commit 324b0398781e7afb846378dd2d8a4374faaf236b upstream.

There is possibility with misconfigured pins that interrupt occurs instantly
after setting irq_set_chained_handler() in gpiochip_set_chained_irqchip().
Now if handler gets called before irq_set_handler_data() the handler gets
NULL handler data.

Fix this by moving irq_set_handler_data() call before
irq_set_chained_handler() in gpiochip_set_chained_irqchip().

Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Jarkko Nikula <jarkko.nikula@linux.intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

commit c15d821ddb9dac9ac6b5beb75bf942f3bc3a4004 upstream.

Fix code when the operation region callback is for an gpio, which
is not at index 0 and for partial pins in a GPIO definition.
For example:
Name (GMOD, ResourceTemplate ()
{
	//3 Outputs that define the Power mode of the device
	GpioIo (Exclusive, PullDown, , , , "\\_SB.GPI2") {10, 11, 12}
	})
}

If opregion callback calls is for:
- Set pin 10, then address = 0 and bit length = 1
- Set pin 11, then address = 1 and bit length = 1
- Set for both pin 11 and pin 12, then address = 1, bit length = 2

This change requires updated ACPICA gpio operation handler code to
send the pin index and bit length.

Fixes: 473ed7be0da0 (gpio / ACPI: Add support for ACPI GPIO operation regions)
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Acked-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

Pull pin control fixes from Linus Walleij:
 "Here are three pin control fixes for the v3.16 series.  Sorry that
  some of these arrive late, the summer heat in Sweden makes me slow.

   - an IRQ handling fix for the STi driver, also for stable
   - another IRQ fix for the RCAR GPIO driver
   - a MAINTAINERS entry"

* tag 'pinctrl-v3.16-3' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-pinctrl:
  gpio: rcar: Add support for DT IRQ flags
  MAINTAINERS: Add entry for the Renesas pin controller driver
  pinctrl: st: Fix irqmux handler

The gpio-rcar driver has no IRQ domain OF xlate function and thus
ignores IRQ flags specified in DT. Fix this by using the two-cell xlate
function.

Signed-off-by: Laurent Pinchart <laurent.pinchart+renesas@ideasonboard.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

Unnecessary checking was added during the merge of the gpio branch.
This patch removes the extra unnecessary checking.

Signed-off-by: Michael Welling <mwelling@ieee.org>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

Commit dd34c37aa3e (gpio: of: Allow -gpio suffix for property names)
added parsing for both -gpio and -gpios suffix but also changed
the handling for deferred probe unintentionally. Because of the
looping the second name will now return -ENOENT instead of
-EPROBE_DEFER. Fix the issue by breaking out of the loop if
-EPROBE_DEFER is encountered.

Signed-off-by: Tony Lindgren <tony@atomide.com>
Reviewed-by: Thierry Reding <treding@nvidia.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>

Pull MFD updates from Lee Jones:
 "Changes to existing drivers:
   - increase DT coverage: arizona, mc13xxx, stmpe-i2c, syscon,
     sun6i-prcm
   - regmap use of and/or clean-up: tps65090, twl6040
   - basic renaming: max14577
   - use new cpufreq helpers: db8500-prcmu
   - increase regulator support: stmpe, arizona, wm5102
   - reduce legacy GPIO overhead: stmpe
   - provide necessary remove path: bcm590xx
   - expand sysfs presence: kempld
   - move driver specific code out to drivers: rtc-s5m, arizona
   - clk handling: twl6040
   - use managed (devm_*) resources: ipaq-micro
   - clean-up/remove unused/duplicated code: tps65218, sec, pm8921,
     abx500-core, db8500-prcmu, menelaus
   - build/boot/sematic bug fixes: rtsx_usb, stmpe, bcm590xx, abx500,
     mc13xxx, rdc321x-southbridge, mfd-core, sec, max14577, syscon,
     cros_ec_spi
   - constify stuff: sm501, tps65910, tps6507x, tps6586x, max77686,
     max8997, kempld, max77693, max8907, rtsx_usb, db8500-prcmu,
     max8998, wm8400, sec, lp3943, max14577, as3711, omap-usb-host,
     ipaq-micro

