/* softirq mask and active fields moved to irq_cpustat_t in
 * asm/hardirq.h to get better cache usage.  KAO
 */

struct softirq_action
{
	void	(*action)(struct softirq_action *);
};

static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp;
软中断的优先级是该数组的下标

enum
{
	HI_SOFTIRQ=0,
	TIMER_SOFTIRQ,
	NET_TX_SOFTIRQ,
	NET_RX_SOFTIRQ,
	BLOCK_SOFTIRQ,
	BLOCK_IOPOLL_SOFTIRQ,
	TASKLET_SOFTIRQ,
	SCHED_SOFTIRQ,
	HRTIMER_SOFTIRQ,
	RCU_SOFTIRQ,    /* Preferable RCU should always be the last softirq */

	NR_SOFTIRQS
};

/*
 * handle_IRQ handles all hardware IRQ's.  Decoded IRQs should
 * not come via this function.  Instead, they should provide their
 * own 'handler'.  Used by platform code implementing C-based 1st
 * level decoding.
 */
void handle_IRQ(unsigned int irq, struct pt_regs *regs)
{
	struct pt_regs *old_regs = set_irq_regs(regs);

	irq_enter();        ///

	/*
	 * Some hardware gives randomly wrong interrupts.  Rather
	 * than crashing, do something sensible.
	 */
	if (unlikely(irq >= nr_irqs)) {
		if (printk_ratelimit())
			printk(KERN_WARNING "Bad IRQ%u\n", irq);
		ack_bad_irq(irq);
	} else {
		generic_handle_irq(irq);
	}

	/* AT91 specific workaround */
	irq_finish(irq);

	irq_exit();           ///
	set_irq_regs(old_regs);
}

/*
 * asm_do_IRQ is the interface to be used from assembly code.
 */
asmlinkage void __exception_irq_entry
asm_do_IRQ(unsigned int irq, struct pt_regs *regs)
{
	handle_IRQ(irq, regs);
}

/*
 * Enter an interrupt context.
 */
void irq_enter(void)
{
	int cpu = smp_processor_id();

	rcu_irq_enter();
	if (is_idle_task(current) && !in_interrupt()) {
		/*
		 * Prevent raise_softirq from needlessly waking up ksoftirqd
		 * here, as softirq will be serviced on return from interrupt.
		 */
		local_bh_disable();
		tick_check_idle(cpu);
		_local_bh_enable();
	}

	__irq_enter();
}

/*
 * It is safe to do non-atomic ops on ->hardirq_context,
 * because NMI handlers may not preempt and the ops are
 * always balanced, so the interrupted value of ->hardirq_context
 * will always be restored.
 */
#define __irq_enter()					\
	do {						\
		account_system_vtime(current);		\
		add_preempt_count(HARDIRQ_OFFSET);	\ 这行代码正是将hardirq对应的bit增加1，标识内核此时正处于中断上下文之中。
		trace_hardirq_enter();			\
	} while (0)

/*
 * Exit an interrupt context. Process softirqs if needed and possible:
 */
void irq_exit(void)
{
	account_system_vtime(current);
	trace_hardirq_exit();
	sub_preempt_count(IRQ_EXIT_OFFSET);
	if (!in_interrupt() && local_softirq_pending())
		invoke_softirq();

#ifdef CONFIG_NO_HZ
	/* Make sure that timer wheel updates are propagated */
	if (idle_cpu(smp_processor_id()) && !in_interrupt() && !need_resched())
		tick_nohz_irq_exit();
#endif
	rcu_irq_exit();
	sched_preempt_enable_no_resched();
}

static inline void invoke_softirq(void)
{
	if (!force_irqthreads) {
#ifdef __ARCH_IRQ_EXIT_IRQS_DISABLED	//这里被定义为1
		__do_softirq();
#else
		do_softirq();
#endif
	} else {
		__local_bh_disable((unsigned long)__builtin_return_address(0),
				SOFTIRQ_OFFSET);
		wakeup_softirqd();
		__local_bh_enable(SOFTIRQ_OFFSET);
	}
}

void local_bh_disable(void)
{
	__local_bh_disable((unsigned long)__builtin_return_address(0),
				SOFTIRQ_DISABLE_OFFSET);
}

static inline void __local_bh_disable(unsigned long ip, unsigned int cnt)
{
	add_preempt_count(cnt);
	barrier();
}

static void __local_bh_enable(unsigned int cnt)
{
	WARN_ON_ONCE(in_irq());
	WARN_ON_ONCE(!irqs_disabled());

	if (softirq_count() == cnt)
		trace_softirqs_on((unsigned long)__builtin_return_address(0));
	sub_preempt_count(cnt);
}

