Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752081AbdHDJ2R (ORCPT ); Fri, 4 Aug 2017 05:28:17 -0400 Received: from merlin.infradead.org ([205.233.59.134]:47964 "EHLO merlin.infradead.org" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751292AbdHDJ2P (ORCPT ); Fri, 4 Aug 2017 05:28:15 -0400 Date: Fri, 4 Aug 2017 11:27:54 +0200 From: Peter Zijlstra To: "Huang, Ying" Cc: Eric Dumazet , linux-kernel@vger.kernel.org, Ingo Molnar , Michael Ellerman , Borislav Petkov , Thomas Gleixner , Juergen Gross , Aaron Lu Subject: Re: [PATCH 3/3] IPI: Avoid to use 2 cache lines for one call_single_data Message-ID: <20170804092754.hyhbhyr2r4gonpu4@hirez.programming.kicks-ass.net> References: <20170802085220.4315-1-ying.huang@intel.com> <20170802085220.4315-4-ying.huang@intel.com> <1501669138.25002.20.camel@edumazet-glaptop3.roam.corp.google.com> <87d18d122e.fsf@yhuang-dev.intel.com> <20170803085752.yrqox3kwrvkj544a@hirez.programming.kicks-ass.net> <87wp6kyvda.fsf@yhuang-dev.intel.com> <87mv7gytmk.fsf@yhuang-dev.intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <87mv7gytmk.fsf@yhuang-dev.intel.com> User-Agent: NeoMutt/20170609 (1.8.3) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 1453 Lines: 46 On Fri, Aug 04, 2017 at 10:05:55AM +0800, Huang, Ying wrote: > "Huang, Ying" writes: > > Peter Zijlstra writes: > >> +struct __call_single_data { > >> struct llist_node llist; > >> smp_call_func_t func; > >> void *info; > >> unsigned int flags; > >> }; > >> > >> +typedef struct __call_single_data call_single_data_t > >> + __aligned(sizeof(struct __call_single_data)); > >> + > > > > Another requirement of the alignment is that it should be the power of > > 2. Otherwise, for example, if someone adds a field to struct, so that > > the size becomes 40 on x86_64. The alignment should be 64 instead of > > 40. > > Thanks Aaron, he reminded me that there is a roundup_pow_of_two(). So > the typedef could be, > > typedef struct __call_single_data call_single_data_t > __aligned(roundup_pow_of_two(sizeof(struct __call_single_data)); > Yes, that would take away the requirement to play padding games with the struct. Then again, maybe its a good thing to have to be explicit about it. If you see: struct __call_single_data { struct llist_node llist; smp_call_func_t func; void *info int flags; void *extra_field; unsigned long __padding[3]; /* make align work */ }; that makes it very clear what is going on. In any case, we can delay this part because the current structure is a power-of-2 for both ILP32 and LP64. So only the person growing this will have to deal with it ;-)