为什么80%的码农都做不了架构师？>>> 
按如下流程来分析epoll：
系统级的初始化
static int __init eventpoll_init(void)
{
struct sysinfo si;
si_meminfo(&si);
/*
* Allows top 4% of lomem to be allocated for epoll watches (per user).
*/
max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) /
EP_ITEM_COST;
BUG_ON(max_user_watches < 0);
/*
* Initialize the structure used to perform epoll file descriptor
* inclusion loops checks.
*/
ep_nested_calls_init(&poll_loop_ncalls);
#ifdef CONFIG_DEBUG_LOCK_ALLOC
/* Initialize the structure used to perform safe poll wait head wake ups */
ep_nested_calls_init(&poll_safewake_ncalls);
#endif
/*
* We can have many thousands of epitems, so prevent this from
* using an extra cache line on 64-bit (and smaller) CPUs
*/
BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128);
/* Allocates slab cache used to allocate "struct epitem" items */
epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem),
0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL);
/* Allocates slab cache used to allocate "struct eppoll_entry" */
pwq_cache = kmem_cache_create("eventpoll_pwq",
sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL);
return 0;
}
fs_initcall(eventpoll_init);按字面意思是以文件系统的方式来初始化。
创建epollfd
/*
* This structure is stored inside the "private_data" member of the file
* structure and represents the main data structure for the eventpoll
* interface.
*
* Access to it is protected by the lock inside wq.
*/
struct eventpoll {
/*
* This mutex is used to ensure that files are not removed
* while epoll is using them. This is held during the event
* collection loop, the file cleanup path, the epoll file exit
* code and the ctl operations.
*/
struct mutex mtx;
/* Wait queue used by sys_epoll_wait() */
wait_queue_head_t wq;
/* Wait queue used by file->poll() */
wait_queue_head_t poll_wait;
/* List of ready file descriptors */
struct list_head rdllist;
/* RB tree root used to store monitored fd structs */
struct rb_root_cached rbr;
/*
* This is a single linked list that chains all the "struct epitem" that
* happened while transferring ready events to userspace w/out
* holding ->wq.lock.
*/
struct epitem *ovflist;
/* wakeup_source used when ep_scan_ready_list is running */
struct wakeup_source *ws;
/* The user that created the eventpoll descriptor */
struct user_struct *user;
struct file *file;
/* used to optimize loop detection check */
int visited;
struct list_head visited_list_link;
#ifdef CONFIG_NET_RX_BUSY_POLL
/* used to track busy poll napi_id */
unsigned int napi_id;
#endif
};
static int ep_alloc(struct eventpoll **pep)
{
int error;
struct user_struct *user;
struct eventpoll *ep;
user = get_current_user();
error = -ENOMEM;
ep = kzalloc(sizeof(*ep), GFP_KERNEL);
if (unlikely(!ep))
goto free_uid;
mutex_init(&ep->mtx);
init_waitqueue_head(&ep->wq);
init_waitqueue_head(&ep->poll_wait);
INIT_LIST_HEAD(&ep->rdllist);
ep->rbr = RB_ROOT_CACHED;
ep->ovflist = EP_UNACTIVE_PTR;
ep->user = user;
*pep = ep;
return 0;
free_uid:
free_uid(user);
return error;
}
static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
{
struct eventpoll *ep = file->private_data;
int depth = 0;
/* Insert inside our poll wait queue */
poll_wait(file, &ep->poll_wait, wait);
/*
* Proceed to find out if wanted events are really available inside
* the ready list.
*/
return ep_scan_ready_list(ep, ep_read_events_proc,
&depth, depth, false);
}
/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
#ifdef CONFIG_PROC_FS
.show_fdinfo = ep_show_fdinfo,
#endif
.release = ep_eventpoll_release,
.poll = ep_eventpoll_poll,
.llseek = noop_llseek,
};
/*
* Open an eventpoll file descriptor.
*/
static int do_epoll_create(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);
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));
if (fd < 0) {
error = fd;
goto out_free_ep;
}
file = anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep,
O_RDWR | (flags & O_CLOEXEC));
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto out_free_fd;
}
ep->file = file;
fd_install(fd, file);
return fd;
out_free_fd:
put_unused_fd(fd);
out_free_ep:
ep_free(ep);
return error;
}
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
return do_epoll_create(flags);
}
SYSCALL_DEFINE1(epoll_create, int, size)
{
if (size <= 0)
return -EINVAL;
return do_epoll_create(0);
}主要是创建并初始化struct eventpoll对象，eventpoll对象关联一个fd，这个fd本身也支持poll操作。
向epollfd添加fd
/*
* Must be called with "mtx" held.
