From: Matthew Wilcox <willy@infradead.org>
To: David Howells <dhowells@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>,
Al Viro <viro@zeniv.linux.org.uk>,
Christoph Hellwig <hch@infradead.org>,
Jens Axboe <axboe@kernel.dk>, Jan Kara <jack@suse.cz>,
Jeff Layton <jlayton@kernel.org>,
Logan Gunthorpe <logang@deltatee.com>,
linux-fsdevel@vger.kernel.org, linux-block@vger.kernel.org,
linux-kernel@vger.kernel.org
Subject: Re: [PATCH v7 0/8] iov_iter: Improve page extraction (ref, pin or just list)
Date: Mon, 23 Jan 2023 16:31:32 +0000 [thread overview]
Message-ID: <Y862ZL5umO30Vu/D@casper.infradead.org> (raw)
In-Reply-To: <20230120175556.3556978-1-dhowells@redhat.com>
On Fri, Jan 20, 2023 at 05:55:48PM +0000, David Howells wrote:
> (3) Make the bio struct carry a pair of flags to indicate the cleanup
> mode. BIO_NO_PAGE_REF is replaced with BIO_PAGE_REFFED (equivalent to
> FOLL_GET) and BIO_PAGE_PINNED (equivalent to BIO_PAGE_PINNED) is
> added.
I think there's a simpler solution than all of this.
As I understand the fundamental problem here, the question is
when to copy a page on fork. We have the optimisation of COW, but
O_DIRECT/RDMA/... breaks it. So all this page pinning is to indicate
to the fork code "You can't do COW to this page".
Why do we want to track that information on a per-page basis? Wouldn't it
be easier to have a VM_NOCOW flag in vma->vm_flags? Set it the first
time somebody does an O_DIRECT read or RDMA pin. That's it. Pages in
that VMA will now never be COWed, regardless of their refcount/mapcount.
And the whole "did we pin or get this page" problem goes away. Along
with folio->pincount.
next prev parent reply other threads:[~2023-01-23 16:31 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-20 17:55 [PATCH v7 0/8] iov_iter: Improve page extraction (ref, pin or just list) David Howells
2023-01-20 17:55 ` [PATCH v7 1/8] iov_iter: Define flags to qualify page extraction David Howells
2023-01-21 13:01 ` Christoph Hellwig
2023-01-20 17:55 ` [PATCH v7 2/8] iov_iter: Add a function to extract a page list from an iterator David Howells
2023-01-21 13:01 ` Christoph Hellwig
2023-01-21 13:10 ` Christoph Hellwig
2023-01-21 13:30 ` David Howells
2023-01-21 13:33 ` Christoph Hellwig
2023-01-23 11:28 ` David Hildenbrand
2023-01-23 11:51 ` David Howells
2023-01-23 13:11 ` David Hildenbrand
2023-01-23 13:19 ` David Howells
2023-01-23 13:24 ` David Hildenbrand
2023-01-23 19:56 ` John Hubbard
2023-01-26 22:15 ` Al Viro
2023-01-26 23:41 ` David Hildenbrand
2023-01-27 0:05 ` David Howells
2023-01-27 0:20 ` David Hildenbrand
2023-01-23 13:38 ` David Howells
2023-01-23 14:20 ` David Hildenbrand
2023-01-23 14:48 ` Christoph Hellwig
2023-01-23 16:11 ` Jan Kara
2023-01-23 16:17 ` Christoph Hellwig
2023-01-23 23:07 ` John Hubbard
2023-01-24 5:57 ` Christoph Hellwig
2023-01-24 6:55 ` John Hubbard
2023-01-23 12:00 ` David Howells
2023-01-20 17:55 ` [PATCH v7 3/8] mm: Provide a helper to drop a pin/ref on a page David Howells
2023-01-20 17:55 ` [PATCH v7 4/8] block: Rename BIO_NO_PAGE_REF to BIO_PAGE_REFFED and invert the meaning David Howells
2023-01-21 13:04 ` Christoph Hellwig
2023-01-23 9:38 ` David Howells
2023-01-23 9:56 ` Christoph Hellwig
2023-01-20 17:55 ` [PATCH v7 5/8] block: Add BIO_PAGE_PINNED David Howells
2023-01-21 13:05 ` Christoph Hellwig
2023-01-20 17:55 ` [PATCH v7 6/8] block: Make bio structs pin pages rather than ref'ing if appropriate David Howells
2023-01-21 13:07 ` Christoph Hellwig
2023-01-23 11:28 ` David Howells
2023-01-23 14:49 ` Christoph Hellwig
2023-01-20 17:55 ` [PATCH v7 7/8] block: Fix bio_flagged() so that gcc can better optimise it David Howells
2023-01-20 17:55 ` [PATCH v7 8/8] mm: Renumber FOLL_GET and FOLL_PIN down David Howells
2023-01-20 18:59 ` Matthew Wilcox
2023-01-20 19:18 ` David Howells
2023-01-23 16:31 ` Matthew Wilcox [this message]
2023-01-23 16:42 ` [PATCH v7 0/8] iov_iter: Improve page extraction (ref, pin or just list) Jan Kara
2023-01-23 17:33 ` Matthew Wilcox
2023-01-23 22:53 ` John Hubbard
2023-01-24 10:29 ` Jan Kara
2023-01-24 13:21 ` Christoph Hellwig
2023-01-23 16:38 ` David Howells
2023-01-23 16:42 ` Matthew Wilcox
2023-01-23 17:25 ` Jan Kara
2023-01-24 10:24 ` David Hildenbrand
2023-01-23 17:19 ` David Howells
2023-01-23 18:04 ` Matthew Wilcox
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=Y862ZL5umO30Vu/D@casper.infradead.org \
--to=willy@infradead.org \
--cc=axboe@kernel.dk \
--cc=dhowells@redhat.com \
--cc=hch@infradead.org \
--cc=jack@suse.cz \
--cc=jhubbard@nvidia.com \
--cc=jlayton@kernel.org \
--cc=linux-block@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=logang@deltatee.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;
as well as URLs for NNTP newsgroup(s).