[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZK8978wUKKP3/zIW@ziepe.ca>
Date: Wed, 12 Jul 2023 20:57:35 -0300
From: Jason Gunthorpe <jgg@...pe.ca>
To: Mina Almasry <almasrymina@...gle.com>
Cc: David Ahern <dsahern@...nel.org>,
Samiullah Khawaja <skhawaja@...gle.com>,
Willem de Bruijn <willemb@...gle.com>,
Jakub Kicinski <kuba@...nel.org>,
Christoph Hellwig <hch@....de>,
John Hubbard <jhubbard@...dia.com>,
Dan Williams <dan.j.williams@...el.com>,
Jesper Dangaard Brouer <jbrouer@...hat.com>,
brouer@...hat.com, Alexander Duyck <alexander.duyck@...il.com>,
Yunsheng Lin <linyunsheng@...wei.com>, davem@...emloft.net,
pabeni@...hat.com, netdev@...r.kernel.org,
linux-kernel@...r.kernel.org,
Lorenzo Bianconi <lorenzo@...nel.org>,
Yisen Zhuang <yisen.zhuang@...wei.com>,
Salil Mehta <salil.mehta@...wei.com>,
Eric Dumazet <edumazet@...gle.com>,
Sunil Goutham <sgoutham@...vell.com>,
Geetha sowjanya <gakula@...vell.com>,
Subbaraya Sundeep <sbhatta@...vell.com>,
hariprasad <hkelam@...vell.com>,
Saeed Mahameed <saeedm@...dia.com>,
Leon Romanovsky <leon@...nel.org>,
Felix Fietkau <nbd@....name>,
Ryder Lee <ryder.lee@...iatek.com>,
Shayne Chen <shayne.chen@...iatek.com>,
Sean Wang <sean.wang@...iatek.com>,
Kalle Valo <kvalo@...nel.org>,
Matthias Brugger <matthias.bgg@...il.com>,
AngeloGioacchino Del Regno
<angelogioacchino.delregno@...labora.com>,
Jesper Dangaard Brouer <hawk@...nel.org>,
Ilias Apalodimas <ilias.apalodimas@...aro.org>,
linux-rdma@...r.kernel.org, linux-wireless@...r.kernel.org,
linux-arm-kernel@...ts.infradead.org,
linux-mediatek@...ts.infradead.org,
Jonathan Lemon <jonathan.lemon@...il.com>,
Christian König <christian.koenig@....com>,
logang@...tatee.com, Bjorn Helgaas <bhelgaas@...gle.com>
Subject: Re: Memory providers multiplexing (Was: [PATCH net-next v4 4/5]
page_pool: remove PP_FLAG_PAGE_FRAG flag)
On Wed, Jul 12, 2023 at 01:16:00PM -0700, Mina Almasry wrote:
> The proposal was that the uapi in step #1 allocates a region of GPU
> memory, and sets up a p2pdma provider for this region of memory.
Honestly that feels too hacky, which is why I've said a few times
you'd actually need to integrate p2p pages into a DRM driver properly.
> 2. The p2pdma semantics seem to be global to the pci device. I.e., 1
> GPU can export 1 p2pdma resource at a time (the way I'm reading the
> API).
All of this is just a reflection that you are trying to use it in a
wrong hacky way. The driver is supposed to create a p2p registration
for its entire BAR at startup. Not on demand and not in fragments.
Jason
Powered by blists - more mailing lists