Merge branch 'merge' of git://git.kernel.org/pub/scm/linux/kernel/git/benh/powerpc

[linux-2.6/cjktty.git] / fs / eventpoll.c

/*
 *  fs/eventpoll.c (Efficient event retrieval implementation)
 *  Copyright (C) 2001,...,2009  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.
 */

/* Epoll private bits inside the event mask */
#define EP_PRIVATE_BITS (EPOLLONESHOT | EPOLLET)

/* Maximum number of nesting allowed inside epoll sets */
#define EP_MAX_NESTS 4

#define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event))

#define EP_UNACTIVE_PTR ((void *) -1L)

#define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry))

struct epoll_filefd {
        struct file *file;
        int fd;
};

/*
 * Structure used to track possible nested calls, for too deep recursions
 * and loop cycles.
 */
struct nested_call_node {
        struct list_head llink;
        void *cookie;
        void *ctx;
};

/*
 * This structure is used as collector for nested calls, to check for
 * maximum recursion dept and loop cycles.
 */
struct nested_calls {
        struct list_head tasks_call_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;

        /* The user that created the eventpoll descriptor */
        struct user_struct *user;
};

/* 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" */
        struct epitem *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;
};

/* Used by the ep_send_events() function as callback private data */
struct ep_send_events_data {
        int maxevents;
        struct epoll_event __user *events;
};

/*
 * Configuration options available inside /proc/sys/fs/epoll/
 */
/* Maximum number of epoll watched descriptors, per user */
static long max_user_watches __read_mostly;

/*
 * This mutex is used to serialize ep_free() and eventpoll_release_file().
 */
static DEFINE_MUTEX(epmutex);

/* Used for safe wake up implementation */
static struct nested_calls poll_safewake_ncalls;

/* Used to call file's f_op->poll() under the nested calls boundaries */
static struct nested_calls poll_readywalk_ncalls;

/* 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;

#ifdef CONFIG_SYSCTL

#include <linux/sysctl.h>

static long zero;
static long long_max = LONG_MAX;

ctl_table epoll_table[] = {
        {
                .procname       = "max_user_watches",
                .data           = &max_user_watches,
                .maxlen         = sizeof(max_user_watches),
                .mode           = 0644,
                .proc_handler   = proc_doulongvec_minmax,
                .extra1         = &zero,
                .extra2         = &long_max,
        },
        { }
};
#endif /* CONFIG_SYSCTL */


/* 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 */
static inline int ep_op_has_event(int op)
{
        return op != EPOLL_CTL_DEL;
}

/* Initialize the poll safe wake up structure */
static void ep_nested_calls_init(struct nested_calls *ncalls)
{
        INIT_LIST_HEAD(&ncalls->tasks_call_list);
        spin_lock_init(&ncalls->lock);
}

/**
 * ep_call_nested - Perform a bound (possibly) nested call, by checking
 *                  that the recursion limit is not exceeded, and that
 *                  the same nested call (by the meaning of same cookie) is
 *                  no re-entered.
 *
 * @ncalls: Pointer to the nested_calls structure to be used for this call.
 * @max_nests: Maximum number of allowed nesting calls.
 * @nproc: Nested call core function pointer.
 * @priv: Opaque data to be passed to the @nproc callback.
 * @cookie: Cookie to be used to identify this nested call.
 * @ctx: This instance context.
 *
 * Returns: Returns the code returned by the @nproc callback, or -1 if
 *          the maximum recursion limit has been exceeded.
 */
static int ep_call_nested(struct nested_calls *ncalls, int max_nests,
                          int (*nproc)(void *, void *, int), void *priv,
                          void *cookie, void *ctx)
{
        int error, call_nests = 0;
        unsigned long flags;
        struct list_head *lsthead = &ncalls->tasks_call_list;
        struct nested_call_node *tncur;
        struct nested_call_node tnode;

        spin_lock_irqsave(&ncalls->lock, flags);

        /*
         * Try to see if the current task is already inside this wakeup call.
         * We use a list here, since the population inside this set is always
         * very much limited.
         */
        list_for_each_entry(tncur, lsthead, llink) {
                if (tncur->ctx == ctx &&
                    (tncur->cookie == cookie || ++call_nests > max_nests)) {
                        /*
                         * Ops ... loop detected or maximum nest level reached.
                         * We abort this wake by breaking the cycle itself.
                         */
                        error = -1;
                        goto out_unlock;
                }
        }

        /* Add the current task and cookie to the list */
        tnode.ctx = ctx;
        tnode.cookie = cookie;
        list_add(&tnode.llink, lsthead);

        spin_unlock_irqrestore(&ncalls->lock, flags);

        /* Call the nested function */
        error = (*nproc)(priv, cookie, call_nests);