/*
 * Special-case - softirqs can safely be enabled in
 * cond_resched_softirq(), or by __do_softirq(),
 * without processing still-pending softirqs:
 */
void _local_bh_enable(void)
{
	__local_bh_enable(SOFTIRQ_DISABLE_OFFSET);
}

static inline void _local_bh_enable_ip(unsigned long ip)
{
	WARN_ON_ONCE(in_irq() || irqs_disabled());
#ifdef CONFIG_TRACE_IRQFLAGS
	local_irq_disable();
#endif
	/*
	 * Are softirqs going to be turned on now:
	 */
	if (softirq_count() == SOFTIRQ_DISABLE_OFFSET)
		trace_softirqs_on(ip);
	/*
	 * Keep preemption disabled until we are done with
	 * softirq processing:
 	 */
	sub_preempt_count(SOFTIRQ_DISABLE_OFFSET - 1);

	if (unlikely(!in_interrupt() && local_softirq_pending()))
		do_softirq();

	dec_preempt_count();
#ifdef CONFIG_TRACE_IRQFLAGS
	local_irq_enable();
#endif
	preempt_check_resched();
}

void local_bh_enable(void)
{
	_local_bh_enable_ip((unsigned long)__builtin_return_address(0));
}
EXPORT_SYMBOL(local_bh_enable);

asmlinkage void do_softirq(void)
{
	__u32 pending;
	unsigned long flags;

	if (in_interrupt())
		return;
注释：此处要求软中断不能发生在任何硬件和软件中断上下文中。
	local_irq_save(flags);

	pending = local_softirq_pending();
注释：确定当前CPU软中断位图中所有置位的比特位，注意此过程必须在关闭本地中断前提下，防止其他进程对该位图做修改。local_irq_save(flags);在这里就是最好的解释。
	if (pending)
		__do_softirq();

	local_irq_restore(flags);
}

/*
 * We restart softirq processing MAX_SOFTIRQ_RESTART times,
 * and we fall back to softirqd after that.
 *
 * This number has been established via experimentation.
 * The two things to balance is latency against fairness -
 * we want to handle softirqs as soon as possible, but they
 * should not be able to lock up the box.
 */
#define MAX_SOFTIRQ_RESTART 10

asmlinkage void __do_softirq(void)
{
	struct softirq_action *h;
	__u32 pending;
	int max_restart = MAX_SOFTIRQ_RESTART;
	int cpu;

	pending = local_softirq_pending();
注释：确定当前CPU软中断位图中所有置位的比特位
	account_system_vtime(current);

	__local_bh_disable((unsigned long)__builtin_return_address(0),
				SOFTIRQ_OFFSET);
	lockdep_softirq_enter();

	cpu = smp_processor_id();
restart:
	/* Reset the pending bitmask before enabling irqs */
	set_softirq_pending(0);
注释：清除pending位图标志，注意从此处的代码向上都需要在关本地中断的情况下执行，为了避免pending标志被别的进程修改。

	local_irq_enable();
注释：注意，软中断处理函数的执行期间是允许外部硬件中断的。

	h = softirq_vec;

	do {
		if (pending & 1) {
			unsigned int vec_nr = h - softirq_vec;
			int prev_count = preempt_count();

			kstat_incr_softirqs_this_cpu(vec_nr);

			trace_softirq_entry(vec_nr);
			h->action(h);
注释：真正的软中断处理函数
			trace_softirq_exit(vec_nr);
			if (unlikely(prev_count != preempt_count())) {
				printk(KERN_ERR "huh, entered softirq %u %s %p"
				       "with preempt_count %08x,"
				       " exited with %08x?\n", vec_nr,
				       softirq_to_name[vec_nr], h->action,
				       prev_count, preempt_count());
				preempt_count() = prev_count;
			}

