#include <linux/mutex.h>
#include <linux/gfp.h>
#include <linux/suspend.h>
+#include <linux/lockdep.h>
+#include <linux/tick.h>
+#include <linux/irq.h>
+#include <trace/events/power.h>
+
+#include <trace/events/sched.h>
#include "smpboot.h"
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);
static struct {
struct task_struct *active_writer;
- struct mutex lock; /* Synchronizes accesses to refcount, */
+ /* wait queue to wake up the active_writer */
+ wait_queue_head_t wq;
+ /* verifies that no writer will get active while readers are active */
+ struct mutex lock;
/*
* Also blocks the new readers during
* an ongoing cpu hotplug operation.
*/
- int refcount;
+ atomic_t refcount;
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+ struct lockdep_map dep_map;
+#endif
} cpu_hotplug = {
.active_writer = NULL,
+ .wq = __WAIT_QUEUE_HEAD_INITIALIZER(cpu_hotplug.wq),
.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_tryread() \
+ lock_map_acquire_tryread(&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++;
+ atomic_inc(&cpu_hotplug.refcount);
mutex_unlock(&cpu_hotplug.lock);
-
}
EXPORT_SYMBOL_GPL(get_online_cpus);
void put_online_cpus(void)
{
+ int refcount;
+
if (cpu_hotplug.active_writer == current)
return;
- mutex_lock(&cpu_hotplug.lock);
- if (WARN_ON(!cpu_hotplug.refcount))
- cpu_hotplug.refcount++; /* try to fix things up */
+ refcount = atomic_dec_return(&cpu_hotplug.refcount);
+ if (WARN_ON(refcount < 0)) /* try to fix things up */
+ atomic_inc(&cpu_hotplug.refcount);
- if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
- wake_up_process(cpu_hotplug.active_writer);
- mutex_unlock(&cpu_hotplug.lock);
+ if (refcount <= 0 && waitqueue_active(&cpu_hotplug.wq))
+ wake_up(&cpu_hotplug.wq);
+
+ cpuhp_lock_release();
}
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)
{
+ DEFINE_WAIT(wait);
+
cpu_hotplug.active_writer = current;
+ cpuhp_lock_acquire();
for (;;) {
mutex_lock(&cpu_hotplug.lock);
- if (likely(!cpu_hotplug.refcount))
- break;
- __set_current_state(TASK_UNINTERRUPTIBLE);
+ prepare_to_wait(&cpu_hotplug.wq, &wait, TASK_UNINTERRUPTIBLE);
+ if (likely(!atomic_read(&cpu_hotplug.refcount)))
+ break;
mutex_unlock(&cpu_hotplug.lock);
schedule();
}
+ finish_wait(&cpu_hotplug.wq, &wait);
}
-static void cpu_hotplug_done(void)
+void cpu_hotplug_done(void)
{
cpu_hotplug.active_writer = NULL;
mutex_unlock(&cpu_hotplug.lock);
+ cpuhp_lock_release();
}
/*
void cpu_hotplug_disable(void)
{
cpu_maps_update_begin();
- cpu_hotplug_disabled = 1;
+ cpu_hotplug_disabled++;
cpu_maps_update_done();
}
+EXPORT_SYMBOL_GPL(cpu_hotplug_disable);
void cpu_hotplug_enable(void)
{
cpu_maps_update_begin();
- cpu_hotplug_disabled = 0;
+ WARN_ON(--cpu_hotplug_disabled < 0);
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 */
+EXPORT_SYMBOL_GPL(cpu_hotplug_enable);
+#endif /* CONFIG_HOTPLUG_CPU */
/* Need to know about CPUs going up/down? */
-int __ref register_cpu_notifier(struct notifier_block *nb)
+int register_cpu_notifier(struct notifier_block *nb)
{
int ret;
cpu_maps_update_begin();
return ret;
}
+int __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)
{
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)
+void unregister_cpu_notifier(struct notifier_block *nb)
{
cpu_maps_update_begin();
raw_notifier_chain_unregister(&cpu_chain, nb);
}
EXPORT_SYMBOL(unregister_cpu_notifier);
+void __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
rcu_read_unlock();
}
-static inline void check_for_tasks(int cpu)
+static inline void check_for_tasks(int dead_cpu)
{
- struct task_struct *p;
- cputime_t utime, stime;
+ struct task_struct *g, *p;
- write_lock_irq(&tasklist_lock);
- for_each_process(p) {
- 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",
- p->comm, task_pid_nr(p), cpu,
- p->state, p->flags);
+ read_lock(&tasklist_lock);
+ for_each_process_thread(g, p) {
+ if (!p->on_rq)
+ continue;
+ /*
+ * We do the check with unlocked task_rq(p)->lock.
