A cross-architectural interface for code cache manipulation

Software code caches help amortize the overhead of dy-namic binary transformation by enabling reuse of trans-formed code. Since code caches contain a potentially-altered copy of every instruction that executes, run-time access to a code cache can be a very powerful opportu-nity. Unfortunately, current research infrastructures lack the ability to model and direct code caching, and as a re-sult, past code cache investigations have required access to the source code of the binary transformation system. This paper presents a code cache-aware interface to the Pin dynamic instrumentation system. While a program exe-cutes, our interface allows a user to inspect the code cache, receive callbacks when key events occur, and manipulate the code cache contents at will. We demonstrate the util-ity of this interface on four architectures (IA32, EM64T, IPF, XScale) and present several tools written using our API. These tools include a self-modifying code handler, a two-phase instrumentation analyzer, a code cache visual-izer, and custom code cache replacement policies. We also show that tools written using our interface have comparable performance to direct, source-level implementations. Both our interface and sample open-source tools that utilize the interface have been incorporated into the standard distribu-tion of the Pin dynamic instrumentation engine, which has been downloaded over 5,000 times in 18 months. 1