[PATCH] inotify (1/5): split kernel API from userspace support

The following series of patches introduces a kernel API for inotify,
making it possible for kernel modules to benefit from inotify's
mechanism for watching inodes.  With these patches, inotify will
maintain for each caller a list of watches (via an embedded struct
inotify_watch), where each inotify_watch is associated with a
corresponding struct inode.  The caller registers an event handler and
specifies for which filesystem events their event handler should be
called per inotify_watch.

Signed-off-by: Amy Griffis <amy.griffis@hp.com>
Acked-by: Robert Love <rml@novell.com>
Acked-by: John McCutchan <john@johnmccutchan.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>

fs/Kconfig

@@ -393,18 +393,30 @@ config INOTIFY
 	bool "Inotify file change notification support"
 	default y
 	---help---
-	  Say Y here to enable inotify support and the associated system
-	  calls.  Inotify is a file change notification system and a
-	  replacement for dnotify.  Inotify fixes numerous shortcomings in
-	  dnotify and introduces several new features.  It allows monitoring
-	  of both files and directories via a single open fd.  Other features
-	  include multiple file events, one-shot support, and unmount
+	  Say Y here to enable inotify support.  Inotify is a file change
+	  notification system and a replacement for dnotify.  Inotify fixes
+	  numerous shortcomings in dnotify and introduces several new features
+	  including multiple file events, one-shot support, and unmount
 	  notification.
 
 	  For more information, see Documentation/filesystems/inotify.txt
 
 	  If unsure, say Y.
 
+config INOTIFY_USER
+	bool "Inotify support for userspace"
+	depends on INOTIFY
+	default y
+	---help---
+	  Say Y here to enable inotify support for userspace, including the
+	  associated system calls.  Inotify allows monitoring of both files and
+	  directories via a single open fd.  Events are read from the file
+	  descriptor, which is also select()- and poll()-able.
+
+	  For more information, see Documentation/filesystems/inotify.txt
+
+	  If unsure, say Y.
+
 config QUOTA
 	bool "Quota support"
 	help

fs/Makefile

@@ -13,6 +13,7 @@ obj-y :=	open.o read_write.o file_table.o buffer.o  bio.o super.o \
 		ioprio.o pnode.o drop_caches.o splice.o sync.o
 
 obj-$(CONFIG_INOTIFY)		+= inotify.o
+obj-$(CONFIG_INOTIFY_USER)	+= inotify_user.o
 obj-$(CONFIG_EPOLL)		+= eventpoll.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
 

