Re: [PATCH v18 10/13] cxl: Add port and dport identifiers to CXL AER trace events

[Jonathan Cameron <jic23@kernel.org>]

On Fri, 17 Jul 2026 17:27:03 -0500
Terry Bowman <terry.bowman@amd.com> wrote:

> From: Dan Williams <djbw@kernel.org>
> 
> Pass struct cxl_port * and struct cxl_dport * to the cxl_aer_*
> trace events instead of a plain struct device * derived at the
> caller. The trace event helpers then derive the right strings for
> endpoints, switch ports, root ports, and RCH downstream ports
> consistently across the CPER and native AER paths.
> 
> The unified cxl_aer_* events keep "memdev" as the legacy field
> (endpoint events populate it with the memdev name; non-endpoint
> events emit memdev="") and add new "port" and "dport" string fields
> populated for all CXL device classes. Updated userspace can key
> off "port" and "dport" without a parallel set of events.
> 
> Remove the separate cxl_port_aer_uncorrectable_error and
> cxl_port_aer_correctable_error trace events. All CXL AER events now
> use the unified cxl_aer_* events with port and dport fields.
> 
> Rework cxl_cper_handle_prot_err() to use find_cxl_port_by_dev() and
> the unified trace helpers, replacing the per-port-type branching and
> bus_find_device() memdev lookup.
> 
> The TP_printk format string places "port=%s dport=%s" between
> "memdev=%s" and "host=%s", changing the text-mode field order from
> the pre-patch output. This does not affect consumers such as
> rasdaemon that use libtraceevent to parse fields by name rather than
> by fixed text position.
> 
> For non-endpoint events (switch port, root port, RCH dport),
> "memdev" is empty and "port"/"dport" carry the topology information.
> 
> The serial number is retrieved via pci_get_dsn() which performs live
> PCI configuration space reads. A following patch ("PCI: Cache PCI
> DSN into pci_dev->dsn during probe") replaces these with a cached
> serial number to avoid config space access in error handlers and panic
> paths.
> 
> Below are examples of the different CXL devices' error trace logs
> after this patch:
> 
>      ---------------------
>      | CXL RP - 0C:00.0  |
>      ---------------------
>                |
>      ---------------------
>      | CXL USP - 0D:00.0 |
>      ---------------------
>                |
>      --------------------
>      | CXL DSP - 0E:00.0 |
>      --------------------
>                |
>      ---------------------
>      | CXL EP - 0F:00.0  |
>      ---------------------
> 
> Root Port:
> cxl_aer_correctable_error: memdev= port=port1 dport=0000:0c:00.0 \
>    host=pci0000:0c serial=0: status: 'Memory Data ECC Error'
> 
> cxl_aer_uncorrectable_error: memdev= port=port1 dport=0000:0c:00.0 \
>    host=pci0000:0c serial=0: status: 'Cache Address Parity Error'  \
>    first_error: 'Cache Address Parity Error'
> 
> Upstream Switch Port:
> cxl_aer_correctable_error: memdev= port=port2 dport= host=0000:0d:00.0 \
>    serial=0: status: 'Memory Data ECC Error'
> 
> UCE NA - Upstream Switch Port UCE's are handled in the portdrv driver's
> PCI AER callbacks that are not CXL aware.
> 
> Downstream Switch Port:
> cxl_aer_correctable_error: memdev= port=port2 dport=0000:0e:00.0 \
>    host=0000:0d:00.0 serial=0: status: 'Memory Data ECC Error'
> 
> cxl_aer_uncorrectable_error: memdev= port=port2 dport=0000:0e:00.0 \
>    host=0000:0d:00.0 serial=0: status: 'Cache Address Parity Error' \
>    first_error: 'Cache Address Parity Error'
> 
> Endpoint:
> cxl_aer_uncorrectable_error: memdev=mem1 port=endpoint4 dport= \
>    host=0000:0f:00.0 serial=0: status: 'Cache Address Parity Error' \
>    first_error: 'Cache Address Parity Error'
> 
> cxl_aer_correctable_error: memdev=mem1 port=endpoint4 dport= host=0000:0f:00.0 \
>    serial=0: status: 'Memory Data ECC Error'
> 
> Co-developed-by: Terry Bowman <terry.bowman@amd.com>
> Signed-off-by: Terry Bowman <terry.bowman@amd.com>
> Signed-off-by: Dan Williams <djbw@kernel.org>

One question inline about reference counts for the port.

