详解sotfirq和tasklet

softirq

软中断是在硬件中断推出后执行。软中断不能被自己打断(即单个cpu上软中断不能嵌套执行)，只能被硬件中断打断（上半部）。

可以并发运行在多个CPU上(同一类型也可以)。所以软中断必须设计为可重入的函数（允许多个CPU同时操作），因此也需要使用自旋锁来保其数据结构。

gic_handle_irq
    __handle_domain_irq
        generic_handle_irq
            generic_handle_irq_desc(desc);
                desc->handle_irq(desc);
    irq_exit

判断是否在中断中

包括中断和软中断 ；下面的__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);就是标记正在执行软中断

#define in_interrupt()		(irq_count())
#define irq_count()	(preempt_count() & (HARDIRQ_MASK | SOFTIRQ_MASK \
				 | NMI_MASK))

static __always_inline void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
{
	preempt_count_add(cnt);
	barrier();
}
            
 

void irq_exit(void)
{
#ifndef __ARCH_IRQ_EXIT_IRQS_DISABLED
	local_irq_disable();
#else
	WARN_ON_ONCE(!irqs_disabled());
#endif

	account_irq_exit_time(current);
	preempt_count_sub(HARDIRQ_OFFSET);
	if (!in_interrupt() && local_softirq_pending())
		invoke_softirq();

	tick_irq_exit();
	rcu_irq_exit();
	trace_hardirq_exit(); /* must be last! */
}

invoke_softirq

1.如果ksoftirqd线程执行中，直接退出

2.force_irqthreads=0执行__do_softirq处理软终端；=1直接执行ksoftirqd

static inline void invoke_softirq(void)
{
	if (ksoftirqd_running(local_softirq_pending()))
		return;

	if (!force_irqthreads) {
#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
		/*
		 * We can safely execute softirq on the current stack if
		 * it is the irq stack, because it should be near empty
		 * at this stage.
		 */
		__do_softirq();
#else
		/*
		 * Otherwise, irq_exit() is called on the task stack that can
		 * be potentially deep already. So call softirq in its own stack
		 * to prevent from any overrun.
		 */
		do_softirq_own_stack();
#endif
	} else {
		wakeup_softirqd();
	}
}

#ifdef CONFIG_IRQ_FORCED_THREADING
# ifdef CONFIG_PREEMPT_RT
#  define force_irqthreads	(true)
# else
extern bool force_irqthreads;
# endif
#else
#define force_irqthreads	(0)
#endif

__do_softirq

1.调用local_softirq_pending函数取得目前有哪些位存在软件中断。

2.调用__local_bh_disable关闭软中断，其实就是设置正在处理软件中断标记，在同一个CPU上使得不能重入__do_softirq函数。

3.set_softirq_pending重新设置软中断标记为0，在之后重新开启中断之后又可以设置软件中断位。

4.调用local_irq_enable，开启硬件中断。

5.之后在一个循环中，遍历pending标志的每一位且调用软件中断的处理函数。在这个过程中硬件中断是开启的，随时可以打断软件中断。这样保证硬件中断不会丢失。

6.之后关闭硬件中断(local_irq_disable)，查看是否又有软件中断处于pending状态，如果是，并且在本次调用__do_softirq函数过程中没有累计重复进入软件中断处理的次数超过max_restart=10次，就可以重新调用软件中断处理。如果超过了10次，就调用wakeup_softirqd()唤醒内核的一个进程来处理软件中断。设立10次的限制，也是为了避免影响系统响应时间。

7.调用_local_bh_enable开启软中断。

asmlinkage __visible void __softirq_entry __do_softirq(void)
{
	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
	unsigned long old_flags = current->flags;
	int max_restart = MAX_SOFTIRQ_RESTART;
	struct softirq_action *h;
	bool in_hardirq;
	__u32 pending;
	int softirq_bit;

	/*
	 * Mask out PF_MEMALLOC as the current task context is borrowed for the
	 * softirq. A softirq handled, such as network RX, might set PF_MEMALLOC
	 * again if the socket is related to swapping.
	 */
	current->flags &= ~PF_MEMALLOC;

	pending = local_softirq_pending(); //#define local_softirq_pending()	(__this_cpu_read(local_softirq_pending_ref))
	account_irq_enter_time(current);

	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
	in_hardirq = lockdep_softirq_start();