fs/inotify_user.c

@@ -0,0 +1,717 @@
+/*
+ * fs/inotify_user.c - inotify support for userspace
+ *
+ * Authors:
+ *	John McCutchan	<ttb@tentacle.dhs.org>
+ *	Robert Love	<rml@novell.com>
+ *
+ * Copyright (C) 2005 John McCutchan
+ * Copyright 2006 Hewlett-Packard Development Company, L.P.
+ *
+ * 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/kernel.h>
+#include <linux/sched.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/inotify.h>
+#include <linux/syscalls.h>
+
+#include <asm/ioctls.h>
+
+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:
+ *
+ * inotify_dev->up_mutex (ensures we don't re-add the same watch)
+ * 	inode->inotify_mutex (protects inode's watch list)
+ * 		inotify_handle->mutex (protects inotify_handle's watch list)
+ * 			inotify_dev->ev_mutex (protects device's event queue)
+ */
+
+/*
+ * Lifetimes of the main data structures:
+ *
+ * inotify_device: Lifetime is managed by reference count, from
+ * sys_inotify_init() until release.  Additional references can bump the count
+ * via get_inotify_dev() and drop the count via put_inotify_dev().
+ *
+ * inotify_user_watch: Lifetime is from create_watch() to the receipt of an
+ * IN_IGNORED event from inotify, or when using IN_ONESHOT, to receipt of the
+ * first event, or to inotify_destroy().
+ */
+
+/*
+ * 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 mutex		ev_mutex;	/* protects event queue */
+	struct mutex		up_mutex;	/* synchronizes watch updates */
+	struct list_head 	events;		/* list of queued events */
+	atomic_t		count;		/* reference count */
+	struct user_struct	*user;		/* user who opened this dev */
+	struct inotify_handle	*ih;		/* inotify handle */
+	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 */
+};
+
+/*
+ * 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->ev_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_user_watch - our version of an inotify_watch, we add
+ * a reference to the associated inotify_device.
+ */
+struct inotify_user_watch {
+	struct inotify_device	*dev;	/* associated device */
+	struct inotify_watch	wdata;	/* inotify watch data */
+};
+
+#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,
+		.procname	= "max_queued_events",
+		.data		= &inotify_max_queued_events,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero
+	},
+	{ .ctl_name = 0 }
+};
+#endif /* CONFIG_SYSCTL */
+
+static inline void get_inotify_dev(struct inotify_device *dev)
+{
+	atomic_inc(&dev->count);
+}
+
+static inline void put_inotify_dev(struct inotify_device *dev)
+{
+	if (atomic_dec_and_test(&dev->count)) {
+		atomic_dec(&dev->user->inotify_devs);
+		free_uid(dev->user);
+		kfree(dev);
+	}
+}
+
+/*
+ * free_inotify_user_watch - cleans up the watch and its references
+ */
+static void free_inotify_user_watch(struct inotify_watch *w)
+{
+	struct inotify_user_watch *watch;
+	struct inotify_device *dev;
+
+	watch = container_of(w, struct inotify_user_watch, wdata);
+	dev = watch->dev;
+
+	atomic_dec(&dev->user->inotify_watches);
+	put_inotify_dev(dev);
+	kmem_cache_free(watch_cachep, watch);
+}
+
+/*
+ * kernel_event - create a new kernel event with the given parameters
+ *
+ * This function can sleep.
+ */
+static struct inotify_kernel_event * kernel_event(s32 wd, u32 mask, u32 cookie,
+						  const char *name)
+{
+	struct inotify_kernel_event *kevent;
+
+	kevent = kmem_cache_alloc(event_cachep, GFP_KERNEL);
+	if (unlikely(!kevent))
+		return NULL;
+
+	/* we hand this out to user-space, so zero it just in case */
+	memset(&kevent->event, 0, sizeof(struct inotify_event));
+
+	kevent->event.wd = wd;
+	kevent->event.mask = mask;
+	kevent->event.cookie = cookie;
+
+	INIT_LIST_HEAD(&kevent->list);
+
+	if (name) {
+		size_t len, rem, event_size = sizeof(struct inotify_event);
+
+		/*
+		 * We need to pad the filename so as to properly align an
+		 * array of inotify_event structures.  Because the structure is
+		 * small and the common case is a small filename, we just round
+		 * up to the next multiple of the structure's sizeof.  This is
