Virtualization for safety-critical, deeply-embedded devices

Abstract

Even today, safety-critical systems in many fields of application use separate processors to isolate software of different criticality from another. The resulting system architecture is non-optimal in regard to flexibility, device size and power consumption. These drawbacks can be prevented by the use of partitioning operating systems that enable the integration of applications with different criticality on a single processor. However, their application for deeply-embedded devices, that are characterized by strict resource constraints and the lack of advanced processor features such as memorymanagement units (MMU), is challenging. In this work, we show that the impact of virtualization on performance and predictability is smaller in the field of deeply-embedded devices than in more complex systems, making it a compelling choice as a partitioning technology. We present a hypervisor that provides time and space partitioning for an MMU-less system, as well as mechanisms for communication and resource sharing. To satisfy the strict power and resource constraints found in deeply-embedded devices, we focus on solutions with a minimal runtime overhead. Furthermore, the hypervisor is integrated with the processor power management, often enabling significant power savings in the resulting system architecture.

uTango: An Open-Source TEE for IoT Devices

“…Classic approaches to provide isolation and implement reliable systems on low-end embedded devices have been evolving from constructive (language/compiler-based) memory protection [58]- [62] and hardware-enforced RTOS mechanisms [21], [63], [64], to lightweight virtualization infrastructures [4], [5], [65], [66]. Tock [59] leverages limited hardware protection mechanisms as well as the type-safety features of the Rust programming language to provide a reliable multiprogramming environment for MCUs.…”

“…Another class of approaches have proposed lightweight virtualization solutions for resource-constrained devices. F. Bruns et al [65] and R. Pan et al [4] have proposed virtualization infrastructures leveraging the MPU. Pinto et al [5] have also proposed a TrustZone-based virtualization solution for Cortex-M MCUs.…”

uTango: an open-source TEE for IoT devices

“…Reliable systems for the IoT. Classic approaches to provide isolation and implement reliable systems on resourceconstrained devices have been evolving from constructive (language/compiler-based) memory protection [52]- [56] and hardware-enforced RTOS mechanisms [21], [57], [58], to lightweight virtualization infrastructures [5], [6], [59], [60]. Tock [53] leverages limited hardware protection mechanisms as well as the type-safety features of the Rust programming language to provide a reliable multiprogramming environment for MCUs.…”

“…F. Paci et al [60] proposed a lightweight I/O virtualization approach using the MPU support on FreeRTOS to create a task which mediates all I/O accesses. F. Bruns et al [59] and R. Pan et al [5] have proposed virtualization infrastructures leveraging the MPU. Pinto et al [6] have also proposed a TrustZone-based virtualization solution for Cortex-M MCUs.…”

Biologically Inspired Safety and Security for Smart Built Environments: Position Paper

“…This not only concerns the backend side of the system, but also the physical world where the data is coming from. The real-time constraints and requirements of deeply embedded devices with limited resources can be addressed by virtualization [7] A malfunctioning sensor could cause a failure in data transmission, which could potentially result in harm to the users. Similarly, the accuracy of the collected data is very important.…”