[MODERATED] Re: [PATCH v7 04/10] TAAv7 4

On Wed, Oct 23, 2019 at 08:46:54AM +0200, speck for Borislav Petkov wrote:
> On Tue, Oct 22, 2019 at 10:25:27PM -0700, speck for Pawan Gupta wrote:
> > I think we first need to agree on whether disabling TSX is the
> > mitigation for X86_BUG_TAA or the lack of bug. Your clearing the bug bit
> > here makes me think that you are treating it as lack of bug. This series
> > treats it as a mitigation when the hardware has the bug. Let me know
> > your thoughts on this.
> 
> Ok, I see your point. And yes, let's do what you're suggesting because
> that mirrors reality optimally:
> 
> static void __init taa_select_mitigation(void)
> { 
>         u64 ia32_cap;
> 
>         if (!boot_cpu_has_bug(X86_BUG_TAA) || cpu_mitigations_off()) {
>                 taa_mitigation = TAA_MITIGATION_OFF;
>                 return;
>         }

There is a small issue with cpu_mitigations_off() check before X86_FEATURE_RTM.

If the user provides cmdline "tsx=off mitigations=off" then sysfs will
show "Vulnerable", when it is actually mitigated because of "tsx=off".

> 
> 	if (!boot_cpu_has(X86_FEATURE_RTM)) {
>                 taa_mitigation = TAA_MITIGATION_TSX_DISABLE;
>                 goto out;
>         }

cpu_mitigations_off() check after X86_FEATURE_RTM check will fix this.

Thanks,
Pawan