The Linux 4.18 Power Regression Affecting Some AMD Graphics Cards Should Be Reverted

Making the rounds last week was a nasty power regression hitting Linux 4.18 stable and as we ended up bisecting was caused by a change to the AMDGPU kernel driver and affected select Radeon graphics cards. It looks like the goal this week is to get that patch reverted from Linux 4.18.

The change causing that big uptick in idle power consumption was boosting the clock values in order to avoid some issues with 4K DP and 1080p HDMI displays sometimes having problems with this open-source AMD kernel driver.

Yep... pic.twitter.com/s9j0VX0vNS

— Phoronix (@phoronix) October 4, 2018

Last week AMD veteran Linux developer and AMDGPU maintainer Alex Deucher commented in an associated bug report, "I don't think this is a bug. The problem is, prior to that patch, the display component was requesting minimum clocks that were 10x too low. This saved power, but led to display problems on some systems because the clocks were too low to sustain the display requirements."

But this week the tune he is sharing in the forums are, "This patch shouldn't have been applied to 4.18. It looks like it was autoselected for 4.18: https://lkml.org/lkml/2018/9/15/172 It should be reverted. I'm working on getting it reverted."

It looks like on the Linux 4.19 kernel some users are reporting less of a power impact from this change (my results were mixed at least during my limited testing then... Will do some Windows 10 comparisons once the October update is re-released), so this patch should have been paired with other DC patches if it was being back-ported to Linux 4.18. But anyhow this patch was automatically selected without the AMDGPU developers realizing and now they will be working on getting it out of the 4.18 tree for an upcoming point release.