Re: [PATCH v6 13/16] drm/amdgpu: Fix hang on device removal.

["Christian König" <ckoenig.leichtzumerken@gmail.com>]

Am 10.05.21 um 18:36 schrieb Andrey Grodzovsky:
> If removing while commands in flight you cannot wait to flush the
> HW fences on a ring since the device is gone.
>
> Signed-off-by: Andrey Grodzovsky <andrey.grodzovsky@amd.com>
> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 16 ++++++++++------
>   1 file changed, 10 insertions(+), 6 deletions(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> index 1ffb36bd0b19..fa03702ecbfb 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
> @@ -36,6 +36,7 @@
>   #include <linux/firmware.h>
>   #include <linux/pm_runtime.h>
>   
> +#include <drm/drm_drv.h>
>   #include "amdgpu.h"
>   #include "amdgpu_trace.h"
>   
> @@ -525,8 +526,7 @@ int amdgpu_fence_driver_init(struct amdgpu_device *adev)
>    */
>   void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
>   {
> -	unsigned i, j;
> -	int r;
> +	int i, r;

Is j not used here any more?

Christian.

>   
>   	for (i = 0; i < AMDGPU_MAX_RINGS; i++) {
>   		struct amdgpu_ring *ring = adev->rings[i];
> @@ -535,11 +535,15 @@ void amdgpu_fence_driver_fini_hw(struct amdgpu_device *adev)
>   			continue;
>   		if (!ring->no_scheduler)
>   			drm_sched_fini(&ring->sched);
> -		r = amdgpu_fence_wait_empty(ring);
> -		if (r) {
> -			/* no need to trigger GPU reset as we are unloading */
> +		/* You can't wait for HW to signal if it's gone */
> +		if (!drm_dev_is_unplugged(&adev->ddev))
> +			r = amdgpu_fence_wait_empty(ring);
> +		else
> +			r = -ENODEV;
> +		/* no need to trigger GPU reset as we are unloading */
> +		if (r)
>   			amdgpu_fence_driver_force_completion(ring);
> -		}
> +
>   		if (ring->fence_drv.irq_src)
>   			amdgpu_irq_put(adev, ring->fence_drv.irq_src,
>   				       ring->fence_drv.irq_type);