
diff --git a/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h b/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h
index 47a1c1c0fd04..eb66729fda63 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h
+++ b/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h
@@ -83,12 +83,17 @@ struct vdec_ap_ipi_dec_start {
  * @status	: VPU exeuction result
  * @ap_inst_addr	: AP vcodec_vpu_inst instance address
  * @vpu_inst_addr	: VPU decoder instance address
+ * @vdec_abi_version:	ABI version of the firmware. Kernel can use it to
+ *			ensure that it is compatible with the firmware.
+ *			This field is not valid for MT8173 and must not be
+ *			accessed for this chip.
  */
 struct vdec_vpu_ipi_init_ack {
 	uint32_t msg_id;
 	int32_t status;
 	uint64_t ap_inst_addr;
 	uint32_t vpu_inst_addr;
+	uint32_t vdec_abi_version;
 };
 
 #endif
diff --git a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
index 58b0e6fa8fd2..203089213e67 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
@@ -24,6 +24,22 @@ static void handle_init_ack_msg(const struct vdec_vpu_ipi_init_ack *msg)
 	vpu->inst_addr = msg->vpu_inst_addr;
 
 	mtk_vcodec_debug(vpu, "- vpu_inst_addr = 0x%x", vpu->inst_addr);
+
+	/* Firmware version field does not exist on MT8173. */
+	if (vpu->ctx->dev->vdec_pdata->chip == MTK_MT8173)
+		return;
+
+	/* Check firmware version. */
+	mtk_vcodec_debug(vpu, "firmware version 0x%x\n", msg->vdec_abi_version);
+	switch (msg->vdec_abi_version) {
+	case 1:
+		break;
+	default:
+		mtk_vcodec_err(vpu, "unhandled firmware version 0x%x\n",
+			       msg->vdec_abi_version);
+		vpu->failure = 1;
+		break;
+	}
 }
 
 /*
@@ -44,6 +60,9 @@ static void vpu_dec_ipi_handler(void *data, unsigned int len, void *priv)
 
 	mtk_vcodec_debug(vpu, "+ id=%X", msg->msg_id);
 
+	vpu->failure = msg->status;
+	vpu->signaled = 1;
+
 	if (msg->status == 0) {
 		switch (msg->msg_id) {
 		case VPU_IPIMSG_DEC_INIT_ACK:
@@ -63,8 +82,6 @@ static void vpu_dec_ipi_handler(void *data, unsigned int len, void *priv)
 	}
 
 	mtk_vcodec_debug(vpu, "- id=%X", msg->msg_id);
-	vpu->failure = msg->status;
-	vpu->signaled = 1;
 }
 
 static int vcodec_vpu_send_msg(struct vdec_vpu_inst *vpu, void *msg, int len)
-- 
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 2/8] media: mtk-vcodec: support version 2 of decoder firmware ABI

[Alexandre Courbot]

Add support for decoder firmware version 2, which makes the kernel
responsible for managing the VSI context and is used for stateless
codecs.

Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 .../media/platform/mtk-vcodec/vdec_ipi_msg.h  | 18 +++++++++---
 .../media/platform/mtk-vcodec/vdec_vpu_if.c   | 28 +++++++++++++++----
 .../media/platform/mtk-vcodec/vdec_vpu_if.h   |  5 ++++
 3 files changed, 42 insertions(+), 9 deletions(-)

diff --git a/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h b/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h
index eb66729fda63..a0e773ae3ab3 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h
+++ b/drivers/media/platform/mtk-vcodec/vdec_ipi_msg.h
@@ -29,11 +29,15 @@ enum vdec_ipi_msgid {
 /**
  * struct vdec_ap_ipi_cmd - generic AP to VPU ipi command format
  * @msg_id	: vdec_ipi_msgid
- * @vpu_inst_addr	: VPU decoder instance address
+ * @vpu_inst_addr : VPU decoder instance address. Used if ABI version < 2.
+ * @inst_id     : instance ID. Used if the ABI version >= 2.
  */
 struct vdec_ap_ipi_cmd {
 	uint32_t msg_id;
-	uint32_t vpu_inst_addr;
+	union {
+		uint32_t vpu_inst_addr;
+		uint32_t inst_id;
+	};
 };
 
 /**
@@ -63,7 +67,8 @@ struct vdec_ap_ipi_init {
 /**
  * struct vdec_ap_ipi_dec_start - for AP_IPIMSG_DEC_START
  * @msg_id	: AP_IPIMSG_DEC_START
- * @vpu_inst_addr	: VPU decoder instance address
+ * @vpu_inst_addr : VPU decoder instance address. Used if ABI version < 2.
+ * @inst_id     : instance ID. Used if the ABI version >= 2.
  * @data	: Header info
  *	H264 decoder [0]:buf_sz [1]:nal_start
  *	VP8 decoder  [0]:width/height
@@ -72,7 +77,10 @@ struct vdec_ap_ipi_init {
  */
 struct vdec_ap_ipi_dec_start {
 	uint32_t msg_id;
-	uint32_t vpu_inst_addr;
+	union {
+		uint32_t vpu_inst_addr;
+		uint32_t inst_id;
+	};
 	uint32_t data[3];
 	uint32_t reserved;
 };
@@ -87,6 +95,7 @@ struct vdec_ap_ipi_dec_start {
  *			ensure that it is compatible with the firmware.
  *			This field is not valid for MT8173 and must not be
  *			accessed for this chip.
+ * @inst_id     : instance ID. Valid only if the ABI version >= 2.
  */
 struct vdec_vpu_ipi_init_ack {
 	uint32_t msg_id;
@@ -94,6 +103,7 @@ struct vdec_vpu_ipi_init_ack {
 	uint64_t ap_inst_addr;
 	uint32_t vpu_inst_addr;
 	uint32_t vdec_abi_version;
+	uint32_t inst_id;
 };
 
 #endif
diff --git a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
index 203089213e67..5dffc459a33d 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.c
@@ -25,18 +25,30 @@ static void handle_init_ack_msg(const struct vdec_vpu_ipi_init_ack *msg)
 
 	mtk_vcodec_debug(vpu, "- vpu_inst_addr = 0x%x", vpu->inst_addr);
 
+	/* Set default ABI version if dealing with unversioned firmware. */
+	vpu->fw_abi_version = 0;
+	/*
+	 * Instance ID is only used if ABI version >= 2. Initialize it with
+	 * garbage by default.
+	 */
+	vpu->inst_id = 0xdeadbeef;
+
 	/* Firmware version field does not exist on MT8173. */
 	if (vpu->ctx->dev->vdec_pdata->chip == MTK_MT8173)
 		return;
 
 	/* Check firmware version. */
-	mtk_vcodec_debug(vpu, "firmware version 0x%x\n", msg->vdec_abi_version);
-	switch (msg->vdec_abi_version) {
+	vpu->fw_abi_version = msg->vdec_abi_version;
+	mtk_vcodec_debug(vpu, "firmware version 0x%x\n", vpu->fw_abi_version);
+	switch (vpu->fw_abi_version) {
 	case 1:
 		break;
+	case 2:
+		vpu->inst_id = msg->inst_id;
+		break;
 	default:
 		mtk_vcodec_err(vpu, "unhandled firmware version 0x%x\n",
-			       msg->vdec_abi_version);
+			       vpu->fw_abi_version);
 		vpu->failure = 1;
 		break;
 	}
@@ -113,7 +125,10 @@ static int vcodec_send_ap_ipi(struct vdec_vpu_inst *vpu, unsigned int msg_id)
 
 	memset(&msg, 0, sizeof(msg));
 	msg.msg_id = msg_id;
-	msg.vpu_inst_addr = vpu->inst_addr;
+	if (vpu->fw_abi_version < 2)
+		msg.vpu_inst_addr = vpu->inst_addr;
+	else
+		msg.inst_id = vpu->inst_id;
 
 	err = vcodec_vpu_send_msg(vpu, &msg, sizeof(msg));
 	mtk_vcodec_debug(vpu, "- id=%X ret=%d", msg_id, err);
@@ -163,7 +178,10 @@ int vpu_dec_start(struct vdec_vpu_inst *vpu, uint32_t *data, unsigned int len)
 
 	memset(&msg, 0, sizeof(msg));
 	msg.msg_id = AP_IPIMSG_DEC_START;
-	msg.vpu_inst_addr = vpu->inst_addr;
+	if (vpu->fw_abi_version < 2)
+		msg.vpu_inst_addr = vpu->inst_addr;
+	else
+		msg.inst_id = vpu->inst_id;
 
 	for (i = 0; i < len; i++)
 		msg.data[i] = data[i];
diff --git a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h
index 85224eb7e34b..c2ed5b6cab8b 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h
+++ b/drivers/media/platform/mtk-vcodec/vdec_vpu_if.h
@@ -18,6 +18,9 @@ struct mtk_vcodec_ctx;
  *                for control and info share
  * @failure     : VPU execution result status, 0: success, others: fail
  * @inst_addr	: VPU decoder instance address
+ * @fw_abi_version : ABI version of the firmware.
+ * @inst_id	: if fw_abi_version >= 2, contains the instance ID to be given
+ *                in place of inst_addr in messages.
  * @signaled    : 1 - Host has received ack message from VPU, 0 - not received
  * @ctx         : context for v4l2 layer integration
  * @dev		: platform device of VPU
@@ -29,6 +32,8 @@ struct vdec_vpu_inst {
 	void *vsi;
 	int32_t failure;
 	uint32_t inst_addr;
+	uint32_t fw_abi_version;
+	uint32_t inst_id;
 	unsigned int signaled;
 	struct mtk_vcodec_ctx *ctx;
 	wait_queue_head_t wq;
-- 
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 3/8] media: add Mediatek's MM21 format

[Alexandre Courbot]

Add Mediatek's non-compressed 8 bit block video mode. This format is
produced by the MT8183 codec and can be converted to a non-proprietary
format by the MDP3 component.

Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 7 +++++++
 drivers/media/v4l2-core/v4l2-ioctl.c                      | 1 +
 include/uapi/linux/videodev2.h                            | 1 +
 3 files changed, 9 insertions(+)

diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
index c9231e18859b..187ea89f7a25 100644
--- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
+++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
@@ -242,6 +242,13 @@ please make a proposal on the linux-media mailing list.
 	It is an opaque intermediate format and the MDP hardware must be
 	used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``,
 	``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``.
+    * .. _V4L2-PIX-FMT-MM21:
+
+      - ``V4L2_PIX_FMT_MM21``
+      - 'MM21'
+      - Non-compressed, tiled two-planar format used by Mediatek MT8183.
+	This is an opaque intermediate format and the MDP3 hardware can be
+	used to convert it to other formats.
     * .. _V4L2-PIX-FMT-SUNXI-TILED-NV12:
 
       - ``V4L2_PIX_FMT_SUNXI_TILED_NV12``
diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-core/v4l2-ioctl.c
index 31d1342e61e8..0b85b2bbc628 100644
--- a/drivers/media/v4l2-core/v4l2-ioctl.c
+++ b/drivers/media/v4l2-core/v4l2-ioctl.c
@@ -1384,6 +1384,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
 	case V4L2_PIX_FMT_TM6000:	descr = "A/V + VBI Mux Packet"; break;
 	case V4L2_PIX_FMT_CIT_YYVYUY:	descr = "GSPCA CIT YYVYUY"; break;
 	case V4L2_PIX_FMT_KONICA420:	descr = "GSPCA KONICA420"; break;
+	case V4L2_PIX_FMT_MM21:		descr = "Mediatek 8-bit block format"; break;
 	case V4L2_PIX_FMT_HSV24:	descr = "24-bit HSV 8-8-8"; break;
 	case V4L2_PIX_FMT_HSV32:	descr = "32-bit XHSV 8-8-8-8"; break;
 	case V4L2_SDR_FMT_CU8:		descr = "Complex U8"; break;
diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
index 79dbde3bcf8d..e6890dae76ec 100644
--- a/include/uapi/linux/videodev2.h
+++ b/include/uapi/linux/videodev2.h
@@ -731,6 +731,7 @@ struct v4l2_pix_format {
 #define V4L2_PIX_FMT_Y12I     v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale 12-bit L/R interleaved */
 #define V4L2_PIX_FMT_Z16      v4l2_fourcc('Z', '1', '6', ' ') /* Depth data 16-bit */
 #define V4L2_PIX_FMT_MT21C    v4l2_fourcc('M', 'T', '2', '1') /* Mediatek compressed block mode  */
+#define V4L2_PIX_FMT_MM21     v4l2_fourcc('M', 'M', '2', '1') /* Mediatek 8-bit block mode, two non-contiguous planes */
 #define V4L2_PIX_FMT_INZI     v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar Greyscale 10-bit and Depth 16-bit */
 #define V4L2_PIX_FMT_SUNXI_TILED_NV12 v4l2_fourcc('S', 'T', '1', '2') /* Sunxi Tiled NV12 Format */
 #define V4L2_PIX_FMT_CNF4     v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit packed depth confidence information */
-- 
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 4/8] media: mtk-vcodec: vdec: support stateless API

[Alexandre Courbot]

From: Yunfei Dong <yunfei.dong@mediatek.com>

Support the stateless codec API that will be used by MT8183.

