From: Jason Gunthorpe <jgg@ziepe.ca>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: Robin Murphy <robin.murphy@arm.com>,
Alexey Kardashevskiy <aik@ozlabs.ru>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Lu Baolu <baolu.lu@linux.intel.com>,
"Rodel, Jorg" <jroedel@suse.de>,
Alex Williamson <alex.williamson@redhat.com>,
"kvm-ppc@vger.kernel.org" <kvm-ppc@vger.kernel.org>
Subject: Re: [RFC PATCH kernel] vfio: Skip checking for IOMMU_CAP_CACHE_COHERENCY on POWER and more
Date: Sun, 03 Jul 2022 00:22:53 +0000 [thread overview]
Message-ID: <20220703002253.GY23621@ziepe.ca> (raw)
In-Reply-To: <BN9PR11MB5276F1DF0264115CA8FCB3EA8CBD9@BN9PR11MB5276.namprd11.prod.outlook.com>
On Fri, Jul 01, 2022 at 11:40:26PM +0000, Tian, Kevin wrote:
> But a bigger problem to me is how dma ownership is managed now on
> POWER. Previously it was guarded by BUG_ON and vfio_group_viable().
Yes. Simply removing or deferring this can't be good.
I think the solution is to not do iommu operations if there are no
iommu_ops, including allocating a blocking domain or trying to change
the domain - but continue to do all the refcounting/etc.
It is just another crufty work around for platforms that don't support
the iommu framework..
Jason
WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe <jgg@ziepe.ca>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: Robin Murphy <robin.murphy@arm.com>,
Alexey Kardashevskiy <aik@ozlabs.ru>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Lu Baolu <baolu.lu@linux.intel.com>,
"Rodel, Jorg" <jroedel@suse.de>,
Alex Williamson <alex.williamson@redhat.com>,
"kvm-ppc@vger.kernel.org" <kvm-ppc@vger.kernel.org>
Subject: Re: [RFC PATCH kernel] vfio: Skip checking for IOMMU_CAP_CACHE_COHERENCY on POWER and more
Date: Sat, 2 Jul 2022 21:22:53 -0300 [thread overview]
Message-ID: <20220703002253.GY23621@ziepe.ca> (raw)
In-Reply-To: <BN9PR11MB5276F1DF0264115CA8FCB3EA8CBD9@BN9PR11MB5276.namprd11.prod.outlook.com>
On Fri, Jul 01, 2022 at 11:40:26PM +0000, Tian, Kevin wrote:
> But a bigger problem to me is how dma ownership is managed now on
> POWER. Previously it was guarded by BUG_ON and vfio_group_viable().
Yes. Simply removing or deferring this can't be good.
I think the solution is to not do iommu operations if there are no
iommu_ops, including allocating a blocking domain or trying to change
the domain - but continue to do all the refcounting/etc.
It is just another crufty work around for platforms that don't support
the iommu framework..
Jason
next prev parent reply other threads:[~2022-07-03 0:22 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-07-01 6:17 [RFC PATCH kernel] vfio: Skip checking for IOMMU_CAP_CACHE_COHERENCY on POWER and more Alexey Kardashevskiy
2022-07-01 6:17 ` Alexey Kardashevskiy
2022-07-01 7:10 ` Tian, Kevin
2022-07-01 7:10 ` Tian, Kevin
2022-07-05 0:49 ` Jason Gunthorpe
2022-07-05 0:49 ` Jason Gunthorpe
2022-07-07 1:06 ` Tian, Kevin
2022-07-07 1:06 ` Tian, Kevin
2022-07-01 10:34 ` Robin Murphy
2022-07-01 10:34 ` Robin Murphy
2022-07-01 23:40 ` Tian, Kevin
2022-07-01 23:40 ` Tian, Kevin
2022-07-03 0:22 ` Jason Gunthorpe [this message]
2022-07-03 0:22 ` Jason Gunthorpe
2022-07-03 0:26 ` Jason Gunthorpe
2022-07-03 0:26 ` 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=20220703002253.GY23621@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=aik@ozlabs.ru \
--cc=alex.williamson@redhat.com \
--cc=baolu.lu@linux.intel.com \
--cc=jroedel@suse.de \
--cc=kevin.tian@intel.com \
--cc=kvm-ppc@vger.kernel.org \
--cc=kvm@vger.kernel.org \
--cc=robin.murphy@arm.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 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.