From: Ralph Campbell <rcampbell@nvidia.com>
To: Christoph Hellwig <hch@lst.de>,
Andrew Morton <akpm@linux-foundation.org>,
Dan Williams <dan.j.williams@intel.com>
Cc: "Felix Kuehling" <Felix.Kuehling@amd.com>,
"Alex Deucher" <alexander.deucher@amd.com>,
"Christian König" <christian.koenig@amd.com>,
"Pan, Xinhui" <Xinhui.Pan@amd.com>,
"Ben Skeggs" <bskeggs@redhat.com>,
"Karol Herbst" <kherbst@redhat.com>,
"Lyude Paul" <lyude@redhat.com>, "Jason Gunthorpe" <jgg@ziepe.ca>,
"Alistair Popple" <apopple@nvidia.com>,
"Logan Gunthorpe" <logang@deltatee.com>,
linux-kernel@vger.kernel.org, amd-gfx@lists.freedesktop.org,
dri-devel@lists.freedesktop.org, nouveau@lists.freedesktop.org,
nvdimm@lists.linux.dev, linux-mm@kvack.org
Subject: Re: [PATCH 7/8] mm: remove the extra ZONE_DEVICE struct page refcount
Date: Mon, 7 Feb 2022 18:25:15 -0800 [thread overview]
Message-ID: <8478b7c5-5079-5c5c-04cd-54a313e3f7c4@nvidia.com> (raw)
In-Reply-To: <20220207063249.1833066-8-hch@lst.de>
On 2/6/22 22:32, Christoph Hellwig wrote:
> ZONE_DEVICE struct pages have an extra reference count that complicates
> the code for put_page() and several places in the kernel that need to
> check the reference count to see that a page is not being used (gup,
> compaction, migration, etc.). Clean up the code so the reference count
> doesn't need to be treated specially for ZONE_DEVICE pages.
>
> Note that this excludes the special idle page wakeup for fsdax pages,
> which still happens at refcount 1. This is a separate issue and will
> be sorted out later. Given that only fsdax pages require the
> notifiacation when the refcount hits 1 now, the PAGEMAP_OPS Kconfig
> symbol can go away and be replaced with a FS_DAX check for this hook
> in the put_page fastpath.
>
> Based on an earlier patch from Ralph Campbell <rcampbell@nvidia.com>.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Thanks for working on this, definite step forward.
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
WARNING: multiple messages have this Message-ID (diff)
From: Ralph Campbell <rcampbell@nvidia.com>
To: Christoph Hellwig <hch@lst.de>,
Andrew Morton <akpm@linux-foundation.org>,
Dan Williams <dan.j.williams@intel.com>
Cc: nvdimm@lists.linux.dev, "Alistair Popple" <apopple@nvidia.com>,
dri-devel@lists.freedesktop.org, linux-mm@kvack.org,
nouveau@lists.freedesktop.org,
"Felix Kuehling" <Felix.Kuehling@amd.com>,
"Pan, Xinhui" <Xinhui.Pan@amd.com>,
linux-kernel@vger.kernel.org, amd-gfx@lists.freedesktop.org,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Ben Skeggs" <bskeggs@redhat.com>,
"Alex Deucher" <alexander.deucher@amd.com>,
"Logan Gunthorpe" <logang@deltatee.com>,
"Christian König" <christian.koenig@amd.com>
Subject: Re: [Nouveau] [PATCH 7/8] mm: remove the extra ZONE_DEVICE struct page refcount
Date: Mon, 7 Feb 2022 18:25:15 -0800 [thread overview]
Message-ID: <8478b7c5-5079-5c5c-04cd-54a313e3f7c4@nvidia.com> (raw)
In-Reply-To: <20220207063249.1833066-8-hch@lst.de>
On 2/6/22 22:32, Christoph Hellwig wrote:
> ZONE_DEVICE struct pages have an extra reference count that complicates
> the code for put_page() and several places in the kernel that need to
> check the reference count to see that a page is not being used (gup,
> compaction, migration, etc.). Clean up the code so the reference count
> doesn't need to be treated specially for ZONE_DEVICE pages.
