Jiří Barnat

In this paper, we introduce an interactive simulator for programs in the form of LLVM bitcode. The main features of the simulator include precise control over thread scheduling, automatic checkpoints and reverse stepping, support for source-level information about functions and variables in C and C++ programs and structured heap visualisation. Additionally, the simulator is compatible with DiVM (DIVINE VM) hypercalls, which makes it possible to load, simulate and analyse counterexamples from an existing model checker.

Symbolic computation is an important approach in automated program analysis. Most state-of-the-art tools perform symbolic computation as interpreters and directly maintain symbolic data. In this paper, we show that it is feasible, and in fact practical, to use a compiler-based strategy instead. Using compiler tooling, we propose and implement a transformation which takes a standard program and outputs a program that performs semantically equivalent, but partially symbolic, computation. The transformed program maintains symbolic values internally and operates directly on them hence the program can be processed by a tool without support for symbolic manipulation. The main motivation for the transformation is in symbolic verification, but there are many other possible use-cases, including test generation and concolic testing. Moreover using the transformation simplifies tools, since the symbolic computation is handled by the program directly. We have implemented the transformation at the level of LLVM bitcode. The paper includes an experimental evaluation, based on an explicit-state software model checker as a verification backend.

An important step toward adoption of formal methods in software development is support for mainstream programming languages. Unfortunately, these languages are often rather complex and come with substantial standard libraries. However, by choosing a suitable intermediate language, most of the complexity can be delegated to existing execution-oriented (as opposed to verification-oriented) compiler frontends and standard library implementations. In this paper, we describe how support for C++ exceptions can take advantage of the same principle. Our work is based on DiVM, an LLVM-derived, verification-friendly intermediate language. Our implementation consists of 2 parts: an implementation of the `libunwind` platform API which is linked to the program under test and consists of 9 C functions. The other part is a preprocessor for LLVM bitcode which prepares exception-related metadata and replaces associated special-purpose LLVM instructions.

We describe a novel approach for adapting an existing software model checker to perform precise runtime verification. The software under test is allowed to communicate with the wider environment (including the file system and network). The modifications to the model checker are small and self-contained, making this a viable strategy for re-using existing model checking tools in a new context. Additionally, from the data that is gathered during a single execution in the runtime verification mode, we automatically re-construct a description of the execution environment which can then be used in the standard, full-blown model checker. This additional verification step can further improve coverage, especially in the case of parallel programs, without introducing substantial overhead into the process of runtime verification.

In this paper, we introduce the concept of a virtual machine with graph-organised memory as a versatile backend for both explicit-state and abstraction-driven verification of software. Our virtual machine uses the LLVM IR as its instruction set, enriched with a small set of hypercalls. We show that the provided hypercalls are sufficient to implement a small operating system, which can then be linked with applications to provide a POSIX-compatible verification environment. Finally, we demonstrate the viability of the approach through a comparison with a more traditionally-designed LLVM model checker.

In various areas of computer science, the problem of dealing with a set of constraints arises. If the set of constraints is unsatisfiable, one may ask for a minimal description of the reason for this unsatisifi- ability. Minimal unsatisifable subsets (MUSes) and maximal satisifiable subsets (MSSes) are two kinds of such minimal descriptions. The goal of this work is the enumeration of MUSes and MSSes for a given constraint system. As such full enumeration may be intractable in general, we focus on building an online algorithm, which produces MUSes/MSSes in an on-the-fly manner as soon as they are discovered. The problem has been studied before even in its online version. However, our algorithm uses a novel approach that is able to outperform current state-of-the art algorithms for online MUS/MSS enumeration. Moreover, the performance of our algorithm can be adjusted using tunable parameters. We evaluate the algorithm on a set of benchmarks.

In the last decade it became a common practice to formalise software requirements to improve the clarity of users’ expectations. In this work we build on the fact that functional requirements can be expressed in temporal logic and we propose new sanity checking techniques that automatically detect flaws and suggest improvements of given requirements. Specifically, we describe and experimentally evaluate approaches to consistency and redundancy checking that identify all inconsistencies and pinpoint their exact source (the smallest inconsistent set). We further report on the experience obtained from employing the consistency and redundancy checking in an industrial environment. To complete the sanity checking we also describe a semi-automatic completeness evaluation that can assess the coverage of user requirements and suggest missing properties the user might have wanted to formulate. The usefulness of our completeness evaluation is demonstrated in a case study of an aeroplane control system.