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

Pull CPU hotplug updates from Thomas Gleixner:
 "Yet another batch of cpu hotplug core updates and conversions:

   - Provide core infrastructure for multi instance drivers so the
     drivers do not have to keep custom lists.

   - Convert custom lists to the new infrastructure. The block-mq custom
     list conversion comes through the block tree and makes the diffstat
     tip over to more lines removed than added.

   - Handle unbalanced hotplug enable/disable calls more gracefully.

   - Remove the obsolete CPU_STARTING/DYING notifier support.

   - Convert another batch of notifier users.

   The relayfs changes which conflicted with the conversion have been
   shipped to me by Andrew.

   The remaining lot is targeted for 4.10 so that we finally can remove
   the rest of the notifiers"

* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (46 commits)
  cpufreq: Fix up conversion to hotplug state machine
  blk/mq: Reserve hotplug states for block multiqueue
  x86/apic/uv: Convert to hotplug state machine
  s390/mm/pfault: Convert to hotplug state machine
  mips/loongson/smp: Convert to hotplug state machine
  mips/octeon/smp: Convert to hotplug state machine
  fault-injection/cpu: Convert to hotplug state machine
  padata: Convert to hotplug state machine
  cpufreq: Convert to hotplug state machine
  ACPI/processor: Convert to hotplug state machine
  virtio scsi: Convert to hotplug state machine
  oprofile/timer: Convert to hotplug state machine
  block/softirq: Convert to hotplug state machine
  lib/irq_poll: Convert to hotplug state machine
  x86/microcode: Convert to hotplug state machine
  sh/SH-X3 SMP: Convert to hotplug state machine
  ia64/mca: Convert to hotplug state machine
  ARM/OMAP/wakeupgen: Convert to hotplug state machine
  ARM/shmobile: Convert to hotplug state machine
  arm64/FP/SIMD: Convert to hotplug state machine
  ...

arch/arm/mach-omap2/omap-wakeupgen.c

@@ -322,34 +322,25 @@ static void irq_save_secure_context(void)
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int irq_cpu_hotplug_notify(struct notifier_block *self,
-				  unsigned long action, void *hcpu)
+static int omap_wakeupgen_cpu_online(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned int)hcpu;
-
-	/*
-	 * Corresponding FROZEN transitions do not have to be handled,
-	 * they are handled by at a higher level
-	 * (drivers/cpuidle/coupled.c).
-	 */
-	switch (action) {
-	case CPU_ONLINE:
-		wakeupgen_irqmask_all(cpu, 0);
-		break;
-	case CPU_DEAD:
-		wakeupgen_irqmask_all(cpu, 1);
-		break;
-	}
-	return NOTIFY_OK;
+	wakeupgen_irqmask_all(cpu, 0);
+	return 0;
 }
 
-static struct notifier_block irq_hotplug_notifier = {
-	.notifier_call = irq_cpu_hotplug_notify,
-};
+static int omap_wakeupgen_cpu_dead(unsigned int cpu)
+{
+	wakeupgen_irqmask_all(cpu, 1);
+	return 0;
+}
 
 static void __init irq_hotplug_init(void)
 {
-	register_hotcpu_notifier(&irq_hotplug_notifier);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "arm/omap-wake:online",
+				  omap_wakeupgen_cpu_online, NULL);
+	cpuhp_setup_state_nocalls(CPUHP_ARM_OMAP_WAKE_DEAD,
+				  "arm/omap-wake:dead", NULL,
+				  omap_wakeupgen_cpu_dead);
 }
 #else
 static void __init irq_hotplug_init(void)

arch/arm/mach-shmobile/platsmp-scu.c

@@ -21,26 +21,14 @@
 static phys_addr_t shmobile_scu_base_phys;
 static void __iomem *shmobile_scu_base;
 
-static int shmobile_smp_scu_notifier_call(struct notifier_block *nfb,
-					  unsigned long action, void *hcpu)
+static int shmobile_scu_cpu_prepare(unsigned int cpu)
 {
-	unsigned int cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-		/* For this particular CPU register SCU SMP boot vector */
-		shmobile_smp_hook(cpu, virt_to_phys(shmobile_boot_scu),
-				  shmobile_scu_base_phys);
-		break;
-	};
-
-	return NOTIFY_OK;
+	/* For this particular CPU register SCU SMP boot vector */
+	shmobile_smp_hook(cpu, virt_to_phys(shmobile_boot_scu),
+			  shmobile_scu_base_phys);
+	return 0;
 }
 
-static struct notifier_block shmobile_smp_scu_notifier = {
-	.notifier_call = shmobile_smp_scu_notifier_call,
-};
-
 void __init shmobile_smp_scu_prepare_cpus(phys_addr_t scu_base_phys,
 					  unsigned int max_cpus)
 {
@@ -54,7 +42,9 @@ void __init shmobile_smp_scu_prepare_cpus(phys_addr_t scu_base_phys,
 	scu_power_mode(shmobile_scu_base, SCU_PM_NORMAL);
 
 	/* Use CPU notifier for reset vector control */
-	register_cpu_notifier(&shmobile_smp_scu_notifier);
+	cpuhp_setup_state_nocalls(CPUHP_ARM_SHMOBILE_SCU_PREPARE,
+				  "arm/shmobile-scu:prepare",
+				  shmobile_scu_cpu_prepare, NULL);
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

arch/arm64/kernel/fpsimd.c

@@ -299,28 +299,16 @@ static inline void fpsimd_pm_init(void) { }
 #endif /* CONFIG_CPU_PM */
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int fpsimd_cpu_hotplug_notifier(struct notifier_block *nfb,
-				       unsigned long action,
-				       void *hcpu)
+static int fpsimd_cpu_dead(unsigned int cpu)
 {
-	unsigned int cpu = (long)hcpu;
-
-	switch (action) {
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		per_cpu(fpsimd_last_state, cpu) = NULL;
-		break;
-	}
-	return NOTIFY_OK;
+	per_cpu(fpsimd_last_state, cpu) = NULL;
+	return 0;
 }
 
-static struct notifier_block fpsimd_cpu_hotplug_notifier_block = {
-	.notifier_call = fpsimd_cpu_hotplug_notifier,
-};
-
 static inline void fpsimd_hotplug_init(void)
 {
-	register_cpu_notifier(&fpsimd_cpu_hotplug_notifier_block);
+	cpuhp_setup_state_nocalls(CPUHP_ARM64_FPSIMD_DEAD, "arm64/fpsimd:dead",
+				  NULL, fpsimd_cpu_dead);
 }
 
 #else

arch/ia64/kernel/mca.c

@@ -1890,7 +1890,7 @@ ia64_mca_cpu_init(void *cpu_data)
 							      PAGE_KERNEL)));
 }
 
-static void ia64_mca_cmc_vector_adjust(void *dummy)
+static int ia64_mca_cpu_online(unsigned int cpu)
 {
 	unsigned long flags;
 
@@ -1898,25 +1898,9 @@ static void ia64_mca_cmc_vector_adjust(void *dummy)
 	if (!cmc_polling_enabled)
 		ia64_mca_cmc_vector_enable(NULL);
 	local_irq_restore(flags);
+	return 0;
 }
 
-static int mca_cpu_callback(struct notifier_block *nfb,
-				      unsigned long action,
-				      void *hcpu)
-{
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		ia64_mca_cmc_vector_adjust(NULL);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block mca_cpu_notifier = {
-	.notifier_call = mca_cpu_callback
-};
-
 /*
  * ia64_mca_init
  *
@@ -2111,15 +2095,13 @@ ia64_mca_late_init(void)
 	if (!mca_init)
 		return 0;
 
-	register_hotcpu_notifier(&mca_cpu_notifier);
-
 	/* Setup the CMCI/P vector and handler */
 	setup_timer(&cmc_poll_timer, ia64_mca_cmc_poll, 0UL);
 
 	/* Unmask/enable the vector */
 	cmc_polling_enabled = 0;
-	schedule_work(&cmc_enable_work);
-
+	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "ia64/mca:online",
+			  ia64_mca_cpu_online, NULL);
 	IA64_MCA_DEBUG("%s: CMCI/P setup and enabled.\n", __func__);
 
 #ifdef CONFIG_ACPI

arch/mips/cavium-octeon/smp.c

@@ -380,29 +380,11 @@ static int octeon_update_boot_vector(unsigned int cpu)
 	return 0;
 }
 
-static int octeon_cpu_callback(struct notifier_block *nfb,
-	unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		octeon_update_boot_vector(cpu);
-		break;
-	case CPU_ONLINE:
-		pr_info("Cpu %d online\n", cpu);
-		break;
-	case CPU_DEAD:
-		break;
-	}
-
-	return NOTIFY_OK;
-}
-
 static int register_cavium_notifier(void)
 {
-	hotcpu_notifier(octeon_cpu_callback, 0);
-	return 0;
+	return cpuhp_setup_state_nocalls(CPUHP_MIPS_SOC_PREPARE,
+					 "mips/cavium:prepare",
+					 octeon_update_boot_vector, NULL);
 }
 late_initcall(register_cavium_notifier);
 

arch/mips/loongson64/loongson-3/smp.c

@@ -677,7 +677,7 @@ void play_dead(void)
 	play_dead_at_ckseg1(state_addr);
 }
 
-void loongson3_disable_clock(int cpu)
+static int loongson3_disable_clock(unsigned int cpu)
 {
 	uint64_t core_id = cpu_data[cpu].core;
 	uint64_t package_id = cpu_data[cpu].package;
@@ -688,9 +688,10 @@ void loongson3_disable_clock(int cpu)
 		if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG))
 			LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3));
 	}
+	return 0;
 }
 
-void loongson3_enable_clock(int cpu)
+static int loongson3_enable_clock(unsigned int cpu)
 {
 	uint64_t core_id = cpu_data[cpu].core;
 	uint64_t package_id = cpu_data[cpu].package;
@@ -701,34 +702,15 @@ void loongson3_enable_clock(int cpu)
 		if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG))
 			LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3);
 	}
-}
-
-#define CPU_POST_DEAD_FROZEN	(CPU_POST_DEAD | CPU_TASKS_FROZEN)
-static int loongson3_cpu_callback(struct notifier_block *nfb,
-	unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action) {
-	case CPU_POST_DEAD:
-	case CPU_POST_DEAD_FROZEN:
-		pr_info("Disable clock for CPU#%d\n", cpu);
-		loongson3_disable_clock(cpu);
-		break;
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		pr_info("Enable clock for CPU#%d\n", cpu);
-		loongson3_enable_clock(cpu);
-		break;
-	}
-
-	return NOTIFY_OK;
+	return 0;
 }
 
 static int register_loongson3_notifier(void)
 {
-	hotcpu_notifier(loongson3_cpu_callback, 0);
-	return 0;
+	return cpuhp_setup_state_nocalls(CPUHP_MIPS_SOC_PREPARE,
+					 "mips/loongson:prepare",
+					 loongson3_enable_clock,
+					 loongson3_disable_clock);
 }
 early_initcall(register_loongson3_notifier);
 

arch/powerpc/mm/mmu_context_nohash.c

@@ -369,44 +369,34 @@ void destroy_context(struct mm_struct *mm)
 }
 
 #ifdef CONFIG_SMP
-
-static int mmu_context_cpu_notify(struct notifier_block *self,
-				  unsigned long action, void *hcpu)
+static int mmu_ctx_cpu_prepare(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned int)(long)hcpu;
-
 	/* We don't touch CPU 0 map, it's allocated at aboot and kept
 	 * around forever
 	 */
 	if (cpu == boot_cpuid)
-		return NOTIFY_OK;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu);
-		stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL);
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu);
-		kfree(stale_map[cpu]);
-		stale_map[cpu] = NULL;
-
-		/* We also clear the cpu_vm_mask bits of CPUs going away */
-		clear_tasks_mm_cpumask(cpu);
-	break;
-#endif /* CONFIG_HOTPLUG_CPU */
-	}
-	return NOTIFY_OK;
+		return 0;
+
+	pr_devel("MMU: Allocating stale context map for CPU %d\n", cpu);
+	stale_map[cpu] = kzalloc(CTX_MAP_SIZE, GFP_KERNEL);
+	return 0;
 }
 
-static struct notifier_block mmu_context_cpu_nb = {
-	.notifier_call	= mmu_context_cpu_notify,
-};
+static int mmu_ctx_cpu_dead(unsigned int cpu)
+{
+#ifdef CONFIG_HOTPLUG_CPU
+	if (cpu == boot_cpuid)
+		return 0;
+
+	pr_devel("MMU: Freeing stale context map for CPU %d\n", cpu);
+	kfree(stale_map[cpu]);
+	stale_map[cpu] = NULL;
+
+	/* We also clear the cpu_vm_mask bits of CPUs going away */
+	clear_tasks_mm_cpumask(cpu);
+#endif
+	return 0;
+}
 
 #endif /* CONFIG_SMP */
 
@@ -469,7 +459,9 @@ void __init mmu_context_init(void)
 #else
 	stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0);
 
-	register_cpu_notifier(&mmu_context_cpu_nb);
+	cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE,
+				  "powerpc/mmu/ctx:prepare",
+				  mmu_ctx_cpu_prepare, mmu_ctx_cpu_dead);
 #endif
 
 	printk(KERN_INFO

arch/powerpc/platforms/powermac/smp.c

@@ -852,37 +852,33 @@ static void smp_core99_setup_cpu(int cpu_nr)
 
 #ifdef CONFIG_PPC64
 #ifdef CONFIG_HOTPLUG_CPU
-static int smp_core99_cpu_notify(struct notifier_block *self,
-				 unsigned long action, void *hcpu)
+static unsigned int smp_core99_host_open;
+
+static int smp_core99_cpu_prepare(unsigned int cpu)
 {
 	int rc;
 
-	switch(action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-		/* Open i2c bus if it was used for tb sync */
-		if (pmac_tb_clock_chip_host) {
-			rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
-			if (rc) {
-				pr_err("Failed to open i2c bus for time sync\n");
-				return notifier_from_errno(rc);
-			}
+	/* Open i2c bus if it was used for tb sync */
+	if (pmac_tb_clock_chip_host && !smp_core99_host_open) {
+		rc = pmac_i2c_open(pmac_tb_clock_chip_host, 1);
+		if (rc) {
+			pr_err("Failed to open i2c bus for time sync\n");
+			return notifier_from_errno(rc);
 		}
-		break;
-	case CPU_ONLINE:
-	case CPU_UP_CANCELED:
-		/* Close i2c bus if it was used for tb sync */
-		if (pmac_tb_clock_chip_host)
-			pmac_i2c_close(pmac_tb_clock_chip_host);
-		break;
-	default:
-		break;
+		smp_core99_host_open = 1;
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block smp_core99_cpu_nb = {
-	.notifier_call	= smp_core99_cpu_notify,
-};
+static int smp_core99_cpu_online(unsigned int cpu)
+{
+	/* Close i2c bus if it was used for tb sync */
+	if (pmac_tb_clock_chip_host && smp_core99_host_open) {
+		pmac_i2c_close(pmac_tb_clock_chip_host);
+		smp_core99_host_open = 0;
+	}
+	return 0;
+}
 #endif /* CONFIG_HOTPLUG_CPU */
 
 static void __init smp_core99_bringup_done(void)
@@ -902,7 +898,11 @@ static void __init smp_core99_bringup_done(void)
 		g5_phy_disable_cpu1();
 	}
 #ifdef CONFIG_HOTPLUG_CPU
-	register_cpu_notifier(&smp_core99_cpu_nb);
+	cpuhp_setup_state_nocalls(CPUHP_POWERPC_PMAC_PREPARE,
+				  "powerpc/pmac:prepare", smp_core99_cpu_prepare,
+				  NULL);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "powerpc/pmac:online",
+				  smp_core99_cpu_online, NULL);
 #endif
 
 	if (ppc_md.progress)

arch/s390/mm/fault.c

@@ -740,28 +740,21 @@ out:
 	put_task_struct(tsk);
 }
 
-static int pfault_cpu_notify(struct notifier_block *self, unsigned long action,
-			     void *hcpu)
+static int pfault_cpu_dead(unsigned int cpu)
 {
 	struct thread_struct *thread, *next;
 	struct task_struct *tsk;
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DEAD:
-		spin_lock_irq(&pfault_lock);
-		list_for_each_entry_safe(thread, next, &pfault_list, list) {
-			thread->pfault_wait = 0;
-			list_del(&thread->list);
-			tsk = container_of(thread, struct task_struct, thread);
-			wake_up_process(tsk);
-			put_task_struct(tsk);
-		}
-		spin_unlock_irq(&pfault_lock);
-		break;
-	default:
-		break;
+	spin_lock_irq(&pfault_lock);
+	list_for_each_entry_safe(thread, next, &pfault_list, list) {
+		thread->pfault_wait = 0;
+		list_del(&thread->list);
+		tsk = container_of(thread, struct task_struct, thread);
+		wake_up_process(tsk);
+		put_task_struct(tsk);
 	}
-	return NOTIFY_OK;
+	spin_unlock_irq(&pfault_lock);
+	return 0;
 }
 
 static int __init pfault_irq_init(void)
@@ -775,7 +768,8 @@ static int __init pfault_irq_init(void)
 	if (rc)
 		goto out_pfault;
 	irq_subclass_register(IRQ_SUBCLASS_SERVICE_SIGNAL);
-	hotcpu_notifier(pfault_cpu_notify, 0);
+	cpuhp_setup_state_nocalls(CPUHP_S390_PFAULT_DEAD, "s390/pfault:dead",
+				  NULL, pfault_cpu_dead);
 	return 0;
 
 out_pfault:

arch/sh/kernel/cpu/sh4a/smp-shx3.c

@@ -122,32 +122,16 @@ static void shx3_update_boot_vector(unsigned int cpu)
 	__raw_writel(STBCR_RESET, STBCR_REG(cpu));
 }
 
-static int
-shx3_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+static int shx3_cpu_prepare(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned int)hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-		shx3_update_boot_vector(cpu);
-		break;
-	case CPU_ONLINE:
-		pr_info("CPU %u is now online\n", cpu);
-		break;
-	case CPU_DEAD:
-		break;
-	}
-
-	return NOTIFY_OK;
+	shx3_update_boot_vector(cpu);
+	return 0;
 }
 
-static struct notifier_block shx3_cpu_notifier = {
-	.notifier_call		= shx3_cpu_callback,
-};
-
 static int register_shx3_cpu_notifier(void)
 {
-	register_hotcpu_notifier(&shx3_cpu_notifier);
+	cpuhp_setup_state_nocalls(CPUHP_SH_SH3X_PREPARE, "sh/shx3:prepare",
+				  shx3_cpu_prepare, NULL);
 	return 0;
 }
 late_initcall(register_shx3_cpu_notifier);

arch/sparc/kernel/smp_32.c

@@ -352,9 +352,7 @@ static void sparc_start_secondary(void *arg)
 	preempt_disable();
 	cpu = smp_processor_id();
 
-	/* Invoke the CPU_STARTING notifier callbacks */
 	notify_cpu_starting(cpu);
-
 	arch_cpu_pre_online(arg);
 
 	/* Set the CPU in the cpu_online_mask */

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -924,7 +924,7 @@ static void uv_heartbeat(unsigned long ignored)
 	mod_timer(timer, jiffies + SCIR_CPU_HB_INTERVAL);
 }
 
-static void uv_heartbeat_enable(int cpu)
+static int uv_heartbeat_enable(unsigned int cpu)
 {
 	while (!uv_cpu_scir_info(cpu)->enabled) {
 		struct timer_list *timer = &uv_cpu_scir_info(cpu)->timer;
@@ -938,43 +938,24 @@ static void uv_heartbeat_enable(int cpu)
 		/* also ensure that boot cpu is enabled */
 		cpu = 0;
 	}
+	return 0;
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static void uv_heartbeat_disable(int cpu)
+static int uv_heartbeat_disable(unsigned int cpu)
 {
 	if (uv_cpu_scir_info(cpu)->enabled) {
 		uv_cpu_scir_info(cpu)->enabled = 0;
 		del_timer(&uv_cpu_scir_info(cpu)->timer);
 	}
 	uv_set_cpu_scir_bits(cpu, 0xff);
-}
-
-/*
- * cpu hotplug notifier
- */
-static int uv_scir_cpu_notify(struct notifier_block *self, unsigned long action,
-			      void *hcpu)
-{
-	long cpu = (long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_DOWN_FAILED:
-	case CPU_ONLINE:
-		uv_heartbeat_enable(cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		uv_heartbeat_disable(cpu);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+	return 0;
 }
 
 static __init void uv_scir_register_cpu_notifier(void)
 {
-	hotcpu_notifier(uv_scir_cpu_notify, 0);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/x2apic-uvx:online",
+				  uv_heartbeat_enable, uv_heartbeat_disable);
 }
 
 #else /* !CONFIG_HOTPLUG_CPU */

arch/x86/kernel/cpu/microcode/core.c

@@ -558,55 +558,36 @@ static struct syscore_ops mc_syscore_ops = {
 	.resume			= mc_bp_resume,
 };
 
