diff options
Diffstat (limited to 'drivers/media/platform/qcom/iris/iris_vpu_buffer.c')
| -rw-r--r-- | drivers/media/platform/qcom/iris/iris_vpu_buffer.c | 701 |
1 files changed, 672 insertions, 29 deletions
diff --git a/drivers/media/platform/qcom/iris/iris_vpu_buffer.c b/drivers/media/platform/qcom/iris/iris_vpu_buffer.c index 4463be05ce16..9270422c1601 100644 --- a/drivers/media/platform/qcom/iris/iris_vpu_buffer.c +++ b/drivers/media/platform/qcom/iris/iris_vpu_buffer.c @@ -9,6 +9,17 @@ #include "iris_hfi_gen2_defines.h" #define HFI_MAX_COL_FRAME 6 +#define HFI_COLOR_FORMAT_YUV420_NV12_UBWC_Y_TILE_HEIGHT (8) +#define HFI_COLOR_FORMAT_YUV420_NV12_UBWC_Y_TILE_WIDTH (32) +#define HFI_COLOR_FORMAT_YUV420_NV12_UBWC_UV_TILE_HEIGHT (8) +#define HFI_COLOR_FORMAT_YUV420_NV12_UBWC_UV_TILE_WIDTH (16) +#define HFI_COLOR_FORMAT_YUV420_TP10_UBWC_Y_TILE_HEIGHT (4) +#define HFI_COLOR_FORMAT_YUV420_TP10_UBWC_Y_TILE_WIDTH (48) +#define HFI_COLOR_FORMAT_YUV420_TP10_UBWC_UV_TILE_HEIGHT (4) +#define HFI_COLOR_FORMAT_YUV420_TP10_UBWC_UV_TILE_WIDTH (24) +#define AV1D_SIZE_BSE_COL_MV_64x64 512 +#define AV1D_SIZE_BSE_COL_MV_128x128 2816 +#define UBWC_TILE_SIZE 256 #ifndef SYSTEM_LAL_TILE10 #define SYSTEM_LAL_TILE10 192 @@ -39,6 +50,31 @@ static u32 hfi_buffer_bin_h264d(u32 frame_width, u32 frame_height, u32 num_vpp_p return size_h264d_hw_bin_buffer(n_aligned_w, n_aligned_h, num_vpp_pipes); } +static u32 size_av1d_hw_bin_buffer(u32 frame_width, u32 frame_height, u32 num_vpp_pipes) +{ + u32 size_yuv, size_bin_hdr, size_bin_res; + + size_yuv = ((frame_width * frame_height) <= BIN_BUFFER_THRESHOLD) ? + ((BIN_BUFFER_THRESHOLD * 3) >> 1) : + ((frame_width * frame_height * 3) >> 1); + size_bin_hdr = size_yuv * AV1_CABAC_HDR_RATIO_HD_TOT; + size_bin_res = size_yuv * AV1_CABAC_RES_RATIO_HD_TOT; + size_bin_hdr = ALIGN(size_bin_hdr / num_vpp_pipes, + DMA_ALIGNMENT) * num_vpp_pipes; + size_bin_res = ALIGN(size_bin_res / num_vpp_pipes, + DMA_ALIGNMENT) * num_vpp_pipes; + + return size_bin_hdr + size_bin_res; +} + +static u32 hfi_buffer_bin_av1d(u32 frame_width, u32 frame_height, u32 num_vpp_pipes) +{ + u32 n_aligned_h = ALIGN(frame_height, 16); + u32 n_aligned_w = ALIGN(frame_width, 16); + + return size_av1d_hw_bin_buffer(n_aligned_w, n_aligned_h, num_vpp_pipes); +} + static u32 size_h265d_hw_bin_buffer(u32 frame_width, u32 frame_height, u32 num_vpp_pipes) { u32 product = frame_width * frame_height; @@ -110,6 +146,26 @@ static u32 hfi_buffer_comv_h265d(u32 frame_width, u32 frame_height, u32 _comv_bu return (_size * (_comv_bufcount)) + 512; } +static u32 num_lcu(u32 frame_width, u32 frame_height, u32 lcu_size) +{ + return ((frame_width + lcu_size - 1) / lcu_size) * + ((frame_height + lcu_size - 1) / lcu_size); +} + +static u32 hfi_buffer_comv_av1d(u32 frame_width, u32 frame_height, u32 comv_bufcount) +{ + u32 size; + + size = 2 * ALIGN(max(num_lcu(frame_width, frame_height, 64) * + AV1D_SIZE_BSE_COL_MV_64x64, + num_lcu(frame_width, frame_height, 128) * + AV1D_SIZE_BSE_COL_MV_128x128), + DMA_ALIGNMENT); + size *= comv_bufcount; + + return size; +} + static u32 size_h264d_bse_cmd_buf(u32 frame_height) { u32 height = ALIGN(frame_height, 32); @@ -122,7 +178,7 @@ static u32 size_h265d_bse_cmd_buf(u32 frame_width, u32 frame_height) { u32 _size = ALIGN(((ALIGN(frame_width, LCU_MAX_SIZE_PELS) / LCU_MIN_SIZE_PELS) * (ALIGN(frame_height, LCU_MAX_SIZE_PELS) / LCU_MIN_SIZE_PELS)) * - NUM_HW_PIC_BUF, DMA_ALIGNMENT); + NUM_HW_PIC_BUF, DMA_ALIGNMENT); _size = min_t(u32, _size, H265D_MAX_SLICE + 1); _size = 2 * _size * SIZE_H265D_BSE_CMD_PER_BUF; @@ -174,6 +230,20 @@ static u32 hfi_buffer_persist_h264d(void) DMA_ALIGNMENT); } +static u32 hfi_buffer_persist_av1d(u32 max_width, u32 max_height, u32 total_ref_count) +{ + u32 comv_size, size; + + comv_size = hfi_buffer_comv_av1d(max_width, max_height, total_ref_count); + size = ALIGN((SIZE_AV1D_SEQUENCE_HEADER * 2 + SIZE_AV1D_METADATA + + AV1D_NUM_HW_PIC_BUF * (SIZE_AV1D_TILE_OFFSET + SIZE_AV1D_QM) + + AV1D_NUM_FRAME_HEADERS * (SIZE_AV1D_FRAME_HEADER + + 2 * SIZE_AV1D_PROB_TABLE) + comv_size + HDR10_HIST_EXTRADATA_SIZE + + SIZE_AV1D_METADATA * AV1D_NUM_HW_PIC_BUF), DMA_ALIGNMENT); + + return ALIGN(size, DMA_ALIGNMENT); +} + static u32 hfi_buffer_non_comv_h264d(u32 frame_width, u32 frame_height, u32 num_vpp_pipes) { u32 size_bse = size_h264d_bse_cmd_buf(frame_height); @@ -459,6 +529,182 @@ static