[PATCH v3 2/8] media: hantro: Add support of compressed reference buffers
Benjamin Gaignard
benjamin.gaignard at collabora.com
Fri Jun 18 06:15:20 PDT 2021
Reference frame compression is a feature added in G2 decoder to compress
frame buffers so that the bandwidth of storing/loading reference frames
can be reduced, especially when the resolution of decoded stream is of
high definition.
Tested on IMX8MQ the maximun frame rate goes up to 50 fps vs 45 fps
without using compressed frames.
Signed-off-by: Benjamin Gaignard <benjamin.gaignard at collabora.com>
---
version 2:
- Define the value for compression storage size
- Add comments about registers usage
.../staging/media/hantro/hantro_g2_hevc_dec.c | 31 +++++++++++++--
drivers/staging/media/hantro/hantro_g2_regs.h | 4 ++
drivers/staging/media/hantro/hantro_hevc.c | 39 ++++++++++++++++++-
drivers/staging/media/hantro/hantro_hw.h | 2 +
4 files changed, 72 insertions(+), 4 deletions(-)
diff --git a/drivers/staging/media/hantro/hantro_g2_hevc_dec.c b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c
index fef16d1724da..bf19825c4d96 100644
--- a/drivers/staging/media/hantro/hantro_g2_hevc_dec.c
+++ b/drivers/staging/media/hantro/hantro_g2_hevc_dec.c
@@ -382,10 +382,12 @@ static int set_ref(struct hantro_ctx *ctx)
const struct v4l2_ctrl_hevc_pps *pps = ctrls->pps;
const struct v4l2_ctrl_hevc_decode_params *decode_params = ctrls->decode_params;
const struct v4l2_hevc_dpb_entry *dpb = decode_params->dpb;
- dma_addr_t luma_addr, chroma_addr, mv_addr = 0;
+ dma_addr_t luma_addr, chroma_addr, mv_addr, compress_luma_addr, compress_chroma_addr = 0;
struct hantro_dev *vpu = ctx->dev;
size_t cr_offset = hantro_hevc_chroma_offset(sps);
size_t mv_offset = hantro_hevc_motion_vectors_offset(sps);
+ size_t compress_luma_offset = hantro_hevc_luma_compress_offset(sps);
+ size_t compress_chroma_offset = hantro_hevc_chroma_compress_offset(sps);
u32 max_ref_frames;
u16 dpb_longterm_e;
static const struct hantro_reg cur_poc[] = {
@@ -458,15 +460,28 @@ static int set_ref(struct hantro_ctx *ctx)
if (!luma_addr)
return -ENOMEM;
+ /*
+ * An allocated frame stores Y and UV planes, motion vectors and
+ * compressed Y and UV planes. Compute all these offsets given
+ * the frame resolution and the pixel format.
+ */
chroma_addr = luma_addr + cr_offset;
mv_addr = luma_addr + mv_offset;
+ compress_luma_addr = luma_addr + compress_luma_offset;
+ compress_chroma_addr = luma_addr + compress_chroma_offset;
if (dpb[i].rps == V4L2_HEVC_DPB_ENTRY_RPS_LT_CURR)
dpb_longterm_e |= BIT(V4L2_HEVC_DPB_ENTRIES_NUM_MAX - 1 - i);
+ /*
+ * For each reference frame Y, UV, motion vector and
+ * compressed Y, UV buffers addresses must be set.
