Re: [RFC PATCH] iommu/arm-smmu-v3: Allow nested attach for PCI bridges without vDEVICE

> Don't use it that way?

Why not? We use pci=config_acs to configure ACS at kernel startup and enable direct PCIe peer-to-peer traffic between GPUs and NICs. All affected devices are assigned to the same VM and IOMMU domain, which also reduces the memory footprint by reducing the number of page tables and lowers IOTLB pressure.

________________________________________
From: Jason Gunthorpe <[email protected]>
Sent: Saturday, August 15, 2026 12:11 AM
To: Dmitry Malkin
Cc: Will Deacon; Robin Murphy; Joerg Roedel; Nicolin Chen; [email protected]; [email protected]; [email protected]; [email protected]; [email protected]; NB-Core Team
Subject: Re: [RFC PATCH] iommu/arm-smmu-v3: Allow nested attach for PCI bridges without vDEVICE

On Fri, Aug 14, 2026 at 06:56:05PM +0000, Dmitry Malkin wrote:
> Hi Jason,
>
> > If viommu should support multi-device groups, I'm not sure. I want to
> > know why you even have multi-device groups in the first place because
> > that is not normal at all.
>
> That is because of the 'pci=config_acs' kernel command-line
> parameter. This causes the kernel to create a single IOMMU group
> containing multiple PCIe devices, including the bridge (PCIe Root
> Port).

Don't use it that way?

If this is an nvidia system you should talk to your support team.

Jason