Re: [PATCH] drm/amdgpu: don't runtime suspend if there are displays attached (v2)

[Paul Menzel <pmenzel@molgen.mpg.de>]

Dear Alex,


Thank you for the patch.

Am 13.04.22 um 22:15 schrieb Alex Deucher:
> We normally runtime suspend when there are displays attached if they
> are in the DPMS off state, however, if something wakes the GPU
> we send a hotplug event on resume (in case any displays were connected
> while the GPU was in suspend) which can cause userspace to light
> up the displays again soon after they were turned off.
> 
> Prior to
> commit 087451f372bf76 ("drm/amdgpu: use generic fb helpers instead of setting up AMD own's."),
> the driver took a runtime pm reference when the fbdev emulation was
> enabled because we didn't implement proper shadowing support for
> vram access when the device was off so the device never runtime
> suspended when there was a console bound.  Once that commit landed,
> we now utilize the core fb helper implementation which properly
> handles the emulation, so runtime pm now suspends in cases where it did
> not before.  Ultimately, we need to sort out why runtime suspend in not
> working in this case for some users, but this should restore similar
> behavior to before.
> 
> v2: move check into runtime_suspend
> 
> Fixes: 087451f372bf76 ("drm/amdgpu: use generic fb helpers instead of setting up AMD own's.")
> Tested-by: Michele Ballabio <ballabio.m@gmail.com>

On what system and device?

> Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 107 ++++++++++++++++--------
>   1 file changed, 72 insertions(+), 35 deletions(-)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 4efaa183abcd..97a1aa02d76e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -2395,6 +2395,71 @@ static int amdgpu_pmops_restore(struct device *dev)
>   	return amdgpu_device_resume(drm_dev, true);
>   }
>   
> +static int amdgpu_runtime_idle_check_display(struct device *dev)
> +{
> +	struct pci_dev *pdev = to_pci_dev(dev);
> +	struct drm_device *drm_dev = pci_get_drvdata(pdev);
> +	struct amdgpu_device *adev = drm_to_adev(drm_dev);
> +
> +	if (adev->mode_info.num_crtc) {
> +		struct drm_connector *list_connector;
> +		struct drm_connector_list_iter iter;
> +		int ret = 0;
> +
> +		/* XXX: Return busy if any displays are connected to avoid
> +		 * possible display wake ups after runtime resume due to

Nit: wakeups

> +		 * hotplug events in case any displays were connected while
> +		 * the GPU was in suspend.  Remove this once that is fixed.
> +		 */

Do you have an (internal) issue to track this?

> +		mutex_lock(&drm_dev->mode_config.mutex);
> +		drm_connector_list_iter_begin(drm_dev, &iter);
> +		drm_for_each_connector_iter(list_connector, &iter) {
> +			if (list_connector->status == connector_status_connected) {
> +				ret = -EBUSY;
> +				break;
> +			}
> +		}
> +		drm_connector_list_iter_end(&iter);
> +		mutex_unlock(&drm_dev->mode_config.mutex);
> +
> +		if (ret)
> +			return ret;
> +
> +		if (amdgpu_device_has_dc_support(adev)) {
> +			struct drm_crtc *crtc;
> +
> +			drm_for_each_crtc(crtc, drm_dev) {
> +				drm_modeset_lock(&crtc->mutex, NULL);
> +				if (crtc->state->active)
> +					ret = -EBUSY;
> +				drm_modeset_unlock(&crtc->mutex);
> +				if (ret < 0)
> +					break;
> +			}
> +		} else {
> +			mutex_lock(&drm_dev->mode_config.mutex);
> +			drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL);
> +
> +			drm_connector_list_iter_begin(drm_dev, &iter);
> +			drm_for_each_connector_iter(list_connector, &iter) {
> +				if (list_connector->dpms ==  DRM_MODE_DPMS_ON) {
> +					ret = -EBUSY;
> +					break;
> +				}
> +			}
> +
> +			drm_connector_list_iter_end(&iter);
> +
> +			drm_modeset_unlock(&drm_dev->mode_config.connection_mutex);
> +			mutex_unlock(&drm_dev->mode_config.mutex);
> +		}
> +		if (ret)
> +			return ret;
> +	}
> +
> +	return 0;
> +}
> +
>   static int amdgpu_pmops_runtime_suspend(struct device *dev)
>   {
>   	struct pci_dev *pdev = to_pci_dev(dev);
> @@ -2407,6 +2472,10 @@ static int amdgpu_pmops_runtime_suspend(struct device *dev)
>   		return -EBUSY;
>   	}
>   
> +	ret = amdgpu_runtime_idle_check_display(dev);
> +	if (ret)
> +		return ret;
> +
>   	/* wait for all rings to drain before suspending */
>   	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
>   		struct amdgpu_ring *ring = adev->rings[i];
> @@ -2516,41 +2585,9 @@ static int amdgpu_pmops_runtime_idle(struct device *dev)
>   		return -EBUSY;
>   	}
>   
> -	if (amdgpu_device_has_dc_support(adev)) {
> -		struct drm_crtc *crtc;
> -
> -		drm_for_each_crtc(crtc, drm_dev) {
> -			drm_modeset_lock(&crtc->mutex, NULL);
> -			if (crtc->state->active)
> -				ret = -EBUSY;
> -			drm_modeset_unlock(&crtc->mutex);
> -			if (ret < 0)
> -				break;
> -		}
> -
> -	} else {
> -		struct drm_connector *list_connector;
> -		struct drm_connector_list_iter iter;
> -
> -		mutex_lock(&drm_dev->mode_config.mutex);
> -		drm_modeset_lock(&drm_dev->mode_config.connection_mutex, NULL);
> -
> -		drm_connector_list_iter_begin(drm_dev, &iter);
> -		drm_for_each_connector_iter(list_connector, &iter) {
> -			if (list_connector->dpms ==  DRM_MODE_DPMS_ON) {
> -				ret = -EBUSY;
> -				break;
> -			}
> -		}
> -
> -		drm_connector_list_iter_end(&iter);
> -
> -		drm_modeset_unlock(&drm_dev->mode_config.connection_mutex);
> -		mutex_unlock(&drm_dev->mode_config.mutex);
> -	}
> -
> -	if (ret == -EBUSY)
> -		DRM_DEBUG_DRIVER("failing to power off - crtc active\n");
> +	ret = amdgpu_runtime_idle_check_display(dev);
> +	if (ret)
> +		return ret;
>   
>   	pm_runtime_mark_last_busy(dev);
>   	pm_runtime_autosuspend(dev);

The overall change looks good.


Kind regards,

Paul