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
  ...

2 files changed, 229 insertions, 113 deletions

diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c
index d41c28d00b57..b74548728fb5 100644
--- a/drivers/net/ethernet/marvell/mvneta.c
+++ b/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>");
diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 1b5f531eeb25..fad84f3f4109 100644
--- a/drivers/net/virtio_net.c
+++ b/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");