drm/amdgpu: shrink critical section in amdgpu_amdkfd_gpuvm_free_memory_of_gpu

Reduce the mem->lock`s protected code area, no need to protect pr_debug.
This also simplifies error handling.

Signed-off-by: Bernard Zhao <bernard@vivo.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Bernard Zhao 2020-04-20 23:48:18 -07:00 committed by Alex Deucher
parent 6f81b2d047
commit fe158997c8

View File

@ -1284,22 +1284,22 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
struct kfd_bo_va_list *entry, *tmp;
struct bo_vm_reservation_context ctx;
struct ttm_validate_buffer *bo_list_entry;
unsigned int mapped_to_gpu_memory;
int ret;
mutex_lock(&mem->lock);
if (mem->mapped_to_gpu_memory > 0) {
pr_debug("BO VA 0x%llx size 0x%lx is still mapped.\n",
mem->va, bo_size);
mutex_unlock(&mem->lock);
return -EBUSY;
}
mapped_to_gpu_memory = mem->mapped_to_gpu_memory;
mutex_unlock(&mem->lock);
/* lock is not needed after this, since mem is unused and will
* be freed anyway
*/
if (mapped_to_gpu_memory > 0) {
pr_debug("BO VA 0x%llx size 0x%lx is still mapped.\n",
mem->va, bo_size);
return -EBUSY;
}
/* No more MMU notifiers */
amdgpu_mn_unregister(mem->bo);