linux 中断线程化

为什么要进行中断线程化?
在 Linux 中，中断具有最高的优先级。不论在任何时刻，只要产生中断事件，内核将立即执行相应的中断处理程序，等到所有挂起的中断和软中断处理完毕后才能执行正常的任务，因此有可能造成实时任务得不到及时的处理。中断线程化之后，中断将作为内核线程运行而且被赋予不同的实时优先级，实时任务可以有比中断线程更高的优先级。这样，具有最高优先级的实时任务就能得到优先处理，即使在严重负载下仍有实时性保证。但是,并不是所有的中断都可以被线程化，比如时钟中断，主要用来维护系统时间以及定时器等，其中定时器是操作系统的脉搏，一旦被线程化，就有可能被挂起，这样后果将不堪设想，所以不应当被线程化。

中断线程化的实现方法是：对于IRQ，在内核初始化阶段init（该函数在内核源码树的文件init/main.c中定义）调用init_hardirqs（该函数在内核源码树的文件kernel/irq/manage.c中定义）来为每一个IRQ创建一个内核线程，IRQ号为0 的中断赋予实时优先级49，IRQ号为1的赋予实时优先级48，依次类推直到25，因此任何IRQ线程的最低实时优先级为25。原来的do_IRQ被分解成两部分，架构相关的放在类似于arch/*/kernel/irq.c的文件中，名称仍然为do_IRQ，而架构独立的部分被放在IRQ子系统的位置 kernel/irq/handle.c中，名称为_do_IRQ。当发生中断时，CPU将执行do_IRQ来处理相应的中断，do_IRQ将做了必要的架构相关的处理后调用_do_IRQ。函数_do_IRQ将判断该中断是否已经被线程化（如果中断描述符的状态字段不包含SA_NODELAY标志说明中断被线程化了），如果是将唤醒相应的处理线程，否则将直接调用handle_IRQ_event（在IRQ子系统位置的kernel/irq /handle.c文件中）来处理。对于已经线程化的情况，中断处理线程被唤醒并开始运行后，将调用do_hardirq(在源码树的IRQ子系统位置的文件kernel/irq/manage.c中定义)来处理相应的中断，该函数将判断是否有中断需要被处理（中断描述符的状态标志 IRQ_INPROGRESS），如果有就调用handle_IRQ_event来处理。handle_IRQ_event将直接调用相应的中断处理句柄来完成中断处理。

申请中断request_irq()与request_threaded_irq()之间的区别？

static inline int __must_check
request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
    const char *name, void *dev)
{
return request_threaded_irq(irq, handler, NULL, flags, name, dev);
}

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)

从定义可以看出request_irq是request_threaded_irq的一个wrapper，只是将其中的thread_fn置为空。

request_threaded_irq函数实现：

/**
 *  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
 */
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;
}

其中调用了__setup_irq 函数，该函数内容如下：

/*
 * 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;
}

其中函数setup_irq_thread 为中断创建了线程，函数内容如下：

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, ¶m);

    /*
     * 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;
}

从函数中可以看到kthread_create 实现了中断线程的创建。

申请中断其它函数原型还有 devm_request_threaded_irq

/**
 *  devm_request_threaded_irq - allocate an interrupt line for a managed device
 */
int devm_request_threaded_irq(struct device *dev, unsigned int irq,
                  irq_handler_t handler, irq_handler_t thread_fn,
                  unsigned long irqflags, const char *devname,
                  void *dev_id)
{
    struct irq_devres *dr;
    int rc;

    dr = devres_alloc(devm_irq_release, sizeof(struct irq_devres),
              GFP_KERNEL);
    if (!dr)
        return -ENOMEM;

    rc = request_threaded_irq(irq, handler, thread_fn, irqflags, devname,
                  dev_id);
    if (rc) {
        devres_free(dr);
        return rc;
    }

    dr->irq = irq;
    dr->dev_id = dev_id;
    devres_add(dev, dr);

    return 0;
}

可以看到devm_request_threaded 也是通过irqrequest_threaded_irq 来实现中断线程的。