[PATCH v5 2/3] PCI: Allow ATS to be always on for pre-CXL devices

[Bjorn Helgaas]

On Wed, May 20, 2026 at 12:46:09PM -0700, Nicolin Chen wrote:
> Some NVIDIA GPU/NIC devices, though they don't implement CXL config space,
> have many CXL-like properties. Call this kind "pre-CXL".
> 
> Similar to CXL.cache capability, these pre-CXL devices also require the ATS
> function even when their RIDs are IOMMU bypassed, i.e. keep ATS "always on"
> v.s. "on demand" when a non-zero PASID line gets enabled in SVA use cases.
> 
> Introduce pci_dev_specific_ats_required() quirk function to scan a list of
> IDs for these devices. Then, include it in pci_ats_required().
> 
> Suggested-by: Jason Gunthorpe <jgg at nvidia.com>
> Reviewed-by: Nirmoy Das <nirmoyd at nvidia.com>
> Tested-by: Nirmoy Das <nirmoyd at nvidia.com>
> Reviewed-by: Jonathan Cameron <jonathan.cameron at huawei.com>
> Reviewed-by: Jason Gunthorpe <jgg at nvidia.com>
> Reviewed-by: Kevin Tian <kevin.tian at intel.com>
> Reviewed-by: Dave Jiang <dave.jiang at intel.com>
> Signed-off-by: Nicolin Chen <nicolinc at nvidia.com>

Acked-by: Bjorn Helgaas <bhelgaas at google.com>

> ---
>  drivers/pci/pci.h    |  9 +++++++++
>  drivers/pci/ats.c    |  3 ++-
>  drivers/pci/quirks.c | 42 ++++++++++++++++++++++++++++++++++++++++++
>  3 files changed, 53 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
> index 4a14f88e543a2..e8ad27abb1cfe 100644
> --- a/drivers/pci/pci.h
> +++ b/drivers/pci/pci.h
> @@ -1155,6 +1155,15 @@ static inline int pci_dev_specific_reset(struct pci_dev *dev, bool probe)
>  }
>  #endif
>  
> +#if defined(CONFIG_PCI_QUIRKS) && defined(CONFIG_PCI_ATS)
> +bool pci_dev_specific_ats_required(struct pci_dev *dev);
> +#else
> +static inline bool pci_dev_specific_ats_required(struct pci_dev *dev)
> +{
> +	return false;
> +}
> +#endif
> +
>  #if defined(CONFIG_PCI_QUIRKS) && defined(CONFIG_ARM64)
>  int acpi_get_rc_resources(struct device *dev, const char *hid, u16 segment,
>  			  struct resource *res);
> diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
> index ebdf761843867..3a04d5b04c883 100644
> --- a/drivers/pci/ats.c
> +++ b/drivers/pci/ats.c
> @@ -247,7 +247,8 @@ bool pci_ats_required(struct pci_dev *pdev)
>  	if (pdev->is_virtfn)
>  		pdev = pci_physfn(pdev);
>  
> -	return pci_cxl_ats_required(pdev);
> +	return pci_cxl_ats_required(pdev) ||
> +	       pci_dev_specific_ats_required(pdev);
>  }
>  EXPORT_SYMBOL_GPL(pci_ats_required);
>  
> diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
> index caaed1a01dc02..c0242f3e9f063 100644
> --- a/drivers/pci/quirks.c
> +++ b/drivers/pci/quirks.c
> @@ -5715,6 +5715,48 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1457, quirk_intel_e2000_no_ats);
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x1459, quirk_intel_e2000_no_ats);
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x145a, quirk_intel_e2000_no_ats);
>  DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_INTEL, 0x145c, quirk_intel_e2000_no_ats);
> +
> +static bool quirk_nvidia_gpu_ats_required(struct pci_dev *pdev)
> +{
> +	switch (pdev->device) {
> +	case 0x2e00 ... 0x2e3f: /* GB20B */
> +		return true;
> +	}
> +	return false;
> +}
> +
> +static const struct pci_dev_ats_required {
> +	u16 vendor;
> +	u16 device;
> +	bool (*ats_required)(struct pci_dev *dev);
> +} pci_dev_ats_required[] = {
> +	/* NVIDIA GPUs */
> +	{ PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID, quirk_nvidia_gpu_ats_required },
> +	/* NVIDIA CX10 Family NVlink-C2C */
> +	{ PCI_VENDOR_ID_MELLANOX, 0x2101, NULL },
> +	{ 0 }
> +};
> +
> +/*
> + * Some NVIDIA devices do not implement CXL config space, but present as PCIe
> + * devices that can issue CXL-like cache operations like CXL.cache. Thus, they
> + * require ATS to obtain host physical addresses, like pci_cxl_ats_required().
> + */
> +bool pci_dev_specific_ats_required(struct pci_dev *pdev)
> +{
> +	const struct pci_dev_ats_required *i;
> +
> +	for (i = pci_dev_ats_required; i->vendor; i++) {
> +		if (i->vendor != pdev->vendor)
> +			continue;
> +		if (i->ats_required && i->ats_required(pdev))
> +			return true;
> +		if (!i->ats_required && i->device == pdev->device)
> +			return true;
> +	}
> +
> +	return false;
> +}
>  #endif /* CONFIG_PCI_ATS */
>  
>  /* Freescale PCIe doesn't support MSI in RC mode */
> -- 
> 2.43.0
>