[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <8cc676db-14eb-442d-b41e-64132f27fa13@redhat.com>
Date: Mon, 20 Jan 2025 09:03:48 +0100
From: David Hildenbrand <david@...hat.com>
To: Lance Yang <ioworker0@...il.com>, akpm@...ux-foundation.org
Cc: 21cnbao@...il.com, ryan.roberts@....com, dev.jain@....com,
shy828301@...il.com, ziy@...dia.com, libang.li@...group.com,
baolin.wang@...ux.alibaba.com, linux-kernel@...r.kernel.org,
linux-mm@...ck.org, Liam.Howlett@...cle.com, lorenzo.stoakes@...cle.com,
vbabka@...e.cz, jannh@...gle.com, Jason@...c4.com,
Mingzhe Yang <mingzhe.yang@...com>
Subject: Re: [RFC 1/1] mm/madvise: fail MADV_PAGEOUT on VM_DROPPABLE VMA
On 20.01.25 02:30, Lance Yang wrote:
> MADV_PAGEOUT should fail on VMAs with the VM_DROPPABLE flag. While
> MADV_PAGEOUT is intended to move anonymous pages to swap, VM_DROPPABLE
> should not be swapped out.
>
> There is an issue where using MADV_PAGEOUT on a VMA with the VM_DROPPABLE
> flag behaves like MADV_DONTNEED, causing the pages to be dropped. This
> could break the semantics of MADV_PAGEOUT, IMO.
It behaves exactly correct I think. They can be dropped any time, which
includes on misplaced MADV_PAGEOUT.
--
Cheers,
David / dhildenb
Powered by blists - more mailing lists