[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <66196d4726670_36222e2942a@dwillia2-xfh.jf.intel.com.notmuch>
Date: Fri, 12 Apr 2024 10:20:07 -0700
From: Dan Williams <dan.j.williams@...el.com>
To: Alistair Popple <apopple@...dia.com>, <linux-mm@...ck.org>
CC: <david@...morbit.com>, <dan.j.williams@...el.com>, <jhubbard@...dia.com>,
<rcampbell@...dia.com>, <willy@...radead.org>, <jgg@...dia.com>,
<linux-fsdevel@...r.kernel.org>, <jack@...e.cz>, <djwong@...nel.org>,
<hch@....de>, <david@...hat.com>, <ruansy.fnst@...itsu.com>,
<nvdimm@...ts.linux.dev>, <linux-xfs@...r.kernel.org>,
<linux-ext4@...r.kernel.org>, <jglisse@...hat.com>, Alistair Popple
<apopple@...dia.com>
Subject: RE: [RFC 03/10] pci/p2pdma: Don't initialise page refcount to one
Alistair Popple wrote:
> The reference counts for ZONE_DEVICE private pages should be
> initialised by the driver when the page is actually allocated by the
> driver allocator, not when they are first created. This is currently
> the case for MEMORY_DEVICE_PRIVATE and MEMORY_DEVICE_COHERENT pages
> but not MEMORY_DEVICE_PCI_P2PDMA pages so fix that up.
I know you said to hold off on looking at this series until you fixed up
the kernel assertions, but I would not expect to remove logic before the
replacement is available. So this seems to be in the wrong place in the
series, or am I missing something?
Powered by blists - more mailing lists