+		 * simple and safe for all architectures.
+		 */
+		len = strlen(name) + 1;
+		rem = event_size - len;
+		if (len > event_size) {
+			rem = event_size - (len % event_size);
+			if (len % event_size == 0)
+				rem = 0;
+		}
+
+		kevent->name = kmalloc(len + rem, GFP_KERNEL);
+		if (unlikely(!kevent->name)) {
+			kmem_cache_free(event_cachep, kevent);
+			return NULL;
+		}
+		memcpy(kevent->name, name, len);
+		if (rem)
+			memset(kevent->name + len, 0, rem);
+		kevent->event.len = len + rem;
+	} else {
+		kevent->event.len = 0;
+		kevent->name = NULL;
+	}
+
+	return kevent;
+}
+
+/*
+ * inotify_dev_get_event - return the next event in the given dev's queue
+ *
+ * Caller must hold dev->ev_mutex.
+ */
+static inline struct inotify_kernel_event *
+inotify_dev_get_event(struct inotify_device *dev)
+{
+	return list_entry(dev->events.next, struct inotify_kernel_event, list);
+}
+
+/*
+ * inotify_dev_queue_event - event handler registered with core inotify, adds
+ * a new event to the given device
+ *
+ * Can sleep (calls kernel_event()).
+ */
+static void inotify_dev_queue_event(struct inotify_watch *w, u32 wd, u32 mask,
+				    u32 cookie, const char *name)
+{
+	struct inotify_user_watch *watch;
+	struct inotify_device *dev;
+	struct inotify_kernel_event *kevent, *last;
+
+	watch = container_of(w, struct inotify_user_watch, wdata);
+	dev = watch->dev;
+
+	mutex_lock(&dev->ev_mutex);
+
+	/* we can safely put the watch as we don't reference it while
+	 * generating the event
+	 */
+	if (mask & IN_IGNORED || mask & IN_ONESHOT)
+		put_inotify_watch(w); /* final put */
+
+	/* coalescing: drop this event if it is a dupe of the previous */
+	last = inotify_dev_get_event(dev);
+	if (last && last->event.mask == mask && last->event.wd == wd &&
+			last->event.cookie == cookie) {
+		const char *lastname = last->name;
+
+		if (!name && !lastname)
+			goto out;
+		if (name && lastname && !strcmp(lastname, name))
+			goto out;
+	}
+
+	/* the queue overflowed and we already sent the Q_OVERFLOW event */
+	if (unlikely(dev->event_count > dev->max_events))
+		goto out;
+
+	/* if the queue overflows, we need to notify user space */
+	if (unlikely(dev->event_count == dev->max_events))
+		kevent = kernel_event(-1, IN_Q_OVERFLOW, cookie, NULL);
+	else
+		kevent = kernel_event(wd, mask, cookie, name);
+
+	if (unlikely(!kevent))
+		goto out;
+
+	/* queue the event and wake up anyone waiting */
+	dev->event_count++;
+	dev->queue_size += sizeof(struct inotify_event) + kevent->event.len;
+	list_add_tail(&kevent->list, &dev->events);
+	wake_up_interruptible(&dev->wq);
+
+out:
+	mutex_unlock(&dev->ev_mutex);
+}
+
+/*
+ * remove_kevent - cleans up and ultimately frees the given kevent
+ *
+ * Caller must hold dev->ev_mutex.
+ */
+static void remove_kevent(struct inotify_device *dev,
+			  struct inotify_kernel_event *kevent)
+{
+	list_del(&kevent->list);
+
+	dev->event_count--;
+	dev->queue_size -= sizeof(struct inotify_event) + kevent->event.len;
+
+	kfree(kevent->name);
+	kmem_cache_free(event_cachep, kevent);
+}
+
+/*
+ * inotify_dev_event_dequeue - destroy an event on the given device
+ *
+ * Caller must hold dev->ev_mutex.
+ */
+static void inotify_dev_event_dequeue(struct inotify_device *dev)
+{
+	if (!list_empty(&dev->events)) {
+		struct inotify_kernel_event *kevent;
+		kevent = inotify_dev_get_event(dev);
+		remove_kevent(dev, kevent);
+	}
+}
+
+/*
+ * find_inode - resolve a user-given path to a specific inode and return a nd
+ */
+static int find_inode(const char __user *dirname, struct nameidata *nd,
+		      unsigned flags)
+{
+	int error;
+
+	error = __user_walk(dirname, flags, nd);
+	if (error)
+		return error;
+	/* you can only watch an inode if you have read permissions on it */
+	error = vfs_permission(nd, MAY_READ);
+	if (error)
+		path_release(nd);
+	return error;
+}
+
+/*
+ * create_watch - creates a watch on the given device.
+ *
+ * Callers must hold dev->up_mutex.
+ */
+static int create_watch(struct inotify_device *dev, struct inode *inode,
