Charles Explorer logo
🇬🇧

Endicheck: Dynamic Analysis for Detecting Endianness Bugs

Publication at Faculty of Mathematics and Physics |
2020

Abstract

Computers store numbers in two mutually incompatible ways: little-endian or big-endian. They differ in the order of bytes within representation of numbers.

This ordering is called endianness. When two computer systems, programs or devices communicate, they must agree on which endianness to use, in order to avoid misinterpretation of numeric data values.

We present Endicheck, a dynamic analysis tool for detecting endianness bugs, which is based on the popular Valgrind framework. It helps developers to find those code locations in their program where they forgot to swap bytes properly.

Endicheck requires less source code annotations than existing tools, such as Sparse used by Linux kernel developers, and it can also detect potential bugs that would only manifest if the given program was run on computer with an opposite endianness. Our approach has been evaluated and validated on the Radeon SI Linux OpenGL driver, which is known to contain endianness-related bugs, and on several open-source programs.

Results of experiments show that Endicheck can successfully identify many endianness-related bugs and provide useful diagnostic messages together with the source code locations of respective bugs.