[PATCH v8 1/2] hung_task: Reset warning budget when problem gets resolved

[Aaron Tomlin]

sysctl_hung_task_warnings currently holds both the configured warning
limit and the remaining budget. Each detailed report decrements the
sysctl, so once it reaches zero, the configured limit is lost and cannot
be restored automatically.

Keep sysctl_hung_task_warnings unchanged and track the remaining budget
in hung_task_warnings_printed. Reset the runtime budget when a watchdog
check sees no hung tasks or when userspace writes a new sysctl value.

Assisted-by: Antigravity:gemini-3.5-flash
Suggested-by: Petr Mladek <pmladek@xxxxxxxx>
Reviewed-by: Lance Yang <lance.yang@xxxxxxxxx>
Tested-by: Lance Yang <lance.yang@xxxxxxxxx>
Signed-off-by: Aaron Tomlin <atomlin@xxxxxxxxxxx>
---
 Documentation/admin-guide/sysctl/kernel.rst |  5 +--
 kernel/hung_task.c                          | 34 ++++++++++++++++-----
 2 files changed, 30 insertions(+), 9 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index c6994e55d141..b0f8e55efc1a 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -459,8 +459,9 @@ hung_task_warnings
 ==================
 
 The maximum number of warnings to report. During a check interval
-if a hung task is detected, this value is decreased by 1.
-When this value reaches 0, no more warnings will be reported.
+if a hung task is detected, the internal warning budget is decreased by 1.
+When this budget reaches 0, no more detailed warnings will be reported. The
+warning budget is reset to the configured limit when no hung task is found.
 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
 
 -1: report an infinite number of warnings.
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 6fcc94ce4ca9..4e1fb0db79d1 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -59,6 +59,8 @@ static unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
 
 static int __read_mostly sysctl_hung_task_warnings = 10;
 
+static int hung_task_warnings_printed = 10;
+
 static int __read_mostly did_panic;
 static bool hung_task_call_panic;
 
@@ -247,9 +249,9 @@ static void hung_task_info(struct task_struct *t, unsigned long timeout,
 	 * CONFIG_DEFAULT_HUNG_TASK_TIMEOUT. Therefore, complain
 	 * accordingly
 	 */
-	if (sysctl_hung_task_warnings || hung_task_call_panic) {
-		if (sysctl_hung_task_warnings > 0)
-			sysctl_hung_task_warnings--;
+	if (hung_task_warnings_printed || hung_task_call_panic) {
+		if (hung_task_warnings_printed > 0)
+			hung_task_warnings_printed--;
 		pr_err("INFO: task %s:%d blocked%s for more than %ld seconds.\n",
 		       t->comm, t->pid, t->in_iowait ? " in I/O wait" : "",
 		       (jiffies - t->last_switch_time) / HZ);
@@ -264,7 +266,7 @@ static void hung_task_info(struct task_struct *t, unsigned long timeout,
 		sched_show_task(t);
 		debug_show_blocker(t, timeout);
 
-		if (!sysctl_hung_task_warnings)
+		if (!hung_task_warnings_printed)
 			pr_info("Future hung task reports are suppressed, see sysctl kernel.hung_task_warnings\n");
 	}
 
@@ -304,7 +306,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	unsigned long last_break = jiffies;
 	struct task_struct *g, *t;
 	unsigned long this_round_count;
-	int need_warning = sysctl_hung_task_warnings;
+	int need_warning = hung_task_warnings_printed;
 	unsigned long si_mask = hung_task_si_mask;
 
 	/*
@@ -340,8 +342,10 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
  unlock:
 	rcu_read_unlock();
 
-	if (!this_round_count)
+	if (!this_round_count) {
+		hung_task_warnings_printed = sysctl_hung_task_warnings;
 		return;
+	}
 
 	if (need_warning || hung_task_call_panic) {
 		si_mask |= SYS_INFO_LOCKS;
@@ -425,6 +429,22 @@ static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int writ
 	return ret;
 }
 
+static int proc_dohung_task_warnings(const struct ctl_table *table, int write,
+				     void *buffer,
+				     size_t *lenp, loff_t *ppos)
+{
+	int ret;
+
+	ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+
+	if (ret || !write)
+		return ret;
+
+	hung_task_warnings_printed = sysctl_hung_task_warnings;
+
+	return 0;
+}
+
 /*
  * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs
  * and hung_task_check_interval_secs
@@ -480,7 +500,7 @@ static const struct ctl_table hung_task_sysctls[] = {
 		.data		= &sysctl_hung_task_warnings,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
+		.proc_handler	= proc_dohung_task_warnings,
 		.extra1		= SYSCTL_NEG_ONE,
 	},
 	{
-- 
2.55.0