Re: [PATCH 02/12] media: hantro: Do not reorder H264 scaling list

[Philipp Zabel <p.zabel@pengutronix.de>]

Hi Jonas,

On Sun, 2019-09-01 at 12:45 +0000, Jonas Karlman wrote:
> Scaling list supplied from userspace using ffmpeg and libva-v4l2-request
> is already in matrix order and can be used without applying the inverse
> scanning process.

"in matrix order" is equivalent to "in raster scan order"?

Could you add this requirement to the
V4L2_CID_MPEG_VIDEO_H264_SCALING_MATRIX documentation?

> The HW also only support 8x8 scaling list for the Y component, indices 0
> and 3 in the scaling list supplied from userspace.
> 
> Remove reordering and write the scaling matrix in an order expected by
> the VPU, also only allocate memory for the two 8x8 lists used.
> 
> Fixes: a9471e25629b ("media: hantro: Add core bits to support H264 decoding")
> Signed-off-by: Jonas Karlman <jonas@kwiboo.se>
> ---
>  drivers/staging/media/hantro/hantro_h264.c | 64 +++++++---------------
>  1 file changed, 20 insertions(+), 44 deletions(-)
> 
> diff --git a/drivers/staging/media/hantro/hantro_h264.c b/drivers/staging/media/hantro/hantro_h264.c
> index 0d758e0c0f99..e2d01145ac4f 100644
> --- a/drivers/staging/media/hantro/hantro_h264.c
> +++ b/drivers/staging/media/hantro/hantro_h264.c
> @@ -20,7 +20,7 @@
>  /* Size with u32 units. */
>  #define CABAC_INIT_BUFFER_SIZE		(460 * 2)
>  #define POC_BUFFER_SIZE			34
> -#define SCALING_LIST_SIZE		(6 * 16 + 6 * 64)
> +#define SCALING_LIST_SIZE		(6 * 16 + 2 * 64)

This changes the size of struct hantro_h264_dec_priv_tbl. Did this
describe the auxiliary buffer format incorrectly before?

>  #define POC_CMP(p0, p1) ((p0) < (p1) ? -1 : 1)
>  
> @@ -194,57 +194,33 @@ static const u32 h264_cabac_table[] = {
>  	0x1f0c2517, 0x1f261440
>  };
>  
> -/*
> - * NOTE: The scaling lists are in zig-zag order, apply inverse scanning process
> - * to get the values in matrix order. In addition, the hardware requires bytes
> - * swapped within each subsequent 4 bytes. Both arrays below include both
> - * transformations.
> - */
> -static const u32 zig_zag_4x4[] = {
> -	3, 2, 7, 11, 6, 1, 0, 5, 10, 15, 14, 9, 4, 8, 13, 12
> -};
> -
> -static const u32 zig_zag_8x8[] = {
> -	3, 2, 11, 19, 10, 1, 0, 9, 18, 27, 35, 26, 17, 8, 7, 6,
> -	15, 16, 25, 34, 43, 51, 42, 33, 24, 23, 14, 5, 4, 13, 22, 31,
> -	32, 41, 50, 59, 58, 49, 40, 39, 30, 21, 12, 20, 29, 38, 47, 48,
> -	57, 56, 55, 46, 37, 28, 36, 45, 54, 63, 62, 53, 44, 52, 61, 60
> -};
> -
>  static void
>  reorder_scaling_list(struct hantro_ctx *ctx)
>  {
>  	const struct hantro_h264_dec_ctrls *ctrls = &ctx->h264_dec.ctrls;
>  	const struct v4l2_ctrl_h264_scaling_matrix *scaling = ctrls->scaling;
> -	const size_t num_list_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4);
> -	const size_t list_len_4x4 = ARRAY_SIZE(scaling->scaling_list_4x4[0]);
> -	const size_t num_list_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8);
> -	const size_t list_len_8x8 = ARRAY_SIZE(scaling->scaling_list_8x8[0]);
>  	struct hantro_h264_dec_priv_tbl *tbl = ctx->h264_dec.priv.cpu;
> -	u8 *dst = tbl->scaling_list;
> -	const u8 *src;
> -	int i, j;
> -
> -	BUILD_BUG_ON(ARRAY_SIZE(zig_zag_4x4) != list_len_4x4);
> -	BUILD_BUG_ON(ARRAY_SIZE(zig_zag_8x8) != list_len_8x8);
> -	BUILD_BUG_ON(ARRAY_SIZE(tbl->scaling_list) !=
> -		     num_list_4x4 * list_len_4x4 +
> -		     num_list_8x8 * list_len_8x8);
> -
> -	src = &scaling->scaling_list_4x4[0][0];
> -	for (i = 0; i < num_list_4x4; ++i) {
> -		for (j = 0; j < list_len_4x4; ++j)
> -			dst[zig_zag_4x4[j]] = src[j];
> -		src += list_len_4x4;
> -		dst += list_len_4x4;
> +	u32 *dst = (u32 *)tbl->scaling_list;
> +	u32 i, j, tmp;
> +
> +	for (i = 0; i < ARRAY_SIZE(scaling->scaling_list_4x4); i++) {
> +		for (j = 0; j < ARRAY_SIZE(scaling->scaling_list_4x4[0]) / 4; j++) {
> +			tmp = (scaling->scaling_list_4x4[i][4 * j + 0] << 24) |
> +			      (scaling->scaling_list_4x4[i][4 * j + 1] << 16) |
> +			      (scaling->scaling_list_4x4[i][4 * j + 2] << 8) |
> +			      (scaling->scaling_list_4x4[i][4 * j + 3]);
> +			*dst++ = tmp;
> +		}

This looks like it could use swab32().

>  	}
>  
> -	src = &scaling->scaling_list_8x8[0][0];
> -	for (i = 0; i < num_list_8x8; ++i) {
> -		for (j = 0; j < list_len_8x8; ++j)
> -			dst[zig_zag_8x8[j]] = src[j];
> -		src += list_len_8x8;
> -		dst += list_len_8x8;
> +	for (i = 0; i < ARRAY_SIZE(scaling->scaling_list_8x8); i += 3) {
> +		for (j = 0; j < ARRAY_SIZE(scaling->scaling_list_8x8[0]) / 4; j++) {
> +			tmp = (scaling->scaling_list_8x8[i][4 * j + 0] << 24) |
> +			      (scaling->scaling_list_8x8[i][4 * j + 1] << 16) |
> +			      (scaling->scaling_list_8x8[i][4 * j + 2] << 8) |
> +			      (scaling->scaling_list_8x8[i][4 * j + 3]);
> +			*dst++ = tmp;
> +		}

After this change, the second 8x8 scaling list has moved to a different
offset. Is this where the hardware has always been looking for it, or is
there a change missing in another place?

regards
Philipp