diff --git a/kernel/smp.c b/kernel/smp.c
index c64044d..e17e6344 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -395,22 +395,9 @@ int smp_call_function_any(const struct cpumask *mask,
 }
 EXPORT_SYMBOL_GPL(smp_call_function_any);
 
-/**
- * smp_call_function_many(): Run a function on a set of other CPUs.
- * @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. Preemption
- * must be disabled when calling this function.
- */
-void smp_call_function_many(const struct cpumask *mask,
-			    smp_call_func_t func, void *info, bool wait)
+static void smp_call_function_many_cond(const struct cpumask *mask,
+					smp_call_func_t func, void *info,
+					bool wait, smp_cond_func_t cond_func)
 {
 	struct call_function_data *cfd;
 	int cpu, next_cpu, this_cpu = smp_processor_id();
@@ -448,7 +435,8 @@ void smp_call_function_many(const struct cpumask *mask,
 
 	/* Fastpath: do that cpu by itself. */
 	if (next_cpu >= nr_cpu_ids) {
-		smp_call_function_single(cpu, func, info, wait);
+		if (!cond_func || (cond_func && cond_func(cpu, info)))
+			smp_call_function_single(cpu, func, info, wait);
 		return;
 	}
 
@@ -465,6 +453,9 @@ void smp_call_function_many(const struct cpumask *mask,
 	for_each_cpu(cpu, cfd->cpumask) {
 		call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu);
 
+		if (cond_func && !cond_func(cpu, info))
+			continue;
+
 		csd_lock(csd);
 		if (wait)
 			csd->flags |= CSD_FLAG_SYNCHRONOUS;
@@ -486,6 +477,26 @@ void smp_call_function_many(const struct cpumask *mask,
 		}
 	}
 }
+
+/**
+ * smp_call_function_many(): Run a function on a set of other CPUs.
+ * @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. Preemption
+ * must be disabled when calling this function.
+ */
+void smp_call_function_many(const struct cpumask *mask,
+			    smp_call_func_t func, void *info, bool wait)
+{
+	smp_call_function_many_cond(mask, func, info, wait, NULL);
+}
 EXPORT_SYMBOL(smp_call_function_many);
 
 /**
@@ -684,33 +695,17 @@ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
 			   void *info, bool wait, gfp_t gfp_flags,
 			   const struct cpumask *mask)
 {
-	cpumask_var_t cpus;
-	int cpu, ret;
+	int cpu = get_cpu();
 
-	might_sleep_if(gfpflags_allow_blocking(gfp_flags));
+	smp_call_function_many_cond(mask, func, info, wait, cond_func);
+	if (cpumask_test_cpu(cpu, mask) && cond_func(cpu, info)) {
+		unsigned long flags;
 
-	if (likely(zalloc_cpumask_var(&cpus, (gfp_flags|__GFP_NOWARN)))) {
-		preempt_disable();
-		for_each_cpu(cpu, mask)
-			if (cond_func(cpu, info))
-				__cpumask_set_cpu(cpu, cpus);
-		on_each_cpu_mask(cpus, func, info, wait);
-		preempt_enable();
-		free_cpumask_var(cpus);
-	} else {
-		/*
-		 * No free cpumask, bother. No matter, we'll
-		 * just have to IPI them one by one.
-		 */
-		preempt_disable();
-		for_each_cpu(cpu, mask)
-			if (cond_func(cpu, info)) {
-				ret = smp_call_function_single(cpu, func,
-								info, wait);
-				WARN_ON_ONCE(ret);
-			}
-		preempt_enable();
+		local_irq_save(flags);
+		func(info);
+		local_irq_restore(flags);
 	}
+	put_cpu();
 }
 EXPORT_SYMBOL(on_each_cpu_cond_mask);