+ * Order the reading to do not warn about a task,
+ * which was running on this cpu in the past, and
+ * it's just been woken on another cpu.
+ */
+ rmb();
+ if (task_cpu(p) != dead_cpu)
+ continue;
+
+ pr_warn("Task %s (pid=%d) is on cpu %d (state=%ld, flags=%x)\n",
+ p->comm, task_pid_nr(p), dead_cpu, p->state, p->flags);
}
- write_unlock_irq(&tasklist_lock);
+ read_unlock(&tasklist_lock);
}
struct take_cpu_down_param {
};
/* Take this CPU down. */
-static int __ref take_cpu_down(void *_param)
+static int take_cpu_down(void *_param)
{
struct take_cpu_down_param *param = _param;
int err;
return err;
cpu_notify(CPU_DYING | param->mod, param->hcpu);
+ /* Give up timekeeping duties */
+ tick_handover_do_timer();
/* Park the stopper thread */
- kthread_park(current);
+ stop_machine_park((long)param->hcpu);
return 0;
}
/* Requires cpu_add_remove_lock to be held */
-static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
+static int _cpu_down(unsigned int cpu, int tasks_frozen)
{
int err, nr_calls = 0;
void *hcpu = (void *)(long)cpu;
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 wait for both.
+ *
+ * Do sync before park smpboot threads to take care the rcu boost case.
+ */
+ if (IS_ENABLED(CONFIG_PREEMPT))
+ synchronize_rcu_mult(call_rcu, call_rcu_sched);
+ else
+ synchronize_rcu();
+
smpboot_park_threads(cpu);
- err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
+ /*
+ * Prevent irq alloc/free while the dying cpu reorganizes the
+ * interrupt affinities.
+ */
+ irq_lock_sparse();
+
+ /*
+ * 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. */
- smpboot_unpark_threads(cpu);
cpu_notify_nofail(CPU_DOWN_FAILED | mod, hcpu);
+ irq_unlock_sparse();
goto out_release;
}
BUG_ON(cpu_online(cpu));
*
* Wait for the stop thread to go away.
*/
- while (!idle_cpu(cpu))
+ while (!per_cpu(cpu_dead_idle, cpu))
cpu_relax();
+ smp_mb(); /* Read from cpu_dead_idle before __cpu_die(). */
+ per_cpu(cpu_dead_idle, cpu) = false;
+ /* Interrupts are moved away from the dying cpu, reenable alloc/free */
+ irq_unlock_sparse();
+
+ hotplug_cpu__broadcast_tick_pull(cpu);
/* This actually kills the CPU. */
__cpu_die(cpu);
/* CPU is completely dead: tell everyone. Too late to complain. */
+ tick_cleanup_dead_cpu(cpu);
cpu_notify_nofail(CPU_DEAD | mod, hcpu);
check_for_tasks(cpu);
out_release:
cpu_hotplug_done();
+ trace_sched_cpu_hotplug(cpu, err, 0);
if (!err)
cpu_notify_nofail(CPU_POST_DEAD | mod, hcpu);
return err;
}
-int __ref cpu_down(unsigned int cpu)
+int cpu_down(unsigned int cpu)
{
int err;
EXPORT_SYMBOL(cpu_down);
#endif /*CONFIG_HOTPLUG_CPU*/
+/*
+ * Unpark per-CPU smpboot kthreads at CPU-online time.
