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 for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20250429172109.3199192-4-fabio.m.de.francesco@linux.intel.com>
Date: Tue, 29 Apr 2025 19:21:08 +0200
From: "Fabio M. De Francesco" <fabio.m.de.francesco@...ux.intel.com>
To: "Rafael J . Wysocki" <rafael@...nel.org>,
	Len Brown <lenb@...nel.org>,
	Davidlohr Bueso <dave@...olabs.net>,
	Jonathan Cameron <jonathan.cameron@...wei.com>,
	Dave Jiang <dave.jiang@...el.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: "Fabio M. De Francesco" <fabio.m.de.francesco@...ux.intel.com>
Subject: [PATCH 3/4 v2] ACPI: extlog: Trace CPER PCI Express Error Section

I/O Machine Check Arcitecture 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>
---
 drivers/acpi/acpi_extlog.c | 30 ++++++++++++++++++++++++++++++
 drivers/pci/pcie/aer.c     |  2 +-
 include/linux/aer.h        | 13 +++++++++++--
 3 files changed, 42 insertions(+), 3 deletions(-)

diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
index caca6ccd6e99..7d7a813169f1 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/drivers/acpi/acpi_extlog.c
@@ -131,6 +131,32 @@ 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) {
+		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)
 {
@@ -182,6 +208,10 @@ 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 d0ebf7c15afa..627fcf434698 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 45d0fb2e2e75..737db92e6570 100644
--- a/include/linux/aer.h
+++ b/include/linux/aer.h
@@ -56,17 +56,26 @@ 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);
+#if defined(CONFIG_ACPI_APEI_PCIEAER)
 int cper_severity_to_aer(int cper_severity);
+#else
+static inline int cper_severity_to_aer(int cper_severity) { return 0; }
+#endif
+
 void aer_recover_queue(int domain, unsigned int bus, unsigned int devfn,
 		       int severity, struct aer_capability_regs *aer_regs);
 #endif //_AER_H_
-- 
2.48.1


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