media: hantro: Add scaling lists feature

If the bitstream embedded scaling lists allow the driver to use
them for decode the frames.
The scaling lists are expected to be in raster scan order (i.e. not up
right diagonal scan order)
Allocate the memory needed to store lists.
Signed-off-by: Benjamin Gaignard <benjamin.gaignard@collabora.com>
Reviewed-by: Ezequiel Garcia <ezequiel@collabora.com>
Signed-off-by: Hans Verkuil <hverkuil-cisco@xs4all.nl>
[hverkuil: add missing @scaling kernel doc description in hantro_hw.h]
Signed-off-by: Mauro Carvalho Chehab <mchehab+huawei@kernel.org>

drivers/staging/media/hantro/hantro_drv.c

@@ -263,9 +263,6 @@ static int hantro_try_ctrl(struct v4l2_ctrl *ctrl)
 		if (sps->bit_depth_luma_minus8 != 0)
 			/* Only 8-bit is supported */
 			return -EINVAL;
-		if (sps->flags & V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED)
-			/* No scaling support */
-			return -EINVAL;
 	}
 	return 0;
 }
@@ -447,6 +444,11 @@ static const struct hantro_ctrl controls[] = {
 		.cfg = {
 			.id = V4L2_CID_MPEG_VIDEO_HEVC_DECODE_PARAMS,
 		},
+	}, {
+		.codec = HANTRO_HEVC_DECODER,
+		.cfg = {
+			.id = V4L2_CID_MPEG_VIDEO_HEVC_SCALING_MATRIX,
+		},
 	}, {
 		.codec = HANTRO_HEVC_DECODER,
 		.cfg = {

drivers/staging/media/hantro/hantro_g2_hevc_dec.c

@@ -516,6 +516,56 @@ static void set_buffers(struct hantro_ctx *ctx)
 	hantro_write_addr(vpu, G2_TILE_BSD, ctx->hevc_dec.tile_bsd.dma);
 }
 
+static void prepare_scaling_list_buffer(struct hantro_ctx *ctx)
+{
+	struct hantro_dev *vpu = ctx->dev;
+	const struct hantro_hevc_dec_ctrls *ctrls = &ctx->hevc_dec.ctrls;
+	const struct v4l2_ctrl_hevc_scaling_matrix *sc = ctrls->scaling;
+	const struct v4l2_ctrl_hevc_sps *sps = ctrls->sps;
+	u8 *p = ((u8 *)ctx->hevc_dec.scaling_lists.cpu);
+	unsigned int scaling_list_enabled;
+	unsigned int i, j, k;
+
+	scaling_list_enabled = !!(sps->flags & V4L2_HEVC_SPS_FLAG_SCALING_LIST_ENABLED);
+	hantro_reg_write(vpu, &g2_scaling_list_e, scaling_list_enabled);
+
+	if (!scaling_list_enabled)
+		return;
+
+	for (i = 0; i < ARRAY_SIZE(sc->scaling_list_dc_coef_16x16); i++)
+		*p++ = sc->scaling_list_dc_coef_16x16[i];
+
+	for (i = 0; i < ARRAY_SIZE(sc->scaling_list_dc_coef_32x32); i++)
+		*p++ = sc->scaling_list_dc_coef_32x32[i];
+
+	/* 128-bit boundary */
+	p += 8;
+
+	/* write scaling lists column by column */
+
+	for (i = 0; i < 6; i++)
+		for (j = 0; j < 4; j++)
+			for (k = 0; k < 4; k++)
+				*p++ = sc->scaling_list_4x4[i][4 * k + j];
+
+	for (i = 0; i < 6; i++)
+		for (j = 0; j < 8; j++)
+			for (k = 0; k < 8; k++)
+				*p++ = sc->scaling_list_8x8[i][8 * k + j];
+
+	for (i = 0; i < 6; i++)
+		for (j = 0; j < 8; j++)
+			for (k = 0; k < 8; k++)
+				*p++ = sc->scaling_list_16x16[i][8 * k + j];
+
+	for (i = 0; i < 2; i++)
+		for (j = 0; j < 8; j++)
+			for (k = 0; k < 8; k++)
+				*p++ = sc->scaling_list_32x32[i][8 * k + j];
+
+	hantro_write_addr(vpu, HEVC_SCALING_LIST, ctx->hevc_dec.scaling_lists.dma);
+}
+
 static void hantro_g2_check_idle(struct hantro_dev *vpu)
 {
 	int i;
@@ -556,6 +606,8 @@ int hantro_g2_hevc_dec_run(struct hantro_ctx *ctx)
 	set_buffers(ctx);
 	prepare_tile_info_buffer(ctx);
 
