1 files changed, 268 insertions, 39 deletions

diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 4a9191617076..d2254c91450b 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Detect Hung Task
  *
@@ -14,18 +15,28 @@
 #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>
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
+#include <linux/sched/sysctl.h>
+#include <linux/hung_task.h>
+#include <linux/rwsem.h>
+#include <linux/sys_info.h>
 
 #include <trace/events/sched.h>
 
 /*
  * 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.
@@ -44,32 +55,38 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_
 /*
  * 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;
 static bool hung_task_call_panic;
 
 static struct task_struct *watchdog_task;
 
 /*
- * Should we panic (and reboot, if panic_timeout= is set) when a
- * hung task is detected:
+ * A bitmask to control what kinds of system info to be printed when
+ * a hung task is detected, it could be task, memory, lock etc. Refer
+ * include/linux/sys_info.h for detailed bit definition.
  */
-unsigned int __read_mostly sysctl_hung_task_panic =
-				CONFIG_BOOTPARAM_HUNG_TASK_PANIC_VALUE;
+static unsigned long hung_task_si_mask;
 
-static int __init hung_task_panic_setup(char *str)
-{
-	int rc = kstrtouint(str, 0, &sysctl_hung_task_panic);
+#ifdef CONFIG_SMP
+/*
+ * Should we dump all CPUs backtraces in a hung task event?
+ * Defaults to 0, can be changed via sysctl.
+ */
+static unsigned int __read_mostly sysctl_hung_task_all_cpu_backtrace;
+#else
+#define sysctl_hung_task_all_cpu_backtrace 0
+#endif /* CONFIG_SMP */
 
-	if (rc)
-		return rc;
-	return 1;
-}
-__setup("hung_task_panic=", hung_task_panic_setup);
+/*
+ * Should we panic (and reboot, if panic_timeout= is set) when a
+ * hung task is detected:
+ */
+static unsigned int __read_mostly sysctl_hung_task_panic =
+	CONFIG_BOOTPARAM_HUNG_TASK_PANIC;
 
 static int
 hung_task_panic(struct notifier_block *this, unsigned long event, void *ptr)
@@ -83,16 +100,19 @@ static struct notifier_block panic_block = {
 	.notifier_call = hung_task_panic,
 };
 
-static void check_hung_task(struct task_struct *t, unsigned long timeout)
+static bool task_is_hung(struct task_struct *t, unsigned long timeout)
 {
 	unsigned long switch_count = t->nvcsw + t->nivcsw;
+	unsigned int state = READ_ONCE(t->__state);
 
 	/*
-	 * Ensure the task is not frozen.
-	 * Also, skip vfork and any other user process that freezer should skip.
+	 * skip the TASK_KILLABLE tasks -- these can be killed
+	 * skip the TASK_IDLE tasks -- those are genuinely idle
+	 * skip the TASK_FROZEN task -- it reasonably stops scheduling by freezer
 	 */
-	if (unlikely(t->flags & (PF_FROZEN | PF_FREEZER_SKIP)))
-	    return;
+	if (!(state & TASK_UNINTERRUPTIBLE) ||
+	    (state & (TASK_WAKEKILL | TASK_NOLOAD | TASK_FROZEN)))
+		return false;
 
 	/*
 	 * When a freshly created task is scheduled once, changes its state to
@@ -100,21 +120,128 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 	 * musn't be checked.
 	 */
 	if (unlikely(!switch_count))
-		return;
+		return false;
 
