genirq: Introduce IRQD_AFFINITY_MANAGED flag

[cascardo/linux.git] / kernel / irq / manage.c

/*
 * linux/kernel/irq/manage.c
 *
 * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
 * Copyright (C) 2005-2006 Thomas Gleixner
 *
 * This file contains driver APIs to the irq subsystem.
 */

#define pr_fmt(fmt) "genirq: " fmt

#include <linux/irq.h>
#include <linux/kthread.h>
#include <linux/module.h>
#include <linux/random.h>
#include <linux/interrupt.h>
#include <linux/slab.h>
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/task_work.h>

#include "internals.h"

#ifdef CONFIG_IRQ_FORCED_THREADING
__read_mostly bool force_irqthreads;

static int __init setup_forced_irqthreads(char *arg)
{
        force_irqthreads = true;
        return 0;
}
early_param("threadirqs", setup_forced_irqthreads);
#endif

static void __synchronize_hardirq(struct irq_desc *desc)
{
        bool inprogress;

        do {
                unsigned long flags;

                /*
                 * Wait until we're out of the critical section.  This might
                 * give the wrong answer due to the lack of memory barriers.
                 */
                while (irqd_irq_inprogress(&desc->irq_data))
                        cpu_relax();

                /* Ok, that indicated we're done: double-check carefully. */
                raw_spin_lock_irqsave(&desc->lock, flags);
                inprogress = irqd_irq_inprogress(&desc->irq_data);
                raw_spin_unlock_irqrestore(&desc->lock, flags);

                /* Oops, that failed? */
        } while (inprogress);
}

/**
 *      synchronize_hardirq - wait for pending hard IRQ handlers (on other CPUs)
 *      @irq: interrupt number to wait for
 *
 *      This function waits for any pending hard IRQ handlers for this
 *      interrupt to complete before returning. If you use this
 *      function while holding a resource the IRQ handler may need you
 *      will deadlock. It does not take associated threaded handlers
 *      into account.
 *
 *      Do not use this for shutdown scenarios where you must be sure
 *      that all parts (hardirq and threaded handler) have completed.
 *
 *      Returns: false if a threaded handler is active.
 *
 *      This function may be called - with care - from IRQ context.
 */
bool synchronize_hardirq(unsigned int irq)
{
        struct irq_desc *desc = irq_to_desc(irq);

        if (desc) {
                __synchronize_hardirq(desc);
                return !atomic_read(&desc->threads_active);
        }

        return true;
}
EXPORT_SYMBOL(synchronize_hardirq);

/**
 *      synchronize_irq - wait for pending IRQ handlers (on other CPUs)
 *      @irq: interrupt number to wait for
 *
 *      This function waits for any pending IRQ handlers for this interrupt
 *      to complete before returning. If you use this function while
 *      holding a resource the IRQ handler may need you will deadlock.
 *
 *      This function may be called - with care - from IRQ context.
 */
void synchronize_irq(unsigned int irq)
{
        struct irq_desc *desc = irq_to_desc(irq);

        if (desc) {
                __synchronize_hardirq(desc);
                /*
                 * We made sure that no hardirq handler is
                 * running. Now verify that no threaded handlers are
                 * active.
                 */
                wait_event(desc->wait_for_threads,
                           !atomic_read(&desc->threads_active));
        }
}
EXPORT_SYMBOL(synchronize_irq);

#ifdef CONFIG_SMP
cpumask_var_t irq_default_affinity;

static bool __irq_can_set_affinity(struct irq_desc *desc)
{
        if (!desc || !irqd_can_balance(&desc->irq_data) ||
            !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
                return false;
        return true;
}

/**
 *      irq_can_set_affinity - Check if the affinity of a given irq can be set
 *      @irq:           Interrupt to check
 *
 */
int irq_can_set_affinity(unsigned int irq)
{
        return __irq_can_set_affinity(irq_to_desc(irq));
}

/**
 * irq_can_set_affinity_usr - Check if affinity of a irq can be set from user space
 * @irq:        Interrupt to check
 *
 * Like irq_can_set_affinity() above, but additionally checks for the
 * AFFINITY_MANAGED flag.
 */
bool irq_can_set_affinity_usr(unsigned int irq)
{
        struct irq_desc *desc = irq_to_desc(irq);

        return __irq_can_set_affinity(desc) &&
                !irqd_affinity_is_managed(&desc->irq_data);
}

/**
 *      irq_set_thread_affinity - Notify irq threads to adjust affinity
 *      @desc:          irq descriptor which has affitnity changed
 *
 *      We just set IRQTF_AFFINITY and delegate the affinity setting
 *      to the interrupt thread itself. We can not call
 *      set_cpus_allowed_ptr() here as we hold desc->lock and this
 *      code can be called from hard interrupt context.
 */
void irq_set_thread_affinity(struct irq_desc *desc)
{
        struct irqaction *action;

        for_each_action_of_desc(desc, action)
                if (action->thread)
                        set_bit(IRQTF_AFFINITY, &action->thread_flags);
}

#ifdef CONFIG_GENERIC_PENDING_IRQ
static inline bool irq_can_move_pcntxt(struct irq_data *data)
{
        return irqd_can_move_in_process_context(data);
}
static inline bool irq_move_pending(struct irq_data *data)
{
        return irqd_is_setaffinity_pending(data);
}
static inline void
irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
{
        cpumask_copy(desc->pending_mask, mask);
}
static inline void
irq_get_pending(struct cpumask *mask, struct irq_desc *desc)
{
        cpumask_copy(mask, desc->pending_mask);
}
#else
static inline bool irq_can_move_pcntxt(struct irq_data *data) { return true; }
static inline bool irq_move_pending(struct irq_data *data) { return false; }
static inline void
irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask) { }
static inline void
irq_get_pending(struct cpumask *mask, struct irq_desc *desc) { }
#endif

int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
                        bool force)
{
        struct irq_desc *desc = irq_data_to_desc(data);
        struct irq_chip *chip = irq_data_get_irq_chip(data);
        int ret;

        ret = chip->irq_set_affinity(data, mask, force);
        switch (ret) {
        case IRQ_SET_MASK_OK:
        case IRQ_SET_MASK_OK_DONE:
                cpumask_copy(desc->irq_common_data.affinity, mask);
        case IRQ_SET_MASK_OK_NOCOPY:
                irq_set_thread_affinity(desc);
                ret = 0;
        }

        return ret;
}

int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
                            bool force)
{
        struct irq_chip *chip = irq_data_get_irq_chip(data);
        struct irq_desc *desc = irq_data_to_desc(data);
        int ret = 0;

        if (!chip || !chip->irq_set_affinity)
                return -EINVAL;

        if (irq_can_move_pcntxt(data)) {
                ret = irq_do_set_affinity(data, mask, force);
        } else {
                irqd_set_move_pending(data);
                irq_copy_pending(desc, mask);
        }

        if (desc->affinity_notify) {
                kref_get(&desc->affinity_notify->kref);
                schedule_work(&desc->affinity_notify->work);
        }
        irqd_set(data, IRQD_AFFINITY_SET);

        return ret;
}

int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
{
        struct irq_desc *desc = irq_to_desc(irq);
        unsigned long flags;
        int ret;

        if (!desc)
                return -EINVAL;

        raw_spin_lock_irqsave(&desc->lock, flags);
        ret = irq_set_affinity_locked(irq_desc_get_irq_data(desc), mask, force);
        raw_spin_unlock_irqrestore(&desc->lock, flags);
        return ret;
}

int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m)
{
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);

