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

Pull smp hotplug updates from Thomas Gleixner:
 "This is the final round of converting the notifier mess to the state
  machine. The removal of the notifiers and the related infrastructure
  will happen around rc1, as there are conversions outstanding in other
  trees.

  The whole exercise removed about 2000 lines of code in total and in
  course of the conversion several dozen bugs got fixed. The new
  mechanism allows to test almost every hotplug step standalone, so
  usage sites can exercise all transitions extensively.

  There is more room for improvement, like integrating all the
  pointlessly different architecture mechanisms of synchronizing,
  setting cpus online etc into the core code"

* 'smp-hotplug-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (60 commits)
  tracing/rb: Init the CPU mask on allocation
  soc/fsl/qbman: Convert to hotplug state machine
  soc/fsl/qbman: Convert to hotplug state machine
  zram: Convert to hotplug state machine
  KVM/PPC/Book3S HV: Convert to hotplug state machine
  arm64/cpuinfo: Convert to hotplug state machine
  arm64/cpuinfo: Make hotplug notifier symmetric
  mm/compaction: Convert to hotplug state machine
  iommu/vt-d: Convert to hotplug state machine
  mm/zswap: Convert pool to hotplug state machine
  mm/zswap: Convert dst-mem to hotplug state machine
  mm/zsmalloc: Convert to hotplug state machine
  mm/vmstat: Convert to hotplug state machine
  mm/vmstat: Avoid on each online CPU loops
  mm/vmstat: Drop get_online_cpus() from init_cpu_node_state/vmstat_cpu_dead()
  tracing/rb: Convert to hotplug state machine
  oprofile/nmi timer: Convert to hotplug state machine
  net/iucv: Use explicit clean up labels in iucv_init()
  x86/pci/amd-bus: Convert to hotplug state machine
  x86/oprofile/nmi: Convert to hotplug state machine
  ...

3 files changed, 117 insertions, 151 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a3cb27af4f9b..132e1ec67da0 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1792,6 +1792,14 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
 	add_timer_on(t, cpu);
 }
 
+static void __mcheck_cpu_setup_timer(void)
+{
+	struct timer_list *t = this_cpu_ptr(&mce_timer);
+	unsigned int cpu = smp_processor_id();
+
+	setup_pinned_timer(t, mce_timer_fn, cpu);
+}
+
 static void __mcheck_cpu_init_timer(void)
 {
 	struct timer_list *t = this_cpu_ptr(&mce_timer);
@@ -1843,7 +1851,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
-	__mcheck_cpu_init_timer();
+	__mcheck_cpu_setup_timer();
 }
 
 /*
@@ -2303,8 +2311,6 @@ static struct bus_type mce_subsys = {
 
 DEFINE_PER_CPU(struct device *, mce_device);
 
-void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
-
 static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
 {
 	return container_of(attr, struct mce_bank, attr);
@@ -2457,6 +2463,10 @@ static int mce_device_create(unsigned int cpu)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
+	dev = per_cpu(mce_device, cpu);
+	if (dev)
+		return 0;
+
 	dev = kzalloc(sizeof *dev, GFP_KERNEL);
 	if (!dev)
 		return -ENOMEM;
@@ -2516,28 +2526,25 @@ static void mce_device_remove(unsigned int cpu)
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
-static void mce_disable_cpu(void *h)
+static void mce_disable_cpu(void)
 {
-	unsigned long action = *(unsigned long *)h;
-
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
-	if (!(action & CPU_TASKS_FROZEN))
+	if (!cpuhp_tasks_frozen)
 		cmci_clear();
 
 	vendor_disable_error_reporting();
 }
 
-static void mce_reenable_cpu(void *h)
+static void mce_reenable_cpu(void)
 {
-	unsigned long action = *(unsigned long *)h;
 	int i;
 
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 
-	if (!(action & CPU_TASKS_FROZEN))
+	if (!cpuhp_tasks_frozen)
 		cmci_reenable();
 	for (i = 0; i < mca_cfg.banks; i++) {
 		struct mce_bank *b = &mce_banks[i];
@@ -2547,45 +2554,43 @@ static void mce_reenable_cpu(void *h)
 	}
 }
 
-/* Get notified when a cpu comes on/off. Be hotplug friendly. */
-static int
-mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
+static int mce_cpu_dead(unsigned int cpu)
+{
+	mce_intel_hcpu_update(cpu);
+
+	/* intentionally ignoring frozen here */
+	if (!cpuhp_tasks_frozen)
+		cmci_rediscover();
+	return 0;
+}
+
+static int mce_cpu_online(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
 	struct timer_list *t = &per_cpu(mce_timer, cpu);
+	int ret;
 
-	switch (action & ~CPU_TASKS_FROZEN) {
-	case CPU_ONLINE:
-		mce_device_create(cpu);
-		if (threshold_cpu_callback)
-			threshold_cpu_callback(action, cpu);
-		break;
-	case CPU_DEAD:
-		if (threshold_cpu_callback)
-			threshold_cpu_callback(action, cpu);
-		mce_device_remove(cpu);
-		mce_intel_hcpu_update(cpu);
+	mce_device_create(cpu);
 
-		/* intentionally ignoring frozen here */
-		if (!(action & CPU_TASKS_FROZEN))
-			cmci_rediscover();
-		break;
-	case CPU_DOWN_PREPARE:
-		smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
-		del_timer_sync(t);
-		break;
-	case CPU_DOWN_FAILED:
-		smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
-		mce_start_timer(cpu, t);
-		break;
+	ret = mce_threshold_create_device(cpu);
+	if (ret) {
+		mce_device_remove(cpu);
+		return ret;
 	}
-
-	return NOTIFY_OK;
+	mce_reenable_cpu();
+	mce_start_timer(cpu, t);
+	return 0;
 }
 
-static struct notifier_block mce_cpu_notifier = {
-	.notifier_call = mce_cpu_callback,
-};
+static int mce_cpu_pre_down(unsigned int cpu)
+{
+	struct timer_list *t = &per_cpu(mce_timer, cpu);
+
+	mce_disable_cpu();
+	del_timer_sync(t);
+	mce_threshold_remove_device(cpu);
+	mce_device_remove(cpu);
+	return 0;
+}
 
 static __init void mce_init_banks(void)
 {
@@ -2607,8 +2612,8 @@ static __init void mce_init_banks(void)
 
 static __init int mcheck_init_device(void)
 {
+	enum cpuhp_state hp_online;
 	int err;
-	int i = 0;
 
 	if (!mce_available(&boot_cpu_data)) {
 		err = -EIO;
@@ -2626,23 +2631,16 @@ static __init int mcheck_init_device(void)
 	if (err)
 		goto err_out_mem;
 
-	cpu_notifier_register_begin();
-	for_each_online_cpu(i) {
-		err = mce_device_create(i);
-		if (err) {
-			/*
-			 * Register notifier anyway (and do not unreg it) so
-			 * that we don't leave undeleted timers, see notifier
-			 * callback above.
-			 */
-			__register_hotcpu_notifier(&mce_cpu_notifier);
-			cpu_notifier_register_done();
-			goto err_device_create;
-		}
-	}
+	err = cpuhp_setup_state(CPUHP_X86_MCE_DEAD, "x86/mce:dead", NULL,
+				mce_cpu_dead);
+	if (err)
+		goto err_out_mem;
 
-	__register_hotcpu_notifier(&mce_cpu_notifier);
-	cpu_notifier_register_done();
+	err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
+				mce_cpu_online, mce_cpu_pre_down);
+	if (err < 0)
+		goto err_out_online;
+	hp_online = err;
 
 	register_syscore_ops(&mce_syscore_ops);
 
@@ -2655,16 +2653,10 @@ static __init int mcheck_init_device(void)
 
 err_register:
 	unregister_syscore_ops(&mce_syscore_ops);
+	cpuhp_remove_state(hp_online);
 
-err_device_create:
-	/*
-	 * We didn't keep track of which devices were created above, but
-	 * even if we had, the set of online cpus might have changed.
-	 * Play safe and remove for every possible cpu, since
-	 * mce_device_remove() will do the right thing.
-	 */
-	for_each_possible_cpu(i)
-		mce_device_remove(i);
+err_out_online:
+	cpuhp_remove_state(CPUHP_X86_MCE_DEAD);
 
 err_out_mem:
 	free_cpumask_var(mce_device_initialized);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 51ad0086b0bb..ffacfdcacb85 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -54,6 +54,8 @@
 /* Threshold LVT offset is at MSR0xC0000410[15:12] */
 #define SMCA_THR_LVT_OFF	0xF000
 
+static bool thresholding_en;
+
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -1235,31 +1237,6 @@ static int threshold_create_bank(unsigned int cpu, unsigned int bank)
 	return err;
 }
 