u32 hfi_buffer_line_h264d(u32 frame_width, u32 frame_height, return ALIGN((size + vpss_lb_size), DMA_ALIGNMENT); } +static u32 size_av1d_lb_opb_wr1_nv12_ubwc(u32 frame_width, u32 frame_height) +{ + u32 size, y_width, y_width_a = 128; + + y_width = ALIGN(frame_width, y_width_a); + + size = ((y_width + HFI_COLOR_FORMAT_YUV420_NV12_UBWC_Y_TILE_WIDTH - 1) / + HFI_COLOR_FORMAT_YUV420_NV12_UBWC_Y_TILE_WIDTH + + (AV1D_MAX_TILE_COLS - 1)); + return size * UBWC_TILE_SIZE; +} + +static u32 size_av1d_lb_opb_wr1_tp10_ubwc(u32 frame_width, u32 frame_height) +{ + u32 size, y_width, y_width_a = 256; + + y_width = ALIGN(frame_width, y_width_a); + + size = ((y_width + HFI_COLOR_FORMAT_YUV420_TP10_UBWC_Y_TILE_WIDTH - 1) / + HFI_COLOR_FORMAT_YUV420_TP10_UBWC_Y_TILE_WIDTH + + (AV1D_MAX_TILE_COLS - 1)); + + return size * UBWC_TILE_SIZE; +} + +static u32 hfi_buffer_line_av1d(u32 frame_width, u32 frame_height, + bool is_opb, u32 num_vpp_pipes) +{ + u32 size, vpss_lb_size, opbwrbufsize, opbwr8, opbwr10; + + size = ALIGN(size_av1d_lb_fe_top_data(frame_width, frame_height), + DMA_ALIGNMENT) + + ALIGN(size_av1d_lb_fe_top_ctrl(frame_width, frame_height), + DMA_ALIGNMENT) + + ALIGN(size_av1d_lb_fe_left_data(frame_width, frame_height), + DMA_ALIGNMENT) * num_vpp_pipes + + ALIGN(size_av1d_lb_fe_left_ctrl(frame_width, frame_height), + DMA_ALIGNMENT) * num_vpp_pipes + + ALIGN(size_av1d_lb_se_left_ctrl(frame_width, frame_height), + DMA_ALIGNMENT) * num_vpp_pipes + + ALIGN(size_av1d_lb_se_top_ctrl(frame_width, frame_height), + DMA_ALIGNMENT) + + ALIGN(size_av1d_lb_pe_top_data(frame_width, frame_height), + DMA_ALIGNMENT) + + ALIGN(size_av1d_lb_vsp_top(frame_width, frame_height), + DMA_ALIGNMENT) + + ALIGN(size_av1d_lb_recon_dma_metadata_wr + (frame_width, frame_height), DMA_ALIGNMENT) * 2 + + ALIGN(size_av1d_qp(frame_width, frame_height), DMA_ALIGNMENT); + opbwr8 = size_av1d_lb_opb_wr1_nv12_ubwc(frame_width, frame_height); + opbwr10 = size_av1d_lb_opb_wr1_tp10_ubwc(frame_width, frame_height); + opbwrbufsize = opbwr8 >= opbwr10 ? opbwr8 : opbwr10; + size = ALIGN((size + opbwrbufsize), DMA_ALIGNMENT); + if (is_opb) { + vpss_lb_size = size_vpss_lb(frame_width, frame_height); + size = ALIGN((size + vpss_lb_size) * 2, DMA_ALIGNMENT); + } + + return size; +} + +static u32 size_av1d_ibc_nv12_ubwc(u32 frame_width, u32 frame_height) +{ + u32 size; + u32 y_width_a = 128, y_height_a = 32; + u32 uv_width_a = 128, uv_height_a = 32; + u32 ybufsize, uvbufsize, y_width, y_height, uv_width, uv_height; + u32 y_meta_width_a = 64, y_meta_height_a = 16; + u32 uv_meta_width_a = 64, uv_meta_height_a = 16; + u32 meta_height, meta_stride, meta_size; + u32 tile_width_y = HFI_COLOR_FORMAT_YUV420_NV12_UBWC_Y_TILE_WIDTH; + u32 tile_height_y = HFI_COLOR_FORMAT_YUV420_NV12_UBWC_Y_TILE_HEIGHT; + u32 tile_width_uv = HFI_COLOR_FORMAT_YUV420_NV12_UBWC_UV_TILE_WIDTH; + u32 tile_height_uv = HFI_COLOR_FORMAT_YUV420_NV12_UBWC_UV_TILE_HEIGHT; + + y_width = ALIGN(frame_width, y_width_a); + y_height = ALIGN(frame_height, y_height_a); + uv_width = ALIGN(frame_width, uv_width_a); + uv_height = ALIGN(((frame_height + 1) >> 1), uv_height_a); + ybufsize = ALIGN((y_width * y_height), HFI_ALIGNMENT_4096); + uvbufsize = ALIGN(uv_width * uv_height, HFI_ALIGNMENT_4096); + size = ybufsize + uvbufsize; + meta_stride = ALIGN(((frame_width + (tile_width_y - 1)) / tile_width_y), + y_meta_width_a); + meta_height = ALIGN(((frame_height + (tile_height_y - 1)) / tile_height_y), + y_meta_height_a); + meta_size = ALIGN(meta_stride * meta_height, HFI_ALIGNMENT_4096); + size += meta_size; + meta_stride = ALIGN(((((frame_width + 1) >> 1) + (tile_width_uv - 1)) / + tile_width_uv), uv_meta_width_a); + meta_height = ALIGN(((((frame_height + 1) >> 1) + (tile_height_uv - 1)) / + tile_height_uv), uv_meta_height_a); + meta_size = ALIGN(meta_stride * meta_height, HFI_ALIGNMENT_4096); + size += meta_size; + + return size; +} + +static u32 hfi_yuv420_tp10_calc_y_stride(u32 frame_width, u32 stride_multiple) +{ + u32 stride; + + stride = ALIGN(frame_width, 192); + stride = ALIGN(stride * 4 / 3, stride_multiple); + + return stride; +} + +static u32 hfi_yuv420_tp10_calc_y_bufheight(u32 frame_height, u32 min_buf_height_multiple) +{ + return ALIGN(frame_height, min_buf_height_multiple); +} + +static u32 hfi_yuv420_tp10_calc_uv_stride(u32 frame_width, u32 stride_multiple) +{ + u32 stride; + + stride = ALIGN(frame_width, 192); + stride = ALIGN(stride * 4 / 3, stride_multiple); + + return stride; +} + +static u32 hfi_yuv420_tp10_calc_uv_bufheight(u32 frame_height, u32 min_buf_height_multiple) +{ + return ALIGN(((frame_height + 1) >> 1), min_buf_height_multiple); +} + +static u32 size_av1d_ibc_tp10_ubwc(u32 frame_width, u32 frame_height) +{ + u32 size; + u32 y_width_a = 256, y_height_a = 16, + uv_width_a = 256, uv_height_a = 16; + u32 ybufsize, uvbufsize, y_width, y_height, uv_width, uv_height; + u32 y_meta_width_a = 64, y_meta_height_a = 16, + uv_meta_width_a = 64, uv_meta_height_a = 16; + u32 meta_height, meta_stride, meta_size; + u32 tile_width_y = HFI_COLOR_FORMAT_YUV420_TP10_UBWC_Y_TILE_WIDTH; + u32 tile_height_y = HFI_COLOR_FORMAT_YUV420_TP10_UBWC_Y_TILE_HEIGHT; + u32 tile_width_uv = HFI_COLOR_FORMAT_YUV420_TP10_UBWC_UV_TILE_WIDTH; + u32 tile_height_uv = HFI_COLOR_FORMAT_YUV420_TP10_UBWC_UV_TILE_HEIGHT; + + y_width = hfi_yuv420_tp10_calc_y_stride(frame_width, y_width_a); + y_height = hfi_yuv420_tp10_calc_y_bufheight(frame_height, y_height_a); + uv_width = hfi_yuv420_tp10_calc_uv_stride(frame_width, uv_width_a); + uv_height = hfi_yuv420_tp10_calc_uv_bufheight(frame_height, uv_height_a); + ybufsize = ALIGN(y_width * y_height, HFI_ALIGNMENT_4096); + uvbufsize = ALIGN(uv_width * uv_height, HFI_ALIGNMENT_4096); + size = ybufsize + uvbufsize; + meta_stride = ALIGN(((frame_width + (tile_width_y - 1)) / tile_width_y), + y_meta_width_a); + meta_height = ALIGN(((frame_height + (tile_height_y - 1)) / tile_height_y), + y_meta_height_a); + meta_size = ALIGN(meta_stride * meta_height, HFI_ALIGNMENT_4096); + size += meta_size; + meta_stride = ALIGN(((((frame_width + 1) >> 1) + (tile_width_uv - 1)) / + tile_width_uv), uv_meta_width_a); + meta_height = ALIGN(((((frame_height + 1) >> 1) + (tile_height_uv - 1)) / + tile_height_uv), uv_meta_height_a); + meta_size = ALIGN(meta_stride * meta_height, HFI_ALIGNMENT_4096); + size += meta_size; + + return size; +} + +static u32 hfi_buffer_ibc_av1d(u32 frame_width, u32 frame_height) +{ + u32 size, ibc8, ibc10; + + ibc8 = size_av1d_ibc_nv12_ubwc(frame_width, frame_height); + ibc10 = size_av1d_ibc_tp10_ubwc(frame_width, frame_height); + size = ibc8 >= ibc10 ? ibc8 : ibc10; + + return ALIGN(size, DMA_ALIGNMENT); +} + static u32 iris_vpu_dec_bin_size(struct iris_inst *inst) { u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; @@ -472,6 +718,8 @@ static u32 iris_vpu_dec_bin_size(struct iris_inst *inst) return hfi_buffer_bin_h265d(width, height, num_vpp_pipes); else if (inst->codec == V4L2_PIX_FMT_VP9) return hfi_buffer_bin_vp9d(width, height, num_vpp_pipes); + else if (inst->codec == V4L2_PIX_FMT_AV1) + return hfi_buffer_bin_av1d(width, height, num_vpp_pipes); return 0; } @@ -487,18 +735,34 @@ static u32 iris_vpu_dec_comv_size(struct iris_inst *inst) return hfi_buffer_comv_h264d(width, height, num_comv); else if (inst->codec == V4L2_PIX_FMT_HEVC) return hfi_buffer_comv_h265d(width, height, num_comv); + else if (inst->codec == V4L2_PIX_FMT_AV1) { + if (inst->fw_caps[DRAP].value) + return 0; + else + return hfi_buffer_comv_av1d(width, height, num_comv); + } return 0; } static u32 iris_vpu_dec_persist_size(struct iris_inst *inst) { + struct platform_inst_caps *caps; + if (inst->codec == V4L2_PIX_FMT_H264) return hfi_buffer_persist_h264d(); else if (inst->codec == V4L2_PIX_FMT_HEVC) return hfi_buffer_persist_h265d(0); else if (inst->codec == V4L2_PIX_FMT_VP9) return hfi_buffer_persist_vp9d(); + else if (inst->codec == V4L2_PIX_FMT_AV1) { + caps = inst->core->iris_platform_data->inst_caps; + if (inst->fw_caps[DRAP].value) + return hfi_buffer_persist_av1d(caps->max_frame_width, + caps->max_frame_height, 16); + else + return hfi_buffer_persist_av1d(0, 0, 0); + } return 0; } @@ -545,6 +809,8 @@ static u32 iris_vpu_dec_line_size(struct iris_inst *inst) else if (inst->codec == V4L2_PIX_FMT_VP9) return hfi_buffer_line_vp9d(width, height, out_min_count, is_opb, num_vpp_pipes); + else if (inst->codec == V4L2_PIX_FMT_AV1) + return hfi_buffer_line_av1d(width, height, is_opb, num_vpp_pipes); return 0; } @@ -556,6 +822,22 @@ static u32 iris_vpu_dec_scratch1_size(struct iris_inst *inst) iris_vpu_dec_line_size(inst); } +static inline u32 iris_vpu_enc_get_bitstream_width(struct iris_inst *inst) +{ + if (is_rotation_90_or_270(inst)) + return inst->fmt_dst->fmt.pix_mp.height; + else + return