Re: [PATCH] PCI/AER: Fix ratelimit and log level of Advisory Non-Fatal Errors

[Bjorn Helgaas <helgaas@kernel.org>]

On Sat, Aug 15, 2026 at 03:47:10PM +0200, Lukas Wunner wrote:
> When Advisory Non-Fatal Errors are reported, the Uncorrectable Error bits
> should be reported using the same ratelimit counter and log level as the
> accompanying Correctable Error.
> 
> This is done correctly when they are handled natively in aer_print_error()
> but it is not done correctly when they are handled in Firmware First mode
> in pci_print_aer().
> 
> Fix it.
> 
> Fixes: 21963e6e4e04 ("PCI/AER: Support Advisory Non-Fatal Errors")
> Signed-off-by: Lukas Wunner <lukas@wunner.de>
> ---
> The offending commit is the top-most one on pci/aer (queued for v7.3-rc1).
> This fix could either be folded into or applied on top of it.

Folded in, thanks!

>  drivers/pci/pcie/aer.c | 27 +++++++++++++++++++++------
>  1 file changed, 21 insertions(+), 6 deletions(-)
> 
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index 2a380bb..dd2aa5d 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -1028,13 +1028,15 @@ int cper_severity_to_aer(int cper_severity)
>  EXPORT_SYMBOL_GPL(cper_severity_to_aer);
>  #endif
>  
> -void pci_print_aer(struct pci_dev *dev, int aer_severity,
> -		   struct aer_capability_regs *aer)
> +static void __pci_print_aer(struct pci_dev *dev, int aer_severity,
> +			    struct aer_capability_regs *aer,
> +			    bool ratelimit_print, const char *level)
>  {
>  	const char *bus_type, *sev;
>  	int tlp_header_valid = 0;
>  	u32 status, mask;
>  	struct aer_err_info info = {
> +		.level = level,
>  		.severity = aer_severity,
>  		.first_error = PCI_ERR_CAP_FEP(aer->cap_control),
>  	};
> @@ -1043,12 +1045,10 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  		status = aer->cor_status;
>  		mask = aer->cor_mask;
>  		sev = "cor";
> -		info.level = KERN_WARNING;
>  	} else {
>  		status = aer->uncor_status;
>  		mask = aer->uncor_mask;
>  		sev = "uncor";
> -		info.level = KERN_ERR;
>  		tlp_header_valid = tlp_header_logged(status & ~mask,
>  						     aer->cap_control);
>  	}
> @@ -1067,7 +1067,7 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  	 * For Advisory Non-Fatal Errors, record statistics and tracing
>  	 * even if ratelimited
>  	 */
> -	if (!aer_ratelimit(dev, info.severity))
> +	if (!ratelimit_print)
>  		goto anfe;
>  
>  	aer_printk(info.level, dev,
> @@ -1094,10 +1094,25 @@ void pci_print_aer(struct pci_dev *dev, int aer_severity,
>  		if (anfe_status) {
>  			aer->uncor_status = anfe_status;
>  			aer->uncor_mask = 0;
> -			pci_print_aer(dev, AER_NONFATAL, aer);
> +			__pci_print_aer(dev, AER_NONFATAL, aer,
> +					ratelimit_print, level);
>  		}
>  	}
>  }
> +
> +void pci_print_aer(struct pci_dev *dev, int aer_severity,
> +		   struct aer_capability_regs *aer)
> +{
> +	/*
> +	 * Precalculate ratelimit counter and log level so that Advisory
> +	 * Non-Fatal Errors are treated like the accompanying Correctable Error
> +	 */
> +	bool ratelimit_print = aer_ratelimit(dev, aer_severity);
> +	const char *level = aer_severity == AER_CORRECTABLE ? KERN_WARNING
> +							    : KERN_ERR;
> +
> +	__pci_print_aer(dev, aer_severity, aer, ratelimit_print, level);
> +}
>  EXPORT_SYMBOL_GPL(pci_print_aer);
>  
>  /**
> 
> base-commit: 21963e6e4e0425b12d3128eea5a5104a3bc909c4
> -- 
> 2.53.0
>