Re: [PATCH v7 1/3] PCI: AtomicOps: Do not enable requests by RCiEPs

[Bjorn Helgaas <helgaas@kernel.org>]

On Tue, Mar 31, 2026 at 02:39:26PM -0400, Kuehling, Felix wrote:
> On 2026-03-31 14:09, Bjorn Helgaas wrote:
> > On Mon, Mar 30, 2026 at 08:01:57PM -0400, Kuehling, Felix wrote:
> > > On 2026-03-30 17:42, Bjorn Helgaas wrote:
> > > > [+to amdgpu, bnxe_re, mlx5 IB, qedr, mlx5 maintainers]
> > > > 
> > > > On Mon, Mar 30, 2026 at 03:09:44PM +0200, Gerd Bayer wrote:
> > > > > Since root complex integrated end points (RCiEPs) attach to a bus that
> > > > > has no bridge device describing the root port, the capability to
> > > > > complete AtomicOps requests cannot be determined with PCIe methods.
> > > > > 
> > > > > Change default of pci_enable_atomic_ops_to_root() to not enable
> > > > > AtomicOps requests on RCiEPs.
> > > > I know I suggested this because there's nothing explicit that tells us
> > > > whether the RC supports atomic ops from RCiEPs [1].  But I'm concerned
> > > > that GPUs, infiniband HCAs, and NICs that use atomic ops may be
> > > > implemented as RCiEPs and would be broken by this.
> > > FWIW, on AMD APUs our driver doesn't call pci_enable_atomic_ops_to_root. It
> > > just assumes that the GPU can do atomic accesses because it doesn't actually
> > > go through PCIe: https://elixir.bootlin.com/linux/v6.19.10/source/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c#L4785
> > What does this mean for the other branch that *does* use
> > pci_enable_atomic_ops_to_root()?  Can any of those devices be RCiEPs?
> 
> Most AMD GPUs are not integrated endpoints. APUs are integrated. There are
> A+A GPUs where the GPUs are separate from the CPU but part of the same
> coherent data fabric as the CPU (adev->gmc.xbmi.connected_to_cpu == true).
> Those may also be considered RCiEPs. (I'm not sure about that, is there an
> easy way to check with lspci?) We may need to include that in the same
> branch as APUs.

Yep, for RCiEPs, "lspci -v" should say something like this:

  Capabilities: [64] Express Root Complex Integrated Endpoint

Dmesg logs from recent kernels would also include it like this:

  pci 0000:00:02.0: [8086:5916] type 00 class 0x030000 PCIe Root Complex Integrated Endpoint

An RCiEP would be on the root bus; it would not be below a Root Port.

> You can see that we did that for a new generation of A+A GPU here: https://gitlab.freedesktop.org/agd5f/linux/-/blob/amd-staging-drm-next/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c?ref_type=heads#L3920.
> We'd need to confirm that the same works for MI200 A+A GPUs as well.

> > > > These drivers use pci_enable_atomic_ops_to_root():
> > > > 
> > > >     amdgpu
> > > >     bnxt_re (infiniband)
> > > >     mlx5 (infinband)
> > > >     qedr (infiniband)
> > > >     mlx5 (ethernet)
> > > > 
> > > > Maybe we should assume that because RCiEPs are directly integrated
> > > > into the RC, the RCiEP would only allow AtomicOp Requester Enable to
> > > > be set if the RC supports atomic ops?
> > > > 
> > > > I don't like making assumptions like that, but it'd be worse to break
> > > > these devices.
> > > > 
> > > > [1] https://lore.kernel.org/all/20260326164002.GA1325368@bhelgaas
> > > > 
> > > > > Signed-off-by: Gerd Bayer <gbayer@linux.ibm.com>
> > > > > ---
> > > > >    drivers/pci/pci.c | 5 ++---
> > > > >    1 file changed, 2 insertions(+), 3 deletions(-)
> > > > > 
> > > > > diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> > > > > index 8479c2e1f74f1044416281aba11bf071ea89488a..135e5b591df405e87e7f520a618d7e2ccba55ce1 100644
> > > > > --- a/drivers/pci/pci.c
> > > > > +++ b/drivers/pci/pci.c
> > > > > @@ -3692,15 +3692,14 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask)
> > > > >    	/*
> > > > >    	 * Per PCIe r4.0, sec 6.15, endpoints and root ports may be
> > > > > -	 * AtomicOp requesters.  For now, we only support endpoints as
> > > > > -	 * requesters and root ports as completers.  No endpoints as
> > > > > +	 * AtomicOp requesters.  For now, we only support (legacy) endpoints
> > > > > +	 * as requesters and root ports as completers.  No endpoints as
> > > > >    	 * completers, and no peer-to-peer.
> > > > >    	 */
> > > > >    	switch (pci_pcie_type(dev)) {
> > > > >    	case PCI_EXP_TYPE_ENDPOINT:
> > > > >    	case PCI_EXP_TYPE_LEG_END:
> > > > > -	case PCI_EXP_TYPE_RC_END:
> > > > >    		break;
> > > > >    	default:
> > > > >    		return -EINVAL;
> > > > > 
> > > > > -- 
> > > > > 2.51.0
> > > > >