openwrt/target/linux/bcm27xx/patches-5.15/950-0018-drm-vc4-Increase-the-core-clock-based-on-HVS-load.patch

From 99c821dc4cd65ff067e2dfff4a47ceb5aa61ad0c Mon Sep 17 00:00:00 2001
From: Maxime Ripard <maxime@cerno.tech>
Date: Wed, 26 May 2021 16:13:02 +0200
Subject: [PATCH] drm/vc4: Increase the core clock based on HVS load

Depending on a given HVS output (HVS to PixelValves) and input (planes
attached to a channel) load, the HVS needs for the core clock to be
raised above its boot time default.

Failing to do so will result in a vblank timeout and a stalled display
pipeline.

Signed-off-by: Maxime Ripard <maxime@cerno.tech>
---
 drivers/gpu/drm/vc4/vc4_crtc.c |  15 +++++
 drivers/gpu/drm/vc4/vc4_drv.h  |   2 +
 drivers/gpu/drm/vc4/vc4_kms.c  | 112 ++++++++++++++++++++++++++++++---
 3 files changed, 119 insertions(+), 10 deletions(-)

--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -663,12 +663,27 @@ static int vc4_crtc_atomic_check(struct
 	struct vc4_crtc_state *vc4_state = to_vc4_crtc_state(crtc_state);
 	struct drm_connector *conn;
 	struct drm_connector_state *conn_state;
+	struct drm_encoder *encoder;
 	int ret, i;
 
 	ret = vc4_hvs_atomic_check(crtc, state);
 	if (ret)
 		return ret;
 
+	encoder = vc4_get_crtc_encoder(crtc, crtc_state);
+	if (encoder) {
+		const struct drm_display_mode *mode = &crtc_state->adjusted_mode;
+		struct vc4_encoder *vc4_encoder = to_vc4_encoder(encoder);
+
+		mode = &crtc_state->adjusted_mode;
+		if (vc4_encoder->type == VC4_ENCODER_TYPE_HDMI0) {
+			vc4_state->hvs_load = max(mode->clock * mode->hdisplay / mode->htotal + 1000,
+						  mode->clock * 9 / 10) * 1000;
+		} else {
+			vc4_state->hvs_load = mode->clock * 1000;
+		}
+	}
+
 	for_each_new_connector_in_state(state, conn, conn_state,
 					i) {
 		if (conn_state->crtc != crtc)
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -558,6 +558,8 @@ struct vc4_crtc_state {
 		unsigned int bottom;
 	} margins;
 
+	unsigned long hvs_load;
+
 	/* Transitional state below, only valid during atomic commits */
 	bool update_muxing;
 };
--- a/drivers/gpu/drm/vc4/vc4_kms.c
+++ b/drivers/gpu/drm/vc4/vc4_kms.c
@@ -39,9 +39,11 @@ static struct vc4_ctm_state *to_vc4_ctm_
 
 struct vc4_hvs_state {
 	struct drm_private_state base;
+	unsigned long core_clock_rate;
 
 	struct {
 		unsigned in_use: 1;
+		unsigned long fifo_load;
 		struct drm_crtc_commit *pending_commit;
 	} fifo_state[HVS_NUM_CHANNELS];
 };
@@ -339,11 +341,20 @@ static void vc4_atomic_commit_tail(struc
 	struct vc4_dev *vc4 = to_vc4_dev(dev);
 	struct vc4_hvs *hvs = vc4->hvs;
 	struct drm_crtc_state *new_crtc_state;
+	struct vc4_hvs_state *new_hvs_state;
 	struct drm_crtc *crtc;
 	struct vc4_hvs_state *old_hvs_state;
 	unsigned int channel;
 	int i;
 
+	old_hvs_state = vc4_hvs_get_old_global_state(state);
+	if (WARN_ON(!old_hvs_state))
+		return;
+
+	new_hvs_state = vc4_hvs_get_new_global_state(state);
+	if (WARN_ON(!new_hvs_state))
+		return;
+
 	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
 		struct vc4_crtc_state *vc4_crtc_state;
 
@@ -354,10 +365,6 @@ static void vc4_atomic_commit_tail(struc
 		vc4_hvs_mask_underrun(dev, vc4_crtc_state->assigned_channel);
 	}
 
-	old_hvs_state = vc4_hvs_get_old_global_state(state);
-	if (IS_ERR(old_hvs_state))
-		return;
-
 	for (channel = 0; channel < HVS_NUM_CHANNELS; channel++) {
 		struct drm_crtc_commit *commit;
 		int ret;
@@ -377,8 +384,13 @@ static void vc4_atomic_commit_tail(struc
 		old_hvs_state->fifo_state[channel].pending_commit = NULL;
 	}
 
