diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index be3b3fb..af2a7f1 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -1090,7 +1090,7 @@ static int __init arch_hw_breakpoint_init(void)
 	 * driven low on this core and there isn't an architected way to
 	 * determine that.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	register_undef_hook(&debug_reg_hook);
 
 	/*
@@ -1098,15 +1098,16 @@ static int __init arch_hw_breakpoint_init(void)
 	 * assume that a halting debugger will leave the world in a nice state
 	 * for us.
 	 */
-	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "arm/hw_breakpoint:online",
-				dbg_reset_online, NULL);
+	ret = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN,
+					   "arm/hw_breakpoint:online",
+					   dbg_reset_online, NULL);
 	unregister_undef_hook(&debug_reg_hook);
 	if (WARN_ON(ret < 0) || !cpumask_empty(&debug_err_mask)) {
 		core_num_brps = 0;
 		core_num_wrps = 0;
 		if (ret > 0)
-			cpuhp_remove_state_nocalls(ret);
-		put_online_cpus();
+			cpuhp_remove_state_nocalls_cpuslocked(ret);
+		cpus_read_unlock();
 		return 0;
 	}
 
@@ -1124,7 +1125,7 @@ static int __init arch_hw_breakpoint_init(void)
 			TRAP_HWBKPT, "watchpoint debug exception");
 	hook_ifault_code(FAULT_CODE_DEBUG, hw_breakpoint_pending, SIGTRAP,
 			TRAP_HWBKPT, "breakpoint debug exception");
-	put_online_cpus();
+	cpus_read_unlock();
 
 	/* Register PM notifiers. */
 	pm_init();
diff --git a/arch/arm/kernel/patch.c b/arch/arm/kernel/patch.c
index 020560b..a1a3472 100644
--- a/arch/arm/kernel/patch.c
+++ b/arch/arm/kernel/patch.c
@@ -124,5 +124,5 @@ void __kprobes patch_text(void *addr, unsigned int insn)
 		.insn = insn,
 	};
 
-	stop_machine(patch_text_stop_machine, &patch, NULL);
+	stop_machine_cpuslocked(patch_text_stop_machine, &patch, NULL);
 }
diff --git a/arch/arm/probes/kprobes/core.c b/arch/arm/probes/kprobes/core.c
index ad1f4e6..52d1cd1 100644
--- a/arch/arm/probes/kprobes/core.c
+++ b/arch/arm/probes/kprobes/core.c
@@ -182,7 +182,8 @@ void __kprobes kprobes_remove_breakpoint(void *addr, unsigned int insn)
 		.addr = addr,
 		.insn = insn,
 	};
-	stop_machine(__kprobes_remove_breakpoint, &p, cpu_online_mask);
+	stop_machine_cpuslocked(__kprobes_remove_breakpoint, &p,
+				cpu_online_mask);
 }
 
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
diff --git a/arch/arm64/include/asm/insn.h b/arch/arm64/include/asm/insn.h
index 29cb2ca..4214c38 100644
--- a/arch/arm64/include/asm/insn.h
+++ b/arch/arm64/include/asm/insn.h
@@ -433,7 +433,6 @@ u32 aarch64_set_branch_offset(u32 insn, s32 offset);
 bool aarch64_insn_hotpatch_safe(u32 old_insn, u32 new_insn);
 
 int aarch64_insn_patch_text_nosync(void *addr, u32 insn);
-int aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt);
 int aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt);
 
 s32 aarch64_insn_adrp_get_offset(u32 insn);
diff --git a/arch/arm64/kernel/insn.c b/arch/arm64/kernel/insn.c
index b884a92..cd87213 100644
--- a/arch/arm64/kernel/insn.c
+++ b/arch/arm64/kernel/insn.c
@@ -255,6 +255,7 @@ static int __kprobes aarch64_insn_patch_text_cb(void *arg)
 	return ret;
 }
 
+static
 int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 {
 	struct aarch64_insn_patch patch = {
@@ -267,8 +268,8 @@ int __kprobes aarch64_insn_patch_text_sync(void *addrs[], u32 insns[], int cnt)
 	if (cnt <= 0)
 		return -EINVAL;
 
-	return stop_machine(aarch64_insn_patch_text_cb, &patch,
-			    cpu_online_mask);
+	return stop_machine_cpuslocked(aarch64_insn_patch_text_cb, &patch,
+				       cpu_online_mask);
 }
 
 int __kprobes aarch64_insn_patch_text(void *addrs[], u32 insns[], int cnt)
diff --git a/arch/mips/kernel/jump_label.c b/arch/mips/kernel/jump_label.c
index 3e586da..32e3168 100644
--- a/arch/mips/kernel/jump_label.c
+++ b/arch/mips/kernel/jump_label.c
@@ -58,7 +58,6 @@ void arch_jump_label_transform(struct jump_entry *e,
 		insn.word = 0; /* nop */
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	if (IS_ENABLED(CONFIG_CPU_MICROMIPS)) {
 		insn_p->halfword[0] = insn.word >> 16;
@@ -70,7 +69,6 @@ void arch_jump_label_transform(struct jump_entry *e,
 			   (unsigned long)insn_p + sizeof(*insn_p));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif /* HAVE_JUMP_LABEL */
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index 3297715..dc4e159 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -43,6 +43,7 @@ extern void __init dump_numa_cpu_topology(void);
 
 extern int sysfs_add_device_to_node(struct device *dev, int nid);
 extern void sysfs_remove_device_from_node(struct device *dev, int nid);
+extern int numa_update_cpu_topology(bool cpus_locked);
 
 static inline int early_cpu_to_node(int cpu)
 {
@@ -71,6 +72,11 @@ static inline void sysfs_remove_device_from_node(struct device *dev,
 						int nid)
 {
 }
+
+static inline int numa_update_cpu_topology(bool cpus_locked)
+{
+	return 0;
+}
 #endif /* CONFIG_NUMA */
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
diff --git a/arch/powerpc/kernel/rtasd.c b/arch/powerpc/kernel/rtasd.c
index 3650732..0f0b1b2 100644
--- a/arch/powerpc/kernel/rtasd.c
+++ b/arch/powerpc/kernel/rtasd.c
@@ -283,7 +283,7 @@ static void prrn_work_fn(struct work_struct *work)
 	 * the RTAS event.
 	 */
 	pseries_devicetree_update(-prrn_update_scope);
-	arch_update_cpu_topology();
+	numa_update_cpu_topology(false);
 }
 
 static DECLARE_WORK(prrn_work, prrn_work_fn);
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 8d1a365..773b35d 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -3368,7 +3368,7 @@ void kvmppc_alloc_host_rm_ops(void)
 		return;
 	}
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	for (cpu = 0; cpu < nr_cpu_ids; cpu += threads_per_core) {
 		if (!cpu_online(cpu))
@@ -3390,17 +3390,17 @@ void kvmppc_alloc_host_rm_ops(void)
 	l_ops = (unsigned long) ops;
 
 	if (cmpxchg64((unsigned long *)&kvmppc_host_rm_ops_hv, 0, l_ops)) {
-		put_online_cpus();
+		cpus_read_unlock();
 		kfree(ops->rm_core);
 		kfree(ops);
 		return;
 	}
 
-	cpuhp_setup_state_nocalls(CPUHP_KVM_PPC_BOOK3S_PREPARE,
-				  "ppc/kvm_book3s:prepare",
-				  kvmppc_set_host_core,
-				  kvmppc_clear_host_core);
-	put_online_cpus();
+	cpuhp_setup_state_nocalls_cpuslocked(CPUHP_KVM_PPC_BOOK3S_PREPARE,
+					     "ppc/kvm_book3s:prepare",
+					     kvmppc_set_host_core,
+					     kvmppc_clear_host_core);
+	cpus_read_unlock();
 }
 
 void kvmppc_free_host_rm_ops(void)
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 371792e..b95c584 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -1311,8 +1311,10 @@ static int update_lookup_table(void *data)
 /*
  * Update the node maps and sysfs entries for each cpu whose home node
  * has changed. Returns 1 when the topology has changed, and 0 otherwise.
+ *
+ * cpus_locked says whether we already hold cpu_hotplug_lock.
  */
-int arch_update_cpu_topology(void)
+int numa_update_cpu_topology(bool cpus_locked)
 {
 	unsigned int cpu, sibling, changed = 0;
 	struct topology_update_data *updates, *ud;
@@ -1400,15 +1402,23 @@ int arch_update_cpu_topology(void)
 	if (!cpumask_weight(&updated_cpus))
 		goto out;
 
-	stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_cpu_topology, &updates[0],
+					&updated_cpus);
+	else
+		stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
 
 	/*
 	 * Update the numa-cpu lookup table with the new mappings, even for
 	 * offline CPUs. It is best to perform this update from the stop-
 	 * machine context.
 	 */
-	stop_machine(update_lookup_table, &updates[0],
+	if (cpus_locked)
+		stop_machine_cpuslocked(update_lookup_table, &updates[0],
 					cpumask_of(raw_smp_processor_id()));
+	else
+		stop_machine(update_lookup_table, &updates[0],
+			     cpumask_of(raw_smp_processor_id()));
 
 	for (ud = &updates[0]; ud; ud = ud->next) {
 		unregister_cpu_under_node(ud->cpu, ud->old_nid);
@@ -1426,6 +1436,12 @@ int arch_update_cpu_topology(void)
 	return changed;
 }
 
