From: Bjorn Helgaas <bhelgaas@google.com>

Previously we decoded the AER Error Source ID in two places.  Consolidate
them so both places use aer_print_port_info().  Add a "details" parameter
so we can add a note when we didn't find any downstream devices with errors
logged in their AER Capability.

When we didn't read any error details from the source device, we logged two
messages: one in aer_isr_one_error() and another in find_source_device().
Since they both contain the same information, only log the first one when
when find_source_device() has found error details.

This changes the dmesg logging when we found no devices with errors logged:

  - pci 0000:00:01.0: AER: Correctable error message received from 0000:02:00.0
  - pci 0000:00:01.0: AER: found no error details for 0000:02:00.0
  + pci 0000:00:01.0: AER: Correctable error message received from 0000:02:00.0 (no details found)

Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/pcie/aer.c | 30 ++++++++++++++++--------------
 1 file changed, 16 insertions(+), 14 deletions(-)

diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index a1cf8c7ef628..b8494ccd935b 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -733,16 +733,17 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
 			info->severity, info->tlp_header_valid, &info->tlp);
 }
 
-static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
+static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info,
+				const char *details)
 {
 	u8 bus = info->id >> 8;
 	u8 devfn = info->id & 0xff;
 
-	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
+	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d%s\n",
 		 info->multi_error_valid ? "Multiple " : "",
 		 aer_error_severity_string[info->severity],
 		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
-		 PCI_FUNC(devfn));
+		 PCI_FUNC(devfn), details);
 }
 
 #ifdef CONFIG_ACPI_APEI_PCIEAER
@@ -926,13 +927,13 @@ static bool find_source_device(struct pci_dev *parent,
 	else
 		pci_walk_bus(parent->subordinate, find_device_iter, e_info);
 
+	/*
+	 * If we didn't find any devices with errors logged in the AER
+	 * Capability, just print the Error Source ID from the Root Port or
+	 * RCEC that received an ERR_* Message.
+	 */
 	if (!e_info->error_dev_num) {
-		u8 bus = e_info->id >> 8;
-		u8 devfn = e_info->id & 0xff;
-
-		pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n",
-			 pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn),
-			 PCI_FUNC(devfn));
+		aer_print_port_info(parent, e_info, " (no details found)");
 		return false;
 	}
 	return true;
@@ -1297,10 +1298,11 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 			e_info.multi_error_valid = 1;
 		else
 			e_info.multi_error_valid = 0;
-		aer_print_port_info(pdev, &e_info);
 
-		if (find_source_device(pdev, &e_info))
+		if (find_source_device(pdev, &e_info)) {
+			aer_print_port_info(pdev, &e_info, "");
 			aer_process_err_devices(&e_info);
+		}
 	}
 
 	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
@@ -1316,10 +1318,10 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
 		else
 			e_info.multi_error_valid = 0;
 
-		aer_print_port_info(pdev, &e_info);
-
-		if (find_source_device(pdev, &e_info))
+		if (find_source_device(pdev, &e_info)) {
+			aer_print_port_info(pdev, &e_info, "");
 			aer_process_err_devices(&e_info);
+		}
 	}
 }
 
-- 
2.43.0

On Mon, 19 May 2025, Bjorn Helgaas wrote:

