Merge branch 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull smp hotplug updates from Thomas Gleixner:
 "This is the next part of the hotplug rework.

   - Convert all notifiers with a priority assigned

   - Convert all CPU_STARTING/DYING notifiers

     The final removal of the STARTING/DYING infrastructure will happen
     when the merge window closes.

  Another 700 hundred line of unpenetrable maze gone :)"

* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (70 commits)
  timers/core: Correct callback order during CPU hot plug
  leds/trigger/cpu: Move from CPU_STARTING to ONLINE level
  powerpc/numa: Convert to hotplug state machine
  arm/perf: Fix hotplug state machine conversion
  irqchip/armada: Avoid unused function warnings
  ARC/time: Convert to hotplug state machine
  clocksource/atlas7: Convert to hotplug state machine
  clocksource/armada-370-xp: Convert to hotplug state machine
  clocksource/exynos_mct: Convert to hotplug state machine
  clocksource/arm_global_timer: Convert to hotplug state machine
  rcu: Convert rcutree to hotplug state machine
  KVM/arm/arm64/vgic-new: Convert to hotplug state machine
  smp/cfd: Convert core to hotplug state machine
  x86/x2apic: Convert to CPU hotplug state machine
  profile: Convert to hotplug state machine
  timers/core: Convert to hotplug state machine
  hrtimer: Convert to hotplug state machine
  x86/tboot: Convert to hotplug state machine
  arm64/armv8 deprecated: Convert to hotplug state machine
  hwtracing/coresight-etm4x: Convert to hotplug state machine
  ...

16 files changed, 340 insertions, 594 deletions

diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 3329844e3c43..f840766659a8 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -331,15 +331,9 @@ static void vgetcpu_cpu_init(void *arg)
 	write_gdt_entry(get_cpu_gdt_table(cpu), GDT_ENTRY_PER_CPU, &d, DESCTYPE_S);
 }
 
-static int
-vgetcpu_cpu_notifier(struct notifier_block *n, unsigned long action, void *arg)
+static int vgetcpu_online(unsigned int cpu)
 {
-	long cpu = (long)arg;
-
-	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN)
-		smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
-
-	return NOTIFY_DONE;
+	return smp_call_function_single(cpu, vgetcpu_cpu_init, NULL, 1);
 }
 
 static int __init init_vdso(void)
@@ -350,15 +344,9 @@ static int __init init_vdso(void)
 	init_vdso_image(&vdso_image_x32);
 #endif
 
-	cpu_notifier_register_begin();
-
-	on_each_cpu(vgetcpu_cpu_init, NULL, 1);
 	/* notifier priority > KVM */
-	__hotcpu_notifier(vgetcpu_cpu_notifier, 30);
-
-	cpu_notifier_register_done();
-
-	return 0;
+	return cpuhp_setup_state(CPUHP_AP_X86_VDSO_VMA_ONLINE,
+				 "AP_X86_VDSO_VMA_ONLINE", vgetcpu_online, NULL);
 }
 subsys_initcall(init_vdso);
 #endif /* CONFIG_X86_64 */
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index bd3e8421b57c..e07a22bb9308 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -370,13 +370,13 @@ static int amd_pmu_cpu_prepare(int cpu)
 	WARN_ON_ONCE(cpuc->amd_nb);
 
 	if (!x86_pmu.amd_nb_constraints)
-		return NOTIFY_OK;
+		return 0;
 
 	cpuc->amd_nb = amd_alloc_nb(cpu);
 	if (!cpuc->amd_nb)
-		return NOTIFY_BAD;
+		return -ENOMEM;
 
-	return NOTIFY_OK;
+	return 0;
 }
 
 static void amd_pmu_cpu_starting(int cpu)
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 72dea2f40fc4..155ea5324ae0 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -725,13 +725,10 @@ static __init int perf_ibs_pmu_init(struct perf_ibs *perf_ibs, char *name)
 	return ret;
 }
 
-static __init int perf_event_ibs_init(void)
+static __init void perf_event_ibs_init(void)
 {
 	struct attribute **attr = ibs_op_format_attrs;
 
-	if (!ibs_caps)
-		return -ENODEV;	/* ibs not supported by the cpu */
-
 	perf_ibs_pmu_init(&perf_ibs_fetch, "ibs_fetch");
 
 	if (ibs_caps & IBS_CAPS_OPCNT) {
@@ -742,13 +739,11 @@ static __init int perf_event_ibs_init(void)
 
 	register_nmi_handler(NMI_LOCAL, perf_ibs_nmi_handler, 0, "perf_ibs");
 	pr_info("perf: AMD IBS detected (0x%08x)\n", ibs_caps);
-
-	return 0;
 }
 
 #else /* defined(CONFIG_PERF_EVENTS) && defined(CONFIG_CPU_SUP_AMD) */
 
-static __init int perf_event_ibs_init(void) { return 0; }
+static __init void perf_event_ibs_init(void) { }
 
 #endif
 
@@ -925,7 +920,7 @@ static inline int get_ibs_lvt_offset(void)
 	return val & IBSCTL_LVT_OFFSET_MASK;
 }
 
-static void setup_APIC_ibs(void *dummy)
+static void setup_APIC_ibs(void)
 {
 	int offset;
 
@@ -940,7 +935,7 @@ failed:
 		smp_processor_id());
 }
 
-static void clear_APIC_ibs(void *dummy)
+static void clear_APIC_ibs(void)
 {
 	int offset;
 
@@ -949,18 +944,24 @@ static void clear_APIC_ibs(void *dummy)
 		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
 }
 
+static int x86_pmu_amd_ibs_starting_cpu(unsigned int cpu)
+{
+	setup_APIC_ibs();
+	return 0;
+}
+
 #ifdef CONFIG_PM
 
 static int perf_ibs_suspend(void)
 {
-	clear_APIC_ibs(NULL);
+	clear_APIC_ibs();
 	return 0;
 }
 
 static void perf_ibs_resume(void)
 {
 	ibs_eilvt_setup();
-	setup_APIC_ibs(NULL);
+	setup_APIC_ibs();
 }
 
 static struct syscore_ops perf_ibs_syscore_ops = {
@@ -979,27 +980,15 @@ static inline void perf_ibs_pm_init(void) { }
 
