[RFC] hung_task:add detecting task in D state milliseconds timeout

From: yang che
Date: Thu Jul 02 2020 - 10:11:16 EST


current hung_task_check_interval_secs and hung_task_timeout_secs
only supports seconds.in some cases,the TASK_UNINTERRUPTIBLE state
takes less than 1 second.The task of the graphical interface,
the unterruptible state lasts for hundreds of milliseconds
will cause the interface to freeze

echo 1 > /proc/sys/kernel/hung_task_milliseconds
value of hung_task_check_interval_secs and hung_task_timeout_secs whill
to milliseconds

Signed-off-by: yang che <chey84736@xxxxxxxxx>
---
include/linux/sched/sysctl.h | 1 +
kernel/hung_task.c | 33 +++++++++++++++++++++++++++------
kernel/sysctl.c | 9 +++++++++
3 files changed, 37 insertions(+), 6 deletions(-)

diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h
index 660ac49..e5e5de2 100644
--- a/include/linux/sched/sysctl.h
+++ b/include/linux/sched/sysctl.h
@@ -16,6 +16,7 @@ extern unsigned int sysctl_hung_task_all_cpu_backtrace;

extern int sysctl_hung_task_check_count;
extern unsigned int sysctl_hung_task_panic;
+extern unsigned int sysctl_hung_task_millisecond;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_check_interval_secs;
extern int sysctl_hung_task_warnings;
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index ce76f49..7f34912 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -44,6 +44,14 @@ 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;

/*
+ * sysctl_hung_task_milliseconds is enable milliseconds
+ *
+ * if is 1 , hung_task_timeout_secs and hung_task_check_interval_secs will
+ * means set to millisecondsuse. as hung_task_timeout_secs is 5, will 5 milliseconds
+ */
+unsigned int __read_mostly sysctl_hung_task_millisecond;
+
+/*
* Zero (default value) means use sysctl_hung_task_timeout_secs:
*/
unsigned long __read_mostly sysctl_hung_task_check_interval_secs;
@@ -108,8 +116,13 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
t->last_switch_time = jiffies;
return;
}
- if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
- return;
+ if (sysctl_hung_task_millisecond) {
+ if (time_is_after_jiffies(t->last_switch_time + (timeout * HZ) / 1000))
+ return;
+ } else {
+ if (time_is_after_jiffies(t->last_switch_time + timeout * HZ))
+ return;
+ }

trace_sched_process_hang(t);

@@ -126,8 +139,12 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
if (sysctl_hung_task_warnings) {
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, (jiffies - t->last_switch_time) / HZ);
+ if (sysctl_hung_task_millisecond)
+ pr_err("INFO: task %s:%d blocked for more than %ld milliiseconds.\n",
+ t->comm, t->pid, (jiffies - t->last_switch_time) / HZ * 1000);
+ else
+ pr_err("INFO: task %s:%d blocked for more than %ld seconds.\n",
+ 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, " "),
@@ -217,8 +234,12 @@ static long hung_timeout_jiffies(unsigned long last_checked,
unsigned long timeout)
{
/* timeout of 0 will disable the watchdog */
- return timeout ? last_checked - jiffies + timeout * HZ :
- MAX_SCHEDULE_TIMEOUT;
+ if (sysctl_hung_task_millisecond)
+ return timeout ? last_checked - jiffies + (timeout * HZ) / 1000 :
+ MAX_SCHEDULE_TIMEOUT;
+ else
+ return timeout ? last_checked - jiffies + timeout * HZ :
+ MAX_SCHEDULE_TIMEOUT;
}

/*
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index db1ce7a..0bdcd66 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -2476,6 +2476,15 @@ static struct ctl_table kern_table[] = {
.extra1 = SYSCTL_ZERO,
},
{
+ .procname = "hung_task_milliseconds",
+ .data = &sysctl_hung_task_millisecond,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = SYSCTL_ZERO,
+ .extra2 = SYSCTL_ONE,
+ },
+ {
.procname = "hung_task_timeout_secs",
.data = &sysctl_hung_task_timeout_secs,
.maxlen = sizeof(unsigned long),
--
2.7.4