			rcu_bh_qs(cpu);
		}
		h++;
		pending >>= 1;
	} while (pending);

	local_irq_disable();
注释：中断处理完成后，我们需要重新检查是否在，软中断期间，pending位又被修改

	pending = local_softirq_pending();
	if (pending && --max_restart)
		goto restart;

	if (pending)
		wakeup_softirqd();

	lockdep_softirq_exit();

	account_system_vtime(current);
	__local_bh_enable(SOFTIRQ_OFFSET);
}

void open_softirq(int nr, void (*action)(struct softirq_action *))
{
	softirq_vec[nr].action = action;
}

void __init softirq_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		int i;

		per_cpu(tasklet_vec, cpu).tail =
			&per_cpu(tasklet_vec, cpu).head;
		per_cpu(tasklet_hi_vec, cpu).tail =
			&per_cpu(tasklet_hi_vec, cpu).head;
		for (i = 0; i < NR_SOFTIRQS; i++)
			INIT_LIST_HEAD(&per_cpu(softirq_work_list[i], cpu));
	}

	register_hotcpu_notifier(&remote_softirq_cpu_notifier);

	open_softirq(TASKLET_SOFTIRQ, tasklet_action);
	open_softirq(HI_SOFTIRQ, tasklet_hi_action);
}

static inline void tasklet_schedule(struct tasklet_struct *t)
{
	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
		__tasklet_schedule(t);
}

void __tasklet_schedule(struct tasklet_struct *t)
{
	unsigned long flags;

	local_irq_save(flags);
	t->next = NULL;
	*__this_cpu_read(tasklet_vec.tail) = t;
	__this_cpu_write(tasklet_vec.tail, &(t->next));
	raise_softirq_irqoff(TASKLET_SOFTIRQ);
	local_irq_restore(flags);
}

asmlinkage void __do_softirq(void)
{
	struct softirq_action *h;
	__u32 pending;
	int max_restart = MAX_SOFTIRQ_RESTART;
	int cpu;

	pending = local_softirq_pending();
	account_system_vtime(current);

	__local_bh_disable((unsigned long)__builtin_return_address(0),
				SOFTIRQ_OFFSET);
	lockdep_softirq_enter();

	cpu = smp_processor_id();
restart:
	/* Reset the pending bitmask before enabling irqs */
	set_softirq_pending(0);

	local_irq_enable();

	h = softirq_vec;

	do {
		if (pending & 1) {
			unsigned int vec_nr = h - softirq_vec;
			int prev_count = preempt_count();

			kstat_incr_softirqs_this_cpu(vec_nr);

			trace_softirq_entry(vec_nr);
			h->action(h);		//最终调用open_softirq时候注册的tasklet_action(仅以tasklet为例子)
			trace_softirq_exit(vec_nr);
			if (unlikely(prev_count != preempt_count())) {
				printk(KERN_ERR "huh, entered softirq %u %s %p"
				       "with preempt_count %08x,"
				       " exited with %08x?\n", vec_nr,
				       softirq_to_name[vec_nr], h->action,
				       prev_count, preempt_count());
				preempt_count() = prev_count;
			}

			rcu_bh_qs(cpu);
		}
		h++;
		pending >>= 1;
	} while (pending);

	local_irq_disable();

	pending = local_softirq_pending();
	if (pending && --max_restart)
		goto restart;

	if (pending)
		wakeup_softirqd();

	lockdep_softirq_exit();

	account_system_vtime(current);
	__local_bh_enable(SOFTIRQ_OFFSET);
}

static void tasklet_action(struct softirq_action *a)
{
	struct tasklet_struct *list;

	local_irq_disable();
	list = __this_cpu_read(tasklet_vec.head);
	__this_cpu_write(tasklet_vec.head, NULL);
	__this_cpu_write(tasklet_vec.tail, &__get_cpu_var(tasklet_vec).head);
	local_irq_enable();

	while (list) {
		struct tasklet_struct *t = list;

		list = list->next;

		if (tasklet_trylock(t)) {
注释：tasklet_trylock用于禁用已经被调度的tasklet，在多CPU的系统中。

            if (!atomic_read(&t->count)) {
				if (!test_and_clear_bit(TASKLET_STATE_SCHED, &t->state))
					BUG();
				t->func(t->data);	//
tasklet_init中初始化好了的func和data，才是真正要执行的函数。