 #endif
 
-static int
-perf_ibs_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+static int x86_pmu_amd_ibs_dying_cpu(unsigned int cpu)
 {
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
-		setup_APIC_ibs(NULL);
-		break;
-	case CPU_DYING:
-		clear_APIC_ibs(NULL);
-		break;
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
+	clear_APIC_ibs();
+	return 0;
 }
 
 static __init int amd_ibs_init(void)
 {
 	u32 caps;
-	int ret = -EINVAL;
 
 	caps = __get_ibs_caps();
 	if (!caps)
@@ -1008,22 +997,25 @@ static __init int amd_ibs_init(void)
 	ibs_eilvt_setup();
 
 	if (!ibs_eilvt_valid())
-		goto out;
+		return -EINVAL;
 
 	perf_ibs_pm_init();
-	cpu_notifier_register_begin();
+
 	ibs_caps = caps;
 	/* make ibs_caps visible to other cpus: */
 	smp_mb();
-	smp_call_function(setup_APIC_ibs, NULL, 1);
-	__perf_cpu_notifier(perf_ibs_cpu_notifier);
-	cpu_notifier_register_done();
+	/*
+	 * x86_pmu_amd_ibs_starting_cpu will be called from core on
+	 * all online cpus.
+	 */
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
+			  "AP_PERF_X86_AMD_IBS_STARTING",
+			  x86_pmu_amd_ibs_starting_cpu,
+			  x86_pmu_amd_ibs_dying_cpu);
 
-	ret = perf_event_ibs_init();
-out:
-	if (ret)
-		pr_err("Failed to setup IBS, %d\n", ret);
-	return ret;
+	perf_event_ibs_init();
+
+	return 0;
 }
 
 /* Since we need the pci subsystem to init ibs we can't do this earlier: */
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 55a3529dbf12..9842270ed2f2 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -228,12 +228,12 @@ static struct pmu pmu_class = {
 	.read		= pmu_event_read,
 };
 
-static void power_cpu_exit(int cpu)
+static int power_cpu_exit(unsigned int cpu)
 {
 	int target;
 
 	if (!cpumask_test_and_clear_cpu(cpu, &cpu_mask))
-		return;
+		return 0;
 
 	/*
 	 * Find a new CPU on the same compute unit, if was set in cpumask
@@ -245,9 +245,10 @@ static void power_cpu_exit(int cpu)
 		cpumask_set_cpu(target, &cpu_mask);
 		perf_pmu_migrate_context(&pmu_class, cpu, target);
 	}
+	return 0;
 }
 
-static void power_cpu_init(int cpu)
+static int power_cpu_init(unsigned int cpu)
 {
 	int target;
 
@@ -255,7 +256,7 @@ static void power_cpu_init(int cpu)
 	 * 1) If any CPU is set at cpu_mask in the same compute unit, do
 	 * nothing.
 	 * 2) If no CPU is set at cpu_mask in the same compute unit,
-	 * set current STARTING CPU.
+	 * set current ONLINE CPU.
 	 *
 	 * Note: if there is a CPU aside of the new one already in the
 	 * sibling mask, then it is also in cpu_mask.
@@ -263,33 +264,9 @@ static void power_cpu_init(int cpu)
 	target = cpumask_any_but(topology_sibling_cpumask(cpu), cpu);
 	if (target >= nr_cpumask_bits)
 		cpumask_set_cpu(cpu, &cpu_mask);
+	return 0;
 }
 
-static int
-power_cpu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DOWN_FAILED:
-	case CPU_STARTING:
-		power_cpu_init(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		power_cpu_exit(cpu);
-		break;
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block power_cpu_notifier_nb = {
-	.notifier_call = power_cpu_notifier,
-	.priority = CPU_PRI_PERF,
-};
-
 static const struct x86_cpu_id cpu_match[] = {
 	{ .vendor = X86_VENDOR_AMD, .family = 0x15 },
 	{},
@@ -297,7 +274,7 @@ static const struct x86_cpu_id cpu_match[] = {
 
 static int __init amd_power_pmu_init(void)
 {
-	int cpu, target, ret;
+	int ret;
 
 	if (!x86_match_cpu(cpu_match))
 		return 0;
@@ -312,38 +289,25 @@ static int __init amd_power_pmu_init(void)
 		return -ENODEV;
 	}
 
-	cpu_notifier_register_begin();
 
-	/* Choose one online core of each compute unit. */
-	for_each_online_cpu(cpu) {
-		target = cpumask_first(topology_sibling_cpumask(cpu));
-		if (!cpumask_test_cpu(target, &cpu_mask))
-			cpumask_set_cpu(target, &cpu_mask);
-	}
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
+			  "AP_PERF_X86_AMD_POWER_ONLINE",
+			  power_cpu_init, power_cpu_exit);
 
 	ret = perf_pmu_register(&pmu_class, "power", -1);
 	if (WARN_ON(ret)) {
 		pr_warn("AMD Power PMU registration failed\n");
-		goto out;
+		return ret;
 	}
 
-	__register_cpu_notifier(&power_cpu_notifier_nb);
-
 	pr_info("AMD Power PMU detected\n");
-
-out:
-	cpu_notifier_register_done();
-
 	return ret;
 }
 module_init(amd_power_pmu_init);
 
 static void __exit amd_power_pmu_exit(void)
 {
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&power_cpu_notifier_nb);
-	cpu_notifier_register_done();
-
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_AMD_POWER_ONLINE);
 	perf_pmu_unregister(&pmu_class);
 }
 module_exit(amd_power_pmu_exit);
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 98ac57381bf9..e6131d4454e6 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -358,7 +358,7 @@ amd_uncore_find_online_sibling(struct amd_uncore *this,
 	return this;
 }
 
-static void amd_uncore_cpu_starting(unsigned int cpu)
+static int amd_uncore_cpu_starting(unsigned int cpu)
 {
 	unsigned int eax, ebx, ecx, edx;
 	struct amd_uncore *uncore;
@@ -384,6 +384,8 @@ static void amd_uncore_cpu_starting(unsigned int cpu)
 		uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2);
 		*per_cpu_ptr(amd_uncore_l2, cpu) = uncore;
 	}
+
+	return 0;
 }
 
 static void uncore_online(unsigned int cpu,
@@ -398,13 +400,15 @@ static void uncore_online(unsigned int cpu,
 		cpumask_set_cpu(cpu, uncore->active_mask);
 }
 
-static void amd_uncore_cpu_online(unsigned int cpu)
+static int amd_uncore_cpu_online(unsigned int cpu)
 {
 	if (amd_uncore_nb)
 		uncore_online(cpu, amd_uncore_nb);
 
 	if (amd_uncore_l2)
 		uncore_online(cpu, amd_uncore_l2);
+
+	return 0;
 }
 
 static void uncore_down_prepare(unsigned int cpu,
@@ -433,13 +437,15 @@ static void uncore_down_prepare(unsigned int cpu,
 	}
 }
 
-static void amd_uncore_cpu_down_prepare(unsigned int cpu)
+static int amd_uncore_cpu_down_prepare(unsigned int cpu)
 {
 	if (amd_uncore_nb)
 		uncore_down_prepare(cpu, amd_uncore_nb);
 
 	if (amd_uncore_l2)
 		uncore_down_prepare(cpu, amd_uncore_l2);
+
+	return 0;
 }
 
 static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
@@ -454,74 +460,19 @@ static void uncore_dead(unsigned int cpu, struct amd_uncore * __percpu *uncores)
 	*per_cpu_ptr(uncores, cpu) = NULL;
 }
 