+int arch_update_cpu_topology(void)
+{
+	lockdep_assert_cpus_held();
+	return numa_update_cpu_topology(true);
+}
+
 static void topology_work_fn(struct work_struct *work)
 {
 	rebuild_sched_domains();
diff --git a/arch/powerpc/platforms/powernv/subcore.c b/arch/powerpc/platforms/powernv/subcore.c
index 8c61192..309876d 100644
--- a/arch/powerpc/platforms/powernv/subcore.c
+++ b/arch/powerpc/platforms/powernv/subcore.c
@@ -348,7 +348,7 @@ static int set_subcores_per_core(int new_mode)
 		state->master = 0;
 	}
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	/* This cpu will update the globals before exiting stop machine */
 	this_cpu_ptr(&split_state)->master = 1;
@@ -356,9 +356,10 @@ static int set_subcores_per_core(int new_mode)
 	/* Ensure state is consistent before we call the other cpus */
 	mb();
 
-	stop_machine(cpu_update_split_mode, &new_mode, cpu_online_mask);
+	stop_machine_cpuslocked(cpu_update_split_mode, &new_mode,
+				cpu_online_mask);
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
diff --git a/arch/s390/kernel/jump_label.c b/arch/s390/kernel/jump_label.c
index 6aa630a8..262506c 100644
--- a/arch/s390/kernel/jump_label.c
+++ b/arch/s390/kernel/jump_label.c
@@ -93,7 +93,7 @@ void arch_jump_label_transform(struct jump_entry *entry,
 	args.entry = entry;
 	args.type = type;
 
-	stop_machine(__sm_arch_jump_label_transform, &args, NULL);
+	stop_machine_cpuslocked(__sm_arch_jump_label_transform, &args, NULL);
 }
 
 void arch_jump_label_transform_static(struct jump_entry *entry,
diff --git a/arch/s390/kernel/kprobes.c b/arch/s390/kernel/kprobes.c
index 3d6a997..6842e45 100644
--- a/arch/s390/kernel/kprobes.c
+++ b/arch/s390/kernel/kprobes.c
@@ -196,7 +196,7 @@ void arch_arm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 1};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_arm_kprobe);
 
@@ -204,7 +204,7 @@ void arch_disarm_kprobe(struct kprobe *p)
 {
 	struct swap_insn_args args = {.p = p, .arm_kprobe = 0};
 
-	stop_machine(swap_instruction, &args, NULL);
+	stop_machine_cpuslocked(swap_instruction, &args, NULL);
 }
 NOKPROBE_SYMBOL(arch_disarm_kprobe);
 
diff --git a/arch/s390/kernel/time.c b/arch/s390/kernel/time.c
index c3a52f9..192efdf 100644
--- a/arch/s390/kernel/time.c
+++ b/arch/s390/kernel/time.c
@@ -636,10 +636,10 @@ static void stp_work_fn(struct work_struct *work)
 		goto out_unlock;
 
 	memset(&stp_sync, 0, sizeof(stp_sync));
-	get_online_cpus();
+	cpus_read_lock();
 	atomic_set(&stp_sync.cpus, num_online_cpus() - 1);
-	stop_machine(stp_sync_clock, &stp_sync, cpu_online_mask);
-	put_online_cpus();
+	stop_machine_cpuslocked(stp_sync_clock, &stp_sync, cpu_online_mask);
+	cpus_read_unlock();
 
 	if (!check_sync_clock())
 		/*
diff --git a/arch/sparc/kernel/jump_label.c b/arch/sparc/kernel/jump_label.c
index 07933b9..93adde1 100644
--- a/arch/sparc/kernel/jump_label.c
+++ b/arch/sparc/kernel/jump_label.c
@@ -41,12 +41,10 @@ void arch_jump_label_transform(struct jump_entry *entry,
 		val = 0x01000000;
 	}
 
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	*insn = val;
 	flushi(insn);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 #endif
diff --git a/arch/tile/kernel/jump_label.c b/arch/tile/kernel/jump_label.c
index 07802d5..93931a4 100644
--- a/arch/tile/kernel/jump_label.c
+++ b/arch/tile/kernel/jump_label.c
@@ -45,14 +45,12 @@ static void __jump_label_transform(struct jump_entry *e,
 void arch_jump_label_transform(struct jump_entry *e,
 				enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 
 	__jump_label_transform(e, type);
 	flush_icache_range(e->code, e->code + sizeof(tilegx_bundle_bits));
 
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 __init_or_module void arch_jump_label_transform_static(struct jump_entry *e,
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 2de0dd7..ff1ea2f 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -2233,7 +2233,6 @@ void perf_check_microcode(void)
 	if (x86_pmu.check_microcode)
 		x86_pmu.check_microcode();
 }
-EXPORT_SYMBOL_GPL(perf_check_microcode);
 
 static struct pmu pmu = {
 	.pmu_enable		= x86_pmu_enable,
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 31acf2a..aa62437 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -3425,12 +3425,10 @@ static void intel_snb_check_microcode(void)
 	int pebs_broken = 0;
 	int cpu;
 
-	get_online_cpus();
 	for_each_online_cpu(cpu) {
 		if ((pebs_broken = intel_snb_pebs_broken(cpu)))
 			break;
 	}
-	put_online_cpus();
 
 	if (pebs_broken == x86_pmu.pebs_broken)
 		return;
@@ -3503,7 +3501,9 @@ static bool check_msr(unsigned long msr, u64 mask)
 static __init void intel_sandybridge_quirk(void)
 {
 	x86_pmu.check_microcode = intel_snb_check_microcode;
+	cpus_read_lock();
 	intel_snb_check_microcode();
+	cpus_read_unlock();
 }
 
 static const struct { int id; char *name; } intel_arch_events_map[] __initconst = {
@@ -4175,13 +4175,12 @@ static __init int fixup_ht_bug(void)
 
 	lockup_detector_resume();
 
-	get_online_cpus();
+	cpus_read_lock();
 
-	for_each_online_cpu(c) {
+	for_each_online_cpu(c)
 		free_excl_cntrs(c);
-	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 	pr_info("PMU erratum BJ122, BV98, HSD29 workaround disabled, HT off\n");
 	return 0;
 }
diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 8c00dc0..2521f77 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -1682,7 +1682,7 @@ static int __init intel_cqm_init(void)
 	 *
 	 * Also, check that the scales match on all cpus.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		struct cpuinfo_x86 *c = &cpu_data(cpu);
 
@@ -1746,14 +1746,14 @@ static int __init intel_cqm_init(void)
 	 * Setup the hot cpu notifier once we are sure cqm
 	 * is enabled to avoid notifier leak.
 	 */
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_STARTING,
-			  "perf/x86/cqm:starting",
-			  intel_cqm_cpu_starting, NULL);
-	cpuhp_setup_state(CPUHP_AP_PERF_X86_CQM_ONLINE, "perf/x86/cqm:online",
-			  NULL, intel_cqm_cpu_exit);
-
+	cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_STARTING,
+				     "perf/x86/cqm:starting",
+				     intel_cqm_cpu_starting, NULL);
+	cpuhp_setup_state_cpuslocked(CPUHP_AP_PERF_X86_CQM_ONLINE,
+				     "perf/x86/cqm:online",
+				     NULL, intel_cqm_cpu_exit);
 out:
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (ret) {
 		kfree(str);
diff --git a/arch/x86/kernel/cpu/mtrr/main.c b/arch/x86/kernel/cpu/mtrr/main.c
index 2bce84d..c5bb63b 100644
--- a/arch/x86/kernel/cpu/mtrr/main.c
+++ b/arch/x86/kernel/cpu/mtrr/main.c
@@ -807,10 +807,8 @@ void mtrr_save_state(void)
 	if (!mtrr_enabled())
 		return;
 
-	get_online_cpus();
 	first_cpu = cpumask_first(cpu_online_mask);
 	smp_call_function_single(first_cpu, mtrr_save_fixed_ranges, NULL, 1);
-	put_online_cpus();
 }
 
 void set_mtrr_aps_delayed_init(void)
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index c37bd0f..ab4f491 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -105,11 +105,9 @@ static void __jump_label_transform(struct jump_entry *entry,
 void arch_jump_label_transform(struct jump_entry *entry,
 			       enum jump_label_type type)
 {
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	__jump_label_transform(entry, type, NULL, 0);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 static enum {
diff --git a/drivers/acpi/processor_driver.c b/drivers/acpi/processor_driver.c
index 8697a82..591d1dd 100644
--- a/drivers/acpi/processor_driver.c
+++ b/drivers/acpi/processor_driver.c
@@ -268,9 +268,9 @@ static int acpi_processor_start(struct device *dev)
 		return -ENODEV;
 
 	/* Protect against concurrent CPU hotplug operations */
-	get_online_cpus();
+	cpu_hotplug_disable();
 	ret = __acpi_processor_start(device);
-	put_online_cpus();
+	cpu_hotplug_enable();
 	return ret;
 }
 
diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c
index 3de34633..7f9aff4 100644
--- a/drivers/acpi/processor_throttling.c
+++ b/drivers/acpi/processor_throttling.c
@@ -909,6 +909,13 @@ static long __acpi_processor_get_throttling(void *data)
 	return pr->throttling.acpi_processor_get_throttling(pr);
 }
 
