[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CANXvt5ojNPpyPVnE0D5o9873hGz6ijF7QfTd9z08Ds-ex3Ye-Q@mail.gmail.com>
Date: Wed, 8 Sep 2021 16:01:14 +0900
From: Shunsuke Mie <mie@...l.co.jp>
To: Christoph Hellwig <hch@...radead.org>
Cc: Zhu Yanjun <zyjzyj2000@...il.com>,
"Christian K??nig" <christian.koenig@....com>,
Alex Deucher <alexander.deucher@....com>,
Daniel Vetter <daniel.vetter@...ll.ch>,
Doug Ledford <dledford@...hat.com>,
Jason Gunthorpe <jgg@...pe.ca>,
Jianxin Xiong <jianxin.xiong@...el.com>,
Leon Romanovsky <leon@...nel.org>,
linux-kernel@...r.kernel.org, linux-rdma@...r.kernel.org,
Damian Hobson-Garcia <dhobsong@...l.co.jp>,
Takanari Hayama <taki@...l.co.jp>,
Tomohito Esaki <etom@...l.co.jp>
Subject: Re: [RFC PATCH 1/3] RDMA/umem: Change for rdma devices has not dma device
Thank you for your comment.
>
> On Wed, Sep 08, 2021 at 03:16:09PM +0900, Shunsuke Mie wrote:
> > To share memory space using dma-buf, a API of the dma-buf requires dma
> > device, but devices such as rxe do not have a dma device. For those case,
> > change to specify a device of struct ib instead of the dma device.
>
> So if dma-buf doesn't actually need a device to dma map why do we ever
> pass the dma_device here? Something does not add up.
As described in the dma-buf api guide [1], the dma_device is used by dma-buf
exporter to know the device buffer constraints of importer.
[1] https://lwn.net/Articles/489703/
Powered by blists - more mailing lists