        if (!desc)
                return -EINVAL;
        desc->affinity_hint = m;
        irq_put_desc_unlock(desc, flags);
        /* set the initial affinity to prevent every interrupt being on CPU0 */
        if (m)
                __irq_set_affinity(irq, m, false);
        return 0;
}
EXPORT_SYMBOL_GPL(irq_set_affinity_hint);

static void irq_affinity_notify(struct work_struct *work)
{
        struct irq_affinity_notify *notify =
                container_of(work, struct irq_affinity_notify, work);
        struct irq_desc *desc = irq_to_desc(notify->irq);
        cpumask_var_t cpumask;
        unsigned long flags;

        if (!desc || !alloc_cpumask_var(&cpumask, GFP_KERNEL))
                goto out;

        raw_spin_lock_irqsave(&desc->lock, flags);
        if (irq_move_pending(&desc->irq_data))
                irq_get_pending(cpumask, desc);
        else
                cpumask_copy(cpumask, desc->irq_common_data.affinity);
        raw_spin_unlock_irqrestore(&desc->lock, flags);

        notify->notify(notify, cpumask);

        free_cpumask_var(cpumask);
out:
        kref_put(&notify->kref, notify->release);
}

/**
 *      irq_set_affinity_notifier - control notification of IRQ affinity changes
 *      @irq:           Interrupt for which to enable/disable notification
 *      @notify:        Context for notification, or %NULL to disable
 *                      notification.  Function pointers must be initialised;
 *                      the other fields will be initialised by this function.
 *
 *      Must be called in process context.  Notification may only be enabled
 *      after the IRQ is allocated and must be disabled before the IRQ is
 *      freed using free_irq().
 */
int
irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
{
        struct irq_desc *desc = irq_to_desc(irq);
        struct irq_affinity_notify *old_notify;
        unsigned long flags;

        /* The release function is promised process context */
        might_sleep();

        if (!desc)
                return -EINVAL;

        /* Complete initialisation of *notify */
        if (notify) {
                notify->irq = irq;
                kref_init(&notify->kref);
                INIT_WORK(&notify->work, irq_affinity_notify);
        }

        raw_spin_lock_irqsave(&desc->lock, flags);
        old_notify = desc->affinity_notify;
        desc->affinity_notify = notify;
        raw_spin_unlock_irqrestore(&desc->lock, flags);

        if (old_notify)
                kref_put(&old_notify->kref, old_notify->release);

        return 0;
}
EXPORT_SYMBOL_GPL(irq_set_affinity_notifier);

#ifndef CONFIG_AUTO_IRQ_AFFINITY
/*
 * Generic version of the affinity autoselector.
 */
static int setup_affinity(struct irq_desc *desc, struct cpumask *mask)
{
        struct cpumask *set = irq_default_affinity;
        int node = irq_desc_get_node(desc);

        /* Excludes PER_CPU and NO_BALANCE interrupts */
        if (!__irq_can_set_affinity(desc))
                return 0;

        /*
         * Preserve an userspace affinity setup, but make sure that
         * one of the targets is online.
         */
        if (irqd_has_set(&desc->irq_data, IRQD_AFFINITY_SET)) {
                if (cpumask_intersects(desc->irq_common_data.affinity,
                                       cpu_online_mask))
                        set = desc->irq_common_data.affinity;
                else
                        irqd_clear(&desc->irq_data, IRQD_AFFINITY_SET);
        }

        cpumask_and(mask, cpu_online_mask, set);
        if (node != NUMA_NO_NODE) {
                const struct cpumask *nodemask = cpumask_of_node(node);

                /* make sure at least one of the cpus in nodemask is online */
                if (cpumask_intersects(mask, nodemask))
                        cpumask_and(mask, mask, nodemask);
        }
        irq_do_set_affinity(&desc->irq_data, mask, false);
        return 0;
}
#else
/* Wrapper for ALPHA specific affinity selector magic */
static inline int setup_affinity(struct irq_desc *d, struct cpumask *mask)
{
        return irq_select_affinity(irq_desc_get_irq(d));
}
#endif

/*
 * Called when affinity is set via /proc/irq
 */
int irq_select_affinity_usr(unsigned int irq, struct cpumask *mask)
{
        struct irq_desc *desc = irq_to_desc(irq);
        unsigned long flags;
        int ret;

        raw_spin_lock_irqsave(&desc->lock, flags);
        ret = setup_affinity(desc, mask);
        raw_spin_unlock_irqrestore(&desc->lock, flags);
        return ret;
}

#else
static inline int
setup_affinity(struct irq_desc *desc, struct cpumask *mask)
{
        return 0;
}
#endif

/**
 *      irq_set_vcpu_affinity - Set vcpu affinity for the interrupt
 *      @irq: interrupt number to set affinity
 *      @vcpu_info: vCPU specific data
 *
 *      This function uses the vCPU specific data to set the vCPU
 *      affinity for an irq. The vCPU specific data is passed from
 *      outside, such as KVM. One example code path is as below:
 *      KVM -> IOMMU -> irq_set_vcpu_affinity().
 */
int irq_set_vcpu_affinity(unsigned int irq, void *vcpu_info)
{
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
        struct irq_data *data;
        struct irq_chip *chip;
        int ret = -ENOSYS;

        if (!desc)
                return -EINVAL;

        data = irq_desc_get_irq_data(desc);
        chip = irq_data_get_irq_chip(data);
        if (chip && chip->irq_set_vcpu_affinity)
                ret = chip->irq_set_vcpu_affinity(data, vcpu_info);
        irq_put_desc_unlock(desc, flags);

        return ret;
}
EXPORT_SYMBOL_GPL(irq_set_vcpu_affinity);

void __disable_irq(struct irq_desc *desc)
{
        if (!desc->depth++)
                irq_disable(desc);
}

static int __disable_irq_nosync(unsigned int irq)
{
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);

        if (!desc)
                return -EINVAL;
        __disable_irq(desc);
        irq_put_desc_busunlock(desc, flags);
        return 0;
}

/**
 *      disable_irq_nosync - disable an irq without waiting
 *      @irq: Interrupt to disable
 *
 *      Disable the selected interrupt line.  Disables and Enables are
 *      nested.
 *      Unlike disable_irq(), this function does not ensure existing
 *      instances of the IRQ handler have completed before returning.
 *
 *      This function may be called from IRQ context.
 */
void disable_irq_nosync(unsigned int irq)
{
        __disable_irq_nosync(irq);
}
EXPORT_SYMBOL(disable_irq_nosync);

/**
 *      disable_irq - disable an irq and wait for completion
 *      @irq: Interrupt to disable
 *
 *      Disable the selected interrupt line.  Enables and Disables are
 *      nested.
 *      This function waits for any pending IRQ handlers for this interrupt
 *      to complete before returning. If you use this function while
 *      holding a resource the IRQ handler may need you will deadlock.
 *
 *      This function may be called - with care - from IRQ context.
 */
void disable_irq(unsigned int irq)
{
        if (!__disable_irq_nosync(irq))
                synchronize_irq(irq);
}
EXPORT_SYMBOL(disable_irq);

/**
 *      disable_hardirq - disables an irq and waits for hardirq completion
 *      @irq: Interrupt to disable
 *
 *      Disable the selected interrupt line.  Enables and Disables are
 *      nested.
 *      This function waits for any pending hard IRQ handlers for this
 *      interrupt to complete before returning. If you use this function while
 *      holding a resource the hard IRQ handler may need you will deadlock.
 *
 *      When used to optimistically disable an interrupt from atomic context
 *      the return value must be checked.
 *
 *      Returns: false if a threaded handler is active.
 *
 *      This function may be called - with care - from IRQ context.
 */
bool disable_hardirq(unsigned int irq)
{
        if (!__disable_irq_nosync(irq))
                return synchronize_hardirq(irq);

        return false;
}
EXPORT_SYMBOL_GPL(disable_hardirq);

void __enable_irq(struct irq_desc *desc)
{
        switch (desc->depth) {
        case 0:
 err_out:
                WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n",
                     irq_desc_get_irq(desc));
                break;
        case 1: {
                if (desc->istate & IRQS_SUSPENDED)
                        goto err_out;
                /* Prevent probing on this irq: */
                irq_settings_set_noprobe(desc);
                irq_enable(desc);
                check_irq_resend(desc);
                /* fall-through */
        }
        default:
                desc->depth--;
        }
}

/**
 *      enable_irq - enable handling of an irq
 *      @irq: Interrupt to enable
 *
 *      Undoes the effect of one call to disable_irq().  If this
 *      matches the last disable, processing of interrupts on this
 *      IRQ line is re-enabled.
 *
 *      This function may be called from IRQ context only when
 *      desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
 */
void enable_irq(unsigned int irq)
{
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);

        if (!desc)
                return;
        if (WARN(!desc->irq_data.chip,
                 KERN_ERR "enable_irq before setup/request_irq: irq %u\n", irq))
                goto out;

        __enable_irq(desc);
out:
        irq_put_desc_busunlock(desc, flags);
}
EXPORT_SYMBOL(enable_irq);

static int set_irq_wake_real(unsigned int irq, unsigned int on)
{
        struct irq_desc *desc = irq_to_desc(irq);
        int ret = -ENXIO;

        if (irq_desc_get_chip(desc)->flags &  IRQCHIP_SKIP_SET_WAKE)
                return 0;

        if (desc->irq_data.chip->irq_set_wake)
                ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);

        return ret;
}

/**
 *      irq_set_irq_wake - control irq power management wakeup
 *      @irq:   interrupt to control
 *      @on:    enable/disable power management wakeup
 *
 *      Enable/disable power management wakeup mode, which is
 *      disabled by default.  Enables and disables must match,
 *      just as they match for non-wakeup mode support.
 *
 *      Wakeup mode lets this IRQ wake the system from sleep
 *      states like "suspend to RAM".
 */
int irq_set_irq_wake(unsigned int irq, unsigned int on)
{
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
        int ret = 0;

        if (!desc)
                return -EINVAL;

        /* wakeup-capable irqs can be shared between drivers that
         * don't need to have the same sleep mode behaviors.
         */
        if (on) {
                if (desc->wake_depth++ == 0) {
                        ret = set_irq_wake_real(irq, on);
                        if (ret)
                                desc->wake_depth = 0;
                        else
                                irqd_set(&desc->irq_data, IRQD_WAKEUP_STATE);
                }
        } else {
                if (desc->wake_depth == 0) {
                        WARN(1, "Unbalanced IRQ %d wake disable\n", irq);
                } else if (--desc->wake_depth == 0) {
                        ret = set_irq_wake_real(irq, on);
                        if (ret)
                                desc->wake_depth = 1;
                        else
                                irqd_clear(&desc->irq_data, IRQD_WAKEUP_STATE);
                }
        }
        irq_put_desc_busunlock(desc, flags);
        return ret;
}
EXPORT_SYMBOL(irq_set_irq_wake);

/*
 * Internal function that tells the architecture code whether a
 * particular irq has been exclusively allocated or is available
 * for driver use.
 */
int can_request_irq(unsigned int irq, unsigned long irqflags)
{
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);
        int canrequest = 0;

        if (!desc)
                return 0;

        if (irq_settings_can_request(desc)) {
                if (!desc->action ||
                    irqflags & desc->action->flags & IRQF_SHARED)
                        canrequest = 1;
        }
        irq_put_desc_unlock(desc, flags);
        return canrequest;
}

int __irq_set_trigger(struct irq_desc *desc, unsigned long flags)
{
        struct irq_chip *chip = desc->irq_data.chip;
        int ret, unmask = 0;

        if (!chip || !chip->irq_set_type) {
                /*
                 * IRQF_TRIGGER_* but the PIC does not support multiple
                 * flow-types?
                 */
                pr_debug("No set_type function for IRQ %d (%s)\n",
                         irq_desc_get_irq(desc),
                         chip ? (chip->name ? : "unknown") : "unknown");
                return 0;
        }

        flags &= IRQ_TYPE_SENSE_MASK;

        if (chip->flags & IRQCHIP_SET_TYPE_MASKED) {
                if (!irqd_irq_masked(&desc->irq_data))
                        mask_irq(desc);
                if (!irqd_irq_disabled(&desc->irq_data))
                        unmask = 1;
        }

        /* caller masked out all except trigger mode flags */
        ret = chip->irq_set_type(&desc->irq_data, flags);

        switch (ret) {
        case IRQ_SET_MASK_OK:
        case IRQ_SET_MASK_OK_DONE:
                irqd_clear(&desc->irq_data, IRQD_TRIGGER_MASK);
                irqd_set(&desc->irq_data, flags);

        case IRQ_SET_MASK_OK_NOCOPY:
                flags = irqd_get_trigger_type(&desc->irq_data);
                irq_settings_set_trigger_mask(desc, flags);
                irqd_clear(&desc->irq_data, IRQD_LEVEL);
                irq_settings_clr_level(desc);
                if (flags & IRQ_TYPE_LEVEL_MASK) {
                        irq_settings_set_level(desc);
                        irqd_set(&desc->irq_data, IRQD_LEVEL);
                }

                ret = 0;
                break;
        default:
                pr_err("Setting trigger mode %lu for irq %u failed (%pF)\n",
                       flags, irq_desc_get_irq(desc), chip->irq_set_type);
        }
        if (unmask)
                unmask_irq(desc);
        return ret;
}

#ifdef CONFIG_HARDIRQS_SW_RESEND
int irq_set_parent(int irq, int parent_irq)
{
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, 0);

        if (!desc)
                return -EINVAL;

        desc->parent_irq = parent_irq;

        irq_put_desc_unlock(desc, flags);
        return 0;
}
#endif

/*
 * Default primary interrupt handler for threaded interrupts. Is
 * assigned as primary handler when request_threaded_irq is called
 * with handler == NULL. Useful for oneshot interrupts.
 */
static irqreturn_t irq_default_primary_handler(int irq, void *dev_id)
{
        return IRQ_WAKE_THREAD;
}

/*
 * Primary handler for nested threaded interrupts. Should never be
 * called.
 */
static irqreturn_t irq_nested_primary_handler(int irq, void *dev_id)
{
        WARN(1, "Primary handler called for nested irq %d\n", irq);
        return IRQ_NONE;
}

static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
{
        WARN(1, "Secondary action handler called for irq %d\n", irq);
        return IRQ_NONE;
}

static int irq_wait_for_interrupt(struct irqaction *action)
{
        set_current_state(TASK_INTERRUPTIBLE);

        while (!kthread_should_stop()) {

                if (test_and_clear_bit(IRQTF_RUNTHREAD,
                                       &action->thread_flags)) {
                        __set_current_state(TASK_RUNNING);
                        return 0;
                }
                schedule();
                set_current_state(TASK_INTERRUPTIBLE);
        }
        __set_current_state(TASK_RUNNING);
        return -1;
}

