sched: Fix latencytop and sleep profiling vs group scheduling

[linux-2.6/linux-2.6-openrd.git] / kernel / cpu.c

/* CPU control.
 * (C) 2001, 2002, 2003, 2004 Rusty Russell
 *
 * This code is licenced under the GPL.
 */
#include <linux/proc_fs.h>
#include <linux/smp.h>
#include <linux/init.h>
#include <linux/notifier.h>
#include <linux/sched.h>
#include <linux/unistd.h>
#include <linux/cpu.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <linux/stop_machine.h>
#include <linux/mutex.h>

#ifdef CONFIG_SMP
/* Serializes the updates to cpu_online_mask, cpu_present_mask */
static DEFINE_MUTEX(cpu_add_remove_lock);

static __cpuinitdata RAW_NOTIFIER_HEAD(cpu_chain);

/* 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;
} cpu_hotplug = {
        .active_writer = NULL,
        .lock = __MUTEX_INITIALIZER(cpu_hotplug.lock),
        .refcount = 0,
};

#ifdef CONFIG_HOTPLUG_CPU

void get_online_cpus(void)
{
        might_sleep();
        if (cpu_hotplug.active_writer == current)
                return;
        mutex_lock(&cpu_hotplug.lock);
        cpu_hotplug.refcount++;
        mutex_unlock(&cpu_hotplug.lock);

}
EXPORT_SYMBOL_GPL(get_online_cpus);

void put_online_cpus(void)
{
        if (cpu_hotplug.active_writer == current)
                return;
        mutex_lock(&cpu_hotplug.lock);
        if (!--cpu_hotplug.refcount && unlikely(cpu_hotplug.active_writer))
                wake_up_process(cpu_hotplug.active_writer);
        mutex_unlock(&cpu_hotplug.lock);

}
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_mask, cpu_present_mask.
 */
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_hotplug_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)
{
        cpu_hotplug.active_writer = current;

        for (;;) {
                mutex_lock(&cpu_hotplug.lock);
                if (likely(!cpu_hotplug.refcount))
                        break;
                __set_current_state(TASK_UNINTERRUPTIBLE);
                mutex_unlock(&cpu_hotplug.lock);
                schedule();
        }
}

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 __ref register_cpu_notifier(struct notifier_block *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

EXPORT_SYMBOL(register_cpu_notifier);

void __ref unregister_cpu_notifier(struct notifier_block *nb)
{
        cpu_maps_update_begin();
        raw_notifier_chain_unregister(&cpu_chain, nb);
        cpu_maps_update_done();
}
EXPORT_SYMBOL(unregister_cpu_notifier);

static inline void check_for_tasks(int cpu)
{
        struct task_struct *p;

        write_lock_irq(&tasklist_lock);
        for_each_process(p) {
                if (task_cpu(p) == cpu &&
                    (!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 = %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 __ref take_cpu_down(void *_param)
{
        struct take_cpu_down_param *param = _param;
        int err;

        /* Ensure this CPU doesn't handle any more interrupts. */
        err = __cpu_disable();
        if (err < 0)
                return err;

        raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
                                param->hcpu);

        /* Force idle task to run as soon as we yield: it should
           immediately notice cpu is offline and die quickly. */
        sched_idle_next();
        return 0;
}

/* Requires cpu_add_remove_lock to be held */
static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
{
        int err, nr_calls = 0;
        cpumask_var_t old_allowed;
        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,
        };

        if (num_online_cpus() == 1)
                return -EBUSY;

        if (!cpu_online(cpu))
                return -EINVAL;

        if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
                return -ENOMEM;

        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",
                                __func__, cpu);
                err = -EINVAL;
                goto out_release;
        }

        /* Ensure that we are not runnable on dying cpu */
        cpumask_copy(old_allowed, &current->cpus_allowed);
        set_cpus_allowed_ptr(current,
                             cpumask_of(cpumask_any_but(cpu_online_mask, cpu)));

        err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
        if (err) {
                /* CPU didn't die: tell everyone.  Can't complain. */
                if (raw_notifier_call_chain(&cpu_chain, CPU_DOWN_FAILED | mod,
                                            hcpu) == NOTIFY_BAD)
                        BUG();

                goto out_allowed;
        }
        BUG_ON(cpu_online(cpu));