+			u32 mask)
+{
+	struct inotify_user_watch *watch;
+	int ret;
+
+	if (atomic_read(&dev->user->inotify_watches) >=
+			inotify_max_user_watches)
+		return -ENOSPC;
+
+	watch = kmem_cache_alloc(watch_cachep, GFP_KERNEL);
+	if (unlikely(!watch))
+		return -ENOMEM;
+
+	/* save a reference to device and bump the count to make it official */
+	get_inotify_dev(dev);
+	watch->dev = dev;
+
+	atomic_inc(&dev->user->inotify_watches);
+
+	ret = inotify_add_watch(dev->ih, &watch->wdata, inode, mask);
+	if (ret < 0)
+		free_inotify_user_watch(&watch->wdata);
+
+	return ret;
+}
+
+/* Device Interface */
+
+static unsigned int inotify_poll(struct file *file, poll_table *wait)
+{
+	struct inotify_device *dev = file->private_data;
+	int ret = 0;
+
+	poll_wait(file, &dev->wq, wait);
+	mutex_lock(&dev->ev_mutex);
+	if (!list_empty(&dev->events))
+		ret = POLLIN | POLLRDNORM;
+	mutex_unlock(&dev->ev_mutex);
+
+	return ret;
+}
+
+static ssize_t inotify_read(struct file *file, char __user *buf,
+			    size_t count, loff_t *pos)
+{
+	size_t event_size = sizeof (struct inotify_event);
+	struct inotify_device *dev;
+	char __user *start;
+	int ret;
+	DEFINE_WAIT(wait);
+
+	start = buf;
+	dev = file->private_data;
+
+	while (1) {
+		int events;
+
+		prepare_to_wait(&dev->wq, &wait, TASK_INTERRUPTIBLE);
+
+		mutex_lock(&dev->ev_mutex);
+		events = !list_empty(&dev->events);
+		mutex_unlock(&dev->ev_mutex);
+		if (events) {
+			ret = 0;
+			break;
+		}
+
+		if (file->f_flags & O_NONBLOCK) {
+			ret = -EAGAIN;
+			break;
+		}
+
+		if (signal_pending(current)) {
+			ret = -EINTR;
+			break;
+		}
+
+		schedule();
+	}
+
+	finish_wait(&dev->wq, &wait);
+	if (ret)
+		return ret;
+
+	mutex_lock(&dev->ev_mutex);
+	while (1) {
+		struct inotify_kernel_event *kevent;
+
+		ret = buf - start;
+		if (list_empty(&dev->events))
+			break;
+
+		kevent = inotify_dev_get_event(dev);
+		if (event_size + kevent->event.len > count)
+			break;
+
+		if (copy_to_user(buf, &kevent->event, event_size)) {
+			ret = -EFAULT;
+			break;
+		}
+		buf += event_size;
+		count -= event_size;
+
+		if (kevent->name) {
+			if (copy_to_user(buf, kevent->name, kevent->event.len)){
+				ret = -EFAULT;
+				break;
+			}
+			buf += kevent->event.len;
+			count -= kevent->event.len;
+		}
+
+		remove_kevent(dev, kevent);
+	}
+	mutex_unlock(&dev->ev_mutex);
+
+	return ret;
+}
+
+static int inotify_release(struct inode *ignored, struct file *file)
+{
+	struct inotify_device *dev = file->private_data;
+
+	inotify_destroy(dev->ih);
+
+	/* destroy all of the events on this device */
+	mutex_lock(&dev->ev_mutex);
+	while (!list_empty(&dev->events))
+		inotify_dev_event_dequeue(dev);
+	mutex_unlock(&dev->ev_mutex);
+
+	/* free this device: the put matching the get in inotify_init() */
+	put_inotify_dev(dev);
+
+	return 0;
+}
+
+static long inotify_ioctl(struct file *file, unsigned int cmd,
+			  unsigned long arg)
+{
+	struct inotify_device *dev;
+	void __user *p;
+	int ret = -ENOTTY;
+
+	dev = file->private_data;
+	p = (void __user *) arg;
+
+	switch (cmd) {
+	case FIONREAD:
+		ret = put_user(dev->queue_size, (int __user *) p);
+		break;
+	}
+
+	return ret;
+}
+
+static const struct file_operations inotify_fops = {
+	.poll           = inotify_poll,
+	.read           = inotify_read,
+	.release        = inotify_release,
+	.unlocked_ioctl = inotify_ioctl,
+	.compat_ioctl	= inotify_ioctl,
+};
+
+static const struct inotify_operations inotify_user_ops = {
+	.handle_event	= inotify_dev_queue_event,
+	.destroy_watch	= free_inotify_user_watch,
+};
+
+asmlinkage long sys_inotify_init(void)
+{
+	struct inotify_device *dev;
+	struct inotify_handle *ih;
+	struct user_struct *user;
+	struct file *filp;
+	int fd, ret;
+
+	fd = get_unused_fd();
+	if (fd < 0)
+		return fd;
+
+	filp = get_empty_filp();
+	if (!filp) {
+		ret = -ENFILE;
+		goto out_put_fd;
+	}
+
+	user = get_uid(current->user);
+	if (unlikely(atomic_read(&user->inotify_devs) >=
+			inotify_max_user_instances)) {
+		ret = -EMFILE;
