All of lore.kernel.org
 help / color / mirror / Atom feed
From: Kaitao Cheng <kaitao.cheng@linux.dev>
To: "David Hildenbrand (Arm)" <david@kernel.org>,
	"Huang, Ying" <ying.huang@linux.alibaba.com>,
	Yuanhe Shu <xiangzao@linux.alibaba.com>
Cc: akpm@linux-foundation.org, vbabka@kernel.org,
	linmiaohe@huawei.com, nao.horiguchi@gmail.com, ziy@nvidia.com,
	wangkefeng.wang@huawei.com, tujinjiang@huawei.com,
	mgorman@techsingularity.net, chengkaitao@kylinos.cn,
	muchun.song@linux.dev, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org
Subject: Re: [PATCH 1/2] mm/compaction: skip folios containing hwpoisoned pages
Date: Tue, 20 Oct 2026 21:31:38 +0800	[thread overview]
Message-ID: <23d3756c-1a87-402d-80b4-c838dfc29f4d@linux.dev> (raw)
In-Reply-To: <bc1b3255-99f7-49c8-bb52-bada6df80f72@kernel.org>



在 2026/10/20 21:07, David Hildenbrand (Arm) 写道:
> On 10/20/26 13:27, Kaitao Cheng wrote:
>>
>>
>> 在 2026/10/11 21:14, Huang, Ying 写道:
>>> Yuanhe Shu <xiangzao@linux.alibaba.com> writes:
>>>
>>>>
>>>> Agreed, and nothing here replaces copy_mc.  Two things the check adds
>>>> while that work is pending: on archs without copy_mc the plain copy
>>>> does not fail, it consumes the poison - the same poison consumption
>>>> commit 841a8bfcbad9 ("mm: prevent poison consumption when splitting
>>>> THP") refused to risk on the split path, at your suggestion; and the
>>>> refusal happens before the copy is attempted at all, while copy_mc
>>>> recovers only during the read.  The check and copy_mc compose.
>>>>
>>>
>>> Is it good to implement the trick in copy_mc_user_highpage() and
>>> copy_mc_highpage() if the macro copy_mc_to_kernel is undefined?
>>
>> On architectures with hardware error correction and exception recovery
>> support, accessing faulty memory automatically triggers an exception,
>> which itself guarantees atomicity.
>>
>> On architectures without such support, even if we implement this logic
>> in copy_mc_user_highpage() and copy_mc_highpage(), checking the hwpoison
>> flag and copying the data remain two separate operations. They cannot
>> be performed atomically, so there is still a race window between them,
>> however small.
> 
> Yes. And you need proper architecture support to fix it?

It does require architecture support, but that doesn't seem practical, haha.

>> Moving the hwpoison check after the copy might address this issue.
>> Is there anything wrong with my understanding?
> 
> Will architectures that are not prepared for copy_mc_user_highpage() not simply
> crash if they trigger an MCE during an access?
> 

Do we need to check both before and after the copy? This feels a bit
redundant, and I'm not sure whether such a small race window warrants
an additional check.

-- 
Thanks
Kaitao Cheng



  reply	other threads:[~2026-10-20 13:31 UTC|newest]

Thread overview: 13+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-28 10:58 [PATCH 0/2] mm: don't migrate folios containing hwpoisoned pages Yuanhe Shu
2026-09-28 10:58 ` [PATCH 1/2] mm/compaction: skip " Yuanhe Shu
2026-09-28 12:12   ` David Hildenbrand (Arm)
2026-09-29  3:41     ` Yuanhe Shu
2026-10-11 13:14       ` Huang, Ying
2026-10-20  7:16         ` Yuanhe Shu
2026-10-20  7:52         ` David Hildenbrand (Arm)
2026-10-20 11:27         ` Kaitao Cheng
2026-10-20 13:07           ` David Hildenbrand (Arm)
2026-10-20 13:31             ` Kaitao Cheng [this message]
2026-10-20 13:58               ` David Hildenbrand (Arm)
2026-10-10  8:35     ` Kaitao Cheng
2026-09-28 10:58 ` [PATCH 2/2] mm/migrate: refuse to migrate " Yuanhe Shu

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=23d3756c-1a87-402d-80b4-c838dfc29f4d@linux.dev \
    --to=kaitao.cheng@linux.dev \
    --cc=akpm@linux-foundation.org \
    --cc=chengkaitao@kylinos.cn \
    --cc=david@kernel.org \
    --cc=linmiaohe@huawei.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mgorman@techsingularity.net \
    --cc=muchun.song@linux.dev \
    --cc=nao.horiguchi@gmail.com \
    --cc=tujinjiang@huawei.com \
    --cc=vbabka@kernel.org \
    --cc=wangkefeng.wang@huawei.com \
    --cc=xiangzao@linux.alibaba.com \
    --cc=ying.huang@linux.alibaba.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.