-static void amd_uncore_cpu_dead(unsigned int cpu)
+static int amd_uncore_cpu_dead(unsigned int cpu)
 {
 	if (amd_uncore_nb)
 		uncore_dead(cpu, amd_uncore_nb);
 
 	if (amd_uncore_l2)
 		uncore_dead(cpu, amd_uncore_l2);
-}
-
-static int
-amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action,
-			void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		if (amd_uncore_cpu_up_prepare(cpu))
-			return notifier_from_errno(-ENOMEM);
-		break;
-
-	case CPU_STARTING:
-		amd_uncore_cpu_starting(cpu);
-		break;
-
-	case CPU_ONLINE:
-		amd_uncore_cpu_online(cpu);
-		break;
-
-	case CPU_DOWN_PREPARE:
-		amd_uncore_cpu_down_prepare(cpu);
-		break;
-
-	case CPU_UP_CANCELED:
-	case CPU_DEAD:
-		amd_uncore_cpu_dead(cpu);
-		break;
-
-	default:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block amd_uncore_cpu_notifier_block = {
-	.notifier_call	= amd_uncore_cpu_notifier,
-	.priority	= CPU_PRI_PERF + 1,
-};
-
-static void __init init_cpu_already_online(void *dummy)
-{
-	unsigned int cpu = smp_processor_id();
-
-	amd_uncore_cpu_starting(cpu);
-	amd_uncore_cpu_online(cpu);
-}
 
-static void cleanup_cpu_online(void *dummy)
-{
-	unsigned int cpu = smp_processor_id();
-
-	amd_uncore_cpu_dead(cpu);
+	return 0;
 }
 
 static int __init amd_uncore_init(void)
 {
-	unsigned int cpu, cpu2;
 	int ret = -ENODEV;
 
 	if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD)
@@ -558,38 +509,29 @@ static int __init amd_uncore_init(void)
 		ret = 0;
 	}
 
-	if (ret)
-		goto fail_nodev;
-
-	cpu_notifier_register_begin();
-
-	/* init cpus already online before registering for hotplug notifier */
-	for_each_online_cpu(cpu) {
-		ret = amd_uncore_cpu_up_prepare(cpu);
-		if (ret)
-			goto fail_online;
-		smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
-	}
-
-	__register_cpu_notifier(&amd_uncore_cpu_notifier_block);
-	cpu_notifier_register_done();
-
+	/*
+	 * Install callbacks. Core will call them for each online cpu.
+	 */
+	if (cpuhp_setup_state(CPUHP_PERF_X86_AMD_UNCORE_PREP,
+			      "PERF_X86_AMD_UNCORE_PREP",
+			      amd_uncore_cpu_up_prepare, amd_uncore_cpu_dead))
+		goto fail_l2;
+
+	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
+			      "AP_PERF_X86_AMD_UNCORE_STARTING",
+			      amd_uncore_cpu_starting, NULL))
+		goto fail_prep;
+	if (cpuhp_setup_state(CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
+			      "AP_PERF_X86_AMD_UNCORE_ONLINE",
+			      amd_uncore_cpu_online,
+			      amd_uncore_cpu_down_prepare))
+		goto fail_start;
 	return 0;
 
-
-fail_online:
-	for_each_online_cpu(cpu2) {
-		if (cpu2 == cpu)
-			break;
-		smp_call_function_single(cpu, cleanup_cpu_online, NULL, 1);
-	}
-	cpu_notifier_register_done();
-
-	/* amd_uncore_nb/l2 should have been freed by cleanup_cpu_online */
-	amd_uncore_nb = amd_uncore_l2 = NULL;
-
-	if (boot_cpu_has(X86_FEATURE_PERFCTR_L2))
-		perf_pmu_unregister(&amd_l2_pmu);
+fail_start:
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING);
+fail_prep:
+	cpuhp_remove_state(CPUHP_PERF_X86_AMD_UNCORE_PREP);
 fail_l2:
 	if (boot_cpu_has(X86_FEATURE_PERFCTR_NB))
 		perf_pmu_unregister(&amd_nb_pmu);
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index dfebbde2a4cc..c17f0de5fd39 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1477,49 +1477,49 @@ NOKPROBE_SYMBOL(perf_event_nmi_handler);
 struct event_constraint emptyconstraint;
 struct event_constraint unconstrained;
 
-static int
-x86_pmu_notifier(struct notifier_block *self, unsigned long action, void *hcpu)
+static int x86_pmu_prepare_cpu(unsigned int cpu)
 {
-	unsigned int cpu = (long)hcpu;
 	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
-	int i, ret = NOTIFY_OK;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		for (i = 0 ; i < X86_PERF_KFREE_MAX; i++)
-			cpuc->kfree_on_online[i] = NULL;
-		if (x86_pmu.cpu_prepare)
-			ret = x86_pmu.cpu_prepare(cpu);
-		break;
-
-	case CPU_STARTING:
-		if (x86_pmu.cpu_starting)
-			x86_pmu.cpu_starting(cpu);
-		break;
+	int i;
 
-	case CPU_ONLINE:
-		for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) {
-			kfree(cpuc->kfree_on_online[i]);
-			cpuc->kfree_on_online[i] = NULL;
-		}
-		break;
+	for (i = 0 ; i < X86_PERF_KFREE_MAX; i++)
+		cpuc->kfree_on_online[i] = NULL;
+	if (x86_pmu.cpu_prepare)
+		return x86_pmu.cpu_prepare(cpu);
+	return 0;
+}
 
-	case CPU_DYING:
-		if (x86_pmu.cpu_dying)
-			x86_pmu.cpu_dying(cpu);
-		break;
+static int x86_pmu_dead_cpu(unsigned int cpu)
+{
+	if (x86_pmu.cpu_dead)
+		x86_pmu.cpu_dead(cpu);
+	return 0;
+}
 
-	case CPU_UP_CANCELED:
-	case CPU_DEAD:
-		if (x86_pmu.cpu_dead)
-			x86_pmu.cpu_dead(cpu);
-		break;
+static int x86_pmu_online_cpu(unsigned int cpu)
+{
+	struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+	int i;
 
-	default:
-		break;
+	for (i = 0 ; i < X86_PERF_KFREE_MAX; i++) {
+		kfree(cpuc->kfree_on_online[i]);
+		cpuc->kfree_on_online[i] = NULL;
 	}
+	return 0;
+}
 
