Commit Graph

480699 Commits

Author SHA1 Message Date
Georgi Djakov 6096d7a8c1 mmc: sdhci-msm: Get COMPILE_TEST support
Increase the build testing coverage.

Signed-off-by: Georgi Djakov <gdjakov@mm-sol.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
2014-07-26 11:08:17 +02:00
Georgi Djakov d30f01b0e8 mmc: sdhci-msm: Remove unnecessary header file inclusion
The header <linux/regulator/consumer.h> is unused. Remove it.

Signed-off-by: Georgi Djakov <gdjakov@mm-sol.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
2014-07-26 11:08:11 +02:00
Georgi Djakov 602bcdeb9a mmc: sdhci-msm: Fix the binding example
The DT binding example in the documentation is missing the -supply
suffix for the vmmc and vqmmc regulators. Fix it.

Signed-off-by: Georgi Djakov <gdjakov@mm-sol.com>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
2014-07-26 11:08:01 +02:00
David Ertman 2a7e19af94 e1000e: Fix Runtime PM blocks EEE link negotiation in S5
Adding a function, and associated calls, to flush writes to (read) the LPIC
MAC register before entering the shutdown flow.  This fixes the problem
of the PHY never negotiating a 100M link (if both sides of the link support
EEE and 100M link) when Runtime PM is enabled.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 21:15:20 -07:00
David Ertman 2116bc25e8 e1000e: Fix EEE in S5 w/ Runtime PM enabled
The process of shutting down the system causes a call to the close PM
callback.  The reset in close causes a loss of link, and the resultant
LSC interrupt causes the Runtime PM idle callback to be called.  The
check for link (while link is down) in the idle callback is wiping the
information about the EEE ability of the link partner.  The information is
still gone when the PHY is powered back up in the shutdown flow.  This
causes EEE in S5 to fail when Runtime PM is active.

Save the link partner's EEE ability in the idle callback so that a Runtime
PM event will not cause a loss of this information.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 21:08:12 -07:00
David Ertman b4c1e6bf1c e1000e: Add support for EEE in Sx states
On I217 and newer hardware, EEE is enabled in the PHY by the software
when link is up and disabled by the hardware when link is lost.

To enable EEE in Sx (When both ends of the link support, and are enabled
for, EEE and 100Mbps), we need to disable LPLU and configure the PHY to
automatically enable EEE when link is up, since there will be no software
to complete the task.

To configure this in the PHY, the Auto Enable LPI bit in the Low Power
Idle GPIO Control register must be set.  For normal operation in S0, this
bit must be cleared.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 21:00:54 -07:00
James Harper 9e334c7564 [media] Fix regression in some dib0700 based devices
Fix regression in some dib0700 based devices.
Set size_of_priv, and don't call dvb_detach unnecessarily.
This resolves the oops(s) for my "Leadtek Winfast DTV Dongle (STK7700P based)"

Signed-off-by: James Harper <james.harper@ejbdigital.com.au>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-26 00:51:02 -03:00
David Ertman 491a04d281 e1000e: Add code to check return values on NVM accesses
Adding code to check and respond to previously ignored return values
from NVM access functions.

Issue discovered through static analysis.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 20:51:00 -07:00
David Ertman 493004d04f e1000e: Fix CRC errors with jumbo traffic
Modifying the jumbo frame workaround for 82579, i217 and i218 client parts
to increase the gap between the read and write pointers in the Tx FIFO.

Signed-off-by: Dave Ertman <david.m.ertman@intel.com>
Tested-by: Aaron Brown <aaron.f.brown@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 20:43:29 -07:00
Arnd Bergmann 64438fe65a [media] staging: lirc: remove sa1100 support
The LIRC support for sa1100 appears to have never worked
because it relies on header files that have never been
present in git history. Actually trying to build the
driver on an ARM sa1100 kernel fails, so let's just remove
the broken support.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Cc: Jarod Wilson <jarod@wilsonet.com>
Cc: Tuomas Tynkkynen <tuomas.tynkkynen@iki.fi>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-26 00:42:18 -03:00
Fabio Estevam 08c8d14e75 [media] coda: Propagate the correct error on devm_request_threaded_irq()
If devm_request_threaded_irq() fails, we should better propagate the real error.

Also, print out the error code in the dev_err message.

Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-26 00:38:27 -03:00
Fabio Estevam 7d37743a3e [media] coda: Return the real error on platform_get_irq()
No need to return a 'fake' return value on platform_get_irq() failure.

Propagate the real error instead.

Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Acked-by: Philipp Zabel <p.zabel@pengutronix.de>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-26 00:37:26 -03:00
George Spelvin 356237d67a [media] ati_remote: Better default keycodes
This tries to make them more like other remotes, and/or
the button labels.

Notably, the (>>) button is made KEY_FASTFORWARD, which is the
correct opposite of (<<)'s KEY_REVERSE.  (It was KEY_FORWARD,
something else entirely.)

Likewise, KEY_STOP is the Sun keyboard "interrupt program" key;
the media key is KEY_STOPCD.

A restriction is that I try to avoid keycodes above 255, as the X11
client/server protocol is limited to 8-bit key codes.  If not for
this, I would have used the KEY_NUMERIC_x codes for the numbers.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:59:06 -03:00
Mark Rustad e90dd26456 ixgbe: Make return values more direct
Make return values more direct, eliminating some gotos and
otherwise unneeded conditionals. This also eliminates some
local variables. Also a few minor cleanups in affected code
so checkpatch won't complain.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 19:58:36 -07:00
George Spelvin 220edfb0f7 [media] ati_remote: Add comments to keycode table
A more detailed description of what the buttons look like and
their intended function makes it easier for people to maintain
this code without access to the hardware.

[m.chehab@samsung.com: Fixed a typo "Mdeia" instead of "Media"]
Signed-off-by: George Spelvin <linux@horizon.com>

Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:54:32 -03:00
George Spelvin d701c8318b [media] ati_remote: Sort buttons in top-to-bottom order
Since numerical order corresponds to top-left-to-bottom-right
order on the remote, this makes the table easier to read.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:52:59 -03:00
George Spelvin 1e182708c2 [media] ati_remote: Use non-alomic __set_bit
There's no reason to use a LOCK prefix here.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:52:15 -03:00
George Spelvin 89b0c0d277 [media] ati_remote: Merge some duplicate code
The KIND_FILTERED assignment of old_jiffies can't be merged, because
it must precede repeat handling.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:51:51 -03:00
George Spelvin 3f245b9cb4 [media] ati_remote: Shrink the ati_remote_tbl even more
Get rid of the unnecessary "type" and "value" fields.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:50:58 -03:00
George Spelvin 8ecd5e32d8 [media] ati_remote: Generalize KIND_ACCEL to accept diagonals
Rather than having special code cases for diagonal mouse
movements, extend the general purpose code used for the
cardinal directions to handle arbitrary (x,y) deltas.

The deltas themselves are stored in translation table's "code"
field; this is also progress toward the goal of eliminating
the "value" element entirely.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:48:41 -03:00
George Spelvin f95589cc41 [media] ati_remote: Delete superfluous input_sync()
It's not necessary, and since both events happen "at the same time"
in response to a single input event, the input device framework prefers
not to have it there.

(It's not a big deal one way or the other, but deleting cruft
is generally a good thing.)

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:46:56 -03:00
George Spelvin 528abb9888 [media] ati_remote: Shrink ati_remote_tbl structure
The variable types are simply larger than they need to be.
Shrink to signed and unsigned chars.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:46:32 -03:00
George Spelvin 20d7e3ca1b [media] ati_remote: Check the checksum
An input report is 4 bytes long, but there are only 12 bits
of actual payload.  The 4 bytes are:
data[0] = 0x14
data[1] = data[2] + data[3] + 0xd5 (a checksum byte)
data[2] = the raw scancode (plus toggle bit in msbit)
data[3] = channel << 4 (the low 4 bits must be zero)

Ignore reports with a bad checksum.

Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:44:23 -03:00
Mark Rustad 9f1fb8acd3 ixgbevf: Remove unused get_supported_physical_layer pointer
Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 19:42:14 -07:00
Mauro Carvalho Chehab 7cec72ce00 [media] rc-core: don't use dynamic_pr_debug for IR_dprintk()
The hole point of IR_dprintk() is that, once a level is
given at debug parameter, all enabled IR parsers will show their
debug messages.

While converting it to dynamic_printk might be a good idea,
right now it just makes very hard to debug the drivers, as
one needs to both pass debug=1 or debug=2 to rc-core and
to use the dynamic printk to enable all the desired lines.

That doesn't make sense!

So, revert to the old way, as a single line is changed,
and the debug parameter will now work as expected.