Signed-off-by: Yunfei Dong <yunfei.dong@mediatek.com>
[acourbot: refactor, cleanup and split]
Co-developed-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 drivers/media/platform/mtk-vcodec/Makefile    |   1 +
 .../platform/mtk-vcodec/mtk_vcodec_dec.c      |  66 ++-
 .../platform/mtk-vcodec/mtk_vcodec_dec.h      |   9 +-
 .../mtk-vcodec/mtk_vcodec_dec_stateless.c     | 427 ++++++++++++++++++
 .../platform/mtk-vcodec/mtk_vcodec_drv.h      |   3 +
 5 files changed, 503 insertions(+), 3 deletions(-)
 create mode 100644 drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateless.c

diff --git a/drivers/media/platform/mtk-vcodec/Makefile b/drivers/media/platform/mtk-vcodec/Makefile
index 9c3cbb5b800e..4ba93d838ab6 100644
--- a/drivers/media/platform/mtk-vcodec/Makefile
+++ b/drivers/media/platform/mtk-vcodec/Makefile
@@ -12,6 +12,7 @@ mtk-vcodec-dec-y := vdec/vdec_h264_if.o \
 		vdec_vpu_if.o \
 		mtk_vcodec_dec.o \
 		mtk_vcodec_dec_stateful.o \
+		mtk_vcodec_dec_stateless.o \
 		mtk_vcodec_dec_pm.o \
 
 mtk-vcodec-enc-y := venc/venc_vp8_if.o \
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
index 4a91d294002b..c286cc0f239f 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.c
@@ -46,6 +46,13 @@ static struct mtk_q_data *mtk_vdec_get_q_data(struct mtk_vcodec_ctx *ctx,
 static int vidioc_try_decoder_cmd(struct file *file, void *priv,
 				struct v4l2_decoder_cmd *cmd)
 {
+	struct mtk_vcodec_ctx *ctx = fh_to_ctx(priv);
+
+	/* Use M2M stateless helper if relevant */
+	if (ctx->dev->vdec_pdata->uses_stateless_api)
+		return v4l2_m2m_ioctl_stateless_try_decoder_cmd(file, priv,
+								cmd);
+
 	switch (cmd->cmd) {
 	case V4L2_DEC_CMD_STOP:
 	case V4L2_DEC_CMD_START:
@@ -72,6 +79,10 @@ static int vidioc_decoder_cmd(struct file *file, void *priv,
 	if (ret)
 		return ret;
 
+	/* Use M2M stateless helper if relevant */
+	if (ctx->dev->vdec_pdata->uses_stateless_api)
+		return v4l2_m2m_ioctl_stateless_decoder_cmd(file, priv, cmd);
+
 	mtk_v4l2_debug(1, "decoder cmd=%u", cmd->cmd);
 	dst_vq = v4l2_m2m_get_vq(ctx->m2m_ctx,
 				V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE);
@@ -414,7 +425,8 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv,
 	 * Setting OUTPUT format after OUTPUT buffers are allocated is invalid
 	 * if using the stateful API.
 	 */
-	if ((f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) &&
+	if (!dec_pdata->uses_stateless_api &&
+	    (f->type == V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE) &&
 	    vb2_is_busy(&ctx->m2m_ctx->out_q_ctx.q)) {
 		mtk_v4l2_err("out_q_ctx buffers already requested");
 		ret = -EBUSY;
@@ -457,6 +469,7 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv,
 		ctx->quantization = pix_mp->quantization;
 		ctx->xfer_func = pix_mp->xfer_func;
 
+		ctx->current_codec = fmt->fourcc;
 		if (ctx->state == MTK_STATE_FREE) {
 			ret = vdec_if_init(ctx, q_data->fmt->fourcc);
 			if (ret) {
@@ -468,6 +481,49 @@ static int vidioc_vdec_s_fmt(struct file *file, void *priv,
 		}
 	}
 
+	/*
+	 * If using the stateless API, S_FMT should have the effect of setting
+	 * the CAPTURE queue resolution no matter which queue it was called on.
+	 */
+	if (dec_pdata->uses_stateless_api) {
+		ctx->picinfo.pic_w = pix_mp->width;
+		ctx->picinfo.pic_h = pix_mp->height;
+
+		ret = vdec_if_get_param(ctx, GET_PARAM_PIC_INFO, &ctx->picinfo);
+		if (ret) {
+			mtk_v4l2_err("[%d]Error!! Get GET_PARAM_PICTURE_INFO Fail",
+				ctx->id);
+			return -EINVAL;
+		}
+
+		ctx->last_decoded_picinfo = ctx->picinfo;
+
+		if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 1) {
+			ctx->q_data[MTK_Q_DATA_DST].sizeimage[0] =
+				ctx->picinfo.fb_sz[0] +
+				ctx->picinfo.fb_sz[1];
+			ctx->q_data[MTK_Q_DATA_DST].bytesperline[0] =
+				ctx->picinfo.buf_w;
+		} else {
+			ctx->q_data[MTK_Q_DATA_DST].sizeimage[0] =
+				ctx->picinfo.fb_sz[0];
+			ctx->q_data[MTK_Q_DATA_DST].bytesperline[0] =
+				ctx->picinfo.buf_w;
+			ctx->q_data[MTK_Q_DATA_DST].sizeimage[1] =
+				ctx->picinfo.fb_sz[1];
+			ctx->q_data[MTK_Q_DATA_DST].bytesperline[1] =
+				ctx->picinfo.buf_w;
+		}
+
+		ctx->q_data[MTK_Q_DATA_DST].coded_width = ctx->picinfo.buf_w;
+		ctx->q_data[MTK_Q_DATA_DST].coded_height = ctx->picinfo.buf_h;
+		mtk_v4l2_debug(2, "[%d] vdec_if_init() num_plane = %d wxh=%dx%d pic wxh=%dx%d sz[0]=0x%x sz[1]=0x%x",
+			ctx->id, pix_mp->num_planes,
+			ctx->picinfo.buf_w, ctx->picinfo.buf_h,
+			ctx->picinfo.pic_w, ctx->picinfo.pic_h,
+			ctx->q_data[MTK_Q_DATA_DST].sizeimage[0],
+			ctx->q_data[MTK_Q_DATA_DST].sizeimage[1]);
+	}
 	return 0;
 }
 
@@ -765,9 +821,15 @@ void vb2ops_vdec_stop_streaming(struct vb2_queue *q)
 		while ((src_buf = v4l2_m2m_src_buf_remove(ctx->m2m_ctx))) {
 			struct mtk_video_dec_buf *buf_info = container_of(
 				 src_buf, struct mtk_video_dec_buf, m2m_buf.vb);
-			if (!buf_info->lastframe)
+			if (!buf_info->lastframe) {
+				struct media_request *req =
+					src_buf->vb2_buf.req_obj.req;
 				v4l2_m2m_buf_done(src_buf,
 						VB2_BUF_STATE_ERROR);
+				if (req)
+					v4l2_ctrl_request_complete(req,
+								&ctx->ctrl_hdl);
+			}
 		}
 		return;
 	}
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h
index 97a8304f6600..a2949e1bc7fe 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec.h
@@ -45,6 +45,7 @@ struct vdec_fb {
  * @lastframe:		Intput buffer is last buffer - EOS
  * @error:		An unrecoverable error occurs on this buffer.
  * @frame_buffer:	Decode status, and buffer information of Capture buffer
+ * @bs_buffer:	Output buffer info
  *
  * Note : These status information help us track and debug buffer state
  */
@@ -55,12 +56,18 @@ struct mtk_video_dec_buf {
 	bool	queued_in_vb2;
 	bool	queued_in_v4l2;
 	bool	lastframe;
+
 	bool	error;
-	struct vdec_fb	frame_buffer;
+
+	union {
+		struct vdec_fb	frame_buffer;
+		struct mtk_vcodec_mem	bs_buffer;
+	};
 };
 
 extern const struct v4l2_ioctl_ops mtk_vdec_ioctl_ops;
 extern const struct v4l2_m2m_ops mtk_vdec_m2m_ops;
+extern const struct media_device_ops mtk_vcodec_media_ops;
 
