1 files changed, 85 insertions, 53 deletions

diff --git a/kernel/cpu.c b/kernel/cpu.c
index b2b227b8212..a343bde710b 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -19,6 +19,8 @@
 #include <linux/mutex.h>
 #include <linux/gfp.h>
 #include <linux/suspend.h>
+#include <linux/lockdep.h>
+#include <trace/events/power.h>
 
 #include "smpboot.h"
 
@@ -27,18 +29,23 @@
 static DEFINE_MUTEX(cpu_add_remove_lock);
 
 /*
- * The following two API's must be used when attempting
- * to serialize the updates to cpu_online_mask, cpu_present_mask.
+ * The following two APIs (cpu_maps_update_begin/done) must be used when
+ * attempting to serialize the updates to cpu_online_mask & cpu_present_mask.
+ * The APIs cpu_notifier_register_begin/done() must be used to protect CPU
+ * hotplug callback (un)registration performed using __register_cpu_notifier()
+ * or __unregister_cpu_notifier().
  */
 void cpu_maps_update_begin(void)
 {
 	mutex_lock(&cpu_add_remove_lock);
 }
+EXPORT_SYMBOL(cpu_notifier_register_begin);
 
 void cpu_maps_update_done(void)
 {
 	mutex_unlock(&cpu_add_remove_lock);
 }
+EXPORT_SYMBOL(cpu_notifier_register_done);
 
 static RAW_NOTIFIER_HEAD(cpu_chain);
 
@@ -57,17 +64,30 @@ static struct {
 	 * an ongoing cpu hotplug operation.
 	 */
 	int refcount;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	struct lockdep_map dep_map;
+#endif
 } cpu_hotplug = {
 	.active_writer = NULL,
 	.lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
 	.refcount = 0,
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	.dep_map = {.name = "cpu_hotplug.lock" },
+#endif
 };
 
+/* Lockdep annotations for get/put_online_cpus() and cpu_hotplug_begin/end() */
+#define cpuhp_lock_acquire_read() lock_map_acquire_read(&cpu_hotplug.dep_map)
+#define cpuhp_lock_acquire()      lock_map_acquire(&cpu_hotplug.dep_map)
+#define cpuhp_lock_release()      lock_map_release(&cpu_hotplug.dep_map)
+
 void get_online_cpus(void)
 {
 	might_sleep();
 	if (cpu_hotplug.active_writer == current)
 		return;
+	cpuhp_lock_acquire_read();
 	mutex_lock(&cpu_hotplug.lock);
 	cpu_hotplug.refcount++;
 	mutex_unlock(&cpu_hotplug.lock);
@@ -87,6 +107,7 @@ void put_online_cpus(void)
 	if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
 		wake_up_process(cpu_hotplug.active_writer);
 	mutex_unlock(&cpu_hotplug.lock);
+	cpuhp_lock_release();
 
 }
 EXPORT_SYMBOL_GPL(put_online_cpus);
@@ -113,10 +134,11 @@ EXPORT_SYMBOL_GPL(put_online_cpus);
  * get_online_cpus() not an api which is called all that often.
  *
  */
-static void cpu_hotplug_begin(void)
+void cpu_hotplug_begin(void)
 {
 	cpu_hotplug.active_writer = current;
 
+	cpuhp_lock_acquire();
 	for (;;) {
 		mutex_lock(&cpu_hotplug.lock);
 		if (likely(!cpu_hotplug.refcount))
@@ -127,10 +149,11 @@ static void cpu_hotplug_begin(void)
 	}
 }
 
-static void cpu_hotplug_done(void)
+void cpu_hotplug_done(void)
 {
 	cpu_hotplug.active_writer = NULL;
 	mutex_unlock(&cpu_hotplug.lock);
+	cpuhp_lock_release();
 }
 
 /*
@@ -154,10 +177,7 @@ void cpu_hotplug_enable(void)
 	cpu_maps_update_done();
 }
 
