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: <20211001205657.815551-1-surenb@google.com> <20211001205657.815551-3-surenb@google.com>
 <20211005184211.GA19804@duo.ucw.cz> <CAJuCfpE5JEThTMhwKPUREfSE1GYcTx4YSLoVhAH97fJH_qR0Zg@mail.gmail.com>
 <20211005200411.GB19804@duo.ucw.cz>
In-Reply-To: <20211005200411.GB19804@duo.ucw.cz>
From:   Suren Baghdasaryan <surenb@google.com>
Date:   Tue, 5 Oct 2021 13:43:43 -0700
Message-ID: <CAJuCfpFZkz2c0ZWeqzOAx8KFqk1ge3K-SiCMeu3dmi6B7bK-9w@mail.gmail.com>
Subject: Re: [PATCH v10 3/3] mm: add anonymous vma name refcounting
To:     Pavel Machek <pavel@ucw.cz>
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,
        Rolf Eike Beer <eb@emlix.com>,
        Cyrill Gorcunov <gorcunov@gmail.com>,
        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"
Precedence: bulk

On Tue, Oct 5, 2021 at 1:04 PM Pavel Machek <pavel@ucw.cz> wrote:
>
> Hi!
>
> > > On Fri 2021-10-01 13:56:57, Suren Baghdasaryan wrote:
> > > > While forking a process with high number (64K) of named anonymous vmas the
> > > > overhead caused by strdup() is noticeable. Experiments with ARM64
> > > Android
> > >
> > > I still believe you should simply use numbers and do the
> > > numbers->strings mapping in userspace. We should not need to optimize
> > > strdups in kernel...
> >
> > Here are complications with mapping numbers to strings in the userspace:
> > Approach 1: hardcode number->string in some header file and let all
> > tools use that mapping. The issue is that whenever that mapping
> > changes all the tools that are using it (including 3rd party ones)
> > have to be rebuilt. This is not really maintainable since we don't
> > control 3rd party tools and even for the ones we control, it will be a
> > maintenance issue figuring out which version of the tool used which
> > header file.
>
> 1a) Just put it into a file in /etc... Similar to header file but
> easier...
>
> > Approach 2: have a centralized facility (a process or a DB)
> > maintaining number->string mapping. This would require an additional
> > request to this facility whenever we want to make a number->string
> > conversion. Moreover, when we want to name a VMA, we would have to
>
> I see it complicates userspace. But that's better than complicating
> kernel, and I don't know what limits on strings you plan, but
> considering you'll be outputing the strings in /proc... someone is
> going to get confused with parsing.

I'm not a fan of complicating kernel but the proposed approach seems
simple enough to me. Again this is subjective, so I can't really have
a good argument here. Maybe, as Andrew suggested, I should keep it
under a separate config so that whoever does not care about this
feature pays no price for it?
On the topic of confusing the parsers, if the parser is written so
that it can't ignore new [anon:...] entry then it does not matter
whether we use strings or numbers, it will get confused either way.
Again, if we are concerned about confusing existing parsers I think
having a separate config option set to 'n' would help. This would
prevent some userspace process from naming an anonymous VMA and
causing parser confusion. OTOH on systems where parsers can handle
anon VMA names (Android) we will set that config and use the feature.
Would that address your concerns?


>
>                                                                 Pavel
> --
> http://www.livejournal.com/~pavelmachek