From mboxrd@z Thu Jan  1 00:00:00 1970
Received: from eggs.gnu.org ([2001:4830:134:3::10]:55109)
	by lists.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1Vlxv2-0008Bq-UL
	for qemu-devel@nongnu.org; Thu, 28 Nov 2013 04:30:02 -0500
Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1Vlxuw-0002Fp-Rq
	for qemu-devel@nongnu.org; Thu, 28 Nov 2013 04:29:56 -0500
Received: from mx1.redhat.com ([209.132.183.28]:61281)
	by eggs.gnu.org with esmtp (Exim 4.71)
	(envelope-from <pbonzini@redhat.com>) id 1Vlxuw-0002FY-A3
	for qemu-devel@nongnu.org; Thu, 28 Nov 2013 04:29:50 -0500
Message-ID: <52970D00.9060109@redhat.com>
Date: Thu, 28 Nov 2013 10:29:36 +0100
From: Paolo Bonzini <pbonzini@redhat.com>
MIME-Version: 1.0
References: <52949847.6020908@redhat.com>
	<CAEbWaipAnmoa=gMbB1aNb=btU6LgYXhcnmQWHJ_89m4yvw6Dug@mail.gmail.com>
	<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>
In-Reply-To: <20131128091903.GA4609@kernel.org>
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 7bit
Subject: Re: [Qemu-devel] [RFC] create a single workqueue for each vm to
 update vm irq routing table
List-Id: <qemu-devel.nongnu.org>
List-Unsubscribe: <https://lists.nongnu.org/mailman/options/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=unsubscribe>
List-Archive: <http://lists.nongnu.org/archive/html/qemu-devel>
List-Post: <mailto:qemu-devel@nongnu.org>
List-Help: <mailto:qemu-devel-request@nongnu.org?subject=help>
List-Subscribe: <https://lists.nongnu.org/mailman/listinfo/qemu-devel>,
	<mailto:qemu-devel-request@nongnu.org?subject=subscribe>
To: Gleb Natapov <gleb@minantech.com>
Cc: Avi Kivity <avi@cloudius-systems.com>, "Huangweidong (C)" <weidong.huang@huawei.com>, Gleb Natapov <gleb@redhat.com>, KVM <kvm@vger.kernel.org>, "Michael S. Tsirkin" <mst@redhat.com>, "Zhanghaoyu (A)" <haoyu.zhang@huawei.com>, Luonengjun <luonengjun@huawei.com>, "qemu-devel@nongnu.org" <qemu-devel@nongnu.org>, Zanghongyong <zanghongyong@huawei.com>, Avi Kivity <avi.kivity@gmail.com>, "Jinxin (F)" <jinxin712@huawei.com>

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.

Paolo

 Seems to me
> it would be fragile for an OS to depend on this behaviour. AFAIK Linux does not.