*/
static int ep_insert(struct eventpoll *ep, const struct epoll_event *event,
struct file *tfile, int fd, int full_check)
{
int error, pwake = 0;
__poll_t revents;
long user_watches;
struct epitem *epi;
struct ep_pqueue epq;
lockdep_assert_irqs_enabled();
user_watches = atomic_long_read(&ep->user->epoll_watches);
if (unlikely(user_watches >= max_user_watches))
return -ENOSPC;
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;
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;
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.
*/
revents = ep_item_poll(epi, &epq.pt, 1);
/*
* 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 */
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.
*/
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_irq(&ep->wq.lock);
/* record NAPI ID of new item if present */
ep_set_busy_poll_napi_id(epi);
/* If the file is already "ready" we drop it inside the ready list */
if (revents && !ep_is_linked(epi)) {
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->wq.lock);
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_cached(&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_irq(&ep->wq.lock);
if (ep_is_linked(epi))
list_del_init(&epi->rdllink);
spin_unlock_irq(&ep->wq.lock);
wakeup_source_unregister(ep_wakeup_source(epi));
error_create_wakeup_source:
kmem_cache_free(epi_cache, epi);
return error;
}
/*
* List of files with newly added links, where we may need to limit the number
* of emanating paths. Protected by the epmutex.
*/
static LIST_HEAD(tfile_check_list);
/*
* 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)))
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 (!file_can_poll(tf.file))
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 (ep_op_has_event(op) && (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 |= EPOLLERR | EPOLLHUP;
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 |= EPOLLERR | EPOLLHUP;
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;
}添加的fd必须支持poll操作，epollfd不能添加自己，但由于epollfd本身支持poll操作，因此可以添加另一个epollfd，但要做依赖检查。
添加时会调ep_item_poll
/*
* Differs from ep_eventpoll_poll() in that internal callers already have
* the ep->mtx so we need to start from depth=1, such that mutex_lock_nested()
* is correctly annotated.
*/
static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt,
int depth)
{
struct eventpoll *ep;
bool locked;
pt->_key = epi->event.events;
if (!is_file_epoll(epi->ffd.file))
return vfs_poll(epi->ffd.file, pt) & epi->event.events;
ep = epi->ffd.file->private_data;
poll_wait(epi->ffd.file, &ep->poll_wait, pt);
locked = pt && (pt->_qproc == ep_ptable_queue_proc);
return ep_scan_ready_list(epi->ffd.file->private_data,
ep_read_events_proc, &depth, depth,
locked) & epi->event.events;
}如果添加的fd不是epollfd，则直接调用vfs_poll，否则调用ep_scan_ready_list。
对于每一个添加的fd，都会创建相应的struct epitem对象，poll table的回调函数是ep_ptable_queue_proc。
/*
* Each file descriptor added to the eventpoll interface will
* have an entry of this type linked to the "rbr" RB tree.
* Avoid increasing the size of this struct, there can be many thousands
* of these on a server and we do not want this to take another cache line.
*/
struct epitem {
union {
/* RB tree node links this structure to the eventpoll RB tree */
struct rb_node rbn;
/* Used to free the struct epitem */
struct rcu_head rcu;
};
/* List header used to link this structure to the eventpoll ready list */
struct list_head rdllink;
/*
* Works together "struct eventpoll"->ovflist in keeping the
* single linked chain of items.
