#include <linux/cpu.h>
#include <linux/init.h>
#include <linux/kthread.h>
-#include <linux/module.h>
+#include <linux/export.h>
#include <linux/percpu.h>
#include <linux/sched.h>
#include <linux/stop_machine.h>
#include <linux/interrupt.h>
#include <linux/kallsyms.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
/*
* Structure to determine completion condition and record errors. May
/* the actual stopper, one per every possible cpu, enabled on online cpus */
struct cpu_stopper {
spinlock_t lock;
+ bool enabled; /* is this stopper enabled? */
struct list_head works; /* list of pending works */
struct task_struct *thread; /* stopper thread */
- bool enabled; /* is this stopper enabled? */
};
static DEFINE_PER_CPU(struct cpu_stopper, cpu_stopper);
+static bool stop_machine_initialized = false;
static void cpu_stop_init_done(struct cpu_stop_done *done, unsigned int nr_todo)
{
static DEFINE_MUTEX(stop_cpus_mutex);
static DEFINE_PER_CPU(struct cpu_stop_work, stop_cpus_work);
-int __stop_cpus(const struct cpumask *cpumask, cpu_stop_fn_t fn, void *arg)
+static void queue_stop_cpus_work(const struct cpumask *cpumask,
+ cpu_stop_fn_t fn, void *arg,
+ struct cpu_stop_done *done)
{
struct cpu_stop_work *work;
- struct cpu_stop_done done;
unsigned int cpu;
/* initialize works and done */
work = &per_cpu(stop_cpus_work, cpu);
work->fn = fn;
work->arg = arg;
- work->done = &done;
+ work->done = done;
}
- cpu_stop_init_done(&done, cpumask_weight(cpumask));
/*
* Disable preemption while queueing to avoid getting
cpu_stop_queue_work(&per_cpu(cpu_stopper, cpu),
&per_cpu(stop_cpus_work, cpu));
preempt_enable();
+}
+
+static int __stop_cpus(const struct cpumask *cpumask,
+ cpu_stop_fn_t fn, void *arg)
+{
+ struct cpu_stop_done done;
+ cpu_stop_init_done(&done, cpumask_weight(cpumask));
+ queue_stop_cpus_work(cpumask, fn, arg, &done);
wait_for_completion(&done.completion);
return done.executed ? done.ret : -ENOENT;
}
cpu_stop_fn_t fn = work->fn;
void *arg = work->arg;
struct cpu_stop_done *done = work->done;
- char ksym_buf[KSYM_NAME_LEN];
+ char ksym_buf[KSYM_NAME_LEN] __maybe_unused;
__set_current_state(TASK_RUNNING);
goto repeat;
}
+extern void sched_set_stop_task(int cpu, struct task_struct *stop);
+
/* manage stopper for a cpu, mostly lifted from sched migration thread mgmt */
static int __cpuinit cpu_stop_cpu_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
- struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 };
unsigned int cpu = (unsigned long)hcpu;
struct cpu_stopper *stopper = &per_cpu(cpu_stopper, cpu);
- struct cpu_stop_work *work;
struct task_struct *p;
switch (action & ~CPU_TASKS_FROZEN) {
case CPU_UP_PREPARE:
BUG_ON(stopper->thread || stopper->enabled ||
!list_empty(&stopper->works));
- p = kthread_create(cpu_stopper_thread, stopper, "stopper/%d",
- cpu);
+ p = kthread_create_on_node(cpu_stopper_thread,
+ stopper,
+ cpu_to_node(cpu),
+ "migration/%d", cpu);
if (IS_ERR(p))
- return NOTIFY_BAD;
- sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m);
+ return notifier_from_errno(PTR_ERR(p));
get_task_struct(p);
+ kthread_bind(p, cpu);
+ sched_set_stop_task(cpu, p);
stopper->thread = p;
break;
case CPU_ONLINE:
- kthread_bind(stopper->thread, cpu);
/* strictly unnecessary, as first user will wake it */
wake_up_process(stopper->thread);
/* mark enabled */
#ifdef CONFIG_HOTPLUG_CPU
case CPU_UP_CANCELED:
- case CPU_DEAD:
+ case CPU_POST_DEAD:
+ {
+ struct cpu_stop_work *work;
+
+ sched_set_stop_task(cpu, NULL);
/* kill the stopper */
kthread_stop(stopper->thread);
/* drain remaining works */
put_task_struct(stopper->thread);
stopper->thread = NULL;
break;
+ }
#endif
}
/* start one for the boot cpu */
err = cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_UP_PREPARE,
bcpu);
- BUG_ON(err == NOTIFY_BAD);
+ BUG_ON(err != NOTIFY_OK);
cpu_stop_cpu_callback(&cpu_stop_cpu_notifier, CPU_ONLINE, bcpu);
register_cpu_notifier(&cpu_stop_cpu_notifier);
+ stop_machine_initialized = true;
