From: Jason Gunthorpe <jgg@nvidia.com>
To: Peter Xu <peterx@redhat.com>
Cc: Alistair Popple <apopple@nvidia.com>,
linux-mm@kvack.org, nouveau@lists.freedesktop.org,
bskeggs@redhat.com, akpm@linux-foundation.org,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
dri-devel@lists.freedesktop.org, jhubbard@nvidia.com,
rcampbell@nvidia.com, jglisse@redhat.com, hch@infradead.org,
daniel@ffwll.ch, willy@infradead.org, bsingharora@gmail.com,
Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH v8 5/8] mm: Device exclusive memory access
Date: Tue, 18 May 2021 14:33:34 -0300 [thread overview]
Message-ID: <20210518173334.GE1002214@nvidia.com> (raw)
In-Reply-To: <YKP5Dj4Q/riGGc43@t490s>
On Tue, May 18, 2021 at 01:27:42PM -0400, Peter Xu wrote:
> I also have a pure and high level question regarding a process fork() when
> there're device exclusive ptes: would the two processes then own the device
> together? Is this a real usecase?
If the pages are MAP_SHARED then yes. All VMAs should point at the
same device_exclusive page and all VMA should migrate back to CPU
pages together.
> Indeed it'll be odd for a COW page since for COW page then it means after
> parent/child writting to the page it'll clone into two, then it's a mistery on
> which one will be the one that "exclusived owned" by the device..
For COW pages it is like every other fork case.. We can't reliably
write-protect the device_exclusive page during fork so we must copy it
at fork time.
Thus three reasonable choices:
- Copy to a new CPU page
- Migrate back to a CPU page and write protect it
- Copy to a new device exclusive page
Jason
WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe <jgg@nvidia.com>
To: Peter Xu <peterx@redhat.com>
Cc: rcampbell@nvidia.com, willy@infradead.org,
linux-doc@vger.kernel.org, nouveau@lists.freedesktop.org,
bsingharora@gmail.com, Alistair Popple <apopple@nvidia.com>,
linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
hch@infradead.org, linux-mm@kvack.org, bskeggs@redhat.com,
daniel@ffwll.ch, akpm@linux-foundation.org,
Christoph Hellwig <hch@lst.de>
Subject: Re: [Nouveau] [PATCH v8 5/8] mm: Device exclusive memory access
Date: Tue, 18 May 2021 14:33:34 -0300 [thread overview]
Message-ID: <20210518173334.GE1002214@nvidia.com> (raw)
In-Reply-To: <YKP5Dj4Q/riGGc43@t490s>
On Tue, May 18, 2021 at 01:27:42PM -0400, Peter Xu wrote:
> I also have a pure and high level question regarding a process fork() when
> there're device exclusive ptes: would the two processes then own the device
> together? Is this a real usecase?
If the pages are MAP_SHARED then yes. All VMAs should point at the
same device_exclusive page and all VMA should migrate back to CPU
pages together.
> Indeed it'll be odd for a COW page since for COW page then it means after
> parent/child writting to the page it'll clone into two, then it's a mistery on
> which one will be the one that "exclusived owned" by the device..
For COW pages it is like every other fork case.. We can't reliably
write-protect the device_exclusive page during fork so we must copy it
at fork time.
Thus three reasonable choices:
- Copy to a new CPU page
- Migrate back to a CPU page and write protect it
- Copy to a new device exclusive page
Jason
_______________________________________________
Nouveau mailing list
Nouveau@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/nouveau
WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe <jgg@nvidia.com>
To: Peter Xu <peterx@redhat.com>
Cc: rcampbell@nvidia.com, willy@infradead.org,
linux-doc@vger.kernel.org, nouveau@lists.freedesktop.org,
bsingharora@gmail.com, Alistair Popple <apopple@nvidia.com>,
linux-kernel@vger.kernel.org, dri-devel@lists.freedesktop.org,
hch@infradead.org, linux-mm@kvack.org, jglisse@redhat.com,
bskeggs@redhat.com, jhubbard@nvidia.com,
akpm@linux-foundation.org, Christoph Hellwig <hch@lst.de>
Subject: Re: [PATCH v8 5/8] mm: Device exclusive memory access
Date: Tue, 18 May 2021 14:33:34 -0300 [thread overview]
Message-ID: <20210518173334.GE1002214@nvidia.com> (raw)
In-Reply-To: <YKP5Dj4Q/riGGc43@t490s>
On Tue, May 18, 2021 at 01:27:42PM -0400, Peter Xu wrote:
> I also have a pure and high level question regarding a process fork() when
> there're device exclusive ptes: would the two processes then own the device
> together? Is this a real usecase?
