linux-kernel - Re: [RFC] Make use of non-dynamic dmabuf in RDMA

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Wed, 25 Aug 2021 09:18:32 -0300
From:   Jason Gunthorpe <jgg@...dia.com>
To:     Christian König <christian.koenig@....com>
Cc:     John Hubbard <jhubbard@...dia.com>,
        Gal Pressman <galpress@...zon.com>,
        Daniel Vetter <daniel@...ll.ch>,
        Sumit Semwal <sumit.semwal@...aro.org>,
        Doug Ledford <dledford@...hat.com>,
        "open list:DMA BUFFER SHARING FRAMEWORK" 
        <linux-media@...r.kernel.org>,
        dri-devel <dri-devel@...ts.freedesktop.org>,
        Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
        linux-rdma <linux-rdma@...r.kernel.org>,
        Oded Gabbay <ogabbay@...ana.ai>,
        Tomer Tayar <ttayar@...ana.ai>,
        Yossi Leybovich <sleybo@...zon.com>,
        Alexander Matushevsky <matua@...zon.com>,
        Leon Romanovsky <leonro@...dia.com>,
        Jianxin Xiong <jianxin.xiong@...el.com>
Subject: Re: [RFC] Make use of non-dynamic dmabuf in RDMA

On Wed, Aug 25, 2021 at 08:17:51AM +0200, Christian König wrote:

> The only real option where you could do P2P with buffer pinning are those
> compute boards where we know that everything is always accessible to
> everybody and we will never need to migrate anything. But even then you want
> some mechanism like cgroups to take care of limiting this. Otherwise any
> runaway process can bring down your whole system.
 
Why? It is not the pin that is the problem, it was allocating GPU
dedicated memory in the first place. pinning it just changes the
sequence to free it. No different than CPU memory.

> Key question at least for me as GPU maintainer is if we are going to see
> modern compute boards together with old non-ODP setups. 

You should stop thinking about it as 'old non-ODP setups'.  ODP is
very much a special case that allows a narrow set of functionality to
work in a narrow situation. It has a high performance penalty and
narrow HW support.

So yes, compute boards are routinely used in scenarios where ODP is
not available, today and for the foreseeable future.

Jason