-static int
-mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
+static int mc_cpu_online(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
 	struct device *dev;
 
 	dev = get_cpu_device(cpu);
+	microcode_update_cpu(cpu);
+	pr_debug("CPU%d added\n", cpu);
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-		microcode_update_cpu(cpu);
-		pr_debug("CPU%d added\n", cpu);
-		/*
-		 * "break" is missing on purpose here because we want to fall
-		 * through in order to create the sysfs group.
-		 */
-
-	case CPU_DOWN_FAILED:
-		if (sysfs_create_group(&dev->kobj, &mc_attr_group))
-			pr_err("Failed to create group for CPU%d\n", cpu);
-		break;
+	if (sysfs_create_group(&dev->kobj, &mc_attr_group))
+		pr_err("Failed to create group for CPU%d\n", cpu);
+	return 0;
+}
 
-	case CPU_DOWN_PREPARE:
-		/* Suspend is in progress, only remove the interface */
-		sysfs_remove_group(&dev->kobj, &mc_attr_group);
-		pr_debug("CPU%d removed\n", cpu);
-		break;
+static int mc_cpu_down_prep(unsigned int cpu)
+{
+	struct device *dev;
 
+	dev = get_cpu_device(cpu);
+	/* Suspend is in progress, only remove the interface */
+	sysfs_remove_group(&dev->kobj, &mc_attr_group);
+	pr_debug("CPU%d removed\n", cpu);
 	/*
-	 * case CPU_DEAD:
-	 *
 	 * When a CPU goes offline, don't free up or invalidate the copy of
 	 * the microcode in kernel memory, so that we can reuse it when the
 	 * CPU comes back online without unnecessarily requesting the userspace
 	 * for it again.
 	 */
-	}
-
-	/* The CPU refused to come up during a system resume */
-	if (action == CPU_UP_CANCELED_FROZEN)
-		microcode_fini_cpu(cpu);
-
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block mc_cpu_notifier = {
-	.notifier_call	= mc_cpu_callback,
-};
-
 static struct attribute *cpu_root_microcode_attrs[] = {
 	&dev_attr_reload.attr,
 	NULL
@@ -665,7 +646,8 @@ int __init microcode_init(void)
 		goto out_ucode_group;
 
 	register_syscore_ops(&mc_syscore_ops);
-	register_hotcpu_notifier(&mc_cpu_notifier);
+	cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/microcode:online",
+				  mc_cpu_online, mc_cpu_down_prep);
 
 	pr_info("Microcode Update Driver: v" MICROCODE_VERSION
 		" <tigran@aivazian.fsnet.co.uk>, Peter Oruba\n");

arch/x86/kernel/kvm.c

@@ -423,12 +423,7 @@ static void __init kvm_smp_prepare_boot_cpu(void)
 	kvm_spinlock_init();
 }
 
-static void kvm_guest_cpu_online(void *dummy)
-{
-	kvm_guest_cpu_init();
-}
-
-static void kvm_guest_cpu_offline(void *dummy)
+static void kvm_guest_cpu_offline(void)
 {
 	kvm_disable_steal_time();
 	if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
@@ -437,29 +432,21 @@ static void kvm_guest_cpu_offline(void *dummy)
 	apf_task_wake_all();
 }
 
-static int kvm_cpu_notify(struct notifier_block *self, unsigned long action,
-			  void *hcpu)
+static int kvm_cpu_online(unsigned int cpu)
 {
-	int cpu = (unsigned long)hcpu;
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-	case CPU_ONLINE_FROZEN:
-		smp_call_function_single(cpu, kvm_guest_cpu_online, NULL, 0);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		smp_call_function_single(cpu, kvm_guest_cpu_offline, NULL, 1);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+	local_irq_disable();
+	kvm_guest_cpu_init();
+	local_irq_enable();
+	return 0;
 }
 
-static struct notifier_block kvm_cpu_notifier = {
-        .notifier_call  = kvm_cpu_notify,
-};
+static int kvm_cpu_down_prepare(unsigned int cpu)
+{
+	local_irq_disable();
+	kvm_guest_cpu_offline();
+	local_irq_enable();
+	return 0;
+}
 #endif
 
 static void __init kvm_apf_trap_init(void)
@@ -494,7 +481,9 @@ void __init kvm_guest_init(void)
 
 #ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = kvm_smp_prepare_boot_cpu;
-	register_cpu_notifier(&kvm_cpu_notifier);
+	if (cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "x86/kvm:online",
+				      kvm_cpu_online, kvm_cpu_down_prepare) < 0)
+		pr_err("kvm_guest: Failed to install cpu hotplug callbacks\n");
 #else
 	kvm_guest_cpu_init();
 #endif

arch/x86/kernel/smpboot.c

@@ -1115,17 +1115,8 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 
 	common_cpu_up(cpu, tidle);
 
-	/*
-	 * We have to walk the irq descriptors to setup the vector
-	 * space for the cpu which comes online.  Prevent irq
-	 * alloc/free across the bringup.
-	 */
-	irq_lock_sparse();
-
 	err = do_boot_cpu(apicid, cpu, tidle);
-
 	if (err) {
-		irq_unlock_sparse();
 		pr_err("do_boot_cpu failed(%d) to wakeup CPU#%u\n", err, cpu);
 		return -EIO;
 	}
@@ -1143,8 +1134,6 @@ int native_cpu_up(unsigned int cpu, struct task_struct *tidle)
 		touch_nmi_watchdog();
 	}
 
-	irq_unlock_sparse();
-
 	return 0;
 }
 

block/blk-softirq.c

@@ -78,30 +78,21 @@ static int raise_blk_irq(int cpu, struct request *rq)
 }
 #endif
 
-static int blk_cpu_notify(struct notifier_block *self, unsigned long action,
-			  void *hcpu)
+static int blk_softirq_cpu_dead(unsigned int cpu)
 {
 	/*
 	 * If a CPU goes away, splice its entries to the current CPU
 	 * and trigger a run of the softirq
 	 */
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		int cpu = (unsigned long) hcpu;
-
-		local_irq_disable();
-		list_splice_init(&per_cpu(blk_cpu_done, cpu),
-				 this_cpu_ptr(&blk_cpu_done));
-		raise_softirq_irqoff(BLOCK_SOFTIRQ);
-		local_irq_enable();
-	}
+	local_irq_disable();
+	list_splice_init(&per_cpu(blk_cpu_done, cpu),
+			 this_cpu_ptr(&blk_cpu_done));
+	raise_softirq_irqoff(BLOCK_SOFTIRQ);
+	local_irq_enable();
 
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block blk_cpu_notifier = {
-	.notifier_call	= blk_cpu_notify,
-};
-
 void __blk_complete_request(struct request *req)
 {
 	int ccpu, cpu;
@@ -180,7 +171,9 @@ static __init int blk_softirq_init(void)
 		INIT_LIST_HEAD(&per_cpu(blk_cpu_done, i));
 
 	open_softirq(BLOCK_SOFTIRQ, blk_done_softirq);
-	register_hotcpu_notifier(&blk_cpu_notifier);
+	cpuhp_setup_state_nocalls(CPUHP_BLOCK_SOFTIRQ_DEAD,
+				  "block/softirq:dead", NULL,
+				  blk_softirq_cpu_dead);
 	return 0;
 }
 subsys_initcall(blk_softirq_init);

drivers/acpi/processor_driver.c

@@ -110,55 +110,46 @@ static void acpi_processor_notify(acpi_handle handle, u32 event, void *data)
 
 static int __acpi_processor_start(struct acpi_device *device);
 
-static int acpi_cpu_soft_notify(struct notifier_block *nfb,
-					  unsigned long action, void *hcpu)
+static int acpi_soft_cpu_online(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
 	struct acpi_processor *pr = per_cpu(processors, cpu);
 	struct acpi_device *device;
-	action &= ~CPU_TASKS_FROZEN;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_DEAD:
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
 
 	if (!pr || acpi_bus_get_device(pr->handle, &device))
-		return NOTIFY_DONE;
-
-	if (action == CPU_ONLINE) {
-		/*
-		 * CPU got physically hotplugged and onlined for the first time:
-		 * Initialize missing things.
-		 */
-		if (pr->flags.need_hotplug_init) {
-			int ret;
-
-			pr_info("Will online and init hotplugged CPU: %d\n",
-				pr->id);
-			pr->flags.need_hotplug_init = 0;
-			ret = __acpi_processor_start(device);
-			WARN(ret, "Failed to start CPU: %d\n", pr->id);
-		} else {
-			/* Normal CPU soft online event. */
-			acpi_processor_ppc_has_changed(pr, 0);
-			acpi_processor_hotplug(pr);
-			acpi_processor_reevaluate_tstate(pr, action);
-			acpi_processor_tstate_has_changed(pr);
-		}
-	} else if (action == CPU_DEAD) {
-		/* Invalidate flag.throttling after the CPU is offline. */
-		acpi_processor_reevaluate_tstate(pr, action);
+		return 0;
+	/*
+	 * CPU got physically hotplugged and onlined for the first time:
+	 * Initialize missing things.
+	 */
+	if (pr->flags.need_hotplug_init) {
+		int ret;
+
+		pr_info("Will online and init hotplugged CPU: %d\n",
+			pr->id);
+		pr->flags.need_hotplug_init = 0;
+		ret = __acpi_processor_start(device);
+		WARN(ret, "Failed to start CPU: %d\n", pr->id);
+	} else {
+		/* Normal CPU soft online event. */
+		acpi_processor_ppc_has_changed(pr, 0);
+		acpi_processor_hotplug(pr);
+		acpi_processor_reevaluate_tstate(pr, false);
+		acpi_processor_tstate_has_changed(pr);
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block acpi_cpu_notifier = {
-	    .notifier_call = acpi_cpu_soft_notify,
-};
+static int acpi_soft_cpu_dead(unsigned int cpu)
+{
+	struct acpi_processor *pr = per_cpu(processors, cpu);
+	struct acpi_device *device;
+
+	if (!pr || acpi_bus_get_device(pr->handle, &device))
+		return 0;
+
+	acpi_processor_reevaluate_tstate(pr, true);
+	return 0;
+}
 
 #ifdef CONFIG_ACPI_CPU_FREQ_PSS
 static int acpi_pss_perf_init(struct acpi_processor *pr,
@@ -303,7 +294,7 @@ static int acpi_processor_stop(struct device *dev)
  * This is needed for the powernow-k8 driver, that works even without
  * ACPI, but needs symbols from this driver
  */
-
+static enum cpuhp_state hp_online;
 static int __init acpi_processor_driver_init(void)
 {
 	int result = 0;
@@ -315,11 +306,22 @@ static int __init acpi_processor_driver_init(void)
 	if (result < 0)
 		return result;
 
-	register_hotcpu_notifier(&acpi_cpu_notifier);
+	result = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					   "acpi/cpu-drv:online",
+					   acpi_soft_cpu_online, NULL);
+	if (result < 0)
+		goto err;
+	hp_online = result;
+	cpuhp_setup_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD, "acpi/cpu-drv:dead",
+				  NULL, acpi_soft_cpu_dead);
+
 	acpi_thermal_cpufreq_init();
 	acpi_processor_ppc_init();
 	acpi_processor_throttling_init();
 	return 0;
+err:
+	driver_unregister(&acpi_processor_driver);
+	return result;
 }
 
 static void __exit acpi_processor_driver_exit(void)
@@ -329,7 +331,8 @@ static void __exit acpi_processor_driver_exit(void)
 
 	acpi_processor_ppc_exit();
 	acpi_thermal_cpufreq_exit();
-	unregister_hotcpu_notifier(&acpi_cpu_notifier);
+	cpuhp_remove_state_nocalls(hp_online);
+	cpuhp_remove_state_nocalls(CPUHP_ACPI_CPUDRV_DEAD);
 	driver_unregister(&acpi_processor_driver);
 }
 

drivers/acpi/processor_throttling.c

@@ -375,11 +375,11 @@ int acpi_processor_tstate_has_changed(struct acpi_processor *pr)
  *	3. TSD domain
  */
 void acpi_processor_reevaluate_tstate(struct acpi_processor *pr,
-					unsigned long action)
+					bool is_dead)
 {
 	int result = 0;
 
-	if (action == CPU_DEAD) {
+	if (is_dead) {
 		/* When one CPU is offline, the T-state throttling
 		 * will be invalidated.
 		 */

drivers/bus/arm-cci.c

@@ -144,15 +144,12 @@ struct cci_pmu {
 	int num_cntrs;
 	atomic_t active_events;
 	struct mutex reserve_mutex;
-	struct list_head entry;
+	struct hlist_node node;
 	cpumask_t cpus;
 };
 
 #define to_cci_pmu(c)	(container_of(c, struct cci_pmu, pmu))
 
-static DEFINE_MUTEX(cci_pmu_mutex);
-static LIST_HEAD(cci_pmu_list);
-
 enum cci_models {
 #ifdef CONFIG_ARM_CCI400_PMU
 	CCI400_R0,
@@ -1506,25 +1503,21 @@ static int cci_pmu_init(struct cci_pmu *cci_pmu, struct platform_device *pdev)
 	return perf_pmu_register(&cci_pmu->pmu, name, -1);
 }
 
-static int cci_pmu_offline_cpu(unsigned int cpu)
+static int cci_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
-	struct cci_pmu *cci_pmu;
+	struct cci_pmu *cci_pmu = hlist_entry_safe(node, struct cci_pmu, node);
 	unsigned int target;
 
-	mutex_lock(&cci_pmu_mutex);
-	list_for_each_entry(cci_pmu, &cci_pmu_list, entry) {
-		if (!cpumask_test_and_clear_cpu(cpu, &cci_pmu->cpus))
-			continue;
-		target = cpumask_any_but(cpu_online_mask, cpu);
-		if (target >= nr_cpu_ids)
-			continue;
-		/*
-		 * TODO: migrate context once core races on event->ctx have
-		 * been fixed.
-		 */
-		cpumask_set_cpu(target, &cci_pmu->cpus);
-	}
-	mutex_unlock(&cci_pmu_mutex);
+	if (!cpumask_test_and_clear_cpu(cpu, &cci_pmu->cpus))
+		return 0;
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+	/*
+	 * TODO: migrate context once core races on event->ctx have
+	 * been fixed.
+	 */
+	cpumask_set_cpu(target, &cci_pmu->cpus);
 	return 0;
 }
 
@@ -1768,10 +1761,8 @@ static int cci_pmu_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	mutex_lock(&cci_pmu_mutex);
-	list_add(&cci_pmu->entry, &cci_pmu_list);
-	mutex_unlock(&cci_pmu_mutex);
-
+	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
+					 &cci_pmu->node);
 	pr_info("ARM %s PMU driver probed", cci_pmu->model->name);
 	return 0;
 }
@@ -1804,9 +1795,9 @@ static int __init cci_platform_init(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCI_ONLINE,
-					"AP_PERF_ARM_CCI_ONLINE", NULL,
-					cci_pmu_offline_cpu);
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCI_ONLINE,
+				      "AP_PERF_ARM_CCI_ONLINE", NULL,
+				      cci_pmu_offline_cpu);
 	if (ret)
 		return ret;
 

drivers/bus/arm-ccn.c

@@ -167,7 +167,7 @@ struct arm_ccn_dt {
 	struct hrtimer hrtimer;
 
 	cpumask_t cpu;
-	struct list_head entry;
+	struct hlist_node node;
 
 	struct pmu pmu;
 };
@@ -190,9 +190,6 @@ struct arm_ccn {
 	int mn_id;
 };
 
-static DEFINE_MUTEX(arm_ccn_mutex);
-static LIST_HEAD(arm_ccn_list);
-
 static int arm_ccn_node_to_xp(int node)
 {
 	return node / CCN_NUM_XP_PORTS;
@@ -1214,30 +1211,24 @@ static enum hrtimer_restart arm_ccn_pmu_timer_handler(struct hrtimer *hrtimer)
 }
 
 
-static int arm_ccn_pmu_offline_cpu(unsigned int cpu)
+static int arm_ccn_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
-	struct arm_ccn_dt *dt;
+	struct arm_ccn_dt *dt = hlist_entry_safe(node, struct arm_ccn_dt, node);
+	struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
 	unsigned int target;
 
-	mutex_lock(&arm_ccn_mutex);
-	list_for_each_entry(dt, &arm_ccn_list, entry) {
-		struct arm_ccn *ccn = container_of(dt, struct arm_ccn, dt);
-
-		if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
-			continue;
-		target = cpumask_any_but(cpu_online_mask, cpu);
-		if (target >= nr_cpu_ids)
-			continue;
-		perf_pmu_migrate_context(&dt->pmu, cpu, target);
-		cpumask_set_cpu(target, &dt->cpu);
-		if (ccn->irq)
-			WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
-	}
-	mutex_unlock(&arm_ccn_mutex);
+	if (!cpumask_test_and_clear_cpu(cpu, &dt->cpu))
+		return 0;
+	target = cpumask_any_but(cpu_online_mask, cpu);
+	if (target >= nr_cpu_ids)
+		return 0;
+	perf_pmu_migrate_context(&dt->pmu, cpu, target);
+	cpumask_set_cpu(target, &dt->cpu);
+	if (ccn->irq)
+		WARN_ON(irq_set_affinity_hint(ccn->irq, &dt->cpu) != 0);
 	return 0;
 }
 
-
 static DEFINE_IDA(arm_ccn_pmu_ida);
 
 static int arm_ccn_pmu_init(struct arm_ccn *ccn)
@@ -1321,9 +1312,8 @@ static int arm_ccn_pmu_init(struct arm_ccn *ccn)
 	if (err)
 		goto error_pmu_register;
 
-	mutex_lock(&arm_ccn_mutex);
-	list_add(&ccn->dt.entry, &arm_ccn_list);
-	mutex_unlock(&arm_ccn_mutex);
+	cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					 &ccn->dt.node);
 	return 0;
 
 error_pmu_register:
@@ -1339,10 +1329,8 @@ static void arm_ccn_pmu_cleanup(struct arm_ccn *ccn)
 {
 	int i;
 
-	mutex_lock(&arm_ccn_mutex);
-	list_del(&ccn->dt.entry);
-	mutex_unlock(&arm_ccn_mutex);
-
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+					    &ccn->dt.node);
 	if (ccn->irq)
 		irq_set_affinity_hint(ccn->irq, NULL);
 	for (i = 0; i < ccn->num_xps; i++)
@@ -1573,9 +1561,9 @@ static int __init arm_ccn_init(void)
 {
 	int i, ret;
 
-	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE,
-					"AP_PERF_ARM_CCN_ONLINE", NULL,
-					arm_ccn_pmu_offline_cpu);
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_CCN_ONLINE,
+				      "AP_PERF_ARM_CCN_ONLINE", NULL,
+				      arm_ccn_pmu_offline_cpu);
 	if (ret)
 		return ret;
 
@@ -1587,7 +1575,7 @@ static int __init arm_ccn_init(void)
 
 static void __exit arm_ccn_exit(void)
 {
-	cpuhp_remove_state_nocalls(CPUHP_AP_PERF_ARM_CCN_ONLINE);
+	cpuhp_remove_multi_state(CPUHP_AP_PERF_ARM_CCN_ONLINE);
 	platform_driver_unregister(&arm_ccn_driver);
 }
 

drivers/bus/mips_cdmm.c

@@ -596,19 +596,20 @@ BUILD_PERDEV_HELPER(cpu_down)       /* int mips_cdmm_cpu_down_helper(...) */
 BUILD_PERDEV_HELPER(cpu_up)         /* int mips_cdmm_cpu_up_helper(...) */
 
 /**
- * mips_cdmm_bus_down() - Tear down the CDMM bus.
- * @data:	Pointer to unsigned int CPU number.
+ * mips_cdmm_cpu_down_prep() - Callback for CPUHP DOWN_PREP:
+ *			       Tear down the CDMM bus.
+ * @cpu:	unsigned int CPU number.
  *
  * This function is executed on the hotplugged CPU and calls the CDMM
  * driver cpu_down callback for all devices on that CPU.
  */
-static long mips_cdmm_bus_down(void *data)
+static int mips_cdmm_cpu_down_prep(unsigned int cpu)
 {
 	struct mips_cdmm_bus *bus;
 	long ret;
 
 	/* Inform all the devices on the bus */
-	ret = bus_for_each_dev(&mips_cdmm_bustype, NULL, data,
+	ret = bus_for_each_dev(&mips_cdmm_bustype, NULL, &cpu,
 			       mips_cdmm_cpu_down_helper);
 