 
 /*
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateless.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateless.c
new file mode 100644
index 000000000000..e2e08f54109b
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_stateless.c
@@ -0,0 +1,427 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "media/videobuf2-v4l2.h"
+#include <media/videobuf2-dma-contig.h>
+#include <media/v4l2-event.h>
+#include <media/v4l2-mem2mem.h>
+#include <linux/module.h>
+
+#include "mtk_vcodec_drv.h"
+#include "mtk_vcodec_dec.h"
+#include "mtk_vcodec_intr.h"
+#include "mtk_vcodec_util.h"
+#include "vdec_drv_if.h"
+#include "mtk_vcodec_dec_pm.h"
+
+/**
+ * struct mtk_stateless_control  - CID control type
+ * @cfg: Control configuration
+ * @codec_type: codec type (V4L2 pixel format) for CID control type
+ * @needed_in_request: whether the control must be present with each request
+ */
+struct mtk_stateless_control {
+	struct v4l2_ctrl_config cfg;
+	int codec_type;
+	bool needed_in_request;
+};
+
+static const struct mtk_stateless_control mtk_stateless_controls[] = {
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_H264_SPS,
+		},
+		.codec_type = V4L2_PIX_FMT_H264_SLICE,
+		.needed_in_request = true,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_H264_PPS,
+		},
+		.codec_type = V4L2_PIX_FMT_H264_SLICE,
+		.needed_in_request = true,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_H264_SCALING_MATRIX,
+		},
+		.codec_type = V4L2_PIX_FMT_H264_SLICE,
+		.needed_in_request = true,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_H264_DECODE_PARAMS,
+		},
+		.codec_type = V4L2_PIX_FMT_H264_SLICE,
+		.needed_in_request = true,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_MPEG_VIDEO_H264_PROFILE,
+			.def = V4L2_MPEG_VIDEO_H264_PROFILE_MAIN,
+			.max = V4L2_MPEG_VIDEO_H264_PROFILE_HIGH,
+			.menu_skip_mask =
+				BIT(V4L2_MPEG_VIDEO_H264_PROFILE_BASELINE) |
+				BIT(V4L2_MPEG_VIDEO_H264_PROFILE_EXTENDED),
+		},
+		.codec_type = V4L2_PIX_FMT_H264_SLICE,
+	},
+	{
+		.cfg = {
+			.id = V4L2_CID_STATELESS_H264_DECODE_MODE,
+			.min = V4L2_STATELESS_H264_DECODE_MODE_FRAME_BASED,
+			.def = V4L2_STATELESS_H264_DECODE_MODE_FRAME_BASED,
+			.max = V4L2_STATELESS_H264_DECODE_MODE_FRAME_BASED,
+		},
+		.codec_type = V4L2_PIX_FMT_H264_SLICE,
+	},
+};
+#define NUM_CTRLS ARRAY_SIZE(mtk_stateless_controls)
+
+static const struct mtk_video_fmt mtk_video_formats[] = {
+	{
+		.fourcc = V4L2_PIX_FMT_H264_SLICE,
+		.type = MTK_FMT_DEC,
+		.num_planes = 1,
+	},
+	{
+		.fourcc = V4L2_PIX_FMT_MM21,
+		.type = MTK_FMT_FRAME,
+		.num_planes = 2,
+	},
+};
+#define NUM_FORMATS ARRAY_SIZE(mtk_video_formats)
+#define DEFAULT_OUT_FMT_IDX    0
+#define DEFAULT_CAP_FMT_IDX    1
+
+static const struct mtk_codec_framesizes mtk_vdec_framesizes[] = {
+	{
+		.fourcc	= V4L2_PIX_FMT_H264_SLICE,
+		.stepwise = {
+			MTK_VDEC_MIN_W, MTK_VDEC_MAX_W, 16,
+			MTK_VDEC_MIN_H, MTK_VDEC_MAX_H, 16,
+		},
+	},
+};
+
+#define NUM_SUPPORTED_FRAMESIZE ARRAY_SIZE(mtk_vdec_framesizes)
+
+static void mtk_vdec_stateless_set_dst_payload(struct mtk_vcodec_ctx *ctx,
+					       struct vdec_fb *fb)
+{
+	struct mtk_video_dec_buf *vdec_frame_buf =
+		container_of(fb, struct mtk_video_dec_buf, frame_buffer);
+	struct vb2_v4l2_buffer *vb = &vdec_frame_buf->m2m_buf.vb;
+	unsigned int cap_y_size = ctx->q_data[MTK_Q_DATA_DST].sizeimage[0];
+
+	vb2_set_plane_payload(&vb->vb2_buf, 0, cap_y_size);
+	if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) {
+		unsigned int cap_c_size =
+			ctx->q_data[MTK_Q_DATA_DST].sizeimage[1];
+
+		vb2_set_plane_payload(&vb->vb2_buf, 1, cap_c_size);
+	}
+}
+
+static struct vdec_fb *vdec_get_cap_buffer(struct mtk_vcodec_ctx *ctx,
+					   struct vb2_v4l2_buffer *vb2_v4l2)
+{
+	struct mtk_video_dec_buf *framebuf =
+		container_of(vb2_v4l2, struct mtk_video_dec_buf, m2m_buf.vb);
+	struct vdec_fb *pfb = &framebuf->frame_buffer;
+	struct vb2_buffer *dst_buf = &vb2_v4l2->vb2_buf;
+
+	pfb = &framebuf->frame_buffer;
+	pfb->base_y.va = vb2_plane_vaddr(dst_buf, 0);
+	pfb->base_y.dma_addr = vb2_dma_contig_plane_dma_addr(dst_buf, 0);
+	pfb->base_y.size = ctx->q_data[MTK_Q_DATA_DST].sizeimage[0];
+
+	if (ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) {
+		pfb->base_c.va = vb2_plane_vaddr(dst_buf, 1);
+		pfb->base_c.dma_addr =
+			vb2_dma_contig_plane_dma_addr(dst_buf, 1);
+		pfb->base_c.size = ctx->q_data[MTK_Q_DATA_DST].sizeimage[1];
+	}
+	mtk_v4l2_debug(1,
+		"id=%d Framebuf  pfb=%p VA=%p Y_DMA=%pad C_DMA=%pad Size=%zx frame_count = %d",
+		dst_buf->index, pfb,
+		pfb->base_y.va, &pfb->base_y.dma_addr,
+		&pfb->base_c.dma_addr, pfb->base_y.size,
+		ctx->decoded_frame_cnt);
+
+	return pfb;
+}
+
+static void vb2ops_vdec_buf_request_complete(struct vb2_buffer *vb)
+{
+	struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+
+	v4l2_ctrl_request_complete(vb->req_obj.req, &ctx->ctrl_hdl);
+}
+
+static int fops_media_request_validate(struct media_request *mreq)
+{
+	const unsigned int buffer_cnt = vb2_request_buffer_cnt(mreq);
+	struct mtk_vcodec_ctx *ctx = NULL;
+	struct media_request_object *req_obj;
+	struct v4l2_ctrl_handler *parent_hdl, *hdl;
+	struct v4l2_ctrl *ctrl;
+	unsigned int i;
+
+	switch (buffer_cnt) {
+	case 1:
+		/* We expect exactly one buffer with the request */
+		break;
+	case 0:
+		mtk_v4l2_err("No buffer provided with the request");
+		return -ENOENT;
+	default:
+		mtk_v4l2_err("Too many buffers (%d) provided with the request",
+			     buffer_cnt);
+		return -EINVAL;
+	}
+
+	list_for_each_entry(req_obj, &mreq->objects, list) {
+		struct vb2_buffer *vb;
+
+		if (vb2_request_object_is_buffer(req_obj)) {
+			vb = container_of(req_obj, struct vb2_buffer, req_obj);
+			ctx = vb2_get_drv_priv(vb->vb2_queue);
+			break;
+		}
+	}
+
+	if (!ctx) {
+		mtk_v4l2_err("Cannot find buffer for request");
+		return -ENOENT;
+	}
+
+	parent_hdl = &ctx->ctrl_hdl;
+
+	hdl = v4l2_ctrl_request_hdl_find(mreq, parent_hdl);
+	if (!hdl) {
+		mtk_v4l2_err("Cannot find control handler for request\n");
+		return -ENOENT;
+	}
+
+	for (i = 0; i < NUM_CTRLS; i++) {
+		if (mtk_stateless_controls[i].codec_type != ctx->current_codec)
+			continue;
+		if (!mtk_stateless_controls[i].needed_in_request)
+			continue;
+
+		ctrl = v4l2_ctrl_request_hdl_ctrl_find(hdl,
+					  mtk_stateless_controls[i].cfg.id);
+		if (!ctrl) {
+			mtk_v4l2_err("Missing required codec control\n");
+			return -ENOENT;
+		}
+	}
+
+	v4l2_ctrl_request_hdl_put(hdl);
+
+	return vb2_request_validate(mreq);
+}
+
+static void mtk_vdec_worker(struct work_struct *work)
+{
+	struct mtk_vcodec_ctx *ctx =
+		container_of(work, struct mtk_vcodec_ctx, decode_work);
+	struct mtk_vcodec_dev *dev = ctx->dev;
+	struct vb2_v4l2_buffer *vb2_v4l2_src, *vb2_v4l2_dst;
+	struct vb2_buffer *vb2_src;
+	struct mtk_vcodec_mem *bs_src;
+	struct mtk_video_dec_buf *dec_buf_src;
+	struct media_request *src_buf_req;
+	struct vdec_fb *dst_buf;
+	bool res_chg = false;
+	int ret;
+
+	vb2_v4l2_src = v4l2_m2m_next_src_buf(ctx->m2m_ctx);
+	if (vb2_v4l2_src == NULL) {
+		v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx);
+		mtk_v4l2_debug(1, "[%d] no available source buffer", ctx->id);
+		return;
+	}
+
+	vb2_v4l2_dst = v4l2_m2m_next_dst_buf(ctx->m2m_ctx);
+	if (vb2_v4l2_dst == NULL) {
+		v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx);
+		mtk_v4l2_debug(1, "[%d] no available destination buffer", ctx->id);
+		return;
+	}
+
+	vb2_src = &vb2_v4l2_src->vb2_buf;
+	dec_buf_src = container_of(vb2_v4l2_src, struct mtk_video_dec_buf,
+				   m2m_buf.vb);
+	bs_src = &dec_buf_src->bs_buffer;
+
+	mtk_v4l2_debug(3, "[%d] (%d) id=%d, vb=%p buf_info = %p",
+			ctx->id, src_buf->vb2_queue->type,
+			src_buf->index, src_buf, src_buf_info);
+
+	bs_src->va = vb2_plane_vaddr(vb2_src, 0);
+	bs_src->dma_addr = vb2_dma_contig_plane_dma_addr(vb2_src, 0);
+	bs_src->size = (size_t)vb2_src->planes[0].bytesused;
+	if (!bs_src->va) {
+		v4l2_m2m_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx);
+		mtk_v4l2_err("[%d] id=%d source buffer is NULL", ctx->id,
+			     vb2_src->index);
+		return;
+	}
+
+	mtk_v4l2_debug(3, "[%d] Bitstream VA=%p DMA=%pad Size=%zx vb=%p",
+			ctx->id, buf->va, &buf->dma_addr, buf->size, src_buf);
+	/* Apply request controls. */
+	src_buf_req = vb2_src->req_obj.req;
+	if (src_buf_req)
+		v4l2_ctrl_request_setup(src_buf_req, &ctx->ctrl_hdl);
+	else
+		mtk_v4l2_err("vb2 buffer media request is NULL");
+
+	dst_buf = vdec_get_cap_buffer(ctx, vb2_v4l2_dst);
+	v4l2_m2m_buf_copy_metadata(vb2_v4l2_src, vb2_v4l2_dst, true);
+	ret = vdec_if_decode(ctx, bs_src, dst_buf, &res_chg);
+	if (ret) {
+		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);
+		if (ret == -EIO) {
+			mutex_lock(&ctx->lock);
+			dec_buf_src->error = true;
+			mutex_unlock(&ctx->lock);
+		}
+	}
+
+	mtk_vdec_stateless_set_dst_payload(ctx, dst_buf);
+
+	v4l2_m2m_buf_done_and_job_finish(dev->m2m_dev_dec, ctx->m2m_ctx,
+		ret ? VB2_BUF_STATE_ERROR : VB2_BUF_STATE_DONE);
+
+	v4l2_ctrl_request_complete(src_buf_req, &ctx->ctrl_hdl);
+}
+
+static void vb2ops_vdec_stateless_buf_queue(struct vb2_buffer *vb)
+{
+	struct mtk_vcodec_ctx *ctx = vb2_get_drv_priv(vb->vb2_queue);
+	struct vb2_v4l2_buffer *vb2_v4l2 = to_vb2_v4l2_buffer(vb);
+
+	mtk_v4l2_debug(3, "[%d] (%d) id=%d, vb=%p",
+			ctx->id, vb->vb2_queue->type,
+			vb->index, vb);
+
+	mutex_lock(&ctx->lock);
+	v4l2_m2m_buf_queue(ctx->m2m_ctx, vb2_v4l2);
+	mutex_unlock(&ctx->lock);
+	if (vb->vb2_queue->type != V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE)
+		return;
+
+	mtk_v4l2_debug(3, "(%d) id=%d, bs=%p",
+		vb->vb2_queue->type, vb->index, src_buf);
+
+	/* If an OUTPUT buffer, we may need to update the state */
+	if (ctx->state == MTK_STATE_INIT) {
+		ctx->state = MTK_STATE_HEADER;
+		mtk_v4l2_debug(1, "Init driver from init to header.");
+	} else {
+		mtk_v4l2_debug(3, "[%d] already init driver %d",
+				ctx->id, ctx->state);
+	}
+}
+
+static int mtk_vdec_flush_decoder(struct mtk_vcodec_ctx *ctx)
+{
+	bool res_chg;
+
+	return vdec_if_decode(ctx, NULL, NULL, &res_chg);
+}
+
+static const struct v4l2_ctrl_ops mtk_vcodec_dec_ctrl_ops = {
+	.g_volatile_ctrl = mtk_vdec_g_v_ctrl,
+};
+
+static int mtk_vcodec_dec_ctrls_setup(struct mtk_vcodec_ctx *ctx)
+{
+	struct v4l2_ctrl *ctrl;
+	unsigned int i;
+
+	v4l2_ctrl_handler_init(&ctx->ctrl_hdl, NUM_CTRLS);
+	if (ctx->ctrl_hdl.error) {
+		mtk_v4l2_err("v4l2_ctrl_handler_init failed\n");
+		return ctx->ctrl_hdl.error;
+	}
+
+	ctrl = v4l2_ctrl_new_std(&ctx->ctrl_hdl,
+				&mtk_vcodec_dec_ctrl_ops,
+				V4L2_CID_MIN_BUFFERS_FOR_CAPTURE,
+				0, 32, 1, 1);
+	ctrl->flags |= V4L2_CTRL_FLAG_VOLATILE;
+
+	for (i = 0; i < NUM_CTRLS; i++) {
+		struct v4l2_ctrl_config cfg = mtk_stateless_controls[i].cfg;
+
+		v4l2_ctrl_new_custom(&ctx->ctrl_hdl, &cfg, NULL);
+		if (ctx->ctrl_hdl.error) {
+			mtk_v4l2_err("Adding control %d failed %d",
+					i, ctx->ctrl_hdl.error);
+			return ctx->ctrl_hdl.error;
+		}
+	}
+
+	v4l2_ctrl_handler_setup(&ctx->ctrl_hdl);
+
+	return 0;
+}
+
+const struct media_device_ops mtk_vcodec_media_ops = {
+	.req_validate	= fops_media_request_validate,
+	.req_queue	= v4l2_m2m_request_queue,
+};
+
+static void mtk_init_vdec_params(struct mtk_vcodec_ctx *ctx)
+{
+	struct vb2_queue *src_vq;
+
+	src_vq = v4l2_m2m_get_vq(ctx->m2m_ctx,
+				 V4L2_BUF_TYPE_VIDEO_OUTPUT_MPLANE);
+
+	/* Support request api for output plane */
+	src_vq->supports_requests = true;
+	src_vq->requires_requests = true;
+}
+
+static int vb2ops_vdec_out_buf_validate(struct vb2_buffer *vb)
+{
+	return 0;
+}
+
+static struct vb2_ops mtk_vdec_request_vb2_ops = {
+	.queue_setup	= vb2ops_vdec_queue_setup,
+	.buf_prepare	= vb2ops_vdec_buf_prepare,
+	.wait_prepare	= vb2_ops_wait_prepare,
+	.wait_finish	= vb2_ops_wait_finish,
+	.start_streaming	= vb2ops_vdec_start_streaming,
+
+	.buf_queue	= vb2ops_vdec_stateless_buf_queue,
+	.buf_out_validate = vb2ops_vdec_out_buf_validate,
+	.buf_init	= vb2ops_vdec_buf_init,
+	.buf_finish	= vb2ops_vdec_buf_finish,
+	.stop_streaming	= vb2ops_vdec_stop_streaming,
+	.buf_request_complete = vb2ops_vdec_buf_request_complete,
+};
+
+const struct mtk_vcodec_dec_pdata mtk_vdec_8183_pdata = {
+	.chip = MTK_MT8183,
+	.init_vdec_params = mtk_init_vdec_params,
+	.ctrls_setup = mtk_vcodec_dec_ctrls_setup,
+	.vdec_vb2_ops = &mtk_vdec_request_vb2_ops,
+	.vdec_formats = mtk_video_formats,
+	.num_formats = NUM_FORMATS,
+	.default_out_fmt = &mtk_video_formats[DEFAULT_OUT_FMT_IDX],
+	.default_cap_fmt = &mtk_video_formats[DEFAULT_CAP_FMT_IDX],
+	.vdec_framesizes = mtk_vdec_framesizes,
+	.num_framesizes = NUM_SUPPORTED_FRAMESIZE,
+	.uses_stateless_api = true,
+	.worker = mtk_vdec_worker,
+	.flush_decoder = mtk_vdec_flush_decoder,
+};
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
index 60bc39efa20d..3b884a321883 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
@@ -251,6 +251,7 @@ struct vdec_pic_info {
  * @encode_work: worker for the encoding
  * @last_decoded_picinfo: pic information get from latest decode
  * @empty_flush_buf: a fake size-0 capture buffer that indicates flush
+ * @current_codec: current set input codec, in V4L2 pixel format
  *
  * @colorspace: enum v4l2_colorspace; supplemental to pixelformat
  * @ycbcr_enc: enum v4l2_ycbcr_encoding, Y'CbCr encoding
@@ -290,6 +291,8 @@ struct mtk_vcodec_ctx {
 	struct vdec_pic_info last_decoded_picinfo;
 	struct mtk_video_dec_buf *empty_flush_buf;
 
