From: Christoph Hellwig <hch@infradead.org>
To: Suren Baghdasaryan <surenb@google.com>
Cc: Christoph Hellwig <hch@infradead.org>,
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 08:25:05 -0700 [thread overview]
Message-ID: <Z9GnUaUD-iaFre_i@infradead.org> (raw)
In-Reply-To: <CAJuCfpGa43OQHG9BmnvxROX1AneCvkuLxFwM+TdxAdR1v9kWSg@mail.gmail.com>
On Wed, Mar 12, 2025 at 08:20:36AM -0700, Suren Baghdasaryan wrote:
> > 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.
Direct I/O (and other users of pin_user_pages) are designed to work
on all anonymous and file backed pages, which is kinda the point.
If you CMA user can't wait for the time of an I/O something is wrong
with that caller and it really should not use CMA.
next prev parent reply other threads:[~2025-03-12 15:25 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 ` [RFC PATCH] block, fs: use FOLL_LONGTERM as gup_flags for direct IO 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
2025-03-12 15:25 ` Christoph Hellwig [this message]
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=Z9GnUaUD-iaFre_i@infradead.org \
--to=hch@infradead.org \
--cc=akpm@linux-foundation.org \
--cc=axboe@kernel.dk \
--cc=dhavale@google.com \
--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=surenb@google.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 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.