 	/*
@@ -623,8 +624,8 @@ static long mips_cdmm_bus_down(void *data)
 }
 
 /**
- * mips_cdmm_bus_up() - Bring up the CDMM bus.
- * @data:	Pointer to unsigned int CPU number.
+ * mips_cdmm_cpu_online() - Callback for CPUHP ONLINE: Bring up the CDMM bus.
+ * @cpu:	unsigned int CPU number.
  *
  * This work_on_cpu callback function is executed on a given CPU to discover
  * CDMM devices on that CPU, or to call the CDMM driver cpu_up callback for all
@@ -634,7 +635,7 @@ static long mips_cdmm_bus_down(void *data)
  * initialisation. When CPUs are brought online the function is
  * invoked directly on the hotplugged CPU.
  */
-static long mips_cdmm_bus_up(void *data)
+static int mips_cdmm_cpu_online(unsigned int cpu)
 {
 	struct mips_cdmm_bus *bus;
 	long ret;
@@ -651,50 +652,12 @@ static long mips_cdmm_bus_up(void *data)
 		mips_cdmm_bus_discover(bus);
 	else
 		/* Inform all the devices on the bus */
-		ret = bus_for_each_dev(&mips_cdmm_bustype, NULL, data,
+		ret = bus_for_each_dev(&mips_cdmm_bustype, NULL, &cpu,
 				       mips_cdmm_cpu_up_helper);
 
 	return ret;
 }
 
-/**
- * mips_cdmm_cpu_notify() - Take action when a CPU is going online or offline.
- * @nb:		CPU notifier block .
- * @action:	Event that has taken place (CPU_*).
- * @data:	CPU number.
- *
- * This notifier is used to keep the CDMM buses updated as CPUs are offlined and
- * onlined. When CPUs go offline or come back online, so does their CDMM bus, so
- * devices must be informed. Also when CPUs come online for the first time the
- * devices on the CDMM bus need discovering.
- *
- * Returns:	NOTIFY_OK if event was used.
- *		NOTIFY_DONE if we didn't care.
- */
-static int mips_cdmm_cpu_notify(struct notifier_block *nb,
-				unsigned long action, void *data)
-{
-	unsigned int cpu = (unsigned int)data;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		mips_cdmm_bus_up(&cpu);
-		break;
-	case CPU_DOWN_PREPARE:
-		mips_cdmm_bus_down(&cpu);
-		break;
-	default:
-		return NOTIFY_DONE;
-	}
-
-	return NOTIFY_OK;
-}
-
-static struct notifier_block mips_cdmm_cpu_nb = {
-	.notifier_call = mips_cdmm_cpu_notify,
-};
-
 /**
  * mips_cdmm_init() - Initialise CDMM bus.
  *
@@ -703,7 +666,6 @@ static struct notifier_block mips_cdmm_cpu_nb = {
  */
 static int __init mips_cdmm_init(void)
 {
-	unsigned int cpu;
 	int ret;
 
 	/* Register the bus */
@@ -712,19 +674,11 @@ static int __init mips_cdmm_init(void)
 		return ret;
 
 	/* We want to be notified about new CPUs */
-	ret = register_cpu_notifier(&mips_cdmm_cpu_nb);
-	if (ret) {
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "bus/cdmm:online",
+				mips_cdmm_cpu_online, mips_cdmm_cpu_down_prep);
+	if (ret < 0)
 		pr_warn("cdmm: Failed to register CPU notifier\n");
-		goto out;
-	}
-
-	/* Discover devices on CDMM of online CPUs */
-	for_each_online_cpu(cpu)
-		work_on_cpu(cpu, mips_cdmm_bus_up, &cpu);
 
-	return 0;
-out:
-	bus_unregister(&mips_cdmm_bustype);
 	return ret;
 }
 subsys_initcall(mips_cdmm_init);

drivers/cpufreq/cpufreq.c

@@ -1286,7 +1286,7 @@ out_free_policy:
 	return ret;
 }
 
-static void cpufreq_offline(unsigned int cpu);
+static int cpufreq_offline(unsigned int cpu);
 
 /**
  * cpufreq_add_dev - the cpufreq interface for a CPU device.
@@ -1321,7 +1321,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif)
 	return ret;
 }
 
-static void cpufreq_offline(unsigned int cpu)
+static int cpufreq_offline(unsigned int cpu)
 {
 	struct cpufreq_policy *policy;
 	int ret;
@@ -1331,7 +1331,7 @@ static void cpufreq_offline(unsigned int cpu)
 	policy = cpufreq_cpu_get_raw(cpu);
 	if (!policy) {
 		pr_debug("%s: No cpu_data found\n", __func__);
-		return;
+		return 0;
 	}
 
 	down_write(&policy->rwsem);
@@ -1380,6 +1380,7 @@ static void cpufreq_offline(unsigned int cpu)
 
 unlock:
 	up_write(&policy->rwsem);
+	return 0;
 }
 
 /**
@@ -2295,28 +2296,6 @@ unlock:
 }
 EXPORT_SYMBOL(cpufreq_update_policy);
 
-static int cpufreq_cpu_callback(struct notifier_block *nfb,
-					unsigned long action, void *hcpu)
-{
-	unsigned int cpu = (unsigned long)hcpu;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-		cpufreq_online(cpu);
-		break;
-
-	case CPU_DOWN_PREPARE:
-		cpufreq_offline(cpu);
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block __refdata cpufreq_cpu_notifier = {
-	.notifier_call = cpufreq_cpu_callback,
-};
-
 /*********************************************************************
  *               BOOST						     *
  *********************************************************************/
@@ -2418,6 +2397,7 @@ EXPORT_SYMBOL_GPL(cpufreq_boost_enabled);
 /*********************************************************************
  *               REGISTER / UNREGISTER CPUFREQ DRIVER                *
  *********************************************************************/
+static enum cpuhp_state hp_online;
 
 /**
  * cpufreq_register_driver - register a CPU Frequency driver
@@ -2480,7 +2460,14 @@ int cpufreq_register_driver(struct cpufreq_driver *driver_data)
 		goto err_if_unreg;
 	}
 
-	register_hotcpu_notifier(&cpufreq_cpu_notifier);
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN, "cpufreq:online",
+					cpufreq_online,
+					cpufreq_offline);
+	if (ret < 0)
+		goto err_if_unreg;
+	hp_online = ret;
+	ret = 0;
+
 	pr_debug("driver %s up and running\n", driver_data->name);
 	goto out;
 
@@ -2519,7 +2506,7 @@ int cpufreq_unregister_driver(struct cpufreq_driver *driver)
 	get_online_cpus();
 	subsys_interface_unregister(&cpufreq_interface);
 	remove_boost_sysfs_file();
-	unregister_hotcpu_notifier(&cpufreq_cpu_notifier);
+	cpuhp_remove_state_nocalls(hp_online);
 
 	write_lock_irqsave(&cpufreq_driver_lock, flags);
 

drivers/cpuidle/coupled.c

@@ -749,65 +749,52 @@ static void cpuidle_coupled_allow_idle(struct cpuidle_coupled *coupled)
 	put_cpu();
 }
 
-/**
- * cpuidle_coupled_cpu_notify - notifier called during hotplug transitions
- * @nb: notifier block
- * @action: hotplug transition
- * @hcpu: target cpu number
- *
- * Called when a cpu is brought on or offline using hotplug.  Updates the
- * coupled cpu set appropriately
- */
-static int cpuidle_coupled_cpu_notify(struct notifier_block *nb,
-		unsigned long action, void *hcpu)
+static int coupled_cpu_online(unsigned int cpu)
 {
-	int cpu = (unsigned long)hcpu;
 	struct cpuidle_device *dev;
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-	case CPU_DOWN_PREPARE:
-	case CPU_ONLINE:
-	case CPU_DEAD:
-	case CPU_UP_CANCELED:
-	case CPU_DOWN_FAILED:
-		break;
-	default:
-		return NOTIFY_OK;
-	}
-
 	mutex_lock(&cpuidle_lock);
 
 	dev = per_cpu(cpuidle_devices, cpu);
-	if (!dev || !dev->coupled)
-		goto out;
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_UP_PREPARE:
-	case CPU_DOWN_PREPARE:
-		cpuidle_coupled_prevent_idle(dev->coupled);
-		break;
-	case CPU_ONLINE:
-	case CPU_DEAD:
+	if (dev && dev->coupled) {
 		cpuidle_coupled_update_online_cpus(dev->coupled);
-		/* Fall through */
-	case CPU_UP_CANCELED:
-	case CPU_DOWN_FAILED:
 		cpuidle_coupled_allow_idle(dev->coupled);
-		break;
 	}
 
-out:
 	mutex_unlock(&cpuidle_lock);
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block cpuidle_coupled_cpu_notifier = {
-	.notifier_call = cpuidle_coupled_cpu_notify,
-};
+static int coupled_cpu_up_prepare(unsigned int cpu)
+{
+	struct cpuidle_device *dev;
+
+	mutex_lock(&cpuidle_lock);
+
+	dev = per_cpu(cpuidle_devices, cpu);
+	if (dev && dev->coupled)
+		cpuidle_coupled_prevent_idle(dev->coupled);
+
+	mutex_unlock(&cpuidle_lock);
+	return 0;
+}
 
 static int __init cpuidle_coupled_init(void)
 {
-	return register_cpu_notifier(&cpuidle_coupled_cpu_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_COUPLED_PREPARE,
+					"cpuidle/coupled:prepare",
+					coupled_cpu_up_prepare,
+					coupled_cpu_online);
+	if (ret)
+		return ret;
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"cpuidle/coupled:online",
+					coupled_cpu_online,
+					coupled_cpu_up_prepare);
+	if (ret < 0)
+		cpuhp_remove_state_nocalls(CPUHP_CPUIDLE_COUPLED_PREPARE);
+	return ret;
 }
 core_initcall(cpuidle_coupled_init);

drivers/cpuidle/cpuidle-powernv.c

@@ -119,40 +119,30 @@ static struct cpuidle_state powernv_states[CPUIDLE_STATE_MAX] = {
 		.enter = snooze_loop },
 };
 
-static int powernv_cpuidle_add_cpu_notifier(struct notifier_block *n,
-			unsigned long action, void *hcpu)
+static int powernv_cpuidle_cpu_online(unsigned int cpu)
 {
-	int hotcpu = (unsigned long)hcpu;
-	struct cpuidle_device *dev =
-				per_cpu(cpuidle_devices, hotcpu);
+	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
 
 	if (dev && cpuidle_get_driver()) {
-		switch (action) {
-		case CPU_ONLINE:
-		case CPU_ONLINE_FROZEN:
-			cpuidle_pause_and_lock();
-			cpuidle_enable_device(dev);
-			cpuidle_resume_and_unlock();
-			break;
+		cpuidle_pause_and_lock();
+		cpuidle_enable_device(dev);
+		cpuidle_resume_and_unlock();
+	}
+	return 0;
+}
 
-		case CPU_DEAD:
-		case CPU_DEAD_FROZEN:
-			cpuidle_pause_and_lock();
-			cpuidle_disable_device(dev);
-			cpuidle_resume_and_unlock();
-			break;
+static int powernv_cpuidle_cpu_dead(unsigned int cpu)
+{
+	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
 
-		default:
-			return NOTIFY_DONE;
-		}
+	if (dev && cpuidle_get_driver()) {
+		cpuidle_pause_and_lock();
+		cpuidle_disable_device(dev);
+		cpuidle_resume_and_unlock();
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block setup_hotplug_notifier = {
-	.notifier_call = powernv_cpuidle_add_cpu_notifier,
-};
-
 /*
  * powernv_cpuidle_driver_init()
  */
@@ -355,7 +345,14 @@ static int __init powernv_processor_idle_init(void)
 		return retval;
 	}
 
-	register_cpu_notifier(&setup_hotplug_notifier);
+	retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					   "cpuidle/powernv:online",
+					   powernv_cpuidle_cpu_online, NULL);
+	WARN_ON(retval < 0);
+	retval = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_DEAD,
+					   "cpuidle/powernv:dead", NULL,
+					   powernv_cpuidle_cpu_dead);
+	WARN_ON(retval < 0);
 	printk(KERN_DEBUG "powernv_idle_driver registered\n");
 	return 0;
 }

drivers/cpuidle/cpuidle-pseries.c

@@ -171,40 +171,30 @@ static struct cpuidle_state shared_states[] = {
 		.enter = &shared_cede_loop },
 };
 
-static int pseries_cpuidle_add_cpu_notifier(struct notifier_block *n,
-			unsigned long action, void *hcpu)
+static int pseries_cpuidle_cpu_online(unsigned int cpu)
 {
-	int hotcpu = (unsigned long)hcpu;
-	struct cpuidle_device *dev =
-				per_cpu(cpuidle_devices, hotcpu);
+	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
 
 	if (dev && cpuidle_get_driver()) {
-		switch (action) {
-		case CPU_ONLINE:
-		case CPU_ONLINE_FROZEN:
-			cpuidle_pause_and_lock();
-			cpuidle_enable_device(dev);
-			cpuidle_resume_and_unlock();
-			break;
+		cpuidle_pause_and_lock();
+		cpuidle_enable_device(dev);
+		cpuidle_resume_and_unlock();
+	}
+	return 0;
+}
 
-		case CPU_DEAD:
-		case CPU_DEAD_FROZEN:
-			cpuidle_pause_and_lock();
-			cpuidle_disable_device(dev);
-			cpuidle_resume_and_unlock();
-			break;
+static int pseries_cpuidle_cpu_dead(unsigned int cpu)
+{
+	struct cpuidle_device *dev = per_cpu(cpuidle_devices, cpu);
 
-		default:
-			return NOTIFY_DONE;
-		}
+	if (dev && cpuidle_get_driver()) {
+		cpuidle_pause_and_lock();
+		cpuidle_disable_device(dev);
+		cpuidle_resume_and_unlock();
 	}
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block setup_hotplug_notifier = {
-	.notifier_call = pseries_cpuidle_add_cpu_notifier,
-};
-
 /*
  * pseries_cpuidle_driver_init()
  */
@@ -273,7 +263,14 @@ static int __init pseries_processor_idle_init(void)
 		return retval;
 	}
 
-	register_cpu_notifier(&setup_hotplug_notifier);
+	retval = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					   "cpuidle/pseries:online",
+					   pseries_cpuidle_cpu_online, NULL);
+	WARN_ON(retval < 0);
+	retval = cpuhp_setup_state_nocalls(CPUHP_CPUIDLE_DEAD,
+					   "cpuidle/pseries:DEAD", NULL,
+					   pseries_cpuidle_cpu_dead);
+	WARN_ON(retval < 0);
 	printk(KERN_DEBUG "pseries_idle_driver registered\n");
 	return 0;
 }

drivers/md/raid5.c

@@ -6349,22 +6349,20 @@ static int alloc_scratch_buffer(struct r5conf *conf, struct raid5_percpu *percpu
 	return 0;
 }
 
-static void raid5_free_percpu(struct r5conf *conf)
+static int raid456_cpu_dead(unsigned int cpu, struct hlist_node *node)
 {
-	unsigned long cpu;
+	struct r5conf *conf = hlist_entry_safe(node, struct r5conf, node);
+
+	free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
+	return 0;
+}
 
+static void raid5_free_percpu(struct r5conf *conf)
+{
 	if (!conf->percpu)
 		return;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	unregister_cpu_notifier(&conf->cpu_notify);
-#endif
-
-	get_online_cpus();
-	for_each_possible_cpu(cpu)
-		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
-	put_online_cpus();
-
+	cpuhp_state_remove_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
 	free_percpu(conf->percpu);
 }
 
@@ -6383,64 +6381,28 @@ static void free_conf(struct r5conf *conf)
 	kfree(conf);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-static int raid456_cpu_notify(struct notifier_block *nfb, unsigned long action,
-			      void *hcpu)
+static int raid456_cpu_up_prepare(unsigned int cpu, struct hlist_node *node)
 {
-	struct r5conf *conf = container_of(nfb, struct r5conf, cpu_notify);
-	long cpu = (long)hcpu;
+	struct r5conf *conf = hlist_entry_safe(node, struct r5conf, node);
 	struct raid5_percpu *percpu = per_cpu_ptr(conf->percpu, cpu);
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		if (alloc_scratch_buffer(conf, percpu)) {
-			pr_err("%s: failed memory allocation for cpu%ld\n",
-			       __func__, cpu);
-			return notifier_from_errno(-ENOMEM);
-		}
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		free_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
-		break;
-	default:
-		break;
+	if (alloc_scratch_buffer(conf, percpu)) {
+		pr_err("%s: failed memory allocation for cpu%u\n",
+		       __func__, cpu);
+		return -ENOMEM;
 	}
-	return NOTIFY_OK;
+	return 0;
 }
-#endif
 
 static int raid5_alloc_percpu(struct r5conf *conf)
 {
-	unsigned long cpu;
 	int err = 0;
 
 	conf->percpu = alloc_percpu(struct raid5_percpu);
 	if (!conf->percpu)
 		return -ENOMEM;
 
-#ifdef CONFIG_HOTPLUG_CPU
-	conf->cpu_notify.notifier_call = raid456_cpu_notify;
-	conf->cpu_notify.priority = 0;
-	err = register_cpu_notifier(&conf->cpu_notify);
-	if (err)
-		return err;
-#endif
-
-	get_online_cpus();
-	for_each_present_cpu(cpu) {
-		err = alloc_scratch_buffer(conf, per_cpu_ptr(conf->percpu, cpu));
-		if (err) {
-			pr_err("%s: failed memory allocation for cpu%ld\n",
-			       __func__, cpu);
-			break;
-		}
-	}
-	put_online_cpus();
-
+	err = cpuhp_state_add_instance(CPUHP_MD_RAID5_PREPARE, &conf->node);
 	if (!err) {
 		conf->scribble_disks = max(conf->raid_disks,
 			conf->previous_raid_disks);
@@ -7985,10 +7947,21 @@ static struct md_personality raid4_personality =
 
 static int __init raid5_init(void)
 {
+	int ret;
+
 	raid5_wq = alloc_workqueue("raid5wq",
 		WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE|WQ_SYSFS, 0);
 	if (!raid5_wq)
 		return -ENOMEM;
+
+	ret = cpuhp_setup_state_multi(CPUHP_MD_RAID5_PREPARE,
+				      "md/raid5:prepare",
+				      raid456_cpu_up_prepare,
+				      raid456_cpu_dead);
+	if (ret) {
+		destroy_workqueue(raid5_wq);
+		return ret;
+	}
 	register_md_personality(&raid6_personality);
 	register_md_personality(&raid5_personality);
 	register_md_personality(&raid4_personality);
@@ -8000,6 +7973,7 @@ static void raid5_exit(void)
 	unregister_md_personality(&raid6_personality);
 	unregister_md_personality(&raid5_personality);
 	unregister_md_personality(&raid4_personality);
+	cpuhp_remove_multi_state(CPUHP_MD_RAID5_PREPARE);
 	destroy_workqueue(raid5_wq);
 }
 

drivers/md/raid5.h

@@ -512,9 +512,7 @@ struct r5conf {
 	} __percpu *percpu;
 	int scribble_disks;
 	int scribble_sectors;
-#ifdef CONFIG_HOTPLUG_CPU
-	struct notifier_block	cpu_notify;
-#endif
+	struct hlist_node node;
 
 	/*
 	 * Free stripes pool

drivers/net/ethernet/marvell/mvneta.c

@@ -382,7 +382,8 @@ struct mvneta_port {
 	struct mvneta_rx_queue *rxqs;
 	struct mvneta_tx_queue *txqs;
 	struct net_device *dev;
-	struct notifier_block cpu_notifier;
+	struct hlist_node node_online;
+	struct hlist_node node_dead;
 	int rxq_def;
 	/* Protect the access to the percpu interrupt registers,
 	 * ensuring that the configuration remains coherent.
@@ -574,6 +575,7 @@ struct mvneta_rx_queue {
 	int next_desc_to_proc;
 };
 
+static enum cpuhp_state online_hpstate;
 /* The hardware supports eight (8) rx queues, but we are only allowing
  * the first one to be used. Therefore, let's just allocate one queue.
  */
@@ -3311,101 +3313,104 @@ static void mvneta_percpu_elect(struct mvneta_port *pp)
 	}
 };
 
-static int mvneta_percpu_notifier(struct notifier_block *nfb,
-				  unsigned long action, void *hcpu)
+static int mvneta_cpu_online(unsigned int cpu, struct hlist_node *node)
 {
-	struct mvneta_port *pp = container_of(nfb, struct mvneta_port,
-					      cpu_notifier);
-	int cpu = (unsigned long)hcpu, other_cpu;
+	int other_cpu;
+	struct mvneta_port *pp = hlist_entry_safe(node, struct mvneta_port,
+						  node_online);
 	struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		spin_lock(&pp->lock);
-		/* Configuring the driver for a new CPU while the
-		 * driver is stopping is racy, so just avoid it.
-		 */
-		if (pp->is_stopped) {
-			spin_unlock(&pp->lock);
-			break;
-		}
-		netif_tx_stop_all_queues(pp->dev);
 
-		/* We have to synchronise on tha napi of each CPU
-		 * except the one just being waked up
-		 */
-		for_each_online_cpu(other_cpu) {
-			if (other_cpu != cpu) {
-				struct mvneta_pcpu_port *other_port =
-					per_cpu_ptr(pp->ports, other_cpu);
+	spin_lock(&pp->lock);
+	/*
+	 * Configuring the driver for a new CPU while the driver is
+	 * stopping is racy, so just avoid it.
+	 */
+	if (pp->is_stopped) {
+		spin_unlock(&pp->lock);
+		return 0;
+	}
+	netif_tx_stop_all_queues(pp->dev);
 
-				napi_synchronize(&other_port->napi);
-			}
+	/*
+	 * We have to synchronise on tha napi of each CPU except the one
+	 * just being woken up
+	 */
+	for_each_online_cpu(other_cpu) {
+		if (other_cpu != cpu) {
+			struct mvneta_pcpu_port *other_port =
+				per_cpu_ptr(pp->ports, other_cpu);
+
+			napi_synchronize(&other_port->napi);
 		}
+	}
 