+		goto out_free_uid;
+	}
+
+	dev = kmalloc(sizeof(struct inotify_device), GFP_KERNEL);
+	if (unlikely(!dev)) {
+		ret = -ENOMEM;
+		goto out_free_uid;
+	}
+
+	ih = inotify_init(&inotify_user_ops);
+	if (unlikely(IS_ERR(ih))) {
+		ret = PTR_ERR(ih);
+		goto out_free_dev;
+	}
+	dev->ih = ih;
+
+	filp->f_op = &inotify_fops;
+	filp->f_vfsmnt = mntget(inotify_mnt);
+	filp->f_dentry = dget(inotify_mnt->mnt_root);
+	filp->f_mapping = filp->f_dentry->d_inode->i_mapping;
+	filp->f_mode = FMODE_READ;
+	filp->f_flags = O_RDONLY;
+	filp->private_data = dev;
+
+	INIT_LIST_HEAD(&dev->events);
+	init_waitqueue_head(&dev->wq);
+	mutex_init(&dev->ev_mutex);
+	mutex_init(&dev->up_mutex);
+	dev->event_count = 0;
+	dev->queue_size = 0;
+	dev->max_events = inotify_max_queued_events;
+	dev->user = user;
+	atomic_set(&dev->count, 0);
+
+	get_inotify_dev(dev);
+	atomic_inc(&user->inotify_devs);
+	fd_install(fd, filp);
+
+	return fd;
+out_free_dev:
+	kfree(dev);
+out_free_uid:
+	free_uid(user);
+	put_filp(filp);
+out_put_fd:
+	put_unused_fd(fd);
+	return ret;
+}
+
+asmlinkage long sys_inotify_add_watch(int fd, const char __user *path, u32 mask)
+{
+	struct inode *inode;
+	struct inotify_device *dev;
+	struct nameidata nd;
+	struct file *filp;
+	int ret, fput_needed;
+	unsigned flags = 0;
+
+	filp = fget_light(fd, &fput_needed);
+	if (unlikely(!filp))
+		return -EBADF;
+
+	/* verify that this is indeed an inotify instance */
+	if (unlikely(filp->f_op != &inotify_fops)) {
+		ret = -EINVAL;
+		goto fput_and_out;
+	}
+
+	if (!(mask & IN_DONT_FOLLOW))
+		flags |= LOOKUP_FOLLOW;
+	if (mask & IN_ONLYDIR)
+		flags |= LOOKUP_DIRECTORY;
+
+	ret = find_inode(path, &nd, flags);
+	if (unlikely(ret))
+		goto fput_and_out;
+
+	/* inode held in place by reference to nd; dev by fget on fd */
+	inode = nd.dentry->d_inode;
+	dev = filp->private_data;
+
+	mutex_lock(&dev->up_mutex);
+	ret = inotify_find_update_watch(dev->ih, inode, mask);
+	if (ret == -ENOENT)
+		ret = create_watch(dev, inode, mask);
+	mutex_unlock(&dev->up_mutex);
+
+	path_release(&nd);
+fput_and_out:
+	fput_light(filp, fput_needed);
+	return ret;
+}
+
+asmlinkage long sys_inotify_rm_watch(int fd, u32 wd)
+{
+	struct file *filp;
+	struct inotify_device *dev;
+	int ret, fput_needed;
+
+	filp = fget_light(fd, &fput_needed);
+	if (unlikely(!filp))
+		return -EBADF;
+
+	/* verify that this is indeed an inotify instance */
+	if (unlikely(filp->f_op != &inotify_fops)) {
+		ret = -EINVAL;
+		goto out;
+	}
+
+	dev = filp->private_data;
+
+	/* we free our watch data when we get IN_IGNORED */
+	ret = inotify_rm_wd(dev->ih, wd);
+
+out:
+	fput_light(filp, fput_needed);
+	return ret;
+}
+
+static struct super_block *
+inotify_get_sb(struct file_system_type *fs_type, int flags,
+	       const char *dev_name, void *data)
+{
+    return get_sb_pseudo(fs_type, "inotify", NULL, 0xBAD1DEA);
+}
+
+static struct file_system_type inotify_fs_type = {
+    .name           = "inotifyfs",
+    .get_sb         = inotify_get_sb,
+    .kill_sb        = kill_anon_super,
+};
+
+/*
+ * inotify_user_setup - Our initialization function.  Note that we cannnot return
+ * error because we have compiled-in VFS hooks.  So an (unlikely) failure here
+ * must result in panic().
+ */
+static int __init inotify_user_setup(void)
+{
+	int ret;
+
+	ret = register_filesystem(&inotify_fs_type);
+	if (unlikely(ret))
+		panic("inotify: register_filesystem returned %d!\n", ret);
+
+	inotify_mnt = kern_mount(&inotify_fs_type);
+	if (IS_ERR(inotify_mnt))
+		panic("inotify: kern_mount ret %ld!\n", PTR_ERR(inotify_mnt));
+
+	inotify_max_queued_events = 16384;
+	inotify_max_user_instances = 128;
+	inotify_max_user_watches = 8192;
+
+	watch_cachep = kmem_cache_create("inotify_watch_cache",
+					 sizeof(struct inotify_user_watch),
+					 0, SLAB_PANIC, NULL, NULL);
+	event_cachep = kmem_cache_create("inotify_event_cache",
+					 sizeof(struct inotify_kernel_event),
+					 0, SLAB_PANIC, NULL, NULL);
+
+	return 0;
+}
+
+module_init(inotify_user_setup);

