USENIX Security '21 - Blinder: Partition-Oblivious Hierarchical Scheduling
Man-Ki Yoon, Mengqi Liu, Hao Chen, Jung-Eun Kim, and Zhong Shao, Yale University
Hierarchical scheduling enables modular reasoning about the temporal behavior of individual applications by partitioning CPU time and thus isolating potential misbehavior. However, conventional time-partitioning mechanisms fail to achieve strong temporal isolation from a security perspective; variations in the executions of partitions can be perceived by others, which enables an algorithmic covert timing-channel between partitions that are completely isolated from each other in the utilization of time. Thus, we present a run-time algorithm that makes partitions oblivious to others' varying behaviors even when an adversary has full control over their timings. It enables the use of dynamic time-partitioning mechanisms that provide improved responsiveness, while guaranteeing the algorithmic-level non-interference that static approaches would achieve. From an implementation on an open-source operating system, we evaluate the costs of the solution in terms of the responsiveness as well as scheduling overhead.
View the full USENIX Security '21 Program at https://www.usenix.org/conference/usenixsecurity21/technical-sessions