-		/* Mask all ethernet port interrupts */
-		on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
-		napi_enable(&port->napi);
+	/* Mask all ethernet port interrupts */
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+	napi_enable(&port->napi);
 
+	/*
+	 * Enable per-CPU interrupts on the CPU that is
+	 * brought up.
+	 */
+	mvneta_percpu_enable(pp);
 
-		/* Enable per-CPU interrupts on the CPU that is
-		 * brought up.
-		 */
-		mvneta_percpu_enable(pp);
+	/*
+	 * Enable per-CPU interrupt on the one CPU we care
+	 * about.
+	 */
+	mvneta_percpu_elect(pp);
 
-		/* Enable per-CPU interrupt on the one CPU we care
-		 * about.
-		 */
-		mvneta_percpu_elect(pp);
-
-		/* Unmask all ethernet port interrupts */
-		on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
-		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
-			MVNETA_CAUSE_PHY_STATUS_CHANGE |
-			MVNETA_CAUSE_LINK_CHANGE |
-			MVNETA_CAUSE_PSC_SYNC_CHANGE);
-		netif_tx_start_all_queues(pp->dev);
-		spin_unlock(&pp->lock);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		netif_tx_stop_all_queues(pp->dev);
-		/* Thanks to this lock we are sure that any pending
-		 * cpu election is done
-		 */
-		spin_lock(&pp->lock);
-		/* Mask all ethernet port interrupts */
-		on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
-		spin_unlock(&pp->lock);
+	/* Unmask all ethernet port interrupts */
+	on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
+	mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+		    MVNETA_CAUSE_PHY_STATUS_CHANGE |
+		    MVNETA_CAUSE_LINK_CHANGE |
+		    MVNETA_CAUSE_PSC_SYNC_CHANGE);
+	netif_tx_start_all_queues(pp->dev);
+	spin_unlock(&pp->lock);
+	return 0;
+}
 
-		napi_synchronize(&port->napi);
-		napi_disable(&port->napi);
-		/* Disable per-CPU interrupts on the CPU that is
-		 * brought down.
-		 */
-		mvneta_percpu_disable(pp);
+static int mvneta_cpu_down_prepare(unsigned int cpu, struct hlist_node *node)
+{
+	struct mvneta_port *pp = hlist_entry_safe(node, struct mvneta_port,
+						  node_online);
+	struct mvneta_pcpu_port *port = per_cpu_ptr(pp->ports, cpu);
 
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		/* Check if a new CPU must be elected now this on is down */
-		spin_lock(&pp->lock);
-		mvneta_percpu_elect(pp);
-		spin_unlock(&pp->lock);
-		/* Unmask all ethernet port interrupts */
-		on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
-		mvreg_write(pp, MVNETA_INTR_MISC_MASK,
-			MVNETA_CAUSE_PHY_STATUS_CHANGE |
-			MVNETA_CAUSE_LINK_CHANGE |
-			MVNETA_CAUSE_PSC_SYNC_CHANGE);
-		netif_tx_start_all_queues(pp->dev);
-		break;
-	}
+	/*
+	 * Thanks to this lock we are sure that any pending cpu election is
+	 * done.
+	 */
+	spin_lock(&pp->lock);
+	/* Mask all ethernet port interrupts */
+	on_each_cpu(mvneta_percpu_mask_interrupt, pp, true);
+	spin_unlock(&pp->lock);
 
-	return NOTIFY_OK;
+	napi_synchronize(&port->napi);
+	napi_disable(&port->napi);
+	/* Disable per-CPU interrupts on the CPU that is brought down. */
+	mvneta_percpu_disable(pp);
+	return 0;
+}
+
+static int mvneta_cpu_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct mvneta_port *pp = hlist_entry_safe(node, struct mvneta_port,
+						  node_dead);
+
+	/* Check if a new CPU must be elected now this on is down */
+	spin_lock(&pp->lock);
+	mvneta_percpu_elect(pp);
+	spin_unlock(&pp->lock);
+	/* Unmask all ethernet port interrupts */
+	on_each_cpu(mvneta_percpu_unmask_interrupt, pp, true);
+	mvreg_write(pp, MVNETA_INTR_MISC_MASK,
+		    MVNETA_CAUSE_PHY_STATUS_CHANGE |
+		    MVNETA_CAUSE_LINK_CHANGE |
+		    MVNETA_CAUSE_PSC_SYNC_CHANGE);
+	netif_tx_start_all_queues(pp->dev);
+	return 0;
 }
 
 static int mvneta_open(struct net_device *dev)
@@ -3442,7 +3447,15 @@ static int mvneta_open(struct net_device *dev)
 	/* Register a CPU notifier to handle the case where our CPU
 	 * might be taken offline.
 	 */
-	register_cpu_notifier(&pp->cpu_notifier);
+	ret = cpuhp_state_add_instance_nocalls(online_hpstate,
+					       &pp->node_online);
+	if (ret)
+		goto err_free_irq;
+
+	ret = cpuhp_state_add_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
+					       &pp->node_dead);
+	if (ret)
+		goto err_free_online_hp;
 
 	/* In default link is down */
 	netif_carrier_off(pp->dev);
@@ -3450,15 +3463,19 @@ static int mvneta_open(struct net_device *dev)
 	ret = mvneta_mdio_probe(pp);
 	if (ret < 0) {
 		netdev_err(dev, "cannot probe MDIO bus\n");
-		goto err_free_irq;
+		goto err_free_dead_hp;
 	}
 
 	mvneta_start_dev(pp);
 
 	return 0;
 
+err_free_dead_hp:
+	cpuhp_state_remove_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
+					    &pp->node_dead);
+err_free_online_hp:
+	cpuhp_state_remove_instance_nocalls(online_hpstate, &pp->node_online);
 err_free_irq:
-	unregister_cpu_notifier(&pp->cpu_notifier);
 	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(pp->dev->irq, pp->ports);
 err_cleanup_txqs:
@@ -3484,7 +3501,10 @@ static int mvneta_stop(struct net_device *dev)
 
 	mvneta_stop_dev(pp);
 	mvneta_mdio_remove(pp);
-	unregister_cpu_notifier(&pp->cpu_notifier);
+
+	cpuhp_state_remove_instance_nocalls(online_hpstate, &pp->node_online);
+	cpuhp_state_remove_instance_nocalls(CPUHP_NET_MVNETA_DEAD,
+					    &pp->node_dead);
 	on_each_cpu(mvneta_percpu_disable, pp, true);
 	free_percpu_irq(dev->irq, pp->ports);
 	mvneta_cleanup_rxqs(pp);
@@ -4024,7 +4044,6 @@ static int mvneta_probe(struct platform_device *pdev)
 	err = of_property_read_string(dn, "managed", &managed);
 	pp->use_inband_status = (err == 0 &&
 				 strcmp(managed, "in-band-status") == 0);
-	pp->cpu_notifier.notifier_call = mvneta_percpu_notifier;
 
 	pp->rxq_def = rxq_def;
 
@@ -4227,7 +4246,42 @@ static struct platform_driver mvneta_driver = {
 	},
 };
 
-module_platform_driver(mvneta_driver);
+static int __init mvneta_driver_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "net/mvmeta:online",
+				      mvneta_cpu_online,
+				      mvneta_cpu_down_prepare);
+	if (ret < 0)
+		goto out;
+	online_hpstate = ret;
+	ret = cpuhp_setup_state_multi(CPUHP_NET_MVNETA_DEAD, "net/mvneta:dead",
+				      NULL, mvneta_cpu_dead);
+	if (ret)
+		goto err_dead;
+
+	ret = platform_driver_register(&mvneta_driver);
+	if (ret)
+		goto err;
+	return 0;
+
+err:
+	cpuhp_remove_multi_state(CPUHP_NET_MVNETA_DEAD);
+err_dead:
+	cpuhp_remove_multi_state(online_hpstate);
+out:
+	return ret;
+}
+module_init(mvneta_driver_init);
+
+static void __exit mvneta_driver_exit(void)
+{
+	platform_driver_unregister(&mvneta_driver);
+	cpuhp_remove_multi_state(CPUHP_NET_MVNETA_DEAD);
+	cpuhp_remove_multi_state(online_hpstate);
+}
+module_exit(mvneta_driver_exit);
 
 MODULE_DESCRIPTION("Marvell NETA Ethernet Driver - www.marvell.com");
 MODULE_AUTHOR("Rami Rosen <rosenr@marvell.com>, Thomas Petazzoni <thomas.petazzoni@free-electrons.com>");

drivers/net/virtio_net.c

@@ -138,8 +138,9 @@ struct virtnet_info {
 	/* Does the affinity hint is set for virtqueues? */
 	bool affinity_hint_set;
 
-	/* CPU hot plug notifier */
-	struct notifier_block nb;
+	/* CPU hotplug instances for online & dead */
+	struct hlist_node node;
+	struct hlist_node node_dead;
 
 	/* Control VQ buffers: protected by the rtnl lock */
 	struct virtio_net_ctrl_hdr ctrl_hdr;
@@ -1237,25 +1238,53 @@ static void virtnet_set_affinity(struct virtnet_info *vi)
 	vi->affinity_hint_set = true;
 }
 
-static int virtnet_cpu_callback(struct notifier_block *nfb,
-			        unsigned long action, void *hcpu)
+static int virtnet_cpu_online(unsigned int cpu, struct hlist_node *node)
 {
-	struct virtnet_info *vi = container_of(nfb, struct virtnet_info, nb);
+	struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info,
+						   node);
+	virtnet_set_affinity(vi);
+	return 0;
+}
 
-	switch(action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-	case CPU_DOWN_FAILED:
-	case CPU_DEAD:
-		virtnet_set_affinity(vi);
-		break;
-	case CPU_DOWN_PREPARE:
-		virtnet_clean_affinity(vi, (long)hcpu);
-		break;
-	default:
-		break;
-	}
+static int virtnet_cpu_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info,
+						   node_dead);
+	virtnet_set_affinity(vi);
+	return 0;
+}
 
-	return NOTIFY_OK;
+static int virtnet_cpu_down_prep(unsigned int cpu, struct hlist_node *node)
+{
+	struct virtnet_info *vi = hlist_entry_safe(node, struct virtnet_info,
+						   node);
+
+	virtnet_clean_affinity(vi, cpu);
+	return 0;
+}
+
+static enum cpuhp_state virtionet_online;
+
+static int virtnet_cpu_notif_add(struct virtnet_info *vi)
+{
+	int ret;
+
+	ret = cpuhp_state_add_instance_nocalls(virtionet_online, &vi->node);
+	if (ret)
+		return ret;
+	ret = cpuhp_state_add_instance_nocalls(CPUHP_VIRT_NET_DEAD,
+					       &vi->node_dead);
+	if (!ret)
+		return ret;
+	cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node);
+	return ret;
+}
+
+static void virtnet_cpu_notif_remove(struct virtnet_info *vi)
+{
+	cpuhp_state_remove_instance_nocalls(virtionet_online, &vi->node);
+	cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_NET_DEAD,
+					    &vi->node_dead);
 }
 
 static void virtnet_get_ringparam(struct net_device *dev,
@@ -1879,8 +1908,7 @@ static int virtnet_probe(struct virtio_device *vdev)
 
 	virtio_device_ready(vdev);
 
-	vi->nb.notifier_call = &virtnet_cpu_callback;
-	err = register_hotcpu_notifier(&vi->nb);
+	err = virtnet_cpu_notif_add(vi);
 	if (err) {
 		pr_debug("virtio_net: registering cpu notifier failed\n");
 		goto free_unregister_netdev;
@@ -1934,7 +1962,7 @@ static void virtnet_remove(struct virtio_device *vdev)
 {
 	struct virtnet_info *vi = vdev->priv;
 
-	unregister_hotcpu_notifier(&vi->nb);
+	virtnet_cpu_notif_remove(vi);
 
 	/* Make sure no work handler is accessing the device. */
 	flush_work(&vi->config_work);
@@ -1953,7 +1981,7 @@ static int virtnet_freeze(struct virtio_device *vdev)
 	struct virtnet_info *vi = vdev->priv;
 	int i;
 
-	unregister_hotcpu_notifier(&vi->nb);
+	virtnet_cpu_notif_remove(vi);
 
 	/* Make sure no work handler is accessing the device */
 	flush_work(&vi->config_work);
@@ -1997,7 +2025,7 @@ static int virtnet_restore(struct virtio_device *vdev)
 	virtnet_set_queues(vi, vi->curr_queue_pairs);
 	rtnl_unlock();
 
-	err = register_hotcpu_notifier(&vi->nb);
+	err = virtnet_cpu_notif_add(vi);
 	if (err)
 		return err;
 
@@ -2039,7 +2067,41 @@ static struct virtio_driver virtio_net_driver = {
 #endif
 };
 
-module_virtio_driver(virtio_net_driver);
+static __init int virtio_net_driver_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "AP_VIRT_NET_ONLINE",
+				      virtnet_cpu_online,
+				      virtnet_cpu_down_prep);
+	if (ret < 0)
+		goto out;
+	virtionet_online = ret;
+	ret = cpuhp_setup_state_multi(CPUHP_VIRT_NET_DEAD, "VIRT_NET_DEAD",
+				      NULL, virtnet_cpu_dead);
+	if (ret)
+		goto err_dead;
+
+        ret = register_virtio_driver(&virtio_net_driver);
+	if (ret)
+		goto err_virtio;
+	return 0;
+err_virtio:
+	cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD);
+err_dead:
+	cpuhp_remove_multi_state(virtionet_online);
+out:
+	return ret;
+}
+module_init(virtio_net_driver_init);
+
+static __exit void virtio_net_driver_exit(void)
+{
+	cpuhp_remove_multi_state(CPUHP_VIRT_NET_DEAD);
+	cpuhp_remove_multi_state(virtionet_online);
+	unregister_virtio_driver(&virtio_net_driver);
+}
+module_exit(virtio_net_driver_exit);
 
 MODULE_DEVICE_TABLE(virtio, id_table);
 MODULE_DESCRIPTION("Virtio network driver");

drivers/oprofile/timer_int.c

@@ -74,37 +74,39 @@ static void oprofile_hrtimer_stop(void)
 	put_online_cpus();
 }
 
-static int oprofile_cpu_notify(struct notifier_block *self,
-			       unsigned long action, void *hcpu)
+static int oprofile_timer_online(unsigned int cpu)
 {
-	long cpu = (long) hcpu;
-
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		smp_call_function_single(cpu, __oprofile_hrtimer_start,
-					 NULL, 1);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		__oprofile_hrtimer_stop(cpu);
-		break;
-	}
-	return NOTIFY_OK;
+	local_irq_disable();
+	__oprofile_hrtimer_start(NULL);
+	local_irq_enable();
+	return 0;
 }
 
-static struct notifier_block __refdata oprofile_cpu_notifier = {
-	.notifier_call = oprofile_cpu_notify,
-};
+static int oprofile_timer_prep_down(unsigned int cpu)
+{
+	__oprofile_hrtimer_stop(cpu);
+	return 0;
+}
+
+static enum cpuhp_state hp_online;
 
 static int oprofile_hrtimer_setup(void)
 {
-	return register_hotcpu_notifier(&oprofile_cpu_notifier);
+	int ret;
+
+	ret = cpuhp_setup_state_nocalls(CPUHP_AP_ONLINE_DYN,
+					"oprofile/timer:online",
+					oprofile_timer_online,
+					oprofile_timer_prep_down);
+	if (ret < 0)
+		return ret;
+	hp_online = ret;
+	return 0;
 }
 
 static void oprofile_hrtimer_shutdown(void)
 {
-	unregister_hotcpu_notifier(&oprofile_cpu_notifier);
+	cpuhp_remove_state_nocalls(hp_online);
 }
 
 int oprofile_timer_init(struct oprofile_operations *ops)

drivers/perf/arm_pmu.c

@@ -709,28 +709,20 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 	return 0;
 }
 
-static DEFINE_SPINLOCK(arm_pmu_lock);
-static LIST_HEAD(arm_pmu_list);
-
 /*
  * PMU hardware loses all context when a CPU goes offline.
  * When a CPU is hotplugged back in, since some hardware registers are
  * UNKNOWN at reset, the PMU must be explicitly reset to avoid reading
  * junk values out of them.
  */
-static int arm_perf_starting_cpu(unsigned int cpu)
+static int arm_perf_starting_cpu(unsigned int cpu, struct hlist_node *node)
 {
-	struct arm_pmu *pmu;
-
-	spin_lock(&arm_pmu_lock);
-	list_for_each_entry(pmu, &arm_pmu_list, entry) {
+	struct arm_pmu *pmu = hlist_entry_safe(node, struct arm_pmu, node);
 
-		if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
-			continue;
-		if (pmu->reset)
-			pmu->reset(pmu);
-	}
-	spin_unlock(&arm_pmu_lock);
+	if (!cpumask_test_cpu(cpu, &pmu->supported_cpus))
+		return 0;
+	if (pmu->reset)
+		pmu->reset(pmu);
 	return 0;
 }
 
@@ -842,9 +834,10 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	if (!cpu_hw_events)
 		return -ENOMEM;
 
-	spin_lock(&arm_pmu_lock);
-	list_add_tail(&cpu_pmu->entry, &arm_pmu_list);
-	spin_unlock(&arm_pmu_lock);
+	err = cpuhp_state_add_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING,
+					       &cpu_pmu->node);
+	if (err)
+		goto out_free;
 
 	err = cpu_pm_pmu_register(cpu_pmu);
 	if (err)
@@ -880,9 +873,9 @@ static int cpu_pmu_init(struct arm_pmu *cpu_pmu)
 	return 0;
 
 out_unregister:
-	spin_lock(&arm_pmu_lock);
-	list_del(&cpu_pmu->entry);
-	spin_unlock(&arm_pmu_lock);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING,
+					    &cpu_pmu->node);
+out_free:
 	free_percpu(cpu_hw_events);
 	return err;
 }
@@ -890,9 +883,8 @@ out_unregister:
 static void cpu_pmu_destroy(struct arm_pmu *cpu_pmu)
 {
 	cpu_pm_pmu_unregister(cpu_pmu);
-	spin_lock(&arm_pmu_lock);
-	list_del(&cpu_pmu->entry);
-	spin_unlock(&arm_pmu_lock);
+	cpuhp_state_remove_instance_nocalls(CPUHP_AP_PERF_ARM_STARTING,
+					    &cpu_pmu->node);
 	free_percpu(cpu_pmu->hw_events);
 }
 
@@ -1091,9 +1083,9 @@ static int arm_pmu_hp_init(void)
 {
 	int ret;
 
-	ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_STARTING,
-					"AP_PERF_ARM_STARTING",
-					arm_perf_starting_cpu, NULL);
+	ret = cpuhp_setup_state_multi(CPUHP_AP_PERF_ARM_STARTING,
+				      "AP_PERF_ARM_STARTING",
+				      arm_perf_starting_cpu, NULL);
 	if (ret)
 		pr_err("CPU hotplug notifier for ARM PMU could not be registered: %d\n",
 		       ret);

drivers/scsi/virtio_scsi.c

@@ -107,8 +107,8 @@ struct virtio_scsi {
 	/* If the affinity hint is set for virtqueues */
 	bool affinity_hint_set;
 
-	/* CPU hotplug notifier */
-	struct notifier_block nb;
+	struct hlist_node node;
+	struct hlist_node node_dead;
 
 	/* Protected by event_vq lock */
 	bool stop_events;
@@ -118,6 +118,7 @@ struct virtio_scsi {
 	struct virtio_scsi_vq req_vqs[];
 };
 
+static enum cpuhp_state virtioscsi_online;
 static struct kmem_cache *virtscsi_cmd_cache;
 static mempool_t *virtscsi_cmd_pool;
 
@@ -852,21 +853,33 @@ static void virtscsi_set_affinity(struct virtio_scsi *vscsi, bool affinity)
 	put_online_cpus();
 }
 
-static int virtscsi_cpu_callback(struct notifier_block *nfb,
-				 unsigned long action, void *hcpu)
+static int virtscsi_cpu_online(unsigned int cpu, struct hlist_node *node)
 {
-	struct virtio_scsi *vscsi = container_of(nfb, struct virtio_scsi, nb);
-	switch(action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		__virtscsi_set_affinity(vscsi, true);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
+	struct virtio_scsi *vscsi = hlist_entry_safe(node, struct virtio_scsi,
+						     node);
+	__virtscsi_set_affinity(vscsi, true);
+	return 0;
+}
+
+static int virtscsi_cpu_notif_add(struct virtio_scsi *vi)
+{
+	int ret;
+
+	ret = cpuhp_state_add_instance(virtioscsi_online, &vi->node);
+	if (ret)
+		return ret;
+
+	ret = cpuhp_state_add_instance(CPUHP_VIRT_SCSI_DEAD, &vi->node_dead);
+	if (ret)
+		cpuhp_state_remove_instance(virtioscsi_online, &vi->node);
+	return ret;
+}
+
+static void virtscsi_cpu_notif_remove(struct virtio_scsi *vi)
+{
+	cpuhp_state_remove_instance_nocalls(virtioscsi_online, &vi->node);
+	cpuhp_state_remove_instance_nocalls(CPUHP_VIRT_SCSI_DEAD,
+					    &vi->node_dead);
 }
 
 static void virtscsi_init_vq(struct virtio_scsi_vq *virtscsi_vq,
@@ -929,8 +942,6 @@ static int virtscsi_init(struct virtio_device *vdev,
 		virtscsi_init_vq(&vscsi->req_vqs[i - VIRTIO_SCSI_VQ_BASE],
 				 vqs[i]);
 
