From: Jason Gunthorpe <jgg@nvidia.com>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: "Raj, Ashok" <ashok.raj@intel.com>,
Shenming Lu <lushenming@huawei.com>,
"Alex Williamson (alex.williamson@redhat.com)"
<alex.williamson@redhat.com>,
Jean-Philippe Brucker <jean-philippe@linaro.org>,
David Gibson <david@gibson.dropbear.id.au>,
Jason Wang <jasowang@redhat.com>,
"parav@mellanox.com" <parav@mellanox.com>,
"Enrico Weigelt, metux IT consult" <lkml@metux.net>,
Paolo Bonzini <pbonzini@redhat.com>,
Joerg Roedel <joro@8bytes.org>,
Eric Auger <eric.auger@redhat.com>,
Jonathan Corbet <corbet@lwn.net>,
"Liu, Yi L" <yi.l.liu@intel.com>, "Wu, Hao" <hao.wu@intel.com>,
"Jiang, Dave" <dave.jiang@intel.com>,
Jacob Pan <jacob.jun.pan@linux.intel.com>,
Kirti Wankhede <kwankhede@nvidia.com>,
Robin Murphy <robin.murphy@arm.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
"iommu@lists.linux-foundation.org"
<iommu@lists.linux-foundation.org>,
David Woodhouse <dwmw2@infradead.org>,
LKML <linux-kernel@vger.kernel.org>,
Lu Baolu <baolu.lu@linux.intel.com>,
"wanghaibin.wang@huawei.com" <wanghaibin.wang@huawei.com>
Subject: Re: [RFC v2] /dev/iommu uAPI proposal
Date: Fri, 16 Jul 2021 15:30:14 -0300 [thread overview]
Message-ID: <20210716183014.GN543781@nvidia.com> (raw)
In-Reply-To: <BN9PR11MB543337BAEA86708470AC1E0C8C119@BN9PR11MB5433.namprd11.prod.outlook.com>
On Fri, Jul 16, 2021 at 01:20:15AM +0000, Tian, Kevin wrote:
> One thought is to have vfio device driver deal with it. In this proposal
> it is the vfio device driver to define the PASID virtualization policy and
> report it to userspace via VFIO_DEVICE_GET_INFO. The driver understands
> the restriction thus could just hide the vPASID capability when the user
> calls GET_INFO on the 2nd mdev in above scenario. In this way the
> user even doesn't need to know such restriction at all and both mdevs
> can be assigned to a single VM w/o any problem.
I think it makes more sense to expose some kind of "pasid group" to
qemu that identifies that each PASID must be unique across the
group. For vIOMMUs that are doing funky things with the RID This means
a single PASID group must not be exposed as two RIDs to the guest.
If the kernel blocks it then it can never be fixed by updating the
vIOMMU design.
Jason
WARNING: multiple messages have this Message-ID (diff)
From: Jason Gunthorpe via iommu <iommu@lists.linux-foundation.org>
To: "Tian, Kevin" <kevin.tian@intel.com>
Cc: "kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Jason Wang <jasowang@redhat.com>,
Kirti Wankhede <kwankhede@nvidia.com>,
Jean-Philippe Brucker <jean-philippe@linaro.org>,
"Jiang, Dave" <dave.jiang@intel.com>,
"Raj, Ashok" <ashok.raj@intel.com>,
Jonathan Corbet <corbet@lwn.net>,
"wanghaibin.wang@huawei.com" <wanghaibin.wang@huawei.com>,
"parav@mellanox.com" <parav@mellanox.com>,
"Alex Williamson \(alex.williamson@redhat.com\)"
<alex.williamson@redhat.com>,
"Enrico Weigelt, metux IT consult" <lkml@metux.net>,
David Gibson <david@gibson.dropbear.id.au>,
Robin Murphy <robin.murphy@arm.com>,
LKML <linux-kernel@vger.kernel.org>,
Shenming Lu <lushenming@huawei.com>,
"iommu@lists.linux-foundation.org"
<iommu@lists.linux-foundation.org>,
Paolo Bonzini <pbonzini@redhat.com>,
David Woodhouse <dwmw2@infradead.org>
Subject: Re: [RFC v2] /dev/iommu uAPI proposal
Date: Fri, 16 Jul 2021 15:30:14 -0300 [thread overview]
Message-ID: <20210716183014.GN543781@nvidia.com> (raw)
In-Reply-To: <BN9PR11MB543337BAEA86708470AC1E0C8C119@BN9PR11MB5433.namprd11.prod.outlook.com>
On Fri, Jul 16, 2021 at 01:20:15AM +0000, Tian, Kevin wrote:
> One thought is to have vfio device driver deal with it. In this proposal
> it is the vfio device driver to define the PASID virtualization policy and
> report it to userspace via VFIO_DEVICE_GET_INFO. The driver understands
> the restriction thus could just hide the vPASID capability when the user
> calls GET_INFO on the 2nd mdev in above scenario. In this way the
> user even doesn't need to know such restriction at all and both mdevs
> can be assigned to a single VM w/o any problem.
I think it makes more sense to expose some kind of "pasid group" to
qemu that identifies that each PASID must be unique across the
group. For vIOMMUs that are doing funky things with the RID This means
a single PASID group must not be exposed as two RIDs to the guest.
If the kernel blocks it then it can never be fixed by updating the
vIOMMU design.
Jason
_______________________________________________
iommu mailing list
iommu@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/iommu
next prev parent reply other threads:[~2021-07-16 18:30 UTC|newest]
Thread overview: 120+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-07-09 7:48 [RFC v2] /dev/iommu uAPI proposal Tian, Kevin
2021-07-09 7:48 ` Tian, Kevin
2021-07-09 21:50 ` Alex Williamson
2021-07-09 21:50 ` Alex Williamson
2021-07-12 1:22 ` Tian, Kevin
2021-07-12 1:22 ` Tian, Kevin
2021-07-12 18:41 ` Alex Williamson
2021-07-12 18:41 ` Alex Williamson
2021-07-12 23:41 ` Tian, Kevin
2021-07-12 23:41 ` Tian, Kevin
2021-07-12 23:56 ` Tian, Kevin
2021-07-12 23:56 ` Tian, Kevin
2021-07-13 12:55 ` Jason Gunthorpe
2021-07-13 12:55 ` Jason Gunthorpe
2021-07-13 16:26 ` Alex Williamson
2021-07-13 16:26 ` Alex Williamson
2021-07-13 16:32 ` Jason Gunthorpe
2021-07-13 16:32 ` Jason Gunthorpe
2021-07-13 22:48 ` Tian, Kevin
2021-07-13 22:48 ` Tian, Kevin
2021-07-13 23:02 ` Jason Gunthorpe
2021-07-13 23:02 ` Jason Gunthorpe
2021-07-13 23:20 ` Tian, Kevin
2021-07-13 23:20 ` Tian, Kevin
2021-07-13 23:22 ` Jason Gunthorpe
2021-07-13 23:22 ` Jason Gunthorpe
2021-07-13 23:24 ` Tian, Kevin
2021-07-13 23:24 ` Tian, Kevin
2021-07-15 3:20 ` Shenming Lu
2021-07-15 3:20 ` Shenming Lu
2021-07-15 3:55 ` Tian, Kevin
2021-07-15 3:55 ` Tian, Kevin
2021-07-15 6:29 ` Shenming Lu
2021-07-15 6:29 ` Shenming Lu
2021-07-15 6:49 ` Tian, Kevin
2021-07-15 6:49 ` Tian, Kevin
2021-07-15 8:14 ` Shenming Lu
2021-07-15 8:14 ` Shenming Lu
2021-07-15 12:48 ` Jason Gunthorpe
2021-07-15 12:48 ` Jason Gunthorpe via iommu
2021-07-15 13:57 ` Raj, Ashok
2021-07-15 13:57 ` Raj, Ashok
2021-07-15 15:23 ` Jason Gunthorpe
2021-07-15 15:23 ` Jason Gunthorpe via iommu
2021-07-15 16:21 ` Raj, Ashok
2021-07-15 16:21 ` Raj, Ashok
2021-07-15 17:18 ` Jason Gunthorpe
2021-07-15 17:18 ` Jason Gunthorpe via iommu
2021-07-15 17:48 ` Raj, Ashok
2021-07-15 17:48 ` Raj, Ashok
2021-07-15 17:53 ` Jason Gunthorpe
2021-07-15 17:53 ` Jason Gunthorpe via iommu
2021-07-15 18:05 ` Raj, Ashok
2021-07-15 18:05 ` Raj, Ashok
2021-07-15 18:13 ` Jason Gunthorpe
2021-07-15 18:13 ` Jason Gunthorpe via iommu
2021-07-16 1:20 ` Tian, Kevin
2021-07-16 1:20 ` Tian, Kevin
2021-07-16 12:20 ` Shenming Lu
2021-07-16 12:20 ` Shenming Lu
2021-07-21 2:13 ` Tian, Kevin
2021-07-21 2:13 ` Tian, Kevin
2021-07-22 16:30 ` Jason Gunthorpe
2021-07-22 16:30 ` Jason Gunthorpe via iommu
