We are getting reports from syzbot where running task seems to be
relevant to a hung task problem but NMI backtrace does not print useful
information [1].
Although commit 8cc05c71ba5f7936 ("locking/lockdep: Move sanity check to
inside lockdep_print_held_locks()") says that calling
lockdep_print_held_locks() on a running thread is considered unsafe,
it is useful for syzbot to show locks and backtrace of running tasks.
Thus, let's allow it if CONFIG_DEBUG_AID_FOR_SYZBOT is defined.
[1]
https://syzkaller.appspot.com/bug?id=8bab7a6a5597bb10f90e8227a7d8a483748d93be
Signed-off-by: Tetsuo Handa <penguin-ker...@i-love.sakura.ne.jp>
Cc: Dmitry Vyukov <dvyu...@google.com>
---
kernel/hung_task.c | 20 ++++++++++++++++++++
kernel/locking/lockdep.c | 9 +++++++++
2 files changed, 29 insertions(+)
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index b9132d1..1ac49a5 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -201,6 +201,26 @@ static void check_hung_uninterruptible_tasks(unsigned long
timeout)
if (hung_task_show_lock)
debug_show_all_locks();
if (hung_task_call_panic) {
+#ifdef CONFIG_DEBUG_AID_FOR_SYZBOT
+ /*
+ * debug_show_all_locks() above forcibly dumped locks held by
+ * running tasks with locks held. Now, let's dump backtrace of
+ * running tasks as well, for NMI backtrace below tends to show
+ * current thread (i.e. khungtaskd thread itself) and idle CPU
+ * which are useless for debugging hung task problems.
+ */
+ rcu_read_lock();
+ for_each_process_thread(g, t) {
+ if (t->state != TASK_RUNNING || t == current)
+ continue;
+ pr_err("INFO: task %s:%d was running.\n", t->comm,
+ t->pid);
+ sched_show_task(t);
+ touch_nmi_watchdog();
+ touch_all_softlockup_watchdogs();
+ }
+ rcu_read_unlock();
+#endif
trigger_all_cpu_backtrace();
panic("hung_task: blocked tasks");
}
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index e406c5f..efeebf6 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -565,12 +565,21 @@ static void lockdep_print_held_locks(struct task_struct
*p)
else
printk("%d lock%s held by %s/%d:\n", depth,
depth > 1 ? "s" : "", p->comm, task_pid_nr(p));
+#ifndef CONFIG_DEBUG_AID_FOR_SYZBOT
/*
* It's not reliable to print a task's held locks if it's not sleeping
* and it's not the current task.
*/
if (p->state == TASK_RUNNING && p != current)
return;
+#else
+ /*
+ * But showing locks and backtrace of running tasks seems to be helpful
+ * for debugging hung task problems. Since syzbot will call panic()
+ * shortly, risking problems caused by accessing stale information is
+ * acceptable here.
+ */
+#endif
for (i = 0; i < depth; i++) {
printk(" #%d: ", i);
print_lock(p->held_locks + i);
--
1.8.3.1