+static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
+{
+	if (direct || (is_percpu_thread() && cpu == smp_processor_id()))
+		return fn(arg);
+	return work_on_cpu(cpu, fn, arg);
+}
+
 static int acpi_processor_get_throttling(struct acpi_processor *pr)
 {
 	if (!pr)
@@ -926,7 +933,7 @@ static int acpi_processor_get_throttling(struct acpi_processor *pr)
 	if (!cpu_online(pr->id))
 		return -ENODEV;
 
-	return work_on_cpu(pr->id, __acpi_processor_get_throttling, pr);
+	return call_on_cpu(pr->id, __acpi_processor_get_throttling, pr, false);
 }
 
 static int acpi_processor_get_fadt_info(struct acpi_processor *pr)
@@ -1076,13 +1083,6 @@ static long acpi_processor_throttling_fn(void *data)
 			arg->target_state, arg->force);
 }
 
-static int call_on_cpu(int cpu, long (*fn)(void *), void *arg, bool direct)
-{
-	if (direct)
-		return fn(arg);
-	return work_on_cpu(cpu, fn, arg);
-}
-
 static int __acpi_processor_set_throttling(struct acpi_processor *pr,
 					   int state, bool force, bool direct)
 {
diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c
index 26b643d..29c5b0c 100644
--- a/drivers/cpufreq/cpufreq.c
+++ b/drivers/cpufreq/cpufreq.c
@@ -887,7 +887,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 	struct freq_attr *fattr = to_attr(attr);
 	ssize_t ret = -EINVAL;
 
-	get_online_cpus();
+	cpus_read_lock();
 
 	if (cpu_online(policy->cpu)) {
 		down_write(&policy->rwsem);
@@ -895,7 +895,7 @@ static ssize_t store(struct kobject *kobj, struct attribute *attr,
 		up_write(&policy->rwsem);
 	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return ret;
 }
@@ -2441,7 +2441,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	pr_debug("trying to register driver %s\n", driver_data->name);
 
 	/* Protect against concurrent CPU online/offline. */
-	get_online_cpus();
+	cpus_read_lock();
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 	if (cpufreq_driver) {
@@ -2474,9 +2474,10 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		goto err_if_unreg;
 	}
 
-	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online",
-					cpuhp_cpufreq_online,
-					cpuhp_cpufreq_offline);
+	ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN,
+						   "cpufreq:online",
+						   cpuhp_cpufreq_online,
+						   cpuhp_cpufreq_offline);
 	if (ret < 0)
 		goto err_if_unreg;
 	hp_online = ret;
@@ -2494,7 +2495,7 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 	cpufreq_driver = NULL;
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
 out:
-	put_online_cpus();
+	cpus_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(cpufreq_register_driver);
@@ -2517,17 +2518,17 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	pr_debug("unregistering driver %s\n", driver->name);
 
 	/* Protect against concurrent cpu hotplug */
-	get_online_cpus();
+	cpus_read_lock();
 	subsys_interface_unregister(&cpufreq_interface);
 	remove_boost_sysfs_file();
-	cpuhp_remove_state_nocalls(hp_online);
+	cpuhp_remove_state_nocalls_cpuslocked(hp_online);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 
 	cpufreq_driver = NULL;
 
 	write_unlock_irqrestore(&cpufreq_driver_lock, flags);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
diff --git a/drivers/hwtracing/coresight/coresight-etm3x.c b/drivers/hwtracing/coresight/coresight-etm3x.c
index a51b6b6..93ee8fc 100644
--- a/drivers/hwtracing/coresight/coresight-etm3x.c
+++ b/drivers/hwtracing/coresight/coresight-etm3x.c
@@ -587,7 +587,7 @@ static void etm_disable_sysfs(struct coresight_device *csdev)
 	 * after cpu online mask indicates the cpu is offline but before the
 	 * DYING hotplug callback is serviced by the ETM driver.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	spin_lock(&drvdata->spinlock);
 
 	/*
@@ -597,7 +597,7 @@ static void etm_disable_sysfs(struct coresight_device *csdev)
 	smp_call_function_single(drvdata->cpu, etm_disable_hw, drvdata, 1);
 
 	spin_unlock(&drvdata->spinlock);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	dev_info(drvdata->dev, "ETM tracing disabled\n");
 }
@@ -795,7 +795,7 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 
 	drvdata->cpu = pdata ? pdata->cpu : 0;
 
-	get_online_cpus();
+	cpus_read_lock();
 	etmdrvdata[drvdata->cpu] = drvdata;
 
 	if (smp_call_function_single(drvdata->cpu,
@@ -803,17 +803,17 @@ static int etm_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "arm/coresight:starting",
-					  etm_starting_cpu, etm_dying_cpu);
-		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"arm/coresight:online",
-						etm_online_cpu, NULL);
+		cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING,
+						     "arm/coresight:starting",
+						     etm_starting_cpu, etm_dying_cpu);
+		ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN,
+							   "arm/coresight:online",
+							   etm_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
 		hp_online = ret;
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (etm_arch_supported(drvdata->arch) == false) {
 		ret = -EINVAL;
diff --git a/drivers/hwtracing/coresight/coresight-etm4x.c b/drivers/hwtracing/coresight/coresight-etm4x.c
index d1340fb..532adc9 100644
--- a/drivers/hwtracing/coresight/coresight-etm4x.c
+++ b/drivers/hwtracing/coresight/coresight-etm4x.c
@@ -371,7 +371,7 @@ static void etm4_disable_sysfs(struct coresight_device *csdev)
 	 * after cpu online mask indicates the cpu is offline but before the
 	 * DYING hotplug callback is serviced by the ETM driver.
 	 */
-	get_online_cpus();
+	cpus_read_lock();
 	spin_lock(&drvdata->spinlock);
 
 	/*
@@ -381,7 +381,7 @@ static void etm4_disable_sysfs(struct coresight_device *csdev)
 	smp_call_function_single(drvdata->cpu, etm4_disable_hw, drvdata, 1);
 
 	spin_unlock(&drvdata->spinlock);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	dev_info(drvdata->dev, "ETM tracing disabled\n");
 }
@@ -982,7 +982,7 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 
 	drvdata->cpu = pdata ? pdata->cpu : 0;
 
-	get_online_cpus();
+	cpus_read_lock();
 	etmdrvdata[drvdata->cpu] = drvdata;
 
 	if (smp_call_function_single(drvdata->cpu,
@@ -990,18 +990,18 @@ static int etm4_probe(struct amba_device *adev, const struct amba_id *id)
 		dev_err(dev, "ETM arch init failed\n");
 
 	if (!etm4_count++) {
-		cpuhp_setup_state_nocalls(CPUHP_AP_ARM_CORESIGHT_STARTING,
-					  "arm/coresight4:starting",
-					  etm4_starting_cpu, etm4_dying_cpu);
-		ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
-						"arm/coresight4:online",
-						etm4_online_cpu, NULL);
+		cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ARM_CORESIGHT_STARTING,
+						     "arm/coresight4:starting",
+						     etm4_starting_cpu, etm4_dying_cpu);
+		ret = cpuhp_setup_state_nocalls_cpuslocked(CPUHP_AP_ONLINE_DYN,
+							   "arm/coresight4:online",
+							   etm4_online_cpu, NULL);
 		if (ret < 0)
 			goto err_arch_supported;
 		hp_online = ret;
 	}
 
-	put_online_cpus();
+	cpus_read_unlock();
 
 	if (etm4_arch_supported(drvdata->arch) == false) {
 		ret = -EINVAL;
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 192e7b6..fe6be63 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -320,10 +320,19 @@ static long local_pci_probe(void *_ddi)
 	return 0;
 }
 
+static bool pci_physfn_is_probed(struct pci_dev *dev)
+{
+#ifdef CONFIG_PCI_IOV
+	return dev->is_virtfn && dev->physfn->is_probed;
+#else
+	return false;
+#endif
+}
+
 static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 			  const struct pci_device_id *id)
 {
-	int error, node;
+	int error, node, cpu;
 	struct drv_dev_and_id ddi = { drv, dev, id };
 
 	/*
@@ -332,33 +341,27 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	 * on the right node.
 	 */
 	node = dev_to_node(&dev->dev);
+	dev->is_probed = 1;
+
+	cpu_hotplug_disable();
 
 	/*
-	 * On NUMA systems, we are likely to call a PF probe function using
-	 * work_on_cpu().  If that probe calls pci_enable_sriov() (which
-	 * adds the VF devices via pci_bus_add_device()), we may re-enter
-	 * this function to call the VF probe function.  Calling
-	 * work_on_cpu() again will cause a lockdep warning.  Since VFs are
-	 * always on the same node as the PF, we can work around this by
-	 * avoiding work_on_cpu() when we're already on the correct node.
-	 *
-	 * Preemption is enabled, so it's theoretically unsafe to use
-	 * numa_node_id(), but even if we run the probe function on the
-	 * wrong node, it should be functionally correct.
+	 * Prevent nesting work_on_cpu() for the case where a Virtual Function
+	 * device is probed from work_on_cpu() of the Physical device.
 	 */
-	if (node >= 0 && node != numa_node_id()) {
-		int cpu;
-
-		get_online_cpus();
+	if (node < 0 || node >= MAX_NUMNODES || !node_online(node) ||
+	    pci_physfn_is_probed(dev))
+		cpu = nr_cpu_ids;
+	else
 		cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
-		if (cpu < nr_cpu_ids)
-			error = work_on_cpu(cpu, local_pci_probe, &ddi);
-		else
-			error = local_pci_probe(&ddi);
-		put_online_cpus();
-	} else
+
+	if (cpu < nr_cpu_ids)
+		error = work_on_cpu(cpu, local_pci_probe, &ddi);
+	else
 		error = local_pci_probe(&ddi);
 
