tag nameiio-for-3.14b (d05908d50e13661a688cd30981b8f4d00d9010c7)
tag date2013-12-22 17:22:33 +0000
tagged byJonathan Cameron <>
tagged objectcommit 6fd92d3add...
2nd round of new IIO drivers, features and cleanups for the 3.14 cycle.
New drivers * HID inclinometer driver. * DHT11 humidity driver. Note that previous humidity drivers have been in hwmon, but no one was ever entirely happy with that, and they should find a more comfortable home in IIO (their original placement in hwmon was my fault - oops). As this is our first humidity driver, core support is also added. New features * Two of mxs-lradc channels are internally wired to a temperature sensor, make this explicit in the driver by providing the relevant temperature channel. * Add support for blocking IO on buffers. * Add a data_available call back to the interface between buffer implementations and the core. This is much cleaner than the old, 'stufftoread' flag. Implemented in the kfifo buffer. Cleanups * Last user of the old event configuration interface is converted and the old interface dropped. Nice to be rid of this thanks to Lars-Peter's hard work! * Replace all remaining instances of the IIO_ST macro with explicit filling of the scan_type structure within struct iio_chan_spec. This macro was a bad idea, that rapidly ceased to cover all elements of the structure. Miss reading of the macro arguements has led to a number of bugs so lets just get rid of it. The final removal patch is awaiting for some fixes to make their way into mainline. In a couple of drivers, no elements of scan_type were even being used so in those case, it has been dropped entirely. * Drop a couple of of_match_ptr helper uses in drivers where devicetree is not optional and hence the structures being protected by this always exist. * Fix up some cases where data was read from a device in a particular byte order, but he code placed it into a s16 or similar. These were highlighted by Sparse. * Use the new ATTRIBUTE_GROUPS macro to drop some boiler plate in the triggers core code. * ad7746 and ad7280a - stop storing buffers on the stack, giving cleaner code and possibly avoiding issues with i2c bus drivers that assume they can dma directly into the buffer. Note that this cannot currently happen as the the i2c_smbus_read_i2c_block_data function has a memcpy from the buffer actually passed to the bus driver. I missed this element of the commit message and don't think it is major enough to rebase the iio tree. * ad5791 and ad5504 stop storing buffers on the stack for an SPI driver. Unlike the i2c drivers, this is a real issue for SPI drivers which can dma directly into the buffer supplied. -----BEGIN PGP SIGNATURE----- Version: GnuPG v2.0.22 (GNU/Linux) iQIcBAABAgAGBQJStyIbAAoJEFSFNJnE9BaI1goQAL0hKYCYuIl3d1fAy65u2I4h 5mzJs/oJmomq/4BqAopfEQ8CbhZhksAYoR4JndOzZH7n4jVY/fRgyY/bH/Ymj0oI OpCtfee6IeeBLA0p8CMeEPem/pnwxRhSDzul9jsiwpTrTRKAIC1BPZwrmLpaoUfc obD8r1ocVZStzfsYBr3DUwkcIpcTQTCVy/Pl8HoKLKKsdYoFhTpNwEHJFOoZdiFi KKGRkeL9Q8VRWt/otWU0L0VFGZFwI1PWlxrqnbisVcGwSs8FF4wGcQvijfC0mUMg BdKDM7J4GrourZhj3og566B/8WMtGo6YTJXAe/QvvPp768rQncccDHem4V0Tnu49 OJbjgD4ZGVXt3uBFaYddBIbMEIB8SfA2VYur/MW3gnZ7saSAtDk6TllsvC6CxIkR +LOOxWylhEGeJFIjyMrFPqRVhrrRNkuDRxPz8ZGTiDc8ovo6DWuTLsJrLSX8EJyZ O6TN6EEk8TCJaf8V63uTFW0Dlom4IQHyQei6LKhfhzwUQq/ri0esBp5P8lGzI3Uq wtOSdCDuYyoUEYPYbwjohFmQJ27w1rx9KcS4Y9BGmhTIRXslUg3hr+wA/gKMSDZ0 /AUkLQajcv9otupfGzsp5mIWkthKKsGt/Y50xc5zIodnFtnM3nQGq4AqlP6t8nzP jucVwVMQLj5KaNH13P6K =Whfv -----END PGP SIGNATURE-----