original development tree for Linux kernel GTP module; now long in mainline.
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

1305 lines
36 KiB

/*
* fs/eventpoll.c (Efficent event polling implementation)
* Copyright (C) 2001,...,2007 Davide Libenzi
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or
* (at your option) any later version.
*
* Davide Libenzi <davidel@xmailserver.org>
*
*/
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/signal.h>
#include <linux/errno.h>
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/poll.h>
#include <linux/string.h>
#include <linux/list.h>
#include <linux/hash.h>
#include <linux/spinlock.h>
#include <linux/syscalls.h>
#include <linux/rbtree.h>
#include <linux/wait.h>
#include <linux/eventpoll.h>
#include <linux/mount.h>
#include <linux/bitops.h>
#include <linux/mutex.h>
#include <linux/anon_inodes.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/mman.h>
#include <asm/atomic.h>
/*
* LOCKING:
* There are three level of locking required by epoll :
*
* 1) epmutex (mutex)
* 2) ep->mtx (mutex)
* 3) ep->lock (spinlock)
*
* The acquire order is the one listed above, from 1 to 3.
* We need a spinlock (ep->lock) because we manipulate objects
* from inside the poll callback, that might be triggered from
* a wake_up() that in turn might be called from IRQ context.
* So we can't sleep inside the poll callback and hence we need
* a spinlock. During the event transfer loop (from kernel to
* user space) we could end up sleeping due a copy_to_user(), so
* we need a lock that will allow us to sleep. This lock is a
* mutex (ep->mtx). It is acquired during the event transfer loop,
* during epoll_ctl(EPOLL_CTL_DEL) and during eventpoll_release_file().
* Then we also need a global mutex to serialize eventpoll_release_file()
* and ep_free().
* This mutex is acquired by ep_free() during the epoll file
* cleanup path and it is also acquired by eventpoll_release_file()
* if a file has been pushed inside an epoll set and it is then
* close()d without a previous call toepoll_ctl(EPOLL_CTL_DEL).
* It is possible to drop the "ep->mtx" and to use the global
* mutex "epmutex" (together with "ep->lock") to have it working,
* but having "ep->mtx" will make the interface more scalable.
* Events that require holding "epmutex" are very rare, while for
* normal operations the epoll private "ep->mtx" will guarantee
* a better scalability.
*/
#define DEBUG_EPOLL 0
#if DEBUG_EPOLL > 0
#define DPRINTK(x) printk x
#define DNPRINTK(n, x) do { if ((n) <= DEBUG_EPOLL) printk x; } while (0)
#else /* #if DEBUG_EPOLL > 0 */
#define DPRINTK(x) (void) 0
#define DNPRINTK(n, x) (void) 0
#endif /* #if DEBUG_EPOLL > 0 */
#define DEBUG_EPI 0
#if DEBUG_EPI != 0
#define EPI_SLAB_DEBUG (SLAB_DEBUG_FREE | SLAB_RED_ZONE /* | SLAB_POISON */)
#else /* #if DEBUG_EPI != 0 */
#define EPI_SLAB_DEBUG 0
#endif /* #if DEBUG_EPI != 0 */
/* Epoll private bits inside the event mask */
#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET)
/* Maximum number of poll wake up nests we are allowing */
#define EP_MAX_POLLWAKE_NESTS 4
/* Maximum msec timeout value storeable in a long int */
#define EP_MAX_MSTIMEO min(1000ULL * MAX_SCHEDULE_TIMEOUT / HZ, (LONG_MAX - 999ULL) / HZ)
#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))
#define EP_UNACTIVE_PTR ((void *) -1L)
struct epoll_filefd {
struct file *file;
int fd;
};
/*
* Node that is linked into the "wake_task_list" member of the "struct poll_safewake".
* It is used to keep track on all tasks that are currently inside the wake_up() code
* to 1) short-circuit the one coming from the same task and same wait queue head
* (loop) 2) allow a maximum number of epoll descriptors inclusion nesting
* 3) let go the ones coming from other tasks.
*/
struct wake_task_node {
struct list_head llink;
struct task_struct *task;
wait_queue_head_t *wq;
};
/*
* This is used to implement the safe poll wake up avoiding to reenter
* the poll callback from inside wake_up().