inst->fmt_dst->fmt.pix_mp.width; +} + +static inline u32 iris_vpu_enc_get_bitstream_height(struct iris_inst *inst) +{ + if (is_rotation_90_or_270(inst)) + return inst->fmt_dst->fmt.pix_mp.width; + else + return inst->fmt_dst->fmt.pix_mp.height; +} + static inline u32 size_bin_bitstream_enc(u32 width, u32 height, u32 rc_type) { @@ -638,10 +920,9 @@ static inline u32 hfi_buffer_bin_enc(u32 width, u32 height, static u32 iris_vpu_enc_bin_size(struct iris_inst *inst) { u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; + u32 height = iris_vpu_enc_get_bitstream_height(inst); + u32 width = iris_vpu_enc_get_bitstream_width(inst); u32 stage = inst->fw_caps[STAGE].value; - struct v4l2_format *f = inst->fmt_dst; - u32 height = f->fmt.pix_mp.height; - u32 width = f->fmt.pix_mp.width; u32 lcu_size; if (inst->codec == V4L2_PIX_FMT_HEVC) @@ -653,6 +934,15 @@ static u32 iris_vpu_enc_bin_size(struct iris_inst *inst) num_vpp_pipes, inst->hfi_rc_type); } +static u32 iris_vpu_dec_partial_size(struct iris_inst *inst) +{ + struct v4l2_format *f = inst->fmt_src; + u32 height = f->fmt.pix_mp.height; + u32 width = f->fmt.pix_mp.width; + + return hfi_buffer_ibc_av1d(width, height); +} + static inline u32 hfi_buffer_comv_enc(u32 frame_width, u32 frame_height, u32 lcu_size, u32 num_recon, u32 standard) @@ -676,9 +966,8 @@ u32 hfi_buffer_comv_enc(u32 frame_width, u32 frame_height, u32 lcu_size, static u32 iris_vpu_enc_comv_size(struct iris_inst *inst) { - struct v4l2_format *f = inst->fmt_dst; - u32 height = f->fmt.pix_mp.height; - u32 width = f->fmt.pix_mp.width; + u32 height = iris_vpu_enc_get_bitstream_height(inst); + u32 width = iris_vpu_enc_get_bitstream_width(inst); u32 num_recon = 1; u32 lcu_size = 16; @@ -958,9 +1247,8 @@ u32 hfi_buffer_non_comv_enc(u32 frame_width, u32 frame_height, static u32 iris_vpu_enc_non_comv_size(struct iris_inst *inst) { u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; - struct v4l2_format *f = inst->fmt_dst; - u32 height = f->fmt.pix_mp.height; - u32 width = f->fmt.pix_mp.width; + u32 height = iris_vpu_enc_get_bitstream_height(inst); + u32 width = iris_vpu_enc_get_bitstream_width(inst); u32 lcu_size = 16; if (inst->codec == V4L2_PIX_FMT_HEVC) { @@ -1051,9 +1339,8 @@ u32 hfi_buffer_line_enc_vpu33(u32 frame_width, u32 frame_height, bool is_ten_bit static u32 iris_vpu_enc_line_size(struct iris_inst *inst) { u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; - struct v4l2_format *f = inst->fmt_dst; - u32 height = f->fmt.pix_mp.height; - u32 width = f->fmt.pix_mp.width; + u32 height = iris_vpu_enc_get_bitstream_height(inst); + u32 width = iris_vpu_enc_get_bitstream_width(inst); u32 lcu_size = 16; if (inst->codec == V4L2_PIX_FMT_HEVC) { @@ -1069,9 +1356,8 @@ static u32 iris_vpu_enc_line_size(struct iris_inst *inst) static u32 iris_vpu33_enc_line_size(struct iris_inst *inst) { u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; - struct v4l2_format *f = inst->fmt_dst; - u32 height = f->fmt.pix_mp.height; - u32 width = f->fmt.pix_mp.width; + u32 height = iris_vpu_enc_get_bitstream_height(inst); + u32 width = iris_vpu_enc_get_bitstream_width(inst); u32 lcu_size = 16; if (inst->codec == V4L2_PIX_FMT_HEVC) { @@ -1131,10 +1417,11 @@ static u32 iris_vpu_enc_arp_size(struct iris_inst *inst) inline bool is_scaling_enabled(struct iris_inst *inst) { - return inst->crop.left != inst->compose.left || - inst->crop.top != inst->compose.top || - inst->crop.width != inst->compose.width || - inst->crop.height != inst->compose.height; + struct v4l2_pix_format_mplane *dst_fmt = &inst->fmt_dst->fmt.pix_mp; + struct v4l2_pix_format_mplane *src_fmt = &inst->fmt_src->fmt.pix_mp; + + return dst_fmt->width != src_fmt->width || + dst_fmt->height != src_fmt->height; } static inline @@ -1291,9 +1578,8 @@ static inline u32 hfi_buffer_scratch1_enc(u32 frame_width, u32 frame_height, static u32 iris_vpu_enc_scratch1_size(struct iris_inst *inst) { u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; - struct v4l2_format *f = inst->fmt_dst; - u32 frame_height = f->fmt.pix_mp.height; - u32 frame_width = f->fmt.pix_mp.width; + u32 frame_height = iris_vpu_enc_get_bitstream_height(inst); + u32 frame_width = iris_vpu_enc_get_bitstream_width(inst); u32 num_ref = 1; u32 lcu_size; bool is_h265; @@ -1389,9 +1675,8 @@ static inline u32 hfi_buffer_scratch2_enc(u32 frame_width, u32 frame_height, static u32 