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
  ...

4 files changed, 80 insertions, 121 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 3fec23cdeb80..6372117f653f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -8008,18 +8008,13 @@ out:
 }
 EXPORT_SYMBOL_GPL(dev_change_net_namespace);
 
-static int dev_cpu_callback(struct notifier_block *nfb,
-			    unsigned long action,
-			    void *ocpu)
+static int dev_cpu_dead(unsigned int oldcpu)
 {
 	struct sk_buff **list_skb;
 	struct sk_buff *skb;
-	unsigned int cpu, oldcpu = (unsigned long)ocpu;
+	unsigned int cpu;
 	struct softnet_data *sd, *oldsd;
 
-	if (action != CPU_DEAD && action != CPU_DEAD_FROZEN)
-		return NOTIFY_OK;
-
 	local_irq_disable();
 	cpu = smp_processor_id();
 	sd = &per_cpu(softnet_data, cpu);
@@ -8069,10 +8064,9 @@ static int dev_cpu_callback(struct notifier_block *nfb,
 		input_queue_head_incr(oldsd);
 	}
 
-	return NOTIFY_OK;
+	return 0;
 }
 
-
 /**
  *	netdev_increment_features - increment feature set by one
  *	@all: current feature set
@@ -8406,7 +8400,9 @@ static int __init net_dev_init(void)
 	open_softirq(NET_TX_SOFTIRQ, net_tx_action);
 	open_softirq(NET_RX_SOFTIRQ, net_rx_action);
 
-	hotcpu_notifier(dev_cpu_callback, 0);
+	rc = cpuhp_setup_state_nocalls(CPUHP_NET_DEV_DEAD, "net/dev:dead",
+				       NULL, dev_cpu_dead);
+	WARN_ON(rc < 0);
 	dst_subsys_init();
 	rc = 0;
 out:
diff --git a/net/core/flow.c b/net/core/flow.c
index 18e8893d4be5..f765c11d8df5 100644
--- a/net/core/flow.c
+++ b/net/core/flow.c
@@ -417,28 +417,20 @@ static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
 	return 0;
 }
 
-static int flow_cache_cpu(struct notifier_block *nfb,
-			  unsigned long action,
-			  void *hcpu)
+static int flow_cache_cpu_up_prep(unsigned int cpu, struct hlist_node *node)
 {
-	struct flow_cache *fc = container_of(nfb, struct flow_cache,
-						hotcpu_notifier);
-	int res, cpu = (unsigned long) hcpu;
+	struct flow_cache *fc = hlist_entry_safe(node, struct flow_cache, node);
+
+	return flow_cache_cpu_prepare(fc, cpu);
+}
+
+static int flow_cache_cpu_dead(unsigned int cpu, struct hlist_node *node)
+{
+	struct flow_cache *fc = hlist_entry_safe(node, struct flow_cache, node);
 	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
 
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		res = flow_cache_cpu_prepare(fc, cpu);
-		if (res)
-			return notifier_from_errno(res);
-		break;
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		__flow_cache_shrink(fc, fcp, 0);
-		break;
-	}
-	return NOTIFY_OK;
+	__flow_cache_shrink(fc, fcp, 0);
+	return 0;
 }
 
 int flow_cache_init(struct net *net)
@@ -465,18 +457,8 @@ int flow_cache_init(struct net *net)
 	if (!fc->percpu)
 		return -ENOMEM;
 
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(i) {
-		if (flow_cache_cpu_prepare(fc, i))
-			goto err;
-	}
-	fc->hotcpu_notifier = (struct notifier_block){
-		.notifier_call = flow_cache_cpu,
-	};
-	__register_hotcpu_notifier(&fc->hotcpu_notifier);
-
-	cpu_notifier_register_done();
+	if (cpuhp_state_add_instance(CPUHP_NET_FLOW_PREPARE, &fc->node))
+		goto err;
 
 	setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd,
 		    (unsigned long) fc);
@@ -492,8 +474,6 @@ err:
 		fcp->hash_table = NULL;
 	}
 
-	cpu_notifier_register_done();
-
 	free_percpu(fc->percpu);
 	fc->percpu = NULL;
 