        /* Remove the current task from the list */
        spin_lock_irqsave(&ncalls->lock, flags);
        list_del(&tnode.llink);
out_unlock:
        spin_unlock_irqrestore(&ncalls->lock, flags);

        return error;
}

#ifdef CONFIG_DEBUG_LOCK_ALLOC
static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
                                     unsigned long events, int subclass)
{
        unsigned long flags;

        spin_lock_irqsave_nested(&wqueue->lock, flags, subclass);
        wake_up_locked_poll(wqueue, events);
        spin_unlock_irqrestore(&wqueue->lock, flags);
}
#else
static inline void ep_wake_up_nested(wait_queue_head_t *wqueue,
                                     unsigned long events, int subclass)
{
        wake_up_poll(wqueue, events);
}
#endif

static int ep_poll_wakeup_proc(void *priv, void *cookie, int call_nests)
{
        ep_wake_up_nested((wait_queue_head_t *) cookie, POLLIN,
                          1 + call_nests);
        return 0;
}

/*
 * 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_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_NESTS deep.
 */
static void ep_poll_safewake(wait_queue_head_t *wq)
{
        int this_cpu = get_cpu();

        ep_call_nested(&poll_safewake_ncalls, EP_MAX_NESTS,
                       ep_poll_wakeup_proc, NULL, wq, (void *) (long) this_cpu);

        put_cpu();
}

/*
 * This function unregisters poll callbacks from the associated file
 * descriptor.  Must be called with "mtx" held (or "epmutex" if called from
 * ep_free).
 */
static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi)
{
        struct list_head *lsthead = &epi->pwqlist;
        struct eppoll_entry *pwq;

        while (!list_empty(lsthead)) {
                pwq = list_first_entry(lsthead, struct eppoll_entry, llink);

                list_del(&pwq->llink);
                remove_wait_queue(pwq->whead, &pwq->wait);
                kmem_cache_free(pwq_cache, pwq);
        }
}

/**
 * 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.
 *
 * Returns: The same integer error code returned by the @sproc callback.
 */
static int ep_scan_ready_list(struct eventpoll *ep,
                              int (*sproc)(struct eventpoll *,
                                           struct list_head *, void *),
                              void *priv)
{
        int error, pwake = 0;
        unsigned long flags;
        struct epitem *epi, *nepi;
        LIST_HEAD(txlist);

        /*
         * We need to lock this because we could be hit by
         * eventpoll_release_file() and epoll_ctl().
         */
        mutex_lock(&ep->mtx);

        /*
         * 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_irqsave(&ep->lock, flags);
        list_splice_init(&ep->rdllist, &txlist);
        ep->ovflist = NULL;
        spin_unlock_irqrestore(&ep->lock, flags);

        /*
         * Now call the callback function.
         */
        error = (*sproc)(ep, &txlist, priv);

        spin_lock_irqsave(&ep->lock, flags);
        /*
         * 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->rdllink))
                        list_add_tail(&epi->rdllink, &ep->rdllist);
        }
        /*
         * 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);

        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_irqrestore(&ep->lock, flags);

        mutex_unlock(&ep->mtx);

        /* We have to call this outside the lock */
        if (pwake)
                ep_poll_safewake(&ep->poll_wait);

        return error;
}

/*
 * 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_lock);
        if (ep_is_linked(&epi->fllink))
                list_del_init(&epi->fllink);
        spin_unlock(&file->f_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);

        atomic_long_dec(&ep->user->epoll_watches);

        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(&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);
        free_uid(ep->user);
        kfree(ep);
}

static int ep_eventpoll_release(struct inode *inode, struct file *file)
{
        struct eventpoll *ep = file->private_data;

        if (ep)
                ep_free(ep);

        return 0;
}

static int ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
                               void *priv)
{
        struct epitem *epi, *tmp;

        list_for_each_entry_safe(epi, tmp, head, rdllink) {
                if (epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
                    epi->event.events)
                        return POLLIN | POLLRDNORM;
                else {
                        /*
                         * Item has been dropped into the ready list by the poll
                         * callback, but it's not actually ready, as far as
                         * caller requested events goes. We can remove it here.
                         */
                        list_del_init(&epi->rdllink);
                }
        }

        return 0;
}

static int ep_poll_readyevents_proc(void *priv, void *cookie, int call_nests)
{
        return ep_scan_ready_list(priv, ep_read_events_proc, NULL);
}

static unsigned int ep_eventpoll_poll(struct file *file, poll_table *wait)
{
        int pollflags;
        struct eventpoll *ep = file->private_data;

