https://bugzilla.kernel.org/show_bug.cgi?id=219009 Christian Haefeli (chaefeli@xxxxxxxxxx) changed: What |Removed |Added ---------------------------------------------------------------------------- CC| |chaefeli@xxxxxxxxxx --- Comment #45 from Christian Haefeli (chaefeli@xxxxxxxxxx) --- (In reply to Mario Limonciello (AMD) from comment #38) > Thanks everyone for your feedback and testing. > > The following change will go into 6.12 and back to the stable kernels to fix > this issue. It is essentially doing the same effect that kvm_amd.vls=0 did. > > https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/commit/?h=x86/ > urgent&id=a5ca1dc46a6b610dd4627d8b633d6c84f9724ef0 Hello I would prefer the more flexible solution via kvm_amd module parameter. I am not having this issue with an Epyc 4244p but am now losing performance due to this hard coded workaround. Does my CPU also qualify as a 'Zen4 Client SoC? Regards Christian -- You may reply to this email to add a comment. You are receiving this mail because: You are watching the assignee of the bug.