@@ -507,7 +487,8 @@ void flow_cache_fini(struct net *net)
 	struct flow_cache *fc = &net->xfrm.flow_cache_global;
 
 	del_timer_sync(&fc->rnd_timer);
-	unregister_hotcpu_notifier(&fc->hotcpu_notifier);
+
+	cpuhp_state_remove_instance_nocalls(CPUHP_NET_FLOW_PREPARE, &fc->node);
 
 	for_each_possible_cpu(i) {
 		struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
@@ -519,3 +500,14 @@ void flow_cache_fini(struct net *net)
 	fc->percpu = NULL;
 }
 EXPORT_SYMBOL(flow_cache_fini);
+
+void __init flow_cache_hp_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_NET_FLOW_PREPARE,
+				      "net/flow:prepare",
+				      flow_cache_cpu_up_prep,
+				      flow_cache_cpu_dead);
+	WARN_ON(ret < 0);
+}
diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 88a2a3ba4212..8f7ef167c45a 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -639,7 +639,7 @@ static void iucv_disable(void)
 	put_online_cpus();
 }
 
-static void free_iucv_data(int cpu)
+static int iucv_cpu_dead(unsigned int cpu)
 {
 	kfree(iucv_param_irq[cpu]);
 	iucv_param_irq[cpu] = NULL;
@@ -647,9 +647,10 @@ static void free_iucv_data(int cpu)
 	iucv_param[cpu] = NULL;
 	kfree(iucv_irq_data[cpu]);
 	iucv_irq_data[cpu] = NULL;
+	return 0;
 }
 
-static int alloc_iucv_data(int cpu)
+static int iucv_cpu_prepare(unsigned int cpu)
 {
 	/* Note: GFP_DMA used to get memory below 2G */
 	iucv_irq_data[cpu] = kmalloc_node(sizeof(struct iucv_irq_data),
@@ -671,58 +672,38 @@ static int alloc_iucv_data(int cpu)
 	return 0;
 
 out_free:
-	free_iucv_data(cpu);
+	iucv_cpu_dead(cpu);
 	return -ENOMEM;
 }
 
-static int iucv_cpu_notify(struct notifier_block *self,
-				     unsigned long action, void *hcpu)
+static int iucv_cpu_online(unsigned int cpu)
 {
-	cpumask_t cpumask;
-	long cpu = (long) hcpu;
-
-	switch (action) {
-	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
-		if (alloc_iucv_data(cpu))
-			return notifier_from_errno(-ENOMEM);
-		break;
-	case CPU_UP_CANCELED:
-	case CPU_UP_CANCELED_FROZEN:
-	case CPU_DEAD:
-	case CPU_DEAD_FROZEN:
-		free_iucv_data(cpu);
-		break;
-	case CPU_ONLINE:
-	case CPU_ONLINE_FROZEN:
-	case CPU_DOWN_FAILED:
-	case CPU_DOWN_FAILED_FROZEN:
-		if (!iucv_path_table)
-			break;
-		smp_call_function_single(cpu, iucv_declare_cpu, NULL, 1);
-		break;
-	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
-		if (!iucv_path_table)
-			break;
-		cpumask_copy(&cpumask, &iucv_buffer_cpumask);
-		cpumask_clear_cpu(cpu, &cpumask);
-		if (cpumask_empty(&cpumask))
-			/* Can't offline last IUCV enabled cpu. */
-			return notifier_from_errno(-EINVAL);
-		smp_call_function_single(cpu, iucv_retrieve_cpu, NULL, 1);
-		if (cpumask_empty(&iucv_irq_cpumask))
-			smp_call_function_single(
-				cpumask_first(&iucv_buffer_cpumask),
-				iucv_allow_cpu, NULL, 1);
-		break;
-	}
-	return NOTIFY_OK;
+	if (!iucv_path_table)
+		return 0;
+	iucv_declare_cpu(NULL);
+	return 0;
 }
 
-static struct notifier_block __refdata iucv_cpu_notifier = {
-	.notifier_call = iucv_cpu_notify,
-};
+static int iucv_cpu_down_prep(unsigned int cpu)
+{
+	cpumask_t cpumask;
+
+	if (!iucv_path_table)
+		return 0;
+
+	cpumask_copy(&cpumask, &iucv_buffer_cpumask);
+	cpumask_clear_cpu(cpu, &cpumask);
+	if (cpumask_empty(&cpumask))
+		/* Can't offline last IUCV enabled cpu. */
+		return -EINVAL;
+
+	iucv_retrieve_cpu(NULL);
+	if (!cpumask_empty(&iucv_irq_cpumask))
+		return 0;
+	smp_call_function_single(cpumask_first(&iucv_buffer_cpumask),
+				 iucv_allow_cpu, NULL, 1);
+	return 0;
+}
 
