From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S934926AbXGYSal (ORCPT ); Wed, 25 Jul 2007 14:30:41 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S932999AbXGYSaM (ORCPT ); Wed, 25 Jul 2007 14:30:12 -0400 Received: from gprs189-60.eurotel.cz ([160.218.189.60]:3019 "EHLO spitz.ucw.cz" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1761083AbXGYSaK (ORCPT ); Wed, 25 Jul 2007 14:30:10 -0400 Date: Wed, 25 Jul 2007 14:18:14 +0000 From: Pavel Machek To: Alan Cox Cc: Dor Laor , Avi Kivity , kvm-devel@lists.sourceforge.net, linux-kernel@vger.kernel.org, Greg KH Subject: Re: [kvm-devel] [RFC] Deferred interrupt handling. Message-ID: <20070725141813.GE9256@ucw.cz> References: <005901c7c921$79c006c0$6d401440$@com> <20070718123040.615795b7@the-village.bc.nu> <64F9B87B6B770947A9F8391472E032160CC16C92@ehost011-8.exch011.intermedia.net> <20070718174736.0baf6d0e@the-village.bc.nu> <469E43D5.70802@qumranet.com> <64F9B87B6B770947A9F8391472E032160CC16D06@ehost011-8.exch011.intermedia.net> <20070718183358.0a0886aa@the-village.bc.nu> <64F9B87B6B770947A9F8391472E032160CC16F3C@ehost011-8.exch011.intermedia.net> <20070718224649.3e49a978@the-village.bc.nu> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20070718224649.3e49a978@the-village.bc.nu> User-Agent: Mutt/1.5.9i Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Hi! I guess this will also allow UIO to work without _any_ kernel parts, with only slight performance penalty in 'almost-never-happens' deadlock case? (Greg, details are below, and better description is in the lkml thread). Pavel > > - Our dummy handler will always return IRQ_HANDLED in case any other > > previous > > irqaction did not return such. It will also issue the timer and mask > > the irq in this case. > > Ok > > > btw, if I'm not mistaken only after bad 99900/100000 the irq is > > disabled. > > (and with GIT providing that they occurred in a short time period) > > > - If the timer pops before the guest acks the irq, the timer handler > > will > > ack the irq and unmask it. The timer's job is only to prevent > > deadlocks. > > Ok I see what you are doing. It's either inspired or insane and I am not > quite sure which of the two. I agree it should work although may cause > performance crunches now and then and will also need care getting the > locking right. -- (english) http://www.livejournal.com/~pavelmachek (cesky, pictures) http://atrey.karlin.mff.cuni.cz/~pavel/picture/horses/blog.html