Dealing with missing values is an important issue in data observation or data recording process. In this paper, we consider a functional linear regression model, where some observations of the real response and the functional covariate are affected by missing data. We use a reconstruction operator that aims to recover the missing parts of the explanatory curves, then we are interested in regression imputation method of missing data on the response variable, using functional principal component regression to estimate the functional coefficient of the model. We study the asymptotic behavior of the prediction error we commit when missing data are replaced by the imputed values in the original dataset. The practical behavior of the method is also studied on simulated data and a real dataset.