[v2,1/2] media: amphion: Reduce decoding latency for HEVC decoder

Commit Message

Ming Qian Jan. 17, 2025, 7:57 a.m. UTC

The amphion decoder firmware supports low latency flush mode for
HEVC format since v1.9.0, it can help reduce the decoding latency by
appending some padding data after every frame, then driver can enable
this feature when the display delay 0 is enabled.

Signed-off-by: Ming Qian <[e-mail]>
---
v2
- Improve commit message
- Add firmware version check

 drivers/media/platform/amphion/vpu_malone.c | 22 ++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

Patch

diff --git a/drivers/media/platform/amphion/vpu_malone.c b/drivers/media/platform/amphion/vpu_malone.c
index 5c6b2a841b6f..1d9e10d9bec1 100644
--- a/drivers/media/platform/amphion/vpu_malone.c
+++ b/drivers/media/platform/amphion/vpu_malone.c
@@ -68,6 +68,9 @@ 
 
 #define MALONE_DEC_FMT_RV_MASK			BIT(21)
 
+#define MALONE_VERSION_MASK			0xFFFFF
+#define MALONE_MIN_VERSION_HEVC_BUFFLUSH	(((1 << 16) | (9 << 8) | 0) & MALONE_VERSION_MASK)
+
 enum vpu_malone_stream_input_mode {
 	INVALID_MODE = 0,
 	FRAME_LVL,
@@ -332,6 +335,8 @@  struct vpu_dec_ctrl {
 	u32 buf_addr[VID_API_NUM_STREAMS];
 };
 
+static const struct malone_padding_scode *get_padding_scode(u32 type, u32 fmt);
+
 u32 vpu_malone_get_data_size(void)
 {
 	return sizeof(struct vpu_dec_ctrl);
@@ -654,9 +659,16 @@  static int vpu_malone_set_params(struct vpu_shared_addr *shared,
 		hc->jpg[instance].jpg_mjpeg_interlaced = 0;
 	}
 
-	hc->codec_param[instance].disp_imm = params->display_delay_enable ? 1 : 0;
-	if (malone_format != MALONE_FMT_AVC)
+	if (params->display_delay_enable &&
+	    get_padding_scode(SCODE_PADDING_BUFFLUSH, params->codec_format))
+		hc->codec_param[instance].disp_imm = 1;
+	else
 		hc->codec_param[instance].disp_imm = 0;
+
+	if (params->codec_format == V4L2_PIX_FMT_HEVC &&
+	    (iface->fw_version & MALONE_VERSION_MASK) < MALONE_MIN_VERSION_HEVC_BUFFLUSH)
+		hc->codec_param[instance].disp_imm = 0;
+
 	hc->codec_param[instance].dbglog_enable = 0;
 	iface->dbglog_desc.level = 0;
 
@@ -1024,6 +1036,7 @@  static const struct malone_padding_scode padding_scodes[] = {
 	{SCODE_PADDING_EOS,      V4L2_PIX_FMT_JPEG,        {0x0, 0x0}},
 	{SCODE_PADDING_BUFFLUSH, V4L2_PIX_FMT_H264,        {0x15010000, 0x0}},
 	{SCODE_PADDING_BUFFLUSH, V4L2_PIX_FMT_H264_MVC,    {0x15010000, 0x0}},
+	{SCODE_PADDING_BUFFLUSH, V4L2_PIX_FMT_HEVC,        {0x3e010000, 0x20}},
 };
 
 static const struct malone_padding_scode padding_scode_dft = {0x0, 0x0};
@@ -1058,8 +1071,11 @@  static int vpu_malone_add_padding_scode(struct vpu_buffer *stream_buffer,
 	int ret;
 
 	ps = get_padding_scode(scode_type, pixelformat);
-	if (!ps)
+	if (!ps) {
+		if (scode_type == SCODE_PADDING_BUFFLUSH)
+			return 0;
 		return -EINVAL;
+	}
 
 	wptr = readl(&str_buf->wptr);
 	if (wptr < stream_buffer->phys || wptr > stream_buffer->phys + stream_buffer->length)