From: "Daniel P. Berrangé" <berrange@redhat.com>
To: Jason Gunthorpe <jgg@nvidia.com>
Cc: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>,
qemu-arm@nongnu.org, qemu-devel@nongnu.org,
eric.auger@redhat.com, peter.maydell@linaro.org,
nicolinc@nvidia.com, ddutile@redhat.com, linuxarm@huawei.com,
wangzhou1@hisilicon.com, jiangkunkun@huawei.com,
jonathan.cameron@huawei.com, zhangfei.gao@linaro.org
Subject: Re: [RFC PATCH 0/5] hw/arm/virt: Add support for user-creatable nested SMMUv3
Date: Fri, 13 Dec 2024 13:19:46 +0000 [thread overview]
Message-ID: <Z1w0cgrK6Ri6smFM@redhat.com> (raw)
In-Reply-To: <Z1wsslDnwlth3A8+@nvidia.com>
On Fri, Dec 13, 2024 at 08:46:42AM -0400, Jason Gunthorpe wrote:
> On Fri, Dec 13, 2024 at 12:00:43PM +0000, Daniel P. Berrangé wrote:
> > On Fri, Nov 08, 2024 at 12:52:37PM +0000, Shameer Kolothum via wrote:
> > > Hi,
> > >
> > > This series adds initial support for a user-creatable "arm-smmuv3-nested"
> > > device to Qemu. At present the Qemu ARM SMMUv3 emulation is per machine
> > > and cannot support multiple SMMUv3s.
> > >
> > > In order to support vfio-pci dev assignment with vSMMUv3, the physical
> > > SMMUv3 has to be configured in nested mode. Having a pluggable
> > > "arm-smmuv3-nested" device enables us to have multiple vSMMUv3 for Guests
> > > running on a host with multiple physical SMMUv3s. A few benefits of doing
> > > this are,
> >
> > I'm not very familiar with arm, but from this description I'm not
> > really seeing how "nesting" is involved here. You're only talking
> > about the host and 1 L1 guest, no L2 guest.
>
> nesting is the term the iommu side is using to refer to the 2
> dimensional paging, ie a guest page table on top of a hypervisor page
> table.
>
> Nothing to do with vm nesting.
Ok, that naming is destined to cause confusion for many, given the
commonly understood use of 'nesting' in the context of VMs...
>
> > Also what is the relation between the physical SMMUv3 and the guest
> > SMMUv3 that's referenced ? Is this in fact some form of host device
> > passthrough rather than nesting ?
>
> It is an acceeleration feature, the iommu HW does more work instead of
> the software emulating things. Similar to how the 2d paging option in
> KVM is an acceleration feature.
>
> All of the iommu series on vfio are creating paravirtualized iommu
> models inside the VM. They access various levels of HW acceleration to
> speed up the paravirtualization.
... describing it as a HW accelerated iommu makes it significantly clearer
to me what this proposal is about. Perhaps the device is better named as
"arm-smmuv3-accel" ?
With regards,
Daniel
--
|: https://berrange.com -o- https://www.flickr.com/photos/dberrange :|
|: https://libvirt.org -o- https://fstop138.berrange.com :|
|: https://entangle-photo.org -o- https://www.instagram.com/dberrange :|
next prev parent reply other threads:[~2024-12-13 13:21 UTC|newest]
Thread overview: 150+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-08 12:52 [RFC PATCH 0/5] hw/arm/virt: Add support for user-creatable nested SMMUv3 Shameer Kolothum via
2024-11-08 12:52 ` [RFC PATCH 1/5] hw/arm/virt: Add an SMMU_IO_LEN macro Shameer Kolothum via
2024-11-13 16:48 ` Eric Auger
2024-11-08 12:52 ` [RFC PATCH 2/5] hw/arm/smmuv3: Add initial support for SMMUv3 Nested device Shameer Kolothum via
2024-11-13 17:12 ` Eric Auger
2024-11-13 18:05 ` Nicolin Chen
2024-11-26 18:28 ` Donald Dutile
2024-11-27 10:21 ` Shameerali Kolothum Thodi via
2024-11-27 16:00 ` Jason Gunthorpe
2024-11-27 16:05 ` Eric Auger
2024-11-28 3:25 ` Zhangfei Gao
2024-11-28 8:06 ` Eric Auger
2024-11-28 8:28 ` Shameerali Kolothum Thodi via
2024-11-28 8:41 ` Eric Auger
2024-11-28 12:52 ` Jason Gunthorpe
2024-11-27 23:03 ` Donald Dutile
2024-11-28 12:51 ` Jason Gunthorpe
2024-11-28 4:29 ` Donald Dutile
2024-11-28 4:44 ` Nicolin Chen
2024-11-28 12:54 ` Jason Gunthorpe
2024-11-28 18:22 ` Nicolin Chen
2024-12-02 18:53 ` Donald Dutile
2024-11-28 8:17 ` Shameerali Kolothum Thodi via
2024-11-14 8:20 ` Shameerali Kolothum Thodi via
2024-11-14 8:41 ` Eric Auger
2024-11-14 13:27 ` Shameerali Kolothum Thodi via
2024-11-15 22:32 ` Nicolin Chen
2024-11-13 18:00 ` Eric Auger
2024-11-08 12:52 ` [RFC PATCH 3/5] hw/arm/smmuv3: Associate a pci bus with a " Shameer Kolothum via
2024-11-13 17:58 ` Eric Auger
2024-11-14 8:30 ` Shameerali Kolothum Thodi via
2025-01-30 16:29 ` Daniel P. Berrangé
2025-01-30 18:19 ` Shameerali Kolothum Thodi via
2024-11-08 12:52 ` [RFC PATCH 4/5] hw/arm/virt-acpi-build: Build IORT with multiple SMMU nodes Shameer Kolothum via
2024-11-18 10:01 ` Eric Auger
2024-11-18 11:44 ` Shameerali Kolothum Thodi via
2024-11-18 13:45 ` Eric Auger
2024-11-18 15:00 ` Shameerali Kolothum Thodi via
2024-11-18 18:09 ` Eric Auger
2024-11-20 14:16 ` Shameerali Kolothum Thodi via
2024-11-20 16:10 ` Eric Auger
2024-11-20 16:26 ` Shameerali Kolothum Thodi via
2024-11-21 9:46 ` Shameerali Kolothum Thodi via
2024-12-10 20:48 ` Nicolin Chen
2024-12-11 15:21 ` Shameerali Kolothum Thodi via
2024-12-13 0:28 ` Nicolin Chen
2024-11-08 12:52 ` [RFC PATCH 5/5] hw/arm/virt-acpi-build: Add IORT RMR regions to handle MSI nested binding Shameer Kolothum via
2024-11-13 18:31 ` Nicolin Chen
2024-11-14 8:48 ` Shameerali Kolothum Thodi via
2024-11-14 10:41 ` Eric Auger
2024-11-15 22:12 ` Nicolin Chen
2024-12-10 23:01 ` Nicolin Chen
2024-12-11 0:48 ` Jason Gunthorpe
2024-12-11 1:28 ` Nicolin Chen
2024-12-11 13:11 ` Jason Gunthorpe
2024-12-11 17:20 ` Nicolin Chen
2024-12-11 18:01 ` Jason Gunthorpe
2024-11-12 22:59 ` [RFC PATCH 0/5] hw/arm/virt: Add support for user-creatable nested SMMUv3 Nicolin Chen
2024-11-14 7:56 ` Shameerali Kolothum Thodi via
2024-11-20 23:59 ` Nathan Chen
2024-11-21 10:12 ` Shameerali Kolothum Thodi via
2024-11-22 1:41 ` Nathan Chen
2024-11-22 17:38 ` Shameerali Kolothum Thodi via
2024-11-22 18:53 ` Nathan Chen
2025-02-04 14:00 ` Eric Auger
2024-12-13 11:58 ` Daniel P. Berrangé
2024-12-13 12:43 ` Jason Gunthorpe
2024-12-12 23:54 ` Nathan Chen
2024-12-13 1:01 ` Nathan Chen
2024-12-16 9:31 ` Shameerali Kolothum Thodi via
2025-01-25 2:43 ` Nathan Chen
2025-01-27 15:26 ` Shameerali Kolothum Thodi via
2025-01-27 23:35 ` Nathan Chen
2024-11-13 16:16 ` Mostafa Saleh
2024-11-14 8:01 ` Shameerali Kolothum Thodi via
2024-11-14 11:49 ` Mostafa Saleh
2024-11-13 21:42 ` Nicolin Chen
2024-11-14 9:11 ` Shameerali Kolothum Thodi via
2024-11-18 10:50 ` Eric Auger
2025-01-30 16:41 ` Daniel P. Berrangé