+	u32 current_codec;
+
 	enum v4l2_colorspace colorspace;
 	enum v4l2_ycbcr_encoding ycbcr_enc;
 	enum v4l2_quantization quantization;
-- 
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 5/8] media: mtk-vcodec: vdec: support stateless H.264 decoding

[Alexandre Courbot]

From: Yunfei Dong <yunfei.dong@mediatek.com>

Add support for H.264 decoding using the stateless API, as supported by
MT8183. This support takes advantage of the V4L2 H.264 reference list
builders.

Signed-off-by: Yunfei Dong <yunfei.dong@mediatek.com>
[acourbot: refactor, cleanup and split]
Co-developed-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 drivers/media/platform/Kconfig                |   1 +
 drivers/media/platform/mtk-vcodec/Makefile    |   1 +
 .../mtk-vcodec/vdec/vdec_h264_req_if.c        | 808 ++++++++++++++++++
 .../media/platform/mtk-vcodec/vdec_drv_if.c   |   3 +
 .../media/platform/mtk-vcodec/vdec_drv_if.h   |   1 +
 5 files changed, 814 insertions(+)
 create mode 100644 drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_if.c

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index fd1831e97b22..c27db5643712 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -295,6 +295,7 @@ config VIDEO_MEDIATEK_VCODEC
 	select V4L2_MEM2MEM_DEV
 	select VIDEO_MEDIATEK_VCODEC_VPU if VIDEO_MEDIATEK_VPU
 	select VIDEO_MEDIATEK_VCODEC_SCP if MTK_SCP
+	select V4L2_H264
 	help
 	  Mediatek video codec driver provides HW capability to
 	  encode and decode in a range of video formats on MT8173
diff --git a/drivers/media/platform/mtk-vcodec/Makefile b/drivers/media/platform/mtk-vcodec/Makefile
index 4ba93d838ab6..ca8e9e7a9c4e 100644
--- a/drivers/media/platform/mtk-vcodec/Makefile
+++ b/drivers/media/platform/mtk-vcodec/Makefile
@@ -7,6 +7,7 @@ obj-$(CONFIG_VIDEO_MEDIATEK_VCODEC) += mtk-vcodec-dec.o \
 mtk-vcodec-dec-y := vdec/vdec_h264_if.o \
 		vdec/vdec_vp8_if.o \
 		vdec/vdec_vp9_if.o \
+		vdec/vdec_h264_req_if.o \
 		mtk_vcodec_dec_drv.o \
 		vdec_drv_if.o \
 		vdec_vpu_if.o \
diff --git a/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_if.c b/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_if.c
new file mode 100644
index 000000000000..8becc73fae35
--- /dev/null
+++ b/drivers/media/platform/mtk-vcodec/vdec/vdec_h264_req_if.c
@@ -0,0 +1,808 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <media/v4l2-mem2mem.h>
+#include <media/h264-ctrls.h>
+#include <media/v4l2-h264.h>
+#include <media/videobuf2-dma-contig.h>
+
+#include "../vdec_drv_if.h"
+#include "../mtk_vcodec_util.h"
+#include "../mtk_vcodec_dec.h"
+#include "../mtk_vcodec_intr.h"
+#include "../vdec_vpu_if.h"
+#include "../vdec_drv_base.h"
+
+#define NAL_NON_IDR_SLICE			0x01
+#define NAL_IDR_SLICE				0x05
+#define NAL_H264_PPS				0x08
+#define NAL_TYPE(value)				((value) & 0x1F)
+
+#define BUF_PREDICTION_SZ			(64 * 4096)
+#define MB_UNIT_LEN				16
+
+/* get used parameters for sps/pps */
+#define GET_MTK_VDEC_FLAG(cond, flag) \
+	{ dst_param->cond = ((src_param->flags & flag) ? (1) : (0)) }
+#define GET_MTK_VDEC_PARAM(param) \
+	{ dst_param->param = src_param->param }
+/* motion vector size (bytes) for every macro block */
+#define HW_MB_STORE_SZ				64
+
+#define H264_MAX_FB_NUM				17
+#define H264_MAX_MV_NUM				32
+#define HDR_PARSING_BUF_SZ			1024
+
+/**
+ * struct mtk_h264_dpb_info  - h264 dpb information
+ * @y_dma_addr: Y bitstream physical address
+ * @c_dma_addr: CbCr bitstream physical address
+ * @reference_flag: reference picture flag (short/long term reference picture)
+ * @field: field picture flag
+ */
+struct mtk_h264_dpb_info {
+	dma_addr_t y_dma_addr;
+	dma_addr_t c_dma_addr;
+	int reference_flag;
+	int field;
+};
+
+/**
+ * struct mtk_h264_sps_param  - parameters for sps
+ */
+struct mtk_h264_sps_param {
+	unsigned char chroma_format_idc;
+	unsigned char bit_depth_luma_minus8;
+	unsigned char bit_depth_chroma_minus8;
+	unsigned char log2_max_frame_num_minus4;
+	unsigned char pic_order_cnt_type;
+	unsigned char log2_max_pic_order_cnt_lsb_minus4;
+	unsigned char max_num_ref_frames;
+	unsigned char separate_colour_plane_flag;
+	unsigned short pic_width_in_mbs_minus1;
+	unsigned short pic_height_in_map_units_minus1;
+	unsigned int max_frame_nums;
+	unsigned char qpprime_y_zero_transform_bypass_flag;
+	unsigned char delta_pic_order_always_zero_flag;
+	unsigned char frame_mbs_only_flag;
+	unsigned char mb_adaptive_frame_field_flag;
+	unsigned char direct_8x8_inference_flag;
+	unsigned char reserved[3];
+};
+
+/**
+ * struct mtk_h264_pps_param  - parameters for pps
+ */
+struct mtk_h264_pps_param {
+	unsigned char num_ref_idx_l0_default_active_minus1;
+	unsigned char num_ref_idx_l1_default_active_minus1;
+	unsigned char weighted_bipred_idc;
+	char pic_init_qp_minus26;
+	char chroma_qp_index_offset;
+	char second_chroma_qp_index_offset;
+	unsigned char entropy_coding_mode_flag;
+	unsigned char pic_order_present_flag;
+	unsigned char deblocking_filter_control_present_flag;
+	unsigned char constrained_intra_pred_flag;
+	unsigned char weighted_pred_flag;
+	unsigned char redundant_pic_cnt_present_flag;
+	unsigned char transform_8x8_mode_flag;
+	unsigned char scaling_matrix_present_flag;
+	unsigned char reserved[2];
+};
+
+struct slice_api_h264_scaling_matrix {
+	unsigned char scaling_list_4x4[6][16];
+	unsigned char scaling_list_8x8[6][64];
+};
+
+struct slice_h264_dpb_entry {
+	unsigned long long reference_ts;
+	unsigned short frame_num;
+	unsigned short pic_num;
+	/* Note that field is indicated by v4l2_buffer.field */
+	int top_field_order_cnt;
+	int bottom_field_order_cnt;
+	unsigned int flags; /* V4L2_H264_DPB_ENTRY_FLAG_* */
+};
+
+/**
+ * struct slice_api_h264_decode_param - parameters for decode.
+ */
+struct slice_api_h264_decode_param {
+	struct slice_h264_dpb_entry dpb[16];
+	unsigned short num_slices;
+	unsigned short nal_ref_idc;
+	unsigned char ref_pic_list_p0[32];
+	unsigned char ref_pic_list_b0[32];
+	unsigned char ref_pic_list_b1[32];
+	int top_field_order_cnt;
+	int bottom_field_order_cnt;
+	unsigned int flags; /* V4L2_H264_DECODE_PARAM_FLAG_* */
+};
+
+/**
+ * struct mtk_h264_dec_slice_param  - parameters for decode current frame
+ */
+struct mtk_h264_dec_slice_param {
+	struct mtk_h264_sps_param			sps;
+	struct mtk_h264_pps_param			pps;
+	struct slice_api_h264_scaling_matrix		scaling_matrix;
+	struct slice_api_h264_decode_param		decode_params;
+	struct mtk_h264_dpb_info h264_dpb_info[16];
+};
+
+/**
+ * struct h264_fb - h264 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 h264_fb {
+	uint64_t vdec_fb_va;
+	uint64_t y_fb_dma;
+	uint64_t c_fb_dma;
+	int32_t poc;
+	uint32_t reserved;
+};
+
+/**
+ * struct vdec_h264_dec_info - decode information
+ * @dpb_sz		: decoding picture buffer size
+ * @resolution_changed  : resoltion change happen
+ * @realloc_mv_buf	: flag to notify driver to re-allocate mv buffer
+ * @cap_num_planes	: number planes of capture buffer
+ * @bs_dma		: Input bit-stream buffer dma address
+ * @y_fb_dma		: Y frame buffer dma address
+ * @c_fb_dma		: C frame buffer dma address
+ * @vdec_fb_va		: VDEC frame buffer struct virtual address
+ */
+struct vdec_h264_dec_info {
+	uint32_t dpb_sz;
+	uint32_t resolution_changed;
+	uint32_t realloc_mv_buf;
+	uint32_t cap_num_planes;
+	uint64_t bs_dma;
+	uint64_t y_fb_dma;
+	uint64_t c_fb_dma;
+	uint64_t vdec_fb_va;
+};
+
+/**
+ * struct vdec_h264_vsi - shared memory for decode information exchange
+ *                        between VPU and Host.
+ *                        The memory is allocated by VPU then mapping to Host
+ *                        in vpu_dec_init() and freed in vpu_dec_deinit()
+ *                        by VPU.
+ *                        AP-W/R : AP is writer/reader on this item
+ *                        VPU-W/R: VPU is write/reader on this item
+ * @pred_buf_dma : HW working predication buffer dma address (AP-W, VPU-R)
+ * @mv_buf_dma   : HW working motion vector buffer dma address (AP-W, VPU-R)
+ * @dec          : decode information (AP-R, VPU-W)
+ * @pic          : picture information (AP-R, VPU-W)
+ * @crop         : crop information (AP-R, VPU-W)
+ */
+struct vdec_h264_vsi {
+	uint64_t pred_buf_dma;
+	uint64_t mv_buf_dma[H264_MAX_MV_NUM];
+	struct vdec_h264_dec_info dec;
+	struct vdec_pic_info pic;
+	struct v4l2_rect crop;
+	struct mtk_h264_dec_slice_param h264_slice_params;
+};
+
+/**
+ * struct vdec_h264_slice_inst - h264 decoder instance
+ * @num_nalu : how many nalus be decoded
+ * @ctx      : point to mtk_vcodec_ctx
+ * @pred_buf : HW working predication buffer
+ * @mv_buf   : HW working motion vector buffer
+ * @vpu      : VPU instance
+ * @vsi_ctx  : Local VSI data for this decoding context
+ */
+struct vdec_h264_slice_inst {
+	unsigned int num_nalu;
+	struct mtk_vcodec_ctx *ctx;
+	struct mtk_vcodec_mem pred_buf;
+	struct mtk_vcodec_mem mv_buf[H264_MAX_MV_NUM];
+	struct vdec_vpu_inst vpu;
+	struct vdec_h264_vsi vsi_ctx;
+	struct mtk_h264_dec_slice_param h264_slice_param;
+
+	struct v4l2_h264_dpb_entry dpb[16];
+};
+
+static void *get_ctrl_ptr(struct mtk_vcodec_ctx *ctx,
+				 int id)
+{
+	struct v4l2_ctrl *ctrl = v4l2_ctrl_find(&ctx->ctrl_hdl, id);
+
+	return ctrl->p_cur.p;
+}
+
+static void get_h264_dpb_list(struct vdec_h264_slice_inst *inst,
+			      struct mtk_h264_dec_slice_param *slice_param)
+{
+	struct vb2_queue *vq;
+	struct vb2_buffer *vb;
+	struct vb2_v4l2_buffer *vb2_v4l2;
+	u64 index;
+
+	vq = v4l2_m2m_get_vq(inst->ctx->m2m_ctx,
+		V4L2_BUF_TYPE_VIDEO_CAPTURE_MPLANE);
+
+	for (index = 0; index < 16; index++) {
+		const struct slice_h264_dpb_entry *dpb;
+		int vb2_index;
+
+		dpb = &slice_param->decode_params.dpb[index];
+		if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)) {
+			slice_param->h264_dpb_info[index].reference_flag = 0;
+			continue;
+		}
+
+		vb2_index = vb2_find_timestamp(vq, dpb->reference_ts, 0);
+		if (vb2_index < 0) {
+			mtk_vcodec_err(inst, "Reference invalid: dpb_index(%lld) reference_ts(%lld)",
+				index, dpb->reference_ts);
+			continue;
+		}
+		/* 1 for short term reference, 2 for long term reference */
+		if (!(dpb->flags & V4L2_H264_DPB_ENTRY_FLAG_LONG_TERM))
+			slice_param->h264_dpb_info[index].reference_flag = 1;
+		else
+			slice_param->h264_dpb_info[index].reference_flag = 2;
+
+		vb = vq->bufs[vb2_index];
+		vb2_v4l2 = container_of(vb, struct vb2_v4l2_buffer, vb2_buf);
+		slice_param->h264_dpb_info[index].field = vb2_v4l2->field;
+
+		slice_param->h264_dpb_info[index].y_dma_addr =
+			vb2_dma_contig_plane_dma_addr(vb, 0);
+		if (inst->ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 2) {
+			slice_param->h264_dpb_info[index].c_dma_addr =
+				vb2_dma_contig_plane_dma_addr(vb, 1);
+		}
+	}
+}
+
+static void get_h264_sps_parameters(struct mtk_h264_sps_param *dst_param,
+	const struct v4l2_ctrl_h264_sps *src_param)
+{
+	GET_MTK_VDEC_PARAM(chroma_format_idc);
+	GET_MTK_VDEC_PARAM(bit_depth_luma_minus8);
+	GET_MTK_VDEC_PARAM(bit_depth_chroma_minus8);
+	GET_MTK_VDEC_PARAM(log2_max_frame_num_minus4);
+	GET_MTK_VDEC_PARAM(pic_order_cnt_type);
+	GET_MTK_VDEC_PARAM(log2_max_pic_order_cnt_lsb_minus4);
+	GET_MTK_VDEC_PARAM(max_num_ref_frames);
+	GET_MTK_VDEC_PARAM(pic_width_in_mbs_minus1);
+	GET_MTK_VDEC_PARAM(pic_height_in_map_units_minus1);
+
+	GET_MTK_VDEC_FLAG(separate_colour_plane_flag,
+		V4L2_H264_SPS_FLAG_SEPARATE_COLOUR_PLANE);
+	GET_MTK_VDEC_FLAG(qpprime_y_zero_transform_bypass_flag,
+		V4L2_H264_SPS_FLAG_QPPRIME_Y_ZERO_TRANSFORM_BYPASS);
+	GET_MTK_VDEC_FLAG(delta_pic_order_always_zero_flag,
+		V4L2_H264_SPS_FLAG_DELTA_PIC_ORDER_ALWAYS_ZERO);
+	GET_MTK_VDEC_FLAG(frame_mbs_only_flag,
+		V4L2_H264_SPS_FLAG_FRAME_MBS_ONLY);
+	GET_MTK_VDEC_FLAG(mb_adaptive_frame_field_flag,
+		V4L2_H264_SPS_FLAG_MB_ADAPTIVE_FRAME_FIELD);
+	GET_MTK_VDEC_FLAG(direct_8x8_inference_flag,
+		V4L2_H264_SPS_FLAG_DIRECT_8X8_INFERENCE);
+}
+
+static void get_h264_pps_parameters(struct mtk_h264_pps_param *dst_param,
+	const struct v4l2_ctrl_h264_pps *src_param)
+{
+	GET_MTK_VDEC_PARAM(num_ref_idx_l0_default_active_minus1);
+	GET_MTK_VDEC_PARAM(num_ref_idx_l1_default_active_minus1);
+	GET_MTK_VDEC_PARAM(weighted_bipred_idc);
+	GET_MTK_VDEC_PARAM(pic_init_qp_minus26);
+	GET_MTK_VDEC_PARAM(chroma_qp_index_offset);
+	GET_MTK_VDEC_PARAM(second_chroma_qp_index_offset);
+
+	GET_MTK_VDEC_FLAG(entropy_coding_mode_flag,
+		V4L2_H264_PPS_FLAG_ENTROPY_CODING_MODE);
+	GET_MTK_VDEC_FLAG(pic_order_present_flag,
+		V4L2_H264_PPS_FLAG_BOTTOM_FIELD_PIC_ORDER_IN_FRAME_PRESENT);
+	GET_MTK_VDEC_FLAG(weighted_pred_flag,
+		V4L2_H264_PPS_FLAG_WEIGHTED_PRED);
+	GET_MTK_VDEC_FLAG(deblocking_filter_control_present_flag,
+		V4L2_H264_PPS_FLAG_DEBLOCKING_FILTER_CONTROL_PRESENT);
+	GET_MTK_VDEC_FLAG(constrained_intra_pred_flag,
+		V4L2_H264_PPS_FLAG_CONSTRAINED_INTRA_PRED);
+	GET_MTK_VDEC_FLAG(redundant_pic_cnt_present_flag,
+		V4L2_H264_PPS_FLAG_REDUNDANT_PIC_CNT_PRESENT);
+	GET_MTK_VDEC_FLAG(transform_8x8_mode_flag,
+		V4L2_H264_PPS_FLAG_TRANSFORM_8X8_MODE);
+	GET_MTK_VDEC_FLAG(scaling_matrix_present_flag,
+		V4L2_H264_PPS_FLAG_SCALING_MATRIX_PRESENT);
+}
+
+static void
+get_h264_scaling_matrix(struct slice_api_h264_scaling_matrix *dst_matrix,
+			const struct v4l2_ctrl_h264_scaling_matrix *src_matrix)
+{
+	memcpy(dst_matrix->scaling_list_4x4, src_matrix->scaling_list_4x4,
+	       sizeof(dst_matrix->scaling_list_4x4));
+
+	memcpy(dst_matrix->scaling_list_8x8, src_matrix->scaling_list_8x8,
+	       sizeof(dst_matrix->scaling_list_8x8));
+}
+
+static void get_h264_decode_parameters(
+	struct slice_api_h264_decode_param *dst_params,
+	const struct v4l2_ctrl_h264_decode_params *src_params,
+	const struct v4l2_h264_dpb_entry dpb[V4L2_H264_NUM_DPB_ENTRIES])
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(dst_params->dpb); i++) {
+		struct slice_h264_dpb_entry *dst_entry = &dst_params->dpb[i];
+		const struct v4l2_h264_dpb_entry *src_entry = &dpb[i];
+
+		dst_entry->reference_ts = src_entry->reference_ts;
+		dst_entry->frame_num = src_entry->frame_num;
+		dst_entry->pic_num = src_entry->pic_num;
+		dst_entry->top_field_order_cnt = src_entry->top_field_order_cnt;
+		dst_entry->bottom_field_order_cnt =
+			src_entry->bottom_field_order_cnt;
+		dst_entry->flags = src_entry->flags;
+	}
+
+	// num_slices is a leftover from the old H.264 support and is ignored
+	// by the firmware.
+	dst_params->num_slices = 0;
+	dst_params->nal_ref_idc = src_params->nal_ref_idc;
+	dst_params->top_field_order_cnt = src_params->top_field_order_cnt;
+	dst_params->bottom_field_order_cnt = src_params->bottom_field_order_cnt;
+	dst_params->flags = src_params->flags;
+}
+
+static bool dpb_entry_match(const struct v4l2_h264_dpb_entry *a,
+			    const struct v4l2_h264_dpb_entry *b)
+{
+	return a->top_field_order_cnt == b->top_field_order_cnt &&
+	       a->bottom_field_order_cnt == b->bottom_field_order_cnt;
+}
+
+/*
+ * Move DPB entries of dec_param that refer to a frame already existing in dpb
+ * into the already existing slot in dpb, and move other entries into new slots.
+ *
+ * This function is an adaptation of the similarly-named function in
+ * hantro_h264.c.
+ */
+static void update_dpb(const struct v4l2_ctrl_h264_decode_params *dec_param,
+		       struct v4l2_h264_dpb_entry *dpb)
+{
+	DECLARE_BITMAP(new, ARRAY_SIZE(dec_param->dpb)) = { 0, };
+	DECLARE_BITMAP(in_use, ARRAY_SIZE(dec_param->dpb)) = { 0, };
+	DECLARE_BITMAP(used, ARRAY_SIZE(dec_param->dpb)) = { 0, };
+	unsigned int i, j;
+
+	/* Disable all entries by default, and mark the ones in use. */
+	for (i = 0; i < ARRAY_SIZE(dec_param->dpb); i++) {
+		if (dpb[i].flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE)
+			set_bit(i, in_use);
+		dpb[i].flags &= ~V4L2_H264_DPB_ENTRY_FLAG_ACTIVE;
+	}
+
+	/* Try to match new DPB entries with existing ones by their POCs. */
+	for (i = 0; i < ARRAY_SIZE(dec_param->dpb); i++) {
+		const struct v4l2_h264_dpb_entry *ndpb = &dec_param->dpb[i];
+
+		if (!(ndpb->flags & V4L2_H264_DPB_ENTRY_FLAG_ACTIVE))
+			continue;
+
+		/*
+		 * To cut off some comparisons, iterate only on target DPB
+		 * entries were already used.
+		 */
+		for_each_set_bit(j, in_use, ARRAY_SIZE(dec_param->dpb)) {
+			struct v4l2_h264_dpb_entry *cdpb;
+
+			cdpb = &dpb[j];
+			if (!dpb_entry_match(cdpb, ndpb))
+				continue;
+
+			*cdpb = *ndpb;
+			set_bit(j, used);
+			/* Don't reiterate on this one. */
+			clear_bit(j, in_use);
+			break;
+		}
+
+		if (j == ARRAY_SIZE(dec_param->dpb))
+			set_bit(i, new);
+	}
+
+	/* For entries that could not be matched, use remaining free slots. */
+	for_each_set_bit(i, new, ARRAY_SIZE(dec_param->dpb)) {
+		const struct v4l2_h264_dpb_entry *ndpb = &dec_param->dpb[i];
+		struct v4l2_h264_dpb_entry *cdpb;
+
+		/*
+		 * Both arrays are of the same sizes, so there is no way
+		 * we can end up with no space in target array, unless
+		 * something is buggy.
+		 */
+		j = find_first_zero_bit(used, ARRAY_SIZE(dec_param->dpb));
+		if (WARN_ON(j >= ARRAY_SIZE(dec_param->dpb)))
+			return;
+
+		cdpb = &dpb[j];
+		*cdpb = *ndpb;
+		set_bit(j, used);
+	}
+}
+
+/*
+ * The firmware expects unused reflist entries to have the value 0x20.
+ */
+static void fixup_ref_list(u8 *ref_list, size_t num_valid)
+{
+	memset(&ref_list[num_valid], 0x20, 32 - num_valid);
+}
+
+static void get_vdec_decode_parameters(struct vdec_h264_slice_inst *inst)
+{
+	const struct v4l2_ctrl_h264_decode_params *dec_params =
+		get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_DECODE_PARAMS);
+	const struct v4l2_ctrl_h264_sps *sps =
+		get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SPS);
+	const struct v4l2_ctrl_h264_pps *pps =
+		get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_PPS);
+	const struct v4l2_ctrl_h264_scaling_matrix *scaling_matrix =
+		get_ctrl_ptr(inst->ctx, V4L2_CID_STATELESS_H264_SCALING_MATRIX);
+	struct mtk_h264_dec_slice_param *slice_param = &inst->h264_slice_param;
+	struct v4l2_h264_reflist_builder reflist_builder;
+	enum v4l2_field dpb_fields[V4L2_H264_NUM_DPB_ENTRIES];
+	u8 *p0_reflist = slice_param->decode_params.ref_pic_list_p0;
+	u8 *b0_reflist = slice_param->decode_params.ref_pic_list_b0;