+
return 0;
}
early_initcall(cpu_stop_init);
+#ifdef CONFIG_STOP_MACHINE
+
/* This controls the threads on each CPU. */
enum stopmachine_state {
/* Dummy starting state for thread. */
/* Exit */
STOPMACHINE_EXIT,
};
-static enum stopmachine_state state;
struct stop_machine_data {
- int (*fn)(void *);
- void *data;
- int fnret;
+ int (*fn)(void *);
+ void *data;
+ /* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
+ unsigned int num_threads;
+ const struct cpumask *active_cpus;
+
+ enum stopmachine_state state;
+ atomic_t thread_ack;
};
-/* Like num_online_cpus(), but hotplug cpu uses us, so we need this. */
-static unsigned int num_threads;
-static atomic_t thread_ack;
-static DEFINE_MUTEX(lock);
-/* setup_lock protects refcount, stop_machine_wq and stop_machine_work. */
-static DEFINE_MUTEX(setup_lock);
-/* Users of stop_machine. */
-static int refcount;
-static struct workqueue_struct *stop_machine_wq;
-static struct stop_machine_data active, idle;
-static const struct cpumask *active_cpus;
-static void __percpu *stop_machine_work;
-
-static void set_state(enum stopmachine_state newstate)
+static void set_state(struct stop_machine_data *smdata,
+ enum stopmachine_state newstate)
{
/* Reset ack counter. */
- atomic_set(&thread_ack, num_threads);
+ atomic_set(&smdata->thread_ack, smdata->num_threads);
smp_wmb();
- state = newstate;
+ smdata->state = newstate;
}
/* Last one to ack a state moves to the next state. */
-static void ack_state(void)
+static void ack_state(struct stop_machine_data *smdata)
{
- if (atomic_dec_and_test(&thread_ack))
- set_state(state + 1);
+ if (atomic_dec_and_test(&smdata->thread_ack))
+ set_state(smdata, smdata->state + 1);
}
-/* This is the actual function which stops the CPU. It runs
- * in the context of a dedicated stopmachine workqueue. */
-static void stop_cpu(struct work_struct *unused)
+/* This is the cpu_stop function which stops the CPU. */
+static int stop_machine_cpu_stop(void *data)
{
+ struct stop_machine_data *smdata = data;
enum stopmachine_state curstate = STOPMACHINE_NONE;
- struct stop_machine_data *smdata = &idle;
- int cpu = smp_processor_id();
- int err;
+ int cpu = smp_processor_id(), err = 0;
+ unsigned long flags;
+ bool is_active;
+
+ /*
+ * When called from stop_machine_from_inactive_cpu(), irq might
+ * already be disabled. Save the state and restore it on exit.
+ */
+ local_save_flags(flags);
+
+ if (!smdata->active_cpus)
+ is_active = cpu == cpumask_first(cpu_online_mask);
+ else
+ is_active = cpumask_test_cpu(cpu, smdata->active_cpus);
- if (!active_cpus) {
- if (cpu == cpumask_first(cpu_online_mask))
- smdata = &active;
- } else {
- if (cpumask_test_cpu(cpu, active_cpus))
- smdata = &active;
- }
/* Simple state machine */
do {
/* Chill out and ensure we re-read stopmachine_state. */
cpu_relax();
- if (state != curstate) {
- curstate = state;
+ if (smdata->state != curstate) {
+ curstate = smdata->state;
switch (curstate) {
case STOPMACHINE_DISABLE_IRQ:
local_irq_disable();
hard_irq_disable();
break;
case STOPMACHINE_RUN:
- /* On multiple CPUs only a single error code
- * is needed to tell that something failed. */
- err = smdata->fn(smdata->data);
- if (err)
- smdata->fnret = err;
+ if (is_active)
+ err = smdata->fn(smdata->data);
break;
default:
break;
}
- ack_state();
+ ack_state(smdata);
}
} while (curstate != STOPMACHINE_EXIT);
- local_irq_enable();
-}
-
-/* Callback for CPUs which aren't supposed to do anything. */
-static int chill(void *unused)
-{
- return 0;
-}
-
-int stop_machine_create(void)
-{
- mutex_lock(&setup_lock);
- if (refcount)
- goto done;
- stop_machine_wq = create_rt_workqueue("kstop");
- if (!stop_machine_wq)
- goto err_out;
- stop_machine_work = alloc_percpu(struct work_struct);
- if (!stop_machine_work)
- goto err_out;
-done:
- refcount++;
- mutex_unlock(&setup_lock);
- return 0;
-
-err_out:
- if (stop_machine_wq)
- destroy_workqueue(stop_machine_wq);
- mutex_unlock(&setup_lock);
- return -ENOMEM;
