diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index e60e618287b4913758e4f055b8a36c0e801a8161..7bd053e528c227744098d50afbe39882ee434fd6 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -127,6 +127,17 @@ static inline __pure struct mcs_spinlock *decode_tail(u32 tail)
 #define _Q_LOCKED_PENDING_MASK (_Q_LOCKED_MASK | _Q_PENDING_MASK)
 
 #if _Q_PENDING_BITS == 8
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	WRITE_ONCE(lock->pending, 0);
+}
+
 /**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
@@ -162,6 +173,17 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 
 #else /* _Q_PENDING_BITS == 8 */
 
+/**
+ * clear_pending - clear the pending bit.
+ * @lock: Pointer to queued spinlock structure
+ *
+ * *,1,* -> *,0,*
+ */
+static __always_inline void clear_pending(struct qspinlock *lock)
+{
+	atomic_andnot(_Q_PENDING_VAL, &lock->val);
+}
+
 /**
  * clear_pending_set_locked - take ownership and clear the pending bit.
  * @lock: Pointer to queued spinlock structure
@@ -266,7 +288,7 @@ static __always_inline u32  __pv_wait_head_or_lock(struct qspinlock *lock,
 void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 {
 	struct mcs_spinlock *prev, *next, *node;
-	u32 new, old, tail;
+	u32 old, tail;
 	int idx;
 
 	BUILD_BUG_ON(CONFIG_NR_CPUS >= (1U << _Q_TAIL_CPU_BITS));
@@ -289,59 +311,51 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 					       (VAL != _Q_PENDING_VAL) || !cnt--);
 	}
 
+	/*
+	 * If we observe any contention; queue.
+	 */
+	if (val & ~_Q_LOCKED_MASK)
+		goto queue;
+
 	/*
 	 * trylock || pending
 	 *
 	 * 0,0,0 -> 0,0,1 ; trylock
 	 * 0,0,1 -> 0,1,1 ; pending
 	 */
-	for (;;) {
+	val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+	if (!(val & ~_Q_LOCKED_MASK)) {
 		/*
-		 * If we observe any contention; queue.
+		 * We're pending, wait for the owner to go away.
+		 *
+		 * *,1,1 -> *,1,0
+		 *
+		 * this wait loop must be a load-acquire such that we match the
+		 * store-release that clears the locked bit and create lock
+		 * sequentiality; this is because not all
+		 * clear_pending_set_locked() implementations imply full
+		 * barriers.
 		 */
-		if (val & ~_Q_LOCKED_MASK)
-			goto queue;
-
-		new = _Q_LOCKED_VAL;
-		if (val == new)
-			new |= _Q_PENDING_VAL;
+		if (val & _Q_LOCKED_MASK) {
+			smp_cond_load_acquire(&lock->val.counter,
+					      !(VAL & _Q_LOCKED_MASK));
+		}
 
 		/*
-		 * Acquire semantic is required here as the function may
-		 * return immediately if the lock was free.
+		 * take ownership and clear the pending bit.
+		 *
+		 * *,1,0 -> *,0,1
 		 */
-		old = atomic_cmpxchg_acquire(&lock->val, val, new);
-		if (old == val)
-			break;
-
-		val = old;
-	}
-
-	/*
-	 * we won the trylock
-	 */
-	if (new == _Q_LOCKED_VAL)
+		clear_pending_set_locked(lock);
 		return;
+	}
 
 	/*
-	 * we're pending, wait for the owner to go away.
-	 *
-	 * *,1,1 -> *,1,0
-	 *
-	 * this wait loop must be a load-acquire such that we match the
-	 * store-release that clears the locked bit and create lock
-	 * sequentiality; this is because not all clear_pending_set_locked()
-	 * implementations imply full barriers.
-	 */
-	smp_cond_load_acquire(&lock->val.counter, !(VAL & _Q_LOCKED_MASK));
-
-	/*
-	 * take ownership and clear the pending bit.
-	 *
-	 * *,1,0 -> *,0,1
+	 * If pending was clear but there are waiters in the queue, then
+	 * we need to undo our setting of pending before we queue ourselves.
 	 */
-	clear_pending_set_locked(lock);
-	return;
+	if (!(val & _Q_PENDING_MASK))
+		clear_pending(lock);
 
 	/*
 	 * End of pending bit optimistic spinning and beginning of MCS
@@ -445,15 +459,15 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * claim the lock:
 	 *
 	 * n,0,0 -> 0,0,1 : lock, uncontended
-	 * *,0,0 -> *,0,1 : lock, contended
+	 * *,*,0 -> *,*,1 : lock, contended
 	 *
-	 * If the queue head is the only one in the queue (lock value == tail),
-	 * clear the tail code and grab the lock. Otherwise, we only need
-	 * to grab the lock.
+	 * If the queue head is the only one in the queue (lock value == tail)
+	 * and nobody is pending, clear the tail code and grab the lock.
+	 * Otherwise, we only need to grab the lock.
 	 */
 	for (;;) {
 		/* In the PV case we might already have _Q_LOCKED_VAL set */
-		if ((val & _Q_TAIL_MASK) != tail) {
+		if ((val & _Q_TAIL_MASK) != tail || (val & _Q_PENDING_MASK)) {
 			set_locked(lock);
 			break;
 		}
diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
index 1435ba7954c3d65c7cc5a9653b8f31b8abe04b30..854443f7b60b6aa8c2a1ab1c55b074216b99055f 100644
--- a/kernel/locking/qspinlock_paravirt.h
+++ b/kernel/locking/qspinlock_paravirt.h
@@ -89,11 +89,6 @@ static __always_inline void set_pending(struct qspinlock *lock)
 	WRITE_ONCE(lock->pending, 1);
 }
 
-static __always_inline void clear_pending(struct qspinlock *lock)
-{
-	WRITE_ONCE(lock->pending, 0);
-}
-
 /*
  * The pending bit check in pv_queued_spin_steal_lock() isn't a memory
  * barrier. Therefore, an atomic cmpxchg_acquire() is used to acquire the