From: Baolin Wang <baolin.wang@linux.alibaba.com>
To: "David Hildenbrand (Arm)" <david@kernel.org>,
akpm@linux-foundation.org, ljs@kernel.org
Cc: riel@surriel.com, liam@infradead.org, vbabka@kernel.org,
harry@kernel.org, jannh@google.com, lance.yang@linux.dev,
rppt@kernel.org, surenb@google.com, mhocko@suse.com,
linux-mm@kvack.org, linux-kernel@vger.kernel.org
Subject: Re: [PATCH v2] mm: use memory barriers for non PMD-sized folios to sync
Date: Wed, 18 Nov 2026 14:19:56 +0800 [thread overview]
Message-ID: <430c6b67-76a2-4f67-abb6-e28d07a84bd4@linux.alibaba.com> (raw)
In-Reply-To: <c254a38b-d5e5-40d0-8d70-c6baa850cf2a@kernel.org>
On 11/18/26 5:19 AM, David Hildenbrand (Arm) wrote:
> On 11/17/26 08:00, Baolin Wang wrote:
>> Commit 243cf1f67b36 ("mm: memory: fix truncation removing mapped folios")
>> uses PMD lock via sync_with_folio_pmd_zap() to synchronize when a cleared
>> PMD is found while unmapping a folio.
>>
>> However, for non PMD-sized folios, the only PMD clear that can race with
>> this unmap is PTE table reclaim, which clears the PMD only after the rmaps
>> for the table have been removed. This is plain message passing, and taking
>> the PMD lock is more than needed, like I did in the previous patch[1].
>>
>> Without barriers, the walker can observe the cleared PMD but a stale
>> mapcount on weakly ordered architectures:
>>
>> CPU 0 (unmap folio) CPU 1 (MADV_DONTNEED, full PMD)
>> ================================ ================================
>> folio_lock()
>> lock(ptl)
>> clear PTEs
>> remove rmaps /* W mapcount */
>> [mapcount load satisfied early,
>> folio still mapped]
>> pmd_clear() /* W pmd */
>> unlock(ptl)
>> pmdp_get_lockless() -> none /* R pmd */
>> skip the PMD
>> folio_mapped() -> true /* R mapcount, stale */
>> unmapping assumed to have failed
>>
>> Pairing an smp_wmb() before the PMD clear with an smp_rmb() after the
>> PMD read forbids this outcome:
>>
>> CPU 0 (unmap folio) CPU 1 (MADV_DONTNEED, full PMD)
>> ================================ ================================
>> remove rmaps /* W mapcount */
>> smp_wmb()
>> pmd_clear() /* W pmd */
>> pmdp_get_lockless() -> none /* R pmd */
>> smp_rmb()
>> folio_mapped() /* R mapcount */
>>
>> If R pmd observes W pmd, R mapcount must observe W mapcount, so
>> folio_mapped() no longer reports the removed mappings.
>>
>> Pass a 'folio' parameter to sync_with_folio_pmd_zap(), allowing us to
>> skip those pfn walkers: pfn_mkclean_range and mapping_wrprotect_range,
>> which don't need synchronization.
>>
>> Similarly, skip sync for page_mapped_in_vma() since the subsequent
>> operations don't check the folio's mapcount.
>
> Do we have any way to measure the benefit of this? I think we'll need that to
> convince reviewers (like Lorenzo :) )
As I replied to Lorenzo, I will try, though it is hard to measure the
performance for this uncommon race case.
next prev parent reply other threads:[~2026-11-18 6:20 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-11-17 7:00 [PATCH v2] mm: use memory barriers for non PMD-sized folios to sync Baolin Wang
2026-11-17 13:53 ` Lorenzo Stoakes (ARM)
2026-11-18 6:17 ` Baolin Wang
2026-11-17 21:19 ` David Hildenbrand (Arm)
2026-11-18 6:19 ` Baolin Wang [this message]
2026-11-18 12:25 ` Lorenzo Stoakes (ARM)
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=430c6b67-76a2-4f67-abb6-e28d07a84bd4@linux.alibaba.com \
--to=baolin.wang@linux.alibaba.com \
--cc=akpm@linux-foundation.org \
--cc=david@kernel.org \
--cc=harry@kernel.org \
--cc=jannh@google.com \
--cc=lance.yang@linux.dev \
--cc=liam@infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ljs@kernel.org \
--cc=mhocko@suse.com \
--cc=riel@surriel.com \
--cc=rppt@kernel.org \
--cc=surenb@google.com \
--cc=vbabka@kernel.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