On 18-5-2017 11:22, Johannes Berg wrote: > On Thu, 2017-05-18 at 10:18 +0200, Arend Van Spriel wrote: >> >>> We should therefore probably set the expectation that wpa_s - if >>> it's new enough - always uses the offloaded functionality and >>> always sets the WANT_1X. Then this is even better with such >>> drivers, since they can immediately reject the connect() command if >>> want_1x isn't set. Getting back at this. With "always" you mean for every connect() regardless whether it is using 1X or PSK? >> Personally I am fine with this and it is how I tested it. So no >> network configuration or driver parameter in wpa_s.conf (mainly >> because I am lazy ;-) ). However, if the driver supports both offload >> and non-offload why not leave it up to user-space. Might be useful if >> people can try either way for example when debugging connection >> issues. > > If that should be possible though, then we'd probably want to have > feature bit both ways, otherwise we'll probably get hard-to-debug > failures at some point with this? You mean adding a nl80211 command in which user-space can indicate what features it supports? Do you want to use the same feature bits on both sides to easily determine the combined feature set? ext_feature does not really have much overlapping so not sure if it adds value. Regards, Arend
