eventpoll.c

// SPDX-License-Identifier: GPL-2.0-or-later
/*
 *  fs/eventpoll.c (Efficient event retrieval implementation)
 *  Copyright (C) 2001,...,2009	 Davide Libenzi
 *
 *  Davide Libenzi <davidel@xmailserver.org>
 */

#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/sched/signal.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 <linux/device.h>
#include <linux/uaccess.h>
#include <asm/io.h>
#include <asm/mman.h>
#include <linux/atomic.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/compat.h>
#include <linux/rculist.h>
#include <net/busy_poll.h>

/*
 * LOCKING:
 * There are three level of locking required by epoll :
 *
 * 1) epmutex (mutex)
 * 2) ep->mtx (mutex)
 * 3) ep->lock (rwlock)
 *
 * The acquire order is the one listed above, from 1 to 3.
 * We need a rwlock (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 to epoll_ctl(EPOLL_CTL_DEL).
 * It is also acquired when inserting an epoll fd onto another epoll
 * fd. We do this so that we walk the epoll tree and ensure that this
 * insertion does not create a cycle of epoll file descriptors, which
 * could lead to deadlock. We need a global mutex to prevent two
 * simultaneous inserts (A into B and B into A) from racing and
 * constructing a cycle without either insert observing that it is
 * going to.
 * It is necessary to acquire multiple "ep->mtx"es at once in the
 * case when one epoll fd is added to another. In this case, we
 * always acquire the locks in the order of nesting (i.e. after
 * epoll_ctl(e1, EPOLL_CTL_ADD, e2), e1->mtx will always be acquired
 * before e2->mtx). Since we disallow cycles of epoll file
 * descriptors, this ensures that the mutexes are well-ordered. In
 * order to communicate this nesting to lockdep, when walking a tree
 * of epoll file descriptors, we use the current recursion depth as
 * the lockdep subkey.
 * 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 (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE)

#define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT)

#define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \
				EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE)

/* 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;
} __packed;

/* Wait structure used by the poll hooks */
struct eppoll_entry {
	/* List header used to link this structure to the "struct epitem" */
	struct eppoll_entry *next;

	/* 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_entry_t wait;

	/* The wait queue head that linked the "wait" wait queue item */
	wait_queue_head_t *whead;
};

/*
 * 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;

	/* List containing poll wait queues */
	struct eppoll_entry *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 structure is stored inside the "private_data" member of the file
 * structure and represents the main data structure for the eventpoll
 * interface.
 */
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;

	/* Lock which protects rdllist and ovflist */
	rwlock_t lock;

	/* 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 ->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 */
	u64 gen;

#ifdef CONFIG_NET_RX_BUSY_POLL
	/* used to track busy poll napi_id */
	unsigned int napi_id;
#endif

#ifdef CONFIG_DEBUG_LOCK_ALLOC
	/* tracks wakeup nests for lockdep validation */
	u8 nests;
#endif
};

/* Wrapper struct used by poll queueing */
struct ep_pqueue {
	poll_table pt;
	struct epitem *epi;
};

/*
 * 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);

static u64 loop_check_gen = 0;

/* Used to check for epoll file descriptor inclusion loops */
static struct eventpoll *inserting_into;

/* 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;

/*
 * 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);

#ifdef CONFIG_SYSCTL

#include <linux/sysctl.h>

static long long_zero;
static long long_max = LONG_MAX;

struct 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		= &long_zero,
		.extra2		= &long_max,
	},
	{ }
};
#endif /* CONFIG_SYSCTL */

static const struct file_operations eventpoll_fops;

static inline int is_file_epoll(struct file *f)
{
	return f->f_op == &eventpoll_fops;
}

/* 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 epitem *epi)
{
	return !list_empty(&epi->rdllink);
}

static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p)
{
	return container_of(p, struct eppoll_entry, wait);
}

/* Get the "struct epitem" from a wait queue pointer */
static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
{
	return container_of(p, struct eppoll_entry, wait)->base;
}

/**
 * ep_events_available - Checks if ready events might be available.
 *
 * @ep: Pointer to the eventpoll context.
 *
 * Returns: Returns a value different than zero if ready events are available,
 *          or zero otherwise.
 */
static inline int ep_events_available(struct eventpoll *ep)
{
	return !list_empty_careful(&ep->rdllist) ||
		READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR;
}