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

	local_irq_enable();

	h = softirq_vec;

	while ((softirq_bit = ffs(pending))) {
		unsigned int vec_nr;
		int prev_count;

		h += softirq_bit - 1;

		vec_nr = h - softirq_vec;
		prev_count = preempt_count();

		kstat_incr_softirqs_this_cpu(vec_nr);

		trace_softirq_entry(vec_nr);
		h->action(h);
		trace_softirq_exit(vec_nr);
		if (unlikely(prev_count != preempt_count())) {
			pr_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_set(prev_count);
		}
		h++;
		pending >>= softirq_bit;
	}

	if (__this_cpu_read(ksoftirqd) == current)
		rcu_softirq_qs();
	local_irq_disable();

	pending = local_softirq_pending();
	if (pending) {
		if (time_before(jiffies, end) && !need_resched() &&
		    --max_restart)
			goto restart;

		wakeup_softirqd();
	}

	lockdep_softirq_end(in_hardirq);
	account_irq_exit_time(current);
	__local_bh_enable(SOFTIRQ_OFFSET);
	WARN_ON_ONCE(in_interrupt());
	current_restore_flags(old_flags, PF_MEMALLOC);
}

ksoftirqd

下面是软中断是否应该执行的判断条件，也即有没软中断pending， 以及run_ksoftirqd线程函数来执行一次软中断

static int ksoftirqd_should_run(unsigned int cpu)
{
	return local_softirq_pending();
}

static void run_ksoftirqd(unsigned int cpu)
{
	local_irq_disable();
	if (local_softirq_pending()) {
		__do_softirq();
		rcu_note_context_switch(cpu);
		local_irq_enable();
		cond_resched();
		return;
	}
	local_irq_enable();
}
static struct smp_hotplug_thread softirq_threads = {
	.store			= &ksoftirqd,
	.thread_should_run	= ksoftirqd_should_run,
	.thread_fn		= run_ksoftirqd,
	.thread_comm		= "ksoftirqd/%u",
};

static __init int spawn_ksoftirqd(void)
{
	register_cpu_notifier(&cpu_nfb);

	BUG_ON(smpboot_register_percpu_thread(&softirq_threads));

	return 0;
}
early_initcall(spawn_ksoftirqd);

smpboot_register_percpu_thread

watchdog_enable_all_cpus ,cpu_stop_init等接口也会使用这个函数来为每个cpu创建对应线程

int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread)
{
	unsigned int cpu;
	int ret = 0;

	mutex_lock(&smpboot_threads_lock);
	for_each_online_cpu(cpu) {
		ret = __smpboot_create_thread(plug_thread, cpu);
		if (ret) {
			smpboot_destroy_threads(plug_thread);
			goto out;
		}
		smpboot_unpark_thread(plug_thread, cpu);
	}
	list_add(&plug_thread->list, &hotplug_threads);
out:
	mutex_unlock(&smpboot_threads_lock);
	return ret;
}

static int
__smpboot_create_thread(struct smp_hotplug_thread *ht, unsigned int cpu)
{
	struct task_struct *tsk = *per_cpu_ptr(ht->store, cpu);
	struct smpboot_thread_data *td;

	if (tsk)
		return 0;

	td = kzalloc_node(sizeof(*td), GFP_KERNEL, cpu_to_node(cpu));
	if (!td)
		return -ENOMEM;
	td->cpu = cpu;
	td->ht = ht;

	tsk = kthread_create_on_cpu(smpboot_thread_fn, td, cpu,
				    ht->thread_comm);
	if (IS_ERR(tsk)) {
		kfree(td);
		return PTR_ERR(tsk);
	}
	get_task_struct(tsk);
	*per_cpu_ptr(ht->store, cpu) = tsk;
	if (ht->create) {
		/*
		 * Make sure that the task has actually scheduled out
		 * into park position, before calling the create
		 * callback. At least the migration thread callback
		 * requires that the task is off the runqueue.
		 */
		if (!wait_task_inactive(tsk, TASK_PARKED))
			WARN_ON(1);
		else
			ht->create(cpu);
	}
	return 0;
}

smpboot_thread_fn

就是根据对应线程的thread_should_run来决定当前的软件中断线程是否需要执行，不需要执行则放弃时间片

static int smpboot_thread_fn(void *data)
{
    struct smpboot_thread_data *td = data;
    struct smp_hotplug_thread *ht = td->ht;

