diff options
Diffstat (limited to 'kernel/hung_task.c')
| -rw-r--r-- | kernel/hung_task.c | 131 |
1 files changed, 118 insertions, 13 deletions
diff --git a/kernel/hung_task.c b/kernel/hung_task.c index ce76f490126c..04efa7a6e69b 100644 --- a/kernel/hung_task.c +++ b/kernel/hung_task.c @@ -15,6 +15,7 @@ #include <linux/kthread.h> #include <linux/lockdep.h> #include <linux/export.h> +#include <linux/panic_notifier.h> #include <linux/sysctl.h> #include <linux/suspend.h> #include <linux/utsname.h> @@ -27,7 +28,12 @@ /* * The number of tasks checked: */ -int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; +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; /* * Limit number of tasks checked in a batch. @@ -42,13 +48,14 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT; * Zero means infinite timeout - no checking done: */ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT; +EXPORT_SYMBOL_GPL(sysctl_hung_task_timeout_secs); /* * Zero (default value) means use sysctl_hung_task_timeout_secs: */ -unsigned long __read_mostly sysctl_hung_task_check_interval_secs; +static unsigned long __read_mostly sysctl_hung_task_check_interval_secs; -int __read_mostly sysctl_hung_task_warnings = 10; +static int __read_mostly sysctl_hung_task_warnings = 10; static int __read_mostly did_panic; static bool hung_task_show_lock; @@ -62,15 +69,17 @@ static struct task_struct *watchdog_task; * Should we dump all CPUs backtraces in a hung task event? * Defaults to 0, can be changed via sysctl. */ -unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace; +#else +#define sysctl_hung_task_all_cpu_backtrace 0 #endif /* CONFIG_SMP */ /* * Should we panic (and reboot, if panic_timeout= is set) when a * hung task is detected: */ -unsigned int __read_mostly sysctl_hung_task_panic = - CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE; +static unsigned int __read_mostly sysctl_hung_task_panic = + IS_ENABLED(CONFIG_BOOTPARAM_HUNG_TASK_PANIC); static int hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr) @@ -92,8 +101,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * Ensure the task is not frozen. * Also, skip vfork and any other user process that freezer should skip. */ - if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP))) - return; + if (unlikely(READ_ONCE(t->__state) & TASK_FROZEN)) + return; /* * When a freshly created task is scheduled once, changes its state to @@ -111,6 +120,12 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (time_is_after_jiffies(t->last_switch_time + timeout * HZ)) return; + /* + * This counter tracks the total number of tasks detected as hung + * since boot. + */ + sysctl_hung_task_detect_count++; + trace_sched_process_hang(t); if (sysctl_hung_task_panic) { @@ -123,7 +138,7 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) * Ok, the task did not get scheduled for more than 2 minutes, * complain: */ - if (sysctl_hung_task_warnings) { + if (sysctl_hung_task_warnings || hung_task_call_panic) { if (sysctl_hung_task_warnings > 0) sysctl_hung_task_warnings--; pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n", @@ -132,6 +147,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); + if (t->flags & PF_POSTCOREDUMP) + pr_err(" Blocked by coredump.\n"); pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\"" " disables this message.\n"); sched_show_task(t); @@ -139,6 +156,8 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout) if (sysctl_hung_task_all_cpu_backtrace) hung_task_show_all_bt = true; + if (!sysctl_hung_task_warnings) + pr_info("Future hung task reports are suppressed, see sysctl kernel.hung_task_warnings\n"); } touch_nmi_watchdog(); @@ -188,6 +207,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) hung_task_show_lock = false; rcu_read_lock(); for_each_process_thread(g, t) { + unsigned int state; + if (!max_count--) goto unlock; if (time_after(jiffies, last_break + HUNG_TASK_LOCK_BREAK)) { @@ -195,8 +216,14 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout) goto unlock; last_break = jiffies; } - /* use "==" to skip the TASK_KILLABLE tasks waiting on NFS */ - if (t->state == TASK_UNINTERRUPTIBLE) + /* + * skip the TASK_KILLABLE tasks -- these can be killed + * skip the TASK_IDLE tasks -- those are genuinely idle + */ + state = READ_ONCE(t->__state); + if ((state & TASK_UNINTERRUPTIBLE) && + !(state & TASK_WAKEKILL) && + !(state & TASK_NOLOAD)) check_hung_task(t, timeout); } unlock: @@ -221,11 +248,12 @@ static long hung_timeout_jiffies(unsigned long last_checked, MAX_SCHEDULE_TIMEOUT; } +#ifdef CONFIG_SYSCTL /* * Process updating of timeout sysctl */ -int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, - void __user *buffer, +static int proc_dohung_task_timeout_secs(const struct ctl_table *table, int write, + void *buffer, size_t *lenp, loff_t *ppos) { int ret; @@ -241,6 +269,82 @@ int proc_dohung_task_timeout_secs(struct ctl_table *table, int write, return ret; } +/* + * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs + * and hung_task_check_interval_secs + */ +static const unsigned long hung_task_timeout_max = (LONG_MAX / HZ); +static const struct ctl_table hung_task_sysctls[] = { +#ifdef CONFIG_SMP + { + .procname = "hung_task_all_cpu_backtrace", + .data = &sysctl_hung_task_all_cpu_backtrace, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, +#endif /* CONFIG_SMP */ + { + .procname = "hung_task_panic", + .data = &sysctl_hung_task_panic, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, + }, + { + .procname = "hung_task_check_count", + .data = &sysctl_hung_task_check_count, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_ZERO, + }, + { + .procname = "hung_task_timeout_secs", + .data = &sysctl_hung_task_timeout_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_check_interval_secs", + .data = &sysctl_hung_task_check_interval_secs, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = proc_dohung_task_timeout_secs, + .extra2 = (void *)&hung_task_timeout_max, + }, + { + .procname = "hung_task_warnings", + .data = &sysctl_hung_task_warnings, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = SYSCTL_NEG_ONE, + }, + { + .procname = "hung_task_detect_count", + .data = &sysctl_hung_task_detect_count, + .maxlen = sizeof(unsigned long), + .mode = 0444, + .proc_handler = proc_doulongvec_minmax, + }, +}; + +static void __init hung_task_sysctl_init(void) +{ + register_sysctl_init("kernel", hung_task_sysctls); +} +#else +#define hung_task_sysctl_init() do { } while (0) +#endif /* CONFIG_SYSCTL */ + + static atomic_t reset_hung_task = ATOMIC_INIT(0); void reset_hung_task_detector(void) @@ -310,6 +414,7 @@ static int __init hung_task_init(void) pm_notifier(hungtask_pm_notify, 0); watchdog_task = kthread_run(watchdog, NULL, "khungtaskd"); + hung_task_sysctl_init(); return 0; } |