Received: by 2002:ac0:a582:0:0:0:0:0 with SMTP id m2-v6csp1239023imm; Wed, 10 Oct 2018 11:15:10 -0700 (PDT) X-Google-Smtp-Source: ACcGV60ur2qYb8eCNbBbOoi9v4JdU4ZNy41lHB/O0Qny8Jp4u2/7J/jV+gBoARC6zkQaFripZRwd X-Received: by 2002:a17:902:7442:: with SMTP id e2-v6mr567980plt.314.1539195309892; Wed, 10 Oct 2018 11:15:09 -0700 (PDT) ARC-Seal: i=1; a=rsa-sha256; t=1539195309; cv=none; d=google.com; s=arc-20160816; b=DXa/b7XdywlHSVcrl8p8snOb+q12CQ0DhVqKR2ZbOKiuin+AeQDMjNA2stWGEKV/mz mhbPaK8K/sqV5bCEWFKj80m+DyCJ0zWAzwlRheZs8ym+pbbfC2kNLZa6jGWh6ZPG/2/S LOZliGV6RqaM//AlJtvuJTuxhmqXwjjgC8j4tG69Wtwezbw4CGZKhA9FjoNWktD0r5Dn +vtFaumbjvYpoB4GmzQAztSWrK7OAfx8wQr62guxGqbe47MEuSvxuv8XnoceIxMjQlDo w/258a/qmx4UjDpnk3XB7IX9C6Ca3SQKn9OEnhu0HRWUtiZnzQqiV8TA2hiKlnXmpaUt Y6PA== ARC-Message-Signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=google.com; s=arc-20160816; h=list-id:precedence:sender:content-transfer-encoding :content-language:in-reply-to:mime-version:user-agent:date :message-id:from:references:cc:to:subject; bh=Nm41iB7rDpG+WLbE9R3jONeM6/4rjHfB3hajOWbo6bU=; b=ktfISjki8VnEMtMewB5gPce3GOJJ4Bdp5yGQs21FK1cpnOWRmbECXiSzTBjFkrusbV npAcLZ4cWUZGfk85NVkRPeT5boEucEoF132/KSw3wEH8GyUlz9JSdbQDjUvNFBNyReHx HNIaoEZWdYxpPR7uW99Dc4KwwRfHlsl1rBfIDjOyaefUASXQEP3CW9F3dnxMN7YdYyXi hOnTglYhhKmYDuHAxyNoHBJQRYv5fcmZAIEKqZTtuMOFwQ+S90y+/HsFJo81iFg8pJF1 y3sUyucEvZJDYEI5yCl0Xwp1Vva879qE/1Z3+/HxmnpD+FWC8tDTkCAj5MMrq8b+LfHr G0dw== ARC-Authentication-Results: i=1; mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Return-Path: Received: from vger.kernel.org (vger.kernel.org. [209.132.180.67]) by mx.google.com with ESMTP id i10-v6si25669964pgc.420.2018.10.10.11.14.54; Wed, 10 Oct 2018 11:15:09 -0700 (PDT) Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67; Authentication-Results: mx.google.com; spf=pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) smtp.mailfrom=linux-kernel-owner@vger.kernel.org; dmarc=fail (p=NONE sp=NONE dis=NONE) header.from=intel.com Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1726854AbeJKBgd (ORCPT + 99 others); Wed, 10 Oct 2018 21:36:33 -0400 Received: from mga14.intel.com ([192.55.52.115]:38148 "EHLO mga14.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1726525AbeJKBgc (ORCPT ); Wed, 10 Oct 2018 21:36:32 -0400 X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False Received: from orsmga006.jf.intel.com ([10.7.209.51]) by fmsmga103.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 10 Oct 2018 11:13:15 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.54,365,1534834800"; d="scan'208";a="81546016" Received: from ahduyck-mobl.amr.corp.intel.com (HELO [10.7.198.156]) ([10.7.198.156]) by orsmga006.jf.intel.com with ESMTP; 10 Oct 2018 11:13:12 -0700 Subject: Re: [PATCH v5 4/4] mm: Defer ZONE_DEVICE page initialization to the point where we init pgmap To: Michal Hocko Cc: Dan Williams , Linux MM , Andrew Morton , Linux Kernel Mailing List , linux-nvdimm , Pasha Tatashin , Dave Hansen , =?UTF-8?B?SsOpcsO0bWUgR2xpc3Nl?= , rppt@linux.vnet.ibm.com, Ingo Molnar , "Kirill A. Shutemov" , yi.z.zhang@linux.intel.com References: <20180925200551.3576.18755.stgit@localhost.localdomain> <20180925202053.3576.66039.stgit@localhost.localdomain> <20181009170051.GA40606@tiger-server> <25092df0-b7b4-d456-8409-9c004cb6e422@linux.intel.com> <20181010095838.GG5873@dhcp22.suse.cz> <20181010172451.GK5873@dhcp22.suse.cz> <98c35e19-13b9-0913-87d9-b3f1ab738b61@linux.intel.com> <20181010175354.GO5873@dhcp22.suse.cz> From: Alexander Duyck Message-ID: <086eb8d2-70a4-ead5-2ed2-260e98a0376f@linux.intel.com> Date: Wed, 10 Oct 2018 11:13:12 -0700 User-Agent: Mozilla/5.0 (Windows NT 10.0; WOW64; rv:60.0) Gecko/20100101 Thunderbird/60.2.1 MIME-Version: 1.0 In-Reply-To: <20181010175354.GO5873@dhcp22.suse.cz> Content-Type: text/plain; charset=utf-8; format=flowed Content-Language: en-US Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org On 10/10/2018 10:53 AM, Michal Hocko wrote: > On Wed 10-10-18 10:39:01, Alexander Duyck wrote: >> >> >> On 