    while (1) {
        set_current_state(TASK_INTERRUPTIBLE);
        //关闭内核抢占机制
        preempt_disable();
        if (kthread_should_stop()) {
            __set_current_state(TASK_RUNNING);
            preempt_enable();
            if (ht->cleanup)
                ht->cleanup(td->cpu, cpu_online(td->cpu));
            kfree(td);
            return 0;
        }

        if (kthread_should_park()) {
            __set_current_state(TASK_RUNNING);
            preempt_enable();
            if (ht->park && td->status == HP_THREAD_ACTIVE) {
                BUG_ON(td->cpu != smp_processor_id());
                ht->park(td->cpu);
                td->status = HP_THREAD_PARKED;
            }
            kthread_parkme();
            /* We might have been woken for stop */
            continue;
        }

        BUG_ON(td->cpu != smp_processor_id());

        /* Check for state change setup */
        switch (td->status) {
        case HP_THREAD_NONE:
            __set_current_state(TASK_RUNNING);
            preempt_enable();
            if (ht->setup)
                ht->setup(td->cpu);
            td->status = HP_THREAD_ACTIVE;
            continue;

        case HP_THREAD_PARKED:
            __set_current_state(TASK_RUNNING);
            preempt_enable();
            if (ht->unpark)
                ht->unpark(td->cpu);
            td->status = HP_THREAD_ACTIVE;
            continue;
        }
        /*
        * 就是通过调用ksoftirqd_should_run 这是在一开始定义的softirq_threads中指定的，检查当前CPU上维护的软件中断数组中是否有中断
        * 的置起了从而决定当前的软件中断线程是否需要执行，不需要执行则放弃时间片
        */
        if (!ht->thread_should_run(td->cpu)) {
　　　　　　　/*
　　　　　　　*没有需要的软件中断需要执行，则放弃时间片
　　　　　　　*/
            preempt_enable_no_resched();
            schedule();
        } else {
            /*
            * 有中断需要执行则直接调用 run_ksoftirqd 执行软件中断注册的接口的调用
            */
            __set_current_state(TASK_RUNNING);
            preempt_enable();
            //这个接口在上面初始化时绑定为run_ksoftirqd
            ht->thread_fn(td->cpu);
        }
    }
}

symbol

软中断描述符

struct softirq_action{ void (*action)(struct softirq_action *);}; 描述每一种类型的软中断，其中void(*action)是软中断触发时的执行函数。

软中断全局数据和类型

static struct softirq_action softirq_vec[NR_SOFTIRQS]
__cacheline_aligned_in_smp;       
enum       {          
HI_SOFTIRQ=0, /*用于高优先级的tasklet*/          
TIMER_SOFTIRQ, /*用于定时器的下半部*/          
NET_TX_SOFTIRQ, /*用于网络层发包*/          
NET_RX_SOFTIRQ, /*用于网络层收报*/          
BLOCK_SOFTIRQ,          
BLOCK_IOPOLL_SOFTIRQ,          
TASKLET_SOFTIRQ, /*用于低优先级的tasklet*/          
SCHED_SOFTIRQ,          
HRTIMER_SOFTIRQ,          
RCU_SOFTIRQ, /* Preferable RCU should always be the last softirq */          
NR_SOFTIRQS     
 };

注册软中断

void open_softirq(int nr, void (*action)(struct softirq_action *))即注册对应类型的处理函数到全局数组softirq_vec中。例如网络发包对应类型为NET_TX_SOFTIRQ的处理函数net_tx_action.

触发软中断

void raise_softirq(unsigned int nr)实际上即以软中断类型nr作为偏移量置位每cpu变量irq_stat[cpu_id]的成员变量__softirq_pending，这也是同一类型软中断可以在多个cpu上并行运行的根本原因

示例

定义软中断的每cpu变量

static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec);
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec);

注册软中断处理函数

void __init softirq_init(void)
{
	int cpu;

	for_each_possible_cpu(cpu) {
		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;
	}