        /* 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. This need to be done under ep_call_nested()
         * supervision, since the call to f_op->poll() done on listed files
         * could re-enter here.
         */
        pollflags = ep_call_nested(&poll_readywalk_ncalls, EP_MAX_NESTS,
                                   ep_poll_readyevents_proc, ep, ep, current);

        return pollflags != -1 ? pollflags : 0;
}

/* File callbacks that implement the eventpoll file behaviour */
static const struct file_operations eventpoll_fops = {
        .release        = ep_eventpoll_release,
        .poll           = ep_eventpoll_poll,
        .llseek         = noop_llseek,
};

/* 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_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 since 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().
         *
         * Besides, ep_remove() acquires the lock, so we can't hold it here.
         */
        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)
{
        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;

        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;
        ep->user = user;

        *pep = ep;

        return 0;

free_uid:
        free_uid(user);
        return error;
}

/*
 * 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;
                }
        }

        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;

        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;

        /*
         * 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 (key && !((unsigned long) key & epi->event.events))
                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))
                list_add_tail(&epi->rdllink, &ep->rdllist);

        /*
         * 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(&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);
        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;
                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;
        }
}

static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi)
{
        int kcmp;
        struct rb_node **p = &ep->rbr.rb_node, *parent = NULL;
        struct epitem *epic;

        while (*p) {
                parent = *p;
                epic = rb_entry(parent, struct epitem, rbn);
                kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd);
                if (kcmp > 0)
                        p = &parent->rb_right;
                else
                        p = &parent->rb_left;
        }
        rb_link_node(&epi->rbn, parent, p);
        rb_insert_color(&epi->rbn, &ep->rbr);
}

/*
 * Must be called with "mtx" held.
 */
static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
                     struct file *tfile, int fd)
{
        int error, revents, pwake = 0;
        unsigned long flags;
        long user_watches;
        struct epitem *epi;
        struct ep_pqueue epq;

        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;

        /* 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 = 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 */
        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.
         */
        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 */
        if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
                list_add_tail(&epi->rdllink, &ep->rdllist);

                /* 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_irqrestore(&ep->lock, flags);

        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_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;
}

/*
 * Modify the interest event mask by dropping an event if the new mask
 * has a match in the current file status. Must be called with "mtx" held.
 */
static int ep_modify(struct eventpoll *ep, struct epitem *epi, struct epoll_event *event)
{
        int pwake = 0;
        unsigned int revents;

        /*
         * Set the new event interest mask before calling f_op->poll();
         * otherwise we might miss an event that happens between the
         * f_op->poll() call and the new event set registering.
         */
        epi->event.events = event->events;
        epi->event.data = event->data; /* protected by mtx */

        /*
         * Get current event bits. We can safely use the file* here because
         * its usage count has been increased by the caller of this function.
         */
        revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL);

        /*
         * If the item is "hot" and it is not registered inside the ready
         * list, push it inside.
         */
        if (revents & event->events) {
                spin_lock_irq(&ep->lock);
                if (!ep_is_linked(&epi->rdllink)) {
                        list_add_tail(&epi->rdllink, &ep->rdllist);

                        /* 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->lock);
        }

        /* We have to call this outside the lock */
        if (pwake)
                ep_poll_safewake(&ep->poll_wait);

        return 0;
}

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;

        /*
         * 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);

                list_del_init(&epi->rdllink);

                revents = epi->ffd.file->f_op->poll(epi->ffd.file, NULL) &
                        epi->event.events;

                /*
                 * 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);
                                return eventcnt ? eventcnt : -EFAULT;
                        }
                        eventcnt++;
                        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, noone 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);
                        }
                }
        }

        return eventcnt;
}

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;

        return ep_scan_ready_list(ep, ep_send_events_proc, &esed);
}

static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
                   int maxevents, long timeout)
{
        int res, eavail, timed_out = 0;
        unsigned long flags;
        long slack;
        wait_queue_t wait;
        struct timespec end_time;
        ktime_t expires, *to = NULL;

        if (timeout > 0) {
                ktime_get_ts(&end_time);
                timespec_add_ns(&end_time, (u64)timeout * NSEC_PER_MSEC);
                slack = select_estimate_accuracy(&end_time);
                to = &expires;
                *to = timespec_to_ktime(end_time);
        } else if (timeout == 0) {
                timed_out = 1;
        }

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

        res = 0;
        if (list_empty(&ep->rdllist)) {
                /*
                 * 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 (!list_empty(&ep->rdllist) || 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);
        }
        /* Is it worth to try to dig for events ? */
        eavail = !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;

        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)
                goto retry;

        return res;
}

/*
 * Open an eventpoll file descriptor.
 */
SYSCALL_DEFINE1(epoll_create1, int, flags)
{
        int error;
        struct eventpoll *ep = NULL;