*/
struct poll_safewake {
struct list_head wake_task_list;
spinlock_t lock;
};
/*
* Each file descriptor added to the eventpoll interface will
* have an entry of this type linked to the "rbr" RB tree.
*/
struct epitem {
/* RB tree node used to link this structure to the eventpoll RB tree */
struct rb_node rbn;
/* 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;
/* The structure that describe the interested events and the source fd */
struct epoll_event event;
};
/*
* This structure is stored inside the "private_data" member of the file
* structure and rapresent the main data sructure for the eventpoll
* interface.
*/
struct eventpoll {
/* Protect the this structure access */
spinlock_t lock;
/*
* 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 rbr;
/*
* This is a single linked list that chains all the "struct epitem" that
* happened while transfering ready events to userspace w/out
* holding ->lock.
*/
struct epitem *ovflist;
};
/* Wait structure used by the poll hooks */
struct eppoll_entry {
/* List header used to link this structure to the "struct epitem" */
struct list_head llink;
/* The "base" pointer is set to the container "struct epitem" */
void *base;
/*
* Wait queue item that will be linked to the target file wait
* queue head.
*/
wait_queue_t wait;
/* The wait queue head that linked the "wait" wait queue item */
wait_queue_head_t *whead;
};
/* Wrapper struct used by poll queueing */
struct ep_pqueue {
poll_table pt;
struct epitem *epi;
};
/*
* This mutex is used to serialize ep_free() and eventpoll_release_file().
*/
static struct mutex epmutex;
/* Safe wake up implementation */
static struct poll_safewake psw;
/* Slab cache used to allocate "struct epitem" */
static struct kmem_cache *epi_cache __read_mostly;
/* Slab cache used to allocate "struct eppoll_entry" */
static struct kmem_cache *pwq_cache __read_mostly;
/* Setup the structure that is used as key for the RB tree */
static inline void ep_set_ffd(struct epoll_filefd *ffd,
struct file *file, int fd)
{
ffd->file = file;
ffd->fd = fd;
}
/* Compare RB tree keys */
static inline int ep_cmp_ffd(struct epoll_filefd *p1,
struct epoll_filefd *p2)
{
return (p1->file > p2->file ? +1:
(p1->file < p2->file ? -1 : p1->fd - p2->fd));
}
/* Tells us if the item is currently linked */
static inline int ep_is_linked(struct list_head *p)
{
return !list_empty(p);
}
/* Get the "struct epitem" from a wait queue pointer */
static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
{
return container_of(p, struct eppoll_entry, wait)->base;
}
/* Get the "struct epitem" from an epoll queue wrapper */
static inline struct epitem *ep_item_from_epqueue(poll_table *p)
{
return container_of(p, struct ep_pqueue, pt)->epi;
}
/* Tells if the epoll_ctl(2) operation needs an event copy from userspace */
epoll: optimizations and cleanups Epoll is doing multiple passes over the ready set at the moment, because of the constraints over the f_op->poll() call. Looking at the code again, I noticed that we already hold the epoll semaphore in read, and this (together with other locking conditions that hold while doing an epoll_wait()) can lead to a smarter way [1] to "ship" events to userspace (in a single pass). This is a stress application that can be used to test the new code. It spwans multiple thread and call epoll_wait() and epoll_ctl() from many threads. Stress tested on my dual Opteron 254 w/out any problems. http://www.xmailserver.org/totalmess.c This is not a benchmark, just something that tries to stress and exploit possible problems with the new code. Also, I made a stupid micro-benchmark: http://www.xmailserver.org/epwbench.c [1] Considering that epoll must be thread-safe, there are five ways we can be hit during an epoll_wait() transfer loop (ep_send_events()): 1) The epoll fd going away and calling ep_free This just can't happen, since we did an fget() in sys_epoll_wait 2) An epoll_ctl(EPOLL_CTL_DEL) This can't happen because epoll_ctl() gets ep->sem in write, and we're holding it in read during ep_send_events() 3) An fd stored inside the epoll fd going away This can't happen because in eventpoll_release_file() we get ep->sem in write, and we're holding it in read during ep_send_events() 4) Another epoll_wait() happening on another thread They both can be inside ep_send_events() at the same time, we get (splice) the ready-list under the spinlock, so each one will get its own ready list. Note that an fd cannot be at the same time inside more than one ready list, because ep_poll_callback() will not re-queue it if it sees it already linked: if (ep_is_linked(&epi->rdllink)) goto is_linked; Another case that can happen, is two concurrent epoll_wait(), coming in with a userspace event buffer of size, say, ten. Suppose there are 50 event ready in the list. The first epoll_wait() will "steal" the whole list, while the second, seeing no events, will go to sleep. But at the end of ep_send_events() in the first epoll_wait(), we will re-inject surplus ready fds, and we will trigger the proper wake_up to the second epoll_wait(). 