From: Jason Gunthorpe <jgg@nvidia.com>
To: Alistair Popple <apopple@nvidia.com>
Cc: linux-mm@kvack.org, david@fromorbit.com,
dan.j.williams@intel.com, jhubbard@nvidia.com,
rcampbell@nvidia.com, willy@infradead.org,
linux-fsdevel@vger.kernel.org, jack@suse.cz, djwong@kernel.org,
hch@lst.de, david@redhat.com, ruansy.fnst@fujitsu.com,
nvdimm@lists.linux.dev, linux-xfs@vger.kernel.org,
linux-ext4@vger.kernel.org, jglisse@redhat.com
Subject: Re: [RFC 07/10] mm: Allow compound zone device pages
Date: Thu, 11 Apr 2024 09:32:04 -0300 [thread overview]
Message-ID: <20240411123204.GS5383@nvidia.com> (raw)
In-Reply-To: <9c21d7ed27117f6a2c2ef86fe9d2d88e4c8c8ad4.1712796818.git-series.apopple@nvidia.com>
On Thu, Apr 11, 2024 at 10:57:28AM +1000, Alistair Popple wrote:
> Zone device pages are used to represent various type of device memory
> managed by device drivers. Currently compound zone device pages are
> not supported. This is because MEMORY_DEVICE_FS_DAX pages are the only
> user of higher order zone device pages and have their own page
> reference counting.
>
> A future change will unify FS DAX reference counting with normal page
> reference counting rules and remove the special FS DAX reference
> counting. Supporting that requires compound zone device pages.
>
> Supporting compound zone device pages requires compound_head() to
> distinguish between head and tail pages whilst still preserving the
> special struct page fields that are specific to zone device pages.
>
> A tail page is distinguished by having bit zero being set in
> page->compound_head, with the remaining bits pointing to the head
> page. For zone device pages page->compound_head is shared with
> page->pgmap.
>
> The page->pgmap field is common to all pages within a memory section.
> Therefore pgmap is the same for both head and tail pages and we can
> use the same scheme to distinguish tail pages. To obtain the pgmap for
> a tail page a new accessor is introduced to fetch it from
> compound_head.
>
> Signed-off-by: Alistair Popple <apopple@nvidia.com>
> ---
> drivers/gpu/drm/nouveau/nouveau_dmem.c | 2 +-
> drivers/pci/p2pdma.c | 2 +-
> include/linux/memremap.h | 12 +++++++++---
> include/linux/migrate.h | 2 +-
> lib/test_hmm.c | 2 +-
> mm/hmm.c | 2 +-
> mm/memory.c | 2 +-
> mm/memremap.c | 6 +++---
> mm/migrate_device.c | 4 ++--
> 9 files changed, 20 insertions(+), 14 deletions(-)
Makes sense to me
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Jason
next prev parent reply other threads:[~2024-04-11 12:32 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-04-11 0:57 [RFC 00/10] fs/dax: Fix FS DAX page reference counts Alistair Popple
2024-04-11 0:57 ` [RFC 01/10] mm/gup.c: Remove redundant check for PCI P2PDMA page Alistair Popple
2024-04-11 12:59 ` Jason Gunthorpe
2024-04-11 13:47 ` David Hildenbrand
2024-04-12 1:37 ` Alistair Popple
2024-04-11 0:57 ` [RFC 02/10] mm/hmm: Remove dead check for HugeTLB and FS DAX Alistair Popple
2024-04-11 12:25 ` Jason Gunthorpe
2024-04-11 13:37 ` Peter Xu
2024-04-12 1:28 ` Alistair Popple
2024-04-11 0:57 ` [RFC 03/10] pci/p2pdma: Don't initialise page refcount to one Alistair Popple
2024-04-11 12:29 ` Jason Gunthorpe
2024-04-12 5:40 ` Alistair Popple
2024-04-12 17:20 ` Dan Williams
2024-05-09 21:59 ` Logan Gunthorpe
2024-05-09 23:14 ` Alistair Popple
2024-04-11 0:57 ` [RFC 04/10] fs/dax: Don't track page mapping/index Alistair Popple
2024-04-12 15:22 ` Jan Kara
2024-04-12 17:31 ` Dan Williams
2024-04-15 7:03 ` Alistair Popple
2024-04-15 20:51 ` Dan Williams
2024-04-16 0:07 ` Alistair Popple
2024-04-16 0:36 ` Dan Williams
2024-04-12 17:21 ` Dan Williams
2024-04-11 0:57 ` [RFC 05/10] fs/dax: Refactor wait for dax idle page Alistair Popple
2024-04-12 14:37 ` Jan Kara
2024-04-13 20:19 ` John Hubbard
2024-04-15 8:41 ` Alistair Popple
2024-04-11 0:57 ` [RFC 06/10] fs/dax: Add dax_page_free callback Alistair Popple
2024-04-11 0:57 ` [RFC 07/10] mm: Allow compound zone device pages Alistair Popple
2024-04-11 12:32 ` Jason Gunthorpe [this message]
2024-04-11 14:10 ` Matthew Wilcox
2024-04-12 1:38 ` Alistair Popple
2024-04-11 0:57 ` [RFC 08/10] fs/dax: Properly refcount fs dax pages Alistair Popple
2024-04-11 0:57 ` [RFC 09/10] mm/khugepage.c: Warn if trying to scan devmap pmd Alistair Popple
2024-04-11 13:45 ` David Hildenbrand
2024-04-12 1:34 ` Alistair Popple
2024-04-11 0:57 ` [RFC 10/10] mm: Remove pXX_devmap Alistair Popple
2024-04-11 12:57 ` Jason Gunthorpe
2024-04-11 17:28 ` [RFC 00/10] fs/dax: Fix FS DAX page reference counts Dan Williams
2024-04-11 17:35 ` Jason Gunthorpe
2024-04-11 17:56 ` Dan Williams
2024-04-12 3:54 ` Alistair Popple
2024-04-12 6:55 ` Alistair Popple
2024-04-12 11:53 ` Jason Gunthorpe
2024-04-12 17:32 ` Dan Williams
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=20240411123204.GS5383@nvidia.com \
--to=jgg@nvidia.com \
--cc=apopple@nvidia.com \
--cc=dan.j.williams@intel.com \
--cc=david@fromorbit.com \
--cc=david@redhat.com \
--cc=djwong@kernel.org \
--cc=hch@lst.de \
--cc=jack@suse.cz \
--cc=jglisse@redhat.com \
--cc=jhubbard@nvidia.com \
--cc=linux-ext4@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-xfs@vger.kernel.org \
--cc=nvdimm@lists.linux.dev \
--cc=rcampbell@nvidia.com \
--cc=ruansy.fnst@fujitsu.com \
--cc=willy@infradead.org \
/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 read-only IMAP folder(s) and NNTP newsgroup(s).