[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20210209134438.GE4718@ziepe.ca>
Date: Tue, 9 Feb 2021 09:44:38 -0400
From: Jason Gunthorpe <jgg@...pe.ca>
To: Daniel Vetter <daniel@...ll.ch>
Cc: Alistair Popple <apopple@...dia.com>,
Linux MM <linux-mm@...ck.org>,
Nouveau Dev <nouveau@...ts.freedesktop.org>,
Ben Skeggs <bskeggs@...hat.com>,
Andrew Morton <akpm@...ux-foundation.org>,
Linux Doc Mailing List <linux-doc@...r.kernel.org>,
Linux Kernel Mailing List <linux-kernel@...r.kernel.org>,
kvm-ppc@...r.kernel.org,
dri-devel <dri-devel@...ts.freedesktop.org>,
John Hubbard <jhubbard@...dia.com>,
Ralph Campbell <rcampbell@...dia.com>,
Jerome Glisse <jglisse@...hat.com>
Subject: Re: [PATCH 0/9] Add support for SVM atomics in Nouveau
On Tue, Feb 09, 2021 at 02:39:51PM +0100, Daniel Vetter wrote:
> Either way ZONE_DEVICE for not vram/device memory sounds wrong. Is
> that really going on here?
My read was this was doing non-coherent atomics on CPU memory.
Atomics on GPU memory is just called migration to GPU memory, it
doesn't need to be special for atomics. In that case it can free the
CPU struct page completely as the data now lives in the ZONE_DEVICE
page so no need for a pin, no problem with movable
Jason
Powered by blists - more mailing lists