I believe this commit (upstream commit b3f20e098293892388d6a0491d6bbb2efb46fbff) introduced a regression that causes the driver to fail to initialize for Intel 3168 devices. A patch for the regression has been submitted to the linux-wireless mailing list here: https://patchwork.kernel.org/patch/11353871/ I would suggest either not including b3f20e0982 in the next v5.4.x stable release, or also applying the above patch, to avoid introducing a regression for users of the v5.4 series. The above patch is also needs inclusion in the v5.5.x series, as the regression is already present there. Cheers, -- Dan
