Subject: Re: [PATCH 00/11] KVM: x86: track guest page access
To: Andrea Arcangeli <aarcange@redhat.com>
References: <1448907973-36066-1-git-send-email-guangrong.xiao@linux.intel.com>
 <565D73BA.8020002@redhat.com> <20151201150242.GB30212@redhat.com>
Cc: Xiao Guangrong <guangrong.xiao@linux.intel.com>, gleb@kernel.org,
        mtosatti@redhat.com, kvm@vger.kernel.org, linux-kernel@vger.kernel.org
From: Paolo Bonzini <pbonzini@redhat.com>
Message-ID: <565DB7EC.8010201@redhat.com>
Date: Tue, 1 Dec 2015 16:08:28 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101
 Thunderbird/38.3.0
MIME-Version: 1.0
In-Reply-To: <20151201150242.GB30212@redhat.com>
Content-Type: text/plain; charset=windows-1252
Content-Transfer-Encoding: 7bit
Sender: linux-kernel-owner@vger.kernel.org
Content-Length: 1216
Lines: 29


On 01/12/2015 16:02, Andrea Arcangeli wrote:
> > Applying your technique to non-leaf shadow pages actually makes this
> > series quite interesting. :)  Shadow paging is still in use for nested
> > EPT, so it's always a good idea to speed it up.
> 
> I don't have the full picture of how userfaultfd write tracking could
> also fit in the leaf/non-leaf shadow pagetable write tracking yet but
> it's good to think about it.

It's unrelated.

Xiao wrote this series for KVM-GT.  I'm suggesting that he uses
userfaultfd write tracking (or similar techniques---but anyway
implemented out of KVM) for KVM-GT.  The benefit is that KVM-GT is then
unrelated to KVM, similar to legacy KVM device assignment vs. VFIO.

However, he also applied this new API to shadow pagetable write
tracking.  He gets measurable (~2%) performance improvement.  We can
look separately at how to get a similar performance improvement, even if
KVM-GT will not use the new page tracking API.

Paolo
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/