#ifdef CONFIG_NET_RX_BUSY_POLL
static bool ep_busy_loop_end(void *p, unsigned long start_time)
{
	struct eventpoll *ep = p;

	return ep_events_available(ep) || busy_loop_timeout(start_time);
}

/*
 * Busy poll if globally on and supporting sockets found && no events,
 * busy loop will return if need_resched or ep_events_available.
 *
 * we must do our busy polling with irqs enabled
 */
static void ep_busy_loop(struct eventpoll *ep, int nonblock)
{
	unsigned int napi_id = READ_ONCE(ep->napi_id);

	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
}

static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
{
	if (ep->napi_id)
		ep->napi_id = 0;
}

/*
 * Set epoll busy poll NAPI ID from sk.
 */
static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
{
	struct eventpoll *ep;
	unsigned int napi_id;
	struct socket *sock;
	struct sock *sk;
	int err;

	if (!net_busy_loop_on())
		return;

	sock = sock_from_file(epi->ffd.file, &err);
	if (!sock)
		return;

	sk = sock->sk;
	if (!sk)
		return;

	napi_id = READ_ONCE(sk->sk_napi_id);
	ep = epi->ep;

	/* Non-NAPI IDs can be rejected
	 *	or
	 * Nothing to do if we already have this ID
	 */
	if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
		return;

	/* record NAPI ID for use in next busy poll */
	ep->napi_id = napi_id;
}

#else

static inline void ep_busy_loop(struct eventpoll *ep, int nonblock)
{
}

static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
{
}

static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
{
}

#endif /* CONFIG_NET_RX_BUSY_POLL */

/*
 * As described in commit 0ccf831cb lockdep: annotate epoll
 * the use of wait queues used by epoll is done in a very controlled
 * manner. Wake ups can nest inside each other, but are never done
 * with the same locking. For example:
 *
 *   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.
 *
 * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle
 * this special case of epoll.
 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC

static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi)
{
	struct eventpoll *ep_src;
	unsigned long flags;
	u8 nests = 0;

	/*
	 * To set the subclass or nesting level for spin_lock_irqsave_nested()
	 * it might be natural to create a per-cpu nest count. However, since
	 * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can
	 * schedule() in the -rt kernel, the per-cpu variable are no longer
	 * protected. Thus, we are introducing a per eventpoll nest field.
	 * If we are not being call from ep_poll_callback(), epi is NULL and
	 * we are at the first level of nesting, 0. Otherwise, we are being
	 * called from ep_poll_callback() and if a previous wakeup source is
	 * not an epoll file itself, we are at depth 1 since the wakeup source
	 * is depth 0. If the wakeup source is a previous epoll file in the
	 * wakeup chain then we use its nests value and record ours as
	 * nests + 1. The previous epoll file nests value is stable since its
	 * already holding its own poll_wait.lock.
	 */
	if (epi) {
		if ((is_file_epoll(epi->ffd.file))) {
			ep_src = epi->ffd.file->private_data;
			nests = ep_src->nests;
		} else {
			nests = 1;
		}
	}
	spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests);
	ep->nests = nests + 1;
	wake_up_locked_poll(&ep->poll_wait, EPOLLIN);
	ep->nests = 0;
	spin_unlock_irqrestore(&ep->poll_wait.lock, flags);
}

#else

static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi)
{
	wake_up_poll(&ep->poll_wait, EPOLLIN);
}

#endif

static void ep_remove_wait_queue(struct eppoll_entry *pwq)
{
	wait_queue_head_t *whead;

	rcu_read_lock();
	/*
	 * If it is cleared by POLLFREE, it should be rcu-safe.
	 * If we read NULL we need a barrier paired with
	 * smp_store_release() in ep_poll_callback(), otherwise
	 * we rely on whead->lock.
	 */
	whead = smp_load_acquire(&pwq->whead);
	if (whead)
		remove_wait_queue(whead, &pwq->wait);
	rcu_read_unlock();
}

/*
 * 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 eppoll_entry **p = &epi->pwqlist;
	struct eppoll_entry *pwq;

	while ((pwq = *p) != NULL) {
		*p = pwq->next;
		ep_remove_wait_queue(pwq);
		kmem_cache_free(pwq_cache, pwq);
	}
}