-	return ret;
+static int x86_pmu_starting_cpu(unsigned int cpu)
+{
+	if (x86_pmu.cpu_starting)
+		x86_pmu.cpu_starting(cpu);
+	return 0;
+}
+
+static int x86_pmu_dying_cpu(unsigned int cpu)
+{
+	if (x86_pmu.cpu_dying)
+		x86_pmu.cpu_dying(cpu);
+	return 0;
 }
 
 static void __init pmu_check_apic(void)
@@ -1787,10 +1787,39 @@ static int __init init_hw_perf_events(void)
 	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
-	perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
-	perf_cpu_notifier(x86_pmu_notifier);
+	/*
+	 * Install callbacks. Core will call them for each online
+	 * cpu.
+	 */
+	err = cpuhp_setup_state(CPUHP_PERF_X86_PREPARE, "PERF_X86_PREPARE",
+				x86_pmu_prepare_cpu, x86_pmu_dead_cpu);
+	if (err)
+		return err;
+
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_STARTING,
+				"AP_PERF_X86_STARTING", x86_pmu_starting_cpu,
+				x86_pmu_dying_cpu);
+	if (err)
+		goto out;
+
+	err = cpuhp_setup_state(CPUHP_AP_PERF_X86_ONLINE, "AP_PERF_X86_ONLINE",
+				x86_pmu_online_cpu, NULL);
+	if (err)
+		goto out1;
+
+	err = perf_pmu_register(&pmu, "cpu", PERF_TYPE_RAW);
+	if (err)
+		goto out2;
 
 	return 0;
+
+out2:
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_ONLINE);
+out1:
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_STARTING);
+out:
+	cpuhp_remove_state(CPUHP_PERF_X86_PREPARE);
+	return err;
 }
 early_initcall(init_hw_perf_events);
 
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 0974ba11e954..2cbde2f449aa 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3109,7 +3109,7 @@ static int intel_pmu_cpu_prepare(int cpu)
 		cpuc->excl_thread_id = 0;
 	}
 
-	return NOTIFY_OK;
+	return 0;
 
 err_constraint_list:
 	kfree(cpuc->constraint_list);
@@ -3120,7 +3120,7 @@ err_shared_regs:
 	cpuc->shared_regs = NULL;
 
 err:
-	return NOTIFY_BAD;
+	return -ENOMEM;
 }
 
 static void intel_pmu_cpu_starting(int cpu)
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 7b5fd811ef45..783c49ddef29 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1577,7 +1577,7 @@ static inline void cqm_pick_event_reader(int cpu)
 		cpumask_set_cpu(cpu, &cqm_cpumask);
 }
 
-static void intel_cqm_cpu_starting(unsigned int cpu)
+static int intel_cqm_cpu_starting(unsigned int cpu)
 {
 	struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
@@ -1588,39 +1588,26 @@ static void intel_cqm_cpu_starting(unsigned int cpu)
 
 	WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
 	WARN_ON(c->x86_cache_occ_scale != cqm_l3_scale);
+
+	cqm_pick_event_reader(cpu);
+	return 0;
 }
 
-static void intel_cqm_cpu_exit(unsigned int cpu)
+static int intel_cqm_cpu_exit(unsigned int cpu)
 {
 	int target;
 
 	/* Is @cpu the current cqm reader for this package ? */
 	if (!cpumask_test_and_clear_cpu(cpu, &cqm_cpumask))
-		return;
+		return 0;
 
 	/* Find another online reader in this package */
 	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
 
 	if (target < nr_cpu_ids)
 		cpumask_set_cpu(target, &cqm_cpumask);
-}
-
-static int intel_cqm_cpu_notifier(struct notifier_block *nb,
-				  unsigned long action, void *hcpu)
-{
-	unsigned int cpu  = (unsigned long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DOWN_PREPARE:
-		intel_cqm_cpu_exit(cpu);
-		break;
-	case CPU_STARTING:
-		intel_cqm_cpu_starting(cpu);
-		cqm_pick_event_reader(cpu);
-		break;
-	}
 
-	return NOTIFY_OK;
+	return 0;
 }
 
 static const struct x86_cpu_id intel_cqm_match[] = {
@@ -1682,7 +1669,7 @@ out:
 static int __init intel_cqm_init(void)
 {
 	char *str = NULL, scale[20];
-	int i, cpu, ret;
+	int cpu, ret;
 
 	if (x86_match_cpu(intel_cqm_match))
 		cqm_enabled = true;
@@ -1705,8 +1692,7 @@ static int __init intel_cqm_init(void)
 	 *
 	 * Also, check that the scales match on all cpus.
 	 */
-	cpu_notifier_register_begin();
-
+	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		struct cpuinfo_x86 *c = &cpu_data(cpu);
 
@@ -1743,11 +1729,6 @@ static int __init intel_cqm_init(void)
 	if (ret)
 		goto out;
 
-	for_each_online_cpu(i) {
-		intel_cqm_cpu_starting(i);
-		cqm_pick_event_reader(i);
-	}
-
 	if (mbm_enabled)
 		ret = intel_mbm_init();
 	if (ret && !cqm_enabled)
@@ -1772,12 +1753,18 @@ static int __init intel_cqm_init(void)
 		pr_info("Intel MBM enabled\n");
 
 	/*
-	 * Register the hot cpu notifier once we are sure cqm
+	 * Setup the hot cpu notifier once we are sure cqm
 	 * is enabled to avoid notifier leak.
 	 */
-	__perf_cpu_notifier(intel_cqm_cpu_notifier);
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
+			  "AP_PERF_X86_CQM_STARTING",
+			  intel_cqm_cpu_starting, NULL);
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "AP_PERF_X86_CQM_ONLINE",
+			  NULL, intel_cqm_cpu_exit);
+
 out:
-	cpu_notifier_register_done();
+	put_online_cpus();
+
 	if (ret) {
 		kfree(str);
 		cqm_cleanup();
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index 4c7638b91fa5..3ca87b5a8677 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -366,7 +366,7 @@ static int cstate_pmu_event_add(struct perf_event *event, int mode)
  * Check if exiting cpu is the designated reader. If so migrate the
  * events when there is a valid target available
  */
-static void cstate_cpu_exit(int cpu)
+static int cstate_cpu_exit(unsigned int cpu)
 {
 	unsigned int target;
 
@@ -391,9 +391,10 @@ static void cstate_cpu_exit(int cpu)
 			perf_pmu_migrate_context(&cstate_pkg_pmu, cpu, target);
 		}
 	}
+	return 0;
 }
 
-static void cstate_cpu_init(int cpu)
+static int cstate_cpu_init(unsigned int cpu)
 {
 	unsigned int target;
 
@@ -415,31 +416,10 @@ static void cstate_cpu_init(int cpu)
 				 topology_core_cpumask(cpu));
 	if (has_cstate_pkg && target >= nr_cpu_ids)
 		cpumask_set_cpu(cpu, &cstate_pkg_cpu_mask);
-}
 
