From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S935249AbdEVPD0 (ORCPT ); Mon, 22 May 2017 11:03:26 -0400 Received: from mx2.suse.de ([195.135.220.15]:45149 "EHLO mx1.suse.de" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S935020AbdEVPDY (ORCPT ); Mon, 22 May 2017 11:03:24 -0400 Date: Mon, 22 May 2017 17:03:22 +0200 From: Michal Hocko To: Mikulas Patocka Cc: Junaid Shahid , David Rientjes , Alasdair Kergon , Mike Snitzer , Andrew Morton , linux-mm@kvack.org, andreslc@google.com, gthelen@google.com, vbabka@suse.cz, linux-kernel@vger.kernel.org Subject: Re: [PATCH] dm ioctl: Restore __GFP_HIGH in copy_params() Message-ID: <20170522150321.GM8509@dhcp22.suse.cz> References: <20170518185040.108293-1-junaids@google.com> <20170518190406.GB2330@dhcp22.suse.cz> <1508444.i5EqlA1upv@js-desktop.svl.corp.google.com> <20170519074647.GC13041@dhcp22.suse.cz> <20170522093725.GF8509@dhcp22.suse.cz> <20170522120937.GI8509@dhcp22.suse.cz> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: 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 Mon 22-05-17 10:52:44, Mikulas Patocka wrote: > > > On Mon, 22 May 2017, Michal Hocko wrote: [...] > > I am not sure I understand. OOM killer is invoked for _all_ allocations > > <= PAGE_ALLOC_COSTLY_ORDER that do not have __GFP_NORETRY as long as the > > OOM killer is not disabled (oom_killer_disable) and that only happens > > from the PM suspend path which makes sure that no userspace is active at > > the time. AFAIU this is a userspace triggered path and so the later > > shouldn't apply to it and GFP_KERNEL should be therefore sufficient. > > Relying to a portion of memory reserves to prevent from deadlock seems > > fundamentaly broken to me. > > > > The lvm2 was designed this way - it is broken, but there is not much that > can be done about it - fixing this would mean major rewrite. The only > thing we can do about it is to lower the deadlock probability with > __GFP_HIGH (or PF_MEMALLOC that was used some times ago). But let me repeat. GFP_KERNEL allocation for order-0 page will not fail. If you need non-failing semantic then just make it clear by adding __GFP_NOFAIL rather than __GFP_HIGH. Memory reserves are a scarce resource and there are users which might really need it from atomic contexts. Anyway, this is not the code I am maintaining so I will not argue more and won't nack the patch. But is smells like a pure cargo cult, to be honest. If you really insist, though, I would just ask to have a more detailed explanation why it is _believed_ the flag is needed because the vague "Use __GFP_HIGH to avoid low memory issues when a device is suspended and the ioctl is needed to resume it." doesn't really clarify much to be honest. Thanks! -- Michal Hocko SUSE Labs