Graphical User Interface (GUI) is unavoidable in modern software apps. It facilitates the interactions between the users and the apps. As shown on the Google play store, some apps with higher downloads often have higher-quality, well-designed and tested GUI. GUI testing has become a necessary step in the app development process, and related research become a hot spot in recent years. However, there isn’t a review about GUI testing of mobile apps, which brings obstacles to new researchers. In this paper, we systematically review publications between 2010 and 2020, to gain an insight into GUI testing for mobile apps. Even though the earliest research was published around 1997 but we believe the considered years are likely to include the advances in the field. Specifically, the paper aims to identify (i) the main objectives of GUI testing, (ii) the approaches applied (iii) the evaluation metrics (iv) the challenges and future research directions. To cover all relevant literature, following a predefined systematic literature review procedure, involving both the automatic and manual search strategies, we found 75 primary studies. Four research questions are proposed to analyze them. We found that functionality is the main objective of GUI testing. Model-based testing is the most common approach. Metrics such as error detection, execution time, and code coverage are often used to evaluate the performance of GUI testing techniques. Finally, we outline some key challenges as well as possible research directions. We believe our work would provide a clue for new researchers as well as more research in GUI testing.