Memory Safety Acceleration on RISC-V for C Programming Language

Download files
Access & Terms of Use
open access
Copyright: Dow, Kenny
Memory corruption vulnerabilities can lead to memory attacks. Three of the top ten most dangerous weaknesses in computer security are memory-related. Memory attack is one of a computer system’s oldest but everlasting problems. Companies and the government lost billions of dollars due to memory security breaches. Memory safety is paramount to securing memory systems. Pointer-based memory safety protection has been shown as a promising solution covering both out-of-bounds and use-after-free errors. However, pointer-based memory safety relies on additional information (metadata) to check validity when a pointer is dereferenced. Such operations on the metadata introduce significant performance overhead to the system. Existing hardware/software implementations are primarily limited to proprietary closed-source microprocessors, simulation-only studies, or require changes to the input source code. In order to provide the need for memory security, we created a memory-safe RISC-V platform with low-performance overhead. In this thesis, a novel hardware/software co-design methodology consisting of a RISC-V based processor is extended with new instructions and microarchitecture enhancements, enabling complete memory safety in the C programming language and faster memory safety checks. Furthermore, a compiler is instrumented to provide security operations considering the changes to the processor. Moreover, a design exploration framework is proposed to provide an in-depth search for optimal hardware/software configuration for application-specific workloads regarding performance overhead, security coverage, area cost, and critical path latency. The entire system is realized by enhancing a RISC-V Rocket-chip system-on-chip (SoC). The resultant processor SoC is implemented on an FPGA and evaluated with applications from SPEC 2006 (for generic applications), MiBench (for embedded applications), and Olden benchmark suites for performance. The system, including the RISC-V CHISEL, compiler, profiling and analysis tool-chain, is fully available and open-source to the public.
Persistent link to this record
Link to Publisher Version
Link to Open Access Version
Additional Link
Conference Proceedings Editor(s)
Other Contributor(s)
Corporate/Industry Contributor(s)
Publication Year
Resource Type
Degree Type
PhD Doctorate
UNSW Faculty
download public version.pdf 7.65 MB Adobe Portable Document Format
Related dataset(s)