litmus-rt.git - The LITMUS^RT kernel.

/*
 *  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 <linux/device.h>
#include <asm/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>

/*
 * 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 (EPOLLWAKEUP | 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;
} __packed;

/*
 * 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.
 * Avoid increasing the size of this struct, there can be many thousands
 * of these on a server and we do not want this to take another cache line.
 */
struct epitem {
	union {
		/* RB tree node links this structure to the eventpoll RB tree */
		struct rb_node rbn;
		/* Used to free the struct epitem */
		struct rcu_head rcu;
	};

	/* List header used to link this structure to the eventpoll ready list */
	struct list_head rdllink;

	/*
	 * Works together "struct eventpoll"->ovflist in keeping the
	 * single linked chain of items.
	 */
	struct epitem *next;

	/* The file descriptor information this item refers to */
	struct epoll_filefd ffd;

	/* Number of active wait queue attached to poll operations */
	int nwait;

	/* List containing poll wait queues */
	struct list_head pwqlist;

	/* The "container" of this item */
	struct eventpoll *ep;

	/* List header used to link this item to the "struct file" items list */
	struct list_head fllink;

	/* wakeup_source used when EPOLLWAKEUP is set */
	struct wakeup_source __rcu *ws;

	/* The structure that describe the interested events and the source fd */
	struct epoll_event event;
};

/*
 * This structure is stored inside the "private_data" member of the file
 * structure and represents the main data structure for the eventpoll
 * interface.
 */
struct eventpoll {
	/* Protect the access to this structure */
	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 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 */
	int visited;
	struct list_head visited_list_link;
};

/* 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 to check for epoll file descriptor inclusion loops */
static struct nested_calls poll_loop_ncalls;

/* 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;

/* Visited nodes during ep_loop_check(), so we can unset them when we finish */
static LIST_HEAD(visited_list);

/*
 * 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 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		= &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 list_head *p)
{
	return !list_empty(p);
}

static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_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_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_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(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
}

/**
 * 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.


context:
space:
mode: