From: "Christian König" <christian.koenig@amd.com>
To: Leon Romanovsky <leon@kernel.org>
Cc: David Hu <dhu@x6u.co>,
sumit.semwal@linaro.org, alex@shazbot.org, ankita@nvidia.com,
chriscli@google.com, david.laight.linux@gmail.com,
dri-devel@lists.freedesktop.org, iommu@lists.linux.dev,
jgg@ziepe.ca, jmoroni@google.com, kevin.tian@intel.com,
kpberry@google.com, linaro-mm-sig@lists.linaro.org,
linux-kernel@vger.kernel.org, linux-media@vger.kernel.org,
nicolinc@nvidia.com, praan@google.com, sashiko-bot@kernel.org,
stable@vger.kernel.org, viursachi@google.com,
xuehaohu@google.com
Subject: Re: [PATCH v8 0/2] dma-buf: Fix silent overflow and alignment
Date: Wed, 2 Sep 2026 15:34:18 +0200 [thread overview]
Message-ID: <7471c6e1-fbba-4430-a196-3f57a73505b7@amd.com> (raw)
In-Reply-To: <20260902105919.GV24140@unreal>
On 9/2/26 12:59, Leon Romanovsky wrote:
...
>> The PCI_P2PDMA_MAP_BUS_ADDR is not supported by DMA-buf and as far as I can see is a complete dead end.
>
> Maybe you mean DRM, but VFIO works perfectly with PCI_P2PDMA_MAP_BUS_ADDR flow in DMA-buf.
> What am I missing?
Well not quite.
The approach PCI_P2PDMA_MAP_BUS_ADDR takes is fundamentally tied to only map a physical CPU address into a PCI address and doesn't take into account that in a lot of configurations the CPU can't access all resources.
So when VFIO uses PCI_P2PDMA_MAP_BUS_ADDR it only works for a small subset of the use cases DMA-buf supports, but yeah as always in DMA-buf pretty much everything is optional.
Regards,
Christian.
>
> Thanks
next prev parent reply other threads:[~2026-09-02 13:34 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-01 17:08 [PATCH v8 0/2] dma-buf: Fix silent overflow and alignment David Hu
2026-09-01 17:08 ` [PATCH v8 1/2] dma-buf: Fix silent overflow for phys vec to sgt David Hu
2026-09-01 17:30 ` sashiko-bot
2026-09-01 17:08 ` [PATCH v8 2/2] dma-buf: Split sgl by largest page-aligned chunk David Hu
2026-09-01 17:30 ` sashiko-bot
2026-09-02 12:08 ` Jason Gunthorpe
2026-09-02 23:07 ` David Hu
2026-09-03 13:49 ` Jason Gunthorpe
2026-09-03 16:36 ` Leon Romanovsky
2026-09-02 7:00 ` [PATCH v8 0/2] dma-buf: Fix silent overflow and alignment Christian König
2026-09-02 7:39 ` Leon Romanovsky
2026-09-02 7:56 ` Christian König
2026-09-02 8:32 ` Leon Romanovsky
2026-09-02 8:44 ` Christian König
2026-09-02 9:53 ` Leon Romanovsky
2026-09-02 10:00 ` Christian König
2026-09-02 10:59 ` Leon Romanovsky
2026-09-02 13:34 ` Christian König [this message]
2026-09-02 17:46 ` Jason Gunthorpe
2026-09-02 13:42 ` Pranjal Shrivastava
2026-09-02 12:03 ` Jason Gunthorpe
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=7471c6e1-fbba-4430-a196-3f57a73505b7@amd.com \
--to=christian.koenig@amd.com \
--cc=alex@shazbot.org \
--cc=ankita@nvidia.com \
--cc=chriscli@google.com \
--cc=david.laight.linux@gmail.com \
--cc=dhu@x6u.co \
--cc=dri-devel@lists.freedesktop.org \
--cc=iommu@lists.linux.dev \
--cc=jgg@ziepe.ca \
--cc=jmoroni@google.com \
--cc=kevin.tian@intel.com \
--cc=kpberry@google.com \
--cc=leon@kernel.org \
--cc=linaro-mm-sig@lists.linaro.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-media@vger.kernel.org \
--cc=nicolinc@nvidia.com \
--cc=praan@google.com \
--cc=sashiko-bot@kernel.org \
--cc=stable@vger.kernel.org \
--cc=sumit.semwal@linaro.org \
--cc=viursachi@google.com \
--cc=xuehaohu@google.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.