Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S969731AbdDSVoE (ORCPT ); Wed, 19 Apr 2017 17:44:04 -0400 Received: from mga03.intel.com ([134.134.136.65]:37829 "EHLO mga03.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1763192AbdDSVoB (ORCPT ); Wed, 19 Apr 2017 17:44:01 -0400 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.37,222,1488873600"; d="scan'208";a="1121502593" Date: Wed, 19 Apr 2017 17:53:09 -0400 From: Keith Busch To: Andrei Vagin Cc: linux-kernel@vger.kernel.org, Thomas Gleixner , Xiaolong Ye Subject: Re: irq/affinity: Fix extra vecs calculation Message-ID: <20170419215308.GF16224@localhost.localdomain> References: <1492104492-19943-1-git-send-email-keith.busch@intel.com> <20170419162027.GA7428@outlook.office365.com> <20170419170359.GE16224@localhost.localdomain> <20170419195343.GA24395@outlook.office365.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20170419195343.GA24395@outlook.office365.com> User-Agent: Mutt/1.7.0 (2016-08-17) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1295 Lines: 30 On Wed, Apr 19, 2017 at 12:53:44PM -0700, Andrei Vagin wrote: > On Wed, Apr 19, 2017 at 01:03:59PM -0400, Keith Busch wrote: > > If it's a divide by 0 as your last link indicates, that must mean there > > are possible nodes, but have no CPUs, and those should be skipped. If > > that's the case, the following should fix it, but I'm going to do some > > more qemu testing with various CPU topologies to confirm. > > I printed variables from my test host, I think this can help to > investigate the issue: > > irq_create_affinity_masks:116: vecs_to_assign 0 ncpus 2 extra_vecs 2 vecs_per_node 0 affv 2 curvec 2 nodes 1 That explains a lot. This setup wants 2 "pre_vectors", but I didn't know that was even a thing. This should fix it: --- diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c index d052947..eb8b689 100644 --- a/kernel/irq/affinity.c +++ b/kernel/irq/affinity.c @@ -98,13 +98,16 @@ irq_create_affinity_masks(int nvecs, const struct irq_affinity *affd) int ncpus, v, vecs_to_assign, vecs_per_node; /* Spread the vectors per node */ - vecs_per_node = (affv - curvec) / nodes; + vecs_per_node = (affv - (curvec - affd->pre_vectors)) / nodes; /* Get the cpus on this node which are in the mask */ cpumask_and(nmsk, cpu_online_mask, cpumask_of_node(n)); --