From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
To: David Hildenbrand <david@redhat.com>,
Sean Christopherson <seanjc@google.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>,
Andrew Morton <akpm@linux-foundation.org>,
linux-kernel@vger.kernel.org,
Matthew Wilcox <willy@infradead.org>,
Olivier Dion <odion@efficios.com>,
linux-mm@kvack.org
Subject: Re: [RFC PATCH 0/2] SKSM: Synchronous Kernel Samepage Merging
Date: Fri, 28 Feb 2025 16:38:02 -0500 [thread overview]
Message-ID: <331ed532-eb98-4665-9d1b-b6b8bf46e396@efficios.com> (raw)
In-Reply-To: <e110e00f-9032-43ec-808e-45a912065fb0@redhat.com>
On 2025-02-28 10:10, David Hildenbrand wrote:
[...]
> For example, QEMU will mark all guest memory is mergeable using MADV, to
> limit the deduplicaton to guest RAM only.
>
On a related note, I think the madvise(2) documentation is inaccurate.
It states:
MADV_MERGEABLE (since Linux 2.6.32)
Enable Kernel Samepage Merging (KSM) for the pages in the range
specified by addr and length. [...]
AFAIU, based on code review of ksm_madvise(), this is not strictly true.
The KSM implementation enables KSM for pages in the entire vma containing the range.
So if it so happens that two mmap areas with identical protection flags are merged,
both will be considered mergeable by KSM as soon as at least one page from any of
those areas is made mergeable.
This does not appear to be an issue in qemu because guard pages with different
protection are placed between distinct mappings, which should prevent combining
the vmas.
Thanks,
Mathieu
--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com
next prev parent reply other threads:[~2025-02-28 21:38 UTC|newest]
Thread overview: 29+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-02-28 2:30 Mathieu Desnoyers
2025-02-28 2:30 ` [RFC PATCH 1/2] mm: Introduce " Mathieu Desnoyers
2025-02-28 2:30 ` [RFC PATCH 2/2] selftests/kskm: Introduce SKSM basic test Mathieu Desnoyers
2025-02-28 2:51 ` [RFC PATCH 0/2] SKSM: Synchronous Kernel Samepage Merging Linus Torvalds
2025-02-28 3:03 ` Mathieu Desnoyers
2025-02-28 5:17 ` Linus Torvalds
2025-02-28 13:59 ` David Hildenbrand
2025-02-28 14:59 ` Sean Christopherson
2025-02-28 15:10 ` David Hildenbrand
2025-02-28 15:19 ` David Hildenbrand
2025-02-28 21:38 ` Mathieu Desnoyers [this message]
2025-02-28 21:45 ` David Hildenbrand
2025-02-28 21:49 ` Mathieu Desnoyers
2025-02-28 15:01 ` Mathieu Desnoyers
2025-02-28 15:18 ` David Hildenbrand
2025-02-28 14:59 ` Mathieu Desnoyers
2025-02-28 16:32 ` Peter Xu
2025-02-28 17:53 ` Mathieu Desnoyers
2025-02-28 22:32 ` Peter Xu
2025-03-01 15:44 ` Mathieu Desnoyers
2025-03-03 15:01 ` Peter Xu
2025-03-03 16:36 ` David Hildenbrand
2025-03-03 20:01 ` Mathieu Desnoyers
2025-03-03 20:45 ` Peter Xu
2025-03-03 20:49 ` David Hildenbrand
2025-03-05 14:06 ` Mathieu Desnoyers
2025-03-05 19:22 ` David Hildenbrand
2025-02-28 15:34 ` David Hildenbrand
2025-02-28 15:38 ` Matthew Wilcox
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=331ed532-eb98-4665-9d1b-b6b8bf46e396@efficios.com \
--to=mathieu.desnoyers@efficios.com \
--cc=akpm@linux-foundation.org \
--cc=david@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=odion@efficios.com \
--cc=seanjc@google.com \
--cc=torvalds@linux-foundation.org \
--cc=willy@infradead.org \
/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