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

tasklet软中断的处理函数的实现的具体实现

tasklet_trylock通过原子操作标记正在运行，来保证只有一个执行单元(一个cpu)执行此类型的tasklet的func；然后依次遍历tasklet_vec或者tasklet_hi_vec链表里的元素

static __latent_entropy void tasklet_action(struct softirq_action *a)
{
	tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ);
}

static __latent_entropy void tasklet_hi_action(struct softirq_action *a)
{
	tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ);
}

static void tasklet_action_common(struct softirq_action *a,
				  struct tasklet_head *tl_head,
				  unsigned int softirq_nr)
{
	struct tasklet_struct *list;

	local_irq_disable();
	list = tl_head->head;
	tl_head->head = NULL;
	tl_head->tail = &tl_head->head;
	local_irq_enable();

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

		list = list->next;

		if (tasklet_trylock(t)) {
			if (!atomic_read(&t->count)) {
				if (!test_and_clear_bit(TASKLET_STATE_SCHED,
							&t->state))
					BUG();
				t->func(t->data);
				tasklet_unlock(t);
				continue;
			}
			tasklet_unlock(t);
		}

		local_irq_disable();
		t->next = NULL;
		*tl_head->tail = t;
		tl_head->tail = &t->next;
		__raise_softirq_irqoff(softirq_nr);
		local_irq_enable();
	}
}

tasklet

由于软中断必须使用可重入函数，这就导致设计上的复杂度变高，作为设备驱动程序的开发者来说，增加了负担。

而如果某种应用并不需要在多个CPU上并行执行，那么软中断其实是没有必要的。因此诞生了弥补以上两个要求的tasklet。它具有以下特性：

1. 一种特定类型的tasklet只能运行在一个CPU上，不能并行，只能串行执行。多个不同类型的tasklet可以并行在多个CPU上。

2. 软中断是静态分配的，在内核编译好之后，就不能改变。但tasklet就灵活许多，可以在运行时改变（比如添加模块时）。

tasklet是在两种软中断类型的基础上实现的(高优先级、低优先级)，因此如果不需要软中断的并行特性，tasklet就是最好的选择。

相关宏和结构体

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

struct tasklet_head {
	struct tasklet_struct *head;
	struct tasklet_struct **tail;
};

#define DECLARE_TASKLET(name, func, data) \
struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(0), func, data }

#define DECLARE_TASKLET_DISABLED(name, func, data) \
struct tasklet_struct name = { NULL, 0, ATOMIC_INIT(1), func, data }

示例

主要包括tasklet的定义和调度

static void kgdb_tasklet_bpt(unsigned long ing)
{
	kgdb_breakpoint();
	atomic_set(&kgdb_break_tasklet_var, 0);
}

static DECLARE_TASKLET(kgdb_tasklet_breakpoint, kgdb_tasklet_bpt, 0);

void kgdb_schedule_breakpoint(void)
{
	if (atomic_read(&kgdb_break_tasklet_var) ||
		atomic_read(&kgdb_active) != -1 ||
		atomic_read(&kgdb_setting_breakpoint))
		return;
	atomic_inc(&kgdb_break_tasklet_var);
	tasklet_schedule(&kgdb_tasklet_breakpoint);
}
EXPORT_SYMBOL_GPL(kgdb_schedule_breakpoint);

调度tasklet

1. 先通过__tasklet_schedule_common将tasklet加入tasklet_vec或者tasklet_hi_vec链表

2. 最终调用wakeup_softirqd唤醒软中断线程

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

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

void __tasklet_schedule(struct tasklet_struct *t)
{
	__tasklet_schedule_common(t, &tasklet_vec,
				  TASKLET_SOFTIRQ);
}
EXPORT_SYMBOL(__tasklet_schedule);

void __tasklet_hi_schedule(struct tasklet_struct *t)
{
	__tasklet_schedule_common(t, &tasklet_hi_vec,
				  HI_SOFTIRQ);
}
EXPORT_SYMBOL(__tasklet_hi_schedule);

static void __tasklet_schedule_common(struct tasklet_struct *t,
				      struct tasklet_head __percpu *headp,
				      unsigned int softirq_nr)
{
	struct tasklet_head *head;
	unsigned long flags;

	local_irq_save(flags);
	head = this_cpu_ptr(headp);
	t->next = NULL;
	*head->tail = t;
	head->tail = &(t->next);
	raise_softirq_irqoff(softirq_nr);
	local_irq_restore(flags);
}

inline void raise_softirq_irqoff(unsigned int nr)
{
	__raise_softirq_irqoff(nr);

	/*
	 * 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();
}