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/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

/**
 *	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);
	bool inprogress;

	if (!desc)
		return;

	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);

	/*
	 * 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;

/**
 *	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)
{
	struct irq_desc *desc = irq_to_desc(irq);

	if (!desc || !irqd_can_balance(&desc->irq_data) ||
	    !desc->irq_data.chip || !desc->irq_data.chip->irq_set_affinity)
		return 0;

	return 1;
}

/**
 *	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 = desc->action;

	while (action) {
		if (action->thread)
			set_bit(IRQTF_AFFINITY, &action->thread_flags);
		action = action->next;
	}
}

#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, false);
	switch (ret) {
	case IRQ_SET_MASK_OK:
		cpumask_copy(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)
{
	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, false);
	} 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;
}

/**
 *	irq_set_affinity - Set the irq affinity of a given irq
 *	@irq:		Interrupt to set affinity
 *	@mask:		cpumask
 *
 */
int irq_set_affinity(unsigned int irq, const struct cpumask *mask)
{
	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);
	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);
	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_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(unsigned int irq, struct irq_desc *desc, struct cpumask *mask)
{
	struct cpumask *set = irq_default_affinity;
	int node = desc->irq_data.node;

	/* Excludes PER_CPU and NO_BALANCE interrupts */
	if (!irq_can_set_affinity(irq))
		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_data.affinity,
				       cpu_online_mask))
			set = desc->irq_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
static inline int
setup_affinity(unsigned int irq, struct irq_desc *d, struct cpumask *mask)
{
	return irq_select_affinity(irq);
}
#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(irq, desc, mask);
	raw_spin_unlock_irqrestore(&desc->lock, flags);
	return ret;
}

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

void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
{
	if (suspend) {
		if (!desc->action || (desc->action->flags & IRQF_NO_SUSPEND))
			return;
		desc->istate |= IRQS_SUSPENDED;
	}

	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, false);
	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);

void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
{
	if (resume) {
		if (!(desc->istate & IRQS_SUSPENDED)) {
			if (!desc->action)
				return;
			if (!(desc->action->flags & IRQF_FORCE_RESUME))
				return;
			/* Pretend that it got disabled ! */
			desc->depth++;
		}
		desc->istate &= ~IRQS_SUSPENDED;
	}

	switch (desc->depth) {
	case 0:
 err_out:
		WARN(1, KERN_WARNING "Unbalanced enable for IRQ %d\n", irq);
		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, irq);
		/* 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, irq, false);
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)
			if (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 int irq,
		      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,
			 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:
		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, 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 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))
		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_irq(desc);

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

#ifdef CONFIG_SMP
/*
 * Check whether we need to chasnge 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_data.affinity)
		cpumask_copy(mask, desc->irq_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 explicitely requested as threaded interupts 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) &&
	    waitqueue_active(&desc->wait_for_threads))
		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);
}

/*
 * Interrupt handler thread
 */
static int irq_thread(void *data)
{
	struct callback_head on_exit_work;
	static const struct sched_param param = {
		.sched_priority = MAX_USER_RT_PRIO/2,
	};
	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;

	sched_setscheduler(current, SCHED_FIFO, &param);

	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 (!noirqdebug)
			note_interrupt(action->irq, desc, action_ret);

		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;
}

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

	new->flags |= IRQF_ONESHOT;

	if (!new->thread_fn) {
		set_bit(IRQTF_FORCED_THREAD, &new->thread_flags);
		new->thread_fn = new->handler;
		new->handler = irq_default_primary_handler;
	}
}

/*
 * 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;

	/*
	 * 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))
			irq_setup_forced_threading(new);
	}

	/*
	 * 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) {
		struct task_struct *t;

		t = kthread_create(irq_thread, new, "irq/%d-%s", irq,
				   new->name);
		if (IS_ERR(t)) {
			ret = PTR_ERR(t);
			goto out_mput;
		}
		/*
		 * 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);
	}

	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;