From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1757613AbbA0Is4 (ORCPT ); Tue, 27 Jan 2015 03:48:56 -0500 Received: from bombadil.infradead.org ([198.137.202.9]:44919 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751553AbbA0Isx (ORCPT ); Tue, 27 Jan 2015 03:48:53 -0500 Date: Tue, 27 Jan 2015 09:48:42 +0100 From: Peter Zijlstra To: Sasha Levin Cc: Kirill Tkhai , linux-kernel@vger.kernel.org, Oleg Nesterov , Ingo Molnar , Burke Libbey , Vladimir Davydov , Kirill Tkhai Subject: Re: [PATCH] sched: Fix race between task_group and sched_task_group Message-ID: <20150127084842.GO2896@worktop.programming.kicks-ass.net> References: <1414405105.19914.169.camel@tkhai> <54C6D1C4.4070802@oracle.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <54C6D1C4.4070802@oracle.com> User-Agent: Mutt/1.5.22.1 (2013-10-16) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Mon, Jan 26, 2015 at 06:46:12PM -0500, Sasha Levin wrote: > This seems to cause the following lockdep warning: unlikely, the fork -> sched_move_task() was only used to establish that rq->lock nests inside p->pi_lock, and there's a gazillion other ways to establish that. That said, its a right mess indeed. Let me stare a wee bit more at this rats nets.