 	if (switch_count != t->last_switch_count) {
 		t->last_switch_count = switch_count;
 		t->last_switch_time = jiffies;
-		return;
+		return false;
 	}
 	if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
+		return false;
+
+	return true;
+}
+
+#ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
+static void debug_show_blocker(struct task_struct *task, unsigned long timeout)
+{
+	struct task_struct *g, *t;
+	unsigned long owner, blocker, blocker_type;
+	const char *rwsem_blocked_by, *rwsem_blocked_as;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
+
+	blocker = READ_ONCE(task->blocker);
+	if (!blocker)
+		return;
+
+	blocker_type = hung_task_get_blocker_type(blocker);
+
+	switch (blocker_type) {
+	case BLOCKER_TYPE_MUTEX:
+		owner = mutex_get_owner(hung_task_blocker_to_lock(blocker));
+		break;
+	case BLOCKER_TYPE_SEM:
+		owner = sem_last_holder(hung_task_blocker_to_lock(blocker));
+		break;
+	case BLOCKER_TYPE_RWSEM_READER:
+	case BLOCKER_TYPE_RWSEM_WRITER:
+		owner = (unsigned long)rwsem_owner(
+					hung_task_blocker_to_lock(blocker));
+		rwsem_blocked_as = (blocker_type == BLOCKER_TYPE_RWSEM_READER) ?
+					"reader" : "writer";
+		rwsem_blocked_by = is_rwsem_reader_owned(
+					hung_task_blocker_to_lock(blocker)) ?
+					"reader" : "writer";
+		break;
+	default:
+		WARN_ON_ONCE(1);
+		return;
+	}
+
+
+	if (unlikely(!owner)) {
+		switch (blocker_type) {
+		case BLOCKER_TYPE_MUTEX:
+			pr_err("INFO: task %s:%d is blocked on a mutex, but the owner is not found.\n",
+			       task->comm, task->pid);
+			break;
+		case BLOCKER_TYPE_SEM:
+			pr_err("INFO: task %s:%d is blocked on a semaphore, but the last holder is not found.\n",
+			       task->comm, task->pid);
+			break;
+		case BLOCKER_TYPE_RWSEM_READER:
+		case BLOCKER_TYPE_RWSEM_WRITER:
+			pr_err("INFO: task %s:%d is blocked on an rw-semaphore, but the owner is not found.\n",
+			       task->comm, task->pid);
+			break;
+		}
+		return;
+	}
+
+	/* Ensure the owner information is correct. */
+	for_each_process_thread(g, t) {
+		if ((unsigned long)t != owner)
+			continue;
+
+		switch (blocker_type) {
+		case BLOCKER_TYPE_MUTEX:
+			pr_err("INFO: task %s:%d is blocked on a mutex likely owned by task %s:%d.\n",
+			       task->comm, task->pid, t->comm, t->pid);
+			break;
+		case BLOCKER_TYPE_SEM:
+			pr_err("INFO: task %s:%d blocked on a semaphore likely last held by task %s:%d\n",
+			       task->comm, task->pid, t->comm, t->pid);
+			break;
+		case BLOCKER_TYPE_RWSEM_READER:
+		case BLOCKER_TYPE_RWSEM_WRITER:
+			pr_err("INFO: task %s:%d <%s> blocked on an rw-semaphore likely owned by task %s:%d <%s>\n",
+			       task->comm, task->pid, rwsem_blocked_as, t->comm,
+			       t->pid, rwsem_blocked_by);
+			break;
+		}
+		/* Avoid duplicated task dump, skip if the task is also hung. */
+		if (!task_is_hung(t, timeout))
+			sched_show_task(t);
+		return;
+	}
+}
+#else
+static inline void debug_show_blocker(struct task_struct *task, unsigned long timeout)
+{
+}
+#endif
+
+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;
 
+	/*
+	 * 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) {
+	if (sysctl_hung_task_panic && total_hung_task >= sysctl_hung_task_panic) {
 		console_verbose();
-		hung_task_show_lock = true;
 		hung_task_call_panic = true;
 	}
 
@@ -122,19 +249,24 @@ 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",
-			t->comm, t->pid, timeout);
+		       t->comm, t->pid, (jiffies - t->last_switch_time) / HZ);
 		pr_err("      %s %s %.*s\n",
 			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);
-		hung_task_show_lock = true;
+		debug_show_blocker(t, timeout);
+
+		if (!sysctl_hung_task_warnings)
+			pr_info("Future hung task reports are suppressed, see sysctl kernel.hung_task_warnings\n");
 	}
 
 	touch_nmi_watchdog();
@@ -173,6 +305,9 @@ 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;
+	int need_warning = sysctl_hung_task_warnings;
+	unsigned long si_mask = hung_task_si_mask;
 
 	/*
 	 * If the system crashed already then all bets are off,
@@ -181,9 +316,10 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
 	if (test_taint(TAINT_DIE) || did_panic)
 		return;
 
-	hung_task_show_lock = false;
+
 	rcu_read_lock();
 	for_each_process_thread(g, t) {
+
 		if (!max_count--)
 			goto unlock;
 		if (time_after(jiffies, last_break + HUNG_TASK_LOCK_BREAK)) {
@@ -191,18 +327,26 @@ 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)
-			check_hung_task(t, timeout);
+
+		check_hung_task(t, timeout, prev_detect_count);
 	}
  unlock:
 	rcu_read_unlock();
-	if (hung_task_show_lock)
-		debug_show_all_locks();
-	if (hung_task_call_panic) {
-		trigger_all_cpu_backtrace();
-		panic("hung_task: blocked tasks");
+
+	if (!(sysctl_hung_task_detect_count - prev_detect_count))
+		return;
+
+	if (need_warning || hung_task_call_panic) {
+		si_mask |= SYS_INFO_LOCKS;
+
+		if (sysctl_hung_task_all_cpu_backtrace)
+			si_mask |= SYS_INFO_ALL_BT;
 	}
+
+	sys_info(si_mask);
+
+	if (hung_task_call_panic)
+		panic("hung_task: blocked tasks");
 }
 
 static long hung_timeout_jiffies(unsigned long last_checked,
@@ -213,11 +357,12 @@ 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;
@@ -233,6 +378,89 @@ 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_INT_MAX,
+	},
+	{
+		.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,
+	},
+	{
+		.procname	= "hung_task_sys_info",
+		.data		= &hung_task_si_mask,
+		.maxlen         = sizeof(hung_task_si_mask),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sys_info_handler,
+	},
+};
+
+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)
@@ -302,6 +530,7 @@ 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;
 }