linux-kernel - Re: [PATCH] proc: added ept

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]

Date:   Wed, 1 Aug 2018 10:44:55 -0700
From:   Peter Shier <pshier@...gle.com>
To:     tglx@...utronix.de
Cc:     mingo@...hat.com, hpa@...or.com, x86@...nel.org, bp@...e.de,
        konrad.wilk@...cle.com, dwmw@...zon.co.uk,
        Jim Mattson <jmattson@...gle.com>,
        linux-kernel@...r.kernel.org, Peter Feiner <pfeiner@...gle.com>
Subject: Re: [PATCH] proc: added ept_ad flag to /proc/cpuinfo

Thank you Thomas. Wording issues understood and will post a new patch
with updated subject.

Re goals: purpose is to expose feature bit with side effect of
"ept_ad" in /proc/cpuinfo and is not necessarily related to VMX code.
We are upstreaming some internal patches that we think would be
generally useful and I will be careful from now on to remove any
wording that is not publicly relevant.

On Mon, Jul 30, 2018 at 3:12 PM Thomas Gleixner <tglx@...utronix.de> wrote:
>
> On Mon, 30 Jul 2018, Peter Shier wrote:
>
> > Subject: [PATCH] proc: added ept_ad flag to /proc/cpuinfo
>
> The 'proc:' prefix is misleading here. x86/cpufeatures is the right
> choice. The /proc/cpuinfo display is a side effect.
>
> Also please avoid 'added'. Changelogs should be written in imperative
> mood. Something like this:
>
>  x86/cpufeatures: Add EPT_AD feature bit
>
> > The Intel Haswell architecture has an EPT feature whereby the access &
> > dirty bits in EPT entries are updated without taking a guest exit.
>
> Why would this be Haswell specific?
>
> Aside of that I don't see what this has to do with exits. From the SDM:
>
>   " * If bit 21 is read as 1, accessed and dirty flags for EPT are
>       supported (see Section 28.2.4)"
>
> And nothing in 28.2.4 says anything about exits. It's all about whether the
> feature is supported or not. If it is supported it can be enabled in EPTP.
>
> > This patch adds the "ept_ad" flag to /proc/cpuinfo if this feature is
> > available.
>
> See Documentation/process/submitting-patches.rst and search for 'This
> patch'.
>
> The other question is why is this new feature bit not used in the VMX code?
> It needs to be checked to enable the AD bit in EPTP ....
>
> Thanks,
>
>         tglx