+	prepare_scaling_list_buffer(ctx);
+
 	hantro_end_prepare_run(ctx);
 
 	hantro_reg_write(vpu, &g2_mode, HEVC_DEC_MODE);

drivers/staging/media/hantro/hantro_hevc.c

@@ -20,6 +20,8 @@
 /* tile border coefficients of filter */
 #define VERT_SAO_RAM_SIZE 48 /* bytes per pixel */
 
+#define SCALING_LIST_SIZE (16 * 64)
+
 #define MAX_TILE_COLS 20
 #define MAX_TILE_ROWS 22
 
@@ -256,6 +258,11 @@ int hantro_hevc_dec_prepare_run(struct hantro_ctx *ctx)
 	if (WARN_ON(!ctrls->decode_params))
 		return -EINVAL;
 
+	ctrls->scaling =
+		hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_HEVC_SCALING_MATRIX);
+	if (WARN_ON(!ctrls->scaling))
+		return -EINVAL;
+
 	ctrls->sps =
 		hantro_get_ctrl(ctx, V4L2_CID_MPEG_VIDEO_HEVC_SPS);
 	if (WARN_ON(!ctrls->sps))
@@ -284,6 +291,12 @@ void hantro_hevc_dec_exit(struct hantro_ctx *ctx)
 				  hevc_dec->tile_sizes.dma);
 	hevc_dec->tile_sizes.cpu = NULL;
 
+	if (hevc_dec->scaling_lists.cpu)
+		dma_free_coherent(vpu->dev, hevc_dec->scaling_lists.size,
+				  hevc_dec->scaling_lists.cpu,
+				  hevc_dec->scaling_lists.dma);
+	hevc_dec->scaling_lists.cpu = NULL;
+
 	if (hevc_dec->tile_filter.cpu)
 		dma_free_coherent(vpu->dev, hevc_dec->tile_filter.size,
 				  hevc_dec->tile_filter.cpu,
@@ -327,6 +340,14 @@ int hantro_hevc_dec_init(struct hantro_ctx *ctx)
 
 	hevc_dec->tile_sizes.size = size;
 
+	hevc_dec->scaling_lists.cpu = dma_alloc_coherent(vpu->dev, SCALING_LIST_SIZE,
+							 &hevc_dec->scaling_lists.dma,
+							 GFP_KERNEL);
+	if (!hevc_dec->scaling_lists.cpu)
+		return -ENOMEM;
+
+	hevc_dec->scaling_lists.size = SCALING_LIST_SIZE;
+
 	hantro_hevc_ref_init(ctx);
 
 	return 0;

drivers/staging/media/hantro/hantro_hw.h

@@ -104,6 +104,7 @@ struct hantro_h264_dec_hw_ctx {
 /**
  * struct hantro_hevc_dec_ctrls
  * @decode_params: Decode params
+ * @scaling:	Scaling matrix
  * @sps:	SPS info
  * @pps:	PPS info
  * @hevc_hdr_skip_length: the number of data (in bits) to skip in the
@@ -112,6 +113,7 @@ struct hantro_h264_dec_hw_ctx {
  */
 struct hantro_hevc_dec_ctrls {
 	const struct v4l2_ctrl_hevc_decode_params *decode_params;
+	const struct v4l2_ctrl_hevc_scaling_matrix *scaling;
 	const struct v4l2_ctrl_hevc_sps *sps;
 	const struct v4l2_ctrl_hevc_pps *pps;
 	u32 hevc_hdr_skip_length;
@@ -124,6 +126,7 @@ struct hantro_hevc_dec_ctrls {
  * @tile_sao:		Tile SAO buffer
  * @tile_bsd:		Tile BSD control buffer
  * @ref_bufs:		Internal reference buffers
+ * @scaling_lists:	Scaling lists buffer
  * @ref_bufs_poc:	Internal reference buffers picture order count
  * @ref_bufs_used:	Bitfield of used reference buffers
  * @ctrls:		V4L2 controls attached to a run
@@ -135,6 +138,7 @@ struct hantro_hevc_dec_hw_ctx {
 	struct hantro_aux_buf tile_sao;
 	struct hantro_aux_buf tile_bsd;
 	struct hantro_aux_buf ref_bufs[NUM_REF_PICTURES];
+	struct hantro_aux_buf scaling_lists;
 	int ref_bufs_poc[NUM_REF_PICTURES];
 	u32 ref_bufs_used;
 	struct hantro_hevc_dec_ctrls ctrls;