> From: Bjorn Helgaas <bhelgaas@google.com>
> 
> Previously we decoded the AER Error Source ID in two places.  Consolidate
> them so both places use aer_print_port_info().  Add a "details" parameter
> so we can add a note when we didn't find any downstream devices with errors
> logged in their AER Capability.
> 
> When we didn't read any error details from the source device, we logged two
> messages: one in aer_isr_one_error() and another in find_source_device().
> Since they both contain the same information, only log the first one when
> when find_source_device() has found error details.
> 
> This changes the dmesg logging when we found no devices with errors logged:
> 
>   - pci 0000:00:01.0: AER: Correctable error message received from 0000:02:00.0
>   - pci 0000:00:01.0: AER: found no error details for 0000:02:00.0
>   + pci 0000:00:01.0: AER: Correctable error message received from 0000:02:00.0 (no details found)
> 
> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
> ---
>  drivers/pci/pcie/aer.c | 30 ++++++++++++++++--------------
>  1 file changed, 16 insertions(+), 14 deletions(-)
> 
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index a1cf8c7ef628..b8494ccd935b 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -733,16 +733,17 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>  			info->severity, info->tlp_header_valid, &info->tlp);
>  }
>  
> -static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
> +static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info,
> +				const char *details)
>  {
>  	u8 bus = info->id >> 8;
>  	u8 devfn = info->id & 0xff;
>  
> -	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
> +	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d%s\n",
>  		 info->multi_error_valid ? "Multiple " : "",
>  		 aer_error_severity_string[info->severity],
>  		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
> -		 PCI_FUNC(devfn));
> +		 PCI_FUNC(devfn), details);
>  }
>  
>  #ifdef CONFIG_ACPI_APEI_PCIEAER
> @@ -926,13 +927,13 @@ static bool find_source_device(struct pci_dev *parent,
>  	else
>  		pci_walk_bus(parent->subordinate, find_device_iter, e_info);
>  
> +	/*
> +	 * If we didn't find any devices with errors logged in the AER
> +	 * Capability, just print the Error Source ID from the Root Port or
> +	 * RCEC that received an ERR_* Message.
> +	 */
>  	if (!e_info->error_dev_num) {
> -		u8 bus = e_info->id >> 8;
> -		u8 devfn = e_info->id & 0xff;
> -
> -		pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n",
> -			 pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn),
> -			 PCI_FUNC(devfn));
> +		aer_print_port_info(parent, e_info, " (no details found)");
>  		return false;
>  	}
>  	return true;
> @@ -1297,10 +1298,11 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
>  			e_info.multi_error_valid = 1;
>  		else
>  			e_info.multi_error_valid = 0;
> -		aer_print_port_info(pdev, &e_info);
>  
> -		if (find_source_device(pdev, &e_info))
> +		if (find_source_device(pdev, &e_info)) {
> +			aer_print_port_info(pdev, &e_info, "");
>  			aer_process_err_devices(&e_info);
> +		}
>  	}
>  
>  	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
> @@ -1316,10 +1318,10 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
>  		else
>  			e_info.multi_error_valid = 0;
>  
> -		aer_print_port_info(pdev, &e_info);
> -
> -		if (find_source_device(pdev, &e_info))
> +		if (find_source_device(pdev, &e_info)) {
> +			aer_print_port_info(pdev, &e_info, "");
>  			aer_process_err_devices(&e_info);
> +		}
>  	}
>  }
>  
> 

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

-- 
 i.

Hi,

On 5/19/25 2:35 PM, Bjorn Helgaas wrote:
> From: Bjorn Helgaas <bhelgaas@google.com>
>
> Previously we decoded the AER Error Source ID in two places.  Consolidate
> them so both places use aer_print_port_info().  Add a "details" parameter
> so we can add a note when we didn't find any downstream devices with errors
> logged in their AER Capability.
>
> When we didn't read any error details from the source device, we logged two
> messages: one in aer_isr_one_error() and another in find_source_device().
> Since they both contain the same information, only log the first one when
> when find_source_device() has found error details.
/s/when//
>
> This changes the dmesg logging when we found no devices with errors logged:
>
>    - pci 0000:00:01.0: AER: Correctable error message received from 0000:02:00.0
>    - pci 0000:00:01.0: AER: found no error details for 0000:02:00.0
>    + pci 0000:00:01.0: AER: Correctable error message received from 0000:02:00.0 (no details found)
>
> Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
> ---
>   drivers/pci/pcie/aer.c | 30 ++++++++++++++++--------------
>   1 file changed, 16 insertions(+), 14 deletions(-)
>
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index a1cf8c7ef628..b8494ccd935b 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -733,16 +733,17 @@ void aer_print_error(struct pci_dev *dev, struct aer_err_info *info)
>   			info->severity, info->tlp_header_valid, &info->tlp);
>   }
>   
> -static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info)
> +static void aer_print_port_info(struct pci_dev *dev, struct aer_err_info *info,
> +				const char *details)
>   {
>   	u8 bus = info->id >> 8;
>   	u8 devfn = info->id & 0xff;
>   
> -	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
> +	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d%s\n",

Instead of relying on the callers, why not add a space before details here?

>   		 info->multi_error_valid ? "Multiple " : "",
>   		 aer_error_severity_string[info->severity],
>   		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
> -		 PCI_FUNC(devfn));
> +		 PCI_FUNC(devfn), details);
>   }
>   
>   #ifdef CONFIG_ACPI_APEI_PCIEAER
> @@ -926,13 +927,13 @@ static bool find_source_device(struct pci_dev *parent,
>   	else
>   		pci_walk_bus(parent->subordinate, find_device_iter, e_info);
>   
> +	/*
> +	 * If we didn't find any devices with errors logged in the AER
> +	 * Capability, just print the Error Source ID from the Root Port or
> +	 * RCEC that received an ERR_* Message.
> +	 */
>   	if (!e_info->error_dev_num) {
> -		u8 bus = e_info->id >> 8;
> -		u8 devfn = e_info->id & 0xff;
> -
> -		pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n",
> -			 pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn),
> -			 PCI_FUNC(devfn));
> +		aer_print_port_info(parent, e_info, " (no details found)");
>   		return false;
>   	}
>   	return true;
> @@ -1297,10 +1298,11 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
>   			e_info.multi_error_valid = 1;
>   		else
>   			e_info.multi_error_valid = 0;
> -		aer_print_port_info(pdev, &e_info);
>   