-static int cstate_cpu_notifier(struct notifier_block *self,
-			       unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_STARTING:
-		cstate_cpu_init(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		cstate_cpu_exit(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block cstate_cpu_nb = {
-	.notifier_call	= cstate_cpu_notifier,
-	.priority       = CPU_PRI_PERF + 1,
-};
-
 static struct pmu cstate_core_pmu = {
 	.attr_groups	= core_attr_groups,
 	.name		= "cstate_core",
@@ -600,18 +580,20 @@ static inline void cstate_cleanup(void)
 
 static int __init cstate_init(void)
 {
-	int cpu, err;
+	int err;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu)
-		cstate_cpu_init(cpu);
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_STARTING,
+			  "AP_PERF_X86_CSTATE_STARTING", cstate_cpu_init,
+			  NULL);
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_CSTATE_ONLINE,
+			  "AP_PERF_X86_CSTATE_ONLINE", NULL, cstate_cpu_exit);
 
 	if (has_cstate_core) {
 		err = perf_pmu_register(&cstate_core_pmu, cstate_core_pmu.name, -1);
 		if (err) {
 			has_cstate_core = false;
 			pr_info("Failed to register cstate core pmu\n");
-			goto out;
+			return err;
 		}
 	}
 
@@ -621,12 +603,10 @@ static int __init cstate_init(void)
 			has_cstate_pkg = false;
 			pr_info("Failed to register cstate pkg pmu\n");
 			cstate_cleanup();
-			goto out;
+			return err;
 		}
 	}
-	__register_cpu_notifier(&cstate_cpu_nb);
-out:
-	cpu_notifier_register_done();
+
 	return err;
 }
 
@@ -652,9 +632,8 @@ module_init(cstate_pmu_init);
 
 static void __exit cstate_pmu_exit(void)
 {
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&cstate_cpu_nb);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_ONLINE);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_CSTATE_STARTING);
 	cstate_cleanup();
-	cpu_notifier_register_done();
 }
 module_exit(cstate_pmu_exit);
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/intel/rapl.c
index d0c58b35155f..28865938aadf 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/intel/rapl.c
@@ -556,14 +556,14 @@ const struct attribute_group *rapl_attr_groups[] = {
 	NULL,
 };
 
-static void rapl_cpu_exit(int cpu)
+static int rapl_cpu_offline(unsigned int cpu)
 {
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
 	/* Check if exiting cpu is used for collecting rapl events */
 	if (!cpumask_test_and_clear_cpu(cpu, &rapl_cpu_mask))
-		return;
+		return 0;
 
 	pmu->cpu = -1;
 	/* Find a new cpu to collect rapl events */
@@ -575,9 +575,10 @@ static void rapl_cpu_exit(int cpu)
 		pmu->cpu = target;
 		perf_pmu_migrate_context(pmu->pmu, cpu, target);
 	}
+	return 0;
 }
 
-static void rapl_cpu_init(int cpu)
+static int rapl_cpu_online(unsigned int cpu)
 {
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
@@ -588,13 +589,14 @@ static void rapl_cpu_init(int cpu)
 	 */
 	target = cpumask_any_and(&rapl_cpu_mask, topology_core_cpumask(cpu));
 	if (target < nr_cpu_ids)
-		return;
+		return 0;
 
 	cpumask_set_cpu(cpu, &rapl_cpu_mask);
 	pmu->cpu = cpu;
+	return 0;
 }
 
-static int rapl_cpu_prepare(int cpu)
+static int rapl_cpu_prepare(unsigned int cpu)
 {
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 
@@ -615,33 +617,6 @@ static int rapl_cpu_prepare(int cpu)
 	return 0;
 }
 
-static int rapl_cpu_notifier(struct notifier_block *self,
-			     unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		rapl_cpu_prepare(cpu);
-		break;
-
-	case CPU_DOWN_FAILED:
-	case CPU_ONLINE:
-		rapl_cpu_init(cpu);
-		break;
-
-	case CPU_DOWN_PREPARE:
-		rapl_cpu_exit(cpu);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block rapl_cpu_nb = {
-	.notifier_call	= rapl_cpu_notifier,
-	.priority       = CPU_PRI_PERF + 1,
-};
-
 static int rapl_check_hw_unit(bool apply_quirk)
 {
 	u64 msr_rapl_power_unit_bits;
@@ -692,24 +667,6 @@ static void __init rapl_advertise(void)
 	}
 }
 
-static int __init rapl_prepare_cpus(void)
-{
-	unsigned int cpu, pkg;
-	int ret;
-
-	for_each_online_cpu(cpu) {
-		pkg = topology_logical_package_id(cpu);
-		if (rapl_pmus->pmus[pkg])
-			continue;
-
-		ret = rapl_cpu_prepare(cpu);
-		if (ret)
-			return ret;
-		rapl_cpu_init(cpu);
-	}
-	return 0;
-}
-
 static void cleanup_rapl_pmus(void)
 {
 	int i;
@@ -837,35 +794,44 @@ static int __init rapl_pmu_init(void)
 	if (ret)
 		return ret;
 
-	cpu_notifier_register_begin();
+	/*
+	 * Install callbacks. Core will call them for each online cpu.
+	 */
 
-	ret = rapl_prepare_cpus();
+	ret = cpuhp_setup_state(CPUHP_PERF_X86_RAPL_PREP, "PERF_X86_RAPL_PREP",
+				rapl_cpu_prepare, NULL);
 	if (ret)
 		goto out;
 
+	ret = cpuhp_setup_state(CPUHP_AP_PERF_X86_RAPL_ONLINE,
+				"AP_PERF_X86_RAPL_ONLINE",
+				rapl_cpu_online, rapl_cpu_offline);
+	if (ret)
+		goto out1;
+
 	ret = perf_pmu_register(&rapl_pmus->pmu, "power", -1);
 	if (ret)
-		goto out;
+		goto out2;
 
-	__register_cpu_notifier(&rapl_cpu_nb);
-	cpu_notifier_register_done();
 	rapl_advertise();
 	return 0;
 
+out2:
+	cpuhp_remove_state(CPUHP_AP_PERF_X86_RAPL_ONLINE);
+out1:
+	cpuhp_remove_state(CPUHP_PERF_X86_RAPL_PREP);
 out:
 	pr_warn("Initialization failed (%d), disabled\n", ret);
 	cleanup_rapl_pmus();
-	cpu_notifier_register_done();
 	return ret;
 }
 module_init(rapl_pmu_init);
 
 static void __exit intel_rapl_exit(void)
 {
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&rapl_cpu_nb);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_RAPL_ONLINE);
+	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_RAPL_PREP);
 	perf_pmu_unregister(&rapl_pmus->pmu);
 	cleanup_rapl_pmus();
-	cpu_notifier_register_done();
 }
 module_exit(intel_rapl_exit);
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index 59b4974c697f..3f3d0d67749b 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -1052,7 +1052,7 @@ static void uncore_pci_exit(void)
 	}
 }
 
-static void uncore_cpu_dying(int cpu)
+static int uncore_cpu_dying(unsigned int cpu)
 {
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
@@ -1069,16 +1069,19 @@ static void uncore_cpu_dying(int cpu)
 				uncore_box_exit(box);
 		}
 	}
+	return 0;
 }
 
