Extra-long underwater tunnels are important traffic nodes in urban road networks and have a high incidence of traffic accidents. The frequent occurrence of curve and longitudinal slope combinations in such tunnels increases crash risk and has a negative impact on traffic safety. Vision is the most important way to obtain traffic information, and visual load is a good measure of driving risk. To explore the impact of curve and longitudinal slope combinations on a driver’s visual load in an extra-long underwater tunnel, eye-movement data and speed data were obtained through a vehicle experiment. Based on driver gaze distribution, the area and location of the visual sensitive region are calculated, and a model of the relationship between the region’s stability and the curve and longitudinal slope at different speeds is established, and applied to the visual-load evaluation. The results show that the curve or longitudinal slope has a significant influence on vehicle speed. High-visual-load areas are mainly located in small-radius curve and large longitudinal slope combination areas and extremely small-radius curve areas. For example, for a combination of left-turn curve and longitudinal slope with a speed of 50–60 km/h, when the curve radius is less than 1150 m and the longitudinal slope is less than −2.4%, or the curve radius is less than 1100 m and the longitudinal slope is greater than 2.2%, the visual load is high and driving safety is poor. This study can provide a theoretical basis for tunnel alignment design and safe operation.