-	virtscsi_set_affinity(vscsi, true);
-
 	virtscsi_config_set(vdev, cdb_size, VIRTIO_SCSI_CDB_SIZE);
 	virtscsi_config_set(vdev, sense_size, VIRTIO_SCSI_SENSE_SIZE);
 
@@ -987,12 +998,9 @@ static int virtscsi_probe(struct virtio_device *vdev)
 	if (err)
 		goto virtscsi_init_failed;
 
-	vscsi->nb.notifier_call = &virtscsi_cpu_callback;
-	err = register_hotcpu_notifier(&vscsi->nb);
-	if (err) {
-		pr_err("registering cpu notifier failed\n");
+	err = virtscsi_cpu_notif_add(vscsi);
+	if (err)
 		goto scsi_add_host_failed;
-	}
 
 	cmd_per_lun = virtscsi_config_get(vdev, cmd_per_lun) ?: 1;
 	shost->cmd_per_lun = min_t(u32, cmd_per_lun, shost->can_queue);
@@ -1049,7 +1057,7 @@ static void virtscsi_remove(struct virtio_device *vdev)
 
 	scsi_remove_host(shost);
 
-	unregister_hotcpu_notifier(&vscsi->nb);
+	virtscsi_cpu_notif_remove(vscsi);
 
 	virtscsi_remove_vqs(vdev);
 	scsi_host_put(shost);
@@ -1061,7 +1069,7 @@ static int virtscsi_freeze(struct virtio_device *vdev)
 	struct Scsi_Host *sh = virtio_scsi_host(vdev);
 	struct virtio_scsi *vscsi = shost_priv(sh);
 
-	unregister_hotcpu_notifier(&vscsi->nb);
+	virtscsi_cpu_notif_remove(vscsi);
 	virtscsi_remove_vqs(vdev);
 	return 0;
 }
@@ -1076,12 +1084,11 @@ static int virtscsi_restore(struct virtio_device *vdev)
 	if (err)
 		return err;
 
-	err = register_hotcpu_notifier(&vscsi->nb);
+	err = virtscsi_cpu_notif_add(vscsi);
 	if (err) {
 		vdev->config->del_vqs(vdev);
 		return err;
 	}
-
 	virtio_device_ready(vdev);
 
 	if (virtio_has_feature(vdev, VIRTIO_SCSI_F_HOTPLUG))
@@ -1136,6 +1143,16 @@ static int __init init(void)
 		pr_err("mempool_create() for virtscsi_cmd_pool failed\n");
 		goto error;
 	}
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+				      "scsi/virtio:online",
+				      virtscsi_cpu_online, NULL);
+	if (ret < 0)
+		goto error;
+	virtioscsi_online = ret;
+	ret = cpuhp_setup_state_multi(CPUHP_VIRT_SCSI_DEAD, "scsi/virtio:dead",
+				      NULL, virtscsi_cpu_online);
+	if (ret)
+		goto error;
 	ret = register_virtio_driver(&virtio_scsi_driver);
 	if (ret < 0)
 		goto error;
@@ -1151,12 +1168,17 @@ error:
 		kmem_cache_destroy(virtscsi_cmd_cache);
 		virtscsi_cmd_cache = NULL;
 	}
+	if (virtioscsi_online)
+		cpuhp_remove_multi_state(virtioscsi_online);
+	cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD);
 	return ret;
 }
 
 static void __exit fini(void)
 {
 	unregister_virtio_driver(&virtio_scsi_driver);
+	cpuhp_remove_multi_state(virtioscsi_online);
+	cpuhp_remove_multi_state(CPUHP_VIRT_SCSI_DEAD);
 	mempool_destroy(virtscsi_cmd_pool);
 	kmem_cache_destroy(virtscsi_cmd_cache);
 }

include/acpi/processor.h

@@ -359,7 +359,7 @@ extern int acpi_processor_set_throttling(struct acpi_processor *pr,
  * onlined/offlined. In such case the flags.throttling will be updated.
  */
 extern void acpi_processor_reevaluate_tstate(struct acpi_processor *pr,
-			unsigned long action);
+			bool is_dead);
 extern const struct file_operations acpi_processor_throttling_fops;
 extern void acpi_processor_throttling_init(void);
 #else
@@ -380,7 +380,7 @@ static inline int acpi_processor_set_throttling(struct acpi_processor *pr,
 }
 
 static inline void acpi_processor_reevaluate_tstate(struct acpi_processor *pr,
-			unsigned long action) {}
+			bool is_dead) {}
 
 static inline void acpi_processor_throttling_init(void) {}
 #endif	/* CONFIG_ACPI_CPU_FREQ_PSS */

include/linux/cpu.h

@@ -61,17 +61,8 @@ struct notifier_block;
 #define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
 #define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
-#define CPU_DYING		0x0008 /* CPU (unsigned)v not running any task,
-					* not handling interrupts, soon dead.
-					* Called on the dying cpu, interrupts
-					* are already disabled. Must not
-					* sleep, must not fail */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
-#define CPU_STARTING		0x000A /* CPU (unsigned)v soon running.
-					* Called on the new cpu, just before
-					* enabling interrupts. Must not sleep,
-					* must not fail */
 #define CPU_BROKEN		0x000B /* CPU (unsigned)v did not die properly,
 					* perhaps due to preemption. */
 
@@ -86,9 +77,6 @@ struct notifier_block;
 #define CPU_DOWN_PREPARE_FROZEN	(CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
 #define CPU_DOWN_FAILED_FROZEN	(CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
 #define CPU_DEAD_FROZEN		(CPU_DEAD | CPU_TASKS_FROZEN)
-#define CPU_DYING_FROZEN	(CPU_DYING | CPU_TASKS_FROZEN)
-#define CPU_STARTING_FROZEN	(CPU_STARTING | CPU_TASKS_FROZEN)
-
 
 #ifdef CONFIG_SMP
 extern bool cpuhp_tasks_frozen;

include/linux/cpuhotplug.h

@@ -16,15 +16,40 @@ enum cpuhp_state {
 	CPUHP_PERF_SUPERH,
 	CPUHP_X86_HPET_DEAD,
 	CPUHP_X86_APB_DEAD,
+	CPUHP_VIRT_NET_DEAD,
+	CPUHP_SLUB_DEAD,
+	CPUHP_MM_WRITEBACK_DEAD,
+	CPUHP_SOFTIRQ_DEAD,
+	CPUHP_NET_MVNETA_DEAD,
+	CPUHP_CPUIDLE_DEAD,
+	CPUHP_ARM64_FPSIMD_DEAD,
+	CPUHP_ARM_OMAP_WAKE_DEAD,
+	CPUHP_IRQ_POLL_DEAD,
+	CPUHP_BLOCK_SOFTIRQ_DEAD,
+	CPUHP_VIRT_SCSI_DEAD,
+	CPUHP_ACPI_CPUDRV_DEAD,
+	CPUHP_S390_PFAULT_DEAD,
+	CPUHP_BLK_MQ_DEAD,
 	CPUHP_WORKQUEUE_PREP,
 	CPUHP_POWER_NUMA_PREPARE,
 	CPUHP_HRTIMERS_PREPARE,
 	CPUHP_PROFILE_PREPARE,
 	CPUHP_X2APIC_PREPARE,
 	CPUHP_SMPCFD_PREPARE,
+	CPUHP_RELAY_PREPARE,
+	CPUHP_SLAB_PREPARE,
+	CPUHP_MD_RAID5_PREPARE,
 	CPUHP_RCUTREE_PREP,
+	CPUHP_CPUIDLE_COUPLED_PREPARE,
+	CPUHP_POWERPC_PMAC_PREPARE,
+	CPUHP_POWERPC_MMU_CTX_PREPARE,
 	CPUHP_NOTIFY_PREPARE,
+	CPUHP_ARM_SHMOBILE_SCU_PREPARE,
+	CPUHP_SH_SH3X_PREPARE,
+	CPUHP_BLK_MQ_PREPARE,
 	CPUHP_TIMERS_DEAD,
+	CPUHP_NOTF_ERR_INJ_PREPARE,
+	CPUHP_MIPS_SOC_PREPARE,
 	CPUHP_BRINGUP_CPU,
 	CPUHP_AP_IDLE_DEAD,
 	CPUHP_AP_OFFLINE,
@@ -72,7 +97,6 @@ enum cpuhp_state {
 	CPUHP_AP_ARM64_ISNDEP_STARTING,
 	CPUHP_AP_SMPCFD_DYING,
 	CPUHP_AP_X86_TBOOT_DYING,
-	CPUHP_AP_NOTIFY_STARTING,
 	CPUHP_AP_ONLINE,
 	CPUHP_TEARDOWN_CPU,
 	CPUHP_AP_ONLINE_IDLE,
@@ -103,7 +127,7 @@ enum cpuhp_state {
 
 int __cpuhp_setup_state(enum cpuhp_state state,	const char *name, bool invoke,
 			int (*startup)(unsigned int cpu),
-			int (*teardown)(unsigned int cpu));
+			int (*teardown)(unsigned int cpu), bool multi_instance);
 
 /**
  * cpuhp_setup_state - Setup hotplug state callbacks with calling the callbacks
@@ -120,7 +144,7 @@ static inline int cpuhp_setup_state(enum cpuhp_state state,
 				    int (*startup)(unsigned int cpu),
 				    int (*teardown)(unsigned int cpu))
 {
-	return __cpuhp_setup_state(state, name, true, startup, teardown);
+	return __cpuhp_setup_state(state, name, true, startup, teardown, false);
 }
 
 /**
@@ -139,7 +163,66 @@ static inline int cpuhp_setup_state_nocalls(enum cpuhp_state state,
 					    int (*startup)(unsigned int cpu),
 					    int (*teardown)(unsigned int cpu))
 {
-	return __cpuhp_setup_state(state, name, false, startup, teardown);
+	return __cpuhp_setup_state(state, name, false, startup, teardown,
+				   false);
+}
+
+/**
+ * cpuhp_setup_state_multi - Add callbacks for multi state
+ * @state:	The state for which the calls are installed
+ * @name:	Name of the callback.
+ * @startup:	startup callback function
+ * @teardown:	teardown callback function
+ *
+ * Sets the internal multi_instance flag and prepares a state to work as a multi
+ * instance callback. No callbacks are invoked at this point. The callbacks are
+ * invoked once an instance for this state are registered via
+ * @cpuhp_state_add_instance or @cpuhp_state_add_instance_nocalls.
+ */
+static inline int cpuhp_setup_state_multi(enum cpuhp_state state,
+					  const char *name,
+					  int (*startup)(unsigned int cpu,
+							 struct hlist_node *node),
+					  int (*teardown)(unsigned int cpu,
+							  struct hlist_node *node))
+{
+	return __cpuhp_setup_state(state, name, false,
+				   (void *) startup,
+				   (void *) teardown, true);
+}
+
+int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
+			       bool invoke);
+
+/**
+ * cpuhp_state_add_instance - Add an instance for a state and invoke startup
+ *                            callback.
+ * @state:	The state for which the instance is installed
+ * @node:	The node for this individual state.
+ *
+ * Installs the instance for the @state and invokes the startup callback on
+ * the present cpus which have already reached the @state. The @state must have
+ * been earlier marked as multi-instance by @cpuhp_setup_state_multi.
+ */
+static inline int cpuhp_state_add_instance(enum cpuhp_state state,
+					   struct hlist_node *node)
+{
+	return __cpuhp_state_add_instance(state, node, true);
+}
+
+/**
+ * cpuhp_state_add_instance_nocalls - Add an instance for a state without
+ *                                    invoking the startup callback.
+ * @state:	The state for which the instance is installed
+ * @node:	The node for this individual state.
+ *
+ * Installs the instance for the @state The @state must have been earlier
+ * marked as multi-instance by @cpuhp_setup_state_multi.
+ */
+static inline int cpuhp_state_add_instance_nocalls(enum cpuhp_state state,
+						   struct hlist_node *node)
+{
+	return __cpuhp_state_add_instance(state, node, false);
 }
 
 void __cpuhp_remove_state(enum cpuhp_state state, bool invoke);
@@ -166,6 +249,51 @@ static inline void cpuhp_remove_state_nocalls(enum cpuhp_state state)
 	__cpuhp_remove_state(state, false);
 }
 
+/**
+ * cpuhp_remove_multi_state - Remove hotplug multi state callback
+ * @state:	The state for which the calls are removed
+ *
+ * Removes the callback functions from a multi state. This is the reverse of
+ * cpuhp_setup_state_multi(). All instances should have been removed before
+ * invoking this function.
+ */
+static inline void cpuhp_remove_multi_state(enum cpuhp_state state)
+{
+	__cpuhp_remove_state(state, false);
+}
+
+int __cpuhp_state_remove_instance(enum cpuhp_state state,
+				  struct hlist_node *node, bool invoke);
+
+/**
+ * cpuhp_state_remove_instance - Remove hotplug instance from state and invoke
+ *                               the teardown callback
+ * @state:	The state from which the instance is removed
+ * @node:	The node for this individual state.
+ *
+ * Removes the instance and invokes the teardown callback on the present cpus
+ * which have already reached the @state.
+ */
+static inline int cpuhp_state_remove_instance(enum cpuhp_state state,
+					      struct hlist_node *node)
+{
+	return __cpuhp_state_remove_instance(state, node, true);
+}
+
+/**
+ * cpuhp_state_remove_instance_nocalls - Remove hotplug instance from state
+ *					 without invoking the reatdown callback
+ * @state:	The state from which the instance is removed
+ * @node:	The node for this individual state.
+ *
+ * Removes the instance without invoking the teardown callback.
+ */
+static inline int cpuhp_state_remove_instance_nocalls(enum cpuhp_state state,
+						      struct hlist_node *node)
+{
+	return __cpuhp_state_remove_instance(state, node, false);
+}
+
 #ifdef CONFIG_SMP
 void cpuhp_online_idle(enum cpuhp_state state);
 #else

include/linux/padata.h

@@ -151,7 +151,7 @@ struct parallel_data {
  * @flags: padata flags.
  */
 struct padata_instance {
-	struct notifier_block		 cpu_notifier;
+	struct hlist_node		 node;
 	struct workqueue_struct		*wq;
 	struct parallel_data		*pd;
 	struct padata_cpumask		cpumask;

include/linux/perf/arm_pmu.h

@@ -116,7 +116,7 @@ struct arm_pmu {
 	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 	struct platform_device	*plat_device;
 	struct pmu_hw_events	__percpu *hw_events;
-	struct list_head	entry;
+	struct hlist_node	node;
 	struct notifier_block	cpu_pm_nb;
 	/* the attr_groups array must be NULL-terminated */
 	const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1];

include/linux/relay.h

@@ -19,6 +19,7 @@
 #include <linux/fs.h>
 #include <linux/poll.h>
 #include <linux/kref.h>
+#include <linux/percpu.h>
 
 /*
  * Tracks changes to rchan/rchan_buf structs
@@ -63,7 +64,7 @@ struct rchan
 	struct kref kref;		/* channel refcount */
 	void *private_data;		/* for user-defined data */
 	size_t last_toobig;		/* tried to log event > subbuf size */
-	struct rchan_buf *buf[NR_CPUS]; /* per-cpu channel buffers */
+	struct rchan_buf ** __percpu buf; /* per-cpu channel buffers */
 	int is_global;			/* One global buffer ? */
 	struct list_head list;		/* for channel list */
 	struct dentry *parent;		/* parent dentry passed to open */
@@ -204,7 +205,7 @@ static inline void relay_write(struct rchan *chan,
 	struct rchan_buf *buf;
 
 	local_irq_save(flags);
-	buf = chan->buf[smp_processor_id()];
+	buf = *this_cpu_ptr(chan->buf);
 	if (unlikely(buf->offset + length > chan->subbuf_size))
 		length = relay_switch_subbuf(buf, length);
 	memcpy(buf->data + buf->offset, data, length);
@@ -230,12 +231,12 @@ static inline void __relay_write(struct rchan *chan,
 {
 	struct rchan_buf *buf;
 
-	buf = chan->buf[get_cpu()];
+	buf = *get_cpu_ptr(chan->buf);
 	if (unlikely(buf->offset + length > buf->chan->subbuf_size))
 		length = relay_switch_subbuf(buf, length);
 	memcpy(buf->data + buf->offset, data, length);
 	buf->offset += length;
-	put_cpu();
+	put_cpu_ptr(chan->buf);
 }
 
 /**
@@ -251,17 +252,19 @@ static inline void __relay_write(struct rchan *chan,
  */
 static inline void *relay_reserve(struct rchan *chan, size_t length)
 {
-	void *reserved;
-	struct rchan_buf *buf = chan->buf[smp_processor_id()];
+	void *reserved = NULL;
+	struct rchan_buf *buf = *get_cpu_ptr(chan->buf);
 
 	if (unlikely(buf->offset + length > buf->chan->subbuf_size)) {
 		length = relay_switch_subbuf(buf, length);
 		if (!length)
-			return NULL;
+			goto end;
 	}
 	reserved = buf->data + buf->offset;
 	buf->offset += length;
 
+end:
+	put_cpu_ptr(chan->buf);
 	return reserved;
 }
 
@@ -285,5 +288,11 @@ static inline void subbuf_start_reserve(struct rchan_buf *buf,
  */
 extern const struct file_operations relay_file_operations;
 
+#ifdef CONFIG_RELAY
+int relay_prepare_cpu(unsigned int cpu);
+#else
+#define relay_prepare_cpu     NULL
+#endif
+
 #endif /* _LINUX_RELAY_H */
 

include/linux/slab.h

@@ -650,4 +650,12 @@ static inline void *kzalloc_node(size_t size, gfp_t flags, int node)
 unsigned int kmem_cache_size(struct kmem_cache *s);
 void __init kmem_cache_init_late(void);
 
+#if defined(CONFIG_SMP) && defined(CONFIG_SLAB)
+int slab_prepare_cpu(unsigned int cpu);
+int slab_dead_cpu(unsigned int cpu);
+#else
+#define slab_prepare_cpu	NULL
+#define slab_dead_cpu		NULL
+#endif
+
 #endif	/* _LINUX_SLAB_H */

include/trace/events/cpuhp.h

@@ -33,6 +33,34 @@ TRACE_EVENT(cpuhp_enter,
 		  __entry->cpu, __entry->target, __entry->idx, __entry->fun)
 );
 
+TRACE_EVENT(cpuhp_multi_enter,
+
+	TP_PROTO(unsigned int cpu,
+		 int target,
+		 int idx,
+		 int (*fun)(unsigned int, struct hlist_node *),
+		 struct hlist_node *node),
+
+	TP_ARGS(cpu, target, idx, fun, node),
+
+	TP_STRUCT__entry(
+		__field( unsigned int,	cpu		)
+		__field( int,		target		)
+		__field( int,		idx		)
+		__field( void *,	fun		)
+	),
+
+	TP_fast_assign(
+		__entry->cpu	= cpu;
+		__entry->target	= target;
+		__entry->idx	= idx;
+		__entry->fun	= fun;
+	),
+
+	TP_printk("cpu: %04u target: %3d step: %3d (%pf)",
+		  __entry->cpu, __entry->target, __entry->idx, __entry->fun)
+);
+
 TRACE_EVENT(cpuhp_exit,
 
 	TP_PROTO(unsigned int cpu,

kernel/cpu.c

@@ -23,6 +23,8 @@
 #include <linux/tick.h>
 #include <linux/irq.h>
 #include <linux/smpboot.h>
+#include <linux/relay.h>
+#include <linux/slab.h>
 
 #include <trace/events/power.h>
 #define CREATE_TRACE_POINTS
@@ -37,8 +39,9 @@
  * @thread:	Pointer to the hotplug thread
  * @should_run:	Thread should execute
  * @rollback:	Perform a rollback
- * @cb_stat:	The state for a single callback (install/uninstall)
- * @cb:		Single callback function (install/uninstall)
+ * @single:	Single callback invocation
+ * @bringup:	Single callback bringup or teardown selector
+ * @cb_state:	The state for a single callback (install/uninstall)
  * @result:	Result of the operation
  * @done:	Signal completion to the issuer of the task
  */
@@ -49,8 +52,10 @@ struct cpuhp_cpu_state {
 	struct task_struct	*thread;
 	bool			should_run;
 	bool			rollback;
+	bool			single;
+	bool			bringup;
+	struct hlist_node	*node;
 	enum cpuhp_state	cb_state;
-	int			(*cb)(unsigned int cpu);
 	int			result;
 	struct completion	done;
 #endif
@@ -68,35 +73,103 @@ static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state);
  * @cant_stop:	Bringup/teardown can't be stopped at this step
  */
 struct cpuhp_step {
-	const char	*name;
-	int		(*startup)(unsigned int cpu);
-	int		(*teardown)(unsigned int cpu);
-	bool		skip_onerr;
-	bool		cant_stop;
+	const char		*name;
+	union {
+		int		(*single)(unsigned int cpu);
+		int		(*multi)(unsigned int cpu,
+					 struct hlist_node *node);
+	} startup;
+	union {
+		int		(*single)(unsigned int cpu);
+		int		(*multi)(unsigned int cpu,
+					 struct hlist_node *node);
+	} teardown;
+	struct hlist_head	list;
+	bool			skip_onerr;
+	bool			cant_stop;
+	bool			multi_instance;
 };
 
 static DEFINE_MUTEX(cpuhp_state_mutex);
 static struct cpuhp_step cpuhp_bp_states[];
 static struct cpuhp_step cpuhp_ap_states[];
 