-static void uncore_cpu_starting(int cpu, bool init)
+static int first_init;
+
+static int uncore_cpu_starting(unsigned int cpu)
 {
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
 	struct intel_uncore_box *box;
 	int i, pkg, ncpus = 1;
 
-	if (init) {
+	if (first_init) {
 		/*
 		 * On init we get the number of online cpus in the package
 		 * and set refcount for all of them.
@@ -1099,9 +1102,11 @@ static void uncore_cpu_starting(int cpu, bool init)
 				uncore_box_init(box);
 		}
 	}
+
+	return 0;
 }
 
-static int uncore_cpu_prepare(int cpu)
+static int uncore_cpu_prepare(unsigned int cpu)
 {
 	struct intel_uncore_type *type, **types = uncore_msr_uncores;
 	struct intel_uncore_pmu *pmu;
@@ -1164,13 +1169,13 @@ static void uncore_change_context(struct intel_uncore_type **uncores,
 		uncore_change_type_ctx(*uncores, old_cpu, new_cpu);
 }
 
-static void uncore_event_exit_cpu(int cpu)
+static int uncore_event_cpu_offline(unsigned int cpu)
 {
 	int target;
 
 	/* Check if exiting cpu is used for collecting uncore events */
 	if (!cpumask_test_and_clear_cpu(cpu, &uncore_cpu_mask))
-		return;
+		return 0;
 
 	/* Find a new cpu to collect uncore events */
 	target = cpumask_any_but(topology_core_cpumask(cpu), cpu);
@@ -1183,9 +1188,10 @@ static void uncore_event_exit_cpu(int cpu)
 
 	uncore_change_context(uncore_msr_uncores, cpu, target);
 	uncore_change_context(uncore_pci_uncores, cpu, target);
+	return 0;
 }
 
-static void uncore_event_init_cpu(int cpu)
+static int uncore_event_cpu_online(unsigned int cpu)
 {
 	int target;
 
@@ -1195,50 +1201,15 @@ static void uncore_event_init_cpu(int cpu)
 	 */
 	target = cpumask_any_and(&uncore_cpu_mask, topology_core_cpumask(cpu));
 	if (target < nr_cpu_ids)
-		return;
+		return 0;
 
 	cpumask_set_cpu(cpu, &uncore_cpu_mask);
 
 	uncore_change_context(uncore_msr_uncores, -1, cpu);
 	uncore_change_context(uncore_pci_uncores, -1, cpu);
+	return 0;
 }
 
-static int uncore_cpu_notifier(struct notifier_block *self,
-			       unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		return notifier_from_errno(uncore_cpu_prepare(cpu));
-
-	case CPU_STARTING:
-		uncore_cpu_starting(cpu, false);
-	case CPU_DOWN_FAILED:
-		uncore_event_init_cpu(cpu);
-		break;
-
-	case CPU_UP_CANCELED:
-	case CPU_DYING:
-		uncore_cpu_dying(cpu);
-		break;
-
-	case CPU_DOWN_PREPARE:
-		uncore_event_exit_cpu(cpu);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block uncore_cpu_nb = {
-	.notifier_call	= uncore_cpu_notifier,
-	/*
-	 * to migrate uncore events, our notifier should be executed
-	 * before perf core's notifier.
-	 */
-	.priority	= CPU_PRI_PERF + 1,
-};
-
 static int __init type_pmu_register(struct intel_uncore_type *type)
 {
 	int i, ret;
@@ -1282,41 +1253,6 @@ err:
 	return ret;
 }
 
-static void __init uncore_cpu_setup(void *dummy)
-{
-	uncore_cpu_starting(smp_processor_id(), true);
-}
-
-/* Lazy to avoid allocation of a few bytes for the normal case */
-static __initdata DECLARE_BITMAP(packages, MAX_LOCAL_APIC);
-
-static int __init uncore_cpumask_init(bool msr)
-{
-	unsigned int cpu;
-
-	for_each_online_cpu(cpu) {
-		unsigned int pkg = topology_logical_package_id(cpu);
-		int ret;
-
-		if (test_and_set_bit(pkg, packages))
-			continue;
-		/*
-		 * The first online cpu of each package allocates and takes
-		 * the refcounts for all other online cpus in that package.
-		 * If msrs are not enabled no allocation is required.
-		 */
-		if (msr) {
-			ret = uncore_cpu_prepare(cpu);
-			if (ret)
-				return ret;
-		}
-		uncore_event_init_cpu(cpu);
-		smp_call_function_single(cpu, uncore_cpu_setup, NULL, 1);
-	}
-	__register_cpu_notifier(&uncore_cpu_nb);
-	return 0;
-}
-
 #define X86_UNCORE_MODEL_MATCH(model, init)	\
 	{ X86_VENDOR_INTEL, 6, model, X86_FEATURE_ANY, (unsigned long)&init }
 
@@ -1440,11 +1376,33 @@ static int __init intel_uncore_init(void)
 	if (cret && pret)
 		return -ENODEV;
 
-	cpu_notifier_register_begin();
-	ret = uncore_cpumask_init(!cret);
-	if (ret)
-		goto err;
-	cpu_notifier_register_done();
+	/*
+	 * Install callbacks. Core will call them for each online cpu.
+	 *
+	 * The first online cpu of each package allocates and takes
+	 * the refcounts for all other online cpus in that package.
+	 * If msrs are not enabled no allocation is required and
+	 * uncore_cpu_prepare() is not called for each online cpu.
+	 */
+	if (!cret) {
+	       ret = cpuhp_setup_state(CPUHP_PERF_X86_UNCORE_PREP,
+					"PERF_X86_UNCORE_PREP",
+					uncore_cpu_prepare, NULL);
+		if (ret)
+			goto err;
+	} else {
+		cpuhp_setup_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP,
+					  "PERF_X86_UNCORE_PREP",
+					  uncore_cpu_prepare, NULL);
+	}
+	first_init = 1;
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_STARTING,
+			  "AP_PERF_X86_UNCORE_STARTING",
+			  uncore_cpu_starting, uncore_cpu_dying);
+	first_init = 0;
+	cpuhp_setup_state(CPUHP_AP_PERF_X86_UNCORE_ONLINE,
+			  "AP_PERF_X86_UNCORE_ONLINE",
+			  uncore_event_cpu_online, uncore_event_cpu_offline);
 	return 0;
 
 err:
@@ -1452,17 +1410,16 @@ err:
 	on_each_cpu_mask(&uncore_cpu_mask, uncore_exit_boxes, NULL, 1);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
-	cpu_notifier_register_done();
 	return ret;
 }
 module_init(intel_uncore_init);
 
