linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@nvidia.com>
To: Christoph Hellwig <hch@infradead.org>
Cc: Alex Williamson <alex.williamson@redhat.com>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	peterx@redhat.com
Subject: Re: [PATCH 3/7] vfio/pci: Use vfio_device_unmap_mapping_range()
Date: Tue, 10 Aug 2021 08:57:22 -0300	[thread overview]
Message-ID: <20210810115722.GA5158@nvidia.com> (raw)
In-Reply-To: <YRI9+7CCSq++pYfM@infradead.org>

On Tue, Aug 10, 2021 at 09:51:07AM +0100, Christoph Hellwig wrote:
> On Fri, Aug 06, 2021 at 02:17:45PM -0600, Alex Williamson wrote:
> > > Now that this is simplified so much, I wonder if we can drop the
> > > memory_lock and just use the dev_set->lock?
> > > 
> > > That avoids the whole down_write_trylock thing and makes it much more
> > > understandable?
> > 
> > Hmm, that would make this case a lot easier, but using a mutex,
> > potentially shared across multiple devices, taken on every non-mmap
> > read/write doesn't really feel like a good trade-off when we're
> > currently using a per device rwsem to retain concurrency here.  Thanks,
> 
> Using a per-set percpu_rw_semaphore might be a good plan here.  Probably
> makes sense to do that incrementally after this change, though.

I'm not sure there is a real performance win to chase here? Doesn't
this only protect mmap against reset? The mmap isn't performance
sensitive, right?

If this really needs extra optimization adding a rwsem to the devset
and using that across the whole set would surely be sufficient.

Jason

  reply	other threads:[~2021-08-10 11:57 UTC|newest]

Thread overview: 38+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-08-05 17:06 [PATCH 0/7] vfio: device fd address space and vfio-pci mmap invalidation cleanup Alex Williamson
2021-08-05 17:07 ` [PATCH 1/7] vfio: Create vfio_fs_type with inode per device Alex Williamson
2021-08-10  8:43   ` Christoph Hellwig
2021-08-10 14:52     ` Alex Williamson
2021-08-10 14:57       ` Christoph Hellwig
2021-08-10 18:49         ` Peter Xu
2021-08-10 21:16           ` Alex Williamson
2021-08-10 22:18             ` Peter Xu
2021-08-05 17:07 ` [PATCH 2/7] vfio: Export unmap_mapping_range() wrapper Alex Williamson
2021-08-10  8:45   ` Christoph Hellwig
2021-08-10 18:56   ` Peter Xu
2021-08-05 17:07 ` [PATCH 3/7] vfio/pci: Use vfio_device_unmap_mapping_range() Alex Williamson
2021-08-06  1:04   ` Jason Gunthorpe
2021-08-06 20:17     ` Alex Williamson
2021-08-10  8:51       ` Christoph Hellwig
2021-08-10 11:57         ` Jason Gunthorpe [this message]
2021-08-10 12:55           ` Christoph Hellwig
2021-08-10 21:50             ` Alex Williamson
2021-08-11 11:57               ` Jason Gunthorpe
2021-08-10  8:53   ` Christoph Hellwig
2021-08-10 19:02     ` Peter Xu
2021-08-10 20:51       ` Alex Williamson
2021-08-10 18:48   ` Peter Xu
2021-08-10 19:59     ` Alex Williamson
2021-08-10 20:20       ` Peter Xu
2021-08-05 17:07 ` [PATCH 4/7] vfio,vfio-pci: Add vma to pfn callback Alex Williamson
2021-08-06  1:01   ` Jason Gunthorpe
2021-08-10  9:00     ` Christoph Hellwig
2021-08-10  9:00   ` Christoph Hellwig
2021-08-05 17:08 ` [PATCH 5/7] mm/interval_tree.c: Export vma interval tree iterators Alex Williamson
2021-08-05 17:08 ` [PATCH 6/7] vfio: Add vfio_device_io_remap_mapping_range() Alex Williamson
2021-08-10  9:04   ` Christoph Hellwig
2021-08-05 17:08 ` [PATCH 7/7] vfio/pci: Remove map-on-fault behavior Alex Williamson
2021-08-10  9:11   ` Christoph Hellwig
2021-08-10 15:04     ` Alex Williamson
2021-08-10 20:54   ` Peter Xu
2021-08-10 21:45     ` Alex Williamson
2021-08-10 22:27       ` Peter Xu

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=20210810115722.GA5158@nvidia.com \
    --to=jgg@nvidia.com \
    --cc=alex.williamson@redhat.com \
    --cc=hch@infradead.org \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=peterx@redhat.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;
as well as URLs for NNTP newsgroup(s).