diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 06ef89f6ccc2..feb8c3b0076b 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -757,7 +757,7 @@ static int uncore_pmu_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (!pmu->registered)
+	if (!uncore_pmu_available(pmu))
 		return -ENOENT;
 
 	/* Sampling not supported yet */
@@ -953,16 +953,18 @@ static int uncore_pmu_register(struct intel_uncore_pmu *pmu)
 
 	ret = perf_pmu_register(&pmu->pmu, pmu->name, -1);
 	if (!ret)
-		pmu->registered = true;
+		uncore_pmu_set_registered(pmu);
 	return ret;
 }
 
 static void uncore_pmu_unregister(struct intel_uncore_pmu *pmu)
 {
-	if (!pmu->registered)
+	if (!uncore_pmu_registered(pmu))
 		return;
 	perf_pmu_unregister(&pmu->pmu);
-	pmu->registered = false;
+
+	/* Keep PMU_BROKEN_BIT sticky. */
+	uncore_pmu_clear_registered(pmu);
 }
 
 static void uncore_free_boxes(struct intel_uncore_pmu *pmu)
@@ -1153,7 +1155,12 @@ static int uncore_box_setup(struct intel_uncore_pmu *pmu,
 {
 	int ret;
 
-	uncore_box_init(box);
+	if (uncore_pmu_broken(pmu))
+		return -ENODEV;
+
+	ret = uncore_box_init(box);
+	if (ret)
+		goto err;
 
 	/* First active box registers the pmu. */
 	if (atomic_inc_return(&pmu->activeboxes) > 1)
@@ -1167,6 +1174,16 @@ static int uncore_box_setup(struct intel_uncore_pmu *pmu,
 
 	return 0;
 err:
+	/*
+	 * If any box fails, mark the per-package PMU as broken regardless of
+	 * whether it was registered or not.
+	 *
+	 * Don't decrement refcnt to avoid other in-die CPUs from trying to set
+	 * up the PMU box again.
+	 *
+	 * Don't kfree box; MSR and MMIO boxes are freed at module exit only.
+	 */
+	uncore_pmu_set_broken(pmu);
 	uncore_box_exit(box);
 	return ret;
 }
@@ -1190,8 +1207,10 @@ static int uncore_pci_pmu_register(struct pci_dev *pdev,
 		return -EINVAL;
 
 	box = uncore_alloc_box(type, NUMA_NO_NODE);
-	if (!box)
+	if (!box) {
+		uncore_pmu_set_broken(pmu);
 		return -ENOMEM;
+	}
 
 	atomic_inc(&box->refcnt);
 	box->dieid = die;
@@ -1507,7 +1526,8 @@ static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 
 		if (old_cpu < 0) {
 			WARN_ON_ONCE(box->cpu != -1);
-			if (uncore_die_has_box(type, die, pmu->pmu_idx)) {
+			if (uncore_die_has_box(type, die, pmu->pmu_idx) &&
+			    !uncore_pmu_broken(pmu)) {
 				box->cpu = new_cpu;
 				cpumask_set_cpu(new_cpu, &pmu->cpu_mask);
 			}
@@ -1515,12 +1535,14 @@ static void uncore_change_type_ctx(struct intel_uncore_type *type, int old_cpu,
 		}
 
 		WARN_ON_ONCE(box->cpu != -1 && box->cpu != old_cpu);
-		box->cpu = -1;
 		cpumask_clear_cpu(old_cpu, &pmu->cpu_mask);
-		if (new_cpu < 0)
+		if (new_cpu < 0) {
+			box->cpu = -1;
 			continue;
+		}
 
-		if (!uncore_die_has_box(type, die, pmu->pmu_idx))
+		/* An inactive box doesn't need migration. */
+		if (box->cpu == -1)
 			continue;
 		uncore_pmu_cancel_hrtimer(box);
 		perf_pmu_migrate_context(&pmu->pmu, old_cpu, new_cpu);
@@ -1596,7 +1618,7 @@ static int allocate_boxes(struct intel_uncore_type **types,
 		type = *types;
 		pmu = type->pmus;
 		for (i = 0; i < type->num_boxes; i++, pmu++) {
-			if (pmu->boxes[die])
+			if (pmu->boxes[die] || uncore_pmu_broken(pmu))
 				continue;
 			box = uncore_alloc_box(type, cpu_to_node(cpu));
 			if (!box)
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index d732b87be0a9..0adb477d9708 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -146,13 +146,24 @@ struct intel_uncore_pmu {
 	struct pmu			pmu;
 	char				name[UNCORE_PMU_NAME_LEN];
 	int				pmu_idx;
-	bool				registered;
+	unsigned long			flags;
 	atomic_t			activeboxes;
 	cpumask_t			cpu_mask;
 	struct intel_uncore_type	*type;
 	struct intel_uncore_box		**boxes;
 };
 
+#define PMU_REGISTERED_BIT	0
+#define PMU_BROKEN_BIT		1
+
+#define uncore_pmu_registered(pmu)	test_bit(PMU_REGISTERED_BIT, &(pmu)->flags)
+#define uncore_pmu_broken(pmu)		test_bit(PMU_BROKEN_BIT, &(pmu)->flags)
+#define uncore_pmu_available(pmu)	(uncore_pmu_registered(pmu) &&  \
+					 !uncore_pmu_broken(pmu))
+#define uncore_pmu_set_registered(pmu)	set_bit(PMU_REGISTERED_BIT, &(pmu)->flags)
+#define uncore_pmu_set_broken(pmu)	set_bit(PMU_BROKEN_BIT, &(pmu)->flags)
+#define uncore_pmu_clear_registered(pmu) clear_bit(PMU_REGISTERED_BIT, &(pmu)->flags)
+
 struct intel_uncore_extra_reg {
 	raw_spinlock_t lock;
 	u64 config, config1, config2;
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index c5347920541c..055131c508ff 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -940,7 +940,7 @@ static int snb_uncore_imc_event_init(struct perf_event *event)
 
 	pmu = uncore_event_to_pmu(event);
 	/* no device found for this pmu */
-	if (!pmu->registered)
+	if (!uncore_pmu_available(pmu))
 		return -ENOENT;
 
 	/* Sampling not supported yet */