Hi Ping, On Jun 23 2014 or thereabouts, Ping Cheng wrote: > Hi Benjamin, > > On Mon, Jun 23, 2014 at 1:57 PM, Benjamin Tissoires > <benjamin.tissoires@xxxxxxxxxx> wrote: > > Currently, the pad events are sent through the stylus input device > > for the Intuos/Cintiqs, and through the touch input device for the > > Bamboos. > > > > To differentiate the buttons pressed on the pad from the ones pressed > > on the stylus, the Intuos/Cintiq uses MISC_SERIAL and ABS_MISC. This > > lead to a multiplexing of the events into one device, which are then > > splitted out in xf86-input-wacom. Bamboos are not using MISC events > > because the pad is attached to the touch interface, and only BTN_TOUCH > > is used for the finger (and DOUBLE_TAP, etc...). However, the user space > > driver still splits out the pad from the touch interface in the same > > way it does for the pro line devices. > > > > The other problem we can see with this fact is that some of the Intuos > > and Cintiq have a wheel, and the effective range of the reported values > > is [0..71]. Unfortunately, the airbrush stylus also sends wheel events > > (there is a small wheel on it), but in the range [0..1023]. From the user > > space point of view it is kind of difficult to understand that because > > the wheel on the pad are quite common, while the airbrush tool is not. > > > > A solution to fix all of these problems is to split out the pad device > > from the stylus/touch. This decision makes more sense because the pad is > > not linked to the absolute position of the finger or pen, and usually, the > > events from the pad are filtered out by the compositor, which then convert > > them into actions or keyboard shortcuts. > > This is a very good solution. I like it. > > > For backward compatibility with current xf86-input-wacom, the pad devices > > still present the ABS_X, ABS_Y and ABS_MISC events, but they can be > > completely ignored in the new implementation. > > I do not think we need to keep ABS_X and ABS_Y for pad. We've already > supported a tablet (Intuos pen small, a pen only tablet with buttons > reported on touch interface) that does not set ABS_X and ABS_Y for > pad. Hmm, actually, when I tried removing X and Y, xf86-input-wacom complained that max_x and max_y where set to 0, and it thus rejected the device. Maybe there is a special quirk in the xorg driver for the device you mentioned? Anyway, it's not a big deal, and when both xorg and libinput will know how to handle properly the pad device nodes, we can remove this. > > Unless you plan to use other means to tell userland those events are > from PAD tool, ABS_MISC is necessary and is a reasonable way to group Well, given that the pad now has its own input node, ABS_MISC could be dropped. We just need to teach the users that whichever event comes from this input device is a PAD event. > PAD events. So, I do not think it is for backward compatibility. It is > there to stay. With that said, the whole patchset is > > > Signed-off-by: Benjamin Tissoires <benjamin.tissoires@xxxxxxxxxx> > > Reviewed-by: Ping Cheng <pingc@xxxxxxxxx> > Thanks, that is greatly appreciated! > Thank you, Benjamin, for your support. > > Ping > Cheers, Benjamin -- To unsubscribe from this list: send the line "unsubscribe linux-input" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
