From 9544f9e6947f6508d29f0d0cc2dacaa749fc1613 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Wed, 15 Oct 2025 14:36:15 +0800 Subject: hung_task: panic when there are more than N hung tasks at the same time The hung_task_panic sysctl is currently a blunt instrument: it's all or nothing. Panicking on a single hung task can be an overreaction to a transient glitch. A more reliable indicator of a systemic problem is when multiple tasks hang simultaneously. Extend hung_task_panic to accept an integer threshold, allowing the kernel to panic only when N hung tasks are detected in a single scan. This provides finer control to distinguish between isolated incidents and system-wide failures. The accepted values are: - 0: Don't panic (unchanged) - 1: Panic on the first hung task (unchanged) - N > 1: Panic after N hung tasks are detected in a single scan The original behavior is preserved for values 0 and 1, maintaining full backward compatibility. [lance.yang@linux.dev: new changelog] Link: https://lkml.kernel.org/r/20251015063615.2632-1-lirongqing@baidu.com Signed-off-by: Li RongQing Reviewed-by: Masami Hiramatsu (Google) Reviewed-by: Lance Yang Tested-by: Lance Yang Acked-by: Andrew Jeffery [aspeed_g5_defconfig] Cc: Anshuman Khandual Cc: Arnd Bergmann Cc: David Hildenbrand Cc: Florian Wesphal Cc: Jakub Kacinski Cc: Jason A. Donenfeld Cc: Joel Granados Cc: Joel Stanley Cc: Jonathan Corbet Cc: Kees Cook Cc: Liam Howlett Cc: Lorenzo Stoakes Cc: "Paul E . McKenney" Cc: Pawan Gupta Cc: Petr Mladek Cc: Phil Auld Cc: Randy Dunlap Cc: Russell King Cc: Shuah Khan Cc: Simon Horman Cc: Stanislav Fomichev Cc: Steven Rostedt Signed-off-by: Andrew Morton --- kernel/configs/debug.config | 2 +- kernel/hung_task.c | 15 ++++++++++----- 2 files changed, 11 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/configs/debug.config b/kernel/configs/debug.config index e81327d2cd63..9f6ab7dabf67 100644 --- a/kernel/configs/debug.config +++ b/kernel/configs/debug.config @@ -83,7 +83,7 @@ CONFIG_SLUB_DEBUG_ON=y # # Debug Oops, Lockups and Hangs # -# CONFIG_BOOTPARAM_HUNG_TASK_PANIC is not set +CONFIG_BOOTPARAM_HUNG_TASK_PANIC=0 # CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set CONFIG_DEBUG_ATOMIC_SLEEP=y CONFIG_DETECT_HUNG_TASK=y diff --git a/kernel/hung_task.c b/kernel/hung_task.c index b2c1f14b8129..84b4b049faa5 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -81,7 +81,7 @@ static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; * hung task is detected: */ static unsigned int __read_mostly sysctl_hung_task_panic = - IS_ENABLED(CONFIG_BOOTPARAM_HUNG_TASK_PANIC); + CONFIG_BOOTPARAM_HUNG_TASK_PANIC; static int hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr) @@ -218,8 +218,11 @@ 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) +static void check_hung_task(struct task_struct *t, unsigned long timeout, + unsigned long prev_detect_count) { + unsigned long total_hung_task; + if (!task_is_hung(t, timeout)) return; @@ -229,9 +232,10 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) */ 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) { + if (sysctl_hung_task_panic && total_hung_task >= sysctl_hung_task_panic) { console_verbose(); hung_task_show_lock = true; hung_task_call_panic = true; @@ -300,6 +304,7 @@ 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; /* * If the system crashed already then all bets are off, @@ -320,7 +325,7 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) last_break = jiffies; } - check_hung_task(t, timeout); + check_hung_task(t, timeout, prev_detect_count); } unlock: rcu_read_unlock(); @@ -389,7 +394,7 @@ static const struct ctl_table hung_task_sysctls[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = SYSCTL_INT_MAX, }, { .procname = "hung_task_check_count", -- cgit v1.2.3