Re: [PATCH v5 1/2] PCI: AtomicOps: Do not enable without support in root complex

[Ilpo Järvinen]

On Mon, 23 Mar 2026, Gerd Bayer wrote:

> When inspecting the config space of a Connect-X physical function in an
> s390 system after it was initialized by the mlx5_core device driver, we
> found the function to be enabled to request AtomicOps despite the
> system's root-complex lacking support for completing them:
> 
> 1ed0:00:00.1 Ethernet controller: Mellanox Technologies MT2894 Family [ConnectX-6 Lx]
> 	Subsystem: Mellanox Technologies Device 0002
>   [...]
> 	DevCtl2: Completion Timeout: 50us to 50ms, TimeoutDis-
> 		 AtomicOpsCtl: ReqEn+
> 		 IDOReq- IDOCompl- LTR- EmergencyPowerReductionReq-
> 		 10BitTagReq- OBFF Disabled, EETLPPrefixBlk-
> 
> Turns out the device driver calls pci_enable_atomic_ops_to_root() which
> defaulted to enable AtomicOps requests even if it had no information
> about the root-port that the PCIe device is attached to. Similarly,
> AtomicOps requests are enabled for root-complex integrated endpoints
> (RCiEPs) unconditionally.
> 
> Change the logic of pci_enable_atomic_ops_to_root() to fully traverse the
> PCIe tree upwards, check that the bridge devices support delivering
> AtomicOps transactions, and finally check that there is a root-port at
> the end that does support completing AtomicOps - or that the support for
> completing AtomicOps at the root complex is announced through some other
> arch-specific way.
> 
> This announcement is implemented through the new
> pcibios_connects_to_atomicops_capable_rc() function - with a default
> implementation to always return "true" to leave the semantics for RCiEPs
> intact. For s390, override pcibios_connects_to_atomicops_capable_rc() to
> always return "false".
> 
> Do not change the enablement of AtomicOps requests if there is no
> positive confirmation that the root complex can complete PCIe AtomicOps.
> 
> Reported-by: Alexander Schmidt <alexs@xxxxxxxxxxxxx>
> Cc: stable@xxxxxxxxxxxxxxx
> Fixes: 430a23689dea ("PCI: Add pci_enable_atomic_ops_to_root()")
> Signed-off-by: Gerd Bayer <gbayer@xxxxxxxxxxxxx>
> ---
>  arch/s390/pci/pci.c |  5 +++++
>  drivers/pci/pci.c   | 46 +++++++++++++++++++++++++++++-----------------
>  include/linux/pci.h |  1 +
>  3 files changed, 35 insertions(+), 17 deletions(-)
> 
> diff --git a/arch/s390/pci/pci.c b/arch/s390/pci/pci.c
> index 2a430722cbe415dd56c92fed2e513e524f46481a..a13235d3218e8ca451e25fe8d9094500fa21aa26 100644
> --- a/arch/s390/pci/pci.c
> +++ b/arch/s390/pci/pci.c
> @@ -265,6 +265,11 @@ static int zpci_cfg_store(struct zpci_dev *zdev, int offset, u32 val, u8 len)
>  	return rc;
>  }
>  
> +bool pcibios_connects_to_atomicops_capable_rc(struct pci_dev *pdev, u32 cap_mask)
> +{
> +	return false;
> +}
> +
>  resource_size_t pcibios_align_resource(void *data, const struct resource *res,
>  				       resource_size_t size,
>  				       resource_size_t align)
> diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
> index 8479c2e1f74f1044416281aba11bf071ea89488a..c1143f8e6b2a0f029feb3c4390ac6f33837f6de1 100644
> --- a/drivers/pci/pci.c
> +++ b/drivers/pci/pci.c
> @@ -3660,6 +3660,21 @@ void pci_acs_init(struct pci_dev *dev)
>  	pci_disable_broken_acs_cap(dev);
>  }
>  
> +

Extra newline.

> +static bool pci_is_atomicops_capable_rp(struct pci_dev *dev, u32 cap, u32 cap_mask)
> +{
> +	if ((!dev) ||

Unnecessary parenthesis.