*/
struct epitem *next;
/* The file descriptor information this item refers to */
struct epoll_filefd ffd;
/* Number of active wait queue attached to poll operations */
int nwait;
/* List containing poll wait queues */
struct list_head pwqlist;
/* The "container" of this item */
struct eventpoll *ep;
/* List header used to link this item to the "struct file" items list */
struct list_head fllink;
/* wakeup_source used when EPOLLWAKEUP is set */
struct wakeup_source __rcu *ws;
/* The structure that describe the interested events and the source fd */
struct epoll_event event;
};
/*
* 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);
struct eppoll_entry *pwq;
if (epi->nwait >= 0 && (pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL))) {
init_waitqueue_func_entry(&pwq->wait, ep_poll_callback);
pwq->whead = whead;
pwq->base = epi;
if (epi->event.events & EPOLLEXCLUSIVE)
add_wait_queue_exclusive(whead, &pwq->wait);
else
add_wait_queue(whead, &pwq->wait);
list_add_tail(&pwq->llink, &epi->pwqlist);
epi->nwait++;
} else {
/* We have to signal that an error occurred */
epi->nwait = -1;
}
}等待队列的唤醒函数是ep_poll_callback。
事件到来，激活唤醒
/*
* 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_entry_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;
__poll_t pollflags = key_to_poll(key);
int ewake = 0;
spin_lock_irqsave(&ep->wq.lock, flags);
ep_set_busy_poll_napi_id(epi);
/*
* 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 (pollflags && !(pollflags & 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)) {
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) &&
!(pollflags & POLLFREE)) {
switch (pollflags & EPOLLINOUT_BITS) {
case EPOLLIN:
if (epi->event.events & EPOLLIN)
ewake = 1;
break;
case EPOLLOUT:
if (epi->event.events & EPOLLOUT)
ewake = 1;
break;
case 0:
ewake = 1;
break;
}
}
wake_up_locked(&ep->wq);
}
if (waitqueue_active(&ep->poll_wait))
pwake++;
out_unlock:
spin_unlock_irqrestore(&ep->wq.lock, flags);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&ep->poll_wait);
if (!(epi->event.events & EPOLLEXCLUSIVE))
ewake = 1;
if (pollflags & POLLFREE) {
/*
* If we race with ep_remove_wait_queue() it can miss
* ->whead = NULL and do another remove_wait_queue() after
* us, so we can't use __remove_wait_queue().
*/
list_del_init(&wait->entry);
/*
* ->whead != NULL protects us from the race with ep_free()
* or ep_remove(), ep_remove_wait_queue() takes whead->lock
* held by the caller. Once we nullify it, nothing protects
* ep/epi or even wait.
*/
smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL);
}
return ewake;
}由驱动触发内核中断执行，核心是
list_add_tail(&epi->rdllink, &ep->rdllist);也就是将激活的fd相关的epi加入到ep->rdllist，后续epoll_wait将从ep->rdllist取回激活的fd及相应事件。
epoll_wait
static __poll_t ep_send_events_proc(struct eventpoll *ep, struct list_head *head,
void *priv)
{
struct ep_send_events_data *esed = priv;
__poll_t 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 (esed->res = 0, uevent = esed->events;
!list_empty(head) && esed->res < 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, 1);
/*
* 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);
if (!esed->res)
esed->res = -EFAULT;
return 0;
}
esed->res++;
uevent++;
if (epi->event.events & EPOLLONESHOT)
epi->event.events &= EP_PRIVATE_BITS;
else if (!(epi->event.events & EPOLLET)) {
/*
* 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);
ep_pm_stay_awake(epi);
}
}
}
return 0;
}
/**
* ep_scan_ready_list - Scans the ready list in a way that makes possible for
* the scan code, to call f_op->poll(). Also allows for
* O(NumReady) performance.
*
* @ep: Pointer to the epoll private data structure.
* @sproc: Pointer to the scan callback.
* @priv: Private opaque data passed to the @sproc callback.
* @depth: The current depth of recursive f_op->poll calls.
* @ep_locked: caller already holds ep->mtx
*
* Returns: The same integer error code returned by the @sproc callback.
*/
static __poll_t ep_scan_ready_list(struct eventpoll *ep,
__poll_t (*sproc)(struct eventpoll *,
struct list_head *, void *),
void *priv, int depth, bool ep_locked)
{
__poll_t res;
int pwake = 0;
struct epitem *epi, *nepi;
LIST_HEAD(txlist);
lockdep_assert_irqs_enabled();
/*
* We need to lock this because we could be hit by
* eventpoll_release_file() and epoll_ctl().
*/
if (!ep_locked)
mutex_lock_nested(&ep->mtx, depth);
/*
* Steal the ready list, and re-init the original one to the
* empty list. Also, set ep->ovflist to NULL so that events
* happening while looping w/out locks, are not lost. We cannot
* have the poll callback to queue directly on ep->rdllist,
* because we want the "sproc" callback to be able to do it
* in a lockless way.
*/
spin_lock_irq(&ep->wq.lock);
list_splice_init(&ep->rdllist, &txlist);
ep->ovflist = NULL;
spin_unlock_irq(&ep->wq.lock);
/*
* Now call the callback function.
*/
res = (*sproc)(ep, &txlist, priv);
spin_lock_irq(&ep->wq.lock);
/*
* During the time we spent inside the "sproc" callback, some
* other events might have been queued by the poll callback.
* We re-insert them inside the main ready-list here.
