diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 7dcb35285be7..02c5d2ce23bf 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -13,18 +13,6 @@
 #include <asm/smp_plat.h>
 #include <asm/tlbflush.h>
 
-static void on_each_cpu_mask(void (*func)(void *), void *info, int wait,
-	const struct cpumask *mask)
-{
-	preempt_disable();
-
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(smp_processor_id(), mask))
-		func(info);
-
-	preempt_enable();
-}
-
 /**********************************************************************/
 
 /*
@@ -87,7 +75,7 @@ void flush_tlb_all(void)
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	if (tlb_ops_need_broadcast())
-		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
+		on_each_cpu_mask(mm_cpumask(mm), ipi_flush_tlb_mm, mm, 1);
 	else
 		local_flush_tlb_mm(mm);
 }
@@ -98,7 +86,8 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		struct tlb_args ta;
 		ta.ta_vma = vma;
 		ta.ta_start = uaddr;
-		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_page,
+					&ta, 1);
 	} else
 		local_flush_tlb_page(vma, uaddr);
 }
@@ -121,7 +110,8 @@ void flush_tlb_range(struct vm_area_struct *vma,
 		ta.ta_vma = vma;
 		ta.ta_start = start;
 		ta.ta_end = end;
-		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
+		on_each_cpu_mask(mm_cpumask(vma->vm_mm), ipi_flush_tlb_range,
+					&ta, 1);
 	} else
 		local_flush_tlb_range(vma, start, end);
 }
diff --git a/arch/tile/include/asm/smp.h b/arch/tile/include/asm/smp.h
index 532124ae4b12..1aa759aeb5b3 100644
--- a/arch/tile/include/asm/smp.h
+++ b/arch/tile/include/asm/smp.h
@@ -43,10 +43,6 @@ void evaluate_message(int tag);
 /* Boot a secondary cpu */
 void online_secondary(void);
 
-/* Call a function on a specified set of CPUs (may include this one). */
-extern void on_each_cpu_mask(const struct cpumask *mask,
-			     void (*func)(void *), void *info, bool wait);
-
 /* Topology of the supervisor tile grid, and coordinates of boot processor */
 extern HV_Topology smp_topology;
 
@@ -91,9 +87,6 @@ void print_disabled_cpus(void);
 
 #else /* !CONFIG_SMP */
 
-#define on_each_cpu_mask(mask, func, info, wait)		\
-  do { if (cpumask_test_cpu(0, (mask))) func(info); } while (0)
-
 #define smp_master_cpu		0
 #define smp_height		1
 #define smp_width		1
diff --git a/arch/tile/kernel/smp.c b/arch/tile/kernel/smp.c
index c52224d5ed45..a44e103c5a63 100644
--- a/arch/tile/kernel/smp.c
+++ b/arch/tile/kernel/smp.c
@@ -87,25 +87,6 @@ void send_IPI_allbutself(int tag)
 	send_IPI_many(&mask, tag);
 }
 
-
-/*
- * Provide smp_call_function_mask, but also run function locally
- * if specified in the mask.
- */
-void on_each_cpu_mask(const struct cpumask *mask, void (*func)(void *),
-		      void *info, bool wait)
-{
-	int cpu = get_cpu();
-	smp_call_function_many(mask, func, info, wait);
-	if (cpumask_test_cpu(cpu, mask)) {
-		local_irq_disable();
-		func(info);
-		local_irq_enable();
-	}
-	put_cpu();
-}
-
-
 /*
  * Functions related to starting/stopping cpus.
  */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 8cc38d3bab0c..d0adb7898d54 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -101,6 +101,13 @@ static inline void call_function_init(void) { }
  */
 int on_each_cpu(smp_call_func_t func, void *info, int wait);
 
+/*
+ * Call a function on processors specified by mask, which might include
+ * the local one.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+		void *info, bool wait);
+
 /*
  * Mark the boot cpu "online" so that it can call console drivers in
  * printk() and can access its per-cpu storage.
@@ -132,6 +139,21 @@ static inline int up_smp_call_function(smp_call_func_t func, void *info)
 		local_irq_enable();		\
 		0;				\
 	})
+/*
+ * Note we still need to test the mask even for UP
+ * because we actually can get an empty mask from
+ * code that on SMP might call us without the local
+ * CPU in the mask.
+ */
+#define on_each_cpu_mask(mask, func, info, wait) \
+	do {						\
+		if (cpumask_test_cpu(0, (mask))) {	\
+			local_irq_disable();		\
+			(func)(info);			\
+			local_irq_enable();		\
+		}					\
+	} while (0)
+
 static inline void smp_send_reschedule(int cpu) { }
 #define num_booting_cpus()			1
 #define smp_prepare_boot_cpu()			do {} while (0)
diff --git a/kernel/smp.c b/kernel/smp.c
index db197d60489b..a081e6ce0e0a 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -701,3 +701,32 @@ int on_each_cpu(void (*func) (void *info), void *info, int wait)
 	return ret;
 }
 EXPORT_SYMBOL(on_each_cpu);
+
+/**
+ * on_each_cpu_mask(): Run a function on processors specified by
+ * cpumask, which may include the local processor.
+ * @mask: The set of cpus to run on (only runs on online subset).
+ * @func: The function to run. This must be fast and non-blocking.
+ * @info: An arbitrary pointer to pass to the function.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
+ *
+ * If @wait is true, then returns once @func has returned.
+ *
+ * You must not call this function with disabled interrupts or
+ * from a hardware interrupt handler or from a bottom half handler.
+ */
+void on_each_cpu_mask(const struct cpumask *mask, smp_call_func_t func,
+			void *info, bool wait)
+{
+	int cpu = get_cpu();
+
+	smp_call_function_many(mask, func, info, wait);
+	if (cpumask_test_cpu(cpu, mask)) {
+		local_irq_disable();
+		func(info);
+		local_irq_enable();
+	}
+	put_cpu();
+}
+EXPORT_SYMBOL(on_each_cpu_mask);