 /**
  * iucv_sever_pathid
@@ -2027,6 +2008,7 @@ struct iucv_interface iucv_if = {
 };
 EXPORT_SYMBOL(iucv_if);
 
+static enum cpuhp_state iucv_online;
 /**
  * iucv_init
  *
@@ -2035,7 +2017,6 @@ EXPORT_SYMBOL(iucv_if);
 static int __init iucv_init(void)
 {
 	int rc;
-	int cpu;
 
 	if (!MACHINE_IS_VM) {
 		rc = -EPROTONOSUPPORT;
@@ -2054,23 +2035,19 @@ static int __init iucv_init(void)
 		goto out_int;
 	}
 
-	cpu_notifier_register_begin();
-
-	for_each_online_cpu(cpu) {
-		if (alloc_iucv_data(cpu)) {
-			rc = -ENOMEM;
-			goto out_free;
-		}
-	}
-	rc = __register_hotcpu_notifier(&iucv_cpu_notifier);
+	rc = cpuhp_setup_state(CPUHP_NET_IUCV_PREPARE, "net/iucv:prepare",
+			       iucv_cpu_prepare, iucv_cpu_dead);
 	if (rc)
-		goto out_free;
-
-	cpu_notifier_register_done();
+		goto out_dev;
+	rc = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "net/iucv:online",
+			       iucv_cpu_online, iucv_cpu_down_prep);
+	if (rc < 0)
+		goto out_prep;
+	iucv_online = rc;
 
 	rc = register_reboot_notifier(&iucv_reboot_notifier);
 	if (rc)
-		goto out_cpu;
+		goto out_remove_hp;
 	ASCEBC(iucv_error_no_listener, 16);
 	ASCEBC(iucv_error_no_memory, 16);
 	ASCEBC(iucv_error_pathid, 16);
@@ -2084,15 +2061,11 @@ static int __init iucv_init(void)
 
 out_reboot:
 	unregister_reboot_notifier(&iucv_reboot_notifier);
-out_cpu:
-	cpu_notifier_register_begin();
-	__unregister_hotcpu_notifier(&iucv_cpu_notifier);
-out_free:
-	for_each_possible_cpu(cpu)
-		free_iucv_data(cpu);
-
-	cpu_notifier_register_done();
-
+out_remove_hp:
+	cpuhp_remove_state(iucv_online);
+out_prep:
+	cpuhp_remove_state(CPUHP_NET_IUCV_PREPARE);
+out_dev:
 	root_device_unregister(iucv_root);
 out_int:
 	unregister_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt);
@@ -2110,7 +2083,6 @@ out:
 static void __exit iucv_exit(void)
 {
 	struct iucv_irq_list *p, *n;
-	int cpu;
 
 	spin_lock_irq(&iucv_queue_lock);
 	list_for_each_entry_safe(p, n, &iucv_task_queue, list)
@@ -2119,11 +2091,9 @@ static void __exit iucv_exit(void)
 		kfree(p);
 	spin_unlock_irq(&iucv_queue_lock);
 	unregister_reboot_notifier(&iucv_reboot_notifier);
-	cpu_notifier_register_begin();
-	__unregister_hotcpu_notifier(&iucv_cpu_notifier);
-	for_each_possible_cpu(cpu)
-		free_iucv_data(cpu);
-	cpu_notifier_register_done();
+
+	cpuhp_remove_state_nocalls(iucv_online);
+	cpuhp_remove_state(CPUHP_NET_IUCV_PREPARE);
 	root_device_unregister(iucv_root);
 	bus_unregister(&iucv_bus);
 	unregister_external_irq(EXT_IRQ_IUCV, iucv_external_interrupt);
diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
index 5bf7e1bfeac7..177e208e8ff5 100644
--- a/net/xfrm/xfrm_policy.c
+++ b/net/xfrm/xfrm_policy.c
@@ -3113,6 +3113,7 @@ static struct pernet_operations __net_initdata xfrm_net_ops = {
 
 void __init xfrm_init(void)
 {
+	flow_cache_hp_init();
 	register_pernet_subsys(&xfrm_net_ops);
 	seqcount_init(&xfrm_policy_hash_generation);
 	xfrm_input_init();