From: Jason Gunthorpe <jgg@nvidia.com>
To: Catalin Marinas <catalin.marinas@arm.com>
Cc: Oliver Upton <oliver.upton@linux.dev>,
Ankit Agrawal <ankita@nvidia.com>,
Sean Christopherson <seanjc@google.com>,
Marc Zyngier <maz@kernel.org>,
"joey.gouly@arm.com" <joey.gouly@arm.com>,
"suzuki.poulose@arm.com" <suzuki.poulose@arm.com>,
"yuzenghui@huawei.com" <yuzenghui@huawei.com>,
"will@kernel.org" <will@kernel.org>,
"ryan.roberts@arm.com" <ryan.roberts@arm.com>,
"shahuang@redhat.com" <shahuang@redhat.com>,
"lpieralisi@kernel.org" <lpieralisi@kernel.org>,
"david@redhat.com" <david@redhat.com>,
Aniket Agashe <aniketa@nvidia.com>, Neo Jia <cjia@nvidia.com>,
Kirti Wankhede <kwankhede@nvidia.com>,
"Tarun Gupta (SW-GPU)" <targupta@nvidia.com>,
Vikram Sethi <vsethi@nvidia.com>,
Andy Currid <acurrid@nvidia.com>,
Alistair Popple <apopple@nvidia.com>,
John Hubbard <jhubbard@nvidia.com>,
Dan Williams <danw@nvidia.com>, Zhi Wang <zhiw@nvidia.com>,
Matt Ochs <mochs@nvidia.com>, Uday Dhoke <udhoke@nvidia.com>,
Dheeraj Nigam <dnigam@nvidia.com>,
Krishnakant Jaju <kjaju@nvidia.com>,
"alex.williamson@redhat.com" <alex.williamson@redhat.com>,
"sebastianene@google.com" <sebastianene@google.com>,
"coltonlewis@google.com" <coltonlewis@google.com>,
"kevin.tian@intel.com" <kevin.tian@intel.com>,
"yi.l.liu@intel.com" <yi.l.liu@intel.com>,
"ardb@kernel.org" <ardb@kernel.org>,
"akpm@linux-foundation.org" <akpm@linux-foundation.org>,
"gshan@redhat.com" <gshan@redhat.com>,
"linux-mm@kvack.org" <linux-mm@kvack.org>,
"ddutile@redhat.com" <ddutile@redhat.com>,
"tabba@google.com" <tabba@google.com>,
"qperret@google.com" <qperret@google.com>,
"kvmarm@lists.linux.dev" <kvmarm@lists.linux.dev>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
"linux-arm-kernel@lists.infradead.org"
<linux-arm-kernel@lists.infradead.org>
Subject: Re: [PATCH v3 1/1] KVM: arm64: Allow cacheable stage 2 mapping using VMA flags
Date: Tue, 22 Apr 2025 14:03:24 -0300 [thread overview]
Message-ID: <20250422170324.GB1645809@nvidia.com> (raw)
In-Reply-To: <aAfI2GR1__-1KQHn@arm.com>
On Tue, Apr 22, 2025 at 05:50:32PM +0100, Catalin Marinas wrote:
> So, for the above, the VMM needs to know that it somehow got into such
> situation. If it knows the device (VFIO) capabilities and that the user
> mapping is Cacheable, coupled with the new KVM CAP, it can infer that
> Stage 2 will be S2FWB, no need for a memory slot flag.
So long as the memslot creation fails for cachable PFNMAP without
S2FWB the VMM is fine. qemu will begin its first steps to startup the
migration destination and immediately fail. The migration will be
aborted before it even gets started on the source side.
As I said before, the present situation requires the site's
orchestration to manage compatibility for live migration of VFIO
devices. We only expect that the migration will abort early if the
site has made a configuration error.
> have such information, maybe a new memory slot flag can be used to probe
> what Stage 2 mapping is going to be: ask for KVM_MEM_PFNMAP_WB. If it
> fails, Stage 2 is Device/NC and can attempt again with the WB flag.
> It's a bit of a stretch for the KVM API but IIUC there's no option to
> query the properties of a memory slot.
I don't know of any use case for something like this. If VFIO gives
the VMM a cachable mapping there is no fallback to WB.
The operator could use a different VFIO device, one that doesn't need
cachable, but the VMM can't flip the VFIO device between modes on the
fly.
