From: Jason Gunthorpe <jgg@ziepe.ca>
To: "Christian König" <christian.koenig@amd.com>
Cc: Shunsuke Mie <mie@igel.co.jp>, Zhu Yanjun <zyjzyj2000@gmail.com>,
Alex Deucher <alexander.deucher@amd.com>,
Daniel Vetter <daniel.vetter@ffwll.ch>,
Doug Ledford <dledford@redhat.com>,
Jianxin Xiong <jianxin.xiong@intel.com>,
Leon Romanovsky <leon@kernel.org>,
Maor Gottlieb <maorg@nvidia.com>,
Sean Hefty <sean.hefty@intel.com>,
Sumit Semwal <sumit.semwal@linaro.org>,
dri-devel@lists.freedesktop.org, linaro-mm-sig@lists.linaro.org,
linux-media@vger.kernel.org,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
linux-rdma <linux-rdma@vger.kernel.org>,
Damian Hobson-Garcia <dhobsong@igel.co.jp>,
Takanari Hayama <taki@igel.co.jp>,
Tomohito Esaki <etom@igel.co.jp>
Subject: Re: [RFC PATCH v4 0/2] RDMA/rxe: Add dma-buf support
Date: Fri, 10 Dec 2021 09:26:56 -0400 [thread overview]
Message-ID: <20211210132656.GH6467@ziepe.ca> (raw)
In-Reply-To: <880e25ad-4fe9-eacd-a971-993eaea37fc4@amd.com>
On Fri, Dec 10, 2021 at 01:47:37PM +0100, Christian König wrote:
> Am 10.12.21 um 13:42 schrieb Jason Gunthorpe:
> > On Fri, Dec 10, 2021 at 08:29:24PM +0900, Shunsuke Mie wrote:
> > > Hi Jason,
> > > Thank you for replying.
> > >
> > > 2021年12月8日(水) 2:14 Jason Gunthorpe <jgg@ziepe.ca>:
> > > > On Fri, Dec 03, 2021 at 12:51:44PM +0900, Shunsuke Mie wrote:
> > > > > Hi maintainers,
> > > > >
> > > > > Could you please review this patch series?
> > > > Why is it RFC?
> > > >
> > > > I'm confused why this is useful?
> > > >
> > > > This can't do copy from MMIO memory, so it shouldn't be compatible
> > > > with things like Gaudi - does something prevent this?
> > > I think if an export of the dma-buf supports vmap, CPU is able to access the
> > > mmio memory.
> > >
> > > Is it wrong? If this is wrong, there is no advantages this changes..
> > I don't know what the dmabuf folks did, but yes, it is wrong.
> >
> > IOMEM must be touched using only special accessors, some platforms
> > crash if you don't do this. Even x86 will crash if you touch it with
> > something like an XMM optimized memcpy.
> >
> > Christian? If the vmap succeeds what rules must the caller use to
> > access the memory?
>
> See dma-buf-map.h and especially struct dma_buf_map.
>
> MMIO memory is perfectly supported here and actually the most common case.
Okay that looks sane, but this rxe RFC seems to ignore this
completely. It stuffs the vaddr directly into a umem which goes to all
manner of places in the driver.
??
Jason
WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe <jgg@ziepe.ca>
To: "Christian König" <christian.koenig@amd.com>
Cc: Damian Hobson-Garcia <dhobsong@igel.co.jp>,
Takanari Hayama <taki@igel.co.jp>,
Leon Romanovsky <leon@kernel.org>,
linux-rdma <linux-rdma@vger.kernel.org>,
Daniel Vetter <daniel.vetter@ffwll.ch>,
Linux Kernel Mailing List <linux-kernel@vger.kernel.org>,
dri-devel@lists.freedesktop.org, Tomohito Esaki <etom@igel.co.jp>,
linaro-mm-sig@lists.linaro.org,
Doug Ledford <dledford@redhat.com>,
Zhu Yanjun <zyjzyj2000@gmail.com>, Shunsuke Mie <mie@igel.co.jp>,
Alex Deucher <alexander.deucher@amd.com>,
Sean Hefty <sean.hefty@intel.com>,
Maor Gottlieb <maorg@nvidia.com>,
Jianxin Xiong <jianxin.xiong@intel.com>,
linux-media@vger.kernel.org
Subject: Re: [RFC PATCH v4 0/2] RDMA/rxe: Add dma-buf support
Date: Fri, 10 Dec 2021 09:26:56 -0400 [thread overview]
Message-ID: <20211210132656.GH6467@ziepe.ca> (raw)
In-Reply-To: <880e25ad-4fe9-eacd-a971-993eaea37fc4@amd.com>
On Fri, Dec 10, 2021 at 01:47:37PM +0100, Christian König wrote:
> Am 10.12.21 um 13:42 schrieb Jason Gunthorpe:
> > On Fri, Dec 10, 2021 at 08:29:24PM +0900, Shunsuke Mie wrote:
> > > Hi Jason,
> > > Thank you for replying.
