Re: [patch 5/8] MDS basics 5

On Tue, 19 Feb 2019, speck for Andi Kleen wrote:

> On Tue, Feb 19, 2019 at 04:07:11PM +0100, speck for Thomas Gleixner wrote:
> > On Tue, 19 Feb 2019, speck for Thomas Gleixner wrote:
> > > +/* Update the static key controlling the MDS CPU buffer clear in idle */
> > > +static void update_mds_branch_idle(void)
> > > +{
> > > +	if (sched_smt_active())
> > > +		static_branch_enable(&user_mds_clear_cpu_buffers);
> > > +	else
> > > +		static_branch_disable(&user_mds_clear_cpu_buffers);
> > 
> > Those obviously need s/user/idle/
> 
> Please don't post untested crap like this. It would be really
> bad if someone applied it.

Your last series contained serious bugs and did not even compile...

> This can be easily verified just by looking at a few PT traces.
> 
> Or just use MDSv2 which actually worked.
> 
> BTW even for the minimum version virtualization is definitely needed.

Did you read the cover letter? It's a todo and I did nowhere claim that it
is complete and perfect.

Thanks,

	tglx