Re: USB autosuspend causing trouble with bluetooth

[Kirill Elagin]

I just realised I had an old USB BT-dongle so I tried it, and the
trackpad was working fine with `auto` in `power/control`, so, yes,
sounds like the builtin BT adapter is faulty.

But here is a strange thing again: as with the keyboard I had to set
`power/control` of the hub to `on` in order for the kernel to detect
the dongle _and_ I also had to switch `power/control` of the dongle
from `auto` to `on` in order for the kernel to notice that the dongle
was plugged out. Weird.


On Tue, Jan 20, 2015 at 3:18 PM, Kirill Elagin <kirelagin@xxxxxxxxx> wrote:
> I use a Logitech wireless keyboard (with a Unifying receiver) and it
> keeps working fine even with `auto`.
>
> That is, everything is OK if the receiver is plugged before
> `power/control` is switched to `auto`.
> But if I first set it to `auto`, then plug the receiver in, it is not
> detected (nothing in dmesg). Kernel
> detects it as soon as I `echo on` to the relevant `power/control`.
>
> This laptop is too old to have USB3.0, both the receiver and BT are
> attached to USB1.1 ports.
> BTW I also noticed a strange thing: USB devices appear on different
> buses when attached,
> depending on their speed (e.g. the keyboard receiver is on bus 6 which
> is USB1.1, while a
> USB stick appears on bus 2 which is USB2.0 when I plug it into that
> same physical port).
> Iâm not sure whether this is strange or normal, as I never really
> payed attention.
>
>
> On Tue Jan 20 2015 at 2:03:45 PM Oliver Neukum <oneukum@xxxxxxx> wrote:
>>
>> On Sun, 2015-01-18 at 17:30 +0400, Kirill Elagin wrote:
>> > Hello,
>> >
>> > Recently I started having issues with my Apple Magic Trackpad and I
>> > realised that the problem was with autosuspend. Whenever I have `auto`
>> > in `power/control` of my BT adapter, `btmon` shows no packets,
>> > nothing. As soon as I `echo on`, all the missing packets arrive.
>>
>> You are not getting remote wakeups. There are two possibilities
>>
>> 1. the firmware of your BT adapter is faulty and the device needs to
>> be added to the list of quirky devices
>>
>> 2. a bug in the kernel breaks remote wakeup.
>>
>> We need to distinguish these cases. Could you connect another device
>> that uses remote wakeup (HID, CDC-ACM, ... - a keyboard or a mouse is
>> easiest) to a port connected to XHCI and test autosuspend on that
>> device?
>>
>>         Regards
>>                 Oliver
>>
>>
>>
>>
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/