Re:Re:Re: [PATCH] net: usb: qmi_wwan: Add support for Cinterion MV32

[Slark Xiao]

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.