kernel/softirq.c

/*
 *	linux/kernel/softirq.c
 *
 *	Copyright (C) 1992 Linus Torvalds
 *
 * Rewritten. Old one was good in 2.2, but in 2.3 it was immoral. --ANK (990903)
 */

#include <linux/module.h>
#include <linux/kernel_stat.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/notifier.h>
#include <linux/percpu.h>
#include <linux/cpu.h>

/*
   - No shared variables, all the data are CPU local.
   - If a softirq needs serialization, let it serialize itself
     by its own spinlocks.
   - Even if softirq is serialized, only local cpu is marked for
     execution. Hence, we get something sort of weak cpu binding.
     Though it is still not clear, will it result in better locality
     or will not.

   Examples:
   - NET RX softirq. It is multithreaded and does not require
     any global serialization.
   - NET TX softirq. It kicks software netdevice queues, hence
     it is logically serialized per device, but this serialization
     is invisible to common code.
   - Tasklets: serialized wrt itself.
 */

#ifndef __ARCH_IRQ_STAT
irq_cpustat_t irq_stat[NR_CPUS] ____cacheline_aligned;
EXPORT_SYMBOL(irq_stat);
#endif

static struct softirq_action softirq_vec[32] __cacheline_aligned_in_smp;

static DEFINE_PER_CPU(struct task_struct *, ksoftirqd);

/*
 * we cannot loop indefinitely here to avoid userspace starvation,
 * but we also don't want to introduce a worst case 1/HZ latency
 * to the pending events, so lets the scheduler to balance
 * the softirq load for us.
 */
static inline void wakeup_softirqd(void)
{
	/* Interrupts are disabled: no need to stop preemption */
	struct task_struct *tsk = __get_cpu_var(ksoftirqd);

	if (tsk && tsk->state != TASK_RUNNING)
		wake_up_process(tsk);
}

/*
 * 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)
{
	int max_restart = MAX_SOFTIRQ_RESTART;
	__u32 pending;
	unsigned long flags;

	if (in_interrupt())
		return;

	local_irq_save(flags);

	pending = local_softirq_pending();

	if (pending) {
		struct softirq_action *h;

		local_bh_disable();
restart:
		/* Reset the pending bitmask before enabling irqs */
		local_softirq_pending() = 0;

		local_irq_enable();

		h = softirq_vec;

		do {
			if (pending & 1)
				h->action(h);
			h++;
			pending >>= 1;
		} while (pending);

		local_irq_disable();

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

	local_irq_restore(flags);
}

EXPORT_SYMBOL(do_softirq);

void local_bh_enable(void)
{
	__local_bh_enable();
	WARN_ON(irqs_disabled());
	if (unlikely(!in_interrupt() &&
		     local_softirq_pending()))
		invoke_softirq();
	preempt_check_resched();
}
EXPORT_SYMBOL(local_bh_enable);

/*
 * This function must run with irqs disabled!
 */
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();
}

EXPORT_SYMBOL(raise_softirq_irqoff);

void raise_softirq(unsigned int nr)
{
	unsigned long flags;

	local_irq_save(flags);
	raise_softirq_irqoff(nr);
	local_irq_restore(flags);
}

EXPORT_SYMBOL(raise_softirq);

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

EXPORT_SYMBOL(open_softirq);

/* Tasklets */
struct tasklet_head
{
	struct tasklet_struct *list;
};

/* Some compilers disobey section attribute on statics when not
   initialized -- RR */
static DEFINE_PER_CPU(struct tasklet_head, tasklet_vec) = { NULL };
static DEFINE_PER_CPU(struct tasklet_head, tasklet_hi_vec) = { NULL };

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

	local_irq_save(flags);
	t->next = __get_cpu_var(tasklet_vec).list;
	__get_cpu_var(tasklet_vec).list = t;
	raise_softirq_irqoff(TASKLET_SOFTIRQ);
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__tasklet_schedule);

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

	local_irq_save(flags);
	t->next = __get_cpu_var(tasklet_hi_vec).list;
	__get_cpu_var(tasklet_hi_vec).list = t;
	raise_softirq_irqoff(HI_SOFTIRQ);
	local_irq_restore(flags);
}

