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

[ Upstream commit 90ca78deb004abe75b5024968a199acb96bb70f9 ]

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>
Signed-off-by: Sasha Levin <sashal@kernel.org>

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
index 6d9252a27916d1ee5f887846e79427cd3ed9b9a2..06242096973c2578ba48a0d40c3c68781e538a7c 100644 (file)
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
@@ -2996,10 +2996,17 @@ 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;