diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 373dfd7d8a1dac70f110288835ad7c157cd002bf..4f73c5e8d6239139b925038154632751a086d4ef 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -760,18 +760,18 @@ static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
 					    &cpu_pmu->node);
 }
 
-struct arm_pmu *armpmu_alloc(void)
+static struct arm_pmu *__armpmu_alloc(gfp_t flags)
 {
 	struct arm_pmu *pmu;
 	int cpu;
 
-	pmu = kzalloc(sizeof(*pmu), GFP_KERNEL);
+	pmu = kzalloc(sizeof(*pmu), flags);
 	if (!pmu) {
 		pr_info("failed to allocate PMU device!\n");
 		goto out;
 	}
 
-	pmu->hw_events = alloc_percpu(struct pmu_hw_events);
+	pmu->hw_events = alloc_percpu_gfp(struct pmu_hw_events, flags);
 	if (!pmu->hw_events) {
 		pr_info("failed to allocate per-cpu PMU data.\n");
 		goto out_free_pmu;
@@ -817,6 +817,17 @@ struct arm_pmu *armpmu_alloc(void)
 	return NULL;
 }
 
+struct arm_pmu *armpmu_alloc(void)
+{
+	return __armpmu_alloc(GFP_KERNEL);
+}
+
+struct arm_pmu *armpmu_alloc_atomic(void)
+{
+	return __armpmu_alloc(GFP_ATOMIC);
+}
+
+
 void armpmu_free(struct arm_pmu *pmu)
 {
 	free_percpu(pmu->hw_events);
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 705f1a390e3123a2d305e0468cec8194d972ed39..30c5f2bbce59a3a040800b497ccb47f23db77c9b 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -127,7 +127,7 @@ static struct arm_pmu *arm_pmu_acpi_find_alloc_pmu(void)
 		return pmu;
 	}
 
-	pmu = armpmu_alloc();
+	pmu = armpmu_alloc_atomic();
 	if (!pmu) {
 		pr_warn("Unable to allocate PMU for CPU%d\n",
 			smp_processor_id());
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 899bc7ef08812e0ff9a2fae60aec99437c46d7d9..1f8bb83ef42fcbcdc1d2845771161209beae4380 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -157,6 +157,7 @@ static inline int arm_pmu_acpi_probe(armpmu_init_fn init_fn) { return 0; }
 
 /* Internal functions only for core arm_pmu code */
 struct arm_pmu *armpmu_alloc(void);
+struct arm_pmu *armpmu_alloc_atomic(void);
 void armpmu_free(struct arm_pmu *pmu);
 int armpmu_register(struct arm_pmu *pmu);
 int armpmu_request_irq(struct arm_pmu *armpmu, int cpu);