From mboxrd@z Thu Jan  1 00:00:00 1970
From: Gleb Natapov <gleb@minantech.com>
Subject: Re: [Qemu-devel] [RFC] create a single workqueue for each vm to
 update vm irq routing table
Date: Thu, 28 Nov 2013 11:43:14 +0200
Message-ID: <20131128094313.GA5822@minantech.com>
References: <5294A68F.6060301@redhat.com>
 <CAF950W+-UiX6xv4vYmnxji9aWDU8ds2rnx7JugnbHQWJdCCD-Q@mail.gmail.com>
 <5294B461.5000405@redhat.com>
 <5294B634.4050801@cloudius-systems.com>
 <20131126150357.GA20352@redhat.com>
 <5294BC3B.6070902@redhat.com>
 <D3E216785288A145B7BC975F83A2ED10448BBAB3@SZXEMA510-MBS.china.huawei.com>
 <5297050E.6000700@redhat.com>
 <20131128091903.GA4609@kernel.org>
 <52970D00.9060109@redhat.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Cc: "Zhanghaoyu (A)" <haoyu.zhang@huawei.com>,
	Avi Kivity <avi@cloudius-systems.com>,
	Avi Kivity <avi.kivity@gmail.com>,
	"Huangweidong (C)" <weidong.huang@huawei.com>,
	KVM <kvm@vger.kernel.org>, "Michael S. Tsirkin" <mst@redhat.com>,
	"Jinxin (F)" <jinxin712@huawei.com>,
	Luonengjun <luonengjun@huawei.com>,
	"qemu-devel@nongnu.org" <qemu-devel@nongnu.org>,
	Zanghongyong <zanghongyong@huawei.com>
To: Paolo Bonzini <pbonzini@redhat.com>
Return-path: <kvm-owner@vger.kernel.org>
Received: from mail-wg0-f44.google.com ([74.125.82.44]:32778 "EHLO
	mail-wg0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
	with ESMTP id S1750841Ab3K1JnS (ORCPT <rfc822;kvm@vger.kernel.org>);
	Thu, 28 Nov 2013 04:43:18 -0500
Received: by mail-wg0-f44.google.com with SMTP id a1so6094527wgh.35
        for <kvm@vger.kernel.org>; Thu, 28 Nov 2013 01:43:17 -0800 (PST)
Content-Disposition: inline
In-Reply-To: <52970D00.9060109@redhat.com>
Sender: kvm-owner@vger.kernel.org
List-ID: <kvm.vger.kernel.org>

On Thu, Nov 28, 2013 at 10:29:36AM +0100, Paolo Bonzini wrote:
> Il 28/11/2013 10:19, Gleb Natapov ha scritto:
> > Not changing current behaviour is certainly safer, but I am still not 100%
> > convinced we have to ensure this.
> > 
> > Suppose guest does:
> > 
> > 1: change msi interrupt by writing to pci register
> > 2: read the pci register to flush the write
> > 3: zero idt
> > 
> > I am pretty certain that this code can get interrupt after step 2 on real HW,
> > but I cannot tell if guest can rely on it to be delivered exactly after
> > read instruction or it can be delayed by couple of instructions.
> 
> I agree it's fragile, but if a dedicated SRCU can meet the requirements
> (possibly with synchronize_srcu_expedited), I prefer not to break it.
> 
Definitely. If we can find reasonable solution that preserves current semantics
it's preferable path to take.

--
			Gleb.