2021-11-05 16:19:54

by Greg Kroah-Hartman

Subject: Re: [PATCH] xhci: Fix USB 3.1 enumeration issues by increasing roothub power-on-good delay

On Fri, Nov 05, 2021 at 06:00:36PM +0200, Mathias Nyman wrote:
> Some USB 3.1 enumeration issues were reported after the hub driver removed
> the minimum 100ms limit for the power-on-good delay.
>
> Since commit 90d28fb53d4a ("usb: core: reduce power-on-good delay time of
> root hub") the hub driver sets the power-on-delay based on the
> bPwrOn2PwrGood value in the hub descriptor.
>
> xhci driver has a 20ms bPwrOn2PwrGood value for both roothubs based
> on xhci spec section 5.4.8, but it's clearly not enough for the
> USB 3.1 devices, causing enumeration issues.
>
> Tests indicate full 100ms delay is needed.
>
> Reported-by: Walt Jr. Brake <[email protected]>
> Signed-off-by: Mathias Nyman <[email protected]>

So this needs:
Fixes: 90d28fb53d4a ("usb: core: reduce power-on-good delay time of root hub")
right?

thanks,

greg k-h

2021-11-05 23:05:53

by Mathias Nyman

Subject: Re: [PATCH] xhci: Fix USB 3.1 enumeration issues by increasing roothub power-on-good delay

On 5.11.2021 18.15, Greg KH wrote:
> On Fri, Nov 05, 2021 at 06:00:36PM +0200, Mathias Nyman wrote:
>> Some USB 3.1 enumeration issues were reported after the hub driver removed
>> the minimum 100ms limit for the power-on-good delay.
>>
>> Since commit 90d28fb53d4a ("usb: core: reduce power-on-good delay time of
>> root hub") the hub driver sets the power-on-delay based on the
>> bPwrOn2PwrGood value in the hub descriptor.
>>
>> xhci driver has a 20ms bPwrOn2PwrGood value for both roothubs based
>> on xhci spec section 5.4.8, but it's clearly not enough for the
>> USB 3.1 devices, causing enumeration issues.
>>
>> Tests indicate full 100ms delay is needed.
>>
>> Reported-by: Walt Jr. Brake <[email protected]>
>> Signed-off-by: Mathias Nyman <[email protected]>
>
> So this needs:
> Fixes: 90d28fb53d4a ("usb: core: reduce power-on-good delay time of root hub")
> right?

I guess so, not sure on "Fixes" policy here.

This patch fixes an xhci issue revealed by ("usb: core: reduce power-on-good delay time of root hub")
That original patch itself looks correct, but these two patches should really go together to
avoid any enumeration issues.

Thanks
-Mathias

2021-11-06 21:34:54

by Greg Kroah-Hartman

Subject: Re: [PATCH] xhci: Fix USB 3.1 enumeration issues by increasing roothub power-on-good delay

On Fri, Nov 05, 2021 at 09:56:59PM +0200, Mathias Nyman wrote:
> On 5.11.2021 18.15, Greg KH wrote:
> > On Fri, Nov 05, 2021 at 06:00:36PM +0200, Mathias Nyman wrote:
> >> Some USB 3.1 enumeration issues were reported after the hub driver removed
> >> the minimum 100ms limit for the power-on-good delay.
> >>
> >> Since commit 90d28fb53d4a ("usb: core: reduce power-on-good delay time of
> >> root hub") the hub driver sets the power-on-delay based on the
> >> bPwrOn2PwrGood value in the hub descriptor.
> >>
> >> xhci driver has a 20ms bPwrOn2PwrGood value for both roothubs based
> >> on xhci spec section 5.4.8, but it's clearly not enough for the
> >> USB 3.1 devices, causing enumeration issues.
> >>
> >> Tests indicate full 100ms delay is needed.
> >>
> >> Reported-by: Walt Jr. Brake <[email protected]>
> >> Signed-off-by: Mathias Nyman <[email protected]>
> >
> > So this needs:
> > Fixes: 90d28fb53d4a ("usb: core: reduce power-on-good delay time of root hub")
> > right?
>
> I guess so, not sure on "Fixes" policy here.
>
> This patch fixes an xhci issue revealed by ("usb: core: reduce power-on-good delay time of root hub")
> That original patch itself looks correct, but these two patches should really go together to
> avoid any enumeration issues.

Great, I'll use that tag for now so that it will get backported
properly.

greg k-h