[PATCH v2 2/2] kernel/rcu/tree_stall: add /sys/kernel/rcu_stall_count

[Max Kellermann <max.kellermann@ionos.com>]

Exposing a simple counter to userspace for monitoring tools.

Signed-off-by: Max Kellermann <max.kellermann@ionos.com>
---
v1 -> v2: added documentation
---
 .../ABI/testing/sysfs-kernel-rcu_stall_count  |  6 +++++
 kernel/rcu/tree_stall.h                       | 26 +++++++++++++++++++
 2 files changed, 32 insertions(+)
 create mode 100644 Documentation/ABI/testing/sysfs-kernel-rcu_stall_count

diff --git a/Documentation/ABI/testing/sysfs-kernel-rcu_stall_count b/Documentation/ABI/testing/sysfs-kernel-rcu_stall_count
new file mode 100644
index 000000000000..a4a97a7f4a4d
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-rcu_stall_count
@@ -0,0 +1,6 @@
+What:		/sys/kernel/rcu_stall_count
+Date:		May 2025
+KernelVersion:	6.16
+Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
+Description:
+		Shows how many times the system has detected an RCU stall since last boot.
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 925fcdad5dea..158330524795 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -20,6 +20,28 @@
 int sysctl_panic_on_rcu_stall __read_mostly;
 int sysctl_max_rcu_stall_to_panic __read_mostly;
 
+#ifdef CONFIG_SYSFS
+
+static unsigned int rcu_stall_count;
+
+static ssize_t rcu_stall_count_show(struct kobject *kobj, struct kobj_attribute *attr,
+				    char *page)
+{
+	return sysfs_emit(page, "%u\n", rcu_stall_count);
+}
+
+static struct kobj_attribute rcu_stall_count_attr = __ATTR_RO(rcu_stall_count);
+
+static __init int kernel_rcu_stall_sysfs_init(void)
+{
+	sysfs_add_file_to_group(kernel_kobj, &rcu_stall_count_attr.attr, NULL);
+	return 0;
+}
+
+late_initcall(kernel_rcu_stall_sysfs_init);
+
+#endif // CONFIG_SYSFS
+
 #ifdef CONFIG_PROVE_RCU
 #define RCU_STALL_DELAY_DELTA		(5 * HZ)
 #else
@@ -784,6 +806,10 @@ static void check_cpu_stall(struct rcu_data *rdp)
 		if (kvm_check_and_clear_guest_paused())
 			return;
 
+#ifdef CONFIG_SYSFS
+		++rcu_stall_count;
+#endif
+
 		rcu_stall_notifier_call_chain(RCU_STALL_NOTIFY_NORM, (void *)j - gps);
 		if (READ_ONCE(csd_lock_suppress_rcu_stall) && csd_lock_is_stuck()) {
 			pr_err("INFO: %s detected stall, but suppressed full report due to a stuck CSD-lock.\n", rcu_state.name);
-- 
2.47.2