+	dev->is_probed = 0;
+	cpu_hotplug_enable();
 	return error;
 }
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index f920812..ca73bc1 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -99,26 +99,32 @@ static inline void cpu_maps_update_done(void)
 extern struct bus_type cpu_subsys;
 
 #ifdef CONFIG_HOTPLUG_CPU
-/* Stop CPUs going up and down. */
-
-extern void cpu_hotplug_begin(void);
-extern void cpu_hotplug_done(void);
-extern void get_online_cpus(void);
-extern void put_online_cpus(void);
+extern void cpus_write_lock(void);
+extern void cpus_write_unlock(void);
+extern void cpus_read_lock(void);
+extern void cpus_read_unlock(void);
+extern void lockdep_assert_cpus_held(void);
 extern void cpu_hotplug_disable(void);
 extern void cpu_hotplug_enable(void);
 void clear_tasks_mm_cpumask(int cpu);
 int cpu_down(unsigned int cpu);
 
-#else		/* CONFIG_HOTPLUG_CPU */
+#else /* CONFIG_HOTPLUG_CPU */
 
-static inline void cpu_hotplug_begin(void) {}
-static inline void cpu_hotplug_done(void) {}
-#define get_online_cpus()	do { } while (0)
-#define put_online_cpus()	do { } while (0)
-#define cpu_hotplug_disable()	do { } while (0)
-#define cpu_hotplug_enable()	do { } while (0)
-#endif		/* CONFIG_HOTPLUG_CPU */
+static inline void cpus_write_lock(void) { }
+static inline void cpus_write_unlock(void) { }
+static inline void cpus_read_lock(void) { }
+static inline void cpus_read_unlock(void) { }
+static inline void lockdep_assert_cpus_held(void) { }
+static inline void cpu_hotplug_disable(void) { }
+static inline void cpu_hotplug_enable(void) { }
+#endif	/* !CONFIG_HOTPLUG_CPU */
+
+/* Wrappers which go away once all code is converted */
+static inline void cpu_hotplug_begin(void) { cpus_write_lock(); }
+static inline void cpu_hotplug_done(void) { cpus_write_unlock(); }
+static inline void get_online_cpus(void) { cpus_read_lock(); }
+static inline void put_online_cpus(void) { cpus_read_unlock(); }
 
 #ifdef CONFIG_PM_SLEEP_SMP
 extern int freeze_secondary_cpus(int primary);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 7f815d9..b56573b 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -153,6 +153,11 @@ int __cpuhp_setup_state(enum cpuhp_state state,	const char *name, bool invoke,
 			int (*startup)(unsigned int cpu),
 			int (*teardown)(unsigned int cpu), bool multi_instance);
 
+int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name,
+				   bool invoke,
+				   int (*startup)(unsigned int cpu),
+				   int (*teardown)(unsigned int cpu),
+				   bool multi_instance);
 /**
  * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks
  * @state:	The state for which the calls are installed
@@ -171,6 +176,15 @@ static inline int cpuhp_setup_state(enum cpuhp_state state,
 	return __cpuhp_setup_state(state, name, true, startup, teardown, false);
 }
 
+static inline int cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
+					       const char *name,
+					       int (*startup)(unsigned int cpu),
+					       int (*teardown)(unsigned int cpu))
+{
+	return __cpuhp_setup_state_cpuslocked(state, name, true, startup,
+					      teardown, false);
+}
+
 /**
  * cpuhp_setup_state_nocalls - Setup hotplug state callbacks without calling the
  *			       callbacks
@@ -191,6 +205,15 @@ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state,
 				   false);
 }
 
+static inline int cpuhp_setup_state_nocalls_cpuslocked(enum cpuhp_state state,
+						     const char *name,
+						     int (*startup)(unsigned int cpu),
+						     int (*teardown)(unsigned int cpu))
+{
+	return __cpuhp_setup_state_cpuslocked(state, name, false, startup,
+					    teardown, false);
+}
+
 /**
  * cpuhp_setup_state_multi - Add callbacks for multi state
  * @state:	The state for which the calls are installed
@@ -217,6 +240,8 @@ static inline int cpuhp_setup_state_multi(enum cpuhp_state state,
 
 int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 			       bool invoke);
+int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
+					  struct hlist_node *node, bool invoke);
 
 /**
  * cpuhp_state_add_instance - Add an instance for a state and invoke startup
@@ -249,7 +274,15 @@ static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state,
 	return __cpuhp_state_add_instance(state, node, false);
 }
 
+static inline int
+cpuhp_state_add_instance_nocalls_cpuslocked(enum cpuhp_state state,
+					    struct hlist_node *node)
+{
+	return __cpuhp_state_add_instance_cpuslocked(state, node, false);
+}
+
 void __cpuhp_remove_state(enum cpuhp_state state, bool invoke);
+void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke);
 
 /**
  * cpuhp_remove_state - Remove hotplug state callbacks and invoke the teardown
@@ -273,6 +306,11 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state)
 	__cpuhp_remove_state(state, false);
 }
 
+static inline void cpuhp_remove_state_nocalls_cpuslocked(enum cpuhp_state state)
+{
+	__cpuhp_remove_state_cpuslocked(state, false);
+}
+
 /**
  * cpuhp_remove_multi_state - Remove hotplug multi state callback
  * @state:	The state for which the calls are removed
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 0f9e567..2f9c1f9 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -166,9 +166,6 @@ struct padata_instance {
 
 extern struct padata_instance *padata_alloc_possible(
 					struct workqueue_struct *wq);
-extern struct padata_instance *padata_alloc(struct workqueue_struct *wq,
-					    const struct cpumask *pcpumask,
-					    const struct cpumask *cbcpumask);
 extern void padata_free(struct padata_instance *pinst);
 extern int padata_do_parallel(struct padata_instance *pinst,
 			      struct padata_priv *padata, int cb_cpu);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 8039f9f..58f1ab0 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -376,6 +376,7 @@ struct pci_dev {
 	unsigned int	irq_managed:1;
 	unsigned int	has_secondary_link:1;
 	unsigned int	non_compliant_bars:1;	/* broken BARs; ignore them */
+	unsigned int	is_probed:1;		/* device probing in progress */
 	pci_dev_flags_t dev_flags;
 	atomic_t	enable_cnt;	/* pci_enable_device has been called */
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 24a6358..7d6aa29 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -801,6 +801,8 @@ struct perf_cpu_context {
 
 	struct list_head		sched_cb_entry;
 	int				sched_cb_usage;
+
+	int				online;
 };
 
 struct perf_output_handle {
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 1f0f427..9c4ca74 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1281,6 +1281,16 @@ extern struct pid *cad_pid;
 #define tsk_used_math(p)			((p)->flags & PF_USED_MATH)
 #define used_math()				tsk_used_math(current)
 
+static inline bool is_percpu_thread(void)
+{
+#ifdef CONFIG_SMP
+	return (current->flags & PF_NO_SETAFFINITY) &&
+		(current->nr_cpus_allowed  == 1);
+#else
+	return true;
+#endif
+}
+
 /* Per-process atomic flags. */
 #define PFA_NO_NEW_PRIVS		0	/* May not gain new privileges. */
 #define PFA_SPREAD_PAGE			1	/* Spread page cache over cpuset */
diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 3cc9632..3d60275 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -116,15 +116,29 @@ static inline int try_stop_cpus(const struct cpumask *cpumask,
  * @fn() runs.
  *
  * This can be thought of as a very heavy write lock, equivalent to
- * grabbing every spinlock in the kernel. */
+ * grabbing every spinlock in the kernel.
+ *
+ * Protects against CPU hotplug.
+ */
 int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
+/**
+ * stop_machine_cpuslocked: freeze the machine on all CPUs and run this function
+ * @fn: the function to run
+ * @data: the data ptr for the @fn()
+ * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
+ *
+ * Same as above. Must be called from with in a cpus_read_lock() protected
+ * region. Avoids nested calls to cpus_read_lock().
+ */
+int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
+
 int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 				   const struct cpumask *cpus);
 #else	/* CONFIG_SMP || CONFIG_HOTPLUG_CPU */
 
-static inline int stop_machine(cpu_stop_fn_t fn, void *data,
-				 const struct cpumask *cpus)
+static inline int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
+					  const struct cpumask *cpus)
 {
 	unsigned long flags;
 	int ret;
@@ -134,6 +148,12 @@ static inline int stop_machine(cpu_stop_fn_t fn, void *data,
 	return ret;
 }
 
+static inline int stop_machine(cpu_stop_fn_t fn, void *data,
+			       const struct cpumask *cpus)
+{
+	return stop_machine_cpuslocked(fn, data, cpus);
+}
+
 static inline int stop_machine_from_inactive_cpu(cpu_stop_fn_t fn, void *data,
 						 const struct cpumask *cpus)
 {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index b86b32e..b03a325 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -27,6 +27,7 @@
 #include <linux/smpboot.h>
 #include <linux/relay.h>
 #include <linux/slab.h>
+#include <linux/percpu-rwsem.h>
 
