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;
Date:   Fri, 24 Sep 2021 02:31:34 +0100
From:   Matthew Wilcox <willy@infradead.org>
To:     Yang Shi <shy828301@gmail.com>
Cc:     Hugh Dickins <hughd@google.com>, Zi Yan <ziy@nvidia.com>,
        "Kirill A. Shutemov" <kirill@shutemov.name>,
        Kent Overstreet <kent.overstreet@gmail.com>,
        Linux FS-devel Mailing List <linux-fsdevel@vger.kernel.org>,
        Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
        Linux MM <linux-mm@kvack.org>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Linus Torvalds <torvalds@linux-foundation.org>,
        Andrew Morton <akpm@linux-foundation.org>,
        "Darrick J. Wong" <djwong@kernel.org>,
        Christoph Hellwig <hch@infradead.org>,
        David Howells <dhowells@redhat.com>,
        Mike Kravetz <mike.kravetz@oracle.com>
Subject: Re: Mapcount of subpages
Message-ID: <YU0qdpbjK5Hdfk2p@casper.infradead.org>
References: <YUvWm6G16+ib+Wnb@moria.home.lan>
 <YUvzINep9m7G0ust@casper.infradead.org>
 <YUwNZFPGDj4Pkspx@moria.home.lan>
 <YUxnnq7uFBAtJ3rT@casper.infradead.org>
 <20210923124502.nxfdaoiov4sysed4@box.shutemov.name>
 <72cc2691-5ebe-8b56-1fe8-eeb4eb4a4c74@google.com>
 <CAHbLzkrELUKR2saOkA9_EeAyZwdboSq0HN6rhmCg2qxwSjdzbg@mail.gmail.com>
 <2A311B26-8B33-458E-B2C1-8BA2CF3484AA@nvidia.com>
 <77b59314-5593-1a2e-293c-b66e8235ad@google.com>
 <CAHbLzkp__irFweEZMEM-CMF_-XQpJcW1dNDFo=RnqaSTGtdJkg@mail.gmail.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <CAHbLzkp__irFweEZMEM-CMF_-XQpJcW1dNDFo=RnqaSTGtdJkg@mail.gmail.com>
Precedence: bulk

On Thu, Sep 23, 2021 at 06:11:19PM -0700, Yang Shi wrote:
> On Thu, Sep 23, 2021 at 4:49 PM Hugh Dickins <hughd@google.com> wrote:
> > I believe Yang Shi is right insofar as the decision on whether it's worth
> > queuing for deferred split is being done based on those subpage _mapcounts.
> > That is a use I had not considered, and I've given no thought to how
> > important or not it is.
> 
> Anyway deferred split is anon THP specific. We don't have to worry
> about this for file THP. So your suggestion about just counting total
> mapcount seems feasible to me for file THP at least.

But I think we probably *should* do deferred split for file THP.
At the moment, when we truncate to the middle of a shmem THP, we try
a few times to split it and then just give up.  We should probably try
once and then queue it for deferred split.