> 
> diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
> index d5dc2c22565da..acf40b2396c3b 100644
> --- a/drivers/cxl/core/ras.c
> +++ b/drivers/cxl/core/ras.c
...
>  
> @@ -109,47 +77,34 @@ static struct cxl_port *find_cxl_port_by_dev(struct device *dev, struct cxl_dpor
>  
>  void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
>  {
> +	struct cxl_dport *dport;
>  	unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device,
>  				       data->prot_err.agent_addr.function);
> -	struct pci_dev *pdev __free(pci_dev_put) =
> -		pci_get_domain_bus_and_slot(data->prot_err.agent_addr.segment,
> -					    data->prot_err.agent_addr.bus,
> -					    devfn);
> -	struct cxl_memdev *cxlmd;
> -	int port_type;
> -
> -	if (!pdev)
> -		return;
> -
> -	port_type = pci_pcie_type(pdev);
> -	if (port_type == PCI_EXP_TYPE_ROOT_PORT ||
> -	    port_type == PCI_EXP_TYPE_DOWNSTREAM ||
> -	    port_type == PCI_EXP_TYPE_UPSTREAM) {
> -		if (data->severity == AER_CORRECTABLE)
> -			cxl_cper_trace_corr_port_prot_err(pdev, data->ras_cap);
> -		else
> -			cxl_cper_trace_uncorr_port_prot_err(pdev, data->ras_cap);
> -
> +	struct pci_dev *pdev __free(pci_dev_put) = pci_get_domain_bus_and_slot(
> +		data->prot_err.agent_addr.segment, data->prot_err.agent_addr.bus, devfn);
> +	if (!pdev) {
> +		pr_err_ratelimited("Failed to find CPER device in CXL topology\n");
>  		return;
>  	}
>  
> -	guard(device)(&pdev->dev);
> -	if (!pdev->dev.driver) {
> -		dev_warn_ratelimited(&pdev->dev,
> -				     "Device is unbound, abort CPER error handling\n");
> +	struct cxl_port *port __free(put_cxl_port) = find_cxl_port_by_dev(&pdev->dev, NULL);
> +	if (!port) {
> +		dev_err_ratelimited(&pdev->dev,
> +				    "Failed to find parent port device in CXL topology\n");
>  		return;
>  	}
>  
> -	struct device *mem_dev __free(put_device) = bus_find_device(
> -		&cxl_bus_type, NULL, pdev, match_memdev_by_parent);
> -	if (!mem_dev)
> -		return;
> +	guard(device)(&port->dev);

Don't we have a reference for this from find_cxl_port_by_dev()?

Superficially scope looks the same.


> +
> +	/* dport is NULL for Endpoint and Upstream Port devices */
> +	dport = cxl_find_dport_by_dev(port, &pdev->dev);
>  
> -	cxlmd = to_cxl_memdev(mem_dev);
>  	if (data->severity == AER_CORRECTABLE)
> -		cxl_cper_trace_corr_prot_err(cxlmd, data->ras_cap);
> +		cxl_cper_trace_corr_prot_err(port, dport, pci_get_dsn(pdev),
> +					     &data->ras_cap);
>  	else
> -		cxl_cper_trace_uncorr_prot_err(cxlmd, data->ras_cap);
> +		cxl_cper_trace_uncorr_prot_err(port, dport, pci_get_dsn(pdev),
> +					       &data->ras_cap);
>  }
>  EXPORT_SYMBOL_GPL(cxl_cper_handle_prot_err);
>  
> @@ -240,14 +195,14 @@ void cxl_do_recovery(struct pci_dev *pdev, struct cxl_port *port, struct cxl_dpo
>  		return;
>  	}
>  
> -	if (cxl_handle_ras(port, dport, ras_base))
> +	if (cxl_handle_ras(port, dport, ras_base, pci_get_dsn(pdev)))
>  		panic("CXL cachemem error");
>  
>  	dev_dbg(&pdev->dev,
>  		"CXL UCE signaled but no CXL RAS status bits set\n");
>  }
>  
> -void cxl_handle_cor_ras(struct cxl_port *port, struct cxl_dport *dport, void __iomem *ras_base)
> +void cxl_handle_cor_ras(struct cxl_port *port, struct cxl_dport *dport, void __iomem *ras_base, u64 serial)
That's over even the modern 100 char limit. Needs a line break.
>  {