>
> Note that this excludes the special idle page wakeup for fsdax pages,
> which still happens at refcount 1. This is a separate issue and will
> be sorted out later. Given that only fsdax pages require the
> notifiacation when the refcount hits 1 now, the PAGEMAP_OPS Kconfig
> symbol can go away and be replaced with a FS_DAX check for this hook
> in the put_page fastpath.
>
> Based on an earlier patch from Ralph Campbell <rcampbell@nvidia.com>.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Thanks for working on this, definite step forward.
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
WARNING: multiple messages have this Message-ID (diff)
From: Ralph Campbell <rcampbell@nvidia.com>
To: Christoph Hellwig <hch@lst.de>,
Andrew Morton <akpm@linux-foundation.org>,
Dan Williams <dan.j.williams@intel.com>
Cc: nvdimm@lists.linux.dev, "Alistair Popple" <apopple@nvidia.com>,
dri-devel@lists.freedesktop.org,
"Karol Herbst" <kherbst@redhat.com>,
linux-mm@kvack.org, nouveau@lists.freedesktop.org,
"Felix Kuehling" <Felix.Kuehling@amd.com>,
"Pan, Xinhui" <Xinhui.Pan@amd.com>,
linux-kernel@vger.kernel.org, amd-gfx@lists.freedesktop.org,
"Jason Gunthorpe" <jgg@ziepe.ca>,
"Ben Skeggs" <bskeggs@redhat.com>,
"Alex Deucher" <alexander.deucher@amd.com>,
"Logan Gunthorpe" <logang@deltatee.com>,
"Christian König" <christian.koenig@amd.com>
Subject: Re: [PATCH 7/8] mm: remove the extra ZONE_DEVICE struct page refcount
Date: Mon, 7 Feb 2022 18:25:15 -0800 [thread overview]
Message-ID: <8478b7c5-5079-5c5c-04cd-54a313e3f7c4@nvidia.com> (raw)
In-Reply-To: <20220207063249.1833066-8-hch@lst.de>
On 2/6/22 22:32, Christoph Hellwig wrote:
> ZONE_DEVICE struct pages have an extra reference count that complicates
> the code for put_page() and several places in the kernel that need to
> check the reference count to see that a page is not being used (gup,
> compaction, migration, etc.). Clean up the code so the reference count
> doesn't need to be treated specially for ZONE_DEVICE pages.
>
> Note that this excludes the special idle page wakeup for fsdax pages,
> which still happens at refcount 1. This is a separate issue and will
> be sorted out later. Given that only fsdax pages require the
> notifiacation when the refcount hits 1 now, the PAGEMAP_OPS Kconfig
> symbol can go away and be replaced with a FS_DAX check for this hook
> in the put_page fastpath.
>
> Based on an earlier patch from Ralph Campbell <rcampbell@nvidia.com>.
>
> Signed-off-by: Christoph Hellwig <hch@lst.de>
Thanks for working on this, definite step forward.
