drm/amdgpu: Sync with VM root BO when switching VM to CPU update mode

This fixes an intermittent bug where a root PD clear operation still in
progress could overwrite a PDE update done by the CPU, resulting in a
VM fault.

Fixes: 108b4d928c03 ("drm/amd/amdgpu: Update VM function pointer")
Reported-by: Jay Cornwall <Jay.Cornwall@amd.com>
Tested-by: Jay Cornwall <Jay.Cornwall@amd.com>
Signed-off-by: Felix Kuehling <Felix.Kuehling@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 414a0b1c2e5a87e942b8d0edb6878528fc322665..7417754e9141b02fde4b3963efb7ce96132f97b3 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -3000,10 +3000,17 @@ int amdgpu_vm_make_compute(struct amdgpu_device *adev, struct amdgpu_vm *vm,
                   !amdgpu_gmc_vram_full_visible(&adev->gmc)),
                  "CPU update of VM recommended only for large BAR system\n");
 
-       if (vm->use_cpu_for_update)
+       if (vm->use_cpu_for_update) {
+               /* Sync with last SDMA update/clear before switching to CPU */
+               r = amdgpu_bo_sync_wait(vm->root.base.bo,
+                                       AMDGPU_FENCE_OWNER_UNDEFINED, true);
+               if (r)
+                       goto free_idr;
+
                vm->update_funcs = &amdgpu_vm_cpu_funcs;
-       else
+       } else {
                vm->update_funcs = &amdgpu_vm_sdma_funcs;
+       }
        dma_fence_put(vm->last_update);
        vm->last_update = NULL;
        vm->is_compute_context = true;