+	u8 *b1_reflist = slice_param->decode_params.ref_pic_list_b1;
+	int i;
+
+	update_dpb(dec_params, inst->dpb);
+
+	get_h264_sps_parameters(&slice_param->sps, sps);
+	get_h264_pps_parameters(&slice_param->pps, pps);
+	get_h264_scaling_matrix(&slice_param->scaling_matrix, scaling_matrix);
+	get_h264_decode_parameters(&slice_param->decode_params, dec_params,
+				   inst->dpb);
+	get_h264_dpb_list(inst, slice_param);
+
+	/* Prepare the fields for our reference lists */
+	for (i = 0; i < V4L2_H264_NUM_DPB_ENTRIES; i++)
+		dpb_fields[i] = slice_param->h264_dpb_info[i].field;
+	/* Build the reference lists */
+	v4l2_h264_init_reflist_builder(&reflist_builder, dec_params, sps,
+				       inst->dpb);
+	v4l2_h264_build_p_ref_list(&reflist_builder, p0_reflist);
+	v4l2_h264_build_b_ref_lists(&reflist_builder, b0_reflist, b1_reflist);
+	/* Adapt the built lists to the firmware's expectations */
+	fixup_ref_list(p0_reflist, reflist_builder.num_valid);
+	fixup_ref_list(b0_reflist, reflist_builder.num_valid);
+	fixup_ref_list(b1_reflist, reflist_builder.num_valid);
+
+	memcpy(&inst->vsi_ctx.h264_slice_params, slice_param,
+	       sizeof(inst->vsi_ctx.h264_slice_params));
+}
+
+static unsigned int get_mv_buf_size(unsigned int width, unsigned int height)
+{
+	int unit_size = (width / MB_UNIT_LEN) * (height / MB_UNIT_LEN) + 8;
+
+	return HW_MB_STORE_SZ * unit_size;
+}
+
+static int allocate_predication_buf(struct vdec_h264_slice_inst *inst)
+{
+	int err = 0;
+
+	inst->pred_buf.size = BUF_PREDICTION_SZ;
+	err = mtk_vcodec_mem_alloc(inst->ctx, &inst->pred_buf);
+	if (err) {
+		mtk_vcodec_err(inst, "failed to allocate ppl buf");
+		return err;
+	}
+
+	inst->vsi_ctx.pred_buf_dma = inst->pred_buf.dma_addr;
+	return 0;
+}
+
+static void free_predication_buf(struct vdec_h264_slice_inst *inst)
+{
+	struct mtk_vcodec_mem *mem = NULL;
+
+	mtk_vcodec_debug_enter(inst);
+
+	inst->vsi_ctx.pred_buf_dma = 0;
+	mem = &inst->pred_buf;
+	if (mem->va)
+		mtk_vcodec_mem_free(inst->ctx, mem);
+}
+
+static int alloc_mv_buf(struct vdec_h264_slice_inst *inst,
+	struct vdec_pic_info *pic)
+{
+	int i;
+	int err;
+	struct mtk_vcodec_mem *mem = NULL;
+	unsigned int buf_sz = get_mv_buf_size(pic->buf_w, pic->buf_h);
+
+	mtk_v4l2_debug(3, "size = 0x%lx", buf_sz);
+	for (i = 0; i < H264_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;
+		}
+		inst->vsi_ctx.mv_buf_dma[i] = mem->dma_addr;
+	}
+
+	return 0;
+}
+
+static void free_mv_buf(struct vdec_h264_slice_inst *inst)
+{
+	int i;
+	struct mtk_vcodec_mem *mem = NULL;
+
+	for (i = 0; i < H264_MAX_MV_NUM; i++) {
+		inst->vsi_ctx.mv_buf_dma[i] = 0;
+		mem = &inst->mv_buf[i];
+		if (mem->va)
+			mtk_vcodec_mem_free(inst->ctx, mem);
+	}
+}
+
+static void get_pic_info(struct vdec_h264_slice_inst *inst,
+			 struct vdec_pic_info *pic)
+{
+	struct mtk_vcodec_ctx *ctx = inst->ctx;
+
+	ctx->picinfo.buf_w = (ctx->picinfo.pic_w + 15) & 0xFFFFFFF0;
+	ctx->picinfo.buf_h = (ctx->picinfo.pic_h + 31) & 0xFFFFFFE0;
+	ctx->picinfo.fb_sz[0] = ctx->picinfo.buf_w * ctx->picinfo.buf_h;
+	ctx->picinfo.fb_sz[1] = ctx->picinfo.fb_sz[0] >> 1;
+	inst->vsi_ctx.dec.cap_num_planes =
+		ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes;
+
+	pic = &ctx->picinfo;
+	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->vsi_ctx.dec.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->vsi_ctx.dec.realloc_mv_buf = true;
+
+		mtk_v4l2_debug(1, "ResChg: (%d %d) : old(%d, %d) -> new(%d, %d)",
+			inst->vsi_ctx.dec.resolution_changed,
+			inst->vsi_ctx.dec.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 get_crop_info(struct vdec_h264_slice_inst *inst,
+	struct v4l2_rect *cr)
+{
+	cr->left = inst->vsi_ctx.crop.left;
+	cr->top = inst->vsi_ctx.crop.top;
+	cr->width = inst->vsi_ctx.crop.width;
+	cr->height = inst->vsi_ctx.crop.height;
+
+	mtk_vcodec_debug(inst, "l=%d, t=%d, w=%d, h=%d",
+			 cr->left, cr->top, cr->width, cr->height);
+}
+
+static void get_dpb_size(struct vdec_h264_slice_inst *inst,
+	unsigned int *dpb_sz)
+{
+	*dpb_sz = inst->vsi_ctx.dec.dpb_sz;
+	mtk_vcodec_debug(inst, "sz=%d", *dpb_sz);
+}
+
+static int vdec_h264_slice_init(struct mtk_vcodec_ctx *ctx)
+{
+	struct vdec_h264_slice_inst *inst = NULL;
+	int err;
+
+	inst = kzalloc(sizeof(*inst), GFP_KERNEL);
+	if (!inst)
+		return -ENOMEM;
+
+	inst->ctx = ctx;
+
+	inst->vpu.id = SCP_IPI_VDEC_H264;
+	inst->vpu.ctx = ctx;
+
+	err = vpu_dec_init(&inst->vpu);
+	if (err) {
+		mtk_vcodec_err(inst, "vdec_h264 init err=%d", err);
+		goto error_free_inst;
+	}
+
+	memcpy(&inst->vsi_ctx, inst->vpu.vsi, sizeof(inst->vsi_ctx));
+	inst->vsi_ctx.dec.resolution_changed = true;
+	inst->vsi_ctx.dec.realloc_mv_buf = true;
+
+	err = allocate_predication_buf(inst);
+	if (err)
+		goto error_deinit;
+
+	mtk_vcodec_debug(inst, "struct size = %d,%d,%d,%d\n",
+		sizeof(struct mtk_h264_sps_param),
+		sizeof(struct mtk_h264_pps_param),
+		sizeof(struct mtk_h264_dec_slice_param),
+		sizeof(struct mtk_h264_dpb_info));
+
+	mtk_vcodec_debug(inst, "H264 Instance >> %p", inst);
+
+	ctx->drv_handle = inst;
+	return 0;
+
+error_deinit:
+	vpu_dec_deinit(&inst->vpu);
+
+error_free_inst:
+	kfree(inst);
+	return err;
+}
+
+static void vdec_h264_slice_deinit(void *h_vdec)
+{
+	struct vdec_h264_slice_inst *inst =
+		(struct vdec_h264_slice_inst *)h_vdec;
+
+	mtk_vcodec_debug_enter(inst);
+
+	vpu_dec_deinit(&inst->vpu);
+	free_predication_buf(inst);
+	free_mv_buf(inst);
+
+	kfree(inst);
+}
+
+static int find_start_code(unsigned char *data, unsigned int data_sz)
+{
+	if (data_sz > 3 && data[0] == 0 && data[1] == 0 && data[2] == 1)
+		return 3;
+
+	if (data_sz > 4 && data[0] == 0 && data[1] == 0 && data[2] == 0 &&
+	    data[3] == 1)
+		return 4;
+
+	return -1;
+}
+
+static int vdec_h264_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+				  struct vdec_fb *fb, bool *res_chg)
+{
+	struct vdec_h264_slice_inst *inst =
+		(struct vdec_h264_slice_inst *)h_vdec;
+	struct vdec_vpu_inst *vpu = &inst->vpu;
+	struct mtk_video_dec_buf *src_buf_info;
+	int nal_start_idx = 0, err = 0;
+	uint32_t nal_type, data[2];
+	unsigned char *buf;
+	uint64_t y_fb_dma;
+	uint64_t c_fb_dma;
+
+	mtk_vcodec_debug(inst, "+ [%d] FB y_dma=%llx c_dma=%llx va=%p",
+			 ++inst->num_nalu, y_fb_dma, c_fb_dma, fb);
+
+	/* bs NULL means flush decoder */
+	if (bs == NULL)
+		return vpu_dec_reset(vpu);
+
+	src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer);
+
+	y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0;
+	c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0;
+
+	buf = (unsigned char *)bs->va;
+	nal_start_idx = find_start_code(buf, bs->size);
+	if (nal_start_idx < 0)
+		goto err_free_fb_out;
+
+	data[0] = bs->size;
+	data[1] = buf[nal_start_idx];
+	nal_type = NAL_TYPE(buf[nal_start_idx]);
+	mtk_vcodec_debug(inst, "\n + NALU[%d] type %d +\n", inst->num_nalu,
+			 nal_type);
+
+	inst->vsi_ctx.dec.bs_dma = (uint64_t)bs->dma_addr;
+	inst->vsi_ctx.dec.y_fb_dma = y_fb_dma;
+	inst->vsi_ctx.dec.c_fb_dma = c_fb_dma;
+	inst->vsi_ctx.dec.vdec_fb_va = (u64)(uintptr_t)fb;
+
+	get_vdec_decode_parameters(inst);
+	*res_chg = inst->vsi_ctx.dec.resolution_changed;
+	if (*res_chg) {
+		mtk_vcodec_debug(inst, "- resolution changed -");
+		if (inst->vsi_ctx.dec.realloc_mv_buf) {
+			err = alloc_mv_buf(inst, &(inst->ctx->picinfo));
+			inst->vsi_ctx.dec.realloc_mv_buf = false;
+			if (err)
+				goto err_free_fb_out;
+		}
+		*res_chg = false;
+	}
+
+	memcpy(inst->vpu.vsi, &inst->vsi_ctx, sizeof(inst->vsi_ctx));
+	err = vpu_dec_start(vpu, data, 2);
+	if (err)
+		goto err_free_fb_out;
+
+	if (nal_type == NAL_NON_IDR_SLICE || nal_type == NAL_IDR_SLICE) {
+		/* wait decoder done interrupt */
+		err = mtk_vcodec_wait_for_done_ctx(inst->ctx,
+						   MTK_INST_IRQ_RECEIVED,
+						   WAIT_INTR_TIMEOUT_MS);
+		if (err)
+			goto err_free_fb_out;
+
+		vpu_dec_end(vpu);
+	}
+
+	memcpy(&inst->vsi_ctx, inst->vpu.vsi, sizeof(inst->vsi_ctx));
+	mtk_vcodec_debug(inst, "\n - NALU[%d] type=%d -\n", inst->num_nalu,
+			 nal_type);
+	return 0;
+
+err_free_fb_out:
+	mtk_vcodec_err(inst, "\n - NALU[%d] err=%d -\n", inst->num_nalu, err);
+	return err;
+}
+
+static int vdec_h264_slice_get_param(void *h_vdec,
+			       enum vdec_get_param_type type, void *out)
+{
+	struct vdec_h264_slice_inst *inst =
+		(struct vdec_h264_slice_inst *)h_vdec;
+
+	switch (type) {
+	case GET_PARAM_PIC_INFO:
+		get_pic_info(inst, out);
+		break;
+
+	case GET_PARAM_DPB_SIZE:
+		get_dpb_size(inst, out);
+		break;
+
+	case GET_PARAM_CROP_INFO:
+		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_h264_slice_if = {
+	.init		= vdec_h264_slice_init,
+	.decode		= vdec_h264_slice_decode,
+	.get_param	= vdec_h264_slice_get_param,
+	.deinit		= vdec_h264_slice_deinit,
+};
diff --git a/drivers/media/platform/mtk-vcodec/vdec_drv_if.c b/drivers/media/platform/mtk-vcodec/vdec_drv_if.c
index b18743b906ea..42008243ceac 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_drv_if.c
+++ b/drivers/media/platform/mtk-vcodec/vdec_drv_if.c
@@ -19,6 +19,9 @@ int vdec_if_init(struct mtk_vcodec_ctx *ctx, unsigned int fourcc)
 	int ret = 0;
 
