[PATCH v3 11/12] drm/msm/dpu: allow sharing of blending stages

[Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>]

It is possible to slightly bend the limitations of the HW blender. If
two rectangles are contiguous (like two rectangles of a single plane)
they can be blended using a single LM blending stage, allowing one to
blend more planes via a single LM.

Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@xxxxxxxxxx>
---
 drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c  |  9 ++++--
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 37 ++++++++++++++++++-----
 2 files changed, 37 insertions(+), 9 deletions(-)

diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
index df4c2e503fa5..4b5b2b7ed494 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c
@@ -456,6 +456,7 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
 
 	uint32_t lm_idx;
 	bool bg_alpha_enable = false;
+	unsigned int stage_indices[DPU_STAGE_MAX] = {};
 	DECLARE_BITMAP(fetch_active, SSPP_MAX);
 
 	memset(fetch_active, 0, sizeof(fetch_active));
@@ -480,7 +481,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
 					   mixer, cstate->num_mixers,
 					   pstate->stage,
 					   format, fb ? fb->modifier : 0,
-					   &pstate->pipe, 0, stage_cfg);
+					   &pstate->pipe,
+					   stage_indices[pstate->stage]++,
+					   stage_cfg);
 
 		if (pstate->r_pipe.sspp) {
 			set_bit(pstate->r_pipe.sspp->idx, fetch_active);
@@ -488,7 +491,9 @@ static void _dpu_crtc_blend_setup_mixer(struct drm_crtc *crtc,
 						   mixer, cstate->num_mixers,
 						   pstate->stage,
 						   format, fb ? fb->modifier : 0,
-						   &pstate->r_pipe, 1, stage_cfg);
+						   &pstate->r_pipe,
+						   stage_indices[pstate->stage]++,
+						   stage_cfg);
 		}
 
 		/* blend config update */
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 61afd1cf033d..e7a157feab22 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -809,13 +809,6 @@ static int dpu_plane_atomic_check_nopipe(struct drm_plane *plane,
 	if (!new_plane_state->visible)
 		return 0;
 
-	pstate->stage = DPU_STAGE_0 + pstate->base.normalized_zpos;
-	if (pstate->stage >= pdpu->catalog->caps->max_mixer_blendstages) {
-		DPU_ERROR("> %d plane stages assigned\n",
-			  pdpu->catalog->caps->max_mixer_blendstages - DPU_STAGE_0);
-		return -EINVAL;
-	}
-
 	fb_rect.x2 = new_plane_state->fb->width;
 	fb_rect.y2 = new_plane_state->fb->height;
 
@@ -952,6 +945,18 @@ static int dpu_plane_try_multirect(struct dpu_plane_state *pstate,
 		prev_pipe->multirect_index = DPU_SSPP_RECT_0;
 		prev_pipe->multirect_mode = DPU_SSPP_MULTIRECT_PARALLEL;
 
+		if (pipe_cfg->dst_rect.y1 == prev_pipe_cfg->dst_rect.y1 &&
+		    pipe_cfg->dst_rect.y2 == prev_pipe_cfg->dst_rect.y2 &&
+		    pipe_cfg->dst_rect.x1 == prev_pipe_cfg->dst_rect.x2) {
+			pstate->stage = prev_pstate->stage;
+		} else if (pipe_cfg->dst_rect.y1 == prev_pipe_cfg->dst_rect.y1 &&
+			   pipe_cfg->dst_rect.y2 == prev_pipe_cfg->dst_rect.y2 &&
+			   pipe_cfg->dst_rect.x2 == prev_pipe_cfg->dst_rect.x1) {
+			pstate->stage = prev_pstate->stage;
+			pipe->multirect_index = DPU_SSPP_RECT_0;
+			prev_pipe->multirect_index = DPU_SSPP_RECT_1;
+		}
+
 		return true;
 	}
 
@@ -1054,6 +1059,13 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
 	if (!new_plane_state->visible)
 		return 0;
 
+	pstate->stage = DPU_STAGE_0 + pstate->base.normalized_zpos;
+	if (pstate->stage >= pdpu->catalog->caps->max_mixer_blendstages) {
+		DPU_ERROR("> %d plane stages assigned\n",
+			  pdpu->catalog->caps->max_mixer_blendstages - DPU_STAGE_0);
+		return -EINVAL;
+	}
+
 	pipe->multirect_index = DPU_SSPP_RECT_SOLO;
 	pipe->multirect_mode = DPU_SSPP_MULTIRECT_NONE;
 	r_pipe->multirect_index = DPU_SSPP_RECT_SOLO;
@@ -1189,6 +1201,11 @@ static int dpu_plane_virtual_assign_resources(struct drm_crtc *crtc,
 
 	max_linewidth = dpu_kms->catalog->caps->max_linewidth;
 
+	if (prev_pstate)
+		pstate->stage = prev_pstate->stage + 1;
+	else
+		pstate->stage = DPU_STAGE_0 + pstate->base.normalized_zpos;
+
 	if (drm_rect_width(&r_pipe_cfg->src_rect) == 0) {
 		if (!prev_pstate ||
 		    !dpu_plane_try_multirect(pstate, prev_pstate, fmt, max_linewidth)) {
@@ -1235,6 +1252,12 @@ static int dpu_plane_virtual_assign_resources(struct drm_crtc *crtc,
 		}
 	}
 
+	if (pstate->stage >= dpu_kms->catalog->caps->max_mixer_blendstages) {
+		DPU_ERROR("> %d plane stages assigned\n",
+			  dpu_kms->catalog->caps->max_mixer_blendstages - DPU_STAGE_0);
+		return -EINVAL;
+	}
+
 	return dpu_plane_atomic_check_pipes(plane, state);
 }
 
-- 
2.39.2