Instead of printing the error information in find_source_device() (a helper function), I think it be better to print it here (the error handler). source_found = find_source_device(pdev, &e_info); aer_print_port_info(pdev, &e_info, source_found? "" : "(no details found) " );

if (source_found) aer_process_err_devices(&e_info)


> -		if (find_source_device(pdev, &e_info))
> +		if (find_source_device(pdev, &e_info)) {
> +			aer_print_port_info(pdev, &e_info, "");
>   			aer_process_err_devices(&e_info);
> +		}
>   	}
>   
>   	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
> @@ -1316,10 +1318,10 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
>   		else
>   			e_info.multi_error_valid = 0;
>   
> -		aer_print_port_info(pdev, &e_info);
> -
> -		if (find_source_device(pdev, &e_info))
> +		if (find_source_device(pdev, &e_info)) {
> +			aer_print_port_info(pdev, &e_info, "");
>   			aer_process_err_devices(&e_info);
> +		}
>   	}
>   }
>   

-- 
Sathyanarayanan Kuppuswamy
Linux Kernel Developer

On Mon, May 19, 2025 at 04:39:19PM -0700, Sathyanarayanan Kuppuswamy wrote:
> On 5/19/25 2:35 PM, Bjorn Helgaas wrote:
> > From: Bjorn Helgaas <bhelgaas@google.com>
> > 
> > Previously we decoded the AER Error Source ID in two places.  Consolidate
> > them so both places use aer_print_port_info().  Add a "details" parameter
> > so we can add a note when we didn't find any downstream devices with errors
> > logged in their AER Capability.
> > 
> > When we didn't read any error details from the source device, we logged two
> > messages: one in aer_isr_one_error() and another in find_source_device().
> > Since they both contain the same information, only log the first one when
> > when find_source_device() has found error details.
> /s/when//

Fixed, thanks!

> > -	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d\n",
> > +	pci_info(dev, "%s%s error message received from %04x:%02x:%02x.%d%s\n",
> 
> Instead of relying on the callers, why not add a space before details here?

Could, but I don't like adding an extra space at the end of the line
when the caller passes "".  The extra space could make the line wrap
unnecessarily.

> >   		 info->multi_error_valid ? "Multiple " : "",
> >   		 aer_error_severity_string[info->severity],
> >   		 pci_domain_nr(dev->bus), bus, PCI_SLOT(devfn),
> > -		 PCI_FUNC(devfn));
> > +		 PCI_FUNC(devfn), details);
> >   }
> >   #ifdef CONFIG_ACPI_APEI_PCIEAER
> > @@ -926,13 +927,13 @@ static bool find_source_device(struct pci_dev *parent,
> >   	else
> >   		pci_walk_bus(parent->subordinate, find_device_iter, e_info);
> > +	/*
> > +	 * If we didn't find any devices with errors logged in the AER
> > +	 * Capability, just print the Error Source ID from the Root Port or
> > +	 * RCEC that received an ERR_* Message.
> > +	 */
> >   	if (!e_info->error_dev_num) {
> > -		u8 bus = e_info->id >> 8;
> > -		u8 devfn = e_info->id & 0xff;
> > -
> > -		pci_info(parent, "found no error details for %04x:%02x:%02x.%d\n",
> > -			 pci_domain_nr(parent->bus), bus, PCI_SLOT(devfn),
> > -			 PCI_FUNC(devfn));
> > +		aer_print_port_info(parent, e_info, " (no details found)");
> >   		return false;
> >   	}
> >   	return true;
> > @@ -1297,10 +1298,11 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
> >   			e_info.multi_error_valid = 1;
> >   		else
> >   			e_info.multi_error_valid = 0;
> > -		aer_print_port_info(pdev, &e_info);
> 
> Instead of printing the error information in find_source_device() (a helper function), I think it be better to print it here (the error handler). source_found = find_source_device(pdev, &e_info); aer_print_port_info(pdev, &e_info, source_found? "" : "(no details found) " );
> 
> if (source_found) aer_process_err_devices(&e_info)

Great idea, thanks!  That looks much nicer.

> > -		if (find_source_device(pdev, &e_info))
> > +		if (find_source_device(pdev, &e_info)) {
> > +			aer_print_port_info(pdev, &e_info, "");
> >   			aer_process_err_devices(&e_info);
> > +		}
> >   	}
> >   	if (e_src->status & PCI_ERR_ROOT_UNCOR_RCV) {
> > @@ -1316,10 +1318,10 @@ static void aer_isr_one_error(struct aer_rpc *rpc,
> >   		else
> >   			e_info.multi_error_valid = 0;
> > -		aer_print_port_info(pdev, &e_info);
> > -
> > -		if (find_source_device(pdev, &e_info))
> > +		if (find_source_device(pdev, &e_info)) {
> > +			aer_print_port_info(pdev, &e_info, "");
> >   			aer_process_err_devices(&e_info);
> > +		}
> >   	}
> >   }
> 
> -- 
> Sathyanarayanan Kuppuswamy
> Linux Kernel Developer
>