From: Alex Goins <agoins@nvidia.com>
To: "Christian König" <christian.koenig@amd.com>
Cc: Alex Goins <agoins@nvidia.com>, <amd-gfx@lists.freedesktop.org>,
<dri-devel@lists.freedesktop.org>, <linux-mm@kvack.org>,
John Hubbard <jhubbard@nvidia.com>, Zi Yan <ziy@nvidia.com>
Subject: [PATCH RFC 0/1] drm/ttm: Allocate transparent huge pages without clearing __GFP_COMP
Date: Wed, 30 Sep 2020 17:18:20 -0500 [thread overview]
Message-ID: <20200930221821.13719-1-agoins@nvidia.com> (raw)
Hi Christian,
I've been looking into the DMA-BUFs exported from AMDGPU / TTM. Would
you mind giving some input on this?
I noticed that your changes implementing transparent huge page support
in TTM are allocating them as non-compound. I understand that using
multiorder non-compound pages is common in device drivers, but I think
this can cause a problem when these pages are exported to other drivers.
It's possible for other drivers to access the DMA-BUF's pages via
gem_prime_import_sg_table(), but without context from TTM, it's
impossible for the importing driver to make sense of them; they simply
appear as individual pages, with only the first page having a non-zero
refcount. Making TTM's THP allocations compound puts them more in line
with the standard definition of a THP, and allows DMA-BUF-importing
drivers to make sense of the pages within.
I would like to propose making these allocations compound, but based on
patch history, it looks like the decision to make them non-compound was
intentional, as there were difficulties figuring out how to map them
into CPU page tables. I did some cursory testing with compound THPs, and
nothing seems obviously broken. I was also able to map compound THP
DMA-BUFs into userspace without issue, and access their contents. Are
you aware of any other potential consequences?
Commit 5c42c64f7d54 ("drm/ttm: fix the fix for huge compound pages") should
probably also be reverted if this is applied.
Thanks,
Alex
Alex Goins (1):
drm-ttm: Allocate compound transparent huge pages
drivers/gpu/drm/ttm/ttm_page_alloc.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
--
2.25.1
WARNING: multiple messages have this Message-ID (diff)
From: Alex Goins <agoins@nvidia.com>
To: "Christian König" <christian.koenig@amd.com>
Cc: John Hubbard <jhubbard@nvidia.com>,
dri-devel@lists.freedesktop.org, linux-mm@kvack.org,
amd-gfx@lists.freedesktop.org, Zi Yan <ziy@nvidia.com>
Subject: [PATCH RFC 0/1] drm/ttm: Allocate transparent huge pages without clearing __GFP_COMP
Date: Wed, 30 Sep 2020 17:18:20 -0500 [thread overview]
Message-ID: <20200930221821.13719-1-agoins@nvidia.com> (raw)
Hi Christian,
I've been looking into the DMA-BUFs exported from AMDGPU / TTM. Would
you mind giving some input on this?
I noticed that your changes implementing transparent huge page support
in TTM are allocating them as non-compound. I understand that using
multiorder non-compound pages is common in device drivers, but I think
this can cause a problem when these pages are exported to other drivers.
It's possible for other drivers to access the DMA-BUF's pages via
gem_prime_import_sg_table(), but without context from TTM, it's
impossible for the importing driver to make sense of them; they simply
appear as individual pages, with only the first page having a non-zero
refcount. Making TTM's THP allocations compound puts them more in line
with the standard definition of a THP, and allows DMA-BUF-importing
drivers to make sense of the pages within.
I would like to propose making these allocations compound, but based on
patch history, it looks like the decision to make them non-compound was
intentional, as there were difficulties figuring out how to map them
into CPU page tables. I did some cursory testing with compound THPs, and
nothing seems obviously broken. I was also able to map compound THP
DMA-BUFs into userspace without issue, and access their contents. Are
you aware of any other potential consequences?
Commit 5c42c64f7d54 ("drm/ttm: fix the fix for huge compound pages") should
probably also be reverted if this is applied.
