diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index 9121595a8ebf..433da8a1a426 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -53,6 +53,9 @@ struct mutex {
 #if defined(CONFIG_DEBUG_MUTEXES) || defined(CONFIG_SMP)
 	struct task_struct	*owner;
 #endif
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+	void			*spin_mlock;	/* Spinner MCS lock */
+#endif
 #ifdef CONFIG_DEBUG_MUTEXES
 	const char 		*name;
 	void			*magic;
diff --git a/kernel/mutex.c b/kernel/mutex.c
index 70ebd855d9e8..1dbd4210baef 100644
--- a/kernel/mutex.c
+++ b/kernel/mutex.c
@@ -55,6 +55,9 @@ __mutex_init(struct mutex *lock, const char *name, struct lock_class_key *key)
 	spin_lock_init(&lock->wait_lock);
 	INIT_LIST_HEAD(&lock->wait_list);
 	mutex_clear_owner(lock);
+#ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+	lock->spin_mlock = NULL;
+#endif
 
 	debug_mutex_init(lock, name, key);
 }
@@ -107,6 +110,60 @@ EXPORT_SYMBOL(mutex_lock);
 #endif
 
 #ifdef CONFIG_MUTEX_SPIN_ON_OWNER
+/*
+ * In order to avoid a stampede of mutex spinners from acquiring the mutex
+ * more or less simultaneously, the spinners need to acquire a MCS lock
+ * first before spinning on the owner field.
+ *
+ * We don't inline mspin_lock() so that perf can correctly account for the
+ * time spent in this lock function.
+ */
+struct mspin_node {
+	struct mspin_node *next ;
+	int		  locked;	/* 1 if lock acquired */
+};
+#define	MLOCK(mutex)	((struct mspin_node **)&((mutex)->spin_mlock))
+
+static noinline
+void mspin_lock(struct mspin_node **lock, struct mspin_node *node)
+{
+	struct mspin_node *prev;
+
+	/* Init node */
+	node->locked = 0;
+	node->next   = NULL;
+
+	prev = xchg(lock, node);
+	if (likely(prev == NULL)) {
+		/* Lock acquired */
+		node->locked = 1;
+		return;
+	}
+	ACCESS_ONCE(prev->next) = node;
+	smp_wmb();
+	/* Wait until the lock holder passes the lock down */
+	while (!ACCESS_ONCE(node->locked))
+		arch_mutex_cpu_relax();
+}
+
+static void mspin_unlock(struct mspin_node **lock, struct mspin_node *node)
+{
+	struct mspin_node *next = ACCESS_ONCE(node->next);
+
+	if (likely(!next)) {
+		/*
+		 * Release the lock by setting it to NULL
+		 */
+		if (cmpxchg(lock, node, NULL) == node)
+			return;
+		/* Wait until the next pointer is set */
+		while (!(next = ACCESS_ONCE(node->next)))
+			arch_mutex_cpu_relax();
+	}
+	ACCESS_ONCE(next->locked) = 1;
+	smp_wmb();
+}
+
 /*
  * Mutex spinning code migrated from kernel/sched/core.c
  */
@@ -150,6 +207,24 @@ int mutex_spin_on_owner(struct mutex *lock, struct task_struct *owner)
 	 */
 	return lock->owner == NULL;
 }
+
+/*
+ * Initial check for entering the mutex spinning loop
+ */
+static inline int mutex_can_spin_on_owner(struct mutex *lock)
+{
+	int retval = 1;
+
+	rcu_read_lock();
+	if (lock->owner)
+		retval = lock->owner->on_cpu;
+	rcu_read_unlock();
+	/*
+	 * if lock->owner is not set, the mutex owner may have just acquired
+	 * it and not set the owner yet or the mutex has been released.
+	 */
+	return retval;
+}
 #endif
 
 static __used noinline void __sched __mutex_unlock_slowpath(atomic_t *lock_count);
@@ -215,26 +290,39 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 	 *
 	 * We can't do this for DEBUG_MUTEXES because that relies on wait_lock
 	 * to serialize everything.
+	 *
+	 * The mutex spinners are queued up using MCS lock so that only one
+	 * spinner can compete for the mutex. However, if mutex spinning isn't
+	 * going to happen, there is no point in going through the lock/unlock
+	 * overhead.
 	 */
+	if (!mutex_can_spin_on_owner(lock))
+		goto slowpath;
 
 	for (;;) {
 		struct task_struct *owner;
+		struct mspin_node  node;
 
 		/*
 		 * If there's an owner, wait for it to either
 		 * release the lock or go to sleep.
 		 */
+		mspin_lock(MLOCK(lock), &node);
 		owner = ACCESS_ONCE(lock->owner);
-		if (owner && !mutex_spin_on_owner(lock, owner))
+		if (owner && !mutex_spin_on_owner(lock, owner)) {
+			mspin_unlock(MLOCK(lock), &node);
 			break;
+		}
 
 		if ((atomic_read(&lock->count) == 1) &&
 		    (atomic_cmpxchg(&lock->count, 1, 0) == 1)) {
 			lock_acquired(&lock->dep_map, ip);
 			mutex_set_owner(lock);
+			mspin_unlock(MLOCK(lock), &node);
 			preempt_enable();
 			return 0;
 		}
+		mspin_unlock(MLOCK(lock), &node);
 
 		/*
 		 * When there's no owner, we might have preempted between the
@@ -253,6 +341,7 @@ __mutex_lock_common(struct mutex *lock, long state, unsigned int subclass,
 		 */
 		arch_mutex_cpu_relax();
 	}
+slowpath:
 #endif
 	spin_lock_mutex(&lock->wait_lock, flags);