iris_vpu_enc_scratch2_size(struct iris_inst *inst) { - struct v4l2_format *f = inst->fmt_dst; - u32 frame_width = f->fmt.pix_mp.width; - u32 frame_height = f->fmt.pix_mp.height; + u32 frame_height = iris_vpu_enc_get_bitstream_height(inst); + u32 frame_width = iris_vpu_enc_get_bitstream_width(inst); u32 num_ref = 1; return hfi_buffer_scratch2_enc(frame_width, frame_height, num_ref, @@ -1408,13 +1693,313 @@ static u32 iris_vpu_enc_vpss_size(struct iris_inst *inst) return hfi_buffer_vpss_enc(width, height, ds_enable, 0, 0); } +static inline u32 size_dpb_opb(u32 height, u32 lcu_size) +{ + u32 max_tile_height = ((height + lcu_size - 1) / lcu_size) * lcu_size + 8; + u32 dpb_opb = 3 * ((max_tile_height >> 3) * DMA_ALIGNMENT); + u32 num_luma_chrome_plane = 2; + + return ALIGN(dpb_opb, DMA_ALIGNMENT) * num_luma_chrome_plane; +} + +static u32 hfi_vpu4x_vp9d_lb_size(u32 frame_width, u32 frame_height, u32 num_vpp_pipes) +{ + u32 vp9_top_lb, vp9_fe_left_lb, vp9_se_left_lb, dpb_opb, vp9d_qp, num_lcu_per_pipe; + u32 lcu_size = 64; + + vp9_top_lb = ALIGN(size_vp9d_lb_vsp_top(frame_width, frame_height), DMA_ALIGNMENT); + vp9_top_lb += ALIGN(size_vpxd_lb_se_top_ctrl(frame_width, frame_height), DMA_ALIGNMENT); + vp9_top_lb += max3(DIV_ROUND_UP(frame_width, BUFFER_ALIGNMENT_16_BYTES) * + MAX_PE_NBR_DATA_LCU16_LINE_BUFFER_SIZE, + DIV_ROUND_UP(frame_width, BUFFER_ALIGNMENT_32_BYTES) * + MAX_PE_NBR_DATA_LCU32_LINE_BUFFER_SIZE, + DIV_ROUND_UP(frame_width, BUFFER_ALIGNMENT_64_BYTES) * + MAX_PE_NBR_DATA_LCU64_LINE_BUFFER_SIZE); + vp9_top_lb = ALIGN(vp9_top_lb, DMA_ALIGNMENT); + vp9_top_lb += ALIGN((DMA_ALIGNMENT * DIV_ROUND_UP(frame_width, lcu_size)), + DMA_ALIGNMENT) * FE_TOP_CTRL_LINE_NUMBERS; + vp9_top_lb += ALIGN(DMA_ALIGNMENT * 8 * DIV_ROUND_UP(frame_width, lcu_size), + DMA_ALIGNMENT) * (FE_TOP_DATA_LUMA_LINE_NUMBERS + + FE_TOP_DATA_CHROMA_LINE_NUMBERS); + + num_lcu_per_pipe = (DIV_ROUND_UP(frame_height, lcu_size) / num_vpp_pipes) + + (DIV_ROUND_UP(frame_height, lcu_size) % num_vpp_pipes); + vp9_fe_left_lb = ALIGN((DMA_ALIGNMENT * num_lcu_per_pipe), DMA_ALIGNMENT) * + FE_LFT_CTRL_LINE_NUMBERS; + vp9_fe_left_lb += ((ALIGN((DMA_ALIGNMENT * 8 * num_lcu_per_pipe), DMA_ALIGNMENT) * + FE_LFT_DB_DATA_LINE_NUMBERS) + + ALIGN((DMA_ALIGNMENT * 3 * num_lcu_per_pipe), DMA_ALIGNMENT) + + ALIGN((DMA_ALIGNMENT * 4 * num_lcu_per_pipe), DMA_ALIGNMENT) + + (ALIGN((DMA_ALIGNMENT * 24 * num_lcu_per_pipe), DMA_ALIGNMENT) * + FE_LFT_LR_DATA_LINE_NUMBERS)); + vp9_fe_left_lb = vp9_fe_left_lb * num_vpp_pipes; + + vp9_se_left_lb = ALIGN(size_vpxd_lb_se_left_ctrl(frame_width, frame_height), + DMA_ALIGNMENT); + dpb_opb = size_dpb_opb(frame_height, lcu_size); + vp9d_qp = ALIGN(size_vp9d_qp(frame_width, frame_height), DMA_ALIGNMENT); + + return vp9_top_lb + vp9_fe_left_lb + (vp9_se_left_lb * num_vpp_pipes) + + (dpb_opb * num_vpp_pipes) + vp9d_qp; +} + +static u32 hfi_vpu4x_buffer_line_vp9d(u32 frame_width, u32 frame_height, u32 _yuv_bufcount_min, + bool is_opb, u32 num_vpp_pipes) +{ + u32 lb_size = hfi_vpu4x_vp9d_lb_size(frame_width, frame_height, num_vpp_pipes); + u32 dpb_obp_size = 0, lcu_size = 64; + + if (is_opb) + dpb_obp_size = size_dpb_opb(frame_height, lcu_size) * num_vpp_pipes; + + return lb_size + dpb_obp_size; +} + +static u32 iris_vpu4x_dec_line_size(struct iris_inst *inst) +{ + u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; + u32 out_min_count = inst->buffers[BUF_OUTPUT].min_count; + struct v4l2_format *f = inst->fmt_src; + u32 height = f->fmt.pix_mp.height; + u32 width = f->fmt.pix_mp.width; + bool is_opb = false; + + if (iris_split_mode_enabled(inst)) + is_opb = true; + + if (inst->codec == V4L2_PIX_FMT_H264) + return hfi_buffer_line_h264d(width, height, is_opb, num_vpp_pipes); + else if (inst->codec == V4L2_PIX_FMT_HEVC) + return hfi_buffer_line_h265d(width, height, is_opb, num_vpp_pipes); + else if (inst->codec == V4L2_PIX_FMT_VP9) + return hfi_vpu4x_buffer_line_vp9d(width, height, out_min_count, is_opb, + num_vpp_pipes); + + return 0; +} + +static u32 hfi_vpu4x_buffer_persist_h265d(u32 rpu_enabled) +{ + return ALIGN((SIZE_SLIST_BUF_H265 * NUM_SLIST_BUF_H265 + H265_NUM_FRM_INFO * + H265_DISPLAY_BUF_SIZE + (H265_NUM_TILE * sizeof(u32)) + (NUM_HW_PIC_BUF * + (SIZE_SEI_USERDATA + SIZE_H265D_ARP + SIZE_THREE_DIMENSION_USERDATA)) + + rpu_enabled * NUM_HW_PIC_BUF * SIZE_DOLBY_RPU_METADATA), DMA_ALIGNMENT); +} + +static u32 