When I was running my testcase which may block hundreds of threads
on fs locks, I got lockup due to output from debug_show_all_locks()
added by commit b2d4c2edb2e4f89a ("locking/hung_task: Show all locks").
For example, if 1000 threads were blocked in TASK_UNINTERRUPTIBLE state
and 500 out of 1000 threads hold some lock, debug_show_all_locks() from
for_each_process_thread() loop will report locks held by 500 threads for
1000 times. This is a too much noise.
In order to make sure rcu_lock_break() is called frequently, we should
avoid calling debug_show_all_locks() from for_each_process_thread() loop
because debug_show_all_locks() effectively calls for_each_process_thread()
loop. Let's defer calling debug_show_all_locks() till before panic() or
leaving for_each_process_thread() loop.
Signed-off-by: Tetsuo Handa <penguin-kernel@xxxxxxxxxxxxxxxxxxx>
Cc: Vegard Nossum <vegard.nossum@xxxxxxxxxx>
---
kernel/hung_task.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index f0f8e2a..751593e 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -43,6 +43,7 @@
int __read_mostly sysctl_hung_task_warnings = 10;
static int __read_mostly did_panic;
+static bool hung_task_show_lock;
static struct task_struct *watchdog_task;
@@ -120,12 +121,14 @@ static void check_hung_task(struct task_struct *t, unsigned long timeout)
pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
" disables this message.\n");
sched_show_task(t);
- debug_show_all_locks();
+ hung_task_show_lock = true;
}
touch_nmi_watchdog();
if (sysctl_hung_task_panic) {
+ if (hung_task_show_lock)
+ debug_show_all_locks();
trigger_all_cpu_backtrace();
panic("hung_task: blocked tasks");
}
@@ -172,6 +175,7 @@ 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--)
@@ -187,6 +191,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
}
unlock:
rcu_read_unlock();
+ if (hung_task_show_lock)
+ debug_show_all_locks();
}
static long hung_timeout_jiffies(unsigned long last_checked,