10/10/2018 10:24 AM, Michal Hocko wrote: >>> On Wed 10-10-18 09:39:08, Alexander Duyck wrote: >>>> On 10/10/2018 2:58 AM, Michal Hocko wrote: >>>>> On Tue 09-10-18 13:26:41, Alexander Duyck wrote: >>>>> [...] >>>>>> I would think with that being the case we still probably need the call to >>>>>> __SetPageReserved to set the bit with the expectation that it will not be >>>>>> cleared for device-pages since the pages are not onlined. Removing the call >>>>>> to __SetPageReserved would probably introduce a number of regressions as >>>>>> there are multiple spots that use the reserved bit to determine if a page >>>>>> can be swapped out to disk, mapped as system memory, or migrated. >>>>> >>>>> PageReserved is meant to tell any potential pfn walkers that might get >>>>> to this struct page to back off and not touch it. Even though >>>>> ZONE_DEVICE doesn't online pages in traditional sense it makes those >>>>> pages available for further use so the page reserved bit should be >>>>> cleared. >>>> >>>> So from what I can tell that isn't necessarily the case. Specifically if the >>>> pagemap type is MEMORY_DEVICE_PRIVATE or MEMORY_DEVICE_PUBLIC both are >>>> special cases where the memory may not be accessible to the CPU or cannot be >>>> pinned in order to allow for eviction. >>> >>> Could you give me an example please? >> >> Honestly I am getting a bit beyond my depth here so maybe Dan could explain >> better. I am basing the above comment on Dan's earlier comment in this >> thread combined with the comment that explains the "memory_type" field for >> the pgmap: >> https://elixir.bootlin.com/linux/v4.19-rc7/source/include/linux/memremap.h#L28 >> >>>> The specific case that Dan and Yi are referring to is for the type >>>> MEMORY_DEVICE_FS_DAX. For that type I could probably look at not setting the >>>> reserved bit. Part of me wants to say that we should wait and clear the bit >>>> later, but that would end up just adding time back to initialization. At >>>> this point I would consider the change more of a follow-up optimization >>>> rather than a fix though since this is tailoring things specifically for DAX >>>> versus the other ZONE_DEVICE types. >>> >>> I thought I have already made it clear that these zone device hacks are >>> not acceptable to the generic hotplug code. If the current reserve bit >>> handling is not correct then give us a specific reason for that and we >>> can start thinking about the proper fix. >> >> I might have misunderstood your earlier comment then. I thought you were >> saying that we shouldn't bother with setting the reserved bit. Now it sounds >> like you were thinking more along the lines of what I was here in my comment >> where I thought the bit should be cleared later in some code specifically >> related to DAX when it is exposing it for use to userspace or KVM. > > I was referring to my earlier comment that if you need to do something > about struct page initialization (move_pfn_range_to_zone) outside of the > lock (with the appropriate ground work that is needed) rather than > pulling more zone device hacks into the generic hotplug code [1] > > [1] http://lkml.kernel.org/r/20180926075540.GD6278@dhcp22.suse.cz The only issue is if we don't pull the code together we are looking at a massive increase in initialization times. So for example just the loop that was originally there that was setting the pgmap and resetting the LRU prev pointer was adding an additional 20+ seconds per node with 3TB allocated per node. That essentially doubles the initialization time. How would you recommend I address that? Currently it is a few extra lines in the memmap_init_zone_device function. Eventually I was planning to combine the memmap_init_zone hoplug functionality and memmap_init_zone_device core functionality into a single function called __init_pageblock[1] and then reuse that functionality for deferred page init as well. [1] http://lkml.kernel.org/r/20181005151224.17473.53398.stgit@localhost.localdomain