diff mbox series

[v2,3/3] drm: bridge: ti-sn65dsi83: Add error recovery mechanism

Message ID 20241217143216.658461-4-herve.codina@bootlin.com (mailing list archive)
State New
Headers show
Series Add support for errors recovery in the TI SN65DSI83 bridge driver | expand

Commit Message

Herve Codina Dec. 17, 2024, 2:32 p.m. UTC
In some cases observed during ESD tests, the TI SN65DSI83 cannot recover
from errors by itself. A full restart of the bridge is needed in those
cases to have the bridge output LVDS signals again.

Also, during tests, cases were observed where reading the status of the
bridge was not even possible. Indeed, in those cases, the bridge stops
to acknowledge I2C transactions. Only a full reset of the bridge (power
off/on) brings back the bridge to a functional state.

The TI SN65DSI83 has some error detection capabilities. Introduce an
error recovery mechanism based on this detection.

The errors detected are signaled through an interrupt. On system where
this interrupt is not available, the driver uses a polling monitoring
fallback to check for errors. When an error is present or when reading
the bridge status leads to an I2C failure, the recovery process is
launched.

Restarting the bridge needs to redo the initialization sequence. This
initialization sequence has to be done with the DSI data lanes driven in
LP11 state. In order to do that, the recovery process resets the whole
output path (i.e the path from the encoder to the connector) where the
bridge is located.

Signed-off-by: Herve Codina <herve.codina@bootlin.com>
---
 drivers/gpu/drm/bridge/ti-sn65dsi83.c | 142 ++++++++++++++++++++++++++
 1 file changed, 142 insertions(+)

Comments

Maxime Ripard Dec. 17, 2024, 5:30 p.m. UTC | #1
On Tue, Dec 17, 2024 at 03:32:15PM +0100, Herve Codina wrote:
> In some cases observed during ESD tests, the TI SN65DSI83 cannot recover
> from errors by itself. A full restart of the bridge is needed in those
> cases to have the bridge output LVDS signals again.
> 
> Also, during tests, cases were observed where reading the status of the
> bridge was not even possible. Indeed, in those cases, the bridge stops
> to acknowledge I2C transactions. Only a full reset of the bridge (power
> off/on) brings back the bridge to a functional state.
> 
> The TI SN65DSI83 has some error detection capabilities. Introduce an
> error recovery mechanism based on this detection.
> 
> The errors detected are signaled through an interrupt. On system where
> this interrupt is not available, the driver uses a polling monitoring
> fallback to check for errors. When an error is present or when reading
> the bridge status leads to an I2C failure, the recovery process is
> launched.
> 
> Restarting the bridge needs to redo the initialization sequence. This
> initialization sequence has to be done with the DSI data lanes driven in