        /* Wait for it to sleep (leaving idle task). */
        while (!idle_cpu(cpu))
                yield();

        /* This actually kills the CPU. */
        __cpu_die(cpu);

        /* CPU is completely dead: tell everyone.  Too late to complain. */
        if (raw_notifier_call_chain(&cpu_chain, CPU_DEAD | mod,
                                    hcpu) == NOTIFY_BAD)
                BUG();

        check_for_tasks(cpu);

out_allowed:
        set_cpus_allowed_ptr(current, old_allowed);
out_release:
        cpu_hotplug_done();
        if (!err) {
                if (raw_notifier_call_chain(&cpu_chain, CPU_POST_DEAD | mod,
                                            hcpu) == NOTIFY_BAD)
                        BUG();
        }
        free_cpumask_var(old_allowed);
        return err;
}

int __ref cpu_down(unsigned int cpu)
{
        int err;

        err = stop_machine_create();
        if (err)
                return err;
        cpu_maps_update_begin();

        if (cpu_hotplug_disabled) {
                err = -EBUSY;
                goto out;
        }

        set_cpu_active(cpu, false);

        /*
         * Make sure the all cpus did the reschedule and are not
         * using stale version of the cpu_active_mask.
         * This is not strictly necessary becuase stop_machine()
         * that we run down the line already provides the required
         * synchronization. But it's really a side effect and we do not
         * want to depend on the innards of the stop_machine here.
         */
        synchronize_sched();

        err = _cpu_down(cpu, 0);

        if (cpu_online(cpu))
                set_cpu_active(cpu, true);

out:
        cpu_maps_update_done();
        stop_machine_destroy();
        return err;
}
EXPORT_SYMBOL(cpu_down);
#endif /*CONFIG_HOTPLUG_CPU*/

/* Requires cpu_add_remove_lock to be held */
static int __cpuinit _cpu_up(unsigned int cpu, int tasks_frozen)
{
        int ret, nr_calls = 0;
        void *hcpu = (void *)(long)cpu;
        unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;

        if (cpu_online(cpu) || !cpu_present(cpu))
                return -EINVAL;

        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",
                                __func__, cpu);
                ret = -EINVAL;
                goto out_notify;
        }

        /* Arch-specific enabling code. */
        ret = __cpu_up(cpu);
        if (ret != 0)
                goto out_notify;
        BUG_ON(!cpu_online(cpu));

        set_cpu_active(cpu, true);

        /* Now call notifier in preparation. */
        raw_notifier_call_chain(&cpu_chain, CPU_ONLINE | mod, hcpu);

out_notify:
        if (ret != 0)
                __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_possible(cpu)) {
                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)
                printk(KERN_ERR "please check additional_cpus= boot "
                                "parameter\n");
#endif
                return -EINVAL;
        }

        cpu_maps_update_begin();

        if (cpu_hotplug_disabled) {
                err = -EBUSY;
                goto out;
        }

        err = _cpu_up(cpu, 0);

out:
        cpu_maps_update_done();
        return err;
}

#ifdef CONFIG_PM_SLEEP_SMP
static cpumask_var_t frozen_cpus;

int disable_nonboot_cpus(void)
{
        int cpu, first_cpu, error;

        error = stop_machine_create();
        if (error)
                return error;
        cpu_maps_update_begin();
        first_cpu = cpumask_first(cpu_online_mask);
        /* 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
         */
        cpumask_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) {
                        cpumask_set_cpu(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();
        stop_machine_destroy();
        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 (cpumask_empty(frozen_cpus))
                goto out;

        printk("Enabling non-boot CPUs ...\n");
        for_each_cpu(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);
        }
        cpumask_clear(frozen_cpus);
out:
        cpu_maps_update_done();
}

static int alloc_frozen_cpus(void)
{
        if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO))
                return -ENOMEM;
        return 0;
}
core_initcall(alloc_frozen_cpus);
#endif /* CONFIG_PM_SLEEP_SMP */

/**
 * notify_cpu_starting(cpu) - call the CPU_STARTING notifiers
 * @cpu: cpu that just started
 *
 * This function calls the cpu_chain notifiers with CPU_STARTING.
 * 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)
{
        unsigned long val = CPU_STARTING;

