linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Isaac Manjarres <isaacmanjarres@google.com>
To: Kalesh Singh <kaleshsingh@google.com>
Cc: anthony.yznaga@oracle.com, lsf-pc@lists.linux-foundation.org,
	linux-mm@kvack.org, Suren Baghdasaryan <surenb@google.com>,
	android-mm <android-mm@google.com>
Subject: Re: [LSF/MM/BPF TOPIC] mshare - sharing page tables across processes
Date: Thu, 26 Feb 2026 15:48:01 -0800	[thread overview]
Message-ID: <aaDbscdpsamHakmj@google.com> (raw)
In-Reply-To: <CAC_TJvdzgOdvf9=uDaF=zBFWdZ5J9Qh=04Y9OHry6V+YiA-3EQ@mail.gmail.com>

On Wed, Feb 25, 2026 at 04:59:32PM -0800, Kalesh Singh wrote:
> On Mon, Feb 23, 2026 at 6:12 PM <anthony.yznaga@oracle.com> wrote:
> >
> > mshare is a new form of shared memory that shares resources between
> > processes, namely the page tables entries and VMAs of the shared
> > objects. Advantages include reduced memory consumption through
> > eliminating the need for duplicated PTEs in each process, reduced
> > overhead needed to fault shared pages into multiple processes, and the
> > ability for updates to the memory such as protection changes to be
> > immdediately visible to all sharing processes.
> >
> > For some time now the proposed API has continued to evolve. With
> > feedback from mm maintainers, a new approach using syscalls is being
> > taken to create, attach, and deattach mshare regions and to map and
> > manipulate the memory objects within a region.
> >
> > Let's discuss the current state of the API and technical challenges of
> > managing and accomodating shared page tables in the kernel.
> >
> > Anthony
> >
> >
> > References:
> >
> > https://lore.kernel.org/linux-mm/20250820010415.699353-1-anthony.yznaga@oracle.com/
> > https://lore.kernel.org/linux-mm/20250404021902.48863-1-anthony.yznaga@oracle.com/
> 
> Hi Anthony,
> 
> I would be very interested in participating in this discussion at LSF/MM.
> 
> As mentioned on the mailing list, we are currently exploring similar
> optimizations to deduplicate page tables for Android's Zygote process.
> I'd love to join the session to discuss how the proposed sharing
> mechanisms might align.
> 
> Thanks,
> Kalesh

Hello Anthony,

I'm also working on optimizing pagetable usage in Android with Kalesh,
so I'm definitely interested in participating in this discussion as
well.

Thanks,
Isaac


      reply	other threads:[~2026-02-26 23:48 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-24  2:11 anthony.yznaga
2026-02-26  0:59 ` Kalesh Singh
2026-02-26 23:48   ` Isaac Manjarres [this message]

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=aaDbscdpsamHakmj@google.com \
    --to=isaacmanjarres@google.com \
    --cc=android-mm@google.com \
    --cc=anthony.yznaga@oracle.com \
    --cc=kaleshsingh@google.com \
    --cc=linux-mm@kvack.org \
    --cc=lsf-pc@lists.linux-foundation.org \
    --cc=surenb@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox