linux-kernel - Re: [PATCH v8 02/14] mm/gup: check every subpage of a compound page during isolation

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <f82dca38-52bd-aa27-2d27-b5a67f5284f5@oracle.com>
Date:   Wed, 3 Feb 2021 16:13:21 +0000
From:   Joao Martins <joao.m.martins@...cle.com>
To:     Jason Gunthorpe <jgg@...pe.ca>
Cc:     Pavel Tatashin <pasha.tatashin@...een.com>,
        linux-kernel@...r.kernel.org, linux-mm@...ck.org,
        akpm@...ux-foundation.org, vbabka@...e.cz, mhocko@...e.com,
        david@...hat.com, osalvador@...e.de, dan.j.williams@...el.com,
        sashal@...nel.org, tyhicks@...ux.microsoft.com,
        iamjoonsoo.kim@....com, mike.kravetz@...cle.com,
        rostedt@...dmis.org, mingo@...hat.com, peterz@...radead.org,
        mgorman@...e.de, willy@...radead.org, rientjes@...gle.com,
        jhubbard@...dia.com, linux-doc@...r.kernel.org,
        ira.weiny@...el.com, linux-kselftest@...r.kernel.org,
        jmorris@...ei.org
Subject: Re: [PATCH v8 02/14] mm/gup: check every subpage of a compound page
 during isolation

On 2/3/21 2:53 PM, Jason Gunthorpe wrote:
> On Wed, Feb 03, 2021 at 01:22:18PM +0000, Joao Martins wrote:
> 
>> With this, longterm gup will 'regress' for hugetlbfs e.g. from ~6k -> ~32k usecs when
>> pinning a 16G hugetlb file.
> 
> Yes, but correctness demands it.
> 
Hence the quotes around the word regress.

But still, we are adding unnecessary overhead (previously nonexistent) to compound pages
even those where the issue doesn't exist (hugetlb).

> The solution is to track these pages as we discover them so we know if
> a PMD/PUD points and can directly skip the duplicated work
> 
That looks better. It would require moving check_and_migrate_movable_pages() elsewhere,
and/or possibly reworking the entire series?

>> Splitting can only occur on THP right? If so, perhaps we could
>> retain the @step increment for compound pages but when
>> !is_transparent_hugepage(head) or just PageHuge(head) like:
> 
> Honestly I'd rather see it fixed properly which will give even bigger
> performance gains - avoiding the entire rescan of the page list will
> be a win
> 

If check_and_migrate_movable_pages() is meant to migrate unpinned pages, then rather than
pinning+unpinning+moving, perhaps it would be called in __get_user_pages() place where we
are walking page tables and know if it's a PUD/PMD and can skip all the subpages and just
record and migrate those instead. Was that your thinking?

	Joao