Re: Linux 2.6.39.1

[Chase Douglas <chase.douglas@canonical.com>]

On 06/06/2011 04:26 PM, Ed Tomlinson wrote:
> On Monday 06 June 2011 14:47:34 Chase Douglas wrote:
>> On 06/03/2011 07:36 PM, Ed Tomlinson wrote:
>>> On Thursday 02 June 2011 20:38:35 you wrote:
>>>> I'm announcing the release of the 2.6.39.1 kernel.
>>>>
>>>> All users of the 2.6.39 kernel series must upgrade.
>>>>
>>>> The updated 2.6.39.y git tree can be found at:
>>>>         git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-2.6.39.y.git
>>>> and can be browsed at the normal kernel.org git web browser:
>>>>         http://git.kernel.org/?p=linux/kernel/git/stable/linux-2.6.39.y.git;a=summary
>>>>
>>>
>>> Greg,
>>>
>>> Just updated to 39.1 and it breaks my magicmouse
>>>
>>> [  107.360715] input: Apple Wireless Mouse as /devices/pci0000:00/0000:00:13.2/usb2/2-4/2-4.4/2-4.4:1.0/bluetooth/hci0/hci0:21/input8
>>> [  107.376797] magicmouse 0005:05AC:030D.0005: input,hidraw3: BLUETOOTH HID v0.84 Mouse [Apple Wireless Mouse] on 00:02:72:20:20:1D
>>> [  107.423387] magicmouse 0005:05AC:030D.0005: unable to request touch data (2)
>>> [  107.451216] magicmouse: probe of 0005:05AC:030D.0005 failed with error 2
>>>
>>> and the magicmouse is dead.
>>>
>>> reverting 23746a66d7d9e73402c68ef00d708796b97ebd72
>>>
>>> makes it work as before.
>>
>> Hi Ed,
>>>
>> Thanks!
>>
>> -- Chase
>>
>>
>> We pushed this commit to fix the regression you reported where the mouse
>> failed to work in 2.6.39. With the commit, the mouse should be working
>> properly.
> 
> Chase,
> 
> The patch that fixed .39 here was
> 
> (From: Ville Tervo <ville.tervo@nokia.com>)
> 
> 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.

-- Chase