EXPORT_SYMBOL(__tasklet_hi_schedule);

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

	local_irq_disable();
	list = __get_cpu_var(tasklet_vec).list;
	__get_cpu_var(tasklet_vec).list = NULL;
	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 = __get_cpu_var(tasklet_vec).list;
		__get_cpu_var(tasklet_vec).list = t;
		__raise_softirq_irqoff(TASKLET_SOFTIRQ);
		local_irq_enable();
	}
}

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

	local_irq_disable();
	list = __get_cpu_var(tasklet_hi_vec).list;
	__get_cpu_var(tasklet_hi_vec).list = NULL;
	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 = __get_cpu_var(tasklet_hi_vec).list;
		__get_cpu_var(tasklet_hi_vec).list = t;
		__raise_softirq_irqoff(HI_SOFTIRQ);
		local_irq_enable();
	}
}


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;
}

EXPORT_SYMBOL(tasklet_init);

void tasklet_kill(struct tasklet_struct *t)
{
	if (in_interrupt())
		printk("Attempt to kill tasklet from interrupt\n");

	while (test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) {
		do
			yield();
		while (test_bit(TASKLET_STATE_SCHED, &t->state));
	}
	tasklet_unlock_wait(t);
	clear_bit(TASKLET_STATE_SCHED, &t->state);
}

EXPORT_SYMBOL(tasklet_kill);

static void tasklet_init_cpu(int cpu)
{
	per_cpu(tasklet_vec, cpu).list = NULL;
	per_cpu(tasklet_hi_vec, cpu).list = NULL;
}
	
static int tasklet_cpu_notify(struct notifier_block *self, 
				unsigned long action, void *hcpu)
{
	long cpu = (long)hcpu;
	switch(action) {
	case CPU_UP_PREPARE:
		tasklet_init_cpu(cpu);
		break;
	default:
		break;
	}
	return 0;
}

static struct notifier_block tasklet_nb = {
	.notifier_call	= tasklet_cpu_notify,
	.next		= NULL,
};

void __init softirq_init(void)
{
	open_softirq(TASKLET_SOFTIRQ, tasklet_action, NULL);
	open_softirq(HI_SOFTIRQ, tasklet_hi_action, NULL);
	tasklet_cpu_notify(&tasklet_nb, (unsigned long)CPU_UP_PREPARE,
				(void *)(long)smp_processor_id());
	register_cpu_notifier(&tasklet_nb);
}

static int ksoftirqd(void * __bind_cpu)
{
	int cpu = (int) (long) __bind_cpu;

	daemonize("ksoftirqd/%d", cpu);
	set_user_nice(current, 19);
	current->flags |= PF_IOTHREAD;

	/* Migrate to the right CPU */
	set_cpus_allowed(current, cpumask_of_cpu(cpu));
	BUG_ON(smp_processor_id() != cpu);

	__set_current_state(TASK_INTERRUPTIBLE);
	mb();

	__get_cpu_var(ksoftirqd) = current;

	for (;;) {
		if (!local_softirq_pending())
			schedule();

		__set_current_state(TASK_RUNNING);

		while (local_softirq_pending()) {
			do_softirq();
			cond_resched();
		}

		__set_current_state(TASK_INTERRUPTIBLE);
	}
}

static int __devinit cpu_callback(struct notifier_block *nfb,
				  unsigned long action,
				  void *hcpu)
{
	int hotcpu = (unsigned long)hcpu;

	if (action == CPU_ONLINE) {
		if (kernel_thread(ksoftirqd, hcpu, CLONE_KERNEL) < 0) {
			printk("ksoftirqd for %i failed\n", hotcpu);
			return NOTIFY_BAD;
		}

		while (!per_cpu(ksoftirqd, hotcpu))
			yield();
 	}
	return NOTIFY_OK;
}

static struct notifier_block __devinitdata cpu_nfb = {
	.notifier_call = cpu_callback
};

__init int spawn_ksoftirqd(void)
{
	cpu_callback(&cpu_nfb, CPU_ONLINE, (void *)(long)smp_processor_id());
	register_cpu_notifier(&cpu_nfb);
	return 0;
}