-#else /* #if CONFIG_HOTPLUG_CPU */
-static void cpu_hotplug_begin(void) {}
-static void cpu_hotplug_done(void) {}
-#endif	/* #else #if CONFIG_HOTPLUG_CPU */
+#endif	/* CONFIG_HOTPLUG_CPU */
 
 /* Need to know about CPUs going up/down? */
 int __ref register_cpu_notifier(struct notifier_block *nb)
@@ -169,6 +189,11 @@ int __ref register_cpu_notifier(struct notifier_block *nb)
 	return ret;
 }
 
+int __ref __register_cpu_notifier(struct notifier_block *nb)
+{
+	return raw_notifier_chain_register(&cpu_chain, nb);
+}
+
 static int __cpu_notify(unsigned long val, void *v, int nr_to_call,
 			int *nr_calls)
 {
@@ -192,6 +217,7 @@ static void cpu_notify_nofail(unsigned long val, void *v)
 	BUG_ON(cpu_notify(val, v));
 }
 EXPORT_SYMBOL(register_cpu_notifier);
+EXPORT_SYMBOL(__register_cpu_notifier);
 
 void __ref unregister_cpu_notifier(struct notifier_block *nb)
 {
@@ -201,6 +227,12 @@ void __ref unregister_cpu_notifier(struct notifier_block *nb)
 }
 EXPORT_SYMBOL(unregister_cpu_notifier);
 
+void __ref __unregister_cpu_notifier(struct notifier_block *nb)
+{
+	raw_notifier_chain_unregister(&cpu_chain, nb);
+}
+EXPORT_SYMBOL(__unregister_cpu_notifier);
+
 /**
  * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU
  * @cpu: a CPU id
@@ -252,8 +284,7 @@ static inline void check_for_tasks(int cpu)
 		task_cputime(p, &utime, &stime);
 		if (task_cpu(p) == cpu && p->state == TASK_RUNNING &&
 		    (utime || stime))
-			printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d "
-				"(state = %ld, flags = %x)\n",
+			pr_warn("Task %s (pid = %d) is on cpu %d (state = %ld, flags = %x)\n",
 				p->comm, task_pid_nr(p), cpu,
 				p->state, p->flags);
 	}
@@ -305,12 +336,32 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 	if (err) {
 		nr_calls--;
 		__cpu_notify(CPU_DOWN_FAILED | mod, hcpu, nr_calls, NULL);
-		printk("%s: attempt to take down CPU %u failed\n",
-				__func__, cpu);
+		pr_warn("%s: attempt to take down CPU %u failed\n",
+			__func__, cpu);
 		goto out_release;
 	}
+
+	/*
+	 * By now we've cleared cpu_active_mask, wait for all preempt-disabled
+	 * and RCU users of this state to go away such that all new such users
+	 * will observe it.
+	 *
+	 * For CONFIG_PREEMPT we have preemptible RCU and its sync_rcu() might
+	 * not imply sync_sched(), so explicitly call both.
+	 *
+	 * Do sync before park smpboot threads to take care the rcu boost case.
+	 */
+#ifdef CONFIG_PREEMPT
+	synchronize_sched();
+#endif
+	synchronize_rcu();
+
 	smpboot_park_threads(cpu);
 
+	/*
+	 * So now all preempt/rcu users must observe !cpu_active().
+	 */
+
 	err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
 	if (err) {
 		/* CPU didn't die: tell everyone.  Can't complain. */
@@ -393,8 +444,8 @@ static int _cpu_up(unsigned int cpu, int tasks_frozen)
 	ret = __cpu_notify(CPU_UP_PREPARE | mod, hcpu, -1, &nr_calls);
 	if (ret) {
 		nr_calls--;
-		printk(KERN_WARNING "%s: attempt to bring up CPU %u failed\n",
-				__func__, cpu);
+		pr_warn("%s: attempt to bring up CPU %u failed\n",
+			__func__, cpu);
 		goto out_notify;
 	}
 
@@ -423,42 +474,18 @@ int cpu_up(unsigned int cpu)
 {
 	int err = 0;
 
