Add a waitqueue helper to add a priority waiter that requires exclusive
wakeups, i.e. that requires that it be the _only_ priority waiter.  The
API will be used by KVM to ensure that at most one of KVM's irqfds is
bound to a single eventfd (across the entire kernel).

Open code the helper instead of using __add_wait_queue() so that the
common path doesn't need to "handle" impossible failures.

Note, the priority_exclusive() name is obviously confusing as the plain
priority() API also sets WQ_FLAG_EXCLUSIVE.  This will be remedied once
KVM switches to add_wait_queue_priority_exclusive(), as the only other
user of add_wait_queue_priority(), Xen's privcmd, doesn't actually operate
in exclusive mode (more than likely, the detail was overlooked when privcmd
copy-pasted (sorry, "was inspired by") KVM's implementation).

Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/wait.h |  2 ++
 kernel/sched/wait.c  | 20 ++++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 6d90ad974408..5fe082c9e52b 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -164,6 +164,8 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern int add_wait_queue_priority_exclusive(struct wait_queue_head *wq_head,
+					     struct wait_queue_entry *wq_entry);
 extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
 static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 51e38f5f4701..80d90d1dc24d 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -47,6 +47,26 @@ void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_
 }
 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;
+	unsigned long flags;
+	int r = 0;
+
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY;
+	spin_lock_irqsave(&wq_head->lock, flags);
+	if (!list_empty(head) &&
+	    (list_first_entry(head, typeof(*wq_entry), entry)->flags & WQ_FLAG_PRIORITY))
+		r = -EBUSY;
+	else
+		list_add(&wq_entry->entry, head);
+	spin_unlock_irqrestore(&wq_head->lock, flags);
+
+	return r;
+}
+EXPORT_SYMBOL(add_wait_queue_priority_exclusive);
+
 void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
-- 
2.49.0.504.g3bcea36a83-goog

Hello Sean,

On 4/2/2025 2:14 AM, Sean Christopherson wrote:
[..snip..]
> diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
> index 51e38f5f4701..80d90d1dc24d 100644
> --- a/kernel/sched/wait.c
> +++ b/kernel/sched/wait.c
> @@ -47,6 +47,26 @@ void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_
>   }
>   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;
> +	unsigned long flags;
> +	int r = 0;
> +
> +	wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY;
> +	spin_lock_irqsave(&wq_head->lock, flags);

nit.

Using "guard(spinlock_irqsave)(&wq_head->lock)" can help you get rid of
both "flags" and "r".

> +	if (!list_empty(head) &&
> +	    (list_first_entry(head, typeof(*wq_entry), entry)->flags & WQ_FLAG_PRIORITY))
> +		r = -EBUSY;
> +	else
> +		list_add(&wq_entry->entry, head);
> +	spin_unlock_irqrestore(&wq_head->lock, flags);
> +
> +	return r;
> +}
> +EXPORT_SYMBOL(add_wait_queue_priority_exclusive);
> +
>   void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
>   {
>   	unsigned long flags;

-- 
Thanks and Regards,
Prateek