drm/imagination: Clear runtime PM errors while resetting the GPU

[ Upstream commit 551507e0d0bf32ce1d7d27533c4b98307380804c ]

The runtime PM might be left in error state if one of the callbacks
returned an error, e.g. if the (auto)suspend callback failed following
a firmware crash.

When that happens, any further attempt to acquire or release a power
reference will then also fail, making it impossible to do anything else
with the GPU. The driver logic will eventually reach the reset code.

In pvr_power_reset(), replace pvr_power_get() with a new API
pvr_power_get_clear() which also attempts to clear any runtime PM error
state if acquiring a power reference is not possible.

Signed-off-by: Alessio Belle <alessio.belle@imgtec.com>
Reviewed-by: Matt Coster <matt.coster@imgtec.com>
Link: https://lore.kernel.org/r/20250624-clear-rpm-errors-gpu-reset-v1-1-b8ff2ae55aac@imgtec.com
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 58 insertions, 1 deletions

diff --git a/drivers/gpu/drm/imagination/pvr_power.c b/drivers/gpu/drm/imagination/pvr_power.c
index 850b318605da..d97613c6a0a9 100644
--- a/drivers/gpu/drm/imagination/pvr_power.c
+++ b/drivers/gpu/drm/imagination/pvr_power.c
@@ -317,6 +317,63 @@ pvr_power_device_idle(struct device *dev)
 	return pvr_power_is_idle(pvr_dev) ? 0 : -EBUSY;
 }
 
+static int
+pvr_power_clear_error(struct pvr_device *pvr_dev)
+{
+	struct device *dev = from_pvr_device(pvr_dev)->dev;
+	int err;
+
+	/* Ensure the device state is known and nothing is happening past this point */
+	pm_runtime_disable(dev);
+
+	/* Attempt to clear the runtime PM error by setting the current state again */
+	if (pm_runtime_status_suspended(dev))
+		err = pm_runtime_set_suspended(dev);
+	else
+		err = pm_runtime_set_active(dev);
+
+	if (err) {
+		drm_err(from_pvr_device(pvr_dev),
+			"%s: Failed to clear runtime PM error (new error %d)\n",
+			__func__, err);
+	}
+
+	pm_runtime_enable(dev);
+
+	return err;
+}
+
+/**
+ * pvr_power_get_clear() - Acquire a power reference, correcting any errors
+ * @pvr_dev: Device pointer
+ *
+ * Attempt to acquire a power reference on the device. If the runtime PM
+ * is in error state, attempt to clear the error and retry.
+ *
+ * Returns:
+ *  * 0 on success, or
+ *  * Any error code returned by pvr_power_get() or the runtime PM API.
+ */
+static int
+pvr_power_get_clear(struct pvr_device *pvr_dev)
+{
+	int err;
+
+	err = pvr_power_get(pvr_dev);
+	if (err == 0)
+		return err;
+
+	drm_warn(from_pvr_device(pvr_dev),
+		 "%s: pvr_power_get returned error %d, attempting recovery\n",
+		 __func__, err);
+
+	err = pvr_power_clear_error(pvr_dev);
+	if (err)
+		return err;
+
+	return pvr_power_get(pvr_dev);
+}
+
 /**
  * pvr_power_reset() - Reset the GPU
  * @pvr_dev: Device pointer
@@ -341,7 +398,7 @@ pvr_power_reset(struct pvr_device *pvr_dev, bool hard_reset)
 	 * Take a power reference during the reset. This should prevent any interference with the
 	 * power state during reset.
 	 */
-	WARN_ON(pvr_power_get(pvr_dev));
+	WARN_ON(pvr_power_get_clear(pvr_dev));
 
 	down_write(&pvr_dev->reset_sem);