> +	     !(pci_pcie_type(dev) != PCI_EXP_TYPE_ROOT_PORT))

This fits to one line.

> +		return false;
> +
> +	return ((cap & cap_mask) == cap_mask);

Extra parenthesis.

> +}
> +
> +bool __weak pcibios_connects_to_atomicops_capable_rc(struct pci_dev *pdev, u32 cap_mask)
> +{
> +	return true;
> +}
> +
>  /**
>   * pci_enable_atomic_ops_to_root - enable AtomicOp requests to root port
>   * @dev: the PCI device
> @@ -3676,7 +3691,7 @@ void pci_acs_init(struct pci_dev *dev)
>  int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask)
>  {
>  	struct pci_bus *bus = dev->bus;
> -	struct pci_dev *bridge;
> +	struct pci_dev *bridge = NULL;
>  	u32 cap, ctl2;
>  
>  	/*
> @@ -3714,29 +3729,26 @@ int pci_enable_atomic_ops_to_root(struct pci_dev *dev, u32 cap_mask)
>  		switch (pci_pcie_type(bridge)) {
>  		/* Ensure switch ports support AtomicOp routing */
>  		case PCI_EXP_TYPE_UPSTREAM:
> -		case PCI_EXP_TYPE_DOWNSTREAM:
> -			if (!(cap & PCI_EXP_DEVCAP2_ATOMIC_ROUTE))
> -				return -EINVAL;
> -			break;
> -
> -		/* Ensure root port supports all the sizes we care about */
> -		case PCI_EXP_TYPE_ROOT_PORT:
> -			if ((cap & cap_mask) != cap_mask)
> -				return -EINVAL;
> -			break;
> -		}
> -
> -		/* Ensure upstream ports don't block AtomicOps on egress */
> -		if (pci_pcie_type(bridge) == PCI_EXP_TYPE_UPSTREAM) {
> +			/* Upstream ports must not block AtomicOps on egress */
>  			pcie_capability_read_dword(bridge, PCI_EXP_DEVCTL2,
>  						   &ctl2);
>  			if (ctl2 & PCI_EXP_DEVCTL2_ATOMIC_EGRESS_BLOCK)
>  				return -EINVAL;
> +			fallthrough;
> +		/* All switch ports need to route AtomicOps */
> +		case PCI_EXP_TYPE_DOWNSTREAM:
> +			if (!(cap & PCI_EXP_DEVCAP2_ATOMIC_ROUTE))
> +				return -EINVAL;
> +			break;
>  		}
> -
>  		bus = bus->parent;
>  	}
>  
> +	/* Finally, last bridge must be root port and support requested sizes */
> +	if (!(pci_is_atomicops_capable_rp(bridge, cap, cap_mask) ||
> +	     pcibios_connects_to_atomicops_capable_rc(dev, cap_mask)))
> +		return -EINVAL;
> +
>  	pcie_capability_set_word(dev, PCI_EXP_DEVCTL2,
>  				 PCI_EXP_DEVCTL2_ATOMIC_REQ);
>  	return 0;
> @@ -3813,7 +3825,7 @@ static int __pci_request_region(struct pci_dev *pdev, int bar,
>  
>  err_out:
>  	pci_warn(pdev, "BAR %d: can't reserve %pR\n", bar,
> -		 &pdev->resource[bar]);
> +			&pdev->resource[bar]);

Unrelated change.

>  	return -EBUSY;
>  }
>  
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index 1c270f1d512301de4d462fe7e5097c32af5c6f8d..498f266c9838c55e9b03d03fef49a82358047f4f 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -692,6 +692,7 @@ void pci_set_host_bridge_release(struct pci_host_bridge *bridge,
>  				 void *release_data);
>  
>  int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge);
> +bool pcibios_connects_to_atomicops_capable_rc(struct pci_dev *pdev, u32 cap_mask);
>  
>  #define PCI_REGION_FLAG_MASK	0x0fU	/* These bits of resource flags tell us the PCI region flags */
>  
> 
> 

-- 
 i.