diff --git a/arch/powerpc/kernel/hw_breakpoint.c b/arch/powerpc/kernel/hw_breakpoint.c
index 9781c69eae5767adc9fdde54232e4df1329e7b92..03d089b3ed726faeb69d3121e27191ed834899bf 100644
--- a/arch/powerpc/kernel/hw_breakpoint.c
+++ b/arch/powerpc/kernel/hw_breakpoint.c
@@ -275,7 +275,7 @@ int hw_breakpoint_handler(struct die_args *args)
 	if (!stepped) {
 		WARN(1, "Unable to handle hardware breakpoint. Breakpoint at "
 			"0x%lx will be disabled.", info->address);
-		perf_event_disable(bp);
+		perf_event_disable_inatomic(bp);
 		goto out;
 	}
 	/*
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index eab0915f59951f2729d212bb96af76785360eff0..a74a2dbc01801a1ccc3c041a6037214c369957bb 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3607,10 +3607,14 @@ __init int intel_pmu_init(void)
 
 	/*
 	 * Quirk: v2 perfmon does not report fixed-purpose events, so
-	 * assume at least 3 events:
+	 * assume at least 3 events, when not running in a hypervisor:
 	 */
-	if (version > 1)
-		x86_pmu.num_counters_fixed = max((int)edx.split.num_counters_fixed, 3);
+	if (version > 1) {
+		int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
+
+		x86_pmu.num_counters_fixed =
+			max((int)edx.split.num_counters_fixed, assume);
+	}
 
 	if (boot_cpu_has(X86_FEATURE_PDCM)) {
 		u64 capabilities;
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 3ca87b5a8677608c86ac8d748b59ead0d160f580..4f5ac726335f899a4faefd01a41aac241b9160be 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -48,7 +48,8 @@
  *			       Scope: Core
  *	MSR_CORE_C6_RESIDENCY: CORE C6 Residency Counter
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ *						SKL,KNL
  *			       Scope: Core
  *	MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
  *			       perf code: 0x03
@@ -56,15 +57,16 @@
  *			       Scope: Core
  *	MSR_PKG_C2_RESIDENCY:  Package C2 Residency Counter.
  *			       perf code: 0x00
- *			       Available model: SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SNB,IVB,HSW,BDW,SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C3_RESIDENCY:  Package C3 Residency Counter.
  *			       perf code: 0x01
- *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C6_RESIDENCY:  Package C6 Residency Counter.
  *			       perf code: 0x02
- *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,SKL
+ *			       Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW
+ *						SKL,KNL
  *			       Scope: Package (physical package)
  *	MSR_PKG_C7_RESIDENCY:  Package C7 Residency Counter.
  *			       perf code: 0x03
@@ -118,6 +120,7 @@ struct cstate_model {
 
 /* Quirk flags */
 #define SLM_PKG_C6_USE_C7_MSR	(1UL << 0)
+#define KNL_CORE_C6_MSR		(1UL << 1)
 
 struct perf_cstate_msr {
 	u64	msr;
@@ -488,6 +491,18 @@ static const struct cstate_model slm_cstates __initconst = {
 	.quirks			= SLM_PKG_C6_USE_C7_MSR,
 };
 
+
+static const struct cstate_model knl_cstates __initconst = {
+	.core_events		= BIT(PERF_CSTATE_CORE_C6_RES),
+
+	.pkg_events		= BIT(PERF_CSTATE_PKG_C2_RES) |
+				  BIT(PERF_CSTATE_PKG_C3_RES) |
+				  BIT(PERF_CSTATE_PKG_C6_RES),
+	.quirks			= KNL_CORE_C6_MSR,
+};
+
+
+
 #define X86_CSTATES_MODEL(model, states)				\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long) &(states) }
 
