From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
To: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: David Hildenbrand <david@redhat.com>,
Andrew Morton <akpm@linux-foundation.org>,
linux-mm@kvack.org, Zi Yan <ziy@nvidia.com>,
Baolin Wang <baolin.wang@linux.alibaba.com>,
Ryan Roberts <ryan.roberts@arm.com>, Dev Jain <dev.jain@arm.com>,
Barry Song <baohua@kernel.org>, Lance Yang <lance.yang@linux.dev>,
Liam.Howlett@oracle.com,
Sidhartha Kumar <sidhartha.kumar@oracle.com>
Subject: Re: [PATCH v3 2/3] mm: mprotect: avoid unnecessary struct page accessing if pte_protnone()
Date: Fri, 17 Oct 2025 09:47:42 +0100 [thread overview]
Message-ID: <34993f2e-b491-46e1-aa4c-10b2451d9be1@lucifer.local> (raw)
In-Reply-To: <fb525b11-c60e-4a97-a5ed-be0792957ef6@huawei.com>
On Thu, Oct 16, 2025 at 09:07:13AM +0800, Kefeng Wang wrote:
>
>
> On 2025/10/16 1:45, David Hildenbrand wrote:
> > On 15.10.25 17:43, Lorenzo Stoakes wrote:
> > > On Wed, Oct 15, 2025 at 08:35:15PM +0800, Kefeng Wang wrote:
> > > > If the pte_protnone() is true, we could avoid unnecessary struct page
> > > > accessing and reduce cache footprint when scanning page tables for prot
> > > > numa, the performance test of pmbench memory accessing benchmark
> > > > should be benifit, see more commit a818f5363a0e ("autonuma: reduce cache
> > > > footprint when scanning page tables").
> > >
> > > Hm should benefit? But you've not tested it? Seems like rather than
> > > guessing you should actually give data. Otherwise I don't know why we're
> > > referencing a benchmark.
> >
>
> Yes, I don't test it, just find the above commit which does same thing
> before and it shows benefit in a benchmark.
Right, so let's just drop this from the commit message please, otherwise
it's a bit weird - saying that you hope it'll be an improvement without
providing any details is not really useful here.
next prev parent reply other threads:[~2025-10-17 8:48 UTC|newest]
Thread overview: 22+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-10-15 12:35 [PATCH v3 0/3] mm: some optimizations for prot numa Kefeng Wang
2025-10-15 12:35 ` [PATCH v3 1/3] mm: mprotect: always skip dma pinned folio in prot_numa_skip() Kefeng Wang
2025-10-15 15:32 ` Lorenzo Stoakes
2025-10-16 1:00 ` Kefeng Wang
2025-10-16 21:10 ` Andrew Morton
2025-10-17 8:46 ` Lorenzo Stoakes
2025-10-17 14:12 ` Kefeng Wang
2025-10-16 1:14 ` Zi Yan
2025-10-16 17:53 ` Dev Jain
2025-10-15 12:35 ` [PATCH v3 2/3] mm: mprotect: avoid unnecessary struct page accessing if pte_protnone() Kefeng Wang
2025-10-15 15:43 ` Lorenzo Stoakes
2025-10-15 17:45 ` David Hildenbrand
2025-10-16 1:07 ` Kefeng Wang
2025-10-17 8:47 ` Lorenzo Stoakes [this message]
2025-10-17 8:46 ` Lorenzo Stoakes
2025-10-16 1:28 ` Zi Yan
2025-10-16 1:35 ` Kefeng Wang
2025-10-16 18:02 ` Dev Jain
2025-10-15 12:35 ` [PATCH v3 3/3] mm: huge_memory: use folio_needs_prot_numa() for pmd folio Kefeng Wang
2025-10-16 19:19 ` David Hildenbrand
2025-10-17 10:07 ` Lorenzo Stoakes
2025-10-17 14:13 ` Kefeng Wang
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=34993f2e-b491-46e1-aa4c-10b2451d9be1@lucifer.local \
--to=lorenzo.stoakes@oracle.com \
--cc=Liam.Howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=baohua@kernel.org \
--cc=baolin.wang@linux.alibaba.com \
--cc=david@redhat.com \
--cc=dev.jain@arm.com \
--cc=lance.yang@linux.dev \
--cc=linux-mm@kvack.org \
--cc=ryan.roberts@arm.com \
--cc=sidhartha.kumar@oracle.com \
--cc=wangkefeng.wang@huawei.com \
--cc=ziy@nvidia.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