hfi_vpu4x_buffer_persist_vp9d(void) +{ + return ALIGN(VP9_NUM_PROBABILITY_TABLE_BUF * VP9_PROB_TABLE_SIZE, DMA_ALIGNMENT) + + (ALIGN(hfi_iris3_vp9d_comv_size(), DMA_ALIGNMENT) * 2) + + ALIGN(MAX_SUPERFRAME_HEADER_LEN, DMA_ALIGNMENT) + + ALIGN(VP9_UDC_HEADER_BUF_SIZE, DMA_ALIGNMENT) + + ALIGN(VP9_NUM_FRAME_INFO_BUF * CCE_TILE_OFFSET_SIZE, DMA_ALIGNMENT) + + ALIGN(VP9_NUM_FRAME_INFO_BUF * VP9_FRAME_INFO_BUF_SIZE_VPU4X, DMA_ALIGNMENT) + + HDR10_HIST_EXTRADATA_SIZE; +} + +static u32 iris_vpu4x_dec_persist_size(struct iris_inst *inst) +{ + if (inst->codec == V4L2_PIX_FMT_H264) + return hfi_buffer_persist_h264d(); + else if (inst->codec == V4L2_PIX_FMT_HEVC) + return hfi_vpu4x_buffer_persist_h265d(0); + else if (inst->codec == V4L2_PIX_FMT_VP9) + return hfi_vpu4x_buffer_persist_vp9d(); + + return 0; +} + +static u32 size_se_lb(u32 standard, u32 num_vpp_pipes_enc, + u32 frame_width_coded, u32 frame_height_coded) +{ + u32 se_tlb_size = ALIGN(frame_width_coded, DMA_ALIGNMENT); + u32 se_llb_size = (standard == HFI_CODEC_ENCODE_HEVC) ? + ((frame_height_coded + BUFFER_ALIGNMENT_32_BYTES - 1) / + BUFFER_ALIGNMENT_32_BYTES) * LOG2_16 * LLB_UNIT_SIZE : + ((frame_height_coded + BUFFER_ALIGNMENT_16_BYTES - 1) / + BUFFER_ALIGNMENT_16_BYTES) * LOG2_32 * LLB_UNIT_SIZE; + + se_llb_size = ALIGN(se_llb_size, BUFFER_ALIGNMENT_32_BYTES); + + if (num_vpp_pipes_enc > 1) + se_llb_size = ALIGN(se_llb_size + BUFFER_ALIGNMENT_512_BYTES, + DMA_ALIGNMENT) * num_vpp_pipes_enc; + + return ALIGN(se_tlb_size + se_llb_size, DMA_ALIGNMENT); +} + +static u32 size_te_lb(bool is_ten_bit, u32 num_vpp_pipes_enc, u32 width_in_lcus, + u32 frame_height_coded, u32 frame_width_coded) +{ + u32 num_pixel_10_bit = 3, num_pixel_8_bit = 2, num_pixel_te_llb = 3; + u32 te_llb_col_rc_size = ALIGN(32 * width_in_lcus / num_vpp_pipes_enc, + DMA_ALIGNMENT) * num_vpp_pipes_enc; + u32 te_tlb_recon_data_size = ALIGN((is_ten_bit ? num_pixel_10_bit : num_pixel_8_bit) * + frame_width_coded, DMA_ALIGNMENT); + u32 te_llb_recon_data_size = ((1 + is_ten_bit) * num_pixel_te_llb * frame_height_coded + + num_vpp_pipes_enc - 1) / num_vpp_pipes_enc; + te_llb_recon_data_size = ALIGN(te_llb_recon_data_size, DMA_ALIGNMENT) * num_vpp_pipes_enc; + + return ALIGN(te_llb_recon_data_size + te_llb_col_rc_size + te_tlb_recon_data_size, + DMA_ALIGNMENT); +} + +static inline u32 calc_fe_tlb_size(u32 size_per_lcu, bool is_ten_bit) +{ + u32 num_pixels_fe_tlb_10_bit = 128, num_pixels_fe_tlb_8_bit = 64; + + return is_ten_bit ? (num_pixels_fe_tlb_10_bit * (size_per_lcu + 1)) : + (size_per_lcu * num_pixels_fe_tlb_8_bit); +} + +static u32 size_fe_lb(bool is_ten_bit, u32 standard, u32 num_vpp_pipes_enc, + u32 frame_height_coded, u32 frame_width_coded) +{ + u32 log2_lcu_size, num_cu_in_height_pipe, num_cu_in_width, + fb_llb_db_ctrl_size, fb_llb_db_luma_size, fb_llb_db_chroma_size, + fb_tlb_db_ctrl_size, fb_tlb_db_luma_size, fb_tlb_db_chroma_size, + fb_llb_sao_ctrl_size, fb_llb_sao_luma_size, fb_llb_sao_chroma_size, + fb_tlb_sao_ctrl_size, fb_tlb_sao_luma_size, fb_tlb_sao_chroma_size, + fb_lb_top_sdc_size, fb_lb_se_ctrl_size, fe_tlb_size, size_per_lcu; + + log2_lcu_size = (standard == HFI_CODEC_ENCODE_HEVC) ? 5 : 4; + num_cu_in_height_pipe = ((frame_height_coded >> log2_lcu_size) + num_vpp_pipes_enc - 1) / + num_vpp_pipes_enc; + num_cu_in_width = frame_width_coded >> log2_lcu_size; + + size_per_lcu = 2; + fe_tlb_size = calc_fe_tlb_size(size_per_lcu, 1); + fb_llb_db_ctrl_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_height_pipe; + fb_llb_db_ctrl_size = ALIGN(fb_llb_db_ctrl_size, DMA_ALIGNMENT) * num_vpp_pipes_enc; + + size_per_lcu = (1 << (log2_lcu_size - 3)); + fe_tlb_size = calc_fe_tlb_size(size_per_lcu, is_ten_bit); + fb_llb_db_luma_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_height_pipe; + fb_llb_db_luma_size = ALIGN(fb_llb_db_luma_size, DMA_ALIGNMENT) * num_vpp_pipes_enc; + + size_per_lcu = ((1 << (log2_lcu_size - 4)) * 2); + fe_tlb_size = calc_fe_tlb_size(size_per_lcu, is_ten_bit); + fb_llb_db_chroma_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_height_pipe; + fb_llb_db_chroma_size = ALIGN(fb_llb_db_chroma_size, DMA_ALIGNMENT) * num_vpp_pipes_enc; + + size_per_lcu = 1; + fe_tlb_size = calc_fe_tlb_size(size_per_lcu, 1); + fb_tlb_db_ctrl_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_width; + fb_llb_sao_ctrl_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_height_pipe; + fb_llb_sao_ctrl_size = fb_llb_sao_ctrl_size * num_vpp_pipes_enc; + fb_tlb_sao_ctrl_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_width; + + size_per_lcu = ((1 << (log2_lcu_size - 3)) + 1); + fe_tlb_size = calc_fe_tlb_size(size_per_lcu, is_ten_bit); + fb_tlb_db_luma_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_width; + + size_per_lcu = (2 * ((1 << (log2_lcu_size - 4)) + 1)); + fe_tlb_size = calc_fe_tlb_size(size_per_lcu, is_ten_bit); + fb_tlb_db_chroma_size = ALIGN(fe_tlb_size, DMA_ALIGNMENT) * num_cu_in_width; + + fb_llb_sao_luma_size = BUFFER_ALIGNMENT_256_BYTES * num_vpp_pipes_enc; + fb_llb_sao_chroma_size = BUFFER_ALIGNMENT_256_BYTES * num_vpp_pipes_enc; + fb_tlb_sao_luma_size = BUFFER_ALIGNMENT_256_BYTES; + fb_tlb_sao_chroma_size = BUFFER_ALIGNMENT_256_BYTES; + fb_lb_top_sdc_size = ALIGN((FE_SDC_DATA_PER_BLOCK * (frame_width_coded >> 5)), + DMA_ALIGNMENT); + fb_lb_se_ctrl_size = ALIGN((SE_CTRL_DATA_PER_BLOCK * (frame_width_coded >> 5)), + DMA_ALIGNMENT); + + return fb_llb_db_ctrl_size + fb_llb_db_luma_size + fb_llb_db_chroma_size + + fb_tlb_db_ctrl_size + fb_tlb_db_luma_size + fb_tlb_db_chroma_size + + fb_llb_sao_ctrl_size + fb_llb_sao_luma_size + fb_llb_sao_chroma_size + + fb_tlb_sao_ctrl_size + fb_tlb_sao_luma_size + fb_tlb_sao_chroma_size + + fb_lb_top_sdc_size + fb_lb_se_ctrl_size; +} + +static u32 size_md_lb(u32 standard, u32 frame_width_coded, + u32 frame_height_coded, u32 num_vpp_pipes_enc) +{ + u32 md_tlb_size = ALIGN(frame_width_coded, DMA_ALIGNMENT); + u32 md_llb_size = (standard == HFI_CODEC_ENCODE_HEVC) ? + ((frame_height_coded + BUFFER_ALIGNMENT_32_BYTES - 1) / + BUFFER_ALIGNMENT_32_BYTES) * LOG2_16 * LLB_UNIT_SIZE : + ((frame_height_coded + BUFFER_ALIGNMENT_16_BYTES - 1) / + BUFFER_ALIGNMENT_16_BYTES) * LOG2_32 * LLB_UNIT_SIZE; + + md_llb_size = ALIGN(md_llb_size, BUFFER_ALIGNMENT_32_BYTES); + + if (num_vpp_pipes_enc > 1) + md_llb_size = ALIGN(md_llb_size + BUFFER_ALIGNMENT_512_BYTES, + DMA_ALIGNMENT) * num_vpp_pipes_enc; + + md_llb_size = ALIGN(md_llb_size, DMA_ALIGNMENT); + + return ALIGN(md_tlb_size + md_llb_size, DMA_ALIGNMENT); +} + +static u32 size_dma_opb_lb(u32 num_vpp_pipes_enc, u32 frame_width_coded, + u32 frame_height_coded) +{ + u32 opb_packet_bytes = 128, opb_bpp = 128, opb_size_per_row = 6; + u32 dma_opb_wr_tlb_y_size = DIV_ROUND_UP(frame_width_coded, 16) * opb_packet_bytes; + u32 dma_opb_wr_tlb_uv_size = DIV_ROUND_UP(frame_width_coded, 16) * opb_packet_bytes; + u32 dma_opb_wr2_tlb_y_size = ALIGN((opb_bpp * opb_size_per_row * frame_height_coded / 8), + DMA_ALIGNMENT) * num_vpp_pipes_enc; + u32 dma_opb_wr2_tlb_uv_size = ALIGN((opb_bpp * opb_size_per_row * frame_height_coded / 8), + DMA_ALIGNMENT) * num_vpp_pipes_enc; + + dma_opb_wr2_tlb_y_size = max(dma_opb_wr2_tlb_y_size, dma_opb_wr_tlb_y_size << 1); + dma_opb_wr2_tlb_uv_size = max(dma_opb_wr2_tlb_uv_size, dma_opb_wr_tlb_uv_size << 1); + + return ALIGN(dma_opb_wr_tlb_y_size + dma_opb_wr_tlb_uv_size + dma_opb_wr2_tlb_y_size + + dma_opb_wr2_tlb_uv_size, DMA_ALIGNMENT); +} + +static u32 hfi_vpu4x_buffer_line_enc(u32 frame_width, u32 frame_height, + bool is_ten_bit, u32 num_vpp_pipes_enc, + u32 lcu_size, u32 standard) +{ + u32 width_in_lcus = (frame_width + lcu_size - 1) / lcu_size; + u32 height_in_lcus = (frame_height + lcu_size - 1) / lcu_size; + u32 frame_width_coded = width_in_lcus * lcu_size; + u32 frame_height_coded = height_in_lcus * lcu_size; + + u32 se_lb_size = size_se_lb(standard, num_vpp_pipes_enc, frame_width_coded, + frame_height_coded); + u32 te_lb_size = size_te_lb(is_ten_bit, num_vpp_pipes_enc, width_in_lcus, + frame_height_coded, frame_width_coded); + u32 fe_lb_size = size_fe_lb(is_ten_bit, standard, num_vpp_pipes_enc, frame_height_coded, + frame_width_coded); + u32 md_lb_size = size_md_lb(standard, frame_width_coded, frame_height_coded, + num_vpp_pipes_enc); + u32 dma_opb_lb_size = size_dma_opb_lb(num_vpp_pipes_enc, frame_width_coded, + frame_height_coded); + u32 dse_lb_size = ALIGN((256 + (16 * (frame_width_coded >> 4))), DMA_ALIGNMENT); + u32 size_vpss_lb_enc = size_vpss_line_buf_vpu33(num_vpp_pipes_enc, frame_width_coded, + frame_height_coded); + + return se_lb_size + te_lb_size + fe_lb_size + md_lb_size + dma_opb_lb_size + + dse_lb_size + size_vpss_lb_enc; +} + +static u32 iris_vpu4x_enc_line_size(struct iris_inst *inst) +{ + u32 num_vpp_pipes = inst->core->iris_platform_data->num_vpp_pipe; + u32 lcu_size = inst->codec == V4L2_PIX_FMT_HEVC ? 