+ */
hantro_write_addr(vpu, G2_REG_ADDR_REF(i), luma_addr);
hantro_write_addr(vpu, G2_REG_CHR_REF(i), chroma_addr);
hantro_write_addr(vpu, G2_REG_DMV_REF(i), mv_addr);
+ hantro_write_addr(vpu, G2_COMP_ADDR_REF(i), compress_luma_addr);
+ hantro_write_addr(vpu, G2_COMP_CHR_REF(i), compress_chroma_addr);
}
luma_addr = hantro_hevc_get_ref_buf(ctx, decode_params->pic_order_cnt_val);
@@ -475,7 +490,12 @@ static int set_ref(struct hantro_ctx *ctx)
chroma_addr = luma_addr + cr_offset;
mv_addr = luma_addr + mv_offset;
+ compress_luma_addr = luma_addr + compress_luma_offset;
+ compress_chroma_addr = luma_addr + compress_chroma_offset;
+ /* The next decoded frame as to be put as the last reference frame entry */
+ hantro_write_addr(vpu, G2_COMP_ADDR_REF(i), compress_luma_addr);
+ hantro_write_addr(vpu, G2_COMP_CHR_REF(i), compress_chroma_addr);
hantro_write_addr(vpu, G2_REG_ADDR_REF(i), luma_addr);
hantro_write_addr(vpu, G2_REG_CHR_REF(i), chroma_addr);
hantro_write_addr(vpu, G2_REG_DMV_REF(i++), mv_addr);
@@ -483,13 +503,18 @@ static int set_ref(struct hantro_ctx *ctx)
hantro_write_addr(vpu, G2_ADDR_DST, luma_addr);
hantro_write_addr(vpu, G2_ADDR_DST_CHR, chroma_addr);
hantro_write_addr(vpu, G2_ADDR_DST_MV, mv_addr);
+ hantro_write_addr(vpu, G2_COMP_ADDR_DST, compress_luma_addr);
+ hantro_write_addr(vpu, G2_COMP_CHR, compress_chroma_addr);
hantro_hevc_ref_remove_unused(ctx);
+ /* Unused reference frames entries most be cleared */
for (; i < V4L2_HEVC_DPB_ENTRIES_NUM_MAX; i++) {
hantro_write_addr(vpu, G2_REG_ADDR_REF(i), 0);
hantro_write_addr(vpu, G2_REG_CHR_REF(i), 0);
hantro_write_addr(vpu, G2_REG_DMV_REF(i), 0);
+ hantro_write_addr(vpu, G2_COMP_ADDR_REF(i), 0);
+ hantro_write_addr(vpu, G2_COMP_CHR_REF(i), 0);
}
hantro_reg_write(vpu, &g2_refer_lterm_e, dpb_longterm_e);
@@ -580,8 +605,8 @@ int hantro_g2_hevc_dec_run(struct hantro_ctx *ctx)
/* Don't disable output */
hantro_reg_write(vpu, &g2_out_dis, 0);
- /* Don't compress buffers */
- hantro_reg_write(vpu, &g2_ref_compress_bypass, 1);
+ /* Compress buffers */
+ hantro_reg_write(vpu, &g2_ref_compress_bypass, 0);
/* use NV12 as output format */
hantro_reg_write(vpu, &g2_out_rs_e, 1);
diff --git a/drivers/staging/media/hantro/hantro_g2_regs.h b/drivers/staging/media/hantro/hantro_g2_regs.h
index 17d84ec9c5c2..0414d92e3860 100644
--- a/drivers/staging/media/hantro/hantro_g2_regs.h
+++ b/drivers/staging/media/hantro/hantro_g2_regs.h
@@ -192,6 +192,10 @@
#define G2_TILE_FILTER (G2_SWREG(179))
#define G2_TILE_SAO (G2_SWREG(181))
#define G2_TILE_BSD (G2_SWREG(183))
+#define G2_COMP_ADDR_DST (G2_SWREG(190))
+#define G2_COMP_ADDR_REF(i) (G2_SWREG(192) + ((i) * 0x8))
+#define G2_COMP_CHR (G2_SWREG(224))
+#define G2_COMP_CHR_REF(i) (G2_SWREG(226) + ((i) * 0x8))
#define g2_strm_buffer_len G2_DEC_REG(258, 0, 0xffffffff)
#define g2_strm_start_offset G2_DEC_REG(259, 0, 0xffffffff)
diff --git a/drivers/staging/media/hantro/hantro_hevc.c b/drivers/staging/media/hantro/hantro_hevc.c
index 5347f5a41c2a..00400dd33a3b 100644
--- a/drivers/staging/media/hantro/hantro_hevc.c