Signed-off-by: Mauro Carvalho Chehab <m.chehab@samsung.com>
2014-07-25 23:40:06 -03:00
Mark Rustad f0ff353a86 ixgbe: Delete a bunch of dead code
All of the code involved with returning the supported physical
layer is actually unused, so delete it.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 19:35:13 -07:00
Mark Rustad 4e86281b59 ixgbe: Fix ixgbe_write_mbx error result
If ixgbe_write_mbx is called and no mbx->ops.write method
exists, no error code is returned. The corresponding read
function explicitly returns an error in such a case as do
other functions, so this appears to be a minor bug. Fix
it for consistency, and generate return values directly
to make things clearer.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 19:26:44 -07:00
Mark Rustad acb1ce223b ixgbe: Correct X540 semaphore error
In the function ixgbe_get_swfw_sync_semaphore, an incorrect
check was treating success as failure and vice-versa. This led
to manipulating the IXGBE_SWFW_SYNC register without holding
the software semaphore first, which is an error. In addition,
if getting the REGSMP bit in the IXGBE_SW_FW_SYNC register
timed out, no error code would be returned, making the caller
think that it had successfully acquired the lock. Fix both of
those issues and clean up the function a bit, such as make the
name in the comment match the function.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 19:01:28 -07:00
Pramod Gurav 91cf07cdae Input: soc_button_array - add missing memory allocation check
Signed-off-by: Pramod Gurav <pramod.gurav@smartplayin.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:58:41 -07:00
Benjamin Tissoires 7dbd229e10 Input: wacom - register an ac power supply for wireless devices
This is used by HID Bluetooth devices but also add some more information
to the USB Wireless Receiver.
We are just porting the bits from hid-wacom.c to the common driver here.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Acked-by: Przemo Firszt <przemo@firszt.eu>
Acked-by: Ping Cheng <pingc@wacom.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:55:54 -07:00
Benjamin Tissoires d70420b914 Input: wacom - use a uniq name for the battery device
The current implementation uses "wacom_battery" as a generic name for
batteries. This prevents us to have two Wacom devices with a battery
attached as the power system will complain about the name which is already
registered.

Use an incremental name for each battery attached.

Related bug:
https://sourceforge.net/p/linuxwacom/bugs/248/

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Acked-by: Przemo Firszt <przemo@firszt.eu>
Acked-by: Ping Cheng <pingc@wacom.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:55:53 -07:00
Benjamin Tissoires ac8d10101b Input: wacom - enhance Wireless Receiver battery reporting
- Reports the current status of the battery (discharging, charging, full).
- Also notify the upower daemon when there is a change in the battery
  value.
- keep the battery value as a percentage, not the raw value
- add WACOM_QUIRK_BATTERY to easily add a battery to a device (required
  for Bluetooth devices)

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Acked-by: Przemo Firszt <przemo@firszt.eu>
Acked-by: Ping Cheng <pingc@wacom.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:55:53 -07:00
Benjamin Tissoires c757cbafd6 Input: wacom - put a flag when the led are initialized
This solves a bug with the wireless receiver:
- at plug, the wireless receiver does not know which Wacom device it is
  connected to, so it does not actually creates all the LEDs
- when the tablet connects, wacom->wacom_wac.features.type is set to the
  proper device so that wacom_wac can understand the packets
- when the receiver is unplugged, it detects that a LED should have been
  created (based on wacom->wacom_wac.features.type) and tries to remove
  it: crash when removing the sysfs group.

Side effect, we can now safely call several times wacom_destroy_leds().

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Acked-by: Ping Cheng <pingc@wacom.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:55:52 -07:00
Jason Gerecke 0b335cad73 Input: wacom - support up to 2048 pressure levels with ISDv4
Signed-off-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:55:52 -07:00
Benjamin Tissoires 471d17148c Input: wacom - move the USB (now hid) Wacom driver in drivers/hid
wacom.ko is now a full HID driver, we have to move it into the proper
subdirectory: drivers/hid.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:55:38 -07:00
Mark Rustad e4856696b4 ixgbe: Fix spurious release of semaphore in EEPROM access
Failure to acquire the semaphore would lead to a spurious release
of the semaphore in several functions. Do not release a semaphore
that you did not get.

