From mboxrd@z Thu Jan  1 00:00:00 1970
From: Qing He <qing.he@intel.com>
Subject: Re: [PATCH 0/6] MSI-INTx interrupt translation for HVM
Date: Mon, 2 Mar 2009 17:24:40 +0800
Message-ID: <20090302092440.GA22064@ub-qhe2>
References: <20090302161339.8372.CB716985@necst.nec.co.jp>
	<C5D14DB9.3DB4%keir.fraser@eu.citrix.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Return-path: <xen-devel-bounces@lists.xensource.com>
Content-Disposition: inline
In-Reply-To: <C5D14DB9.3DB4%keir.fraser@eu.citrix.com>
List-Unsubscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=unsubscribe>
List-Post: <mailto:xen-devel@lists.xensource.com>
List-Help: <mailto:xen-devel-request@lists.xensource.com?subject=help>
List-Subscribe: <http://lists.xensource.com/mailman/listinfo/xen-devel>,
	<mailto:xen-devel-request@lists.xensource.com?subject=subscribe>
Sender: xen-devel-bounces@lists.xensource.com
Errors-To: xen-devel-bounces@lists.xensource.com
To: Keir Fraser <keir.fraser@eu.citrix.com>
Cc: "xen-devel@lists.xensource.com" <xen-devel@lists.xensource.com>, Shohei Fujiwara <fujiwara-sxa@necst.nec.co.jp>
List-Id: xen-devel@lists.xenproject.org

On Mon, 2009-03-02 at 16:47 +0800, Keir Fraser wrote:
> On 02/03/2009 07:19, "Shohei Fujiwara" <fujiwara-sxa@necst.nec.co.jp> wrote:
> 
> > Today, I found the hypervisor issues EOI ASAP. So Qing's explanation
> > reflected the implementation of the hypervisor.
> > 
> > xen/drivers/passthrough/io.c:
> > void hvm_dirq_assist(struct vcpu *v)
> > {
> > ...
> >             if ( hvm_irq_dpci->mirq[irq].flags & HVM_IRQ_DPCI_TRANSLATE )
> >             {
> >                 /* for translated MSI to INTx interrupt, eoi as early as
> > possible */
> >                 __msi_pirq_eoi(d, irq);
> >             }
> 
> Ah, well the passthrough-specific logic is not something I'm so familiar
> with! That above code indeed doesn't look correct. :-)

I recently learned that some device may keep issuing MSI until it is explicitly
cleared by software. In that case it just behaves like level-triggered
interrupt, and doing something like the code above will cause interrupt storm.
This is reflected in cs. 19065.

Do you mean this issue?

Thanks,
Qing


> 
>  -- Keir
> 
>