Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Peter Xu <peterx@redhat.com>
To:     linux-mm@kvack.org, linux-kernel@vger.kernel.org
Cc:     "Maya B . Gokhale" <gokhale2@llnl.gov>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Yang Shi <yang.shi@linux.alibaba.com>,
        Marty Mcfadden <mcfadden8@llnl.gov>, peterx@redhat.com,
        Kirill Shutemov <kirill@shutemov.name>,
        Oleg Nesterov <oleg@redhat.com>, Jann Horn <jannh@google.com>,
        Jan Kara <jack@suse.cz>, Kirill Tkhai <ktkhai@virtuozzo.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Christoph Hellwig <hch@lst.de>,
        Andrew Morton <akpm@linux-foundation.org>
Subject: [PATCH 0/4] mm: Simplfy cow handling
Date:   Fri, 21 Aug 2020 19:49:54 -0400
Message-Id: <20200821234958.7896-1-peterx@redhat.com>
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: quoted-printable
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This is a small series that I picked up from Linus's suggestion [0] to simp=
lify=0D
cow handling (and also more strict) by checking against page refcounts rath=
er=0D
than mapcounts.=0D
=0D
I'm CCing the author and reviewer of commit 52d1e606ee73 on ksm ("mm: reuse=
=0D
only-pte-mapped KSM page in do_wp_page()", 2019-03-05).  Please shoot if=0D
there's any reason to keep the logic, or it'll be removed in this series.  =
For=0D
more information, please refer to [3,4].=0D
=0D
The new mm counter in the last patch can be seen as RFC, depending on wheth=
er=0D
anyone dislikes it... I used it majorly for observing the page reuses, so i=
t is=0D
kind of optional.=0D
=0D
Two tests I did:=0D
=0D
  - Run a busy loop dirty program [1] that uses 6G of memory, restrict to 1=
G=0D
    RAM + 5G swap (cgroup).  A few hours later, all things still look good.=
=0D
    Make sure to observe (still massive) correct page reuses using the new=
=0D
    counter using the last patch, probably when swapping in.=0D
=0D
  - Run umapsort [2] to make sure uffd-wp will work again after applying th=
is=0D
    series upon master 5.9-rc1 (5.9-rc1 is broken).=0D
=0D
In all cases, I must confess it's quite pleased to post a series with diffs=
tat=0D
like this...  Hopefully this won't break anyone but only to make everything=
=0D
better.=0D
=0D
Please review, thanks.=0D
=0D
[0] https://lore.kernel.org/lkml/CAHk-=3Dwjn90-=3Ds6MBerxTuP=3D-FVEZtR-LpoH=
9eenEQ3A-QfKTZw@mail.gmail.com=0D
[1] https://github.com/xzpeter/clibs/blob/master/bsd/mig_mon/mig_mon.c=0D
[2] https://github.com/LLNL/umap-apps/blob/develop/src/umapsort/umapsort.cp=
p=0D
[3] https://lore.kernel.org/lkml/CAHk-=3Dwh0syDtNzt9jGyHRV0r1pVX5gkdJWdenwm=
vy=3Ddq0AL5mA@mail.gmail.com=0D
[4] https://lore.kernel.org/lkml/CAHk-=3Dwj5Oyg0LeAxSw_vizerm=3DsLd=3DsHfcV=
ecZMKPZn6kNbbXA@mail.gmail.com=0D
=0D
Linus Torvalds (1):=0D
  mm: Trial do_wp_page() simplification=0D
=0D
Peter Xu (3):=0D
  mm/ksm: Remove reuse_ksm_page()=0D
  mm/gup: Remove enfornced COW mechanism=0D
  mm: Add PGREUSE counter=0D
=0D
 drivers/gpu/drm/i915/gem/i915_gem_userptr.c |  8 ---=0D
 include/linux/ksm.h                         |  7 ---=0D
 include/linux/vm_event_item.h               |  1 +=0D
 mm/gup.c                                    | 40 ++------------=0D
 mm/huge_memory.c                            |  7 +--=0D
 mm/ksm.c                                    | 25 ---------=0D
 mm/memory.c                                 | 60 +++++++--------------=0D
 mm/vmstat.c                                 |  1 +=0D
 8 files changed, 29 insertions(+), 120 deletions(-)=0D
=0D
-- =0D
2.26.2=0D
=0D