+ local_irq_restore(flags);
+ return err;
}
-EXPORT_SYMBOL_GPL(stop_machine_create);
-
-void stop_machine_destroy(void)
-{
- mutex_lock(&setup_lock);
- refcount--;
- if (refcount)
- goto done;
- destroy_workqueue(stop_machine_wq);
- free_percpu(stop_machine_work);
-done:
- mutex_unlock(&setup_lock);
-}
-EXPORT_SYMBOL_GPL(stop_machine_destroy);
int __stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
{
- struct work_struct *sm_work;
- int i, ret;
-
- /* Set up initial state. */
- mutex_lock(&lock);
- num_threads = num_online_cpus();
- active_cpus = cpus;
- active.fn = fn;
- active.data = data;
- active.fnret = 0;
- idle.fn = chill;
- idle.data = NULL;
-
- set_state(STOPMACHINE_PREPARE);
-
- /* Schedule the stop_cpu work on all cpus: hold this CPU so one
- * doesn't hit this CPU until we're ready. */
- get_cpu();
- for_each_online_cpu(i) {
- sm_work = per_cpu_ptr(stop_machine_work, i);
- INIT_WORK(sm_work, stop_cpu);
- queue_work_on(i, stop_machine_wq, sm_work);
+ struct stop_machine_data smdata = { .fn = fn, .data = data,
+ .num_threads = num_online_cpus(),
+ .active_cpus = cpus };
+
+ if (!stop_machine_initialized) {
+ /*
+ * Handle the case where stop_machine() is called
+ * early in boot before stop_machine() has been
+ * initialized.
+ */
+ unsigned long flags;
+ int ret;
+
+ WARN_ON_ONCE(smdata.num_threads != 1);
+
+ local_irq_save(flags);
+ hard_irq_disable();
+ ret = (*fn)(data);
+ local_irq_restore(flags);
+
+ return ret;
}
- /* This will release the thread on our CPU. */
- put_cpu();
- flush_workqueue(stop_machine_wq);
- ret = active.fnret;
- mutex_unlock(&lock);
- return ret;
+
+ /* Set the initial state and stop all online cpus. */
+ set_state(&smdata, STOPMACHINE_PREPARE);
+ return stop_cpus(cpu_online_mask, stop_machine_cpu_stop, &smdata);
}
int stop_machine(int (*fn)(void *), void *data, const struct cpumask *cpus)
{
int ret;
- ret = stop_machine_create();
- if (ret)
- return ret;
/* No CPUs can come up or down during this. */
get_online_cpus();
ret = __stop_machine(fn, data, cpus);
put_online_cpus();
- stop_machine_destroy();
return ret;
}
EXPORT_SYMBOL_GPL(stop_machine);
+
+/**
+ * stop_machine_from_inactive_cpu - stop_machine() from inactive CPU
+ * @fn: the function to run
+ * @data: the data ptr for the @fn()
+ * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
+ *
+ * This is identical to stop_machine() but can be called from a CPU which
+ * is not active. The local CPU is in the process of hotplug (so no other
+ * CPU hotplug can start) and not marked active and doesn't have enough
+ * context to sleep.
+ *
+ * This function provides stop_machine() functionality for such state by
+ * using busy-wait for synchronization and executing @fn directly for local
+ * CPU.
+ *
+ * CONTEXT:
+ * Local CPU is inactive. Temporarily stops all active CPUs.
+ *
+ * RETURNS:
+ * 0 if all executions of @fn returned 0, any non zero return value if any
+ * returned non zero.
+ */
+int stop_machine_from_inactive_cpu(int (*fn)(void *), void *data,
+ const struct cpumask *cpus)
+{
+ struct stop_machine_data smdata = { .fn = fn, .data = data,
+ .active_cpus = cpus };
+ struct cpu_stop_done done;
+ int ret;
+
+ /* Local CPU must be inactive and CPU hotplug in progress. */
+ BUG_ON(cpu_active(raw_smp_processor_id()));
+ smdata.num_threads = num_active_cpus() + 1; /* +1 for local */
+
+ /* No proper task established and can't sleep - busy wait for lock. */
+ while (!mutex_trylock(&stop_cpus_mutex))
+ cpu_relax();
+
+ /* Schedule work on other CPUs and execute directly for local CPU */
+ set_state(&smdata, STOPMACHINE_PREPARE);
+ cpu_stop_init_done(&done, num_active_cpus());
+ queue_stop_cpus_work(cpu_active_mask, stop_machine_cpu_stop, &smdata,
+ &done);
+ ret = stop_machine_cpu_stop(&smdata);
+
+ /* Busy wait for completion. */
+ while (!completion_done(&done.completion))
+ cpu_relax();
+
+ mutex_unlock(&stop_cpus_mutex);
+ return ret ?: done.ret;
+}
+
+#endif /* CONFIG_STOP_MACHINE */