public inbox for kvm@vger.kernel.org
 help / color / mirror / Atom feed
From: Jason Gunthorpe <jgg@ziepe.ca>
To: Alex Williamson <alex.williamson@redhat.com>
Cc: Keith Busch <kbusch@meta.com>,
	kvm@vger.kernel.org, Keith Busch <kbusch@kernel.org>
Subject: Re: [PATCH rfc] vfio-pci: Allow write combining
Date: Thu, 1 Aug 2024 14:13:55 -0300	[thread overview]
Message-ID: <20240801171355.GA4830@ziepe.ca> (raw)
In-Reply-To: <20240801105218.7c297f9a.alex.williamson@redhat.com>

On Thu, Aug 01, 2024 at 10:52:18AM -0600, Alex Williamson wrote:
> > > vfio_region_info.flags in not currently tested for input therefore this
> > > proposal could lead to unexpected behavior for a caller that doesn't
> > > currently zero this field.  It's intended as an output-only field.  
> > 
> > Perhaps a REGION_INFO2 then?
> > 
> > I still think per-request is better than a global flag
> 
> I don't understand why we'd need a REGION_INFO2, we already have
> support for defining new regions.

It is not a new region, it is a modified mmap behavior for an existing
region.

> We'd populate these new regions only for BARs that support prefetch and
> mmap 

That's not the point, prefetch has nothing to do with write combining.

Every BAR can be mapped writecombining, it is up to the VFIO userspace
to understand if it can use it or not. The only use case for this
feature would be something like in DPDK.

VM side write combining is already handled by KVM allowing the VM to
upgrade the page attributes to WC from NC.

Doubling all the region indexes just for WC does not seem like a good
idea to me...

Jason

  reply	other threads:[~2024-08-01 17:13 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2024-07-31 15:53 [PATCH rfc] vfio-pci: Allow write combining Keith Busch
2024-08-01 14:19 ` Jason Gunthorpe
2024-08-01 15:41   ` Alex Williamson
2024-08-01 16:11     ` Jason Gunthorpe
2024-08-01 16:52       ` Alex Williamson
2024-08-01 17:13         ` Jason Gunthorpe [this message]
2024-08-01 17:33           ` Alex Williamson
2024-08-01 17:53             ` Jason Gunthorpe
2024-08-01 18:16               ` Alex Williamson
2024-08-02 11:53                 ` Jason Gunthorpe
2024-08-02 17:05                   ` Alex Williamson
2024-08-06 16:53                     ` Jason Gunthorpe
2024-08-06 18:43                       ` Alex Williamson
2024-08-07 14:19                         ` Jason Gunthorpe
2024-08-07 17:46                           ` Alex Williamson
2024-08-13 18:02                             ` Jason Gunthorpe
2024-08-02 14:24             ` Keith Busch
2024-08-02 14:33               ` Jason Gunthorpe
2024-08-06  7:19                 ` Tian, Kevin
2024-08-06 16:47                   ` Jason Gunthorpe
2024-08-15  5:05               ` Christoph Hellwig

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=20240801171355.GA4830@ziepe.ca \
    --to=jgg@ziepe.ca \
    --cc=alex.williamson@redhat.com \
    --cc=kbusch@kernel.org \
    --cc=kbusch@meta.com \
    --cc=kvm@vger.kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox