[PATCH v2 8/8] drm/amdgpu: Prevent any job recoveries after device is unplugged.

[Daniel Vetter]

On Sun, Jun 21, 2020 at 02:03:08AM -0400, Andrey Grodzovsky wrote:
> No point to try recovery if device is gone, just messes up things.
> 
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky at amd.com>
> ---
>  drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 16 ++++++++++++++++
>  drivers/gpu/drm/amd/amdgpu/amdgpu_job.c |  8 ++++++++
>  2 files changed, 24 insertions(+)
> 
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> index 6932d75..5d6d3d9 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c
> @@ -1129,12 +1129,28 @@ static int amdgpu_pci_probe(struct pci_dev *pdev,
>  	return ret;
>  }
>  
> +static void amdgpu_cancel_all_tdr(struct amdgpu_device *adev)
> +{
> +	int i;
> +
> +	for (i = 0; i < AMDGPU_MAX_RINGS; ++i) {
> +		struct amdgpu_ring *ring = adev->rings[i];
> +
> +		if (!ring || !ring->sched.thread)
> +			continue;
> +
> +		cancel_delayed_work_sync(&ring->sched.work_tdr);
> +	}
> +}

I think this is a function that's supposed to be in drm/scheduler, not
here. Might also just be your cleanup code being ordered wrongly, or your
split in one of the earlier patches not done quite right.
-Daniel

> +
>  static void
>  amdgpu_pci_remove(struct pci_dev *pdev)
>  {
>  	struct drm_device *dev = pci_get_drvdata(pdev);
> +	struct amdgpu_device *adev = dev->dev_private;
>  
>  	drm_dev_unplug(dev);
> +	amdgpu_cancel_all_tdr(adev);
>  	ttm_bo_unmap_virtual_address_space(&adev->mman.bdev);
>  	amdgpu_driver_unload_kms(dev);
>  
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> index 4720718..87ff0c0 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
> @@ -28,6 +28,8 @@
>  #include "amdgpu.h"
>  #include "amdgpu_trace.h"
>  
> +#include <drm/drm_drv.h>
> +
>  static void amdgpu_job_timedout(struct drm_sched_job *s_job)
>  {
>  	struct amdgpu_ring *ring = to_amdgpu_ring(s_job->sched);
> @@ -37,6 +39,12 @@ static void amdgpu_job_timedout(struct drm_sched_job *s_job)
>  
>  	memset(&ti, 0, sizeof(struct amdgpu_task_info));
>  
> +	if (drm_dev_is_unplugged(adev->ddev)) {
> +		DRM_INFO("ring %s timeout, but device unplugged, skipping.\n",
> +					  s_job->sched->name);
> +		return;
> +	}
> +
>  	if (amdgpu_ring_soft_recovery(ring, job->vmid, s_job->s_fence->parent)) {
>  		DRM_ERROR("ring %s timeout, but soft recovered\n",
>  			  s_job->sched->name);
> -- 
> 2.7.4
> 

-- 
Daniel Vetter
Software Engineer, Intel Corporation
http://blog.ffwll.ch