[PATCH 1/2] drm/dsc: Update drm_dsc to reflect native 4.2.0 DSC spec

[Cornij, Nikola]

This looks good, too.

-----Original Message-----
From: mikita.lipski at amd.com <mikita.lipski at amd.com> 
Sent: November 13, 2019 2:07 PM
To: amd-gfx at lists.freedesktop.org
Cc: Wentland, Harry <Harry.Wentland at amd.com>; Deucher, Alexander <Alexander.Deucher at amd.com>; Cornij, Nikola <Nikola.Cornij at amd.com>; manasi.d.navare at intel.com; Lipski, Mikita <Mikita.Lipski at amd.com>; David Francis <David.Francis at amd.com>
Subject: [PATCH 1/2] drm/dsc: Update drm_dsc to reflect native 4.2.0 DSC spec

From: Mikita Lipski <mikita.lipski at amd.com>

[Why]
Some parts of the DSC spec relating to 4.2.0 were not reflected in drm_dsc_compute_rc_parameters, causing unexpected config failures

[How]
Add nsl_bpg_offset and rbs_min computation

Signed-off-by: David Francis <David.Francis at amd.com>
Signed-off-by: Mikita Lipski <mikita.lipski at amd.com>
---
 drivers/gpu/drm/drm_dsc.c | 72 ++++++++++++++++++++++++++++++++++++---
 1 file changed, 68 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/drm_dsc.c b/drivers/gpu/drm/drm_dsc.c index 77f4e5ae4197..79c71e3fc973 100644
--- a/drivers/gpu/drm/drm_dsc.c
+++ b/drivers/gpu/drm/drm_dsc.c
@@ -245,6 +245,38 @@ void drm_dsc_pps_payload_pack(struct drm_dsc_picture_parameter_set *pps_payload,  }  EXPORT_SYMBOL(drm_dsc_pps_payload_pack);
 
+static int compute_offset(struct drm_dsc_config *vdsc_cfg, int pixels_per_group,
+				int groups_per_line, int grpcnt)
+{
+	int offset = 0;
+	int grpcnt_id = DIV_ROUND_UP(vdsc_cfg->initial_xmit_delay, 
+pixels_per_group);
+
+	if (grpcnt <= grpcnt_id)
+		offset = DIV_ROUND_UP(grpcnt * pixels_per_group * vdsc_cfg->bits_per_pixel, 16);
+	else
+		offset = DIV_ROUND_UP(grpcnt_id * pixels_per_group * vdsc_cfg->bits_per_pixel, 16)
+			- (((grpcnt - grpcnt_id) * vdsc_cfg->slice_bpg_offset) >> 11);
+
+	if (grpcnt <= groups_per_line)
+		offset += grpcnt * vdsc_cfg->first_line_bpg_offset;
+	else
+		offset += groups_per_line * vdsc_cfg->first_line_bpg_offset
+			- (((grpcnt - groups_per_line) * vdsc_cfg->nfl_bpg_offset) >> 11);
+
+	if (vdsc_cfg->native_420) {
+		if (grpcnt <= groups_per_line)
+			offset -= (grpcnt * vdsc_cfg->nsl_bpg_offset) >> 11;
+		else if (grpcnt <= 2 * groups_per_line)
+			offset += (grpcnt - groups_per_line) * vdsc_cfg->second_line_bpg_offset
+				- ((groups_per_line * vdsc_cfg->nsl_bpg_offset) >> 11);
+		else
+			offset += (grpcnt - groups_per_line) * vdsc_cfg->second_line_bpg_offset
+				- (((grpcnt - groups_per_line) * vdsc_cfg->nsl_bpg_offset) >> 11);
+	}
+
+	return offset;
+}
+
 /**
  * drm_dsc_compute_rc_parameters() - Write rate control
  * parameters to the dsc configuration defined in @@ -264,6 +296,7 @@ int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg)
 	unsigned long hrd_delay = 0;
 	unsigned long final_scale = 0;
 	unsigned long rbs_min = 0;
+	unsigned long max_offset = 0;
 
 	if (vdsc_cfg->native_420 || vdsc_cfg->native_422) {
 		/* Number of groups used to code each line of a slice */ @@ -342,6 +375,17 @@ int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg)
 		return -ERANGE;
 	}
 
+	if (vdsc_cfg->slice_height > 2)
+		vdsc_cfg->nsl_bpg_offset = DIV_ROUND_UP((vdsc_cfg->second_line_bpg_offset << 11),
+							(vdsc_cfg->slice_height - 1));
+	else
+		vdsc_cfg->nsl_bpg_offset = 0;
+
+	if (vdsc_cfg->nsl_bpg_offset > 65535) {
+		DRM_DEBUG_KMS("NslBpgOffset is too large for this slice height\n");
+		return -ERANGE;
+	}
+
 	/* Number of groups used to code the entire slice */
 	groups_total = groups_per_line * vdsc_cfg->slice_height;
 
@@ -361,6 +405,7 @@ int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg)
 		vdsc_cfg->scale_increment_interval =
 				(vdsc_cfg->final_offset * (1 << 11)) /
 				((vdsc_cfg->nfl_bpg_offset +
+				vdsc_cfg->nsl_bpg_offset +
 				vdsc_cfg->slice_bpg_offset) *
 				(final_scale - 9));
 	} else {
@@ -381,10 +426,29 @@ int drm_dsc_compute_rc_parameters(struct drm_dsc_config *vdsc_cfg)
 	 * bits/pixel (bpp) rate that is used by the encoder,
 	 * in steps of 1/16 of a bit per pixel
 	 */
-	rbs_min = vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset +
-		DIV_ROUND_UP(vdsc_cfg->initial_xmit_delay *
-			     vdsc_cfg->bits_per_pixel, 16) +
-		groups_per_line * vdsc_cfg->first_line_bpg_offset;
+	if (vdsc_cfg->dsc_version_minor == 2 && (vdsc_cfg->native_420 || 
+vdsc_cfg->native_422)) {
+
+		max_offset = compute_offset(vdsc_cfg, DSC_RC_PIXELS_PER_GROUP, groups_per_line,
+					DIV_ROUND_UP(vdsc_cfg->initial_xmit_delay,
+						DSC_RC_PIXELS_PER_GROUP));
+
+		max_offset = max(max_offset,
+				compute_offset(vdsc_cfg, DSC_RC_PIXELS_PER_GROUP, groups_per_line,
+					DIV_ROUND_UP(vdsc_cfg->initial_xmit_delay,
+						groups_per_line)));
+
+		max_offset = max(max_offset,
+				compute_offset(vdsc_cfg, DSC_RC_PIXELS_PER_GROUP, groups_per_line,
+					DIV_ROUND_UP(vdsc_cfg->initial_xmit_delay,
+						groups_per_line * 2)));
+
+		rbs_min = vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset + max_offset;
+	} else {
+		rbs_min = vdsc_cfg->rc_model_size - vdsc_cfg->initial_offset +
+			DIV_ROUND_UP(vdsc_cfg->initial_xmit_delay *
+				     vdsc_cfg->bits_per_pixel, 16) +
+			groups_per_line * vdsc_cfg->first_line_bpg_offset;
+	}
 
 	hrd_delay = DIV_ROUND_UP((rbs_min * 16), vdsc_cfg->bits_per_pixel);
 	vdsc_cfg->rc_bits = (hrd_delay * vdsc_cfg->bits_per_pixel) / 16;
--
2.17.1