[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20241016154555.GE4020792@ziepe.ca>
Date: Wed, 16 Oct 2024 12:45:55 -0300
From: Jason Gunthorpe <jgg@...pe.ca>
To: Alistair Popple <apopple@...dia.com>
Cc: Yonatan Maman <ymaman@...dia.com>, nouveau@...ts.freedesktop.org,
linux-kernel@...r.kernel.org, linux-rdma@...r.kernel.org,
linux-mm@...ck.org, herbst@...hat.com, lyude@...hat.com,
dakr@...hat.com, airlied@...il.com, simona@...ll.ch,
leon@...nel.org, jglisse@...hat.com, akpm@...ux-foundation.org,
dri-devel@...ts.freedesktop.org, bskeggs@...dia.com,
Gal Shalom <GalShalom@...dia.com>
Subject: Re: [PATCH v1 1/4] mm/hmm: HMM API for P2P DMA to device zone pages
On Wed, Oct 16, 2024 at 04:10:53PM +1100, Alistair Popple wrote:
> On that note how is the refcounting of the returned p2pdma page expected
> to work? We don't want the driver calling hmm_range_fault() to be able
> to pin the page with eg. get_page(), so the returned p2pdma page should
> have a zero refcount to enforce that.
I think that is just the rule for hmm stuff in general, don't touch
the refcount.
We don't need to enforce, it we don't know what else the driver will
want to use that P2P page for after all. It might stick it in a VMA
for some unrelated reason.
Jason
Powered by blists - more mailing lists