diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index 3e70bed8a978e7ef3541d80ef860185c8a0f12de..055c60a057567ff655be0157c4756e4dd36dbccc 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -6,9 +6,30 @@
 #include <asm/cpufeature.h>
 #include <asm-generic/qspinlock_types.h>
 #include <asm/paravirt.h>
+#include <asm/rmwcc.h>
 
 #define _Q_PENDING_LOOPS	(1 << 9)
 
+#define queued_fetch_set_pending_acquire queued_fetch_set_pending_acquire
+
+static __always_inline bool __queued_RMW_btsl(struct qspinlock *lock)
+{
+	GEN_BINARY_RMWcc(LOCK_PREFIX "btsl", lock->val.counter,
+			 "I", _Q_PENDING_OFFSET, "%0", c);
+}
+
+static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
+{
+	u32 val = 0;
+
+	if (__queued_RMW_btsl(lock))
+		val |= _Q_PENDING_VAL;
+
+	val |= atomic_read(&lock->val) & ~_Q_PENDING_MASK;
+
+	return val;
+}
+
 #ifdef CONFIG_PARAVIRT_SPINLOCKS
 extern void native_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
 extern void __pv_init_lock_hash(void);
diff --git a/kernel/locking/qspinlock.c b/kernel/locking/qspinlock.c
index ec343276f975e92388cd0759f248903d04363da3..edd75e0c7d961f293164afe77a6ce5c932968dc7 100644
--- a/kernel/locking/qspinlock.c
+++ b/kernel/locking/qspinlock.c
@@ -231,6 +231,20 @@ static __always_inline u32 xchg_tail(struct qspinlock *lock, u32 tail)
 }
 #endif /* _Q_PENDING_BITS == 8 */
 
+/**
+ * queued_fetch_set_pending_acquire - fetch the whole lock value and set pending
+ * @lock : Pointer to queued spinlock structure
+ * Return: The previous lock value
+ *
+ * *,*,* -> *,1,*
+ */
+#ifndef queued_fetch_set_pending_acquire
+static __always_inline u32 queued_fetch_set_pending_acquire(struct qspinlock *lock)
+{
+	return atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+}
+#endif
+
 /**
  * set_locked - Set the lock bit and own the lock
  * @lock: Pointer to queued spinlock structure
@@ -329,7 +343,8 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * 0,0,0 -> 0,0,1 ; trylock
 	 * 0,0,1 -> 0,1,1 ; pending
 	 */
-	val = atomic_fetch_or_acquire(_Q_PENDING_VAL, &lock->val);
+	val = queued_fetch_set_pending_acquire(lock);
+
 	/*
 	 * If we observe any contention; undo and queue.
 	 */