Re: [PATCH v2] PCI: Accept AtomicOps already enabled by the hypervisor

[Prica, Nikola]

Hi Christian, Gerd,

Yes, this fixes a recent regression that we recognized with 6.8.0-135-generic kernel release. And it is the commit that Gerd referenced. I'll add Fixes tag.

Thanks for your attention and help!

Regards,
Nikola

On 9/14/2026 3:54 PM, Christian König wrote:
> On 9/14/26 15:41, Gerd Bayer wrote:
> > On Mon, 2026-09-07 at 18:17 +0200, Nikola Prica wrote:
> > > From: Nikola Prica <nikola.prica@xxxxxxx>
> > >
> > > pci_enable_atomic_ops_to_root() currently fails when no root port is
> > > visible. That is common in passthrough guests (ESXi, Hyper-V): the
> > > endpoint is assigned to the VM, but the guest topology has no root
> > > port above it.
> > >
> > > In those setups the hypervisor may already have enabled AtomicOp
> > > requester enable on the device. If PCI_EXP_DEVCTL2_ATOMIC_REQ is set,
> > > treat AtomicOps as already enabled and return success instead of
> > > failing the Root Port walk.
> >
> > Hi Nikola,
> >
> > your patch got me interested, since it touches those parts of
> > pci_enable_atomic_ops_to_root() that commit 1ae8c4ce1570 ("PCI: Enable
> > AtomicOps only if Root Port supports them") has modified.
> >
> > I like your solution for putting the hypervisor in control of the
> > enablement of Atomic Ops on root-less PCI functions and did test your
> > change on s390/Connect-X, successfully.
> >
> > > Signed-off-by: Nikola Prica <nikola.prica@xxxxxxx>
> >
> > If that commit of mine regressed your use-cases, you might even want to
> > add a Fixes: tag?
>
> Oh, that's an interesting point. I wasn't aware that the root complex check was added so recently.
>
> So indeed question @Nikola did that worked out of the box before kernel 7.1? If yes then that would be a regression.
>
> Regards,
> Christian.
>
> > > ---
> > > Changes in v2:
> > > - Be more strict and only apply logic in headless device case.
> > >
> > >   drivers/pci/pci.c | 12 +++++++++++-
> > >   1 file changed, 11 insertions(+), 1 deletion(-)
> > >
> > > diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> > > index b2879a6be5f8..62729ade496f 100644
> > > --- a/drivers/pci/pci.c
> > > +++ b/drivers/pci/pci.c
> > > @@ -3769,8 +3769,18 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask)
> > >        }
> > >
> > >        root = pcie_find_root_port(dev);
> > > -     if (!root)
> > > +     if (!root) {
> > > +             /*
> > > +              * A hypervisor may expose a headless topology with no
> > > +              * visible root port.  If it has already set AtomicOp
> > > +              * Requester Enable, there is nothing more to do.
> > > +              */
> > > +             pcie_capability_read_dword(dev, PCI_EXP_DEVCTL2, &ctl2);
> > > +             if (ctl2 & PCI_EXP_DEVCTL2_ATOMIC_REQ)
> > > +                     return 0;
> > > +
> > >                return -EINVAL;
> > > +     }
> > >
> > >        pcie_capability_read_dword(root, PCI_EXP_DEVCAP2, &cap);
> > >        if ((cap & cap_mask) != cap_mask)
> >
> > At any rate, feel free to add my
> >
> > Reviewed-by: Gerd Bayer <gbayer@xxxxxxxxxxxxx>
> > Tested-by: Gerd Bayer <gbayer@xxxxxxxxxxxxx>