 #include <trace/events/power.h>
 #define CREATE_TRACE_POINTS
@@ -65,6 +66,12 @@ struct cpuhp_cpu_state {
 
 static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
 
+#if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP)
+static struct lock_class_key cpuhp_state_key;
+static struct lockdep_map cpuhp_state_lock_map =
+	STATIC_LOCKDEP_MAP_INIT("cpuhp_state", &cpuhp_state_key);
+#endif
+
 /**
  * cpuhp_step - Hotplug state machine step
  * @name:	Name of the step
@@ -196,121 +203,41 @@ void cpu_maps_update_done(void)
 	mutex_unlock(&cpu_add_remove_lock);
 }
 
-/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
+/*
+ * If set, cpu_up and cpu_down will return -EBUSY and do nothing.
  * Should always be manipulated under cpu_add_remove_lock
  */
 static int cpu_hotplug_disabled;
 
 #ifdef CONFIG_HOTPLUG_CPU
 
-static struct {
-	struct task_struct *active_writer;
-	/* wait queue to wake up the active_writer */
-	wait_queue_head_t wq;
-	/* verifies that no writer will get active while readers are active */
-	struct mutex lock;
-	/*
-	 * Also blocks the new readers during
-	 * an ongoing cpu hotplug operation.
-	 */
-	atomic_t refcount;
+DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock);
 
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	struct lockdep_map dep_map;
-#endif
-} cpu_hotplug = {
-	.active_writer = NULL,
-	.wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
-	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
-#ifdef CONFIG_DEBUG_LOCK_ALLOC
-	.dep_map = STATIC_LOCKDEP_MAP_INIT("cpu_hotplug.dep_map", &cpu_hotplug.dep_map),
-#endif
-};
-
-/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
-#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
-#define cpuhp_lock_acquire_tryread() \
-				  lock_map_acquire_tryread(&cpu_hotplug.dep_map)
-#define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
-#define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
-
-
-void get_online_cpus(void)
+void cpus_read_lock(void)
 {
-	might_sleep();
-	if (cpu_hotplug.active_writer == current)
-		return;
-	cpuhp_lock_acquire_read();
-	mutex_lock(&cpu_hotplug.lock);
-	atomic_inc(&cpu_hotplug.refcount);
-	mutex_unlock(&cpu_hotplug.lock);
+	percpu_down_read(&cpu_hotplug_lock);
 }
-EXPORT_SYMBOL_GPL(get_online_cpus);
+EXPORT_SYMBOL_GPL(cpus_read_lock);
 
-void put_online_cpus(void)
+void cpus_read_unlock(void)
 {
-	int refcount;
-
-	if (cpu_hotplug.active_writer == current)
-		return;
-
-	refcount = atomic_dec_return(&cpu_hotplug.refcount);
-	if (WARN_ON(refcount < 0)) /* try to fix things up */
-		atomic_inc(&cpu_hotplug.refcount);
-
-	if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
-		wake_up(&cpu_hotplug.wq);
-
-	cpuhp_lock_release();
-
+	percpu_up_read(&cpu_hotplug_lock);
 }
-EXPORT_SYMBOL_GPL(put_online_cpus);
+EXPORT_SYMBOL_GPL(cpus_read_unlock);
 
-/*
- * This ensures that the hotplug operation can begin only when the
- * refcount goes to zero.
- *
- * Note that during a cpu-hotplug operation, the new readers, if any,
- * will be blocked by the cpu_hotplug.lock
- *
- * Since cpu_hotplug_begin() is always called after invoking
- * cpu_maps_update_begin(), we can be sure that only one writer is active.
- *
- * Note that theoretically, there is a possibility of a livelock:
- * - Refcount goes to zero, last reader wakes up the sleeping
- *   writer.
- * - Last reader unlocks the cpu_hotplug.lock.
- * - A new reader arrives at this moment, bumps up the refcount.
- * - The writer acquires the cpu_hotplug.lock finds the refcount
- *   non zero and goes to sleep again.
- *
- * However, this is very difficult to achieve in practice since
- * get_online_cpus() not an api which is called all that often.
- *
- */
-void cpu_hotplug_begin(void)
+void cpus_write_lock(void)
 {
-	DEFINE_WAIT(wait);
-
-	cpu_hotplug.active_writer = current;
-	cpuhp_lock_acquire();
-
-	for (;;) {
-		mutex_lock(&cpu_hotplug.lock);
-		prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
-		if (likely(!atomic_read(&cpu_hotplug.refcount)))
-				break;
-		mutex_unlock(&cpu_hotplug.lock);
-		schedule();
-	}
-	finish_wait(&cpu_hotplug.wq, &wait);
+	percpu_down_write(&cpu_hotplug_lock);
 }
 
-void cpu_hotplug_done(void)
+void cpus_write_unlock(void)
 {
-	cpu_hotplug.active_writer = NULL;
-	mutex_unlock(&cpu_hotplug.lock);
-	cpuhp_lock_release();
+	percpu_up_write(&cpu_hotplug_lock);
+}
+
+void lockdep_assert_cpus_held(void)
+{
+	percpu_rwsem_assert_held(&cpu_hotplug_lock);
 }
 
 /*
@@ -344,8 +271,6 @@ void cpu_hotplug_enable(void)
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
 #endif	/* CONFIG_HOTPLUG_CPU */
 
-/* Notifier wrappers for transitioning to state machine */
-
 static int bringup_wait_for_ap(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
@@ -484,6 +409,7 @@ static void cpuhp_thread_fun(unsigned int cpu)
 
 	st->should_run = false;
 
+	lock_map_acquire(&cpuhp_state_lock_map);
 	/* Single callback invocation for [un]install ? */
 	if (st->single) {
 		if (st->cb_state < CPUHP_AP_ONLINE) {
@@ -510,6 +436,7 @@ static void cpuhp_thread_fun(unsigned int cpu)
 		else if (st->state > st->target)
 			ret = cpuhp_ap_offline(cpu, st);
 	}
+	lock_map_release(&cpuhp_state_lock_map);
 	st->result = ret;
 	complete(&st->done);
 }
@@ -524,6 +451,9 @@ cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
 	if (!cpu_online(cpu))
 		return 0;
 
+	lock_map_acquire(&cpuhp_state_lock_map);
+	lock_map_release(&cpuhp_state_lock_map);
+
 	/*
 	 * If we are up and running, use the hotplug thread. For early calls
 	 * we invoke the thread function directly.
@@ -567,6 +497,8 @@ static int cpuhp_kick_ap_work(unsigned int cpu)
 	enum cpuhp_state state = st->state;
 
 	trace_cpuhp_enter(cpu, st->target, state, cpuhp_kick_ap_work);
+	lock_map_acquire(&cpuhp_state_lock_map);
+	lock_map_release(&cpuhp_state_lock_map);
 	__cpuhp_kick_ap_work(st);
 	wait_for_completion(&st->done);
 	trace_cpuhp_exit(cpu, st->state, state, st->result);
@@ -630,30 +562,6 @@ void clear_tasks_mm_cpumask(int cpu)
 	rcu_read_unlock();
 }
 
-static inline void check_for_tasks(int dead_cpu)
-{
-	struct task_struct *g, *p;
-
-	read_lock(&tasklist_lock);
-	for_each_process_thread(g, p) {
-		if (!p->on_rq)
-			continue;
-		/*
-		 * We do the check with unlocked task_rq(p)->lock.
-		 * Order the reading to do not warn about a task,
-		 * which was running on this cpu in the past, and
-		 * it's just been woken on another cpu.
-		 */
-		rmb();
-		if (task_cpu(p) != dead_cpu)
-			continue;
-
-		pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n",
-			p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags);
-	}
-	read_unlock(&tasklist_lock);
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -701,7 +609,7 @@ static int takedown_cpu(unsigned int cpu)
 	/*
 	 * So now all preempt/rcu users must observe !cpu_active().
 	 */
-	err = stop_machine(take_cpu_down, NULL, cpumask_of(cpu));
+	err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu));
 	if (err) {
 		/* CPU refused to die */
 		irq_unlock_sparse();
@@ -773,7 +681,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	if (!cpu_present(cpu))
 		return -EINVAL;
 
-	cpu_hotplug_begin();
+	cpus_write_lock();
 
 	cpuhp_tasks_frozen = tasks_frozen;
 
@@ -811,7 +719,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	}
 
 out:
-	cpu_hotplug_done();
+	cpus_write_unlock();
 	return ret;
 }
 
@@ -893,7 +801,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 	struct task_struct *idle;
 	int ret = 0;
 
-	cpu_hotplug_begin();
+	cpus_write_lock();
 
 	if (!cpu_present(cpu)) {
 		ret = -EINVAL;
@@ -941,7 +849,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 	target = min((int)target, CPUHP_BRINGUP_CPU);
 	ret = cpuhp_up_callbacks(cpu, st, target);
 out:
-	cpu_hotplug_done();
+	cpus_write_unlock();
 	return ret;
 }
 
@@ -1418,18 +1326,20 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
 	}
 }
 
-int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
-			       bool invoke)
+int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state,
+					  struct hlist_node *node,
+					  bool invoke)
 {
 	struct cpuhp_step *sp;
 	int cpu;
 	int ret;
 
+	lockdep_assert_cpus_held();
+
 	sp = cpuhp_get_step(state);
 	if (sp->multi_instance == false)
 		return -EINVAL;
 
-	get_online_cpus();
 	mutex_lock(&cpuhp_state_mutex);
 
 	if (!invoke || !sp->startup.multi)
@@ -1458,13 +1368,23 @@ int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
 	hlist_add_head(node, &sp->list);
 unlock:
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
+	return ret;
+}
+
+int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
+			       bool invoke)
+{
+	int ret;
+
+	cpus_read_lock();
+	ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke);
+	cpus_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
 