Signed-off-by: Mark Rustad <mark.d.rustad@intel.com>
Tested-by: Phil Schmitt <phillip.j.schmitt@intel.com>
Signed-off-by: Jeff Kirsher <jeffrey.t.kirsher@intel.com>
2014-07-25 18:54:09 -07:00
Benjamin Tissoires a3e6f6543d Input: wacom - keep wacom_ids ordered
No Functional changes, just some reordering.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:56 -07:00
Benjamin Tissoires 80befa9381 Input: wacom - remove field pktlen declaration in the list of devices
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 <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:56 -07:00
Benjamin Tissoires 198fdee282 Input: wacom - use hidinput_calc_abs_res instead of duplicating its code
This may infer a small difference with the previous implementation
due to the DIV_ROUND_CLOSEST() in the hid implementation.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:55 -07:00
Benjamin Tissoires c669fb2b9a Input: wacom - use in-kernel HID parser
HID already parses the report descriptor, so use it instead of implementing
our own.  The special case for Bamboo PT 3rd gen is also removed and
handled in the same way Intuos 5 is treated, by hardcoding it in the
driver.  Last, the unit_exponent stored into the hid field already is
signed, so there is no need to handle a two's complement anymore.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:55 -07:00
Benjamin Tissoires e2114ce1af Input: wacom - use hid_info instead of plain dev_info
Removes one more need of usb and intf.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:54 -07:00
Benjamin Tissoires dd3181a70c Input: wacom - register power device at the HID level
Use the HID device as the parent for the power device when dealing with
a wireless receiver.
Removes one more usb dependency and does not break user space.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:53 -07:00
Benjamin Tissoires 4451e088cf Input: wacom - remove usb dependency for siblings devices
Wacom tablets can share different physical sensors on one physical device.
These are called siblings in the code. The current way of implementation
relies on the USB topology to be able to share data amongs those sensors.

We can replace the code to match a HID subsystem, without involving the USB
topology:
- the first probed sensor does not find any siblings in the list
  wacom_udev_list, so it creates its own wacom_hdev_data with its own
  struct hid_device
- the other sensor checks the current list of siblings in wacom_hdev_data,
  and if there is a match, it associates itself to the matched device.

To be sure that we are not associating different sensors from different
physical devices, we also check for the phys path of the hid device which
contains the USB topology.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:53 -07:00
Benjamin Tissoires b6c79f2ca1 Input: wacom - register the input devices on top of the HID one
Matches the current behavior of the HID subsystem and removes one more
dependency over USB.

The current user space clients which relies on this to fetch the
LEDs path need an update. However, we already break them in the
kernel v3.11 for the Bluetooth Wacom devices. They are going to be fixed
soon.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:52 -07:00
Benjamin Tissoires c31a408f7a Input: wacom - install LED/OLED sysfs files in the HID device instead of USB
Removes one more dependency over USB, but requires some changes in
the user space to find the sysfs files correctly.

This patch breaks the user space. However, the number of program
accessing the LEDs is quite limited and we can easily patch them
to handle the new HID behavior.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:52 -07:00
Benjamin Tissoires 01c846f953 Input: wacom - compute the HID report size to get the actual packet size
This removes an USB dependency and is more accurate: the computed pktlen
is the actual maximum size of the reports forwarded by the device.

Given that the pktlen is correctly computed/validated, we can store it now
in the features struct instead of having a special handling in the rest of
the code.

Likewise, this information is not mandatory anymore in the description
of devices in wacom_wac.c. They will be removed in a separate patch.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:51 -07:00
Benjamin Tissoires ba9a3541fb Input: wacom - use HID core to actually fetch the report descriptor
HID core already retrieves the report descritor. There is no need
to ask ourself for one.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:51 -07:00
Benjamin Tissoires 27b20a9dec Input: wacom - use hid communication instead of plain usb
Wacom.ko was a plain USB driver for a HID device. The communications
from/to the devices can actually be replaced with the HID API.

At the USB level, the reports are exactly the same.

This will allow to use uhid virtual devices instead of true USB devices.
This step is necessary to implement regression tests.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:50 -07:00
Benjamin Tissoires 29b4739134 Input: wacom - switch from an USB driver to a HID driver
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 <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:50 -07:00
Benjamin Tissoires f54bc61cf7 Input: wacom - include and use linux/hid.h
The current wacom code redefines constants that are already in linux/hid.h
This patch includes the official implementation and use it accross the code.

There is a conflict with HID_USAGE and others at the same level:
- in the wacom.ko implementation, those are the #define regarding the
  value of the field in the report descriptor
- in the hid.h, those are bitmask
So add HDESC_ in their current definition.

Also, the struct hid_descriptor slightly differs from the linux/hid.h
point of view, so mark it as custom for this driver.

Signed-off-by: Benjamin Tissoires <benjamin.tissoires@redhat.com>
Reviewed-by: Jason Gerecke <killertofu@gmail.com>
Tested-by: Jason Gerecke <killertofu@gmail.com>
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
2014-07-25 18:53:49 -07:00