Thanks,
Alex
Alex Goins (1):
drm-ttm: Allocate compound transparent huge pages
drivers/gpu/drm/ttm/ttm_page_alloc.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
--
2.25.1
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/dri-devel
WARNING: multiple messages have this Message-ID (diff)
From: Alex Goins <agoins@nvidia.com>
To: "Christian König" <christian.koenig@amd.com>
Cc: Alex Goins <agoins@nvidia.com>,
John Hubbard <jhubbard@nvidia.com>,
dri-devel@lists.freedesktop.org, linux-mm@kvack.org,
amd-gfx@lists.freedesktop.org, Zi Yan <ziy@nvidia.com>
Subject: [PATCH RFC 0/1] drm/ttm: Allocate transparent huge pages without clearing __GFP_COMP
Date: Wed, 30 Sep 2020 17:18:20 -0500 [thread overview]
Message-ID: <20200930221821.13719-1-agoins@nvidia.com> (raw)
Hi Christian,
I've been looking into the DMA-BUFs exported from AMDGPU / TTM. Would
you mind giving some input on this?
I noticed that your changes implementing transparent huge page support
in TTM are allocating them as non-compound. I understand that using
multiorder non-compound pages is common in device drivers, but I think
this can cause a problem when these pages are exported to other drivers.
It's possible for other drivers to access the DMA-BUF's pages via
gem_prime_import_sg_table(), but without context from TTM, it's
impossible for the importing driver to make sense of them; they simply
appear as individual pages, with only the first page having a non-zero
refcount. Making TTM's THP allocations compound puts them more in line
with the standard definition of a THP, and allows DMA-BUF-importing
drivers to make sense of the pages within.
I would like to propose making these allocations compound, but based on
patch history, it looks like the decision to make them non-compound was
intentional, as there were difficulties figuring out how to map them
into CPU page tables. I did some cursory testing with compound THPs, and
nothing seems obviously broken. I was also able to map compound THP
DMA-BUFs into userspace without issue, and access their contents. Are
you aware of any other potential consequences?
Commit 5c42c64f7d54 ("drm/ttm: fix the fix for huge compound pages") should
probably also be reverted if this is applied.
Thanks,
Alex
Alex Goins (1):
drm-ttm: Allocate compound transparent huge pages
drivers/gpu/drm/ttm/ttm_page_alloc.c | 5 ++---
1 file changed, 2 insertions(+), 3 deletions(-)
--
2.25.1
_______________________________________________
amd-gfx mailing list
amd-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
next reply other threads:[~2020-09-30 22:18 UTC|newest]
Thread overview: 18+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-30 22:18 Alex Goins [this message]
2020-09-30 22:18 ` [PATCH RFC 0/1] drm/ttm: Allocate transparent huge pages without clearing __GFP_COMP Alex Goins
2020-09-30 22:18 ` Alex Goins
2020-09-30 22:18 ` [PATCH RFC 1/1] drm-ttm: " Alex Goins
2020-09-30 22:18 ` Alex Goins
2020-09-30 22:18 ` Alex Goins
2020-10-01 7:19 ` [PATCH RFC 0/1] drm/ttm: " Christian König
2020-10-01 7:19 ` Christian König
2020-10-01 7:19 ` Christian König
2020-10-01 18:45 ` Alex Goins
2020-10-01 18:45 ` Alex Goins
2020-10-01 18:45 ` Alex Goins
2020-10-02 6:41 ` Christian König
2020-10-02 6:41 ` Christian König
2020-10-02 6:41 ` Christian König
2020-10-02 7:31 ` Daniel Vetter
2020-10-02 7:31 ` Daniel Vetter
2020-10-02 7:31 ` Daniel Vetter
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=20200930221821.13719-1-agoins@nvidia.com \
--to=agoins@nvidia.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=christian.koenig@amd.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=jhubbard@nvidia.com \
--cc=linux-mm@kvack.org \
--cc=ziy@nvidia.com \
/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.