Return-Path: Received: from ozlabs.org (ozlabs.org [103.22.144.67]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 332101A0EA7 for ; Thu, 22 Jan 2015 16:29:29 +1100 (AEDT) Message-ID: <1421904568.4598.5.camel@ellerman.id.au> Subject: Re: offlining cpus breakage From: Michael Ellerman To: Preeti U Murthy Date: Thu, 22 Jan 2015 16:29:28 +1100 In-Reply-To: <54B8D56D.3070904@linux.vnet.ibm.com> References: <54ACFE6D.3070308@ozlabs.ru> <54B7BEF9.8090603@linux.vnet.ibm.com> <54B85B3C.1030000@ozlabs.ru> <1421377482.18166.5.camel@ellerman.id.au> <54B8D228.4000407@linux.vnet.ibm.com> <54B8D56D.3070904@linux.vnet.ibm.com> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Cc: Alexey Kardashevskiy , "Shreyas B. Prabhu" , "linuxppc-dev@lists.ozlabs.org" , Anton Blanchard , Paul Mackerras List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , On Fri, 2015-01-16 at 14:40 +0530, Preeti U Murthy wrote: > On 01/16/2015 02:26 PM, Preeti U Murthy wrote: > > On 01/16/2015 08:34 AM, Michael Ellerman wrote: > >> On Fri, 2015-01-16 at 13:28 +1300, Alexey Kardashevskiy wrote: > >>> On 01/16/2015 02:22 AM, Preeti U Murthy wrote: > >>>> Hi Alexey, > >>>> > >>>> Can you let me know if the following patch fixes the issue for you ? > >>>> It did for us on one of our machines that we were investigating on. > >>> > >>> This fixes the issue for me as well, thanks! > >>> > >>> Tested-by: Alexey Kardashevskiy > >> > >> OK, that's great. > >> > >> But, I really don't think we can ask upstream to merge this patch to generic > >> code when we don't have a good explanation for why it's necessary. At least I'm > >> not going to ask anyone to do that :) > >> > >> So Pretti can you either write a 100% convincing explanation of why this patch > >> is correct in the general case, or (preferably) do some more investigating to > >> work out what Alexey's bug actually is. > > > > Yes will do so. Its better to investigate where precisely is the bug. > > This patch helped me narrow down on the buggy scenario. > > On a side note, while I was tracking the race condition, I noticed that > in the final stage of the cpu offline path, after the state of the > hotplugged cpu is set to CPU_DEAD, we check if there were interrupts > delivered during the soft disabled state and service them if there were. > It makes sense to check for pending interrupts in the idle path. In the > offline path however, this did not look right to me at first glance. Am > I missing something ? That does sound a bit fishy. I guess we're just assuming that all interrupts have been migrated away prior to the offline? cheers