Re: [RFC PATCH 0/5] PCI/vfio-pci: Guard resets against active SR-IOV VFs
From: Samiullah Khawaja
Date: Tue Nov 17 2026 - 18:31:20 EST
On Tue, Nov 17, 2026 at 03:02:00PM -0800, Vipin Sharma wrote:
On Thu, Aug 13, 2026 at 10:30:45PM +0000, Samiullah Khawaja wrote:
On Tue, Aug 11, 2026 at 10:53:18PM -0600, Alex Williamson wrote:
> It's recently been found[1] that vfio-pci doesn't restrict resets on PFs
> while SR-IOV is enabled. This can not only result in an uncoordinated
> disruption of the use of the associated VFs, but the ongoing use of and
> access to the VF has the potential to result in machine checks.
>
> This series proposes that this gap is largely an oversight of
> pci_reset_function() to recognize that a PF reset affecting SR-IOV VFs
> violates the scope boundary of the pci_reset_function() API.
Hi Alex,
Thanks for sending out the RFC to fix this issue. I cherry-picked it
into my environment to verify that whether it fixes the issue I was
experiencing and it does fix it. I will continue to do more testing, but
when you send this as a formal v1, you can add:
Tested-by: Samiullah Khawaja <skhawaja@xxxxxxxxxx>
Reported-by: Samiullah Khawaja <skhawaja@xxxxxxxxxx>
Hi Alex,
Is this series still on your radar for formal v1?
If this is the direction we are going in I can use it for liveupdate work
https://lore.kernel.org/all/auzftbPFO_6XBYVw%40google.com/
Thanks
Vipin
Hi Vipin,
Alex asked me whether I or someone on our team could pick up this
series. Pranjal is working on it and will send out a new version. There
is some extra work needed on the IOMMU side to make sure that the device
is moved to a blocking domain when the reset is skipped.
But I think the patch you need is fairly independent and can be sent out
separately from this series:
https://lore.kernel.org/kvm/20260812045325.2733631-6-alex.williamson@xxxxxxxxxx/
Thanks,
Sami