/*
 * Oneshot interrupts keep the irq line masked until the threaded
 * handler finished. unmask if the interrupt has not been disabled and
 * is marked MASKED.
 */
static void irq_finalize_oneshot(struct irq_desc *desc,
                                 struct irqaction *action)
{
        if (!(desc->istate & IRQS_ONESHOT) ||
            action->handler == irq_forced_secondary_handler)
                return;
again:
        chip_bus_lock(desc);
        raw_spin_lock_irq(&desc->lock);

        /*
         * Implausible though it may be we need to protect us against
         * the following scenario:
         *
         * The thread is faster done than the hard interrupt handler
         * on the other CPU. If we unmask the irq line then the
         * interrupt can come in again and masks the line, leaves due
         * to IRQS_INPROGRESS and the irq line is masked forever.
         *
         * This also serializes the state of shared oneshot handlers
         * versus "desc->threads_onehsot |= action->thread_mask;" in
         * irq_wake_thread(). See the comment there which explains the
         * serialization.
         */
        if (unlikely(irqd_irq_inprogress(&desc->irq_data))) {
                raw_spin_unlock_irq(&desc->lock);
                chip_bus_sync_unlock(desc);
                cpu_relax();
                goto again;
        }

        /*
         * Now check again, whether the thread should run. Otherwise
         * we would clear the threads_oneshot bit of this thread which
         * was just set.
         */
        if (test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
                goto out_unlock;

        desc->threads_oneshot &= ~action->thread_mask;

        if (!desc->threads_oneshot && !irqd_irq_disabled(&desc->irq_data) &&
            irqd_irq_masked(&desc->irq_data))
                unmask_threaded_irq(desc);

out_unlock:
        raw_spin_unlock_irq(&desc->lock);
        chip_bus_sync_unlock(desc);
}

#ifdef CONFIG_SMP
/*
 * Check whether we need to change the affinity of the interrupt thread.
 */
static void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
{
        cpumask_var_t mask;
        bool valid = true;

        if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
                return;

        /*
         * In case we are out of memory we set IRQTF_AFFINITY again and
         * try again next time
         */
        if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
                set_bit(IRQTF_AFFINITY, &action->thread_flags);
                return;
        }

        raw_spin_lock_irq(&desc->lock);
        /*
         * This code is triggered unconditionally. Check the affinity
         * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
         */
        if (desc->irq_common_data.affinity)
                cpumask_copy(mask, desc->irq_common_data.affinity);
        else
                valid = false;
        raw_spin_unlock_irq(&desc->lock);

        if (valid)
                set_cpus_allowed_ptr(current, mask);
        free_cpumask_var(mask);
}
#else
static inline void
irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action) { }
#endif

/*
 * Interrupts which are not explicitely requested as threaded
 * interrupts rely on the implicit bh/preempt disable of the hard irq
 * context. So we need to disable bh here to avoid deadlocks and other
 * side effects.
 */
static irqreturn_t
irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
{
        irqreturn_t ret;

        local_bh_disable();
        ret = action->thread_fn(action->irq, action->dev_id);
        irq_finalize_oneshot(desc, action);
        local_bh_enable();
        return ret;
}

/*
 * Interrupts explicitly requested as threaded interrupts want to be
 * preemtible - many of them need to sleep and wait for slow busses to
 * complete.
 */
static irqreturn_t irq_thread_fn(struct irq_desc *desc,
                struct irqaction *action)
{
        irqreturn_t ret;

        ret = action->thread_fn(action->irq, action->dev_id);
        irq_finalize_oneshot(desc, action);
        return ret;
}

static void wake_threads_waitq(struct irq_desc *desc)
{
        if (atomic_dec_and_test(&desc->threads_active))
                wake_up(&desc->wait_for_threads);
}

static void irq_thread_dtor(struct callback_head *unused)
{
        struct task_struct *tsk = current;
        struct irq_desc *desc;
        struct irqaction *action;

        if (WARN_ON_ONCE(!(current->flags & PF_EXITING)))
                return;

        action = kthread_data(tsk);

        pr_err("exiting task \"%s\" (%d) is an active IRQ thread (irq %d)\n",
               tsk->comm, tsk->pid, action->irq);


        desc = irq_to_desc(action->irq);
        /*
         * If IRQTF_RUNTHREAD is set, we need to decrement
         * desc->threads_active and wake possible waiters.
         */
        if (test_and_clear_bit(IRQTF_RUNTHREAD, &action->thread_flags))
                wake_threads_waitq(desc);

        /* Prevent a stale desc->threads_oneshot */
        irq_finalize_oneshot(desc, action);
}

static void irq_wake_secondary(struct irq_desc *desc, struct irqaction *action)
{
        struct irqaction *secondary = action->secondary;

        if (WARN_ON_ONCE(!secondary))
                return;

        raw_spin_lock_irq(&desc->lock);
        __irq_wake_thread(desc, secondary);
        raw_spin_unlock_irq(&desc->lock);
}

/*
 * Interrupt handler thread
 */
static int irq_thread(void *data)
{
        struct callback_head on_exit_work;
        struct irqaction *action = data;
        struct irq_desc *desc = irq_to_desc(action->irq);
        irqreturn_t (*handler_fn)(struct irq_desc *desc,
                        struct irqaction *action);

        if (force_irqthreads && test_bit(IRQTF_FORCED_THREAD,
                                        &action->thread_flags))
                handler_fn = irq_forced_thread_fn;
        else
                handler_fn = irq_thread_fn;

        init_task_work(&on_exit_work, irq_thread_dtor);
        task_work_add(current, &on_exit_work, false);

        irq_thread_check_affinity(desc, action);

        while (!irq_wait_for_interrupt(action)) {
                irqreturn_t action_ret;

                irq_thread_check_affinity(desc, action);

                action_ret = handler_fn(desc, action);
                if (action_ret == IRQ_HANDLED)
                        atomic_inc(&desc->threads_handled);
                if (action_ret == IRQ_WAKE_THREAD)
                        irq_wake_secondary(desc, action);

                wake_threads_waitq(desc);
        }

        /*
         * This is the regular exit path. __free_irq() is stopping the
         * thread via kthread_stop() after calling
         * synchronize_irq(). So neither IRQTF_RUNTHREAD nor the
         * oneshot mask bit can be set. We cannot verify that as we
         * cannot touch the oneshot mask at this point anymore as
         * __setup_irq() might have given out currents thread_mask
         * again.
         */
        task_work_cancel(current, irq_thread_dtor);
        return 0;
}

/**
 *      irq_wake_thread - wake the irq thread for the action identified by dev_id
 *      @irq:           Interrupt line
 *      @dev_id:        Device identity for which the thread should be woken
 *
 */
void irq_wake_thread(unsigned int irq, void *dev_id)
{
        struct irq_desc *desc = irq_to_desc(irq);
        struct irqaction *action;
        unsigned long flags;

        if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
                return;

        raw_spin_lock_irqsave(&desc->lock, flags);
        for_each_action_of_desc(desc, action) {
                if (action->dev_id == dev_id) {
                        if (action->thread)
                                __irq_wake_thread(desc, action);
                        break;
                }
        }
        raw_spin_unlock_irqrestore(&desc->lock, flags);
}
EXPORT_SYMBOL_GPL(irq_wake_thread);

static int irq_setup_forced_threading(struct irqaction *new)
{
        if (!force_irqthreads)
                return 0;
        if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
                return 0;

        new->flags |= IRQF_ONESHOT;

        /*
         * Handle the case where we have a real primary handler and a
         * thread handler. We force thread them as well by creating a
         * secondary action.
         */
        if (new->handler != irq_default_primary_handler && new->thread_fn) {
                /* Allocate the secondary action */
                new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
                if (!new->secondary)
                        return -ENOMEM;
                new->secondary->handler = irq_forced_secondary_handler;
                new->secondary->thread_fn = new->thread_fn;
                new->secondary->dev_id = new->dev_id;
                new->secondary->irq = new->irq;
                new->secondary->name = new->name;
        }
        /* Deal with the primary handler */
        set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
        new->thread_fn = new->handler;
        new->handler = irq_default_primary_handler;
        return 0;
}

static int irq_request_resources(struct irq_desc *desc)
{
        struct irq_data *d = &desc->irq_data;
        struct irq_chip *c = d->chip;

        return c->irq_request_resources ? c->irq_request_resources(d) : 0;
}

static void irq_release_resources(struct irq_desc *desc)
{
        struct irq_data *d = &desc->irq_data;
        struct irq_chip *c = d->chip;

        if (c->irq_release_resources)
                c->irq_release_resources(d);
}

static int
setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
{
        struct task_struct *t;
        struct sched_param param = {
                .sched_priority = MAX_USER_RT_PRIO/2,
        };

        if (!secondary) {
                t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
                                   new->name);
        } else {
                t = kthread_create(irq_thread, new, "irq/%d-s-%s", irq,
                                   new->name);
                param.sched_priority -= 1;
        }

        if (IS_ERR(t))
                return PTR_ERR(t);

        sched_setscheduler_nocheck(t, SCHED_FIFO, &param);

        /*
         * We keep the reference to the task struct even if
         * the thread dies to avoid that the interrupt code
         * references an already freed task_struct.
         */
        get_task_struct(t);
        new->thread = t;
        /*
         * Tell the thread to set its affinity. This is
         * important for shared interrupt handlers as we do
         * not invoke setup_affinity() for the secondary
         * handlers as everything is already set up. Even for
         * interrupts marked with IRQF_NO_BALANCE this is
         * correct as we want the thread to move to the cpu(s)
         * on which the requesting code placed the interrupt.
         */
        set_bit(IRQTF_AFFINITY, &new->thread_flags);
        return 0;
}

/*
 * Internal function to register an irqaction - typically used to
 * allocate special interrupts that are part of the architecture.
 */
static int
__setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
{
        struct irqaction *old, **old_ptr;
        unsigned long flags, thread_mask = 0;
        int ret, nested, shared = 0;
        cpumask_var_t mask;

        if (!desc)
                return -EINVAL;

        if (desc->irq_data.chip == &no_irq_chip)
                return -ENOSYS;
        if (!try_module_get(desc->owner))
                return -ENODEV;

        new->irq = irq;

        /*
         * Check whether the interrupt nests into another interrupt
         * thread.
         */
        nested = irq_settings_is_nested_thread(desc);
        if (nested) {
                if (!new->thread_fn) {
                        ret = -EINVAL;
                        goto out_mput;
                }
                /*
                 * Replace the primary handler which was provided from
                 * the driver for non nested interrupt handling by the
                 * dummy function which warns when called.
                 */
                new->handler = irq_nested_primary_handler;
        } else {
                if (irq_settings_can_thread(desc)) {
                        ret = irq_setup_forced_threading(new);
                        if (ret)
                                goto out_mput;
                }
        }

        /*
         * Create a handler thread when a thread function is supplied
         * and the interrupt does not nest into another interrupt
         * thread.
         */
        if (new->thread_fn && !nested) {
                ret = setup_irq_thread(new, irq, false);
                if (ret)
                        goto out_mput;
                if (new->secondary) {
                        ret = setup_irq_thread(new->secondary, irq, true);
                        if (ret)
                                goto out_thread;
                }
        }

        if (!alloc_cpumask_var(&mask, GFP_KERNEL)) {
                ret = -ENOMEM;
                goto out_thread;
        }

        /*
         * Drivers are often written to work w/o knowledge about the
         * underlying irq chip implementation, so a request for a
         * threaded irq without a primary hard irq context handler
         * requires the ONESHOT flag to be set. Some irq chips like
         * MSI based interrupts are per se one shot safe. Check the
         * chip flags, so we can avoid the unmask dance at the end of
         * the threaded handler for those.
         */
        if (desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)
                new->flags &= ~IRQF_ONESHOT;

        /*
         * The following block of code has to be executed atomically
         */
        raw_spin_lock_irqsave(&desc->lock, flags);
        old_ptr = &desc->action;
        old = *old_ptr;
        if (old) {
                /*
                 * Can't share interrupts unless both agree to and are
                 * the same type (level, edge, polarity). So both flag
                 * fields must have IRQF_SHARED set and the bits which
                 * set the trigger type must match. Also all must
                 * agree on ONESHOT.
                 */
                if (!((old->flags & new->flags) & IRQF_SHARED) ||
                    ((old->flags ^ new->flags) & IRQF_TRIGGER_MASK) ||
                    ((old->flags ^ new->flags) & IRQF_ONESHOT))
                        goto mismatch;

                /* All handlers must agree on per-cpuness */
                if ((old->flags & IRQF_PERCPU) !=
                    (new->flags & IRQF_PERCPU))
                        goto mismatch;

                /* add new interrupt at end of irq queue */
                do {
                        /*
                         * Or all existing action->thread_mask bits,
                         * so we can find the next zero bit for this
                         * new action.
                         */
                        thread_mask |= old->thread_mask;
                        old_ptr = &old->next;
                        old = *old_ptr;
                } while (old);
                shared = 1;
        }

        /*
         * Setup the thread mask for this irqaction for ONESHOT. For
         * !ONESHOT irqs the thread mask is 0 so we can avoid a
         * conditional in irq_wake_thread().
         */
        if (new->flags & IRQF_ONESHOT) {
                /*
                 * Unlikely to have 32 resp 64 irqs sharing one line,
                 * but who knows.
                 */
                if (thread_mask == ~0UL) {
                        ret = -EBUSY;
                        goto out_mask;
                }
                /*
                 * The thread_mask for the action is or'ed to
                 * desc->thread_active to indicate that the
                 * IRQF_ONESHOT thread handler has been woken, but not
                 * yet finished. The bit is cleared when a thread
                 * completes. When all threads of a shared interrupt
                 * line have completed desc->threads_active becomes
                 * zero and the interrupt line is unmasked. See
                 * handle.c:irq_wake_thread() for further information.
                 *
                 * If no thread is woken by primary (hard irq context)
                 * interrupt handlers, then desc->threads_active is
                 * also checked for zero to unmask the irq line in the
                 * affected hard irq flow handlers
                 * (handle_[fasteoi|level]_irq).
                 *
                 * The new action gets the first zero bit of
                 * thread_mask assigned. See the loop above which or's
                 * all existing action->thread_mask bits.
                 */
                new->thread_mask = 1 << ffz(thread_mask);

        } else if (new->handler == irq_default_primary_handler &&
                   !(desc->irq_data.chip->flags & IRQCHIP_ONESHOT_SAFE)) {
                /*
                 * The interrupt was requested with handler = NULL, so
                 * we use the default primary handler for it. But it
                 * does not have the oneshot flag set. In combination
                 * with level interrupts this is deadly, because the
                 * default primary handler just wakes the thread, then
                 * the irq lines is reenabled, but the device still
                 * has the level irq asserted. Rinse and repeat....
                 *
                 * While this works for edge type interrupts, we play
                 * it safe and reject unconditionally because we can't
                 * say for sure which type this interrupt really
                 * has. The type flags are unreliable as the
                 * underlying chip implementation can override them.
                 */
                pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
                       irq);
                ret = -EINVAL;
                goto out_mask;
        }

        if (!shared) {
                ret = irq_request_resources(desc);
                if (ret) {
                        pr_err("Failed to request resources for %s (irq %d) on irqchip %s\n",
                               new->name, irq, desc->irq_data.chip->name);
                        goto out_mask;
                }

                init_waitqueue_head(&desc->wait_for_threads);

                /* Setup the type (level, edge polarity) if configured: */
                if (new->flags & IRQF_TRIGGER_MASK) {
                        ret = __irq_set_trigger(desc,
                                                new->flags & IRQF_TRIGGER_MASK);

                        if (ret)
                                goto out_mask;
                }

                desc->istate &= ~(IRQS_AUTODETECT | IRQS_SPURIOUS_DISABLED | \
                                  IRQS_ONESHOT | IRQS_WAITING);
                irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);

                if (new->flags & IRQF_PERCPU) {
                        irqd_set(&desc->irq_data, IRQD_PER_CPU);
                        irq_settings_set_per_cpu(desc);
                }

                if (new->flags & IRQF_ONESHOT)
                        desc->istate |= IRQS_ONESHOT;

                if (irq_settings_can_autoenable(desc))
                        irq_startup(desc, true);
                else
                        /* Undo nested disables: */
                        desc->depth = 1;

                /* Exclude IRQ from balancing if requested */
                if (new->flags & IRQF_NOBALANCING) {
                        irq_settings_set_no_balancing(desc);
                        irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
                }

                /* Set default affinity mask once everything is setup */
                setup_affinity(desc, mask);

        } else if (new->flags & IRQF_TRIGGER_MASK) {
                unsigned int nmsk = new->flags & IRQF_TRIGGER_MASK;
                unsigned int omsk = irq_settings_get_trigger_mask(desc);

                if (nmsk != omsk)
                        /* hope the handler works with current  trigger mode */
                        pr_warn("irq %d uses trigger mode %u; requested %u\n",
                                irq, nmsk, omsk);
        }

        *old_ptr = new;

        irq_pm_install_action(desc, new);

        /* Reset broken irq detection when installing new handler */
        desc->irq_count = 0;
        desc->irqs_unhandled = 0;

        /*
         * Check whether we disabled the irq via the spurious handler
         * before. Reenable it and give it another chance.
         */
        if (shared && (desc->istate & IRQS_SPURIOUS_DISABLED)) {
                desc->istate &= ~IRQS_SPURIOUS_DISABLED;
                __enable_irq(desc);
        }

        raw_spin_unlock_irqrestore(&desc->lock, flags);

        /*
         * Strictly no need to wake it up, but hung_task complains
         * when no hard interrupt wakes the thread up.
         */
        if (new->thread)
                wake_up_process(new->thread);
        if (new->secondary)
                wake_up_process(new->secondary->thread);

        register_irq_proc(irq, desc);
        new->dir = NULL;
        register_handler_proc(irq, new);
        free_cpumask_var(mask);

        return 0;

mismatch:
        if (!(new->flags & IRQF_PROBE_SHARED)) {
                pr_err("Flags mismatch irq %d. %08x (%s) vs. %08x (%s)\n",
                       irq, new->flags, new->name, old->flags, old->name);
#ifdef CONFIG_DEBUG_SHIRQ
                dump_stack();
#endif
        }
        ret = -EBUSY;

out_mask:
        raw_spin_unlock_irqrestore(&desc->lock, flags);
        free_cpumask_var(mask);

out_thread:
        if (new->thread) {
                struct task_struct *t = new->thread;

                new->thread = NULL;
                kthread_stop(t);
                put_task_struct(t);
        }
        if (new->secondary && new->secondary->thread) {
                struct task_struct *t = new->secondary->thread;

                new->secondary->thread = NULL;
                kthread_stop(t);
                put_task_struct(t);
        }
out_mput:
        module_put(desc->owner);
        return ret;
}

/**
 *      setup_irq - setup an interrupt
 *      @irq: Interrupt line to setup
 *      @act: irqaction for the interrupt
 *
 * Used to statically setup interrupts in the early boot process.
 */
int setup_irq(unsigned int irq, struct irqaction *act)
{
        int retval;
        struct irq_desc *desc = irq_to_desc(irq);

        if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
                return -EINVAL;
        chip_bus_lock(desc);
        retval = __setup_irq(irq, desc, act);
        chip_bus_sync_unlock(desc);

        return retval;
}
EXPORT_SYMBOL_GPL(setup_irq);

/*
 * Internal function to unregister an irqaction - used to free
 * regular and special interrupts that are part of the architecture.
 */
static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
{
        struct irq_desc *desc = irq_to_desc(irq);
        struct irqaction *action, **action_ptr;
        unsigned long flags;

        WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);

        if (!desc)
                return NULL;

        chip_bus_lock(desc);
        raw_spin_lock_irqsave(&desc->lock, flags);

        /*
         * There can be multiple actions per IRQ descriptor, find the right
         * one based on the dev_id:
         */
        action_ptr = &desc->action;
        for (;;) {
                action = *action_ptr;

                if (!action) {
                        WARN(1, "Trying to free already-free IRQ %d\n", irq);
                        raw_spin_unlock_irqrestore(&desc->lock, flags);
                        chip_bus_sync_unlock(desc);
                        return NULL;
                }

                if (action->dev_id == dev_id)
                        break;
                action_ptr = &action->next;
        }

        /* Found it - now remove it from the list of entries: */
        *action_ptr = action->next;

        irq_pm_remove_action(desc, action);

        /* If this was the last handler, shut down the IRQ line: */
        if (!desc->action) {
                irq_settings_clr_disable_unlazy(desc);
                irq_shutdown(desc);
                irq_release_resources(desc);
        }

#ifdef CONFIG_SMP
        /* make sure affinity_hint is cleaned up */
        if (WARN_ON_ONCE(desc->affinity_hint))
                desc->affinity_hint = NULL;
#endif

        raw_spin_unlock_irqrestore(&desc->lock, flags);
        chip_bus_sync_unlock(desc);

        unregister_handler_proc(irq, action);

        /* Make sure it's not being used on another CPU: */
        synchronize_irq(irq);

#ifdef CONFIG_DEBUG_SHIRQ
        /*
         * It's a shared IRQ -- the driver ought to be prepared for an IRQ
         * event to happen even now it's being freed, so let's make sure that
         * is so by doing an extra call to the handler ....
         *
         * ( We do this after actually deregistering it, to make sure that a
         *   'real' IRQ doesn't run in * parallel with our fake. )
         */
        if (action->flags & IRQF_SHARED) {
                local_irq_save(flags);
                action->handler(irq, dev_id);
                local_irq_restore(flags);
        }
#endif

        if (action->thread) {
                kthread_stop(action->thread);
                put_task_struct(action->thread);
                if (action->secondary && action->secondary->thread) {
                        kthread_stop(action->secondary->thread);
                        put_task_struct(action->secondary->thread);
                }
        }

        module_put(desc->owner);
        kfree(action->secondary);
        return action;
}

/**
 *      remove_irq - free an interrupt
 *      @irq: Interrupt line to free
 *      @act: irqaction for the interrupt
 *
 * Used to remove interrupts statically setup by the early boot process.
 */
void remove_irq(unsigned int irq, struct irqaction *act)
{
        struct irq_desc *desc = irq_to_desc(irq);

        if (desc && !WARN_ON(irq_settings_is_per_cpu_devid(desc)))
            __free_irq(irq, act->dev_id);
}
EXPORT_SYMBOL_GPL(remove_irq);

/**
 *      free_irq - free an interrupt allocated with request_irq
 *      @irq: Interrupt line to free
 *      @dev_id: Device identity to free
 *
 *      Remove an interrupt handler. The handler is removed and if the
 *      interrupt line is no longer in use by any driver it is disabled.
 *      On a shared IRQ the caller must ensure the interrupt is disabled
 *      on the card it drives before calling this function. The function
 *      does not return until any executing interrupts for this IRQ
 *      have completed.
 *
 *      This function must not be called from interrupt context.
 */
void free_irq(unsigned int irq, void *dev_id)
{
        struct irq_desc *desc = irq_to_desc(irq);

        if (!desc || WARN_ON(irq_settings_is_per_cpu_devid(desc)))
                return;

#ifdef CONFIG_SMP
        if (WARN_ON(desc->affinity_notify))
                desc->affinity_notify = NULL;
#endif

        kfree(__free_irq(irq, dev_id));
}
EXPORT_SYMBOL(free_irq);

/**
 *      request_threaded_irq - allocate an interrupt line
 *      @irq: Interrupt line to allocate
 *      @handler: Function to be called when the IRQ occurs.
 *                Primary handler for threaded interrupts
 *                If NULL and thread_fn != NULL the default
 *                primary handler is installed
 *      @thread_fn: Function called from the irq handler thread
 *                  If NULL, no irq thread is created
 *      @irqflags: Interrupt type flags
 *      @devname: An ascii name for the claiming device
 *      @dev_id: A cookie passed back to the handler function
 *
 *      This call allocates interrupt resources and enables the
 *      interrupt line and IRQ handling. From the point this
 *      call is made your handler function may be invoked. Since
 *      your handler function must clear any interrupt the board
 *      raises, you must take care both to initialise your hardware
 *      and to set up the interrupt handler in the right order.
 *
 *      If you want to set up a threaded irq handler for your device
 *      then you need to supply @handler and @thread_fn. @handler is
 *      still called in hard interrupt context and has to check
 *      whether the interrupt originates from the device. If yes it
 *      needs to disable the interrupt on the device and return
 *      IRQ_WAKE_THREAD which will wake up the handler thread and run
 *      @thread_fn. This split handler design is necessary to support
 *      shared interrupts.
 *
 *      Dev_id must be globally unique. Normally the address of the
 *      device data structure is used as the cookie. Since the handler
 *      receives this value it makes sense to use it.
 *
 *      If your interrupt is shared you must pass a non NULL dev_id
 *      as this is required when freeing the interrupt.
 *
 *      Flags:
 *
 *      IRQF_SHARED             Interrupt is shared
 *      IRQF_TRIGGER_*          Specify active edge(s) or level
 *
 */
int request_threaded_irq(unsigned int irq, irq_handler_t handler,
                         irq_handler_t thread_fn, unsigned long irqflags,
                         const char *devname, void *dev_id)
{
        struct irqaction *action;
        struct irq_desc *desc;
        int retval;

        if (irq == IRQ_NOTCONNECTED)
                return -ENOTCONN;

        /*
         * Sanity-check: shared interrupts must pass in a real dev-ID,
         * otherwise we'll have trouble later trying to figure out
         * which interrupt is which (messes up the interrupt freeing
         * logic etc).
         *
         * Also IRQF_COND_SUSPEND only makes sense for shared interrupts and
         * it cannot be set along with IRQF_NO_SUSPEND.
         */
        if (((irqflags & IRQF_SHARED) && !dev_id) ||
            (!(irqflags & IRQF_SHARED) && (irqflags & IRQF_COND_SUSPEND)) ||
            ((irqflags & IRQF_NO_SUSPEND) && (irqflags & IRQF_COND_SUSPEND)))
                return -EINVAL;

        desc = irq_to_desc(irq);
        if (!desc)
                return -EINVAL;

        if (!irq_settings_can_request(desc) ||
            WARN_ON(irq_settings_is_per_cpu_devid(desc)))
                return -EINVAL;

        if (!handler) {
                if (!thread_fn)
                        return -EINVAL;
                handler = irq_default_primary_handler;
        }

        action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
        if (!action)
                return -ENOMEM;

        action->handler = handler;
        action->thread_fn = thread_fn;
        action->flags = irqflags;
        action->name = devname;
        action->dev_id = dev_id;

        chip_bus_lock(desc);
        retval = __setup_irq(irq, desc, action);
        chip_bus_sync_unlock(desc);

        if (retval) {
                kfree(action->secondary);
                kfree(action);
        }

#ifdef CONFIG_DEBUG_SHIRQ_FIXME
        if (!retval && (irqflags & IRQF_SHARED)) {
                /*
                 * It's a shared IRQ -- the driver ought to be prepared for it
                 * to happen immediately, so let's make sure....
                 * We disable the irq to make sure that a 'real' IRQ doesn't
                 * run in parallel with our fake.
                 */
                unsigned long flags;

                disable_irq(irq);
                local_irq_save(flags);

                handler(irq, dev_id);

                local_irq_restore(flags);
                enable_irq(irq);
        }
#endif
        return retval;
}
EXPORT_SYMBOL(request_threaded_irq);

/**
 *      request_any_context_irq - allocate an interrupt line
 *      @irq: Interrupt line to allocate
 *      @handler: Function to be called when the IRQ occurs.
 *                Threaded handler for threaded interrupts.
 *      @flags: Interrupt type flags
 *      @name: An ascii name for the claiming device
 *      @dev_id: A cookie passed back to the handler function
 *
 *      This call allocates interrupt resources and enables the
 *      interrupt line and IRQ handling. It selects either a
 *      hardirq or threaded handling method depending on the
 *      context.
 *
 *      On failure, it returns a negative value. On success,
 *      it returns either IRQC_IS_HARDIRQ or IRQC_IS_NESTED.
 */
int request_any_context_irq(unsigned int irq, irq_handler_t handler,
                            unsigned long flags, const char *name, void *dev_id)
{
        struct irq_desc *desc;
        int ret;

        if (irq == IRQ_NOTCONNECTED)
                return -ENOTCONN;

        desc = irq_to_desc(irq);
        if (!desc)
                return -EINVAL;

        if (irq_settings_is_nested_thread(desc)) {
                ret = request_threaded_irq(irq, NULL, handler,
                                           flags, name, dev_id);
                return !ret ? IRQC_IS_NESTED : ret;
        }

        ret = request_irq(irq, handler, flags, name, dev_id);
        return !ret ? IRQC_IS_HARDIRQ : ret;
}
EXPORT_SYMBOL_GPL(request_any_context_irq);

void enable_percpu_irq(unsigned int irq, unsigned int type)
{
        unsigned int cpu = smp_processor_id();
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);

        if (!desc)
                return;

        type &= IRQ_TYPE_SENSE_MASK;
        if (type != IRQ_TYPE_NONE) {
                int ret;

                ret = __irq_set_trigger(desc, type);

                if (ret) {
                        WARN(1, "failed to set type for IRQ%d\n", irq);
                        goto out;
                }
        }

        irq_percpu_enable(desc, cpu);
out:
        irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(enable_percpu_irq);

/**
 * irq_percpu_is_enabled - Check whether the per cpu irq is enabled
 * @irq:        Linux irq number to check for
 *
 * Must be called from a non migratable context. Returns the enable
 * state of a per cpu interrupt on the current cpu.
 */
bool irq_percpu_is_enabled(unsigned int irq)
{
        unsigned int cpu = smp_processor_id();
        struct irq_desc *desc;
        unsigned long flags;
        bool is_enabled;

        desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);
        if (!desc)
                return false;

        is_enabled = cpumask_test_cpu(cpu, desc->percpu_enabled);
        irq_put_desc_unlock(desc, flags);

        return is_enabled;
}
EXPORT_SYMBOL_GPL(irq_percpu_is_enabled);

void disable_percpu_irq(unsigned int irq)
{
        unsigned int cpu = smp_processor_id();
        unsigned long flags;
        struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_PERCPU);

        if (!desc)
                return;

        irq_percpu_disable(desc, cpu);
        irq_put_desc_unlock(desc, flags);
}
EXPORT_SYMBOL_GPL(disable_percpu_irq);

/*
 * Internal function to unregister a percpu irqaction.
 */
static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
        struct irq_desc *desc = irq_to_desc(irq);
        struct irqaction *action;
        unsigned long flags;

        WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);

        if (!desc)
                return NULL;

        raw_spin_lock_irqsave(&desc->lock, flags);

        action = desc->action;
        if (!action || action->percpu_dev_id != dev_id) {
                WARN(1, "Trying to free already-free IRQ %d\n", irq);
                goto bad;
        }

        if (!cpumask_empty(desc->percpu_enabled)) {
                WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
                     irq, cpumask_first(desc->percpu_enabled));
                goto bad;
        }

        /* Found it - now remove it from the list of entries: */
        desc->action = NULL;

        raw_spin_unlock_irqrestore(&desc->lock, flags);

        unregister_handler_proc(irq, action);

        module_put(desc->owner);
        return action;

bad:
        raw_spin_unlock_irqrestore(&desc->lock, flags);
        return NULL;
}

/**
 *      remove_percpu_irq - free a per-cpu interrupt
 *      @irq: Interrupt line to free
 *      @act: irqaction for the interrupt
 *
 * Used to remove interrupts statically setup by the early boot process.
 */
void remove_percpu_irq(unsigned int irq, struct irqaction *act)
{
        struct irq_desc *desc = irq_to_desc(irq);

        if (desc && irq_settings_is_per_cpu_devid(desc))
            __free_percpu_irq(irq, act->percpu_dev_id);
}

/**
 *      free_percpu_irq - free an interrupt allocated with request_percpu_irq
 *      @irq: Interrupt line to free
 *      @dev_id: Device identity to free
 *
 *      Remove a percpu interrupt handler. The handler is removed, but
 *      the interrupt line is not disabled. This must be done on each
 *      CPU before calling this function. The function does not return
 *      until any executing interrupts for this IRQ have completed.
 *
 *      This function must not be called from interrupt context.
 */
void free_percpu_irq(unsigned int irq, void __percpu *dev_id)
{
        struct irq_desc *desc = irq_to_desc(irq);

        if (!desc || !irq_settings_is_per_cpu_devid(desc))
                return;

        chip_bus_lock(desc);
        kfree(__free_percpu_irq(irq, dev_id));
        chip_bus_sync_unlock(desc);
}
EXPORT_SYMBOL_GPL(free_percpu_irq);

/**
 *      setup_percpu_irq - setup a per-cpu interrupt
 *      @irq: Interrupt line to setup
 *      @act: irqaction for the interrupt
 *
 * Used to statically setup per-cpu interrupts in the early boot process.
 */
int setup_percpu_irq(unsigned int irq, struct irqaction *act)
{
        struct irq_desc *desc = irq_to_desc(irq);
        int retval;

        if (!desc || !irq_settings_is_per_cpu_devid(desc))
                return -EINVAL;
        chip_bus_lock(desc);
        retval = __setup_irq(irq, desc, act);
        chip_bus_sync_unlock(desc);

        return retval;
}

/**
 *      request_percpu_irq - allocate a percpu interrupt line
 *      @irq: Interrupt line to allocate
 *      @handler: Function to be called when the IRQ occurs.
 *      @devname: An ascii name for the claiming device
 *      @dev_id: A percpu cookie passed back to the handler function
 *
 *      This call allocates interrupt resources and enables the
 *      interrupt on the local CPU. If the interrupt is supposed to be
 *      enabled on other CPUs, it has to be done on each CPU using
 *      enable_percpu_irq().
 *
 *      Dev_id must be globally unique. It is a per-cpu variable, and
 *      the handler gets called with the interrupted CPU's instance of
 *      that variable.
 */
int request_percpu_irq(unsigned int irq, irq_handler_t handler,
                       const char *devname, void __percpu *dev_id)
{
        struct irqaction *action;
        struct irq_desc *desc;
        int retval;

        if (!dev_id)
                return -EINVAL;

        desc = irq_to_desc(irq);
        if (!desc || !irq_settings_can_request(desc) ||
            !irq_settings_is_per_cpu_devid(desc))
                return -EINVAL;

        action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
        if (!action)
                return -ENOMEM;

        action->handler = handler;
        action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND;
        action->name = devname;
        action->percpu_dev_id = dev_id;

        chip_bus_lock(desc);
        retval = __setup_irq(irq, desc, action);
        chip_bus_sync_unlock(desc);

        if (retval)
                kfree(action);

        return retval;
}
EXPORT_SYMBOL_GPL(request_percpu_irq);

/**
 *      irq_get_irqchip_state - returns the irqchip state of a interrupt.
 *      @irq: Interrupt line that is forwarded to a VM
 *      @which: One of IRQCHIP_STATE_* the caller wants to know about
 *      @state: a pointer to a boolean where the state is to be storeed
 *
 *      This call snapshots the internal irqchip state of an
 *      interrupt, returning into @state the bit corresponding to
 *      stage @which
 *
 *      This function should be called with preemption disabled if the
 *      interrupt controller has per-cpu registers.
 */
int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
                          bool *state)
{
        struct irq_desc *desc;
        struct irq_data *data;
        struct irq_chip *chip;
        unsigned long flags;
        int err = -EINVAL;

        desc = irq_get_desc_buslock(irq, &flags, 0);
        if (!desc)
                return err;

        data = irq_desc_get_irq_data(desc);

        do {
                chip = irq_data_get_irq_chip(data);
                if (chip->irq_get_irqchip_state)
                        break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
                data = data->parent_data;
#else
                data = NULL;
#endif
        } while (data);

        if (data)
                err = chip->irq_get_irqchip_state(data, which, state);

        irq_put_desc_busunlock(desc, flags);
        return err;
}
EXPORT_SYMBOL_GPL(irq_get_irqchip_state);

/**
 *      irq_set_irqchip_state - set the state of a forwarded interrupt.
 *      @irq: Interrupt line that is forwarded to a VM
 *      @which: State to be restored (one of IRQCHIP_STATE_*)
 *      @val: Value corresponding to @which
 *
 *      This call sets the internal irqchip state of an interrupt,
 *      depending on the value of @which.
 *
 *      This function should be called with preemption disabled if the
 *      interrupt controller has per-cpu registers.
 */
int irq_set_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
                          bool val)
{
        struct irq_desc *desc;
        struct irq_data *data;
        struct irq_chip *chip;
        unsigned long flags;
        int err = -EINVAL;

        desc = irq_get_desc_buslock(irq, &flags, 0);
        if (!desc)
                return err;

        data = irq_desc_get_irq_data(desc);

        do {
                chip = irq_data_get_irq_chip(data);
                if (chip->irq_set_irqchip_state)
                        break;
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
                data = data->parent_data;
#else
                data = NULL;
#endif
        } while (data);

        if (data)
                err = chip->irq_set_irqchip_state(data, which, val);

        irq_put_desc_busunlock(desc, flags);
        return err;
}
EXPORT_SYMBOL_GPL(irq_set_irqchip_state);