Simultaneous Multithreading (SMT) architectures are attractive targets for side-channel enabled attackers, with their inherently broader attack surface that exposes more per physical core microarchitecture components than cross-core attacks. In this work, we explore SMT execution engine sharing as a side-channel leakage source. We target ports to stacks of execution units to create a high-resolution timing side-channel due to port contention, inherently stealthy since it does not depend on the memory subsystem like other cache or TLB based attacks. Implementing our channel on Intel Skylake and Kaby Lake architectures featuring Hyper-Threading, we mount an end-to-end attack that recovers a P-384 private key from an OpenSSL-powered TLS server using a small number of repeated TLS handshake attempts. Furthermore, we show that traces targeting shared libraries, static builds, and SGX enclaves are essentially identical, hence our channel has wide target application.
SM2 is a public key cryptography suite originating from Chinese standards, including digital signatures and public key encryption. Ahead of schedule, code for this functionality was recently mainlined in OpenSSL, marked for the upcoming 1.1.1 release. We perform a security review of this implementation, uncovering various deficiencies ranging from traditional software quality issues to side-channel risks. To assess the latter, we carry out a side-channel security evaluation and discover that the implementation hits every pitfall seen for OpenSSL's ECDSA code in the past decade. We carry out remote timings, cache timings, and EM analysis, with accompanying empirical data to demonstrate secret information leakage during execution of both digital signature generation and public key decryption. Finally, we propose, implement, and empirically evaluate countermeasures.
Software ever-increasingly relies on building blocks implemented by security libraries, which provide access to evolving standards, protocols, and cryptographic primitives. These libraries are often subject to complex development models and long decision-making processes, which limit the ability of contributors to participate in the development process, hinder the deployment of scientific results and pose challenges for OS maintainers. In this paper, focusing on OpenSSL as a de-facto standard, we analyze these limits, their impact on the security of modern systems, and their significance for researchers. We propose the OpenSSL ENGINE API as a tool in a framework to overcome these limits, describing how it fits in the OpenSSL architecture, its features, and a technical review of its internals. We evaluate our methodology by instantiating libsuola, a new ENGINE providing support for emerging cryptographic standards such as X25519 and Ed25519 for currently deployed versions of OpenSSL, performing benchmarks to demonstrate the viability and benefits. The results confirm that the ENGINE API offers (1) an ideal architecture to address wide-ranging security concerns; (2) a valuable tool to enhance future research by easing testing and facilitating the dissemination of novel results in real-world systems; and (3) a means to bridge the gaps between research results and currently deployed systems.