 	switch (fourcc) {
+	case V4L2_PIX_FMT_H264_SLICE:
+		ctx->dec_if = &vdec_h264_slice_if;
+		break;
 	case V4L2_PIX_FMT_H264:
 		ctx->dec_if = &vdec_h264_if;
 		break;
diff --git a/drivers/media/platform/mtk-vcodec/vdec_drv_if.h b/drivers/media/platform/mtk-vcodec/vdec_drv_if.h
index 270d8dc9984b..961b2b6072b5 100644
--- a/drivers/media/platform/mtk-vcodec/vdec_drv_if.h
+++ b/drivers/media/platform/mtk-vcodec/vdec_drv_if.h
@@ -55,6 +55,7 @@ struct vdec_fb_node {
 };
 
 extern const struct vdec_common_if vdec_h264_if;
+extern const struct vdec_common_if vdec_h264_slice_if;
 extern const struct vdec_common_if vdec_vp8_if;
 extern const struct vdec_common_if vdec_vp9_if;
 
-- 
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 6/8] media: mtk-vcodec: vdec: add media device if using stateless api

[Alexandre Courbot]

From: Yunfei Dong <yunfei.dong@mediatek.com>

The stateless API requires a media device for issuing requests. Add one
if we are being instantiated as a stateless decoder.

Signed-off-by: Yunfei Dong <yunfei.dong@mediatek.com>
[acourbot: refactor, cleanup and split]
Co-developed-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 drivers/media/platform/Kconfig                |  1 +
 .../platform/mtk-vcodec/mtk_vcodec_dec_drv.c  | 39 +++++++++++++++++++
 .../platform/mtk-vcodec/mtk_vcodec_drv.h      |  2 +
 3 files changed, 42 insertions(+)

diff --git a/drivers/media/platform/Kconfig b/drivers/media/platform/Kconfig
index c27db5643712..9d83b4223ecc 100644
--- a/drivers/media/platform/Kconfig
+++ b/drivers/media/platform/Kconfig
@@ -296,6 +296,7 @@ config VIDEO_MEDIATEK_VCODEC
 	select VIDEO_MEDIATEK_VCODEC_VPU if VIDEO_MEDIATEK_VPU
 	select VIDEO_MEDIATEK_VCODEC_SCP if MTK_SCP
 	select V4L2_H264
+	select MEDIA_CONTROLLER
 	help
 	  Mediatek video codec driver provides HW capability to
 	  encode and decode in a range of video formats on MT8173
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
index 533781d4680a..e942e28f96fe 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
@@ -14,6 +14,7 @@
 #include <media/v4l2-event.h>
 #include <media/v4l2-mem2mem.h>
 #include <media/videobuf2-dma-contig.h>
+#include <media/v4l2-device.h>
 
 #include "mtk_vcodec_drv.h"
 #include "mtk_vcodec_dec.h"
@@ -324,6 +325,31 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 		goto err_event_workq;
 	}
 
+	if (dev->vdec_pdata->uses_stateless_api) {
+		dev->mdev_dec.dev = &pdev->dev;
+		strscpy(dev->mdev_dec.model, MTK_VCODEC_DEC_NAME,
+				sizeof(dev->mdev_dec.model));
+
+		media_device_init(&dev->mdev_dec);
+		dev->mdev_dec.ops = &mtk_vcodec_media_ops;
+		dev->v4l2_dev.mdev = &dev->mdev_dec;
+
+		ret = v4l2_m2m_register_media_controller(dev->m2m_dev_dec,
+			dev->vfd_dec, MEDIA_ENT_F_PROC_VIDEO_DECODER);
+		if (ret) {
+			mtk_v4l2_err("Failed to register media controller");
+			goto err_reg_cont;
+		}
+
+		ret = media_device_register(&dev->mdev_dec);
+		if (ret) {
+			mtk_v4l2_err("Failed to register media device");
+			goto err_media_reg;
+		}
+
+		mtk_v4l2_debug(0, "media registered as /dev/media%d",
+			vfd_dec->num);
+	}
 	ret = video_register_device(vfd_dec, VFL_TYPE_VIDEO, 0);
 	if (ret) {
 		mtk_v4l2_err("Failed to register video device");
@@ -336,6 +362,12 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 	return 0;
 
 err_dec_reg:
+	if (dev->vdec_pdata->uses_stateless_api)
+		media_device_unregister(&dev->mdev_dec);
+err_media_reg:
+	if (dev->vdec_pdata->uses_stateless_api)
+		v4l2_m2m_unregister_media_controller(dev->m2m_dev_dec);
+err_reg_cont:
 	destroy_workqueue(dev->decode_workqueue);
 err_event_workq:
 	v4l2_m2m_release(dev->m2m_dev_dec);
@@ -368,6 +400,13 @@ static int mtk_vcodec_dec_remove(struct platform_device *pdev)
 
 	flush_workqueue(dev->decode_workqueue);
 	destroy_workqueue(dev->decode_workqueue);
+
+	if (media_devnode_is_registered(dev->mdev_dec.devnode)) {
+		media_device_unregister(&dev->mdev_dec);
+		v4l2_m2m_unregister_media_controller(dev->m2m_dev_dec);
+		media_device_cleanup(&dev->mdev_dec);
+	}
+
 	if (dev->m2m_dev_dec)
 		v4l2_m2m_release(dev->m2m_dev_dec);
 
diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
index 3b884a321883..79d6a1e6c916 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_drv.h
@@ -384,6 +384,7 @@ struct mtk_vcodec_enc_pdata {
  * struct mtk_vcodec_dev - driver data
  * @v4l2_dev: V4L2 device to register video devices for.
  * @vfd_dec: Video device for decoder
+ * @mdev_dec: Media device for decoder
  * @vfd_enc: Video device for encoder.
  *
  * @m2m_dev_dec: m2m device for decoder
@@ -420,6 +421,7 @@ struct mtk_vcodec_enc_pdata {
 struct mtk_vcodec_dev {
 	struct v4l2_device v4l2_dev;
 	struct video_device *vfd_dec;
+	struct media_device mdev_dec;
 	struct video_device *vfd_enc;
 
 	struct v4l2_m2m_dev *m2m_dev_dec;
-- 
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 7/8] dt-bindings: media: document mediatek,mt8183-vcodec-dec

[Alexandre Courbot]

MT8183's decoder is instantiated similarly to MT8173's.

Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 Documentation/devicetree/bindings/media/mediatek-vcodec.txt | 1 +
 1 file changed, 1 insertion(+)

diff --git a/Documentation/devicetree/bindings/media/mediatek-vcodec.txt b/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
index 8217424fd4bd..30c5888bf2d6 100644
--- a/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
+++ b/Documentation/devicetree/bindings/media/mediatek-vcodec.txt
@@ -7,6 +7,7 @@ Required properties:
 - compatible : "mediatek,mt8173-vcodec-enc" for MT8173 encoder
   "mediatek,mt8183-vcodec-enc" for MT8183 encoder.
   "mediatek,mt8173-vcodec-dec" for MT8173 decoder.
+  "mediatek,mt8183-vcodec-dec" for MT8183 decoder.
 - reg : Physical base address of the video codec registers and length of
   memory mapped region.
 - interrupts : interrupt number to the cpu.
-- 
2.30.0.617.g56c4b15f3c-goog

[PATCH v2 8/8] media: mtk-vcodec: enable MT8183 decoder

[Alexandre Courbot]

From: Yunfei Dong <yunfei.dong@mediatek.com>

Now that all the supporting blocks are present, enable decoder for
MT8183.

