kernel/hung_task.c: allow to set checking interval separately from timeout

Currently task hung checking interval is equal to timeout, as the result
hung is detected anywhere between timeout and 2*timeout.  This is fine for
most interactive environments, but this hurts automated testing setups
(syzbot).  In an automated setup we need to strictly order CPU lockup <
RCU stall < workqueue lockup < task hung < silent loss, so that RCU stall
is not detected as task hung and task hung is not detected as silent
machine loss.  The large variance in task hung detection timeout requires
setting silent machine loss timeout to a very large value (e.g.  if task
hung is 3 mins, then silent loss need to be set to ~7 mins).  The
additional 3 minutes significantly reduce testing efficiency because
usually we crash kernel within a minute, and this can add hours to bug
localization process as it needs to do dozens of tests.

Allow setting checking interval separately from timeout.  This allows to
set timeout to, say, 3 minutes, but checking interval to 10 secs.

The interval is controlled via a new hung_task_check_interval_secs sysctl,
similar to the existing hung_task_timeout_secs sysctl.  The default value
of 0 results in the current behavior: checking interval is equal to
timeout.

[akpm@linux-foundation.org: update hung_task_timeout_max's comment]
Link: http://lkml.kernel.org/r/20180611111004.203513-1-dvyukov@google.com
Signed-off-by: Dmitry Vyukov <dvyukov@google.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 27 insertions, 2 deletions

diff --git a/kernel/fork.c b/kernel/fork.c
index 8c760effa42e..8bcef2413f1b 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1302,6 +1302,7 @@ static int copy_mm(unsigned long clone_flags, struct task_struct *tsk)
 	tsk->nvcsw = tsk->nivcsw = 0;
 #ifdef CONFIG_DETECT_HUNG_TASK
 	tsk->last_switch_count = tsk->nvcsw + tsk->nivcsw;
+	tsk->last_switch_time = 0;
 #endif
 
 	tsk->mm = NULL;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index 32b479468e4d..b9132d1269ef 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -40,6 +40,11 @@ int __read_mostly sysctl_hung_task_check_count = PID_MAX_LIMIT;
  */
 unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_TASK_TIMEOUT;
 
+/*
+ * Zero (default value) means use sysctl_hung_task_timeout_secs:
+ */
+unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
+
 int __read_mostly sysctl_hung_task_warnings = 10;
 
 static int __read_mostly did_panic;
@@ -98,8 +103,11 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
 
 	if (switch_count != t->last_switch_count) {
 		t->last_switch_count = switch_count;
+		t->last_switch_time = jiffies;
 		return;
 	}
+	if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
+		return;
 
 	trace_sched_process_hang(t);
 
@@ -245,8 +253,13 @@ static int watchdog(void *dummy)
 
 	for ( ; ; ) {
 		unsigned long timeout = sysctl_hung_task_timeout_secs;
-		long t = hung_timeout_jiffies(hung_last_checked, timeout);
+		unsigned long interval = sysctl_hung_task_check_interval_secs;
+		long t;
 
+		if (interval == 0)
+			interval = timeout;
+		interval = min_t(unsigned long, interval, timeout);
+		t = hung_timeout_jiffies(hung_last_checked, interval);
 		if (t <= 0) {
 			if (!atomic_xchg(&reset_hung_task, 0))
 				check_hung_uninterruptible_tasks(timeout);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index f22f76b7a138..dbdcb6673b27 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -145,7 +145,10 @@ static int minolduid;
 static int ngroups_max = NGROUPS_MAX;
 static const int cap_last_cap = CAP_LAST_CAP;
 
-/*this is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs */
+/*
+ * This is needed for proc_doulongvec_minmax of sysctl_hung_task_timeout_secs
+ * and hung_task_check_interval_secs
+ */
 #ifdef CONFIG_DETECT_HUNG_TASK
 static unsigned long hung_task_timeout_max = (LONG_MAX/HZ);
 #endif
@@ -1091,6 +1094,14 @@ static struct ctl_table kern_table[] = {
 		.extra2		= &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		= &hung_task_timeout_max,
+	},
+	{
 		.procname	= "hung_task_warnings",
 		.data		= &sysctl_hung_task_warnings,
 		.maxlen		= sizeof(int),