 static void __exit intel_uncore_exit(void)
 {
-	cpu_notifier_register_begin();
-	__unregister_cpu_notifier(&uncore_cpu_nb);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_ONLINE);
+	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_X86_UNCORE_STARTING);
+	cpuhp_remove_state_nocalls(CPUHP_PERF_X86_UNCORE_PREP);
 	uncore_types_exit(uncore_msr_uncores);
 	uncore_pci_exit();
-	cpu_notifier_register_done();
 }
 module_exit(intel_uncore_exit);
diff --git a/arch/x86/kernel/apb_timer.c b/arch/x86/kernel/apb_timer.c
index cefacbad1531..456316f6c868 100644
--- a/arch/x86/kernel/apb_timer.c
+++ b/arch/x86/kernel/apb_timer.c
@@ -215,26 +215,18 @@ void apbt_setup_secondary_clock(void)
  * cpu timers during the offline process due to the ordering of notification.
  * the extra interrupt is harmless.
  */
-static int apbt_cpuhp_notify(struct notifier_block *n,
-			     unsigned long action, void *hcpu)
+static int apbt_cpu_dead(unsigned int cpu)
 {
-	unsigned long cpu = (unsigned long)hcpu;
 	struct apbt_dev *adev = &per_cpu(cpu_apbt_dev, cpu);
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DEAD:
-		dw_apb_clockevent_pause(adev->timer);
-		if (system_state == SYSTEM_RUNNING) {
-			pr_debug("skipping APBT CPU %lu offline\n", cpu);
-		} else {
-			pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
-			dw_apb_clockevent_stop(adev->timer);
-		}
-		break;
-	default:
-		pr_debug("APBT notified %lu, no action\n", action);
+	dw_apb_clockevent_pause(adev->timer);
+	if (system_state == SYSTEM_RUNNING) {
+		pr_debug("skipping APBT CPU %u offline\n", cpu);
+	} else {
+		pr_debug("APBT clockevent for cpu %u offline\n", cpu);
+		dw_apb_clockevent_stop(adev->timer);
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
 static __init int apbt_late_init(void)
@@ -242,9 +234,8 @@ static __init int apbt_late_init(void)
 	if (intel_mid_timer_options == INTEL_MID_TIMER_LAPIC_APBT ||
 		!apb_timer_block_enabled)
 		return 0;
-	/* This notifier should be called after workqueue is ready */
-	hotcpu_notifier(apbt_cpuhp_notify, -20);
-	return 0;
+	return cpuhp_setup_state(CPUHP_X86_APB_DEAD, "X86_APB_DEAD", NULL,
+				 apbt_cpu_dead);
 }
 fs_initcall(apbt_late_init);
 #else
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 24170d0809ba..6368fa69d2af 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -152,68 +152,48 @@ static void init_x2apic_ldr(void)
 	}
 }
 
- /*
-  * At CPU state changes, update the x2apic cluster sibling info.
-  */
-static int
-update_clusterinfo(struct notifier_block *nfb, unsigned long action, void *hcpu)
+/*
+ * At CPU state changes, update the x2apic cluster sibling info.
+ */
+int x2apic_prepare_cpu(unsigned int cpu)
 {
-	unsigned int this_cpu = (unsigned long)hcpu;
-	unsigned int cpu;
-	int err = 0;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-		if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, this_cpu),
-					GFP_KERNEL)) {
-			err = -ENOMEM;
-		} else if (!zalloc_cpumask_var(&per_cpu(ipi_mask, this_cpu),
-					       GFP_KERNEL)) {
-			free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
-			err = -ENOMEM;
-		}
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DEAD:
-		for_each_online_cpu(cpu) {
-			if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
-				continue;
-			cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
-			cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
-		}
-		free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
-		free_cpumask_var(per_cpu(ipi_mask, this_cpu));
-		break;
+	if (!zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL))
+		return -ENOMEM;
+
+	if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL)) {
+		free_cpumask_var(per_cpu(cpus_in_cluster, cpu));
+		return -ENOMEM;
 	}
 
-	return notifier_from_errno(err);
+	return 0;
 }
 
-static struct notifier_block x2apic_cpu_notifier = {
-	.notifier_call = update_clusterinfo,
-};
-
-static int x2apic_init_cpu_notifier(void)
+int x2apic_dead_cpu(unsigned int this_cpu)
 {
-	int cpu = smp_processor_id();
-
-	zalloc_cpumask_var(&per_cpu(cpus_in_cluster, cpu), GFP_KERNEL);
-	zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL);
+	int cpu;
 
-	BUG_ON(!per_cpu(cpus_in_cluster, cpu) || !per_cpu(ipi_mask, cpu));
-
-	cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
-	register_hotcpu_notifier(&x2apic_cpu_notifier);
-	return 1;
+	for_each_online_cpu(cpu) {
+		if (x2apic_cluster(this_cpu) != x2apic_cluster(cpu))
+			continue;
+		cpumask_clear_cpu(this_cpu, per_cpu(cpus_in_cluster, cpu));
+		cpumask_clear_cpu(cpu, per_cpu(cpus_in_cluster, this_cpu));
+	}
+	free_cpumask_var(per_cpu(cpus_in_cluster, this_cpu));
+	free_cpumask_var(per_cpu(ipi_mask, this_cpu));
+	return 0;
 }
 
 static int x2apic_cluster_probe(void)
 {
-	if (x2apic_mode)
-		return x2apic_init_cpu_notifier();
-	else
+	int cpu = smp_processor_id();
+
+	if (!x2apic_mode)
 		return 0;
+
+	cpumask_set_cpu(cpu, per_cpu(cpus_in_cluster, cpu));
+	cpuhp_setup_state(CPUHP_X2APIC_PREPARE, "X2APIC_PREPARE",
+			  x2apic_prepare_cpu, x2apic_dead_cpu);
+	return 1;
 }
 
 static const struct cpumask *x2apic_cluster_target_cpus(void)
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index f112af7aa62e..3d747070fe67 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -710,31 +710,29 @@ static void hpet_work(struct work_struct *w)
 	complete(&hpet_work->complete);
 }
 
-static int hpet_cpuhp_notify(struct notifier_block *n,
-		unsigned long action, void *hcpu)
+static int hpet_cpuhp_online(unsigned int cpu)
 {
-	unsigned long cpu = (unsigned long)hcpu;
 	struct hpet_work_struct work;
+
+	INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
+	init_completion(&work.complete);
+	/* FIXME: add schedule_work_on() */
+	schedule_delayed_work_on(cpu, &work.work, 0);
+	wait_for_completion(&work.complete);
+	destroy_delayed_work_on_stack(&work.work);
+	return 0;
+}
+
+static int hpet_cpuhp_dead(unsigned int cpu)
+{
 	struct hpet_dev *hdev = per_cpu(cpu_hpet_dev, cpu);
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-		INIT_DELAYED_WORK_ONSTACK(&work.work, hpet_work);
-		init_completion(&work.complete);
-		/* FIXME: add schedule_work_on() */
-		schedule_delayed_work_on(cpu, &work.work, 0);
-		wait_for_completion(&work.complete);
-		destroy_delayed_work_on_stack(&work.work);
-		break;
-	case CPU_DEAD:
-		if (hdev) {
-			free_irq(hdev->irq, hdev);
-			hdev->flags &= ~HPET_DEV_USED;
-			per_cpu(cpu_hpet_dev, cpu) = NULL;
-		}
-		break;
-	}
-	return NOTIFY_OK;
+	if (!hdev)
+		return 0;
+	free_irq(hdev->irq, hdev);
+	hdev->flags &= ~HPET_DEV_USED;
+	per_cpu(cpu_hpet_dev, cpu) = NULL;
+	return 0;
 }
 #else
 