> LP11 state. In order to do that, the recovery process resets the whole
> output path (i.e the path from the encoder to the connector) where the
> bridge is located.
> 
> Signed-off-by: Herve Codina <herve.codina@bootlin.com>
> ---
>  drivers/gpu/drm/bridge/ti-sn65dsi83.c | 142 ++++++++++++++++++++++++++
>  1 file changed, 142 insertions(+)
> 
> diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
> index e6264514bb3f..f3d66d17f28c 100644
> --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c
> +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
> @@ -35,9 +35,12 @@
>  #include <linux/of_graph.h>
>  #include <linux/regmap.h>
>  #include <linux/regulator/consumer.h>
> +#include <linux/timer.h>
> +#include <linux/workqueue.h>
>  
>  #include <drm/drm_atomic_helper.h>
>  #include <drm/drm_bridge.h>
> +#include <drm/drm_drv.h> /* DRM_MODESET_LOCK_ALL_BEGIN() need drm_drv_uses_atomic_modeset() */
>  #include <drm/drm_mipi_dsi.h>
>  #include <drm/drm_of.h>
>  #include <drm/drm_panel.h>
> @@ -147,6 +150,9 @@ struct sn65dsi83 {
>  	struct regulator		*vcc;
>  	bool				lvds_dual_link;
>  	bool				lvds_dual_link_even_odd_swap;
> +	bool				use_irq;
> +	struct delayed_work		monitor_work;
> +	struct work_struct		reset_work;
>  };
>  
>  static const struct regmap_range sn65dsi83_readable_ranges[] = {
> @@ -328,6 +334,106 @@ static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx)
>  	return dsi_div - 1;
>  }
>  
> +static int sn65dsi83_reset_drm_output(struct sn65dsi83 *sn65dsi83)
> +{
> +	struct drm_atomic_state *state = ERR_PTR(-EINVAL);
> +	struct drm_device *dev = sn65dsi83->bridge.dev;
> +	struct drm_modeset_acquire_ctx ctx;
> +	struct drm_connector *connector;
> +	int err;
> +
> +	/*
> +	 * Reset components available from the encoder to the connector.
> +	 * To do that, we disable then re-enable the connector linked to the
> +	 * encoder.
> +	 *
> +	 * This way, drm core will reconfigure each components. In our case,
> +	 * this will force the previous component to go back in LP11 mode and
> +	 * so allow the reconfiguration of SN64DSI83 bridge.
> +	 *
> +	 * Keep the lock during the whole operation to be atomic.
> +	 */
> +
> +	DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, 0, err);
> +
> +	state = drm_atomic_helper_duplicate_state(dev, &ctx);
> +	if (IS_ERR(state)) {
> +		err = PTR_ERR(state);
> +		goto unlock;
> +	}
> +
> +	connector = drm_atomic_get_old_connector_for_encoder(state,
> +							     sn65dsi83->bridge.encoder);
> +	if (!connector) {
> +		err = -EINVAL;
> +		goto unlock;
> +	}
> +
> +	err = drm_atomic_helper_disable_connector(connector, &ctx);
> +	if (err < 0)
> +		goto unlock;
> +
> +	/* Restore original state to re-enable the connector */
> +	err = drm_atomic_helper_commit_duplicated_state(state, &ctx);
> +
> +unlock:
> +	DRM_MODESET_LOCK_ALL_END(dev, ctx, err);
> +	if (!IS_ERR(state))
> +		drm_atomic_state_put(state);
> +	return err;
> +}

