drm/amd/display: Handle HDR use cases.

Implementation of de-gamma, blnd-gamma, shaper and
3d lut's.
Removed memory allocations in transfer functions.
Refactor color module.

Signed-off-by: Vitaly Prosyak <vitaly.prosyak@amd.com>
Reviewed-by: Krunoslav Kovac <Krunoslav.Kovac@amd.com>
Reviewed-by: Tony Cheng <Tony.Cheng@amd.com>
Acked-by: Harry Wentland <harry.wentland@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

1 files changed, 153 insertions, 0 deletions

diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
index b3db6397d353..881a1bff94d2 100644
--- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
+++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_cm_common.c
@@ -416,3 +416,156 @@ bool cm_helper_translate_curve_to_hw_format(
 
 	return true;
 }
+
+#define NUM_DEGAMMA_REGIONS    12
+
+
+bool cm_helper_translate_curve_to_degamma_hw_format(
+				const struct dc_transfer_func *output_tf,
+				struct pwl_params *lut_params)
+{
+	struct curve_points *arr_points;
+	struct pwl_result_data *rgb_resulted;
+	struct pwl_result_data *rgb;
+	struct pwl_result_data *rgb_plus_1;
+	struct fixed31_32 y_r;
+	struct fixed31_32 y_g;
+	struct fixed31_32 y_b;
+	struct fixed31_32 y1_min;
+	struct fixed31_32 y3_max;
+
+	int32_t region_start, region_end;
+	int32_t i;
+	uint32_t j, k, seg_distr[MAX_REGIONS_NUMBER], increment, start_index, hw_points;
+
+	if (output_tf == NULL || lut_params == NULL || output_tf->type == TF_TYPE_BYPASS)
+		return false;
+
+	PERF_TRACE();
+
+	arr_points = lut_params->arr_points;
+	rgb_resulted = lut_params->rgb_resulted;
+	hw_points = 0;
+
+	memset(lut_params, 0, sizeof(struct pwl_params));
+	memset(seg_distr, 0, sizeof(seg_distr));
+
+	region_start = -NUM_DEGAMMA_REGIONS;
+	region_end   = 0;
+
+
+	for (i = region_end - region_start; i < MAX_REGIONS_NUMBER ; i++)
+		seg_distr[i] = -1;
+	/* 12 segments
+	 * segments are from 2^-12 to 0
+	 */
+	for (i = 0; i < NUM_DEGAMMA_REGIONS ; i++)
+		seg_distr[i] = 4;
+
+	for (k = 0; k < MAX_REGIONS_NUMBER; k++) {
+		if (seg_distr[k] != -1)
+			hw_points += (1 << seg_distr[k]);
+	}
+
+	j = 0;
+	for (k = 0; k < (region_end - region_start); k++) {
+		increment = NUMBER_SW_SEGMENTS / (1 << seg_distr[k]);
+		start_index = (region_start + k + MAX_LOW_POINT) *
+				NUMBER_SW_SEGMENTS;
+		for (i = start_index; i < start_index + NUMBER_SW_SEGMENTS;
+				i += increment) {
+			if (j == hw_points - 1)
+				break;
+			rgb_resulted[j].red = output_tf->tf_pts.red[i];
+			rgb_resulted[j].green = output_tf->tf_pts.green[i];
+			rgb_resulted[j].blue = output_tf->tf_pts.blue[i];
+			j++;
+		}
+	}
+
+	/* last point */
+	start_index = (region_end + MAX_LOW_POINT) * NUMBER_SW_SEGMENTS;
+	rgb_resulted[hw_points - 1].red = output_tf->tf_pts.red[start_index];
+	rgb_resulted[hw_points - 1].green = output_tf->tf_pts.green[start_index];
+	rgb_resulted[hw_points - 1].blue = output_tf->tf_pts.blue[start_index];
+
+	arr_points[0].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
+					     dal_fixed31_32_from_int(region_start));
+	arr_points[1].x = dal_fixed31_32_pow(dal_fixed31_32_from_int(2),
+					     dal_fixed31_32_from_int(region_end));
+
+	y_r = rgb_resulted[0].red;
+	y_g = rgb_resulted[0].green;
+	y_b = rgb_resulted[0].blue;
+
+	y1_min = dal_fixed31_32_min(y_r, dal_fixed31_32_min(y_g, y_b));
+
+	arr_points[0].y = y1_min;
+	arr_points[0].slope = dal_fixed31_32_div(arr_points[0].y, arr_points[0].x);
+	y_r = rgb_resulted[hw_points - 1].red;
+	y_g = rgb_resulted[hw_points - 1].green;
+	y_b = rgb_resulted[hw_points - 1].blue;
+
+	/* see comment above, m_arrPoints[1].y should be the Y value for the
+	 * region end (m_numOfHwPoints), not last HW point(m_numOfHwPoints - 1)
+	 */
+	y3_max = dal_fixed31_32_max(y_r, dal_fixed31_32_max(y_g, y_b));
+
+	arr_points[1].y = y3_max;
+
+	arr_points[1].slope = dal_fixed31_32_zero;
+
+	if (output_tf->tf == TRANSFER_FUNCTION_PQ) {
+		/* for PQ, we want to have a straight line from last HW X point,
+		 * and the slope to be such that we hit 1.0 at 10000 nits.
+		 */
+		const struct fixed31_32 end_value =
+				dal_fixed31_32_from_int(125);
+
+		arr_points[1].slope = dal_fixed31_32_div(
+			dal_fixed31_32_sub(dal_fixed31_32_one, arr_points[1].y),
+			dal_fixed31_32_sub(end_value, arr_points[1].x));
+	}
+
+	lut_params->hw_points_num = hw_points;
+
+	i = 1;
+	for (k = 0; k < MAX_REGIONS_NUMBER && i < MAX_REGIONS_NUMBER; k++) {
+		if (seg_distr[k] != -1) {
+			lut_params->arr_curve_points[k].segments_num =
+					seg_distr[k];
+			lut_params->arr_curve_points[i].offset =
+					lut_params->arr_curve_points[k].offset + (1 << seg_distr[k]);
+		}
+		i++;
+	}
+
+	if (seg_distr[k] != -1)
+		lut_params->arr_curve_points[k].segments_num = seg_distr[k];
+
+	rgb = rgb_resulted;
+	rgb_plus_1 = rgb_resulted + 1;
+
+	i = 1;
+	while (i != hw_points + 1) {
+		if (dal_fixed31_32_lt(rgb_plus_1->red, rgb->red))
+			rgb_plus_1->red = rgb->red;
+		if (dal_fixed31_32_lt(rgb_plus_1->green, rgb->green))
+			rgb_plus_1->green = rgb->green;
+		if (dal_fixed31_32_lt(rgb_plus_1->blue, rgb->blue))
+			rgb_plus_1->blue = rgb->blue;
+
+		rgb->delta_red   = dal_fixed31_32_sub(rgb_plus_1->red,   rgb->red);
+		rgb->delta_green = dal_fixed31_32_sub(rgb_plus_1->green, rgb->green);
+		rgb->delta_blue  = dal_fixed31_32_sub(rgb_plus_1->blue,  rgb->blue);
+
+		++rgb_plus_1;
+		++rgb;
+		++i;
+	}
+	cm_helper_convert_to_custom_float(rgb_resulted,
+						lut_params->arr_points,
+						hw_points, false);
+
+	return true;
+}