summaryrefslogtreecommitdiffstats
path: root/kernel/hung_task.c
diff options
context:
space:
mode:
authorDmitry Vyukov <dvyukov@google.com>2018-08-21 21:55:52 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2018-08-22 10:52:47 -0700
commita2e514453861dd39b53b7a50b6771bd3f9852078 (patch)
tree5c5f930b2503ecd1fa5657b7fa95d897a799e6f9 /kernel/hung_task.c
parent91bc9aaf746ae41016bd6b61a48133e162542574 (diff)
downloadlinux-a2e514453861dd39b53b7a50b6771bd3f9852078.tar.bz2
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>
Diffstat (limited to 'kernel/hung_task.c')
-rw-r--r--kernel/hung_task.c15
1 files changed, 14 insertions, 1 deletions
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);