From: Aaron Tomlin Date: Tue, 3 Mar 2026 20:30:29 +0000 (-0500) Subject: hung_task: refactor detection logic and atomicise detection count X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=00b5cdeb9fe761654d5a76a411c79b8ff04a81e5;p=thirdparty%2Fkernel%2Fstable.git hung_task: refactor detection logic and atomicise detection count Patch series "hung_task: Provide runtime reset interface for hung task detector", v9. This series introduces the ability to reset /proc/sys/kernel/hung_task_detect_count. Writing a "0" value to this file atomically resets the counter of detected hung tasks. This functionality provides system administrators with the means to clear the cumulative diagnostic history following incident resolution, thereby simplifying subsequent monitoring without necessitating a system restart. This patch (of 3): The check_hung_task() function currently conflates two distinct responsibilities: validating whether a task is hung and handling the subsequent reporting (printing warnings, triggering panics, or tracepoints). This patch refactors the logic by introducing hung_task_info(), a function dedicated solely to reporting. The actual detection check, task_is_hung(), is hoisted into the primary loop within check_hung_uninterruptible_tasks(). This separation clearly decouples the mechanism of detection from the policy of reporting. Furthermore, to facilitate future support for concurrent hung task detection, the global sysctl_hung_task_detect_count variable is converted from unsigned long to atomic_long_t. Consequently, the counting logic is updated to accumulate the number of hung tasks locally (this_round_count) during the iteration. The global counter is then updated atomically via atomic_long_cmpxchg_relaxed() once the loop concludes, rather than incrementally during the scan. These changes are strictly preparatory and introduce no functional change to the system's runtime behaviour. Link: https://lkml.kernel.org/r/20260303203031.4097316-1-atomlin@atomlin.com Link: https://lkml.kernel.org/r/20260303203031.4097316-2-atomlin@atomlin.com Signed-off-by: Aaron Tomlin Reviewed-by: Masami Hiramatsu (Google) Reviewed-by: Petr Mladek Cc: Greg Kroah-Hartman Cc: Lance Yang Cc: Masami Hiramatsu Cc: Joel Granados Signed-off-by: Andrew Morton --- diff --git a/kernel/hung_task.c b/kernel/hung_task.c index d2254c91450b..df10830ed9ef 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -36,7 +36,7 @@ static int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; /* * 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. @@ -223,31 +223,29 @@ static inline void debug_show_blocker(struct task_struct *task, unsigned long ti } #endif -static void check_hung_task(struct task_struct *t, unsigned long timeout, - unsigned long prev_detect_count) +/** + * hung_task_info - Print diagnostic details for a hung task + * @t: Pointer to the detected hung task. + * @timeout: Timeout threshold for detecting hung tasks + * @this_round_count: Count of hung tasks detected in the current iteration + * + * Print structured information about the specified hung task, if warnings + * are enabled or if the panic batch threshold is exceeded. + */ +static void hung_task_info(struct task_struct *t, unsigned long timeout, + unsigned long this_round_count) { - unsigned long total_hung_task; - - if (!task_is_hung(t, timeout)) - return; - - /* - * This counter tracks the total number of tasks detected as hung - * since boot. - */ - sysctl_hung_task_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) { + if (sysctl_hung_task_panic && this_round_count >= sysctl_hung_task_panic) { console_verbose(); hung_task_call_panic = true; } /* - * Ok, the task did not get scheduled for more than 2 minutes, - * complain: + * The given task did not get scheduled for more than + * CONFIG_DEFAULT_HUNG_TASK_TIMEOUT. Therefore, complain + * accordingly */ if (sysctl_hung_task_warnings || hung_task_call_panic) { if (sysctl_hung_task_warnings > 0) @@ -297,18 +295,18 @@ static bool rcu_lock_break(struct task_struct *g, struct task_struct *t) /* * Check whether a TASK_UNINTERRUPTIBLE does not get woken up for - * a really long time (120 seconds). If that happens, print out - * a warning. + * a really long time. If that happens, print out a warning. */ static void check_hung_uninterruptible_tasks(unsigned long timeout) { 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 total_count, this_round_count; int need_warning = sysctl_hung_task_warnings; unsigned long si_mask = hung_task_si_mask; + total_count = atomic_long_read(&sysctl_hung_task_detect_count); /* * If the system crashed already then all bets are off, * do not report extra hung tasks: @@ -316,10 +314,9 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) if (test_taint(TAINT_DIE) || did_panic) return; - + this_round_count = 0; rcu_read_lock(); for_each_process_thread(g, t) { - if (!max_count--) goto unlock; if (time_after(jiffies, last_break + HUNG_TASK_LOCK_BREAK)) { @@ -328,14 +325,25 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) last_break = jiffies; } - check_hung_task(t, timeout, prev_detect_count); + if (task_is_hung(t, timeout)) { + this_round_count++; + hung_task_info(t, timeout, this_round_count); + } } unlock: rcu_read_unlock(); - if (!(sysctl_hung_task_detect_count - prev_detect_count)) + if (!this_round_count) return; + /* + * This counter tracks the total number of tasks detected as hung + * since boot. + */ + atomic_long_cmpxchg_relaxed(&sysctl_hung_task_detect_count, + total_count, total_count + + this_round_count); + if (need_warning || hung_task_call_panic) { si_mask |= SYS_INFO_LOCKS;