From: Jason Gunthorpe <jgg@ziepe.ca>
To: Vasant Hegde <vasant.hegde@amd.com>
Cc: Baolu Lu <baolu.lu@linux.intel.com>,
Joerg Roedel <joro@8bytes.org>,
"iommu@lists.linux.dev" <iommu@lists.linux.dev>,
Suravee Suthikulpanit <suravee.suthikulpanit@amd.com>,
Will Deacon <will@kernel.org>,
Robin Murphy <robin.murphy@arm.com>
Subject: Re: [RFC] iommu_ops->domain_alloc_paging() enhancement to support AMD IOMMU driver
Date: Fri, 28 Jun 2024 12:34:14 -0300 [thread overview]
Message-ID: <20240628153414.GZ791043@ziepe.ca> (raw)
In-Reply-To: <6df92d7e-6042-46df-971f-732e0ad4192d@amd.com>
On Fri, Jun 28, 2024 at 08:20:50PM +0530, Vasant Hegde wrote:
> > means the allocated domain requires PASID to support on both device and
> > IOMMU. If the hardware lacks this support, it should return failure.
>
> Sure. Flag is fine for us. We can do
> domain_alloc_paging(dev, flag)
>
> But that means:
> - For IOMMU_DOMAIN_DMA[_FQ] : pass DOMAIN_ALLOC_FLAG_PASID
> - DOMAIN_PAGING_UNMANAGED : *No* flags
As I said, VFIO would have to set the flag once it gets PASID support,
which is likely to happen in a few months.
So this won't solve the problem you stated of poor DID caching.
IMHO if you want to optimize the DID assignment then that is a
algorithm contained in the driver and we don't need to disturb any of
the core code or uAPI for you to make that optimization.
JAson
next prev parent reply other threads:[~2024-06-28 15:34 UTC|newest]
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-06-28 6:43 [RFC] iommu_ops->domain_alloc_paging() enhancement to support AMD IOMMU driver Vasant Hegde
2024-06-28 12:23 ` Baolu Lu
2024-06-28 13:06 ` Robin Murphy
2024-06-28 17:08 ` Vasant Hegde
2024-06-28 17:58 ` Robin Murphy
2024-07-01 10:28 ` Vasant Hegde
2024-06-28 14:50 ` Vasant Hegde
2024-06-28 15:34 ` Jason Gunthorpe [this message]
2024-06-28 13:03 ` Jason Gunthorpe
2024-06-28 17:49 ` Vasant Hegde
2024-06-28 18:04 ` Jason Gunthorpe
2024-07-01 10:48 ` Vasant Hegde
2024-07-01 17:26 ` Jason Gunthorpe
2024-07-03 5:42 ` Vasant Hegde
2024-07-03 6:57 ` Yi Liu
2024-07-09 18:23 ` Jason Gunthorpe
2024-07-10 4:17 ` Yi Liu
2024-07-11 23:49 ` Jason Gunthorpe
2024-07-12 13:40 ` Robin Murphy
2024-07-12 13:53 ` Jason Gunthorpe
2024-07-12 15:12 ` Robin Murphy
2024-07-12 15:19 ` Jason Gunthorpe
2024-07-15 8:46 ` Yi Liu
2024-07-11 10:15 ` Vasant Hegde
2024-07-11 13:56 ` Yi Liu
2024-07-12 1:39 ` Baolu Lu
2024-07-12 2:43 ` Yi Liu
2024-07-15 10:39 ` Vasant Hegde
2024-07-16 7:43 ` Yi Liu
2024-07-16 13:41 ` 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=20240628153414.GZ791043@ziepe.ca \
--to=jgg@ziepe.ca \
--cc=baolu.lu@linux.intel.com \
--cc=iommu@lists.linux.dev \
--cc=joro@8bytes.org \
--cc=robin.murphy@arm.com \
--cc=suravee.suthikulpanit@amd.com \
--cc=vasant.hegde@amd.com \
--cc=will@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