From: Jason Gunthorpe <jgg@nvidia.com>
To: Steven Sistare <steven.sistare@oracle.com>
Cc: iommu@lists.linux.dev, Kevin Tian <kevin.tian@intel.com>,
Nicolin Chen <nicolinc@nvidia.com>
Subject: Re: [PATCH V3 8/9] iommufd: optimize file mapping
Date: Mon, 21 Oct 2024 13:11:50 -0300 [thread overview]
Message-ID: <20241021161150.GB13034@nvidia.com> (raw)
In-Reply-To: <9c0f4c03-6373-4263-b389-262f8018ad02@oracle.com>
On Mon, Oct 21, 2024 at 10:29:02AM -0400, Steven Sistare wrote:
> Despite this I can make one further simplification of the V4 code. In pin_memfd_pages,
> if !upages, I can skip folio_add_pins and instead call it from batch_from_folios. This
> guarantees that in pfn_reader_release_pins, each folio to be released has only 1 pin,
> so I can call the existing unpin_folios and delete folios_unpin_partial.
That sounds pretty good, if the loop in the memfd_pin_folios() can
just be computing npages then that is a reasonable place to come later
and optimized by changing the mm code.
Jason
next prev parent reply other threads:[~2024-10-21 16:11 UTC|newest]
Thread overview: 39+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-04 18:48 [PATCH V3 0/9] iommu_ioas_map_file Steve Sistare
2024-10-04 18:48 ` [PATCH V3 1/9] mm/gup: folio_add_pins Steve Sistare
2024-10-04 18:52 ` Steven Sistare
2024-10-04 20:20 ` David Hildenbrand
2024-10-16 12:17 ` Jason Gunthorpe
2024-10-04 18:48 ` [PATCH V3 2/9] iommufd: rename uptr in iopt_alloc_iova Steve Sistare
2024-10-04 18:48 ` [PATCH V3 3/9] iommufd: generalize iopt_pages address Steve Sistare
2024-10-04 18:48 ` [PATCH V3 4/9] iommufd: pfn reader for file mappings Steve Sistare
2024-10-16 12:37 ` Jason Gunthorpe
2024-10-17 17:01 ` Steven Sistare
2024-10-17 19:20 ` Jason Gunthorpe
2024-10-04 18:48 ` [PATCH V3 5/9] iommufd: IOMMU_IOAS_MAP_FILE Steve Sistare
2024-10-16 12:41 ` Jason Gunthorpe
2024-10-17 17:00 ` Steven Sistare
2024-10-17 19:20 ` Jason Gunthorpe
2024-10-04 18:48 ` [PATCH V3 6/9] iommufd: file mappings for mdev Steve Sistare
2024-10-04 18:48 ` [PATCH V3 7/9] iommufd: pfn reader local variables Steve Sistare
2024-10-16 12:42 ` Jason Gunthorpe
2024-10-04 18:48 ` [PATCH V3 8/9] iommufd: optimize file mapping Steve Sistare
2024-10-16 13:00 ` Jason Gunthorpe
2024-10-16 13:09 ` Steven Sistare
2024-10-16 13:21 ` Jason Gunthorpe
2024-10-17 17:02 ` Steven Sistare
2024-10-17 19:24 ` Jason Gunthorpe
2024-10-17 19:37 ` Steven Sistare
2024-10-18 0:10 ` Jason Gunthorpe
2024-10-18 14:34 ` Steven Sistare
2024-10-18 16:04 ` Jason Gunthorpe
2024-10-18 17:54 ` Steven Sistare
2024-10-18 17:59 ` Jason Gunthorpe
2024-10-18 18:10 ` Steven Sistare
2024-10-18 23:10 ` Jason Gunthorpe
2024-10-21 14:06 ` Steven Sistare
2024-10-21 14:29 ` Steven Sistare
2024-10-21 16:11 ` Jason Gunthorpe [this message]
2024-10-21 17:29 ` Steven Sistare
2024-10-21 16:10 ` Jason Gunthorpe
2024-10-04 18:48 ` [PATCH V3 9/9] iommufd: map file selftest Steve Sistare
2024-10-16 12:23 ` [PATCH V3 0/9] iommu_ioas_map_file Jason Gunthorpe
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=20241021161150.GB13034@nvidia.com \
--to=jgg@nvidia.com \
--cc=iommu@lists.linux.dev \
--cc=kevin.tian@intel.com \
--cc=nicolinc@nvidia.com \
--cc=steven.sistare@oracle.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox