The Linux Kernel Mailing List
 help / color / mirror / Atom feed
From: Aaron Tomlin <atomlin@atomlin.com>
To: akpm@linux-foundation.org, lance.yang@linux.dev,
	mhiramat@kernel.org, pmladek@suse.com
Cc: linux-kernel@vger.kernel.org, david.laight.linux@gmail.com,
	atomlin@atomlin.com, neelx@suse.com, sean@ashe.io,
	chjohnst@gmail.com, steve@abita.co, mproche@gmail.com,
	nick.lange@gmail.com
Subject: [PATCH 1/2] hung_task: Reset warning budget when problem gets resolved
Date: Mon,  3 Aug 2026 20:15:41 -0400	[thread overview]
Message-ID: <20260804001542.249639-2-atomlin@atomlin.com> (raw)
In-Reply-To: <20260804001542.249639-1-atomlin@atomlin.com>

From: Petr Mladek <pmladek@suse.com>

sysctl_hung_task_warnings counts how many hung tasks are reported.
The watchdog does not report anything once the limit is reached.
Currently, this budget is decremented permanently, meaning the kernel is
left blind to subsequent hung tasks even after the original issue resolves.

Keep the global sysctl_hung_task_warnings intact, and instead decrement
a copy (hung_task_warnings_printed) when warnings are printed. Reset
the copy back to the configured sysctl_hung_task_warnings limit once the
problem on the system gets resolved and check_hung_uninterruptible_tasks()
detects no hung tasks in a check interval.

Also keep the copy updated when the global sysctl_hung_task_warnings
value is updated via sysctl, and update documentation to reflect
the new behavior.

Assisted-by: gemini-3.5-flash
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 Documentation/admin-guide/sysctl/kernel.rst |  6 ++--
 kernel/hung_task.c                          | 34 ++++++++++++++++-----
 2 files changed, 31 insertions(+), 9 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index c6994e55d141..eaa1d837c739 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -459,8 +459,10 @@ 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 warnings will be reported.
+The warning budget is reset back to the configured limit when the problem on the
+system gets resolved and 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


  reply	other threads:[~2026-08-04  0:16 UTC|newest]

Thread overview: 8+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-08-04  0:15 [PATCH 0/2] hung_task: Improve warning budget handling and task reporting Aaron Tomlin
2026-08-04  0:15 ` Aaron Tomlin [this message]
2026-08-04  2:24   ` [PATCH 1/2] hung_task: Reset warning budget when problem gets resolved Lance Yang
2026-08-04 14:19     ` Aaron Tomlin
2026-08-04  3:18   ` Lance Yang
2026-08-04 14:54     ` Aaron Tomlin
2026-08-04  0:15 ` [PATCH 2/2] hung_task: Always print basic hung task info header Aaron Tomlin
2026-08-04  3:19   ` Lance Yang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260804001542.249639-2-atomlin@atomlin.com \
    --to=atomlin@atomlin.com \
    --cc=akpm@linux-foundation.org \
    --cc=chjohnst@gmail.com \
    --cc=david.laight.linux@gmail.com \
    --cc=lance.yang@linux.dev \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mhiramat@kernel.org \
    --cc=mproche@gmail.com \
    --cc=neelx@suse.com \
    --cc=nick.lange@gmail.com \
    --cc=pmladek@suse.com \
    --cc=sean@ashe.io \
    --cc=steve@abita.co \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox