Efficient Hardware-Assisted Heap Memory Safety for Embedded RISC-V Systems
By Hyunjae Park 1; Yonghae Kim 2; Dongwook Kang 3; Hongil Ju 3; Gaeil An 3 and Yongwoo Kim 4
1 Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of Korea
2 Security and Privacy Research, Intel Labs, Hillsboro, OR 97124, USA
3 Cyber Security Research Division, Electronics and Telecommunications Research Institute, Daejeon 34129, Republic of Korea
4 Department of Technology Education, Korea National University of Education, Cheongju 28173, Republic of Korea
Abstract:
In recent years, memory safety issues in embedded environments have garnered significant attention, with spatial and temporal memory violations in heap memory emerging as critical security threats. To address these challenges, this paper proposes an efficient tag-based memory verification system specifically designed for RISC-V in-order processors. The proposed system integrates a Heap Check Cache (HC-Cache), FIFO Buffer, and Store Head Buffer/Clear Head Buffer (SHB/CHB) with a replay mechanism at the hardware level to minimize performance overhead. On the software side, it incorporates extended RISC-V ISA instructions and a modified Newlib C library to automate metadata management and tag generation without requiring additional modifications to user applications. The system was implemented on an FPGA platform using the Xilinx VC707 board. The implementation results indicate a 16.07% increase in LUTs and a 58.25% increase in Flip-Flops, while maintaining minimal overhead for BRAM (0.66%) and LUTRAM (0.99%). Performance evaluations using workloads such as Mibench, Olden, and SPEC2006 demonstrated a significantly lower average performance overhead compared to previous work. Furthermore, verification using the NIST Juliet Test Suite 1.3 revealed that the system successfully detected 100% of heap-related vulnerabilities, including 1,924 heap-based overflows, 803 double-free errors, and 394 use-after-free errors. These results demonstrate that the proposed system provides high security and performance efficiency, even in resource-constrained embedded environments.
To read the full article, click here
Related Semiconductor IP
- 64 bit RISC-V Multicore Processor with 2048-bit VLEN and AMM
- RISC-V AI Acceleration Platform - Scalable, standards-aligned soft chiplet IP
- 32 bit RISC-V Multicore Processor with 256-bit VLEN and AMM
- All-In-One RISC-V NPU
- ISO26262 ASIL-B/D Compliant 32-bit RISC-V Core
Related White Papers
- A RISC-V Multicore and GPU SoC Platform with a Qualifiable Software Stack for Safety Critical Systems
- ACE: Confidential Computing for Embedded RISC-V Systems
- NAND Flash memory in embedded systems
- Rethinking embedded memory
Latest White Papers
- How Next-Gen Chips Are Unlocking RISC-V’s Customization Advantage
- Efficient Hardware-Assisted Heap Memory Safety for Embedded RISC-V Systems
- Automatically Retargeting Hardware and Code Generation for RISC-V Custom Instructions
- How Mature-Technology ASICs Can Give You the Edge
- Exploring the Latest Innovations in MIPI D-PHY and MIPI C-PHY