1 files changed, 98 insertions, 75 deletions

diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 6eb1f8efd221..20f27e2cf7ae 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
 /*
  * Generic waiting primitives.
  *
@@ -36,6 +37,35 @@ void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue
 }
 EXPORT_SYMBOL(add_wait_queue_exclusive);
 
+void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
+{
+	unsigned long flags;
+
+	wq_entry->flags |= WQ_FLAG_PRIORITY;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	__add_wait_queue(wq_head, wq_entry);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_wait_queue_priority);
+
+int add_wait_queue_priority_exclusive(struct wait_queue_head *wq_head,
+				      struct wait_queue_entry *wq_entry)
+{
+	struct list_head *head = &wq_head->head;
+
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY;
+
+	guard(spinlock_irqsave)(&wq_head->lock);
+
+	if (!list_empty(head) &&
+	    (list_first_entry(head, typeof(*wq_entry), entry)->flags & WQ_FLAG_PRIORITY))
+		return -EBUSY;
+
+	list_add(&wq_entry->entry, head);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(add_wait_queue_priority_exclusive);
+
 void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
@@ -47,37 +77,26 @@ void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry
 EXPORT_SYMBOL(remove_wait_queue);
 
 /*
- * Scan threshold to break wait queue walk.
- * This allows a waker to take a break from holding the
- * wait queue lock during the wait queue walk.
- */
-#define WAITQUEUE_WALK_BREAK_CNT 64
-
-/*
  * The core wakeup function. Non-exclusive wakeups (nr_exclusive == 0) just
  * wake everything up. If it's an exclusive wakeup (nr_exclusive == small +ve
- * number) then we wake all the non-exclusive tasks and one exclusive task.
+ * number) then we wake that number of exclusive tasks, and potentially all
+ * the non-exclusive tasks. Normally, exclusive tasks will be at the end of
+ * the list and any non-exclusive tasks will be woken first. A priority task
+ * may be at the head of the list, and can consume the event without any other
+ * tasks being woken if it's also an exclusive task.
  *
  * There are circumstances in which we can try to wake a task which has already
  * started to run but is not in state TASK_RUNNING. try_to_wake_up() returns
  * zero in this (rare) case, and we handle it by continuing to scan the queue.
  */
 static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
-			int nr_exclusive, int wake_flags, void *key,
-			wait_queue_entry_t *bookmark)
+			int nr_exclusive, int wake_flags, void *key)
 {
 	wait_queue_entry_t *curr, *next;
-	int cnt = 0;
 
 	lockdep_assert_held(&wq_head->lock);
 
-	if (bookmark && (bookmark->flags & WQ_FLAG_BOOKMARK)) {
-		curr = list_next_entry(bookmark, entry);
-
-		list_del(&bookmark->entry);
-		bookmark->flags = 0;
-	} else
-		curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
+	curr = list_first_entry(&wq_head->head, wait_queue_entry_t, entry);
 
 	if (&curr->entry == &wq_head->head)
 		return nr_exclusive;
@@ -86,47 +105,28 @@ static int __wake_up_common(struct wait_queue_head *wq_head, unsigned int mode,
 		unsigned flags = curr->flags;
 		int ret;
 
-		if (flags & WQ_FLAG_BOOKMARK)
-			continue;
-
 		ret = curr->func(curr, mode, wake_flags, key);
 		if (ret < 0)
 			break;
 		if (ret && (flags & WQ_FLAG_EXCLUSIVE) && !--nr_exclusive)
 			break;
-
-		if (bookmark && (++cnt > WAITQUEUE_WALK_BREAK_CNT) &&
-				(&next->entry != &wq_head->head)) {
-			bookmark->flags = WQ_FLAG_BOOKMARK;
-			list_add_tail(&bookmark->entry, &next->entry);
-			break;
-		}
 	}
 
 	return nr_exclusive;
 }
 
-static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int mode,
+static int __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int mode,
 			int nr_exclusive, int wake_flags, void *key)
 {
 	unsigned long flags;
-	wait_queue_entry_t bookmark;
-
-	bookmark.flags = 0;
-	bookmark.private = NULL;
-	bookmark.func = NULL;
-	INIT_LIST_HEAD(&bookmark.entry);
+	int remaining;
 
 	spin_lock_irqsave(&wq_head->lock, flags);
-	nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags, key, &bookmark);
+	remaining = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags,
+			key);
 	spin_unlock_irqrestore(&wq_head->lock, flags);
 
