#include <linux/stop_machine.h>
#include <linux/mutex.h>
-/* This protects CPUs going up and down... */
+/* Serializes the updates to cpu_online_map, cpu_present_map */
static DEFINE_MUTEX(cpu_add_remove_lock);
-static DEFINE_MUTEX(cpu_bitmask_lock);
-static __cpuinitdata BLOCKING_NOTIFIER_HEAD(cpu_chain);
+static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);
-#ifdef CONFIG_HOTPLUG_CPU
+/* If set, cpu_up and cpu_down will return -EBUSY and do nothing.
+ * Should always be manipulated under cpu_add_remove_lock
+ */
+static int cpu_hotplug_disabled;
+
+static struct {
+ struct task_struct *active_writer;
+ struct mutex lock; /* Synchronizes accesses to refcount, */
+ /*
+ * Also blocks the new readers during
+ * an ongoing cpu hotplug operation.
+ */
+ int refcount;
+ wait_queue_head_t writer_queue;
+} cpu_hotplug;
+
+#define writer_exists() (cpu_hotplug.active_writer != NULL)
+
+void __init cpu_hotplug_init(void)
+{
+ cpu_hotplug.active_writer = NULL;
+ mutex_init(&cpu_hotplug.lock);
+ cpu_hotplug.refcount = 0;
+ init_waitqueue_head(&cpu_hotplug.writer_queue);
+}
-/* Crappy recursive lock-takers in cpufreq! Complain loudly about idiots */
-static struct task_struct *recursive;
-static int recursive_depth;
+#ifdef CONFIG_HOTPLUG_CPU
-void lock_cpu_hotplug(void)
+void get_online_cpus(void)
{
- struct task_struct *tsk = current;
-
- if (tsk == recursive) {
- static int warnings = 10;
- if (warnings) {
- printk(KERN_ERR "Lukewarm IQ detected in hotplug locking\n");
- WARN_ON(1);
- warnings--;
- }
- recursive_depth++;
+ might_sleep();
+ if (cpu_hotplug.active_writer == current)
return;
- }
- mutex_lock(&cpu_bitmask_lock);
- recursive = tsk;
+ mutex_lock(&cpu_hotplug.lock);
+ cpu_hotplug.refcount++;
+ mutex_unlock(&cpu_hotplug.lock);
+
}
-EXPORT_SYMBOL_GPL(lock_cpu_hotplug);
+EXPORT_SYMBOL_GPL(get_online_cpus);
-void unlock_cpu_hotplug(void)
+void put_online_cpus(void)
{
- WARN_ON(recursive != current);
- if (recursive_depth) {
- recursive_depth--;
+ if (cpu_hotplug.active_writer == current)
return;
- }
- mutex_unlock(&cpu_bitmask_lock);
- recursive = NULL;
+ mutex_lock(&cpu_hotplug.lock);
+ cpu_hotplug.refcount--;
+
+ if (unlikely(writer_exists()) && !cpu_hotplug.refcount)
+ wake_up(&cpu_hotplug.writer_queue);
+
+ mutex_unlock(&cpu_hotplug.lock);
+
}
-EXPORT_SYMBOL_GPL(unlock_cpu_hotplug);
+EXPORT_SYMBOL_GPL(put_online_cpus);
#endif /* CONFIG_HOTPLUG_CPU */
+/*
+ * The following two API's must be used when attempting
+ * to serialize the updates to cpu_online_map, cpu_present_map.
+ */
+void cpu_maps_update_begin(void)
+{
+ mutex_lock(&cpu_add_remove_lock);
+}
+
+void cpu_maps_update_done(void)
+{
+ mutex_unlock(&cpu_add_remove_lock);
+}
+
+/*
+ * This ensures that the hotplug operation can begin only when the
+ * refcount goes to zero.
+ *
+ * Note that during a cpu-hotplug operation, the new readers, if any,
+ * will be blocked by the cpu_hotplug.lock
+ *
+ * Since cpu_maps_update_begin is always called after invoking
+ * cpu_maps_update_begin, we can be sure that only one writer is active.
+ *
+ * Note that theoretically, there is a possibility of a livelock:
+ * - Refcount goes to zero, last reader wakes up the sleeping
+ * writer.
+ * - Last reader unlocks the cpu_hotplug.lock.
+ * - A new reader arrives at this moment, bumps up the refcount.
+ * - The writer acquires the cpu_hotplug.lock finds the refcount
+ * non zero and goes to sleep again.
+ *
+ * However, this is very difficult to achieve in practice since
+ * get_online_cpus() not an api which is called all that often.
