linux-kernel - [PATCH 6/6 v7] ACPI: extlog: Trace CPER CXL Protocol Error Section

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: <20251104182446.863422-7-fabio.m.de.francesco@linux.intel.com>
Date: Tue,  4 Nov 2025 19:22:37 +0100
From: "Fabio M. De Francesco" <fabio.m.de.francesco@...ux.intel.com>
To: linux-cxl@...r.kernel.org
Cc: "Rafael J . Wysocki" <rafael@...nel.org>,
	Len Brown <lenb@...nel.org>,
	Tony Luck <tony.luck@...el.com>,
	Borislav Petkov <bp@...en8.de>,
	Hanjun Guo <guohanjun@...wei.com>,
	Mauro Carvalho Chehab <mchehab@...nel.org>,
	Shuai Xue <xueshuai@...ux.alibaba.com>,
	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>,
	linux-kernel@...r.kernel.org,
	linux-acpi@...r.kernel.org,
	linuxppc-dev@...ts.ozlabs.org,
	linux-pci@...r.kernel.org,
	"Fabio M. De Francesco" <fabio.m.de.francesco@...ux.intel.com>,
	Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@...ux.intel.com>
Subject: [PATCH 6/6 v7] 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.

Cc: Dan Williams <dan.j.williams@...el.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@...wei.com>
Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@...ux.intel.com>
Signed-off-by: Fabio M. De Francesco <fabio.m.de.francesco@...ux.intel.com>
---
 drivers/acpi/Kconfig       |  1 +
 drivers/acpi/acpi_extlog.c | 22 ++++++++++++++++++++++
 drivers/cxl/core/ras.c     |  3 ++-
 include/cxl/event.h        |  2 ++
 4 files changed, 27 insertions(+), 1 deletion(-)

diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig
index be02634f2320..c2ad24e77ddf 100644
--- a/drivers/acpi/Kconfig
+++ b/drivers/acpi/Kconfig
@@ -498,6 +498,7 @@ config ACPI_EXTLOG
 	select ACPI_APEI
 	select ACPI_APEI_PCIEAER
 	select UEFI_CPER
+	select CXL_BUS
 	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 b3976ceb4ee4..e6fb25395984 100644
--- a/drivers/acpi/acpi_extlog.c
+++ b/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>
@@ -160,6 +161,21 @@ static void extlog_print_pcie(struct cper_sec_pcie *pcie_err,
 	pci_dev_put(pdev);
 }
 
+static void
+extlog_cxl_cper_handle_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				int severity)
+{
+	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);
+}
+
 static int extlog_print(struct notifier_block *nb, unsigned long val,
 			void *data)
 {
@@ -211,6 +227,12 @@ 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);
 
diff --git a/drivers/cxl/core/ras.c b/drivers/cxl/core/ras.c
index 2731ba3a0799..a90480d07c87 100644
--- a/drivers/cxl/core/ras.c
+++ b/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)
 {
diff --git a/include/cxl/event.h b/include/cxl/event.h
index 94081aec597a..ff97fea718d2 100644
--- a/include/cxl/event.h
+++ b/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 */
-- 
2.51.1