diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index 33e0f0a64c42..0384defc2a01 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -111,6 +111,11 @@ struct kvm_arch {
 	 */
 	bool return_nisv_io_abort_to_user;
 
+	/*
+	 * VM-wide PMU filter, implemented as a bitmap and big enough for
+	 * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+).
+	 */
+	unsigned long *pmu_filter;
 	unsigned int pmuver;
 };
 
diff --git a/arch/arm64/include/uapi/asm/kvm.h b/arch/arm64/include/uapi/asm/kvm.h
index ba85bb23f060..7b1511d6ce44 100644
--- a/arch/arm64/include/uapi/asm/kvm.h
+++ b/arch/arm64/include/uapi/asm/kvm.h
@@ -159,6 +159,21 @@ struct kvm_sync_regs {
 struct kvm_arch_memory_slot {
 };
 
+/*
+ * PMU filter structure. Describe a range of events with a particular
+ * action. To be used with KVM_ARM_VCPU_PMU_V3_FILTER.
+ */
+struct kvm_pmu_event_filter {
+	__u16	base_event;
+	__u16	nevents;
+
+#define KVM_PMU_EVENT_ALLOW	0
+#define KVM_PMU_EVENT_DENY	1
+
+	__u8	action;
+	__u8	pad[3];
+};
+
 /* for KVM_GET/SET_VCPU_EVENTS */
 struct kvm_vcpu_events {
 	struct {
@@ -329,6 +344,7 @@ struct kvm_vcpu_events {
 #define KVM_ARM_VCPU_PMU_V3_CTRL	0
 #define   KVM_ARM_VCPU_PMU_V3_IRQ	0
 #define   KVM_ARM_VCPU_PMU_V3_INIT	1
+#define   KVM_ARM_VCPU_PMU_V3_FILTER	2
 #define KVM_ARM_VCPU_TIMER_CTRL		1
 #define   KVM_ARM_VCPU_TIMER_IRQ_VTIMER		0
 #define   KVM_ARM_VCPU_TIMER_IRQ_PTIMER		1
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 46dc3d75cf13..427848ff6f20 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -145,6 +145,8 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 {
 	int i;
 
+	bitmap_free(kvm->arch.pmu_filter);
+
 	kvm_vgic_destroy(kvm);
 
 	for (i = 0; i < KVM_MAX_VCPUS; ++i) {
diff --git a/arch/arm64/kvm/pmu-emul.c b/arch/arm64/kvm/pmu-emul.c
index 10d3860a9c0a..8cd365968af1 100644
--- a/arch/arm64/kvm/pmu-emul.c
+++ b/arch/arm64/kvm/pmu-emul.c
@@ -593,11 +593,21 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	data = __vcpu_sys_reg(vcpu, reg);
 
 	kvm_pmu_stop_counter(vcpu, pmc);
-	eventsel = data & kvm_pmu_event_mask(vcpu->kvm);;
+	if (pmc->idx == ARMV8_PMU_CYCLE_IDX)
+		eventsel = ARMV8_PMUV3_PERFCTR_CPU_CYCLES;
+	else
+		eventsel = data & kvm_pmu_event_mask(vcpu->kvm);
 
-	/* Software increment event does't need to be backed by a perf event */
-	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR &&
-	    pmc->idx != ARMV8_PMU_CYCLE_IDX)
+	/* Software increment event doesn't need to be backed by a perf event */
+	if (eventsel == ARMV8_PMUV3_PERFCTR_SW_INCR)
+		return;
+
+	/*
+	 * If we have a filter in place and that the event isn't allowed, do
+	 * not install a perf event either.
+	 */
+	if (vcpu->kvm->arch.pmu_filter &&
+	    !test_bit(eventsel, vcpu->kvm->arch.pmu_filter))
 		return;
 
 	memset(&attr, 0, sizeof(struct perf_event_attr));
@@ -609,8 +619,7 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 	attr.exclude_kernel = data & ARMV8_PMU_EXCLUDE_EL1 ? 1 : 0;
 	attr.exclude_hv = 1; /* Don't count EL2 events */
 	attr.exclude_host = 1; /* Don't count host events */
-	attr.config = (pmc->idx == ARMV8_PMU_CYCLE_IDX) ?
-		ARMV8_PMUV3_PERFCTR_CPU_CYCLES : eventsel;
+	attr.config = eventsel;
 
 	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
@@ -889,6 +898,53 @@ int kvm_arm_pmu_v3_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 		vcpu->arch.pmu.irq_num = irq;
 		return 0;
 	}
+	case KVM_ARM_VCPU_PMU_V3_FILTER: {
+		struct kvm_pmu_event_filter __user *uaddr;
+		struct kvm_pmu_event_filter filter;
+		int nr_events;
+
+		nr_events = kvm_pmu_event_mask(vcpu->kvm) + 1;
+
+		uaddr = (struct kvm_pmu_event_filter __user *)(long)attr->addr;
+
+		if (copy_from_user(&filter, uaddr, sizeof(filter)))
+			return -EFAULT;
+
+		if (((u32)filter.base_event + filter.nevents) > nr_events ||
+		    (filter.action != KVM_PMU_EVENT_ALLOW &&
+		     filter.action != KVM_PMU_EVENT_DENY))
+			return -EINVAL;
+
+		mutex_lock(&vcpu->kvm->lock);
+
+		if (!vcpu->kvm->arch.pmu_filter) {
+			vcpu->kvm->arch.pmu_filter = bitmap_alloc(nr_events, GFP_KERNEL);
+			if (!vcpu->kvm->arch.pmu_filter) {
+				mutex_unlock(&vcpu->kvm->lock);
+				return -ENOMEM;
+			}
+
+			/*
+			 * The default depends on the first applied filter.
+			 * If it allows events, the default is to deny.
+			 * Conversely, if the first filter denies a set of
+			 * events, the default is to allow.
+			 */
+			if (filter.action == KVM_PMU_EVENT_ALLOW)
+				bitmap_zero(vcpu->kvm->arch.pmu_filter, nr_events);
+			else
+				bitmap_fill(vcpu->kvm->arch.pmu_filter, nr_events);
+		}
+
+		if (filter.action == KVM_PMU_EVENT_ALLOW)
+			bitmap_set(vcpu->kvm->arch.pmu_filter, filter.base_event, filter.nevents);
+		else
+			bitmap_clear(vcpu->kvm->arch.pmu_filter, filter.base_event, filter.nevents);
+
+		mutex_unlock(&vcpu->kvm->lock);
+
+		return 0;
+	}
 	case KVM_ARM_VCPU_PMU_V3_INIT:
 		return kvm_arm_pmu_v3_init(vcpu);
 	}
@@ -925,6 +981,7 @@ int kvm_arm_pmu_v3_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr)
 	switch (attr->attr) {
 	case KVM_ARM_VCPU_PMU_V3_IRQ:
 	case KVM_ARM_VCPU_PMU_V3_INIT:
+	case KVM_ARM_VCPU_PMU_V3_FILTER:
 		if (kvm_arm_support_pmu_v3() &&
 		    test_bit(KVM_ARM_VCPU_PMU_V3, vcpu->arch.features))
 			return 0;