From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753519Ab3GHEhI (ORCPT ); Mon, 8 Jul 2013 00:37:08 -0400 Received: from one.firstfloor.org ([193.170.194.197]:51348 "EHLO one.firstfloor.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750793Ab3GHEhG (ORCPT ); Mon, 8 Jul 2013 00:37:06 -0400 Date: Mon, 8 Jul 2013 06:37:03 +0200 From: Andi Kleen To: Rusty Russell Cc: Bjorn Helgaas , Alexander Duyck , "linux-pci@vger.kernel.org" , "linux-kernel@vger.kernel.org" , Andi Kleen , Greg Kroah-Hartman Subject: Re: [PATCH] pci: Avoid unnecessary calls to work_on_cpu Message-ID: <20130708043703.GT6123@two.firstfloor.org> References: <20130624195942.40795.27292.stgit@ahduyck-cp1.jf.intel.com> <87wqp1esff.fsf@rustcorp.com.au> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <87wqp1esff.fsf@rustcorp.com.au> User-Agent: Mutt/1.5.20 (2009-06-14) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org > > But Rusty added this (in 873392ca51), and he knows way more about this > > stuff than I do. > > Actually, I just stopped the code from playing cpumask games, which is > what it used to do. You're right the numa_node_id() check ptimization is not 100% safe on preempt kernels and should be probably removed. Also I agree it would probably make sense to move it up to the generic device layer (although I'm not sure that other bus types really care that much about NUMA locality) None of it seems to be a fatal problem though, so it boils down to "if someone cares enough to write a patch" -Andi