drm/amdkfd: fix restore worker race condition

[ Upstream commit f7646585a30ed8ef5ab300d4dc3b0c1d6afbe71d ]

In free memory of gpu path, remove bo from validate_list to make sure
restore worker don't access the BO any more, then unregister bo MMU
interval notifier. Otherwise, the restore worker will crash in the
middle of validating BO user pages if MMU interval notifer is gone.

Signed-off-by: Philip Yang <Philip.Yang@amd.com>
Reviewed-by: Felix Kuehling <Felix.Kuehling@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
index edb561baf8b90ad95091477526ff0ff018ff2186..f3fa271e3394c0b75070605764505b3710ffe2fc 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
@@ -1247,15 +1247,15 @@ int amdgpu_amdkfd_gpuvm_free_memory_of_gpu(
         * be freed anyway
         */
 
-       /* No more MMU notifiers */
-       amdgpu_mn_unregister(mem->bo);
-
        /* Make sure restore workers don't access the BO any more */
        bo_list_entry = &mem->validate_list;
        mutex_lock(&process_info->lock);
        list_del(&bo_list_entry->head);
        mutex_unlock(&process_info->lock);
 
+       /* No more MMU notifiers */
+       amdgpu_mn_unregister(mem->bo);
+
        ret = reserve_bo_and_cond_vms(mem, NULL, BO_VM_ALL, &ctx);
        if (unlikely(ret))
                return ret;