/* call only when ep->mtx is held */
static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi)
{
	return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx));
}

/* call only when ep->mtx is held */
static inline void ep_pm_stay_awake(struct epitem *epi)
{
	struct wakeup_source *ws = ep_wakeup_source(epi);

	if (ws)
		__pm_stay_awake(ws);
}

static inline bool ep_has_wakeup_source(struct epitem *epi)
{
	return rcu_access_pointer(epi->ws) ? true : false;
}

/* call when ep->mtx cannot be held (ep_poll_callback) */
static inline void ep_pm_stay_awake_rcu(struct epitem *epi)
{
	struct wakeup_source *ws;

	rcu_read_lock();
	ws = rcu_dereference(epi->ws);
	if (ws)
		__pm_stay_awake(ws);
	rcu_read_unlock();
}


/*
 * ep->mutex needs to be held because we could be hit by
 * eventpoll_release_file() and epoll_ctl().
 */
static void ep_start_scan(struct eventpoll *ep, struct list_head *txlist)
{
	/*
	 * 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.
	 */
	lockdep_assert_irqs_enabled();
	write_lock_irq(&ep->lock);
	list_splice_init(&ep->rdllist, txlist);
	WRITE_ONCE(ep->ovflist, NULL);
	write_unlock_irq(&ep->lock);
}

static void ep_done_scan(struct eventpoll *ep,
			 struct list_head *txlist)
{
	struct epitem *epi, *nepi;

	write_lock_irq(&ep->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 = READ_ONCE(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)) {
			/*
			 * ->ovflist is LIFO, so we have to reverse it in order
			 * to keep in FIFO.
			 */
			list_add(&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.
	 */
	WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR);

	/*
	 * Quickly re-inject items left on "txlist".
	 */
	list_splice(txlist, &ep->rdllist);
	__pm_relax(ep->ws);
	write_unlock_irq(&ep->lock);
}

static void epi_rcu_free(struct rcu_head *head)
{
	struct epitem *epi = container_of(head, struct epitem, rcu);
	kmem_cache_free(epi_cache, epi);
}

/*
 * 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)
{
	struct file *file = epi->ffd.file;

	lockdep_assert_irqs_enabled();

	/*
	 * Removes poll wait queue hooks.
	 */
	ep_unregister_pollwait(ep, epi);

	/* Remove the current item from the list of epoll hooks */
	spin_lock(&file->f_lock);
	list_del_rcu(&epi->fllink);
	spin_unlock(&file->f_lock);

	rb_erase_cached(&epi->rbn, &ep->rbr);

	write_lock_irq(&ep->lock);
	if (ep_is_linked(epi))
		list_del_init(&epi->rdllink);
	write_unlock_irq(&ep->lock);

	wakeup_source_unregister(ep_wakeup_source(epi));
	/*
	 * At this point it is safe to free the eventpoll item. Use the union
	 * field epi->rcu, since we are trying to minimize the size of
	 * 'struct epitem'. The 'rbn' field is no longer in use. Protected by
	 * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make
	 * use of the rbn field.
	 */
	call_rcu(&epi->rcu, epi_rcu_free);

	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, NULL);

	/*
	 * 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 sufficient here.
	 */
	mutex_lock(&epmutex);

	/*
	 * Walks through the whole tree by unregistering poll callbacks.
	 */
	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
		epi = rb_entry(rbp, struct epitem, rbn);

		ep_unregister_pollwait(ep, epi);
		cond_resched();
	}

	/*
	 * 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".
	 * We do not need to lock ep->mtx, either, we only do it to prevent
	 * a lockdep warning.
	 */
	mutex_lock(&ep->mtx);
	while ((rbp = rb_first_cached(&ep->rbr)) != NULL) {
		epi = rb_entry(rbp, struct epitem, rbn);
		ep_remove(ep, epi);
		cond_resched();
	}
	mutex_unlock(&ep->mtx);

	mutex_unlock(&epmutex);
	mutex_destroy(&ep->mtx);
	free_uid(ep->user);
	wakeup_source_unregister(ep->ws);
	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 __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
			       int depth);

static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth)
{
	struct eventpoll *ep = file->private_data;
	LIST_HEAD(txlist);
	__poll_t res;