> > >
> > > 2021年12月8日(水) 2:14 Jason Gunthorpe <jgg@ziepe.ca>:
> > > > On Fri, Dec 03, 2021 at 12:51:44PM +0900, Shunsuke Mie wrote:
> > > > > Hi maintainers,
> > > > >
> > > > > Could you please review this patch series?
> > > > Why is it RFC?
> > > >
> > > > I'm confused why this is useful?
> > > >
> > > > This can't do copy from MMIO memory, so it shouldn't be compatible
> > > > with things like Gaudi - does something prevent this?
> > > I think if an export of the dma-buf supports vmap, CPU is able to access the
> > > mmio memory.
> > >
> > > Is it wrong? If this is wrong, there is no advantages this changes..
> > I don't know what the dmabuf folks did, but yes, it is wrong.
> >
> > IOMEM must be touched using only special accessors, some platforms
> > crash if you don't do this. Even x86 will crash if you touch it with
> > something like an XMM optimized memcpy.
> >
> > Christian? If the vmap succeeds what rules must the caller use to
> > access the memory?
>
> See dma-buf-map.h and especially struct dma_buf_map.
>
> MMIO memory is perfectly supported here and actually the most common case.
Okay that looks sane, but this rxe RFC seems to ignore this
completely. It stuffs the vaddr directly into a umem which goes to all
manner of places in the driver.
??
Jason
next prev parent reply other threads:[~2021-12-10 13:27 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-11-22 11:08 [RFC PATCH v4 0/2] RDMA/rxe: Add dma-buf support Shunsuke Mie
2021-11-22 11:08 ` Shunsuke Mie
2021-11-22 11:08 ` [RFC PATCH v4 1/2] RDMA/umem: Change for rdma devices has not dma device Shunsuke Mie
2021-11-22 11:08 ` Shunsuke Mie
2021-11-22 11:08 ` [RFC PATCH v4 2/2] RDMA/rxe: Add dma-buf support Shunsuke Mie
2021-11-22 11:08 ` Shunsuke Mie
2021-12-03 3:51 ` [RFC PATCH v4 0/2] " Shunsuke Mie
2021-12-03 3:51 ` Shunsuke Mie
2021-12-07 17:14 ` Jason Gunthorpe
2021-12-07 17:14 ` Jason Gunthorpe
2021-12-10 11:29 ` Shunsuke Mie
2021-12-10 11:29 ` Shunsuke Mie
2021-12-10 12:42 ` Jason Gunthorpe
2021-12-10 12:42 ` Jason Gunthorpe
2021-12-10 12:47 ` Christian König
2021-12-10 12:47 ` Christian König
2021-12-10 13:26 ` Jason Gunthorpe [this message]
2021-12-10 13:26 ` Jason Gunthorpe
2021-12-10 13:28 ` Christian König
2021-12-10 13:28 ` Christian König
2021-12-13 11:18 ` Shunsuke Mie
2021-12-13 11:18 ` Shunsuke Mie
2021-12-14 8:53 ` Christian König
2021-12-14 8:53 ` Christian König
2021-12-14 9:02 ` Shunsuke Mie
2021-12-14 9:02 ` Shunsuke Mie
2021-12-20 9:31 ` Daniel Vetter
2021-12-20 9:31 ` 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=20211210132656.GH6467@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=alexander.deucher@amd.com \
--cc=christian.koenig@amd.com \
--cc=daniel.vetter@ffwll.ch \
--cc=dhobsong@igel.co.jp \
--cc=dledford@redhat.com \
--cc=dri-devel@lists.freedesktop.org \
--cc=etom@igel.co.jp \
--cc=jianxin.xiong@intel.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=linux-rdma@vger.kernel.org \
--cc=maorg@nvidia.com \
--cc=mie@igel.co.jp \
--cc=sean.hefty@intel.com \
--cc=sumit.semwal@linaro.org \
--cc=taki@igel.co.jp \
--cc=zyjzyj2000@gmail.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.