linux-kernel - Re: [PATCH v6 03/16] PCI/AER: Consolidate Error Source ID logging in aer_print_port

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <9ac2bb02-974f-4952-b069-1bcc94682d89@linux.intel.com>
Date: Mon, 19 May 2025 16:39:19 -0700
From: Sathyanarayanan Kuppuswamy <sathyanarayanan.kuppuswamy@...ux.intel.com>
To: Bjorn Helgaas <helgaas@...nel.org>, linux-pci@...r.kernel.org
Cc: Jon Pan-Doh <pandoh@...gle.com>,
 Karolina Stolarek <karolina.stolarek@...cle.com>,
 Martin Petersen <martin.petersen@...cle.com>,
 Ben Fuller <ben.fuller@...cle.com>, Drew Walton <drewwalton@...rosoft.com>,
 Anil Agrawal <anilagrawal@...a.com>, Tony Luck <tony.luck@...el.com>,
 Ilpo Järvinen <ilpo.jarvinen@...ux.intel.com>,
 Lukas Wunner <lukas@...ner.de>,
 Jonathan Cameron <Jonathan.Cameron@...wei.com>,
 Sargun Dhillon <sargun@...a.com>, "Paul E . McKenney" <paulmck@...nel.org>,
 Mahesh J Salgaonkar <mahesh@...ux.ibm.com>,
 Oliver O'Halloran <oohall@...il.com>, Kai-Heng Feng <kaihengf@...dia.com>,
 Keith Busch <kbusch@...nel.org>, Robert Richter <rrichter@....com>,
 Terry Bowman <terry.bowman@....com>, Shiju Jose <shiju.jose@...wei.com>,
 Dave Jiang <dave.jiang@...el.com>, linux-kernel@...r.kernel.org,
 linuxppc-dev@...ts.ozlabs.org, Bjorn Helgaas <bhelgaas@...gle.com>
Subject: Re: [PATCH v6 03/16] PCI/AER: Consolidate Error Source ID logging in
 aer_print_port_info()

Hi,

On 5/19/25 2:35 PM, Bjorn Helgaas wrote:
> From: Bjorn Helgaas <bhelgaas@...gle.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@...gle.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