From: Suren Baghdasaryan <surenb@google.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: Sooyong Suk <s.suk@samsung.com>,
Jaewon Kim <jaewon31.kim@gmail.com>,
viro@zeniv.linux.org.uk, linux-kernel@vger.kernel.org,
akpm@linux-foundation.org, linux-mm@kvack.org, spssyr@gmail.com,
axboe@kernel.dk, linux-block@vger.kernel.org,
dhavale@google.com
Subject: Re: [RFC PATCH] block, fs: use FOLL_LONGTERM as gup_flags for direct IO
Date: Wed, 12 Mar 2025 08:20:36 -0700 [thread overview]
Message-ID: <CAJuCfpGa43OQHG9BmnvxROX1AneCvkuLxFwM+TdxAdR1v9kWSg@mail.gmail.com> (raw)
In-Reply-To: <Z9Gld_s3XYic8-dG@infradead.org>
On Wed, Mar 12, 2025 at 8:17 AM Christoph Hellwig <hch@infradead.org> wrote:
>
> On Thu, Mar 06, 2025 at 06:28:40PM -0800, Suren Baghdasaryan wrote:
> > I think this will help you only when the pages are faulted in but if
> > __get_user_pages() finds an already mapped page which happens to be
> > allocated from CMA, it will not migrate it. So, you might still end up
> > with unmovable pages inside CMA.
>
> Direct I/O pages are not unmovable. They are temporarily pinned for
> the duration of the direct I/O.
Yes but even temporarily pinned pages can cause CMA allocation
failure. My point is that if we know beforehand that the pages will be
pinned we could avoid using CMA and these failures would go away.
>
> I really don't understand what problem you're trying to fix here.
>
next prev parent reply other threads:[~2025-03-12 15:20 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <CGME20250306074101epcas1p4b24ac546f93df2c7fe3176607b20e47f@epcas1p4.samsung.com>
2025-03-06 7:40 ` Sooyong Suk
2025-03-06 15:26 ` Christoph Hellwig
2025-03-06 23:28 ` Jaewon Kim
2025-03-07 2:07 ` Sooyong Suk
2025-03-07 2:28 ` Suren Baghdasaryan
2025-03-07 6:38 ` Sooyong Suk
2025-03-12 15:17 ` Christoph Hellwig
2025-03-12 15:20 ` Suren Baghdasaryan [this message]
2025-03-12 15:25 ` Christoph Hellwig
2025-03-12 15:38 ` Suren Baghdasaryan
2025-03-12 15:52 ` Christoph Hellwig
2025-03-12 16:03 ` Bart Van Assche
2025-03-12 16:06 ` Suren Baghdasaryan
2025-03-12 16:21 ` Christoph Hellwig
2025-03-07 20:23 ` Matthew Wilcox
2025-03-07 21:37 ` Suren Baghdasaryan
2025-03-12 15:21 ` Christoph Hellwig
2025-03-13 22:49 ` David Hildenbrand
2025-03-15 1:04 ` John Hubbard
2025-03-15 23:00 ` David Hildenbrand
2025-03-15 23:09 ` Zi Yan
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=CAJuCfpGa43OQHG9BmnvxROX1AneCvkuLxFwM+TdxAdR1v9kWSg@mail.gmail.com \
--to=surenb@google.com \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=dhavale@google.com \
--cc=hch@infradead.org \
--cc=jaewon31.kim@gmail.com \
--cc=linux-block@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=s.suk@samsung.com \
--cc=spssyr@gmail.com \
--cc=viro@zeniv.linux.org.uk \
/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