From mboxrd@z Thu Jan 1 00:00:00 1970 From: Gleb Natapov Subject: Re: [PATCHv1 dont apply] RFC: kvm eoi PV using shared memory Date: Tue, 17 Apr 2012 11:45:48 +0300 Message-ID: <20120417084548.GZ11918@redhat.com> References: <20120416100807.GO11918@redhat.com> <20120416110919.GA11605@redhat.com> <20120416112446.GQ11918@redhat.com> <20120416121824.GD11605@redhat.com> <20120416123047.GS11918@redhat.com> <20120416131328.GF11605@redhat.com> <20120416151011.GB18613@redhat.com> <20120416163327.GB18914@redhat.com> <20120416175116.GB5541@redhat.com> <20120416190128.GB20294@redhat.com> Mime-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: kvm@vger.kernel.org To: "Michael S. Tsirkin" Return-path: Received: from mx1.redhat.com ([209.132.183.28]:2689 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755810Ab2DQJKk (ORCPT ); Tue, 17 Apr 2012 05:10:40 -0400 Received: from int-mx12.intmail.prod.int.phx2.redhat.com (int-mx12.intmail.prod.int.phx2.redhat.com [10.5.11.25]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id q3H9AdNV012561 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK) for ; Tue, 17 Apr 2012 05:10:40 -0400 Content-Disposition: inline In-Reply-To: <20120416190128.GB20294@redhat.com> Sender: kvm-owner@vger.kernel.org List-ID: On Mon, Apr 16, 2012 at 10:01:29PM +0300, Michael S. Tsirkin wrote: > On Mon, Apr 16, 2012 at 08:51:16PM +0300, Gleb Natapov wrote: > > > > Only when eoi is pending. This is rare. > > > > > > This is exactly while guest handles an interrupt. > > > It's not all that rare at all: e.g. device > > > drivers cause an exit from interrupt > > > handler by doing io. > > So eoi will be coalesced with io that device driver does. Exactly what > > we want. > > It won't. While we handle interrupts eoi is still set. > So there will be a couple of tests + read from userspace > Wasted not a huge overhead but it's the principle of the thing. > Linux acks irq before calling device handler. Windows for some devices does IO to a device before acking. -- Gleb.