TWiCe: Time Window Counter Based Row Refresh to Prevent Row-Hammering

Abstract

Computer systems using DRAM are exposed to row-hammering attacks, which can flip data in a DRAM row without directly accessing a row but by frequently activating its adjacent ones. There have been a number of proposals to prevent row-hammering, but they either incur large area/performance overhead or provide probabilistic protection. In this paper, we propose a new row-hammering mitigation mechanism named T ime Wi ndow C ount e r based row refresh (TWiCe) which prevents row-hammering by using a small number of counters without performance overhead. We first make a key observation that the number of rows that can cause flipping their adjacent ones (aggressor candidates) is limited by the maximum values of row activation frequency and DRAM cell retention time. TWiCe exploits this limit to reduce the required number of counter entries by counting only actually activated DRAM rows and periodically invalidating the entries that are not activated frequently enough to be an aggressor. We calculate the maximum number of required counter entries per DRAM bank, with which row-hammering prevention is guaranteed. We further improve energy efficiency by adopting a pseudo-associative cache design to TWiCe. Our analysis shows that TWiCe incurs no performance overhead on normal DRAM operations and less than 0.7 percent area and energy overheads over contemporary DRAM devices.