From: Jason Gunthorpe <jgg@nvidia.com>
To: David Hildenbrand <david@redhat.com>
Cc: John Hubbard <jhubbard@nvidia.com>,
Alistair Popple <apopple@nvidia.com>,
Christoph Hellwig <hch@infradead.org>,
Andrew Morton <akpm@linux-foundation.org>,
LKML <linux-kernel@vger.kernel.org>,
linux-mm@kvack.org, linux-stable@vger.kernel.org,
Vivek Kasireddy <vivek.kasireddy@intel.com>,
Dave Airlie <airlied@redhat.com>,
Gerd Hoffmann <kraxel@redhat.com>,
Matthew Wilcox <willy@infradead.org>,
Peter Xu <peterx@redhat.com>, Arnd Bergmann <arnd@arndb.de>,
Daniel Vetter <daniel.vetter@ffwll.ch>,
Dongwon Kim <dongwon.kim@intel.com>,
Hugh Dickins <hughd@google.com>,
Junxiao Chang <junxiao.chang@intel.com>,
Mike Kravetz <mike.kravetz@oracle.com>,
Oscar Salvador <osalvador@suse.de>
Subject: Re: [PATCH] mm/gup: restore the ability to pin more than 2GB at a time
Date: Wed, 30 Oct 2024 09:04:53 -0300 [thread overview]
Message-ID: <20241030120453.GC6956@nvidia.com> (raw)
In-Reply-To: <bfee966f-807d-4668-b353-159a6e8066f2@redhat.com>
On Wed, Oct 30, 2024 at 09:34:51AM +0100, David Hildenbrand wrote:
> The unusual thing is not the amount of system memory we are pinning but *how
> many* pages we try pinning in the single call.
>
> If you stare at vfio_pin_pages_remote, we seem to be batching it.
>
> long req_pages = min_t(long, npage, batch->capacity);
>
> Which is
>
> #define VFIO_BATCH_MAX_CAPACITY (PAGE_SIZE / sizeof(struct page *))
>
> So you can fix this in your driver ;)
Yeah, everything batches that I'm aware of. RDMA also uses a 4k batch
size, and iommufd uses 64k.
Jason
next prev parent reply other threads:[~2024-10-30 12:05 UTC|newest]
Thread overview: 25+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-30 3:01 [PATCH] mm/gup: restore the ability to pin more than 2GB at a time John Hubbard
2024-10-30 3:02 ` kernel test robot
2024-10-30 3:10 ` John Hubbard
2024-10-30 4:21 ` Christoph Hellwig
2024-10-30 4:30 ` John Hubbard
2024-10-30 4:33 ` Christoph Hellwig
2024-10-30 4:39 ` John Hubbard
2024-10-30 4:42 ` Christoph Hellwig
2024-10-30 4:44 ` John Hubbard
2024-10-30 6:18 ` Alistair Popple
2024-10-30 6:50 ` John Hubbard
2024-10-30 8:34 ` David Hildenbrand
2024-10-30 9:01 ` David Hildenbrand
2024-10-30 18:34 ` John Hubbard
2024-10-31 0:02 ` Jason Gunthorpe
2024-10-31 0:17 ` John Hubbard
2024-10-31 0:25 ` Jason Gunthorpe
2024-10-31 0:47 ` John Hubbard
2024-10-30 12:04 ` Jason Gunthorpe [this message]
2024-10-30 17:25 ` John Hubbard
2024-10-30 11:59 ` Jason Gunthorpe
2024-10-30 11:03 ` Vlastimil Babka
2024-10-30 17:29 ` John Hubbard
2024-10-30 17:42 ` Vlastimil Babka
2024-10-30 17:49 ` John Hubbard
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20241030120453.GC6956@nvidia.com \
--to=jgg@nvidia.com \
--cc=airlied@redhat.com \
--cc=akpm@linux-foundation.org \
--cc=apopple@nvidia.com \
--cc=arnd@arndb.de \
--cc=daniel.vetter@ffwll.ch \
--cc=david@redhat.com \
--cc=dongwon.kim@intel.com \
--cc=hch@infradead.org \
--cc=hughd@google.com \
--cc=jhubbard@nvidia.com \
--cc=junxiao.chang@intel.com \
--cc=kraxel@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-stable@vger.kernel.org \
--cc=mike.kravetz@oracle.com \
--cc=osalvador@suse.de \
--cc=peterx@redhat.com \
--cc=vivek.kasireddy@intel.com \
--cc=willy@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.