/* Init poll structure */
void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
unsigned long mask)
{
INIT_WORK(&poll->work, func);
init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
init_poll_funcptr(&poll->table, vhost_poll_func);
poll->mask = mask;
}
static void scif_poll_initwait(struct poll_wqueues *pwq)
{
init_poll_funcptr(&pwq->pt, __pollwait);
pwq->polling_task = current;
pwq->triggered = 0;
pwq->error = 0;
pwq->table = NULL;
pwq->inline_index = 0;
}
/* Init poll structure */
void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn,
unsigned long mask, struct vhost_dev *dev)
{
init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
init_poll_funcptr(&poll->table, vhost_poll_func);
poll->mask = mask;
poll->dev = dev;
vhost_work_init(&poll->work, fn);
}
static int virqfd_enable(struct vfio_pci_device *vdev,
int (*handler)(struct vfio_pci_device *, void *),
void (*thread)(struct vfio_pci_device *, void *),
void *data, struct virqfd **pvirqfd, int fd)
{
struct fd irqfd;
struct eventfd_ctx *ctx;
struct virqfd *virqfd;
int ret = 0;
unsigned int events;
virqfd = kzalloc(sizeof(*virqfd), GFP_KERNEL);
if (!virqfd)
return -ENOMEM;
virqfd->pvirqfd = pvirqfd;
virqfd->vdev = vdev;
virqfd->handler = handler;
virqfd->thread = thread;
virqfd->data = data;
INIT_WORK(&virqfd->shutdown, virqfd_shutdown);
INIT_WORK(&virqfd->inject, virqfd_inject);
irqfd = fdget(fd);
if (!irqfd.file) {
ret = -EBADF;
goto err_fd;
}
ctx = eventfd_ctx_fileget(irqfd.file);
if (IS_ERR(ctx)) {
ret = PTR_ERR(ctx);
goto err_ctx;
}
virqfd->eventfd = ctx;
/*
* virqfds can be released by closing the eventfd or directly
* through ioctl. These are both done through a workqueue, so
* we update the pointer to the virqfd under lock to avoid
* pushing multiple jobs to release the same virqfd.
*/
spin_lock_irq(&vdev->irqlock);
if (*pvirqfd) {
spin_unlock_irq(&vdev->irqlock);
ret = -EBUSY;
goto err_busy;
}
*pvirqfd = virqfd;
spin_unlock_irq(&vdev->irqlock);
/*
* Install our own custom wake-up handling so we are notified via
* a callback whenever someone signals the underlying eventfd.
*/
init_waitqueue_func_entry(&virqfd->wait, virqfd_wakeup);
init_poll_funcptr(&virqfd->pt, virqfd_ptable_queue_proc);
events = irqfd.file->f_op->poll(irqfd.file, &virqfd->pt);
/*
* Check if there was an event already pending on the eventfd
* before we registered and trigger it as if we didn't miss it.
*/
if (events & POLLIN) {
if ((!handler || handler(vdev, data)) && thread)
schedule_work(&virqfd->inject);
}
/*
* Do not drop the file until the irqfd is fully initialized,
* otherwise we might race against the POLLHUP.
*/
fdput(irqfd);
return 0;
err_busy:
eventfd_ctx_put(ctx);
err_ctx:
fdput(irqfd);
err_fd:
kfree(virqfd);
return ret;
}
void poll_initwait(struct poll_wqueues *pwq)
{
init_poll_funcptr(&pwq->pt, __pollwait);
pwq->error = 0;
pwq->table = NULL;
}
/*
* ep_insert()在epoll_ctl()中被调用, 完成往epollfd里面添加一个监听fd的工作
* tfile是fd在内核态的struct file结构
*/
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
struct file *tfile, int fd)
{
int error, revents, pwake = 0;
unsigned long flags;
struct epitem *epi;
struct ep_pqueue epq;
/* 查看是否达到当前用户的最大监听数 */
if (unlikely(atomic_read(&ep->user->epoll_watches) >=
max_user_watches))
return -ENOSPC;
/* 从著名的slab中分配一个epitem */
if (!(epi = kmem_cache_alloc(epi_cache, GFP_KERNEL)))
return -ENOMEM;
/* Item initialization follow here ... */
/* 这些都是相关成员的初始化... */
INIT_LIST_HEAD(&epi->rdllink);
INIT_LIST_HEAD(&epi->fllink);
INIT_LIST_HEAD(&epi->pwqlist);
epi->ep = ep;
/* 这里保存了我们需要监听的文件fd和它的file结构 */
ep_set_ffd(&epi->ffd, tfile, fd);
epi->event = *event;
epi->nwait = 0;
/* 这个指针的初值不是NULL哦... */
epi->next = EP_UNACTIVE_PTR;
/* Initialize the poll table using the queue callback */
/* 好, 我们终于要进入到poll的正题了 */
epq.epi = epi;
/* 初始化一个poll_table
* 其实就是指定调用poll_wait(注意不是epoll_wait!!!)时的回调函数,和我们关心哪些events,
* ep_ptable_queue_proc()就是我们的回调啦, 初值是所有event都关心 */
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.
*/
/* 这一部很关键, 也比较难懂, 完全是内核的poll机制导致的...
* 首先, f_op->poll()一般来说只是个wrapper, 它会调用真正的poll实现,
* 拿UDP的socket来举例, 这里就是这样的调用流程: f_op->poll(), sock_poll(),
* udp_poll(), datagram_poll(), sock_poll_wait(), 最后调用到我们上面指定的
* ep_ptable_queue_proc()这个回调函数...(好深的调用路径...).
* 完成这一步, 我们的epitem就跟这个socket关联起来了, 当它有状态变化时,
* 会通过ep_poll_callback()来通知.
* 最后, 这个函数还会查询当前的fd是不是已经有啥event已经ready了, 有的话
* 会将event返回. */
revents = tfile->f_op->poll(tfile, &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 */
/* 这个就是每个文件会将所有监听自己的epitem链起来 */
spin_lock(&tfile->f_lock);
list_add_tail(&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.
*/
/* 都搞定后, 将epitem插入到对应的eventpoll中去 */
ep_rbtree_insert(ep, 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 */
/* 到达这里后, 如果我们监听的fd已经有事件发生, 那就要处理一下 */
if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
/* 将当前的epitem加入到ready list中去 */
list_add_tail(&epi->rdllink, &ep->rdllist);
/* Notify waiting tasks that events are available */
/* 谁在epoll_wait, 就唤醒它... */
if (waitqueue_active(&ep->wq))
wake_up_locked(&ep->wq);
/* 谁在epoll当前的epollfd, 也唤醒它... */
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
spin_unlock_irqrestore(&ep->lock, flags);
atomic_inc(&ep->user->epoll_watches);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&ep->poll_wait);
return 0;
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);
kmem_cache_free(epi_cache, epi);
return error;
}