Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752976Ab3IXIVq (ORCPT ); Tue, 24 Sep 2013 04:21:46 -0400 Received: from merlin.infradead.org ([205.233.59.134]:41103 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1750738Ab3IXIVo (ORCPT ); Tue, 24 Sep 2013 04:21:44 -0400 Date: Tue, 24 Sep 2013 10:21:28 +0200 From: Peter Zijlstra To: Benjamin Herrenschmidt Cc: Linus Torvalds , "H. Peter Anvin" , Frederic Weisbecker , Thomas Gleixner , LKML , Paul Mackerras , Ingo Molnar , James Hogan , "James E.J. Bottomley" , Helge Deller , Martin Schwidefsky , Heiko Carstens , "David S. Miller" , Andrew Morton , Anton Blanchard Subject: Re: [RFC GIT PULL] softirq: Consolidation and stack overrun fix Message-ID: <20130924082128.GJ9326@twins.programming.kicks-ass.net> References: <1379824754.24090.11.camel@pasglop> <1379824861.24090.12.camel@pasglop> <20130922162410.GA10649@laptop.programming.kicks-ass.net> <1379887000.24090.19.camel@pasglop> <1379981427.5443.8.camel@pasglop> <1379987527.5443.20.camel@pasglop> <20130924080436.GH9326@twins.programming.kicks-ass.net> <1380010613.5443.40.camel@pasglop> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <1380010613.5443.40.camel@pasglop> User-Agent: Mutt/1.5.21 (2012-12-30) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1144 Lines: 21 On Tue, Sep 24, 2013 at 06:16:53PM +1000, Benjamin Herrenschmidt wrote: > On Tue, 2013-09-24 at 10:04 +0200, Peter Zijlstra wrote: > > On Tue, Sep 24, 2013 at 11:52:07AM +1000, Benjamin Herrenschmidt wrote: > > > So if that holds, we have a solid way to do per-cpu. On one side, I tend > > > to think that r13 being task/thread/thread_info is probably a better > > > overall choice, I'm worried that going in a different direction than x86 > > > means generic code will get "tuned" to use per-cpu for performance > > > critical stuff rather than task/thread/thread_info in inflexible ways. > > > > The plus side of per-cpu over per-task is that one typically has a lot > > less cpus than tasks. Also, its far easier/cheaper to iterate cpus than > > it is to iterate tasks. > > I don't see how that relates to the above though... It was a comment on the increase of per-cpu usage in generic code. -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/