In the previous version, we advised to create a generic helper similar
to vc4 and i915 reset_pipe() and and intel_modeset_commit_pipes().

It looks like you chose a different path. Can you expand why?

Maxime
Herve Codina Dec. 18, 2024, 8:24 a.m. UTC | #2
Hi Maxime,

On Tue, 17 Dec 2024 18:30:52 +0100
Maxime Ripard <mripard@kernel.org> wrote:

> On Tue, Dec 17, 2024 at 03:32:15PM +0100, Herve Codina wrote:
> > In some cases observed during ESD tests, the TI SN65DSI83 cannot recover
> > from errors by itself. A full restart of the bridge is needed in those
> > cases to have the bridge output LVDS signals again.
> > 
> > Also, during tests, cases were observed where reading the status of the
> > bridge was not even possible. Indeed, in those cases, the bridge stops
> > to acknowledge I2C transactions. Only a full reset of the bridge (power
> > off/on) brings back the bridge to a functional state.
> > 
> > The TI SN65DSI83 has some error detection capabilities. Introduce an
> > error recovery mechanism based on this detection.
> > 
> > The errors detected are signaled through an interrupt. On system where
> > this interrupt is not available, the driver uses a polling monitoring
> > fallback to check for errors. When an error is present or when reading
> > the bridge status leads to an I2C failure, the recovery process is
> > launched.
> > 
> > Restarting the bridge needs to redo the initialization sequence. This
> > initialization sequence has to be done with the DSI data lanes driven in
> > LP11 state. In order to do that, the recovery process resets the whole
> > output path (i.e the path from the encoder to the connector) where the
> > bridge is located.
> > 
> > Signed-off-by: Herve Codina <herve.codina@bootlin.com>
> > ---
> >  drivers/gpu/drm/bridge/ti-sn65dsi83.c | 142 ++++++++++++++++++++++++++
> >  1 file changed, 142 insertions(+)
> > 
> > diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
> > index e6264514bb3f..f3d66d17f28c 100644
> > --- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c
> > +++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
> > @@ -35,9 +35,12 @@
> >  #include <linux/of_graph.h>
> >  #include <linux/regmap.h>
> >  #include <linux/regulator/consumer.h>
> > +#include <linux/timer.h>
> > +#include <linux/workqueue.h>
> >  
> >  #include <drm/drm_atomic_helper.h>
> >  #include <drm/drm_bridge.h>
> > +#include <drm/drm_drv.h> /* DRM_MODESET_LOCK_ALL_BEGIN() need drm_drv_uses_atomic_modeset() */
> >  #include <drm/drm_mipi_dsi.h>
> >  #include <drm/drm_of.h>
> >  #include <drm/drm_panel.h>
> > @@ -147,6 +150,9 @@ struct sn65dsi83 {
> >  	struct regulator		*vcc;
> >  	bool				lvds_dual_link;
> >  	bool				lvds_dual_link_even_odd_swap;
> > +	bool				use_irq;
> > +	struct delayed_work		monitor_work;
> > +	struct work_struct		reset_work;
> >  };
> >  
> >  static const struct regmap_range sn65dsi83_readable_ranges[] = {
> > @@ -328,6 +334,106 @@ static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx)
> >  	return dsi_div - 1;
> >  }
> >  
> > +static int sn65dsi83_reset_drm_output(struct sn65dsi83 *sn65dsi83)
> > +{
> > +	struct drm_atomic_state *state = ERR_PTR(-EINVAL);
> > +	struct drm_device *dev = sn65dsi83->bridge.dev;
> > +	struct drm_modeset_acquire_ctx ctx;
> > +	struct drm_connector *connector;
> > +	int err;
> > +
> > +	/*
> > +	 * Reset components available from the encoder to the connector.
> > +	 * To do that, we disable then re-enable the connector linked to the
> > +	 * encoder.
> > +	 *
> > +	 * This way, drm core will reconfigure each components. In our case,
> > +	 * this will force the previous component to go back in LP11 mode and
> > +	 * so allow the reconfiguration of SN64DSI83 bridge.
> > +	 *
> > +	 * Keep the lock during the whole operation to be atomic.
> > +	 */
> > +
> > +	DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, 0, err);
> > +
> > +	state = drm_atomic_helper_duplicate_state(dev, &ctx);
> > +	if (IS_ERR(state)) {
> > +		err = PTR_ERR(state);
> > +		goto unlock;
> > +	}
> > +
> > +	connector = drm_atomic_get_old_connector_for_encoder(state,
> > +							     sn65dsi83->bridge.encoder);
> > +	if (!connector) {
> > +		err = -EINVAL;
> > +		goto unlock;
> > +	}
> > +
> > +	err = drm_atomic_helper_disable_connector(connector, &ctx);
> > +	if (err < 0)
> > +		goto unlock;
> > +
> > +	/* Restore original state to re-enable the connector */
> > +	err = drm_atomic_helper_commit_duplicated_state(state, &ctx);
> > +
> > +unlock:
> > +	DRM_MODESET_LOCK_ALL_END(dev, ctx, err);
> > +	if (!IS_ERR(state))
> > +		drm_atomic_state_put(state);
> > +	return err;
> > +}  
> 
> In the previous version, we advised to create a generic helper similar
> to vc4 and i915 reset_pipe() and and intel_modeset_commit_pipes().
> 
> It looks like you chose a different path. Can you expand why?
> 

I didn't choose a different path.
I created the drm_atomic_helper_disable_connector(). Maybe it is not enough.

I can move (copy/paste) sn65dsi83_reset_drm_output() to a new helper:
  int drm_atomic_helper_disable_output(struct drm_encoder *encoder)

Is it what you expect?

Also, are operations done in current sn65dsi83_reset_drm_output() correct
in order to reset the output? It works on my system but what is your
feedback on operations performed.

