+ hung_task-enable-runtime-reset-of-hung_task_detect_count.patch added to mm-nonmm-unstable branch

[Andrew Morton <akpm@linux-foundation.org>]

The patch titled
     Subject: hung_task: enable runtime reset of hung_task_detect_count
has been added to the -mm mm-nonmm-unstable branch.  Its filename is
     hung_task-enable-runtime-reset-of-hung_task_detect_count.patch

This patch will shortly appear at
     https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/hung_task-enable-runtime-reset-of-hung_task_detect_count.patch

This patch will later appear in the mm-nonmm-unstable branch at
    git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm

Before you just go and hit "reply", please:
   a) Consider who else should be cc'ed
   b) Prefer to cc a suitable mailing list as well
   c) Ideally: find the original patch on the mailing list and do a
      reply-to-all to that, adding suitable additional cc's

*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***

The -mm tree is included into linux-next via various
branches at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
and is updated there most days

------------------------------------------------------
From: Aaron Tomlin <atomlin@atomlin.com>
Subject: hung_task: enable runtime reset of hung_task_detect_count
Date: Tue, 30 Dec 2025 19:41:25 -0500

Introduce support for writing to /proc/sys/kernel/hung_task_detect_count.

Writing a value of zero to this file atomically resets the counter of
detected hung tasks.  This grants system administrators the ability to
clear the cumulative diagnostic history after resolving an incident,
simplifying monitoring without requiring a system restart.

Link: https://lkml.kernel.org/r/20251231004125.2380105-3-atomlin@atomlin.com
Signed-off-by: Aaron Tomlin <atomlin@atomlin.com>
Cc: Feng Tang <feng.tang@linux.alibaba.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Cc: Petr Mladek <pmladek@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---

 Documentation/admin-guide/sysctl/kernel.rst |    3 
 kernel/hung_task.c                          |   82 +++++++++++++++---
 2 files changed, 73 insertions(+), 12 deletions(-)

--- a/Documentation/admin-guide/sysctl/kernel.rst~hung_task-enable-runtime-reset-of-hung_task_detect_count
+++ a/Documentation/admin-guide/sysctl/kernel.rst
@@ -418,7 +418,8 @@ hung_task_detect_count
 ======================
 
 Indicates the total number of tasks that have been detected as hung since
-the system boot.
+the system boot or since the counter was reset. The counter is zeroed when
+a value of 0 is written.
 
 This file shows up if ``CONFIG_DETECT_HUNG_TASK`` is enabled.
 
--- a/kernel/hung_task.c~hung_task-enable-runtime-reset-of-hung_task_detect_count
+++ a/kernel/hung_task.c
@@ -17,6 +17,7 @@
 #include <linux/export.h>
 #include <linux/panic_notifier.h>
 #include <linux/sysctl.h>
+#include <linux/atomic.h>
 #include <linux/suspend.h>
 #include <linux/utsname.h>
 #include <linux/sched/signal.h>
@@ -36,7 +37,7 @@ static int __read_mostly sysctl_hung_tas
 /*
  * Total number of tasks detected as hung since boot:
  */
-static unsigned long __read_mostly sysctl_hung_task_detect_count;
+static atomic_long_t sysctl_hung_task_detect_count = ATOMIC_LONG_INIT(0);
 
 /*
  * Limit number of tasks checked in a batch.
@@ -246,20 +247,26 @@ static inline void hung_task_diagnostics
 }
 
 static void check_hung_task(struct task_struct *t, unsigned long timeout,
-		unsigned long prev_detect_count)
+			    unsigned long prev_detect_count)
 {
-	unsigned long total_hung_task;
+	unsigned long total_hung_task, cur_detect_count;
 
 	if (!task_is_hung(t, timeout))
 		return;
 
 	/*
 	 * This counter tracks the total number of tasks detected as hung
-	 * since boot.
+	 * since boot. If a reset occurred during the scan, we treat the
+	 * current count as the new delta to avoid an underflow error.
+	 * Ensure hang details are globally visible before the counter
+	 * update.
 	 */
-	sysctl_hung_task_detect_count++;
+	cur_detect_count = atomic_long_inc_return_release(&sysctl_hung_task_detect_count);
+	if (cur_detect_count >= prev_detect_count)
+		total_hung_task = cur_detect_count - prev_detect_count;
+	else
+		total_hung_task = cur_detect_count;
 
