Re: Device failing to enumerate with EHCI

On Fri, 23 Mar 2007, Oliver Neukum wrote:

> Hi,
> 
> I got a bug report about a device failing if EHCI is loaded shortly
> after OHCI had been loaded. The device stalls. This seems to violate
> the spec. Is there a reason not to clear the halt?
> 
> 	Regards
> 		Oliver
> 
> usb 2-6.1.4: khubd timed out on ep0in len=0/255
> usb 2-6.1.4: string descriptor 0 read error: -32
> usb 2-6.1.4: new device found, idVendor=0430, idProduct=00a2
> usb 2-6.1.4: new device strings: Mfr=0, Product=1, SerialNumber=0
> usb 2-6.1.4: uevent
> usb 2-6.1.4: device is bus-powered
> usb 2-6.1.4: configuration #1 chosen from 1 choice
> usb 2-6.1.4: can't set config #1, error -32

Looks like the device isn't working too well: a timeout and two STALLs.  
Maybe it doesn't like to be reset while it's in the middle of enumerating, 
which is what typically happens when ehci-hcd is loaded shortly after the 
other HCDs.  (That's why we always recommend loading ehci-hcd first.)

Stalling endpoint 0 isn't against the spec.  It's the proper way for a
device to respond to a request that it doesn't support.

We don't clear the halt because the host is never supposed to clear halts
on ep0.  If the halt is a "protocol stall" (the normal case) then the
device will clear it automatically when it receives the next SETUP packet.  
If the halt is a "functional stall" (discouraged by the USB spec) there
is no way to clear it -- the Clear-Halt request won't get through because
ep0 is halted!

Alan Stern


-------------------------------------------------------------------------
Take Surveys. Earn Cash. Influence the Future of IT
Join SourceForge.net's Techsay panel and you'll get the chance to share your
opinions on IT & business topics through brief surveys-and earn cash
http://www.techsay.com/default.php?page=join.php&p=sourceforge&CID=DEVDEV
_______________________________________________
[email protected]
To unsubscribe, use the last form field at:
https://lists.sourceforge.net/lists/listinfo/linux-usb-devel