-	while (bookmark.flags & WQ_FLAG_BOOKMARK) {
-		spin_lock_irqsave(&wq_head->lock, flags);
-		nr_exclusive = __wake_up_common(wq_head, mode, nr_exclusive,
-						wake_flags, key, &bookmark);
-		spin_unlock_irqrestore(&wq_head->lock, flags);
-	}
+	return nr_exclusive - remaining;
 }
 
 /**
@@ -136,43 +136,41 @@ static void __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int
  * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: is directly passed to the wakeup function
  *
- * If this function wakes up a task, it executes a full memory barrier before
- * accessing the task state.
+ * If this function wakes up a task, it executes a full memory barrier
+ * before accessing the task state.  Returns the number of exclusive
+ * tasks that were awaken.
  */
-void __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
-			int nr_exclusive, void *key)
+int __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
+	      int nr_exclusive, void *key)
 {
-	__wake_up_common_lock(wq_head, mode, nr_exclusive, 0, key);
+	return __wake_up_common_lock(wq_head, mode, nr_exclusive, 0, key);
 }
 EXPORT_SYMBOL(__wake_up);
 
+void __wake_up_on_current_cpu(struct wait_queue_head *wq_head, unsigned int mode, void *key)
+{
+	__wake_up_common_lock(wq_head, mode, 1, WF_CURRENT_CPU, key);
+}
+
 /*
  * Same as __wake_up but called with the spinlock in wait_queue_head_t held.
  */
 void __wake_up_locked(struct wait_queue_head *wq_head, unsigned int mode, int nr)
 {
-	__wake_up_common(wq_head, mode, nr, 0, NULL, NULL);
+	__wake_up_common(wq_head, mode, nr, 0, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked);
 
 void __wake_up_locked_key(struct wait_queue_head *wq_head, unsigned int mode, void *key)
 {
-	__wake_up_common(wq_head, mode, 1, 0, key, NULL);
+	__wake_up_common(wq_head, mode, 1, 0, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_key);
 
-void __wake_up_locked_key_bookmark(struct wait_queue_head *wq_head,
-		unsigned int mode, void *key, wait_queue_entry_t *bookmark)
-{
-	__wake_up_common(wq_head, mode, 1, 0, key, bookmark);
-}
-EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
-
 /**
  * __wake_up_sync_key - wake up threads blocked on a waitqueue.
  * @wq_head: the waitqueue
  * @mode: which threads
- * @nr_exclusive: how many wake-one or wake-many threads to wake up
  * @key: opaque value to be passed to wakeup targets
  *
  * The sync wakeup differs that the waker knows that it will schedule
@@ -186,29 +184,54 @@ EXPORT_SYMBOL_GPL(__wake_up_locked_key_bookmark);
  * accessing the task state.
  */
 void __wake_up_sync_key(struct wait_queue_head *wq_head, unsigned int mode,
-			int nr_exclusive, void *key)
+			void *key)
 {
-	int wake_flags = 1; /* XXX WF_SYNC */
-
 	if (unlikely(!wq_head))
 		return;
 
-	if (unlikely(nr_exclusive != 1))
-		wake_flags = 0;
-
-	__wake_up_common_lock(wq_head, mode, nr_exclusive, wake_flags, key);
+	__wake_up_common_lock(wq_head, mode, 1, WF_SYNC, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync_key);
 
