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);
            }
        }