Intelligent diagnostic methods based on deep learning have proven to be effective in equipment management and maintenance. However, in practical industrial applications in which data is scarce and equipment, load, and operating conditions are variable, the performance of well-trained laboratory models degrades significantly. To this end, this study proposes a domain adaptation meta-learning network with feature-oriented discard-supplement module (FD-DAML) for few-shot cross-domain rotating machinery fault diagnosis. This method addresses the diagnosis issues of severe domain distribution discrepancy, label space mismatch, and scarcity of labeled samples in the target domain within a unified framework. Specifically, the proposed method attempts a training mode that alternates the execution of the source and target domains meta-learning, and combines it with domain adversarial training. Such a training mode not only contributes to the accumulation of domain-invariant meta-knowledge from the source domain for the model, but also effectively learns the discriminative model for the target domain and achieves good generalization over it. Moreover, a plug-and-play feature-oriented discard-supplement module is designed to perform discard and supplement operations on extracted features against the context, to improve the generalization of the model. Extensive comparative experiments on public datasets, experimental datasets, and actual wind turbine datasets validate the effectiveness of the proposed FD-DAML and the feasibility of engineering diagnostics. The code will be published at https://github.com/zhangyu-ysu/FD-DAML.