+static bool cpuhp_is_ap_state(enum cpuhp_state state)
+{
+	/*
+	 * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
+	 * purposes as that state is handled explicitly in cpu_down.
+	 */
+	return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
+}
+
+static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
+{
+	struct cpuhp_step *sp;
+
+	sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
+	return sp + state;
+}
+
 /**
  * cpuhp_invoke_callback _ Invoke the callbacks for a given state
  * @cpu:	The cpu for which the callback should be invoked
  * @step:	The step in the state machine
- * @cb:		The callback function to invoke
+ * @bringup:	True if the bringup callback should be invoked
  *
- * Called from cpu hotplug and from the state register machinery
+ * Called from cpu hotplug and from the state register machinery.
  */
-static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state step,
-				 int (*cb)(unsigned int))
+static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state,
+				 bool bringup, struct hlist_node *node)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
-	int ret = 0;
-
-	if (cb) {
-		trace_cpuhp_enter(cpu, st->target, step, cb);
+	struct cpuhp_step *step = cpuhp_get_step(state);
+	int (*cbm)(unsigned int cpu, struct hlist_node *node);
+	int (*cb)(unsigned int cpu);
+	int ret, cnt;
+
+	if (!step->multi_instance) {
+		cb = bringup ? step->startup.single : step->teardown.single;
+		if (!cb)
+			return 0;
+		trace_cpuhp_enter(cpu, st->target, state, cb);
 		ret = cb(cpu);
-		trace_cpuhp_exit(cpu, st->state, step, ret);
+		trace_cpuhp_exit(cpu, st->state, state, ret);
+		return ret;
+	}
+	cbm = bringup ? step->startup.multi : step->teardown.multi;
+	if (!cbm)
+		return 0;
+
+	/* Single invocation for instance add/remove */
+	if (node) {
+		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
+		ret = cbm(cpu, node);
+		trace_cpuhp_exit(cpu, st->state, state, ret);
+		return ret;
+	}
+
+	/* State transition. Invoke on all instances */
+	cnt = 0;
+	hlist_for_each(node, &step->list) {
+		trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node);
+		ret = cbm(cpu, node);
+		trace_cpuhp_exit(cpu, st->state, state, ret);
+		if (ret)
+			goto err;
+		cnt++;
+	}
+	return 0;
+err:
+	/* Rollback the instances if one failed */
+	cbm = !bringup ? step->startup.multi : step->teardown.multi;
+	if (!cbm)
+		return ret;
+
+	hlist_for_each(node, &step->list) {
+		if (!cnt--)
+			break;
+		cbm(cpu, node);
 	}
 	return ret;
 }
@@ -260,10 +333,17 @@ void cpu_hotplug_disable(void)
 }
 EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
 
+static void __cpu_hotplug_enable(void)
+{
+	if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n"))
+		return;
+	cpu_hotplug_disabled--;
+}
+
 void cpu_hotplug_enable(void)
 {
 	cpu_maps_update_begin();
-	WARN_ON(--cpu_hotplug_disabled < 0);
+	__cpu_hotplug_enable();
 	cpu_maps_update_done();
 }
 EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
@@ -330,12 +410,6 @@ static int notify_online(unsigned int cpu)
 	return 0;
 }
 
-static int notify_starting(unsigned int cpu)
-{
-	cpu_notify(CPU_STARTING, cpu);
-	return 0;
-}
-
 static int bringup_wait_for_ap(unsigned int cpu)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
@@ -349,8 +423,16 @@ static int bringup_cpu(unsigned int cpu)
 	struct task_struct *idle = idle_thread_get(cpu);
 	int ret;
 
+	/*
+	 * Some architectures have to walk the irq descriptors to
+	 * setup the vector space for the cpu which comes online.
+	 * Prevent irq alloc/free across the bringup.
+	 */
+	irq_lock_sparse();
+
 	/* Arch-specific enabling code. */
 	ret = __cpu_up(cpu, idle);
+	irq_unlock_sparse();
 	if (ret) {
 		cpu_notify(CPU_UP_CANCELED, cpu);
 		return ret;
@@ -363,62 +445,55 @@ static int bringup_cpu(unsigned int cpu)
 /*
  * Hotplug state machine related functions
  */
-static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st,
-			  struct cpuhp_step *steps)
+static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st)
 {
 	for (st->state++; st->state < st->target; st->state++) {
-		struct cpuhp_step *step = steps + st->state;
+		struct cpuhp_step *step = cpuhp_get_step(st->state);
 
 		if (!step->skip_onerr)
-			cpuhp_invoke_callback(cpu, st->state, step->startup);
+			cpuhp_invoke_callback(cpu, st->state, true, NULL);
 	}
 }
 
 static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
-				struct cpuhp_step *steps, enum cpuhp_state target)
+				enum cpuhp_state target)
 {
 	enum cpuhp_state prev_state = st->state;
 	int ret = 0;
 
 	for (; st->state > target; st->state--) {
-		struct cpuhp_step *step = steps + st->state;
-
-		ret = cpuhp_invoke_callback(cpu, st->state, step->teardown);
+		ret = cpuhp_invoke_callback(cpu, st->state, false, NULL);
 		if (ret) {
 			st->target = prev_state;
-			undo_cpu_down(cpu, st, steps);
+			undo_cpu_down(cpu, st);
 			break;
 		}
 	}
 	return ret;
 }
 
-static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st,
-			struct cpuhp_step *steps)
+static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st)
 {
 	for (st->state--; st->state > st->target; st->state--) {
-		struct cpuhp_step *step = steps + st->state;
+		struct cpuhp_step *step = cpuhp_get_step(st->state);
 
 		if (!step->skip_onerr)
-			cpuhp_invoke_callback(cpu, st->state, step->teardown);
+			cpuhp_invoke_callback(cpu, st->state, false, NULL);
 	}
 }
 
 static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st,
-			      struct cpuhp_step *steps, enum cpuhp_state target)
+			      enum cpuhp_state target)
 {
 	enum cpuhp_state prev_state = st->state;
 	int ret = 0;
 
 	while (st->state < target) {
-		struct cpuhp_step *step;
-
 		st->state++;
-		step = steps + st->state;
-		ret = cpuhp_invoke_callback(cpu, st->state, step->startup);
+		ret = cpuhp_invoke_callback(cpu, st->state, true, NULL);
 		if (ret) {
 			st->target = prev_state;
-			undo_cpu_up(cpu, st, steps);
+			undo_cpu_up(cpu, st);
 			break;
 		}
 	}
@@ -447,13 +522,13 @@ static int cpuhp_ap_offline(unsigned int cpu, struct cpuhp_cpu_state *st)
 {
 	enum cpuhp_state target = max((int)st->target, CPUHP_TEARDOWN_CPU);
 
-	return cpuhp_down_callbacks(cpu, st, cpuhp_ap_states, target);
+	return cpuhp_down_callbacks(cpu, st, target);
 }
 
 /* Execute the online startup callbacks. Used to be CPU_ONLINE */
 static int cpuhp_ap_online(unsigned int cpu, struct cpuhp_cpu_state *st)
 {
-	return cpuhp_up_callbacks(cpu, st, cpuhp_ap_states, st->target);
+	return cpuhp_up_callbacks(cpu, st, st->target);
 }
 
 /*
@@ -476,18 +551,20 @@ static void cpuhp_thread_fun(unsigned int cpu)
 	st->should_run = false;
 
 	/* Single callback invocation for [un]install ? */
-	if (st->cb) {
+	if (st->single) {
 		if (st->cb_state < CPUHP_AP_ONLINE) {
 			local_irq_disable();
-			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
+			ret = cpuhp_invoke_callback(cpu, st->cb_state,
+						    st->bringup, st->node);
 			local_irq_enable();
 		} else {
-			ret = cpuhp_invoke_callback(cpu, st->cb_state, st->cb);
+			ret = cpuhp_invoke_callback(cpu, st->cb_state,
+						    st->bringup, st->node);
 		}
 	} else if (st->rollback) {
 		BUG_ON(st->state < CPUHP_AP_ONLINE_IDLE);
 
-		undo_cpu_down(cpu, st, cpuhp_ap_states);
+		undo_cpu_down(cpu, st);
 		/*
 		 * This is a momentary workaround to keep the notifier users
 		 * happy. Will go away once we got rid of the notifiers.
@@ -509,8 +586,9 @@ static void cpuhp_thread_fun(unsigned int cpu)
 }
 
 /* Invoke a single callback on a remote cpu */
-static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state,
-				    int (*cb)(unsigned int))
+static int
+cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup,
+			 struct hlist_node *node)
 {
 	struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
 
@@ -522,10 +600,13 @@ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state,
 	 * we invoke the thread function directly.
 	 */
 	if (!st->thread)
-		return cpuhp_invoke_callback(cpu, state, cb);
+		return cpuhp_invoke_callback(cpu, state, bringup, node);
 
 	st->cb_state = state;
-	st->cb = cb;
+	st->single = true;
+	st->bringup = bringup;
+	st->node = node;
+
 	/*
 	 * Make sure the above stores are visible before should_run becomes
 	 * true. Paired with the mb() above in cpuhp_thread_fun()
@@ -541,7 +622,7 @@ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state,
 static void __cpuhp_kick_ap_work(struct cpuhp_cpu_state *st)
 {
 	st->result = 0;
-	st->cb = NULL;
+	st->single = false;
 	/*
 	 * Make sure the above stores are visible before should_run becomes
 	 * true. Paired with the mb() above in cpuhp_thread_fun()
@@ -674,12 +755,6 @@ static int notify_down_prepare(unsigned int cpu)
 	return err;
 }
 
-static int notify_dying(unsigned int cpu)
-{
-	cpu_notify(CPU_DYING, cpu);
-	return 0;
-}
-
 /* Take this CPU down. */
 static int take_cpu_down(void *_param)
 {
@@ -692,12 +767,16 @@ static int take_cpu_down(void *_param)
 	if (err < 0)
 		return err;
 
+	/*
+	 * We get here while we are in CPUHP_TEARDOWN_CPU state and we must not
+	 * do this step again.
+	 */
+	WARN_ON(st->state != CPUHP_TEARDOWN_CPU);
+	st->state--;
 	/* Invoke the former CPU_DYING callbacks */
-	for (; st->state > target; st->state--) {
-		struct cpuhp_step *step = cpuhp_ap_states + st->state;
+	for (; st->state > target; st->state--)
+		cpuhp_invoke_callback(cpu, st->state, false, NULL);
 
-		cpuhp_invoke_callback(cpu, st->state, step->teardown);
-	}
 	/* Give up timekeeping duties */
 	tick_handover_do_timer();
 	/* Park the stopper thread */
@@ -734,7 +813,7 @@ static int takedown_cpu(unsigned int cpu)
 	BUG_ON(cpu_online(cpu));
 
 	/*
-	 * The migration_call() CPU_DYING callback will have removed all
+	 * The CPUHP_AP_SCHED_MIGRATE_DYING callback will have removed all
 	 * runnable tasks from the cpu, there's only the idle task left now
 	 * that the migration thread is done doing the stop_machine thing.
 	 *
@@ -787,7 +866,6 @@ void cpuhp_report_idle_dead(void)
 #define notify_down_prepare	NULL
 #define takedown_cpu		NULL
 #define notify_dead		NULL
-#define notify_dying		NULL
 #endif
 
 #ifdef CONFIG_HOTPLUG_CPU
@@ -836,7 +914,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen,
 	 * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need
 	 * to do the further cleanups.
 	 */
-	ret = cpuhp_down_callbacks(cpu, st, cpuhp_bp_states, target);
+	ret = cpuhp_down_callbacks(cpu, st, target);
 	if (ret && st->state > CPUHP_TEARDOWN_CPU && st->state < prev_state) {
 		st->target = prev_state;
 		st->rollback = true;
@@ -877,10 +955,9 @@ EXPORT_SYMBOL(cpu_down);
 #endif /*CONFIG_HOTPLUG_CPU*/
 
 /**
- * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
+ * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU
  * @cpu: cpu that just started
  *
- * This function calls the cpu_chain notifiers with CPU_STARTING.
  * It must be called by the arch code on the new cpu, before the new cpu
  * enables interrupts and before the "boot" cpu returns from __cpu_up().
  */
@@ -891,11 +968,8 @@ void notify_cpu_starting(unsigned int cpu)
 
 	rcu_cpu_starting(cpu);	/* Enables RCU usage on this CPU. */
 	while (st->state < target) {
-		struct cpuhp_step *step;
-
 		st->state++;
-		step = cpuhp_ap_states + st->state;
-		cpuhp_invoke_callback(cpu, st->state, step->startup);
+		cpuhp_invoke_callback(cpu, st->state, true, NULL);
 	}
 }
 
@@ -980,7 +1054,7 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target)
 	 * responsible for bringing it up to the target state.
 	 */
 	target = min((int)target, CPUHP_BRINGUP_CPU);
-	ret = cpuhp_up_callbacks(cpu, st, cpuhp_bp_states, target);
+	ret = cpuhp_up_callbacks(cpu, st, target);
 out:
 	cpu_hotplug_done();
 	return ret;
@@ -1083,7 +1157,7 @@ void enable_nonboot_cpus(void)
 
 	/* Allow everyone to use the CPU hotplug again */
 	cpu_maps_update_begin();
-	WARN_ON(--cpu_hotplug_disabled < 0);
+	__cpu_hotplug_enable();
 	if (cpumask_empty(frozen_cpus))
 		goto out;
 
@@ -1172,40 +1246,50 @@ core_initcall(cpu_hotplug_pm_sync_init);
 static struct cpuhp_step cpuhp_bp_states[] = {
 	[CPUHP_OFFLINE] = {
 		.name			= "offline",
-		.startup		= NULL,
-		.teardown		= NULL,
+		.startup.single		= NULL,
+		.teardown.single	= NULL,
 	},
 #ifdef CONFIG_SMP
 	[CPUHP_CREATE_THREADS]= {
-		.name			= "threads:create",
-		.startup		= smpboot_create_threads,
-		.teardown		= NULL,
+		.name			= "threads:prepare",
+		.startup.single		= smpboot_create_threads,
+		.teardown.single	= NULL,
 		.cant_stop		= true,
 	},
 	[CPUHP_PERF_PREPARE] = {
-		.name = "perf prepare",
-		.startup = perf_event_init_cpu,
-		.teardown = perf_event_exit_cpu,
+		.name			= "perf:prepare",
+		.startup.single		= perf_event_init_cpu,
+		.teardown.single	= perf_event_exit_cpu,
 	},
 	[CPUHP_WORKQUEUE_PREP] = {
-		.name = "workqueue prepare",
-		.startup = workqueue_prepare_cpu,
-		.teardown = NULL,
+		.name			= "workqueue:prepare",
+		.startup.single		= workqueue_prepare_cpu,
+		.teardown.single	= NULL,
 	},
 	[CPUHP_HRTIMERS_PREPARE] = {
-		.name = "hrtimers prepare",
-		.startup = hrtimers_prepare_cpu,
-		.teardown = hrtimers_dead_cpu,
+		.name			= "hrtimers:prepare",
+		.startup.single		= hrtimers_prepare_cpu,
+		.teardown.single	= hrtimers_dead_cpu,
 	},
 	[CPUHP_SMPCFD_PREPARE] = {
-		.name = "SMPCFD prepare",
-		.startup = smpcfd_prepare_cpu,
-		.teardown = smpcfd_dead_cpu,
+		.name			= "smpcfd:prepare",
+		.startup.single		= smpcfd_prepare_cpu,
+		.teardown.single	= smpcfd_dead_cpu,
+	},
+	[CPUHP_RELAY_PREPARE] = {
+		.name			= "relay:prepare",
+		.startup.single		= relay_prepare_cpu,
+		.teardown.single	= NULL,
+	},
+	[CPUHP_SLAB_PREPARE] = {
+		.name			= "slab:prepare",
+		.startup.single		= slab_prepare_cpu,
+		.teardown.single	= slab_dead_cpu,
 	},
 	[CPUHP_RCUTREE_PREP] = {
-		.name = "RCU-tree prepare",
-		.startup = rcutree_prepare_cpu,
-		.teardown = rcutree_dead_cpu,
+		.name			= "RCU/tree:prepare",
+		.startup.single		= rcutree_prepare_cpu,
+		.teardown.single	= rcutree_dead_cpu,
 	},
 	/*
 	 * Preparatory and dead notifiers. Will be replaced once the notifiers
@@ -1213,8 +1297,8 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 	 */
 	[CPUHP_NOTIFY_PREPARE] = {
 		.name			= "notify:prepare",
-		.startup		= notify_prepare,
-		.teardown		= notify_dead,
+		.startup.single		= notify_prepare,
+		.teardown.single	= notify_dead,
 		.skip_onerr		= true,
 		.cant_stop		= true,
 	},
@@ -1224,20 +1308,21 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 	 * otherwise a RCU stall occurs.
 	 */
 	[CPUHP_TIMERS_DEAD] = {
-		.name = "timers dead",
-		.startup = NULL,
-		.teardown = timers_dead_cpu,
+		.name			= "timers:dead",
+		.startup.single		= NULL,
+		.teardown.single	= timers_dead_cpu,
 	},
 	/* Kicks the plugged cpu into life */
 	[CPUHP_BRINGUP_CPU] = {
 		.name			= "cpu:bringup",
-		.startup		= bringup_cpu,
-		.teardown		= NULL,
+		.startup.single		= bringup_cpu,
+		.teardown.single	= NULL,
 		.cant_stop		= true,
 	},
 	[CPUHP_AP_SMPCFD_DYING] = {
-		.startup = NULL,
-		.teardown = smpcfd_dying_cpu,
+		.name			= "smpcfd:dying",
+		.startup.single		= NULL,
+		.teardown.single	= smpcfd_dying_cpu,
 	},
 	/*
 	 * Handled on controll processor until the plugged processor manages
@@ -1245,8 +1330,8 @@ static struct cpuhp_step cpuhp_bp_states[] = {
 	 */
 	[CPUHP_TEARDOWN_CPU] = {
 		.name			= "cpu:teardown",
-		.startup		= NULL,
-		.teardown		= takedown_cpu,
+		.startup.single		= NULL,
+		.teardown.single	= takedown_cpu,
 		.cant_stop		= true,
 	},
 #else
@@ -1272,24 +1357,13 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 	/* First state is scheduler control. Interrupts are disabled */
 	[CPUHP_AP_SCHED_STARTING] = {
 		.name			= "sched:starting",
-		.startup		= sched_cpu_starting,
-		.teardown		= sched_cpu_dying,
+		.startup.single		= sched_cpu_starting,
+		.teardown.single	= sched_cpu_dying,
 	},
 	[CPUHP_AP_RCUTREE_DYING] = {
-		.startup = NULL,
-		.teardown = rcutree_dying_cpu,
-	},
-	/*
-	 * Low level startup/teardown notifiers. Run with interrupts
-	 * disabled. Will be removed once the notifiers are converted to
-	 * states.
-	 */
-	[CPUHP_AP_NOTIFY_STARTING] = {
-		.name			= "notify:starting",
-		.startup		= notify_starting,
-		.teardown		= notify_dying,
-		.skip_onerr		= true,
-		.cant_stop		= true,
+		.name			= "RCU/tree:dying",
+		.startup.single		= NULL,
+		.teardown.single	= rcutree_dying_cpu,
 	},
 	/* Entry state on starting. Interrupts enabled from here on. Transient
 	 * state for synchronsization */
@@ -1298,24 +1372,24 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 	},
 	/* Handle smpboot threads park/unpark */
 	[CPUHP_AP_SMPBOOT_THREADS] = {
-		.name			= "smpboot:threads",
-		.startup		= smpboot_unpark_threads,
-		.teardown		= NULL,
+		.name			= "smpboot/threads:online",
+		.startup.single		= smpboot_unpark_threads,
+		.teardown.single	= NULL,
 	},
 	[CPUHP_AP_PERF_ONLINE] = {
-		.name = "perf online",
-		.startup = perf_event_init_cpu,
-		.teardown = perf_event_exit_cpu,
+		.name			= "perf:online",
+		.startup.single		= perf_event_init_cpu,
+		.teardown.single	= perf_event_exit_cpu,
 	},
 	[CPUHP_AP_WORKQUEUE_ONLINE] = {
-		.name = "workqueue online",
-		.startup = workqueue_online_cpu,
-		.teardown = workqueue_offline_cpu,
+		.name			= "workqueue:online",
+		.startup.single		= workqueue_online_cpu,
+		.teardown.single	= workqueue_offline_cpu,
 	},
 	[CPUHP_AP_RCUTREE_ONLINE] = {
-		.name = "RCU-tree online",
-		.startup = rcutree_online_cpu,
-		.teardown = rcutree_offline_cpu,
+		.name			= "RCU/tree:online",
+		.startup.single		= rcutree_online_cpu,
+		.teardown.single	= rcutree_offline_cpu,
 	},
 
