[RFC PATCH] x86/mce: Provide sysfs interface to show CMCI storm state

From: Tony Luck
Date: Tue Jun 01 2021 - 16:05:24 EST


Scripts that process error logs can do better if they know whether
Linux is executing in CMCI storm mode (only polling and reporting
some errors instead of trying to report them all). While it is possible
to parse the console log for:

CMCI storm detected: switching to poll mode
CMCI storm subsided: switching to interrupt mode

messages, that is error prone.

Add a new file to sysfs to report the current storm count.

Reported-by: Christopher BeSerra <beserra@xxxxxxxxxx>
Signed-off-by: Tony Luck <tony.luck@xxxxxxxxx>
---

RFC questions:
1) Is there a better way to do this?
2) Maybe just return 0 or 1 instead of the count?
3) Is there a cleaner way to handle the CONFIG_X86_MCE_INTEL dependency

arch/x86/kernel/cpu/mce/core.c | 20 ++++++++++++++++++++
arch/x86/kernel/cpu/mce/intel.c | 5 +++++
2 files changed, 25 insertions(+)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index bf7fe87a7e88..4c4d6b1ec120 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -2431,6 +2431,20 @@ static ssize_t store_int_with_restart(struct device *s,
return ret;
}

+#ifndef CONFIG_X86_MCE_INTEL
+static int cmci_storm_value(void)
+{
+ return 0;
+}
+#else
+int cmci_storm_value(void);
+#endif
+
+static ssize_t show_storm(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", cmci_storm_value());
+}
+
static DEVICE_INT_ATTR(tolerant, 0644, mca_cfg.tolerant);
static DEVICE_INT_ATTR(monarch_timeout, 0644, mca_cfg.monarch_timeout);
static DEVICE_BOOL_ATTR(dont_log_ce, 0644, mca_cfg.dont_log_ce);
@@ -2451,6 +2465,11 @@ static struct dev_ext_attribute dev_attr_cmci_disabled = {
&mca_cfg.cmci_disabled
};

+static struct dev_ext_attribute dev_attr_show_storm = {
+ __ATTR(show_storm, 0444, show_storm, NULL),
+ NULL
+};
+
static struct device_attribute *mce_device_attrs[] = {
&dev_attr_tolerant.attr,
&dev_attr_check_interval.attr,
@@ -2462,6 +2481,7 @@ static struct device_attribute *mce_device_attrs[] = {
&dev_attr_print_all.attr,
&dev_attr_ignore_ce.attr,
&dev_attr_cmci_disabled.attr,
+ &dev_attr_show_storm.attr,
NULL
};

diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index acfd5d9f93c6..4edaa0608de3 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -73,6 +73,11 @@ enum {

static atomic_t cmci_storm_on_cpus;

+int cmci_storm_value(void)
+{
+ return atomic_read(&cmci_storm_on_cpus);
+}
+
static int cmci_supported(int *banks)
{
u64 cap;
--
2.29.2