使用方法：
tasklet_init(&ttime->tasklet,	__tasklet_hrtimer_trampoline,	(unsigned long)ttimer);

原型：
void tasklet_init(struct tasklet_struct *t,
              void (*func)(unsigned long), unsigned long data)
{
t->next = NULL;
t->state = 0;
atomic_set(&t->count, 0);
t->func = func;
t->data = data;
}
				tasklet_unlock(t);
				continue;
			}
			tasklet_unlock(t);
		}

		local_irq_disable();
		t->next = NULL;
		*__this_cpu_read(tasklet_vec.tail) = t;
		__this_cpu_write(tasklet_vec.tail, &(t->next));
		__raise_softirq_irqoff(TASKLET_SOFTIRQ);
		local_irq_enable();
	}
}

static inline int tasklet_trylock(struct tasklet_struct *t)
{
	return !test_and_set_bit(TASKLET_STATE_RUN, &(t)->state);
}

/*
 * This function must run with irqs disabled!
 */
inline void raise_softirq_irqoff(unsigned int nr)
{
	__raise_softirq_irqoff(nr);
设置pending位置位，需要设置软中断可运行标志

	/*
	 * If we're in an interrupt or softirq, we're done
	 * (this also catches softirq-disabled code). We will
	 * actually run the softirq once we return from
	 * the irq or softirq.
	 *
	 * Otherwise we wake up ksoftirqd to make sure we
	 * schedule the softirq soon.
	 */
	if (!in_interrupt())
		wakeup_softirqd();
如果此时处于硬件或者软件中断上下文中，我们知道此时必将马上运行此软中断，因为如果是处于硬件上下文中的时候，马上就会在irq_exit中call软中断；如果此时处于软中断中，那么当执行的软中断执行完毕之后，软件会重新查看pending位，这个时候就可以执行上面的这个软中断。
}

struct tasklet_struct
{
	struct tasklet_struct *next;
	unsigned long state;
	atomic_t count;
	void (*func)(unsigned long);
	unsigned long data;
};

static struct tasklet_struct my_tasklet;	/*定义自己的tasklet_struct变量*/

static void tasklet_handler (unsigned long data)
{
	printk(KERN_ALERT "tasklet_handler is running.\n");
}

static int __init test_init (void)
{
	tasklet_init(&my_tasklet, tasklet_handler, 0); /*挂入钩子函数tasklet_handler*/
	tasklet_schedule(&my_tasklet);	/*触发softirq的TASKLET_SOFTIRQ,在下一次运行softirq时运行这个tasklet*/
	return 0;
}

static void __exit test_exit(void)
{
	tasklet_kill(&my_tasklet);	/*禁止该tasklet的运行*/
	printk(KERN_ALERT "test_exit running.\n");
}
MODULE_LICENSE("GPL");

module_init(test_init);
module_exit(test_exit);

void tasklet_init(struct tasklet_struct *t,
		  void (*func)(unsigned long), unsigned long data)
{
	t->next = NULL;
	t->state = 0;
	atomic_set(&t->count, 0);
	t->func = func;
	t->data = data;
}

static inline void tasklet_schedule(struct tasklet_struct *t)
{
	if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state))
		__tasklet_schedule(t);
}

void __tasklet_schedule(struct tasklet_struct *t)
{
	unsigned long flags;

	local_irq_save(flags);
	t->next = NULL;
	*__this_cpu_read(tasklet_vec.tail) = t;
	__this_cpu_write(tasklet_vec.tail, &(t->next));
注释：将需要调度的tasklet_struct放入到tasklet_vec链表中。
	raise_softirq_irqoff(TASKLET_SOFTIRQ);
	local_irq_restore(flags);
}

void __tasklet_hi_schedule(struct tasklet_struct *t)
{
	unsigned long flags;

	local_irq_save(flags);
	t->next = NULL;
	*__this_cpu_read(tasklet_hi_vec.tail) = t;
	__this_cpu_write(tasklet_hi_vec.tail,  &(t->next));
注释：将需要调度的tasklet_struct放入到tasklet_hi_vec链表中，该tasklet的优先级比较高。
	raise_softirq_irqoff(HI_SOFTIRQ);
	local_irq_restore(flags);
}

/*
 * The externally visible workqueue abstraction is an array of
 * per-CPU workqueues:
 */
struct workqueue_struct {
	unsigned int		flags;		/* W: WQ_* flags */
	union {
		struct cpu_workqueue_struct __percpu	*pcpu;
		struct cpu_workqueue_struct		*single;
		unsigned long				v;
	} cpu_wq;				/* I: cwq's */
	struct list_head	list;		/* W: list of all workqueues */

	struct mutex		flush_mutex;	/* protects wq flushing */
	int			work_color;	/* F: current work color */
	int			flush_color;	/* F: current flush color */
	atomic_t		nr_cwqs_to_flush; /* flush in progress */
	struct wq_flusher	*first_flusher;	/* F: first flusher */
	struct list_head	flusher_queue;	/* F: flush waiters */
	struct list_head	flusher_overflow; /* F: flush overflow list */

	mayday_mask_t		mayday_mask;	/* cpus requesting rescue */
	struct worker		*rescuer;	/* I: rescue worker */

	int			nr_drainers;	/* W: drain in progress */
	int			saved_max_active; /* W: saved cwq max_active */
#ifdef CONFIG_LOCKDEP
	struct lockdep_map	lockdep_map;
#endif
	char			name[];		/* I: workqueue name */
};

struct work_struct {
	atomic_long_t data;
	struct list_head entry;
	work_func_t func;
#ifdef CONFIG_LOCKDEP
	struct lockdep_map lockdep_map;
#endif
};

#define INIT_WORK(_work, _func)					\
	do {							\
		__INIT_WORK((_work), (_func), 0);		\
	} while (0)

#define __INIT_WORK(_work, _func, _onstack)				\
	do {								\
		__init_work((_work), _onstack);				\
		(_work)->data = (atomic_long_t) WORK_DATA_INIT();	\
		INIT_LIST_HEAD(&(_work)->entry);			\
		PREPARE_WORK((_work), (_func));				\
	} while (0)
#endif

/*
 * initialize a work item's function pointer
 */
#define PREPARE_WORK(_work, _func)				\
	do {							\
		(_work)->func = (_func);			\
	} while (0)

struct work_structwork;
static void work_handler(struct work_struct *work) {
printk(“hello!\n”);
}
INIT_WORK(&work, work_handler);

/**
 * schedule_work - put work task in global workqueue
 * @work: job to be done
 *
 * Returns zero if @work was already on the kernel-global workqueue and
 * non-zero otherwise.
 *
 * This puts a job in the kernel-global workqueue if it was not already
 * queued and leaves it in the same position on the kernel-global
 * workqueue otherwise.
 */
int schedule_work(struct work_struct *work)
{
	return queue_work(system_wq, work);
}
EXPORT_SYMBOL(schedule_work);

/**
 * flush_delayed_work - wait for a dwork to finish executing the last queueing
 * @dwork: the delayed work to flush
 *
 * Delayed timer is cancelled and the pending work is queued for
 * immediate execution.  Like flush_work(), this function only
 * considers the last queueing instance of @dwork.
 *
 * RETURNS:
 * %true if flush_work() waited for the work to finish execution,
 * %false if it was already idle.
 */
bool flush_delayed_work(struct delayed_work *dwork)
{
	if (del_timer_sync(&dwork->timer))
		__queue_work(raw_smp_processor_id(),
			     get_work_cwq(&dwork->work)->wq, &dwork->work);
	return flush_work(&dwork->work);
}
EXPORT_SYMBOL(flush_delayed_work);