1 files changed, 60 insertions, 6 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index d098337c10e9..84fd0a31b701 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -1,9 +1,6 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Copyright (C) 2015 Broadcom
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
  */
 
 /**
@@ -488,6 +485,61 @@ static void vc4_write_scaling_parameters(struct drm_plane_state *state,
 	}
 }
 
+static void vc4_plane_calc_load(struct drm_plane_state *state)
+{
+	unsigned int hvs_load_shift, vrefresh, i;
+	struct drm_framebuffer *fb = state->fb;
+	struct vc4_plane_state *vc4_state;
+	struct drm_crtc_state *crtc_state;
+	unsigned int vscale_factor;
+
+	vc4_state = to_vc4_plane_state(state);
+	crtc_state = drm_atomic_get_existing_crtc_state(state->state,
+							state->crtc);
+	vrefresh = drm_mode_vrefresh(&crtc_state->adjusted_mode);
+
+	/* The HVS is able to process 2 pixels/cycle when scaling the source,
+	 * 4 pixels/cycle otherwise.
+	 * Alpha blending step seems to be pipelined and it's always operating
+	 * at 4 pixels/cycle, so the limiting aspect here seems to be the
+	 * scaler block.
+	 * HVS load is expressed in clk-cycles/sec (AKA Hz).
+	 */
+	if (vc4_state->x_scaling[0] != VC4_SCALING_NONE ||
+	    vc4_state->x_scaling[1] != VC4_SCALING_NONE ||
+	    vc4_state->y_scaling[0] != VC4_SCALING_NONE ||
+	    vc4_state->y_scaling[1] != VC4_SCALING_NONE)
+		hvs_load_shift = 1;
+	else
+		hvs_load_shift = 2;
+
+	vc4_state->membus_load = 0;
+	vc4_state->hvs_load = 0;
+	for (i = 0; i < fb->format->num_planes; i++) {
+		/* Even if the bandwidth/plane required for a single frame is
+		 *
+		 * vc4_state->src_w[i] * vc4_state->src_h[i] * cpp * vrefresh
+		 *
+		 * when downscaling, we have to read more pixels per line in
+		 * the time frame reserved for a single line, so the bandwidth
+		 * demand can be punctually higher. To account for that, we
+		 * calculate the down-scaling factor and multiply the plane
+		 * load by this number. We're likely over-estimating the read
+		 * demand, but that's better than under-estimating it.
+		 */
+		vscale_factor = DIV_ROUND_UP(vc4_state->src_h[i],
+					     vc4_state->crtc_h);
+		vc4_state->membus_load += vc4_state->src_w[i] *
+					  vc4_state->src_h[i] * vscale_factor *
+					  fb->format->cpp[i];
+		vc4_state->hvs_load += vc4_state->crtc_h * vc4_state->crtc_w;
+	}
+
+	vc4_state->hvs_load *= vrefresh;
+	vc4_state->hvs_load >>= hvs_load_shift;
+	vc4_state->membus_load *= vrefresh;
+}
+
 static int vc4_plane_allocate_lbm(struct drm_plane_state *state)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(state->plane->dev);
@@ -875,6 +927,8 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	 */
 	vc4_state->dlist_initialized = 1;
 
+	vc4_plane_calc_load(state);
+
 	return 0;
 }
 
@@ -968,7 +1022,7 @@ static void vc4_plane_atomic_async_update(struct drm_plane *plane,
 {
 	struct vc4_plane_state *vc4_state, *new_vc4_state;
 
-	drm_atomic_set_fb_for_plane(plane->state, state->fb);
+	swap(plane->state->fb, state->fb);
 	plane->state->crtc_x = state->crtc_x;
 	plane->state->crtc_y = state->crtc_y;
 	plane->state->crtc_w = state->crtc_w;
@@ -1082,7 +1136,7 @@ static int vc4_prepare_fb(struct drm_plane *plane,
 
 	bo = to_vc4_bo(&drm_fb_cma_get_gem_obj(state->fb, 0)->base);
 
-	fence = reservation_object_get_excl_rcu(bo->resv);
+	fence = reservation_object_get_excl_rcu(bo->base.base.resv);
 	drm_atomic_set_fence_for_plane(state, fence);
 
 	if (plane->state->fb == state->fb)