Tags

gpio-v3.16-1

This is the bulk of GPIO changes for the v3.16 series:

- We are finalizing and fixing up the gpiochip irqchip helpers
  bringing a helpful irqchip implementation into the gpiolib
  core and avoiding duplicate code and, more importantly,
  duplicate bug fixes:

  - Support for using the helpers with threaded interrupt
    handlers as used on sleeping GPIO-irqchips

  - Do not set up hardware triggers for edges or levels if
    the default IRQ type is IRQ_TYPE_NONE - some drivers
    would exploit the fact that you could get default
    initialization of the IRQ type from the core at probe()
    but if no default type is set up from the helper, we
    should not call the driver to configure anything. Wait
    until a consumer requests the interrupt instead.

  - Make the irqchip helpers put the GPIO irqs into their
    own lock class. The GPIO irqchips can often emit
    (harmless, but annoying) lockdep warnings about recursions
    when they are in fact just cascaded IRQs. By putting
    them into their own lock class we help the lockdep core
    to keep track of things.

  - Switch the tc3589x GPIO expanders to use the irqchip
    helpers

  - Switch the OMAP GPIO driver to use the irqchip helpers

  - Add some documentation for the irqchip helpers

  - select IRQ_DOMAIN when using the helpers since some
    platforms may not be using this by default and it's a
    strict dependency.

- Continued GPIO descriptor refactoring:

  - Remove the one instance of gpio_to_desc() from the
    device tree code, making the OF GPIO code use GPIO
    descriptors only.

  - Introduce gpiod_get_optional() and
    gpiod_get_optional_index() akin to the similar
    regulator functions for cases where the use of GPIO
    is optional and not strictly required.

  - Make of_get_named_gpiod_flags() private - we do not
    want to unnecessarily expose APIs to drivers that
    make the gpiolib harder than necessary to maintain
    and refactor. Privatize this function.

- Support "-gpio" suffix for the OF GPIO retrieveal path.
  We used to look for "foo-gpios" or just "gpios" in device
  tree nodes, but it turns out that some drivers with a
  single GPIO line will just state "foo-gpio" (singularis).
  Sigh. Support this with a fallback looking for it, as
  this simplifies driver code and handles it in core code.

- Switch the ACPI GPIO core to fetch GPIOs with the
  *_cansleep function variants as the GPIO operation
  region handler can sleep, and shall be able to handle
  gpiochips that sleep.

- Tons of cleanups and janitorial work from Jingoo Han,
  Axel Lin, Javier Martinez Canillas and Abdoulaye Berthe.
  Notably Jingoo cut off a ton of pointless OOM messages.

- Incremental development and fixes for various drivers,
  nothing really special here.

topic/core-stuff-2014-06-02

v3.12.21

This is the 3.12.21 stable release

v3.15-rc8

Linux 3.15-rc8

v3.14.5

This is the 3.14.5 stable release

v3.10.41

This is the 3.10.41 stable release

pm+acpi-3.15-rc8

ACPI and power management fixes for 3.15-rc8

 - A workqueue is destroyed too early during the ACPI thermal driver
   module unload which leads to a NULL pointer dereference in the
   driver's remove callback.  Fix from Aaron Lu.

 - A wrong argument is passed to devm_regulator_get_optional() in
   the probe routine of the cpu0 cpufreq driver which leads to
   resource leaks if the driver is unbound from the cpufreq
   platform device.  Fix from Lucas Stach.

 - A lock is missing in cpufreq_governor_dbs() which leads to
   memory corruption and NULL pointer dereferences during
   system suspend/resume, for example.  Fix from Bibek Basu.

/

ubuntu-ifc6410-14.05

Linaro 14.05

mfd-omap-v3.16-1

Second immutable branch between MFD and OMAP due for the v3.16 merge window.

fixes-for-3.15

ARM: SoC fixes for 3.15

A slightly larger set of fixes than we'd like at this point in the
release. Hopefully our very last batch before 3.15:

 - OMAP:
   * Fix boot regression with CPU_IDLE enabled
   * Fixes for audio playback on OMAP5
   * Clock rate setting fix for OMAP3
   * Misc idle/PM fixes
 - Exynos:
   * Removal of a couple of power domains to work around issues with access
     when they are powered down
   * Enabling missing highspeed-i2c driver to make MMC regulators work
   * Secondary CPU spin-up fix for 4212
   * Remove MDMA1 engine to avoid conflicts on secure mode platforms
   * A few other DT fixes
 - Marvell:
   * PCI-e fixes for clocks and resource allocation

 + a few other smaller fixes, add a MAINTAINERS entry for reset drivers, etc.

drm-intel-fixes-2014-05-27

pinctrl-v3.15-4

A single last pinctrl fix for the v3.15 series:
the vt8500 driver was failing to update the output value
when the combined set direction output and set value was
executed.

v3.15-rc7

Linux 3.15-rc7

sunxi-drivers-for-3.16-2

Allwinner drivers changes for 3.16, take 2

Add reset driver for the A31

sunxi-dt-for-3.16-2

Allwinner DT changes for 3.16, take 2

  - Introduction of a new board, the i12-tvbox
  - Enable the MMC and USB controllers on the Colombus
  - Add the enable-method to the A31 cpus
  - a few fixes

sunxi-defconfig-for-3.16-2

Allwinner defconfig changes, take 2

Add the A31 reset driver to the sunxi-related defconfigs

sunxi-core-for-3.16-2

Allwinner Core additions for 3.16, take 2

  - Convert the A31 SMP operations to the CPU_METHOD_OF_DECLARE mechanism
  - Remove the reset code from the machine definition, that removes pretty much
    all the code left in mach-sunxi

drm-intel-next-2014-05-23

- prep refactoring for execlists (Oscar Mateo)
- corner-case fixes for runtime pm (Imre)
- tons of vblank improvements from Ville
- prep work for atomic plane/sprite updates (Ville)
- more chv code, now almost complete (tons of different people)
- refactoring and improvements for drm_irq.c merged through drm-intel-next
- g4x/ilk reset improvements (Ville)
- removal of encoder->mode_set
- moved audio state tracking into pipe_config
- shuffled fb pinning out of the platform crtc modeset callbacks into core code
- userptr support (Chris)
- OOM handling improvements from Chris, with now have a neat oom notifier which
  jumps additional debug information.
- topdown allocation of ppgtt PDEs (Ben)
- fixes and small improvements all over

ib-mfd-gpio-v3.16

Immutable branch between MFD and GPIO due for the v3.16 merge window.

asoc-v3.16

ASoC: Updates for v3.16

Lots of cleanup work going on in the core this release but very little
visible to external users except for the new drivers that have been
added.

 - Support for specifying aux CODECs in DT.
 - Removal of the deprecated mux and enum macros.
 - More moves towards full componentisation.
 - Removal of some unused I/O code.
 - Lots of cleanups, fixes and enhancements to the davinci, Freescale,
   Haswell and Realtek drivers.
 - Several drivers exposed directly in Kconfig for use with simple-card.
 - New drivers for Cirrus CS42L56, Realtek RT5639, RT5642 and RT5651 and
   ST STA350.