	/* 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.
	 */
	mutex_lock_nested(&ep->mtx, depth);
	ep_start_scan(ep, &txlist);
	res = ep_read_events_proc(ep, &txlist, depth + 1);
	ep_done_scan(ep, &txlist);
	mutex_unlock(&ep->mtx);
	return res;
}

/*
 * 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 file *file = epi->ffd.file;
	__poll_t res;

	pt->_key = epi->event.events;
	if (!is_file_epoll(file))
		res = vfs_poll(file, pt);
	else
		res = __ep_eventpoll_poll(file, pt, depth);
	return res & epi->event.events;
}

static __poll_t ep_read_events_proc(struct eventpoll *ep, struct list_head *head,
			       int depth)
{
	struct epitem *epi, *tmp;
	poll_table pt;

	init_poll_funcptr(&pt, NULL);

	list_for_each_entry_safe(epi, tmp, head, rdllink) {
		if (ep_item_poll(epi, &pt, depth)) {
			return EPOLLIN | EPOLLRDNORM;
		} 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.
			 */
			__pm_relax(ep_wakeup_source(epi));
			list_del_init(&epi->rdllink);
		}
	}

	return 0;
}

static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait)
{
	return __ep_eventpoll_poll(file, wait, 0);
}

#ifdef CONFIG_PROC_FS
static void ep_show_fdinfo(struct seq_file *m, struct file *f)
{
	struct eventpoll *ep = f->private_data;
	struct rb_node *rbp;

	mutex_lock(&ep->mtx);
	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
		struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
		struct inode *inode = file_inode(epi->ffd.file);

		seq_printf(m, "tfd: %8d events: %8x data: %16llx "
			   " pos:%lli ino:%lx sdev:%x\n",
			   epi->ffd.fd, epi->event.events,
			   (long long)epi->event.data,
			   (long long)epi->ffd.file->f_pos,
			   inode->i_ino, inode->i_sb->s_dev);
		if (seq_has_overflowed(m))
			break;
	}
	mutex_unlock(&ep->mtx);
}
#endif

/* 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,
};

/*
 * 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 eventpoll *ep;
	struct epitem *epi, *next;

	/*
	 * 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 no one 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);
	list_for_each_entry_safe(epi, next, &file->f_ep_links, fllink) {
		ep = epi->ep;
		mutex_lock_nested(&ep->mtx, 0);
		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;

	mutex_init(&ep->mtx);
	rwlock_init(&ep->lock);
	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;
}

/*
 * 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_root.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;
}

#ifdef CONFIG_CHECKPOINT_RESTORE
static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
{
	struct rb_node *rbp;
	struct epitem *epi;

	for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) {
		epi = rb_entry(rbp, struct epitem, rbn);
		if (epi->ffd.fd == tfd) {
			if (toff == 0)
				return epi;
			else
				toff--;
		}
		cond_resched();
	}

	return NULL;
}

struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
				     unsigned long toff)
{
	struct file *file_raw;
	struct eventpoll *ep;
	struct epitem *epi;

	if (!is_file_epoll(file))
		return ERR_PTR(-EINVAL);

	ep = file->private_data;

	mutex_lock(&ep->mtx);
	epi = ep_find_tfd(ep, tfd, toff);
	if (epi)
		file_raw = epi->ffd.file;
	else
		file_raw = ERR_PTR(-ENOENT);
	mutex_unlock(&ep->mtx);

	return file_raw;
}
#endif /* CONFIG_CHECKPOINT_RESTORE */

/**
 * Adds a new entry to the tail of the list in a lockless way, i.e.
 * multiple CPUs are allowed to call this function concurrently.
 *
 * Beware: it is necessary to prevent any other modifications of the
 *         existing list until all changes are completed, in other words
 *         concurrent list_add_tail_lockless() calls should be protected
 *         with a read lock, where write lock acts as a barrier which
 *         makes sure all list_add_tail_lockless() calls are fully
 *         completed.
 *
 *        Also an element can be locklessly added to the list only in one
 *        direction i.e. either to the tail either to the head, otherwise
 *        concurrent access will corrupt the list.
 *
 * Returns %false if element has been already added to the list, %true
 * otherwise.
 */
static inline bool list_add_tail_lockless(struct list_head *new,
					  struct list_head *head)
{
	struct list_head *prev;

	/*
	 * This is simple 'new->next = head' operation, but cmpxchg()
	 * is used in order to detect that same element has been just