 /**
- * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
+ * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state
  * @state:		The state to setup
  * @invoke:		If true, the startup function is invoked for cpus where
  *			cpu state >= @state
@@ -1473,25 +1393,27 @@ EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
  * @multi_instance:	State is set up for multiple instances which get
  *			added afterwards.
  *
+ * The caller needs to hold cpus read locked while calling this function.
  * Returns:
  *   On success:
  *      Positive state number if @state is CPUHP_AP_ONLINE_DYN
  *      0 for all other states
  *   On failure: proper (negative) error code
  */
-int __cpuhp_setup_state(enum cpuhp_state state,
-			const char *name, bool invoke,
-			int (*startup)(unsigned int cpu),
-			int (*teardown)(unsigned int cpu),
-			bool multi_instance)
+int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state,
+				   const char *name, bool invoke,
+				   int (*startup)(unsigned int cpu),
+				   int (*teardown)(unsigned int cpu),
+				   bool multi_instance)
 {
 	int cpu, ret = 0;
 	bool dynstate;
 
+	lockdep_assert_cpus_held();
+
 	if (cpuhp_cb_check(state) || !name)
 		return -EINVAL;
 
-	get_online_cpus();
 	mutex_lock(&cpuhp_state_mutex);
 
 	ret = cpuhp_store_callbacks(state, name, startup, teardown,
@@ -1527,7 +1449,6 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 	}
 out:
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
 	/*
 	 * If the requested state is CPUHP_AP_ONLINE_DYN, return the
 	 * dynamically allocated state in case of success.
@@ -1536,6 +1457,22 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 		return state;
 	return ret;
 }
+EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked);
+
+int __cpuhp_setup_state(enum cpuhp_state state,
+			const char *name, bool invoke,
+			int (*startup)(unsigned int cpu),
+			int (*teardown)(unsigned int cpu),
+			bool multi_instance)
+{
+	int ret;
+
+	cpus_read_lock();
+	ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup,
+					     teardown, multi_instance);
+	cpus_read_unlock();
+	return ret;
+}
 EXPORT_SYMBOL(__cpuhp_setup_state);
 
 int __cpuhp_state_remove_instance(enum cpuhp_state state,
@@ -1549,7 +1486,7 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 	if (!sp->multi_instance)
 		return -EINVAL;
 
-	get_online_cpus();
+	cpus_read_lock();
 	mutex_lock(&cpuhp_state_mutex);
 
 	if (!invoke || !cpuhp_get_teardown_cb(state))
@@ -1570,29 +1507,30 @@ int __cpuhp_state_remove_instance(enum cpuhp_state state,
 remove:
 	hlist_del(node);
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
+	cpus_read_unlock();
 
 	return 0;
 }
 EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
 
 /**
- * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
+ * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state
  * @state:	The state to remove
  * @invoke:	If true, the teardown function is invoked for cpus where
  *		cpu state >= @state
  *
+ * The caller needs to hold cpus read locked while calling this function.
  * The teardown callback is currently not allowed to fail. Think
  * about module removal!
  */
-void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
+void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke)
 {
 	struct cpuhp_step *sp = cpuhp_get_step(state);
 	int cpu;
 
 	BUG_ON(cpuhp_cb_check(state));
 
-	get_online_cpus();
+	lockdep_assert_cpus_held();
 
 	mutex_lock(&cpuhp_state_mutex);
 	if (sp->multi_instance) {
@@ -1620,7 +1558,14 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 remove:
 	cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
 	mutex_unlock(&cpuhp_state_mutex);
-	put_online_cpus();
+}
+EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked);
+
+void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
+{
+	cpus_read_lock();
+	__cpuhp_remove_state_cpuslocked(state, invoke);
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL(__cpuhp_remove_state);
 
@@ -1689,7 +1634,7 @@ static struct attribute *cpuhp_cpu_attrs[] = {
 	NULL
 };
 
-static struct attribute_group cpuhp_cpu_attr_group = {
+static const struct attribute_group cpuhp_cpu_attr_group = {
 	.attrs = cpuhp_cpu_attrs,
 	.name = "hotplug",
 	NULL
@@ -1721,7 +1666,7 @@ static struct attribute *cpuhp_cpu_root_attrs[] = {
 	NULL
 };
 
-static struct attribute_group cpuhp_cpu_root_attr_group = {
+static const struct attribute_group cpuhp_cpu_root_attr_group = {
 	.attrs = cpuhp_cpu_root_attrs,
 	.name = "hotplug",
 	NULL
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc63f8d..4d2c32f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -389,6 +389,7 @@ static atomic_t nr_switch_events __read_mostly;
 static LIST_HEAD(pmus);
 static DEFINE_MUTEX(pmus_lock);
 static struct srcu_struct pmus_srcu;
+static cpumask_var_t perf_online_mask;
 
 /*
  * perf event paranoia level:
@@ -3807,14 +3808,6 @@ find_get_context(struct pmu *pmu, struct task_struct *task,
 		if (perf_paranoid_cpu() && !capable(CAP_SYS_ADMIN))
 			return ERR_PTR(-EACCES);
 
-		/*
-		 * We could be clever and allow to attach a event to an
-		 * offline CPU and activate it when the CPU comes up, but
-		 * that's for later.
-		 */
-		if (!cpu_online(cpu))
-			return ERR_PTR(-ENODEV);
-
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
 		ctx = &cpuctx->ctx;
 		get_ctx(ctx);
@@ -7723,7 +7716,8 @@ static int swevent_hlist_get_cpu(int cpu)
 	int err = 0;
 
 	mutex_lock(&swhash->hlist_mutex);
-	if (!swevent_hlist_deref(swhash) && cpu_online(cpu)) {
+	if (!swevent_hlist_deref(swhash) &&
+	    cpumask_test_cpu(cpu, perf_online_mask)) {
 		struct swevent_hlist *hlist;
 
 		hlist = kzalloc(sizeof(*hlist), GFP_KERNEL);
@@ -7744,7 +7738,7 @@ static int swevent_hlist_get(void)
 {
 	int err, cpu, failed_cpu;
 
-	get_online_cpus();
+	mutex_lock(&pmus_lock);
 	for_each_possible_cpu(cpu) {
 		err = swevent_hlist_get_cpu(cpu);
 		if (err) {
@@ -7752,8 +7746,7 @@ static int swevent_hlist_get(void)
 			goto fail;
 		}
 	}
-	put_online_cpus();
-
+	mutex_unlock(&pmus_lock);
 	return 0;
 fail:
 	for_each_possible_cpu(cpu) {
@@ -7761,8 +7754,7 @@ static int swevent_hlist_get(void)
 			break;
 		swevent_hlist_put_cpu(cpu);
 	}
-
-	put_online_cpus();
+	mutex_unlock(&pmus_lock);
 	return err;
 }
 
@@ -8940,7 +8932,7 @@ perf_event_mux_interval_ms_store(struct device *dev,
 	pmu->hrtimer_interval_ms = timer;
 
 	/* update all cpuctx for this PMU */
-	get_online_cpus();
+	cpus_read_lock();
 	for_each_online_cpu(cpu) {
 		struct perf_cpu_context *cpuctx;
 		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
@@ -8949,7 +8941,7 @@ perf_event_mux_interval_ms_store(struct device *dev,
 		cpu_function_call(cpu,
 			(remote_function_f)perf_mux_hrtimer_restart, cpuctx);
 	}
-	put_online_cpus();
+	cpus_read_unlock();
 	mutex_unlock(&mux_interval_mutex);
 
 	return count;
@@ -9079,6 +9071,7 @@ int perf_pmu_register(struct pmu *pmu, const char *name, int type)
 		lockdep_set_class(&cpuctx->ctx.mutex, &cpuctx_mutex);
 		lockdep_set_class(&cpuctx->ctx.lock, &cpuctx_lock);
 		cpuctx->ctx.pmu = pmu;
+		cpuctx->online = cpumask_test_cpu(cpu, perf_online_mask);
 
 		__perf_mux_hrtimer_init(cpuctx, cpu);
 	}
@@ -9903,12 +9896,10 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_task;
 	}
 
-	get_online_cpus();
-
 	if (task) {
 		err = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
 		if (err)
-			goto err_cpus;
+			goto err_task;
 
 		/*
 		 * Reuse ptrace permission checks for now.
@@ -10094,6 +10085,23 @@ SYSCALL_DEFINE5(perf_event_open,
 		goto err_locked;
 	}
 
+	if (!task) {
+		/*
+		 * Check if the @cpu we're creating an event for is online.
+		 *
+		 * We use the perf_cpu_context::ctx::mutex to serialize against
+		 * the hotplug notifiers. See perf_event_{init,exit}_cpu().
+		 */
+		struct perf_cpu_context *cpuctx =
+			container_of(ctx, struct perf_cpu_context, ctx);
+
+		if (!cpuctx->online) {
+			err = -ENODEV;
+			goto err_locked;
+		}
+	}
+
+
 	/*
 	 * Must be under the same ctx::mutex as perf_install_in_context(),
 	 * because we need to serialize with concurrent event creation.
@@ -10183,8 +10191,6 @@ SYSCALL_DEFINE5(perf_event_open,
 		put_task_struct(task);
 	}
 
