epoll边沿触发和水平触发源码分析

昨天面试被文档epoll相关内容，回答的很差，又被鄙视了，回来下载了源码分析了一下，好多看不懂的内容，留待分析，先总结一下分析完成的部分。

参考代码内核版本：linux-4.4.73

水平触发会不断发送OK状态到ready队列中，边沿触发只发送一次

1、epoll_create:

/*
 * Open an eventpoll file descriptor.
 */

SYSCALL_DEFINE1(epoll_create, int, size)
{
if (size <= 0)
return -EINVAL;  //size变量没有实际使用，只做了大于0的判断，新版本不需要这个参数但为了兼容老版本的内核保留这个参数。

// 参见：http://www.man7.org/linux/man-pages/man2/epoll_create.2.html的note部分

return sys_epoll_create1(0); 
}

SYSCALL_DEFINE1(epoll_create1, int, flags)
{
int error, fd;
struct eventpoll *ep = NULL;
struct file *file;


/* Check the EPOLL_* constant for consistency.  */
BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC);


if (flags & ~EPOLL_CLOEXEC)
return -EINVAL;
/*
* Create the internal data structure ("struct eventpoll").
*/
error = ep_alloc(&ep);//创建eventpoll结构体完成初始化
if (error < 0)
return error;
/*
* Creates all the items needed to setup an eventpoll file. That is,
* a file structure and a free file descriptor.
*/
fd = get_unused_fd_flags(O_RDWR | (flags & O_CLOEXEC));//获取一个未使用的文件描述符
if (fd < 0) {
error = fd;
goto out_free_ep;
}
file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,//创建一个内部使用非完整的文件，此处有内部简化文件，详情待分析
O_RDWR | (flags & O_CLOEXEC));
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto out_free_fd;
}
ep->file = file;
fd_install(fd, file);//设置文件和fd到当前任务的文件fd列表
return fd;


out_free_fd:
put_unused_fd(fd);
out_free_ep:
ep_free(ep);
return error;
}

2、epoll_ctl

/*
 * 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;
if (ep_op_has_event(op) &&
   copy_from_user(&epds, event, sizeof(struct epoll_event)))//从用户空间拷贝内容到内核空间
goto error_return;


error = -EBADF;
f = fdget(epfd);//文件epfd属性校验 详情待分析
if (!f.file)
goto error_return;


/* Get the "struct file *" for the target file */
tf = fdget(fd);//文件fd属性校验 详情待分析
if (!tf.file)
goto error_fput;


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


/* Check if EPOLLWAKEUP is allowed */
if (ep_op_has_event(op))
ep_take_care_of_epollwakeup(&epds);//校验设置EPOLLWAKEUP 待分析完整应用


/*
* 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))//epoll文件校验，见注释
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;//获取epoll结构体指针


/*
* 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);//添加互斥锁  该段内容待分析，可参照注释
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);//获取存在的epi


error = -EINVAL;
switch (op) {
case EPOLL_CTL_ADD://添加的处理过程
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://删除处理过程
if (epi)
error = ep_remove(ep, epi);
else
error = -ENOENT;
break;
case EPOLL_CTL_MOD://修改处理过程
if (epi) {
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;
}

3、epoll_wait

/*
 * Implement the event wait interface for the eventpoll file. It is the kernel
 * part of the user space epoll_wait(2).
 */
SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
int, maxevents, int, timeout)
{
int error;
struct fd f;
struct eventpoll *ep;


/* The maximum number of event must be greater than zero */
if (maxevents <= 0 || maxevents > EP_MAX_EVENTS)//校验maxevents参数
return -EINVAL;


/* Verify that the area passed by the user is writeable */
if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event)))//校验event参数
return -EFAULT;


/* Get the "struct file *" for the eventpoll file */
f = fdget(epfd);//校验epfd参数
if (!f.file)
return -EBADF;


/*
* We have to check that the file structure underneath the fd
* the user passed to us _is_ an eventpoll file.
*/
error = -EINVAL;
if (!is_file_epoll(f.file))
goto error_fput;