-#ifdef	CONFIG_MEMORY_HOTPLUG
-	int nid;
-	pg_data_t	*pgdat;
-#endif
-
 	if (!cpu_possible(cpu)) {
-		printk(KERN_ERR "can't online cpu %d because it is not "
-			"configured as may-hotadd at boot time\n", cpu);
+		pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n",
+		       cpu);
 #if defined(CONFIG_IA64)
-		printk(KERN_ERR "please check additional_cpus= boot "
-				"parameter\n");
+		pr_err("please check additional_cpus= boot parameter\n");
 #endif
 		return -EINVAL;
 	}
 
-#ifdef	CONFIG_MEMORY_HOTPLUG
-	nid = cpu_to_node(cpu);
-	if (!node_online(nid)) {
-		err = mem_online_node(nid);
-		if (err)
-			return err;
-	}
-
-	pgdat = NODE_DATA(nid);
-	if (!pgdat) {
-		printk(KERN_ERR
-			"Can't online cpu %d due to NULL pgdat\n", cpu);
-		return -ENOMEM;
-	}
-
-	if (pgdat->node_zonelists->_zonerefs->zone == NULL) {
-		mutex_lock(&zonelists_mutex);
-		build_all_zonelists(NULL, NULL);
-		mutex_unlock(&zonelists_mutex);
-	}
-#endif
+	err = try_online_node(cpu_to_node(cpu));
+	if (err)
+		return err;
 
 	cpu_maps_update_begin();
 
@@ -490,16 +517,17 @@ int disable_nonboot_cpus(void)
 	 */
 	cpumask_clear(frozen_cpus);
 
-	printk("Disabling non-boot CPUs ...\n");
+	pr_info("Disabling non-boot CPUs ...\n");
 	for_each_online_cpu(cpu) {
 		if (cpu == first_cpu)
 			continue;
+		trace_suspend_resume(TPS("CPU_OFF"), cpu, true);
 		error = _cpu_down(cpu, 1);
+		trace_suspend_resume(TPS("CPU_OFF"), cpu, false);
 		if (!error)
 			cpumask_set_cpu(cpu, frozen_cpus);
 		else {
-			printk(KERN_ERR "Error taking CPU%d down: %d\n",
-				cpu, error);
+			pr_err("Error taking CPU%d down: %d\n", cpu, error);
 			break;
 		}
 	}
@@ -509,7 +537,7 @@ int disable_nonboot_cpus(void)
 		/* Make sure the CPUs won't be enabled by someone else */
 		cpu_hotplug_disabled = 1;
 	} else {
-		printk(KERN_ERR "Non-boot CPUs are not disabled\n");
+		pr_err("Non-boot CPUs are not disabled\n");
 	}
 	cpu_maps_update_done();
 	return error;
@@ -533,17 +561,19 @@ void __ref enable_nonboot_cpus(void)
 	if (cpumask_empty(frozen_cpus))
 		goto out;
 
-	printk(KERN_INFO "Enabling non-boot CPUs ...\n");
+	pr_info("Enabling non-boot CPUs ...\n");
 
 	arch_enable_nonboot_cpus_begin();
 
 	for_each_cpu(cpu, frozen_cpus) {
+		trace_suspend_resume(TPS("CPU_ON"), cpu, true);
 		error = _cpu_up(cpu, 1);
+		trace_suspend_resume(TPS("CPU_ON"), cpu, false);
 		if (!error) {
-			printk(KERN_INFO "CPU%d is up\n", cpu);
+			pr_info("CPU%d is up\n", cpu);
 			continue;
 		}
-		printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
+		pr_warn("Error taking CPU%d up: %d\n", cpu, error);
 	}
 
 	arch_enable_nonboot_cpus_end();
@@ -698,10 +728,12 @@ void set_cpu_present(unsigned int cpu, bool present)
 
 void set_cpu_online(unsigned int cpu, bool online)
 {
-	if (online)
+	if (online) {
 		cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
-	else
+		cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
+	} else {
 		cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
+	}
 }
 
 void set_cpu_active(unsigned int cpu, bool active)