-	put_online_cpus();
-
 	mutex_lock(&current->perf_event_mutex);
 	list_add_tail(&event->owner_entry, &current->perf_event_list);
 	mutex_unlock(&current->perf_event_mutex);
@@ -10218,8 +10224,6 @@ SYSCALL_DEFINE5(perf_event_open,
 err_cred:
 	if (task)
 		mutex_unlock(&task->signal->cred_guard_mutex);
-err_cpus:
-	put_online_cpus();
 err_task:
 	if (task)
 		put_task_struct(task);
@@ -10274,6 +10278,21 @@ perf_event_create_kernel_counter(struct perf_event_attr *attr, int cpu,
 		goto err_unlock;
 	}
 
+	if (!task) {
+		/*
+		 * Check if the @cpu we're creating an event for is online.
+		 *
+		 * We use the perf_cpu_context::ctx::mutex to serialize against
+		 * the hotplug notifiers. See perf_event_{init,exit}_cpu().
+		 */
+		struct perf_cpu_context *cpuctx =
+			container_of(ctx, struct perf_cpu_context, ctx);
+		if (!cpuctx->online) {
+			err = -ENODEV;
+			goto err_unlock;
+		}
+	}
+
 	if (!exclusive_event_installable(event, ctx)) {
 		err = -EBUSY;
 		goto err_unlock;
@@ -10941,6 +10960,8 @@ static void __init perf_event_init_all_cpus(void)
 	struct swevent_htable *swhash;
 	int cpu;
 
+	zalloc_cpumask_var(&perf_online_mask, GFP_KERNEL);
+
 	for_each_possible_cpu(cpu) {
 		swhash = &per_cpu(swevent_htable, cpu);
 		mutex_init(&swhash->hlist_mutex);
@@ -10956,7 +10977,7 @@ static void __init perf_event_init_all_cpus(void)
 	}
 }
 
-int perf_event_init_cpu(unsigned int cpu)
+void perf_swevent_init_cpu(unsigned int cpu)
 {
 	struct swevent_htable *swhash = &per_cpu(swevent_htable, cpu);
 
@@ -10969,7 +10990,6 @@ int perf_event_init_cpu(unsigned int cpu)
 		rcu_assign_pointer(swhash->swevent_hlist, hlist);
 	}
 	mutex_unlock(&swhash->hlist_mutex);
-	return 0;
 }
 
 #if defined CONFIG_HOTPLUG_CPU || defined CONFIG_KEXEC_CORE
@@ -10987,19 +11007,22 @@ static void __perf_event_exit_context(void *__info)
 
 static void perf_event_exit_cpu_context(int cpu)
 {
+	struct perf_cpu_context *cpuctx;
 	struct perf_event_context *ctx;
 	struct pmu *pmu;
-	int idx;
 
-	idx = srcu_read_lock(&pmus_srcu);
-	list_for_each_entry_rcu(pmu, &pmus, entry) {
-		ctx = &per_cpu_ptr(pmu->pmu_cpu_context, cpu)->ctx;
+	mutex_lock(&pmus_lock);
+	list_for_each_entry(pmu, &pmus, entry) {
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
 
 		mutex_lock(&ctx->mutex);
 		smp_call_function_single(cpu, __perf_event_exit_context, ctx, 1);
+		cpuctx->online = 0;
 		mutex_unlock(&ctx->mutex);
 	}
-	srcu_read_unlock(&pmus_srcu, idx);
+	cpumask_clear_cpu(cpu, perf_online_mask);
+	mutex_unlock(&pmus_lock);
 }
 #else
 
@@ -11007,6 +11030,29 @@ static void perf_event_exit_cpu_context(int cpu) { }
 
 #endif
 
+int perf_event_init_cpu(unsigned int cpu)
+{
+	struct perf_cpu_context *cpuctx;
+	struct perf_event_context *ctx;
+	struct pmu *pmu;
+
+	perf_swevent_init_cpu(cpu);
+
+	mutex_lock(&pmus_lock);
+	cpumask_set_cpu(cpu, perf_online_mask);
+	list_for_each_entry(pmu, &pmus, entry) {
+		cpuctx = per_cpu_ptr(pmu->pmu_cpu_context, cpu);
+		ctx = &cpuctx->ctx;
+
+		mutex_lock(&ctx->mutex);
+		cpuctx->online = 1;
+		mutex_unlock(&ctx->mutex);
+	}
+	mutex_unlock(&pmus_lock);
+
+	return 0;
+}
+
 int perf_event_exit_cpu(unsigned int cpu)
 {
 	perf_event_exit_cpu_context(cpu);
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 6c9cb20..d11c506 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -15,6 +15,7 @@
 #include <linux/static_key.h>
 #include <linux/jump_label_ratelimit.h>
 #include <linux/bug.h>
+#include <linux/cpu.h>
 
 #ifdef HAVE_JUMP_LABEL
 
@@ -124,6 +125,7 @@ void static_key_slow_inc(struct static_key *key)
 			return;
 	}
 
+	cpus_read_lock();
 	jump_label_lock();
 	if (atomic_read(&key->enabled) == 0) {
 		atomic_set(&key->enabled, -1);
@@ -133,12 +135,14 @@ void static_key_slow_inc(struct static_key *key)
 		atomic_inc(&key->enabled);
 	}
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 EXPORT_SYMBOL_GPL(static_key_slow_inc);
 
 static void __static_key_slow_dec(struct static_key *key,
 		unsigned long rate_limit, struct delayed_work *work)
 {
+	cpus_read_lock();
 	/*
 	 * The negative count check is valid even when a negative
 	 * key->enabled is in use by static_key_slow_inc(); a
@@ -149,6 +153,7 @@ static void __static_key_slow_dec(struct static_key *key,
 	if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
 		WARN(atomic_read(&key->enabled) < 0,
 		     "jump label: negative count!\n");
+		cpus_read_unlock();
 		return;
 	}
 
@@ -159,6 +164,7 @@ static void __static_key_slow_dec(struct static_key *key,
 		jump_label_update(key);
 	}
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 static void jump_label_update_timeout(struct work_struct *work)
@@ -334,6 +340,7 @@ void __init jump_label_init(void)
 	if (static_key_initialized)
 		return;
 
+	cpus_read_lock();
 	jump_label_lock();
 	jump_label_sort_entries(iter_start, iter_stop);
 
@@ -353,6 +360,7 @@ void __init jump_label_init(void)
 	}
 	static_key_initialized = true;
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 #ifdef CONFIG_MODULES
@@ -590,28 +598,28 @@ jump_label_module_notify(struct notifier_block *self, unsigned long val,
 	struct module *mod = data;
 	int ret = 0;
 
+	cpus_read_lock();
+	jump_label_lock();
+
 	switch (val) {
 	case MODULE_STATE_COMING:
-		jump_label_lock();
 		ret = jump_label_add_module(mod);
 		if (ret) {
 			WARN(1, "Failed to allocatote memory: jump_label may not work properly.\n");
 			jump_label_del_module(mod);
 		}
-		jump_label_unlock();
 		break;
 	case MODULE_STATE_GOING:
-		jump_label_lock();
 		jump_label_del_module(mod);
-		jump_label_unlock();
 		break;
 	case MODULE_STATE_LIVE:
-		jump_label_lock();
 		jump_label_invalidate_module_init(mod);
-		jump_label_unlock();
 		break;
 	}
 
+	jump_label_unlock();
+	cpus_read_unlock();
+
 	return notifier_from_errno(ret);
 }
 
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index adfe3b4..6756d75 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -483,11 +483,6 @@ static DECLARE_DELAYED_WORK(optimizing_work, kprobe_optimizer);
  */
 static void do_optimize_kprobes(void)
 {
-	/* Optimization never be done when disarmed */
-	if (kprobes_all_disarmed || !kprobes_allow_optimization ||
-	    list_empty(&optimizing_list))
-		return;
-
 	/*
 	 * The optimization/unoptimization refers online_cpus via
 	 * stop_machine() and cpu-hotplug modifies online_cpus.
@@ -495,14 +490,19 @@ static void do_optimize_kprobes(void)
 	 * This combination can cause a deadlock (cpu-hotplug try to lock
 	 * text_mutex but stop_machine can not be done because online_cpus
 	 * has been changed)
-	 * To avoid this deadlock, we need to call get_online_cpus()
+	 * To avoid this deadlock, caller must have locked cpu hotplug
 	 * for preventing cpu-hotplug outside of text_mutex locking.
 	 */
-	get_online_cpus();
+	lockdep_assert_cpus_held();
+
+	/* Optimization never be done when disarmed */
+	if (kprobes_all_disarmed || !kprobes_allow_optimization ||
+	    list_empty(&optimizing_list))
+		return;
+
 	mutex_lock(&text_mutex);
 	arch_optimize_kprobes(&optimizing_list);
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 /*
@@ -513,12 +513,13 @@ static void do_unoptimize_kprobes(void)
 {
 	struct optimized_kprobe *op, *tmp;
 
+	/* See comment in do_optimize_kprobes() */
+	lockdep_assert_cpus_held();
+
 	/* Unoptimization must be done anytime */
 	if (list_empty(&unoptimizing_list))
 		return;
 
-	/* Ditto to do_optimize_kprobes */
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 	arch_unoptimize_kprobes(&unoptimizing_list, &freeing_list);
 	/* Loop free_list for disarming */
@@ -537,7 +538,6 @@ static void do_unoptimize_kprobes(void)
 			list_del_init(&op->list);
 	}
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 }
 
