diff --git a/arch/s390/include/asm/mmu.h b/arch/s390/include/asm/mmu.h
index bea785d7f853..af85d6b12028 100644
--- a/arch/s390/include/asm/mmu.h
+++ b/arch/s390/include/asm/mmu.h
@@ -5,6 +5,7 @@
 #include <linux/errno.h>
 
 typedef struct {
+	spinlock_t lock;
 	cpumask_t cpu_attach_mask;
 	atomic_t flush_count;
 	unsigned int flush_mm;
@@ -25,6 +26,7 @@ typedef struct {
 } mm_context_t;
 
 #define INIT_MM_CONTEXT(name)						   \
+	.context.lock =	__SPIN_LOCK_UNLOCKED(name.context.lock),	   \
 	.context.pgtable_lock =						   \
 			__SPIN_LOCK_UNLOCKED(name.context.pgtable_lock),   \
 	.context.pgtable_list = LIST_HEAD_INIT(name.context.pgtable_list), \
diff --git a/arch/s390/include/asm/mmu_context.h b/arch/s390/include/asm/mmu_context.h
index dd359859a3e4..f65a708ac395 100644
--- a/arch/s390/include/asm/mmu_context.h
+++ b/arch/s390/include/asm/mmu_context.h
@@ -15,6 +15,7 @@
 static inline int init_new_context(struct task_struct *tsk,
 				   struct mm_struct *mm)
 {
+	spin_lock_init(&mm->context.lock);
 	spin_lock_init(&mm->context.pgtable_lock);
 	INIT_LIST_HEAD(&mm->context.pgtable_list);
 	spin_lock_init(&mm->context.gmap_lock);
@@ -111,8 +112,7 @@ static inline void finish_arch_post_lock_switch(void)
 		while (atomic_read(&mm->context.flush_count))
 			cpu_relax();
 		cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
-		if (mm->context.flush_mm)
-			__tlb_flush_mm(mm);
+		__tlb_flush_mm_lazy(mm);
 		preempt_enable();
 	}
 	set_fs(current->thread.mm_segment);
diff --git a/arch/s390/include/asm/tlbflush.h b/arch/s390/include/asm/tlbflush.h
index 043c2aab6622..eed927aeb08f 100644
--- a/arch/s390/include/asm/tlbflush.h
+++ b/arch/s390/include/asm/tlbflush.h
@@ -96,10 +96,12 @@ static inline void __tlb_flush_kernel(void)
 
 static inline void __tlb_flush_mm_lazy(struct mm_struct * mm)
 {
+	spin_lock(&mm->context.lock);
 	if (mm->context.flush_mm) {
-		__tlb_flush_mm(mm);
 		mm->context.flush_mm = 0;
+		__tlb_flush_mm(mm);
 	}
+	spin_unlock(&mm->context.lock);
 }
 
 /*