ACPI: extlog: Trace CPER CXL Protocol Error Section

When Firmware First is enabled, BIOS handles errors first and then it
makes them available to the kernel via the Common Platform Error Record
(CPER) sections (UEFI 2.11 Appendix N.2.13). Linux parses the CPER
sections via one of two similar paths, either ELOG or GHES. The errors
managed by ELOG are signaled to the BIOS by the I/O Machine Check
Architecture (I/O MCA).

Currently, ELOG and GHES show some inconsistencies in how they report to
userspace via trace events.

Therefore, make the two mentioned paths act similarly by tracing the CPER
CXL Protocol Error Section.

Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Fabio M. De Francesco <fabio.m.de.francesco@linux.intel.com>
Link: https://patch.msgid.link/20260114101543.85926-6-fabio.m.de.francesco@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>

Author: fdefranc

drivers/acpi/Kconfig

@@ -494,6 +494,8 @@ config ACPI_EXTLOG
 	tristate "Extended Error Log support"
 	depends on X86_MCE && X86_LOCAL_APIC && EDAC
 	select UEFI_CPER
+	select ACPI_APEI
+	select ACPI_APEI_GHES
 	help
 	  Certain usages such as Predictive Failure Analysis (PFA) require
 	  more information about the error than what can be described in

drivers/acpi/acpi_extlog.c

@@ -12,6 +12,7 @@
 #include <linux/ratelimit.h>
 #include <linux/edac.h>
 #include <linux/ras.h>
+#include <cxl/event.h>
 #include <acpi/ghes.h>
 #include <asm/cpu.h>
 #include <asm/mce.h>
@@ -162,6 +163,23 @@ static void extlog_print_pcie(struct cper_sec_pcie *pcie_err,
 #endif
 }
 
+static void
+extlog_cxl_cper_handle_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				int severity)
+{
+#ifdef ACPI_APEI_PCIEAER
+	struct cxl_cper_prot_err_work_data wd;
+
+	if (cxl_cper_sec_prot_err_valid(prot_err))
+		return;
+
+	if (cxl_cper_setup_prot_err_work_data(&wd, prot_err, severity))
+		return;
+
+	cxl_cper_handle_prot_err(&wd);
+#endif
+}
+
 static int extlog_print(struct notifier_block *nb, unsigned long val,
 			void *data)
 {
@@ -213,6 +231,12 @@ 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_CXL_PROT_ERR)) {
+			struct cxl_cper_sec_prot_err *prot_err =
+				acpi_hest_get_payload(gdata);
+
+			extlog_cxl_cper_handle_prot_err(prot_err,
+							gdata->error_severity);
 		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
 			struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
 

drivers/cxl/core/ras.c

@@ -63,7 +63,7 @@ static int match_memdev_by_parent(struct device *dev, const void *uport)
 	return 0;
 }
 
-static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
+void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 {
 	unsigned int devfn = PCI_DEVFN(data->prot_err.agent_addr.device,
 				       data->prot_err.agent_addr.function);
@@ -104,6 +104,7 @@ static void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *data)
 	else
 		cxl_cper_trace_uncorr_prot_err(cxlmd, data->ras_cap);
 }
+EXPORT_SYMBOL_GPL(cxl_cper_handle_prot_err);
 
 static void cxl_cper_prot_err_work_fn(struct work_struct *work)
 {

include/cxl/event.h

@@ -340,4 +340,6 @@ cxl_cper_setup_prot_err_work_data(struct cxl_cper_prot_err_work_data *wd,
 }
 #endif
 
+void cxl_cper_handle_prot_err(struct cxl_cper_prot_err_work_data *wd);
+
 #endif /* _LINUX_CXL_EVENT_H */