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 <[email protected]>)
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 */
--
> Now you are reporting that the mouse fails to work with the commit, but
> does work without the commit. This is perplexing :). I'm also not sure
> what you mean by:
The bug referenced in the commit below is: https://bugzilla.kernel.org/show_bug.cgi?id=35022
which was not mine and does show up with the id below in my 39.1 tree...
> "reverting 23746a66d7d9e73402c68ef00d708796b97ebd72 makes it work as before"
Bottom line. I tested the correct kernels and the fix for 35022 breaks things here.
Thanks,
Ed
* Jiri Kosina <[email protected]> [2011-06-16 12:25:32 +0200]:
> On Mon, 13 Jun 2011, Gustavo F. Padovan wrote:
>
> > > > > 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.
> > > >
> > > > This patch is in my tree. It will be on its way to Linus' tree today.
> > >
> > > Doesn't seem to be present in Linus' tree as of today. Has there been any
> > > issue discovered in the meantime?
> >
> > No, it is on wireless-2.6 right now. Then goes to net-2.6 and finally linus-2.6.
>
> Still doesn't seem to be present in Linus' tree today.
>
> Could you please point me to where it is queued now? I am going to revert
> the "workaround" I have for magicmouse today (which is buggy), but I want
> to make sure that the actual fix (i.e. Villo's patch) flows in soon.
Yes, still on wireless-2.6 . :(
I'll check if I can make it go fast.
Gustavo
On Mon, 13 Jun 2011, Gustavo F. Padovan wrote:
> > > > 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.
> > >
> > > This patch is in my tree. It will be on its way to Linus' tree today.
> >
> > Doesn't seem to be present in Linus' tree as of today. Has there been any
> > issue discovered in the meantime?
>
> No, it is on wireless-2.6 right now. Then goes to net-2.6 and finally linus-2.6.
Still doesn't seem to be present in Linus' tree today.
Could you please point me to where it is queued now? I am going to revert
the "workaround" I have for magicmouse today (which is buggy), but I want
to make sure that the actual fix (i.e. Villo's patch) flows in soon.
Thanks,
--
Jiri Kosina
SUSE Labs
* Jiri Kosina <[email protected]> [2011-06-13 00:11:04 +0200]:
> On Wed, 8 Jun 2011, Gustavo F. Padovan wrote:
>
> > > > 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.
> >
> > This patch is in my tree. It will be on its way to Linus' tree today.
>
> Doesn't seem to be present in Linus' tree as of today. Has there been any
> issue discovered in the meantime?
No, it is on wireless-2.6 right now. Then goes to net-2.6 and finally linus-2.6.
Gustavo
On Wed, 8 Jun 2011, Gustavo F. Padovan wrote:
> > > 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.
>
> This patch is in my tree. It will be on its way to Linus' tree today.
Doesn't seem to be present in Linus' tree as of today. Has there been any
issue discovered in the meantime?
Thanks,
--
Jiri Kosina
SUSE Labs
On Thu, 9 Jun 2011, Ed Tomlinson 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 for confirming. I'll wait for Chase's confirmation that it works
for him as well (so that we could rule out hardware differencies playing
a role), and will then push revert to Linus.
Thanks,
--
Jiri Kosina
SUSE Labs
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
* Chase Douglas <[email protected]> [2011-06-08 08:36:37 -0700]:
> 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 <[email protected]>)
> >
> > 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.
This patch is in my tree. It will be on its way to Linus' tree today.
Gustavo
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?
Chase, could you please try the same on your side? Thanks,
--
Jiri Kosina
SUSE Labs
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 <[email protected]>)
>
> 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