There's a second batch of power management changes on top of the main feature material that came last week. Power management changes for this secondary pull include some CPUFreq regressions, improve the safety around MSRs for hardware-managed P-States, and various fixes.
One of the changes to catch my attention in this pull request today was, "Rework the intel_pstate's P-state election algorithm used on Atom processors to avoid known problems with the current one and to make the computation more straightforward, which also happens to improve performance in multiple benchmarks a bit."
The patch explains in more details but doesn't include any reference benchmark figures. "The new algorithm will set the new P-state to be 1.25 times the available maximum times the (frequency-invariant) utilization during the previous sampling period except when the target P-state computed this way is lower than the average P-state during the previous sampling period. In the latter case, it will increase the target by 50% of the difference between it and the average P-state to prevent performance from dropping down too fast in some cases."