*/
for (nepi = ep->ovflist; (epi = nepi) != NULL;
nepi = epi->next, epi->next = EP_UNACTIVE_PTR) {
/*
* We need to check if the item is already in the list.
* During the "sproc" callback execution time, items are
* queued into ->ovflist but the "txlist" might already
* contain them, and the list_splice() below takes care of them.
*/
if (!ep_is_linked(epi)) {
list_add_tail(&epi->rdllink, &ep->rdllist);
ep_pm_stay_awake(epi);
}
}
/*
* We need to set back ep->ovflist to EP_UNACTIVE_PTR, so that after
* releasing the lock, events will be queued in the normal way inside
* ep->rdllist.
*/
ep->ovflist = EP_UNACTIVE_PTR;
/*
* Quickly re-inject items left on "txlist".
*/
list_splice(&txlist, &ep->rdllist);
__pm_relax(ep->ws);
if (!list_empty(&ep->rdllist)) {
/*
* Wake up (if active) both the eventpoll wait list and
* the ->poll() wait list (delayed after we release the lock).
*/
if (waitqueue_active(&ep->wq))
wake_up_locked(&ep->wq);
if (waitqueue_active(&ep->poll_wait))
pwake++;
}
spin_unlock_irq(&ep->wq.lock);
if (!ep_locked)
mutex_unlock(&ep->mtx);
/* We have to call this outside the lock */
if (pwake)
ep_poll_safewake(&ep->poll_wait);
return res;
}
static int ep_send_events(struct eventpoll *ep,
struct epoll_event __user *events, int maxevents)
{
struct ep_send_events_data esed;
esed.maxevents = maxevents;
esed.events = events;
ep_scan_ready_list(ep, ep_send_events_proc, &esed, 0, false);
return esed.res;
}
/**
* 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;
u64 slack = 0;
wait_queue_entry_t wait;
ktime_t expires, *to = NULL;
lockdep_assert_irqs_enabled();
if (timeout > 0) {
struct timespec64 end_time = ep_set_mstimeout(timeout);
slack = select_estimate_accuracy(&end_time);
to = &expires;
*to = timespec64_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_irq(&ep->wq.lock);
goto check_events;
}
fetch_events:
if (!ep_events_available(ep))
ep_busy_loop(ep, timed_out);
spin_lock_irq(&ep->wq.lock);
if (!ep_events_available(ep)) {
/*
* Busy poll timed out. Drop NAPI ID for now, we can add
* it back in when we have moved a socket with a valid NAPI
* ID onto the ready list.
*/
ep_reset_busy_poll_napi_id(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);
/*
* Always short-circuit for fatal signals to allow
* threads to make a timely exit without the chance of
* finding more events available and fetching
* repeatedly.
*/
if (fatal_signal_pending(current)) {
res = -EINTR;
break;
}
if (ep_events_available(ep) || timed_out)
break;
if (signal_pending(current)) {
res = -EINTR;
break;
}
spin_unlock_irq(&ep->wq.lock);
if (!schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS))
timed_out = 1;
spin_lock_irq(&ep->wq.lock);
}
__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_irq(&ep->wq.lock);
/*
* 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)
goto fetch_events;
return res;
}
/*
* Implement the event wait interface for the eventpoll file. It is the kernel
* part of the user space epoll_wait(2).
*/
static int do_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)
return -EINVAL;
/* Verify that the area passed by the user is writeable */
if (!access_ok(VERIFY_WRITE, events, maxevents * sizeof(struct epoll_event)))
return -EFAULT;
/* Get the "struct file *" for the eventpoll file */
f = fdget(epfd);
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;
/* Time to fish for events ... */
error = ep_poll(ep, events, maxevents, timeout);
error_fput:
fdput(f);
return error;
}
SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events,
int, maxevents, int, timeout)
{
return do_epoll_wait(epfd, events, maxevents, timeout);
}ep_scan_ready_list将ep->rdllist另存为一个临时列表txlist，ep_send_events_proc扫描txlist将数据写往用户空间。由于写内存是一个很耗时的操作，将ep->ovflist置为NULL，那么在这段写的时间内如果还有其它的fd激活的话，ep_poll_callback会把这些fd对应的epi加入ep->ovflist队列。另外，为什么ep_send_events_proc中还要再做一次event标记检查呢？因为从激活到scan list的这段时间，fd的状态有可能改变，当然，即使在此处做了检查，到用户态有可能也变了，所以epoll一定要配合非阻塞fd使用，这样才不会发生不期望的阻塞。