  Support for new devices:
   - add support for max77836 into max14577
   - add support for tps658640 into tps6586x
   - add support for cros-ec-i2c-tunnel into cros_ec
   - add new driver for rtsx_usb_sdmmc and rtsx_usb_ms
   - add new driver for axp20x
   - add new driver for sun6i-prcm
   - add new driver for ipaq-micro"

* tag 'mfd-for-linus-3.16' of git://git.kernel.org/pub/scm/linux/kernel/git/lee/mfd: (77 commits)
  mfd: wm5102: Correct default for LDO Control 2 register
  mfd: menelaus: Use module_i2c_driver
  mfd: tps65218: Terminate of match table
  mfd: db8500-prcmu: Remove check for CONFIG_DBX500_PRCMU_DEBUG
  mfd: ti-keystone-devctrl: Add bindings for device state control
  mfd: palmas: Format the header file
  mfd: abx500-core: Remove unused function abx500_dump_all_banks()
  mfd: arizona: Correct addresses of always-on trigger registers
  mfd: max14577: Cast to architecture agnostic data type
  i2c: ChromeOS EC tunnel driver
  mfd: cros_ec: Sync to the latest cros_ec_commands.h from EC sources
  mfd: cros_ec: spi: Increase cros_ec_spi deadline from 5ms to 100ms
  mfd: cros_ec: spi: Make the cros_ec_spi timeout more reliable
  mfd: cros_ec: spi: Add mutex to cros_ec_spi
  mfd: cros_ec: spi: Calculate delay between transfers correctly
  mfd: arizona: Correct error message for addition of main IRQ chip
  mfd: wm8997: Add registers for high power mode
  mfd: arizona: Add MICVDD to mapped regulators
  mfd: ipaq-micro: Make mfd_cell array const
  mfd: ipaq-micro: Use devm_ioremap_resource()
  ...

Pull GPIO updates from Linus Walleij:
 "This is the bulk of GPIO changes for the v3.16 series.

  There is a lot of action in the GPIO subsystem doing refactorings and
  cleanups, almost as many deletions as insertions and minor feature
  growth and no new drivers this time.  Which is actually pretty nice.
  Some GPIO-related stuff will come in through the pin control tree as
  well.

  Details:

   - 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"

* tag 'gpio-v3.16-1' of git://git.kernel.org/pub/scm/linux/kernel/git/linusw/linux-gpio: (85 commits)
  gpio: select IRQ_DOMAIN for gpiolib irqchip helpers
  gpio: pca953x: use gpiolib irqchip helpers
  gpio: pcf857x: Add IRQF_SHARED when request irq
  gpio: pcf857x: Avoid calling irq_domain_cleanup twice
  gpio: mcp23s08: switch chip count to int
  gpio: dwapb: use a second irq chip
  gpio: ep93xx: Use devm_ioremap_resource()
  gpio: mcp23s08: fixed count variable for devicetree probing
  gpio: Add run-time dependencies to R-Car driver
  gpio: pch: add slab include
  Documentation / ACPI: Fix location of GPIO documentation
  gpio / ACPI: use *_cansleep version of gpiod_get/set APIs
  gpio: generic: add request function pointer
  gpio-pch: Fix Kconfig dependencies
  gpio: make of_get_named_gpiod_flags() private
  gpio: gpioep93xx: use devm functions
  gpio: janzttl: use devm function
  gpio: timberdale: use devm functions
  gpio: bt8xx: use devm function for memory allocation
  gpio: include linux/bug.h in interface header
  ...

These helpers depend on the IRQ_DOMAIN so select it explicitly,
as it will not be present on all platforms such as Intel
desktops and laptops using Intel-MID.

Signed-off-by: Linus Walleij <linus.walleij@linaro.org>