drm/vc4: Add a load tracker to prevent HVS underflow errors

The HVS block is supposed to fill the pixelvalve FIFOs fast enough to
meet the requested framerate. The problem is, the HVS and memory bus
bandwidths are limited, and if we don't take these limitations into
account we might end up with HVS underflow errors.

This patch is trying to model the per-plane HVS and memory bus bandwidth
consumption and take a decision at atomic_check() time whether the
estimated load will fit in the HVS and membus budget.

Note that we take an extra margin on the memory bus consumption to let
the system run smoothly when other blocks are doing heavy use of the
memory bus. Same goes for the HVS limit, except the margin is smaller in
this case, since the HVS is not used by external components.

Signed-off-by: Boris Brezillon <boris.brezillon@bootlin.com>
Signed-off-by: Paul Kocialkowski <paul.kocialkowski@bootlin.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Maxime Ripard <maxime.ripard@bootlin.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20190220155124.25022-3-paul.kocialkowski@bootlin.com

1 files changed, 57 insertions, 0 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_plane.c b/drivers/gpu/drm/vc4/vc4_plane.c
index 1babfeca0c92..4d918d3e4858 100644
--- a/drivers/gpu/drm/vc4/vc4_plane.c
+++ b/drivers/gpu/drm/vc4/vc4_plane.c
@@ -488,6 +488,61 @@ 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 +930,8 @@ static int vc4_plane_mode_set(struct drm_plane *plane,
 	 */
 	vc4_state->dlist_initialized = 1;
 
+	vc4_plane_calc_load(state);
+
 	return 0;
 }