Commit 6ba60345 authored by Harish Kasiviswanathan's avatar Harish Kasiviswanathan Committed by Alex Deucher
Browse files

drm/amdgpu: Fix double deletion of validate_list 



If amdgpu_amdkfd_gpuvm_free_memory_of_gpu() fails after kgd_mem is
removed from validate_list, the mem handle still lingers in the KFD idr.
This means when process is terminated,
kfd_process_free_outstanding_kfd_bos() will call
amdgpu_amdkfd_gpuvm_free_memory_of_gpu() again resulting in double
deletion.

To avoid this -
 (a) Check if list is empty before deleting it
 (b) Rearragne amdgpu_amdkfd_gpuvm_free_memory_of_gpu() such that it can
     be safely called again if it returns failure the first time.

Signed-off-by: default avatarHarish Kasiviswanathan <Harish.Kasiviswanathan@amd.com>
Reviewed-by: default avatarPhilip Yang <Philip.Yang@amd.com>
Signed-off-by: default avatarAlex Deucher <alexander.deucher@amd.com>
parent 08b1eb62

drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c

+7 −7
Original line number Diff line number Diff line
@@ -1924,21 +1924,21 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu( 


	/* Make sure restore workers don't access the BO any more */

	mutex_lock(&process_info->lock);

	list_del(&mem->validate_list);

	if (!list_empty(&mem->validate_list))

		list_del_init(&mem->validate_list);

	mutex_unlock(&process_info->lock);



	ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);

	if (unlikely(ret))

		return ret;



	/* Cleanup user pages and MMU notifiers */

	if (amdgpu_ttm_tt_get_usermm(mem->bo->tbo.ttm)) {

		amdgpu_hmm_unregister(mem->bo);

		mutex_lock(&process_info->notifier_lock);

		amdgpu_hmm_range_free(mem->range);

		mutex_unlock(&process_info->notifier_lock);

		mem->range = NULL;

	}



	ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);

	if (unlikely(ret))

		return ret;



	amdgpu_amdkfd_remove_eviction_fence(mem->bo,

					process_info->eviction_fence);

	pr_debug("Release VA 0x%llx - 0x%llx\n", mem->va,