[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Message-ID: <6f3020e7-f7e8-4d40-b9ce-32a02932a656@redhat.com>
Date: Mon, 26 Aug 2024 19:03:44 +0200
From: David Hildenbrand <david@...hat.com>
To: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>,
zhiguojiang <justinjiang@...o.com>
Cc: Andrew Morton <akpm@...ux-foundation.org>, linux-mm@...ck.org,
linux-kernel@...r.kernel.org, oe-lkp@...ts.linux.dev, lkp@...el.com,
opensource.kernel@...o.com
Subject: Re: [PATCH v2] vma remove the unneeded avc bound with non-CoWed folio
On 25.08.24 08:42, Lorenzo Stoakes wrote:
> On Sun, Aug 25, 2024 at 01:06:40PM GMT, zhiguojiang wrote:
>>
>>
>> 在 2024/8/25 0:26, Lorenzo Stoakes 写道:
>>> [Some people who received this message don't often get email from lorenzo.stoakes@...cle.com. Learn why this is important at https://aka.ms/LearnAboutSenderIdentification ]
>>>
>>> On Fri, Aug 23, 2024 at 11:02:06PM GMT, Zhiguo Jiang wrote:
>>>> After CoWed by do_wp_page, the vma established a new mapping relationship
>>>> with the CoWed folio instead of the non-CoWed folio. However, regarding
>>>> the situation where vma->anon_vma and the non-CoWed folio's anon_vma are
>>>> not same, the avc binding relationship between them will no longer be
>>>> needed, so it is issue for the avc binding relationship still existing
>>>> between them.
>>>>
>>>> This patch will remove the avc binding relationship between vma and the
>>>> non-CoWed folio's anon_vma, which each has their own independent
>>>> anon_vma. It can also alleviates rmap overhead simultaneously.
>>>>
>>>> Signed-off-by: Zhiguo Jiang <justinjiang@...o.com>
>>>
>>> NACK (until fixed). This is broken (see below).
>>>
>> Hi Lorenzo Stoakes,
>>
>> Thank you for your comments.
>>> I'm not seeing any numbers to back anything up here as to why we want to
>>> make changes to this incredibly sensitive code?
>> I added a debug trace log (as follows) in wp_page_copy() and observed
>> that a large number of these orphan avc-objects still exist. I believe
>> this will have a certain redundant overhead impact on anonymous folios'
>> rmap avcs, so I want to remove it, which is also the most essential
>> value of this patch.
>
> Sorry nack to that idea unless you can provide actual _data_ to demonstrate
> an overhead.
Agreed.
--
Cheers,
David / dhildenb
Powered by blists - more mailing lists