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, 102 insertions, 1 deletions

diff --git a/drivers/gpu/drm/vc4/vc4_kms.c b/drivers/gpu/drm/vc4/vc4_kms.c
index b971258dcfd4..6e20604573de 100644
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -34,6 +34,18 @@ static struct vc4_ctm_state *to_vc4_ctm_state(struct drm_private_state *priv)
 	return container_of(priv, struct vc4_ctm_state, base);
 }
 
+struct vc4_load_tracker_state {
+	struct drm_private_state base;
+	u64 hvs_load;
+	u64 membus_load;
+};
+
+static struct vc4_load_tracker_state *
+to_vc4_load_tracker_state(struct drm_private_state *priv)
+{
+	return container_of(priv, struct vc4_load_tracker_state, base);
+}
+
 static struct vc4_ctm_state *vc4_get_ctm_state(struct drm_atomic_state *state,
 					       struct drm_private_obj *manager)
 {
@@ -395,6 +407,81 @@ vc4_ctm_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
 	return 0;
 }
 
+static int vc4_load_tracker_atomic_check(struct drm_atomic_state *state)
+{
+	struct drm_plane_state *old_plane_state, *new_plane_state;
+	struct vc4_dev *vc4 = to_vc4_dev(state->dev);
+	struct vc4_load_tracker_state *load_state;
+	struct drm_private_state *priv_state;
+	struct drm_plane *plane;
+	int i;
+
+	priv_state = drm_atomic_get_private_obj_state(state,
+						      &vc4->load_tracker);
+	if (IS_ERR(priv_state))
+		return PTR_ERR(priv_state);
+
+	load_state = to_vc4_load_tracker_state(priv_state);
+	for_each_oldnew_plane_in_state(state, plane, old_plane_state,
+				       new_plane_state, i) {
+		struct vc4_plane_state *vc4_plane_state;
+
+		if (old_plane_state->fb && old_plane_state->crtc) {
+			vc4_plane_state = to_vc4_plane_state(old_plane_state);
+			load_state->membus_load -= vc4_plane_state->membus_load;
+			load_state->hvs_load -= vc4_plane_state->hvs_load;
+		}
+
+		if (new_plane_state->fb && new_plane_state->crtc) {
+			vc4_plane_state = to_vc4_plane_state(new_plane_state);
+			load_state->membus_load += vc4_plane_state->membus_load;
+			load_state->hvs_load += vc4_plane_state->hvs_load;
+		}
+	}
+
+	/* The absolute limit is 2Gbyte/sec, but let's take a margin to let
+	 * the system work when other blocks are accessing the memory.
+	 */
+	if (load_state->membus_load > SZ_1G + SZ_512M)
+		return -ENOSPC;
+
+	/* HVS clock is supposed to run @ 250Mhz, let's take a margin and
+	 * consider the maximum number of cycles is 240M.
+	 */
+	if (load_state->hvs_load > 240000000ULL)
+		return -ENOSPC;
+
+	return 0;
+}
+
+static struct drm_private_state *
+vc4_load_tracker_duplicate_state(struct drm_private_obj *obj)
+{
+	struct vc4_load_tracker_state *state;
+
+	state = kmemdup(obj->state, sizeof(*state), GFP_KERNEL);
+	if (!state)
+		return NULL;
+
+	__drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
+
+	return &state->base;
+}
+
+static void vc4_load_tracker_destroy_state(struct drm_private_obj *obj,
+					   struct drm_private_state *state)
+{
+	struct vc4_load_tracker_state *load_state;
+
+	load_state = to_vc4_load_tracker_state(state);
+	kfree(load_state);
+}
+
+static const struct drm_private_state_funcs vc4_load_tracker_state_funcs = {
+	.atomic_duplicate_state = vc4_load_tracker_duplicate_state,
+	.atomic_destroy_state = vc4_load_tracker_destroy_state,
+};
+
 static int
 vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
 {
@@ -404,7 +491,11 @@ vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
 	if (ret < 0)
 		return ret;
 
-	return drm_atomic_helper_check(dev, state);
+	ret = drm_atomic_helper_check(dev, state);
+	if (ret)
+		return ret;
+
+	return vc4_load_tracker_atomic_check(state);
 }
 
 static const struct drm_mode_config_funcs vc4_mode_funcs = {
@@ -417,6 +508,7 @@ int vc4_kms_load(struct drm_device *dev)
 {
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_ctm_state *ctm_state;
+	struct vc4_load_tracker_state *load_state;
 	int ret;
 
 	sema_init(&vc4->async_modeset, 1);
@@ -446,6 +538,15 @@ int vc4_kms_load(struct drm_device *dev)
 	drm_atomic_private_obj_init(dev, &vc4->ctm_manager, &ctm_state->base,
 				    &vc4_ctm_state_funcs);
 
+	load_state = kzalloc(sizeof(*load_state), GFP_KERNEL);
+	if (!load_state) {
+		drm_atomic_private_obj_fini(&vc4->ctm_manager);
+		return -ENOMEM;
+	}
+
+	drm_atomic_private_obj_init(dev, &vc4->load_tracker, &load_state->base,
+				    &vc4_load_tracker_state_funcs);
+
 	drm_mode_config_reset(dev);
 
 	drm_kms_helper_poll_init(dev);