Hi Breno,
On 02/02/26 at 06:27am, Breno Leitao wrote:
> Add a sysfs directory at /sys/kernel/hwerr_recovery_stats/ to expose
> hardware error recovery statistics that are already tracked by the
> kernel. This allows userspace monitoring tools to track recovered
> hardware errors without requiring kernel crashes.
>
> This is useful to track recoverable hardware errors in a time series,
> even if the host doesn't crash.
>
> The sysfs directory contains one file per error subsystem:
>
> /sys/kernel/hwerr_recovery_stats/cpu - CPU-related errors (MCE, ARM
> errors)
> /sys/kernel/hwerr_recovery_stats/memory - Memory-related errors
> /sys/kernel/hwerr_recovery_stats/pci - PCI/PCIe AER non-fatal errors
> /sys/kernel/hwerr_recovery_stats/cxl - CXL errors
> /sys/kernel/hwerr_recovery_stats/others - Other hardware errors
>
> Each file contains a single integer representing the count of recovered
> errors for that subsystem.
>
> These statistics provide visibility into the health of the system's
> hardware and can be used by system administrators to proactively detect
> failing components before they cause system crashes.
>
> Signed-off-by: Breno Leitao <[email protected]>
> ---
> kernel/vmcore_info.c | 55
> ++++++++++++++++++++++++++++++++++++++++++++++++++++
> 1 file changed, 55 insertions(+)
>
> diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
> index e2784038bbed7..b7fcd21be7c59 100644
> --- a/kernel/vmcore_info.c
> +++ b/kernel/vmcore_info.c
Since we agreed hwerr_recovery_stats has nothing to do with vmcore, it
seems inappropriate to put its sysfs handling code in
kernel/vmcore_info.c. File kernel/vmcore_info.c is only used to build
vmcore info for later vmcore dumping. And hwerr_log_error_type() should
not be put in kernel/vmcore_info.c. either. I didn't check this
carefully before, sorry. Please reconsider if these can be handled better.
Thanks
Baoquan
> @@ -6,6 +6,8 @@
>
> #include <linux/buildid.h>
> #include <linux/init.h>
> +#include <linux/kobject.h>
> +#include <linux/sysfs.h>
> #include <linux/utsname.h>
> #include <linux/vmalloc.h>
> #include <linux/sizes.h>
> @@ -139,6 +141,56 @@ void hwerr_log_error_type(enum hwerr_error_type src)
> }
> EXPORT_SYMBOL_GPL(hwerr_log_error_type);
>
> +/* sysfs interface for hardware error recovery statistics */
> +#define HWERR_ATTR_RO(_name, _type) \
> +static ssize_t _name##_show(struct kobject *kobj, \
> + struct kobj_attribute *attr, char *buf) \
> +{ \
> + return sysfs_emit(buf, "%d\n", \
> + atomic_read(&hwerr_data[_type].count)); \
> +} \
> +static struct kobj_attribute hwerr_##_name##_attr = __ATTR_RO(_name)
> +
> +HWERR_ATTR_RO(cpu, HWERR_RECOV_CPU);
> +HWERR_ATTR_RO(memory, HWERR_RECOV_MEMORY);
> +HWERR_ATTR_RO(pci, HWERR_RECOV_PCI);
> +HWERR_ATTR_RO(cxl, HWERR_RECOV_CXL);
> +HWERR_ATTR_RO(others, HWERR_RECOV_OTHERS);
> +
> +static struct attribute *hwerr_recovery_stats_attrs[] = {
> + &hwerr_cpu_attr.attr,
> + &hwerr_memory_attr.attr,
> + &hwerr_pci_attr.attr,
> + &hwerr_cxl_attr.attr,
> + &hwerr_others_attr.attr,
> + NULL,
> +};
> +
> +static const struct attribute_group hwerr_recovery_stats_group = {
> + .attrs = hwerr_recovery_stats_attrs,
> +};
> +
> +static struct kobject *hwerr_recovery_stats_kobj;
> +
> +static int __init hwerr_recovery_stats_init(void)
> +{
> + hwerr_recovery_stats_kobj =
> kobject_create_and_add("hwerr_recovery_stats",
> + kernel_kobj);
> + if (!hwerr_recovery_stats_kobj) {
> + pr_warn("Failed to create hwerr_recovery_stats kobject\n");
> + return -ENOMEM;
> + }
> +
> + if (sysfs_create_group(hwerr_recovery_stats_kobj,
> + &hwerr_recovery_stats_group)) {
> + kobject_put(hwerr_recovery_stats_kobj);
> + pr_warn("Failed to create hwerr_recovery_stats sysfs group\n");
> + return -ENOMEM;
> + }
> +
> + return 0;
> +}
> +
> static int __init crash_save_vmcoreinfo_init(void)
> {
> vmcoreinfo_data = (unsigned char *)get_zeroed_page(GFP_KERNEL);
> @@ -248,6 +300,9 @@ static int __init crash_save_vmcoreinfo_init(void)
> arch_crash_save_vmcoreinfo();
> update_vmcoreinfo_note();
>
> + /* Create /sys/kernel/hwerr_recovery_stats/ directory */
> + hwerr_recovery_stats_init();
> +
> return 0;
> }
>
>
> --
> 2.47.3
>