linux-kernel - Re: [PATCH v2] x86/speculation/l1tf: Add KConfig for setting the L1D cache flush mode

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <CA+noqojQ9FmvQ3k7r1Yh5bdrtDF4+eDd-Spo4PG7fdMSVxVP1w@mail.gmail.com>
Date:   Thu, 2 Jul 2020 15:14:38 -0700
From:   Abhishek Bhardwaj <abhishekbh@...gle.com>
To:     Randy Dunlap <rdunlap@...radead.org>
Cc:     LKML <linux-kernel@...r.kernel.org>,
        Anthony Steinhauser <asteinhauser@...gle.com>,
        Borislav Petkov <bp@...en8.de>,
        "H. Peter Anvin" <hpa@...or.com>, Ingo Molnar <mingo@...hat.com>,
        Jim Mattson <jmattson@...gle.com>,
        Joerg Roedel <joro@...tes.org>,
        Josh Poimboeuf <jpoimboe@...hat.com>,
        Mark Gross <mgross@...ux.intel.com>,
        Paolo Bonzini <pbonzini@...hat.com>,
        Pawan Gupta <pawan.kumar.gupta@...ux.intel.com>,
        Peter Zijlstra <peterz@...radead.org>,
        Sean Christopherson <sean.j.christopherson@...el.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Tony Luck <tony.luck@...el.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Waiman Long <longman@...hat.com>,
        Wanpeng Li <wanpengli@...cent.com>, kvm@...r.kernel.org,
        x86@...nel.org
Subject: Re: [PATCH v2] x86/speculation/l1tf: Add KConfig for setting the L1D
 cache flush mode

On Thu, Jul 2, 2020 at 3:01 PM Randy Dunlap <rdunlap@...radead.org> wrote:
>
> Hi--
>
> On 7/2/20 2:38 PM, Abhishek Bhardwaj wrote:
> > This change adds a new kernel configuration that sets the l1d cache
> > flush setting at compile time rather than at run time.
> >
> > Signed-off-by: Abhishek Bhardwaj <abhishekbh@...gle.com>
> >
> > ---
> >
> > Changes in v2:
> > - Fix typo in the help of the new KConfig.
> >
> >  arch/x86/kernel/cpu/bugs.c |  8 ++++++++
> >  arch/x86/kvm/Kconfig       | 17 +++++++++++++++++
> >  2 files changed, 25 insertions(+)
> >
> > diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
> > index 0b71970d2d3d2..1dcc875cf5547 100644
> > --- a/arch/x86/kernel/cpu/bugs.c
> > +++ b/arch/x86/kernel/cpu/bugs.c
> > @@ -1406,7 +1406,15 @@ enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH;
> >  #if IS_ENABLED(CONFIG_KVM_INTEL)
> >  EXPORT_SYMBOL_GPL(l1tf_mitigation);
> >  #endif
> > +#if (CONFIG_KVM_VMENTRY_L1D_FLUSH == 1)
> > +enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_NEVER;
> > +#elif (CONFIG_KVM_VMENTRY_L1D_FLUSH == 2)
> > +enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_COND;
> > +#elif (CONFIG_KVM_VMENTRY_L1D_FLUSH == 3)
> > +enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_ALWAYS;
> > +#else
> >  enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
> > +#endif
> >  EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation);
> >
> >  /*
> > diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
> > index b277a2db62676..d375dcedd447d 100644
> > --- a/arch/x86/kvm/Kconfig
> > +++ b/arch/x86/kvm/Kconfig
> > @@ -107,4 +107,21 @@ config KVM_MMU_AUDIT
> >        This option adds a R/W kVM module parameter 'mmu_audit', which allows
> >        auditing of KVM MMU events at runtime.
> >
> > +config KVM_VMENTRY_L1D_FLUSH
> > +     int "L1D cache flush settings (1-3)"
> > +     range 1 3
> > +     default "2"
> > +     depends on KVM && X86 && X86_64
>
> Why does this apply only to KVM?
Sorry, I don't know what this means. The runtime options this aims to
emulate applied to kvm driver.
Hence, this kernel config applies to KVM ?

>
> and the "X86 && X86_64" is more than is needed. Just "X86_64" alone
> should be enough.
Fixed in v3.

>
>
> > +     help
> > +      This setting determines the L1D cache flush behavior before a VMENTER.
> > +      This is similar to setting the option / parameter to
> > +      kvm-intel.vmentry_l1d_flush.
> > +      1 - Never flush.
> > +      2 - Conditionally flush.
> > +      3 - Always flush.
> > +
> > +# OK, it's a little counter-intuitive to do this, but it puts it neatly under
> > +# the virtualization menu.
> > +source "drivers/vhost/Kconfig"
This was a bad copy paste. Removed in v3.
>
>
> I don't quite understand why this 'source' line is here.
> Can you explain more about that, please?
>
> It puts "VHOST drivers" in the menu 2 times, in 2 totally unrelated
> places.  Seems like it could be confusing.
>
> > +
> >  endif # VIRTUALIZATION
>
>
> --
> ~Randy
>


-- 
Abhishek