Instruction Caches in Static WCET Analysis of Artificially Diversified Software

Artificial Software Diversity is a well-established method to increase security of computer systems by thwarting code-reuse attacks, which is particularly beneficial in safety-critical real-time systems. However, static worst-case execution time (WCET) analysis on complex hardware involving caches only delivers sound results for single versions of the program, as it relies on absolute addresses for all instructions. To overcome this problem, we present an abstract interpretation based instruction cache analysis that provides a safe yet precise upper bound for the execution of all variants of a program. We achieve this by integrating uncertainties in the absolute and relative positioning of code fragments when updating the abstract cache state during the analysis. We demonstrate the effectiveness of our approach in an in-depth evaluation and provide an overview of the impact of different diversity techniques on the WCET estimations