5) ep_poll_callback() hitting us asyncronously This is the tricky part. As I said above, the ep_is_linked() test done inside ep_poll_callback(), will guarantee us that until the item will result linked to a list, ep_poll_callback() will not try to re-queue it again (read, write data on any of its members). When we do a list_del() in ep_send_events(), the item will still satisfy the ep_is_linked() test (whatever data is written in prev/next, it'll never be its own pointer), so ep_poll_callback() will still leave us alone. It's only after the eventual smp_mb()+INIT_LIST_HEAD(&epi->rdllink) that it'll become visible to ep_poll_callback(), but at the point we're already past it. [akpm@osdl.org: 80 cols] Signed-off-by: Davide Libenzi <davidel@xmailserver.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
15 years ago
static inline int ep_op_has_event(int op)
{
return op != EPOLL_CTL_DEL;
}
/* Initialize the poll safe wake up structure */
static void ep_poll_safewake_init(struct poll_safewake *psw)
{
INIT_LIST_HEAD(&psw->wake_task_list);
spin_lock_init(&psw->lock);
}
/*
* Perform a safe wake up of the poll wait list. The problem is that
* with the new callback'd wake up system, it is possible that the
* poll callback is reentered from inside the call to wake_up() done
* on the poll wait queue head. The rule is that we cannot reenter the
* wake up code from the same task more than EP_MAX_POLLWAKE_NESTS times,
* and we cannot reenter the same wait queue head at all. This will
* enable to have a hierarchy of epoll file descriptor of no more than
* EP_MAX_POLLWAKE_NESTS deep. We need the irq version of the spin lock
* because this one gets called by the poll callback, that in turn is called
* from inside a wake_up(), that might be called from irq context.
*/
static void ep_poll_safewake(struct poll_safewake *psw, wait_queue_head_t *wq)
{
int wake_nests = 0;
unsigned long flags;
struct task_struct *this_task = current;
struct list_head *lsthead = &psw->wake_task_list;
struct wake_task_node *tncur;
struct wake_task_node tnode;
spin_lock_irqsave(&psw->lock, flags);
/* Try to see if the current task is already inside this wakeup call */
list_for_each_entry(tncur, lsthead, llink) {
if (tncur->wq == wq ||
(tncur->task == this_task && ++wake_nests > EP_MAX_POLLWAKE_NESTS)) {
/*
* Ops ... loop detected or maximum nest level reached.
* We abort this wake by breaking the cycle itself.
*/
spin_unlock_irqrestore(&psw->lock, flags);
return;
}
}
/* Add the current task to the list */
tnode.task = this_task;
tnode.wq = wq;
list_add(&tnode.llink, lsthead);
spin_unlock_irqrestore(&psw->lock, flags);
/* Do really wake up now */
lockdep: annotate epoll On Sat, 2008-01-05 at 13:35 -0800, Davide Libenzi wrote: > I remember I talked with Arjan about this time ago. Basically, since 1) > you can drop an epoll fd inside another epoll fd 2) callback-based wakeups > are used, you can see a wake_up() from inside another wake_up(), but they > will never refer to the same lock instance. > Think about: > > dfd = socket(...); > efd1 = epoll_create(); > efd2 = epoll_create(); > epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); > epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); > > When a packet arrives to the device underneath "dfd", the net code will > issue a wake_up() on its poll wake list. Epoll (efd1) has installed a > callback wakeup entry on that queue, and the wake_up() performed by the > "dfd" net code will end up in ep_poll_callback(). At this point epoll > (efd1) notices that it may have some event ready, so it needs to wake up > the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() > that ends up in another wake_up(), after having checked about the > recursion constraints. That are, no more than EP_MAX_POLLWAKE_NESTS, to > avoid stack blasting. Never hit the same queue, to avoid loops like: > > epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); > epoll_ctl(efd3, EPOLL_CTL_ADD, efd2, ...); > epoll_ctl(efd4, EPOLL_CTL_ADD, efd3, ...); > epoll_ctl(efd1, EPOLL_CTL_ADD, efd4, ...); > > The code "if (tncur->wq == wq || ..." prevents re-entering the same > queue/lock. Since the epoll code is very careful to not nest same instance locks allow the recursion. Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Tested-by: Stefan Richter <stefanr@s5r6.in-berlin.de> Acked-by: Davide Libenzi <davidel@xmailserver.org> Cc: <stable@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
14 years ago
wake_up_nested(wq, 1 + wake_nests);
/* Remove the current task from the list */
spin_lock_irqsave(&psw->lock, flags);
list_del(&tnode.llink);
spin_unlock_irqrestore(&psw->lock, flags);
}
/*
* This function unregister poll callbacks from the associated file descriptor.
