[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ee523bd5-2818-269b-8b94-89106ad41767@deltatee.com>
Date: Tue, 11 Jan 2022 16:02:44 -0700
From: Logan Gunthorpe <logang@...tatee.com>
To: Jason Gunthorpe <jgg@...dia.com>
Cc: Matthew Wilcox <willy@...radead.org>, linux-kernel@...r.kernel.org,
Christoph Hellwig <hch@....de>,
Joao Martins <joao.m.martins@...cle.com>,
John Hubbard <jhubbard@...dia.com>,
Ming Lei <ming.lei@...hat.com>, linux-block@...r.kernel.org,
netdev@...r.kernel.org, linux-mm@...ck.org,
linux-rdma@...r.kernel.org, dri-devel@...ts.freedesktop.org,
nvdimm@...ts.linux.dev
Subject: Re: Phyr Starter
On 2022-01-11 3:57 p.m., Jason Gunthorpe wrote:
> On Tue, Jan 11, 2022 at 03:09:13PM -0700, Logan Gunthorpe wrote:
>
>> Either that, or we need a wrapper that allocates an appropriately
>> sized SGL to pass to any dma_map implementation that doesn't support
>> the new structures.
>
> This is what I think we should do. If we start with RDMA then we can
> motivate the 4 main server IOMMU drivers to get updated ASAP, then it
> can acceptably start to spread to other users.
I suspect the preferred path forward is for the IOMMU drivers that don't
use dma-iommu should be converted to use it. Then anything we do to
dma-iommu will be applicable to the IOMMU drivers. Better than expecting
them to implement a bunch of new functionality themselves.
Logan
Powered by blists - more mailing lists