From: David Hildenbrand <david@redhat.com>
To: Peter Xu <peterx@redhat.com>
Cc: "Daniel P. Berrangé" <berrange@redhat.com>,
"Eduardo Habkost" <ehabkost@redhat.com>,
"Michael S. Tsirkin" <mst@redhat.com>,
"Jason Wang" <jasowang@redhat.com>,
qemu-devel@nongnu.org, "Markus Armbruster" <armbru@redhat.com>,
"Eric Auger" <eric.auger@redhat.com>,
"Alex Williamson" <alex.williamson@redhat.com>,
"Paolo Bonzini" <pbonzini@redhat.com>,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>
Subject: Re: [PATCH 4/4] vl: Prioritize realizations of devices
Date: Wed, 25 Aug 2021 10:08:38 +0200 [thread overview]
Message-ID: <ca60c3c9-3372-53bb-04ff-dca1d2081e78@redhat.com> (raw)
In-Reply-To: <YSVOCUREQaw+rTen@t490s>
On 24.08.21 21:52, Peter Xu wrote:
> On Tue, Aug 24, 2021 at 06:24:27PM +0200, David Hildenbrand wrote:
>>>> Not so much; here's the list of priorities and the devices using it:
>>>>
>>>> |--------------------+---------|
>>>> | priority | devices |
>>>> |--------------------+---------|
>>>> | MIG_PRI_IOMMU | 3 |
>>>> | MIG_PRI_PCI_BUS | 7 |
>>>> | MIG_PRI_VIRTIO_MEM | 1 |
>>>> | MIG_PRI_GICV3_ITS | 1 |
>>>> | MIG_PRI_GICV3 | 1 |
>>>> |--------------------+---------|
>>>
>>> iommu is probably ok. I think virtio mem is ok too,
>>> in that it is normally created by virtio-mem-pci ...
>>
>> IIRC:
>>
>> intel-iommu has to be created on the QEMU cmdline before creating
>> virtio-mem-pci.
>>
>> -device intel-iommu,caching-mode=on,intremap=on,device-iotlb=on \
>> ...
>> -device virtio-mem-pci,disable-legacy=on,disable-modern=off,iommu_platform=on,ats=on,id=vm0,...
>>
>> Creating virtio-mem-pci will implicitly create virtio-mem. virtio-mem device
>> state has to be migrated before migrating intel-iommu state.
>
> Since we're at it.. frankly I didn't fully digest why virtio-mem needs to be
> migrated before when reading commit 0fd7616e0f1171b. It gives me the feeling
> more like that virtio-mem has a ordering dependency with vfio-pci not
> virtio-mem, but I could be wrong.
"We have to take care of incoming migration: at the point the
IOMMUs get restored and start creating mappings in vfio,
RamDiscardManager implementations might not be back up and running yet:
let's add runstate priorities to enforce the order when restoring.
s/runstate/vmstate/ :|
I recall that we can see IOMMU_NOTIFIER_MAP events when restoring an
IOMMU device. vfio_get_xlat_addr() would be called and could reject
mappings targeting virtio-mem memory in case the virtio-mem device has
not restored its bitmap from the migration stream such that
ram_discard_manager_is_populated() would be reliable. Consequently, we
have to restore the virtio-mem device state (not the virtio-mem-pci
device state!) before restoring an IOMMU.
>
> E.g., the IOMMU unit shouldn't be walking page table if without a device using
> it, then it won't fail until the device walks it in region_add() hooks when
> memory replay happens.
I recall it happened when switching to the iommu region e.g., in
vtd_post_load()->vtd_switch_address_space(). But I forgot the exact call
path.
--
Thanks,
David / dhildenb
next prev parent reply other threads:[~2021-08-25 8:09 UTC|newest]
Thread overview: 52+ messages / expand[flat|nested] mbox.gz Atom feed top
2021-08-18 19:42 [PATCH 0/4] vl: Prioritize device realizations Peter Xu
2021-08-18 19:42 ` [PATCH 1/4] qdev-monitor: Trace qdev creation Peter Xu
2021-08-18 19:43 ` [PATCH 2/4] qemu-config: Allow in-place sorting of QemuOptsList Peter Xu
2021-08-18 19:43 ` [PATCH 3/4] qdev: Export qdev_get_device_class() Peter Xu
2021-08-18 19:43 ` [PATCH 4/4] vl: Prioritize realizations of devices Peter Xu
2021-08-23 18:49 ` Eduardo Habkost
2021-08-23 19:18 ` Peter Xu
2021-08-23 21:07 ` Eduardo Habkost
2021-08-23 21:31 ` Peter Xu
2021-08-23 21:54 ` Michael S. Tsirkin
2021-08-23 22:51 ` Peter Xu
2021-08-23 21:56 ` Eduardo Habkost
2021-08-23 23:05 ` Peter Xu
2021-08-25 9:39 ` Markus Armbruster
2021-08-25 12:28 ` Markus Armbruster
2021-08-25 21:50 ` Peter Xu
2021-08-26 3:50 ` Peter Xu
2021-08-26 8:01 ` Markus Armbruster
2021-08-26 11:36 ` Igor Mammedov
2021-08-26 13:43 ` Peter Xu
2021-08-30 19:02 ` Peter Xu
2021-08-31 11:35 ` Markus Armbruster
2021-09-02 8:26 ` Igor Mammedov
2021-09-02 13:45 ` Peter Xu
2021-09-02 13:53 ` Daniel P. Berrangé
2021-09-02 14:21 ` Peter Xu
2021-09-02 14:57 ` Markus Armbruster
2021-09-03 15:48 ` Peter Xu
2021-09-02 15:06 ` Daniel P. Berrangé
2021-09-02 15:26 ` Markus Armbruster
2021-09-03 13:00 ` Igor Mammedov
2021-09-03 16:03 ` Peter Xu
2021-09-06 8:49 ` Igor Mammedov
2021-09-02 7:46 ` Igor Mammedov
2021-08-26 4:57 ` Markus Armbruster
2021-08-23 22:05 ` Michael S. Tsirkin
2021-08-23 22:36 ` Peter Xu
2021-08-24 2:52 ` Jason Wang
2021-08-24 15:50 ` Peter Xu
2021-08-25 4:23 ` Jason Wang
2021-09-06 9:22 ` Eric Auger
2021-08-24 16:24 ` David Hildenbrand
2021-08-24 19:52 ` Peter Xu
2021-08-25 8:08 ` David Hildenbrand [this message]
2021-08-24 2:51 ` Jason Wang
2021-10-20 13:44 ` [PATCH 0/4] vl: Prioritize device realizations David Hildenbrand
2021-10-20 13:48 ` Daniel P. Berrangé
2021-10-20 13:58 ` David Hildenbrand
2021-10-21 4:20 ` Peter Xu
2021-10-21 7:17 ` David Hildenbrand
2021-10-21 8:00 ` Peter Xu
2021-10-21 16:54 ` David Hildenbrand
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=ca60c3c9-3372-53bb-04ff-dca1d2081e78@redhat.com \
--to=david@redhat.com \
--cc=alex.williamson@redhat.com \
--cc=armbru@redhat.com \
--cc=berrange@redhat.com \
--cc=dgilbert@redhat.com \
--cc=ehabkost@redhat.com \
--cc=eric.auger@redhat.com \
--cc=jasowang@redhat.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=peterx@redhat.com \
--cc=qemu-devel@nongnu.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).