2024-12-13 12:00 ` Daniel P. Berrangé
2024-12-13 12:46 ` Jason Gunthorpe
2024-12-13 13:19 ` Daniel P. Berrangé [this message]
2024-12-16 9:38 ` Shameerali Kolothum Thodi via
2024-12-17 18:36 ` Donald Dutile
2024-12-13 13:33 ` Peter Maydell
2024-12-16 10:01 ` Shameerali Kolothum Thodi via
2025-01-09 4:45 ` Nicolin Chen
2025-01-11 4:05 ` Donald Dutile
2025-01-23 4:10 ` Nicolin Chen
2025-01-23 8:28 ` Shameerali Kolothum Thodi via
2025-01-23 8:40 ` Nicolin Chen
2025-01-23 11:07 ` Duan, Zhenzhong
2025-02-17 9:17 ` Duan, Zhenzhong
2025-02-18 6:52 ` Shameerali Kolothum Thodi via
2025-03-06 17:59 ` Eric Auger
2025-03-06 18:27 ` Shameerali Kolothum Thodi via
2025-03-06 18:40 ` Eric Auger
2025-01-31 16:54 ` Eric Auger
2025-02-03 18:50 ` Nicolin Chen
2025-02-04 17:49 ` Eric Auger
2025-02-05 0:08 ` Nicolin Chen
2025-02-05 10:43 ` Shameerali Kolothum Thodi via
2025-02-05 12:35 ` Eric Auger
2025-02-06 10:34 ` Shameerali Kolothum Thodi via
2025-02-06 18:58 ` Nicolin Chen
2025-03-03 15:21 ` Shameerali Kolothum Thodi via
2025-03-03 17:04 ` Nicolin Chen
2025-03-04 9:30 ` Shameerali Kolothum Thodi via
2025-01-30 16:00 ` Daniel P. Berrangé
2025-01-30 18:09 ` Shameerali Kolothum Thodi via
2025-01-31 9:33 ` Shameerali Kolothum Thodi via
2025-01-31 10:07 ` Eric Auger
2025-01-31 14:24 ` Jason Gunthorpe
2025-01-31 14:39 ` Shameerali Kolothum Thodi via
2025-01-31 14:54 ` Jason Gunthorpe
2025-01-31 15:23 ` Shameerali Kolothum Thodi via
2025-01-31 16:08 ` Eric Auger
2025-02-05 20:53 ` Nathan Chen
2025-02-06 8:54 ` Daniel P. Berrangé
2025-02-06 8:53 ` Daniel P. Berrangé
2025-02-06 16:44 ` Eric Auger
2025-01-31 21:41 ` Daniel P. Berrangé
2025-02-06 10:02 ` Shameerali Kolothum Thodi via
2025-02-06 10:37 ` Daniel P. Berrangé
2025-02-06 13:51 ` Shameerali Kolothum Thodi via
2025-02-06 14:46 ` Daniel P. Berrangé
2025-02-06 15:07 ` Shameerali Kolothum Thodi via
2025-02-06 17:02 ` Jason Gunthorpe
2025-02-06 17:10 ` Daniel P. Berrangé
2025-02-06 17:46 ` Jason Gunthorpe
2025-02-06 17:54 ` Daniel P. Berrangé
2025-02-06 17:58 ` Jason Gunthorpe
2025-02-06 18:04 ` Shameerali Kolothum Thodi via
2025-02-06 18:13 ` Jason Gunthorpe
2025-02-06 18:18 ` Shameerali Kolothum Thodi via
2025-02-06 18:22 ` Jason Gunthorpe
2025-02-06 20:33 ` Nicolin Chen
2025-02-06 20:38 ` Jason Gunthorpe
2025-02-06 20:48 ` Nicolin Chen
2025-02-06 21:11 ` Jason Gunthorpe
2025-02-06 22:46 ` Nicolin Chen
2025-02-07 0:08 ` Jason Gunthorpe
2025-02-07 10:21 ` Shameerali Kolothum Thodi via
2025-02-07 10:31 ` Daniel P. Berrangé
2025-02-07 12:21 ` Shameerali Kolothum Thodi via
2025-02-07 12:53 ` Jason Gunthorpe
2025-02-06 18:18 ` Daniel P. Berrangé
2025-02-06 17:57 ` Shameerali Kolothum Thodi via
2025-02-06 17:59 ` 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=Z1w0cgrK6Ri6smFM@redhat.com \
--to=berrange@redhat.com \
--cc=ddutile@redhat.com \
--cc=eric.auger@redhat.com \
--cc=jgg@nvidia.com \
--cc=jiangkunkun@huawei.com \
--cc=jonathan.cameron@huawei.com \
--cc=linuxarm@huawei.com \
--cc=nicolinc@nvidia.com \
--cc=peter.maydell@linaro.org \
--cc=qemu-arm@nongnu.org \
--cc=qemu-devel@nongnu.org \
--cc=shameerali.kolothum.thodi@huawei.com \
--cc=wangzhou1@hisilicon.com \
--cc=zhangfei.gao@linaro.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).