        /* 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.
         */
        error = anon_inode_getfd("[eventpoll]", &eventpoll_fops, ep,
                                 O_RDWR | (flags & O_CLOEXEC));
        if (error < 0)
                ep_free(ep);

        return error;
}

SYSCALL_DEFINE1(epoll_create, int, size)
{
        if (size <= 0)
                return -EINVAL;

        return sys_epoll_create1(0);
}

/*
 * 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;
        struct file *file, *tfile;
        struct eventpoll *ep;
        struct epitem *epi;
        struct epoll_event epds;

        error = -EFAULT;
        if (ep_op_has_event(op) &&
            copy_from_user(&epds, event, sizeof(struct epoll_event)))
                goto error_return;

        /* Get the "struct file *" for the eventpoll file */
        error = -EBADF;
        file = fget(epfd);
        if (!file)
                goto error_return;

        /* Get the "struct file *" for the target file */
        tfile = fget(fd);
        if (!tfile)
                goto error_fput;

        /* The target file descriptor must support poll */
        error = -EPERM;
        if (!tfile->f_op || !tfile->f_op->poll)
                goto error_tgt_fput;

        /*
         * 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 (file == tfile || !is_file_epoll(file))
                goto error_tgt_fput;

        /*
         * At this point it is safe to assume that the "private_data" contains
         * our own data structure.
         */
        ep = file->private_data;

        mutex_lock(&ep->mtx);

        /*
         * 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, tfile, fd);

        error = -EINVAL;
        switch (op) {
        case EPOLL_CTL_ADD:
                if (!epi) {
                        epds.events |= POLLERR | POLLHUP;
                        error = ep_insert(ep, &epds, tfile, fd);
                } else
                        error = -EEXIST;
                break;
        case EPOLL_CTL_DEL:
                if (epi)
                        error = ep_remove(ep, epi);
                else
                        error = -ENOENT;
                break;
        case EPOLL_CTL_MOD:
                if (epi) {
                        epds.events |= POLLERR | POLLHUP;
                        error = ep_modify(ep, epi, &epds);
                } else
                        error = -ENOENT;
                break;
        }
        mutex_unlock(&ep->mtx);

error_tgt_fput:
        fput(tfile);
error_fput:
        fput(file);
error_return:

        return error;
}

/*
 * 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 file *file;
        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))) {
                error = -EFAULT;
                goto error_return;
        }

        /* Get the "struct file *" for the eventpoll file */
        error = -EBADF;
        file = fget(epfd);
        if (!file)
                goto error_return;

        /*
         * 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(file))
                goto error_fput;

        /*
         * At this point it is safe to assume that the "private_data" contains
         * our own data structure.
         */
        ep = file->private_data;

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

error_fput:
        fput(file);
error_return:

        return error;
}

#ifdef HAVE_SET_RESTORE_SIGMASK

/*
 * Implement the event wait interface for the eventpoll file. It is the kernel
 * part of the user space epoll_pwait(2).
 */
SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events,
                int, maxevents, int, timeout, const sigset_t __user *, sigmask,
                size_t, sigsetsize)
{
        int error;
        sigset_t ksigmask, sigsaved;

        /*
         * If the caller wants a certain signal mask to be set during the wait,
         * we apply it here.
         */
        if (sigmask) {
                if (sigsetsize != sizeof(sigset_t))
                        return -EINVAL;
                if (copy_from_user(&ksigmask, sigmask, sizeof(ksigmask)))
                        return -EFAULT;
                sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP));
                sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
        }

        error = sys_epoll_wait(epfd, events, maxevents, timeout);

        /*
         * If we changed the signal mask, we need to restore the original one.
         * In case we've got a signal while waiting, we do not restore the
         * signal mask yet, and we allow do_signal() to deliver the signal on
         * the way back to userspace, before the signal mask is restored.
         */
        if (sigmask) {
                if (error == -EINTR) {
                        memcpy(&current->saved_sigmask, &sigsaved,
                               sizeof(sigsaved));
                        set_restore_sigmask();
                } else
                        sigprocmask(SIG_SETMASK, &sigsaved, NULL);
        }

        return error;
}

#endif /* HAVE_SET_RESTORE_SIGMASK */

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 safe poll wait head wake ups */
        ep_nested_calls_init(&poll_safewake_ncalls);

        /* Initialize the structure used to perform file's f_op->poll() calls */
        ep_nested_calls_init(&poll_readywalk_ncalls);

        /* 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, NULL);

        /* Allocates slab cache used to allocate "struct eppoll_entry" */
        pwq_cache = kmem_cache_create("eventpoll_pwq",
                        sizeof(struct eppoll_entry), 0, SLAB_PANIC, NULL);

        return 0;
}
fs_initcall(eventpoll_init);