[PATCH V2 2/4] sched/wait: avoid abort_exclusive_wait() in ___wait_event()

[Oleg Nesterov]

___wait_event() doesn't really need abort_exclusive_wait(), we can simply
change prepare_to_wait_event() to remove the waiter from q->task_list if
it was interrupted.

This simplifies the code/logic, and this way prepare_to_wait_event() can
have more users, see the next change.

Signed-off-by: Oleg Nesterov <oleg@xxxxxxxxxx>
---
 include/linux/wait.h |  7 +------
 kernel/sched/wait.c  | 23 ++++++++++++++++++-----
 2 files changed, 19 insertions(+), 11 deletions(-)

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 329f796..5179915 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -280,12 +280,7 @@ wait_queue_head_t *bit_waitqueue(void *, int);
 									\
 		if (___wait_is_interruptible(state) && __int) {		\
 			__ret = __int;					\
-			if (exclusive) {				\
-				abort_exclusive_wait(&wq, &__wait, 	\
-						     NULL);		\
-				goto __out;				\
-			}						\
-			break;						\
+			goto __out;					\
 		}							\
 									\
 		cmd;							\
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 2bbba01..4af0dc8 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -199,15 +199,28 @@ EXPORT_SYMBOL(prepare_to_wait_exclusive);
 long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
 {
 	unsigned long flags;
-
-	if (signal_pending_state(state, current))
-		return -ERESTARTSYS;
+	long ret = 0;
 
 	wait->private = current;
 	wait->func = autoremove_wake_function;
 
 	spin_lock_irqsave(&q->lock, flags);
-	if (list_empty(&wait->task_list)) {
+	if (unlikely(signal_pending_state(state, current))) {
+		/*
+		 * Exclusive waiter must not fail if it was selected by wakeup,
+		 * it should "consume" the condition we were waiting for.
+		 *
+		 * The caller will recheck the condition and return success if
+		 * we were already woken up, we can not miss the event because
+		 * wakeup locks/unlocks the same q->lock.
+		 *
+		 * But we need to ensure that set-condition + wakeup after that
+		 * can't see us, it should wake up another exclusive waiter if
+		 * we fail.
+		 */
+		list_del_init(&wait->task_list);
+		ret = -ERESTARTSYS;
+	} else if (list_empty(&wait->task_list)) {
 		if (wait->flags & WQ_FLAG_EXCLUSIVE)
 			__add_wait_queue_tail(q, wait);
 		else
@@ -216,7 +229,7 @@ long prepare_to_wait_event(wait_queue_head_t *q, wait_queue_t *wait, int state)
 	set_current_state(state);
 	spin_unlock_irqrestore(&q->lock, flags);
 
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL(prepare_to_wait_event);
 
-- 
2.5.0