| 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
| ||
|
Message-ID: <788af5cd-4e2d-4949-9d5a-9943f13da481@intel.com>
Date: Tue, 3 Jun 2025 14:33:43 -0700
From: Dave Jiang <dave.jiang@...el.com>
To: "Fabio M. De Francesco" <fabio.m.de.francesco@...ux.intel.com>,
"Rafael J . Wysocki" <rafael@...nel.org>, Len Brown <lenb@...nel.org>,
Davidlohr Bueso <dave@...olabs.net>,
Jonathan Cameron <jonathan.cameron@...wei.com>,
Alison Schofield <alison.schofield@...el.com>,
Vishal Verma <vishal.l.verma@...el.com>, Ira Weiny <ira.weiny@...el.com>,
Dan Williams <dan.j.williams@...el.com>,
Mahesh J Salgaonkar <mahesh@...ux.ibm.com>,
Oliver O'Halloran <oohall@...il.com>, Bjorn Helgaas <bhelgaas@...gle.com>,
Tony Luck <tony.luck@...el.com>, Borislav Petkov <bp@...en8.de>,
linux-kernel@...r.kernel.org, linux-acpi@...r.kernel.org,
linux-cxl@...r.kernel.org, linuxppc-dev@...ts.ozlabs.org,
linux-pci@...r.kernel.org, linux-edac@...r.kernel.org
Cc: Yazen Ghannam <yazen.ghannam@....com>
Subject: Re: [PATCH 3/4 v3] ACPI: extlog: Trace CPER PCI Express Error Section
On 6/3/25 8:54 AM, Fabio M. De Francesco wrote:
> I/O Machine Check Architecture events may signal failing PCIe components
> or links. The AER event contains details on what was happening on the wire
> when the error was signaled.
>
> Trace the CPER PCIe Error section (UEFI v2.10, Appendix N.2.7) reported
> by the I/O MCA.
>
> Cc: Dan Williams <dan.j.williams@...el.com>
> Signed-off-by: Fabio M. De Francesco <fabio.m.de.francesco@...ux.intel.com>
Reviewed-by: Dave Jiang <dave.jiang@...el.com>
> ---
> drivers/acpi/Kconfig | 1 +
> drivers/acpi/acpi_extlog.c | 32 ++++++++++++++++++++++++++++++++
> drivers/pci/pcie/aer.c | 2 +-
> include/linux/aer.h | 8 ++++++--
> 4 files changed, 40 insertions(+), 3 deletions(-)
>
> diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
> index 7bc40c2735ac0..2bbd9e4868ad7 100644
> --- a/drivers/acpi/Kconfig
> +++ b/drivers/acpi/Kconfig
> @@ -493,6 +493,7 @@ config ACPI_EXTLOG
> tristate "Extended Error Log support"
> depends on X86_MCE && X86_LOCAL_APIC && EDAC
> select UEFI_CPER
> + select ACPI_APEI_PCIEAER
> help
> Certain usages such as Predictive Failure Analysis (PFA) require
> more information about the error than what can be described in
> diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
> index 47d11cb5c9120..b2928ff297eda 100644
> --- a/drivers/acpi/acpi_extlog.c
> +++ b/drivers/acpi/acpi_extlog.c
> @@ -132,6 +132,34 @@ static int print_extlog_rcd(const char *pfx,
> return 1;
> }
>
> +static void extlog_print_pcie(struct cper_sec_pcie *pcie_err,
> + int severity)
> +{
> + struct aer_capability_regs *aer;
> + struct pci_dev *pdev;
> + unsigned int devfn;
> + unsigned int bus;
> + int aer_severity;
> + int domain;
> +
> + if (!(pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID ||
> + pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO))
> + return;
> +
> + aer_severity = cper_severity_to_aer(severity);
> + aer = (struct aer_capability_regs *)pcie_err->aer_info;
> + domain = pcie_err->device_id.segment;
> + bus = pcie_err->device_id.bus;
> + devfn = PCI_DEVFN(pcie_err->device_id.device,
> + pcie_err->device_id.function);
> + pdev = pci_get_domain_bus_and_slot(domain, bus, devfn);
> + if (!pdev)
> + return;
> +
> + pci_print_aer(KERN_DEBUG, pdev, aer_severity, aer);
> + pci_dev_put(pdev);
> +}
> +
> static int extlog_print(struct notifier_block *nb, unsigned long val,
> void *data)
> {
> @@ -183,6 +211,10 @@ static int extlog_print(struct notifier_block *nb, unsigned long val,
> if (gdata->error_data_length >= sizeof(*mem))
> trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
> (u8)gdata->error_severity);
> + } else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
> + struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
> +
> + extlog_print_pcie(pcie_err, gdata->error_severity);
> } else {
> void *err = acpi_hest_get_payload(gdata);
>
> diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
> index d0ebf7c15afa9..627fcf4346983 100644
> --- a/drivers/pci/pcie/aer.c
> +++ b/drivers/pci/pcie/aer.c
> @@ -801,7 +801,7 @@ void pci_print_aer(char *level, struct pci_dev *dev, int aer_severity,
> trace_aer_event(dev_name(&dev->dev), (status & ~mask),
> aer_severity, tlp_header_valid, &aer->header_log);
> }
> -EXPORT_SYMBOL_NS_GPL(pci_print_aer, "CXL");
> +EXPORT_SYMBOL_GPL(pci_print_aer);
>
> /**
> * add_error_device - list device to be handled
> diff --git a/include/linux/aer.h b/include/linux/aer.h
> index 45d0fb2e2e759..6ce433cee4625 100644
> --- a/include/linux/aer.h
> +++ b/include/linux/aer.h
> @@ -56,16 +56,20 @@ struct aer_capability_regs {
> #if defined(CONFIG_PCIEAER)
> int pci_aer_clear_nonfatal_status(struct pci_dev *dev);
> int pcie_aer_is_native(struct pci_dev *dev);
> +void pci_print_aer(char *level, struct pci_dev *dev, int aer_severity,
> + struct aer_capability_regs *aer);
> #else
> static inline int pci_aer_clear_nonfatal_status(struct pci_dev *dev)
> {
> return -EINVAL;
> }
> static inline int pcie_aer_is_native(struct pci_dev *dev) { return 0; }
> +static inline void pci_print_aer(char *level, struct pci_dev *dev,
> + int aer_severity,
> + struct aer_capability_regs *aer)
> +{ }
> #endif
>
> -void pci_print_aer(char *level, struct pci_dev *dev, int aer_severity,
> - struct aer_capability_regs *aer);
> int cper_severity_to_aer(int cper_severity);
> void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
> int severity, struct aer_capability_regs *aer_regs);
Powered by blists - more mailing lists