源码剖析之epoll(2)

1. 源码剖析

本篇主要分析epoll_ctl以及相关函数

以下源码取自4.10

1.1 epoll_ctl

用于添加/调整/删除我们要监视的事件

fs/eventpoll.c

/*
 * The following function implements the controller interface for
 * the eventpoll file that enables the insertion/removal/change of
 * file descriptors inside the interest set.
 */
SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
        struct epoll_event __user *, event)
{
    int error;
    int full_check = 0;
    struct fd f, tf;
    struct eventpoll *ep;
    struct epitem *epi;
    struct epoll_event epds;
    struct eventpoll *tep = NULL;

    error = -EFAULT;
    /* 调用copy_from_user获得我们关注的事件 */
    if (ep_op_has_event(op) &&
        copy_from_user(&epds, event, sizeof(struct epoll_event)))
        goto error_return;

    error = -EBADF;
    f = fdget(epfd);
    if (!f.file)
        goto error_return;

    /* Get the "struct file *" for the target file */
    tf = fdget(fd);
    if (!tf.file)
        goto error_fput;

    /* The target file descriptor must support poll */
    error = -EPERM;
    if (!tf.file->f_op->poll)
        goto error_tgt_fput;

    /* Check if EPOLLWAKEUP is allowed */
    if (ep_op_has_event(op))
        ep_take_care_of_epollwakeup(&epds);

    /*
     * We have to check that the file structure underneath the file descriptor
     * the user passed to us _is_ an eventpoll file. And also we do not permit
     * adding an epoll file descriptor inside itself.
     */
    error = -EINVAL;
    if (f.file == tf.file || !is_file_epoll(f.file))
        goto error_tgt_fput;

    /*
     * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only,
     * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
     * Also, we do not currently supported nested exclusive wakeups.
     */
    if (epds.events & EPOLLEXCLUSIVE) {
        if (op == EPOLL_CTL_MOD)
            goto error_tgt_fput;
        if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
                (epds.events & ~EPOLLEXCLUSIVE_OK_BITS)))
            goto error_tgt_fput;
    }

    /*
     * At this point it is safe to assume that the "private_data" contains
     * our own data structure.
     */
    ep = f.file->private_data;

    /*
     * When we insert an epoll file descriptor, inside another epoll file
     * descriptor, there is the change of creating closed loops, which are
     * better be handled here, than in more critical paths. While we are
     * checking for loops we also determine the list of files reachable
     * and hang them on the tfile_check_list, so we can check that we
     * haven't created too many possible wakeup paths.
     *
     * We do not need to take the global 'epumutex' on EPOLL_CTL_ADD when
     * the epoll file descriptor is attaching directly to a wakeup source,
     * unless the epoll file descriptor is nested. The purpose of taking the
     * 'epmutex' on add is to prevent complex toplogies such as loops and
     * deep wakeup paths from forming in parallel through multiple
     * EPOLL_CTL_ADD operations.
     */
    mutex_lock_nested(&ep->mtx, 0);
    if (op == EPOLL_CTL_ADD) {
        if (!list_empty(&f.file->f_ep_links) ||
                        is_file_epoll(tf.file)) {
            full_check = 1;
            mutex_unlock(&ep->mtx);
            mutex_lock(&epmutex);
            if (is_file_epoll(tf.file)) {
                error = -ELOOP;
                if (ep_loop_check(ep, tf.file) != 0) {
                    clear_tfile_check_list();
                    goto error_tgt_fput;
                }
            } else
                list_add(&tf.file->f_tfile_llink,
                            &tfile_check_list);
            mutex_lock_nested(&ep->mtx, 0);
            if (is_file_epoll(tf.file)) {
                tep = tf.file->private_data;
                mutex_lock_nested(&tep->mtx, 1);
            }
        }
    }

    /*
     * Try to lookup the file inside our RB tree, Since we grabbed "mtx"
     * above, we can be sure to be able to use the item looked up by
     * ep_find() till we release the mutex.
     */
    epi = ep_find(ep, tf.file, fd);

    error = -EINVAL;
    switch (op) {
    case EPOLL_CTL_ADD:
        if (!epi) {
            epds.events |= POLLERR | POLLHUP;
            error = ep_insert(ep, &epds, tf.file, fd, full_check);
        } else
            error = -EEXIST;
        if (full_check)
            clear_tfile_check_list();
        break;
    case EPOLL_CTL_DEL:
        if (epi)
            error = ep_remove(ep, epi);
        else
            error = -ENOENT;
        break;
    case EPOLL_CTL_MOD:
        if (epi) {
            if (!(epi->event.events & EPOLLEXCLUSIVE)) {
                epds.events |= POLLERR | POLLHUP;
                error = ep_modify(ep, epi, &epds);
            }
        } else
            error = -ENOENT;
        break;
    }
    if (tep != NULL)
        mutex_unlock(&tep->mtx);
    mutex_unlock(&ep->mtx);

error_tgt_fput:
    if (full_check)
        mutex_unlock(&epmutex);

    fdput(tf);
error_fput:
    fdput(f);
error_return:

    return error;
}

1.2 ep_insert

fs/eventpoll.c

static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
             struct file *tfile, int fd, int full_check)
{
    int error, revents, pwake = 0;
    unsigned long flags;
    long user_watches;
    struct epitem *epi;
    struct ep_pqueue epq;