include/linux/inotify.h

@@ -68,8 +68,37 @@ struct inotify_event {
 #include <linux/dcache.h>
 #include <linux/fs.h>
 
+/*
+ * struct inotify_watch - represents a watch request on a specific inode
+ *
+ * h_list is protected by ih->mutex of the associated inotify_handle.
+ * i_list, mask are protected by inode->inotify_mutex of the associated inode.
+ * ih, inode, and wd are never written to once the watch is created.
+ *
+ * Callers must use the established inotify interfaces to access inotify_watch
+ * contents.  The content of this structure is private to the inotify
+ * implementation.
+ */
+struct inotify_watch {
+	struct list_head	h_list;	/* entry in inotify_handle's list */
+	struct list_head	i_list;	/* entry in inode's list */
+	atomic_t		count;	/* reference count */
+	struct inotify_handle	*ih;	/* associated inotify handle */
+	struct inode		*inode;	/* associated inode */
+	__s32			wd;	/* watch descriptor */
+	__u32			mask;	/* event mask for this watch */
+};
+
+struct inotify_operations {
+	void (*handle_event)(struct inotify_watch *, u32, u32, u32,
+			     const char *);
+	void (*destroy_watch)(struct inotify_watch *);
+};
+
 #ifdef CONFIG_INOTIFY
 