32 : 16; + struct v4l2_format *f = inst->fmt_dst; + u32 height = f->fmt.pix_mp.height; + u32 width = f->fmt.pix_mp.width; + + return hfi_vpu4x_buffer_line_enc(width, height, 0, num_vpp_pipes, + lcu_size, inst->codec); +} + static int output_min_count(struct iris_inst *inst) { int output_min_count = 4; /* fw_min_count > 0 indicates reconfig event has already arrived */ if (inst->fw_min_count) { - if (iris_split_mode_enabled(inst) && inst->codec == V4L2_PIX_FMT_VP9) + if (iris_split_mode_enabled(inst) && + (inst->codec == V4L2_PIX_FMT_VP9 || + inst->codec == V4L2_PIX_FMT_AV1)) return min_t(u32, 4, inst->fw_min_count); else return inst->fw_min_count; @@ -1422,6 +2007,8 @@ static int output_min_count(struct iris_inst *inst) if (inst->codec == V4L2_PIX_FMT_VP9) output_min_count = 9; + else if (inst->codec == V4L2_PIX_FMT_AV1) + output_min_count = 11; return output_min_count; } @@ -1444,6 +2031,7 @@ u32 iris_vpu_buf_size(struct iris_inst *inst, enum iris_buffer_type buffer_type) {BUF_PERSIST, iris_vpu_dec_persist_size }, {BUF_DPB, iris_vpu_dec_dpb_size }, {BUF_SCRATCH_1, iris_vpu_dec_scratch1_size }, + {BUF_PARTIAL, iris_vpu_dec_partial_size }, }; static const struct iris_vpu_buf_type_handle enc_internal_buf_type_handle[] = { @@ -1503,6 +2091,50 @@ u32 iris_vpu33_buf_size(struct iris_inst *inst, enum iris_buffer_type buffer_typ return size; } +u32 iris_vpu4x_buf_size(struct iris_inst *inst, enum iris_buffer_type buffer_type) +{ + const struct iris_vpu_buf_type_handle *buf_type_handle_arr = NULL; + u32 size = 0, buf_type_handle_size = 0, i; + + static const struct iris_vpu_buf_type_handle dec_internal_buf_type_handle[] = { + {BUF_BIN, iris_vpu_dec_bin_size }, + {BUF_COMV, iris_vpu_dec_comv_size }, + {BUF_NON_COMV, iris_vpu_dec_non_comv_size }, + {BUF_LINE, iris_vpu4x_dec_line_size }, + {BUF_PERSIST, iris_vpu4x_dec_persist_size }, + {BUF_DPB, iris_vpu_dec_dpb_size }, + {BUF_SCRATCH_1, iris_vpu_dec_scratch1_size }, + }; + + static const struct iris_vpu_buf_type_handle enc_internal_buf_type_handle[] = { + {BUF_BIN, iris_vpu_enc_bin_size }, + {BUF_COMV, iris_vpu_enc_comv_size }, + {BUF_NON_COMV, iris_vpu_enc_non_comv_size }, + {BUF_LINE, iris_vpu4x_enc_line_size }, + {BUF_ARP, iris_vpu_enc_arp_size }, + {BUF_VPSS, iris_vpu_enc_vpss_size }, + {BUF_SCRATCH_1, iris_vpu_enc_scratch1_size }, + {BUF_SCRATCH_2, iris_vpu_enc_scratch2_size }, + }; + + if (inst->domain == DECODER) { + buf_type_handle_size = ARRAY_SIZE(dec_internal_buf_type_handle); + buf_type_handle_arr = dec_internal_buf_type_handle; + } else if (inst->domain == ENCODER) { + buf_type_handle_size = ARRAY_SIZE(enc_internal_buf_type_handle); + buf_type_handle_arr = enc_internal_buf_type_handle; + } + + for (i = 0; i < buf_type_handle_size; i++) { + if (buf_type_handle_arr[i].type == buffer_type) { + size = buf_type_handle_arr[i].handle(inst); + break; + } + } + + return size; +} + static u32 internal_buffer_count(struct iris_inst *inst, enum iris_buffer_type buffer_type) { @@ -1510,14 +2142,20 @@ static u32 internal_buffer_count(struct iris_inst *inst, buffer_type == BUF_PERSIST) { return 1; } else if (buffer_type == BUF_COMV || buffer_type == BUF_NON_COMV) { - if (inst->codec == V4L2_PIX_FMT_H264 || inst->codec == V4L2_PIX_FMT_HEVC) + if (inst->codec == V4L2_PIX_FMT_H264 || + inst->codec == V4L2_PIX_FMT_HEVC || + inst->codec == V4L2_PIX_FMT_AV1) return 1; } + return 0; } static inline int iris_vpu_dpb_count(struct iris_inst *inst) { + if (inst->codec == V4L2_PIX_FMT_AV1) + return 11; + if (iris_split_mode_enabled(inst)) { return inst->fw_min_count ? inst->fw_min_count : inst->buffers[BUF_OUTPUT].min_count; @@ -1536,9 +2174,13 @@ int iris_vpu_buf_count(struct iris_inst *inst, enum iris_buffer_type buffer_type return MIN_BUFFERS; else return output_min_count(inst); + case BUF_NON_COMV: + if (inst->codec == V4L2_PIX_FMT_AV1) + return 0; + else + return 1; case BUF_BIN: case BUF_COMV: - case BUF_NON_COMV: case BUF_LINE: case BUF_PERSIST: return internal_buffer_count(inst, buffer_type); @@ -1546,6 +2188,7 @@ int iris_vpu_buf_count(struct iris_inst *inst, enum iris_buffer_type buffer_type case BUF_SCRATCH_2: case BUF_VPSS: case BUF_ARP: + case BUF_PARTIAL: return 1; /* internal buffer count needed by firmware is 1 */ case BUF_DPB: return iris_vpu_dpb_count(inst); |