Jason
next prev parent reply other threads:[~2025-04-22 17:03 UTC|newest]
Thread overview: 61+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-03-10 10:30 [PATCH v3 0/1] KVM: arm64: Map GPU device memory as cacheable ankita
2025-03-10 10:30 ` [PATCH v3 1/1] KVM: arm64: Allow cacheable stage 2 mapping using VMA flags ankita
2025-03-10 11:54 ` Marc Zyngier
2025-03-11 3:42 ` Ankit Agrawal
2025-03-11 11:18 ` Marc Zyngier
2025-03-11 12:07 ` Ankit Agrawal
2025-03-12 8:21 ` Marc Zyngier
2025-03-17 5:55 ` Ankit Agrawal
2025-03-17 9:27 ` Marc Zyngier
2025-03-17 19:54 ` Catalin Marinas
2025-03-18 9:39 ` Marc Zyngier
2025-03-18 12:55 ` Jason Gunthorpe
2025-03-18 19:27 ` Catalin Marinas
2025-03-18 19:35 ` David Hildenbrand
2025-03-18 19:40 ` Oliver Upton
2025-03-20 3:30 ` bibo mao
2025-03-20 7:24 ` bibo mao
2025-03-18 23:17 ` Jason Gunthorpe
2025-03-19 18:03 ` Catalin Marinas
2025-03-18 19:30 ` Oliver Upton
2025-03-18 23:09 ` Jason Gunthorpe
2025-03-19 7:01 ` Oliver Upton
2025-03-19 17:04 ` Jason Gunthorpe
2025-03-19 18:11 ` Catalin Marinas
2025-03-19 19:22 ` Jason Gunthorpe
2025-03-19 21:48 ` Catalin Marinas
2025-03-26 8:31 ` Ankit Agrawal
2025-03-26 14:53 ` Sean Christopherson
2025-03-26 15:42 ` Marc Zyngier
2025-03-26 16:10 ` Sean Christopherson
2025-03-26 18:02 ` Marc Zyngier
2025-03-26 18:24 ` Sean Christopherson
2025-03-26 18:51 ` Oliver Upton
2025-03-31 14:44 ` Jason Gunthorpe
2025-03-31 14:56 ` Jason Gunthorpe
2025-04-07 15:20 ` Sean Christopherson
2025-04-07 16:15 ` Jason Gunthorpe
2025-04-07 16:43 ` Sean Christopherson
2025-04-16 8:51 ` Ankit Agrawal
2025-04-21 16:03 ` Ankit Agrawal
2025-04-22 7:49 ` Oliver Upton
2025-04-22 13:54 ` Jason Gunthorpe
2025-04-22 16:50 ` Catalin Marinas
2025-04-22 17:03 ` Jason Gunthorpe [this message]
2025-04-22 21:28 ` Oliver Upton
2025-04-22 23:35 ` Jason Gunthorpe
2025-04-23 10:45 ` Catalin Marinas
2025-04-23 12:02 ` Jason Gunthorpe
2025-04-23 12:26 ` Catalin Marinas
2025-04-23 13:03 ` Jason Gunthorpe
2025-04-29 10:47 ` Ankit Agrawal
2025-04-29 13:27 ` Catalin Marinas
2025-04-29 14:14 ` Jason Gunthorpe
2025-04-29 16:03 ` Catalin Marinas
2025-04-29 16:44 ` Jason Gunthorpe
2025-04-29 18:09 ` Catalin Marinas
2025-04-29 18:19 ` Jason Gunthorpe
2025-05-07 15:26 ` Ankit Agrawal
2025-05-09 12:47 ` Catalin Marinas
2025-04-22 14:53 ` Sean Christopherson
2025-03-18 12:57 ` 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=20250422170324.GB1645809@nvidia.com \
--to=jgg@nvidia.com \
--cc=acurrid@nvidia.com \
--cc=akpm@linux-foundation.org \
--cc=alex.williamson@redhat.com \
--cc=aniketa@nvidia.com \
--cc=ankita@nvidia.com \
--cc=apopple@nvidia.com \
--cc=ardb@kernel.org \
--cc=catalin.marinas@arm.com \
--cc=cjia@nvidia.com \
--cc=coltonlewis@google.com \
--cc=danw@nvidia.com \
--cc=david@redhat.com \
--cc=ddutile@redhat.com \
--cc=dnigam@nvidia.com \
--cc=gshan@redhat.com \
--cc=jhubbard@nvidia.com \
--cc=joey.gouly@arm.com \
--cc=kevin.tian@intel.com \
--cc=kjaju@nvidia.com \
--cc=kvmarm@lists.linux.dev \
--cc=kwankhede@nvidia.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lpieralisi@kernel.org \
--cc=maz@kernel.org \
--cc=mochs@nvidia.com \
--cc=oliver.upton@linux.dev \
--cc=qperret@google.com \
--cc=ryan.roberts@arm.com \
--cc=seanjc@google.com \
--cc=sebastianene@google.com \
--cc=shahuang@redhat.com \
--cc=suzuki.poulose@arm.com \
--cc=tabba@google.com \
--cc=targupta@nvidia.com \
--cc=udhoke@nvidia.com \
--cc=vsethi@nvidia.com \
--cc=will@kernel.org \
--cc=yi.l.liu@intel.com \
--cc=yuzenghui@huawei.com \
--cc=zhiw@nvidia.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox