Re: [PATCH] platform: hp_accel: add a i8042 filter to remove HPQ6000 data from kb bus stream

[Dmitry Torokhov <dmitry.torokhov@gmail.com>]

On Wed, Oct 29, 2014 at 06:40:56PM -0700, Darren Hart wrote:
> On Wed, Oct 29, 2014 at 09:16:22PM +0200, Giedrius Statkevicius wrote:
> > Add a i8042 filter to hp_accel to remove accelerometer's data with acpi
> > id HPQ6000 from keyboard bus stream. The codes sent by accelerometer are
> > e0 25, e0 26, e0 27 and e0 28. The relevant information is already
> > passed through /dev/freefall so no need to send these undocumented weird
> > signals through the keyboard bus. Also, unclogs `dmesg` because atkbd
> > complained about weird scan codes, saves processing power and disk
> > space.
> > 
> > Signed-off-by: Giedrius Statkevičius <giedriuswork@gmail.com>
> > ---
> > First of all, any Tested-Bys are very welcome by people who also have a
> > accelerometer with acpi id HPQ6000. If it happens with HPQ6007 too we
> > can easily modify this to install the filter when HPQ6007 is detected.
> > For the time being the filter is only installed when HPQ6000 is
> > detected. 
> > 
> > Now moving to what was changed since the RFC. I reworked the filter
> > function to hopefully make it more clear what it is doing. Since the
> > codes sent by the accelerometer are extended then we need to filter all
> > of 0xe0's and then send one 0xe0 back when the actual key isn't in the
> > range of 0x25-0x28. Also, I've removed the check for errors for
> > i8042_install_filter() because it's unnecessary to check if it failed.
> > If multiple HPQ6000's are in the system then no issue occurs even if
> > multiple i8042_install_filter() are issued because this is handled by
> > i8042 and it's smart enough not to install the same filter two or more
> > times.
> > 
> >  drivers/platform/x86/hp_accel.c | 45 ++++++++++++++++++++++++++++++++++++++++-
> >  1 file changed, 44 insertions(+), 1 deletion(-)
> > 
> > diff --git a/drivers/platform/x86/hp_accel.c b/drivers/platform/x86/hp_accel.c
> > index 13e14ec..a751621 100644
> > --- a/drivers/platform/x86/hp_accel.c
> > +++ b/drivers/platform/x86/hp_accel.c
> > @@ -38,6 +38,8 @@
> >  #include <linux/atomic.h>
> >  #include <linux/acpi.h>
> >  #include "../../misc/lis3lv02d/lis3lv02d.h"
> > +#include <linux/i8042.h>
> > +#include <linux/serio.h>
> 
> Please include before the relative path includes.
> 
> Otherwise, I'm happy with this - but I'd like a serio / i8042 person to weigh
> in.... Dmitry?

Yes, this is fine. Such uses with platform injecting weird bits into
keyboard/mouse data stream was the reason for introducing i8042 filter
facility.

I ma not sure what is more efficient, a case with 5 branches or
strchr(), but regardless:

Acked-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>

Thanks.

-- 
Dmitry