Signed-off-by: Yunfei Dong <yunfei.dong@mediatek.com>
[acourbot: refactor, cleanup and split]
Co-developed-by: Alexandre Courbot <acourbot@chromium.org>
Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
---
 drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
index e942e28f96fe..e0526c0900c8 100644
--- a/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
+++ b/drivers/media/platform/mtk-vcodec/mtk_vcodec_dec_drv.c
@@ -383,12 +383,17 @@ static int mtk_vcodec_probe(struct platform_device *pdev)
 }
 
 extern const struct mtk_vcodec_dec_pdata mtk_vdec_8173_pdata;
+extern const struct mtk_vcodec_dec_pdata mtk_vdec_8183_pdata;
 
 static const struct of_device_id mtk_vcodec_match[] = {
 	{
 		.compatible = "mediatek,mt8173-vcodec-dec",
 		.data = &mtk_vdec_8173_pdata,
 	},
+	{
+		.compatible = "mediatek,mt8183-vcodec-dec",
+		.data = &mtk_vdec_8183_pdata,
+	},
 	{},
 };
 
-- 
2.30.0.617.g56c4b15f3c-goog

Re: [PATCH v2 3/8] media: add Mediatek's MM21 format

[Nicolas Dufresne]

Le jeudi 25 février 2021 à 19:16 +0900, Alexandre Courbot a écrit :
> Add Mediatek's non-compressed 8 bit block video mode. This format is
> produced by the MT8183 codec and can be converted to a non-proprietary
> format by the MDP3 component.
> 
> Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
> ---
>  Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 7 +++++++
>  drivers/media/v4l2-core/v4l2-ioctl.c                      | 1 +
>  include/uapi/linux/videodev2.h                            | 1 +
>  3 files changed, 9 insertions(+)
> 
> diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> index c9231e18859b..187ea89f7a25 100644
> --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> @@ -242,6 +242,13 @@ please make a proposal on the linux-media mailing list.
>         It is an opaque intermediate format and the MDP hardware must be
>         used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``,
>         ``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``.
> +    * .. _V4L2-PIX-FMT-MM21:
> +
> +      - ``V4L2_PIX_FMT_MM21``
> +      - 'MM21'
> +      - Non-compressed, tiled two-planar format used by Mediatek MT8183.
> +       This is an opaque intermediate format and the MDP3 hardware can be
> +       used to convert it to other formats.
>      * .. _V4L2-PIX-FMT-SUNXI-TILED-NV12:

The SUNXI one was a mistake,  it's linear layout 32x32 tiles. The problem with
calling this a vendor format, is that other vendor might be using it too. But
they won't know and the format might endup duplicated, even if it's the same
one.

So here's my request, have you tried to understand a bit more what the tiling
layout is ? Could be tiled + SAND, could use zigzag layout like Samsung do. I
think if we can avoid vendor formats, we can preserve the pixel format list
sanity here. Most of the HW I've encoutered was very easy to reverse, even if
undocumented (except the compressed one).

If not possible, I would like to suggest:

  V4L2_PIX_FMT_MTK_NV21

The important part is to add a clear seperation for the vendor name, it easy to
recognize then.

>  
>        - ``V4L2_PIX_FMT_SUNXI_TILED_NV12``
> diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-
> core/v4l2-ioctl.c
> index 31d1342e61e8..0b85b2bbc628 100644
> --- a/drivers/media/v4l2-core/v4l2-ioctl.c
> +++ b/drivers/media/v4l2-core/v4l2-ioctl.c
> @@ -1384,6 +1384,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
>         case V4L2_PIX_FMT_TM6000:       descr = "A/V + VBI Mux Packet"; break;
>         case V4L2_PIX_FMT_CIT_YYVYUY:   descr = "GSPCA CIT YYVYUY"; break;
>         case V4L2_PIX_FMT_KONICA420:    descr = "GSPCA KONICA420"; break;
> +       case V4L2_PIX_FMT_MM21:         descr = "Mediatek 8-bit block format";
> break;
>         case V4L2_PIX_FMT_HSV24:        descr = "24-bit HSV 8-8-8"; break;
>         case V4L2_PIX_FMT_HSV32:        descr = "32-bit XHSV 8-8-8-8"; break;
>         case V4L2_SDR_FMT_CU8:          descr = "Complex U8"; break;
> diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
> index 79dbde3bcf8d..e6890dae76ec 100644
> --- a/include/uapi/linux/videodev2.h
> +++ b/include/uapi/linux/videodev2.h
> @@ -731,6 +731,7 @@ struct v4l2_pix_format {
>  #define V4L2_PIX_FMT_Y12I     v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale
> 12-bit L/R interleaved */
>  #define V4L2_PIX_FMT_Z16      v4l2_fourcc('Z', '1', '6', ' ') /* Depth data
> 16-bit */
>  #define V4L2_PIX_FMT_MT21C    v4l2_fourcc('M', 'T', '2', '1') /* Mediatek
> compressed block mode  */
> +#define V4L2_PIX_FMT_MM21     v4l2_fourcc('M', 'M', '2', '1') /* Mediatek 8-
> bit block mode, two non-contiguous planes */
>  #define V4L2_PIX_FMT_INZI     v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar
> Greyscale 10-bit and Depth 16-bit */
>  #define V4L2_PIX_FMT_SUNXI_TILED_NV12 v4l2_fourcc('S', 'T', '1', '2') /*
> Sunxi Tiled NV12 Format */
>  #define V4L2_PIX_FMT_CNF4     v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit
> packed depth confidence information */

Re: [PATCH v2 3/8] media: add Mediatek's MM21 format

[Alexandre Courbot]

Hi Nicolas,

On Wed, Mar 3, 2021 at 2:38 AM Nicolas Dufresne <nicolas@ndufresne.ca> wrote:
>
> Le jeudi 25 février 2021 à 19:16 +0900, Alexandre Courbot a écrit :
> > Add Mediatek's non-compressed 8 bit block video mode. This format is
> > produced by the MT8183 codec and can be converted to a non-proprietary
> > format by the MDP3 component.
> >
> > Signed-off-by: Alexandre Courbot <acourbot@chromium.org>
> > ---
> >  Documentation/userspace-api/media/v4l/pixfmt-reserved.rst | 7 +++++++
> >  drivers/media/v4l2-core/v4l2-ioctl.c                      | 1 +
> >  include/uapi/linux/videodev2.h                            | 1 +
> >  3 files changed, 9 insertions(+)
> >
> > diff --git a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> > b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> > index c9231e18859b..187ea89f7a25 100644
> > --- a/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> > +++ b/Documentation/userspace-api/media/v4l/pixfmt-reserved.rst
> > @@ -242,6 +242,13 @@ please make a proposal on the linux-media mailing list.
> >         It is an opaque intermediate format and the MDP hardware must be
> >         used to convert ``V4L2_PIX_FMT_MT21C`` to ``V4L2_PIX_FMT_NV12M``,
> >         ``V4L2_PIX_FMT_YUV420M`` or ``V4L2_PIX_FMT_YVU420``.
> > +    * .. _V4L2-PIX-FMT-MM21:
> > +
> > +      - ``V4L2_PIX_FMT_MM21``
> > +      - 'MM21'
> > +      - Non-compressed, tiled two-planar format used by Mediatek MT8183.
> > +       This is an opaque intermediate format and the MDP3 hardware can be
> > +       used to convert it to other formats.
> >      * .. _V4L2-PIX-FMT-SUNXI-TILED-NV12:
>
> The SUNXI one was a mistake,  it's linear layout 32x32 tiles. The problem with
> calling this a vendor format, is that other vendor might be using it too. But
> they won't know and the format might endup duplicated, even if it's the same
> one.
>
> So here's my request, have you tried to understand a bit more what the tiling
> layout is ? Could be tiled + SAND, could use zigzag layout like Samsung do. I
> think if we can avoid vendor formats, we can preserve the pixel format list
> sanity here. Most of the HW I've encoutered was very easy to reverse, even if
> undocumented (except the compressed one).

Unfortunately I don't think I can look too closely into that, for
non-technical reasons. But if MTK could come forward and document
their format, that would be indeed ideal.

>
> If not possible, I would like to suggest:
>
>   V4L2_PIX_FMT_MTK_NV21
>
> The important part is to add a clear seperation for the vendor name, it easy to
> recognize then.

The MTK prefix makes sense, but I do not know if NV21 is a correct
denomination for that format. Note that we have another MTK-only
format currently named V4L2_PIX_FMT_MT21C, which is already public. It
would be nice to rename it as well, but since it is part of the public
API I'm afraid the cat is already out of the bag for that one...

>
> >
> >        - ``V4L2_PIX_FMT_SUNXI_TILED_NV12``
> > diff --git a/drivers/media/v4l2-core/v4l2-ioctl.c b/drivers/media/v4l2-
> > core/v4l2-ioctl.c
> > index 31d1342e61e8..0b85b2bbc628 100644
> > --- a/drivers/media/v4l2-core/v4l2-ioctl.c
> > +++ b/drivers/media/v4l2-core/v4l2-ioctl.c
> > @@ -1384,6 +1384,7 @@ static void v4l_fill_fmtdesc(struct v4l2_fmtdesc *fmt)
> >         case V4L2_PIX_FMT_TM6000:       descr = "A/V + VBI Mux Packet"; break;
> >         case V4L2_PIX_FMT_CIT_YYVYUY:   descr = "GSPCA CIT YYVYUY"; break;
> >         case V4L2_PIX_FMT_KONICA420:    descr = "GSPCA KONICA420"; break;
> > +       case V4L2_PIX_FMT_MM21:         descr = "Mediatek 8-bit block format";
> > break;
> >         case V4L2_PIX_FMT_HSV24:        descr = "24-bit HSV 8-8-8"; break;
> >         case V4L2_PIX_FMT_HSV32:        descr = "32-bit XHSV 8-8-8-8"; break;
> >         case V4L2_SDR_FMT_CU8:          descr = "Complex U8"; break;
> > diff --git a/include/uapi/linux/videodev2.h b/include/uapi/linux/videodev2.h
> > index 79dbde3bcf8d..e6890dae76ec 100644
> > --- a/include/uapi/linux/videodev2.h
> > +++ b/include/uapi/linux/videodev2.h
> > @@ -731,6 +731,7 @@ struct v4l2_pix_format {
> >  #define V4L2_PIX_FMT_Y12I     v4l2_fourcc('Y', '1', '2', 'I') /* Greyscale
> > 12-bit L/R interleaved */
> >  #define V4L2_PIX_FMT_Z16      v4l2_fourcc('Z', '1', '6', ' ') /* Depth data
> > 16-bit */
> >  #define V4L2_PIX_FMT_MT21C    v4l2_fourcc('M', 'T', '2', '1') /* Mediatek
> > compressed block mode  */
> > +#define V4L2_PIX_FMT_MM21     v4l2_fourcc('M', 'M', '2', '1') /* Mediatek 8-
> > bit block mode, two non-contiguous planes */
> >  #define V4L2_PIX_FMT_INZI     v4l2_fourcc('I', 'N', 'Z', 'I') /* Intel Planar
> > Greyscale 10-bit and Depth 16-bit */
> >  #define V4L2_PIX_FMT_SUNXI_TILED_NV12 v4l2_fourcc('S', 'T', '1', '2') /*
> > Sunxi Tiled NV12 Format */
> >  #define V4L2_PIX_FMT_CNF4     v4l2_fourcc('C', 'N', 'F', '4') /* Intel 4-bit
> > packed depth confidence information */
>
>