+++ b/drivers/staging/media/hantro/hantro_hevc.c
@@ -27,6 +27,13 @@
#define G2_ALIGN 16
+#define CBS_SIZE 16 /* compression table size in bytes */
+#define CBS_LUMA 8 /* luminance CBS is composed of 1 8x8 coded block */
+#define CBS_CHROMA_W (8*2) /* chrominance CBS is composed of two 8x4 coded
+ * blocks, with Cb CB first then Cr CB following
+ */
+#define CBS_CHROMA_H 4
+
size_t hantro_hevc_chroma_offset(const struct v4l2_ctrl_hevc_sps *sps)
{
int bytes_per_pixel = sps->bit_depth_luma_minus8 == 0 ? 1 : 2;
@@ -61,12 +68,42 @@ static size_t hantro_hevc_mv_size(const struct v4l2_ctrl_hevc_sps *sps)
return mv_size;
}
+size_t hantro_hevc_luma_compress_offset(const struct v4l2_ctrl_hevc_sps *sps)
+{
+ return hantro_hevc_motion_vectors_offset(sps) + hantro_hevc_mv_size(sps);
+}
+
+static size_t hantro_hevc_luma_compress_size(const struct v4l2_ctrl_hevc_sps *sps)
+{
+ u32 pic_width_in_cbsy =
+ round_up((sps->pic_width_in_luma_samples + CBS_LUMA - 1) / CBS_LUMA, CBS_SIZE);
+ u32 pic_height_in_cbsy = (sps->pic_height_in_luma_samples + CBS_LUMA - 1) / CBS_LUMA;
+
+ return round_up(pic_width_in_cbsy * pic_height_in_cbsy, CBS_SIZE);
+}
+
+size_t hantro_hevc_chroma_compress_offset(const struct v4l2_ctrl_hevc_sps *sps)
+{
+ return hantro_hevc_luma_compress_offset(sps) + hantro_hevc_luma_compress_size(sps);
+}
+
+static size_t hantro_hevc_chroma_compress_size(const struct v4l2_ctrl_hevc_sps *sps)
+{
+ u32 pic_width_in_cbsc =
+ round_up((sps->pic_width_in_luma_samples + CBS_CHROMA_W - 1) / CBS_CHROMA_W, CBS_SIZE);
+ u32 pic_height_in_cbsc = (sps->pic_height_in_luma_samples / 2 + CBS_CHROMA_H - 1) / CBS_CHROMA_H;
+
+ return round_up(pic_width_in_cbsc * pic_height_in_cbsc, CBS_SIZE);
+}
+
static size_t hantro_hevc_ref_size(struct hantro_ctx *ctx)
{
const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls;
const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps;
- return hantro_hevc_motion_vectors_offset(sps) + hantro_hevc_mv_size(sps);
+ return hantro_hevc_motion_vectors_offset(sps) + hantro_hevc_mv_size(sps) +
+ hantro_hevc_luma_compress_size(sps) +
+ hantro_hevc_chroma_compress_size(sps);
}
static void hantro_hevc_ref_free(struct hantro_ctx *ctx)
diff --git a/drivers/staging/media/hantro/hantro_hw.h b/drivers/staging/media/hantro/hantro_hw.h
index 8fa0aacb61cd..c5374cd74d66 100644
--- a/drivers/staging/media/hantro/hantro_hw.h
+++ b/drivers/staging/media/hantro/hantro_hw.h
@@ -246,6 +246,8 @@ dma_addr_t hantro_hevc_get_ref_buf(struct hantro_ctx *ctx, int poc);
void hantro_hevc_ref_remove_unused(struct hantro_ctx *ctx);
size_t hantro_hevc_chroma_offset(const struct v4l2_ctrl_hevc_sps *sps);
size_t hantro_hevc_motion_vectors_offset(const struct v4l2_ctrl_hevc_sps *sps);
+size_t hantro_hevc_luma_compress_offset(const struct v4l2_ctrl_hevc_sps *sps);
+size_t hantro_hevc_chroma_compress_offset(const struct v4l2_ctrl_hevc_sps *sps);
static inline size_t
hantro_h264_mv_size(unsigned int width, unsigned int height)
--
2.25.1
More information about the Linux-rockchip
mailing list