At 2022-08-10 20:35:24, "Bjørn Mork" <bjorn@xxxxxxx> wrote: >"Slark Xiao" <slark_xiao@xxxxxxx> writes: >> At 2022-08-10 17:28:51, "Slark Xiao" <slark_xiao@xxxxxxx> wrote: >> >>>I have a concern, if Cinterion or other Vendors, like Quectel, use other >>>chip (such as intel, mediateck and so on), this methods may won't work, >> >> My bad. QMI_WWAN driver is designed for Qualcomm based chips only, >> right? > >Yes, but your concern is still valid if any of them re-use ff/ff/50 for >something which is not RMNET/QMI. We do not want this driver to start >matching a non-Qualcomm based device. > >>>because they share a same VID. Also this may be changed once Qualcomm >>>update the protocol patterns for future chip. > >Yes, that' a risk since we have no knowledge of Qualcomm's plans or >thoughts around this. It's all pure guesswork from my side. But as >such, it doesn't differ from the rest of this driver :-) Qualcomm can >change whatever they want and we'll just have to follow up with whatever >is required. Like what happened when raw-ip became mandatory. > >I do find it unlikely that Qualcomm will ever change the meaning of this >pattern now that they've started using it. That would not make any >sense. If they need to create a new vendor specific function type, then >they can just use one of the "free" protocol numbers (and also subclass >if they run out of protocol numbers). > >But it's your call. If you want to play it safe and keep the VID+PID >matching, then I'm fine with that too. > > >Bjørn Then please help me apply it directly. There is no more commit request for MV32 serials if they don't update base line. Thanks.