@@ -750,11 +748,8 @@ static void hpet_reserve_msi_timers(struct hpet_data *hd)
 }
 #endif
 
-static int hpet_cpuhp_notify(struct notifier_block *n,
-		unsigned long action, void *hcpu)
-{
-	return NOTIFY_OK;
-}
+#define hpet_cpuhp_online	NULL
+#define hpet_cpuhp_dead		NULL
 
 #endif
 
@@ -931,7 +926,7 @@ out_nohpet:
  */
 static __init int hpet_late_init(void)
 {
-	int cpu;
+	int ret;
 
 	if (boot_hpet_disable)
 		return -ENODEV;
@@ -961,16 +956,20 @@ static __init int hpet_late_init(void)
 	if (boot_cpu_has(X86_FEATURE_ARAT))
 		return 0;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(cpu) {
-		hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);
-	}
-
 	/* This notifier should be called after workqueue is ready */
-	__hotcpu_notifier(hpet_cpuhp_notify, -20);
-	cpu_notifier_register_done();
-
+	ret = cpuhp_setup_state(CPUHP_AP_X86_HPET_ONLINE, "AP_X86_HPET_ONLINE",
+				hpet_cpuhp_online, NULL);
+	if (ret)
+		return ret;
+	ret = cpuhp_setup_state(CPUHP_X86_HPET_DEAD, "X86_HPET_DEAD", NULL,
+				hpet_cpuhp_dead);
+	if (ret)
+		goto err_cpuhp;
 	return 0;
+
+err_cpuhp:
+	cpuhp_remove_state(CPUHP_AP_X86_HPET_ONLINE);
+	return ret;
 }
 fs_initcall(hpet_late_init);
 
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 9b0185fbe3eb..654f6c66fe45 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -323,25 +323,16 @@ static int tboot_wait_for_aps(int num_aps)
 	return !(atomic_read((atomic_t *)&tboot->num_in_wfs) == num_aps);
 }
 
-static int tboot_cpu_callback(struct notifier_block *nfb, unsigned long action,
-			      void *hcpu)
+static int tboot_dying_cpu(unsigned int cpu)
 {
-	switch (action) {
-	case CPU_DYING:
-		atomic_inc(&ap_wfs_count);
-		if (num_online_cpus() == 1)
-			if (tboot_wait_for_aps(atomic_read(&ap_wfs_count)))
-				return NOTIFY_BAD;
-		break;
+	atomic_inc(&ap_wfs_count);
+	if (num_online_cpus() == 1) {
+		if (tboot_wait_for_aps(atomic_read(&ap_wfs_count)))
+			return -EBUSY;
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block tboot_cpu_notifier =
-{
-	.notifier_call = tboot_cpu_callback,
-};
-
 #ifdef CONFIG_DEBUG_FS
 
 #define TBOOT_LOG_UUID	{ 0x26, 0x25, 0x19, 0xc0, 0x30, 0x6b, 0xb4, 0x4d, \
@@ -417,8 +408,8 @@ static __init int tboot_late_init(void)
 	tboot_create_trampoline();
 
 	atomic_set(&ap_wfs_count, 0);
-	register_hotcpu_notifier(&tboot_cpu_notifier);
-
+	cpuhp_setup_state(CPUHP_AP_X86_TBOOT_DYING, "AP_X86_TBOOT_DYING", NULL,
+			  tboot_dying_cpu);
 #ifdef CONFIG_DEBUG_FS
 	debugfs_create_file("tboot_log", S_IRUSR,
 			arch_debugfs_dir, NULL, &tboot_log_fops);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b2766723c951..45608a7da9b3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -5552,9 +5552,10 @@ int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size, unsigned short port)
 }
 EXPORT_SYMBOL_GPL(kvm_fast_pio_out);
 
-static void tsc_bad(void *info)
+static int kvmclock_cpu_down_prep(unsigned int cpu)
 {
 	__this_cpu_write(cpu_tsc_khz, 0);
+	return 0;
 }
 
 static void tsc_khz_changed(void *data)
@@ -5659,35 +5660,18 @@ static struct notifier_block kvmclock_cpufreq_notifier_block = {
 	.notifier_call  = kvmclock_cpufreq_notifier
 };
 
-static int kvmclock_cpu_notifier(struct notifier_block *nfb,
-					unsigned long action, void *hcpu)
+static int kvmclock_cpu_online(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action) {
-		case CPU_ONLINE:
-		case CPU_DOWN_FAILED:
-			smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
-			break;
-		case CPU_DOWN_PREPARE:
-			smp_call_function_single(cpu, tsc_bad, NULL, 1);
-			break;
-	}
-	return NOTIFY_OK;
+	tsc_khz_changed(NULL);
+	return 0;
 }
 
-static struct notifier_block kvmclock_cpu_notifier_block = {
-	.notifier_call  = kvmclock_cpu_notifier,
-	.priority = -INT_MAX
-};
-
 static void kvm_timer_init(void)
 {
 	int cpu;
 
 	max_tsc_khz = tsc_khz;
 
-	cpu_notifier_register_begin();
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
 #ifdef CONFIG_CPU_FREQ
 		struct cpufreq_policy policy;
@@ -5702,12 +5686,9 @@ static void kvm_timer_init(void)
 					  CPUFREQ_TRANSITION_NOTIFIER);
 	}
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
-	for_each_online_cpu(cpu)
-		smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
-
-	__register_hotcpu_notifier(&kvmclock_cpu_notifier_block);
-	cpu_notifier_register_done();
 
+	cpuhp_setup_state(CPUHP_AP_X86_KVM_CLK_ONLINE, "AP_X86_KVM_CLK_ONLINE",
+			  kvmclock_cpu_online, kvmclock_cpu_down_prep);
 }
 
 static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
@@ -5896,7 +5877,7 @@ void kvm_arch_exit(void)
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC))
 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
 					    CPUFREQ_TRANSITION_NOTIFIER);
-	unregister_hotcpu_notifier(&kvmclock_cpu_notifier_block);
+	cpuhp_remove_state_nocalls(CPUHP_AP_X86_KVM_CLK_ONLINE);
 #ifdef CONFIG_X86_64
 	pvclock_gtod_unregister_notifier(&pvclock_gtod_notifier);
 #endif