Comment 337 for bug 1690085

I think both RCU workaround and disabling C6 (either through MSR or using the BIOS option) just masks the problem, which is probably on hardware level. It is likely also masked on Windows through how its power management works. I strongly believe that AMD should properly investigate this issue instead of waving it off on PSUs. This happens on all kinds of PSUs, including those that definitely support C6/C7.

One thing I noticed is that with C6 disabled through the script or using the "Typical Current" power supply option in BIOS in my case MB sensors never report Vcore less than 0.8V, which indicates that indeed it doesn't reach lower idle states even if only "package C6" is disabled. On default settings it will frequently report 0.4-0.5V range when idle.

Since Zen would only apply boosting and especially XFR when certain power and thermal conditions are met, disabling the deep idle states may affect this adversely. So IMO all that should be well tested before applying a workaround like this on the kernel level.