Reviewed-by: Ralph Campbell <rcampbell@nvidia.com>
next prev parent reply other threads:[~2022-02-08 2:25 UTC|newest]
Thread overview: 141+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-07 6:32 start sorting out the ZONE_DEVICE refcount mess Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 6:32 ` [PATCH 1/8] mm: remove a pointless CONFIG_ZONE_DEVICE check in memremap_pages Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 18:08 ` Dan Williams
2022-02-07 18:08 ` Dan Williams
2022-02-07 18:08 ` [Nouveau] " Dan Williams
2022-02-07 19:22 ` Jason Gunthorpe
2022-02-07 19:22 ` Jason Gunthorpe
2022-02-07 19:22 ` [Nouveau] " Jason Gunthorpe
2022-02-08 7:17 ` Chaitanya Kulkarni
2022-02-08 7:17 ` [Nouveau] " Chaitanya Kulkarni
2022-02-08 7:17 ` Chaitanya Kulkarni
2022-02-08 8:06 ` Muchun Song
2022-02-08 8:06 ` [Nouveau] " Muchun Song
2022-02-08 8:06 ` Muchun Song
2022-02-07 6:32 ` [PATCH 2/8] mm: remove the __KERNEL__ guard from <linux/mm.h> Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 18:08 ` Dan Williams
2022-02-07 18:08 ` Dan Williams
2022-02-07 18:08 ` [Nouveau] " Dan Williams
2022-02-07 19:26 ` Jason Gunthorpe
2022-02-07 19:26 ` [Nouveau] " Jason Gunthorpe
2022-02-07 19:26 ` Jason Gunthorpe
2022-02-08 7:21 ` Chaitanya Kulkarni
2022-02-08 7:21 ` [Nouveau] " Chaitanya Kulkarni
2022-02-08 7:21 ` Chaitanya Kulkarni
2022-02-08 8:07 ` Muchun Song
2022-02-08 8:07 ` [Nouveau] " Muchun Song
2022-02-08 8:07 ` Muchun Song
2022-02-07 6:32 ` [PATCH 3/8] mm: remove pointless includes from <linux/hmm.h> Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 14:01 ` Jason Gunthorpe
2022-02-07 14:01 ` Jason Gunthorpe
2022-02-07 14:01 ` [Nouveau] " Jason Gunthorpe
2022-02-08 7:27 ` Chaitanya Kulkarni
2022-02-08 7:27 ` [Nouveau] " Chaitanya Kulkarni
2022-02-08 7:27 ` Chaitanya Kulkarni
2022-02-07 6:32 ` [PATCH 4/8] mm: move free_devmap_managed_page to memremap.c Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 19:06 ` Dan Williams
2022-02-07 19:06 ` Dan Williams
2022-02-07 19:06 ` [Nouveau] " Dan Williams
2022-02-07 19:27 ` Jason Gunthorpe
2022-02-07 19:27 ` Jason Gunthorpe
2022-02-07 19:27 ` [Nouveau] " Jason Gunthorpe
2022-02-08 7:34 ` Chaitanya Kulkarni
2022-02-08 7:34 ` [Nouveau] " Chaitanya Kulkarni
2022-02-08 7:34 ` Chaitanya Kulkarni
2022-02-08 8:09 ` Muchun Song
2022-02-08 8:09 ` [Nouveau] " Muchun Song
2022-02-08 8:09 ` Muchun Song
2022-02-07 6:32 ` [PATCH 5/8] mm: simplify freeing of devmap managed pages Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 19:34 ` Jason Gunthorpe
2022-02-07 19:34 ` Jason Gunthorpe
2022-02-07 19:34 ` [Nouveau] " Jason Gunthorpe
2022-02-07 23:42 ` Dan Williams
2022-02-07 23:42 ` Dan Williams
2022-02-07 23:42 ` [Nouveau] " Dan Williams
2022-02-08 7:50 ` Chaitanya Kulkarni
2022-02-08 7:50 ` [Nouveau] " Chaitanya Kulkarni
2022-02-08 7:50 ` Chaitanya Kulkarni
2022-02-07 6:32 ` [PATCH 6/8] mm: don't include <linux/memremap.h> in <linux/mm.h> Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 17:38 ` Logan Gunthorpe
2022-02-07 17:38 ` Logan Gunthorpe
2022-02-07 17:38 ` [Nouveau] " Logan Gunthorpe
2022-02-07 19:35 ` Jason Gunthorpe
2022-02-07 19:35 ` Jason Gunthorpe
2022-02-07 19:35 ` [Nouveau] " Jason Gunthorpe
2022-02-07 21:19 ` Felix Kuehling
