Re: [patch 5/8] MDS basics 5

On Tue, 19 Feb 2019, speck for Andrew Cooper wrote:

> On 19/02/2019 17:40, speck for Thomas Gleixner wrote:
> > On Tue, 19 Feb 2019, speck for Andi Kleen wrote:
> >
> >>> +	case MDS_MITIGATION_AUTO:
> >>> +	case MDS_MITIGATION_FULL:
> >>> +		if (boot_cpu_has(X86_FEATURE_MD_CLEAR)) {
> >>> +			mds_mitigation = MDS_MITIGATION_FULL;
> >>> +			static_branch_enable(&user_mds_clear_cpu_buffers);
> >>
> >> This violates Linus' feedback of unconditionally enabling for one year
> >> to work around VMWare breakage.
> > That's easy enough to turn the other way round. That's what review is for,
> > isn't it?
> >
> > What's the VMware breakage? I can't remember that I've read that mail.
> 
> VMWare reckon they will have updated microcode long before guest VM's
> get to the the MD_CLEAR CPUID bit, and wanted guests to issue the VERW
> instruction in the hope that it might do something.

Thanks for the reminder. I was in the room and chuckled when this was
discussed, but it slipped from memory.

Oh well...

Thanks,

	tglx