Real-world data tends to follow a long-tailed distribution, which greatly challenges the robustness of algorithms. Current long-tailed learning methods usually focus on devising exquisite re-sampling strategies or innovative loss functions to address the class-wise imbalance, yet rarely pay attention to the pervasive problem of attribute imbalance within classes. That is to say, attribute imbalance naturally exists in class imbalance, which brings more complex challenges to current long-tailed learning. In this work, we propose an attribute rebalancing strategy to address imbalance in imbalance. First, we propose attribute-balanced re-sampling, which potentially re-samples the attributes within the class during up/down-sampling to avoid damage to rare attributes. Then, we design an attribute-constrained loss to trade off the intertwined imbalances in class and attribute levels. Comprehensive experiments show that attribute rebalancing can consistently perform well on generalized long-tailed benchmark datasets.