 /* Reclaim all kprobes on the free_list */
@@ -562,6 +562,7 @@ static void kick_kprobe_optimizer(void)
 static void kprobe_optimizer(struct work_struct *work)
 {
 	mutex_lock(&kprobe_mutex);
+	cpus_read_lock();
 	/* Lock modules while optimizing kprobes */
 	mutex_lock(&module_mutex);
 
@@ -587,6 +588,7 @@ static void kprobe_optimizer(struct work_struct *work)
 	do_free_cleaned_kprobes();
 
 	mutex_unlock(&module_mutex);
+	cpus_read_unlock();
 	mutex_unlock(&kprobe_mutex);
 
 	/* Step 5: Kick optimizer again if needed */
@@ -650,9 +652,8 @@ static void optimize_kprobe(struct kprobe *p)
 /* Short cut to direct unoptimizing */
 static void force_unoptimize_kprobe(struct optimized_kprobe *op)
 {
-	get_online_cpus();
+	lockdep_assert_cpus_held();
 	arch_unoptimize_kprobe(op);
-	put_online_cpus();
 	if (kprobe_disabled(&op->kp))
 		arch_disarm_kprobe(&op->kp);
 }
@@ -791,6 +792,7 @@ static void try_to_optimize_kprobe(struct kprobe *p)
 		return;
 
 	/* For preparing optimization, jump_label_text_reserved() is called */
+	cpus_read_lock();
 	jump_label_lock();
 	mutex_lock(&text_mutex);
 
@@ -812,6 +814,7 @@ static void try_to_optimize_kprobe(struct kprobe *p)
 out:
 	mutex_unlock(&text_mutex);
 	jump_label_unlock();
+	cpus_read_unlock();
 }
 
 #ifdef CONFIG_SYSCTL
@@ -826,6 +829,7 @@ static void optimize_all_kprobes(void)
 	if (kprobes_allow_optimization)
 		goto out;
 
+	cpus_read_lock();
 	kprobes_allow_optimization = true;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
@@ -833,6 +837,7 @@ static void optimize_all_kprobes(void)
 			if (!kprobe_disabled(p))
 				optimize_kprobe(p);
 	}
+	cpus_read_unlock();
 	printk(KERN_INFO "Kprobes globally optimized\n");
 out:
 	mutex_unlock(&kprobe_mutex);
@@ -851,6 +856,7 @@ static void unoptimize_all_kprobes(void)
 		return;
 	}
 
+	cpus_read_lock();
 	kprobes_allow_optimization = false;
 	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		head = &kprobe_table[i];
@@ -859,6 +865,7 @@ static void unoptimize_all_kprobes(void)
 				unoptimize_kprobe(p, false);
 		}
 	}
+	cpus_read_unlock();
 	mutex_unlock(&kprobe_mutex);
 
 	/* Wait for unoptimizing completion */
@@ -1010,14 +1017,11 @@ static void arm_kprobe(struct kprobe *kp)
 		arm_kprobe_ftrace(kp);
 		return;
 	}
-	/*
-	 * Here, since __arm_kprobe() doesn't use stop_machine(),
-	 * this doesn't cause deadlock on text_mutex. So, we don't
-	 * need get_online_cpus().
-	 */
+	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	__arm_kprobe(kp);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 }
 
 /* Disarm a kprobe with text_mutex */
@@ -1027,10 +1031,12 @@ static void disarm_kprobe(struct kprobe *kp, bool reopt)
 		disarm_kprobe_ftrace(kp);
 		return;
 	}
-	/* Ditto */
+
+	cpus_read_lock();
 	mutex_lock(&text_mutex);
 	__disarm_kprobe(kp, reopt);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 }
 
 /*
@@ -1298,13 +1304,10 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
 	int ret = 0;
 	struct kprobe *ap = orig_p;
 
+	cpus_read_lock();
+
 	/* For preparing optimization, jump_label_text_reserved() is called */
 	jump_label_lock();
-	/*
-	 * Get online CPUs to avoid text_mutex deadlock.with stop machine,
-	 * which is invoked by unoptimize_kprobe() in add_new_kprobe()
-	 */
-	get_online_cpus();
 	mutex_lock(&text_mutex);
 
 	if (!kprobe_aggrprobe(orig_p)) {
@@ -1352,8 +1355,8 @@ static int register_aggr_kprobe(struct kprobe *orig_p, struct kprobe *p)
 
 out:
 	mutex_unlock(&text_mutex);
-	put_online_cpus();
 	jump_label_unlock();
+	cpus_read_unlock();
 
 	if (ret == 0 && kprobe_disabled(ap) && !kprobe_disabled(p)) {
 		ap->flags &= ~KPROBE_FLAG_DISABLED;
@@ -1555,9 +1558,12 @@ int register_kprobe(struct kprobe *p)
 		goto out;
 	}
 
-	mutex_lock(&text_mutex);	/* Avoiding text modification */
+	cpus_read_lock();
+	/* Prevent text modification */
+	mutex_lock(&text_mutex);
 	ret = prepare_kprobe(p);
 	mutex_unlock(&text_mutex);
+	cpus_read_unlock();
 	if (ret)
 		goto out;
 
@@ -1570,7 +1576,6 @@ int register_kprobe(struct kprobe *p)
 
 	/* Try to optimize kprobe */
 	try_to_optimize_kprobe(p);
-
 out:
 	mutex_unlock(&kprobe_mutex);
 
diff --git a/kernel/padata.c b/kernel/padata.c
index ac8f1e5..868f947 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -934,29 +934,18 @@ static struct kobj_type padata_attr_type = {
 };
 
 /**
- * padata_alloc_possible - Allocate and initialize padata instance.
- *                         Use the cpu_possible_mask for serial and
- *                         parallel workers.
- *
- * @wq: workqueue to use for the allocated padata instance
- */
-struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq)
-{
-	return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask);
-}
-EXPORT_SYMBOL(padata_alloc_possible);
-
-/**
  * padata_alloc - allocate and initialize a padata instance and specify
  *                cpumasks for serial and parallel workers.
  *
  * @wq: workqueue to use for the allocated padata instance
  * @pcpumask: cpumask that will be used for padata parallelization
  * @cbcpumask: cpumask that will be used for padata serialization
+ *
+ * Must be called from a cpus_read_lock() protected region
  */
-struct padata_instance *padata_alloc(struct workqueue_struct *wq,
-				     const struct cpumask *pcpumask,
-				     const struct cpumask *cbcpumask)
+static struct padata_instance *padata_alloc(struct workqueue_struct *wq,
+					    const struct cpumask *pcpumask,
+					    const struct cpumask *cbcpumask)
 {
 	struct padata_instance *pinst;
 	struct parallel_data *pd = NULL;
@@ -965,7 +954,6 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 	if (!pinst)
 		goto err;
 
-	get_online_cpus();
 	if (!alloc_cpumask_var(&pinst->cpumask.pcpu, GFP_KERNEL))
 		goto err_free_inst;
 	if (!alloc_cpumask_var(&pinst->cpumask.cbcpu, GFP_KERNEL)) {
@@ -989,14 +977,12 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 
 	pinst->flags = 0;
 
-	put_online_cpus();
-
 	BLOCKING_INIT_NOTIFIER_HEAD(&pinst->cpumask_change_notifier);
 	kobject_init(&pinst->kobj, &padata_attr_type);
 	mutex_init(&pinst->lock);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	cpuhp_state_add_instance_nocalls(hp_online, &pinst->node);
+	cpuhp_state_add_instance_nocalls_cpuslocked(hp_online, &pinst->node);
 #endif
 	return pinst;
 
@@ -1005,12 +991,27 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 	free_cpumask_var(pinst->cpumask.cbcpu);
 err_free_inst:
 	kfree(pinst);
-	put_online_cpus();
 err:
 	return NULL;
 }
 
 /**
+ * padata_alloc_possible - Allocate and initialize padata instance.
+ *                         Use the cpu_possible_mask for serial and
+ *                         parallel workers.
+ *
+ * @wq: workqueue to use for the allocated padata instance
+ *
+ * Must be called from a cpus_read_lock() protected region
+ */
+struct padata_instance *padata_alloc_possible(struct workqueue_struct *wq)
+{
+	lockdep_assert_cpus_held();
+	return padata_alloc(wq, cpu_possible_mask, cpu_possible_mask);
+}
+EXPORT_SYMBOL(padata_alloc_possible);
+
+/**
  * padata_free - free a padata instance
  *
  * @padata_inst: padata instance to free
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index 1eb8266..b759126 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -552,7 +552,8 @@ static int __init cpu_stop_init(void)
 }
 early_initcall(cpu_stop_init);
 
-static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
+int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data,
+			    const struct cpumask *cpus)
 {
 	struct multi_stop_data msdata = {
 		.fn = fn,
@@ -561,6 +562,8 @@ static int __stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cp
 		.active_cpus = cpus,
 	};
 
+	lockdep_assert_cpus_held();
+
 	if (!stop_machine_initialized) {
 		/*
 		 * Handle the case where stop_machine() is called
@@ -590,9 +593,9 @@ int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus)
 	int ret;
 
 	/* No CPUs can come up or down during this. */
-	get_online_cpus();
-	ret = __stop_machine(fn, data, cpus);
-	put_online_cpus();
+	cpus_read_lock();
+	ret = stop_machine_cpuslocked(fn, data, cpus);
+	cpus_read_unlock();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(stop_machine);