+ *
+ */
+static void cpu_hotplug_begin(void)
+{
+ DECLARE_WAITQUEUE(wait, current);
+
+ mutex_lock(&cpu_hotplug.lock);
+
+ cpu_hotplug.active_writer = current;
+ add_wait_queue_exclusive(&cpu_hotplug.writer_queue, &wait);
+ while (cpu_hotplug.refcount) {
+ set_current_state(TASK_UNINTERRUPTIBLE);
+ mutex_unlock(&cpu_hotplug.lock);
+ schedule();
+ mutex_lock(&cpu_hotplug.lock);
+ }
+ remove_wait_queue_locked(&cpu_hotplug.writer_queue, &wait);
+}
+
+static void cpu_hotplug_done(void)
+{
+ cpu_hotplug.active_writer = NULL;
+ mutex_unlock(&cpu_hotplug.lock);
+}
/* Need to know about CPUs going up/down? */
int __cpuinit register_cpu_notifier(struct notifier_block *nb)
{
- return blocking_notifier_chain_register(&cpu_chain, nb);
+ int ret;
+ cpu_maps_update_begin();
+ ret = raw_notifier_chain_register(&cpu_chain, nb);
+ cpu_maps_update_done();
+ return ret;
}
#ifdef CONFIG_HOTPLUG_CPU
void unregister_cpu_notifier(struct notifier_block *nb)
{
- blocking_notifier_chain_unregister(&cpu_chain, nb);
+ cpu_maps_update_begin();
+ raw_notifier_chain_unregister(&cpu_chain, nb);
+ cpu_maps_update_done();
}
EXPORT_SYMBOL(unregister_cpu_notifier);
(!cputime_eq(p->utime, cputime_zero) ||
!cputime_eq(p->stime, cputime_zero)))
printk(KERN_WARNING "Task %s (pid = %d) is on cpu %d\
- (state = %ld, flags = %lx) \n",
- p->comm, p->pid, cpu, p->state, p->flags);
+ (state = %ld, flags = %x) \n",
+ p->comm, task_pid_nr(p), cpu,
+ p->state, p->flags);
}
write_unlock_irq(&tasklist_lock);
}
+struct take_cpu_down_param {
+ unsigned long mod;
+ void *hcpu;
+};
+
/* Take this CPU down. */
-static int take_cpu_down(void *unused)
+static int take_cpu_down(void *_param)
{
+ struct take_cpu_down_param *param = _param;
int err;
+ raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
+ param->hcpu);
/* Ensure this CPU doesn't handle any more interrupts. */
err = __cpu_disable();
if (err < 0)
return 0;
}
-int cpu_down(unsigned int cpu)
+/* Requires cpu_add_remove_lock to be held */
+static int _cpu_down(unsigned int cpu, int tasks_frozen)
{
- int err;
+ int err, nr_calls = 0;
struct task_struct *p;
cpumask_t old_allowed, tmp;
+ void *hcpu = (void *)(long)cpu;
+ unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+ struct take_cpu_down_param tcd_param = {
+ .mod = mod,
+ .hcpu = hcpu,
+ };
- mutex_lock(&cpu_add_remove_lock);
- if (num_online_cpus() == 1) {
- err = -EBUSY;
- goto out;
- }
+ if (num_online_cpus() == 1)
+ return -EBUSY;
- if (!cpu_online(cpu)) {
- err = -EINVAL;
- goto out;
- }
+ if (!cpu_online(cpu))
+ return -EINVAL;
- err = blocking_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE,
- (void *)(long)cpu);
+ cpu_hotplug_begin();
+ err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
+ hcpu, -1, &nr_calls);
if (err == NOTIFY_BAD) {
+ nr_calls--;
+ __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
+ hcpu, nr_calls, NULL);
printk("%s: attempt to take down CPU %u failed\n",
__FUNCTION__, cpu);
err = -EINVAL;
- goto out;
+ goto out_release;
}
/* Ensure that we are not runnable on dying cpu */
cpu_clear(cpu, tmp);
set_cpus_allowed(current, tmp);
- mutex_lock(&cpu_bitmask_lock);
- p = __stop_machine_run(take_cpu_down, NULL, cpu);
- mutex_unlock(&cpu_bitmask_lock);
+ p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
- if (IS_ERR(p)) {
+ if (IS_ERR(p) || cpu_online(cpu)) {
/* CPU didn't die: tell everyone. Can't complain. */
- if (blocking_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED,
- (void *)(long)cpu) == NOTIFY_BAD)
+ if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
+ hcpu) == NOTIFY_BAD)
BUG();
- err = PTR_ERR(p);
- goto out_allowed;
- }
-
- if (cpu_online(cpu))
+ if (IS_ERR(p)) {
+ err = PTR_ERR(p);
+ goto out_allowed;
+ }
goto out_thread;
+ }
/* Wait for it to sleep (leaving idle task). */
while (!idle_cpu(cpu))
/* This actually kills the CPU. */
__cpu_die(cpu);
- /* Move it here so it can run. */
- kthread_bind(p, get_cpu());
- put_cpu();
-
