path: root/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 <linux/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 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 (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 p