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;
MIME-Version: 1.0
References: <20210827191858.2037087-1-surenb@google.com> <20210827191858.2037087-4-surenb@google.com>
 <15537178.k4V9gYNSIy@devpool47>
In-Reply-To: <15537178.k4V9gYNSIy@devpool47>
From:   Suren Baghdasaryan <surenb@google.com>
Date:   Mon, 30 Aug 2021 09:12:04 -0700
Message-ID: <CAJuCfpH+EsqTTok8sT1dXoO6_jz0UJa+PsCbX-_zUty6g-mPYQ@mail.gmail.com>
Subject: Re: [PATCH v8 3/3] mm: add anonymous vma name refcounting
To:     Rolf Eike Beer <eb@emlix.com>
Cc:     Andrew Morton <akpm@linux-foundation.org>,
        Colin Cross <ccross@google.com>,
        Sumit Semwal <sumit.semwal@linaro.org>,
        Michal Hocko <mhocko@suse.com>,
        Dave Hansen <dave.hansen@intel.com>,
        Kees Cook <keescook@chromium.org>,
        Matthew Wilcox <willy@infradead.org>,
        "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
        Vlastimil Babka <vbabka@suse.cz>,
        Johannes Weiner <hannes@cmpxchg.org>,
        Jonathan Corbet <corbet@lwn.net>,
        Al Viro <viro@zeniv.linux.org.uk>,
        Randy Dunlap <rdunlap@infradead.org>,
        Kalesh Singh <kaleshsingh@google.com>,
        Peter Xu <peterx@redhat.com>, rppt@kernel.org,
        Peter Zijlstra <peterz@infradead.org>,
        Catalin Marinas <catalin.marinas@arm.com>,
        vincenzo.frascino@arm.com,
        =?UTF-8?B?Q2hpbndlbiBDaGFuZyAo5by16Yym5paHKQ==?= 
        <chinwen.chang@mediatek.com>,
        Axel Rasmussen <axelrasmussen@google.com>,
        Andrea Arcangeli <aarcange@redhat.com>,
        Jann Horn <jannh@google.com>, apopple@nvidia.com,
        John Hubbard <jhubbard@nvidia.com>,
        Yu Zhao <yuzhao@google.com>, Will Deacon <will@kernel.org>,
        fenghua.yu@intel.com, thunder.leizhen@huawei.com,
        Hugh Dickins <hughd@google.com>, feng.tang@intel.com,
        Jason Gunthorpe <jgg@ziepe.ca>, Roman Gushchin <guro@fb.com>,
        Thomas Gleixner <tglx@linutronix.de>, krisman@collabora.com,
        chris.hyser@oracle.com, Peter Collingbourne <pcc@google.com>,
        "Eric W. Biederman" <ebiederm@xmission.com>,
        Jens Axboe <axboe@kernel.dk>, legion@kernel.org,
        Muchun Song <songmuchun@bytedance.com>,
        Viresh Kumar <viresh.kumar@linaro.org>,
        Thomas Cedeno <thomascedeno@google.com>, sashal@kernel.org,
        cxfcosmos@gmail.com, Rasmus Villemoes <linux@rasmusvillemoes.dk>,
        LKML <linux-kernel@vger.kernel.org>,
        linux-fsdevel@vger.kernel.org, linux-doc@vger.kernel.org,
        linux-mm <linux-mm@kvack.org>,
        kernel-team <kernel-team@android.com>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Precedence: bulk

On Mon, Aug 30, 2021 at 12:03 AM Rolf Eike Beer <eb@emlix.com> wrote:
>
> Am Freitag, 27. August 2021, 21:18:58 CEST schrieb Suren Baghdasaryan:
> > While forking a process with high number (64K) of named anonymous vmas =
the
> > overhead caused by strdup() is noticeable. Experiments with ARM64 Andro=
id
> > device show up to 40% performance regression when forking a process wit=
h
> > 64k unpopulated anonymous vmas using the max name lengths vs the same
> > process with the same number of anonymous vmas having no name.
> > Introduce anon_vma_name refcounted structure to avoid the overhead of
> > copying vma names during fork() and when splitting named anonymous vmas=
.
> > When a vma is duplicated, instead of copying the name we increment the
> > refcount of this structure. Multiple vmas can point to the same
> > anon_vma_name as long as they increment the refcount. The name member o=
f
> > anon_vma_name structure is assigned at structure allocation time and is
> > never changed. If vma name changes then the refcount of the original
> > structure is dropped, a new anon_vma_name structure is allocated
> > to hold the new name and the vma pointer is updated to point to the new
> > structure.
> > With this approach the fork() performance regressions is reduced 3-4x
> > times and with usecases using more reasonable number of VMAs (a few
> > thousand) the regressions is not measurable.
> >
> > Signed-off-by: Suren Baghdasaryan <surenb@google.com>
> > ---
> >  include/linux/mm_types.h |  9 ++++++++-
> >  mm/madvise.c             | 42 +++++++++++++++++++++++++++++++++-------
> >  2 files changed, 43 insertions(+), 8 deletions(-)
> >
> > diff --git a/mm/madvise.c b/mm/madvise.c
> > index bc029f3fca6a..32ac5dc5ebf3 100644
> > --- a/mm/madvise.c
> > +++ b/mm/madvise.c
> > @@ -63,6 +63,27 @@ static int madvise_need_mmap_write(int behavior)
> >       }
> >  }
> >
> > +static struct anon_vma_name *anon_vma_name_alloc(const char *name)
> > +{
> > +     struct anon_vma_name *anon_name;
> > +     size_t len =3D strlen(name);
> > +
> > +     /* Add 1 for NUL terminator at the end of the anon_name->name */
> > +     anon_name =3D kzalloc(sizeof(*anon_name) + len + 1,
> > +                         GFP_KERNEL);
> > +     kref_init(&anon_name->kref);
> > +     strcpy(anon_name->name, name);
> > +
> > +     return anon_name;
> > +}
>
> Given that you overwrite anything in that struct anyway this could be red=
uced
> to kmalloc(), no? And it definitely needs a NULL check.

Ack. I'll address both points in the next revision.
Thanks!
Suren.

>
> Eike
> --
> Rolf Eike Beer, emlix GmbH, http://www.emlix.com
> Fon +49 551 30664-0, Fax +49 551 30664-11
> Gothaer Platz 3, 37083 G=C3=B6ttingen, Germany
> Sitz der Gesellschaft: G=C3=B6ttingen, Amtsgericht G=C3=B6ttingen HR B 31=
60
> Gesch=C3=A4ftsf=C3=BChrung: Heike Jordan, Dr. Uwe Kracke =E2=80=93 Ust-Id=
Nr.: DE 205 198 055
>
> emlix - smart embedded open source