drm/amdgpu: fix task hang from failed job submission during process kill

commit aa5fc43 upstream.

During process kill, drm_sched_entity_flush() will kill the vm
entities. The following job submissions of this process will fail, and
the resources of these jobs have not been released, nor have the fences
been signalled, causing tasks to hang and timeout.

Fix by check entity status in amdgpu_vm_ready() and avoid submit jobs to
stopped entity.

v2: add amdgpu_vm_ready() check before amdgpu_vm_clear_freed() in
function amdgpu_cs_vm_handling().

Fixes: 1f02f20 ("drm/amdgpu: Avoid extra evict-restore process.")
Signed-off-by: Liu01 Tong <[email protected]>
Signed-off-by: Lin.Cao <[email protected]>
Reviewed-by: Christian König <[email protected]>
Signed-off-by: Alex Deucher <[email protected]>
(cherry picked from commit f101c13)
Signed-off-by: Greg Kroah-Hartman <[email protected]>

Author: Liu01 Tong

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

@@ -1138,6 +1138,9 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
 		}
 	}
 
+	if (!amdgpu_vm_ready(vm))
+		return -EINVAL;
+
 	r = amdgpu_vm_clear_freed(adev, vm, NULL);
 	if (r)
 		return r;

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

@@ -654,22 +654,29 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
  * Check if all VM PDs/PTs are ready for updates
  *
  * Returns:
- * True if VM is not evicting.
+ * True if VM is not evicting and all VM entities are not stopped
  */
 bool amdgpu_vm_ready(struct amdgpu_vm *vm)
 {
-	bool empty;
 	bool ret;
 
 	amdgpu_vm_eviction_lock(vm);
 	ret = !vm->evicting;
 	amdgpu_vm_eviction_unlock(vm);
 
 	spin_lock(&vm->status_lock);
-	empty = list_empty(&vm->evicted);
+	ret &= list_empty(&vm->evicted);
 	spin_unlock(&vm->status_lock);
 
-	return ret && empty;
+	spin_lock(&vm->immediate.lock);
+	ret &= !vm->immediate.stopped;
+	spin_unlock(&vm->immediate.lock);
+
+	spin_lock(&vm->delayed.lock);
+	ret &= !vm->delayed.stopped;
+	spin_unlock(&vm->delayed.lock);
+
+	return ret;
 }
 
 /**