Tags

ARM: SoC defconfig updates for 3.16

A number of defconfig updates for 3.16. We have quite a few of these as
new SoCs and drivers get supported, and we've started collecting them
in one shared branch.

We started halfway through the merge window so there'll be some small
conflicts with other branches on nearby changes, but nothing major. Next
cycle should be smoother.

ARM: SoC cleanups for 3.16

Cleanups for 3.16. Among these are:

- A bunch of misc cleanups for Broadcom platforms, mostly housekeeping
- Enabling Common Clock Framework on the older s3c24xx Samsung chipsets
- Cleanup of the Versatile Express system controller code, moving it to syscon
- Power management cleanups for OMAP platforms

+ a handful of other cleanups across the place

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.

This is the 3.12.21 stable release

Linux 3.15-rc8

This is the 3.14.5 stable release

This is the 3.10.41 stable release

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.

/

Linaro 14.05

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

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.

DT queued up for v3.16

Mostly bug fixes, but also some rework to improve path handling and device naming

sound fixes for 3.15-rc8

Just two small stable fixes: an HD-audio fix for the new Intel chipsets
and a PM handling fix in PCM dmaengine core.

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.

regulator: Support newer revisions of tps658640

There are two different variants of the tps658640 with slightly
different feature sets.

Linux 3.15-rc7