#ifdef CONFIG_PM_SLEEP_SMP
        if (frozen_cpus != NULL && cpumask_test_cpu(cpu, frozen_cpus))
                val = CPU_STARTING_FROZEN;
#endif /* CONFIG_PM_SLEEP_SMP */
        raw_notifier_call_chain(&cpu_chain, val, (void *)(long)cpu);
}

#endif /* CONFIG_SMP */

/*
 * cpu_bit_bitmap[] is a special, "compressed" data structure that
 * represents all NR_CPUS bits binary values of 1<<nr.
 *
 * It is used by cpumask_of() to get a constant address to a CPU
 * mask value that has a single bit set only.
 */

/* cpu_bit_bitmap[0] is empty - so we can back into it */
#define MASK_DECLARE_1(x)       [x+1][0] = 1UL << (x)
#define MASK_DECLARE_2(x)       MASK_DECLARE_1(x), MASK_DECLARE_1(x+1)
#define MASK_DECLARE_4(x)       MASK_DECLARE_2(x), MASK_DECLARE_2(x+2)
#define MASK_DECLARE_8(x)       MASK_DECLARE_4(x), MASK_DECLARE_4(x+4)

const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = {

        MASK_DECLARE_8(0),      MASK_DECLARE_8(8),
        MASK_DECLARE_8(16),     MASK_DECLARE_8(24),
#if BITS_PER_LONG > 32
        MASK_DECLARE_8(32),     MASK_DECLARE_8(40),
        MASK_DECLARE_8(48),     MASK_DECLARE_8(56),
#endif
};
EXPORT_SYMBOL_GPL(cpu_bit_bitmap);

const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL;
EXPORT_SYMBOL(cpu_all_bits);

#ifdef CONFIG_INIT_ALL_POSSIBLE
static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly
        = CPU_BITS_ALL;
#else
static DECLARE_BITMAP(cpu_possible_bits, CONFIG_NR_CPUS) __read_mostly;
#endif
const struct cpumask *const cpu_possible_mask = to_cpumask(cpu_possible_bits);
EXPORT_SYMBOL(cpu_possible_mask);

static DECLARE_BITMAP(cpu_online_bits, CONFIG_NR_CPUS) __read_mostly;
const struct cpumask *const cpu_online_mask = to_cpumask(cpu_online_bits);
EXPORT_SYMBOL(cpu_online_mask);

static DECLARE_BITMAP(cpu_present_bits, CONFIG_NR_CPUS) __read_mostly;
const struct cpumask *const cpu_present_mask = to_cpumask(cpu_present_bits);
EXPORT_SYMBOL(cpu_present_mask);

static DECLARE_BITMAP(cpu_active_bits, CONFIG_NR_CPUS) __read_mostly;
const struct cpumask *const cpu_active_mask = to_cpumask(cpu_active_bits);
EXPORT_SYMBOL(cpu_active_mask);

void set_cpu_possible(unsigned int cpu, bool possible)
{
        if (possible)
                cpumask_set_cpu(cpu, to_cpumask(cpu_possible_bits));
        else
                cpumask_clear_cpu(cpu, to_cpumask(cpu_possible_bits));
}

void set_cpu_present(unsigned int cpu, bool present)
{
        if (present)
                cpumask_set_cpu(cpu, to_cpumask(cpu_present_bits));
        else
                cpumask_clear_cpu(cpu, to_cpumask(cpu_present_bits));
}

void set_cpu_online(unsigned int cpu, bool online)
{
        if (online)
                cpumask_set_cpu(cpu, to_cpumask(cpu_online_bits));
        else
                cpumask_clear_cpu(cpu, to_cpumask(cpu_online_bits));
}

void set_cpu_active(unsigned int cpu, bool active)
{
        if (active)
                cpumask_set_cpu(cpu, to_cpumask(cpu_active_bits));
        else
                cpumask_clear_cpu(cpu, to_cpumask(cpu_active_bits));
}

void init_cpu_present(const struct cpumask *src)
{
        cpumask_copy(to_cpumask(cpu_present_bits), src);
}

void init_cpu_possible(const struct cpumask *src)
{
        cpumask_copy(to_cpumask(cpu_possible_bits), src);
}

void init_cpu_online(const struct cpumask *src)
{
        cpumask_copy(to_cpumask(cpu_online_bits), src);
}