sched/wait: Add a waitqueue helper for fully exclusive priority waiters

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.

Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250522235223.3178519-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>

1 files changed, 18 insertions, 0 deletions

diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4ab3ab195277..15632c89c4f2 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -47,6 +47,24 @@ 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;
+
+	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;