/* CPU is completely dead: tell everyone. Too late to complain. */
- if (blocking_notifier_call_chain(&cpu_chain, CPU_DEAD,
- (void *)(long)cpu) == NOTIFY_BAD)
+ if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD | mod,
+ hcpu) == NOTIFY_BAD)
BUG();
check_for_tasks(cpu);
err = kthread_stop(p);
out_allowed:
set_cpus_allowed(current, old_allowed);
-out:
- mutex_unlock(&cpu_add_remove_lock);
+out_release:
+ cpu_hotplug_done();
+ return err;
+}
+
+int cpu_down(unsigned int cpu)
+{
+ int err = 0;
+
+ cpu_maps_update_begin();
+ if (cpu_hotplug_disabled)
+ err = -EBUSY;
+ else
+ err = _cpu_down(cpu, 0);
+
+ cpu_maps_update_done();
return err;
}
#endif /*CONFIG_HOTPLUG_CPU*/
-int __devinit cpu_up(unsigned int cpu)
+/* Requires cpu_add_remove_lock to be held */
+static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
{
- int ret;
+ int ret, nr_calls = 0;
void *hcpu = (void *)(long)cpu;
+ unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
- mutex_lock(&cpu_add_remove_lock);
- if (cpu_online(cpu) || !cpu_present(cpu)) {
- ret = -EINVAL;
- goto out;
- }
+ if (cpu_online(cpu) || !cpu_present(cpu))
+ return -EINVAL;
- ret = blocking_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE, hcpu);
+ cpu_hotplug_begin();
+ ret = __raw_notifier_call_chain(&cpu_chain, CPU_UP_PREPARE | mod, hcpu,
+ -1, &nr_calls);
if (ret == NOTIFY_BAD) {
+ nr_calls--;
printk("%s: attempt to bring up CPU %u failed\n",
__FUNCTION__, cpu);
ret = -EINVAL;
}
/* Arch-specific enabling code. */
- mutex_lock(&cpu_bitmask_lock);
ret = __cpu_up(cpu);
- mutex_unlock(&cpu_bitmask_lock);
if (ret != 0)
goto out_notify;
BUG_ON(!cpu_online(cpu));
/* Now call notifier in preparation. */
- blocking_notifier_call_chain(&cpu_chain, CPU_ONLINE, hcpu);
+ raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);
out_notify:
if (ret != 0)
- blocking_notifier_call_chain(&cpu_chain,
- CPU_UP_CANCELED, hcpu);
-out:
- mutex_unlock(&cpu_add_remove_lock);
+ __raw_notifier_call_chain(&cpu_chain,
+ CPU_UP_CANCELED | mod, hcpu, nr_calls, NULL);
+ cpu_hotplug_done();
+
return ret;
}
+
+int __cpuinit cpu_up(unsigned int cpu)
+{
+ int err = 0;
+ if (!cpu_isset(cpu, cpu_possible_map)) {
+ printk(KERN_ERR "can't online cpu %d because it is not "
+ "configured as may-hotadd at boot time\n", cpu);
+#if defined(CONFIG_IA64) || defined(CONFIG_X86_64) || defined(CONFIG_S390)
+ printk(KERN_ERR "please check additional_cpus= boot "
+ "parameter\n");
+#endif
+ return -EINVAL;
+ }
+
+ cpu_maps_update_begin();
+ if (cpu_hotplug_disabled)
+ err = -EBUSY;
+ else
+ err = _cpu_up(cpu, 0);
+
+ cpu_maps_update_done();
+ return err;
+}
+
+#ifdef CONFIG_PM_SLEEP_SMP
+static cpumask_t frozen_cpus;
+
+int disable_nonboot_cpus(void)
+{
+ int cpu, first_cpu, error = 0;
+
+ cpu_maps_update_begin();
+ first_cpu = first_cpu(cpu_online_map);
+ /* We take down all of the non-boot CPUs in one shot to avoid races
+ * with the userspace trying to use the CPU hotplug at the same time
+ */
+ cpus_clear(frozen_cpus);
+ printk("Disabling non-boot CPUs ...\n");
+ for_each_online_cpu(cpu) {
+ if (cpu == first_cpu)
+ continue;
+ error = _cpu_down(cpu, 1);
+ if (!error) {
+ cpu_set(cpu, frozen_cpus);
+ printk("CPU%d is down\n", cpu);
+ } else {
+ printk(KERN_ERR "Error taking CPU%d down: %d\n",
+ cpu, error);
+ break;
+ }
+ }
+ 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");
+ }
+ cpu_maps_update_done();
+ return error;
+}
+
+void __ref enable_nonboot_cpus(void)
+{
+ int cpu, error;
+
+ /* Allow everyone to use the CPU hotplug again */
+ cpu_maps_update_begin();
+ cpu_hotplug_disabled = 0;
+ if (cpus_empty(frozen_cpus))
+ goto out;
+
+ printk("Enabling non-boot CPUs ...\n");
+ for_each_cpu_mask(cpu, frozen_cpus) {
+ error = _cpu_up(cpu, 1);
+ if (!error) {
+ printk("CPU%d is up\n", cpu);
+ continue;
+ }
+ printk(KERN_WARNING "Error taking CPU%d up: %d\n", cpu, error);
+ }
+ cpus_clear(frozen_cpus);
+out:
+ cpu_maps_update_done();
+}
+#endif /* CONFIG_PM_SLEEP_SMP */