We consider the problem of phase retrieval that consists in recovering an n-dimensional real vector from the magnitude of its m-linear measurements. This paper presents a new approach allowing to lift the classical global Lipschitz continuity requirement on the gradient of the non-convex objective to minimize. We propose a mirror descent algorithm based on a wisely chosen Bregman divergence. We show that when the number of measurements m is large enough, the mirror descent algorithm, carefully initialized, converges linearly with a dimension-independent convergence rate. Consequently, the original signal can be reconstructed exactly up to a global sign change. We state our results for two types of measurements: iid standard Gaussian and those obtained by Coded Diffraction Patterns (CDP) for Randomized Fourier Transform.