sched/wake_q: Reduce reference counting for special users

Some users, specifically futexes and rwsems, required fixes
that allowed the callers to be safe when wakeups occur before
they are expected by wake_up_q(). Such scenarios also play
games and rely on reference counting, and until now were
pivoting on wake_q doing it. With the wake_q_add() call being
moved down, this can no longer be the case. As such we end up
with a a double task refcounting overhead; and these callers
care enough about this (being rather core-ish).

This patch introduces a wake_q_add_safe() call that serves
for callers that have already done refcounting and therefore the
task is 'safe' from wake_q point of view (int that it requires
reference throughout the entire queue/>wakeup cycle). In the one
case it has internal reference counting, in the other case it
consumes the reference counting.

Signed-off-by: Davidlohr Bueso <dbueso@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Xie Yongji <xieyongji@baidu.com>
Cc: Yongji Xie <elohimes@gmail.com>
Cc: andrea.parri@amarulasolutions.com
Cc: lilin24@baidu.com
Cc: liuqi16@baidu.com
Cc: nixun@baidu.com
Cc: yuanlinsi01@baidu.com
Cc: zhangyu31@baidu.com
Link: https://lkml.kernel.org/r/20181218195352.7orq3upiwfdbrdne@linux-r8p5
Signed-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/sched/wake_q.h

@@ -51,8 +51,8 @@ static inline void wake_q_init(struct wake_q_head *head)
 	head->lastp = &head->first;
 }
 
-extern void wake_q_add(struct wake_q_head *head,
+extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
-		       struct task_struct *task);
+extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
 
 #endif /* _LINUX_SCHED_WAKE_Q_H */

kernel/futex.c

@@ -1463,8 +1463,7 @@ static void mark_wake_futex(struct wake_q_head *wake_q, struct futex_q *q)
 	 * Queue the task for later wakeup for after we've released
 	 * the hb->lock. wake_q_add() grabs reference to p.
 	 */
-	wake_q_add(wake_q, p);
+	wake_q_add_safe(wake_q, p);
-	put_task_struct(p);
 }
 
 /*

kernel/locking/rwsem-xadd.c

@@ -211,9 +211,7 @@ static void __rwsem_mark_wake(struct rw_semaphore *sem,
 		 * Ensure issuing the wakeup (either by us or someone else)
 		 * after setting the reader waiter to nil.
 		 */
-		wake_q_add(wake_q, tsk);
+		wake_q_add_safe(wake_q, tsk);
-		/* wake_q_add() already take the task ref */
-		put_task_struct(tsk);
 	}
 
 	adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;

kernel/sched/core.c

@@ -396,6 +396,30 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+	struct wake_q_node *node = &task->wake_q;
+
+	/*
+	 * Atomically grab the task, if ->wake_q is !nil already it means
+	 * its already queued (either by us or someone else) and will get the
+	 * wakeup due to that.
+	 *
+	 * In order to ensure that a pending wakeup will observe our pending
+	 * state, even in the failed case, an explicit smp_mb() must be used.
+	 */
+	smp_mb__before_atomic();
+	if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
+		return false;
+
+	/*
+	 * The head is context local, there can be no concurrency.
+	 */
+	*head->lastp = node;
+	head->lastp = &node->next;
+	return true;
+}
+
 /**
  * wake_q_add() - queue a wakeup for 'later' waking.
  * @head: the wake_q_head to add @task to
@@ -410,27 +434,31 @@ static bool set_nr_if_polling(struct task_struct *p)
  */
 void wake_q_add(struct wake_q_head *head, struct task_struct *task)
 {
-	struct wake_q_node *node = &task->wake_q;
+	if (__wake_q_add(head, task))
+		get_task_struct(task);
+}
 
-	/*
+/**
-	 * Atomically grab the task, if ->wake_q is !nil already it means
+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
-	 * its already queued (either by us or someone else) and will get the
+ * @head: the wake_q_head to add @task to
-	 * wakeup due to that.
+ * @task: the task to queue for 'later' wakeup
-	 *
+ *
-	 * In order to ensure that a pending wakeup will observe our pending
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
-	 * state, even in the failed case, an explicit smp_mb() must be used.
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
-	 */
+ * instantly.
-	smp_mb__before_atomic();
+ *
-	if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
+ * This function must be used as-if it were wake_up_process(); IOW the task
-		return;
+ * must be ready to be woken at this location.
-
+ *
-	get_task_struct(task);
+ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
-
+ * that already hold reference to @task can call the 'safe' version and trust
-	/*
+ * wake_q to do the right thing depending whether or not the @task is already
-	 * The head is context local, there can be no concurrency.
+ * queued for wakeup.
-	 */
+ */
-	*head->lastp = node;
+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
-	head->lastp = &node->next;
+{
+	if (!__wake_q_add(head, task))
+		put_task_struct(task);
 }
 
 void wake_up_q(struct wake_q_head *head)