2022-02-07 21:19 ` Felix Kuehling
2022-02-07 21:19 ` [Nouveau] " Felix Kuehling
2022-02-08 6:46 ` Christoph Hellwig
2022-02-08 6:46 ` Christoph Hellwig
2022-02-08 6:46 ` [Nouveau] " Christoph Hellwig
2022-02-09 17:48 ` Christoph Hellwig
2022-02-09 17:48 ` Christoph Hellwig
2022-02-09 17:48 ` [Nouveau] " Christoph Hellwig
2022-02-10 2:10 ` Alistair Popple
2022-02-10 2:10 ` Alistair Popple
2022-02-10 2:10 ` [Nouveau] " Alistair Popple
2022-02-10 6:45 ` Christoph Hellwig
2022-02-10 6:45 ` Christoph Hellwig
2022-02-10 6:45 ` [Nouveau] " Christoph Hellwig
2022-02-10 21:00 ` Felix Kuehling
2022-02-10 21:00 ` Felix Kuehling
2022-02-10 21:00 ` [Nouveau] " Felix Kuehling
2022-02-07 23:49 ` Dan Williams
2022-02-07 23:49 ` Dan Williams
2022-02-07 23:49 ` [Nouveau] " Dan Williams
2022-02-08 23:53 ` Dan Williams
2022-02-08 23:53 ` Dan Williams
2022-02-08 23:53 ` [Nouveau] " Dan Williams
2022-02-09 6:22 ` Christoph Hellwig
2022-02-09 6:22 ` Christoph Hellwig
2022-02-09 6:22 ` [Nouveau] " Christoph Hellwig
2022-02-07 6:32 ` [PATCH 7/8] mm: remove the extra ZONE_DEVICE struct page refcount Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 19:21 ` Jason Gunthorpe
2022-02-07 19:21 ` Jason Gunthorpe
2022-02-07 19:21 ` [Nouveau] " Jason Gunthorpe
2022-02-08 2:25 ` Ralph Campbell [this message]
2022-02-08 2:25 ` Ralph Campbell
2022-02-08 2:25 ` [Nouveau] " Ralph Campbell
2022-02-09 3:30 ` Dan Williams
2022-02-09 3:30 ` Dan Williams
2022-02-09 3:30 ` [Nouveau] " Dan Williams
2022-02-09 6:23 ` Christoph Hellwig
2022-02-09 6:23 ` Christoph Hellwig
2022-02-09 6:23 ` [Nouveau] " Christoph Hellwig
2022-02-09 12:29 ` Jason Gunthorpe
2022-02-09 12:29 ` [Nouveau] " Jason Gunthorpe
2022-02-09 12:29 ` Jason Gunthorpe
2022-02-09 13:53 ` Christoph Hellwig
2022-02-09 13:53 ` Christoph Hellwig
2022-02-09 13:53 ` [Nouveau] " Christoph Hellwig
2022-02-09 14:14 ` Jason Gunthorpe
2022-02-09 14:14 ` Jason Gunthorpe
2022-02-09 14:14 ` [Nouveau] " Jason Gunthorpe
2022-02-07 6:32 ` [PATCH 8/8] fsdax: depend on ZONE_DEVICE || FS_DAX_LIMITED Christoph Hellwig
2022-02-07 6:32 ` Christoph Hellwig
2022-02-07 6:32 ` [Nouveau] " Christoph Hellwig
2022-02-07 19:36 ` Jason Gunthorpe
2022-02-07 19:36 ` Jason Gunthorpe
2022-02-07 19:36 ` [Nouveau] " Jason Gunthorpe
2022-02-07 23:51 ` start sorting out the ZONE_DEVICE refcount mess Logan Gunthorpe
2022-02-07 23:51 ` Logan Gunthorpe
2022-02-07 23:51 ` [Nouveau] " Logan Gunthorpe
2022-02-08 3:03 ` Miaohe Lin
2022-02-08 3:03 ` [Nouveau] " Miaohe Lin
2022-02-08 3:03 ` Miaohe Lin
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=8478b7c5-5079-5c5c-04cd-54a313e3f7c4@nvidia.com \
--to=rcampbell@nvidia.com \
--cc=Felix.Kuehling@amd.com \
--cc=Xinhui.Pan@amd.com \
--cc=akpm@linux-foundation.org \
--cc=alexander.deucher@amd.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=apopple@nvidia.com \
--cc=bskeggs@redhat.com \
--cc=christian.koenig@amd.com \
--cc=dan.j.williams@intel.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=hch@lst.de \
--cc=jgg@ziepe.ca \
--cc=kherbst@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=logang@deltatee.com \
--cc=lyude@redhat.com \
--cc=nouveau@lists.freedesktop.org \
--cc=nvdimm@lists.linux.dev \
/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.