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


/* Time to fish for events ... */
error = ep_poll(ep, events, maxevents, timeout);//执行poll


error_fput:
fdput(f);
return error;
}

/**
 * ep_poll - Retrieves ready events, and delivers them to the caller supplied
 *           event buffer.
 *
 * @ep: Pointer to the eventpoll context.
 * @events: Pointer to the userspace buffer where the ready events should be
 *          stored.
 * @maxevents: Size (in terms of number of events) of the caller event buffer.
 * @timeout: Maximum timeout for the ready events fetch operation, in
 *           milliseconds. If the @timeout is zero, the function will not block,
 *           while if the @timeout is less than zero, the function will block
 *           until at least one event has been retrieved (or an error
 *           occurred).
 *
 * Returns: Returns the number of ready events which have been fetched, or an
 *          error code, in case of error.
 */
static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
  int maxevents, long timeout)
{
int res = 0, eavail, timed_out = 0;
unsigned long flags;
long slack = 0;
wait_queue_t wait;
ktime_t expires, *to = NULL;


if (timeout > 0) {
struct timespec end_time = ep_set_mstimeout(timeout);


slack = select_estimate_accuracy(&end_time);
to = &expires;
*to = timespec_to_ktime(end_time);
} else if (timeout == 0) {
/*
* Avoid the unnecessary trip to the wait queue loop, if the
* caller specified a non blocking operation.
*/
timed_out = 1;
spin_lock_irqsave(&ep->lock, flags);
goto check_events;
}


fetch_events:
spin_lock_irqsave(&ep->lock, flags);


if (!ep_events_available(ep)) {
/*
* We don't have any available event to return to the caller.
* We need to sleep here, and we will be wake up by
* ep_poll_callback() when events will become available.
*/
init_waitqueue_entry(&wait, current);
__add_wait_queue_exclusive(&ep->wq, &wait);


for (;;) {
/*
* We don't want to sleep if the ep_poll_callback() sends us
* a wakeup in between. That's why we set the task state
* to TASK_INTERRUPTIBLE before doing the checks.
*/
set_current_state(TASK_INTERRUPTIBLE);
if (ep_events_available(ep) || timed_out)
break;
if (signal_pending(current)) {
res = -EINTR;
break;
}


spin_unlock_irqrestore(&ep->lock, flags);
if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
timed_out = 1;


spin_lock_irqsave(&ep->lock, flags);
}


__remove_wait_queue(&ep->wq, &wait);
__set_current_state(TASK_RUNNING);
}
check_events:
/* Is it worth to try to dig for events ? */
eavail = ep_events_available(ep);


spin_unlock_irqrestore(&ep->lock, flags);


/*
* Try to transfer events to user space. In case we get 0 events and
* there's still timeout left over, we go trying again in search of
* more luck.
*/
if (!res && eavail &&
   !(res = ep_send_events(ep, events, maxevents)) && !timed_out)//设置ready事件到列表
goto fetch_events;


return res;
}

ep_send_events --->ep_scan_ready_list--->ep_send_events_proc

static int ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
      void *priv)
{
struct ep_send_events_data *esed = priv;
int eventcnt;
unsigned int revents;
struct epitem *epi;
struct epoll_event __user *uevent;
struct wakeup_source *ws;
poll_table pt;


init_poll_funcptr(&pt, NULL);


/*
* We can loop without lock because we are passed a task private list.
* Items cannot vanish during the loop because ep_scan_ready_list() is
* holding "mtx" during this call.
*/
for (eventcnt = 0, uevent = esed->events;
    !list_empty(head) && eventcnt < esed->maxevents;) {
epi = list_first_entry(head, struct epitem, rdllink);


/*
* Activate ep->ws before deactivating epi->ws to prevent
* triggering auto-suspend here (in case we reactive epi->ws
* below).
*
* This could be rearranged to delay the deactivation of epi->ws
* instead, but then epi->ws would temporarily be out of sync
* with ep_is_linked().
*/
ws = ep_wakeup_source(epi);
if (ws) {
if (ws->active)
__pm_stay_awake(ep->ws);
__pm_relax(ws);
}


list_del_init(&epi->rdllink);


revents = ep_item_poll(epi, &pt);


/*
* If the event mask intersect the caller-requested one,
* deliver the event to userspace. Again, ep_scan_ready_list()
* is holding "mtx", so no operations coming from userspace
* can change the item.
*/
if (revents) {
if (__put_user(revents, &uevent->events) ||
   __put_user(epi->event.data, &uevent->data)) {
list_add(&epi->rdllink, head);
ep_pm_stay_awake(epi);
return eventcnt ? eventcnt : -EFAULT;
}
eventcnt++;
uevent++;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
else if (!(epi->event.events & EPOLLET)) {//判断是否是水平触发，是需要添加到队列
/*
* If this file has been added with Level
* Trigger mode, we need to insert back inside
* the ready list, so that the next call to
* epoll_wait() will check again the events
* availability. At this point, no one can insert
* into ep->rdllist besides us. The epoll_ctl()
* callers are locked out by
* ep_scan_ready_list() holding "mtx" and the
* poll callback will queue them in ep->ovflist.
*/
list_add_tail(&epi->rdllink, &ep->rdllist);//添加到队列
ep_pm_stay_awake(epi);
}
}
}


return eventcnt;
}