[PATCH] drm/amdgpu: avoid restore process run into dead loop.

[Felix Kuehling]

Am 2023-03-02 um 13:15 schrieb Gang Ba:
> In restore process worker, pinned BO cause update PTE fail, then
> the function re-schedule the restore_work. This will generate dead loop.
>
> Signed-off-by: Gang Ba <gaba at amd.com>

Reviewed-by: Felix Kuehling <Felix.Kuehling at amd.com>


> ---
>   drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c | 5 ++++-
>   1 file changed, 4 insertions(+), 1 deletion(-)
>
> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> index 4b46b936a804..a38be83e486e 100644
> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
> @@ -2586,7 +2586,7 @@ int amdgpu_amdkfd_gpuvm_export_ipc_obj(struct amdgpu_device *adev, void *vm,
>   	struct dma_buf *dmabuf;
>   	int r;
>   
> -	if (!adev|| !vm || !mem)
> +	if (!adev || !vm || !mem)
>   		return -EINVAL;
>   
>   	mutex_lock(&mem->lock);
> @@ -3170,6 +3170,9 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef)
>   			if (!attachment->is_mapped)
>   				continue;
>   
> +			if (attachment->bo_va->base.bo->tbo.pin_count)
> +				continue;
> +
>   			kfd_mem_dmaunmap_attachment(mem, attachment);
>   			ret = update_gpuvm_pte(mem, attachment, &sync_obj);
>   			if (ret) {