2021-07-16 18:30 ` Jason Gunthorpe [this message]
2021-07-16 18:30 ` Jason Gunthorpe via iommu
2021-07-21 2:11 ` Tian, Kevin
2021-07-21 2:11 ` Tian, Kevin
2021-07-26 4:50 ` David Gibson
2021-07-26 4:50 ` David Gibson
2021-07-28 4:04 ` Tian, Kevin
2021-07-28 4:04 ` Tian, Kevin
2021-08-03 1:50 ` David Gibson
2021-08-03 1:50 ` David Gibson
2021-08-03 3:19 ` Tian, Kevin
2021-08-03 3:19 ` Tian, Kevin
2021-08-06 4:45 ` David Gibson
2021-08-06 4:45 ` David Gibson
2021-08-06 12:32 ` Jason Gunthorpe
2021-08-06 12:32 ` Jason Gunthorpe via iommu
2021-08-10 6:10 ` David Gibson
2021-08-10 6:10 ` David Gibson
2021-08-09 8:34 ` Tian, Kevin
2021-08-09 8:34 ` Tian, Kevin
2021-08-10 4:47 ` David Gibson
2021-08-10 4:47 ` David Gibson
2021-08-10 6:04 ` Tian, Kevin
2021-08-10 6:04 ` Tian, Kevin
2021-07-30 14:51 ` Jason Gunthorpe
2021-07-30 14:51 ` Jason Gunthorpe via iommu
2021-08-02 2:49 ` Tian, Kevin
2021-08-02 2:49 ` Tian, Kevin
2021-08-04 14:04 ` Jason Gunthorpe
2021-08-04 14:04 ` Jason Gunthorpe via iommu
2021-08-04 22:59 ` Tian, Kevin
2021-08-04 22:59 ` Tian, Kevin
2021-08-05 11:27 ` Jason Gunthorpe
2021-08-05 11:27 ` Jason Gunthorpe via iommu
2021-08-05 22:44 ` Tian, Kevin
2021-08-05 22:44 ` Tian, Kevin
2021-08-06 4:47 ` David Gibson
2021-08-06 4:47 ` David Gibson
2021-08-03 1:58 ` David Gibson
2021-08-03 1:58 ` David Gibson
2021-08-04 14:07 ` Jason Gunthorpe
2021-08-04 14:07 ` Jason Gunthorpe via iommu
2021-08-06 4:24 ` David Gibson
2021-08-06 4:24 ` David Gibson
2021-07-26 8:14 ` Jean-Philippe Brucker
2021-07-26 8:14 ` Jean-Philippe Brucker
2021-07-28 4:05 ` Tian, Kevin
2021-07-28 4:05 ` Tian, Kevin
2021-08-04 15:59 ` Eric Auger
2021-08-04 15:59 ` Eric Auger
2021-08-05 0:36 ` Tian, Kevin
2021-08-05 0:36 ` Tian, Kevin
2021-08-10 7:17 ` Eric Auger
2021-08-10 7:17 ` Eric Auger
2021-08-10 9:00 ` Tian, Kevin
2021-08-10 9:00 ` Tian, Kevin
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=20210716183014.GN543781@nvidia.com \
--to=jgg@nvidia.com \
--cc=alex.williamson@redhat.com \
--cc=ashok.raj@intel.com \
--cc=baolu.lu@linux.intel.com \
--cc=corbet@lwn.net \
--cc=dave.jiang@intel.com \
--cc=david@gibson.dropbear.id.au \
--cc=dwmw2@infradead.org \
--cc=eric.auger@redhat.com \
--cc=hao.wu@intel.com \
--cc=iommu@lists.linux-foundation.org \
--cc=jacob.jun.pan@linux.intel.com \
--cc=jasowang@redhat.com \
--cc=jean-philippe@linaro.org \
--cc=joro@8bytes.org \
--cc=kevin.tian@intel.com \
--cc=kvm@vger.kernel.org \
--cc=kwankhede@nvidia.com \
--cc=linux-kernel@vger.kernel.org \
--cc=lkml@metux.net \
--cc=lushenming@huawei.com \
--cc=parav@mellanox.com \
--cc=pbonzini@redhat.com \
--cc=robin.murphy@arm.com \
--cc=wanghaibin.wang@huawei.com \
--cc=yi.l.liu@intel.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.