The Channel State Information (CSI) of the orthogonal frequency division multiplexing (OFDM) comprises data pertaining to the attenuation of multipath propagation. In this paper, we assume that the amplitude fading of both line-ofsight (LoS) and non-line-of-sight (NLoS) paths conforms to the Nakagami-m distribution. Via establishing a relationship between the distribution parameters and the propagation distance, we propose a CSI-based ranging method utilizing the Expectation Maximization (EM)-Revisited Approximate Message Passing (reVAMP) algorithm. This algorithm is not only applicable to the CSI-based ranging estimation but can also be extended to other parameter estimation scenarios. It effectively tackles challenges associated with generalized linear models (GLMs) that involve hidden random variables and the intractability of posterior distributions during the EM iterations.