MOESI-prime: preventing coherence-induced hammering in commodity workloads

Abstract

Prior work shows that Rowhammer attacks---which flip bits in DRAM via frequent activations of the same row(s)---are viable. Adversaries typically mount these attacks via instruction sequences that are carefully-crafted to bypass CPU caches. However, we discover a novel form of hammering that we refer to as coherence-induced hammering, caused by Intel's implementations of cache coherent non-uniform memory access (ccNUMA) protocols. We show that this hammering occurs in commodity benchmarks on a major cloud provider's production hardware, the first hammering found to be generated by non-malicious code. Given DRAM's rising susceptibility to bit flips, it is paramount to prevent coherence-induced hammering to ensure reliability and security in the cloud. Accordingly, we introduce MOESI-prime, a ccNUMA coherence protocol that mitigates coherence-induced hammering while retaining Intel's state-of-the-art scalability. MOESI-prime shows that most DRAM reads and writes triggering such hammering are unnecessary. Thus, by encoding additional information in the coherence protocol, MOESI-prime can omit these reads and writes, preventing coherence-induced hammering in non-malicious and malicious workloads. Furthermore, by omitting unnecessary reads and writes, MOESI-prime has negligible effect on average performance (within ±0.61% of MESI and MOESI) and average DRAM power (0.03%-0.22% improvement) across evaluated ccNUMA configurations.