[TensorRT EP] Fix concurrency issue for TRT custom op list (microsoft…

…#20093)

The `CreateTensorRTCustomOpDomainList()` is not thread-safe due to its
static variables, `created_custom_op_list` and `custom_op_domain`.
This PR makes sure synchronization using mutex.

see issue: microsoft#20089

onnxruntime/core/providers/tensorrt/tensorrt_execution_provider_custom_ops.cc

@@ -28,6 +28,8 @@ extern TensorrtLogger& GetTensorrtLogger();
 common::Status CreateTensorRTCustomOpDomainList(std::vector<OrtCustomOpDomain*>& domain_list, const std::string extra_plugin_lib_paths) {
   static std::unique_ptr<OrtCustomOpDomain> custom_op_domain = std::make_unique<OrtCustomOpDomain>();
   static std::vector<std::unique_ptr<TensorRTCustomOp>> created_custom_op_list;
+  static OrtMutex mutex;
+  std::lock_guard<OrtMutex> lock(mutex);
   if (custom_op_domain->domain_ != "" && custom_op_domain->custom_ops_.size() > 0) {
     domain_list.push_back(custom_op_domain.get());
     return Status::OK();