The current computation for fractional part of the magnetic field is broken. This patch fixes it by taking a different approach. We expose the raw reading in milli Gauss (to avoid rounding errors) with a scale of 0.001. Thus the final computation is done in userspace where floating point operation are more relaxed. Fixes: abeb6b1e7b ("iio: magnetometer: Add support for MEMSIC MMC35240") Signed-off-by: Daniel Baluta <daniel.baluta@intel.com> Signed-off-by: Jonathan Cameron <jic23@kernel.org>