-	total_hung_task = sysctl_hung_task_detect_count - prev_detect_count;
 	trace_sched_process_hang(t);
 
 	if (sysctl_hung_task_panic && total_hung_task >= sysctl_hung_task_panic) {
@@ -318,10 +325,12 @@ static void check_hung_uninterruptible_t
 	int max_count = sysctl_hung_task_check_count;
 	unsigned long last_break = jiffies;
 	struct task_struct *g, *t;
-	unsigned long prev_detect_count = sysctl_hung_task_detect_count;
+	unsigned long cur_detect_count, prev_detect_count, delta;
 	int need_warning = sysctl_hung_task_warnings;
 	unsigned long si_mask = hung_task_si_mask;
 
+	/* Acquire prevents reordering task checks before this point. */
+	prev_detect_count = atomic_long_read_acquire(&sysctl_hung_task_detect_count);
 	/*
 	 * If the system crashed already then all bets are off,
 	 * do not report extra hung tasks:
@@ -346,7 +355,14 @@ static void check_hung_uninterruptible_t
  unlock:
 	rcu_read_unlock();
 
-	if (!(sysctl_hung_task_detect_count - prev_detect_count))
+	/* Ensures we see all hang details recorded during the scan. */
+	cur_detect_count = atomic_long_read_acquire(&sysctl_hung_task_detect_count);
+	if (cur_detect_count < prev_detect_count)
+		delta = cur_detect_count;
+	else
+		delta = cur_detect_count - prev_detect_count;
+
+	if (!delta)
 		return;
 
 	if (need_warning || hung_task_call_panic) {
@@ -371,6 +387,51 @@ static long hung_timeout_jiffies(unsigne
 }
 
 #ifdef CONFIG_SYSCTL
+
+/**
+ * proc_dohung_task_detect_count - proc handler for hung_task_detect_count
+ * @table: Pointer to the struct ctl_table definition for this proc entry
+ * @dir: Flag indicating the operation
+ * @buffer: User space buffer for data transfer
+ * @lenp: Pointer to the length of the data being transferred
+ * @ppos: Pointer to the current file offset
+ *
+ * This handler is used for reading the current hung task detection count
+ * and for resetting it to zero when a write operation is performed using a
+ * zero value only. Returns 0 on success or a negative error code on
+ * failure.
+ */
+static int proc_dohung_task_detect_count(const struct ctl_table *table, int dir,
+					 void *buffer, size_t *lenp, loff_t *ppos)
+{
+	unsigned long detect_count;
+	struct ctl_table proxy_table;
+	int err;
+
+	proxy_table = *table;
+	proxy_table.data = &detect_count;
+
+	if (SYSCTL_KERN_TO_USER(dir)) {
+		detect_count = atomic_long_read(&sysctl_hung_task_detect_count);
+
+		return proc_doulongvec_minmax(&proxy_table, dir, buffer, lenp, ppos);
+	}
+
+	err = proc_doulongvec_minmax(&proxy_table, dir, buffer, lenp, ppos);
+	if (err < 0)
+		return err;
+
+	if (SYSCTL_USER_TO_KERN(dir)) {
+		/* The only valid value for clearing is zero. */
+		if (detect_count)
+			return -EINVAL;
+		atomic_long_set(&sysctl_hung_task_detect_count, 0);
+	}
+
+	*ppos += *lenp;
+	return err;
+}
+
 /*
  * Process updating of timeout sysctl
  */
@@ -451,10 +512,9 @@ static const struct ctl_table hung_task_
 	},
 	{
 		.procname	= "hung_task_detect_count",
-		.data		= &sysctl_hung_task_detect_count,
 		.maxlen		= sizeof(unsigned long),
-		.mode		= 0444,
-		.proc_handler	= proc_doulongvec_minmax,
+		.mode		= 0644,
+		.proc_handler	= proc_dohung_task_detect_count,
 	},
 	{
 		.procname	= "hung_task_sys_info",
_

Patches currently in -mm which might be from atomlin@atomlin.com are

fs-proc-expose-mm_cpumask-in-proc-status.patch
hung_task-introduce-helper-for-hung-task-warning.patch
hung_task-enable-runtime-reset-of-hung_task_detect_count.patch
hung_task-provide-runtime-reset-interface-for-hung-task-detector.patch