Merge tag 'iio-fixes-for-4.8a' of git://git.kernel.org/pub/scm/linux/kernel/git/jic23/iio into work-linus

Jonathan writes:

First round of IIO fixes for the 4.8 cycle.

This is somewhat of a bumper set due to my unavailabilty earlier in the
month.  The only slightly unusual ones are the dts updates for the
rockchip adc reset.  The fix in the driver only makes sense with these
and the rockchip maintainer is happy with them going through IIO to
reach mainline.

Core stuff

* Fix an issue with a blocking op when !TASK_RUNNING. This been there
  a while and snuck in with seemingly minor additions to some core
  code paths.
* Tools
  - generic_buffer failed to initialize the channel array pointer thus
    in the case of no channels blows up trying to free a random memory
    address.
* sw-trigger:
  - Fix config group initialization when configfs is built as a module.

Drivers

* ad5933
  - Fix an incorrect overwrite of an error value.
* ad799x
  - A missed assignment of the update_scan_mode callback means buffered mode
    doesn't work on the ad7991, ad7995 or ad7999.
* ads1015
  - wrong pointer returned from i2c_get_clientdata (missmatch of assumptions)
* am2315
  - Timestamps are reported, but never actually acquired from anywhere
    (so always 0)
  - missing buffer selects in Kconfig
* am335x adc
  - Protect fifo1 from concurrent access.
  - Increase timeout waiting for ADC to be long enough in all cases.
* as3935
  - Timestamps are reported, but never actually acquired from anywhere
    (so always 0)
* at91
  - Fix reading of channel 3.
* atlas-ph-sensor
  - Typo means that the scale of electrical conductivity readings is way off.
* bma220
  - Timestamps are reported, but never actually acquired from anywhere
    (so always 0)
  - Missing buffer selects in Kconfig
* bmp280
  - pass the write pointer to PTR_ERR (i.e. the one that was just checked
    with IS_ERR).
  - suspend /resume crash due to wrong assumption about what dev_get_drvdata
    would return.
* hdc100x
  - It superficially appeared that smbus_read_byte commands would allow
  reading of the outputs in two goes.  In reality it doesn't work, but
  instead returns the same for the upper and lower bytes (nice catch from
  Alison!)
* kxsd9
  - Fix raw read return value to ensure it actually reports the value rather
  than a blank string.
* max44000
  - Missing buffer selects in Kconfig
* rockchip_saradc
  - Add use of reset controller to enforce a clean state of the ADC.
    Some bootloaders can leave it in an 'intersting' state and effectively
    frozen without this. A couple of associated dts updates.
* stk8ba50
  - Missing buffer selects in Kconfig
* stx104
  - Fix a possible race due to use of devm_iio_device_register when there
    was other stuff in the remove function.