diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 6bd05700d8c94cfe5c190008c1eb8910bf8ae0ae..05f05f17a7c2e4fc14f8fa858abc9f7d7715c7b9 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -21,38 +21,34 @@
 
 #include <asm-generic/qspinlock_types.h>
 
+/**
+ * queued_spin_unlock_wait - wait until the _current_ lock holder releases the lock
+ * @lock : Pointer to queued spinlock structure
+ *
+ * There is a very slight possibility of live-lock if the lockers keep coming
+ * and the waiter is just unfortunate enough to not see any unlock state.
+ */
+#ifndef queued_spin_unlock_wait
+extern void queued_spin_unlock_wait(struct qspinlock *lock);
+#endif
+
 /**
  * queued_spin_is_locked - is the spinlock locked?
  * @lock: Pointer to queued spinlock structure
  * Return: 1 if it is locked, 0 otherwise
  */
+#ifndef queued_spin_is_locked
 static __always_inline int queued_spin_is_locked(struct qspinlock *lock)
 {
 	/*
-	 * queued_spin_lock_slowpath() can ACQUIRE the lock before
-	 * issuing the unordered store that sets _Q_LOCKED_VAL.
-	 *
-	 * See both smp_cond_acquire() sites for more detail.
-	 *
-	 * This however means that in code like:
-	 *
-	 *   spin_lock(A)		spin_lock(B)
-	 *   spin_unlock_wait(B)	spin_is_locked(A)
-	 *   do_something()		do_something()
-	 *
-	 * Both CPUs can end up running do_something() because the store
-	 * setting _Q_LOCKED_VAL will pass through the loads in
-	 * spin_unlock_wait() and/or spin_is_locked().
+	 * See queued_spin_unlock_wait().
 	 *
-	 * Avoid this by issuing a full memory barrier between the spin_lock()
-	 * and the loads in spin_unlock_wait() and spin_is_locked().
-	 *
-	 * Note that regular mutual exclusion doesn't care about this
-	 * delayed store.
+	 * Any !0 state indicates it is locked, even if _Q_LOCKED_VAL
+	 * isn't immediately observable.
 	 */
-	smp_mb();
-	return atomic_read(&lock->val) & _Q_LOCKED_MASK;
+	return atomic_read(&lock->val);
 }
+#endif
 
 /**
  * queued_spin_value_unlocked - is the spinlock structure unlocked?
@@ -122,21 +118,6 @@ static __always_inline void queued_spin_unlock(struct qspinlock *lock)
 }
 #endif
 
-/**
- * queued_spin_unlock_wait - wait until current lock holder releases the lock
- * @lock : Pointer to queued spinlock structure
- *
- * There is a very slight possibility of live-lock if the lockers keep coming
- * and the waiter is just unfortunate enough to not see any unlock state.
- */
-static inline void queued_spin_unlock_wait(struct qspinlock *lock)
-{
-	/* See queued_spin_is_locked() */
-	smp_mb();
-	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
-		cpu_relax();
-}
-
 #ifndef virt_spin_lock
 static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 {
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ce2f75e32ae155b30cfe324c56f9bc526771b66a..5fc8c311b8fe59d46decc2c5a049ce6e860a07b8 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -267,6 +267,66 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 #define queued_spin_lock_slowpath	native_queued_spin_lock_slowpath
 #endif
 
+/*
+ * queued_spin_lock_slowpath() can (load-)ACQUIRE the lock before
+ * issuing an _unordered_ store to set _Q_LOCKED_VAL.
+ *
+ * This means that the store can be delayed, but no later than the
+ * store-release from the unlock. This means that simply observing
+ * _Q_LOCKED_VAL is not sufficient to determine if the lock is acquired.
+ *
+ * There are two paths that can issue the unordered store:
+ *
+ *  (1) clear_pending_set_locked():	*,1,0 -> *,0,1
+ *
+ *  (2) set_locked():			t,0,0 -> t,0,1 ; t != 0
+ *      atomic_cmpxchg_relaxed():	t,0,0 -> 0,0,1
+ *
+ * However, in both cases we have other !0 state we've set before to queue
+ * ourseves:
+ *
+ * For (1) we have the atomic_cmpxchg_acquire() that set _Q_PENDING_VAL, our
+ * load is constrained by that ACQUIRE to not pass before that, and thus must
+ * observe the store.
+ *
+ * For (2) we have a more intersting scenario. We enqueue ourselves using
+ * xchg_tail(), which ends up being a RELEASE. This in itself is not
+ * sufficient, however that is followed by an smp_cond_acquire() on the same
+ * word, giving a RELEASE->ACQUIRE ordering. This again constrains our load and
+ * guarantees we must observe that store.
+ *
+ * Therefore both cases have other !0 state that is observable before the
+ * unordered locked byte store comes through. This means we can use that to
+ * wait for the lock store, and then wait for an unlock.
+ */
+#ifndef queued_spin_unlock_wait
+void queued_spin_unlock_wait(struct qspinlock *lock)
+{
+	u32 val;
+
+	for (;;) {
+		val = atomic_read(&lock->val);
+
+		if (!val) /* not locked, we're done */
+			goto done;
+
+		if (val & _Q_LOCKED_MASK) /* locked, go wait for unlock */
+			break;
+
+		/* not locked, but pending, wait until we observe the lock */
+		cpu_relax();
+	}
+
+	/* any unlock is good */
+	while (atomic_read(&lock->val) & _Q_LOCKED_MASK)
+		cpu_relax();
+
+done:
+	smp_rmb(); /* CTRL + RMB -> ACQUIRE */
+}
+EXPORT_SYMBOL(queued_spin_unlock_wait);
+#endif
+
 #endif /* _GEN_PV_LOCK_SLOWPATH */
 
 /**