linux-dev/drivers/input/tablet/wacom_wac.c, branch linus/master

Input: wacom - move the USB (now hid) Wacom driver in drivers/hid

2014-07-26T01:55:38Z

wacom.ko is now a full HID driver, we have to move it into the proper subdirectory: drivers/hid. Signed-off-by: Benjamin Tissoires Signed-off-by: Dmitry Torokhov

Input: wacom - keep wacom_ids ordered

2014-07-26T01:53:56Z

No Functional changes, just some reordering. Signed-off-by: Benjamin Tissoires Reviewed-by: Jason Gerecke Tested-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - remove field pktlen declaration in the list of devices

2014-07-26T01:53:56Z

pktlen is now overwritten by the driver directly by reading the hid report descriptor. There is no need to declare it statically. We also move down the position of the field in the struct so that we can keep the current declaration of Wacom devices. Signed-off-by: Benjamin Tissoires Reviewed-by: Jason Gerecke Tested-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - switch from an USB driver to a HID driver

2014-07-26T01:53:50Z

All USB Wacom tablets are actually HID devices. For historical reasons, they are handled as plain USB devices. The current code makes more and more reference to the HID subsystem like implementing its own HID report descriptor parser to handle new devices. From the user point of view, we can transparently switch from this state to a driver handled in the HID subsystem and clean up a lot of USB specific code in the wacom.ko driver. The other benefit once the USB dependecies have been removed is that we can use a tool like uhid to make regression tests and allow further cleanup or new implementations without risking breaking current behaviors. To match the current handling of devices in wacom_wac.c, we rely on the hid_type set by usbhid. usbhid sets the hid_type to HID_TYPE_USBMOUSE when it sees a USB boot mouse protocol declared and HID_TYPE_USBNONE when the device is plain HID. There is thus a one to one matching between the list of supported devices before and after the switch from USB to HID. Signed-off-by: Benjamin Tissoires Reviewed-by: Jason Gerecke Tested-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - split out the pad device for Graphire G4 and MO

2014-07-26T01:53:48Z

MSC_SERIAL can be safely removed from pad devices. If it is not here, xf86-input-wacom correctly generates ones for its internal use. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Reviewed-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - split out the pad device for DTUS

2014-07-26T01:53:48Z

MSC_SERIAL can be safely removed from the pad device. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Reviewed-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - split out the pad device for Bamboos

2014-07-26T01:53:47Z

We rely on the return code of wacom_bpt*() to do the input_sync(). wacom_wac_irq() then properly sync the input devices. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Reviewed-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - split out the pad device for Intuos/Cintiq

2014-07-26T01:53:47Z

MSC_SERIAL can be safely dropped for pad input devices. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Reviewed-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - create a separate input device for pads

2014-07-26T01:53:46Z

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. 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. Signed-off-by: Benjamin Tissoires Reviewed-by: Ping Cheng Reviewed-by: Jason Gerecke Signed-off-by: Dmitry Torokhov

Input: wacom - process outbound for newer Cintiqs

2014-05-29T07:09:16Z

New Cintiq tablets have a 200 tablet counts outside of screen area. Add x/y_min for ABS_X/Y to pass this information to userland. Signed-off-by: Ping Cheng Reviewed-by: Jason Gerecke Tested-by: Jason Gerecke Signed-off-by: Dmitry Torokhov