From: Jason Gunthorpe via iommu <iommu@lists.linux-foundation.org>
To: Robin Murphy <robin.murphy@arm.com>
Cc: "Tian, Kevin" <kevin.tian@intel.com>,
"Raj, Ashok" <ashok.raj@intel.com>,
David Airlie <airlied@linux.ie>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"iommu@lists.linux-foundation.org"
<iommu@lists.linux-foundation.org>,
"Pan, Jacob jun" <jacob.jun.pan@intel.com>,
Christoph Hellwig <hch@infradead.org>,
Alex Williamson <alex.williamson@redhat.com>,
Thierry Reding <thierry.reding@gmail.com>,
Ben Skeggs <bskeggs@redhat.com>, Daniel Vetter <daniel@ffwll.ch>,
Jonathan Hunter <jonathanh@nvidia.com>,
Will Deacon <will@kernel.org>
Subject: Re: [PATCH 0/7] iommu cleanup and refactoring
Date: Tue, 25 Jan 2022 11:16:02 -0400 [thread overview]
Message-ID: <20220125151602.GL84788@nvidia.com> (raw)
In-Reply-To: <7febcba4-f5bf-6bf6-6180-895b18d1b806@arm.com>
On Tue, Jan 25, 2022 at 02:48:02PM +0000, Robin Murphy wrote:
> Agreed, certainly an IOMMU_DOMAIN_SVA type that can both encapsulate the mm
> and effectively replace iommu_sva seems like a logical and fairly small next
> step. We already have the paradigm of different domain types supporting
> different ops, so initially an SVA domain would simply allow bind/unbind
> rather than attach/detach/map/unmap.
I hope we can quickly get to a PASID enabled generic attach/detach
scheme - we really need this to do the uAPI part of this interface.
> they are fundamentally different things in their own right, and the ideal
> API should give us the orthogonality to also bind a device to an SVA domain
> without PASID (e.g. for KVM stage 2, or userspace assignment of simpler
> fault/stall-tolerant devices), or attach PASIDs to regular iommu_domains.
Yes, these are orthogonal things. A iommu driver that supports PASID
ideally should support PASID enabled attach/detatch for every
iommu_domain type it supports.
SVA should not be entangled with PASID beyond that SVA is often used
with PASID - a SVA iommu_domain should be fully usable with a RID too.
I'm hoping to see the core iommu code provide some simplified "SVA"
API that under the covers creates a SVA domain and then does a normal
PASID attach using the global PASID in the mm_struct - the
driver should not care what, or even if, PASID is used for a SVA
domain.
Jason
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2022-01-25 15:16 UTC|newest]
Thread overview: 48+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-01-24 7:10 [PATCH 0/7] iommu cleanup and refactoring Lu Baolu
2022-01-24 7:10 ` [PATCH 1/7] iommu/vt-d: Remove guest pasid related callbacks Lu Baolu
2022-01-24 9:25 ` Christoph Hellwig
2022-01-24 7:10 ` [PATCH 2/7] iommu: Remove guest pasid related interfaces and definitions Lu Baolu
2022-01-24 9:26 ` Christoph Hellwig
2022-01-24 7:10 ` [PATCH 3/7] iommu/vt-d: Remove aux-domain related callbacks Lu Baolu
2022-01-24 9:26 ` Christoph Hellwig
2022-01-24 7:10 ` [PATCH 4/7] iommu: Remove aux-domain related interfaces and iommu_ops Lu Baolu
2022-01-24 9:27 ` Christoph Hellwig
2022-01-24 7:11 ` [PATCH 5/7] drm/nouveau/device: Get right pgsize_bitmap of iommu_domain Lu Baolu
2022-01-24 9:29 ` Christoph Hellwig
2022-01-25 2:59 ` Lu Baolu
2022-01-24 7:11 ` [PATCH 6/7] iommu: Use right way to retrieve iommu_ops Lu Baolu
2022-01-24 9:32 ` Christoph Hellwig
2022-01-25 3:01 ` Lu Baolu
2022-01-24 9:48 ` Tian, Kevin
2022-01-25 3:04 ` Lu Baolu
2022-01-24 17:36 ` Jason Gunthorpe via iommu
2022-01-25 3:18 ` Lu Baolu
2022-01-25 0:20 ` Robin Murphy
2022-01-25 3:54 ` Lu Baolu
2022-01-24 7:11 ` [PATCH 7/7] iommu: Add iommu_domain::domain_ops Lu Baolu
2022-01-24 9:37 ` Christoph Hellwig
2022-01-24 17:24 ` Jason Gunthorpe via iommu
2022-01-25 4:43 ` Lu Baolu
2022-01-25 4:42 ` Lu Baolu
2022-01-24 9:58 ` Tian, Kevin
2022-01-24 10:16 ` Jean-Philippe Brucker
2022-01-24 16:33 ` Jason Gunthorpe via iommu
2022-01-26 9:41 ` Jean-Philippe Brucker
2022-01-24 17:17 ` Jason Gunthorpe via iommu
2022-01-25 4:59 ` Lu Baolu
2022-01-25 12:37 ` Jason Gunthorpe via iommu
2022-01-24 17:55 ` Jason Gunthorpe via iommu
2022-01-25 5:04 ` Lu Baolu
2022-01-25 0:57 ` Robin Murphy
2022-01-25 6:27 ` Lu Baolu
2022-01-25 14:23 ` Robin Murphy
2022-01-25 15:00 ` Jason Gunthorpe via iommu
2022-01-24 9:46 ` [PATCH 0/7] iommu cleanup and refactoring Tian, Kevin
2022-01-24 17:44 ` Jason Gunthorpe via iommu
2022-01-25 1:11 ` Tian, Kevin
2022-01-25 14:48 ` Robin Murphy
2022-01-25 15:16 ` Jason Gunthorpe via iommu [this message]
2022-01-26 1:51 ` Lu Baolu
2022-01-26 13:27 ` Jason Gunthorpe via iommu
2022-01-26 14:00 ` Robin Murphy
2022-02-08 1:32 ` Lu Baolu
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=20220125151602.GL84788@nvidia.com \
--to=iommu@lists.linux-foundation.org \
--cc=airlied@linux.ie \
--cc=alex.williamson@redhat.com \
--cc=ashok.raj@intel.com \
--cc=bskeggs@redhat.com \
--cc=daniel@ffwll.ch \
--cc=hch@infradead.org \
--cc=jacob.jun.pan@intel.com \
--cc=jgg@nvidia.com \
--cc=jonathanh@nvidia.com \
--cc=kevin.tian@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=robin.murphy@arm.com \
--cc=thierry.reding@gmail.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;
as well as URLs for NNTP newsgroup(s).