public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Jon Masters <jcm@redhat.com>
To: Peter Maydell <peter.maydell@linaro.org>,
	Mario Smarduch <m.smarduch@samsung.com>
Cc: Laszlo Ersek <lersek@redhat.com>, kvm-devel <kvm@vger.kernel.org>,
	Ard Biesheuvel <ard.biesheuvel@linaro.org>,
	Paolo Bonzini <pbonzini@redhat.com>,
	"kvmarm@lists.cs.columbia.edu" <kvmarm@lists.cs.columbia.edu>
Subject: Re: [PATCH 3/3] arm, arm64: KVM: handle potential incoherency of readonly memslots
Date: Thu, 20 Nov 2014 14:49:54 -0500	[thread overview]
Message-ID: <546E45E2.1030002@redhat.com> (raw)
In-Reply-To: <CAFEAcA-nSTY_k1gvJ8_y9P6wP2MmOgJzobK-rXp1W6XtrPAMbw@mail.gmail.com>

On 11/20/2014 01:40 PM, Peter Maydell wrote:
> On 20 November 2014 18:35, Mario Smarduch <m.smarduch@samsung.com> wrote:
>> I think beyond consistency, there should be no double mappings with
>> conflicting attributes at any time or CPU state is undefined.
> 
> The situation is not so bleak as this. See section B2.9 "Mismatched
> memory attributes" in the ARMv8 ARM ARM (DDI0487A.d), which lays
> out in some detail what the results of mismatched attributes are
> (generally, you lose ordering or coherency guarantees you might
> have hoped to have). They're not pretty, but it's not as bad
> as completely UNPREDICTABLE behaviour.

Quick side note that I did raise exactly this issue with the ARM
Architecture team several years ago (that of missmatched memory
attributes between a guest and hypervisor) and it is a known concern.
I'm personally concerned about a couple of things that I won't go into
here but will followup on what the longer term plan might be.

Jon.



  parent reply	other threads:[~2014-11-20 19:50 UTC|newest]

Thread overview: 24+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2014-11-17 14:58 [PATCH 1/3] kvm: add a memslot flag for incoherent memory regions Ard Biesheuvel
2014-11-17 14:58 ` [PATCH 2/3] arm, arm64: KVM: allow forced dcache flush on page faults Ard Biesheuvel
2014-11-17 14:58 ` [PATCH 3/3] arm, arm64: KVM: handle potential incoherency of readonly memslots Ard Biesheuvel
2014-11-17 15:29   ` Paolo Bonzini
2014-11-17 15:39     ` Marc Zyngier
2014-11-17 16:03       ` Paolo Bonzini
2014-11-17 15:49     ` Laszlo Ersek
2014-11-19 23:32       ` Mario Smarduch
2014-11-20  8:08         ` Laszlo Ersek
2014-11-20 18:35           ` Mario Smarduch
2014-11-20 18:40             ` Peter Maydell
2014-11-20 19:15               ` Mario Smarduch
2014-11-20 19:49               ` Jon Masters [this message]
2014-11-20 20:10                 ` Peter Maydell
2014-11-20 21:13                   ` Laszlo Ersek
2014-11-20 21:59                     ` Peter Maydell
2014-11-21 11:19         ` Christoffer Dall
2014-11-22  1:50           ` Mario Smarduch
2014-11-22 10:18             ` Christoffer Dall
2014-11-22 10:26               ` Laszlo Ersek
2014-11-22 12:27             ` Peter Maydell
2014-11-19  8:51   ` Ard Biesheuvel
2014-11-19 11:02     ` Paolo Bonzini
2014-11-19 11:03     ` Paolo Bonzini

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=546E45E2.1030002@redhat.com \
    --to=jcm@redhat.com \
    --cc=ard.biesheuvel@linaro.org \
    --cc=kvm@vger.kernel.org \
    --cc=kvmarm@lists.cs.columbia.edu \
    --cc=lersek@redhat.com \
    --cc=m.smarduch@samsung.com \
    --cc=pbonzini@redhat.com \
    --cc=peter.maydell@linaro.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox