At 2022-08-10 17:28:51, "Slark Xiao" <slark_xiao@xxxxxxx> wrote: >At 2022-08-10 14:55:42, "Bjørn Mork" <bjorn@xxxxxxx> wrote: >>Slark Xiao <slark_xiao@xxxxxxx> writes: >> >>> There are 2 models for MV32 serials. MV32-W-A is designed >>> based on Qualcomm SDX62 chip, and MV32-W-B is designed based >>> on Qualcomm SDX65 chip. So we use 2 different PID to separate it. >>> >>> Test evidence as below: >>> T: Bus=03 Lev=01 Prnt=01 Port=02 Cnt=03 Dev#= 3 Spd=480 MxCh= 0 >>> D: Ver= 2.10 Cls=ef(misc ) Sub=02 Prot=01 MxPS=64 #Cfgs= 1 >>> P: Vendor=1e2d ProdID=00f3 Rev=05.04 >>> S: Manufacturer=Cinterion >>> S: Product=Cinterion PID 0x00F3 USB Mobile Broadband >>> S: SerialNumber=d7b4be8d >>> C: #Ifs= 4 Cfg#= 1 Atr=a0 MxPwr=500mA >>> I: If#=0x0 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=50 Driver=qmi_wwan >>> I: If#=0x1 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option >>> I: If#=0x2 Alt= 0 #EPs= 3 Cls=ff(vend.) Sub=ff Prot=40 Driver=option >>> I: If#=0x3 Alt= 0 #EPs= 2 Cls=ff(vend.) Sub=ff Prot=30 Driver=option >> >>The patch looks nice, but I have a couple of questions since you're one >>of the first pushing one of these SDX6x modems. >> >>Is that protocol pattern fixed on this generation of Qualcomm chips? It >>looks like an extension of what they started with the SDX55 generation, >>where the DIAG port was identified by ff/ff/30 across multiple vendors. >> > Seems yes. I checked some different usb_compositions and found that > diag port is using protocol '30' always. > >>Specifically wrt this driver and patch, I wonder if we can/should match >>on ff/ff/50 instead of interface number here? I note that the interface > >I checked all our edited usb_compositions and all QC default usb >compositions(9025, 90db, 9067,90d5,9084,9091,90ad,90b8,90e5), >ff/ff/50 is rmnet used only. > >>numbers are allocated sequentionally. Probably in the order these >>function are enabled by the firmware? If so, are we sure this is static? > >This needs more time to confirm. I will keep you updated. > >>Or could we risk config variants where the RMNET/QMI function have a >>different interface number for the same PIDs? >> >>And another possibility you might consider. Assuming that ff/ff/50 >>uniquely identifies RMNET/QMI functions regardless of PID, would you >>consider a VID+class match to catch all of them? This would not only >>support both the PIDs of this patch in one go, but also any future PIDs >>without the need for further driver patches. >> >> >>Bjørn > >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? >because they share a same VID. Also this may be changed once Qualcomm >update the protocol patterns for future chip.
