mce: acpi/apei: Honour Firmware First for MCA banks listed in APEI HEST CMC
The Corrected Machine Check structure (CMC) in HEST has a flag which can be
set by the firmware to indicate to the OS that it prefers to process the
corrected error events first. In this scenario, the OS is expected to not
monitor for corrected errors (through CMCI/polling). Instead, the firmware
notifies the OS on corrected error events through GHES.
Linux already has support for GHES. This patch adds support for parsing CMC
structure and to disable CMCI/polling if the firmware first flag is set.
Further, the list of machine check bank structures at the end of CMC is used
to determine which MCA banks function in FF mode, so that we continue to
monitor error events on the other banks.
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Acked-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Tony Luck <tony.luck@intel.com>
diff --git a/drivers/acpi/apei/hest.c b/drivers/acpi/apei/hest.c
index f5ef5d5..b108b11 100644
--- a/drivers/acpi/apei/hest.c
+++ b/drivers/acpi/apei/hest.c
@@ -36,6 +36,7 @@
#include <linux/io.h>
#include <linux/platform_device.h>
#include <acpi/apei.h>
+#include <asm/mce.h>
#include "apei-internal.h"
@@ -121,6 +122,40 @@
}
EXPORT_SYMBOL_GPL(apei_hest_parse);
+/*
+ * Check if firmware advertises firmware first mode. We need FF bit to be set
+ * along with a set of MC banks which work in FF mode.
+ */
+static int __init hest_parse_cmc(struct acpi_hest_header *hest_hdr, void *data)
+{
+ int i;
+ struct acpi_hest_ia_corrected *cmc;
+ struct acpi_hest_ia_error_bank *mc_bank;
+
+ if (hest_hdr->type != ACPI_HEST_TYPE_IA32_CORRECTED_CHECK)
+ return 0;
+
+ cmc = (struct acpi_hest_ia_corrected *)hest_hdr;
+ if (!cmc->enabled)
+ return 0;
+
+ /*
+ * We expect HEST to provide a list of MC banks that report errors
+ * in firmware first mode. Otherwise, return non-zero value to
+ * indicate that we are done parsing HEST.
+ */
+ if (!(cmc->flags & ACPI_HEST_FIRMWARE_FIRST) || !cmc->num_hardware_banks)
+ return 1;
+
+ pr_info(HEST_PFX "Enabling Firmware First mode for corrected errors.\n");
+
+ mc_bank = (struct acpi_hest_ia_error_bank *)(cmc + 1);
+ for (i = 0; i < cmc->num_hardware_banks; i++, mc_bank++)
+ mce_disable_bank(mc_bank->bank_number);
+
+ return 1;
+}
+
struct ghes_arr {
struct platform_device **ghes_devs;
unsigned int count;
@@ -227,6 +262,8 @@
goto err;
}
+ apei_hest_parse(hest_parse_cmc, NULL);
+
if (!ghes_disable) {
rc = apei_hest_parse(hest_parse_ghes_count, &ghes_count);
if (rc)