Best regards,
Hervé
diff mbox series

Patch

diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi83.c b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
index e6264514bb3f..f3d66d17f28c 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi83.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi83.c
@@ -35,9 +35,12 @@ 
 #include <linux/of_graph.h>
 #include <linux/regmap.h>
 #include <linux/regulator/consumer.h>
+#include <linux/timer.h>
+#include <linux/workqueue.h>
 
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_bridge.h>
+#include <drm/drm_drv.h> /* DRM_MODESET_LOCK_ALL_BEGIN() need drm_drv_uses_atomic_modeset() */
 #include <drm/drm_mipi_dsi.h>
 #include <drm/drm_of.h>
 #include <drm/drm_panel.h>
@@ -147,6 +150,9 @@  struct sn65dsi83 {
 	struct regulator		*vcc;
 	bool				lvds_dual_link;
 	bool				lvds_dual_link_even_odd_swap;
+	bool				use_irq;
+	struct delayed_work		monitor_work;
+	struct work_struct		reset_work;
 };
 
 static const struct regmap_range sn65dsi83_readable_ranges[] = {
@@ -328,6 +334,106 @@  static u8 sn65dsi83_get_dsi_div(struct sn65dsi83 *ctx)
 	return dsi_div - 1;
 }
 
+static int sn65dsi83_reset_drm_output(struct sn65dsi83 *sn65dsi83)
+{
+	struct drm_atomic_state *state = ERR_PTR(-EINVAL);
+	struct drm_device *dev = sn65dsi83->bridge.dev;
+	struct drm_modeset_acquire_ctx ctx;
+	struct drm_connector *connector;
+	int err;
+
+	/*
+	 * Reset components available from the encoder to the connector.
+	 * To do that, we disable then re-enable the connector linked to the
+	 * encoder.
+	 *
+	 * This way, drm core will reconfigure each components. In our case,
+	 * this will force the previous component to go back in LP11 mode and
+	 * so allow the reconfiguration of SN64DSI83 bridge.
+	 *
+	 * Keep the lock during the whole operation to be atomic.
+	 */
+
+	DRM_MODESET_LOCK_ALL_BEGIN(dev, ctx, 0, err);
+
+	state = drm_atomic_helper_duplicate_state(dev, &ctx);
+	if (IS_ERR(state)) {
+		err = PTR_ERR(state);
+		goto unlock;
+	}
+
+	connector = drm_atomic_get_old_connector_for_encoder(state,
+							     sn65dsi83->bridge.encoder);
+	if (!connector) {
+		err = -EINVAL;
+		goto unlock;
+	}
+
+	err = drm_atomic_helper_disable_connector(connector, &ctx);
+	if (err < 0)
+		goto unlock;
+
+	/* Restore original state to re-enable the connector */
+	err = drm_atomic_helper_commit_duplicated_state(state, &ctx);
+
+unlock:
+	DRM_MODESET_LOCK_ALL_END(dev, ctx, err);
+	if (!IS_ERR(state))
+		drm_atomic_state_put(state);
+	return err;
+}
+
+static void sn65dsi83_reset_work(struct work_struct *ws)
+{
+	struct sn65dsi83 *ctx = container_of(ws, struct sn65dsi83, reset_work);
+	int ret;
+
+	dev_warn(ctx->dev, "reset the drm output\n");
+
+	/* Reset the output */
+	ret = sn65dsi83_reset_drm_output(ctx);
+	if (ret) {
+		dev_err(ctx->dev, "reset drm output failed %pe\n", ERR_PTR(ret));
+		return;
+	}
+}
+
+static void sn65dsi83_handle_errors(struct sn65dsi83 *ctx)
+{
+	unsigned int irq_stat;
+	int ret;
+
+	/*
+	 * Schedule a reset in case of:
+	 *  - the bridge doesn't answer
+	 *  - the bridge signals an error
+	 */
+
+	ret = regmap_read(ctx->regmap, REG_IRQ_STAT, &irq_stat);
+	if (ret || irq_stat)
+		schedule_work(&ctx->reset_work);
+}
+
+static void sn65dsi83_monitor_work(struct work_struct *work)
+{
+	struct sn65dsi83 *ctx = container_of(to_delayed_work(work),
+					     struct sn65dsi83, monitor_work);
+
+	sn65dsi83_handle_errors(ctx);
+
+	schedule_delayed_work(&ctx->monitor_work, msecs_to_jiffies(1000));
+}
+
+static void sn65dsi83_monitor_start(struct sn65dsi83 *ctx)
+{
+	schedule_delayed_work(&ctx->monitor_work, msecs_to_jiffies(1000));
+}
+
+static void sn65dsi83_monitor_stop(struct sn65dsi83 *ctx)
+{
+	cancel_delayed_work_sync(&ctx->monitor_work);
+}
+
 static void sn65dsi83_atomic_pre_enable(struct drm_bridge *bridge,
 					struct drm_bridge_state *old_bridge_state)
 {
@@ -516,6 +622,15 @@  static void sn65dsi83_atomic_enable(struct drm_bridge *bridge,
 	regmap_read(ctx->regmap, REG_IRQ_STAT, &pval);
 	if (pval)
 		dev_err(ctx->dev, "Unexpected link status 0x%02x\n", pval);
+
+	if (ctx->use_irq) {
+		/* Enable irq to detect errors */
+		regmap_write(ctx->regmap, REG_IRQ_GLOBAL, REG_IRQ_GLOBAL_IRQ_EN);
+		regmap_write(ctx->regmap, REG_IRQ_EN, 0xff);
+	} else {
+		/* Use the polling task */
+		sn65dsi83_monitor_start(ctx);
+	}
 }
 