* Since this must be called without holding "ep->lock" the atomic exchange trick
* will protect us from multiple unregister.
*/
static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
{
int nwait;
struct list_head *lsthead = &epi->pwqlist;
struct eppoll_entry *pwq;
/* This is called without locks, so we need the atomic exchange */
nwait = xchg(&epi->nwait, 0);
if (nwait) {
while (!list_empty(lsthead)) {
pwq = list_first_entry(lsthead, struct eppoll_entry, llink);
list_del_init(&pwq->llink);
remove_wait_queue(pwq->whead, &pwq->wait);
kmem_cache_free(pwq_cache, pwq);
}
}
}
/*
* Removes a "struct epitem" from the eventpoll RB tree and deallocates
* all the associated resources. Must be called with "mtx" held.
*/
static int ep_remove(struct eventpoll *ep, struct epitem *epi)
{
unsigned long flags;
struct file *file = epi->ffd.file;
/*
* Removes poll wait queue hooks. We _have_ to do this without holding
* the "ep->lock" otherwise a deadlock might occur. This because of the
* sequence of the lock acquisition. Here we do "ep->lock" then the wait
* queue head lock when unregistering the wait queue. The wakeup callback
* will run by holding the wait queue head lock and will call our callback
* that will try to get "ep->lock".
*/
ep_unregister_pollwait(ep, epi);
/* Remove the current item from the list of epoll hooks */
spin_lock(&file->f_ep_lock);
if (ep_is_linked(&epi->fllink))
list_del_init(&epi->fllink);
spin_unlock(&file->f_ep_lock);
rb_erase(&epi->rbn, &ep->rbr);
spin_lock_irqsave(&ep->lock, flags);
if (ep_is_linked(&epi->rdllink))
list_del_init(&epi->rdllink);
spin_unlock_irqrestore(&ep->lock, flags);
/* At this point it is safe to free the eventpoll item */
kmem_cache_free(epi_cache, epi);
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_remove(%p, %p)\n",
current, ep, file));
return 0;
}
static void ep_free(struct eventpoll *ep)
{
struct rb_node *rbp;
struct epitem *epi;
/* We need to release all tasks waiting for these file */
if (waitqueue_active(&ep->poll_wait))
ep_poll_safewake(&psw, &ep->poll_wait);
/*
* We need to lock this because we could be hit by
* eventpoll_release_file() while we're freeing the "struct eventpoll".
* We do not need to hold "ep->mtx" here because the epoll file
* is on the way to be removed and no one has references to it
* anymore. The only hit might come from eventpoll_release_file() but
* holding "epmutex" is sufficent here.
*/
mutex_lock(&epmutex);
/*
* Walks through the whole tree by unregistering poll callbacks.
*/
for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_unregister_pollwait(ep, epi);
}
/*
* Walks through the whole tree by freeing each "struct epitem". At this
* point we are sure no poll callbacks will be lingering around, and also by
* holding "epmutex" we can be sure that no file cleanup code will hit
* us during this operation. So we can avoid the lock on "ep->lock".