-	if (vc4->hvs->hvs5)
-		clk_set_min_rate(hvs->core_clk, 500000000);
+	if (vc4->hvs->hvs5) {
+		unsigned long core_rate = max_t(unsigned long,
+						500000000,
+						new_hvs_state->core_clock_rate);
+
+		clk_set_min_rate(hvs->core_clk, core_rate);
+	}
 
 	drm_atomic_helper_commit_modeset_disables(dev, state);
 
@@ -401,8 +413,12 @@ static void vc4_atomic_commit_tail(struc
 
 	drm_atomic_helper_cleanup_planes(dev, state);
 
-	if (vc4->hvs->hvs5)
-		clk_set_min_rate(hvs->core_clk, 0);
+	if (vc4->hvs->hvs5) {
+		drm_dbg(dev, "Running the core clock at %lu Hz\n",
+			new_hvs_state->core_clock_rate);
+
+		clk_set_min_rate(hvs->core_clk, new_hvs_state->core_clock_rate);
+	}
 }
 
 static int vc4_atomic_commit_setup(struct drm_atomic_state *state)
@@ -659,11 +675,13 @@ vc4_hvs_channels_duplicate_state(struct
 
 	__drm_atomic_helper_private_obj_duplicate_state(obj, &state->base);
 
-
 	for (i = 0; i < HVS_NUM_CHANNELS; i++) {
 		state->fifo_state[i].in_use = old_state->fifo_state[i].in_use;
+		state->fifo_state[i].fifo_load = old_state->fifo_state[i].fifo_load;
 	}
 
+	state->core_clock_rate = old_state->core_clock_rate;
+
 	return &state->base;
 }
 
@@ -819,6 +837,76 @@ static int vc4_pv_muxing_atomic_check(st
 }
 
 static int
+vc4_core_clock_atomic_check(struct drm_atomic_state *state)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(state->dev);
+	struct drm_private_state *priv_state;
+	struct vc4_hvs_state *hvs_new_state;
+	struct vc4_load_tracker_state *load_state;
+	struct drm_crtc_state *old_crtc_state, *new_crtc_state;
+	struct drm_crtc *crtc;
+	unsigned int num_outputs;
+	unsigned long pixel_rate;
+	unsigned long cob_rate;
+	unsigned 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);
+
+	hvs_new_state = vc4_hvs_get_global_state(state);
+	if (!hvs_new_state)
+		return -EINVAL;
+
+	for_each_oldnew_crtc_in_state(state, crtc,
+				      old_crtc_state,
+				      new_crtc_state,
+				      i) {
+		if (old_crtc_state->active) {
+			struct vc4_crtc_state *old_vc4_state =
+				to_vc4_crtc_state(old_crtc_state);
+			unsigned int channel = old_vc4_state->assigned_channel;
+
+			hvs_new_state->fifo_state[channel].fifo_load = 0;
+		}
+
+		if (new_crtc_state->active) {
+			struct vc4_crtc_state *new_vc4_state =
+				to_vc4_crtc_state(new_crtc_state);
+			unsigned int channel = new_vc4_state->assigned_channel;
+
+			hvs_new_state->fifo_state[channel].fifo_load =
+				new_vc4_state->hvs_load;
+		}
+	}
+
+	cob_rate = 0;
+	num_outputs = 0;
+	for (i = 0; i < HVS_NUM_CHANNELS; i++) {
+		if (!hvs_new_state->fifo_state[i].in_use)
+			continue;
+
+		num_outputs++;
+		cob_rate += hvs_new_state->fifo_state[i].fifo_load;
+	}
+
+	pixel_rate = load_state->hvs_load;
+	if (num_outputs > 1) {
+		pixel_rate = (pixel_rate * 40) / 100;
+	} else {
+		pixel_rate = (pixel_rate * 60) / 100;
+	}
+
+	hvs_new_state->core_clock_rate = max(cob_rate, pixel_rate);
+
+	return 0;
+}
+
+
+static int
 vc4_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
 {
 	int ret;
@@ -835,7 +923,11 @@ vc4_atomic_check(struct drm_device *dev,
 	if (ret)
 		return ret;
 
-	return vc4_load_tracker_atomic_check(state);
+	ret = vc4_load_tracker_atomic_check(state);
+	if (ret)
+		return ret;
+
+	return vc4_core_clock_atomic_check(state);
 }
 
 static struct drm_mode_config_helper_funcs vc4_mode_config_helpers = {