 	/*
@@ -1324,8 +1398,8 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 	 */
 	[CPUHP_AP_NOTIFY_ONLINE] = {
 		.name			= "notify:online",
-		.startup		= notify_online,
-		.teardown		= notify_down_prepare,
+		.startup.single		= notify_online,
+		.teardown.single	= notify_down_prepare,
 		.skip_onerr		= true,
 	},
 #endif
@@ -1337,16 +1411,16 @@ static struct cpuhp_step cpuhp_ap_states[] = {
 	/* Last state is scheduler control setting the cpu active */
 	[CPUHP_AP_ACTIVE] = {
 		.name			= "sched:active",
-		.startup		= sched_cpu_activate,
-		.teardown		= sched_cpu_deactivate,
+		.startup.single		= sched_cpu_activate,
+		.teardown.single	= sched_cpu_deactivate,
 	},
 #endif
 
 	/* CPU is fully up and running. */
 	[CPUHP_ONLINE] = {
 		.name			= "online",
-		.startup		= NULL,
-		.teardown		= NULL,
+		.startup.single		= NULL,
+		.teardown.single	= NULL,
 	},
 };
 
@@ -1358,54 +1432,42 @@ static int cpuhp_cb_check(enum cpuhp_state state)
 	return 0;
 }
 
-static bool cpuhp_is_ap_state(enum cpuhp_state state)
-{
-	/*
-	 * The extra check for CPUHP_TEARDOWN_CPU is only for documentation
-	 * purposes as that state is handled explicitely in cpu_down.
-	 */
-	return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU;
-}
-
-static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state)
-{
-	struct cpuhp_step *sp;
-
-	sp = cpuhp_is_ap_state(state) ? cpuhp_ap_states : cpuhp_bp_states;
-	return sp + state;
-}
-
 static void cpuhp_store_callbacks(enum cpuhp_state state,
 				  const char *name,
 				  int (*startup)(unsigned int cpu),
-				  int (*teardown)(unsigned int cpu))
+				  int (*teardown)(unsigned int cpu),
+				  bool multi_instance)
 {
 	/* (Un)Install the callbacks for further cpu hotplug operations */
 	struct cpuhp_step *sp;
 
 	mutex_lock(&cpuhp_state_mutex);
 	sp = cpuhp_get_step(state);
-	sp->startup = startup;
-	sp->teardown = teardown;
+	sp->startup.single = startup;
+	sp->teardown.single = teardown;
 	sp->name = name;
+	sp->multi_instance = multi_instance;
+	INIT_HLIST_HEAD(&sp->list);
 	mutex_unlock(&cpuhp_state_mutex);
 }
 
 static void *cpuhp_get_teardown_cb(enum cpuhp_state state)
 {
-	return cpuhp_get_step(state)->teardown;
+	return cpuhp_get_step(state)->teardown.single;
 }
 
 /*
  * Call the startup/teardown function for a step either on the AP or
  * on the current CPU.
  */
-static int cpuhp_issue_call(int cpu, enum cpuhp_state state,
-			    int (*cb)(unsigned int), bool bringup)
+static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup,
+			    struct hlist_node *node)
 {
+	struct cpuhp_step *sp = cpuhp_get_step(state);
 	int ret;
 
-	if (!cb)
+	if ((bringup && !sp->startup.single) ||
+	    (!bringup && !sp->teardown.single))
 		return 0;
 	/*
 	 * The non AP bound callbacks can fail on bringup. On teardown
@@ -1413,11 +1475,11 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state,
 	 */
 #ifdef CONFIG_SMP
 	if (cpuhp_is_ap_state(state))
-		ret = cpuhp_invoke_ap_callback(cpu, state, cb);
+		ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node);
 	else
-		ret = cpuhp_invoke_callback(cpu, state, cb);
+		ret = cpuhp_invoke_callback(cpu, state, bringup, node);
 #else
-	ret = cpuhp_invoke_callback(cpu, state, cb);
+	ret = cpuhp_invoke_callback(cpu, state, bringup, node);
 #endif
 	BUG_ON(ret && !bringup);
 	return ret;
@@ -1429,13 +1491,10 @@ static int cpuhp_issue_call(int cpu, enum cpuhp_state state,
  * Note: The teardown callbacks for rollback are not allowed to fail!
  */
 static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
-				   int (*teardown)(unsigned int cpu))
+				   struct hlist_node *node)
 {
 	int cpu;
 
-	if (!teardown)
-		return;
-
 	/* Roll back the already executed steps on the other cpus */
 	for_each_present_cpu(cpu) {
 		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
@@ -1446,7 +1505,7 @@ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state,
 
 		/* Did we invoke the startup call on that cpu ? */
 		if (cpustate >= state)
-			cpuhp_issue_call(cpu, state, teardown, false);
+			cpuhp_issue_call(cpu, state, false, node);
 	}
 }
 
@@ -1473,6 +1532,52 @@ static int cpuhp_reserve_state(enum cpuhp_state state)
 	return -ENOSPC;
 }
 
+int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node,
+			       bool invoke)
+{
+	struct cpuhp_step *sp;
+	int cpu;
+	int ret;
+
+	sp = cpuhp_get_step(state);
+	if (sp->multi_instance == false)
+		return -EINVAL;
+
+	get_online_cpus();
+
+	if (!invoke || !sp->startup.multi)
+		goto add_node;
+
+	/*
+	 * Try to call the startup callback for each present cpu
+	 * depending on the hotplug state of the cpu.
+	 */
+	for_each_present_cpu(cpu) {
+		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+		int cpustate = st->state;
+
+		if (cpustate < state)
+			continue;
+
+		ret = cpuhp_issue_call(cpu, state, true, node);
+		if (ret) {
+			if (sp->teardown.multi)
+				cpuhp_rollback_install(cpu, state, node);
+			goto err;
+		}
+	}
+add_node:
+	ret = 0;
+	mutex_lock(&cpuhp_state_mutex);
+	hlist_add_head(node, &sp->list);
+	mutex_unlock(&cpuhp_state_mutex);
+
+err:
+	put_online_cpus();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance);
+
 /**
  * __cpuhp_setup_state - Setup the callbacks for an hotplug machine state
  * @state:	The state to setup
@@ -1486,7 +1591,8 @@ static int cpuhp_reserve_state(enum cpuhp_state state)
 int __cpuhp_setup_state(enum cpuhp_state state,
 			const char *name, bool invoke,
 			int (*startup)(unsigned int cpu),
-			int (*teardown)(unsigned int cpu))
+			int (*teardown)(unsigned int cpu),
+			bool multi_instance)
 {
 	int cpu, ret = 0;
 	int dyn_state = 0;
@@ -1505,7 +1611,7 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 		state = ret;
 	}
 
-	cpuhp_store_callbacks(state, name, startup, teardown);
+	cpuhp_store_callbacks(state, name, startup, teardown, multi_instance);
 
 	if (!invoke || !startup)
 		goto out;
@@ -1521,10 +1627,11 @@ int __cpuhp_setup_state(enum cpuhp_state state,
 		if (cpustate < state)
 			continue;
 
-		ret = cpuhp_issue_call(cpu, state, startup, true);
+		ret = cpuhp_issue_call(cpu, state, true, NULL);
 		if (ret) {
-			cpuhp_rollback_install(cpu, state, teardown);
-			cpuhp_store_callbacks(state, NULL, NULL, NULL);
+			if (teardown)
+				cpuhp_rollback_install(cpu, state, NULL);
+			cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
 			goto out;
 		}
 	}
@@ -1536,6 +1643,42 @@ out:
 }
 EXPORT_SYMBOL(__cpuhp_setup_state);
 
+int __cpuhp_state_remove_instance(enum cpuhp_state state,
+				  struct hlist_node *node, bool invoke)
+{
+	struct cpuhp_step *sp = cpuhp_get_step(state);
+	int cpu;
+
+	BUG_ON(cpuhp_cb_check(state));
+
+	if (!sp->multi_instance)
+		return -EINVAL;
+
+	get_online_cpus();
+	if (!invoke || !cpuhp_get_teardown_cb(state))
+		goto remove;
+	/*
+	 * Call the teardown callback for each present cpu depending
+	 * on the hotplug state of the cpu. This function is not
+	 * allowed to fail currently!
+	 */
+	for_each_present_cpu(cpu) {
+		struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu);
+		int cpustate = st->state;
+
+		if (cpustate >= state)
+			cpuhp_issue_call(cpu, state, false, node);
+	}
+
+remove:
+	mutex_lock(&cpuhp_state_mutex);
+	hlist_del(node);
+	mutex_unlock(&cpuhp_state_mutex);
+	put_online_cpus();
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance);
 /**
  * __cpuhp_remove_state - Remove the callbacks for an hotplug machine state
  * @state:	The state to remove
@@ -1547,14 +1690,21 @@ EXPORT_SYMBOL(__cpuhp_setup_state);
  */
 void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 {
-	int (*teardown)(unsigned int cpu) = cpuhp_get_teardown_cb(state);
+	struct cpuhp_step *sp = cpuhp_get_step(state);
 	int cpu;
 
 	BUG_ON(cpuhp_cb_check(state));
 
 	get_online_cpus();
 
-	if (!invoke || !teardown)
+	if (sp->multi_instance) {
+		WARN(!hlist_empty(&sp->list),
+		     "Error: Removing state %d which has instances left.\n",
+		     state);
+		goto remove;
+	}
+
+	if (!invoke || !cpuhp_get_teardown_cb(state))
 		goto remove;
 
 	/*
@@ -1567,10 +1717,10 @@ void __cpuhp_remove_state(enum cpuhp_state state, bool invoke)
 		int cpustate = st->state;
 
 		if (cpustate >= state)
-			cpuhp_issue_call(cpu, state, teardown, false);
+			cpuhp_issue_call(cpu, state, false, NULL);
 	}
 remove:
-	cpuhp_store_callbacks(state, NULL, NULL, NULL);
+	cpuhp_store_callbacks(state, NULL, NULL, NULL, false);
 	put_online_cpus();
 }
 EXPORT_SYMBOL(__cpuhp_remove_state);

kernel/padata.c

@@ -30,6 +30,7 @@
 #include <linux/slab.h>
 #include <linux/sysfs.h>
 #include <linux/rcupdate.h>
+#include <linux/module.h>
 
 #define MAX_OBJ_NUM 1000
 
@@ -769,52 +770,43 @@ static inline int pinst_has_cpu(struct padata_instance *pinst, int cpu)
 		cpumask_test_cpu(cpu, pinst->cpumask.cbcpu);
 }
 
-
-static int padata_cpu_callback(struct notifier_block *nfb,
-			       unsigned long action, void *hcpu)
+static int padata_cpu_online(unsigned int cpu, struct hlist_node *node)
 {
-	int err;
 	struct padata_instance *pinst;
-	int cpu = (unsigned long)hcpu;
+	int ret;
 
-	pinst = container_of(nfb, struct padata_instance, cpu_notifier);
+	pinst = hlist_entry_safe(node, struct padata_instance, node);
+	if (!pinst_has_cpu(pinst, cpu))
+		return 0;
 
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		if (!pinst_has_cpu(pinst, cpu))
-			break;
-		mutex_lock(&pinst->lock);
-		err = __padata_add_cpu(pinst, cpu);
-		mutex_unlock(&pinst->lock);
-		if (err)
-			return notifier_from_errno(err);
-		break;
+	mutex_lock(&pinst->lock);
+	ret = __padata_add_cpu(pinst, cpu);
+	mutex_unlock(&pinst->lock);
+	return ret;
+}
 
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		if (!pinst_has_cpu(pinst, cpu))
-			break;
-		mutex_lock(&pinst->lock);
-		err = __padata_remove_cpu(pinst, cpu);
-		mutex_unlock(&pinst->lock);
-		if (err)
-			return notifier_from_errno(err);
-		break;
-	}
+static int padata_cpu_prep_down(unsigned int cpu, struct hlist_node *node)
+{
+	struct padata_instance *pinst;
+	int ret;
+
+	pinst = hlist_entry_safe(node, struct padata_instance, node);
+	if (!pinst_has_cpu(pinst, cpu))
+		return 0;
 
-	return NOTIFY_OK;
+	mutex_lock(&pinst->lock);
+	ret = __padata_remove_cpu(pinst, cpu);
+	mutex_unlock(&pinst->lock);
+	return ret;
 }
+
+static enum cpuhp_state hp_online;
 #endif
 
 static void __padata_free(struct padata_instance *pinst)
 {
 #ifdef CONFIG_HOTPLUG_CPU
-	unregister_hotcpu_notifier(&pinst->cpu_notifier);
+	cpuhp_state_remove_instance_nocalls(hp_online, &pinst->node);
 #endif
 
 	padata_stop(pinst);
@@ -1012,11 +1004,8 @@ struct padata_instance *padata_alloc(struct workqueue_struct *wq,
 	mutex_init(&pinst->lock);
 
 #ifdef CONFIG_HOTPLUG_CPU
-	pinst->cpu_notifier.notifier_call = padata_cpu_callback;
-	pinst->cpu_notifier.priority = 0;
-	register_hotcpu_notifier(&pinst->cpu_notifier);
+	cpuhp_state_add_instance_nocalls(hp_online, &pinst->node);
 #endif
-
 	return pinst;
 
 err_free_masks:
@@ -1039,3 +1028,26 @@ void padata_free(struct padata_instance *pinst)
 	kobject_put(&pinst->kobj);
 }
 EXPORT_SYMBOL(padata_free);
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static __init int padata_driver_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, "padata:online",
+				      padata_cpu_online,
+				      padata_cpu_prep_down);
+	if (ret < 0)
+		return ret;
+	hp_online = ret;
+	return 0;
+}
+module_init(padata_driver_init);
+
+static __exit void padata_driver_exit(void)
+{
+	cpuhp_remove_multi_state(hp_online);
+}
+module_exit(padata_driver_exit);
+#endif

kernel/relay.c

@@ -214,7 +214,7 @@ static void relay_destroy_buf(struct rchan_buf *buf)
 			__free_page(buf->page_array[i]);
 		relay_free_page_array(buf->page_array);
 	}
-	chan->buf[buf->cpu] = NULL;
+	*per_cpu_ptr(chan->buf, buf->cpu) = NULL;
 	kfree(buf->padding);
 	kfree(buf);
 	kref_put(&chan->kref, relay_destroy_channel);
@@ -382,20 +382,21 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init)
  */
 void relay_reset(struct rchan *chan)
 {
+	struct rchan_buf *buf;
 	unsigned int i;
 
 	if (!chan)
 		return;
 
-	if (chan->is_global && chan->buf[0]) {
-		__relay_reset(chan->buf[0], 0);
+	if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) {
+		__relay_reset(buf, 0);
 		return;
 	}
 
 	mutex_lock(&relay_channels_mutex);
 	for_each_possible_cpu(i)
-		if (chan->buf[i])
-			__relay_reset(chan->buf[i], 0);
+		if ((buf = *per_cpu_ptr(chan->buf, i)))
+			__relay_reset(buf, 0);
 	mutex_unlock(&relay_channels_mutex);
 }
 EXPORT_SYMBOL_GPL(relay_reset);
@@ -440,7 +441,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
 	struct dentry *dentry;
 
  	if (chan->is_global)
-		return chan->buf[0];
+		return *per_cpu_ptr(chan->buf, 0);
 
 	buf = relay_create_buf(chan);
 	if (!buf)
@@ -464,7 +465,7 @@ static struct rchan_buf *relay_open_buf(struct rchan *chan, unsigned int cpu)
  	__relay_reset(buf, 1);
 
  	if(chan->is_global) {
- 		chan->buf[0] = buf;
+		*per_cpu_ptr(chan->buf, 0) = buf;
  		buf->cpu = 0;
   	}
 
@@ -512,46 +513,25 @@ static void setup_callbacks(struct rchan *chan,
 	chan->cb = cb;
 }
 
-/**
- * 	relay_hotcpu_callback - CPU hotplug callback
- * 	@nb: notifier block
- * 	@action: hotplug action to take
- * 	@hcpu: CPU number
- *
- * 	Returns the success/failure of the operation. (%NOTIFY_OK, %NOTIFY_BAD)
- */
-static int relay_hotcpu_callback(struct notifier_block *nb,
-				unsigned long action,
-				void *hcpu)
+int relay_prepare_cpu(unsigned int cpu)
 {
-	unsigned int hotcpu = (unsigned long)hcpu;
 	struct rchan *chan;
+	struct rchan_buf *buf;
 
-	switch(action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		mutex_lock(&relay_channels_mutex);
-		list_for_each_entry(chan, &relay_channels, list) {
-			if (chan->buf[hotcpu])
-				continue;
-			chan->buf[hotcpu] = relay_open_buf(chan, hotcpu);
-			if(!chan->buf[hotcpu]) {
-				printk(KERN_ERR
-					"relay_hotcpu_callback: cpu %d buffer "
-					"creation failed\n", hotcpu);
-				mutex_unlock(&relay_channels_mutex);
-				return notifier_from_errno(-ENOMEM);
-			}
+	mutex_lock(&relay_channels_mutex);
+	list_for_each_entry(chan, &relay_channels, list) {
+		if ((buf = *per_cpu_ptr(chan->buf, cpu)))
+			continue;
+		buf = relay_open_buf(chan, cpu);
+		if (!buf) {
+			pr_err("relay: cpu %d buffer creation failed\n", cpu);
+			mutex_unlock(&relay_channels_mutex);
+			return -ENOMEM;
 		}
-		mutex_unlock(&relay_channels_mutex);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		/* No need to flush the cpu : will be flushed upon
-		 * final relay_flush() call. */
-		break;
+		*per_cpu_ptr(chan->buf, cpu) = buf;
 	}
-	return NOTIFY_OK;
+	mutex_unlock(&relay_channels_mutex);
+	return 0;
 }
 
 /**
@@ -583,6 +563,7 @@ struct rchan *relay_open(const char *base_filename,
 {
 	unsigned int i;
 	struct rchan *chan;
+	struct rchan_buf *buf;
 
 	if (!(subbuf_size && n_subbufs))
 		return NULL;
@@ -593,6 +574,7 @@ struct rchan *relay_open(const char *base_filename,
 	if (!chan)
 		return NULL;
 
+	chan->buf = alloc_percpu(struct rchan_buf *);
 	chan->version = RELAYFS_CHANNEL_VERSION;
 	chan->n_subbufs = n_subbufs;
 	chan->subbuf_size = subbuf_size;
@@ -608,9 +590,10 @@ struct rchan *relay_open(const char *base_filename,
 
 	mutex_lock(&relay_channels_mutex);
 	for_each_online_cpu(i) {
-		chan->buf[i] = relay_open_buf(chan, i);
-		if (!chan->buf[i])
+		buf = relay_open_buf(chan, i);
+		if (!buf)
 			goto free_bufs;
+		*per_cpu_ptr(chan->buf, i) = buf;
 	}
 	list_add(&chan->list, &relay_channels);
 	mutex_unlock(&relay_channels_mutex);
@@ -619,8 +602,8 @@ struct rchan *relay_open(const char *base_filename,
 
 free_bufs:
 	for_each_possible_cpu(i) {
-		if (chan->buf[i])
-			relay_close_buf(chan->buf[i]);
+		if ((buf = *per_cpu_ptr(chan->buf, i)))
+			relay_close_buf(buf);
 	}
 
 	kref_put(&chan->kref, relay_destroy_channel);
@@ -666,6 +649,7 @@ int relay_late_setup_files(struct rchan *chan,
 	unsigned int i, curr_cpu;
 	unsigned long flags;
 	struct dentry *dentry;
+	struct rchan_buf *buf;
 	struct rchan_percpu_buf_dispatcher disp;
 
 	if (!chan || !base_filename)
@@ -684,10 +668,11 @@ int relay_late_setup_files(struct rchan *chan,
 
 	if (chan->is_global) {
 		err = -EINVAL;
-		if (!WARN_ON_ONCE(!chan->buf[0])) {
-			dentry = relay_create_buf_file(chan, chan->buf[0], 0);
+		buf = *per_cpu_ptr(chan->buf, 0);
+		if (!WARN_ON_ONCE(!buf)) {
+			dentry = relay_create_buf_file(chan, buf, 0);
 			if (dentry && !WARN_ON_ONCE(!chan->is_global)) {
-				relay_set_buf_dentry(chan->buf[0], dentry);
+				relay_set_buf_dentry(buf, dentry);
 				err = 0;
 			}
 		}
@@ -702,13 +687,14 @@ int relay_late_setup_files(struct rchan *chan,
 	 * on all currently online CPUs.
 	 */
 	for_each_online_cpu(i) {
-		if (unlikely(!chan->buf[i])) {
+		buf = *per_cpu_ptr(chan->buf, i);
+		if (unlikely(!buf)) {
 			WARN_ONCE(1, KERN_ERR "CPU has no buffer!\n");
 			err = -EINVAL;
 			break;
 		}
 
-		dentry = relay_create_buf_file(chan, chan->buf[i], i);
+		dentry = relay_create_buf_file(chan, buf, i);
 		if (unlikely(!dentry)) {
 			err = -EINVAL;
 			break;
@@ -716,10 +702,10 @@ int relay_late_setup_files(struct rchan *chan,
 
 		if (curr_cpu == i) {
 			local_irq_save(flags);
-			relay_set_buf_dentry(chan->buf[i], dentry);
+			relay_set_buf_dentry(buf, dentry);
 			local_irq_restore(flags);
 		} else {
-			disp.buf = chan->buf[i];
+			disp.buf = buf;
 			disp.dentry = dentry;
 			smp_mb();
 			/* relay_channels_mutex must be held, so wait. */
@@ -822,11 +808,10 @@ void relay_subbufs_consumed(struct rchan *chan,
 	if (!chan)
 		return;
 
-	if (cpu >= NR_CPUS || !chan->buf[cpu] ||
-					subbufs_consumed > chan->n_subbufs)
+	buf = *per_cpu_ptr(chan->buf, cpu);
+	if (cpu >= NR_CPUS || !buf || subbufs_consumed > chan->n_subbufs)
 		return;
 
-	buf = chan->buf[cpu];
 	if (subbufs_consumed > buf->subbufs_produced - buf->subbufs_consumed)
 		buf->subbufs_consumed = buf->subbufs_produced;
 	else
@@ -842,18 +827,19 @@ EXPORT_SYMBOL_GPL(relay_subbufs_consumed);
  */
 void relay_close(struct rchan *chan)
 {
+	struct rchan_buf *buf;
 	unsigned int i;
 
 	if (!chan)
 		return;
 
 	mutex_lock(&relay_channels_mutex);
-	if (chan->is_global && chan->buf[0])
-		relay_close_buf(chan->buf[0]);
+	if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0)))
+		relay_close_buf(buf);
 	else
 		for_each_possible_cpu(i)
-			if (chan->buf[i])
-				relay_close_buf(chan->buf[i]);
+			if ((buf = *per_cpu_ptr(chan->buf, i)))
+				relay_close_buf(buf);
 
 	if (chan->last_toobig)
 		printk(KERN_WARNING "relay: one or more items not logged "
@@ -874,20 +860,21 @@ EXPORT_SYMBOL_GPL(relay_close);
  */
 void relay_flush(struct rchan *chan)
 {
+	struct rchan_buf *buf;
 	unsigned int i;
 
 	if (!chan)
 		return;
 
-	if (chan->is_global && chan->buf[0]) {
-		relay_switch_subbuf(chan->buf[0], 0);
+	if (chan->is_global && (buf = *per_cpu_ptr(chan->buf, 0))) {
+		relay_switch_subbuf(buf, 0);
 		return;
 	}
 
 	mutex_lock(&relay_channels_mutex);
 	for_each_possible_cpu(i)
-		if (chan->buf[i])
-			relay_switch_subbuf(chan->buf[i], 0);
+		if ((buf = *per_cpu_ptr(chan->buf, i)))
+			relay_switch_subbuf(buf, 0);
 	mutex_unlock(&relay_channels_mutex);
 }
 EXPORT_SYMBOL_GPL(relay_flush);
@@ -1377,12 +1364,3 @@ const struct file_operations relay_file_operations = {
 	.splice_read	= relay_file_splice_read,
 };
 EXPORT_SYMBOL_GPL(relay_file_operations);
-
-static __init int relay_init(void)
-{
-
-	hotcpu_notifier(relay_hotcpu_callback, 0);
-	return 0;
-}
-
-early_initcall(relay_init);

kernel/softirq.c

@@ -714,7 +714,7 @@ void tasklet_kill_immediate(struct tasklet_struct *t, unsigned int cpu)
 	BUG();
 }
 
-static void takeover_tasklets(unsigned int cpu)
+static int takeover_tasklets(unsigned int cpu)
 {
 	/* CPU is dead, so no lock needed. */
 	local_irq_disable();
@@ -737,27 +737,12 @@ static void takeover_tasklets(unsigned int cpu)
 	raise_softirq_irqoff(HI_SOFTIRQ);
 
 	local_irq_enable();
+	return 0;
 }
+#else
+#define takeover_tasklets	NULL
 #endif /* CONFIG_HOTPLUG_CPU */
 
-static int cpu_callback(struct notifier_block *nfb, unsigned long action,
-			void *hcpu)
-{
-	switch (action) {
-#ifdef CONFIG_HOTPLUG_CPU
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		takeover_tasklets((unsigned long)hcpu);
-		break;
-#endif /* CONFIG_HOTPLUG_CPU */
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block cpu_nfb = {
-	.notifier_call = cpu_callback
-};
-
 static struct smp_hotplug_thread softirq_threads = {
 	.store			= &ksoftirqd,
 	.thread_should_run	= ksoftirqd_should_run,
@@ -767,8 +752,8 @@ static struct smp_hotplug_thread softirq_threads = {
 
 static __init int spawn_ksoftirqd(void)
 {
-	register_cpu_notifier(&cpu_nfb);
-
+	cpuhp_setup_state_nocalls(CPUHP_SOFTIRQ_DEAD, "softirq:dead", NULL,
+				  takeover_tasklets);
 	BUG_ON(smpboot_register_percpu_thread(&softirq_threads));
 
 	return 0;

lib/cpu-notifier-error-inject.c

@@ -8,16 +8,47 @@ static int priority;
 module_param(priority, int, 0);
 MODULE_PARM_DESC(priority, "specify cpu notifier priority");
 
+#define UP_PREPARE 0
+#define UP_PREPARE_FROZEN 0
+#define DOWN_PREPARE 0
+#define DOWN_PREPARE_FROZEN 0
+
 static struct notifier_err_inject cpu_notifier_err_inject = {
 	.actions = {
-		{ NOTIFIER_ERR_INJECT_ACTION(CPU_UP_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(CPU_UP_PREPARE_FROZEN) },
-		{ NOTIFIER_ERR_INJECT_ACTION(CPU_DOWN_PREPARE) },
-		{ NOTIFIER_ERR_INJECT_ACTION(CPU_DOWN_PREPARE_FROZEN) },
+		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE) },
+		{ NOTIFIER_ERR_INJECT_ACTION(UP_PREPARE_FROZEN) },
+		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE) },
+		{ NOTIFIER_ERR_INJECT_ACTION(DOWN_PREPARE_FROZEN) },
 		{}
 	}
 };
 
+static int notf_err_handle(struct notifier_err_inject_action *action)
+{
+	int ret;
+
+	ret = action->error;
+	if (ret)
+		pr_info("Injecting error (%d) to %s\n", ret, action->name);
+	return ret;
+}
+
+static int notf_err_inj_up_prepare(unsigned int cpu)
+{
+	if (!cpuhp_tasks_frozen)
+		return notf_err_handle(&cpu_notifier_err_inject.actions[0]);
+	else
+		return notf_err_handle(&cpu_notifier_err_inject.actions[1]);
+}
+
+static int notf_err_inj_dead(unsigned int cpu)
+{
+	if (!cpuhp_tasks_frozen)
+		return notf_err_handle(&cpu_notifier_err_inject.actions[2]);
+	else
+		return notf_err_handle(&cpu_notifier_err_inject.actions[3]);
+}
+
 static struct dentry *dir;
 
 static int err_inject_init(void)
@@ -29,7 +60,10 @@ static int err_inject_init(void)
 	if (IS_ERR(dir))
 		return PTR_ERR(dir);
 
-	err = register_hotcpu_notifier(&cpu_notifier_err_inject.nb);
+	err = cpuhp_setup_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE,
+					"cpu-err-notif:prepare",
+					notf_err_inj_up_prepare,
+					notf_err_inj_dead);
 	if (err)
 		debugfs_remove_recursive(dir);
 
@@ -38,7 +72,7 @@ static int err_inject_init(void)
 
 static void err_inject_exit(void)
 {
-	unregister_hotcpu_notifier(&cpu_notifier_err_inject.nb);
+	cpuhp_remove_state_nocalls(CPUHP_NOTF_ERR_INJ_PREPARE);
 	debugfs_remove_recursive(dir);
 }
 

lib/irq_poll.c

@@ -184,30 +184,21 @@ void irq_poll_init(struct irq_poll *iop, int weight, irq_poll_fn *poll_fn)
 }
 EXPORT_SYMBOL(irq_poll_init);
 
-static int irq_poll_cpu_notify(struct notifier_block *self,
-				 unsigned long action, void *hcpu)
+static int irq_poll_cpu_dead(unsigned int cpu)
 {
 	/*
 	 * If a CPU goes away, splice its entries to the current CPU
 	 * and trigger a run of the softirq
 	 */
-	if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) {
-		int cpu = (unsigned long) hcpu;
-
-		local_irq_disable();
-		list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
-				 this_cpu_ptr(&blk_cpu_iopoll));
-		__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
-		local_irq_enable();
-	}
+	local_irq_disable();
+	list_splice_init(&per_cpu(blk_cpu_iopoll, cpu),
+			 this_cpu_ptr(&blk_cpu_iopoll));
+	__raise_softirq_irqoff(IRQ_POLL_SOFTIRQ);
+	local_irq_enable();
 
-	return NOTIFY_OK;
+	return 0;
 }
 
-static struct notifier_block irq_poll_cpu_notifier = {
-	.notifier_call	= irq_poll_cpu_notify,
-};
-
 static __init int irq_poll_setup(void)
 {
 	int i;
@@ -216,7 +207,8 @@ static __init int irq_poll_setup(void)
 		INIT_LIST_HEAD(&per_cpu(blk_cpu_iopoll, i));
 
 	open_softirq(IRQ_POLL_SOFTIRQ, irq_poll_softirq);
-	register_hotcpu_notifier(&irq_poll_cpu_notifier);
+	cpuhp_setup_state_nocalls(CPUHP_IRQ_POLL_DEAD, "irq_poll:dead", NULL,
+				  irq_poll_cpu_dead);
 	return 0;
 }
 subsys_initcall(irq_poll_setup);

mm/page-writeback.c

@@ -2080,26 +2080,12 @@ void writeback_set_ratelimit(void)
 		ratelimit_pages = 16;
 }
 
-static int
-ratelimit_handler(struct notifier_block *self, unsigned long action,
-		  void *hcpu)
+static int page_writeback_cpu_online(unsigned int cpu)
 {
-
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-	case CPU_DEAD:
-		writeback_set_ratelimit();
-		return NOTIFY_OK;
-	default:
-		return NOTIFY_DONE;
-	}
+	writeback_set_ratelimit();
+	return 0;
 }
 
-static struct notifier_block ratelimit_nb = {
-	.notifier_call	= ratelimit_handler,
-	.next		= NULL,
-};
-
 /*
  * Called early on to tune the page writeback dirty limits.
  *
@@ -2122,8 +2108,10 @@ void __init page_writeback_init(void)
 {
 	BUG_ON(wb_domain_init(&global_wb_domain, GFP_KERNEL));
 
-	writeback_set_ratelimit();
-	register_cpu_notifier(&ratelimit_nb);
+	cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "mm/writeback:online",
+			  page_writeback_cpu_online, NULL);
+	cpuhp_setup_state(CPUHP_MM_WRITEBACK_DEAD, "mm/writeback:dead", NULL,
+			  page_writeback_cpu_online);
 }
 
 /**

mm/slab.c

@@ -886,6 +886,7 @@ static int init_cache_node(struct kmem_cache *cachep, int node, gfp_t gfp)
 	return 0;
 }
 
+#if (defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)) || defined(CONFIG_SMP)
 /*
  * Allocates and initializes node for a node on each slab cache, used for
  * either memory or cpu hotplug.  If memory is being hot-added, the kmem_cache_node
@@ -908,6 +909,7 @@ static int init_cache_node_node(int node)
 
 	return 0;
 }
+#endif
 
 static int setup_kmem_cache_node(struct kmem_cache *cachep,
 				int node, gfp_t gfp, bool force_change)
@@ -975,6 +977,8 @@ fail:
 	return ret;
 }
 
+#ifdef CONFIG_SMP
+
 static void cpuup_canceled(long cpu)
 {
 	struct kmem_cache *cachep;
@@ -1075,65 +1079,54 @@ bad:
 	return -ENOMEM;
 }
 
-static int cpuup_callback(struct notifier_block *nfb,
-				    unsigned long action, void *hcpu)
+int slab_prepare_cpu(unsigned int cpu)
 {
-	long cpu = (long)hcpu;
-	int err = 0;
+	int err;
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		mutex_lock(&slab_mutex);
-		err = cpuup_prepare(cpu);
-		mutex_unlock(&slab_mutex);
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		start_cpu_timer(cpu);
-		break;
-#ifdef CONFIG_HOTPLUG_CPU
-  	case CPU_DOWN_PREPARE:
-  	case CPU_DOWN_PREPARE_FROZEN:
-		/*
-		 * Shutdown cache reaper. Note that the slab_mutex is
-		 * held so that if cache_reap() is invoked it cannot do
-		 * anything expensive but will only modify reap_work
-		 * and reschedule the timer.
-		*/
-		cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
-		/* Now the cache_reaper is guaranteed to be not running. */
-		per_cpu(slab_reap_work, cpu).work.func = NULL;
-  		break;
-  	case CPU_DOWN_FAILED:
-  	case CPU_DOWN_FAILED_FROZEN:
-		start_cpu_timer(cpu);
-  		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		/*
-		 * Even if all the cpus of a node are down, we don't free the
-		 * kmem_cache_node of any cache. This to avoid a race between
-		 * cpu_down, and a kmalloc allocation from another cpu for
-		 * memory from the node of the cpu going down.  The node
-		 * structure is usually allocated from kmem_cache_create() and
-		 * gets destroyed at kmem_cache_destroy().
-		 */
-		/* fall through */
+	mutex_lock(&slab_mutex);
+	err = cpuup_prepare(cpu);
+	mutex_unlock(&slab_mutex);
+	return err;
+}
+
+/*
+ * This is called for a failed online attempt and for a successful
+ * offline.
+ *
+ * Even if all the cpus of a node are down, we don't free the
+ * kmem_list3 of any cache. This to avoid a race between cpu_down, and
+ * a kmalloc allocation from another cpu for memory from the node of
+ * the cpu going down.  The list3 structure is usually allocated from
+ * kmem_cache_create() and gets destroyed at kmem_cache_destroy().
+ */
+int slab_dead_cpu(unsigned int cpu)
+{
+	mutex_lock(&slab_mutex);
+	cpuup_canceled(cpu);
+	mutex_unlock(&slab_mutex);
+	return 0;
+}
 #endif
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-		mutex_lock(&slab_mutex);
-		cpuup_canceled(cpu);
-		mutex_unlock(&slab_mutex);
-		break;
-	}
-	return notifier_from_errno(err);
+
+static int slab_online_cpu(unsigned int cpu)
+{
+	start_cpu_timer(cpu);
+	return 0;
 }
 
-static struct notifier_block cpucache_notifier = {
-	&cpuup_callback, NULL, 0
-};
+static int slab_offline_cpu(unsigned int cpu)
+{
+	/*
+	 * Shutdown cache reaper. Note that the slab_mutex is held so
+	 * that if cache_reap() is invoked it cannot do anything
+	 * expensive but will only modify reap_work and reschedule the
+	 * timer.
+	 */
+	cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
+	/* Now the cache_reaper is guaranteed to be not running. */
+	per_cpu(slab_reap_work, cpu).work.func = NULL;
+	return 0;
+}
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
 /*
@@ -1336,12 +1329,6 @@ void __init kmem_cache_init_late(void)
 	/* Done! */
 	slab_state = FULL;
 
-	/*
-	 * Register a cpu startup notifier callback that initializes
-	 * cpu_cache_get for all new cpus
-	 */
-	register_cpu_notifier(&cpucache_notifier);
-
 #ifdef CONFIG_NUMA
 	/*
 	 * Register a memory hotplug callback that initializes and frees
@@ -1358,13 +1345,14 @@ void __init kmem_cache_init_late(void)
 
 static int __init cpucache_init(void)
 {
-	int cpu;
+	int ret;
 
 	/*
 	 * Register the timers that return unneeded pages to the page allocator
 	 */
-	for_each_online_cpu(cpu)
-		start_cpu_timer(cpu);
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "SLAB online",
+				slab_online_cpu, slab_offline_cpu);
+	WARN_ON(ret < 0);
 
 	/* Done! */
 	slab_state = FULL;

mm/slub.c

@@ -194,10 +194,6 @@ static inline bool kmem_cache_has_cpu_partial(struct kmem_cache *s)
 #define __OBJECT_POISON		0x80000000UL /* Poison object */
 #define __CMPXCHG_DOUBLE	0x40000000UL /* Use cmpxchg_double */
 
-#ifdef CONFIG_SMP
-static struct notifier_block slab_notifier;
-#endif
-
 /*
  * Tracking user of a slab.
  */
@@ -2304,6 +2300,25 @@ static void flush_all(struct kmem_cache *s)
 	on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC);
 }
 
+/*
+ * Use the cpu notifier to insure that the cpu slabs are flushed when
+ * necessary.
+ */
+static int slub_cpu_dead(unsigned int cpu)
+{
+	struct kmem_cache *s;
+	unsigned long flags;
+
+	mutex_lock(&slab_mutex);
+	list_for_each_entry(s, &slab_caches, list) {
+		local_irq_save(flags);
+		__flush_cpu_slab(s, cpu);
+		local_irq_restore(flags);
+	}
+	mutex_unlock(&slab_mutex);
+	return 0;
+}
+
 /*
  * Check if the objects in a per cpu structure fit numa
  * locality expectations.
@@ -4144,9 +4159,8 @@ void __init kmem_cache_init(void)
 	/* Setup random freelists for each cache */
 	init_freelist_randomization();
 
-#ifdef CONFIG_SMP
-	register_cpu_notifier(&slab_notifier);
-#endif
+	cpuhp_setup_state_nocalls(CPUHP_SLUB_DEAD, "slub:dead", NULL,
+				  slub_cpu_dead);
 
 	pr_info("SLUB: HWalign=%d, Order=%d-%d, MinObjects=%d, CPUs=%d, Nodes=%d\n",
 		cache_line_size(),
@@ -4210,43 +4224,6 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
 	return err;
 }
 
-#ifdef CONFIG_SMP
-/*
- * Use the cpu notifier to insure that the cpu slabs are flushed when
- * necessary.
- */
-static int slab_cpuup_callback(struct notifier_block *nfb,
-		unsigned long action, void *hcpu)
-{
-	long cpu = (long)hcpu;
-	struct kmem_cache *s;
-	unsigned long flags;
-
-	switch (action) {
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		mutex_lock(&slab_mutex);
-		list_for_each_entry(s, &slab_caches, list) {
-			local_irq_save(flags);
-			__flush_cpu_slab(s, cpu);
-			local_irq_restore(flags);
-		}
-		mutex_unlock(&slab_mutex);
-		break;
-	default:
-		break;
-	}
-	return NOTIFY_OK;
-}
-
-static struct notifier_block slab_notifier = {
-	.notifier_call = slab_cpuup_callback
-};
-
-#endif
-
 void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
 {
 	struct kmem_cache *s;

tools/testing/radix-tree/linux/cpu.h

@@ -7,19 +7,8 @@
 #define CPU_DOWN_PREPARE	0x0005 /* CPU (unsigned)v going down */
 #define CPU_DOWN_FAILED		0x0006 /* CPU (unsigned)v NOT going down */
 #define CPU_DEAD		0x0007 /* CPU (unsigned)v dead */
-#define CPU_DYING		0x0008 /* CPU (unsigned)v not running any task,
-					* not handling interrupts, soon dead.
-					* Called on the dying cpu, interrupts
-					* are already disabled. Must not
-					* sleep, must not fail */
 #define CPU_POST_DEAD		0x0009 /* CPU (unsigned)v dead, cpu_hotplug
 					* lock is dropped */
-#define CPU_STARTING		0x000A /* CPU (unsigned)v soon running.
-					* Called on the new cpu, just before
-					* enabling interrupts. Must not sleep,
-					* must not fail */
-#define CPU_DYING_IDLE		0x000B /* CPU (unsigned)v dying, reached
-					* idle loop. */
 #define CPU_BROKEN		0x000C /* CPU (unsigned)v did not die properly,
 					* perhaps due to preemption. */
 #define CPU_TASKS_FROZEN	0x0010
@@ -30,5 +19,3 @@
 #define CPU_DOWN_PREPARE_FROZEN (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
 #define CPU_DOWN_FAILED_FROZEN  (CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
 #define CPU_DEAD_FROZEN		(CPU_DEAD | CPU_TASKS_FROZEN)
-#define CPU_DYING_FROZEN	(CPU_DYING | CPU_TASKS_FROZEN)
-#define CPU_STARTING_FROZEN	(CPU_STARTING | CPU_TASKS_FROZEN)