 static void sn65dsi83_atomic_disable(struct drm_bridge *bridge,
@@ -524,6 +639,15 @@  static void sn65dsi83_atomic_disable(struct drm_bridge *bridge,
 	struct sn65dsi83 *ctx = bridge_to_sn65dsi83(bridge);
 	int ret;
 
+	if (ctx->use_irq) {
+		/* Disable irq */
+		regmap_write(ctx->regmap, REG_IRQ_EN, 0x0);
+		regmap_write(ctx->regmap, REG_IRQ_GLOBAL, 0x0);
+	} else {
+		/* Stop the polling task */
+		sn65dsi83_monitor_stop(ctx);
+	}
+
 	/* Put the chip in reset, pull EN line low, and assure 10ms reset low timing. */
 	gpiod_set_value_cansleep(ctx->enable_gpio, 0);
 	usleep_range(10000, 11000);
@@ -681,6 +805,14 @@  static int sn65dsi83_host_attach(struct sn65dsi83 *ctx)
 	return 0;
 }
 
+static irqreturn_t sn65dsi83_irq(int irq, void *data)
+{
+	struct sn65dsi83 *ctx = data;
+
+	sn65dsi83_handle_errors(ctx);
+	return IRQ_HANDLED;
+}
+
 static int sn65dsi83_probe(struct i2c_client *client)
 {
 	const struct i2c_device_id *id = i2c_client_get_device_id(client);
@@ -698,6 +830,8 @@  static int sn65dsi83_probe(struct i2c_client *client)
 		return ret;
 
 	ctx->dev = dev;
+	INIT_WORK(&ctx->reset_work, sn65dsi83_reset_work);
+	INIT_DELAYED_WORK(&ctx->monitor_work, sn65dsi83_monitor_work);
 
 	if (dev->of_node) {
 		model = (enum sn65dsi83_model)(uintptr_t)
@@ -722,6 +856,14 @@  static int sn65dsi83_probe(struct i2c_client *client)
 	if (IS_ERR(ctx->regmap))
 		return dev_err_probe(dev, PTR_ERR(ctx->regmap), "failed to get regmap\n");
 
+	if (client->irq) {
+		ret = devm_request_threaded_irq(ctx->dev, client->irq, NULL, sn65dsi83_irq,
+						IRQF_ONESHOT, dev_name(ctx->dev), ctx);
+		if (ret)
+			return dev_err_probe(dev, ret, "failed to request irq\n");
+		ctx->use_irq = true;
+	}
+
 	dev_set_drvdata(dev, ctx);
 	i2c_set_clientdata(client, ctx);