    // 检测目前监视数量是否超过限制
    user_watches = atomic_long_read(&ep->user->epoll_watches);
    if (unlikely(user_watches >= max_user_watches))
        return -ENOSPC;

    // 从slab中分配空间用于存储epitem
    if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
        return -ENOMEM;

    /* Item initialization follow here ... */
    INIT_LIST_HEAD(&epi->rdllink);
    INIT_LIST_HEAD(&epi->fllink);
    INIT_LIST_HEAD(&epi->pwqlist);
    epi->ep = ep;

    /* 设置epitem在RB-Tree中的key */
    ep_set_ffd(&epi->ffd, tfile, fd);
    epi->event = *event;
    epi->nwait = 0;
    epi->next = EP_UNACTIVE_PTR;
    if (epi->event.events & EPOLLWAKEUP) {
        error = ep_create_wakeup_source(epi);
        if (error)
            goto error_create_wakeup_source;
    } else {
        RCU_INIT_POINTER(epi->ws, NULL);
    }

    /* Initialize the poll table using the queue callback */
    epq.epi = epi;
    /* 用ep_ptable_queue_proc作为poll的回调函数 */
    /* 回调函数的作用是将该epitem加入的文件的等待队列中去 */
    init_poll_funcptr(&epq.pt, ep_ptable_queue_proc);

    /*
     * Attach the item to the poll hooks and get current event bits.
     * We can safely use the file* here because its usage count has
     * been increased by the caller of this function. Note that after
     * this operation completes, the poll callback can start hitting
     * the new item.
     * 获取文件当前就绪事件的掩码，并执行poll的回调函数ep_ptable_queue_proc 
     */
    revents = ep_item_poll(epi, &epq.pt);

    /*
     * We have to check if something went wrong during the poll wait queue
     * install process. Namely an allocation for a wait queue failed due
     * high memory pressure.
     */
    error = -ENOMEM;
    if (epi->nwait < 0)
        goto error_unregister;

    /**
     * Add the current item to the list of active epoll hook for this file 
     * 文件会链接所有监听自己的epitem，把当前epitem加入到文件的链表中
     */
    spin_lock(&tfile->f_lock);
    list_add_tail_rcu(&epi->fllink, &tfile->f_ep_links);
    spin_unlock(&tfile->f_lock);

    /*
     * Add the current item to the RB tree. All RB tree operations are
     * protected by "mtx", and ep_insert() is called with "mtx" held.
     * 将epitem插入到eventpoll的RB-Tree中
     */
    ep_rbtree_insert(ep, epi);

    /* now check if we've created too many backpaths */
    error = -EINVAL;
    if (full_check && reverse_path_check())
        goto error_remove_epi;

    /* We have to drop the new item inside our item list to keep track of it */
    spin_lock_irqsave(&ep->lock, flags);

    /* If the file is already "ready" we drop it inside the ready list */
    if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {

        /* 将epitem加入到对应eventpoll的就绪链表中 */
        list_add_tail(&epi->rdllink, &ep->rdllist);
        ep_pm_stay_awake(epi);

        /* Notify waiting tasks that events are available */
        /* 唤醒所有阻塞与epoll_wait调用的所有进程/线程 */
        if (waitqueue_active(&ep->wq))
            wake_up_locked(&ep->wq);

        /* 唤醒阻塞于epoll该eventpoll的所有进程/线程 */
        if (waitqueue_active(&ep->poll_wait))
            pwake++;
    }

    spin_unlock_irqrestore(&ep->lock, flags);

    atomic_long_inc(&ep->user->epoll_watches);

    /* We have to call this outside the lock */
    if (pwake)
        ep_poll_safewake(&ep->poll_wait);

    return 0;

error_remove_epi:
    spin_lock(&tfile->f_lock);
    list_del_rcu(&epi->fllink);
    spin_unlock(&tfile->f_lock);

    rb_erase(&epi->rbn, &ep->rbr);

error_unregister:
    ep_unregister_pollwait(ep, epi);

