1 files changed, 37 insertions, 58 deletions

diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 133b74730738..20f27e2cf7ae 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -4,6 +4,7 @@
  *
  * (C) 2004 Nadia Yvette Chambers, Oracle
  */
+#include "sched.h"
 
 void __init_waitqueue_head(struct wait_queue_head *wq_head, const char *name, struct lock_class_key *key)
 {
@@ -40,13 +41,31 @@ void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_
 {
 	unsigned long flags;
 
-	wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY;
+	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;
@@ -58,41 +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 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.
+ * 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;
@@ -101,21 +105,11 @@ 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;
@@ -125,20 +119,12 @@ static int __wake_up_common_lock(struct wait_queue_head *wq_head, unsigned int m
 			int nr_exclusive, int wake_flags, void *key)
 {
 	unsigned long flags;
-	wait_queue_entry_t bookmark;
-	int remaining = nr_exclusive;
+	int remaining;
 
-	bookmark.flags = 0;
-	bookmark.private = NULL;
-	bookmark.func = NULL;
-	INIT_LIST_HEAD(&bookmark.entry);
-
-	do {
-		spin_lock_irqsave(&wq_head->lock, flags);
-		remaining = __wake_up_common(wq_head, mode, remaining,
-						wake_flags, key, &bookmark);
-		spin_unlock_irqrestore(&wq_head->lock, flags);
-	} while (bookmark.flags & WQ_FLAG_BOOKMARK);
+	spin_lock_irqsave(&wq_head->lock, flags);
+	remaining = __wake_up_common(wq_head, mode, nr_exclusive, wake_flags,
+			key);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
 
 	return nr_exclusive - remaining;
 }
@@ -161,28 +147,26 @@ int __wake_up(struct wait_queue_head *wq_head, unsigned int mode,
 }
 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
@@ -228,7 +212,7 @@ EXPORT_SYMBOL_GPL(__wake_up_sync_key);
 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, NULL);
+        __wake_up_common(wq_head, mode, 1, WF_SYNC, key);
 }
 EXPORT_SYMBOL_GPL(__wake_up_locked_sync_key);
 
@@ -425,11 +409,6 @@ int autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned mode, i
 }
 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);
  *
@@ -459,7 +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);