Redflag: A Framework for Analysis of Kernel-Level Concurrency

Although sophisticated runtime bug detection tools exist to root out several kinds of concurrency errors, they cannot easily be used at the kernel level. Our

Redflag

framework and system seeks to bring these essential techniques to the Linux kernel by addressing issues faced by other tools. First, other tools typically examine every potentially concurrent memory access, which is infeasible in the kernel because of the overhead it would introduce. Redflag minimizes overhead by using offline analysis together with an efficient in-line logging system and by supporting targeted configurable logging of specific kernel components and data structures. Targeted analysis reduces overhead and avoids presenting developers with error reports for components they are not responsible for. Second, other tools do not take into account some of the synchronization patterns found in the kernel, resulting in false positives. We explore two algorithms for detecting concurrency errors: one for race conditions and another for atomicity violations; we enhanced them to take into account some specifics of synchronization in the kernel. In particular, we introduce Lexical Object Availability (LOA) analysis to deal with multi-stage escape and other complex order-enforcing synchronization. We evaluate the effectiveness and performance of Redflag on two file systems and a video driver.