From a8fe996084e358c6f4ec7c51ec28fd3c1ddf68d1 Mon Sep 17 00:00:00 2001 From: Jonas Karlman Date: Wed, 6 Nov 2019 23:34:21 +0100 Subject: media: hantro: Reduce H264 extra space for motion vectors A decoded 8-bit 4:2:0 frame need memory for up to 448 bytes per macroblock with additional 32 bytes on multi-core variants. Memory layout is as follow: +---------------------------+ | Y-plane 256 bytes x MBs | +---------------------------+ | UV-plane 128 bytes x MBs | +---------------------------+ | MV buffer 64 bytes x MBs | +---------------------------+ | MC sync 32 bytes | +---------------------------+ Reduce the extra space allocated now that motion vector buffer offset no longer is based on the extra space. Only allocate extra space for 64 bytes x MBs of motion vector buffer and 32 bytes for multi-core sync. Fixes: a9471e25629b ("media: hantro: Add core bits to support H264 decoding") Signed-off-by: Jonas Karlman Reviewed-by: Boris Brezillon Signed-off-by: Hans Verkuil Signed-off-by: Mauro Carvalho Chehab --- drivers/staging/media/hantro/hantro_v4l2.c | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) (limited to 'drivers/staging') diff --git a/drivers/staging/media/hantro/hantro_v4l2.c b/drivers/staging/media/hantro/hantro_v4l2.c index fcf95c1d39ca..1dae76f20034 100644 --- a/drivers/staging/media/hantro/hantro_v4l2.c +++ b/drivers/staging/media/hantro/hantro_v4l2.c @@ -240,14 +240,30 @@ static int vidioc_try_fmt(struct file *file, void *priv, struct v4l2_format *f, v4l2_fill_pixfmt_mp(pix_mp, fmt->fourcc, pix_mp->width, pix_mp->height); /* + * A decoded 8-bit 4:2:0 NV12 frame may need memory for up to + * 448 bytes per macroblock with additional 32 bytes on + * multi-core variants. + * * The H264 decoder needs extra space on the output buffers * to store motion vectors. This is needed for reference * frames. + * + * Memory layout is as follow: + * + * +---------------------------+ + * | Y-plane 256 bytes x MBs | + * +---------------------------+ + * | UV-plane 128 bytes x MBs | + * +---------------------------+ + * | MV buffer 64 bytes x MBs | + * +---------------------------+ + * | MC sync 32 bytes | + * +---------------------------+ */ if (ctx->vpu_src_fmt->fourcc == V4L2_PIX_FMT_H264_SLICE) pix_mp->plane_fmt[0].sizeimage += - 128 * DIV_ROUND_UP(pix_mp->width, 16) * - DIV_ROUND_UP(pix_mp->height, 16); + 64 * MB_WIDTH(pix_mp->width) * + MB_WIDTH(pix_mp->height) + 32; } else if (!pix_mp->plane_fmt[0].sizeimage) { /* * For coded formats the application can specify -- cgit v1.2.3-59-g8ed1b