[Paper Review] A Multi-Core Processor Platform for Open Embedded Systems

Hiroaki Inoue|arXiv (Cornell University)|Jun 29, 2010

Parallel Computing and Optimization Techniques1 references3 citations

TL;DR

This paper proposes a multi-core processor platform for open embedded systems that achieves both scalability and security through hardware-supported secure processor partitioning and four novel techniques: seamless communication, asymmetric virtualization, secure dynamic partitioning, and secure execution of legacy and open applications. The platform enables secure, scalable, and efficient execution of multiple operating systems on shared hardware without software modifications.

ABSTRACT

Recent proliferation of embedded systems has generated a bold new paradigm, known as open embedded systems. While traditional embedded systems provide only closed base applications (natively-installed software) to users, open embedded systems allow the users to freely execute open applications (additionally-installed software) in order to meet various user requirements, such as user personalization and device coordination. Key to the success of platforms required for open embedded systems is the achievement of both the scalable extension of base applications and the secure execution of open applications. Most existing platforms, however, have focused on either scalable or secure execution, limiting their applicability. This dissertation presents a new secure platform using multi-core processors, which achieves both scalability and security. Four techniques feature the new platform: (1) seamless communication, by which legacy applications designed for a single processor make it possible to be executed on multiple processors without any software modifications; (2) secure processor partitioning with hardware support, by which Operating Systems (OSs) required for base and open applications are securely executed on separate processors; (3) asymmetric virtualization, by which many OSs over the number of processors are securely executed under secure processor partitioning; and (4) secure dynamic partitioning, by which the number of processors allocated to individual OSs makes it possible to be dynamically changed under secure processor partitioning.

Motivation & Objective

• To address the growing need for open embedded systems that support user-customizable applications while maintaining system security.
• To overcome the limitations of existing platforms that prioritize either scalability or security, but not both.
• To design a secure, extensible platform for open embedded systems using multi-core processors.
• To enable seamless execution of legacy single-processor applications on multi-core architectures without modification.
• To support dynamic and secure allocation of processor resources to multiple operating systems.

Proposed method

• Enables seamless communication between legacy applications and multi-core systems without software changes, using a communication layer that abstracts processor distribution.
• Implements hardware-supported secure processor partitioning to isolate base and open application operating systems on separate cores.
• Applies asymmetric virtualization to run more operating systems than physical cores by time-multiplexing, while maintaining isolation and security.
• Introduces secure dynamic partitioning to allow runtime reconfiguration of processor allocation among OSs, preserving security during transitions.
• Uses hardware-enforced isolation to ensure that open applications cannot interfere with base system functionality or other OSs.
• Combines these techniques into a unified platform that supports both backward compatibility and extensibility in open embedded environments.

Experimental results

Research questions

• RQ1 How can legacy single-processor applications be executed on multi-core systems without modification?
• RQ2 How can multiple operating systems be securely isolated and executed on shared multi-core hardware?
• RQ3 Can more operating systems be supported than the number of physical cores while maintaining security?
• RQ4 How can processor allocation be dynamically adjusted at runtime without compromising security?
• RQ5 Can a platform achieve both scalability and strong security in open embedded systems?

Key findings

• The platform enables legacy applications to run on multi-core systems without modification, ensuring backward compatibility.
• Hardware-supported secure processor partitioning successfully isolates base and open application operating systems, preventing interference.
• Asymmetric virtualization allows more OS instances than physical cores to be securely executed through time-multiplexed scheduling.
• Secure dynamic partitioning enables runtime adjustment of processor allocation among OSs, supporting flexible workload management.
• The integration of all four techniques results in a secure, scalable, and extensible platform suitable for open embedded systems.
• The platform demonstrates feasibility and practicality for real-world embedded systems requiring both openness and strong security.