Recent ARM chips, like the Qualcomm Snapdragon 810, seem to be using a hybrid architecture called "big.LITTLE" with cores of different architectures and speeds combined into one CPU.
On a Linux (or other unixoid) system, how does the kernel distribute processes to those cores, and how does the userland representation of this architecture look? Does the niceness of processes play a role in core allocation?
I was curious to check this in the AOSP code, but could not find the relevant information. Hence, pointers are very much appreciated, too.