path: root/fs/inotify.c

/*
 * fs/inotify.c - inode-based file event notifications
 *
 * Authors:
 *	John McCutchan	<ttb@tentacle.dhs.org>
 *	Robert Love	<rml@novell.com>
 *
 * Copyright (C) 2005 John McCutchan
 *
 * 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, or (at your option) any
 * later version.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 */

#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/sched.h>
#include <linux/spinlock.h>
#include <linux/idr.h>
#include <linux/slab.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/mount.h>
#include <linux/namei.h>
#include <linux/poll.h>
#include <linux/init.h>
#include <linux/list.h>
#include <linux/writeback.h>
#include <linux/inotify.h>
#include <linux/syscalls.h>

#include <asm/ioctls.h>

static atomic_t inotify_cookie;

static kmem_cache_t *watch_cachep __read_mostly;
static kmem_cache_t *event_cachep __read_mostly;

static struct vfsmount *inotify_mnt __read_mostly;

/* these are configurable via /proc/sys/fs/inotify/ */
int inotify_max_user_instances __read_mostly;
int inotify_max_user_watches __read_mostly;
int inotify_max_queued_events __read_mostly;

/*
 * Lock ordering:
 *
 * dentry->d_lock (used to keep d_move() away from dentry->d_parent)
 * iprune_mutex (synchronize shrink_icache_memory())
 * 	inode_lock (protects the super_block->s_inodes list)
 * 	inode->inotify_mutex (protects inode->inotify_watches and watches->i_list)
 * 		inotify_dev->mutex (protects inotify_device and watches->d_list)
 */

/*
 * Lifetimes of the three main data structures--inotify_device, inode, and
 * inotify_watch--are managed by reference count.
 *
 * inotify_device: Lifetime is from inotify_init() until release.  Additional
 * references can bump the count via get_inotify_dev() and drop the count via
 * put_inotify_dev().
 *
 * inotify_watch: Lifetime is from create_watch() to destory_watch().
 * Additional references can bump the count via get_inotify_watch() and drop
 * the count via put_inotify_watch().
 *
 * inode: Pinned so long as the inode is associated with a watch, from
 * create_watch() to put_inotify_watch().
 */

/*
 * struct inotify_device - represents an inotify instance
 *
 * This structure is protected by the mutex 'mutex'.
 */
struct inotify_device {
	wait_queue_head_t 	wq;		/* wait queue for i/o */
	struct idr		idr;		/* idr mapping wd -> watch */
	struct mutex		mutex;		/* protects this bad boy */
	struct list_head 	events;		/* list of queued events */
	struct list_head	watches;	/* list of watches */
	atomic_t		count;		/* reference count */
	struct user_struct	*user;		/* user who opened this dev */
	unsigned int		queue_size;	/* size of the queue (bytes) */
	unsigned int		event_count;	/* number of pending events */
	unsigned int		max_events;	/* maximum number of events */
	u32			last_wd;	/* the last wd allocated */
};

/*
 * struct inotify_kernel_event - An inotify event, originating from a watch and
 * queued for user-space.  A list of these is attached to each instance of the
 * device.  In read(), this list is walked and all events that can fit in the
 * buffer are returned.
 *
 * Protected by dev->mutex of the device in which we are queued.
 */
struct inotify_kernel_event {
	struct inotify_event	event;	/* the user-space event */
	struct list_head        list;	/* entry in inotify_device's list */
	char			*name;	/* filename, if any */
};

/*
 * struct inotify_watch - represents a watch request on a specific inode
 *
 * d_list is protected by dev->mutex of the associated watch->dev.
 * i_list and mask are protected by inode->inotify_mutex of the associated inode.
 * dev, inode, and wd are never written to once the watch is created.
 */
struct inotify_watch {
	struct list_head	d_list;	/* entry in inotify_device's list */
	struct list_head	i_list;	/* entry in inode's list */
	atomic_t		count;	/* reference count */
	struct inotify_device	*dev;	/* associated device */
	struct inode		*inode;	/* associated inode */
	s32 			wd;	/* watch descriptor */
	u32			mask;	/* event mask for this watch */
};

#ifdef CONFIG_SYSCTL

#include <linux/sysctl.h>

static int zero;

ctl_table inotify_table[] = {
	{
		.ctl_name	= INOTIFY_MAX_USER_INSTANCES,
		.procname	= "max_user_instances",
		.data		= &inotify_max_user_instances,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero,
	},
	{
		.ctl_name	= INOTIFY_MAX_USER_WATCHES,
		.procname	= "max_user_watches",
		.data		= &inotify_max_user_watches,
		.maxlen		= sizeof(int),
		.mode		= 0644,
		.proc_handler	= &proc_dointvec_minmax,
		.strategy	= &sysctl_intvec,
		.extra1		= &zero, 
	},
	{
		.ctl_name	= INOTIFY_MAX_QUEUED_EVENTS,