Abstract
Modern real-time embedded systems demand strong component isolation for safety and security. Normally, interrupts are handled in kernel mode before they are passed on to the application, which induces high latency if isolated components need to react to external events. Thus, hardware-assisted, low-latency user-level interrupts are highly desirable. Nevertheless, existing hardware mechanisms only optimize average-case performance while neglecting worst-case latency for sensitive applications including autonomous vehicles and robots. To overcome this limitation, we propose a novel open-source hardware extension that integrates spatial isolation setup, execution budget management, cross-domain nesting, and accelerated context switching for user-level interrupts with tight latency. It enables direct, deterministic delivery upon user-level interrupt arrival-without kernel intervention-even when the target process is dormant. Across the entire design space, the best-performing design reduces worst-case latency by over 50×, while the lowest-overhead design incurs only a 23% increase in core area (2% of total die area) and a 3% increase in dynamic power. To the best of our knowledge, this is the first integrated mechanism to guarantee multi-tenant user-level interrupt delivery with a nanosecond-scale yet bounded worst-case latency. It provides a holistic solution for developing secure, dependable, and low-latency cyber-physical systems in real-time consolidation scenarios.
Funding Information
  • National Key R&D Program of China (2022YFB4502001)
  • National Natural Science Foundation of China (62402291)
  • National Natural Science Foundation of China (62302265)
  • National Natural Science Foundation of China (62232010)
  • National Natural Science Foundation of China (U23A20332)
  • Shandong Province Natural Science Foundation (ZR2023QF172)
  • Shandong Province Natural Science Foundation (2024HWYQ-020)

This publication has 35 references indexed in Scilit: