From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755198AbeDCImQ (ORCPT ); Tue, 3 Apr 2018 04:42:16 -0400 Received: from bombadil.infradead.org ([198.137.202.133]:58206 "EHLO bombadil.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1755133AbeDCImP (ORCPT ); Tue, 3 Apr 2018 04:42:15 -0400 Date: Tue, 3 Apr 2018 10:42:01 +0200 From: Peter Zijlstra To: Martin Schwidefsky Cc: Frederic Weisbecker , LKML , Sebastian Andrzej Siewior , Tony Luck , "David S . Miller" , Michael Ellerman , Helge Deller , Benjamin Herrenschmidt , Paul Mackerras , Thomas Gleixner , Ingo Molnar , Fenghua Yu , "James E . J . Bottomley" , heiko.carstens@de.ibm.com Subject: Re: [PATCH 10/10] softirq: Remove __ARCH_SET_SOFTIRQ_PENDING Message-ID: <20180403084201.GX4082@hirez.programming.kicks-ass.net> References: <1522290425-22844-1-git-send-email-frederic@kernel.org> <1522290425-22844-11-git-send-email-frederic@kernel.org> <20180329071619.GO4082@hirez.programming.kicks-ass.net> <20180329134745.GA12958@lerouge> <20180329140111.GC4043@hirez.programming.kicks-ass.net> <20180329140748.GB12958@lerouge> <20180329165343.39f4486f@mschwideX1> <20180329180836.GS4082@hirez.programming.kicks-ass.net> <20180403075225.69ad3d25@mschwideX1> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20180403075225.69ad3d25@mschwideX1> User-Agent: Mutt/1.9.3 (2018-01-21) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Tue, Apr 03, 2018 at 07:52:25AM +0200, Martin Schwidefsky wrote: > On Thu, 29 Mar 2018 20:08:36 +0200 > Peter Zijlstra wrote: > > > On Thu, Mar 29, 2018 at 04:53:43PM +0200, Martin Schwidefsky wrote: > > > The lowcore optimization for softirq_pending field is not really needed, > > > just nice to have. But if there is a strong reason to make a common > > > definition for it we can certainly do that. > > > > A slightly related question; would it make sense to move all kernel > > static per-cpu stuff into lowcore, or is that asking for too much > > trickery? > > The space in lowcore is quite limited, for zArch the structure is 8K with > many pre-defined fields. I fear that putting all of the static per-cpu > stuff in there is too much. > > So far I used the lowcore as optimization for selected per-cpu fields > which are performance relevant. Fair enough; and yes 8k isn't much. Thanks for the info.