From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752089AbXEaNbA (ORCPT ); Thu, 31 May 2007 09:31:00 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1751192AbXEaNax (ORCPT ); Thu, 31 May 2007 09:30:53 -0400 Received: from ebiederm.dsl.xmission.com ([166.70.28.69]:50207 "EHLO ebiederm.dsl.xmission.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751035AbXEaNaw (ORCPT ); Thu, 31 May 2007 09:30:52 -0400 From: ebiederm@xmission.com (Eric W. Biederman) To: Andi Kleen Cc: Andrew Morton , "Siddha, Suresh B" , mingo@elte.hu, linux-kernel@vger.kernel.org, nanhai.zou@intel.com, asit.k.mallick@intel.com, keith.packard@intel.com, "Yinghai Lu" Subject: Re: [PATCH] x86_64 irq: check remote IRR bit before migrating level triggered irq (v2) References: <20070517230324.GB8089@linux-os.sc.intel.com> <200705311401.02221.ak@suse.de> Date: Thu, 31 May 2007 07:29:43 -0600 In-Reply-To: <200705311401.02221.ak@suse.de> (Andi Kleen's message of "Thu, 31 May 2007 14:01:02 +0200") Message-ID: User-Agent: Gnus/5.110006 (No Gnus v0.6) Emacs/21.4 (gnu/linux) MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Sender: linux-kernel-owner@vger.kernel.org X-Mailing-List: linux-kernel@vger.kernel.org Andi Kleen writes: > On Thursday 31 May 2007 13:34:21 Eric W. Biederman wrote: >> >> On x86_64 kernel, level triggered irq migration gets initiated in the context >> of that interrupt(after executing the irq handler) and following steps are >> followed to do the irq migration. > > What's the confidence level in the patch? Is it a .22 candidate? Yes. I just ran it for a little while and nothing fell over, and level triggered irqs continued to migrate. So it's not horribly broken. Outside of implementation errors the worst case that can happen with this code is the current behavior, with a small slow down. So since I can not reproduce the original problem I would appreciate an eyeball or two more just to make certain I reimplemented this correctly and didn't do anything stupid. But I don't expect anything to be found. The code is pretty straight forward. Eric