*/
while ((rbp = rb_first(&ep->rbr)) != NULL) {
epi = rb_entry(rbp, struct epitem, rbn);
ep_remove(ep, epi);
}
mutex_unlock(&epmutex);
mutex_destroy(&ep->mtx);
kfree(ep);
}
static int ep_eventpoll_release(struct inode *inode, struct file *file)
{
struct eventpoll *ep = file->private_data;
if (ep)
ep_free(ep);
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: close() ep=%p\n", current, ep));
return 0;
}
static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
{
unsigned int pollflags = 0;
unsigned long flags;
struct eventpoll *ep = file->private_data;
/* Insert inside our poll wait queue */
poll_wait(file, &ep->poll_wait, wait);
/* Check our condition */
spin_lock_irqsave(&ep->lock, flags);
if (!list_empty(&ep->rdllist))
pollflags = POLLIN | POLLRDNORM;
spin_unlock_irqrestore(&ep->lock, flags);
return pollflags;
}
/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
.release = ep_eventpoll_release,
.poll = ep_eventpoll_poll
};
/* Fast test to see if the file is an evenpoll file */
static inline int is_file_epoll(struct file *f)
{
return f->f_op == &eventpoll_fops;
}
/*
* This is called from eventpoll_release() to unlink files from the eventpoll
* interface. We need to have this facility to cleanup correctly files that are
* closed without being removed from the eventpoll interface.
*/
void eventpoll_release_file(struct file *file)
{
struct list_head *lsthead = &file->f_ep_links;
struct eventpoll *ep;
struct epitem *epi;
/*
* We don't want to get "file->f_ep_lock" because it is not
* necessary. It is not necessary because we're in the "struct file"
* cleanup path, and this means that noone is using this file anymore.
* So, for example, epoll_ctl() cannot hit here sicne if we reach this
* point, the file counter already went to zero and fget() would fail.
* The only hit might come from ep_free() but by holding the mutex
* will correctly serialize the operation. We do need to acquire
* "ep->mtx" after "epmutex" because ep_remove() requires it when called
* from anywhere but ep_free().
*/
mutex_lock(&epmutex);
while (!list_empty(lsthead)) {
epi = list_first_entry(lsthead, struct epitem, fllink);
ep = epi->ep;
list_del_init(&epi->fllink);
mutex_lock(&ep->mtx);
ep_remove(ep, epi);
mutex_unlock(&ep->mtx);
}
mutex_unlock(&epmutex);
}
static int ep_alloc(struct eventpoll **pep)
{
struct eventpoll *ep = kzalloc(sizeof(*ep), GFP_KERNEL);
if (!ep)
return -ENOMEM;
spin_lock_init(&ep->lock);
mutex_init(&ep->mtx);
init_waitqueue_head(&ep->wq);
init_waitqueue_head(&ep->poll_wait);
INIT_LIST_HEAD(&ep->rdllist);
ep->rbr = RB_ROOT;
ep->ovflist = EP_UNACTIVE_PTR;
*pep = ep;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_alloc() ep=%p\n",
current, ep));
return 0;
}
/*
* Search the file inside the eventpoll tree. The RB tree operations
* are protected by the "mtx" mutex, and ep_find() must be called with
* "mtx" held.
*/
static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
{
int kcmp;
struct rb_node *rbp;
struct epitem *epi, *epir = NULL;
struct epoll_filefd ffd;
ep_set_ffd(&ffd, file, fd);
for (rbp = ep->rbr.rb_node; rbp; ) {
epi = rb_entry(rbp, struct epitem, rbn);
kcmp = ep_cmp_ffd(&ffd, &epi->ffd);
if (kcmp > 0)
rbp = rbp->rb_right;
else if (kcmp < 0)
rbp = rbp->rb_left;
else {
epir = epi;
break;
}
}
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: ep_find(%p) -> %p\n",
current, file, epir));
return epir;
}
/*
* This is the callback that is passed to the wait queue wakeup
* machanism. 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;
DNPRINTK(3, (KERN_INFO "[%p] eventpoll: poll_callback(%p) epi=%p ep=%p\n",
current, epi->ffd.file, epi, ep));
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;
/*
* If we are trasfering 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 happens 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;
}
goto out_unlock;
}
/* If this file is already in the ready list we exit soon */
if (ep_is_linked(&epi->rdllink))
goto is_linked;
list_add_tail(&epi->rdllink, &ep->rdllist);
is_linked:
/*
* Wake up ( if active ) both the eventpoll wait list and the ->poll()
* wait list.
*/
if (waitqueue_active(&ep->wq))
wake_up_locked(&ep->wq);
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(&psw, &ep->poll_wait);
return 1;
}
/*
* 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);