SpecPref: High Performing Speculative Attacks Resilient Hardware Prefetchers

Abstract

With the inception of the Spectre attack in 2018, microarchitecture mitigation strategies propose secure cache hi-erarchies that do not leak the speculative state. Among many mitigation strategies, MuonTrap, proposes an efficient, secure cache hierarchy that provides speculative attack resiliency with minimum performance slowdown. Hardware prefetchers play a significant role in improving application performance by fetching and bringing data and instructions into caches before time. To prevent hardware prefetchers from leaking information about the speculative blocks brought into the cache, MuonTrap trains and triggers hardware prefetchers on the committed instruction streams, eliminating speculative state leakage. We find that on-commit prefetching can lead to significant performance slowdown as high as 20.46 % (primarily because of prefetch timeliness issues), making hardware prefetchers less effective. We propose Speculative yet Secure Prefetching (SpecPref), enhancements on top of the MuonTrap hierarchy that allows prefetching both on-commit and speculatively. We focus on improving the performance slowdown with the state-of-the-art hardware prefetchers without compromising the security guarantee provided by the MuonTrap implementation and provide an average performance slowdown of 1.17%.