    /*
     * We need to do this because an event could have been arrived on some
     * allocated wait queue. Note that we don't care about the ep->ovflist
     * list, since that is used/cleaned only inside a section bound by "mtx".
     * And ep_insert() is called with "mtx" held.
     */
    spin_lock_irqsave(&ep->lock, flags);
    if (ep_is_linked(&epi->rdllink))
        list_del_init(&epi->rdllink);
    spin_unlock_irqrestore(&ep->lock, flags);

    wakeup_source_unregister(ep_wakeup_source(epi));

error_create_wakeup_source:
    kmem_cache_free(epi_cache, epi);

    return error;
}

/** 
 * ffd.file->f_op->poll的warpper
 * 调用poll_table中指定的回调函数
 * 如果文件当前发生了epitem的关心事件，返回事件掩码
 */
static inline unsigned int ep_item_poll(struct epitem *epi, poll_table *pt)
{
    pt->_key = epi->event.events;

    /**
     * 调用被监视文件对应的poll函数
     * 如果是tcp socket，那么调用tcp_poll
     * 如果是udp socket，那么调用udp_poll
     */
    return epi->ffd.file->f_op->poll(epi->ffd.file, pt) & epi->event.events;
}

1.3 tcp_poll

net/ipv4/tcp.c

unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
{
    unsigned int mask;
    struct sock *sk = sock->sk;
    const struct tcp_sock *tp = tcp_sk(sk);
    int state;

    sock_rps_record_flow(sk);

    /* 通过sk_sleep(sk)的得到该文件的等待队列作为第二个参数 */
    /* 最终以同样的这三个参数调用poll_wait */
    sock_poll_wait(file, sk_sleep(sk), wait);
    // code omitted
    return mask;
}

1.4 sk_sleep

该函数返回socket文件的的等待队列

include/net/sock.h

static inline wait_queue_head_t *sk_sleep(struct sock *sk)
{
    BUILD_BUG_ON(offsetof(struct socket_wq, wait) != 0);
    return &rcu_dereference_raw(sk->sk_wq)->wait;
}

1.5 poll_wait

该函数会调用poll_table->_qproc函数

include/linux/poll.h

static inline void poll_wait(struct file * filp, wait_queue_head_t * wait_address, poll_table *p)
{
    /* 如果poll_table中指定函数不为空，那么就调用该函数，否则什么也不做 */
    if (p && p->_qproc && wait_address)
        p->_qproc(filp, wait_address, p);
}

1.6 ep_ptable_queue_proc

该函数是的作用是将包含epitem信息的等待队列项加入文件的等待队列

fs/eventpoll.c

/*
 * This is the callback that is used to add our wait queue to the
 * target file wakeup lists.
 */
static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead,
                 poll_table *pt)
{
    struct epitem *epi = ep_item_from_epqueue(pt);
    /* 用于关联epitem/wait_queue_t/wait_queue_head_t三者，以便在回调的时候能找到 */
    struct eppoll_entry *pwq;

    if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
        /* 设置等待队列项的回调函数为ep_poll_callback */
        init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
        pwq->whead = whead;
        pwq->base = epi;

        /* 将配置好的等待队列项加入对应的等待队列中去 */
        if (epi->event.events & EPOLLEXCLUSIVE)
            add_wait_queue_exclusive(whead, &pwq->wait);
        else
            add_wait_queue(whead, &pwq->wait);

        /* 关联epitem和epoll_entry */
        list_add_tail(&pwq->llink, &epi->pwqlist);
        epi->nwait++;
    } else {
        /* We have to signal that an error occurred */
        epi->nwait = -1;
    }
}

1.7 ep_poll_callback

该函数是当文件有事件发生时的回调函数

fs/eventpoll.c

/*
 * This is the callback that is passed to the wait queue wakeup
 * mechanism. It is called by the stored file descriptors when they
 * have events to report.
 */
static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
{
    int pwake = 0;
    unsigned long flags;
    struct epitem *epi = ep_item_from_wait(wait);
    struct eventpoll *ep = epi->ep;
    int ewake = 0;

    if ((unsigned long)key & POLLFREE) {
        ep_pwq_from_wait(wait)->whead = NULL;
        /*
         * whead = NULL above can race with ep_remove_wait_queue()
         * which can do another remove_wait_queue() after us, so we
         * can't use __remove_wait_queue(). whead->lock is held by
         * the caller.
         */
        list_del_init(&wait->task_list);
    }

    spin_lock_irqsave(&ep->lock, flags);

    /*
     * If the event mask does not contain any poll(2) event, we consider the
     * descriptor to be disabled. This condition is likely the effect of the
     * EPOLLONESHOT bit that disables the descriptor when an event is received,
     * until the next EPOLL_CTL_MOD will be issued.
     */
    if (!(epi->event.events & ~EP_PRIVATE_BITS))
        goto out_unlock;

    /*
     * Check the events coming with the callback. At this stage, not
     * every device reports the events in the "key" parameter of the
     * callback. We need to be able to handle both cases here, hence the
     * test for "key" != NULL before the event match test.
     */
    if (key && !((unsigned long) key & epi->event.events))
        goto out_unlock;

