From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753419Ab0FXHEg (ORCPT ); Thu, 24 Jun 2010 03:04:36 -0400 Received: from mga11.intel.com ([192.55.52.93]:34090 "EHLO mga11.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751398Ab0FXHEf (ORCPT ); Thu, 24 Jun 2010 03:04:35 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.53,472,1272870000"; d="scan'208";a="811010440" Subject: Re: [RFC][PATCH] irq_work From: Huang Ying To: Peter Zijlstra Cc: Ingo Molnar , "H.PeterA" <"nvin hpa"@zytor.com>, "linux-kernel@vger.kernel.org" , Andi Kleen In-Reply-To: <1277362680.1875.845.camel@laptop> References: <1277348698-17311-1-git-send-email-ying.huang@intel.com> <1277361352.1875.838.camel@laptop> <1277361791.3947.11.camel@yhuang-dev.sh.intel.com> <1277362073.1875.839.camel@laptop> <1277362243.3947.20.camel@yhuang-dev.sh.intel.com> <1277362680.1875.845.camel@laptop> Content-Type: text/plain; charset="UTF-8" Date: Thu, 24 Jun 2010 15:04:29 +0800 Message-ID: <1277363069.3947.30.camel@yhuang-dev.sh.intel.com> Mime-Version: 1.0 X-Mailer: Evolution 2.30.1.2 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, 2010-06-24 at 14:58 +0800, Peter Zijlstra wrote: > On Thu, 2010-06-24 at 14:50 +0800, Huang Ying wrote: > > On Thu, 2010-06-24 at 14:47 +0800, Peter Zijlstra wrote: > > > On Thu, 2010-06-24 at 14:43 +0800, Huang Ying wrote: > > > > Hi, Peter, > > > > > > > I fact I uses exactly the similar method in my patches, just trigger it > > > > with soft_irq instead of IRQ. Please take a look at > > > > nmi_return_notifier_schedule in > > > > > > But then why still use softirq? Once you have this its completely > > > useless. > > > > Some systems have no self interrupt, for example the system without > > APIC. We need to provide a fallback for them. soft_irq can help here. > > So there's systems that don't have self-ipi but do have NMI context? Yes. NMI is there from 8259 age. > Can't we run the callbacks from the tick or something for such legacy > muck? I really don't like the whole softirq mess. That is possible. But in NO_HZ system, we have no tick to rely on. soft_irq is better here, because it will be triggered for any interrupt. Best Regards, Huang Ying