Re: Linux 2.6.39.1

[Ed Tomlinson <edt@aei.ca>]

On Wednesday 08 June 2011 11:41:03 Jiri Kosina wrote:
> On Wed, 8 Jun 2011, Chase Douglas wrote:
> 
> > > I also played a bit with 1.1 CSR dongle and couldn't find any mask that would
> > > be accepted. I think this command can be left out for older than 1.2 devices.
> > > 
> > > Following patch should do it. Could you verify it. I don't have access to old
> > > hw ATM.
> > > 
> > > diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
> > > index 19cd4af..86d1e26 100644
> > > --- a/net/bluetooth/hci_event.c
> > > +++ b/net/bluetooth/hci_event.c
> > > @@ -477,14 +477,16 @@ static void hci_setup_event_mask(struct hci_dev *hdev)
> > >          * command otherwise */
> > >         u8 events[8] = { 0xff, 0xff, 0xfb, 0xff, 0x00, 0x00, 0x00, 0x00 };
> > >  
> > > -       /* Events for 1.2 and newer controllers */
> > > -       if (hdev->lmp_ver > 1) {
> > > -               events[4] |= 0x01; /* Flow Specification Complete */
> > > -               events[4] |= 0x02; /* Inquiry Result with RSSI */
> > > -               events[4] |= 0x04; /* Read Remote Extended Features Complete */
> > > -               events[5] |= 0x08; /* Synchronous Connection Complete */
> > > -               events[5] |= 0x10; /* Synchronous Connection Changed */
> > > -       }
> > > +       /* CSR 1.1 dongles does not accept any bitfield so don't try to set
> > > +        * any event mask for pre 1.2 devices */
> > > +       if (hdev->lmp_ver <= 1)
> > > +               return;
> > > +
> > > +       events[4] |= 0x01; /* Flow Specification Complete */
> > > +       events[4] |= 0x02; /* Inquiry Result with RSSI */
> > > +       events[4] |= 0x04; /* Read Remote Extended Features Complete */
> > > +       events[5] |= 0x08; /* Synchronous Connection Complete */
> > > +       events[5] |= 0x10; /* Synchronous Connection Changed */
> > >  
> > >         if (hdev->features[3] & LMP_RSSI_INQ)
> > >                 events[4] |= 0x04; /* Inquiry Result with RSSI */
> > 
> > Where did this patch come from? I don't see it in Linus' tree. If this
> > patch is merged, I can test the a new kernel out to see if we should
> > back out the commit from Jiri. However, right now my magic trackpad
> > (which has the same issue as the magic mouse) works fine on plain 2.6.39.1.
> 
> It might be because of different versions of CSR dongles you guys might 
> have.
> 
> I am still a bit lost here -- Ed, do you say that with the patch above, 
> and with my patch reverted, your device is working properly?

Yes.  Your understanding is correct.

Thanks,
Ed