[PATCH v7 02/17] PCI/DPC: Log Error Source ID only when valid

Ilpo Järvinen ilpo.jarvinen at linux.intel.com
Wed May 21 20:09:07 AEST 2025


On Tue, 20 May 2025, Bjorn Helgaas wrote:

> From: Bjorn Helgaas <bhelgaas at google.com>
> 
> DPC Error Source ID is only valid when the DPC Trigger Reason indicates
> that DPC was triggered due to reception of an ERR_NONFATAL or ERR_FATAL
> Message (PCIe r6.0, sec 7.9.14.5).
> 
> When DPC was triggered by ERR_NONFATAL (PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE)
> or ERR_FATAL (PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) from a downstream device,
> log the Error Source ID (decoded into domain/bus/device/function).  Don't
> print the source otherwise, since it's not valid.
> 
> For DPC trigger due to reception of ERR_NONFATAL or ERR_FATAL, the dmesg
> logging changes:
> 
>   - pci 0000:00:01.0: DPC: containment event, status:0x000d source:0x0200
>   - pci 0000:00:01.0: DPC: ERR_FATAL detected
>   + pci 0000:00:01.0: DPC: containment event, status:0x000d, ERR_FATAL received from 0000:02:00.0
> 
> and when DPC triggered for other reasons, where DPC Error Source ID is
> undefined, e.g., unmasked uncorrectable error:
> 
>   - pci 0000:00:01.0: DPC: containment event, status:0x0009 source:0x0200
>   - pci 0000:00:01.0: DPC: unmasked uncorrectable error detected
>   + pci 0000:00:01.0: DPC: containment event, status:0x0009: unmasked uncorrectable error detected
> 
> Previously the "containment event" message was at KERN_INFO and the
> "%s detected" message was at KERN_WARNING.  Now the single message is at
> KERN_WARNING.
> 
> Signed-off-by: Bjorn Helgaas <bhelgaas at google.com>
> Tested-by: Krzysztof Wilczyński <kwilczynski at kernel.org>
> Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy at linux.intel.com>
> ---
>  drivers/pci/pcie/dpc.c | 64 ++++++++++++++++++++++++------------------
>  1 file changed, 36 insertions(+), 28 deletions(-)
> 
> diff --git a/drivers/pci/pcie/dpc.c b/drivers/pci/pcie/dpc.c
> index 3daaf61c79c9..9d85f1b3b761 100644
> --- a/drivers/pci/pcie/dpc.c
> +++ b/drivers/pci/pcie/dpc.c
> @@ -261,37 +261,45 @@ void dpc_process_error(struct pci_dev *pdev)
>  	struct aer_err_info info = {};
>  
>  	pci_read_config_word(pdev, cap + PCI_EXP_DPC_STATUS, &status);
> -	pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID, &source);
> -
> -	pci_info(pdev, "containment event, status:%#06x source:%#06x\n",
> -		 status, source);
>  
>  	reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN;
> -	ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
> -	pci_warn(pdev, "%s detected\n",
> -		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR) ?
> -		 "unmasked uncorrectable error" :
> -		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE) ?
> -		 "ERR_NONFATAL" :
> -		 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ?
> -		 "ERR_FATAL" :
> -		 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ?
> -		 "RP PIO error" :
> -		 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ?
> -		 "software trigger" :
> -		 "reserved error");
>  
> -	/* show RP PIO error detail information */
> -	if (pdev->dpc_rp_extensions &&
> -	    reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT &&
> -	    ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO)
> -		dpc_process_rp_pio_error(pdev);
> -	else if (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR &&
> -		 dpc_get_aer_uncorrect_severity(pdev, &info) &&
> -		 aer_get_device_error_info(pdev, &info)) {
> -		aer_print_error(pdev, &info);
> -		pci_aer_clear_nonfatal_status(pdev);
> -		pci_aer_clear_fatal_status(pdev);
> +	switch (reason) {
> +	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_UNCOR:
> +		pci_warn(pdev, "containment event, status:%#06x: unmasked uncorrectable error detected\n",
> +			 status);
> +		if (dpc_get_aer_uncorrect_severity(pdev, &info) &&
> +		    aer_get_device_error_info(pdev, &info)) {
> +			aer_print_error(pdev, &info);
> +			pci_aer_clear_nonfatal_status(pdev);
> +			pci_aer_clear_fatal_status(pdev);
> +		}
> +		break;
> +	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_NFE:
> +	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE:
> +		pci_read_config_word(pdev, cap + PCI_EXP_DPC_SOURCE_ID,
> +				     &source);
> +		pci_warn(pdev, "containment event, status:%#06x, %s received from %04x:%02x:%02x.%d\n",
> +			 status,
> +			 (reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_FE) ?
> +				"ERR_FATAL" : "ERR_NONFATAL",
> +			 pci_domain_nr(pdev->bus), PCI_BUS_NUM(source),
> +			 PCI_SLOT(source), PCI_FUNC(source));
> +		break;
> +	case PCI_EXP_DPC_STATUS_TRIGGER_RSN_IN_EXT:
> +		ext_reason = status & PCI_EXP_DPC_STATUS_TRIGGER_RSN_EXT;
> +		pci_warn(pdev, "containment event, status:%#06x: %s detected\n",
> +			 status,
> +			 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO) ?
> +			 "RP PIO error" :
> +			 (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_SW_TRIGGER) ?
> +			 "software trigger" :
> +			 "reserved error");
> +		/* show RP PIO error detail information */
> +		if (ext_reason == PCI_EXP_DPC_STATUS_TRIGGER_RSN_RP_PIO &&
> +		    pdev->dpc_rp_extensions)
> +			dpc_process_rp_pio_error(pdev);
> +		break;
>  	}
>  }
>  
> 

Reviewed-by: Ilpo Järvinen <ilpo.jarvinen at linux.intel.com>

-- 
 i.


More information about the Linuxppc-dev mailing list