+ */
+static int smpboot_thread_call(struct notifier_block *nfb,
+ unsigned long action, void *hcpu)
+{
+ int cpu = (long)hcpu;
+
+ switch (action & ~CPU_TASKS_FROZEN) {
+
+ case CPU_DOWN_FAILED:
+ case CPU_ONLINE:
+ smpboot_unpark_threads(cpu);
+ break;
+
+ default:
+ break;
+ }
+
+ return NOTIFY_OK;
+}
+
+static struct notifier_block smpboot_thread_notifier = {
+ .notifier_call = smpboot_thread_call,
+ .priority = CPU_PRI_SMPBOOT,
+};
+
+void smpboot_thread_init(void)
+{
+ register_cpu_notifier(&smpboot_thread_notifier);
+}
+
/* Requires cpu_add_remove_lock to be held */
-static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
+static int _cpu_up(unsigned int cpu, int tasks_frozen)
{
int ret, nr_calls = 0;
void *hcpu = (void *)(long)cpu;
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;
}
/* Arch-specific enabling code. */
ret = __cpu_up(cpu, idle);
+
if (ret != 0)
goto out_notify;
BUG_ON(!cpu_online(cpu));
- /* Wake the per cpu threads */
- smpboot_unpark_threads(cpu);
-
/* Now call notifier in preparation. */
cpu_notify(CPU_ONLINE | mod, hcpu);
__cpu_notify(CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
out:
cpu_hotplug_done();
+ trace_sched_cpu_hotplug(cpu, ret, 1);
return ret;
}
-int __cpuinit cpu_up(unsigned int cpu)
+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();
*/
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;
}
}
- if (!error) {
+ if (!error)
BUG_ON(num_online_cpus() > 1);
- /* 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");
- }
+ else
+ pr_err("Non-boot CPUs are not disabled\n");
+
+ /*
+ * Make sure the CPUs won't be enabled by someone else. We need to do
+ * this even in case of failure as all disable_nonboot_cpus() users are
+ * supposed to do enable_nonboot_cpus() on the failure path.
+ */
+ cpu_hotplug_disabled++;
+
cpu_maps_update_done();
return error;
}
{
}
-void __ref enable_nonboot_cpus(void)
+void enable_nonboot_cpus(void)
{
int cpu, error;
+ struct device *cpu_device;
/* Allow everyone to use the CPU hotplug again */
cpu_maps_update_begin();
- cpu_hotplug_disabled = 0;
+ WARN_ON(--cpu_hotplug_disabled < 0);
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);
+ cpu_device = get_cpu_device(cpu);
+ if (!cpu_device)
+ pr_err("%s: failed to get cpu%d device\n",
+ __func__, cpu);
+ else
+ kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE);
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();
* 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().
*/
-void __cpuinit notify_cpu_starting(unsigned int cpu)
+void notify_cpu_starting(unsigned int cpu)
{
unsigned long val = CPU_STARTING;
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)
{
cpumask_copy(to_cpumask(cpu_online_bits), src);
}
+
+static ATOMIC_NOTIFIER_HEAD(idle_notifier);
+
+void idle_notifier_register(struct notifier_block *n)
+{
+ atomic_notifier_chain_register(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_register);
+
+void idle_notifier_unregister(struct notifier_block *n)
+{
+ atomic_notifier_chain_unregister(&idle_notifier, n);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_unregister);
+
+void idle_notifier_call_chain(unsigned long val)
+{
+ atomic_notifier_call_chain(&idle_notifier, val, NULL);
+}
+EXPORT_SYMBOL_GPL(idle_notifier_call_chain);