Messages in this thread | | | From | Andy Lutomirski <> | Date | Wed, 6 Jun 2018 10:11:06 -0700 | Subject | Re: [PATCH v2 5/8] x86/msr: write_rdtscp_aux() to use wrmsr_safe() |
| |
On Wed, Jun 6, 2018 at 9:23 AM Chang S. Bae <chang.seok.bae@intel.com> wrote: > > Using wrmsr_safe() can make code a bit simpler by removing > some condition check
NAK.
If we really want to stop checking the cpu feature and unconditionally write the MSR, then there should be a single patch that does it. If we don't, then we should not make this change, since it will make the very useful warning if we screwed it up go away.
I think we should continue checking the cpu feature, personally. I also thing that, if we make the change, it should not be part of the FSGSBASE series.
| |