sched/core: Introduce set_special_state()

Gaurav reported a perceived problem with TASK_PARKED, which turned out
to be a broken wait-loop pattern in __kthread_parkme(), but the
reported issue can (and does) in fact happen for states that do not do
condition based sleeps.

When the 'current->state = TASK_RUNNING' store of a previous
(concurrent) try_to_wake_up() collides with the setting of a 'special'
sleep state, we can loose the sleep state.

Normal condition based wait-loops are immune to this problem, but for
sleep states that are not condition based are subject to this problem.

There already is a fix for TASK_DEAD. Abstract that and also apply it
to TASK_STOPPED and TASK_TRACED, both of which are also without
condition based wait-loop.

Reported-by: Gaurav Kohli <gkohli@codeaurora.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

2 files changed, 46 insertions, 6 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index b3d697f3b573..c2413703f45d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -112,17 +112,36 @@ struct task_group;
 
 #ifdef CONFIG_DEBUG_ATOMIC_SLEEP
 
+/*
+ * Special states are those that do not use the normal wait-loop pattern. See
+ * the comment with set_special_state().
+ */
+#define is_special_task_state(state)				\
+	((state) & (__TASK_STOPPED | __TASK_TRACED | TASK_DEAD))
+
 #define __set_current_state(state_value)			\
 	do {							\
+		WARN_ON_ONCE(is_special_task_state(state_value));\
 		current->task_state_change = _THIS_IP_;		\
 		current->state = (state_value);			\
 	} while (0)
+
 #define set_current_state(state_value)				\
 	do {							\
+		WARN_ON_ONCE(is_special_task_state(state_value));\
 		current->task_state_change = _THIS_IP_;		\
 		smp_store_mb(current->state, (state_value));	\
 	} while (0)
 
+#define set_special_state(state_value)					\
+	do {								\
+		unsigned long flags; /* may shadow */			\
+		WARN_ON_ONCE(!is_special_task_state(state_value));	\
+		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
+		current->task_state_change = _THIS_IP_;			\
+		current->state = (state_value);				\
+		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
+	} while (0)
 #else
 /*
  * set_current_state() includes a barrier so that the write of current->state
@@ -144,8 +163,8 @@ struct task_group;
  *
  * The above is typically ordered against the wakeup, which does:
  *
- *	need_sleep = false;
- *	wake_up_state(p, TASK_UNINTERRUPTIBLE);
+ *   need_sleep = false;
+ *   wake_up_state(p, TASK_UNINTERRUPTIBLE);
  *
  * Where wake_up_state() (and all other wakeup primitives) imply enough
  * barriers to order the store of the variable against wakeup.
@@ -154,12 +173,33 @@ struct task_group;
  * once it observes the TASK_UNINTERRUPTIBLE store the waking CPU can issue a
  * TASK_RUNNING store which can collide with __set_current_state(TASK_RUNNING).
  *
- * This is obviously fine, since they both store the exact same value.
+ * However, with slightly different timing the wakeup TASK_RUNNING store can
+ * also collide with the TASK_UNINTERRUPTIBLE store. Loosing that store is not
+ * a problem either because that will result in one extra go around the loop
+ * and our @cond test will save the day.
  *
  * Also see the comments of try_to_wake_up().
  */
-#define __set_current_state(state_value) do { current->state = (state_value); } while (0)
-#define set_current_state(state_value)	 smp_store_mb(current->state, (state_value))
+#define __set_current_state(state_value)				\
+	current->state = (state_value)
+
+#define set_current_state(state_value)					\
+	smp_store_mb(current->state, (state_value))
+
+/*
+ * set_special_state() should be used for those states when the blocking task
+ * can not use the regular condition based wait-loop. In that case we must
+ * serialize against wakeups such that any possible in-flight TASK_RUNNING stores
+ * will not collide with our state change.
+ */
+#define set_special_state(state_value)					\
+	do {								\
+		unsigned long flags; /* may shadow */			\
+		raw_spin_lock_irqsave(&current->pi_lock, flags);	\
+		current->state = (state_value);				\
+		raw_spin_unlock_irqrestore(&current->pi_lock, flags);	\
+	} while (0)
+
 #endif
 
 /* Task command name length: */
diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h
index a7ce74c74e49..113d1ad1ced7 100644
--- a/include/linux/sched/signal.h
+++ b/include/linux/sched/signal.h
@@ -280,7 +280,7 @@ static inline void kernel_signal_stop(void)
 {
 	spin_lock_irq(&current->sighand->siglock);
 	if (current->jobctl & JOBCTL_STOP_DEQUEUED)
-		__set_current_state(TASK_STOPPED);
+		set_special_state(TASK_STOPPED);
 	spin_unlock_irq(&current->sighand->siglock);
 
 	schedule();