From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1753819AbdK1TAC (ORCPT ); Tue, 28 Nov 2017 14:00:02 -0500 Received: from foss.arm.com ([217.140.101.70]:58488 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751418AbdK1S77 (ORCPT ); Tue, 28 Nov 2017 13:59:59 -0500 Date: Tue, 28 Nov 2017 19:00:01 +0000 From: Will Deacon To: Michal Hocko Cc: linux-mm@kvack.org, Minchan Kim , Andrea Argangeli , Ingo Molnar , Andrew Morton , Linus Torvalds , LKML , linux-arch@vger.kernel.org, Michal Hocko Subject: Re: [RFC PATCH] arch, mm: introduce arch_tlb_gather_mmu_exit Message-ID: <20171128190001.GD8187@arm.com> References: <20171123090236.18574-1-mhocko@kernel.org> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20171123090236.18574-1-mhocko@kernel.org> User-Agent: Mutt/1.5.23 (2014-03-12) Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On Thu, Nov 23, 2017 at 10:02:36AM +0100, Michal Hocko wrote: > From: Michal Hocko > > 5a7862e83000 ("arm64: tlbflush: avoid flushing when fullmm == 1") has > introduced an optimization to not flush tlb when we are tearing the > whole address space down. Will goes on to explain > > : Basically, we tag each address space with an ASID (PCID on x86) which > : is resident in the TLB. This means we can elide TLB invalidation when > : pulling down a full mm because we won't ever assign that ASID to > : another mm without doing TLB invalidation elsewhere (which actually > : just nukes the whole TLB). > > This all is nice but tlb_gather users are not aware of that and this can > actually cause some real problems. E.g. the oom_reaper tries to reap the > whole address space but it might race with threads accessing the memory [1]. > It is possible that soft-dirty handling might suffer from the same > problem [2] as soon as it starts supporting the feature. > > Introduce an explicit exit variant tlb_gather_mmu_exit which allows the > behavior arm64 implements for the fullmm case and replace it by an > explicit exit flag in the mmu_gather structure. exit_mmap path is then > turned into the explicit exit variant. Other architectures simply ignore > the flag. > > [1] http://lkml.kernel.org/r/20171106033651.172368-1-wangnan0@huawei.com > [2] http://lkml.kernel.org/r/20171110001933.GA12421@bbox > Signed-off-by: Michal Hocko > --- > Hi, > I am sending this as an RFC because I am not fully familiar with the tlb > gather arch implications, espacially the semantic of fullmm. Therefore > I might duplicate some of its functionality. I hope people on the CC > list will help me to sort this out. > > Comments? Objections? I can't think of a case where we'd have exit set but not be doing the fullmm, in which case I'd be inclined to remove the last two parameters from tlb_gather_mmu_exit. Will