+/**
+ * __wake_up_locked_sync_key - wake up a thread blocked on a locked waitqueue.
+ * @wq_head: the waitqueue
+ * @mode: which threads
+ * @key: opaque value to be passed to wakeup targets
+ *
+ * The sync wakeup differs in that the waker knows that it will schedule
+ * away soon, so while the target thread will be woken up, it will not
+ * be migrated to another CPU - ie. the two threads are 'synchronized'
+ * with each other. This can prevent needless bouncing between CPUs.
+ *
+ * On UP it can prevent extra preemption.
+ *
+ * If this function wakes up a task, it executes a full memory barrier before
+ * accessing the task state.
+ */
+void __wake_up_locked_sync_key(struct wait_queue_head *wq_head,
+			       unsigned int mode, void *key)
+{
+        __wake_up_common(wq_head, mode, 1, WF_SYNC, key);
+}
+EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);
+
 /*
  * __wake_up_sync - see __wake_up_sync_key()
  */
-void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode, int nr_exclusive)
+void __wake_up_sync(struct wait_queue_head *wq_head, unsigned int mode)
 {
-	__wake_up_sync_key(wq_head, mode, nr_exclusive, NULL);
+	__wake_up_sync_key(wq_head, mode, NULL);
 }
 EXPORT_SYMBOL_GPL(__wake_up_sync);	/* For internal use only */
 
+void __wake_up_pollfree(struct wait_queue_head *wq_head)
+{
+	__wake_up(wq_head, TASK_NORMAL, 0, poll_to_key(EPOLLHUP | POLLFREE));
+	/* POLLFREE must have cleared the queue. */
+	WARN_ON_ONCE(waitqueue_active(wq_head));
+}
+
 /*
  * Note: we use "set_current_state()" _after_ the wait-queue add,
  * because we need a memory barrier there on SMP, so that any
@@ -235,17 +258,22 @@ prepare_to_wait(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_ent
 }
 EXPORT_SYMBOL(prepare_to_wait);
 
-void
+/* Returns true if we are the first waiter in the queue, false otherwise. */
+bool
 prepare_to_wait_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry, int state)
 {
 	unsigned long flags;
+	bool was_empty = false;
 
 	wq_entry->flags |= WQ_FLAG_EXCLUSIVE;
 	spin_lock_irqsave(&wq_head->lock, flags);
-	if (list_empty(&wq_entry->entry))
+	if (list_empty(&wq_entry->entry)) {
+		was_empty = list_empty(&wq_head->head);
 		__add_wait_queue_entry_tail(wq_head, wq_entry);
+	}
 	set_current_state(state);
 	spin_unlock_irqrestore(&wq_head->lock, flags);
+	return was_empty;
 }
 EXPORT_SYMBOL(prepare_to_wait_exclusive);
 
@@ -375,17 +403,12 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i
 	int ret = default_wake_function(wq_entry, mode, sync, key);
 
 	if (ret)
-		list_del_init(&wq_entry->entry);
+		list_del_init_careful(&wq_entry->entry);
 
 	return ret;
 }
 EXPORT_SYMBOL(autoremove_wake_function);
 
-static inline bool is_kthread_should_stop(void)
-{
-	return (current->flags & PF_KTHREAD) && kthread_should_stop();
-}
-
 /*
  * DEFINE_WAIT_FUNC(wait, woken_wake_func);
  *
@@ -415,7 +438,7 @@ long wait_woken(struct wait_queue_entry *wq_entry, unsigned mode, long timeout)
 	 * or woken_wake_function() sees our store to current->state.
 	 */
 	set_current_state(mode); /* A */
-	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !is_kthread_should_stop())
+	if (!(wq_entry->flags & WQ_FLAG_WOKEN) && !kthread_should_stop_or_park())
 		timeout = schedule_timeout(timeout);
 	__set_current_state(TASK_RUNNING);