    /*
     * If we are transferring events to userspace, we can hold no locks
     * (because we're accessing user memory, and because of linux f_op->poll()
     * semantics). All the events that happen during that period of time are
     * chained in ep->ovflist and requeued later on.
     */
    if (unlikely(ep->ovflist != EP_UNACTIVE_PTR)) {
        if (epi->next == EP_UNACTIVE_PTR) {
            epi->next = ep->ovflist;
            ep->ovflist = epi;
            if (epi->ws) {
                /*
                 * Activate ep->ws since epi->ws may get
                 * deactivated at any time.
                 */
                __pm_stay_awake(ep->ws);
            }

        }
        goto out_unlock;
    }

    /* If this file is already in the ready list we exit soon */
    if (!ep_is_linked(&epi->rdllink)) {
        list_add_tail(&epi->rdllink, &ep->rdllist);
        ep_pm_stay_awake_rcu(epi);
    }

    /*
     * Wake up ( if active ) both the eventpoll wait list and the ->poll()
     * wait list.
     */
    if (waitqueue_active(&ep->wq)) {
        if ((epi->event.events & EPOLLEXCLUSIVE) &&
                    !((unsigned long)key & POLLFREE)) {
            switch ((unsigned long)key & EPOLLINOUT_BITS) {
            case POLLIN:
                if (epi->event.events & POLLIN)
                    ewake = 1;
                break;
            case POLLOUT:
                if (epi->event.events & POLLOUT)
                    ewake = 1;
                break;
            case 0:
                ewake = 1;
                break;
            }
        }
        /* 唤醒阻塞于epoll_wait和epoll_pwait调用的进程/线程 */
        wake_up_locked(&ep->wq);
    }
    /* 唤醒阻塞于poll该eventpoll的进程/线程 */
    if (waitqueue_active(&ep->poll_wait))
        pwake++;

out_unlock:
    spin_unlock_irqrestore(&ep->lock, flags);

    /* We have to call this outside the lock */
    if (pwake)
        ep_poll_safewake(&ep->poll_wait);

    if (epi->event.events & EPOLLEXCLUSIVE)
        return ewake;

    return 1;
}

1.8 ep_modify

由于ep_modify和ep_insert类似，所以不具体分析了

fs/eventpoll.c

/*
 * Modify the interest event mask by dropping an event if the new mask
 * has a match in the current file status. Must be called with "mtx" held.
 */
static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_event *event)
{
    int pwake = 0;
    unsigned int revents;
    poll_table pt;

    init_poll_funcptr(&pt, NULL);

    /*
     * Set the new event interest mask before calling f_op->poll();
     * otherwise we might miss an event that happens between the
     * f_op->poll() call and the new event set registering.
     */
    epi->event.events = event->events; /* need barrier below */
    epi->event.data = event->data; /* protected by mtx */
    if (epi->event.events & EPOLLWAKEUP) {
        if (!ep_has_wakeup_source(epi))
            ep_create_wakeup_source(epi);
    } else if (ep_has_wakeup_source(epi)) {
        ep_destroy_wakeup_source(epi);
    }

    /*
     * The following barrier has two effects:
     *
     * 1) Flush epi changes above to other CPUs.  This ensures
     *    we do not miss events from ep_poll_callback if an
     *    event occurs immediately after we call f_op->poll().
     *    We need this because we did not take ep->lock while
     *    changing epi above (but ep_poll_callback does take
     *    ep->lock).
     *
     * 2) We also need to ensure we do not miss _past_ events
     *    when calling f_op->poll().  This barrier also
     *    pairs with the barrier in wq_has_sleeper (see
     *    comments for wq_has_sleeper).
     *
     * This barrier will now guarantee ep_poll_callback or f_op->poll
     * (or both) will notice the readiness of an item.
     */
    smp_mb();

    /*
     * Get current event bits. We can safely use the file* here because
     * its usage count has been increased by the caller of this function.
     */
    revents = ep_item_poll(epi, &pt);

    /*
     * If the item is "hot" and it is not registered inside the ready
     * list, push it inside.
     */
    if (revents & event->events) {
        spin_lock_irq(&ep->lock);
        if (!ep_is_linked(&epi->rdllink)) {
            list_add_tail(&epi->rdllink, &ep->rdllist);
            ep_pm_stay_awake(epi);

            /* Notify waiting tasks that events are available */
            if (waitqueue_active(&ep->wq))
                wake_up_locked(&ep->wq);
            if (waitqueue_active(&ep->poll_wait))
                pwake++;
        }
        spin_unlock_irq(&ep->lock);
    }

    /* We have to call this outside the lock */
    if (pwake)
        ep_poll_safewake(&ep->poll_wait);

    return 0;
}