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>

diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index 545f371380574e785abbb0ab3a09eeff9657ce94..ad826d2a4557dea643c18e2c160c6d1f48650431 100644 (file)
--- a/include/linux/sched/wake_q.h
+++ b/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,
-                      struct task_struct *task);
+extern void wake_q_add(struct wake_q_head *head, 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 */

diff --git a/kernel/futex.c b/kernel/futex.c
index 69e619baf709b9245f0cbf26f8fc3c91c17fd418..2abe1a0b30626c6161e8ec18e57d5ba6b04a74b5 100644 (file)
--- a/kernel/futex.c
+++ b/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);
-       put_task_struct(p);
+       wake_q_add_safe(wake_q, p);
 }
 
 /*

diff --git a/kernel/locking/rwsem-xadd.c b/kernel/locking/rwsem-xadd.c
index 50d9af615dc49850acb3e0dd263cebf14130a8b6..fbe96341beeed2c37f84526cb70adbe1b8734156 100644 (file)
--- a/kernel/locking/rwsem-xadd.c
+++ b/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() already take the task ref */
-               put_task_struct(tsk);
+               wake_q_add_safe(wake_q, tsk);
        }
 
        adjustment = woken * RWSEM_ACTIVE_READ_BIAS - adjustment;

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 3c8b4dba3d2d5d4c6c8a7152dea1b455e3a27f9f..64ceaa5158c514b04595a2e71e19c600772972b7 100644 (file)
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -396,19 +396,7 @@ static bool set_nr_if_polling(struct task_struct *p)
 #endif
 #endif
 
-/**
- * wake_q_add() - queue a wakeup for 'later' waking.
- * @head: the wake_q_head to add @task to
- * @task: the task to queue for 'later' wakeup
- *
- * Queue a task for later wakeup, most likely by the wake_up_q() call in the
- * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
- * instantly.
- *
- * This function must be used as-if it were wake_up_process(); IOW the task
- * must be ready to be woken at this location.
- */
-void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
 {
        struct wake_q_node *node = &task->wake_q;
 
@@ -422,15 +410,55 @@ void wake_q_add(struct wake_q_head *head, struct task_struct *task)
         */
        smp_mb__before_atomic();
        if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
-               return;
-
-       get_task_struct(task);
+               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
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ */
+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
+{
+       if (__wake_q_add(head, task))
+               get_task_struct(task);
+}
+
+/**
+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
+ * @head: the wake_q_head to add @task to
+ * @task: the task to queue for 'later' wakeup
+ *
+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
+ * instantly.
+ *
+ * This function must be used as-if it were wake_up_process(); IOW the task
+ * must be ready to be woken at this location.
+ *
+ * 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
+ * queued for wakeup.
+ */
+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
+{
+       if (!__wake_q_add(head, task))
+               put_task_struct(task);
 }
 
 void wake_up_q(struct wake_q_head *head)