If the pages are MAP_SHARED then yes. All VMAs should point at the
same device_exclusive page and all VMA should migrate back to CPU
pages together.
> Indeed it'll be odd for a COW page since for COW page then it means after
> parent/child writting to the page it'll clone into two, then it's a mistery on
> which one will be the one that "exclusived owned" by the device..
For COW pages it is like every other fork case.. We can't reliably
write-protect the device_exclusive page during fork so we must copy it
at fork time.
Thus three reasonable choices:
- Copy to a new CPU page
- Migrate back to a CPU page and write protect it
- Copy to a new device exclusive page
Jason
next prev parent reply other threads:[~2021-05-18 17:33 UTC|newest]
Thread overview: 126+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-04-07 8:42 [PATCH v8 0/8] Add support for SVM atomics in Nouveau Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-04-07 8:42 ` [PATCH v8 1/8] mm: Remove special swap entry functions Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-05-18 2:17 ` Peter Xu
2021-05-18 2:17 ` Peter Xu
2021-05-18 2:17 ` [Nouveau] " Peter Xu
2021-05-18 11:58 ` Alistair Popple
2021-05-18 11:58 ` Alistair Popple
2021-05-18 11:58 ` [Nouveau] " Alistair Popple
2021-05-18 14:17 ` Peter Xu
2021-05-18 14:17 ` Peter Xu
2021-05-18 14:17 ` [Nouveau] " Peter Xu
2021-04-07 8:42 ` [PATCH v8 2/8] mm/swapops: Rework swap entry manipulation code Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-04-07 8:42 ` [PATCH v8 3/8] mm/rmap: Split try_to_munlock from try_to_unmap Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-05-18 20:04 ` Liam Howlett
2021-05-18 20:04 ` Liam Howlett
2021-05-18 20:04 ` [Nouveau] " Liam Howlett
2021-05-19 12:38 ` Alistair Popple
2021-05-19 12:38 ` Alistair Popple
2021-05-19 12:38 ` [Nouveau] " Alistair Popple
2021-05-20 20:24 ` Liam Howlett
2021-05-20 20:24 ` Liam Howlett
2021-05-20 20:24 ` [Nouveau] " Liam Howlett
2021-05-21 2:23 ` Alistair Popple
2021-05-21 2:23 ` Alistair Popple
2021-05-21 2:23 ` [Nouveau] " Alistair Popple
2021-04-07 8:42 ` [PATCH v8 4/8] mm/rmap: Split migration into its own function Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-04-07 8:42 ` [PATCH v8 5/8] mm: Device exclusive memory access Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-05-18 2:08 ` Peter Xu
2021-05-18 2:08 ` Peter Xu
2021-05-18 2:08 ` [Nouveau] " Peter Xu
2021-05-18 13:19 ` Alistair Popple
2021-05-18 13:19 ` Alistair Popple
2021-05-18 13:19 ` [Nouveau] " Alistair Popple
2021-05-18 17:27 ` Peter Xu
2021-05-18 17:27 ` Peter Xu
2021-05-18 17:27 ` [Nouveau] " Peter Xu
2021-05-18 17:33 ` Jason Gunthorpe [this message]
2021-05-18 17:33 ` Jason Gunthorpe
2021-05-18 17:33 ` [Nouveau] " Jason Gunthorpe
2021-05-18 18:01 ` Peter Xu
2021-05-18 18:01 ` Peter Xu
2021-05-18 18:01 ` [Nouveau] " Peter Xu
2021-05-18 19:45 ` Jason Gunthorpe
2021-05-18 19:45 ` Jason Gunthorpe
2021-05-18 19:45 ` [Nouveau] " Jason Gunthorpe
2021-05-18 20:29 ` Peter Xu
2021-05-18 20:29 ` Peter Xu
2021-05-18 20:29 ` [Nouveau] " Peter Xu
2021-05-18 23:03 ` Jason Gunthorpe
