kernel/hung_task.c: defer showing held locks

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 b2d4c2edb2 ("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.

Link: http://lkml.kernel.org/r/1489296834-60436-1-git-send-email-penguin-kernel@I-love.SAKURA.ne.jp
Signed-off-by: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reviewed-by: Vegard Nossum <vegard.nossum@oracle.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
Tetsuo Handa 2017-05-08 15:55:11 -07:00 committed by Linus Torvalds
parent 31b8cc8077
commit 780cbcf287
1 changed files with 7 additions and 1 deletions

View File

@ -43,6 +43,7 @@ unsigned long __read_mostly sysctl_hung_task_timeout_secs = CONFIG_DEFAULT_HUNG_
int __read_mostly sysctl_hung_task_warnings = 10; int __read_mostly sysctl_hung_task_warnings = 10;
static int __read_mostly did_panic; static int __read_mostly did_panic;
static bool hung_task_show_lock;
static struct task_struct *watchdog_task; 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\"" pr_err("\"echo 0 > /proc/sys/kernel/hung_task_timeout_secs\""
" disables this message.\n"); " disables this message.\n");
sched_show_task(t); sched_show_task(t);
debug_show_all_locks(); hung_task_show_lock = true;
} }
touch_nmi_watchdog(); touch_nmi_watchdog();
if (sysctl_hung_task_panic) { if (sysctl_hung_task_panic) {
if (hung_task_show_lock)
debug_show_all_locks();
trigger_all_cpu_backtrace(); trigger_all_cpu_backtrace();
panic("hung_task: blocked tasks"); 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) if (test_taint(TAINT_DIE) || did_panic)
return; return;
hung_task_show_lock = false;
rcu_read_lock(); rcu_read_lock();
for_each_process_thread(g, t) { for_each_process_thread(g, t) {
if (!max_count--) if (!max_count--)
@ -187,6 +191,8 @@ static void check_hung_uninterruptible_tasks(unsigned long timeout)
} }
unlock: unlock:
rcu_read_unlock(); rcu_read_unlock();
if (hung_task_show_lock)
debug_show_all_locks();
} }
static long hung_timeout_jiffies(unsigned long last_checked, static long hung_timeout_jiffies(unsigned long last_checked,