-/* create dir/files for all valid threshold banks */
-static int threshold_create_device(unsigned int cpu)
-{
-	unsigned int bank;
-	struct threshold_bank **bp;
-	int err = 0;
-
-	bp = kzalloc(sizeof(struct threshold_bank *) * mca_cfg.banks,
-		     GFP_KERNEL);
-	if (!bp)
-		return -ENOMEM;
-
-	per_cpu(threshold_banks, cpu) = bp;
-
-	for (bank = 0; bank < mca_cfg.banks; ++bank) {
-		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
-			continue;
-		err = threshold_create_bank(cpu, bank);
-		if (err)
-			return err;
-	}
-
-	return err;
-}
-
 static void deallocate_threshold_block(unsigned int cpu,
 						 unsigned int bank)
 {
@@ -1327,48 +1304,71 @@ free_out:
 	per_cpu(threshold_banks, cpu)[bank] = NULL;
 }
 
-static void threshold_remove_device(unsigned int cpu)
+int mce_threshold_remove_device(unsigned int cpu)
 {
 	unsigned int bank;
 
+	if (!thresholding_en)
+		return 0;
+
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
 		threshold_remove_bank(cpu, bank);
 	}
 	kfree(per_cpu(threshold_banks, cpu));
+	per_cpu(threshold_banks, cpu) = NULL;
+	return 0;
 }
 
-/* get notified when a cpu comes on/off */
-static void
-amd_64_threshold_cpu_callback(unsigned long action, unsigned int cpu)
+/* create dir/files for all valid threshold banks */
+int mce_threshold_create_device(unsigned int cpu)
 {
-	switch (action) {
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-		threshold_create_device(cpu);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		threshold_remove_device(cpu);
-		break;
-	default:
-		break;
+	unsigned int bank;
+	struct threshold_bank **bp;
+	int err = 0;
+
+	if (!thresholding_en)
+		return 0;
+
+	bp = per_cpu(threshold_banks, cpu);
+	if (bp)
+		return 0;
+
+	bp = kzalloc(sizeof(struct threshold_bank *) * mca_cfg.banks,
+		     GFP_KERNEL);
+	if (!bp)
+		return -ENOMEM;
+
+	per_cpu(threshold_banks, cpu) = bp;
+
+	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
+			continue;
+		err = threshold_create_bank(cpu, bank);
+		if (err)
+			goto err;
 	}
+	return err;
+err:
+	mce_threshold_remove_device(cpu);
+	return err;
 }
 
 static __init int threshold_init_device(void)
 {
 	unsigned lcpu = 0;
 
+	if (mce_threshold_vector == amd_threshold_interrupt)
+		thresholding_en = true;
+
 	/* to hit CPUs online before the notifier is up */
 	for_each_online_cpu(lcpu) {
-		int err = threshold_create_device(lcpu);
+		int err = mce_threshold_create_device(lcpu);
 
 		if (err)
 			return err;
 	}
-	threshold_cpu_callback = amd_64_threshold_cpu_callback;
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 2f5c3418b18b..465aca8be009 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -270,58 +270,32 @@ static void thermal_throttle_remove_dev(struct device *dev)
 }
 
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
-static int
-thermal_throttle_cpu_callback(struct notifier_block *nfb,
-			      unsigned long action,
-			      void *hcpu)
+static int thermal_throttle_online(unsigned int cpu)
 {
-	unsigned int cpu = (unsigned long)hcpu;
-	struct device *dev;
-	int err = 0;
-
-	dev = get_cpu_device(cpu);
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		err = thermal_throttle_add_dev(dev, cpu);
-		WARN_ON(err);
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		thermal_throttle_remove_dev(dev);
-		break;
-	}
-	return notifier_from_errno(err);
+	struct device *dev = get_cpu_device(cpu);
+
+	return thermal_throttle_add_dev(dev, cpu);
 }
 
-static struct notifier_block thermal_throttle_cpu_notifier =
+static int thermal_throttle_offline(unsigned int cpu)
 {
-	.notifier_call = thermal_throttle_cpu_callback,
-};
+	struct device *dev = get_cpu_device(cpu);
+
+	thermal_throttle_remove_dev(dev);
+	return 0;
+}
 
 static __init int thermal_throttle_init_device(void)
 {
-	unsigned int cpu = 0;
-	int err;
+	int ret;
 
 	if (!atomic_read(&therm_throt_en))
 		return 0;
 
-	cpu_notifier_register_begin();
-
-	/* connect live CPUs to sysfs */
-	for_each_online_cpu(cpu) {
-		err = thermal_throttle_add_dev(get_cpu_device(cpu), cpu);
-		WARN_ON(err);
-	}
-
-	__register_hotcpu_notifier(&thermal_throttle_cpu_notifier);
-	cpu_notifier_register_done();
-
-	return 0;
+	ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/therm:online",
+				thermal_throttle_online,
+				thermal_throttle_offline);
+	return ret < 0 ? ret : 0;
 }
 device_initcall(thermal_throttle_init_device);