@@ -523,6 +538,8 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
 
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_MOBILE,  snb_cstates),
 	X86_CSTATES_MODEL(INTEL_FAM6_SKYLAKE_DESKTOP, snb_cstates),
+
+	X86_CSTATES_MODEL(INTEL_FAM6_XEON_PHI_KNL, knl_cstates),
 	{ },
 };
 MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
@@ -558,6 +575,11 @@ static int __init cstate_probe(const struct cstate_model *cm)
 	if (cm->quirks & SLM_PKG_C6_USE_C7_MSR)
 		pkg_msr[PERF_CSTATE_PKG_C6_RES].msr = MSR_PKG_C7_RESIDENCY;
 
+	/* KNL has different MSR for CORE C6 */
+	if (cm->quirks & KNL_CORE_C6_MSR)
+		pkg_msr[PERF_CSTATE_CORE_C6_RES].msr = MSR_KNL_CORE_C6_RESIDENCY;
+
+
 	has_cstate_core = cstate_probe_msr(cm->core_events,
 					   PERF_CSTATE_CORE_EVENT_MAX,
 					   core_msr, core_events_attrs);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 060d0ede88df6dfc34fbfcd1e60629d8dce5373d..4741ecdb981743151b70afff63b10740dfaa4132 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1257,6 +1257,7 @@ extern u64 perf_swevent_set_period(struct perf_event *event);
 extern void perf_event_enable(struct perf_event *event);
 extern void perf_event_disable(struct perf_event *event);
 extern void perf_event_disable_local(struct perf_event *event);
+extern void perf_event_disable_inatomic(struct perf_event *event);
 extern void perf_event_task_tick(void);
 #else /* !CONFIG_PERF_EVENTS: */
 static inline void *
diff --git a/kernel/events/core.c b/kernel/events/core.c
index c6e47e97b33fdb7b0bbabf91016d51bc76d4b63c..0e292132efacaaa09fa4960b92315c9c967b0e82 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1960,6 +1960,12 @@ void perf_event_disable(struct perf_event *event)
 }
 EXPORT_SYMBOL_GPL(perf_event_disable);
 
+void perf_event_disable_inatomic(struct perf_event *event)
+{
+	event->pending_disable = 1;
+	irq_work_queue(&event->pending);
+}
+
 static void perf_set_shadow_time(struct perf_event *event,
 				 struct perf_event_context *ctx,
 				 u64 tstamp)
@@ -7075,8 +7081,8 @@ static int __perf_event_overflow(struct perf_event *event,
 	if (events && atomic_dec_and_test(&event->event_limit)) {
 		ret = 1;
 		event->pending_kill = POLL_HUP;
-		event->pending_disable = 1;
-		irq_work_queue(&event->pending);
+
+		perf_event_disable_inatomic(event);
 	}
 
 	READ_ONCE(event->overflow_handler)(event, data, regs);
@@ -8855,7 +8861,10 @@ EXPORT_SYMBOL_GPL(perf_pmu_register);
 
 void perf_pmu_unregister(struct pmu *pmu)
 {
+	int remove_device;
+
 	mutex_lock(&pmus_lock);
+	remove_device = pmu_bus_running;
 	list_del_rcu(&pmu->entry);
 	mutex_unlock(&pmus_lock);
 
@@ -8869,10 +8878,12 @@ void perf_pmu_unregister(struct pmu *pmu)
 	free_percpu(pmu->pmu_disable_count);
 	if (pmu->type >= PERF_TYPE_MAX)
 		idr_remove(&pmu_idr, pmu->type);
-	if (pmu->nr_addr_filters)
-		device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
-	device_del(pmu->dev);
-	put_device(pmu->dev);
+	if (remove_device) {
+		if (pmu->nr_addr_filters)
+			device_remove_file(pmu->dev, &dev_attr_nr_addr_filters);
+		device_del(pmu->dev);
+		put_device(pmu->dev);
+	}
 	free_pmu_context(pmu);
 }
 EXPORT_SYMBOL_GPL(perf_pmu_unregister);