+/* Kernel API for producing events */
+
 extern void inotify_d_instantiate(struct dentry *, struct inode *);
 extern void inotify_d_move(struct dentry *);
 extern void inotify_inode_queue_event(struct inode *, __u32, __u32,
@@ -80,6 +109,18 @@ extern void inotify_unmount_inodes(struct list_head *);
 extern void inotify_inode_is_dead(struct inode *);
 extern u32 inotify_get_cookie(void);
 
+/* Kernel Consumer API */
+
+extern struct inotify_handle *inotify_init(const struct inotify_operations *);
+extern void inotify_destroy(struct inotify_handle *);
+extern __s32 inotify_find_update_watch(struct inotify_handle *, struct inode *,
+				       u32);
+extern __s32 inotify_add_watch(struct inotify_handle *, struct inotify_watch *,
+			       struct inode *, __u32);
+extern int inotify_rm_wd(struct inotify_handle *, __u32);
+extern void get_inotify_watch(struct inotify_watch *);
+extern void put_inotify_watch(struct inotify_watch *);
+
 #else
 
 static inline void inotify_d_instantiate(struct dentry *dentry,
@@ -116,6 +157,41 @@ static inline u32 inotify_get_cookie(void)
 	return 0;
 }
 
+static inline struct inotify_handle *inotify_init(const struct inotify_operations *ops)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+
+static inline void inotify_destroy(struct inotify_handle *ih)
+{
+}
+
+static inline __s32 inotify_find_update_watch(struct inotify_handle *ih,
+					      struct inode *inode, u32 mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline __s32 inotify_add_watch(struct inotify_handle *ih,
+				      struct inotify_watch *watch,
+				      struct inode *inode, __u32 mask)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline int inotify_rm_wd(struct inotify_handle *ih, __u32 wd)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void get_inotify_watch(struct inotify_watch *watch)
+{
+}
+
+static inline void put_inotify_watch(struct inotify_watch *watch)
+{
+}
+
 #endif	/* CONFIG_INOTIFY */
 
 #endif	/* __KERNEL __ */

include/linux/sched.h

@@ -494,7 +494,7 @@ struct user_struct {
 	atomic_t processes;	/* How many processes does this user have? */
 	atomic_t files;		/* How many open files does this user have? */
 	atomic_t sigpending;	/* How many pending signals does this user have? */
-#ifdef CONFIG_INOTIFY
+#ifdef CONFIG_INOTIFY_USER
 	atomic_t inotify_watches; /* How many inotify watches does this user have? */
 	atomic_t inotify_devs;	/* How many inotify devs does this user have opened? */
 #endif

kernel/sysctl.c

@@ -150,7 +150,7 @@ extern ctl_table random_table[];
 #ifdef CONFIG_UNIX98_PTYS
 extern ctl_table pty_table[];
 #endif
-#ifdef CONFIG_INOTIFY
+#ifdef CONFIG_INOTIFY_USER
 extern ctl_table inotify_table[];
 #endif
 
@@ -1028,7 +1028,7 @@ static ctl_table fs_table[] = {
 		.mode		= 0644,
 		.proc_handler	= &proc_doulongvec_minmax,
 	},
-#ifdef CONFIG_INOTIFY
+#ifdef CONFIG_INOTIFY_USER
 	{
 		.ctl_name	= FS_INOTIFY,
 		.procname	= "inotify",

kernel/user.c

@@ -140,7 +140,7 @@ struct user_struct * alloc_uid(uid_t uid)
 		atomic_set(&new->processes, 0);
 		atomic_set(&new->files, 0);
 		atomic_set(&new->sigpending, 0);
-#ifdef CONFIG_INOTIFY
+#ifdef CONFIG_INOTIFY_USER
 		atomic_set(&new->inotify_watches, 0);
 		atomic_set(&new->inotify_devs, 0);
 #endif