2021-05-18 23:03 ` Jason Gunthorpe
2021-05-18 23:03 ` [Nouveau] " Jason Gunthorpe
2021-05-18 23:45 ` Peter Xu
2021-05-18 23:45 ` Peter Xu
2021-05-18 23:45 ` [Nouveau] " Peter Xu
2021-05-19 11:04 ` Alistair Popple
2021-05-19 11:04 ` Alistair Popple
2021-05-19 11:04 ` [Nouveau] " Alistair Popple
2021-05-19 12:15 ` Peter Xu
2021-05-19 12:15 ` Peter Xu
2021-05-19 12:15 ` [Nouveau] " Peter Xu
2021-05-19 13:11 ` Alistair Popple
2021-05-19 13:11 ` Alistair Popple
2021-05-19 13:11 ` [Nouveau] " Alistair Popple
2021-05-19 14:04 ` Peter Xu
2021-05-19 14:04 ` Peter Xu
2021-05-19 14:04 ` [Nouveau] " Peter Xu
2021-05-19 13:28 ` Jason Gunthorpe
2021-05-19 13:28 ` Jason Gunthorpe
2021-05-19 13:28 ` [Nouveau] " Jason Gunthorpe
2021-05-19 14:09 ` Peter Xu
2021-05-19 14:09 ` Peter Xu
2021-05-19 14:09 ` [Nouveau] " Peter Xu
2021-05-19 18:11 ` Jason Gunthorpe
2021-05-19 18:11 ` Jason Gunthorpe
2021-05-19 18:11 ` [Nouveau] " Jason Gunthorpe
2021-05-19 11:35 ` Alistair Popple
2021-05-19 11:35 ` Alistair Popple
2021-05-19 11:35 ` [Nouveau] " Alistair Popple
2021-05-19 12:21 ` Peter Xu
2021-05-19 12:21 ` Peter Xu
2021-05-19 12:21 ` [Nouveau] " Peter Xu
2021-05-19 12:46 ` Alistair Popple
2021-05-19 12:46 ` Alistair Popple
2021-05-19 12:46 ` [Nouveau] " Alistair Popple
2021-05-21 6:53 ` Alistair Popple
2021-05-21 6:53 ` Alistair Popple
2021-05-21 6:53 ` [Nouveau] " Alistair Popple
2021-05-18 21:16 ` Peter Xu
2021-05-18 21:16 ` Peter Xu
2021-05-18 21:16 ` [Nouveau] " Peter Xu
2021-05-19 10:49 ` Alistair Popple
2021-05-19 10:49 ` Alistair Popple
2021-05-19 10:49 ` [Nouveau] " Alistair Popple
2021-05-19 12:24 ` Peter Xu
2021-05-19 12:24 ` Peter Xu
2021-05-19 12:24 ` [Nouveau] " Peter Xu
2021-05-19 12:46 ` Alistair Popple
2021-05-19 12:46 ` Alistair Popple
2021-05-19 12:46 ` [Nouveau] " Alistair Popple
2021-04-07 8:42 ` [PATCH v8 6/8] mm: Selftests for exclusive device memory Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-04-07 8:42 ` [PATCH v8 7/8] nouveau/svm: Refactor nouveau_range_fault Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-04-07 8:42 ` [PATCH v8 8/8] nouveau/svm: Implement atomic SVM access Alistair Popple
2021-04-07 8:42 ` Alistair Popple
2021-04-07 8:42 ` [Nouveau] " Alistair Popple
2021-05-21 4:04 ` Ben Skeggs
2021-05-21 4:04 ` Ben Skeggs
2021-05-21 4:04 ` [Nouveau] " Ben Skeggs
2021-05-06 7:43 ` [PATCH v8 0/8] Add support for SVM atomics in Nouveau Alistair Popple
2021-05-06 7:43 ` Alistair Popple
2021-05-06 7:43 ` [Nouveau] " Alistair Popple
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=20210518173334.GE1002214@nvidia.com \
--to=jgg@nvidia.com \
--cc=akpm@linux-foundation.org \
--cc=apopple@nvidia.com \
--cc=bsingharora@gmail.com \
--cc=bskeggs@redhat.com \
--cc=daniel@ffwll.ch \
--cc=dri-devel@lists.freedesktop.org \
--cc=hch@infradead.org \
--cc=hch@lst.de \
--cc=jglisse@redhat.com \
--cc=jhubbard@nvidia.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=nouveau@lists.freedesktop.org \
--cc=peterx@redhat.com \
--cc=rcampbell@nvidia.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 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.