[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <4856517e-fb68-436f-8130-b7eb5749b7c0@redhat.com>
Date: Thu, 26 Jun 2025 23:52:51 +0200
From: David Hildenbrand <david@...hat.com>
To: Barry Song <21cnbao@...il.com>, Lance Yang <ioworker0@...il.com>
Cc: akpm@...ux-foundation.org, baolin.wang@...ux.alibaba.com,
chrisl@...nel.org, kasong@...cent.com, lance.yang@...ux.dev,
linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, linux-riscv@...ts.infradead.org,
lorenzo.stoakes@...cle.com, ryan.roberts@....com, v-songbaohua@...o.com,
x86@...nel.org, ying.huang@...el.com, zhengtangquan@...o.com
Subject: Re: [PATCH v4 3/4] mm: Support batched unmap for lazyfree large
folios during reclamation
On 26.06.25 23:46, Barry Song wrote:
> On Thu, Jun 26, 2025 at 9:29 PM Lance Yang <ioworker0@...il.com> wrote:
>>
> [...]
>> +
>> + /*
>> + * If we are sure that we batched the entire folio and cleared
>> + * all PTEs, we can just optimize and stop right here.
>> + */
>> + if (nr_pages == folio_nr_pages(folio))
>
> David also mentioned if (nr_pages > 1 && nr_pages == folio_nr_pages(folio)).
> I assume it’s still fine when nr_pages == 1 for small folios? No?
Yeah, as raised I think it is fine. We should never have any folio page
mapped multiple times into the same VMA in any case. (excluding KSM
pages, but they are handled differenty, using a specialized rmap walk)
--
Cheers,
David / dhildenb
Powered by blists - more mailing lists